For more information, please see the manpage (man batctl).
-batctl is available on http://www.open-mesh.org/
+batctl is available on https://www.open-mesh.org/
CONTACT
M: Simon Wunderlich <sw@simonwunderlich.de>
M: Antonio Quartulli <a@unstable.cc>
L: b.a.t.m.a.n@lists.open-mesh.org
-W: http://www.open-mesh.org/
+W: https://www.open-mesh.org/
S: Maintained
F: net/batman-adv/
return retval;
}
+static void __ad_actor_update_port(struct port *port)
+{
+ const struct bonding *bond = bond_get_bond_by_slave(port->slave);
+
+ port->actor_system = BOND_AD_INFO(bond).system.sys_mac_addr;
+ port->actor_system_priority = BOND_AD_INFO(bond).system.sys_priority;
+}
+
/* Conversions */
/**
port->actor_admin_port_key = bond->params.ad_user_port_key << 6;
ad_update_actor_keys(port, false);
/* actor system is the bond's system */
- port->actor_system = BOND_AD_INFO(bond).system.sys_mac_addr;
- port->actor_system_priority =
- BOND_AD_INFO(bond).system.sys_priority;
+ __ad_actor_update_port(port);
/* tx timer(to verify that no more than MAX_TX_IN_SECOND
* lacpdu's are sent in one second)
*/
spin_unlock_bh(&bond->mode_lock);
}
+/**
+ * bond_3ad_update_ad_actor_settings - reflect change of actor settings to ports
+ * @bond: bonding struct to work on
+ *
+ * If an ad_actor setting gets changed we need to update the individual port
+ * settings so the bond device will use the new values when it gets upped.
+ */
+void bond_3ad_update_ad_actor_settings(struct bonding *bond)
+{
+ struct list_head *iter;
+ struct slave *slave;
+
+ ASSERT_RTNL();
+
+ BOND_AD_INFO(bond).system.sys_priority = bond->params.ad_actor_sys_prio;
+ if (is_zero_ether_addr(bond->params.ad_actor_system))
+ BOND_AD_INFO(bond).system.sys_mac_addr =
+ *((struct mac_addr *)bond->dev->dev_addr);
+ else
+ BOND_AD_INFO(bond).system.sys_mac_addr =
+ *((struct mac_addr *)bond->params.ad_actor_system);
+
+ spin_lock_bh(&bond->mode_lock);
+ bond_for_each_slave(bond, slave, iter)
+ __ad_actor_update_port(&(SLAVE_AD_INFO(slave)->port));
+ spin_unlock_bh(&bond->mode_lock);
+}
+
/**
* bond_3ad_state_machine_handler - handle state machines timeout
* @bond: bonding struct to work on
static void bond_set_dev_addr(struct net_device *bond_dev,
struct net_device *slave_dev)
{
- netdev_dbg(bond_dev, "bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n",
- bond_dev, slave_dev, slave_dev->addr_len);
+ netdev_dbg(bond_dev, "bond_dev=%p slave_dev=%p slave_dev->name=%s slave_dev->addr_len=%d\n",
+ bond_dev, slave_dev, slave_dev->name, slave_dev->addr_len);
memcpy(bond_dev->dev_addr, slave_dev->dev_addr, slave_dev->addr_len);
bond_dev->addr_assign_type = NET_ADDR_STOLEN;
call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
if (!rv)
return;
- if (netif_carrier_ok(bond->dev)) {
+ if (netif_carrier_ok(bond->dev))
netdev_info(bond->dev, "first active interface up!\n");
- } else {
+ else
netdev_info(bond->dev, "now running without any active interface!\n");
- }
}
}
}
}
- if (bond_should_deliver_exact_match(skb, slave, bond)) {
+ if (bond_should_deliver_exact_match(skb, slave, bond))
return RX_HANDLER_EXACT;
- }
skb->dev = bond->dev;
{
struct slave *slave = NULL;
- slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
+ slave = kzalloc(sizeof(*slave), GFP_KERNEL);
if (!slave)
return NULL;
stats->rx_bytes += sstats->rx_bytes - pstats->rx_bytes;
stats->rx_errors += sstats->rx_errors - pstats->rx_errors;
stats->rx_dropped += sstats->rx_dropped - pstats->rx_dropped;
+ stats->rx_nohandler += sstats->rx_nohandler - pstats->rx_nohandler;
stats->tx_packets += sstats->tx_packets - pstats->tx_packets;;
stats->tx_bytes += sstats->tx_bytes - pstats->tx_bytes;
newval->value);
bond->params.ad_actor_sys_prio = newval->value;
+ bond_3ad_update_ad_actor_settings(bond);
+
return 0;
}
netdev_info(bond->dev, "Setting ad_actor_system to %pM\n", mac);
ether_addr_copy(bond->params.ad_actor_system, mac);
+ bond_3ad_update_ad_actor_settings(bond);
+
return 0;
err:
};
MODULE_DEVICE_TABLE(bcma, bgmac_bcma_tbl);
+static inline bool bgmac_is_bcm4707_family(struct bgmac *bgmac)
+{
+ switch (bgmac->core->bus->chipinfo.id) {
+ case BCMA_CHIP_ID_BCM4707:
+ case BCMA_CHIP_ID_BCM53018:
+ return true;
+ default:
+ return false;
+ }
+}
+
static bool bgmac_wait_value(struct bcma_device *core, u16 reg, u32 mask,
u32 value, int timeout)
{
static void bgmac_miiconfig(struct bgmac *bgmac)
{
struct bcma_device *core = bgmac->core;
- struct bcma_chipinfo *ci = &core->bus->chipinfo;
u8 imode;
- if (ci->id == BCMA_CHIP_ID_BCM4707 ||
- ci->id == BCMA_CHIP_ID_BCM53018) {
+ if (bgmac_is_bcm4707_family(bgmac)) {
bcma_awrite32(core, BCMA_IOCTL,
bcma_aread32(core, BCMA_IOCTL) | 0x40 |
BGMAC_BCMA_IOCTL_SW_CLKEN);
}
/* Request Misc PLL for corerev > 2 */
- if (core->id.rev > 2 &&
- ci->id != BCMA_CHIP_ID_BCM4707 &&
- ci->id != BCMA_CHIP_ID_BCM53018) {
+ if (core->id.rev > 2 && !bgmac_is_bcm4707_family(bgmac)) {
bgmac_set(bgmac, BCMA_CLKCTLST,
BGMAC_BCMA_CLKCTLST_MISC_PLL_REQ);
bgmac_wait_value(bgmac->core, BCMA_CLKCTLST,
break;
}
- if (ci->id != BCMA_CHIP_ID_BCM4707 &&
- ci->id != BCMA_CHIP_ID_BCM53018) {
+ if (!bgmac_is_bcm4707_family(bgmac)) {
rxq_ctl = bgmac_read(bgmac, BGMAC_RXQ_CTL);
rxq_ctl &= ~BGMAC_RXQ_CTL_MDP_MASK;
bp_clk = bcma_pmu_get_bus_clock(&bgmac->core->bus->drv_cc) /
static int bgmac_mii_register(struct bgmac *bgmac)
{
- struct bcma_chipinfo *ci = &bgmac->core->bus->chipinfo;
struct mii_bus *mii_bus;
struct phy_device *phy_dev;
char bus_id[MII_BUS_ID_SIZE + 3];
int err = 0;
- if (ci->id == BCMA_CHIP_ID_BCM4707 ||
- ci->id == BCMA_CHIP_ID_BCM53018)
+ if (bgmac_is_bcm4707_family(bgmac))
return bgmac_fixed_phy_register(bgmac);
mii_bus = mdiobus_alloc();
/* http://bcm-v4.sipsolutions.net/mac-gbit/gmac/chipattach */
static int bgmac_probe(struct bcma_device *core)
{
- struct bcma_chipinfo *ci = &core->bus->chipinfo;
struct net_device *net_dev;
struct bgmac *bgmac;
struct ssb_sprom *sprom = &core->bus->sprom;
bgmac_chip_reset(bgmac);
/* For Northstar, we have to take all GMAC core out of reset */
- if (ci->id == BCMA_CHIP_ID_BCM4707 ||
- ci->id == BCMA_CHIP_ID_BCM53018) {
+ if (bgmac_is_bcm4707_family(bgmac)) {
struct bcma_device *ns_core;
int ns_gmac;
#define BE3_MAX_TX_QS 16
#define BE3_MAX_EVT_QS 16
#define BE3_SRIOV_MAX_EVT_QS 8
+#define SH_VF_MAX_NIC_EQS 3 /* Skyhawk VFs can have a max of 4 EQs
+ * and at least 1 is granted to either
+ * SURF/DPDK
+ */
#define MAX_RSS_IFACES 15
#define MAX_RX_QS 32
#define BE_UC_PMAC_COUNT 30
#define BE_VF_UC_PMAC_COUNT 2
+#define MAX_ERR_RECOVERY_RETRY_COUNT 3
+#define ERR_DETECTION_DELAY 1000
+#define ERR_RECOVERY_RETRY_DELAY 30000
+
/* Ethtool set_dump flags */
#define LANCER_INITIATE_FW_DUMP 0x1
#define LANCER_DELETE_FW_DUMP 0x2
u16 work_counter;
struct delayed_work be_err_detection_work;
+ u8 recovery_retries;
u8 err_flags;
u32 flags;
u32 cmd_privileges;
CMD_SUBSYSTEM_COMMON,
BE_PRIV_LNKMGMT | BE_PRIV_VHADM |
BE_PRIV_DEVCFG | BE_PRIV_DEVSEC
- }
+ },
+ {
+ OPCODE_LOWLEVEL_HOST_DDR_DMA,
+ CMD_SUBSYSTEM_LOWLEVEL,
+ BE_PRIV_DEVCFG | BE_PRIV_DEVSEC
+ },
+ {
+ OPCODE_LOWLEVEL_LOOPBACK_TEST,
+ CMD_SUBSYSTEM_LOWLEVEL,
+ BE_PRIV_DEVCFG | BE_PRIV_DEVSEC
+ },
+ {
+ OPCODE_LOWLEVEL_SET_LOOPBACK_MODE,
+ CMD_SUBSYSTEM_LOWLEVEL,
+ BE_PRIV_DEVCFG | BE_PRIV_DEVSEC
+ },
};
static bool be_cmd_allowed(struct be_adapter *adapter, u8 opcode, u8 subsystem)
if (base_status != MCC_STATUS_SUCCESS &&
!be_skip_err_log(opcode, base_status, addl_status)) {
- if (base_status == MCC_STATUS_UNAUTHORIZED_REQUEST) {
+ if (base_status == MCC_STATUS_UNAUTHORIZED_REQUEST ||
+ addl_status == MCC_ADDL_STATUS_INSUFFICIENT_PRIVILEGES) {
dev_warn(&adapter->pdev->dev,
"VF is not privileged to issue opcode %d-%d\n",
opcode, subsystem);
struct be_cmd_req_set_lmode *req;
int status;
+ if (!be_cmd_allowed(adapter, OPCODE_LOWLEVEL_SET_LOOPBACK_MODE,
+ CMD_SUBSYSTEM_LOWLEVEL))
+ return -EPERM;
+
spin_lock_bh(&adapter->mcc_lock);
wrb = wrb_from_mccq(adapter);
struct be_cmd_resp_loopback_test *resp;
int status;
+ if (!be_cmd_allowed(adapter, OPCODE_LOWLEVEL_LOOPBACK_TEST,
+ CMD_SUBSYSTEM_LOWLEVEL))
+ return -EPERM;
+
spin_lock_bh(&adapter->mcc_lock);
wrb = wrb_from_mccq(adapter);
int status;
int i, j = 0;
+ if (!be_cmd_allowed(adapter, OPCODE_LOWLEVEL_HOST_DDR_DMA,
+ CMD_SUBSYSTEM_LOWLEVEL))
+ return -EPERM;
+
spin_lock_bh(&adapter->mcc_lock);
wrb = wrb_from_mccq(adapter);
MCC_ADDL_STATUS_TOO_MANY_INTERFACES = 0x4a,
MCC_ADDL_STATUS_INSUFFICIENT_VLANS = 0xab,
MCC_ADDL_STATUS_INVALID_SIGNATURE = 0x56,
- MCC_ADDL_STATUS_MISSING_SIGNATURE = 0x57
+ MCC_ADDL_STATUS_MISSING_SIGNATURE = 0x57,
+ MCC_ADDL_STATUS_INSUFFICIENT_PRIVILEGES = 0x60
};
#define CQE_BASE_STATUS_MASK 0xFFFF
enum ethtool_phys_id_state state)
{
struct be_adapter *adapter = netdev_priv(netdev);
+ int status = 0;
switch (state) {
case ETHTOOL_ID_ACTIVE:
- be_cmd_get_beacon_state(adapter, adapter->hba_port_num,
- &adapter->beacon_state);
- return 1; /* cycle on/off once per second */
+ status = be_cmd_get_beacon_state(adapter, adapter->hba_port_num,
+ &adapter->beacon_state);
+ if (status)
+ return be_cmd_status(status);
+ return 1; /* cycle on/off once per second */
case ETHTOOL_ID_ON:
- be_cmd_set_beacon_state(adapter, adapter->hba_port_num, 0, 0,
- BEACON_STATE_ENABLED);
+ status = be_cmd_set_beacon_state(adapter, adapter->hba_port_num,
+ 0, 0, BEACON_STATE_ENABLED);
break;
case ETHTOOL_ID_OFF:
- be_cmd_set_beacon_state(adapter, adapter->hba_port_num, 0, 0,
- BEACON_STATE_DISABLED);
+ status = be_cmd_set_beacon_state(adapter, adapter->hba_port_num,
+ 0, 0, BEACON_STATE_DISABLED);
break;
case ETHTOOL_ID_INACTIVE:
- be_cmd_set_beacon_state(adapter, adapter->hba_port_num, 0, 0,
- adapter->beacon_state);
+ status = be_cmd_set_beacon_state(adapter, adapter->hba_port_num,
+ 0, 0, adapter->beacon_state);
}
- return 0;
+ return be_cmd_status(status);
}
static int be_set_dump(struct net_device *netdev, struct ethtool_dump *dump)
if (lancer_chip(adapter) && vid == 0)
return 0;
+ if (!test_bit(vid, adapter->vids))
+ return 0;
+
clear_bit(vid, adapter->vids);
adapter->vlans_added--;
if (!aic->enable)
return 0;
- if (time_before_eq(now, aic->jiffies) ||
- jiffies_to_msecs(now - aic->jiffies) < 1)
+ if (jiffies_to_msecs(now - aic->jiffies) < 1)
eqd = aic->prev_eqd;
else
eqd = be_get_new_eqd(eqo);
struct be_resources res = adapter->pool_res;
u16 num_vf_qs = 1;
- /* Distribute the queue resources equally among the PF and it's VFs
+ /* Distribute the queue resources among the PF and it's VFs
* Do not distribute queue resources in multi-channel configuration.
*/
if (num_vfs && !be_is_mc(adapter)) {
- /* If number of VFs requested is 8 less than max supported,
- * assign 8 queue pairs to the PF and divide the remaining
- * resources evenly among the VFs
- */
- if (num_vfs < (be_max_vfs(adapter) - 8))
- num_vf_qs = (res.max_rss_qs - 8) / num_vfs;
- else
- num_vf_qs = res.max_rss_qs / num_vfs;
+ /* Divide the qpairs evenly among the VFs and the PF, capped
+ * at VF-EQ-count. Any remainder qpairs belong to the PF.
+ */
+ num_vf_qs = min(SH_VF_MAX_NIC_EQS,
+ res.max_rss_qs / (num_vfs + 1));
/* Skyhawk-R chip supports only MAX_RSS_IFACES RSS capable
* interfaces per port. Provide RSS on VFs, only if number
adapter->flags |= BE_FLAGS_WORKER_SCHEDULED;
}
-static void be_schedule_err_detection(struct be_adapter *adapter)
+static void be_schedule_err_detection(struct be_adapter *adapter, u32 delay)
{
schedule_delayed_work(&adapter->be_err_detection_work,
- msecs_to_jiffies(1000));
+ msecs_to_jiffies(delay));
adapter->flags |= BE_FLAGS_ERR_DETECTION_SCHEDULED;
}
static int be_err_recover(struct be_adapter *adapter)
{
- struct device *dev = &adapter->pdev->dev;
int status;
+ /* Error recovery is supported only Lancer as of now */
+ if (!lancer_chip(adapter))
+ return -EIO;
+
+ /* Wait for adapter to reach quiescent state before
+ * destroying queues
+ */
+ status = be_fw_wait_ready(adapter);
+ if (status)
+ goto err;
+
+ be_cleanup(adapter);
+
status = be_resume(adapter);
if (status)
goto err;
- dev_info(dev, "Adapter recovery successful\n");
return 0;
err:
- if (be_physfn(adapter))
- dev_err(dev, "Adapter recovery failed\n");
- else
- dev_err(dev, "Re-trying adapter recovery\n");
-
return status;
}
struct be_adapter *adapter =
container_of(work, struct be_adapter,
be_err_detection_work.work);
- int status = 0;
+ struct device *dev = &adapter->pdev->dev;
+ int recovery_status;
+ int delay = ERR_DETECTION_DELAY;
be_detect_error(adapter);
- if (be_check_error(adapter, BE_ERROR_HW)) {
- be_cleanup(adapter);
-
- /* As of now error recovery support is in Lancer only */
- if (lancer_chip(adapter))
- status = be_err_recover(adapter);
+ if (be_check_error(adapter, BE_ERROR_HW))
+ recovery_status = be_err_recover(adapter);
+ else
+ goto reschedule_task;
+
+ if (!recovery_status) {
+ adapter->recovery_retries = 0;
+ dev_info(dev, "Adapter recovery successful\n");
+ goto reschedule_task;
+ } else if (be_virtfn(adapter)) {
+ /* For VFs, check if PF have allocated resources
+ * every second.
+ */
+ dev_err(dev, "Re-trying adapter recovery\n");
+ goto reschedule_task;
+ } else if (adapter->recovery_retries++ <
+ MAX_ERR_RECOVERY_RETRY_COUNT) {
+ /* In case of another error during recovery, it takes 30 sec
+ * for adapter to come out of error. Retry error recovery after
+ * this time interval.
+ */
+ dev_err(&adapter->pdev->dev, "Re-trying adapter recovery\n");
+ delay = ERR_RECOVERY_RETRY_DELAY;
+ goto reschedule_task;
+ } else {
+ dev_err(dev, "Adapter recovery failed\n");
}
- /* Always attempt recovery on VFs */
- if (!status || be_virtfn(adapter))
- be_schedule_err_detection(adapter);
+ return;
+reschedule_task:
+ be_schedule_err_detection(adapter, delay);
}
static void be_log_sfp_info(struct be_adapter *adapter)
be_roce_dev_add(adapter);
- be_schedule_err_detection(adapter);
+ be_schedule_err_detection(adapter, ERR_DETECTION_DELAY);
/* On Die temperature not supported for VF. */
if (be_physfn(adapter) && IS_ENABLED(CONFIG_BE2NET_HWMON)) {
if (status)
return status;
- be_schedule_err_detection(adapter);
+ be_schedule_err_detection(adapter, ERR_DETECTION_DELAY);
if (adapter->wol_en)
be_setup_wol(adapter, false);
if (status)
goto err;
- be_schedule_err_detection(adapter);
+ be_schedule_err_detection(adapter, ERR_DETECTION_DELAY);
return;
err:
dev_err(&adapter->pdev->dev, "EEH resume failed\n");
#define I40E_FLAG_VEB_MODE_ENABLED BIT_ULL(40)
#define I40E_FLAG_GENEVE_OFFLOAD_CAPABLE BIT_ULL(41)
#define I40E_FLAG_NO_PCI_LINK_CHECK BIT_ULL(42)
+#define I40E_FLAG_100M_SGMII_CAPABLE BIT_ULL(43)
+#define I40E_FLAG_RESTART_AUTONEG BIT_ULL(44)
#define I40E_FLAG_PF_MAC BIT_ULL(50)
/* tracks features that get auto disabled by errors */
i40e_aqc_opc_get_phy_wol_caps = 0x0621,
i40e_aqc_opc_set_phy_debug = 0x0622,
i40e_aqc_opc_upload_ext_phy_fm = 0x0625,
+ i40e_aqc_opc_run_phy_activity = 0x0626,
/* NVM commands */
i40e_aqc_opc_nvm_read = 0x0701,
#define I40E_AQ_CAP_ID_OS2BMC_CAP 0x0004
#define I40E_AQ_CAP_ID_FUNCTIONS_VALID 0x0005
#define I40E_AQ_CAP_ID_ALTERNATE_RAM 0x0006
+#define I40E_AQ_CAP_ID_WOL_AND_PROXY 0x0008
#define I40E_AQ_CAP_ID_SRIOV 0x0012
#define I40E_AQ_CAP_ID_VF 0x0013
#define I40E_AQ_CAP_ID_VMDQ 0x0014
#define I40E_AQ_CAP_ID_LED 0x0061
#define I40E_AQ_CAP_ID_SDP 0x0062
#define I40E_AQ_CAP_ID_MDIO 0x0063
+#define I40E_AQ_CAP_ID_WSR_PROT 0x0064
#define I40E_AQ_CAP_ID_FLEX10 0x00F1
#define I40E_AQ_CAP_ID_CEM 0x00F2
#define I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT 9
#define I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK 0x1E00
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_XVLAN 0
+#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN 0
#define I40E_AQC_ADD_CLOUD_TNL_TYPE_NVGRE_OMAC 1
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_NGE 2
+#define I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE 2
#define I40E_AQC_ADD_CLOUD_TNL_TYPE_IP 3
__le32 tenant_id;
u8 config;
#define I40E_AQ_CONFIG_CRC_ENA 0x04
#define I40E_AQ_CONFIG_PACING_MASK 0x78
- u8 reserved[5];
+ u8 external_power_ability;
+#define I40E_AQ_LINK_POWER_CLASS_1 0x00
+#define I40E_AQ_LINK_POWER_CLASS_2 0x01
+#define I40E_AQ_LINK_POWER_CLASS_3 0x02
+#define I40E_AQ_LINK_POWER_CLASS_4 0x03
+ u8 reserved[4];
};
I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status);
I40E_AQC_PHY_REG_EXERNAL_MODULE = 0x3
};
+/* Run PHY Activity (0x0626) */
+struct i40e_aqc_run_phy_activity {
+ __le16 activity_id;
+ u8 flags;
+ u8 reserved1;
+ __le32 control;
+ __le32 data;
+ u8 reserved2[4];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity);
+
/* NVM Read command (indirect 0x0701)
* NVM Erase commands (direct 0x0702)
* NVM Update commands (indirect 0x0703)
case I40E_DEV_ID_20G_KR2_A:
hw->mac.type = I40E_MAC_XL710;
break;
+ case I40E_DEV_ID_KX_X722:
+ case I40E_DEV_ID_QSFP_X722:
case I40E_DEV_ID_SFP_X722:
case I40E_DEV_ID_1G_BASE_T_X722:
case I40E_DEV_ID_10G_BASE_T_X722:
return status;
}
-#define I40E_DEV_FUNC_CAP_SWITCH_MODE 0x01
-#define I40E_DEV_FUNC_CAP_MGMT_MODE 0x02
-#define I40E_DEV_FUNC_CAP_NPAR 0x03
-#define I40E_DEV_FUNC_CAP_OS2BMC 0x04
-#define I40E_DEV_FUNC_CAP_VALID_FUNC 0x05
-#define I40E_DEV_FUNC_CAP_SRIOV_1_1 0x12
-#define I40E_DEV_FUNC_CAP_VF 0x13
-#define I40E_DEV_FUNC_CAP_VMDQ 0x14
-#define I40E_DEV_FUNC_CAP_802_1_QBG 0x15
-#define I40E_DEV_FUNC_CAP_802_1_QBH 0x16
-#define I40E_DEV_FUNC_CAP_VSI 0x17
-#define I40E_DEV_FUNC_CAP_DCB 0x18
-#define I40E_DEV_FUNC_CAP_FCOE 0x21
-#define I40E_DEV_FUNC_CAP_ISCSI 0x22
-#define I40E_DEV_FUNC_CAP_RSS 0x40
-#define I40E_DEV_FUNC_CAP_RX_QUEUES 0x41
-#define I40E_DEV_FUNC_CAP_TX_QUEUES 0x42
-#define I40E_DEV_FUNC_CAP_MSIX 0x43
-#define I40E_DEV_FUNC_CAP_MSIX_VF 0x44
-#define I40E_DEV_FUNC_CAP_FLOW_DIRECTOR 0x45
-#define I40E_DEV_FUNC_CAP_IEEE_1588 0x46
-#define I40E_DEV_FUNC_CAP_FLEX10 0xF1
-#define I40E_DEV_FUNC_CAP_CEM 0xF2
-#define I40E_DEV_FUNC_CAP_IWARP 0x51
-#define I40E_DEV_FUNC_CAP_LED 0x61
-#define I40E_DEV_FUNC_CAP_SDP 0x62
-#define I40E_DEV_FUNC_CAP_MDIO 0x63
-#define I40E_DEV_FUNC_CAP_WR_CSR_PROT 0x64
-
/**
* i40e_parse_discover_capabilities
* @hw: pointer to the hw struct
major_rev = cap->major_rev;
switch (id) {
- case I40E_DEV_FUNC_CAP_SWITCH_MODE:
+ case I40E_AQ_CAP_ID_SWITCH_MODE:
p->switch_mode = number;
break;
- case I40E_DEV_FUNC_CAP_MGMT_MODE:
+ case I40E_AQ_CAP_ID_MNG_MODE:
p->management_mode = number;
break;
- case I40E_DEV_FUNC_CAP_NPAR:
+ case I40E_AQ_CAP_ID_NPAR_ACTIVE:
p->npar_enable = number;
break;
- case I40E_DEV_FUNC_CAP_OS2BMC:
+ case I40E_AQ_CAP_ID_OS2BMC_CAP:
p->os2bmc = number;
break;
- case I40E_DEV_FUNC_CAP_VALID_FUNC:
+ case I40E_AQ_CAP_ID_FUNCTIONS_VALID:
p->valid_functions = number;
break;
- case I40E_DEV_FUNC_CAP_SRIOV_1_1:
+ case I40E_AQ_CAP_ID_SRIOV:
if (number == 1)
p->sr_iov_1_1 = true;
break;
- case I40E_DEV_FUNC_CAP_VF:
+ case I40E_AQ_CAP_ID_VF:
p->num_vfs = number;
p->vf_base_id = logical_id;
break;
- case I40E_DEV_FUNC_CAP_VMDQ:
+ case I40E_AQ_CAP_ID_VMDQ:
if (number == 1)
p->vmdq = true;
break;
- case I40E_DEV_FUNC_CAP_802_1_QBG:
+ case I40E_AQ_CAP_ID_8021QBG:
if (number == 1)
p->evb_802_1_qbg = true;
break;
- case I40E_DEV_FUNC_CAP_802_1_QBH:
+ case I40E_AQ_CAP_ID_8021QBR:
if (number == 1)
p->evb_802_1_qbh = true;
break;
- case I40E_DEV_FUNC_CAP_VSI:
+ case I40E_AQ_CAP_ID_VSI:
p->num_vsis = number;
break;
- case I40E_DEV_FUNC_CAP_DCB:
+ case I40E_AQ_CAP_ID_DCB:
if (number == 1) {
p->dcb = true;
p->enabled_tcmap = logical_id;
p->maxtc = phys_id;
}
break;
- case I40E_DEV_FUNC_CAP_FCOE:
+ case I40E_AQ_CAP_ID_FCOE:
if (number == 1)
p->fcoe = true;
break;
- case I40E_DEV_FUNC_CAP_ISCSI:
+ case I40E_AQ_CAP_ID_ISCSI:
if (number == 1)
p->iscsi = true;
break;
- case I40E_DEV_FUNC_CAP_RSS:
+ case I40E_AQ_CAP_ID_RSS:
p->rss = true;
p->rss_table_size = number;
p->rss_table_entry_width = logical_id;
break;
- case I40E_DEV_FUNC_CAP_RX_QUEUES:
+ case I40E_AQ_CAP_ID_RXQ:
p->num_rx_qp = number;
p->base_queue = phys_id;
break;
- case I40E_DEV_FUNC_CAP_TX_QUEUES:
+ case I40E_AQ_CAP_ID_TXQ:
p->num_tx_qp = number;
p->base_queue = phys_id;
break;
- case I40E_DEV_FUNC_CAP_MSIX:
+ case I40E_AQ_CAP_ID_MSIX:
p->num_msix_vectors = number;
break;
- case I40E_DEV_FUNC_CAP_MSIX_VF:
+ case I40E_AQ_CAP_ID_VF_MSIX:
p->num_msix_vectors_vf = number;
break;
- case I40E_DEV_FUNC_CAP_FLEX10:
+ case I40E_AQ_CAP_ID_FLEX10:
if (major_rev == 1) {
if (number == 1) {
p->flex10_enable = true;
p->flex10_mode = logical_id;
p->flex10_status = phys_id;
break;
- case I40E_DEV_FUNC_CAP_CEM:
+ case I40E_AQ_CAP_ID_CEM:
if (number == 1)
p->mgmt_cem = true;
break;
- case I40E_DEV_FUNC_CAP_IWARP:
+ case I40E_AQ_CAP_ID_IWARP:
if (number == 1)
p->iwarp = true;
break;
- case I40E_DEV_FUNC_CAP_LED:
+ case I40E_AQ_CAP_ID_LED:
if (phys_id < I40E_HW_CAP_MAX_GPIO)
p->led[phys_id] = true;
break;
- case I40E_DEV_FUNC_CAP_SDP:
+ case I40E_AQ_CAP_ID_SDP:
if (phys_id < I40E_HW_CAP_MAX_GPIO)
p->sdp[phys_id] = true;
break;
- case I40E_DEV_FUNC_CAP_MDIO:
+ case I40E_AQ_CAP_ID_MDIO:
if (number == 1) {
p->mdio_port_num = phys_id;
p->mdio_port_mode = logical_id;
}
break;
- case I40E_DEV_FUNC_CAP_IEEE_1588:
+ case I40E_AQ_CAP_ID_1588:
if (number == 1)
p->ieee_1588 = true;
break;
- case I40E_DEV_FUNC_CAP_FLOW_DIRECTOR:
+ case I40E_AQ_CAP_ID_FLOW_DIRECTOR:
p->fd = true;
p->fd_filters_guaranteed = number;
p->fd_filters_best_effort = logical_id;
break;
- case I40E_DEV_FUNC_CAP_WR_CSR_PROT:
+ case I40E_AQ_CAP_ID_WSR_PROT:
p->wr_csr_prot = (u64)number;
p->wr_csr_prot |= (u64)logical_id << 32;
break;
struct i40e_aqc_get_cee_dcb_cfg_resp cee_cfg;
struct i40e_aqc_get_cee_dcb_cfg_v1_resp cee_v1_cfg;
- /* If Firmware version < v4.33 IEEE only */
- if (((hw->aq.fw_maj_ver == 4) && (hw->aq.fw_min_ver < 33)) ||
- (hw->aq.fw_maj_ver < 4))
+ /* If Firmware version < v4.33 on X710/XL710, IEEE only */
+ if ((hw->mac.type == I40E_MAC_XL710) &&
+ (((hw->aq.fw_maj_ver == 4) && (hw->aq.fw_min_ver < 33)) ||
+ (hw->aq.fw_maj_ver < 4)))
return i40e_get_ieee_dcb_config(hw);
- /* If Firmware version == v4.33 use old CEE struct */
- if ((hw->aq.fw_maj_ver == 4) && (hw->aq.fw_min_ver == 33)) {
+ /* If Firmware version == v4.33 on X710/XL710, use old CEE struct */
+ if ((hw->mac.type == I40E_MAC_XL710) &&
+ ((hw->aq.fw_maj_ver == 4) && (hw->aq.fw_min_ver == 33))) {
ret = i40e_aq_get_cee_dcb_config(hw, &cee_v1_cfg,
sizeof(cee_v1_cfg), NULL);
if (!ret) {
#define I40E_DEV_ID_10G_BASE_T4 0x1589
#define I40E_DEV_ID_VF 0x154C
#define I40E_DEV_ID_VF_HV 0x1571
+#define I40E_DEV_ID_KX_X722 0x37CE
+#define I40E_DEV_ID_QSFP_X722 0x37CF
#define I40E_DEV_ID_SFP_X722 0x37D0
#define I40E_DEV_ID_1G_BASE_T_X722 0x37D1
#define I40E_DEV_ID_10G_BASE_T_X722 0x37D2
SUPPORTED_1000baseT_Full;
if (hw_link_info->requested_speeds & I40E_LINK_SPEED_1GB)
ecmd->advertising |= ADVERTISED_1000baseT_Full;
- if (pf->hw.mac.type == I40E_MAC_X722) {
+ if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) {
ecmd->supported |= SUPPORTED_100baseT_Full;
if (hw_link_info->requested_speeds &
I40E_LINK_SPEED_100MB)
if (pf->hw.mac.type == I40E_MAC_X722) {
ecmd->supported |= SUPPORTED_100baseT_Full;
ecmd->advertising |= ADVERTISED_100baseT_Full;
+ if (pf->flags & I40E_FLAG_100M_SGMII_CAPABLE) {
+ ecmd->supported |= SUPPORTED_100baseT_Full;
+ ecmd->advertising |= ADVERTISED_100baseT_Full;
+ }
}
}
if (phy_types & I40E_CAP_PHY_TYPE_XAUI ||
case TCP_V4_FLOW:
switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
case 0:
- hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
- break;
+ return -EINVAL;
case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE)
+ hena |=
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK);
+
hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
break;
default:
case TCP_V6_FLOW:
switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
case 0:
- hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
- break;
+ return -EINVAL;
case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE)
+ hena |=
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK);
+
hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
break;
default:
case UDP_V4_FLOW:
switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
case 0:
- hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
- BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
- break;
+ return -EINVAL;
case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE)
+ hena |=
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) |
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP);
+
hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
break;
case UDP_V6_FLOW:
switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
case 0:
- hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
- BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
- break;
+ return -EINVAL;
case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE)
+ hena |=
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) |
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP);
+
hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
break;
#define DRV_VERSION_MAJOR 1
#define DRV_VERSION_MINOR 4
-#define DRV_VERSION_BUILD 8
+#define DRV_VERSION_BUILD 10
#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
__stringify(DRV_VERSION_MINOR) "." \
__stringify(DRV_VERSION_BUILD) DRV_KERN
{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_X722), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_1G_BASE_T_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_X722), 0},
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);
+static struct workqueue_struct *i40e_wq;
+
/**
* i40e_allocate_dma_mem_d - OS specific memory alloc for shared code
* @hw: pointer to the HW structure
if (!test_bit(__I40E_DOWN, &pf->state) &&
!test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state) &&
!test_and_set_bit(__I40E_SERVICE_SCHED, &pf->state))
- schedule_work(&pf->service_task);
+ queue_work(i40e_wq, &pf->service_task);
}
/**
f->changed = true;
INIT_LIST_HEAD(&f->list);
- list_add(&f->list, &vsi->mac_filter_list);
+ list_add_tail(&f->list, &vsi->mac_filter_list);
}
/* increment counter and add a new flag if needed */
wr32(hw, I40E_REG_MSS, val);
}
- if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
- (pf->hw.aq.fw_maj_ver < 4)) {
+ if (pf->flags & I40E_FLAG_RESTART_AUTONEG) {
msleep(75);
ret = i40e_aq_set_link_restart_an(&pf->hw, true, NULL);
if (ret)
return ret;
}
+/**
+ * i40e_get_rss_aq - Get RSS keys and lut by using AQ commands
+ * @vsi: Pointer to vsi structure
+ * @seed: Buffter to store the hash keys
+ * @lut: Buffer to store the lookup table entries
+ * @lut_size: Size of buffer to store the lookup table entries
+ *
+ * Return 0 on success, negative on failure
+ */
+static int i40e_get_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) {
+ ret = i40e_aq_get_rss_key(hw, vsi->id,
+ (struct i40e_aqc_get_set_rss_key_data *)seed);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Cannot get RSS key, err %s aq_err %s\n",
+ i40e_stat_str(&pf->hw, ret),
+ i40e_aq_str(&pf->hw,
+ pf->hw.aq.asq_last_status));
+ return ret;
+ }
+ }
+
+ if (lut) {
+ bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false;
+
+ ret = i40e_aq_get_rss_lut(hw, vsi->id, pf_lut, lut, lut_size);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Cannot get RSS lut, err %s aq_err %s\n",
+ i40e_stat_str(&pf->hw, ret),
+ i40e_aq_str(&pf->hw,
+ pf->hw.aq.asq_last_status));
+ return ret;
+ }
+ }
+
+ return ret;
+}
+
/**
* i40e_config_rss_reg - Configure RSS keys and lut by writing registers
* @vsi: Pointer to vsi structure
*/
int i40e_get_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size)
{
- return i40e_get_rss_reg(vsi, seed, lut, lut_size);
+ struct i40e_pf *pf = vsi->back;
+
+ if (pf->flags & I40E_FLAG_RSS_AQ_CAPABLE)
+ return i40e_get_rss_aq(vsi, seed, lut, lut_size);
+ else
+ return i40e_get_rss_reg(vsi, seed, lut, lut_size);
}
/**
pf->hw.func_caps.fd_filters_best_effort;
}
+ if (((pf->hw.mac.type == I40E_MAC_X710) ||
+ (pf->hw.mac.type == I40E_MAC_XL710)) &&
+ (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
+ (pf->hw.aq.fw_maj_ver < 4)))
+ pf->flags |= I40E_FLAG_RESTART_AUTONEG;
+
if (pf->hw.func_caps.vmdq) {
pf->num_vmdq_vsis = I40E_DEFAULT_NUM_VMDQ_VSI;
pf->flags |= I40E_FLAG_VMDQ_ENABLED;
I40E_FLAG_OUTER_UDP_CSUM_CAPABLE |
I40E_FLAG_WB_ON_ITR_CAPABLE |
I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE |
+ I40E_FLAG_100M_SGMII_CAPABLE |
I40E_FLAG_GENEVE_OFFLOAD_CAPABLE;
}
pf->eeprom_version = 0xDEAD;
np = netdev_priv(netdev);
np->vsi = vsi;
- netdev->hw_enc_features |= NETIF_F_IP_CSUM |
- NETIF_F_RXCSUM |
- NETIF_F_GSO_UDP_TUNNEL |
- NETIF_F_GSO_GRE |
- NETIF_F_TSO;
+ netdev->hw_enc_features |= NETIF_F_IP_CSUM |
+ NETIF_F_GSO_UDP_TUNNEL |
+ NETIF_F_GSO_GRE |
+ NETIF_F_TSO |
+ 0;
netdev->features = NETIF_F_SG |
NETIF_F_IP_CSUM |
wr32(hw, I40E_REG_MSS, val);
}
- if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 33)) ||
- (pf->hw.aq.fw_maj_ver < 4)) {
+ if (pf->flags & I40E_FLAG_RESTART_AUTONEG) {
msleep(75);
err = i40e_aq_set_link_restart_an(&pf->hw, true, NULL);
if (err)
i40e_driver_string, i40e_driver_version_str);
pr_info("%s: %s\n", i40e_driver_name, i40e_copyright);
+ /* we will see if single thread per module is enough for now,
+ * it can't be any worse than using the system workqueue which
+ * was already single threaded
+ */
+ i40e_wq = create_singlethread_workqueue(i40e_driver_name);
+ if (!i40e_wq) {
+ pr_err("%s: Failed to create workqueue\n", i40e_driver_name);
+ return -ENOMEM;
+ }
+
i40e_dbg_init();
return pci_register_driver(&i40e_driver);
}
static void __exit i40e_exit_module(void)
{
pci_unregister_driver(&i40e_driver);
+ destroy_workqueue(i40e_wq);
i40e_dbg_exit();
}
module_exit(i40e_exit_module);
vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_RSS_REG;
}
+ if (pf->flags & I40E_FLAG_MULTIPLE_TCP_UDP_RSS_PCTYPE) {
+ if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
+ vfres->vf_offload_flags |=
+ I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2;
+ }
+
if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING)
vfres->vf_offload_flags |= I40E_VIRTCHNL_VF_OFFLOAD_RX_POLLING;
+ if (pf->flags & I40E_FLAG_WB_ON_ITR_CAPABLE) {
+ if (vf->driver_caps & I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
+ vfres->vf_offload_flags |=
+ I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR;
+ }
+
vfres->num_vsis = num_vsis;
vfres->num_queue_pairs = vf->num_queue_pairs;
vfres->max_vectors = pf->hw.func_caps.num_msix_vectors_vf;
i40e_aqc_opc_get_phy_wol_caps = 0x0621,
i40e_aqc_opc_set_phy_debug = 0x0622,
i40e_aqc_opc_upload_ext_phy_fm = 0x0625,
+ i40e_aqc_opc_run_phy_activity = 0x0626,
/* NVM commands */
i40e_aqc_opc_nvm_read = 0x0701,
#define I40E_AQ_CAP_ID_OS2BMC_CAP 0x0004
#define I40E_AQ_CAP_ID_FUNCTIONS_VALID 0x0005
#define I40E_AQ_CAP_ID_ALTERNATE_RAM 0x0006
+#define I40E_AQ_CAP_ID_WOL_AND_PROXY 0x0008
#define I40E_AQ_CAP_ID_SRIOV 0x0012
#define I40E_AQ_CAP_ID_VF 0x0013
#define I40E_AQ_CAP_ID_VMDQ 0x0014
#define I40E_AQ_CAP_ID_LED 0x0061
#define I40E_AQ_CAP_ID_SDP 0x0062
#define I40E_AQ_CAP_ID_MDIO 0x0063
+#define I40E_AQ_CAP_ID_WSR_PROT 0x0064
#define I40E_AQ_CAP_ID_FLEX10 0x00F1
#define I40E_AQ_CAP_ID_CEM 0x00F2
#define I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT 9
#define I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK 0x1E00
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_XVLAN 0
+#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN 0
#define I40E_AQC_ADD_CLOUD_TNL_TYPE_NVGRE_OMAC 1
-#define I40E_AQC_ADD_CLOUD_TNL_TYPE_NGE 2
+#define I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE 2
#define I40E_AQC_ADD_CLOUD_TNL_TYPE_IP 3
__le32 tenant_id;
u8 config;
#define I40E_AQ_CONFIG_CRC_ENA 0x04
#define I40E_AQ_CONFIG_PACING_MASK 0x78
- u8 reserved[5];
+ u8 external_power_ability;
+#define I40E_AQ_LINK_POWER_CLASS_1 0x00
+#define I40E_AQ_LINK_POWER_CLASS_2 0x01
+#define I40E_AQ_LINK_POWER_CLASS_3 0x02
+#define I40E_AQ_LINK_POWER_CLASS_4 0x03
+ u8 reserved[4];
};
I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status);
I40E_AQC_PHY_REG_EXERNAL_MODULE = 0x3
};
+/* Run PHY Activity (0x0626) */
+struct i40e_aqc_run_phy_activity {
+ __le16 activity_id;
+ u8 flags;
+ u8 reserved1;
+ __le32 control;
+ __le32 data;
+ u8 reserved2[4];
+};
+
+I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity);
+
/* NVM Read command (indirect 0x0701)
* NVM Erase commands (direct 0x0702)
* NVM Update commands (indirect 0x0703)
tx_ring->q_vector->tx.total_bytes += total_bytes;
tx_ring->q_vector->tx.total_packets += total_packets;
+ if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) {
+ unsigned int j = 0;
+ /* check to see if there are < 4 descriptors
+ * waiting to be written back, then kick the hardware to force
+ * them to be written back in case we stay in NAPI.
