int (*set_loopback)(struct hnae3_handle *handle,
enum hnae3_loop loop_mode, bool en);
- void (*set_promisc_mode)(struct hnae3_handle *handle, bool en_uc_pmc,
- bool en_mc_pmc);
+ int (*set_promisc_mode)(struct hnae3_handle *handle, bool en_uc_pmc,
+ bool en_mc_pmc);
int (*set_mtu)(struct hnae3_handle *handle, int new_mtu);
void (*get_pauseparam)(struct hnae3_handle *handle,
int vector_num,
struct hnae3_ring_chain_node *vr_chain);
- void (*reset_queue)(struct hnae3_handle *handle, u16 queue_id);
+ int (*reset_queue)(struct hnae3_handle *handle, u16 queue_id);
u32 (*get_fw_version)(struct hnae3_handle *handle);
void (*get_mdix_mode)(struct hnae3_handle *handle,
u8 *tp_mdix_ctrl, u8 *tp_mdix);
h->netdev_flags = new_flags;
}
-void hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags)
+int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = priv->ae_handle;
if (h->ae_algo->ops->set_promisc_mode) {
- h->ae_algo->ops->set_promisc_mode(h,
- promisc_flags & HNAE3_UPE,
- promisc_flags & HNAE3_MPE);
+ return h->ae_algo->ops->set_promisc_mode(h,
+ promisc_flags & HNAE3_UPE,
+ promisc_flags & HNAE3_MPE);
}
+
+ return 0;
}
void hns3_enable_vlan_filter(struct net_device *netdev, bool enable)
return ret;
}
-static void hns3_restore_vlan(struct net_device *netdev)
+static int hns3_restore_vlan(struct net_device *netdev)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
+ int ret = 0;
u16 vid;
- int ret;
for_each_set_bit(vid, priv->active_vlans, VLAN_N_VID) {
ret = hns3_vlan_rx_add_vid(netdev, htons(ETH_P_8021Q), vid);
- if (ret)
- netdev_warn(netdev, "Restore vlan: %d filter, ret:%d\n",
- vid, ret);
+ if (ret) {
+ netdev_err(netdev, "Restore vlan: %d filter, ret:%d\n",
+ vid, ret);
+ return ret;
+ }
}
+
+ return ret;
}
static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
chain = devm_kzalloc(&pdev->dev, sizeof(*chain),
GFP_KERNEL);
if (!chain)
- return -ENOMEM;
+ goto err_free_chain;
cur_chain->next = chain;
chain->tqp_index = tx_ring->tqp->tqp_index;
while (rx_ring) {
chain = devm_kzalloc(&pdev->dev, sizeof(*chain), GFP_KERNEL);
if (!chain)
- return -ENOMEM;
+ goto err_free_chain;
cur_chain->next = chain;
chain->tqp_index = rx_ring->tqp->tqp_index;
}
return 0;
+
+err_free_chain:
+ cur_chain = head->next;
+ while (cur_chain) {
+ chain = cur_chain->next;
+ devm_kfree(&pdev->dev, chain);
+ cur_chain = chain;
+ }
+
+ return -ENOMEM;
}
static void hns3_free_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector,
struct hnae3_handle *h = priv->ae_handle;
struct hns3_enet_tqp_vector *tqp_vector;
int ret = 0;
- u16 i;
+ int i;
hns3_nic_set_cpumask(priv);
hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain);
if (ret)
- return ret;
+ goto map_ring_fail;
netif_napi_add(priv->netdev, &tqp_vector->napi,
hns3_nic_common_poll, NAPI_POLL_WEIGHT);
}
return 0;
+
+map_ring_fail:
+ while (i--)
+ netif_napi_del(&priv->tqp_vector[i].napi);
+
+ return ret;
}
static int hns3_nic_alloc_vector_data(struct hns3_nic_priv *priv)
return ret;
ret = hns3_ring_get_cfg(tqp, priv, HNAE3_RING_TYPE_RX);
- if (ret)
+ if (ret) {
+ devm_kfree(priv->dev, priv->ring_data[tqp->tqp_index].ring);
return ret;
+ }
return 0;
}
return 0;
err:
+ while (i--) {
+ devm_kfree(priv->dev, priv->ring_data[i].ring);
+ devm_kfree(priv->dev,
+ priv->ring_data[i + h->kinfo.num_tqps].ring);
+ }
+
devm_kfree(&pdev->dev, priv->ring_data);
return ret;
}
int i;
for (i = 0; i < h->kinfo.num_tqps; i++) {
- if (h->ae_algo->ops->reset_queue)
- h->ae_algo->ops->reset_queue(h, i);
-
hns3_fini_ring(priv->ring_data[i].ring);
hns3_fini_ring(priv->ring_data[i + h->kinfo.num_tqps].ring);
}
}
/* Set mac addr if it is configured. or leave it to the AE driver */
-static void hns3_init_mac_addr(struct net_device *netdev, bool init)
+static int hns3_init_mac_addr(struct net_device *netdev, bool init)
{
struct hns3_nic_priv *priv = netdev_priv(netdev);
struct hnae3_handle *h = priv->ae_handle;
