diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 45819b235800..a2d4c626f659 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -74,19 +74,17 @@ properties:
- rev-rmii
- moca
- # RX and TX delays are added by the MAC when required
+ # RX and TX delays are provided by the PCB. See below
- rgmii
- # RGMII with internal RX and TX delays provided by the PHY,
- # the MAC should not add the RX or TX delays in this case
+ # RX and TX delays are not provided by the PCB. This is the most
+ # frequent case. See below
- rgmii-id
- # RGMII with internal RX delay provided by the PHY, the MAC
- # should not add an RX delay in this case
+ # TX delay is provided by the PCB. See below
- rgmii-rxid
- # RGMII with internal TX delay provided by the PHY, the MAC
- # should not add an TX delay in this case
+ # RX delay is provided by the PCB. See below
- rgmii-txid
- rtbi
- smii
@@ -286,4 +284,89 @@ allOf:
additionalProperties: true
+# Informative
+# ===========
+#
+# 'phy-modes' & 'phy-connection-type' properties 'rgmii', 'rgmii-id',
+# 'rgmii-rxid', and 'rgmii-txid' are frequently used wrongly by
+# developers. This informative section clarifies their usage.
+#
+# The RGMII specification requires a 2ns delay between the data and
+# clock signals on the RGMII bus. How this delay is implemented is not
+# specified.
+#
+# One option is to make the clock traces on the PCB longer than the
+# data traces. A sufficiently difference in length can provide the 2ns
+# delay. If both the RX and TX delays are implemented in this manner,
+# 'rgmii' should be used, so indicating the PCB adds the delays.
+#
+# If the PCB does not add these delays via extra long traces,
+# 'rgmii-id' should be used. Here, 'id' refers to 'internal delay',
+# where either the MAC or PHY adds the delay.
+#
+# If only one of the two delays are implemented via extra long clock
+# lines, either 'rgmii-rxid' or 'rgmii-txid' should be used,
+# indicating the MAC or PHY should implement one of the delays
+# internally, while the PCB implements the other delay.
+#
+# Device Tree describes hardware, and in this case, it describes the
+# PCB between the MAC and the PHY, if the PCB implements delays or
+# not.
+#
+# In practice, very few PCBs make use of extra long clock lines. Hence
+# any RGMII phy mode other than 'rgmii-id' is probably wrong, and is
+# unlikely to be accepted during review without details provided in
+# the commit description and comments in the .dts file.
+#
+# When the PCB does not implement the delays, the MAC or PHY must. As
+# such, this is software configuration, and so not described in Device
+# Tree.
+#
+# The following describes how Linux implements the configuration of
+# the MAC and PHY to add these delays when the PCB does not. As stated
+# above, developers often get this wrong, and the aim of this section
+# is reduce the frequency of these errors by Linux developers. Other
+# users of the Device Tree may implement it differently, and still be
+# consistent with both the normative and informative description
+# above.
+#
+# By default in Linux, when using phylib/phylink, the MAC is expected
+# to read the 'phy-mode' from Device Tree, not implement any delays,
+# and pass the value to the PHY. The PHY will then implement delays as
+# specified by the 'phy-mode'. The PHY should always be reconfigured
+# to implement the needed delays, replacing any setting performed by
+# strapping or the bootloader, etc.
+#
+# Experience to date is that all PHYs which implement RGMII also
+# implement the ability to add or not add the needed delays. Hence
+# this default is expected to work in all cases. Ignoring this default
+# is likely to be questioned by Reviews, and require a strong argument
+# to be accepted.
+#
+# There are a small number of cases where the MAC has hard coded
+# delays which cannot be disabled. The 'phy-mode' only describes the
+# PCB. The inability to disable the delays in the MAC does not change
+# the meaning of 'phy-mode'. It does however mean that a 'phy-mode' of
+# 'rgmii' is now invalid, it cannot be supported, since both the PCB
+# and the MAC and PHY adding delays cannot result in a functional
+# link. Thus the MAC should report a fatal error for any modes which
+# cannot be supported. When the MAC implements the delay, it must
+# ensure that the PHY does not also implement the same delay. So it
+# must modify the phy-mode it passes to the PHY, removing the delay it
+# has added. Failure to remove the delay will result in a
+# non-functioning link.
+#
+# Sometimes there is a need to fine tune the delays. Often the MAC or
+# PHY can perform this fine tuning. In the MAC node, the Device Tree
+# properties 'rx-internal-delay-ps' and 'tx-internal-delay-ps' should
+# be used to indicate fine tuning performed by the MAC. The values
+# expected here are small. A value of 2000ps, i.e 2ns, and a phy-mode
+# of 'rgmii' will not be accepted by Reviewers.
+#
+# If the PHY is to perform fine tuning, the properties
+# 'rx-internal-delay-ps' and 'tx-internal-delay-ps' in the PHY node
+# should be used. When the PHY is implementing delays, e.g. 'rgmii-id'
+# these properties should have a value near to 2000ps. If the PCB is
+# implementing delays, e.g. 'rgmii', a small value can be used to fine
+# tune the delay added by the PCB.
...
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index 884a6352c42b..c2c116ce1087 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -2379,6 +2379,7 @@ struct m_can_classdev *m_can_class_allocate_dev(struct device *dev,
SET_NETDEV_DEV(net_dev, dev);
m_can_of_parse_mram(class_dev, mram_config_vals);
+ spin_lock_init(&class_dev->tx_handling_spinlock);
out:
return class_dev;
}
@@ -2462,9 +2463,9 @@ EXPORT_SYMBOL_GPL(m_can_class_register);
void m_can_class_unregister(struct m_can_classdev *cdev)
{
+ unregister_candev(cdev->net);
if (cdev->is_peripheral)
can_rx_offload_del(&cdev->offload);
- unregister_candev(cdev->net);
}
EXPORT_SYMBOL_GPL(m_can_class_unregister);
diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 7107a37da36c..c3fb3176ce42 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -937,8 +937,8 @@ static void rkcanfd_remove(struct platform_device *pdev)
struct rkcanfd_priv *priv = platform_get_drvdata(pdev);
struct net_device *ndev = priv->ndev;
- can_rx_offload_del(&priv->offload);
rkcanfd_unregister(priv);
+ can_rx_offload_del(&priv->offload);
free_candev(ndev);
}
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 3bc56517fe7a..c30b04f8fc0d 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -75,6 +75,24 @@ static const struct can_bittiming_const mcp251xfd_data_bittiming_const = {
.brp_inc = 1,
};
+/* The datasheet of the mcp2518fd (DS20006027B) specifies a range of
+ * [-64,63] for TDCO, indicating a relative TDCO.
+ *
+ * Manual tests have shown, that using a relative TDCO configuration
+ * results in bus off, while an absolute configuration works.
+ *
+ * For TDCO use the max value (63) from the data sheet, but 0 as the
+ * minimum.
+ */
+static const struct can_tdc_const mcp251xfd_tdc_const = {
+ .tdcv_min = 0,
+ .tdcv_max = 63,
+ .tdco_min = 0,
+ .tdco_max = 63,
+ .tdcf_min = 0,
+ .tdcf_max = 0,
+};
+
static const char *__mcp251xfd_get_model_str(enum mcp251xfd_model model)
{
switch (model) {
@@ -510,8 +528,7 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv)
{
const struct can_bittiming *bt = &priv->can.bittiming;
const struct can_bittiming *dbt = &priv->can.data_bittiming;
- u32 val = 0;
- s8 tdco;
+ u32 tdcmod, val = 0;
int err;
/* CAN Control Register
@@ -575,11 +592,16 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv)
return err;
/* Transmitter Delay Compensation */
- tdco = clamp_t(int, dbt->brp * (dbt->prop_seg + dbt->phase_seg1),
- -64, 63);
- val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK,
- MCP251XFD_REG_TDC_TDCMOD_AUTO) |
- FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, tdco);
+ if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_AUTO)
+ tdcmod = MCP251XFD_REG_TDC_TDCMOD_AUTO;
+ else if (priv->can.ctrlmode & CAN_CTRLMODE_TDC_MANUAL)
+ tdcmod = MCP251XFD_REG_TDC_TDCMOD_MANUAL;
+ else
+ tdcmod = MCP251XFD_REG_TDC_TDCMOD_DISABLED;
+
+ val = FIELD_PREP(MCP251XFD_REG_TDC_TDCMOD_MASK, tdcmod) |
+ FIELD_PREP(MCP251XFD_REG_TDC_TDCV_MASK, priv->can.tdc.tdcv) |
+ FIELD_PREP(MCP251XFD_REG_TDC_TDCO_MASK, priv->can.tdc.tdco);
return regmap_write(priv->map_reg, MCP251XFD_REG_TDC, val);
}
@@ -2083,10 +2105,12 @@ static int mcp251xfd_probe(struct spi_device *spi)
priv->can.do_get_berr_counter = mcp251xfd_get_berr_counter;
priv->can.bittiming_const = &mcp251xfd_bittiming_const;
priv->can.data_bittiming_const = &mcp251xfd_data_bittiming_const;
+ priv->can.tdc_const = &mcp251xfd_tdc_const;
priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_BERR_REPORTING |
CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO |
- CAN_CTRLMODE_CC_LEN8_DLC;
+ CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO |
+ CAN_CTRLMODE_TDC_MANUAL;
set_bit(MCP251XFD_FLAGS_DOWN, priv->flags);
priv->ndev = ndev;
priv->spi = spi;
@@ -2174,8 +2198,8 @@ static void mcp251xfd_remove(struct spi_device *spi)
struct mcp251xfd_priv *priv = spi_get_drvdata(spi);
struct net_device *ndev = priv->ndev;
- can_rx_offload_del(&priv->offload);
mcp251xfd_unregister(priv);
+ can_rx_offload_del(&priv->offload);
spi->max_speed_hz = priv->spi_max_speed_hz_orig;
free_candev(ndev);
}
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index e5ba71897906..9eb39cfa5fb2 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -373,15 +373,17 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
b53_read8(dev, B53_VLAN_PAGE, B53_VLAN_CTRL5, &vc5);
}
+ vc1 &= ~VC1_RX_MCST_FWD_EN;
+
if (enable) {
vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID;
- vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN;
+ vc1 |= VC1_RX_MCST_UNTAG_EN;
vc4 &= ~VC4_ING_VID_CHECK_MASK;
if (enable_filtering) {
vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S;
vc5 |= VC5_DROP_VTABLE_MISS;
} else {
- vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S;
+ vc4 |= VC4_NO_ING_VID_CHK << VC4_ING_VID_CHECK_S;
vc5 &= ~VC5_DROP_VTABLE_MISS;
}
@@ -393,7 +395,7 @@ static void b53_enable_vlan(struct b53_device *dev, int port, bool enable,
} else {
vc0 &= ~(VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID);
- vc1 &= ~(VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN);
+ vc1 &= ~VC1_RX_MCST_UNTAG_EN;
vc4 &= ~VC4_ING_VID_CHECK_MASK;
vc5 &= ~VC5_DROP_VTABLE_MISS;
@@ -576,6 +578,18 @@ static void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable)
b53_write16(dev, B53_EEE_PAGE, B53_EEE_EN_CTRL, reg);
}
+int b53_setup_port(struct dsa_switch *ds, int port)
+{
+ struct b53_device *dev = ds->priv;
+
+ b53_port_set_ucast_flood(dev, port, true);
+ b53_port_set_mcast_flood(dev, port, true);
+ b53_port_set_learning(dev, port, false);
+
+ return 0;
+}
+EXPORT_SYMBOL(b53_setup_port);
+
int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
{
struct b53_device *dev = ds->priv;
@@ -588,10 +602,6 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy)
cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
- b53_port_set_ucast_flood(dev, port, true);
- b53_port_set_mcast_flood(dev, port, true);
- b53_port_set_learning(dev, port, false);
-
if (dev->ops->irq_enable)
ret = dev->ops->irq_enable(dev, port);
if (ret)
@@ -722,10 +732,6 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port)
b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl);
b53_brcm_hdr_setup(dev->ds, port);
-
- b53_port_set_ucast_flood(dev, port, true);
- b53_port_set_mcast_flood(dev, port, true);
- b53_port_set_learning(dev, port, false);
}
static void b53_enable_mib(struct b53_device *dev)
@@ -761,6 +767,22 @@ static bool b53_vlan_port_needs_forced_tagged(struct dsa_switch *ds, int port)
return dev->tag_protocol == DSA_TAG_PROTO_NONE && dsa_is_cpu_port(ds, port);
}
+static bool b53_vlan_port_may_join_untagged(struct dsa_switch *ds, int port)
+{
+ struct b53_device *dev = ds->priv;
+ struct dsa_port *dp;
+
+ if (!dev->vlan_filtering)
+ return true;
+
+ dp = dsa_to_port(ds, port);
+
+ if (dsa_port_is_cpu(dp))
+ return true;
+
+ return dp->bridge == NULL;
+}
+
int b53_configure_vlan(struct dsa_switch *ds)
{
struct b53_device *dev = ds->priv;
@@ -779,7 +801,7 @@ int b53_configure_vlan(struct dsa_switch *ds)
b53_do_vlan_op(dev, VTA_CMD_CLEAR);
}
- b53_enable_vlan(dev, -1, dev->vlan_enabled, ds->vlan_filtering);
+ b53_enable_vlan(dev, -1, dev->vlan_enabled, dev->vlan_filtering);
/* Create an untagged VLAN entry for the default PVID in case
* CONFIG_VLAN_8021Q is disabled and there are no calls to
@@ -787,26 +809,39 @@ int b53_configure_vlan(struct dsa_switch *ds)
* entry. Do this only when the tagging protocol is not
* DSA_TAG_PROTO_NONE
*/
+ v = &dev->vlans[def_vid];
b53_for_each_port(dev, i) {
- v = &dev->vlans[def_vid];
- v->members |= BIT(i);
+ if (!b53_vlan_port_may_join_untagged(ds, i))
+ continue;
+
+ vl.members |= BIT(i);
if (!b53_vlan_port_needs_forced_tagged(ds, i))
- v->untag = v->members;
- b53_write16(dev, B53_VLAN_PAGE,
- B53_VLAN_PORT_DEF_TAG(i), def_vid);
+ vl.untag = vl.members;
+ b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(i),
+ def_vid);
}
+ b53_set_vlan_entry(dev, def_vid, &vl);
- /* Upon initial call we have not set-up any VLANs, but upon
- * system resume, we need to restore all VLAN entries.
