[PATCH AUTOSEL 6.8 03/68] bnx2x: Fix firmware version string character counts

[PATCH AUTOSEL 6.8 03/68] bnx2x: Fix firmware version string character counts

[Sasha Levin]

From: Kees Cook <keescook@chromium.org>

[ Upstream commit 5642c82b9463c3263c086efb002516244bd4c668 ]

A potential string truncation was reported in bnx2x_fill_fw_str(),
when a long bp->fw_ver and a long phy_fw_ver might coexist, but seems
unlikely with real-world hardware.

Use scnprintf() to indicate the intent that truncations are tolerated.

While reading this code, I found a collection of various buffer size
counting issues. None looked like they might lead to a buffer overflow
with current code (the small buffers are 20 bytes and might only ever
consume 10 bytes twice with a trailing %NUL). However, early truncation
(due to a %NUL in the middle of the string) might be happening under
likely rare conditions. Regardless fix the formatters and related
functions:

- Switch from a separate strscpy() to just adding an additional "%s" to
  the format string that immediately follows it in bnx2x_fill_fw_str().
- Use sizeof() universally instead of using unbound defines.
- Fix bnx2x_7101_format_ver() and bnx2x_null_format_ver() to report the
  number of characters written, not including the trailing %NUL (as
  already done with the other firmware formatting functions).
- Require space for at least 1 byte in bnx2x_get_ext_phy_fw_version()
  for the trailing %NUL.
- Correct the needed buffer size in bnx2x_3_seq_format_ver().

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202401260858.jZN6vD1k-lkp@intel.com/
Cc: Ariel Elior <aelior@marvell.com>
Cc: Sudarsana Kalluru <skalluru@marvell.com>
Cc: Manish Chopra <manishc@marvell.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20240126041044.work.220-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c    |  9 +++++----
 .../net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c    |  2 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c   | 14 +++++++-------
 3 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index e9c1e1bb55806..528441b28c4ef 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -147,10 +147,11 @@ void bnx2x_fill_fw_str(struct bnx2x *bp, char *buf, size_t buf_len)
 
 		phy_fw_ver[0] = '\0';
 		bnx2x_get_ext_phy_fw_version(&bp->link_params,
-					     phy_fw_ver, PHY_FW_VER_LEN);
-		strscpy(buf, bp->fw_ver, buf_len);
-		snprintf(buf + strlen(bp->fw_ver), 32 - strlen(bp->fw_ver),
-			 "bc %d.%d.%d%s%s",
+					     phy_fw_ver, sizeof(phy_fw_ver));
+		/* This may become truncated. */
+		scnprintf(buf, buf_len,
+			 "%sbc %d.%d.%d%s%s",
+			 bp->fw_ver,
 			 (bp->common.bc_ver & 0xff0000) >> 16,
 			 (bp->common.bc_ver & 0xff00) >> 8,
 			 (bp->common.bc_ver & 0xff),
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 81d232e6d05fe..0bc7690cdee16 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1132,7 +1132,7 @@ static void bnx2x_get_drvinfo(struct net_device *dev,
 	}
 
 	memset(version, 0, sizeof(version));
-	bnx2x_fill_fw_str(bp, version, ETHTOOL_FWVERS_LEN);
+	bnx2x_fill_fw_str(bp, version, sizeof(version));
 	strlcat(info->fw_version, version, sizeof(info->fw_version));
 
 	strscpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 02808513ffe45..ea310057fe3af 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -6163,8 +6163,8 @@ static void bnx2x_link_int_ack(struct link_params *params,
 
 static int bnx2x_null_format_ver(u32 spirom_ver, u8 *str, u16 *len)
 {
-	str[0] = '\0';
-	(*len)--;
+	if (*len)
+		str[0] = '\0';
 	return 0;
 }
 
@@ -6173,7 +6173,7 @@ static int bnx2x_format_ver(u32 num, u8 *str, u16 *len)
 	u16 ret;
 
 	if (*len < 10) {
-		/* Need more than 10chars for this format */
+		/* Need more than 10 chars for this format */
 		bnx2x_null_format_ver(num, str, len);
 		return -EINVAL;
 	}
@@ -6188,8 +6188,8 @@ static int bnx2x_3_seq_format_ver(u32 num, u8 *str, u16 *len)
 {
 	u16 ret;
 
-	if (*len < 10) {
-		/* Need more than 10chars for this format */
+	if (*len < 9) {
+		/* Need more than 9 chars for this format */
 		bnx2x_null_format_ver(num, str, len);
 		return -EINVAL;
 	}
@@ -6208,7 +6208,7 @@ int bnx2x_get_ext_phy_fw_version(struct link_params *params, u8 *version,
 	int status = 0;
 	u8 *ver_p = version;
 	u16 remain_len = len;
-	if (version == NULL || params == NULL)
+	if (version == NULL || params == NULL || len == 0)
 		return -EINVAL;
 	bp = params->bp;
 
@@ -11546,7 +11546,7 @@ static int bnx2x_7101_format_ver(u32 spirom_ver, u8 *str, u16 *len)
 	str[2] = (spirom_ver & 0xFF0000) >> 16;
 	str[3] = (spirom_ver & 0xFF000000) >> 24;
 	str[4] = '\0';
-	*len -= 5;
+	*len -= 4;
 	return 0;
 }
 
-- 
2.43.0

[PATCH AUTOSEL 6.8 04/68] batman-adv: Return directly after a failed batadv_dat_select_candidates() in batadv_dat_forward_data()

[Sasha Levin]

From: Markus Elfring <elfring@users.sourceforge.net>

[ Upstream commit ffc15626c861f811f9778914be004fcf43810a91 ]

The kfree() function was called in one case by
the batadv_dat_forward_data() function during error handling
even if the passed variable contained a null pointer.
This issue was detected by using the Coccinelle software.

* Thus return directly after a batadv_dat_select_candidates() call failed
  at the beginning.

* Delete the label “out” which became unnecessary with this refactoring.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Acked-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/batman-adv/distributed-arp-table.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 28a939d560906..4c7e855343245 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -684,7 +684,7 @@ static bool batadv_dat_forward_data(struct batadv_priv *bat_priv,
 
 	cand = batadv_dat_select_candidates(bat_priv, ip, vid);
 	if (!cand)
-		goto out;
+		return ret;
 
 	batadv_dbg(BATADV_DBG_DAT, bat_priv, "DHT_SEND for %pI4\n", &ip);
 
@@ -728,7 +728,6 @@ static bool batadv_dat_forward_data(struct batadv_priv *bat_priv,
 		batadv_orig_node_put(cand[i].orig_node);
 	}
 
-out:
 	kfree(cand);
 	return ret;
 }
-- 
2.43.0

[PATCH AUTOSEL 6.8 05/68] batman-adv: Improve exception handling in batadv_throw_uevent()

[Sasha Levin]

From: Markus Elfring <elfring@users.sourceforge.net>

[ Upstream commit 5593e9abf1cf2bf096366d8c7fd933bc69d561ce ]

The kfree() function was called in up to three cases by
the batadv_throw_uevent() function during error handling
even if the passed variable contained a null pointer.
This issue was detected by using the Coccinelle software.

* Thus adjust jump targets.

