From 6778948f9de86c3cfaf36725a7c87dcff9ba247f Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 08:20:59 +0000
Subject: [PATCH] kernel_5.10 no rt
---
kernel/drivers/net/ethernet/intel/i40e/i40e_main.c | 2716 ++++++++++++++++++++++++++++++++++++++++++++--------------
1 files changed, 2,031 insertions(+), 685 deletions(-)
diff --git a/kernel/drivers/net/ethernet/intel/i40e/i40e_main.c b/kernel/drivers/net/ethernet/intel/i40e/i40e_main.c
index 21ea0cd..2c60d2a 100644
--- a/kernel/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/kernel/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -5,11 +5,14 @@
#include <linux/of_net.h>
#include <linux/pci.h>
#include <linux/bpf.h>
+#include <generated/utsrelease.h>
/* Local includes */
#include "i40e.h"
#include "i40e_diag.h"
+#include "i40e_xsk.h"
#include <net/udp_tunnel.h>
+#include <net/xdp_sock_drv.h>
/* All i40e tracepoints are defined by the include below, which
* must be included exactly once across the whole kernel with
* CREATE_TRACE_POINTS defined
@@ -21,23 +24,14 @@
static const char i40e_driver_string[] =
"Intel(R) Ethernet Connection XL710 Network Driver";
-#define DRV_KERN "-k"
-
-#define DRV_VERSION_MAJOR 2
-#define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 2
-#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
- __stringify(DRV_VERSION_MINOR) "." \
- __stringify(DRV_VERSION_BUILD) DRV_KERN
-const char i40e_driver_version_str[] = DRV_VERSION;
-static const char i40e_copyright[] = "Copyright (c) 2013 - 2014 Intel Corporation.";
+static const char i40e_copyright[] = "Copyright (c) 2013 - 2019 Intel Corporation.";
/* a bit of forward declarations */
static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi);
static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired);
static int i40e_add_vsi(struct i40e_vsi *vsi);
static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi);
-static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit);
+static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acquired);
static int i40e_setup_misc_vector(struct i40e_pf *pf);
static void i40e_determine_queue_usage(struct i40e_pf *pf);
static int i40e_setup_pf_filter_control(struct i40e_pf *pf);
@@ -46,11 +40,15 @@
bool lock_acquired);
static int i40e_reset(struct i40e_pf *pf);
static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired);
+static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf);
+static int i40e_restore_interrupt_scheme(struct i40e_pf *pf);
+static bool i40e_check_recovery_mode(struct i40e_pf *pf);
+static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw);
static void i40e_fdir_sb_setup(struct i40e_pf *pf);
static int i40e_veb_get_bw_info(struct i40e_veb *veb);
static int i40e_get_capabilities(struct i40e_pf *pf,
enum i40e_admin_queue_opc list_type);
-
+static bool i40e_is_total_port_shutdown_enabled(struct i40e_pf *pf);
/* i40e_pci_tbl - PCI Device ID Table
*
@@ -69,6 +67,9 @@
{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_C), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_BC), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_SFP), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_B), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X722), 0},
@@ -77,6 +78,8 @@
{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_I_X722), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_20G_KR2_A), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_X710_N3000), 0},
+ {PCI_VDEVICE(INTEL, I40E_DEV_ID_XXV710_N3000), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_B), 0},
{PCI_VDEVICE(INTEL, I40E_DEV_ID_25G_SFP28), 0},
/* required last entry */
@@ -91,8 +94,7 @@
MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>");
MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver");
-MODULE_LICENSE("GPL");
-MODULE_VERSION(DRV_VERSION);
+MODULE_LICENSE("GPL v2");
static struct workqueue_struct *i40e_wq;
@@ -127,8 +129,8 @@
struct i40e_pf *pf = (struct i40e_pf *)hw->back;
mem->size = ALIGN(size, alignment);
- mem->va = dma_zalloc_coherent(&pf->pdev->dev, mem->size,
- &mem->pa, GFP_KERNEL);
+ mem->va = dma_alloc_coherent(&pf->pdev->dev, mem->size, &mem->pa,
+ GFP_KERNEL);
if (!mem->va)
return -ENOMEM;
@@ -302,56 +304,39 @@
**/
void i40e_service_event_schedule(struct i40e_pf *pf)
{
- if (!test_bit(__I40E_DOWN, pf->state) &&
- !test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+ if ((!test_bit(__I40E_DOWN, pf->state) &&
+ !test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) ||
+ test_bit(__I40E_RECOVERY_MODE, pf->state))
queue_work(i40e_wq, &pf->service_task);
}
/**
* i40e_tx_timeout - Respond to a Tx Hang
* @netdev: network interface device structure
+ * @txqueue: queue number timing out
*
* If any port has noticed a Tx timeout, it is likely that the whole
* device is munged, not just the one netdev port, so go for the full
* reset.
**/
-static void i40e_tx_timeout(struct net_device *netdev)
+static void i40e_tx_timeout(struct net_device *netdev, unsigned int txqueue)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
struct i40e_ring *tx_ring = NULL;
- unsigned int i, hung_queue = 0;
+ unsigned int i;
u32 head, val;
pf->tx_timeout_count++;
- /* find the stopped queue the same way the stack does */
- for (i = 0; i < netdev->num_tx_queues; i++) {
- struct netdev_queue *q;
- unsigned long trans_start;
-
- q = netdev_get_tx_queue(netdev, i);
- trans_start = q->trans_start;
- if (netif_xmit_stopped(q) &&
- time_after(jiffies,
- (trans_start + netdev->watchdog_timeo))) {
- hung_queue = i;
- break;
- }
- }
-
- if (i == netdev->num_tx_queues) {
- netdev_info(netdev, "tx_timeout: no netdev hung queue found\n");
- } else {
- /* now that we have an index, find the tx_ring struct */
- for (i = 0; i < vsi->num_queue_pairs; i++) {
- if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) {
- if (hung_queue ==
- vsi->tx_rings[i]->queue_index) {
- tx_ring = vsi->tx_rings[i];
- break;
- }
+ /* with txqueue index, find the tx_ring struct */
+ for (i = 0; i < vsi->num_queue_pairs; i++) {
+ if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) {
+ if (txqueue ==
+ vsi->tx_rings[i]->queue_index) {
+ tx_ring = vsi->tx_rings[i];
+ break;
}
}
}
@@ -377,14 +362,14 @@
val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0);
netdev_info(netdev, "tx_timeout: VSI_seid: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n",
- vsi->seid, hung_queue, tx_ring->next_to_clean,
+ vsi->seid, txqueue, tx_ring->next_to_clean,
head, tx_ring->next_to_use,
readl(tx_ring->tail), val);
}
pf->tx_timeout_last_recovery = jiffies;
- netdev_info(netdev, "tx_timeout recovery level %d, hung_queue %d\n",
- pf->tx_timeout_recovery_level, hung_queue);
+ netdev_info(netdev, "tx_timeout recovery level %d, txqueue %d\n",
+ pf->tx_timeout_recovery_level, txqueue);
switch (pf->tx_timeout_recovery_level) {
case 1:
@@ -397,7 +382,9 @@
set_bit(__I40E_GLOBAL_RESET_REQUESTED, pf->state);
break;
default:
- netdev_err(netdev, "tx_timeout recovery unsuccessful\n");
+ netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in non-recoverable state.\n");
+ set_bit(__I40E_DOWN_REQUESTED, pf->state);
+ set_bit(__I40E_VSI_DOWN_REQUESTED, vsi->state);
break;
}
@@ -553,10 +540,55 @@
sizeof(pf->veb[i]->stats));
memset(&pf->veb[i]->stats_offsets, 0,
sizeof(pf->veb[i]->stats_offsets));
+ memset(&pf->veb[i]->tc_stats, 0,
+ sizeof(pf->veb[i]->tc_stats));
+ memset(&pf->veb[i]->tc_stats_offsets, 0,
+ sizeof(pf->veb[i]->tc_stats_offsets));
pf->veb[i]->stat_offsets_loaded = false;
}
}
pf->hw_csum_rx_error = 0;
+}
+
+/**
+ * i40e_compute_pci_to_hw_id - compute index form PCI function.
+ * @vsi: ptr to the VSI to read from.
+ * @hw: ptr to the hardware info.
+ **/
+static u32 i40e_compute_pci_to_hw_id(struct i40e_vsi *vsi, struct i40e_hw *hw)
+{
+ int pf_count = i40e_get_pf_count(hw);
+
+ if (vsi->type == I40E_VSI_SRIOV)
+ return (hw->port * BIT(7)) / pf_count + vsi->vf_id;
+
+ return hw->port + BIT(7);
+}
+
+/**
+ * i40e_stat_update64 - read and update a 64 bit stat from the chip.
+ * @hw: ptr to the hardware info.
+ * @hireg: the high 32 bit reg to read.
+ * @loreg: the low 32 bit reg to read.
+ * @offset_loaded: has the initial offset been loaded yet.
+ * @offset: ptr to current offset value.
+ * @stat: ptr to the stat.
+ *
+ * Since the device stats are not reset at PFReset, they will not
+ * be zeroed when the driver starts. We'll save the first values read
+ * and use them as offsets to be subtracted from the raw values in order
+ * to report stats that count from zero.
+ **/
+static void i40e_stat_update64(struct i40e_hw *hw, u32 hireg, u32 loreg,
+ bool offset_loaded, u64 *offset, u64 *stat)
+{
+ u64 new_data;
+
+ new_data = rd64(hw, loreg);
+
+ if (!offset_loaded || new_data < *offset)
+ *offset = new_data;
+ *stat = new_data - *offset;
}
/**
@@ -631,6 +663,34 @@
}
/**
+ * i40e_stats_update_rx_discards - update rx_discards.
+ * @vsi: ptr to the VSI to be updated.
+ * @hw: ptr to the hardware info.
+ * @stat_idx: VSI's stat_counter_idx.
+ * @offset_loaded: ptr to the VSI's stat_offsets_loaded.
+ * @stat_offset: ptr to stat_offset to store first read of specific register.
+ * @stat: ptr to VSI's stat to be updated.
+ **/
+static void
+i40e_stats_update_rx_discards(struct i40e_vsi *vsi, struct i40e_hw *hw,
+ int stat_idx, bool offset_loaded,
+ struct i40e_eth_stats *stat_offset,
+ struct i40e_eth_stats *stat)
+{
+ u64 rx_rdpc, rx_rxerr;
+
+ i40e_stat_update32(hw, I40E_GLV_RDPC(stat_idx), offset_loaded,
+ &stat_offset->rx_discards, &rx_rdpc);
+ i40e_stat_update64(hw,
+ I40E_GL_RXERR1H(i40e_compute_pci_to_hw_id(vsi, hw)),
+ I40E_GL_RXERR1L(i40e_compute_pci_to_hw_id(vsi, hw)),
+ offset_loaded, &stat_offset->rx_discards_other,
+ &rx_rxerr);
+
+ stat->rx_discards = rx_rdpc + rx_rxerr;
+}
+
+/**
* i40e_update_eth_stats - Update VSI-specific ethernet statistics counters.
* @vsi: the VSI to be updated
**/
@@ -655,9 +715,6 @@
i40e_stat_update32(hw, I40E_GLV_RUPP(stat_idx),
vsi->stat_offsets_loaded,
&oes->rx_unknown_protocol, &es->rx_unknown_protocol);
- i40e_stat_update32(hw, I40E_GLV_TEPC(stat_idx),
- vsi->stat_offsets_loaded,
- &oes->tx_errors, &es->tx_errors);
i40e_stat_update48(hw, I40E_GLV_GORCH(stat_idx),
I40E_GLV_GORCL(stat_idx),
@@ -692,6 +749,10 @@
I40E_GLV_BPTCL(stat_idx),
vsi->stat_offsets_loaded,
&oes->tx_broadcast, &es->tx_broadcast);
+
+ i40e_stats_update_rx_discards(vsi, hw, stat_idx,
+ vsi->stat_offsets_loaded, oes, es);
+
vsi->stat_offsets_loaded = true;
}
@@ -699,7 +760,7 @@
* i40e_update_veb_stats - Update Switch component statistics
* @veb: the VEB being updated
**/
-static void i40e_update_veb_stats(struct i40e_veb *veb)
+void i40e_update_veb_stats(struct i40e_veb *veb)
{
struct i40e_pf *pf = veb->pf;
struct i40e_hw *hw = &pf->hw;
@@ -852,6 +913,25 @@
rx_p += packets;
rx_buf += p->rx_stats.alloc_buff_failed;
rx_page += p->rx_stats.alloc_page_failed;
+
+ if (i40e_enabled_xdp_vsi(vsi)) {
+ /* locate XDP ring */
+ p = READ_ONCE(vsi->xdp_rings[q]);
+ if (!p)
+ continue;
+
+ do {
+ start = u64_stats_fetch_begin_irq(&p->syncp);
+ packets = p->stats.packets;
+ bytes = p->stats.bytes;
+ } while (u64_stats_fetch_retry_irq(&p->syncp, start));
+ tx_b += bytes;
+ tx_p += packets;
+ tx_restart += p->tx_stats.restart_queue;
+ tx_busy += p->tx_stats.tx_busy;
+ tx_linearize += p->tx_stats.tx_linearize;
+ tx_force_wb += p->tx_stats.tx_force_wb;
+ }
}
rcu_read_unlock();
vsi->tx_restart = tx_restart;
@@ -1129,6 +1209,25 @@
i40e_update_pf_stats(pf);
i40e_update_vsi_stats(vsi);
+}
+
+/**
+ * i40e_count_filters - counts VSI mac filters
+ * @vsi: the VSI to be searched
+ *
+ * Returns count of mac filters
+ **/
+int i40e_count_filters(struct i40e_vsi *vsi)
+{
+ struct i40e_mac_filter *f;
+ struct hlist_node *h;
+ int bkt;
+ int cnt = 0;
+
+ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist)
+ ++cnt;
+
+ return cnt;
}
/**
@@ -1530,8 +1629,7 @@
bool found = false;
int bkt;
- WARN(!spin_is_locked(&vsi->mac_filter_hash_lock),
- "Missing mac_filter_hash_lock\n");
+ lockdep_assert_held(&vsi->mac_filter_hash_lock);
hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
if (ether_addr_equal(macaddr, f->macaddr)) {
__i40e_del_filter(vsi, f);
@@ -1569,8 +1667,8 @@
return 0;
}
- if (test_bit(__I40E_VSI_DOWN, vsi->back->state) ||
- test_bit(__I40E_RESET_RECOVERY_PENDING, vsi->back->state))
+ if (test_bit(__I40E_DOWN, pf->state) ||
+ test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
return -EADDRNOTAVAIL;
if (ether_addr_equal(hw->mac.addr, addr->sa_data))
@@ -1594,8 +1692,7 @@
if (vsi->type == I40E_VSI_MAIN) {
i40e_status ret;
- ret = i40e_aq_mac_address_write(&vsi->back->hw,
- I40E_AQC_WRITE_TYPE_LAA_WOL,
+ ret = i40e_aq_mac_address_write(hw, I40E_AQC_WRITE_TYPE_LAA_WOL,
addr->sa_data, NULL);
if (ret)
netdev_info(netdev, "Ignoring error from firmware on LAA update, status %s, AQ ret %s\n",
@@ -1606,7 +1703,7 @@
/* schedule our worker thread which will take care of
* applying the new filter changes
*/
- i40e_service_event_schedule(vsi->back);
+ i40e_service_event_schedule(pf);
return 0;
}
@@ -1614,6 +1711,8 @@
* i40e_config_rss_aq - Prepare for RSS using AQ commands
* @vsi: vsi structure
* @seed: RSS hash seed
+ * @lut: pointer to lookup table of lut_size
+ * @lut_size: size of the lookup table
**/
static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed,
u8 *lut, u16 lut_size)
@@ -1635,7 +1734,7 @@
}
}
if (lut) {
- bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false;
+ bool pf_lut = vsi->type == I40E_VSI_MAIN;
ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size);
if (ret) {
@@ -1800,6 +1899,8 @@
sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID;
offset = 0;
+ /* zero out queue mapping, it will get updated on the end of the function */
+ memset(ctxt->info.queue_mapping, 0, sizeof(ctxt->info.queue_mapping));
if (vsi->type == I40E_VSI_MAIN) {
/* This code helps add more queue to the VSI if we have
@@ -1808,18 +1909,24 @@
* non-zero req_queue_pairs says that user requested a new
* queue count via ethtool's set_channels, so use this
* value for queues distribution across traffic classes
+ * We need at least one queue pair for the interface
+ * to be usable as we see in else statement.
*/
if (vsi->req_queue_pairs > 0)
vsi->num_queue_pairs = vsi->req_queue_pairs;
else if (pf->flags & I40E_FLAG_MSIX_ENABLED)
vsi->num_queue_pairs = pf->num_lan_msix;
+ else
+ vsi->num_queue_pairs = 1;
}
/* Number of queues per enabled TC */
- if (vsi->type == I40E_VSI_MAIN)
+ if (vsi->type == I40E_VSI_MAIN ||
+ (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs != 0))
num_tc_qps = vsi->num_queue_pairs;
else
num_tc_qps = vsi->alloc_queue_pairs;
+
if (enabled_tc && (vsi->back->flags & I40E_FLAG_DCB_ENABLED)) {
/* Find numtc from enabled TC bitmap */
for (i = 0, numtc = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
@@ -1858,7 +1965,7 @@
num_tc_qps);
break;
}
- /* fall through */
+ fallthrough;
case I40E_VSI_FDIR:
case I40E_VSI_SRIOV:
case I40E_VSI_VMDQ2:
@@ -1897,10 +2004,12 @@
}
ctxt->info.tc_mapping[i] = cpu_to_le16(qmap);
}
- /* Do not change previously set num_queue_pairs for PFs */
+ /* Do not change previously set num_queue_pairs for PFs and VFs*/
if ((vsi->type == I40E_VSI_MAIN && numtc != 1) ||
- vsi->type != I40E_VSI_MAIN)
+ (vsi->type == I40E_VSI_SRIOV && vsi->num_queue_pairs == 0) ||
+ (vsi->type != I40E_VSI_MAIN && vsi->type != I40E_VSI_SRIOV))
vsi->num_queue_pairs = offset;
+
/* Scheduler section valid can only be set for ADD VSI */
if (is_add) {
sections |= I40E_AQ_VSI_PROP_SCHED_VALID;
@@ -2154,11 +2263,22 @@
fcnt = i40e_update_filter_state(num_add, list, add_head);
if (fcnt != num_add) {
- set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
- dev_warn(&vsi->back->pdev->dev,
- "Error %s adding RX filters on %s, promiscuous mode forced on\n",
- i40e_aq_str(hw, aq_err),
- vsi_name);
+ if (vsi->type == I40E_VSI_MAIN) {
+ set_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state);
+ dev_warn(&vsi->back->pdev->dev,
+ "Error %s adding RX filters on %s, promiscuous mode forced on\n",
+ i40e_aq_str(hw, aq_err), vsi_name);
+ } else if (vsi->type == I40E_VSI_SRIOV ||
+ vsi->type == I40E_VSI_VMDQ1 ||
+ vsi->type == I40E_VSI_VMDQ2) {
+ dev_warn(&vsi->back->pdev->dev,
+ "Error %s adding RX filters on %s, please set promiscuous on manually for %s\n",
+ i40e_aq_str(hw, aq_err), vsi_name, vsi_name);
+ } else {
+ dev_warn(&vsi->back->pdev->dev,
+ "Error %s adding RX filters on %s, incorrect VSI type: %i.\n",
+ i40e_aq_str(hw, aq_err), vsi_name, vsi->type);
+ }
}
}
@@ -2565,6 +2685,9 @@
vsi_name,
i40e_stat_str(hw, aq_ret),
i40e_aq_str(hw, hw->aq.asq_last_status));
+ } else {
+ dev_info(&pf->pdev->dev, "%s allmulti mode.\n",
+ cur_multipromisc ? "entering" : "leaving");
}
}
@@ -2671,8 +2794,8 @@
return -EINVAL;
}
- netdev_info(netdev, "changing MTU from %d to %d\n",
- netdev->mtu, new_mtu);
+ netdev_dbg(netdev, "changing MTU from %d to %d\n",
+ netdev->mtu, new_mtu);
netdev->mtu = new_mtu;
if (netif_running(netdev))
i40e_vsi_reinit_locked(vsi);
@@ -3014,9 +3137,9 @@
**/
void i40e_vsi_remove_pvid(struct i40e_vsi *vsi)
{
- i40e_vlan_stripping_disable(vsi);
-
vsi->info.pvid = 0;
+
+ i40e_vlan_stripping_disable(vsi);
}
/**
@@ -3129,6 +3252,26 @@
}
/**
+ * i40e_xsk_pool - Retrieve the AF_XDP buffer pool if XDP and ZC is enabled
+ * @ring: The Tx or Rx ring
+ *
+ * Returns the AF_XDP buffer pool or NULL.
