* [net-next v2 2/4] openvswitch: export get_dp() API.
From: Andy Zhou @ 2017-10-17 7:36 UTC (permalink / raw)
To: netdev; +Cc: pshelar, joe, gvrose8192, Andy Zhou
In-Reply-To: <1508225805-11613-1-git-send-email-azhou@ovn.org>
Later patches will invoke get_dp() outside of datapath.c. Export it.
Signed-off-by: Andy Zhou <azhou@ovn.org>
---
net/openvswitch/datapath.c | 29 -----------------------------
net/openvswitch/datapath.h | 31 +++++++++++++++++++++++++++++++
2 files changed, 31 insertions(+), 29 deletions(-)
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index c3aec6227c91..ac7154018676 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -142,35 +142,6 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *,
const struct dp_upcall_info *,
uint32_t cutlen);
-/* Must be called with rcu_read_lock. */
-static struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
-{
- struct net_device *dev = dev_get_by_index_rcu(net, dp_ifindex);
-
- if (dev) {
- struct vport *vport = ovs_internal_dev_get_vport(dev);
- if (vport)
- return vport->dp;
- }
-
- return NULL;
-}
-
-/* The caller must hold either ovs_mutex or rcu_read_lock to keep the
- * returned dp pointer valid.
- */
-static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
-{
- struct datapath *dp;
-
- WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held());
- rcu_read_lock();
- dp = get_dp_rcu(net, dp_ifindex);
- rcu_read_unlock();
-
- return dp;
-}
-
/* Must be called with rcu_read_lock or ovs_mutex. */
const char *ovs_dp_name(const struct datapath *dp)
{
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 480600649d0b..ad14b571219d 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -30,6 +30,7 @@
#include "conntrack.h"
#include "flow.h"
#include "flow_table.h"
+#include "vport-internal_dev.h"
#define DP_MAX_PORTS USHRT_MAX
#define DP_VPORT_HASH_BUCKETS 1024
@@ -190,6 +191,36 @@ static inline struct vport *ovs_vport_ovsl(const struct datapath *dp, int port_n
return ovs_lookup_vport(dp, port_no);
}
+/* Must be called with rcu_read_lock. */
+static inline struct datapath *get_dp_rcu(struct net *net, int dp_ifindex)
+{
+ struct net_device *dev = dev_get_by_index_rcu(net, dp_ifindex);
+
+ if (dev) {
+ struct vport *vport = ovs_internal_dev_get_vport(dev);
+
+ if (vport)
+ return vport->dp;
+ }
+
+ return NULL;
+}
+
+/* The caller must hold either ovs_mutex or rcu_read_lock to keep the
+ * returned dp pointer valid.
+ */
+static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
+{
+ struct datapath *dp;
+
+ WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_ovsl_is_held());
+ rcu_read_lock();
+ dp = get_dp_rcu(net, dp_ifindex);
+ rcu_read_unlock();
+
+ return dp;
+}
+
extern struct notifier_block ovs_dp_device_notifier;
extern struct genl_family dp_vport_genl_family;
--
1.8.3.1
^ permalink raw reply related
* [net-next v2 1/4] openvswitch: Add meter netlink definitions
From: Andy Zhou @ 2017-10-17 7:36 UTC (permalink / raw)
To: netdev; +Cc: pshelar, joe, gvrose8192, Andy Zhou
In-Reply-To: <1508225805-11613-1-git-send-email-azhou@ovn.org>
Meter has its own netlink family. Define netlink messages and attributes
for communicating with the user space programs.
Signed-off-by: Andy Zhou <azhou@ovn.org>
---
include/uapi/linux/openvswitch.h | 51 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 51 insertions(+)
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 0cd6f8833147..d413a2398214 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -851,4 +851,55 @@ enum ovs_action_attr {
#define OVS_ACTION_ATTR_MAX (__OVS_ACTION_ATTR_MAX - 1)
+/* Meters. */
+#define OVS_METER_FAMILY "ovs_meter"
+#define OVS_METER_MCGROUP "ovs_meter"
+#define OVS_METER_VERSION 0x1
+
+enum ovs_meter_cmd {
+ OVS_METER_CMD_UNSPEC,
+ OVS_METER_CMD_FEATURES, /* Get features supported by the datapath. */
+ OVS_METER_CMD_SET, /* Add or modify a meter. */
+ OVS_METER_CMD_DEL, /* Delete a meter. */
+ OVS_METER_CMD_GET /* Get meter stats. */
+};
+
+enum ovs_meter_attr {
+ OVS_METER_ATTR_UNSPEC,
+ OVS_METER_ATTR_ID, /* u32 meter ID within datapath. */
+ OVS_METER_ATTR_KBPS, /* No argument. If set, units in kilobits
+ * per second. Otherwise, units in
+ * packets per second.
+ */
+ OVS_METER_ATTR_STATS, /* struct ovs_flow_stats for the meter. */
+ OVS_METER_ATTR_BANDS, /* Nested attributes for meter bands. */
+ OVS_METER_ATTR_USED, /* u64 msecs last used in monotonic time. */
+ OVS_METER_ATTR_CLEAR, /* Flag to clear stats, used. */
+ OVS_METER_ATTR_MAX_METERS, /* u32 number of meters supported. */
+ OVS_METER_ATTR_MAX_BANDS, /* u32 max number of bands per meter. */
+ OVS_METER_ATTR_PAD,
+ __OVS_METER_ATTR_MAX
+};
+
+#define OVS_METER_ATTR_MAX (__OVS_METER_ATTR_MAX - 1)
+
+enum ovs_band_attr {
+ OVS_BAND_ATTR_UNSPEC,
+ OVS_BAND_ATTR_TYPE, /* u32 OVS_METER_BAND_TYPE_* constant. */
+ OVS_BAND_ATTR_RATE, /* u32 band rate in meter units (see above). */
+ OVS_BAND_ATTR_BURST, /* u32 burst size in meter units. */
+ OVS_BAND_ATTR_STATS, /* struct ovs_flow_stats for the band. */
+ __OVS_BAND_ATTR_MAX
+};
+
+#define OVS_BAND_ATTR_MAX (__OVS_BAND_ATTR_MAX - 1)
+
+enum ovs_meter_band_type {
+ OVS_METER_BAND_TYPE_UNSPEC,
+ OVS_METER_BAND_TYPE_DROP, /* Drop exceeding packets. */
+ __OVS_METER_BAND_TYPE_MAX
+};
+
+#define OVS_METER_BAND_TYPE_MAX (__OVS_METER_BAND_TYPE_MAX - 1)
+
#endif /* _LINUX_OPENVSWITCH_H */
--
1.8.3.1
^ permalink raw reply related
* [net-next v2 0/4] Openvswitch meter action
From: Andy Zhou @ 2017-10-17 7:36 UTC (permalink / raw)
To: netdev; +Cc: pshelar, joe, gvrose8192, Andy Zhou
This patch series is the first attempt to add openvswitch
meter support. We have previously experimented with adding
metering support in nftables. However 1) It was not clear
how to expose a named nftables object cleanly, and 2)
the logic that implements metering is quite small, < 100 lines
of code.
With those two observations, it seems cleaner to add meter
support in the openvswitch module directly.
---
v1(RFC)->v2: remove unused code
improve locking
and other review comments
Andy Zhou (4):
openvswitch: Add meter netlink definitions
openvswitch: export get_dp() API.
openvswitch: Add meter infrastructure
openvswitch: Add meter action support
include/uapi/linux/openvswitch.h | 54 ++++
net/openvswitch/Makefile | 1 +
net/openvswitch/actions.c | 6 +
net/openvswitch/datapath.c | 43 +--
net/openvswitch/datapath.h | 35 +++
net/openvswitch/flow_netlink.c | 6 +
net/openvswitch/meter.c | 604 +++++++++++++++++++++++++++++++++++++++
net/openvswitch/meter.h | 54 ++++
8 files changed, 772 insertions(+), 31 deletions(-)
create mode 100644 net/openvswitch/meter.c
create mode 100644 net/openvswitch/meter.h
--
1.8.3.1
^ permalink raw reply
* [PATCH net-next 6/6] net: ena: increase ena driver version to 1.3.0
From: netanel @ 2017-10-17 7:34 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
In-Reply-To: <1508225641-106366-1-git-send-email-netanel@amazon.com>
From: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_netdev.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index eafc5774dd49..ed8bd0a579c4 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -44,7 +44,7 @@
#include "ena_eth_com.h"
#define DRV_MODULE_VER_MAJOR 1
-#define DRV_MODULE_VER_MINOR 2
+#define DRV_MODULE_VER_MINOR 3
#define DRV_MODULE_VER_SUBMINOR 0
#define DRV_MODULE_NAME "ena"
@@ -52,7 +52,7 @@
#define DRV_MODULE_VERSION \
__stringify(DRV_MODULE_VER_MAJOR) "." \
__stringify(DRV_MODULE_VER_MINOR) "." \
- __stringify(DRV_MODULE_VER_SUBMINOR) "k"
+ __stringify(DRV_MODULE_VER_SUBMINOR) "K"
#endif
#define DEVICE_NAME "Elastic Network Adapter (ENA)"
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 5/6] net: ena: add new admin define for future support of IPv6 RSS
From: netanel @ 2017-10-17 7:34 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
In-Reply-To: <1508225641-106366-1-git-send-email-netanel@amazon.com>
From: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_admin_defs.h | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
index 305dc1996b4e..4532e574ebcd 100644
--- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
+++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h
@@ -627,6 +627,12 @@ enum ena_admin_flow_hash_proto {
ENA_ADMIN_RSS_NOT_IP = 7,
+ /* TCPv6 with extension header */
+ ENA_ADMIN_RSS_TCP6_EX = 8,
+
+ /* IPv6 with extension header */
+ ENA_ADMIN_RSS_IP6_EX = 9,
+
ENA_ADMIN_RSS_PROTO_NUM = 16,
};
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 4/6] net: ena: add statistics for missed tx packets
From: netanel @ 2017-10-17 7:33 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
In-Reply-To: <1508225641-106366-1-git-send-email-netanel@amazon.com>
From: Netanel Belgazal <netanel@amazon.com>
Add a new statistic to ethtool stats that show the number of packets
without transmit acknowledgement from ENA device.
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_ethtool.c | 1 +
drivers/net/ethernet/amazon/ena/ena_netdev.c | 30 +++++++++++++++------------
drivers/net/ethernet/amazon/ena/ena_netdev.h | 1 +
3 files changed, 19 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 2aa1fd0e15ec..060cb18fa659 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -81,6 +81,7 @@ struct ena_stats {
ENA_STAT_TX_ENTRY(doorbells),
ENA_STAT_TX_ENTRY(prepare_ctx_err),
ENA_STAT_TX_ENTRY(bad_req_id),
+ ENA_STAT_TX_ENTRY(missed_tx),
};
static const struct ena_stats ena_stats_rx_strings[] = {
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 0aa56707d7cc..5417e4da64ca 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2648,7 +2648,7 @@ static int check_missing_comp_in_queue(struct ena_adapter *adapter,
struct ena_tx_buffer *tx_buf;
unsigned long last_jiffies;
u32 missed_tx = 0;
- int i;
+ int i, rc = 0;
for (i = 0; i < tx_ring->ring_size; i++) {
tx_buf = &tx_ring->tx_buffer_info[i];
@@ -2662,21 +2662,25 @@ static int check_missing_comp_in_queue(struct ena_adapter *adapter,
tx_buf->print_once = 1;
missed_tx++;
-
- if (unlikely(missed_tx > adapter->missing_tx_completion_threshold)) {
- netif_err(adapter, tx_err, adapter->netdev,
- "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n",
- missed_tx,
- adapter->missing_tx_completion_threshold);
- adapter->reset_reason =
- ENA_REGS_RESET_MISS_TX_CMPL;
- set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
- return -EIO;
- }
}
}
- return 0;
+ if (unlikely(missed_tx > adapter->missing_tx_completion_threshold)) {
+ netif_err(adapter, tx_err, adapter->netdev,
+ "The number of lost tx completions is above the threshold (%d > %d). Reset the device\n",
+ missed_tx,
+ adapter->missing_tx_completion_threshold);
+ adapter->reset_reason =
+ ENA_REGS_RESET_MISS_TX_CMPL;
+ set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+ rc = -EIO;
+ }
+
+ u64_stats_update_begin(&tx_ring->syncp);
+ tx_ring->tx_stats.missed_tx = missed_tx;
+ u64_stats_update_end(&tx_ring->syncp);
+
+ return rc;
}
static void check_for_missing_tx_completions(struct ena_adapter *adapter)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 7b07bfbf0fe4..eafc5774dd49 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -185,6 +185,7 @@ struct ena_stats_tx {
u64 tx_poll;
u64 doorbells;
u64 bad_req_id;
+ u64 missed_tx;
};
struct ena_stats_rx {
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 3/6] net: ena: add power management ops to the ENA driver
From: netanel @ 2017-10-17 7:33 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
In-Reply-To: <1508225641-106366-1-git-send-email-netanel@amazon.com>
From: Netanel Belgazal <netanel@amazon.com>
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_ethtool.c | 2 +
drivers/net/ethernet/amazon/ena/ena_netdev.c | 117 ++++++++++++++++++++------
drivers/net/ethernet/amazon/ena/ena_netdev.h | 3 +
3 files changed, 95 insertions(+), 27 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 1cd8eb8e5a15..2aa1fd0e15ec 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -60,6 +60,8 @@ struct ena_stats {
static const struct ena_stats ena_stats_global_strings[] = {
ENA_STAT_GLOBAL_ENTRY(tx_timeout),
+ ENA_STAT_GLOBAL_ENTRY(suspend),
+ ENA_STAT_GLOBAL_ENTRY(resume),
ENA_STAT_GLOBAL_ENTRY(wd_expired),
ENA_STAT_GLOBAL_ENTRY(interface_up),
ENA_STAT_GLOBAL_ENTRY(interface_down),
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index dbeff3064c0d..0aa56707d7cc 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2529,38 +2529,31 @@ static int ena_enable_msix_and_set_admin_interrupts(struct ena_adapter *adapter,
return rc;
}
-static void ena_fw_reset_device(struct work_struct *work)
+static void ena_destroy_device(struct ena_adapter *adapter)
{
- struct ena_com_dev_get_features_ctx get_feat_ctx;
- struct ena_adapter *adapter =
- container_of(work, struct ena_adapter, reset_task);
struct net_device *netdev = adapter->netdev;
struct ena_com_dev *ena_dev = adapter->ena_dev;
- struct pci_dev *pdev = adapter->pdev;
- bool dev_up, wd_state;
- int rc;
-
- if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
- dev_err(&pdev->dev,
- "device reset schedule while reset bit is off\n");
- return;
- }
+ bool dev_up;
netif_carrier_off(netdev);
del_timer_sync(&adapter->timer_service);
- rtnl_lock();
-
dev_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags);
+ adapter->dev_up_before_reset = dev_up;
+
ena_com_set_admin_running_state(ena_dev, false);
- /* After calling ena_close the tx queues and the napi
- * are disabled so no one can interfere or touch the
- * data structures
- */
ena_close(netdev);
+ /* Before releasing the ENA resources, a device reset is required.
+ * (to prevent the device from accessing them).
+ * In case the reset flag is set and the device is up, ena_close
+ * already perform the reset, so it can be skipped.
+ */
+ if (!(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags) && dev_up))
+ ena_com_dev_reset(adapter->ena_dev, adapter->reset_reason);
+
ena_free_mgmnt_irq(adapter);
ena_disable_msix(adapter);
@@ -2574,9 +2567,17 @@ static void ena_fw_reset_device(struct work_struct *work)
ena_com_mmio_reg_read_request_destroy(ena_dev);
adapter->reset_reason = ENA_REGS_RESET_NORMAL;
+
clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+}
- /* Finish with the destroy part. Start the init part */
+static int ena_restore_device(struct ena_adapter *adapter)
+{
+ struct ena_com_dev_get_features_ctx get_feat_ctx;
+ struct ena_com_dev *ena_dev = adapter->ena_dev;
+ struct pci_dev *pdev = adapter->pdev;
+ bool wd_state;
+ int rc;
rc = ena_device_init(ena_dev, adapter->pdev, &get_feat_ctx, &wd_state);
if (rc) {
@@ -2598,7 +2599,7 @@ static void ena_fw_reset_device(struct work_struct *work)
goto err_device_destroy;
}
/* If the interface was up before the reset bring it up */
- if (dev_up) {
+ if (adapter->dev_up_before_reset) {
rc = ena_up(adapter);
if (rc) {
dev_err(&pdev->dev, "Failed to create I/O queues\n");
@@ -2607,24 +2608,38 @@ static void ena_fw_reset_device(struct work_struct *work)
}
mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
-
- rtnl_unlock();
-
dev_err(&pdev->dev, "Device reset completed successfully\n");
- return;
+ return rc;
err_disable_msix:
ena_free_mgmnt_irq(adapter);
ena_disable_msix(adapter);
err_device_destroy:
ena_com_admin_destroy(ena_dev);
err:
- rtnl_unlock();
-
clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags);
dev_err(&pdev->dev,
"Reset attempt failed. Can not reset the device\n");
+
+ return rc;
+}
+
+static void ena_fw_reset_device(struct work_struct *work)
+{
+ struct ena_adapter *adapter =
+ container_of(work, struct ena_adapter, reset_task);
+ struct pci_dev *pdev = adapter->pdev;
+
+ if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
+ dev_err(&pdev->dev,
+ "device reset schedule while reset bit is off\n");
+ return;
+ }
+ rtnl_lock();
+ ena_destroy_device(adapter);
+ ena_restore_device(adapter);
+ rtnl_unlock();
}
static int check_missing_comp_in_queue(struct ena_adapter *adapter,
@@ -3379,11 +3394,59 @@ static void ena_remove(struct pci_dev *pdev)
vfree(ena_dev);
}
+#ifdef CONFIG_PM
+/* ena_suspend - PM suspend callback
+ * @pdev: PCI device information struct
+ * @state:power state
+ */
+static int ena_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+ struct ena_adapter *adapter = pci_get_drvdata(pdev);
+
+ u64_stats_update_begin(&adapter->syncp);
+ adapter->dev_stats.suspend++;
+ u64_stats_update_end(&adapter->syncp);
+
+ rtnl_lock();
+ if (unlikely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) {
+ dev_err(&pdev->dev,
+ "ignoring device reset request as the device is being suspended\n");
+ clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags);
+ }
+ ena_destroy_device(adapter);
+ rtnl_unlock();
+ return 0;
+}
+
+/* ena_resume - PM resume callback
+ * @pdev: PCI device information struct
+ *
+ */
+static int ena_resume(struct pci_dev *pdev)
+{
+ struct ena_adapter *adapter = pci_get_drvdata(pdev);
+ int rc;
+
+ u64_stats_update_begin(&adapter->syncp);
+ adapter->dev_stats.resume++;
+ u64_stats_update_end(&adapter->syncp);
+
+ rtnl_lock();
+ rc = ena_restore_device(adapter);
+ rtnl_unlock();
+ return rc;
+}
+#endif
+
static struct pci_driver ena_pci_driver = {
.name = DRV_MODULE_NAME,
.id_table = ena_pci_tbl,
.probe = ena_probe,
.remove = ena_remove,
+#ifdef CONFIG_PM
+ .suspend = ena_suspend,
+ .resume = ena_resume,
+#endif
.sriov_configure = ena_sriov_configure,
};
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index fb0c98bb9290..7b07bfbf0fe4 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -257,6 +257,8 @@ struct ena_ring {
struct ena_stats_dev {
u64 tx_timeout;
+ u64 suspend;
+ u64 resume;
u64 wd_expired;
u64 interface_up;
u64 interface_down;
@@ -327,6 +329,7 @@ struct ena_adapter {
struct timer_list timer_service;
bool wd_state;
+ bool dev_up_before_reset;
unsigned long last_keep_alive_jiffies;
struct u64_stats_sync syncp;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 2/6] net: ena: remove legacy suspend suspend/resume support
From: netanel @ 2017-10-17 7:33 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
In-Reply-To: <1508225641-106366-1-git-send-email-netanel@amazon.com>
From: Netanel Belgazal <netanel@amazon.com>
Remove ena_device_io_suspend/resume() methods
Those methods were intend to be used by the device to trigger
suspend/resume but eventually it was dropped.
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_ethtool.c | 2 --
drivers/net/ethernet/amazon/ena/ena_netdev.c | 50 ---------------------------
drivers/net/ethernet/amazon/ena/ena_netdev.h | 4 ---
3 files changed, 56 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index 967020fb26ee..1cd8eb8e5a15 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -60,8 +60,6 @@ struct ena_stats {
static const struct ena_stats ena_stats_global_strings[] = {
ENA_STAT_GLOBAL_ENTRY(tx_timeout),
- ENA_STAT_GLOBAL_ENTRY(io_suspend),
- ENA_STAT_GLOBAL_ENTRY(io_resume),
ENA_STAT_GLOBAL_ENTRY(wd_expired),
ENA_STAT_GLOBAL_ENTRY(interface_up),
ENA_STAT_GLOBAL_ENTRY(interface_down),
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index c6bd5e24005d..dbeff3064c0d 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2361,38 +2361,6 @@ static void ena_get_stats64(struct net_device *netdev,
#endif /* CONFIG_NET_POLL_CONTROLLER */
};
-static void ena_device_io_suspend(struct work_struct *work)
-{
- struct ena_adapter *adapter =
- container_of(work, struct ena_adapter, suspend_io_task);
- struct net_device *netdev = adapter->netdev;
-
- /* ena_napi_disable_all disables only the IO handling.