* Reorder kfree() calls at the end.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Acked-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/batman-adv/main.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 5fc754b0b3f7f..75119f1ffcccf 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -691,29 +691,31 @@ int batadv_throw_uevent(struct batadv_priv *bat_priv, enum batadv_uev_type type,
 				  "%s%s", BATADV_UEV_TYPE_VAR,
 				  batadv_uev_type_str[type]);
 	if (!uevent_env[0])
-		goto out;
+		goto report_error;
 
 	uevent_env[1] = kasprintf(GFP_ATOMIC,
 				  "%s%s", BATADV_UEV_ACTION_VAR,
 				  batadv_uev_action_str[action]);
 	if (!uevent_env[1])
-		goto out;
+		goto free_first_env;
 
 	/* If the event is DEL, ignore the data field */
 	if (action != BATADV_UEV_DEL) {
 		uevent_env[2] = kasprintf(GFP_ATOMIC,
 					  "%s%s", BATADV_UEV_DATA_VAR, data);
 		if (!uevent_env[2])
-			goto out;
+			goto free_second_env;
 	}
 
 	ret = kobject_uevent_env(bat_kobj, KOBJ_CHANGE, uevent_env);
-out:
-	kfree(uevent_env[0]);
-	kfree(uevent_env[1]);
 	kfree(uevent_env[2]);
+free_second_env:
+	kfree(uevent_env[1]);
+free_first_env:
+	kfree(uevent_env[0]);
 
 	if (ret)
+report_error:
 		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
 			   "Impossible to send uevent for (%s,%s,%s) event (err: %d)\n",
 			   batadv_uev_type_str[type],
-- 
2.43.0

[PATCH AUTOSEL 6.8 07/68] net: stmmac: dwmac-starfive: Add support for JH7100 SoC

[Sasha Levin]

From: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>

[ Upstream commit 8d4597b871210429bda0f5c3a8816b7d9b6daf7e ]

Add a missing quirk to enable support for the StarFive JH7100 SoC.

Additionally, for greater flexibility in operation, allow using the
rgmii-rxid and rgmii-txid phy modes.

Co-developed-by: Emil Renner Berthing <kernel@esmil.dk>
Signed-off-by: Emil Renner Berthing <kernel@esmil.dk>
Signed-off-by: Cristian Ciocaltea <cristian.ciocaltea@collabora.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/Kconfig   |  6 ++--
 .../ethernet/stmicro/stmmac/dwmac-starfive.c  | 32 ++++++++++++++++---
 2 files changed, 31 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 85dcda51df052..4ec61f1ee71a2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -165,9 +165,9 @@ config DWMAC_STARFIVE
 	help
 	  Support for ethernet controllers on StarFive RISC-V SoCs
 
-	  This selects the StarFive platform specific glue layer support for
-	  the stmmac device driver. This driver is used for StarFive JH7110
-	  ethernet controller.
+	  This selects the StarFive platform specific glue layer support
+	  for the stmmac device driver. This driver is used for the
+	  StarFive JH7100 and JH7110 ethernet controllers.
 
 config DWMAC_STI
 	tristate "STi GMAC support"
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
index 5d630affb4d15..4e1076faee0cd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
@@ -15,13 +15,20 @@
 
 #include "stmmac_platform.h"
 
-#define STARFIVE_DWMAC_PHY_INFT_RGMII	0x1
-#define STARFIVE_DWMAC_PHY_INFT_RMII	0x4
-#define STARFIVE_DWMAC_PHY_INFT_FIELD	0x7U
+#define STARFIVE_DWMAC_PHY_INFT_RGMII		0x1
+#define STARFIVE_DWMAC_PHY_INFT_RMII		0x4
+#define STARFIVE_DWMAC_PHY_INFT_FIELD		0x7U
+
+#define JH7100_SYSMAIN_REGISTER49_DLYCHAIN	0xc8
+
+struct starfive_dwmac_data {
+	unsigned int gtxclk_dlychain;
+};
 
 struct starfive_dwmac {
 	struct device *dev;
 	struct clk *clk_tx;
+	const struct starfive_dwmac_data *data;
 };
 
 static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
@@ -67,6 +74,8 @@ static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat)
 
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		mode = STARFIVE_DWMAC_PHY_INFT_RGMII;
 		break;
 
@@ -89,6 +98,14 @@ static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat)
 	if (err)
 		return dev_err_probe(dwmac->dev, err, "error setting phy mode\n");
 
+	if (dwmac->data) {
+		err = regmap_write(regmap, JH7100_SYSMAIN_REGISTER49_DLYCHAIN,
+				   dwmac->data->gtxclk_dlychain);
+		if (err)
+			return dev_err_probe(dwmac->dev, err,
+					     "error selecting gtxclk delay chain\n");
+	}
+
 	return 0;
 }
 
@@ -114,6 +131,8 @@ static int starfive_dwmac_probe(struct platform_device *pdev)
 	if (!dwmac)
 		return -ENOMEM;
 
+	dwmac->data = device_get_match_data(&pdev->dev);
+
 	dwmac->clk_tx = devm_clk_get_enabled(&pdev->dev, "tx");
 	if (IS_ERR(dwmac->clk_tx))
 		return dev_err_probe(&pdev->dev, PTR_ERR(dwmac->clk_tx),
@@ -144,8 +163,13 @@ static int starfive_dwmac_probe(struct platform_device *pdev)
 	return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 }
 
+static const struct starfive_dwmac_data jh7100_data = {
+	.gtxclk_dlychain = 4,
+};
+
 static const struct of_device_id starfive_dwmac_match[] = {
-	{ .compatible = "starfive,jh7110-dwmac"	},
+	{ .compatible = "starfive,jh7100-dwmac", .data = &jh7100_data },
+	{ .compatible = "starfive,jh7110-dwmac" },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, starfive_dwmac_match);
-- 
2.43.0

[PATCH AUTOSEL 6.8 08/68] net: phy: phy_device: Prevent nullptr exceptions on ISR

[Sasha Levin]

From: Andre Werner <andre.werner@systec-electronic.com>

[ Upstream commit 61c81872815f46006982bb80460c0c80a949b35b ]

If phydev->irq is set unconditionally, check
for valid interrupt handler or fall back to polling mode to prevent
nullptr exceptions in interrupt service routine.

Signed-off-by: Andre Werner <andre.werner@systec-electronic.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://lore.kernel.org/r/20240129135734.18975-2-andre.werner@systec-electronic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/phy/phy_device.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 3611ea64875ef..7cbe7c7141773 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1413,6 +1413,11 @@ int phy_sfp_probe(struct phy_device *phydev,
 }
 EXPORT_SYMBOL(phy_sfp_probe);
 
+static bool phy_drv_supports_irq(struct phy_driver *phydrv)
+{
+	return phydrv->config_intr && phydrv->handle_interrupt;
+}
+
 /**
  * phy_attach_direct - attach a network device to a given PHY device pointer
  * @dev: network device to attach
@@ -1527,6 +1532,9 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	if (phydev->dev_flags & PHY_F_NO_IRQ)
 		phydev->irq = PHY_POLL;
 
+	if (!phy_drv_supports_irq(phydev->drv) && phy_interrupt_is_valid(phydev))
+		phydev->irq = PHY_POLL;
+
 	/* Port is set to PORT_TP by default and the actual PHY driver will set
 	 * it to different value depending on the PHY configuration. If we have
 	 * the generic PHY driver we can't figure it out, thus set the old
@@ -2992,11 +3000,6 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev,
 }
 EXPORT_SYMBOL(phy_get_internal_delay);
 
-static bool phy_drv_supports_irq(struct phy_driver *phydrv)
-{
-	return phydrv->config_intr && phydrv->handle_interrupt;
-}
-
 static int phy_led_set_brightness(struct led_classdev *led_cdev,
 				  enum led_brightness value)
 {
-- 
2.43.0

[PATCH AUTOSEL 6.8 14/68] net: dsa: qca8k: put MDIO controller OF node if unavailable

[Sasha Levin]

From: Vladimir Oltean <vladimir.oltean@nxp.com>

[ Upstream commit 08932323ccf7f8c4c85db9cb12a791ed81264f66 ]

It was pointed out during the review [1] of commit e66bf63a7f67 ("net:
dsa: qca8k: skip MDIO bus creation if its OF node has status =
"disabled"") that we now leak a reference to the "mdio" OF node if it is
disabled.

This is only a concern when using dynamic OF as far as I can tell (like
probing on an overlay), since OF nodes are never freed in the regular
case. Additionally, I'm unaware of any actual device trees (in
production or elsewhere) which have status = "disabled" for the MDIO OF
node. So handling this as a simple enhancement.

