Netdev List
 help / color / mirror / Atom feed
* [PATCH v2 14/15] net: phy: adin: add ethtool get_stats support
From: Alexandru Ardelean @ 2019-08-08 12:30 UTC (permalink / raw)
  To: netdev, devicetree, linux-kernel
  Cc: davem, robh+dt, mark.rutland, f.fainelli, hkallweit1, andrew,
	Alexandru Ardelean
In-Reply-To: <20190808123026.17382-1-alexandru.ardelean@analog.com>

This change implements retrieving all the error counters from the PHY.
The PHY supports several error counters/stats. The `Mean Square Errors`
status values are only valie when a link is established, and shouldn't be
accumulated. These values characterize the quality of a signal.

The rest of the error counters are self-clearing on read.
Most of them are reports from the Frame Checker engine that the PHY has.

Not retrieving the `LPI Wake Error Count Register` here, since that is used
by the PHY framework to check for any EEE errors. And that register is
self-clearing when read (as per IEEE spec).

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
---
 drivers/net/phy/adin.c | 109 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 109 insertions(+)

diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index d6d1f5037eb7..d170d1e837b5 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -155,12 +155,40 @@ static struct adin_clause45_mmd_map adin_clause45_mmd_map[] = {
 	{ MDIO_MMD_PCS, MDIO_PCS_EEE_WK_ERR,	ADIN1300_LPI_WAKE_ERR_CNT_REG },
 };
 
+struct adin_hw_stat {
+	const char *string;
+	u16 reg1;
+	u16 reg2;
+	bool do_not_accumulate;
+};
+
+/* Named just like in the datasheet */
+static struct adin_hw_stat adin_hw_stats[] = {
+	{ "RxErrCnt",		0x0014,	},
+	{ "MseA",		0x8402,	0,	true },
+	{ "MseB",		0x8403,	0,	true },
+	{ "MseC",		0x8404,	0,	true },
+	{ "MseD",		0x8405,	0,	true },
+	{ "FcFrmCnt",		0x940A, 0x940B }, /* FcFrmCntH + FcFrmCntL */
+	{ "FcLenErrCnt",	0x940C },
+	{ "FcAlgnErrCnt",	0x940D },
+	{ "FcSymbErrCnt",	0x940E },
+	{ "FcOszCnt",		0x940F },
+	{ "FcUszCnt",		0x9410 },
+	{ "FcOddCnt",		0x9411 },
+	{ "FcOddPreCnt",	0x9412 },
+	{ "FcDribbleBitsCnt",	0x9413 },
+	{ "FcFalseCarrierCnt",	0x9414 },
+};
+
 /**
  * struct adin_priv - ADIN PHY driver private data
  * edpd_enabled		true if Energy Detect Powerdown mode is enabled
+ * stats		statistic counters for the PHY
  */
 struct adin_priv {
 	bool			edpd_enabled;
+	u64			stats[ARRAY_SIZE(adin_hw_stats)];
 };
 
 static int adin_lookup_reg_value(const struct adin_cfg_reg_map *tbl, int cfg)
@@ -561,6 +589,81 @@ static int adin_reset(struct phy_device *phydev)
 	return adin_subsytem_soft_reset(phydev);
 }
 
+static int adin_get_sset_count(struct phy_device *phydev)
+{
+	return ARRAY_SIZE(adin_hw_stats);
+}
+
+static void adin_get_strings(struct phy_device *phydev, u8 *data)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(adin_hw_stats); i++) {
+		strlcpy(&data[i * ETH_GSTRING_LEN],
+			adin_hw_stats[i].string, ETH_GSTRING_LEN);
+	}
+}
+
+static int adin_read_mmd_stat_regs(struct phy_device *phydev,
+				   struct adin_hw_stat *stat,
+				   u32 *val)
+{
+	int ret;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, stat->reg1);
+	if (ret < 0)
+		return ret;
+
+	*val = (ret & 0xffff);
+
+	if (stat->reg2 == 0)
+		return 0;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, stat->reg2);
+	if (ret < 0)
+		return ret;
+
+	*val <<= 16;
+	*val |= (ret & 0xffff);
+
+	return 0;
+}
+
+static u64 adin_get_stat(struct phy_device *phydev, int i)
+{
+	struct adin_hw_stat *stat = &adin_hw_stats[i];
+	struct adin_priv *priv = phydev->priv;
+	u32 val;
+	int ret;
+
+	if (stat->reg1 > 0x1f) {
+		ret = adin_read_mmd_stat_regs(phydev, stat, &val);
+		if (ret < 0)
+			return (u64)(~0);
+	} else {
+		ret = phy_read(phydev, stat->reg1);
+		if (ret < 0)
+			return (u64)(~0);
+		val = (ret & 0xffff);
+	}
+
+	if (stat->do_not_accumulate)
+		priv->stats[i] = val;
+	else
+		priv->stats[i] += val;
+
+	return priv->stats[i];
+}
+
+static void adin_get_stats(struct phy_device *phydev,
+			   struct ethtool_stats *stats, u64 *data)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(adin_hw_stats); i++)
+		data[i] = adin_get_stat(phydev, i);
+}
+
 static int adin_probe(struct phy_device *phydev)
 {
 	struct device *dev = &phydev->mdio.dev;
@@ -588,6 +691,9 @@ static struct phy_driver adin_driver[] = {
 		.get_features	= genphy_read_abilities,
 		.ack_interrupt	= adin_phy_ack_intr,
 		.config_intr	= adin_phy_config_intr,
+		.get_sset_count	= adin_get_sset_count,
+		.get_strings	= adin_get_strings,
+		.get_stats	= adin_get_stats,
 		.resume		= genphy_resume,
 		.suspend	= genphy_suspend,
 		.read_mmd	= adin_read_mmd,
@@ -603,6 +709,9 @@ static struct phy_driver adin_driver[] = {
 		.get_features	= genphy_read_abilities,
 		.ack_interrupt	= adin_phy_ack_intr,
 		.config_intr	= adin_phy_config_intr,
+		.get_sset_count	= adin_get_sset_count,
+		.get_strings	= adin_get_strings,
+		.get_stats	= adin_get_stats,
 		.resume		= genphy_resume,
 		.suspend	= genphy_suspend,
 		.read_mmd	= adin_read_mmd,
-- 
2.20.1


^ permalink raw reply related

* [PATCH v2 12/15] net: phy: adin: implement Energy Detect Powerdown mode
From: Alexandru Ardelean @ 2019-08-08 12:30 UTC (permalink / raw)
  To: netdev, devicetree, linux-kernel
  Cc: davem, robh+dt, mark.rutland, f.fainelli, hkallweit1, andrew,
	Alexandru Ardelean
In-Reply-To: <20190808123026.17382-1-alexandru.ardelean@analog.com>

The ADIN PHYs support Energy Detect Powerdown mode, which puts the PHY into
a low power mode when there is no signal on the wire (typically cable
unplugged).
This behavior is enabled by default, but can be disabled via device
property.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
---
 drivers/net/phy/adin.c | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index f276d692bdee..bc4393195de7 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -24,6 +24,11 @@
 #define   ADIN1300_AUTO_MDI_EN			BIT(10)
 #define   ADIN1300_MAN_MDIX_EN			BIT(9)
 
+#define ADIN1300_PHY_CTRL_STATUS2		0x0015
+#define   ADIN1300_NRG_PD_EN			BIT(3)
+#define   ADIN1300_NRG_PD_TX_EN			BIT(2)
+#define   ADIN1300_NRG_PD_STATUS		BIT(1)
+
 #define ADIN1300_INT_MASK_REG			0x0018
 #define   ADIN1300_INT_MDIO_SYNC_EN		BIT(9)
 #define   ADIN1300_INT_ANEG_STAT_CHNG_EN	BIT(8)
@@ -138,6 +143,14 @@ static struct adin_clause45_mmd_map adin_clause45_mmd_map[] = {
 	{ MDIO_MMD_PCS, MDIO_PCS_EEE_WK_ERR,	ADIN1300_LPI_WAKE_ERR_CNT_REG },
 };
 
+/**
+ * struct adin_priv - ADIN PHY driver private data
+ * edpd_enabled		true if Energy Detect Powerdown mode is enabled
+ */
+struct adin_priv {
+	bool			edpd_enabled;
+};
+
 static int adin_lookup_reg_value(const struct adin_cfg_reg_map *tbl, int cfg)
 {
 	size_t i;
@@ -246,6 +259,18 @@ static int adin_config_rmii_mode(struct phy_device *phydev)
 			     ADIN1300_GE_RMII_CFG_REG, reg);
 }
 
+static int adin_config_init_edpd(struct phy_device *phydev)
+{
+	struct adin_priv *priv = phydev->priv;
+
+	if (priv->edpd_enabled)
+		return phy_set_bits(phydev, ADIN1300_PHY_CTRL_STATUS2,
+				(ADIN1300_NRG_PD_EN | ADIN1300_NRG_PD_TX_EN));
+
+	return phy_clear_bits(phydev, ADIN1300_PHY_CTRL_STATUS2,
+			(ADIN1300_NRG_PD_EN | ADIN1300_NRG_PD_TX_EN));
+}
+
 static int adin_config_init(struct phy_device *phydev)
 {
 	int rc;
@@ -264,6 +289,10 @@ static int adin_config_init(struct phy_device *phydev)
 	if (rc < 0)
 		return rc;
 
+	rc = adin_config_init_edpd(phydev);
+	if (rc < 0)
+		return rc;
+
 	phydev_dbg(phydev, "PHY is using mode '%s'\n",
 		   phy_modes(phydev->interface));
 
@@ -495,6 +524,17 @@ static int adin_reset(struct phy_device *phydev)
 
 static int adin_probe(struct phy_device *phydev)
 {
+	struct device *dev = &phydev->mdio.dev;
+	struct adin_priv *priv;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->edpd_enabled =
+		device_property_read_bool(dev, "adi,disable-energy-detect");
+	phydev->priv = priv;
+
 	return adin_reset(phydev);
 }
 
-- 
2.20.1


^ permalink raw reply related

* [PATCH v2 11/15] net: phy: adin: implement PHY subsystem software reset
From: Alexandru Ardelean @ 2019-08-08 12:30 UTC (permalink / raw)
  To: netdev, devicetree, linux-kernel
  Cc: davem, robh+dt, mark.rutland, f.fainelli, hkallweit1, andrew,
	Alexandru Ardelean
In-Reply-To: <20190808123026.17382-1-alexandru.ardelean@analog.com>

The ADIN PHYs supports 4 types of reset:
1. The standard PHY reset via BMCR_RESET bit in MII_BMCR reg
2. Reset via GPIO
3. Reset via reg GeSftRst (0xff0c) & reload previous pin configs
4. Reset via reg GeSftRst (0xff0c) & request new pin configs

Resets 2 & 4 are almost identical, with the exception that the crystal
oscillator is available during reset for 2.

As it turns out, phylib already supports GPIO reset.
In case this is configured, the PHY driver won't do anything. In case it
isn't specified the subsystem software reset will kick in.

Resetting via GeSftRst or via GPIO is useful when doing a warm reboot,
because this will reset the subsystem registers to default values.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
---
 drivers/net/phy/adin.c | 43 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index c1cea1b6bd75..f276d692bdee 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -6,6 +6,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/bitfield.h>
+#include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -53,6 +54,9 @@
 #define ADIN1300_CLOCK_STOP_REG			0x9400
 #define ADIN1300_LPI_WAKE_ERR_CNT_REG		0xa000
 
+#define ADIN1300_GE_SOFT_RESET_REG		0xff0c
+#define   ADIN1300_GE_SOFT_RESET		BIT(0)
+
 #define ADIN1300_GE_RGMII_CFG_REG		0xff23
 #define   ADIN1300_GE_RGMII_RX_MSK		GENMASK(8, 6)
 #define   ADIN1300_GE_RGMII_RX_SEL(x)		\
@@ -457,11 +461,49 @@ static int adin_read_status(struct phy_device *phydev)
 	return genphy_read_status(phydev);
 }
 
+static int adin_subsytem_soft_reset(struct phy_device *phydev)
+{
+	int reg, rc, i;
+
+	rc = phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+			      ADIN1300_GE_SOFT_RESET_REG,
+			      ADIN1300_GE_SOFT_RESET);
+	if (rc < 0)
+		return rc;
+
+	for (i = 0; i < 20; i++) {
+		usleep_range(500, 1000);
+		reg = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				   ADIN1300_GE_SOFT_RESET_REG);
+		if (reg < 0 || (reg & ADIN1300_GE_SOFT_RESET))
+			continue;
+		return 0;
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int adin_reset(struct phy_device *phydev)
+{
+	/* If there is a reset GPIO just exit */
+	if (!IS_ERR_OR_NULL(phydev->mdio.reset_gpio))
+		return 0;
+
+	/* Reset PHY core regs & subsystem regs */
+	return adin_subsytem_soft_reset(phydev);
+}
+
+static int adin_probe(struct phy_device *phydev)
+{
+	return adin_reset(phydev);
+}
+
 static struct phy_driver adin_driver[] = {
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_ADIN1200),
 		.name		= "ADIN1200",
 		.config_init	= adin_config_init,
+		.probe		= adin_probe,
 		.config_aneg	= adin_config_aneg,
 		.read_status	= adin_read_status,
 		.get_features	= genphy_read_abilities,
@@ -476,6 +518,7 @@ static struct phy_driver adin_driver[] = {
 		PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300),
 		.name		= "ADIN1300",
 		.config_init	= adin_config_init,
+		.probe		= adin_probe,
 		.config_aneg	= adin_config_aneg,
 		.read_status	= adin_read_status,
 		.get_features	= genphy_read_abilities,
-- 
2.20.1


^ permalink raw reply related

* [PATCH v2 09/15] net: phy: adin: add support MDI/MDIX/Auto-MDI selection
From: Alexandru Ardelean @ 2019-08-08 12:30 UTC (permalink / raw)
  To: netdev, devicetree, linux-kernel
  Cc: davem, robh+dt, mark.rutland, f.fainelli, hkallweit1, andrew,
	Alexandru Ardelean
In-Reply-To: <20190808123026.17382-1-alexandru.ardelean@analog.com>

The ADIN PHYs support automatic MDI/MDIX negotiation. By default this is
disabled, so this is enabled at `config_init`.