- * We are still subject to AENQ keep alive watchdog.
- */
- u64_stats_update_begin(&adapter->syncp);
- adapter->dev_stats.io_suspend++;
- u64_stats_update_begin(&adapter->syncp);
- ena_napi_disable_all(adapter);
- netif_tx_lock(netdev);
- netif_device_detach(netdev);
- netif_tx_unlock(netdev);
-}
-
-static void ena_device_io_resume(struct work_struct *work)
-{
- struct ena_adapter *adapter =
- container_of(work, struct ena_adapter, resume_io_task);
- struct net_device *netdev = adapter->netdev;
-
- u64_stats_update_begin(&adapter->syncp);
- adapter->dev_stats.io_resume++;
- u64_stats_update_end(&adapter->syncp);
-
- netif_device_attach(netdev);
- ena_napi_enable_all(adapter);
-}
-
static int ena_device_validate_params(struct ena_adapter *adapter,
struct ena_com_dev_get_features_ctx *get_feat_ctx)
{
@@ -3276,8 +3244,6 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto err_rss;
}
- INIT_WORK(&adapter->suspend_io_task, ena_device_io_suspend);
- INIT_WORK(&adapter->resume_io_task, ena_device_io_resume);
INIT_WORK(&adapter->reset_task, ena_fw_reset_device);
adapter->last_keep_alive_jiffies = jiffies;
@@ -3311,8 +3277,6 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
err_worker_destroy:
ena_com_destroy_interrupt_moderation(ena_dev);
del_timer(&adapter->timer_service);
- cancel_work_sync(&adapter->suspend_io_task);
- cancel_work_sync(&adapter->resume_io_task);
err_netdev_destroy:
free_netdev(netdev);
err_device_destroy:
@@ -3382,10 +3346,6 @@ static void ena_remove(struct pci_dev *pdev)
cancel_work_sync(&adapter->reset_task);
- cancel_work_sync(&adapter->suspend_io_task);
-
- cancel_work_sync(&adapter->resume_io_task);
-
/* Reset the device only if the device is running. */
if (test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags))
ena_com_dev_reset(ena_dev, adapter->reset_reason);
@@ -3504,16 +3464,6 @@ static void ena_notification(void *adapter_data,
ENA_ADMIN_NOTIFICATION);
switch (aenq_e->aenq_common_desc.syndrom) {
- case ENA_ADMIN_SUSPEND:
- /* Suspend just the IO queues.
- * We deliberately don't suspend admin so the timer and
- * the keep_alive events should remain.
- */
- queue_work(ena_wq, &adapter->suspend_io_task);
- break;
- case ENA_ADMIN_RESUME:
- queue_work(ena_wq, &adapter->resume_io_task);
- break;
case ENA_ADMIN_UPDATE_HINTS:
hints = (struct ena_admin_ena_hw_hints *)
(&aenq_e->inline_data_w4);
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index 29bb5704260b..fb0c98bb9290 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -257,8 +257,6 @@ struct ena_ring {
struct ena_stats_dev {
u64 tx_timeout;
- u64 io_suspend;
- u64 io_resume;
u64 wd_expired;
u64 interface_up;
u64 interface_down;
@@ -326,8 +324,6 @@ struct ena_adapter {
/* timer service */
struct work_struct reset_task;
- struct work_struct suspend_io_task;
- struct work_struct resume_io_task;
struct timer_list timer_service;
bool wd_state;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 1/6] net: ena: improve ENA driver boot time.
From: netanel @ 2017-10-17 7:33 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
In-Reply-To: <1508225641-106366-1-git-send-email-netanel@amazon.com>
From: Netanel Belgazal <netanel@amazon.com>
The ena admin commands timeout is in resolutions of 100ms.
Therefore, When the driver works in polling mode, it sleeps for 100ms
each time. The overall boot time of the ENA driver is ~1.5 sec.
To reduce the boot time, This change modifies the granularity of
the sleeps to 5ms.
This change improves the boot time to 220ms.
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_com.c | 12 ++++++++----
1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index ded29af648c9..bf2de5298005 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -63,6 +63,8 @@
#define ENA_REGS_ADMIN_INTR_MASK 1
+#define ENA_POLL_MS 5
+
/*****************************************************************************/
/*****************************************************************************/
/*****************************************************************************/
@@ -533,7 +535,7 @@ static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_c
goto err;
}
- msleep(100);
+ msleep(ENA_POLL_MS);
}
if (unlikely(comp_ctx->status == ENA_CMD_ABORTED)) {
@@ -746,6 +748,9 @@ static int wait_for_reset_state(struct ena_com_dev *ena_dev, u32 timeout,
{
u32 val, i;
+ /* Convert timeout from resolution of 100ms to ENA_POLL_MS */
+ timeout = (timeout * 100) / ENA_POLL_MS;
+
for (i = 0; i < timeout; i++) {
val = ena_com_reg_bar_read32(ena_dev, ENA_REGS_DEV_STS_OFF);
@@ -758,8 +763,7 @@ static int wait_for_reset_state(struct ena_com_dev *ena_dev, u32 timeout,
exp_state)
return 0;
- /* The resolution of the timeout is 100ms */
- msleep(100);
+ msleep(ENA_POLL_MS);
}
return -ETIME;
@@ -1253,7 +1257,7 @@ void ena_com_wait_for_abort_completion(struct ena_com_dev *ena_dev)
spin_lock_irqsave(&admin_queue->q_lock, flags);
while (atomic_read(&admin_queue->outstanding_cmds) != 0) {
spin_unlock_irqrestore(&admin_queue->q_lock, flags);
- msleep(20);
+ msleep(ENA_POLL_MS);
spin_lock_irqsave(&admin_queue->q_lock, flags);
}
spin_unlock_irqrestore(&admin_queue->q_lock, flags);
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 0/6] update ENA driver to releawse 1.3.0
From: netanel @ 2017-10-17 7:33 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
From: Netanel Belgazal <netanel@amazon.com>
Netanel Belgazal (6):
net: ena: improve ENA driver boot time.
net: ena: remove legacy suspend suspend/resume support
net: ena: add power management ops to the ENA driver
net: ena: add statistics for missed tx packets
net: ena: add new admin define for future support of IPv6 RSS
net: ena: increase ena driver version to 1.3.0
drivers/net/ethernet/amazon/ena/ena_admin_defs.h | 6 +
drivers/net/ethernet/amazon/ena/ena_com.c | 12 +-
drivers/net/ethernet/amazon/ena/ena_ethtool.c | 5 +-
drivers/net/ethernet/amazon/ena/ena_netdev.c | 197 ++++++++++++-----------
drivers/net/ethernet/amazon/ena/ena_netdev.h | 12 +-
5 files changed, 130 insertions(+), 102 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH net 1/3] net: ena: reduce the severity of some printouts
From: netanel @ 2017-10-17 7:33 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
In-Reply-To: <1508225585-106167-1-git-send-email-netanel@amazon.com>
From: Netanel Belgazal <netanel@amazon.com>
Decrease log level of checksum errors as these messages can be
triggered remotely by bad packets.
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_netdev.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index f7dc22f65d9f..7040b9052747 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -966,7 +966,7 @@ static inline void ena_rx_checksum(struct ena_ring *rx_ring,
u64_stats_update_begin(&rx_ring->syncp);
rx_ring->rx_stats.bad_csum++;
u64_stats_update_end(&rx_ring->syncp);
- netif_err(rx_ring->adapter, rx_err, rx_ring->netdev,
+ netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev,
"RX IPv4 header checksum error\n");
return;
}
@@ -979,7 +979,7 @@ static inline void ena_rx_checksum(struct ena_ring *rx_ring,
u64_stats_update_begin(&rx_ring->syncp);
rx_ring->rx_stats.bad_csum++;
u64_stats_update_end(&rx_ring->syncp);
- netif_err(rx_ring->adapter, rx_err, rx_ring->netdev,
+ netif_dbg(rx_ring->adapter, rx_err, rx_ring->netdev,
"RX L4 checksum error\n");
skb->ip_summed = CHECKSUM_NONE;
return;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net 3/3] net: ena: fix wrong max Tx/Rx queues on ethtool
From: netanel @ 2017-10-17 7:33 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
In-Reply-To: <1508225585-106167-1-git-send-email-netanel@amazon.com>
From: Netanel Belgazal <netanel@amazon.com>
ethtool ena_get_channels() expose the max number of queues as the max
number of queues ENA supports (128 queues) and not the actual number
of created queues.