- */
- for (vid = def_vid; vid < dev->num_vlans; vid++) {
- v = &dev->vlans[vid];
+ if (dev->vlan_filtering) {
+ /* Upon initial call we have not set-up any VLANs, but upon
+ * system resume, we need to restore all VLAN entries.
+ */
+ for (vid = def_vid + 1; vid < dev->num_vlans; vid++) {
+ v = &dev->vlans[vid];
- if (!v->members)
- continue;
+ if (!v->members)
+ continue;
+
+ b53_set_vlan_entry(dev, vid, v);
+ b53_fast_age_vlan(dev, vid);
+ }
- b53_set_vlan_entry(dev, vid, v);
- b53_fast_age_vlan(dev, vid);
+ b53_for_each_port(dev, i) {
+ if (!dsa_is_cpu_port(ds, i))
+ b53_write16(dev, B53_VLAN_PAGE,
+ B53_VLAN_PORT_DEF_TAG(i),
+ dev->ports[i].pvid);
+ }
}
return 0;
@@ -1125,7 +1160,9 @@ EXPORT_SYMBOL(b53_setup_devlink_resources);
static int b53_setup(struct dsa_switch *ds)
{
struct b53_device *dev = ds->priv;
+ struct b53_vlan *vl;
unsigned int port;
+ u16 pvid;
int ret;
/* Request bridge PVID untagged when DSA_TAG_PROTO_NONE is set
@@ -1133,12 +1170,26 @@ static int b53_setup(struct dsa_switch *ds)
*/
ds->untag_bridge_pvid = dev->tag_protocol == DSA_TAG_PROTO_NONE;
+ /* The switch does not tell us the original VLAN for untagged
+ * packets, so keep the CPU port always tagged.
+ */
+ ds->untag_vlan_aware_bridge_pvid = true;
+
ret = b53_reset_switch(dev);
if (ret) {
dev_err(ds->dev, "failed to reset switch\n");
return ret;
}
+ /* setup default vlan for filtering mode */
+ pvid = b53_default_pvid(dev);
+ vl = &dev->vlans[pvid];
+ b53_for_each_port(dev, port) {
+ vl->members |= BIT(port);
+ if (!b53_vlan_port_needs_forced_tagged(ds, port))
+ vl->untag |= BIT(port);
+ }
+
b53_reset_mib(dev);
ret = b53_apply_config(dev);
@@ -1492,7 +1543,10 @@ int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering,
{
struct b53_device *dev = ds->priv;
- b53_enable_vlan(dev, port, dev->vlan_enabled, vlan_filtering);
+ if (dev->vlan_filtering != vlan_filtering) {
+ dev->vlan_filtering = vlan_filtering;
+ b53_apply_config(dev);
+ }
return 0;
}
@@ -1517,7 +1571,7 @@ static int b53_vlan_prepare(struct dsa_switch *ds, int port,
if (vlan->vid >= dev->num_vlans)
return -ERANGE;
- b53_enable_vlan(dev, port, true, ds->vlan_filtering);
+ b53_enable_vlan(dev, port, true, dev->vlan_filtering);
return 0;
}
@@ -1530,18 +1584,29 @@ int b53_vlan_add(struct dsa_switch *ds, int port,
bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
struct b53_vlan *vl;
+ u16 old_pvid, new_pvid;
int err;
err = b53_vlan_prepare(ds, port, vlan);
if (err)
return err;
- vl = &dev->vlans[vlan->vid];
+ if (vlan->vid == 0)
+ return 0;
- b53_get_vlan_entry(dev, vlan->vid, vl);
+ old_pvid = dev->ports[port].pvid;
+ if (pvid)
+ new_pvid = vlan->vid;
+ else if (!pvid && vlan->vid == old_pvid)
+ new_pvid = b53_default_pvid(dev);
+ else
+ new_pvid = old_pvid;
+ dev->ports[port].pvid = new_pvid;
+
+ vl = &dev->vlans[vlan->vid];
- if (vlan->vid == 0 && vlan->vid == b53_default_pvid(dev))
- untagged = true;
+ if (dsa_is_cpu_port(ds, port))
+ untagged = false;
vl->members |= BIT(port);
if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
@@ -1549,13 +1614,16 @@ int b53_vlan_add(struct dsa_switch *ds, int port,
else
vl->untag &= ~BIT(port);
+ if (!dev->vlan_filtering)
+ return 0;
+
b53_set_vlan_entry(dev, vlan->vid, vl);
b53_fast_age_vlan(dev, vlan->vid);
- if (pvid && !dsa_is_cpu_port(ds, port)) {
+ if (!dsa_is_cpu_port(ds, port) && new_pvid != old_pvid) {
b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port),
- vlan->vid);
- b53_fast_age_vlan(dev, vlan->vid);
+ new_pvid);
+ b53_fast_age_vlan(dev, old_pvid);
}
return 0;
@@ -1570,20 +1638,25 @@ int b53_vlan_del(struct dsa_switch *ds, int port,
struct b53_vlan *vl;
u16 pvid;
- b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid);
+ if (vlan->vid == 0)
+ return 0;
- vl = &dev->vlans[vlan->vid];
+ pvid = dev->ports[port].pvid;
- b53_get_vlan_entry(dev, vlan->vid, vl);
+ vl = &dev->vlans[vlan->vid];
vl->members &= ~BIT(port);
if (pvid == vlan->vid)
pvid = b53_default_pvid(dev);
+ dev->ports[port].pvid = pvid;
if (untagged && !b53_vlan_port_needs_forced_tagged(ds, port))
vl->untag &= ~(BIT(port));
+ if (!dev->vlan_filtering)
+ return 0;
+
b53_set_vlan_entry(dev, vlan->vid, vl);
b53_fast_age_vlan(dev, vlan->vid);
@@ -1916,8 +1989,9 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
bool *tx_fwd_offload, struct netlink_ext_ack *extack)
{
struct b53_device *dev = ds->priv;
+ struct b53_vlan *vl;
s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
- u16 pvlan, reg;
+ u16 pvlan, reg, pvid;
unsigned int i;
/* On 7278, port 7 which connects to the ASP should only receive
@@ -1926,15 +2000,29 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
if (dev->chip_id == BCM7278_DEVICE_ID && port == 7)
return -EINVAL;
- /* Make this port leave the all VLANs join since we will have proper
- * VLAN entries from now on
- */
- if (is58xx(dev)) {
- b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, ®);
- reg &= ~BIT(port);
- if ((reg & BIT(cpu_port)) == BIT(cpu_port))
- reg &= ~BIT(cpu_port);
- b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
+ pvid = b53_default_pvid(dev);
+ vl = &dev->vlans[pvid];
+
+ if (dev->vlan_filtering) {
+ /* Make this port leave the all VLANs join since we will have
+ * proper VLAN entries from now on
+ */
+ if (is58xx(dev)) {
+ b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN,
+ ®);
+ reg &= ~BIT(port);
+ if ((reg & BIT(cpu_port)) == BIT(cpu_port))
+ reg &= ~BIT(cpu_port);
+ b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN,
+ reg);
+ }
+
+ b53_get_vlan_entry(dev, pvid, vl);
+ vl->members &= ~BIT(port);
+ if (vl->members == BIT(cpu_port))
+ vl->members &= ~BIT(cpu_port);
+ vl->untag = vl->members;
+ b53_set_vlan_entry(dev, pvid, vl);
}
b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan);
@@ -1967,7 +2055,7 @@ EXPORT_SYMBOL(b53_br_join);
void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
{
struct b53_device *dev = ds->priv;
- struct b53_vlan *vl = &dev->vlans[0];
+ struct b53_vlan *vl;
s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index;
unsigned int i;
u16 pvlan, reg, pvid;
@@ -1993,15 +2081,18 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
dev->ports[port].vlan_ctl_mask = pvlan;
pvid = b53_default_pvid(dev);
+ vl = &dev->vlans[pvid];
+
+ if (dev->vlan_filtering) {
+ /* Make this port join all VLANs without VLAN entries */
+ if (is58xx(dev)) {
+ b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, ®);
+ reg |= BIT(port);
+ if (!(reg & BIT(cpu_port)))
+ reg |= BIT(cpu_port);
+ b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
+ }
- /* Make this port join all VLANs without VLAN entries */
- if (is58xx(dev)) {
- b53_read16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, ®);
- reg |= BIT(port);
- if (!(reg & BIT(cpu_port)))
- reg |= BIT(cpu_port);
- b53_write16(dev, B53_VLAN_PAGE, B53_JOIN_ALL_VLAN_EN, reg);
- } else {
b53_get_vlan_entry(dev, pvid, vl);
vl->members |= BIT(port) | BIT(cpu_port);
vl->untag |= BIT(port) | BIT(cpu_port);
@@ -2300,6 +2391,7 @@ static const struct dsa_switch_ops b53_switch_ops = {
.phy_read = b53_phy_read16,
.phy_write = b53_phy_write16,
.phylink_get_caps = b53_phylink_get_caps,
+ .port_setup = b53_setup_port,
.port_enable = b53_enable_port,
.port_disable = b53_disable_port,
.support_eee = b53_support_eee,
@@ -2757,6 +2849,7 @@ struct b53_device *b53_switch_alloc(struct device *base,
ds->ops = &b53_switch_ops;
ds->phylink_mac_ops = &b53_phylink_mac_ops;
dev->vlan_enabled = true;
+ dev->vlan_filtering = false;
/* Let DSA handle the case were multiple bridges span the same switch
* device and different VLAN awareness settings are requested, which
* would be breaking filtering semantics for any of the other bridge
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 0166c37a13a7..2cf3e6a81e37 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -96,6 +96,7 @@ struct b53_pcs {
struct b53_port {
u16 vlan_ctl_mask;
+ u16 pvid;
struct ethtool_keee eee;
};
@@ -147,6 +148,7 @@ struct b53_device {
unsigned int num_vlans;
struct b53_vlan *vlans;
bool vlan_enabled;
+ bool vlan_filtering;
unsigned int num_ports;
struct b53_port *ports;
@@ -382,6 +384,7 @@ enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port,
enum dsa_tag_protocol mprot);
void b53_mirror_del(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror);
+int b53_setup_port(struct dsa_switch *ds, int port);
int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy);
void b53_disable_port(struct dsa_switch *ds, int port);
void b53_brcm_hdr_setup(struct dsa_switch *ds, int port);
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index fa2bf3fa9019..454a8c7fd7ee 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1230,6 +1230,7 @@ static const struct dsa_switch_ops bcm_sf2_ops = {
.resume = bcm_sf2_sw_resume,
.get_wol = bcm_sf2_sw_get_wol,
.set_wol = bcm_sf2_sw_set_wol,
+ .port_setup = b53_setup_port,
.port_enable = bcm_sf2_port_setup,
.port_disable = bcm_sf2_port_disable,
.support_eee = b53_support_eee,
diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c
index 7a5710f9ccf6..ead0625e781f 100644
--- a/drivers/net/ethernet/airoha/airoha_npu.c
+++ b/drivers/net/ethernet/airoha/airoha_npu.c
@@ -104,12 +104,14 @@ struct ppe_mbox_data {
u8 xpon_hal_api;
u8 wan_xsi;
u8 ct_joyme4;
- int ppe_type;
- int wan_mode;
- int wan_sel;
+ u8 max_packet;
+ u8 rsv[3];
+ u32 ppe_type;
+ u32 wan_mode;
+ u32 wan_sel;
} init_info;
struct {
- int func_id;
+ u32 func_id;
u32 size;
u32 data;
} set_info;
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.c b/drivers/net/ethernet/intel/ice/ice_adapter.c
index 01a08cfd0090..66e070095d1b 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.c
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.c
@@ -1,7 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
// SPDX-FileCopyrightText: Copyright Red Hat
-#include <linux/bitfield.h>
#include <linux/cleanup.h>
#include <linux/mutex.h>
#include <linux/pci.h>
@@ -14,32 +13,16 @@
static DEFINE_XARRAY(ice_adapters);
static DEFINE_MUTEX(ice_adapters_mutex);
-/* PCI bus number is 8 bits. Slot is 5 bits. Domain can have the rest. */
-#define INDEX_FIELD_DOMAIN GENMASK(BITS_PER_LONG - 1, 13)
-#define INDEX_FIELD_DEV GENMASK(31, 16)
-#define INDEX_FIELD_BUS GENMASK(12, 5)
-#define INDEX_FIELD_SLOT GENMASK(4, 0)
-
-static unsigned long ice_adapter_index(const struct pci_dev *pdev)
+static unsigned long ice_adapter_index(u64 dsn)
{
- unsigned int domain = pci_domain_nr(pdev->bus);
-
- WARN_ON(domain > FIELD_MAX(INDEX_FIELD_DOMAIN));
-
- switch (pdev->device) {
- case ICE_DEV_ID_E825C_BACKPLANE:
- case ICE_DEV_ID_E825C_QSFP:
- case ICE_DEV_ID_E825C_SFP:
- case ICE_DEV_ID_E825C_SGMII:
- return FIELD_PREP(INDEX_FIELD_DEV, pdev->device);
- default:
- return FIELD_PREP(INDEX_FIELD_DOMAIN, domain) |
- FIELD_PREP(INDEX_FIELD_BUS, pdev->bus->number) |
- FIELD_PREP(INDEX_FIELD_SLOT, PCI_SLOT(pdev->devfn));
- }
+#if BITS_PER_LONG == 64
+ return dsn;
+#else
+ return (u32)dsn ^ (u32)(dsn >> 32);
+#endif
}
-static struct ice_adapter *ice_adapter_new(void)
+static struct ice_adapter *ice_adapter_new(u64 dsn)
{
struct ice_adapter *adapter;
@@ -47,6 +30,7 @@ static struct ice_adapter *ice_adapter_new(void)
if (!adapter)
return NULL;
+ adapter->device_serial_number = dsn;
spin_lock_init(&adapter->ptp_gltsyn_time_lock);
refcount_set(&adapter->refcount, 1);
@@ -77,23 +61,26 @@ static void ice_adapter_free(struct ice_adapter *adapter)
* Return: Pointer to ice_adapter on success.