This is controlled via the PHY Control 1 register.
The supported modes are:
  1. Manual MDI
  2. Manual MDIX
  3. Auto MDIX - prefer MDIX
  4. Auto MDIX - prefer MDI

The phydev mdix & mdix_ctrl fields include modes 3 & 4 into a single
auto-mode. So, the default mode this driver enables is 4 when Auto-MDI mode
is used.

When detecting MDI/MDIX mode, a combination of the PHY Control 1 register
and PHY Status 1 register is used to determine the correct MDI/MDIX mode.

If Auto-MDI mode is not set, then the manual MDI/MDIX mode is returned.
If Auto-MDI mode is set, then MDIX mode is returned differs from the
preferred MDI/MDIX mode.
This covers all cases where:
  1. MDI preferred  & Pair01Swapped   == MDIX
  2. MDIX preferred & Pair01Swapped   == MDI
  3. MDI preferred  & ! Pair01Swapped == MDIX
  4. MDIX preferred & ! Pair01Swapped == MDI

The preferred MDI/MDIX mode is not configured via SW, but can be configured
via HW pins. Note that the `Pair01Swapped` is the Green-Yellow physical
pairs.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
---
 drivers/net/phy/adin.c | 117 +++++++++++++++++++++++++++++++++++++++--
 1 file changed, 113 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index 26b2f2b21596..69ef53bbecc3 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -19,6 +19,10 @@
 #define ADIN1300_MII_EXT_REG_PTR		0x0010
 #define ADIN1300_MII_EXT_REG_DATA		0x0011
 
+#define ADIN1300_PHY_CTRL1			0x0012
+#define   ADIN1300_AUTO_MDI_EN			BIT(10)
+#define   ADIN1300_MAN_MDIX_EN			BIT(9)
+
 #define ADIN1300_INT_MASK_REG			0x0018
 #define   ADIN1300_INT_MDIO_SYNC_EN		BIT(9)
 #define   ADIN1300_INT_ANEG_STAT_CHNG_EN	BIT(8)
@@ -35,6 +39,9 @@
 	 ADIN1300_INT_HW_IRQ_EN)
 #define ADIN1300_INT_STATUS_REG			0x0019
 
+#define ADIN1300_PHY_STATUS1			0x001a
+#define   ADIN1300_PAIR_01_SWAP			BIT(11)
+
 #define ADIN1300_GE_RGMII_CFG_REG		0xff23
 #define   ADIN1300_GE_RGMII_RX_MSK		GENMASK(8, 6)
 #define   ADIN1300_GE_RGMII_RX_SEL(x)		\
@@ -208,6 +215,8 @@ static int adin_config_init(struct phy_device *phydev)
 {
 	int rc;
 
+	phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
+
 	rc = genphy_config_init(phydev);
 	if (rc < 0)
 		return rc;
@@ -283,13 +292,113 @@ static int adin_write_mmd(struct phy_device *phydev, int devad, u16 regnum,
 	return __mdiobus_write(bus, phy_addr, ADIN1300_MII_EXT_REG_DATA, val);
 }
 
+static int adin_config_mdix(struct phy_device *phydev)
+{
+	bool auto_en, mdix_en;
+	int reg;
+
+	mdix_en = false;
+	auto_en = false;
+	switch (phydev->mdix_ctrl) {
+	case ETH_TP_MDI:
+		break;
+	case ETH_TP_MDI_X:
+		mdix_en = true;
+		break;
+	case ETH_TP_MDI_AUTO:
+		auto_en = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	reg = phy_read(phydev, ADIN1300_PHY_CTRL1);
+	if (reg < 0)
+		return reg;
+
+	if (mdix_en)
+		reg |= ADIN1300_MAN_MDIX_EN;
+	else
+		reg &= ~ADIN1300_MAN_MDIX_EN;
+
+	if (auto_en)
+		reg |= ADIN1300_AUTO_MDI_EN;
+	else
+		reg &= ~ADIN1300_AUTO_MDI_EN;
+
+	return phy_write(phydev, ADIN1300_PHY_CTRL1, reg);
+}
+
+static int adin_config_aneg(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = adin_config_mdix(phydev);
+	if (ret)
+		return ret;
+
+	return genphy_config_aneg(phydev);
+}
+
+static int adin_mdix_update(struct phy_device *phydev)
+{
+	bool auto_en, mdix_en;
+	bool swapped;
+	int reg;
+
+	reg = phy_read(phydev, ADIN1300_PHY_CTRL1);
+	if (reg < 0)
+		return reg;
+
+	auto_en = !!(reg & ADIN1300_AUTO_MDI_EN);
+	mdix_en = !!(reg & ADIN1300_MAN_MDIX_EN);
+
+	/* If MDI/MDIX is forced, just read it from the control reg */
+	if (!auto_en) {
+		if (mdix_en)
+			phydev->mdix = ETH_TP_MDI_X;
+		else
+			phydev->mdix = ETH_TP_MDI;
+		return 0;
+	}
+
+	/**
+	 * Otherwise, we need to deduce it from the PHY status2 reg.
+	 * When Auto-MDI is enabled, the ADIN1300_MAN_MDIX_EN bit implies
+	 * a preference for MDIX when it is set.
+	 */
+	reg = phy_read(phydev, ADIN1300_PHY_STATUS1);
+	if (reg < 0)
+		return reg;
+
+	swapped = !!(reg & ADIN1300_PAIR_01_SWAP);
+
+	if (mdix_en != swapped)
+		phydev->mdix = ETH_TP_MDI_X;
+	else
+		phydev->mdix = ETH_TP_MDI;
+
+	return 0;
+}
+
+static int adin_read_status(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = adin_mdix_update(phydev);
+	if (ret < 0)
+		return ret;
+
+	return genphy_read_status(phydev);
+}
+
 static struct phy_driver adin_driver[] = {
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_ADIN1200),
 		.name		= "ADIN1200",
 		.config_init	= adin_config_init,
-		.config_aneg	= genphy_config_aneg,
-		.read_status	= genphy_read_status,
+		.config_aneg	= adin_config_aneg,
+		.read_status	= adin_read_status,
 		.get_features	= genphy_read_abilities,
 		.ack_interrupt	= adin_phy_ack_intr,
 		.config_intr	= adin_phy_config_intr,
@@ -302,8 +411,8 @@ static struct phy_driver adin_driver[] = {
 		PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300),
 		.name		= "ADIN1300",
 		.config_init	= adin_config_init,
-		.config_aneg	= genphy_config_aneg,
-		.read_status	= genphy_read_status,
+		.config_aneg	= adin_config_aneg,
+		.read_status	= adin_read_status,
 		.get_features	= genphy_read_abilities,
 		.ack_interrupt	= adin_phy_ack_intr,
 		.config_intr	= adin_phy_config_intr,
-- 
2.20.1


^ permalink raw reply related

* [PATCH v2 08/15] net: phy: adin: make RMII fifo depth configurable
From: Alexandru Ardelean @ 2019-08-08 12:30 UTC (permalink / raw)
  To: netdev, devicetree, linux-kernel
  Cc: davem, robh+dt, mark.rutland, f.fainelli, hkallweit1, andrew,
	Alexandru Ardelean
In-Reply-To: <20190808123026.17382-1-alexandru.ardelean@analog.com>

The FIFO depth can be configured for the RMII mode. This change adds
support for doing this via device-tree (or ACPI).

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
---
 drivers/net/phy/adin.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index 62c1268e55f7..26b2f2b21596 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -54,8 +54,19 @@
 #define	ADIN1300_RGMII_2_40_NS			0x0007
 
 #define ADIN1300_GE_RMII_CFG_REG		0xff24
+#define   ADIN1300_GE_RMII_FIFO_DEPTH_MSK	GENMASK(6, 4)
+#define   ADIN1300_GE_RMII_FIFO_DEPTH_SEL(x)	\
+		FIELD_PREP(ADIN1300_GE_RMII_FIFO_DEPTH_MSK, x)
 #define   ADIN1300_GE_RMII_EN			BIT(0)
 
+/* RMII fifo depth values */
+#define ADIN1300_RMII_4_BITS			0x0000
+#define ADIN1300_RMII_8_BITS			0x0001
+#define ADIN1300_RMII_12_BITS			0x0002
+#define ADIN1300_RMII_16_BITS			0x0003
+#define ADIN1300_RMII_20_BITS			0x0004
+#define ADIN1300_RMII_24_BITS			0x0005
+
 /**
  * struct adin_cfg_reg_map - map a config value to aregister value
  * @cfg		value in device configuration
@@ -75,6 +86,16 @@ static const struct adin_cfg_reg_map adin_rgmii_delays[] = {
 	{ },
 };
 
+static const struct adin_cfg_reg_map adin_rmii_fifo_depths[] = {
+	{ 4,  ADIN1300_RMII_4_BITS },
+	{ 8,  ADIN1300_RMII_8_BITS },
+	{ 12, ADIN1300_RMII_12_BITS },
+	{ 16, ADIN1300_RMII_16_BITS },
+	{ 20, ADIN1300_RMII_20_BITS },
+	{ 24, ADIN1300_RMII_24_BITS },
+	{ },
+};
+
 static int adin_lookup_reg_value(const struct adin_cfg_reg_map *tbl, int cfg)
 {
 	size_t i;
@@ -158,6 +179,7 @@ static int adin_config_rgmii_mode(struct phy_device *phydev)
 
 static int adin_config_rmii_mode(struct phy_device *phydev)
 {
+	u32 val;
 	int reg;
 
 	if (phydev->interface != PHY_INTERFACE_MODE_RMII)
@@ -171,6 +193,13 @@ static int adin_config_rmii_mode(struct phy_device *phydev)
 
 	reg |= ADIN1300_GE_RMII_EN;
 
+	val = adin_get_reg_value(phydev, "adi,fifo-depth-bits",
+				 adin_rmii_fifo_depths,
+				 ADIN1300_RMII_8_BITS);
+
+	reg &= ~ADIN1300_GE_RMII_FIFO_DEPTH_MSK;
+	reg |= ADIN1300_GE_RMII_FIFO_DEPTH_SEL(val);
+
 	return phy_write_mmd(phydev, MDIO_MMD_VEND1,
 			     ADIN1300_GE_RMII_CFG_REG, reg);
 }
-- 
2.20.1


^ permalink raw reply related

* [PATCH v2 05/15] net: phy: adin: add {write,read}_mmd hooks
From: Alexandru Ardelean @ 2019-08-08 12:30 UTC (permalink / raw)
  To: netdev, devicetree, linux-kernel
  Cc: davem, robh+dt, mark.rutland, f.fainelli, hkallweit1, andrew,
	Alexandru Ardelean
In-Reply-To: <20190808123026.17382-1-alexandru.ardelean@analog.com>

Both ADIN1200 & ADIN1300 support Clause 45 access.
The Extended Management Interface (EMI) registers are accessible via both
Clause 45 (at register MDIO_MMD_VEND1) and using Clause 22.

However, the Clause 22 MMD access operations differ from the implementation
in the kernel, in the sense that it uses registers ExtRegPtr (0x10) &
ExtRegData (0x11) to access Clause 45 & EMI registers.

The indirect access is done via the following mechanism (for both R/W):
1. Write the address of the register in the ExtRegPtr
2. Read/write the value of the register (written at ExtRegPtr)

This mechanism is needed to manage configuration of chip settings and to
access EEE registers (via Clause 22).