u8 mac_addr_temp[ETH_ALEN];
+ int ret = 0;
if (h->ae_algo->ops->get_mac_addr && init) {
h->ae_algo->ops->get_mac_addr(h, mac_addr_temp);
}
if (h->ae_algo->ops->set_mac_addr)
- h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr, true);
+ ret = h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr, true);
+ return ret;
}
static int hns3_restore_fd_rules(struct net_device *netdev)
return ret;
}
-static void hns3_recover_hw_addr(struct net_device *ndev)
+static int hns3_recover_hw_addr(struct net_device *ndev)
{
struct netdev_hw_addr_list *list;
struct netdev_hw_addr *ha, *tmp;
+ int ret = 0;
/* go through and sync uc_addr entries to the device */
list = &ndev->uc;
- list_for_each_entry_safe(ha, tmp, &list->list, list)
- hns3_nic_uc_sync(ndev, ha->addr);
+ list_for_each_entry_safe(ha, tmp, &list->list, list) {
+ ret = hns3_nic_uc_sync(ndev, ha->addr);
+ if (ret)
+ return ret;
+ }
/* go through and sync mc_addr entries to the device */
list = &ndev->mc;
- list_for_each_entry_safe(ha, tmp, &list->list, list)
- hns3_nic_mc_sync(ndev, ha->addr);
+ list_for_each_entry_safe(ha, tmp, &list->list, list) {
+ ret = hns3_nic_mc_sync(ndev, ha->addr);
+ if (ret)
+ return ret;
+ }
+
+ return ret;
}
static void hns3_remove_hw_addr(struct net_device *netdev)
int ret;
for (i = 0; i < h->kinfo.num_tqps; i++) {
- h->ae_algo->ops->reset_queue(h, i);
+ ret = h->ae_algo->ops->reset_queue(h, i);
+ if (ret)
+ return ret;
+
hns3_init_ring_hw(priv->ring_data[i].ring);
/* We need to clear tx ring here because self test will
bool vlan_filter_enable;
int ret;
- hns3_init_mac_addr(netdev, false);
- hns3_recover_hw_addr(netdev);
- hns3_update_promisc_mode(netdev, handle->netdev_flags);
+ ret = hns3_init_mac_addr(netdev, false);
+ if (ret)
+ return ret;
+
+ ret = hns3_recover_hw_addr(netdev);
+ if (ret)
+ return ret;
+
+ ret = hns3_update_promisc_mode(netdev, handle->netdev_flags);
+ if (ret)
+ return ret;
+
vlan_filter_enable = netdev->flags & IFF_PROMISC ? false : true;
hns3_enable_vlan_filter(netdev, vlan_filter_enable);
-
/* Hardware table is only clear when pf resets */
- if (!(handle->flags & HNAE3_SUPPORT_VF))
- hns3_restore_vlan(netdev);
+ if (!(handle->flags & HNAE3_SUPPORT_VF)) {
+ ret = hns3_restore_vlan(netdev);
+ return ret;
+ }
- hns3_restore_fd_rules(netdev);
+ ret = hns3_restore_fd_rules(netdev);
+ if (ret)
+ return ret;
/* Carrier off reporting is important to ethtool even BEFORE open */
netif_carrier_off(netdev);
u32 rl_value);
void hns3_enable_vlan_filter(struct net_device *netdev, bool enable);
-void hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags);
+int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags);
#ifdef CONFIG_HNS3_DCB
void hns3_dcbnl_setup(struct hnae3_handle *handle);
return ring->desc_num - used - 1;
}
-static int is_valid_csq_clean_head(struct hclge_cmq_ring *ring, int h)
+static int is_valid_csq_clean_head(struct hclge_cmq_ring *ring, int head)
{
- int u = ring->next_to_use;
- int c = ring->next_to_clean;
+ int ntu = ring->next_to_use;
+ int ntc = ring->next_to_clean;
- if (unlikely(h >= ring->desc_num))
- return 0;
+ if (ntu > ntc)
+ return head >= ntc && head <= ntu;
- return u > c ? (h > c && h <= u) : (h > c || h <= u);
+ return head >= ntc || head <= ntu;
}
static int hclge_alloc_cmd_desc(struct hclge_cmq_ring *ring)
{
int ret;
+ /* Setup the lock for command queue */
+ spin_lock_init(&hdev->hw.cmq.csq.lock);
+ spin_lock_init(&hdev->hw.cmq.crq.lock);
+
/* Setup the queue entries for use cmd queue */
hdev->hw.cmq.csq.desc_num = HCLGE_NIC_CMQ_DESC_NUM;
hdev->hw.cmq.crq.desc_num = HCLGE_NIC_CMQ_DESC_NUM;
u32 version;
int ret;
+ spin_lock_bh(&hdev->hw.cmq.csq.lock);
+ spin_lock_bh(&hdev->hw.cmq.crq.lock);
+
hdev->hw.cmq.csq.next_to_clean = 0;
hdev->hw.cmq.csq.next_to_use = 0;
hdev->hw.cmq.crq.next_to_clean = 0;
hdev->hw.cmq.crq.next_to_use = 0;
- /* Setup the lock for command queue */
- spin_lock_init(&hdev->hw.cmq.csq.lock);
