CISCO VIC ETHERNET NIC DRIVER
M: Christian Benvenuti <benve@cisco.com>
-M: Roopa Prabhu <roprabhu@cisco.com>
+M: Sujith Sankar <ssujith@cisco.com>
+M: Govindarajulu Varadarajan <govindarajulu90@gmail.com>
M: Neel Patel <neepatel@cisco.com>
M: Nishank Trivedi <nistrive@cisco.com>
S: Supported
INTEL WIRELESS WIFI LINK (iwlwifi)
M: Johannes Berg <johannes.berg@intel.com>
-M: Wey-Yi Guy <wey-yi.w.guy@intel.com>
+M: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
M: Intel Linux Wireless <ilw@linux.intel.com>
L: linux-wireless@vger.kernel.org
W: http://intellinuxwireless.org
M: Samuel Ortiz <sameo@linux.intel.com>
L: linux-wireless@vger.kernel.org
L: linux-nfc@lists.01.org (moderated for non-subscribers)
-S: Maintained
+S: Supported
F: net/nfc/
F: include/net/nfc/
F: include/uapi/linux/nfc.h
M: Pawel Moll <pawel.moll@arm.com>
M: Mark Rutland <mark.rutland@arm.com>
M: Stephen Warren <swarren@wwwdotorg.org>
- M: Ian Campbell <ian.campbell@citrix.com>
+ M: Ian Campbell <ijc+devicetree@hellion.org.uk>
L: devicetree@vger.kernel.org
S: Maintained
F: Documentation/devicetree/
S: Maintained
F: Documentation/networking/sctp.txt
F: include/linux/sctp.h
+F: include/uapi/linux/sctp.h
F: include/net/sctp/
F: net/sctp/
F: arch/m68k/include/asm/sun3*
F: drivers/net/ethernet/i825xx/sun3*
+SUNDANCE NETWORK DRIVER
+M: Denis Kirjanov <kda@linux-powerpc.org>
+L: netdev@vger.kernel.org
+S: Maintained
+F: drivers/net/ethernet/dlink/sundance.c
+
SUPERH
M: Paul Mundt <lethal@linux-sh.org>
L: linux-sh@vger.kernel.org
struct bnx2x_fp_stats *to_fp_stats = &bp->fp_stats[to];
int old_max_eth_txqs, new_max_eth_txqs;
int old_txdata_index = 0, new_txdata_index = 0;
+ struct bnx2x_agg_info *old_tpa_info = to_fp->tpa_info;
/* Copy the NAPI object as it has been already initialized */
from_fp->napi = to_fp->napi;
memcpy(to_fp, from_fp, sizeof(*to_fp));
to_fp->index = to;
+ /* Retain the tpa_info of the original `to' version as we don't want
+ * 2 FPs to contain the same tpa_info pointer.
+ */
+ to_fp->tpa_info = old_tpa_info;
+
/* move sp_objs contents as well, as their indices match fp ones */
memcpy(to_sp_objs, from_sp_objs, sizeof(*to_sp_objs));
}
}
-static int bnx2x_init_rss_pf(struct bnx2x *bp)
+static int bnx2x_init_rss(struct bnx2x *bp)
{
int i;
u8 num_eth_queues = BNX2X_NUM_ETH_QUEUES(bp);
return bnx2x_config_rss_eth(bp, bp->port.pmf || !CHIP_IS_E1x(bp));
}
-int bnx2x_config_rss_pf(struct bnx2x *bp, struct bnx2x_rss_config_obj *rss_obj,
- bool config_hash)
+int bnx2x_rss(struct bnx2x *bp, struct bnx2x_rss_config_obj *rss_obj,
+ bool config_hash, bool enable)
{
struct bnx2x_config_rss_params params = {NULL};
__set_bit(RAMROD_COMP_WAIT, ¶ms.ramrod_flags);
- __set_bit(BNX2X_RSS_MODE_REGULAR, ¶ms.rss_flags);
-
- /* RSS configuration */
- __set_bit(BNX2X_RSS_IPV4, ¶ms.rss_flags);
- __set_bit(BNX2X_RSS_IPV4_TCP, ¶ms.rss_flags);
- __set_bit(BNX2X_RSS_IPV6, ¶ms.rss_flags);
- __set_bit(BNX2X_RSS_IPV6_TCP, ¶ms.rss_flags);
- if (rss_obj->udp_rss_v4)
- __set_bit(BNX2X_RSS_IPV4_UDP, ¶ms.rss_flags);
- if (rss_obj->udp_rss_v6)
- __set_bit(BNX2X_RSS_IPV6_UDP, ¶ms.rss_flags);
+ if (enable) {
+ __set_bit(BNX2X_RSS_MODE_REGULAR, ¶ms.rss_flags);
+
+ /* RSS configuration */
+ __set_bit(BNX2X_RSS_IPV4, ¶ms.rss_flags);
+ __set_bit(BNX2X_RSS_IPV4_TCP, ¶ms.rss_flags);
+ __set_bit(BNX2X_RSS_IPV6, ¶ms.rss_flags);
+ __set_bit(BNX2X_RSS_IPV6_TCP, ¶ms.rss_flags);
+ if (rss_obj->udp_rss_v4)
+ __set_bit(BNX2X_RSS_IPV4_UDP, ¶ms.rss_flags);
+ if (rss_obj->udp_rss_v6)
+ __set_bit(BNX2X_RSS_IPV6_UDP, ¶ms.rss_flags);
+ } else {
+ __set_bit(BNX2X_RSS_MODE_DISABLED, ¶ms.rss_flags);
+ }
/* Hash bits */
params.rss_result_mask = MULTI_MASK;
if (config_hash) {
/* RSS keys */
- prandom_bytes(params.rss_key, sizeof(params.rss_key));
+ prandom_bytes(params.rss_key, T_ETH_RSS_KEY * 4);
__set_bit(BNX2X_RSS_SET_SRCH, ¶ms.rss_flags);
}
- return bnx2x_config_rss(bp, ¶ms);
+ if (IS_PF(bp))
+ return bnx2x_config_rss(bp, ¶ms);
+ else
+ return bnx2x_vfpf_config_rss(bp, ¶ms);
}
static int bnx2x_init_hw(struct bnx2x *bp, u32 load_code)
rparam.mcast_obj = &bp->mcast_obj;
__set_bit(RAMROD_DRV_CLR_ONLY, &rparam.ramrod_flags);
- /* Add a DEL command... */
+ /* Add a DEL command... - Since we're doing a driver cleanup only,
+ * we take a lock surrounding both the initial send and the CONTs,
+ * as we don't want a true completion to disrupt us in the middle.
+ */
+ netif_addr_lock_bh(bp->dev);
rc = bnx2x_config_mcast(bp, &rparam, BNX2X_MCAST_CMD_DEL);
if (rc < 0)
BNX2X_ERR("Failed to add a new DEL command to a multi-cast object: %d\n",
if (rc < 0) {
BNX2X_ERR("Failed to clean multi-cast object: %d\n",
rc);
+ netif_addr_unlock_bh(bp->dev);
return;
}
rc = bnx2x_config_mcast(bp, &rparam, BNX2X_MCAST_CMD_CONT);
}
+ netif_addr_unlock_bh(bp->dev);
}
#ifndef BNX2X_STOP_ON_ERROR
}
/* Initialize Rx filter. */
- netif_addr_lock_bh(bp->dev);
- bnx2x_set_rx_mode(bp->dev);
- netif_addr_unlock_bh(bp->dev);
+ bnx2x_set_rx_mode_inner(bp);
/* re-read iscsi info */
bnx2x_get_iscsi_info(bp);
/* initialize FW coalescing state machines in RAM */
bnx2x_update_coalesce(bp);
+ }
- /* setup the leading queue */
- rc = bnx2x_setup_leading(bp);
- if (rc) {
- BNX2X_ERR("Setup leading failed!\n");
- LOAD_ERROR_EXIT(bp, load_error3);
- }
-
- /* set up the rest of the queues */
- for_each_nondefault_eth_queue(bp, i) {
- rc = bnx2x_setup_queue(bp, &bp->fp[i], 0);
- if (rc) {
- BNX2X_ERR("Queue setup failed\n");
- LOAD_ERROR_EXIT(bp, load_error3);
- }
- }
+ /* setup the leading queue */
+ rc = bnx2x_setup_leading(bp);
+ if (rc) {
+ BNX2X_ERR("Setup leading failed!\n");
+ LOAD_ERROR_EXIT(bp, load_error3);
+ }
- /* setup rss */
- rc = bnx2x_init_rss_pf(bp);
+ /* set up the rest of the queues */
+ for_each_nondefault_eth_queue(bp, i) {
+ if (IS_PF(bp))
+ rc = bnx2x_setup_queue(bp, &bp->fp[i], false);
+ else /* VF */
+ rc = bnx2x_vfpf_setup_q(bp, &bp->fp[i], false);
if (rc) {
- BNX2X_ERR("PF RSS init failed\n");
+ BNX2X_ERR("Queue %d setup failed\n", i);
LOAD_ERROR_EXIT(bp, load_error3);
}
+ }
- } else { /* vf */
- for_each_eth_queue(bp, i) {
- rc = bnx2x_vfpf_setup_q(bp, i);
- if (rc) {
- BNX2X_ERR("Queue setup failed\n");
- LOAD_ERROR_EXIT(bp, load_error3);
- }
- }
+ /* setup rss */
+ rc = bnx2x_init_rss(bp);
+ if (rc) {
+ BNX2X_ERR("PF RSS init failed\n");
+ LOAD_ERROR_EXIT(bp, load_error3);
}
/* Now when Clients are configured we are ready to work */
/* Start fast path */
/* Initialize Rx filter. */
- netif_addr_lock_bh(bp->dev);
- bnx2x_set_rx_mode(bp->dev);
- netif_addr_unlock_bh(bp->dev);
+ bnx2x_set_rx_mode_inner(bp);
/* Start the Tx */
switch (load_mode) {
if (IS_PF(bp)) {
if (CNIC_LOADED(bp))
bnx2x_free_mem_cnic(bp);
- bnx2x_free_mem(bp);
}
+ bnx2x_free_mem(bp);
+
bp->state = BNX2X_STATE_CLOSED;
bp->cnic_loaded = false;
void bnx2x_set_ctx_validation(struct bnx2x *bp, struct eth_context *cxt,
u32 cid)
{
+ if (!cxt) {
+ BNX2X_ERR("bad context pointer %p\n", cxt);
+ return;
+ }
+
/* ustorm cxt validation */
cxt->ustorm_ag_context.cdu_usage =
CDU_RSRVD_VALUE_TYPE_A(HW_CID(bp, cid),
bnx2x_init_block(bp, BLOCK_TM, PHASE_COMMON);
bnx2x_init_block(bp, BLOCK_DORQ, PHASE_COMMON);
- REG_WR(bp, DORQ_REG_DPM_CID_OFST, BNX2X_DB_SHIFT);
+
if (!CHIP_REV_IS_SLOW(bp))
/* enable hw interrupt from doorbell Q */
REG_WR(bp, DORQ_REG_DORQ_INT_MASK, 0);
{
int i;
- BNX2X_PCI_FREE(bp->def_status_blk, bp->def_status_blk_mapping,
- sizeof(struct host_sp_status_block));
-
BNX2X_PCI_FREE(bp->fw_stats, bp->fw_stats_mapping,
bp->fw_stats_data_sz + bp->fw_stats_req_sz);
+ if (IS_VF(bp))
+ return;
+
+ BNX2X_PCI_FREE(bp->def_status_blk, bp->def_status_blk_mapping,
+ sizeof(struct host_sp_status_block));
+
BNX2X_PCI_FREE(bp->slowpath, bp->slowpath_mapping,
sizeof(struct bnx2x_slowpath));
int bnx2x_setup_leading(struct bnx2x *bp)
{
- return bnx2x_setup_queue(bp, &bp->fp[0], 1);
+ if (IS_PF(bp))
+ return bnx2x_setup_queue(bp, &bp->fp[0], true);
+ else /* VF */
+ return bnx2x_vfpf_setup_q(bp, &bp->fp[0], true);
}
/**
{
int rc = 0;
- if (IS_VF(bp) && int_mode != BNX2X_INT_MODE_MSIX)
+ if (IS_VF(bp) && int_mode != BNX2X_INT_MODE_MSIX) {
+ BNX2X_ERR("VF not loaded since interrupt mode not msix\n");
return -EINVAL;
+ }
switch (int_mode) {
case BNX2X_INT_MODE_MSIX:
}
}
- if (test_and_clear_bit(BNX2X_SP_RTNL_VFPF_STORM_RX_MODE,
- &bp->sp_rtnl_state)) {
- DP(BNX2X_MSG_SP,
- "sending set storm rx mode vf pf channel message from rtnl sp-task\n");
- bnx2x_vfpf_storm_rx_mode(bp);
+ if (test_and_clear_bit(BNX2X_SP_RTNL_RX_MODE, &bp->sp_rtnl_state)) {
+ DP(BNX2X_MSG_SP, "Handling Rx Mode setting\n");
+ bnx2x_set_rx_mode_inner(bp);
}
if (test_and_clear_bit(BNX2X_SP_RTNL_HYPERVISOR_VLAN,
* second status block for the L2 queue, and a third status block for
* CNIC if supported.
*/
- if (CNIC_SUPPORT(bp))
+ if (IS_VF(bp))
+ bp->min_msix_vec_cnt = 1;
+ else if (CNIC_SUPPORT(bp))
bp->min_msix_vec_cnt = 3;
- else
+ else /* PF w/o cnic */
bp->min_msix_vec_cnt = 2;
BNX2X_DEV_INFO("bp->min_msix_vec_cnt %d", bp->min_msix_vec_cnt);
void bnx2x_set_rx_mode(struct net_device *dev)
{
struct bnx2x *bp = netdev_priv(dev);
- u32 rx_mode = BNX2X_RX_MODE_NORMAL;
if (bp->state != BNX2X_STATE_OPEN) {
DP(NETIF_MSG_IFUP, "state is %x, returning\n", bp->state);
return;
+ } else {
+ /* Schedule an SP task to handle rest of change */
+ DP(NETIF_MSG_IFUP, "Scheduling an Rx mode change\n");
+ smp_mb__before_clear_bit();
+ set_bit(BNX2X_SP_RTNL_RX_MODE, &bp->sp_rtnl_state);
+ smp_mb__after_clear_bit();
+ schedule_delayed_work(&bp->sp_rtnl_task, 0);
}
+}
+
+void bnx2x_set_rx_mode_inner(struct bnx2x *bp)
+{
+ u32 rx_mode = BNX2X_RX_MODE_NORMAL;
DP(NETIF_MSG_IFUP, "dev->flags = %x\n", bp->dev->flags);
- if (dev->flags & IFF_PROMISC)
+ netif_addr_lock_bh(bp->dev);
+
+ if (bp->dev->flags & IFF_PROMISC) {
rx_mode = BNX2X_RX_MODE_PROMISC;
- else if ((dev->flags & IFF_ALLMULTI) ||
- ((netdev_mc_count(dev) > BNX2X_MAX_MULTICAST) &&
- CHIP_IS_E1(bp)))
+ } else if ((bp->dev->flags & IFF_ALLMULTI) ||
+ ((netdev_mc_count(bp->dev) > BNX2X_MAX_MULTICAST) &&
+ CHIP_IS_E1(bp))) {
rx_mode = BNX2X_RX_MODE_ALLMULTI;
- else {
+ } else {
if (IS_PF(bp)) {
/* some multicasts */
if (bnx2x_set_mc_list(bp) < 0)
rx_mode = BNX2X_RX_MODE_ALLMULTI;
+ /* release bh lock, as bnx2x_set_uc_list might sleep */
+ netif_addr_unlock_bh(bp->dev);
if (bnx2x_set_uc_list(bp) < 0)
rx_mode = BNX2X_RX_MODE_PROMISC;
+ netif_addr_lock_bh(bp->dev);
} else {
/* configuring mcast to a vf involves sleeping (when we
- * wait for the pf's response). Since this function is
- * called from non sleepable context we must schedule
- * a work item for this purpose
+ * wait for the pf's response).
*/
smp_mb__before_clear_bit();
set_bit(BNX2X_SP_RTNL_VFPF_MCAST,
/* Schedule the rx_mode command */
if (test_bit(BNX2X_FILTER_RX_MODE_PENDING, &bp->sp_state)) {
set_bit(BNX2X_FILTER_RX_MODE_SCHED, &bp->sp_state);
+ netif_addr_unlock_bh(bp->dev);
return;
}
if (IS_PF(bp)) {
bnx2x_set_storm_rx_mode(bp);
+ netif_addr_unlock_bh(bp->dev);
} else {
- /* configuring rx mode to storms in a vf involves sleeping (when
- * we wait for the pf's response). Since this function is
- * called from non sleepable context we must schedule
- * a work item for this purpose
+ /* VF will need to request the PF to make this change, and so
+ * the VF needs to release the bottom-half lock prior to the
+ * request (as it will likely require sleep on the VF side)
*/
- smp_mb__before_clear_bit();
- set_bit(BNX2X_SP_RTNL_VFPF_STORM_RX_MODE,
- &bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
- schedule_delayed_work(&bp->sp_rtnl_task, 0);
+ netif_addr_unlock_bh(bp->dev);
+ bnx2x_vfpf_storm_rx_mode(bp);
}
}
* @dev: pci device
*
*/
-static int bnx2x_get_num_non_def_sbs(struct pci_dev *pdev,
- int cnic_cnt, bool is_vf)
+static int bnx2x_get_num_non_def_sbs(struct pci_dev *pdev, int cnic_cnt)
{
- int pos, index;
+ int index;
u16 control = 0;
- pos = pci_find_capability(pdev, PCI_CAP_ID_MSIX);
-
/*
* If MSI-X is not supported - return number of SBs needed to support
* one fast path queue: one FP queue + SB for CNIC
*/
- if (!pos) {
+ if (!pdev->msix_cap) {
dev_info(&pdev->dev, "no msix capability found\n");
return 1 + cnic_cnt;
}
* without the default SB.
* For VFs there is no default SB, then we return (index+1).
*/
- pci_read_config_word(pdev, pos + PCI_MSI_FLAGS, &control);
+ pci_read_config_word(pdev, pdev->msix_cap + PCI_MSI_FLAGS, &control);
index = control & PCI_MSIX_FLAGS_QSIZE;
- return is_vf ? index + 1 : index;
+ return index;
}
static int set_max_cos_est(int chip_id)
is_vf = set_is_vf(ent->driver_data);
cnic_cnt = is_vf ? 0 : 1;
- max_non_def_sbs = bnx2x_get_num_non_def_sbs(pdev, cnic_cnt, is_vf);
+ max_non_def_sbs = bnx2x_get_num_non_def_sbs(pdev, cnic_cnt);
+
+ /* add another SB for VF as it has no default SB */
+ max_non_def_sbs += is_vf ? 1 : 0;
/* Maximum number of RSS queues: one IGU SB goes to CNIC */
- rss_count = is_vf ? 1 : max_non_def_sbs - cnic_cnt;
+ rss_count = max_non_def_sbs - cnic_cnt;
if (rss_count < 1)
return -EINVAL;
BNX2X_VFOP_QTEARDOWN_DONE
};
+enum bnx2x_vfop_rss_state {
+ BNX2X_VFOP_RSS_CONFIG,
+ BNX2X_VFOP_RSS_DONE
+};
+
#define bnx2x_vfop_reset_wq(vf) atomic_set(&vf->op_in_progress, 0)
void bnx2x_vfop_qctor_dump_tx(struct bnx2x *bp, struct bnx2x_virtf *vf,
__set_bit(BNX2X_Q_FLG_TX_SEC, &setup_p->flags);
__set_bit(BNX2X_Q_FLG_ANTI_SPOOF, &setup_p->flags);
- if (vfq_is_leading(q)) {
- __set_bit(BNX2X_Q_FLG_LEADING_RSS, &setup_p->flags);
- __set_bit(BNX2X_Q_FLG_MCAST, &setup_p->flags);
- }
-
/* Setup-op rx parameters */
if (test_bit(BNX2X_Q_TYPE_HAS_RX, &q_type)) {
struct bnx2x_rxq_setup_params *rxq_p = &setup_p->rxq_params;
BNX2X_Q_LOGICAL_STATE_STOPPED) {
DP(BNX2X_MSG_IOV,
"Entered qdtor but queue was already stopped. Aborting gracefully\n");
- goto op_done;
+
+ /* next state */
+ vfop->state = BNX2X_VFOP_QDTOR_DONE;
+
+ bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
}
/* next state */
op_done:
case BNX2X_VFOP_QDTOR_DONE:
/* invalidate the context */
- qdtor->cxt->ustorm_ag_context.cdu_usage = 0;
- qdtor->cxt->xstorm_ag_context.cdu_reserved = 0;
+ if (qdtor->cxt) {
+ qdtor->cxt->ustorm_ag_context.cdu_usage = 0;
+ qdtor->cxt->xstorm_ag_context.cdu_reserved = 0;
+ }
bnx2x_vfop_end(bp, vf, vfop);
return;
default:
return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qdtor,
cmd->block);
}
- DP(BNX2X_MSG_IOV, "VF[%d] failed to add a vfop.\n", vf->abs_vfid);
+ DP(BNX2X_MSG_IOV, "VF[%d] failed to add a vfop. rc %d\n",
+ vf->abs_vfid, vfop->rc);
return -ENOMEM;
}
{
struct bnx2x_virtf *vf = bnx2x_vf_by_abs_fid(bp, abs_vfid);
if (vf) {
+ /* the first igu entry belonging to VFs of this PF */
+ if (!BP_VFDB(bp)->first_vf_igu_entry)
+ BP_VFDB(bp)->first_vf_igu_entry = igu_sb_id;
+
+ /* the first igu entry belonging to this VF */
if (!vf_sb_count(vf))
vf->igu_base_id = igu_sb_id;
+
++vf_sb_count(vf);
+ ++vf->sb_count;
}
+ BP_VFDB(bp)->vf_sbs_pool++;
}
/* VFOP MAC/VLAN helpers */
* and a valid credit counter
*/
if (!vfop->rc && args->credit) {
- int cnt = 0;
struct list_head *pos;
+ int read_lock;
+ int cnt = 0;
+
+ read_lock = bnx2x_vlan_mac_h_read_lock(bp, obj);
+ if (read_lock)
+ DP(BNX2X_MSG_SP, "Failed to take vlan mac read head; continuing anyway\n");
list_for_each(pos, &obj->head)
cnt++;
+ if (!read_lock)
+ bnx2x_vlan_mac_h_read_unlock(bp, obj);
+
atomic_set(args->credit, cnt);
}
}
return 0;
}
- static int
- bnx2x_vfop_config_vlan0(struct bnx2x *bp,
- struct bnx2x_vlan_mac_ramrod_params *vlan_mac,
- bool add)
- {
- int rc;
-
- vlan_mac->user_req.cmd = add ? BNX2X_VLAN_MAC_ADD :
- BNX2X_VLAN_MAC_DEL;
- vlan_mac->user_req.u.vlan.vlan = 0;
-
- rc = bnx2x_config_vlan_mac(bp, vlan_mac);
- if (rc == -EEXIST)
- rc = 0;
- return rc;
- }
-
static int bnx2x_vfop_config_list(struct bnx2x *bp,
struct bnx2x_vfop_filters *filters,
struct bnx2x_vlan_mac_ramrod_params *vlan_mac)
case BNX2X_VFOP_VLAN_CONFIG_LIST:
/* next state */
- vfop->state = BNX2X_VFOP_VLAN_CONFIG_LIST_0;
-
- /* remove vlan0 - could be no-op */
- vfop->rc = bnx2x_vfop_config_vlan0(bp, vlan_mac, false);
- if (vfop->rc)
- goto op_err;
+ vfop->state = BNX2X_VFOP_VLAN_MAC_CHK_DONE;
- /* Do vlan list config. if this operation fails we try to
- * restore vlan0 to keep the queue is working order
- */
+ /* do list config */
vfop->rc = bnx2x_vfop_config_list(bp, filters, vlan_mac);
if (!vfop->rc) {
set_bit(RAMROD_CONT, &vlan_mac->ramrod_flags);
vfop->rc = bnx2x_config_vlan_mac(bp, vlan_mac);
}
- bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT); /* fall-through */
-
- case BNX2X_VFOP_VLAN_CONFIG_LIST_0:
- /* next state */
- vfop->state = BNX2X_VFOP_VLAN_MAC_CHK_DONE;
-
- if (list_empty(&obj->head))
- /* add vlan0 */
- vfop->rc = bnx2x_vfop_config_vlan0(bp, vlan_mac, true);
bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
default:
int qid, bool drv_only)
{
struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+ int rc;
if (vfop) {
struct bnx2x_vfop_args_filters filters = {
bnx2x_vfop_mac_prep_ramrod(ramrod, &flags);
/* set object */
+ rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj));
+ if (rc)
+ return rc;
ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
/* set extra args */
int qid, bool drv_only)
{
struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+ int rc;
if (vfop) {
struct bnx2x_vfop_args_filters filters = {
bnx2x_vfop_mac_prep_ramrod(ramrod, &flags);
/* set object */
+ rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj));
+ if (rc)
+ return rc;
ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
/* set extra args */
int qid, u16 vid, bool add)
{
struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+ int rc;
if (vfop) {
struct bnx2x_vfop_args_filters filters = {
ramrod->user_req.u.vlan.vlan = vid;
/* set object */
+ rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
+ if (rc)
+ return rc;
ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
/* set extra args */
int qid, bool drv_only)
{
struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+ int rc;
if (vfop) {
struct bnx2x_vfop_args_filters filters = {
bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
/* set object */
+ rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
+ if (rc)
+ return rc;
ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
/* set extra args */
int qid, bool drv_only)
{
struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+ int rc;
if (vfop) {
struct bnx2x_vfop_args_filters filters = {
bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
/* set object */
+ rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
+ if (rc)
+ return rc;
ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
/* set extra args */
case BNX2X_VFOP_QFLR_CLR_VLAN:
/* vlan-clear-all: driver-only, don't consume credit */
vfop->state = BNX2X_VFOP_QFLR_CLR_MAC;
- vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd, qid, true);
+ if (!validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj)))
+ vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd, qid,
+ true);
if (vfop->rc)
goto op_err;
- return;
+ bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
case BNX2X_VFOP_QFLR_CLR_MAC:
/* mac-clear-all: driver only consume credit */
vfop->state = BNX2X_VFOP_QFLR_TERMINATE;
- vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd, qid, true);
+ if (!validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj)))
+ vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd, qid,
+ true);
DP(BNX2X_MSG_IOV,
"VF[%d] vfop->rc after bnx2x_vfop_mac_delall_cmd was %d",
vf->abs_vfid, vfop->rc);
if (vfop->rc)
goto op_err;
- return;
+ bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
case BNX2X_VFOP_QFLR_TERMINATE:
qstate = &vfop->op_p->qctor.qstate;
{
struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+ /* for non leading queues skip directly to qdown sate */
if (vfop) {
vfop->args.qx.qid = qid;
- bnx2x_vfop_opset(BNX2X_VFOP_QTEARDOWN_RXMODE,
- bnx2x_vfop_qdown, cmd->done);
+ bnx2x_vfop_opset(qid == LEADING_IDX ?
+ BNX2X_VFOP_QTEARDOWN_RXMODE :
+ BNX2X_VFOP_QTEARDOWN_QDTOR, bnx2x_vfop_qdown,
+ cmd->done);
return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qdown,
cmd->block);
}
* both known
*/
static void
-bnx2x_iov_static_resc(struct bnx2x *bp, struct vf_pf_resc_request *resc)
+bnx2x_iov_static_resc(struct bnx2x *bp, struct bnx2x_virtf *vf)
{
+ struct vf_pf_resc_request *resc = &vf->alloc_resc;
u16 vlan_count = 0;
/* will be set only during VF-ACQUIRE */
resc->num_rxqs = 0;
resc->num_txqs = 0;
- /* no credit calculcis for macs (just yet) */
+ /* no credit calculations for macs (just yet) */
resc->num_mac_filters = 1;
/* divvy up vlan rules */
resc->num_mc_filters = 0;
/* num_sbs already set */
+ resc->num_sbs = vf->sb_count;
}
/* FLR routines: */
static void bnx2x_vf_free_resc(struct bnx2x *bp, struct bnx2x_virtf *vf)
{
/* reset the state variables */
- bnx2x_iov_static_resc(bp, &vf->alloc_resc);
+ bnx2x_iov_static_resc(bp, vf);
vf->state = VF_FREE;
}
/* The VF doorbell size 0 - *B, 4 - 128B. We set it here to match
* the Pf doorbell size although the 2 are independent.
*/
- REG_WR(bp, DORQ_REG_VF_NORM_CID_OFST,
- BNX2X_DB_SHIFT - BNX2X_DB_MIN_SHIFT);
+ REG_WR(bp, DORQ_REG_VF_NORM_CID_OFST, 3);
/* No security checks for now -
* configure single rule (out of 16) mask = 0x1, value = 0x0,
{
int sb_id;
u32 val;
- u8 fid;
+ u8 fid, current_pf = 0;
/* IGU in normal mode - read CAM */
for (sb_id = 0; sb_id < IGU_REG_MAPPING_MEMORY_SIZE; sb_id++) {
if (!(val & IGU_REG_MAPPING_MEMORY_VALID))
continue;
fid = GET_FIELD((val), IGU_REG_MAPPING_MEMORY_FID);
- if (!(fid & IGU_FID_ENCODE_IS_PF))
+ if (fid & IGU_FID_ENCODE_IS_PF)
+ current_pf = fid & IGU_FID_PF_NUM_MASK;
+ else if (current_pf == BP_ABS_FUNC(bp))
bnx2x_vf_set_igu_info(bp, sb_id,
(fid & IGU_FID_VF_NUM_MASK));
-
DP(BNX2X_MSG_IOV, "%s[%d], igu_sb_id=%d, msix=%d\n",
((fid & IGU_FID_ENCODE_IS_PF) ? "PF" : "VF"),
((fid & IGU_FID_ENCODE_IS_PF) ? (fid & IGU_FID_PF_NUM_MASK) :
(fid & IGU_FID_VF_NUM_MASK)), sb_id,
GET_FIELD((val), IGU_REG_MAPPING_MEMORY_VECTOR));
}
+ DP(BNX2X_MSG_IOV, "vf_sbs_pool is %d\n", BP_VFDB(bp)->vf_sbs_pool);
}
static void __bnx2x_iov_free_vfdb(struct bnx2x *bp)
return 0;
}
-static u8 bnx2x_iov_get_max_queue_count(struct bnx2x *bp)
-{
- int i;
- u8 queue_count = 0;
-
- if (IS_SRIOV(bp))
- for_each_vf(bp, i)
- queue_count += bnx2x_vf(bp, i, alloc_resc.num_sbs);
-
- return queue_count;
-}
-
/* must be called after PF bars are mapped */
int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param,
- int num_vfs_param)
+ int num_vfs_param)
{
- int err, i, qcount;
+ int err, i;
struct bnx2x_sriov *iov;
struct pci_dev *dev = bp->pdev;
/* re-read the IGU CAM for VFs - index and abs_vfid must be set */
bnx2x_get_vf_igu_cam_info(bp);
- /* get the total queue count and allocate the global queue arrays */
- qcount = bnx2x_iov_get_max_queue_count(bp);
-
/* allocate the queue arrays for all VFs */
- bp->vfdb->vfqs = kzalloc(qcount * sizeof(struct bnx2x_vf_queue),
- GFP_KERNEL);
+ bp->vfdb->vfqs = kzalloc(
+ BNX2X_MAX_NUM_VF_QUEUES * sizeof(struct bnx2x_vf_queue),
+ GFP_KERNEL);
+
+ DP(BNX2X_MSG_IOV, "bp->vfdb->vfqs was %p\n", bp->vfdb->vfqs);
+
if (!bp->vfdb->vfqs) {
BNX2X_ERR("failed to allocate vf queue array\n");
err = -ENOMEM;
q_type);
DP(BNX2X_MSG_IOV,
- "initialized vf %d's queue object. func id set to %d\n",
- vf->abs_vfid, q->sp_obj.func_id);
-
- /* mac/vlan objects are per queue, but only those
- * that belong to the leading queue are initialized
- */
- if (vfq_is_leading(q)) {
- /* mac */
- bnx2x_init_mac_obj(bp, &q->mac_obj,
- cl_id, q->cid, func_id,
- bnx2x_vf_sp(bp, vf, mac_rdata),
- bnx2x_vf_sp_map(bp, vf, mac_rdata),
- BNX2X_FILTER_MAC_PENDING,
- &vf->filter_state,
- BNX2X_OBJ_TYPE_RX_TX,
- &bp->macs_pool);
- /* vlan */
- bnx2x_init_vlan_obj(bp, &q->vlan_obj,
- cl_id, q->cid, func_id,
- bnx2x_vf_sp(bp, vf, vlan_rdata),
- bnx2x_vf_sp_map(bp, vf, vlan_rdata),
- BNX2X_FILTER_VLAN_PENDING,
- &vf->filter_state,
- BNX2X_OBJ_TYPE_RX_TX,
- &bp->vlans_pool);
-
- /* mcast */
- bnx2x_init_mcast_obj(bp, &vf->mcast_obj, cl_id,
- q->cid, func_id, func_id,
- bnx2x_vf_sp(bp, vf, mcast_rdata),
- bnx2x_vf_sp_map(bp, vf, mcast_rdata),
- BNX2X_FILTER_MCAST_PENDING,
- &vf->filter_state,
- BNX2X_OBJ_TYPE_RX_TX);
-
- vf->leading_rss = cl_id;
- }
+ "initialized vf %d's queue object. func id set to %d. cid set to 0x%x\n",
+ vf->abs_vfid, q->sp_obj.func_id, q->cid);
}
/* called by bnx2x_nic_load */
int bnx2x_iov_nic_init(struct bnx2x *bp)
{
- int vfid, qcount, i;
+ int vfid;
if (!IS_SRIOV(bp)) {
DP(BNX2X_MSG_IOV, "vfdb was not allocated\n");
BNX2X_FIRST_VF_CID + base_vf_cid, base_cxt);
/* init statically provisioned resources */
- bnx2x_iov_static_resc(bp, &vf->alloc_resc);
+ bnx2x_iov_static_resc(bp, vf);
/* queues are initialized during VF-ACQUIRE */
}
/* Final VF init */
- qcount = 0;
- for_each_vf(bp, i) {
- struct bnx2x_virtf *vf = BP_VF(bp, i);
+ for_each_vf(bp, vfid) {
+ struct bnx2x_virtf *vf = BP_VF(bp, vfid);
/* fill in the BDF and bars */
- vf->bus = bnx2x_vf_bus(bp, i);
- vf->devfn = bnx2x_vf_devfn(bp, i);
+ vf->bus = bnx2x_vf_bus(bp, vfid);
+ vf->devfn = bnx2x_vf_devfn(bp, vfid);
bnx2x_vf_set_bars(bp, vf);
DP(BNX2X_MSG_IOV,
(unsigned)vf->bars[0].bar, vf->bars[0].size,
(unsigned)vf->bars[1].bar, vf->bars[1].size,
(unsigned)vf->bars[2].bar, vf->bars[2].size);
-
- /* set local queue arrays */
- vf->vfqs = &bp->vfdb->vfqs[qcount];
- qcount += bnx2x_vf(bp, i, alloc_resc.num_sbs);
}
return 0;
for_each_vfq(vf, j) {
struct bnx2x_vf_queue *rxq = vfq_get(vf, j);
+ dma_addr_t q_stats_addr =
+ vf->fw_stat_map + j * vf->stats_stride;
+
/* collect stats fro active queues only */
if (bnx2x_get_q_logical_state(bp, &rxq->sp_obj) ==
BNX2X_Q_LOGICAL_STATE_STOPPED)
/* create stats query entry for this queue */
cur_query_entry->kind = STATS_TYPE_QUEUE;
- cur_query_entry->index = vfq_cl_id(vf, rxq);
+ cur_query_entry->index = vfq_stat_id(vf, rxq);
cur_query_entry->funcID =
cpu_to_le16(FW_VF_HANDLE(vf->abs_vfid));
cur_query_entry->address.hi =
- cpu_to_le32(U64_HI(vf->fw_stat_map));
+ cpu_to_le32(U64_HI(q_stats_addr));
cur_query_entry->address.lo =
- cpu_to_le32(U64_LO(vf->fw_stat_map));
+ cpu_to_le32(U64_LO(q_stats_addr));
DP(BNX2X_MSG_IOV,
"added address %x %x for vf %d queue %d client %d\n",
cur_query_entry->address.hi,
cur_query_entry++;
cur_data_offset += sizeof(struct per_queue_stats);
stats_count++;
+
+ /* all stats are coalesced to the leading queue */
+ if (vf->cfg_flags & VF_CFG_STATS_COALESCE)
+ break;
}
}
bp->fw_stats_req->hdr.cmd_num = bp->fw_stats_num + stats_count;
for_each_vf(bp, i) {
struct bnx2x_virtf *vf = BP_VF(bp, i);
+ if (!vf) {
+ BNX2X_ERR("VF was null! skipping...\n");
+ continue;
+ }
+
if (!list_empty(&vf->op_list_head) &&
atomic_read(&vf->op_in_progress)) {
DP(BNX2X_MSG_IOV, "running pending op for vf %d\n", i);
struct bnx2x_vf_queue *q = vfq_get(vf, i);
if (!q) {
- DP(BNX2X_MSG_IOV, "q number %d was not allocated\n", i);
+ BNX2X_ERR("q number %d was not allocated\n", i);
return -EINVAL;
}
return 0;
}
+ struct set_vf_state_cookie {
+ struct bnx2x_virtf *vf;
+ u8 state;
+ };
+
+ void bnx2x_set_vf_state(void *cookie)
+ {
+ struct set_vf_state_cookie *p = (struct set_vf_state_cookie *)cookie;
+
+ p->vf->state = p->state;
+ }
+
/* VFOP close (teardown the queues, delete mcasts and close HW) */
static void bnx2x_vfop_close(struct bnx2x *bp, struct bnx2x_virtf *vf)
{
op_err:
BNX2X_ERR("VF[%d] CLOSE error: rc %d\n", vf->abs_vfid, vfop->rc);
op_done:
- vf->state = VF_ACQUIRED;
+
+ /* need to make sure there are no outstanding stats ramrods which may
+ * cause the device to access the VF's stats buffer which it will free
+ * as soon as we return from the close flow.
+ */
+ {
+ struct set_vf_state_cookie cookie;
+
+ cookie.vf = vf;
+ cookie.state = VF_ACQUIRED;
+ bnx2x_stats_safe_exec(bp, bnx2x_set_vf_state, &cookie);
+ }
+
DP(BNX2X_MSG_IOV, "set state to acquired\n");
bnx2x_vfop_end(bp, vf, vfop);
}
bnx2x_vfop_end(bp, vf, vfop);
}
+static void bnx2x_vfop_rss(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+ struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+ enum bnx2x_vfop_rss_state state;
+
+ if (!vfop) {
+ BNX2X_ERR("vfop was null\n");
+ return;
+ }
+
+ state = vfop->state;
+ bnx2x_vfop_reset_wq(vf);
+
+ if (vfop->rc < 0)
+ goto op_err;
+
+ DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
+
+ switch (state) {
+ case BNX2X_VFOP_RSS_CONFIG:
+ /* next state */
+ vfop->state = BNX2X_VFOP_RSS_DONE;
+ bnx2x_config_rss(bp, &vfop->op_p->rss);
+ bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
+op_err:
+ BNX2X_ERR("RSS error: rc %d\n", vfop->rc);
+op_done:
+ case BNX2X_VFOP_RSS_DONE:
+ bnx2x_vfop_end(bp, vf, vfop);
+ return;
+ default:
+ bnx2x_vfop_default(state);
+ }
+op_pending:
+ return;
+}
+
int bnx2x_vfop_release_cmd(struct bnx2x *bp,
struct bnx2x_virtf *vf,
struct bnx2x_vfop_cmd *cmd)
return -ENOMEM;
}
+int bnx2x_vfop_rss_cmd(struct bnx2x *bp,
+ struct bnx2x_virtf *vf,
+ struct bnx2x_vfop_cmd *cmd)
+{
+ struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+ if (vfop) {
+ bnx2x_vfop_opset(BNX2X_VFOP_RSS_CONFIG, bnx2x_vfop_rss,
+ cmd->done);
+ return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_rss,
+ cmd->block);
+ }
+ return -ENOMEM;
+}
+
/* VF release ~ VF close + VF release-resources
* Release is the ultimate SW shutdown and is called whenever an
* irrecoverable error is encountered.
.block = block,
};
int rc;
+
+ DP(BNX2X_MSG_IOV, "PF releasing vf %d\n", vf->abs_vfid);
bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_RELEASE_VF);
rc = bnx2x_vfop_release_cmd(bp, vf, &cmd);
void bnx2x_lock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
enum channel_tlvs tlv)
{
+ /* we don't lock the channel for unsupported tlvs */
+ if (!bnx2x_tlv_supported(tlv)) {
+ BNX2X_ERR("attempting to lock with unsupported tlv. Aborting\n");
+ return;
+ }
+
/* lock the channel */
mutex_lock(&vf->op_mutex);
void bnx2x_unlock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
enum channel_tlvs expected_tlv)
{
+ enum channel_tlvs current_tlv;
+
+ if (!vf) {
+ BNX2X_ERR("VF was %p\n", vf);
+ return;
+ }
+
+ current_tlv = vf->op_current;
+
+ /* we don't unlock the channel for unsupported tlvs */
+ if (!bnx2x_tlv_supported(expected_tlv))
+ return;
+
WARN(expected_tlv != vf->op_current,
"lock mismatch: expected %d found %d", expected_tlv,
vf->op_current);
+ /* record the locking op */
+ vf->op_current = CHANNEL_TLV_NONE;
+
/* lock the channel */
mutex_unlock(&vf->op_mutex);
/* log the unlock */
DP(BNX2X_MSG_IOV, "VF[%d]: vf pf channel unlocked by %d\n",
vf->abs_vfid, vf->op_current);
-
- /* record the locking op */
- vf->op_current = CHANNEL_TLV_NONE;
}
int bnx2x_sriov_configure(struct pci_dev *dev, int num_vfs_param)
return bnx2x_enable_sriov(bp);
}
}
+#define IGU_ENTRY_SIZE 4
int bnx2x_enable_sriov(struct bnx2x *bp)
{
int rc = 0, req_vfs = bp->requested_nr_virtfn;
+ int vf_idx, sb_idx, vfq_idx, qcount, first_vf;
+ u32 igu_entry, address;
+ u16 num_vf_queues;
+
+ if (req_vfs == 0)
+ return 0;
+
+ first_vf = bp->vfdb->sriov.first_vf_in_pf;
+
+ /* statically distribute vf sb pool between VFs */
+ num_vf_queues = min_t(u16, BNX2X_VF_MAX_QUEUES,
+ BP_VFDB(bp)->vf_sbs_pool / req_vfs);
+
+ /* zero previous values learned from igu cam */
+ for (vf_idx = 0; vf_idx < req_vfs; vf_idx++) {
+ struct bnx2x_virtf *vf = BP_VF(bp, vf_idx);
+
+ vf->sb_count = 0;
+ vf_sb_count(BP_VF(bp, vf_idx)) = 0;
+ }
+ bp->vfdb->vf_sbs_pool = 0;
+
+ /* prepare IGU cam */
+ sb_idx = BP_VFDB(bp)->first_vf_igu_entry;
+ address = IGU_REG_MAPPING_MEMORY + sb_idx * IGU_ENTRY_SIZE;
+ for (vf_idx = first_vf; vf_idx < first_vf + req_vfs; vf_idx++) {
+ for (vfq_idx = 0; vfq_idx < num_vf_queues; vfq_idx++) {
+ igu_entry = vf_idx << IGU_REG_MAPPING_MEMORY_FID_SHIFT |
+ vfq_idx << IGU_REG_MAPPING_MEMORY_VECTOR_SHIFT |
+ IGU_REG_MAPPING_MEMORY_VALID;
+ DP(BNX2X_MSG_IOV, "assigning sb %d to vf %d\n",
+ sb_idx, vf_idx);
+ REG_WR(bp, address, igu_entry);
+ sb_idx++;
+ address += IGU_ENTRY_SIZE;
+ }
+ }
+
+ /* Reinitialize vf database according to igu cam */
+ bnx2x_get_vf_igu_cam_info(bp);
+
+ DP(BNX2X_MSG_IOV, "vf_sbs_pool %d, num_vf_queues %d\n",
+ BP_VFDB(bp)->vf_sbs_pool, num_vf_queues);
+ qcount = 0;
+ for_each_vf(bp, vf_idx) {
+ struct bnx2x_virtf *vf = BP_VF(bp, vf_idx);
+
+ /* set local queue arrays */
+ vf->vfqs = &bp->vfdb->vfqs[qcount];
+ qcount += vf_sb_count(vf);
+ }
+
+ /* prepare msix vectors in VF configuration space */
+ for (vf_idx = first_vf; vf_idx < first_vf + req_vfs; vf_idx++) {
+ bnx2x_pretend_func(bp, HW_VF_HANDLE(bp, vf_idx));
+ REG_WR(bp, PCICFG_OFFSET + GRC_CONFIG_REG_VF_MSIX_CONTROL,
+ num_vf_queues);
+ }
+ bnx2x_pretend_func(bp, BP_ABS_FUNC(bp));
+
+ /* enable sriov. This will probe all the VFs, and consequentially cause
+ * the "acquire" messages to appear on the VF PF channel.
+ */
+ DP(BNX2X_MSG_IOV, "about to call enable sriov\n");
+ pci_disable_sriov(bp->pdev);
rc = pci_enable_sriov(bp->pdev, req_vfs);
if (rc) {
BNX2X_ERR("pci_enable_sriov failed with %d\n", rc);
pci_disable_sriov(bp->pdev);
}
-static int bnx2x_vf_ndo_prep(struct bnx2x *bp, int vfidx,
- struct bnx2x_virtf **vf,
- struct pf_vf_bulletin_content **bulletin)
+int bnx2x_vf_ndo_prep(struct bnx2x *bp, int vfidx, struct bnx2x_virtf **vf,
+ struct pf_vf_bulletin_content **bulletin)
{
if (bp->state != BNX2X_STATE_OPEN) {
BNX2X_ERR("vf ndo called though PF is down\n");
*bulletin = BP_VF_BULLETIN(bp, vfidx);
if (!*vf) {
- BNX2X_ERR("vf ndo called but vf was null. vfidx was %d\n",
+ BNX2X_ERR("vf ndo called but vf struct is null. vfidx was %d\n",
+ vfidx);
+ return -EINVAL;
+ }
+
+ if (!(*vf)->vfqs) {
+ BNX2X_ERR("vf ndo called but vfqs struct is null. Was ndo invoked before dynamically enabling SR-IOV? vfidx was %d\n",
vfidx);
return -EINVAL;
}
rc = bnx2x_vf_ndo_prep(bp, vfidx, &vf, &bulletin);
if (rc)
return rc;
- mac_obj = &bnx2x_vfq(vf, 0, mac_obj);
- vlan_obj = &bnx2x_vfq(vf, 0, vlan_obj);
+ mac_obj = &bnx2x_leading_vfq(vf, mac_obj);
+ vlan_obj = &bnx2x_leading_vfq(vf, vlan_obj);
if (!mac_obj || !vlan_obj) {
BNX2X_ERR("VF partially initialized\n");
return -EINVAL;
ivi->spoofchk = 1; /*always enabled */
if (vf->state == VF_ENABLED) {
/* mac and vlan are in vlan_mac objects */
- mac_obj->get_n_elements(bp, mac_obj, 1, (u8 *)&ivi->mac,
- 0, ETH_ALEN);
- vlan_obj->get_n_elements(bp, vlan_obj, 1, (u8 *)&ivi->vlan,
- 0, VLAN_HLEN);
+ if (validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj)))
+ mac_obj->get_n_elements(bp, mac_obj, 1, (u8 *)&ivi->mac,
+ 0, ETH_ALEN);
+ if (validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, vlan_obj)))
+ vlan_obj->get_n_elements(bp, vlan_obj, 1,
+ (u8 *)&ivi->vlan, 0,
+ VLAN_HLEN);
} else {
/* mac */
if (bulletin->valid_bitmap & (1 << MAC_ADDR_VALID))
return rc;
}
- /* is vf initialized and queue set up? */
q_logical_state =
- bnx2x_get_q_logical_state(bp, &bnx2x_vfq(vf, 0, sp_obj));
+ bnx2x_get_q_logical_state(bp, &bnx2x_leading_vfq(vf, sp_obj));
if (vf->state == VF_ENABLED &&
q_logical_state == BNX2X_Q_LOGICAL_STATE_ACTIVE) {
/* configure the mac in device on this vf's queue */
unsigned long ramrod_flags = 0;
- struct bnx2x_vlan_mac_obj *mac_obj = &bnx2x_vfq(vf, 0, mac_obj);
+ struct bnx2x_vlan_mac_obj *mac_obj =
+ &bnx2x_leading_vfq(vf, mac_obj);
+
+ rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
+ if (rc)
+ return rc;
/* must lock vfpf channel to protect against vf flows */
bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_MAC);
/* is vf initialized and queue set up? */
q_logical_state =
- bnx2x_get_q_logical_state(bp, &bnx2x_vfq(vf, 0, sp_obj));
+ bnx2x_get_q_logical_state(bp, &bnx2x_leading_vfq(vf, sp_obj));
if (vf->state == VF_ENABLED &&
q_logical_state == BNX2X_Q_LOGICAL_STATE_ACTIVE) {
/* configure the vlan in device on this vf's queue */
unsigned long ramrod_flags = 0;
unsigned long vlan_mac_flags = 0;
struct bnx2x_vlan_mac_obj *vlan_obj =
- &bnx2x_vfq(vf, 0, vlan_obj);
+ &bnx2x_leading_vfq(vf, vlan_obj);
struct bnx2x_vlan_mac_ramrod_params ramrod_param;
struct bnx2x_queue_state_params q_params = {NULL};
struct bnx2x_queue_update_params *update_params;
+ rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
+ if (rc)
+ return rc;
memset(&ramrod_param, 0, sizeof(ramrod_param));
/* must lock vfpf channel to protect against vf flows */
*/
__set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
q_params.cmd = BNX2X_Q_CMD_UPDATE;
- q_params.q_obj = &bnx2x_vfq(vf, 0, sp_obj);
+ q_params.q_obj = &bnx2x_leading_vfq(vf, sp_obj);
update_params = &q_params.params.update;
__set_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN_CHNG,
&update_params->update_flags);
#define DRV_MODULE_NAME "tg3"
#define TG3_MAJ_NUM 3
-#define TG3_MIN_NUM 132
+#define TG3_MIN_NUM 133
#define DRV_MODULE_VERSION \
__stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM)
-#define DRV_MODULE_RELDATE "May 21, 2013"
+#define DRV_MODULE_RELDATE "Jul 29, 2013"
#define RESET_KIND_SHUTDOWN 0
#define RESET_KIND_INIT 1
return false;
}
+ static bool tg3_phy_led_bug(struct tg3 *tp)
+ {
+ switch (tg3_asic_rev(tp)) {
+ case ASIC_REV_5719:
+ if ((tp->phy_flags & TG3_PHYFLG_MII_SERDES) &&
+ !tp->pci_fn)
+ return true;
+ return false;
+ }
+
+ return false;
+ }
+
static void tg3_power_down_phy(struct tg3 *tp, bool do_low_power)
{
u32 val;
}
return;
} else if (do_low_power) {
- tg3_writephy(tp, MII_TG3_EXT_CTRL,
- MII_TG3_EXT_CTRL_FORCE_LED_OFF);
+ if (!tg3_phy_led_bug(tp))
+ tg3_writephy(tp, MII_TG3_EXT_CTRL,
+ MII_TG3_EXT_CTRL_FORCE_LED_OFF);
val = MII_TG3_AUXCTL_PCTL_100TX_LPWR |
MII_TG3_AUXCTL_PCTL_SPR_ISOLATE |
static void tg3_power_down(struct tg3 *tp)
{
- tg3_power_down_prepare(tp);
-
pci_wake_from_d3(tp->pdev, tg3_flag(tp, WOL_ENABLE));
pci_set_power_state(tp->pdev, PCI_D3hot);
}
/* tp->lock must be held */
static void tg3_refclk_write(struct tg3 *tp, u64 newval)
{
- tw32(TG3_EAV_REF_CLCK_CTL, TG3_EAV_REF_CLCK_CTL_STOP);
+ u32 clock_ctl = tr32(TG3_EAV_REF_CLCK_CTL);
+
+ tw32(TG3_EAV_REF_CLCK_CTL, clock_ctl | TG3_EAV_REF_CLCK_CTL_STOP);
tw32(TG3_EAV_REF_CLCK_LSB, newval & 0xffffffff);
tw32(TG3_EAV_REF_CLCK_MSB, newval >> 32);
- tw32_f(TG3_EAV_REF_CLCK_CTL, TG3_EAV_REF_CLCK_CTL_RESUME);
+ tw32_f(TG3_EAV_REF_CLCK_CTL, clock_ctl | TG3_EAV_REF_CLCK_CTL_RESUME);
}
static inline void tg3_full_lock(struct tg3 *tp, int irq_sync);
static int tg3_ptp_enable(struct ptp_clock_info *ptp,
struct ptp_clock_request *rq, int on)
{
+ struct tg3 *tp = container_of(ptp, struct tg3, ptp_info);
+ u32 clock_ctl;
+ int rval = 0;
+
+ switch (rq->type) {
+ case PTP_CLK_REQ_PEROUT:
+ if (rq->perout.index != 0)
+ return -EINVAL;
+
+ tg3_full_lock(tp, 0);
+ clock_ctl = tr32(TG3_EAV_REF_CLCK_CTL);
+ clock_ctl &= ~TG3_EAV_CTL_TSYNC_GPIO_MASK;
+
+ if (on) {
+ u64 nsec;
+
+ nsec = rq->perout.start.sec * 1000000000ULL +
+ rq->perout.start.nsec;
+
+ if (rq->perout.period.sec || rq->perout.period.nsec) {
+ netdev_warn(tp->dev,
+ "Device supports only a one-shot timesync output, period must be 0\n");
+ rval = -EINVAL;
+ goto err_out;
+ }
+
+ if (nsec & (1ULL << 63)) {
+ netdev_warn(tp->dev,
+ "Start value (nsec) is over limit. Maximum size of start is only 63 bits\n");
+ rval = -EINVAL;
+ goto err_out;
+ }
+
+ tw32(TG3_EAV_WATCHDOG0_LSB, (nsec & 0xffffffff));
+ tw32(TG3_EAV_WATCHDOG0_MSB,
+ TG3_EAV_WATCHDOG0_EN |
+ ((nsec >> 32) & TG3_EAV_WATCHDOG_MSB_MASK));
+
+ tw32(TG3_EAV_REF_CLCK_CTL,
+ clock_ctl | TG3_EAV_CTL_TSYNC_WDOG0);
+ } else {
+ tw32(TG3_EAV_WATCHDOG0_MSB, 0);
+ tw32(TG3_EAV_REF_CLCK_CTL, clock_ctl);
+ }
+
+err_out:
+ tg3_full_unlock(tp);
+ return rval;
+
+ default:
+ break;
+ }
+
return -EOPNOTSUPP;
}
.max_adj = 250000000,
.n_alarm = 0,
.n_ext_ts = 0,
- .n_per_out = 0,
+ .n_per_out = 1,
.pps = 0,
.adjfreq = tg3_ptp_adjfreq,
.adjtime = tg3_ptp_adjtime,
if (!i && tg3_flag(tp, ENABLE_RSS))
continue;
- tnapi->rx_rcb = dma_alloc_coherent(&tp->pdev->dev,
- TG3_RX_RCB_RING_BYTES(tp),
- &tnapi->rx_rcb_mapping,
- GFP_KERNEL | __GFP_ZERO);
+ tnapi->rx_rcb = dma_zalloc_coherent(&tp->pdev->dev,
+ TG3_RX_RCB_RING_BYTES(tp),
+ &tnapi->rx_rcb_mapping,
+ GFP_KERNEL);
if (!tnapi->rx_rcb)
goto err_out;
}
{
int i;
- tp->hw_stats = dma_alloc_coherent(&tp->pdev->dev,
- sizeof(struct tg3_hw_stats),
- &tp->stats_mapping,
- GFP_KERNEL | __GFP_ZERO);
+ tp->hw_stats = dma_zalloc_coherent(&tp->pdev->dev,
+ sizeof(struct tg3_hw_stats),
+ &tp->stats_mapping, GFP_KERNEL);
if (!tp->hw_stats)
goto err_out;
struct tg3_napi *tnapi = &tp->napi[i];
struct tg3_hw_status *sblk;
- tnapi->hw_status = dma_alloc_coherent(&tp->pdev->dev,
- TG3_HW_STATUS_SIZE,
- &tnapi->status_mapping,
- GFP_KERNEL | __GFP_ZERO);
+ tnapi->hw_status = dma_zalloc_coherent(&tp->pdev->dev,
+ TG3_HW_STATUS_SIZE,
+ &tnapi->status_mapping,
+ GFP_KERNEL);
if (!tnapi->hw_status)
goto err_out;
if (tg3_flag(tp, 5755_PLUS))
tp->rx_mode |= RX_MODE_IPV6_CSUM_ENABLE;
+ if (tg3_asic_rev(tp) == ASIC_REV_5762)
+ tp->rx_mode |= RX_MODE_IPV4_FRAG_FIX;
+
if (tg3_flag(tp, ENABLE_RSS))
tp->rx_mode |= RX_MODE_RSS_ENABLE |
RX_MODE_RSS_ITBL_HASH_BITS_7 |
memset(&tp->net_stats_prev, 0, sizeof(tp->net_stats_prev));
memset(&tp->estats_prev, 0, sizeof(tp->estats_prev));
- tg3_power_down(tp);
+ tg3_power_down_prepare(tp);
tg3_carrier_off(tp);
if (tg3_flag(tp, NO_NVRAM))
return -EINVAL;
- if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER)
- return -EAGAIN;
-
offset = eeprom->offset;
len = eeprom->len;
eeprom->len = 0;
u8 *buf;
__be32 start, end;
- if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER)
- return -EAGAIN;
-
if (tg3_flag(tp, NO_NVRAM) ||
eeprom->magic != TG3_EEPROM_MAGIC)
return -EINVAL;
tg3_phy_start(tp);
}
if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER)
- tg3_power_down(tp);
+ tg3_power_down_prepare(tp);
}
*/
if (tg3_flag(tp, 5780_CLASS)) {
tg3_flag_set(tp, 40BIT_DMA_BUG);
- tp->msi_cap = pci_find_capability(tp->pdev, PCI_CAP_ID_MSI);
+ tp->msi_cap = tp->pdev->msi_cap;
} else {
struct pci_dev *bridge = NULL;
tg3_asic_rev(tp) == ASIC_REV_5762)
tg3_flag_set(tp, PTP_CAPABLE);
- if (tg3_flag(tp, 5717_PLUS)) {
- /* Resume a low-power mode */
- tg3_frob_aux_power(tp, false);
- }
-
tg3_timer_init(tp);
tg3_carrier_off(tp);
static SIMPLE_DEV_PM_OPS(tg3_pm_ops, tg3_suspend, tg3_resume);
+static void tg3_shutdown(struct pci_dev *pdev)
+{
+ struct net_device *dev = pci_get_drvdata(pdev);
+ struct tg3 *tp = netdev_priv(dev);
+
+ rtnl_lock();
+ netif_device_detach(dev);
+
+ if (netif_running(dev))
+ dev_close(dev);
+
+ if (system_state == SYSTEM_POWER_OFF)
+ tg3_power_down(tp);
+
+ rtnl_unlock();
+}
+
/**
* tg3_io_error_detected - called when PCI error is detected
* @pdev: Pointer to PCI device
.remove = tg3_remove_one,
.err_handler = &tg3_err_handler,
.driver.pm = &tg3_pm_ops,
+ .shutdown = tg3_shutdown,
};
module_pci_driver(tg3_driver);
#include "be_cmds.h"
#include <asm/div64.h>
#include <linux/aer.h>
+#include <linux/if_bridge.h>
MODULE_VERSION(DRV_VER);
MODULE_DEVICE_TABLE(pci, be_dev_ids);
q->len = len;
q->entry_size = entry_size;
mem->size = len * entry_size;
- mem->va = dma_alloc_coherent(&adapter->pdev->dev, mem->size, &mem->dma,
- GFP_KERNEL | __GFP_ZERO);
+ mem->va = dma_zalloc_coherent(&adapter->pdev->dev, mem->size, &mem->dma,
+ GFP_KERNEL);
if (!mem->va)
return -ENOMEM;
return 0;
static int be_mac_addr_set(struct net_device *netdev, void *p)
{
struct be_adapter *adapter = netdev_priv(netdev);
+ struct device *dev = &adapter->pdev->dev;
struct sockaddr *addr = p;
- int status = 0;
- u8 current_mac[ETH_ALEN];
- u32 pmac_id = adapter->pmac_id[0];
- bool active_mac = true;
+ int status;
+ u8 mac[ETH_ALEN];
+ u32 old_pmac_id = adapter->pmac_id[0], curr_pmac_id = 0;
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
- /* For BE VF, MAC address is already activated by PF.
- * Hence only operation left is updating netdev->devaddr.
- * Update it if user is passing the same MAC which was used
- * during configuring VF MAC from PF(Hypervisor).
+ /* The PMAC_ADD cmd may fail if the VF doesn't have FILTMGMT
+ * privilege or if PF did not provision the new MAC address.
+ * On BE3, this cmd will always fail if the VF doesn't have the
+ * FILTMGMT privilege. This failure is OK, only if the PF programmed
+ * the MAC for the VF.
*/
- if (!lancer_chip(adapter) && !be_physfn(adapter)) {
- status = be_cmd_mac_addr_query(adapter, current_mac,
- false, adapter->if_handle, 0);
- if (!status && !memcmp(current_mac, addr->sa_data, ETH_ALEN))
- goto done;
- else
- goto err;
- }
+ status = be_cmd_pmac_add(adapter, (u8 *)addr->sa_data,
+ adapter->if_handle, &adapter->pmac_id[0], 0);
+ if (!status) {
+ curr_pmac_id = adapter->pmac_id[0];
- if (!memcmp(addr->sa_data, netdev->dev_addr, ETH_ALEN))
- goto done;
+ /* Delete the old programmed MAC. This call may fail if the
+ * old MAC was already deleted by the PF driver.
+ */
+ if (adapter->pmac_id[0] != old_pmac_id)
+ be_cmd_pmac_del(adapter, adapter->if_handle,
+ old_pmac_id, 0);
+ }
- /* For Lancer check if any MAC is active.
- * If active, get its mac id.
+ /* Decide if the new MAC is successfully activated only after
+ * querying the FW
*/
- if (lancer_chip(adapter) && !be_physfn(adapter))
- be_cmd_get_mac_from_list(adapter, current_mac, &active_mac,
- &pmac_id, 0);
-
- status = be_cmd_pmac_add(adapter, (u8 *)addr->sa_data,
- adapter->if_handle,
- &adapter->pmac_id[0], 0);
-
+ status = be_cmd_get_active_mac(adapter, curr_pmac_id, mac);
if (status)
goto err;
- if (active_mac)
- be_cmd_pmac_del(adapter, adapter->if_handle,
- pmac_id, 0);
-done:
+ /* The MAC change did not happen, either due to lack of privilege
+ * or PF didn't pre-provision.
+ */
+ if (memcmp(addr->sa_data, mac, ETH_ALEN)) {
+ status = -EPERM;
+ goto err;
+ }
+
memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
+ dev_info(dev, "MAC address changed to %pM\n", mac);
return 0;
err:
- dev_err(&adapter->pdev->dev, "MAC %pM set Failed\n", addr->sa_data);
+ dev_warn(dev, "MAC address change to %pM failed\n", addr->sa_data);
return status;
}
ACCESS_ONCE(*acc) = newacc;
}
-void populate_erx_stats(struct be_adapter *adapter,
+static void populate_erx_stats(struct be_adapter *adapter,
struct be_rx_obj *rxo,
u32 erx_stat)
{
if (adapter->promiscuous)
return 0;
- if (adapter->vlans_added > adapter->max_vlans)
+ if (adapter->vlans_added > be_max_vlans(adapter))
goto set_vlan_promisc;
/* Construct VLAN Table to give to HW */
goto ret;
adapter->vlan_tag[vid] = 1;
- if (adapter->vlans_added <= (adapter->max_vlans + 1))
+ if (adapter->vlans_added <= (be_max_vlans(adapter) + 1))
status = be_vid_config(adapter);
if (!status)
goto ret;
adapter->vlan_tag[vid] = 0;
- if (adapter->vlans_added <= adapter->max_vlans)
+ if (adapter->vlans_added <= be_max_vlans(adapter))
status = be_vid_config(adapter);
if (!status)
/* Enable multicast promisc if num configured exceeds what we support */
if (netdev->flags & IFF_ALLMULTI ||
- netdev_mc_count(netdev) > adapter->max_mcast_mac) {
+ netdev_mc_count(netdev) > be_max_mc(adapter)) {
be_cmd_rx_filter(adapter, IFF_ALLMULTI, ON);
goto done;
}
adapter->pmac_id[i], 0);
}
- if (netdev_uc_count(netdev) > adapter->max_pmac_cnt) {
+ if (netdev_uc_count(netdev) > be_max_uc(adapter)) {
be_cmd_rx_filter(adapter, IFF_PROMISC, ON);
adapter->promiscuous = true;
goto done;
struct be_adapter *adapter = netdev_priv(netdev);
struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
int status;
- bool active_mac = false;
- u32 pmac_id;
- u8 old_mac[ETH_ALEN];
if (!sriov_enabled(adapter))
return -EPERM;
if (!is_valid_ether_addr(mac) || vf >= adapter->num_vfs)
return -EINVAL;
- if (lancer_chip(adapter)) {
- status = be_cmd_get_mac_from_list(adapter, old_mac, &active_mac,
- &pmac_id, vf + 1);
- if (!status && active_mac)
- be_cmd_pmac_del(adapter, vf_cfg->if_handle,
- pmac_id, vf + 1);
-
- status = be_cmd_set_mac_list(adapter, mac, 1, vf + 1);
- } else {
- status = be_cmd_pmac_del(adapter, vf_cfg->if_handle,
- vf_cfg->pmac_id, vf + 1);
+ if (BEx_chip(adapter)) {
+ be_cmd_pmac_del(adapter, vf_cfg->if_handle, vf_cfg->pmac_id,
+ vf + 1);
status = be_cmd_pmac_add(adapter, mac, vf_cfg->if_handle,
&vf_cfg->pmac_id, vf + 1);
+ } else {
+ status = be_cmd_set_mac(adapter, mac, vf_cfg->if_handle,
+ vf + 1);
}
if (status)
adapter->vf_cfg[vf].vlan_tag = vlan;
status = be_cmd_set_hsw_config(adapter, vlan,
- vf + 1, adapter->vf_cfg[vf].if_handle);
+ vf + 1, adapter->vf_cfg[vf].if_handle, 0);
}
} else {
/* Reset Transparent Vlan Tagging. */
adapter->vf_cfg[vf].vlan_tag = 0;
vlan = adapter->vf_cfg[vf].def_vid;
status = be_cmd_set_hsw_config(adapter, vlan, vf + 1,
- adapter->vf_cfg[vf].if_handle);
+ adapter->vf_cfg[vf].if_handle, 0);
}
}
/* Process the RX completion indicated by rxcp when GRO is enabled */
-void be_rx_compl_process_gro(struct be_rx_obj *rxo, struct napi_struct *napi,
- struct be_rx_compl_info *rxcp)
+static void be_rx_compl_process_gro(struct be_rx_obj *rxo,
+ struct napi_struct *napi,
+ struct be_rx_compl_info *rxcp)
{
struct be_adapter *adapter = rxo->adapter;
struct be_rx_page_info *page_info;
if (eqo->q.created) {
be_eq_clean(eqo);
be_cmd_q_destroy(adapter, &eqo->q, QTYPE_EQ);
+ netif_napi_del(&eqo->napi);
}
be_queue_free(adapter, &eqo->q);
}
struct be_eq_obj *eqo;
int i, rc;
- adapter->num_evt_qs = num_irqs(adapter);
+ adapter->num_evt_qs = min_t(u16, num_irqs(adapter),
+ adapter->cfg_num_qs);
for_all_evt_queues(adapter, eqo, i) {
+ netif_napi_add(adapter->netdev, &eqo->napi, be_poll,
+ BE_NAPI_WEIGHT);
eqo->adapter = adapter;
eqo->tx_budget = BE_TX_BUDGET;
eqo->idx = i;
if (rc)
return rc;
- rc = be_cmd_eq_create(adapter, eq, eqo->cur_eqd);
+ rc = be_cmd_eq_create(adapter, eqo);
if (rc)
return rc;
}
}
}
-static int be_num_txqs_want(struct be_adapter *adapter)
-{
- if ((!lancer_chip(adapter) && sriov_want(adapter)) ||
- be_is_mc(adapter) ||
- (!lancer_chip(adapter) && !be_physfn(adapter)) ||
- BE2_chip(adapter))
- return 1;
- else
- return adapter->max_tx_queues;
-}
-
-static int be_tx_cqs_create(struct be_adapter *adapter)
+static int be_tx_qs_create(struct be_adapter *adapter)
{
struct be_queue_info *cq, *eq;
- int status;
struct be_tx_obj *txo;
- u8 i;
+ int status, i;
- adapter->num_tx_qs = be_num_txqs_want(adapter);
- if (adapter->num_tx_qs != MAX_TX_QS) {
- rtnl_lock();
- netif_set_real_num_tx_queues(adapter->netdev,
- adapter->num_tx_qs);
- rtnl_unlock();
- }
+ adapter->num_tx_qs = min(adapter->num_evt_qs, be_max_txqs(adapter));
for_all_tx_queues(adapter, txo, i) {
cq = &txo->cq;
status = be_cmd_cq_create(adapter, cq, eq, false, 3);
if (status)
return status;
- }
- return 0;
-}
-
-static int be_tx_qs_create(struct be_adapter *adapter)
-{
- struct be_tx_obj *txo;
- int i, status;
- for_all_tx_queues(adapter, txo, i) {
status = be_queue_alloc(adapter, &txo->q, TX_Q_LEN,
sizeof(struct be_eth_wrb));
if (status)
struct be_rx_obj *rxo;
int rc, i;
- /* We'll create as many RSS rings as there are irqs.
- * But when there's only one irq there's no use creating RSS rings
+ /* We can create as many RSS rings as there are EQs. */
+ adapter->num_rx_qs = adapter->num_evt_qs;
+
+ /* We'll use RSS only if atleast 2 RSS rings are supported.
+ * When RSS is used, we'll need a default RXQ for non-IP traffic.
*/
- adapter->num_rx_qs = (num_irqs(adapter) > 1) ?
- num_irqs(adapter) + 1 : 1;
- if (adapter->num_rx_qs != MAX_RX_QS) {
- rtnl_lock();
- netif_set_real_num_rx_queues(adapter->netdev,
- adapter->num_rx_qs);
- rtnl_unlock();
- }
+ if (adapter->num_rx_qs > 1)
+ adapter->num_rx_qs++;
adapter->big_page_size = (1 << get_order(rx_frag_size)) * PAGE_SIZE;
for_all_rx_queues(adapter, rxo, i) {
if (msix_enabled(adapter)) {
pci_disable_msix(adapter->pdev);
adapter->num_msix_vec = 0;
+ adapter->num_msix_roce_vec = 0;
}
}
-static uint be_num_rss_want(struct be_adapter *adapter)
-{
- u32 num = 0;
-
- if ((adapter->function_caps & BE_FUNCTION_CAPS_RSS) &&
- (lancer_chip(adapter) ||
- (!sriov_want(adapter) && be_physfn(adapter)))) {
- num = adapter->max_rss_queues;
- num = min_t(u32, num, (u32)netif_get_num_default_rss_queues());
- }
- return num;
-}
-
static int be_msix_enable(struct be_adapter *adapter)
{
-#define BE_MIN_MSIX_VECTORS 1
- int i, status, num_vec, num_roce_vec = 0;
+ int i, status, num_vec;
struct device *dev = &adapter->pdev->dev;
- /* If RSS queues are not used, need a vec for default RX Q */
- num_vec = min(be_num_rss_want(adapter), num_online_cpus());
- if (be_roce_supported(adapter)) {
- num_roce_vec = min_t(u32, MAX_ROCE_MSIX_VECTORS,
- (num_online_cpus() + 1));
- num_roce_vec = min(num_roce_vec, MAX_ROCE_EQS);
- num_vec += num_roce_vec;
- num_vec = min(num_vec, MAX_MSIX_VECTORS);
- }
- num_vec = max(num_vec, BE_MIN_MSIX_VECTORS);
+ /* If RoCE is supported, program the max number of NIC vectors that
+ * may be configured via set-channels, along with vectors needed for
+ * RoCe. Else, just program the number we'll use initially.
+ */
+ if (be_roce_supported(adapter))
+ num_vec = min_t(int, 2 * be_max_eqs(adapter),
+ 2 * num_online_cpus());
+ else
+ num_vec = adapter->cfg_num_qs;
for (i = 0; i < num_vec; i++)
adapter->msix_entries[i].entry = i;
status = pci_enable_msix(adapter->pdev, adapter->msix_entries, num_vec);
if (status == 0) {
goto done;
- } else if (status >= BE_MIN_MSIX_VECTORS) {
+ } else if (status >= MIN_MSIX_VECTORS) {
num_vec = status;
status = pci_enable_msix(adapter->pdev, adapter->msix_entries,
num_vec);
}
dev_warn(dev, "MSIx enable failed\n");
+
/* INTx is not supported in VFs, so fail probe if enable_msix fails */
if (!be_physfn(adapter))
return status;
return 0;
done:
- if (be_roce_supported(adapter)) {
- if (num_vec > num_roce_vec) {
- adapter->num_msix_vec = num_vec - num_roce_vec;
- adapter->num_msix_roce_vec =
- num_vec - adapter->num_msix_vec;
- } else {
- adapter->num_msix_vec = num_vec;
- adapter->num_msix_roce_vec = 0;
- }
- } else
- adapter->num_msix_vec = num_vec;
- dev_info(dev, "enabled %d MSI-x vector(s)\n", adapter->num_msix_vec);
+ if (be_roce_supported(adapter) && num_vec > MIN_MSIX_VECTORS) {
+ adapter->num_msix_roce_vec = num_vec / 2;
+ dev_info(dev, "enabled %d MSI-x vector(s) for RoCE\n",
+ adapter->num_msix_roce_vec);
+ }
+
+ adapter->num_msix_vec = num_vec - adapter->num_msix_roce_vec;
+
+ dev_info(dev, "enabled %d MSI-x vector(s) for NIC\n",
+ adapter->num_msix_vec);
return 0;
}
static inline int be_msix_vec_get(struct be_adapter *adapter,
struct be_eq_obj *eqo)
{
- return adapter->msix_entries[eqo->idx].vector;
+ return adapter->msix_entries[eqo->msix_idx].vector;
}
static int be_msix_register(struct be_adapter *adapter)
memset(mac, 0, ETH_ALEN);
cmd.size = sizeof(struct be_cmd_req_acpi_wol_magic_config);
- cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
- GFP_KERNEL | __GFP_ZERO);
+ cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+ GFP_KERNEL);
if (cmd.va == NULL)
return -1;
be_vf_eth_addr_generate(adapter, mac);
for_all_vfs(adapter, vf_cfg, vf) {
- if (lancer_chip(adapter)) {
- status = be_cmd_set_mac_list(adapter, mac, 1, vf + 1);
- } else {
+ if (BEx_chip(adapter))
status = be_cmd_pmac_add(adapter, mac,
vf_cfg->if_handle,
&vf_cfg->pmac_id, vf + 1);
- }
+ else
+ status = be_cmd_set_mac(adapter, mac, vf_cfg->if_handle,
+ vf + 1);
if (status)
dev_err(&adapter->pdev->dev,
int status, vf;
u8 mac[ETH_ALEN];
struct be_vf_cfg *vf_cfg;
- bool active;
+ bool active = false;
for_all_vfs(adapter, vf_cfg, vf) {
be_cmd_get_mac_from_list(adapter, mac, &active,
pci_disable_sriov(adapter->pdev);
for_all_vfs(adapter, vf_cfg, vf) {
- if (lancer_chip(adapter))
- be_cmd_set_mac_list(adapter, NULL, 0, vf + 1);
- else
+ if (BEx_chip(adapter))
be_cmd_pmac_del(adapter, vf_cfg->if_handle,
vf_cfg->pmac_id, vf + 1);
+ else
+ be_cmd_set_mac(adapter, NULL, vf_cfg->if_handle,
+ vf + 1);
be_cmd_if_destroy(adapter, vf_cfg->if_handle, vf + 1);
}
adapter->num_vfs = 0;
}
-static int be_clear(struct be_adapter *adapter)
+static void be_clear_queues(struct be_adapter *adapter)
{
- int i = 1;
+ be_mcc_queues_destroy(adapter);
+ be_rx_cqs_destroy(adapter);
+ be_tx_queues_destroy(adapter);
+ be_evt_queues_destroy(adapter);
+}
+static void be_cancel_worker(struct be_adapter *adapter)
+{
if (adapter->flags & BE_FLAGS_WORKER_SCHEDULED) {
cancel_delayed_work_sync(&adapter->work);
adapter->flags &= ~BE_FLAGS_WORKER_SCHEDULED;
}
+}
+
+static int be_clear(struct be_adapter *adapter)
+{
+ int i;
+
+ be_cancel_worker(adapter);
if (sriov_enabled(adapter))
be_vf_clear(adapter);
- for (; adapter->uc_macs > 0; adapter->uc_macs--, i++)
+ /* delete the primary mac along with the uc-mac list */
+ for (i = 0; i < (adapter->uc_macs + 1); i++)
be_cmd_pmac_del(adapter, adapter->if_handle,
- adapter->pmac_id[i], 0);
+ adapter->pmac_id[i], 0);
+ adapter->uc_macs = 0;
be_cmd_if_destroy(adapter, adapter->if_handle, 0);
- be_mcc_queues_destroy(adapter);
- be_rx_cqs_destroy(adapter);
- be_tx_queues_destroy(adapter);
- be_evt_queues_destroy(adapter);
+ be_clear_queues(adapter);
kfree(adapter->pmac_id);
adapter->pmac_id = NULL;
static int be_vfs_if_create(struct be_adapter *adapter)
{
+ struct be_resources res = {0};
struct be_vf_cfg *vf_cfg;
u32 cap_flags, en_flags, vf;
int status;
BE_IF_FLAGS_MULTICAST;
for_all_vfs(adapter, vf_cfg, vf) {
- if (!BE3_chip(adapter))
- be_cmd_get_profile_config(adapter, &cap_flags,
- NULL, vf + 1);
+ if (!BE3_chip(adapter)) {
+ status = be_cmd_get_profile_config(adapter, &res,
+ vf + 1);
+ if (!status)
+ cap_flags = res.if_cap_flags;
+ }
/* If a FW profile exists, then cap_flags are updated */
en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED |
u16 def_vlan, lnk_speed;
int status, old_vfs, vf;
struct device *dev = &adapter->pdev->dev;
+ u32 privileges;
old_vfs = pci_num_vf(adapter->pdev);
if (old_vfs) {
dev_warn(dev, "Ignoring num_vfs=%d setting\n", num_vfs);
adapter->num_vfs = old_vfs;
} else {
- if (num_vfs > adapter->dev_num_vfs)
+ if (num_vfs > be_max_vfs(adapter))
dev_info(dev, "Device supports %d VFs and not %d\n",
- adapter->dev_num_vfs, num_vfs);
- adapter->num_vfs = min_t(u16, num_vfs, adapter->dev_num_vfs);
+ be_max_vfs(adapter), num_vfs);
+ adapter->num_vfs = min_t(u16, num_vfs, be_max_vfs(adapter));
if (!adapter->num_vfs)
return 0;
}
}
for_all_vfs(adapter, vf_cfg, vf) {
+ /* Allow VFs to programs MAC/VLAN filters */
+ status = be_cmd_get_fn_privileges(adapter, &privileges, vf + 1);
+ if (!status && !(privileges & BE_PRIV_FILTMGMT)) {
+ status = be_cmd_set_fn_privileges(adapter,
+ privileges |
+ BE_PRIV_FILTMGMT,
+ vf + 1);
+ if (!status)
+ dev_info(dev, "VF%d has FILTMGMT privilege\n",
+ vf);
+ }
+
/* BE3 FW, by default, caps VF TX-rate to 100mbps.
* Allow full available bandwidth
*/
vf_cfg->tx_rate = lnk_speed;
status = be_cmd_get_hsw_config(adapter, &def_vlan,
- vf + 1, vf_cfg->if_handle);
+ vf + 1, vf_cfg->if_handle, NULL);
if (status)
goto err;
vf_cfg->def_vid = def_vlan;
return status;
}
+/* On BE2/BE3 FW does not suggest the supported limits */
+static void BEx_get_resources(struct be_adapter *adapter,
+ struct be_resources *res)
+{
+ struct pci_dev *pdev = adapter->pdev;
+ bool use_sriov = false;
+
+ if (BE3_chip(adapter) && be_physfn(adapter)) {
+ int max_vfs;
+
+ max_vfs = pci_sriov_get_totalvfs(pdev);
+ res->max_vfs = max_vfs > 0 ? min(MAX_VFS, max_vfs) : 0;
+ use_sriov = res->max_vfs && num_vfs;
+ }
+
+ if (be_physfn(adapter))
+ res->max_uc_mac = BE_UC_PMAC_COUNT;
+ else
+ res->max_uc_mac = BE_VF_UC_PMAC_COUNT;
+
+ if (adapter->function_mode & FLEX10_MODE)
+ res->max_vlans = BE_NUM_VLANS_SUPPORTED/8;
+ else
+ res->max_vlans = BE_NUM_VLANS_SUPPORTED;
+ res->max_mcast_mac = BE_MAX_MC;
+
+ if (BE2_chip(adapter) || use_sriov || be_is_mc(adapter) ||
+ !be_physfn(adapter))
+ res->max_tx_qs = 1;
+ else
+ res->max_tx_qs = BE3_MAX_TX_QS;
+
+ if ((adapter->function_caps & BE_FUNCTION_CAPS_RSS) &&
+ !use_sriov && be_physfn(adapter))
+ res->max_rss_qs = (adapter->be3_native) ?
+ BE3_MAX_RSS_QS : BE2_MAX_RSS_QS;
+ res->max_rx_qs = res->max_rss_qs + 1;
+
+ res->max_evt_qs = be_physfn(adapter) ? BE3_MAX_EVT_QS : 1;
+
+ res->if_cap_flags = BE_IF_CAP_FLAGS_WANT;
+ if (!(adapter->function_caps & BE_FUNCTION_CAPS_RSS))
+ res->if_cap_flags &= ~BE_IF_FLAGS_RSS;
+}
+
static void be_setup_init(struct be_adapter *adapter)
{
adapter->vlan_prio_bmap = 0xff;
adapter->cmd_privileges = MIN_PRIVILEGES;
}
-static int be_get_mac_addr(struct be_adapter *adapter, u8 *mac, u32 if_handle,
- bool *active_mac, u32 *pmac_id)
+static int be_get_resources(struct be_adapter *adapter)
{
- int status = 0;
-
- if (!is_zero_ether_addr(adapter->netdev->perm_addr)) {
- memcpy(mac, adapter->netdev->dev_addr, ETH_ALEN);
- if (!lancer_chip(adapter) && !be_physfn(adapter))
- *active_mac = true;
- else
- *active_mac = false;
+ struct device *dev = &adapter->pdev->dev;
+ struct be_resources res = {0};
+ int status;
- return status;
+ if (BEx_chip(adapter)) {
+ BEx_get_resources(adapter, &res);
+ adapter->res = res;
}
- if (lancer_chip(adapter)) {
- status = be_cmd_get_mac_from_list(adapter, mac,
- active_mac, pmac_id, 0);
- if (*active_mac) {
- status = be_cmd_mac_addr_query(adapter, mac, false,
- if_handle, *pmac_id);
- }
- } else if (be_physfn(adapter)) {
- /* For BE3, for PF get permanent MAC */
- status = be_cmd_mac_addr_query(adapter, mac, true, 0, 0);
- *active_mac = false;
- } else {
- /* For BE3, for VF get soft MAC assigned by PF*/
- status = be_cmd_mac_addr_query(adapter, mac, false,
- if_handle, 0);
- *active_mac = true;
+ /* For BE3 only check if FW suggests a different max-txqs value */
+ if (BE3_chip(adapter)) {
+ status = be_cmd_get_profile_config(adapter, &res, 0);
+ if (!status && res.max_tx_qs)
+ adapter->res.max_tx_qs =
+ min(adapter->res.max_tx_qs, res.max_tx_qs);
}
- return status;
-}
-
-static void be_get_resources(struct be_adapter *adapter)
-{
- u16 dev_num_vfs;
- int pos, status;
- bool profile_present = false;
- u16 txq_count = 0;
+ /* For Lancer, SH etc read per-function resource limits from FW.
+ * GET_FUNC_CONFIG returns per function guaranteed limits.
+ * GET_PROFILE_CONFIG returns PCI-E related limits PF-pool limits
+ */
if (!BEx_chip(adapter)) {
- status = be_cmd_get_func_config(adapter);
- if (!status)
- profile_present = true;
- } else if (BE3_chip(adapter) && be_physfn(adapter)) {
- be_cmd_get_profile_config(adapter, NULL, &txq_count, 0);
- }
-
- if (profile_present) {
- /* Sanity fixes for Lancer */
- adapter->max_pmac_cnt = min_t(u16, adapter->max_pmac_cnt,
- BE_UC_PMAC_COUNT);
- adapter->max_vlans = min_t(u16, adapter->max_vlans,
- BE_NUM_VLANS_SUPPORTED);
- adapter->max_mcast_mac = min_t(u16, adapter->max_mcast_mac,
- BE_MAX_MC);
- adapter->max_tx_queues = min_t(u16, adapter->max_tx_queues,
- MAX_TX_QS);
- adapter->max_rss_queues = min_t(u16, adapter->max_rss_queues,
- BE3_MAX_RSS_QS);
- adapter->max_event_queues = min_t(u16,
- adapter->max_event_queues,
- BE3_MAX_RSS_QS);
-
- if (adapter->max_rss_queues &&
- adapter->max_rss_queues == adapter->max_rx_queues)
- adapter->max_rss_queues -= 1;
-
- if (adapter->max_event_queues < adapter->max_rss_queues)
- adapter->max_rss_queues = adapter->max_event_queues;
-
- } else {
- if (be_physfn(adapter))
- adapter->max_pmac_cnt = BE_UC_PMAC_COUNT;
- else
- adapter->max_pmac_cnt = BE_VF_UC_PMAC_COUNT;
-
- if (adapter->function_mode & FLEX10_MODE)
- adapter->max_vlans = BE_NUM_VLANS_SUPPORTED/8;
- else
- adapter->max_vlans = BE_NUM_VLANS_SUPPORTED;
+ status = be_cmd_get_func_config(adapter, &res);
+ if (status)
+ return status;
- adapter->max_mcast_mac = BE_MAX_MC;
- adapter->max_tx_queues = txq_count ? txq_count : MAX_TX_QS;
- adapter->max_tx_queues = min_t(u16, adapter->max_tx_queues,
- MAX_TX_QS);
- adapter->max_rss_queues = (adapter->be3_native) ?
- BE3_MAX_RSS_QS : BE2_MAX_RSS_QS;
- adapter->max_event_queues = BE3_MAX_RSS_QS;
+ /* If RoCE may be enabled stash away half the EQs for RoCE */
+ if (be_roce_supported(adapter))
+ res.max_evt_qs /= 2;
+ adapter->res = res;
- adapter->if_cap_flags = BE_IF_FLAGS_UNTAGGED |
- BE_IF_FLAGS_BROADCAST |
- BE_IF_FLAGS_MULTICAST |
- BE_IF_FLAGS_PASS_L3L4_ERRORS |
- BE_IF_FLAGS_MCAST_PROMISCUOUS |
- BE_IF_FLAGS_VLAN_PROMISCUOUS |
- BE_IF_FLAGS_PROMISCUOUS;
+ if (be_physfn(adapter)) {
+ status = be_cmd_get_profile_config(adapter, &res, 0);
+ if (status)
+ return status;
+ adapter->res.max_vfs = res.max_vfs;
+ }
- if (adapter->function_caps & BE_FUNCTION_CAPS_RSS)
- adapter->if_cap_flags |= BE_IF_FLAGS_RSS;
+ dev_info(dev, "Max: txqs %d, rxqs %d, rss %d, eqs %d, vfs %d\n",
+ be_max_txqs(adapter), be_max_rxqs(adapter),
+ be_max_rss(adapter), be_max_eqs(adapter),
+ be_max_vfs(adapter));
+ dev_info(dev, "Max: uc-macs %d, mc-macs %d, vlans %d\n",
+ be_max_uc(adapter), be_max_mc(adapter),
+ be_max_vlans(adapter));
}
- pos = pci_find_ext_capability(adapter->pdev, PCI_EXT_CAP_ID_SRIOV);
- if (pos) {
- pci_read_config_word(adapter->pdev, pos + PCI_SRIOV_TOTAL_VF,
- &dev_num_vfs);
- if (BE3_chip(adapter))
- dev_num_vfs = min_t(u16, dev_num_vfs, MAX_VFS);
- adapter->dev_num_vfs = dev_num_vfs;
- }
+ return 0;
}
/* Routine to query per function resource limits */
&adapter->function_caps,
&adapter->asic_rev);
if (status)
- goto err;
+ return status;
- be_get_resources(adapter);
+ status = be_get_resources(adapter);
+ if (status)
+ return status;
/* primary mac needs 1 pmac entry */
- adapter->pmac_id = kcalloc(adapter->max_pmac_cnt + 1,
- sizeof(u32), GFP_KERNEL);
- if (!adapter->pmac_id) {
- status = -ENOMEM;
- goto err;
- }
+ adapter->pmac_id = kcalloc(be_max_uc(adapter) + 1, sizeof(u32),
+ GFP_KERNEL);
+ if (!adapter->pmac_id)
+ return -ENOMEM;
-err:
- return status;
+ /* Sanitize cfg_num_qs based on HW and platform limits */
+ adapter->cfg_num_qs = min(adapter->cfg_num_qs, be_max_qs(adapter));
+
+ return 0;
}
-static int be_setup(struct be_adapter *adapter)
+static int be_mac_setup(struct be_adapter *adapter)
{
- struct device *dev = &adapter->pdev->dev;
- u32 en_flags;
- u32 tx_fc, rx_fc;
- int status;
u8 mac[ETH_ALEN];
- bool active_mac;
+ int status;
- be_setup_init(adapter);
+ if (is_zero_ether_addr(adapter->netdev->dev_addr)) {
+ status = be_cmd_get_perm_mac(adapter, mac);
+ if (status)
+ return status;
- if (!lancer_chip(adapter))
- be_cmd_req_native_mode(adapter);
+ memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
+ memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN);
+ } else {
+ /* Maybe the HW was reset; dev_addr must be re-programmed */
+ memcpy(mac, adapter->netdev->dev_addr, ETH_ALEN);
+ }
- status = be_get_config(adapter);
+ /* On BE3 VFs this cmd may fail due to lack of privilege.
+ * Ignore the failure as in this case pmac_id is fetched
+ * in the IFACE_CREATE cmd.
+ */
+ be_cmd_pmac_add(adapter, mac, adapter->if_handle,
+ &adapter->pmac_id[0], 0);
+ return 0;
+}
+
+static void be_schedule_worker(struct be_adapter *adapter)
+{
+ schedule_delayed_work(&adapter->work, msecs_to_jiffies(1000));
+ adapter->flags |= BE_FLAGS_WORKER_SCHEDULED;
+}
+
+static int be_setup_queues(struct be_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int status;
+
+ status = be_evt_queues_create(adapter);
if (status)
goto err;
- status = be_msix_enable(adapter);
+ status = be_tx_qs_create(adapter);
if (status)
goto err;
- status = be_evt_queues_create(adapter);
+ status = be_rx_cqs_create(adapter);
if (status)
goto err;
- status = be_tx_cqs_create(adapter);
+ status = be_mcc_queues_create(adapter);
if (status)
goto err;
- status = be_rx_cqs_create(adapter);
+ status = netif_set_real_num_rx_queues(netdev, adapter->num_rx_qs);
if (status)
goto err;
- status = be_mcc_queues_create(adapter);
+ status = netif_set_real_num_tx_queues(netdev, adapter->num_tx_qs);
if (status)
goto err;
- be_cmd_get_fn_privileges(adapter, &adapter->cmd_privileges, 0);
- /* In UMC mode FW does not return right privileges.
- * Override with correct privilege equivalent to PF.
+ return 0;
+err:
+ dev_err(&adapter->pdev->dev, "queue_setup failed\n");
+ return status;
+}
+
+int be_update_queues(struct be_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ int status;
+
+ if (netif_running(netdev))
+ be_close(netdev);
+
+ be_cancel_worker(adapter);
+
+ /* If any vectors have been shared with RoCE we cannot re-program
+ * the MSIx table.
*/
- if (be_is_mc(adapter))
- adapter->cmd_privileges = MAX_PRIVILEGES;
+ if (!adapter->num_msix_roce_vec)
+ be_msix_disable(adapter);
- en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
- BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS;
+ be_clear_queues(adapter);
- if (adapter->function_caps & BE_FUNCTION_CAPS_RSS)
- en_flags |= BE_IF_FLAGS_RSS;
+ if (!msix_enabled(adapter)) {
+ status = be_msix_enable(adapter);
+ if (status)
+ return status;
+ }
- en_flags = en_flags & adapter->if_cap_flags;
+ status = be_setup_queues(adapter);
+ if (status)
+ return status;
- status = be_cmd_if_create(adapter, adapter->if_cap_flags, en_flags,
- &adapter->if_handle, 0);
- if (status != 0)
+ be_schedule_worker(adapter);
+
+ if (netif_running(netdev))
+ status = be_open(netdev);
+
+ return status;
+}
+
+static int be_setup(struct be_adapter *adapter)
+{
+ struct device *dev = &adapter->pdev->dev;
+ u32 tx_fc, rx_fc, en_flags;
+ int status;
+
+ be_setup_init(adapter);
+
+ if (!lancer_chip(adapter))
+ be_cmd_req_native_mode(adapter);
+
+ status = be_get_config(adapter);
+ if (status)
goto err;
- memset(mac, 0, ETH_ALEN);
- active_mac = false;
- status = be_get_mac_addr(adapter, mac, adapter->if_handle,
- &active_mac, &adapter->pmac_id[0]);
- if (status != 0)
+ status = be_msix_enable(adapter);
+ if (status)
goto err;
- if (!active_mac) {
- status = be_cmd_pmac_add(adapter, mac, adapter->if_handle,
- &adapter->pmac_id[0], 0);
- if (status != 0)
- goto err;
- }
+ en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
+ BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS;
+ if (adapter->function_caps & BE_FUNCTION_CAPS_RSS)
+ en_flags |= BE_IF_FLAGS_RSS;
+ en_flags = en_flags & be_if_cap_flags(adapter);
+ status = be_cmd_if_create(adapter, be_if_cap_flags(adapter), en_flags,
+ &adapter->if_handle, 0);
+ if (status)
+ goto err;
- if (is_zero_ether_addr(adapter->netdev->dev_addr)) {
- memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
- memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN);
- }
+ /* Updating real_num_tx/rx_queues() requires rtnl_lock() */
+ rtnl_lock();
+ status = be_setup_queues(adapter);
+ rtnl_unlock();
+ if (status)
+ goto err;
- status = be_tx_qs_create(adapter);
+ be_cmd_get_fn_privileges(adapter, &adapter->cmd_privileges, 0);
+ /* In UMC mode FW does not return right privileges.
+ * Override with correct privilege equivalent to PF.
+ */
+ if (be_is_mc(adapter))
+ adapter->cmd_privileges = MAX_PRIVILEGES;
+
+ status = be_mac_setup(adapter);
if (status)
goto err;
be_cmd_set_flow_control(adapter, adapter->tx_fc,
adapter->rx_fc);
- if (be_physfn(adapter)) {
- if (adapter->dev_num_vfs)
+ if (be_physfn(adapter) && num_vfs) {
+ if (be_max_vfs(adapter))
be_vf_setup(adapter);
else
dev_warn(dev, "device doesn't support SRIOV\n");
if (!status && be_pause_supported(adapter))
adapter->phy.fc_autoneg = 1;
- schedule_delayed_work(&adapter->work, msecs_to_jiffies(1000));
- adapter->flags |= BE_FLAGS_WORKER_SCHEDULED;
+ be_schedule_worker(adapter);
return 0;
err:
be_clear(adapter);
#endif
#define FW_FILE_HDR_SIGN "ServerEngines Corp. "
-char flash_cookie[2][16] = {"*** SE FLAS", "H DIRECTORY *** "};
+static char flash_cookie[2][16] = {"*** SE FLAS", "H DIRECTORY *** "};
static bool be_flash_redboot(struct be_adapter *adapter,
const u8 *p, u32 img_start, int image_size,
}
-struct flash_section_info *get_fsec_info(struct be_adapter *adapter,
+static struct flash_section_info *get_fsec_info(struct be_adapter *adapter,
int header_size,
const struct firmware *fw)
{
return status;
}
+static int be_ndo_bridge_setlink(struct net_device *dev,
+ struct nlmsghdr *nlh)
+{
+ struct be_adapter *adapter = netdev_priv(dev);
+ struct nlattr *attr, *br_spec;
+ int rem;
+ int status = 0;
+ u16 mode = 0;
+
+ if (!sriov_enabled(adapter))
+ return -EOPNOTSUPP;
+
+ br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+
+ nla_for_each_nested(attr, br_spec, rem) {
+ if (nla_type(attr) != IFLA_BRIDGE_MODE)
+ continue;
+
+ mode = nla_get_u16(attr);
+ if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB)
+ return -EINVAL;
+
+ status = be_cmd_set_hsw_config(adapter, 0, 0,
+ adapter->if_handle,
+ mode == BRIDGE_MODE_VEPA ?
+ PORT_FWD_TYPE_VEPA :
+ PORT_FWD_TYPE_VEB);
+ if (status)
+ goto err;
+
+ dev_info(&adapter->pdev->dev, "enabled switch mode: %s\n",
+ mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB");
+
+ return status;
+ }
+err:
+ dev_err(&adapter->pdev->dev, "Failed to set switch mode %s\n",
+ mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB");
+
+ return status;
+}
+
+static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+ struct net_device *dev,
+ u32 filter_mask)
+{
+ struct be_adapter *adapter = netdev_priv(dev);
+ int status = 0;
+ u8 hsw_mode;
+
+ if (!sriov_enabled(adapter))
+ return 0;
+
+ /* BE and Lancer chips support VEB mode only */
+ if (BEx_chip(adapter) || lancer_chip(adapter)) {
+ hsw_mode = PORT_FWD_TYPE_VEB;
+ } else {
+ status = be_cmd_get_hsw_config(adapter, NULL, 0,
+ adapter->if_handle, &hsw_mode);
+ if (status)
+ return 0;
+ }
+
+ return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
+ hsw_mode == PORT_FWD_TYPE_VEPA ?
+ BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB);
+}
+
static const struct net_device_ops be_netdev_ops = {
.ndo_open = be_open,
.ndo_stop = be_close,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = be_netpoll,
#endif
+ .ndo_bridge_setlink = be_ndo_bridge_setlink,
+ .ndo_bridge_getlink = be_ndo_bridge_getlink,
};
static void be_netdev_init(struct net_device *netdev)
{
struct be_adapter *adapter = netdev_priv(netdev);
- struct be_eq_obj *eqo;
- int i;
netdev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |
netdev->netdev_ops = &be_netdev_ops;
SET_ETHTOOL_OPS(netdev, &be_ethtool_ops);
-
- for_all_evt_queues(adapter, eqo, i)
- netif_napi_add(netdev, &eqo->napi, be_poll, BE_NAPI_WEIGHT);
}
static void be_unmap_pci_bars(struct be_adapter *adapter)
memset(mbox_mem_align->va, 0, sizeof(struct be_mcc_mailbox));
rx_filter->size = sizeof(struct be_cmd_req_rx_filter);
- rx_filter->va = dma_alloc_coherent(&adapter->pdev->dev, rx_filter->size,
- &rx_filter->dma,
- GFP_KERNEL | __GFP_ZERO);
+ rx_filter->va = dma_zalloc_coherent(&adapter->pdev->dev,
+ rx_filter->size, &rx_filter->dma,
+ GFP_KERNEL);
if (rx_filter->va == NULL) {
status = -ENOMEM;
goto free_mbox;
/* BE3 and Skyhawk */
cmd->size = sizeof(struct be_cmd_req_get_stats_v1);
- cmd->va = dma_alloc_coherent(&adapter->pdev->dev, cmd->size, &cmd->dma,
- GFP_KERNEL | __GFP_ZERO);
+ cmd->va = dma_zalloc_coherent(&adapter->pdev->dev, cmd->size, &cmd->dma,
+ GFP_KERNEL);
if (cmd->va == NULL)
return -1;
return 0;
level = be_get_fw_log_level(adapter);
adapter->msg_enable = level <= FW_LOG_LEVEL_DEFAULT ? NETIF_MSG_HW : 0;
+ adapter->cfg_num_qs = netif_get_num_default_rss_queues();
return 0;
}
be_cmd_get_stats(adapter, &adapter->stats_cmd);
}
- if (MODULO(adapter->work_counter, adapter->be_get_temp_freq) == 0)
+ if (be_physfn(adapter) &&
+ MODULO(adapter->work_counter, adapter->be_get_temp_freq) == 0)
be_cmd_get_die_temperature(adapter);
for_all_rx_queues(adapter, rxo, i) {
status = pci_enable_pcie_error_reporting(pdev);
if (status)
- dev_err(&pdev->dev, "Could not use PCIe error reporting\n");
+ dev_info(&pdev->dev, "Could not use PCIe error reporting\n");
status = be_ctrl_init(adapter);
if (status)
pci_set_power_state(pdev, PCI_D0);
pci_restore_state(pdev);
+ status = be_fw_wait_ready(adapter);
+ if (status)
+ return status;
+
/* tell fw we're ready to fire cmds */
status = be_cmd_fw_init(adapter);
if (status)
#endif
#define DRIVER_NAME "fec"
-#define FEC_NAPI_WEIGHT 64
/* Pause frame feild and FIFO threshold */
#define FEC_ENET_FCE (1 << 5)
static int mii_cnt;
- static struct bufdesc *fec_enet_get_nextdesc(struct bufdesc *bdp, int is_ex)
+ static inline
+ struct bufdesc *fec_enet_get_nextdesc(struct bufdesc *bdp, struct fec_enet_private *fep)
{
- struct bufdesc_ex *ex = (struct bufdesc_ex *)bdp;
- if (is_ex)
- return (struct bufdesc *)(ex + 1);
+ struct bufdesc *new_bd = bdp + 1;
+ struct bufdesc_ex *ex_new_bd = (struct bufdesc_ex *)bdp + 1;
+ struct bufdesc_ex *ex_base;
+ struct bufdesc *base;
+ int ring_size;
+
+ if (bdp >= fep->tx_bd_base) {
+ base = fep->tx_bd_base;
+ ring_size = fep->tx_ring_size;
+ ex_base = (struct bufdesc_ex *)fep->tx_bd_base;
+ } else {
+ base = fep->rx_bd_base;
+ ring_size = fep->rx_ring_size;
+ ex_base = (struct bufdesc_ex *)fep->rx_bd_base;
+ }
+
+ if (fep->bufdesc_ex)
+ return (struct bufdesc *)((ex_new_bd >= (ex_base + ring_size)) ?
+ ex_base : ex_new_bd);
else
- return bdp + 1;
+ return (new_bd >= (base + ring_size)) ?
+ base : new_bd;
}
- static struct bufdesc *fec_enet_get_prevdesc(struct bufdesc *bdp, int is_ex)
+ static inline
+ struct bufdesc *fec_enet_get_prevdesc(struct bufdesc *bdp, struct fec_enet_private *fep)
{
- struct bufdesc_ex *ex = (struct bufdesc_ex *)bdp;
- if (is_ex)
- return (struct bufdesc *)(ex - 1);
+ struct bufdesc *new_bd = bdp - 1;
+ struct bufdesc_ex *ex_new_bd = (struct bufdesc_ex *)bdp - 1;
+ struct bufdesc_ex *ex_base;
+ struct bufdesc *base;
+ int ring_size;
+
+ if (bdp >= fep->tx_bd_base) {
+ base = fep->tx_bd_base;
+ ring_size = fep->tx_ring_size;
+ ex_base = (struct bufdesc_ex *)fep->tx_bd_base;
+ } else {
+ base = fep->rx_bd_base;
+ ring_size = fep->rx_ring_size;
+ ex_base = (struct bufdesc_ex *)fep->rx_bd_base;
+ }
+
+ if (fep->bufdesc_ex)
+ return (struct bufdesc *)((ex_new_bd < ex_base) ?
+ (ex_new_bd + ring_size) : ex_new_bd);
else
- return bdp - 1;
+ return (new_bd < base) ? (new_bd + ring_size) : new_bd;
}
static void *swap_buffer(void *bufaddr, int len)
}
}
- bdp_pre = fec_enet_get_prevdesc(bdp, fep->bufdesc_ex);
+ bdp_pre = fec_enet_get_prevdesc(bdp, fep);
if ((id_entry->driver_data & FEC_QUIRK_ERR006358) &&
!(bdp_pre->cbd_sc & BD_ENET_TX_READY)) {
fep->delay_work.trig_tx = true;
}
/* If this was the last BD in the ring, start at the beginning again. */
- if (status & BD_ENET_TX_WRAP)
- bdp = fep->tx_bd_base;
- else
- bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_nextdesc(bdp, fep);
fep->cur_tx = bdp;
/* Initialize the receive buffer descriptors. */
bdp = fep->rx_bd_base;
- for (i = 0; i < RX_RING_SIZE; i++) {
+ for (i = 0; i < fep->rx_ring_size; i++) {
/* Initialize the BD for every fragment in the page. */
if (bdp->cbd_bufaddr)
bdp->cbd_sc = BD_ENET_RX_EMPTY;
else
bdp->cbd_sc = 0;
- bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_nextdesc(bdp, fep);
}
/* Set the last buffer to wrap */
- bdp = fec_enet_get_prevdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_prevdesc(bdp, fep);
bdp->cbd_sc |= BD_SC_WRAP;
fep->cur_rx = fep->rx_bd_base;
/* ...and the same for transmit */
bdp = fep->tx_bd_base;
fep->cur_tx = bdp;
- for (i = 0; i < TX_RING_SIZE; i++) {
+ for (i = 0; i < fep->tx_ring_size; i++) {
/* Initialize the BD for every fragment in the page. */
bdp->cbd_sc = 0;
fep->tx_skbuff[i] = NULL;
}
bdp->cbd_bufaddr = 0;
- bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_nextdesc(bdp, fep);
}
/* Set the last buffer to wrap */
- bdp = fec_enet_get_prevdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_prevdesc(bdp, fep);
bdp->cbd_sc |= BD_SC_WRAP;
fep->dirty_tx = bdp;
}
writel(fep->bd_dma, fep->hwp + FEC_R_DES_START);
if (fep->bufdesc_ex)
writel((unsigned long)fep->bd_dma + sizeof(struct bufdesc_ex)
- * RX_RING_SIZE, fep->hwp + FEC_X_DES_START);
+ * fep->rx_ring_size, fep->hwp + FEC_X_DES_START);
else
writel((unsigned long)fep->bd_dma + sizeof(struct bufdesc)
- * RX_RING_SIZE, fep->hwp + FEC_X_DES_START);
+ * fep->rx_ring_size, fep->hwp + FEC_X_DES_START);
for (i = 0; i <= TX_RING_MOD_MASK; i++) {
bdp = fep->dirty_tx;
/* get next bdp of dirty_tx */
- if (bdp->cbd_sc & BD_ENET_TX_WRAP)
- bdp = fep->tx_bd_base;
- else
- bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_nextdesc(bdp, fep);
while (((status = bdp->cbd_sc) & BD_ENET_TX_READY) == 0) {
fep->dirty_tx = bdp;
/* Update pointer to next buffer descriptor to be transmitted */
- if (status & BD_ENET_TX_WRAP)
- bdp = fep->tx_bd_base;
- else
- bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_nextdesc(bdp, fep);
/* Since we have freed up a buffer, the ring is no longer full
*/
htons(ETH_P_8021Q),
vlan_tag);
- if (!skb_defer_rx_timestamp(skb))
- napi_gro_receive(&fep->napi, skb);
+ napi_gro_receive(&fep->napi, skb);
}
bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, data,
}
/* Update BD pointer to next entry */
- if (status & BD_ENET_RX_WRAP)
- bdp = fep->rx_bd_base;
- else
- bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_nextdesc(bdp, fep);
+
/* Doing this here will keep the FEC running while we process
* incoming frames. On a heavily loaded network, we should be
* able to keep up at the expense of system resources.
static void fec_get_mac(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
- struct fec_platform_data *pdata = fep->pdev->dev.platform_data;
+ struct fec_platform_data *pdata = dev_get_platdata(&fep->pdev->dev);
unsigned char *iap, tmpaddr[ETH_ALEN];
/*
* 4) FEC mac registers set by bootloader
*/
if (!is_valid_ether_addr(iap)) {
- *((unsigned long *) &tmpaddr[0]) =
- be32_to_cpu(readl(fep->hwp + FEC_ADDR_LOW));
- *((unsigned short *) &tmpaddr[4]) =
- be16_to_cpu(readl(fep->hwp + FEC_ADDR_HIGH) >> 16);
+ *((__be32 *) &tmpaddr[0]) =
+ cpu_to_be32(readl(fep->hwp + FEC_ADDR_LOW));
+ *((__be16 *) &tmpaddr[4]) =
+ cpu_to_be16(readl(fep->hwp + FEC_ADDR_HIGH) >> 16);
iap = &tmpaddr[0];
}
struct bufdesc *bdp;
bdp = fep->rx_bd_base;
- for (i = 0; i < RX_RING_SIZE; i++) {
+ for (i = 0; i < fep->rx_ring_size; i++) {
skb = fep->rx_skbuff[i];
if (bdp->cbd_bufaddr)
FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
if (skb)
dev_kfree_skb(skb);
- bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_nextdesc(bdp, fep);
}
bdp = fep->tx_bd_base;
- for (i = 0; i < TX_RING_SIZE; i++)
+ for (i = 0; i < fep->tx_ring_size; i++)
kfree(fep->tx_bounce[i]);
}
struct bufdesc *bdp;
bdp = fep->rx_bd_base;
- for (i = 0; i < RX_RING_SIZE; i++) {
+ for (i = 0; i < fep->rx_ring_size; i++) {
skb = netdev_alloc_skb(ndev, FEC_ENET_RX_FRSIZE);
if (!skb) {
fec_enet_free_buffers(ndev);
ebdp->cbd_esc = BD_ENET_RX_INT;
}
- bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_nextdesc(bdp, fep);
}
/* Set the last buffer to wrap. */
- bdp = fec_enet_get_prevdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_prevdesc(bdp, fep);
bdp->cbd_sc |= BD_SC_WRAP;
bdp = fep->tx_bd_base;
- for (i = 0; i < TX_RING_SIZE; i++) {
+ for (i = 0; i < fep->tx_ring_size; i++) {
fep->tx_bounce[i] = kmalloc(FEC_ENET_TX_FRSIZE, GFP_KERNEL);
bdp->cbd_sc = 0;
ebdp->cbd_esc = BD_ENET_TX_INT;
}
- bdp = fec_enet_get_nextdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_nextdesc(bdp, fep);
}
/* Set the last buffer to wrap. */
- bdp = fec_enet_get_prevdesc(bdp, fep->bufdesc_ex);
+ bdp = fec_enet_get_prevdesc(bdp, fep);
bdp->cbd_sc |= BD_SC_WRAP;
return 0;
/* Get the Ethernet address */
fec_get_mac(ndev);
+ /* init the tx & rx ring size */
+ fep->tx_ring_size = TX_RING_SIZE;
+ fep->rx_ring_size = RX_RING_SIZE;
+
/* Set receive and transmit descriptor base. */
fep->rx_bd_base = cbd_base;
if (fep->bufdesc_ex)
fep->tx_bd_base = (struct bufdesc *)
- (((struct bufdesc_ex *)cbd_base) + RX_RING_SIZE);
+ (((struct bufdesc_ex *)cbd_base) + fep->rx_ring_size);
else
- fep->tx_bd_base = cbd_base + RX_RING_SIZE;
+ fep->tx_bd_base = cbd_base + fep->rx_ring_size;
/* The FEC Ethernet specific entries in the device structure */
ndev->watchdog_timeo = TX_TIMEOUT;
ndev->ethtool_ops = &fec_enet_ethtool_ops;
writel(FEC_RX_DISABLED_IMASK, fep->hwp + FEC_IMASK);
- netif_napi_add(ndev, &fep->napi, fec_enet_rx_napi, FEC_NAPI_WEIGHT);
+ netif_napi_add(ndev, &fep->napi, fec_enet_rx_napi, NAPI_POLL_WEIGHT);
if (id_entry->driver_data & FEC_QUIRK_HAS_VLAN) {
/* enable hw VLAN support */
if (of_id)
pdev->id_entry = of_id->data;
- r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!r)
- return -ENXIO;
-
/* Init network device */
ndev = alloc_etherdev(sizeof(struct fec_enet_private));
if (!ndev)
fep->pause_flag |= FEC_PAUSE_FLAG_AUTONEG;
#endif
+ r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
fep->hwp = devm_ioremap_resource(&pdev->dev, r);
if (IS_ERR(fep->hwp)) {
ret = PTR_ERR(fep->hwp);
ret = of_get_phy_mode(pdev->dev.of_node);
if (ret < 0) {
- pdata = pdev->dev.platform_data;
+ pdata = dev_get_platdata(&pdev->dev);
if (pdata)
fep->phy_interface = pdata->phy;
else
fep->bufdesc_ex = 0;
}
- clk_prepare_enable(fep->clk_ahb);
- clk_prepare_enable(fep->clk_ipg);
- clk_prepare_enable(fep->clk_enet_out);
- clk_prepare_enable(fep->clk_ptp);
+ ret = clk_prepare_enable(fep->clk_ahb);
+ if (ret)
+ goto failed_clk;
+
+ ret = clk_prepare_enable(fep->clk_ipg);
+ if (ret)
+ goto failed_clk_ipg;
+
+ if (fep->clk_enet_out) {
+ ret = clk_prepare_enable(fep->clk_enet_out);
+ if (ret)
+ goto failed_clk_enet_out;
+ }
+
+ if (fep->clk_ptp) {
+ ret = clk_prepare_enable(fep->clk_ptp);
+ if (ret)
+ goto failed_clk_ptp;
+ }
fep->reg_phy = devm_regulator_get(&pdev->dev, "phy");
if (!IS_ERR(fep->reg_phy)) {
ret = irq;
goto failed_irq;
}
- ret = request_irq(irq, fec_enet_interrupt, IRQF_DISABLED, pdev->name, ndev);
- if (ret) {
- while (--i >= 0) {
- irq = platform_get_irq(pdev, i);
- free_irq(irq, ndev);
- }
+ ret = devm_request_irq(&pdev->dev, irq, fec_enet_interrupt,
+ IRQF_DISABLED, pdev->name, ndev);
+ if (ret)
goto failed_irq;
- }
}
ret = fec_enet_mii_init(pdev);
fec_enet_mii_remove(fep);
failed_mii_init:
failed_irq:
- for (i = 0; i < FEC_IRQ_NUM; i++) {
- irq = platform_get_irq(pdev, i);
- if (irq > 0)
- free_irq(irq, ndev);
- }
failed_init:
if (fep->reg_phy)
regulator_disable(fep->reg_phy);
failed_regulator:
- clk_disable_unprepare(fep->clk_ahb);
+ if (fep->clk_ptp)
+ clk_disable_unprepare(fep->clk_ptp);
+failed_clk_ptp:
+ if (fep->clk_enet_out)
+ clk_disable_unprepare(fep->clk_enet_out);
+failed_clk_enet_out:
clk_disable_unprepare(fep->clk_ipg);
- clk_disable_unprepare(fep->clk_enet_out);
- clk_disable_unprepare(fep->clk_ptp);
+failed_clk_ipg:
+ clk_disable_unprepare(fep->clk_ahb);
failed_clk:
failed_ioremap:
free_netdev(ndev);
{
struct net_device *ndev = platform_get_drvdata(pdev);
struct fec_enet_private *fep = netdev_priv(ndev);
- int i;
cancel_delayed_work_sync(&(fep->delay_work.delay_work));
unregister_netdev(ndev);
fec_enet_mii_remove(fep);
del_timer_sync(&fep->time_keep);
- for (i = 0; i < FEC_IRQ_NUM; i++) {
- int irq = platform_get_irq(pdev, i);
- if (irq > 0)
- free_irq(irq, ndev);
- }
if (fep->reg_phy)
regulator_disable(fep->reg_phy);
- clk_disable_unprepare(fep->clk_ptp);
+ if (fep->clk_ptp)
+ clk_disable_unprepare(fep->clk_ptp);
if (fep->ptp_clock)
ptp_clock_unregister(fep->ptp_clock);
- clk_disable_unprepare(fep->clk_enet_out);
- clk_disable_unprepare(fep->clk_ahb);
+ if (fep->clk_enet_out)
+ clk_disable_unprepare(fep->clk_enet_out);
clk_disable_unprepare(fep->clk_ipg);
+ clk_disable_unprepare(fep->clk_ahb);
free_netdev(ndev);
return 0;
fec_stop(ndev);
netif_device_detach(ndev);
}
- clk_disable_unprepare(fep->clk_enet_out);
- clk_disable_unprepare(fep->clk_ahb);
+ if (fep->clk_ptp)
+ clk_disable_unprepare(fep->clk_ptp);
+ if (fep->clk_enet_out)
+ clk_disable_unprepare(fep->clk_enet_out);
clk_disable_unprepare(fep->clk_ipg);
+ clk_disable_unprepare(fep->clk_ahb);
if (fep->reg_phy)
regulator_disable(fep->reg_phy);
return ret;
}
- clk_prepare_enable(fep->clk_enet_out);
- clk_prepare_enable(fep->clk_ahb);
- clk_prepare_enable(fep->clk_ipg);
+ ret = clk_prepare_enable(fep->clk_ahb);
+ if (ret)
+ goto failed_clk_ahb;
+
+ ret = clk_prepare_enable(fep->clk_ipg);
+ if (ret)
+ goto failed_clk_ipg;
+
+ if (fep->clk_enet_out) {
+ ret = clk_prepare_enable(fep->clk_enet_out);
+ if (ret)
+ goto failed_clk_enet_out;
+ }
+
+ if (fep->clk_ptp) {
+ ret = clk_prepare_enable(fep->clk_ptp);
+ if (ret)
+ goto failed_clk_ptp;
+ }
+
if (netif_running(ndev)) {
fec_restart(ndev, fep->full_duplex);
netif_device_attach(ndev);
}
return 0;
+
+failed_clk_ptp:
+ if (fep->clk_enet_out)
+ clk_disable_unprepare(fep->clk_enet_out);
+failed_clk_enet_out:
+ clk_disable_unprepare(fep->clk_ipg);
+failed_clk_ipg:
+ clk_disable_unprepare(fep->clk_ahb);
+failed_clk_ahb:
+ if (fep->reg_phy)
+ regulator_disable(fep->reg_phy);
+ return ret;
}
#endif /* CONFIG_PM_SLEEP */
#define MVNETA_MAC_ADDR_HIGH 0x2418
#define MVNETA_SDMA_CONFIG 0x241c
#define MVNETA_SDMA_BRST_SIZE_16 4
-#define MVNETA_NO_DESC_SWAP 0x0
#define MVNETA_RX_BRST_SZ_MASK(burst) ((burst) << 1)
#define MVNETA_RX_NO_DATA_SWAP BIT(4)
#define MVNETA_TX_NO_DATA_SWAP BIT(5)
+#define MVNETA_DESC_SWAP BIT(6)
#define MVNETA_TX_BRST_SZ_MASK(burst) ((burst) << 22)
#define MVNETA_PORT_STATUS 0x2444
#define MVNETA_TX_IN_PRGRS BIT(1)
#define MVNETA_GMAC_FORCE_LINK_PASS BIT(1)
#define MVNETA_GMAC_CONFIG_MII_SPEED BIT(5)
#define MVNETA_GMAC_CONFIG_GMII_SPEED BIT(6)
+ #define MVNETA_GMAC_AN_SPEED_EN BIT(7)
#define MVNETA_GMAC_CONFIG_FULL_DUPLEX BIT(12)
+ #define MVNETA_GMAC_AN_DUPLEX_EN BIT(13)
#define MVNETA_MIB_COUNTERS_BASE 0x3080
#define MVNETA_MIB_LATE_COLLISION 0x7c
#define MVNETA_DA_FILT_SPEC_MCAST 0x3400
* layout of the transmit and reception DMA descriptors, and their
* layout is therefore defined by the hardware design
*/
-struct mvneta_tx_desc {
- u32 command; /* Options used by HW for packet transmitting.*/
+
#define MVNETA_TX_L3_OFF_SHIFT 0
#define MVNETA_TX_IP_HLEN_SHIFT 8
#define MVNETA_TX_L4_UDP BIT(16)
#define MVNETA_TX_L4_CSUM_FULL BIT(30)
#define MVNETA_TX_L4_CSUM_NOT BIT(31)
- u16 reserverd1; /* csum_l4 (for future use) */
- u16 data_size; /* Data size of transmitted packet in bytes */
- u32 buf_phys_addr; /* Physical addr of transmitted buffer */
- u32 reserved2; /* hw_cmd - (for future use, PMT) */
- u32 reserved3[4]; /* Reserved - (for future use) */
-};
-
-struct mvneta_rx_desc {
- u32 status; /* Info about received packet */
#define MVNETA_RXD_ERR_CRC 0x0
#define MVNETA_RXD_ERR_SUMMARY BIT(16)
#define MVNETA_RXD_ERR_OVERRUN BIT(17)
#define MVNETA_RXD_FIRST_LAST_DESC (BIT(26) | BIT(27))
#define MVNETA_RXD_L4_CSUM_OK BIT(30)
+#if defined(__LITTLE_ENDIAN)
+struct mvneta_tx_desc {
+ u32 command; /* Options used by HW for packet transmitting.*/
+ u16 reserverd1; /* csum_l4 (for future use) */
+ u16 data_size; /* Data size of transmitted packet in bytes */
+ u32 buf_phys_addr; /* Physical addr of transmitted buffer */
+ u32 reserved2; /* hw_cmd - (for future use, PMT) */
+ u32 reserved3[4]; /* Reserved - (for future use) */
+};
+
+struct mvneta_rx_desc {
+ u32 status; /* Info about received packet */
u16 reserved1; /* pnc_info - (for future use, PnC) */
u16 data_size; /* Size of received packet in bytes */
+
u32 buf_phys_addr; /* Physical address of the buffer */
u32 reserved2; /* pnc_flow_id (for future use, PnC) */
+
u32 buf_cookie; /* cookie for access to RX buffer in rx path */
u16 reserved3; /* prefetch_cmd, for future use */
u16 reserved4; /* csum_l4 - (for future use, PnC) */
+
+ u32 reserved5; /* pnc_extra PnC (for future use, PnC) */
+ u32 reserved6; /* hw_cmd (for future use, PnC and HWF) */
+};
+#else
+struct mvneta_tx_desc {
+ u16 data_size; /* Data size of transmitted packet in bytes */
+ u16 reserverd1; /* csum_l4 (for future use) */
+ u32 command; /* Options used by HW for packet transmitting.*/
+ u32 reserved2; /* hw_cmd - (for future use, PMT) */
+ u32 buf_phys_addr; /* Physical addr of transmitted buffer */
+ u32 reserved3[4]; /* Reserved - (for future use) */
+};
+
+struct mvneta_rx_desc {
+ u16 data_size; /* Size of received packet in bytes */
+ u16 reserved1; /* pnc_info - (for future use, PnC) */
+ u32 status; /* Info about received packet */
+
+ u32 reserved2; /* pnc_flow_id (for future use, PnC) */
+ u32 buf_phys_addr; /* Physical address of the buffer */
+
+ u16 reserved4; /* csum_l4 - (for future use, PnC) */
+ u16 reserved3; /* prefetch_cmd, for future use */
+ u32 buf_cookie; /* cookie for access to RX buffer in rx path */
+
u32 reserved5; /* pnc_extra PnC (for future use, PnC) */
u32 reserved6; /* hw_cmd (for future use, PnC and HWF) */
};
+#endif
struct mvneta_tx_queue {
/* Number of this TX queue, in the range 0-7 */
/* Default burst size */
val |= MVNETA_TX_BRST_SZ_MASK(MVNETA_SDMA_BRST_SIZE_16);
val |= MVNETA_RX_BRST_SZ_MASK(MVNETA_SDMA_BRST_SIZE_16);
+ val |= MVNETA_RX_NO_DATA_SWAP | MVNETA_TX_NO_DATA_SWAP;
- val |= (MVNETA_RX_NO_DATA_SWAP | MVNETA_TX_NO_DATA_SWAP |
- MVNETA_NO_DESC_SWAP);
+#if defined(__BIG_ENDIAN)
+ val |= MVNETA_DESC_SWAP;
+#endif
/* Assign port SDMA configuration */
mvreg_write(pp, MVNETA_SDMA_CONFIG, val);
+ /* Disable PHY polling in hardware, since we're using the
+ * kernel phylib to do this.
+ */
+ val = mvreg_read(pp, MVNETA_UNIT_CONTROL);
+ val &= ~MVNETA_PHY_POLLING_ENABLE;
+ mvreg_write(pp, MVNETA_UNIT_CONTROL, val);
+
mvneta_set_ucast_table(pp, -1);
mvneta_set_special_mcast_table(pp, -1);
mvneta_set_other_mcast_table(pp, -1);
val = mvreg_read(pp, MVNETA_GMAC_AUTONEG_CONFIG);
val &= ~(MVNETA_GMAC_CONFIG_MII_SPEED |
MVNETA_GMAC_CONFIG_GMII_SPEED |
- MVNETA_GMAC_CONFIG_FULL_DUPLEX);
+ MVNETA_GMAC_CONFIG_FULL_DUPLEX |
+ MVNETA_GMAC_AN_SPEED_EN |
+ MVNETA_GMAC_AN_DUPLEX_EN);
if (phydev->duplex)
val |= MVNETA_GMAC_CONFIG_FULL_DUPLEX;
return 0;
}
+ static int mvneta_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+ {
+ struct mvneta_port *pp = netdev_priv(dev);
+ int ret;
+
+ if (!pp->phy_dev)
+ return -ENOTSUPP;
+
+ ret = phy_mii_ioctl(pp->phy_dev, ifr, cmd);
+ if (!ret)
+ mvneta_adjust_link(dev);
+
+ return ret;
+ }
+
/* Ethtool methods */
/* Get settings (phy address, speed) for ethtools */
.ndo_change_mtu = mvneta_change_mtu,
.ndo_tx_timeout = mvneta_tx_timeout,
.ndo_get_stats64 = mvneta_get_stats64,
+ .ndo_do_ioctl = mvneta_ioctl,
};
const struct ethtool_ops mvneta_eth_tool_ops = {
for (ring = 0; ring < adapter->max_sds_rings; ring++) {
sds_ring = &recv_ctx->sds_rings[ring];
netif_napi_add(netdev, &sds_ring->napi,
- netxen_nic_poll, NETXEN_NETDEV_WEIGHT);
+ netxen_nic_poll, NAPI_POLL_WEIGHT);
}
return 0;
static void netxen_set_msix_bit(struct pci_dev *pdev, int enable)
{
u32 control;
- int pos;
- pos = pci_find_capability(pdev, PCI_CAP_ID_MSIX);
- if (pos) {
- pci_read_config_dword(pdev, pos, &control);
+ if (pdev->msix_cap) {
+ pci_read_config_dword(pdev, pdev->msix_cap, &control);
if (enable)
control |= PCI_MSIX_FLAGS_ENABLE;
else
control = 0;
- pci_write_config_dword(pdev, pos, control);
+ pci_write_config_dword(pdev, pdev->msix_cap, control);
}
}
[RMCR] = 0x0258,
[TFUCR] = 0x0264,
[RFOCR] = 0x0268,
+ [RMIIMODE] = 0x026c,
[FCFTR] = 0x0270,
[TRIMD] = 0x027c,
};
.set_duplex = sh_eth_set_duplex,
.set_rate = sh_eth_set_rate_r8a777x,
+ .register_type = SH_ETH_REG_FAST_RCAR,
+
.ecsr_value = ECSR_PSRTO | ECSR_LCHNG | ECSR_ICD,
.ecsipr_value = ECSIPR_PSRTOIP | ECSIPR_LCHNGIP | ECSIPR_ICDIP,
.eesipr_value = 0x01ff009f,
.hw_swap = 1,
};
+/* R8A7790 */
+static struct sh_eth_cpu_data r8a7790_data = {
+ .set_duplex = sh_eth_set_duplex,
+ .set_rate = sh_eth_set_rate_r8a777x,
+
+ .register_type = SH_ETH_REG_FAST_RCAR,
+
+ .ecsr_value = ECSR_PSRTO | ECSR_LCHNG | ECSR_ICD,
+ .ecsipr_value = ECSIPR_PSRTOIP | ECSIPR_LCHNGIP | ECSIPR_ICDIP,
+ .eesipr_value = 0x01ff009f,
+
+ .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_RTO,
+ .eesr_err_check = EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE |
+ EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE |
+ EESR_ECI,
+
+ .apr = 1,
+ .mpr = 1,
+ .tpauser = 1,
+ .hw_swap = 1,
+ .rmiimode = 1,
+ .shift_rd0 = 1,
+};
+
static void sh_eth_set_rate_sh7724(struct net_device *ndev)
{
struct sh_eth_private *mdp = netdev_priv(ndev);
.set_duplex = sh_eth_set_duplex,
.set_rate = sh_eth_set_rate_sh7724,
+ .register_type = SH_ETH_REG_FAST_SH4,
+
.ecsr_value = ECSR_PSRTO | ECSR_LCHNG | ECSR_ICD,
.ecsipr_value = ECSIPR_PSRTOIP | ECSIPR_LCHNGIP | ECSIPR_ICDIP,
.eesipr_value = 0x01ff009f,
.set_duplex = sh_eth_set_duplex,
.set_rate = sh_eth_set_rate_sh7757,
+ .register_type = SH_ETH_REG_FAST_SH4,
+
.eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff,
.rmcr_value = 0x00000001,
.set_duplex = sh_eth_set_duplex,
.set_rate = sh_eth_set_rate_giga,
+ .register_type = SH_ETH_REG_GIGABIT,
+
.ecsr_value = ECSR_ICD | ECSR_MPD,
.ecsipr_value = ECSIPR_LCHNGIP | ECSIPR_ICDIP | ECSIPR_MPDIP,
.eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff,
.set_duplex = sh_eth_set_duplex,
.set_rate = sh_eth_set_rate_gether,
+ .register_type = SH_ETH_REG_GIGABIT,
+
.ecsr_value = ECSR_ICD | ECSR_MPD,
.ecsipr_value = ECSIPR_LCHNGIP | ECSIPR_ICDIP | ECSIPR_MPDIP,
.eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff,
.set_duplex = sh_eth_set_duplex,
.set_rate = sh_eth_set_rate_gether,
+ .register_type = SH_ETH_REG_GIGABIT,
+
.ecsr_value = ECSR_ICD | ECSR_MPD,
.ecsipr_value = ECSIPR_LCHNGIP | ECSIPR_ICDIP | ECSIPR_MPDIP,
.eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff,
.set_duplex = sh_eth_set_duplex,
.set_rate = sh_eth_set_rate_gether,
+ .register_type = SH_ETH_REG_GIGABIT,
+
.ecsr_value = ECSR_ICD | ECSR_MPD,
.ecsipr_value = ECSIPR_LCHNGIP | ECSIPR_ICDIP | ECSIPR_MPDIP,
.eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff,
};
static struct sh_eth_cpu_data sh7619_data = {
+ .register_type = SH_ETH_REG_FAST_SH3_SH2,
+
.eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff,
.apr = 1,
};
static struct sh_eth_cpu_data sh771x_data = {
+ .register_type = SH_ETH_REG_FAST_SH3_SH2,
+
.eesipr_value = DMAC_M_RFRMER | DMAC_M_ECI | 0x003fffff,
.tsu = 1,
};
if (ret)
goto out;
+ if (mdp->cd->rmiimode)
+ sh_eth_write(ndev, 0x1, RMIIMODE);
+
/* Descriptor format */
sh_eth_ring_format(ndev);
if (mdp->cd->rpadir)
mdp->rx_skbuff[entry] = NULL;
if (mdp->cd->rpadir)
skb_reserve(skb, NET_IP_ALIGN);
+ dma_sync_single_for_cpu(&ndev->dev, rxdesc->addr,
+ mdp->rx_buf_sz,
+ DMA_FROM_DEVICE);
skb_put(skb, pkt_len);
skb->protocol = eth_type_trans(skb, ndev);
- netif_rx(skb);
+ netif_receive_skb(skb);
ndev->stats.rx_packets++;
ndev->stats.rx_bytes += pkt_len;
}
pm_runtime_get_sync(&mdp->pdev->dev);
+ napi_enable(&mdp->napi);
+
ret = request_irq(ndev->irq, sh_eth_interrupt,
mdp->cd->irq_flags, ndev->name, ndev);
if (ret) {
dev_err(&ndev->dev, "Can not assign IRQ number\n");
- return ret;
+ goto out_napi_off;
}
/* Descriptor set */
if (ret)
goto out_free_irq;
- napi_enable(&mdp->napi);
-
return ret;
out_free_irq:
free_irq(ndev->irq, ndev);
+ out_napi_off:
+ napi_disable(&mdp->napi);
pm_runtime_put_sync(&mdp->pdev->dev);
return ret;
}
{
struct sh_eth_private *mdp = netdev_priv(ndev);
- napi_disable(&mdp->napi);
-
netif_stop_queue(ndev);
/* Disable interrupts by clearing the interrupt mask. */
free_irq(ndev->irq, ndev);
+ napi_disable(&mdp->napi);
+
/* Free all the skbuffs in the Rx queue. */
sh_eth_ring_free(ndev);
struct resource *res;
struct net_device *ndev = NULL;
struct sh_eth_private *mdp = NULL;
- struct sh_eth_plat_data *pd = pdev->dev.platform_data;
+ struct sh_eth_plat_data *pd = dev_get_platdata(&pdev->dev);
const struct platform_device_id *id = platform_get_device_id(pdev);
/* get base addr */
SET_NETDEV_DEV(ndev, &pdev->dev);
- /* Fill in the fields of the device structure with ethernet values. */
- ether_setup(ndev);
-
mdp = netdev_priv(ndev);
mdp->num_tx_ring = TX_RING_SIZE;
mdp->num_rx_ring = RX_RING_SIZE;
mdp->edmac_endian = pd->edmac_endian;
mdp->no_ether_link = pd->no_ether_link;
mdp->ether_link_active_low = pd->ether_link_active_low;
- mdp->reg_offset = sh_eth_get_register_offset(pd->register_type);
/* set cpu data */
mdp->cd = (struct sh_eth_cpu_data *)id->driver_data;
+ mdp->reg_offset = sh_eth_get_register_offset(mdp->cd->register_type);
sh_eth_set_default_cpu_data(mdp->cd);
/* set function */
{ "sh7763-gether", (kernel_ulong_t)&sh7763_data },
{ "r8a7740-gether", (kernel_ulong_t)&r8a7740_data },
{ "r8a777x-ether", (kernel_ulong_t)&r8a777x_data },
+ { "r8a7790-ether", (kernel_ulong_t)&r8a7790_data },
{ }
};
MODULE_DEVICE_TABLE(platform, sh_eth_id_table);
plat->force_sf_dma_mode = 1;
}
- dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL);
- if (!dma_cfg)
- return -ENOMEM;
-
- plat->dma_cfg = dma_cfg;
- of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl);
- dma_cfg->fixed_burst = of_property_read_bool(np, "snps,fixed-burst");
- dma_cfg->mixed_burst = of_property_read_bool(np, "snps,mixed-burst");
+ if (of_find_property(np, "snps,pbl", NULL)) {
+ dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg),
+ GFP_KERNEL);
+ if (!dma_cfg)
+ return -ENOMEM;
+ plat->dma_cfg = dma_cfg;
+ of_property_read_u32(np, "snps,pbl", &dma_cfg->pbl);
+ dma_cfg->fixed_burst =
+ of_property_read_bool(np, "snps,fixed-burst");
+ dma_cfg->mixed_burst =
+ of_property_read_bool(np, "snps,mixed-burst");
+ }
+ plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode");
+ if (plat->force_thresh_dma_mode) {
+ plat->force_sf_dma_mode = 0;
+ pr_warn("force_sf_dma_mode is ignored if force_thresh_dma_mode is set.");
- }
return 0;
}
const char *mac = NULL;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!res)
- return -ENODEV;
-
addr = devm_ioremap_resource(dev, res);
if (IS_ERR(addr))
return PTR_ERR(addr);
- plat_dat = pdev->dev.platform_data;
+ plat_dat = dev_get_platdata(&pdev->dev);
if (pdev->dev.of_node) {
if (!plat_dat)
plat_dat = devm_kzalloc(&pdev->dev,
struct sk_buff *skb);
int (*transport_finish)(struct sk_buff *skb,
int async);
+ void (*local_error)(struct sk_buff *skb, u32 mtu);
};
extern int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo);
extern int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo);
+ extern struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
+ extern void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo);
extern void xfrm_state_delete_tunnel(struct xfrm_state *x);
extern int xfrm_output_resume(struct sk_buff *skb, int err);
extern int xfrm_output(struct sk_buff *skb);
extern int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb);
+ extern void xfrm_local_error(struct sk_buff *skb, int mtu);
extern int xfrm4_extract_header(struct sk_buff *skb);
extern int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb);
extern int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
extern int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family);
extern int xfrm4_mode_tunnel_input_register(struct xfrm_tunnel *handler);
extern int xfrm4_mode_tunnel_input_deregister(struct xfrm_tunnel *handler);
+ extern void xfrm4_local_error(struct sk_buff *skb, u32 mtu);
extern int xfrm6_extract_header(struct sk_buff *skb);
extern int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb);
extern int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi);
extern int xfrm6_output_finish(struct sk_buff *skb);
extern int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb,
u8 **prevhdr);
+ extern void xfrm6_local_error(struct sk_buff *skb, u32 mtu);
#ifdef CONFIG_XFRM
extern int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb);
int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info);
u32 xfrm_get_acqseq(void);
extern int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi);
-struct xfrm_state *xfrm_find_acq(struct net *net, struct xfrm_mark *mark,
+struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark,
u8 mode, u32 reqid, u8 proto,
const xfrm_address_t *daddr,
const xfrm_address_t *saddr, int create,
mdst = br_mdb_get(br, skb, vid);
if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
- br_multicast_querier_exists(br))
+ br_multicast_querier_exists(br, eth_hdr(skb)))
br_multicast_deliver(mdst, skb);
else
br_flood_deliver(br, skb, false);
int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp)
{
struct netpoll *np;
- int err = 0;
+ int err;
+
+ if (!p->br->dev->npinfo)
+ return 0;
np = kzalloc(sizeof(*p->np), gfp);
- err = -ENOMEM;
if (!np)
- goto out;
+ return -ENOMEM;
err = __netpoll_setup(np, p->dev, gfp);
if (err) {
kfree(np);
- goto out;
+ return err;
}
p->np = np;
-
-out:
return err;
}
#include <net/netlink.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
+#include <net/addrconf.h>
#endif
#include "br_private.h"
for (i = 0; i < mdb->max; i++) {
struct net_bridge_mdb_entry *mp;
- struct net_bridge_port_group *p, **pp;
+ struct net_bridge_port_group *p;
+ struct net_bridge_port_group __rcu **pp;
struct net_bridge_port *port;
hlist_for_each_entry_rcu(mp, &mdb->mhash[i], hlist[mdb->ver]) {
return false;
#if IS_ENABLED(CONFIG_IPV6)
} else if (entry->addr.proto == htons(ETH_P_IPV6)) {
- if (!ipv6_is_transient_multicast(&entry->addr.u.ip6))
+ if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6))
return false;
#endif
} else
if (!netif_running(br->dev) || br->multicast_disabled)
return -EINVAL;
- if (timer_pending(&br->multicast_querier_timer))
- return -EBUSY;
-
ip.proto = entry->addr.proto;
- if (ip.proto == htons(ETH_P_IP))
+ if (ip.proto == htons(ETH_P_IP)) {
+ if (timer_pending(&br->ip4_querier.timer))
+ return -EBUSY;
+
ip.u.ip4 = entry->addr.u.ip4;
#if IS_ENABLED(CONFIG_IPV6)
- else
+ } else {
+ if (timer_pending(&br->ip6_querier.timer))
+ return -EBUSY;
+
ip.u.ip6 = entry->addr.u.ip6;
#endif
+ }
spin_lock_bh(&br->multicast_lock);
mdb = mlock_dereference(br->mdb, br);
#include <net/ipv6.h>
#include <net/mld.h>
#include <net/ip6_checksum.h>
+#include <net/addrconf.h>
#endif
#include "br_private.h"
- static void br_multicast_start_querier(struct net_bridge *br);
+ static void br_multicast_start_querier(struct net_bridge *br,
+ struct bridge_mcast_query *query);
unsigned int br_mdb_rehash_seq;
static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
{
struct br_ip br_group;
- if (!ipv6_is_transient_multicast(group))
+ if (ipv6_addr_is_ll_all_nodes(group))
return 0;
br_group.u.ip6 = *group;
{
}
- static void br_multicast_querier_expired(unsigned long data)
+ static void br_multicast_querier_expired(struct net_bridge *br,
+ struct bridge_mcast_query *query)
{
- struct net_bridge *br = (void *)data;
-
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) || br->multicast_disabled)
goto out;
- br_multicast_start_querier(br);
+ br_multicast_start_querier(br, query);
out:
spin_unlock(&br->multicast_lock);
}
+ static void br_ip4_multicast_querier_expired(unsigned long data)
+ {
+ struct net_bridge *br = (void *)data;
+
+ br_multicast_querier_expired(br, &br->ip4_query);
+ }
+
+ #if IS_ENABLED(CONFIG_IPV6)
+ static void br_ip6_multicast_querier_expired(unsigned long data)
+ {
+ struct net_bridge *br = (void *)data;
+
+ br_multicast_querier_expired(br, &br->ip6_query);
+ }
+ #endif
+
static void __br_multicast_send_query(struct net_bridge *br,
struct net_bridge_port *port,
struct br_ip *ip)
}
static void br_multicast_send_query(struct net_bridge *br,
- struct net_bridge_port *port, u32 sent)
+ struct net_bridge_port *port,
+ struct bridge_mcast_query *query)
{
unsigned long time;
struct br_ip br_group;
+ struct bridge_mcast_querier *querier = NULL;
if (!netif_running(br->dev) || br->multicast_disabled ||
- !br->multicast_querier ||
- timer_pending(&br->multicast_querier_timer))
+ !br->multicast_querier)
return;
memset(&br_group.u, 0, sizeof(br_group.u));
- br_group.proto = htons(ETH_P_IP);
- __br_multicast_send_query(br, port, &br_group);
-
+ if (port ? (query == &port->ip4_query) :
+ (query == &br->ip4_query)) {
+ querier = &br->ip4_querier;
+ br_group.proto = htons(ETH_P_IP);
#if IS_ENABLED(CONFIG_IPV6)
- br_group.proto = htons(ETH_P_IPV6);
- __br_multicast_send_query(br, port, &br_group);
+ } else {
+ querier = &br->ip6_querier;
+ br_group.proto = htons(ETH_P_IPV6);
#endif
+ }
+
+ if (!querier || timer_pending(&querier->timer))
+ return;
+
+ __br_multicast_send_query(br, port, &br_group);
time = jiffies;
- time += sent < br->multicast_startup_query_count ?
+ time += query->startup_sent < br->multicast_startup_query_count ?
br->multicast_startup_query_interval :
br->multicast_query_interval;
- mod_timer(port ? &port->multicast_query_timer :
- &br->multicast_query_timer, time);
+ mod_timer(&query->timer, time);
}
- static void br_multicast_port_query_expired(unsigned long data)
+ static void br_multicast_port_query_expired(struct net_bridge_port *port,
+ struct bridge_mcast_query *query)
{
- struct net_bridge_port *port = (void *)data;
struct net_bridge *br = port->br;
spin_lock(&br->multicast_lock);
port->state == BR_STATE_BLOCKING)
goto out;
- if (port->multicast_startup_queries_sent <
- br->multicast_startup_query_count)
- port->multicast_startup_queries_sent++;
+ if (query->startup_sent < br->multicast_startup_query_count)
+ query->startup_sent++;
- br_multicast_send_query(port->br, port,
- port->multicast_startup_queries_sent);
+ br_multicast_send_query(port->br, port, query);
out:
spin_unlock(&br->multicast_lock);
}
+ static void br_ip4_multicast_port_query_expired(unsigned long data)
+ {
+ struct net_bridge_port *port = (void *)data;
+
+ br_multicast_port_query_expired(port, &port->ip4_query);
+ }
+
+ #if IS_ENABLED(CONFIG_IPV6)
+ static void br_ip6_multicast_port_query_expired(unsigned long data)
+ {
+ struct net_bridge_port *port = (void *)data;
+
+ br_multicast_port_query_expired(port, &port->ip6_query);
+ }
+ #endif
+
void br_multicast_add_port(struct net_bridge_port *port)
{
port->multicast_router = 1;
setup_timer(&port->multicast_router_timer, br_multicast_router_expired,
(unsigned long)port);
- setup_timer(&port->multicast_query_timer,
- br_multicast_port_query_expired, (unsigned long)port);
+ setup_timer(&port->ip4_query.timer, br_ip4_multicast_port_query_expired,
+ (unsigned long)port);
+ #if IS_ENABLED(CONFIG_IPV6)
+ setup_timer(&port->ip6_query.timer, br_ip6_multicast_port_query_expired,
+ (unsigned long)port);
+ #endif
}
void br_multicast_del_port(struct net_bridge_port *port)
del_timer_sync(&port->multicast_router_timer);
}
- static void __br_multicast_enable_port(struct net_bridge_port *port)
+ static void br_multicast_enable(struct bridge_mcast_query *query)
{
- port->multicast_startup_queries_sent = 0;
+ query->startup_sent = 0;
- if (try_to_del_timer_sync(&port->multicast_query_timer) >= 0 ||
- del_timer(&port->multicast_query_timer))
- mod_timer(&port->multicast_query_timer, jiffies);
+ if (try_to_del_timer_sync(&query->timer) >= 0 ||
+ del_timer(&query->timer))
+ mod_timer(&query->timer, jiffies);
}
void br_multicast_enable_port(struct net_bridge_port *port)
if (br->multicast_disabled || !netif_running(br->dev))
goto out;
- __br_multicast_enable_port(port);
+ br_multicast_enable(&port->ip4_query);
+ #if IS_ENABLED(CONFIG_IPV6)
+ br_multicast_enable(&port->ip6_query);
+ #endif
out:
spin_unlock(&br->multicast_lock);
if (!hlist_unhashed(&port->rlist))
hlist_del_init_rcu(&port->rlist);
del_timer(&port->multicast_router_timer);
- del_timer(&port->multicast_query_timer);
+ del_timer(&port->ip4_query.timer);
+ #if IS_ENABLED(CONFIG_IPV6)
+ del_timer(&port->ip6_query.timer);
+ #endif
spin_unlock(&br->multicast_lock);
}
}
#endif
- static void br_multicast_update_querier_timer(struct net_bridge *br,
- unsigned long max_delay)
+ static void
+ br_multicast_update_querier_timer(struct net_bridge *br,
+ struct bridge_mcast_querier *querier,
+ unsigned long max_delay)
{
- if (!timer_pending(&br->multicast_querier_timer))
- br->multicast_querier_delay_time = jiffies + max_delay;
+ if (!timer_pending(&querier->timer))
+ querier->delay_time = jiffies + max_delay;
- mod_timer(&br->multicast_querier_timer,
- jiffies + br->multicast_querier_interval);
+ mod_timer(&querier->timer, jiffies + br->multicast_querier_interval);
}
/*
static void br_multicast_query_received(struct net_bridge *br,
struct net_bridge_port *port,
+ struct bridge_mcast_querier *querier,
int saddr,
unsigned long max_delay)
{
if (saddr)
- br_multicast_update_querier_timer(br, max_delay);
- else if (timer_pending(&br->multicast_querier_timer))
+ br_multicast_update_querier_timer(br, querier, max_delay);
+ else if (timer_pending(&querier->timer))
return;
br_multicast_mark_router(br, port);
IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1;
}
- br_multicast_query_received(br, port, !!iph->saddr, max_delay);
+ br_multicast_query_received(br, port, &br->ip4_querier, !!iph->saddr,
+ max_delay);
if (!group)
goto out;
if (!mld2q->mld2q_nsrcs)
group = &mld2q->mld2q_mca;
- max_delay = max(msecs_to_jiffies(MLDV2_MRC(ntohs(mld2q->mld2q_mrc))), 1UL);
+ max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL);
}
- br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr),
- max_delay);
+ br_multicast_query_received(br, port, &br->ip6_querier,
+ !ipv6_addr_any(&ip6h->saddr), max_delay);
if (!group)
goto out;
static void br_multicast_leave_group(struct net_bridge *br,
struct net_bridge_port *port,
- struct br_ip *group)
+ struct br_ip *group,
+ struct bridge_mcast_querier *querier,
+ struct bridge_mcast_query *query)
{
struct net_bridge_mdb_htable *mdb;
struct net_bridge_mdb_entry *mp;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) ||
(port && port->state == BR_STATE_DISABLED) ||
- timer_pending(&br->multicast_querier_timer))
+ timer_pending(&querier->timer))
goto out;
mdb = mlock_dereference(br->mdb, br);
if (!mp)
goto out;
- if (br->multicast_querier &&
- !timer_pending(&br->multicast_querier_timer)) {
+ if (br->multicast_querier) {
__br_multicast_send_query(br, port, &mp->addr);
time = jiffies + br->multicast_last_member_count *
br->multicast_last_member_interval;
- mod_timer(port ? &port->multicast_query_timer :
- &br->multicast_query_timer, time);
+
+ mod_timer(&query->timer, time);
for (p = mlock_dereference(mp->ports, br);
p != NULL;
mod_timer(&mp->timer, time);
}
}
-
out:
spin_unlock(&br->multicast_lock);
}
__u16 vid)
{
struct br_ip br_group;
+ struct bridge_mcast_query *query = port ? &port->ip4_query :
+ &br->ip4_query;
if (ipv4_is_local_multicast(group))
return;
br_group.proto = htons(ETH_P_IP);
br_group.vid = vid;
- br_multicast_leave_group(br, port, &br_group);
+ br_multicast_leave_group(br, port, &br_group, &br->ip4_querier, query);
}
#if IS_ENABLED(CONFIG_IPV6)
__u16 vid)
{
struct br_ip br_group;
+ struct bridge_mcast_query *query = port ? &port->ip6_query :
+ &br->ip6_query;
+
- if (!ipv6_is_transient_multicast(group))
+ if (ipv6_addr_is_ll_all_nodes(group))
return;
br_group.u.ip6 = *group;
br_group.proto = htons(ETH_P_IPV6);
br_group.vid = vid;
- br_multicast_leave_group(br, port, &br_group);
+ br_multicast_leave_group(br, port, &br_group, &br->ip6_querier, query);
}
#endif
* - MLD has always Router Alert hop-by-hop option
* - But we do not support jumbrograms.
*/
- if (ip6h->version != 6 ||
- ip6h->nexthdr != IPPROTO_HOPOPTS ||
+ if (ip6h->version != 6)
+ return 0;
+
+ /* Prevent flooding this packet if there is no listener present */
+ if (!ipv6_addr_is_ll_all_nodes(&ip6h->daddr))
+ BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
+
+ if (ip6h->nexthdr != IPPROTO_HOPOPTS ||
ip6h->payload_len == 0)
return 0;
return 0;
}
- static void br_multicast_query_expired(unsigned long data)
+ static void br_multicast_query_expired(struct net_bridge *br,
+ struct bridge_mcast_query *query)
+ {
+ spin_lock(&br->multicast_lock);
+ if (query->startup_sent < br->multicast_startup_query_count)
+ query->startup_sent++;
+
+ br_multicast_send_query(br, NULL, query);
+ spin_unlock(&br->multicast_lock);
+ }
+
+ static void br_ip4_multicast_query_expired(unsigned long data)
{
struct net_bridge *br = (void *)data;
- spin_lock(&br->multicast_lock);
- if (br->multicast_startup_queries_sent <
- br->multicast_startup_query_count)
- br->multicast_startup_queries_sent++;
+ br_multicast_query_expired(br, &br->ip4_query);
+ }
- br_multicast_send_query(br, NULL, br->multicast_startup_queries_sent);
+ #if IS_ENABLED(CONFIG_IPV6)
+ static void br_ip6_multicast_query_expired(unsigned long data)
+ {
+ struct net_bridge *br = (void *)data;
- spin_unlock(&br->multicast_lock);
+ br_multicast_query_expired(br, &br->ip6_query);
}
+ #endif
void br_multicast_init(struct net_bridge *br)
{
br->multicast_querier_interval = 255 * HZ;
br->multicast_membership_interval = 260 * HZ;
- br->multicast_querier_delay_time = 0;
+ br->ip4_querier.delay_time = 0;
+ #if IS_ENABLED(CONFIG_IPV6)
+ br->ip6_querier.delay_time = 0;
+ #endif
spin_lock_init(&br->multicast_lock);
setup_timer(&br->multicast_router_timer,
br_multicast_local_router_expired, 0);
- setup_timer(&br->multicast_querier_timer,
- br_multicast_querier_expired, (unsigned long)br);
- setup_timer(&br->multicast_query_timer, br_multicast_query_expired,
+ setup_timer(&br->ip4_querier.timer, br_ip4_multicast_querier_expired,
+ (unsigned long)br);
+ setup_timer(&br->ip4_query.timer, br_ip4_multicast_query_expired,
(unsigned long)br);
+ #if IS_ENABLED(CONFIG_IPV6)
+ setup_timer(&br->ip6_querier.timer, br_ip6_multicast_querier_expired,
+ (unsigned long)br);
+ setup_timer(&br->ip6_query.timer, br_ip6_multicast_query_expired,
+ (unsigned long)br);
+ #endif
}
- void br_multicast_open(struct net_bridge *br)
+ static void __br_multicast_open(struct net_bridge *br,
+ struct bridge_mcast_query *query)
{
- br->multicast_startup_queries_sent = 0;
+ query->startup_sent = 0;
if (br->multicast_disabled)
return;
- mod_timer(&br->multicast_query_timer, jiffies);
+ mod_timer(&query->timer, jiffies);
+ }
+
+ void br_multicast_open(struct net_bridge *br)
+ {
+ __br_multicast_open(br, &br->ip4_query);
+ #if IS_ENABLED(CONFIG_IPV6)
+ __br_multicast_open(br, &br->ip6_query);
+ #endif
}
void br_multicast_stop(struct net_bridge *br)
int i;
del_timer_sync(&br->multicast_router_timer);
- del_timer_sync(&br->multicast_querier_timer);
- del_timer_sync(&br->multicast_query_timer);
+ del_timer_sync(&br->ip4_querier.timer);
+ del_timer_sync(&br->ip4_query.timer);
+ #if IS_ENABLED(CONFIG_IPV6)
+ del_timer_sync(&br->ip6_querier.timer);
+ del_timer_sync(&br->ip6_query.timer);
+ #endif
spin_lock_bh(&br->multicast_lock);
mdb = mlock_dereference(br->mdb, br);
return err;
}
- static void br_multicast_start_querier(struct net_bridge *br)
+ static void br_multicast_start_querier(struct net_bridge *br,
+ struct bridge_mcast_query *query)
{
struct net_bridge_port *port;
- br_multicast_open(br);
+ __br_multicast_open(br, query);
list_for_each_entry(port, &br->port_list, list) {
if (port->state == BR_STATE_DISABLED ||
port->state == BR_STATE_BLOCKING)
continue;
- __br_multicast_enable_port(port);
+ if (query == &br->ip4_query)
+ br_multicast_enable(&port->ip4_query);
+ #if IS_ENABLED(CONFIG_IPV6)
+ else
+ br_multicast_enable(&port->ip6_query);
+ #endif
}
}
goto rollback;
}
- br_multicast_start_querier(br);
+ br_multicast_start_querier(br, &br->ip4_query);
+ #if IS_ENABLED(CONFIG_IPV6)
+ br_multicast_start_querier(br, &br->ip6_query);
+ #endif
unlock:
spin_unlock_bh(&br->multicast_lock);
goto unlock;
max_delay = br->multicast_query_response_interval;
- if (!timer_pending(&br->multicast_querier_timer))
- br->multicast_querier_delay_time = jiffies + max_delay;
- br_multicast_start_querier(br);
+ if (!timer_pending(&br->ip4_querier.timer))
+ br->ip4_querier.delay_time = jiffies + max_delay;
+
+ br_multicast_start_querier(br, &br->ip4_query);
+
+ #if IS_ENABLED(CONFIG_IPV6)
+ if (!timer_pending(&br->ip6_querier.timer))
+ br->ip6_querier.delay_time = jiffies + max_delay;
+
+ br_multicast_start_querier(br, &br->ip6_query);
+ #endif
unlock:
spin_unlock_bh(&br->multicast_lock);
__u16 vid;
};
+ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
+ /* our own querier */
+ struct bridge_mcast_query {
+ struct timer_list timer;
+ u32 startup_sent;
+ };
+
+ /* other querier */
+ struct bridge_mcast_querier {
+ struct timer_list timer;
+ unsigned long delay_time;
+ };
+ #endif
+
struct net_port_vlans {
u16 port_idx;
u16 pvid;
#define BR_FLOOD 0x00000040
#ifdef CONFIG_BRIDGE_IGMP_SNOOPING
- u32 multicast_startup_queries_sent;
+ struct bridge_mcast_query ip4_query;
+ #if IS_ENABLED(CONFIG_IPV6)
+ struct bridge_mcast_query ip6_query;
+ #endif /* IS_ENABLED(CONFIG_IPV6) */
unsigned char multicast_router;
struct timer_list multicast_router_timer;
- struct timer_list multicast_query_timer;
struct hlist_head mglist;
struct hlist_node rlist;
#endif
u32 hash_max;
u32 multicast_last_member_count;
- u32 multicast_startup_queries_sent;
u32 multicast_startup_query_count;
unsigned long multicast_last_member_interval;
unsigned long multicast_query_interval;
unsigned long multicast_query_response_interval;
unsigned long multicast_startup_query_interval;
- unsigned long multicast_querier_delay_time;
spinlock_t multicast_lock;
struct net_bridge_mdb_htable __rcu *mdb;
struct hlist_head router_list;
struct timer_list multicast_router_timer;
- struct timer_list multicast_querier_timer;
- struct timer_list multicast_query_timer;
+ struct bridge_mcast_querier ip4_querier;
+ struct bridge_mcast_query ip4_query;
+ #if IS_ENABLED(CONFIG_IPV6)
+ struct bridge_mcast_querier ip6_querier;
+ struct bridge_mcast_query ip6_query;
+ #endif /* IS_ENABLED(CONFIG_IPV6) */
#endif
struct timer_list hello_timer;
extern netdev_tx_t br_dev_xmit(struct sk_buff *skb,
struct net_device *dev);
#ifdef CONFIG_NET_POLL_CONTROLLER
-static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br)
-{
- return br->dev->npinfo;
-}
-
static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
struct sk_buff *skb)
{
extern int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp);
extern void br_netpoll_disable(struct net_bridge_port *p);
#else
-static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br)
-{
- return NULL;
-}
-
static inline void br_netpoll_send_skb(const struct net_bridge_port *p,
struct sk_buff *skb)
{
extern struct net_bridge_port_group *br_multicast_new_port_group(
struct net_bridge_port *port,
struct br_ip *group,
- struct net_bridge_port_group *next,
+ struct net_bridge_port_group __rcu *next,
unsigned char state);
extern void br_mdb_init(void);
extern void br_mdb_uninit(void);
#define mlock_dereference(X, br) \
rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
-#if IS_ENABLED(CONFIG_IPV6)
-#include <net/addrconf.h>
-static inline int ipv6_is_transient_multicast(const struct in6_addr *addr)
-{
- if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr))
- return 1;
- return 0;
-}
-#endif
-
static inline bool br_multicast_is_router(struct net_bridge *br)
{
return br->multicast_router == 2 ||
timer_pending(&br->multicast_router_timer));
}
- static inline bool br_multicast_querier_exists(struct net_bridge *br)
+ static inline bool
+ __br_multicast_querier_exists(struct net_bridge *br,
+ struct bridge_mcast_querier *querier)
{
- return time_is_before_jiffies(br->multicast_querier_delay_time) &&
- (br->multicast_querier ||
- timer_pending(&br->multicast_querier_timer));
+ return time_is_before_jiffies(querier->delay_time) &&
+ (br->multicast_querier || timer_pending(&querier->timer));
+ }
+
+ static inline bool br_multicast_querier_exists(struct net_bridge *br,
+ struct ethhdr *eth)
+ {
+ switch (eth->h_proto) {
+ case (htons(ETH_P_IP)):
+ return __br_multicast_querier_exists(br, &br->ip4_querier);
+ #if IS_ENABLED(CONFIG_IPV6)
+ case (htons(ETH_P_IPV6)):
+ return __br_multicast_querier_exists(br, &br->ip6_querier);
+ #endif
+ default:
+ return false;
+ }
}
#else
static inline int br_multicast_rcv(struct net_bridge *br,
{
return 0;
}
- static inline bool br_multicast_querier_exists(struct net_bridge *br)
+ static inline bool br_multicast_querier_exists(struct net_bridge *br,
+ struct ethhdr *eth)
{
return false;
}
break;
}
case IPPROTO_IPIP:
- goto again;
+ proto = htons(ETH_P_IP);
+ goto ip;
+ case IPPROTO_IPV6:
+ proto = htons(ETH_P_IPV6);
+ goto ipv6;
default:
break;
}
if (new_index < 0)
new_index = skb_tx_hash(dev, skb);
- if (queue_index != new_index && sk) {
- struct dst_entry *dst =
- rcu_dereference_check(sk->sk_dst_cache, 1);
-
- if (dst && skb_dst(skb) == dst)
- sk_tx_queue_set(sk, queue_index);
-
- }
+ if (queue_index != new_index && sk &&
+ rcu_access_pointer(sk->sk_dst_cache))
+ sk_tx_queue_set(sk, queue_index);
queue_index = new_index;
}
struct ip_tunnel *tunnel;
const struct iphdr *iph;
- if (iptunnel_pull_header(skb, 0, tpi.proto))
- goto drop;
-
iph = ip_hdr(skb);
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
iph->saddr, iph->daddr, 0);
if (tunnel) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
+ if (iptunnel_pull_header(skb, 0, tpi.proto))
+ goto drop;
return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
}
dev->flags = IFF_NOARP;
dev->iflink = 0;
dev->addr_len = 4;
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->features |= NETIF_F_LLTX;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
static void __net_exit ipip_exit_net(struct net *net)
{
struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
- ip_tunnel_delete_net(itn);
+ ip_tunnel_delete_net(itn, &ipip_link_ops);
}
static struct pernet_operations ipip_net_ops = {
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
- inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP,
+ inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP |
+ (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0);
if (!inet->hdrincl) {
srcp = inet->inet_num;
seq_printf(seq, "%4d: %08X:%04X %08X:%04X"
- " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n",
+ " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d\n",
i, src, srcp, dest, destp, sp->sk_state,
sk_wmem_alloc_get(sp),
sk_rmem_alloc_get(sp),
int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
+int sysctl_tcp_min_tso_segs __read_mostly = 2;
+
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
icsk->icsk_sync_mss = tcp_sync_mss;
- /* Presumed zeroed, in order of appearance:
- * cookie_in_always, cookie_out_never,
- * s_data_constant, s_data_in, s_data_out
- */
sk->sk_sndbuf = sysctl_tcp_wmem[1];
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
mask |= POLLIN | POLLRDNORM;
if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
- if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
+ if (sk_stream_is_writeable(sk)) {
mask |= POLLOUT | POLLWRNORM;
} else { /* send SIGIO later */
set_bit(SOCK_ASYNC_NOSPACE,
* wspace test but before the flags are set,
* IO signal will be lost.
*/
- if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
+ if (sk_stream_is_writeable(sk))
mask |= POLLOUT | POLLWRNORM;
}
} else
xmit_size_goal = mss_now;
if (large_allowed && sk_can_gso(sk)) {
- xmit_size_goal = ((sk->sk_gso_max_size - 1) -
- inet_csk(sk)->icsk_af_ops->net_header_len -
- inet_csk(sk)->icsk_ext_hdr_len -
- tp->tcp_header_len);
+ u32 gso_size, hlen;
+
+ /* Maybe we should/could use sk->sk_prot->max_header here ? */
+ hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
+ inet_csk(sk)->icsk_ext_hdr_len +
+ tp->tcp_header_len;
+
+ /* Goal is to send at least one packet per ms,
+ * not one big TSO packet every 100 ms.
+ * This preserves ACK clocking and is consistent
+ * with tcp_tso_should_defer() heuristic.
+ */
+ gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
+ gso_size = max_t(u32, gso_size,
+ sysctl_tcp_min_tso_segs * mss_now);
- /* TSQ : try to have two TSO segments in flight */
+ xmit_size_goal = min_t(u32, gso_size,
+ sk->sk_gso_max_size - 1 - hlen);
+
+ /* TSQ : try to have at least two segments in flight
+ * (one in NIC TX ring, another in Qdisc)
+ */
xmit_size_goal = min_t(u32, xmit_size_goal,
sysctl_tcp_limit_output_bytes >> 1);
case TCP_THIN_DUPACK:
if (val < 0 || val > 1)
err = -EINVAL;
- else
+ else {
tp->thin_dupack = val;
if (tp->thin_dupack)
tcp_disable_early_retrans(tp);
+ }
break;
case TCP_REPAIR:
else
tp->tsoffset = val - tcp_time_stamp;
break;
+ case TCP_NOTSENT_LOWAT:
+ tp->notsent_lowat = val;
+ sk->sk_write_space(sk);
+ break;
default:
err = -ENOPROTOOPT;
break;
case TCP_TIMESTAMP:
val = tcp_time_stamp + tp->tsoffset;
break;
+ case TCP_NOTSENT_LOWAT:
+ val = tp->notsent_lowat;
+ break;
default:
return -ENOPROTOOPT;
}
}
}
+/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
+ * Note: TCP stack does not yet implement pacing.
+ * FQ packet scheduler can be used to implement cheap but effective
+ * TCP pacing, to smooth the burst on large writes when packets
+ * in flight is significantly lower than cwnd (or rwin)
+ */
+static void tcp_update_pacing_rate(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ u64 rate;
+
+ /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
+ rate = (u64)tp->mss_cache * 2 * (HZ << 3);
+
+ rate *= max(tp->snd_cwnd, tp->packets_out);
+
+ /* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3),
+ * be conservative and assume srtt = 1 (125 us instead of 1.25 ms)
+ * We probably need usec resolution in the future.
+ * Note: This also takes care of possible srtt=0 case,
+ * when tcp_rtt_estimator() was not yet called.
+ */
+ if (tp->srtt > 8 + 2)
+ do_div(rate, tp->srtt);
+
+ sk->sk_pacing_rate = min_t(u64, rate, ~0U);
+}
+
/* Calculate rto without backoff. This is the second half of Van Jacobson's
* routine referred to above.
*/
int reord;
int fack_count;
int flag;
+ s32 rtt; /* RTT measured by SACKing never-retransmitted data */
};
/* Check if skb is fully within the SACK block. In presence of GSO skbs,
static u8 tcp_sacktag_one(struct sock *sk,
struct tcp_sacktag_state *state, u8 sacked,
u32 start_seq, u32 end_seq,
- bool dup_sack, int pcount)
+ int dup_sack, int pcount, u32 xmit_time)
{
struct tcp_sock *tp = tcp_sk(sk);
int fack_count = state->fack_count;
state->reord);
if (!after(end_seq, tp->high_seq))
state->flag |= FLAG_ORIG_SACK_ACKED;
+ /* Pick the earliest sequence sacked for RTT */
+ if (state->rtt < 0)
+ state->rtt = tcp_time_stamp - xmit_time;
}
if (sacked & TCPCB_LOST) {
* tcp_highest_sack_seq() when skb is highest_sack.
*/
tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked,
- start_seq, end_seq, dup_sack, pcount);
+ start_seq, end_seq, dup_sack, pcount,
+ TCP_SKB_CB(skb)->when);
if (skb == tp->lost_skb_hint)
tp->lost_cnt_hint += pcount;
TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(skb)->end_seq,
dup_sack,
- tcp_skb_pcount(skb));
+ tcp_skb_pcount(skb),
+ TCP_SKB_CB(skb)->when);
if (!before(TCP_SKB_CB(skb)->seq,
tcp_highest_sack_seq(tp)))
static int
tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
- u32 prior_snd_una)
+ u32 prior_snd_una, s32 *sack_rtt)
{
struct tcp_sock *tp = tcp_sk(sk);
const unsigned char *ptr = (skb_transport_header(ack_skb) +
state.flag = 0;
state.reord = tp->packets_out;
+ state.rtt = -1;
if (!tp->sacked_out) {
if (WARN_ON(tp->fackets_out))
WARN_ON((int)tp->retrans_out < 0);
WARN_ON((int)tcp_packets_in_flight(tp) < 0);
#endif
+ *sack_rtt = state.rtt;
return state.flag;
}
}
tcp_verify_left_out(tp);
- tp->reordering = min_t(unsigned int, tp->reordering,
- sysctl_tcp_reordering);
+ /* Timeout in disordered state after receiving substantial DUPACKs
+ * suggests that the degree of reordering is over-estimated.
+ */
+ if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
+ tp->sacked_out >= sysctl_tcp_reordering)
+ tp->reordering = min_t(unsigned int, tp->reordering,
+ sysctl_tcp_reordering);
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);
if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
tcp_try_keep_open(sk);
- if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
- tcp_moderate_cwnd(tp);
} else {
tcp_cwnd_reduction(sk, prior_unsacked, 0);
}
tcp_xmit_retransmit_queue(sk);
}
-void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt)
+static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag,
+ s32 seq_rtt, s32 sack_rtt)
{
- tcp_rtt_estimator(sk, seq_rtt);
- tcp_set_rto(sk);
- inet_csk(sk)->icsk_backoff = 0;
-}
-EXPORT_SYMBOL(tcp_valid_rtt_meas);
+ const struct tcp_sock *tp = tcp_sk(sk);
+
+ /* Prefer RTT measured from ACK's timing to TS-ECR. This is because
+ * broken middle-boxes or peers may corrupt TS-ECR fields. But
+ * Karn's algorithm forbids taking RTT if some retransmitted data
+ * is acked (RFC6298).
+ */
+ if (flag & FLAG_RETRANS_DATA_ACKED)
+ seq_rtt = -1;
+
+ if (seq_rtt < 0)
+ seq_rtt = sack_rtt;
-/* Read draft-ietf-tcplw-high-performance before mucking
- * with this code. (Supersedes RFC1323)
- */
-static void tcp_ack_saw_tstamp(struct sock *sk, int flag)
-{
/* RTTM Rule: A TSecr value received in a segment is used to
* update the averaged RTT measurement only if the segment
* acknowledges some new data, i.e., only if it advances the
* left edge of the send window.
- *
* See draft-ietf-tcplw-high-performance-00, section 3.3.
- * 1998/04/10 Andrey V. Savochkin <saw@msu.ru>
- *
- * Changed: reset backoff as soon as we see the first valid sample.
- * If we do not, we get strongly overestimated rto. With timestamps
- * samples are accepted even from very old segments: f.e., when rtt=1
- * increases to 8, we retransmit 5 times and after 8 seconds delayed
- * answer arrives rto becomes 120 seconds! If at least one of segments
- * in window is lost... Voila. --ANK (010210)
*/
- struct tcp_sock *tp = tcp_sk(sk);
-
- tcp_valid_rtt_meas(sk, tcp_time_stamp - tp->rx_opt.rcv_tsecr);
-}
+ if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
+ seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
-static void tcp_ack_no_tstamp(struct sock *sk, u32 seq_rtt, int flag)
-{
- /* We don't have a timestamp. Can only use
- * packets that are not retransmitted to determine
- * rtt estimates. Also, we must not reset the
- * backoff for rto until we get a non-retransmitted
- * packet. This allows us to deal with a situation
- * where the network delay has increased suddenly.
- * I.e. Karn's algorithm. (SIGCOMM '87, p5.)
- */
+ if (seq_rtt < 0)
+ return false;
- if (flag & FLAG_RETRANS_DATA_ACKED)
- return;
+ tcp_rtt_estimator(sk, seq_rtt);
+ tcp_set_rto(sk);
- tcp_valid_rtt_meas(sk, seq_rtt);
+ /* RFC6298: only reset backoff on valid RTT measurement. */
+ inet_csk(sk)->icsk_backoff = 0;
+ return true;
}
-static inline void tcp_ack_update_rtt(struct sock *sk, const int flag,
- const s32 seq_rtt)
+/* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */
+static void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req)
{
- const struct tcp_sock *tp = tcp_sk(sk);
- /* Note that peer MAY send zero echo. In this case it is ignored. (rfc1323) */
- if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
- tcp_ack_saw_tstamp(sk, flag);
- else if (seq_rtt >= 0)
- tcp_ack_no_tstamp(sk, seq_rtt, flag);
+ struct tcp_sock *tp = tcp_sk(sk);
+ s32 seq_rtt = -1;
+
+ if (tp->lsndtime && !tp->total_retrans)
+ seq_rtt = tcp_time_stamp - tp->lsndtime;
+ tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1);
}
static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
* arrived at the other end.
*/
static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
- u32 prior_snd_una)
+ u32 prior_snd_una, s32 sack_rtt)
{
struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
if (sacked & TCPCB_SACKED_RETRANS)
tp->retrans_out -= acked_pcount;
flag |= FLAG_RETRANS_DATA_ACKED;
- ca_seq_rtt = -1;
- seq_rtt = -1;
} else {
ca_seq_rtt = now - scb->when;
last_ackt = skb->tstamp;
if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
flag |= FLAG_SACK_RENEGING;
+ if (tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt) ||
+ (flag & FLAG_ACKED))
+ tcp_rearm_rto(sk);
+
if (flag & FLAG_ACKED) {
const struct tcp_congestion_ops *ca_ops
= inet_csk(sk)->icsk_ca_ops;
tcp_mtup_probe_success(sk);
}
- tcp_ack_update_rtt(sk, flag, seq_rtt);
- tcp_rearm_rto(sk);
-
if (tcp_is_reno(tp)) {
tcp_remove_reno_sacks(sk, pkts_acked);
} else {
inet_csk(sk)->icsk_ca_state != TCP_CA_Open;
}
+/* Decide wheather to run the increase function of congestion control. */
static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
{
- const struct tcp_sock *tp = tcp_sk(sk);
- return (!(flag & FLAG_ECE) || tp->snd_cwnd < tp->snd_ssthresh) &&
- !tcp_in_cwnd_reduction(sk);
+ if (tcp_in_cwnd_reduction(sk))
+ return false;
+
+ /* If reordering is high then always grow cwnd whenever data is
+ * delivered regardless of its ordering. Otherwise stay conservative
+ * and only grow cwnd on in-order delivery in Open state, and retain
+ * cwnd in Disordered state (RFC5681). A stretched ACK with
+ * new SACK or ECE mark may first advance cwnd here and later reduce
+ * cwnd in tcp_fastretrans_alert() based on more states.
+ */
+ if (tcp_sk(sk)->reordering > sysctl_tcp_reordering)
+ return flag & FLAG_FORWARD_PROGRESS;
+
+ return inet_csk(sk)->icsk_ca_state == TCP_CA_Open &&
+ flag & FLAG_DATA_ACKED;
}
/* Check that window update is acceptable.
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
bool is_dupack = false;
- u32 prior_in_flight;
+ u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt;
u32 prior_fackets;
int prior_packets = tp->packets_out;
const int prior_unsacked = tp->packets_out - tp->sacked_out;
int acked = 0; /* Number of packets newly acked */
+ s32 sack_rtt = -1;
/* If the ack is older than previous acks
* then we can probably ignore it.
flag |= tcp_ack_update_window(sk, skb, ack, ack_seq);
if (TCP_SKB_CB(skb)->sacked)
- flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
+ flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
+ &sack_rtt);
if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
flag |= FLAG_ECE;
/* See if we can take anything off of the retransmit queue. */
acked = tp->packets_out;
- flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
+ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt);
acked -= tp->packets_out;
+ /* Advance cwnd if state allows */
+ if (tcp_may_raise_cwnd(sk, flag))
+ tcp_cong_avoid(sk, ack, prior_in_flight);
+
if (tcp_ack_is_dubious(sk, flag)) {
- /* Advance CWND, if state allows this. */
- if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag))
- tcp_cong_avoid(sk, ack, prior_in_flight);
is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
tcp_fastretrans_alert(sk, acked, prior_unsacked,
is_dupack, flag);
- } else {
- if (flag & FLAG_DATA_ACKED)
- tcp_cong_avoid(sk, ack, prior_in_flight);
}
-
if (tp->tlp_high_seq)
tcp_process_tlp_ack(sk, ack, flag);
if (icsk->icsk_pending == ICSK_TIME_RETRANS)
tcp_schedule_loss_probe(sk);
+ if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd)
+ tcp_update_pacing_rate(sk);
return 1;
no_queue:
* If data was DSACKed, see if we can undo a cwnd reduction.
*/
if (TCP_SKB_CB(skb)->sacked) {
- flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
+ flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
+ &sack_rtt);
tcp_fastretrans_alert(sk, acked, prior_unsacked,
is_dupack, flag);
}
++ptr;
tp->rx_opt.rcv_tsval = ntohl(*ptr);
++ptr;
- tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset;
+ if (*ptr)
+ tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset;
+ else
+ tp->rx_opt.rcv_tsecr = 0;
return true;
}
return false;
}
tcp_parse_options(skb, &tp->rx_opt, 1, NULL);
- if (tp->rx_opt.saw_tstamp)
+ if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
return true;
* the rest is checked inline. Fast processing is turned on in
* tcp_data_queue when everything is OK.
*/
-int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
- const struct tcphdr *th, unsigned int len)
+void tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
+ const struct tcphdr *th, unsigned int len)
{
struct tcp_sock *tp = tcp_sk(sk);
tcp_ack(sk, skb, 0);
__kfree_skb(skb);
tcp_data_snd_check(sk);
- return 0;
+ return;
} else { /* Header too small */
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_INERRS);
goto discard;
if (eaten)
kfree_skb_partial(skb, fragstolen);
sk->sk_data_ready(sk, 0);
- return 0;
+ return;
}
}
*/
if (!tcp_validate_incoming(sk, skb, th, 1))
- return 0;
+ return;
step5:
if (tcp_ack(sk, skb, FLAG_SLOWPATH | FLAG_UPDATE_TS_RECENT) < 0)
tcp_data_snd_check(sk);
tcp_ack_snd_check(sk);
- return 0;
+ return;
csum_error:
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_CSUMERRORS);
discard:
__kfree_skb(skb);
- return 0;
}
EXPORT_SYMBOL(tcp_rcv_established);
int saved_clamp = tp->rx_opt.mss_clamp;
tcp_parse_options(skb, &tp->rx_opt, 0, &foc);
- if (tp->rx_opt.saw_tstamp)
+ if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
if (th->ack) {
* so release it.
*/
if (req) {
- tcp_synack_rtt_meas(sk, req);
tp->total_retrans = req->num_retrans;
-
reqsk_fastopen_remove(sk, req, false);
} else {
/* Make sure socket is routed, for correct metrics. */
tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale;
tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
+ tcp_synack_rtt_meas(sk, req);
if (tp->rx_opt.tstamp_ok)
tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
+unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX;
+EXPORT_SYMBOL(sysctl_tcp_notsent_lowat);
+
static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
int push_one, gfp_t gfp);
/* If a full-sized TSO skb can be sent, do it. */
if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
- sk->sk_gso_max_segs * tp->mss_cache))
+ tp->xmit_size_goal_segs * tp->mss_cache))
goto send_now;
/* Middle in queue won't get any more data, full sendable already? */
int tcp_header_size;
int mss;
- skb = alloc_skb(MAX_TCP_HEADER + 15, sk_gfp_atomic(sk, GFP_ATOMIC));
+ skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
if (unlikely(!skb)) {
dst_release(dst);
return NULL;
if (likely(!tp->repair))
tp->rcv_nxt = 0;
+ else
+ tp->rcv_tstamp = tcp_time_stamp;
tp->rcv_wup = tp->rcv_nxt;
tp->copied_seq = tp->rcv_nxt;
#define ACONF_DEBUG 2
#if ACONF_DEBUG >= 3
-#define ADBG(x) printk x
+#define ADBG(fmt, ...) printk(fmt, ##__VA_ARGS__)
#else
-#define ADBG(x)
+#define ADBG(fmt, ...) do { if (0) printk(fmt, ##__VA_ARGS__); } while (0)
#endif
#define INFINITY_LIFE_TIME 0xFFFFFFFF
.accept_redirects = 1,
.autoconf = 1,
.force_mld_version = 0,
+ .mldv1_unsolicited_report_interval = 10 * HZ,
+ .mldv2_unsolicited_report_interval = HZ,
.dad_transmits = 1,
.rtr_solicits = MAX_RTR_SOLICITATIONS,
.rtr_solicit_interval = RTR_SOLICITATION_INTERVAL,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
.accept_dad = 1,
+ .suppress_frag_ndisc = 1,
};
static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
.accept_ra = 1,
.accept_redirects = 1,
.autoconf = 1,
+ .force_mld_version = 0,
+ .mldv1_unsolicited_report_interval = 10 * HZ,
+ .mldv2_unsolicited_report_interval = HZ,
.dad_transmits = 1,
.rtr_solicits = MAX_RTR_SOLICITATIONS,
.rtr_solicit_interval = RTR_SOLICITATION_INTERVAL,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
.accept_dad = 1,
+ .suppress_frag_ndisc = 1,
};
-/* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */
-const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT;
-const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT;
-const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT;
-const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT;
-const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT;
-const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT;
-const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT;
-
/* Check if a valid qdisc is available */
static inline bool addrconf_qdisc_ok(const struct net_device *dev)
{
return -ENOMEM;
}
-static void snmp6_free_dev(struct inet6_dev *idev)
-{
- kfree(idev->stats.icmpv6msgdev);
- kfree(idev->stats.icmpv6dev);
- snmp_mib_free((void __percpu **)idev->stats.ipv6);
-}
-
-/* Nobody refers to this device, we may destroy it. */
-
-void in6_dev_finish_destroy(struct inet6_dev *idev)
-{
- struct net_device *dev = idev->dev;
-
- WARN_ON(!list_empty(&idev->addr_list));
- WARN_ON(idev->mc_list != NULL);
- WARN_ON(timer_pending(&idev->rs_timer));
-
-#ifdef NET_REFCNT_DEBUG
- pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL");
-#endif
- dev_put(dev);
- if (!idev->dead) {
- pr_warn("Freeing alive inet6 device %p\n", idev);
- return;
- }
- snmp6_free_dev(idev);
- kfree_rcu(idev, rcu);
-}
-EXPORT_SYMBOL(in6_dev_finish_destroy);
-
static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
{
struct inet6_dev *ndev;
dev_hold(dev);
if (snmp6_alloc_dev(ndev) < 0) {
- ADBG((KERN_WARNING
+ ADBG(KERN_WARNING
"%s: cannot allocate memory for statistics; dev=%s.\n",
- __func__, dev->name));
+ __func__, dev->name);
neigh_parms_release(&nd_tbl, ndev->nd_parms);
dev_put(dev);
kfree(ndev);
}
if (snmp6_register_dev(ndev) < 0) {
- ADBG((KERN_WARNING
+ ADBG(KERN_WARNING
"%s: cannot create /proc/net/dev_snmp6/%s\n",
- __func__, dev->name));
+ __func__, dev->name);
neigh_parms_release(&nd_tbl, ndev->nd_parms);
ndev->dead = 1;
in6_dev_finish_destroy(ndev);
/* Ignore adding duplicate addresses on an interface */
if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) {
- ADBG(("ipv6_add_addr: already assigned\n"));
+ ADBG("ipv6_add_addr: already assigned\n");
err = -EEXIST;
goto out;
}
ifa = kzalloc(sizeof(struct inet6_ifaddr), GFP_ATOMIC);
if (ifa == NULL) {
- ADBG(("ipv6_add_addr: malloc failed\n"));
+ ADBG("ipv6_add_addr: malloc failed\n");
err = -ENOBUFS;
goto out;
}
unsigned long regen_advance;
int tmp_plen;
int ret = 0;
- int max_addresses;
u32 addr_flags;
unsigned long now = jiffies;
idev->cnf.temp_prefered_lft + age -
idev->cnf.max_desync_factor);
tmp_plen = ifp->prefix_len;
- max_addresses = idev->cnf.max_addresses;
tmp_tstamp = ifp->tstamp;
spin_unlock_bh(&ifp->lock);
return __ipv6_isatap_ifid(eui, *(__be32 *)dev->dev_addr);
}
+static int addrconf_ifid_ip6tnl(u8 *eui, struct net_device *dev)
+{
+ memcpy(eui, dev->perm_addr, 3);
+ memcpy(eui + 5, dev->perm_addr + 3, 3);
+ eui[3] = 0xFF;
+ eui[4] = 0xFE;
+ eui[0] ^= 2;
+ return 0;
+}
+
static int ipv6_generate_eui64(u8 *eui, struct net_device *dev)
{
switch (dev->type) {
return addrconf_ifid_eui64(eui, dev);
case ARPHRD_IEEE1394:
return addrconf_ifid_ieee1394(eui, dev);
+ case ARPHRD_TUNNEL6:
+ return addrconf_ifid_ip6tnl(eui, dev);
}
return -1;
}
pinfo = (struct prefix_info *) opt;
if (len < sizeof(struct prefix_info)) {
- ADBG(("addrconf: prefix option too short\n"));
+ ADBG("addrconf: prefix option too short\n");
return;
}
(dev->type != ARPHRD_ARCNET) &&
(dev->type != ARPHRD_INFINIBAND) &&
(dev->type != ARPHRD_IEEE802154) &&
- (dev->type != ARPHRD_IEEE1394)) {
+ (dev->type != ARPHRD_IEEE1394) &&
+ (dev->type != ARPHRD_TUNNEL6)) {
/* Alas, we support only Ethernet autoconfiguration. */
return;
}
return -1;
}
-static void ip6_tnl_add_linklocal(struct inet6_dev *idev)
-{
- struct net_device *link_dev;
- struct net *net = dev_net(idev->dev);
-
- /* first try to inherit the link-local address from the link device */
- if (idev->dev->iflink &&
- (link_dev = __dev_get_by_index(net, idev->dev->iflink))) {
- if (!ipv6_inherit_linklocal(idev, link_dev))
- return;
- }
- /* then try to inherit it from any device */
- for_each_netdev(net, link_dev) {
- if (!ipv6_inherit_linklocal(idev, link_dev))
- return;
- }
- pr_debug("init ip6-ip6: add_linklocal failed\n");
-}
-
-/*
- * Autoconfigure tunnel with a link-local address so routing protocols,
- * DHCPv6, MLD etc. can be run over the virtual link
- */
-
-static void addrconf_ip6_tnl_config(struct net_device *dev)
-{
- struct inet6_dev *idev;
-
- ASSERT_RTNL();
-
- idev = addrconf_add_dev(dev);
- if (IS_ERR(idev)) {
- pr_debug("init ip6-ip6: add_dev failed\n");
- return;
- }
- ip6_tnl_add_linklocal(idev);
-}
-
static int addrconf_notify(struct notifier_block *this, unsigned long event,
void *ptr)
{
addrconf_gre_config(dev);
break;
#endif
- case ARPHRD_TUNNEL6:
- addrconf_ip6_tnl_config(dev);
- break;
case ARPHRD_LOOPBACK:
init_loopback(dev);
break;
static void addrconf_rs_timer(unsigned long data)
{
struct inet6_dev *idev = (struct inet6_dev *)data;
+ struct net_device *dev = idev->dev;
struct in6_addr lladdr;
write_lock(&idev->lock);
goto out;
if (idev->rs_probes++ < idev->cnf.rtr_solicits) {
- if (!__ipv6_get_lladdr(idev, &lladdr, IFA_F_TENTATIVE))
- ndisc_send_rs(idev->dev, &lladdr,
+ write_unlock(&idev->lock);
+ if (!ipv6_get_lladdr(dev, &lladdr, IFA_F_TENTATIVE))
+ ndisc_send_rs(dev, &lladdr,
&in6addr_linklocal_allrouters);
else
- goto out;
+ goto put;
+ write_lock(&idev->lock);
/* The wait after the last probe can be shorter */
addrconf_mod_rs_timer(idev, (idev->rs_probes ==
idev->cnf.rtr_solicits) ?
out:
write_unlock(&idev->lock);
+put:
in6_dev_put(idev);
}
if (time_before(next_sched, jiffies + ADDRCONF_TIMER_FUZZ_MAX))
next_sched = jiffies + ADDRCONF_TIMER_FUZZ_MAX;
- ADBG((KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n",
- now, next, next_sec, next_sched));
+ ADBG(KERN_DEBUG "now = %lu, schedule = %lu, rounded schedule = %lu => %lu\n",
+ now, next, next_sec, next_sched);
addr_chk_timer.expires = next_sched;
add_timer(&addr_chk_timer);
array[DEVCONF_RTR_SOLICIT_DELAY] =
jiffies_to_msecs(cnf->rtr_solicit_delay);
array[DEVCONF_FORCE_MLD_VERSION] = cnf->force_mld_version;
+ array[DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL] =
+ jiffies_to_msecs(cnf->mldv1_unsolicited_report_interval);
+ array[DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL] =
+ jiffies_to_msecs(cnf->mldv2_unsolicited_report_interval);
#ifdef CONFIG_IPV6_PRIVACY
array[DEVCONF_USE_TEMPADDR] = cnf->use_tempaddr;
array[DEVCONF_TEMP_VALID_LFT] = cnf->temp_valid_lft;
array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad;
array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao;
array[DEVCONF_NDISC_NOTIFY] = cnf->ndisc_notify;
+ array[DEVCONF_SUPPRESS_FRAG_NDISC] = cnf->suppress_frag_ndisc;
}
static inline size_t inet6_ifla6_size(void)
break;
}
atomic_inc(&net->ipv6.dev_addr_genid);
+ rt_genid_bump_ipv6(net);
}
static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "mldv1_unsolicited_report_interval",
+ .data =
+ &ipv6_devconf.mldv1_unsolicited_report_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_ms_jiffies,
+ },
+ {
+ .procname = "mldv2_unsolicited_report_interval",
+ .data =
+ &ipv6_devconf.mldv2_unsolicited_report_interval,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_ms_jiffies,
+ },
#ifdef CONFIG_IPV6_PRIVACY
{
.procname = "use_tempaddr",
.mode = 0644,
.proc_handler = proc_dointvec
},
+ {
+ .procname = "suppress_frag_ndisc",
+ .data = &ipv6_devconf.suppress_frag_ndisc,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
{
/* sentinel */
}
if (type == ICMPV6_PKT_TOOBIG)
ip6_update_pmtu(skb, net, info, 0, 0);
else if (type == NDISC_REDIRECT)
- ip6_redirect(skb, net, 0, 0);
+ ip6_redirect(skb, net, skb->dev->ifindex, 0);
if (!(type & ICMPV6_INFOMSG_MASK))
if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
.err = ECONNREFUSED,
.fatal = 1,
},
+ { /* POLICY_FAIL */
+ .err = EACCES,
+ .fatal = 1,
+ },
+ { /* REJECT_ROUTE */
+ .err = EACCES,
+ .fatal = 1,
+ },
};
int icmpv6_err_convert(u8 type, u8 code, int *err)
switch (type) {
case ICMPV6_DEST_UNREACH:
fatal = 1;
- if (code <= ICMPV6_PORT_UNREACH) {
+ if (code < ARRAY_SIZE(tab_unreach)) {
*err = tab_unreach[code].err;
fatal = tab_unreach[code].fatal;
}
dev->rtnl_link_ops = &ip6gre_link_ops;
nt->dev = dev;
+ nt->net = dev_net(dev);
ip6gre_tnl_link_config(nt, 1);
if (register_netdevice(dev) < 0)
goto drop;
}
- secpath_reset(skb);
-
skb->protocol = gre_proto;
/* WCCP version 1 and 2 protocol decoding.
* - Change protocol to IP
skb->mac_header = skb->network_header;
__pskb_pull(skb, offset);
skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
- skb->pkt_type = PACKET_HOST;
if (((flags&GRE_CSUM) && csum) ||
(!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
}
- __skb_tunnel_rx(skb, tunnel->dev);
+ __skb_tunnel_rx(skb, tunnel->dev, tunnel->net);
skb_reset_network_header(skb);
tunnel->err_count = 0;
}
+ skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
+
max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + dst->header_len;
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
skb = new_skb;
}
- skb_dst_drop(skb);
-
if (fl6->flowi6_mark) {
skb_dst_set(skb, dst);
ndst = NULL;
ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
}
+ if (likely(!skb->encapsulation)) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
+ }
+
skb_push(skb, gre_hlen);
skb_reset_network_header(skb);
skb_set_transport_header(skb, sizeof(*ipv6h));
tunnel = netdev_priv(dev);
tunnel->dev = dev;
+ tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr));
struct ip6_tnl *tunnel = netdev_priv(dev);
tunnel->dev = dev;
+ tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
tunnel->hlen = sizeof(struct ipv6hdr) + 4;
tunnel = netdev_priv(dev);
tunnel->dev = dev;
+ tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
ip6gre_tnl_link_config(tunnel, 1);
eth_hw_addr_random(dev);
nt->dev = dev;
+ nt->net = dev_net(dev);
ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
/* Can use a lockless transmit, unless we generate output sequences */
#include <net/checksum.h>
#include <linux/mroute6.h>
-int __ip6_local_out(struct sk_buff *skb)
-{
- int len;
-
- len = skb->len - sizeof(struct ipv6hdr);
- if (len > IPV6_MAXPLEN)
- len = 0;
- ipv6_hdr(skb)->payload_len = htons(len);
-
- return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
- skb_dst(skb)->dev, dst_output);
-}
-
-int ip6_local_out(struct sk_buff *skb)
-{
- int err;
-
- err = __ip6_local_out(skb);
- if (likely(err == 1))
- err = dst_output(skb);
-
- return err;
-}
-EXPORT_SYMBOL_GPL(ip6_local_out);
-
static int ip6_finish_output2(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
hdr->saddr = fl6->saddr;
hdr->daddr = *first_hop;
+ skb->protocol = htons(ETH_P_IPV6);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
/* initialize protocol header pointer */
skb->transport_header = skb->network_header + fragheaderlen;
+ skb->protocol = htons(ETH_P_IPV6);
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
}
/*
* Fill in the control structures
*/
+ skb->protocol = htons(ETH_P_IPV6);
skb->ip_summed = CHECKSUM_NONE;
skb->csum = 0;
/* reserve for fragmentation and ipsec header */
#include <linux/netfilter_ipv6.h>
#include <linux/slab.h>
#include <linux/hash.h>
+#include <linux/etherdevice.h>
#include <asm/uaccess.h>
#include <linux/atomic.h>
t = netdev_priv(dev);
t->parms = *p;
+ t->net = dev_net(dev);
err = ip6_tnl_create2(dev);
if (err < 0)
goto failed_free;
ip6_tnl_dev_uninit(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
- struct net *net = dev_net(dev);
+ struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
if (dev == ip6n->fb_tnl_dev)
{
struct __ip6_tnl_parm *p = &t->parms;
int ret = 0;
- struct net *net = dev_net(t->dev);
+ struct net *net = t->net;
if ((p->flags & IP6_TNL_F_CAP_RCV) ||
((p->flags & IP6_TNL_F_CAP_PER_PACKET) &&
rcu_read_unlock();
goto discard;
}
- secpath_reset(skb);
skb->mac_header = skb->network_header;
skb_reset_network_header(skb);
skb->protocol = htons(protocol);
- skb->pkt_type = PACKET_HOST;
memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
- __skb_tunnel_rx(skb, t->dev);
+ __skb_tunnel_rx(skb, t->dev, t->net);
err = dscp_ecn_decapsulate(t, ipv6h, skb);
if (unlikely(err)) {
{
struct __ip6_tnl_parm *p = &t->parms;
int ret = 0;
- struct net *net = dev_net(t->dev);
+ struct net *net = t->net;
if (p->flags & IP6_TNL_F_CAP_XMIT) {
struct net_device *ldev = NULL;
int encap_limit,
__u32 *pmtu)
{
- struct net *net = dev_net(dev);
struct ip6_tnl *t = netdev_priv(dev);
+ struct net *net = t->net;
struct net_device_stats *stats = &t->dev->stats;
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct ipv6_tel_txoption opt;
goto tx_err_dst_release;
}
+ skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
+
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
consume_skb(skb);
skb = new_skb;
}
- skb_dst_drop(skb);
if (fl6->flowi6_mark) {
skb_dst_set(skb, dst);
ndst = NULL;
init_tel_txopt(&opt, encap_limit);
ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
}
+
+ if (likely(!skb->encapsulation)) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
+ }
+
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
int strict = (ipv6_addr_type(&p->raddr) &
(IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
- struct rt6_info *rt = rt6_lookup(dev_net(dev),
+ struct rt6_info *rt = rt6_lookup(t->net,
&p->raddr, &p->laddr,
p->link, strict);
static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
{
- struct net *net = dev_net(t->dev);
+ struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
int err;
dev->mtu-=8;
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+ /* This perm addr will be used as interface identifier by IPv6 */
+ dev->addr_assign_type = NET_ADDR_RANDOM;
+ eth_random_addr(dev->perm_addr);
}
struct ip6_tnl *t = netdev_priv(dev);
t->dev = dev;
+ t->net = dev_net(dev);
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
- struct ip6_tnl *t;
+ struct ip6_tnl *t = netdev_priv(dev);
struct __ip6_tnl_parm p;
- struct net *net = dev_net(dev);
+ struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
if (dev == ip6n->fb_tnl_dev)
static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
{
+ struct net *net = dev_net(ip6n->fb_tnl_dev);
+ struct net_device *dev, *aux;
int h;
struct ip6_tnl *t;
LIST_HEAD(list);
+ for_each_netdev_safe(net, dev, aux)
+ if (dev->rtnl_link_ops == &ip6_link_ops)
+ unregister_netdevice_queue(dev, &list);
+
for (h = 0; h < HASH_SIZE; h++) {
t = rtnl_dereference(ip6n->tnls_r_l[h]);
while (t != NULL) {
- unregister_netdevice_queue(t->dev, &list);
+ /* If dev is in the same netns, it has already
+ * been added to the list by the previous loop.
+ */
+ if (!net_eq(dev_net(t->dev), net))
+ unregister_netdevice_queue(t->dev, &list);
t = rtnl_dereference(t->next);
}
}
if (!ip6n->fb_tnl_dev)
goto err_alloc_dev;
dev_net_set(ip6n->fb_tnl_dev, net);
+ /* FB netdevice is special: we have one, and only one per netns.
+ * Allowing to move it to another netns is clearly unsafe.
+ */
+ ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL;
err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
if (err < 0)
int tlen = dev->needed_tailroom;
struct sock *sk = dev_net(dev)->ipv6.ndisc_sk;
struct sk_buff *skb;
- int err;
- skb = sock_alloc_send_skb(sk,
- hlen + sizeof(struct ipv6hdr) + len + tlen,
- 1, &err);
+ skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC);
if (!skb) {
- ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb, err=%d\n",
- __func__, err);
+ ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n",
+ __func__);
return NULL;
}
skb_reserve(skb, hlen + sizeof(struct ipv6hdr));
skb_reset_transport_header(skb);
+ /* Manually assign socket ownership as we avoid calling
+ * sock_alloc_send_pskb() to bypass wmem buffer limits
+ */
+ skb_set_owner_w(skb, sk);
+
return skb;
}
type = icmp6h->icmp6_type;
if (!dst) {
- struct sock *sk = net->ipv6.ndisc_sk;
struct flowi6 fl6;
icmpv6_flow_init(sk, &fl6, type, saddr, daddr, skb->dev->ifindex);
rcu_read_unlock();
}
-static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
- const struct in6_addr *daddr,
- const struct in6_addr *solicited_addr,
- bool router, bool solicited, bool override, bool inc_opt)
+void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
+ const struct in6_addr *daddr,
+ const struct in6_addr *solicited_addr,
+ bool router, bool solicited, bool override, bool inc_opt)
{
struct sk_buff *skb;
struct in6_addr tmpaddr;
}
ndisc_send_ns(dev, neigh, target, target, saddr);
} else if ((probes -= neigh->parms->app_probes) < 0) {
-#ifdef CONFIG_ARPD
neigh_app_ns(neigh);
-#endif
} else {
addrconf_addr_solict_mult(target, &mcaddr);
ndisc_send_ns(dev, NULL, target, &mcaddr, saddr);
return;
if (!ndopts.nd_opts_rh) {
- ip6_redirect_no_header(skb, dev_net(skb->dev), 0, 0);
+ ip6_redirect_no_header(skb, dev_net(skb->dev),
+ skb->dev->ifindex, 0);
return;
}
kfree_skb(skb);
}
+static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb)
+{
+ struct inet6_dev *idev = __in6_dev_get(skb->dev);
+
+ if (!idev)
+ return true;
+ if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED &&
+ idev->cnf.suppress_frag_ndisc) {
+ net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n");
+ return true;
+ }
+ return false;
+}
+
int ndisc_rcv(struct sk_buff *skb)
{
struct nd_msg *msg;
+ if (ndisc_suppress_frag_ndisc(skb))
+ return 0;
+
if (skb_linearize(skb))
return 0;
#include <linux/seq_file.h>
#include <linux/export.h>
+#define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */
+
static struct raw_hashinfo raw_v6_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock),
};
*/
static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb)
{
- struct icmp6hdr *_hdr;
+ struct icmp6hdr _hdr;
const struct icmp6hdr *hdr;
+ /* We require only the four bytes of the ICMPv6 header, not any
+ * additional bytes of message body in "struct icmp6hdr".
+ */
hdr = skb_header_pointer(skb, skb_transport_offset(skb),
- sizeof(_hdr), &_hdr);
+ ICMPV6_HDRLEN, &_hdr);
if (hdr) {
const __u32 *data = &raw6_sk(sk)->filter.data[0];
unsigned int type = hdr->icmp6_type;
goto error;
skb_reserve(skb, hlen);
+ skb->protocol = htons(ETH_P_IPV6);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
skb_dst_set(skb, &rt->dst);
tunnel->parms.iph.protocol != 0)
goto out;
- secpath_reset(skb);
skb->mac_header = skb->network_header;
skb_reset_network_header(skb);
IPCB(skb)->flags = 0;
skb->protocol = htons(ETH_P_IPV6);
- skb->pkt_type = PACKET_HOST;
if (tunnel->dev->priv_flags & IFF_ISATAP) {
if (!isatap_chksrc(skb, iph, tunnel)) {
}
}
- __skb_tunnel_rx(skb, tunnel->dev);
+ __skb_tunnel_rx(skb, tunnel->dev, tunnel->net);
err = IP_ECN_decapsulate(iph, skb);
if (unlikely(err)) {
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
- if (tunnel->net != dev_net(tunnel->dev))
- skb_scrub_packet(skb);
netif_rx(skb);
return 0;
const struct iphdr *iph;
struct ip_tunnel *tunnel;
- if (iptunnel_pull_header(skb, 0, tpi.proto))
- goto drop;
-
iph = ip_hdr(skb);
-
tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
iph->saddr, iph->daddr);
if (tunnel != NULL) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
+ if (iptunnel_pull_header(skb, 0, tpi.proto))
+ goto drop;
return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error);
}
tunnel->err_count = 0;
}
- if (tunnel->net != dev_net(dev))
- skb_scrub_packet(skb);
-
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
ttl = iph6->hop_limit;
tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
- err = iptunnel_xmit(dev_net(dev), rt, skb, fl4.saddr, fl4.daddr,
- IPPROTO_IPV6, tos, ttl, df);
+ if (likely(!skb->encapsulation)) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
+ }
+
+ err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, IPPROTO_IPV6, tos,
+ ttl, df, !net_eq(tunnel->net, dev_net(dev)));
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
return NETDEV_TX_OK;
/* If dev is in the same netns, it has already
* been added to the list by the previous loop.
*/
- if (dev_net(t->dev) != net)
+ if (!net_eq(dev_net(t->dev), net))
unregister_netdevice_queue(t->dev,
head);
t = rtnl_dereference(t->next);
if (!ipv6_unicast_destination(skb))
goto drop;
- if (inet_csk_reqsk_queue_is_full(sk) && !isn) {
+ if ((sysctl_tcp_syncookies == 2 ||
+ inet_csk_reqsk_queue_is_full(sk)) && !isn) {
want_cookie = tcp_syn_flood_action(sk, skb, "TCPv6");
if (!want_cookie)
goto drop;
newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
tcp_initialize_rcv_mss(newsk);
- tcp_synack_rtt_meas(newsk, req);
- newtp->total_retrans = req->num_retrans;
newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
}
}
- if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len))
- goto reset;
+ tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len);
if (opt_skb)
goto ipv6_pktoptions;
return 0;
if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim)
np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit;
if (np->rxopt.bits.rxtclass)
- np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(skb));
+ np->rcv_tclass = ipv6_get_dsfield(ipv6_hdr(opt_skb));
if (ipv6_opt_accepted(sk, opt_skb)) {
skb_set_owner_r(opt_skb, sk);
opt_skb = xchg(&np->pktoptions, opt_skb);
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
- "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK\n",
+ "%02X %08X:%08X %02X:%08lX %08X %5u %8d %d %d %pK\n",
i,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3],
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
- "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %lu %lu %u %u %d\n",
+ "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %lu %lu %u %u %d\n",
i,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3], srcp,
.unhash = inet_unhash,
.get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
+ .stream_memory_free = tcp_stream_memory_free,
.sockets_allocated = &tcp_sockets_allocated,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
{
BUG_ON(!policy->walk.dead);
- if (del_timer(&policy->timer))
+ if (del_timer(&policy->timer) || del_timer(&policy->polq.hold_timer))
BUG();
security_xfrm_policy_free(policy->security);
{
struct sk_buff *skb;
- while ((skb = skb_dequeue(list)) != NULL) {
- dev_put(skb->dev);
+ while ((skb = skb_dequeue(list)) != NULL)
kfree_skb(skb);
- }
}
/* Rule must be locked. Release descentant resources, announce
xfrm_pol_hold(policy);
net->xfrm.policy_count[dir]++;
atomic_inc(&flow_cache_genid);
- rt_genid_bump(net);
+
+ /* After previous checking, family can either be AF_INET or AF_INET6 */
+ if (policy->family == AF_INET)
+ rt_genid_bump_ipv4(net);
+ else
+ rt_genid_bump_ipv6(net);
+
if (delpol) {
xfrm_policy_requeue(delpol, policy);
__xfrm_policy_unlink(delpol, dir);
struct sk_buff *skb;
struct sock *sk;
struct dst_entry *dst;
- struct net_device *dev;
struct xfrm_policy *pol = (struct xfrm_policy *)arg;
struct xfrm_policy_queue *pq = &pol->polq;
struct flowi fl;
dst = xfrm_lookup(xp_net(pol), skb_dst(skb)->path,
&fl, skb->sk, 0);
if (IS_ERR(dst)) {
- dev_put(skb->dev);
kfree_skb(skb);
continue;
}
skb_dst_drop(skb);
skb_dst_set(skb, dst);
- dev = skb->dev;
err = dst_output(skb);
- dev_put(dev);
}
return;
}
skb_dst_force(skb);
- dev_hold(skb->dev);
spin_lock_bh(&pq->hold_queue.lock);
* have the xfrm_state's. We need to wait for KM to
* negotiate new SA's or bail out with error.*/
if (net->xfrm.sysctl_larval_drop) {
- /* EREMOTE tells the caller to generate
- * a one-shot blackhole route. */
dst_release(dst);
xfrm_pols_put(pols, drop_pols);
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES);
static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
- static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family);
- static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo);
-
static inline unsigned int xfrm_dst_hash(struct net *net,
const xfrm_address_t *daddr,
const xfrm_address_t *saddr,
INIT_HLIST_NODE(&x->bydst);
INIT_HLIST_NODE(&x->bysrc);
INIT_HLIST_NODE(&x->byspi);
- tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler, CLOCK_REALTIME, HRTIMER_MODE_ABS);
+ tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler,
+ CLOCK_BOOTTIME, HRTIMER_MODE_ABS);
setup_timer(&x->rtimer, xfrm_replay_timer_handler,
(unsigned long)x);
x->curlft.add_time = get_seconds();
EXPORT_SYMBOL(xfrm_state_insert);
/* xfrm_state_lock is held */
-static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m,
+static struct xfrm_state *__find_acq_core(struct net *net,
+ const struct xfrm_mark *m,
unsigned short family, u8 mode,
u32 reqid, u8 proto,
const xfrm_address_t *daddr,
- const xfrm_address_t *saddr, int create)
+ const xfrm_address_t *saddr,
+ int create)
{
unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family);
struct xfrm_state *x;
EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
struct xfrm_state *
-xfrm_find_acq(struct net *net, struct xfrm_mark *mark, u8 mode, u32 reqid, u8 proto,
- const xfrm_address_t *daddr, const xfrm_address_t *saddr,
- int create, unsigned short family)
+xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid,
+ u8 proto, const xfrm_address_t *daddr,
+ const xfrm_address_t *saddr, int create, unsigned short family)
{
struct xfrm_state *x;
}
EXPORT_SYMBOL(xfrm_state_unregister_afinfo);
- static struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
+ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family)
{
struct xfrm_state_afinfo *afinfo;
if (unlikely(family >= NPROTO))
return afinfo;
}
- static void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo)
+ void xfrm_state_put_afinfo(struct xfrm_state_afinfo *afinfo)
{
rcu_read_unlock();
}
projects / linux.git / commitdiff