* ERR_PTR() on error. -ENOMEM is the only possible error.
*/
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev)
{
- unsigned long index = ice_adapter_index(pdev);
+ u64 dsn = pci_get_dsn(pdev);
struct ice_adapter *adapter;
+ unsigned long index;
int err;
+ index = ice_adapter_index(dsn);
scoped_guard(mutex, &ice_adapters_mutex) {
err = xa_insert(&ice_adapters, index, NULL, GFP_KERNEL);
if (err == -EBUSY) {
adapter = xa_load(&ice_adapters, index);
refcount_inc(&adapter->refcount);
+ WARN_ON_ONCE(adapter->device_serial_number != dsn);
return adapter;
}
if (err)
return ERR_PTR(err);
- adapter = ice_adapter_new();
+ adapter = ice_adapter_new(dsn);
if (!adapter)
return ERR_PTR(-ENOMEM);
xa_store(&ice_adapters, index, adapter, GFP_KERNEL);
@@ -110,11 +97,13 @@ struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev)
*
* Context: Process, may sleep.
*/
-void ice_adapter_put(const struct pci_dev *pdev)
+void ice_adapter_put(struct pci_dev *pdev)
{
- unsigned long index = ice_adapter_index(pdev);
+ u64 dsn = pci_get_dsn(pdev);
struct ice_adapter *adapter;
+ unsigned long index;
+ index = ice_adapter_index(dsn);
scoped_guard(mutex, &ice_adapters_mutex) {
adapter = xa_load(&ice_adapters, index);
if (WARN_ON(!adapter))
diff --git a/drivers/net/ethernet/intel/ice/ice_adapter.h b/drivers/net/ethernet/intel/ice/ice_adapter.h
index e233225848b3..ac15c0d2bc1a 100644
--- a/drivers/net/ethernet/intel/ice/ice_adapter.h
+++ b/drivers/net/ethernet/intel/ice/ice_adapter.h
@@ -32,6 +32,7 @@ struct ice_port_list {
* @refcount: Reference count. struct ice_pf objects hold the references.
* @ctrl_pf: Control PF of the adapter
* @ports: Ports list
+ * @device_serial_number: DSN cached for collision detection on 32bit systems
*/
struct ice_adapter {
refcount_t refcount;
@@ -40,9 +41,10 @@ struct ice_adapter {
struct ice_pf *ctrl_pf;
struct ice_port_list ports;
+ u64 device_serial_number;
};
-struct ice_adapter *ice_adapter_get(const struct pci_dev *pdev);
-void ice_adapter_put(const struct pci_dev *pdev);
+struct ice_adapter *ice_adapter_get(struct pci_dev *pdev);
+void ice_adapter_put(struct pci_dev *pdev);
#endif /* _ICE_ADAPTER_H */
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 8fda4ce80d81..22a532695fb0 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -3186,11 +3186,19 @@ static int mtk_dma_init(struct mtk_eth *eth)
static void mtk_dma_free(struct mtk_eth *eth)
{
const struct mtk_soc_data *soc = eth->soc;
- int i;
+ int i, j, txqs = 1;
+
+ if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA))
+ txqs = MTK_QDMA_NUM_QUEUES;
+
+ for (i = 0; i < MTK_MAX_DEVS; i++) {
+ if (!eth->netdev[i])
+ continue;
+
+ for (j = 0; j < txqs; j++)
+ netdev_tx_reset_subqueue(eth->netdev[i], j);
+ }
- for (i = 0; i < MTK_MAX_DEVS; i++)
- if (eth->netdev[i])
- netdev_reset_queue(eth->netdev[i]);
if (!MTK_HAS_CAPS(soc->caps, MTK_SRAM) && eth->scratch_ring) {
dma_free_coherent(eth->dma_dev,
MTK_QDMA_RING_SIZE * soc->tx.desc_size,
@@ -3465,9 +3473,6 @@ static int mtk_open(struct net_device *dev)
}
mtk_gdm_config(eth, target_mac->id, gdm_config);
}
- /* Reset and enable PSE */
- mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
- mtk_w32(eth, 0, MTK_RST_GL);
napi_enable(ð->tx_napi);
napi_enable(ð->rx_napi);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index 4ca7b99ef131..de6b1a340f55 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -154,14 +154,14 @@ struct fbnic_dev *fbnic_devlink_alloc(struct pci_dev *pdev);
void fbnic_devlink_register(struct fbnic_dev *fbd);
void fbnic_devlink_unregister(struct fbnic_dev *fbd);
-int fbnic_fw_enable_mbx(struct fbnic_dev *fbd);
-void fbnic_fw_disable_mbx(struct fbnic_dev *fbd);
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd);
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd);
void fbnic_hwmon_register(struct fbnic_dev *fbd);
void fbnic_hwmon_unregister(struct fbnic_dev *fbd);
-int fbnic_pcs_irq_enable(struct fbnic_dev *fbd);
-void fbnic_pcs_irq_disable(struct fbnic_dev *fbd);
+int fbnic_pcs_request_irq(struct fbnic_dev *fbd);
+void fbnic_pcs_free_irq(struct fbnic_dev *fbd);
void fbnic_napi_name_irqs(struct fbnic_dev *fbd);
int fbnic_napi_request_irq(struct fbnic_dev *fbd,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index 3b12a0ab5906..51bee8072420 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -796,8 +796,10 @@ enum {
/* PUL User Registers */
#define FBNIC_CSR_START_PUL_USER 0x31000 /* CSR section delimiter */
#define FBNIC_PUL_OB_TLP_HDR_AW_CFG 0x3103d /* 0xc40f4 */
+#define FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH CSR_BIT(19)
#define FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME CSR_BIT(18)
#define FBNIC_PUL_OB_TLP_HDR_AR_CFG 0x3103e /* 0xc40f8 */
+#define FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH CSR_BIT(19)
#define FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME CSR_BIT(18)
#define FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0 \
0x3106e /* 0xc41b8 */
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 88db3dacb940..3d9636a6c968 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -17,11 +17,29 @@ static void __fbnic_mbx_wr_desc(struct fbnic_dev *fbd, int mbx_idx,
{
u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
+ /* Write the upper 32b and then the lower 32b. Doing this the
+ * FW can then read lower, upper, lower to verify that the state
+ * of the descriptor wasn't changed mid-transaction.
+ */
fw_wr32(fbd, desc_offset + 1, upper_32_bits(desc));
fw_wrfl(fbd);
fw_wr32(fbd, desc_offset, lower_32_bits(desc));
}
+static void __fbnic_mbx_invalidate_desc(struct fbnic_dev *fbd, int mbx_idx,
+ int desc_idx, u32 desc)
+{
+ u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
+
+ /* For initialization we write the lower 32b of the descriptor first.
+ * This way we can set the state to mark it invalid before we clear the
+ * upper 32b.
+ */
+ fw_wr32(fbd, desc_offset, desc);
+ fw_wrfl(fbd);
+ fw_wr32(fbd, desc_offset + 1, 0);
+}
+
static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
{
u32 desc_offset = FBNIC_IPC_MBX(mbx_idx, desc_idx);
@@ -33,29 +51,41 @@ static u64 __fbnic_mbx_rd_desc(struct fbnic_dev *fbd, int mbx_idx, int desc_idx)
return desc;
}
-static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_reset_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
{
int desc_idx;
+ /* Disable DMA transactions from the device,
+ * and flush any transactions triggered during cleaning
+ */
+ switch (mbx_idx) {
+ case FBNIC_IPC_MBX_RX_IDX:
+ wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+ FBNIC_PUL_OB_TLP_HDR_AW_CFG_FLUSH);
+ break;
+ case FBNIC_IPC_MBX_TX_IDX:
+ wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+ FBNIC_PUL_OB_TLP_HDR_AR_CFG_FLUSH);
+ break;
+ }
+
+ wrfl(fbd);
+
/* Initialize first descriptor to all 0s. Doing this gives us a
* solid stop for the firmware to hit when it is done looping
* through the ring.
*/
- __fbnic_mbx_wr_desc(fbd, mbx_idx, 0, 0);
-
- fw_wrfl(fbd);
+ __fbnic_mbx_invalidate_desc(fbd, mbx_idx, 0, 0);
/* We then fill the rest of the ring starting at the end and moving
* back toward descriptor 0 with skip descriptors that have no
* length nor address, and tell the firmware that they can skip
* them and just move past them to the one we initialized to 0.
*/
- for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;) {
- __fbnic_mbx_wr_desc(fbd, mbx_idx, desc_idx,
- FBNIC_IPC_MBX_DESC_FW_CMPL |
- FBNIC_IPC_MBX_DESC_HOST_CMPL);
- fw_wrfl(fbd);
- }
+ for (desc_idx = FBNIC_IPC_MBX_DESC_LEN; --desc_idx;)
+ __fbnic_mbx_invalidate_desc(fbd, mbx_idx, desc_idx,
+ FBNIC_IPC_MBX_DESC_FW_CMPL |
+ FBNIC_IPC_MBX_DESC_HOST_CMPL);
}
void fbnic_mbx_init(struct fbnic_dev *fbd)
@@ -76,7 +106,7 @@ void fbnic_mbx_init(struct fbnic_dev *fbd)
wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
- fbnic_mbx_init_desc_ring(fbd, i);
+ fbnic_mbx_reset_desc_ring(fbd, i);
}
static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
@@ -141,7 +171,7 @@ static void fbnic_mbx_clean_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
{
int i;
- fbnic_mbx_init_desc_ring(fbd, mbx_idx);
+ fbnic_mbx_reset_desc_ring(fbd, mbx_idx);
for (i = FBNIC_IPC_MBX_DESC_LEN; i--;)
fbnic_mbx_unmap_and_free_msg(fbd, mbx_idx, i);
@@ -322,67 +352,41 @@ static int fbnic_fw_xmit_simple_msg(struct fbnic_dev *fbd, u32 msg_type)
return err;
}
-/**
- * fbnic_fw_xmit_cap_msg - Allocate and populate a FW capabilities message
- * @fbd: FBNIC device structure
- *
- * Return: NULL on failure to allocate, error pointer on error, or pointer
- * to new TLV test message.
- *
- * Sends a single TLV header indicating the host wants the firmware to
- * confirm the capabilities and version.
- **/
-static int fbnic_fw_xmit_cap_msg(struct fbnic_dev *fbd)
-{
- int err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
-
- /* Return 0 if we are not calling this on ASIC */
- return (err == -EOPNOTSUPP) ? 0 : err;
-}
-
-static void fbnic_mbx_postinit_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
+static void fbnic_mbx_init_desc_ring(struct fbnic_dev *fbd, int mbx_idx)
{
struct fbnic_fw_mbx *mbx = &fbd->mbx[mbx_idx];
- /* This is a one time init, so just exit if it is completed */
- if (mbx->ready)
- return;
-
mbx->ready = true;
switch (mbx_idx) {
case FBNIC_IPC_MBX_RX_IDX:
+ /* Enable DMA writes from the device */
+ wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
+ FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
+
/* Make sure we have a page for the FW to write to */
fbnic_mbx_alloc_rx_msgs(fbd);
break;
case FBNIC_IPC_MBX_TX_IDX:
- /* Force version to 1 if we successfully requested an update
- * from the firmware. This should be overwritten once we get
- * the actual version from the firmware in the capabilities
- * request message.
- */
- if (!fbnic_fw_xmit_cap_msg(fbd) &&
- !fbd->fw_cap.running.mgmt.version)
- fbd->fw_cap.running.mgmt.version = 1;
+ /* Enable DMA reads from the device */
+ wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
+ FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
break;
}
}
-static void fbnic_mbx_postinit(struct fbnic_dev *fbd)
+static bool fbnic_mbx_event(struct fbnic_dev *fbd)
{
- int i;
-
- /* We only need to do this on the first interrupt following init.
+ /* We only need to do this on the first interrupt following reset.
* this primes the mailbox so that we will have cleared all the
* skip descriptors.
*/
if (!(rd32(fbd, FBNIC_INTR_STATUS(0)) & (1u << FBNIC_FW_MSIX_ENTRY)))
- return;
+ return false;
wr32(fbd, FBNIC_INTR_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
- for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
- fbnic_mbx_postinit_desc_ring(fbd, i);
+ return true;
}
/**
@@ -859,7 +863,7 @@ static void fbnic_mbx_process_rx_msgs(struct fbnic_dev *fbd)
void fbnic_mbx_poll(struct fbnic_dev *fbd)
{
- fbnic_mbx_postinit(fbd);
+ fbnic_mbx_event(fbd);
fbnic_mbx_process_tx_msgs(fbd);
fbnic_mbx_process_rx_msgs(fbd);
@@ -867,60 +871,97 @@ void fbnic_mbx_poll(struct fbnic_dev *fbd)
int fbnic_mbx_poll_tx_ready(struct fbnic_dev *fbd)
{
- struct fbnic_fw_mbx *tx_mbx;
- int attempts = 50;
+ unsigned long timeout = jiffies + 10 * HZ + 1;
+ int err, i;
- /* Immediate fail if BAR4 isn't there */
- if (!fbnic_fw_present(fbd))
- return -ENODEV;
+ do {
+ if (!time_is_after_jiffies(timeout))
+ return -ETIMEDOUT;
- tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
- while (!tx_mbx->ready && --attempts) {
/* Force the firmware to trigger an interrupt response to
* avoid the mailbox getting stuck closed if the interrupt
* is reset.
*/
- fbnic_mbx_init_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
+ fbnic_mbx_reset_desc_ring(fbd, FBNIC_IPC_MBX_TX_IDX);
- msleep(200);
+ /* Immediate fail if BAR4 went away */
+ if (!fbnic_fw_present(fbd))
+ return -ENODEV;
- fbnic_mbx_poll(fbd);
- }
+ msleep(20);
+ } while (!fbnic_mbx_event(fbd));
+
+ /* FW has shown signs of life. Enable DMA and start Tx/Rx */
+ for (i = 0; i < FBNIC_IPC_MBX_INDICES; i++)
+ fbnic_mbx_init_desc_ring(fbd, i);
+
+ /* Request an update from the firmware. This should overwrite
+ * mgmt.version once we get the actual version from the firmware
+ * in the capabilities request message.
+ */
+ err = fbnic_fw_xmit_simple_msg(fbd, FBNIC_TLV_MSG_ID_HOST_CAP_REQ);
+ if (err)
+ goto clean_mbx;
+
+ /* Use "1" to indicate we entered the state waiting for a response */
+ fbd->fw_cap.running.mgmt.version = 1;
+
+ return 0;
+clean_mbx:
+ /* Cleanup Rx buffers and disable mailbox */
+ fbnic_mbx_clean(fbd);
+ return err;
+}
+
+static void __fbnic_fw_evict_cmpl(struct fbnic_fw_completion *cmpl_data)
+{
+ cmpl_data->result = -EPIPE;
+ complete(&cmpl_data->done);
+}
- return attempts ? 0 : -ETIMEDOUT;
+static void fbnic_mbx_evict_all_cmpl(struct fbnic_dev *fbd)
+{
+ if (fbd->cmpl_data) {
+ __fbnic_fw_evict_cmpl(fbd->cmpl_data);
+ fbd->cmpl_data = NULL;
+ }
}
void fbnic_mbx_flush_tx(struct fbnic_dev *fbd)
{
+ unsigned long timeout = jiffies + 10 * HZ + 1;
struct fbnic_fw_mbx *tx_mbx;
- int attempts = 50;
- u8 count = 0;
-
- /* Nothing to do if there is no mailbox */
- if (!fbnic_fw_present(fbd))
- return;
+ u8 tail;
/* Record current Rx stats */
tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX];
- /* Nothing to do if mailbox never got to ready */
- if (!tx_mbx->ready)
- return;
+ spin_lock_irq(&fbd->fw_tx_lock);
+
+ /* Clear ready to prevent any further attempts to transmit */
+ tx_mbx->ready = false;
+
+ /* Read tail to determine the last tail state for the ring */
+ tail = tx_mbx->tail;
+
+ /* Flush any completions as we are no longer processing Rx */
+ fbnic_mbx_evict_all_cmpl(fbd);
+
+ spin_unlock_irq(&fbd->fw_tx_lock);
/* Give firmware time to process packet,
- * we will wait up to 10 seconds which is 50 waits of 200ms.
+ * we will wait up to 10 seconds which is 500 waits of 20ms.
*/
do {
u8 head = tx_mbx->head;
- if (head == tx_mbx->tail)
+ /* Tx ring is empty once head == tail */
+ if (head == tail)
break;
- msleep(200);
+ msleep(20);
fbnic_mbx_process_tx_msgs(fbd);
-
- count += (tx_mbx->head - head) % FBNIC_IPC_MBX_DESC_LEN;
- } while (count < FBNIC_IPC_MBX_DESC_LEN && --attempts);
+ } while (time_is_after_jiffies(timeout));
}
void fbnic_get_fw_ver_commit_str(struct fbnic_dev *fbd, char *fw_version,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
index 1bbc0e56f3a0..1c88a2bf3a7a 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c
@@ -19,69 +19,105 @@ static irqreturn_t fbnic_fw_msix_intr(int __always_unused irq, void *data)
return IRQ_HANDLED;
}
+static int __fbnic_fw_enable_mbx(struct fbnic_dev *fbd, int vector)
+{
+ int err;
+
+ /* Initialize mailbox and attempt to poll it into ready state */
+ fbnic_mbx_init(fbd);
+ err = fbnic_mbx_poll_tx_ready(fbd);
+ if (err) {
+ dev_warn(fbd->dev, "FW mailbox did not enter ready state\n");
+ return err;
+ }
+
+ /* Enable interrupt and unmask the vector */
+ enable_irq(vector);
+ fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
+
+ return 0;
+}
+
/**
- * fbnic_fw_enable_mbx - Configure and initialize Firmware Mailbox
+ * fbnic_fw_request_mbx - Configure and initialize Firmware Mailbox
* @fbd: Pointer to device to initialize
*
- * This function will initialize the firmware mailbox rings, enable the IRQ
- * and initialize the communication between the Firmware and the host. The
- * firmware is expected to respond to the initialization by sending an
- * interrupt essentially notifying the host that it has seen the
- * initialization and is now synced up.
+ * This function will allocate the IRQ and then reinitialize the mailbox
+ * starting communication between the host and firmware.
*
* Return: non-zero on failure.
**/
-int fbnic_fw_enable_mbx(struct fbnic_dev *fbd)
+int fbnic_fw_request_mbx(struct fbnic_dev *fbd)
{
- u32 vector = fbd->fw_msix_vector;
- int err;
+ struct pci_dev *pdev = to_pci_dev(fbd->dev);
+ int vector, err;
+
+ WARN_ON(fbd->fw_msix_vector);
+
+ vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY);
+ if (vector < 0)
+ return vector;
/* Request the IRQ for FW Mailbox vector. */
err = request_threaded_irq(vector, NULL, &fbnic_fw_msix_intr,
- IRQF_ONESHOT, dev_name(fbd->dev), fbd);
+ IRQF_ONESHOT | IRQF_NO_AUTOEN,
+ dev_name(fbd->dev), fbd);
if (err)
return err;
/* Initialize mailbox and attempt to poll it into ready state */
- fbnic_mbx_init(fbd);
- err = fbnic_mbx_poll_tx_ready(fbd);
- if (err) {
- dev_warn(fbd->dev, "FW mailbox did not enter ready state\n");
+ err = __fbnic_fw_enable_mbx(fbd, vector);
+ if (err)
free_irq(vector, fbd);
- return err;
- }
- /* Enable interrupts */
- fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_FW_MSIX_ENTRY);
+ fbd->fw_msix_vector = vector;
- return 0;
+ return err;
}
/**
- * fbnic_fw_disable_mbx - Disable mailbox and place it in standby state
- * @fbd: Pointer to device to disable
+ * fbnic_fw_disable_mbx - Temporarily place mailbox in standby state
+ * @fbd: Pointer to device
*
- * This function will disable the mailbox interrupt, free any messages still
- * in the mailbox and place it into a standby state. The firmware is
- * expected to see the update and assume that the host is in the reset state.
+ * Shutdown the mailbox by notifying the firmware to stop sending us logs, mask
+ * and synchronize the IRQ, and then clean up the rings.
**/
-void fbnic_fw_disable_mbx(struct fbnic_dev *fbd)
+static void fbnic_fw_disable_mbx(struct fbnic_dev *fbd)
{
- /* Disable interrupt and free vector */
- fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY);
+ /* Disable interrupt and synchronize the IRQ */
+ disable_irq(fbd->fw_msix_vector);
- /* Free the vector */
- free_irq(fbd->fw_msix_vector, fbd);
+ /* Mask the vector */
+ fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_FW_MSIX_ENTRY);
/* Make sure disabling logs message is sent, must be done here to
* avoid risk of completing without a running interrupt.
*/
fbnic_mbx_flush_tx(fbd);
-
- /* Reset the mailboxes to the initialized state */
fbnic_mbx_clean(fbd);
}
+/**
+ * fbnic_fw_free_mbx - Disable mailbox and place it in standby state
+ * @fbd: Pointer to device to disable
+ *
+ * This function will disable the mailbox interrupt, free any messages still
+ * in the mailbox and place it into a disabled state. The firmware is
+ * expected to see the update and assume that the host is in the reset state.
+ **/
+void fbnic_fw_free_mbx(struct fbnic_dev *fbd)
+{
+ /* Vector has already been freed */
+ if (!fbd->fw_msix_vector)
+ return;
+
+ fbnic_fw_disable_mbx(fbd);
+
+ /* Free the vector */
+ free_irq(fbd->fw_msix_vector, fbd);
+ fbd->fw_msix_vector = 0;
+}
+
static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
{
struct fbnic_dev *fbd = data;
@@ -101,7 +137,7 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
}
/**
- * fbnic_pcs_irq_enable - Configure the MAC to enable it to advertise link
+ * fbnic_pcs_request_irq - Configure the PCS to enable it to advertise link
* @fbd: Pointer to device to initialize
*
* This function provides basic bringup for the MAC/PCS IRQ. For now the IRQ
@@ -109,41 +145,61 @@ static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data)
*
* Return: non-zero on failure.
**/
-int fbnic_pcs_irq_enable(struct fbnic_dev *fbd)
+int fbnic_pcs_request_irq(struct fbnic_dev *fbd)
{
- u32 vector = fbd->pcs_msix_vector;
- int err;
+ struct pci_dev *pdev = to_pci_dev(fbd->dev);
+ int vector, err;
- /* Request the IRQ for MAC link vector.
- * Map MAC cause to it, and unmask it
+ WARN_ON(fbd->pcs_msix_vector);
+
+ vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY);
+ if (vector < 0)
+ return vector;
+
+ /* Request the IRQ for PCS link vector.
+ * Map PCS cause to it, and unmask it
*/
err = request_irq(vector, &fbnic_pcs_msix_intr, 0,
fbd->netdev->name, fbd);
if (err)
return err;
+ /* Map and enable interrupt, unmask vector after link is configured */
fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
FBNIC_PCS_MSIX_ENTRY | FBNIC_INTR_MSIX_CTRL_ENABLE);
+ fbd->pcs_msix_vector = vector;
+
return 0;
}
/**
- * fbnic_pcs_irq_disable - Teardown the MAC IRQ to prepare for stopping
+ * fbnic_pcs_free_irq - Teardown the PCS IRQ to prepare for stopping
* @fbd: Pointer to device that is stopping
*
- * This function undoes the work done in fbnic_pcs_irq_enable and prepares
+ * This function undoes the work done in fbnic_pcs_request_irq and prepares
* the device to no longer receive traffic on the host interface.
**/
-void fbnic_pcs_irq_disable(struct fbnic_dev *fbd)
+void fbnic_pcs_free_irq(struct fbnic_dev *fbd)
{
+ /* Vector has already been freed */
+ if (!fbd->pcs_msix_vector)
+ return;
+
/* Disable interrupt */
fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX),
FBNIC_PCS_MSIX_ENTRY);
+ fbnic_wrfl(fbd);
+
+ /* Synchronize IRQ to prevent race that would unmask vector */
+ synchronize_irq(fbd->pcs_msix_vector);
+
+ /* Mask the vector */
fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_PCS_MSIX_ENTRY);
/* Free the vector */
free_irq(fbd->pcs_msix_vector, fbd);
+ fbd->pcs_msix_vector = 0;
}
void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr)
@@ -226,9 +282,6 @@ void fbnic_free_irqs(struct fbnic_dev *fbd)
{
struct pci_dev *pdev = to_pci_dev(fbd->dev);
- fbd->pcs_msix_vector = 0;
- fbd->fw_msix_vector = 0;
-
fbd->num_irqs = 0;
pci_free_irq_vectors(pdev);
@@ -254,8 +307,5 @@ int fbnic_alloc_irqs(struct fbnic_dev *fbd)
fbd->num_irqs = num_irqs;
- fbd->pcs_msix_vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY);
- fbd->fw_msix_vector = pci_irq_vector(pdev, FBNIC_FW_MSIX_ENTRY);
-
return 0;
}
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
index 14291401f463..dde4a37116e2 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
@@ -79,12 +79,6 @@ static void fbnic_mac_init_axi(struct fbnic_dev *fbd)
fbnic_init_readrq(fbd, FBNIC_QM_RNI_RBP_CTL, cls, readrq);
fbnic_init_mps(fbd, FBNIC_QM_RNI_RDE_CTL, cls, mps);
fbnic_init_mps(fbd, FBNIC_QM_RNI_RCM_CTL, cls, mps);
-
- /* Enable XALI AR/AW outbound */
- wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AW_CFG,
- FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME);
- wr32(fbd, FBNIC_PUL_OB_TLP_HDR_AR_CFG,
- FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME);
}
static void fbnic_mac_init_qm(struct fbnic_dev *fbd)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index 79a01fdd1dd1..2524d9b88d59 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -44,9 +44,10 @@ int __fbnic_open(struct fbnic_net *fbn)
if (err)
goto time_stop;
- err = fbnic_pcs_irq_enable(fbd);
+ err = fbnic_pcs_request_irq(fbd);
if (err)
goto time_stop;
+
/* Pull the BMC config and initialize the RPC */
fbnic_bmc_rpc_init(fbd);
fbnic_rss_reinit(fbd, fbn);
@@ -82,7 +83,7 @@ static int fbnic_stop(struct net_device *netdev)
struct fbnic_net *fbn = netdev_priv(netdev);
fbnic_down(fbn);
- fbnic_pcs_irq_disable(fbn->fbd);
+ fbnic_pcs_free_irq(fbn->fbd);
fbnic_time_stop(fbn);
fbnic_fw_xmit_ownership_msg(fbn->fbd, false);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
index 6cbbc2ee3e1f..4e8595239c0f 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
@@ -283,7 +283,7 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
goto free_irqs;
}
- err = fbnic_fw_enable_mbx(fbd);
+ err = fbnic_fw_request_mbx(fbd);
if (err) {
dev_err(&pdev->dev,
"Firmware mailbox initialization failure\n");
@@ -363,7 +363,7 @@ static void fbnic_remove(struct pci_dev *pdev)
fbnic_hwmon_unregister(fbd);
fbnic_dbg_fbd_exit(fbd);
fbnic_devlink_unregister(fbd);
- fbnic_fw_disable_mbx(fbd);
+ fbnic_fw_free_mbx(fbd);
fbnic_free_irqs(fbd);
fbnic_devlink_free(fbd);
@@ -387,7 +387,7 @@ static int fbnic_pm_suspend(struct device *dev)
rtnl_unlock();
null_uc_addr:
- fbnic_fw_disable_mbx(fbd);
+ fbnic_fw_free_mbx(fbd);
/* Free the IRQs so they aren't trying to occupy sleeping CPUs */
fbnic_free_irqs(fbd);
@@ -420,7 +420,7 @@ static int __fbnic_pm_resume(struct device *dev)
fbd->mac->init_regs(fbd);
/* Re-enable mailbox */
- err = fbnic_fw_enable_mbx(fbd);
+ err = fbnic_fw_request_mbx(fbd);
if (err)
goto err_free_irqs;
@@ -438,15 +438,15 @@ static int __fbnic_pm_resume(struct device *dev)
if (netif_running(netdev)) {
err = __fbnic_open(fbn);
if (err)
- goto err_disable_mbx;
+ goto err_free_mbx;
}
rtnl_unlock();
return 0;
-err_disable_mbx:
+err_free_mbx:
rtnl_unlock();
- fbnic_fw_disable_mbx(fbd);
+ fbnic_fw_free_mbx(fbd);
err_free_irqs:
fbnic_free_irqs(fbd);
err_invalidate_uc_addr:
diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index b4be76e13a2f..d88a0180294e 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -187,7 +187,6 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
xdp_return_frame(xdpf);
break;
default:
- netdev_err(ndev, "tx_complete: invalid swdata type %d\n", swdata->type);
prueth_xmit_free(tx_chn, desc_tx);
ndev->stats.tx_dropped++;
continue;
@@ -567,6 +566,7 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
{
struct cppi5_host_desc_t *first_desc;
struct net_device *ndev = emac->ndev;
+ struct netdev_queue *netif_txq;
struct prueth_tx_chn *tx_chn;
dma_addr_t desc_dma, buf_dma;
struct prueth_swdata *swdata;
@@ -620,12 +620,17 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
swdata->data.xdpf = xdpf;
}
+ /* Report BQL before sending the packet */
+ netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
+ netdev_tx_sent_queue(netif_txq, xdpf->len);
+
cppi5_hdesc_set_pktlen(first_desc, xdpf->len);
desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
if (ret) {
netdev_err(ndev, "xdp tx: push failed: %d\n", ret);
+ netdev_tx_completed_queue(netif_txq, 1, xdpf->len);
goto drop_free_descs;
}
@@ -650,6 +655,8 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
struct page *page, u32 *len)
{
struct net_device *ndev = emac->ndev;
+ struct netdev_queue *netif_txq;
+ int cpu = smp_processor_id();
struct bpf_prog *xdp_prog;
struct xdp_frame *xdpf;
u32 pkt_len = *len;
@@ -669,8 +676,11 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
goto drop;
}
- q_idx = smp_processor_id() % emac->tx_ch_num;
+ q_idx = cpu % emac->tx_ch_num;
+ netif_txq = netdev_get_tx_queue(ndev, q_idx);
+ __netif_tx_lock(netif_txq, cpu);
result = emac_xmit_xdp_frame(emac, xdpf, page, q_idx);
+ __netif_tx_unlock(netif_txq);
if (result == ICSSG_XDP_CONSUMED) {
ndev->stats.tx_dropped++;
goto drop;
@@ -979,6 +989,7 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev
ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
if (ret) {
netdev_err(ndev, "tx: push failed: %d\n", ret);
+ netdev_tx_completed_queue(netif_txq, 1, pkt_len);
goto drop_free_descs;
}
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 443f90fa6557..86fc1278127c 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1075,17 +1075,21 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame
{
struct prueth_emac *emac = netdev_priv(dev);
struct net_device *ndev = emac->ndev;
+ struct netdev_queue *netif_txq;
+ int cpu = smp_processor_id();
struct xdp_frame *xdpf;
unsigned int q_idx;
int nxmit = 0;
u32 err;
int i;
- q_idx = smp_processor_id() % emac->tx_ch_num;
+ q_idx = cpu % emac->tx_ch_num;
+ netif_txq = netdev_get_tx_queue(ndev, q_idx);
if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
return -EINVAL;
+ __netif_tx_lock(netif_txq, cpu);
for (i = 0; i < n; i++) {
xdpf = frames[i];
err = emac_xmit_xdp_frame(emac, xdpf, NULL, q_idx);
@@ -1095,6 +1099,7 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame
}
nxmit++;
}
+ __netif_tx_unlock(netif_txq);
return nxmit;
}
@@ -1109,11 +1114,6 @@ static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frame
static int emac_xdp_setup(struct prueth_emac *emac, struct netdev_bpf *bpf)
{
struct bpf_prog *prog = bpf->prog;
- xdp_features_t val;
-
- val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
- NETDEV_XDP_ACT_NDO_XMIT;
- xdp_set_features_flag(emac->ndev, val);
if (!emac->xdpi.prog && !prog)
return 0;
@@ -1291,6 +1291,10 @@ static int prueth_netdev_init(struct prueth *prueth,
ndev->hw_features = NETIF_F_SG;
ndev->features = ndev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER;
ndev->hw_features |= NETIF_PRUETH_HSR_OFFLOAD_FEATURES;
+ xdp_set_features_flag(ndev,
+ NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT);
netif_napi_add(ndev, &emac->napi_rx, icssg_napi_rx_poll);
hrtimer_setup(&emac->rx_hrtimer, &emac_rx_timer_callback, CLOCK_MONOTONIC,
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 848fab51dfa1..e53ba600605a 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3383,12 +3383,15 @@ static void __virtnet_rx_resume(struct virtnet_info *vi,
bool refill)
{
bool running = netif_running(vi->dev);
+ bool schedule_refill = false;
if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))
- schedule_delayed_work(&vi->refill, 0);
-
+ schedule_refill = true;
if (running)
virtnet_napi_enable(rq);
+
+ if (schedule_refill)
+ schedule_delayed_work(&vi->refill, 0);
}
static void virtnet_rx_resume_all(struct virtnet_info *vi)
@@ -3728,8 +3731,10 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
succ:
vi->curr_queue_pairs = queue_pairs;
/* virtnet_open() will refill when device is going to up. */
- if (dev->flags & IFF_UP)
+ spin_lock_bh(&vi->refill_lock);
+ if (dev->flags & IFF_UP && vi->refill_enabled)
schedule_delayed_work(&vi->refill, 0);
+ spin_unlock_bh(&vi->refill_lock);
return 0;
}
@@ -5673,6 +5678,10 @@ static void virtnet_get_base_stats(struct net_device *dev,
if (vi->device_stats_cap & VIRTIO_NET_STATS_TYPE_TX_SPEED)
tx->hw_drop_ratelimits = 0;
+
+ netdev_stat_queue_sum(dev,
+ dev->real_num_rx_queues, vi->max_queue_pairs, rx,
+ dev->real_num_tx_queues, vi->max_queue_pairs, tx);
}
static const struct netdev_stat_ops virtnet_stat_ops = {
@@ -5885,8 +5894,10 @@ static int virtnet_xsk_pool_enable(struct net_device *dev,
hdr_dma = virtqueue_dma_map_single_attrs(sq->vq, &xsk_hdr, vi->hdr_len,
DMA_TO_DEVICE, 0);
- if (virtqueue_dma_mapping_error(sq->vq, hdr_dma))
- return -ENOMEM;
+ if (virtqueue_dma_mapping_error(sq->vq, hdr_dma)) {
+ err = -ENOMEM;
+ goto err_free_buffs;
+ }
err = xsk_pool_dma_map(pool, dma_dev, 0);
if (err)
@@ -5914,6 +5925,8 @@ static int virtnet_xsk_pool_enable(struct net_device *dev,
err_xsk_map:
virtqueue_dma_unmap_single_attrs(rq->vq, hdr_dma, vi->hdr_len,
DMA_TO_DEVICE, 0);
+err_free_buffs:
+ kvfree(rq->xsk_buffs);
return err;
}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index debeea2b3ae5..00056e76ea3d 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -588,6 +588,8 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
IWL_DEV_INFO(0x7A70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
IWL_DEV_INFO(0x7AF0, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name),
IWL_DEV_INFO(0x7AF0, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
+ IWL_DEV_INFO(0x7F70, 0x1691, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690s_name),
+ IWL_DEV_INFO(0x7F70, 0x1692, iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_killer_1690i_name),
IWL_DEV_INFO(0x271C, 0x0214, iwl9260_2ac_cfg, iwl9260_1_name),
IWL_DEV_INFO(0x7E40, 0x1691, iwl_cfg_ma, iwl_ax411_killer_1690s_name),
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 508d466de1cc..457b4fba88bd 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1526,7 +1526,7 @@ struct ieee80211_mgmt {
struct {
u8 action_code;
u8 dialog_token;
- u8 status_code;
+ __le16 status_code;
u8 variable[];
} __packed ttlm_res;
struct {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2d11d013cabe..7ea022750e4e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4972,6 +4972,7 @@ static inline void __dev_mc_unsync(struct net_device *dev,
/* Functions used for secondary unicast and multicast support */
void dev_set_rx_mode(struct net_device *dev);
+int netif_set_promiscuity(struct net_device *dev, int inc);
int dev_set_promiscuity(struct net_device *dev, int inc);
int netif_set_allmulti(struct net_device *dev, int inc, bool notify);
int dev_set_allmulti(struct net_device *dev, int inc);
diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index 825141d675e5..d01c82983b4d 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -103,6 +103,12 @@ struct netdev_stat_ops {
struct netdev_queue_stats_tx *tx);
};
+void netdev_stat_queue_sum(struct net_device *netdev,
+ int rx_start, int rx_end,
+ struct netdev_queue_stats_rx *rx_sum,
+ int tx_start, int tx_end,
+ struct netdev_queue_stats_tx *tx_sum);
+
/**
* struct netdev_queue_mgmt_ops - netdev ops for queue management
*
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 28705ae67784..fd404729b115 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -4968,6 +4968,9 @@ union bpf_attr {
* the netns switch takes place from ingress to ingress without
* going through the CPU's backlog queue.
*
+ * *skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during
+ * the netns switch.
+ *
* The *flags* argument is reserved and must be 0. The helper is
* currently only supported for tc BPF program types at the
* ingress hook and for veth and netkit target device types. The
diff --git a/net/can/gw.c b/net/can/gw.c
index ef93293c1fae..55eccb1c7620 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -130,7 +130,7 @@ struct cgw_job {
u32 handled_frames;
u32 dropped_frames;
u32 deleted_frames;
- struct cf_mod mod;
+ struct cf_mod __rcu *cf_mod;
union {
/* CAN frame data source */
struct net_device *dev;
@@ -459,6 +459,7 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
struct cgw_job *gwj = (struct cgw_job *)data;
struct canfd_frame *cf;
struct sk_buff *nskb;
+ struct cf_mod *mod;
int modidx = 0;
/* process strictly Classic CAN or CAN FD frames */
@@ -506,7 +507,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
* When there is at least one modification function activated,
* we need to copy the skb as we want to modify skb->data.
*/
- if (gwj->mod.modfunc[0])
+ mod = rcu_dereference(gwj->cf_mod);
+ if (mod->modfunc[0])
nskb = skb_copy(skb, GFP_ATOMIC);
else
nskb = skb_clone(skb, GFP_ATOMIC);
@@ -529,8 +531,8 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
cf = (struct canfd_frame *)nskb->data;
/* perform preprocessed modification functions if there are any */
- while (modidx < MAX_MODFUNCTIONS && gwj->mod.modfunc[modidx])
- (*gwj->mod.modfunc[modidx++])(cf, &gwj->mod);
+ while (modidx < MAX_MODFUNCTIONS && mod->modfunc[modidx])
+ (*mod->modfunc[modidx++])(cf, mod);
/* Has the CAN frame been modified? */
if (modidx) {
@@ -546,11 +548,11 @@ static void can_can_gw_rcv(struct sk_buff *skb, void *data)
}
/* check for checksum updates */
- if (gwj->mod.csumfunc.crc8)
- (*gwj->mod.csumfunc.crc8)(cf, &gwj->mod.csum.crc8);
+ if (mod->csumfunc.crc8)
+ (*mod->csumfunc.crc8)(cf, &mod->csum.crc8);
- if (gwj->mod.csumfunc.xor)
- (*gwj->mod.csumfunc.xor)(cf, &gwj->mod.csum.xor);
+ if (mod->csumfunc.xor)
+ (*mod->csumfunc.xor)(cf, &mod->csum.xor);
}
/* clear the skb timestamp if not configured the other way */
@@ -581,9 +583,20 @@ static void cgw_job_free_rcu(struct rcu_head *rcu_head)
{
struct cgw_job *gwj = container_of(rcu_head, struct cgw_job, rcu);
+ /* cgw_job::cf_mod is always accessed from the same cgw_job object within
+ * the same RCU read section. Once cgw_job is scheduled for removal,
+ * cf_mod can also be removed without mandating an additional grace period.
+ */
+ kfree(rcu_access_pointer(gwj->cf_mod));
kmem_cache_free(cgw_cache, gwj);
}
+/* Return cgw_job::cf_mod with RTNL protected section */
+static struct cf_mod *cgw_job_cf_mod(struct cgw_job *gwj)
+{
+ return rcu_dereference_protected(gwj->cf_mod, rtnl_is_locked());
+}
+
static int cgw_notifier(struct notifier_block *nb,
unsigned long msg, void *ptr)
{
@@ -616,6 +629,7 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type,
{
struct rtcanmsg *rtcan;
struct nlmsghdr *nlh;
+ struct cf_mod *mod;
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtcan), flags);
if (!nlh)
@@ -650,82 +664,83 @@ static int cgw_put_job(struct sk_buff *skb, struct cgw_job *gwj, int type,
goto cancel;
}
+ mod = cgw_job_cf_mod(gwj);
if (gwj->flags & CGW_FLAGS_CAN_FD) {
struct cgw_fdframe_mod mb;
- if (gwj->mod.modtype.and) {
- memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.and;
+ if (mod->modtype.and) {
+ memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf));
+ mb.modtype = mod->modtype.and;
if (nla_put(skb, CGW_FDMOD_AND, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.or) {
- memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.or;
+ if (mod->modtype.or) {
+ memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf));
+ mb.modtype = mod->modtype.or;
if (nla_put(skb, CGW_FDMOD_OR, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.xor) {
- memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.xor;
+ if (mod->modtype.xor) {
+ memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf));
+ mb.modtype = mod->modtype.xor;
if (nla_put(skb, CGW_FDMOD_XOR, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.set) {
- memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.set;
+ if (mod->modtype.set) {
+ memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf));
+ mb.modtype = mod->modtype.set;
if (nla_put(skb, CGW_FDMOD_SET, sizeof(mb), &mb) < 0)
goto cancel;
}
} else {
struct cgw_frame_mod mb;
- if (gwj->mod.modtype.and) {
- memcpy(&mb.cf, &gwj->mod.modframe.and, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.and;
+ if (mod->modtype.and) {
+ memcpy(&mb.cf, &mod->modframe.and, sizeof(mb.cf));
+ mb.modtype = mod->modtype.and;
if (nla_put(skb, CGW_MOD_AND, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.or) {
- memcpy(&mb.cf, &gwj->mod.modframe.or, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.or;
+ if (mod->modtype.or) {
+ memcpy(&mb.cf, &mod->modframe.or, sizeof(mb.cf));
+ mb.modtype = mod->modtype.or;
if (nla_put(skb, CGW_MOD_OR, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.xor) {
- memcpy(&mb.cf, &gwj->mod.modframe.xor, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.xor;
+ if (mod->modtype.xor) {
+ memcpy(&mb.cf, &mod->modframe.xor, sizeof(mb.cf));
+ mb.modtype = mod->modtype.xor;
if (nla_put(skb, CGW_MOD_XOR, sizeof(mb), &mb) < 0)
goto cancel;
}
- if (gwj->mod.modtype.set) {
- memcpy(&mb.cf, &gwj->mod.modframe.set, sizeof(mb.cf));
- mb.modtype = gwj->mod.modtype.set;
+ if (mod->modtype.set) {
+ memcpy(&mb.cf, &mod->modframe.set, sizeof(mb.cf));
+ mb.modtype = mod->modtype.set;
if (nla_put(skb, CGW_MOD_SET, sizeof(mb), &mb) < 0)
goto cancel;
}
}
- if (gwj->mod.uid) {
- if (nla_put_u32(skb, CGW_MOD_UID, gwj->mod.uid) < 0)
+ if (mod->uid) {
+ if (nla_put_u32(skb, CGW_MOD_UID, mod->uid) < 0)
goto cancel;
}
- if (gwj->mod.csumfunc.crc8) {
+ if (mod->csumfunc.crc8) {
if (nla_put(skb, CGW_CS_CRC8, CGW_CS_CRC8_LEN,
- &gwj->mod.csum.crc8) < 0)
+ &mod->csum.crc8) < 0)
goto cancel;
}
- if (gwj->mod.csumfunc.xor) {
+ if (mod->csumfunc.xor) {
if (nla_put(skb, CGW_CS_XOR, CGW_CS_XOR_LEN,
- &gwj->mod.csum.xor) < 0)
+ &mod->csum.xor) < 0)
goto cancel;
}
@@ -1059,7 +1074,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net *net = sock_net(skb->sk);
struct rtcanmsg *r;
struct cgw_job *gwj;
- struct cf_mod mod;
+ struct cf_mod *mod;
struct can_can_gw ccgw;
u8 limhops = 0;
int err = 0;
@@ -1078,37 +1093,48 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh,
if (r->gwtype != CGW_TYPE_CAN_CAN)
return -EINVAL;
- err = cgw_parse_attr(nlh, &mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops);
+ mod = kmalloc(sizeof(*mod), GFP_KERNEL);
+ if (!mod)
+ return -ENOMEM;
+
+ err = cgw_parse_attr(nlh, mod, CGW_TYPE_CAN_CAN, &ccgw, &limhops);
if (err < 0)
- return err;
+ goto out_free_cf;
- if (mod.uid) {
+ if (mod->uid) {
ASSERT_RTNL();
/* check for updating an existing job with identical uid */
hlist_for_each_entry(gwj, &net->can.cgw_list, list) {
- if (gwj->mod.uid != mod.uid)
+ struct cf_mod *old_cf;
+
+ old_cf = cgw_job_cf_mod(gwj);
+ if (old_cf->uid != mod->uid)
continue;
/* interfaces & filters must be identical */
- if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw)))
- return -EINVAL;
+ if (memcmp(&gwj->ccgw, &ccgw, sizeof(ccgw))) {
+ err = -EINVAL;
+ goto out_free_cf;
+ }
- /* update modifications with disabled softirq & quit */
- local_bh_disable();
- memcpy(&gwj->mod, &mod, sizeof(mod));
- local_bh_enable();
+ rcu_assign_pointer(gwj->cf_mod, mod);
+ kfree_rcu_mightsleep(old_cf);
return 0;
}
}
/* ifindex == 0 is not allowed for job creation */
- if (!ccgw.src_idx || !ccgw.dst_idx)
- return -ENODEV;
+ if (!ccgw.src_idx || !ccgw.dst_idx) {
+ err = -ENODEV;
+ goto out_free_cf;
+ }
gwj = kmem_cache_alloc(cgw_cache, GFP_KERNEL);
- if (!gwj)
- return -ENOMEM;
+ if (!gwj) {
+ err = -ENOMEM;
+ goto out_free_cf;
+ }
gwj->handled_frames = 0;
gwj->dropped_frames = 0;
@@ -1118,7 +1144,7 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh,
gwj->limit_hops = limhops;
/* insert already parsed information */
- memcpy(&gwj->mod, &mod, sizeof(mod));
+ RCU_INIT_POINTER(gwj->cf_mod, mod);
memcpy(&gwj->ccgw, &ccgw, sizeof(ccgw));
err = -ENODEV;
@@ -1152,9 +1178,11 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh,
if (!err)
hlist_add_head_rcu(&gwj->list, &net->can.cgw_list);
out:
- if (err)
+ if (err) {
kmem_cache_free(cgw_cache, gwj);
-
+out_free_cf:
+ kfree(mod);
+ }
return err;
}
@@ -1214,19 +1242,22 @@ static int cgw_remove_job(struct sk_buff *skb, struct nlmsghdr *nlh,
/* remove only the first matching entry */
hlist_for_each_entry_safe(gwj, nx, &net->can.cgw_list, list) {
+ struct cf_mod *cf_mod;
+
if (gwj->flags != r->flags)
continue;
if (gwj->limit_hops != limhops)
continue;
+ cf_mod = cgw_job_cf_mod(gwj);
/* we have a match when uid is enabled and identical */
- if (gwj->mod.uid || mod.uid) {
- if (gwj->mod.uid != mod.uid)
+ if (cf_mod->uid || mod.uid) {
+ if (cf_mod->uid != mod.uid)
continue;
} else {
/* no uid => check for identical modifications */
- if (memcmp(&gwj->mod, &mod, sizeof(mod)))
+ if (memcmp(cf_mod, &mod, sizeof(mod)))
continue;
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 1be7cb73a602..11da1e272ec2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9193,18 +9193,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
return 0;
}
-/**
- * dev_set_promiscuity - update promiscuity count on a device
- * @dev: device
- * @inc: modifier
- *
- * Add or remove promiscuity from a device. While the count in the device
- * remains above zero the interface remains promiscuous. Once it hits zero
- * the device reverts back to normal filtering operation. A negative inc
- * value is used to drop promiscuity on the device.
- * Return 0 if successful or a negative errno code on error.
- */
-int dev_set_promiscuity(struct net_device *dev, int inc)
+int netif_set_promiscuity(struct net_device *dev, int inc)
{
unsigned int old_flags = dev->flags;
int err;
@@ -9216,7 +9205,6 @@ int dev_set_promiscuity(struct net_device *dev, int inc)
dev_set_rx_mode(dev);
return err;
}
-EXPORT_SYMBOL(dev_set_promiscuity);
int netif_set_allmulti(struct net_device *dev, int inc, bool notify)
{
@@ -11966,9 +11954,9 @@ void unregister_netdevice_many_notify(struct list_head *head,
struct sk_buff *skb = NULL;
/* Shutdown queueing discipline. */
+ netdev_lock_ops(dev);
dev_shutdown(dev);
dev_tcx_uninstall(dev);
- netdev_lock_ops(dev);
dev_xdp_uninstall(dev);
dev_memory_provider_uninstall(dev);
netdev_unlock_ops(dev);
@@ -12161,7 +12149,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
synchronize_net();
/* Shutdown queueing discipline. */
+ netdev_lock_ops(dev);
dev_shutdown(dev);
+ netdev_unlock_ops(dev);
/* Notify protocols, that we are about to destroy
* this device. They should clean all the things.
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 90898cd540ce..f9a160ab596f 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -267,6 +267,29 @@ void dev_disable_lro(struct net_device *dev)
}
EXPORT_SYMBOL(dev_disable_lro);
+/**
+ * dev_set_promiscuity() - update promiscuity count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * Add or remove promiscuity from a device. While the count in the device
+ * remains above zero the interface remains promiscuous. Once it hits zero
+ * the device reverts back to normal filtering operation. A negative inc
+ * value is used to drop promiscuity on the device.
+ * Return 0 if successful or a negative errno code on error.
+ */
+int dev_set_promiscuity(struct net_device *dev, int inc)
+{
+ int ret;
+
+ netdev_lock_ops(dev);
+ ret = netif_set_promiscuity(dev, inc);
+ netdev_unlock_ops(dev);
+
+ return ret;
+}
+EXPORT_SYMBOL(dev_set_promiscuity);
+
/**
* dev_set_allmulti() - update allmulti count on a device
* @dev: device
diff --git a/net/core/filter.c b/net/core/filter.c
index 79cab4d78dc3..577a4504e26f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2509,6 +2509,7 @@ int skb_do_redirect(struct sk_buff *skb)
goto out_drop;
skb->dev = dev;
dev_sw_netstats_rx_add(dev, skb->len);
+ skb_scrub_packet(skb, false);
return -EAGAIN;
}
return flags & BPF_F_NEIGH ?
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 230743bdbb14..dae9f0d432fb 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -708,25 +708,66 @@ netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp,
return 0;
}
+/**
+ * netdev_stat_queue_sum() - add up queue stats from range of queues
+ * @netdev: net_device
+ * @rx_start: index of the first Rx queue to query
+ * @rx_end: index after the last Rx queue (first *not* to query)
+ * @rx_sum: output Rx stats, should be already initialized
+ * @tx_start: index of the first Tx queue to query
+ * @tx_end: index after the last Tx queue (first *not* to query)
+ * @tx_sum: output Tx stats, should be already initialized
+ *
+ * Add stats from [start, end) range of queue IDs to *x_sum structs.
+ * The sum structs must be already initialized. Usually this
+ * helper is invoked from the .get_base_stats callbacks of drivers
+ * to account for stats of disabled queues. In that case the ranges
+ * are usually [netdev->real_num_*x_queues, netdev->num_*x_queues).
+ */
+void netdev_stat_queue_sum(struct net_device *netdev,
+ int rx_start, int rx_end,
+ struct netdev_queue_stats_rx *rx_sum,
+ int tx_start, int tx_end,
+ struct netdev_queue_stats_tx *tx_sum)
+{
+ const struct netdev_stat_ops *ops;
+ struct netdev_queue_stats_rx rx;
+ struct netdev_queue_stats_tx tx;
+ int i;
+
+ ops = netdev->stat_ops;
+
+ for (i = rx_start; i < rx_end; i++) {
+ memset(&rx, 0xff, sizeof(rx));
+ if (ops->get_queue_stats_rx)
+ ops->get_queue_stats_rx(netdev, i, &rx);
+ netdev_nl_stats_add(rx_sum, &rx, sizeof(rx));
+ }
+ for (i = tx_start; i < tx_end; i++) {
+ memset(&tx, 0xff, sizeof(tx));
+ if (ops->get_queue_stats_tx)
+ ops->get_queue_stats_tx(netdev, i, &tx);
+ netdev_nl_stats_add(tx_sum, &tx, sizeof(tx));
+ }
+}
+EXPORT_SYMBOL(netdev_stat_queue_sum);
+
static int
netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
const struct genl_info *info)
{
- struct netdev_queue_stats_rx rx_sum, rx;
- struct netdev_queue_stats_tx tx_sum, tx;
- const struct netdev_stat_ops *ops;
+ struct netdev_queue_stats_rx rx_sum;
+ struct netdev_queue_stats_tx tx_sum;
void *hdr;
- int i;
- ops = netdev->stat_ops;
/* Netdev can't guarantee any complete counters */
- if (!ops->get_base_stats)
+ if (!netdev->stat_ops->get_base_stats)
return 0;
memset(&rx_sum, 0xff, sizeof(rx_sum));
memset(&tx_sum, 0xff, sizeof(tx_sum));
- ops->get_base_stats(netdev, &rx_sum, &tx_sum);
+ netdev->stat_ops->get_base_stats(netdev, &rx_sum, &tx_sum);
/* The op was there, but nothing reported, don't bother */
if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) &&
@@ -739,18 +780,8 @@ netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp,
if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex))
goto nla_put_failure;
- for (i = 0; i < netdev->real_num_rx_queues; i++) {
- memset(&rx, 0xff, sizeof(rx));
- if (ops->get_queue_stats_rx)
- ops->get_queue_stats_rx(netdev, i, &rx);
- netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx));
- }
- for (i = 0; i < netdev->real_num_tx_queues; i++) {
- memset(&tx, 0xff, sizeof(tx));
- if (ops->get_queue_stats_tx)
- ops->get_queue_stats_tx(netdev, i, &tx);
- netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx));
- }
+ netdev_stat_queue_sum(netdev, 0, netdev->real_num_rx_queues, &rx_sum,
+ 0, netdev->real_num_tx_queues, &tx_sum);
if (netdev_nl_stats_write_rx(rsp, &rx_sum) ||
netdev_nl_stats_write_tx(rsp, &tx_sum))
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 9ba83f0c9928..c6b22170dc49 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3214,16 +3214,13 @@ static void add_v4_addrs(struct inet6_dev *idev)
struct in6_addr addr;
struct net_device *dev;
struct net *net = dev_net(idev->dev);
- int scope, plen, offset = 0;
+ int scope, plen;
u32 pflags = 0;
ASSERT_RTNL();
memset(&addr, 0, sizeof(struct in6_addr));
- /* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */
- if (idev->dev->addr_len == sizeof(struct in6_addr))
- offset = sizeof(struct in6_addr) - 4;
- memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4);
+ memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4);
if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) {
scope = IPV6_ADDR_COMPATv4;
@@ -3534,7 +3531,13 @@ static void addrconf_gre_config(struct net_device *dev)
return;
}
- if (dev->type == ARPHRD_ETHER) {
+ /* Generate the IPv6 link-local address using addrconf_addr_gen(),
+ * unless we have an IPv4 GRE device not bound to an IP address and
+ * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this
+ * case). Such devices fall back to add_v4_addrs() instead.
+ */
+ if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 &&
+ idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) {
addrconf_addr_gen(idev, true);
return;
}
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 5d1f2d6d09ad..35eaf0812c5b 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7675,6 +7675,7 @@ ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata,
int hdr_len = offsetofend(struct ieee80211_mgmt, u.action.u.ttlm_res);
int ttlm_max_len = 2 + 1 + sizeof(struct ieee80211_ttlm_elem) + 1 +
2 * 2 * IEEE80211_TTLM_NUM_TIDS;
+ u16 status_code;
skb = dev_alloc_skb(local->tx_headroom + hdr_len + ttlm_max_len);
if (!skb)
@@ -7697,19 +7698,18 @@ ieee80211_send_neg_ttlm_res(struct ieee80211_sub_if_data *sdata,
WARN_ON(1);
fallthrough;
case NEG_TTLM_RES_REJECT:
- mgmt->u.action.u.ttlm_res.status_code =
- WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING;
+ status_code = WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING;
break;
case NEG_TTLM_RES_ACCEPT:
- mgmt->u.action.u.ttlm_res.status_code = WLAN_STATUS_SUCCESS;
+ status_code = WLAN_STATUS_SUCCESS;
break;
case NEG_TTLM_RES_SUGGEST_PREFERRED:
- mgmt->u.action.u.ttlm_res.status_code =
- WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED;
+ status_code = WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED;
ieee80211_neg_ttlm_add_suggested_map(skb, neg_ttlm);
break;
}
+ mgmt->u.action.u.ttlm_res.status_code = cpu_to_le16(status_code);
ieee80211_tx_skb(sdata, skb);
}
@@ -7875,7 +7875,7 @@ void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata,
* This can be better implemented in the future, to handle request
* rejections.
*/
- if (mgmt->u.action.u.ttlm_res.status_code != WLAN_STATUS_SUCCESS)
+ if (le16_to_cpu(mgmt->u.action.u.ttlm_res.status_code) != WLAN_STATUS_SUCCESS)
__ieee80211_disconnect(sdata);
}
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index cf3ce72c3de6..5251524b96af 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -64,7 +64,7 @@ struct hbucket {
#define ahash_sizeof_regions(htable_bits) \
(ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region))
#define ahash_region(n, htable_bits) \
- ((n) % ahash_numof_locks(htable_bits))
+ ((n) / jhash_size(HTABLE_REGION_BITS))
#define ahash_bucket_start(h, htable_bits) \
((htable_bits) < HTABLE_REGION_BITS ? 0 \
: (h) * jhash_size(HTABLE_REGION_BITS))
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 3313bceb6cc9..014f07740369 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -119,13 +119,12 @@ __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu)
return false;
}
-/* Get route to daddr, update *saddr, optionally bind route to saddr */
+/* Get route to daddr, optionally bind route to saddr */
static struct rtable *do_output_route4(struct net *net, __be32 daddr,
- int rt_mode, __be32 *saddr)
+ int rt_mode, __be32 *ret_saddr)
{
struct flowi4 fl4;
struct rtable *rt;
- bool loop = false;
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = daddr;
@@ -135,23 +134,17 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr,
retry:
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt)) {
- /* Invalid saddr ? */
- if (PTR_ERR(rt) == -EINVAL && *saddr &&
- rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
- *saddr = 0;
- flowi4_update_output(&fl4, 0, daddr, 0);
- goto retry;
- }
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
return NULL;
- } else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
+ }
+ if (rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
ip_rt_put(rt);
- *saddr = fl4.saddr;
flowi4_update_output(&fl4, 0, daddr, fl4.saddr);
- loop = true;
+ rt_mode = 0;
goto retry;
}
- *saddr = fl4.saddr;
+ if (ret_saddr)
+ *ret_saddr = fl4.saddr;
return rt;
}
@@ -344,19 +337,15 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
if (ret_saddr)
*ret_saddr = dest_dst->dst_saddr.ip;
} else {
- __be32 saddr = htonl(INADDR_ANY);
-
noref = 0;
/* For such unconfigured boxes avoid many route lookups
* for performance reasons because we do not remember saddr
*/
rt_mode &= ~IP_VS_RT_MODE_CONNECT;
- rt = do_output_route4(net, daddr, rt_mode, &saddr);
+ rt = do_output_route4(net, daddr, rt_mode, ret_saddr);
if (!rt)
goto err_unreach;
- if (ret_saddr)
- *ret_saddr = saddr;
}
local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0;
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 61fea7baae5d..2f22ca59586f 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -975,8 +975,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
upcall.cmd = OVS_PACKET_CMD_ACTION;
upcall.mru = OVS_CB(skb)->mru;
- for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
- a = nla_next(a, &rem)) {
+ nla_for_each_nested(a, attr, rem) {
switch (nla_type(a)) {
case OVS_USERSPACE_ATTR_USERDATA:
upcall.userdata = a;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 4b9a639b642e..14bf71f57057 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -348,7 +348,8 @@ static void htb_add_to_wait_tree(struct htb_sched *q,
*/
static inline void htb_next_rb_node(struct rb_node **n)
{
- *n = rb_next(*n);
+ if (*n)
+ *n = rb_next(*n);
}
/**
@@ -609,8 +610,8 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl)
*/
static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl)
{
- WARN_ON(!cl->prio_activity);
-
+ if (!cl->prio_activity)
+ return;
htb_deactivate_prios(q, cl);
cl->prio_activity = 0;
}
@@ -1485,8 +1486,6 @@ static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg)
{
struct htb_class *cl = (struct htb_class *)arg;
- if (!cl->prio_activity)
- return;
htb_deactivate(qdisc_priv(sch), cl);
}
@@ -1740,8 +1739,7 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg,
if (cl->parent)
cl->parent->children--;
- if (cl->prio_activity)
- htb_deactivate(q, cl);
+ htb_deactivate(q, cl);
if (cl->cmode != HTB_CAN_SEND)
htb_safe_rb_erase(&cl->pq_node,
@@ -1949,8 +1947,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
/* turn parent into inner node */
qdisc_purge_queue(parent->leaf.q);
parent_qdisc = parent->leaf.q;
- if (parent->prio_activity)
- htb_deactivate(q, parent);
+ htb_deactivate(q, parent);
/* remove from evt list because of level change */
if (parent->cmode != HTB_CAN_SEND) {
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 9865f305275d..ddd3a97f6609 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2681,7 +2681,7 @@ cfg80211_defrag_mle(const struct element *mle, const u8 *ie, size_t ielen,
/* Required length for first defragmentation */
buf_len = mle->datalen - 1;
for_each_element(elem, mle->data + mle->datalen,
- ielen - sizeof(*mle) + mle->datalen) {
+ ie + ielen - mle->data - mle->datalen) {
if (elem->id != WLAN_EID_FRAGMENT)
break;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 28705ae67784..fd404729b115 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4968,6 +4968,9 @@ union bpf_attr {
* the netns switch takes place from ingress to ingress without
* going through the CPU's backlog queue.
*
+ * *skb*\ **->mark** and *skb*\ **->tstamp** are not cleared during
+ * the netns switch.
+ *
* The *flags* argument is reserved and must be 0. The helper is
* currently only supported for tc BPF program types at the
* ingress hook and for veth and netkit target device types. The
diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c
index ce32cb35007d..c4da34048ef8 100644
--- a/tools/net/ynl/lib/ynl.c
+++ b/tools/net/ynl/lib/ynl.c
@@ -364,7 +364,7 @@ int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr)
"Invalid attribute (binary %s)", policy->name);
return -1;
case YNL_PT_NUL_STR:
- if ((!policy->len || len <= policy->len) && !data[len - 1])
+ if (len && (!policy->len || len <= policy->len) && !data[len - 1])
break;
yerr(yarg->ys, YNL_ERROR_ATTR_INVALID,
"Invalid attribute (string %s)", policy->name);
diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py
index 4b6822866066..af8df2313a3b 100755
--- a/tools/testing/selftests/drivers/net/ping.py
+++ b/tools/testing/selftests/drivers/net/ping.py
@@ -9,11 +9,11 @@
from lib.py import bkg, cmd, wait_port_listen, rand_port
from lib.py import defer, ethtool, ip
-remote_ifname=""
no_sleep=False
def _test_v4(cfg) -> None:
- cfg.require_ipver("4")
+ if not cfg.addr_v["4"]:
+ return
cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["4"])
cmd("ping -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
@@ -21,7 +21,8 @@ def _test_v4(cfg) -> None:
cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
def _test_v6(cfg) -> None:
- cfg.require_ipver("6")
+ if not cfg.addr_v["6"]:
+ return
cmd("ping -c 1 -W5 " + cfg.remote_addr_v["6"])
cmd("ping -c 1 -W5 " + cfg.addr_v["6"], host=cfg.remote)
@@ -57,7 +58,7 @@ def _set_offload_checksum(cfg, netnl, on) -> None:
def _set_xdp_generic_sb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
cmd(f"ip link set dev {cfg.ifname} mtu 1500 xdpgeneric obj {prog} sec xdp", shell=True)
defer(cmd, f"ip link set dev {cfg.ifname} xdpgeneric off")
@@ -66,8 +67,8 @@ def _set_xdp_generic_sb_on(cfg) -> None:
def _set_xdp_generic_mb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
- defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+ defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
ip("link set dev %s mtu 9000 xdpgeneric obj %s sec xdp.frags" % (cfg.ifname, prog))
defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdpgeneric off")
@@ -76,7 +77,7 @@ def _set_xdp_generic_mb_on(cfg) -> None:
def _set_xdp_native_sb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
cmd(f"ip -j link set dev {cfg.ifname} mtu 1500 xdp obj {prog} sec xdp", shell=True)
defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
xdp_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
@@ -93,8 +94,8 @@ def _set_xdp_native_sb_on(cfg) -> None:
def _set_xdp_native_mb_on(cfg) -> None:
prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
- cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
- defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+ defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote)
try:
cmd(f"ip link set dev {cfg.ifname} mtu 9000 xdp obj {prog} sec xdp.frags", shell=True)
defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
@@ -112,18 +113,15 @@ def _set_xdp_offload_on(cfg) -> None:
except Exception as e:
raise KsftSkipEx('device does not support offloaded XDP')
defer(ip, f"link set dev {cfg.ifname} xdpoffload off")
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
if no_sleep != True:
time.sleep(10)
def get_interface_info(cfg) -> None:
- global remote_ifname
global no_sleep
- remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_addr_v['4']} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout
- remote_ifname = remote_info.rstrip('\n')
- if remote_ifname == "":
+ if cfg.remote_ifname == "":
raise KsftFailEx('Can not get remote interface')
local_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
if 'parentbus' in local_info and local_info['parentbus'] == "netdevsim":
@@ -136,15 +134,25 @@ def set_interface_init(cfg) -> None:
cmd(f"ip link set dev {cfg.ifname} xdp off ", shell=True)
cmd(f"ip link set dev {cfg.ifname} xdpgeneric off ", shell=True)
cmd(f"ip link set dev {cfg.ifname} xdpoffload off", shell=True)
- cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+ cmd(f"ip link set dev {cfg.remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+
+def test_default_v4(cfg, netnl) -> None:
+ cfg.require_ipver("4")
-def test_default(cfg, netnl) -> None:
_set_offload_checksum(cfg, netnl, "off")
_test_v4(cfg)
- _test_v6(cfg)
_test_tcp(cfg)
_set_offload_checksum(cfg, netnl, "on")
_test_v4(cfg)
+ _test_tcp(cfg)
+
+def test_default_v6(cfg, netnl) -> None:
+ cfg.require_ipver("6")
+
+ _set_offload_checksum(cfg, netnl, "off")
+ _test_v6(cfg)
+ _test_tcp(cfg)
+ _set_offload_checksum(cfg, netnl, "on")
_test_v6(cfg)
_test_tcp(cfg)
@@ -202,7 +210,8 @@ def main() -> None:
with NetDrvEpEnv(__file__) as cfg:
get_interface_info(cfg)
set_interface_init(cfg)
- ksft_run([test_default,
+ ksft_run([test_default_v4,
+ test_default_v6,
test_xdp_generic_sb,
test_xdp_generic_mb,
test_xdp_native_sb,
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 124078b56fa4..70a38f485d4d 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -31,6 +31,7 @@ TEST_PROGS += veth.sh
TEST_PROGS += ioam6.sh
TEST_PROGS += gro.sh
TEST_PROGS += gre_gso.sh
+TEST_PROGS += gre_ipv6_lladdr.sh
TEST_PROGS += cmsg_so_mark.sh
TEST_PROGS += cmsg_so_priority.sh
TEST_PROGS += test_so_rcv.sh
diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
new file mode 100755
index 000000000000..5b34f6e1f831
--- /dev/null
+++ b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
@@ -0,0 +1,177 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./lib.sh
+
+PAUSE_ON_FAIL="no"
+
+# The trap function handler
+#
+exit_cleanup_all()
+{
+ cleanup_all_ns
+
+ exit "${EXIT_STATUS}"
+}
+
+# Add fake IPv4 and IPv6 networks on the loopback device, to be used as
+# underlay by future GRE devices.
+#
+setup_basenet()
+{
+ ip -netns "${NS0}" link set dev lo up
+ ip -netns "${NS0}" address add dev lo 192.0.2.10/24
+ ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad
+}
+
+# Check if network device has an IPv6 link-local address assigned.
+#
+# Parameters:
+#
+# * $1: The network device to test
+# * $2: An extra regular expression that should be matched (to verify the
+# presence of extra attributes)
+# * $3: The expected return code from grep (to allow checking the absence of
+# a link-local address)
+# * $4: The user visible name for the scenario being tested
+#
+check_ipv6_ll_addr()
+{
+ local DEV="$1"
+ local EXTRA_MATCH="$2"
+ local XRET="$3"
+ local MSG="$4"
+
+ RET=0
+ set +e
+ ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}"
+ check_err_fail "${XRET}" $? ""
+ log_test "${MSG}"
+ set -e
+}
+
+# Create a GRE device and verify that it gets an IPv6 link-local address as
+# expected.
+#
+# Parameters:
+#
+# * $1: The device type (gre, ip6gre, gretap or ip6gretap)
+# * $2: The local underlay IP address (can be an IPv4, an IPv6 or "any")
+# * $3: The remote underlay IP address (can be an IPv4, an IPv6 or "any")
+# * $4: The IPv6 interface identifier generation mode to use for the GRE
+# device (eui64, none, stable-privacy or random).
+#
+test_gre_device()
+{
+ local GRE_TYPE="$1"
+ local LOCAL_IP="$2"
+ local REMOTE_IP="$3"
+ local MODE="$4"
+ local ADDR_GEN_MODE
+ local MATCH_REGEXP
+ local MSG
+
+ ip link add netns "${NS0}" name gretest type "${GRE_TYPE}" local "${LOCAL_IP}" remote "${REMOTE_IP}"
+
+ case "${MODE}" in
+ "eui64")
+ ADDR_GEN_MODE=0
+ MATCH_REGEXP=""
+ MSG="${GRE_TYPE}, mode: 0 (EUI64), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ ;;
+ "none")
+ ADDR_GEN_MODE=1
+ MATCH_REGEXP=""
+ MSG="${GRE_TYPE}, mode: 1 (none), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=1 # No link-local address should be generated
+ ;;
+ "stable-privacy")
+ ADDR_GEN_MODE=2
+ MATCH_REGEXP="stable-privacy"
+ MSG="${GRE_TYPE}, mode: 2 (stable privacy), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ # Initialise stable_secret (required for stable-privacy mode)
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.stable_secret="2001:db8::abcd"
+ ;;
+ "random")
+ ADDR_GEN_MODE=3
+ MATCH_REGEXP="stable-privacy"
+ MSG="${GRE_TYPE}, mode: 3 (random), ${LOCAL_IP} -> ${REMOTE_IP}"
+ XRET=0
+ ;;
+ esac
+
+ # Check that IPv6 link-local address is generated when device goes up
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+ ip -netns "${NS0}" link set dev gretest up
+ check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}"
+
+ # Now disable link-local address generation
+ ip -netns "${NS0}" link set dev gretest down
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1
+ ip -netns "${NS0}" link set dev gretest up
+
+ # Check that link-local address generation works when re-enabled while
+ # the device is already up
+ ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+ check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}"
+
+ ip -netns "${NS0}" link del dev gretest
+}
+
+test_gre4()
+{
+ local GRE_TYPE
+ local MODE
+
+ for GRE_TYPE in "gre" "gretap"; do
+ printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+ for MODE in "eui64" "none" "stable-privacy" "random"; do
+ test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" any 192.0.2.11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" 192.0.2.10 any "${MODE}"
+ done
+ done
+}
+
+test_gre6()
+{
+ local GRE_TYPE
+ local MODE
+
+ for GRE_TYPE in "ip6gre" "ip6gretap"; do
+ printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+ for MODE in "eui64" "none" "stable-privacy" "random"; do
+ test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" any 2001:db8::11 "${MODE}"
+ test_gre_device "${GRE_TYPE}" 2001:db8::10 any "${MODE}"
+ done
+ done
+}
+
+usage()
+{
+ echo "Usage: $0 [-p]"
+ exit 1
+}
+
+while getopts :p o
+do
+ case $o in
+ p) PAUSE_ON_FAIL="yes";;
+ *) usage;;
+ esac
+done
+
+setup_ns NS0
+
+set -e
+trap exit_cleanup_all EXIT
+
+setup_basenet
+
+test_gre4
+test_gre6
diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 0843f6d37e9c..a951c0d33cd2 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -538,5 +538,40 @@
"$TC qdisc del dev $DUMMY handle 1:0 root",
"$IP addr del 10.10.10.10/24 dev $DUMMY || true"
]
+ },
+ {
+ "id": "62c4",
+ "name": "Test HTB with FQ_CODEL - basic functionality",
+ "category": [
+ "qdisc",
+ "htb",
+ "fq_codel"
+ ],
+ "plugins": {
+ "requires": [
+ "nsPlugin",
+ "scapyPlugin"
+ ]
+ },
+ "setup": [
+ "$TC qdisc add dev $DEV1 root handle 1: htb default 11",
+ "$TC class add dev $DEV1 parent 1: classid 1:1 htb rate 10kbit",
+ "$TC class add dev $DEV1 parent 1:1 classid 1:11 htb rate 10kbit prio 0 quantum 1486",
+ "$TC qdisc add dev $DEV1 parent 1:11 fq_codel quantum 300 noecn",
+ "sleep 0.5"
+ ],
+ "scapy": {
+ "iface": "$DEV0",
+ "count": 5,
+ "packet": "Ether()/IP(dst='10.10.10.1', src='10.10.10.10')/TCP(sport=12345, dport=80)"
+ },
+ "cmdUnderTest": "$TC -s qdisc show dev $DEV1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC -s qdisc show dev $DEV1 | grep -A 5 'qdisc fq_codel'",
+ "matchPattern": "Sent [0-9]+ bytes [0-9]+ pkt",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV1 handle 1: root"
+ ]
}
]