+ **/
+static struct xsk_buff_pool *i40e_xsk_pool(struct i40e_ring *ring)
+{
+ bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
+ int qid = ring->queue_index;
+
+ if (ring_is_xdp(ring))
+ qid -= ring->vsi->alloc_queue_pairs;
+
+ if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps))
+ return NULL;
+
+ return xsk_get_pool_from_qid(ring->vsi->netdev, qid);
+}
+
+/**
* i40e_configure_tx_ring - Configure a transmit ring context and rest
* @ring: The Tx ring to configure
*
@@ -3142,6 +3285,9 @@
struct i40e_hmc_obj_txq tx_ctx;
i40e_status err = 0;
u32 qtx_ctl = 0;
+
+ if (ring_is_xdp(ring))
+ ring->xsk_pool = i40e_xsk_pool(ring);
/* some ATR related tx ring init */
if (vsi->back->flags & I40E_FLAG_FD_ATR_ENABLED) {
@@ -3252,13 +3398,45 @@
struct i40e_hw *hw = &vsi->back->hw;
struct i40e_hmc_obj_rxq rx_ctx;
i40e_status err = 0;
+ bool ok;
+ int ret;
bitmap_zero(ring->state, __I40E_RING_STATE_NBITS);
/* clear the context structure first */
memset(&rx_ctx, 0, sizeof(rx_ctx));
- ring->rx_buf_len = vsi->rx_buf_len;
+ if (ring->vsi->type == I40E_VSI_MAIN)
+ xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+
+ ring->xsk_pool = i40e_xsk_pool(ring);
+ if (ring->xsk_pool) {
+ ring->rx_buf_len =
+ xsk_pool_get_rx_frame_size(ring->xsk_pool);
+ /* For AF_XDP ZC, we disallow packets to span on
+ * multiple buffers, thus letting us skip that
+ * handling in the fast-path.
+ */
+ chain_len = 1;
+ ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+ MEM_TYPE_XSK_BUFF_POOL,
+ NULL);
+ if (ret)
+ return ret;
+ dev_info(&vsi->back->pdev->dev,
+ "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
+ ring->queue_index);
+
+ } else {
+ ring->rx_buf_len = vsi->rx_buf_len;
+ if (ring->vsi->type == I40E_VSI_MAIN) {
+ ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+ MEM_TYPE_PAGE_SHARED,
+ NULL);
+ if (ret)
+ return ret;
+ }
+ }
rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len,
BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT));
@@ -3266,8 +3444,8 @@
rx_ctx.base = (ring->dma / 128);
rx_ctx.qlen = ring->count;
- /* use 32 byte descriptors */
- rx_ctx.dsize = 1;
+ /* use 16 byte descriptors */
+ rx_ctx.dsize = 0;
/* descriptor type is always zero
* rx_ctx.dtype = 0;
@@ -3314,7 +3492,21 @@
ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
writel(0, ring->tail);
- i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
+ if (ring->xsk_pool) {
+ xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
+ ok = i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring));
+ } else {
+ ok = !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
+ }
+ if (!ok) {
+ /* Log this in case the user has forgotten to give the kernel
+ * any buffers, even later in the application.
+ */
+ dev_info(&vsi->back->pdev->dev,
+ "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n",
+ ring->xsk_pool ? "AF_XDP ZC enabled " : "",
+ ring->queue_index, pf_q);
+ }
return 0;
}
@@ -3333,7 +3525,7 @@
for (i = 0; (i < vsi->num_queue_pairs) && !err; i++)
err = i40e_configure_tx_ring(vsi->tx_rings[i]);
- if (!i40e_enabled_xdp_vsi(vsi))
+ if (err || !i40e_enabled_xdp_vsi(vsi))
return err;
for (i = 0; (i < vsi->num_queue_pairs) && !err; i++)
@@ -3631,7 +3823,7 @@
(I40E_QUEUE_TYPE_TX
<< I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
- wr32(hw, I40E_QINT_TQCTL(nextqp), val);
+ wr32(hw, I40E_QINT_TQCTL(nextqp), val);
}
val = I40E_QINT_TQCTL_CAUSE_ENA_MASK |
@@ -4006,7 +4198,8 @@
enable_intr:
/* re-enable interrupt causes */
wr32(hw, I40E_PFINT_ICR0_ENA, ena_mask);
- if (!test_bit(__I40E_DOWN, pf->state)) {
+ if (!test_bit(__I40E_DOWN, pf->state) ||
+ test_bit(__I40E_RECOVERY_MODE, pf->state)) {
i40e_service_event_schedule(pf);
i40e_irq_dynamic_enable_icr0(pf);
}
@@ -5321,6 +5514,58 @@
}
/**
+ * i40e_update_adq_vsi_queues - update queue mapping for ADq VSI
+ * @vsi: the VSI being reconfigured
+ * @vsi_offset: offset from main VF VSI
+ */
+int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset)
+{
+ struct i40e_vsi_context ctxt = {};
+ struct i40e_pf *pf;
+ struct i40e_hw *hw;
+ int ret;
+
+ if (!vsi)
+ return I40E_ERR_PARAM;
+ pf = vsi->back;
+ hw = &pf->hw;
+
+ ctxt.seid = vsi->seid;
+ ctxt.pf_num = hw->pf_id;
+ ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id + vsi_offset;
+ ctxt.uplink_seid = vsi->uplink_seid;
+ ctxt.connection_type = I40E_AQ_VSI_CONN_TYPE_NORMAL;
+ ctxt.flags = I40E_AQ_VSI_TYPE_VF;
+ ctxt.info = vsi->info;
+
+ i40e_vsi_setup_queue_map(vsi, &ctxt, vsi->tc_config.enabled_tc,
+ false);
+ if (vsi->reconfig_rss) {
+ vsi->rss_size = min_t(int, pf->alloc_rss_size,
+ vsi->num_queue_pairs);
+ ret = i40e_vsi_config_rss(vsi);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "Failed to reconfig rss for num_queues\n");
+ return ret;
+ }
+ vsi->reconfig_rss = false;
+ }
+
+ ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev, "Update vsi config failed, err %s aq_err %s\n",
+ i40e_stat_str(hw, ret),
+ i40e_aq_str(hw, hw->aq.asq_last_status));
+ return ret;
+ }
+ /* update the local VSI info with updated queue map */
+ i40e_vsi_update_queue_map(vsi, &ctxt);
+ vsi->info.valid_sections = 0;
+
+ return ret;
+}
+
+/**
* i40e_vsi_config_tc - Configure VSI Tx Scheduler for given TC map
* @vsi: VSI to be configured
* @enabled_tc: TC bitmap
@@ -5482,6 +5727,26 @@
}
/**
+ * i40e_bw_bytes_to_mbits - Convert max_tx_rate from bytes to mbits
+ * @vsi: Pointer to vsi structure
+ * @max_tx_rate: max TX rate in bytes to be converted into Mbits
+ *
+ * Helper function to convert units before send to set BW limit
+ **/
+static u64 i40e_bw_bytes_to_mbits(struct i40e_vsi *vsi, u64 max_tx_rate)
+{
+ if (max_tx_rate < I40E_BW_MBPS_DIVISOR) {
+ dev_warn(&vsi->back->pdev->dev,
+ "Setting max tx rate to minimum usable value of 50Mbps.\n");
+ max_tx_rate = I40E_BW_CREDIT_DIVISOR;
+ } else {
+ do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR);
+ }
+
+ return max_tx_rate;
+}
+
+/**
* i40e_set_bw_limit - setup BW limit for Tx traffic based on max_tx_rate
* @vsi: VSI to be configured
* @seid: seid of the channel/VSI
@@ -5503,10 +5768,10 @@
max_tx_rate, seid);
return -EINVAL;
}
- if (max_tx_rate && max_tx_rate < 50) {
+ if (max_tx_rate && max_tx_rate < I40E_BW_CREDIT_DIVISOR) {
dev_warn(&pf->pdev->dev,
"Setting max tx rate to minimum usable value of 50Mbps.\n");
- max_tx_rate = 50;
+ max_tx_rate = I40E_BW_CREDIT_DIVISOR;
}
/* Tx rate credits are in values of 50Mbps, 0 is disabled */
@@ -5608,24 +5873,6 @@
kfree(ch);
}
INIT_LIST_HEAD(&vsi->ch_list);
-}
-
-/**
- * i40e_is_any_channel - channel exist or not
- * @vsi: ptr to VSI to which channels are associated with
- *
- * Returns true or false if channel(s) exist for associated VSI or not
- **/
-static bool i40e_is_any_channel(struct i40e_vsi *vsi)
-{
- struct i40e_channel *ch, *ch_tmp;
-
- list_for_each_entry_safe(ch, ch_tmp, &vsi->ch_list, list) {
- if (ch->initialized)
- return true;
- }
-
- return false;
}
/**
@@ -5764,7 +6011,6 @@
/**
* i40e_channel_setup_queue_map - Setup a channel queue map
* @pf: ptr to PF device
- * @vsi: the VSI being setup
* @ctxt: VSI context structure
* @ch: ptr to channel structure
*
@@ -5852,11 +6098,13 @@
return -ENOENT;
}
- /* Success, update channel */
- ch->enabled_tc = enabled_tc;
+ /* Success, update channel, set enabled_tc only if the channel
+ * is not a macvlan
+ */
+ ch->enabled_tc = !i40e_is_channel_macvlan(ch) && enabled_tc;
ch->seid = ctxt.seid;
ch->vsi_number = ctxt.vsi_number;
- ch->stat_counter_idx = cpu_to_le16(ctxt.info.stat_counter_idx);
+ ch->stat_counter_idx = le16_to_cpu(ctxt.info.stat_counter_idx);
/* copy just the sections touched not the entire info
* since not all sections are valid as returned by
@@ -6005,8 +6253,7 @@
/**
* i40e_setup_channel - setup new channel using uplink element
* @pf: ptr to PF device
- * @type: type of channel to be created (VMDq2/VF)
- * @uplink_seid: underlying HW switching element (VEB) ID
+ * @vsi: pointer to the VSI to set up the channel within
* @ch: ptr to channel structure
*
* Setup new channel (VSI) based on specified type (VMDq2/VF)
@@ -6133,26 +6380,15 @@
/* By default we are in VEPA mode, if this is the first VF/VMDq
* VSI to be added switch to VEB mode.
*/
- if ((!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) ||
- (!i40e_is_any_channel(vsi))) {
- if (!is_power_of_2(vsi->tc_config.tc_info[0].qcount)) {
- dev_dbg(&pf->pdev->dev,
- "Failed to create channel. Override queues (%u) not power of 2\n",
- vsi->tc_config.tc_info[0].qcount);
- return -EINVAL;
- }
- if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
- pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
+ if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
+ pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
- if (vsi->type == I40E_VSI_MAIN) {
- if (pf->flags & I40E_FLAG_TC_MQPRIO)
- i40e_do_reset(pf, I40E_PF_RESET_FLAG,
- true);
- else
- i40e_do_reset_safe(pf,
- I40E_PF_RESET_FLAG);
- }
+ if (vsi->type == I40E_VSI_MAIN) {
+ if (pf->flags & I40E_FLAG_TC_MQPRIO)
+ i40e_do_reset(pf, I40E_PF_RESET_FLAG, true);
+ else
+ i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
}
/* now onwards for main VSI, number of queues will be value
* of TC0's queue count
@@ -6416,11 +6652,13 @@
* Also do not enable DCBx if FW LLDP agent is disabled
*/
if ((pf->hw_features & I40E_HW_NO_DCB_SUPPORT) ||
- (pf->flags & I40E_FLAG_DISABLE_FW_LLDP))
+ (pf->flags & I40E_FLAG_DISABLE_FW_LLDP)) {
+ dev_info(&pf->pdev->dev, "DCB is not supported or FW LLDP is disabled\n");
+ err = I40E_NOT_SUPPORTED;
goto out;
+ }
- /* Get the initial DCB configuration */
- err = i40e_init_dcb(hw);
+ err = i40e_init_dcb(hw, true);
if (!err) {
/* Device/Function is not DCBX capable */
if ((!hw->func_caps.dcb) ||
@@ -6457,8 +6695,7 @@
return err;
}
#endif /* CONFIG_I40E_DCB */
-#define SPEED_SIZE 14
-#define FC_SIZE 8
+
/**
* i40e_print_link_message - print link up or down
* @vsi: the VSI for which link needs a message
@@ -6474,7 +6711,10 @@
char *req_fec = "";
char *an = "";
- new_speed = pf->hw.phy.link_info.link_speed;
+ if (isup)
+ new_speed = pf->hw.phy.link_info.link_speed;
+ else
+ new_speed = I40E_LINK_SPEED_UNKNOWN;
if ((vsi->current_isup == isup) && (vsi->current_speed == new_speed))
return;
@@ -6507,6 +6747,12 @@
case I40E_LINK_SPEED_10GB:
speed = "10 G";
break;
+ case I40E_LINK_SPEED_5GB:
+ speed = "5 G";
+ break;
+ case I40E_LINK_SPEED_2_5GB:
+ speed = "2.5 G";
+ break;
case I40E_LINK_SPEED_1GB:
speed = "1000 M";
break;
@@ -6533,19 +6779,19 @@
}
if (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) {
- req_fec = ", Requested FEC: None";
- fec = ", FEC: None";
- an = ", Autoneg: False";
+ req_fec = "None";
+ fec = "None";
+ an = "False";
if (pf->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED)
- an = ", Autoneg: True";
+ an = "True";
if (pf->hw.phy.link_info.fec_info &
I40E_AQ_CONFIG_FEC_KR_ENA)
- fec = ", FEC: CL74 FC-FEC/BASE-R";
+ fec = "CL74 FC-FEC/BASE-R";
else if (pf->hw.phy.link_info.fec_info &
I40E_AQ_CONFIG_FEC_RS_ENA)
- fec = ", FEC: CL108 RS-FEC";
+ fec = "CL108 RS-FEC";
/* 'CL108 RS-FEC' should be displayed when RS is requested, or
* both RS and FC are requested
@@ -6554,14 +6800,38 @@
(I40E_AQ_REQUEST_FEC_KR | I40E_AQ_REQUEST_FEC_RS)) {
if (vsi->back->hw.phy.link_info.req_fec_info &
I40E_AQ_REQUEST_FEC_RS)
- req_fec = ", Requested FEC: CL108 RS-FEC";
+ req_fec = "CL108 RS-FEC";
else
- req_fec = ", Requested FEC: CL74 FC-FEC/BASE-R";
+ req_fec = "CL74 FC-FEC/BASE-R";
}
+ netdev_info(vsi->netdev,
+ "NIC Link is Up, %sbps Full Duplex, Requested FEC: %s, Negotiated FEC: %s, Autoneg: %s, Flow Control: %s\n",
+ speed, req_fec, fec, an, fc);
+ } else if (pf->hw.device_id == I40E_DEV_ID_KX_X722) {
+ req_fec = "None";
+ fec = "None";
+ an = "False";
+
+ if (pf->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED)
+ an = "True";
+
+ if (pf->hw.phy.link_info.fec_info &
+ I40E_AQ_CONFIG_FEC_KR_ENA)
+ fec = "CL74 FC-FEC/BASE-R";
+
+ if (pf->hw.phy.link_info.req_fec_info &
+ I40E_AQ_REQUEST_FEC_KR)
+ req_fec = "CL74 FC-FEC/BASE-R";
+
+ netdev_info(vsi->netdev,
+ "NIC Link is Up, %sbps Full Duplex, Requested FEC: %s, Negotiated FEC: %s, Autoneg: %s, Flow Control: %s\n",
+ speed, req_fec, fec, an, fc);
+ } else {
+ netdev_info(vsi->netdev,
+ "NIC Link is Up, %sbps Full Duplex, Flow Control: %s\n",
+ speed, fc);
}
- netdev_info(vsi->netdev, "NIC Link is Up, %sbps Full Duplex%s%s%s, Flow Control: %s\n",
- speed, req_fec, fec, an, fc);
}
/**
@@ -6622,28 +6892,12 @@
{
struct i40e_pf *pf = vsi->back;
- WARN_ON(in_interrupt());
while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state))
usleep_range(1000, 2000);
i40e_down(vsi);
i40e_up(vsi);
clear_bit(__I40E_CONFIG_BUSY, pf->state);
-}
-
-/**
- * i40e_up - Bring the connection back up after being down
- * @vsi: the VSI being configured
- **/
-int i40e_up(struct i40e_vsi *vsi)
-{
- int err;
-
- err = i40e_vsi_configure(vsi);
- if (!err)
- err = i40e_up_complete(vsi);
-
- return err;
}
/**
@@ -6655,6 +6909,7 @@
{
struct i40e_aq_get_phy_abilities_resp abilities;
struct i40e_aq_set_phy_config config = {0};
+ bool non_zero_phy_type = is_up;
struct i40e_hw *hw = &pf->hw;
i40e_status err;
u64 mask;
@@ -6690,8 +6945,11 @@
/* If link needs to go up, but was not forced to go down,
* and its speed values are OK, no need for a flap
+ * if non_zero_phy_type was set, still need to force up
*/
- if (is_up && abilities.phy_type != 0 && abilities.link_speed != 0)
+ if (pf->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED)
+ non_zero_phy_type = true;
+ else if (is_up && abilities.phy_type != 0 && abilities.link_speed != 0)
return I40E_SUCCESS;
/* To force link we need to set bits for all supported PHY types,
@@ -6699,10 +6957,18 @@
* across two fields.