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_ethtool.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
index b1212debc2e1..967020fb26ee 100644
--- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c
+++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c
@@ -742,8 +742,8 @@ static void ena_get_channels(struct net_device *netdev,
{
struct ena_adapter *adapter = netdev_priv(netdev);
- channels->max_rx = ENA_MAX_NUM_IO_QUEUES;
- channels->max_tx = ENA_MAX_NUM_IO_QUEUES;
+ channels->max_rx = adapter->num_queues;
+ channels->max_tx = adapter->num_queues;
channels->max_other = 0;
channels->max_combined = 0;
channels->rx_count = adapter->num_queues;
--
1.8.3.1
^ permalink raw reply related
* [PATCH net 2/3] net: ena: fix rare kernel crash when bar memory remap fails
From: netanel @ 2017-10-17 7:33 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
In-Reply-To: <1508225585-106167-1-git-send-email-netanel@amazon.com>
From: Netanel Belgazal <netanel@amazon.com>
This failure is rare and only found on testing where deliberately fail
devm_ioremap()
[ 451.170464] ena 0000:04:00.0: failed to remap regs bar
451.170549] Workqueue: pciehp-1 pciehp_power_thread
[ 451.170551] task: ffff88085a5f2d00 task.stack: ffffc9000756c000
[ 451.170552] RIP: 0010:devm_iounmap+0x2d/0x40
[ 451.170553] RSP: 0018:ffffc9000756fac0 EFLAGS: 00010282
[ 451.170554] RAX: 00000000fffffffe RBX: 0000000000000000 RCX:
0000000000000000
[ 451.170555] RDX: ffffffff813a7e00 RSI: 0000000000000282 RDI:
0000000000000282
[ 451.170556] RBP: ffffc9000756fac8 R08: 00000000fffffffe R09:
00000000000009b7
[ 451.170557] R10: 0000000000000005 R11: 00000000000009b6 R12:
ffff880856c9d0a0
[ 451.170558] R13: ffffc9000f5c90c0 R14: ffff880856c9d0a0 R15:
0000000000000028
[ 451.170559] FS: 0000000000000000(0000) GS:ffff88085f400000(0000)
knlGS:0000000000000000
[ 451.170560] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 451.170561] CR2: 00007f169038b000 CR3: 0000000001c09000 CR4:
00000000003406f0
[ 451.170562] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
0000000000000000
[ 451.170562] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
0000000000000400
[ 451.170563] Call Trace:
[ 451.170572] ena_release_bars.isra.48+0x34/0x60 [ena]
[ 451.170574] ena_probe+0x144/0xd90 [ena]
[ 451.170579] ? ida_simple_get+0x98/0x100
[ 451.170585] ? kernfs_next_descendant_post+0x40/0x50
[ 451.170591] local_pci_probe+0x45/0xa0
[ 451.170592] pci_device_probe+0x157/0x180
[ 451.170599] driver_probe_device+0x2a8/0x460
[ 451.170600] __device_attach_driver+0x7e/0xe0
[ 451.170602] ? driver_allows_async_probing+0x30/0x30
[ 451.170603] bus_for_each_drv+0x68/0xb0
[ 451.170605] __device_attach+0xdd/0x160
[ 451.170607] device_attach+0x10/0x20
[ 451.170610] pci_bus_add_device+0x4f/0xa0
[ 451.170611] pci_bus_add_devices+0x39/0x70
[ 451.170613] pciehp_configure_device+0x96/0x120
[ 451.170614] pciehp_enable_slot+0x1b3/0x290
[ 451.170616] pciehp_power_thread+0x3b/0xb0
[ 451.170622] process_one_work+0x149/0x360
[ 451.170623] worker_thread+0x4d/0x3c0
[ 451.170626] kthread+0x109/0x140
[ 451.170627] ? rescuer_thread+0x380/0x380
[ 451.170628] ? kthread_park+0x60/0x60
[ 451.170632] ret_from_fork+0x25/0x30
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
---
drivers/net/ethernet/amazon/ena/ena_netdev.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 7040b9052747..c6bd5e24005d 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -3064,7 +3064,8 @@ static void ena_release_bars(struct ena_com_dev *ena_dev, struct pci_dev *pdev)
if (ena_dev->mem_bar)
devm_iounmap(&pdev->dev, ena_dev->mem_bar);
- devm_iounmap(&pdev->dev, ena_dev->reg_bar);
+ if (ena_dev->reg_bar)
+ devm_iounmap(&pdev->dev, ena_dev->reg_bar);
release_bars = pci_select_bars(pdev, IORESOURCE_MEM) & ENA_BAR_MASK;
pci_release_selected_regions(pdev, release_bars);
--
1.8.3.1
^ permalink raw reply related
* [PATCH net 0/3] ENA ethernet driver bug fixes
From: netanel @ 2017-10-17 7:33 UTC (permalink / raw)
To: davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
From: Netanel Belgazal <netanel@amazon.com>
Some fixes for ENA ethernet driver
Netanel Belgazal (3):
net: ena: reduce the severity of some printouts
net: ena: fix rare kernel crash when bar memory remap fails
net: ena: fix wrong max Tx/Rx queues on ethtool
drivers/net/ethernet/amazon/ena/ena_ethtool.c | 4 ++--
drivers/net/ethernet/amazon/ena/ena_netdev.c | 7 ++++---
2 files changed, 6 insertions(+), 5 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH net-next] MAINTAINERS: change ENA driver maintainers email domain
From: netanel @ 2017-10-17 7:30 UTC (permalink / raw)
To: linux-kernel, davem, netdev
Cc: Netanel Belgazal, dwmw, zorik, matua, saeedb, msw, aliguori,
nafea, evgenys
From: Netanel Belgazal <netanel@amazon.com>
ENA driver was developed by developers from Annapurna Labs.
Annapurna Labs was acquired by Amazon and the company's domain
(@annapurnalabs.com) will become deprecated soon.
Update the email addresses of the maintainers to the alternative amazon
emails (@amazon.com)
Signed-off-by: Netanel Belgazal <netanel@amazon.com>
---
MAINTAINERS | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 3944f1626911..f218fe1e43fe 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -700,9 +700,9 @@ F: include/linux/altera_uart.h
F: include/linux/altera_jtaguart.h
AMAZON ETHERNET DRIVERS
-M: Netanel Belgazal <netanel@annapurnalabs.com>
-R: Saeed Bishara <saeed@annapurnalabs.com>
-R: Zorik Machulsky <zorik@annapurnalabs.com>
+M: Netanel Belgazal <netanel@amazon.com>
+R: Saeed Bishara <saeedb@amazon.com>
+R: Zorik Machulsky <zorik@amazon.com>
L: netdev@vger.kernel.org
S: Supported
F: Documentation/networking/ena.txt
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next] qed: Fix iWARP out of order flow
From: Michal Kalderon @ 2017-10-17 7:23 UTC (permalink / raw)
To: davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
dledford-H+wXaHxf7aLQT0dZR+AlfA, Michal Kalderon,
Manish Rangankar, Ariel Elior
Out of order flow is not working for iWARP.
This patch got cut out from initial series that added out
of order support for iWARP.
Make out of order code common for iWARP and iSCSI.
Add new configuration option CONFIG_QED_OOO. Set by
qedr and qedi Kconfigs.
Fixes: d1abfd0b4ee2 ("qed: Add iWARP out of order support")
Signed-off-by: Michal Kalderon <Michal.Kalderon-YGCgFSpz5w/QT0dZR+AlfA@public.gmane.org>
Signed-off-by: Manish Rangankar <Manish.Rangankar-YGCgFSpz5w/QT0dZR+AlfA@public.gmane.org>
Signed-off-by: Ariel Elior <Ariel.Elior-YGCgFSpz5w/QT0dZR+AlfA@public.gmane.org>
---
drivers/infiniband/hw/qedr/Kconfig | 1 +
drivers/net/ethernet/qlogic/Kconfig | 3 +++
drivers/net/ethernet/qlogic/qed/Makefile | 3 ++-
drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 7 ++++++-
drivers/net/ethernet/qlogic/qed/qed_ooo.c | 16 +++++++++++++---
drivers/net/ethernet/qlogic/qed/qed_ooo.h | 2 +-
drivers/scsi/qedi/Kconfig | 1 +
7 files changed, 27 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/hw/qedr/Kconfig b/drivers/infiniband/hw/qedr/Kconfig
index 6c9f392..60e867d 100644
--- a/drivers/infiniband/hw/qedr/Kconfig
+++ b/drivers/infiniband/hw/qedr/Kconfig
@@ -2,6 +2,7 @@ config INFINIBAND_QEDR
tristate "QLogic RoCE driver"
depends on 64BIT && QEDE
select QED_LL2
+ select QED_OOO
select QED_RDMA
---help---
This driver provides low-level InfiniBand over Ethernet
diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig
index c2e24af..26ddf09 100644
--- a/drivers/net/ethernet/qlogic/Kconfig
+++ b/drivers/net/ethernet/qlogic/Kconfig
@@ -117,4 +117,7 @@ config QED_ISCSI
config QED_FCOE
bool
+config QED_OOO
+ bool
+
endif # NET_VENDOR_QLOGIC
diff --git a/drivers/net/ethernet/qlogic/qed/Makefile b/drivers/net/ethernet/qlogic/qed/Makefile
index 82dd470..c3c5999 100644
--- a/drivers/net/ethernet/qlogic/qed/Makefile
+++ b/drivers/net/ethernet/qlogic/qed/Makefile
@@ -6,5 +6,6 @@ qed-y := qed_cxt.o qed_dev.o qed_hw.o qed_init_fw_funcs.o qed_init_ops.o \
qed-$(CONFIG_QED_SRIOV) += qed_sriov.o qed_vf.o
qed-$(CONFIG_QED_LL2) += qed_ll2.o
qed-$(CONFIG_QED_RDMA) += qed_roce.o qed_rdma.o qed_iwarp.o
-qed-$(CONFIG_QED_ISCSI) += qed_iscsi.o qed_ooo.o
+qed-$(CONFIG_QED_ISCSI) += qed_iscsi.o
qed-$(CONFIG_QED_FCOE) += qed_fcoe.o
+qed-$(CONFIG_QED_OOO) += qed_ooo.o
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index b2b1f87..409041e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -1410,13 +1410,18 @@ int qed_iwarp_alloc(struct qed_hwfn *p_hwfn)
INIT_LIST_HEAD(&p_hwfn->p_rdma_info->iwarp.ep_free_list);
spin_lock_init(&p_hwfn->p_rdma_info->iwarp.iw_lock);
- return qed_iwarp_prealloc_ep(p_hwfn, true);
+ rc = qed_iwarp_prealloc_ep(p_hwfn, true);
+ if (rc)
+ return rc;
+
+ return qed_ooo_alloc(p_hwfn);
}
void qed_iwarp_resc_free(struct qed_hwfn *p_hwfn)
{
struct qed_iwarp_info *iwarp_info = &p_hwfn->p_rdma_info->iwarp;
+ qed_ooo_free(p_hwfn);
qed_rdma_bmap_free(p_hwfn, &p_hwfn->p_rdma_info->tcp_cid_map, 1);
kfree(iwarp_info->mpa_bufs);
kfree(iwarp_info->partial_fpdus);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.c b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
index 0006365..6172354 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.c
@@ -103,18 +103,28 @@ int qed_ooo_alloc(struct qed_hwfn *p_hwfn)
{
u16 max_num_archipelagos = 0, cid_base;
struct qed_ooo_info *p_ooo_info;
+ enum protocol_type proto;
u16 max_num_isles = 0;
u32 i;
- if (p_hwfn->hw_info.personality != QED_PCI_ISCSI) {
+ switch (p_hwfn->hw_info.personality) {
+ case QED_PCI_ISCSI:
+ proto = PROTOCOLID_ISCSI;
+ break;
+ case QED_PCI_ETH_RDMA:
+ case QED_PCI_ETH_IWARP:
+ proto = PROTOCOLID_IWARP;
+ break;
+ default:
DP_NOTICE(p_hwfn,
"Failed to allocate qed_ooo_info: unknown personality\n");
return -EINVAL;
}
- max_num_archipelagos = p_hwfn->pf_params.iscsi_pf_params.num_cons;
+ max_num_archipelagos = (u16)qed_cxt_get_proto_cid_count(p_hwfn, proto,
+ NULL);
max_num_isles = QED_MAX_NUM_ISLES + max_num_archipelagos;
- cid_base = (u16)qed_cxt_get_proto_cid_start(p_hwfn, PROTOCOLID_ISCSI);
+ cid_base = (u16)qed_cxt_get_proto_cid_start(p_hwfn, proto);
if (!max_num_archipelagos) {
DP_NOTICE(p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ooo.h b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
index e8ed40b..49c4e75 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ooo.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ooo.h
@@ -83,7 +83,7 @@ struct qed_ooo_info {
u16 cid_base;
};
-#if IS_ENABLED(CONFIG_QED_ISCSI)
+#if IS_ENABLED(CONFIG_QED_OOO)
void qed_ooo_save_history_entry(struct qed_hwfn *p_hwfn,
struct qed_ooo_info *p_ooo_info,
struct ooo_opaque *p_cqe);
diff --git a/drivers/scsi/qedi/Kconfig b/drivers/scsi/qedi/Kconfig
index 2ff753c..d1db92d 100644
--- a/drivers/scsi/qedi/Kconfig
+++ b/drivers/scsi/qedi/Kconfig
@@ -4,6 +4,7 @@ config QEDI
depends on QED
select SCSI_ISCSI_ATTRS
select QED_LL2
+ select QED_OOO
select QED_ISCSI
select ISCSI_BOOT_SYSFS
---help---
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH v2 net-next] net: hns3: Add mqprio hardware offload support in hns3 driver
From: Yunsheng Lin @ 2017-10-17 6:51 UTC (permalink / raw)
To: davem
Cc: huangdaode, xuwei5, liguozhu, Yisen.Zhuang, gabriele.paoloni,
john.garry, linuxarm, yisen.zhuang, salil.mehta, lipeng321,
netdev, linux-kernel
When using tc qdisc, dcb_ops->setup_tc is used to tell hclge_dcb
module to do the tm related setup. Only TC_MQPRIO_MODE_CHANNEL
offload mode is supported.
