An example is given below::
/* Disables missing prototype warnings */
- __diag_push();
- __diag_ignore_all("-Wmissing-prototypes",
- "Global kfuncs as their definitions will be in BTF");
+ __bpf_kfunc_start_defs();
__bpf_kfunc struct task_struct *bpf_find_get_task_by_vpid(pid_t nr)
{
return find_get_task_by_vpid(nr);
}
- __diag_pop();
+ __bpf_kfunc_end_defs();
A wrapper kfunc is often needed when we need to annotate parameters of the
kfunc. Otherwise one may directly make the kfunc visible to the BPF program by
name: roce-bit
-
name: migratable-bit
+ -
+ name: ipsec-crypto-bit
+ -
+ name: ipsec-packet-bit
-
type: enum
name: sb-threshold-type
wmem - INTEGER
Initial size of send buffer used by SMC sockets.
- The default value inherits from net.ipv4.tcp_wmem[1].
The minimum value is 16KiB and there is no hard limit for max value, but
only allowed 512KiB for SMC-R and 1MiB for SMC-D.
- Default: 16K
+ Default: 64KiB
rmem - INTEGER
Initial size of receive buffer (RMB) used by SMC sockets.
- The default value inherits from net.ipv4.tcp_rmem[1].
The minimum value is 16KiB and there is no hard limit for max value, but
only allowed 512KiB for SMC-R and 1MiB for SMC-D.
- Default: 128K
+ Default: 64KiB
struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx;
reg <<= 2; /* reg num to offset */
- mutex_lock(&sw_dev->device->bus->mdio_lock);
+ mutex_lock_nested(&sw_dev->device->bus->mdio_lock, MDIO_MUTEX_NESTED);
lan9303_mdio_real_write(sw_dev->device, reg, val & 0xffff);
lan9303_mdio_real_write(sw_dev->device, reg + 2, (val >> 16) & 0xffff);
mutex_unlock(&sw_dev->device->bus->mdio_lock);
struct lan9303_mdio *sw_dev = (struct lan9303_mdio *)ctx;
reg <<= 2; /* reg num to offset */
- mutex_lock(&sw_dev->device->bus->mdio_lock);
+ mutex_lock_nested(&sw_dev->device->bus->mdio_lock, MDIO_MUTEX_NESTED);
*val = lan9303_mdio_real_read(sw_dev->device, reg);
*val |= (lan9303_mdio_real_read(sw_dev->device, reg + 2) << 16);
mutex_unlock(&sw_dev->device->bus->mdio_lock);
tnapi->tx_cons = sw_idx;
- /* Need to make the tx_cons update visible to tg3_start_xmit()
+ /* Need to make the tx_cons update visible to __tg3_start_xmit()
* before checking for netif_queue_stopped(). Without the
- * memory barrier, there is a small possibility that tg3_start_xmit()
+ * memory barrier, there is a small possibility that __tg3_start_xmit()
* will miss it and cause the queue to be stopped forever.
*/
smp_mb();
return skb_shinfo(skb)->gso_segs < tnapi->tx_pending / 3;
}
-static netdev_tx_t tg3_start_xmit(struct sk_buff *, struct net_device *);
+static netdev_tx_t __tg3_start_xmit(struct sk_buff *, struct net_device *);
/* Use GSO to workaround all TSO packets that meet HW bug conditions
* indicated in tg3_tx_frag_set()
skb_list_walk_safe(segs, seg, next) {
skb_mark_not_on_list(seg);
- tg3_start_xmit(seg, tp->dev);
+ __tg3_start_xmit(seg, tp->dev);
}
tg3_tso_bug_end:
}
/* hard_start_xmit for all devices */
-static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t __tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct tg3 *tp = netdev_priv(dev);
u32 len, entry, base_flags, mss, vlan = 0;
netif_tx_wake_queue(txq);
}
- if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
- /* Packets are ready, update Tx producer idx on card. */
- tw32_tx_mbox(tnapi->prodmbox, entry);
- }
-
return NETDEV_TX_OK;
dma_error:
return NETDEV_TX_OK;
}
+static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct netdev_queue *txq;
+ u16 skb_queue_mapping;
+ netdev_tx_t ret;
+
+ skb_queue_mapping = skb_get_queue_mapping(skb);
+ txq = netdev_get_tx_queue(dev, skb_queue_mapping);
+
+ ret = __tg3_start_xmit(skb, dev);
+
+ /* Notify the hardware that packets are ready by updating the TX ring
+ * tail pointer. We respect netdev_xmit_more() thus avoiding poking
+ * the hardware for every packet. To guarantee forward progress the TX
+ * ring must be drained when it is full as indicated by
+ * netif_xmit_stopped(). This needs to happen even when the current
+ * skb was dropped or rejected with NETDEV_TX_BUSY. Otherwise packets
+ * queued by previous __tg3_start_xmit() calls might get stuck in
+ * the queue forever.
+ */
+ if (!netdev_xmit_more() || netif_xmit_stopped(txq)) {
+ struct tg3_napi *tnapi;
+ struct tg3 *tp;
+
+ tp = netdev_priv(dev);
+ tnapi = &tp->napi[skb_queue_mapping];
+
+ if (tg3_flag(tp, ENABLE_TSS))
+ tnapi++;
+
+ tw32_tx_mbox(tnapi->prodmbox, tnapi->tx_prod);
+ }
+
+ return ret;
+}
+
static void tg3_mac_loopback(struct tg3 *tp, bool enable)
{
if (enable) {
* device behind the EPB cannot support DMA addresses > 40-bit.
* On 64-bit systems with IOMMU, use 40-bit dma_mask.
* On 64-bit systems without IOMMU, use 64-bit dma_mask and
- * do DMA address check in tg3_start_xmit().
+ * do DMA address check in __tg3_start_xmit().
*/
if (tg3_flag(tp, IS_5788))
persist_dma_mask = dma_mask = DMA_BIT_MASK(32);
if (netif_running(dev))
dev_close(dev);
- tg3_power_down(tp);
+ if (system_state == SYSTEM_POWER_OFF)
+ tg3_power_down(tp);
rtnl_unlock();
if (priv->min_num_stack_tx_queues + num_xdp_tx_queues >
priv->num_tx_rings) {
NL_SET_ERR_MSG_FMT_MOD(extack,
- "Reserving %d XDP TXQs does not leave a minimum of %d TXQs for network stack (total %d available)",
+ "Reserving %d XDP TXQs does not leave a minimum of %d for stack (total %d)",
num_xdp_tx_queues,
priv->min_num_stack_tx_queues,
priv->num_tx_rings);
**/
void i40e_devlink_destroy_port(struct i40e_pf *pf)
{
- devlink_port_type_clear(&pf->devlink_port);
devlink_port_unregister(&pf->devlink_port);
}
}
set_bit(__I40E_VSI_RELEASING, vsi->state);
uplink_seid = vsi->uplink_seid;
- if (vsi->type == I40E_VSI_MAIN)
- i40e_devlink_destroy_port(pf);
+
if (vsi->type != I40E_VSI_SRIOV) {
if (vsi->netdev_registered) {
vsi->netdev_registered = false;
i40e_vsi_disable_irq(vsi);
}
+ if (vsi->type == I40E_VSI_MAIN)
+ i40e_devlink_destroy_port(pf);
+
spin_lock_bh(&vsi->mac_filter_hash_lock);
/* clear the sync flag on all filters */
err_rings:
i40e_vsi_free_q_vectors(vsi);
- if (vsi->type == I40E_VSI_MAIN)
- i40e_devlink_destroy_port(pf);
if (vsi->netdev_registered) {
vsi->netdev_registered = false;
unregister_netdev(vsi->netdev);
free_netdev(vsi->netdev);
vsi->netdev = NULL;
}
+ if (vsi->type == I40E_VSI_MAIN)
+ i40e_devlink_destroy_port(pf);
i40e_aq_delete_element(&pf->hw, vsi->seid, NULL);
err_vsi:
i40e_vsi_clear(vsi);
INIT_LIST_HEAD(&ndlist.node);
rcu_read_lock();
for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
- nl = kzalloc(sizeof(*nl), GFP_KERNEL);
+ nl = kzalloc(sizeof(*nl), GFP_ATOMIC);
if (!nl)
break;
*/
static void ice_lag_disable_sriov_bond(struct ice_lag *lag)
{
- struct ice_lag_netdev_list *entry;
struct ice_netdev_priv *np;
- struct net_device *netdev;
struct ice_pf *pf;
- list_for_each_entry(entry, lag->netdev_head, node) {
- netdev = entry->netdev;
- np = netdev_priv(netdev);
- pf = np->vsi->back;
-
- ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
- }
+ np = netdev_priv(lag->netdev);
+ pf = np->vsi->back;
+ ice_clear_feature_support(pf, ICE_F_SRIOV_LAG);
}
/**
rcu_read_lock();
for_each_netdev_in_bond_rcu(upper_netdev, tmp_nd) {
- nd_list = kzalloc(sizeof(*nd_list), GFP_KERNEL);
+ nd_list = kzalloc(sizeof(*nd_list), GFP_ATOMIC);
if (!nd_list)
break;
INIT_LIST_HEAD(&ndlist.node);
rcu_read_lock();
for_each_netdev_in_bond_rcu(lag->upper_netdev, tmp_nd) {
- nl = kzalloc(sizeof(*nl), GFP_KERNEL);
+ nl = kzalloc(sizeof(*nl), GFP_ATOMIC);
if (!nl)
break;
return ice_tc_tun_get_type(dev) != TNL_LAST;
}
-static int
-ice_eswitch_tc_parse_action(struct ice_tc_flower_fltr *fltr,
- struct flow_action_entry *act)
+static bool ice_tc_is_dev_uplink(struct net_device *dev)
+{
+ return netif_is_ice(dev) || ice_is_tunnel_supported(dev);
+}
+
+static int ice_tc_setup_redirect_action(struct net_device *filter_dev,
+ struct ice_tc_flower_fltr *fltr,
+ struct net_device *target_dev)
{
struct ice_repr *repr;
+ fltr->action.fltr_act = ICE_FWD_TO_VSI;
+
+ if (ice_is_port_repr_netdev(filter_dev) &&
+ ice_is_port_repr_netdev(target_dev)) {
+ repr = ice_netdev_to_repr(target_dev);
+
+ fltr->dest_vsi = repr->src_vsi;
+ fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
+ } else if (ice_is_port_repr_netdev(filter_dev) &&
+ ice_tc_is_dev_uplink(target_dev)) {
+ repr = ice_netdev_to_repr(filter_dev);
+
+ fltr->dest_vsi = repr->src_vsi->back->switchdev.uplink_vsi;
+ fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
+ } else if (ice_tc_is_dev_uplink(filter_dev) &&
+ ice_is_port_repr_netdev(target_dev)) {
+ repr = ice_netdev_to_repr(target_dev);
+
+ fltr->dest_vsi = repr->src_vsi;
+ fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
+ } else {
+ NL_SET_ERR_MSG_MOD(fltr->extack,
+ "Unsupported netdevice in switchdev mode");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int
+ice_tc_setup_drop_action(struct net_device *filter_dev,
+ struct ice_tc_flower_fltr *fltr)
+{
+ fltr->action.fltr_act = ICE_DROP_PACKET;
+
+ if (ice_is_port_repr_netdev(filter_dev)) {
+ fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
+ } else if (ice_tc_is_dev_uplink(filter_dev)) {
+ fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
+ } else {
+ NL_SET_ERR_MSG_MOD(fltr->extack,
+ "Unsupported netdevice in switchdev mode");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int ice_eswitch_tc_parse_action(struct net_device *filter_dev,
+ struct ice_tc_flower_fltr *fltr,
+ struct flow_action_entry *act)
+{
+ int err;
+
switch (act->id) {
case FLOW_ACTION_DROP:
- fltr->action.fltr_act = ICE_DROP_PACKET;
+ err = ice_tc_setup_drop_action(filter_dev, fltr);
+ if (err)
+ return err;
+
break;
case FLOW_ACTION_REDIRECT:
- fltr->action.fltr_act = ICE_FWD_TO_VSI;
-
- if (ice_is_port_repr_netdev(act->dev)) {
- repr = ice_netdev_to_repr(act->dev);
-
- fltr->dest_vsi = repr->src_vsi;
- fltr->direction = ICE_ESWITCH_FLTR_INGRESS;
- } else if (netif_is_ice(act->dev) ||
- ice_is_tunnel_supported(act->dev)) {
- fltr->direction = ICE_ESWITCH_FLTR_EGRESS;
- } else {
- NL_SET_ERR_MSG_MOD(fltr->extack, "Unsupported netdevice in switchdev mode");
- return -EINVAL;
- }
+ err = ice_tc_setup_redirect_action(filter_dev, fltr, act->dev);
+ if (err)
+ return err;
break;
goto exit;
}
- /* egress traffic is always redirect to uplink */
- if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS)
- fltr->dest_vsi = vsi->back->switchdev.uplink_vsi;
-
rule_info.sw_act.fltr_act = fltr->action.fltr_act;
if (fltr->action.fltr_act != ICE_DROP_PACKET)
rule_info.sw_act.vsi_handle = fltr->dest_vsi->idx;
rule_info.flags_info.act_valid = true;
if (fltr->direction == ICE_ESWITCH_FLTR_INGRESS) {
+ /* Uplink to VF */
rule_info.sw_act.flag |= ICE_FLTR_RX;
rule_info.sw_act.src = hw->pf_id;
rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE;
- } else {
+ } else if (fltr->direction == ICE_ESWITCH_FLTR_EGRESS &&
+ fltr->dest_vsi == vsi->back->switchdev.uplink_vsi) {
+ /* VF to Uplink */
rule_info.sw_act.flag |= ICE_FLTR_TX;
rule_info.sw_act.src = vsi->idx;
rule_info.flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE;
+ } else {
+ /* VF to VF */
+ rule_info.sw_act.flag |= ICE_FLTR_TX;
+ rule_info.sw_act.src = vsi->idx;
+ rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE;
}
/* specify the cookie as filter_rule_id */
/**
* ice_parse_tc_flower_actions - Parse the actions for a TC filter
+ * @filter_dev: Pointer to device on which filter is being added
* @vsi: Pointer to VSI
* @cls_flower: Pointer to TC flower offload structure
* @fltr: Pointer to TC flower filter structure
*
* Parse the actions for a TC filter
*/
-static int
-ice_parse_tc_flower_actions(struct ice_vsi *vsi,
- struct flow_cls_offload *cls_flower,
- struct ice_tc_flower_fltr *fltr)
+static int ice_parse_tc_flower_actions(struct net_device *filter_dev,
+ struct ice_vsi *vsi,
+ struct flow_cls_offload *cls_flower,
+ struct ice_tc_flower_fltr *fltr)
{
struct flow_rule *rule = flow_cls_offload_flow_rule(cls_flower);
struct flow_action *flow_action = &rule->action;
flow_action_for_each(i, act, flow_action) {
if (ice_is_eswitch_mode_switchdev(vsi->back))
- err = ice_eswitch_tc_parse_action(fltr, act);
+ err = ice_eswitch_tc_parse_action(filter_dev, fltr, act);
else
err = ice_tc_parse_action(vsi, fltr, act);
if (err)
if (err < 0)
goto err;
- err = ice_parse_tc_flower_actions(vsi, f, fltr);
+ err = ice_parse_tc_flower_actions(netdev, vsi, f, fltr);
if (err < 0)
goto err;
*/
int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off)
{
- const struct skb_shared_info *shinfo = skb_shinfo(skb);
+ const struct skb_shared_info *shinfo;
union {
struct iphdr *v4;
struct ipv6hdr *v6;
u32 paylen, l4_start;
int err;
- if (!shinfo->gso_size)
+ if (!skb_is_gso(skb))
return 0;
err = skb_cow_head(skb, 0);
if (err < 0)
return err;
+ shinfo = skb_shinfo(skb);
+
ip.hdr = skb_network_header(skb);
l4.hdr = skb_transport_header(skb);
int qidx, sqe_tail, sqe_head;
struct otx2_snd_queue *sq;
u64 incr, *ptr, val;
- int timeout = 1000;
ptr = (u64 *)otx2_get_regaddr(pfvf, NIX_LF_SQ_OP_STATUS);
for (qidx = 0; qidx < otx2_get_total_tx_queues(pfvf); qidx++) {
continue;
incr = (u64)qidx << 32;
- while (timeout) {
- val = otx2_atomic64_add(incr, ptr);
- sqe_head = (val >> 20) & 0x3F;
- sqe_tail = (val >> 28) & 0x3F;
- if (sqe_head == sqe_tail)
- break;
- usleep_range(1, 3);
- timeout--;
- }
+ val = otx2_atomic64_add(incr, ptr);
+ sqe_head = (val >> 20) & 0x3F;
+ sqe_tail = (val >> 28) & 0x3F;
+ if (sqe_head != sqe_tail)
+ usleep_range(50, 60);
}
}
int otx2_txsch_alloc(struct otx2_nic *pfvf);
void otx2_txschq_stop(struct otx2_nic *pfvf);
void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq);
+void otx2_free_pending_sqe(struct otx2_nic *pfvf);
void otx2_sqb_flush(struct otx2_nic *pfvf);
int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
dma_addr_t *dma);
};
static char *nix_snd_status_e_str[NIX_SND_STATUS_MAX] = {
- "NIX_SND_STATUS_GOOD",
- "NIX_SND_STATUS_SQ_CTX_FAULT",
- "NIX_SND_STATUS_SQ_CTX_POISON",
- "NIX_SND_STATUS_SQB_FAULT",
- "NIX_SND_STATUS_SQB_POISON",
- "NIX_SND_STATUS_HDR_ERR",
- "NIX_SND_STATUS_EXT_ERR",
- "NIX_SND_STATUS_JUMP_FAULT",
- "NIX_SND_STATUS_JUMP_POISON",
- "NIX_SND_STATUS_CRC_ERR",
- "NIX_SND_STATUS_IMM_ERR",
- "NIX_SND_STATUS_SG_ERR",
- "NIX_SND_STATUS_MEM_ERR",
- "NIX_SND_STATUS_INVALID_SUBDC",
- "NIX_SND_STATUS_SUBDC_ORDER_ERR",
- "NIX_SND_STATUS_DATA_FAULT",
- "NIX_SND_STATUS_DATA_POISON",
- "NIX_SND_STATUS_NPC_DROP_ACTION",
- "NIX_SND_STATUS_LOCK_VIOL",
- "NIX_SND_STATUS_NPC_UCAST_CHAN_ERR",
- "NIX_SND_STATUS_NPC_MCAST_CHAN_ERR",
- "NIX_SND_STATUS_NPC_MCAST_ABORT",
- "NIX_SND_STATUS_NPC_VTAG_PTR_ERR",
- "NIX_SND_STATUS_NPC_VTAG_SIZE_ERR",
- "NIX_SND_STATUS_SEND_STATS_ERR",
+ [NIX_SND_STATUS_GOOD] = "NIX_SND_STATUS_GOOD",
+ [NIX_SND_STATUS_SQ_CTX_FAULT] = "NIX_SND_STATUS_SQ_CTX_FAULT",
+ [NIX_SND_STATUS_SQ_CTX_POISON] = "NIX_SND_STATUS_SQ_CTX_POISON",
+ [NIX_SND_STATUS_SQB_FAULT] = "NIX_SND_STATUS_SQB_FAULT",
+ [NIX_SND_STATUS_SQB_POISON] = "NIX_SND_STATUS_SQB_POISON",
+ [NIX_SND_STATUS_HDR_ERR] = "NIX_SND_STATUS_HDR_ERR",
+ [NIX_SND_STATUS_EXT_ERR] = "NIX_SND_STATUS_EXT_ERR",
+ [NIX_SND_STATUS_JUMP_FAULT] = "NIX_SND_STATUS_JUMP_FAULT",
+ [NIX_SND_STATUS_JUMP_POISON] = "NIX_SND_STATUS_JUMP_POISON",
+ [NIX_SND_STATUS_CRC_ERR] = "NIX_SND_STATUS_CRC_ERR",
+ [NIX_SND_STATUS_IMM_ERR] = "NIX_SND_STATUS_IMM_ERR",
+ [NIX_SND_STATUS_SG_ERR] = "NIX_SND_STATUS_SG_ERR",
+ [NIX_SND_STATUS_MEM_ERR] = "NIX_SND_STATUS_MEM_ERR",
+ [NIX_SND_STATUS_INVALID_SUBDC] = "NIX_SND_STATUS_INVALID_SUBDC",
+ [NIX_SND_STATUS_SUBDC_ORDER_ERR] = "NIX_SND_STATUS_SUBDC_ORDER_ERR",
+ [NIX_SND_STATUS_DATA_FAULT] = "NIX_SND_STATUS_DATA_FAULT",
+ [NIX_SND_STATUS_DATA_POISON] = "NIX_SND_STATUS_DATA_POISON",
+ [NIX_SND_STATUS_NPC_DROP_ACTION] = "NIX_SND_STATUS_NPC_DROP_ACTION",
+ [NIX_SND_STATUS_LOCK_VIOL] = "NIX_SND_STATUS_LOCK_VIOL",
+ [NIX_SND_STATUS_NPC_UCAST_CHAN_ERR] = "NIX_SND_STAT_NPC_UCAST_CHAN_ERR",
+ [NIX_SND_STATUS_NPC_MCAST_CHAN_ERR] = "NIX_SND_STAT_NPC_MCAST_CHAN_ERR",
+ [NIX_SND_STATUS_NPC_MCAST_ABORT] = "NIX_SND_STATUS_NPC_MCAST_ABORT",
+ [NIX_SND_STATUS_NPC_VTAG_PTR_ERR] = "NIX_SND_STATUS_NPC_VTAG_PTR_ERR",
+ [NIX_SND_STATUS_NPC_VTAG_SIZE_ERR] = "NIX_SND_STATUS_NPC_VTAG_SIZE_ERR",
+ [NIX_SND_STATUS_SEND_MEM_FAULT] = "NIX_SND_STATUS_SEND_MEM_FAULT",
+ [NIX_SND_STATUS_SEND_STATS_ERR] = "NIX_SND_STATUS_SEND_STATS_ERR",
};
static irqreturn_t otx2_q_intr_handler(int irq, void *data)
continue;
if (val & BIT_ULL(42)) {
- netdev_err(pf->netdev, "CQ%lld: error reading NIX_LF_CQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
+ netdev_err(pf->netdev,
+ "CQ%lld: error reading NIX_LF_CQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
qidx, otx2_read64(pf, NIX_LF_ERR_INT));
} else {
if (val & BIT_ULL(NIX_CQERRINT_DOOR_ERR))
netdev_err(pf->netdev, "CQ%lld: Doorbell error",
qidx);
if (val & BIT_ULL(NIX_CQERRINT_CQE_FAULT))
- netdev_err(pf->netdev, "CQ%lld: Memory fault on CQE write to LLC/DRAM",
+ netdev_err(pf->netdev,
+ "CQ%lld: Memory fault on CQE write to LLC/DRAM",
qidx);
}
(val & NIX_SQINT_BITS));
if (val & BIT_ULL(42)) {
- netdev_err(pf->netdev, "SQ%lld: error reading NIX_LF_SQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
+ netdev_err(pf->netdev,
+ "SQ%lld: error reading NIX_LF_SQ_OP_INT, NIX_LF_ERR_INT 0x%llx\n",
qidx, otx2_read64(pf, NIX_LF_ERR_INT));
goto done;
}
goto chk_mnq_err_dbg;
sq_op_err_code = FIELD_GET(GENMASK(7, 0), sq_op_err_dbg);
- netdev_err(pf->netdev, "SQ%lld: NIX_LF_SQ_OP_ERR_DBG(%llx) err=%s\n",
- qidx, sq_op_err_dbg, nix_sqoperr_e_str[sq_op_err_code]);
+ netdev_err(pf->netdev,
+ "SQ%lld: NIX_LF_SQ_OP_ERR_DBG(0x%llx) err=%s(%#x)\n",
+ qidx, sq_op_err_dbg,
+ nix_sqoperr_e_str[sq_op_err_code],
+ sq_op_err_code);
otx2_write64(pf, NIX_LF_SQ_OP_ERR_DBG, BIT_ULL(44));
goto chk_snd_err_dbg;
mnq_err_code = FIELD_GET(GENMASK(7, 0), mnq_err_dbg);
- netdev_err(pf->netdev, "SQ%lld: NIX_LF_MNQ_ERR_DBG(%llx) err=%s\n",
- qidx, mnq_err_dbg, nix_mnqerr_e_str[mnq_err_code]);
+ netdev_err(pf->netdev,
+ "SQ%lld: NIX_LF_MNQ_ERR_DBG(0x%llx) err=%s(%#x)\n",
+ qidx, mnq_err_dbg, nix_mnqerr_e_str[mnq_err_code],
+ mnq_err_code);
otx2_write64(pf, NIX_LF_MNQ_ERR_DBG, BIT_ULL(44));
chk_snd_err_dbg:
snd_err_dbg = otx2_read64(pf, NIX_LF_SEND_ERR_DBG);
if (snd_err_dbg & BIT(44)) {
snd_err_code = FIELD_GET(GENMASK(7, 0), snd_err_dbg);
- netdev_err(pf->netdev, "SQ%lld: NIX_LF_SND_ERR_DBG:0x%llx err=%s\n",
- qidx, snd_err_dbg, nix_snd_status_e_str[snd_err_code]);
+ netdev_err(pf->netdev,
+ "SQ%lld: NIX_LF_SND_ERR_DBG:0x%llx err=%s(%#x)\n",
+ qidx, snd_err_dbg,
+ nix_snd_status_e_str[snd_err_code],
+ snd_err_code);
otx2_write64(pf, NIX_LF_SEND_ERR_DBG, BIT_ULL(44));
}
else
otx2_cleanup_tx_cqes(pf, cq);
}
+ otx2_free_pending_sqe(pf);
otx2_free_sq_res(pf);
NIX_SND_STATUS_EXT_ERR = 0x6,
NIX_SND_STATUS_JUMP_FAULT = 0x7,
NIX_SND_STATUS_JUMP_POISON = 0x8,
- NIX_SND_STATUS_CRC_ERR = 0x9,
- NIX_SND_STATUS_IMM_ERR = 0x10,
- NIX_SND_STATUS_SG_ERR = 0x11,
- NIX_SND_STATUS_MEM_ERR = 0x12,
- NIX_SND_STATUS_INVALID_SUBDC = 0x13,
- NIX_SND_STATUS_SUBDC_ORDER_ERR = 0x14,
- NIX_SND_STATUS_DATA_FAULT = 0x15,
- NIX_SND_STATUS_DATA_POISON = 0x16,
- NIX_SND_STATUS_NPC_DROP_ACTION = 0x17,
- NIX_SND_STATUS_LOCK_VIOL = 0x18,
- NIX_SND_STATUS_NPC_UCAST_CHAN_ERR = 0x19,
- NIX_SND_STATUS_NPC_MCAST_CHAN_ERR = 0x20,
- NIX_SND_STATUS_NPC_MCAST_ABORT = 0x21,
- NIX_SND_STATUS_NPC_VTAG_PTR_ERR = 0x22,
- NIX_SND_STATUS_NPC_VTAG_SIZE_ERR = 0x23,
- NIX_SND_STATUS_SEND_MEM_FAULT = 0x24,
- NIX_SND_STATUS_SEND_STATS_ERR = 0x25,
+ NIX_SND_STATUS_CRC_ERR = 0x10,
+ NIX_SND_STATUS_IMM_ERR = 0x11,
+ NIX_SND_STATUS_SG_ERR = 0x12,
+ NIX_SND_STATUS_MEM_ERR = 0x13,
+ NIX_SND_STATUS_INVALID_SUBDC = 0x14,
+ NIX_SND_STATUS_SUBDC_ORDER_ERR = 0x15,
+ NIX_SND_STATUS_DATA_FAULT = 0x16,
+ NIX_SND_STATUS_DATA_POISON = 0x17,
+ NIX_SND_STATUS_NPC_DROP_ACTION = 0x20,
+ NIX_SND_STATUS_LOCK_VIOL = 0x21,
+ NIX_SND_STATUS_NPC_UCAST_CHAN_ERR = 0x22,
+ NIX_SND_STATUS_NPC_MCAST_CHAN_ERR = 0x23,
+ NIX_SND_STATUS_NPC_MCAST_ABORT = 0x24,
+ NIX_SND_STATUS_NPC_VTAG_PTR_ERR = 0x25,
+ NIX_SND_STATUS_NPC_VTAG_SIZE_ERR = 0x26,
+ NIX_SND_STATUS_SEND_MEM_FAULT = 0x27,
+ NIX_SND_STATUS_SEND_STATS_ERR = 0x28,
NIX_SND_STATUS_MAX,
};
void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq)
{
+ int tx_pkts = 0, tx_bytes = 0;
struct sk_buff *skb = NULL;
struct otx2_snd_queue *sq;
struct nix_cqe_tx_s *cqe;
+ struct netdev_queue *txq;
int processed_cqe = 0;
struct sg_list *sg;
int qidx;
sg = &sq->sg[cqe->comp.sqe_id];
skb = (struct sk_buff *)sg->skb;
if (skb) {
+ tx_bytes += skb->len;
+ tx_pkts++;
otx2_dma_unmap_skb_frags(pfvf, sg);
dev_kfree_skb_any(skb);
sg->skb = (u64)NULL;
}
}
+ if (likely(tx_pkts)) {
+ if (qidx >= pfvf->hw.tx_queues)
+ qidx -= pfvf->hw.xdp_queues;