*/
mask = I40E_PHY_TYPES_BITMASK;
- config.phy_type = is_up ? cpu_to_le32((u32)(mask & 0xffffffff)) : 0;
- config.phy_type_ext = is_up ? (u8)((mask >> 32) & 0xff) : 0;
+ config.phy_type =
+ non_zero_phy_type ? cpu_to_le32((u32)(mask & 0xffffffff)) : 0;
+ config.phy_type_ext =
+ non_zero_phy_type ? (u8)((mask >> 32) & 0xff) : 0;
/* Copy the old settings, except of phy_type */
config.abilities = abilities.abilities;
+ if (pf->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED) {
+ if (is_up)
+ config.abilities |= I40E_AQ_PHY_ENABLE_LINK;
+ else
+ config.abilities &= ~(I40E_AQ_PHY_ENABLE_LINK);
+ }
if (abilities.link_speed != 0)
config.link_speed = abilities.link_speed;
else
@@ -6733,9 +6999,29 @@
i40e_update_link_info(hw);
}
- i40e_aq_set_link_restart_an(hw, true, NULL);
+ i40e_aq_set_link_restart_an(hw, is_up, NULL);
return I40E_SUCCESS;
+}
+
+/**
+ * i40e_up - Bring the connection back up after being down
+ * @vsi: the VSI being configured
+ **/
+int i40e_up(struct i40e_vsi *vsi)
+{
+ int err;
+
+ if (vsi->type == I40E_VSI_MAIN &&
+ (vsi->back->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED ||
+ vsi->back->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED))
+ i40e_force_link_state(vsi->back, true);
+
+ err = i40e_vsi_configure(vsi);
+ if (!err)
+ err = i40e_up_complete(vsi);
+
+ return err;
}
/**
@@ -6756,14 +7042,20 @@
i40e_vsi_disable_irq(vsi);
i40e_vsi_stop_rings(vsi);
if (vsi->type == I40E_VSI_MAIN &&
- vsi->back->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED)
+ (vsi->back->flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED ||
+ vsi->back->flags & I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED))
i40e_force_link_state(vsi->back, false);
i40e_napi_disable_all(vsi);
for (i = 0; i < vsi->num_queue_pairs; i++) {
i40e_clean_tx_ring(vsi->tx_rings[i]);
- if (i40e_enabled_xdp_vsi(vsi))
+ if (i40e_enabled_xdp_vsi(vsi)) {
+ /* Make sure that in-progress ndo_xdp_xmit and
+ * ndo_xsk_wakeup calls are completed.
+ */
+ synchronize_rcu();
i40e_clean_tx_ring(vsi->xdp_rings[i]);
+ }
i40e_clean_rx_ring(vsi->rx_rings[i]);
}
@@ -6841,6 +7133,491 @@
else
vsi->tc_config.tc_info[i].qcount = 1;
vsi->tc_config.tc_info[i].netdev_tc = 0;
+ }
+}
+
+/**
+ * i40e_del_macvlan_filter
+ * @hw: pointer to the HW structure
+ * @seid: seid of the channel VSI
+ * @macaddr: the mac address to apply as a filter
+ * @aq_err: store the admin Q error
+ *
+ * This function deletes a mac filter on the channel VSI which serves as the
+ * macvlan. Returns 0 on success.
+ **/
+static i40e_status i40e_del_macvlan_filter(struct i40e_hw *hw, u16 seid,
+ const u8 *macaddr, int *aq_err)
+{
+ struct i40e_aqc_remove_macvlan_element_data element;
+ i40e_status status;
+
+ memset(&element, 0, sizeof(element));
+ ether_addr_copy(element.mac_addr, macaddr);
+ element.vlan_tag = 0;
+ element.flags = I40E_AQC_MACVLAN_DEL_PERFECT_MATCH;
+ status = i40e_aq_remove_macvlan(hw, seid, &element, 1, NULL);
+ *aq_err = hw->aq.asq_last_status;
+
+ return status;
+}
+
+/**
+ * i40e_add_macvlan_filter
+ * @hw: pointer to the HW structure
+ * @seid: seid of the channel VSI
+ * @macaddr: the mac address to apply as a filter
+ * @aq_err: store the admin Q error
+ *
+ * This function adds a mac filter on the channel VSI which serves as the
+ * macvlan. Returns 0 on success.
+ **/
+static i40e_status i40e_add_macvlan_filter(struct i40e_hw *hw, u16 seid,
+ const u8 *macaddr, int *aq_err)
+{
+ struct i40e_aqc_add_macvlan_element_data element;
+ i40e_status status;
+ u16 cmd_flags = 0;
+
+ ether_addr_copy(element.mac_addr, macaddr);
+ element.vlan_tag = 0;
+ element.queue_number = 0;
+ element.match_method = I40E_AQC_MM_ERR_NO_RES;
+ cmd_flags |= I40E_AQC_MACVLAN_ADD_PERFECT_MATCH;
+ element.flags = cpu_to_le16(cmd_flags);
+ status = i40e_aq_add_macvlan(hw, seid, &element, 1, NULL);
+ *aq_err = hw->aq.asq_last_status;
+
+ return status;
+}
+
+/**
+ * i40e_reset_ch_rings - Reset the queue contexts in a channel
+ * @vsi: the VSI we want to access
+ * @ch: the channel we want to access
+ */
+static void i40e_reset_ch_rings(struct i40e_vsi *vsi, struct i40e_channel *ch)
+{
+ struct i40e_ring *tx_ring, *rx_ring;
+ u16 pf_q;
+ int i;
+
+ for (i = 0; i < ch->num_queue_pairs; i++) {
+ pf_q = ch->base_queue + i;
+ tx_ring = vsi->tx_rings[pf_q];
+ tx_ring->ch = NULL;
+ rx_ring = vsi->rx_rings[pf_q];
+ rx_ring->ch = NULL;
+ }
+}
+
+/**
+ * i40e_free_macvlan_channels
+ * @vsi: the VSI we want to access
+ *
+ * This function frees the Qs of the channel VSI from
+ * the stack and also deletes the channel VSIs which
+ * serve as macvlans.
+ */
+static void i40e_free_macvlan_channels(struct i40e_vsi *vsi)
+{
+ struct i40e_channel *ch, *ch_tmp;
+ int ret;
+
+ if (list_empty(&vsi->macvlan_list))
+ return;
+
+ list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
+ struct i40e_vsi *parent_vsi;
+
+ if (i40e_is_channel_macvlan(ch)) {
+ i40e_reset_ch_rings(vsi, ch);
+ clear_bit(ch->fwd->bit_no, vsi->fwd_bitmask);
+ netdev_unbind_sb_channel(vsi->netdev, ch->fwd->netdev);
+ netdev_set_sb_channel(ch->fwd->netdev, 0);
+ kfree(ch->fwd);
+ ch->fwd = NULL;
+ }
+
+ list_del(&ch->list);
+ parent_vsi = ch->parent_vsi;
+ if (!parent_vsi || !ch->initialized) {
+ kfree(ch);
+ continue;
+ }
+
+ /* remove the VSI */
+ ret = i40e_aq_delete_element(&vsi->back->hw, ch->seid,
+ NULL);
+ if (ret)
+ dev_err(&vsi->back->pdev->dev,
+ "unable to remove channel (%d) for parent VSI(%d)\n",
+ ch->seid, parent_vsi->seid);
+ kfree(ch);
+ }
+ vsi->macvlan_cnt = 0;
+}
+
+/**
+ * i40e_fwd_ring_up - bring the macvlan device up
+ * @vsi: the VSI we want to access
+ * @vdev: macvlan netdevice
+ * @fwd: the private fwd structure
+ */
+static int i40e_fwd_ring_up(struct i40e_vsi *vsi, struct net_device *vdev,
+ struct i40e_fwd_adapter *fwd)
+{
+ struct i40e_channel *ch = NULL, *ch_tmp, *iter;
+ int ret = 0, num_tc = 1, i, aq_err;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+
+ /* Go through the list and find an available channel */
+ list_for_each_entry_safe(iter, ch_tmp, &vsi->macvlan_list, list) {
+ if (!i40e_is_channel_macvlan(iter)) {
+ iter->fwd = fwd;
+ /* record configuration for macvlan interface in vdev */
+ for (i = 0; i < num_tc; i++)
+ netdev_bind_sb_channel_queue(vsi->netdev, vdev,
+ i,
+ iter->num_queue_pairs,
+ iter->base_queue);
+ for (i = 0; i < iter->num_queue_pairs; i++) {
+ struct i40e_ring *tx_ring, *rx_ring;
+ u16 pf_q;
+
+ pf_q = iter->base_queue + i;
+
+ /* Get to TX ring ptr */
+ tx_ring = vsi->tx_rings[pf_q];
+ tx_ring->ch = iter;
+
+ /* Get the RX ring ptr */
+ rx_ring = vsi->rx_rings[pf_q];
+ rx_ring->ch = iter;
+ }
+ ch = iter;
+ break;
+ }
+ }
+
+ if (!ch)
+ return -EINVAL;
+
+ /* Guarantee all rings are updated before we update the
+ * MAC address filter.
+ */
+ wmb();
+
+ /* Add a mac filter */
+ ret = i40e_add_macvlan_filter(hw, ch->seid, vdev->dev_addr, &aq_err);
+ if (ret) {
+ /* if we cannot add the MAC rule then disable the offload */
+ macvlan_release_l2fw_offload(vdev);
+ for (i = 0; i < ch->num_queue_pairs; i++) {
+ struct i40e_ring *rx_ring;
+ u16 pf_q;
+
+ pf_q = ch->base_queue + i;
+ rx_ring = vsi->rx_rings[pf_q];
+ rx_ring->netdev = NULL;
+ }
+ dev_info(&pf->pdev->dev,
+ "Error adding mac filter on macvlan err %s, aq_err %s\n",
+ i40e_stat_str(hw, ret),
+ i40e_aq_str(hw, aq_err));
+ netdev_err(vdev, "L2fwd offload disabled to L2 filter error\n");
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_setup_macvlans - create the channels which will be macvlans
+ * @vsi: the VSI we want to access
+ * @macvlan_cnt: no. of macvlans to be setup
+ * @qcnt: no. of Qs per macvlan
+ * @vdev: macvlan netdevice
+ */
+static int i40e_setup_macvlans(struct i40e_vsi *vsi, u16 macvlan_cnt, u16 qcnt,
+ struct net_device *vdev)
+{
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ struct i40e_vsi_context ctxt;
+ u16 sections, qmap, num_qps;
+ struct i40e_channel *ch;
+ int i, pow, ret = 0;
+ u8 offset = 0;
+
+ if (vsi->type != I40E_VSI_MAIN || !macvlan_cnt)
+ return -EINVAL;
+
+ num_qps = vsi->num_queue_pairs - (macvlan_cnt * qcnt);
+
+ /* find the next higher power-of-2 of num queue pairs */
+ pow = fls(roundup_pow_of_two(num_qps) - 1);
+
+ qmap = (offset << I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) |
+ (pow << I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT);
+
+ /* Setup context bits for the main VSI */
+ sections = I40E_AQ_VSI_PROP_QUEUE_MAP_VALID;
+ sections |= I40E_AQ_VSI_PROP_SCHED_VALID;
+ memset(&ctxt, 0, sizeof(ctxt));
+ ctxt.seid = vsi->seid;
+ ctxt.pf_num = vsi->back->hw.pf_id;
+ ctxt.vf_num = 0;
+ ctxt.uplink_seid = vsi->uplink_seid;
+ ctxt.info = vsi->info;
+ ctxt.info.tc_mapping[0] = cpu_to_le16(qmap);
+ ctxt.info.mapping_flags |= cpu_to_le16(I40E_AQ_VSI_QUE_MAP_CONTIG);
+ ctxt.info.queue_mapping[0] = cpu_to_le16(vsi->base_queue);
+ ctxt.info.valid_sections |= cpu_to_le16(sections);
+
+ /* Reconfigure RSS for main VSI with new max queue count */
+ vsi->rss_size = max_t(u16, num_qps, qcnt);
+ ret = i40e_vsi_config_rss(vsi);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Failed to reconfig RSS for num_queues (%u)\n",
+ vsi->rss_size);
+ return ret;
+ }
+ vsi->reconfig_rss = true;
+ dev_dbg(&vsi->back->pdev->dev,
+ "Reconfigured RSS with num_queues (%u)\n", vsi->rss_size);
+ vsi->next_base_queue = num_qps;
+ vsi->cnt_q_avail = vsi->num_queue_pairs - num_qps;
+
+ /* Update the VSI after updating the VSI queue-mapping
+ * information
+ */
+ ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "Update vsi tc config failed, err %s aq_err %s\n",
+ i40e_stat_str(hw, ret),
+ i40e_aq_str(hw, hw->aq.asq_last_status));
+ return ret;
+ }
+ /* update the local VSI info with updated queue map */
+ i40e_vsi_update_queue_map(vsi, &ctxt);
+ vsi->info.valid_sections = 0;
+
+ /* Create channels for macvlans */
+ INIT_LIST_HEAD(&vsi->macvlan_list);
+ for (i = 0; i < macvlan_cnt; i++) {
+ ch = kzalloc(sizeof(*ch), GFP_KERNEL);
+ if (!ch) {
+ ret = -ENOMEM;
+ goto err_free;
+ }
+ INIT_LIST_HEAD(&ch->list);
+ ch->num_queue_pairs = qcnt;
+ if (!i40e_setup_channel(pf, vsi, ch)) {
+ ret = -EINVAL;
+ kfree(ch);
+ goto err_free;
+ }
+ ch->parent_vsi = vsi;
+ vsi->cnt_q_avail -= ch->num_queue_pairs;
+ vsi->macvlan_cnt++;
+ list_add_tail(&ch->list, &vsi->macvlan_list);
+ }
+
+ return ret;
+
+err_free:
+ dev_info(&pf->pdev->dev, "Failed to setup macvlans\n");
+ i40e_free_macvlan_channels(vsi);
+
+ return ret;
+}
+
+/**
+ * i40e_fwd_add - configure macvlans
+ * @netdev: net device to configure
+ * @vdev: macvlan netdevice
+ **/
+static void *i40e_fwd_add(struct net_device *netdev, struct net_device *vdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ u16 q_per_macvlan = 0, macvlan_cnt = 0, vectors;
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_fwd_adapter *fwd;
+ int avail_macvlan, ret;
+
+ if ((pf->flags & I40E_FLAG_DCB_ENABLED)) {
+ netdev_info(netdev, "Macvlans are not supported when DCB is enabled\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if ((pf->flags & I40E_FLAG_TC_MQPRIO)) {
+ netdev_info(netdev, "Macvlans are not supported when HW TC offload is on\n");
+ return ERR_PTR(-EINVAL);
+ }
+ if (pf->num_lan_msix < I40E_MIN_MACVLAN_VECTORS) {
+ netdev_info(netdev, "Not enough vectors available to support macvlans\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ /* The macvlan device has to be a single Q device so that the
+ * tc_to_txq field can be reused to pick the tx queue.
+ */
+ if (netif_is_multiqueue(vdev))
+ return ERR_PTR(-ERANGE);
+
+ if (!vsi->macvlan_cnt) {
+ /* reserve bit 0 for the pf device */
+ set_bit(0, vsi->fwd_bitmask);
+
+ /* Try to reserve as many queues as possible for macvlans. First
+ * reserve 3/4th of max vectors, then half, then quarter and
+ * calculate Qs per macvlan as you go
+ */
+ vectors = pf->num_lan_msix;
+ if (vectors <= I40E_MAX_MACVLANS && vectors > 64) {
+ /* allocate 4 Qs per macvlan and 32 Qs to the PF*/
+ q_per_macvlan = 4;
+ macvlan_cnt = (vectors - 32) / 4;
+ } else if (vectors <= 64 && vectors > 32) {
+ /* allocate 2 Qs per macvlan and 16 Qs to the PF*/
+ q_per_macvlan = 2;
+ macvlan_cnt = (vectors - 16) / 2;
+ } else if (vectors <= 32 && vectors > 16) {
+ /* allocate 1 Q per macvlan and 16 Qs to the PF*/
+ q_per_macvlan = 1;
+ macvlan_cnt = vectors - 16;
+ } else if (vectors <= 16 && vectors > 8) {
+ /* allocate 1 Q per macvlan and 8 Qs to the PF */
+ q_per_macvlan = 1;
+ macvlan_cnt = vectors - 8;
+ } else {
+ /* allocate 1 Q per macvlan and 1 Q to the PF */
+ q_per_macvlan = 1;
+ macvlan_cnt = vectors - 1;
+ }
+
+ if (macvlan_cnt == 0)
+ return ERR_PTR(-EBUSY);
+
+ /* Quiesce VSI queues */
+ i40e_quiesce_vsi(vsi);
+
+ /* sets up the macvlans but does not "enable" them */
+ ret = i40e_setup_macvlans(vsi, macvlan_cnt, q_per_macvlan,
+ vdev);
+ if (ret)
+ return ERR_PTR(ret);
+
+ /* Unquiesce VSI */
+ i40e_unquiesce_vsi(vsi);
+ }
+ avail_macvlan = find_first_zero_bit(vsi->fwd_bitmask,
+ vsi->macvlan_cnt);
+ if (avail_macvlan >= I40E_MAX_MACVLANS)
+ return ERR_PTR(-EBUSY);
+
+ /* create the fwd struct */
+ fwd = kzalloc(sizeof(*fwd), GFP_KERNEL);
+ if (!fwd)
+ return ERR_PTR(-ENOMEM);
+
+ set_bit(avail_macvlan, vsi->fwd_bitmask);
+ fwd->bit_no = avail_macvlan;
+ netdev_set_sb_channel(vdev, avail_macvlan);
+ fwd->netdev = vdev;
+
+ if (!netif_running(netdev))
+ return fwd;
+
+ /* Set fwd ring up */
+ ret = i40e_fwd_ring_up(vsi, vdev, fwd);
+ if (ret) {
+ /* unbind the queues and drop the subordinate channel config */
+ netdev_unbind_sb_channel(netdev, vdev);
+ netdev_set_sb_channel(vdev, 0);
+
+ kfree(fwd);
+ return ERR_PTR(-EINVAL);
+ }
+
+ return fwd;
+}
+
+/**
+ * i40e_del_all_macvlans - Delete all the mac filters on the channels
+ * @vsi: the VSI we want to access
+ */
+static void i40e_del_all_macvlans(struct i40e_vsi *vsi)
+{
+ struct i40e_channel *ch, *ch_tmp;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ int aq_err, ret = 0;
+
+ if (list_empty(&vsi->macvlan_list))
+ return;
+
+ list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
+ if (i40e_is_channel_macvlan(ch)) {
+ ret = i40e_del_macvlan_filter(hw, ch->seid,
+ i40e_channel_mac(ch),
+ &aq_err);
+ if (!ret) {
+ /* Reset queue contexts */
+ i40e_reset_ch_rings(vsi, ch);
+ clear_bit(ch->fwd->bit_no, vsi->fwd_bitmask);
+ netdev_unbind_sb_channel(vsi->netdev,
+ ch->fwd->netdev);
+ netdev_set_sb_channel(ch->fwd->netdev, 0);
+ kfree(ch->fwd);
+ ch->fwd = NULL;
+ }
+ }
+ }
+}
+
+/**
+ * i40e_fwd_del - delete macvlan interfaces
+ * @netdev: net device to configure
+ * @vdev: macvlan netdevice
+ */
+static void i40e_fwd_del(struct net_device *netdev, void *vdev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_fwd_adapter *fwd = vdev;
+ struct i40e_channel *ch, *ch_tmp;
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+ int aq_err, ret = 0;
+
+ /* Find the channel associated with the macvlan and del mac filter */
+ list_for_each_entry_safe(ch, ch_tmp, &vsi->macvlan_list, list) {
+ if (i40e_is_channel_macvlan(ch) &&
+ ether_addr_equal(i40e_channel_mac(ch),
+ fwd->netdev->dev_addr)) {
+ ret = i40e_del_macvlan_filter(hw, ch->seid,
+ i40e_channel_mac(ch),
+ &aq_err);
+ if (!ret) {
+ /* Reset queue contexts */
+ i40e_reset_ch_rings(vsi, ch);
+ clear_bit(ch->fwd->bit_no, vsi->fwd_bitmask);
+ netdev_unbind_sb_channel(netdev, fwd->netdev);
+ netdev_set_sb_channel(fwd->netdev, 0);
+ kfree(ch->fwd);
+ ch->fwd = NULL;
+ } else {
+ dev_info(&pf->pdev->dev,
+ "Error deleting mac filter on macvlan err %s, aq_err %s\n",
+ i40e_stat_str(hw, ret),
+ i40e_aq_str(hw, aq_err));
+ }
+ break;
+ }
}
}
@@ -6939,13 +7716,25 @@
vsi->seid);
need_reset = true;
goto exit;
+ } else if (enabled_tc &&
+ (!is_power_of_2(vsi->tc_config.tc_info[0].qcount))) {
+ netdev_info(netdev,
+ "Failed to create channel. Override queues (%u) not power of 2\n",
+ vsi->tc_config.tc_info[0].qcount);
+ ret = -EINVAL;
+ need_reset = true;
+ goto exit;
}
+
+ dev_info(&vsi->back->pdev->dev,
+ "Setup channel (id:%u) utilizing num_queues %d\n",
+ vsi->seid, vsi->tc_config.tc_info[0].qcount);
if (pf->flags & I40E_FLAG_TC_MQPRIO) {
if (vsi->mqprio_qopt.max_rate[0]) {
- u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
+ u64 max_tx_rate = i40e_bw_bytes_to_mbits(vsi,
+ vsi->mqprio_qopt.max_rate[0]);
- do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR);
ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate);
if (!ret) {
u64 credits = max_tx_rate;
@@ -6994,8 +7783,8 @@
i40e_set_cld_element(struct i40e_cloud_filter *filter,
struct i40e_aqc_cloud_filters_element_data *cld)
{
- int i, j;
u32 ipa;
+ int i;
memset(cld, 0, sizeof(*cld));
ether_addr_copy(cld->outer_mac, filter->dst_mac);
@@ -7006,14 +7795,14 @@
if (filter->n_proto == ETH_P_IPV6) {
#define IPV6_MAX_INDEX (ARRAY_SIZE(filter->dst_ipv6) - 1)
- for (i = 0, j = 0; i < ARRAY_SIZE(filter->dst_ipv6);
- i++, j += 2) {
+ for (i = 0; i < ARRAY_SIZE(filter->dst_ipv6); i++) {
ipa = be32_to_cpu(filter->dst_ipv6[IPV6_MAX_INDEX - i]);
- ipa = cpu_to_le32(ipa);
- memcpy(&cld->ipaddr.raw_v6.data[j], &ipa, sizeof(ipa));
+
+ *(__le32 *)&cld->ipaddr.raw_v6.data[i * 2] = cpu_to_le32(ipa);
}
} else {
ipa = be32_to_cpu(filter->dst_ipv4);
+
memcpy(&cld->ipaddr.v4.data, &ipa, sizeof(ipa));
}
@@ -7208,19 +7997,21 @@
/**
* i40e_parse_cls_flower - Parse tc flower filters provided by kernel
* @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @f: Pointer to struct flow_cls_offload
* @filter: Pointer to cloud filter structure
*
**/
static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
- struct tc_cls_flower_offload *f,
+ struct flow_cls_offload *f,
struct i40e_cloud_filter *filter)
{
+ struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+ struct flow_dissector *dissector = rule->match.dissector;
u16 n_proto_mask = 0, n_proto_key = 0, addr_type = 0;
struct i40e_pf *pf = vsi->back;
u8 field_flags = 0;
- if (f->dissector->used_keys &
+ if (dissector->used_keys &
~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
BIT(FLOW_DISSECTOR_KEY_BASIC) |
BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -7230,143 +8021,109 @@
BIT(FLOW_DISSECTOR_KEY_PORTS) |
BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n",
- f->dissector->used_keys);
+ dissector->used_keys);
return -EOPNOTSUPP;
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
- struct flow_dissector_key_keyid *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ENC_KEYID,
- f->key);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+ struct flow_match_enc_keyid match;
- struct flow_dissector_key_keyid *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ENC_KEYID,
- f->mask);
-
- if (mask->keyid != 0)
+ flow_rule_match_enc_keyid(rule, &match);
+ if (match.mask->keyid != 0)
field_flags |= I40E_CLOUD_FIELD_TEN_ID;
- filter->tenant_id = be32_to_cpu(key->keyid);
+ filter->tenant_id = be32_to_cpu(match.key->keyid);
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
- struct flow_dissector_key_basic *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->key);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+ struct flow_match_basic match;
- struct flow_dissector_key_basic *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
- f->mask);
-
- n_proto_key = ntohs(key->n_proto);
- n_proto_mask = ntohs(mask->n_proto);
+ flow_rule_match_basic(rule, &match);
+ n_proto_key = ntohs(match.key->n_proto);
+ n_proto_mask = ntohs(match.mask->n_proto);
if (n_proto_key == ETH_P_ALL) {
n_proto_key = 0;
n_proto_mask = 0;
}
filter->n_proto = n_proto_key & n_proto_mask;
- filter->ip_proto = key->ip_proto;
+ filter->ip_proto = match.key->ip_proto;
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
- struct flow_dissector_key_eth_addrs *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ETH_ADDRS,
- f->key);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+ struct flow_match_eth_addrs match;
- struct flow_dissector_key_eth_addrs *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_ETH_ADDRS,
- f->mask);
+ flow_rule_match_eth_addrs(rule, &match);
/* use is_broadcast and is_zero to check for all 0xf or 0 */
- if (!is_zero_ether_addr(mask->dst)) {
- if (is_broadcast_ether_addr(mask->dst)) {
+ if (!is_zero_ether_addr(match.mask->dst)) {
+ if (is_broadcast_ether_addr(match.mask->dst)) {
field_flags |= I40E_CLOUD_FIELD_OMAC;
} else {
dev_err(&pf->pdev->dev, "Bad ether dest mask %pM\n",
- mask->dst);
+ match.mask->dst);
return I40E_ERR_CONFIG;
}
}
- if (!is_zero_ether_addr(mask->src)) {
- if (is_broadcast_ether_addr(mask->src)) {
+ if (!is_zero_ether_addr(match.mask->src)) {
+ if (is_broadcast_ether_addr(match.mask->src)) {
field_flags |= I40E_CLOUD_FIELD_IMAC;
} else {
dev_err(&pf->pdev->dev, "Bad ether src mask %pM\n",
- mask->src);
+ match.mask->src);
return I40E_ERR_CONFIG;
}
}
- ether_addr_copy(filter->dst_mac, key->dst);
- ether_addr_copy(filter->src_mac, key->src);
+ ether_addr_copy(filter->dst_mac, match.key->dst);
+ ether_addr_copy(filter->src_mac, match.key->src);
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
- struct flow_dissector_key_vlan *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_VLAN,
- f->key);
- struct flow_dissector_key_vlan *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_VLAN,
- f->mask);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+ struct flow_match_vlan match;
- if (mask->vlan_id) {
- if (mask->vlan_id == VLAN_VID_MASK) {
+ flow_rule_match_vlan(rule, &match);
+ if (match.mask->vlan_id) {
+ if (match.mask->vlan_id == VLAN_VID_MASK) {
field_flags |= I40E_CLOUD_FIELD_IVLAN;
} else {
dev_err(&pf->pdev->dev, "Bad vlan mask 0x%04x\n",
- mask->vlan_id);
+ match.mask->vlan_id);
return I40E_ERR_CONFIG;
}
}
- filter->vlan_id = cpu_to_be16(key->vlan_id);
+ filter->vlan_id = cpu_to_be16(match.key->vlan_id);
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
- struct flow_dissector_key_control *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_CONTROL,
- f->key);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+ struct flow_match_control match;
- addr_type = key->addr_type;
+ flow_rule_match_control(rule, &match);
+ addr_type = match.key->addr_type;
}
if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
- struct flow_dissector_key_ipv4_addrs *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV4_ADDRS,
- f->key);
- struct flow_dissector_key_ipv4_addrs *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV4_ADDRS,
- f->mask);
+ struct flow_match_ipv4_addrs match;
- if (mask->dst) {
- if (mask->dst == cpu_to_be32(0xffffffff)) {
+ flow_rule_match_ipv4_addrs(rule, &match);
+ if (match.mask->dst) {
+ if (match.mask->dst == cpu_to_be32(0xffffffff)) {
field_flags |= I40E_CLOUD_FIELD_IIP;
} else {
dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4b\n",
- &mask->dst);
+ &match.mask->dst);
return I40E_ERR_CONFIG;
}
}
- if (mask->src) {
- if (mask->src == cpu_to_be32(0xffffffff)) {
+ if (match.mask->src) {
+ if (match.mask->src == cpu_to_be32(0xffffffff)) {
field_flags |= I40E_CLOUD_FIELD_IIP;
} else {
dev_err(&pf->pdev->dev, "Bad ip src mask %pI4b\n",
- &mask->src);
+ &match.mask->src);
return I40E_ERR_CONFIG;
}
}
@@ -7375,70 +8132,60 @@
dev_err(&pf->pdev->dev, "Tenant id not allowed for ip filter\n");
return I40E_ERR_CONFIG;
}
- filter->dst_ipv4 = key->dst;
- filter->src_ipv4 = key->src;
+ filter->dst_ipv4 = match.key->dst;
+ filter->src_ipv4 = match.key->src;
}
if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
- struct flow_dissector_key_ipv6_addrs *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV6_ADDRS,
- f->key);
- struct flow_dissector_key_ipv6_addrs *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_IPV6_ADDRS,
- f->mask);
+ struct flow_match_ipv6_addrs match;
+
+ flow_rule_match_ipv6_addrs(rule, &match);
/* src and dest IPV6 address should not be LOOPBACK
* (0:0:0:0:0:0:0:1), which can be represented as ::1
*/
- if (ipv6_addr_loopback(&key->dst) ||
- ipv6_addr_loopback(&key->src)) {
+ if (ipv6_addr_loopback(&match.key->dst) ||
+ ipv6_addr_loopback(&match.key->src)) {
dev_err(&pf->pdev->dev,
"Bad ipv6, addr is LOOPBACK\n");
return I40E_ERR_CONFIG;
}
- if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src))
+ if (!ipv6_addr_any(&match.mask->dst) ||
+ !ipv6_addr_any(&match.mask->src))
field_flags |= I40E_CLOUD_FIELD_IIP;
- memcpy(&filter->src_ipv6, &key->src.s6_addr32,
+ memcpy(&filter->src_ipv6, &match.key->src.s6_addr32,
sizeof(filter->src_ipv6));
- memcpy(&filter->dst_ipv6, &key->dst.s6_addr32,
+ memcpy(&filter->dst_ipv6, &match.key->dst.s6_addr32,
sizeof(filter->dst_ipv6));
}
- if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
- struct flow_dissector_key_ports *key =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_PORTS,
- f->key);
- struct flow_dissector_key_ports *mask =
- skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_PORTS,
- f->mask);
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+ struct flow_match_ports match;
- if (mask->src) {
- if (mask->src == cpu_to_be16(0xffff)) {
+ flow_rule_match_ports(rule, &match);
+ if (match.mask->src) {
+ if (match.mask->src == cpu_to_be16(0xffff)) {
field_flags |= I40E_CLOUD_FIELD_IIP;
} else {
dev_err(&pf->pdev->dev, "Bad src port mask 0x%04x\n",
- be16_to_cpu(mask->src));
+ be16_to_cpu(match.mask->src));
return I40E_ERR_CONFIG;
}
}
- if (mask->dst) {
- if (mask->dst == cpu_to_be16(0xffff)) {
+ if (match.mask->dst) {
+ if (match.mask->dst == cpu_to_be16(0xffff)) {
field_flags |= I40E_CLOUD_FIELD_IIP;
} else {
dev_err(&pf->pdev->dev, "Bad dst port mask 0x%04x\n",
- be16_to_cpu(mask->dst));
+ be16_to_cpu(match.mask->dst));
return I40E_ERR_CONFIG;
}
}
- filter->dst_port = key->dst;
- filter->src_port = key->src;
+ filter->dst_port = match.key->dst;
+ filter->src_port = match.key->src;
switch (filter->ip_proto) {
case IPPROTO_TCP:
@@ -7492,11 +8239,11 @@
/**
* i40e_configure_clsflower - Configure tc flower filters
* @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
*
**/
static int i40e_configure_clsflower(struct i40e_vsi *vsi,
- struct tc_cls_flower_offload *cls_flower)
+ struct flow_cls_offload *cls_flower)
{
int tc = tc_classid_to_hwtc(vsi->netdev, cls_flower->classid);
struct i40e_cloud_filter *filter = NULL;
@@ -7506,6 +8253,11 @@
if (tc < 0) {
dev_err(&vsi->back->pdev->dev, "Invalid traffic class\n");
return -EOPNOTSUPP;
+ }
+
+ if (!tc) {
+ dev_err(&pf->pdev->dev, "Unable to add filter because of invalid destination");
+ return -EINVAL;
}
if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
@@ -7587,11 +8339,11 @@
/**
* i40e_delete_clsflower - Remove tc flower filters
* @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
*
**/
static int i40e_delete_clsflower(struct i40e_vsi *vsi,
- struct tc_cls_flower_offload *cls_flower)
+ struct flow_cls_offload *cls_flower)
{
struct i40e_cloud_filter *filter = NULL;
struct i40e_pf *pf = vsi->back;
@@ -7630,20 +8382,20 @@
/**
* i40e_setup_tc_cls_flower - flower classifier offloads
- * @netdev: net device to configure
- * @type_data: offload data
+ * @np: net device to configure
+ * @cls_flower: offload data
**/
static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np,
- struct tc_cls_flower_offload *cls_flower)
+ struct flow_cls_offload *cls_flower)
{
struct i40e_vsi *vsi = np->vsi;
switch (cls_flower->command) {
- case TC_CLSFLOWER_REPLACE:
+ case FLOW_CLS_REPLACE:
return i40e_configure_clsflower(vsi, cls_flower);
- case TC_CLSFLOWER_DESTROY:
+ case FLOW_CLS_DESTROY:
return i40e_delete_clsflower(vsi, cls_flower);
- case TC_CLSFLOWER_STATS:
+ case FLOW_CLS_STATS:
return -EOPNOTSUPP;
default:
return -EOPNOTSUPP;
@@ -7667,34 +8419,21 @@
}
}
-static int i40e_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct i40e_netdev_priv *np = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb,
- np, np, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
+static LIST_HEAD(i40e_block_cb_list);
static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
void *type_data)
{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+
switch (type) {
case TC_SETUP_QDISC_MQPRIO:
return i40e_setup_tc(netdev, type_data);
case TC_SETUP_BLOCK:
- return i40e_setup_tc_block(netdev, type_data);
+ return flow_block_cb_setup_simple(type_data,
+ &i40e_block_cb_list,
+ i40e_setup_tc_block_cb,
+ np, np, true);
default:
return -EOPNOTSUPP;
}
@@ -7962,9 +8701,6 @@
{
u32 val;
- WARN_ON(in_interrupt());
-
-
/* do the biggest reset indicated */
if (reset_flags & BIT_ULL(__I40E_GLOBAL_RESET_REQUESTED)) {
@@ -8013,6 +8749,10 @@
*/
i40e_prep_for_reset(pf, lock_acquired);
i40e_reset_and_rebuild(pf, true, lock_acquired);
+ dev_info(&pf->pdev->dev,
+ pf->flags & I40E_FLAG_DISABLE_FW_LLDP ?
+ "FW LLDP is disabled\n" :
+ "FW LLDP is enabled\n");
} else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) {
int v;
@@ -8202,8 +8942,8 @@
i40e_service_event_schedule(pf);
} else {
i40e_pf_unquiesce_all_vsi(pf);
- set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
- set_bit(__I40E_CLIENT_L2_CHANGE, pf->state);
+ set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
+ set_bit(__I40E_CLIENT_L2_CHANGE, pf->state);
}
exit:
@@ -8489,13 +9229,6 @@
return i40e_get_current_fd_count(pf) - pf->fdir_pf_active_filters;
}
-/* We can see up to 256 filter programming desc in transit if the filters are
- * being applied really fast; before we see the first
- * filter miss error on Rx queue 0. Accumulating enough error messages before
- * reacting will make sure we don't cause flush too often.
- */
-#define I40E_MAX_FD_PROGRAM_ERROR 256
-
/**
* i40e_fdir_reinit_subtask - Worker thread to reinit FDIR filter table
* @pf: board private structure
@@ -8585,14 +9318,9 @@
i40e_status status;
bool new_link, old_link;
- /* save off old link status information */
- pf->hw.phy.link_info_old = pf->hw.phy.link_info;
-
/* set this to force the get_link_status call to refresh state */
pf->hw.phy.get_link_info = true;
-
old_link = (pf->hw.phy.link_info_old.link_info & I40E_AQ_LINK_UP);
-
status = i40e_get_link_status(&pf->hw, &new_link);
/* On success, disable temp link polling */
@@ -8622,7 +9350,7 @@
/* Notify the base of the switch tree connected to
* the link. Floating VEBs are not notified.