+ * In this mode on X722 we do not enable Interrupt.
+ */
+ j = i40evf_get_tx_pending(tx_ring);
+
+ if (budget &&
+ ((j / (WB_STRIDE + 1)) == 0) && (j > 0) &&
+ !test_bit(__I40E_DOWN, &tx_ring->vsi->state) &&
+ (I40E_DESC_UNUSED(tx_ring) != tx_ring->count))
+ tx_ring->arm_wb = true;
+ }
+
netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev,
tx_ring->queue_index),
total_packets, total_bytes);
__I40EVF_RESETTING, /* in reset */
/* Below here, watchdog is running */
__I40EVF_DOWN, /* ready, can be opened */
+ __I40EVF_DOWN_PENDING, /* descending, waiting for watchdog */
__I40EVF_TESTING, /* in ethtool self-test */
__I40EVF_RUNNING, /* opened, working */
};
struct ethtool_rxnfc *nfc)
{
struct i40e_hw *hw = &adapter->hw;
+ u32 flags = adapter->vf_res->vf_offload_flags;
u64 hena = (u64)rd32(hw, I40E_VFQF_HENA(0)) |
((u64)rd32(hw, I40E_VFQF_HENA(1)) << 32);
switch (nfc->flow_type) {
case TCP_V4_FLOW:
- switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
- case 0:
- hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
- break;
- case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+ if (flags & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
+ hena |=
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK);
+
hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
- break;
- default:
+ } else {
return -EINVAL;
}
break;
case TCP_V6_FLOW:
- switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
- case 0:
- hena &= ~BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
- break;
- case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+ if (flags & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
+ hena |=
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK);
+
hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
- break;
- default:
+ } else {
return -EINVAL;
}
break;
case UDP_V4_FLOW:
- switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
- case 0:
- hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
- BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
- break;
- case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+ if (flags & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
+ hena |=
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) |
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP);
+
hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) |
BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4));
- break;
- default:
+ } else {
return -EINVAL;
}
break;
case UDP_V6_FLOW:
- switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
- case 0:
- hena &= ~(BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
- BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
- break;
- case (RXH_L4_B_0_1 | RXH_L4_B_2_3):
+ if (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
+ if (flags & I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
+ hena |=
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) |
+ BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP);
+
hena |= (BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) |
BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6));
- break;
- default:
+ } else {
return -EINVAL;
}
break;
MODULE_LICENSE("GPL");
MODULE_VERSION(DRV_VERSION);
+static struct workqueue_struct *i40evf_wq;
+
/**
* i40evf_allocate_dma_mem_d - OS specific memory alloc for shared code
* @hw: pointer to the HW structure
if (!(adapter->flags & (I40EVF_FLAG_RESET_PENDING |
I40EVF_FLAG_RESET_NEEDED))) {
adapter->flags |= I40EVF_FLAG_RESET_NEEDED;
- schedule_work(&adapter->reset_task);
+ queue_work(i40evf_wq, &adapter->reset_task);
}
}
struct net_device *netdev = adapter->netdev;
struct i40evf_mac_filter *f;
- if (adapter->state == __I40EVF_DOWN)
+ if (adapter->state <= __I40EVF_DOWN_PENDING)
return;
while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK,
if (!adapter->vsi_res)
return;
kfree(adapter->tx_rings);
+ adapter->tx_rings = NULL;
kfree(adapter->rx_rings);
+ adapter->rx_rings = NULL;
}
/**
int ret;
/* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */
- hena = I40E_DEFAULT_RSS_HENA;
+ if (adapter->vf_res->vf_offload_flags &
+ I40E_VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
+ hena = I40E_DEFAULT_RSS_HENA_EXPANDED;
+ else
+ hena = I40E_DEFAULT_RSS_HENA;
wr32(hw, I40E_VFQF_HENA(0), (u32)hena);
wr32(hw, I40E_VFQF_HENA(1), (u32)(hena >> 32));
dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n");
return -EIO;
}
- if (adapter->state != __I40EVF_DOWN || adapter->aq_required)
+
+ if (adapter->state != __I40EVF_DOWN)
return -EBUSY;
/* allocate transmit descriptors */
{
struct i40evf_adapter *adapter = netdev_priv(netdev);
- if (adapter->state <= __I40EVF_DOWN)
+ if (adapter->state <= __I40EVF_DOWN_PENDING)
return 0;
set_bit(__I40E_DOWN, &adapter->vsi.state);
i40evf_down(adapter);
- adapter->state = __I40EVF_DOWN;
+ adapter->state = __I40EVF_DOWN_PENDING;
i40evf_free_traffic_irqs(adapter);
return 0;
if (adapter->vf_res->vf_offload_flags &
I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE;
- if (!RSS_AQ(adapter))
- i40evf_init_rss(adapter);
+
+ if (adapter->vf_res->vf_offload_flags &
+ I40E_VIRTCHNL_VF_OFFLOAD_WB_ON_ITR)
+ adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE;
+
err = i40evf_request_misc_irq(adapter);
if (err)
goto err_sw_init;
pr_info("%s\n", i40evf_copyright);
+ i40evf_wq = create_singlethread_workqueue(i40evf_driver_name);
+ if (!i40evf_wq) {
+ pr_err("%s: Failed to create workqueue\n", i40evf_driver_name);
+ return -ENOMEM;
+ }
ret = pci_register_driver(&i40evf_driver);
return ret;
}
static void __exit i40evf_exit_module(void)
{
pci_unregister_driver(&i40evf_driver);
+ destroy_workqueue(i40evf_wq);
}
module_exit(i40evf_exit_module);
case I40E_VIRTCHNL_OP_DISABLE_QUEUES:
i40evf_free_all_tx_resources(adapter);
i40evf_free_all_rx_resources(adapter);
+ if (adapter->state == __I40EVF_DOWN_PENDING)
+ adapter->state = __I40EVF_DOWN;
break;
case I40E_VIRTCHNL_OP_VERSION:
case I40E_VIRTCHNL_OP_CONFIG_IRQ_MAP:
*
* Copyright (C) 2014-2015 Renesas Electronics Corporation
* Copyright (C) 2015 Renesas Solutions Corp.
- * Copyright (C) 2015 Cogent Embedded, Inc. <source@cogentembedded.com>
+ * Copyright (C) 2015-2016 Cogent Embedded, Inc. <source@cogentembedded.com>
*
* Based on the SuperH Ethernet driver
*
iowrite32(data, priv->addr + reg);
}
+void ravb_modify(struct net_device *ndev, enum ravb_reg reg, u32 clear,
+ u32 set);
int ravb_wait(struct net_device *ndev, enum ravb_reg reg, u32 mask, u32 value);
irqreturn_t ravb_ptp_interrupt(struct net_device *ndev);
*
* Copyright (C) 2014-2015 Renesas Electronics Corporation
* Copyright (C) 2015 Renesas Solutions Corp.
- * Copyright (C) 2015 Cogent Embedded, Inc. <source@cogentembedded.com>
+ * Copyright (C) 2015-2016 Cogent Embedded, Inc. <source@cogentembedded.com>
*
* Based on the SuperH Ethernet driver
*
NETIF_MSG_RX_ERR | \
NETIF_MSG_TX_ERR)
+void ravb_modify(struct net_device *ndev, enum ravb_reg reg, u32 clear,
+ u32 set)
+{
+ ravb_write(ndev, (ravb_read(ndev, reg) & ~clear) | set, reg);
+}
+
int ravb_wait(struct net_device *ndev, enum ravb_reg reg, u32 mask, u32 value)
{
int i;
int error;
/* Set config mode */
- ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_OPC) | CCC_OPC_CONFIG,
- CCC);
+ ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG);
/* Check if the operating mode is changed to the config mode */
error = ravb_wait(ndev, CSR, CSR_OPS, CSR_OPS_CONFIG);
if (error)
static void ravb_set_duplex(struct net_device *ndev)
{
struct ravb_private *priv = netdev_priv(ndev);
- u32 ecmr = ravb_read(ndev, ECMR);
- if (priv->duplex) /* Full */
- ecmr |= ECMR_DM;
- else /* Half */
- ecmr &= ~ECMR_DM;
- ravb_write(ndev, ecmr, ECMR);
+ ravb_modify(ndev, ECMR, ECMR_DM, priv->duplex ? ECMR_DM : 0);
}
static void ravb_set_rate(struct net_device *ndev)
{
struct ravb_private *priv = container_of(ctrl, struct ravb_private,
mdiobb);
- u32 pir = ravb_read(priv->ndev, PIR);
- if (set)
- pir |= mask;
- else
- pir &= ~mask;
- ravb_write(priv->ndev, pir, PIR);
+ ravb_modify(priv->ndev, PIR, mask, set ? mask : 0);
}
/* MDC pin control */
ravb_ring_format(ndev, RAVB_NC);
#if defined(__LITTLE_ENDIAN)
- ravb_write(ndev, ravb_read(ndev, CCC) & ~CCC_BOC, CCC);
+ ravb_modify(ndev, CCC, CCC_BOC, 0);
#else
- ravb_write(ndev, ravb_read(ndev, CCC) | CCC_BOC, CCC);
+ ravb_modify(ndev, CCC, CCC_BOC, CCC_BOC);
#endif
/* Set AVB RX */
ravb_write(ndev, TIC_FTE0 | TIC_FTE1 | TIC_TFUE, TIC);
/* Setting the control will start the AVB-DMAC process. */
- ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_OPC) | CCC_OPC_OPERATION,
- CCC);
+ ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_OPERATION);
return 0;
}
break;
}
}
- ravb_write(ndev, ravb_read(ndev, TCCR) | TCCR_TFR, TCCR);
+ ravb_modify(ndev, TCCR, TCCR_TFR, TCCR_TFR);
}
}
static void ravb_rcv_snd_disable(struct net_device *ndev)
{
/* Disable TX and RX */
- ravb_write(ndev, ravb_read(ndev, ECMR) & ~(ECMR_RE | ECMR_TE), ECMR);
+ ravb_modify(ndev, ECMR, ECMR_RE | ECMR_TE, 0);
}
static void ravb_rcv_snd_enable(struct net_device *ndev)
{
/* Enable TX and RX */
- ravb_write(ndev, ravb_read(ndev, ECMR) | ECMR_RE | ECMR_TE, ECMR);
+ ravb_modify(ndev, ECMR, ECMR_RE | ECMR_TE, ECMR_RE | ECMR_TE);
}
/* function for waiting dma process finished */
/* Re-enable RX/TX interrupts */
spin_lock_irqsave(&priv->lock, flags);
- ravb_write(ndev, ravb_read(ndev, RIC0) | mask, RIC0);
- ravb_write(ndev, ravb_read(ndev, TIC) | mask, TIC);
+ ravb_modify(ndev, RIC0, mask, mask);
+ ravb_modify(ndev, TIC, mask, mask);
mmiowb();
spin_unlock_irqrestore(&priv->lock, flags);
ravb_set_rate(ndev);
}
if (!priv->link) {
- ravb_write(ndev, ravb_read(ndev, ECMR) & ~ECMR_TXF,
- ECMR);
+ ravb_modify(ndev, ECMR, ECMR_TXF, 0);
new_state = true;
priv->link = phydev->link;
if (priv->no_avb_link)
desc--;
desc->die_dt = DT_FSTART;
- ravb_write(ndev, ravb_read(ndev, TCCR) | (TCCR_TSRQ0 << q), TCCR);
+ ravb_modify(ndev, TCCR, TCCR_TSRQ0 << q, TCCR_TSRQ0 << q);
priv->cur_tx[q] += NUM_TX_DESC;
if (priv->cur_tx[q] - priv->dirty_tx[q] >
{
struct ravb_private *priv = netdev_priv(ndev);
unsigned long flags;
- u32 ecmr;
spin_lock_irqsave(&priv->lock, flags);
- ecmr = ravb_read(ndev, ECMR);
- if (ndev->flags & IFF_PROMISC)
- ecmr |= ECMR_PRM;
- else
- ecmr &= ~ECMR_PRM;
- ravb_write(ndev, ecmr, ECMR);
+ ravb_modify(ndev, ECMR, ECMR_PRM,
+ ndev->flags & IFF_PROMISC ? ECMR_PRM : 0);
mmiowb();
spin_unlock_irqrestore(&priv->lock, flags);
}
/* Set AVB config mode */
if (chip_id == RCAR_GEN2) {
- ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_OPC) |
- CCC_OPC_CONFIG, CCC);
+ ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG);
/* Set CSEL value */
- ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_CSEL) |
- CCC_CSEL_HPB, CCC);
+ ravb_modify(ndev, CCC, CCC_CSEL, CCC_CSEL_HPB);
} else {
- ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_OPC) |
- CCC_OPC_CONFIG | CCC_GAC | CCC_CSEL_HPB, CCC);
+ ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG |
+ CCC_GAC | CCC_CSEL_HPB);
}
/* Set CSEL value */
goto out_release;
/* Request GTI loading */
- ravb_write(ndev, ravb_read(ndev, GCCR) | GCCR_LTI, GCCR);
+ ravb_modify(ndev, GCCR, GCCR_LTI, GCCR_LTI);
/* Allocate descriptor base address table */
priv->desc_bat_size = sizeof(struct ravb_desc) * DBAT_ENTRY_NUM;
*
* Copyright (C) 2013-2015 Renesas Electronics Corporation
* Copyright (C) 2015 Renesas Solutions Corp.
- * Copyright (C) 2015 Cogent Embedded, Inc. <source@cogentembedded.com>
+ * Copyright (C) 2015-2016 Cogent Embedded, Inc. <source@cogentembedded.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
if (error)
return error;
- ravb_write(ndev, ravb_read(ndev, GCCR) | request, GCCR);
+ ravb_modify(ndev, GCCR, request, request);
return ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ);
}
ptp.info);
struct net_device *ndev = priv->ndev;
unsigned long flags;
- u32 gic;
if (req->index)
return -EINVAL;
priv->ptp.extts[req->index] = on;
spin_lock_irqsave(&priv->lock, flags);
- gic = ravb_read(ndev, GIC);
- if (on)
- gic |= GIC_PTCE;
- else
- gic &= ~GIC_PTCE;
- ravb_write(ndev, gic, GIC);
+ ravb_modify(ndev, GIC, GIC_PTCE, on ? GIC_PTCE : 0);
mmiowb();
spin_unlock_irqrestore(&priv->lock, flags);
struct ravb_ptp_perout *perout;
unsigned long flags;
int error = 0;
- u32 gic;
if (req->index)
return -EINVAL;
error = ravb_ptp_update_compare(priv, (u32)start_ns);
if (!error) {
/* Unmask interrupt */
- gic = ravb_read(ndev, GIC);
- gic |= GIC_PTME;
- ravb_write(ndev, gic, GIC);
+ ravb_modify(ndev, GIC, GIC_PTME, GIC_PTME);
}
} else {
spin_lock_irqsave(&priv->lock, flags);
perout->period = 0;
/* Mask interrupt */
- gic = ravb_read(ndev, GIC);
- gic &= ~GIC_PTME;
- ravb_write(ndev, gic, GIC);
+ ravb_modify(ndev, GIC, GIC_PTME, 0);
}
mmiowb();
spin_unlock_irqrestore(&priv->lock, flags);
{
struct ravb_private *priv = netdev_priv(ndev);
unsigned long flags;
- u32 gccr;
priv->ptp.info = ravb_ptp_info;
spin_lock_irqsave(&priv->lock, flags);
ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ);
- gccr = ravb_read(ndev, GCCR) & ~GCCR_TCSS;
- ravb_write(ndev, gccr | GCCR_TCSS_ADJGPTP, GCCR);
+ ravb_modify(ndev, GCCR, GCCR_TCSS, GCCR_TCSS_ADJGPTP);
mmiowb();
spin_unlock_irqrestore(&priv->lock, flags);
* Copyright (C) 2014 Renesas Electronics Corporation
* Copyright (C) 2006-2012 Nobuhiro Iwamatsu
* Copyright (C) 2008-2014 Renesas Solutions Corp.
- * Copyright (C) 2013-2014 Cogent Embedded, Inc.
+ * Copyright (C) 2013-2016 Cogent Embedded, Inc.
* Copyright (C) 2014 Codethink Limited
*
* This program is free software; you can redistribute it and/or modify it
return ioread32(mdp->addr + offset);
}
+static void sh_eth_modify(struct net_device *ndev, int enum_index, u32 clear,
+ u32 set)
+{
+ sh_eth_write(ndev, (sh_eth_read(ndev, enum_index) & ~clear) | set,
+ enum_index);
+}
+
static bool sh_eth_is_gether(struct sh_eth_private *mdp)
{
return mdp->reg_offset == sh_eth_offset_gigabit;
{
struct sh_eth_private *mdp = netdev_priv(ndev);
- if (mdp->duplex) /* Full */
- sh_eth_write(ndev, sh_eth_read(ndev, ECMR) | ECMR_DM, ECMR);
- else /* Half */
- sh_eth_write(ndev, sh_eth_read(ndev, ECMR) & ~ECMR_DM, ECMR);
+ sh_eth_modify(ndev, ECMR, ECMR_DM, mdp->duplex ? ECMR_DM : 0);
}
static void sh_eth_chip_reset(struct net_device *ndev)
switch (mdp->speed) {
case 10: /* 10BASE */
- sh_eth_write(ndev, sh_eth_read(ndev, ECMR) & ~ECMR_ELB, ECMR);
+ sh_eth_modify(ndev, ECMR, ECMR_ELB, 0);
break;
case 100:/* 100BASE */
- sh_eth_write(ndev, sh_eth_read(ndev, ECMR) | ECMR_ELB, ECMR);
+ sh_eth_modify(ndev, ECMR, ECMR_ELB, ECMR_ELB);
break;
default:
break;
switch (mdp->speed) {
case 10: /* 10BASE */
- sh_eth_write(ndev, sh_eth_read(ndev, ECMR) & ~ECMR_RTM, ECMR);
+ sh_eth_modify(ndev, ECMR, ECMR_RTM, 0);
break;
case 100:/* 100BASE */
- sh_eth_write(ndev, sh_eth_read(ndev, ECMR) | ECMR_RTM, ECMR);
+ sh_eth_modify(ndev, ECMR, ECMR_RTM, ECMR_RTM);
break;
default:
break;
if (sh_eth_is_gether(mdp) || sh_eth_is_rz_fast_ether(mdp)) {
sh_eth_write(ndev, EDSR_ENALL, EDSR);
- sh_eth_write(ndev, sh_eth_read(ndev, EDMR) | EDMR_SRST_GETHER,
- EDMR);
+ sh_eth_modify(ndev, EDMR, EDMR_SRST_GETHER, EDMR_SRST_GETHER);
ret = sh_eth_check_reset(ndev);
if (ret)
if (mdp->cd->select_mii)
sh_eth_select_mii(ndev);
} else {
- sh_eth_write(ndev, sh_eth_read(ndev, EDMR) | EDMR_SRST_ETHER,
- EDMR);
+ sh_eth_modify(ndev, EDMR, EDMR_SRST_ETHER, EDMR_SRST_ETHER);
mdelay(3);
- sh_eth_write(ndev, sh_eth_read(ndev, EDMR) & ~EDMR_SRST_ETHER,
- EDMR);
+ sh_eth_modify(ndev, EDMR, EDMR_SRST_ETHER, 0);
}
return ret;
sh_eth_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN,
RFLR);
- sh_eth_write(ndev, sh_eth_read(ndev, EESR), EESR);
+ sh_eth_modify(ndev, EESR, 0, 0);
if (start) {
mdp->irq_enabled = true;
sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR);
static void sh_eth_rcv_snd_disable(struct net_device *ndev)
{
/* disable tx and rx */
- sh_eth_write(ndev, sh_eth_read(ndev, ECMR) &
- ~(ECMR_RE | ECMR_TE), ECMR);
+ sh_eth_modify(ndev, ECMR, ECMR_RE | ECMR_TE, 0);
}
static void sh_eth_rcv_snd_enable(struct net_device *ndev)
{
/* enable tx and rx */
- sh_eth_write(ndev, sh_eth_read(ndev, ECMR) |
- (ECMR_RE | ECMR_TE), ECMR);
+ sh_eth_modify(ndev, ECMR, ECMR_RE | ECMR_TE, ECMR_RE | ECMR_TE);
}
/* error control function */
sh_eth_rcv_snd_disable(ndev);
} else {
/* Link Up */
- sh_eth_write(ndev, sh_eth_read(ndev, EESIPR) &
- ~DMAC_M_ECI, EESIPR);
+ sh_eth_modify(ndev, EESIPR, DMAC_M_ECI, 0);
/* clear int */
- sh_eth_write(ndev, sh_eth_read(ndev, ECSR),
- ECSR);
- sh_eth_write(ndev, sh_eth_read(ndev, EESIPR) |
- DMAC_M_ECI, EESIPR);
+ sh_eth_modify(ndev, ECSR, 0, 0);
+ sh_eth_modify(ndev, EESIPR, DMAC_M_ECI,
+ DMAC_M_ECI);
/* enable tx and rx */
sh_eth_rcv_snd_enable(ndev);
}
mdp->cd->set_rate(ndev);
}
if (!mdp->link) {
- sh_eth_write(ndev,
- sh_eth_read(ndev, ECMR) & ~ECMR_TXF,
- ECMR);
+ sh_eth_modify(ndev, ECMR, ECMR_TXF, 0);
new_state = 1;
mdp->link = phydev->link;
if (mdp->cd->no_psr || mdp->no_ether_link)
obj-$(CONFIG_SXGBE_ETH) += samsung-sxgbe.o
samsung-sxgbe-objs:= sxgbe_platform.o sxgbe_main.o sxgbe_desc.o \
sxgbe_dma.o sxgbe_core.o sxgbe_mtl.o sxgbe_mdio.o \
- sxgbe_ethtool.o sxgbe_xpcs.o $(samsung-sxgbe-y)
+ sxgbe_ethtool.o $(samsung-sxgbe-y)
+++ /dev/null
-/* 10G controller driver for Samsung SoCs
- *
- * Copyright (C) 2013 Samsung Electronics Co., Ltd.
- * http://www.samsung.com
- *
- * Author: Siva Reddy Kallam <siva.kallam@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/bitops.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
-#include <linux/phy.h>
-#include "sxgbe_common.h"
-#include "sxgbe_xpcs.h"
-
-static int sxgbe_xpcs_read(struct net_device *ndev, unsigned int reg)
-{
- u32 value;
- struct sxgbe_priv_data *priv = netdev_priv(ndev);
-
- value = readl(priv->ioaddr + XPCS_OFFSET + reg);
-
- return value;
-}
-
-static int sxgbe_xpcs_write(struct net_device *ndev, int reg, int data)
-{
- struct sxgbe_priv_data *priv = netdev_priv(ndev);
-
- writel(data, priv->ioaddr + XPCS_OFFSET + reg);
-
- return 0;
-}
-
-int sxgbe_xpcs_init(struct net_device *ndev)
-{
- u32 value;
-
- value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
- /* 10G XAUI mode */
- sxgbe_xpcs_write(ndev, SR_PCS_CONTROL2, XPCS_TYPE_SEL_X);
- sxgbe_xpcs_write(ndev, VR_PCS_MMD_XAUI_MODE_CONTROL, XPCS_XAUI_MODE);
- sxgbe_xpcs_write(ndev, VR_PCS_MMD_XAUI_MODE_CONTROL, value | BIT(13));
- sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value | BIT(11));
-
- do {
- value = sxgbe_xpcs_read(ndev, VR_PCS_MMD_DIGITAL_STATUS);
- } while ((value & XPCS_QSEQ_STATE_MPLLOFF) == XPCS_QSEQ_STATE_STABLE);
-
- value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
- sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value & ~BIT(11));
-
- do {
- value = sxgbe_xpcs_read(ndev, VR_PCS_MMD_DIGITAL_STATUS);
- } while ((value & XPCS_QSEQ_STATE_MPLLOFF) != XPCS_QSEQ_STATE_STABLE);
-
- return 0;
-}
-
-int sxgbe_xpcs_init_1G(struct net_device *ndev)
-{
- int value;
-
- /* 10GBASE-X PCS (1G) mode */
- sxgbe_xpcs_write(ndev, SR_PCS_CONTROL2, XPCS_TYPE_SEL_X);
- sxgbe_xpcs_write(ndev, VR_PCS_MMD_XAUI_MODE_CONTROL, XPCS_XAUI_MODE);
- value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
- sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value & ~BIT(13));
-
- value = sxgbe_xpcs_read(ndev, SR_MII_MMD_CONTROL);
- sxgbe_xpcs_write(ndev, SR_MII_MMD_CONTROL, value | BIT(6));
- sxgbe_xpcs_write(ndev, SR_MII_MMD_CONTROL, value & ~BIT(13));
- value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
- sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value | BIT(11));
-
- do {
- value = sxgbe_xpcs_read(ndev, VR_PCS_MMD_DIGITAL_STATUS);
- } while ((value & XPCS_QSEQ_STATE_MPLLOFF) != XPCS_QSEQ_STATE_STABLE);
-
- value = sxgbe_xpcs_read(ndev, SR_PCS_MMD_CONTROL1);
- sxgbe_xpcs_write(ndev, SR_PCS_MMD_CONTROL1, value & ~BIT(11));
-
- /* Auto Negotiation cluase 37 enable */
- value = sxgbe_xpcs_read(ndev, SR_MII_MMD_CONTROL);
- sxgbe_xpcs_write(ndev, SR_MII_MMD_CONTROL, value | BIT(12));
-
- return 0;
-}
+++ /dev/null
-/* 10G controller driver for Samsung SoCs
- *
- * Copyright (C) 2013 Samsung Electronics Co., Ltd.
- * http://www.samsung.com
- *
- * Author: Byungho An <bh74.an@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __SXGBE_XPCS_H__
-#define __SXGBE_XPCS_H__
-
-/* XPCS Registers */
-#define XPCS_OFFSET 0x1A060000
-#define SR_PCS_MMD_CONTROL1 0x030000
-#define SR_PCS_CONTROL2 0x030007
-#define VR_PCS_MMD_XAUI_MODE_CONTROL 0x038004
-#define VR_PCS_MMD_DIGITAL_STATUS 0x038010
-#define SR_MII_MMD_CONTROL 0x1F0000
-#define SR_MII_MMD_AN_ADV 0x1F0004
-#define SR_MII_MMD_AN_LINK_PARTNER_BA 0x1F0005
-#define VR_MII_MMD_AN_CONTROL 0x1F8001
-#define VR_MII_MMD_AN_INT_STATUS 0x1F8002
-
-#define XPCS_QSEQ_STATE_STABLE 0x10
-#define XPCS_QSEQ_STATE_MPLLOFF 0x1c
-#define XPCS_TYPE_SEL_R 0x00
-#define XPCS_TYPE_SEL_X 0x01
-#define XPCS_TYPE_SEL_W 0x02
-#define XPCS_XAUI_MODE 0x00
-#define XPCS_RXAUI_MODE 0x01
-
-int sxgbe_xpcs_init(struct net_device *ndev);
-int sxgbe_xpcs_init_1G(struct net_device *ndev);
-
-#endif /* __SXGBE_XPCS_H__ */
#include <linux/mutex.h>
#include <linux/highmem.h>
#include <linux/if_vlan.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/sunvnet.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <linux/icmpv6.h>
err = vnet_rx_one(port, desc);
if (err == -ECONNRESET)
return err;
+ trace_vnet_rx_one(port->vio._local_sid, port->vio._peer_sid,
+ index, desc->hdr.ack);
desc->hdr.state = VIO_DESC_DONE;
err = put_rx_desc(port, dr, desc, index);
if (err < 0)
ack_start = ack_end = vio_dring_prev(dr, start);
if (send_ack) {
port->napi_resume = false;
+ trace_vnet_tx_send_stopped_ack(port->vio._local_sid,
+ port->vio._peer_sid,
+ ack_end, *npkts);
return vnet_send_ack(port, dr, ack_start, ack_end,
VIO_DRING_STOPPED);
} else {
+ trace_vnet_tx_defer_stopped_ack(port->vio._local_sid,
+ port->vio._peer_sid,
+ ack_end, *npkts);
port->napi_resume = true;
port->napi_stop_idx = ack_end;
return 1;
/* sync for race conditions with vnet_start_xmit() and tell xmit it
* is time to send a trigger.
*/
+ trace_vnet_rx_stopped_ack(port->vio._local_sid,
+ port->vio._peer_sid, end);
dr->cons = vio_dring_next(dr, end);
desc = vio_dring_entry(dr, dr->cons);
if (desc->hdr.state == VIO_DESC_READY && !port->start_cons) {
int retries = 0;
if (port->stop_rx) {
+ trace_vnet_tx_pending_stopped_ack(port->vio._local_sid,
+ port->vio._peer_sid,
+ port->stop_rx_idx, -1);
err = vnet_send_ack(port,
&port->vio.drings[VIO_DRIVER_RX_RING],
port->stop_rx_idx, -1,
if (retries++ > VNET_MAX_RETRIES)
break;
} while (err == -EAGAIN);
+ trace_vnet_tx_trigger(port->vio._local_sid,
+ port->vio._peer_sid, start, err);
return err;
}
* producer to consumer announcement that work is available to the
* consumer
*/
- if (!port->start_cons)
- goto ldc_start_done; /* previous trigger suffices */
+ if (!port->start_cons) { /* previous trigger suffices */
+ trace_vnet_skip_tx_trigger(port->vio._local_sid,
+ port->vio._peer_sid, dr->cons);
+ goto ldc_start_done;
+ }
err = __vnet_tx_trigger(port, dr->cons);
if (unlikely(err < 0)) {
ipvlan->dev = dev;
ipvlan->port = port;
ipvlan->sfeatures = IPVLAN_FEATURES;
+ ipvlan_adjust_mtu(ipvlan, phy_dev);
INIT_LIST_HEAD(&ipvlan->addrs);
/* TODO Probably put random address here to be presented to the
u64_stats_update_end(&pcpu_stats->syncp);
skb->dev = team->dev;
+ } else if (res == RX_HANDLER_EXACT) {
+ this_cpu_inc(team->pcpu_stats->rx_nohandler);
} else {
this_cpu_inc(team->pcpu_stats->rx_dropped);
}
struct team *team = netdev_priv(dev);
struct team_pcpu_stats *p;
u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes;
- u32 rx_dropped = 0, tx_dropped = 0;
+ u32 rx_dropped = 0, tx_dropped = 0, rx_nohandler = 0;
unsigned int start;
int i;
stats->tx_packets += tx_packets;
stats->tx_bytes += tx_bytes;
/*
- * rx_dropped & tx_dropped are u32, updated
- * without syncp protection.
+ * rx_dropped, tx_dropped & rx_nohandler are u32,
+ * updated without syncp protection.
