*/
off = offsetof(struct bpf_array, ptrs);
emit_a64_mov_i64(tmp, off, ctx);
- emit(A64_LDR64(tmp, r2, tmp), ctx);
- emit(A64_LDR64(prg, tmp, r3), ctx);
+ emit(A64_ADD(1, tmp, r2, tmp), ctx);
+ emit(A64_LSL(1, prg, r3, 3), ctx);
+ emit(A64_LDR64(prg, tmp, prg), ctx);
emit(A64_CBZ(1, prg, jmp_offset), ctx);
/* goto *(prog->bpf_func + prologue_size); */
mv88e6xxx_g1_stats_read(chip, reg, &low);
if (s->sizeof_stat == 8)
mv88e6xxx_g1_stats_read(chip, reg + 1, &high);
+ break;
+ default:
+ return UINT64_MAX;
}
value = (((u64)high) << 16) | low;
return value;
static int hw_atl_a0_hw_offload_set(struct aq_hw_s *self,
struct aq_nic_cfg_s *aq_nic_cfg)
{
- int err = 0;
-
/* TX checksums offloads*/
tpo_ipv4header_crc_offload_en_set(self, 1);
tpo_tcp_udp_crc_offload_en_set(self, 1);
- if (err < 0)
- goto err_exit;
/* RX checksums offloads*/
rpo_ipv4header_crc_offload_en_set(self, 1);
rpo_tcp_udp_crc_offload_en_set(self, 1);
- if (err < 0)
- goto err_exit;
/* LSO offloads*/
tdm_large_send_offload_en_set(self, 0xFFFFFFFFU);
- if (err < 0)
- goto err_exit;
-
- err = aq_hw_err_from_flags(self);
-err_exit:
- return err;
+ return aq_hw_err_from_flags(self);
}
static int hw_atl_a0_hw_init_tx_path(struct aq_hw_s *self)
static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
struct aq_nic_cfg_s *aq_nic_cfg)
{
- int err = 0;
unsigned int i;
/* TX checksums offloads*/
tpo_ipv4header_crc_offload_en_set(self, 1);
tpo_tcp_udp_crc_offload_en_set(self, 1);
- if (err < 0)
- goto err_exit;
/* RX checksums offloads*/
rpo_ipv4header_crc_offload_en_set(self, 1);
rpo_tcp_udp_crc_offload_en_set(self, 1);
- if (err < 0)
- goto err_exit;
/* LSO offloads*/
tdm_large_send_offload_en_set(self, 0xFFFFFFFFU);
- if (err < 0)
- goto err_exit;
/* LRO offloads */
{
rpo_lro_en_set(self, aq_nic_cfg->is_lro ? 0xFFFFFFFFU : 0U);
}
- err = aq_hw_err_from_flags(self);
-
-err_exit:
- return err;
+ return aq_hw_err_from_flags(self);
}
static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self)
int port = 0;
if (msi_x) {
- int nreq = dev->caps.num_ports * num_online_cpus() + 1;
-
- nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
- nreq);
- if (nreq > MAX_MSIX)
- nreq = MAX_MSIX;
+ int nreq = min3(dev->caps.num_ports *
+ (int)num_online_cpus() + 1,
+ dev->caps.num_eqs - dev->caps.reserved_eqs,
+ MAX_MSIX);
entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
if (!entries)
void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn);
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv);
void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv);
int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
ptys2ethtool_supported_port(link_ksettings, eth_proto_cap);
ptys2ethtool_supported_link(supported, eth_proto_cap);
ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
- ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Asym_Pause);
}
static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
unsigned long *advertising = link_ksettings->link_modes.advertising;
ptys2ethtool_adver_link(advertising, eth_proto_cap);
- if (tx_pause)
+ if (rx_pause)
ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
if (tx_pause ^ rx_pause)
ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Asym_Pause);
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5_core_dev *mdev = priv->mdev;
u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
+ u32 rx_pause = 0;
+ u32 tx_pause = 0;
u32 eth_proto_cap;
u32 eth_proto_admin;
u32 eth_proto_lp;
an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
an_status = MLX5_GET(ptys_reg, out, an_status);
+ mlx5_query_port_pause(mdev, &rx_pause, &tx_pause);
+
ethtool_link_ksettings_zero_link_mode(link_ksettings, supported);
ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
get_supported(eth_proto_cap, link_ksettings);
- get_advertising(eth_proto_admin, 0, 0, link_ksettings);
+ get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings);
get_speed_duplex(netdev, eth_proto_oper, link_ksettings);
eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
mlx5e_destroy_flow_table(&ttc->ft);
}
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv, u32 underlay_qpn)
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv)
{
struct mlx5e_ttc_table *ttc = &priv->fs.ttc;
struct mlx5_flow_table_attr ft_attr = {};
ft_attr.max_fte = MLX5E_TTC_TABLE_SIZE;
ft_attr.level = MLX5E_TTC_FT_LEVEL;
ft_attr.prio = MLX5E_NIC_PRIO;
- ft_attr.underlay_qpn = underlay_qpn;
ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr);
if (IS_ERR(ft->t)) {
priv->netdev->hw_features &= ~NETIF_F_NTUPLE;
}
- err = mlx5e_create_ttc_table(priv, 0);
+ err = mlx5e_create_ttc_table(priv);
if (err) {
netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n",
err);
new_channels.params = priv->channels.params;
new_channels.params.num_tc = tc ? tc : 1;
- if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
priv->channels.params = new_channels.params;
goto out;
}
#include "eswitch.h"
int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
- struct mlx5_flow_table *ft)
+ struct mlx5_flow_table *ft, u32 underlay_qpn)
{
u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)] = {0};
u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {0};
if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
- ft->underlay_qpn == 0)
+ underlay_qpn == 0)
return 0;
MLX5_SET(set_flow_table_root_in, in, opcode,
MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
MLX5_SET(set_flow_table_root_in, in, table_type, ft->type);
MLX5_SET(set_flow_table_root_in, in, table_id, ft->id);
+ MLX5_SET(set_flow_table_root_in, in, underlay_qpn, underlay_qpn);
if (ft->vport) {
MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport);
MLX5_SET(set_flow_table_root_in, in, other_vport, 1);
}
- if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) &&
- ft->underlay_qpn != 0)
- MLX5_SET(set_flow_table_root_in, in, underlay_qpn, ft->underlay_qpn);
-
return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}
unsigned int index);
int mlx5_cmd_update_root_ft(struct mlx5_core_dev *dev,
- struct mlx5_flow_table *ft);
+ struct mlx5_flow_table *ft,
+ u32 underlay_qpn);
int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u16 *id);
int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u16 id);
if (ft->level >= min_level)
return 0;
- err = mlx5_cmd_update_root_ft(root->dev, ft);
+ err = mlx5_cmd_update_root_ft(root->dev, ft, root->underlay_qpn);
if (err)
mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n",
ft->id);
goto unlock_root;
}
- ft->underlay_qpn = ft_attr->underlay_qpn;
-
tree_init_node(&ft->node, 1, del_flow_table);
log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0;
next_ft = find_next_chained_ft(fs_prio);
new_root_ft = find_next_ft(ft);
if (new_root_ft) {
- int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft);
+ int err = mlx5_cmd_update_root_ft(root->dev, new_root_ft,
+ root->underlay_qpn);
if (err) {
mlx5_core_warn(root->dev, "Update root flow table of id=%u failed\n",
mlx5_cleanup_fs(dev);
return err;
}
+
+int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn)
+{
+ struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns;
+
+ root->underlay_qpn = underlay_qpn;
+ return 0;
+}
+EXPORT_SYMBOL(mlx5_fs_add_rx_underlay_qpn);
+
+int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn)
+{
+ struct mlx5_flow_root_namespace *root = dev->priv.steering->root_ns;
+
+ root->underlay_qpn = 0;
+ return 0;
+}
+EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn);
/* FWD rules that point on this flow table */
struct list_head fwd_rules;
u32 flags;
- u32 underlay_qpn;
};
struct mlx5_fc_cache {
struct mlx5_flow_table *root_ft;
/* Should be held when chaining flow tables */
struct mutex chain_lock;
+ u32 underlay_qpn;
};
int mlx5_init_fc_stats(struct mlx5_core_dev *dev);
mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev));
+ /* Override RQ params as IPoIB supports only LINKED LIST RQ for now */
+ mlx5e_set_rq_type_params(mdev, &priv->channels.params, MLX5_WQ_TYPE_LINKED_LIST);
+ priv->channels.params.lro_en = false;
+
mutex_init(&priv->state_lock);
netdev->hw_features |= NETIF_F_SG;
static void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, struct mlx5_core_qp *qp)
{
+ mlx5_fs_remove_rx_underlay_qpn(mdev, qp->qpn);
+
mlx5_core_destroy_qp(mdev, qp);
}
return err;
}
+ mlx5_fs_add_rx_underlay_qpn(priv->mdev, ipriv->qp.qpn);
+
err = mlx5e_create_tis(priv->mdev, 0 /* tc */, ipriv->qp.qpn, &priv->tisn[0]);
if (err) {
mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err);
static int mlx5i_create_flow_steering(struct mlx5e_priv *priv)
{
- struct mlx5i_priv *ipriv = priv->ppriv;
int err;
priv->fs.ns = mlx5_get_flow_namespace(priv->mdev,
priv->netdev->hw_features &= ~NETIF_F_NTUPLE;
}
- err = mlx5e_create_ttc_table(priv, ipriv->qp.qpn);
+ err = mlx5e_create_ttc_table(priv);
if (err) {
netdev_err(priv->netdev, "Failed to create ttc table, err=%d\n",
err);
cmd.req.arg3 = 0;
if (recv_ctx->state == NX_HOST_CTX_STATE_ACTIVE)
- netxen_issue_cmd(adapter, &cmd);
+ rcode = netxen_issue_cmd(adapter, &cmd);
if (rcode != NX_RCODE_SUCCESS)
return -EIO;
memset(&camline, 0, sizeof(union gft_cam_line_union));
qed_wr(p_hwfn, p_ptt, PRS_REG_GFT_CAM + CAM_LINE_SIZE * pf_id,
camline.cam_line_mapped.camline);
- memset(&ramline, 0, sizeof(union gft_cam_line_union));
+ memset(&ramline, 0, sizeof(ramline));
for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++) {
u32 hw_addr = PRS_REG_GFT_PROFILE_MASK_RAM;
#define _QLCNIC_LINUX_MAJOR 5
#define _QLCNIC_LINUX_MINOR 3
-#define _QLCNIC_LINUX_SUBVERSION 65
-#define QLCNIC_LINUX_VERSIONID "5.3.65"
+#define _QLCNIC_LINUX_SUBVERSION 66
+#define QLCNIC_LINUX_VERSIONID "5.3.66"
#define QLCNIC_DRV_IDC_VER 0x01
#define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\
(_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION))
return 0;
}
+void qlcnic_83xx_get_port_type(struct qlcnic_adapter *adapter)
+{
+ struct qlcnic_hardware_context *ahw = adapter->ahw;
+ struct qlcnic_cmd_args cmd;
+ u32 config;
+ int err;
+
+ err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_GET_LINK_STATUS);
+ if (err)
+ return;
+
+ err = qlcnic_issue_cmd(adapter, &cmd);
+ if (err) {
+ dev_info(&adapter->pdev->dev,
+ "Get Link Status Command failed: 0x%x\n", err);
+ goto out;
+ } else {
+ config = cmd.rsp.arg[3];
+
+ switch (QLC_83XX_SFP_MODULE_TYPE(config)) {
+ case QLC_83XX_MODULE_FIBRE_1000BASE_SX:
+ case QLC_83XX_MODULE_FIBRE_1000BASE_LX:
+ case QLC_83XX_MODULE_FIBRE_1000BASE_CX:
+ case QLC_83XX_MODULE_TP_1000BASE_T:
+ ahw->port_type = QLCNIC_GBE;
+ break;
+ default:
+ ahw->port_type = QLCNIC_XGBE;
+ }
+ }
+out:
+ qlcnic_free_mbx_args(&cmd);
+}
+
int qlcnic_83xx_test_link(struct qlcnic_adapter *adapter)
{
u8 pci_func;
int qlcnic_83xx_set_pauseparam(struct qlcnic_adapter *,
struct ethtool_pauseparam *);
int qlcnic_83xx_test_link(struct qlcnic_adapter *);
+void qlcnic_83xx_get_port_type(struct qlcnic_adapter *adapter);
int qlcnic_83xx_reg_test(struct qlcnic_adapter *);
int qlcnic_83xx_get_regs_len(struct qlcnic_adapter *);
int qlcnic_83xx_get_registers(struct qlcnic_adapter *, u32 *);
u32 ret = 0;
struct qlcnic_adapter *adapter = netdev_priv(dev);
+ if (qlcnic_83xx_check(adapter))
+ qlcnic_83xx_get_port_type(adapter);
+
if (adapter->ahw->port_type != QLCNIC_GBE)
return -EOPNOTSUPP;
/* Allocate rx SKB if we don't have one available. */
if (!qca->rx_skb) {
- qca->rx_skb = netdev_alloc_skb(net_dev,
- net_dev->mtu + VLAN_ETH_HLEN);
+ qca->rx_skb = netdev_alloc_skb_ip_align(net_dev,
+ net_dev->mtu +
+ VLAN_ETH_HLEN);
if (!qca->rx_skb) {
netdev_dbg(net_dev, "out of RX resources\n");
qca->stats.out_of_mem++;
qca->rx_skb, qca->rx_skb->dev);
qca->rx_skb->ip_summed = CHECKSUM_UNNECESSARY;
netif_rx_ni(qca->rx_skb);
- qca->rx_skb = netdev_alloc_skb(net_dev,
+ qca->rx_skb = netdev_alloc_skb_ip_align(net_dev,
net_dev->mtu + VLAN_ETH_HLEN);
if (!qca->rx_skb) {
netdev_dbg(net_dev, "out of RX resources\n");
if (!qca->rx_buffer)
return -ENOBUFS;
- qca->rx_skb = netdev_alloc_skb(dev, qca->net_dev->mtu + VLAN_ETH_HLEN);
+ qca->rx_skb = netdev_alloc_skb_ip_align(dev, qca->net_dev->mtu +
+ VLAN_ETH_HLEN);
if (!qca->rx_skb) {
kfree(qca->rx_buffer);
netdev_info(qca->net_dev, "Failed to allocate RX sk_buff.\n");
#include "mcdi.h"
enum {
- EFX_REV_SIENA_A0 = 0,
- EFX_REV_HUNT_A0 = 1,
+ /* Revisions 0-2 were Falcon A0, A1 and B0 respectively.
+ * They are not supported by this driver but these revision numbers
+ * form part of the ethtool API for register dumping.
+ */
+ EFX_REV_SIENA_A0 = 3,
+ EFX_REV_HUNT_A0 = 4,
};
static inline int efx_nic_rev(struct efx_nic *efx)
ep++;
} else {
seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
- i, (unsigned int)virt_to_phys(ep),
+ i, (unsigned int)virt_to_phys(p),
le32_to_cpu(p->des0), le32_to_cpu(p->des1),
le32_to_cpu(p->des2), le32_to_cpu(p->des3));
p++;
if (port) {
del_timer_sync(&port->vio.timer);
+ del_timer_sync(&port->clean_timer);
napi_disable(&port->napi);
+ unregister_netdev(port->dev);
list_del_rcu(&port->list);
synchronize_rcu();
- del_timer_sync(&port->clean_timer);
spin_lock_irqsave(&port->vp->lock, flags);
sunvnet_port_rm_txq_common(port);
spin_unlock_irqrestore(&port->vp->lock, flags);
dev_set_drvdata(&vdev->dev, NULL);
- unregister_netdev(port->dev);
free_netdev(port->dev);
}
tx_pipe->dma_channel = knav_dma_open_channel(dev,
tx_pipe->dma_chan_name, &config);
- if (IS_ERR_OR_NULL(tx_pipe->dma_channel)) {
+ if (IS_ERR(tx_pipe->dma_channel)) {
dev_err(dev, "failed opening tx chan(%s)\n",
tx_pipe->dma_chan_name);
+ ret = PTR_ERR(tx_pipe->dma_channel);
goto err;
}
netcp->rx_channel = knav_dma_open_channel(netcp->netcp_device->device,
netcp->dma_chan_name, &config);
- if (IS_ERR_OR_NULL(netcp->rx_channel)) {
+ if (IS_ERR(netcp->rx_channel)) {
dev_err(netcp->ndev_dev, "failed opening rx chan(%s\n",
netcp->dma_chan_name);
+ ret = PTR_ERR(netcp->rx_channel);
goto fail;
}
case HWTSTAMP_FILTER_NONE:
cpts_rx_enable(cpts, 0);
break;
- case HWTSTAMP_FILTER_ALL:
case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
* are "42101001.sb" or "42101002.sb"
*/
sprintf(stir421x_fw_name, "4210%4X.sb",
- self->usbdev->descriptor.bcdDevice);
+ le16_to_cpu(self->usbdev->descriptor.bcdDevice));
ret = request_firmware(&fw, stir421x_fw_name, &self->usbdev->dev);
if (ret < 0)
return ret;
*/
static struct lock_class_key macvlan_netdev_addr_lock_key;
-#define ALWAYS_ON_FEATURES \
- (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | NETIF_F_LLTX | \
+#define ALWAYS_ON_OFFLOADS \
+ (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \
NETIF_F_GSO_ROBUST)
+#define ALWAYS_ON_FEATURES (ALWAYS_ON_OFFLOADS | NETIF_F_LLTX)
+
#define MACVLAN_FEATURES \
(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \
NETIF_F_GSO | NETIF_F_TSO | NETIF_F_UFO | NETIF_F_LRO | \
dev->features |= ALWAYS_ON_FEATURES;
dev->hw_features |= NETIF_F_LRO;
dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES;
+ dev->vlan_features |= ALWAYS_ON_OFFLOADS;
dev->gso_max_size = lowerdev->gso_max_size;
dev->gso_max_segs = lowerdev->gso_max_segs;
dev->hard_header_len = lowerdev->hard_header_len;
pb = devm_kzalloc(dev, sizeof(*pb), GFP_KERNEL);
if (pb == NULL) {
ret_val = -ENOMEM;
- goto err_parent_bus;
+ goto err_pb_kz;
}
-
pb->switch_data = data;
pb->switch_fn = switch_fn;
pb->current_child = -1;
cb->mii_bus = mdiobus_alloc();
if (!cb->mii_bus) {
ret_val = -ENOMEM;
+ devm_kfree(dev, cb);
of_node_put(child_bus_node);
break;
}
mdiobus_free(cb->mii_bus);
devm_kfree(dev, cb);
} else {
- of_node_get(child_bus_node);
cb->next = pb->children;
pb->children = cb;
}
return 0;
}
+ devm_kfree(dev, pb);
+err_pb_kz:
/* balance the reference of_mdio_find_bus() took */
- put_device(&pb->mii_bus->dev);
-
+ if (!mux_bus)
+ put_device(&parent_bus->dev);
err_parent_bus:
of_node_put(parent_bus_node);
return ret_val;
mutex_init(&bus->mdio_lock);
- if (bus->reset)
- bus->reset(bus);
-
/* de-assert bus level PHY GPIO resets */
if (bus->num_reset_gpios > 0) {
bus->reset_gpiod = devm_kcalloc(&bus->dev,
}
}
+ if (bus->reset)
+ bus->reset(bus);
+
for (i = 0; i < PHY_MAX_ADDR; i++) {
if ((bus->phy_mask & (1 << i)) == 0) {
struct phy_device *phydev;
int rd_mac_len = 0;
netdev_dbg(dev->net, "get_mac_address:\n\tusbnet VID:%0x PID:%0x\n",
- dev->udev->descriptor.idVendor,
- dev->udev->descriptor.idProduct);
+ le16_to_cpu(dev->udev->descriptor.idVendor),
+ le16_to_cpu(dev->udev->descriptor.idProduct));
memset(mac_addr, 0, sizeof(mac_addr));
rd_mac_len = control_read(dev, REQUEST_READ, 0,
/* we need to enable NAPI, otherwise dev_close will deadlock */
for (i = 0; i < adapter->num_rx_queues; i++)
napi_enable(&adapter->rx_queue[i].napi);
+ /*
+ * Need to clear the quiesce bit to ensure that vmxnet3_close
+ * can quiesce the device properly
+ */
+ clear_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state);
dev_close(adapter->netdev);
}
static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
+ kfree_skb(skb);
return 0;
}
{
struct net *net = dev_net(dev);
- if (NF_HOOK(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) < 0)
+ if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1)
skb = NULL; /* kfree_skb(skb) handled by nf code */
return skb;
xennet_disconnect_backend(info);
xennet_destroy_queues(info);
out:
- unregister_netdev(info->netdev);
- xennet_free_netdev(info->netdev);
+ device_unregister(&dev->dev);
return err;
}
};
struct qeth_discipline {
+ const struct device_type *devtype;
void (*start_poll)(struct ccw_device *, int, unsigned long);
qdio_handler_t *input_handler;
qdio_handler_t *output_handler;
extern struct qeth_discipline qeth_l3_discipline;
extern const struct attribute_group *qeth_generic_attr_groups[];
extern const struct attribute_group *qeth_osn_attr_groups[];
+extern const struct attribute_group qeth_device_attr_group;
+extern const struct attribute_group qeth_device_blkt_group;
+extern const struct device_type qeth_generic_devtype;
extern struct workqueue_struct *qeth_wq;
int qeth_card_hw_is_reachable(struct qeth_card *);
card->discipline = NULL;
}
-static const struct device_type qeth_generic_devtype = {
+const struct device_type qeth_generic_devtype = {
.name = "qeth_generic",
.groups = qeth_generic_attr_groups,
};
+EXPORT_SYMBOL_GPL(qeth_generic_devtype);
+
static const struct device_type qeth_osn_devtype = {
.name = "qeth_osn",
.groups = qeth_osn_attr_groups,
goto err_card;
}
- if (card->info.type == QETH_CARD_TYPE_OSN)
- gdev->dev.type = &qeth_osn_devtype;
- else
- gdev->dev.type = &qeth_generic_devtype;
-
switch (card->info.type) {
case QETH_CARD_TYPE_OSN:
case QETH_CARD_TYPE_OSM:
rc = qeth_core_load_discipline(card, QETH_DISCIPLINE_LAYER2);
if (rc)
goto err_card;
+
+ gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN)
+ ? card->discipline->devtype
+ : &qeth_osn_devtype;
rc = card->discipline->setup(card->gdev);
if (rc)
goto err_disc;
- case QETH_CARD_TYPE_OSD:
- case QETH_CARD_TYPE_OSX:
+ break;
default:
+ gdev->dev.type = &qeth_generic_devtype;
break;
}
if (rc)
goto err;
rc = card->discipline->setup(card->gdev);
- if (rc)
+ if (rc) {
+ qeth_core_free_discipline(card);
goto err;
+ }
}
rc = card->discipline->set_online(gdev);
err:
if (card->options.layer2 == newdis)
goto out;
- else {
- card->info.mac_bits = 0;
- if (card->discipline) {
- card->discipline->remove(card->gdev);
- qeth_core_free_discipline(card);
- }
+ if (card->info.type == QETH_CARD_TYPE_OSM) {
+ /* fixed layer, can't switch */
+ rc = -EOPNOTSUPP;
+ goto out;
+ }
+
+ card->info.mac_bits = 0;
+ if (card->discipline) {
+ card->discipline->remove(card->gdev);
+ qeth_core_free_discipline(card);
}
rc = qeth_core_load_discipline(card, newdis);
goto out;
rc = card->discipline->setup(card->gdev);
+ if (rc)
+ qeth_core_free_discipline(card);
out:
mutex_unlock(&card->discipline_mutex);
return rc ? rc : count;
&dev_attr_inter_jumbo.attr,
NULL,
};
-static struct attribute_group qeth_device_blkt_group = {
+const struct attribute_group qeth_device_blkt_group = {
.name = "blkt",
.attrs = qeth_blkt_device_attrs,
};
+EXPORT_SYMBOL_GPL(qeth_device_blkt_group);
static struct attribute *qeth_device_attrs[] = {
&dev_attr_state.attr,
&dev_attr_switch_attrs.attr,
NULL,
};
-static struct attribute_group qeth_device_attr_group = {
+const struct attribute_group qeth_device_attr_group = {
.attrs = qeth_device_attrs,
};
+EXPORT_SYMBOL_GPL(qeth_device_attr_group);
const struct attribute_group *qeth_generic_attr_groups[] = {
&qeth_device_attr_group,
#include "qeth_core.h"
+extern const struct attribute_group *qeth_l2_attr_groups[];
+
int qeth_l2_create_device_attributes(struct device *);
void qeth_l2_remove_device_attributes(struct device *);
void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
return 0;
}
+static const struct device_type qeth_l2_devtype = {
+ .name = "qeth_layer2",
+ .groups = qeth_l2_attr_groups,
+};
+
static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
{
struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+ int rc;
- qeth_l2_create_device_attributes(&gdev->dev);
+ if (gdev->dev.type == &qeth_generic_devtype) {
+ rc = qeth_l2_create_device_attributes(&gdev->dev);
+ if (rc)
+ return rc;
+ }
INIT_LIST_HEAD(&card->vid_list);
hash_init(card->mac_htable);
card->options.layer2 = 1;
{
struct qeth_card *card = dev_get_drvdata(&cgdev->dev);
- qeth_l2_remove_device_attributes(&cgdev->dev);
+ if (cgdev->dev.type == &qeth_generic_devtype)
+ qeth_l2_remove_device_attributes(&cgdev->dev);
qeth_set_allowed_threads(card, 0, 1);
wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
case QETH_CARD_TYPE_OSN:
card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN,
ether_setup);
- card->dev->flags |= IFF_NOARP;
break;
default:
card->dev = alloc_etherdev(0);
card->dev->min_mtu = 64;
card->dev->max_mtu = ETH_MAX_MTU;
card->dev->netdev_ops = &qeth_l2_netdev_ops;
- card->dev->ethtool_ops =
- (card->info.type != QETH_CARD_TYPE_OSN) ?