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
---
 drivers/net/phy/adin.c | 46 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index 69000fb16704..a833e329be6f 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -14,6 +14,9 @@
 #define PHY_ID_ADIN1200				0x0283bc20
 #define PHY_ID_ADIN1300				0x0283bc30
 
+#define ADIN1300_MII_EXT_REG_PTR		0x0010
+#define ADIN1300_MII_EXT_REG_DATA		0x0011
+
 #define ADIN1300_INT_MASK_REG			0x0018
 #define   ADIN1300_INT_MDIO_SYNC_EN		BIT(9)
 #define   ADIN1300_INT_ANEG_STAT_CHNG_EN	BIT(8)
@@ -53,6 +56,45 @@ static int adin_phy_config_intr(struct phy_device *phydev)
 			      ADIN1300_INT_MASK_EN);
 }
 
+static int adin_read_mmd(struct phy_device *phydev, int devad, u16 regnum)
+{
+	struct mii_bus *bus = phydev->mdio.bus;
+	int phy_addr = phydev->mdio.addr;
+	int err;
+
+	if (phydev->is_c45) {
+		u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff);
+
+		return __mdiobus_read(bus, phy_addr, addr);
+	}
+
+	err = __mdiobus_write(bus, phy_addr, ADIN1300_MII_EXT_REG_PTR, regnum);
+	if (err)
+		return err;
+
+	return __mdiobus_read(bus, phy_addr, ADIN1300_MII_EXT_REG_DATA);
+}
+
+static int adin_write_mmd(struct phy_device *phydev, int devad, u16 regnum,
+			  u16 val)
+{
+	struct mii_bus *bus = phydev->mdio.bus;
+	int phy_addr = phydev->mdio.addr;
+	int err;
+
+	if (phydev->is_c45) {
+		u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff);
+
+		return __mdiobus_write(bus, phy_addr, addr, val);
+	}
+
+	err = __mdiobus_write(bus, phy_addr, ADIN1300_MII_EXT_REG_PTR, regnum);
+	if (err)
+		return err;
+
+	return __mdiobus_write(bus, phy_addr, ADIN1300_MII_EXT_REG_DATA, val);
+}
+
 static struct phy_driver adin_driver[] = {
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_ADIN1200),
@@ -65,6 +107,8 @@ static struct phy_driver adin_driver[] = {
 		.config_intr	= adin_phy_config_intr,
 		.resume		= genphy_resume,
 		.suspend	= genphy_suspend,
+		.read_mmd	= adin_read_mmd,
+		.write_mmd	= adin_write_mmd,
 	},
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300),
@@ -77,6 +121,8 @@ static struct phy_driver adin_driver[] = {
 		.config_intr	= adin_phy_config_intr,
 		.resume		= genphy_resume,
 		.suspend	= genphy_suspend,
+		.read_mmd	= adin_read_mmd,
+		.write_mmd	= adin_write_mmd,
 	},
 };
 
-- 
2.20.1


^ permalink raw reply related

* [PATCH v2 02/15] net: phy: adin: hook genphy_read_abilities() to get_features
From: Alexandru Ardelean @ 2019-08-08 12:30 UTC (permalink / raw)
  To: netdev, devicetree, linux-kernel
  Cc: davem, robh+dt, mark.rutland, f.fainelli, hkallweit1, andrew,
	Alexandru Ardelean
In-Reply-To: <20190808123026.17382-1-alexandru.ardelean@analog.com>

The ADIN PHYs can operate with Clause 45, however they are not typical for
how phylib considers Clause 45 PHYs.

If the `features` field & the `get_features` hook are unspecified, and the
device wants to operate via Clause 45, it would also try to read features
via the `genphy_c45_pma_read_abilities()`, which will try to read PMA regs
that are unsupported.

Hooking the `genphy_read_abilities()` function to the `get_features` hook
will ensure that this does not happen and the PHY features are read
correctly regardless of Clause 22 or Clause 45 operation.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
---
 drivers/net/phy/adin.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index 6d7af4743957..879797d076e0 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -26,6 +26,7 @@ static struct phy_driver adin_driver[] = {
 		.config_init	= adin_config_init,
 		.config_aneg	= genphy_config_aneg,
 		.read_status	= genphy_read_status,
+		.get_features	= genphy_read_abilities,
 	},
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300),
@@ -33,6 +34,7 @@ static struct phy_driver adin_driver[] = {
 		.config_init	= adin_config_init,
 		.config_aneg	= genphy_config_aneg,
 		.read_status	= genphy_read_status,
+		.get_features	= genphy_read_abilities,
 	},
 };
 
-- 
2.20.1


^ permalink raw reply related

* [PATCH v2 00/15] net: phy: adin: add support for Analog Devices PHYs
From: Alexandru Ardelean @ 2019-08-08 12:30 UTC (permalink / raw)
  To: netdev, devicetree, linux-kernel
  Cc: davem, robh+dt, mark.rutland, f.fainelli, hkallweit1, andrew,
	Alexandru Ardelean

This changeset adds support for Analog Devices Industrial Ethernet PHYs.
Particularly the PHYs this driver adds support for:
 * ADIN1200 - Robust, Industrial, Low Power 10/100 Ethernet PHY
 * ADIN1300 - Robust, Industrial, Low Latency 10/100/1000 Gigabit
   Ethernet PHY

The 2 chips are pin & register compatible with one another. The main
difference being that ADIN1200 doesn't operate in gigabit mode.

The chips can be operated by the Generic PHY driver as well via the
standard IEEE PHY registers (0x0000 - 0x000F) which are supported by the
kernel as well. This assumes that configuration of the PHY has been done
completely in HW, according to spec, i.e. no extra SW configuration
required.

This changeset also implements the ability to configure the chips via SW
registers.

Datasheets:
  https://www.analog.com/media/en/technical-documentation/data-sheets/ADIN1300.pdf
  https://www.analog.com/media/en/technical-documentation/data-sheets/ADIN1200.pdf

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>

Alexandru Ardelean (15):
  net: phy: adin: add support for Analog Devices PHYs
  net: phy: adin: hook genphy_read_abilities() to get_features
  net: phy: adin: hook genphy_{suspend,resume} into the driver
  net: phy: adin: add support for interrupts
  net: phy: adin: add {write,read}_mmd hooks
  net: phy: adin: configure RGMII/RMII/MII modes on config
  net: phy: adin: make RGMII internal delays configurable
  net: phy: adin: make RMII fifo depth configurable
  net: phy: adin: add support MDI/MDIX/Auto-MDI selection
  net: phy: adin: add EEE translation layer from Clause 45 to Clause 22
  net: phy: adin: implement PHY subsystem software reset
  net: phy: adin: implement Energy Detect Powerdown mode
  net: phy: adin: configure downshift on config_init
  net: phy: adin: add ethtool get_stats support
  dt-bindings: net: add bindings for ADIN PHY driver

 .../devicetree/bindings/net/adi,adin.yaml     |  76 ++
 MAINTAINERS                                   |   8 +
 drivers/net/phy/Kconfig                       |   9 +
 drivers/net/phy/Makefile                      |   1 +
 drivers/net/phy/adin.c                        | 732 ++++++++++++++++++
 5 files changed, 826 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/adi,adin.yaml
 create mode 100644 drivers/net/phy/adin.c

-- 


Changelog v1 -> v2:
[ patch numbers are from v1 ]

* patch 01/16: net: phy: adin: add support for Analog Devices PHYs
   - return genphy_config_init() directly
   - remove `features` field; the ADIN1200/ADIN1300 support the standard IEEE regs
     for reading link caps
   - use PHY_ID_MATCH_MODEL() macro in `adin_tbl` and `adin_driver` tables
* added new patch: net: phy: adin: hook genphy_read_abilities() to get_features
   - this hooks the genphy_read_abilities() to `get_features` hook to make sure
     that features are initialized correctly
* patch 03/16: net: phy: adin: add support for interrupts
   - removed deprecated `.flags = PHY_HAS_INTERRUPT,`
   - compress return code in `adin_phy_ack_intr()`
* patch 04/16: net: phy: adin: add {write,read}_mmd hooks
   - changed reg-style to 4 digit format; it was the only place where this was
     inconsistent
* patch 05/16: net: phy: adin: configure RGMII/RMII/MII modes on config
   - removed `goto` statements; used `phy_clear_bits_mmd()` for clean
     disable-n-exit path
   - dev_info -> phydev_dbg
   - fixed `phy_interface_t` type conversion for rc; reverted back to `int` in 
     `genphy_config_init()`
   - added missing space in commit description
     `For RGMII with internal delays (modes RGMII_ID, RGMII_TXID, RGMII_RXID)`
   - overall: things have been simplified since this no longer needs to account
     for `phy-mode-internal` thingi/patch
* dropped: patch 06/16: net: phy: adin: support PHY mode converters
* patch 07/16: net: phy: adin: make RGMII internal delays configurable
   - changed mechanism, to specify delays in pico-seconds and convert them
     to register values; mechanism will be used for RMII fifo depth as well
   - fixed masking bug for internal delays when reworking this mechanism
   - changed DT props `adi,{rx,tx}-internal-delay` -> `adi,{rx,tx}-internal-delay-ps`
* patch 08/16: net: phy: adin: make RMII fifo depth configurable
   - using same mechanism to access access RMII fifo depth bits
   - changed DT prop `adi,fifo-depth` -> `adi,fifo-depth-bits`
* patch 10/16: net: phy: adin: add EEE translation layer for Clause 22
   - use `phydev_err` instead of `pr_err()` in `adin_cl22_to_adin_reg()` helper
   - renamed types from cl22 -> cl45 or clause22 -> clause45; the translation
     is from Clause 45 to Clause 22 indirect access
* patch 11/16: net: phy: adin: PHY reset mechanisms
   - dropped GPIO logic; using phylib's
   - doing SW subsystem reset if there is no reset GPIO defined via phylib
* dropped: patch 12/16: net: phy: adin: read EEE setting from device-tree
* patch 14/16: net: phy: adin: make sure down-speed auto-neg is enabled
   - use `phy_set_bits` to enable/disable down-speed
   - implemented downshift similar to marvell driver; also configuring
     num-speed retries
* patch 15/16:  net: phy: adin: add ethtool get_stats support
   - changed `do_not_inc` -> `do_not_accumulate`
   - in commit comment: `incremented` -> `accumulated`
   - use `strlcpy()` instead of `memcpy()` for get_stats
* patch 16/16: dt-bindings: net: add bindings for ADIN PHY driver
   - updated bindings with all stuff that was left in the driver; some things
     went away (like reset-gpio)
   - implemented Rob's suggestions

2.20.1


^ permalink raw reply

* [PATCH v2 01/15] net: phy: adin: add support for Analog Devices PHYs
From: Alexandru Ardelean @ 2019-08-08 12:30 UTC (permalink / raw)
  To: netdev, devicetree, linux-kernel
  Cc: davem, robh+dt, mark.rutland, f.fainelli, hkallweit1, andrew,
	Alexandru Ardelean
In-Reply-To: <20190808123026.17382-1-alexandru.ardelean@analog.com>

This change adds support for Analog Devices Industrial Ethernet PHYs.
Particularly the PHYs this driver adds support for:
 * ADIN1200 - Robust, Industrial, Low Power 10/100 Ethernet PHY
 * ADIN1300 - Robust, Industrial, Low Latency 10/100/1000 Gigabit
   Ethernet PHY

The 2 chips are pin & register compatible with one another. The main
difference being that ADIN1200 doesn't operate in gigabit mode.

The chips can be operated by the Generic PHY driver as well via the
standard IEEE PHY registers (0x0000 - 0x000F) which are supported by the
kernel as well. This assumes that configuration of the PHY has been done
completely in HW, according to spec.

Configuration can also be done via registers, which will be supported by
this driver.