*/
rx_dropped += p->rx_dropped;
tx_dropped += p->tx_dropped;
+ rx_nohandler += p->rx_nohandler;
}
stats->rx_dropped = rx_dropped;
stats->tx_dropped = tx_dropped;
+ stats->rx_nohandler = rx_nohandler;
return stats;
}
virtio_net_ctrl_ack ctrl_status;
u8 ctrl_promisc;
u8 ctrl_allmulti;
+
+ /* Ethtool settings */
+ u8 duplex;
+ u32 speed;
};
struct padded_vnet_hdr {
channels->other_count = 0;
}
+/* Check if the user is trying to change anything besides speed/duplex */
+static bool virtnet_validate_ethtool_cmd(const struct ethtool_cmd *cmd)
+{
+ struct ethtool_cmd diff1 = *cmd;
+ struct ethtool_cmd diff2 = {};
+
+ /* advertising and cmd are usually set, ignore port because we set it */
+ ethtool_cmd_speed_set(&diff1, 0);
+ diff1.advertising = 0;
+ diff1.duplex = 0;
+ diff1.port = 0;
+ diff1.cmd = 0;
+
+ return !memcmp(&diff1, &diff2, sizeof(diff1));
+}
+
+static int virtnet_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ u32 speed;
+
+ speed = ethtool_cmd_speed(cmd);
+ /* don't allow custom speed and duplex */
+ if (!ethtool_validate_speed(speed) ||
+ !ethtool_validate_duplex(cmd->duplex) ||
+ !virtnet_validate_ethtool_cmd(cmd))
+ return -EINVAL;
+ vi->speed = speed;
+ vi->duplex = cmd->duplex;
+
+ return 0;
+}
+
+static int virtnet_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+
+ ethtool_cmd_speed_set(cmd, vi->speed);
+ cmd->duplex = vi->duplex;
+ cmd->port = PORT_OTHER;
+
+ return 0;
+}
+
+static void virtnet_init_settings(struct net_device *dev)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+
+ vi->speed = SPEED_UNKNOWN;
+ vi->duplex = DUPLEX_UNKNOWN;
+}
+
static const struct ethtool_ops virtnet_ethtool_ops = {
.get_drvinfo = virtnet_get_drvinfo,
.get_link = ethtool_op_get_link,
.set_channels = virtnet_set_channels,
.get_channels = virtnet_get_channels,
.get_ts_info = ethtool_op_get_ts_info,
+ .get_settings = virtnet_get_settings,
+ .set_settings = virtnet_set_settings,
};
#define MIN_MTU 68
netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs);
netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs);
+ virtnet_init_settings(dev);
+
err = register_netdev(dev);
if (err) {
pr_debug("virtio_net: registering device failed\n");
return nla_put_u32(skb, IFLA_VRF_TABLE, vrf->tb_id);
}
+static size_t vrf_get_slave_size(const struct net_device *bond_dev,
+ const struct net_device *slave_dev)
+{
+ return nla_total_size(sizeof(u32)); /* IFLA_VRF_PORT_TABLE */
+}
+
+static int vrf_fill_slave_info(struct sk_buff *skb,
+ const struct net_device *vrf_dev,
+ const struct net_device *slave_dev)
+{
+ struct net_vrf *vrf = netdev_priv(vrf_dev);
+
+ if (nla_put_u32(skb, IFLA_VRF_PORT_TABLE, vrf->tb_id))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
static const struct nla_policy vrf_nl_policy[IFLA_VRF_MAX + 1] = {
[IFLA_VRF_TABLE] = { .type = NLA_U32 },
};
.validate = vrf_validate,
.fill_info = vrf_fillinfo,
+ .get_slave_size = vrf_get_slave_size,
+ .fill_slave_info = vrf_fill_slave_info,
+
.newlink = vrf_newlink,
.dellink = vrf_dellink,
.setup = vrf_setup,
gbp->policy_id = htons(md->gbp & VXLAN_GBP_ID_MASK);
}
-#if IS_ENABLED(CONFIG_IPV6)
-static int vxlan6_xmit_skb(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb,
- struct net_device *dev, struct in6_addr *saddr,
- struct in6_addr *daddr, __u8 prio, __u8 ttl,
- __be16 src_port, __be16 dst_port, __be32 vni,
- struct vxlan_metadata *md, bool xnet, u32 vxflags)
+static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
+ int iphdr_len, __be32 vni,
+ struct vxlan_metadata *md, u32 vxflags,
+ bool udp_sum)
{
struct vxlanhdr *vxh;
int min_headroom;
int err;
- bool udp_sum = !(vxflags & VXLAN_F_UDP_ZERO_CSUM6_TX);
int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
u16 hdrlen = sizeof(struct vxlanhdr);
}
}
- skb_scrub_packet(skb, xnet);
-
min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
- + VXLAN_HLEN + sizeof(struct ipv6hdr)
- + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
-
- /* Need space for new headers (invalidates iph ptr) */
- err = skb_cow_head(skb, min_headroom);
- if (unlikely(err)) {
- kfree_skb(skb);
- goto err;
- }
-
- skb = vlan_hwaccel_push_inside(skb);
- if (WARN_ON(!skb)) {
- err = -ENOMEM;
- goto err;
- }
-
- skb = iptunnel_handle_offloads(skb, udp_sum, type);
- if (IS_ERR(skb)) {
- err = -EINVAL;
- goto err;
- }
-
- vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
- vxh->vx_flags = htonl(VXLAN_HF_VNI);
- vxh->vx_vni = vni;
-
- if (type & SKB_GSO_TUNNEL_REMCSUM) {
- u32 data = (skb_checksum_start_offset(skb) - hdrlen) >>
- VXLAN_RCO_SHIFT;
-
- if (skb->csum_offset == offsetof(struct udphdr, check))
- data |= VXLAN_RCO_UDP;
-
- vxh->vx_vni |= htonl(data);
- vxh->vx_flags |= htonl(VXLAN_HF_RCO);
-
- if (!skb_is_gso(skb)) {
- skb->ip_summed = CHECKSUM_NONE;
- skb->encapsulation = 0;
- }
- }
-
- if (vxflags & VXLAN_F_GBP)
- vxlan_build_gbp_hdr(vxh, vxflags, md);
-
- skb_set_inner_protocol(skb, htons(ETH_P_TEB));
-
- udp_tunnel6_xmit_skb(dst, sk, skb, dev, saddr, daddr, prio,
- ttl, src_port, dst_port,
- !!(vxflags & VXLAN_F_UDP_ZERO_CSUM6_TX));
- return 0;
-err:
- dst_release(dst);
- return err;
-}
-#endif
-
-static int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
- __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
- __be16 src_port, __be16 dst_port, __be32 vni,
- struct vxlan_metadata *md, bool xnet, u32 vxflags)
-{
- struct vxlanhdr *vxh;
- int min_headroom;
- int err;
- bool udp_sum = !!(vxflags & VXLAN_F_UDP_CSUM);
- int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
- u16 hdrlen = sizeof(struct vxlanhdr);
-
- if ((vxflags & VXLAN_F_REMCSUM_TX) &&
- skb->ip_summed == CHECKSUM_PARTIAL) {
- int csum_start = skb_checksum_start_offset(skb);
-
- if (csum_start <= VXLAN_MAX_REMCSUM_START &&
- !(csum_start & VXLAN_RCO_SHIFT_MASK) &&
- (skb->csum_offset == offsetof(struct udphdr, check) ||
- skb->csum_offset == offsetof(struct tcphdr, check))) {
- udp_sum = false;
- type |= SKB_GSO_TUNNEL_REMCSUM;
- }
- }
-
- min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
- + VXLAN_HLEN + sizeof(struct iphdr)
+ + VXLAN_HLEN + iphdr_len
+ (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
/* Need space for new headers (invalidates iph ptr) */
vxlan_build_gbp_hdr(vxh, vxflags, md);
skb_set_inner_protocol(skb, htons(ETH_P_TEB));
-
- udp_tunnel_xmit_skb(rt, sk, skb, src, dst, tos, ttl, df,
- src_port, dst_port, xnet,
- !(vxflags & VXLAN_F_UDP_CSUM));
return 0;
}
+static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
+ struct sk_buff *skb, int oif, u8 tos,
+ __be32 daddr, __be32 *saddr)
+{
+ struct rtable *rt = NULL;
+ struct flowi4 fl4;
+
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.flowi4_oif = oif;
+ fl4.flowi4_tos = RT_TOS(tos);
+ fl4.flowi4_mark = skb->mark;
+ fl4.flowi4_proto = IPPROTO_UDP;
+ fl4.daddr = daddr;
+ fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr;
+
+ rt = ip_route_output_key(vxlan->net, &fl4);
+ if (!IS_ERR(rt))
+ *saddr = fl4.saddr;
+ return rt;
+}
+
#if IS_ENABLED(CONFIG_IPV6)
static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
struct sk_buff *skb, int oif,
struct sock *sk;
struct rtable *rt = NULL;
const struct iphdr *old_iph;
- struct flowi4 fl4;
union vxlan_addr *dst;
union vxlan_addr remote_ip;
struct vxlan_metadata _md;
__u8 tos, ttl;
int err;
u32 flags = vxlan->flags;
+ bool udp_sum = false;
+ bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev));
info = skb_tunnel_info(skb);
if (info) {
ttl = info->key.ttl;
tos = info->key.tos;
+ udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM);
if (info->options_len)
md = ip_tunnel_info_opts(info);
}
if (dst->sa.sa_family == AF_INET) {
+ __be32 saddr;
+
if (!vxlan->vn4_sock)
goto drop;
sk = vxlan->vn4_sock->sock->sk;
if (info) {
if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)
df = htons(IP_DF);
-
- if (info->key.tun_flags & TUNNEL_CSUM)
- flags |= VXLAN_F_UDP_CSUM;
- else
- flags &= ~VXLAN_F_UDP_CSUM;
+ } else {
+ udp_sum = !!(flags & VXLAN_F_UDP_CSUM);
}
- memset(&fl4, 0, sizeof(fl4));
- fl4.flowi4_oif = rdst ? rdst->remote_ifindex : 0;
- fl4.flowi4_tos = RT_TOS(tos);
- fl4.flowi4_mark = skb->mark;
- fl4.flowi4_proto = IPPROTO_UDP;
- fl4.daddr = dst->sin.sin_addr.s_addr;
- fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr;
-
- rt = ip_route_output_key(vxlan->net, &fl4);
+ rt = vxlan_get_route(vxlan, skb,
+ rdst ? rdst->remote_ifindex : 0, tos,
+ dst->sin.sin_addr.s_addr, &saddr);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n",
&dst->sin.sin_addr.s_addr);
tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
- err = vxlan_xmit_skb(rt, sk, skb, fl4.saddr,
- dst->sin.sin_addr.s_addr, tos, ttl, df,
- src_port, dst_port, htonl(vni << 8), md,
- !net_eq(vxlan->net, dev_net(vxlan->dev)),
- flags);
- if (err < 0) {
- /* skb is already freed. */
- skb = NULL;
- goto rt_tx_error;
- }
+ err = vxlan_build_skb(skb, &rt->dst, sizeof(struct iphdr),
+ htonl(vni << 8), md, flags, udp_sum);
+ if (err < 0)
+ goto xmit_tx_error;
+
+ udp_tunnel_xmit_skb(rt, sk, skb, saddr,
+ dst->sin.sin_addr.s_addr, tos, ttl, df,
+ src_port, dst_port, xnet, !udp_sum);
#if IS_ENABLED(CONFIG_IPV6)
} else {
struct dst_entry *ndst;
return;
}
- if (info) {
- if (info->key.tun_flags & TUNNEL_CSUM)
- flags &= ~VXLAN_F_UDP_ZERO_CSUM6_TX;
- else
- flags |= VXLAN_F_UDP_ZERO_CSUM6_TX;
- }
+ if (!info)
+ udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
ttl = ttl ? : ip6_dst_hoplimit(ndst);
- err = vxlan6_xmit_skb(ndst, sk, skb, dev, &saddr, &dst->sin6.sin6_addr,
- 0, ttl, src_port, dst_port, htonl(vni << 8), md,
- !net_eq(vxlan->net, dev_net(vxlan->dev)),
- flags);
+ skb_scrub_packet(skb, xnet);
+ err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
+ htonl(vni << 8), md, flags, udp_sum);
+ if (err < 0) {
+ dst_release(ndst);
+ return;
+ }
+ udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
+ &saddr, &dst->sin6.sin6_addr,
+ 0, ttl, src_port, dst_port, !udp_sum);
#endif
}
dev->stats.tx_dropped++;
goto tx_free;
+xmit_tx_error:
+ /* skb is already freed. */
+ skb = NULL;
rt_tx_error:
ip_rt_put(rt);
tx_error:
return __vxlan_change_mtu(dev, lowerdev, dst, new_mtu, true);
}
-static int egress_ipv4_tun_info(struct net_device *dev, struct sk_buff *skb,
- struct ip_tunnel_info *info,
- __be16 sport, __be16 dport)
-{
- struct vxlan_dev *vxlan = netdev_priv(dev);
- struct rtable *rt;
- struct flowi4 fl4;
-
- memset(&fl4, 0, sizeof(fl4));
- fl4.flowi4_tos = RT_TOS(info->key.tos);
- fl4.flowi4_mark = skb->mark;
- fl4.flowi4_proto = IPPROTO_UDP;
- fl4.daddr = info->key.u.ipv4.dst;
-
- rt = ip_route_output_key(vxlan->net, &fl4);
- if (IS_ERR(rt))
- return PTR_ERR(rt);
- ip_rt_put(rt);
-
- info->key.u.ipv4.src = fl4.saddr;
- info->key.tp_src = sport;
- info->key.tp_dst = dport;
- return 0;
-}
-
static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
dport = info->key.tp_dst ? : vxlan->cfg.dst_port;
if (ip_tunnel_info_af(info) == AF_INET) {
+ struct rtable *rt;
+
if (!vxlan->vn4_sock)
return -EINVAL;
- return egress_ipv4_tun_info(dev, skb, info, sport, dport);
+ rt = vxlan_get_route(vxlan, skb, 0, info->key.tos,
+ info->key.u.ipv4.dst,
+ &info->key.u.ipv4.src);
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
+ ip_rt_put(rt);
} else {
#if IS_ENABLED(CONFIG_IPV6)
struct dst_entry *ndst;
if (IS_ERR(ndst))
return PTR_ERR(ndst);
dst_release(ndst);
-
- info->key.tp_src = sport;
- info->key.tp_dst = dport;
#else /* !CONFIG_IPV6 */
return -EPFNOSUPPORT;
#endif
}
+ info->key.tp_src = sport;
+ info->key.tp_dst = dport;
return 0;
}
unsigned int stalled_queues;
struct xenbus_watch credit_watch;
+ struct xenbus_watch mcast_ctrl_watch;
spinlock_t lock;
goto abort_transaction;
}
- /* We support multicast-control. */
+ /* We support dynamic multicast-control. */
err = xenbus_printf(xbt, dev->nodename,
"feature-multicast-control", "%d", 1);
if (err) {
goto abort_transaction;
}
+ err = xenbus_printf(xbt, dev->nodename,
+ "feature-dynamic-multicast-control",
+ "%d", 1);
+ if (err) {
+ message = "writing feature-dynamic-multicast-control";
+ goto abort_transaction;
+ }
+
err = xenbus_transaction_end(xbt, 0);
} while (err == -EAGAIN);
}
}
-static int xen_register_watchers(struct xenbus_device *dev, struct xenvif *vif)
+static int xen_register_credit_watch(struct xenbus_device *dev,
+ struct xenvif *vif)
{
int err = 0;
char *node;
return err;
}
-static void xen_unregister_watchers(struct xenvif *vif)
+static void xen_unregister_credit_watch(struct xenvif *vif)
{
if (vif->credit_watch.node) {
unregister_xenbus_watch(&vif->credit_watch);
}
}
+static void xen_mcast_ctrl_changed(struct xenbus_watch *watch,
+ const char **vec, unsigned int len)
+{
+ struct xenvif *vif = container_of(watch, struct xenvif,
+ mcast_ctrl_watch);
+ struct xenbus_device *dev = xenvif_to_xenbus_device(vif);
+ int val;
+
+ if (xenbus_scanf(XBT_NIL, dev->otherend,
+ "request-multicast-control", "%d", &val) < 0)
+ val = 0;
+ vif->multicast_control = !!val;
+}
+
+static int xen_register_mcast_ctrl_watch(struct xenbus_device *dev,
+ struct xenvif *vif)
+{
+ int err = 0;
+ char *node;
+ unsigned maxlen = strlen(dev->otherend) +
+ sizeof("/request-multicast-control");
+
+ if (vif->mcast_ctrl_watch.node) {
+ pr_err_ratelimited("Watch is already registered\n");
+ return -EADDRINUSE;
+ }
+
+ node = kmalloc(maxlen, GFP_KERNEL);
+ if (!node) {
+ pr_err("Failed to allocate memory for watch\n");
+ return -ENOMEM;
+ }
+ snprintf(node, maxlen, "%s/request-multicast-control",
+ dev->otherend);
+ vif->mcast_ctrl_watch.node = node;
+ vif->mcast_ctrl_watch.callback = xen_mcast_ctrl_changed;
+ err = register_xenbus_watch(&vif->mcast_ctrl_watch);
+ if (err) {
+ pr_err("Failed to set watcher %s\n",
+ vif->mcast_ctrl_watch.node);
+ kfree(node);
+ vif->mcast_ctrl_watch.node = NULL;
+ vif->mcast_ctrl_watch.callback = NULL;
+ }
+ return err;
+}
+
+static void xen_unregister_mcast_ctrl_watch(struct xenvif *vif)
+{
+ if (vif->mcast_ctrl_watch.node) {
+ unregister_xenbus_watch(&vif->mcast_ctrl_watch);
+ kfree(vif->mcast_ctrl_watch.node);
+ vif->mcast_ctrl_watch.node = NULL;
+ }
+}
+
+static void xen_register_watchers(struct xenbus_device *dev,
+ struct xenvif *vif)
+{
+ xen_register_credit_watch(dev, vif);
+ xen_register_mcast_ctrl_watch(dev, vif);
+}
+
+static void xen_unregister_watchers(struct xenvif *vif)
+{
+ xen_unregister_mcast_ctrl_watch(vif);
+ xen_unregister_credit_watch(vif);
+}
+
static void unregister_hotplug_status_watch(struct backend_info *be)
{
if (be->have_hotplug_status_watch) {
val = 0;
vif->ipv6_csum = !!val;
- if (xenbus_scanf(XBT_NIL, dev->otherend, "request-multicast-control",
- "%d", &val) < 0)
- val = 0;
- vif->multicast_control = !!val;
-
return 0;
}
union {
char value[0] __aligned(8);
void *ptrs[0] __aligned(8);
+ void __percpu *pptrs[0] __aligned(8);
};
};
#define MAX_TAIL_CALL_CNT 32
int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
int bpf_obj_get_user(const char __user *pathname);
+int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
+int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
+int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
+ u64 flags);
+int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
+ u64 flags);
+
+/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
+ * forced to use 'long' read/writes to try to atomically copy long counters.
+ * Best-effort only. No barriers here, since it _will_ race with concurrent
+ * updates from BPF programs. Called from bpf syscall and mostly used with
+ * size 8 or 16 bytes, so ask compiler to inline it.
+ */
+static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
+{
+ const long *lsrc = src;
+ long *ldst = dst;
+
+ size /= sizeof(long);
+ while (size--)
+ *ldst++ = *lsrc++;
+}
+
/* verify correctness of eBPF program */
int bpf_check(struct bpf_prog **fp, union bpf_attr *attr);
#else
struct u64_stats_sync syncp;
u32 rx_dropped;
u32 tx_dropped;
+ u32 rx_nohandler;
};
struct team;
* do not use this in drivers
* @tx_dropped: Dropped packets by core network,
* do not use this in drivers
+ * @rx_nohandler: nohandler dropped packets by core network on
+ * inactive devices, do not use this in drivers
*
* @wireless_handlers: List of functions to handle Wireless Extensions,
* instead of ioctl,
atomic_long_t rx_dropped;
atomic_long_t tx_dropped;
+ atomic_long_t rx_nohandler;
#ifdef CONFIG_WIRELESS_EXT
const struct iw_handler_def * wireless_handlers;
/* RSS keys are 40 or 52 bytes long */
#define NETDEV_RSS_KEY_LEN 52
-extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN];
+extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly;
void netdev_rss_key_fill(void *buffer, size_t len);
int dev_get_nest_level(struct net_device *dev,
u32 prr_delivered; /* Number of newly delivered packets to
* receiver in Recovery. */
u32 prr_out; /* Total number of pkts sent during Recovery. */
+ u32 delivered; /* Total data packets delivered incl. rexmits */
u32 rcv_wnd; /* Current receiver window */
u32 write_seq; /* Tail(+1) of data held in tcp send buffer */
struct slave *slave);
int bond_3ad_set_carrier(struct bonding *bond);
void bond_3ad_update_lacp_rate(struct bonding *bond);
+void bond_3ad_update_ad_actor_settings(struct bonding *bond);
#endif /* _NET_BOND_3AD_H */
int sysctl_tcp_keepalive_probes;
int sysctl_tcp_keepalive_intvl;
+ int sysctl_tcp_syn_retries;
+ int sysctl_tcp_synack_retries;
+ int sysctl_tcp_syncookies;
+ int sysctl_tcp_reordering;
+ int sysctl_tcp_retries1;
+ int sysctl_tcp_retries2;
+ int sysctl_tcp_orphan_retries;
+ int sysctl_tcp_fin_timeout;
+ unsigned int sysctl_tcp_notsent_lowat;
+
struct ping_group_range ping_group_range;
atomic_t dev_addr_genid;
extern int sysctl_tcp_timestamps;
extern int sysctl_tcp_window_scaling;
extern int sysctl_tcp_sack;
-extern int sysctl_tcp_fin_timeout;
-extern int sysctl_tcp_syn_retries;
-extern int sysctl_tcp_synack_retries;
-extern int sysctl_tcp_retries1;
-extern int sysctl_tcp_retries2;
-extern int sysctl_tcp_orphan_retries;
-extern int sysctl_tcp_syncookies;
extern int sysctl_tcp_fastopen;
extern int sysctl_tcp_retrans_collapse;
extern int sysctl_tcp_stdurg;
extern int sysctl_tcp_early_retrans;
extern int sysctl_tcp_limit_output_bytes;
extern int sysctl_tcp_challenge_ack_limit;
-extern unsigned int sysctl_tcp_notsent_lowat;
extern int sysctl_tcp_min_tso_segs;
extern int sysctl_tcp_min_rtt_wlen;
extern int sysctl_tcp_autocorking;
void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);
void tcp_reset(struct sock *sk);
void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb);
+void tcp_fin(struct sock *sk);
/* tcp_timer.c */
void tcp_init_xmit_timers(struct sock *);
*/
static inline void tcp_enable_early_retrans(struct tcp_sock *tp)
{
+ struct net *net = sock_net((struct sock *)tp);
+
tp->do_early_retrans = sysctl_tcp_early_retrans &&
sysctl_tcp_early_retrans < 4 && !sysctl_tcp_thin_dupack &&
- sysctl_tcp_reordering == 3;
+ net->ipv4.sysctl_tcp_reordering == 3;
}
static inline void tcp_disable_early_retrans(struct tcp_sock *tp)
static inline int tcp_fin_time(const struct sock *sk)
{
- int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout;
+ int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout;
const int rto = inet_csk(sk)->icsk_rto;
if (fin_timeout < (rto << 2) - (rto >> 1))
extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
int tcp_fastopen_reset_cipher(void *key, unsigned int len);
+void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb);
struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct tcp_fastopen_cookie *foc,
static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
{
- return tp->notsent_lowat ?: sysctl_tcp_notsent_lowat;
+ struct net *net = sock_net((struct sock *)tp);
+ return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat;
}
static inline bool tcp_stream_memory_free(const struct sock *sk)
#include <linux/udp.h>
#include <net/dst_metadata.h>
+/* VXLAN protocol (RFC 7348) header:
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |R|R|R|R|I|R|R|R| Reserved |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | VXLAN Network Identifier (VNI) | Reserved |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * I = VXLAN Network Identifier (VNI) present.
+ */
+struct vxlanhdr {
+ __be32 vx_flags;
+ __be32 vx_vni;
+};
+
+/* VXLAN header flags. */
+#define VXLAN_HF_VNI BIT(27)
+
+#define VXLAN_N_VID (1u << 24)
+#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
+#define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8)
+#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
+
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
+#define FDB_HASH_BITS 8
+#define FDB_HASH_SIZE (1<<FDB_HASH_BITS)
+
+/* Remote checksum offload for VXLAN (VXLAN_F_REMCSUM_[RT]X):
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |R|R|R|R|I|R|R|R|R|R|C| Reserved |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | VXLAN Network Identifier (VNI) |O| Csum start |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * C = Remote checksum offload bit. When set indicates that the
+ * remote checksum offload data is present.
+ *
+ * O = Offset bit. Indicates the checksum offset relative to
+ * checksum start.
+ *
+ * Csum start = Checksum start divided by two.
+ *
+ * http://tools.ietf.org/html/draft-herbert-vxlan-rco
+ */
+
+/* VXLAN-RCO header flags. */
+#define VXLAN_HF_RCO BIT(21)
+
+/* Remote checksum offload header option */
+#define VXLAN_RCO_MASK 0x7f /* Last byte of vni field */
+#define VXLAN_RCO_UDP 0x80 /* Indicate UDP RCO (TCP when not set *) */
+#define VXLAN_RCO_SHIFT 1 /* Left shift of start */
+#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1)
+#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT)
/*
- * VXLAN Group Based Policy Extension:
+ * VXLAN Group Based Policy Extension (VXLAN_F_GBP):
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * |1|-|-|-|1|-|-|-|R|D|R|R|A|R|R|R| Group Policy ID |
+ * |G|R|R|R|I|R|R|R|R|D|R|R|A|R|R|R| Group Policy ID |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
* | VXLAN Network Identifier (VNI) | Reserved |
* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
+ * G = Group Policy ID present.
+ *
* D = Don't Learn bit. When set, this bit indicates that the egress
* VTEP MUST NOT learn the source address of the encapsulated frame.
*
* this packet. Policies MUST NOT be applied by devices when the
* A bit is set.
*
- * [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy
+ * https://tools.ietf.org/html/draft-smith-vxlan-group-policy
*/
struct vxlanhdr_gbp {
- __u8 vx_flags;
+ u8 vx_flags;
#ifdef __LITTLE_ENDIAN_BITFIELD
- __u8 reserved_flags1:3,
+ u8 reserved_flags1:3,
policy_applied:1,
reserved_flags2:2,
dont_learn:1,
reserved_flags3:1;
#elif defined(__BIG_ENDIAN_BITFIELD)
- __u8 reserved_flags1:1,
+ u8 reserved_flags1:1,
dont_learn:1,
reserved_flags2:2,
policy_applied:1,
__be32 vx_vni;
};
+/* VXLAN-GBP header flags. */
+#define VXLAN_HF_GBP BIT(31)
+
#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | 0xFFFFFF)
/* skb->mark mapping
#define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16)
#define VXLAN_GBP_ID_MASK (0xFFFF)
-/* VXLAN protocol header:
- * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * |G|R|R|R|I|R|R|C| Reserved |
- * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * | VXLAN Network Identifier (VNI) | Reserved |
- * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- *
- * G = 1 Group Policy (VXLAN-GBP)
- * I = 1 VXLAN Network Identifier (VNI) present
- * C = 1 Remote checksum offload (RCO)
- */
-struct vxlanhdr {
- __be32 vx_flags;
- __be32 vx_vni;
-};
-
-/* VXLAN header flags. */
-#define VXLAN_HF_RCO BIT(21)
-#define VXLAN_HF_VNI BIT(27)
-#define VXLAN_HF_GBP BIT(31)
-
-/* Remote checksum offload header option */
-#define VXLAN_RCO_MASK 0x7f /* Last byte of vni field */
-#define VXLAN_RCO_UDP 0x80 /* Indicate UDP RCO (TCP when not set *) */
-#define VXLAN_RCO_SHIFT 1 /* Left shift of start */
-#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1)
-#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT)
-
-#define VXLAN_N_VID (1u << 24)
-#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
-#define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8)
-#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
-
-#define VNI_HASH_BITS 10
-#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
-#define FDB_HASH_BITS 8
-#define FDB_HASH_SIZE (1<<FDB_HASH_BITS)
-
struct vxlan_metadata {
u32 gbp;
};
int remote_ifindex;
int mtu;
__be16 dst_port;
- __u16 port_min;
- __u16 port_max;
- __u8 tos;
- __u8 ttl;
+ u16 port_min;
+ u16 port_max;
+ u8 tos;
+ u8 ttl;
u32 flags;
unsigned long age_interval;
unsigned int addrmax;
--- /dev/null
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sunvnet
+
+#if !defined(_TRACE_SUNVNET_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SUNVNET_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(vnet_rx_one,
+
+ TP_PROTO(int lsid, int rsid, int index, int needs_ack),
+
+ TP_ARGS(lsid, rsid, index, needs_ack),
+
+ TP_STRUCT__entry(
+ __field(int, lsid)
+ __field(int, rsid)
+ __field(int, index)
+ __field(int, needs_ack)
+ ),
+
+ TP_fast_assign(
+ __entry->lsid = lsid;
+ __entry->rsid = rsid;
+ __entry->index = index;
+ __entry->needs_ack = needs_ack;
+ ),
+
+ TP_printk("(%x:%x) walk_rx_one index %d; needs_ack %d",
+ __entry->lsid, __entry->rsid,
+ __entry->index, __entry->needs_ack)
+);
+
+DECLARE_EVENT_CLASS(vnet_tx_stopped_ack_template,
+
+ TP_PROTO(int lsid, int rsid, int ack_end, int npkts),
+
+ TP_ARGS(lsid, rsid, ack_end, npkts),
+
+ TP_STRUCT__entry(
+ __field(int, lsid)
+ __field(int, rsid)
+ __field(int, ack_end)
+ __field(int, npkts)
+ ),
+
+ TP_fast_assign(
+ __entry->lsid = lsid;
+ __entry->rsid = rsid;
+ __entry->ack_end = ack_end;
+ __entry->npkts = npkts;
+ ),
+
+ TP_printk("(%x:%x) stopped ack for %d; npkts %d",
+ __entry->lsid, __entry->rsid,
+ __entry->ack_end, __entry->npkts)
+);
+DEFINE_EVENT(vnet_tx_stopped_ack_template, vnet_tx_send_stopped_ack,
+ TP_PROTO(int lsid, int rsid, int ack_end, int npkts),
+ TP_ARGS(lsid, rsid, ack_end, npkts));
+DEFINE_EVENT(vnet_tx_stopped_ack_template, vnet_tx_defer_stopped_ack,
+ TP_PROTO(int lsid, int rsid, int ack_end, int npkts),
+ TP_ARGS(lsid, rsid, ack_end, npkts));
+DEFINE_EVENT(vnet_tx_stopped_ack_template, vnet_tx_pending_stopped_ack,
+ TP_PROTO(int lsid, int rsid, int ack_end, int npkts),
+ TP_ARGS(lsid, rsid, ack_end, npkts));
+
+TRACE_EVENT(vnet_rx_stopped_ack,
+
+ TP_PROTO(int lsid, int rsid, int end),
+
+ TP_ARGS(lsid, rsid, end),
+
+ TP_STRUCT__entry(
+ __field(int, lsid)
+ __field(int, rsid)
+ __field(int, end)
+ ),
+
+ TP_fast_assign(
+ __entry->lsid = lsid;
+ __entry->rsid = rsid;
+ __entry->end = end;
+ ),
+
+ TP_printk("(%x:%x) stopped ack for index %d",
+ __entry->lsid, __entry->rsid, __entry->end)
+);
+
+TRACE_EVENT(vnet_tx_trigger,
+
+ TP_PROTO(int lsid, int rsid, int start, int err),
+
+ TP_ARGS(lsid, rsid, start, err),
+
+ TP_STRUCT__entry(
+ __field(int, lsid)
+ __field(int, rsid)
+ __field(int, start)
+ __field(int, err)
+ ),
+
+ TP_fast_assign(
+ __entry->lsid = lsid;
+ __entry->rsid = rsid;
+ __entry->start = start;
+ __entry->err = err;
+ ),
+
+ TP_printk("(%x:%x) Tx trigger for %d sent with err %d %s",
+ __entry->lsid, __entry->rsid, __entry->start,
+ __entry->err, __entry->err > 0 ? "(ok)" : " ")
+);
+
+TRACE_EVENT(vnet_skip_tx_trigger,
+
+ TP_PROTO(int lsid, int rsid, int last),
+
+ TP_ARGS(lsid, rsid, last),
+
+ TP_STRUCT__entry(
+ __field(int, lsid)
+ __field(int, rsid)
+ __field(int, last)
+ ),
+
+ TP_fast_assign(
+ __entry->lsid = lsid;
+ __entry->rsid = rsid;
+ __entry->last = last;
+ ),
+
+ TP_printk("(%x:%x) Skip Tx trigger. Last trigger sent was %d",
+ __entry->lsid, __entry->rsid, __entry->last)
+);
+#endif /* _TRACE_SOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
BPF_MAP_TYPE_ARRAY,
BPF_MAP_TYPE_PROG_ARRAY,
BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+ BPF_MAP_TYPE_PERCPU_HASH,
+ BPF_MAP_TYPE_PERCPU_ARRAY,
};
enum bpf_prog_type {
#define SPEED_UNKNOWN -1
+static inline int ethtool_validate_speed(__u32 speed)
+{
+ switch (speed) {
+ case SPEED_10:
+ case SPEED_100:
+ case SPEED_1000:
+ case SPEED_2500:
+ case SPEED_5000:
+ case SPEED_10000:
+ case SPEED_20000:
+ case SPEED_25000:
+ case SPEED_40000:
+ case SPEED_50000:
+ case SPEED_56000:
+ case SPEED_100000:
+ case SPEED_UNKNOWN:
+ return 1;
+ }
+
+ return 0;
+}
+
/* Duplex, half or full. */
#define DUPLEX_HALF 0x00
#define DUPLEX_FULL 0x01
#define DUPLEX_UNKNOWN 0xff
+static inline int ethtool_validate_duplex(__u8 duplex)
+{
+ switch (duplex) {
+ case DUPLEX_HALF:
+ case DUPLEX_FULL:
+ case DUPLEX_UNKNOWN:
+ return 1;
+ }
+
+ return 0;
+}
+
/* Which connector port. */
#define PORT_TP 0x00
#define PORT_AUI 0x01
#define MDB_TEMPORARY 0
#define MDB_PERMANENT 1
__u8 state;
+#define MDB_FLAGS_OFFLOAD (1 << 0)
+ __u8 flags;
__u16 vid;
struct {
union {
/* for cslip etc */
__u32 rx_compressed;
__u32 tx_compressed;
+
+ __u32 rx_nohandler; /* dropped, no handler found */
};
/* The main device statistics structure */
/* for cslip etc */
__u64 rx_compressed;
__u64 tx_compressed;
+
+ __u64 rx_nohandler; /* dropped, no handler found */
};
/* The struct should be in sync with struct ifmap */
#define IFLA_VRF_MAX (__IFLA_VRF_MAX - 1)
+enum {
+ IFLA_VRF_PORT_UNSPEC,
+ IFLA_VRF_PORT_TABLE,
+ __IFLA_VRF_PORT_MAX
+};
+
+#define IFLA_VRF_PORT_MAX (__IFLA_VRF_PORT_MAX - 1)
+
/* IPVLAN section */
enum {
IFLA_IPVLAN_UNSPEC,
#include <linux/filter.h>
#include <linux/perf_event.h>
+static void bpf_array_free_percpu(struct bpf_array *array)
+{
+ int i;
+
+ for (i = 0; i < array->map.max_entries; i++)
+ free_percpu(array->pptrs[i]);
+}
+
+static int bpf_array_alloc_percpu(struct bpf_array *array)
+{
+ void __percpu *ptr;
+ int i;
+
+ for (i = 0; i < array->map.max_entries; i++) {
+ ptr = __alloc_percpu_gfp(array->elem_size, 8,
+ GFP_USER | __GFP_NOWARN);
+ if (!ptr) {
+ bpf_array_free_percpu(array);
+ return -ENOMEM;
+ }
+ array->pptrs[i] = ptr;
+ }
+
+ return 0;
+}
+
/* Called from syscall */
static struct bpf_map *array_map_alloc(union bpf_attr *attr)
{
+ bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
struct bpf_array *array;
- u32 elem_size, array_size;
+ u64 array_size;
+ u32 elem_size;
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
elem_size = round_up(attr->value_size, 8);
- /* check round_up into zero and u32 overflow */
- if (elem_size == 0 ||
- attr->max_entries > (U32_MAX - PAGE_SIZE - sizeof(*array)) / elem_size)
+ array_size = sizeof(*array);
+ if (percpu)
+ array_size += (u64) attr->max_entries * sizeof(void *);
+ else
+ array_size += (u64) attr->max_entries * elem_size;
+
+ /* make sure there is no u32 overflow later in round_up() */
+ if (array_size >= U32_MAX - PAGE_SIZE)
return ERR_PTR(-ENOMEM);
- array_size = sizeof(*array) + attr->max_entries * elem_size;
/* allocate all map elements and zero-initialize them */
array = kzalloc(array_size, GFP_USER | __GFP_NOWARN);
}
/* copy mandatory map attributes */
+ array->map.map_type = attr->map_type;
array->map.key_size = attr->key_size;
array->map.value_size = attr->value_size;
array->map.max_entries = attr->max_entries;
- array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT;
array->elem_size = elem_size;
+ if (!percpu)
+ goto out;
+
+ array_size += (u64) attr->max_entries * elem_size * num_possible_cpus();
+
+ if (array_size >= U32_MAX - PAGE_SIZE ||
+ elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
+ kvfree(array);
+ return ERR_PTR(-ENOMEM);
+ }
+out:
+ array->map.pages = round_up(array_size, PAGE_SIZE) >> PAGE_SHIFT;
+
return &array->map;
}
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
- if (index >= array->map.max_entries)
+ if (unlikely(index >= array->map.max_entries))
return NULL;
return array->value + array->elem_size * index;
}
+/* Called from eBPF program */
+static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ u32 index = *(u32 *)key;
+
+ if (unlikely(index >= array->map.max_entries))
+ return NULL;
+
+ return this_cpu_ptr(array->pptrs[index]);
+}
+
+int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ u32 index = *(u32 *)key;
+ void __percpu *pptr;
+ int cpu, off = 0;
+ u32 size;
+
+ if (unlikely(index >= array->map.max_entries))
+ return -ENOENT;
+
+ /* per_cpu areas are zero-filled and bpf programs can only
+ * access 'value_size' of them, so copying rounded areas
+ * will not leak any kernel data
+ */
+ size = round_up(map->value_size, 8);
+ rcu_read_lock();
+ pptr = array->pptrs[index];
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size);
+ off += size;
+ }
+ rcu_read_unlock();
+ return 0;
+}
+
/* Called from syscall */
static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
struct bpf_array *array = container_of(map, struct bpf_array, map);
u32 index = *(u32 *)key;
- if (map_flags > BPF_EXIST)
+ if (unlikely(map_flags > BPF_EXIST))
/* unknown flags */
return -EINVAL;
- if (index >= array->map.max_entries)
+ if (unlikely(index >= array->map.max_entries))
/* all elements were pre-allocated, cannot insert a new one */
return -E2BIG;
- if (map_flags == BPF_NOEXIST)
+ if (unlikely(map_flags == BPF_NOEXIST))
/* all elements already exist */
return -EEXIST;
- memcpy(array->value + array->elem_size * index, value, map->value_size);
+ if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ memcpy(this_cpu_ptr(array->pptrs[index]),
+ value, map->value_size);
+ else
+ memcpy(array->value + array->elem_size * index,
+ value, map->value_size);
+ return 0;
+}
+
+int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
+ u64 map_flags)
+{
+ struct bpf_array *array = container_of(map, struct bpf_array, map);
+ u32 index = *(u32 *)key;
+ void __percpu *pptr;
+ int cpu, off = 0;
+ u32 size;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ /* unknown flags */
+ return -EINVAL;
+
+ if (unlikely(index >= array->map.max_entries))
+ /* all elements were pre-allocated, cannot insert a new one */
+ return -E2BIG;
+
+ if (unlikely(map_flags == BPF_NOEXIST))
+ /* all elements already exist */
+ return -EEXIST;
+
+ /* the user space will provide round_up(value_size, 8) bytes that
+ * will be copied into per-cpu area. bpf programs can only access
+ * value_size of it. During lookup the same extra bytes will be
+ * returned or zeros which were zero-filled by percpu_alloc,
+ * so no kernel data leaks possible
+ */
+ size = round_up(map->value_size, 8);
+ rcu_read_lock();
+ pptr = array->pptrs[index];
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size);
+ off += size;
+ }
+ rcu_read_unlock();
return 0;
}
*/
synchronize_rcu();
+ if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ bpf_array_free_percpu(array);
+
kvfree(array);
}
.type = BPF_MAP_TYPE_ARRAY,
};
+static const struct bpf_map_ops percpu_array_ops = {
+ .map_alloc = array_map_alloc,
+ .map_free = array_map_free,
+ .map_get_next_key = array_map_get_next_key,
+ .map_lookup_elem = percpu_array_map_lookup_elem,
+ .map_update_elem = array_map_update_elem,
+ .map_delete_elem = array_map_delete_elem,
+};
+
+static struct bpf_map_type_list percpu_array_type __read_mostly = {
+ .ops = &percpu_array_ops,
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+};
+
static int __init register_array_map(void)
{
bpf_register_map_type(&array_type);
+ bpf_register_map_type(&percpu_array_type);
return 0;
}
late_initcall(register_array_map);
struct htab_elem {
struct hlist_node hash_node;
struct rcu_head rcu;
- u32 hash;
+ union {
+ u32 hash;
+ u32 key_size;
+ };
char key[0] __aligned(8);
};
/* Called from syscall */
static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
{
+ bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_HASH;
struct bpf_htab *htab;
int err, i;
+ u64 cost;
htab = kzalloc(sizeof(*htab), GFP_USER);
if (!htab)
return ERR_PTR(-ENOMEM);
/* mandatory map attributes */
+ htab->map.map_type = attr->map_type;
htab->map.key_size = attr->key_size;
htab->map.value_size = attr->value_size;
htab->map.max_entries = attr->max_entries;
*/
goto free_htab;
+ if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE)
+ /* make sure the size for pcpu_alloc() is reasonable */
+ goto free_htab;
+
htab->elem_size = sizeof(struct htab_elem) +
- round_up(htab->map.key_size, 8) +
- htab->map.value_size;
+ round_up(htab->map.key_size, 8);
+ if (percpu)
+ htab->elem_size += sizeof(void *);
+ else
+ htab->elem_size += htab->map.value_size;
/* prevent zero size kmalloc and check for u32 overflow */
if (htab->n_buckets == 0 ||
htab->n_buckets > U32_MAX / sizeof(struct bucket))
goto free_htab;
- if ((u64) htab->n_buckets * sizeof(struct bucket) +
- (u64) htab->elem_size * htab->map.max_entries >=
- U32_MAX - PAGE_SIZE)
+ cost = (u64) htab->n_buckets * sizeof(struct bucket) +
+ (u64) htab->elem_size * htab->map.max_entries;
+
+ if (percpu)
+ cost += (u64) round_up(htab->map.value_size, 8) *
+ num_possible_cpus() * htab->map.max_entries;
+
+ if (cost >= U32_MAX - PAGE_SIZE)
/* make sure page count doesn't overflow */
goto free_htab;
- htab->map.pages = round_up(htab->n_buckets * sizeof(struct bucket) +
- htab->elem_size * htab->map.max_entries,
- PAGE_SIZE) >> PAGE_SHIFT;
+ htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
err = -ENOMEM;
htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket),
}
/* Called from syscall or from eBPF program */
-static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
+static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
struct hlist_head *head;
l = lookup_elem_raw(head, hash, key, key_size);
+ return l;
+}
+
+static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct htab_elem *l = __htab_map_lookup_elem(map, key);
+
if (l)
return l->key + round_up(map->key_size, 8);
return -ENOENT;
}
+
+static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
+ void __percpu *pptr)
+{
+ *(void __percpu **)(l->key + key_size) = pptr;
+}
+
+static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size)
+{
+ return *(void __percpu **)(l->key + key_size);
+}
+
+static void htab_percpu_elem_free(struct htab_elem *l)
+{
+ free_percpu(htab_elem_get_ptr(l, l->key_size));
+ kfree(l);
+}
+
+static void htab_percpu_elem_free_rcu(struct rcu_head *head)
+{
+ struct htab_elem *l = container_of(head, struct htab_elem, rcu);
+
+ htab_percpu_elem_free(l);
+}
+
+static void free_htab_elem(struct htab_elem *l, bool percpu, u32 key_size)
+{
+ if (percpu) {
+ l->key_size = key_size;
+ call_rcu(&l->rcu, htab_percpu_elem_free_rcu);
+ } else {
+ kfree_rcu(l, rcu);
+ }
+}
+
+static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
+ void *value, u32 key_size, u32 hash,
+ bool percpu, bool onallcpus)
+{
+ u32 size = htab->map.value_size;
+ struct htab_elem *l_new;
+ void __percpu *pptr;
+
+ l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
+ if (!l_new)
+ return NULL;
+
+ memcpy(l_new->key, key, key_size);
+ if (percpu) {
+ /* round up value_size to 8 bytes */
+ size = round_up(size, 8);
+
+ /* alloc_percpu zero-fills */
+ pptr = __alloc_percpu_gfp(size, 8, GFP_ATOMIC | __GFP_NOWARN);
+ if (!pptr) {
+ kfree(l_new);
+ return NULL;
+ }
+
+ if (!onallcpus) {
+ /* copy true value_size bytes */
+ memcpy(this_cpu_ptr(pptr), value, htab->map.value_size);
+ } else {
+ int off = 0, cpu;
+
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(per_cpu_ptr(pptr, cpu),
+ value + off, size);
+ off += size;
+ }
+ }
+ htab_elem_set_ptr(l_new, key_size, pptr);
+ } else {
+ memcpy(l_new->key + round_up(key_size, 8), value, size);
+ }
+
+ l_new->hash = hash;
+ return l_new;
+}
+
+static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
+ u64 map_flags)
+{
+ if (!l_old && unlikely(atomic_read(&htab->count) >= htab->map.max_entries))
+ /* if elem with this 'key' doesn't exist and we've reached
+ * max_entries limit, fail insertion of new elem
+ */
+ return -E2BIG;
+
+ if (l_old && map_flags == BPF_NOEXIST)
+ /* elem already exists */
+ return -EEXIST;
+
+ if (!l_old && map_flags == BPF_EXIST)
+ /* elem doesn't exist, cannot update it */
+ return -ENOENT;
+
+ return 0;
+}
+
/* Called from syscall or from eBPF program */
static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,
u64 map_flags)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
- struct htab_elem *l_new, *l_old;
+ struct htab_elem *l_new = NULL, *l_old;
struct hlist_head *head;
- struct bucket *b;
unsigned long flags;
- u32 key_size;
+ struct bucket *b;
+ u32 key_size, hash;
int ret;
- if (map_flags > BPF_EXIST)
+ if (unlikely(map_flags > BPF_EXIST))
/* unknown flags */
return -EINVAL;
WARN_ON_ONCE(!rcu_read_lock_held());
- /* allocate new element outside of lock */
- l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
- if (!l_new)
- return -ENOMEM;
-
key_size = map->key_size;
- memcpy(l_new->key, key, key_size);
- memcpy(l_new->key + round_up(key_size, 8), value, map->value_size);
+ hash = htab_map_hash(key, key_size);
+
+ /* allocate new element outside of the lock, since
+ * we're most likley going to insert it
+ */
+ l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false);
+ if (!l_new)
+ return -ENOMEM;
- l_new->hash = htab_map_hash(l_new->key, key_size);
- b = __select_bucket(htab, l_new->hash);
+ b = __select_bucket(htab, hash);
head = &b->head;
/* bpf_map_update_elem() can be called in_irq() */
raw_spin_lock_irqsave(&b->lock, flags);
- l_old = lookup_elem_raw(head, l_new->hash, key, key_size);
+ l_old = lookup_elem_raw(head, hash, key, key_size);
- if (!l_old && unlikely(atomic_read(&htab->count) >= map->max_entries)) {
- /* if elem with this 'key' doesn't exist and we've reached
- * max_entries limit, fail insertion of new elem
- */
- ret = -E2BIG;
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
goto err;
- }
- if (l_old && map_flags == BPF_NOEXIST) {
- /* elem already exists */
- ret = -EEXIST;
- goto err;
- }
-
- if (!l_old && map_flags == BPF_EXIST) {
- /* elem doesn't exist, cannot update it */
- ret = -ENOENT;
- goto err;
- }
-
- /* add new element to the head of the list, so that concurrent
- * search will find it before old elem
+ /* add new element to the head of the list, so that
+ * concurrent search will find it before old elem
*/
hlist_add_head_rcu(&l_new->hash_node, head);
if (l_old) {
atomic_inc(&htab->count);
}
raw_spin_unlock_irqrestore(&b->lock, flags);
-
return 0;
err:
raw_spin_unlock_irqrestore(&b->lock, flags);
return ret;
}
+static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags,
+ bool onallcpus)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct htab_elem *l_new = NULL, *l_old;
+ struct hlist_head *head;
+ unsigned long flags;
+ struct bucket *b;
+ u32 key_size, hash;
+ int ret;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ /* unknown flags */
+ return -EINVAL;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ key_size = map->key_size;
+
+ hash = htab_map_hash(key, key_size);
+
+ b = __select_bucket(htab, hash);
+ head = &b->head;
+
+ /* bpf_map_update_elem() can be called in_irq() */
+ raw_spin_lock_irqsave(&b->lock, flags);
+
+ l_old = lookup_elem_raw(head, hash, key, key_size);
+
+ ret = check_flags(htab, l_old, map_flags);
+ if (ret)
+ goto err;
+
+ if (l_old) {
+ void __percpu *pptr = htab_elem_get_ptr(l_old, key_size);
+ u32 size = htab->map.value_size;
+
+ /* per-cpu hash map can update value in-place */
+ if (!onallcpus) {
+ memcpy(this_cpu_ptr(pptr), value, size);
+ } else {
+ int off = 0, cpu;
+
+ size = round_up(size, 8);
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(per_cpu_ptr(pptr, cpu),
+ value + off, size);
+ off += size;
+ }
+ }
+ } else {
+ l_new = alloc_htab_elem(htab, key, value, key_size,
+ hash, true, onallcpus);
+ if (!l_new) {
+ ret = -ENOMEM;
+ goto err;
+ }
+ hlist_add_head_rcu(&l_new->hash_node, head);
+ atomic_inc(&htab->count);
+ }
+ ret = 0;
+err:
+ raw_spin_unlock_irqrestore(&b->lock, flags);
+ return ret;
+}
+
+static int htab_percpu_map_update_elem(struct bpf_map *map, void *key,
+ void *value, u64 map_flags)
+{
+ return __htab_percpu_map_update_elem(map, key, value, map_flags, false);
+}
+
/* Called from syscall or from eBPF program */
static int htab_map_delete_elem(struct bpf_map *map, void *key)
{
struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ bool percpu = map->map_type == BPF_MAP_TYPE_PERCPU_HASH;
struct hlist_head *head;
struct bucket *b;
struct htab_elem *l;
if (l) {
hlist_del_rcu(&l->hash_node);
atomic_dec(&htab->count);
- kfree_rcu(l, rcu);
+ free_htab_elem(l, percpu, key_size);
ret = 0;
}
hlist_for_each_entry_safe(l, n, head, hash_node) {
hlist_del_rcu(&l->hash_node);
atomic_dec(&htab->count);
- kfree(l);
+ if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) {
+ l->key_size = htab->map.key_size;
+ htab_percpu_elem_free(l);
+ } else {
+ kfree(l);
+ }
}
}
}
.type = BPF_MAP_TYPE_HASH,
};
+/* Called from eBPF program */
+static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct htab_elem *l = __htab_map_lookup_elem(map, key);
+
+ if (l)
+ return this_cpu_ptr(htab_elem_get_ptr(l, map->key_size));
+ else
+ return NULL;
+}
+
+int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value)
+{
+ struct htab_elem *l;
+ void __percpu *pptr;
+ int ret = -ENOENT;
+ int cpu, off = 0;
+ u32 size;
+
+ /* per_cpu areas are zero-filled and bpf programs can only
+ * access 'value_size' of them, so copying rounded areas
+ * will not leak any kernel data
+ */
+ size = round_up(map->value_size, 8);
+ rcu_read_lock();
+ l = __htab_map_lookup_elem(map, key);
+ if (!l)
+ goto out;
+ pptr = htab_elem_get_ptr(l, map->key_size);
+ for_each_possible_cpu(cpu) {
+ bpf_long_memcpy(value + off,
+ per_cpu_ptr(pptr, cpu), size);
+ off += size;
+ }
+ ret = 0;
+out:
+ rcu_read_unlock();
+ return ret;
+}
+
+int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
+ u64 map_flags)
+{
+ return __htab_percpu_map_update_elem(map, key, value, map_flags, true);
+}
+
+static const struct bpf_map_ops htab_percpu_ops = {
+ .map_alloc = htab_map_alloc,
+ .map_free = htab_map_free,
+ .map_get_next_key = htab_map_get_next_key,
+ .map_lookup_elem = htab_percpu_map_lookup_elem,
+ .map_update_elem = htab_percpu_map_update_elem,
+ .map_delete_elem = htab_map_delete_elem,
+};
+
+static struct bpf_map_type_list htab_percpu_type __read_mostly = {
+ .ops = &htab_percpu_ops,
+ .type = BPF_MAP_TYPE_PERCPU_HASH,
+};
+
static int __init register_htab_map(void)
{
bpf_register_map_type(&htab_type);
+ bpf_register_map_type(&htab_percpu_type);
return 0;
}
late_initcall(register_htab_map);
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value, *ptr;
+ u32 value_size;
struct fd f;
int err;
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ value_size = round_up(map->value_size, 8) * num_possible_cpus();
+ else
+ value_size = map->value_size;
+
err = -ENOMEM;
- value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
+ value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
if (!value)
goto free_key;
- rcu_read_lock();
- ptr = map->ops->map_lookup_elem(map, key);
- if (ptr)
- memcpy(value, ptr, map->value_size);
- rcu_read_unlock();
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) {
+ err = bpf_percpu_hash_copy(map, key, value);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
+ err = bpf_percpu_array_copy(map, key, value);
+ } else {
+ rcu_read_lock();
+ ptr = map->ops->map_lookup_elem(map, key);
+ if (ptr)
+ memcpy(value, ptr, value_size);
+ rcu_read_unlock();
+ err = ptr ? 0 : -ENOENT;
+ }
- err = -ENOENT;
- if (!ptr)
+ if (err)
goto free_value;
err = -EFAULT;
- if (copy_to_user(uvalue, value, map->value_size) != 0)
+ if (copy_to_user(uvalue, value, value_size) != 0)
goto free_value;
err = 0;
int ufd = attr->map_fd;
struct bpf_map *map;
void *key, *value;
+ u32 value_size;
struct fd f;
int err;
if (copy_from_user(key, ukey, map->key_size) != 0)
goto free_key;
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
+ value_size = round_up(map->value_size, 8) * num_possible_cpus();
+ else
+ value_size = map->value_size;
+
err = -ENOMEM;
- value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN);
+ value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
if (!value)
goto free_key;
err = -EFAULT;
- if (copy_from_user(value, uvalue, map->value_size) != 0)
+ if (copy_from_user(value, uvalue, value_size) != 0)
goto free_value;
- /* eBPF program that use maps are running under rcu_read_lock(),
- * therefore all map accessors rely on this fact, so do the same here
- */
- rcu_read_lock();
- err = map->ops->map_update_elem(map, key, value, attr->flags);
- rcu_read_unlock();
+ if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH) {
+ err = bpf_percpu_hash_update(map, key, value, attr->flags);
+ } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
+ err = bpf_percpu_array_update(map, key, value, attr->flags);
+ } else {
+ rcu_read_lock();
+ err = map->ops->map_update_elem(map, key, value, attr->flags);
+ rcu_read_unlock();
+ }
free_value:
kfree(value);
B.A.T.M.A.N. (better approach to mobile ad-hoc networking) is
a routing protocol for multi-hop ad-hoc mesh networks. The
networks may be wired or wireless. See
- http://www.open-mesh.org/ for more information and user space
+ https://www.open-mesh.org/ for more information and user space
tools.
config BATMAN_ADV_BLA
#
-# Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+# Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
#
# Marek Lindner, Simon Wunderlich
#
-/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
* in the given ring buffer
* @lq_recv: pointer to the ring buffer
*
- * Returns computed average value.
+ * Return: computed average value.
*/
static u8 batadv_ring_buffer_avg(const u8 lq_recv[])
{
* @orig_node: the orig_node that has to be changed
* @max_if_num: the current amount of interfaces
*
- * Returns 0 on success, a negative error code otherwise.
+ * Return: 0 on success, a negative error code otherwise.
*/
static int batadv_iv_ogm_orig_add_if(struct batadv_orig_node *orig_node,
int max_if_num)
* @max_if_num: the current amount of interfaces
* @del_if_num: the index of the interface being removed
*
- * Returns 0 on success, a negative error code otherwise.
+ * Return: 0 on success, a negative error code otherwise.
*/
static int batadv_iv_ogm_orig_del_if(struct batadv_orig_node *orig_node,
int max_if_num, int del_if_num)
* @bat_priv: the bat priv with all the soft interface information
* @addr: mac address of the originator
*
- * Returns the originator object corresponding to the passed mac address or NULL
+ * Return: the originator object corresponding to the passed mac address or NULL
* on failure.
* If the object does not exists it is created an initialised.
*/
return new_tq;
}
-/* is there another aggregated packet here? */
+/**
+ * batadv_iv_ogm_aggr_packet - checks if there is another OGM attached
+ * @buff_pos: current position in the skb
+ * @packet_len: total length of the skb
+ * @tvlv_len: tvlv length of the previously considered OGM
+ *
+ * Return: true if there is enough space for another OGM, false otherwise.
+ */
static bool batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len,
__be16 tvlv_len)
{
* @if_outgoing: interface for which the retransmission should be considered
* @forw_packet: the forwarded packet which should be checked
*
- * Returns true if new_packet can be aggregated with forw_packet
+ * Return: true if new_packet can be aggregated with forw_packet
*/
static bool
batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
* @if_incoming: interface where the packet was received
* @if_outgoing: interface for which the retransmission should be considered
*
- * Returns 1 if the link can be considered bidirectional, 0 otherwise
+ * Return: 1 if the link can be considered bidirectional, 0 otherwise
*/
static int batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node,
struct batadv_orig_node *orig_neigh_node,
* @if_incoming: interface on which the OGM packet was received
* @if_outgoing: interface for which the retransmission should be considered
*
- * Returns duplicate status as enum batadv_dup_status
+ * Return: duplicate status as enum batadv_dup_status
*/
static enum batadv_dup_status
batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr,
* @neigh2: the second neighbor object of the comparison
* @if_outgoing2: outgoing interface for the second neighbor
*
- * Returns a value less, equal to or greater than 0 if the metric via neigh1 is
+ * Return: a value less, equal to or greater than 0 if the metric via neigh1 is
* lower, the same as or higher than the metric via neigh2
*/
static int batadv_iv_ogm_neigh_cmp(struct batadv_neigh_node *neigh1,
* @neigh2: the second neighbor object of the comparison
* @if_outgoing2: outgoing interface for the second neighbor
*
- * Returns true if the metric via neigh1 is equally good or better than
+ * Return: true if the metric via neigh1 is equally good or better than
* the metric via neigh2, false otherwise.
*/
static bool
-/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2016 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*
bitmap_shift_left(seq_bits, seq_bits, n, BATADV_TQ_LOCAL_WINDOW_SIZE);
}
-/* receive and process one packet within the sequence number window.
+/**
+ * batadv_bit_get_packet - receive and process one packet within the sequence
+ * number window
+ * @priv: the bat priv with all the soft interface information
+ * @seq_bits: pointer to the sequence number receive packet
+ * @seq_num_diff: difference between the current/received sequence number and
+ * the last sequence number
+ * @set_mark: whether this packet should be marked in seq_bits
*
- * returns:
- * 1 if the window was moved (either new or very old)
+ * Return: 1 if the window was moved (either new or very old),
* 0 if the window was not moved/shifted.
*/
int batadv_bit_get_packet(void *priv, unsigned long *seq_bits, s32 seq_num_diff,
-/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2016 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*
#include <linux/compiler.h>
#include <linux/types.h>
-/* Returns 1 if the corresponding bit in the given seq_bits indicates true
+/**
+ * batadv_test_bit - check if bit is set in the current window
+ *
+ * @seq_bits: pointer to the sequence number receive packet
+ * @last_seqno: latest sequence number in seq_bits
+ * @curr_seqno: sequence number to test for
+ *
+ * Return: 1 if the corresponding bit in the given seq_bits indicates true
* and curr_seqno is within range of last_seqno. Otherwise returns 0.
*/
static inline int batadv_test_bit(const unsigned long *seq_bits,
set_bit(n, seq_bits); /* turn the position on */
}
-/* receive and process one packet, returns 1 if received seq_num is considered
- * new, 0 if old
- */
int batadv_bit_get_packet(void *priv, unsigned long *seq_bits, s32 seq_num_diff,
int set_mark);
-/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich
*
batadv_bla_send_announce(struct batadv_priv *bat_priv,
struct batadv_bla_backbone_gw *backbone_gw);
-/* return the index of the claim */
+/**
+ * batadv_choose_claim - choose the right bucket for a claim.
+ * @data: data to hash
+ * @size: size of the hash table
+ *
+ * Return: the hash index of the claim
+ */
static inline u32 batadv_choose_claim(const void *data, u32 size)
{
struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data;
return hash % size;
}
-/* return the index of the backbone gateway */
+/**
+ * batadv_choose_backbone_gw - choose the right bucket for a backbone gateway.
+ * @data: data to hash
+ * @size: size of the hash table
+ *
+ * Return: the hash index of the backbone gateway
+ */
static inline u32 batadv_choose_backbone_gw(const void *data, u32 size)
{
const struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data;
return hash % size;
}
-/* compares address and vid of two backbone gws */
+/**
+ * batadv_compare_backbone_gw - compare address and vid of two backbone gws
+ * @node: list node of the first entry to compare
+ * @data2: pointer to the second backbone gateway
+ *
+ * Return: 1 if the backbones have the same data, 0 otherwise
+ */
static int batadv_compare_backbone_gw(const struct hlist_node *node,
const void *data2)
{
return 1;
}
-/* compares address and vid of two claims */
+/**
+ * batadv_compare_backbone_gw - compare address and vid of two claims
+ * @node: list node of the first entry to compare
+ * @data2: pointer to the second claims
+ *
+ * Return: 1 if the claim have the same data, 0 otherwise
+ */
static int batadv_compare_claim(const struct hlist_node *node,
const void *data2)
{
return 1;
}
-/* free a backbone gw */
+/**
+ * batadv_compare_backbone_gw - free backbone gw
+ * @backbone_gw: backbone gateway to be free'd
+ */
static void
batadv_backbone_gw_free_ref(struct batadv_bla_backbone_gw *backbone_gw)
{
kfree_rcu(backbone_gw, rcu);
}
-/* finally deinitialize the claim */
+/**
+ * batadv_claim_release - release claim from lists and queue for free after rcu
+ * grace period
+ * @ref: kref pointer of the claim
+ */
static void batadv_claim_release(struct batadv_bla_claim *claim)
{
batadv_backbone_gw_free_ref(claim->backbone_gw);
kfree_rcu(claim, rcu);
}
-/* free a claim, call claim_free_rcu if its the last reference */
+/**
+ * batadv_claim_free_ref - decrement the claim refcounter and possibly
+ * release it
+ * @claim: claim to be free'd
+ */
static void batadv_claim_free_ref(struct batadv_bla_claim *claim)
{
if (atomic_dec_and_test(&claim->refcount))
}
/**
- * batadv_claim_hash_find
+ * batadv_claim_hash_find - looks for a claim in the claim hash
* @bat_priv: the bat priv with all the soft interface information
* @data: search data (may be local/static data)
*
- * looks for a claim in the hash, and returns it if found
- * or NULL otherwise.
+ * Return: claim if found or NULL otherwise.
*/
static struct batadv_bla_claim
*batadv_claim_hash_find(struct batadv_priv *bat_priv,
}
/**
- * batadv_backbone_hash_find - looks for a claim in the hash
+ * batadv_backbone_hash_find - looks for a backbone gateway in the hash
* @bat_priv: the bat priv with all the soft interface information
* @addr: the address of the originator
* @vid: the VLAN ID
*
- * Returns claim if found or NULL otherwise.
+ * Return: backbone gateway if found or NULL otherwise
*/
static struct batadv_bla_backbone_gw *
batadv_backbone_hash_find(struct batadv_priv *bat_priv, u8 *addr,
return backbone_gw_tmp;
}
-/* delete all claims for a backbone */
+/**
+ * batadv_bla_del_backbone_claims - delete all claims for a backbone
+ * @backbone_gw: backbone gateway where the claims should be removed
+ */
static void
batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw)
{
}
/**
- * batadv_bla_get_backbone_gw
+ * batadv_bla_get_backbone_gw - finds or creates a backbone gateway
* @bat_priv: the bat priv with all the soft interface information
* @orig: the mac address of the originator
* @vid: the VLAN ID
* @own_backbone: set if the requested backbone is local
*
- * searches for the backbone gw or creates a new one if it could not
- * be found.
+ * Return: the (possibly created) backbone gateway or NULL on error
*/
static struct batadv_bla_backbone_gw *
batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, u8 *orig,
return entry;
}
-/* update or add the own backbone gw to make sure we announce
+/**
+ * batadv_bla_update_own_backbone_gw - updates the own backbone gw for a VLAN
+ * @bat_priv: the bat priv with all the soft interface information
+ * @primary_if: the selected primary interface
+ * @vid: VLAN identifier
+ *
+ * update or add the own backbone gw to make sure we announce
* where we receive other backbone gws
*/
static void
}
/**
- * batadv_bla_send_announce
+ * batadv_bla_send_announce - Send an announcement frame
* @bat_priv: the bat priv with all the soft interface information
* @backbone_gw: our backbone gateway which should be announced
- *
- * This function sends an announcement. It is called from multiple
- * places.
*/
static void batadv_bla_send_announce(struct batadv_priv *bat_priv,
struct batadv_bla_backbone_gw *backbone_gw)
batadv_claim_free_ref(claim);
}
-/* Delete a claim from the claim hash which has the
- * given mac address and vid.
+/**
+ * batadv_bla_del_claim - delete a claim from the claim hash
+ * @bat_priv: the bat priv with all the soft interface information
+ * @mac: mac address of the claim to be removed
+ * @vid: VLAN id for the claim to be removed
*/
static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
const u8 *mac, const unsigned short vid)
batadv_claim_free_ref(claim);
}
-/* check for ANNOUNCE frame, return 1 if handled */
+/**
+ * batadv_handle_announce - check for ANNOUNCE frame
+ * @bat_priv: the bat priv with all the soft interface information
+ * @an_addr: announcement mac address (ARP Sender HW address)
+ * @backbone_addr: originator address of the sender (Ethernet source MAC)
+ * @vid: the VLAN ID of the frame
+ *
+ * Return: 1 if handled
+ */
static int batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr,
u8 *backbone_addr, unsigned short vid)
{
return 1;
}
-/* check for REQUEST frame, return 1 if handled */
+/**
+ * batadv_handle_request - check for REQUEST frame
+ * @bat_priv: the bat priv with all the soft interface information
+ * @primary_if: the primary hard interface of this batman soft interface
+ * @backbone_addr: backbone address to be requested (ARP sender HW MAC)
+ * @ethhdr: ethernet header of a packet
+ * @vid: the VLAN ID of the frame
+ *
+ * Return: 1 if handled
+ */
static int batadv_handle_request(struct batadv_priv *bat_priv,
struct batadv_hard_iface *primary_if,
u8 *backbone_addr, struct ethhdr *ethhdr,
return 1;
}
-/* check for UNCLAIM frame, return 1 if handled */
+/**
+ * batadv_handle_unclaim - check for UNCLAIM frame
+ * @bat_priv: the bat priv with all the soft interface information
+ * @primary_if: the primary hard interface of this batman soft interface
+ * @backbone_addr: originator address of the backbone (Ethernet source)
+ * @claim_addr: Client to be unclaimed (ARP sender HW MAC)
+ * @vid: the VLAN ID of the frame
+ *
+ * Return: 1 if handled
+ */
static int batadv_handle_unclaim(struct batadv_priv *bat_priv,
struct batadv_hard_iface *primary_if,
u8 *backbone_addr, u8 *claim_addr,
return 1;
}
-/* check for CLAIM frame, return 1 if handled */
+/**
+ * batadv_handle_claim - check for CLAIM frame
+ * @bat_priv: the bat priv with all the soft interface information
+ * @primary_if: the primary hard interface of this batman soft interface
+ * @backbone_addr: originator address of the backbone (Ethernet Source)
+ * @claim_addr: client mac address to be claimed (ARP sender HW MAC)
+ * @vid: the VLAN ID of the frame
+ *
+ * Return: 1 if handled
+ */
static int batadv_handle_claim(struct batadv_priv *bat_priv,
struct batadv_hard_iface *primary_if,
u8 *backbone_addr, u8 *claim_addr,
}
/**
- * batadv_check_claim_group
+ * batadv_check_claim_group - check for claim group membership
* @bat_priv: the bat priv with all the soft interface information
* @primary_if: the primary interface of this batman interface
* @hw_src: the Hardware source in the ARP Header
* This function also applies the group ID of the sender
* if it is in the same mesh.
*
- * returns:
+ * Return:
* 2 - if it is a claim packet and on the same group
* 1 - if is a claim packet from another group
* 0 - if it is not a claim packet
}
/**
- * batadv_bla_process_claim
+ * batadv_bla_process_claim - Check if this is a claim frame, and process it
* @bat_priv: the bat priv with all the soft interface information
* @primary_if: the primary hard interface of this batman soft interface
* @skb: the frame to be checked
*
- * Check if this is a claim frame, and process it accordingly.
- *
- * returns 1 if it was a claim frame, otherwise return 0 to
+ * Return: 1 if it was a claim frame, otherwise return 0 to
* tell the callee that it can use the frame on its own.
*/
static int batadv_bla_process_claim(struct batadv_priv *bat_priv,
return 1;
}
-/* Check when we last heard from other nodes, and remove them in case of
+/**
+ * batadv_bla_purge_backbone_gw - Remove backbone gateways after a timeout or
+ * immediately
+ * @bat_priv: the bat priv with all the soft interface information
+ * @now: whether the whole hash shall be wiped now
+ *
+ * Check when we last heard from other nodes, and remove them in case of
* a time out, or clean all backbone gws if now is set.
*/
static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now)
}
/**
- * batadv_bla_purge_claims
+ * batadv_bla_purge_claims - Remove claims after a timeout or immediately
* @bat_priv: the bat priv with all the soft interface information
* @primary_if: the selected primary interface, may be NULL if now is set
* @now: whether the whole hash shall be wiped now
}
/**
- * batadv_bla_update_orig_address
+ * batadv_bla_update_orig_address - Update the backbone gateways when the own
+ * originator address changes
* @bat_priv: the bat priv with all the soft interface information
* @primary_if: the new selected primary_if
* @oldif: the old primary interface, may be NULL
- *
- * Update the backbone gateways when the own orig address changes.
*/
void batadv_bla_update_orig_address(struct batadv_priv *bat_priv,
struct batadv_hard_iface *primary_if,
batadv_hardif_free_ref(primary_if);
}
-/* periodic work to do:
+/**
+ * batadv_bla_periodic_work - performs periodic bla work
+ * @work: kernel work struct
+ *
+ * periodic work to do:
* * purge structures when they are too old
* * send announcements
*/
static struct lock_class_key batadv_claim_hash_lock_class_key;
static struct lock_class_key batadv_backbone_hash_lock_class_key;
-/* initialize all bla structures */
+/**
+ * batadv_bla_init - initialize all bla structures
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * Return: 0 on success, < 0 on error.
+ */
int batadv_bla_init(struct batadv_priv *bat_priv)
{
int i;
}
/**
- * batadv_bla_check_bcast_duplist
+ * batadv_bla_check_bcast_duplist - Check if a frame is in the broadcast dup.
* @bat_priv: the bat priv with all the soft interface information
* @skb: contains the bcast_packet to be checked
*
* with a good chance that it is the same packet. If it is furthermore
* sent by another host, drop it. We allow equal packets from
* the same host however as this might be intended.
+ *
+ * Return: 1 if a packet is in the duplicate list, 0 otherwise.
*/
int batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv,
struct sk_buff *skb)
}
/**
- * batadv_bla_is_backbone_gw_orig
+ * batadv_bla_is_backbone_gw_orig - Check if the originator is a gateway for
+ * the VLAN identified by vid.
* @bat_priv: the bat priv with all the soft interface information
* @orig: originator mac address
* @vid: VLAN identifier
*
- * Check if the originator is a gateway for the VLAN identified by vid.
- *
- * Returns true if orig is a backbone for this vid, false otherwise.
+ * Return: true if orig is a backbone for this vid, false otherwise.
*/
bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, u8 *orig,
unsigned short vid)
}
/**
- * batadv_bla_is_backbone_gw
+ * batadv_bla_is_backbone_gw - check if originator is a backbone gw for a VLAN.
* @skb: the frame to be checked
* @orig_node: the orig_node of the frame
* @hdr_size: maximum length of the frame
*
- * bla_is_backbone_gw inspects the skb for the VLAN ID and returns 1
- * if the orig_node is also a gateway on the soft interface, otherwise it
- * returns 0.
+ * Return: 1 if the orig_node is also a gateway on the soft interface, otherwise
+ * it returns 0.
*/
int batadv_bla_is_backbone_gw(struct sk_buff *skb,
struct batadv_orig_node *orig_node, int hdr_size)
return 1;
}
-/* free all bla structures (for softinterface free or module unload) */
+/**
+ * batadv_bla_init - free all bla structures
+ * @bat_priv: the bat priv with all the soft interface information
+ *
+ * for softinterface free or module unload
+ */
void batadv_bla_free(struct batadv_priv *bat_priv)
{
struct batadv_hard_iface *primary_if;
}
/**
- * batadv_bla_rx
+ * batadv_bla_rx - check packets coming from the mesh.
* @bat_priv: the bat priv with all the soft interface information
* @skb: the frame to be checked
* @vid: the VLAN ID of the frame
* @is_bcast: the packet came in a broadcast packet type.
*
- * bla_rx avoidance checks if:
+ * batadv_bla_rx avoidance checks if:
* * we have to race for a claim
* * if the frame is allowed on the LAN
*
- * in these cases, the skb is further handled by this function and
- * returns 1, otherwise it returns 0 and the caller shall further
+ * in these cases, the skb is further handled by this function
+ *
+ * Return: 1 if handled, otherwise it returns 0 and the caller shall further
* process the skb.
*/
int batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
}
/**
- * batadv_bla_tx
+ * batadv_bla_tx - check packets going into the mesh
* @bat_priv: the bat priv with all the soft interface information
* @skb: the frame to be checked
* @vid: the VLAN ID of the frame
*
- * bla_tx checks if:
+ * batadv_bla_tx checks if:
* * a claim was received which has to be processed
* * the frame is allowed on the mesh
*
- * in these cases, the skb is further handled by this function and
- * returns 1, otherwise it returns 0 and the caller shall further
- * process the skb.
+ * in these cases, the skb is further handled by this function.
*
* This call might reallocate skb data.
+ *
+ * Return: 1 if handled, otherwise it returns 0 and the caller shall further
+ * process the skb.
*/
int batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
unsigned short vid)
return ret;
}
+/**
+ * batadv_bla_claim_table_seq_print_text - print the claim table in a seq file
+ * @seq: seq file to print on
+ * @offset: not used
+ *
+ * Return: always 0
+ */
int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset)
{
struct net_device *net_dev = (struct net_device *)seq->private;
return 0;
}
+/**
+ * batadv_bla_backbone_table_seq_print_text - print the backbone table in a seq
+ * file
+ * @seq: seq file to print on
+ * @offset: not used
+ *
+ * Return: always 0
+ */
int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset)
{
struct net_device *net_dev = (struct net_device *)seq->private;
-/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich
*
-/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
* originator table of an hard interface
* @inode: inode pointer to debugfs file
* @file: pointer to the seq_file
+ *
+ * Return: 0 on success or negative error number in case of failure
*/
static int batadv_originators_hardif_open(struct inode *inode,
struct file *file)
* batadv_dat_cache_open - Prepare file handler for reads from dat_chache
* @inode: inode which was opened
* @file: file handle to be initialized
+ *
+ * Return: 0 on success or negative error number in case of failure
*/
static int batadv_dat_cache_open(struct inode *inode, struct file *file)
{
* batadv_debugfs_add_hardif - creates the base directory for a hard interface
* in debugfs.
* @hard_iface: hard interface which should be added.
+ *
+ * Return: 0 on success or negative error number in case of failure
*/
int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface)
{
-/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
-/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors:
*
* Antonio Quartulli
*
* batadv_dat_to_purge - check whether a dat_entry has to be purged or not
* @dat_entry: the entry to check
*
- * Returns true if the entry has to be purged now, false otherwise.
+ * Return: true if the entry has to be purged now, false otherwise.
*/
static bool batadv_dat_to_purge(struct batadv_dat_entry *dat_entry)
{
* @node: node in the local table
* @data2: second object to compare the node to
*
- * Returns 1 if the two entries are the same, 0 otherwise.
+ * Return: 1 if the two entries are the same, 0 otherwise.
*/
static int batadv_compare_dat(const struct hlist_node *node, const void *data2)
{
* @skb: ARP packet
* @hdr_size: size of the possible header before the ARP packet
*
- * Returns the value of the hw_src field in the ARP packet.
+ * Return: the value of the hw_src field in the ARP packet.
*/
static u8 *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size)
{
* @skb: ARP packet
* @hdr_size: size of the possible header before the ARP packet
*
- * Returns the value of the ip_src field in the ARP packet.
+ * Return: the value of the ip_src field in the ARP packet.
*/
static __be32 batadv_arp_ip_src(struct sk_buff *skb, int hdr_size)
{
* @skb: ARP packet
* @hdr_size: size of the possible header before the ARP packet
*
- * Returns the value of the hw_dst field in the ARP packet.
+ * Return: the value of the hw_dst field in the ARP packet.
*/
static u8 *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size)
{
* @skb: ARP packet
* @hdr_size: size of the possible header before the ARP packet
*
- * Returns the value of the ip_dst field in the ARP packet.
+ * Return: the value of the ip_dst field in the ARP packet.
*/
static __be32 batadv_arp_ip_dst(struct sk_buff *skb, int hdr_size)
{
* @data: data to hash
* @size: size of the hash table
*
- * Returns the selected index in the hash table for the given data.
+ * Return: the selected index in the hash table for the given data.
*/
static u32 batadv_hash_dat(const void *data, u32 size)
{
* @ip: search key
* @vid: VLAN identifier
*
- * Returns the dat_entry if found, NULL otherwise.
+ * Return: the dat_entry if found, NULL otherwise.
*/
static struct batadv_dat_entry *
batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip,
* @candidate: orig_node under evaluation
* @max_orig_node: last selected candidate
*
- * Returns true if the node has been elected as next candidate or false
+ * Return: true if the node has been elected as next candidate or false
* otherwise.
*/
static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res,
* closest values (from the LEFT, with wrap around if needed) then the hash
* value of the key. ip_dst is the key.
*
- * Returns the candidate array of size BATADV_DAT_CANDIDATE_NUM.
+ * Return: the candidate array of size BATADV_DAT_CANDIDATE_NUM.
*/
static struct batadv_dat_candidate *
batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst)
* This function copies the skb with pskb_copy() and is sent as unicast packet
* to each of the selected candidates.
*
- * Returns true if the packet is sent to at least one candidate, false
+ * Return: true if the packet is sent to at least one candidate, false
* otherwise.
*/
static bool batadv_dat_send_data(struct batadv_priv *bat_priv,
/**
* batadv_dat_init - initialise the DAT internals
* @bat_priv: the bat priv with all the soft interface information
+ *
+ * Return: 0 in case of success, a negative error code otherwise
*/
int batadv_dat_init(struct batadv_priv *bat_priv)
{
* batadv_dat_cache_seq_print_text - print the local DAT hash table
* @seq: seq file to print on
* @offset: not used
+ *
+ * Return: always 0
*/
int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset)
{
* @skb: packet to analyse
* @hdr_size: size of the possible header before the ARP packet in the skb
*
- * Returns the ARP type if the skb contains a valid ARP packet, 0 otherwise.
+ * Return: the ARP type if the skb contains a valid ARP packet, 0 otherwise.
*/
static u16 batadv_arp_get_type(struct batadv_priv *bat_priv,
struct sk_buff *skb, int hdr_size)
* @skb: the buffer containing the packet to extract the VID from
* @hdr_size: the size of the batman-adv header encapsulating the packet
*
- * If the packet embedded in the skb is vlan tagged this function returns the
- * VID with the BATADV_VLAN_HAS_TAG flag. Otherwise BATADV_NO_FLAGS is returned.
+ * Return: If the packet embedded in the skb is vlan tagged this function
+ * returns the VID with the BATADV_VLAN_HAS_TAG flag. Otherwise BATADV_NO_FLAGS
+ * is returned.
*/
static unsigned short batadv_dat_get_vid(struct sk_buff *skb, int *hdr_size)
{
* @bat_priv: the bat priv with all the soft interface information
* @skb: packet to check
*
- * Returns true if the message has been sent to the dht candidates, false
+ * Return: true if the message has been sent to the dht candidates, false
* otherwise. In case of a positive return value the message has to be enqueued
* to permit the fallback.
*/
* @skb: packet to check
* @hdr_size: size of the encapsulation header
*
- * Returns true if the request has been answered, false otherwise.
+ * Return: true if the request has been answered, false otherwise.
*/
bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
struct sk_buff *skb, int hdr_size)
* @skb: packet to check
* @hdr_size: size of the encapsulation header
*
- * Returns true if the packet was snooped and consumed by DAT. False if the
+ * Return: true if the packet was snooped and consumed by DAT. False if the
* packet has to be delivered to the interface
*/
bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
* @bat_priv: the bat priv with all the soft interface information
* @forw_packet: the broadcast packet
*
- * Returns true if the node can drop the packet, false otherwise.
+ * Return: true if the node can drop the packet, false otherwise.
*/
bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv,
struct batadv_forw_packet *forw_packet)
-/* Copyright (C) 2011-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2011-2016 B.A.T.M.A.N. contributors:
*
* Antonio Quartulli
*
-/* Copyright (C) 2013-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2016 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll <martin@hundeboll.net>
*
/**
* batadv_frag_size_limit - maximum possible size of packet to be fragmented
*
- * Returns the maximum size of payload that can be fragmented.
+ * Return: the maximum size of payload that can be fragmented.
*/
static int batadv_frag_size_limit(void)
{
*
* Caller must hold chain->lock.
*
- * Returns true if chain is empty and caller can just insert the new fragment
+ * Return: true if chain is empty and caller can just insert the new fragment
* without searching for the right position.
*/
static bool batadv_frag_init_chain(struct batadv_frag_table_entry *chain,
* Insert a new fragment into the reverse ordered chain in the right table
* entry. The hash table entry is cleared if "old" fragments exist in it.
*
- * Returns true if skb is buffered, false on error. If the chain has all the
+ * Return: true if skb is buffered, false on error. If the chain has all the
* fragments needed to merge the packet, the chain is moved to the passed head
* to avoid locking the chain in the table.
*/
/**
* batadv_frag_merge_packets - merge a chain of fragments
* @chain: head of chain with fragments
- * @skb: packet with total size of skb after merging
*
* Expand the first skb in the chain and copy the content of the remaining
* skb's into the expanded one. After doing so, clear the chain.
*
- * Returns the merged skb or NULL on error.
+ * Return: the merged skb or NULL on error.
*/
static struct sk_buff *
batadv_frag_merge_packets(struct hlist_head *chain)
* There are three possible outcomes: 1) Packet is merged: Return true and
* set *skb to merged packet; 2) Packet is buffered: Return true and set *skb
* to NULL; 3) Error: Return false and leave skb as is.
+ *
+ * Return: true when packet is merged or buffered, false when skb is not not
+ * used.
*/
bool batadv_frag_skb_buffer(struct sk_buff **skb,
struct batadv_orig_node *orig_node_src)
* will exceed the MTU towards the next-hop. If so, the fragment is forwarded
* without merging it.
*
- * Returns true if the fragment is consumed/forwarded, false otherwise.
+ * Return: true if the fragment is consumed/forwarded, false otherwise.
*/
bool batadv_frag_skb_fwd(struct sk_buff *skb,
struct batadv_hard_iface *recv_if,
* passed mtu and the old one with the rest. The new skb contains data from the
* tail of the old skb.
*
- * Returns the new fragment, NULL on error.
+ * Return: the new fragment, NULL on error.
*/
static struct sk_buff *batadv_frag_create(struct sk_buff *skb,
struct batadv_frag_packet *frag_head,
* @orig_node: final destination of the created fragments
* @neigh_node: next-hop of the created fragments
*
- * Returns true on success, false otherwise.
+ * Return: true on success, false otherwise.
*/
bool batadv_frag_send_packet(struct sk_buff *skb,
struct batadv_orig_node *orig_node,
-/* Copyright (C) 2013-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2013-2016 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll <martin@hundeboll.net>
*
* batadv_frag_check_entry - check if a list of fragments has timed out
* @frags_entry: table entry to check
*
- * Returns true if the frags entry has timed out, false otherwise.
+ * Return: true if the frags entry has timed out, false otherwise.
*/
static inline bool
batadv_frag_check_entry(struct batadv_frag_table_entry *frags_entry)
-/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
* @bat_priv: the bat priv with all the soft interface information
* @orig_node: originator announcing gateway capabilities
*
- * Returns gateway node if found or NULL otherwise.
+ * Return: gateway node if found or NULL otherwise.
*/
static struct batadv_gw_node *
batadv_gw_node_get(struct batadv_priv *bat_priv,
* @chaddr: buffer where the client address will be stored. Valid
* only if the function returns BATADV_DHCP_TO_CLIENT
*
- * Returns:
+ * This function may re-allocate the data buffer of the skb passed as argument.
+ *
+ * Return:
* - BATADV_DHCP_NO if the packet is not a dhcp message or if there was an error
* while parsing it
* - BATADV_DHCP_TO_SERVER if this is a message going to the DHCP server
* - BATADV_DHCP_TO_CLIENT if this is a message going to a DHCP client
- *
- * This function may re-allocate the data buffer of the skb passed as argument.
*/
enum batadv_dhcp_recipient
batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len,
* server. Due to topology changes it may be the case that the GW server
* previously selected is not the best one anymore.
*
- * Returns true if the packet destination is unicast and it is not the best gw,
- * false otherwise.
- *
* This call might reallocate skb data.
* Must be invoked only when the DHCP packet is going TO a DHCP SERVER.
+ *
+ * Return: true if the packet destination is unicast and it is not the best gw,
+ * false otherwise.
*/
bool batadv_gw_out_of_range(struct batadv_priv *bat_priv,
struct sk_buff *skb)
-/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
-/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
* @description: text shown when throughput string cannot be parsed
* @throughput: pointer holding the returned throughput information
*
- * Returns false on parse error and true otherwise.
+ * Return: false on parse error and true otherwise.
*/
static bool batadv_parse_throughput(struct net_device *net_dev, char *buff,
const char *description, u32 *throughput)
-/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
* This function recursively checks all the fathers of the device passed as
* argument looking for a batman-adv soft interface.
*
- * Returns true if the device is descendant of a batman-adv mesh interface (or
+ * Return: true if the device is descendant of a batman-adv mesh interface (or
* if it is a batman-adv interface itself), false otherwise
*/
static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
* interface
* @net_device: the device to check
*
- * Returns true if the net device is a 802.11 wireless device, false otherwise.
+ * Return: true if the net device is a 802.11 wireless device, false otherwise.
*/
bool batadv_is_wifi_netdev(struct net_device *net_device)
{
*
* Invoke ndo_del_slave on master passing slave as argument. In this way slave
* is free'd and master can correctly change its internal state.
- * Return 0 on success, a negative value representing the error otherwise
+ *
+ * Return: 0 on success, a negative value representing the error otherwise
*/
static int batadv_master_del_slave(struct batadv_hard_iface *slave,
struct net_device *master)
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
-/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2016 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*
-/* Copyright (C) 2006-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2006-2016 B.A.T.M.A.N. contributors:
*
* Simon Wunderlich, Marek Lindner
*
struct lock_class_key;
/* callback to a compare function. should compare 2 element datas for their
- * keys, return 0 if same and not 0 if not same
+ * keys
+ *
+ * Return: 0 if same and not 0 if not same
*/
typedef int (*batadv_hashdata_compare_cb)(const struct hlist_node *,
const void *);
-/* the hashfunction, should return an index
- * based on the key in the data of the first
- * argument and the size the second
+/* the hashfunction
+ *
+ * Return: an index based on the key in the data of the first argument and the
+ * size the second
*/
typedef u32 (*batadv_hashdata_choose_cb)(const void *, u32);
typedef void (*batadv_hashdata_free_cb)(struct hlist_node *, void *);
* @data: data passed to the aforementioned callbacks as argument
* @data_node: to be added element
*
- * Returns 0 on success, 1 if the element already is in the hash
+ * Return: 0 on success, 1 if the element already is in the hash
* and -1 on error.
*/
static inline int batadv_hash_add(struct batadv_hashtable *hash,
return ret;
}
-/* removes data from hash, if found. returns pointer do data on success, so you
- * can remove the used structure yourself, or NULL on error . data could be the
- * structure you use with just the key filled, we just need the key for
- * comparing.
+/* removes data from hash, if found. data could be the structure you use with
+ * just the key filled, we just need the key for comparing.
+ *
+ * Return: returns pointer do data on success, so you can remove the used
+ * structure yourself, or NULL on error
*/
static inline void *batadv_hash_remove(struct batadv_hashtable *hash,
batadv_hashdata_compare_cb compare,
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
* @bat_priv: the bat priv with all the soft interface information
* @addr: the address to check
*
- * Returns 'true' if the mac address was found, false otherwise.
+ * Return: 'true' if the mac address was found, false otherwise.
*/
bool batadv_is_my_mac(struct batadv_priv *bat_priv, const u8 *addr)
{
* function that requires the primary interface
* @seq: debugfs table seq_file struct
*
- * Returns primary interface if found or NULL otherwise.
+ * Return: primary interface if found or NULL otherwise.
*/
struct batadv_hard_iface *
batadv_seq_print_text_primary_if_get(struct seq_file *seq)
* batadv_max_header_len - calculate maximum encapsulation overhead for a
* payload packet
*
- * Return the maximum encapsulation overhead in bytes.
+ * Return: the maximum encapsulation overhead in bytes.
*/
int batadv_max_header_len(void)
{
*
* payload_ptr must always point to an address in the skb head buffer and not to
* a fragment.
+ *
+ * Return: big endian crc32c of the checksummed data
*/
__be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr)
{
* @type: tvlv handler type to look for
* @version: tvlv handler version to look for
*
- * Returns tvlv handler if found or NULL otherwise.
+ * Return: tvlv handler if found or NULL otherwise.
*/
static struct batadv_tvlv_handler
*batadv_tvlv_handler_get(struct batadv_priv *bat_priv, u8 type, u8 version)
* Has to be called with the appropriate locks being acquired
* (tvlv.container_list_lock).
*
- * Returns tvlv container if found or NULL otherwise.
+ * Return: tvlv container if found or NULL otherwise.
*/
static struct batadv_tvlv_container
*batadv_tvlv_container_get(struct batadv_priv *bat_priv, u8 type, u8 version)
* Has to be called with the appropriate locks being acquired
* (tvlv.container_list_lock).
*
- * Returns size of all currently registered tvlv containers in bytes.
+ * Return: size of all currently registered tvlv containers in bytes.
*/
static u16 batadv_tvlv_container_list_size(struct batadv_priv *bat_priv)
{
* @additional_packet_len: requested additional packet size on top of minimum
* size
*
- * Returns true of the packet buffer could be changed to the requested size,
+ * Return: true of the packet buffer could be changed to the requested size,
* false otherwise.
*/
static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff,
* The ogm packet might be enlarged or shrunk depending on the current size
* and the size of the to-be-appended tvlv containers.
*
- * Returns size of all appended tvlv containers in bytes.
+ * Return: size of all appended tvlv containers in bytes.
*/
u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv,
unsigned char **packet_buff,
* @tvlv_value: tvlv content
* @tvlv_value_len: tvlv content length
*
- * Returns success if handler was not found or the return value of the handler
+ * Return: success if handler was not found or the return value of the handler
* callback.
*/
static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv,
* @tvlv_value: tvlv content
* @tvlv_value_len: tvlv content length
*
- * Returns success when processing an OGM or the return value of all called
+ * Return: success when processing an OGM or the return value of all called
* handler callbacks.
*/
int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
* @skb: the buffer containing the packet
* @header_len: length of the batman header preceding the ethernet header
*
- * If the packet embedded in the skb is vlan tagged this function returns the
- * VID with the BATADV_VLAN_HAS_TAG flag. Otherwise BATADV_NO_FLAGS is returned.
+ * Return: VID with the BATADV_VLAN_HAS_TAG flag when the packet embedded in the
+ * skb is vlan tagged. Otherwise BATADV_NO_FLAGS.
*/
unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len)
{
* @vid: the VLAN identifier for which the AP isolation attributed as to be
* looked up
*
- * Returns true if AP isolation is on for the VLAN idenfied by vid, false
+ * Return: true if AP isolation is on for the VLAN idenfied by vid, false
* otherwise
*/
bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid)
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
pr_err("%s: " fmt, _netdev->name, ## arg); \
} while (0)
-/* returns 1 if they are the same ethernet addr
+/**
+ * batadv_compare_eth - Compare two not u16 aligned Ethernet addresses
+ * @data1: Pointer to a six-byte array containing the Ethernet address
+ * @data2: Pointer other six-byte array containing the Ethernet address
*
* note: can't use ether_addr_equal() as it requires aligned memory
+ *
+ * Return: 1 if they are the same ethernet addr
*/
static inline bool batadv_compare_eth(const void *data1, const void *data2)
{
* @timestamp: base value to compare with (in jiffies)
* @timeout: added to base value before comparing (in milliseconds)
*
- * Returns true if current time is after timestamp + timeout
+ * Return: true if current time is after timestamp + timeout
*/
static inline bool batadv_has_timed_out(unsigned long timestamp,
unsigned int timeout)
#define batadv_inc_counter(b, i) batadv_add_counter(b, i, 1)
-/* Sum and return the cpu-local counters for index 'idx' */
+/**
+ * batadv_sum_counter - Sum the cpu-local counters for index 'idx'
+ * @bat_priv: the bat priv with all the soft interface information
+ * @idx: index of counter to sum up
+ *
+ * Return: sum of all cpu-local counters
+ */
static inline u64 batadv_sum_counter(struct batadv_priv *bat_priv, size_t idx)
{
u64 *counters, sum = 0;
-/* Copyright (C) 2014-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2014-2016 B.A.T.M.A.N. contributors:
*
* Linus Lüssing
*
* Collect multicast addresses of the local multicast listeners
* on the given soft interface, dev, in the given mcast_list.
*
- * Returns -ENOMEM on memory allocation error or the number of
+ * Return: -ENOMEM on memory allocation error or the number of
* items added to the mcast_list otherwise.
*/
static int batadv_mcast_mla_softif_get(struct net_device *dev,
* @mcast_addr: the multicast address to check
* @mcast_list: the list with multicast addresses to search in
*
- * Returns true if the given address is already in the given list.
+ * Return: true if the given address is already in the given list.
* Otherwise returns false.
*/
static bool batadv_mcast_mla_is_duplicate(u8 *mcast_addr,
* batadv_mcast_has_bridge - check whether the soft-iface is bridged
* @bat_priv: the bat priv with all the soft interface information
*
- * Checks whether there is a bridge on top of our soft interface. Returns
- * true if so, false otherwise.
+ * Checks whether there is a bridge on top of our soft interface.
+ *
+ * Return: true if there is a bridge, false otherwise.
*/
static bool batadv_mcast_has_bridge(struct batadv_priv *bat_priv)
{
* Updates the own multicast tvlv with our current multicast related settings,
* capabilities and inabilities.
*
- * Returns true if the tvlv container is registered afterwards. Otherwise
+ * Return: true if the tvlv container is registered afterwards. Otherwise
* returns false.
*/
static bool batadv_mcast_mla_tvlv_update(struct batadv_priv *bat_priv)
* Checks whether the given IPv4 packet has the potential to be forwarded with a
* mode more optimal than classic flooding.
*
- * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM in case of
- * memory allocation failure.
+ * Return: If so then 0. Otherwise -EINVAL or -ENOMEM in case of memory
+ * allocation failure.
*/
static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv,
struct sk_buff *skb,
* Checks whether the given IPv6 packet has the potential to be forwarded with a
* mode more optimal than classic flooding.
*
- * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM if we are out
- * of memory.
+ * Return: If so then 0. Otherwise -EINVAL is or -ENOMEM if we are out of memory
*/
static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
struct sk_buff *skb,
* Checks whether the given multicast ethernet frame has the potential to be
* forwarded with a mode more optimal than classic flooding.
*
- * If so then returns 0. Otherwise -EINVAL is returned or -ENOMEM if we are out
- * of memory.
+ * Return: If so then 0. Otherwise -EINVAL is or -ENOMEM if we are out of memory
*/
static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv,
struct sk_buff *skb,
* @bat_priv: the bat priv with all the soft interface information
* @ethhdr: ethernet header of a packet
*
- * Returns the number of nodes which want all IPv4 multicast traffic if the
+ * Return: the number of nodes which want all IPv4 multicast traffic if the
* given ethhdr is from an IPv4 packet or the number of nodes which want all
* IPv6 traffic if it matches an IPv6 packet.
*/
* @bat_priv: the bat priv with all the soft interface information
* @ethhdr: the ether header containing the multicast destination
*
- * Returns an orig_node matching the multicast address provided by ethhdr
+ * Return: an orig_node matching the multicast address provided by ethhdr
* via a translation table lookup. This increases the returned nodes refcount.
*/
static struct batadv_orig_node *
* batadv_mcast_want_forw_ipv4_node_get - get a node with an ipv4 flag
* @bat_priv: the bat priv with all the soft interface information
*
- * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 flag set and
+ * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 flag set and
* increases its refcount.
*/
static struct batadv_orig_node *
* batadv_mcast_want_forw_ipv6_node_get - get a node with an ipv6 flag
* @bat_priv: the bat priv with all the soft interface information
*
- * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV6 flag set
+ * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_IPV6 flag set
* and increases its refcount.
*/
static struct batadv_orig_node *
* @bat_priv: the bat priv with all the soft interface information
* @ethhdr: an ethernet header to determine the protocol family from
*
- * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 or
+ * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_IPV4 or
* BATADV_MCAST_WANT_ALL_IPV6 flag, depending on the provided ethhdr, set and
* increases its refcount.
*/
* batadv_mcast_want_forw_unsnoop_node_get - get a node with an unsnoopable flag
* @bat_priv: the bat priv with all the soft interface information
*
- * Returns an orig_node which has the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag
+ * Return: an orig_node which has the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag
* set and increases its refcount.
*/
static struct batadv_orig_node *
* @skb: The multicast packet to check
* @orig: an originator to be set to forward the skb to
*
- * Returns the forwarding mode as enum batadv_forw_mode and in case of
+ * Return: the forwarding mode as enum batadv_forw_mode and in case of
* BATADV_FORW_SINGLE set the orig to the single originator the skb
* should be forwarded to.
*/
-/* Copyright (C) 2014-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2014-2016 B.A.T.M.A.N. contributors:
*
* Linus Lüssing
*
struct sk_buff;
/**
- * batadv_forw_mode - the way a packet should be forwarded as
+ * enum batadv_forw_mode - the way a packet should be forwarded as
* @BATADV_FORW_ALL: forward the packet to all nodes (currently via classic
* flooding)
* @BATADV_FORW_SINGLE: forward the packet to a single node (currently via the
-/* Copyright (C) 2012-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2012-2016 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll, Jeppe Ledet-Pedersen
*
/**
* batadv_nc_init - one-time initialization for network coding
+ *
+ * Return: 0 on success or negative error number in case of failure
*/
int __init batadv_nc_init(void)
{
/**
* batadv_nc_mesh_init - initialise coding hash table and start house keeping
* @bat_priv: the bat priv with all the soft interface information
+ *
+ * Return: 0 on success or negative error number in case of failure
*/
int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
{
* @bat_priv: the bat priv with all the soft interface information
* @nc_node: the nc node to check
*
- * Returns true if the entry has to be purged now, false otherwise
+ * Return: true if the entry has to be purged now, false otherwise
*/
static bool batadv_nc_to_purge_nc_node(struct batadv_priv *bat_priv,
struct batadv_nc_node *nc_node)
* @bat_priv: the bat priv with all the soft interface information
* @nc_path: the nc path to check
*
- * Returns true if the entry has to be purged now, false otherwise
+ * Return: true if the entry has to be purged now, false otherwise
*/
static bool batadv_nc_to_purge_nc_path_coding(struct batadv_priv *bat_priv,
struct batadv_nc_path *nc_path)
* @bat_priv: the bat priv with all the soft interface information
* @nc_path: the nc path to check
*
- * Returns true if the entry has to be purged now, false otherwise
+ * Return: true if the entry has to be purged now, false otherwise
*/
static bool batadv_nc_to_purge_nc_path_decoding(struct batadv_priv *bat_priv,
struct batadv_nc_path *nc_path)
* @data: data to hash
* @size: size of the hash table
*
- * Returns the selected index in the hash table for the given data.
+ * Return: the selected index in the hash table for the given data.
*/
static u32 batadv_nc_hash_choose(const void *data, u32 size)
{
* @node: node in the local table
* @data2: second object to compare the node to
*
- * Returns 1 if the two entry are the same, 0 otherwise
+ * Return: 1 if the two entry are the same, 0 otherwise
*/
static int batadv_nc_hash_compare(const struct hlist_node *node,
const void *data2)
* @hash: hash table containing the nc path
* @data: search key
*
- * Returns the nc_path if found, NULL otherwise.
+ * Return: the nc_path if found, NULL otherwise.
*/
static struct batadv_nc_path *
batadv_nc_hash_find(struct batadv_hashtable *hash,
* timeout. If so, the packet is no longer kept and the entry deleted from the
* queue. Has to be called with the appropriate locks.
*
- * Returns false as soon as the entry in the fifo queue has not been timed out
+ * Return: false as soon as the entry in the fifo queue has not been timed out
* yet and true otherwise.
*/
static bool batadv_nc_sniffed_purge(struct batadv_priv *bat_priv,
* packet is no longer delayed, immediately sent and the entry deleted from the
* queue. Has to be called with the appropriate locks.
*
- * Returns false as soon as the entry in the fifo queue has not been timed out
+ * Return: false as soon as the entry in the fifo queue has not been timed out
* yet and true otherwise.
*/
static bool batadv_nc_fwd_flush(struct batadv_priv *bat_priv,
* @orig_node: neighboring orig node which may be used as nc candidate
* @ogm_packet: incoming ogm packet also used for the checks
*
- * Returns true if:
+ * Return: true if:
* 1) The OGM must have the most recent sequence number.
* 2) The TTL must be decremented by one and only one.
* 3) The OGM must be received from the first hop from orig_node.
* (can be equal to orig_node)
* @in_coding: traverse incoming or outgoing network coding list
*
- * Returns the nc_node if found, NULL otherwise.
+ * Return: the nc_node if found, NULL otherwise.
*/
static struct batadv_nc_node
*batadv_nc_find_nc_node(struct batadv_orig_node *orig_node,
* (can be equal to orig_node)
* @in_coding: traverse incoming or outgoing network coding list
*
- * Returns the nc_node if found or created, NULL in case of an error.
+ * Return: the nc_node if found or created, NULL in case of an error.
*/
static struct batadv_nc_node
*batadv_nc_get_nc_node(struct batadv_priv *bat_priv,
* @src: ethernet source address - first half of the nc path search key
* @dst: ethernet destination address - second half of the nc path search key
*
- * Returns pointer to nc_path if the path was found or created, returns NULL
+ * Return: pointer to nc_path if the path was found or created, returns NULL
* on error.
*/
static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv,
* batadv_nc_random_weight_tq - scale the receivers TQ-value to avoid unfair
* selection of a receiver with slightly lower TQ than the other
* @tq: to be weighted tq value
+ *
+ * Return: scaled tq value
*/
static u8 batadv_nc_random_weight_tq(u8 tq)
{
* @nc_packet: structure containing the packet to the skb can be coded with
* @neigh_node: next hop to forward packet to
*
- * Returns true if both packets are consumed, false otherwise.
+ * Return: true if both packets are consumed, false otherwise.
*/
static bool batadv_nc_code_packets(struct batadv_priv *bat_priv,
struct sk_buff *skb,
* Since the source encoded the packet we can be certain it has all necessary
* decode information.
*
- * Returns true if coding of a decoded packet is allowed.
+ * Return: true if coding of a decoded packet is allowed.
*/
static bool batadv_nc_skb_coding_possible(struct sk_buff *skb, u8 *dst, u8 *src)
{
* @skb: data skb to forward
* @eth_dst: next hop mac address of skb
*
- * Returns true if coding of a decoded skb is allowed.
+ * Return: true if coding of a decoded skb is allowed.
*/
static struct batadv_nc_packet *
batadv_nc_path_search(struct batadv_priv *bat_priv,
* @eth_src: source mac address of skb
* @in_nc_node: pointer to skb next hop's neighbor nc node
*
- * Returns an nc packet if a suitable coding packet was found, NULL otherwise.
+ * Return: an nc packet if a suitable coding packet was found, NULL otherwise.
*/
static struct batadv_nc_packet *
batadv_nc_skb_src_search(struct batadv_priv *bat_priv,
* next hop that potentially sent a packet which our next hop also received
* (overheard) and has stored for later decoding.
*
- * Returns true if the skb was consumed (encoded packet sent) or false otherwise
+ * Return: true if the skb was consumed (encoded packet sent) or false otherwise
*/
static bool batadv_nc_skb_dst_search(struct sk_buff *skb,
struct batadv_neigh_node *neigh_node,
* @neigh_node: next hop to forward packet to
* @packet_id: checksum to identify packet
*
- * Returns true if the packet was buffered or false in case of an error.
+ * Return: true if the packet was buffered or false in case of an error.
*/
static bool batadv_nc_skb_add_to_path(struct sk_buff *skb,
struct batadv_nc_path *nc_path,
* @skb: data skb to forward
* @neigh_node: next hop to forward packet to
*
- * Returns true if the skb was consumed (encoded packet sent) or false otherwise
+ * Return: true if the skb was consumed (encoded packet sent) or false otherwise
*/
bool batadv_nc_skb_forward(struct sk_buff *skb,
struct batadv_neigh_node *neigh_node)
* @skb: unicast skb to decode
* @nc_packet: decode data needed to decode the skb
*
- * Returns pointer to decoded unicast packet if the packet was decoded or NULL
+ * Return: pointer to decoded unicast packet if the packet was decoded or NULL
* in case of an error.
*/
static struct batadv_unicast_packet *
* @ethhdr: pointer to the ethernet header inside the coded packet
* @coded: coded packet we try to find decode data for
*
- * Returns pointer to nc packet if the needed data was found or NULL otherwise.
+ * Return: pointer to nc packet if the needed data was found or NULL otherwise.
*/
static struct batadv_nc_packet *
batadv_nc_find_decoding_packet(struct batadv_priv *bat_priv,
* resulting unicast packet
* @skb: incoming coded packet
* @recv_if: pointer to interface this packet was received on
+ *
+ * Return: NET_RX_SUCCESS if the packet has been consumed or NET_RX_DROP
+ * otherwise.
*/
static int batadv_nc_recv_coded_packet(struct sk_buff *skb,
struct batadv_hard_iface *recv_if)
* batadv_nc_nodes_seq_print_text - print the nc node information
* @seq: seq file to print on
* @offset: not used
+ *
+ * Return: always 0
*/
int batadv_nc_nodes_seq_print_text(struct seq_file *seq, void *offset)
{
/**
* batadv_nc_init_debugfs - create nc folder and related files in debugfs
* @bat_priv: the bat priv with all the soft interface information
+ *
+ * Return: 0 on success or negative error number in case of failure
*/
int batadv_nc_init_debugfs(struct batadv_priv *bat_priv)
{
-/* Copyright (C) 2012-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2012-2016 B.A.T.M.A.N. contributors:
*
* Martin Hundebøll, Jeppe Ledet-Pedersen
*
-/* Copyright (C) 2009-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2009-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
static void batadv_purge_orig(struct work_struct *work);
-/* returns 1 if they are the same originator */
+/**
+ * batadv_compare_orig - comparing function used in the originator hash table
+ * @node: node in the local table
+ * @data2: second object to compare the node to
+ *
+ * Return: 1 if they are the same originator
+ */
int batadv_compare_orig(const struct hlist_node *node, const void *data2)
{
const void *data1 = container_of(node, struct batadv_orig_node,
* @orig_node: the originator serving the VLAN
* @vid: the VLAN identifier
*
- * Returns the vlan object identified by vid and belonging to orig_node or NULL
+ * Return: the vlan object identified by vid and belonging to orig_node or NULL
* if it does not exist.
*/
struct batadv_orig_node_vlan *
* @orig_node: the originator serving the VLAN
* @vid: the VLAN identifier
*
- * Returns NULL in case of failure or the vlan object identified by vid and
+ * Return: NULL in case of failure or the vlan object identified by vid and
* belonging to orig_node otherwise. The object is created and added to the list
* if it does not exist.
*
* @if_outgoing: the interface where the payload packet has been received or
* the OGM should be sent to
*
- * Returns the neighbor which should be router for this orig_node/iface.
+ * Return: the neighbor which should be router for this orig_node/iface.
*
* The object is returned with refcounter increased by 1.
*/
* @orig_node: the orig node to be queried
* @if_outgoing: the interface for which the ifinfo should be acquired
*
- * Returns the requested orig_ifinfo or NULL if not found.
+ * Return: the requested orig_ifinfo or NULL if not found.
*
* The object is returned with refcounter increased by 1.
*/
* @orig_node: the orig node to be queried
* @if_outgoing: the interface for which the ifinfo should be acquired
*
- * Returns NULL in case of failure or the orig_ifinfo object for the if_outgoing
+ * Return: NULL in case of failure or the orig_ifinfo object for the if_outgoing
* interface otherwise. The object is created and added to the list
* if it does not exist.
*
/**
* batadv_neigh_ifinfo_get - find the ifinfo from an neigh_node
- * @neigh_node: the neigh node to be queried
+ * @neigh: the neigh node to be queried
* @if_outgoing: the interface for which the ifinfo should be acquired
*
* The object is returned with refcounter increased by 1.
*
- * Returns the requested neigh_ifinfo or NULL if not found
+ * Return: the requested neigh_ifinfo or NULL if not found
*/
struct batadv_neigh_ifinfo *
batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh,
/**
* batadv_neigh_ifinfo_new - search and possibly create an neigh_ifinfo object
- * @neigh_node: the neigh node to be queried
+ * @neigh: the neigh node to be queried
* @if_outgoing: the interface for which the ifinfo should be acquired
*
- * Returns NULL in case of failure or the neigh_ifinfo object for the
+ * Return: NULL in case of failure or the neigh_ifinfo object for the
* if_outgoing interface otherwise. The object is created and added to the list
* if it does not exist.
*
*
* Looks for and possibly returns a neighbour belonging to this originator list
* which is connected through the provided hard interface.
- * Returns NULL if the neighbour is not found.
+ *
+ * Return: neighbor when found. Othwerwise NULL
*/
static struct batadv_neigh_node *
batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
* @hard_iface: the interface this neighbour is connected to
* @neigh_addr: the interface address of the neighbour to retrieve
*
- * Returns the hardif neighbour node if found or created or NULL otherwise.
+ * Return: the hardif neighbour node if found or created or NULL otherwise.
*/
static struct batadv_hardif_neigh_node *
batadv_hardif_neigh_create(struct batadv_hard_iface *hard_iface,
* @hard_iface: the interface this neighbour is connected to
* @neigh_addr: the interface address of the neighbour to retrieve
*
- * Returns the hardif neighbour node if found or created or NULL otherwise.
+ * Return: the hardif neighbour node if found or created or NULL otherwise.
*/
static struct batadv_hardif_neigh_node *
batadv_hardif_neigh_get_or_create(struct batadv_hard_iface *hard_iface,
* @neigh_addr: the address of the neighbour
*
* Looks for and possibly returns a neighbour belonging to this hard interface.
- * Returns NULL if the neighbour is not found.
+ *
+ * Return: neighbor when found. Othwerwise NULL
*/
struct batadv_hardif_neigh_node *
batadv_hardif_neigh_get(const struct batadv_hard_iface *hard_iface,
* @neigh_addr: the mac address of the neighbour interface
*
* Allocates a new neigh_node object and initialises all the generic fields.
- * Returns the new object or NULL on failure.
+ *
+ * Return: neighbor when found. Othwerwise NULL
*/
struct batadv_neigh_node *
batadv_neigh_node_new(struct batadv_orig_node *orig_node,
* @seq: neighbour table seq_file struct
* @offset: not used
*
- * Always returns 0.
+ * Return: always 0
*/
int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset)
{
*
* Creates a new originator object and initialise all the generic fields.
* The new object is not added to the originator list.
- * Returns the newly created object or NULL on failure.
+ *
+ * Return: the newly created object or NULL on failure.
*/
struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
const u8 *addr)
* @bat_priv: the bat priv with all the soft interface information
* @orig_node: orig node which is to be checked
*
- * Returns true if any ifinfo entry was purged, false otherwise.
+ * Return: true if any ifinfo entry was purged, false otherwise.
*/
static bool
batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv,
* @bat_priv: the bat priv with all the soft interface information
* @orig_node: orig node which is to be checked
*
- * Returns true if any neighbor was purged, false otherwise
+ * Return: true if any neighbor was purged, false otherwise
*/
static bool
batadv_purge_orig_neighbors(struct batadv_priv *bat_priv,
* @orig_node: orig node which is to be checked
* @if_outgoing: the interface for which the metric should be compared
*
- * Returns the current best neighbor, with refcount increased.
+ * Return: the current best neighbor, with refcount increased.
*/
static struct batadv_neigh_node *
batadv_find_best_neighbor(struct batadv_priv *bat_priv,
* This function checks if the orig_node or substructures of it have become
* obsolete, and purges this information if that's the case.
*
- * Returns true if the orig_node is to be removed, false otherwise.
+ * Return: true if the orig_node is to be removed, false otherwise.
*/
static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node)
* @seq: debugfs table seq_file struct
* @offset: not used
*
- * Returns 0
+ * Return: 0
*/
int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset)
{
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
};
/**
- * batadv_vlan_flags - flags for the four MSB of any vlan ID field
+ * enum batadv_vlan_flags - flags for the four MSB of any vlan ID field
* @BATADV_VLAN_HAS_TAG: whether the field contains a valid vlan tag or not
*/
enum batadv_vlan_flags {
* @version: batman-adv protocol version, part of the genereal header
* @ttl: time to live for this packet, part of the genereal header
* @flags: contains routing relevant flags - see enum batadv_iv_flags
+ * @seqno: sequence identification
+ * @orig: address of the source node
+ * @prev_sender: address of the previous sender
+ * @reserved: reserved byte for alignment
+ * @tq: transmission quality
* @tvlv_len: length of tvlv data following the ogm header
*/
struct batadv_ogm_packet {
#define BATADV_OGM_HLEN sizeof(struct batadv_ogm_packet)
/**
- * batadv_icmp_header - common members among all the ICMP packets
+ * struct batadv_icmp_header - common members among all the ICMP packets
* @packet_type: batman-adv packet type, part of the general header
* @version: batman-adv protocol version, part of the genereal header
* @ttl: time to live for this packet, part of the genereal header
};
/**
- * batadv_icmp_packet - ICMP packet
+ * struct batadv_icmp_packet - ICMP packet
* @packet_type: batman-adv packet type, part of the general header
* @version: batman-adv protocol version, part of the genereal header
* @ttl: time to live for this packet, part of the genereal header
#define BATADV_RR_LEN 16
/**
- * batadv_icmp_packet_rr - ICMP RouteRecord packet
+ * struct batadv_icmp_packet_rr - ICMP RouteRecord packet
* @packet_type: batman-adv packet type, part of the general header
* @version: batman-adv protocol version, part of the genereal header
* @ttl: time to live for this packet, part of the genereal header
* @u: common unicast packet header
* @src: address of the source
* @subtype: packet subtype
+ * @reserved: reserved byte for alignment
*/
struct batadv_unicast_4addr_packet {
struct batadv_unicast_packet u;
* @packet_type: batman-adv packet type, part of the general header
* @version: batman-adv protocol version, part of the genereal header
* @ttl: time to live for this packet, part of the genereal header
- * @reserved: Align following fields to 2-byte boundaries
* @first_source: original source of first included packet
* @first_orig_dest: original destinal of first included packet
* @first_crc: checksum of first included packet
* struct batadv_tvlv_tt_data - tt data propagated through the tt tvlv container
* @flags: translation table flags (see batadv_tt_data_flags)
* @ttvn: translation table version number
- * @vlan_num: number of announced VLANs. In the TVLV this struct is followed by
+ * @num_vlan: number of announced VLANs. In the TVLV this struct is followed by
* one batadv_tvlv_tt_vlan_data object per announced vlan
*/
struct batadv_tvlv_tt_data {
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
batadv_neigh_node_free_ref(router);
}
-/* checks whether the host restarted and is in the protection time.
- * returns:
- * 0 if the packet is to be accepted
+/**
+ * batadv_window_protected - checks whether the host restarted and is in the
+ * protection time.
+ * @bat_priv: the bat priv with all the soft interface information
+ * @seq_num_diff: difference between the current/received sequence number and
+ * the last sequence number
+ * @last_reset: jiffies timestamp of the last reset, will be updated when reset
+ * is detected
+ *
+ * Return:
+ * 0 if the packet is to be accepted.
* 1 if the packet is to be ignored.
*/
int batadv_window_protected(struct batadv_priv *bat_priv, s32 seq_num_diff,
* @bat_priv: the bat priv with all the soft interface information
* @skb: icmp packet to process
*
- * Returns NET_RX_SUCCESS if the packet has been consumed or NET_RX_DROP
+ * Return: NET_RX_SUCCESS if the packet has been consumed or NET_RX_DROP
* otherwise.
*/
static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv,
* @skb: packet to check
* @hdr_size: size of header to pull
*
- * Check for short header and bad addresses in given packet. Returns negative
- * value when check fails and 0 otherwise. The negative value depends on the
- * reason: -ENODATA for bad header, -EBADR for broadcast destination or source,
- * and -EREMOTE for non-local (other host) destination.
+ * Check for short header and bad addresses in given packet.
+ *
+ * Return: negative value when check fails and 0 otherwise. The negative value
+ * depends on the reason: -ENODATA for bad header, -EBADR for broadcast
+ * destination or source, and -EREMOTE for non-local (other host) destination.
*/
static int batadv_check_unicast_packet(struct batadv_priv *bat_priv,
struct sk_buff *skb, int hdr_size)
* @orig_node: the destination node
* @recv_if: pointer to interface this packet was received on
*
- * Returns the router which should be used for this orig_node on
+ * Return: the router which should be used for this orig_node on
* this interface, or NULL if not available.
*/
struct batadv_neigh_node *
* the new corresponding information (originator address where the destination
* client currently is and its known TTVN)
*
- * Returns true if the packet header has been updated, false otherwise
+ * Return: true if the packet header has been updated, false otherwise
*/
static bool
batadv_reroute_unicast_packet(struct batadv_priv *bat_priv,
* @skb: unicast tvlv packet to process
* @recv_if: pointer to interface this packet was received on
*
- * Returns NET_RX_SUCCESS if the packet has been consumed or NET_RX_DROP
+ * Return: NET_RX_SUCCESS if the packet has been consumed or NET_RX_DROP
* otherwise.
*/
int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb,
* batadv_recv_unicast_tvlv - receive and process unicast tvlv packets
* @skb: unicast tvlv packet to process
* @recv_if: pointer to interface this packet was received on
- * @dst_addr: the payload destination
*
- * Returns NET_RX_SUCCESS if the packet has been consumed or NET_RX_DROP
+ * Return: NET_RX_SUCCESS if the packet has been consumed or NET_RX_DROP
* otherwise.
*/
int batadv_recv_unicast_tvlv(struct sk_buff *skb,
* the assembled packet will exceed our MTU; 2) Buffer fragment, if we till
* lack further fragments; 3) Merge fragments, if we have all needed parts.
*
- * Return NET_RX_DROP if the skb is not consumed, NET_RX_SUCCESS otherwise.
+ * Return: NET_RX_DROP if the skb is not consumed, NET_RX_SUCCESS otherwise.
*/
int batadv_recv_frag_packet(struct sk_buff *skb,
struct batadv_hard_iface *recv_if)
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
* host, NULL can be passed as recv_if and no interface alternating is
* attempted.
*
- * Returns NET_XMIT_SUCCESS on success, NET_XMIT_DROP on failure, or
+ * Return: NET_XMIT_SUCCESS on success, NET_XMIT_DROP on failure, or
* NET_XMIT_POLICED if the skb is buffered for later transmit.
*/
int batadv_send_skb_to_orig(struct sk_buff *skb,
* @hdr_size: amount of bytes to push at the beginning of the skb
* @orig_node: the destination node
*
- * Returns false if the buffer extension was not possible or true otherwise.
+ * Return: false if the buffer extension was not possible or true otherwise.
*/
static bool
batadv_send_skb_push_fill_unicast(struct sk_buff *skb, int hdr_size,
* @skb: the skb containing the payload to encapsulate
* @orig_node: the destination node
*
- * Returns false if the payload could not be encapsulated or true otherwise.
+ * Return: false if the payload could not be encapsulated or true otherwise.
*/
static bool batadv_send_skb_prepare_unicast(struct sk_buff *skb,
struct batadv_orig_node *orig_node)
* unicast 4addr header
* @bat_priv: the bat priv with all the soft interface information
* @skb: the skb containing the payload to encapsulate
- * @orig_node: the destination node
+ * @orig: the destination node
* @packet_subtype: the unicast 4addr packet subtype to use
*
- * Returns false if the payload could not be encapsulated or true otherwise.
+ * Return: false if the payload could not be encapsulated or true otherwise.
*/
bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv,
struct sk_buff *skb,
* as packet_type. Then send this frame to the given orig_node and release a
* reference to this orig_node.
*
- * Returns NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
+ * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
*/
int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
struct sk_buff *skb, int packet_type,
* BATADV_UNICAST_4ADDR was supplied as packet_type. Then send this frame
* to the according destination node.
*
- * Returns NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
+ * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
*/
int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv,
struct sk_buff *skb, int packet_type,
* Look up the currently selected gateway. Wrap the given skb into a batman-adv
* unicast header and send this frame to this gateway node.
*
- * Returns NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
+ * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
*/
int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb,
unsigned short vid)
send_time);
}
-/* add a broadcast packet to the queue and setup timers. broadcast packets
- * are sent multiple times to increase probability for being received.
+/**
+ * batadv_add_bcast_packet_to_list - queue broadcast packet for multiple sends
+ * @bat_priv: the bat priv with all the soft interface information
+ * @skb: broadcast packet to add
+ * @delay: number of jiffies to wait before sending
*
- * This function returns NETDEV_TX_OK on success and NETDEV_TX_BUSY on
- * errors.
+ * add a broadcast packet to the queue and setup timers. broadcast packets
+ * are sent multiple times to increase probability for being received.
*
* The skb is not consumed, so the caller should make sure that the
* skb is freed.
+ *
+ * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY on errors.
*/
int batadv_add_bcast_packet_to_list(struct batadv_priv *bat_priv,
const struct sk_buff *skb,
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
* header via the translation table. Wrap the given skb into a batman-adv
* unicast header. Then send this frame to the according destination node.
*
- * Returns NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
+ * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
*/
static inline int batadv_send_skb_via_tt(struct batadv_priv *bat_priv,
struct sk_buff *skb, u8 *dst_hint,
* unicast-4addr header. Then send this frame to the according destination
* node.
*
- * Returns NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
+ * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise.
*/
static inline int batadv_send_skb_via_tt_4addr(struct batadv_priv *bat_priv,
struct sk_buff *skb,
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
/**
* batadv_softif_vlan_free_ref - decrease the vlan object refcounter and
* possibly free it
- * @softif_vlan: the vlan object to release
+ * @vlan: the vlan object to release
*/
void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *vlan)
{
* @bat_priv: the bat priv with all the soft interface information
* @vid: the identifier of the vlan object to retrieve
*
- * Returns the private data of the vlan matching the vid passed as argument or
+ * Return: the private data of the vlan matching the vid passed as argument or
* NULL otherwise. The refcounter of the returned object is incremented by 1.
*/
struct batadv_softif_vlan *batadv_softif_vlan_get(struct batadv_priv *bat_priv,
* @bat_priv: the bat priv with all the soft interface information
* @vid: the VLAN identifier
*
- * Returns 0 on success, a negative error otherwise.
+ * Return: 0 on success, a negative error otherwise.
*/
int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
{
/**
* batadv_interface_add_vid - ndo_add_vid API implementation
* @dev: the netdev of the mesh interface
+ * @proto: protocol of the the vlan id
* @vid: identifier of the new vlan
*
* Set up all the internal structures for handling the new vlan on top of the
* mesh interface
*
- * Returns 0 on success or a negative error code in case of failure.
+ * Return: 0 on success or a negative error code in case of failure.
*/
static int batadv_interface_add_vid(struct net_device *dev, __be16 proto,
unsigned short vid)
/**
* batadv_interface_kill_vid - ndo_kill_vid API implementation
* @dev: the netdev of the mesh interface
+ * @proto: protocol of the the vlan id
* @vid: identifier of the deleted vlan
*
* Destroy all the internal structures used to handle the vlan identified by vid
* on top of the mesh interface
*
- * Returns 0 on success, -EINVAL if the specified prototype is not ETH_P_8021Q
+ * Return: 0 on success, -EINVAL if the specified prototype is not ETH_P_8021Q
* or -ENOENT if the specified vlan id wasn't registered.
*/
static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto,
* batadv_softif_init_late - late stage initialization of soft interface
* @dev: registered network device to modify
*
- * Returns error code on failures
+ * Return: error code on failures
*/
static int batadv_softif_init_late(struct net_device *dev)
{
* @dev: batadv_soft_interface used as master interface
* @slave_dev: net_device which should become the slave interface
*
- * Return 0 if successful or error otherwise.
+ * Return: 0 if successful or error otherwise.
*/
static int batadv_softif_slave_add(struct net_device *dev,
struct net_device *slave_dev)
* @dev: batadv_soft_interface used as master interface
* @slave_dev: net_device which should be removed from the master interface
*
- * Return 0 if successful or error otherwise.
+ * Return: 0 if successful or error otherwise.
*/
static int batadv_softif_slave_del(struct net_device *dev,
struct net_device *slave_dev)
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
-/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
* batadv_vlan_kobj_to_batpriv - convert a vlan kobj in the associated batpriv
* @obj: kobject to covert
*
- * Returns the associated batadv_priv struct.
+ * Return: the associated batadv_priv struct.
*/
static struct batadv_priv *batadv_vlan_kobj_to_batpriv(struct kobject *obj)
{
/**
* batadv_kobj_to_vlan - convert a kobj in the associated softif_vlan struct
+ * @bat_priv: the bat priv with all the soft interface information
* @obj: kobject to covert
*
- * Returns the associated softif_vlan struct if found, NULL otherwise.
+ * Return: the associated softif_vlan struct if found, NULL otherwise.
*/
static struct batadv_softif_vlan *
batadv_kobj_to_vlan(struct batadv_priv *bat_priv, struct kobject *obj)
* @attr: the batman-adv attribute the user is interacting with
* @buff: the buffer that will contain the data to send back to the user
*
- * Returns the number of bytes written into 'buff' on success or a negative
+ * Return: the number of bytes written into 'buff' on success or a negative
* error code in case of failure
*/
static ssize_t batadv_show_isolation_mark(struct kobject *kobj,
* @buff: the buffer containing the user data
* @count: number of bytes in the buffer
*
- * Returns 'count' on success or a negative error code in case of failure
+ * Return: 'count' on success or a negative error code in case of failure
*/
static ssize_t batadv_store_isolation_mark(struct kobject *kobj,
struct attribute *attr, char *buff,
BATADV_ATTR_VLAN_BOOL(ap_isolation, S_IRUGO | S_IWUSR, NULL);
-/**
- * batadv_vlan_attrs - array of vlan specific sysfs attributes
- */
+/* array of vlan specific sysfs attributes */
static struct batadv_attribute *batadv_vlan_attrs[] = {
&batadv_attr_vlan_ap_isolation,
NULL,
* @dev: netdev of the mesh interface
* @vlan: private data of the newly added VLAN interface
*
- * Returns 0 on success and -ENOMEM if any of the structure allocations fails.
+ * Return: 0 on success and -ENOMEM if any of the structure allocations fails.
*/
int batadv_sysfs_add_vlan(struct net_device *dev,
struct batadv_softif_vlan *vlan)
-/* Copyright (C) 2010-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2010-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner
*
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich, Antonio Quartulli
*
unsigned short vid, const char *message,
bool roaming);
-/* returns 1 if they are the same mac addr and vid */
+/**
+ * batadv_compare_tt - check if two TT entries are the same
+ * @node: the list element pointer of the first TT entry
+ * @data2: pointer to the tt_common_entry of the second TT entry
+ *
+ * Compare the MAC address and the VLAN ID of the two TT entries and check if
+ * they are the same TT client.
+ * Return: 1 if the two TT clients are the same, 0 otherwise
+ */
static int batadv_compare_tt(const struct hlist_node *node, const void *data2)
{
const void *data1 = container_of(node, struct batadv_tt_common_entry,
* @data: pointer to the tt_common_entry object to map
* @size: the size of the hash table
*
- * Returns the hash index where the object represented by 'data' should be
+ * Return: the hash index where the object represented by 'data' should be
* stored at.
*/
static inline u32 batadv_choose_tt(const void *data, u32 size)
* @addr: the mac address of the client to look for
* @vid: VLAN identifier
*
- * Returns a pointer to the tt_common struct belonging to the searched client if
+ * Return: a pointer to the tt_common struct belonging to the searched client if
* found, NULL otherwise.
*/
static struct batadv_tt_common_entry *
* @addr: the mac address of the client to look for
* @vid: VLAN identifier
*
- * Returns a pointer to the corresponding tt_local_entry struct if the client is
+ * Return: a pointer to the corresponding tt_local_entry struct if the client is
* found, NULL otherwise.
*/
static struct batadv_tt_local_entry *
* @addr: the mac address of the client to look for
* @vid: VLAN identifier
*
- * Returns a pointer to the corresponding tt_global_entry struct if the client
+ * Return: a pointer to the corresponding tt_global_entry struct if the client
* is found, NULL otherwise.
*/
static struct batadv_tt_global_entry *
/**
* batadv_tt_global_hash_count - count the number of orig entries
- * @hash: hash table containing the tt entries
+ * @bat_priv: the bat priv with all the soft interface information
* @addr: the mac address of the client to count entries for
* @vid: VLAN identifier
*
- * Return the number of originators advertising the given address/data
+ * Return: the number of originators advertising the given address/data
* (excluding ourself).
*/
int batadv_tt_global_hash_count(struct batadv_priv *bat_priv,
}
/**
- * batadv_tt_global_size_mod - change the size by v of the local table
- * identified by vid
- * @bat_priv: the bat priv with all the soft interface information
+ * batadv_tt_global_size_mod - change the size by v of the global table
+ * for orig_node identified by vid
+ * @orig_node: the originator for which the table has to be modified
* @vid: the VLAN identifier
* @v: the amount to sum to the global table size
*/
* batadv_tt_len - compute length in bytes of given number of tt changes
* @changes_num: number of tt changes
*
- * Returns computed length in bytes.
+ * Return: computed length in bytes.
*/
static int batadv_tt_len(int changes_num)
{
* batadv_tt_entries - compute the number of entries fitting in tt_len bytes
* @tt_len: available space
*
- * Returns the number of entries.
+ * Return: the number of entries.
*/
static u16 batadv_tt_entries(u16 tt_len)
{
* size when transmitted over the air
* @bat_priv: the bat priv with all the soft interface information
*
- * Returns local translation table size in bytes.
+ * Return: local translation table size in bytes.
*/
static int batadv_tt_local_table_transmit_size(struct batadv_priv *bat_priv)
{
* @mark: the value contained in the skb->mark field of the received packet (if
* any)
*
- * Returns true if the client was successfully added, false otherwise.
+ * Return: true if the client was successfully added, false otherwise.
*/
bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
unsigned short vid, int ifindex, u32 mark)
* function reserves the amount of space needed to send the entire global TT
* table. In case of success the value is updated with the real amount of
* reserved bytes
-
* Allocate the needed amount of memory for the entire TT TVLV and write its
* header made up by one tvlv_tt_data object and a series of tvlv_tt_vlan_data
* objects, one per active VLAN served by the originator node.
*
- * Return the size of the allocated buffer or 0 in case of failure.
+ * Return: the size of the allocated buffer or 0 in case of failure.
*/
static u16
batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node,
* header made up by one tvlv_tt_data object and a series of tvlv_tt_vlan_data
* objects, one per active VLAN.
*
- * Return the size of the allocated buffer or 0 in case of failure.
+ * Return: the size of the allocated buffer or 0 in case of failure.
*/
static u16
batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
* @message: message to append to the log on deletion
* @roaming: true if the deletion is due to a roaming event
*
- * Returns the flags assigned to the local entry before being deleted
+ * Return: the flags assigned to the local entry before being deleted
*/
u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr,
unsigned short vid, const char *message,
spin_unlock_bh(&bat_priv->tt.changes_list_lock);
}
-/* retrieves the orig_tt_list_entry belonging to orig_node from the
+/**
+ * batadv_tt_global_orig_entry_find - find a TT orig_list_entry
+ * @entry: the TT global entry where the orig_list_entry has to be
+ * extracted from
+ * @orig_node: the originator for which the orig_list_entry has to be found
+ *
+ * retrieve the orig_tt_list_entry belonging to orig_node from the
* batadv_tt_global_entry list
*
- * returns it with an increased refcounter, NULL if not found
+ * Return: it with an increased refcounter, NULL if not found
*/
static struct batadv_tt_orig_list_entry *
batadv_tt_global_orig_entry_find(const struct batadv_tt_global_entry *entry,
return orig_entry;
}
-/* find out if an orig_node is already in the list of a tt_global_entry.
- * returns true if found, false otherwise
+/**
+ * batadv_tt_global_entry_has_orig - check if a TT global entry is also handled
+ * by a given originator
+ * @entry: the TT global entry to check
+ * @orig_node: the originator to search in the list
+ *
+ * find out if an orig_node is already in the list of a tt_global_entry.
+ *
+ * Return: true if found, false otherwise
*/
static bool
batadv_tt_global_entry_has_orig(const struct batadv_tt_global_entry *entry,
*
* The caller must hold orig_node refcount.
*
- * Return true if the new entry has been added, false otherwise
+ * Return: true if the new entry has been added, false otherwise
*/
static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
* @tt_global_entry: global translation table entry to be analyzed
*
* This functon assumes the caller holds rcu_read_lock().
- * Returns best originator list entry or NULL on errors.
+ * Return: best originator list entry or NULL on errors.
*/
static struct batadv_tt_orig_list_entry *
batadv_transtable_best_orig(struct batadv_priv *bat_priv,
* @addr: mac address of the destination client
* @vid: VLAN identifier
*
- * Returns a pointer to the originator that was selected as destination in the
+ * Return: a pointer to the originator that was selected as destination in the
* mesh for contacting the client 'addr', NULL otherwise.
* In case of multiple originators serving the same client, the function returns
* the best one (best in terms of metric towards the destination node).
* because the XOR operation can combine them all while trying to reduce the
* noise as much as possible.
*
- * Returns the checksum of the global table of a given originator.
+ * Return: the checksum of the global table of a given originator.
*/
static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
* For details about the computation, please refer to the documentation for
* batadv_tt_global_crc().
*
- * Returns the checksum of the local table
+ * Return: the checksum of the local table
*/
static u32 batadv_tt_local_crc(struct batadv_priv *bat_priv,
unsigned short vid)
* @bat_priv: the bat priv with all the soft interface information
* @orig_node: orig node this request is being issued for
*
- * Returns the pointer to the new tt_req_node struct if no request
+ * Return: the pointer to the new tt_req_node struct if no request
* has already been issued for this orig_node, NULL otherwise.
*/
static struct batadv_tt_req_node *
* @entry_ptr: to be checked local tt entry
* @data_ptr: not used but definition required to satisfy the callback prototype
*
- * Returns 1 if the entry is a valid, 0 otherwise.
+ * Return: 1 if the entry is a valid, 0 otherwise.
*/
static int batadv_tt_local_valid(const void *entry_ptr, const void *data_ptr)
{
* @orig_node: originator for which the CRCs have to be checked
* @tt_vlan: pointer to the first tvlv VLAN entry
* @num_vlan: number of tvlv VLAN entries
- * @create: if true, create VLAN objects if not found
*
- * Return true if all the received CRCs match the locally stored ones, false
+ * Return: true if all the received CRCs match the locally stored ones, false
* otherwise
*/
static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node,
* @num_vlan: number of tvlv VLAN entries
* @full_table: ask for the entire translation table if true, while only for the
* last TT diff otherwise
+ *
+ * Return: true if the TT Request was sent, false otherwise
*/
static int batadv_send_tt_request(struct batadv_priv *bat_priv,
struct batadv_orig_node *dst_orig_node,
* @req_src: mac address of tt request sender
* @req_dst: mac address of tt request recipient
*
- * Returns true if tt request reply was sent, false otherwise.
+ * Return: true if tt request reply was sent, false otherwise.
*/
static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv,
struct batadv_tvlv_tt_data *tt_data,
* @tt_data: tt data containing the tt request information
* @req_src: mac address of tt request sender
*
- * Returns true if tt request reply was sent, false otherwise.
+ * Return: true if tt request reply was sent, false otherwise.
*/
static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv,
struct batadv_tvlv_tt_data *tt_data,
* @req_src: mac address of tt request sender
* @req_dst: mac address of tt request recipient
*
- * Returns true if tt request reply was sent, false otherwise.
+ * Return: true if tt request reply was sent, false otherwise.
*/
static bool batadv_send_tt_response(struct batadv_priv *bat_priv,
struct batadv_tvlv_tt_data *tt_data,
* @addr: the mac address of the client to check
* @vid: VLAN identifier
*
- * Returns true if the client is served by this node, false otherwise.
+ * Return: true if the client is served by this node, false otherwise.
*/
bool batadv_is_my_client(struct batadv_priv *bat_priv, const u8 *addr,
unsigned short vid)
spin_unlock_bh(&bat_priv->tt.roam_list_lock);
}
-/* This function checks whether the client already reached the
+/**
+ * batadv_tt_check_roam_count - check if a client has roamed too frequently
+ * @bat_priv: the bat priv with all the soft interface information
+ * @client: mac address of the roaming client
+ *
+ * This function checks whether the client already reached the
* maximum number of possible roaming phases. In this case the ROAMING_ADV
* will not be sent.
*
- * returns true if the ROAMING_ADV can be sent, false otherwise
+ * Return: true if the ROAMING_ADV can be sent, false otherwise
*/
static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client)
{
* batadv_tt_update_orig - update global translation table with new tt
* information received via ogms
* @bat_priv: the bat priv with all the soft interface information
- * @orig: the orig_node of the ogm
- * @tt_vlan: pointer to the first tvlv VLAN entry
+ * @orig_node: the orig_node of the ogm
+ * @tt_buff: pointer to the first tvlv VLAN entry
* @tt_num_vlan: number of tvlv VLAN entries
* @tt_change: pointer to the first entry in the TT buffer
* @tt_num_changes: number of tt changes inside the tt buffer
* @ttvn: translation table version number of this changeset
- * @tt_crc: crc32 checksum of orig node's translation table
*/
static void batadv_tt_update_orig(struct batadv_priv *bat_priv,
struct batadv_orig_node *orig_node,
* @addr: the mac address of the client to check
* @vid: VLAN identifier
*
- * Returns true if we know that the client has moved from its old originator
+ * Return: true if we know that the client has moved from its old originator
* to another one. This entry is still kept for consistency purposes and will be
* deleted later by a DEL or because of timeout
*/
* @addr: the mac address of the local client to query
* @vid: VLAN identifier
*
- * Returns true if the local client is known to be roaming (it is not served by
+ * Return: true if the local client is known to be roaming (it is not served by
* this node anymore) or not. If yes, the client is still present in the table
* to keep the latter consistent with the node TTVN
*/
* @tvlv_value: tvlv buffer containing the tt data
* @tvlv_value_len: tvlv buffer length
*
- * Returns NET_RX_DROP if the tt tvlv is to be re-routed, NET_RX_SUCCESS
+ * Return: NET_RX_DROP if the tt tvlv is to be re-routed, NET_RX_SUCCESS
* otherwise.
*/
static int batadv_tt_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv,
* @tvlv_value: tvlv buffer containing the tt data
* @tvlv_value_len: tvlv buffer length
*
- * Returns NET_RX_DROP if the tt roam tvlv is to be re-routed, NET_RX_SUCCESS
+ * Return: NET_RX_DROP if the tt roam tvlv is to be re-routed, NET_RX_SUCCESS
* otherwise.
*/
static int batadv_roam_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv,
* batadv_tt_init - initialise the translation table internals
* @bat_priv: the bat priv with all the soft interface information
*
- * Return 0 on success or negative error number in case of failure.
+ * Return: 0 on success or negative error number in case of failure.
*/
int batadv_tt_init(struct batadv_priv *bat_priv)
{
* @addr: the mac address of the client
* @vid: the identifier of the VLAN where this client is connected
*
- * Returns true if the client is marked with the TT_CLIENT_ISOLA flag, false
+ * Return: true if the client is marked with the TT_CLIENT_ISOLA flag, false
* otherwise
*/
bool batadv_tt_global_is_isolated(struct batadv_priv *bat_priv,
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich, Antonio Quartulli
*
-/* Copyright (C) 2007-2015 B.A.T.M.A.N. contributors:
+/* Copyright (C) 2007-2016 B.A.T.M.A.N. contributors:
*
* Marek Lindner, Simon Wunderlich
*
#define BATADV_TT_SYNC_MASK 0x00F0
/**
- * struct batadv_hard_iface_bat_iv - per hard interface B.A.T.M.A.N. IV data
+ * struct batadv_hard_iface_bat_iv - per hard-interface B.A.T.M.A.N. IV data
* @ogm_buff: buffer holding the OGM packet
* @ogm_buff_len: length of the OGM packet buffer
* @ogm_seqno: OGM sequence number - used to identify each OGM
* batman-adv for this interface
* @soft_iface: the batman-adv interface which uses this network interface
* @rcu: struct used for freeing in an RCU-safe manner
- * @bat_iv: BATMAN IV specific per hard interface data
- * @cleanup_work: work queue callback item for hard interface deinit
+ * @bat_iv: per hard-interface B.A.T.M.A.N. IV data
+ * @cleanup_work: work queue callback item for hard-interface deinit
* @debug_dir: dentry for nc subdir in batman-adv directory in debugfs
* @neigh_list: list of unique single hop neighbors via this interface
* @neigh_list_lock: lock protecting neigh_list
/**
* struct batadv_orig_ifinfo - originator info per outgoing interface
* @list: list node for orig_node::ifinfo_list
- * @if_outgoing: pointer to outgoing hard interface
+ * @if_outgoing: pointer to outgoing hard-interface
* @router: router that should be used to reach this originator
* @last_real_seqno: last and best known sequence number
* @last_ttl: ttl of last received packet
/**
* struct batadv_orig_bat_iv - B.A.T.M.A.N. IV private orig_node members
- * @bcast_own: set of bitfields (one per hard interface) where each one counts
+ * @bcast_own: set of bitfields (one per hard-interface) where each one counts
* the number of our OGMs this orig_node rebroadcasted "back" to us (relative
* to last_real_seqno). Every bitfield is BATADV_TQ_LOCAL_WINDOW_SIZE bits long.
* @bcast_own_sum: sum of bcast_own
};
/**
- * batadv_hardif_neigh_node - unique neighbor per hard interface
+ * struct batadv_hardif_neigh_node - unique neighbor per hard-interface
* @list: list node for batadv_hard_iface::neigh_list
* @addr: the MAC address of the neighboring interface
- * @if_incoming: pointer to incoming hard interface
+ * @if_incoming: pointer to incoming hard-interface
+ * @last_seen: when last packet via this neighbor was received
* @refcount: number of contexts the object is used
* @rcu: struct used for freeing in a RCU-safe manner
*/
* @addr: the MAC address of the neighboring interface
* @ifinfo_list: list for routing metrics per outgoing interface
* @ifinfo_lock: lock protecting private ifinfo members and list
- * @if_incoming: pointer to incoming hard interface
+ * @if_incoming: pointer to incoming hard-interface
* @last_seen: when last packet via this neighbor was received
* @refcount: number of contexts the object is used
* @rcu: struct used for freeing in an RCU-safe manner
/**
* struct batadv_neigh_ifinfo_bat_iv - neighbor information per outgoing
- * interface for BATMAN IV
+ * interface for B.A.T.M.A.N. IV
* @tq_recv: ring buffer of received TQ values from this neigh node
* @tq_index: ring buffer index
* @tq_avg: averaged tq of all tq values in the ring buffer (tq_recv)
/**
* struct batadv_neigh_ifinfo - neighbor information per outgoing interface
* @list: list node for batadv_neigh_node::ifinfo_list
- * @if_outgoing: pointer to outgoing hard interface
+ * @if_outgoing: pointer to outgoing hard-interface
* @bat_iv: B.A.T.M.A.N. IV private structure
* @last_ttl: last received ttl from this neigh node
* @refcount: number of contexts the object is used
* @orig_interval: OGM broadcast interval in milliseconds
* @hop_penalty: penalty which will be applied to an OGM's tq-field on every hop
* @log_level: configured log level (see batadv_dbg_level)
+ * @isolation_mark: the skb->mark value used to match packets for AP isolation
+ * @isolation_mark_mask: bitmask identifying the bits in skb->mark to be used
+ * for the isolation mark
* @bcast_seqno: last sent broadcast packet sequence number
* @bcast_queue_left: number of remaining buffered broadcast packet slots
* @batman_queue_left: number of remaining OGM packet slots
* @forw_bat_list_lock: lock protecting forw_bat_list
* @forw_bcast_list_lock: lock protecting forw_bcast_list
* @orig_work: work queue callback item for orig node purging
- * @cleanup_work: work queue callback item for soft interface deinit
- * @primary_if: one of the hard interfaces assigned to this mesh interface
+ * @cleanup_work: work queue callback item for soft-interface deinit
+ * @primary_if: one of the hard-interfaces assigned to this mesh interface
* becomes the primary interface
* @bat_algo_ops: routing algorithm used by this mesh interface
* @softif_vlan_list: a list of softif_vlan structs, one per VLAN created on top
return -EMSGSIZE;
}
+static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags)
+{
+ e->state = flags & MDB_PG_FLAGS_PERMANENT;
+ e->flags = 0;
+ if (flags & MDB_PG_FLAGS_OFFLOAD)
+ e->flags |= MDB_FLAGS_OFFLOAD;
+}
+
static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
struct net_device *dev)
{
struct br_mdb_entry e;
memset(&e, 0, sizeof(e));
e.ifindex = port->dev->ifindex;
- e.state = p->state;
e.vid = p->addr.vid;
+ __mdb_entry_fill_flags(&e, p->flags);
if (p->addr.proto == htons(ETH_P_IP))
e.addr.u.ip4 = p->addr.u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
}
static void __br_mdb_notify(struct net_device *dev, struct br_mdb_entry *entry,
- int type)
+ int type, struct net_bridge_port_group *pg)
{
struct switchdev_obj_port_mdb mdb = {
.obj = {
#endif
mdb.obj.orig_dev = port_dev;
- if (port_dev && type == RTM_NEWMDB)
- switchdev_port_obj_add(port_dev, &mdb.obj);
- else if (port_dev && type == RTM_DELMDB)
+ if (port_dev && type == RTM_NEWMDB) {
+ err = switchdev_port_obj_add(port_dev, &mdb.obj);
+ if (!err && pg)
+ pg->flags |= MDB_PG_FLAGS_OFFLOAD;
+ } else if (port_dev && type == RTM_DELMDB) {
switchdev_port_obj_del(port_dev, &mdb.obj);
+ }
skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC);
if (!skb)
rtnl_set_sk_err(net, RTNLGRP_MDB, err);
}
-void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
- struct br_ip *group, int type, u8 state)
+void br_mdb_notify(struct net_device *dev, struct net_bridge_port_group *pg,
+ int type)
{
struct br_mdb_entry entry;
memset(&entry, 0, sizeof(entry));
- entry.ifindex = port->dev->ifindex;
- entry.addr.proto = group->proto;
- entry.addr.u.ip4 = group->u.ip4;
+ entry.ifindex = pg->port->dev->ifindex;
+ entry.addr.proto = pg->addr.proto;
+ entry.addr.u.ip4 = pg->addr.u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
- entry.addr.u.ip6 = group->u.ip6;
+ entry.addr.u.ip6 = pg->addr.u.ip6;
#endif
- entry.state = state;
- entry.vid = group->vid;
- __br_mdb_notify(dev, &entry, type);
+ entry.vid = pg->addr.vid;
+ __mdb_entry_fill_flags(&entry, pg->flags);
+ __br_mdb_notify(dev, &entry, type, pg);
}
static int nlmsg_populate_rtr_fill(struct sk_buff *skb,
}
static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
- struct br_ip *group, unsigned char state)
+ struct br_ip *group, unsigned char state,
+ struct net_bridge_port_group **pg)
{
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
if (unlikely(!p))
return -ENOMEM;
rcu_assign_pointer(*pp, p);
+ *pg = p;
if (state == MDB_TEMPORARY)
mod_timer(&p->timer, now + br->multicast_membership_interval);
}
static int __br_mdb_add(struct net *net, struct net_bridge *br,
- struct br_mdb_entry *entry)
+ struct br_mdb_entry *entry,
+ struct net_bridge_port_group **pg)
{
struct br_ip ip;
struct net_device *dev;
#endif
spin_lock_bh(&br->multicast_lock);
- ret = br_mdb_add_group(br, p, &ip, entry->state);
+ ret = br_mdb_add_group(br, p, &ip, entry->state, pg);
spin_unlock_bh(&br->multicast_lock);
return ret;
}
static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct net *net = sock_net(skb->sk);
+ struct net_bridge_port_group *pg;
struct net_bridge_vlan_group *vg;
struct net_device *dev, *pdev;
struct br_mdb_entry *entry;
if (br_vlan_enabled(br) && vg && entry->vid == 0) {
list_for_each_entry(v, &vg->vlan_list, vlist) {
entry->vid = v->vid;
- err = __br_mdb_add(net, br, entry);
+ err = __br_mdb_add(net, br, entry, &pg);
if (err)
break;
- __br_mdb_notify(dev, entry, RTM_NEWMDB);
+ __br_mdb_notify(dev, entry, RTM_NEWMDB, pg);
}
} else {
- err = __br_mdb_add(net, br, entry);
+ err = __br_mdb_add(net, br, entry, &pg);
if (!err)
- __br_mdb_notify(dev, entry, RTM_NEWMDB);
+ __br_mdb_notify(dev, entry, RTM_NEWMDB, pg);
}
return err;
if (p->port->state == BR_STATE_DISABLED)
goto unlock;
- entry->state = p->state;
+ __mdb_entry_fill_flags(entry, p->flags);
rcu_assign_pointer(*pp, p->next);
hlist_del_init(&p->mglist);
del_timer(&p->timer);
entry->vid = v->vid;
err = __br_mdb_del(br, entry);
if (!err)
- __br_mdb_notify(dev, entry, RTM_DELMDB);
+ __br_mdb_notify(dev, entry, RTM_DELMDB, NULL);
}
} else {
err = __br_mdb_del(br, entry);
if (!err)
- __br_mdb_notify(dev, entry, RTM_DELMDB);
+ __br_mdb_notify(dev, entry, RTM_DELMDB, NULL);
}
return err;
rcu_assign_pointer(*pp, p->next);
hlist_del_init(&p->mglist);
del_timer(&p->timer);
- br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB,
- p->state);
+ br_mdb_notify(br->dev, p, RTM_DELMDB);
call_rcu_bh(&p->rcu, br_multicast_free_pg);
if (!mp->ports && !mp->mglist &&
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) || timer_pending(&pg->timer) ||
- hlist_unhashed(&pg->mglist) || pg->state & MDB_PERMANENT)
+ hlist_unhashed(&pg->mglist) || pg->flags & MDB_PG_FLAGS_PERMANENT)
goto out;
br_multicast_del_pg(br, pg);
struct net_bridge_port *port,
struct br_ip *group,
struct net_bridge_port_group __rcu *next,
- unsigned char state)
+ unsigned char flags)
{
struct net_bridge_port_group *p;
p->addr = *group;
p->port = port;
- p->state = state;
+ p->flags = flags;
rcu_assign_pointer(p->next, next);
hlist_add_head(&p->mglist, &port->mglist);
setup_timer(&p->timer, br_multicast_port_group_expired,
break;
}
- p = br_multicast_new_port_group(port, group, *pp, MDB_TEMPORARY);
+ p = br_multicast_new_port_group(port, group, *pp, 0);
if (unlikely(!p))
goto err;
rcu_assign_pointer(*pp, p);
- br_mdb_notify(br->dev, port, group, RTM_NEWMDB, MDB_TEMPORARY);
+ br_mdb_notify(br->dev, p, RTM_NEWMDB);
found:
mod_timer(&p->timer, now + br->multicast_membership_interval);
spin_lock(&br->multicast_lock);
hlist_for_each_entry_safe(pg, n, &port->mglist, mglist)
- if (pg->state == MDB_TEMPORARY)
+ if (!(pg->flags & MDB_PG_FLAGS_PERMANENT))
br_multicast_del_pg(br, pg);
if (!hlist_unhashed(&port->rlist)) {
hlist_del_init(&p->mglist);
del_timer(&p->timer);
call_rcu_bh(&p->rcu, br_multicast_free_pg);
- br_mdb_notify(br->dev, port, group, RTM_DELMDB,
- p->state);
+ br_mdb_notify(br->dev, p, RTM_DELMDB);
if (!mp->ports && !mp->mglist &&
netif_running(br->dev))
struct rcu_head rcu;
};
+#define MDB_PG_FLAGS_PERMANENT BIT(0)
+#define MDB_PG_FLAGS_OFFLOAD BIT(1)
+
struct net_bridge_port_group {
struct net_bridge_port *port;
struct net_bridge_port_group __rcu *next;
struct rcu_head rcu;
struct timer_list timer;
struct br_ip addr;
- unsigned char state;
+ unsigned char flags;
};
struct net_bridge_mdb_entry
struct net_bridge_port_group *
br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group,
struct net_bridge_port_group __rcu *next,
- unsigned char state);
+ unsigned char flags);
void br_mdb_init(void);
void br_mdb_uninit(void);
-void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
- struct br_ip *group, int type, u8 state);
+void br_mdb_notify(struct net_device *dev, struct net_bridge_port_group *pg,
+ int type);
void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port,
int type);
ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
} else {
drop:
- atomic_long_inc(&skb->dev->rx_dropped);
+ if (!deliver_exact)
+ atomic_long_inc(&skb->dev->rx_dropped);
+ else
+ atomic_long_inc(&skb->dev->rx_nohandler);
kfree_skb(skb);
/* Jamal, now you will not able to escape explaining
* me how you were going to use this. :-)
}
}
-/* Convert net_device_stats to rtnl_link_stats64. They have the same
- * fields in the same order, with only the type differing.
+/* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has
+ * all the same fields in the same order as net_device_stats, with only
+ * the type differing, but rtnl_link_stats64 may have additional fields
+ * at the end for newer counters.
*/
void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
const struct net_device_stats *netdev_stats)
{
#if BITS_PER_LONG == 64
- BUILD_BUG_ON(sizeof(*stats64) != sizeof(*netdev_stats));
+ BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats));
memcpy(stats64, netdev_stats, sizeof(*stats64));
+ /* zero out counters that only exist in rtnl_link_stats64 */
+ memset((char *)stats64 + sizeof(*netdev_stats), 0,
+ sizeof(*stats64) - sizeof(*netdev_stats));
#else
- size_t i, n = sizeof(*stats64) / sizeof(u64);
+ size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long);
const unsigned long *src = (const unsigned long *)netdev_stats;
u64 *dst = (u64 *)stats64;
- BUILD_BUG_ON(sizeof(*netdev_stats) / sizeof(unsigned long) !=
- sizeof(*stats64) / sizeof(u64));
+ BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64));
for (i = 0; i < n; i++)
dst[i] = src[i];
+ /* zero out counters that only exist in rtnl_link_stats64 */
+ memset((char *)stats64 + n * sizeof(u64), 0,
+ sizeof(*stats64) - n * sizeof(u64));
#endif
}
EXPORT_SYMBOL(netdev_stats_to_stats64);
}
storage->rx_dropped += atomic_long_read(&dev->rx_dropped);
storage->tx_dropped += atomic_long_read(&dev->tx_dropped);
+ storage->rx_nohandler += atomic_long_read(&dev->rx_nohandler);
return storage;
}
EXPORT_SYMBOL(dev_get_stats);
return 0;
}
-u8 netdev_rss_key[NETDEV_RSS_KEY_LEN];
+u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly;
void netdev_rss_key_fill(void *buffer, size_t len)
{
NETSTAT_ENTRY(tx_window_errors);
NETSTAT_ENTRY(rx_compressed);
NETSTAT_ENTRY(tx_compressed);
+NETSTAT_ENTRY(rx_nohandler);
static struct attribute *netstat_attrs[] = {
&dev_attr_rx_packets.attr,
&dev_attr_tx_window_errors.attr,
&dev_attr_rx_compressed.attr,
&dev_attr_tx_compressed.attr,
+ &dev_attr_rx_nohandler.attr,
NULL
};
a->rx_compressed = b->rx_compressed;
a->tx_compressed = b->tx_compressed;
+
+ a->rx_nohandler = b->rx_nohandler;
}
static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b)
#define AF_INET_FAMILY(fam) true
#endif
-/* Only thing we need from tcp.h */
-extern int sysctl_tcp_synack_retries;
-
-
/* Decide when to expire the request and when to resend SYN-ACK */
static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
const int max_retries,
{
struct request_sock *req = (struct request_sock *)data;
struct sock *sk_listener = req->rsk_listener;
+ struct net *net = sock_net(sk_listener);
struct inet_connection_sock *icsk = inet_csk(sk_listener);
struct request_sock_queue *queue = &icsk->icsk_accept_queue;
int qlen, expire = 0, resend = 0;
if (sk_state_load(sk_listener) != TCP_LISTEN)
goto drop;
- max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries;
+ max_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
thresh = max_retries;
/* Normally all the openreqs are young and become mature
* (i.e. converted to established socket) for first timeout.
#include <net/tcp.h>
#include <net/route.h>
-extern int sysctl_tcp_syncookies;
-
static u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS] __read_mostly;
#define COOKIEBITS 24 /* Upper bits store count */
__u8 rcv_wscale;
struct flowi4 fl4;
- if (!sysctl_tcp_syncookies || !th->ack || th->rst)
+ if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
goto out;
if (tcp_synq_no_recent_overflow(sk))
.extra1 = &ip_ttl_min,
.extra2 = &ip_ttl_max,
},
- {
- .procname = "tcp_syn_retries",
- .data = &sysctl_tcp_syn_retries,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = &tcp_syn_retries_min,
- .extra2 = &tcp_syn_retries_max
- },
- {
- .procname = "tcp_synack_retries",
- .data = &sysctl_tcp_synack_retries,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
{
.procname = "tcp_max_orphans",
.data = &sysctl_tcp_max_orphans,
.mode = 0644,
.proc_handler = proc_dointvec
},
- {
- .procname = "tcp_retries1",
- .data = &sysctl_tcp_retries1,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra2 = &tcp_retr1_max
- },
- {
- .procname = "tcp_retries2",
- .data = &sysctl_tcp_retries2,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
- .procname = "tcp_fin_timeout",
- .data = &sysctl_tcp_fin_timeout,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
-#ifdef CONFIG_SYN_COOKIES
- {
- .procname = "tcp_syncookies",
- .data = &sysctl_tcp_syncookies,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
-#endif
{
.procname = "tcp_fastopen",
.data = &sysctl_tcp_fastopen,
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
- {
- .procname = "tcp_orphan_retries",
- .data = &sysctl_tcp_orphan_retries,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
{
.procname = "tcp_fack",
.data = &sysctl_tcp_fack,
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
- .procname = "tcp_reordering",
- .data = &sysctl_tcp_reordering,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
{
.procname = "tcp_max_reordering",
.data = &sysctl_tcp_max_reordering,
.proc_handler = proc_dointvec_minmax,
.extra1 = &one,
},
- {
- .procname = "tcp_notsent_lowat",
- .data = &sysctl_tcp_notsent_lowat,
- .maxlen = sizeof(sysctl_tcp_notsent_lowat),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
{
.procname = "tcp_rmem",
.data = &sysctl_tcp_rmem,
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
+ {
+ .procname = "tcp_syn_retries",
+ .data = &init_net.ipv4.sysctl_tcp_syn_retries,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &tcp_syn_retries_min,
+ .extra2 = &tcp_syn_retries_max
+ },
+ {
+ .procname = "tcp_synack_retries",
+ .data = &init_net.ipv4.sysctl_tcp_synack_retries,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+#ifdef CONFIG_SYN_COOKIES
+ {
+ .procname = "tcp_syncookies",
+ .data = &init_net.ipv4.sysctl_tcp_syncookies,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+#endif
+ {
+ .procname = "tcp_reordering",
+ .data = &init_net.ipv4.sysctl_tcp_reordering,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_retries1",
+ .data = &init_net.ipv4.sysctl_tcp_retries1,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra2 = &tcp_retr1_max
+ },
+ {
+ .procname = "tcp_retries2",
+ .data = &init_net.ipv4.sysctl_tcp_retries2,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_orphan_retries",
+ .data = &init_net.ipv4.sysctl_tcp_orphan_retries,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .procname = "tcp_fin_timeout",
+ .data = &init_net.ipv4.sysctl_tcp_fin_timeout,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
+ {
+ .procname = "tcp_notsent_lowat",
+ .data = &init_net.ipv4.sysctl_tcp_notsent_lowat,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
{ }
};
#include <asm/unaligned.h>
#include <net/busy_poll.h>
-int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
-
int sysctl_tcp_min_tso_segs __read_mostly = 2;
int sysctl_tcp_autocorking __read_mostly = 1;
tp->mss_cache = TCP_MSS_DEFAULT;
u64_stats_init(&tp->syncp);
- tp->reordering = sysctl_tcp_reordering;
+ tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
tcp_enable_early_retrans(tp);
tcp_assign_congestion_control(sk);
while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
offset = seq - TCP_SKB_CB(skb)->seq;
- if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
+ if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+ pr_err_once("%s: found a SYN, please report !\n", __func__);
offset--;
+ }
if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) {
*off = offset;
return skb;
break;
offset = *seq - TCP_SKB_CB(skb)->seq;
- if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
+ if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
+ pr_err_once("%s: found a SYN, please report !\n", __func__);
offset--;
+ }
if (offset < skb->len)
goto found_ok_skb;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct net *net = sock_net(sk);
int val;
int err = 0;
case TCP_LINGER2:
if (val < 0)
tp->linger2 = -1;
- else if (val > sysctl_tcp_fin_timeout / HZ)
+ else if (val > net->ipv4.sysctl_tcp_fin_timeout / HZ)
tp->linger2 = 0;
else
tp->linger2 = val * HZ;
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
int val, len;
if (get_user(len, optlen))
val = keepalive_probes(tp);
break;
case TCP_SYNCNT:
- val = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
+ val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
break;
case TCP_LINGER2:
val = tp->linger2;
if (val >= 0)
- val = (val ? : sysctl_tcp_fin_timeout) / HZ;
+ val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ;
break;
case TCP_DEFER_ACCEPT:
val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
return false;
}
+
+/* If an incoming SYN or SYNACK frame contains a payload and/or FIN,
+ * queue this additional data / FIN.
+ */
+void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (TCP_SKB_CB(skb)->end_seq == tp->rcv_nxt)
+ return;
+
+ skb = skb_clone(skb, GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ skb_dst_drop(skb);
+ __skb_pull(skb, tcp_hdrlen(skb));
+ skb_set_owner_r(skb, sk);
+
+ TCP_SKB_CB(skb)->seq++;
+ TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
+
+ tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ __skb_queue_tail(&sk->sk_receive_queue, skb);
+ tp->syn_data_acked = 1;
+
+ /* u64_stats_update_begin(&tp->syncp) not needed here,
+ * as we certainly are not changing upper 32bit value (0)
+ */
+ tp->bytes_received = skb->len;
+
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+ tcp_fin(sk);
+}
+
static struct sock *tcp_fastopen_create_child(struct sock *sk,
struct sk_buff *skb,
struct dst_entry *dst,
struct tcp_sock *tp;
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
struct sock *child;
- u32 end_seq;
bool own_req;
req->num_retrans = 0;
tcp_init_metrics(child);
tcp_init_buffer_space(child);
- /* Queue the data carried in the SYN packet.
- * We used to play tricky games with skb_get().
- * With lockless listener, it is a dead end.
- * Do not think about it.
- *
- * XXX (TFO) - we honor a zero-payload TFO request for now,
- * (any reason not to?) but no need to queue the skb since
- * there is no data. How about SYN+FIN?
- */
- end_seq = TCP_SKB_CB(skb)->end_seq;
- if (end_seq != TCP_SKB_CB(skb)->seq + 1) {
- struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
-
- if (likely(skb2)) {
- skb_dst_drop(skb2);
- __skb_pull(skb2, tcp_hdrlen(skb));
- skb_set_owner_r(skb2, child);
- __skb_queue_tail(&child->sk_receive_queue, skb2);
- tp->syn_data_acked = 1;
-
- /* u64_stats_update_begin(&tp->syncp) not needed here,
- * as we certainly are not changing upper 32bit value (0)
- */
- tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1;
- } else {
- end_seq = TCP_SKB_CB(skb)->seq + 1;
- }
- }
- tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq;
+ tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+
+ tcp_fastopen_add_skb(child, skb);
+
+ tcp_rsk(req)->rcv_nxt = tp->rcv_nxt;
/* tcp_conn_request() is sending the SYNACK,
* and queues the child into listener accept queue.
*/
int sysctl_tcp_window_scaling __read_mostly = 1;
int sysctl_tcp_sack __read_mostly = 1;
int sysctl_tcp_fack __read_mostly = 1;
-int sysctl_tcp_reordering __read_mostly = TCP_FASTRETRANS_THRESH;
int sysctl_tcp_max_reordering __read_mostly = 300;
-EXPORT_SYMBOL(sysctl_tcp_reordering);
int sysctl_tcp_dsack __read_mostly = 1;
int sysctl_tcp_app_win __read_mostly = 31;
int sysctl_tcp_adv_win_scale __read_mostly = 1;
#define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH)
#define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH))
+#define REXMIT_NONE 0 /* no loss recovery to do */
+#define REXMIT_LOST 1 /* retransmit packets marked lost */
+#define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */
+
/* Adapt the MSS value used to make delayed ack decision to the
* real world.
*/
sacked |= TCPCB_SACKED_ACKED;
state->flag |= FLAG_DATA_SACKED;
tp->sacked_out += pcount;
+ tp->delivered += pcount; /* Out-of-order packets delivered */
fack_count += pcount;
static void tcp_add_reno_sack(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ u32 prior_sacked = tp->sacked_out;
+
tp->sacked_out++;
tcp_check_reno_reordering(sk, 0);
+ if (tp->sacked_out > prior_sacked)
+ tp->delivered++; /* Some out-of-order packet is delivered */
tcp_verify_left_out(tp);
}
if (acked > 0) {
/* One ACK acked hole. The rest eat duplicate ACKs. */
+ tp->delivered += max_t(int, acked - tp->sacked_out, 1);
if (acked - 1 >= tp->sacked_out)
tp->sacked_out = 0;
else
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
struct sk_buff *skb;
bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
bool is_reneg; /* is receiver reneging on SACKs? */
* suggests that the degree of reordering is over-estimated.
*/
if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
- tp->sacked_out >= sysctl_tcp_reordering)
+ tp->sacked_out >= net->ipv4.sysctl_tcp_reordering)
tp->reordering = min_t(unsigned int, tp->reordering,
- sysctl_tcp_reordering);
+ net->ipv4.sysctl_tcp_reordering);
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
tcp_ecn_queue_cwr(tp);
{
struct tcp_sock *tp = tcp_sk(sk);
__u32 packets_out;
+ int tcp_reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
/* Trick#1: The loss is proven. */
if (tp->lost_out)
*/
packets_out = tp->packets_out;
if (packets_out <= tp->reordering &&
- tp->sacked_out >= max_t(__u32, packets_out/2, sysctl_tcp_reordering) &&
+ tp->sacked_out >= max_t(__u32, packets_out/2, tcp_reordering) &&
!tcp_may_send_now(sk)) {
/* We have nothing to send. This connection is limited
* either by receiver window or by application.
tcp_ecn_queue_cwr(tp);
}
-static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked,
- int fast_rexmit, int flag)
+static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked,
+ int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
int sndcnt = 0;
int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp);
- int newly_acked_sacked = prior_unsacked -
- (tp->packets_out - tp->sacked_out);
if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd))
return;
} else {
sndcnt = min(delta, newly_acked_sacked);
}
- sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0));
+ /* Force a fast retransmit upon entering fast recovery */
+ sndcnt = max(sndcnt, (tp->prr_out ? 0 : 1));
tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt;
}
}
}
-static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked)
+static void tcp_try_to_open(struct sock *sk, int flag)
{
struct tcp_sock *tp = tcp_sk(sk);
if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
tcp_try_keep_open(sk);
- } else {
- tcp_cwnd_reduction(sk, prior_unsacked, 0, flag);
}
}
/* Process an ACK in CA_Loss state. Move to CA_Open if lost data are
* recovered or spurious. Otherwise retransmits more on partial ACKs.
*/
-static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
+static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack,
+ int *rexmit)
{
struct tcp_sock *tp = tcp_sk(sk);
bool recovered = !before(tp->snd_una, tp->high_seq);
tp->frto = 0; /* Step 3.a. loss was real */
} else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) {
tp->high_seq = tp->snd_nxt;
- __tcp_push_pending_frames(sk, tcp_current_mss(sk),
- TCP_NAGLE_OFF);
- if (after(tp->snd_nxt, tp->high_seq))
- return; /* Step 2.b */
+ /* Step 2.b. Try send new data (but deferred until cwnd
+ * is updated in tcp_ack()). Otherwise fall back to
+ * the conventional recovery.
+ */
+ if (tcp_send_head(sk) &&
+ after(tcp_wnd_end(tp), tp->snd_nxt)) {
+ *rexmit = REXMIT_NEW;
+ return;
+ }
tp->frto = 0;
}
}
else if (flag & FLAG_SND_UNA_ADVANCED)
tcp_reset_reno_sack(tp);
}
- tcp_xmit_retransmit_queue(sk);
+ *rexmit = REXMIT_LOST;
}
/* Undo during fast recovery after partial ACK. */
-static bool tcp_try_undo_partial(struct sock *sk, const int acked,
- const int prior_unsacked, int flag)
+static bool tcp_try_undo_partial(struct sock *sk, const int acked)
{
struct tcp_sock *tp = tcp_sk(sk);
* can undo. Otherwise we clock out new packets but do not
* mark more packets lost or retransmit more.
*/
- if (tp->retrans_out) {
- tcp_cwnd_reduction(sk, prior_unsacked, 0, flag);
+ if (tp->retrans_out)
return true;
- }
if (!tcp_any_retrans_done(sk))
tp->retrans_stamp = 0;
* taking into account both packets sitting in receiver's buffer and
* packets lost by network.
*
- * Besides that it does CWND reduction, when packet loss is detected
- * and changes state of machine.
+ * Besides that it updates the congestion state when packet loss or ECN
+ * is detected. But it does not reduce the cwnd, it is done by the
+ * congestion control later.
*
* It does _not_ decide what to send, it is made in function
* tcp_xmit_retransmit_queue().
*/
static void tcp_fastretrans_alert(struct sock *sk, const int acked,
- const int prior_unsacked,
- bool is_dupack, int flag)
+ bool is_dupack, int *ack_flag, int *rexmit)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ int fast_rexmit = 0, flag = *ack_flag;
bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
(tcp_fackets_out(tp) > tp->reordering));
- int fast_rexmit = 0;
if (WARN_ON(!tp->packets_out && tp->sacked_out))
tp->sacked_out = 0;
/* Use RACK to detect loss */
if (sysctl_tcp_recovery & TCP_RACK_LOST_RETRANS &&
- tcp_rack_mark_lost(sk))
+ tcp_rack_mark_lost(sk)) {
flag |= FLAG_LOST_RETRANS;
+ *ack_flag |= FLAG_LOST_RETRANS;
+ }
/* E. Process state. */
switch (icsk->icsk_ca_state) {
if (tcp_is_reno(tp) && is_dupack)
tcp_add_reno_sack(sk);
} else {
- if (tcp_try_undo_partial(sk, acked, prior_unsacked, flag))
+ if (tcp_try_undo_partial(sk, acked))
return;
/* Partial ACK arrived. Force fast retransmit. */
do_lost = tcp_is_reno(tp) ||
}
break;
case TCP_CA_Loss:
- tcp_process_loss(sk, flag, is_dupack);
+ tcp_process_loss(sk, flag, is_dupack, rexmit);
if (icsk->icsk_ca_state != TCP_CA_Open &&
!(flag & FLAG_LOST_RETRANS))
return;
tcp_try_undo_dsack(sk);
if (!tcp_time_to_recover(sk, flag)) {
- tcp_try_to_open(sk, flag, prior_unsacked);
+ tcp_try_to_open(sk, flag);
return;
}
if (do_lost)
tcp_update_scoreboard(sk, fast_rexmit);
- tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit, flag);
- tcp_xmit_retransmit_queue(sk);
+ *rexmit = REXMIT_LOST;
}
/* Kathleen Nichols' algorithm for tracking the minimum value of
* arrived at the other end.
*/
static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
- u32 prior_snd_una,
+ u32 prior_snd_una, int *acked,
struct tcp_sacktag_state *sack)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
flag |= FLAG_ORIG_SACK_ACKED;
}
- if (sacked & TCPCB_SACKED_ACKED)
+ if (sacked & TCPCB_SACKED_ACKED) {
tp->sacked_out -= acked_pcount;
- else if (tcp_is_sack(tp) && !tcp_skb_spurious_retrans(tp, skb))
- tcp_rack_advance(tp, &skb->skb_mstamp, sacked);
+ } else if (tcp_is_sack(tp)) {
+ tp->delivered += acked_pcount;
+ if (!tcp_skb_spurious_retrans(tp, skb))
+ tcp_rack_advance(tp, &skb->skb_mstamp, sacked);
+ }
if (sacked & TCPCB_LOST)
tp->lost_out -= acked_pcount;
}
}
#endif
+ *acked = pkts_acked;
return flag;
}
/* Decide wheather to run the increase function of congestion control. */
static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
{
- if (tcp_in_cwnd_reduction(sk))
- return false;
-
/* If reordering is high then always grow cwnd whenever data is
* delivered regardless of its ordering. Otherwise stay conservative
* and only grow cwnd on in-order delivery (RFC5681). A stretched ACK w/
* new SACK or ECE mark may first advance cwnd here and later reduce
* cwnd in tcp_fastretrans_alert() based on more states.
*/
- if (tcp_sk(sk)->reordering > sysctl_tcp_reordering)
+ if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering)
return flag & FLAG_FORWARD_PROGRESS;
return flag & FLAG_DATA_ACKED;
}
+/* The "ultimate" congestion control function that aims to replace the rigid
+ * cwnd increase and decrease control (tcp_cong_avoid,tcp_*cwnd_reduction).
+ * It's called toward the end of processing an ACK with precise rate
+ * information. All transmission or retransmission are delayed afterwards.
+ */
+static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked,
+ int flag)
+{
+ if (tcp_in_cwnd_reduction(sk)) {
+ /* Reduce cwnd if state mandates */
+ tcp_cwnd_reduction(sk, acked_sacked, flag);
+ } else if (tcp_may_raise_cwnd(sk, flag)) {
+ /* Advance cwnd if state allows */
+ tcp_cong_avoid(sk, ack, acked_sacked);
+ }
+ tcp_update_pacing_rate(sk);
+}
+
/* Check that window update is acceptable.
* The function assumes that snd_una<=ack<=snd_next.
*/
icsk->icsk_ca_ops->in_ack_event(sk, flags);
}
+/* Congestion control has updated the cwnd already. So if we're in
+ * loss recovery then now we do any new sends (for FRTO) or
+ * retransmits (for CA_Loss or CA_recovery) that make sense.
+ */
+static void tcp_xmit_recovery(struct sock *sk, int rexmit)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (rexmit == REXMIT_NONE)
+ return;
+
+ if (unlikely(rexmit == 2)) {
+ __tcp_push_pending_frames(sk, tcp_current_mss(sk),
+ TCP_NAGLE_OFF);
+ if (after(tp->snd_nxt, tp->high_seq))
+ return;
+ tp->frto = 0;
+ }
+ tcp_xmit_retransmit_queue(sk);
+}
+
/* This routine deals with incoming acks, but not outgoing ones. */
static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
{
bool is_dupack = false;
u32 prior_fackets;
int prior_packets = tp->packets_out;
- const int prior_unsacked = tp->packets_out - tp->sacked_out;
+ u32 prior_delivered = tp->delivered;
int acked = 0; /* Number of packets newly acked */
+ int rexmit = REXMIT_NONE; /* Flag to (re)transmit to recover losses */
sack_state.first_sackt.v64 = 0;
goto no_queue;
/* See if we can take anything off of the retransmit queue. */
- acked = tp->packets_out;
- flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una,
+ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked,
&sack_state);
- acked -= tp->packets_out;
if (tcp_ack_is_dubious(sk, flag)) {
is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
- tcp_fastretrans_alert(sk, acked, prior_unsacked,
- is_dupack, flag);
+ tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
}
if (tp->tlp_high_seq)
tcp_process_tlp_ack(sk, ack, flag);
- /* Advance cwnd if state allows */
- if (tcp_may_raise_cwnd(sk, flag))
- tcp_cong_avoid(sk, ack, acked);
-
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) {
struct dst_entry *dst = __sk_dst_get(sk);
if (dst)
if (icsk->icsk_pending == ICSK_TIME_RETRANS)
tcp_schedule_loss_probe(sk);
- tcp_update_pacing_rate(sk);
+ tcp_cong_control(sk, ack, tp->delivered - prior_delivered, flag);
+ tcp_xmit_recovery(sk, rexmit);
return 1;
no_queue:
/* If data was DSACKed, see if we can undo a cwnd reduction. */
if (flag & FLAG_DSACKING_ACK)
- tcp_fastretrans_alert(sk, acked, prior_unsacked,
- is_dupack, flag);
+ tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
* it needs to be for normal retransmission.
if (TCP_SKB_CB(skb)->sacked) {
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
&sack_state);
- tcp_fastretrans_alert(sk, acked, prior_unsacked,
- is_dupack, flag);
+ tcp_fastretrans_alert(sk, acked, is_dupack, &flag, &rexmit);
+ tcp_xmit_recovery(sk, rexmit);
}
SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
*
* If we are in FINWAIT-2, a received FIN moves us to TIME-WAIT.
*/
-static void tcp_fin(struct sock *sk)
+void tcp_fin(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
tp->syn_data_acked = tp->syn_data;
if (tp->syn_data_acked)
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
+
+ tcp_fastopen_add_skb(sk, synack);
+
return false;
}
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
const char *msg = "Dropping request";
bool want_cookie = false;
+ struct net *net = sock_net(sk);
#ifdef CONFIG_SYN_COOKIES
- if (sysctl_tcp_syncookies) {
+ if (net->ipv4.sysctl_tcp_syncookies) {
msg = "Sending cookies";
want_cookie = true;
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
if (!queue->synflood_warned &&
- sysctl_tcp_syncookies != 2 &&
+ net->ipv4.sysctl_tcp_syncookies != 2 &&
xchg(&queue->synflood_warned, 1) == 0)
pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n",
proto, ntohs(tcp_hdr(skb)->dest), msg);
__u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn;
struct tcp_options_received tmp_opt;
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
struct sock *fastopen_sk = NULL;
struct dst_entry *dst = NULL;
struct request_sock *req;
* limitations, they conserve resources and peer is
* evidently real one.
*/
- if ((sysctl_tcp_syncookies == 2 ||
+ if ((net->ipv4.sysctl_tcp_syncookies == 2 ||
inet_csk_reqsk_queue_is_full(sk)) && !isn) {
want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name);
if (!want_cookie)
}
}
/* Kill the following clause, if you dislike this way. */
- else if (!sysctl_tcp_syncookies &&
+ else if (!net->ipv4.sysctl_tcp_syncookies &&
(sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
(sysctl_max_syn_backlog >> 2)) &&
!tcp_peer_is_proven(req, dst, false,
kfree(inet_rsk(req)->opt);
}
-
#ifdef CONFIG_TCP_MD5SIG
/*
* RFC2385 MD5 checksumming requires a mapping of
net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES;
net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL;
+ net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES;
+ net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES;
+ net->ipv4.sysctl_tcp_syncookies = 1;
+ net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH;
+ net->ipv4.sysctl_tcp_retries1 = TCP_RETR1;
+ net->ipv4.sysctl_tcp_retries2 = TCP_RETR2;
+ net->ipv4.sysctl_tcp_orphan_retries = 0;
+ net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT;
+ net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX;
+
return 0;
fail:
tcp_sk_exit(net);
const struct inet_connection_sock *icsk = inet_csk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
struct tcp_metrics_block *tm;
unsigned long rtt;
u32 val;
if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) {
val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
if (val < tp->reordering &&
- tp->reordering != sysctl_tcp_reordering)
+ tp->reordering != net->ipv4.sysctl_tcp_reordering)
tcp_metric_set(tm, TCP_METRIC_REORDERING,
tp->reordering);
}
#include <net/inet_common.h>
#include <net/xfrm.h>
-int sysctl_tcp_syncookies __read_mostly = 1;
-EXPORT_SYMBOL(sysctl_tcp_syncookies);
-
int sysctl_tcp_abort_on_overflow __read_mostly;
struct inet_timewait_death_row tcp_death_row = {
/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
-unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX;
-EXPORT_SYMBOL(sysctl_tcp_notsent_lowat);
-
static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
int push_one, gfp_t gfp);
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
unsigned long probe_max;
int err;
}
if (err <= 0) {
- if (icsk->icsk_backoff < sysctl_tcp_retries2)
+ if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2)
icsk->icsk_backoff++;
icsk->icsk_probes_out++;
probe_max = TCP_RTO_MAX;
#include <linux/gfp.h>
#include <net/tcp.h>
-int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES;
-int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES;
-int sysctl_tcp_retries1 __read_mostly = TCP_RETR1;
-int sysctl_tcp_retries2 __read_mostly = TCP_RETR2;
-int sysctl_tcp_orphan_retries __read_mostly;
int sysctl_tcp_thin_linear_timeouts __read_mostly;
static void tcp_write_err(struct sock *sk)
/* Calculate maximal number or retries on an orphaned socket. */
static int tcp_orphan_retries(struct sock *sk, bool alive)
{
- int retries = sysctl_tcp_orphan_retries; /* May be zero. */
+ int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */
/* We know from an ICMP that something is wrong. */
if (sk->sk_err_soft && !alive)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
int retry_until;
bool do_reset, syn_set = false;
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENACTIVEFAIL);
}
- retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
+ retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
syn_set = true;
} else {
- if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
+ if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0, 0)) {
/* Some middle-boxes may black-hole Fast Open _after_
* the handshake. Therefore we conservatively disable
* Fast Open on this path on recurring timeouts with
if (tp->syn_data_acked &&
tp->bytes_acked <= tp->rx_opt.mss_clamp) {
tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
- if (icsk->icsk_retransmits == sysctl_tcp_retries1)
+ if (icsk->icsk_retransmits == net->ipv4.sysctl_tcp_retries1)
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENACTIVEFAIL);
}
dst_negative_advice(sk);
}
- retry_until = sysctl_tcp_retries2;
+ retry_until = net->ipv4.sysctl_tcp_retries2;
if (sock_flag(sk, SOCK_DEAD)) {
const bool alive = icsk->icsk_rto < TCP_RTO_MAX;
(s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout)
goto abort;
- max_probes = sysctl_tcp_retries2;
+ max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
if (sock_flag(sk, SOCK_DEAD)) {
const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
{
struct inet_connection_sock *icsk = inet_csk(sk);
int max_retries = icsk->icsk_syn_retries ? :
- sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
+ sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
struct request_sock *req;
req = tcp_sk(sk)->fastopen_rsk;
void tcp_retransmit_timer(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
+ struct net *net = sock_net(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
if (tp->fastopen_rsk) {
icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
}
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
- if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0, 0))
+ if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0, 0))
__sk_dst_reset(sk);
out:;
struct dst_entry *dst;
__u8 rcv_wscale;
- if (!sysctl_tcp_syncookies || !th->ack || th->rst)
+ if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
goto out;
if (tcp_synq_no_recent_overflow(sk))
return res;
}
+static int __packet_rcv_vnet(const struct sk_buff *skb,
+ struct virtio_net_hdr *vnet_hdr)
+{
+ *vnet_hdr = (const struct virtio_net_hdr) { 0 };
+
+ if (skb_is_gso(skb)) {
+ struct skb_shared_info *sinfo = skb_shinfo(skb);
+
+ /* This is a hint as to how much should be linear. */
+ vnet_hdr->hdr_len =
+ __cpu_to_virtio16(vio_le(), skb_headlen(skb));
+ vnet_hdr->gso_size =
+ __cpu_to_virtio16(vio_le(), sinfo->gso_size);
+
+ if (sinfo->gso_type & SKB_GSO_TCPV4)
+ vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
+ else if (sinfo->gso_type & SKB_GSO_TCPV6)
+ vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+ else if (sinfo->gso_type & SKB_GSO_UDP)
+ vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
+ else if (sinfo->gso_type & SKB_GSO_FCOE)
+ return -EINVAL;
+ else
+ BUG();
+
+ if (sinfo->gso_type & SKB_GSO_TCP_ECN)
+ vnet_hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN;
+ } else
+ vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE;
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ vnet_hdr->flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+ vnet_hdr->csum_start = __cpu_to_virtio16(vio_le(),
+ skb_checksum_start_offset(skb));
+ vnet_hdr->csum_offset = __cpu_to_virtio16(vio_le(),
+ skb->csum_offset);
+ } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+ vnet_hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
+ } /* else everything is zero */
+
+ return 0;
+}
+
+static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb,
+ size_t *len)
+{
+ struct virtio_net_hdr vnet_hdr;
+
+ if (*len < sizeof(vnet_hdr))
+ return -EINVAL;
+ *len -= sizeof(vnet_hdr);
+
+ if (__packet_rcv_vnet(skb, &vnet_hdr))
+ return -EINVAL;
+
+ return memcpy_to_msg(msg, (void *)&vnet_hdr, sizeof(vnet_hdr));
+}
+
/*
* This function makes lazy skb cloning in hope that most of packets
* are discarded by BPF.
unsigned int maclen = skb_network_offset(skb);
netoff = TPACKET_ALIGN(po->tp_hdrlen +
(maclen < 16 ? 16 : maclen)) +
- po->tp_reserve;
+ po->tp_reserve;
+ if (po->has_vnet_hdr)
+ netoff += sizeof(struct virtio_net_hdr);
macoff = netoff - maclen;
}
if (po->tp_version <= TPACKET_V2) {
h.raw = packet_current_rx_frame(po, skb,
TP_STATUS_KERNEL, (macoff+snaplen));
if (!h.raw)
- goto ring_is_full;
+ goto drop_n_account;
if (po->tp_version <= TPACKET_V2) {
packet_increment_rx_head(po, &po->rx_ring);
/*
}
spin_unlock(&sk->sk_receive_queue.lock);
+ if (po->has_vnet_hdr) {
+ if (__packet_rcv_vnet(skb, h.raw + macoff -
+ sizeof(struct virtio_net_hdr))) {
+ spin_lock(&sk->sk_receive_queue.lock);
+ goto drop_n_account;
+ }
+ }
+
skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
if (!(ts_status = tpacket_get_timestamp(skb, &ts, po->tp_tstamp)))
kfree_skb(skb);
return 0;
-ring_is_full:
+drop_n_account:
po->stats.stats1.tp_drops++;
spin_unlock(&sk->sk_receive_queue.lock);
}
}
+static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t len)
+{
+ unsigned short gso_type = 0;
+
+ if ((vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
+ (__virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) +
+ __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2 >
+ __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len)))
+ vnet_hdr->hdr_len = __cpu_to_virtio16(vio_le(),
+ __virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) +
+ __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2);
+
+ if (__virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len) > len)
+ return -EINVAL;
+
+ if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+ switch (vnet_hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+ case VIRTIO_NET_HDR_GSO_TCPV4:
+ gso_type = SKB_GSO_TCPV4;
+ break;
+ case VIRTIO_NET_HDR_GSO_TCPV6:
+ gso_type = SKB_GSO_TCPV6;
+ break;
+ case VIRTIO_NET_HDR_GSO_UDP:
+ gso_type = SKB_GSO_UDP;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (vnet_hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
+ gso_type |= SKB_GSO_TCP_ECN;
+
+ if (vnet_hdr->gso_size == 0)
+ return -EINVAL;
+ }
+
+ vnet_hdr->gso_type = gso_type; /* changes type, temporary storage */
+ return 0;
+}
+
+static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len,
+ struct virtio_net_hdr *vnet_hdr)
+{
+ int n;
+
+ if (*len < sizeof(*vnet_hdr))
+ return -EINVAL;
+ *len -= sizeof(*vnet_hdr);
+
+ n = copy_from_iter(vnet_hdr, sizeof(*vnet_hdr), &msg->msg_iter);
+ if (n != sizeof(*vnet_hdr))
+ return -EFAULT;
+
+ return __packet_snd_vnet_parse(vnet_hdr, *len);
+}
+
+static int packet_snd_vnet_gso(struct sk_buff *skb,
+ struct virtio_net_hdr *vnet_hdr)
+{
+ if (vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+ u16 s = __virtio16_to_cpu(vio_le(), vnet_hdr->csum_start);
+ u16 o = __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset);
+
+ if (!skb_partial_csum_set(skb, s, o))
+ return -EINVAL;
+ }
+
+ skb_shinfo(skb)->gso_size =
+ __virtio16_to_cpu(vio_le(), vnet_hdr->gso_size);
+ skb_shinfo(skb)->gso_type = vnet_hdr->gso_type;
+
+ /* Header must be checked, and gso_segs computed. */
+ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
+ skb_shinfo(skb)->gso_segs = 0;
+ return 0;
+}
+
static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
- void *frame, struct net_device *dev, int size_max,
- __be16 proto, unsigned char *addr, int hlen)
+ void *frame, struct net_device *dev, void *data, int tp_len,
+ __be16 proto, unsigned char *addr, int hlen, int copylen)
{
union tpacket_uhdr ph;
- int to_write, offset, len, tp_len, nr_frags, len_max;
+ int to_write, offset, len, nr_frags, len_max;
struct socket *sock = po->sk.sk_socket;
struct page *page;
- void *data;
int err;
ph.raw = frame;
sock_tx_timestamp(&po->sk, &skb_shinfo(skb)->tx_flags);
skb_shinfo(skb)->destructor_arg = ph.raw;
- switch (po->tp_version) {
- case TPACKET_V2:
- tp_len = ph.h2->tp_len;
- break;
- default:
- tp_len = ph.h1->tp_len;
- break;
- }
- if (unlikely(tp_len > size_max)) {
- pr_err("packet size is too long (%d > %d)\n", tp_len, size_max);
- return -EMSGSIZE;
- }
-
skb_reserve(skb, hlen);
skb_reset_network_header(skb);
- if (unlikely(po->tp_tx_has_off)) {
- int off_min, off_max, off;
- off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
- off_max = po->tx_ring.frame_size - tp_len;
- if (sock->type == SOCK_DGRAM) {
- switch (po->tp_version) {
- case TPACKET_V2:
- off = ph.h2->tp_net;
- break;
- default:
- off = ph.h1->tp_net;
- break;
- }
- } else {
- switch (po->tp_version) {
- case TPACKET_V2:
- off = ph.h2->tp_mac;
- break;
- default:
- off = ph.h1->tp_mac;
- break;
- }
- }
- if (unlikely((off < off_min) || (off_max < off)))
- return -EINVAL;
- data = ph.raw + off;
- } else {
- data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll);
- }
to_write = tp_len;
if (sock->type == SOCK_DGRAM) {
NULL, tp_len);
if (unlikely(err < 0))
return -EINVAL;
- } else if (dev->hard_header_len) {
- if (ll_header_truncated(dev, tp_len))
- return -EINVAL;
-
+ } else if (copylen) {
skb_push(skb, dev->hard_header_len);
- err = skb_store_bits(skb, 0, data,
- dev->hard_header_len);
+ skb_put(skb, copylen - dev->hard_header_len);
+ err = skb_store_bits(skb, 0, data, copylen);
if (unlikely(err))
return err;
if (!skb->protocol)
tpacket_set_protocol(dev, skb);
- data += dev->hard_header_len;
- to_write -= dev->hard_header_len;
+ data += copylen;
+ to_write -= copylen;
}
offset = offset_in_page(data);
return tp_len;
}
+static int tpacket_parse_header(struct packet_sock *po, void *frame,
+ int size_max, void **data)
+{
+ union tpacket_uhdr ph;
+ int tp_len, off;
+
+ ph.raw = frame;
+
+ switch (po->tp_version) {
+ case TPACKET_V2:
+ tp_len = ph.h2->tp_len;
+ break;
+ default:
+ tp_len = ph.h1->tp_len;
+ break;
+ }
+ if (unlikely(tp_len > size_max)) {
+ pr_err("packet size is too long (%d > %d)\n", tp_len, size_max);
+ return -EMSGSIZE;
+ }
+
+ if (unlikely(po->tp_tx_has_off)) {
+ int off_min, off_max;
+
+ off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll);
+ off_max = po->tx_ring.frame_size - tp_len;
+ if (po->sk.sk_type == SOCK_DGRAM) {
+ switch (po->tp_version) {
+ case TPACKET_V2:
+ off = ph.h2->tp_net;
+ break;
+ default:
+ off = ph.h1->tp_net;
+ break;
+ }
+ } else {
+ switch (po->tp_version) {
+ case TPACKET_V2:
+ off = ph.h2->tp_mac;
+ break;
+ default:
+ off = ph.h1->tp_mac;
+ break;
+ }
+ }
+ if (unlikely((off < off_min) || (off_max < off)))
+ return -EINVAL;
+ } else {
+ off = po->tp_hdrlen - sizeof(struct sockaddr_ll);
+ }
+
+ *data = frame + off;
+ return tp_len;
+}
+
static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
{
struct sk_buff *skb;
struct net_device *dev;
+ struct virtio_net_hdr *vnet_hdr = NULL;
__be16 proto;
int err, reserve = 0;
void *ph;
bool need_wait = !(msg->msg_flags & MSG_DONTWAIT);
int tp_len, size_max;
unsigned char *addr;
+ void *data;
int len_sum = 0;
int status = TP_STATUS_AVAILABLE;
- int hlen, tlen;
+ int hlen, tlen, copylen = 0;
mutex_lock(&po->pg_vec_lock);
size_max = po->tx_ring.frame_size
- (po->tp_hdrlen - sizeof(struct sockaddr_ll));
- if (size_max > dev->mtu + reserve + VLAN_HLEN)
+ if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !po->has_vnet_hdr)
size_max = dev->mtu + reserve + VLAN_HLEN;
do {
continue;
}
+ skb = NULL;
+ tp_len = tpacket_parse_header(po, ph, size_max, &data);
+ if (tp_len < 0)
+ goto tpacket_error;
+
status = TP_STATUS_SEND_REQUEST;
hlen = LL_RESERVED_SPACE(dev);
tlen = dev->needed_tailroom;
+ if (po->has_vnet_hdr) {
+ vnet_hdr = data;
+ data += sizeof(*vnet_hdr);
+ tp_len -= sizeof(*vnet_hdr);
+ if (tp_len < 0 ||
+ __packet_snd_vnet_parse(vnet_hdr, tp_len)) {
+ tp_len = -EINVAL;
+ goto tpacket_error;
+ }
+ copylen = __virtio16_to_cpu(vio_le(),
+ vnet_hdr->hdr_len);
+ }
+ if (dev->hard_header_len) {
+ if (ll_header_truncated(dev, tp_len)) {
+ tp_len = -EINVAL;
+ goto tpacket_error;
+ }
+ copylen = max_t(int, copylen, dev->hard_header_len);
+ }
skb = sock_alloc_send_skb(&po->sk,
- hlen + tlen + sizeof(struct sockaddr_ll),
+ hlen + tlen + sizeof(struct sockaddr_ll) +
+ (copylen - dev->hard_header_len),
!need_wait, &err);
if (unlikely(skb == NULL)) {
err = len_sum;
goto out_status;
}
- tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
- addr, hlen);
+ tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto,
+ addr, hlen, copylen);
if (likely(tp_len >= 0) &&
tp_len > dev->mtu + reserve &&
+ !po->has_vnet_hdr &&
!packet_extra_vlan_len_allowed(dev, skb))
tp_len = -EMSGSIZE;
if (unlikely(tp_len < 0)) {
+tpacket_error:
if (po->tp_loss) {
__packet_set_status(po, ph,
TP_STATUS_AVAILABLE);
}
}
+ if (po->has_vnet_hdr && packet_snd_vnet_gso(skb, vnet_hdr)) {
+ tp_len = -EINVAL;
+ goto tpacket_error;
+ }
+
packet_pick_tx_queue(dev, skb);
skb->destructor = tpacket_destruct_skb;
struct sockcm_cookie sockc;
struct virtio_net_hdr vnet_hdr = { 0 };
int offset = 0;
- int vnet_hdr_len;
struct packet_sock *po = pkt_sk(sk);
- unsigned short gso_type = 0;
int hlen, tlen;
int extra_len = 0;
- ssize_t n;
/*
* Get and verify the address.
if (sock->type == SOCK_RAW)
reserve = dev->hard_header_len;
if (po->has_vnet_hdr) {
- vnet_hdr_len = sizeof(vnet_hdr);
-
- err = -EINVAL;
- if (len < vnet_hdr_len)
- goto out_unlock;
-
- len -= vnet_hdr_len;
-
- err = -EFAULT;
- n = copy_from_iter(&vnet_hdr, vnet_hdr_len, &msg->msg_iter);
- if (n != vnet_hdr_len)
- goto out_unlock;
-
- if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
- (__virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) +
- __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2 >
- __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len)))
- vnet_hdr.hdr_len = __cpu_to_virtio16(vio_le(),
- __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start) +
- __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset) + 2);
-
- err = -EINVAL;
- if (__virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len) > len)
+ err = packet_snd_vnet_parse(msg, &len, &vnet_hdr);
+ if (err)
goto out_unlock;
-
- if (vnet_hdr.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
- switch (vnet_hdr.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
- case VIRTIO_NET_HDR_GSO_TCPV4:
- gso_type = SKB_GSO_TCPV4;
- break;
- case VIRTIO_NET_HDR_GSO_TCPV6:
- gso_type = SKB_GSO_TCPV6;
- break;
- case VIRTIO_NET_HDR_GSO_UDP:
- gso_type = SKB_GSO_UDP;
- break;
- default:
- goto out_unlock;
- }
-
- if (vnet_hdr.gso_type & VIRTIO_NET_HDR_GSO_ECN)
- gso_type |= SKB_GSO_TCP_ECN;
-
- if (vnet_hdr.gso_size == 0)
- goto out_unlock;
-
- }
}
if (unlikely(sock_flag(sk, SOCK_NOFCS))) {
}
err = -EMSGSIZE;
- if (!gso_type && (len > dev->mtu + reserve + VLAN_HLEN + extra_len))
+ if (!vnet_hdr.gso_type &&
+ (len > dev->mtu + reserve + VLAN_HLEN + extra_len))
goto out_unlock;
err = -ENOBUFS;
sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
- if (!gso_type && (len > dev->mtu + reserve + extra_len) &&
+ if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) &&
!packet_extra_vlan_len_allowed(dev, skb)) {
err = -EMSGSIZE;
goto out_free;
packet_pick_tx_queue(dev, skb);
if (po->has_vnet_hdr) {
- if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
- u16 s = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_start);
- u16 o = __virtio16_to_cpu(vio_le(), vnet_hdr.csum_offset);
- if (!skb_partial_csum_set(skb, s, o)) {
- err = -EINVAL;
- goto out_free;
- }
- }
-
- skb_shinfo(skb)->gso_size =
- __virtio16_to_cpu(vio_le(), vnet_hdr.gso_size);
- skb_shinfo(skb)->gso_type = gso_type;
-
- /* Header must be checked, and gso_segs computed. */
- skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
- skb_shinfo(skb)->gso_segs = 0;
-
- len += vnet_hdr_len;
+ err = packet_snd_vnet_gso(skb, &vnet_hdr);
+ if (err)
+ goto out_free;
+ len += sizeof(vnet_hdr);
}
skb_probe_transport_header(skb, reserve);
packet_rcv_has_room(pkt_sk(sk), NULL);
if (pkt_sk(sk)->has_vnet_hdr) {
- struct virtio_net_hdr vnet_hdr = { 0 };
-
- err = -EINVAL;
- vnet_hdr_len = sizeof(vnet_hdr);
- if (len < vnet_hdr_len)
- goto out_free;
-
- len -= vnet_hdr_len;
-
- if (skb_is_gso(skb)) {
- struct skb_shared_info *sinfo = skb_shinfo(skb);
-
- /* This is a hint as to how much should be linear. */
- vnet_hdr.hdr_len =
- __cpu_to_virtio16(vio_le(), skb_headlen(skb));
- vnet_hdr.gso_size =
- __cpu_to_virtio16(vio_le(), sinfo->gso_size);
- if (sinfo->gso_type & SKB_GSO_TCPV4)
- vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
- else if (sinfo->gso_type & SKB_GSO_TCPV6)
- vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
- else if (sinfo->gso_type & SKB_GSO_UDP)
- vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP;
- else if (sinfo->gso_type & SKB_GSO_FCOE)
- goto out_free;
- else
- BUG();
- if (sinfo->gso_type & SKB_GSO_TCP_ECN)
- vnet_hdr.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
- } else
- vnet_hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE;
-
- if (skb->ip_summed == CHECKSUM_PARTIAL) {
- vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
- vnet_hdr.csum_start = __cpu_to_virtio16(vio_le(),
- skb_checksum_start_offset(skb));
- vnet_hdr.csum_offset = __cpu_to_virtio16(vio_le(),
- skb->csum_offset);
- } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
- vnet_hdr.flags = VIRTIO_NET_HDR_F_DATA_VALID;
- } /* else everything is zero */
-
- err = memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_len);
- if (err < 0)
+ err = packet_rcv_vnet(msg, skb, &len);
+ if (err)
goto out_free;
+ vnet_hdr_len = sizeof(struct virtio_net_hdr);
}
/* You lose any data beyond the buffer you gave. If it worries
}
if (optlen < len)
return -EINVAL;
- if (pkt_sk(sk)->has_vnet_hdr)
- return -EINVAL;
if (copy_from_user(&req_u.req, optval, len))
return -EFAULT;
return packet_set_ring(sk, &req_u, 0,
struct tipc_link {
u32 addr;
char name[TIPC_MAX_LINK_NAME];
- struct tipc_media_addr *media_addr;
struct net *net;
/* Management and link supervision data */
return rc;
}
-/*
- * Send protocol message to the other endpoint.
- */
-static void tipc_link_proto_xmit(struct tipc_link *l, u32 msg_typ,
- int probe_msg, u32 gap, u32 tolerance,
- u32 priority)
-{
- struct sk_buff *skb = NULL;
- struct sk_buff_head xmitq;
-
- __skb_queue_head_init(&xmitq);
- tipc_link_build_proto_msg(l, msg_typ, probe_msg, gap,
- tolerance, priority, &xmitq);
- skb = __skb_dequeue(&xmitq);
- if (!skb)
- return;
- tipc_bearer_xmit_skb(l->net, l->bearer_id, skb, l->media_addr);
- l->rcv_unacked = 0;
-}
-
static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
u16 rcvgap, int tolerance, int priority,
struct sk_buff_head *xmitq)
if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL))
l->tolerance = peers_tol;
+ if (peers_prio && in_range(peers_prio, TIPC_MIN_LINK_PRI,
+ TIPC_MAX_LINK_PRI)) {
+ l->priority = peers_prio;
+ rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
+ }
+
l->silent_intv_cnt = 0;
l->stats.recv_states++;
if (msg_probe(hdr))
return -EMSGSIZE;
}
-void tipc_link_set_tolerance(struct tipc_link *l, u32 tol)
+void tipc_link_set_tolerance(struct tipc_link *l, u32 tol,
+ struct sk_buff_head *xmitq)
{
l->tolerance = tol;
- tipc_link_proto_xmit(l, STATE_MSG, 0, 0, tol, 0);
+ tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, tol, 0, xmitq);
}
-void tipc_link_set_prio(struct tipc_link *l, u32 prio)
+void tipc_link_set_prio(struct tipc_link *l, u32 prio,
+ struct sk_buff_head *xmitq)
{
l->priority = prio;
- tipc_link_proto_xmit(l, STATE_MSG, 0, 0, 0, prio);
+ tipc_link_build_proto_msg(l, STATE_MSG, 0, 0, 0, prio, xmitq);
}
void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit)
int tipc_link_prio(struct tipc_link *l);
int tipc_link_window(struct tipc_link *l);
unsigned long tipc_link_tolerance(struct tipc_link *l);
-void tipc_link_set_tolerance(struct tipc_link *l, u32 tol);
-void tipc_link_set_prio(struct tipc_link *l, u32 prio);
+void tipc_link_set_tolerance(struct tipc_link *l, u32 tol,
+ struct sk_buff_head *xmitq);
+void tipc_link_set_prio(struct tipc_link *l, u32 prio,
+ struct sk_buff_head *xmitq);
void tipc_link_set_abort_limit(struct tipc_link *l, u32 limit);
void tipc_link_set_queue_limits(struct tipc_link *l, u32 window);
int __tipc_nl_add_link(struct net *net, struct tipc_nl_msg *msg,
struct tipc_subscription *s)
{
struct sub_seq *sseq = nseq->sseqs;
+ struct tipc_name_seq ns;
+
+ tipc_subscrp_convert_seq(&s->evt.s.seq, s->swap, &ns);
list_add(&s->nameseq_list, &nseq->subscriptions);
return;
while (sseq != &nseq->sseqs[nseq->first_free]) {
- if (tipc_subscrp_check_overlap(s, sseq->lower, sseq->upper)) {
+ if (tipc_subscrp_check_overlap(&ns, sseq->lower, sseq->upper)) {
struct publication *crs;
struct name_info *info = sseq->info;
int must_report = 1;
void tipc_nametbl_subscribe(struct tipc_subscription *s)
{
struct tipc_net *tn = net_generic(s->net, tipc_net_id);
- u32 type = s->seq.type;
+ u32 type = tipc_subscrp_convert_seq_type(s->evt.s.seq.type, s->swap);
int index = hash(type);
struct name_seq *seq;
+ struct tipc_name_seq ns;
spin_lock_bh(&tn->nametbl_lock);
seq = nametbl_find_seq(s->net, type);
tipc_nameseq_subscribe(seq, s);
spin_unlock_bh(&seq->lock);
} else {
+ tipc_subscrp_convert_seq(&s->evt.s.seq, s->swap, &ns);
pr_warn("Failed to create subscription for {%u,%u,%u}\n",
- s->seq.type, s->seq.lower, s->seq.upper);
+ ns.type, ns.lower, ns.upper);
}
spin_unlock_bh(&tn->nametbl_lock);
}
{
struct tipc_net *tn = net_generic(s->net, tipc_net_id);
struct name_seq *seq;
+ u32 type = tipc_subscrp_convert_seq_type(s->evt.s.seq.type, s->swap);
spin_lock_bh(&tn->nametbl_lock);
- seq = nametbl_find_seq(s->net, s->seq.type);
+ seq = nametbl_find_seq(s->net, type);
if (seq != NULL) {
spin_lock_bh(&seq->lock);
list_del_init(&s->nameseq_list);
char *name;
struct tipc_link *link;
struct tipc_node *node;
+ struct sk_buff_head xmitq;
struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1];
struct net *net = sock_net(skb->sk);
+ __skb_queue_head_init(&xmitq);
+
if (!info->attrs[TIPC_NLA_LINK])
return -EINVAL;
u32 tol;
tol = nla_get_u32(props[TIPC_NLA_PROP_TOL]);
- tipc_link_set_tolerance(link, tol);
+ tipc_link_set_tolerance(link, tol, &xmitq);
}
if (props[TIPC_NLA_PROP_PRIO]) {
u32 prio;
prio = nla_get_u32(props[TIPC_NLA_PROP_PRIO]);
- tipc_link_set_prio(link, prio);
+ tipc_link_set_prio(link, prio, &xmitq);
}
if (props[TIPC_NLA_PROP_WIN]) {
u32 win;
out:
tipc_node_read_unlock(node);
-
+ tipc_bearer_xmit(net, bearer_id, &xmitq, &node->links[bearer_id].maddr);
return res;
}
static int tipc_work_start(struct tipc_server *s)
{
- s->rcv_wq = alloc_workqueue("tipc_rcv", WQ_UNBOUND, 1);
+ s->rcv_wq = alloc_ordered_workqueue("tipc_rcv", 0);
if (!s->rcv_wq) {
pr_err("can't start tipc receive workqueue\n");
return -ENOMEM;
}
- s->send_wq = alloc_workqueue("tipc_send", WQ_UNBOUND, 1);
+ s->send_wq = alloc_ordered_workqueue("tipc_send", 0);
if (!s->send_wq) {
pr_err("can't start tipc send workqueue\n");
destroy_workqueue(s->rcv_wq);
*
* Returns 1 if there is overlap, otherwise 0.
*/
-int tipc_subscrp_check_overlap(struct tipc_subscription *sub, u32 found_lower,
+int tipc_subscrp_check_overlap(struct tipc_name_seq *seq, u32 found_lower,
u32 found_upper)
{
- if (found_lower < sub->seq.lower)
- found_lower = sub->seq.lower;
- if (found_upper > sub->seq.upper)
- found_upper = sub->seq.upper;
+ if (found_lower < seq->lower)
+ found_lower = seq->lower;
+ if (found_upper > seq->upper)
+ found_upper = seq->upper;
if (found_lower > found_upper)
return 0;
return 1;
}
+u32 tipc_subscrp_convert_seq_type(u32 type, int swap)
+{
+ return htohl(type, swap);
+}
+
+void tipc_subscrp_convert_seq(struct tipc_name_seq *in, int swap,
+ struct tipc_name_seq *out)
+{
+ out->type = htohl(in->type, swap);
+ out->lower = htohl(in->lower, swap);
+ out->upper = htohl(in->upper, swap);
+}
+
void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,
u32 found_upper, u32 event, u32 port_ref,
u32 node, int must)
{
- if (!tipc_subscrp_check_overlap(sub, found_lower, found_upper))
+ struct tipc_name_seq seq;
+
+ tipc_subscrp_convert_seq(&sub->evt.s.seq, sub->swap, &seq);
+ if (!tipc_subscrp_check_overlap(&seq, found_lower, found_upper))
return;
- if (!must && !(sub->filter & TIPC_SUB_PORTS))
+ if (!must &&
+ !(htohl(sub->evt.s.filter, sub->swap) & TIPC_SUB_PORTS))
return;
tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref,
static void tipc_subscrb_delete(struct tipc_subscriber *subscriber)
{
struct tipc_subscription *sub, *temp;
+ u32 timeout;
spin_lock_bh(&subscriber->lock);
/* Destroy any existing subscriptions for subscriber */
list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list,
subscrp_list) {
- if (del_timer(&sub->timer)) {
+ timeout = htohl(sub->evt.s.timeout, sub->swap);
+ if ((timeout == TIPC_WAIT_FOREVER) || del_timer(&sub->timer)) {
tipc_subscrp_delete(sub);
tipc_subscrb_put(subscriber);
}
struct tipc_subscriber *subscriber)
{
struct tipc_subscription *sub, *temp;
+ u32 timeout;
spin_lock_bh(&subscriber->lock);
/* Find first matching subscription, exit if not found */
list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list,
subscrp_list) {
if (!memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) {
- if (del_timer(&sub->timer)) {
+ timeout = htohl(sub->evt.s.timeout, sub->swap);
+ if ((timeout == TIPC_WAIT_FOREVER) ||
+ del_timer(&sub->timer)) {
tipc_subscrp_delete(sub);
tipc_subscrb_put(subscriber);
}
spin_unlock_bh(&subscriber->lock);
}
-static int tipc_subscrp_create(struct net *net, struct tipc_subscr *s,
- struct tipc_subscriber *subscriber,
- struct tipc_subscription **sub_p)
+static struct tipc_subscription *tipc_subscrp_create(struct net *net,
+ struct tipc_subscr *s,
+ int swap)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
struct tipc_subscription *sub;
- int swap;
-
- /* Determine subscriber's endianness */
- swap = !(s->filter & (TIPC_SUB_PORTS | TIPC_SUB_SERVICE));
-
- /* Detect & process a subscription cancellation request */
- if (s->filter & htohl(TIPC_SUB_CANCEL, swap)) {
- s->filter &= ~htohl(TIPC_SUB_CANCEL, swap);
- tipc_subscrp_cancel(s, subscriber);
- return 0;
- }
+ u32 filter = htohl(s->filter, swap);
/* Refuse subscription if global limit exceeded */
if (atomic_read(&tn->subscription_count) >= TIPC_MAX_SUBSCRIPTIONS) {
pr_warn("Subscription rejected, limit reached (%u)\n",
TIPC_MAX_SUBSCRIPTIONS);
- return -EINVAL;
+ return NULL;
}
/* Allocate subscription object */
sub = kmalloc(sizeof(*sub), GFP_ATOMIC);
if (!sub) {
pr_warn("Subscription rejected, no memory\n");
- return -ENOMEM;
+ return NULL;
}
/* Initialize subscription object */
sub->net = net;
- sub->seq.type = htohl(s->seq.type, swap);
- sub->seq.lower = htohl(s->seq.lower, swap);
- sub->seq.upper = htohl(s->seq.upper, swap);
- sub->timeout = msecs_to_jiffies(htohl(s->timeout, swap));
- sub->filter = htohl(s->filter, swap);
- if ((!(sub->filter & TIPC_SUB_PORTS) ==
- !(sub->filter & TIPC_SUB_SERVICE)) ||
- (sub->seq.lower > sub->seq.upper)) {
+ if (((filter & TIPC_SUB_PORTS) && (filter & TIPC_SUB_SERVICE)) ||
+ (htohl(s->seq.lower, swap) > htohl(s->seq.upper, swap))) {
pr_warn("Subscription rejected, illegal request\n");
kfree(sub);
- return -EINVAL;
+ return NULL;
}
- spin_lock_bh(&subscriber->lock);
- list_add(&sub->subscrp_list, &subscriber->subscrp_list);
- spin_unlock_bh(&subscriber->lock);
- sub->subscriber = subscriber;
+
sub->swap = swap;
memcpy(&sub->evt.s, s, sizeof(*s));
atomic_inc(&tn->subscription_count);
+ return sub;
+}
+
+static void tipc_subscrp_subscribe(struct net *net, struct tipc_subscr *s,
+ struct tipc_subscriber *subscriber, int swap)
+{
+ struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct tipc_subscription *sub = NULL;
+ u32 timeout;
+
+ sub = tipc_subscrp_create(net, s, swap);
+ if (!sub)
+ return tipc_conn_terminate(tn->topsrv, subscriber->conid);
+
+ spin_lock_bh(&subscriber->lock);
+ list_add(&sub->subscrp_list, &subscriber->subscrp_list);
+ tipc_subscrb_get(subscriber);
+ sub->subscriber = subscriber;
+ tipc_nametbl_subscribe(sub);
+ spin_unlock_bh(&subscriber->lock);
+
+ timeout = htohl(sub->evt.s.timeout, swap);
+ if (timeout == TIPC_WAIT_FOREVER)
+ return;
+
setup_timer(&sub->timer, tipc_subscrp_timeout, (unsigned long)sub);
- if (sub->timeout != TIPC_WAIT_FOREVER)
- sub->timeout += jiffies;
- if (!mod_timer(&sub->timer, sub->timeout))
- tipc_subscrb_get(subscriber);
- *sub_p = sub;
- return 0;
+ mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout));
}
/* Handle one termination request for the subscriber */
struct sockaddr_tipc *addr, void *usr_data,
void *buf, size_t len)
{
- struct tipc_subscriber *subscrb = usr_data;
- struct tipc_subscription *sub = NULL;
- struct tipc_net *tn = net_generic(net, tipc_net_id);
+ struct tipc_subscriber *subscriber = usr_data;
+ struct tipc_subscr *s = (struct tipc_subscr *)buf;
+ int swap;
+
+ /* Determine subscriber's endianness */
+ swap = !(s->filter & (TIPC_SUB_PORTS | TIPC_SUB_SERVICE |
+ TIPC_SUB_CANCEL));
- if (tipc_subscrp_create(net, (struct tipc_subscr *)buf, subscrb, &sub))
- return tipc_conn_terminate(tn->topsrv, subscrb->conid);
+ /* Detect & process a subscription cancellation request */
+ if (s->filter & htohl(TIPC_SUB_CANCEL, swap)) {
+ s->filter &= ~htohl(TIPC_SUB_CANCEL, swap);
+ return tipc_subscrp_cancel(s, subscriber);
+ }
- tipc_nametbl_subscribe(sub);
+ tipc_subscrp_subscribe(net, s, subscriber, swap);
}
/* Handle one request to establish a new subscriber */
* @subscriber: pointer to its subscriber
* @seq: name sequence associated with subscription
* @net: point to network namespace
- * @timeout: duration of subscription (in ms)
- * @filter: event filtering to be done for subscription
* @timer: timer governing subscription duration (optional)
* @nameseq_list: adjacent subscriptions in name sequence's subscription list
* @subscrp_list: adjacent subscriptions in subscriber's subscription list
- * @server_ref: object reference of server port associated with subscription
* @swap: indicates if subscriber uses opposite endianness in its messages
* @evt: template for events generated by subscription
*/
struct tipc_subscription {
struct tipc_subscriber *subscriber;
- struct tipc_name_seq seq;
struct net *net;
- unsigned long timeout;
- u32 filter;
struct timer_list timer;
struct list_head nameseq_list;
struct list_head subscrp_list;
struct tipc_event evt;
};
-int tipc_subscrp_check_overlap(struct tipc_subscription *sub, u32 found_lower,
+int tipc_subscrp_check_overlap(struct tipc_name_seq *seq, u32 found_lower,
u32 found_upper);
void tipc_subscrp_report_overlap(struct tipc_subscription *sub,
u32 found_lower, u32 found_upper, u32 event,
u32 port_ref, u32 node, int must);
+void tipc_subscrp_convert_seq(struct tipc_name_seq *in, int swap,
+ struct tipc_name_seq *out);
+u32 tipc_subscrp_convert_seq_type(u32 type, int swap);
int tipc_topsrv_start(struct net *net);
void tipc_topsrv_stop(struct net *net);
{
int i;
unsigned char max_level = 0;
- int unix_sock_count = 0;
if (too_many_unix_fds(current))
return -ETOOMANYREFS;
for (i = scm->fp->count - 1; i >= 0; i--) {
struct sock *sk = unix_get_socket(scm->fp->fp[i]);
- if (sk) {
- unix_sock_count++;
+ if (sk)
max_level = max(max_level,
unix_sk(sk)->recursion_level);
- }
}
if (unlikely(max_level > MAX_RECURSION_LEVEL))
return -ETOOMANYREFS;
close(map_fd);
}
+/* sanity tests for percpu map API */
+static void test_percpu_hashmap_sanity(int task, void *data)
+{
+ long long key, next_key;
+ int expected_key_mask = 0;
+ unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+ long long value[nr_cpus];
+ int map_fd, i;
+
+ map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_HASH, sizeof(key),
+ sizeof(value[0]), 2);
+ if (map_fd < 0) {
+ printf("failed to create hashmap '%s'\n", strerror(errno));
+ exit(1);
+ }
+
+ for (i = 0; i < nr_cpus; i++)
+ value[i] = i + 100;
+ key = 1;
+ /* insert key=1 element */
+ assert(!(expected_key_mask & key));
+ assert(bpf_update_elem(map_fd, &key, value, BPF_ANY) == 0);
+ expected_key_mask |= key;
+
+ /* BPF_NOEXIST means: add new element if it doesn't exist */
+ assert(bpf_update_elem(map_fd, &key, value, BPF_NOEXIST) == -1 &&
+ /* key=1 already exists */
+ errno == EEXIST);
+
+ /* -1 is an invalid flag */
+ assert(bpf_update_elem(map_fd, &key, value, -1) == -1 &&
+ errno == EINVAL);
+
+ /* check that key=1 can be found. value could be 0 if the lookup
+ * was run from a different cpu.
+ */
+ value[0] = 1;
+ assert(bpf_lookup_elem(map_fd, &key, value) == 0 && value[0] == 100);
+
+ key = 2;
+ /* check that key=2 is not found */
+ assert(bpf_lookup_elem(map_fd, &key, value) == -1 && errno == ENOENT);
+
+ /* BPF_EXIST means: update existing element */
+ assert(bpf_update_elem(map_fd, &key, value, BPF_EXIST) == -1 &&
+ /* key=2 is not there */
+ errno == ENOENT);
+
+ /* insert key=2 element */
+ assert(!(expected_key_mask & key));
+ assert(bpf_update_elem(map_fd, &key, value, BPF_NOEXIST) == 0);
+ expected_key_mask |= key;
+
+ /* key=1 and key=2 were inserted, check that key=0 cannot be inserted
+ * due to max_entries limit
+ */
+ key = 0;
+ assert(bpf_update_elem(map_fd, &key, value, BPF_NOEXIST) == -1 &&
+ errno == E2BIG);
+
+ /* check that key = 0 doesn't exist */
+ assert(bpf_delete_elem(map_fd, &key) == -1 && errno == ENOENT);
+
+ /* iterate over two elements */
+ while (!bpf_get_next_key(map_fd, &key, &next_key)) {
+ assert((expected_key_mask & next_key) == next_key);
+ expected_key_mask &= ~next_key;
+
+ assert(bpf_lookup_elem(map_fd, &next_key, value) == 0);
+ for (i = 0; i < nr_cpus; i++)
+ assert(value[i] == i + 100);
+
+ key = next_key;
+ }
+ assert(errno == ENOENT);
+
+ /* Update with BPF_EXIST */
+ key = 1;
+ assert(bpf_update_elem(map_fd, &key, value, BPF_EXIST) == 0);
+
+ /* delete both elements */
+ key = 1;
+ assert(bpf_delete_elem(map_fd, &key) == 0);
+ key = 2;
+ assert(bpf_delete_elem(map_fd, &key) == 0);
+ assert(bpf_delete_elem(map_fd, &key) == -1 && errno == ENOENT);
+
+ key = 0;
+ /* check that map is empty */
+ assert(bpf_get_next_key(map_fd, &key, &next_key) == -1 &&
+ errno == ENOENT);
+ close(map_fd);
+}
+
static void test_arraymap_sanity(int i, void *data)
{
int key, next_key, map_fd;
close(map_fd);
}
+static void test_percpu_arraymap_many_keys(void)
+{
+ unsigned nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+ unsigned nr_keys = 20000;
+ long values[nr_cpus];
+ int key, map_fd, i;
+
+ map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
+ sizeof(values[0]), nr_keys);
+ if (map_fd < 0) {
+ printf("failed to create per-cpu arraymap '%s'\n",
+ strerror(errno));
+ exit(1);
+ }
+
+ for (i = 0; i < nr_cpus; i++)
+ values[i] = i + 10;
+
+ for (key = 0; key < nr_keys; key++)
+ assert(bpf_update_elem(map_fd, &key, values, BPF_ANY) == 0);
+
+ for (key = 0; key < nr_keys; key++) {
+ for (i = 0; i < nr_cpus; i++)
+ values[i] = 0;
+ assert(bpf_lookup_elem(map_fd, &key, values) == 0);
+ for (i = 0; i < nr_cpus; i++)
+ assert(values[i] == i + 10);
+ }
+
+ close(map_fd);
+}
+
+static void test_percpu_arraymap_sanity(int i, void *data)
+{
+ unsigned nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+ long values[nr_cpus];
+ int key, next_key, map_fd;
+
+ map_fd = bpf_create_map(BPF_MAP_TYPE_PERCPU_ARRAY, sizeof(key),
+ sizeof(values[0]), 2);
+ if (map_fd < 0) {
+ printf("failed to create arraymap '%s'\n", strerror(errno));
+ exit(1);
+ }
+
+ for (i = 0; i < nr_cpus; i++)
+ values[i] = i + 100;
+
+ key = 1;
+ /* insert key=1 element */
+ assert(bpf_update_elem(map_fd, &key, values, BPF_ANY) == 0);
+
+ values[0] = 0;
+ assert(bpf_update_elem(map_fd, &key, values, BPF_NOEXIST) == -1 &&
+ errno == EEXIST);
+
+ /* check that key=1 can be found */
+ assert(bpf_lookup_elem(map_fd, &key, values) == 0 && values[0] == 100);
+
+ key = 0;
+ /* check that key=0 is also found and zero initialized */
+ assert(bpf_lookup_elem(map_fd, &key, values) == 0 &&
+ values[0] == 0 && values[nr_cpus - 1] == 0);
+
+
+ /* check that key=2 cannot be inserted due to max_entries limit */
+ key = 2;
+ assert(bpf_update_elem(map_fd, &key, values, BPF_EXIST) == -1 &&
+ errno == E2BIG);
+
+ /* check that key = 2 doesn't exist */
+ assert(bpf_lookup_elem(map_fd, &key, values) == -1 && errno == ENOENT);
+
+ /* iterate over two elements */
+ assert(bpf_get_next_key(map_fd, &key, &next_key) == 0 &&
+ next_key == 0);
+ assert(bpf_get_next_key(map_fd, &next_key, &next_key) == 0 &&
+ next_key == 1);
+ assert(bpf_get_next_key(map_fd, &next_key, &next_key) == -1 &&
+ errno == ENOENT);
+
+ /* delete shouldn't succeed */
+ key = 1;
+ assert(bpf_delete_elem(map_fd, &key) == -1 && errno == EINVAL);
+
+ close(map_fd);
+}
+
#define MAP_SIZE (32 * 1024)
static void test_map_large(void)
{
static void test_map_stress(void)
{
run_parallel(100, test_hashmap_sanity, NULL);
+ run_parallel(100, test_percpu_hashmap_sanity, NULL);
run_parallel(100, test_arraymap_sanity, NULL);
+ run_parallel(100, test_percpu_arraymap_sanity, NULL);
}
#define TASKS 1024
int main(void)
{
test_hashmap_sanity(0, NULL);
+ test_percpu_hashmap_sanity(0, NULL);
test_arraymap_sanity(0, NULL);
+ test_percpu_arraymap_sanity(0, NULL);
+ test_percpu_arraymap_many_keys();
+
test_map_large();
test_map_parallel();
test_map_stress();
};
struct bpf_map_def SEC("maps") my_hist_map = {
- .type = BPF_MAP_TYPE_HASH,
+ .type = BPF_MAP_TYPE_PERCPU_HASH,
.key_size = sizeof(struct hist_key),
.value_size = sizeof(long),
.max_entries = 1024,
static void print_hist_for_pid(int fd, void *task)
{
struct hist_key key = {}, next_key;
+ unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+ long values[nr_cpus];
char starstr[MAX_STARS];
long value;
long data[MAX_INDEX] = {};
key = next_key;
continue;
}
- bpf_lookup_elem(fd, &next_key, &value);
+ bpf_lookup_elem(fd, &next_key, values);
+ value = 0;
+ for (i = 0; i < nr_cpus; i++)
+ value += values[i];
ind = next_key.index;
data[ind] = value;
if (value && ind > max_ind)
/* kprobe is NOT a stable ABI. If kernel internals change this bpf+kprobe
* example will no longer be meaningful
*/
-SEC("kprobe/blk_mq_start_request")
+SEC("kprobe/blk_start_request")
int bpf_prog1(struct pt_regs *ctx)
{
long rq = PT_REGS_PARM1(ctx);
#define SLOTS 100
struct bpf_map_def SEC("maps") lat_map = {
- .type = BPF_MAP_TYPE_ARRAY,
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
.key_size = sizeof(u32),
.value_size = sizeof(u64),
.max_entries = SLOTS,
};
-SEC("kprobe/blk_update_request")
+SEC("kprobe/blk_account_io_completion")
int bpf_prog2(struct pt_regs *ctx)
{
long rq = PT_REGS_PARM1(ctx);
value = bpf_map_lookup_elem(&lat_map, &index);
if (value)
- __sync_fetch_and_add((long *)value, 1);
+ *value += 1;
return 0;
}
static void clear_stats(int fd)
{
+ unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+ __u64 values[nr_cpus];
__u32 key;
- __u64 value = 0;
+ memset(values, 0, sizeof(values));
for (key = 0; key < SLOTS; key++)
- bpf_update_elem(fd, &key, &value, BPF_ANY);
+ bpf_update_elem(fd, &key, values, BPF_ANY);
}
const char *color[] = {
static void print_hist(int fd)
{
- __u32 key;
- __u64 value;
- __u64 cnt[SLOTS];
- __u64 max_cnt = 0;
+ unsigned int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
__u64 total_events = 0;
+ long values[nr_cpus];
+ __u64 max_cnt = 0;
+ __u64 cnt[SLOTS];
+ __u64 value;
+ __u32 key;
+ int i;
for (key = 0; key < SLOTS; key++) {
+ bpf_lookup_elem(fd, &key, values);
value = 0;
- bpf_lookup_elem(fd, &key, &value);
+ for (i = 0; i < nr_cpus; i++)
+ value += values[i];
cnt[key] = value;
total_events += value;
if (value > max_cnt)