- &qeth_l2_ethtool_ops : &qeth_l2_osn_ops;
+ if (card->info.type == QETH_CARD_TYPE_OSN) {
+ card->dev->ethtool_ops = &qeth_l2_osn_ops;
+ card->dev->flags |= IFF_NOARP;
+ } else {
+ card->dev->ethtool_ops = &qeth_l2_ethtool_ops;
+ }
card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
card->dev->hw_features = NETIF_F_SG;
}
struct qeth_discipline qeth_l2_discipline = {
+ .devtype = &qeth_l2_devtype,
.start_poll = qeth_qdio_start_poll,
.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
} else
qeth_bridgeport_an_set(card, 0);
}
+
+const struct attribute_group *qeth_l2_attr_groups[] = {
+ &qeth_device_attr_group,
+ &qeth_device_blkt_group,
+ /* l2 specific, see l2_{create,remove}_device_attributes(): */
+ &qeth_l2_bridgeport_attr_group,
+ NULL,
+};
static int qeth_l3_probe_device(struct ccwgroup_device *gdev)
{
struct qeth_card *card = dev_get_drvdata(&gdev->dev);
+ int rc;
- qeth_l3_create_device_attributes(&gdev->dev);
+ rc = qeth_l3_create_device_attributes(&gdev->dev);
+ if (rc)
+ return rc;
+ hash_init(card->ip_htable);
+ hash_init(card->ip_mc_htable);
card->options.layer2 = 0;
card->info.hwtrap = 0;
return 0;
}
struct qeth_discipline qeth_l3_discipline = {
+ .devtype = &qeth_generic_devtype,
.start_poll = qeth_qdio_start_poll,
.input_handler = (qdio_handler_t *) qeth_qdio_input_handler,
.output_handler = (qdio_handler_t *) qeth_qdio_output_handler,
* @name: slave channel name
* @config: dma configuration parameters
*
- * Returns pointer to appropriate DMA channel on success or NULL.
+ * Returns pointer to appropriate DMA channel on success or error.
*/
void *knav_dma_open_channel(struct device *dev, const char *name,
struct knav_dma_cfg *config)
*/
s64 min_value;
u64 max_value;
+ u32 min_align;
+ u32 aux_off;
+ u32 aux_off_align;
};
enum bpf_stack_slot_type {
struct bpf_prog *prog; /* eBPF program being verified */
struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
int stack_size; /* number of states to be processed */
+ bool strict_alignment; /* perform strict pointer alignment checks */
struct bpf_verifier_state cur_state; /* current verifier state */
struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */
int max_fte;
u32 level;
u32 flags;
- u32 underlay_qpn;
};
struct mlx5_flow_table *
void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
void mlx5_fc_query_cached(struct mlx5_fc *counter,
u64 *bytes, u64 *packets, u64 *lastuse);
+int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn);
+int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn);
+
#endif
int dev_get_phys_port_name(struct net_device *dev,
char *name, size_t len);
int dev_change_proto_down(struct net_device *dev, bool proto_down);
-int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
- int fd, u32 flags);
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, int *ret);
+
+typedef int (*xdp_op_t)(struct net_device *dev, struct netdev_xdp *xdp);
+int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
+ int fd, u32 flags);
+bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op);
+
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
bool is_skb_forwardable(const struct net_device *dev,
*/
#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will perform strict alignment checking as if the kernel
+ * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
+ * and NET_IP_ALIGN defined to 2.
+ */
+#define BPF_F_STRICT_ALIGNMENT (1U << 0)
+
#define BPF_PSEUDO_MAP_FD 1
/* flags for BPF_MAP_UPDATE_ELEM command */
__u32 log_size; /* size of user buffer */
__aligned_u64 log_buf; /* user supplied buffer */
__u32 kern_version; /* checked when prog_type=kprobe */
+ __u32 prog_flags;
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
/* XDP section */
#define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0)
-#define XDP_FLAGS_SKB_MODE (2U << 0)
+#define XDP_FLAGS_SKB_MODE (1U << 1)
+#define XDP_FLAGS_DRV_MODE (1U << 2)
#define XDP_FLAGS_MASK (XDP_FLAGS_UPDATE_IF_NOEXIST | \
- XDP_FLAGS_SKB_MODE)
+ XDP_FLAGS_SKB_MODE | \
+ XDP_FLAGS_DRV_MODE)
+
+/* These are stored into IFLA_XDP_ATTACHED on dump. */
+enum {
+ XDP_ATTACHED_NONE = 0,
+ XDP_ATTACHED_DRV,
+ XDP_ATTACHED_SKB,
+};
enum {
IFLA_XDP_UNSPEC,
EXPORT_SYMBOL_GPL(bpf_prog_get_type);
/* last field in 'union bpf_attr' used by this command */
-#define BPF_PROG_LOAD_LAST_FIELD kern_version
+#define BPF_PROG_LOAD_LAST_FIELD prog_flags
static int bpf_prog_load(union bpf_attr *attr)
{
if (CHECK_ATTR(BPF_PROG_LOAD))
return -EINVAL;
+ if (attr->prog_flags & ~BPF_F_STRICT_ALIGNMENT)
+ return -EINVAL;
+
/* copy eBPF program license from user space */
if (strncpy_from_user(license, u64_to_user_ptr(attr->license),
sizeof(license) - 1) < 0)
if (reg->max_value != BPF_REGISTER_MAX_RANGE)
verbose(",max_value=%llu",
(unsigned long long)reg->max_value);
+ if (reg->min_align)
+ verbose(",min_align=%u", reg->min_align);
+ if (reg->aux_off)
+ verbose(",aux_off=%u", reg->aux_off);
+ if (reg->aux_off_align)
+ verbose(",aux_off_align=%u", reg->aux_off_align);
}
for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) {
if (state->stack_slot_type[i] == STACK_SPILL)
regs[i].imm = 0;
regs[i].min_value = BPF_REGISTER_MIN_RANGE;
regs[i].max_value = BPF_REGISTER_MAX_RANGE;
+ regs[i].min_align = 0;
+ regs[i].aux_off = 0;
+ regs[i].aux_off_align = 0;
}
/* frame pointer */
{
regs[regno].min_value = BPF_REGISTER_MIN_RANGE;
regs[regno].max_value = BPF_REGISTER_MAX_RANGE;
+ regs[regno].min_align = 0;
}
static void mark_reg_unknown_value_and_range(struct bpf_reg_state *regs,
}
static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg,
- int off, int size)
+ int off, int size, bool strict)
{
- if (reg->id && size != 1) {
- verbose("Unknown alignment. Only byte-sized access allowed in packet access.\n");
- return -EACCES;
+ int ip_align;
+ int reg_off;
+
+ /* Byte size accesses are always allowed. */
+ if (!strict || size == 1)
+ return 0;
+
+ reg_off = reg->off;
+ if (reg->id) {
+ if (reg->aux_off_align % size) {
+ verbose("Packet access is only %u byte aligned, %d byte access not allowed\n",
+ reg->aux_off_align, size);
+ return -EACCES;
+ }
+ reg_off += reg->aux_off;
}
- /* skb->data is NET_IP_ALIGN-ed */
- if ((NET_IP_ALIGN + reg->off + off) % size != 0) {
+ /* skb->data is NET_IP_ALIGN-ed, but for strict alignment checking
+ * we force this to 2 which is universally what architectures use
+ * when they don't set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
+ */
+ ip_align = strict ? 2 : NET_IP_ALIGN;
+ if ((ip_align + reg_off + off) % size != 0) {
verbose("misaligned packet access off %d+%d+%d size %d\n",
- NET_IP_ALIGN, reg->off, off, size);
+ ip_align, reg_off, off, size);
return -EACCES;
}
}
static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
- int size)
+ int size, bool strict)
{
- if (size != 1) {
+ if (strict && size != 1) {
verbose("Unknown alignment. Only byte-sized access allowed in value access.\n");
return -EACCES;
}
return 0;
}
-static int check_ptr_alignment(const struct bpf_reg_state *reg,
+static int check_ptr_alignment(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
int off, int size)
{
+ bool strict = env->strict_alignment;
+
+ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
+ strict = true;
+
switch (reg->type) {
case PTR_TO_PACKET:
- return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
- check_pkt_ptr_alignment(reg, off, size);
+ return check_pkt_ptr_alignment(reg, off, size, strict);
case PTR_TO_MAP_VALUE_ADJ:
- return IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ? 0 :
- check_val_ptr_alignment(reg, size);
+ return check_val_ptr_alignment(reg, size, strict);
default:
if (off % size != 0) {
verbose("misaligned access off %d size %d\n",
if (size < 0)
return size;
- err = check_ptr_alignment(reg, off, size);
+ err = check_ptr_alignment(env, reg, off, size);
if (err)
return err;
value_regno);
/* note that reg.[id|off|range] == 0 */
state->regs[value_regno].type = reg_type;
+ state->regs[value_regno].aux_off = 0;
+ state->regs[value_regno].aux_off_align = 0;
}
} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
*/
dst_reg->off += imm;
} else {
+ bool had_id;
+
if (src_reg->type == PTR_TO_PACKET) {
/* R6=pkt(id=0,off=0,r=62) R7=imm22; r7 += r6 */
tmp_reg = *dst_reg; /* save r7 state */
src_reg->imm);
return -EACCES;
}
+
+ had_id = (dst_reg->id != 0);
+
/* dst_reg stays as pkt_ptr type and since some positive
* integer value was added to the pointer, increment its 'id'
*/
dst_reg->id = ++env->id_gen;
- /* something was added to pkt_ptr, set range and off to zero */
+ /* something was added to pkt_ptr, set range to zero */
+ dst_reg->aux_off += dst_reg->off;
dst_reg->off = 0;
dst_reg->range = 0;
+ if (had_id)
+ dst_reg->aux_off_align = min(dst_reg->aux_off_align,
+ src_reg->min_align);
+ else
+ dst_reg->aux_off_align = src_reg->min_align;
}
return 0;
}
reg->min_value = BPF_REGISTER_MIN_RANGE;
}
+static u32 calc_align(u32 imm)
+{
+ if (!imm)
+ return 1U << 31;
+ return imm - ((imm - 1) & imm);
+}
+
static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
struct bpf_insn *insn)
{
s64 min_val = BPF_REGISTER_MIN_RANGE;
u64 max_val = BPF_REGISTER_MAX_RANGE;
u8 opcode = BPF_OP(insn->code);
+ u32 dst_align, src_align;
dst_reg = ®s[insn->dst_reg];
+ src_align = 0;
if (BPF_SRC(insn->code) == BPF_X) {
check_reg_overflow(®s[insn->src_reg]);
min_val = regs[insn->src_reg].min_value;
regs[insn->src_reg].type != UNKNOWN_VALUE) {
min_val = BPF_REGISTER_MIN_RANGE;
max_val = BPF_REGISTER_MAX_RANGE;
+ src_align = 0;
+ } else {
+ src_align = regs[insn->src_reg].min_align;
}
} else if (insn->imm < BPF_REGISTER_MAX_RANGE &&
(s64)insn->imm > BPF_REGISTER_MIN_RANGE) {
min_val = max_val = insn->imm;
+ src_align = calc_align(insn->imm);
}
+ dst_align = dst_reg->min_align;
+
/* We don't know anything about what was done to this register, mark it
* as unknown.