Datasheets:
  https://www.analog.com/media/en/technical-documentation/data-sheets/ADIN1300.pdf
  https://www.analog.com/media/en/technical-documentation/data-sheets/ADIN1200.pdf

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
---
 MAINTAINERS              |  7 ++++++
 drivers/net/phy/Kconfig  |  9 ++++++++
 drivers/net/phy/Makefile |  1 +
 drivers/net/phy/adin.c   | 49 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 66 insertions(+)
 create mode 100644 drivers/net/phy/adin.c

diff --git a/MAINTAINERS b/MAINTAINERS
index e352550a6895..e8aa8a667864 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -938,6 +938,13 @@ S:	Supported
 F:	drivers/mux/adgs1408.c
 F:	Documentation/devicetree/bindings/mux/adi,adgs1408.txt
 
+ANALOG DEVICES INC ADIN DRIVER
+M:	Alexandru Ardelean <alexaundru.ardelean@analog.com>
+L:	netdev@vger.kernel.org
+W:	http://ez.analog.com/community/linux-device-drivers
+S:	Supported
+F:	drivers/net/phy/adin.c
+
 ANALOG DEVICES INC ADIS DRIVER LIBRARY
 M:	Alexandru Ardelean <alexandru.ardelean@analog.com>
 S:	Supported
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 48ca213c0ada..03be30cde552 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -257,6 +257,15 @@ config SFP
 	depends on HWMON || HWMON=n
 	select MDIO_I2C
 
+config ADIN_PHY
+	tristate "Analog Devices Industrial Ethernet PHYs"
+	help
+	  Adds support for the Analog Devices Industrial Ethernet PHYs.
+	  Currently supports the:
+	  - ADIN1200 - Robust,Industrial, Low Power 10/100 Ethernet PHY
+	  - ADIN1300 - Robust,Industrial, Low Latency 10/100/1000 Gigabit
+	    Ethernet PHY
+
 config AMD_PHY
 	tristate "AMD PHYs"
 	---help---
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index ba07c27e4208..a03437e091f3 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -47,6 +47,7 @@ obj-$(CONFIG_SFP)		+= sfp.o
 sfp-obj-$(CONFIG_SFP)		+= sfp-bus.o
 obj-y				+= $(sfp-obj-y) $(sfp-obj-m)
 
+obj-$(CONFIG_ADIN_PHY)		+= adin.o
 obj-$(CONFIG_AMD_PHY)		+= amd.o
 aquantia-objs			+= aquantia_main.o
 ifdef CONFIG_HWMON
diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
new file mode 100644
index 000000000000..6d7af4743957
--- /dev/null
+++ b/drivers/net/phy/adin.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0+
+/**
+ *  Driver for Analog Devices Industrial Ethernet PHYs
+ *
+ * Copyright 2019 Analog Devices Inc.
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mii.h>
+#include <linux/phy.h>
+
+#define PHY_ID_ADIN1200				0x0283bc20
+#define PHY_ID_ADIN1300				0x0283bc30
+
+static int adin_config_init(struct phy_device *phydev)
+{
+	return genphy_config_init(phydev);
+}
+
+static struct phy_driver adin_driver[] = {
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_ADIN1200),
+		.name		= "ADIN1200",
+		.config_init	= adin_config_init,
+		.config_aneg	= genphy_config_aneg,
+		.read_status	= genphy_read_status,
+	},
+	{
+		PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300),
+		.name		= "ADIN1300",
+		.config_init	= adin_config_init,
+		.config_aneg	= genphy_config_aneg,
+		.read_status	= genphy_read_status,
+	},
+};
+
+module_phy_driver(adin_driver);
+
+static struct mdio_device_id __maybe_unused adin_tbl[] = {
+	{ PHY_ID_MATCH_MODEL(PHY_ID_ADIN1200) },
+	{ PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300) },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, adin_tbl);
+MODULE_DESCRIPTION("Analog Devices Industrial Ethernet PHY driver");
+MODULE_LICENSE("GPL");
-- 
2.20.1


^ permalink raw reply related

* [PATCH v2 03/15] net: phy: adin: hook genphy_{suspend,resume} into the driver
From: Alexandru Ardelean @ 2019-08-08 12:30 UTC (permalink / raw)
  To: netdev, devicetree, linux-kernel
  Cc: davem, robh+dt, mark.rutland, f.fainelli, hkallweit1, andrew,
	Alexandru Ardelean
In-Reply-To: <20190808123026.17382-1-alexandru.ardelean@analog.com>

The chip supports standard suspend/resume via BMCR reg.
Hook these functions into the `adin` driver.

Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
---
 drivers/net/phy/adin.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c
index 879797d076e0..45490fbe273b 100644
--- a/drivers/net/phy/adin.c
+++ b/drivers/net/phy/adin.c
@@ -27,6 +27,8 @@ static struct phy_driver adin_driver[] = {
 		.config_aneg	= genphy_config_aneg,
 		.read_status	= genphy_read_status,
 		.get_features	= genphy_read_abilities,
+		.resume		= genphy_resume,
+		.suspend	= genphy_suspend,
 	},
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300),
@@ -35,6 +37,8 @@ static struct phy_driver adin_driver[] = {
 		.config_aneg	= genphy_config_aneg,
 		.read_status	= genphy_read_status,
 		.get_features	= genphy_read_abilities,
+		.resume		= genphy_resume,
+		.suspend	= genphy_suspend,
 	},
 };
 
-- 
2.20.1


^ permalink raw reply related

* Re: [PATCH V4 7/9] vhost: do not use RCU to synchronize MMU notifier with worker
From: Jason Wang @ 2019-08-08 12:54 UTC (permalink / raw)
  To: Jason Gunthorpe; +Cc: mst, kvm, virtualization, netdev, linux-kernel, linux-mm
In-Reply-To: <ba5f375f-435a-91fd-7fca-bfab0915594b@redhat.com>

[-- Attachment #1: Type: text/plain, Size: 13623 bytes --]


On 2019/8/7 下午10:02, Jason Wang wrote:
>
> On 2019/8/7 下午8:07, Jason Gunthorpe wrote:
>> On Wed, Aug 07, 2019 at 03:06:15AM -0400, Jason Wang wrote:
>>> We used to use RCU to synchronize MMU notifier with worker. This leads
>>> calling synchronize_rcu() in invalidate_range_start(). But on a busy
>>> system, there would be many factors that may slow down the
>>> synchronize_rcu() which makes it unsuitable to be called in MMU
>>> notifier.
>>>
>>> So this patch switches use seqlock counter to track whether or not the
>>> map was used. The counter was increased when vq try to start or finish
>>> uses the map. This means, when it was even, we're sure there's no
>>> readers and MMU notifier is synchronized. When it was odd, it means
>>> there's a reader we need to wait it to be even again then we are
>>> synchronized. Consider the read critical section is pretty small the
>>> synchronization should be done very fast.
>>>
>>> Reported-by: Michael S. Tsirkin <mst@redhat.com>
>>> Fixes: 7f466032dc9e ("vhost: access vq metadata through kernel
>>> virtual address")
>>> Signed-off-by: Jason Wang <jasowang@redhat.com>
>>>   drivers/vhost/vhost.c | 141
>>> ++++++++++++++++++++++++++----------------
>>>   drivers/vhost/vhost.h |   7 ++-
>>>   2 files changed, 90 insertions(+), 58 deletions(-)
>>>
>>> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
>>> index cfc11f9ed9c9..57bfbb60d960 100644
>>> +++ b/drivers/vhost/vhost.c
>>> @@ -324,17 +324,16 @@ static void vhost_uninit_vq_maps(struct
>>> vhost_virtqueue *vq)
>>>         spin_lock(&vq->mmu_lock);
>>>       for (i = 0; i < VHOST_NUM_ADDRS; i++) {
>>> -        map[i] = rcu_dereference_protected(vq->maps[i],
>>> -                  lockdep_is_held(&vq->mmu_lock));
>>> +        map[i] = vq->maps[i];
>>>           if (map[i]) {
>>>               vhost_set_map_dirty(vq, map[i], i);
>>> -            rcu_assign_pointer(vq->maps[i], NULL);
>>> +            vq->maps[i] = NULL;
>>>           }
>>>       }
>>>       spin_unlock(&vq->mmu_lock);
>>>   -    /* No need for synchronize_rcu() or kfree_rcu() since we are
>>> -     * serialized with memory accessors (e.g vq mutex held).
>>> +    /* No need for synchronization since we are serialized with
>>> +     * memory accessors (e.g vq mutex held).
>>>        */
>>>         for (i = 0; i < VHOST_NUM_ADDRS; i++)
>>> @@ -362,6 +361,40 @@ static bool vhost_map_range_overlap(struct
>>> vhost_uaddr *uaddr,
>>>       return !(end < uaddr->uaddr || start > uaddr->uaddr - 1 +
>>> uaddr->size);
>>>   }
>>>   +static void inline vhost_vq_access_map_begin(struct
>>> vhost_virtqueue *vq)
>>> +{
>>> +    write_seqcount_begin(&vq->seq);
>>> +}
>>> +
>>> +static void inline vhost_vq_access_map_end(struct vhost_virtqueue *vq)
>>> +{
>>> +    write_seqcount_end(&vq->seq);
>>> +}
>> The write side of a seqlock only provides write barriers. Access to
>>
>>     map = vq->maps[VHOST_ADDR_USED];
>>
>> Still needs a read side barrier, and then I think this will be no
>> better than a normal spinlock.
>>
>> It also doesn't seem like this algorithm even needs a seqlock, as this
>> is just a one bit flag
>
>
> Right, so then I tend to use spinlock first for correctness.
>
>
>>
>> atomic_set_bit(using map)
>> smp_mb__after_atomic()
>> .. maps [...]
>> atomic_clear_bit(using map)
>>
>>
>> map = NULL;
>> smp_mb__before_atomic();
>> while (atomic_read_bit(using map))
>>     relax()
>>
>> Again, not clear this could be faster than a spinlock when the
>> barriers are correct...
>

I've done some benchmark[1] on x86, and yes it looks even slower. It
looks to me the atomic stuffs is not necessary, so in order to compare
it better with spinlock. I tweak it a little bit through
smp_load_acquire()/store_releaes() + mb() like:

static struct vhost_map *vhost_vq_access_map_begin(struct
vhost_virtqueue
*vq,                                                                          

                                                   unsigned int
type)                                                                                   

{                                                                                                                                                       

       
++vq->counter;                                                                                                                                  

        /* Ensure map was read after incresing the counter.
Paired                                                                                      

         * with smp_mb() in
vhost_vq_sync_access().                                                                                                     

        
*/                                                                                                                                             

       
smp_mb();                                                                                                                                       

        return
vq->maps[type];                                                                                                                          

}                                                                                                                                                       

                                                                                                                                                        

static void inline vhost_vq_access_map_end(struct vhost_virtqueue
*vq)                                                                                  

{                                                                                                                                                       

        /* Ensure all memory access through map was done
before                                                                                         

         * reducing the counter. Paired with smp_load_acquire()
in                                                                                      

         * vhost_vq_sync_access()
*/                                                                                                                    

        smp_store_release(&vq->counter,
--vq->counter);                                                                                                 

}                                                                                                                                                       

                                                                                                                                                        

static void inline vhost_vq_sync_access(struct vhost_virtqueue
*vq)                                                                                     

{                                                                                                                                                       

        /* Ensure new map value is visible before checking counter.
*/                                                                                  

       
smp_mb();                                                                                                                                       

        /* Ensure map was freed after reading counter value,
paired                                                                                     

         * with smp_store_release() in
vhost_vq_access_map_end().                                                                                       

        
*/                                                                                                                                             

        while (smp_load_acquire(&vq->counter))
{                                                                                                        

                if
(need_resched())                                                                                                                     

                       
schedule();                                                                                                                     

       
}                                                                                                                                               

}         


And the result is something like:

         base | direct + atomic bitops | direct + spinlock() | direct +
counter + smp_mb() | direct + RCU     |
SMAP on  | 5.0Mpps | 5.0Mpps     (+0%)      | 5.7Mpps      (+14%)      |
5.9Mpps  (+18%)            | 6.2Mpps  (+24%)  |
SMAP off | 7.0Mpps | 7.0Mpps     (+0%)      | 7.0Mpps   (+0%)     |
7.5Mpps  (+7%)            | 8.2Mpps  (+17%)  |


base: normal copy_to_user()/copy_from_user() path.
direct + atomic bitops: using direct mapping but synchronize through
atomic bitops like you suggested above
direct + spinlock(): using direct mapping but synchronize through spinlocks
direct + counter + smp_mb(): using direct mapping but synchronize
through counter + smp_mb()
direct + RCU: using direct mapping and synchronize through RCU (buggy
and need to be addressed by this series)


So smp_mb() + counter is fastest way. And spinlock can still show some
improvement (+14%) in the case of SMAP, but no the case when SMAP is off.

I don't have any objection to convert  to spinlock() but just want to
know if any case that the above smp_mb() + counter looks good to you?

Thanks


>
> Yes, for next release we may want to use the idea from Michael like to
> mitigate the impact of mb.
>
> https://lwn.net/Articles/775871/
>
> Thanks
>
>
>>
>> Jason

[-- Attachment #2: pEpkey.asc --]
[-- Type: application/pgp-keys, Size: 2493 bytes --]

^ permalink raw reply

* Re: [PATCH V4 7/9] vhost: do not use RCU to synchronize MMU notifier       with worker
From: Jason Wang @ 2019-08-08 13:01 UTC (permalink / raw)
  To: Jason Gunthorpe; +Cc: kvm, mst, netdev, linux-kernel, virtualization, linux-mm
In-Reply-To: <1000f8a3-19a9-0383-61e5-ba08ddc9fcba@redhat.com>



----- Original Message -----
> 
> On 2019/8/7 下午10:02, Jason Wang wrote:
> >
> > On 2019/8/7 下午8:07, Jason Gunthorpe wrote:
> >> On Wed, Aug 07, 2019 at 03:06:15AM -0400, Jason Wang wrote:
> >>> We used to use RCU to synchronize MMU notifier with worker. This leads
> >>> calling synchronize_rcu() in invalidate_range_start(). But on a busy
> >>> system, there would be many factors that may slow down the
> >>> synchronize_rcu() which makes it unsuitable to be called in MMU
> >>> notifier.
> >>>
> >>> So this patch switches use seqlock counter to track whether or not the
> >>> map was used. The counter was increased when vq try to start or finish
> >>> uses the map. This means, when it was even, we're sure there's no
> >>> readers and MMU notifier is synchronized. When it was odd, it means
> >>> there's a reader we need to wait it to be even again then we are
> >>> synchronized. Consider the read critical section is pretty small the
> >>> synchronization should be done very fast.
> >>>
> >>> Reported-by: Michael S. Tsirkin <mst@redhat.com>
> >>> Fixes: 7f466032dc9e ("vhost: access vq metadata through kernel
> >>> virtual address")
> >>> Signed-off-by: Jason Wang <jasowang@redhat.com>
> >>>   drivers/vhost/vhost.c | 141
> >>> ++++++++++++++++++++++++++----------------
> >>>   drivers/vhost/vhost.h |   7 ++-
> >>>   2 files changed, 90 insertions(+), 58 deletions(-)
> >>>
> >>> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> >>> index cfc11f9ed9c9..57bfbb60d960 100644
> >>> +++ b/drivers/vhost/vhost.c
> >>> @@ -324,17 +324,16 @@ static void vhost_uninit_vq_maps(struct
> >>> vhost_virtqueue *vq)
> >>>         spin_lock(&vq->mmu_lock);
> >>>       for (i = 0; i < VHOST_NUM_ADDRS; i++) {
> >>> -        map[i] = rcu_dereference_protected(vq->maps[i],
> >>> -                  lockdep_is_held(&vq->mmu_lock));
> >>> +        map[i] = vq->maps[i];
> >>>           if (map[i]) {
> >>>               vhost_set_map_dirty(vq, map[i], i);
> >>> -            rcu_assign_pointer(vq->maps[i], NULL);
> >>> +            vq->maps[i] = NULL;
> >>>           }
> >>>       }
> >>>       spin_unlock(&vq->mmu_lock);
> >>>   -    /* No need for synchronize_rcu() or kfree_rcu() since we are
> >>> -     * serialized with memory accessors (e.g vq mutex held).
> >>> +    /* No need for synchronization since we are serialized with
> >>> +     * memory accessors (e.g vq mutex held).
> >>>        */
> >>>         for (i = 0; i < VHOST_NUM_ADDRS; i++)
> >>> @@ -362,6 +361,40 @@ static bool vhost_map_range_overlap(struct
> >>> vhost_uaddr *uaddr,
> >>>       return !(end < uaddr->uaddr || start > uaddr->uaddr - 1 +
> >>> uaddr->size);
> >>>   }
> >>>   +static void inline vhost_vq_access_map_begin(struct
> >>> vhost_virtqueue *vq)
> >>> +{
> >>> +    write_seqcount_begin(&vq->seq);
> >>> +}
> >>> +
> >>> +static void inline vhost_vq_access_map_end(struct vhost_virtqueue *vq)
> >>> +{
> >>> +    write_seqcount_end(&vq->seq);
> >>> +}
> >> The write side of a seqlock only provides write barriers. Access to
> >>
> >>     map = vq->maps[VHOST_ADDR_USED];
> >>
> >> Still needs a read side barrier, and then I think this will be no
> >> better than a normal spinlock.
> >>
> >> It also doesn't seem like this algorithm even needs a seqlock, as this
> >> is just a one bit flag
> >
> >
> > Right, so then I tend to use spinlock first for correctness.
> >
> >
> >>
> >> atomic_set_bit(using map)
> >> smp_mb__after_atomic()
> >> .. maps [...]
> >> atomic_clear_bit(using map)
> >>
> >>
> >> map = NULL;
> >> smp_mb__before_atomic();
> >> while (atomic_read_bit(using map))
> >>     relax()
> >>
> >> Again, not clear this could be faster than a spinlock when the
> >> barriers are correct...
> >
> 
> I've done some benchmark[1] on x86, and yes it looks even slower. It
> looks to me the atomic stuffs is not necessary, so in order to compare
> it better with spinlock. I tweak it a little bit through
> smp_load_acquire()/store_releaes() + mb() like:
> 

Sorry the format is messed up:

The code should be something like:

static struct vhost_map *vhost_vq_access_map_begin(struct vhost_virtqueue *vq,
                                                   unsigned int type)
{
        ++vq->counter;
        /* Ensure map was read after incresing the counter. Paired
         * with smp_mb() in vhost_vq_sync_access().
         */
        smp_mb();
        return vq->maps[type];
}

static void inline vhost_vq_access_map_end(struct vhost_virtqueue *vq)
{
 	/* Ensure all memory access through map was done before
         * reducing the counter. Paired with smp_load_acquire() in
         * vhost_vq_sync_access() */
        smp_store_release(&vq->counter, --vq->counter);
}

static void inline vhost_vq_sync_access(struct vhost_virtqueue *vq)
{
        /* Ensure new map value is visible before checking counter. */
        smp_mb();
        /* Ensure map was freed after reading counter value, paired
         * with smp_store_release() in vhost_vq_access_map_end().
         */
        while (smp_load_acquire(&vq->counter)) {
                if (need_resched())
                        schedule();
        }
}

And the benchmark result is:

         | base    | direct + atomic bitops | direct + spinlock() | direct + counter + smp_mb() | direct + RCU     |
SMAP on  | 5.0Mpps | 5.0Mpps     (+0%)      | 5.7Mpps  	(+14%)	  | 5.9Mpps  (+18%)	        | 6.2Mpps  (+24%)  |
SMAP off | 7.0Mpps | 7.0Mpps     (+0%)      | 7.0Mpps   (+0%)     | 7.5Mpps  (+7%)	        | 8.2Mpps  (+17%)  |


> 
> 
> base: normal copy_to_user()/copy_from_user() path.
> direct + atomic bitops: using direct mapping but synchronize through
> atomic bitops like you suggested above
> direct + spinlock(): using direct mapping but synchronize through spinlocks
> direct + counter + smp_mb(): using direct mapping but synchronize
> through counter + smp_mb()
> direct + RCU: using direct mapping and synchronize through RCU (buggy
> and need to be addressed by this series)
> 
> 
> So smp_mb() + counter is fastest way. And spinlock can still show some
> improvement (+14%) in the case of SMAP, but no the case when SMAP is off.
> 
> I don't have any objection to convert  to spinlock() but just want to
> know if any case that the above smp_mb() + counter looks good to you?
> 
> Thanks
> 
> 
> >
> > Yes, for next release we may want to use the idea from Michael like to
> > mitigate the impact of mb.
> >
> > https://lwn.net/Articles/775871/
> >
> > Thanks
> >
> >
> >>
> >> Jason
> 
> _______________________________________________
> Virtualization mailing list
> Virtualization@lists.linux-foundation.org
> https://lists.linuxfoundation.org/mailman/listinfo/virtualization

^ permalink raw reply

* Re: [PATCH V4 7/9] vhost: do not use RCU to synchronize MMU notifier with worker
From: Jason Gunthorpe @ 2019-08-08 13:05 UTC (permalink / raw)
  To: Jason Wang; +Cc: mst, kvm, virtualization, netdev, linux-kernel, linux-mm
In-Reply-To: <1000f8a3-19a9-0383-61e5-ba08ddc9fcba@redhat.com>

On Thu, Aug 08, 2019 at 08:54:54PM +0800, Jason Wang wrote:

> I don't have any objection to convert  to spinlock() but just want to
> know if any case that the above smp_mb() + counter looks good to you?

This email is horribly mangled, but I don't think mixing smb_mb() and
smp_load_acquire() would be considerd a best-practice, and using
smp_store_release() instead would be the wrong barrier.

spinlock does seem to be the only existing locking primitive that does
what is needed here.

Jason

^ permalink raw reply

* [PATCH 1/2] batman-adv: Fix netlink dumping of all mcast_flags buckets
From: Simon Wunderlich @ 2019-08-08 13:02 UTC (permalink / raw)
  To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20190808130208.2124-1-sw@simonwunderlich.de>

From: Sven Eckelmann <sven@narfation.org>

The bucket variable is only updated outside the loop over the mcast_flags
buckets. It will only be updated during a dumping run when the dumping has
to be interrupted and a new message has to be started.

This could result in repeated or missing entries when the multicast flags
are dumped to userspace.

Fixes: d2d489b7d851 ("batman-adv: Add inconsistent multicast netlink dump detection")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/multicast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 67d7f83009ae..a3488cfb3d1e 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -2303,7 +2303,7 @@ __batadv_mcast_flags_dump(struct sk_buff *msg, u32 portid,
 
 	while (bucket_tmp < hash->size) {
 		if (batadv_mcast_flags_dump_bucket(msg, portid, cb, hash,
-						   *bucket, &idx_tmp))
+						   bucket_tmp, &idx_tmp))
 			break;
 
 		bucket_tmp++;
-- 
2.20.1


^ permalink raw reply related

* [PATCH 2/2] batman-adv: Fix deletion of RTR(4|6) mcast list entries
From: Simon Wunderlich @ 2019-08-08 13:02 UTC (permalink / raw)
  To: davem
  Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Linus Lüssing,
	Simon Wunderlich
In-Reply-To: <20190808130208.2124-1-sw@simonwunderlich.de>

From: Sven Eckelmann <sven@narfation.org>

The multicast code uses the lists bat_priv->mcast.want_all_rtr*_list to
store all all originator nodes which don't have the flag no-RTR4 or no-RTR6
set. When an originator is purged, it has to be removed from these lists.

Since all entries without the BATADV_MCAST_WANT_NO_RTR4/6 are stored in
these lists, they have to be handled like entries which have these flags
set to force the update routines to remove them from the lists when purging
the originator.

Not doing so will leave a pointer to a freed memory region inside the list.
Trying to operate on these lists will then cause an use-after-free error:

  BUG: KASAN: use-after-free in batadv_mcast_want_rtr4_update+0x335/0x3a0 [batman_adv]
  Write of size 8 at addr ffff888007b41a38 by task swapper/0/0

Fixes: 61caf3d109f5 ("batman-adv: mcast: detect, distribute and maintain multicast router presence")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Acked-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/multicast.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index a3488cfb3d1e..1d5bdf3a4b65 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -2420,8 +2420,10 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig)
 	batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS);
 	batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS);
 	batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS);
-	batadv_mcast_want_rtr4_update(bat_priv, orig, BATADV_NO_FLAGS);
-	batadv_mcast_want_rtr6_update(bat_priv, orig, BATADV_NO_FLAGS);
+	batadv_mcast_want_rtr4_update(bat_priv, orig,
+				      BATADV_MCAST_WANT_NO_RTR4);
+	batadv_mcast_want_rtr6_update(bat_priv, orig,
+				      BATADV_MCAST_WANT_NO_RTR6);
 
 	spin_unlock_bh(&orig->mcast_handler_lock);
 }
-- 
2.20.1


^ permalink raw reply related

* [PATCH 0/2] pull request for net: batman-adv 2019-08-08
From: Simon Wunderlich @ 2019-08-08 13:02 UTC (permalink / raw)
  To: davem; +Cc: netdev, b.a.t.m.a.n, Simon Wunderlich

Hi David,

here are some bugfixes which we would like to have integrated into net.

Please pull or let me know of any problem!

Thank you,
      Simon

The following changes since commit 5f9e832c137075045d15cd6899ab0505cfb2ca4b:

  Linus 5.3-rc1 (2019-07-21 14:05:38 -0700)

are available in the Git repository at:

  git://git.open-mesh.org/linux-merge.git tags/batadv-net-for-davem-20190808

for you to fetch changes up to f7af86ccf1882084293b11077deec049fd01da63:

  batman-adv: Fix deletion of RTR(4|6) mcast list entries (2019-07-22 21:34:58 +0200)

----------------------------------------------------------------
Here are some batman-adv bugfixes:

 - Fix netlink dumping of all mcast_flags buckets, by Sven Eckelmann

 - Fix deletion of RTR(4|6) mcast list entries, by Sven Eckelmann

----------------------------------------------------------------
Sven Eckelmann (2):
      batman-adv: Fix netlink dumping of all mcast_flags buckets
      batman-adv: Fix deletion of RTR(4|6) mcast list entries

 net/batman-adv/multicast.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

^ permalink raw reply

* [PATCH 1/4] batman-adv: Start new development cycle
From: Simon Wunderlich @ 2019-08-08 13:06 UTC (permalink / raw)
  To: davem; +Cc: netdev, b.a.t.m.a.n, Simon Wunderlich
In-Reply-To: <20190808130619.4481-1-sw@simonwunderlich.de>

Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/main.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 3d4c04d87ff3..6967f2e4c3f4 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -13,7 +13,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2019.3"
+#define BATADV_SOURCE_VERSION "2019.4"
 #endif
 
 /* B.A.T.M.A.N. parameters */
-- 
2.20.1


^ permalink raw reply related

* [PATCH 2/4] batman-adv: Replace usage of strlcpy with strscpy
From: Simon Wunderlich @ 2019-08-08 13:06 UTC (permalink / raw)
  To: davem; +Cc: netdev, b.a.t.m.a.n, Sven Eckelmann, Simon Wunderlich
In-Reply-To: <20190808130619.4481-1-sw@simonwunderlich.de>

From: Sven Eckelmann <sven@narfation.org>

The strscpy was introduced to fix some API problems around strlcpy. And
checkpatch started to report recently that strlcpy is deprecated and
strscpy is preferred.

The functionality introduced in commit 30035e45753b ("string: provide
strscpy()") improves following points compared to strlcpy:

* it doesn't read from memory beyond (src + size)
* provides an easy way to check for destination buffer overflow
* robust against asynchronous source buffer changes

Since batman-adv doesn't depend on any of the previously mentioned behavior
changes, the usage of strlcpy can simply be replaced by strscpy to silence
checkpatch.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/soft-interface.c | 8 ++++----
 net/batman-adv/sysfs.c          | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index c7a2e77ca1da..a1146cb10919 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -943,10 +943,10 @@ static const struct net_device_ops batadv_netdev_ops = {
 static void batadv_get_drvinfo(struct net_device *dev,
 			       struct ethtool_drvinfo *info)
 {
-	strlcpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver));
-	strlcpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version));
-	strlcpy(info->fw_version, "N/A", sizeof(info->fw_version));
-	strlcpy(info->bus_info, "batman", sizeof(info->bus_info));
+	strscpy(info->driver, "B.A.T.M.A.N. advanced", sizeof(info->driver));
+	strscpy(info->version, BATADV_SOURCE_VERSION, sizeof(info->version));
+	strscpy(info->fw_version, "N/A", sizeof(info->fw_version));
+	strscpy(info->bus_info, "batman", sizeof(info->bus_info));
 }
 
 /* Inspired by drivers/net/ethernet/dlink/sundance.c:1702
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 1efcb97039cd..e5bbc28ed12c 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -1070,7 +1070,7 @@ static ssize_t batadv_store_mesh_iface(struct kobject *kobj,
 	dev_hold(net_dev);
 	INIT_WORK(&store_work->work, batadv_store_mesh_iface_work);
 	store_work->net_dev = net_dev;
-	strlcpy(store_work->soft_iface_name, buff,
+	strscpy(store_work->soft_iface_name, buff,
 		sizeof(store_work->soft_iface_name));
 
 	queue_work(batadv_event_workqueue, &store_work->work);
-- 
2.20.1


^ permalink raw reply related

* [PATCH 4/4] batman-adv: BATMAN_V: aggregate OGMv2 packets
From: Simon Wunderlich @ 2019-08-08 13:06 UTC (permalink / raw)
  To: davem
  Cc: netdev, b.a.t.m.a.n, Linus Lüssing, Sven Eckelmann,
	Simon Wunderlich
In-Reply-To: <20190808130619.4481-1-sw@simonwunderlich.de>

From: Linus Lüssing <linus.luessing@c0d3.blue>

Instead of transmitting individual OGMv2 packets from the aggregation
queue merge those OGMv2 packets into a single one and transmit this
aggregate instead.

This reduces overhead as it saves an ethernet header and a transmission
per aggregated OGMv2 packet.

Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_v_ogm.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 52c990b54de5..319249f0f85f 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -191,18 +191,44 @@ static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface)
  * batadv_v_ogm_aggr_send() - flush & send aggregation queue
  * @hard_iface: the interface with the aggregation queue to flush
  *
+ * Aggregates all OGMv2 packets currently in the aggregation queue into a
+ * single OGMv2 packet and transmits this aggregate.
+ *
+ * The aggregation queue is empty after this call.
+ *
  * Caller needs to hold the hard_iface->bat_v.aggr_list_lock.
  */
 static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface)
 {
+	unsigned int aggr_len = hard_iface->bat_v.aggr_len;
+	struct sk_buff *skb_aggr;
+	unsigned int ogm_len;
 	struct sk_buff *skb;
 
 	lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock);
 
+	if (!aggr_len)
+		return;
+
+	skb_aggr = dev_alloc_skb(aggr_len + ETH_HLEN + NET_IP_ALIGN);
+	if (!skb_aggr) {
+		batadv_v_ogm_aggr_list_free(hard_iface);
+		return;
+	}
+
+	skb_reserve(skb_aggr, ETH_HLEN + NET_IP_ALIGN);
+	skb_reset_network_header(skb_aggr);
+
 	while ((skb = skb_dequeue(&hard_iface->bat_v.aggr_list))) {
 		hard_iface->bat_v.aggr_len -= batadv_v_ogm_len(skb);
-		batadv_v_ogm_send_to_if(skb, hard_iface);
+
+		ogm_len = batadv_v_ogm_len(skb);
+		skb_put_data(skb_aggr, skb->data, ogm_len);
+
+		consume_skb(skb);
 	}
+
+	batadv_v_ogm_send_to_if(skb_aggr, hard_iface);
 }
 
 /**
-- 
2.20.1


^ permalink raw reply related

* [PATCH 3/4] batman-adv: BATMAN_V: introduce per hard-iface OGMv2 queues
From: Simon Wunderlich @ 2019-08-08 13:06 UTC (permalink / raw)
  To: davem
  Cc: netdev, b.a.t.m.a.n, Linus Lüssing, Sven Eckelmann,
	Simon Wunderlich
In-Reply-To: <20190808130619.4481-1-sw@simonwunderlich.de>

From: Linus Lüssing <linus.luessing@c0d3.blue>

In preparation for the OGMv2 packet aggregation, hold OGMv2 packets for
up to BATADV_MAX_AGGREGATION_MS milliseconds (100ms) on per
hard-interface queues, before transmitting.

This allows us to later squash multiple OGMs into a single frame
and transmission for reduced overhead.

Signed-off-by: Linus Lüssing <linus.luessing@c0d3.blue>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_v.c     |   7 ++
 net/batman-adv/bat_v_ogm.c | 153 ++++++++++++++++++++++++++++++++++++-
 net/batman-adv/bat_v_ogm.h |   3 +
 net/batman-adv/types.h     |  12 +++
 4 files changed, 173 insertions(+), 2 deletions(-)

diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 22672cb3e25d..64054edc2e3c 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -79,6 +79,7 @@ static int batadv_v_iface_enable(struct batadv_hard_iface *hard_iface)
 
 static void batadv_v_iface_disable(struct batadv_hard_iface *hard_iface)
 {
+	batadv_v_ogm_iface_disable(hard_iface);
 	batadv_v_elp_iface_disable(hard_iface);
 }
 
@@ -1081,6 +1082,12 @@ void batadv_v_hardif_init(struct batadv_hard_iface *hard_iface)
 	 */
 	atomic_set(&hard_iface->bat_v.throughput_override, 0);
 	atomic_set(&hard_iface->bat_v.elp_interval, 500);
+
+	hard_iface->bat_v.aggr_len = 0;
+	skb_queue_head_init(&hard_iface->bat_v.aggr_list);
+	spin_lock_init(&hard_iface->bat_v.aggr_list_lock);
+	INIT_DELAYED_WORK(&hard_iface->bat_v.aggr_wq,
+			  batadv_v_ogm_aggr_work);
 }
 
 /**
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index fad95ef64e01..52c990b54de5 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -17,12 +17,14 @@
 #include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/list.h>
+#include <linux/lockdep.h>
 #include <linux/netdevice.h>
 #include <linux/random.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
 #include <linux/stddef.h>
 #include <linux/string.h>
 #include <linux/types.h>
@@ -76,6 +78,20 @@ struct batadv_orig_node *batadv_v_ogm_orig_get(struct batadv_priv *bat_priv,
 	return orig_node;
 }
 
+/**
+ * batadv_v_ogm_start_queue_timer() - restart the OGM aggregation timer
+ * @hard_iface: the interface to use to send the OGM
+ */
+static void batadv_v_ogm_start_queue_timer(struct batadv_hard_iface *hard_iface)
+{
+	unsigned int msecs = BATADV_MAX_AGGREGATION_MS * 1000;
+
+	/* msecs * [0.9, 1.1] */
+	msecs += prandom_u32() % (msecs / 5) - (msecs / 10);
+	queue_delayed_work(batadv_event_workqueue, &hard_iface->bat_v.aggr_wq,
+			   msecs_to_jiffies(msecs / 1000));
+}
+
 /**
  * batadv_v_ogm_start_timer() - restart the OGM sending timer
  * @bat_priv: the bat priv with all the soft interface information
@@ -115,6 +131,104 @@ static void batadv_v_ogm_send_to_if(struct sk_buff *skb,
 	batadv_send_broadcast_skb(skb, hard_iface);
 }
 
+/**
+ * batadv_v_ogm_len() - OGMv2 packet length
+ * @skb: the OGM to check
+ *
+ * Return: Length of the given OGMv2 packet, including tvlv length, excluding
+ * ethernet header length.
+ */
+static unsigned int batadv_v_ogm_len(struct sk_buff *skb)
+{
+	struct batadv_ogm2_packet *ogm_packet;
+
+	ogm_packet = (struct batadv_ogm2_packet *)skb->data;
+	return BATADV_OGM2_HLEN + ntohs(ogm_packet->tvlv_len);
+}
+
+/**
+ * batadv_v_ogm_queue_left() - check if given OGM still fits aggregation queue
+ * @skb: the OGM to check
+ * @hard_iface: the interface to use to send the OGM
+ *
+ * Caller needs to hold the hard_iface->bat_v.aggr_list_lock.
+ *
+ * Return: True, if the given OGMv2 packet still fits, false otherwise.
+ */
+static bool batadv_v_ogm_queue_left(struct sk_buff *skb,
+				    struct batadv_hard_iface *hard_iface)
+{
+	unsigned int max = min_t(unsigned int, hard_iface->net_dev->mtu,
+				 BATADV_MAX_AGGREGATION_BYTES);
+	unsigned int ogm_len = batadv_v_ogm_len(skb);
+
+	lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock);
+
+	return hard_iface->bat_v.aggr_len + ogm_len <= max;
+}
+
+/**
+ * batadv_v_ogm_aggr_list_free - free all elements in an aggregation queue
+ * @hard_iface: the interface holding the aggregation queue
+ *
+ * Empties the OGMv2 aggregation queue and frees all the skbs it contained.
+ *
+ * Caller needs to hold the hard_iface->bat_v.aggr_list_lock.
+ */
+static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface)
+{
+	struct sk_buff *skb;
+
+	lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock);
+
+	while ((skb = skb_dequeue(&hard_iface->bat_v.aggr_list)))
+		kfree_skb(skb);
+
+	hard_iface->bat_v.aggr_len = 0;
+}
+
+/**
+ * batadv_v_ogm_aggr_send() - flush & send aggregation queue
+ * @hard_iface: the interface with the aggregation queue to flush
+ *
+ * Caller needs to hold the hard_iface->bat_v.aggr_list_lock.
+ */
+static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface)
+{
+	struct sk_buff *skb;
+
+	lockdep_assert_held(&hard_iface->bat_v.aggr_list_lock);
+
+	while ((skb = skb_dequeue(&hard_iface->bat_v.aggr_list))) {
+		hard_iface->bat_v.aggr_len -= batadv_v_ogm_len(skb);
+		batadv_v_ogm_send_to_if(skb, hard_iface);
+	}
+}
+
+/**
+ * batadv_v_ogm_queue_on_if() - queue a batman ogm on a given interface
+ * @skb: the OGM to queue
+ * @hard_iface: the interface to queue the OGM on
+ */
+static void batadv_v_ogm_queue_on_if(struct sk_buff *skb,
+				     struct batadv_hard_iface *hard_iface)
+{
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+
+	if (!atomic_read(&bat_priv->aggregated_ogms)) {
+		batadv_v_ogm_send_to_if(skb, hard_iface);
+		return;
+	}
+
+	spin_lock_bh(&hard_iface->bat_v.aggr_list_lock);
+	if (!batadv_v_ogm_queue_left(skb, hard_iface))
+		batadv_v_ogm_aggr_send(hard_iface);
+
+	hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb);
+	skb_queue_tail(&hard_iface->bat_v.aggr_list, skb);
+	spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock);
+}
+
 /**
  * batadv_v_ogm_send() - periodic worker broadcasting the own OGM
  * @work: work queue item
@@ -210,7 +324,7 @@ static void batadv_v_ogm_send(struct work_struct *work)
 			break;
 		}
 
-		batadv_v_ogm_send_to_if(skb_tmp, hard_iface);
+		batadv_v_ogm_queue_on_if(skb_tmp, hard_iface);
 		batadv_hardif_put(hard_iface);
 	}
 	rcu_read_unlock();
@@ -223,6 +337,27 @@ static void batadv_v_ogm_send(struct work_struct *work)
 	return;
 }
 
+/**
+ * batadv_v_ogm_aggr_work() - OGM queue periodic task per interface
+ * @work: work queue item
+ *
+ * Emits aggregated OGM message in regular intervals.
+ */
+void batadv_v_ogm_aggr_work(struct work_struct *work)
+{
+	struct batadv_hard_iface_bat_v *batv;
+	struct batadv_hard_iface *hard_iface;
+
+	batv = container_of(work, struct batadv_hard_iface_bat_v, aggr_wq.work);
+	hard_iface = container_of(batv, struct batadv_hard_iface, bat_v);
+
+	spin_lock_bh(&hard_iface->bat_v.aggr_list_lock);
+	batadv_v_ogm_aggr_send(hard_iface);
+	spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock);
+
+	batadv_v_ogm_start_queue_timer(hard_iface);
+}
+
 /**
  * batadv_v_ogm_iface_enable() - prepare an interface for B.A.T.M.A.N. V
  * @hard_iface: the interface to prepare
@@ -235,11 +370,25 @@ int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
 {
 	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
 
+	batadv_v_ogm_start_queue_timer(hard_iface);
 	batadv_v_ogm_start_timer(bat_priv);
 
 	return 0;
 }
 
+/**
+ * batadv_v_ogm_iface_disable() - release OGM interface private resources
+ * @hard_iface: interface for which the resources have to be released
+ */
+void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface)
+{
+	cancel_delayed_work_sync(&hard_iface->bat_v.aggr_wq);
+
+	spin_lock_bh(&hard_iface->bat_v.aggr_list_lock);
+	batadv_v_ogm_aggr_list_free(hard_iface);
+	spin_unlock_bh(&hard_iface->bat_v.aggr_list_lock);
+}
+
 /**
  * batadv_v_ogm_primary_iface_set() - set a new primary interface
  * @primary_iface: the new primary interface
@@ -382,7 +531,7 @@ static void batadv_v_ogm_forward(struct batadv_priv *bat_priv,
 		   if_outgoing->net_dev->name, ntohl(ogm_forward->throughput),
 		   ogm_forward->ttl, if_incoming->net_dev->name);
 
-	batadv_v_ogm_send_to_if(skb, if_outgoing);
+	batadv_v_ogm_queue_on_if(skb, if_outgoing);
 
 out:
 	if (orig_ifinfo)
diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h
index 2a50df7fc2bf..bf16d040461d 100644
--- a/net/batman-adv/bat_v_ogm.h
+++ b/net/batman-adv/bat_v_ogm.h
@@ -11,10 +11,13 @@
 
 #include <linux/skbuff.h>
 #include <linux/types.h>
+#include <linux/workqueue.h>
 
 int batadv_v_ogm_init(struct batadv_priv *bat_priv);
 void batadv_v_ogm_free(struct batadv_priv *bat_priv);
+void batadv_v_ogm_aggr_work(struct work_struct *work);
 int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface);
+void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface);
 struct batadv_orig_node *batadv_v_ogm_orig_get(struct batadv_priv *bat_priv,
 					       const u8 *addr);
 void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface);
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 6ae139d74e0f..be7c02aa91e2 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -117,6 +117,18 @@ struct batadv_hard_iface_bat_v {
 	/** @elp_wq: workqueue used to schedule ELP transmissions */
 	struct delayed_work elp_wq;
 
+	/** @aggr_wq: workqueue used to transmit queued OGM packets */
+	struct delayed_work aggr_wq;
+
+	/** @aggr_list: queue for to be aggregated OGM packets */
+	struct sk_buff_head aggr_list;
+
+	/** @aggr_len: size of the OGM aggregate (excluding ethernet header) */
+	unsigned int aggr_len;
+
+	/** @aggr_list_lock: protects aggr_list */
+	spinlock_t aggr_list_lock;
+
 	/**
 	 * @throughput_override: throughput override to disable link
 	 *  auto-detection
-- 
2.20.1


^ permalink raw reply related

* [PATCH 0/4] pull request for net-next: batman-adv 2019-08-08
From: Simon Wunderlich @ 2019-08-08 13:06 UTC (permalink / raw)
  To: davem; +Cc: netdev, b.a.t.m.a.n, Simon Wunderlich

Hi David,

here is a small feature/cleanup pull request of batman-adv to go into net-next.

Please pull or let me know of any problem!

Thank you,
      Simon

The following changes since commit 5f9e832c137075045d15cd6899ab0505cfb2ca4b:

  Linus 5.3-rc1 (2019-07-21 14:05:38 -0700)

are available in the Git repository at:

  git://git.open-mesh.org/linux-merge.git tags/batadv-next-for-davem-20190808

for you to fetch changes up to 9cb9a17813bf0de1f8ad6deb9538296d5148b5a8:

  batman-adv: BATMAN_V: aggregate OGMv2 packets (2019-08-04 22:22:00 +0200)

----------------------------------------------------------------
This feature/cleanup patchset includes the following patches:

 - bump version strings, by Simon Wunderlich

 - Replace usage of strlcpy with strscpy, by Sven Eckelmann

 - Add OGMv2 per-interface queue and aggregations, by Linus Luessing
   (2 patches)

----------------------------------------------------------------
Linus Lüssing (2):
      batman-adv: BATMAN_V: introduce per hard-iface OGMv2 queues
      batman-adv: BATMAN_V: aggregate OGMv2 packets

Simon Wunderlich (1):
      batman-adv: Start new development cycle

Sven Eckelmann (1):
      batman-adv: Replace usage of strlcpy with strscpy

 net/batman-adv/bat_v.c          |   7 ++
 net/batman-adv/bat_v_ogm.c      | 179 +++++++++++++++++++++++++++++++++++++++-
 net/batman-adv/bat_v_ogm.h      |   3 +
 net/batman-adv/main.h           |   2 +-
 net/batman-adv/soft-interface.c |   8 +-
 net/batman-adv/sysfs.c          |   2 +-
 net/batman-adv/types.h          |  12 +++
 7 files changed, 205 insertions(+), 8 deletions(-)

^ permalink raw reply

* Re: [PATCH net-next] net/ncsi: allow to customize BMC MAC Address offset
From: Andrew Lunn @ 2019-08-08 13:32 UTC (permalink / raw)
  To: Tao Ren
  Cc: Jakub Kicinski, Samuel Mendoza-Jonas, David S . Miller,
	netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	openbmc@lists.ozlabs.org, William Kennington, Joel Stanley
In-Reply-To: <806a76a8-229a-7f24-33c7-2cf2094f3436@fb.com>

> Let me prepare patch v2 using device tree. I'm not sure if standard
> "mac-address" fits this situation because all we need is an offset
> (integer) and BMC MAC is calculated by adding the offset to NIC's
> MAC address. Anyways, let me work out v2 patch we can discuss more
> then.

Hi Tao

I don't know BMC terminology. By NICs MAC address, you are referring
to the hosts MAC address? The MAC address the big CPU is using for its
interface?  Where does this NIC get its MAC address from? If the BMCs
bootloader has access to it, it can set the mac-address property in
the device tree.

    Andrew

^ permalink raw reply

* [PATCH net-next v2 1/9] net: introduce the MACSEC netdev feature
From: Antoine Tenart @ 2019-08-08 14:05 UTC (permalink / raw)
  To: davem, sd, andrew, f.fainelli, hkallweit1
  Cc: Antoine Tenart, netdev, linux-kernel, thomas.petazzoni,
	alexandre.belloni, allan.nielsen, camelia.groza, Simon.Edelhaus
In-Reply-To: <20190808140600.21477-1-antoine.tenart@bootlin.com>

This patch introduce a new netdev feature, which will be used by drivers
to state they can perform MACsec transformations in hardware.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
---
 include/linux/netdev_features.h | 3 +++
 net/core/ethtool.c              | 1 +
 2 files changed, 4 insertions(+)

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 4b19c544c59a..020f8542b92f 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -81,6 +81,8 @@ enum {
 	NETIF_F_GRO_HW_BIT,		/* Hardware Generic receive offload */
 	NETIF_F_HW_TLS_RECORD_BIT,	/* Offload TLS record */
 
+	NETIF_F_HW_MACSEC_BIT,		/* Offload MACsec operations */
+
 	/*
 	 * Add your fresh new feature above and remember to update
 	 * netdev_features_strings[] in net/core/ethtool.c and maybe
@@ -150,6 +152,7 @@ enum {
 #define NETIF_F_GSO_UDP_L4	__NETIF_F(GSO_UDP_L4)
 #define NETIF_F_HW_TLS_TX	__NETIF_F(HW_TLS_TX)
 #define NETIF_F_HW_TLS_RX	__NETIF_F(HW_TLS_RX)
+#define NETIF_F_HW_MACSEC	__NETIF_F(HW_MACSEC)
 
 /* Finds the next feature with the highest number of the range of start till 0.
  */
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 6288e69e94fc..4a410e0ff179 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -111,6 +111,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_HW_TLS_RECORD_BIT] =	"tls-hw-record",
 	[NETIF_F_HW_TLS_TX_BIT] =	 "tls-hw-tx-offload",
 	[NETIF_F_HW_TLS_RX_BIT] =	 "tls-hw-rx-offload",
+	[NETIF_F_HW_MACSEC_BIT] =	 "macsec-hw-offload",
 };
 
 static const char
-- 
2.21.0


^ permalink raw reply related

* [PATCH net-next v2 2/9] net: macsec: move some definitions in a dedicated header
From: Antoine Tenart @ 2019-08-08 14:05 UTC (permalink / raw)
  To: davem, sd, andrew, f.fainelli, hkallweit1
  Cc: Antoine Tenart, netdev, linux-kernel, thomas.petazzoni,
	alexandre.belloni, allan.nielsen, camelia.groza, Simon.Edelhaus
In-Reply-To: <20190808140600.21477-1-antoine.tenart@bootlin.com>

This patch moves some structure, type and identifier definitions into a
MACsec specific header. This patch does not modify how the MACsec code
is running and only move things around. This is a preparation for the
future MACsec hardware offloading support, which will re-use those
definitions outside macsec.c.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
---
 drivers/net/macsec.c           | 163 ------------------------------
 include/net/macsec.h           | 179 +++++++++++++++++++++++++++++++++
 include/uapi/linux/if_macsec.h |   3 +-
 3 files changed, 180 insertions(+), 165 deletions(-)
 create mode 100644 include/net/macsec.h

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 8f46aa1ddec0..3815cb6e9bf2 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -19,8 +19,6 @@
 
 #include <uapi/linux/if_macsec.h>
 
-typedef u64 __bitwise sci_t;
-
 #define MACSEC_SCI_LEN 8
 
 /* SecTAG length = macsec_eth_header without the optional SCI */
@@ -58,8 +56,6 @@ struct macsec_eth_header {
 #define GCM_AES_IV_LEN 12
 #define DEFAULT_ICV_LEN 16
 
-#define MACSEC_NUM_AN 4 /* 2 bits for the association number */
-
 #define for_each_rxsc(secy, sc)				\
 	for (sc = rcu_dereference_bh(secy->rx_sc);	\
 	     sc;					\
@@ -77,49 +73,6 @@ struct gcm_iv {
 	__be32 pn;
 };
 
-/**
- * struct macsec_key - SA key
- * @id: user-provided key identifier
- * @tfm: crypto struct, key storage
- */
-struct macsec_key {
-	u8 id[MACSEC_KEYID_LEN];
-	struct crypto_aead *tfm;
-};
-
-struct macsec_rx_sc_stats {
-	__u64 InOctetsValidated;
-	__u64 InOctetsDecrypted;
-	__u64 InPktsUnchecked;
-	__u64 InPktsDelayed;
-	__u64 InPktsOK;
-	__u64 InPktsInvalid;
-	__u64 InPktsLate;
-	__u64 InPktsNotValid;
-	__u64 InPktsNotUsingSA;
-	__u64 InPktsUnusedSA;
-};
-
-struct macsec_rx_sa_stats {
-	__u32 InPktsOK;
-	__u32 InPktsInvalid;
-	__u32 InPktsNotValid;
-	__u32 InPktsNotUsingSA;
-	__u32 InPktsUnusedSA;
-};
-
-struct macsec_tx_sa_stats {
-	__u32 OutPktsProtected;
-	__u32 OutPktsEncrypted;
-};
-
-struct macsec_tx_sc_stats {
-	__u64 OutPktsProtected;
-	__u64 OutPktsEncrypted;
-	__u64 OutOctetsProtected;
-	__u64 OutOctetsEncrypted;
-};
-
 struct macsec_dev_stats {
 	__u64 OutPktsUntagged;
 	__u64 InPktsUntagged;
@@ -131,124 +84,8 @@ struct macsec_dev_stats {
 	__u64 InPktsOverrun;
 };
 
-/**
- * struct macsec_rx_sa - receive secure association
- * @active:
- * @next_pn: packet number expected for the next packet
- * @lock: protects next_pn manipulations
- * @key: key structure
- * @stats: per-SA stats
- */
-struct macsec_rx_sa {
-	struct macsec_key key;
-	spinlock_t lock;
-	u32 next_pn;
-	refcount_t refcnt;
-	bool active;
-	struct macsec_rx_sa_stats __percpu *stats;
-	struct macsec_rx_sc *sc;
-	struct rcu_head rcu;
-};
-
-struct pcpu_rx_sc_stats {
-	struct macsec_rx_sc_stats stats;
-	struct u64_stats_sync syncp;
-};
-
-/**
- * struct macsec_rx_sc - receive secure channel
- * @sci: secure channel identifier for this SC
- * @active: channel is active
- * @sa: array of secure associations
- * @stats: per-SC stats
- */
-struct macsec_rx_sc {
-	struct macsec_rx_sc __rcu *next;
-	sci_t sci;
-	bool active;
-	struct macsec_rx_sa __rcu *sa[MACSEC_NUM_AN];
-	struct pcpu_rx_sc_stats __percpu *stats;
-	refcount_t refcnt;
-	struct rcu_head rcu_head;
-};
-
-/**
- * struct macsec_tx_sa - transmit secure association
- * @active:
- * @next_pn: packet number to use for the next packet
- * @lock: protects next_pn manipulations
- * @key: key structure
- * @stats: per-SA stats
- */
-struct macsec_tx_sa {
-	struct macsec_key key;
-	spinlock_t lock;
-	u32 next_pn;
-	refcount_t refcnt;
-	bool active;
-	struct macsec_tx_sa_stats __percpu *stats;
-	struct rcu_head rcu;
-};
-
-struct pcpu_tx_sc_stats {
-	struct macsec_tx_sc_stats stats;
-	struct u64_stats_sync syncp;
-};
-
-/**
- * struct macsec_tx_sc - transmit secure channel
- * @active:
- * @encoding_sa: association number of the SA currently in use
- * @encrypt: encrypt packets on transmit, or authenticate only
- * @send_sci: always include the SCI in the SecTAG
- * @end_station:
- * @scb: single copy broadcast flag
- * @sa: array of secure associations
- * @stats: stats for this TXSC
- */
-struct macsec_tx_sc {
-	bool active;
-	u8 encoding_sa;
-	bool encrypt;
-	bool send_sci;
-	bool end_station;
-	bool scb;
-	struct macsec_tx_sa __rcu *sa[MACSEC_NUM_AN];
-	struct pcpu_tx_sc_stats __percpu *stats;
-};
-
 #define MACSEC_VALIDATE_DEFAULT MACSEC_VALIDATE_STRICT
 
-/**
- * struct macsec_secy - MACsec Security Entity
- * @netdev: netdevice for this SecY
- * @n_rx_sc: number of receive secure channels configured on this SecY
- * @sci: secure channel identifier used for tx
- * @key_len: length of keys used by the cipher suite
- * @icv_len: length of ICV used by the cipher suite
- * @validate_frames: validation mode
- * @operational: MAC_Operational flag
- * @protect_frames: enable protection for this SecY
- * @replay_protect: enable packet number checks on receive
- * @replay_window: size of the replay window
- * @tx_sc: transmit secure channel
- * @rx_sc: linked list of receive secure channels
- */
-struct macsec_secy {
-	struct net_device *netdev;
-	unsigned int n_rx_sc;
-	sci_t sci;
-	u16 key_len;
-	u16 icv_len;
-	enum macsec_validation_type validate_frames;
-	bool operational;
-	bool protect_frames;
-	bool replay_protect;
-	u32 replay_window;
-	struct macsec_tx_sc tx_sc;
-	struct macsec_rx_sc __rcu *rx_sc;
-};
-
 struct pcpu_secy_stats {
 	struct macsec_dev_stats stats;
 	struct u64_stats_sync syncp;
diff --git a/include/net/macsec.h b/include/net/macsec.h
new file mode 100644
index 000000000000..5db18a272ffd
--- /dev/null
+++ b/include/net/macsec.h
@@ -0,0 +1,179 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * MACsec netdev header, used for h/w accelerated implementations.
+ *
+ * Copyright (c) 2015 Sabrina Dubroca <sd@queasysnail.net>
+ */
+#ifndef _NET_MACSEC_H_
+#define _NET_MACSEC_H_
+
+#include <linux/u64_stats_sync.h>
+#include <uapi/linux/if_link.h>
+#include <uapi/linux/if_macsec.h>
+
+typedef u64 __bitwise sci_t;
+
+#define MACSEC_NUM_AN 4 /* 2 bits for the association number */
+#define MACSEC_KEYID_LEN 16
+
+/**
+ * struct macsec_key - SA key
+ * @id: user-provided key identifier
+ * @tfm: crypto struct, key storage
+ */
+struct macsec_key {
+	u8 id[MACSEC_KEYID_LEN];
+	struct crypto_aead *tfm;
+};
+
+struct macsec_rx_sc_stats {
+	__u64 InOctetsValidated;
+	__u64 InOctetsDecrypted;
+	__u64 InPktsUnchecked;
+	__u64 InPktsDelayed;
+	__u64 InPktsOK;
+	__u64 InPktsInvalid;
+	__u64 InPktsLate;
+	__u64 InPktsNotValid;
+	__u64 InPktsNotUsingSA;
+	__u64 InPktsUnusedSA;
+};
+
+struct macsec_rx_sa_stats {
+	__u32 InPktsOK;
+	__u32 InPktsInvalid;
+	__u32 InPktsNotValid;
+	__u32 InPktsNotUsingSA;
+	__u32 InPktsUnusedSA;
+};
+
+struct macsec_tx_sa_stats {
+	__u32 OutPktsProtected;
+	__u32 OutPktsEncrypted;
+};
+
+struct macsec_tx_sc_stats {
+	__u64 OutPktsProtected;
+	__u64 OutPktsEncrypted;
+	__u64 OutOctetsProtected;
+	__u64 OutOctetsEncrypted;
+};
+
+/**
+ * struct macsec_rx_sa - receive secure association
+ * @active:
+ * @next_pn: packet number expected for the next packet
+ * @lock: protects next_pn manipulations
+ * @key: key structure
+ * @stats: per-SA stats
+ */
+struct macsec_rx_sa {
+	struct macsec_key key;
+	spinlock_t lock;
+	u32 next_pn;
+	refcount_t refcnt;
+	bool active;
+	struct macsec_rx_sa_stats __percpu *stats;
+	struct macsec_rx_sc *sc;
+	struct rcu_head rcu;
+};
+
+struct pcpu_rx_sc_stats {
+	struct macsec_rx_sc_stats stats;
+	struct u64_stats_sync syncp;
+};
+
+struct pcpu_tx_sc_stats {
+	struct macsec_tx_sc_stats stats;
+	struct u64_stats_sync syncp;
+};
+
+/**
+ * struct macsec_rx_sc - receive secure channel
+ * @sci: secure channel identifier for this SC
+ * @active: channel is active
+ * @sa: array of secure associations
+ * @stats: per-SC stats
+ */
+struct macsec_rx_sc {
+	struct macsec_rx_sc __rcu *next;
+	sci_t sci;
+	bool active;
+	struct macsec_rx_sa __rcu *sa[MACSEC_NUM_AN];
+	struct pcpu_rx_sc_stats __percpu *stats;
+	refcount_t refcnt;
+	struct rcu_head rcu_head;
+};
+
+/**
+ * struct macsec_tx_sa - transmit secure association
+ * @active:
+ * @next_pn: packet number to use for the next packet
+ * @lock: protects next_pn manipulations
+ * @key: key structure
+ * @stats: per-SA stats
+ */
+struct macsec_tx_sa {
+	struct macsec_key key;
+	spinlock_t lock;
+	u32 next_pn;
+	refcount_t refcnt;
+	bool active;
+	bool offloaded;
+	struct macsec_tx_sa_stats __percpu *stats;
+	struct rcu_head rcu;
+};
+
+/**
+ * struct macsec_tx_sc - transmit secure channel
+ * @active:
+ * @encoding_sa: association number of the SA currently in use
+ * @encrypt: encrypt packets on transmit, or authenticate only
+ * @send_sci: always include the SCI in the SecTAG
+ * @end_station:
+ * @scb: single copy broadcast flag
+ * @sa: array of secure associations
+ * @stats: stats for this TXSC
+ */
+struct macsec_tx_sc {
+	bool active;
+	u8 encoding_sa;
+	bool encrypt;
+	bool send_sci;
+	bool end_station;
+	bool scb;
+	struct macsec_tx_sa __rcu *sa[MACSEC_NUM_AN];
+	struct pcpu_tx_sc_stats __percpu *stats;
+};
+
+/**
+ * struct macsec_secy - MACsec Security Entity
+ * @netdev: netdevice for this SecY
+ * @n_rx_sc: number of receive secure channels configured on this SecY
+ * @sci: secure channel identifier used for tx
+ * @key_len: length of keys used by the cipher suite
+ * @icv_len: length of ICV used by the cipher suite
+ * @validate_frames: validation mode
+ * @operational: MAC_Operational flag
+ * @protect_frames: enable protection for this SecY
+ * @replay_protect: enable packet number checks on receive
+ * @replay_window: size of the replay window
+ * @tx_sc: transmit secure channel
+ * @rx_sc: linked list of receive secure channels
+ */
+struct macsec_secy {
+	struct net_device *netdev;
+	unsigned int n_rx_sc;
+	sci_t sci;
+	u16 key_len;
+	u16 icv_len;
+	enum macsec_validation_type validate_frames;
+	bool operational;
+	bool protect_frames;
+	bool replay_protect;
+	u32 replay_window;
+	struct macsec_tx_sc tx_sc;
+	struct macsec_rx_sc __rcu *rx_sc;
+};
+
+#endif /* _NET_MACSEC_H_ */
diff --git a/include/uapi/linux/if_macsec.h b/include/uapi/linux/if_macsec.h
index 98e4d5d7c45c..573208cac210 100644
--- a/include/uapi/linux/if_macsec.h
+++ b/include/uapi/linux/if_macsec.h
@@ -14,14 +14,13 @@
 #define _UAPI_MACSEC_H
 
 #include <linux/types.h>
+#include <net/macsec.h>
 
 #define MACSEC_GENL_NAME "macsec"
 #define MACSEC_GENL_VERSION 1
 
 #define MACSEC_MAX_KEY_LEN 128
 
-#define MACSEC_KEYID_LEN 16
-
 /* cipher IDs as per IEEE802.1AEbn-2011 */
 #define MACSEC_CIPHER_ID_GCM_AES_128 0x0080C20001000001ULL
 #define MACSEC_CIPHER_ID_GCM_AES_256 0x0080C20001000002ULL
-- 
2.21.0


^ permalink raw reply related

* [PATCH net-next v2 7/9] net: phy: export __phy_read_page/__phy_write_page
From: Antoine Tenart @ 2019-08-08 14:05 UTC (permalink / raw)
  To: davem, sd, andrew, f.fainelli, hkallweit1
  Cc: Antoine Tenart, netdev, linux-kernel, thomas.petazzoni,
	alexandre.belloni, allan.nielsen, camelia.groza, Simon.Edelhaus
In-Reply-To: <20190808140600.21477-1-antoine.tenart@bootlin.com>

This patch exports the __phy_read_page and __phy_write_page helpers, to
allow reading and setting the current page when a function already holds
the MDIO lock.

This is something the Microsemi PHY driver does during its
initialization because parts of its registers and engines are shared
between ports. With the upcoming MACsec offloading support in this PHY,
we'll need to configure the MACsec engine and to do so changing pages is
required.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
---
 drivers/net/phy/phy-core.c | 6 ++++--
 include/linux/phy.h        | 3 +++
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 16667fbac8bf..09621193ba2c 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -648,15 +648,17 @@ int phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum,
 }
 EXPORT_SYMBOL_GPL(phy_modify_mmd);
 
-static int __phy_read_page(struct phy_device *phydev)
+int __phy_read_page(struct phy_device *phydev)
 {
 	return phydev->drv->read_page(phydev);
 }
+EXPORT_SYMBOL_GPL(__phy_read_page);
 
-static int __phy_write_page(struct phy_device *phydev, int page)
+int __phy_write_page(struct phy_device *phydev, int page)
 {
 	return phydev->drv->write_page(phydev, page);
 }
+EXPORT_SYMBOL_GPL(__phy_write_page);
 
 /**
  * phy_save_page() - take the bus lock and save the current page
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 6947a19587e4..a64b99158b38 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -792,6 +792,9 @@ int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask,
 			 u16 set);
 int phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask,
 		       u16 set);
+int __phy_read_page(struct phy_device *phydev);
+int __phy_write_page(struct phy_device *phydev, int page);
+
 int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set);
 int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set);
 
-- 
2.21.0


^ permalink raw reply related


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox