* [PATCH net-next v4 0/6] r8169: add support for phylink
From: javen @ 2026-07-03 9:24 UTC (permalink / raw)
To: hkallweit1, nic_swsd, andrew+netdev, davem, edumazet, kuba,
pabeni, horms
Cc: netdev, linux-kernel, Javen Xu
From: Javen Xu <javen_xu@realsil.com.cn>
This series patch adds support for phylink. RTL8116af is a fiber mode
card, link status and speed can not be read from standard phy reg. So
we read link status and speed from serdes reg by pcs. So as RTL8127atf.
Javen Xu (6):
r8169: add speed in private struct
r8169: add support for phylink
r8169: add support for RTL8116af
r8169: add ltr support for RTL8117 series
r8169: fix RTL8116af can not enter s0idle and c10
r8169: add phylink support for RTL8127atf
drivers/net/ethernet/realtek/Kconfig | 1 +
drivers/net/ethernet/realtek/r8169_main.c | 619 +++++++++++++++++-----
drivers/net/phy/realtek/realtek_main.c | 53 --
include/net/phy/realtek_phy.h | 7 -
4 files changed, 479 insertions(+), 201 deletions(-)
delete mode 100644 include/net/phy/realtek_phy.h
--
2.43.0
^ permalink raw reply
* [PATCH net-next v4 1/6] r8169: add speed in private struct
From: javen @ 2026-07-03 9:24 UTC (permalink / raw)
To: hkallweit1, nic_swsd, andrew+netdev, davem, edumazet, kuba,
pabeni, horms
Cc: netdev, linux-kernel, Javen Xu
In-Reply-To: <20260703092459.1124-1-javen_xu@realsil.com.cn>
From: Javen Xu <javen_xu@realsil.com.cn>
This patch adds speed in private struct in order to decouple
from phydev in the following patch supporting for phylink.
Signed-off-by: Javen Xu <javen_xu@realsil.com.cn>
---
Changes in v2:
- repalce current_speed with speed
Changes in v3:
- update tp->speed in rtl8169_set_link_ksettings()
Changes in v4:
- no changes
---
drivers/net/ethernet/realtek/r8169_main.c | 23 ++++++++++++-----------
1 file changed, 12 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index ec4fc21fa21f..c60710f9bd21 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -750,6 +750,7 @@ struct rtl8169_private {
u32 irq_mask;
int irq;
struct clk *clk;
+ int speed;
struct {
DECLARE_BITMAP(flags, RTL_FLAG_MAX);
@@ -1673,16 +1674,14 @@ static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
rtl_pci_commit(tp);
}
-static void rtl_link_chg_patch(struct rtl8169_private *tp)
+static void rtl_link_chg_patch(struct rtl8169_private *tp, int speed)
{
- struct phy_device *phydev = tp->phydev;
-
if (tp->mac_version == RTL_GIGA_MAC_VER_34 ||
tp->mac_version == RTL_GIGA_MAC_VER_38) {
- if (phydev->speed == SPEED_1000) {
+ if (speed == SPEED_1000) {
rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011);
rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005);
- } else if (phydev->speed == SPEED_100) {
+ } else if (speed == SPEED_100) {
rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x0000001f);
rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005);
} else {
@@ -1692,7 +1691,7 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
rtl_reset_packet_filter(tp);
} else if (tp->mac_version == RTL_GIGA_MAC_VER_35 ||
tp->mac_version == RTL_GIGA_MAC_VER_36) {
- if (phydev->speed == SPEED_1000) {
+ if (speed == SPEED_1000) {
rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011);
rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005);
} else {
@@ -1700,7 +1699,7 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x0000003f);
}
} else if (tp->mac_version == RTL_GIGA_MAC_VER_37) {
- if (phydev->speed == SPEED_10) {
+ if (speed == SPEED_10) {
rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x4d02);
rtl_eri_write(tp, 0x1dc, ERIAR_MASK_0011, 0x0060a);
} else {
@@ -2074,11 +2073,11 @@ rtl_coalesce_info(struct rtl8169_private *tp)
ci = rtl_coalesce_info_8168_8136;
/* if speed is unknown assume highest one */
- if (tp->phydev->speed == SPEED_UNKNOWN)
+ if (tp->speed == SPEED_UNKNOWN)
return ci;
for (; ci->speed; ci++) {
- if (tp->phydev->speed == ci->speed)
+ if (tp->speed == ci->speed)
return ci;
}
@@ -2236,7 +2235,7 @@ static void rtl_set_eee_txidle_timer(struct rtl8169_private *tp)
static unsigned int r8169_get_tx_lpi_timer_us(struct rtl8169_private *tp)
{
- unsigned int speed = tp->phydev->speed;
+ unsigned int speed = tp->speed;
unsigned int timer = tp->tx_lpi_timer;
if (!timer || speed == SPEED_UNKNOWN)
@@ -4968,8 +4967,9 @@ static void r8169_phylink_handler(struct net_device *ndev)
struct rtl8169_private *tp = netdev_priv(ndev);
struct device *d = tp_to_dev(tp);
+ tp->speed = tp->phydev->speed;
if (netif_carrier_ok(ndev)) {
- rtl_link_chg_patch(tp);
+ rtl_link_chg_patch(tp, tp->speed);
rtl_enable_tx_lpi(tp, tp->phydev->enable_tx_lpi);
pm_request_resume(d);
} else {
@@ -5667,6 +5667,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
ext_xid_str, xid);
tp->mac_version = chip->mac_version;
tp->fw_name = chip->fw_name;
+ tp->speed = SPEED_UNKNOWN;
/* Disable ASPM L1 as that cause random device stop working
* problems as well as full system hangs for some PCIe devices users.
--
2.43.0
^ permalink raw reply related
* [PATCH net-next v4 5/6] r8169: fix RTL8116af can not enter s0idle and c10
From: javen @ 2026-07-03 9:24 UTC (permalink / raw)
To: hkallweit1, nic_swsd, andrew+netdev, davem, edumazet, kuba,
pabeni, horms
Cc: netdev, linux-kernel, Javen Xu
In-Reply-To: <20260703092459.1124-1-javen_xu@realsil.com.cn>
From: Javen Xu <javen_xu@realsil.com.cn>
RTL8116AF is a multi-function device. Functions 2 to 7 are hidden from
the PCI core and return an all-ones response when their vendor ID is read,
so they are not enumerated as normal PCI functions.
However, these hidden functions can still affect platform power
management. If they are left in D0 or keep ASPM disabled, the platform may
fail to enter the low-power s0ix state and the CPU package may fail to
enter Package C10.
Put functions 2 to 7 into D3hot and enable ASPM on their PCIe link control
register. Since these functions are hidden, access their configuration
space through pci_bus_read_config_dword() / pci_bus_write_config_dword()
using the same slot and the target function numbers.
Ignore functions that return a PCI error response when reading their
configuration space.
Signed-off-by: Javen Xu <javen_xu@realsil.com.cn>
---
Changes in v2:
- no changes
Changes in v3:
- no changes
Changes in v4:
- add gate for rtl_lowpower_hidden_functions, only for RTL8116af
---
drivers/net/ethernet/realtek/r8169_main.c | 57 ++++++++++++++++++-----
1 file changed, 46 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 635131c51db9..0dd805f0d613 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -97,17 +97,20 @@
#define JUMBO_9K (9 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
#define JUMBO_16K (SZ_16K - VLAN_ETH_HLEN - ETH_FCS_LEN)
-#define OCP_SDS_ADDR_REG 0xEB10
-#define OCP_SDS_CMD_REG 0xEB0E
-#define OCP_SDS_DATA_REG 0xEB14
-#define SDS_CMD_READ 0x0001
-#define RTL_SDS_C22_BASE 0x40
-#define RTL_PKG_DETECT 0xdc00
-#define RTL_PKG_DETECT_MASK 0x0078
-#define RTL_PKG_DETECT_8116AF 0x0030
-#define RTL_INT_HW_ID 0xd006
-#define RTL_INT_HW_ID_MASK 0x00ff
-#define RTL_INT_HW_ID_8116AF 0x0000
+#define OCP_SDS_ADDR_REG 0xEB10
+#define OCP_SDS_CMD_REG 0xEB0E
+#define OCP_SDS_DATA_REG 0xEB14
+#define SDS_CMD_READ 0x0001
+#define RTL_SDS_C22_BASE 0x40
+#define RTL_PKG_DETECT 0xdc00
+#define RTL_PKG_DETECT_MASK 0x0078
+#define RTL_PKG_DETECT_8116AF 0x0030
+#define RTL_INT_HW_ID 0xd006
+#define RTL_INT_HW_ID_MASK 0x00ff
+#define RTL_INT_HW_ID_8116AF 0x0000
+#define RTL8116AF_FUNC_PM_CSR 0x80
+#define RTL8116AF_FUNC_EXP_LNKCTL 0x44
+#define RTL_PM_D3HOT GENMASK(1, 0)
static const struct rtl_chip_info {
u32 mask;
@@ -3779,6 +3782,35 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
r8168_mac_ocp_modify(tp, 0xe860, 0x0000, 0x0080);
}
+static void rtl_lowpower_hidden_functions(struct pci_dev *pdev)
+{
+ unsigned int slot = PCI_SLOT(pdev->devfn);
+ struct pci_bus *bus = pdev->bus;
+ unsigned int devfn;
+ int func;
+ int ret;
+ u32 val;
+
+ for (func = 2; func < 8; func++) {
+ devfn = PCI_DEVFN(slot, func);
+
+ ret = pci_bus_read_config_dword(bus, devfn, RTL8116AF_FUNC_PM_CSR, &val);
+ if (!ret && !PCI_POSSIBLE_ERROR(val)) {
+ val &= ~PCI_PM_CTRL_PME_STATUS;
+ val &= ~(PCI_PM_CTRL_STATE_MASK | PCI_PM_CTRL_PME_ENABLE);
+ val |= (RTL_PM_D3HOT | PCI_PM_CTRL_PME_ENABLE);
+ pci_bus_write_config_dword(bus, devfn, RTL8116AF_FUNC_PM_CSR, val);
+ }
+
+ ret = pci_bus_read_config_dword(bus, devfn, RTL8116AF_FUNC_EXP_LNKCTL, &val);
+ if (!ret && !PCI_POSSIBLE_ERROR(val)) {
+ val &= ~((PCI_EXP_LNKSTA_LBMS | PCI_EXP_LNKSTA_LABS) << 16);
+ val |= PCI_EXP_LNKCTL_ASPMC;
+ pci_bus_write_config_dword(bus, devfn, RTL8116AF_FUNC_EXP_LNKCTL, val);
+ }
+ }
+}
+
static void rtl_hw_start_8117(struct rtl8169_private *tp)
{
static const struct ephy_info e_info_8117[] = {
@@ -3835,6 +3867,9 @@ static void rtl_hw_start_8117(struct rtl8169_private *tp)
r8168_mac_ocp_write(tp, 0xc094, 0x0000);
r8168_mac_ocp_write(tp, 0xc09e, 0x0000);
+ if (rtl_is_8116af(tp))
+ rtl_lowpower_hidden_functions(tp->pci_dev);
+
/* firmware is for MAC only */
r8169_apply_firmware(tp);
}
--
2.43.0
^ permalink raw reply related
* [PATCH net-next v4 6/6] r8169: add phylink support for RTL8127atf
From: javen @ 2026-07-03 9:24 UTC (permalink / raw)
To: hkallweit1, nic_swsd, andrew+netdev, davem, edumazet, kuba,
pabeni, horms
Cc: netdev, linux-kernel, Javen Xu
In-Reply-To: <20260703092459.1124-1-javen_xu@realsil.com.cn>
From: Javen Xu <javen_xu@realsil.com.cn>
RTL8127 ATF is a 10G SFP mode of RTL8127. Like RTL8116af, it has no
internal phy, so phylink uses a pcs to get the link status from the
serdes registers instead of standard phy registers.
The interface mode is PHY_INTERFACE_MODE_10GBASER. rtl_mac_select_pcs()
returns tp->pcs for it, and the serdes is configured for 10G in
pcs_config() via r8127_sfp_init_10g(). Speed and duplex are hardcoded
to 10Gbps Full-Duplex.
Signed-off-by: Javen Xu <javen_xu@realsil.com.cn>
---
Changes in v3:
- No changes. New file.
Changes in v4:
- remove DUMMY_PHY in driver/net/phy/realtek/realtek_main.c and related
function
---
drivers/net/ethernet/realtek/r8169_main.c | 80 ++++++++++-------------
drivers/net/phy/realtek/realtek_main.c | 53 ---------------
include/net/phy/realtek_phy.h | 7 --
3 files changed, 35 insertions(+), 105 deletions(-)
delete mode 100644 include/net/phy/realtek_phy.h
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 0dd805f0d613..26d96edb3c42 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -102,6 +102,7 @@
#define OCP_SDS_DATA_REG 0xEB14
#define SDS_CMD_READ 0x0001
#define RTL_SDS_C22_BASE 0x40
+#define RTL_SDS_C45_BASE 0x0080
#define RTL_PKG_DETECT 0xdc00
#define RTL_PKG_DETECT_MASK 0x0078
#define RTL_PKG_DETECT_8116AF 0x0030
@@ -1158,10 +1159,6 @@ static int r8168_phy_ocp_read(struct rtl8169_private *tp, u32 reg)
if (rtl_ocp_reg_failure(reg))
return 0;
- /* Return dummy MII_PHYSID2 in SFP mode to match SFP PHY driver */
- if (tp->sfp_mode == RTL_SFP_8127_ATF && reg == (OCP_STD_PHY_BASE + 2 * MII_PHYSID2))
- return PHY_ID_RTL_DUMMY_SFP & 0xffff;
-
RTL_W32(tp, GPHY_OCP, reg << 15);
return rtl_loop_wait_high(tp, &rtl_ocp_gphy_cond, 25, 10) ?
@@ -1247,12 +1244,6 @@ static void r8127_sfp_init_10g(struct rtl8169_private *tp)
r8168_phy_ocp_write(tp, 0xc804, (val & ~0x000f) | 0x000c);
}
-static void rtl_sfp_init(struct rtl8169_private *tp)
-{
- if (tp->mac_version == RTL_GIGA_MAC_VER_80)
- r8127_sfp_init_10g(tp);
-}
-
static void rtl_sfp_reset(struct rtl8169_private *tp)
{
if (tp->mac_version == RTL_GIGA_MAC_VER_80)
@@ -2442,30 +2433,8 @@ static int rtl8169_set_link_ksettings(struct net_device *ndev,
const struct ethtool_link_ksettings *cmd)
{
struct rtl8169_private *tp = netdev_priv(ndev);
- struct phy_device *phydev = tp->phydev;
- int duplex = cmd->base.duplex;
- int speed = cmd->base.speed;
-
- if (tp->sfp_mode != RTL_SFP_8127_ATF)
- return phylink_ethtool_ksettings_set(tp->phylink, cmd);
-
- if (cmd->base.autoneg != AUTONEG_DISABLE)
- return -EINVAL;
- if (!phy_check_valid(speed, duplex, phydev->supported))
- return -EINVAL;
-
- mutex_lock(&phydev->lock);
-
- phydev->autoneg = AUTONEG_DISABLE;
- phydev->speed = speed;
- phydev->duplex = duplex;
-
- rtl_sfp_init(tp);
-
- mutex_unlock(&phydev->lock);
-
- return 0;
+ return phylink_ethtool_ksettings_set(tp->phylink, cmd);
}
static int rtl8169_nway_reset(struct net_device *dev)
@@ -2614,9 +2583,6 @@ static void rtl8169_init_phy(struct rtl8169_private *tp)
tp->pci_dev->subsystem_device == 0xe000)
phy_write_paged(tp->phydev, 0x0001, 0x10, 0xf01b);
- if (tp->sfp_mode == RTL_SFP_8127_ATF)
- rtl_sfp_init(tp);
-
/* We may have called phy_speed_down before */
phy_speed_up(tp->phydev);
@@ -5036,7 +5002,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
if (status & LinkChg) {
if (tp->phydev)
phy_mac_interrupt(tp->phydev);
- else if (tp->sfp_mode == RTL_SFP_8168_AF)
+ else if (tp->sfp_mode)
phylink_mac_change(tp->phylink,
!!(RTL_R8(tp, PHYstatus) & LinkStatus));
}
@@ -5767,7 +5733,8 @@ static struct phylink_pcs *rtl_mac_select_pcs(struct phylink_config *config,
if (!tp->pcs.ops)
return NULL;
- if (interface == PHY_INTERFACE_MODE_1000BASEX)
+ if (interface == PHY_INTERFACE_MODE_1000BASEX ||
+ interface == PHY_INTERFACE_MODE_10GBASER)
return &tp->pcs;
return NULL;
@@ -5797,12 +5764,28 @@ static void rtl8169_pcs_get_state(struct phylink_pcs *pcs,
struct phylink_link_state *state)
{
struct rtl8169_private *tp = container_of(pcs, struct rtl8169_private, pcs);
- u16 bmsr, lpa;
- bmsr = rtl8169_sds_read(tp, RTL_SDS_C22_BASE + MII_BMSR);
- lpa = rtl8169_sds_read(tp, RTL_SDS_C22_BASE + MII_LPA);
+ if (tp->sfp_mode == RTL_SFP_8127_ATF) {
+ u16 stat1;
+
+ stat1 = rtl8169_sds_read(tp, RTL_SDS_C45_BASE + MDIO_STAT1);
+
+ if (!(stat1 & MDIO_STAT1_LSTATUS))
+ stat1 = rtl8169_sds_read(tp, RTL_SDS_C45_BASE + MDIO_STAT1);
+
+ state->link = !!(stat1 & MDIO_STAT1_LSTATUS);
+ if (!state->link)
+ return;
- phylink_mii_c22_pcs_decode_state(state, neg_mode, bmsr, lpa);
+ state->duplex = DUPLEX_FULL;
+ state->speed = SPEED_10000;
+ } else {
+ u16 bmsr, lpa;
+
+ bmsr = rtl8169_sds_read(tp, RTL_SDS_C22_BASE + MII_BMSR);
+ lpa = rtl8169_sds_read(tp, RTL_SDS_C22_BASE + MII_LPA);
+ phylink_mii_c22_pcs_decode_state(state, neg_mode, bmsr, lpa);
+ }
}
static int rtl8169_pcs_config(struct phylink_pcs *pcs, unsigned int mode,
@@ -5810,6 +5793,11 @@ static int rtl8169_pcs_config(struct phylink_pcs *pcs, unsigned int mode,
const unsigned long *advertising,
bool permit_pause_to_mac)
{
+ struct rtl8169_private *tp = container_of(pcs, struct rtl8169_private, pcs);
+
+ if (tp->sfp_mode == RTL_SFP_8127_ATF)
+ r8127_sfp_init_10g(tp);
+
return 0;
}
@@ -5855,7 +5843,7 @@ static unsigned long rtl8169_get_lpi_caps(struct rtl8169_private *tp)
{
unsigned long caps = 0;
- if (!rtl_supports_eee(tp))
+ if (!rtl_supports_eee(tp) || tp->sfp_mode == RTL_SFP_8127_ATF)
return 0;
caps |= MAC_100FD | MAC_1000FD;
@@ -5899,7 +5887,9 @@ static int rtl_init_phylink(struct rtl8169_private *tp)
tp->phylink_config.mac_capabilities |= MAC_1000FD;
break;
case RTL_SFP_8127_ATF:
- phy_mode = PHY_INTERFACE_MODE_INTERNAL;
+ tp->pcs.ops = &r8169_pcs_ops;
+ phy_mode = PHY_INTERFACE_MODE_10GBASER;
+ tp->phylink_config.default_an_inband = true;
tp->phylink_config.mac_capabilities |= MAC_10000FD;
break;
default:
@@ -6129,7 +6119,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
if (rc)
return rc;
- if (tp->sfp_mode != RTL_SFP_8168_AF) {
+ if (tp->sfp_mode == RTL_SFP_NONE) {
rc = r8169_mdio_register(tp);
if (rc) {
phylink_destroy(tp->phylink);
diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c
index b65d0f5fa1a0..7f904de583e0 100644
--- a/drivers/net/phy/realtek/realtek_main.c
+++ b/drivers/net/phy/realtek/realtek_main.c
@@ -2646,45 +2646,6 @@ static irqreturn_t rtl8221b_handle_interrupt(struct phy_device *phydev)
return IRQ_HANDLED;
}
-static int rtlgen_sfp_get_features(struct phy_device *phydev)
-{
- linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
- phydev->supported);
-
- /* set default mode */
- phydev->speed = SPEED_10000;
- phydev->duplex = DUPLEX_FULL;
-
- phydev->port = PORT_FIBRE;
-
- return 0;
-}
-
-static int rtlgen_sfp_read_status(struct phy_device *phydev)
-{
- int val, err;
-
- err = genphy_update_link(phydev);
- if (err)
- return err;
-
- if (!phydev->link)
- return 0;
-
- val = phy_read(phydev, RTL_PHYSR);
- if (val < 0)
- return val;
-
- rtlgen_decode_physr(phydev, val);
-
- return 0;
-}
-
-static int rtlgen_sfp_config_aneg(struct phy_device *phydev)
-{
- return 0;
-}
-
static struct phy_driver realtek_drvs[] = {
{
PHY_ID_MATCH_EXACT(0x00008201),
@@ -2934,20 +2895,6 @@ static struct phy_driver realtek_drvs[] = {
.write_page = rtl821x_write_page,
.read_mmd = rtl822x_read_mmd,
.write_mmd = rtl822x_write_mmd,
- }, {
- PHY_ID_MATCH_EXACT(PHY_ID_RTL_DUMMY_SFP),
- .name = "Realtek SFP PHY Mode",
- .flags = PHY_IS_INTERNAL,
- .probe = rtl822x_probe,
- .get_features = rtlgen_sfp_get_features,
- .config_aneg = rtlgen_sfp_config_aneg,
- .read_status = rtlgen_sfp_read_status,
- .suspend = genphy_suspend,
- .resume = rtlgen_resume,
- .read_page = rtl821x_read_page,
- .write_page = rtl821x_write_page,
- .read_mmd = rtl822x_read_mmd,
- .write_mmd = rtl822x_write_mmd,
}, {
PHY_ID_MATCH_EXACT(0x001ccad0),
.name = "RTL8224 2.5Gbps PHY",
diff --git a/include/net/phy/realtek_phy.h b/include/net/phy/realtek_phy.h
deleted file mode 100644
index d683bc1b0659..000000000000
--- a/include/net/phy/realtek_phy.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _REALTEK_PHY_H
-#define _REALTEK_PHY_H
-
-#define PHY_ID_RTL_DUMMY_SFP 0x001ccbff
-
-#endif /* _REALTEK_PHY_H */
--
2.43.0
^ permalink raw reply related
* [PATCH net-next v4 3/6] r8169: add support for RTL8116af
From: javen @ 2026-07-03 9:24 UTC (permalink / raw)
To: hkallweit1, nic_swsd, andrew+netdev, davem, edumazet, kuba,
pabeni, horms
Cc: netdev, linux-kernel, Javen Xu
In-Reply-To: <20260703092459.1124-1-javen_xu@realsil.com.cn>
From: Javen Xu <javen_xu@realsil.com.cn>
RTL8116af is sfp mode. Phylink uses pcs to get the link status from its
serdes reg, instead of standard phy reg. Speed and duplex are hardcoded
to 1000Mbps Full-Duplex. Also, RTL8116af doesn't have internal phy, so
we add some checks to ensure that tp->phydev is not empty when we need it.
In rtl_hw_start_8117(), the MAC calibration for register 0xd412 relies
on reading the internal PHY register 0x0c42. Since RTL8116af does not
have an internal PHY, this calibration step is intentionally bypassed.
Signed-off-by: Javen Xu <javen_xu@realsil.com.cn>
---
Changes in v2:
- replace some magic numbers with macro
Changes in v3:
- change commit message
- add lock when we do rtl8169_sds_read
- use phylink_mii_c22_pcs_decode_state to get status
- add phylink_mac_change for RTL8116af for it doesn't have phy
Changes in v4:
- if tp->pcs.ops is not initial, just return NULL in rtl_mac_select_pcs
---
drivers/net/ethernet/realtek/r8169_main.c | 186 ++++++++++++++++++----
1 file changed, 153 insertions(+), 33 deletions(-)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 8f06dedc33d1..b5816550a4a6 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -97,6 +97,18 @@
#define JUMBO_9K (9 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
#define JUMBO_16K (SZ_16K - VLAN_ETH_HLEN - ETH_FCS_LEN)
+#define OCP_SDS_ADDR_REG 0xEB10
+#define OCP_SDS_CMD_REG 0xEB0E
+#define OCP_SDS_DATA_REG 0xEB14
+#define SDS_CMD_READ 0x0001
+#define RTL_SDS_C22_BASE 0x40
+#define RTL_PKG_DETECT 0xdc00
+#define RTL_PKG_DETECT_MASK 0x0078
+#define RTL_PKG_DETECT_8116AF 0x0030
+#define RTL_INT_HW_ID 0xd006
+#define RTL_INT_HW_ID_MASK 0x00ff
+#define RTL_INT_HW_ID_8116AF 0x0000
+
static const struct rtl_chip_info {
u32 mask;
u32 val;
@@ -729,6 +741,12 @@ enum rtl_dash_type {
RTL_DASH_25_BP,
};
+enum rtl_sfp_mode {
+ RTL_SFP_NONE,
+ RTL_SFP_8168_AF,
+ RTL_SFP_8127_ATF,
+};
+
struct rtl8169_private {
void __iomem *mmio_addr; /* memory map physical address */
struct pci_dev *pci_dev;
@@ -737,6 +755,7 @@ struct rtl8169_private {
struct napi_struct napi;
enum mac_version mac_version;
enum rtl_dash_type dash_type;
+ enum rtl_sfp_mode sfp_mode;
u32 cur_rx; /* Index into the Rx descriptor buffer of next Rx pkt. */
u32 cur_tx; /* Index into the Tx descriptor buffer of next Rx pkt. */
u32 dirty_tx;
@@ -764,7 +783,6 @@ struct rtl8169_private {
unsigned supports_gmii:1;
unsigned aspm_manageable:1;
unsigned dash_enabled:1;
- bool sfp_mode:1;
dma_addr_t counters_phys_addr;
struct rtl8169_counters *counters;
struct rtl8169_tc_offsets tc_offset;
@@ -778,6 +796,7 @@ struct rtl8169_private {
u32 ocp_base;
struct phylink *phylink;
struct phylink_config phylink_config;
+ struct phylink_pcs pcs;
struct ethtool_pauseparam saved_pause;
bool jumbo_pause_saved;
};
@@ -1135,7 +1154,7 @@ static int r8168_phy_ocp_read(struct rtl8169_private *tp, u32 reg)
return 0;
/* Return dummy MII_PHYSID2 in SFP mode to match SFP PHY driver */
- if (tp->sfp_mode && reg == (OCP_STD_PHY_BASE + 2 * MII_PHYSID2))
+ if (tp->sfp_mode == RTL_SFP_8127_ATF && reg == (OCP_STD_PHY_BASE + 2 * MII_PHYSID2))
return PHY_ID_RTL_DUMMY_SFP & 0xffff;
RTL_W32(tp, GPHY_OCP, reg << 15);
@@ -1289,6 +1308,15 @@ static void mac_mcu_write(struct rtl8169_private *tp, int reg, int value)
r8168_mac_ocp_write(tp, tp->ocp_base + reg, value);
}
+static bool rtl_is_8116af(struct rtl8169_private *tp)
+{
+ return tp->mac_version == RTL_GIGA_MAC_VER_52 &&
+ (r8168_mac_ocp_read(tp, RTL_PKG_DETECT) & RTL_PKG_DETECT_MASK) ==
+ RTL_PKG_DETECT_8116AF &&
+ (r8168_mac_ocp_read(tp, RTL_INT_HW_ID) & RTL_INT_HW_ID_MASK) ==
+ RTL_INT_HW_ID_8116AF;
+}
+
static int mac_mcu_read(struct rtl8169_private *tp, int reg)
{
return r8168_mac_ocp_read(tp, tp->ocp_base + reg);
@@ -1584,6 +1612,20 @@ static bool rtl_dash_is_enabled(struct rtl8169_private *tp)
}
}
+static enum rtl_sfp_mode rtl_get_sfp_mode(struct rtl8169_private *tp)
+{
+ if (rtl_is_8125(tp)) {
+ u16 data = r8168_mac_ocp_read(tp, RTL_INT_HW_ID);
+
+ if ((data & 0xff) == 0x07)
+ return RTL_SFP_8127_ATF;
+ } else if (rtl_is_8116af(tp)) {
+ return RTL_SFP_8168_AF;
+ }
+
+ return RTL_SFP_NONE;
+}
+
static enum rtl_dash_type rtl_get_dash_type(struct rtl8169_private *tp)
{
switch (tp->mac_version) {
@@ -2399,7 +2441,7 @@ static int rtl8169_set_link_ksettings(struct net_device *ndev,
int duplex = cmd->base.duplex;
int speed = cmd->base.speed;
- if (!tp->sfp_mode)
+ if (tp->sfp_mode != RTL_SFP_8127_ATF)
return phylink_ethtool_ksettings_set(tp->phylink, cmd);
if (cmd->base.autoneg != AUTONEG_DISABLE)
@@ -2511,9 +2553,10 @@ void r8169_apply_firmware(struct rtl8169_private *tp)
tp->ocp_base = OCP_STD_PHY_BASE;
/* PHY soft reset may still be in progress */
- phy_read_poll_timeout(tp->phydev, MII_BMCR, val,
- !(val & BMCR_RESET),
- 50000, 600000, true);
+ if (tp->phydev)
+ phy_read_poll_timeout(tp->phydev, MII_BMCR, val,
+ !(val & BMCR_RESET),
+ 50000, 600000, true);
}
}
@@ -2550,6 +2593,8 @@ static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
static void rtl8169_init_phy(struct rtl8169_private *tp)
{
+ phy_init_hw(tp->phydev);
+ phy_resume(tp->phydev);
r8169_hw_phy_config(tp, tp->phydev, tp->mac_version);
if (tp->mac_version <= RTL_GIGA_MAC_VER_06) {
@@ -2564,7 +2609,7 @@ static void rtl8169_init_phy(struct rtl8169_private *tp)
tp->pci_dev->subsystem_device == 0xe000)
phy_write_paged(tp->phydev, 0x0001, 0x10, 0xf01b);
- if (tp->sfp_mode)
+ if (tp->sfp_mode == RTL_SFP_8127_ATF)
rtl_sfp_init(tp);
/* We may have called phy_speed_down before */
@@ -3751,12 +3796,14 @@ static void rtl_hw_start_8117(struct rtl8169_private *tp)
rtl_pcie_state_l2l3_disable(tp);
- rg_saw_cnt = phy_read_paged(tp->phydev, 0x0c42, 0x13) & 0x3fff;
- if (rg_saw_cnt > 0) {
- u16 sw_cnt_1ms_ini;
+ if (tp->phydev) {
+ rg_saw_cnt = phy_read_paged(tp->phydev, 0x0c42, 0x13) & 0x3fff;
+ if (rg_saw_cnt > 0) {
+ u16 sw_cnt_1ms_ini;
- sw_cnt_1ms_ini = (16000000 / rg_saw_cnt) & 0x0fff;
- r8168_mac_ocp_modify(tp, 0xd412, 0x0fff, sw_cnt_1ms_ini);
+ sw_cnt_1ms_ini = (16000000 / rg_saw_cnt) & 0x0fff;
+ r8168_mac_ocp_modify(tp, 0xd412, 0x0fff, sw_cnt_1ms_ini);
+ }
}
r8168_mac_ocp_modify(tp, 0xe056, 0x00f0, 0x0000);
@@ -4932,8 +4979,13 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
goto out;
}
- if (status & LinkChg)
- phy_mac_interrupt(tp->phydev);
+ if (status & LinkChg) {
+ if (tp->phydev)
+ phy_mac_interrupt(tp->phydev);
+ else if (tp->sfp_mode == RTL_SFP_8168_AF)
+ phylink_mac_change(tp->phylink,
+ !!(RTL_R8(tp, PHYstatus) & LinkStatus));
+ }
rtl_irq_disable(tp);
napi_schedule(&tp->napi);
@@ -5045,7 +5097,7 @@ static void rtl8169_down(struct rtl8169_private *tp)
phylink_stop(tp->phylink);
/* Reset SerDes PHY to bring down fiber link */
- if (tp->sfp_mode)
+ if (tp->sfp_mode == RTL_SFP_8127_ATF)
rtl_sfp_reset(tp);
rtl8169_update_counters(tp);
@@ -5067,9 +5119,9 @@ static void rtl8169_up(struct rtl8169_private *tp)
rtl8168_driver_start(tp);
pci_set_master(tp->pci_dev);
- phy_init_hw(tp->phydev);
- phy_resume(tp->phydev);
- rtl8169_init_phy(tp);
+ if (tp->phydev)
+ rtl8169_init_phy(tp);
+
napi_enable(&tp->napi);
enable_work(&tp->wk.work);
rtl_reset_work(tp);
@@ -5147,9 +5199,11 @@ static int rtl_open(struct net_device *dev)
if (retval < 0)
goto err_release_fw_2;
- retval = r8169_phy_connect(tp);
- if (retval)
- goto err_free_irq;
+ if (tp->phydev) {
+ retval = r8169_phy_connect(tp);
+ if (retval)
+ goto err_free_irq;
+ }
rtl8169_up(tp);
rtl8169_init_counter_offsets(tp);
@@ -5654,6 +5708,14 @@ static void rtl_mac_link_up(struct phylink_config *config, struct phy_device *ph
static struct phylink_pcs *rtl_mac_select_pcs(struct phylink_config *config,
phy_interface_t interface)
{
+ struct rtl8169_private *tp = container_of(config, struct rtl8169_private, phylink_config);
+
+ if (!tp->pcs.ops)
+ return NULL;
+
+ if (interface == PHY_INTERFACE_MODE_1000BASEX)
+ return &tp->pcs;
+
return NULL;
}
@@ -5662,6 +5724,51 @@ static void rtl_mac_config(struct phylink_config *config, unsigned int mode,
{
}
+static u16 rtl8169_sds_read(struct rtl8169_private *tp, u16 sds_reg)
+{
+ unsigned long flags;
+ u16 val = 0;
+
+ raw_spin_lock_irqsave(&tp->mac_ocp_lock, flags);
+ __r8168_mac_ocp_write(tp, OCP_SDS_ADDR_REG, sds_reg);
+ __r8168_mac_ocp_write(tp, OCP_SDS_CMD_REG, SDS_CMD_READ);
+ val = __r8168_mac_ocp_read(tp, OCP_SDS_DATA_REG);
+ raw_spin_unlock_irqrestore(&tp->mac_ocp_lock, flags);
+
+ return val;
+}
+
+static void rtl8169_pcs_get_state(struct phylink_pcs *pcs,
+ unsigned int neg_mode,
+ struct phylink_link_state *state)
+{
+ struct rtl8169_private *tp = container_of(pcs, struct rtl8169_private, pcs);
+ u16 bmsr, lpa;
+
+ bmsr = rtl8169_sds_read(tp, RTL_SDS_C22_BASE + MII_BMSR);
+ lpa = rtl8169_sds_read(tp, RTL_SDS_C22_BASE + MII_LPA);
+
+ phylink_mii_c22_pcs_decode_state(state, neg_mode, bmsr, lpa);
+}
+
+static int rtl8169_pcs_config(struct phylink_pcs *pcs, unsigned int mode,
+ phy_interface_t interface,
+ const unsigned long *advertising,
+ bool permit_pause_to_mac)
+{
+ return 0;
+}
+
+static int rtl8169_pcs_validate(struct phylink_pcs *pcs, unsigned long *supported,
+ const struct phylink_link_state *state)
+{
+ return 0;
+}
+
+static void rtl8169_pcs_an_restart(struct phylink_pcs *pcs)
+{
+}
+
static void rtl_mac_disable_tx_lpi(struct phylink_config *config)
{
struct rtl8169_private *tp = container_of(config, struct rtl8169_private, phylink_config);
@@ -5712,6 +5819,13 @@ static unsigned long rtl8169_get_lpi_caps(struct rtl8169_private *tp)
return caps;
}
+static const struct phylink_pcs_ops r8169_pcs_ops = {
+ .pcs_validate = rtl8169_pcs_validate,
+ .pcs_get_state = rtl8169_pcs_get_state,
+ .pcs_config = rtl8169_pcs_config,
+ .pcs_an_restart = rtl8169_pcs_an_restart,
+};
+
static int rtl_init_phylink(struct rtl8169_private *tp)
{
struct phylink *pl;
@@ -5723,10 +5837,18 @@ static int rtl_init_phylink(struct rtl8169_private *tp)
tp->phylink_config.lpi_capabilities = rtl8169_get_lpi_caps(tp);
tp->phylink_config.mac_capabilities |= MAC_ASYM_PAUSE | MAC_SYM_PAUSE;
- if (tp->sfp_mode) {
+ switch (tp->sfp_mode) {
+ case RTL_SFP_8168_AF:
+ tp->pcs.ops = &r8169_pcs_ops;
+ tp->phylink_config.default_an_inband = true;
+ phy_mode = PHY_INTERFACE_MODE_1000BASEX;
+ tp->phylink_config.mac_capabilities |= MAC_1000FD;
+ break;
+ case RTL_SFP_8127_ATF:
phy_mode = PHY_INTERFACE_MODE_INTERNAL;
tp->phylink_config.mac_capabilities |= MAC_10000FD;
- } else {
+ break;
+ default:
phy_mode = PHY_INTERFACE_MODE_INTERNAL;
tp->phylink_config.mac_capabilities |= MAC_10 | MAC_100;
@@ -5747,6 +5869,7 @@ static int rtl_init_phylink(struct rtl8169_private *tp)
PHY_INTERFACE_MODE_MII;
else
phy_mode = PHY_INTERFACE_MODE_INTERNAL;
+ break;
}
__set_bit(phy_mode, tp->phylink_config.supported_interfaces);
@@ -5844,12 +5967,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
}
tp->aspm_manageable = !rc;
- if (rtl_is_8125(tp)) {
- u16 data = r8168_mac_ocp_read(tp, 0xd006);
-
- if ((data & 0xff) == 0x07)
- tp->sfp_mode = true;
- }
+ tp->sfp_mode = rtl_get_sfp_mode(tp);
tp->dash_type = rtl_get_dash_type(tp);
tp->dash_enabled = rtl_dash_is_enabled(tp);
@@ -5957,10 +6075,12 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
if (rc)
return rc;
- rc = r8169_mdio_register(tp);
- if (rc) {
- phylink_destroy(tp->phylink);
- return rc;
+ if (tp->sfp_mode != RTL_SFP_8168_AF) {
+ rc = r8169_mdio_register(tp);
+ if (rc) {
+ phylink_destroy(tp->phylink);
+ return rc;
+ }
}
rc = register_netdev(dev);
--
2.43.0
^ permalink raw reply related
* [PATCH net-next v4 4/6] r8169: add ltr support for RTL8117 series
From: javen @ 2026-07-03 9:24 UTC (permalink / raw)
To: hkallweit1, nic_swsd, andrew+netdev, davem, edumazet, kuba,
pabeni, horms
Cc: netdev, linux-kernel, Javen Xu
In-Reply-To: <20260703092459.1124-1-javen_xu@realsil.com.cn>
From: Javen Xu <javen_xu@realsil.com.cn>
This patch adds ltr support for RTL8117 series, enables RTL8117 series
enter l1.2 state. This makes sense for the system to enter c10 state.
Signed-off-by: Javen Xu <javen_xu@realsil.com.cn>
---
Changes in v2:
- no changes
Changes in v3:
- no changes
Changes in v4:
- no changes
---
drivers/net/ethernet/realtek/r8169_main.c | 21 ++++++++++++++++++++-
1 file changed, 20 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index b5816550a4a6..635131c51db9 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -347,11 +347,13 @@ enum rtl_registers {
ALDPS_LTR = 0xe0a2,
LTR_OBFF_LOCK = 0xe032,
LTR_SNOOP = 0xe034,
+ SEND_LTR_MSG = 0xe038,
#define ALDPS_LTR_EN BIT(0)
#define LTR_OBFF_LOCK_EN BIT(0)
#define LINK_SPEED_CHANGE_EN BIT(14)
#define LTR_SNOOP_EN GENMASK(15, 14)
+#define LTR_MSG_EN BIT(0)
};
enum rtl8168_8101_registers {
@@ -3201,8 +3203,22 @@ static void rtl_enable_ltr(struct rtl8169_private *tp)
r8168_mac_ocp_write(tp, 0xcdf2, 0x9003);
r8168_mac_ocp_modify(tp, LTR_OBFF_LOCK, 0x0000, LINK_SPEED_CHANGE_EN);
break;
- case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
case RTL_GIGA_MAC_VER_52:
+ r8168_mac_ocp_write(tp, 0xcdd0, 0x9003);
+ r8168_mac_ocp_modify(tp, LTR_SNOOP, 0x0000, LTR_SNOOP_EN);
+ r8168_mac_ocp_write(tp, 0xe02c, 0x1880);
+ r8168_mac_ocp_write(tp, 0xe02e, 0x4880);
+ r8168_mac_ocp_modify(tp, ALDPS_LTR, 0x0000, ALDPS_LTR_EN);
+ r8168_mac_ocp_write(tp, 0xcdd8, 0x9003);
+ r8168_mac_ocp_write(tp, 0xcdda, 0x9003);
+ r8168_mac_ocp_write(tp, 0xcddc, 0x9003);
+ r8168_mac_ocp_write(tp, 0xcdd2, 0x883c);
+ r8168_mac_ocp_write(tp, 0xcdd4, 0x8c12);
+ r8168_mac_ocp_write(tp, 0xcdd6, 0x9003);
+ r8168_mac_ocp_write(tp, 0xe0a6, 0x9003);
+ r8168_mac_ocp_write(tp, 0xe0a8, 0x9003);
+ break;
+ case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
r8168_mac_ocp_modify(tp, ALDPS_LTR, 0x0000, ALDPS_LTR_EN);
RTL_W8(tp, COMBO_LTR_EXTEND, RTL_R8(tp, COMBO_LTR_EXTEND) | COMBO_LTR_EXTEND_EN);
fallthrough;
@@ -3222,6 +3238,7 @@ static void rtl_enable_ltr(struct rtl8169_private *tp)
}
/* chip can trigger LTR */
r8168_mac_ocp_modify(tp, LTR_OBFF_LOCK, 0x0003, LTR_OBFF_LOCK_EN);
+ r8168_mac_ocp_modify(tp, SEND_LTR_MSG, 0x0000, LTR_MSG_EN);
}
static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
@@ -3255,6 +3272,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
rtl_enable_ltr(tp);
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
+ case RTL_GIGA_MAC_VER_52:
case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
/* reset ephy tx/rx disable timer */
r8168_mac_ocp_modify(tp, 0xe094, 0xff00, 0);
@@ -3267,6 +3285,7 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
} else {
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_46 ... RTL_GIGA_MAC_VER_48:
+ case RTL_GIGA_MAC_VER_52:
case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_LAST:
r8168_mac_ocp_modify(tp, 0xe092, 0x00ff, 0);
break;
--
2.43.0
^ permalink raw reply related
* [PATCH net-next v4 2/6] r8169: add support for phylink
From: javen @ 2026-07-03 9:24 UTC (permalink / raw)
To: hkallweit1, nic_swsd, andrew+netdev, davem, edumazet, kuba,
pabeni, horms
Cc: netdev, linux-kernel, Javen Xu
In-Reply-To: <20260703092459.1124-1-javen_xu@realsil.com.cn>
From: Javen Xu <javen_xu@realsil.com.cn>
Transfer old framework to phylink. Phylink can support fiber mode card
which can not get link status or link speed from standard phy registers.
Signed-off-by: Javen Xu <javen_xu@realsil.com.cn>
---
Changes in v2:
- merge patch v1 3/6 and v1 4/6.
- add helper rtl_mac_enable_tx_lpi(), rtl_mac_disable_tx_lpi()
and rtl8169_get_lpi_caps()
Changes in v3:
- use phylink_ethtool_set_pauseparam to set pause status when change
mtu
- replace phy_do_ioctl_running with rtl8169_ioctl
- recover phy_mode according to tp->supports_gmii for 1G nics
Changes in v4:
- set lpi_interface if support eee
- Only if jumbo changes, set pause
---
drivers/net/ethernet/realtek/Kconfig | 1 +
drivers/net/ethernet/realtek/r8169_main.c | 320 +++++++++++++++++-----
2 files changed, 247 insertions(+), 74 deletions(-)
diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index 9b0f4f9631db..49ac72734225 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -88,6 +88,7 @@ config R8169
select CRC32
select PHYLIB
select REALTEK_PHY
+ select PHYLINK
help
Say Y here if you have a Realtek Ethernet adapter belonging to
the following families:
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index c60710f9bd21..8f06dedc33d1 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -26,6 +26,7 @@
#include <linux/dma-mapping.h>
#include <linux/pm_runtime.h>
#include <linux/bitfield.h>
+#include <linux/phylink.h>
#include <linux/prefetch.h>
#include <linux/ipv6.h>
#include <linux/unaligned.h>
@@ -775,6 +776,10 @@ struct rtl8169_private {
struct r8169_led_classdev *leds;
u32 ocp_base;
+ struct phylink *phylink;
+ struct phylink_config phylink_config;
+ struct ethtool_pauseparam saved_pause;
+ bool jumbo_pause_saved;
};
typedef void (*rtl_generic_fct)(struct rtl8169_private *tp);
@@ -2253,7 +2258,7 @@ static int rtl8169_get_eee(struct net_device *dev, struct ethtool_keee *data)
if (!rtl_supports_eee(tp))
return -EOPNOTSUPP;
- ret = phy_ethtool_get_eee(tp->phydev, data);
+ ret = phylink_ethtool_get_eee(tp->phylink, data);
if (ret)
return ret;
@@ -2269,7 +2274,7 @@ static int rtl8169_set_eee(struct net_device *dev, struct ethtool_keee *data)
if (!rtl_supports_eee(tp))
return -EOPNOTSUPP;
- return phy_ethtool_set_eee(tp->phydev, data);
+ return phylink_ethtool_set_eee(tp->phylink, data);
}
static void rtl8169_get_ringparam(struct net_device *dev,
@@ -2300,13 +2305,8 @@ static void rtl8169_get_pauseparam(struct net_device *dev,
struct ethtool_pauseparam *data)
{
struct rtl8169_private *tp = netdev_priv(dev);
- bool tx_pause, rx_pause;
- phy_get_pause(tp->phydev, &tx_pause, &rx_pause);
-
- data->autoneg = tp->phydev->autoneg;
- data->tx_pause = tx_pause ? 1 : 0;
- data->rx_pause = rx_pause ? 1 : 0;
+ phylink_ethtool_get_pauseparam(tp->phylink, data);
}
static int rtl8169_set_pauseparam(struct net_device *dev,
@@ -2317,9 +2317,7 @@ static int rtl8169_set_pauseparam(struct net_device *dev,
if (dev->mtu > ETH_DATA_LEN)
return -EOPNOTSUPP;
- phy_set_asym_pause(tp->phydev, data->rx_pause, data->tx_pause);
-
- return 0;
+ return phylink_ethtool_set_pauseparam(tp->phylink, data);
}
static void rtl8169_get_eth_mac_stats(struct net_device *dev,
@@ -2385,6 +2383,14 @@ static void rtl8169_get_eth_ctrl_stats(struct net_device *dev,
le32_to_cpu(tp->counters->rx_unknown_opcode);
}
+static int rtl8169_get_link_ksettings(struct net_device *ndev,
+ struct ethtool_link_ksettings *cmd)
+{
+ struct rtl8169_private *tp = netdev_priv(ndev);
+
+ return phylink_ethtool_ksettings_get(tp->phylink, cmd);
+}
+
static int rtl8169_set_link_ksettings(struct net_device *ndev,
const struct ethtool_link_ksettings *cmd)
{
@@ -2394,7 +2400,7 @@ static int rtl8169_set_link_ksettings(struct net_device *ndev,
int speed = cmd->base.speed;
if (!tp->sfp_mode)
- return phy_ethtool_ksettings_set(phydev, cmd);
+ return phylink_ethtool_ksettings_set(tp->phylink, cmd);
if (cmd->base.autoneg != AUTONEG_DISABLE)
return -EINVAL;
@@ -2415,6 +2421,13 @@ static int rtl8169_set_link_ksettings(struct net_device *ndev,
return 0;
}
+static int rtl8169_nway_reset(struct net_device *dev)
+{
+ struct rtl8169_private *tp = netdev_priv(dev);
+
+ return phylink_ethtool_nway_reset(tp->phylink);
+}
+
static const struct ethtool_ops rtl8169_ethtool_ops = {
.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
ETHTOOL_COALESCE_MAX_FRAMES,
@@ -2430,10 +2443,10 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
.get_sset_count = rtl8169_get_sset_count,
.get_ethtool_stats = rtl8169_get_ethtool_stats,
.get_ts_info = ethtool_op_get_ts_info,
- .nway_reset = phy_ethtool_nway_reset,
+ .nway_reset = rtl8169_nway_reset,
.get_eee = rtl8169_get_eee,
.set_eee = rtl8169_set_eee,
- .get_link_ksettings = phy_ethtool_get_link_ksettings,
+ .get_link_ksettings = rtl8169_get_link_ksettings,
.set_link_ksettings = rtl8169_set_link_ksettings,
.get_ringparam = rtl8169_get_ringparam,
.get_pause_stats = rtl8169_get_pause_stats,
@@ -2623,6 +2636,51 @@ static void rtl8169_init_ring_indexes(struct rtl8169_private *tp)
tp->dirty_tx = tp->cur_tx = tp->cur_rx = 0;
}
+static void rtl_jumbo_config_pause(struct rtl8169_private *tp)
+{
+ bool jumbo = tp->dev->mtu > ETH_DATA_LEN;
+ struct ethtool_pauseparam pause = {};
+
+ ASSERT_RTNL();
+
+ if (jumbo) {
+ if (!tp->jumbo_pause_saved) {
+ struct ethtool_link_ksettings cmd = {};
+ bool adv_pause, adv_asym;
+
+ phylink_ethtool_get_pauseparam(tp->phylink, &tp->saved_pause);
+ if (tp->saved_pause.autoneg) {
+ phylink_ethtool_ksettings_get(tp->phylink, &cmd);
+ adv_pause = ethtool_link_ksettings_test_link_mode(&cmd,
+ advertising,
+ Pause);
+ adv_asym = ethtool_link_ksettings_test_link_mode(&cmd,
+ advertising,
+ Asym_Pause);
+ if (adv_pause && !adv_asym) {
+ tp->saved_pause.rx_pause = 1;
+ tp->saved_pause.tx_pause = 1;
+ } else if (adv_pause && adv_asym) {
+ tp->saved_pause.rx_pause = 1;
+ tp->saved_pause.tx_pause = 0;
+ } else if (!adv_pause && adv_asym) {
+ tp->saved_pause.rx_pause = 0;
+ tp->saved_pause.tx_pause = 1;
+ } else {
+ tp->saved_pause.rx_pause = 0;
+ tp->saved_pause.tx_pause = 0;
+ }
+ }
+ tp->jumbo_pause_saved = true;
+ }
+ pause.autoneg = tp->saved_pause.autoneg;
+ phylink_ethtool_set_pauseparam(tp->phylink, &pause);
+ } else if (tp->jumbo_pause_saved) {
+ phylink_ethtool_set_pauseparam(tp->phylink, &tp->saved_pause);
+ tp->jumbo_pause_saved = false;
+ }
+}
+
static void rtl_jumbo_config(struct rtl8169_private *tp)
{
bool jumbo = tp->dev->mtu > ETH_DATA_LEN;
@@ -2656,15 +2714,6 @@ static void rtl_jumbo_config(struct rtl8169_private *tp)
if (pci_is_pcie(tp->pci_dev) && tp->supports_gmii)
pcie_set_readrq(tp->pci_dev, readrq);
-
- /* Chip doesn't support pause in jumbo mode */
- if (jumbo) {
- linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT,
- tp->phydev->advertising);
- linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
- tp->phydev->advertising);
- phy_start_aneg(tp->phydev);
- }
}
DECLARE_RTL_COND(rtl_chipcmd_cond)
@@ -2779,7 +2828,7 @@ static void rtl_prepare_power_down(struct rtl8169_private *tp)
rtl_ephy_write(tp, 0x19, 0xff64);
if (device_may_wakeup(tp_to_dev(tp))) {
- phy_speed_down(tp->phydev, false);
+ phylink_speed_down(tp->phylink, false);
rtl_wol_enable_rx(tp);
}
}
@@ -2831,6 +2880,16 @@ static void rtl8169_set_magic_reg(struct rtl8169_private *tp)
RTL_W32(tp, 0x7c, val);
}
+static int rtl8169_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+{
+ struct rtl8169_private *tp = netdev_priv(dev);
+
+ if (!netif_running(dev))
+ return -ENODEV;
+
+ return phylink_mii_ioctl(tp->phylink, ifr, cmd);
+}
+
static void rtl_set_rx_mode(struct net_device *dev)
{
u32 rx_mode = AcceptBroadcast | AcceptMyPhys | AcceptMulticast;
@@ -4138,12 +4197,17 @@ static void rtl_hw_start(struct rtl8169_private *tp)
static int rtl8169_change_mtu(struct net_device *dev, int new_mtu)
{
struct rtl8169_private *tp = netdev_priv(dev);
+ bool jumbo_before = dev->mtu > ETH_DATA_LEN;
+ bool jumbo_after = new_mtu > ETH_DATA_LEN;
WRITE_ONCE(dev->mtu, new_mtu);
netdev_update_features(dev);
rtl_jumbo_config(tp);
rtl_set_eee_txidle_timer(tp);
+ if (jumbo_before != jumbo_after)
+ rtl_jumbo_config_pause(tp);
+
return 0;
}
@@ -4929,9 +4993,6 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
static void rtl_enable_tx_lpi(struct rtl8169_private *tp, bool enable)
{
- if (!rtl_supports_eee(tp))
- return;
-
switch (tp->mac_version) {
case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_52:
/* Adjust EEE LED frequency */
@@ -4962,41 +5023,15 @@ static void rtl_enable_tx_lpi(struct rtl8169_private *tp, bool enable)
}
}
-static void r8169_phylink_handler(struct net_device *ndev)
-{
- struct rtl8169_private *tp = netdev_priv(ndev);
- struct device *d = tp_to_dev(tp);
-
- tp->speed = tp->phydev->speed;
- if (netif_carrier_ok(ndev)) {
- rtl_link_chg_patch(tp, tp->speed);
- rtl_enable_tx_lpi(tp, tp->phydev->enable_tx_lpi);
- pm_request_resume(d);
- } else {