- spin_lock_init(&hdev->hw.cmq.crq.lock);
-
hclge_cmd_init_regs(&hdev->hw);
clear_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+ spin_unlock_bh(&hdev->hw.cmq.crq.lock);
+ spin_unlock_bh(&hdev->hw.cmq.csq.lock);
+
ret = hclge_cmd_query_firmware_version(&hdev->hw, &version);
if (ret) {
dev_err(&hdev->pdev->dev,
ret = hclge_cmd_clear_error(hdev, &desc_wr, &desc_rd,
HCLGE_NCSI_INT_CLR, 0);
if (ret)
- dev_err(dev, "failed(=%d) to clear NCSI intrerrupt status\n",
+ dev_err(dev, "failed(=%d) to clear NCSI interrupt status\n",
ret);
}
}
/* clear the source of interrupt if it is not cause by reset */
- if (event_cause != HCLGE_VECTOR0_EVENT_RST) {
+ if (event_cause == HCLGE_VECTOR0_EVENT_MBX) {
hclge_clear_event_cause(hdev, event_cause, clearval);
hclge_enable_vector(&hdev->misc_vector, true);
}
handle = &hdev->vport[0].nic;
rtnl_lock();
hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+ rtnl_unlock();
if (!hclge_reset_wait(hdev)) {
+ rtnl_lock();
hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
hclge_reset_ae_dev(hdev->ae_dev);
hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
hclge_clear_reset_cause(hdev);
} else {
+ rtnl_lock();
/* schedule again to check pending resets later */
set_bit(hdev->reset_type, &hdev->reset_pending);
hclge_reset_task_schedule(hdev);
param->vf_id = vport_id;
}
-static void hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc,
- bool en_mc_pmc)
+static int hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc,
+ bool en_mc_pmc)
{
struct hclge_vport *vport = hclge_get_vport(handle);
struct hclge_dev *hdev = vport->back;
hclge_promisc_param_init(¶m, en_uc_pmc, en_mc_pmc, true,
vport->vport_id);
- hclge_cmd_set_promisc_mode(hdev, ¶m);
+ return hclge_cmd_set_promisc_mode(hdev, ¶m);
}
static int hclge_get_fd_mode(struct hclge_dev *hdev, u8 *fd_mode)
return tqp->index;
}
-void hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
+int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
{
struct hclge_vport *vport = hclge_get_vport(handle);
struct hclge_dev *hdev = vport->back;
int reset_try_times = 0;
int reset_status;
u16 queue_gid;
- int ret;
-
- if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
- return;
+ int ret = 0;
queue_gid = hclge_covert_handle_qid_global(handle, queue_id);
ret = hclge_tqp_enable(hdev, queue_id, 0, false);
if (ret) {
- dev_warn(&hdev->pdev->dev, "Disable tqp fail, ret = %d\n", ret);
- return;
+ dev_err(&hdev->pdev->dev, "Disable tqp fail, ret = %d\n", ret);
+ return ret;
}
ret = hclge_send_reset_tqp_cmd(hdev, queue_gid, true);
if (ret) {
- dev_warn(&hdev->pdev->dev,
- "Send reset tqp cmd fail, ret = %d\n", ret);
- return;
+ dev_err(&hdev->pdev->dev,
+ "Send reset tqp cmd fail, ret = %d\n", ret);
+ return ret;
}
reset_try_times = 0;
}
if (reset_try_times >= HCLGE_TQP_RESET_TRY_TIMES) {
- dev_warn(&hdev->pdev->dev, "Reset TQP fail\n");
- return;
+ dev_err(&hdev->pdev->dev, "Reset TQP fail\n");
+ return ret;
}
ret = hclge_send_reset_tqp_cmd(hdev, queue_gid, false);
- if (ret) {
- dev_warn(&hdev->pdev->dev,
- "Deassert the soft reset fail, ret = %d\n", ret);
- return;
- }
+ if (ret)
+ dev_err(&hdev->pdev->dev,
+ "Deassert the soft reset fail, ret = %d\n", ret);
+
+ return ret;
}
void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id)
void hclge_rss_indir_init_cfg(struct hclge_dev *hdev);
void hclge_mbx_handler(struct hclge_dev *hdev);
-void hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id);
+int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id);
void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id);
int hclge_cfg_flowctrl(struct hclge_dev *hdev);
int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id);
/* handle all the mailbox requests in the queue */
while (!hclge_cmd_crq_empty(&hdev->hw)) {
+ if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) {
+ dev_warn(&hdev->pdev->dev,
+ "command queue needs re-initializing\n");
+ return;
+ }
+
desc = &crq->desc[crq->next_to_use];
req = (struct hclge_mbx_vf_to_pf_cmd *)desc->data;
struct hclge_desc desc;
int ret;
- if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
+ if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state))
return 0;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MDIO_CONFIG, false);
struct hclge_desc desc;
int ret;
- if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
+ if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state))
return 0;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MDIO_CONFIG, true);
return status;
}
-static void hclgevf_set_promisc_mode(struct hnae3_handle *handle,
- bool en_uc_pmc, bool en_mc_pmc)
+static int hclgevf_set_promisc_mode(struct hnae3_handle *handle,
+ bool en_uc_pmc, bool en_mc_pmc)
{
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
- hclgevf_cmd_set_promisc_mode(hdev, en_uc_pmc, en_mc_pmc);
+ return hclgevf_cmd_set_promisc_mode(hdev, en_uc_pmc, en_mc_pmc);
}
static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, int tqp_id,
1, false, NULL, 0);
}
-static void hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
+static int hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
{
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
u8 msg_data[2];
/* disable vf queue before send queue reset msg to PF */
ret = hclgevf_tqp_enable(hdev, queue_id, 0, false);
if (ret)
- return;
+ return ret;
- hclgevf_send_mbx_msg(hdev, HCLGE_MBX_QUEUE_RESET, 0, msg_data,
- 2, true, NULL, 0);
+ return hclgevf_send_mbx_msg(hdev, HCLGE_MBX_QUEUE_RESET, 0, msg_data,
+ 2, true, NULL, 0);
}
static int hclgevf_notify_client(struct hclgevf_dev *hdev,
/* bring down the nic to stop any ongoing TX/RX */
hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT);
+ rtnl_unlock();
+
/* check if VF could successfully fetch the hardware reset completion
* status from the hardware
*/
ret);
dev_warn(&hdev->pdev->dev, "VF reset failed, disabling VF!\n");
+ rtnl_lock();
hclgevf_notify_client(hdev, HNAE3_UNINIT_CLIENT);
rtnl_unlock();
return ret;
}
+ rtnl_lock();
+
/* now, re-initialize the nic client and ae device*/
ret = hclgevf_reset_stack(hdev);
if (ret)
rq->stats->ecn_mark += !!rc;
}
-static __be32 mlx5e_get_fcs(struct sk_buff *skb)
+static u32 mlx5e_get_fcs(const struct sk_buff *skb)
{
- int last_frag_sz, bytes_in_prev, nr_frags;
- u8 *fcs_p1, *fcs_p2;
- skb_frag_t *last_frag;
- __be32 fcs_bytes;
+ const void *fcs_bytes;
+ u32 _fcs_bytes;
- if (!skb_is_nonlinear(skb))
- return *(__be32 *)(skb->data + skb->len - ETH_FCS_LEN);
+ fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN,
+ ETH_FCS_LEN, &_fcs_bytes);
- nr_frags = skb_shinfo(skb)->nr_frags;
- last_frag = &skb_shinfo(skb)->frags[nr_frags - 1];
- last_frag_sz = skb_frag_size(last_frag);
-
- /* If all FCS data is in last frag */
- if (last_frag_sz >= ETH_FCS_LEN)
- return *(__be32 *)(skb_frag_address(last_frag) +
- last_frag_sz - ETH_FCS_LEN);
-
- fcs_p2 = (u8 *)skb_frag_address(last_frag);
- bytes_in_prev = ETH_FCS_LEN - last_frag_sz;
-
- /* Find where the other part of the FCS is - Linear or another frag */
- if (nr_frags == 1) {
- fcs_p1 = skb_tail_pointer(skb);
- } else {
- skb_frag_t *prev_frag = &skb_shinfo(skb)->frags[nr_frags - 2];
-
- fcs_p1 = skb_frag_address(prev_frag) +
- skb_frag_size(prev_frag);
- }
- fcs_p1 -= bytes_in_prev;
-
- memcpy(&fcs_bytes, fcs_p1, bytes_in_prev);
- memcpy(((u8 *)&fcs_bytes) + bytes_in_prev, fcs_p2, last_frag_sz);
-
- return fcs_bytes;
+ return __get_unaligned_cpu32(fcs_bytes);
}
static u8 get_ip_proto(struct sk_buff *skb, __be16 proto)
network_depth - ETH_HLEN,
skb->csum);
if (unlikely(netdev->features & NETIF_F_RXFCS))
- skb->csum = csum_add(skb->csum,
- (__force __wsum)mlx5e_get_fcs(skb));
+ skb->csum = csum_block_add(skb->csum,
+ (__force __wsum)mlx5e_get_fcs(skb),
+ skb->len - ETH_FCS_LEN);
stats->csum_complete++;
return;
}
* Configures the ETS elements.
*/
#define MLXSW_REG_QEEC_ID 0x400D
-#define MLXSW_REG_QEEC_LEN 0x1C
+#define MLXSW_REG_QEEC_LEN 0x20
MLXSW_REG_DEFINE(qeec, MLXSW_REG_QEEC_ID, MLXSW_REG_QEEC_LEN);
*/
MLXSW_ITEM32(reg, qeec, next_element_index, 0x08, 0, 8);
+/* reg_qeec_mise
+ * Min shaper configuration enable. Enables configuration of the min
+ * shaper on this ETS element
+ * 0 - Disable
+ * 1 - Enable
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qeec, mise, 0x0C, 31, 1);
+
enum {
MLXSW_REG_QEEC_BYTES_MODE,
MLXSW_REG_QEEC_PACKETS_MODE,
*/
MLXSW_ITEM32(reg, qeec, pb, 0x0C, 28, 1);
+/* The smallest permitted min shaper rate. */
+#define MLXSW_REG_QEEC_MIS_MIN 200000 /* Kbps */
+
+/* reg_qeec_min_shaper_rate
+ * Min shaper information rate.
+ * For CPU port, can only be configured for port hierarchy.
+ * When in bytes mode, value is specified in units of 1000bps.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qeec, min_shaper_rate, 0x0C, 0, 28);
+
/* reg_qeec_mase
* Max shaper configuration enable. Enables configuration of the max
* shaper on this ETS element.
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qeec), qeec_pl);
}
+static int mlxsw_sp_port_min_bw_set(struct mlxsw_sp_port *mlxsw_sp_port,
+ enum mlxsw_reg_qeec_hr hr, u8 index,
+ u8 next_index, u32 minrate)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ char qeec_pl[MLXSW_REG_QEEC_LEN];
+
+ mlxsw_reg_qeec_pack(qeec_pl, mlxsw_sp_port->local_port, hr, index,
+ next_index);
+ mlxsw_reg_qeec_mise_set(qeec_pl, true);
+ mlxsw_reg_qeec_min_shaper_rate_set(qeec_pl, minrate);
+
+ return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qeec), qeec_pl);
+}
+
int mlxsw_sp_port_prio_tc_set(struct mlxsw_sp_port *mlxsw_sp_port,
u8 switch_prio, u8 tclass)
{
return err;
}
+ /* Configure the min shaper for multicast TCs. */
+ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+ err = mlxsw_sp_port_min_bw_set(mlxsw_sp_port,
+ MLXSW_REG_QEEC_HIERARCY_TC,
+ i + 8, i,
+ MLXSW_REG_QEEC_MIS_MIN);
+ if (err)
+ return err;
+ }
+
/* Map all priorities to traffic class 0. */
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
err = mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, i, 0);
#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/interval_tree_generic.h>
+#include <linux/nospec.h>
#include "vhost.h"
if (idx >= d->nvqs)
return -ENOBUFS;
+ idx = array_index_nospec(idx, d->nvqs);
vq = d->vqs[idx];
mutex_lock(&vq->mutex);
* PTR_TO_MAP_VALUE_OR_NULL
*/
struct bpf_map *map_ptr;
+
+ /* Max size from any of the above. */
+ unsigned long raw;
};
/* Fixed part of pointer offset, pointer types only */
s32 off;
void unix_gc(void);
void wait_for_unix_gc(void);
struct sock *unix_get_socket(struct file *filp);
-struct sock *unix_peer_get(struct sock *);
+struct sock *unix_peer_get(struct sock *sk);
#define UNIX_HASH_SIZE 256
#define UNIX_HASH_BITS 8
u32 consumed;
} __randomize_layout;
-#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb))
+#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb))
#define unix_state_lock(s) spin_lock(&unix_sk(s)->lock)
#define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock)
regs[BPF_REG_0].type = NOT_INIT;
} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
fn->ret_type == RET_PTR_TO_MAP_VALUE) {
- if (fn->ret_type == RET_PTR_TO_MAP_VALUE)
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
- else
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
/* remember map_ptr, so that check_map_access()
return -EINVAL;
}
regs[BPF_REG_0].map_ptr = meta.map_ptr;
- regs[BPF_REG_0].id = ++env->id_gen;
+ if (fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
+ } else {
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+ regs[BPF_REG_0].id = ++env->id_gen;
+ }
} else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
int id = acquire_reference_state(env, insn_idx);
if (id < 0)
dst_reg->umax_value = umax_ptr;
dst_reg->var_off = ptr_reg->var_off;
dst_reg->off = ptr_reg->off + smin_val;
- dst_reg->range = ptr_reg->range;
+ dst_reg->raw = ptr_reg->raw;
break;
}
/* A new variable offset is created. Note that off_reg->off
}
dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
+ dst_reg->raw = ptr_reg->raw;
if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
- dst_reg->range = 0;
+ dst_reg->raw = 0;
}
break;
case BPF_SUB:
dst_reg->var_off = ptr_reg->var_off;
dst_reg->id = ptr_reg->id;
dst_reg->off = ptr_reg->off - smin_val;
- dst_reg->range = ptr_reg->range;
+ dst_reg->raw = ptr_reg->raw;
break;
}
/* A new variable offset is created. If the subtrahend is known
}
dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off);
dst_reg->off = ptr_reg->off;
+ dst_reg->raw = ptr_reg->raw;
if (reg_is_pkt_pointer(ptr_reg)) {
dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range to zero */
if (smin_val < 0)
- dst_reg->range = 0;
+ dst_reg->raw = 0;
}
break;
case BPF_AND:
ret = err;
goto out;
}
+ copied = -EAGAIN;
}
ret = copied;
out:
prog->expected_attach_type = type;
}
-#define BPF_PROG_SEC_IMPL(string, ptype, eatype, atype) \
- { string, sizeof(string) - 1, ptype, eatype, atype }
+#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \
+ { string, sizeof(string) - 1, ptype, eatype, is_attachable, atype }
/* Programs that can NOT be attached. */
-#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, -EINVAL)
+#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0)
/* Programs that can be attached. */
#define BPF_APROG_SEC(string, ptype, atype) \
- BPF_PROG_SEC_IMPL(string, ptype, 0, atype)
+ BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype)
/* Programs that must specify expected attach type at load time. */
#define BPF_EAPROG_SEC(string, ptype, eatype) \
- BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype)
+ BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype)
/* Programs that can be attached but attach type can't be identified by section
* name. Kept for backward compatibility.
size_t len;
enum bpf_prog_type prog_type;
enum bpf_attach_type expected_attach_type;
+ int is_attachable;
enum bpf_attach_type attach_type;
} section_names[] = {
BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER),
for (i = 0; i < ARRAY_SIZE(section_names); i++) {
if (strncmp(name, section_names[i].sec, section_names[i].len))
continue;
- if (section_names[i].attach_type == -EINVAL)
+ if (!section_names[i].is_attachable)
return -EINVAL;
*attach_type = section_names[i].attach_type;
return 0;
#include <bpf/bpf.h>
#include <bpf/libbpf.h>
+#include "bpf_rlimit.h"
+
const char *cfg_pin_path = "/sys/fs/bpf/flow_dissector";
const char *cfg_map_name = "jmp_table";
bool cfg_attach = true;
echo -n "Wait for testing link-local IP to become available "
for _i in $(seq ${MAX_PING_TRIES}); do
echo -n "."
- if ping -6 -q -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
+ if $PING6 -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
echo " OK"
return
fi
BPF_PROG_SECTION="cgroup_id_logger"
BPF_PROG_ID=0
PROG="${DIR}/test_skb_cgroup_id_user"
+type ping6 >/dev/null 2>&1 && PING6="ping6" || PING6="ping -6"
main
ping_once()
{
- ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
+ type ping${1} >/dev/null 2>&1 && PING="ping${1}" || PING="ping -${1}"
+ $PING -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
}
wait_for_ip()
int fixup_percpu_cgroup_storage[MAX_FIXUPS];
const char *errstr;
const char *errstr_unpriv;
- uint32_t retval;
+ uint32_t retval, retval_unpriv;
enum {
UNDEF,
ACCEPT,
.fixup_prog1 = { 2 },
.result = ACCEPT,
.retval = 42,
+ /* Verifier rewrite for unpriv skips tail call here. */
+ .retval_unpriv = 2,
},
{
"stack pointer arithmetic",
.errstr = "R1 min value is negative",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
+ {
+ "map access: known scalar += value_ptr",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = ACCEPT,
+ .retval = 1,
+ },
+ {
+ "map access: value_ptr += known scalar",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = ACCEPT,
+ .retval = 1,
+ },
+ {
+ "map access: unknown scalar += value_ptr",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = ACCEPT,
+ .retval = 1,
+ },
+ {
+ "map access: value_ptr += unknown scalar",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = ACCEPT,
+ .retval = 1,
+ },
+ {
+ "map access: value_ptr += value_ptr",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = REJECT,
+ .errstr = "R0 pointer += pointer prohibited",
+ },
+ {
+ "map access: known scalar -= value_ptr",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 4),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = REJECT,
+ .errstr = "R1 tried to subtract pointer from scalar",
+ },
+ {
+ "map access: value_ptr -= known scalar",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 4),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = REJECT,
+ .errstr = "R0 min value is outside of the array range",
+ },
+ {
+ "map access: value_ptr -= known scalar, 2",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_MOV64_IMM(BPF_REG_2, 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_2),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = ACCEPT,
+ .retval = 1,
+ },
+ {
+ "map access: unknown scalar -= value_ptr",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = REJECT,
+ .errstr = "R1 tried to subtract pointer from scalar",
+ },
+ {
+ "map access: value_ptr -= unknown scalar",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = REJECT,
+ .errstr = "R0 min value is negative",
+ },
+ {
+ "map access: value_ptr -= unknown scalar, 2",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf),
+ BPF_ALU64_IMM(BPF_OR, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = ACCEPT,
+ .retval = 1,
+ },
+ {
+ "map access: value_ptr -= value_ptr",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = REJECT,
+ .errstr = "R0 invalid mem access 'inv'",
+ .errstr_unpriv = "R0 pointer -= pointer prohibited",
+ },
{
"map lookup helper access to map",
.insns = {
}
}
+static int set_admin(bool admin)
+{
+ cap_t caps;
+ const cap_value_t cap_val = CAP_SYS_ADMIN;
+ int ret = -1;
+
+ caps = cap_get_proc();
+ if (!caps) {
+ perror("cap_get_proc");
+ return -1;
+ }
+ if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val,
+ admin ? CAP_SET : CAP_CLEAR)) {
+ perror("cap_set_flag");
+ goto out;
+ }
+ if (cap_set_proc(caps)) {
+ perror("cap_set_proc");
+ goto out;
+ }
+ ret = 0;
+out:
+ if (cap_free(caps))
+ perror("cap_free");
+ return ret;
+}
+
static void do_test_single(struct bpf_test *test, bool unpriv,
int *passes, int *errors)
{
struct bpf_insn *prog = test->insns;
int map_fds[MAX_NR_MAPS];
const char *expected_err;
+ uint32_t expected_val;
uint32_t retval;
int i, err;
test->result_unpriv : test->result;
expected_err = unpriv && test->errstr_unpriv ?
test->errstr_unpriv : test->errstr;
+ expected_val = unpriv && test->retval_unpriv ?
+ test->retval_unpriv : test->retval;
reject_from_alignment = fd_prog < 0 &&
(test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) &&
__u8 tmp[TEST_DATA_LEN << 2];
__u32 size_tmp = sizeof(tmp);
+ if (unpriv)
+ set_admin(true);
err = bpf_prog_test_run(fd_prog, 1, test->data,
sizeof(test->data), tmp, &size_tmp,
&retval, NULL);
+ if (unpriv)
+ set_admin(false);
if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
printf("Unexpected bpf_prog_test_run error\n");
goto fail_log;
}
- if (!err && retval != test->retval &&
- test->retval != POINTER_VALUE) {
- printf("FAIL retval %d != %d\n", retval, test->retval);
+ if (!err && retval != expected_val &&
+ expected_val != POINTER_VALUE) {
+ printf("FAIL retval %d != %d\n", retval, expected_val);
goto fail_log;
}
}
return (sysadmin == CAP_SET);
}
-static int set_admin(bool admin)
-{
- cap_t caps;
- const cap_value_t cap_val = CAP_SYS_ADMIN;
- int ret = -1;
-
- caps = cap_get_proc();
- if (!caps) {
- perror("cap_get_proc");
- return -1;
- }
- if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val,
- admin ? CAP_SET : CAP_CLEAR)) {
- perror("cap_set_flag");
- goto out;
- }
- if (cap_set_proc(caps)) {
- perror("cap_set_proc");
- goto out;
- }
- ret = 0;
-out:
- if (cap_free(caps))
- perror("cap_free");
- return ret;
-}
-
static void get_unpriv_disabled()
{
char buf[2];
# Thus we set MTU to 10K on all involved interfaces. Then both unicast and
# multicast traffic uses 8K frames.
#
-# +-----------------------+ +----------------------------------+
-# | H1 | | H2 |
-# | | | unicast --> + $h2.111 |
-# | | | traffic | 192.0.2.129/28 |
-# | multicast | | | e-qos-map 0:1 |
-# | traffic | | | |
-# | $h1 + <----- | | + $h2 |
-# +-----|-----------------+ +--------------|-------------------+
-# | |
-# +-----|-------------------------------------------------|-------------------+
-# | + $swp1 + $swp2 |
-# | | >1Gbps | >1Gbps |
-# | +---|----------------+ +----------|----------------+ |
-# | | + $swp1.1 | | + $swp2.111 | |
+# +---------------------------+ +----------------------------------+
+# | H1 | | H2 |
+# | | | unicast --> + $h2.111 |
+# | multicast | | traffic | 192.0.2.129/28 |
+# | traffic | | | e-qos-map 0:1 |
+# | $h1 + <----- | | | |
+# | 192.0.2.65/28 | | | + $h2 |
+# +---------------|-----------+ +--------------|-------------------+
+# | |
+# +---------------|---------------------------------------|-------------------+
+# | $swp1 + + $swp2 |
+# | >1Gbps | | >1Gbps |
+# | +-------------|------+ +----------|----------------+ |
+# | | $swp1.1 + | | + $swp2.111 | |
# | | BR1 | SW | BR111 | |
-# | | + $swp3.1 | | + $swp3.111 | |
-# | +---|----------------+ +----------|----------------+ |
-# | \_________________________________________________/ |
+# | | $swp3.1 + | | + $swp3.111 | |
+# | +-------------|------+ +----------|----------------+ |
+# | \_______________________________________/ |
# | | |
# | + $swp3 |
# | | 1Gbps bottleneck |
# |
# +--|-----------------+
# | + $h3 H3 |
+# | | 192.0.2.66/28 |
# | | |
# | + $h3.111 |
# | 192.0.2.130/28 |
ALL_TESTS="
ping_ipv4
test_mc_aware
+ test_uc_aware
"
lib_dir=$(dirname $0)/../../../net/forwarding
h1_create()
{
- simple_if_init $h1
+ simple_if_init $h1 192.0.2.65/28
mtu_set $h1 10000
}
h1_destroy()
{
mtu_restore $h1
- simple_if_fini $h1
+ simple_if_fini $h1 192.0.2.65/28
}
h2_create()
h3_create()
{
- simple_if_init $h3
+ simple_if_init $h3 192.0.2.66/28
mtu_set $h3 10000
vlan_create $h3 111 v$h3 192.0.2.130/28
vlan_destroy $h3 111
mtu_restore $h3
- simple_if_fini $h3
+ simple_if_fini $h3 192.0.2.66/28
}
switch_create()
# average ingress rate to somewhat mitigate this.
local min_ingress=2147483648
- mausezahn $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
+ $MZ $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
-a own -b $h3mac -t udp -q &
sleep 1
check_err $? "Could not get high enough UC-only ingress rate"
local ucth1=${uc_rate[1]}
- mausezahn $h1 -p 8000 -c 0 -a own -b bc -t udp -q &
+ $MZ $h1 -p 8000 -c 0 -a own -b bc -t udp -q &
local d0=$(date +%s)
local t0=$(ethtool_stats_get $h3 rx_octets_prio_0)
ret = 100 * ($ucth1 - $ucth2) / $ucth1
if (ret > 0) { ret } else { 0 }
")
- check_err $(bc <<< "$deg > 10")
+ check_err $(bc <<< "$deg > 25")
local interval=$((d1 - d0))
local mc_ir=$(rate $u0 $u1 $interval)
echo " egress UC throughput $(humanize ${uc_rate_2[1]})"
echo " ingress MC throughput $(humanize $mc_ir)"
echo " egress MC throughput $(humanize $mc_er)"
+ echo
+}
+
+test_uc_aware()
+{
+ RET=0
+
+ $MZ $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \
+ -a own -b $h3mac -t udp -q &
+
+ local d0=$(date +%s)
+ local t0=$(ethtool_stats_get $h3 rx_octets_prio_1)
+ local u0=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+ sleep 1
+
+ local attempts=50
+ local passes=0
+ local i
+
+ for ((i = 0; i < attempts; ++i)); do
+ if $ARPING -c 1 -I $h1 -b 192.0.2.66 -q -w 0.1; then
+ ((passes++))
+ fi
+
+ sleep 0.1
+ done
+
+ local d1=$(date +%s)
+ local t1=$(ethtool_stats_get $h3 rx_octets_prio_1)
+ local u1=$(ethtool_stats_get $swp2 rx_octets_prio_1)
+
+ local interval=$((d1 - d0))
+ local uc_ir=$(rate $u0 $u1 $interval)
+ local uc_er=$(rate $t0 $t1 $interval)
+
+ ((attempts == passes))
+ check_err $?
+
+ # Suppress noise from killing mausezahn.
+ { kill %% && wait; } 2>/dev/null
+
+ log_test "MC performace under UC overload"
+ echo " ingress UC throughput $(humanize ${uc_ir})"
+ echo " egress UC throughput $(humanize ${uc_er})"
+ echo " sent $attempts BC ARPs, got $passes responses"
}
trap cleanup EXIT
projects / linux-2.6-block.git / commitdiff