+ txq = netdev_get_tx_queue(pfvf->netdev, qidx);
+ netdev_tx_completed_queue(txq, tx_pkts, tx_bytes);
+ }
/* Free CQEs to HW */
otx2_write64(pfvf, NIX_LF_CQ_OP_DOOR,
((u64)cq->cq_idx << 32) | processed_cqe);
return err;
}
+void otx2_free_pending_sqe(struct otx2_nic *pfvf)
+{
+ int tx_pkts = 0, tx_bytes = 0;
+ struct sk_buff *skb = NULL;
+ struct otx2_snd_queue *sq;
+ struct netdev_queue *txq;
+ struct sg_list *sg;
+ int sq_idx, sqe;
+
+ for (sq_idx = 0; sq_idx < pfvf->hw.tx_queues; sq_idx++) {
+ sq = &pfvf->qset.sq[sq_idx];
+ for (sqe = 0; sqe < sq->sqe_cnt; sqe++) {
+ sg = &sq->sg[sqe];
+ skb = (struct sk_buff *)sg->skb;
+ if (skb) {
+ tx_bytes += skb->len;
+ tx_pkts++;
+ otx2_dma_unmap_skb_frags(pfvf, sg);
+ dev_kfree_skb_any(skb);
+ sg->skb = (u64)NULL;
+ }
+ }
+
+ if (!tx_pkts)
+ continue;
+ txq = netdev_get_tx_queue(pfvf->netdev, sq_idx);
+ netdev_tx_completed_queue(txq, tx_pkts, tx_bytes);
+ tx_pkts = 0;
+ tx_bytes = 0;
+ }
+}
+
static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, u64 dma_addr,
int len, int *offset)
{
if (dev->flags & IFF_PROMISC) {
rx_mode |= AcceptAllPhys;
+ } else if (!(dev->flags & IFF_MULTICAST)) {
+ rx_mode &= ~AcceptMulticast;
} else if (netdev_mc_count(dev) > MC_FILTER_LIMIT ||
dev->flags & IFF_ALLMULTI ||
- tp->mac_version == RTL_GIGA_MAC_VER_35) {
+ tp->mac_version == RTL_GIGA_MAC_VER_35 ||
+ tp->mac_version == RTL_GIGA_MAC_VER_46 ||
+ tp->mac_version == RTL_GIGA_MAC_VER_48) {
/* accept all multicasts */
} else if (netdev_mc_empty(dev)) {
rx_mode &= ~AcceptMulticast;
((val) << XGMAC_PPS_MINIDX(x))
#define XGMAC_PPSCMD_START 0x2
#define XGMAC_PPSCMD_STOP 0x5
-#define XGMAC_PPSEN0 BIT(4)
+#define XGMAC_PPSENx(x) BIT(4 + (x) * 8)
#define XGMAC_PPSx_TARGET_TIME_SEC(x) (0x00000d80 + (x) * 0x10)
#define XGMAC_PPSx_TARGET_TIME_NSEC(x) (0x00000d84 + (x) * 0x10)
#define XGMAC_TRGTBUSY0 BIT(31)
val |= XGMAC_PPSCMDx(index, XGMAC_PPSCMD_START);
val |= XGMAC_TRGTMODSELx(index, XGMAC_PPSCMD_START);
- val |= XGMAC_PPSEN0;
+
+ /* XGMAC Core has 4 PPS outputs at most.
+ *
+ * Prior XGMAC Core 3.20, Fixed mode or Flexible mode are selectable for
+ * PPS0 only via PPSEN0. PPS{1,2,3} are in Flexible mode by default,
+ * and can not be switched to Fixed mode, since PPSEN{1,2,3} are
+ * read-only reserved to 0.
+ * But we always set PPSEN{1,2,3} do not make things worse ;-)
+ *
+ * From XGMAC Core 3.20 and later, PPSEN{0,1,2,3} are writable and must
+ * be set, or the PPS outputs stay in Fixed PPS mode by default.
+ */
+ val |= XGMAC_PPSENx(index);
writel(cfg->start.tv_sec, ioaddr + XGMAC_PPSx_TARGET_TIME_SEC(index));
/* rx_pause/tx_pause */
if (rx_pause)
- mac_control |= CPSW_SL_CTL_RX_FLOW_EN;
+ mac_control |= CPSW_SL_CTL_TX_FLOW_EN;
if (tx_pause)
- mac_control |= CPSW_SL_CTL_TX_FLOW_EN;
+ mac_control |= CPSW_SL_CTL_RX_FLOW_EN;
cpsw_sl_ctl_set(port->slave.mac_sl, mac_control);
if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
writel(upper_32_bits(ns), iep->base +
iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG1]);
- writel(upper_32_bits(ns), iep->base + iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG0]);
+ writel(lower_32_bits(ns), iep->base + iep->plat_data->reg_offs[ICSS_IEP_COUNT_REG0]);
}
static void icss_iep_update_to_next_boundary(struct icss_iep *iep, u64 start_ns);
/* Information about built-in Ethernet MAC interfaces */
struct eth_plat_info {
- u8 phy; /* MII PHY ID, 0 - 31 */
u8 rxq; /* configurable, currently 0 - 31 only */
u8 txreadyq;
u8 hwaddr[ETH_ALEN];
if ((err = register_netdev(ndev)))
goto err_phy_dis;
- netdev_info(ndev, "%s: MII PHY %i on %s\n", ndev->name, plat->phy,
+ netdev_info(ndev, "%s: MII PHY %s on %s\n", ndev->name, phydev_name(phydev),
npe_name(port->npe));
return 0;
MODULE_AUTHOR("Calvin Johnson <calvin.johnson@oss.nxp.com>");
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ACPI MDIO bus (Ethernet PHY) accessors");
/**
* __acpi_mdiobus_register - Register mii_bus and create PHYs from the ACPI ASL.
MODULE_AUTHOR("Calvin Johnson <calvin.johnson@oss.nxp.com>");
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("FWNODE MDIO bus (Ethernet PHY) accessors");
static struct pse_control *
fwnode_find_pse_control(struct fwnode_handle *fwnode)
MODULE_AUTHOR("Andrew Jeffery <andrew@aj.id.au>");
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ASPEED MDIO bus controller");
EXPORT_SYMBOL(free_mdio_bitbang);
MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Bitbanged MDIO buses");
MODULE_AUTHOR("Grant Likely <grant.likely@secretlab.ca>");
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("OpenFirmware MDIO bus (Ethernet PHY) accessors");
/* Extract the clause 22 phy ID from the compatible string of the form
* ethernet-phy-idAAAA.BBBB */
EXPORT_SYMBOL_GPL(bcm_ptp_probe);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Broadcom PHY PTP driver");
module_phy_driver(bcm87xx_driver);
MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Broadcom BCM87xx PHY driver");
pl->config = config;
if (config->type == PHYLINK_NETDEV) {
pl->netdev = to_net_dev(config->dev);
+ netif_carrier_off(pl->netdev);
} else if (config->type == PHYLINK_DEV) {
pl->dev = config->dev;
} else {
module_init(phylink_init);
MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("phylink models the MAC to optional PHY connection");
MODULE_ALIAS("platform:sfp");
MODULE_AUTHOR("Russell King");
MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("SFP cage support");
/* uprog->len is unsigned short, so no overflow here */
fprog.len = uprog->len;
- fprog.filter = memdup_user(uprog->filter,
- uprog->len * sizeof(struct sock_filter));
+ fprog.filter = memdup_array_user(uprog->filter,
+ uprog->len, sizeof(struct sock_filter));
if (IS_ERR(fprog.filter))
return ERR_CAST(fprog.filter);
container_of(pccontext->clk, struct ptp_clock, clock);
struct timestamp_event_queue *queue;
char debugfsname[32];
+ unsigned long flags;
queue = kzalloc(sizeof(*queue), GFP_KERNEL);
if (!queue)
}
bitmap_set(queue->mask, 0, PTP_MAX_CHANNELS);
spin_lock_init(&queue->lock);
+ spin_lock_irqsave(&ptp->tsevqs_lock, flags);
list_add_tail(&queue->qlist, &ptp->tsevqs);
+ spin_unlock_irqrestore(&ptp->tsevqs_lock, flags);
pccontext->private_clkdata = queue;
/* Debugfs contents */
{
struct timestamp_event_queue *queue = pccontext->private_clkdata;
unsigned long flags;
+ struct ptp_clock *ptp =
+ container_of(pccontext->clk, struct ptp_clock, clock);
- if (queue) {
- debugfs_remove(queue->debugfs_instance);
- pccontext->private_clkdata = NULL;
- spin_lock_irqsave(&queue->lock, flags);
- list_del(&queue->qlist);
- spin_unlock_irqrestore(&queue->lock, flags);
- bitmap_free(queue->mask);
- kfree(queue);
- }
+ debugfs_remove(queue->debugfs_instance);
+ pccontext->private_clkdata = NULL;
+ spin_lock_irqsave(&ptp->tsevqs_lock, flags);
+ list_del(&queue->qlist);
+ spin_unlock_irqrestore(&ptp->tsevqs_lock, flags);
+ bitmap_free(queue->mask);
+ kfree(queue);
return 0;
}
free_event:
kfree(event);
exit:
- if (result < 0)
- ptp_release(pccontext);
return result;
}
mutex_destroy(&ptp->pincfg_mux);
mutex_destroy(&ptp->n_vclocks_mux);
/* Delete first entry */
+ spin_lock_irqsave(&ptp->tsevqs_lock, flags);
tsevq = list_first_entry(&ptp->tsevqs, struct timestamp_event_queue,
qlist);
- spin_lock_irqsave(&tsevq->lock, flags);
list_del(&tsevq->qlist);
- spin_unlock_irqrestore(&tsevq->lock, flags);
+ spin_unlock_irqrestore(&ptp->tsevqs_lock, flags);
bitmap_free(tsevq->mask);
kfree(tsevq);
debugfs_remove(ptp->debugfs_root);
if (!queue)
goto no_memory_queue;
list_add_tail(&queue->qlist, &ptp->tsevqs);
+ spin_lock_init(&ptp->tsevqs_lock);
queue->mask = bitmap_alloc(PTP_MAX_CHANNELS, GFP_KERNEL);
if (!queue->mask)
goto no_memory_bitmap;
{
struct timestamp_event_queue *tsevq;
struct pps_event_time evt;
+ unsigned long flags;
switch (event->type) {
case PTP_CLOCK_EXTTS:
/* Enqueue timestamp on selected queues */
+ spin_lock_irqsave(&ptp->tsevqs_lock, flags);
list_for_each_entry(tsevq, &ptp->tsevqs, qlist) {
if (test_bit((unsigned int)event->index, tsevq->mask))
enqueue_external_timestamp(tsevq, event);
}
+ spin_unlock_irqrestore(&ptp->tsevqs_lock, flags);
wake_up_interruptible(&ptp->tsev_wq);
break;
struct pps_device *pps_source;
long dialed_frequency; /* remembers the frequency adjustment */
struct list_head tsevqs; /* timestamp fifo list */
+ spinlock_t tsevqs_lock; /* protects tsevqs from concurrent access */
struct mutex pincfg_mux; /* protect concurrent info->pin_config access */
wait_queue_head_t tsev_wq;
int defunct; /* tells readers to go away when clock is being removed */
static void qeth_check_outbound_queue(struct qeth_qdio_out_q *queue)
{
/*
- * check if weed have to switch to non-packing mode or if
+ * check if we have to switch to non-packing mode or if
* we have to get a pci flag out on the queue
*/
if ((atomic_read(&queue->used_buffers) <= QETH_LOW_WATERMARK_PACK) ||
*/
#define __bpf_kfunc __used noinline
+#define __bpf_kfunc_start_defs() \
+ __diag_push(); \
+ __diag_ignore_all("-Wmissing-declarations", \
+ "Global kfuncs as their definitions will be in BTF");\
+ __diag_ignore_all("-Wmissing-prototypes", \
+ "Global kfuncs as their definitions will be in BTF")
+
+#define __bpf_kfunc_end_defs() __diag_pop()
+#define __bpf_hook_start() __bpf_kfunc_start_defs()
+#define __bpf_hook_end() __bpf_kfunc_end_defs()
+
/*
* Return the name of the passed struct, if exists, or halt the build if for
* example the structure gets renamed. In this way, developers have to revisit
/**
* ethtool_sprintf - Write formatted string to ethtool string data
- * @data: Pointer to start of string to update
+ * @data: Pointer to a pointer to the start of string to update
* @fmt: Format of string to write
*
- * Write formatted string to data. Update data to point at start of
+ * Write formatted string to *data. Update *data to point at start of
* next string.
*/
extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...);
*/
#define idr_for_each_entry_ul(idr, entry, tmp, id) \
for (tmp = 0, id = 0; \
- tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \
+ ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \
tmp = id, ++id)
/**
* @id: Entry ID.
*
* Continue to iterate over entries, continuing after the current position.
+ * After normal termination @entry is left with the value NULL. This
+ * is convenient for a "not found" value.
*/
#define idr_for_each_entry_continue_ul(idr, entry, tmp, id) \
for (tmp = id; \
- tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \
+ ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \
tmp = id, ++id)
/*
u64 snt_synack; /* first SYNACK sent time */
bool tfo_listener;
bool is_mptcp;
- s8 req_usec_ts;
+ bool req_usec_ts;
#if IS_ENABLED(CONFIG_MPTCP)
bool drop_req;
#endif
#define FLOWI_FLAG_KNOWN_NH 0x02
__u32 flowic_secid;
kuid_t flowic_uid;
- struct flowi_tunnel flowic_tun_key;
__u32 flowic_multipath_hash;
+ struct flowi_tunnel flowic_tun_key;
};
union flowi_uli {
#endif
}
-static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct nf_conn *ct)
+static inline void nf_conn_act_ct_ext_fill(struct sk_buff *skb, struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo)
+{
+#if IS_ENABLED(CONFIG_NET_ACT_CT)
+ struct nf_conn_act_ct_ext *act_ct_ext;
+
+ act_ct_ext = nf_conn_act_ct_ext_find(ct);
+ if (dev_net(skb->dev) == &init_net && act_ct_ext)
+ act_ct_ext->ifindex[CTINFO2DIR(ctinfo)] = skb->dev->ifindex;
+#endif
+}
+
+static inline struct
+nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct sk_buff *skb,
+ struct nf_conn *ct,
+ enum ip_conntrack_info ctinfo)
{
#if IS_ENABLED(CONFIG_NET_ACT_CT)
struct nf_conn_act_ct_ext *act_ct = nf_ct_ext_find(ct, NF_CT_EXT_ACT_CT);
return act_ct;
act_ct = nf_ct_ext_add(ct, NF_CT_EXT_ACT_CT, GFP_ATOMIC);
+ nf_conn_act_ct_ext_fill(skb, ct, ctinfo);
return act_ct;
#else
return NULL;
#endif
}
-static inline void nf_conn_act_ct_ext_fill(struct sk_buff *skb, struct nf_conn *ct,
- enum ip_conntrack_info ctinfo)
-{
-#if IS_ENABLED(CONFIG_NET_ACT_CT)
- struct nf_conn_act_ct_ext *act_ct_ext;
-
- act_ct_ext = nf_conn_act_ct_ext_find(ct);
- if (dev_net(skb->dev) == &init_net && act_ct_ext)
- act_ct_ext->ifindex[CTINFO2DIR(ctinfo)] = skb->dev->ifindex;
-#endif
-}
-
#endif /* _NF_CONNTRACK_ACT_CT_H */
#define tcp_hash_fail(msg, family, skb, fmt, ...) \
do { \
const struct tcphdr *th = tcp_hdr(skb); \
- char hdr_flags[5] = {}; \
+ char hdr_flags[6]; \
char *f = hdr_flags; \
\
if (th->fin) \
*f++ = 'S'; \
if (th->rst) \
*f++ = 'R'; \
+ if (th->psh) \
+ *f++ = 'P'; \
if (th->ack) \
- *f++ = 'A'; \
- if (f != hdr_flags) \
- *f = ' '; \
+ *f++ = '.'; \
+ *f = 0; \
if ((family) == AF_INET) { \
- net_info_ratelimited("%s for (%pI4, %d)->(%pI4, %d) %s" fmt "\n", \
+ net_info_ratelimited("%s for %pI4.%d->%pI4.%d [%s] " fmt "\n", \
msg, &ip_hdr(skb)->saddr, ntohs(th->source), \
&ip_hdr(skb)->daddr, ntohs(th->dest), \
hdr_flags, ##__VA_ARGS__); \
} else { \
- net_info_ratelimited("%s for [%pI6c]:%u->[%pI6c]:%u %s" fmt "\n", \
+ net_info_ratelimited("%s for [%pI6c].%d->[%pI6c].%d [%s]" fmt "\n", \
msg, &ipv6_hdr(skb)->saddr, ntohs(th->source), \
&ipv6_hdr(skb)->daddr, ntohs(th->dest), \
hdr_flags, ##__VA_ARGS__); \
/* Documentation/netlink/specs/nfsd.yaml */
/* YNL-GEN uapi header */
-#ifndef _UAPI_LINUX_NFSD_H
-#define _UAPI_LINUX_NFSD_H
+#ifndef _UAPI_LINUX_NFSD_NETLINK_H
+#define _UAPI_LINUX_NFSD_NETLINK_H
#define NFSD_FAMILY_NAME "nfsd"
#define NFSD_FAMILY_VERSION 1
NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1)
};
-#endif /* _UAPI_LINUX_NFSD_H */
+#endif /* _UAPI_LINUX_NFSD_NETLINK_H */
int end; /* final value, exclusive */
} __aligned(8);
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc int bpf_iter_num_new(struct bpf_iter_num *it, int start, int end)
{
s->cur = s->end = 0;
}
-__diag_pop();
+__bpf_kfunc_end_defs();
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__cgroup, cgroup),
- PTR_TO_BTF_ID_OR_NULL },
+ PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
},
.seq_info = &cgroup_iter_seq_info,
};
unsigned int flags;
} __attribute__((aligned(8)));
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it,
struct cgroup_subsys_state *start, unsigned int flags)
{
}
-__diag_pop();
\ No newline at end of file
+__bpf_kfunc_end_defs();
return cpu < nr_cpu_ids;
}
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global kfuncs as their definitions will be in BTF");
+__bpf_kfunc_start_defs();
/**
* bpf_cpumask_create() - Create a mutable BPF cpumask.
return cpumask_any_and_distribute(src1, src2);
}
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(cpumask_kfunc_btf_ids)
BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL)
ret = -EBUSY;
goto out;
}
- if (!atomic64_read(&map->usercnt)) {
- /* maps with timers must be either held by user space
- * or pinned in bpffs.
- */
- ret = -EPERM;
- goto out;
- }
/* allocate hrtimer via map_kmalloc to use memcg accounting */
t = bpf_map_kmalloc_node(map, sizeof(*t), GFP_ATOMIC, map->numa_node);
if (!t) {
rcu_assign_pointer(t->callback_fn, NULL);
hrtimer_init(&t->timer, clockid, HRTIMER_MODE_REL_SOFT);
t->timer.function = bpf_timer_cb;
- timer->timer = t;
+ WRITE_ONCE(timer->timer, t);
+ /* Guarantee the order between timer->timer and map->usercnt. So
+ * when there are concurrent uref release and bpf timer init, either
+ * bpf_timer_cancel_and_free() called by uref release reads a no-NULL
+ * timer or atomic64_read() below returns a zero usercnt.
+ */
+ smp_mb();
+ if (!atomic64_read(&map->usercnt)) {
+ /* maps with timers must be either held by user space
+ * or pinned in bpffs.
+ */
+ WRITE_ONCE(timer->timer, NULL);
+ kfree(t);
+ ret = -EPERM;
+ }
out:
__bpf_spin_unlock_irqrestore(&timer->lock);
return ret;
/* The subsequent bpf_timer_start/cancel() helpers won't be able to use
* this timer, since it won't be initialized.
*/
- timer->timer = NULL;
+ WRITE_ONCE(timer->timer, NULL);
out:
__bpf_spin_unlock_irqrestore(&timer->lock);
if (!t)
}
}
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign)
{
WARN(1, "A call to BPF exception callback should never return\n");
}
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(generic_btf_ids)
#ifdef CONFIG_KEXEC_CORE
BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU)
BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY)
+#ifdef CONFIG_CGROUPS
BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS)
BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY)
-BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
-BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
-BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL)
BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY)
+#endif
+BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED)
+BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY)
BTF_ID_FLAGS(func, bpf_dynptr_adjust)
BTF_ID_FLAGS(func, bpf_dynptr_is_null)
BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly)
late_initcall(bpf_map_iter_init);
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map)
{
return ret;
}
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(bpf_map_iter_kfunc_ids)
BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS)
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__task, task),
- PTR_TO_BTF_ID_OR_NULL },
+ PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
},
.seq_info = &task_seq_info,
.fill_link_info = bpf_iter_fill_link_info,
struct bpf_iter_task_vma_kern_data *data;
} __attribute__((aligned(8)));
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
struct task_struct *task, u64 addr)
}
}
-__diag_pop();
+__bpf_kfunc_end_defs();
+
+#ifdef CONFIG_CGROUPS
struct bpf_iter_css_task {
__u64 __opaque[1];
struct css_task_iter *css_it;
} __attribute__((aligned(8)));
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it,
struct cgroup_subsys_state *css, unsigned int flags)
bpf_mem_free(&bpf_global_ma, kit->css_it);
}
-__diag_pop();
+__bpf_kfunc_end_defs();
+
+#endif /* CONFIG_CGROUPS */
struct bpf_iter_task {
__u64 __opaque[3];
BPF_TASK_ITER_PROC_THREADS
};
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it,
struct task_struct *task__nullable, unsigned int flags)
{
}
-__diag_pop();
+__bpf_kfunc_end_defs();
DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
if (class == BPF_ALU || class == BPF_ALU64) {
if (!bt_is_reg_set(bt, dreg))
return 0;
- if (opcode == BPF_MOV) {
+ if (opcode == BPF_END || opcode == BPF_NEG) {
+ /* sreg is reserved and unused
+ * dreg still need precision before this insn
+ */
+ return 0;
+ } else if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
/* dreg = sreg or dreg = (s8, s16, s32)sreg
* dreg needs precision after this insn
insn->imm != 0 && env->bpf_capable) {
struct bpf_reg_state fake_reg = {};
- __mark_reg_known(&fake_reg, (u32)insn->imm);
+ __mark_reg_known(&fake_reg, insn->imm);
fake_reg.type = SCALAR_VALUE;
save_register_state(state, spi, &fake_reg, size);
} else if (reg && is_spillable_regtype(reg->type)) {
/* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */
BTF_SET_START(rcu_protected_types)
BTF_ID(struct, prog_test_ref_kfunc)
+#ifdef CONFIG_CGROUPS
BTF_ID(struct, cgroup)
+#endif
BTF_ID(struct, bpf_cpumask)
BTF_ID(struct, task_struct)
BTF_SET_END(rcu_protected_types)
BTF_ID(func, bpf_percpu_obj_new_impl)
BTF_ID(func, bpf_percpu_obj_drop_impl)
BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
BTF_ID(func, bpf_iter_css_task_new)
+#endif
BTF_SET_END(special_kfunc_set)
BTF_ID_LIST(special_kfunc_list)
BTF_ID(func, bpf_percpu_obj_new_impl)
BTF_ID(func, bpf_percpu_obj_drop_impl)
BTF_ID(func, bpf_throw)
+#ifdef CONFIG_CGROUPS
BTF_ID(func, bpf_iter_css_task_new)
+#else
+BTF_ID_UNUSED
+#endif
static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
{
&meta->arg_rbtree_root.field);
}
+/*
+ * css_task iter allowlist is needed to avoid dead locking on css_set_lock.
+ * LSM hooks and iters (both sleepable and non-sleepable) are safe.
+ * Any sleepable progs are also safe since bpf_check_attach_target() enforce
+ * them can only be attached to some specific hook points.
+ */
static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
{
enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
switch (prog_type) {
case BPF_PROG_TYPE_LSM:
return true;
- case BPF_TRACE_ITER:
- return env->prog->aux->sleepable;
+ case BPF_PROG_TYPE_TRACING:
+ if (env->prog->expected_attach_type == BPF_TRACE_ITER)
+ return true;
+ fallthrough;
default:
- return false;
+ return env->prog->aux->sleepable;
}
}
case KF_ARG_PTR_TO_ITER:
if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) {
if (!check_css_task_iter_allowlist(env)) {
- verbose(env, "css_task_iter is only allowed in bpf_lsm and bpf iter-s\n");
+ verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n");
return -EINVAL;
}
}
* optimize away the callsite. Therefore, __weak is needed to ensure that the
* call is still emitted, by telling the compiler that we don't know what the
* function might eventually be.
- *
- * __diag_* below are needed to dismiss the missing prototype warning.
*/
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "kfuncs which will be used in BPF programs");
+
+__bpf_hook_start();
__weak noinline void bpf_rstat_flush(struct cgroup *cgrp,
struct cgroup *parent, int cpu)
{
}
-__diag_pop();
+__bpf_hook_end();
/* see cgroup_rstat_flush() */
static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
};
#ifdef CONFIG_KEYS
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "kfuncs which will be used in BPF programs");
+__bpf_kfunc_start_defs();
/**
* bpf_lookup_user_key - lookup a key by its serial
}
#endif /* CONFIG_SYSTEM_DATA_VERIFICATION */
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(key_sig_kfunc_set)
BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE)
* architecture dependent calling conventions. 7+ can be supported in the
* future.
*/
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
+
__bpf_kfunc int bpf_fentry_test1(int a)
{
return a + 1;
{
}
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(bpf_test_modify_return_ids)
BTF_ID_FLAGS(func, bpf_modify_return_test)
module_init(ebtable_broute_init);
module_exit(ebtable_broute_fini);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Force packets to be routed instead of bridged");
module_init(ebtable_filter_init);
module_exit(ebtable_filter_fini);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ebtables legacy filter table");
module_init(ebtable_nat_init);
module_exit(ebtable_nat_fini);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ebtables legacy stateless nat table");
module_init(ebtables_init);
module_exit(ebtables_fini);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ebtables legacy core");
MODULE_ALIAS("nf_conntrack-" __stringify(AF_BRIDGE));
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Bridge IPv4 and IPv6 connection tracking");
return func;
}
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
__bpf_kfunc int bpf_dynptr_from_skb(struct sk_buff *skb, u64 flags,
struct bpf_dynptr_kern *ptr__uninit)
{
return 0;
}
-__diag_pop();
+__bpf_kfunc_end_defs();
int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
struct bpf_dynptr_kern *ptr__uninit)
}
late_initcall(bpf_kfunc_init);
-/* Disables missing prototype warnings */
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
/* bpf_sock_destroy: Destroy the given socket with ECONNABORTED error code.
*
return sk->sk_prot->diag_destroy(sk, ECONNABORTED);
}
-__diag_pop()
+__bpf_kfunc_end_defs();
BTF_SET8_START(bpf_sk_iter_kfunc_ids)
BTF_ID_FLAGS(func, bpf_sock_destroy, KF_TRUSTED_ARGS)
return -ENOMEM;
#endif
- if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
+ if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) {
+#ifdef CONFIG_PAGE_POOL_STATS
+ free_percpu(pool->recycle_stats);
+#endif
return -ENOMEM;
+ }
atomic_set(&pool->pages_state_release_cnt, 0);
return nxdpf;
}
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in vmlinux BTF");
+__bpf_kfunc_start_defs();
/**
* bpf_xdp_metadata_rx_timestamp - Read XDP frame RX timestamp.
return -EOPNOTSUPP;
}
-__diag_pop();
+__bpf_kfunc_end_defs();
BTF_SET8_START(xdp_metadata_kfunc_ids)
#define XDP_METADATA_KFUNC(_, __, name, ___) BTF_ID_FLAGS(func, name, KF_TRUSTED_ARGS)
if (dccp_parse_options(sk, dreq, skb))
goto drop_and_free;
- if (security_inet_conn_request(sk, skb, req))
- goto drop_and_free;
-
ireq = inet_rsk(req);
sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
ireq->ireq_family = AF_INET;
ireq->ir_iif = READ_ONCE(sk->sk_bound_dev_if);
+ if (security_inet_conn_request(sk, skb, req))
+ goto drop_and_free;
+
/*
* Step 3: Process LISTEN state
*
if (dccp_parse_options(sk, dreq, skb))
goto drop_and_free;
- if (security_inet_conn_request(sk, skb, req))
- goto drop_and_free;
-
ireq = inet_rsk(req);
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
ireq->ireq_family = AF_INET6;
ireq->ir_mark = inet_request_mark(sk, skb);
+ if (security_inet_conn_request(sk, skb, req))
+ goto drop_and_free;
+
if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY, },
[DEVLINK_PORT_FN_ATTR_STATE] = NLA_POLICY_MAX(NLA_U8, 1),
[DEVLINK_PORT_FN_ATTR_OPSTATE] = NLA_POLICY_MAX(NLA_U8, 1),
- [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(3),
+ [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(15),
};
const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1] = {
skb = skb_copy_expand(frame->skb_std, 0,
skb_tailroom(frame->skb_std) + HSR_HLEN,
GFP_ATOMIC);
- prp_fill_rct(skb, frame, port);
-
- return skb;
+ return prp_fill_rct(skb, frame, port);
}
static void hsr_deliver_master(struct sk_buff *skb, struct net_device *dev,
FOU_BPF_ENCAP_GUE,
};
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in BTF");
+__bpf_kfunc_start_defs();
/* bpf_skb_set_fou_encap - Set FOU encap parameters
*
return 0;
}
-__diag_pop()
+__bpf_kfunc_end_defs();
BTF_SET8_START(fou_kfunc_set)
BTF_ID_FLAGS(func, bpf_skb_set_fou_encap)
module_exit(iptable_nat_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("iptables legacy nat table");
module_init(iptable_raw_init);
module_exit(iptable_raw_fini);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("iptables legacy raw table");
module_exit(nf_defrag_fini);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv4 defragmentation support");
EXPORT_SYMBOL_GPL(nf_send_unreach);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv4 packet rejection core");
treq->af_specific = af_ops;
treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
- treq->req_usec_ts = -1;
+ treq->req_usec_ts = false;
#if IS_ENABLED(CONFIG_MPTCP)
treq->is_mptcp = sk_is_mptcp(sk);
key->maclen = cmd->maclen ?: 12; /* 12 is the default in RFC5925 */
/* Check: maclen + tcp-ao header <= (MAX_TCP_OPTION_SPACE - mss
- * - tstamp - wscale - sackperm),
+ * - tstamp (including sackperm)
+ * - wscale),
* see tcp_syn_options(), tcp_synack_options(), commit 33ad798c924b.
*
* In order to allow D-SACK with TCP-AO, the header size should be:
* large to leave sufficient option space.
*/
syn_tcp_option_space = MAX_TCP_OPTION_SPACE;
+ syn_tcp_option_space -= TCPOLEN_MSS_ALIGNED;
syn_tcp_option_space -= TCPOLEN_TSTAMP_ALIGNED;
syn_tcp_option_space -= TCPOLEN_WSCALE_ALIGNED;
- syn_tcp_option_space -= TCPOLEN_SACKPERM_ALIGNED;
if (tcp_ao_len(key) > syn_tcp_option_space) {
err = -EMSGSIZE;
goto err_kfree;
req->syncookie = want_cookie;
tcp_rsk(req)->af_specific = af_ops;
tcp_rsk(req)->ts_off = 0;
- tcp_rsk(req)->req_usec_ts = -1;
+ tcp_rsk(req)->req_usec_ts = false;
#if IS_ENABLED(CONFIG_MPTCP)
tcp_rsk(req)->is_mptcp = 0;
#endif
if (!dst)
goto drop_and_free;
- if (tmp_opt.tstamp_ok)
+ if (tmp_opt.tstamp_ok) {
+ tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst);
tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
-
+ }
if (!want_cookie && !isn) {
int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog);
}
#endif
+static __be32 *process_tcp_ao_options(struct tcp_sock *tp,
+ const struct tcp_request_sock *tcprsk,
+ struct tcp_out_options *opts,
+ struct tcp_key *key, __be32 *ptr)
+{
+#ifdef CONFIG_TCP_AO
+ u8 maclen = tcp_ao_maclen(key->ao_key);
+
+ if (tcprsk) {
+ u8 aolen = maclen + sizeof(struct tcp_ao_hdr);
+
+ *ptr++ = htonl((TCPOPT_AO << 24) | (aolen << 16) |
+ (tcprsk->ao_keyid << 8) |
+ (tcprsk->ao_rcv_next));
+ } else {
+ struct tcp_ao_key *rnext_key;
+ struct tcp_ao_info *ao_info;
+
+ ao_info = rcu_dereference_check(tp->ao_info,
+ lockdep_sock_is_held(&tp->inet_conn.icsk_inet.sk));
+ rnext_key = READ_ONCE(ao_info->rnext_key);
+ if (WARN_ON_ONCE(!rnext_key))
+ return ptr;
+ *ptr++ = htonl((TCPOPT_AO << 24) |
+ (tcp_ao_len(key->ao_key) << 16) |
+ (key->ao_key->sndid << 8) |
+ (rnext_key->rcvid));
+ }
+ opts->hash_location = (__u8 *)ptr;
+ ptr += maclen / sizeof(*ptr);
+ if (unlikely(maclen % sizeof(*ptr))) {
+ memset(ptr, TCPOPT_NOP, sizeof(*ptr));
+ ptr++;
+ }
+#endif
+ return ptr;
+}
+
/* Write previously computed TCP options to the packet.
*
* Beware: Something in the Internet is very sensitive to the ordering of
opts->hash_location = (__u8 *)ptr;
ptr += 4;
} else if (tcp_key_is_ao(key)) {
-#ifdef CONFIG_TCP_AO
- u8 maclen = tcp_ao_maclen(key->ao_key);
-
- if (tcprsk) {
- u8 aolen = maclen + sizeof(struct tcp_ao_hdr);
-
- *ptr++ = htonl((TCPOPT_AO << 24) | (aolen << 16) |
- (tcprsk->ao_keyid << 8) |
- (tcprsk->ao_rcv_next));
- } else {
- struct tcp_ao_key *rnext_key;
- struct tcp_ao_info *ao_info;
-
- ao_info = rcu_dereference_check(tp->ao_info,
- lockdep_sock_is_held(&tp->inet_conn.icsk_inet.sk));
- rnext_key = READ_ONCE(ao_info->rnext_key);
- if (WARN_ON_ONCE(!rnext_key))
- goto out_ao;
- *ptr++ = htonl((TCPOPT_AO << 24) |
- (tcp_ao_len(key->ao_key) << 16) |
- (key->ao_key->sndid << 8) |
- (rnext_key->rcvid));
- }
- opts->hash_location = (__u8 *)ptr;
- ptr += maclen / sizeof(*ptr);
- if (unlikely(maclen % sizeof(*ptr))) {
- memset(ptr, TCPOPT_NOP, sizeof(*ptr));
- ptr++;
- }
-out_ao:
-#endif
+ ptr = process_tcp_ao_options(tp, tcprsk, opts, key, ptr);
}
if (unlikely(opts->mss)) {
*ptr++ = htonl((TCPOPT_MSS << 24) |
mss = tcp_mss_clamp(tp, dst_metric_advmss(dst));
memset(&opts, 0, sizeof(opts));
- if (tcp_rsk(req)->req_usec_ts < 0)
- tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst);
now = tcp_clock_ns();
#ifdef CONFIG_SYN_COOKIES
if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok))
*/
void tcp_sigpool_release(unsigned int id)
{
- if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg))
+ if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg))
return;
/* slow-path */
*/
void tcp_sigpool_get(unsigned int id)
{
- if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg))
+ if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg))
return;
kref_get(&cpool[id].kref);
}
struct crypto_ahash *hash;
rcu_read_lock_bh();
- if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg)) {
+ if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg)) {
rcu_read_unlock_bh();
return -EINVAL;
}
*/
size_t tcp_sigpool_algo(unsigned int id, char *buf, size_t buf_len)
{
- if (WARN_ON_ONCE(id > cpool_populated || !cpool[id].alg))
+ if (WARN_ON_ONCE(id >= cpool_populated || !cpool[id].alg))
return -EINVAL;
return strscpy(buf, cpool[id].alg, buf_len);
module_exit(ip6table_nat_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Ip6tables legacy nat table");
module_init(ip6table_raw_init);
module_exit(ip6table_raw_fini);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Ip6tables legacy raw table");
module_exit(nf_defrag_fini);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv6 defragmentation support");
EXPORT_SYMBOL_GPL(nf_send_unreach6);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv6 packet rejection core");
treq = tcp_rsk(req);
treq->tfo_listener = false;
- if (security_inet_conn_request(sk, skb, req))
- goto out_free;
-
req->mss = mss;
ireq->ir_rmt_port = th->source;
ireq->ir_num = ntohs(th->dest);
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
+
+ if (security_inet_conn_request(sk, skb, req))
+ goto out_free;
+
if (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
module_exit(kcm_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("KCM (Kernel Connection Multiplexor) sockets");
MODULE_ALIAS_NETPROTO(PF_KCM);
skb->transport_header += llc_len;
skb_pull(skb, llc_len);
if (skb->protocol == htons(ETH_P_802_2)) {
- __be16 pdulen = eth_hdr(skb)->h_proto;
- s32 data_size = ntohs(pdulen) - llc_len;
+ __be16 pdulen;
+ s32 data_size;
+
+ if (skb->mac_len < ETH_HLEN)
+ return 0;
+
+ pdulen = eth_hdr(skb)->h_proto;
+ data_size = ntohs(pdulen) - llc_len;
if (data_size < 0 ||
!pskb_may_pull(skb, data_size))
int rc = 1;
u32 data_size;
+ if (skb->mac_len < ETH_HLEN)
+ return 1;
+
llc_pdu_decode_sa(skb, mac_da);
llc_pdu_decode_da(skb, mac_sa);
llc_pdu_decode_ssap(skb, &dsap);
u32 data_size;
struct sk_buff *nskb;
+ if (skb->mac_len < ETH_HLEN)
+ goto out;
+
/* The test request command is type U (llc_len = 3) */
data_size = ntohs(eth_hdr(skb)->h_proto) - 3;
nskb = llc_alloc_frame(NULL, skb->dev, LLC_PDU_TYPE_U, data_size);
module_init(ip_vs_init);
module_exit(ip_vs_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IP Virtual Server");
module_init(ip_vs_dh_init);
module_exit(ip_vs_dh_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs destination hashing scheduler");
module_init(ip_vs_fo_init);
module_exit(ip_vs_fo_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs weighted failover scheduler");
module_init(ip_vs_ftp_init);
module_exit(ip_vs_ftp_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs ftp helper");
module_init(ip_vs_lblc_init);
module_exit(ip_vs_lblc_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs locality-based least-connection scheduler");
module_init(ip_vs_lblcr_init);
module_exit(ip_vs_lblcr_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs locality-based least-connection with replication scheduler");
module_init(ip_vs_lc_init);
module_exit(ip_vs_lc_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs least connection scheduler");
module_init(ip_vs_nq_init);
module_exit(ip_vs_nq_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs never queue scheduler");
module_init(ip_vs_ovf_init);
module_exit(ip_vs_ovf_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs overflow connection scheduler");
module_init(ip_vs_sip_init);
module_exit(ip_vs_sip_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs sip helper");
module_init(ip_vs_rr_init);
module_exit(ip_vs_rr_cleanup);
+MODULE_DESCRIPTION("ipvs round-robin scheduler");
MODULE_LICENSE("GPL");
module_init(ip_vs_sed_init);
module_exit(ip_vs_sed_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs shortest expected delay scheduler");
module_init(ip_vs_sh_init);
module_exit(ip_vs_sh_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs source hashing scheduler");
module_init(ip_vs_twos_init);
module_exit(ip_vs_twos_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs power of twos choice scheduler");
module_init(ip_vs_wlc_init);
module_exit(ip_vs_wlc_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs weighted least connection scheduler");
module_init(ip_vs_wrr_init);
module_exit(ip_vs_wrr_cleanup);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ipvs weighted round-robin scheduler");
return 0;
}
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in nf_conntrack BTF");
+__bpf_kfunc_start_defs();
/* bpf_xdp_ct_alloc - Allocate a new CT entry
*
return nf_ct_change_status_common(nfct, status);
}
-__diag_pop()
+__bpf_kfunc_end_defs();
BTF_SET8_START(nf_ct_kfunc_set)
BTF_ID_FLAGS(func, bpf_xdp_ct_alloc, KF_ACQUIRE | KF_RET_NULL)
EXPORT_SYMBOL_GPL(nf_conntrack_broadcast_help);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Broadcast connection tracking helper");
#include "nf_internals.h"
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("List and change connection tracking table");
struct ctnetlink_list_dump_ctx {
struct nf_conn *last;
MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET));
MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6));
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv4 and IPv6 connection tracking");
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_nat.h>
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in nf_nat BTF");
+__bpf_kfunc_start_defs();
/* bpf_ct_set_nat_info - Set source or destination nat address
*
return nf_nat_setup_info(ct, &range, manip) == NF_DROP ? -ENOMEM : 0;
}
-__diag_pop()
+__bpf_kfunc_end_defs();
BTF_SET8_START(nf_nat_kfunc_set)
BTF_ID_FLAGS(func, bpf_ct_set_nat_info, KF_TRUSTED_ARGS)
}
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Network address translation core");
module_init(nf_nat_init);
module_exit(nf_nat_cleanup);
static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT;
+static bool nf_nat_redirect_ipv6_usable(const struct inet6_ifaddr *ifa, unsigned int scope)
+{
+ unsigned int ifa_addr_type = ipv6_addr_type(&ifa->addr);
+
+ if (ifa_addr_type & IPV6_ADDR_MAPPED)
+ return false;
+
+ if ((ifa->flags & IFA_F_TENTATIVE) && (!(ifa->flags & IFA_F_OPTIMISTIC)))
+ return false;
+
+ if (scope) {
+ unsigned int ifa_scope = ifa_addr_type & IPV6_ADDR_SCOPE_MASK;
+
+ if (!(scope & ifa_scope))
+ return false;
+ }
+
+ return true;
+}
+
unsigned int
nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range,
unsigned int hooknum)
if (hooknum == NF_INET_LOCAL_OUT) {
newdst.in6 = loopback_addr;
} else {
+ unsigned int scope = ipv6_addr_scope(&ipv6_hdr(skb)->daddr);
struct inet6_dev *idev;
- struct inet6_ifaddr *ifa;
bool addr = false;
idev = __in6_dev_get(skb->dev);
if (idev != NULL) {
+ const struct inet6_ifaddr *ifa;
+
read_lock_bh(&idev->lock);
list_for_each_entry(ifa, &idev->addr_list, if_list) {
+ if (!nf_nat_redirect_ipv6_usable(ifa, scope))
+ continue;
+
newdst.in6 = ifa->addr;
addr = true;
break;
return ret;
}
+static void nft_setelem_catchall_destroy(struct nft_set_elem_catchall *catchall)
+{
+ list_del_rcu(&catchall->list);
+ kfree_rcu(catchall, rcu);
+}
+
static void nft_setelem_catchall_remove(const struct net *net,
const struct nft_set *set,
struct nft_elem_priv *elem_priv)
list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
if (catchall->elem == elem_priv) {
- list_del_rcu(&catchall->list);
- kfree_rcu(catchall, rcu);
+ nft_setelem_catchall_destroy(catchall);
break;
}
}
unsigned int gc_seq,
bool sync)
{
- struct nft_set_elem_catchall *catchall;
+ struct nft_set_elem_catchall *catchall, *next;
const struct nft_set *set = gc->set;
+ struct nft_elem_priv *elem_priv;
struct nft_set_ext *ext;
- list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
+ list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
ext = nft_set_elem_ext(set, catchall->elem);
if (!nft_set_elem_expired(ext))
if (!gc)
return NULL;
- nft_trans_gc_elem_add(gc, catchall->elem);
+ elem_priv = catchall->elem;
+ if (sync) {
+ nft_setelem_data_deactivate(gc->net, gc->set, elem_priv);
+ nft_setelem_catchall_destroy(catchall);
+ }
+
+ nft_trans_gc_elem_add(gc, elem_priv);
}
return gc;
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_DESCRIPTION("Framework for packet filtering and classification");
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFTABLES);
module_exit(nfnl_osf_fini);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Passive OS fingerprint matching");
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF);
module_exit(nft_chain_nat_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("nftables network address translation support");
#ifdef CONFIG_NF_TABLES_IPV4
MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat");
#endif
EXPORT_SYMBOL_GPL(nft_fib_reduce);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Query routing table from nftables");
MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_DESCRIPTION("nftables netdev packet forwarding support");
MODULE_ALIAS_NFT_AF_EXPR(5, "fwd");
{
struct recent_table *t = pde_data(file_inode(file));
struct recent_entry *e;
- char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:5afe:c0de")];
+ char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:255.255.255.255")];
const char *c = buf;
union nf_inet_addr addr = {};
u_int16_t family;
module_init(netlink_diag_init);
module_exit(netlink_diag_exit);
+MODULE_DESCRIPTION("Netlink-based socket monitoring/diagnostic interface (sock_diag)");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 16 /* AF_NETLINK */);
if (err)
return err;
- nf_conn_act_ct_ext_add(ct);
+ nf_conn_act_ct_ext_add(skb, ct, ctinfo);
} else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
labels_nonzero(&info->labels.mask)) {
err = ovs_ct_set_labels(ct, key, &info->labels.value,
conn->idle_timestamp = jiffies;
if (atomic_dec_and_test(&conn->active))
rxrpc_set_service_reap_timer(conn->rxnet,
- jiffies + rxrpc_connection_expiry);
+ jiffies + rxrpc_connection_expiry * HZ);
}
rxrpc_put_call(call, rxrpc_call_put_io_thread);
struct rxrpc_local *local =
container_of(timer, struct rxrpc_local, client_conn_reap_timer);
- if (local->kill_all_client_conns &&
+ if (!local->kill_all_client_conns &&
test_and_set_bit(RXRPC_CLIENT_CONN_REAP_TIMER, &local->client_conn_flags))
rxrpc_wake_up_io_thread(local);
}
}
} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
if (unlikely(!rcu_access_pointer(a->goto_chain))) {
- net_warn_ratelimited("can't go to NULL chain!\n");
+ tcf_set_drop_reason(res, SKB_DROP_REASON_TC_ERROR);
return TC_ACT_SHOT;
}
tcf_action_goto_chain_exec(a, res);
entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir];
}
+static void tcf_ct_flow_ct_ext_ifidx_update(struct flow_offload *entry)
+{
+ struct nf_conn_act_ct_ext *act_ct_ext;
+
+ act_ct_ext = nf_conn_act_ct_ext_find(entry->ct);
+ if (act_ct_ext) {
+ tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL);
+ tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY);
+ }
+}
+
static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft,
struct nf_conn *ct,
bool tcp, bool bidirectional)
else
ctinfo = IP_CT_ESTABLISHED_REPLY;
+ nf_conn_act_ct_ext_fill(skb, ct, ctinfo);
+ tcf_ct_flow_ct_ext_ifidx_update(flow);
flow_offload_refresh(nf_ft, flow, force_refresh);
if (!test_bit(IPS_ASSURED_BIT, &ct->status)) {
/* Process this flow in SW to allow promoting to ASSURED */
tcf_ct_act_set_labels(ct, p->labels, p->labels_mask);
if (!nf_ct_is_confirmed(ct))
- nf_conn_act_ct_ext_add(ct);
+ nf_conn_act_ct_ext_add(skb, ct, ctinfo);
/* This will take care of sending queued events
* even if the connection is already confirmed.
module_init(gate_init_module);
module_exit(gate_cleanup_module);
+MODULE_DESCRIPTION("TC gate action");
MODULE_LICENSE("GPL v2");
int act_index,
u32 *last_executed_chain)
{
+ u32 orig_reason = res->drop_reason;
#ifdef CONFIG_NET_CLS_ACT
const int max_reclassify_loop = 16;
const struct tcf_proto *first_tp;
goto reset;
}
#endif
- if (err >= 0)
+ if (err >= 0) {
+ /* Policy drop or drop reason is over-written by
+ * classifiers with a bogus value(0) */
+ if (err == TC_ACT_SHOT &&
+ res->drop_reason == SKB_NOT_DROPPED_YET)
+ tcf_set_drop_reason(res, orig_reason);
return err;
+ }
}
if (unlikely(n)) {
module_init(init_basic)
module_exit(exit_basic)
+MODULE_DESCRIPTION("TC basic classifier");
MODULE_LICENSE("GPL");
module_init(init_cgroup_cls);
module_exit(exit_cgroup_cls);
+MODULE_DESCRIPTION("TC cgroup classifier");
MODULE_LICENSE("GPL");
module_init(init_fw)
module_exit(exit_fw)
+MODULE_DESCRIPTION("SKB mark based TC classifier");
MODULE_LICENSE("GPL");
module_init(init_route4)
module_exit(exit_route4)
+MODULE_DESCRIPTION("Routing table realm based TC classifier");
MODULE_LICENSE("GPL");
module_init(init_u32)
module_exit(exit_u32)
+MODULE_DESCRIPTION("Universal 32bit based TC Classifier");
MODULE_LICENSE("GPL");
module_init(cbs_module_init)
module_exit(cbs_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Credit Based shaper");
module_exit(choke_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Choose and keep responsive flows scheduler");
module_init(drr_init);
module_exit(drr_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Deficit Round Robin scheduler");
module_init(etf_module_init)
module_exit(etf_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Earliest TxTime First (ETF) qdisc");
module_init(ets_init);
module_exit(ets_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Enhanced Transmission Selection(ETS) scheduler");
return q ? : ERR_PTR(err);
}
EXPORT_SYMBOL(fifo_create_dflt);
+MODULE_DESCRIPTION("Single queue packet and byte based First In First Out(P/BFIFO) scheduler");
[TCA_FQ_TIMER_SLACK] = { .type = NLA_U32 },
[TCA_FQ_HORIZON] = { .type = NLA_U32 },
[TCA_FQ_HORIZON_DROP] = { .type = NLA_U8 },
- [TCA_FQ_PRIOMAP] = {
- .type = NLA_BINARY,
- .len = sizeof(struct tc_prio_qopt),
- },
- [TCA_FQ_WEIGHTS] = {
- .type = NLA_BINARY,
- .len = FQ_BANDS * sizeof(s32),
- },
+ [TCA_FQ_PRIOMAP] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_prio_qopt)),
+ [TCA_FQ_WEIGHTS] = NLA_POLICY_EXACT_LEN(FQ_BANDS * sizeof(s32)),
};
/* compress a u8 array with all elems <= 3 to an array of 2-bit fields */
module_exit(gred_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Generic Random Early Detection qdisc");
}
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Hierarchical Fair Service Curve scheduler");
module_init(hfsc_init);
module_exit(hfsc_cleanup);
module_init(htb_module_init)
module_exit(htb_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Hierarchical Token Bucket scheduler");
MODULE_ALIAS("sch_clsact");
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Ingress and clsact based ingress and egress qdiscs");
module_exit(mqprio_module_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Classful multiqueue prio qdisc");
EXPORT_SYMBOL_GPL(mqprio_fp_to_offload);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Shared mqprio qdisc code currently between taprio and mqprio");
module_exit(multiq_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Multi queue to hardware queue mapping qdisc");
module_init(netem_module_init)
module_exit(netem_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Network characteristics emulator qdisc");
module_init(plug_module_init)
module_exit(plug_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Qdisc to plug and unplug traffic via netlink control");
module_exit(prio_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Simple 3-band priority qdisc");
module_init(qfq_init);
module_exit(qfq_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Quick Fair Queueing Plus qdisc");
module_exit(red_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Random Early Detection qdisc");
module_init(sfq_module_init)
module_exit(sfq_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Stochastic Fairness qdisc");
module_exit(skbprio_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SKB priority based scheduling qdisc");
module_init(taprio_module_init);
module_exit(taprio_module_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Time Aware Priority qdisc");
module_init(tbf_module_init)
module_exit(tbf_module_exit)
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Token Bucket Filter qdisc");
module_exit(teql_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("True (or trivial) link equalizer qdisc");
if (!smc->use_fallback) {
rc = smc_close_active(smc);
- sock_set_flag(sk, SOCK_DEAD);
+ smc_sock_set_flag(sk, SOCK_DEAD);
sk->sk_shutdown |= SHUTDOWN_MASK;
} else {
if (sk->sk_state != SMC_CLOSED) {
if (new_clcsock)
sock_release(new_clcsock);
new_sk->sk_state = SMC_CLOSED;
- sock_set_flag(new_sk, SOCK_DEAD);
+ smc_sock_set_flag(new_sk, SOCK_DEAD);
sock_put(new_sk); /* final */
*new_smc = NULL;
goto out;
int smc_nl_enable_hs_limitation(struct sk_buff *skb, struct genl_info *info);
int smc_nl_disable_hs_limitation(struct sk_buff *skb, struct genl_info *info);
+static inline void smc_sock_set_flag(struct sock *sk, enum sock_flags flag)
+{
+ set_bit(flag, &sk->sk_flags);
+}
+
#endif /* __SMC_H */
{
struct smc_cdc_tx_pend *cdcpend = (struct smc_cdc_tx_pend *)pnd_snd;
struct smc_connection *conn = cdcpend->conn;
+ struct smc_buf_desc *sndbuf_desc;
struct smc_sock *smc;
int diff;
+ sndbuf_desc = conn->sndbuf_desc;
smc = container_of(conn, struct smc_sock, conn);
bh_lock_sock(&smc->sk);
- if (!wc_status) {
- diff = smc_curs_diff(cdcpend->conn->sndbuf_desc->len,
+ if (!wc_status && sndbuf_desc) {
+ diff = smc_curs_diff(sndbuf_desc->len,
&cdcpend->conn->tx_curs_fin,
&cdcpend->cursor);
/* sndbuf_space is decreased in smc_sendmsg */
union smc_host_cursor cfed;
int rc;
- if (unlikely(!READ_ONCE(conn->sndbuf_desc)))
- return -ENOBUFS;
-
smc_cdc_add_pending_send(conn, pend);
conn->tx_cdc_seq++;
smc->sk.sk_shutdown |= RCV_SHUTDOWN;
if (smc->clcsock && smc->clcsock->sk)
smc->clcsock->sk->sk_shutdown |= RCV_SHUTDOWN;
- sock_set_flag(&smc->sk, SOCK_DONE);
+ smc_sock_set_flag(&smc->sk, SOCK_DONE);
sock_hold(&smc->sk); /* sock_put in close_work */
if (!queue_work(smc_close_wq, &conn->close_work))
sock_put(&smc->sk);
struct sock *sk = &smc->sk;
release_sock(sk);
- cancel_work_sync(&smc->conn.close_work);
+ if (cancel_work_sync(&smc->conn.close_work))
+ sock_put(sk);
cancel_delayed_work_sync(&smc->conn.tx_work);
lock_sock(sk);
}
break;
}
- sock_set_flag(sk, SOCK_DEAD);
+ smc_sock_set_flag(sk, SOCK_DEAD);
sk->sk_state_change(sk);
if (release_clcsock) {
* Therefore, __weak is needed to ensure that the call is still
* emitted, by telling the compiler that we don't know what the
* function might eventually be.
- *
- * __diag_* below are needed to dismiss the missing prototype warning.
*/
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "A fmod_ret entry point for BPF programs");
+__bpf_hook_start();
__weak noinline int update_socket_protocol(int family, int type, int protocol)
{
return protocol;
}
-__diag_pop();
+__bpf_hook_end();
int __sys_socket(int family, int type, int protocol)
{
const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = {
[TIPC_NLA_LINK_UNSPEC] = { .type = NLA_UNSPEC },
- [TIPC_NLA_LINK_NAME] = { .type = NLA_STRING,
+ [TIPC_NLA_LINK_NAME] = { .type = NLA_NUL_STRING,
.len = TIPC_MAX_LINK_NAME },
[TIPC_NLA_LINK_MTU] = { .type = NLA_U32 },
[TIPC_NLA_LINK_BROADCAST] = { .type = NLA_FLAG },
const struct nla_policy tipc_nl_bearer_policy[TIPC_NLA_BEARER_MAX + 1] = {
[TIPC_NLA_BEARER_UNSPEC] = { .type = NLA_UNSPEC },
- [TIPC_NLA_BEARER_NAME] = { .type = NLA_STRING,
+ [TIPC_NLA_BEARER_NAME] = { .type = NLA_NUL_STRING,
.len = TIPC_MAX_BEARER_NAME },
[TIPC_NLA_BEARER_PROP] = { .type = NLA_NESTED },
[TIPC_NLA_BEARER_DOMAIN] = { .type = NLA_U32 }
hdr->dst_port = cpu_to_le32(dst_port);
hdr->flags = cpu_to_le32(info->flags);
hdr->len = cpu_to_le32(payload_len);
+ hdr->buf_alloc = cpu_to_le32(0);
+ hdr->fwd_cnt = cpu_to_le32(0);
}
static void virtio_transport_copy_nonlinear_skb(const struct sk_buff *skb,
vsk->peer_shutdown |= RCV_SHUTDOWN;
if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SHUTDOWN_SEND)
vsk->peer_shutdown |= SEND_SHUTDOWN;
- if (vsk->peer_shutdown == SHUTDOWN_MASK &&
- vsock_stream_has_data(vsk) <= 0 &&
- !sock_flag(sk, SOCK_DONE)) {
- (void)virtio_transport_reset(vsk, NULL);
- virtio_transport_do_close(vsk, true);
+ if (vsk->peer_shutdown == SHUTDOWN_MASK) {
+ if (vsock_stream_has_data(vsk) <= 0 && !sock_flag(sk, SOCK_DONE)) {
+ (void)virtio_transport_reset(vsk, NULL);
+ virtio_transport_do_close(vsk, true);
+ }
+ /* Remove this socket anyway because the remote peer sent
+ * the shutdown. This way a new connection will succeed
+ * if the remote peer uses the same source port,
+ * even if the old socket is still unreleased, but now disconnected.
+ */
+ vsock_remove_sock(vsk);
}
if (le32_to_cpu(virtio_vsock_hdr(skb)->flags))
sk->sk_state_change(sk);
int link;
};
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in xfrm_interface BTF");
+__bpf_kfunc_start_defs();
/* bpf_skb_get_xfrm_info - Get XFRM metadata
*
return 0;
}
-__diag_pop()
+__bpf_kfunc_end_defs();
BTF_SET8_START(xfrm_ifc_kfunc_set)
BTF_ID_FLAGS(func, bpf_skb_get_xfrm_info)
static const char * const devlink_port_fn_attr_cap_strmap[] = {
[0] = "roce-bit",
[1] = "migratable-bit",
+ [2] = "ipsec-crypto-bit",
+ [3] = "ipsec-packet-bit",
};
const char *devlink_port_fn_attr_cap_str(enum devlink_port_fn_attr_cap value)
/* Common nested types */
/* ============== NFSD_CMD_RPC_STATUS_GET ============== */
/* NFSD_CMD_RPC_STATUS_GET - dump */
-void nfsd_rpc_status_get_list_free(struct nfsd_rpc_status_get_list *rsp)
+int nfsd_rpc_status_get_rsp_dump_parse(const struct nlmsghdr *nlh, void *data)
{
- struct nfsd_rpc_status_get_list *next = rsp;
+ struct nfsd_rpc_status_get_rsp_dump *dst;
+ struct ynl_parse_arg *yarg = data;
+ unsigned int n_compound_ops = 0;
+ const struct nlattr *attr;
+ int i;
+
+ dst = yarg->data;
+
+ if (dst->compound_ops)
+ return ynl_error_parse(yarg, "attribute already present (rpc-status.compound-ops)");
+
+ mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+ unsigned int type = mnl_attr_get_type(attr);
+
+ if (type == NFSD_A_RPC_STATUS_XID) {
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+ dst->_present.xid = 1;
+ dst->xid = mnl_attr_get_u32(attr);
+ } else if (type == NFSD_A_RPC_STATUS_FLAGS) {
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+ dst->_present.flags = 1;
+ dst->flags = mnl_attr_get_u32(attr);
+ } else if (type == NFSD_A_RPC_STATUS_PROG) {
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+ dst->_present.prog = 1;
+ dst->prog = mnl_attr_get_u32(attr);
+ } else if (type == NFSD_A_RPC_STATUS_VERSION) {
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+ dst->_present.version = 1;
+ dst->version = mnl_attr_get_u8(attr);
+ } else if (type == NFSD_A_RPC_STATUS_PROC) {
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+ dst->_present.proc = 1;
+ dst->proc = mnl_attr_get_u32(attr);
+ } else if (type == NFSD_A_RPC_STATUS_SERVICE_TIME) {
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+ dst->_present.service_time = 1;
+ dst->service_time = mnl_attr_get_u64(attr);
+ } else if (type == NFSD_A_RPC_STATUS_SADDR4) {
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+ dst->_present.saddr4 = 1;
+ dst->saddr4 = mnl_attr_get_u32(attr);
+ } else if (type == NFSD_A_RPC_STATUS_DADDR4) {
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+ dst->_present.daddr4 = 1;
+ dst->daddr4 = mnl_attr_get_u32(attr);
+ } else if (type == NFSD_A_RPC_STATUS_SADDR6) {
+ unsigned int len;
+
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+
+ len = mnl_attr_get_payload_len(attr);
+ dst->_present.saddr6_len = len;
+ dst->saddr6 = malloc(len);
+ memcpy(dst->saddr6, mnl_attr_get_payload(attr), len);
+ } else if (type == NFSD_A_RPC_STATUS_DADDR6) {
+ unsigned int len;
+
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+
+ len = mnl_attr_get_payload_len(attr);
+ dst->_present.daddr6_len = len;
+ dst->daddr6 = malloc(len);
+ memcpy(dst->daddr6, mnl_attr_get_payload(attr), len);
+ } else if (type == NFSD_A_RPC_STATUS_SPORT) {
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+ dst->_present.sport = 1;
+ dst->sport = mnl_attr_get_u16(attr);
+ } else if (type == NFSD_A_RPC_STATUS_DPORT) {
+ if (ynl_attr_validate(yarg, attr))
+ return MNL_CB_ERROR;
+ dst->_present.dport = 1;
+ dst->dport = mnl_attr_get_u16(attr);
+ } else if (type == NFSD_A_RPC_STATUS_COMPOUND_OPS) {
+ n_compound_ops++;
+ }
+ }
+
+ if (n_compound_ops) {
+ dst->compound_ops = calloc(n_compound_ops, sizeof(*dst->compound_ops));
+ dst->n_compound_ops = n_compound_ops;
+ i = 0;
+ mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) {
+ if (mnl_attr_get_type(attr) == NFSD_A_RPC_STATUS_COMPOUND_OPS) {
+ dst->compound_ops[i] = mnl_attr_get_u32(attr);
+ i++;
+ }
+ }
+ }
+
+ return MNL_CB_OK;
+}
+
+void
+nfsd_rpc_status_get_rsp_list_free(struct nfsd_rpc_status_get_rsp_list *rsp)
+{
+ struct nfsd_rpc_status_get_rsp_list *next = rsp;
while ((void *)next != YNL_LIST_END) {
rsp = next;
}
}
-struct nfsd_rpc_status_get_list *nfsd_rpc_status_get_dump(struct ynl_sock *ys)
+struct nfsd_rpc_status_get_rsp_list *
+nfsd_rpc_status_get_dump(struct ynl_sock *ys)
{
struct ynl_dump_state yds = {};
struct nlmsghdr *nlh;
int err;
yds.ys = ys;
- yds.alloc_sz = sizeof(struct nfsd_rpc_status_get_list);
- yds.cb = nfsd_rpc_status_get_rsp_parse;
+ yds.alloc_sz = sizeof(struct nfsd_rpc_status_get_rsp_list);
+ yds.cb = nfsd_rpc_status_get_rsp_dump_parse;
yds.rsp_cmd = NFSD_CMD_RPC_STATUS_GET;
yds.rsp_policy = &nfsd_rpc_status_nest;
return yds.first;
free_list:
- nfsd_rpc_status_get_list_free(yds.first);
+ nfsd_rpc_status_get_rsp_list_free(yds.first);
return NULL;
}
/* Common nested types */
/* ============== NFSD_CMD_RPC_STATUS_GET ============== */
/* NFSD_CMD_RPC_STATUS_GET - dump */
-struct nfsd_rpc_status_get_list {
- struct nfsd_rpc_status_get_list *next;
- struct nfsd_rpc_status_get_rsp obj __attribute__ ((aligned (8)));
+struct nfsd_rpc_status_get_rsp_dump {
+ struct {
+ __u32 xid:1;
+ __u32 flags:1;
+ __u32 prog:1;
+ __u32 version:1;
+ __u32 proc:1;
+ __u32 service_time:1;
+ __u32 saddr4:1;
+ __u32 daddr4:1;
+ __u32 saddr6_len;
+ __u32 daddr6_len;
+ __u32 sport:1;
+ __u32 dport:1;
+ } _present;
+
+ __u32 xid /* big-endian */;
+ __u32 flags;
+ __u32 prog;
+ __u8 version;
+ __u32 proc;
+ __s64 service_time;
+ __u32 saddr4 /* big-endian */;
+ __u32 daddr4 /* big-endian */;
+ void *saddr6;
+ void *daddr6;
+ __u16 sport /* big-endian */;
+ __u16 dport /* big-endian */;
+ unsigned int n_compound_ops;
+ __u32 *compound_ops;
+};
+
+struct nfsd_rpc_status_get_rsp_list {
+ struct nfsd_rpc_status_get_rsp_list *next;
+ struct nfsd_rpc_status_get_rsp_dump obj __attribute__((aligned(8)));
};
-void nfsd_rpc_status_get_list_free(struct nfsd_rpc_status_get_list *rsp);
+void
+nfsd_rpc_status_get_rsp_list_free(struct nfsd_rpc_status_get_rsp_list *rsp);
-struct nfsd_rpc_status_get_list *nfsd_rpc_status_get_dump(struct ynl_sock *ys);
+struct nfsd_rpc_status_get_rsp_list *
+nfsd_rpc_status_get_dump(struct ynl_sock *ys);
#endif /* _LINUX_NFSD_GEN_H */
import argparse
import collections
+import filecmp
import os
import re
import shutil
if out_file is None:
self._out = os.sys.stdout
else:
- self._out = tempfile.TemporaryFile('w+')
+ self._out = tempfile.NamedTemporaryFile('w+')
self._out_file = out_file
def __del__(self):
def close_out_file(self):
if self._out == os.sys.stdout:
return
+ # Avoid modifying the file if contents didn't change
+ self._out.flush()
+ if os.path.isfile(self._out_file) and filecmp.cmp(self._out.name, self._out_file, shallow=False):
+ return
with open(self._out_file, 'w+') as out_file:
self._out.seek(0)
shutil.copyfileobj(self._out, out_file)
int b;
};
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
- "Global functions as their definitions will be in bpf_testmod.ko BTF");
+__bpf_hook_start();
noinline int
bpf_testmod_test_struct_arg_1(struct bpf_testmod_struct_arg_2 a, int b, int c) {
}
EXPORT_SYMBOL_GPL(bpf_fentry_shadow_test);
-__diag_pop();
+__bpf_hook_end();
static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
.attr = { .name = "bpf_testmod", .mode = 0666, },
static int create_hash(void)
{
- struct bpf_map_create_opts map_opts = {
- .sz = sizeof(map_opts),
- .map_flags = BPF_F_NO_PREALLOC,
- };
+ LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = BPF_F_NO_PREALLOC);
return map_create(BPF_MAP_TYPE_HASH, "hash", &map_opts);
}
static int create_percpu_hash(void)
{
- struct bpf_map_create_opts map_opts = {
- .sz = sizeof(map_opts),
- .map_flags = BPF_F_NO_PREALLOC,
- };
+ LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = BPF_F_NO_PREALLOC);
return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash", &map_opts);
}
static int create_lru_hash(__u32 type, __u32 map_flags)
{
- struct bpf_map_create_opts map_opts = {
- .sz = sizeof(map_opts),
- .map_flags = map_flags,
- };
+ LIBBPF_OPTS(bpf_map_create_opts, map_opts, .map_flags = map_flags);
return map_create(type, "lru_hash", &map_opts);
}
static int create_hash_of_maps(void)
{
- struct bpf_map_create_opts map_opts = {
- .sz = sizeof(map_opts),
+ LIBBPF_OPTS(bpf_map_create_opts, map_opts,
.map_flags = BPF_F_NO_PREALLOC,
.inner_map_fd = create_small_hash(),
- };
+ );
int ret;
ret = map_create_opts(BPF_MAP_TYPE_HASH_OF_MAPS, "hash_of_maps",
#include <test_progs.h>
#include <bpf/libbpf.h>
#include <bpf/btf.h>
+#include "iters_css_task.skel.h"
#include "cgroup_iter.skel.h"
#include "cgroup_helpers.h"
close(cgrp_fd);
}
+static void test_walk_self_only_css_task(void)
+{
+ struct iters_css_task *skel;
+ int err;
+
+ skel = iters_css_task__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ bpf_program__set_autoload(skel->progs.cgroup_id_printer, true);
+
+ err = iters_css_task__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto cleanup;
+
+ err = join_cgroup(cg_path[CHILD2]);
+ if (!ASSERT_OK(err, "join_cgroup"))
+ goto cleanup;
+
+ skel->bss->target_pid = getpid();
+ snprintf(expected_output, sizeof(expected_output),
+ PROLOGUE "%8llu\n" EPILOGUE, cg_id[CHILD2]);
+ read_from_cgroup_iter(skel->progs.cgroup_id_printer, cg_fd[CHILD2],
+ BPF_CGROUP_ITER_SELF_ONLY, "test_walk_self_only_css_task");
+ ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt");
+cleanup:
+ iters_css_task__destroy(skel);
+}
+
void test_cgroup_iter(void)
{
struct cgroup_iter *skel = NULL;
test_walk_self_only(skel);
if (test__start_subtest("cgroup_iter__dead_self_only"))
test_walk_dead_self_only(skel);
+ if (test__start_subtest("cgroup_iter__self_only_css_task"))
+ test_walk_self_only_css_task();
+
out:
cgroup_iter__destroy(skel);
cleanup_cgroups();
RUN_TESTS(iters_state_safety);
RUN_TESTS(iters_looping);
RUN_TESTS(iters);
+ RUN_TESTS(iters_css_task);
if (env.has_testmod)
RUN_TESTS(iters_testmod_seq);
#include <sys/types.h>
#include <test_progs.h>
-#define TDIR "/sys/kernel/debug"
+/* TDIR must be in a location we can create a directory in. */
+#define TDIR "/tmp/test_bpffs_testdir"
static int read_iter(char *file)
{
if (!ASSERT_OK(err, "mount /"))
goto out;
- err = umount(TDIR);
- if (!ASSERT_OK(err, "umount " TDIR))
+ err = mkdir(TDIR, 0777);
+ /* If the directory already exists we can carry on. It may be left over
+ * from a previous run.
+ */
+ if ((err && errno != EEXIST) && !ASSERT_OK(err, "mkdir " TDIR))
goto out;
err = mount("none", TDIR, "tmpfs", 0, NULL);
rmdir(TDIR "/fs1");
rmdir(TDIR "/fs2");
umount(TDIR);
+ rmdir(TDIR);
exit(err);
}
#include "verifier_movsx.skel.h"
#include "verifier_netfilter_ctx.skel.h"
#include "verifier_netfilter_retcode.skel.h"
+#include "verifier_precision.skel.h"
#include "verifier_prevent_map_lookup.skel.h"
#include "verifier_raw_stack.skel.h"
#include "verifier_raw_tp_writable.skel.h"
void test_verifier_movsx(void) { RUN(verifier_movsx); }
void test_verifier_netfilter_ctx(void) { RUN(verifier_netfilter_ctx); }
void test_verifier_netfilter_retcode(void) { RUN(verifier_netfilter_retcode); }
+void test_verifier_precision(void) { RUN(verifier_precision); }
void test_verifier_prevent_map_lookup(void) { RUN(verifier_prevent_map_lookup); }
void test_verifier_raw_stack(void) { RUN(verifier_raw_stack); }
void test_verifier_raw_tp_writable(void) { RUN(verifier_raw_tp_writable); }
char _license[] SEC("license") = "GPL";
+struct cgroup *bpf_cgroup_acquire(struct cgroup *p) __ksym;
struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym;
void bpf_cgroup_release(struct cgroup *p) __ksym;
return -EPERM;
}
+
+static inline u64 cgroup_id(struct cgroup *cgrp)
+{
+ return cgrp->kn->id;
+}
+
+SEC("?iter/cgroup")
+int cgroup_id_printer(struct bpf_iter__cgroup *ctx)
+{
+ struct seq_file *seq = ctx->meta->seq;
+ struct cgroup *cgrp = ctx->cgroup;
+ struct cgroup_subsys_state *css;
+ struct task_struct *task;
+
+ /* epilogue */
+ if (cgrp == NULL) {
+ BPF_SEQ_PRINTF(seq, "epilogue\n");
+ return 0;
+ }
+
+ /* prologue */
+ if (ctx->meta->seq_num == 0)
+ BPF_SEQ_PRINTF(seq, "prologue\n");
+
+ BPF_SEQ_PRINTF(seq, "%8llu\n", cgroup_id(cgrp));
+
+ css = &cgrp->self;
+ css_task_cnt = 0;
+ bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+ if (task->pid == target_pid)
+ css_task_cnt++;
+ }
+
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int BPF_PROG(iter_css_task_for_each_sleep)
+{
+ u64 cgrp_id = bpf_get_current_cgroup_id();
+ struct cgroup *cgrp = bpf_cgroup_from_id(cgrp_id);
+ struct cgroup_subsys_state *css;
+ struct task_struct *task;
+
+ if (cgrp == NULL)
+ return 0;
+ css = &cgrp->self;
+
+ bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) {
+
+ }
+ bpf_cgroup_release(cgrp);
+ return 0;
+}
return 0;
}
-SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
-__failure __msg("css_task_iter is only allowed in bpf_lsm and bpf iter-s")
+SEC("?fentry/" SYS_PREFIX "sys_getpgid")
+__failure __msg("css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs")
int BPF_PROG(iter_css_task_for_each)
{
u64 cg_id = bpf_get_current_cgroup_id();
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 SUSE LLC */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0xfffffff8 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (87) r2 = -r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 8")
+__naked int bpf_neg(void)
+{
+ asm volatile (
+ "r2 = 8;"
+ "r2 = -r2;"
+ "if r2 != -8 goto 1f;"
+ "r1 = r10;"
+ "r1 += r2;"
+ "1:"
+ "r0 = 0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (d4) r2 = le16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_to_le(void)
+{
+ asm volatile (
+ "r2 = 0;"
+ "r2 = le16 r2;"
+ "if r2 != 0 goto 1f;"
+ "r1 = r10;"
+ "r1 += r2;"
+ "1:"
+ "r0 = 0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (dc) r2 = be16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_to_be(void)
+{
+ asm volatile (
+ "r2 = 0;"
+ "r2 = be16 r2;"
+ "if r2 != 0 goto 1f;"
+ "r1 = r10;"
+ "r1 += r2;"
+ "1:"
+ "r0 = 0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+#if (defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86) || \
+ (defined(__TARGET_ARCH_riscv) && __riscv_xlen == 64) || \
+ defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_s390)) && \
+ __clang_major__ >= 18
+
+SEC("?raw_tp")
+__success __log_level(2)
+__msg("mark_precise: frame0: regs=r2 stack= before 3: (bf) r1 = r10")
+__msg("mark_precise: frame0: regs=r2 stack= before 2: (55) if r2 != 0x0 goto pc+2")
+__msg("mark_precise: frame0: regs=r2 stack= before 1: (d7) r2 = bswap16 r2")
+__msg("mark_precise: frame0: regs=r2 stack= before 0: (b7) r2 = 0")
+__naked int bpf_end_bswap(void)
+{
+ asm volatile (
+ "r2 = 0;"
+ "r2 = bswap16 r2;"
+ "if r2 != 0 goto 1f;"
+ "r1 = r10;"
+ "r1 += r2;"
+ "1:"
+ "r0 = 0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+#endif /* v4 instruction */
.expected_attach_type = BPF_SK_LOOKUP,
.runs = -1,
},
+{
+ "BPF_ST_MEM stack imm sign",
+ /* Check if verifier correctly reasons about sign of an
+ * immediate spilled to stack by BPF_ST instruction.
+ *
+ * fp[-8] = -44;
+ * r0 = fp[-8];
+ * if r0 s< 0 goto ret0;
+ * r0 = -1;
+ * exit;
+ * ret0:
+ * r0 = 0;
+ * exit;
+ */
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, -44),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+ BPF_JMP_IMM(BPF_JSLT, BPF_REG_0, 0, 2),
+ BPF_MOV64_IMM(BPF_REG_0, -1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ /* Use prog type that requires return value in range [0, 1] */
+ .prog_type = BPF_PROG_TYPE_SK_LOOKUP,
+ .expected_attach_type = BPF_SK_LOOKUP,
+ .result = VERBOSE_ACCEPT,
+ .runs = -1,
+ .errstr = "0: (7a) *(u64 *)(r10 -8) = -44 ; R10=fp0 fp-8_w=-44\
+ 2: (c5) if r0 s< 0x0 goto pc+2\
+ R0_w=-44",
+},
static void read_args(int argc, char *argv[])
{
- char opt;
+ int opt;
while ((opt = getopt(argc, argv, "mh")) != -1) {
switch (opt) {
case $ret in
0)
all_skipped=false
- [ $exitcode=$ksft_skip ] && exitcode=0
+ [ $exitcode -eq $ksft_skip ] && exitcode=0
;;
$ksft_skip)
[ $all_skipped = true ] && exitcode=$ksft_skip
close(epollfd);
}
+/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */
+int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type)
+{
+ struct sockaddr_vm sa_client = {
+ .svm_family = AF_VSOCK,
+ .svm_cid = VMADDR_CID_ANY,
+ .svm_port = bind_port,
+ };
+ struct sockaddr_vm sa_server = {
+ .svm_family = AF_VSOCK,
+ .svm_cid = cid,
+ .svm_port = port,
+ };
+
+ int client_fd, ret;
+
+ client_fd = socket(AF_VSOCK, type, 0);
+ if (client_fd < 0) {
+ perror("socket");
+ exit(EXIT_FAILURE);
+ }
+
+ if (bind(client_fd, (struct sockaddr *)&sa_client, sizeof(sa_client))) {
+ perror("bind");
+ exit(EXIT_FAILURE);
+ }
+
+ timeout_begin(TIMEOUT);
+ do {
+ ret = connect(client_fd, (struct sockaddr *)&sa_server, sizeof(sa_server));
+ timeout_check("connect");
+ } while (ret < 0 && errno == EINTR);
+ timeout_end();
+
+ if (ret < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+
+ return client_fd;
+}
+
/* Connect to <cid, port> and return the file descriptor. */
static int vsock_connect(unsigned int cid, unsigned int port, int type)
{
control_expectln("LISTENING");
fd = socket(AF_VSOCK, type, 0);
+ if (fd < 0) {
+ perror("socket");
+ exit(EXIT_FAILURE);
+ }
timeout_begin(TIMEOUT);
do {
return vsock_connect(cid, port, SOCK_SEQPACKET);
}
-/* Listen on <cid, port> and return the first incoming connection. The remote
- * address is stored to clientaddrp. clientaddrp may be NULL.
- */
-static int vsock_accept(unsigned int cid, unsigned int port,
- struct sockaddr_vm *clientaddrp, int type)
+/* Listen on <cid, port> and return the file descriptor. */
+static int vsock_listen(unsigned int cid, unsigned int port, int type)
{
union {
struct sockaddr sa;
.svm_cid = cid,
},
};
- union {
- struct sockaddr sa;
- struct sockaddr_vm svm;
- } clientaddr;
- socklen_t clientaddr_len = sizeof(clientaddr.svm);
int fd;
- int client_fd;
- int old_errno;
fd = socket(AF_VSOCK, type, 0);
+ if (fd < 0) {
+ perror("socket");
+ exit(EXIT_FAILURE);
+ }
if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
perror("bind");
exit(EXIT_FAILURE);
}
+ return fd;
+}
+
+/* Listen on <cid, port> and return the first incoming connection. The remote
+ * address is stored to clientaddrp. clientaddrp may be NULL.
+ */
+static int vsock_accept(unsigned int cid, unsigned int port,
+ struct sockaddr_vm *clientaddrp, int type)
+{
+ union {
+ struct sockaddr sa;
+ struct sockaddr_vm svm;
+ } clientaddr;
+ socklen_t clientaddr_len = sizeof(clientaddr.svm);
+ int fd, client_fd, old_errno;
+
+ fd = vsock_listen(cid, port, type);
+
control_writeln("LISTENING");
timeout_begin(TIMEOUT);
return vsock_accept(cid, port, clientaddrp, SOCK_STREAM);
}
+int vsock_stream_listen(unsigned int cid, unsigned int port)
+{
+ return vsock_listen(cid, port, SOCK_STREAM);
+}
+
int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
struct sockaddr_vm *clientaddrp)
{
void init_signals(void);
unsigned int parse_cid(const char *str);
int vsock_stream_connect(unsigned int cid, unsigned int port);
+int vsock_bind_connect(unsigned int cid, unsigned int port,
+ unsigned int bind_port, int type);
int vsock_seqpacket_connect(unsigned int cid, unsigned int port);
int vsock_stream_accept(unsigned int cid, unsigned int port,
struct sockaddr_vm *clientaddrp);
+int vsock_stream_listen(unsigned int cid, unsigned int port);
int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
struct sockaddr_vm *clientaddrp);
void vsock_wait_remote_close(int fd);
close(fd);
}
+static void test_double_bind_connect_server(const struct test_opts *opts)
+{
+ int listen_fd, client_fd, i;
+ struct sockaddr_vm sa_client;
+ socklen_t socklen_client = sizeof(sa_client);
+
+ listen_fd = vsock_stream_listen(VMADDR_CID_ANY, 1234);
+
+ for (i = 0; i < 2; i++) {
+ control_writeln("LISTENING");
+
+ timeout_begin(TIMEOUT);
+ do {
+ client_fd = accept(listen_fd, (struct sockaddr *)&sa_client,
+ &socklen_client);
+ timeout_check("accept");
+ } while (client_fd < 0 && errno == EINTR);
+ timeout_end();
+
+ if (client_fd < 0) {
+ perror("accept");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Waiting for remote peer to close connection */
+ vsock_wait_remote_close(client_fd);
+ }
+
+ close(listen_fd);
+}
+
+static void test_double_bind_connect_client(const struct test_opts *opts)
+{
+ int i, client_fd;
+
+ for (i = 0; i < 2; i++) {
+ /* Wait until server is ready to accept a new connection */
+ control_expectln("LISTENING");
+
+ client_fd = vsock_bind_connect(opts->peer_cid, 1234, 4321, SOCK_STREAM);
+
+ close(client_fd);
+ }
+}
+
static struct test_case test_cases[] = {
{
.name = "SOCK_STREAM connection reset",
.run_client = test_stream_msgzcopy_empty_errq_client,
.run_server = test_stream_msgzcopy_empty_errq_server,
},
+ {
+ .name = "SOCK_STREAM double bind connect",
+ .run_client = test_double_bind_connect_client,
+ .run_server = test_double_bind_connect_server,
+ },
{},
};