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
V2:
1. Add HCLGE_FLAG_MQPRIO_ENABLE to indicate offlaoding the
mqprio.
2. Change to support TC_MQPRIO_MODE_CHANNEL mode.
---
drivers/net/ethernet/hisilicon/hns3/hnae3.h | 1 +
.../net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c | 47 +++++++++++++++++-
.../ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 1 +
.../net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c | 56 +++++++++++++++-------
4 files changed, 86 insertions(+), 19 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 575f50d..3acd8db 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -381,6 +381,7 @@ struct hnae3_dcb_ops {
u8 (*setdcbx)(struct hnae3_handle *, u8);
int (*map_update)(struct hnae3_handle *);
+ int (*setup_tc)(struct hnae3_handle *, u8, u8 *);
};
struct hnae3_ae_algo {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index 1b30a6f..5018d66 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -178,7 +178,8 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
u8 num_tc = 0;
int ret;
- if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
+ if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
+ hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
return -EINVAL;
ret = hclge_ets_validate(hdev, ets, &num_tc, &map_changed);
@@ -228,7 +229,8 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
struct hclge_dev *hdev = vport->back;
u8 i, j, pfc_map, *prio_tc;
- if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE))
+ if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
+ hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
return -EINVAL;
prio_tc = hdev->tm_info.prio_tc;
@@ -257,6 +259,9 @@ static u8 hclge_getdcbx(struct hnae3_handle *h)
struct hclge_vport *vport = hclge_get_vport(h);
struct hclge_dev *hdev = vport->back;
+ if (hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
+ return 0;
+
return hdev->dcbx_cap;
}
@@ -276,6 +281,43 @@ static u8 hclge_setdcbx(struct hnae3_handle *h, u8 mode)
return 0;
}
+/* Set up TC for hardware offloaded mqprio in channel mode */
+static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc)
+{
+ struct hclge_vport *vport = hclge_get_vport(h);
+ struct hclge_dev *hdev = vport->back;
+ int ret;
+
+ if (hdev->flag & HCLGE_FLAG_DCB_ENABLE)
+ return -EINVAL;
+
+ if (tc > hdev->tc_max) {
+ dev_err(&hdev->pdev->dev,
+ "setup tc failed, tc(%u) > tc_max(%u)\n",
+ tc, hdev->tc_max);
+ return -EINVAL;
+ }
+
+ hclge_tm_schd_info_update(hdev, tc);
+
+ ret = hclge_tm_prio_tc_info_update(hdev, prio_tc);
+ if (ret)
+ return ret;
+
+ ret = hclge_tm_init_hw(hdev);
+ if (ret)
+ return ret;
+
+ hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
+
+ if (tc > 1)
+ hdev->flag |= HCLGE_FLAG_MQPRIO_ENABLE;
+ else
+ hdev->flag &= ~HCLGE_FLAG_MQPRIO_ENABLE;
+
+ return 0;
+}
+
static const struct hnae3_dcb_ops hns3_dcb_ops = {
.ieee_getets = hclge_ieee_getets,
.ieee_setets = hclge_ieee_setets,
@@ -284,6 +326,7 @@ static u8 hclge_setdcbx(struct hnae3_handle *h, u8 mode)
.getdcbx = hclge_getdcbx,
.setdcbx = hclge_setdcbx,
.map_update = hclge_map_update,
+ .setup_tc = hclge_setup_tc,
};
void hclge_dcb_ops_set(struct hclge_dev *hdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index a7c018c..bca4430 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -470,6 +470,7 @@ struct hclge_dev {
#define HCLGE_FLAG_MAIN 0x00000004
#define HCLGE_FLAG_DCB_CAPABLE 0x00000008
#define HCLGE_FLAG_DCB_ENABLE 0x00000010
+#define HCLGE_FLAG_MQPRIO_ENABLE 0x00000020
u32 flag;
u32 pkt_buf_size; /* Total pf buf size for tx/rx */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
index ba550c1..8fa4e65 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hns3_enet.c
@@ -19,6 +19,7 @@
#include <linux/sctp.h>
#include <linux/vermagic.h>
#include <net/gre.h>
+#include <net/pkt_cls.h>
#include <net/vxlan.h>
#include "hnae3.h"
@@ -1186,53 +1187,74 @@ static void hns3_nic_udp_tunnel_del(struct net_device *netdev,
}
}
-static int hns3_setup_tc(struct net_device *netdev, u8 tc)
+static int hns3_setup_tc(struct net_device *netdev, void *type_data)
{
+ struct tc_mqprio_qopt_offload *mqprio_qopt = type_data;
struct hnae3_handle *h = hns3_get_handle(netdev);
struct hnae3_knic_private_info *kinfo = &h->kinfo;
+ u8 *prio_tc = mqprio_qopt->qopt.prio_tc_map;
+ u8 tc = mqprio_qopt->qopt.num_tc;
+ u16 mode = mqprio_qopt->mode;
+ u8 hw = mqprio_qopt->qopt.hw;
+ bool if_running;
unsigned int i;
int ret;
+ if (!((hw == TC_MQPRIO_HW_OFFLOAD_TCS &&
+ mode == TC_MQPRIO_MODE_CHANNEL) || (!hw && tc == 0)))
+ return -EOPNOTSUPP;
+
if (tc > HNAE3_MAX_TC)
return -EINVAL;
- if (kinfo->num_tc == tc)
- return 0;
-
if (!netdev)
return -EINVAL;
- if (!tc) {
- netdev_reset_tc(netdev);
- return 0;
+ if_running = netif_running(netdev);
+ if (if_running) {
+ hns3_nic_net_stop(netdev);
+ msleep(100);
}
- /* Set num_tc for netdev */
- ret = netdev_set_num_tc(netdev, tc);
+ ret = (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
+ kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP;
if (ret)
- return ret;
+ goto out;
+
+ if (tc <= 1) {
+ netdev_reset_tc(netdev);
+ } else {
+ ret = netdev_set_num_tc(netdev, tc);
+ if (ret)
+ goto out;
+
+ for (i = 0; i < HNAE3_MAX_TC; i++) {
+ if (!kinfo->tc_info[i].enable)
+ continue;
- /* Set per TC queues for the VSI */
- for (i = 0; i < HNAE3_MAX_TC; i++) {
- if (kinfo->tc_info[i].enable)
netdev_set_tc_queue(netdev,
kinfo->tc_info[i].tc,
kinfo->tc_info[i].tqp_count,
kinfo->tc_info[i].tqp_offset);
+ }
}
- return 0;
+ ret = hns3_nic_set_real_num_queue(netdev);
+
+out:
+ if (if_running)
+ hns3_nic_net_open(netdev);
+
+ return ret;
}
static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
- struct tc_mqprio_qopt *mqprio = type_data;
-
if (type != TC_SETUP_MQPRIO)
return -EOPNOTSUPP;
- return hns3_setup_tc(dev, mqprio->num_tc);
+ return hns3_setup_tc(dev, type_data);
}
static int hns3_vlan_rx_add_vid(struct net_device *netdev,
--
1.9.1
^ permalink raw reply related
* [PATCH net-next] tcp: Enable TFO without a cookie on a per-socket basis
From: Christoph Paasch @ 2017-10-17 6:37 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Eric Dumazet, Yuchung Cheng
We already allow to enable TFO without a cookie by using the
fastopen-sysctl and setting it to TFO_SERVER_COOKIE_NOT_REQD (0x200).
This is safe to do in certain environments where we know that there
isn't a malicous host (aka., data-centers).
A server however might be talking to both sides (public Internet and
data-center). So, this server would want to enable cookie-less TFO for
the connections that go to the data-center while enforcing cookies for
the traffic from the Internet.
This patch exposes a socket-option to enable this (protected by
CAP_NET_ADMIN).
Signed-off-by: Christoph Paasch <cpaasch@apple.com>
---
include/linux/tcp.h | 1 +
include/uapi/linux/tcp.h | 1 +
net/ipv4/tcp.c | 14 ++++++++++++++
net/ipv4/tcp_fastopen.c | 6 ++++--
4 files changed, 20 insertions(+), 2 deletions(-)
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 1d2c44e09e31..cda5d4dc8d70 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -228,6 +228,7 @@ struct tcp_sock {
syn_fastopen_ch:1, /* Active TFO re-enabling probe */
syn_data_acked:1,/* data in SYN is acked by SYN-ACK */
save_syn:1, /* Save headers of SYN packet */
+ no_tfo_cookie:1, /* Allow send/recv SYN+data without a cookie */
is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 15c25eccab2b..d44f4bef056c 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -119,6 +119,7 @@ enum {
#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */
#define TCP_ULP 31 /* Attach a ULP to a TCP connection */
#define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */
+#define TCP_NO_TFO_COOKIE 33 /* Enable TFO without a TFO cookie */
struct tcp_repair_opt {
__u32 opt_code;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3b34850d361f..88c90be12d9f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2821,6 +2821,16 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
err = -EOPNOTSUPP;
}
break;
+ case TCP_NO_TFO_COOKIE:
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ err = -EPERM;
+ else if (val > 1 || val < 0)
+ err = -EINVAL;
+ else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
+ err = -EINVAL;
+ else
+ tp->no_tfo_cookie = 1;
+ break;
case TCP_TIMESTAMP:
if (!tp->repair)
err = -EPERM;
@@ -3219,6 +3229,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
val = tp->fastopen_connect;
break;
+ case TCP_NO_TFO_COOKIE:
+ val = tp->no_tfo_cookie;
+ break;
+
case TCP_TIMESTAMP:
val = tcp_time_stamp_raw() + tp->tsoffset;
break;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 7ee4aadcdd71..c1b00b666b43 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -309,7 +309,8 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
return NULL;
}
- if (syn_data && (tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
+ if (syn_data && ((tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD) ||
+ tcp_sk(sk)->no_tfo_cookie))
goto fastopen;
if (foc->len >= 0 && /* Client presents or requests a cookie */
@@ -363,7 +364,8 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
return false;
}
- if (sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) {
+ if ((sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) ||
+ tcp_sk(sk)->no_tfo_cookie) {
cookie->len = -1;
return true;
}
--
2.14.1
^ permalink raw reply related
* Re: [net-next 4/9] i40e: Enable 'channel' mode in mqprio for TC configs
From: Yunsheng Lin @ 2017-10-17 6:24 UTC (permalink / raw)
To: Nambiar, Amritha, Jeff Kirsher, davem; +Cc: netdev, nhorman, sassmann, jogreene
In-Reply-To: <4e06d67d-5eea-02ea-1ce2-993666e19b2e@intel.com>
Hi, Nambiar
On 2017/10/17 0:03, Nambiar, Amritha wrote:
> On 10/16/2017 1:53 AM, Yunsheng Lin wrote:
>> Hi, Jeff
>>
>> On 2017/10/14 5:52, Jeff Kirsher wrote:
>>> From: Amritha Nambiar <amritha.nambiar@intel.com>
>>>
>>> The i40e driver is modified to enable the new mqprio hardware
>>> offload mode and factor the TCs and queue configuration by
>>> creating channel VSIs. In this mode, the priority to traffic
>>> class mapping and the user specified queue ranges are used
>>> to configure the traffic classes by setting the mode option to
>>> 'channel'.
>>>
>>> Example:
>>> map 0 0 0 0 1 2 2 3 queues 2@0 2@2 1@4 1@5\
>>> hw 1 mode channel
>>>
>>> qdisc mqprio 8038: root tc 4 map 0 0 0 0 1 2 2 3 0 0 0 0 0 0 0 0
>>> queues:(0:1) (2:3) (4:4) (5:5)
>>> mode:channel
>>> shaper:dcb
>>>
>>> The HW channels created are removed and all the queue configuration
>>> is set to default when the qdisc is detached from the root of the
>>> device.
>>>
>>> This patch also disables setting up channels via ethtool (ethtool -L)
>>> when the TCs are configured using mqprio scheduler.
>>>
>>> The patch also limits setting ethtool Rx flow hash indirection
>>> (ethtool -X eth0 equal N) to max queues configured via mqprio.
>>> The Rx flow hash indirection input through ethtool should be
>>> validated so that it is within in the queue range configured via
>>> tc/mqprio. The bound checking is achieved by reporting the current
>>> rss size to the kernel when queues are configured via mqprio.
>>>
>>> Example:
>>> map 0 0 0 1 0 2 3 0 queues 2@0 4@2 8@6 11@14\
>>> hw 1 mode channel
>>>
>>> Cannot set RX flow hash configuration: Invalid argument
>>>
>>> Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
>>> Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
>>> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
>>> ---
>>> drivers/net/ethernet/intel/i40e/i40e.h | 3 +
>>> drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 8 +-
>>> drivers/net/ethernet/intel/i40e/i40e_main.c | 457 +++++++++++++++++++------
>>> 3 files changed, 362 insertions(+), 106 deletions(-)
>>>
>>> diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
>>> index bde982541772..024c88474951 100644
>>> --- a/drivers/net/ethernet/intel/i40e/i40e.h
>>> +++ b/drivers/net/ethernet/intel/i40e/i40e.h
>>> @@ -54,6 +54,7 @@
>>> #include <linux/clocksource.h>
>>> #include <linux/net_tstamp.h>
>>> #include <linux/ptp_clock_kernel.h>
>>> +#include <net/pkt_cls.h>
>>> #include "i40e_type.h"
>>> #include "i40e_prototype.h"
>>> #include "i40e_client.h"
>>> @@ -700,6 +701,7 @@ struct i40e_vsi {
>>> enum i40e_vsi_type type; /* VSI type, e.g., LAN, FCoE, etc */
>>> s16 vf_id; /* Virtual function ID for SRIOV VSIs */
>>>
>>> + struct tc_mqprio_qopt_offload mqprio_qopt; /* queue parameters */
>>> struct i40e_tc_configuration tc_config;
>>> struct i40e_aqc_vsi_properties_data info;
>>>
>>> @@ -725,6 +727,7 @@ struct i40e_vsi {
>>> u16 cnt_q_avail; /* num of queues available for channel usage */
>>> u16 orig_rss_size;
>>> u16 current_rss_size;
>>> + bool reconfig_rss;
>>>
>>> u16 next_base_queue; /* next queue to be used for channel setup */
>>>
>>> diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
>>> index afd3ca8d9851..72d5f2cdf419 100644
>>> --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
>>> +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
>>> @@ -2652,7 +2652,7 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
>>>
>>> switch (cmd->cmd) {
>>> case ETHTOOL_GRXRINGS:
>>> - cmd->data = vsi->num_queue_pairs;
>>> + cmd->data = vsi->rss_size;
>>> ret = 0;
>>> break;
>>> case ETHTOOL_GRXFH:
>>> @@ -3897,6 +3897,12 @@ static int i40e_set_channels(struct net_device *dev,
>>> if (vsi->type != I40E_VSI_MAIN)
>>> return -EINVAL;
>>>
>>> + /* We do not support setting channels via ethtool when TCs are
>>> + * configured through mqprio
>>> + */
>>> + if (pf->flags & I40E_FLAG_TC_MQPRIO)
>>> + return -EINVAL;
>>> +
>>> /* verify they are not requesting separate vectors */
>>> if (!count || ch->rx_count || ch->tx_count)
>>> return -EINVAL;
>>> diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
>>> index e23105bee6d1..e803aa1552c6 100644
>>> --- a/drivers/net/ethernet/intel/i40e/i40e_main.c
>>> +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
>>> @@ -1588,6 +1588,170 @@ static int i40e_set_mac(struct net_device *netdev, void *p)
>>> return 0;
>>> }
>>>
>>> +/**
>>> + * i40e_config_rss_aq - Prepare for RSS using AQ commands
>>> + * @vsi: vsi structure
>>> + * @seed: RSS hash seed
>>> + **/
>>
>> [...]
>>
>>> + * i40e_vsi_set_default_tc_config - set default values for tc configuration
>>> + * @vsi: the VSI being configured
>>> + **/
>>> +static void i40e_vsi_set_default_tc_config(struct i40e_vsi *vsi)
>>> +{
>>> + u16 qcount;
>>> + int i;
>>> +
>>> + /* Only TC0 is enabled */
>>> + vsi->tc_config.numtc = 1;
>>> + vsi->tc_config.enabled_tc = 1;
>>> + qcount = min_t(int, vsi->alloc_queue_pairs,
>>> + i40e_pf_get_max_q_per_tc(vsi->back));
>>> + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
>>> + /* For the TC that is not enabled set the offset to to default
>>> + * queue and allocate one queue for the given TC.
>>> + */
>>> + vsi->tc_config.tc_info[i].qoffset = 0;
>>> + if (i == 0)
>>> + vsi->tc_config.tc_info[i].qcount = qcount;
>>> + else
>>> + vsi->tc_config.tc_info[i].qcount = 1;
>>> + vsi->tc_config.tc_info[i].netdev_tc = 0;
>>> + }
>>> +}
>>> +
>>> /**
>>> * i40e_setup_tc - configure multiple traffic classes
>>> * @netdev: net device to configure
>>> - * @tc: number of traffic classes to enable
>>> + * @type_data: tc offload data
>>> **/
>>> -static int i40e_setup_tc(struct net_device *netdev, u8 tc)
>>> +static int i40e_setup_tc(struct net_device *netdev, void *type_data)
>>> {
>>> + struct tc_mqprio_qopt_offload *mqprio_qopt = type_data;
>>> struct i40e_netdev_priv *np = netdev_priv(netdev);
>>> struct i40e_vsi *vsi = np->vsi;
>>> struct i40e_pf *pf = vsi->back;
>>> - u8 enabled_tc = 0;
>>> + u8 enabled_tc = 0, num_tc, hw;
>>> + bool need_reset = false;
>>> int ret = -EINVAL;
>>> + u16 mode;
>>> int i;
>>>
>>> - /* Check if DCB enabled to continue */
>>> - if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) {
>>> - netdev_info(netdev, "DCB is not enabled for adapter\n");
>>> - goto exit;
>>> + num_tc = mqprio_qopt->qopt.num_tc;
>>> + hw = mqprio_qopt->qopt.hw;
>>> + mode = mqprio_qopt->mode;
>>> + if (!hw) {
>>
>> When stack call the ndo_setup_tc, then qopt.hw is always non-zero, Can you
>> tell me why you need to check for this?
>
> This needs to be checked here because when the qdisc is detached from
> root of the device, i.e. 'tc qdisc del dev <interface>', the 'mqprio
> destroy' flow calls ndo_setup_tc with the offload values zeroed out for
> proper clean up.
I see, Thanks.
>
> -Amritha
>
>>
>> Thanks,
>> Yunsheng Lin
>>
>>> + pf->flags &= ~I40E_FLAG_TC_MQPRIO;
>>> + memcpy(&vsi->mqprio_qopt, mqprio_qopt, sizeof(*mqprio_qopt));
>>> + goto config_tc;
>>> }
>>>
>>> /* Check if MFP enabled */
>>> if (pf->flags & I40E_FLAG_MFP_ENABLED) {
>>> - netdev_info(netdev, "Configuring TC not supported in MFP mode\n");
>>> - goto exit;
>>> + netdev_info(netdev,
>>> + "Configuring TC not supported in MFP mode\n");
>>> + return ret;
>>> }
>>> + switch (mode) {
>>> + case TC_MQPRIO_MODE_DCB:
>>> + pf->flags &= ~I40E_FLAG_TC_MQPRIO;
>>>
>>> - /* Check whether tc count is within enabled limit */
>>> - if (tc > i40e_pf_get_num_tc(pf)) {
>>> - netdev_info(netdev, "TC count greater than enabled on link for adapter\n");
>>> - goto exit;
>>> + /* Check if DCB enabled to continue */
>>> + if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) {
>>> + netdev_info(netdev,
>>> + "DCB is not enabled for adapter\n");
>>> + return ret;
>>> + }
>>> +
>>> + /* Check whether tc count is within enabled limit */
>>> + if (num_tc > i40e_pf_get_num_tc(pf)) {
>>> + netdev_info(netdev,
>>> + "TC count greater than enabled on link for adapter\n");
>>> + return ret;
>>> + }
>>> + break;
>>> + case TC_MQPRIO_MODE_CHANNEL:
>>> + if (pf->flags & I40E_FLAG_DCB_ENABLED) {
>>> + netdev_info(netdev,
>>> + "Full offload of TC Mqprio options is not supported when DCB is enabled\n");
>>> + return ret;
>>> + }
>>> + if (!(pf->flags & I40E_FLAG_MSIX_ENABLED))
>>> + return ret;
>>> + ret = i40e_validate_mqprio_qopt(vsi, mqprio_qopt);
>>> + if (ret)
>>> + return ret;
>>> + memcpy(&vsi->mqprio_qopt, mqprio_qopt,
>>> + sizeof(*mqprio_qopt));
>>> + pf->flags |= I40E_FLAG_TC_MQPRIO;
>>> + pf->flags &= ~I40E_FLAG_DCB_ENABLED;
>>> + break;
>>> + default:
>>> + return -EINVAL;
>>> }
>>>
>>> +config_tc:
>>> /* Generate TC map for number of tc requested */
>>> - for (i = 0; i < tc; i++)
>>> + for (i = 0; i < num_tc; i++)
>>> enabled_tc |= BIT(i);
>>>
>>> /* Requesting same TC configuration as already enabled */
>>> - if (enabled_tc == vsi->tc_config.enabled_tc)
>>> + if (enabled_tc == vsi->tc_config.enabled_tc &&
>>> + mode != TC_MQPRIO_MODE_CHANNEL)
>>> return 0;
>>>
>>> /* Quiesce VSI queues */
>>> i40e_quiesce_vsi(vsi);
>>>
>>> + if (!hw && !(pf->flags & I40E_FLAG_TC_MQPRIO))
>>> + i40e_remove_queue_channels(vsi);
>>> +
>>> /* Configure VSI for enabled TCs */
>>> ret = i40e_vsi_config_tc(vsi, enabled_tc);
>>> if (ret) {
>>> netdev_info(netdev, "Failed configuring TC for VSI seid=%d\n",
>>> vsi->seid);
>>> + need_reset = true;
>>> goto exit;
>>> }
>>>
>>> @@ -6272,11 +6595,18 @@ static int i40e_setup_tc(struct net_device *netdev, u8 tc)
>>> if (ret) {
>>> netdev_info(netdev,
>>> "Failed configuring queue channels\n");
>>> + need_reset = true;
>>> goto exit;
>>> }
>>> }
>>>
>>> exit:
>>> + /* Reset the configuration data to defaults, only TC0 is enabled */
>>> + if (need_reset) {
>>> + i40e_vsi_set_default_tc_config(vsi);
>>> + need_reset = false;
>>> + }
>>> +
>>> /* Unquiesce VSI */
>>> i40e_unquiesce_vsi(vsi);
>>> return ret;
>>> @@ -6285,14 +6615,10 @@ static int i40e_setup_tc(struct net_device *netdev, u8 tc)
>>> static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
>>> void *type_data)
>>> {
>>> - struct tc_mqprio_qopt *mqprio = type_data;
>>> -
>>> if (type != TC_SETUP_MQPRIO)
>>> return -EOPNOTSUPP;
>>>
>>> - mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
>>> -
>>> - return i40e_setup_tc(netdev, mqprio->num_tc);
>>> + return i40e_setup_tc(netdev, type_data);
>>> }
>>>
>>> /**
>>> @@ -9153,45 +9479,6 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf)
>>> return err;
>>> }
>>>
>>> -/**
>>> - * i40e_config_rss_aq - Prepare for RSS using AQ commands
>>> - * @vsi: vsi structure
>>> - * @seed: RSS hash seed
>>> - **/
>>> -static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
>>> - u8 *lut, u16 lut_size)
>>> -{
>>> - struct i40e_pf *pf = vsi->back;
>>> - struct i40e_hw *hw = &pf->hw;
>>> - int ret = 0;
>>> -
>>> - if (seed) {
>>> - struct i40e_aqc_get_set_rss_key_data *seed_dw =
>>> - (struct i40e_aqc_get_set_rss_key_data *)seed;
>>> - ret = i40e_aq_set_rss_key(hw, vsi->id, seed_dw);
>>> - if (ret) {
>>> - dev_info(&pf->pdev->dev,
>>> - "Cannot set RSS key, err %s aq_err %s\n",
>>> - i40e_stat_str(hw, ret),
>>> - i40e_aq_str(hw, hw->aq.asq_last_status));
>>> - return ret;
>>> - }
>>> - }
>>> - if (lut) {
>>> - bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false;
>>> -
>>> - ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size);
>>> - if (ret) {
>>> - dev_info(&pf->pdev->dev,
>>> - "Cannot set RSS lut, err %s aq_err %s\n",
>>> - i40e_stat_str(hw, ret),
>>> - i40e_aq_str(hw, hw->aq.asq_last_status));
>>> - return ret;
>>> - }
>>> - }
>>> - return ret;
>>> -}
>>> -
>>> /**
>>> * i40e_get_rss_aq - Get RSS keys and lut by using AQ commands
>>> * @vsi: Pointer to vsi structure
>>> @@ -9238,46 +9525,6 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
>>> return ret;
>>> }
>>>
>>> -/**
>>> - * i40e_vsi_config_rss - Prepare for VSI(VMDq) RSS if used
>>> - * @vsi: VSI structure
>>> - **/
>>> -static int i40e_vsi_config_rss(struct i40e_vsi *vsi)
>>> -{
>>> - u8 seed[I40E_HKEY_ARRAY_SIZE];
>>> - struct i40e_pf *pf = vsi->back;
>>> - u8 *lut;
>>> - int ret;
>>> -
>>> - if (!(pf->hw_features & I40E_HW_RSS_AQ_CAPABLE))
>>> - return 0;
>>> -
>>> - if (!vsi->rss_size)
>>> - vsi->rss_size = min_t(int, pf->alloc_rss_size,
>>> - vsi->num_queue_pairs);
>>> - if (!vsi->rss_size)
>>> - return -EINVAL;
>>> -
>>> - lut = kzalloc(vsi->rss_table_size, GFP_KERNEL);
>>> - if (!lut)
>>> - return -ENOMEM;
>>> - /* Use the user configured hash keys and lookup table if there is one,
>>> - * otherwise use default
>>> - */
>>> - if (vsi->rss_lut_user)
>>> - memcpy(lut, vsi->rss_lut_user, vsi->rss_table_size);
>>> - else
>>> - i40e_fill_rss_lut(pf, lut, vsi->rss_table_size, vsi->rss_size);
>>> - if (vsi->rss_hkey_user)
>>> - memcpy(seed, vsi->rss_hkey_user, I40E_HKEY_ARRAY_SIZE);
>>> - else
>>> - netdev_rss_key_fill((void *)seed, I40E_HKEY_ARRAY_SIZE);
>>> - ret = i40e_config_rss_aq(vsi, seed, lut, vsi->rss_table_size);
>>> - kfree(lut);
>>> -
>>> - return ret;
>>> -}
>>> -
>>> /**
>>> * i40e_config_rss_reg - Configure RSS keys and lut by writing registers
>>> * @vsi: Pointer to vsi structure
>>>
>>
>
> .
>
^ permalink raw reply
* Re: Linux 4.12+ memory leak on router with i40e NICs
From: Vitezslav Samel @ 2017-10-17 5:51 UTC (permalink / raw)
To: Paweł Staszewski
Cc: Pavlos Parissis, Alexander Duyck, Anders K. Pedersen | Cohaesio,
netdev@vger.kernel.org, intel-wired-lan@lists.osuosl.org,
alexander.h.duyck@intel.com
In-Reply-To: <39696136-2a4a-9c6c-3a63-4485ed2a1bf3@itcare.pl>
On Tue, Oct 17, 2017 at 01:34:29AM +0200, Paweł Staszewski wrote:
> W dniu 2017-10-16 o 18:26, Paweł Staszewski pisze:
> > W dniu 2017-10-16 o 13:20, Pavlos Parissis pisze:
> > > On 15/10/2017 02:58 πμ, Alexander Duyck wrote:
> > > > Hi Pawel,
> > > >
> > > > To clarify is that Dave Miller's tree or Linus's that you are talking
> > > > about? If it is Dave's tree how long ago was it you pulled it since I
> > > > think the fix was just pushed by Jeff Kirsher a few days ago.
> > > >
> > > > The issue should be fixed in the following commit:
> > > > https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git/commit/drivers/net/ethernet/intel/i40e/i40e_txrx.c?id=2b9478ffc550f17c6cd8c69057234e91150f5972
> > >
> > > Do you know when it is going to be available on net-next and
> > > linux-stable repos?
> > >
> > > Cheers,
> > > Pavlos
> > >
> > >
> > I will make some tests today night with "net" git tree where this patch
> > is included.
> > Starting from 0:00 CET
> > :)
> >
> >
> Upgraded and looks like problem is not solved with that patch
> Currently running system with
> https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git/
> kernel
>
> Still about 0.5GB of memory is leaking somewhere
>
> Also can confirm that the latest kernel where memory is not leaking (with
> use i40e driver intel 710 cards) is 4.11.12
> With kernel 4.11.12 - after hour no change in memory usage.
>
> also checked that with ixgbe instead of i40e with same net.git kernel there
> is no memleak - after hour same memory usage - so for 100% this is i40e
> driver problem.
I have (probably) the same problem here but with X520 cards: booting
4.12.x gives me oops after circa 20 minutes of our workload. Booting
4.9.y is OK. This machine is in production so any testing is very
limited.
Machine was stable for >2 months (on the desk before got to
production) with 4.12.8 but with no traffic on X520 cards.
Cheers,
Vita
^ permalink raw reply
* Re: [PATCH] can: check for null sk before deferencing it via the call to sock_net
From: Marc Kleine-Budde @ 2017-10-17 5:49 UTC (permalink / raw)
To: Colin King, Oliver Hartkopp, David S . Miller, linux-can, netdev
Cc: kernel-janitors, linux-kernel
In-Reply-To: <20170908150235.2931-1-colin.king@canonical.com>
[-- Attachment #1.1: Type: text/plain, Size: 950 bytes --]
On 09/08/2017 05:02 PM, Colin King wrote:
> From: Colin Ian King <colin.king@canonical.com>
>
> The assignment of net via call sock_net will dereference sk. This
> is performed before a sanity null check on sk, so there could be
> a potential null dereference on the sock_net call if sk is null.