[1] https://lore.kernel.org/netdev/CAJq09z4--Ug+3FAmp=EimQ8HTQYOWOuVon-PUMGB5a1N=RPv4g@mail.gmail.com/

Suggested-by: Luiz Angelo Daros de Luca <luizluca@gmail.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/dsa/qca/qca8k-8xxx.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index 7a864329cb726..95d78b3181d1c 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -954,7 +954,7 @@ qca8k_mdio_register(struct qca8k_priv *priv)
 
 	mdio = of_get_child_by_name(dev->of_node, "mdio");
 	if (mdio && !of_device_is_available(mdio))
-		goto out;
+		goto out_put_node;
 
 	bus = devm_mdiobus_alloc(dev);
 	if (!bus) {
@@ -988,7 +988,6 @@ qca8k_mdio_register(struct qca8k_priv *priv)
 
 out_put_node:
 	of_node_put(mdio);
-out:
 	return err;
 }
 
-- 
2.43.0

[PATCH AUTOSEL 6.8 28/68] net: add netdev_lockdep_set_classes() to virtual drivers

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 0bef512012b1cd8820f0c9ec80e5f8ceb43fdd59 ]

Based on a syzbot report, it appears many virtual
drivers do not yet use netdev_lockdep_set_classes(),
triggerring lockdep false positives.

WARNING: possible recursive locking detected
6.8.0-rc4-next-20240212-syzkaller #0 Not tainted

syz-executor.0/19016 is trying to acquire lock:
 ffff8880162cb298 (_xmit_ETHER#2){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
 ffff8880162cb298 (_xmit_ETHER#2){+.-.}-{2:2}, at: __netif_tx_lock include/linux/netdevice.h:4452 [inline]
 ffff8880162cb298 (_xmit_ETHER#2){+.-.}-{2:2}, at: sch_direct_xmit+0x1c4/0x5f0 net/sched/sch_generic.c:340

but task is already holding lock:
 ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
 ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: __netif_tx_lock include/linux/netdevice.h:4452 [inline]
 ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: sch_direct_xmit+0x1c4/0x5f0 net/sched/sch_generic.c:340

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
  lock(_xmit_ETHER#2);
  lock(_xmit_ETHER#2);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

9 locks held by syz-executor.0/19016:
  #0: ffffffff8f385208 (rtnl_mutex){+.+.}-{3:3}, at: rtnl_lock net/core/rtnetlink.c:79 [inline]
  #0: ffffffff8f385208 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x82c/0x1040 net/core/rtnetlink.c:6603
  #1: ffffc90000a08c00 ((&in_dev->mr_ifc_timer)){+.-.}-{0:0}, at: call_timer_fn+0xc0/0x600 kernel/time/timer.c:1697
  #2: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:298 [inline]
  #2: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:750 [inline]
  #2: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x45f/0x1360 net/ipv4/ip_output.c:228
  #3: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: local_bh_disable include/linux/bottom_half.h:20 [inline]
  #3: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: rcu_read_lock_bh include/linux/rcupdate.h:802 [inline]
  #3: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: __dev_queue_xmit+0x2c4/0x3b10 net/core/dev.c:4284
  #4: ffff8880416e3258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: spin_trylock include/linux/spinlock.h:361 [inline]
  #4: ffff8880416e3258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: qdisc_run_begin include/net/sch_generic.h:195 [inline]
  #4: ffff8880416e3258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: __dev_xmit_skb net/core/dev.c:3771 [inline]
  #4: ffff8880416e3258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: __dev_queue_xmit+0x1262/0x3b10 net/core/dev.c:4325
  #5: ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: spin_lock include/linux/spinlock.h:351 [inline]
  #5: ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: __netif_tx_lock include/linux/netdevice.h:4452 [inline]
  #5: ffff8880223db4d8 (_xmit_ETHER#2){+.-.}-{2:2}, at: sch_direct_xmit+0x1c4/0x5f0 net/sched/sch_generic.c:340
  #6: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: rcu_lock_acquire include/linux/rcupdate.h:298 [inline]
  #6: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: rcu_read_lock include/linux/rcupdate.h:750 [inline]
  #6: ffffffff8e131520 (rcu_read_lock){....}-{1:2}, at: ip_finish_output2+0x45f/0x1360 net/ipv4/ip_output.c:228
  #7: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: local_bh_disable include/linux/bottom_half.h:20 [inline]
  #7: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: rcu_read_lock_bh include/linux/rcupdate.h:802 [inline]
  #7: ffffffff8e131580 (rcu_read_lock_bh){....}-{1:2}, at: __dev_queue_xmit+0x2c4/0x3b10 net/core/dev.c:4284
  #8: ffff888014d9d258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: spin_trylock include/linux/spinlock.h:361 [inline]
  #8: ffff888014d9d258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: qdisc_run_begin include/net/sch_generic.h:195 [inline]
  #8: ffff888014d9d258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: __dev_xmit_skb net/core/dev.c:3771 [inline]
  #8: ffff888014d9d258 (dev->qdisc_tx_busylock ?: &qdisc_tx_busylock){+...}-{2:2}, at: __dev_queue_xmit+0x1262/0x3b10 net/core/dev.c:4325

stack backtrace:
CPU: 1 PID: 19016 Comm: syz-executor.0 Not tainted 6.8.0-rc4-next-20240212-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
Call Trace:
 <IRQ>
  __dump_stack lib/dump_stack.c:88 [inline]
  dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
  check_deadlock kernel/locking/lockdep.c:3062 [inline]
  validate_chain+0x15c1/0x58e0 kernel/locking/lockdep.c:3856
  __lock_acquire+0x1346/0x1fd0 kernel/locking/lockdep.c:5137
  lock_acquire+0x1e4/0x530 kernel/locking/lockdep.c:5754
  __raw_spin_lock include/linux/spinlock_api_smp.h:133 [inline]
  _raw_spin_lock+0x2e/0x40 kernel/locking/spinlock.c:154
  spin_lock include/linux/spinlock.h:351 [inline]
  __netif_tx_lock include/linux/netdevice.h:4452 [inline]
  sch_direct_xmit+0x1c4/0x5f0 net/sched/sch_generic.c:340
  __dev_xmit_skb net/core/dev.c:3784 [inline]
  __dev_queue_xmit+0x1912/0x3b10 net/core/dev.c:4325
  neigh_output include/net/neighbour.h:542 [inline]
  ip_finish_output2+0xe66/0x1360 net/ipv4/ip_output.c:235
  iptunnel_xmit+0x540/0x9b0 net/ipv4/ip_tunnel_core.c:82
  ip_tunnel_xmit+0x20ee/0x2960 net/ipv4/ip_tunnel.c:831
  erspan_xmit+0x9de/0x1460 net/ipv4/ip_gre.c:720
  __netdev_start_xmit include/linux/netdevice.h:4989 [inline]
  netdev_start_xmit include/linux/netdevice.h:5003 [inline]
  xmit_one net/core/dev.c:3555 [inline]
  dev_hard_start_xmit+0x242/0x770 net/core/dev.c:3571
  sch_direct_xmit+0x2b6/0x5f0 net/sched/sch_generic.c:342
  __dev_xmit_skb net/core/dev.c:3784 [inline]
  __dev_queue_xmit+0x1912/0x3b10 net/core/dev.c:4325
  neigh_output include/net/neighbour.h:542 [inline]
  ip_finish_output2+0xe66/0x1360 net/ipv4/ip_output.c:235
  igmpv3_send_cr net/ipv4/igmp.c:723 [inline]
  igmp_ifc_timer_expire+0xb71/0xd90 net/ipv4/igmp.c:813
  call_timer_fn+0x17e/0x600 kernel/time/timer.c:1700
  expire_timers kernel/time/timer.c:1751 [inline]
  __run_timers+0x621/0x830 kernel/time/timer.c:2038
  run_timer_softirq+0x67/0xf0 kernel/time/timer.c:2051
  __do_softirq+0x2bc/0x943 kernel/softirq.c:554
  invoke_softirq kernel/softirq.c:428 [inline]
  __irq_exit_rcu+0xf2/0x1c0 kernel/softirq.c:633
  irq_exit_rcu+0x9/0x30 kernel/softirq.c:645
  instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1076 [inline]
  sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1076
 </IRQ>
 <TASK>
  asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702
 RIP: 0010:resched_offsets_ok kernel/sched/core.c:10127 [inline]
 RIP: 0010:__might_resched+0x16f/0x780 kernel/sched/core.c:10142
Code: 00 4c 89 e8 48 c1 e8 03 48 ba 00 00 00 00 00 fc ff df 48 89 44 24 38 0f b6 04 10 84 c0 0f 85 87 04 00 00 41 8b 45 00 c1 e0 08 <01> d8 44 39 e0 0f 85 d6 00 00 00 44 89 64 24 1c 48 8d bc 24 a0 00
RSP: 0018:ffffc9000ee069e0 EFLAGS: 00000246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff8880296a9e00
RDX: dffffc0000000000 RSI: ffff8880296a9e00 RDI: ffffffff8bfe8fa0
RBP: ffffc9000ee06b00 R08: ffffffff82326877 R09: 1ffff11002b5ad1b
R10: dffffc0000000000 R11: ffffed1002b5ad1c R12: 0000000000000000
R13: ffff8880296aa23c R14: 000000000000062a R15: 1ffff92001dc0d44
  down_write+0x19/0x50 kernel/locking/rwsem.c:1578
  kernfs_activate fs/kernfs/dir.c:1403 [inline]
  kernfs_add_one+0x4af/0x8b0 fs/kernfs/dir.c:819
  __kernfs_create_file+0x22e/0x2e0 fs/kernfs/file.c:1056
  sysfs_add_file_mode_ns+0x24a/0x310 fs/sysfs/file.c:307
  create_files fs/sysfs/group.c:64 [inline]
  internal_create_group+0x4f4/0xf20 fs/sysfs/group.c:152
  internal_create_groups fs/sysfs/group.c:192 [inline]
  sysfs_create_groups+0x56/0x120 fs/sysfs/group.c:218
  create_dir lib/kobject.c:78 [inline]
  kobject_add_internal+0x472/0x8d0 lib/kobject.c:240
  kobject_add_varg lib/kobject.c:374 [inline]
  kobject_init_and_add+0x124/0x190 lib/kobject.c:457
  netdev_queue_add_kobject net/core/net-sysfs.c:1706 [inline]
  netdev_queue_update_kobjects+0x1f3/0x480 net/core/net-sysfs.c:1758
  register_queue_kobjects net/core/net-sysfs.c:1819 [inline]
  netdev_register_kobject+0x265/0x310 net/core/net-sysfs.c:2059
  register_netdevice+0x1191/0x19c0 net/core/dev.c:10298
  bond_newlink+0x3b/0x90 drivers/net/bonding/bond_netlink.c:576
  rtnl_newlink_create net/core/rtnetlink.c:3506 [inline]
  __rtnl_newlink net/core/rtnetlink.c:3726 [inline]
  rtnl_newlink+0x158f/0x20a0 net/core/rtnetlink.c:3739
  rtnetlink_rcv_msg+0x885/0x1040 net/core/rtnetlink.c:6606
  netlink_rcv_skb+0x1e3/0x430 net/netlink/af_netlink.c:2543
  netlink_unicast_kernel net/netlink/af_netlink.c:1341 [inline]
  netlink_unicast+0x7ea/0x980 net/netlink/af_netlink.c:1367
  netlink_sendmsg+0xa3c/0xd70 net/netlink/af_netlink.c:1908
  sock_sendmsg_nosec net/socket.c:730 [inline]
  __sock_sendmsg+0x221/0x270 net/socket.c:745
  __sys_sendto+0x3a4/0x4f0 net/socket.c:2191
  __do_sys_sendto net/socket.c:2203 [inline]
  __se_sys_sendto net/socket.c:2199 [inline]
  __x64_sys_sendto+0xde/0x100 net/socket.c:2199
 do_syscall_64+0xfb/0x240
 entry_SYSCALL_64_after_hwframe+0x6d/0x75
RIP: 0033:0x7fc3fa87fa9c

Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240212140700.2795436-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/dummy.c            | 1 +
 drivers/net/geneve.c           | 1 +
 drivers/net/loopback.c         | 1 +
 drivers/net/veth.c             | 1 +
 drivers/net/vxlan/vxlan_core.c | 1 +
 net/ipv4/ip_tunnel.c           | 1 +
 net/ipv6/ip6_gre.c             | 2 ++
 net/ipv6/ip6_tunnel.c          | 1 +
 net/ipv6/ip6_vti.c             | 1 +
 net/ipv6/sit.c                 | 1 +
 10 files changed, 11 insertions(+)

diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 768454aa36d6c..946bba0701a4f 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -71,6 +71,7 @@ static int dummy_dev_init(struct net_device *dev)
 	if (!dev->lstats)
 		return -ENOMEM;
 
+	netdev_lockdep_set_classes(dev);
 	return 0;
 }
 
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index c4ed36c718974..097a8db0d1d99 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -349,6 +349,7 @@ static int geneve_init(struct net_device *dev)
 		gro_cells_destroy(&geneve->gro_cells);
 		return err;
 	}
+	netdev_lockdep_set_classes(dev);
 	return 0;
 }
 
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index f6d53e63ef4ec..f6eab66c26608 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -144,6 +144,7 @@ static int loopback_dev_init(struct net_device *dev)
 	dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats);
 	if (!dev->lstats)
 		return -ENOMEM;
+	netdev_lockdep_set_classes(dev);
 	return 0;
 }
 
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index cd4a6fe458f95..1ff3f93d4e037 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1483,6 +1483,7 @@ static void veth_free_queues(struct net_device *dev)
 
 static int veth_dev_init(struct net_device *dev)
 {
+	netdev_lockdep_set_classes(dev);
 	return veth_alloc_queues(dev);
 }
 
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 16106e088c630..0bedb804824ba 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2855,6 +2855,7 @@ static int vxlan_init(struct net_device *dev)
 	if (err)
 		goto err_gro_cells_destroy;
 
+	netdev_lockdep_set_classes(dev);
 	return 0;
 
 err_gro_cells_destroy:
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 1b6981de3f295..e92093cc0e8af 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1285,6 +1285,7 @@ int ip_tunnel_init(struct net_device *dev)
 
 	if (tunnel->collect_md)
 		netif_keep_dst(dev);
+	netdev_lockdep_set_classes(dev);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_init);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 070d87abf7c02..447d244c01b15 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1511,6 +1511,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
 	ip6gre_tnl_init_features(dev);
 
 	netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL);
+	netdev_lockdep_set_classes(dev);
 	return 0;
 
 cleanup_dst_cache_init:
@@ -1903,6 +1904,7 @@ static int ip6erspan_tap_init(struct net_device *dev)
 	ip6erspan_tnl_link_config(tunnel, 1);
 
 	netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL);
+	netdev_lockdep_set_classes(dev);
 	return 0;
 
 cleanup_dst_cache_init:
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 9bbabf750a21e..70478027a7af7 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1898,6 +1898,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
 	dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len;
 
 	netdev_hold(dev, &t->dev_tracker, GFP_KERNEL);
+	netdev_lockdep_set_classes(dev);
 	return 0;
 
 destroy_dst:
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index e550240c85e1c..1163ca6ea4af1 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -935,6 +935,7 @@ static inline int vti6_dev_init_gen(struct net_device *dev)
 	if (!dev->tstats)
 		return -ENOMEM;
 	netdev_hold(dev, &t->dev_tracker, GFP_KERNEL);
+	netdev_lockdep_set_classes(dev);
 	return 0;
 }
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 5e9f625b76e36..fbad6e1c970e4 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1460,6 +1460,7 @@ static int ipip6_tunnel_init(struct net_device *dev)
 		return err;
 	}
 	netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL);
+	netdev_lockdep_set_classes(dev);
 	return 0;
 }
 
-- 
2.43.0

[PATCH AUTOSEL 6.8 37/68] ionic: set adminq irq affinity

[Sasha Levin]

From: Shannon Nelson <shannon.nelson@amd.com>

[ Upstream commit c699f35d658f3c21b69ed24e64b2ea26381e941d ]

We claim to have the AdminQ on our irq0 and thus cpu id 0,
but we need to be sure we set the affinity hint to try to
keep it there.

Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/pensando/ionic/ionic_lif.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index fcb44ceeb6aa5..44d30115ded13 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -3391,9 +3391,12 @@ static int ionic_lif_adminq_init(struct ionic_lif *lif)
 
 	napi_enable(&qcq->napi);
 
-	if (qcq->flags & IONIC_QCQ_F_INTR)
+	if (qcq->flags & IONIC_QCQ_F_INTR) {
+		irq_set_affinity_hint(qcq->intr.vector,
+				      &qcq->intr.affinity_mask);
 		ionic_intr_mask(idev->intr_ctrl, qcq->intr.index,
 				IONIC_INTR_MASK_CLEAR);
+	}
 
 	qcq->flags |= IONIC_QCQ_F_INITED;
 
-- 
2.43.0

[PATCH AUTOSEL 6.8 39/68] net: mdio: mdio-bcm-unimac: Manage clock around I/O accesses

[Sasha Levin]

From: Florian Fainelli <florian.fainelli@broadcom.com>

[ Upstream commit ee975351cf0c2a11cdf97eae58265c126cb32850 ]

Up until now we have managed not to have the mdio-bcm-unimac manage its
clock except during probe and suspend/resume. This works most of the
time, except where it does not.

With a fully modular build, we can get into a situation whereby the
GENET driver is fully registered, and so is the mdio-bcm-unimac driver,
however the Ethernet PHY driver is not yet, because it depends on a
resource that is not yet available (e.g.: GPIO provider). In that state,
the network device is not usable yet, and so to conserve power, the
GENET driver will have turned off its "main" clock which feeds its MDIO
controller.

When the PHY driver finally probes however, we make an access to the PHY
registers to e.g.: disable interrupts, and this causes a bus error
within the MDIO controller space because the MDIO controller clock(s)
are turned off.

To remedy that, we manage the clock around all of the I/O accesses to
the hardware which are done exclusively during read, write and clock
divider configuration.

This ensures that the register space is accessible, and this also
ensures that there are not unnecessarily elevated reference counts
keeping the clocks active when the network device is administratively
turned off. It would be the case with the previous way of managing the
clock.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/mdio/mdio-bcm-unimac.c            | 93 ++++++++++---------
 include/linux/platform_data/mdio-bcm-unimac.h |  3 +
 2 files changed, 53 insertions(+), 43 deletions(-)

diff --git a/drivers/net/mdio/mdio-bcm-unimac.c b/drivers/net/mdio/mdio-bcm-unimac.c
index 68f8ee0ec8baa..6fe08427fdd4a 100644
--- a/drivers/net/mdio/mdio-bcm-unimac.c
+++ b/drivers/net/mdio/mdio-bcm-unimac.c
@@ -94,6 +94,10 @@ static int unimac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 	int ret;
 	u32 cmd;
 
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		return ret;
+
 	/* Prepare the read operation */
 	cmd = MDIO_RD | (phy_id << MDIO_PMD_SHIFT) | (reg << MDIO_REG_SHIFT);
 	unimac_mdio_writel(priv, cmd, MDIO_CMD);
@@ -103,7 +107,7 @@ static int unimac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 
 	ret = priv->wait_func(priv->wait_func_data);
 	if (ret)
-		return ret;
+		goto out;
 
 	cmd = unimac_mdio_readl(priv, MDIO_CMD);
 
@@ -112,10 +116,15 @@ static int unimac_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 	 * that condition here and ignore the MDIO controller read failure
 	 * indication.
 	 */
-	if (!(bus->phy_ignore_ta_mask & 1 << phy_id) && (cmd & MDIO_READ_FAIL))
-		return -EIO;
+	if (!(bus->phy_ignore_ta_mask & 1 << phy_id) && (cmd & MDIO_READ_FAIL)) {
+		ret = -EIO;
+		goto out;
+	}
 
-	return cmd & 0xffff;
+	ret = cmd & 0xffff;
+out:
+	clk_disable_unprepare(priv->clk);
+	return ret;
 }
 
 static int unimac_mdio_write(struct mii_bus *bus, int phy_id,
@@ -123,6 +132,11 @@ static int unimac_mdio_write(struct mii_bus *bus, int phy_id,
 {
 	struct unimac_mdio_priv *priv = bus->priv;
 	u32 cmd;
+	int ret;
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		return ret;
 
 	/* Prepare the write operation */
 	cmd = MDIO_WR | (phy_id << MDIO_PMD_SHIFT) |
@@ -131,7 +145,10 @@ static int unimac_mdio_write(struct mii_bus *bus, int phy_id,
 
 	unimac_mdio_start(priv);
 
-	return priv->wait_func(priv->wait_func_data);
+	ret = priv->wait_func(priv->wait_func_data);
+	clk_disable_unprepare(priv->clk);
+
+	return ret;
 }
 
 /* Workaround for integrated BCM7xxx Gigabit PHYs which have a problem with
@@ -178,14 +195,19 @@ static int unimac_mdio_reset(struct mii_bus *bus)
 	return 0;
 }
 
-static void unimac_mdio_clk_set(struct unimac_mdio_priv *priv)
+static int unimac_mdio_clk_set(struct unimac_mdio_priv *priv)
 {
 	unsigned long rate;
 	u32 reg, div;
+	int ret;
 
 	/* Keep the hardware default values */
 	if (!priv->clk_freq)
-		return;
+		return 0;
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		return ret;
 
 	if (!priv->clk)
 		rate = 250000000;
@@ -195,7 +217,8 @@ static void unimac_mdio_clk_set(struct unimac_mdio_priv *priv)
 	div = (rate / (2 * priv->clk_freq)) - 1;
 	if (div & ~MDIO_CLK_DIV_MASK) {
 		pr_warn("Incorrect MDIO clock frequency, ignoring\n");
-		return;
+		ret = 0;
+		goto out;
 	}
 
 	/* The MDIO clock is the reference clock (typically 250Mhz) divided by
@@ -205,6 +228,9 @@ static void unimac_mdio_clk_set(struct unimac_mdio_priv *priv)
 	reg &= ~(MDIO_CLK_DIV_MASK << MDIO_CLK_DIV_SHIFT);
 	reg |= div << MDIO_CLK_DIV_SHIFT;
 	unimac_mdio_writel(priv, reg, MDIO_CFG);
+out:
+	clk_disable_unprepare(priv->clk);
+	return ret;
 }
 
 static int unimac_mdio_probe(struct platform_device *pdev)
@@ -235,24 +261,12 @@ static int unimac_mdio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
-	priv->clk = devm_clk_get_optional(&pdev->dev, NULL);
-	if (IS_ERR(priv->clk))
-		return PTR_ERR(priv->clk);
-
-	ret = clk_prepare_enable(priv->clk);
-	if (ret)
-		return ret;
-
 	if (of_property_read_u32(np, "clock-frequency", &priv->clk_freq))
 		priv->clk_freq = 0;
 
-	unimac_mdio_clk_set(priv);
-
 	priv->mii_bus = mdiobus_alloc();
-	if (!priv->mii_bus) {
-		ret = -ENOMEM;
-		goto out_clk_disable;
-	}
+	if (!priv->mii_bus)
+		return -ENOMEM;
 
 	bus = priv->mii_bus;
 	bus->priv = priv;
@@ -261,17 +275,29 @@ static int unimac_mdio_probe(struct platform_device *pdev)
 		priv->wait_func = pdata->wait_func;
 		priv->wait_func_data = pdata->wait_func_data;
 		bus->phy_mask = ~pdata->phy_mask;
+		priv->clk = pdata->clk;
 	} else {
 		bus->name = "unimac MII bus";
 		priv->wait_func_data = priv;
 		priv->wait_func = unimac_mdio_poll;
+		priv->clk = devm_clk_get_optional(&pdev->dev, NULL);
+	}
+
+	if (IS_ERR(priv->clk)) {
+		ret = PTR_ERR(priv->clk);
+		goto out_mdio_free;
 	}
+
 	bus->parent = &pdev->dev;
 	bus->read = unimac_mdio_read;
 	bus->write = unimac_mdio_write;
 	bus->reset = unimac_mdio_reset;
 	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-%d", pdev->name, pdev->id);
 
+	ret = unimac_mdio_clk_set(priv);
+	if (ret)
+		goto out_mdio_free;
+
 	ret = of_mdiobus_register(bus, np);
 	if (ret) {
 		dev_err(&pdev->dev, "MDIO bus registration failed\n");
@@ -286,8 +312,6 @@ static int unimac_mdio_probe(struct platform_device *pdev)
 
 out_mdio_free:
 	mdiobus_free(bus);
-out_clk_disable:
-	clk_disable_unprepare(priv->clk);
 	return ret;
 }
 
@@ -297,34 +321,17 @@ static void unimac_mdio_remove(struct platform_device *pdev)
 
 	mdiobus_unregister(priv->mii_bus);
 	mdiobus_free(priv->mii_bus);
-	clk_disable_unprepare(priv->clk);
-}
-
-static int __maybe_unused unimac_mdio_suspend(struct device *d)
-{
-	struct unimac_mdio_priv *priv = dev_get_drvdata(d);
-
-	clk_disable_unprepare(priv->clk);
-
-	return 0;
 }
 
 static int __maybe_unused unimac_mdio_resume(struct device *d)
 {
 	struct unimac_mdio_priv *priv = dev_get_drvdata(d);
-	int ret;
 
-	ret = clk_prepare_enable(priv->clk);
-	if (ret)
-		return ret;
-
-	unimac_mdio_clk_set(priv);
-
-	return 0;
+	return unimac_mdio_clk_set(priv);
 }
 
 static SIMPLE_DEV_PM_OPS(unimac_mdio_pm_ops,
-			 unimac_mdio_suspend, unimac_mdio_resume);
+			 NULL, unimac_mdio_resume);
 
 static const struct of_device_id unimac_mdio_ids[] = {
 	{ .compatible = "brcm,asp-v2.1-mdio", },
diff --git a/include/linux/platform_data/mdio-bcm-unimac.h b/include/linux/platform_data/mdio-bcm-unimac.h
index 8a5f9f0b2c520..724e1f57b81ff 100644
--- a/include/linux/platform_data/mdio-bcm-unimac.h
+++ b/include/linux/platform_data/mdio-bcm-unimac.h
@@ -1,11 +1,14 @@
 #ifndef __MDIO_BCM_UNIMAC_PDATA_H
 #define __MDIO_BCM_UNIMAC_PDATA_H
 
+struct clk;
+
 struct unimac_mdio_pdata {
 	u32 phy_mask;
 	int (*wait_func)(void *data);
 	void *wait_func_data;
 	const char *bus_name;
+	struct clk *clk;
 };
 
 #define UNIMAC_MDIO_DRV_NAME	"unimac-mdio"
-- 
2.43.0

Re: [PATCH AUTOSEL 6.8 39/68] net: mdio: mdio-bcm-unimac: Manage clock around I/O accesses

[Florian Fainelli]

[-- Attachment #1: Type: text/plain, Size: 2090 bytes --]



On 3/29/2024 5:25 AM, Sasha Levin wrote:
> From: Florian Fainelli <florian.fainelli@broadcom.com>
> 
> [ Upstream commit ee975351cf0c2a11cdf97eae58265c126cb32850 ]
> 
> Up until now we have managed not to have the mdio-bcm-unimac manage its
> clock except during probe and suspend/resume. This works most of the
> time, except where it does not.
> 
> With a fully modular build, we can get into a situation whereby the
> GENET driver is fully registered, and so is the mdio-bcm-unimac driver,
> however the Ethernet PHY driver is not yet, because it depends on a
> resource that is not yet available (e.g.: GPIO provider). In that state,
> the network device is not usable yet, and so to conserve power, the
> GENET driver will have turned off its "main" clock which feeds its MDIO
> controller.
> 
> When the PHY driver finally probes however, we make an access to the PHY
> registers to e.g.: disable interrupts, and this causes a bus error
> within the MDIO controller space because the MDIO controller clock(s)
> are turned off.
> 
> To remedy that, we manage the clock around all of the I/O accesses to
> the hardware which are done exclusively during read, write and clock
> divider configuration.
> 
> This ensures that the register space is accessible, and this also
> ensures that there are not unnecessarily elevated reference counts
> keeping the clocks active when the network device is administratively
> turned off. It would be the case with the previous way of managing the
> clock.
> 
> Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
> Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
> Signed-off-by: David S. Miller <davem@davemloft.net>
> Signed-off-by: Sasha Levin <sashal@kernel.org>

Please drop this patch, it is usable in isolation and needs 2 additional 
patches to be meaningful:

https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=ee2b4cf8b281606bbf332cbd73ce2a73eac417f0
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
/commit/?id=ba0b78371c46b2104197ff2c244f13f011ddfa80

Thanks!
-- 
Florian

[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4221 bytes --]

Re: [PATCH AUTOSEL 6.8 39/68] net: mdio: mdio-bcm-unimac: Manage clock around I/O accesses

[Sasha Levin]

On Tue, Apr 02, 2024 at 05:41:44AM -0700, Florian Fainelli wrote:
>
>
>On 3/29/2024 5:25 AM, Sasha Levin wrote:
>>From: Florian Fainelli <florian.fainelli@broadcom.com>
>>
>>[ Upstream commit ee975351cf0c2a11cdf97eae58265c126cb32850 ]
>>
>>Up until now we have managed not to have the mdio-bcm-unimac manage its
>>clock except during probe and suspend/resume. This works most of the
>>time, except where it does not.
>>
>>With a fully modular build, we can get into a situation whereby the
>>GENET driver is fully registered, and so is the mdio-bcm-unimac driver,
>>however the Ethernet PHY driver is not yet, because it depends on a
>>resource that is not yet available (e.g.: GPIO provider). In that state,
>>the network device is not usable yet, and so to conserve power, the
>>GENET driver will have turned off its "main" clock which feeds its MDIO
>>controller.
>>
>>When the PHY driver finally probes however, we make an access to the PHY
>>registers to e.g.: disable interrupts, and this causes a bus error
>>within the MDIO controller space because the MDIO controller clock(s)
>>are turned off.
>>
>>To remedy that, we manage the clock around all of the I/O accesses to
>>the hardware which are done exclusively during read, write and clock
>>divider configuration.
>>
>>This ensures that the register space is accessible, and this also
>>ensures that there are not unnecessarily elevated reference counts
>>keeping the clocks active when the network device is administratively
>>turned off. It would be the case with the previous way of managing the
>>clock.
>>
>>Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
>>Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
>>Signed-off-by: David S. Miller <davem@davemloft.net>
>>Signed-off-by: Sasha Levin <sashal@kernel.org>
>
>Please drop this patch, it is usable in isolation and needs 2 
>additional patches to be meaningful:
>
>https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=ee2b4cf8b281606bbf332cbd73ce2a73eac417f0
>https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
>/commit/?id=ba0b78371c46b2104197ff2c244f13f011ddfa80

Ack, thanks!

-- 
Thanks,
Sasha

[PATCH AUTOSEL 6.8 49/68] net: pcs: xpcs: Return EINVAL in the internal methods

[Sasha Levin]

From: Serge Semin <fancer.lancer@gmail.com>

[ Upstream commit f5151005d379d9ce42e327fd3b2d2aaef61cda81 ]

In particular the xpcs_soft_reset() and xpcs_do_config() functions
currently return -1 if invalid auto-negotiation mode is specified. That
value might be then passed to the generic kernel subsystems which require
a standard kernel errno value. Even though the erroneous conditions are
very specific (memory corruption or buggy driver implementation) using a
hard-coded -1 literal doesn't seem correct anyway especially when it comes
to passing it higher to the network subsystem or printing to the system
log.  Convert the hard-coded error values to -EINVAL then.

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Tested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/pcs/pcs-xpcs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 31f0beba638a2..03d6a6aef77cd 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -293,7 +293,7 @@ static int xpcs_soft_reset(struct dw_xpcs *xpcs,
 		dev = MDIO_MMD_VEND2;
 		break;
 	default:
-		return -1;
+		return -EINVAL;
 	}
 
 	ret = xpcs_write(xpcs, dev, MDIO_CTRL1, MDIO_CTRL1_RESET);
@@ -891,7 +891,7 @@ int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface,
 			return ret;
 		break;
 	default:
-		return -1;
+		return -EINVAL;
 	}
 
 	if (compat->pma_config) {
-- 
2.43.0

[PATCH AUTOSEL 6.8 58/68] wifi: cfg80211: check A-MSDU format more carefully

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit 9ad7974856926129f190ffbe3beea78460b3b7cc ]

If it looks like there's another subframe in the A-MSDU
but the header isn't fully there, we can end up reading
data out of bounds, only to discard later. Make this a
bit more careful and check if the subframe header can
even be present.

Reported-by: syzbot+d050d437fe47d479d210@syzkaller.appspotmail.com
Link: https://msgid.link/20240226203405.a731e2c95e38.I82ce7d8c0cc8970ce29d0a39fdc07f1ffc425be4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/wireless/util.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/wireless/util.c b/net/wireless/util.c
index d1ce3bee27973..b9d15f369378b 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -791,15 +791,19 @@ ieee80211_amsdu_subframe_length(void *field, u8 mesh_flags, u8 hdr_type)
 
 bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr)
 {
-	int offset = 0, remaining, subframe_len, padding;
+	int offset = 0, subframe_len, padding;
 
 	for (offset = 0; offset < skb->len; offset += subframe_len + padding) {
+		int remaining = skb->len - offset;
 		struct {
 		    __be16 len;
 		    u8 mesh_flags;
 		} hdr;
 		u16 len;
 
+		if (sizeof(hdr) > remaining)
+			return false;
+
 		if (skb_copy_bits(skb, offset + 2 * ETH_ALEN, &hdr, sizeof(hdr)) < 0)
 			return false;
 
@@ -807,7 +811,6 @@ bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr)
 						      mesh_hdr);
 		subframe_len = sizeof(struct ethhdr) + len;
 		padding = (4 - subframe_len) & 0x3;
-		remaining = skb->len - offset;
 
 		if (subframe_len > remaining)
 			return false;
@@ -825,7 +828,7 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 {
 	unsigned int hlen = ALIGN(extra_headroom, 4);
 	struct sk_buff *frame = NULL;
-	int offset = 0, remaining;
+	int offset = 0;
 	struct {
 		struct ethhdr eth;
 		uint8_t flags;
@@ -839,10 +842,14 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 		copy_len = sizeof(hdr);
 
 	while (!last) {
+		int remaining = skb->len - offset;
 		unsigned int subframe_len;
 		int len, mesh_len = 0;
 		u8 padding;
 
+		if (copy_len > remaining)
+			goto purge;
+
 		skb_copy_bits(skb, offset, &hdr, copy_len);
 		if (iftype == NL80211_IFTYPE_MESH_POINT)
 			mesh_len = __ieee80211_get_mesh_hdrlen(hdr.flags);
@@ -852,7 +859,6 @@ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list,
 		padding = (4 - subframe_len) & 0x3;
 
 		/* the last MSDU has no padding */
-		remaining = skb->len - offset;
 		if (subframe_len > remaining)
 			goto purge;
 		/* mitigate A-MSDU aggregation injection attacks */
-- 
2.43.0

[PATCH AUTOSEL 6.8 63/68] ice: use relative VSI index for VFs instead of PF VSI number

[Sasha Levin]

From: Jacob Keller <jacob.e.keller@intel.com>

[ Upstream commit 11fbb1bfb5bc8c98b2d7db9da332b5e568f4aaab ]

When initializing over virtchnl, the PF is required to pass a VSI ID to the
VF as part of its capabilities exchange. The VF driver reports this value
back to the PF in a variety of commands. The PF driver validates that this
value matches the value it sent to the VF.

Some hardware families such as the E700 series could use this value when
reading RSS registers or communicating directly with firmware over the
Admin Queue.

However, E800 series hardware does not support any of these interfaces and
the VF's only use for this value is to report it back to the PF. Thus,
there is no requirement that this value be an actual VSI ID value of any
kind.

The PF driver already does not trust that the VF sends it a real VSI ID.
The VSI structure is always looked up from the VF structure. The PF does
validate that the VSI ID provided matches a VSI associated with the VF, but
otherwise does not use the VSI ID for any purpose.

Instead of reporting the VSI number relative to the PF space, report a
fixed value of 1. When communicating with the VF over virtchnl, validate
that the VSI number is returned appropriately.

This avoids leaking information about the firmware of the PF state.
Currently the ice driver only supplies a VF with a single VSI. However, it
appears that virtchnl has some support for allowing multiple VSIs. I did
not attempt to implement this. However, space is left open to allow further
relative indexes if additional VSIs are provided in future feature
development. For this reason, keep the ice_vc_isvalid_vsi_id function in
place to allow extending it for multiple VSIs in the future.

This change will also simplify handling of live migration in a future
series. Since we no longer will provide a real VSI number to the VF, there
will be no need to keep track of this number when migrating to a new host.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl.c | 9 ++-------
 drivers/net/ethernet/intel/ice/ice_virtchnl.h | 9 +++++++++
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 6f2328a049bf1..7b550d7d96b68 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -499,7 +499,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	vfres->rss_lut_size = ICE_LUT_VSI_SIZE;
 	vfres->max_mtu = ice_vc_get_max_frame_size(vf);
 
-	vfres->vsi_res[0].vsi_id = vf->lan_vsi_num;
+	vfres->vsi_res[0].vsi_id = ICE_VF_VSI_ID;
 	vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV;
 	vfres->vsi_res[0].num_queue_pairs = vsi->num_txq;
 	ether_addr_copy(vfres->vsi_res[0].default_mac_addr,
@@ -545,12 +545,7 @@ static void ice_vc_reset_vf_msg(struct ice_vf *vf)
  */
 bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id)
 {
-	struct ice_pf *pf = vf->pf;
-	struct ice_vsi *vsi;
-
-	vsi = ice_find_vsi(pf, vsi_id);
-
-	return (vsi && (vsi->vf == vf));
+	return vsi_id == ICE_VF_VSI_ID;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
index 60dfbe05980aa..3a41158691532 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
@@ -19,6 +19,15 @@
 #define ICE_MAX_MACADDR_PER_VF		18
 #define ICE_FLEX_DESC_RXDID_MAX_NUM	64
 
+/* VFs only get a single VSI. For ice hardware, the VF does not need to know
+ * its VSI index. However, the virtchnl interface requires a VSI number,
+ * mainly due to legacy hardware.
+ *
+ * Since the VF doesn't need this information, report a static value to the VF
+ * instead of leaking any information about the PF or hardware setup.
+ */
+#define ICE_VF_VSI_ID	1
+
 struct ice_virtchnl_ops {
 	int (*get_ver_msg)(struct ice_vf *vf, u8 *msg);
 	int (*get_vf_res_msg)(struct ice_vf *vf, u8 *msg);
-- 
2.43.0

[PATCH AUTOSEL 6.8 64/68] net/smc: reduce rtnl pressure in smc_pnet_create_pnetids_list()

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 00af2aa93b76b1bade471ad0d0525d4d29ca5cc0 ]

Many syzbot reports show extreme rtnl pressure, and many of them hint
that smc acquires rtnl in netns creation for no good reason [1]

This patch returns early from smc_pnet_net_init()
if there is no netdevice yet.

I am not even sure why smc_pnet_create_pnetids_list() even exists,
because smc_pnet_netdev_event() is also calling
smc_pnet_add_base_pnetid() when handling NETDEV_UP event.

[1] extract of typical syzbot reports

2 locks held by syz-executor.3/12252:
  #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline]
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878
2 locks held by syz-executor.4/12253:
  #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline]
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878
2 locks held by syz-executor.1/12257:
  #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline]
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878
2 locks held by syz-executor.2/12261:
  #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline]
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878
2 locks held by syz-executor.0/12265:
  #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline]
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878
2 locks held by syz-executor.3/12268:
  #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline]
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878
2 locks held by syz-executor.4/12271:
  #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline]
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878
2 locks held by syz-executor.1/12274:
  #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline]
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878
2 locks held by syz-executor.2/12280:
  #0: ffffffff8f369610 (pernet_ops_rwsem){++++}-{3:3}, at: copy_net_ns+0x4c7/0x7b0 net/core/net_namespace.c:491
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_create_pnetids_list net/smc/smc_pnet.c:809 [inline]
  #1: ffffffff8f375b88 (rtnl_mutex){+.+.}-{3:3}, at: smc_pnet_net_init+0x10a/0x1e0 net/smc/smc_pnet.c:878

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Wenjia Zhang <wenjia@linux.ibm.com>
Cc: Jan Karcher <jaka@linux.ibm.com>
Cc: "D. Wythe" <alibuda@linux.alibaba.com>
Cc: Tony Lu <tonylu@linux.alibaba.com>
Cc: Wen Gu <guwen@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Link: https://lore.kernel.org/r/20240302100744.3868021-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/smc/smc_pnet.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 9f2c58c5a86b7..2adb92b8c4699 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -806,6 +806,16 @@ static void smc_pnet_create_pnetids_list(struct net *net)
 	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
 	struct net_device *dev;
 
+	/* Newly created netns do not have devices.
+	 * Do not even acquire rtnl.
+	 */
+	if (list_empty(&net->dev_base_head))
+		return;
+
+	/* Note: This might not be needed, because smc_pnet_netdev_event()
+	 * is also calling smc_pnet_add_base_pnetid() when handling
+	 * NETDEV_UP event.
+	 */
 	rtnl_lock();
 	for_each_netdev(net, dev)
 		smc_pnet_add_base_pnetid(net, dev, ndev_pnetid);
-- 
2.43.0

[PATCH AUTOSEL 6.8 65/68] netdev: let netlink core handle -EMSGSIZE errors

[Sasha Levin]

From: Jakub Kicinski <kuba@kernel.org>

[ Upstream commit 0b11b1c5c320555483e8a94c44549db24c289987 ]

Previous change added -EMSGSIZE handling to af_netlink, we don't
have to hide these errors any longer.

Theoretically the error handling changes from:
 if (err == -EMSGSIZE)
to
 if (err == -EMSGSIZE && skb->len)

everywhere, but in practice it doesn't matter.
All messages fit into NLMSG_GOODSIZE, so overflow of an empty
skb cannot happen.

Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/netdev-genl.c    | 15 +++------------
 net/core/page_pool_user.c |  2 --
 2 files changed, 3 insertions(+), 14 deletions(-)

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index fd98936da3aec..918b109e0cf40 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -152,10 +152,7 @@ int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 	rtnl_unlock();
 
-	if (err != -EMSGSIZE)
-		return err;
-
-	return skb->len;
+	return err;
 }
 
 static int
@@ -287,10 +284,7 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 	rtnl_unlock();
 
-	if (err != -EMSGSIZE)
-		return err;
-
-	return skb->len;
+	return err;
 }
 
 static int
@@ -463,10 +457,7 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 	rtnl_unlock();
 
-	if (err != -EMSGSIZE)
-		return err;
-
-	return skb->len;
+	return err;
 }
 
 static int netdev_genl_netdevice_event(struct notifier_block *nb,
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index 278294aca66ab..3a3277ba167b1 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -103,8 +103,6 @@ netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb,
 	mutex_unlock(&page_pools_lock);
 	rtnl_unlock();
 
-	if (skb->len && err == -EMSGSIZE)
-		return skb->len;
 	return err;
 }
 
-- 
2.43.0

[PATCH AUTOSEL 6.8 68/68] Bluetooth: Add new quirk for broken read key length on ATS2851

[Sasha Levin]

From: Vinicius Peixoto <nukelet64@gmail.com>

[ Upstream commit 48201a3b3f398be6a01f78a14b18bd5d31c47458 ]

The ATS2851 controller erroneously reports support for the "Read
Encryption Key Length" HCI command. This makes it unable to connect
to any devices, since this command is issued by the kernel during the
connection process in response to an "Encryption Change" HCI event.

Add a new quirk (HCI_QUIRK_BROKEN_ENC_KEY_SIZE) to hint that the command
is unsupported, preventing it from interrupting the connection process.

This is the error log from btmon before this patch:

> HCI Event: Encryption Change (0x08) plen 4
        Status: Success (0x00)
        Handle: 2048 Address: ...
        Encryption: Enabled with E0 (0x01)
< HCI Command: Read Encryption Key Size (0x05|0x0008) plen 2
        Handle: 2048 Address: ...
> HCI Event: Command Status (0x0f) plen 4
      Read Encryption Key Size (0x05|0x0008) ncmd 1
        Status: Unknown HCI Command (0x01)

Signed-off-by: Vinicius Peixoto <nukelet64@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/bluetooth/btusb.c   | 1 +
 include/net/bluetooth/hci.h | 8 ++++++++
 net/bluetooth/hci_event.c   | 3 ++-
 3 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index d31edad7a0560..0c0e06ea92863 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -4481,6 +4481,7 @@ static int btusb_probe(struct usb_interface *intf,
 		set_bit(HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER, &hdev->quirks);
 		set_bit(HCI_QUIRK_BROKEN_SET_RPA_TIMEOUT, &hdev->quirks);
 		set_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &hdev->quirks);
+		set_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks);
 	}
 
 	if (!reset)
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index bdee5d649cc61..8c36e094ec99f 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -330,6 +330,14 @@ enum {
 	 * during the hdev->setup vendor callback.
 	 */
 	HCI_QUIRK_BROKEN_LE_CODED,
+
+	/*
+	 * When this quirk is set, the HCI_OP_READ_ENC_KEY_SIZE command is
+	 * skipped during an HCI_EV_ENCRYPT_CHANGE event. This is required
+	 * for Actions Semiconductor ATS2851 based controllers, which erroneously
+	 * claim to support it.
+	 */
+	HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE,
 };
 
 /* HCI device flags */
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 2a5f5a7d2412b..8652cdee14b00 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3660,7 +3660,8 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, void *data,
 		 * controller really supports it. If it doesn't, assume
 		 * the default size (16).
 		 */
-		if (!(hdev->commands[20] & 0x10)) {
+		if (!(hdev->commands[20] & 0x10) ||
+		    test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks)) {
 			conn->enc_key_size = HCI_LINK_KEY_SIZE;
 			goto notify;
 		}
-- 
2.43.0