*/
dst_reg->min_value += min_val;
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value += max_val;
+ dst_reg->min_align = min(src_align, dst_align);
break;
case BPF_SUB:
if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
dst_reg->min_value -= min_val;
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value -= max_val;
+ dst_reg->min_align = min(src_align, dst_align);
break;
case BPF_MUL:
if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
dst_reg->min_value *= min_val;
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value *= max_val;
+ dst_reg->min_align = max(src_align, dst_align);
break;
case BPF_AND:
/* Disallow AND'ing of negative numbers, ain't nobody got time
else
dst_reg->min_value = 0;
dst_reg->max_value = max_val;
+ dst_reg->min_align = max(src_align, dst_align);
break;
case BPF_LSH:
/* Gotta have special overflow logic here, if we're shifting
* more than MAX_RANGE then just assume we have an invalid
* range.
*/
- if (min_val > ilog2(BPF_REGISTER_MAX_RANGE))
+ if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) {
dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
- else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
- dst_reg->min_value <<= min_val;
-
+ dst_reg->min_align = 1;
+ } else {
+ if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
+ dst_reg->min_value <<= min_val;
+ if (!dst_reg->min_align)
+ dst_reg->min_align = 1;
+ dst_reg->min_align <<= min_val;
+ }
if (max_val > ilog2(BPF_REGISTER_MAX_RANGE))
dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
/* RSH by a negative number is undefined, and the BPF_RSH is an
* unsigned shift, so make the appropriate casts.
*/
- if (min_val < 0 || dst_reg->min_value < 0)
+ if (min_val < 0 || dst_reg->min_value < 0) {
dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
- else
+ } else {
dst_reg->min_value =
(u64)(dst_reg->min_value) >> min_val;
+ }
+ if (min_val < 0) {
+ dst_reg->min_align = 1;
+ } else {
+ dst_reg->min_align >>= (u64) min_val;
+ if (!dst_reg->min_align)
+ dst_reg->min_align = 1;
+ }
if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
dst_reg->max_value >>= max_val;
break;
regs[insn->dst_reg].imm = insn->imm;
regs[insn->dst_reg].max_value = insn->imm;
regs[insn->dst_reg].min_value = insn->imm;
+ regs[insn->dst_reg].min_align = calc_align(insn->imm);
}
} else if (opcode > BPF_END) {
goto process_bpf_exit;
}
- if (log_level && do_print_state) {
- verbose("\nfrom %d to %d:", prev_insn_idx, insn_idx);
+ if (log_level > 1 || (log_level && do_print_state)) {
+ if (log_level > 1)
+ verbose("%d:", insn_idx);
+ else
+ verbose("\nfrom %d to %d:",
+ prev_insn_idx, insn_idx);
print_verifier_state(&env->cur_state);
do_print_state = false;
}
} else {
log_level = 0;
}
+ if (attr->prog_flags & BPF_F_STRICT_ALIGNMENT)
+ env->strict_alignment = true;
+ else
+ env->strict_alignment = false;
ret = replace_map_fd_with_map_ptr(env);
if (ret < 0)
mutex_lock(&bpf_verifier_lock);
log_level = 0;
+ env->strict_alignment = false;
env->explored_states = kcalloc(env->prog->len,
sizeof(struct bpf_verifier_state_list *),
}
EXPORT_SYMBOL(dev_change_proto_down);
+bool __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op)
+{
+ struct netdev_xdp xdp;
+
+ memset(&xdp, 0, sizeof(xdp));
+ xdp.command = XDP_QUERY_PROG;
+
+ /* Query must always succeed. */
+ WARN_ON(xdp_op(dev, &xdp) < 0);
+ return xdp.prog_attached;
+}
+
+static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op,
+ struct netlink_ext_ack *extack,
+ struct bpf_prog *prog)
+{
+ struct netdev_xdp xdp;
+
+ memset(&xdp, 0, sizeof(xdp));
+ xdp.command = XDP_SETUP_PROG;
+ xdp.extack = extack;
+ xdp.prog = prog;
+
+ return xdp_op(dev, &xdp);
+}
+
/**
* dev_change_xdp_fd - set or clear a bpf program for a device rx path
* @dev: device
int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
int fd, u32 flags)
{
- int (*xdp_op)(struct net_device *dev, struct netdev_xdp *xdp);
const struct net_device_ops *ops = dev->netdev_ops;
struct bpf_prog *prog = NULL;
- struct netdev_xdp xdp;
+ xdp_op_t xdp_op, xdp_chk;
int err;
ASSERT_RTNL();
- xdp_op = ops->ndo_xdp;
+ xdp_op = xdp_chk = ops->ndo_xdp;
+ if (!xdp_op && (flags & XDP_FLAGS_DRV_MODE))
+ return -EOPNOTSUPP;
if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE))
xdp_op = generic_xdp_install;
+ if (xdp_op == xdp_chk)
+ xdp_chk = generic_xdp_install;
if (fd >= 0) {
- if (flags & XDP_FLAGS_UPDATE_IF_NOEXIST) {
- memset(&xdp, 0, sizeof(xdp));
- xdp.command = XDP_QUERY_PROG;
-
- err = xdp_op(dev, &xdp);
- if (err < 0)
- return err;
- if (xdp.prog_attached)
- return -EBUSY;
- }
+ if (xdp_chk && __dev_xdp_attached(dev, xdp_chk))
+ return -EEXIST;
+ if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
+ __dev_xdp_attached(dev, xdp_op))
+ return -EBUSY;
prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
if (IS_ERR(prog))
return PTR_ERR(prog);
}
- memset(&xdp, 0, sizeof(xdp));
- xdp.command = XDP_SETUP_PROG;
- xdp.extack = extack;
- xdp.prog = prog;
-
- err = xdp_op(dev, &xdp);
+ err = dev_xdp_install(dev, xdp_op, extack, prog);
if (err < 0 && prog)
bpf_prog_put(prog);
static size_t rtnl_xdp_size(void)
{
size_t xdp_size = nla_total_size(0) + /* nest IFLA_XDP */
- nla_total_size(1) + /* XDP_ATTACHED */
- nla_total_size(4); /* XDP_FLAGS */
+ nla_total_size(1); /* XDP_ATTACHED */
return xdp_size;
}
return 0;
}
+static u8 rtnl_xdp_attached_mode(struct net_device *dev)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ ASSERT_RTNL();
+
+ if (rcu_access_pointer(dev->xdp_prog))
+ return XDP_ATTACHED_SKB;
+ if (ops->ndo_xdp && __dev_xdp_attached(dev, ops->ndo_xdp))
+ return XDP_ATTACHED_DRV;
+
+ return XDP_ATTACHED_NONE;
+}
+
static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
{
struct nlattr *xdp;
- u32 xdp_flags = 0;
- u8 val = 0;
int err;
xdp = nla_nest_start(skb, IFLA_XDP);
if (!xdp)
return -EMSGSIZE;
- if (rcu_access_pointer(dev->xdp_prog)) {
- xdp_flags = XDP_FLAGS_SKB_MODE;
- val = 1;
- } else if (dev->netdev_ops->ndo_xdp) {
- struct netdev_xdp xdp_op = {};
-
- xdp_op.command = XDP_QUERY_PROG;
- err = dev->netdev_ops->ndo_xdp(dev, &xdp_op);
- if (err)
- goto err_cancel;
- val = xdp_op.prog_attached;
- }
- err = nla_put_u8(skb, IFLA_XDP_ATTACHED, val);
+
+ err = nla_put_u8(skb, IFLA_XDP_ATTACHED,
+ rtnl_xdp_attached_mode(dev));
if (err)
goto err_cancel;
- if (xdp_flags) {
- err = nla_put_u32(skb, IFLA_XDP_FLAGS, xdp_flags);
- if (err)
- goto err_cancel;
- }
nla_nest_end(skb, xdp);
return 0;
err = -EINVAL;
goto errout;
}
+ if ((xdp_flags & XDP_FLAGS_SKB_MODE) &&
+ (xdp_flags & XDP_FLAGS_DRV_MODE)) {
+ err = -EINVAL;
+ goto errout;
+ }
}
if (xdp[IFLA_XDP_FD]) {
* delay queue. We want to allow the owner socket to send more
* packets, as if they were already TX completed by a typical driver.
* But we also want to keep skb->sk set because some packet schedulers
- * rely on it (sch_fq for example). So we set skb->truesize to a small
- * amount (1) and decrease sk_wmem_alloc accordingly.
+ * rely on it (sch_fq for example).
*/
void skb_orphan_partial(struct sk_buff *skb)
{
- /* If this skb is a TCP pure ACK or already went here,
- * we have nothing to do. 2 is already a very small truesize.
- */
- if (skb->truesize <= 2)
+ if (skb_is_tcp_pure_ack(skb))
return;
- /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc,
- * so we do not completely orphan skb, but transfert all
- * accounted bytes but one, to avoid unexpected reorders.
- */
if (skb->destructor == sock_wfree
#ifdef CONFIG_INET
|| skb->destructor == tcp_wfree
#endif
) {
- atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc);
- skb->truesize = 1;
+ struct sock *sk = skb->sk;
+
+ if (atomic_inc_not_zero(&sk->sk_refcnt)) {
+ atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
+ skb->destructor = sock_efree;
+ }
} else {
skb_orphan(skb);
}
newsk->sk_backlog_rcv = dccp_v4_do_rcv;
newnp->pktoptions = NULL;
newnp->opt = NULL;
+ newnp->ipv6_mc_list = NULL;
+ newnp->ipv6_ac_list = NULL;
+ newnp->ipv6_fl_list = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
+ newnp->ipv6_mc_list = NULL;
+ newnp->ipv6_ac_list = NULL;
+ newnp->ipv6_fl_list = NULL;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
*/
if (pkt_len > mss) {
unsigned int new_len = (pkt_len / mss) * mss;
- if (!in_sack && new_len < pkt_len) {
+ if (!in_sack && new_len < pkt_len)
new_len += mss;
- if (new_len >= skb->len)
- return 0;
- }
pkt_len = new_len;
}
+
+ if (pkt_len >= skb->len && !in_sack)
+ return 0;
+
err = tcp_fragment(sk, skb, pkt_len, mss, GFP_ATOMIC);
if (err < 0)
return err;
INIT_HLIST_NODE(&ifa->addr_lst);
ifa->scope = scope;
ifa->prefix_len = pfxlen;
- ifa->flags = flags | IFA_F_TENTATIVE;
+ ifa->flags = flags;
+ /* No need to add the TENTATIVE flag for addresses with NODAD */
+ if (!(flags & IFA_F_NODAD))
+ ifa->flags |= IFA_F_TENTATIVE;
ifa->valid_lft = valid_lft;
ifa->prefered_lft = prefered_lft;
ifa->cstamp = ifa->tstamp = jiffies;
newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
#endif
+ newnp->ipv6_mc_list = NULL;
newnp->ipv6_ac_list = NULL;
newnp->ipv6_fl_list = NULL;
newnp->pktoptions = NULL;
First: no IPv4 options.
*/
newinet->inet_opt = NULL;
+ newnp->ipv6_mc_list = NULL;
newnp->ipv6_ac_list = NULL;
newnp->ipv6_fl_list = NULL;
dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
}
- sockc.tsflags = po->sk.sk_tsflags;
- if (msg->msg_controllen) {
- err = sock_cmsg_send(&po->sk, msg, &sockc);
- if (unlikely(err))
- goto out;
- }
-
err = -ENXIO;
if (unlikely(dev == NULL))
goto out;
if (unlikely(!(dev->flags & IFF_UP)))
goto out_put;
+ sockc.tsflags = po->sk.sk_tsflags;
+ if (msg->msg_controllen) {
+ err = sock_cmsg_send(&po->sk, msg, &sockc);
+ if (unlikely(err))
+ goto out_put;
+ }
+
if (po->sk.sk_socket->type == SOCK_RAW)
reserve = dev->hard_header_len;
size_max = po->tx_ring.frame_size
if (!qdisc_dev(root))
return 0;
+ if (tcm->tcm_parent) {
+ q = qdisc_match_from_root(root, TC_H_MAJ(tcm->tcm_parent));
+ if (q && tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0)
+ return -1;
+ return 0;
+ }
hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) {
if (tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0)
return -1;
struct sctp_bind_addr *bp;
struct ipv6_pinfo *np = inet6_sk(sk);
struct sctp_sockaddr_entry *laddr;
- union sctp_addr *baddr = NULL;
union sctp_addr *daddr = &t->ipaddr;
union sctp_addr dst_saddr;
struct in6_addr *final_p, final;
__u8 matchlen = 0;
- __u8 bmatchlen;
sctp_scope_t scope;
memset(fl6, 0, sizeof(struct flowi6));
*/
rcu_read_lock();
list_for_each_entry_rcu(laddr, &bp->address_list, list) {
- if (!laddr->valid)
+ struct dst_entry *bdst;
+ __u8 bmatchlen;
+
+ if (!laddr->valid ||
+ laddr->state != SCTP_ADDR_SRC ||
+ laddr->a.sa.sa_family != AF_INET6 ||
+ scope > sctp_scope(&laddr->a))
continue;
- if ((laddr->state == SCTP_ADDR_SRC) &&
- (laddr->a.sa.sa_family == AF_INET6) &&
- (scope <= sctp_scope(&laddr->a))) {
- bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
- if (!baddr || (matchlen < bmatchlen)) {
- baddr = &laddr->a;
- matchlen = bmatchlen;
- }
- }
- }
- if (baddr) {
- fl6->saddr = baddr->v6.sin6_addr;
- fl6->fl6_sport = baddr->v6.sin6_port;
+
+ fl6->saddr = laddr->a.v6.sin6_addr;
+ fl6->fl6_sport = laddr->a.v6.sin6_port;
final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
- dst = ip6_dst_lookup_flow(sk, fl6, final_p);
+ bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
+
+ if (!IS_ERR(bdst) &&
+ ipv6_chk_addr(dev_net(bdst->dev),
+ &laddr->a.v6.sin6_addr, bdst->dev, 1)) {
+ if (!IS_ERR_OR_NULL(dst))
+ dst_release(dst);
+ dst = bdst;
+ break;
+ }
+
+ bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
+ if (matchlen > bmatchlen)
+ continue;
+
+ if (!IS_ERR_OR_NULL(dst))
+ dst_release(dst);
+ dst = bdst;
+ matchlen = bmatchlen;
}
rcu_read_unlock();
return 0;
}
-#define tipc_wait_for_cond(sock_, timeout_, condition_) \
-({ \
- int rc_ = 0; \
- int done_ = 0; \
- \
- while (!(condition_) && !done_) { \
- struct sock *sk_ = sock->sk; \
- DEFINE_WAIT_FUNC(wait_, woken_wake_function); \
- \
- rc_ = tipc_sk_sock_err(sock_, timeout_); \
- if (rc_) \
- break; \
- prepare_to_wait(sk_sleep(sk_), &wait_, \
- TASK_INTERRUPTIBLE); \
- done_ = sk_wait_event(sk_, timeout_, \
- (condition_), &wait_); \
- remove_wait_queue(sk_sleep(sk_), &wait_); \
- } \
- rc_; \
+#define tipc_wait_for_cond(sock_, timeo_, condition_) \
+({ \
+ struct sock *sk_; \
+ int rc_; \
+ \
+ while ((rc_ = !(condition_))) { \
+ DEFINE_WAIT_FUNC(wait_, woken_wake_function); \
+ sk_ = (sock_)->sk; \
+ rc_ = tipc_sk_sock_err((sock_), timeo_); \
+ if (rc_) \
+ break; \
+ prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \
+ release_sock(sk_); \
+ *(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \
+ sched_annotate_sleep(); \
+ lock_sock(sk_); \
+ remove_wait_queue(sk_sleep(sk_), &wait_); \
+ } \
+ rc_; \
})
/**
prog_attach_iptables(argv[2]);
if (cfg_test_traffic) {
if (signal(SIGINT, finish) == SIG_ERR)
- error(1, errno, "register handler failed");
+ error(1, errno, "register SIGINT handler failed");
+ if (signal(SIGTERM, finish) == SIG_ERR)
+ error(1, errno, "register SIGTERM handler failed");
while (!test_finish) {
print_table();
printf("\n");
setrlimit(RLIMIT_MEMLOCK, &r);
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
if (load_kallsyms()) {
printf("failed to process /proc/kallsyms\n");
return 1;
}
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
/* do sampling */
printf("Sampling at %d Hertz for %d seconds. Ctrl-C also ends.\n",
setrlimit(RLIMIT_MEMLOCK, &r);
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
if (load_kallsyms()) {
printf("failed to process /proc/kallsyms\n");
}
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
/* start 'ping' in the background to have some kfree_skb events */
f = popen("ping -c5 localhost", "r");
fprintf(stderr,
"usage: %s [OPTS] IFINDEX\n\n"
"OPTS:\n"
- " -S use skb-mode\n",
+ " -S use skb-mode\n"
+ " -N enforce native mode\n",
prog);
}
int main(int argc, char **argv)
{
- const char *optstr = "S";
+ const char *optstr = "SN";
char filename[256];
int opt;
case 'S':
xdp_flags |= XDP_FLAGS_SKB_MODE;
break;
+ case 'N':
+ xdp_flags |= XDP_FLAGS_DRV_MODE;
+ break;
default:
usage(basename(argv[0]));
return 1;
}
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
if (set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) {
printf("link set xdp fd failed\n");
printf(" -m <dest-MAC> Used in sending the IP Tunneled pkt\n");
printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n");
printf(" -P <IP-Protocol> Default is TCP\n");
+ printf(" -S use skb-mode\n");
+ printf(" -N enforce native mode\n");
printf(" -h Display this help\n");
}
{
unsigned char opt_flags[256] = {};
unsigned int kill_after_s = 0;
- const char *optstr = "i:a:p:s:d:m:T:P:Sh";
+ const char *optstr = "i:a:p:s:d:m:T:P:SNh";
int min_port = 0, max_port = 0;
struct iptnl_info tnl = {};
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
case 'S':
xdp_flags |= XDP_FLAGS_SKB_MODE;
break;
+ case 'N':
+ xdp_flags |= XDP_FLAGS_DRV_MODE;
+ break;
default:
usage(argv[0]);
return 1;
}
signal(SIGINT, int_exit);
+ signal(SIGTERM, int_exit);
while (min_port <= max_port) {
vip.dport = htons(min_port++);
attr.log_size = 0;
attr.log_level = 0;
attr.kern_version = 0;
+ attr.prog_flags = 0;
/*
* Test existence of __NR_bpf and BPF_PROG_LOAD.
*/
#define BPF_F_ALLOW_OVERRIDE (1U << 0)
+/* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
+ * verifier will perform strict alignment checking as if the kernel
+ * has been built with CONFIG_EFFICIENT_UNALIGNED_ACCESS not set,
+ * and NET_IP_ALIGN defined to 2.
+ */
+#define BPF_F_STRICT_ALIGNMENT (1U << 0)
+
#define BPF_PSEUDO_MAP_FD 1
/* flags for BPF_MAP_UPDATE_ELEM command */
__u32 log_size; /* size of user buffer */
__aligned_u64 log_buf; /* user supplied buffer */
__u32 kern_version; /* checked when prog_type=kprobe */
+ __u32 prog_flags;
};
struct { /* anonymous struct used by BPF_OBJ_* commands */
* u32 bpf_get_socket_uid(skb)
* Get the owner uid of the socket stored inside sk_buff.
* @skb: pointer to skb
- * Return: uid of the socket owner on success or 0 if the socket pointer
- * inside sk_buff is NULL
+ * Return: uid of the socket owner on success or overflowuid if failed.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
}
+int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+ size_t insns_cnt, int strict_alignment,
+ const char *license, __u32 kern_version,
+ char *log_buf, size_t log_buf_sz)
+{
+ union bpf_attr attr;
+
+ bzero(&attr, sizeof(attr));
+ attr.prog_type = type;
+ attr.insn_cnt = (__u32)insns_cnt;
+ attr.insns = ptr_to_u64(insns);
+ attr.license = ptr_to_u64(license);
+ attr.log_buf = ptr_to_u64(log_buf);
+ attr.log_size = log_buf_sz;
+ attr.log_level = 2;
+ log_buf[0] = 0;
+ attr.kern_version = kern_version;
+ attr.prog_flags = strict_alignment ? BPF_F_STRICT_ALIGNMENT : 0;
+
+ return sys_bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
+}
+
int bpf_map_update_elem(int fd, const void *key, const void *value,
__u64 flags)
{
size_t insns_cnt, const char *license,
__u32 kern_version, char *log_buf,
size_t log_buf_sz);
+int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns,
+ size_t insns_cnt, int strict_alignment,
+ const char *license, __u32 kern_version,
+ char *log_buf, size_t log_buf_sz);
int bpf_map_update_elem(int fd, const void *key, const void *value,
__u64 flags);
CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
LDLIBS += -lcap -lelf
-TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs
+TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
+ test_align
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o
CLANG ?= clang
%.o: %.c
- $(CLANG) -I. -I../../../include/uapi -I../../../../samples/bpf/ \
+ $(CLANG) -I. -I./include/uapi -I../../../include/uapi \
+ -I../../../../samples/bpf/ \
-Wno-compare-distinct-pointer-types \
-O2 -target bpf -c $< -o $@
--- /dev/null
+#ifndef _UAPI_LINUX_TYPES_H
+#define _UAPI_LINUX_TYPES_H
+
+#include <asm-generic/int-ll64.h>
+
+#endif /* _UAPI_LINUX_TYPES_H */
--- /dev/null
+#include <asm/types.h>
+#include <linux/types.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <errno.h>
+#include <string.h>
+#include <stddef.h>
+#include <stdbool.h>
+
+#include <linux/unistd.h>
+#include <linux/filter.h>
+#include <linux/bpf_perf_event.h>
+#include <linux/bpf.h>
+
+#include <bpf/bpf.h>
+
+#include "../../../include/linux/filter.h"
+
+#ifndef ARRAY_SIZE
+# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+#define MAX_INSNS 512
+#define MAX_MATCHES 16
+
+struct bpf_align_test {
+ const char *descr;
+ struct bpf_insn insns[MAX_INSNS];
+ enum {
+ UNDEF,
+ ACCEPT,
+ REJECT
+ } result;
+ enum bpf_prog_type prog_type;
+ const char *matches[MAX_MATCHES];
+};
+
+static struct bpf_align_test tests[] = {
+ {
+ .descr = "mov",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_3, 2),
+ BPF_MOV64_IMM(BPF_REG_3, 4),
+ BPF_MOV64_IMM(BPF_REG_3, 8),
+ BPF_MOV64_IMM(BPF_REG_3, 16),
+ BPF_MOV64_IMM(BPF_REG_3, 32),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "1: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
+ "2: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+ "3: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+ "4: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
+ "5: R1=ctx R3=imm32,min_value=32,max_value=32,min_align=32 R10=fp",
+ },
+ },
+ {
+ .descr = "shift",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_3, 4),
+ BPF_MOV64_IMM(BPF_REG_4, 32),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "1: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp",
+ "2: R1=ctx R3=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
+ "3: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+ "4: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+ "5: R1=ctx R3=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
+ "6: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R10=fp",
+ "7: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm32,min_value=32,max_value=32,min_align=32 R10=fp",
+ "8: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm16,min_value=16,max_value=16,min_align=16 R10=fp",
+ "9: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+ "10: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+ "11: R1=ctx R3=imm1,min_value=1,max_value=1,min_align=1 R4=imm2,min_value=2,max_value=2,min_align=2 R10=fp",
+ },
+ },
+ {
+ .descr = "addsub",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_3, 4),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 4),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 2),
+ BPF_MOV64_IMM(BPF_REG_4, 8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "1: R1=ctx R3=imm4,min_value=4,max_value=4,min_align=4 R10=fp",
+ "2: R1=ctx R3=imm8,min_value=8,max_value=8,min_align=4 R10=fp",
+ "3: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R10=fp",
+ "4: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm8,min_value=8,max_value=8,min_align=8 R10=fp",
+ "5: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm12,min_value=12,max_value=12,min_align=4 R10=fp",
+ "6: R1=ctx R3=imm10,min_value=10,max_value=10,min_align=2 R4=imm14,min_value=14,max_value=14,min_align=2 R10=fp",
+ },
+ },
+ {
+ .descr = "mul",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_3, 7),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 2),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 4),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "1: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp",
+ "2: R1=ctx R3=imm7,min_value=7,max_value=7,min_align=1 R10=fp",
+ "3: R1=ctx R3=imm14,min_value=14,max_value=14,min_align=2 R10=fp",
+ "4: R1=ctx R3=imm56,min_value=56,max_value=56,min_align=4 R10=fp",
+ },
+ },
+
+#define PREP_PKT_POINTERS \
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, \
+ offsetof(struct __sk_buff, data)), \
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, \
+ offsetof(struct __sk_buff, data_end))
+
+#define LOAD_UNKNOWN(DST_REG) \
+ PREP_PKT_POINTERS, \
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), \
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8), \
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_0, 1), \
+ BPF_EXIT_INSN(), \
+ BPF_LDX_MEM(BPF_B, DST_REG, BPF_REG_2, 0)
+
+ {
+ .descr = "unknown shift",
+ .insns = {
+ LOAD_UNKNOWN(BPF_REG_3),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_3, 1),
+ LOAD_UNKNOWN(BPF_REG_4),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_4, 5),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_ALU64_IMM(BPF_RSH, BPF_REG_4, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp",
+ "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv55,min_align=2 R10=fp",
+ "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv54,min_align=4 R10=fp",
+ "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv53,min_align=8 R10=fp",
+ "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv52,min_align=16 R10=fp",
+ "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv56 R10=fp",
+ "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv51,min_align=32 R10=fp",
+ "20: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv52,min_align=16 R10=fp",
+ "21: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv53,min_align=8 R10=fp",
+ "22: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv54,min_align=4 R10=fp",
+ "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv55,min_align=2 R10=fp",
+ },
+ },
+ {
+ .descr = "unknown mul",
+ .insns = {
+ LOAD_UNKNOWN(BPF_REG_3),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 1),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 4),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_3),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 8),
+ BPF_ALU64_IMM(BPF_MUL, BPF_REG_4, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "7: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R10=fp",
+ "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+ "9: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv55,min_align=1 R10=fp",
+ "10: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+ "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv54,min_align=2 R10=fp",
+ "12: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+ "13: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv53,min_align=4 R10=fp",
+ "14: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv56 R10=fp",
+ "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv52,min_align=8 R10=fp",
+ "16: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=inv56 R4=inv50,min_align=8 R10=fp"
+ },
+ },
+ {
+ .descr = "packet const offset",
+ .insns = {
+ PREP_PKT_POINTERS,
+ BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+
+ /* Skip over ethernet header. */
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+ BPF_EXIT_INSN(),
+
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 2),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_5, 3),
+ BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 0),
+ BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_5, 2),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
+
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ "4: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=0,r=0) R10=fp",
+ "5: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R5=pkt(id=0,off=14,r=0) R10=fp",
+ "6: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=0) R3=pkt_end R4=pkt(id=0,off=14,r=0) R5=pkt(id=0,off=14,r=0) R10=fp",
+ "10: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv56 R5=pkt(id=0,off=14,r=18) R10=fp",
+ "14: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp",
+ "15: R0=imm0,min_value=0,max_value=0,min_align=2147483648 R1=ctx R2=pkt(id=0,off=0,r=18) R3=pkt_end R4=inv48 R5=pkt(id=0,off=14,r=18) R10=fp",
+ },
+ },
+ {
+ .descr = "packet variable offset",
+ .insns = {
+ LOAD_UNKNOWN(BPF_REG_6),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_6, 2),
+
+ /* First, add a constant to the R5 packet pointer,
+ * then a variable with a known alignment.
+ */
+ BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+ BPF_EXIT_INSN(),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
+
+ /* Now, test in the other direction. Adding first
+ * the variable offset to R5, then the constant.
+ */
+ BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+ BPF_EXIT_INSN(),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
+
+ /* Test multiple accumulations of unknown values
+ * into a packet pointer.
+ */
+ BPF_MOV64_REG(BPF_REG_5, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 14),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_5, 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_5, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_5),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 4),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_4, 1),
+ BPF_EXIT_INSN(),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_5, 0),
+
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .matches = {
+ /* Calculated offset in R6 has unknown value, but known
+ * alignment of 4.
+ */
+ "8: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R6=inv54,min_align=4 R10=fp",
+
+ /* Offset is added to packet pointer R5, resulting in known
+ * auxiliary alignment and offset.
+ */
+ "11: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R5=pkt(id=1,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+ /* At the time the word size load is performed from R5,
+ * it's total offset is NET_IP_ALIGN + reg->off (0) +
+ * reg->aux_off (14) which is 16. Then the variable
+ * offset is considered using reg->aux_off_align which
+ * is 4 and meets the load's requirements.
+ */
+ "15: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=1,off=4,r=4),aux_off=14,aux_off_align=4 R5=pkt(id=1,off=0,r=4),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+
+ /* Variable offset is added to R5 packet pointer,
+ * resulting in auxiliary alignment of 4.
+ */
+ "18: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=0,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+ /* Constant offset is added to R5, resulting in
+ * reg->off of 14.
+ */
+ "19: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off=14,aux_off_align=4 R5=pkt(id=2,off=14,r=0),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+ /* At the time the word size load is performed from R5,
+ * it's total offset is NET_IP_ALIGN + reg->off (14) which
+ * is 16. Then the variable offset is considered using
+ * reg->aux_off_align which is 4 and meets the load's
+ * requirements.
+ */
+ "23: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=2,off=18,r=18),aux_off_align=4 R5=pkt(id=2,off=14,r=18),aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+
+ /* Constant offset is added to R5 packet pointer,
+ * resulting in reg->off value of 14.
+ */
+ "26: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=0,off=14,r=8) R6=inv54,min_align=4 R10=fp",
+ /* Variable offset is added to R5, resulting in an
+ * auxiliary offset of 14, and an auxiliary alignment of 4.
+ */
+ "27: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=0,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+ /* Constant is added to R5 again, setting reg->off to 4. */
+ "28: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=3,off=4,r=0),aux_off=14,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+ /* And once more we add a variable, which causes an accumulation
+ * of reg->off into reg->aux_off_align, with resulting value of
+ * 18. The auxiliary alignment stays at 4.
+ */
+ "29: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=inv,aux_off_align=4 R5=pkt(id=4,off=0,r=0),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+ /* At the time the word size load is performed from R5,
+ * it's total offset is NET_IP_ALIGN + reg->off (0) +
+ * reg->aux_off (18) which is 20. Then the variable offset
+ * is considered using reg->aux_off_align which is 4 and meets
+ * the load's requirements.
+ */
+ "33: R0=pkt(id=0,off=8,r=8) R1=ctx R2=pkt(id=0,off=0,r=8) R3=pkt_end R4=pkt(id=4,off=4,r=4),aux_off=18,aux_off_align=4 R5=pkt(id=4,off=0,r=4),aux_off=18,aux_off_align=4 R6=inv54,min_align=4 R10=fp",
+ },
+ },
+};
+
+static int probe_filter_length(const struct bpf_insn *fp)
+{
+ int len;
+
+ for (len = MAX_INSNS - 1; len > 0; --len)
+ if (fp[len].code != 0 || fp[len].imm != 0)
+ break;
+ return len + 1;
+}
+
+static char bpf_vlog[32768];
+
+static int do_test_single(struct bpf_align_test *test)
+{
+ struct bpf_insn *prog = test->insns;
+ int prog_type = test->prog_type;
+ int prog_len, i;
+ int fd_prog;
+ int ret;
+
+ prog_len = probe_filter_length(prog);
+ fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
+ prog, prog_len, 1, "GPL", 0,
+ bpf_vlog, sizeof(bpf_vlog));
+ if (fd_prog < 0) {
+ printf("Failed to load program.\n");
+ printf("%s", bpf_vlog);
+ ret = 1;
+ } else {
+ ret = 0;
+ for (i = 0; i < MAX_MATCHES; i++) {
+ const char *t, *m = test->matches[i];
+
+ if (!m)
+ break;
+ t = strstr(bpf_vlog, m);
+ if (!t) {
+ printf("Failed to find match: %s\n", m);
+ ret = 1;
+ printf("%s", bpf_vlog);
+ break;
+ }
+ }
+ close(fd_prog);
+ }
+ return ret;
+}
+
+static int do_test(unsigned int from, unsigned int to)
+{
+ int all_pass = 0;
+ int all_fail = 0;
+ unsigned int i;
+
+ for (i = from; i < to; i++) {
+ struct bpf_align_test *test = &tests[i];
+ int fail;
+
+ printf("Test %3d: %s ... ",
+ i, test->descr);
+ fail = do_test_single(test);
+ if (fail) {
+ all_fail++;
+ printf("FAIL\n");
+ } else {
+ all_pass++;
+ printf("PASS\n");
+ }
+ }
+ printf("Results: %d pass %d fail\n",
+ all_pass, all_fail);
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ unsigned int from = 0, to = ARRAY_SIZE(tests);
+
+ if (argc == 3) {
+ unsigned int l = atoi(argv[argc - 2]);
+ unsigned int u = atoi(argv[argc - 1]);
+
+ if (l < to && u < to) {
+ from = l;
+ to = u + 1;
+ }
+ } else if (argc == 2) {
+ unsigned int t = atoi(argv[argc - 1]);
+
+ if (t < to) {
+ from = t;
+ to = t + 1;
+ }
+ }
+ return do_test(from, to);
+}
projects / karo-tx-linux.git / commitdiff