> Fix this by assigning net after the sk null check. Also replace
> the sk == NULL with the more usual !sk idiom.
>
> Detected by CoverityScan CID#1431862 ("Dereference before null check")
>
> Fixes: 384317ef4187 ("can: network namespace support for CAN_BCM protocol")
> Signed-off-by: Colin Ian King <colin.king@canonical.com>
Applied to can.
Tnx,
Marc
--
Pengutronix e.K. | Marc Kleine-Budde |
Industrial Linux Solutions | Phone: +49-231-2826-924 |
Vertretung West/Dortmund | Fax: +49-5121-206917-5555 |
Amtsgericht Hildesheim, HRA 2686 | http://www.pengutronix.de |
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* Re: pull-request: mac80211 2017-10-16
From: Johannes Berg @ 2017-10-17 5:46 UTC (permalink / raw)
To: Jason A. Donenfeld
Cc: David Miller, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-wireless-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <CAHmME9rHMMAgJs3uQYpt15V8eh-PjDqioqURA3KPKEhc2a9OEg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Tue, 2017-10-17 at 01:30 +0200, Jason A. Donenfeld wrote:
> Mobile phone right now, so not able to write patch, but you probably
> should be using crypto_memneq for comparing those two keys, not
> memcmp.
I know that's a gut instinct, but I really don't see the point.
If you actually get this to evaluate to "equal", you're already being
attacked, and the attacker already knows they're trying to get the same
key to be installed again. If it's not equal, you execute so much code
beneath, going to the driver etc., that I'd think this particular time
is in the noise.
Also, this isn't something that the attacker can directly observe
anyway, and if they can, then surely the fact that we *skip* a large
amount of code when returning 0 is also observable.
Besides, the only thing that can observe the timing is hostapd or
wpa_supplicant, which obviously know the key (and in the fixed versions
will already have done the comparison themselves).
And lastly, if you wanted to use this as an oracle to get the key back
from the kernel, then you already have admin permissions (in your
network namespace), and can just sniff netlink traffic anyway.
johannes
^ permalink raw reply
* [PATCH net] sock_diag: request _diag module only when the family or proto has been registered
From: Xin Long @ 2017-10-17 5:13 UTC (permalink / raw)
To: network dev; +Cc: davem, Marcelo Ricardo Leitner, Sabrina Dubroca
Now when using 'ss' in iproute, kernel would try to load all _diag
modules. It causes the corresponding family or proto modules to be
loaded as well.
Like after 'ss -a', sctp, dccp, af_packet(if it works as a moudle)
will be loaded.
As these family or proto modules are loaded unexpectly, this might
have some security implications.
This patch is to introduce sock_diag_request_module() in which we
only request the _diag module when it's corresponding family or
proto has been registered.
Note that we can't just load _diag module without the family or
proto loaded, as some symbols in _diag module are from the family
or proto moudle.
Reported-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
include/linux/net.h | 1 +
include/linux/sock_diag.h | 1 +
net/core/sock_diag.c | 32 ++++++++++++++++++++++++--------
net/ipv4/inet_diag.c | 3 +--
net/socket.c | 5 +++++
5 files changed, 32 insertions(+), 10 deletions(-)
diff --git a/include/linux/net.h b/include/linux/net.h
index d97d80d..6c7cf09 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -225,6 +225,7 @@ enum {
int sock_wake_async(struct socket_wq *sk_wq, int how, int band);
int sock_register(const struct net_proto_family *fam);
void sock_unregister(int family);
+bool sock_is_registered(int family);
int __sock_create(struct net *net, int family, int type, int proto,
struct socket **res, int kern);
int sock_create(int family, int type, int proto, struct socket **res);
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
index a2f8109..e9a1b8d 100644
--- a/include/linux/sock_diag.h
+++ b/include/linux/sock_diag.h
@@ -77,4 +77,5 @@ bool sock_diag_has_destroy_listeners(const struct sock *sk)
void sock_diag_broadcast_destroy(struct sock *sk);
int sock_diag_destroy(struct sock *sk, int err);
+int sock_diag_request_module(int family, int protocol);
#endif
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 217f4e3..caad6b6 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -7,6 +7,7 @@
#include <net/net_namespace.h>
#include <linux/module.h>
#include <net/sock.h>
+#include <net/protocol.h>
#include <linux/kernel.h>
#include <linux/tcp.h>
#include <linux/workqueue.h>
@@ -207,6 +208,25 @@ void sock_diag_unregister(const struct sock_diag_handler *hnld)
}
EXPORT_SYMBOL_GPL(sock_diag_unregister);
+int sock_diag_request_module(int family, int protocol)
+{
+ if (!protocol) {
+ if (!sock_is_registered(family))
+ return -ENOENT;
+
+ return request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
+ NETLINK_SOCK_DIAG, family);
+ }
+
+ if (family == AF_INET &&
+ !rcu_access_pointer(inet_protos[protocol]))
+ return -ENOENT;
+
+ return request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK,
+ NETLINK_SOCK_DIAG, family, protocol);
+}
+EXPORT_SYMBOL_GPL(sock_diag_request_module);
+
static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh)
{
int err;
@@ -220,8 +240,7 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh)
return -EINVAL;
if (sock_diag_handlers[req->sdiag_family] == NULL)
- request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
- NETLINK_SOCK_DIAG, req->sdiag_family);
+ sock_diag_request_module(req->sdiag_family, 0);
mutex_lock(&sock_diag_table_mutex);
hndl = sock_diag_handlers[req->sdiag_family];
@@ -247,8 +266,7 @@ static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
case TCPDIAG_GETSOCK:
case DCCPDIAG_GETSOCK:
if (inet_rcv_compat == NULL)
- request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
- NETLINK_SOCK_DIAG, AF_INET);
+ sock_diag_request_module(AF_INET, 0);
mutex_lock(&sock_diag_table_mutex);
if (inet_rcv_compat != NULL)
@@ -281,14 +299,12 @@ static int sock_diag_bind(struct net *net, int group)
case SKNLGRP_INET_TCP_DESTROY:
case SKNLGRP_INET_UDP_DESTROY:
if (!sock_diag_handlers[AF_INET])
- request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
- NETLINK_SOCK_DIAG, AF_INET);
+ sock_diag_request_module(AF_INET, 0);
break;
case SKNLGRP_INET6_TCP_DESTROY:
case SKNLGRP_INET6_UDP_DESTROY:
if (!sock_diag_handlers[AF_INET6])
- request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
- NETLINK_SOCK_DIAG, AF_INET);
+ sock_diag_request_module(AF_INET, 0);
break;
}
return 0;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index c9c35b6..d10c8fa 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -53,8 +53,7 @@ static DEFINE_MUTEX(inet_diag_table_mutex);
static const struct inet_diag_handler *inet_diag_lock_handler(int proto)
{
if (!inet_diag_table[proto])
- request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK,
- NETLINK_SOCK_DIAG, AF_INET, proto);
+ sock_diag_request_module(AF_INET, proto);
mutex_lock(&inet_diag_table_mutex);
if (!inet_diag_table[proto])
diff --git a/net/socket.c b/net/socket.c
index c729625..733d657 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2590,6 +2590,11 @@ void sock_unregister(int family)
}
EXPORT_SYMBOL(sock_unregister);
+bool sock_is_registered(int family)
+{
+ return family < NPROTO && rcu_access_pointer(net_families[family]);
+}
+
static int __init sock_init(void)
{
int err;
--
2.1.0
^ permalink raw reply related
* Re: [PATCH] bpf: devmap: Check attr->max_entries more carefully
From: John Fastabend @ 2017-10-17 4:30 UTC (permalink / raw)
To: Richard Weinberger, netdev; +Cc: linux-kernel, daniel, ast, sp3485
In-Reply-To: <100542240.i6NpMmsy5C@blindfold>
On 10/15/2017 03:13 PM, Richard Weinberger wrote:
> Am Montag, 16. Oktober 2017, 00:00:20 CEST schrieb Richard Weinberger:
>> max_entries is user controlled and used as input for __alloc_percpu().
>> This function expects that the allocation size is a power of two and
>> less than PCPU_MIN_UNIT_SIZE.
>> Otherwise a WARN() is triggered.
>
> On a second though, I think we should also have a hard limit for ->max_entries
> or check for an overflow here:
>
Or just,
static u64 dev_map_bitmap_size(const union bpf_attr *attr)
{
return BITS_TO_LONGS((u64) attr->max_entries) *
sizeof(unsigned long);
}
Let me know if you want me to send a patch or if you want to.
Thanks,
John
> static u64 dev_map_bitmap_size(const union bpf_attr *attr)
> {
> return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
> }
>
> Thanks,
> //richard
>
^ permalink raw reply
* Re: [PATCH net-next] tcp: Check daddr_cache before use in tracepoint
From: Eric Dumazet @ 2017-10-17 3:45 UTC (permalink / raw)
To: David Ahern; +Cc: netdev, xiyou.wangcong
In-Reply-To: <1508189387-27931-1-git-send-email-dsahern@gmail.com>
On Mon, 2017-10-16 at 14:29 -0700, David Ahern wrote:
> Running perf in one window to capture tcp_retransmit_skb tracepoint:
> $ perf record -e tcp:tcp_retransmit_skb -a
>
> And causing a retransmission on an active TCP session (e.g., dropping
> packets in the receiver, changing MTU on the interface to 500 and back
> to 1500) triggers a panic:
...
> Check that daddr_cache is non-NULL before de-referencing.
>
> Fixes: e086101b150a ("tcp: add a tracepoint for tcp retransmission")
> Signed-off-by: David Ahern <dsahern@gmail.com>
> ---
> include/trace/events/tcp.h | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
> index 3d1cbd072b7e..13e8ee8af2c8 100644
> --- a/include/trace/events/tcp.h
> +++ b/include/trace/events/tcp.h
> @@ -48,7 +48,8 @@ TRACE_EVENT(tcp_retransmit_skb,
> pin6 = (struct in6_addr *)__entry->saddr_v6;
> *pin6 = np->saddr;
> pin6 = (struct in6_addr *)__entry->daddr_v6;
> - *pin6 = *(np->daddr_cache);
> + if (np->daddr_cache)
> + *pin6 = *(np->daddr_cache);
> } else {
> pin6 = (struct in6_addr *)__entry->saddr_v6;
> ipv6_addr_set_v4mapped(inet->inet_saddr, pin6);
This is weird.
IPV6 TCP uses sk->sk_v6_daddr and sk->->sk_v6_rcv_saddr
So I would rather remove the need to fetch np = inet6_sk(sk) in the
first place, and look at sk->sk_family instead.
No need to get to np at all.
^ 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