*/
- if (pf->lan_veb != I40E_NO_VEB && pf->veb[pf->lan_veb])
+ if (pf->lan_veb < I40E_MAX_VEB && pf->veb[pf->lan_veb])
i40e_veb_link_event(pf->veb[pf->lan_veb], new_link);
else
i40e_vsi_link_event(vsi, new_link);
@@ -9100,6 +9828,7 @@
/**
* i40e_get_capabilities - get info about the HW
* @pf: the PF struct
+ * @list_type: AQ capability to be queried
**/
static int i40e_get_capabilities(struct i40e_pf *pf,
enum i40e_admin_queue_opc list_type)
@@ -9337,6 +10066,21 @@
}
/**
+ * i40e_clean_xps_state - clean xps state for every tx_ring
+ * @vsi: ptr to the VSI
+ **/
+static void i40e_clean_xps_state(struct i40e_vsi *vsi)
+{
+ int i;
+
+ if (vsi->tx_rings)
+ for (i = 0; i < vsi->num_queue_pairs; i++)
+ if (vsi->tx_rings[i])
+ clear_bit(__I40E_TX_XPS_INIT_DONE,
+ vsi->tx_rings[i]->state);
+}
+
+/**
* i40e_prep_for_reset - prep for the core to reset
* @pf: board private structure
* @lock_acquired: indicates whether or not the lock has been acquired
@@ -9367,8 +10111,10 @@
rtnl_unlock();
for (v = 0; v < pf->num_alloc_vsi; v++) {
- if (pf->vsi[v])
+ if (pf->vsi[v]) {
+ i40e_clean_xps_state(pf->vsi[v]);
pf->vsi[v]->seid = 0;
+ }
}
i40e_shutdown_adminq(&pf->hw);
@@ -9380,6 +10126,11 @@
dev_warn(&pf->pdev->dev,
"shutdown_lan_hmc failed: %d\n", ret);
}
+
+ /* Save the current PTP time so that we can restore the time after the
+ * reset completes.
+ */
+ i40e_ptp_save_hw_time(pf);
}
/**
@@ -9390,11 +10141,11 @@
{
struct i40e_driver_version dv;
- dv.major_version = DRV_VERSION_MAJOR;
- dv.minor_version = DRV_VERSION_MINOR;
- dv.build_version = DRV_VERSION_BUILD;
+ dv.major_version = 0xff;
+ dv.minor_version = 0xff;
+ dv.build_version = 0xff;
dv.subbuild_version = 0;
- strlcpy(dv.driver_string, DRV_VERSION, sizeof(dv.driver_string));
+ strlcpy(dv.driver_string, UTS_RELEASE, sizeof(dv.driver_string));
i40e_aq_send_driver_version(&pf->hw, &dv, NULL);
}
@@ -9472,13 +10223,19 @@
**/
static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
{
+ const bool is_recovery_mode_reported = i40e_check_recovery_mode(pf);
struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
struct i40e_hw *hw = &pf->hw;
i40e_status ret;
u32 val;
int v;
- if (test_bit(__I40E_DOWN, pf->state))
+ if (test_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state) &&
+ is_recovery_mode_reported)
+ i40e_set_ethtool_ops(pf->vsi[pf->lan_vsi]->netdev);
+
+ if (test_bit(__I40E_DOWN, pf->state) &&
+ !test_bit(__I40E_RECOVERY_MODE, pf->state))
goto clear_recovery;
dev_dbg(&pf->pdev->dev, "Rebuilding internal switch\n");
@@ -9500,6 +10257,43 @@
/* re-verify the eeprom if we just had an EMP reset */
if (test_and_clear_bit(__I40E_EMP_RESET_INTR_RECEIVED, pf->state))
i40e_verify_eeprom(pf);
+
+ /* if we are going out of or into recovery mode we have to act
+ * accordingly with regard to resources initialization
+ * and deinitialization
+ */
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+ if (i40e_get_capabilities(pf,
+ i40e_aqc_opc_list_func_capabilities))
+ goto end_unlock;
+
+ if (is_recovery_mode_reported) {
+ /* we're staying in recovery mode so we'll reinitialize
+ * misc vector here
+ */
+ if (i40e_setup_misc_vector_for_recovery_mode(pf))
+ goto end_unlock;
+ } else {
+ if (!lock_acquired)
+ rtnl_lock();
+ /* we're going out of recovery mode so we'll free
+ * the IRQ allocated specifically for recovery mode
+ * and restore the interrupt scheme
+ */
+ free_irq(pf->pdev->irq, pf);
+ i40e_clear_interrupt_scheme(pf);
+ if (i40e_restore_interrupt_scheme(pf))
+ goto end_unlock;
+ }
+
+ /* tell the firmware that we're starting */
+ i40e_send_version(pf);
+
+ /* bail out in case recovery mode was detected, as there is
+ * no need for further configuration.
+ */
+ goto end_unlock;
+ }
i40e_clear_pxe_mode(hw);
ret = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
@@ -9532,7 +10326,7 @@
/* do basic switch setup */
if (!lock_acquired)
rtnl_lock();
- ret = i40e_setup_pf_switch(pf, reinit);
+ ret = i40e_setup_pf_switch(pf, reinit, true);
if (ret)
goto end_unlock;
@@ -9602,10 +10396,10 @@
}
if (vsi->mqprio_qopt.max_rate[0]) {
- u64 max_tx_rate = vsi->mqprio_qopt.max_rate[0];
+ u64 max_tx_rate = i40e_bw_bytes_to_mbits(vsi,
+ vsi->mqprio_qopt.max_rate[0]);
u64 credits = 0;
- do_div(max_tx_rate, I40E_BW_MBPS_DIVISOR);
ret = i40e_set_bw_limit(vsi, vsi->seid, max_tx_rate);
if (ret)
goto end_unlock;
@@ -9745,7 +10539,6 @@
{
struct i40e_hw *hw = &pf->hw;
bool mdd_detected = false;
- bool pf_mdd_detected = false;
struct i40e_vf *vf;
u32 reg;
int i;
@@ -9791,19 +10584,12 @@
reg = rd32(hw, I40E_PF_MDET_TX);
if (reg & I40E_PF_MDET_TX_VALID_MASK) {
wr32(hw, I40E_PF_MDET_TX, 0xFFFF);
- dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n");
- pf_mdd_detected = true;
+ dev_dbg(&pf->pdev->dev, "TX driver issue detected on PF\n");
}
reg = rd32(hw, I40E_PF_MDET_RX);
if (reg & I40E_PF_MDET_RX_VALID_MASK) {
wr32(hw, I40E_PF_MDET_RX, 0xFFFF);
- dev_info(&pf->pdev->dev, "RX driver issue detected, PF reset issued\n");
- pf_mdd_detected = true;
- }
- /* Queue belongs to the PF, initiate a reset */
- if (pf_mdd_detected) {
- set_bit(__I40E_PF_RESET_REQUESTED, pf->state);
- i40e_service_event_schedule(pf);
+ dev_dbg(&pf->pdev->dev, "RX driver issue detected on PF\n");
}
}
@@ -9816,6 +10602,9 @@
vf->num_mdd_events++;
dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n",
i);
+ dev_info(&pf->pdev->dev,
+ "Use PF Control I/F to re-enable the VF\n");
+ set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
}
reg = rd32(hw, I40E_VP_MDET_RX(i));
@@ -9824,11 +10613,6 @@
vf->num_mdd_events++;
dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n",
i);
- }
-
- if (vf->num_mdd_events > I40E_DEFAULT_NUM_MDD_EVENTS_ALLOWED) {
- dev_info(&pf->pdev->dev,
- "Too many MDD events on VF %d, disabled\n", i);
dev_info(&pf->pdev->dev,
"Use PF Control I/F to re-enable the VF\n");
set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states);
@@ -9843,106 +10627,6 @@
i40e_flush(hw);
}
-static const char *i40e_tunnel_name(u8 type)
-{
- switch (type) {
- case UDP_TUNNEL_TYPE_VXLAN:
- return "vxlan";
- case UDP_TUNNEL_TYPE_GENEVE:
- return "geneve";
- default:
- return "unknown";
- }
-}
-
-/**
- * i40e_sync_udp_filters - Trigger a sync event for existing UDP filters
- * @pf: board private structure
- **/
-static void i40e_sync_udp_filters(struct i40e_pf *pf)
-{
- int i;
-
- /* loop through and set pending bit for all active UDP filters */
- for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
- if (pf->udp_ports[i].port)
- pf->pending_udp_bitmap |= BIT_ULL(i);
- }
-
- set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state);
-}
-
-/**
- * i40e_sync_udp_filters_subtask - Sync the VSI filter list with HW
- * @pf: board private structure
- **/
-static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf)
-{
- struct i40e_hw *hw = &pf->hw;
- u8 filter_index, type;
- u16 port;
- int i;
-
- if (!test_and_clear_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state))
- return;
-
- /* acquire RTNL to maintain state of flags and port requests */
- rtnl_lock();
-
- for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
- if (pf->pending_udp_bitmap & BIT_ULL(i)) {
- struct i40e_udp_port_config *udp_port;
- i40e_status ret = 0;
-
- udp_port = &pf->udp_ports[i];
- pf->pending_udp_bitmap &= ~BIT_ULL(i);
-
- port = READ_ONCE(udp_port->port);
- type = READ_ONCE(udp_port->type);
- filter_index = READ_ONCE(udp_port->filter_index);
-
- /* release RTNL while we wait on AQ command */
- rtnl_unlock();
-
- if (port)
- ret = i40e_aq_add_udp_tunnel(hw, port,
- type,
- &filter_index,
- NULL);
- else if (filter_index != I40E_UDP_PORT_INDEX_UNUSED)
- ret = i40e_aq_del_udp_tunnel(hw, filter_index,
- NULL);
-
- /* reacquire RTNL so we can update filter_index */
- rtnl_lock();
-
- if (ret) {
- dev_info(&pf->pdev->dev,
- "%s %s port %d, index %d failed, err %s aq_err %s\n",
- i40e_tunnel_name(type),
- port ? "add" : "delete",
- port,
- filter_index,
- i40e_stat_str(&pf->hw, ret),
- i40e_aq_str(&pf->hw,
- pf->hw.aq.asq_last_status));
- if (port) {
- /* failed to add, just reset port,
- * drop pending bit for any deletion
- */
- udp_port->port = 0;
- pf->pending_udp_bitmap &= ~BIT_ULL(i);
- }
- } else if (port) {
- /* record filter index on success */
- udp_port->filter_index = filter_index;
- }
- }
- }
-
- rtnl_unlock();
-}
-
/**
* i40e_service_task - Run the driver's async subtasks
* @work: pointer to work_struct containing our data
@@ -9955,31 +10639,37 @@
unsigned long start_time = jiffies;
/* don't bother with service tasks if a reset is in progress */
- if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state))
+ if (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state) ||
+ test_bit(__I40E_SUSPENDED, pf->state))
return;
if (test_and_set_bit(__I40E_SERVICE_SCHED, pf->state))
return;
- i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]);
- i40e_sync_filters_subtask(pf);
- i40e_reset_subtask(pf);
- i40e_handle_mdd_event(pf);
- i40e_vc_process_vflr_event(pf);
- i40e_watchdog_subtask(pf);
- i40e_fdir_reinit_subtask(pf);
- if (test_and_clear_bit(__I40E_CLIENT_RESET, pf->state)) {
- /* Client subtask will reopen next time through. */
- i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi], true);
+ if (!test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+ i40e_detect_recover_hung(pf->vsi[pf->lan_vsi]);
+ i40e_sync_filters_subtask(pf);
+ i40e_reset_subtask(pf);
+ i40e_handle_mdd_event(pf);
+ i40e_vc_process_vflr_event(pf);
+ i40e_watchdog_subtask(pf);
+ i40e_fdir_reinit_subtask(pf);
+ if (test_and_clear_bit(__I40E_CLIENT_RESET, pf->state)) {
+ /* Client subtask will reopen next time through. */
+ i40e_notify_client_of_netdev_close(pf->vsi[pf->lan_vsi],
+ true);
+ } else {
+ i40e_client_subtask(pf);
+ if (test_and_clear_bit(__I40E_CLIENT_L2_CHANGE,
+ pf->state))
+ i40e_notify_client_of_l2_param_changes(
+ pf->vsi[pf->lan_vsi]);
+ }
+ i40e_sync_filters_subtask(pf);
} else {
- i40e_client_subtask(pf);
- if (test_and_clear_bit(__I40E_CLIENT_L2_CHANGE,
- pf->state))
- i40e_notify_client_of_l2_param_changes(
- pf->vsi[pf->lan_vsi]);
+ i40e_reset_subtask(pf);
}
- i40e_sync_filters_subtask(pf);
- i40e_sync_udp_filters_subtask(pf);
+
i40e_clean_adminq_subtask(pf);
/* flush memory to make sure state is correct before next watchdog */
@@ -9999,7 +10689,7 @@
/**
* i40e_service_timer - timer callback
- * @data: pointer to PF struct
+ * @t: timer list pointer
**/
static void i40e_service_timer(struct timer_list *t)
{
@@ -10021,8 +10711,12 @@
switch (vsi->type) {
case I40E_VSI_MAIN:
vsi->alloc_queue_pairs = pf->num_lan_qps;
- vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
- I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_tx_desc)
+ vsi->num_tx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_rx_desc)
+ vsi->num_rx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
if (pf->flags & I40E_FLAG_MSIX_ENABLED)
vsi->num_q_vectors = pf->num_lan_msix;
else
@@ -10032,22 +10726,32 @@
case I40E_VSI_FDIR:
vsi->alloc_queue_pairs = 1;
- vsi->num_desc = ALIGN(I40E_FDIR_RING_COUNT,
- I40E_REQ_DESCRIPTOR_MULTIPLE);
+ vsi->num_tx_desc = ALIGN(I40E_FDIR_RING_COUNT,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ vsi->num_rx_desc = ALIGN(I40E_FDIR_RING_COUNT,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
vsi->num_q_vectors = pf->num_fdsb_msix;
break;
case I40E_VSI_VMDQ2:
vsi->alloc_queue_pairs = pf->num_vmdq_qps;
- vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
- I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_tx_desc)
+ vsi->num_tx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_rx_desc)
+ vsi->num_rx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
vsi->num_q_vectors = pf->num_vmdq_msix;
break;
case I40E_VSI_SRIOV:
vsi->alloc_queue_pairs = pf->num_vf_qps;
- vsi->num_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
- I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_tx_desc)
+ vsi->num_tx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
+ if (!vsi->num_rx_desc)
+ vsi->num_rx_desc = ALIGN(I40E_DEFAULT_NUM_DESCRIPTORS,
+ I40E_REQ_DESCRIPTOR_MULTIPLE);
break;
default:
@@ -10160,6 +10864,12 @@
hash_init(vsi->mac_filter_hash);
vsi->irqs_ready = false;
+ if (type == I40E_VSI_MAIN) {
+ vsi->af_xdp_zc_qps = bitmap_zalloc(pf->num_lan_qps, GFP_KERNEL);
+ if (!vsi->af_xdp_zc_qps)
+ goto err_rings;
+ }
+
ret = i40e_set_num_rings_in_vsi(vsi);
if (ret)
goto err_rings;
@@ -10178,6 +10888,7 @@
goto unlock_pf;
err_rings:
+ bitmap_free(vsi->af_xdp_zc_qps);
pf->next_vsi = i - 1;
kfree(vsi);
unlock_pf:
@@ -10258,6 +10969,7 @@
i40e_put_lump(pf->qp_pile, vsi->base_queue, vsi->idx);
i40e_put_lump(pf->irq_pile, vsi->base_vector, vsi->idx);
+ bitmap_free(vsi->af_xdp_zc_qps);
i40e_vsi_free_arrays(vsi, true);
i40e_clear_rss_config_user(vsi);
@@ -10315,7 +11027,7 @@
ring->vsi = vsi;
ring->netdev = vsi->netdev;
ring->dev = &pf->pdev->dev;
- ring->count = vsi->num_desc;
+ ring->count = vsi->num_tx_desc;
ring->size = 0;
ring->dcb_tc = 0;
if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE)
@@ -10332,7 +11044,7 @@
ring->vsi = vsi;
ring->netdev = NULL;
ring->dev = &pf->pdev->dev;
- ring->count = vsi->num_desc;
+ ring->count = vsi->num_tx_desc;
ring->size = 0;
ring->dcb_tc = 0;
if (vsi->back->hw_features & I40E_HW_WB_ON_ITR_CAPABLE)
@@ -10348,7 +11060,7 @@
ring->vsi = vsi;
ring->netdev = vsi->netdev;
ring->dev = &pf->pdev->dev;
- ring->count = vsi->num_desc;
+ ring->count = vsi->num_rx_desc;
ring->size = 0;
ring->dcb_tc = 0;
ring->itr_setting = pf->rx_itr_default;
@@ -10616,11 +11328,10 @@
* i40e_vsi_alloc_q_vector - Allocate memory for a single interrupt vector
* @vsi: the VSI being configured
* @v_idx: index of the vector in the vsi struct
- * @cpu: cpu to be used on affinity_mask
*
* We allocate one q_vector. If allocation fails we return -ENOMEM.
**/
-static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu)
+static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx)
{
struct i40e_q_vector *q_vector;
@@ -10653,7 +11364,7 @@
static int i40e_vsi_alloc_q_vectors(struct i40e_vsi *vsi)
{
struct i40e_pf *pf = vsi->back;
- int err, v_idx, num_q_vectors, current_cpu;
+ int err, v_idx, num_q_vectors;
/* if not MSIX, give the one vector only to the LAN VSI */
if (pf->flags & I40E_FLAG_MSIX_ENABLED)
@@ -10663,15 +11374,10 @@
else
return -EINVAL;
- current_cpu = cpumask_first(cpu_online_mask);
-
for (v_idx = 0; v_idx < num_q_vectors; v_idx++) {
- err = i40e_vsi_alloc_q_vector(vsi, v_idx, current_cpu);
+ err = i40e_vsi_alloc_q_vector(vsi, v_idx);
if (err)
goto err_out;
- current_cpu = cpumask_next(current_cpu, cpu_online_mask);
- if (unlikely(current_cpu >= nr_cpu_ids))
- current_cpu = cpumask_first(cpu_online_mask);
}
return 0;
@@ -10793,6 +11499,48 @@
}
/**
+ * i40e_setup_misc_vector_for_recovery_mode - Setup the misc vector to handle
+ * non queue events in recovery mode
+ * @pf: board private structure
+ *
+ * This sets up the handler for MSIX 0 or MSI/legacy, which is used to manage
+ * the non-queue interrupts, e.g. AdminQ and errors in recovery mode.
+ * This is handled differently than in recovery mode since no Tx/Rx resources
+ * are being allocated.
+ **/
+static int i40e_setup_misc_vector_for_recovery_mode(struct i40e_pf *pf)
+{
+ int err;
+
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ err = i40e_setup_misc_vector(pf);
+
+ if (err) {
+ dev_info(&pf->pdev->dev,
+ "MSI-X misc vector request failed, error %d\n",
+ err);
+ return err;
+ }
+ } else {
+ u32 flags = pf->flags & I40E_FLAG_MSI_ENABLED ? 0 : IRQF_SHARED;
+
+ err = request_irq(pf->pdev->irq, i40e_intr, flags,
+ pf->int_name, pf);
+
+ if (err) {
+ dev_info(&pf->pdev->dev,
+ "MSI/legacy misc vector request failed, error %d\n",
+ err);
+ return err;
+ }
+ i40e_enable_misc_int_causes(pf);
+ i40e_irq_dynamic_enable_icr0(pf);
+ }
+
+ return 0;
+}
+
+/**
* i40e_setup_misc_vector - Setup the misc vector to handle non queue events
* @pf: board private structure
*
@@ -10861,7 +11609,7 @@
}
if (lut) {
- bool pf_lut = vsi->type == I40E_VSI_MAIN ? true : false;
+ bool pf_lut = vsi->type == I40E_VSI_MAIN;
ret = i40e_aq_get_rss_lut(hw, vsi->id, pf_lut, lut, lut_size);
if (ret) {
@@ -11103,6 +11851,7 @@
if (!(pf->flags & I40E_FLAG_RSS_ENABLED))
return 0;
+ queue_count = min_t(int, queue_count, num_online_cpus());
new_rss_size = min_t(int, queue_count, pf->rss_size_max);
if (queue_count != vsi->num_queue_pairs) {
@@ -11264,6 +12013,58 @@
}
/**
+ * i40e_is_total_port_shutdown_enabled - read NVM and return value
+ * if total port shutdown feature is enabled for this PF
+ * @pf: board private structure
+ **/
+static bool i40e_is_total_port_shutdown_enabled(struct i40e_pf *pf)
+{
+#define I40E_TOTAL_PORT_SHUTDOWN_ENABLED BIT(4)
+#define I40E_FEATURES_ENABLE_PTR 0x2A
+#define I40E_CURRENT_SETTING_PTR 0x2B
+#define I40E_LINK_BEHAVIOR_WORD_OFFSET 0x2D
+#define I40E_LINK_BEHAVIOR_WORD_LENGTH 0x1
+#define I40E_LINK_BEHAVIOR_OS_FORCED_ENABLED BIT(0)
+#define I40E_LINK_BEHAVIOR_PORT_BIT_LENGTH 4
+ i40e_status read_status = I40E_SUCCESS;
+ u16 sr_emp_sr_settings_ptr = 0;
+ u16 features_enable = 0;
+ u16 link_behavior = 0;
+ bool ret = false;
+
+ read_status = i40e_read_nvm_word(&pf->hw,
+ I40E_SR_EMP_SR_SETTINGS_PTR,
+ &sr_emp_sr_settings_ptr);
+ if (read_status)
+ goto err_nvm;
+ read_status = i40e_read_nvm_word(&pf->hw,
+ sr_emp_sr_settings_ptr +
+ I40E_FEATURES_ENABLE_PTR,
+ &features_enable);
+ if (read_status)
+ goto err_nvm;
+ if (I40E_TOTAL_PORT_SHUTDOWN_ENABLED & features_enable) {
+ read_status = i40e_read_nvm_module_data(&pf->hw,
+ I40E_SR_EMP_SR_SETTINGS_PTR,
+ I40E_CURRENT_SETTING_PTR,
+ I40E_LINK_BEHAVIOR_WORD_OFFSET,
+ I40E_LINK_BEHAVIOR_WORD_LENGTH,
+ &link_behavior);
+ if (read_status)
+ goto err_nvm;
+ link_behavior >>= (pf->hw.port * I40E_LINK_BEHAVIOR_PORT_BIT_LENGTH);
+ ret = I40E_LINK_BEHAVIOR_OS_FORCED_ENABLED & link_behavior;
+ }
+ return ret;
+
+err_nvm:
+ dev_warn(&pf->pdev->dev,
+ "total-port-shutdown feature is off due to read nvm error: %s\n",
+ i40e_stat_str(&pf->hw, read_status));
+ return ret;
+}
+
+/**
* i40e_sw_init - Initialize general software structures (struct i40e_pf)
* @pf: board private structure to initialize
*
@@ -11405,16 +12206,15 @@
/* IWARP needs one extra vector for CQP just like MISC.*/
pf->num_iwarp_msix = (int)num_online_cpus() + 1;
}
- /* Stopping the FW LLDP engine is only supported on the
- * XL710 with a FW ver >= 1.7. Also, stopping FW LLDP
- * engine is not supported if NPAR is functioning on this
- * part
+ /* Stopping FW LLDP engine is supported on XL710 and X722
+ * starting from FW versions determined in i40e_init_adminq.
+ * Stopping the FW LLDP engine is not supported on XL710
+ * if NPAR is functioning so unset this hw flag in this case.
*/
if (pf->hw.mac.type == I40E_MAC_XL710 &&
- !pf->hw.func_caps.npar_enable &&
- (pf->hw.aq.api_maj_ver > 1 ||
- (pf->hw.aq.api_maj_ver == 1 && pf->hw.aq.api_min_ver > 6)))
- pf->hw_features |= I40E_HW_STOPPABLE_FW_LLDP;
+ pf->hw.func_caps.npar_enable &&
+ (pf->hw.flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE))
+ pf->hw.flags &= ~I40E_HW_FLAG_FW_LLDP_STOPPABLE;
#ifdef CONFIG_PCI_IOV
if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) {
@@ -11444,6 +12244,16 @@
pf->tx_timeout_recovery_level = 1;
+ if (pf->hw.mac.type != I40E_MAC_X722 &&
+ i40e_is_total_port_shutdown_enabled(pf)) {
+ /* Link down on close must be on when total port shutdown
+ * is enabled for a given port
+ */
+ pf->flags |= (I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED |
+ I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED);
+ dev_info(&pf->pdev->dev,
+ "total-port-shutdown was enabled, link-down-on-close is forced on\n");
+ }
mutex_init(&pf->switch_mutex);
sw_init_done:
@@ -11550,6 +12360,9 @@
return -EINVAL;
}
+ if (!(features & NETIF_F_HW_L2FW_DOFFLOAD) && vsi->macvlan_cnt)
+ i40e_del_all_macvlans(vsi);
+
need_reset = i40e_set_ntuple(pf, features);
if (need_reset)
@@ -11558,131 +12371,48 @@
return 0;
}
-/**
- * i40e_get_udp_port_idx - Lookup a possibly offloaded for Rx UDP port
- * @pf: board private structure
- * @port: The UDP port to look up
- *
- * Returns the index number or I40E_MAX_PF_UDP_OFFLOAD_PORTS if port not found
- **/
-static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, u16 port)
-{
- u8 i;
-
- for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) {
- /* Do not report ports with pending deletions as
- * being available.
- */
- if (!port && (pf->pending_udp_bitmap & BIT_ULL(i)))
- continue;
- if (pf->udp_ports[i].port == port)
- return i;
- }
-
- return i;
-}
-
-/**
- * i40e_udp_tunnel_add - Get notifications about UDP tunnel ports that come up
- * @netdev: This physical port's netdev
- * @ti: Tunnel endpoint information
- **/
-static void i40e_udp_tunnel_add(struct net_device *netdev,
- struct udp_tunnel_info *ti)
+static int i40e_udp_tunnel_set_port(struct net_device *netdev,
+ unsigned int table, unsigned int idx,
+ struct udp_tunnel_info *ti)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
- struct i40e_vsi *vsi = np->vsi;
- struct i40e_pf *pf = vsi->back;
- u16 port = ntohs(ti->port);
- u8 next_idx;
- u8 idx;
+ struct i40e_hw *hw = &np->vsi->back->hw;
+ u8 type, filter_index;
+ i40e_status ret;
- idx = i40e_get_udp_port_idx(pf, port);
+ type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? I40E_AQC_TUNNEL_TYPE_VXLAN :
+ I40E_AQC_TUNNEL_TYPE_NGE;
- /* Check if port already exists */
- if (idx < I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
- netdev_info(netdev, "port %d already offloaded\n", port);
- return;
+ ret = i40e_aq_add_udp_tunnel(hw, ntohs(ti->port), type, &filter_index,
+ NULL);
+ if (ret) {
+ netdev_info(netdev, "add UDP port failed, err %s aq_err %s\n",
+ i40e_stat_str(hw, ret),
+ i40e_aq_str(hw, hw->aq.asq_last_status));
+ return -EIO;
}
- /* Now check if there is space to add the new port */
- next_idx = i40e_get_udp_port_idx(pf, 0);
-
- if (next_idx == I40E_MAX_PF_UDP_OFFLOAD_PORTS) {
- netdev_info(netdev, "maximum number of offloaded UDP ports reached, not adding port %d\n",
- port);
- return;
- }
-
- switch (ti->type) {
- case UDP_TUNNEL_TYPE_VXLAN:
- pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_VXLAN;
- break;
- case UDP_TUNNEL_TYPE_GENEVE:
- if (!(pf->hw_features & I40E_HW_GENEVE_OFFLOAD_CAPABLE))
- return;
- pf->udp_ports[next_idx].type = I40E_AQC_TUNNEL_TYPE_NGE;
- break;
- default:
- return;
- }
-
- /* New port: add it and mark its index in the bitmap */
- pf->udp_ports[next_idx].port = port;
- pf->udp_ports[next_idx].filter_index = I40E_UDP_PORT_INDEX_UNUSED;
- pf->pending_udp_bitmap |= BIT_ULL(next_idx);
- set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state);
+ udp_tunnel_nic_set_port_priv(netdev, table, idx, filter_index);
+ return 0;
}
-/**
- * i40e_udp_tunnel_del - Get notifications about UDP tunnel ports that go away
- * @netdev: This physical port's netdev
- * @ti: Tunnel endpoint information
- **/
-static void i40e_udp_tunnel_del(struct net_device *netdev,
- struct udp_tunnel_info *ti)
+static int i40e_udp_tunnel_unset_port(struct net_device *netdev,
+ unsigned int table, unsigned int idx,
+ struct udp_tunnel_info *ti)
{
struct i40e_netdev_priv *np = netdev_priv(netdev);
- struct i40e_vsi *vsi = np->vsi;
- struct i40e_pf *pf = vsi->back;
- u16 port = ntohs(ti->port);
- u8 idx;
+ struct i40e_hw *hw = &np->vsi->back->hw;
+ i40e_status ret;
- idx = i40e_get_udp_port_idx(pf, port);
-
- /* Check if port already exists */
- if (idx >= I40E_MAX_PF_UDP_OFFLOAD_PORTS)
- goto not_found;
-
- switch (ti->type) {
- case UDP_TUNNEL_TYPE_VXLAN:
- if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_VXLAN)
- goto not_found;
- break;
- case UDP_TUNNEL_TYPE_GENEVE:
- if (pf->udp_ports[idx].type != I40E_AQC_TUNNEL_TYPE_NGE)
- goto not_found;
- break;
- default:
- goto not_found;
+ ret = i40e_aq_del_udp_tunnel(hw, ti->hw_priv, NULL);
+ if (ret) {
+ netdev_info(netdev, "delete UDP port failed, err %s aq_err %s\n",
+ i40e_stat_str(hw, ret),
+ i40e_aq_str(hw, hw->aq.asq_last_status));
+ return -EIO;
}
- /* if port exists, set it to 0 (mark for deletion)
- * and make it pending
- */
- pf->udp_ports[idx].port = 0;
-
- /* Toggle pending bit instead of setting it. This way if we are
- * deleting a port that has yet to be added we just clear the pending
- * bit and don't have to worry about it.
- */
- pf->pending_udp_bitmap ^= BIT_ULL(idx);
- set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state);
-
- return;
-not_found:
- netdev_warn(netdev, "UDP port %d was not found, not deleting\n",
- port);
+ return 0;
}
static int i40e_get_phys_port_id(struct net_device *netdev,
@@ -11709,11 +12439,13 @@
* @addr: the MAC address entry being added
* @vid: VLAN ID
* @flags: instructions from stack about fdb operation
+ * @extack: netlink extended ack, unused currently
*/
static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid,
- u16 flags)
+ u16 flags,
+ struct netlink_ext_ack *extack)
{
struct i40e_netdev_priv *np = netdev_priv(dev);
struct i40e_pf *pf = np->vsi->back;
@@ -11754,6 +12486,7 @@
* @dev: the netdev being configured
* @nlh: RTNL message
* @flags: bridge flags
+ * @extack: netlink extended ack
*
* Inserts a new hardware bridge if not already created and
* enables the bridging mode requested (VEB or VEPA). If the
@@ -11766,7 +12499,8 @@
**/
static int i40e_ndo_bridge_setlink(struct net_device *dev,
struct nlmsghdr *nlh,
- u16 flags)
+ u16 flags,
+ struct netlink_ext_ack *extack)
{
struct i40e_netdev_priv *np = netdev_priv(dev);
struct i40e_vsi *vsi = np->vsi;
@@ -11953,8 +12687,20 @@
old_prog = xchg(&vsi->xdp_prog, prog);
- if (need_reset)
+ if (need_reset) {
+ if (!prog)
+ /* Wait until ndo_xsk_wakeup completes. */
+ synchronize_rcu();
i40e_reset_and_rebuild(pf, true, true);
+ }
+
+ if (!i40e_enabled_xdp_vsi(vsi) && prog) {
+ if (i40e_realloc_rx_bi_zc(vsi, true))
+ return -ENOMEM;
+ } else if (i40e_enabled_xdp_vsi(vsi) && !prog) {
+ if (i40e_realloc_rx_bi_zc(vsi, false))
+ return -ENOMEM;
+ }
for (i = 0; i < vsi->num_queue_pairs; i++)
WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog);
@@ -11962,7 +12708,272 @@
if (old_prog)
bpf_prog_put(old_prog);
+ /* Kick start the NAPI context if there is an AF_XDP socket open
+ * on that queue id. This so that receiving will start.
+ */
+ if (need_reset && prog)
+ for (i = 0; i < vsi->num_queue_pairs; i++)
+ if (vsi->xdp_rings[i]->xsk_pool)
+ (void)i40e_xsk_wakeup(vsi->netdev, i,
+ XDP_WAKEUP_RX);
+
return 0;
+}
+
+/**
+ * i40e_enter_busy_conf - Enters busy config state
+ * @vsi: vsi
+ *
+ * Returns 0 on success, <0 for failure.
+ **/
+static int i40e_enter_busy_conf(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+ int timeout = 50;
+
+ while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) {
+ timeout--;
+ if (!timeout)
+ return -EBUSY;
+ usleep_range(1000, 2000);
+ }
+
+ return 0;
+}
+
+/**
+ * i40e_exit_busy_conf - Exits busy config state
+ * @vsi: vsi
+ **/
+static void i40e_exit_busy_conf(struct i40e_vsi *vsi)
+{
+ struct i40e_pf *pf = vsi->back;
+
+ clear_bit(__I40E_CONFIG_BUSY, pf->state);
+}
+
+/**
+ * i40e_queue_pair_reset_stats - Resets all statistics for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ **/
+static void i40e_queue_pair_reset_stats(struct i40e_vsi *vsi, int queue_pair)
+{
+ memset(&vsi->rx_rings[queue_pair]->rx_stats, 0,
+ sizeof(vsi->rx_rings[queue_pair]->rx_stats));
+ memset(&vsi->tx_rings[queue_pair]->stats, 0,
+ sizeof(vsi->tx_rings[queue_pair]->stats));
+ if (i40e_enabled_xdp_vsi(vsi)) {
+ memset(&vsi->xdp_rings[queue_pair]->stats, 0,
+ sizeof(vsi->xdp_rings[queue_pair]->stats));
+ }
+}
+
+/**
+ * i40e_queue_pair_clean_rings - Cleans all the rings of a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ **/
+static void i40e_queue_pair_clean_rings(struct i40e_vsi *vsi, int queue_pair)
+{
+ i40e_clean_tx_ring(vsi->tx_rings[queue_pair]);
+ if (i40e_enabled_xdp_vsi(vsi)) {
+ /* Make sure that in-progress ndo_xdp_xmit calls are
+ * completed.
+ */
+ synchronize_rcu();
+ i40e_clean_tx_ring(vsi->xdp_rings[queue_pair]);
+ }
+ i40e_clean_rx_ring(vsi->rx_rings[queue_pair]);
+}
+
+/**
+ * i40e_queue_pair_toggle_napi - Enables/disables NAPI for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ * @enable: true for enable, false for disable
+ **/
+static void i40e_queue_pair_toggle_napi(struct i40e_vsi *vsi, int queue_pair,
+ bool enable)
+{
+ struct i40e_ring *rxr = vsi->rx_rings[queue_pair];
+ struct i40e_q_vector *q_vector = rxr->q_vector;
+
+ if (!vsi->netdev)
+ return;
+
+ /* All rings in a qp belong to the same qvector. */
+ if (q_vector->rx.ring || q_vector->tx.ring) {
+ if (enable)
+ napi_enable(&q_vector->napi);
+ else
+ napi_disable(&q_vector->napi);
+ }
+}
+
+/**
+ * i40e_queue_pair_toggle_rings - Enables/disables all rings for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ * @enable: true for enable, false for disable
+ *
+ * Returns 0 on success, <0 on failure.
+ **/
+static int i40e_queue_pair_toggle_rings(struct i40e_vsi *vsi, int queue_pair,
+ bool enable)
+{
+ struct i40e_pf *pf = vsi->back;
+ int pf_q, ret = 0;
+
+ pf_q = vsi->base_queue + queue_pair;
+ ret = i40e_control_wait_tx_q(vsi->seid, pf, pf_q,
+ false /*is xdp*/, enable);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "VSI seid %d Tx ring %d %sable timeout\n",
+ vsi->seid, pf_q, (enable ? "en" : "dis"));
+ return ret;
+ }
+
+ i40e_control_rx_q(pf, pf_q, enable);
+ ret = i40e_pf_rxq_wait(pf, pf_q, enable);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "VSI seid %d Rx ring %d %sable timeout\n",
+ vsi->seid, pf_q, (enable ? "en" : "dis"));
+ return ret;
+ }
+
+ /* Due to HW errata, on Rx disable only, the register can
+ * indicate done before it really is. Needs 50ms to be sure
+ */
+ if (!enable)
+ mdelay(50);
+
+ if (!i40e_enabled_xdp_vsi(vsi))
+ return ret;
+
+ ret = i40e_control_wait_tx_q(vsi->seid, pf,
+ pf_q + vsi->alloc_queue_pairs,
+ true /*is xdp*/, enable);
+ if (ret) {
+ dev_info(&pf->pdev->dev,
+ "VSI seid %d XDP Tx ring %d %sable timeout\n",
+ vsi->seid, pf_q, (enable ? "en" : "dis"));
+ }
+
+ return ret;
+}
+
+/**
+ * i40e_queue_pair_enable_irq - Enables interrupts for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue_pair
+ **/
+static void i40e_queue_pair_enable_irq(struct i40e_vsi *vsi, int queue_pair)
+{
+ struct i40e_ring *rxr = vsi->rx_rings[queue_pair];
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+
+ /* All rings in a qp belong to the same qvector. */
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED)
+ i40e_irq_dynamic_enable(vsi, rxr->q_vector->v_idx);
+ else
+ i40e_irq_dynamic_enable_icr0(pf);
+
+ i40e_flush(hw);
+}
+
+/**
+ * i40e_queue_pair_disable_irq - Disables interrupts for a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue_pair
+ **/
+static void i40e_queue_pair_disable_irq(struct i40e_vsi *vsi, int queue_pair)
+{
+ struct i40e_ring *rxr = vsi->rx_rings[queue_pair];
+ struct i40e_pf *pf = vsi->back;
+ struct i40e_hw *hw = &pf->hw;
+
+ /* For simplicity, instead of removing the qp interrupt causes
+ * from the interrupt linked list, we simply disable the interrupt, and
+ * leave the list intact.
+ *
+ * All rings in a qp belong to the same qvector.
+ */
+ if (pf->flags & I40E_FLAG_MSIX_ENABLED) {
+ u32 intpf = vsi->base_vector + rxr->q_vector->v_idx;
+
+ wr32(hw, I40E_PFINT_DYN_CTLN(intpf - 1), 0);
+ i40e_flush(hw);
+ synchronize_irq(pf->msix_entries[intpf].vector);
+ } else {
+ /* Legacy and MSI mode - this stops all interrupt handling */
+ wr32(hw, I40E_PFINT_ICR0_ENA, 0);
+ wr32(hw, I40E_PFINT_DYN_CTL0, 0);
+ i40e_flush(hw);
+ synchronize_irq(pf->pdev->irq);
+ }
+}
+
+/**
+ * i40e_queue_pair_disable - Disables a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ *
+ * Returns 0 on success, <0 on failure.
+ **/
+int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair)
+{
+ int err;
+
+ err = i40e_enter_busy_conf(vsi);
+ if (err)
+ return err;
+
+ i40e_queue_pair_disable_irq(vsi, queue_pair);
+ err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */);
+ i40e_clean_rx_ring(vsi->rx_rings[queue_pair]);
+ i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */);
+ i40e_queue_pair_clean_rings(vsi, queue_pair);
+ i40e_queue_pair_reset_stats(vsi, queue_pair);
+
+ return err;
+}
+
+/**
+ * i40e_queue_pair_enable - Enables a queue pair
+ * @vsi: vsi
+ * @queue_pair: queue pair
+ *
+ * Returns 0 on success, <0 on failure.
+ **/
+int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair)
+{
+ int err;
+
+ err = i40e_configure_tx_ring(vsi->tx_rings[queue_pair]);
+ if (err)
+ return err;
+
+ if (i40e_enabled_xdp_vsi(vsi)) {
+ err = i40e_configure_tx_ring(vsi->xdp_rings[queue_pair]);
+ if (err)
+ return err;
+ }
+
+ err = i40e_configure_rx_ring(vsi->rx_rings[queue_pair]);
+ if (err)
+ return err;
+
+ err = i40e_queue_pair_toggle_rings(vsi, queue_pair, true /* on */);
+ i40e_queue_pair_toggle_napi(vsi, queue_pair, true /* on */);
+ i40e_queue_pair_enable_irq(vsi, queue_pair);
+
+ i40e_exit_busy_conf(vsi);
+
+ return err;
}
/**
@@ -11982,9 +12993,9 @@
switch (xdp->command) {
case XDP_SETUP_PROG:
return i40e_xdp_setup(vsi, xdp->prog);
- case XDP_QUERY_PROG:
- xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
- return 0;
+ case XDP_SETUP_XSK_POOL:
+ return i40e_xsk_pool_setup(vsi, xdp->xsk.pool,
+ xdp->xsk.queue_id);
default:
return -EINVAL;
}
@@ -12007,16 +13018,18 @@
.ndo_poll_controller = i40e_netpoll,
#endif
.ndo_setup_tc = __i40e_setup_tc,
+ .ndo_select_queue = i40e_lan_select_queue,
.ndo_set_features = i40e_set_features,
.ndo_set_vf_mac = i40e_ndo_set_vf_mac,
.ndo_set_vf_vlan = i40e_ndo_set_vf_port_vlan,
+ .ndo_get_vf_stats = i40e_get_vf_stats,
.ndo_set_vf_rate = i40e_ndo_set_vf_bw,
.ndo_get_vf_config = i40e_ndo_get_vf_config,
.ndo_set_vf_link_state = i40e_ndo_set_vf_link_state,
.ndo_set_vf_spoofchk = i40e_ndo_set_vf_spoofchk,
.ndo_set_vf_trust = i40e_ndo_set_vf_trust,
- .ndo_udp_tunnel_add = i40e_udp_tunnel_add,
- .ndo_udp_tunnel_del = i40e_udp_tunnel_del,
+ .ndo_udp_tunnel_add = udp_tunnel_nic_add_port,
+ .ndo_udp_tunnel_del = udp_tunnel_nic_del_port,
.ndo_get_phys_port_id = i40e_get_phys_port_id,
.ndo_fdb_add = i40e_ndo_fdb_add,
.ndo_features_check = i40e_features_check,
@@ -12024,6 +13037,9 @@
.ndo_bridge_setlink = i40e_ndo_bridge_setlink,
.ndo_bpf = i40e_xdp,
.ndo_xdp_xmit = i40e_xdp_xmit,
+ .ndo_xsk_wakeup = i40e_xsk_wakeup,
+ .ndo_dfwd_add_station = i40e_fwd_add,
+ .ndo_dfwd_del_station = i40e_fwd_del,
};
/**
@@ -12068,6 +13084,7 @@
NETIF_F_GSO_IPXIP6 |
NETIF_F_GSO_UDP_TUNNEL |
NETIF_F_GSO_UDP_TUNNEL_CSUM |
+ NETIF_F_GSO_UDP_L4 |
NETIF_F_SCTP_CRC |
NETIF_F_RXHASH |
NETIF_F_RXCSUM |
@@ -12076,6 +13093,8 @@
if (!(pf->hw_features & I40E_HW_OUTER_UDP_CSUM_CAPABLE))
netdev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM;
+ netdev->udp_tunnel_nic_info = &pf->udp_tunnel_nic;
+
netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
netdev->hw_enc_features |= hw_enc_features;
@@ -12083,12 +13102,15 @@
/* record features VLANs can make use of */
netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID;
- if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
- netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC;
+ /* enable macvlan offloads */
+ netdev->hw_features |= NETIF_F_HW_L2FW_DOFFLOAD;
hw_features = hw_enc_features |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_CTAG_RX;
+
+ if (!(pf->flags & I40E_FLAG_MFP_ENABLED))
+ hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC;
netdev->hw_features |= hw_features;
@@ -12195,7 +13217,7 @@
struct i40e_pf *pf = vsi->back;
/* Uplink is not a bridge so default to VEB */
- if (vsi->veb_idx == I40E_NO_VEB)
+ if (vsi->veb_idx >= I40E_MAX_VEB)
return 1;
veb = pf->veb[vsi->veb_idx];
@@ -12836,8 +13858,7 @@
/* Setup DCB netlink interface */
i40e_dcbnl_setup(vsi);
#endif /* CONFIG_I40E_DCB */
- /* fall through */
-
+ fallthrough;
case I40E_VSI_FDIR:
/* set up vectors and rings if needed */
ret = i40e_vsi_setup_vectors(vsi);
@@ -12853,7 +13874,6 @@
i40e_vsi_reset_stats(vsi);
break;
-
default:
/* no netdev or rings for the other VSI types */
break;
@@ -13179,7 +14199,7 @@
for (vsi_idx = 0; vsi_idx < pf->num_alloc_vsi; vsi_idx++)
if (pf->vsi[vsi_idx] && pf->vsi[vsi_idx]->seid == vsi_seid)
break;
- if (vsi_idx >= pf->num_alloc_vsi && vsi_seid != 0) {
+ if (vsi_idx == pf->num_alloc_vsi && vsi_seid != 0) {
dev_info(&pf->pdev->dev, "vsi seid %d not found\n",
vsi_seid);
return NULL;
@@ -13256,7 +14276,7 @@
/* Main VEB? */
if (uplink_seid != pf->mac_seid)
break;
- if (pf->lan_veb == I40E_NO_VEB) {
+ if (pf->lan_veb >= I40E_MAX_VEB) {
int v;
/* find existing or else empty VEB */
@@ -13266,13 +14286,15 @@
break;
}
}
- if (pf->lan_veb == I40E_NO_VEB) {
+ if (pf->lan_veb >= I40E_MAX_VEB) {
v = i40e_veb_mem_alloc(pf);
if (v < 0)
break;
pf->lan_veb = v;
}
}
+ if (pf->lan_veb >= I40E_MAX_VEB)
+ break;
pf->veb[pf->lan_veb]->seid = seid;
pf->veb[pf->lan_veb]->uplink_seid = pf->mac_seid;
@@ -13370,10 +14392,11 @@
* i40e_setup_pf_switch - Setup the HW switch on startup or after reset
* @pf: board private structure
* @reinit: if the Main VSI needs to re-initialized.
+ * @lock_acquired: indicates whether or not the lock has been acquired
*
* Returns 0 on success, negative value on failure
**/
-static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit)
+static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acquired)
{
u16 flags = 0;
int ret;
@@ -13426,7 +14449,7 @@
/* Set up the PF VSI associated with the PF's main VSI
* that is already in the HW switch
*/
- if (pf->lan_veb != I40E_NO_VEB && pf->veb[pf->lan_veb])
+ if (pf->lan_veb < I40E_MAX_VEB && pf->veb[pf->lan_veb])
uplink_seid = pf->veb[pf->lan_veb]->seid;
else
uplink_seid = pf->mac_seid;
@@ -13475,8 +14498,14 @@
i40e_ptp_init(pf);
+ if (!lock_acquired)
+ rtnl_lock();
+
/* repopulate tunnel port filters */
- i40e_sync_udp_filters(pf);
+ udp_tunnel_nic_reset_ntf(pf->vsi[pf->lan_vsi]->netdev);
+
+ if (!lock_acquired)
+ rtnl_unlock();
return ret;
}
@@ -13626,29 +14655,29 @@
i = snprintf(buf, INFO_STRING_LEN, "Features: PF-id[%d]", hw->pf_id);
#ifdef CONFIG_PCI_IOV
- i += snprintf(&buf[i], REMAIN(i), " VFs: %d", pf->num_req_vfs);
+ i += scnprintf(&buf[i], REMAIN(i), " VFs: %d", pf->num_req_vfs);
#endif
- i += snprintf(&buf[i], REMAIN(i), " VSIs: %d QP: %d",
+ i += scnprintf(&buf[i], REMAIN(i), " VSIs: %d QP: %d",
pf->hw.func_caps.num_vsis,
pf->vsi[pf->lan_vsi]->num_queue_pairs);
if (pf->flags & I40E_FLAG_RSS_ENABLED)
- i += snprintf(&buf[i], REMAIN(i), " RSS");
+ i += scnprintf(&buf[i], REMAIN(i), " RSS");
if (pf->flags & I40E_FLAG_FD_ATR_ENABLED)
- i += snprintf(&buf[i], REMAIN(i), " FD_ATR");
+ i += scnprintf(&buf[i], REMAIN(i), " FD_ATR");
if (pf->flags & I40E_FLAG_FD_SB_ENABLED) {
- i += snprintf(&buf[i], REMAIN(i), " FD_SB");
- i += snprintf(&buf[i], REMAIN(i), " NTUPLE");
+ i += scnprintf(&buf[i], REMAIN(i), " FD_SB");
+ i += scnprintf(&buf[i], REMAIN(i), " NTUPLE");
}
if (pf->flags & I40E_FLAG_DCB_CAPABLE)
- i += snprintf(&buf[i], REMAIN(i), " DCB");
- i += snprintf(&buf[i], REMAIN(i), " VxLAN");
- i += snprintf(&buf[i], REMAIN(i), " Geneve");
+ i += scnprintf(&buf[i], REMAIN(i), " DCB");
+ i += scnprintf(&buf[i], REMAIN(i), " VxLAN");
+ i += scnprintf(&buf[i], REMAIN(i), " Geneve");
if (pf->flags & I40E_FLAG_PTP)
- i += snprintf(&buf[i], REMAIN(i), " PTP");
+ i += scnprintf(&buf[i], REMAIN(i), " PTP");
if (pf->flags & I40E_FLAG_VEB_MODE_ENABLED)
- i += snprintf(&buf[i], REMAIN(i), " VEB");
+ i += scnprintf(&buf[i], REMAIN(i), " VEB");
else
- i += snprintf(&buf[i], REMAIN(i), " VEPA");
+ i += scnprintf(&buf[i], REMAIN(i), " VEPA");
dev_info(&pf->pdev->dev, "%s\n", buf);
kfree(buf);
@@ -13669,6 +14698,236 @@
{
if (eth_platform_get_mac_address(&pdev->dev, pf->hw.mac.addr))
i40e_get_mac_addr(&pf->hw, pf->hw.mac.addr);
+}
+
+/**
+ * i40e_set_fec_in_flags - helper function for setting FEC options in flags
+ * @fec_cfg: FEC option to set in flags
+ * @flags: ptr to flags in which we set FEC option
+ **/
+void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags)
+{
+ if (fec_cfg & I40E_AQ_SET_FEC_AUTO)
+ *flags |= I40E_FLAG_RS_FEC | I40E_FLAG_BASE_R_FEC;
+ if ((fec_cfg & I40E_AQ_SET_FEC_REQUEST_RS) ||
+ (fec_cfg & I40E_AQ_SET_FEC_ABILITY_RS)) {
+ *flags |= I40E_FLAG_RS_FEC;
+ *flags &= ~I40E_FLAG_BASE_R_FEC;
+ }
+ if ((fec_cfg & I40E_AQ_SET_FEC_REQUEST_KR) ||
+ (fec_cfg & I40E_AQ_SET_FEC_ABILITY_KR)) {
+ *flags |= I40E_FLAG_BASE_R_FEC;
+ *flags &= ~I40E_FLAG_RS_FEC;
+ }
+ if (fec_cfg == 0)
+ *flags &= ~(I40E_FLAG_RS_FEC | I40E_FLAG_BASE_R_FEC);
+}
+
+/**
+ * i40e_check_recovery_mode - check if we are running transition firmware
+ * @pf: board private structure
+ *
+ * Check registers indicating the firmware runs in recovery mode. Sets the
+ * appropriate driver state.
+ *
+ * Returns true if the recovery mode was detected, false otherwise
+ **/
+static bool i40e_check_recovery_mode(struct i40e_pf *pf)
+{
+ u32 val = rd32(&pf->hw, I40E_GL_FWSTS);
+
+ if (val & I40E_GL_FWSTS_FWS1B_MASK) {
+ dev_crit(&pf->pdev->dev, "Firmware recovery mode detected. Limiting functionality.\n");
+ dev_crit(&pf->pdev->dev, "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n");
+ set_bit(__I40E_RECOVERY_MODE, pf->state);
+
+ return true;
+ }
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state))
+ dev_info(&pf->pdev->dev, "Please do Power-On Reset to initialize adapter in normal mode with full functionality.\n");
+
+ return false;
+}
+
+/**
+ * i40e_pf_loop_reset - perform reset in a loop.
+ * @pf: board private structure
+ *
+ * This function is useful when a NIC is about to enter recovery mode.
+ * When a NIC's internal data structures are corrupted the NIC's
+ * firmware is going to enter recovery mode.
+ * Right after a POR it takes about 7 minutes for firmware to enter
+ * recovery mode. Until that time a NIC is in some kind of intermediate
+ * state. After that time period the NIC almost surely enters
+ * recovery mode. The only way for a driver to detect intermediate
+ * state is to issue a series of pf-resets and check a return value.
+ * If a PF reset returns success then the firmware could be in recovery
+ * mode so the caller of this code needs to check for recovery mode
+ * if this function returns success. There is a little chance that
+ * firmware will hang in intermediate state forever.
+ * Since waiting 7 minutes is quite a lot of time this function waits
+ * 10 seconds and then gives up by returning an error.
+ *
+ * Return 0 on success, negative on failure.
+ **/
+static i40e_status i40e_pf_loop_reset(struct i40e_pf *pf)
+{
+ /* wait max 10 seconds for PF reset to succeed */
+ const unsigned long time_end = jiffies + 10 * HZ;
+
+ struct i40e_hw *hw = &pf->hw;
+ i40e_status ret;
+
+ ret = i40e_pf_reset(hw);
+ while (ret != I40E_SUCCESS && time_before(jiffies, time_end)) {
+ usleep_range(10000, 20000);
+ ret = i40e_pf_reset(hw);
+ }
+
+ if (ret == I40E_SUCCESS)
+ pf->pfr_count++;
+ else
+ dev_info(&pf->pdev->dev, "PF reset failed: %d\n", ret);
+
+ return ret;
+}
+
+/**
+ * i40e_check_fw_empr - check if FW issued unexpected EMP Reset
+ * @pf: board private structure
+ *
+ * Check FW registers to determine if FW issued unexpected EMP Reset.
+ * Every time when unexpected EMP Reset occurs the FW increments
+ * a counter of unexpected EMP Resets. When the counter reaches 10
+ * the FW should enter the Recovery mode
+ *
+ * Returns true if FW issued unexpected EMP Reset
+ **/
+static bool i40e_check_fw_empr(struct i40e_pf *pf)
+{
+ const u32 fw_sts = rd32(&pf->hw, I40E_GL_FWSTS) &
+ I40E_GL_FWSTS_FWS1B_MASK;
+ return (fw_sts > I40E_GL_FWSTS_FWS1B_EMPR_0) &&
+ (fw_sts <= I40E_GL_FWSTS_FWS1B_EMPR_10);
+}
+
+/**
+ * i40e_handle_resets - handle EMP resets and PF resets
+ * @pf: board private structure
+ *
+ * Handle both EMP resets and PF resets and conclude whether there are
+ * any issues regarding these resets. If there are any issues then
+ * generate log entry.
+ *
+ * Return 0 if NIC is healthy or negative value when there are issues
+ * with resets
+ **/
+static i40e_status i40e_handle_resets(struct i40e_pf *pf)
+{
+ const i40e_status pfr = i40e_pf_loop_reset(pf);
+ const bool is_empr = i40e_check_fw_empr(pf);
+
+ if (is_empr || pfr != I40E_SUCCESS)
+ dev_crit(&pf->pdev->dev, "Entering recovery mode due to repeated FW resets. This may take several minutes. Refer to the Intel(R) Ethernet Adapters and Devices User Guide.\n");
+
+ return is_empr ? I40E_ERR_RESET_FAILED : pfr;
+}
+
+/**
+ * i40e_init_recovery_mode - initialize subsystems needed in recovery mode
+ * @pf: board private structure
+ * @hw: ptr to the hardware info
+ *
+ * This function does a minimal setup of all subsystems needed for running
+ * recovery mode.
+ *
+ * Returns 0 on success, negative on failure
+ **/
+static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw)
+{
+ struct i40e_vsi *vsi;
+ int err;
+ int v_idx;
+
+ pci_save_state(pf->pdev);
+
+ /* set up periodic task facility */
+ timer_setup(&pf->service_timer, i40e_service_timer, 0);
+ pf->service_timer_period = HZ;
+
+ INIT_WORK(&pf->service_task, i40e_service_task);
+ clear_bit(__I40E_SERVICE_SCHED, pf->state);
+
+ err = i40e_init_interrupt_scheme(pf);
+ if (err)
+ goto err_switch_setup;
+
+ /* The number of VSIs reported by the FW is the minimum guaranteed
+ * to us; HW supports far more and we share the remaining pool with
+ * the other PFs. We allocate space for more than the guarantee with
+ * the understanding that we might not get them all later.
+ */
+ if (pf->hw.func_caps.num_vsis < I40E_MIN_VSI_ALLOC)
+ pf->num_alloc_vsi = I40E_MIN_VSI_ALLOC;
+ else
+ pf->num_alloc_vsi = pf->hw.func_caps.num_vsis;
+
+ /* Set up the vsi struct and our local tracking of the MAIN PF vsi. */
+ pf->vsi = kcalloc(pf->num_alloc_vsi, sizeof(struct i40e_vsi *),
+ GFP_KERNEL);
+ if (!pf->vsi) {
+ err = -ENOMEM;
+ goto err_switch_setup;
+ }
+
+ /* We allocate one VSI which is needed as absolute minimum
+ * in order to register the netdev
+ */
+ v_idx = i40e_vsi_mem_alloc(pf, I40E_VSI_MAIN);
+ if (v_idx < 0) {
+ err = v_idx;
+ goto err_switch_setup;
+ }
+ pf->lan_vsi = v_idx;
+ vsi = pf->vsi[v_idx];
+ if (!vsi) {
+ err = -EFAULT;
+ goto err_switch_setup;
+ }
+ vsi->alloc_queue_pairs = 1;
+ err = i40e_config_netdev(vsi);
+ if (err)
+ goto err_switch_setup;
+ err = register_netdev(vsi->netdev);
+ if (err)
+ goto err_switch_setup;
+ vsi->netdev_registered = true;
+ i40e_dbg_pf_init(pf);
+
+ err = i40e_setup_misc_vector_for_recovery_mode(pf);
+ if (err)
+ goto err_switch_setup;
+
+ /* tell the firmware that we're starting */
+ i40e_send_version(pf);
+
+ /* since everything's happy, start the service_task timer */
+ mod_timer(&pf->service_timer,
+ round_jiffies(jiffies + pf->service_timer_period));
+
+ return 0;
+
+err_switch_setup:
+ i40e_reset_interrupt_capability(pf);
+ del_timer_sync(&pf->service_timer);
+ i40e_shutdown_adminq(hw);
+ iounmap(hw->hw_addr);
+ pci_disable_pcie_error_reporting(pf->pdev);
+ pci_release_mem_regions(pf->pdev);
+ pci_disable_device(pf->pdev);
+ kfree(pf);
+
+ return err;
}
/**
@@ -13739,7 +14998,17 @@
pf->ioremap_len = min_t(int, pci_resource_len(pdev, 0),
I40E_MAX_CSR_SPACE);
-
+ /* We believe that the highest register to read is
+ * I40E_GLGEN_STAT_CLEAR, so we check if the BAR size
+ * is not less than that before mapping to prevent a
+ * kernel panic.
+ */
+ if (pf->ioremap_len < I40E_GLGEN_STAT_CLEAR) {
+ dev_err(&pdev->dev, "Cannot map registers, bar size 0x%X too small, aborting\n",
+ pf->ioremap_len);
+ err = -ENOMEM;
+ goto err_ioremap;
+ }
hw->hw_addr = ioremap(pci_resource_start(pdev, 0), pf->ioremap_len);
if (!hw->hw_addr) {
err = -EIO;
@@ -13767,6 +15036,7 @@
INIT_LIST_HEAD(&pf->l3_flex_pit_list);
INIT_LIST_HEAD(&pf->l4_flex_pit_list);
+ INIT_LIST_HEAD(&pf->ddp_old_prof);
/* set up the locks for the AQ, do this only once in probe
* and destroy them only once in remove
@@ -13794,12 +15064,19 @@
/* Reset here to make sure all is clean and to define PF 'n' */
i40e_clear_hw(hw);
- err = i40e_pf_reset(hw);
+
+ err = i40e_set_mac_type(hw);
if (err) {
- dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err);
+ dev_warn(&pdev->dev, "unidentified MAC or BLANK NVM: %d\n",
+ err);
goto err_pf_reset;
}
- pf->pfr_count++;
+
+ err = i40e_handle_resets(pf);
+ if (err)
+ goto err_pf_reset;
+
+ i40e_check_recovery_mode(pf);
hw->aq.num_arq_entries = I40E_AQ_LEN;
hw->aq.num_asq_entries = I40E_AQ_LEN;
@@ -13825,7 +15102,11 @@
if (err) {
if (err == I40E_ERR_FIRMWARE_API_VERSION)
dev_info(&pdev->dev,
- "The driver for the device stopped because the NVM image is newer than expected. You must install the most recent version of the network driver.\n");
+ "The driver for the device stopped because the NVM image v%u.%u is newer than expected v%u.%u. You must install the most recent version of the network driver.\n",
+ hw->aq.api_maj_ver,
+ hw->aq.api_min_ver,
+ I40E_FW_API_VERSION_MAJOR,
+ I40E_FW_MINOR_VERSION(hw));
else
dev_info(&pdev->dev,
"The driver for the device stopped because the device firmware failed to init. Try updating your NVM image.\n");
@@ -13834,19 +15115,28 @@
}
i40e_get_oem_version(hw);
- /* provide nvm, fw, api versions */
- dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s\n",
+ /* provide nvm, fw, api versions, vendor:device id, subsys vendor:device id */
+ dev_info(&pdev->dev, "fw %d.%d.%05d api %d.%d nvm %s [%04x:%04x] [%04x:%04x]\n",
hw->aq.fw_maj_ver, hw->aq.fw_min_ver, hw->aq.fw_build,
hw->aq.api_maj_ver, hw->aq.api_min_ver,
- i40e_nvm_version_str(hw));
+ i40e_nvm_version_str(hw), hw->vendor_id, hw->device_id,
+ hw->subsystem_vendor_id, hw->subsystem_device_id);
if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw))
- dev_info(&pdev->dev,
- "The driver for the device detected a newer version of the NVM image than expected. Please install the most recent version of the network driver.\n");
+ dev_dbg(&pdev->dev,
+ "The driver for the device detected a newer version of the NVM image v%u.%u than v%u.%u.\n",
+ hw->aq.api_maj_ver,
+ hw->aq.api_min_ver,
+ I40E_FW_API_VERSION_MAJOR,
+ I40E_FW_MINOR_VERSION(hw));
else if (hw->aq.api_maj_ver == 1 && hw->aq.api_min_ver < 4)
dev_info(&pdev->dev,
- "The driver for the device detected an older version of the NVM image than expected. Please update the NVM image.\n");
+ "The driver for the device detected an older version of the NVM image v%u.%u than expected v%u.%u. Please update the NVM image.\n",
+ hw->aq.api_maj_ver,
+ hw->aq.api_min_ver,
+ I40E_FW_API_VERSION_MAJOR,
+ I40E_FW_MINOR_VERSION(hw));
i40e_verify_eeprom(pf);
@@ -13855,6 +15145,7 @@
dev_warn(&pdev->dev, "This device is a pre-production adapter/LOM. Please be aware there may be issues with your hardware. If you are experiencing problems please contact your Intel or hardware representative who provided you with this hardware.\n");
i40e_clear_pxe_mode(hw);
+
err = i40e_get_capabilities(pf, i40e_aqc_opc_list_func_capabilities);
if (err)
goto err_adminq_setup;
@@ -13864,6 +15155,9 @@
dev_info(&pdev->dev, "sw_init failed: %d\n", err);
goto err_sw_init;
}
+
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state))
+ return i40e_init_recovery_mode(pf, hw);
err = i40e_init_lan_hmc(hw, hw->func_caps.num_tx_qp,
hw->func_caps.num_rx_qp, 0, 0);
@@ -13885,7 +15179,7 @@
*/
if (pf->hw_features & I40E_HW_STOP_FW_LLDP) {
dev_info(&pdev->dev, "Stopping firmware LLDP agent.\n");
- i40e_aq_stop_lldp(hw, true, NULL);
+ i40e_aq_stop_lldp(hw, true, false, NULL);
}
/* allow a platform config to override the HW addr */
@@ -13904,6 +15198,11 @@
pci_set_drvdata(pdev, pf);
pci_save_state(pdev);
+
+ dev_info(&pdev->dev,
+ (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) ?
+ "FW LLDP is disabled\n" :
+ "FW LLDP is enabled\n");
/* Enable FW to write default DCB config on link-up */
i40e_aq_set_dcb_parameters(hw, true, NULL);
@@ -13938,6 +15237,14 @@
if (err)
goto err_switch_setup;
+ pf->udp_tunnel_nic.set_port = i40e_udp_tunnel_set_port;
+ pf->udp_tunnel_nic.unset_port = i40e_udp_tunnel_unset_port;
+ pf->udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP;
+ pf->udp_tunnel_nic.shared = &pf->udp_tunnel_shared;
+ pf->udp_tunnel_nic.tables[0].n_entries = I40E_MAX_PF_UDP_OFFLOAD_PORTS;
+ pf->udp_tunnel_nic.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN |
+ UDP_TUNNEL_TYPE_GENEVE;
+
/* The number of VSIs reported by the FW is the minimum guaranteed
* to us; HW supports far more and we share the remaining pool with
* the other PFs. We allocate space for more than the guarantee with
@@ -13947,6 +15254,12 @@
pf->num_alloc_vsi = I40E_MIN_VSI_ALLOC;
else
pf->num_alloc_vsi = pf->hw.func_caps.num_vsis;
+ if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) {
+ dev_warn(&pf->pdev->dev,
+ "limiting the VSI count due to UDP tunnel limitation %d > %d\n",
+ pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES);
+ pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES;
+ }
/* Set up the *vsi struct and our local tracking of the MAIN PF vsi. */
pf->vsi = kcalloc(pf->num_alloc_vsi, sizeof(struct i40e_vsi *),
@@ -13965,7 +15278,7 @@
pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
}
#endif
- err = i40e_setup_pf_switch(pf, false);
+ err = i40e_setup_pf_switch(pf, false, false);
if (err) {
dev_info(&pdev->dev, "setup_pf_switch failed: %d\n", err);
goto err_vsis;
@@ -14106,23 +15419,23 @@
switch (hw->bus.speed) {
case i40e_bus_speed_8000:
- strncpy(speed, "8.0", PCI_SPEED_SIZE); break;
+ strlcpy(speed, "8.0", PCI_SPEED_SIZE); break;
case i40e_bus_speed_5000:
- strncpy(speed, "5.0", PCI_SPEED_SIZE); break;
+ strlcpy(speed, "5.0", PCI_SPEED_SIZE); break;
case i40e_bus_speed_2500:
- strncpy(speed, "2.5", PCI_SPEED_SIZE); break;
+ strlcpy(speed, "2.5", PCI_SPEED_SIZE); break;
default:
break;
}
switch (hw->bus.width) {
case i40e_bus_width_pcie_x8:
- strncpy(width, "8", PCI_WIDTH_SIZE); break;
+ strlcpy(width, "8", PCI_WIDTH_SIZE); break;
case i40e_bus_width_pcie_x4:
- strncpy(width, "4", PCI_WIDTH_SIZE); break;
+ strlcpy(width, "4", PCI_WIDTH_SIZE); break;
case i40e_bus_width_pcie_x2:
- strncpy(width, "2", PCI_WIDTH_SIZE); break;
+ strlcpy(width, "2", PCI_WIDTH_SIZE); break;
case i40e_bus_width_pcie_x1:
- strncpy(width, "1", PCI_WIDTH_SIZE); break;
+ strlcpy(width, "1", PCI_WIDTH_SIZE); break;
default:
break;
}
@@ -14145,12 +15458,23 @@
i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
pf->hw.phy.link_info.requested_speeds = abilities.link_speed;
+ /* set the FEC config due to the board capabilities */
+ i40e_set_fec_in_flags(abilities.fec_cfg_curr_mod_ext_info, &pf->flags);
+
/* get the supported phy types from the fw */
err = i40e_aq_get_phy_capabilities(hw, false, true, &abilities, NULL);
if (err)
dev_dbg(&pf->pdev->dev, "get supported phy types ret = %s last_status = %s\n",
i40e_stat_str(&pf->hw, err),
i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+
+ /* make sure the MFS hasn't been set lower than the default */
+#define MAX_FRAME_SIZE_DEFAULT 0x2600
+ val = (rd32(&pf->hw, I40E_PRTGL_SAH) &
+ I40E_PRTGL_SAH_MFS_MASK) >> I40E_PRTGL_SAH_MFS_SHIFT;
+ if (val < MAX_FRAME_SIZE_DEFAULT)
+ dev_warn(&pdev->dev, "MFS for port %x has been set below the default: %x\n",
+ i, val);
/* Add a filter to drop all Flow control frames from any VSI from being
* transmitted. By doing so we stop a malicious VF from sending out
@@ -14239,6 +15563,19 @@
if (pf->service_task.func)
cancel_work_sync(&pf->service_task);
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state)) {
+ struct i40e_vsi *vsi = pf->vsi[0];
+
+ /* We know that we have allocated only one vsi for this PF,
+ * it was just for registering netdevice, so the interface
+ * could be visible in the 'ifconfig' output
+ */
+ unregister_netdev(vsi->netdev);
+ free_netdev(vsi->netdev);
+
+ goto unmap;
+ }
+
/* Client close must be called explicitly here because the timer
* has been stopped.
*/
@@ -14283,6 +15620,12 @@
ret_code);
}
+unmap:
+ /* Free MSI/legacy interrupt 0 when in recovery mode. */
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state) &&
+ !(pf->flags & I40E_FLAG_MSIX_ENABLED))
+ free_irq(pf->pdev->irq, pf);
+
/* shutdown the adminq */
i40e_shutdown_adminq(hw);
@@ -14295,7 +15638,8 @@
i40e_clear_interrupt_scheme(pf);
for (i = 0; i < pf->num_alloc_vsi; i++) {
if (pf->vsi[i]) {
- i40e_vsi_clear_rings(pf->vsi[i]);
+ if (!test_bit(__I40E_RECOVERY_MODE, pf->state))
+ i40e_vsi_clear_rings(pf->vsi[i]);
i40e_vsi_clear(pf->vsi[i]);
pf->vsi[i] = NULL;
}
@@ -14328,7 +15672,7 @@
* remediation.
**/
static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev,
- enum pci_channel_state error)
+ pci_channel_state_t error)
{
struct i40e_pf *pf = pci_get_drvdata(pdev);
@@ -14361,7 +15705,6 @@
{
struct i40e_pf *pf = pci_get_drvdata(pdev);
pci_ers_result_t result;
- int err;
u32 reg;
dev_dbg(&pdev->dev, "%s\n", __func__);
@@ -14380,14 +15723,6 @@
result = PCI_ERS_RESULT_RECOVERED;
else
result = PCI_ERS_RESULT_DISCONNECT;
- }
-
- err = pci_cleanup_aer_uncorrect_error_status(pdev);
- if (err) {
- dev_info(&pdev->dev,
- "pci_cleanup_aer_uncorrect_error_status failed 0x%0x\n",
- err);
- /* non-fatal, continue */
}
return result;
@@ -14512,6 +15847,11 @@
wr32(hw, I40E_PFPM_WUFC,
(pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
+ /* Free MSI/legacy interrupt 0 when in recovery mode. */
+ if (test_bit(__I40E_RECOVERY_MODE, pf->state) &&
+ !(pf->flags & I40E_FLAG_MSIX_ENABLED))
+ free_irq(pf->pdev->irq, pf);
+
/* Since we're going to destroy queues during the
* i40e_clear_interrupt_scheme() we should hold the RTNL lock for this
* whole section
@@ -14532,8 +15872,7 @@
**/
static int __maybe_unused i40e_suspend(struct device *dev)
{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct i40e_pf *pf = pci_get_drvdata(pdev);
+ struct i40e_pf *pf = dev_get_drvdata(dev);
struct i40e_hw *hw = &pf->hw;
/* If we're already suspended, then there is nothing to do */
@@ -14583,8 +15922,7 @@
**/
static int __maybe_unused i40e_resume(struct device *dev)
{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct i40e_pf *pf = pci_get_drvdata(pdev);
+ struct i40e_pf *pf = dev_get_drvdata(dev);
int err;
/* If we're not suspended, then there is nothing to do */
@@ -14601,7 +15939,7 @@
*/
err = i40e_restore_interrupt_scheme(pf);
if (err) {
- dev_err(&pdev->dev, "Cannot restore interrupt scheme: %d\n",
+ dev_err(dev, "Cannot restore interrupt scheme: %d\n",
err);
}
@@ -14651,8 +15989,9 @@
**/
static int __init i40e_init_module(void)
{
- pr_info("%s: %s - version %s\n", i40e_driver_name,
- i40e_driver_string, i40e_driver_version_str);
+ int err;
+
+ pr_info("%s: %s\n", i40e_driver_name, i40e_driver_string);
pr_info("%s: %s\n", i40e_driver_name, i40e_copyright);
/* There is no need to throttle the number of active tasks because
@@ -14669,7 +16008,14 @@
}
i40e_dbg_init();
- return pci_register_driver(&i40e_driver);
+ err = pci_register_driver(&i40e_driver);
+ if (err) {
+ destroy_workqueue(i40e_wq);
+ i40e_dbg_exit();
+ return err;
+ }
+
+ return 0;
}
module_init(i40e_init_module);
--
Gitblit v1.6.2