- pm_runtime_idle(d);
- }
-
- phy_print_status(tp->phydev);
-}
-
static int r8169_phy_connect(struct rtl8169_private *tp)
{
- struct phy_device *phydev = tp->phydev;
- phy_interface_t phy_mode;
int ret;
- phy_mode = tp->supports_gmii ? PHY_INTERFACE_MODE_GMII :
- PHY_INTERFACE_MODE_MII;
-
- ret = phy_connect_direct(tp->dev, phydev, r8169_phylink_handler,
- phy_mode);
- if (ret)
+ ret = phylink_connect_phy(tp->phylink, tp->phydev);
+ if (ret) {
+ netdev_err(tp->dev, "failed to connect phy\n");
return ret;
-
- if (!tp->supports_gmii)
- phy_set_max_speed(phydev, SPEED_100);
-
- phy_attached_info(phydev);
+ }
return 0;
}
@@ -5007,7 +5042,7 @@ static void rtl8169_down(struct rtl8169_private *tp)
/* Clear all task flags */
bitmap_zero(tp->wk.flags, RTL_FLAG_MAX);
- phy_stop(tp->phydev);
+ phylink_stop(tp->phylink);
/* Reset SerDes PHY to bring down fiber link */
if (tp->sfp_mode)
@@ -5039,7 +5074,7 @@ static void rtl8169_up(struct rtl8169_private *tp)
enable_work(&tp->wk.work);
rtl_reset_work(tp);
- phy_start(tp->phydev);
+ phylink_start(tp->phylink);
}
static int rtl8169_close(struct net_device *dev)
@@ -5055,7 +5090,7 @@ static int rtl8169_close(struct net_device *dev)
free_irq(tp->irq, tp);
- phy_disconnect(tp->phydev);
+ phylink_disconnect_phy(tp->phylink);
dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray,
tp->RxPhyAddr);
@@ -5190,8 +5225,11 @@ static int rtl8169_runtime_resume(struct device *dev)
rtl_rar_set(tp, tp->dev->dev_addr);
__rtl8169_set_wol(tp, tp->saved_wolopts);
- if (tp->TxDescArray)
+ if (tp->TxDescArray) {
+ rtnl_lock();
rtl8169_up(tp);
+ rtnl_unlock();
+ }
netif_device_attach(tp->dev);
@@ -5288,6 +5326,8 @@ static void rtl_remove_one(struct pci_dev *pdev)
r8169_remove_leds(tp->leds);
unregister_netdev(tp->dev);
+ if (tp->phylink)
+ phylink_destroy(tp->phylink);
if (tp->dash_type != RTL_DASH_NONE)
rtl8168_driver_stop(tp);
@@ -5310,7 +5350,7 @@ static const struct net_device_ops rtl_netdev_ops = {
.ndo_fix_features = rtl8169_fix_features,
.ndo_set_features = rtl8169_set_features,
.ndo_set_mac_address = rtl_set_mac_address,
- .ndo_eth_ioctl = phy_do_ioctl_running,
+ .ndo_eth_ioctl = rtl8169_ioctl,
.ndo_set_rx_mode = rtl_set_rx_mode,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = rtl8169_netpoll,
@@ -5474,16 +5514,6 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
return -EUNATCH;
}
- tp->phydev->mac_managed_pm = true;
- if (rtl_supports_eee(tp))
- phy_support_eee(tp->phydev);
- phy_support_asym_pause(tp->phydev);
-
- /* mimic behavior of r8125/r8126 vendor drivers */
- if (tp->mac_version == RTL_GIGA_MAC_VER_61)
- phy_disable_eee_mode(tp->phydev,
- ETHTOOL_LINK_MODE_2500baseT_Full_BIT);
-
/* PHY will be woken up in rtl_open() */
phy_suspend(tp->phydev);
@@ -5599,6 +5629,140 @@ static bool rtl_aspm_is_safe(struct rtl8169_private *tp)
return false;
}
+static void rtl_mac_link_down(struct phylink_config *config, unsigned int mode,
+ phy_interface_t interface)
+{
+ struct rtl8169_private *tp = container_of(config, struct rtl8169_private, phylink_config);
+
+ tp->speed = SPEED_UNKNOWN;
+ pm_runtime_idle(tp_to_dev(tp));
+}
+
+static void rtl_mac_link_up(struct phylink_config *config, struct phy_device *phydev,
+ unsigned int mode, phy_interface_t interface,
+ int speed, int duplex, bool tx_pause, bool rx_pause)
+{
+ struct rtl8169_private *tp = container_of(config, struct rtl8169_private, phylink_config);
+ struct device *d = tp_to_dev(tp);
+
+ tp->speed = speed;
+ rtl_link_chg_patch(tp, speed);
+
+ pm_request_resume(d);
+}
+
+static struct phylink_pcs *rtl_mac_select_pcs(struct phylink_config *config,
+ phy_interface_t interface)
+{
+ return NULL;
+}
+
+static void rtl_mac_config(struct phylink_config *config, unsigned int mode,
+ const struct phylink_link_state *state)
+{
+}
+
+static void rtl_mac_disable_tx_lpi(struct phylink_config *config)
+{
+ struct rtl8169_private *tp = container_of(config, struct rtl8169_private, phylink_config);
+
+ rtl_enable_tx_lpi(tp, false);
+}
+
+static int rtl_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, bool tx_clk_stop)
+{
+ struct rtl8169_private *tp = container_of(config, struct rtl8169_private, phylink_config);
+
+ if (!rtl_supports_eee(tp))
+ return -EOPNOTSUPP;
+
+ rtl_enable_tx_lpi(tp, true);
+
+ return 0;
+}
+
+static const struct phylink_mac_ops rtl_phylink_mac_ops = {
+ .mac_select_pcs = rtl_mac_select_pcs,
+ .mac_config = rtl_mac_config,
+ .mac_link_down = rtl_mac_link_down,
+ .mac_link_up = rtl_mac_link_up,
+ .mac_disable_tx_lpi = rtl_mac_disable_tx_lpi,
+ .mac_enable_tx_lpi = rtl_mac_enable_tx_lpi,
+};
+
+static unsigned long rtl8169_get_lpi_caps(struct rtl8169_private *tp)
+{
+ unsigned long caps = 0;
+
+ if (!rtl_supports_eee(tp))
+ return 0;
+
+ caps |= MAC_100FD | MAC_1000FD;
+
+ /* mimic behavior of r8125/r8126 vendor drivers
+ * RTL_GIGA_MAC_VER_61 doesn't support 2.5G eee
+ */
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_63)
+ caps |= MAC_2500FD;
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_70)
+ caps |= MAC_5000FD;
+ if (tp->mac_version == RTL_GIGA_MAC_VER_80)
+ caps |= MAC_10000FD;
+
+ return caps;
+}
+
+static int rtl_init_phylink(struct rtl8169_private *tp)
+{
+ struct phylink *pl;
+ phy_interface_t phy_mode;
+
+ tp->phylink_config.dev = &tp->dev->dev;
+ tp->phylink_config.type = PHYLINK_NETDEV;
+ tp->phylink_config.mac_managed_pm = true;
+ tp->phylink_config.lpi_capabilities = rtl8169_get_lpi_caps(tp);
+ tp->phylink_config.mac_capabilities |= MAC_ASYM_PAUSE | MAC_SYM_PAUSE;
+
+ if (tp->sfp_mode) {
+ phy_mode = PHY_INTERFACE_MODE_INTERNAL;
+ tp->phylink_config.mac_capabilities |= MAC_10000FD;
+ } else {
+ phy_mode = PHY_INTERFACE_MODE_INTERNAL;
+ tp->phylink_config.mac_capabilities |= MAC_10 | MAC_100;
+
+ if (tp->mac_version == RTL_GIGA_MAC_VER_80)
+ tp->phylink_config.mac_capabilities |= MAC_1000FD | MAC_2500FD |
+ MAC_5000FD | MAC_10000FD;
+ else if (tp->mac_version == RTL_GIGA_MAC_VER_70)
+ tp->phylink_config.mac_capabilities |= MAC_1000FD |
+ MAC_2500FD | MAC_5000FD;
+ else if (tp->mac_version >= RTL_GIGA_MAC_VER_61)
+ tp->phylink_config.mac_capabilities |= MAC_1000FD | MAC_2500FD;
+ else
+ if (tp->supports_gmii)
+ tp->phylink_config.mac_capabilities |= MAC_1000FD;
+
+ if (tp->mac_version < RTL_GIGA_MAC_VER_61)
+ phy_mode = tp->supports_gmii ? PHY_INTERFACE_MODE_GMII :
+ PHY_INTERFACE_MODE_MII;
+ else
+ phy_mode = PHY_INTERFACE_MODE_INTERNAL;
+ }
+
+ __set_bit(phy_mode, tp->phylink_config.supported_interfaces);
+ if (tp->phylink_config.lpi_capabilities)
+ __set_bit(phy_mode, tp->phylink_config.lpi_interfaces);
+
+ pl = phylink_create(&tp->phylink_config, tp_to_dev(tp)->fwnode,
+ phy_mode, &rtl_phylink_mac_ops);
+ if (IS_ERR(pl))
+ return PTR_ERR(pl);
+
+ tp->phylink = pl;
+
+ return 0;
+}
+
static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
{
const struct rtl_chip_info *chip;
@@ -5789,13 +5953,21 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
pci_set_drvdata(pdev, tp);
- rc = r8169_mdio_register(tp);
+ rc = rtl_init_phylink(tp);
if (rc)
return rc;
+ rc = r8169_mdio_register(tp);
+ if (rc) {
+ phylink_destroy(tp->phylink);
+ return rc;
+ }
+
rc = register_netdev(dev);
- if (rc)
+ if (rc) {
+ phylink_destroy(tp->phylink);
return rc;
+ }
if (IS_ENABLED(CONFIG_R8169_LEDS)) {
if (rtl_is_8125(tp))
--
2.43.0
^ permalink raw reply related
* Re: [RFC PATCH 3/3] coredump, net: remove `SOCK_COREDUMP`
From: Christian Brauner @ 2026-07-03 9:31 UTC (permalink / raw)
To: John Ericson
Cc: Christian Brauner, John Ericson, David S . Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Cong Wang, Kuniyuki Iwashima,
Simon Horman, David Rheinsberg, Andy Lutomirski, Sergei Zimmerman,
network dev, linux-fsdevel, Mickaël Salaün,
Günther Noack, Paul Moore, linux-security-module, LKML
In-Reply-To: <7acb650b-a0de-4244-861f-4dda70ca8993@app.fastmail.com>
On 2026-07-03 05:08 -0400, John Ericson wrote:
> On Fri, Jul 3, 2026, at 4:11 AM, Christian Brauner wrote:
> > I don't think dragging the bowels of net/ into fs/coredump.c just for
> > the sake of getting a purely internal SOCK_COREDUMP flag out of the way
> > is the right way to go.
> >
> > I suspect the saner thing to do would be to introduce a primitive for
> > connecting to an AF_UNIX path-based socket directly instead of this
> > weird dance here, no?
> >
> > int kernel_unix_connect(const char *path, struct socket *socket, unsigned int o_flags, int type)
> >
> > then my kthread changes would collapse this into:
> >
> > scoped_with_init_fs()
> > retval = kernel_unix_connect(path, socket, O_NONBLOCK, SOCK_STREAM);
>
> That works for this case, but the destination I am trying to eventually
> reach is being allowed (in userspace) to connect to unbound sockets by
> their fd --- no path, no abstract socket name.
But these are orthogonal changes. It sill doesn't mean we should sprawl
net internals over coredump code anymore than we already have to. I'm
fond of kernel_unix_connect() int dfd, const char *path even would be
fine.
> unix_connectat(int fd, const char *path, struct socket *socket,
> unsigned int at_flags, unsigned int o_flags,
> int type)
>
> is a mouthful, but it would work. Still, there is a subtlety about the
> retry logic. When one does something like:
>
> > connect(..."/dev/fd/N",...)
>
> it will repeatedly re-lookup "/dev/fd/N" until the timeout is reached. I
> consider that pretty terrible --- the rest of the program could race to
> change what that file descriptor (number) refers to. Therefore, I think
> table stakes to make a good `unix_connectat` is to make the
> `AT_EMPTY_PATH` case not re-lookup the socket.
I have no idea how this has any bearong on the three helper split.
> (making a sockfs file descriptor work is separate, I already have the
> patch for that, I can include it.)
>
> > The two helpers also make no sense to me and force a bunch of cleanup on
> > the caller as well.
>
> I am fine with `unix_connectat`, but just for reference, me breaking up
> the steps is because I generally like the decomposition of `fverb`
> rather than `verbat` system calls, since the latter would typically be
> used with `openat` or so. It seems the `kernel_*` "syscalls" generally
> take `struct path` rather than strings, which seems good and in the
There's a time to follow precedence and there's a time to do what the
maintainability demands. I think here clearly we don't want to pass a
struct path. That makes no sense because we don't care about using that
object at all. It's merely an intermediate jumping point. This is
fundamentally about connecting from the kernel to a specific pathname
that functions as a socket address. Intermediary objects don't matter
(yet).
> spirit of that decomposition, but then even `struct path` is overkill to
> refer to a socket. So putting all that together, the final composition I
> had was:
>
> 1. string path (from /proc/...) -> `struct path`
> 2. `struct path` -> `struct sock *`
> 3. connect to `struct sock *`
>
> So I quite liked those 3 orthogonal knobs, vs an all-singing-all-dancing
> `unix_connectat`. (I suppose making it `struct socket *` would make it
> slightly less internals-y?) But again, anything that puts us on track to
> being able to connect to an unbound socket without procfs is good enough
> for me.
To me this reads like you're introducing moving parts for the sake of a
philosophical argument. I couldn't care less about that. What matters is
maintainability. Having three knobs that introduce potentially three
separate cleanup requirements and exposing three different objects when
it's not needed is just a burden.
>
> > I'm not sure why we would go on altering all kinds of LSM hooks as well.
>
> That's in the commit message, it is because without `SOCK_COREDUMP`
> those are all dead code. Instead of removing them in this commit, I can
> just keep those flags, or remove them in a separate commit. Fine
Do it as a separte commit once we've decided to do this, I think.
^ permalink raw reply
* Re: [Intel-wired-lan] [PATCH 2/4] ice: use kzalloc() to allocate staging buffer for reading from GNSS
From: Przemek Kitszel @ 2026-07-03 9:34 UTC (permalink / raw)
To: Mike Rapoport
Cc: Andrew Lunn, David S. Miller, Eric Dumazet, Jakub Kicinski,
Manish Chopra, Paolo Abeni, Edward Cree, Sudarsana Kalluru,
Tony Nguyen, intel-wired-lan, linux-kernel, linux-mm,
linux-net-drivers, netdev
In-Reply-To: <akZ4dBzkuoKPkIZT@kernel.org>
On 7/2/26 4:40 PM, Mike Rapoport wrote:
> On Thu, Jul 02, 2026 at 03:49:36PM +0200, Przemek Kitszel wrote:
>> On 7/1/26 15:57, Mike Rapoport (Microsoft) wrote:
>>> ice_gnss_read() uses get_zeroed_page() to allocate a staging buffer for
>>> reading GNSS module data via I2C bus.
>>>
>>> This buffer can be allocated with kmalloc() as there's nothing special
>>> about it to go directly to the page allocator.
>>>
>>> kmalloc() provides a better API that does not require ugly casts and
>>> kfree() does not need to know the size of the freed object.
>>>
>>> Performance difference between kmalloc() and __get_free_pages() is not
>>> measurable as both allocators take an object/page from a per-CPU list for
>>> fast path allocations.
>>>
>>> For the slow path the performance is anyway determined by the amount of
>>> reclaim involved rather than by what allocator is used.
>>>
>>> Replace use of get_zeroed_page() with kzalloc() and free_page() with
>>> kfree().
>>>
>>> Link: https://lore.kernel.org/all/635405e4-9423-4a25-a6e7-e03c8ea0bcbe@redhat.com
>>> Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
>>> ---
>>> drivers/net/ethernet/intel/ice/ice_gnss.c | 5 +++--
>>> 1 file changed, 3 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c
>>> index 8fd954f1ebd6..7d21c3417b0b 100644
>>> --- a/drivers/net/ethernet/intel/ice/ice_gnss.c
>>> +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c
>>> @@ -2,6 +2,7 @@
>>> /* Copyright (C) 2021-2022, Intel Corporation. */
>>> #include "ice.h"
>>> +#include <linux/slab.h>
>>> #include "ice_lib.h"
>>> /**
>>> @@ -124,7 +125,7 @@ static void ice_gnss_read(struct kthread_work *work)
>>> data_len = min_t(typeof(data_len), data_len, PAGE_SIZE);
>>> - buf = (char *)get_zeroed_page(GFP_KERNEL);
>>> + buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
>>
>> nit:
>> from the code it is clear that we read at most a page, and @data_len
>> stores the actual amount needed
>>
>> comment:
>> I don't know why we limit to a page, it's outside of the scope of this
>> series, but likely you have removed the limit (which will go into the
>> loop - single AQ call is likely limited by a PAGE too).
>
> Not sure I follow how the limit changed. buf remains PAGE_SIZE regardless
> of allocation API.
data_len passed by the caller could be bigger than PAGE_SIZE, we cap it
to PAGE_SIZE, likely due to the old allocation method
but I don't insist on any change to this patch (esp. given all other are
fine)
>
>> Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
>
> Thanks!
>
We are fine to merge it directly via netdev.
^ permalink raw reply
* [PATCH net v2] gtp: parse extension headers before reading inner protocol
From: Zhixing Chen @ 2026-07-03 9:37 UTC (permalink / raw)
To: Pablo Neira Ayuso, Harald Welte
Cc: Andrew Lunn, David S . Miller, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, osmocom-net-gprs, netdev, Zhixing Chen
GTPv1-U packets may carry a chain of extension headers before the inner
IP packet. The receive path already parses and skips these extension
headers, but it currently reads the inner protocol before doing so.
As a result, the first extension header byte is interpreted as the inner
IP version. Packets with extension headers are then dropped before PDP
lookup.
Parse the extension header chain before calling gtp_inner_proto(), so the
inner protocol is read from the actual inner IP header.
Fixes: c75fc0b9e5be ("gtp: identify tunnel via GTP device + GTP version + TEID + family")
Signed-off-by: Zhixing Chen <running910@gmail.com>
---
Changes in v2:
- Add missing Fixes tag.
v1: https://lore.kernel.org/netdev/20260703084244.59077-1-running910@gmail.com/T/
---
drivers/net/gtp.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index a60ef32b35b8..4a8b00548673 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -826,6 +826,10 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
if (!pskb_may_pull(skb, hdrlen))
return -1;
+ if (gtp1->flags & GTP1_F_EXTHDR &&
+ gtp_parse_exthdrs(skb, &hdrlen) < 0)
+ return -1;
+
if (gtp_inner_proto(skb, hdrlen, &inner_proto) < 0) {
netdev_dbg(gtp->dev, "GTP packet does not encapsulate an IP packet\n");
return -1;
@@ -840,10 +844,6 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
return 1;
}
- if (gtp1->flags & GTP1_F_EXTHDR &&
- gtp_parse_exthdrs(skb, &hdrlen) < 0)
- return -1;
-
return gtp_rx(pctx, skb, hdrlen, gtp->role, inner_proto);
}
--
2.34.1
^ permalink raw reply related
* Re: [PATCH v2 2/2] bonding: reuse neigh_setup from slave neigh_parms
From: Paritosh Potukuchi @ 2026-07-03 9:47 UTC (permalink / raw)
To: kuniyu
Cc: netdev, linux-kernel, kuba, edumazet, andrew+netdev, jv, davem,
pabeni, paritosh.potukuchi
In-Reply-To: <20260703064109.1836070-1-kuniyu@google.com>
Hi Kuniyuki,
>This introduces O(n) list traversal while it can be done
>with fixed costs (3 dereferences + 1 call).
>Since neigh_table is global (arp_tbl or nd_tbl), the O(n)
>list traversal could take longer and rather de-optimise.
Yes, that is true. One reason why I chose to do that is
because ndo_neigh_setup is a function primarily meant
to setup the neigh_parms structure, when neigh_parms does
not exist.
On the other hand, lookup_neigh_parms is meant
to search for a near-complete neigh_parms structure,
that is already associated with a netdev.
Even if we want to use ndo_neigh_setup, since it takes
less time, I would suggest using it as a fallback to
not finding an already existing parms, setup.
Moreover, time complexity might not be an issue in this
path since, this is rarely used aggresively.
One issue with ndo_neigh_setup in bond-like devices is
that, to get the underlying netdevs neigh_setup function,
it expects us to pass a dummy neigh_parms structure that
has been zeroed out. This seems to be fragile as suggested
in a TODO in bond_neigh_init().
Generally its main goal is to fill the parms.neigh_setup
field.
Can we populate a few more fields in the zeroed-
out parms structure, before passing to the driver in
ndo_neigh_setup? That seems to be a much safer approach.
Regards,
Paritosh
^ permalink raw reply
* Re: [PATCH net] gtp: parse extension headers before reading inner protocol
From: Zhixing Chen @ 2026-07-03 9:49 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: Harald Welte, Andrew Lunn, David S . Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, osmocom-net-gprs, netdev
In-Reply-To: <akd4sLY7qR0597Si@chamomile>
> Missing Fixes: tag.
Thanks for pointing this out. I have sent v2 with the Fixes tag added.
^ permalink raw reply
* [PATCH v2 net-next] ethtool: link 10000baseCR to SFF-8431, Appendix-E SFP+ DA
From: Siddaraju DH @ 2026-07-03 10:05 UTC (permalink / raw)
To: Michal Kubecek, Andrew Lunn, Maxime Chevallier, kuba, netdev
Cc: Shubham Das, Balaji Chintalapalle, Vijay Srinivasan,
Magnus Lindberg, Niklas Damberg, Jonas Wirandi, Siddaraju DH,
Siddaraju DH
Add comment to clarify the physical media 10000baseCR follows.
10000baseCR does not correspond to any IEEE 802.3 *base-CR PMD.
It has no autonegotiation, no link training, and no mandatory FEC.
The industry standard for this media type is SFF-8431 Appendix-E
Direct Attach cable, also known as 10G_SFI_DA.
Link: https://lore.kernel.org/r/SN7PR11MB69003D33489DB1D6B17EF72A9AF52@SN7PR11MB6900.namprd11.prod.outlook.com
Signed-off-by: Siddaraju DH <siddaraju.dh@intel.com>
---
include/uapi/linux/ethtool.h | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index a2091d4e00f3..986d70caec33 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -2013,7 +2013,13 @@ enum ethtool_link_mode_bit_indices {
ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT = 39,
ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT = 40,
ETHTOOL_LINK_MODE_1000baseX_Full_BIT = 41,
+
+ /* Despite the "baseCR" in 10000baseCR, this is not an IEEE 802.3 baseCR
+ * It represents SFF-8431 Appendix-E SFP+ Direct Attach (10G-SFI-DA).
+ * The name is kept as-is for uAPI backward compatibility.
+ */
ETHTOOL_LINK_MODE_10000baseCR_Full_BIT = 42,
+
ETHTOOL_LINK_MODE_10000baseSR_Full_BIT = 43,
ETHTOOL_LINK_MODE_10000baseLR_Full_BIT = 44,
ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT = 45,
--
2.25.1
^ permalink raw reply related
* Re: [PATCH v4 1/7] dt-bindings: mtd: jedec,spi-nor: allow the SFDP to be exposed via NVMEM
From: Miquel Raynal @ 2026-07-03 10:10 UTC (permalink / raw)
To: Rob Herring
Cc: Manikandan.M, krzk, pratyush, mwalle, takahiro.kuwano, richard,
vigneshr, krzk+dt, conor+dt, srini, Nicolas.Ferre,
alexandre.belloni, claudiu.beznea, linux, richardcochran, linusw,
arnd, michael, linux-mtd, devicetree, linux-kernel,
linux-arm-kernel, netdev
In-Reply-To: <20260702163723.GA227454-robh@kernel.org>
On 02/07/2026 at 11:37:23 -05, Rob Herring <robh@kernel.org> wrote:
> On Thu, Jul 02, 2026 at 06:55:15AM +0000, Manikandan.M@microchip.com wrote:
>> Hi Krzysztof,
>>
>> On 7/2/26 11:46 AM, Krzysztof Kozlowski wrote:
>> > EXTERNAL EMAIL: Do not click links or open attachments unless you know the content is safe
>> >
>> > On Tue, Jun 30, 2026 at 02:54:00PM +0530, Manikandan Muralidharan wrote:
>> >> Add an optional "sfdp" child node (compatible "jedec,sfdp") that
>> >> describes the SFDP as a read-only NVMEM provider via nvmem.yaml, so its
>> >
>> > What is SFDP?
>> >
>> SFDP is the Serial Flash Discoverable Parameters -- a JEDEC-standardised
>> (JESD216) read-only parameter table present in most SPI NOR flashes, the
>> table contents provide basic information about the flash. There are
>> standard tables which are specified by the JEDEC standard and there are
>> vendor tables.
>
> Is SFDP present or not discoverable? Or we have a table of discoverable
> parameters that itself is not discoverable.
SFDP is almost always there. I don't think there are any non SFDP chips
manufactured today (?). The thing is, even if we don't need to define it
in DT, we might need to point to it in order to extract eg. a unique ID
or a MAC address through the NVMEM interface.
SFDP is split into several sub-tables, the first one is mandatory, but
then there are optional tables which can be discovered dynamically.
Thanks,
Miquèl
^ permalink raw reply
* Re: [PATCH net-next v11 1/7] dt-bindings: phy: document the serdes PHY on sa8255p
From: Konrad Dybcio @ 2026-07-03 10:13 UTC (permalink / raw)
To: Geert Uytterhoeven, Bartosz Golaszewski
Cc: Vinod Koul, Bjorn Andersson, Konrad Dybcio, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Andrew Lunn, David S. Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Maxime Coquelin,
Alexandre Torgue, Giuseppe Cavallaro, Chen-Yu Tsai,
Jernej Skrabec, Neil Armstrong, Kevin Hilman, Jerome Brunet,
Shawn Guo, Fabio Estevam, Jan Petrous, s32, Mohd Ayaan Anwar,
Romain Gantois, Magnus Damm, Maxime Ripard, Christophe Roullier,
Radu Rendec, linux-arm-msm, devicetree, linux-kernel, netdev,
linux-stm32, linux-arm-kernel, Drew Fustini, linux-sunxi,
linux-amlogic, linux-mips, imx, linux-renesas-soc, linux-rockchip,
sophgo, linux-riscv, Bartosz Golaszewski, Bartosz Golaszewski
In-Reply-To: <CAMuHMdXNG=C=XcioQUEN1M7cQgKhO0AxUyg5X+TWb2rQ3-H3fw@mail.gmail.com>
On 7/2/26 11:16 AM, Geert Uytterhoeven wrote:
> Hi Bartosz,
>
> On Thu, 2 Jul 2026 at 11:12, Bartosz Golaszewski <brgl@kernel.org> wrote:
>> On Tue, 30 Jun 2026 12:23:16 +0200, Vinod Koul <vkoul@kernel.org> said:
>>> On 29-06-26, 16:51, Geert Uytterhoeven wrote:
>>>>> Russell King asked me to put the PHY logic for SCMI pm domains into the PHY
>>>>> driver instead of the MAC driver where it was previously. Instead of cramming
>>>>> both HLOS and firmware handling into the same driver, I figured it makes more
>>>>> sense to have a dedicated, cleaner driver as the two share very little code (if
>>>>> any).
>>>>
>>>> I think you are mixing up DT bindings and driver implementation?
>>>
>>> Should the bindings change if we have different driver and firmware
>>> implementations? Isn't binding supposed to be agnostic of
>>> implementations..?
>>
>> I've thought about it some more and I believe this question is philosophical in
>> nature.
>>
>> sa8775p and sa8255p are *the same* hardware. I can flash different firmware on
>> the same Lemans Ride board and it becomes one or the other. Yet they are not
>> described by the same DTS and the bindings differ as well. I don't see why we
>> wouldn't allow the same approach for the this PHY.
>>
>> We treat it as different HW variant when it's managed by firmware - just like
>> we do with the rest of the SoC.
>
> DT describes hardware, not software policy.
DT describes hardware, to the extent that it's accessible by the OS
In this case, lemans-bare-metal and lemans-auto are essentially 2
separate platforms because the way we can interface with the hardware
is so vastly different
Konrad
^ permalink raw reply
* Re: [PATCH net-next 0/4] net: usb: move exported code to usbnet
From: Oliver Neukum @ 2026-07-03 10:16 UTC (permalink / raw)
To: Andrew Lunn, Oliver Neukum
Cc: andrew+netdev, davem, edumazet, kuba, pabeni, shaoxul, netdev,
linux-usb, linux-kernel
In-Reply-To: <ea92d680-39f6-4dde-b558-4008ffbee587@lunn.ch>
On 02.07.26 20:15, Andrew Lunn wrote:
> On Thu, Jul 02, 2026 at 04:25:29PM +0200, Oliver Neukum wrote:
>> Some drivers are reusing common code originating in other drivers.
>> This means that two drivers need to be loaded for one device.
>
> Maybe consider using 'framework' or 'library', rather than driver,
> when referring to the shared code?
>
> I tend to think of a driver as the leaf node which probes based on
> enumeration of a bus. But usbnet.c itself is never probed.
Yes, I also think of a leaf node when a "driver" is referred to.
That is the very point. Currently you need _two_ drivers and
usbnet for some devices.
Should I reformulate? If so, how exactly?
Regards
Oliver
^ permalink raw reply
* [PATCH v2 ethtool] man: ethtool: link 10000baseCR to SFF-8431, Appendix-E SFP+ DA
From: Siddaraju DH @ 2026-07-03 10:20 UTC (permalink / raw)
To: Michal Kubecek, Andrew Lunn, Maxime Chevallier, netdev
Cc: Shubham Das, Balaji Chintalapalle, Vijay Srinivasan,
Magnus Lindberg, Niklas Damberg, Jonas Wirandi, Siddaraju DH,
Siddaraju DH
Annotate the 10000baseCR entry in the advertise mask table so users
understand what physical media this mode it actually represents.
10000baseCR does not correspond to any IEEE 802.3 *base-CR PMD.
It has no autonegotiation, no link training, and no mandatory FEC.
The industry standard for this media type is SFF-8431 Appendix-E
Direct Attach cable, also known as 10G_SFI_DA.
Link: https://lore.kernel.org/r/SN7PR11MB69003D33489DB1D6B17EF72A9AF52@SN7PR11MB6900.namprd11.prod.outlook.com
Signed-off-by: Siddaraju DH <siddaraju.dh@intel.com>
---
ethtool.8.in | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/ethtool.8.in b/ethtool.8.in
index 3173287..604de9e 100644
--- a/ethtool.8.in
+++ b/ethtool.8.in
@@ -937,7 +937,7 @@ lB l lB.
0x40000 10000baseKX4 Full
0x80000 10000baseKR Full
0x100000 10000baseR_FEC
-0x40000000000 10000baseCR Full
+0x40000000000 10000baseCR Full (a.k.a 10G_SFI_DA, SFF-8431 Appendix-E)
0x80000000000 10000baseSR Full
0x100000000000 10000baseLR Full
0x200000000000 10000baseLRM Full
--
2.25.1
^ permalink raw reply related
* Re: [PATCH net-next v11 1/7] dt-bindings: phy: document the serdes PHY on sa8255p
From: Krzysztof Kozlowski @ 2026-07-03 10:20 UTC (permalink / raw)
To: Geert Uytterhoeven, Bartosz Golaszewski
Cc: Vinod Koul, Bjorn Andersson, Konrad Dybcio, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Andrew Lunn, David S. Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Maxime Coquelin,
Alexandre Torgue, Giuseppe Cavallaro, Chen-Yu Tsai,
Jernej Skrabec, Neil Armstrong, Kevin Hilman, Jerome Brunet,
Shawn Guo, Fabio Estevam, Jan Petrous, s32, Mohd Ayaan Anwar,
Romain Gantois, Magnus Damm, Maxime Ripard, Christophe Roullier,
Radu Rendec, linux-arm-msm, devicetree, linux-kernel, netdev,
linux-stm32, linux-arm-kernel, Drew Fustini, linux-sunxi,
linux-amlogic, linux-mips, imx, linux-renesas-soc, linux-rockchip,
sophgo, linux-riscv, Bartosz Golaszewski, Bartosz Golaszewski
In-Reply-To: <CAMuHMdXNG=C=XcioQUEN1M7cQgKhO0AxUyg5X+TWb2rQ3-H3fw@mail.gmail.com>
On 02/07/2026 11:16, Geert Uytterhoeven wrote:
> Hi Bartosz,
>
> On Thu, 2 Jul 2026 at 11:12, Bartosz Golaszewski <brgl@kernel.org> wrote:
>> On Tue, 30 Jun 2026 12:23:16 +0200, Vinod Koul <vkoul@kernel.org> said:
>>> On 29-06-26, 16:51, Geert Uytterhoeven wrote:
>>>>> Russell King asked me to put the PHY logic for SCMI pm domains into the PHY
>>>>> driver instead of the MAC driver where it was previously. Instead of cramming
>>>>> both HLOS and firmware handling into the same driver, I figured it makes more
>>>>> sense to have a dedicated, cleaner driver as the two share very little code (if
>>>>> any).
>>>>
>>>> I think you are mixing up DT bindings and driver implementation?
>>>
>>> Should the bindings change if we have different driver and firmware
>>> implementations? Isn't binding supposed to be agnostic of
>>> implementations..?
>>
>> I've thought about it some more and I believe this question is philosophical in
>> nature.
>>
>> sa8775p and sa8255p are *the same* hardware. I can flash different firmware on
>> the same Lemans Ride board and it becomes one or the other. Yet they are not
>> described by the same DTS and the bindings differ as well. I don't see why we
>> wouldn't allow the same approach for the this PHY.
>>
>> We treat it as different HW variant when it's managed by firmware - just like
>> we do with the rest of the SoC.
>
> DT describes hardware, not software policy.
So everything is fine here. Bartosz described the hardware how it is
available to the software (OS).
Best regards,
Krzysztof
^ permalink raw reply
* Re: [PATCH net-next v11 1/7] dt-bindings: phy: document the serdes PHY on sa8255p
From: Krzysztof Kozlowski @ 2026-07-03 10:21 UTC (permalink / raw)
To: Bartosz Golaszewski, Geert Uytterhoeven
Cc: Vinod Koul, Bjorn Andersson, Konrad Dybcio, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Andrew Lunn, David S. Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Maxime Coquelin,
Alexandre Torgue, Giuseppe Cavallaro, Chen-Yu Tsai,
Jernej Skrabec, Neil Armstrong, Kevin Hilman, Jerome Brunet,
Shawn Guo, Fabio Estevam, Jan Petrous, s32, Mohd Ayaan Anwar,
Romain Gantois, Magnus Damm, Maxime Ripard, Christophe Roullier,
Radu Rendec, linux-arm-msm, devicetree, linux-kernel, netdev,
linux-stm32, linux-arm-kernel, Drew Fustini, linux-sunxi,
linux-amlogic, linux-mips, imx, linux-renesas-soc, linux-rockchip,
sophgo, linux-riscv, Bartosz Golaszewski, Bartosz Golaszewski
In-Reply-To: <CAMRc=MfwB_51OLjX_19eagZ1m3UUM2iHny5rx6besR6+Np_A0g@mail.gmail.com>
On 02/07/2026 11:44, Bartosz Golaszewski wrote:
> On Thu, 2 Jul 2026 11:16:22 +0200, Geert Uytterhoeven
> <geert@linux-m68k.org> said:
>> Hi Bartosz,
>>
>> On Thu, 2 Jul 2026 at 11:12, Bartosz Golaszewski <brgl@kernel.org> wrote:
>>> On Tue, 30 Jun 2026 12:23:16 +0200, Vinod Koul <vkoul@kernel.org> said:
>>>> On 29-06-26, 16:51, Geert Uytterhoeven wrote:
>>>>>> Russell King asked me to put the PHY logic for SCMI pm domains into the PHY
>>>>>> driver instead of the MAC driver where it was previously. Instead of cramming
>>>>>> both HLOS and firmware handling into the same driver, I figured it makes more
>>>>>> sense to have a dedicated, cleaner driver as the two share very little code (if
>>>>>> any).
>>>>>
>>>>> I think you are mixing up DT bindings and driver implementation?
>>>>
>>>> Should the bindings change if we have different driver and firmware
>>>> implementations? Isn't binding supposed to be agnostic of
>>>> implementations..?
>>>
>>> I've thought about it some more and I believe this question is philosophical in
>>> nature.
>>>
>>> sa8775p and sa8255p are *the same* hardware. I can flash different firmware on
>>> the same Lemans Ride board and it becomes one or the other. Yet they are not
>>> described by the same DTS and the bindings differ as well. I don't see why we
>>> wouldn't allow the same approach for the this PHY.
>>>
>>> We treat it as different HW variant when it's managed by firmware - just like
>>> we do with the rest of the SoC.
>>
>> DT describes hardware, not software policy.
>>
>
> I'll defer to DT maintainers then for that particular case because it affects
I provided the review tag. It is still valid, also after reading the
discussions here.
Best regards,
Krzysztof
^ permalink raw reply
* [PATCH iwl] ice: acquire NVM lock around each flash read
From: Robert Malz @ 2026-07-03 10:32 UTC (permalink / raw)
To: Tony Nguyen, Przemek Kitszel, Andrew Lunn, David S. Miller,
Eric Dumazet, Jakub Kicinski, Paolo Abeni, Alexander Lobakin,
Jacob Keller, Jesse Brandeburg
Cc: Robert Malz, intel-wired-lan, netdev, linux-kernel
FW caps the NVM read lock at a maximum of 3000ms regardless of the timeout
requested via ice_acquire_nvm(). ice_read_flat_nvm() splits a read into
multiple ice_aq_read_nvm() commands, one per 4KB sector, all issued under a
single lock taken by the caller. Reading a large region can exceed 3000ms,
so FW reclaims the lock mid-read and the remaining commands might fail.
Move the lock acquire/release into ice_read_flat_nvm() so it brackets each
individual ice_aq_read_nvm() command, ensuring the lock is never held
across more than one FW read. ice_release_nvm() issues its own AQ command
and would overwrite sq_last_status, so the read's AQ error is preserved
across the release for callers such as ice_discover_flash_size() that
inspect it.
Callers that previously took the lock around ice_read_flat_nvm(),
ice_read_sr_word() or ice_read_flash_module() now call them without it.
The per-block locking in ice_devlink_nvm_snapshot() is now redundant
and dropped.
Fixes: e94509906d6b ("ice: create function to read a section of the NVM and Shadow RAM")
Signed-off-by: Robert Malz <robert.malz@canonical.com>
---
.../net/ethernet/intel/ice/devlink/devlink.c | 21 -------
drivers/net/ethernet/intel/ice/ice_ethtool.c | 11 +---
drivers/net/ethernet/intel/ice/ice_nvm.c | 58 ++++++++++---------
3 files changed, 32 insertions(+), 58 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index 22b7d8e6bd9e..7c7fe3d2e9d9 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -1891,26 +1891,15 @@ static int ice_devlink_nvm_snapshot(struct devlink *devlink,
for (i = 0; i < num_blks; i++) {
u32 read_sz = min_t(u32, ICE_DEVLINK_READ_BLK_SIZE, left);
- status = ice_acquire_nvm(hw, ICE_RES_READ);
- if (status) {
- dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n",
- status, hw->adminq.sq_last_status);
- NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore");
- vfree(nvm_data);
- return -EIO;
- }
-
status = ice_read_flat_nvm(hw, i * ICE_DEVLINK_READ_BLK_SIZE,
&read_sz, tmp, read_shadow_ram);
if (status) {
dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n",
read_sz, status, hw->adminq.sq_last_status);
NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents");
- ice_release_nvm(hw);
vfree(nvm_data);
return -EIO;
}
- ice_release_nvm(hw);
tmp += read_sz;
left -= read_sz;
@@ -1966,24 +1955,14 @@ static int ice_devlink_nvm_read(struct devlink *devlink,
return -ERANGE;
}
- status = ice_acquire_nvm(hw, ICE_RES_READ);
- if (status) {
- dev_dbg(dev, "ice_acquire_nvm failed, err %d aq_err %d\n",
- status, hw->adminq.sq_last_status);
- NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore");
- return -EIO;
- }
-
status = ice_read_flat_nvm(hw, (u32)offset, &size, data,
read_shadow_ram);
if (status) {
dev_dbg(dev, "ice_read_flat_nvm failed after reading %u bytes, err %d aq_err %d\n",
size, status, hw->adminq.sq_last_status);
NL_SET_ERR_MSG_MOD(extack, "Failed to read NVM contents");
- ice_release_nvm(hw);
return -EIO;
}
- ice_release_nvm(hw);
return 0;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 49371b065845..ddeca39d822b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -869,24 +869,15 @@ ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
if (!buf)
return -ENOMEM;
- ret = ice_acquire_nvm(hw, ICE_RES_READ);
- if (ret) {
- dev_err(dev, "ice_acquire_nvm failed, err %d aq_err %s\n",
- ret, libie_aq_str(hw->adminq.sq_last_status));
- goto out;
- }
-
ret = ice_read_flat_nvm(hw, eeprom->offset, &eeprom->len, buf,
false);
if (ret) {
dev_err(dev, "ice_read_flat_nvm failed, err %d aq_err %s\n",
ret, libie_aq_str(hw->adminq.sq_last_status));
- goto release;
+ goto out;
}
memcpy(bytes, buf, eeprom->len);
-release:
- ice_release_nvm(hw);
out:
kfree(buf);
return ret;
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 7e187a804dfa..cb1541844242 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -58,6 +58,11 @@ int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
* breaks read requests across Shadow RAM sectors and ensures that no single
* read request exceeds the maximum 4KB read for a single AdminQ command.
*
+ * FW caps the read lock at a maximum of 3000ms, so a read spanning multiple
+ * 4KB sectors cannot be done under a single lock without FW reclaiming it
+ * mid-read. The NVM lock is therefore acquired and released around each AQ
+ * read, so this function must be called without the lock held.
+ *
* Returns a status code on failure. Note that the data pointer may be
* partially updated if some reads succeed before a failure.
*/
@@ -65,6 +70,7 @@ int
ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data,
bool read_shadow_ram)
{
+ enum libie_aq_err aq_err;
u32 inlen = *length;
u32 bytes_read = 0;
bool last_cmd;
@@ -92,12 +98,28 @@ ice_read_flat_nvm(struct ice_hw *hw, u32 offset, u32 *length, u8 *data,
last_cmd = !(bytes_read + read_size < inlen);
+ status = ice_acquire_nvm(hw, ICE_RES_READ);
+ if (status)
+ break;
+
status = ice_aq_read_nvm(hw, ICE_AQC_NVM_START_POINT,
offset, read_size,
data + bytes_read, last_cmd,
read_shadow_ram, NULL);
- if (status)
+ if (status) {
+ /* ice_release_nvm() issues an AQ command that would
+ * overwrite sq_last_status, which some callers
+ * inspect after a failed read. Preserve the read's
+ * AQ error across the release.
+ */
+ aq_err = hw->adminq.sq_last_status;
+
+ ice_release_nvm(hw);
+ hw->adminq.sq_last_status = aq_err;
break;
+ }
+
+ ice_release_nvm(hw);
bytes_read += read_size;
offset += read_size;
@@ -330,14 +352,8 @@ ice_read_flash_module(struct ice_hw *hw, enum ice_bank_select bank, u16 module,
return -EINVAL;
}
- status = ice_acquire_nvm(hw, ICE_RES_READ);
- if (status)
- return status;
-
status = ice_read_flat_nvm(hw, start + offset, &length, data, false);
- ice_release_nvm(hw);
-
return status;
}
@@ -419,24 +435,19 @@ ice_read_netlist_module(struct ice_hw *hw, enum ice_bank_select bank, u32 offset
}
/**
- * ice_read_sr_word - Reads Shadow RAM word and acquire NVM if necessary
+ * ice_read_sr_word - Reads Shadow RAM word
* @hw: pointer to the HW structure
* @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
* @data: word read from the Shadow RAM
*
- * Reads one 16 bit word from the Shadow RAM using the ice_read_sr_word_aq.
+ * Reads one 16 bit word from the Shadow RAM using ice_read_sr_word_aq.
+ *
+ * The NVM lock is acquired and released internally by ice_read_flat_nvm()
+ * around the FW read, so this function must be called without the lock held.
*/
int ice_read_sr_word(struct ice_hw *hw, u16 offset, u16 *data)
{
- int status;
-
- status = ice_acquire_nvm(hw, ICE_RES_READ);
- if (!status) {
- status = ice_read_sr_word_aq(hw, offset, data);
- ice_release_nvm(hw);
- }
-
- return status;
+ return ice_read_sr_word_aq(hw, offset, data);
}
/**
@@ -856,11 +867,7 @@ int ice_get_inactive_netlist_ver(struct ice_hw *hw, struct ice_netlist_info *net
static int ice_discover_flash_size(struct ice_hw *hw)
{
u32 min_size = 0, max_size = ICE_AQC_NVM_MAX_OFFSET + 1;
- int status;
-
- status = ice_acquire_nvm(hw, ICE_RES_READ);
- if (status)
- return status;
+ int status = 0;
while ((max_size - min_size) > 1) {
u32 offset = (max_size + min_size) / 2;
@@ -880,7 +887,7 @@ static int ice_discover_flash_size(struct ice_hw *hw)
min_size = offset;
} else {
/* an unexpected error occurred */
- goto err_read_flat_nvm;
+ return status;
}
}
@@ -888,9 +895,6 @@ static int ice_discover_flash_size(struct ice_hw *hw)
hw->flash.flash_size = max_size;
-err_read_flat_nvm:
- ice_release_nvm(hw);
-
return status;
}
--
2.34.1
^ permalink raw reply related
* Re: [REGRESSION][BISECTED] tun/tap & vhost-net: multi-threaded network performance
From: Simon Schippers @ 2026-07-03 10:34 UTC (permalink / raw)
To: Michael S. Tsirkin, Brett Sheffield
Cc: regressions, netdev, Jakub Kicinski, Tim Gebauer,
Willem de Bruijn, Jason Wang, Andrew Lunn, David S. Miller,
Eric Dumazet, Paolo Abeni, linux-kernel
In-Reply-To: <20260702183435-mutt-send-email-mst@kernel.org>
On 7/3/26 00:44, Michael S. Tsirkin wrote:
> Well, the issue was with host to guest right?
> Then testing what does bql do might be interesting.
> Might help.
> Something like this? Lightly tested.
Your approach calls netdev_tx_completed_queue() per individual packet
which is wrong and will cause a constant BQL limit of 2 as we have seen
in [1], causing a regression *100%*.
Citing the documentation of netdev_tx_completed_queue() in netdevice.h:
* Must be called at most once per TX completion round (and not per
* individual packet), so that BQL can adjust its limits appropriately.
[1] Link: https://lore.kernel.org/all/e8cdba04-aa9a-45c6-9807-8274b62920df@tu-dortmund.de/
>
>
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index bfa49fa9e3a1..abc46354c107 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -1076,6 +1076,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
> queue = netdev_get_tx_queue(dev, txq);
>
> spin_lock(&tfile->tx_ring.producer_lock);
> + netdev_tx_sent_queue(queue, len);
> ret = __ptr_ring_produce(&tfile->tx_ring, skb);
> if (!qdisc_txq_has_no_queue(queue) &&
> __ptr_ring_check_produce(&tfile->tx_ring) == -ENOSPC) {
> @@ -1088,6 +1089,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
> spin_unlock(&tfile->tx_ring.producer_lock);
>
> if (ret) {
> + netdev_tx_completed_queue(queue, 1, len);
> /* This should be a rare case if a qdisc is present, but
> * can happen due to lltx.
> * Since skb_tx_timestamp(), skb_orphan(),
> @@ -2148,15 +2150,19 @@ static ssize_t tun_put_user(struct tun_struct *tun,
>
> /* Callers must hold ring.consumer_lock */
> static void __tun_wake_queue(struct tun_struct *tun,
> - struct tun_file *tfile, int consumed)
> + struct tun_file *tfile,
> + unsigned int pkts, unsigned int bytes)
> {
> struct netdev_queue *txq = netdev_get_tx_queue(tun->dev,
> tfile->queue_index);
>
> + if (bytes)
> + netdev_tx_completed_queue(txq, pkts, bytes);
> +
Right here.
> /* Paired with smp_mb__after_atomic() in tun_net_xmit() */
> smp_mb();
> if (netif_tx_queue_stopped(txq)) {
> - tfile->cons_cnt += consumed;
> + tfile->cons_cnt += pkts;
> if (tfile->cons_cnt >= tfile->tx_ring.size / 2 ||
> __ptr_ring_empty(&tfile->tx_ring)) {
> netif_tx_wake_queue(txq);
> @@ -2167,12 +2173,16 @@ static void __tun_wake_queue(struct tun_struct *tun,
>
> static void *tun_ring_consume(struct tun_struct *tun, struct tun_file *tfile)
> {
> + unsigned int bytes = 0;
> void *ptr;
>
> spin_lock(&tfile->tx_ring.consumer_lock);
> ptr = __ptr_ring_consume(&tfile->tx_ring);
> - if (ptr)
> - __tun_wake_queue(tun, tfile, 1);
> + if (ptr) {
> + if (!tun_is_xdp_frame(ptr))
> + bytes = ((struct sk_buff *)ptr)->len;
> + __tun_wake_queue(tun, tfile, 1, bytes);
> + }
>
> spin_unlock(&tfile->tx_ring.consumer_lock);
> return ptr;
> @@ -3805,7 +3815,7 @@ struct ptr_ring *tun_get_tx_ring(struct file *file)
> EXPORT_SYMBOL_GPL(tun_get_tx_ring);
>
> /* Callers must hold ring.consumer_lock */
> -void tun_wake_queue(struct file *file, int consumed)
> +void tun_wake_queue(struct file *file, unsigned int pkts, unsigned int bytes)
> {
> struct tun_file *tfile;
> struct tun_struct *tun;
> @@ -3821,7 +3831,7 @@ void tun_wake_queue(struct file *file, int consumed)
>
> tun = rcu_dereference(tfile->tun);
> if (tun)
> - __tun_wake_queue(tun, tfile, consumed);
> + __tun_wake_queue(tun, tfile, pkts, bytes);
>
> rcu_read_unlock();
> }
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index db341c922673..5267b323bd59 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -181,14 +181,23 @@ static int vhost_net_buf_produce(struct sock *sk,
> {
> struct file *file = sk->sk_socket->file;
> struct vhost_net_buf *rxq = &nvq->rxq;
> + unsigned int bytes = 0;
> + int i;
>
> rxq->head = 0;
> spin_lock(&nvq->rx_ring->consumer_lock);
> rxq->tail = __ptr_ring_consume_batched(nvq->rx_ring, rxq->queue,
> VHOST_NET_BATCH);
>
> - if (rxq->tail)
> - tun_wake_queue(file, rxq->tail);
> + if (rxq->tail) {
> + for (i = 0; i < rxq->tail; i++) {
> + void *ptr = rxq->queue[i];
> +
> + if (!tun_is_xdp_frame(ptr))
> + bytes += ((struct sk_buff *)ptr)->len;
> + }
> + tun_wake_queue(file, rxq->tail, bytes);
> + }
>
> spin_unlock(&nvq->rx_ring->consumer_lock);
> return rxq->tail;
> diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
> index 5f3e206c7a73..49b85bf4f828 100644
> --- a/include/linux/if_tun.h
> +++ b/include/linux/if_tun.h
> @@ -22,7 +22,7 @@ struct tun_msg_ctl {
> #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE)
> struct socket *tun_get_socket(struct file *);
> struct ptr_ring *tun_get_tx_ring(struct file *file);
> -void tun_wake_queue(struct file *file, int consumed);
> +void tun_wake_queue(struct file *file, unsigned int pkts, unsigned int bytes);
>
> static inline bool tun_is_xdp_frame(void *ptr)
> {
> @@ -56,7 +56,8 @@ static inline struct ptr_ring *tun_get_tx_ring(struct file *f)
> return ERR_PTR(-EINVAL);
> }
>
> -static inline void tun_wake_queue(struct file *f, int consumed) {}
> +static inline void tun_wake_queue(struct file *f,
> + unsigned int pkts, unsigned int bytes) {}
>
> static inline bool tun_is_xdp_frame(void *ptr)
> {
>
^ permalink raw reply
* Re: [REGRESSION][BISECTED] tun/tap & vhost-net: multi-threaded network performance
From: Simon Schippers @ 2026-07-03 10:35 UTC (permalink / raw)
To: Michael S. Tsirkin, Brett Sheffield
Cc: regressions, netdev, Jakub Kicinski, Tim Gebauer,
Willem de Bruijn, Jason Wang, Andrew Lunn, David S. Miller,
Eric Dumazet, Paolo Abeni, linux-kernel
In-Reply-To: <20260702185420-mutt-send-email-mst@kernel.org>
On 7/3/26 00:55, Michael S. Tsirkin wrote:
> Maybe it's the supposedly rare case? Does this change anything
> for you?
In the "rare case" we would have packet drops, visible by iperf3 TCP
retransmissions. But these packet drops don't occur as I stated before.
Also, we are still not allowed to return NETDEV_TX_BUSY here, because
run_ebpf_filter() and pskb_trim() could have tinkered with the SKB.
>
>
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index bfa49fa9e3a1..bacd89460078 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -1018,7 +1018,6 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
> struct netdev_queue *queue;
> struct tun_file *tfile;
> int len = skb->len;
> - int ret;
>
> rcu_read_lock();
> tfile = rcu_dereference(tun->tfiles[txq]);
> @@ -1064,19 +1063,24 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
> goto drop;
> }
>
> - skb_tx_timestamp(skb);
> -
> - /* Orphan the skb - required as we might hang on to it
> - * for indefinite time.
> - */
> - skb_orphan(skb);
> -
> - nf_reset_ct(skb);
> -
> queue = netdev_get_tx_queue(dev, txq);
>
> spin_lock(&tfile->tx_ring.producer_lock);
> - ret = __ptr_ring_produce(&tfile->tx_ring, skb);
> + if (__ptr_ring_check_produce(&tfile->tx_ring)) {
> + spin_unlock(&tfile->tx_ring.producer_lock);
> + netif_tx_stop_queue(queue);
> + smp_mb__after_atomic();
> + if (!__ptr_ring_check_produce(&tfile->tx_ring))
> + netif_tx_wake_queue(queue);
> + rcu_read_unlock();
> + return NETDEV_TX_BUSY;
> + }
> +
> + skb_tx_timestamp(skb);
> + skb_orphan(skb);
> + nf_reset_ct(skb);
> +
> + __ptr_ring_produce(&tfile->tx_ring, skb);
> if (!qdisc_txq_has_no_queue(queue) &&
> __ptr_ring_check_produce(&tfile->tx_ring) == -ENOSPC) {
> netif_tx_stop_queue(queue);
> @@ -1087,18 +1091,6 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
> }
> spin_unlock(&tfile->tx_ring.producer_lock);
>
> - if (ret) {
> - /* This should be a rare case if a qdisc is present, but
> - * can happen due to lltx.
> - * Since skb_tx_timestamp(), skb_orphan(),
> - * run_ebpf_filter() and pskb_trim() could have tinkered
> - * with the SKB, returning NETDEV_TX_BUSY is unsafe and
> - * we must drop instead.
> - */
> - drop_reason = SKB_DROP_REASON_FULL_RING;
> - goto drop;
> - }
> -
> /* dev->lltx requires to do our own update of trans_start */
> txq_trans_cond_update(queue);
>
>
^ permalink raw reply
* [PATCH v3 net-next 00/14] net: enetc: cleanups and improvements
From: wei.fang @ 2026-07-03 10:13 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
From: Wei Fang <wei.fang@nxp.com>
The first group of patches (1, 2, 5-7) eliminates code duplication
between the ENETC v1 and v4 drivers. Since both hardware generations
share identical register layouts for MAC promiscuous mode, MAC hash
filters, and VLAN promiscuous mode - differing only in register address
offsets - common helper functions are extracted into enetc_pf_common.c
and shared by both drivers.
Patch 3 converts ndo_set_rx_mode() to ndo_set_rx_mode_async(), removing
the dedicated workqueue that was previously needed to defer MAC address
list updates to a sleepable context.
Patch 4 replaces counter-based MAFT entry tracking with a bitmap, which
keeps hardware and software state in sync and avoids partial failures
during entry allocation.
Patches 8 and 9 fix phylink-related issues: removing invalid code from
enetc4_pl_mac_link_up() and properly differentiating phylink capabilities
between pseudo-MAC and standalone MAC.
The remaining patches (10-14) are minor cleanups: removing a redundant
VLAN promiscuous mode initialization in probe, using the PCI device name
for the debugfs directory, simplifying port speed configuration, removing
a redundant num_vsi field, using alloc_etherdev_mqs() for the VF driver,
and using kzalloc_flex() for a flexible array allocation.
---
v3:
1. Add a check to speed in enetc4_set_port_speed()
2. Remove PHY_INTERFACE_MODE_XGMII from the driver
3. Restore the VLAN promiscuous mode setting for all SIs in probe phase
4. Remove half_duplex field from struct enetc_port_caps
5. Limit the maximum value of txqs/rxqs of alloc_etherdev_mqs() to
ENETC_MAX_NUM_TXQS
6. Update the commit messages
7. Collect tags
v2 link: https://lore.kernel.org/imx/20260702025714.456233-1-wei.fang@oss.nxp.com/
v1 link: https://lore.kernel.org/imx/20260630072036.382761-1-wei.fang@oss.nxp.com/
---
Claudiu Manoil (1):
net: enetc: differentiate phylink capabilities for pseudo-MAC and
standalone MAC
Wei Fang (13):
net: enetc: extract common helpers for MAC promiscuous mode setting
net: enetc: extract common helpers for MAC hash filter configuration
net: enetc: convert ndo_set_rx_mode() to ndo_set_rx_mode_async()
net: enetc: improve MAFT entry management with bitmap tracking
net: enetc: use PCI device name for debugfs directory
net: enetc: simplify enetc4_set_port_speed()
net: enetc: remove invalid code from enetc4_pl_mac_link_up()
net: enetc: open-code enetc4_set_default_si_vlan_promisc()
net: enetc: refactor SI VLAN promiscuous mode configuration
net: enetc: move enetc_set_si_vlan_promisc() to enetc_pf_common.c
net: enetc: remove redundant num_vsi field from enetc_port_caps
net: enetc: use alloc_etherdev_mqs() to create netdev for VF driver
net: enetc: use kzalloc_flex() for enetc_psfp_gate allocation
drivers/net/ethernet/freescale/enetc/enetc.h | 4 +-
.../ethernet/freescale/enetc/enetc4_debugfs.c | 42 +-
.../net/ethernet/freescale/enetc/enetc4_hw.h | 7 +-
.../net/ethernet/freescale/enetc/enetc4_pf.c | 424 +++++++-----------
.../ethernet/freescale/enetc/enetc_ethtool.c | 2 +-
.../net/ethernet/freescale/enetc/enetc_hw.h | 12 +-
.../net/ethernet/freescale/enetc/enetc_pf.c | 94 +---
.../net/ethernet/freescale/enetc/enetc_pf.h | 6 -
.../freescale/enetc/enetc_pf_common.c | 150 ++++++-
.../freescale/enetc/enetc_pf_common.h | 5 +
.../net/ethernet/freescale/enetc/enetc_qos.c | 4 +-
.../net/ethernet/freescale/enetc/enetc_vf.c | 9 +-
include/linux/fsl/ntmp.h | 2 +
13 files changed, 367 insertions(+), 394 deletions(-)
--
2.34.1
^ permalink raw reply
* [PATCH v3 net-next 01/14] net: enetc: extract common helpers for MAC promiscuous mode setting
From: wei.fang @ 2026-07-03 10:13 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260703101328.550714-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
The PSIPMMR (Port Station Interface Promiscuous MAC Mode Register) in
ENETC v4 has the same bit layout as the PSIPMR register in ENETC v1: bit
n controls unicast promiscuous mode for SI n, and bit (n + 16) controls
multicast promiscuous mode for SI n. The only difference between the two
hardware generations is the register address offset.
Since the register functionality is identical, the MAC promiscuous mode
setting code can be shared between ENETC v1 and v4 drivers.
Rename ENETC_PSIPMR to ENETC_PSIPMMR in enetc_hw.h to match the actual
register name used in the reference manual, and extract two new common
helper functions, enetc_set_si_uc_promisc() and
enetc_set_si_mc_promisc(), into enetc_pf_common.c. These helpers select
the correct register offset based on the hardware revision via
is_enetc_rev1().
Remove the v4-specific enetc4_pf_set_si_mac_promisc() function from
enetc4_pf.c and the duplicate PSIPMMR_SI_MAC_UP/MP macro definitions
from enetc4_hw.h, as they are now superseded by the shared code.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
.../net/ethernet/freescale/enetc/enetc4_hw.h | 2 -
.../net/ethernet/freescale/enetc/enetc4_pf.c | 21 +--------
.../ethernet/freescale/enetc/enetc_ethtool.c | 2 +-
.../net/ethernet/freescale/enetc/enetc_hw.h | 7 +--
.../net/ethernet/freescale/enetc/enetc_pf.c | 11 ++---
.../freescale/enetc/enetc_pf_common.c | 44 +++++++++++++++++++
.../freescale/enetc/enetc_pf_common.h | 2 +
7 files changed, 56 insertions(+), 33 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
index f18437556a0e..6a8f2ed56017 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h
@@ -69,8 +69,6 @@
/* Port Station interface promiscuous MAC mode register */
#define ENETC4_PSIPMMR 0x200
-#define PSIPMMR_SI_MAC_UP(a) BIT(a) /* a = SI index */
-#define PSIPMMR_SI_MAC_MP(a) BIT((a) + 16)
/* Port Station interface promiscuous VLAN mode register */
#define ENETC4_PSIPVMR 0x204
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 437a15bbb47b..304ec069654d 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -75,24 +75,6 @@ static void enetc4_pf_get_si_primary_mac(struct enetc_hw *hw, int si,
put_unaligned_le16(lower, addr + 4);
}
-static void enetc4_pf_set_si_mac_promisc(struct enetc_hw *hw, int si,
- bool uc_promisc, bool mc_promisc)
-{
- u32 val = enetc_port_rd(hw, ENETC4_PSIPMMR);
-
- if (uc_promisc)
- val |= PSIPMMR_SI_MAC_UP(si);
- else
- val &= ~PSIPMMR_SI_MAC_UP(si);
-
- if (mc_promisc)
- val |= PSIPMMR_SI_MAC_MP(si);
- else
- val &= ~PSIPMMR_SI_MAC_MP(si);
-
- enetc_port_wr(hw, ENETC4_PSIPMMR, val);
-}
-
static void enetc4_pf_set_si_uc_hash_filter(struct enetc_hw *hw, int si,
u64 hash)
{
@@ -515,7 +497,8 @@ static void enetc4_psi_do_set_rx_mode(struct work_struct *work)
type = ENETC_MAC_FILTER_TYPE_ALL;
}
- enetc4_pf_set_si_mac_promisc(hw, 0, uc_promisc, mc_promisc);
+ enetc_set_si_uc_promisc(si, 0, uc_promisc);
+ enetc_set_si_mc_promisc(si, 0, mc_promisc);
if (uc_promisc) {
enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index 71f376ef1be1..07b7832f2427 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -29,7 +29,7 @@ static const u32 enetc_rxbdr_regs[] = {
};
static const u32 enetc_port_regs[] = {
- ENETC_PMR, ENETC_PSR, ENETC_PSIPMR, ENETC_PSIPMAR0(0),
+ ENETC_PMR, ENETC_PSR, ENETC_PSIPMMR, ENETC_PSIPMAR0(0),
ENETC_PSIPMAR1(0), ENETC_PTXMBAR, ENETC_PCAPR0, ENETC_PCAPR1,
ENETC_PSICFGR0(0), ENETC_PRFSCAPR, ENETC_PTCMSDUR(0),
ENETC_PM0_CMD_CFG, ENETC_PM0_MAXFRM, ENETC_PM0_IF_MODE
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index bf99b65d7598..66bfda60da9c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -180,9 +180,10 @@ enum enetc_bdr_type {TX, RX};
#define ENETC_PMR_PSPEED_1000M BIT(9)
#define ENETC_PMR_PSPEED_2500M BIT(10)
#define ENETC_PSR 0x0004 /* RO */
-#define ENETC_PSIPMR 0x0018
-#define ENETC_PSIPMR_SET_UP(n) BIT(n) /* n = SI index */
-#define ENETC_PSIPMR_SET_MP(n) BIT((n) + 16)
+#define ENETC_PSIPMMR 0x0018
+#define PSIPMMR_SI_MAC_UP(n) BIT(n) /* n = SI index */
+#define PSIPMMR_SI_MAC_MP(n) BIT((n) + 16)
+
#define ENETC_PSIPVMR 0x001c
#define ENETC_VLAN_PROMISC_MAP_ALL 0x7
#define ENETC_PSIPVMR_SET_VP(simap) ((simap) & 0x7)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 2d687bb8c3a0..a97d2e2dd07b 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -159,21 +159,17 @@ static void enetc_pf_set_rx_mode(struct net_device *ndev)
{
struct enetc_ndev_priv *priv = netdev_priv(ndev);
struct enetc_pf *pf = enetc_si_priv(priv->si);
- struct enetc_hw *hw = &priv->si->hw;
bool uprom = false, mprom = false;
struct enetc_mac_filter *filter;
struct netdev_hw_addr *ha;
- u32 psipmr = 0;
bool em;
if (ndev->flags & IFF_PROMISC) {
/* enable promisc mode for SI0 (PF) */
- psipmr = ENETC_PSIPMR_SET_UP(0) | ENETC_PSIPMR_SET_MP(0);
uprom = true;
mprom = true;
} else if (ndev->flags & IFF_ALLMULTI) {
/* enable multi cast promisc mode for SI0 (PF) */
- psipmr = ENETC_PSIPMR_SET_MP(0);
mprom = true;
}
@@ -211,9 +207,8 @@ static void enetc_pf_set_rx_mode(struct net_device *ndev)
/* update PF entries */
enetc_sync_mac_filters(pf);
- psipmr |= enetc_port_rd(hw, ENETC_PSIPMR) &
- ~(ENETC_PSIPMR_SET_UP(0) | ENETC_PSIPMR_SET_MP(0));
- enetc_port_wr(hw, ENETC_PSIPMR, psipmr);
+ enetc_set_si_uc_promisc(priv->si, 0, uprom);
+ enetc_set_si_mc_promisc(priv->si, 0, mprom);
}
static void enetc_set_loopback(struct net_device *ndev, bool en)
@@ -474,7 +469,7 @@ static void enetc_configure_port(struct enetc_pf *pf)
pf->vlan_promisc_simap = ENETC_VLAN_PROMISC_MAP_ALL;
enetc_set_vlan_promisc(hw, pf->vlan_promisc_simap);
- enetc_port_wr(hw, ENETC_PSIPMR, 0);
+ enetc_port_wr(hw, ENETC_PSIPMMR, 0);
/* enable port */
enetc_port_wr(hw, ENETC_PMR, ENETC_PMR_EN);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index 6e5d2f869915..b0c0dc668e34 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -87,6 +87,50 @@ int enetc_setup_mac_addresses(struct device_node *np, struct enetc_pf *pf)
}
EXPORT_SYMBOL_GPL(enetc_setup_mac_addresses);
+void enetc_set_si_uc_promisc(struct enetc_si *si, int si_id, bool promisc)
+{
+ struct enetc_hw *hw = &si->hw;
+ int psipmmr_off;
+ u32 val;
+
+ if (is_enetc_rev1(si))
+ psipmmr_off = ENETC_PSIPMMR;
+ else
+ psipmmr_off = ENETC4_PSIPMMR;
+
+ val = enetc_port_rd(hw, psipmmr_off);
+
+ if (promisc)
+ val |= PSIPMMR_SI_MAC_UP(si_id);
+ else
+ val &= ~PSIPMMR_SI_MAC_UP(si_id);
+
+ enetc_port_wr(hw, psipmmr_off, val);
+}
+EXPORT_SYMBOL_GPL(enetc_set_si_uc_promisc);
+
+void enetc_set_si_mc_promisc(struct enetc_si *si, int si_id, bool promisc)
+{
+ struct enetc_hw *hw = &si->hw;
+ int psipmmr_off;
+ u32 val;
+
+ if (is_enetc_rev1(si))
+ psipmmr_off = ENETC_PSIPMMR;
+ else
+ psipmmr_off = ENETC4_PSIPMMR;
+
+ val = enetc_port_rd(hw, psipmmr_off);
+
+ if (promisc)
+ val |= PSIPMMR_SI_MAC_MP(si_id);
+ else
+ val &= ~PSIPMMR_SI_MAC_MP(si_id);
+
+ enetc_port_wr(hw, psipmmr_off, val);
+}
+EXPORT_SYMBOL_GPL(enetc_set_si_mc_promisc);
+
void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
const struct net_device_ops *ndev_ops)
{
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
index 57d2e0ebd2b0..a619fb8fed9c 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
@@ -17,6 +17,8 @@ void enetc_set_default_rss_key(struct enetc_pf *pf);
int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid);
int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid);
int enetc_init_sriov_resources(struct enetc_pf *pf);
+void enetc_set_si_uc_promisc(struct enetc_si *si, int si_id, bool promisc);
+void enetc_set_si_mc_promisc(struct enetc_si *si, int si_id, bool promisc);
static inline u16 enetc_get_ip_revision(struct enetc_hw *hw)
{
--
2.34.1
^ permalink raw reply related
* [PATCH v3 net-next 02/14] net: enetc: extract common helpers for MAC hash filter configuration
From: wei.fang @ 2026-07-03 10:13 UTC (permalink / raw)
To: claudiu.manoil, vladimir.oltean, xiaoning.wang, andrew+netdev,
davem, edumazet, kuba, pabeni, linux, wei.fang, chleroy,
maxime.chevallier
Cc: imx, netdev, linux-kernel, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20260703101328.550714-1-wei.fang@oss.nxp.com>
From: Wei Fang <wei.fang@nxp.com>
The PSIUMHFR and PSIMMHFR registers in ENETC v4 have the same bit layout
as in ENETC v1. The only difference between the two hardware generations
is the register address offsets.
Since the register functionality is identical, the MAC hash filter
configuration code can be shared between the ENETC v1 and v4 drivers.
Extract two new common helper functions, enetc_set_si_uc_hash_filter()
and enetc_set_si_mc_hash_filter(), into enetc_pf_common.c. These helpers
select the correct register offset based on the hardware revision via
is_enetc_rev1().
Remove v1-specific enetc_clear_mac_ht_flt() and enetc_set_mac_ht_flt()
from enetc_pf.c, and v4-specific enetc4_pf_set_si_uc_hash_filter() and
enetc4_pf_set_si_mc_hash_filter() from enetc4_pf.c, as they are now
superseded by the shared implementations.
Signed-off-by: Wei Fang <wei.fang@nxp.com>
---
.../net/ethernet/freescale/enetc/enetc4_pf.c | 43 +++++++---------
.../net/ethernet/freescale/enetc/enetc_pf.c | 51 +++++--------------
.../freescale/enetc/enetc_pf_common.c | 40 +++++++++++++++
.../freescale/enetc/enetc_pf_common.h | 2 +
4 files changed, 73 insertions(+), 63 deletions(-)
diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 304ec069654d..48a74db90ed5 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -75,20 +75,6 @@ static void enetc4_pf_get_si_primary_mac(struct enetc_hw *hw, int si,
put_unaligned_le16(lower, addr + 4);
}
-static void enetc4_pf_set_si_uc_hash_filter(struct enetc_hw *hw, int si,
- u64 hash)
-{
- enetc_port_wr(hw, ENETC4_PSIUMHFR0(si), lower_32_bits(hash));
- enetc_port_wr(hw, ENETC4_PSIUMHFR1(si), upper_32_bits(hash));
-}
-
-static void enetc4_pf_set_si_mc_hash_filter(struct enetc_hw *hw, int si,
- u64 hash)
-{
- enetc_port_wr(hw, ENETC4_PSIMMHFR0(si), lower_32_bits(hash));
- enetc_port_wr(hw, ENETC4_PSIMMHFR1(si), upper_32_bits(hash));
-}
-
static void enetc4_pf_set_loopback(struct net_device *ndev, bool en)
{
struct enetc_ndev_priv *priv = netdev_priv(ndev);
@@ -147,11 +133,12 @@ static int enetc4_pf_set_uc_exact_filter(struct enetc_pf *pf)
int max_num_mfe = pf->caps.mac_filter_num;
struct enetc_mac_filter mac_filter = {};
struct net_device *ndev = pf->si->ndev;
- struct enetc_hw *hw = &pf->si->hw;
struct enetc_mac_addr *mac_tbl;
+ struct enetc_si *si = pf->si;
struct netdev_hw_addr *ha;
int i = 0, err;
int mac_cnt;
+ u64 hash;
netif_addr_lock_bh(ndev);
@@ -159,7 +146,7 @@ static int enetc4_pf_set_uc_exact_filter(struct enetc_pf *pf)
if (!mac_cnt) {
netif_addr_unlock_bh(ndev);
/* clear both MAC hash and exact filters */
- enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+ enetc_set_si_uc_hash_filter(si, 0, 0);
enetc4_pf_clear_maft_entries(pf);
return 0;
@@ -186,11 +173,13 @@ static int enetc4_pf_set_uc_exact_filter(struct enetc_pf *pf)
/* Set temporary unicast hash filters in case of Rx loss when
* updating MAC address filter table
*/
- enetc4_pf_set_si_uc_hash_filter(hw, 0, *mac_filter.mac_hash_table);
+ bitmap_to_arr64(&hash, mac_filter.mac_hash_table,
+ ENETC_MADDR_HASH_TBL_SZ);
+ enetc_set_si_uc_hash_filter(si, 0, hash);
enetc4_pf_clear_maft_entries(pf);
if (!enetc4_pf_add_maft_entries(pf, mac_tbl, i))
- enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+ enetc_set_si_uc_hash_filter(si, 0, 0);
kfree(mac_tbl);
@@ -206,8 +195,9 @@ static void enetc4_pf_set_mac_hash_filter(struct enetc_pf *pf, int type)
{
struct net_device *ndev = pf->si->ndev;
struct enetc_mac_filter *mac_filter;
- struct enetc_hw *hw = &pf->si->hw;
+ struct enetc_si *si = pf->si;
struct netdev_hw_addr *ha;
+ u64 hash;
netif_addr_lock_bh(ndev);
if (type & ENETC_MAC_FILTER_TYPE_UC) {
@@ -216,8 +206,9 @@ static void enetc4_pf_set_mac_hash_filter(struct enetc_pf *pf, int type)
netdev_for_each_uc_addr(ha, ndev)
enetc_add_mac_addr_ht_filter(mac_filter, ha->addr);
- enetc4_pf_set_si_uc_hash_filter(hw, 0,
- *mac_filter->mac_hash_table);
+ bitmap_to_arr64(&hash, mac_filter->mac_hash_table,
+ ENETC_MADDR_HASH_TBL_SZ);
+ enetc_set_si_uc_hash_filter(si, 0, hash);
}
if (type & ENETC_MAC_FILTER_TYPE_MC) {
@@ -226,8 +217,9 @@ static void enetc4_pf_set_mac_hash_filter(struct enetc_pf *pf, int type)
netdev_for_each_mc_addr(ha, ndev)
enetc_add_mac_addr_ht_filter(mac_filter, ha->addr);
- enetc4_pf_set_si_mc_hash_filter(hw, 0,
- *mac_filter->mac_hash_table);
+ bitmap_to_arr64(&hash, mac_filter->mac_hash_table,
+ ENETC_MADDR_HASH_TBL_SZ);
+ enetc_set_si_mc_hash_filter(si, 0, hash);
}
netif_addr_unlock_bh(ndev);
}
@@ -480,7 +472,6 @@ static void enetc4_psi_do_set_rx_mode(struct work_struct *work)
struct enetc_si *si = container_of(work, struct enetc_si, rx_mode_task);
struct enetc_pf *pf = enetc_si_priv(si);
struct net_device *ndev = si->ndev;
- struct enetc_hw *hw = &si->hw;
bool uc_promisc = false;
bool mc_promisc = false;
int type = 0;
@@ -501,12 +492,12 @@ static void enetc4_psi_do_set_rx_mode(struct work_struct *work)
enetc_set_si_mc_promisc(si, 0, mc_promisc);
if (uc_promisc) {
- enetc4_pf_set_si_uc_hash_filter(hw, 0, 0);
+ enetc_set_si_uc_hash_filter(si, 0, 0);
enetc4_pf_clear_maft_entries(pf);
}
if (mc_promisc)
- enetc4_pf_set_si_mc_hash_filter(hw, 0, 0);
+ enetc_set_si_mc_hash_filter(si, 0, 0);
/* Set new MAC filter */
enetc4_pf_set_mac_filter(pf, type);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index a97d2e2dd07b..db2a800a7aaf 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -80,37 +80,6 @@ static void enetc_add_mac_addr_em_filter(struct enetc_mac_filter *filter,
filter->mac_addr_cnt++;
}
-static void enetc_clear_mac_ht_flt(struct enetc_si *si, int si_idx, int type)
-{
- bool err = si->errata & ENETC_ERR_UCMCSWP;
-
- if (type == UC) {
- enetc_port_wr(&si->hw, ENETC_PSIUMHFR0(si_idx, err), 0);
- enetc_port_wr(&si->hw, ENETC_PSIUMHFR1(si_idx), 0);
- } else { /* MC */
- enetc_port_wr(&si->hw, ENETC_PSIMMHFR0(si_idx, err), 0);
- enetc_port_wr(&si->hw, ENETC_PSIMMHFR1(si_idx), 0);
- }
-}
-
-static void enetc_set_mac_ht_flt(struct enetc_si *si, int si_idx, int type,
- unsigned long hash)
-{
- bool err = si->errata & ENETC_ERR_UCMCSWP;
-
- if (type == UC) {
- enetc_port_wr(&si->hw, ENETC_PSIUMHFR0(si_idx, err),
- lower_32_bits(hash));
- enetc_port_wr(&si->hw, ENETC_PSIUMHFR1(si_idx),
- upper_32_bits(hash));
- } else { /* MC */
- enetc_port_wr(&si->hw, ENETC_PSIMMHFR0(si_idx, err),
- lower_32_bits(hash));
- enetc_port_wr(&si->hw, ENETC_PSIMMHFR1(si_idx),
- upper_32_bits(hash));
- }
-}
-
static void enetc_sync_mac_filters(struct enetc_pf *pf)
{
struct enetc_mac_filter *f = pf->mac_filter;
@@ -122,12 +91,16 @@ static void enetc_sync_mac_filters(struct enetc_pf *pf)
for (i = 0; i < MADDR_TYPE; i++, f++) {
bool em = (f->mac_addr_cnt == 1) && (i == UC);
bool clear = !f->mac_addr_cnt;
+ u64 hash;
if (clear) {
- if (i == UC)
+ if (i == UC) {
enetc_clear_mac_flt_entry(si, pos);
+ enetc_set_si_uc_hash_filter(si, 0, 0);
+ } else {
+ enetc_set_si_mc_hash_filter(si, 0, 0);
+ }
- enetc_clear_mac_ht_flt(si, 0, i);
continue;
}
@@ -135,7 +108,7 @@ static void enetc_sync_mac_filters(struct enetc_pf *pf)
if (em) {
int err;
- enetc_clear_mac_ht_flt(si, 0, UC);
+ enetc_set_si_uc_hash_filter(si, 0, 0);
err = enetc_set_mac_flt_entry(si, pos, f->mac_addr,
BIT(0));
@@ -147,11 +120,15 @@ static void enetc_sync_mac_filters(struct enetc_pf *pf)
err);
}
+ bitmap_to_arr64(&hash, f->mac_hash_table,
+ ENETC_MADDR_HASH_TBL_SZ);
/* hash table filter, clear EM filter for UC entries */
- if (i == UC)
+ if (i == UC) {
enetc_clear_mac_flt_entry(si, pos);
-
- enetc_set_mac_ht_flt(si, 0, i, *f->mac_hash_table);
+ enetc_set_si_uc_hash_filter(si, 0, hash);
+ } else {
+ enetc_set_si_mc_hash_filter(si, 0, hash);
+ }
}
}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
index b0c0dc668e34..3597cb81a7cc 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c
@@ -131,6 +131,46 @@ void enetc_set_si_mc_promisc(struct enetc_si *si, int si_id, bool promisc)
}
EXPORT_SYMBOL_GPL(enetc_set_si_mc_promisc);
+void enetc_set_si_uc_hash_filter(struct enetc_si *si, int si_id, u64 hash)
+{
+ int psiumhfr0_off, psiumhfr1_off;
+ struct enetc_hw *hw = &si->hw;
+
+ if (is_enetc_rev1(si)) {
+ bool err = si->errata & ENETC_ERR_UCMCSWP;
+
+ psiumhfr0_off = ENETC_PSIUMHFR0(si_id, err);
+ psiumhfr1_off = ENETC_PSIUMHFR1(si_id);
+ } else {
+ psiumhfr0_off = ENETC4_PSIUMHFR0(si_id);
+ psiumhfr1_off = ENETC4_PSIUMHFR1(si_id);
+ }
+
+ enetc_port_wr(hw, psiumhfr0_off, lower_32_bits(hash));
+ enetc_port_wr(hw, psiumhfr1_off, upper_32_bits(hash));
+}
+EXPORT_SYMBOL_GPL(enetc_set_si_uc_hash_filter);
+
+void enetc_set_si_mc_hash_filter(struct enetc_si *si, int si_id, u64 hash)
+{
+ int psimmhfr0_off, psimmhfr1_off;
+ struct enetc_hw *hw = &si->hw;
+
+ if (is_enetc_rev1(si)) {
+ bool err = si->errata & ENETC_ERR_UCMCSWP;
+
+ psimmhfr0_off = ENETC_PSIMMHFR0(si_id, err);
+ psimmhfr1_off = ENETC_PSIMMHFR1(si_id);
+ } else {
+ psimmhfr0_off = ENETC4_PSIMMHFR0(si_id);
+ psimmhfr1_off = ENETC4_PSIMMHFR1(si_id);
+ }
+
+ enetc_port_wr(hw, psimmhfr0_off, lower_32_bits(hash));
+ enetc_port_wr(hw, psimmhfr1_off, upper_32_bits(hash));
+}
+EXPORT_SYMBOL_GPL(enetc_set_si_mc_hash_filter);
+
void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
const struct net_device_ops *ndev_ops)
{
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
index a619fb8fed9c..bf9029b0a017 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.h
@@ -19,6 +19,8 @@ int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid);
int enetc_init_sriov_resources(struct enetc_pf *pf);
void enetc_set_si_uc_promisc(struct enetc_si *si, int si_id, bool promisc);
void enetc_set_si_mc_promisc(struct enetc_si *si, int si_id, bool promisc);
+void enetc_set_si_uc_hash_filter(struct enetc_si *si, int si_id, u64 hash);
+void enetc_set_si_mc_hash_filter(struct enetc_si *si, int si_id, u64 hash);
static inline u16 enetc_get_ip_revision(struct enetc_hw *hw)
{
--
2.34.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox