linux-stable/drivers/net/dsa/mt7530.c

3440 lines
90 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Mediatek MT7530 DSA Switch driver
* Copyright (C) 2017 Sean Wang <sean.wang@mediatek.com>
*/
#include <linux/etherdevice.h>
#include <linux/if_bridge.h>
#include <linux/iopoll.h>
#include <linux/mdio.h>
#include <linux/mfd/syscon.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/of_irq.h>
#include <linux/of_mdio.h>
#include <linux/of_net.h>
#include <linux/of_platform.h>
#include <linux/phylink.h>
#include <linux/regmap.h>
#include <linux/regulator/consumer.h>
#include <linux/reset.h>
#include <linux/gpio/consumer.h>
#include <linux/gpio/driver.h>
#include <net/dsa.h>
#include "mt7530.h"
static struct mt753x_pcs *pcs_to_mt753x_pcs(struct phylink_pcs *pcs)
{
return container_of(pcs, struct mt753x_pcs, pcs);
}
/* String, offset, and register size in bytes if different from 4 bytes */
static const struct mt7530_mib_desc mt7530_mib[] = {
MIB_DESC(1, 0x00, "TxDrop"),
MIB_DESC(1, 0x04, "TxCrcErr"),
MIB_DESC(1, 0x08, "TxUnicast"),
MIB_DESC(1, 0x0c, "TxMulticast"),
MIB_DESC(1, 0x10, "TxBroadcast"),
MIB_DESC(1, 0x14, "TxCollision"),
MIB_DESC(1, 0x18, "TxSingleCollision"),
MIB_DESC(1, 0x1c, "TxMultipleCollision"),
MIB_DESC(1, 0x20, "TxDeferred"),
MIB_DESC(1, 0x24, "TxLateCollision"),
MIB_DESC(1, 0x28, "TxExcessiveCollistion"),
MIB_DESC(1, 0x2c, "TxPause"),
MIB_DESC(1, 0x30, "TxPktSz64"),
MIB_DESC(1, 0x34, "TxPktSz65To127"),
MIB_DESC(1, 0x38, "TxPktSz128To255"),
MIB_DESC(1, 0x3c, "TxPktSz256To511"),
MIB_DESC(1, 0x40, "TxPktSz512To1023"),
MIB_DESC(1, 0x44, "Tx1024ToMax"),
MIB_DESC(2, 0x48, "TxBytes"),
MIB_DESC(1, 0x60, "RxDrop"),
MIB_DESC(1, 0x64, "RxFiltering"),
MIB_DESC(1, 0x68, "RxUnicast"),
MIB_DESC(1, 0x6c, "RxMulticast"),
MIB_DESC(1, 0x70, "RxBroadcast"),
MIB_DESC(1, 0x74, "RxAlignErr"),
MIB_DESC(1, 0x78, "RxCrcErr"),
MIB_DESC(1, 0x7c, "RxUnderSizeErr"),
MIB_DESC(1, 0x80, "RxFragErr"),
MIB_DESC(1, 0x84, "RxOverSzErr"),
MIB_DESC(1, 0x88, "RxJabberErr"),
MIB_DESC(1, 0x8c, "RxPause"),
MIB_DESC(1, 0x90, "RxPktSz64"),
MIB_DESC(1, 0x94, "RxPktSz65To127"),
MIB_DESC(1, 0x98, "RxPktSz128To255"),
MIB_DESC(1, 0x9c, "RxPktSz256To511"),
MIB_DESC(1, 0xa0, "RxPktSz512To1023"),
MIB_DESC(1, 0xa4, "RxPktSz1024ToMax"),
MIB_DESC(2, 0xa8, "RxBytes"),
MIB_DESC(1, 0xb0, "RxCtrlDrop"),
MIB_DESC(1, 0xb4, "RxIngressDrop"),
MIB_DESC(1, 0xb8, "RxArlDrop"),
};
/* Since phy_device has not yet been created and
* phy_{read,write}_mmd_indirect is not available, we provide our own
* core_{read,write}_mmd_indirect with core_{clear,write,set} wrappers
* to complete this function.
*/
static int
core_read_mmd_indirect(struct mt7530_priv *priv, int prtad, int devad)
{
struct mii_bus *bus = priv->bus;
int value, ret;
/* Write the desired MMD Devad */
ret = bus->write(bus, 0, MII_MMD_CTRL, devad);
if (ret < 0)
goto err;
/* Write the desired MMD register address */
ret = bus->write(bus, 0, MII_MMD_DATA, prtad);
if (ret < 0)
goto err;
/* Select the Function : DATA with no post increment */
ret = bus->write(bus, 0, MII_MMD_CTRL, (devad | MII_MMD_CTRL_NOINCR));
if (ret < 0)
goto err;
/* Read the content of the MMD's selected register */
value = bus->read(bus, 0, MII_MMD_DATA);
return value;
err:
dev_err(&bus->dev, "failed to read mmd register\n");
return ret;
}
static int
core_write_mmd_indirect(struct mt7530_priv *priv, int prtad,
int devad, u32 data)
{
struct mii_bus *bus = priv->bus;
int ret;
/* Write the desired MMD Devad */
ret = bus->write(bus, 0, MII_MMD_CTRL, devad);
if (ret < 0)
goto err;
/* Write the desired MMD register address */
ret = bus->write(bus, 0, MII_MMD_DATA, prtad);
if (ret < 0)
goto err;
/* Select the Function : DATA with no post increment */
ret = bus->write(bus, 0, MII_MMD_CTRL, (devad | MII_MMD_CTRL_NOINCR));
if (ret < 0)
goto err;
/* Write the data into MMD's selected register */
ret = bus->write(bus, 0, MII_MMD_DATA, data);
err:
if (ret < 0)
dev_err(&bus->dev,
"failed to write mmd register\n");
return ret;
}
static void
mt7530_mutex_lock(struct mt7530_priv *priv)
{
if (priv->bus)
mutex_lock_nested(&priv->bus->mdio_lock, MDIO_MUTEX_NESTED);
}
static void
mt7530_mutex_unlock(struct mt7530_priv *priv)
{
if (priv->bus)
mutex_unlock(&priv->bus->mdio_lock);
}
static void
core_write(struct mt7530_priv *priv, u32 reg, u32 val)
{
mt7530_mutex_lock(priv);
core_write_mmd_indirect(priv, reg, MDIO_MMD_VEND2, val);
mt7530_mutex_unlock(priv);
}
static void
core_rmw(struct mt7530_priv *priv, u32 reg, u32 mask, u32 set)
{
u32 val;
mt7530_mutex_lock(priv);
val = core_read_mmd_indirect(priv, reg, MDIO_MMD_VEND2);
val &= ~mask;
val |= set;
core_write_mmd_indirect(priv, reg, MDIO_MMD_VEND2, val);
mt7530_mutex_unlock(priv);
}
static void
core_set(struct mt7530_priv *priv, u32 reg, u32 val)
{
core_rmw(priv, reg, 0, val);
}
static void
core_clear(struct mt7530_priv *priv, u32 reg, u32 val)
{
core_rmw(priv, reg, val, 0);
}
static int
mt7530_mii_write(struct mt7530_priv *priv, u32 reg, u32 val)
{
int ret;
ret = regmap_write(priv->regmap, reg, val);
if (ret < 0)
dev_err(priv->dev,
"failed to write mt7530 register\n");
return ret;
}
static u32
mt7530_mii_read(struct mt7530_priv *priv, u32 reg)
{
int ret;
u32 val;
ret = regmap_read(priv->regmap, reg, &val);
if (ret) {
WARN_ON_ONCE(1);
dev_err(priv->dev,
"failed to read mt7530 register\n");
return 0;
}
return val;
}
static void
mt7530_write(struct mt7530_priv *priv, u32 reg, u32 val)
{
mt7530_mutex_lock(priv);
mt7530_mii_write(priv, reg, val);
mt7530_mutex_unlock(priv);
}
static u32
_mt7530_unlocked_read(struct mt7530_dummy_poll *p)
{
return mt7530_mii_read(p->priv, p->reg);
}
static u32
_mt7530_read(struct mt7530_dummy_poll *p)
{
u32 val;
mt7530_mutex_lock(p->priv);
val = mt7530_mii_read(p->priv, p->reg);
mt7530_mutex_unlock(p->priv);
return val;
}
static u32
mt7530_read(struct mt7530_priv *priv, u32 reg)
{
struct mt7530_dummy_poll p;
INIT_MT7530_DUMMY_POLL(&p, priv, reg);
return _mt7530_read(&p);
}
static void
mt7530_rmw(struct mt7530_priv *priv, u32 reg,
u32 mask, u32 set)
{
mt7530_mutex_lock(priv);
regmap_update_bits(priv->regmap, reg, mask, set);
mt7530_mutex_unlock(priv);
}
static void
mt7530_set(struct mt7530_priv *priv, u32 reg, u32 val)
{
mt7530_rmw(priv, reg, val, val);
}
static void
mt7530_clear(struct mt7530_priv *priv, u32 reg, u32 val)
{
mt7530_rmw(priv, reg, val, 0);
}
static int
mt7530_fdb_cmd(struct mt7530_priv *priv, enum mt7530_fdb_cmd cmd, u32 *rsp)
{
u32 val;
int ret;
struct mt7530_dummy_poll p;
/* Set the command operating upon the MAC address entries */
val = ATC_BUSY | ATC_MAT(0) | cmd;
mt7530_write(priv, MT7530_ATC, val);
INIT_MT7530_DUMMY_POLL(&p, priv, MT7530_ATC);
ret = readx_poll_timeout(_mt7530_read, &p, val,
!(val & ATC_BUSY), 20, 20000);
if (ret < 0) {
dev_err(priv->dev, "reset timeout\n");
return ret;
}
/* Additional sanity for read command if the specified
* entry is invalid
*/
val = mt7530_read(priv, MT7530_ATC);
if ((cmd == MT7530_FDB_READ) && (val & ATC_INVALID))
return -EINVAL;
if (rsp)
*rsp = val;
return 0;
}
static void
mt7530_fdb_read(struct mt7530_priv *priv, struct mt7530_fdb *fdb)
{
u32 reg[3];
int i;
/* Read from ARL table into an array */
for (i = 0; i < 3; i++) {
reg[i] = mt7530_read(priv, MT7530_TSRA1 + (i * 4));
dev_dbg(priv->dev, "%s(%d) reg[%d]=0x%x\n",
__func__, __LINE__, i, reg[i]);
}
fdb->vid = (reg[1] >> CVID) & CVID_MASK;
fdb->aging = (reg[2] >> AGE_TIMER) & AGE_TIMER_MASK;
fdb->port_mask = (reg[2] >> PORT_MAP) & PORT_MAP_MASK;
fdb->mac[0] = (reg[0] >> MAC_BYTE_0) & MAC_BYTE_MASK;
fdb->mac[1] = (reg[0] >> MAC_BYTE_1) & MAC_BYTE_MASK;
fdb->mac[2] = (reg[0] >> MAC_BYTE_2) & MAC_BYTE_MASK;
fdb->mac[3] = (reg[0] >> MAC_BYTE_3) & MAC_BYTE_MASK;
fdb->mac[4] = (reg[1] >> MAC_BYTE_4) & MAC_BYTE_MASK;
fdb->mac[5] = (reg[1] >> MAC_BYTE_5) & MAC_BYTE_MASK;
fdb->noarp = ((reg[2] >> ENT_STATUS) & ENT_STATUS_MASK) == STATIC_ENT;
}
static void
mt7530_fdb_write(struct mt7530_priv *priv, u16 vid,
u8 port_mask, const u8 *mac,
u8 aging, u8 type)
{
u32 reg[3] = { 0 };
int i;
reg[1] |= vid & CVID_MASK;
reg[1] |= ATA2_IVL;
reg[1] |= ATA2_FID(FID_BRIDGED);
reg[2] |= (aging & AGE_TIMER_MASK) << AGE_TIMER;
reg[2] |= (port_mask & PORT_MAP_MASK) << PORT_MAP;
/* STATIC_ENT indicate that entry is static wouldn't
* be aged out and STATIC_EMP specified as erasing an
* entry
*/
reg[2] |= (type & ENT_STATUS_MASK) << ENT_STATUS;
reg[1] |= mac[5] << MAC_BYTE_5;
reg[1] |= mac[4] << MAC_BYTE_4;
reg[0] |= mac[3] << MAC_BYTE_3;
reg[0] |= mac[2] << MAC_BYTE_2;
reg[0] |= mac[1] << MAC_BYTE_1;
reg[0] |= mac[0] << MAC_BYTE_0;
/* Write array into the ARL table */
for (i = 0; i < 3; i++)
mt7530_write(priv, MT7530_ATA1 + (i * 4), reg[i]);
}
net: dsa: mt7530: permit port 5 to work without port 6 on MT7621 SoC The MT7530 switch from the MT7621 SoC has 2 ports which can be set up as internal: port 5 and 6. Arınç reports that the GMAC1 attached to port 5 receives corrupted frames, unless port 6 (attached to GMAC0) has been brought up by the driver. This is true regardless of whether port 5 is used as a user port or as a CPU port (carrying DSA tags). Offline debugging (blind for me) which began in the linked thread showed experimentally that the configuration done by the driver for port 6 contains a step which is needed by port 5 as well - the write to CORE_GSWPLL_GRP2 (note that I've no idea as to what it does, apart from the comment "Set core clock into 500Mhz"). Prints put by Arınç show that the reset value of CORE_GSWPLL_GRP2 is RG_GSWPLL_POSDIV_500M(1) | RG_GSWPLL_FBKDIV_500M(40) (0x128), both on the MCM MT7530 from the MT7621 SoC, as well as on the standalone MT7530 from MT7623NI Bananapi BPI-R2. Apparently, port 5 on the standalone MT7530 can work under both values of the register, while on the MT7621 SoC it cannot. The call path that triggers the register write is: mt753x_phylink_mac_config() for port 6 -> mt753x_pad_setup() -> mt7530_pad_clk_setup() so this fully explains the behavior noticed by Arınç, that bringing port 6 up is necessary. The simplest fix for the problem is to extract the register writes which are needed for both port 5 and 6 into a common mt7530_pll_setup() function, which is called at mt7530_setup() time, immediately after switch reset. We can argue that this mirrors the code layout introduced in mt7531_setup() by commit 42bc4fafe359 ("net: mt7531: only do PLL once after the reset"), in that the PLL setup has the exact same positioning, and further work to consolidate the separate setup() functions is not hindered. Testing confirms that: - the slight reordering of writes to MT7530_P6ECR and to CORE_GSWPLL_GRP1 / CORE_GSWPLL_GRP2 introduced by this change does not appear to cause problems for the operation of port 6 on MT7621 and on MT7623 (where port 5 also always worked) - packets sent through port 5 are not corrupted anymore, regardless of whether port 6 is enabled by phylink or not (or even present in the device tree) My algorithm for determining the Fixes: tag is as follows. Testing shows that some logic from mt7530_pad_clk_setup() is needed even for port 5. Prior to commit ca366d6c889b ("net: dsa: mt7530: Convert to PHYLINK API"), a call did exist for all phy_is_pseudo_fixed_link() ports - so port 5 included. That commit replaced it with a temporary "Port 5 is not supported!" comment, and the following commit 38f790a80560 ("net: dsa: mt7530: Add support for port 5") replaced that comment with a configuration procedure in mt7530_setup_port5() which was insufficient for port 5 to work. I'm laying the blame on the patch that claimed support for port 5, although one would have also needed the change from commit c3b8e07909db ("net: dsa: mt7530: setup core clock even in TRGMII mode") for the write to be performed completely independently from port 6's configuration. Thanks go to Arınç for describing the problem, for debugging and for testing. Reported-by: Arınç ÜNAL <arinc.unal@arinc9.com> Link: https://lore.kernel.org/netdev/f297c2c4-6e7c-57ac-2394-f6025d309b9d@arinc9.com/ Fixes: 38f790a80560 ("net: dsa: mt7530: Add support for port 5") Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Arınç ÜNAL <arinc.unal@arinc9.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Link: https://lore.kernel.org/r/20230307155411.868573-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-03-07 15:54:11 +00:00
/* Set up switch core clock for MT7530 */
static void mt7530_pll_setup(struct mt7530_priv *priv)
{
/* Disable core clock */
core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
net: dsa: mt7530: permit port 5 to work without port 6 on MT7621 SoC The MT7530 switch from the MT7621 SoC has 2 ports which can be set up as internal: port 5 and 6. Arınç reports that the GMAC1 attached to port 5 receives corrupted frames, unless port 6 (attached to GMAC0) has been brought up by the driver. This is true regardless of whether port 5 is used as a user port or as a CPU port (carrying DSA tags). Offline debugging (blind for me) which began in the linked thread showed experimentally that the configuration done by the driver for port 6 contains a step which is needed by port 5 as well - the write to CORE_GSWPLL_GRP2 (note that I've no idea as to what it does, apart from the comment "Set core clock into 500Mhz"). Prints put by Arınç show that the reset value of CORE_GSWPLL_GRP2 is RG_GSWPLL_POSDIV_500M(1) | RG_GSWPLL_FBKDIV_500M(40) (0x128), both on the MCM MT7530 from the MT7621 SoC, as well as on the standalone MT7530 from MT7623NI Bananapi BPI-R2. Apparently, port 5 on the standalone MT7530 can work under both values of the register, while on the MT7621 SoC it cannot. The call path that triggers the register write is: mt753x_phylink_mac_config() for port 6 -> mt753x_pad_setup() -> mt7530_pad_clk_setup() so this fully explains the behavior noticed by Arınç, that bringing port 6 up is necessary. The simplest fix for the problem is to extract the register writes which are needed for both port 5 and 6 into a common mt7530_pll_setup() function, which is called at mt7530_setup() time, immediately after switch reset. We can argue that this mirrors the code layout introduced in mt7531_setup() by commit 42bc4fafe359 ("net: mt7531: only do PLL once after the reset"), in that the PLL setup has the exact same positioning, and further work to consolidate the separate setup() functions is not hindered. Testing confirms that: - the slight reordering of writes to MT7530_P6ECR and to CORE_GSWPLL_GRP1 / CORE_GSWPLL_GRP2 introduced by this change does not appear to cause problems for the operation of port 6 on MT7621 and on MT7623 (where port 5 also always worked) - packets sent through port 5 are not corrupted anymore, regardless of whether port 6 is enabled by phylink or not (or even present in the device tree) My algorithm for determining the Fixes: tag is as follows. Testing shows that some logic from mt7530_pad_clk_setup() is needed even for port 5. Prior to commit ca366d6c889b ("net: dsa: mt7530: Convert to PHYLINK API"), a call did exist for all phy_is_pseudo_fixed_link() ports - so port 5 included. That commit replaced it with a temporary "Port 5 is not supported!" comment, and the following commit 38f790a80560 ("net: dsa: mt7530: Add support for port 5") replaced that comment with a configuration procedure in mt7530_setup_port5() which was insufficient for port 5 to work. I'm laying the blame on the patch that claimed support for port 5, although one would have also needed the change from commit c3b8e07909db ("net: dsa: mt7530: setup core clock even in TRGMII mode") for the write to be performed completely independently from port 6's configuration. Thanks go to Arınç for describing the problem, for debugging and for testing. Reported-by: Arınç ÜNAL <arinc.unal@arinc9.com> Link: https://lore.kernel.org/netdev/f297c2c4-6e7c-57ac-2394-f6025d309b9d@arinc9.com/ Fixes: 38f790a80560 ("net: dsa: mt7530: Add support for port 5") Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Arınç ÜNAL <arinc.unal@arinc9.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Link: https://lore.kernel.org/r/20230307155411.868573-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-03-07 15:54:11 +00:00
/* Disable PLL */
core_write(priv, CORE_GSWPLL_GRP1, 0);
/* Set core clock into 500Mhz */
core_write(priv, CORE_GSWPLL_GRP2,
RG_GSWPLL_POSDIV_500M(1) |
RG_GSWPLL_FBKDIV_500M(25));
/* Enable PLL */
core_write(priv, CORE_GSWPLL_GRP1,
RG_GSWPLL_EN_PRE |
RG_GSWPLL_POSDIV_200M(2) |
RG_GSWPLL_FBKDIV_200M(32));
udelay(20);
/* Enable core clock */
core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
net: dsa: mt7530: permit port 5 to work without port 6 on MT7621 SoC The MT7530 switch from the MT7621 SoC has 2 ports which can be set up as internal: port 5 and 6. Arınç reports that the GMAC1 attached to port 5 receives corrupted frames, unless port 6 (attached to GMAC0) has been brought up by the driver. This is true regardless of whether port 5 is used as a user port or as a CPU port (carrying DSA tags). Offline debugging (blind for me) which began in the linked thread showed experimentally that the configuration done by the driver for port 6 contains a step which is needed by port 5 as well - the write to CORE_GSWPLL_GRP2 (note that I've no idea as to what it does, apart from the comment "Set core clock into 500Mhz"). Prints put by Arınç show that the reset value of CORE_GSWPLL_GRP2 is RG_GSWPLL_POSDIV_500M(1) | RG_GSWPLL_FBKDIV_500M(40) (0x128), both on the MCM MT7530 from the MT7621 SoC, as well as on the standalone MT7530 from MT7623NI Bananapi BPI-R2. Apparently, port 5 on the standalone MT7530 can work under both values of the register, while on the MT7621 SoC it cannot. The call path that triggers the register write is: mt753x_phylink_mac_config() for port 6 -> mt753x_pad_setup() -> mt7530_pad_clk_setup() so this fully explains the behavior noticed by Arınç, that bringing port 6 up is necessary. The simplest fix for the problem is to extract the register writes which are needed for both port 5 and 6 into a common mt7530_pll_setup() function, which is called at mt7530_setup() time, immediately after switch reset. We can argue that this mirrors the code layout introduced in mt7531_setup() by commit 42bc4fafe359 ("net: mt7531: only do PLL once after the reset"), in that the PLL setup has the exact same positioning, and further work to consolidate the separate setup() functions is not hindered. Testing confirms that: - the slight reordering of writes to MT7530_P6ECR and to CORE_GSWPLL_GRP1 / CORE_GSWPLL_GRP2 introduced by this change does not appear to cause problems for the operation of port 6 on MT7621 and on MT7623 (where port 5 also always worked) - packets sent through port 5 are not corrupted anymore, regardless of whether port 6 is enabled by phylink or not (or even present in the device tree) My algorithm for determining the Fixes: tag is as follows. Testing shows that some logic from mt7530_pad_clk_setup() is needed even for port 5. Prior to commit ca366d6c889b ("net: dsa: mt7530: Convert to PHYLINK API"), a call did exist for all phy_is_pseudo_fixed_link() ports - so port 5 included. That commit replaced it with a temporary "Port 5 is not supported!" comment, and the following commit 38f790a80560 ("net: dsa: mt7530: Add support for port 5") replaced that comment with a configuration procedure in mt7530_setup_port5() which was insufficient for port 5 to work. I'm laying the blame on the patch that claimed support for port 5, although one would have also needed the change from commit c3b8e07909db ("net: dsa: mt7530: setup core clock even in TRGMII mode") for the write to be performed completely independently from port 6's configuration. Thanks go to Arınç for describing the problem, for debugging and for testing. Reported-by: Arınç ÜNAL <arinc.unal@arinc9.com> Link: https://lore.kernel.org/netdev/f297c2c4-6e7c-57ac-2394-f6025d309b9d@arinc9.com/ Fixes: 38f790a80560 ("net: dsa: mt7530: Add support for port 5") Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Arınç ÜNAL <arinc.unal@arinc9.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Link: https://lore.kernel.org/r/20230307155411.868573-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-03-07 15:54:11 +00:00
}
net: dsa: introduce preferred_default_local_cpu_port and use on MT7530 Since the introduction of the OF bindings, DSA has always had a policy that in case multiple CPU ports are present in the device tree, the numerically smallest one is always chosen. The MT7530 switch family, except the switch on the MT7988 SoC, has 2 CPU ports, 5 and 6, where port 6 is preferable on the MT7531BE switch because it has higher bandwidth. The MT7530 driver developers had 3 options: - to modify DSA when the MT7531 switch support was introduced, such as to prefer the better port - to declare both CPU ports in device trees as CPU ports, and live with the sub-optimal performance resulting from not preferring the better port - to declare just port 6 in the device tree as a CPU port Of course they chose the path of least resistance (3rd option), kicking the can down the road. The hardware description in the device tree is supposed to be stable - developers are not supposed to adopt the strategy of piecemeal hardware description, where the device tree is updated in lockstep with the features that the kernel currently supports. Now, as a result of the fact that they did that, any attempts to modify the device tree and describe both CPU ports as CPU ports would make DSA change its default selection from port 6 to 5, effectively resulting in a performance degradation visible to users with the MT7531BE switch as can be seen below. Without preferring port 6: [ ID][Role] Interval Transfer Bitrate Retr [ 5][TX-C] 0.00-20.00 sec 374 MBytes 157 Mbits/sec 734 sender [ 5][TX-C] 0.00-20.00 sec 373 MBytes 156 Mbits/sec receiver [ 7][RX-C] 0.00-20.00 sec 1.81 GBytes 778 Mbits/sec 0 sender [ 7][RX-C] 0.00-20.00 sec 1.81 GBytes 777 Mbits/sec receiver With preferring port 6: [ ID][Role] Interval Transfer Bitrate Retr [ 5][TX-C] 0.00-20.00 sec 1.99 GBytes 856 Mbits/sec 273 sender [ 5][TX-C] 0.00-20.00 sec 1.99 GBytes 855 Mbits/sec receiver [ 7][RX-C] 0.00-20.00 sec 1.72 GBytes 737 Mbits/sec 15 sender [ 7][RX-C] 0.00-20.00 sec 1.71 GBytes 736 Mbits/sec receiver Using one port for WAN and the other ports for LAN is a very popular use case which is what this test emulates. As such, this change proposes that we retroactively modify stable kernels (which don't support the modification of the CPU port assignments, so as to let user space fix the problem and restore the throughput) to keep the mt7530 driver preferring port 6 even with device trees where the hardware is more fully described. Fixes: c288575f7810 ("net: dsa: mt7530: Add the support of MT7531 switch") Signed-off-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-17 06:26:48 +00:00
/* If port 6 is available as a CPU port, always prefer that as the default,
* otherwise don't care.
*/
static struct dsa_port *
mt753x_preferred_default_local_cpu_port(struct dsa_switch *ds)
{
struct dsa_port *cpu_dp = dsa_to_port(ds, 6);
if (dsa_port_is_cpu(cpu_dp))
return cpu_dp;
return NULL;
}
/* Setup port 6 interface mode and TRGMII TX circuit */
static int
mt7530_pad_clk_setup(struct dsa_switch *ds, phy_interface_t interface)
{
struct mt7530_priv *priv = ds->priv;
u32 ncpo1, ssc_delta, trgint, xtal;
xtal = mt7530_read(priv, MT7530_MHWTRAP) & HWTRAP_XTAL_MASK;
if (xtal == HWTRAP_XTAL_20MHZ) {
dev_err(priv->dev,
"%s: MT7530 with a 20MHz XTAL is not supported!\n",
__func__);
return -EINVAL;
}
switch (interface) {
case PHY_INTERFACE_MODE_RGMII:
trgint = 0;
break;
case PHY_INTERFACE_MODE_TRGMII:
trgint = 1;
if (xtal == HWTRAP_XTAL_25MHZ)
ssc_delta = 0x57;
else
ssc_delta = 0x87;
if (priv->id == ID_MT7621) {
/* PLL frequency: 125MHz: 1.0GBit */
if (xtal == HWTRAP_XTAL_40MHZ)
ncpo1 = 0x0640;
if (xtal == HWTRAP_XTAL_25MHZ)
ncpo1 = 0x0a00;
} else { /* PLL frequency: 250MHz: 2.0Gbit */
if (xtal == HWTRAP_XTAL_40MHZ)
ncpo1 = 0x0c80;
if (xtal == HWTRAP_XTAL_25MHZ)
ncpo1 = 0x1400;
}
break;
default:
dev_err(priv->dev, "xMII interface %d not supported\n",
interface);
return -EINVAL;
}
mt7530_rmw(priv, MT7530_P6ECR, P6_INTF_MODE_MASK,
P6_INTF_MODE(trgint));
if (trgint) {
/* Disable the MT7530 TRGMII clocks */
core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_TRGMIICK_EN);
/* Setup the MT7530 TRGMII Tx Clock */
core_write(priv, CORE_PLL_GROUP5, RG_LCDDS_PCW_NCPO1(ncpo1));
core_write(priv, CORE_PLL_GROUP6, RG_LCDDS_PCW_NCPO0(0));
core_write(priv, CORE_PLL_GROUP10, RG_LCDDS_SSC_DELTA(ssc_delta));
core_write(priv, CORE_PLL_GROUP11, RG_LCDDS_SSC_DELTA1(ssc_delta));
core_write(priv, CORE_PLL_GROUP4,
RG_SYSPLL_DDSFBK_EN | RG_SYSPLL_BIAS_EN |
RG_SYSPLL_BIAS_LPF_EN);
core_write(priv, CORE_PLL_GROUP2,
RG_SYSPLL_EN_NORMAL | RG_SYSPLL_VODEN |
RG_SYSPLL_POSDIV(1));
core_write(priv, CORE_PLL_GROUP7,
RG_LCDDS_PCW_NCPO_CHG | RG_LCCDS_C(3) |
RG_LCDDS_PWDB | RG_LCDDS_ISO_EN);
/* Enable the MT7530 TRGMII clocks */
core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_TRGMIICK_EN);
}
return 0;
}
static bool mt7531_dual_sgmii_supported(struct mt7530_priv *priv)
{
u32 val;
val = mt7530_read(priv, MT7531_TOP_SIG_SR);
return (val & PAD_DUAL_SGMII_EN) != 0;
}
static int
mt7531_pad_setup(struct dsa_switch *ds, phy_interface_t interface)
{
return 0;
}
static void
mt7531_pll_setup(struct mt7530_priv *priv)
{
u32 top_sig;
u32 hwstrap;
u32 xtal;
u32 val;
if (mt7531_dual_sgmii_supported(priv))
return;
val = mt7530_read(priv, MT7531_CREV);
top_sig = mt7530_read(priv, MT7531_TOP_SIG_SR);
hwstrap = mt7530_read(priv, MT7531_HWTRAP);
if ((val & CHIP_REV_M) > 0)
xtal = (top_sig & PAD_MCM_SMI_EN) ? HWTRAP_XTAL_FSEL_40MHZ :
HWTRAP_XTAL_FSEL_25MHZ;
else
xtal = hwstrap & HWTRAP_XTAL_FSEL_MASK;
/* Step 1 : Disable MT7531 COREPLL */
val = mt7530_read(priv, MT7531_PLLGP_EN);
val &= ~EN_COREPLL;
mt7530_write(priv, MT7531_PLLGP_EN, val);
/* Step 2: switch to XTAL output */
val = mt7530_read(priv, MT7531_PLLGP_EN);
val |= SW_CLKSW;
mt7530_write(priv, MT7531_PLLGP_EN, val);
val = mt7530_read(priv, MT7531_PLLGP_CR0);
val &= ~RG_COREPLL_EN;
mt7530_write(priv, MT7531_PLLGP_CR0, val);
/* Step 3: disable PLLGP and enable program PLLGP */
val = mt7530_read(priv, MT7531_PLLGP_EN);
val |= SW_PLLGP;
mt7530_write(priv, MT7531_PLLGP_EN, val);
/* Step 4: program COREPLL output frequency to 500MHz */
val = mt7530_read(priv, MT7531_PLLGP_CR0);
val &= ~RG_COREPLL_POSDIV_M;
val |= 2 << RG_COREPLL_POSDIV_S;
mt7530_write(priv, MT7531_PLLGP_CR0, val);
usleep_range(25, 35);
switch (xtal) {
case HWTRAP_XTAL_FSEL_25MHZ:
val = mt7530_read(priv, MT7531_PLLGP_CR0);
val &= ~RG_COREPLL_SDM_PCW_M;
val |= 0x140000 << RG_COREPLL_SDM_PCW_S;
mt7530_write(priv, MT7531_PLLGP_CR0, val);
break;
case HWTRAP_XTAL_FSEL_40MHZ:
val = mt7530_read(priv, MT7531_PLLGP_CR0);
val &= ~RG_COREPLL_SDM_PCW_M;
val |= 0x190000 << RG_COREPLL_SDM_PCW_S;
mt7530_write(priv, MT7531_PLLGP_CR0, val);
break;
}
/* Set feedback divide ratio update signal to high */
val = mt7530_read(priv, MT7531_PLLGP_CR0);
val |= RG_COREPLL_SDM_PCW_CHG;
mt7530_write(priv, MT7531_PLLGP_CR0, val);
/* Wait for at least 16 XTAL clocks */
usleep_range(10, 20);
/* Step 5: set feedback divide ratio update signal to low */
val = mt7530_read(priv, MT7531_PLLGP_CR0);
val &= ~RG_COREPLL_SDM_PCW_CHG;
mt7530_write(priv, MT7531_PLLGP_CR0, val);
/* Enable 325M clock for SGMII */
mt7530_write(priv, MT7531_ANA_PLLGP_CR5, 0xad0000);
/* Enable 250SSC clock for RGMII */
mt7530_write(priv, MT7531_ANA_PLLGP_CR2, 0x4f40000);
/* Step 6: Enable MT7531 PLL */
val = mt7530_read(priv, MT7531_PLLGP_CR0);
val |= RG_COREPLL_EN;
mt7530_write(priv, MT7531_PLLGP_CR0, val);
val = mt7530_read(priv, MT7531_PLLGP_EN);
val |= EN_COREPLL;
mt7530_write(priv, MT7531_PLLGP_EN, val);
usleep_range(25, 35);
}
static void
mt7530_mib_reset(struct dsa_switch *ds)
{
struct mt7530_priv *priv = ds->priv;
mt7530_write(priv, MT7530_MIB_CCR, CCR_MIB_FLUSH);
mt7530_write(priv, MT7530_MIB_CCR, CCR_MIB_ACTIVATE);
}
static int mt7530_phy_read_c22(struct mt7530_priv *priv, int port, int regnum)
{
return mdiobus_read_nested(priv->bus, port, regnum);
}
static int mt7530_phy_write_c22(struct mt7530_priv *priv, int port, int regnum,
u16 val)
{
return mdiobus_write_nested(priv->bus, port, regnum, val);
}
static int mt7530_phy_read_c45(struct mt7530_priv *priv, int port,
int devad, int regnum)
{
return mdiobus_c45_read_nested(priv->bus, port, devad, regnum);
}
static int mt7530_phy_write_c45(struct mt7530_priv *priv, int port, int devad,
int regnum, u16 val)
{
return mdiobus_c45_write_nested(priv->bus, port, devad, regnum, val);
}
static int
mt7531_ind_c45_phy_read(struct mt7530_priv *priv, int port, int devad,
int regnum)
{
struct mt7530_dummy_poll p;
u32 reg, val;
int ret;
INIT_MT7530_DUMMY_POLL(&p, priv, MT7531_PHY_IAC);
mt7530_mutex_lock(priv);
ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val,
!(val & MT7531_PHY_ACS_ST), 20, 100000);
if (ret < 0) {
dev_err(priv->dev, "poll timeout\n");
goto out;
}
reg = MT7531_MDIO_CL45_ADDR | MT7531_MDIO_PHY_ADDR(port) |
MT7531_MDIO_DEV_ADDR(devad) | regnum;
mt7530_mii_write(priv, MT7531_PHY_IAC, reg | MT7531_PHY_ACS_ST);
ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val,
!(val & MT7531_PHY_ACS_ST), 20, 100000);
if (ret < 0) {
dev_err(priv->dev, "poll timeout\n");
goto out;
}
reg = MT7531_MDIO_CL45_READ | MT7531_MDIO_PHY_ADDR(port) |
MT7531_MDIO_DEV_ADDR(devad);
mt7530_mii_write(priv, MT7531_PHY_IAC, reg | MT7531_PHY_ACS_ST);
ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val,
!(val & MT7531_PHY_ACS_ST), 20, 100000);
if (ret < 0) {
dev_err(priv->dev, "poll timeout\n");
goto out;
}
ret = val & MT7531_MDIO_RW_DATA_MASK;
out:
mt7530_mutex_unlock(priv);
return ret;
}
static int
mt7531_ind_c45_phy_write(struct mt7530_priv *priv, int port, int devad,
int regnum, u16 data)
{
struct mt7530_dummy_poll p;
u32 val, reg;
int ret;
INIT_MT7530_DUMMY_POLL(&p, priv, MT7531_PHY_IAC);
mt7530_mutex_lock(priv);
ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val,
!(val & MT7531_PHY_ACS_ST), 20, 100000);
if (ret < 0) {
dev_err(priv->dev, "poll timeout\n");
goto out;
}
reg = MT7531_MDIO_CL45_ADDR | MT7531_MDIO_PHY_ADDR(port) |
MT7531_MDIO_DEV_ADDR(devad) | regnum;
mt7530_mii_write(priv, MT7531_PHY_IAC, reg | MT7531_PHY_ACS_ST);
ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val,
!(val & MT7531_PHY_ACS_ST), 20, 100000);
if (ret < 0) {
dev_err(priv->dev, "poll timeout\n");
goto out;
}
reg = MT7531_MDIO_CL45_WRITE | MT7531_MDIO_PHY_ADDR(port) |
MT7531_MDIO_DEV_ADDR(devad) | data;
mt7530_mii_write(priv, MT7531_PHY_IAC, reg | MT7531_PHY_ACS_ST);
ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val,
!(val & MT7531_PHY_ACS_ST), 20, 100000);
if (ret < 0) {
dev_err(priv->dev, "poll timeout\n");
goto out;
}
out:
mt7530_mutex_unlock(priv);
return ret;
}
static int
mt7531_ind_c22_phy_read(struct mt7530_priv *priv, int port, int regnum)
{
struct mt7530_dummy_poll p;
int ret;
u32 val;
INIT_MT7530_DUMMY_POLL(&p, priv, MT7531_PHY_IAC);
mt7530_mutex_lock(priv);
ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val,
!(val & MT7531_PHY_ACS_ST), 20, 100000);
if (ret < 0) {
dev_err(priv->dev, "poll timeout\n");
goto out;
}
val = MT7531_MDIO_CL22_READ | MT7531_MDIO_PHY_ADDR(port) |
MT7531_MDIO_REG_ADDR(regnum);
mt7530_mii_write(priv, MT7531_PHY_IAC, val | MT7531_PHY_ACS_ST);
ret = readx_poll_timeout(_mt7530_unlocked_read, &p, val,
!(val & MT7531_PHY_ACS_ST), 20, 100000);
if (ret < 0) {
dev_err(priv->dev, "poll timeout\n");
goto out;
}
ret = val & MT7531_MDIO_RW_DATA_MASK;
out:
mt7530_mutex_unlock(priv);
return ret;
}
static int
mt7531_ind_c22_phy_write(struct mt7530_priv *priv, int port, int regnum,
u16 data)
{
struct mt7530_dummy_poll p;
int ret;
u32 reg;
INIT_MT7530_DUMMY_POLL(&p, priv, MT7531_PHY_IAC);
mt7530_mutex_lock(priv);
ret = readx_poll_timeout(_mt7530_unlocked_read, &p, reg,
!(reg & MT7531_PHY_ACS_ST), 20, 100000);
if (ret < 0) {
dev_err(priv->dev, "poll timeout\n");
goto out;
}
reg = MT7531_MDIO_CL22_WRITE | MT7531_MDIO_PHY_ADDR(port) |
MT7531_MDIO_REG_ADDR(regnum) | data;
mt7530_mii_write(priv, MT7531_PHY_IAC, reg | MT7531_PHY_ACS_ST);
ret = readx_poll_timeout(_mt7530_unlocked_read, &p, reg,
!(reg & MT7531_PHY_ACS_ST), 20, 100000);
if (ret < 0) {
dev_err(priv->dev, "poll timeout\n");
goto out;
}
out:
mt7530_mutex_unlock(priv);
return ret;
}
static int
mt753x_phy_read_c22(struct mii_bus *bus, int port, int regnum)
{
struct mt7530_priv *priv = bus->priv;
return priv->info->phy_read_c22(priv, port, regnum);
}
static int
mt753x_phy_read_c45(struct mii_bus *bus, int port, int devad, int regnum)
{
struct mt7530_priv *priv = bus->priv;
return priv->info->phy_read_c45(priv, port, devad, regnum);
}
static int
mt753x_phy_write_c22(struct mii_bus *bus, int port, int regnum, u16 val)
{
struct mt7530_priv *priv = bus->priv;
return priv->info->phy_write_c22(priv, port, regnum, val);
}
static int
mt753x_phy_write_c45(struct mii_bus *bus, int port, int devad, int regnum,
u16 val)
{
struct mt7530_priv *priv = bus->priv;
return priv->info->phy_write_c45(priv, port, devad, regnum, val);
}
static void
mt7530_get_strings(struct dsa_switch *ds, int port, u32 stringset,
uint8_t *data)
{
int i;
if (stringset != ETH_SS_STATS)
return;
for (i = 0; i < ARRAY_SIZE(mt7530_mib); i++)
ethtool_puts(&data, mt7530_mib[i].name);
}
static void
mt7530_get_ethtool_stats(struct dsa_switch *ds, int port,
uint64_t *data)
{
struct mt7530_priv *priv = ds->priv;
const struct mt7530_mib_desc *mib;
u32 reg, i;
u64 hi;
for (i = 0; i < ARRAY_SIZE(mt7530_mib); i++) {
mib = &mt7530_mib[i];
reg = MT7530_PORT_MIB_COUNTER(port) + mib->offset;
data[i] = mt7530_read(priv, reg);
if (mib->size == 2) {
hi = mt7530_read(priv, reg + 4);
data[i] |= hi << 32;
}
}
}
static int
mt7530_get_sset_count(struct dsa_switch *ds, int port, int sset)
{
if (sset != ETH_SS_STATS)
return 0;
return ARRAY_SIZE(mt7530_mib);
}
static int
mt7530_set_ageing_time(struct dsa_switch *ds, unsigned int msecs)
{
struct mt7530_priv *priv = ds->priv;
unsigned int secs = msecs / 1000;
unsigned int tmp_age_count;
unsigned int error = -1;
unsigned int age_count;
unsigned int age_unit;
/* Applied timer is (AGE_CNT + 1) * (AGE_UNIT + 1) seconds */
if (secs < 1 || secs > (AGE_CNT_MAX + 1) * (AGE_UNIT_MAX + 1))
return -ERANGE;
/* iterate through all possible age_count to find the closest pair */
for (tmp_age_count = 0; tmp_age_count <= AGE_CNT_MAX; ++tmp_age_count) {
unsigned int tmp_age_unit = secs / (tmp_age_count + 1) - 1;
if (tmp_age_unit <= AGE_UNIT_MAX) {
unsigned int tmp_error = secs -
(tmp_age_count + 1) * (tmp_age_unit + 1);
/* found a closer pair */
if (error > tmp_error) {
error = tmp_error;
age_count = tmp_age_count;
age_unit = tmp_age_unit;
}
/* found the exact match, so break the loop */
if (!error)
break;
}
}
mt7530_write(priv, MT7530_AAC, AGE_CNT(age_count) | AGE_UNIT(age_unit));
return 0;
}
static const char *p5_intf_modes(unsigned int p5_interface)
{
switch (p5_interface) {
case P5_DISABLED:
return "DISABLED";
case P5_INTF_SEL_PHY_P0:
return "PHY P0";
case P5_INTF_SEL_PHY_P4:
return "PHY P4";
case P5_INTF_SEL_GMAC5:
return "GMAC5";
case P5_INTF_SEL_GMAC5_SGMII:
return "GMAC5_SGMII";
default:
return "unknown";
}
}
static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface)
{
struct mt7530_priv *priv = ds->priv;
u8 tx_delay = 0;
int val;
mutex_lock(&priv->reg_mutex);
val = mt7530_read(priv, MT7530_MHWTRAP);
val |= MHWTRAP_MANUAL | MHWTRAP_P5_MAC_SEL | MHWTRAP_P5_DIS;
val &= ~MHWTRAP_P5_RGMII_MODE & ~MHWTRAP_PHY0_SEL;
switch (priv->p5_intf_sel) {
case P5_INTF_SEL_PHY_P0:
/* MT7530_P5_MODE_GPHY_P0: 2nd GMAC -> P5 -> P0 */
val |= MHWTRAP_PHY0_SEL;
fallthrough;
case P5_INTF_SEL_PHY_P4:
/* MT7530_P5_MODE_GPHY_P4: 2nd GMAC -> P5 -> P4 */
val &= ~MHWTRAP_P5_MAC_SEL & ~MHWTRAP_P5_DIS;
/* Setup the MAC by default for the cpu port */
mt7530_write(priv, MT7530_PMCR_P(5), 0x56300);
break;
case P5_INTF_SEL_GMAC5:
/* MT7530_P5_MODE_GMAC: P5 -> External phy or 2nd GMAC */
val &= ~MHWTRAP_P5_DIS;
break;
case P5_DISABLED:
interface = PHY_INTERFACE_MODE_NA;
break;
default:
dev_err(ds->dev, "Unsupported p5_intf_sel %d\n",
priv->p5_intf_sel);
goto unlock_exit;
}
/* Setup RGMII settings */
if (phy_interface_mode_is_rgmii(interface)) {
val |= MHWTRAP_P5_RGMII_MODE;
/* P5 RGMII RX Clock Control: delay setting for 1000M */
mt7530_write(priv, MT7530_P5RGMIIRXCR, CSR_RGMII_EDGE_ALIGN);
/* Don't set delay in DSA mode */
if (!dsa_is_dsa_port(priv->ds, 5) &&
(interface == PHY_INTERFACE_MODE_RGMII_TXID ||
interface == PHY_INTERFACE_MODE_RGMII_ID))
tx_delay = 4; /* n * 0.5 ns */
/* P5 RGMII TX Clock Control: delay x */
mt7530_write(priv, MT7530_P5RGMIITXCR,
CSR_RGMII_TXC_CFG(0x10 + tx_delay));
/* reduce P5 RGMII Tx driving, 8mA */
mt7530_write(priv, MT7530_IO_DRV_CR,
P5_IO_CLK_DRV(1) | P5_IO_DATA_DRV(1));
}
mt7530_write(priv, MT7530_MHWTRAP, val);
dev_dbg(ds->dev, "Setup P5, HWTRAP=0x%x, intf_sel=%s, phy-mode=%s\n",
val, p5_intf_modes(priv->p5_intf_sel), phy_modes(interface));
priv->p5_interface = interface;
unlock_exit:
mutex_unlock(&priv->reg_mutex);
}
net: dsa: mt7530: trap link-local frames regardless of ST Port State [ Upstream commit 17c560113231ddc20088553c7b499b289b664311 ] In Clause 5 of IEEE Std 802-2014, two sublayers of the data link layer (DLL) of the Open Systems Interconnection basic reference model (OSI/RM) are described; the medium access control (MAC) and logical link control (LLC) sublayers. The MAC sublayer is the one facing the physical layer. In 8.2 of IEEE Std 802.1Q-2022, the Bridge architecture is described. A Bridge component comprises a MAC Relay Entity for interconnecting the Ports of the Bridge, at least two Ports, and higher layer entities with at least a Spanning Tree Protocol Entity included. Each Bridge Port also functions as an end station and shall provide the MAC Service to an LLC Entity. Each instance of the MAC Service is provided to a distinct LLC Entity that supports protocol identification, multiplexing, and demultiplexing, for protocol data unit (PDU) transmission and reception by one or more higher layer entities. It is described in 8.13.9 of IEEE Std 802.1Q-2022 that in a Bridge, the LLC Entity associated with each Bridge Port is modeled as being directly connected to the attached Local Area Network (LAN). On the switch with CPU port architecture, CPU port functions as Management Port, and the Management Port functionality is provided by software which functions as an end station. Software is connected to an IEEE 802 LAN that is wholly contained within the system that incorporates the Bridge. Software provides access to the LLC Entity associated with each Bridge Port by the value of the source port field on the special tag on the frame received by software. We call frames that carry control information to determine the active topology and current extent of each Virtual Local Area Network (VLAN), i.e., spanning tree or Shortest Path Bridging (SPB) and Multiple VLAN Registration Protocol Data Units (MVRPDUs), and frames from other link constrained protocols, such as Extensible Authentication Protocol over LAN (EAPOL) and Link Layer Discovery Protocol (LLDP), link-local frames. They are not forwarded by a Bridge. Permanently configured entries in the filtering database (FDB) ensure that such frames are discarded by the Forwarding Process. In 8.6.3 of IEEE Std 802.1Q-2022, this is described in detail: Each of the reserved MAC addresses specified in Table 8-1 (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]) shall be permanently configured in the FDB in C-VLAN components and ERs. Each of the reserved MAC addresses specified in Table 8-2 (01-80-C2-00-00-[01,02,03,04,05,06,07,08,09,0A,0E]) shall be permanently configured in the FDB in S-VLAN components. Each of the reserved MAC addresses specified in Table 8-3 (01-80-C2-00-00-[01,02,04,0E]) shall be permanently configured in the FDB in TPMR components. The FDB entries for reserved MAC addresses shall specify filtering for all Bridge Ports and all VIDs. Management shall not provide the capability to modify or remove entries for reserved MAC addresses. The addresses in Table 8-1, Table 8-2, and Table 8-3 determine the scope of propagation of PDUs within a Bridged Network, as follows: The Nearest Bridge group address (01-80-C2-00-00-0E) is an address that no conformant Two-Port MAC Relay (TPMR) component, Service VLAN (S-VLAN) component, Customer VLAN (C-VLAN) component, or MAC Bridge can forward. PDUs transmitted using this destination address, or any other addresses that appear in Table 8-1, Table 8-2, and Table 8-3 (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]), can therefore travel no further than those stations that can be reached via a single individual LAN from the originating station. The Nearest non-TPMR Bridge group address (01-80-C2-00-00-03), is an address that no conformant S-VLAN component, C-VLAN component, or MAC Bridge can forward; however, this address is relayed by a TPMR component. PDUs using this destination address, or any of the other addresses that appear in both Table 8-1 and Table 8-2 but not in Table 8-3 (01-80-C2-00-00-[00,03,05,06,07,08,09,0A,0B,0C,0D,0F]), will be relayed by any TPMRs but will propagate no further than the nearest S-VLAN component, C-VLAN component, or MAC Bridge. The Nearest Customer Bridge group address (01-80-C2-00-00-00) is an address that no conformant C-VLAN component, MAC Bridge can forward; however, it is relayed by TPMR components and S-VLAN components. PDUs using this destination address, or any of the other addresses that appear in Table 8-1 but not in either Table 8-2 or Table 8-3 (01-80-C2-00-00-[00,0B,0C,0D,0F]), will be relayed by TPMR components and S-VLAN components but will propagate no further than the nearest C-VLAN component or MAC Bridge. Because the LLC Entity associated with each Bridge Port is provided via CPU port, we must not filter these frames but forward them to CPU port. In a Bridge, the transmission Port is majorly decided by ingress and egress rules, FDB, and spanning tree Port State functions of the Forwarding Process. For link-local frames, only CPU port should be designated as destination port in the FDB, and the other functions of the Forwarding Process must not interfere with the decision of the transmission Port. We call this process trapping frames to CPU port. Therefore, on the switch with CPU port architecture, link-local frames must be trapped to CPU port, and certain link-local frames received by a Port of a Bridge comprising a TPMR component or an S-VLAN component must be excluded from it. A Bridge of the switch with CPU port architecture cannot comprise a Two-Port MAC Relay (TPMR) component as a TPMR component supports only a subset of the functionality of a MAC Bridge. A Bridge comprising two Ports (Management Port doesn't count) of this architecture will either function as a standard MAC Bridge or a standard VLAN Bridge. Therefore, a Bridge of this architecture can only comprise S-VLAN components, C-VLAN components, or MAC Bridge components. Since there's no TPMR component, we don't need to relay PDUs using the destination addresses specified on the Nearest non-TPMR section, and the proportion of the Nearest Customer Bridge section where they must be relayed by TPMR components. One option to trap link-local frames to CPU port is to add static FDB entries with CPU port designated as destination port. However, because that Independent VLAN Learning (IVL) is being used on every VID, each entry only applies to a single VLAN Identifier (VID). For a Bridge comprising a MAC Bridge component or a C-VLAN component, there would have to be 16 times 4096 entries. This switch intellectual property can only hold a maximum of 2048 entries. Using this option, there also isn't a mechanism to prevent link-local frames from being discarded when the spanning tree Port State of the reception Port is discarding. The remaining option is to utilise the BPC, RGAC1, RGAC2, RGAC3, and RGAC4 registers. Whilst this applies to every VID, it doesn't contain all of the reserved MAC addresses without affecting the remaining Standard Group MAC Addresses. The REV_UN frame tag utilised using the RGAC4 register covers the remaining 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] destination addresses. It also includes the 01-80-C2-00-00-22 to 01-80-C2-00-00-FF destination addresses which may be relayed by MAC Bridges or VLAN Bridges. The latter option provides better but not complete conformance. This switch intellectual property also does not provide a mechanism to trap link-local frames with specific destination addresses to CPU port by Bridge, to conform to the filtering rules for the distinct Bridge components. Therefore, regardless of the type of the Bridge component, link-local frames with these destination addresses will be trapped to CPU port: 01-80-C2-00-00-[00,01,02,03,0E] In a Bridge comprising a MAC Bridge component or a C-VLAN component: Link-local frames with these destination addresses won't be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] In a Bridge comprising an S-VLAN component: Link-local frames with these destination addresses will be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-00 Link-local frames with these destination addresses won't be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-[04,05,06,07,08,09,0A] Currently on this switch intellectual property, if the spanning tree Port State of the reception Port is discarding, link-local frames will be discarded. To trap link-local frames regardless of the spanning tree Port State, make the switch regard them as Bridge Protocol Data Units (BPDUs). This switch intellectual property only lets the frames regarded as BPDUs bypass the spanning tree Port State function of the Forwarding Process. With this change, the only remaining interference is the ingress rules. When the reception Port has no PVID assigned on software, VLAN-untagged frames won't be allowed in. There doesn't seem to be a mechanism on the switch intellectual property to have link-local frames bypass this function of the Forwarding Process. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Reviewed-by: Daniel Golle <daniel@makrotopia.org> Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Link: https://lore.kernel.org/r/20240409-b4-for-net-mt7530-fix-link-local-when-stp-discarding-v2-1-07b1150164ac@arinc9.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-04-09 15:01:14 +00:00
/* In Clause 5 of IEEE Std 802-2014, two sublayers of the data link layer (DLL)
* of the Open Systems Interconnection basic reference model (OSI/RM) are
* described; the medium access control (MAC) and logical link control (LLC)
* sublayers. The MAC sublayer is the one facing the physical layer.
net: dsa: mt7530: fix handling of all link-local frames [ Upstream commit 69ddba9d170bdaee1dc0eb4ced38d7e4bb7b92af ] Currently, the MT753X switches treat frames with :01-0D and :0F MAC DAs as regular multicast frames, therefore flooding them to user ports. On page 205, section "8.6.3 Frame filtering" of the active standard, IEEE Std 802.1Q™-2022, it is stated that frames with 01:80:C2:00:00:00-0F as MAC DA must only be propagated to C-VLAN and MAC Bridge components. That means VLAN-aware and VLAN-unaware bridges. On the switch designs with CPU ports, these frames are supposed to be processed by the CPU (software). So we make the switch only forward them to the CPU port. And if received from a CPU port, forward to a single port. The software is responsible of making the switch conform to the latter by setting a single port as destination port on the special tag. This switch intellectual property cannot conform to this part of the standard fully. Whilst the REV_UN frame tag covers the remaining :04-0D and :0F MAC DAs, it also includes :22-FF which the scope of propagation is not supposed to be restricted for these MAC DAs. Set frames with :01-03 MAC DAs to be trapped to the CPU port(s). Add a comment for the remaining MAC DAs. Note that the ingress port must have a PVID assigned to it for the switch to forward untagged frames. A PVID is set by default on VLAN-aware and VLAN-unaware ports. However, when the network interface that pertains to the ingress port is attached to a vlan_filtering enabled bridge, the user can remove the PVID assignment from it which would prevent the link-local frames from being trapped to the CPU port. I am yet to see a way to forward link-local frames while preventing other untagged frames from being forwarded too. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-03-14 09:33:42 +00:00
*
net: dsa: mt7530: trap link-local frames regardless of ST Port State [ Upstream commit 17c560113231ddc20088553c7b499b289b664311 ] In Clause 5 of IEEE Std 802-2014, two sublayers of the data link layer (DLL) of the Open Systems Interconnection basic reference model (OSI/RM) are described; the medium access control (MAC) and logical link control (LLC) sublayers. The MAC sublayer is the one facing the physical layer. In 8.2 of IEEE Std 802.1Q-2022, the Bridge architecture is described. A Bridge component comprises a MAC Relay Entity for interconnecting the Ports of the Bridge, at least two Ports, and higher layer entities with at least a Spanning Tree Protocol Entity included. Each Bridge Port also functions as an end station and shall provide the MAC Service to an LLC Entity. Each instance of the MAC Service is provided to a distinct LLC Entity that supports protocol identification, multiplexing, and demultiplexing, for protocol data unit (PDU) transmission and reception by one or more higher layer entities. It is described in 8.13.9 of IEEE Std 802.1Q-2022 that in a Bridge, the LLC Entity associated with each Bridge Port is modeled as being directly connected to the attached Local Area Network (LAN). On the switch with CPU port architecture, CPU port functions as Management Port, and the Management Port functionality is provided by software which functions as an end station. Software is connected to an IEEE 802 LAN that is wholly contained within the system that incorporates the Bridge. Software provides access to the LLC Entity associated with each Bridge Port by the value of the source port field on the special tag on the frame received by software. We call frames that carry control information to determine the active topology and current extent of each Virtual Local Area Network (VLAN), i.e., spanning tree or Shortest Path Bridging (SPB) and Multiple VLAN Registration Protocol Data Units (MVRPDUs), and frames from other link constrained protocols, such as Extensible Authentication Protocol over LAN (EAPOL) and Link Layer Discovery Protocol (LLDP), link-local frames. They are not forwarded by a Bridge. Permanently configured entries in the filtering database (FDB) ensure that such frames are discarded by the Forwarding Process. In 8.6.3 of IEEE Std 802.1Q-2022, this is described in detail: Each of the reserved MAC addresses specified in Table 8-1 (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]) shall be permanently configured in the FDB in C-VLAN components and ERs. Each of the reserved MAC addresses specified in Table 8-2 (01-80-C2-00-00-[01,02,03,04,05,06,07,08,09,0A,0E]) shall be permanently configured in the FDB in S-VLAN components. Each of the reserved MAC addresses specified in Table 8-3 (01-80-C2-00-00-[01,02,04,0E]) shall be permanently configured in the FDB in TPMR components. The FDB entries for reserved MAC addresses shall specify filtering for all Bridge Ports and all VIDs. Management shall not provide the capability to modify or remove entries for reserved MAC addresses. The addresses in Table 8-1, Table 8-2, and Table 8-3 determine the scope of propagation of PDUs within a Bridged Network, as follows: The Nearest Bridge group address (01-80-C2-00-00-0E) is an address that no conformant Two-Port MAC Relay (TPMR) component, Service VLAN (S-VLAN) component, Customer VLAN (C-VLAN) component, or MAC Bridge can forward. PDUs transmitted using this destination address, or any other addresses that appear in Table 8-1, Table 8-2, and Table 8-3 (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]), can therefore travel no further than those stations that can be reached via a single individual LAN from the originating station. The Nearest non-TPMR Bridge group address (01-80-C2-00-00-03), is an address that no conformant S-VLAN component, C-VLAN component, or MAC Bridge can forward; however, this address is relayed by a TPMR component. PDUs using this destination address, or any of the other addresses that appear in both Table 8-1 and Table 8-2 but not in Table 8-3 (01-80-C2-00-00-[00,03,05,06,07,08,09,0A,0B,0C,0D,0F]), will be relayed by any TPMRs but will propagate no further than the nearest S-VLAN component, C-VLAN component, or MAC Bridge. The Nearest Customer Bridge group address (01-80-C2-00-00-00) is an address that no conformant C-VLAN component, MAC Bridge can forward; however, it is relayed by TPMR components and S-VLAN components. PDUs using this destination address, or any of the other addresses that appear in Table 8-1 but not in either Table 8-2 or Table 8-3 (01-80-C2-00-00-[00,0B,0C,0D,0F]), will be relayed by TPMR components and S-VLAN components but will propagate no further than the nearest C-VLAN component or MAC Bridge. Because the LLC Entity associated with each Bridge Port is provided via CPU port, we must not filter these frames but forward them to CPU port. In a Bridge, the transmission Port is majorly decided by ingress and egress rules, FDB, and spanning tree Port State functions of the Forwarding Process. For link-local frames, only CPU port should be designated as destination port in the FDB, and the other functions of the Forwarding Process must not interfere with the decision of the transmission Port. We call this process trapping frames to CPU port. Therefore, on the switch with CPU port architecture, link-local frames must be trapped to CPU port, and certain link-local frames received by a Port of a Bridge comprising a TPMR component or an S-VLAN component must be excluded from it. A Bridge of the switch with CPU port architecture cannot comprise a Two-Port MAC Relay (TPMR) component as a TPMR component supports only a subset of the functionality of a MAC Bridge. A Bridge comprising two Ports (Management Port doesn't count) of this architecture will either function as a standard MAC Bridge or a standard VLAN Bridge. Therefore, a Bridge of this architecture can only comprise S-VLAN components, C-VLAN components, or MAC Bridge components. Since there's no TPMR component, we don't need to relay PDUs using the destination addresses specified on the Nearest non-TPMR section, and the proportion of the Nearest Customer Bridge section where they must be relayed by TPMR components. One option to trap link-local frames to CPU port is to add static FDB entries with CPU port designated as destination port. However, because that Independent VLAN Learning (IVL) is being used on every VID, each entry only applies to a single VLAN Identifier (VID). For a Bridge comprising a MAC Bridge component or a C-VLAN component, there would have to be 16 times 4096 entries. This switch intellectual property can only hold a maximum of 2048 entries. Using this option, there also isn't a mechanism to prevent link-local frames from being discarded when the spanning tree Port State of the reception Port is discarding. The remaining option is to utilise the BPC, RGAC1, RGAC2, RGAC3, and RGAC4 registers. Whilst this applies to every VID, it doesn't contain all of the reserved MAC addresses without affecting the remaining Standard Group MAC Addresses. The REV_UN frame tag utilised using the RGAC4 register covers the remaining 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] destination addresses. It also includes the 01-80-C2-00-00-22 to 01-80-C2-00-00-FF destination addresses which may be relayed by MAC Bridges or VLAN Bridges. The latter option provides better but not complete conformance. This switch intellectual property also does not provide a mechanism to trap link-local frames with specific destination addresses to CPU port by Bridge, to conform to the filtering rules for the distinct Bridge components. Therefore, regardless of the type of the Bridge component, link-local frames with these destination addresses will be trapped to CPU port: 01-80-C2-00-00-[00,01,02,03,0E] In a Bridge comprising a MAC Bridge component or a C-VLAN component: Link-local frames with these destination addresses won't be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] In a Bridge comprising an S-VLAN component: Link-local frames with these destination addresses will be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-00 Link-local frames with these destination addresses won't be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-[04,05,06,07,08,09,0A] Currently on this switch intellectual property, if the spanning tree Port State of the reception Port is discarding, link-local frames will be discarded. To trap link-local frames regardless of the spanning tree Port State, make the switch regard them as Bridge Protocol Data Units (BPDUs). This switch intellectual property only lets the frames regarded as BPDUs bypass the spanning tree Port State function of the Forwarding Process. With this change, the only remaining interference is the ingress rules. When the reception Port has no PVID assigned on software, VLAN-untagged frames won't be allowed in. There doesn't seem to be a mechanism on the switch intellectual property to have link-local frames bypass this function of the Forwarding Process. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Reviewed-by: Daniel Golle <daniel@makrotopia.org> Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Link: https://lore.kernel.org/r/20240409-b4-for-net-mt7530-fix-link-local-when-stp-discarding-v2-1-07b1150164ac@arinc9.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-04-09 15:01:14 +00:00
* In 8.2 of IEEE Std 802.1Q-2022, the Bridge architecture is described. A
* Bridge component comprises a MAC Relay Entity for interconnecting the Ports
* of the Bridge, at least two Ports, and higher layer entities with at least a
* Spanning Tree Protocol Entity included.
*
* Each Bridge Port also functions as an end station and shall provide the MAC
* Service to an LLC Entity. Each instance of the MAC Service is provided to a
* distinct LLC Entity that supports protocol identification, multiplexing, and
* demultiplexing, for protocol data unit (PDU) transmission and reception by
* one or more higher layer entities.
*
* It is described in 8.13.9 of IEEE Std 802.1Q-2022 that in a Bridge, the LLC
* Entity associated with each Bridge Port is modeled as being directly
* connected to the attached Local Area Network (LAN).
*
* On the switch with CPU port architecture, CPU port functions as Management
* Port, and the Management Port functionality is provided by software which
* functions as an end station. Software is connected to an IEEE 802 LAN that is
* wholly contained within the system that incorporates the Bridge. Software
* provides access to the LLC Entity associated with each Bridge Port by the
* value of the source port field on the special tag on the frame received by
* software.
*
* We call frames that carry control information to determine the active
* topology and current extent of each Virtual Local Area Network (VLAN), i.e.,
* spanning tree or Shortest Path Bridging (SPB) and Multiple VLAN Registration
* Protocol Data Units (MVRPDUs), and frames from other link constrained
* protocols, such as Extensible Authentication Protocol over LAN (EAPOL) and
* Link Layer Discovery Protocol (LLDP), link-local frames. They are not
* forwarded by a Bridge. Permanently configured entries in the filtering
* database (FDB) ensure that such frames are discarded by the Forwarding
* Process. In 8.6.3 of IEEE Std 802.1Q-2022, this is described in detail:
*
* Each of the reserved MAC addresses specified in Table 8-1
* (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]) shall be
* permanently configured in the FDB in C-VLAN components and ERs.
*
* Each of the reserved MAC addresses specified in Table 8-2
* (01-80-C2-00-00-[01,02,03,04,05,06,07,08,09,0A,0E]) shall be permanently
* configured in the FDB in S-VLAN components.
*
* Each of the reserved MAC addresses specified in Table 8-3
* (01-80-C2-00-00-[01,02,04,0E]) shall be permanently configured in the FDB in
* TPMR components.
*
* The FDB entries for reserved MAC addresses shall specify filtering for all
* Bridge Ports and all VIDs. Management shall not provide the capability to
* modify or remove entries for reserved MAC addresses.
*
* The addresses in Table 8-1, Table 8-2, and Table 8-3 determine the scope of
* propagation of PDUs within a Bridged Network, as follows:
*
* The Nearest Bridge group address (01-80-C2-00-00-0E) is an address that no
* conformant Two-Port MAC Relay (TPMR) component, Service VLAN (S-VLAN)
* component, Customer VLAN (C-VLAN) component, or MAC Bridge can forward.
* PDUs transmitted using this destination address, or any other addresses
* that appear in Table 8-1, Table 8-2, and Table 8-3
* (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]), can
* therefore travel no further than those stations that can be reached via a
* single individual LAN from the originating station.
*
* The Nearest non-TPMR Bridge group address (01-80-C2-00-00-03), is an
* address that no conformant S-VLAN component, C-VLAN component, or MAC
* Bridge can forward; however, this address is relayed by a TPMR component.
* PDUs using this destination address, or any of the other addresses that
* appear in both Table 8-1 and Table 8-2 but not in Table 8-3
* (01-80-C2-00-00-[00,03,05,06,07,08,09,0A,0B,0C,0D,0F]), will be relayed by
* any TPMRs but will propagate no further than the nearest S-VLAN component,
* C-VLAN component, or MAC Bridge.
*
* The Nearest Customer Bridge group address (01-80-C2-00-00-00) is an address
* that no conformant C-VLAN component, MAC Bridge can forward; however, it is
* relayed by TPMR components and S-VLAN components. PDUs using this
* destination address, or any of the other addresses that appear in Table 8-1
* but not in either Table 8-2 or Table 8-3 (01-80-C2-00-00-[00,0B,0C,0D,0F]),
* will be relayed by TPMR components and S-VLAN components but will propagate
* no further than the nearest C-VLAN component or MAC Bridge.
*
* Because the LLC Entity associated with each Bridge Port is provided via CPU
* port, we must not filter these frames but forward them to CPU port.
*
* In a Bridge, the transmission Port is majorly decided by ingress and egress
* rules, FDB, and spanning tree Port State functions of the Forwarding Process.
* For link-local frames, only CPU port should be designated as destination port
* in the FDB, and the other functions of the Forwarding Process must not
* interfere with the decision of the transmission Port. We call this process
* trapping frames to CPU port.
*
* Therefore, on the switch with CPU port architecture, link-local frames must
* be trapped to CPU port, and certain link-local frames received by a Port of a
* Bridge comprising a TPMR component or an S-VLAN component must be excluded
* from it.
*
* A Bridge of the switch with CPU port architecture cannot comprise a Two-Port
* MAC Relay (TPMR) component as a TPMR component supports only a subset of the
* functionality of a MAC Bridge. A Bridge comprising two Ports (Management Port
* doesn't count) of this architecture will either function as a standard MAC
* Bridge or a standard VLAN Bridge.
*
* Therefore, a Bridge of this architecture can only comprise S-VLAN components,
* C-VLAN components, or MAC Bridge components. Since there's no TPMR component,
* we don't need to relay PDUs using the destination addresses specified on the
* Nearest non-TPMR section, and the proportion of the Nearest Customer Bridge
* section where they must be relayed by TPMR components.
*
* One option to trap link-local frames to CPU port is to add static FDB entries
* with CPU port designated as destination port. However, because that
* Independent VLAN Learning (IVL) is being used on every VID, each entry only
* applies to a single VLAN Identifier (VID). For a Bridge comprising a MAC
* Bridge component or a C-VLAN component, there would have to be 16 times 4096
* entries. This switch intellectual property can only hold a maximum of 2048
* entries. Using this option, there also isn't a mechanism to prevent
* link-local frames from being discarded when the spanning tree Port State of
* the reception Port is discarding.
*
* The remaining option is to utilise the BPC, RGAC1, RGAC2, RGAC3, and RGAC4
* registers. Whilst this applies to every VID, it doesn't contain all of the
* reserved MAC addresses without affecting the remaining Standard Group MAC
* Addresses. The REV_UN frame tag utilised using the RGAC4 register covers the
* remaining 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] destination
* addresses. It also includes the 01-80-C2-00-00-22 to 01-80-C2-00-00-FF
* destination addresses which may be relayed by MAC Bridges or VLAN Bridges.
* The latter option provides better but not complete conformance.
*
* This switch intellectual property also does not provide a mechanism to trap
* link-local frames with specific destination addresses to CPU port by Bridge,
* to conform to the filtering rules for the distinct Bridge components.
*
* Therefore, regardless of the type of the Bridge component, link-local frames
* with these destination addresses will be trapped to CPU port:
*
* 01-80-C2-00-00-[00,01,02,03,0E]
*
* In a Bridge comprising a MAC Bridge component or a C-VLAN component:
*
* Link-local frames with these destination addresses won't be trapped to CPU
* port which won't conform to IEEE Std 802.1Q-2022:
*
* 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F]
*
* In a Bridge comprising an S-VLAN component:
*
* Link-local frames with these destination addresses will be trapped to CPU
* port which won't conform to IEEE Std 802.1Q-2022:
*
* 01-80-C2-00-00-00
*
* Link-local frames with these destination addresses won't be trapped to CPU
* port which won't conform to IEEE Std 802.1Q-2022:
*
* 01-80-C2-00-00-[04,05,06,07,08,09,0A]
*
* To trap link-local frames to CPU port as conformant as this switch
* intellectual property can allow, link-local frames are made to be regarded as
* Bridge Protocol Data Units (BPDUs). This is because this switch intellectual
* property only lets the frames regarded as BPDUs bypass the spanning tree Port
* State function of the Forwarding Process.
*
* The only remaining interference is the ingress rules. When the reception Port
* has no PVID assigned on software, VLAN-untagged frames won't be allowed in.
* There doesn't seem to be a mechanism on the switch intellectual property to
* have link-local frames bypass this function of the Forwarding Process.
net: dsa: mt7530: fix handling of all link-local frames [ Upstream commit 69ddba9d170bdaee1dc0eb4ced38d7e4bb7b92af ] Currently, the MT753X switches treat frames with :01-0D and :0F MAC DAs as regular multicast frames, therefore flooding them to user ports. On page 205, section "8.6.3 Frame filtering" of the active standard, IEEE Std 802.1Q™-2022, it is stated that frames with 01:80:C2:00:00:00-0F as MAC DA must only be propagated to C-VLAN and MAC Bridge components. That means VLAN-aware and VLAN-unaware bridges. On the switch designs with CPU ports, these frames are supposed to be processed by the CPU (software). So we make the switch only forward them to the CPU port. And if received from a CPU port, forward to a single port. The software is responsible of making the switch conform to the latter by setting a single port as destination port on the special tag. This switch intellectual property cannot conform to this part of the standard fully. Whilst the REV_UN frame tag covers the remaining :04-0D and :0F MAC DAs, it also includes :22-FF which the scope of propagation is not supposed to be restricted for these MAC DAs. Set frames with :01-03 MAC DAs to be trapped to the CPU port(s). Add a comment for the remaining MAC DAs. Note that the ingress port must have a PVID assigned to it for the switch to forward untagged frames. A PVID is set by default on VLAN-aware and VLAN-unaware ports. However, when the network interface that pertains to the ingress port is attached to a vlan_filtering enabled bridge, the user can remove the PVID assignment from it which would prevent the link-local frames from being trapped to the CPU port. I am yet to see a way to forward link-local frames while preventing other untagged frames from being forwarded too. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-03-14 09:33:42 +00:00
*/
static void
mt753x_trap_frames(struct mt7530_priv *priv)
{
net: dsa: mt7530: fix link-local frames that ingress vlan filtering ports [ Upstream commit e8bf353577f382c7066c661fed41b2adc0fc7c40 ] Whether VLAN-aware or not, on every VID VLAN table entry that has the CPU port as a member of it, frames are set to egress the CPU port with the VLAN tag stacked. This is so that VLAN tags can be appended after hardware special tag (called DSA tag in the context of Linux drivers). For user ports on a VLAN-unaware bridge, frame ingressing the user port egresses CPU port with only the special tag. For user ports on a VLAN-aware bridge, frame ingressing the user port egresses CPU port with the special tag and the VLAN tag. This causes issues with link-local frames, specifically BPDUs, because the software expects to receive them VLAN-untagged. There are two options to make link-local frames egress untagged. Setting CONSISTENT or UNTAGGED on the EG_TAG bits on the relevant register. CONSISTENT means frames egress exactly as they ingress. That means egressing with the VLAN tag they had at ingress or egressing untagged if they ingressed untagged. Although link-local frames are not supposed to be transmitted VLAN-tagged, if they are done so, when egressing through a CPU port, the special tag field will be broken. BPDU egresses CPU port with VLAN tag egressing stacked, received on software: 00:01:25.104821 AF Unknown (382365846), length 106: | STAG | | VLAN | 0x0000: 0000 6c27 614d 4143 0001 0000 8100 0001 ..l'aMAC........ 0x0010: 0026 4242 0300 0000 0000 0000 6c27 614d .&BB........l'aM 0x0020: 4143 0000 0000 0000 6c27 614d 4143 0000 AC......l'aMAC.. 0x0030: 0000 1400 0200 0f00 0000 0000 0000 0000 ................ BPDU egresses CPU port with VLAN tag egressing untagged, received on software: 00:23:56.628708 AF Unknown (25215488), length 64: | STAG | 0x0000: 0000 6c27 614d 4143 0001 0000 0026 4242 ..l'aMAC.....&BB 0x0010: 0300 0000 0000 0000 6c27 614d 4143 0000 ........l'aMAC.. 0x0020: 0000 0000 6c27 614d 4143 0000 0000 1400 ....l'aMAC...... 0x0030: 0200 0f00 0000 0000 0000 0000 ............ BPDU egresses CPU port with VLAN tag egressing tagged, received on software: 00:01:34.311963 AF Unknown (25215488), length 64: | Mess | 0x0000: 0000 6c27 614d 4143 0001 0001 0026 4242 ..l'aMAC.....&BB 0x0010: 0300 0000 0000 0000 6c27 614d 4143 0000 ........l'aMAC.. 0x0020: 0000 0000 6c27 614d 4143 0000 0000 1400 ....l'aMAC...... 0x0030: 0200 0f00 0000 0000 0000 0000 ............ To prevent confusing the software, force the frame to egress UNTAGGED instead of CONSISTENT. This way, frames can't possibly be received TAGGED by software which would have the special tag field broken. VLAN Tag Egress Procedure For all frames, one of these options set the earliest in this order will apply to the frame: - EG_TAG in certain registers for certain frames. This will apply to frame with matching MAC DA or EtherType. - EG_TAG in the address table. This will apply to frame at its incoming port. - EG_TAG in the PVC register. This will apply to frame at its incoming port. - EG_CON and [EG_TAG per port] in the VLAN table. This will apply to frame at its outgoing port. - EG_TAG in the PCR register. This will apply to frame at its outgoing port. EG_TAG in certain registers for certain frames: PPPoE Discovery_ARP/RARP: PPP_EG_TAG and ARP_EG_TAG in the APC register. IGMP_MLD: IGMP_EG_TAG and MLD_EG_TAG in the IMC register. BPDU and PAE: BPDU_EG_TAG and PAE_EG_TAG in the BPC register. REV_01 and REV_02: R01_EG_TAG and R02_EG_TAG in the RGAC1 register. REV_03 and REV_0E: R03_EG_TAG and R0E_EG_TAG in the RGAC2 register. REV_10 and REV_20: R10_EG_TAG and R20_EG_TAG in the RGAC3 register. REV_21 and REV_UN: R21_EG_TAG and RUN_EG_TAG in the RGAC4 register. With this change, it can be observed that a bridge interface with stp_state and vlan_filtering enabled will properly block ports now. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-03-14 09:33:41 +00:00
/* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress them
* VLAN-untagged.
*/
net: dsa: mt7530: trap link-local frames regardless of ST Port State [ Upstream commit 17c560113231ddc20088553c7b499b289b664311 ] In Clause 5 of IEEE Std 802-2014, two sublayers of the data link layer (DLL) of the Open Systems Interconnection basic reference model (OSI/RM) are described; the medium access control (MAC) and logical link control (LLC) sublayers. The MAC sublayer is the one facing the physical layer. In 8.2 of IEEE Std 802.1Q-2022, the Bridge architecture is described. A Bridge component comprises a MAC Relay Entity for interconnecting the Ports of the Bridge, at least two Ports, and higher layer entities with at least a Spanning Tree Protocol Entity included. Each Bridge Port also functions as an end station and shall provide the MAC Service to an LLC Entity. Each instance of the MAC Service is provided to a distinct LLC Entity that supports protocol identification, multiplexing, and demultiplexing, for protocol data unit (PDU) transmission and reception by one or more higher layer entities. It is described in 8.13.9 of IEEE Std 802.1Q-2022 that in a Bridge, the LLC Entity associated with each Bridge Port is modeled as being directly connected to the attached Local Area Network (LAN). On the switch with CPU port architecture, CPU port functions as Management Port, and the Management Port functionality is provided by software which functions as an end station. Software is connected to an IEEE 802 LAN that is wholly contained within the system that incorporates the Bridge. Software provides access to the LLC Entity associated with each Bridge Port by the value of the source port field on the special tag on the frame received by software. We call frames that carry control information to determine the active topology and current extent of each Virtual Local Area Network (VLAN), i.e., spanning tree or Shortest Path Bridging (SPB) and Multiple VLAN Registration Protocol Data Units (MVRPDUs), and frames from other link constrained protocols, such as Extensible Authentication Protocol over LAN (EAPOL) and Link Layer Discovery Protocol (LLDP), link-local frames. They are not forwarded by a Bridge. Permanently configured entries in the filtering database (FDB) ensure that such frames are discarded by the Forwarding Process. In 8.6.3 of IEEE Std 802.1Q-2022, this is described in detail: Each of the reserved MAC addresses specified in Table 8-1 (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]) shall be permanently configured in the FDB in C-VLAN components and ERs. Each of the reserved MAC addresses specified in Table 8-2 (01-80-C2-00-00-[01,02,03,04,05,06,07,08,09,0A,0E]) shall be permanently configured in the FDB in S-VLAN components. Each of the reserved MAC addresses specified in Table 8-3 (01-80-C2-00-00-[01,02,04,0E]) shall be permanently configured in the FDB in TPMR components. The FDB entries for reserved MAC addresses shall specify filtering for all Bridge Ports and all VIDs. Management shall not provide the capability to modify or remove entries for reserved MAC addresses. The addresses in Table 8-1, Table 8-2, and Table 8-3 determine the scope of propagation of PDUs within a Bridged Network, as follows: The Nearest Bridge group address (01-80-C2-00-00-0E) is an address that no conformant Two-Port MAC Relay (TPMR) component, Service VLAN (S-VLAN) component, Customer VLAN (C-VLAN) component, or MAC Bridge can forward. PDUs transmitted using this destination address, or any other addresses that appear in Table 8-1, Table 8-2, and Table 8-3 (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]), can therefore travel no further than those stations that can be reached via a single individual LAN from the originating station. The Nearest non-TPMR Bridge group address (01-80-C2-00-00-03), is an address that no conformant S-VLAN component, C-VLAN component, or MAC Bridge can forward; however, this address is relayed by a TPMR component. PDUs using this destination address, or any of the other addresses that appear in both Table 8-1 and Table 8-2 but not in Table 8-3 (01-80-C2-00-00-[00,03,05,06,07,08,09,0A,0B,0C,0D,0F]), will be relayed by any TPMRs but will propagate no further than the nearest S-VLAN component, C-VLAN component, or MAC Bridge. The Nearest Customer Bridge group address (01-80-C2-00-00-00) is an address that no conformant C-VLAN component, MAC Bridge can forward; however, it is relayed by TPMR components and S-VLAN components. PDUs using this destination address, or any of the other addresses that appear in Table 8-1 but not in either Table 8-2 or Table 8-3 (01-80-C2-00-00-[00,0B,0C,0D,0F]), will be relayed by TPMR components and S-VLAN components but will propagate no further than the nearest C-VLAN component or MAC Bridge. Because the LLC Entity associated with each Bridge Port is provided via CPU port, we must not filter these frames but forward them to CPU port. In a Bridge, the transmission Port is majorly decided by ingress and egress rules, FDB, and spanning tree Port State functions of the Forwarding Process. For link-local frames, only CPU port should be designated as destination port in the FDB, and the other functions of the Forwarding Process must not interfere with the decision of the transmission Port. We call this process trapping frames to CPU port. Therefore, on the switch with CPU port architecture, link-local frames must be trapped to CPU port, and certain link-local frames received by a Port of a Bridge comprising a TPMR component or an S-VLAN component must be excluded from it. A Bridge of the switch with CPU port architecture cannot comprise a Two-Port MAC Relay (TPMR) component as a TPMR component supports only a subset of the functionality of a MAC Bridge. A Bridge comprising two Ports (Management Port doesn't count) of this architecture will either function as a standard MAC Bridge or a standard VLAN Bridge. Therefore, a Bridge of this architecture can only comprise S-VLAN components, C-VLAN components, or MAC Bridge components. Since there's no TPMR component, we don't need to relay PDUs using the destination addresses specified on the Nearest non-TPMR section, and the proportion of the Nearest Customer Bridge section where they must be relayed by TPMR components. One option to trap link-local frames to CPU port is to add static FDB entries with CPU port designated as destination port. However, because that Independent VLAN Learning (IVL) is being used on every VID, each entry only applies to a single VLAN Identifier (VID). For a Bridge comprising a MAC Bridge component or a C-VLAN component, there would have to be 16 times 4096 entries. This switch intellectual property can only hold a maximum of 2048 entries. Using this option, there also isn't a mechanism to prevent link-local frames from being discarded when the spanning tree Port State of the reception Port is discarding. The remaining option is to utilise the BPC, RGAC1, RGAC2, RGAC3, and RGAC4 registers. Whilst this applies to every VID, it doesn't contain all of the reserved MAC addresses without affecting the remaining Standard Group MAC Addresses. The REV_UN frame tag utilised using the RGAC4 register covers the remaining 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] destination addresses. It also includes the 01-80-C2-00-00-22 to 01-80-C2-00-00-FF destination addresses which may be relayed by MAC Bridges or VLAN Bridges. The latter option provides better but not complete conformance. This switch intellectual property also does not provide a mechanism to trap link-local frames with specific destination addresses to CPU port by Bridge, to conform to the filtering rules for the distinct Bridge components. Therefore, regardless of the type of the Bridge component, link-local frames with these destination addresses will be trapped to CPU port: 01-80-C2-00-00-[00,01,02,03,0E] In a Bridge comprising a MAC Bridge component or a C-VLAN component: Link-local frames with these destination addresses won't be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] In a Bridge comprising an S-VLAN component: Link-local frames with these destination addresses will be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-00 Link-local frames with these destination addresses won't be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-[04,05,06,07,08,09,0A] Currently on this switch intellectual property, if the spanning tree Port State of the reception Port is discarding, link-local frames will be discarded. To trap link-local frames regardless of the spanning tree Port State, make the switch regard them as Bridge Protocol Data Units (BPDUs). This switch intellectual property only lets the frames regarded as BPDUs bypass the spanning tree Port State function of the Forwarding Process. With this change, the only remaining interference is the ingress rules. When the reception Port has no PVID assigned on software, VLAN-untagged frames won't be allowed in. There doesn't seem to be a mechanism on the switch intellectual property to have link-local frames bypass this function of the Forwarding Process. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Reviewed-by: Daniel Golle <daniel@makrotopia.org> Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Link: https://lore.kernel.org/r/20240409-b4-for-net-mt7530-fix-link-local-when-stp-discarding-v2-1-07b1150164ac@arinc9.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-04-09 15:01:14 +00:00
mt7530_rmw(priv, MT753X_BPC,
MT753X_PAE_BPDU_FR | MT753X_PAE_EG_TAG_MASK |
MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK |
MT753X_BPDU_PORT_FW_MASK,
MT753X_PAE_BPDU_FR |
MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) |
MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
MT753X_BPDU_CPU_ONLY);
net: dsa: mt7530: fix handling of all link-local frames [ Upstream commit 69ddba9d170bdaee1dc0eb4ced38d7e4bb7b92af ] Currently, the MT753X switches treat frames with :01-0D and :0F MAC DAs as regular multicast frames, therefore flooding them to user ports. On page 205, section "8.6.3 Frame filtering" of the active standard, IEEE Std 802.1Q™-2022, it is stated that frames with 01:80:C2:00:00:00-0F as MAC DA must only be propagated to C-VLAN and MAC Bridge components. That means VLAN-aware and VLAN-unaware bridges. On the switch designs with CPU ports, these frames are supposed to be processed by the CPU (software). So we make the switch only forward them to the CPU port. And if received from a CPU port, forward to a single port. The software is responsible of making the switch conform to the latter by setting a single port as destination port on the special tag. This switch intellectual property cannot conform to this part of the standard fully. Whilst the REV_UN frame tag covers the remaining :04-0D and :0F MAC DAs, it also includes :22-FF which the scope of propagation is not supposed to be restricted for these MAC DAs. Set frames with :01-03 MAC DAs to be trapped to the CPU port(s). Add a comment for the remaining MAC DAs. Note that the ingress port must have a PVID assigned to it for the switch to forward untagged frames. A PVID is set by default on VLAN-aware and VLAN-unaware ports. However, when the network interface that pertains to the ingress port is attached to a vlan_filtering enabled bridge, the user can remove the PVID assignment from it which would prevent the link-local frames from being trapped to the CPU port. I am yet to see a way to forward link-local frames while preventing other untagged frames from being forwarded too. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-03-14 09:33:42 +00:00
/* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and egress
* them VLAN-untagged.
*/
net: dsa: mt7530: trap link-local frames regardless of ST Port State [ Upstream commit 17c560113231ddc20088553c7b499b289b664311 ] In Clause 5 of IEEE Std 802-2014, two sublayers of the data link layer (DLL) of the Open Systems Interconnection basic reference model (OSI/RM) are described; the medium access control (MAC) and logical link control (LLC) sublayers. The MAC sublayer is the one facing the physical layer. In 8.2 of IEEE Std 802.1Q-2022, the Bridge architecture is described. A Bridge component comprises a MAC Relay Entity for interconnecting the Ports of the Bridge, at least two Ports, and higher layer entities with at least a Spanning Tree Protocol Entity included. Each Bridge Port also functions as an end station and shall provide the MAC Service to an LLC Entity. Each instance of the MAC Service is provided to a distinct LLC Entity that supports protocol identification, multiplexing, and demultiplexing, for protocol data unit (PDU) transmission and reception by one or more higher layer entities. It is described in 8.13.9 of IEEE Std 802.1Q-2022 that in a Bridge, the LLC Entity associated with each Bridge Port is modeled as being directly connected to the attached Local Area Network (LAN). On the switch with CPU port architecture, CPU port functions as Management Port, and the Management Port functionality is provided by software which functions as an end station. Software is connected to an IEEE 802 LAN that is wholly contained within the system that incorporates the Bridge. Software provides access to the LLC Entity associated with each Bridge Port by the value of the source port field on the special tag on the frame received by software. We call frames that carry control information to determine the active topology and current extent of each Virtual Local Area Network (VLAN), i.e., spanning tree or Shortest Path Bridging (SPB) and Multiple VLAN Registration Protocol Data Units (MVRPDUs), and frames from other link constrained protocols, such as Extensible Authentication Protocol over LAN (EAPOL) and Link Layer Discovery Protocol (LLDP), link-local frames. They are not forwarded by a Bridge. Permanently configured entries in the filtering database (FDB) ensure that such frames are discarded by the Forwarding Process. In 8.6.3 of IEEE Std 802.1Q-2022, this is described in detail: Each of the reserved MAC addresses specified in Table 8-1 (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]) shall be permanently configured in the FDB in C-VLAN components and ERs. Each of the reserved MAC addresses specified in Table 8-2 (01-80-C2-00-00-[01,02,03,04,05,06,07,08,09,0A,0E]) shall be permanently configured in the FDB in S-VLAN components. Each of the reserved MAC addresses specified in Table 8-3 (01-80-C2-00-00-[01,02,04,0E]) shall be permanently configured in the FDB in TPMR components. The FDB entries for reserved MAC addresses shall specify filtering for all Bridge Ports and all VIDs. Management shall not provide the capability to modify or remove entries for reserved MAC addresses. The addresses in Table 8-1, Table 8-2, and Table 8-3 determine the scope of propagation of PDUs within a Bridged Network, as follows: The Nearest Bridge group address (01-80-C2-00-00-0E) is an address that no conformant Two-Port MAC Relay (TPMR) component, Service VLAN (S-VLAN) component, Customer VLAN (C-VLAN) component, or MAC Bridge can forward. PDUs transmitted using this destination address, or any other addresses that appear in Table 8-1, Table 8-2, and Table 8-3 (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]), can therefore travel no further than those stations that can be reached via a single individual LAN from the originating station. The Nearest non-TPMR Bridge group address (01-80-C2-00-00-03), is an address that no conformant S-VLAN component, C-VLAN component, or MAC Bridge can forward; however, this address is relayed by a TPMR component. PDUs using this destination address, or any of the other addresses that appear in both Table 8-1 and Table 8-2 but not in Table 8-3 (01-80-C2-00-00-[00,03,05,06,07,08,09,0A,0B,0C,0D,0F]), will be relayed by any TPMRs but will propagate no further than the nearest S-VLAN component, C-VLAN component, or MAC Bridge. The Nearest Customer Bridge group address (01-80-C2-00-00-00) is an address that no conformant C-VLAN component, MAC Bridge can forward; however, it is relayed by TPMR components and S-VLAN components. PDUs using this destination address, or any of the other addresses that appear in Table 8-1 but not in either Table 8-2 or Table 8-3 (01-80-C2-00-00-[00,0B,0C,0D,0F]), will be relayed by TPMR components and S-VLAN components but will propagate no further than the nearest C-VLAN component or MAC Bridge. Because the LLC Entity associated with each Bridge Port is provided via CPU port, we must not filter these frames but forward them to CPU port. In a Bridge, the transmission Port is majorly decided by ingress and egress rules, FDB, and spanning tree Port State functions of the Forwarding Process. For link-local frames, only CPU port should be designated as destination port in the FDB, and the other functions of the Forwarding Process must not interfere with the decision of the transmission Port. We call this process trapping frames to CPU port. Therefore, on the switch with CPU port architecture, link-local frames must be trapped to CPU port, and certain link-local frames received by a Port of a Bridge comprising a TPMR component or an S-VLAN component must be excluded from it. A Bridge of the switch with CPU port architecture cannot comprise a Two-Port MAC Relay (TPMR) component as a TPMR component supports only a subset of the functionality of a MAC Bridge. A Bridge comprising two Ports (Management Port doesn't count) of this architecture will either function as a standard MAC Bridge or a standard VLAN Bridge. Therefore, a Bridge of this architecture can only comprise S-VLAN components, C-VLAN components, or MAC Bridge components. Since there's no TPMR component, we don't need to relay PDUs using the destination addresses specified on the Nearest non-TPMR section, and the proportion of the Nearest Customer Bridge section where they must be relayed by TPMR components. One option to trap link-local frames to CPU port is to add static FDB entries with CPU port designated as destination port. However, because that Independent VLAN Learning (IVL) is being used on every VID, each entry only applies to a single VLAN Identifier (VID). For a Bridge comprising a MAC Bridge component or a C-VLAN component, there would have to be 16 times 4096 entries. This switch intellectual property can only hold a maximum of 2048 entries. Using this option, there also isn't a mechanism to prevent link-local frames from being discarded when the spanning tree Port State of the reception Port is discarding. The remaining option is to utilise the BPC, RGAC1, RGAC2, RGAC3, and RGAC4 registers. Whilst this applies to every VID, it doesn't contain all of the reserved MAC addresses without affecting the remaining Standard Group MAC Addresses. The REV_UN frame tag utilised using the RGAC4 register covers the remaining 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] destination addresses. It also includes the 01-80-C2-00-00-22 to 01-80-C2-00-00-FF destination addresses which may be relayed by MAC Bridges or VLAN Bridges. The latter option provides better but not complete conformance. This switch intellectual property also does not provide a mechanism to trap link-local frames with specific destination addresses to CPU port by Bridge, to conform to the filtering rules for the distinct Bridge components. Therefore, regardless of the type of the Bridge component, link-local frames with these destination addresses will be trapped to CPU port: 01-80-C2-00-00-[00,01,02,03,0E] In a Bridge comprising a MAC Bridge component or a C-VLAN component: Link-local frames with these destination addresses won't be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] In a Bridge comprising an S-VLAN component: Link-local frames with these destination addresses will be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-00 Link-local frames with these destination addresses won't be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-[04,05,06,07,08,09,0A] Currently on this switch intellectual property, if the spanning tree Port State of the reception Port is discarding, link-local frames will be discarded. To trap link-local frames regardless of the spanning tree Port State, make the switch regard them as Bridge Protocol Data Units (BPDUs). This switch intellectual property only lets the frames regarded as BPDUs bypass the spanning tree Port State function of the Forwarding Process. With this change, the only remaining interference is the ingress rules. When the reception Port has no PVID assigned on software, VLAN-untagged frames won't be allowed in. There doesn't seem to be a mechanism on the switch intellectual property to have link-local frames bypass this function of the Forwarding Process. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Reviewed-by: Daniel Golle <daniel@makrotopia.org> Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Link: https://lore.kernel.org/r/20240409-b4-for-net-mt7530-fix-link-local-when-stp-discarding-v2-1-07b1150164ac@arinc9.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-04-09 15:01:14 +00:00
mt7530_rmw(priv, MT753X_RGAC1,
MT753X_R02_BPDU_FR | MT753X_R02_EG_TAG_MASK |
MT753X_R02_PORT_FW_MASK | MT753X_R01_BPDU_FR |
MT753X_R01_EG_TAG_MASK | MT753X_R01_PORT_FW_MASK,
MT753X_R02_BPDU_FR |
MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) |
MT753X_R01_BPDU_FR |
MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
MT753X_BPDU_CPU_ONLY);
net: dsa: mt7530: fix handling of all link-local frames [ Upstream commit 69ddba9d170bdaee1dc0eb4ced38d7e4bb7b92af ] Currently, the MT753X switches treat frames with :01-0D and :0F MAC DAs as regular multicast frames, therefore flooding them to user ports. On page 205, section "8.6.3 Frame filtering" of the active standard, IEEE Std 802.1Q™-2022, it is stated that frames with 01:80:C2:00:00:00-0F as MAC DA must only be propagated to C-VLAN and MAC Bridge components. That means VLAN-aware and VLAN-unaware bridges. On the switch designs with CPU ports, these frames are supposed to be processed by the CPU (software). So we make the switch only forward them to the CPU port. And if received from a CPU port, forward to a single port. The software is responsible of making the switch conform to the latter by setting a single port as destination port on the special tag. This switch intellectual property cannot conform to this part of the standard fully. Whilst the REV_UN frame tag covers the remaining :04-0D and :0F MAC DAs, it also includes :22-FF which the scope of propagation is not supposed to be restricted for these MAC DAs. Set frames with :01-03 MAC DAs to be trapped to the CPU port(s). Add a comment for the remaining MAC DAs. Note that the ingress port must have a PVID assigned to it for the switch to forward untagged frames. A PVID is set by default on VLAN-aware and VLAN-unaware ports. However, when the network interface that pertains to the ingress port is attached to a vlan_filtering enabled bridge, the user can remove the PVID assignment from it which would prevent the link-local frames from being trapped to the CPU port. I am yet to see a way to forward link-local frames while preventing other untagged frames from being forwarded too. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-03-14 09:33:42 +00:00
/* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and egress
* them VLAN-untagged.
net: dsa: mt7530: fix link-local frames that ingress vlan filtering ports [ Upstream commit e8bf353577f382c7066c661fed41b2adc0fc7c40 ] Whether VLAN-aware or not, on every VID VLAN table entry that has the CPU port as a member of it, frames are set to egress the CPU port with the VLAN tag stacked. This is so that VLAN tags can be appended after hardware special tag (called DSA tag in the context of Linux drivers). For user ports on a VLAN-unaware bridge, frame ingressing the user port egresses CPU port with only the special tag. For user ports on a VLAN-aware bridge, frame ingressing the user port egresses CPU port with the special tag and the VLAN tag. This causes issues with link-local frames, specifically BPDUs, because the software expects to receive them VLAN-untagged. There are two options to make link-local frames egress untagged. Setting CONSISTENT or UNTAGGED on the EG_TAG bits on the relevant register. CONSISTENT means frames egress exactly as they ingress. That means egressing with the VLAN tag they had at ingress or egressing untagged if they ingressed untagged. Although link-local frames are not supposed to be transmitted VLAN-tagged, if they are done so, when egressing through a CPU port, the special tag field will be broken. BPDU egresses CPU port with VLAN tag egressing stacked, received on software: 00:01:25.104821 AF Unknown (382365846), length 106: | STAG | | VLAN | 0x0000: 0000 6c27 614d 4143 0001 0000 8100 0001 ..l'aMAC........ 0x0010: 0026 4242 0300 0000 0000 0000 6c27 614d .&BB........l'aM 0x0020: 4143 0000 0000 0000 6c27 614d 4143 0000 AC......l'aMAC.. 0x0030: 0000 1400 0200 0f00 0000 0000 0000 0000 ................ BPDU egresses CPU port with VLAN tag egressing untagged, received on software: 00:23:56.628708 AF Unknown (25215488), length 64: | STAG | 0x0000: 0000 6c27 614d 4143 0001 0000 0026 4242 ..l'aMAC.....&BB 0x0010: 0300 0000 0000 0000 6c27 614d 4143 0000 ........l'aMAC.. 0x0020: 0000 0000 6c27 614d 4143 0000 0000 1400 ....l'aMAC...... 0x0030: 0200 0f00 0000 0000 0000 0000 ............ BPDU egresses CPU port with VLAN tag egressing tagged, received on software: 00:01:34.311963 AF Unknown (25215488), length 64: | Mess | 0x0000: 0000 6c27 614d 4143 0001 0001 0026 4242 ..l'aMAC.....&BB 0x0010: 0300 0000 0000 0000 6c27 614d 4143 0000 ........l'aMAC.. 0x0020: 0000 0000 6c27 614d 4143 0000 0000 1400 ....l'aMAC...... 0x0030: 0200 0f00 0000 0000 0000 0000 ............ To prevent confusing the software, force the frame to egress UNTAGGED instead of CONSISTENT. This way, frames can't possibly be received TAGGED by software which would have the special tag field broken. VLAN Tag Egress Procedure For all frames, one of these options set the earliest in this order will apply to the frame: - EG_TAG in certain registers for certain frames. This will apply to frame with matching MAC DA or EtherType. - EG_TAG in the address table. This will apply to frame at its incoming port. - EG_TAG in the PVC register. This will apply to frame at its incoming port. - EG_CON and [EG_TAG per port] in the VLAN table. This will apply to frame at its outgoing port. - EG_TAG in the PCR register. This will apply to frame at its outgoing port. EG_TAG in certain registers for certain frames: PPPoE Discovery_ARP/RARP: PPP_EG_TAG and ARP_EG_TAG in the APC register. IGMP_MLD: IGMP_EG_TAG and MLD_EG_TAG in the IMC register. BPDU and PAE: BPDU_EG_TAG and PAE_EG_TAG in the BPC register. REV_01 and REV_02: R01_EG_TAG and R02_EG_TAG in the RGAC1 register. REV_03 and REV_0E: R03_EG_TAG and R0E_EG_TAG in the RGAC2 register. REV_10 and REV_20: R10_EG_TAG and R20_EG_TAG in the RGAC3 register. REV_21 and REV_UN: R21_EG_TAG and RUN_EG_TAG in the RGAC4 register. With this change, it can be observed that a bridge interface with stp_state and vlan_filtering enabled will properly block ports now. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-03-14 09:33:41 +00:00
*/
net: dsa: mt7530: trap link-local frames regardless of ST Port State [ Upstream commit 17c560113231ddc20088553c7b499b289b664311 ] In Clause 5 of IEEE Std 802-2014, two sublayers of the data link layer (DLL) of the Open Systems Interconnection basic reference model (OSI/RM) are described; the medium access control (MAC) and logical link control (LLC) sublayers. The MAC sublayer is the one facing the physical layer. In 8.2 of IEEE Std 802.1Q-2022, the Bridge architecture is described. A Bridge component comprises a MAC Relay Entity for interconnecting the Ports of the Bridge, at least two Ports, and higher layer entities with at least a Spanning Tree Protocol Entity included. Each Bridge Port also functions as an end station and shall provide the MAC Service to an LLC Entity. Each instance of the MAC Service is provided to a distinct LLC Entity that supports protocol identification, multiplexing, and demultiplexing, for protocol data unit (PDU) transmission and reception by one or more higher layer entities. It is described in 8.13.9 of IEEE Std 802.1Q-2022 that in a Bridge, the LLC Entity associated with each Bridge Port is modeled as being directly connected to the attached Local Area Network (LAN). On the switch with CPU port architecture, CPU port functions as Management Port, and the Management Port functionality is provided by software which functions as an end station. Software is connected to an IEEE 802 LAN that is wholly contained within the system that incorporates the Bridge. Software provides access to the LLC Entity associated with each Bridge Port by the value of the source port field on the special tag on the frame received by software. We call frames that carry control information to determine the active topology and current extent of each Virtual Local Area Network (VLAN), i.e., spanning tree or Shortest Path Bridging (SPB) and Multiple VLAN Registration Protocol Data Units (MVRPDUs), and frames from other link constrained protocols, such as Extensible Authentication Protocol over LAN (EAPOL) and Link Layer Discovery Protocol (LLDP), link-local frames. They are not forwarded by a Bridge. Permanently configured entries in the filtering database (FDB) ensure that such frames are discarded by the Forwarding Process. In 8.6.3 of IEEE Std 802.1Q-2022, this is described in detail: Each of the reserved MAC addresses specified in Table 8-1 (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]) shall be permanently configured in the FDB in C-VLAN components and ERs. Each of the reserved MAC addresses specified in Table 8-2 (01-80-C2-00-00-[01,02,03,04,05,06,07,08,09,0A,0E]) shall be permanently configured in the FDB in S-VLAN components. Each of the reserved MAC addresses specified in Table 8-3 (01-80-C2-00-00-[01,02,04,0E]) shall be permanently configured in the FDB in TPMR components. The FDB entries for reserved MAC addresses shall specify filtering for all Bridge Ports and all VIDs. Management shall not provide the capability to modify or remove entries for reserved MAC addresses. The addresses in Table 8-1, Table 8-2, and Table 8-3 determine the scope of propagation of PDUs within a Bridged Network, as follows: The Nearest Bridge group address (01-80-C2-00-00-0E) is an address that no conformant Two-Port MAC Relay (TPMR) component, Service VLAN (S-VLAN) component, Customer VLAN (C-VLAN) component, or MAC Bridge can forward. PDUs transmitted using this destination address, or any other addresses that appear in Table 8-1, Table 8-2, and Table 8-3 (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]), can therefore travel no further than those stations that can be reached via a single individual LAN from the originating station. The Nearest non-TPMR Bridge group address (01-80-C2-00-00-03), is an address that no conformant S-VLAN component, C-VLAN component, or MAC Bridge can forward; however, this address is relayed by a TPMR component. PDUs using this destination address, or any of the other addresses that appear in both Table 8-1 and Table 8-2 but not in Table 8-3 (01-80-C2-00-00-[00,03,05,06,07,08,09,0A,0B,0C,0D,0F]), will be relayed by any TPMRs but will propagate no further than the nearest S-VLAN component, C-VLAN component, or MAC Bridge. The Nearest Customer Bridge group address (01-80-C2-00-00-00) is an address that no conformant C-VLAN component, MAC Bridge can forward; however, it is relayed by TPMR components and S-VLAN components. PDUs using this destination address, or any of the other addresses that appear in Table 8-1 but not in either Table 8-2 or Table 8-3 (01-80-C2-00-00-[00,0B,0C,0D,0F]), will be relayed by TPMR components and S-VLAN components but will propagate no further than the nearest C-VLAN component or MAC Bridge. Because the LLC Entity associated with each Bridge Port is provided via CPU port, we must not filter these frames but forward them to CPU port. In a Bridge, the transmission Port is majorly decided by ingress and egress rules, FDB, and spanning tree Port State functions of the Forwarding Process. For link-local frames, only CPU port should be designated as destination port in the FDB, and the other functions of the Forwarding Process must not interfere with the decision of the transmission Port. We call this process trapping frames to CPU port. Therefore, on the switch with CPU port architecture, link-local frames must be trapped to CPU port, and certain link-local frames received by a Port of a Bridge comprising a TPMR component or an S-VLAN component must be excluded from it. A Bridge of the switch with CPU port architecture cannot comprise a Two-Port MAC Relay (TPMR) component as a TPMR component supports only a subset of the functionality of a MAC Bridge. A Bridge comprising two Ports (Management Port doesn't count) of this architecture will either function as a standard MAC Bridge or a standard VLAN Bridge. Therefore, a Bridge of this architecture can only comprise S-VLAN components, C-VLAN components, or MAC Bridge components. Since there's no TPMR component, we don't need to relay PDUs using the destination addresses specified on the Nearest non-TPMR section, and the proportion of the Nearest Customer Bridge section where they must be relayed by TPMR components. One option to trap link-local frames to CPU port is to add static FDB entries with CPU port designated as destination port. However, because that Independent VLAN Learning (IVL) is being used on every VID, each entry only applies to a single VLAN Identifier (VID). For a Bridge comprising a MAC Bridge component or a C-VLAN component, there would have to be 16 times 4096 entries. This switch intellectual property can only hold a maximum of 2048 entries. Using this option, there also isn't a mechanism to prevent link-local frames from being discarded when the spanning tree Port State of the reception Port is discarding. The remaining option is to utilise the BPC, RGAC1, RGAC2, RGAC3, and RGAC4 registers. Whilst this applies to every VID, it doesn't contain all of the reserved MAC addresses without affecting the remaining Standard Group MAC Addresses. The REV_UN frame tag utilised using the RGAC4 register covers the remaining 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] destination addresses. It also includes the 01-80-C2-00-00-22 to 01-80-C2-00-00-FF destination addresses which may be relayed by MAC Bridges or VLAN Bridges. The latter option provides better but not complete conformance. This switch intellectual property also does not provide a mechanism to trap link-local frames with specific destination addresses to CPU port by Bridge, to conform to the filtering rules for the distinct Bridge components. Therefore, regardless of the type of the Bridge component, link-local frames with these destination addresses will be trapped to CPU port: 01-80-C2-00-00-[00,01,02,03,0E] In a Bridge comprising a MAC Bridge component or a C-VLAN component: Link-local frames with these destination addresses won't be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] In a Bridge comprising an S-VLAN component: Link-local frames with these destination addresses will be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-00 Link-local frames with these destination addresses won't be trapped to CPU port which won't conform to IEEE Std 802.1Q-2022: 01-80-C2-00-00-[04,05,06,07,08,09,0A] Currently on this switch intellectual property, if the spanning tree Port State of the reception Port is discarding, link-local frames will be discarded. To trap link-local frames regardless of the spanning tree Port State, make the switch regard them as Bridge Protocol Data Units (BPDUs). This switch intellectual property only lets the frames regarded as BPDUs bypass the spanning tree Port State function of the Forwarding Process. With this change, the only remaining interference is the ingress rules. When the reception Port has no PVID assigned on software, VLAN-untagged frames won't be allowed in. There doesn't seem to be a mechanism on the switch intellectual property to have link-local frames bypass this function of the Forwarding Process. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Reviewed-by: Daniel Golle <daniel@makrotopia.org> Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Link: https://lore.kernel.org/r/20240409-b4-for-net-mt7530-fix-link-local-when-stp-discarding-v2-1-07b1150164ac@arinc9.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-04-09 15:01:14 +00:00
mt7530_rmw(priv, MT753X_RGAC2,
MT753X_R0E_BPDU_FR | MT753X_R0E_EG_TAG_MASK |
MT753X_R0E_PORT_FW_MASK | MT753X_R03_BPDU_FR |
MT753X_R03_EG_TAG_MASK | MT753X_R03_PORT_FW_MASK,
MT753X_R0E_BPDU_FR |
MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) |
MT753X_R03_BPDU_FR |
MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
MT753X_BPDU_CPU_ONLY);
}
static int
mt753x_cpu_port_enable(struct dsa_switch *ds, int port)
{
struct mt7530_priv *priv = ds->priv;
int ret;
/* Setup max capability of CPU port at first */
if (priv->info->cpu_port_config) {
ret = priv->info->cpu_port_config(ds, port);
if (ret)
return ret;
}
/* Enable Mediatek header mode on the cpu port */
mt7530_write(priv, MT7530_PVC_P(port),
PORT_SPEC_TAG);
net: dsa: mt7530: fix network connectivity with multiple CPU ports On mt753x_cpu_port_enable() there's code that enables flooding for the CPU port only. Since mt753x_cpu_port_enable() runs twice when both CPU ports are enabled, port 6 becomes the only port to forward the frames to. But port 5 is the active port, so no frames received from the user ports will be forwarded to port 5 which breaks network connectivity. Every bit of the BC_FFP, UNM_FFP, and UNU_FFP bits represents a port. Fix this issue by setting the bit that corresponds to the CPU port without overwriting the other bits. Clear the bits beforehand only for the MT7531 switch. According to the documents MT7621 Giga Switch Programming Guide v0.3 and MT7531 Reference Manual for Development Board v1.0, after reset, the BC_FFP, UNM_FFP, and UNU_FFP bits are set to 1 for MT7531, 0 for MT7530. The commit 5e5502e012b8 ("net: dsa: mt7530: fix roaming from DSA user ports") silently changed the method to set the bits on the MT7530_MFC. Instead of clearing the relevant bits before mt7530_cpu_port_enable() which runs under a for loop, the commit started doing it on mt7530_cpu_port_enable(). Back then, this didn't really matter as only a single CPU port could be used since the CPU port number was hardcoded. The driver was later changed with commit 1f9a6abecf53 ("net: dsa: mt7530: get cpu-port via dp->cpu_dp instead of constant") to retrieve the CPU port via dp->cpu_dp. With that, this silent change became an issue for when using multiple CPU ports. Fixes: 5e5502e012b8 ("net: dsa: mt7530: fix roaming from DSA user ports") Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-05-02 21:09:47 +00:00
/* Enable flooding on the CPU port */
mt7530_set(priv, MT7530_MFC, BC_FFP(BIT(port)) | UNM_FFP(BIT(port)) |
UNU_FFP(BIT(port)));
/* Set CPU port number */
if (priv->id == ID_MT7530 || priv->id == ID_MT7621)
mt7530_rmw(priv, MT7530_MFC, CPU_MASK, CPU_EN | CPU_PORT(port));
/* Add the CPU port to the CPU port bitmap for MT7531 and the switch on
* the MT7988 SoC. Trapped frames will be forwarded to the CPU port that
* is affine to the inbound user port.
*/
if (priv->id == ID_MT7531 || priv->id == ID_MT7988)
mt7530_set(priv, MT7531_CFC, MT7531_CPU_PMAP(BIT(port)));
/* CPU port gets connected to all user ports of
* the switch.
*/
mt7530_write(priv, MT7530_PCR_P(port),
PCR_MATRIX(dsa_user_ports(priv->ds)));
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
/* Set to fallback mode for independent VLAN learning */
mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
MT7530_PORT_FALLBACK_MODE);
return 0;
}
static int
mt7530_port_enable(struct dsa_switch *ds, int port,
struct phy_device *phy)
{
struct dsa_port *dp = dsa_to_port(ds, port);
struct mt7530_priv *priv = ds->priv;
mutex_lock(&priv->reg_mutex);
/* Allow the user port gets connected to the cpu port and also
* restore the port matrix if the port is the member of a certain
* bridge.
*/
if (dsa_port_is_user(dp)) {
struct dsa_port *cpu_dp = dp->cpu_dp;
priv->ports[port].pm |= PCR_MATRIX(BIT(cpu_dp->index));
}
priv->ports[port].enable = true;
mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK,
priv->ports[port].pm);
mt7530_clear(priv, MT7530_PMCR_P(port), PMCR_LINK_SETTINGS_MASK);
mutex_unlock(&priv->reg_mutex);
return 0;
}
static void
mt7530_port_disable(struct dsa_switch *ds, int port)
{
struct mt7530_priv *priv = ds->priv;
mutex_lock(&priv->reg_mutex);
/* Clear up all port matrix which could be restored in the next
* enablement for the port.
*/
priv->ports[port].enable = false;
mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK,
PCR_MATRIX_CLR);
mt7530_clear(priv, MT7530_PMCR_P(port), PMCR_LINK_SETTINGS_MASK);
mutex_unlock(&priv->reg_mutex);
}
static int
mt7530_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
{
struct mt7530_priv *priv = ds->priv;
int length;
u32 val;
/* When a new MTU is set, DSA always set the CPU port's MTU to the
* largest MTU of the user ports. Because the switch only has a global
* RX length register, only allowing CPU port here is enough.
*/
if (!dsa_is_cpu_port(ds, port))
return 0;
mt7530_mutex_lock(priv);
val = mt7530_mii_read(priv, MT7530_GMACCR);
val &= ~MAX_RX_PKT_LEN_MASK;
/* RX length also includes Ethernet header, MTK tag, and FCS length */
length = new_mtu + ETH_HLEN + MTK_HDR_LEN + ETH_FCS_LEN;
if (length <= 1522) {
val |= MAX_RX_PKT_LEN_1522;
} else if (length <= 1536) {
val |= MAX_RX_PKT_LEN_1536;
} else if (length <= 1552) {
val |= MAX_RX_PKT_LEN_1552;
} else {
val &= ~MAX_RX_JUMBO_MASK;
val |= MAX_RX_JUMBO(DIV_ROUND_UP(length, 1024));
val |= MAX_RX_PKT_LEN_JUMBO;
}
mt7530_mii_write(priv, MT7530_GMACCR, val);
mt7530_mutex_unlock(priv);
return 0;
}
static int
mt7530_port_max_mtu(struct dsa_switch *ds, int port)
{
return MT7530_MAX_MTU;
}
static void
mt7530_stp_state_set(struct dsa_switch *ds, int port, u8 state)
{
struct mt7530_priv *priv = ds->priv;
u32 stp_state;
switch (state) {
case BR_STATE_DISABLED:
stp_state = MT7530_STP_DISABLED;
break;
case BR_STATE_BLOCKING:
stp_state = MT7530_STP_BLOCKING;
break;
case BR_STATE_LISTENING:
stp_state = MT7530_STP_LISTENING;
break;
case BR_STATE_LEARNING:
stp_state = MT7530_STP_LEARNING;
break;
case BR_STATE_FORWARDING:
default:
stp_state = MT7530_STP_FORWARDING;
break;
}
mt7530_rmw(priv, MT7530_SSP_P(port), FID_PST_MASK(FID_BRIDGED),
FID_PST(FID_BRIDGED, stp_state));
}
static int
mt7530_port_pre_bridge_flags(struct dsa_switch *ds, int port,
struct switchdev_brport_flags flags,
struct netlink_ext_ack *extack)
{
if (flags.mask & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD |
BR_BCAST_FLOOD))
return -EINVAL;
return 0;
}
static int
mt7530_port_bridge_flags(struct dsa_switch *ds, int port,
struct switchdev_brport_flags flags,
struct netlink_ext_ack *extack)
{
struct mt7530_priv *priv = ds->priv;
if (flags.mask & BR_LEARNING)
mt7530_rmw(priv, MT7530_PSC_P(port), SA_DIS,
flags.val & BR_LEARNING ? 0 : SA_DIS);
if (flags.mask & BR_FLOOD)
mt7530_rmw(priv, MT7530_MFC, UNU_FFP(BIT(port)),
flags.val & BR_FLOOD ? UNU_FFP(BIT(port)) : 0);
if (flags.mask & BR_MCAST_FLOOD)
mt7530_rmw(priv, MT7530_MFC, UNM_FFP(BIT(port)),
flags.val & BR_MCAST_FLOOD ? UNM_FFP(BIT(port)) : 0);
if (flags.mask & BR_BCAST_FLOOD)
mt7530_rmw(priv, MT7530_MFC, BC_FFP(BIT(port)),
flags.val & BR_BCAST_FLOOD ? BC_FFP(BIT(port)) : 0);
return 0;
}
static int
mt7530_port_bridge_join(struct dsa_switch *ds, int port,
struct dsa_bridge bridge, bool *tx_fwd_offload,
struct netlink_ext_ack *extack)
{
struct dsa_port *dp = dsa_to_port(ds, port), *other_dp;
struct dsa_port *cpu_dp = dp->cpu_dp;
u32 port_bitmap = BIT(cpu_dp->index);
struct mt7530_priv *priv = ds->priv;
mutex_lock(&priv->reg_mutex);
dsa_switch_for_each_user_port(other_dp, ds) {
int other_port = other_dp->index;
if (dp == other_dp)
continue;
/* Add this port to the port matrix of the other ports in the
* same bridge. If the port is disabled, port matrix is kept
* and not being setup until the port becomes enabled.
*/
net: dsa: keep the bridge_dev and bridge_num as part of the same structure The main desire behind this is to provide coherent bridge information to the fast path without locking. For example, right now we set dp->bridge_dev and dp->bridge_num from separate code paths, it is theoretically possible for a packet transmission to read these two port properties consecutively and find a bridge number which does not correspond with the bridge device. Another desire is to start passing more complex bridge information to dsa_switch_ops functions. For example, with FDB isolation, it is expected that drivers will need to be passed the bridge which requested an FDB/MDB entry to be offloaded, and along with that bridge_dev, the associated bridge_num should be passed too, in case the driver might want to implement an isolation scheme based on that number. We already pass the {bridge_dev, bridge_num} pair to the TX forwarding offload switch API, however we'd like to remove that and squash it into the basic bridge join/leave API. So that means we need to pass this pair to the bridge join/leave API. During dsa_port_bridge_leave, first we unset dp->bridge_dev, then we call the driver's .port_bridge_leave with what used to be our dp->bridge_dev, but provided as an argument. When bridge_dev and bridge_num get folded into a single structure, we need to preserve this behavior in dsa_port_bridge_leave: we need a copy of what used to be in dp->bridge. Switch drivers check bridge membership by comparing dp->bridge_dev with the provided bridge_dev, but now, if we provide the struct dsa_bridge as a pointer, they cannot keep comparing dp->bridge to the provided pointer, since this only points to an on-stack copy. To make this obvious and prevent driver writers from forgetting and doing stupid things, in this new API, the struct dsa_bridge is provided as a full structure (not very large, contains an int and a pointer) instead of a pointer. An explicit comparison function needs to be used to determine bridge membership: dsa_port_offloads_bridge(). Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Alvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-12-06 16:57:56 +00:00
if (!dsa_port_offloads_bridge(other_dp, &bridge))
continue;
if (priv->ports[other_port].enable)
mt7530_set(priv, MT7530_PCR_P(other_port),
PCR_MATRIX(BIT(port)));
priv->ports[other_port].pm |= PCR_MATRIX(BIT(port));
port_bitmap |= BIT(other_port);
}
/* Add the all other ports to this port matrix. */
if (priv->ports[port].enable)
mt7530_rmw(priv, MT7530_PCR_P(port),
PCR_MATRIX_MASK, PCR_MATRIX(port_bitmap));
priv->ports[port].pm |= PCR_MATRIX(port_bitmap);
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
/* Set to fallback mode for independent VLAN learning */
mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
MT7530_PORT_FALLBACK_MODE);
mutex_unlock(&priv->reg_mutex);
return 0;
}
static void
mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port)
{
struct mt7530_priv *priv = ds->priv;
bool all_user_ports_removed = true;
int i;
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
/* This is called after .port_bridge_leave when leaving a VLAN-aware
* bridge. Don't set standalone ports to fallback mode.
*/
if (dsa_port_bridge_dev_get(dsa_to_port(ds, port)))
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
MT7530_PORT_FALLBACK_MODE);
mt7530_rmw(priv, MT7530_PVC_P(port),
VLAN_ATTR_MASK | PVC_EG_TAG_MASK | ACC_FRM_MASK,
VLAN_ATTR(MT7530_VLAN_TRANSPARENT) |
PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT) |
MT7530_VLAN_ACC_ALL);
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
/* Set PVID to 0 */
mt7530_rmw(priv, MT7530_PPBV1_P(port), G0_PORT_VID_MASK,
G0_PORT_VID_DEF);
for (i = 0; i < MT7530_NUM_PORTS; i++) {
if (dsa_is_user_port(ds, i) &&
dsa_port_is_vlan_filtering(dsa_to_port(ds, i))) {
all_user_ports_removed = false;
break;
}
}
/* CPU port also does the same thing until all user ports belonging to
* the CPU port get out of VLAN filtering mode.
*/
if (all_user_ports_removed) {
struct dsa_port *dp = dsa_to_port(ds, port);
struct dsa_port *cpu_dp = dp->cpu_dp;
mt7530_write(priv, MT7530_PCR_P(cpu_dp->index),
PCR_MATRIX(dsa_user_ports(priv->ds)));
mt7530_write(priv, MT7530_PVC_P(cpu_dp->index), PORT_SPEC_TAG
| PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
}
}
static void
mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port)
{
struct mt7530_priv *priv = ds->priv;
/* Trapped into security mode allows packet forwarding through VLAN
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
* table lookup.
*/
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
if (dsa_is_user_port(ds, port)) {
mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
MT7530_PORT_SECURITY_MODE);
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
mt7530_rmw(priv, MT7530_PPBV1_P(port), G0_PORT_VID_MASK,
G0_PORT_VID(priv->ports[port].pvid));
/* Only accept tagged frames if PVID is not set */
if (!priv->ports[port].pvid)
mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK,
MT7530_VLAN_ACC_TAGGED);
net: dsa: mt7530: don't change PVC_EG_TAG when CPU port becomes VLAN-aware Frank reports that in a mt7530 setup where some ports are standalone and some are in a VLAN-aware bridge, 8021q uppers of the standalone ports lose their VLAN tag on xmit, as seen by the link partner. This seems to occur because once the other ports join the VLAN-aware bridge, mt7530_port_vlan_filtering() also calls mt7530_port_set_vlan_aware(ds, cpu_dp->index), and this affects the way that the switch processes the traffic of the standalone port. Relevant is the PVC_EG_TAG bit. The MT7530 documentation says about it: EG_TAG: Incoming Port Egress Tag VLAN Attribution 0: disabled (system default) 1: consistent (keep the original ingress tag attribute) My interpretation is that this setting applies on the ingress port, and "disabled" is basically the normal behavior, where the egress tag format of the packet (tagged or untagged) is decided by the VLAN table (MT7530_VLAN_EGRESS_UNTAG or MT7530_VLAN_EGRESS_TAG). But there is also an option of overriding the system default behavior, and for the egress tagging format of packets to be decided not by the VLAN table, but simply by copying the ingress tag format (if ingress was tagged, egress is tagged; if ingress was untagged, egress is untagged; aka "consistent). This is useful in 2 scenarios: - VLAN-unaware bridge ports will always encounter a miss in the VLAN table. They should forward a packet as-is, though. So we use "consistent" there. See commit e045124e9399 ("net: dsa: mt7530: fix tagged frames pass-through in VLAN-unaware mode"). - Traffic injected from the CPU port. The operating system is in god mode; if it wants a packet to exit as VLAN-tagged, it sends it as VLAN-tagged. Otherwise it sends it as VLAN-untagged*. *This is true only if we don't consider the bridge TX forwarding offload feature, which mt7530 doesn't support. So for now, make the CPU port always stay in "consistent" mode to allow software VLANs to be forwarded to their egress ports with the VLAN tag intact, and not stripped. Link: https://lore.kernel.org/netdev/trinity-e6294d28-636c-4c40-bb8b-b523521b00be-1674233135062@3c-app-gmx-bs36/ Fixes: e045124e9399 ("net: dsa: mt7530: fix tagged frames pass-through in VLAN-unaware mode") Reported-by: Frank Wunderlich <frank-w@public-files.de> Tested-by: Frank Wunderlich <frank-w@public-files.de> Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Arınç ÜNAL <arinc.unal@arinc9.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/20230205140713.1609281-1-vladimir.oltean@nxp.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2023-02-05 14:07:13 +00:00
/* Set the port as a user port which is to be able to recognize
* VID from incoming packets before fetching entry within the
* VLAN table.
*/
mt7530_rmw(priv, MT7530_PVC_P(port),
VLAN_ATTR_MASK | PVC_EG_TAG_MASK,
VLAN_ATTR(MT7530_VLAN_USER) |
PVC_EG_TAG(MT7530_VLAN_EG_DISABLED));
} else {
/* Also set CPU ports to the "user" VLAN port attribute, to
* allow VLAN classification, but keep the EG_TAG attribute as
* "consistent" (i.o.w. don't change its value) for packets
* received by the switch from the CPU, so that tagged packets
* are forwarded to user ports as tagged, and untagged as
* untagged.
*/
mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK,
VLAN_ATTR(MT7530_VLAN_USER));
}
}
static void
mt7530_port_bridge_leave(struct dsa_switch *ds, int port,
net: dsa: keep the bridge_dev and bridge_num as part of the same structure The main desire behind this is to provide coherent bridge information to the fast path without locking. For example, right now we set dp->bridge_dev and dp->bridge_num from separate code paths, it is theoretically possible for a packet transmission to read these two port properties consecutively and find a bridge number which does not correspond with the bridge device. Another desire is to start passing more complex bridge information to dsa_switch_ops functions. For example, with FDB isolation, it is expected that drivers will need to be passed the bridge which requested an FDB/MDB entry to be offloaded, and along with that bridge_dev, the associated bridge_num should be passed too, in case the driver might want to implement an isolation scheme based on that number. We already pass the {bridge_dev, bridge_num} pair to the TX forwarding offload switch API, however we'd like to remove that and squash it into the basic bridge join/leave API. So that means we need to pass this pair to the bridge join/leave API. During dsa_port_bridge_leave, first we unset dp->bridge_dev, then we call the driver's .port_bridge_leave with what used to be our dp->bridge_dev, but provided as an argument. When bridge_dev and bridge_num get folded into a single structure, we need to preserve this behavior in dsa_port_bridge_leave: we need a copy of what used to be in dp->bridge. Switch drivers check bridge membership by comparing dp->bridge_dev with the provided bridge_dev, but now, if we provide the struct dsa_bridge as a pointer, they cannot keep comparing dp->bridge to the provided pointer, since this only points to an on-stack copy. To make this obvious and prevent driver writers from forgetting and doing stupid things, in this new API, the struct dsa_bridge is provided as a full structure (not very large, contains an int and a pointer) instead of a pointer. An explicit comparison function needs to be used to determine bridge membership: dsa_port_offloads_bridge(). Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Alvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-12-06 16:57:56 +00:00
struct dsa_bridge bridge)
{
struct dsa_port *dp = dsa_to_port(ds, port), *other_dp;
struct dsa_port *cpu_dp = dp->cpu_dp;
struct mt7530_priv *priv = ds->priv;
mutex_lock(&priv->reg_mutex);
dsa_switch_for_each_user_port(other_dp, ds) {
int other_port = other_dp->index;
if (dp == other_dp)
continue;
/* Remove this port from the port matrix of the other ports
* in the same bridge. If the port is disabled, port matrix
* is kept and not being setup until the port becomes enabled.
*/
net: dsa: keep the bridge_dev and bridge_num as part of the same structure The main desire behind this is to provide coherent bridge information to the fast path without locking. For example, right now we set dp->bridge_dev and dp->bridge_num from separate code paths, it is theoretically possible for a packet transmission to read these two port properties consecutively and find a bridge number which does not correspond with the bridge device. Another desire is to start passing more complex bridge information to dsa_switch_ops functions. For example, with FDB isolation, it is expected that drivers will need to be passed the bridge which requested an FDB/MDB entry to be offloaded, and along with that bridge_dev, the associated bridge_num should be passed too, in case the driver might want to implement an isolation scheme based on that number. We already pass the {bridge_dev, bridge_num} pair to the TX forwarding offload switch API, however we'd like to remove that and squash it into the basic bridge join/leave API. So that means we need to pass this pair to the bridge join/leave API. During dsa_port_bridge_leave, first we unset dp->bridge_dev, then we call the driver's .port_bridge_leave with what used to be our dp->bridge_dev, but provided as an argument. When bridge_dev and bridge_num get folded into a single structure, we need to preserve this behavior in dsa_port_bridge_leave: we need a copy of what used to be in dp->bridge. Switch drivers check bridge membership by comparing dp->bridge_dev with the provided bridge_dev, but now, if we provide the struct dsa_bridge as a pointer, they cannot keep comparing dp->bridge to the provided pointer, since this only points to an on-stack copy. To make this obvious and prevent driver writers from forgetting and doing stupid things, in this new API, the struct dsa_bridge is provided as a full structure (not very large, contains an int and a pointer) instead of a pointer. An explicit comparison function needs to be used to determine bridge membership: dsa_port_offloads_bridge(). Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Alvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-12-06 16:57:56 +00:00
if (!dsa_port_offloads_bridge(other_dp, &bridge))
continue;
if (priv->ports[other_port].enable)
mt7530_clear(priv, MT7530_PCR_P(other_port),
PCR_MATRIX(BIT(port)));
priv->ports[other_port].pm &= ~PCR_MATRIX(BIT(port));
}
/* Set the cpu port to be the only one in the port matrix of
* this port.
*/
if (priv->ports[port].enable)
mt7530_rmw(priv, MT7530_PCR_P(port), PCR_MATRIX_MASK,
PCR_MATRIX(BIT(cpu_dp->index)));
priv->ports[port].pm = PCR_MATRIX(BIT(cpu_dp->index));
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
/* When a port is removed from the bridge, the port would be set up
* back to the default as is at initial boot which is a VLAN-unaware
* port.
*/
mt7530_rmw(priv, MT7530_PCR_P(port), PCR_PORT_VLAN_MASK,
MT7530_PORT_MATRIX_MODE);
mutex_unlock(&priv->reg_mutex);
}
static int
mt7530_port_fdb_add(struct dsa_switch *ds, int port,
net: dsa: request drivers to perform FDB isolation For DSA, to encourage drivers to perform FDB isolation simply means to track which bridge does each FDB and MDB entry belong to. It then becomes the driver responsibility to use something that makes the FDB entry from one bridge not match the FDB lookup of ports from other bridges. The top-level functions where the bridge is determined are: - dsa_port_fdb_{add,del} - dsa_port_host_fdb_{add,del} - dsa_port_mdb_{add,del} - dsa_port_host_mdb_{add,del} aka the pre-crosschip-notifier functions. Changing the API to pass a reference to a bridge is not superfluous, and looking at the passed bridge argument is not the same as having the driver look at dsa_to_port(ds, port)->bridge from the ->port_fdb_add() method. DSA installs FDB and MDB entries on shared (CPU and DSA) ports as well, and those do not have any dp->bridge information to retrieve, because they are not in any bridge - they are merely the pipes that serve the user ports that are in one or multiple bridges. The struct dsa_bridge associated with each FDB/MDB entry is encapsulated in a larger "struct dsa_db" database. Although only databases associated to bridges are notified for now, this API will be the starting point for implementing IFF_UNICAST_FLT in DSA. There, the idea is to install FDB entries on the CPU port which belong to the corresponding user port's port database. These are supposed to match only when the port is standalone. It is better to introduce the API in its expected final form than to introduce it for bridges first, then to have to change drivers which may have made one or more assumptions. Drivers can use the provided bridge.num, but they can also use a different numbering scheme that is more convenient. DSA must perform refcounting on the CPU and DSA ports by also taking into account the bridge number. So if two bridges request the same local address, DSA must notify the driver twice, once for each bridge. In fact, if the driver supports FDB isolation, DSA must perform refcounting per bridge, but if the driver doesn't, DSA must refcount host addresses across all bridges, otherwise it would be telling the driver to delete an FDB entry for a bridge and the driver would delete it for all bridges. So introduce a bool fdb_isolation in drivers which would make all bridge databases passed to the cross-chip notifier have the same number (0). This makes dsa_mac_addr_find() -> dsa_db_equal() say that all bridge databases are the same database - which is essentially the legacy behavior. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-25 09:22:22 +00:00
const unsigned char *addr, u16 vid,
struct dsa_db db)
{
struct mt7530_priv *priv = ds->priv;
int ret;
u8 port_mask = BIT(port);
mutex_lock(&priv->reg_mutex);
mt7530_fdb_write(priv, vid, port_mask, addr, -1, STATIC_ENT);
ret = mt7530_fdb_cmd(priv, MT7530_FDB_WRITE, NULL);
mutex_unlock(&priv->reg_mutex);
return ret;
}
static int
mt7530_port_fdb_del(struct dsa_switch *ds, int port,
net: dsa: request drivers to perform FDB isolation For DSA, to encourage drivers to perform FDB isolation simply means to track which bridge does each FDB and MDB entry belong to. It then becomes the driver responsibility to use something that makes the FDB entry from one bridge not match the FDB lookup of ports from other bridges. The top-level functions where the bridge is determined are: - dsa_port_fdb_{add,del} - dsa_port_host_fdb_{add,del} - dsa_port_mdb_{add,del} - dsa_port_host_mdb_{add,del} aka the pre-crosschip-notifier functions. Changing the API to pass a reference to a bridge is not superfluous, and looking at the passed bridge argument is not the same as having the driver look at dsa_to_port(ds, port)->bridge from the ->port_fdb_add() method. DSA installs FDB and MDB entries on shared (CPU and DSA) ports as well, and those do not have any dp->bridge information to retrieve, because they are not in any bridge - they are merely the pipes that serve the user ports that are in one or multiple bridges. The struct dsa_bridge associated with each FDB/MDB entry is encapsulated in a larger "struct dsa_db" database. Although only databases associated to bridges are notified for now, this API will be the starting point for implementing IFF_UNICAST_FLT in DSA. There, the idea is to install FDB entries on the CPU port which belong to the corresponding user port's port database. These are supposed to match only when the port is standalone. It is better to introduce the API in its expected final form than to introduce it for bridges first, then to have to change drivers which may have made one or more assumptions. Drivers can use the provided bridge.num, but they can also use a different numbering scheme that is more convenient. DSA must perform refcounting on the CPU and DSA ports by also taking into account the bridge number. So if two bridges request the same local address, DSA must notify the driver twice, once for each bridge. In fact, if the driver supports FDB isolation, DSA must perform refcounting per bridge, but if the driver doesn't, DSA must refcount host addresses across all bridges, otherwise it would be telling the driver to delete an FDB entry for a bridge and the driver would delete it for all bridges. So introduce a bool fdb_isolation in drivers which would make all bridge databases passed to the cross-chip notifier have the same number (0). This makes dsa_mac_addr_find() -> dsa_db_equal() say that all bridge databases are the same database - which is essentially the legacy behavior. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-25 09:22:22 +00:00
const unsigned char *addr, u16 vid,
struct dsa_db db)
{
struct mt7530_priv *priv = ds->priv;
int ret;
u8 port_mask = BIT(port);
mutex_lock(&priv->reg_mutex);
mt7530_fdb_write(priv, vid, port_mask, addr, -1, STATIC_EMP);
ret = mt7530_fdb_cmd(priv, MT7530_FDB_WRITE, NULL);
mutex_unlock(&priv->reg_mutex);
return ret;
}
static int
mt7530_port_fdb_dump(struct dsa_switch *ds, int port,
dsa_fdb_dump_cb_t *cb, void *data)
{
struct mt7530_priv *priv = ds->priv;
struct mt7530_fdb _fdb = { 0 };
int cnt = MT7530_NUM_FDB_RECORDS;
int ret = 0;
u32 rsp = 0;
mutex_lock(&priv->reg_mutex);
ret = mt7530_fdb_cmd(priv, MT7530_FDB_START, &rsp);
if (ret < 0)
goto err;
do {
if (rsp & ATC_SRCH_HIT) {
mt7530_fdb_read(priv, &_fdb);
if (_fdb.port_mask & BIT(port)) {
ret = cb(_fdb.mac, _fdb.vid, _fdb.noarp,
data);
if (ret < 0)
break;
}
}
} while (--cnt &&
!(rsp & ATC_SRCH_END) &&
!mt7530_fdb_cmd(priv, MT7530_FDB_NEXT, &rsp));
err:
mutex_unlock(&priv->reg_mutex);
return 0;
}
static int
mt7530_port_mdb_add(struct dsa_switch *ds, int port,
net: dsa: request drivers to perform FDB isolation For DSA, to encourage drivers to perform FDB isolation simply means to track which bridge does each FDB and MDB entry belong to. It then becomes the driver responsibility to use something that makes the FDB entry from one bridge not match the FDB lookup of ports from other bridges. The top-level functions where the bridge is determined are: - dsa_port_fdb_{add,del} - dsa_port_host_fdb_{add,del} - dsa_port_mdb_{add,del} - dsa_port_host_mdb_{add,del} aka the pre-crosschip-notifier functions. Changing the API to pass a reference to a bridge is not superfluous, and looking at the passed bridge argument is not the same as having the driver look at dsa_to_port(ds, port)->bridge from the ->port_fdb_add() method. DSA installs FDB and MDB entries on shared (CPU and DSA) ports as well, and those do not have any dp->bridge information to retrieve, because they are not in any bridge - they are merely the pipes that serve the user ports that are in one or multiple bridges. The struct dsa_bridge associated with each FDB/MDB entry is encapsulated in a larger "struct dsa_db" database. Although only databases associated to bridges are notified for now, this API will be the starting point for implementing IFF_UNICAST_FLT in DSA. There, the idea is to install FDB entries on the CPU port which belong to the corresponding user port's port database. These are supposed to match only when the port is standalone. It is better to introduce the API in its expected final form than to introduce it for bridges first, then to have to change drivers which may have made one or more assumptions. Drivers can use the provided bridge.num, but they can also use a different numbering scheme that is more convenient. DSA must perform refcounting on the CPU and DSA ports by also taking into account the bridge number. So if two bridges request the same local address, DSA must notify the driver twice, once for each bridge. In fact, if the driver supports FDB isolation, DSA must perform refcounting per bridge, but if the driver doesn't, DSA must refcount host addresses across all bridges, otherwise it would be telling the driver to delete an FDB entry for a bridge and the driver would delete it for all bridges. So introduce a bool fdb_isolation in drivers which would make all bridge databases passed to the cross-chip notifier have the same number (0). This makes dsa_mac_addr_find() -> dsa_db_equal() say that all bridge databases are the same database - which is essentially the legacy behavior. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-25 09:22:22 +00:00
const struct switchdev_obj_port_mdb *mdb,
struct dsa_db db)
{
struct mt7530_priv *priv = ds->priv;
const u8 *addr = mdb->addr;
u16 vid = mdb->vid;
u8 port_mask = 0;
int ret;
mutex_lock(&priv->reg_mutex);
mt7530_fdb_write(priv, vid, 0, addr, 0, STATIC_EMP);
if (!mt7530_fdb_cmd(priv, MT7530_FDB_READ, NULL))
port_mask = (mt7530_read(priv, MT7530_ATRD) >> PORT_MAP)
& PORT_MAP_MASK;
port_mask |= BIT(port);
mt7530_fdb_write(priv, vid, port_mask, addr, -1, STATIC_ENT);
ret = mt7530_fdb_cmd(priv, MT7530_FDB_WRITE, NULL);
mutex_unlock(&priv->reg_mutex);
return ret;
}
static int
mt7530_port_mdb_del(struct dsa_switch *ds, int port,
net: dsa: request drivers to perform FDB isolation For DSA, to encourage drivers to perform FDB isolation simply means to track which bridge does each FDB and MDB entry belong to. It then becomes the driver responsibility to use something that makes the FDB entry from one bridge not match the FDB lookup of ports from other bridges. The top-level functions where the bridge is determined are: - dsa_port_fdb_{add,del} - dsa_port_host_fdb_{add,del} - dsa_port_mdb_{add,del} - dsa_port_host_mdb_{add,del} aka the pre-crosschip-notifier functions. Changing the API to pass a reference to a bridge is not superfluous, and looking at the passed bridge argument is not the same as having the driver look at dsa_to_port(ds, port)->bridge from the ->port_fdb_add() method. DSA installs FDB and MDB entries on shared (CPU and DSA) ports as well, and those do not have any dp->bridge information to retrieve, because they are not in any bridge - they are merely the pipes that serve the user ports that are in one or multiple bridges. The struct dsa_bridge associated with each FDB/MDB entry is encapsulated in a larger "struct dsa_db" database. Although only databases associated to bridges are notified for now, this API will be the starting point for implementing IFF_UNICAST_FLT in DSA. There, the idea is to install FDB entries on the CPU port which belong to the corresponding user port's port database. These are supposed to match only when the port is standalone. It is better to introduce the API in its expected final form than to introduce it for bridges first, then to have to change drivers which may have made one or more assumptions. Drivers can use the provided bridge.num, but they can also use a different numbering scheme that is more convenient. DSA must perform refcounting on the CPU and DSA ports by also taking into account the bridge number. So if two bridges request the same local address, DSA must notify the driver twice, once for each bridge. In fact, if the driver supports FDB isolation, DSA must perform refcounting per bridge, but if the driver doesn't, DSA must refcount host addresses across all bridges, otherwise it would be telling the driver to delete an FDB entry for a bridge and the driver would delete it for all bridges. So introduce a bool fdb_isolation in drivers which would make all bridge databases passed to the cross-chip notifier have the same number (0). This makes dsa_mac_addr_find() -> dsa_db_equal() say that all bridge databases are the same database - which is essentially the legacy behavior. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-25 09:22:22 +00:00
const struct switchdev_obj_port_mdb *mdb,
struct dsa_db db)
{
struct mt7530_priv *priv = ds->priv;
const u8 *addr = mdb->addr;
u16 vid = mdb->vid;
u8 port_mask = 0;
int ret;
mutex_lock(&priv->reg_mutex);
mt7530_fdb_write(priv, vid, 0, addr, 0, STATIC_EMP);
if (!mt7530_fdb_cmd(priv, MT7530_FDB_READ, NULL))
port_mask = (mt7530_read(priv, MT7530_ATRD) >> PORT_MAP)
& PORT_MAP_MASK;
port_mask &= ~BIT(port);
mt7530_fdb_write(priv, vid, port_mask, addr, -1,
port_mask ? STATIC_ENT : STATIC_EMP);
ret = mt7530_fdb_cmd(priv, MT7530_FDB_WRITE, NULL);
mutex_unlock(&priv->reg_mutex);
return ret;
}
static int
mt7530_vlan_cmd(struct mt7530_priv *priv, enum mt7530_vlan_cmd cmd, u16 vid)
{
struct mt7530_dummy_poll p;
u32 val;
int ret;
val = VTCR_BUSY | VTCR_FUNC(cmd) | vid;
mt7530_write(priv, MT7530_VTCR, val);
INIT_MT7530_DUMMY_POLL(&p, priv, MT7530_VTCR);
ret = readx_poll_timeout(_mt7530_read, &p, val,
!(val & VTCR_BUSY), 20, 20000);
if (ret < 0) {
dev_err(priv->dev, "poll timeout\n");
return ret;
}
val = mt7530_read(priv, MT7530_VTCR);
if (val & VTCR_INVALID) {
dev_err(priv->dev, "read VTCR invalid\n");
return -EINVAL;
}
return 0;
}
static int
mt7530_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering,
struct netlink_ext_ack *extack)
{
struct dsa_port *dp = dsa_to_port(ds, port);
struct dsa_port *cpu_dp = dp->cpu_dp;
if (vlan_filtering) {
/* The port is being kept as VLAN-unaware port when bridge is
* set up with vlan_filtering not being set, Otherwise, the
* port and the corresponding CPU port is required the setup
* for becoming a VLAN-aware port.
*/
mt7530_port_set_vlan_aware(ds, port);
mt7530_port_set_vlan_aware(ds, cpu_dp->index);
} else {
mt7530_port_set_vlan_unaware(ds, port);
}
return 0;
}
static void
mt7530_hw_vlan_add(struct mt7530_priv *priv,
struct mt7530_hw_vlan_entry *entry)
{
struct dsa_port *dp = dsa_to_port(priv->ds, entry->port);
u8 new_members;
u32 val;
new_members = entry->old_members | BIT(entry->port);
/* Validate the entry with independent learning, create egress tag per
* VLAN and joining the port as one of the port members.
*/
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
val = IVL_MAC | VTAG_EN | PORT_MEM(new_members) | FID(FID_BRIDGED) |
VLAN_VALID;
mt7530_write(priv, MT7530_VAWD1, val);
/* Decide whether adding tag or not for those outgoing packets from the
* port inside the VLAN.
* CPU port is always taken as a tagged port for serving more than one
* VLANs across and also being applied with egress type stack mode for
* that VLAN tags would be appended after hardware special tag used as
* DSA tag.
*/
if (dsa_port_is_cpu(dp))
val = MT7530_VLAN_EGRESS_STACK;
else if (entry->untagged)
val = MT7530_VLAN_EGRESS_UNTAG;
else
val = MT7530_VLAN_EGRESS_TAG;
mt7530_rmw(priv, MT7530_VAWD2,
ETAG_CTRL_P_MASK(entry->port),
ETAG_CTRL_P(entry->port, val));
}
static void
mt7530_hw_vlan_del(struct mt7530_priv *priv,
struct mt7530_hw_vlan_entry *entry)
{
u8 new_members;
u32 val;
new_members = entry->old_members & ~BIT(entry->port);
val = mt7530_read(priv, MT7530_VAWD1);
if (!(val & VLAN_VALID)) {
dev_err(priv->dev,
"Cannot be deleted due to invalid entry\n");
return;
}
if (new_members) {
val = IVL_MAC | VTAG_EN | PORT_MEM(new_members) |
VLAN_VALID;
mt7530_write(priv, MT7530_VAWD1, val);
} else {
mt7530_write(priv, MT7530_VAWD1, 0);
mt7530_write(priv, MT7530_VAWD2, 0);
}
}
static void
mt7530_hw_vlan_update(struct mt7530_priv *priv, u16 vid,
struct mt7530_hw_vlan_entry *entry,
mt7530_vlan_op vlan_op)
{
u32 val;
/* Fetch entry */
mt7530_vlan_cmd(priv, MT7530_VTCR_RD_VID, vid);
val = mt7530_read(priv, MT7530_VAWD1);
entry->old_members = (val >> PORT_MEM_SHFT) & PORT_MEM_MASK;
/* Manipulate entry */
vlan_op(priv, entry);
/* Flush result to hardware */
mt7530_vlan_cmd(priv, MT7530_VTCR_WR_VID, vid);
}
static int
mt7530_setup_vlan0(struct mt7530_priv *priv)
{
u32 val;
/* Validate the entry with independent learning, keep the original
* ingress tag attribute.
*/
val = IVL_MAC | EG_CON | PORT_MEM(MT7530_ALL_MEMBERS) | FID(FID_BRIDGED) |
VLAN_VALID;
mt7530_write(priv, MT7530_VAWD1, val);
return mt7530_vlan_cmd(priv, MT7530_VTCR_WR_VID, 0);
}
net: dsa: remove the transactional logic from VLAN objects It should be the driver's business to logically separate its VLAN offloading into a preparation and a commit phase, and some drivers don't need / can't do this. So remove the transactional shim from DSA and let drivers propagate errors directly from the .port_vlan_add callback. It would appear that the code has worse error handling now than it had before. DSA is the only in-kernel user of switchdev that offloads one switchdev object to more than one port: for every VLAN object offloaded to a user port, that VLAN is also offloaded to the CPU port. So the "prepare for user port -> check for errors -> prepare for CPU port -> check for errors -> commit for user port -> commit for CPU port" sequence appears to make more sense than the one we are using now: "offload to user port -> check for errors -> offload to CPU port -> check for errors", but it is really a compromise. In the new way, we can catch errors from the commit phase that we previously had to ignore. But we have our hands tied and cannot do any rollback now: if we add a VLAN on the CPU port and it fails, we can't do the rollback by simply deleting it from the user port, because the switchdev API is not so nice with us: it could have simply been there already, even with the same flags. So we don't even attempt to rollback anything on addition error, just leave whatever VLANs managed to get offloaded right where they are. This should not be a problem at all in practice. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Jiri Pirko <jiri@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-09 00:01:53 +00:00
static int
mt7530_port_vlan_add(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_vlan *vlan,
struct netlink_ext_ack *extack)
{
bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
struct mt7530_hw_vlan_entry new_entry;
struct mt7530_priv *priv = ds->priv;
mutex_lock(&priv->reg_mutex);
net: switchdev: remove vid_begin -> vid_end range from VLAN objects The call path of a switchdev VLAN addition to the bridge looks something like this today: nbp_vlan_init | __br_vlan_set_default_pvid | | | | | br_afspec | | | | | | | v | | | br_process_vlan_info | | | | | | | v | | | br_vlan_info | | | / \ / | | / \ / | | / \ / | | / \ / v v v v v nbp_vlan_add br_vlan_add ------+ | ^ ^ | | | / | | | | / / / | \ br_vlan_get_master/ / v \ ^ / / br_vlan_add_existing \ | / / | \ | / / / \ | / / / \ | / / / \ | / / / v | | v / __vlan_add / / | / / | / v | / __vlan_vid_add | / \ | / v v v br_switchdev_port_vlan_add The ranges UAPI was introduced to the bridge in commit bdced7ef7838 ("bridge: support for multiple vlans and vlan ranges in setlink and dellink requests") (Jan 10 2015). But the VLAN ranges (parsed in br_afspec) have always been passed one by one, through struct bridge_vlan_info tmp_vinfo, to br_vlan_info. So the range never went too far in depth. Then Scott Feldman introduced the switchdev_port_bridge_setlink function in commit 47f8328bb1a4 ("switchdev: add new switchdev bridge setlink"). That marked the introduction of the SWITCHDEV_OBJ_PORT_VLAN, which made full use of the range. But switchdev_port_bridge_setlink was called like this: br_setlink -> br_afspec -> switchdev_port_bridge_setlink Basically, the switchdev and the bridge code were not tightly integrated. Then commit 41c498b9359e ("bridge: restore br_setlink back to original") came, and switchdev drivers were required to implement .ndo_bridge_setlink = switchdev_port_bridge_setlink for a while. In the meantime, commits such as 0944d6b5a2fa ("bridge: try switchdev op first in __vlan_vid_add/del") finally made switchdev penetrate the br_vlan_info() barrier and start to develop the call path we have today. But remember, br_vlan_info() still receives VLANs one by one. Then Arkadi Sharshevsky refactored the switchdev API in 2017 in commit 29ab586c3d83 ("net: switchdev: Remove bridge bypass support from switchdev") so that drivers would not implement .ndo_bridge_setlink any longer. The switchdev_port_bridge_setlink also got deleted. This refactoring removed the parallel bridge_setlink implementation from switchdev, and left the only switchdev VLAN objects to be the ones offloaded from __vlan_vid_add (basically RX filtering) and __vlan_add (the latter coming from commit 9c86ce2c1ae3 ("net: bridge: Notify about bridge VLANs")). That is to say, today the switchdev VLAN object ranges are not used in the kernel. Refactoring the above call path is a bit complicated, when the bridge VLAN call path is already a bit complicated. Let's go off and finish the job of commit 29ab586c3d83 by deleting the bogus iteration through the VLAN ranges from the drivers. Some aspects of this feature never made too much sense in the first place. For example, what is a range of VLANs all having the BRIDGE_VLAN_INFO_PVID flag supposed to mean, when a port can obviously have a single pvid? This particular configuration _is_ denied as of commit 6623c60dc28e ("bridge: vlan: enforce no pvid flag in vlan ranges"), but from an API perspective, the driver still has to play pretend, and only offload the vlan->vid_end as pvid. And the addition of a switchdev VLAN object can modify the flags of another, completely unrelated, switchdev VLAN object! (a VLAN that is PVID will invalidate the PVID flag from whatever other VLAN had previously been offloaded with switchdev and had that flag. Yet switchdev never notifies about that change, drivers are supposed to guess). Nonetheless, having a VLAN range in the API makes error handling look scarier than it really is - unwinding on errors and all of that. When in reality, no one really calls this API with more than one VLAN. It is all unnecessary complexity. And despite appearing pretentious (two-phase transactional model and all), the switchdev API is really sloppy because the VLAN addition and removal operations are not paired with one another (you can add a VLAN 100 times and delete it just once). The bridge notifies through switchdev of a VLAN addition not only when the flags of an existing VLAN change, but also when nothing changes. There are switchdev drivers out there who don't like adding a VLAN that has already been added, and those checks don't really belong at driver level. But the fact that the API contains ranges is yet another factor that prevents this from being addressed in the future. Of the existing switchdev pieces of hardware, it appears that only Mellanox Spectrum supports offloading more than one VLAN at a time, through mlxsw_sp_port_vlan_set. I have kept that code internal to the driver, because there is some more bookkeeping that makes use of it, but I deleted it from the switchdev API. But since the switchdev support for ranges has already been de facto deleted by a Mellanox employee and nobody noticed for 4 years, I'm going to assume it's not a biggie. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Ido Schimmel <idosch@nvidia.com> # switchdev and mlxsw Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de> # hellcreek Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-09 00:01:46 +00:00
mt7530_hw_vlan_entry_init(&new_entry, port, untagged);
mt7530_hw_vlan_update(priv, vlan->vid, &new_entry, mt7530_hw_vlan_add);
if (pvid) {
net: switchdev: remove vid_begin -> vid_end range from VLAN objects The call path of a switchdev VLAN addition to the bridge looks something like this today: nbp_vlan_init | __br_vlan_set_default_pvid | | | | | br_afspec | | | | | | | v | | | br_process_vlan_info | | | | | | | v | | | br_vlan_info | | | / \ / | | / \ / | | / \ / | | / \ / v v v v v nbp_vlan_add br_vlan_add ------+ | ^ ^ | | | / | | | | / / / | \ br_vlan_get_master/ / v \ ^ / / br_vlan_add_existing \ | / / | \ | / / / \ | / / / \ | / / / \ | / / / v | | v / __vlan_add / / | / / | / v | / __vlan_vid_add | / \ | / v v v br_switchdev_port_vlan_add The ranges UAPI was introduced to the bridge in commit bdced7ef7838 ("bridge: support for multiple vlans and vlan ranges in setlink and dellink requests") (Jan 10 2015). But the VLAN ranges (parsed in br_afspec) have always been passed one by one, through struct bridge_vlan_info tmp_vinfo, to br_vlan_info. So the range never went too far in depth. Then Scott Feldman introduced the switchdev_port_bridge_setlink function in commit 47f8328bb1a4 ("switchdev: add new switchdev bridge setlink"). That marked the introduction of the SWITCHDEV_OBJ_PORT_VLAN, which made full use of the range. But switchdev_port_bridge_setlink was called like this: br_setlink -> br_afspec -> switchdev_port_bridge_setlink Basically, the switchdev and the bridge code were not tightly integrated. Then commit 41c498b9359e ("bridge: restore br_setlink back to original") came, and switchdev drivers were required to implement .ndo_bridge_setlink = switchdev_port_bridge_setlink for a while. In the meantime, commits such as 0944d6b5a2fa ("bridge: try switchdev op first in __vlan_vid_add/del") finally made switchdev penetrate the br_vlan_info() barrier and start to develop the call path we have today. But remember, br_vlan_info() still receives VLANs one by one. Then Arkadi Sharshevsky refactored the switchdev API in 2017 in commit 29ab586c3d83 ("net: switchdev: Remove bridge bypass support from switchdev") so that drivers would not implement .ndo_bridge_setlink any longer. The switchdev_port_bridge_setlink also got deleted. This refactoring removed the parallel bridge_setlink implementation from switchdev, and left the only switchdev VLAN objects to be the ones offloaded from __vlan_vid_add (basically RX filtering) and __vlan_add (the latter coming from commit 9c86ce2c1ae3 ("net: bridge: Notify about bridge VLANs")). That is to say, today the switchdev VLAN object ranges are not used in the kernel. Refactoring the above call path is a bit complicated, when the bridge VLAN call path is already a bit complicated. Let's go off and finish the job of commit 29ab586c3d83 by deleting the bogus iteration through the VLAN ranges from the drivers. Some aspects of this feature never made too much sense in the first place. For example, what is a range of VLANs all having the BRIDGE_VLAN_INFO_PVID flag supposed to mean, when a port can obviously have a single pvid? This particular configuration _is_ denied as of commit 6623c60dc28e ("bridge: vlan: enforce no pvid flag in vlan ranges"), but from an API perspective, the driver still has to play pretend, and only offload the vlan->vid_end as pvid. And the addition of a switchdev VLAN object can modify the flags of another, completely unrelated, switchdev VLAN object! (a VLAN that is PVID will invalidate the PVID flag from whatever other VLAN had previously been offloaded with switchdev and had that flag. Yet switchdev never notifies about that change, drivers are supposed to guess). Nonetheless, having a VLAN range in the API makes error handling look scarier than it really is - unwinding on errors and all of that. When in reality, no one really calls this API with more than one VLAN. It is all unnecessary complexity. And despite appearing pretentious (two-phase transactional model and all), the switchdev API is really sloppy because the VLAN addition and removal operations are not paired with one another (you can add a VLAN 100 times and delete it just once). The bridge notifies through switchdev of a VLAN addition not only when the flags of an existing VLAN change, but also when nothing changes. There are switchdev drivers out there who don't like adding a VLAN that has already been added, and those checks don't really belong at driver level. But the fact that the API contains ranges is yet another factor that prevents this from being addressed in the future. Of the existing switchdev pieces of hardware, it appears that only Mellanox Spectrum supports offloading more than one VLAN at a time, through mlxsw_sp_port_vlan_set. I have kept that code internal to the driver, because there is some more bookkeeping that makes use of it, but I deleted it from the switchdev API. But since the switchdev support for ranges has already been de facto deleted by a Mellanox employee and nobody noticed for 4 years, I'm going to assume it's not a biggie. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Ido Schimmel <idosch@nvidia.com> # switchdev and mlxsw Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de> # hellcreek Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-09 00:01:46 +00:00
priv->ports[port].pvid = vlan->vid;
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
/* Accept all frames if PVID is set */
mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK,
MT7530_VLAN_ACC_ALL);
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
/* Only configure PVID if VLAN filtering is enabled */
if (dsa_port_is_vlan_filtering(dsa_to_port(ds, port)))
mt7530_rmw(priv, MT7530_PPBV1_P(port),
G0_PORT_VID_MASK,
G0_PORT_VID(vlan->vid));
} else if (vlan->vid && priv->ports[port].pvid == vlan->vid) {
/* This VLAN is overwritten without PVID, so unset it */
priv->ports[port].pvid = G0_PORT_VID_DEF;
/* Only accept tagged frames if the port is VLAN-aware */
if (dsa_port_is_vlan_filtering(dsa_to_port(ds, port)))
mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK,
MT7530_VLAN_ACC_TAGGED);
mt7530_rmw(priv, MT7530_PPBV1_P(port), G0_PORT_VID_MASK,
G0_PORT_VID_DEF);
}
mutex_unlock(&priv->reg_mutex);
net: dsa: remove the transactional logic from VLAN objects It should be the driver's business to logically separate its VLAN offloading into a preparation and a commit phase, and some drivers don't need / can't do this. So remove the transactional shim from DSA and let drivers propagate errors directly from the .port_vlan_add callback. It would appear that the code has worse error handling now than it had before. DSA is the only in-kernel user of switchdev that offloads one switchdev object to more than one port: for every VLAN object offloaded to a user port, that VLAN is also offloaded to the CPU port. So the "prepare for user port -> check for errors -> prepare for CPU port -> check for errors -> commit for user port -> commit for CPU port" sequence appears to make more sense than the one we are using now: "offload to user port -> check for errors -> offload to CPU port -> check for errors", but it is really a compromise. In the new way, we can catch errors from the commit phase that we previously had to ignore. But we have our hands tied and cannot do any rollback now: if we add a VLAN on the CPU port and it fails, we can't do the rollback by simply deleting it from the user port, because the switchdev API is not so nice with us: it could have simply been there already, even with the same flags. So we don't even attempt to rollback anything on addition error, just leave whatever VLANs managed to get offloaded right where they are. This should not be a problem at all in practice. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Jiri Pirko <jiri@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-09 00:01:53 +00:00
return 0;
}
static int
mt7530_port_vlan_del(struct dsa_switch *ds, int port,
const struct switchdev_obj_port_vlan *vlan)
{
struct mt7530_hw_vlan_entry target_entry;
struct mt7530_priv *priv = ds->priv;
mutex_lock(&priv->reg_mutex);
net: switchdev: remove vid_begin -> vid_end range from VLAN objects The call path of a switchdev VLAN addition to the bridge looks something like this today: nbp_vlan_init | __br_vlan_set_default_pvid | | | | | br_afspec | | | | | | | v | | | br_process_vlan_info | | | | | | | v | | | br_vlan_info | | | / \ / | | / \ / | | / \ / | | / \ / v v v v v nbp_vlan_add br_vlan_add ------+ | ^ ^ | | | / | | | | / / / | \ br_vlan_get_master/ / v \ ^ / / br_vlan_add_existing \ | / / | \ | / / / \ | / / / \ | / / / \ | / / / v | | v / __vlan_add / / | / / | / v | / __vlan_vid_add | / \ | / v v v br_switchdev_port_vlan_add The ranges UAPI was introduced to the bridge in commit bdced7ef7838 ("bridge: support for multiple vlans and vlan ranges in setlink and dellink requests") (Jan 10 2015). But the VLAN ranges (parsed in br_afspec) have always been passed one by one, through struct bridge_vlan_info tmp_vinfo, to br_vlan_info. So the range never went too far in depth. Then Scott Feldman introduced the switchdev_port_bridge_setlink function in commit 47f8328bb1a4 ("switchdev: add new switchdev bridge setlink"). That marked the introduction of the SWITCHDEV_OBJ_PORT_VLAN, which made full use of the range. But switchdev_port_bridge_setlink was called like this: br_setlink -> br_afspec -> switchdev_port_bridge_setlink Basically, the switchdev and the bridge code were not tightly integrated. Then commit 41c498b9359e ("bridge: restore br_setlink back to original") came, and switchdev drivers were required to implement .ndo_bridge_setlink = switchdev_port_bridge_setlink for a while. In the meantime, commits such as 0944d6b5a2fa ("bridge: try switchdev op first in __vlan_vid_add/del") finally made switchdev penetrate the br_vlan_info() barrier and start to develop the call path we have today. But remember, br_vlan_info() still receives VLANs one by one. Then Arkadi Sharshevsky refactored the switchdev API in 2017 in commit 29ab586c3d83 ("net: switchdev: Remove bridge bypass support from switchdev") so that drivers would not implement .ndo_bridge_setlink any longer. The switchdev_port_bridge_setlink also got deleted. This refactoring removed the parallel bridge_setlink implementation from switchdev, and left the only switchdev VLAN objects to be the ones offloaded from __vlan_vid_add (basically RX filtering) and __vlan_add (the latter coming from commit 9c86ce2c1ae3 ("net: bridge: Notify about bridge VLANs")). That is to say, today the switchdev VLAN object ranges are not used in the kernel. Refactoring the above call path is a bit complicated, when the bridge VLAN call path is already a bit complicated. Let's go off and finish the job of commit 29ab586c3d83 by deleting the bogus iteration through the VLAN ranges from the drivers. Some aspects of this feature never made too much sense in the first place. For example, what is a range of VLANs all having the BRIDGE_VLAN_INFO_PVID flag supposed to mean, when a port can obviously have a single pvid? This particular configuration _is_ denied as of commit 6623c60dc28e ("bridge: vlan: enforce no pvid flag in vlan ranges"), but from an API perspective, the driver still has to play pretend, and only offload the vlan->vid_end as pvid. And the addition of a switchdev VLAN object can modify the flags of another, completely unrelated, switchdev VLAN object! (a VLAN that is PVID will invalidate the PVID flag from whatever other VLAN had previously been offloaded with switchdev and had that flag. Yet switchdev never notifies about that change, drivers are supposed to guess). Nonetheless, having a VLAN range in the API makes error handling look scarier than it really is - unwinding on errors and all of that. When in reality, no one really calls this API with more than one VLAN. It is all unnecessary complexity. And despite appearing pretentious (two-phase transactional model and all), the switchdev API is really sloppy because the VLAN addition and removal operations are not paired with one another (you can add a VLAN 100 times and delete it just once). The bridge notifies through switchdev of a VLAN addition not only when the flags of an existing VLAN change, but also when nothing changes. There are switchdev drivers out there who don't like adding a VLAN that has already been added, and those checks don't really belong at driver level. But the fact that the API contains ranges is yet another factor that prevents this from being addressed in the future. Of the existing switchdev pieces of hardware, it appears that only Mellanox Spectrum supports offloading more than one VLAN at a time, through mlxsw_sp_port_vlan_set. I have kept that code internal to the driver, because there is some more bookkeeping that makes use of it, but I deleted it from the switchdev API. But since the switchdev support for ranges has already been de facto deleted by a Mellanox employee and nobody noticed for 4 years, I'm going to assume it's not a biggie. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Ido Schimmel <idosch@nvidia.com> # switchdev and mlxsw Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de> # hellcreek Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-09 00:01:46 +00:00
mt7530_hw_vlan_entry_init(&target_entry, port, 0);
mt7530_hw_vlan_update(priv, vlan->vid, &target_entry,
mt7530_hw_vlan_del);
net: switchdev: remove vid_begin -> vid_end range from VLAN objects The call path of a switchdev VLAN addition to the bridge looks something like this today: nbp_vlan_init | __br_vlan_set_default_pvid | | | | | br_afspec | | | | | | | v | | | br_process_vlan_info | | | | | | | v | | | br_vlan_info | | | / \ / | | / \ / | | / \ / | | / \ / v v v v v nbp_vlan_add br_vlan_add ------+ | ^ ^ | | | / | | | | / / / | \ br_vlan_get_master/ / v \ ^ / / br_vlan_add_existing \ | / / | \ | / / / \ | / / / \ | / / / \ | / / / v | | v / __vlan_add / / | / / | / v | / __vlan_vid_add | / \ | / v v v br_switchdev_port_vlan_add The ranges UAPI was introduced to the bridge in commit bdced7ef7838 ("bridge: support for multiple vlans and vlan ranges in setlink and dellink requests") (Jan 10 2015). But the VLAN ranges (parsed in br_afspec) have always been passed one by one, through struct bridge_vlan_info tmp_vinfo, to br_vlan_info. So the range never went too far in depth. Then Scott Feldman introduced the switchdev_port_bridge_setlink function in commit 47f8328bb1a4 ("switchdev: add new switchdev bridge setlink"). That marked the introduction of the SWITCHDEV_OBJ_PORT_VLAN, which made full use of the range. But switchdev_port_bridge_setlink was called like this: br_setlink -> br_afspec -> switchdev_port_bridge_setlink Basically, the switchdev and the bridge code were not tightly integrated. Then commit 41c498b9359e ("bridge: restore br_setlink back to original") came, and switchdev drivers were required to implement .ndo_bridge_setlink = switchdev_port_bridge_setlink for a while. In the meantime, commits such as 0944d6b5a2fa ("bridge: try switchdev op first in __vlan_vid_add/del") finally made switchdev penetrate the br_vlan_info() barrier and start to develop the call path we have today. But remember, br_vlan_info() still receives VLANs one by one. Then Arkadi Sharshevsky refactored the switchdev API in 2017 in commit 29ab586c3d83 ("net: switchdev: Remove bridge bypass support from switchdev") so that drivers would not implement .ndo_bridge_setlink any longer. The switchdev_port_bridge_setlink also got deleted. This refactoring removed the parallel bridge_setlink implementation from switchdev, and left the only switchdev VLAN objects to be the ones offloaded from __vlan_vid_add (basically RX filtering) and __vlan_add (the latter coming from commit 9c86ce2c1ae3 ("net: bridge: Notify about bridge VLANs")). That is to say, today the switchdev VLAN object ranges are not used in the kernel. Refactoring the above call path is a bit complicated, when the bridge VLAN call path is already a bit complicated. Let's go off and finish the job of commit 29ab586c3d83 by deleting the bogus iteration through the VLAN ranges from the drivers. Some aspects of this feature never made too much sense in the first place. For example, what is a range of VLANs all having the BRIDGE_VLAN_INFO_PVID flag supposed to mean, when a port can obviously have a single pvid? This particular configuration _is_ denied as of commit 6623c60dc28e ("bridge: vlan: enforce no pvid flag in vlan ranges"), but from an API perspective, the driver still has to play pretend, and only offload the vlan->vid_end as pvid. And the addition of a switchdev VLAN object can modify the flags of another, completely unrelated, switchdev VLAN object! (a VLAN that is PVID will invalidate the PVID flag from whatever other VLAN had previously been offloaded with switchdev and had that flag. Yet switchdev never notifies about that change, drivers are supposed to guess). Nonetheless, having a VLAN range in the API makes error handling look scarier than it really is - unwinding on errors and all of that. When in reality, no one really calls this API with more than one VLAN. It is all unnecessary complexity. And despite appearing pretentious (two-phase transactional model and all), the switchdev API is really sloppy because the VLAN addition and removal operations are not paired with one another (you can add a VLAN 100 times and delete it just once). The bridge notifies through switchdev of a VLAN addition not only when the flags of an existing VLAN change, but also when nothing changes. There are switchdev drivers out there who don't like adding a VLAN that has already been added, and those checks don't really belong at driver level. But the fact that the API contains ranges is yet another factor that prevents this from being addressed in the future. Of the existing switchdev pieces of hardware, it appears that only Mellanox Spectrum supports offloading more than one VLAN at a time, through mlxsw_sp_port_vlan_set. I have kept that code internal to the driver, because there is some more bookkeeping that makes use of it, but I deleted it from the switchdev API. But since the switchdev support for ranges has already been de facto deleted by a Mellanox employee and nobody noticed for 4 years, I'm going to assume it's not a biggie. Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Reviewed-by: Ido Schimmel <idosch@nvidia.com> # switchdev and mlxsw Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de> # hellcreek Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-01-09 00:01:46 +00:00
/* PVID is being restored to the default whenever the PVID port
* is being removed from the VLAN.
*/
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
if (priv->ports[port].pvid == vlan->vid) {
priv->ports[port].pvid = G0_PORT_VID_DEF;
/* Only accept tagged frames if the port is VLAN-aware */
if (dsa_port_is_vlan_filtering(dsa_to_port(ds, port)))
mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK,
MT7530_VLAN_ACC_TAGGED);
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
mt7530_rmw(priv, MT7530_PPBV1_P(port), G0_PORT_VID_MASK,
G0_PORT_VID_DEF);
}
mutex_unlock(&priv->reg_mutex);
return 0;
}
static int mt753x_mirror_port_get(unsigned int id, u32 val)
{
return (id == ID_MT7531) ? MT7531_MIRROR_PORT_GET(val) :
MIRROR_PORT(val);
}
static int mt753x_mirror_port_set(unsigned int id, u32 val)
{
return (id == ID_MT7531) ? MT7531_MIRROR_PORT_SET(val) :
MIRROR_PORT(val);
}
static int mt753x_port_mirror_add(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror,
bool ingress, struct netlink_ext_ack *extack)
{
struct mt7530_priv *priv = ds->priv;
int monitor_port;
u32 val;
/* Check for existent entry */
if ((ingress ? priv->mirror_rx : priv->mirror_tx) & BIT(port))
return -EEXIST;
val = mt7530_read(priv, MT753X_MIRROR_REG(priv->id));
/* MT7530 only supports one monitor port */
monitor_port = mt753x_mirror_port_get(priv->id, val);
if (val & MT753X_MIRROR_EN(priv->id) &&
monitor_port != mirror->to_local_port)
return -EEXIST;
val |= MT753X_MIRROR_EN(priv->id);
val &= ~MT753X_MIRROR_MASK(priv->id);
val |= mt753x_mirror_port_set(priv->id, mirror->to_local_port);
mt7530_write(priv, MT753X_MIRROR_REG(priv->id), val);
val = mt7530_read(priv, MT7530_PCR_P(port));
if (ingress) {
val |= PORT_RX_MIR;
priv->mirror_rx |= BIT(port);
} else {
val |= PORT_TX_MIR;
priv->mirror_tx |= BIT(port);
}
mt7530_write(priv, MT7530_PCR_P(port), val);
return 0;
}
static void mt753x_port_mirror_del(struct dsa_switch *ds, int port,
struct dsa_mall_mirror_tc_entry *mirror)
{
struct mt7530_priv *priv = ds->priv;
u32 val;
val = mt7530_read(priv, MT7530_PCR_P(port));
if (mirror->ingress) {
val &= ~PORT_RX_MIR;
priv->mirror_rx &= ~BIT(port);
} else {
val &= ~PORT_TX_MIR;
priv->mirror_tx &= ~BIT(port);
}
mt7530_write(priv, MT7530_PCR_P(port), val);
if (!priv->mirror_rx && !priv->mirror_tx) {
val = mt7530_read(priv, MT753X_MIRROR_REG(priv->id));
val &= ~MT753X_MIRROR_EN(priv->id);
mt7530_write(priv, MT753X_MIRROR_REG(priv->id), val);
}
}
static enum dsa_tag_protocol
mtk_get_tag_protocol(struct dsa_switch *ds, int port,
enum dsa_tag_protocol mp)
{
return DSA_TAG_PROTO_MTK;
}
#ifdef CONFIG_GPIOLIB
static inline u32
mt7530_gpio_to_bit(unsigned int offset)
{
/* Map GPIO offset to register bit
* [ 2: 0] port 0 LED 0..2 as GPIO 0..2
* [ 6: 4] port 1 LED 0..2 as GPIO 3..5
* [10: 8] port 2 LED 0..2 as GPIO 6..8
* [14:12] port 3 LED 0..2 as GPIO 9..11
* [18:16] port 4 LED 0..2 as GPIO 12..14
*/
return BIT(offset + offset / 3);
}
static int
mt7530_gpio_get(struct gpio_chip *gc, unsigned int offset)
{
struct mt7530_priv *priv = gpiochip_get_data(gc);
u32 bit = mt7530_gpio_to_bit(offset);
return !!(mt7530_read(priv, MT7530_LED_GPIO_DATA) & bit);
}
static void
mt7530_gpio_set(struct gpio_chip *gc, unsigned int offset, int value)
{
struct mt7530_priv *priv = gpiochip_get_data(gc);
u32 bit = mt7530_gpio_to_bit(offset);
if (value)
mt7530_set(priv, MT7530_LED_GPIO_DATA, bit);
else
mt7530_clear(priv, MT7530_LED_GPIO_DATA, bit);
}
static int
mt7530_gpio_get_direction(struct gpio_chip *gc, unsigned int offset)
{
struct mt7530_priv *priv = gpiochip_get_data(gc);
u32 bit = mt7530_gpio_to_bit(offset);
return (mt7530_read(priv, MT7530_LED_GPIO_DIR) & bit) ?
GPIO_LINE_DIRECTION_OUT : GPIO_LINE_DIRECTION_IN;
}
static int
mt7530_gpio_direction_input(struct gpio_chip *gc, unsigned int offset)
{
struct mt7530_priv *priv = gpiochip_get_data(gc);
u32 bit = mt7530_gpio_to_bit(offset);
mt7530_clear(priv, MT7530_LED_GPIO_OE, bit);
mt7530_clear(priv, MT7530_LED_GPIO_DIR, bit);
return 0;
}
static int
mt7530_gpio_direction_output(struct gpio_chip *gc, unsigned int offset, int value)
{
struct mt7530_priv *priv = gpiochip_get_data(gc);
u32 bit = mt7530_gpio_to_bit(offset);
mt7530_set(priv, MT7530_LED_GPIO_DIR, bit);
if (value)
mt7530_set(priv, MT7530_LED_GPIO_DATA, bit);
else
mt7530_clear(priv, MT7530_LED_GPIO_DATA, bit);
mt7530_set(priv, MT7530_LED_GPIO_OE, bit);
return 0;
}
static int
mt7530_setup_gpio(struct mt7530_priv *priv)
{
struct device *dev = priv->dev;
struct gpio_chip *gc;
gc = devm_kzalloc(dev, sizeof(*gc), GFP_KERNEL);
if (!gc)
return -ENOMEM;
mt7530_write(priv, MT7530_LED_GPIO_OE, 0);
mt7530_write(priv, MT7530_LED_GPIO_DIR, 0);
mt7530_write(priv, MT7530_LED_IO_MODE, 0);
gc->label = "mt7530";
gc->parent = dev;
gc->owner = THIS_MODULE;
gc->get_direction = mt7530_gpio_get_direction;
gc->direction_input = mt7530_gpio_direction_input;
gc->direction_output = mt7530_gpio_direction_output;
gc->get = mt7530_gpio_get;
gc->set = mt7530_gpio_set;
gc->base = -1;
gc->ngpio = 15;
gc->can_sleep = true;
return devm_gpiochip_add_data(dev, gc, priv);
}
#endif /* CONFIG_GPIOLIB */
static irqreturn_t
mt7530_irq_thread_fn(int irq, void *dev_id)
{
struct mt7530_priv *priv = dev_id;
bool handled = false;
u32 val;
int p;
mt7530_mutex_lock(priv);
val = mt7530_mii_read(priv, MT7530_SYS_INT_STS);
mt7530_mii_write(priv, MT7530_SYS_INT_STS, val);
mt7530_mutex_unlock(priv);
for (p = 0; p < MT7530_NUM_PHYS; p++) {
if (BIT(p) & val) {
unsigned int irq;
irq = irq_find_mapping(priv->irq_domain, p);
handle_nested_irq(irq);
handled = true;
}
}
return IRQ_RETVAL(handled);
}
static void
mt7530_irq_mask(struct irq_data *d)
{
struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
priv->irq_enable &= ~BIT(d->hwirq);
}
static void
mt7530_irq_unmask(struct irq_data *d)
{
struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
priv->irq_enable |= BIT(d->hwirq);
}
static void
mt7530_irq_bus_lock(struct irq_data *d)
{
struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
mt7530_mutex_lock(priv);
}
static void
mt7530_irq_bus_sync_unlock(struct irq_data *d)
{
struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
mt7530_mii_write(priv, MT7530_SYS_INT_EN, priv->irq_enable);
mt7530_mutex_unlock(priv);
}
static struct irq_chip mt7530_irq_chip = {
.name = KBUILD_MODNAME,
.irq_mask = mt7530_irq_mask,
.irq_unmask = mt7530_irq_unmask,
.irq_bus_lock = mt7530_irq_bus_lock,
.irq_bus_sync_unlock = mt7530_irq_bus_sync_unlock,
};
static int
mt7530_irq_map(struct irq_domain *domain, unsigned int irq,
irq_hw_number_t hwirq)
{
irq_set_chip_data(irq, domain->host_data);
irq_set_chip_and_handler(irq, &mt7530_irq_chip, handle_simple_irq);
irq_set_nested_thread(irq, true);
irq_set_noprobe(irq);
return 0;
}
static const struct irq_domain_ops mt7530_irq_domain_ops = {
.map = mt7530_irq_map,
.xlate = irq_domain_xlate_onecell,
};
static void
mt7988_irq_mask(struct irq_data *d)
{
struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
priv->irq_enable &= ~BIT(d->hwirq);
mt7530_mii_write(priv, MT7530_SYS_INT_EN, priv->irq_enable);
}
static void
mt7988_irq_unmask(struct irq_data *d)
{
struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
priv->irq_enable |= BIT(d->hwirq);
mt7530_mii_write(priv, MT7530_SYS_INT_EN, priv->irq_enable);
}
static struct irq_chip mt7988_irq_chip = {
.name = KBUILD_MODNAME,
.irq_mask = mt7988_irq_mask,
.irq_unmask = mt7988_irq_unmask,
};
static int
mt7988_irq_map(struct irq_domain *domain, unsigned int irq,
irq_hw_number_t hwirq)
{
irq_set_chip_data(irq, domain->host_data);
irq_set_chip_and_handler(irq, &mt7988_irq_chip, handle_simple_irq);
irq_set_nested_thread(irq, true);
irq_set_noprobe(irq);
return 0;
}
static const struct irq_domain_ops mt7988_irq_domain_ops = {
.map = mt7988_irq_map,
.xlate = irq_domain_xlate_onecell,
};
static void
mt7530_setup_mdio_irq(struct mt7530_priv *priv)
{
struct dsa_switch *ds = priv->ds;
int p;
for (p = 0; p < MT7530_NUM_PHYS; p++) {
if (BIT(p) & ds->phys_mii_mask) {
unsigned int irq;
irq = irq_create_mapping(priv->irq_domain, p);
ds->user_mii_bus->irq[p] = irq;
}
}
}
static int
mt7530_setup_irq(struct mt7530_priv *priv)
{
struct device *dev = priv->dev;
struct device_node *np = dev->of_node;
int ret;
if (!of_property_read_bool(np, "interrupt-controller")) {
dev_info(dev, "no interrupt support\n");
return 0;
}
priv->irq = of_irq_get(np, 0);
if (priv->irq <= 0) {
dev_err(dev, "failed to get parent IRQ: %d\n", priv->irq);
return priv->irq ? : -EINVAL;
}
if (priv->id == ID_MT7988)
priv->irq_domain = irq_domain_add_linear(np, MT7530_NUM_PHYS,
&mt7988_irq_domain_ops,
priv);
else
priv->irq_domain = irq_domain_add_linear(np, MT7530_NUM_PHYS,
&mt7530_irq_domain_ops,
priv);
if (!priv->irq_domain) {
dev_err(dev, "failed to create IRQ domain\n");
return -ENOMEM;
}
/* This register must be set for MT7530 to properly fire interrupts */
if (priv->id != ID_MT7531)
mt7530_set(priv, MT7530_TOP_SIG_CTRL, TOP_SIG_CTRL_NORMAL);
ret = request_threaded_irq(priv->irq, NULL, mt7530_irq_thread_fn,
IRQF_ONESHOT, KBUILD_MODNAME, priv);
if (ret) {
irq_domain_remove(priv->irq_domain);
dev_err(dev, "failed to request IRQ: %d\n", ret);
return ret;
}
return 0;
}
static void
mt7530_free_mdio_irq(struct mt7530_priv *priv)
{
int p;
for (p = 0; p < MT7530_NUM_PHYS; p++) {
if (BIT(p) & priv->ds->phys_mii_mask) {
unsigned int irq;
irq = irq_find_mapping(priv->irq_domain, p);
irq_dispose_mapping(irq);
}
}
}
static void
mt7530_free_irq_common(struct mt7530_priv *priv)
{
free_irq(priv->irq, priv);
irq_domain_remove(priv->irq_domain);
}
static void
mt7530_free_irq(struct mt7530_priv *priv)
{
mt7530_free_mdio_irq(priv);
mt7530_free_irq_common(priv);
}
static int
mt7530_setup_mdio(struct mt7530_priv *priv)
{
struct dsa_switch *ds = priv->ds;
struct device *dev = priv->dev;
struct mii_bus *bus;
static int idx;
int ret;
bus = devm_mdiobus_alloc(dev);
if (!bus)
return -ENOMEM;
ds->user_mii_bus = bus;
bus->priv = priv;
bus->name = KBUILD_MODNAME "-mii";
snprintf(bus->id, MII_BUS_ID_SIZE, KBUILD_MODNAME "-%d", idx++);
bus->read = mt753x_phy_read_c22;
bus->write = mt753x_phy_write_c22;
bus->read_c45 = mt753x_phy_read_c45;
bus->write_c45 = mt753x_phy_write_c45;
bus->parent = dev;
bus->phy_mask = ~ds->phys_mii_mask;
if (priv->irq)
mt7530_setup_mdio_irq(priv);
ret = devm_mdiobus_register(dev, bus);
if (ret) {
dev_err(dev, "failed to register MDIO bus: %d\n", ret);
if (priv->irq)
mt7530_free_mdio_irq(priv);
}
return ret;
}
static int
mt7530_setup(struct dsa_switch *ds)
{
struct mt7530_priv *priv = ds->priv;
struct device_node *dn = NULL;
struct device_node *phy_node;
struct device_node *mac_np;
struct mt7530_dummy_poll p;
phy_interface_t interface;
struct dsa_port *cpu_dp;
u32 id, val;
int ret, i;
/* The parent node of conduit netdev which holds the common system
* controller also is the container for two GMACs nodes representing
* as two netdev instances.
*/
dsa_switch_for_each_cpu_port(cpu_dp, ds) {
dn = cpu_dp->conduit->dev.of_node->parent;
/* It doesn't matter which CPU port is found first,
* their conduits should share the same parent OF node
*/
break;
}
if (!dn) {
dev_err(ds->dev, "parent OF node of DSA conduit not found");
return -EINVAL;
}
ds->assisted_learning_on_cpu_port = true;
ds->mtu_enforcement_ingress = true;
if (priv->id == ID_MT7530) {
regulator_set_voltage(priv->core_pwr, 1000000, 1000000);
ret = regulator_enable(priv->core_pwr);
if (ret < 0) {
dev_err(priv->dev,
"Failed to enable core power: %d\n", ret);
return ret;
}
regulator_set_voltage(priv->io_pwr, 3300000, 3300000);
ret = regulator_enable(priv->io_pwr);
if (ret < 0) {
dev_err(priv->dev, "Failed to enable io pwr: %d\n",
ret);
return ret;
}
}
/* Reset whole chip through gpio pin or memory-mapped registers for
* different type of hardware
*/
if (priv->mcm) {
reset_control_assert(priv->rstc);
net: dsa: mt7530: prevent possible incorrect XTAL frequency selection [ Upstream commit f490c492e946d8ffbe65ad4efc66de3c5ede30a4 ] On MT7530, the HT_XTAL_FSEL field of the HWTRAP register stores a 2-bit value that represents the frequency of the crystal oscillator connected to the switch IC. The field is populated by the state of the ESW_P4_LED_0 and ESW_P4_LED_0 pins, which is done right after reset is deasserted. ESW_P4_LED_0 ESW_P3_LED_0 Frequency ----------------------------------------- 0 0 Reserved 0 1 20MHz 1 0 40MHz 1 1 25MHz On MT7531, the XTAL25 bit of the STRAP register stores this. The LAN0LED0 pin is used to populate the bit. 25MHz when the pin is high, 40MHz when it's low. These pins are also used with LEDs, therefore, their state can be set to something other than the bootstrapping configuration. For example, a link may be established on port 3 before the DSA subdriver takes control of the switch which would set ESW_P3_LED_0 to high. Currently on mt7530_setup() and mt7531_setup(), 1000 - 1100 usec delay is described between reset assertion and deassertion. Some switch ICs in real life conditions cannot always have these pins set back to the bootstrapping configuration before reset deassertion in this amount of delay. This causes wrong crystal frequency to be selected which puts the switch in a nonfunctional state after reset deassertion. The tests below are conducted on an MT7530 with a 40MHz crystal oscillator by Justin Swartz. With a cable from an active peer connected to port 3 before reset, an incorrect crystal frequency (0b11 = 25MHz) is selected: [1] [3] [5] : : : _____________________________ __________________ ESW_P4_LED_0 |_______| _____________________________ ESW_P3_LED_0 |__________________________ : : : : : : [4]...: : : [2]................: [1] Reset is asserted. [2] Period of 1000 - 1100 usec. [3] Reset is deasserted. [4] Period of 315 usec. HWTRAP register is populated with incorrect XTAL frequency. [5] Signals reflect the bootstrapped configuration. Increase the delay between reset_control_assert() and reset_control_deassert(), and gpiod_set_value_cansleep(priv->reset, 0) and gpiod_set_value_cansleep(priv->reset, 1) to 5000 - 5100 usec. This amount ensures a higher possibility that the switch IC will have these pins back to the bootstrapping configuration before reset deassertion. With a cable from an active peer connected to port 3 before reset, the correct crystal frequency (0b10 = 40MHz) is selected: [1] [2-1] [3] [5] : : : : _____________________________ __________________ ESW_P4_LED_0 |_______| ___________________ _______ ESW_P3_LED_0 |_________| |__________________ : : : : : : [2-2]...: [4]...: [2]................: [1] Reset is asserted. [2] Period of 5000 - 5100 usec. [2-1] ESW_P3_LED_0 goes low. [2-2] Remaining period of 5000 - 5100 usec. [3] Reset is deasserted. [4] Period of 310 usec. HWTRAP register is populated with bootstrapped XTAL frequency. [5] Signals reflect the bootstrapped configuration. ESW_P3_LED_0 low period before reset deassertion: 5000 usec - 5100 usec TEST RESET HOLD # (usec) --------------------- 1 5410 2 5440 3 4375 4 5490 5 5475 6 4335 7 4370 8 5435 9 4205 10 4335 11 3750 12 3170 13 4395 14 4375 15 3515 16 4335 17 4220 18 4175 19 4175 20 4350 Min 3170 Max 5490 Median 4342.500 Avg 4466.500 Revert commit 2920dd92b980 ("net: dsa: mt7530: disable LEDs before reset"). Changing the state of pins via reset assertion is simpler and more efficient than doing so by setting the LED controller off. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Fixes: c288575f7810 ("net: dsa: mt7530: Add the support of MT7531 switch") Co-developed-by: Justin Swartz <justin.swartz@risingedge.co.za> Signed-off-by: Justin Swartz <justin.swartz@risingedge.co.za> Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-03-14 09:28:35 +00:00
usleep_range(5000, 5100);
reset_control_deassert(priv->rstc);
} else {
gpiod_set_value_cansleep(priv->reset, 0);
net: dsa: mt7530: prevent possible incorrect XTAL frequency selection [ Upstream commit f490c492e946d8ffbe65ad4efc66de3c5ede30a4 ] On MT7530, the HT_XTAL_FSEL field of the HWTRAP register stores a 2-bit value that represents the frequency of the crystal oscillator connected to the switch IC. The field is populated by the state of the ESW_P4_LED_0 and ESW_P4_LED_0 pins, which is done right after reset is deasserted. ESW_P4_LED_0 ESW_P3_LED_0 Frequency ----------------------------------------- 0 0 Reserved 0 1 20MHz 1 0 40MHz 1 1 25MHz On MT7531, the XTAL25 bit of the STRAP register stores this. The LAN0LED0 pin is used to populate the bit. 25MHz when the pin is high, 40MHz when it's low. These pins are also used with LEDs, therefore, their state can be set to something other than the bootstrapping configuration. For example, a link may be established on port 3 before the DSA subdriver takes control of the switch which would set ESW_P3_LED_0 to high. Currently on mt7530_setup() and mt7531_setup(), 1000 - 1100 usec delay is described between reset assertion and deassertion. Some switch ICs in real life conditions cannot always have these pins set back to the bootstrapping configuration before reset deassertion in this amount of delay. This causes wrong crystal frequency to be selected which puts the switch in a nonfunctional state after reset deassertion. The tests below are conducted on an MT7530 with a 40MHz crystal oscillator by Justin Swartz. With a cable from an active peer connected to port 3 before reset, an incorrect crystal frequency (0b11 = 25MHz) is selected: [1] [3] [5] : : : _____________________________ __________________ ESW_P4_LED_0 |_______| _____________________________ ESW_P3_LED_0 |__________________________ : : : : : : [4]...: : : [2]................: [1] Reset is asserted. [2] Period of 1000 - 1100 usec. [3] Reset is deasserted. [4] Period of 315 usec. HWTRAP register is populated with incorrect XTAL frequency. [5] Signals reflect the bootstrapped configuration. Increase the delay between reset_control_assert() and reset_control_deassert(), and gpiod_set_value_cansleep(priv->reset, 0) and gpiod_set_value_cansleep(priv->reset, 1) to 5000 - 5100 usec. This amount ensures a higher possibility that the switch IC will have these pins back to the bootstrapping configuration before reset deassertion. With a cable from an active peer connected to port 3 before reset, the correct crystal frequency (0b10 = 40MHz) is selected: [1] [2-1] [3] [5] : : : : _____________________________ __________________ ESW_P4_LED_0 |_______| ___________________ _______ ESW_P3_LED_0 |_________| |__________________ : : : : : : [2-2]...: [4]...: [2]................: [1] Reset is asserted. [2] Period of 5000 - 5100 usec. [2-1] ESW_P3_LED_0 goes low. [2-2] Remaining period of 5000 - 5100 usec. [3] Reset is deasserted. [4] Period of 310 usec. HWTRAP register is populated with bootstrapped XTAL frequency. [5] Signals reflect the bootstrapped configuration. ESW_P3_LED_0 low period before reset deassertion: 5000 usec - 5100 usec TEST RESET HOLD # (usec) --------------------- 1 5410 2 5440 3 4375 4 5490 5 5475 6 4335 7 4370 8 5435 9 4205 10 4335 11 3750 12 3170 13 4395 14 4375 15 3515 16 4335 17 4220 18 4175 19 4175 20 4350 Min 3170 Max 5490 Median 4342.500 Avg 4466.500 Revert commit 2920dd92b980 ("net: dsa: mt7530: disable LEDs before reset"). Changing the state of pins via reset assertion is simpler and more efficient than doing so by setting the LED controller off. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Fixes: c288575f7810 ("net: dsa: mt7530: Add the support of MT7531 switch") Co-developed-by: Justin Swartz <justin.swartz@risingedge.co.za> Signed-off-by: Justin Swartz <justin.swartz@risingedge.co.za> Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-03-14 09:28:35 +00:00
usleep_range(5000, 5100);
gpiod_set_value_cansleep(priv->reset, 1);
}
/* Waiting for MT7530 got to stable */
INIT_MT7530_DUMMY_POLL(&p, priv, MT7530_HWTRAP);
ret = readx_poll_timeout(_mt7530_read, &p, val, val != 0,
20, 1000000);
if (ret < 0) {
dev_err(priv->dev, "reset timeout\n");
return ret;
}
id = mt7530_read(priv, MT7530_CREV);
id >>= CHIP_NAME_SHIFT;
if (id != MT7530_ID) {
dev_err(priv->dev, "chip %x can't be supported\n", id);
return -ENODEV;
}
/* Reset the switch through internal reset */
mt7530_write(priv, MT7530_SYS_CTRL,
SYS_CTRL_PHY_RST | SYS_CTRL_SW_RST |
SYS_CTRL_REG_RST);
net: dsa: mt7530: permit port 5 to work without port 6 on MT7621 SoC The MT7530 switch from the MT7621 SoC has 2 ports which can be set up as internal: port 5 and 6. Arınç reports that the GMAC1 attached to port 5 receives corrupted frames, unless port 6 (attached to GMAC0) has been brought up by the driver. This is true regardless of whether port 5 is used as a user port or as a CPU port (carrying DSA tags). Offline debugging (blind for me) which began in the linked thread showed experimentally that the configuration done by the driver for port 6 contains a step which is needed by port 5 as well - the write to CORE_GSWPLL_GRP2 (note that I've no idea as to what it does, apart from the comment "Set core clock into 500Mhz"). Prints put by Arınç show that the reset value of CORE_GSWPLL_GRP2 is RG_GSWPLL_POSDIV_500M(1) | RG_GSWPLL_FBKDIV_500M(40) (0x128), both on the MCM MT7530 from the MT7621 SoC, as well as on the standalone MT7530 from MT7623NI Bananapi BPI-R2. Apparently, port 5 on the standalone MT7530 can work under both values of the register, while on the MT7621 SoC it cannot. The call path that triggers the register write is: mt753x_phylink_mac_config() for port 6 -> mt753x_pad_setup() -> mt7530_pad_clk_setup() so this fully explains the behavior noticed by Arınç, that bringing port 6 up is necessary. The simplest fix for the problem is to extract the register writes which are needed for both port 5 and 6 into a common mt7530_pll_setup() function, which is called at mt7530_setup() time, immediately after switch reset. We can argue that this mirrors the code layout introduced in mt7531_setup() by commit 42bc4fafe359 ("net: mt7531: only do PLL once after the reset"), in that the PLL setup has the exact same positioning, and further work to consolidate the separate setup() functions is not hindered. Testing confirms that: - the slight reordering of writes to MT7530_P6ECR and to CORE_GSWPLL_GRP1 / CORE_GSWPLL_GRP2 introduced by this change does not appear to cause problems for the operation of port 6 on MT7621 and on MT7623 (where port 5 also always worked) - packets sent through port 5 are not corrupted anymore, regardless of whether port 6 is enabled by phylink or not (or even present in the device tree) My algorithm for determining the Fixes: tag is as follows. Testing shows that some logic from mt7530_pad_clk_setup() is needed even for port 5. Prior to commit ca366d6c889b ("net: dsa: mt7530: Convert to PHYLINK API"), a call did exist for all phy_is_pseudo_fixed_link() ports - so port 5 included. That commit replaced it with a temporary "Port 5 is not supported!" comment, and the following commit 38f790a80560 ("net: dsa: mt7530: Add support for port 5") replaced that comment with a configuration procedure in mt7530_setup_port5() which was insufficient for port 5 to work. I'm laying the blame on the patch that claimed support for port 5, although one would have also needed the change from commit c3b8e07909db ("net: dsa: mt7530: setup core clock even in TRGMII mode") for the write to be performed completely independently from port 6's configuration. Thanks go to Arınç for describing the problem, for debugging and for testing. Reported-by: Arınç ÜNAL <arinc.unal@arinc9.com> Link: https://lore.kernel.org/netdev/f297c2c4-6e7c-57ac-2394-f6025d309b9d@arinc9.com/ Fixes: 38f790a80560 ("net: dsa: mt7530: Add support for port 5") Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Arınç ÜNAL <arinc.unal@arinc9.com> Reviewed-by: Simon Horman <simon.horman@corigine.com> Link: https://lore.kernel.org/r/20230307155411.868573-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2023-03-07 15:54:11 +00:00
mt7530_pll_setup(priv);
/* Lower Tx driving for TRGMII path */
for (i = 0; i < NUM_TRGMII_CTRL; i++)
mt7530_write(priv, MT7530_TRGMII_TD_ODT(i),
TD_DM_DRVP(8) | TD_DM_DRVN(8));
for (i = 0; i < NUM_TRGMII_CTRL; i++)
mt7530_rmw(priv, MT7530_TRGMII_RD(i),
RD_TAP_MASK, RD_TAP(16));
/* Enable port 6 */
val = mt7530_read(priv, MT7530_MHWTRAP);
val &= ~MHWTRAP_P6_DIS & ~MHWTRAP_PHY_ACCESS;
val |= MHWTRAP_MANUAL;
mt7530_write(priv, MT7530_MHWTRAP, val);
priv->p6_interface = PHY_INTERFACE_MODE_NA;
mt753x_trap_frames(priv);
/* Enable and reset MIB counters */
mt7530_mib_reset(ds);
for (i = 0; i < MT7530_NUM_PORTS; i++) {
/* Disable forwarding by default on all ports */
mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
PCR_MATRIX_CLR);
/* Disable learning by default on all ports */
mt7530_set(priv, MT7530_PSC_P(i), SA_DIS);
if (dsa_is_cpu_port(ds, i)) {
ret = mt753x_cpu_port_enable(ds, i);
if (ret)
return ret;
} else {
mt7530_port_disable(ds, i);
net: dsa: mt7530: use independent VLAN learning on VLAN-unaware bridges Consider the following bridge configuration, where bond0 is not offloaded: +-- br0 --+ / / | \ / / | \ / | | bond0 / | | / \ swp0 swp1 swp2 swp3 swp4 . . . . . . A B C Ideally, when the switch receives a packet from swp3 or swp4, it should forward the packet to the CPU, according to the port matrix and unknown unicast flood settings. But packet loss will happen if the destination address is at one of the offloaded ports (swp0~2). For example, when client C sends a packet to A, the FDB lookup will indicate that it should be forwarded to swp0, but the port matrix of swp3 and swp4 is configured to only allow the CPU to be its destination, so it is dropped. However, this issue does not happen if the bridge is VLAN-aware. That is because VLAN-aware bridges use independent VLAN learning, i.e. use VID for FDB lookup, on offloaded ports. As swp3 and swp4 are not offloaded, shared VLAN learning with default filter ID of 0 is used instead. So the lookup for A with filter ID 0 never hits and the packet can be forwarded to the CPU. In the current code, only two combinations were used to toggle user ports' VLAN awareness: one is PCR.PORT_VLAN set to port matrix mode with PVC.VLAN_ATTR set to transparent port, the other is PCR.PORT_VLAN set to security mode with PVC.VLAN_ATTR set to user port. It turns out that only PVC.VLAN_ATTR contributes to VLAN awareness, and port matrix mode just skips the VLAN table lookup. The reference manual is somehow misleading when describing PORT_VLAN modes. It states that PORT_MEM (VLAN port member) is used for destination if the VLAN table lookup hits, but actually **PORT_MEM & PORT_MATRIX** (bitwise AND of VLAN port member and port matrix) is used instead, which means we can have two or more separate VLAN-aware bridges with the same PVID and traffic won't leak between them. Therefore, to solve this, enable independent VLAN learning with PVID 0 on VLAN-unaware bridges, by setting their PCR.PORT_VLAN to fallback mode, while leaving standalone ports in port matrix mode. The CPU port is always set to fallback mode to serve those bridges. During testing, it is found that FDB lookup with filter ID of 0 will also hit entries with VID 0 even with independent VLAN learning. To avoid that, install all VLANs with filter ID of 1. Signed-off-by: DENG Qingfang <dqfext@gmail.com> Reviewed-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-08-03 16:04:02 +00:00
/* Set default PVID to 0 on all user ports */
mt7530_rmw(priv, MT7530_PPBV1_P(i), G0_PORT_VID_MASK,
G0_PORT_VID_DEF);
}
/* Enable consistent egress tag */
mt7530_rmw(priv, MT7530_PVC_P(i), PVC_EG_TAG_MASK,
PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
}
/* Setup VLAN ID 0 for VLAN-unaware bridges */
ret = mt7530_setup_vlan0(priv);
if (ret)
return ret;
/* Setup port 5 */
priv->p5_intf_sel = P5_DISABLED;
interface = PHY_INTERFACE_MODE_NA;
if (!dsa_is_unused_port(ds, 5)) {
priv->p5_intf_sel = P5_INTF_SEL_GMAC5;
ret = of_get_phy_mode(dsa_to_port(ds, 5)->dn, &interface);
if (ret && ret != -ENODEV)
return ret;
} else {
/* Scan the ethernet nodes. look for GMAC1, lookup used phy */
for_each_child_of_node(dn, mac_np) {
if (!of_device_is_compatible(mac_np,
"mediatek,eth-mac"))
continue;
ret = of_property_read_u32(mac_np, "reg", &id);
if (ret < 0 || id != 1)
continue;
phy_node = of_parse_phandle(mac_np, "phy-handle", 0);
if (!phy_node)
continue;
if (phy_node->parent == priv->dev->of_node->parent) {
ret = of_get_phy_mode(mac_np, &interface);
if (ret && ret != -ENODEV) {
of_node_put(mac_np);
of_node_put(phy_node);
return ret;
}
id = of_mdio_parse_addr(ds->dev, phy_node);
if (id == 0)
priv->p5_intf_sel = P5_INTF_SEL_PHY_P0;
if (id == 4)
priv->p5_intf_sel = P5_INTF_SEL_PHY_P4;
}
of_node_put(mac_np);
of_node_put(phy_node);
break;
}
}
#ifdef CONFIG_GPIOLIB
if (of_property_read_bool(priv->dev->of_node, "gpio-controller")) {
ret = mt7530_setup_gpio(priv);
if (ret)
return ret;
}
#endif /* CONFIG_GPIOLIB */
mt7530_setup_port5(ds, interface);
/* Flush the FDB table */
ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL);
if (ret < 0)
return ret;
return 0;
}
static int
mt7531_setup_common(struct dsa_switch *ds)
{
struct mt7530_priv *priv = ds->priv;
int ret, i;
mt753x_trap_frames(priv);
/* Enable and reset MIB counters */
mt7530_mib_reset(ds);
net: dsa: mt7530: fix network connectivity with multiple CPU ports On mt753x_cpu_port_enable() there's code that enables flooding for the CPU port only. Since mt753x_cpu_port_enable() runs twice when both CPU ports are enabled, port 6 becomes the only port to forward the frames to. But port 5 is the active port, so no frames received from the user ports will be forwarded to port 5 which breaks network connectivity. Every bit of the BC_FFP, UNM_FFP, and UNU_FFP bits represents a port. Fix this issue by setting the bit that corresponds to the CPU port without overwriting the other bits. Clear the bits beforehand only for the MT7531 switch. According to the documents MT7621 Giga Switch Programming Guide v0.3 and MT7531 Reference Manual for Development Board v1.0, after reset, the BC_FFP, UNM_FFP, and UNU_FFP bits are set to 1 for MT7531, 0 for MT7530. The commit 5e5502e012b8 ("net: dsa: mt7530: fix roaming from DSA user ports") silently changed the method to set the bits on the MT7530_MFC. Instead of clearing the relevant bits before mt7530_cpu_port_enable() which runs under a for loop, the commit started doing it on mt7530_cpu_port_enable(). Back then, this didn't really matter as only a single CPU port could be used since the CPU port number was hardcoded. The driver was later changed with commit 1f9a6abecf53 ("net: dsa: mt7530: get cpu-port via dp->cpu_dp instead of constant") to retrieve the CPU port via dp->cpu_dp. With that, this silent change became an issue for when using multiple CPU ports. Fixes: 5e5502e012b8 ("net: dsa: mt7530: fix roaming from DSA user ports") Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-05-02 21:09:47 +00:00
/* Disable flooding on all ports */
mt7530_clear(priv, MT7530_MFC, BC_FFP_MASK | UNM_FFP_MASK |
UNU_FFP_MASK);
for (i = 0; i < MT7530_NUM_PORTS; i++) {
/* Disable forwarding by default on all ports */
mt7530_rmw(priv, MT7530_PCR_P(i), PCR_MATRIX_MASK,
PCR_MATRIX_CLR);
/* Disable learning by default on all ports */
mt7530_set(priv, MT7530_PSC_P(i), SA_DIS);
mt7530_set(priv, MT7531_DBG_CNT(i), MT7531_DIS_CLR);
if (dsa_is_cpu_port(ds, i)) {
ret = mt753x_cpu_port_enable(ds, i);
if (ret)
return ret;
} else {
mt7530_port_disable(ds, i);
/* Set default PVID to 0 on all user ports */
mt7530_rmw(priv, MT7530_PPBV1_P(i), G0_PORT_VID_MASK,
G0_PORT_VID_DEF);
}
/* Enable consistent egress tag */
mt7530_rmw(priv, MT7530_PVC_P(i), PVC_EG_TAG_MASK,
PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT));
}
/* Flush the FDB table */
ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL);
if (ret < 0)
return ret;
return 0;
}
static int
mt7531_setup(struct dsa_switch *ds)
{
struct mt7530_priv *priv = ds->priv;
struct mt7530_dummy_poll p;
u32 val, id;
int ret, i;
/* Reset whole chip through gpio pin or memory-mapped registers for
* different type of hardware
*/
if (priv->mcm) {
reset_control_assert(priv->rstc);
net: dsa: mt7530: prevent possible incorrect XTAL frequency selection [ Upstream commit f490c492e946d8ffbe65ad4efc66de3c5ede30a4 ] On MT7530, the HT_XTAL_FSEL field of the HWTRAP register stores a 2-bit value that represents the frequency of the crystal oscillator connected to the switch IC. The field is populated by the state of the ESW_P4_LED_0 and ESW_P4_LED_0 pins, which is done right after reset is deasserted. ESW_P4_LED_0 ESW_P3_LED_0 Frequency ----------------------------------------- 0 0 Reserved 0 1 20MHz 1 0 40MHz 1 1 25MHz On MT7531, the XTAL25 bit of the STRAP register stores this. The LAN0LED0 pin is used to populate the bit. 25MHz when the pin is high, 40MHz when it's low. These pins are also used with LEDs, therefore, their state can be set to something other than the bootstrapping configuration. For example, a link may be established on port 3 before the DSA subdriver takes control of the switch which would set ESW_P3_LED_0 to high. Currently on mt7530_setup() and mt7531_setup(), 1000 - 1100 usec delay is described between reset assertion and deassertion. Some switch ICs in real life conditions cannot always have these pins set back to the bootstrapping configuration before reset deassertion in this amount of delay. This causes wrong crystal frequency to be selected which puts the switch in a nonfunctional state after reset deassertion. The tests below are conducted on an MT7530 with a 40MHz crystal oscillator by Justin Swartz. With a cable from an active peer connected to port 3 before reset, an incorrect crystal frequency (0b11 = 25MHz) is selected: [1] [3] [5] : : : _____________________________ __________________ ESW_P4_LED_0 |_______| _____________________________ ESW_P3_LED_0 |__________________________ : : : : : : [4]...: : : [2]................: [1] Reset is asserted. [2] Period of 1000 - 1100 usec. [3] Reset is deasserted. [4] Period of 315 usec. HWTRAP register is populated with incorrect XTAL frequency. [5] Signals reflect the bootstrapped configuration. Increase the delay between reset_control_assert() and reset_control_deassert(), and gpiod_set_value_cansleep(priv->reset, 0) and gpiod_set_value_cansleep(priv->reset, 1) to 5000 - 5100 usec. This amount ensures a higher possibility that the switch IC will have these pins back to the bootstrapping configuration before reset deassertion. With a cable from an active peer connected to port 3 before reset, the correct crystal frequency (0b10 = 40MHz) is selected: [1] [2-1] [3] [5] : : : : _____________________________ __________________ ESW_P4_LED_0 |_______| ___________________ _______ ESW_P3_LED_0 |_________| |__________________ : : : : : : [2-2]...: [4]...: [2]................: [1] Reset is asserted. [2] Period of 5000 - 5100 usec. [2-1] ESW_P3_LED_0 goes low. [2-2] Remaining period of 5000 - 5100 usec. [3] Reset is deasserted. [4] Period of 310 usec. HWTRAP register is populated with bootstrapped XTAL frequency. [5] Signals reflect the bootstrapped configuration. ESW_P3_LED_0 low period before reset deassertion: 5000 usec - 5100 usec TEST RESET HOLD # (usec) --------------------- 1 5410 2 5440 3 4375 4 5490 5 5475 6 4335 7 4370 8 5435 9 4205 10 4335 11 3750 12 3170 13 4395 14 4375 15 3515 16 4335 17 4220 18 4175 19 4175 20 4350 Min 3170 Max 5490 Median 4342.500 Avg 4466.500 Revert commit 2920dd92b980 ("net: dsa: mt7530: disable LEDs before reset"). Changing the state of pins via reset assertion is simpler and more efficient than doing so by setting the LED controller off. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Fixes: c288575f7810 ("net: dsa: mt7530: Add the support of MT7531 switch") Co-developed-by: Justin Swartz <justin.swartz@risingedge.co.za> Signed-off-by: Justin Swartz <justin.swartz@risingedge.co.za> Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-03-14 09:28:35 +00:00
usleep_range(5000, 5100);
reset_control_deassert(priv->rstc);
} else {
gpiod_set_value_cansleep(priv->reset, 0);
net: dsa: mt7530: prevent possible incorrect XTAL frequency selection [ Upstream commit f490c492e946d8ffbe65ad4efc66de3c5ede30a4 ] On MT7530, the HT_XTAL_FSEL field of the HWTRAP register stores a 2-bit value that represents the frequency of the crystal oscillator connected to the switch IC. The field is populated by the state of the ESW_P4_LED_0 and ESW_P4_LED_0 pins, which is done right after reset is deasserted. ESW_P4_LED_0 ESW_P3_LED_0 Frequency ----------------------------------------- 0 0 Reserved 0 1 20MHz 1 0 40MHz 1 1 25MHz On MT7531, the XTAL25 bit of the STRAP register stores this. The LAN0LED0 pin is used to populate the bit. 25MHz when the pin is high, 40MHz when it's low. These pins are also used with LEDs, therefore, their state can be set to something other than the bootstrapping configuration. For example, a link may be established on port 3 before the DSA subdriver takes control of the switch which would set ESW_P3_LED_0 to high. Currently on mt7530_setup() and mt7531_setup(), 1000 - 1100 usec delay is described between reset assertion and deassertion. Some switch ICs in real life conditions cannot always have these pins set back to the bootstrapping configuration before reset deassertion in this amount of delay. This causes wrong crystal frequency to be selected which puts the switch in a nonfunctional state after reset deassertion. The tests below are conducted on an MT7530 with a 40MHz crystal oscillator by Justin Swartz. With a cable from an active peer connected to port 3 before reset, an incorrect crystal frequency (0b11 = 25MHz) is selected: [1] [3] [5] : : : _____________________________ __________________ ESW_P4_LED_0 |_______| _____________________________ ESW_P3_LED_0 |__________________________ : : : : : : [4]...: : : [2]................: [1] Reset is asserted. [2] Period of 1000 - 1100 usec. [3] Reset is deasserted. [4] Period of 315 usec. HWTRAP register is populated with incorrect XTAL frequency. [5] Signals reflect the bootstrapped configuration. Increase the delay between reset_control_assert() and reset_control_deassert(), and gpiod_set_value_cansleep(priv->reset, 0) and gpiod_set_value_cansleep(priv->reset, 1) to 5000 - 5100 usec. This amount ensures a higher possibility that the switch IC will have these pins back to the bootstrapping configuration before reset deassertion. With a cable from an active peer connected to port 3 before reset, the correct crystal frequency (0b10 = 40MHz) is selected: [1] [2-1] [3] [5] : : : : _____________________________ __________________ ESW_P4_LED_0 |_______| ___________________ _______ ESW_P3_LED_0 |_________| |__________________ : : : : : : [2-2]...: [4]...: [2]................: [1] Reset is asserted. [2] Period of 5000 - 5100 usec. [2-1] ESW_P3_LED_0 goes low. [2-2] Remaining period of 5000 - 5100 usec. [3] Reset is deasserted. [4] Period of 310 usec. HWTRAP register is populated with bootstrapped XTAL frequency. [5] Signals reflect the bootstrapped configuration. ESW_P3_LED_0 low period before reset deassertion: 5000 usec - 5100 usec TEST RESET HOLD # (usec) --------------------- 1 5410 2 5440 3 4375 4 5490 5 5475 6 4335 7 4370 8 5435 9 4205 10 4335 11 3750 12 3170 13 4395 14 4375 15 3515 16 4335 17 4220 18 4175 19 4175 20 4350 Min 3170 Max 5490 Median 4342.500 Avg 4466.500 Revert commit 2920dd92b980 ("net: dsa: mt7530: disable LEDs before reset"). Changing the state of pins via reset assertion is simpler and more efficient than doing so by setting the LED controller off. Fixes: b8f126a8d543 ("net-next: dsa: add dsa support for Mediatek MT7530 switch") Fixes: c288575f7810 ("net: dsa: mt7530: Add the support of MT7531 switch") Co-developed-by: Justin Swartz <justin.swartz@risingedge.co.za> Signed-off-by: Justin Swartz <justin.swartz@risingedge.co.za> Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-03-14 09:28:35 +00:00
usleep_range(5000, 5100);
gpiod_set_value_cansleep(priv->reset, 1);
}
/* Waiting for MT7530 got to stable */
INIT_MT7530_DUMMY_POLL(&p, priv, MT7530_HWTRAP);
ret = readx_poll_timeout(_mt7530_read, &p, val, val != 0,
20, 1000000);
if (ret < 0) {
dev_err(priv->dev, "reset timeout\n");
return ret;
}
id = mt7530_read(priv, MT7531_CREV);
id >>= CHIP_NAME_SHIFT;
if (id != MT7531_ID) {
dev_err(priv->dev, "chip %x can't be supported\n", id);
return -ENODEV;
}
/* all MACs must be forced link-down before sw reset */
for (i = 0; i < MT7530_NUM_PORTS; i++)
mt7530_write(priv, MT7530_PMCR_P(i), MT7531_FORCE_LNK);
/* Reset the switch through internal reset */
mt7530_write(priv, MT7530_SYS_CTRL,
SYS_CTRL_PHY_RST | SYS_CTRL_SW_RST |
SYS_CTRL_REG_RST);
mt7531_pll_setup(priv);
if (mt7531_dual_sgmii_supported(priv)) {
priv->p5_intf_sel = P5_INTF_SEL_GMAC5_SGMII;
/* Let ds->user_mii_bus be able to access external phy. */
mt7530_rmw(priv, MT7531_GPIO_MODE1, MT7531_GPIO11_RG_RXD2_MASK,
MT7531_EXT_P_MDC_11);
mt7530_rmw(priv, MT7531_GPIO_MODE1, MT7531_GPIO12_RG_RXD3_MASK,
MT7531_EXT_P_MDIO_12);
} else {
priv->p5_intf_sel = P5_INTF_SEL_GMAC5;
}
dev_dbg(ds->dev, "P5 support %s interface\n",
p5_intf_modes(priv->p5_intf_sel));
mt7530_rmw(priv, MT7531_GPIO_MODE0, MT7531_GPIO0_MASK,
MT7531_GPIO0_INTERRUPT);
/* Let phylink decide the interface later. */
priv->p5_interface = PHY_INTERFACE_MODE_NA;
priv->p6_interface = PHY_INTERFACE_MODE_NA;
/* Enable PHY core PLL, since phy_device has not yet been created
* provided for phy_[read,write]_mmd_indirect is called, we provide
* our own mt7531_ind_mmd_phy_[read,write] to complete this
* function.
*/
val = mt7531_ind_c45_phy_read(priv, MT753X_CTRL_PHY_ADDR,
MDIO_MMD_VEND2, CORE_PLL_GROUP4);
val |= MT7531_PHY_PLL_BYPASS_MODE;
val &= ~MT7531_PHY_PLL_OFF;
mt7531_ind_c45_phy_write(priv, MT753X_CTRL_PHY_ADDR, MDIO_MMD_VEND2,
CORE_PLL_GROUP4, val);
mt7531_setup_common(ds);
/* Setup VLAN ID 0 for VLAN-unaware bridges */
ret = mt7530_setup_vlan0(priv);
if (ret)
return ret;
ds->assisted_learning_on_cpu_port = true;
ds->mtu_enforcement_ingress = true;
return 0;
}
static void mt7530_mac_port_get_caps(struct dsa_switch *ds, int port,
struct phylink_config *config)
{
switch (port) {
case 0 ... 4: /* Internal phy */
__set_bit(PHY_INTERFACE_MODE_GMII,
config->supported_interfaces);
break;
case 5: /* 2nd cpu port with phy of port 0 or 4 / external phy */
phy_interface_set_rgmii(config->supported_interfaces);
__set_bit(PHY_INTERFACE_MODE_MII,
config->supported_interfaces);
__set_bit(PHY_INTERFACE_MODE_GMII,
config->supported_interfaces);
break;
case 6: /* 1st cpu port */
__set_bit(PHY_INTERFACE_MODE_RGMII,
config->supported_interfaces);
__set_bit(PHY_INTERFACE_MODE_TRGMII,
config->supported_interfaces);
break;
}
}
static bool mt7531_is_rgmii_port(struct mt7530_priv *priv, u32 port)
{
return (port == 5) && (priv->p5_intf_sel != P5_INTF_SEL_GMAC5_SGMII);
}
static void mt7531_mac_port_get_caps(struct dsa_switch *ds, int port,
struct phylink_config *config)
{
struct mt7530_priv *priv = ds->priv;
switch (port) {
case 0 ... 4: /* Internal phy */
__set_bit(PHY_INTERFACE_MODE_GMII,
config->supported_interfaces);
break;
case 5: /* 2nd cpu port supports either rgmii or sgmii/8023z */
if (mt7531_is_rgmii_port(priv, port)) {
phy_interface_set_rgmii(config->supported_interfaces);
break;
}
fallthrough;
case 6: /* 1st cpu port supports sgmii/8023z only */
__set_bit(PHY_INTERFACE_MODE_SGMII,
config->supported_interfaces);
__set_bit(PHY_INTERFACE_MODE_1000BASEX,
config->supported_interfaces);
__set_bit(PHY_INTERFACE_MODE_2500BASEX,
config->supported_interfaces);
config->mac_capabilities |= MAC_2500FD;
break;
}
}
static void mt7988_mac_port_get_caps(struct dsa_switch *ds, int port,
struct phylink_config *config)
{
phy_interface_zero(config->supported_interfaces);
switch (port) {
case 0 ... 4: /* Internal phy */
__set_bit(PHY_INTERFACE_MODE_INTERNAL,
config->supported_interfaces);
break;
case 6:
__set_bit(PHY_INTERFACE_MODE_INTERNAL,
config->supported_interfaces);
config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
MAC_10000FD;
}
}
static int
mt753x_pad_setup(struct dsa_switch *ds, const struct phylink_link_state *state)
{
struct mt7530_priv *priv = ds->priv;
return priv->info->pad_setup(ds, state->interface);
}
static int
mt7530_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
phy_interface_t interface)
{
struct mt7530_priv *priv = ds->priv;
/* Only need to setup port5. */
if (port != 5)
return 0;
mt7530_setup_port5(priv->ds, interface);
return 0;
}
static int mt7531_rgmii_setup(struct mt7530_priv *priv, u32 port,
phy_interface_t interface,
struct phy_device *phydev)
{
u32 val;
if (!mt7531_is_rgmii_port(priv, port)) {
dev_err(priv->dev, "RGMII mode is not available for port %d\n",
port);
return -EINVAL;
}
val = mt7530_read(priv, MT7531_CLKGEN_CTRL);
val |= GP_CLK_EN;
val &= ~GP_MODE_MASK;
val |= GP_MODE(MT7531_GP_MODE_RGMII);
val &= ~CLK_SKEW_IN_MASK;
val |= CLK_SKEW_IN(MT7531_CLK_SKEW_NO_CHG);
val &= ~CLK_SKEW_OUT_MASK;
val |= CLK_SKEW_OUT(MT7531_CLK_SKEW_NO_CHG);
val |= TXCLK_NO_REVERSE | RXCLK_NO_DELAY;
/* Do not adjust rgmii delay when vendor phy driver presents. */
if (!phydev || phy_driver_is_genphy(phydev)) {
val &= ~(TXCLK_NO_REVERSE | RXCLK_NO_DELAY);
switch (interface) {
case PHY_INTERFACE_MODE_RGMII:
val |= TXCLK_NO_REVERSE;
val |= RXCLK_NO_DELAY;
break;
case PHY_INTERFACE_MODE_RGMII_RXID:
val |= TXCLK_NO_REVERSE;
break;
case PHY_INTERFACE_MODE_RGMII_TXID:
val |= RXCLK_NO_DELAY;
break;
case PHY_INTERFACE_MODE_RGMII_ID:
break;
default:
return -EINVAL;
}
}
mt7530_write(priv, MT7531_CLKGEN_CTRL, val);
return 0;
}
static bool mt753x_is_mac_port(u32 port)
{
return (port == 5 || port == 6);
}
static int
mt7988_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
phy_interface_t interface)
{
if (dsa_is_cpu_port(ds, port) &&
interface == PHY_INTERFACE_MODE_INTERNAL)
return 0;
return -EINVAL;
}
static int
mt7531_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
phy_interface_t interface)
{
struct mt7530_priv *priv = ds->priv;
struct phy_device *phydev;
struct dsa_port *dp;
if (!mt753x_is_mac_port(port)) {
dev_err(priv->dev, "port %d is not a MAC port\n", port);
return -EINVAL;
}
switch (interface) {
case PHY_INTERFACE_MODE_RGMII:
case PHY_INTERFACE_MODE_RGMII_ID:
case PHY_INTERFACE_MODE_RGMII_RXID:
case PHY_INTERFACE_MODE_RGMII_TXID:
dp = dsa_to_port(ds, port);
phydev = dp->user->phydev;
return mt7531_rgmii_setup(priv, port, interface, phydev);
case PHY_INTERFACE_MODE_SGMII:
case PHY_INTERFACE_MODE_NA:
case PHY_INTERFACE_MODE_1000BASEX:
case PHY_INTERFACE_MODE_2500BASEX:
/* handled in SGMII PCS driver */
return 0;
default:
return -EINVAL;
}
return -EINVAL;
}
static int
mt753x_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
const struct phylink_link_state *state)
{
struct mt7530_priv *priv = ds->priv;
return priv->info->mac_port_config(ds, port, mode, state->interface);
}
static struct phylink_pcs *
mt753x_phylink_mac_select_pcs(struct dsa_switch *ds, int port,
phy_interface_t interface)
{
struct mt7530_priv *priv = ds->priv;
switch (interface) {
case PHY_INTERFACE_MODE_TRGMII:
return &priv->pcs[port].pcs;
case PHY_INTERFACE_MODE_SGMII:
case PHY_INTERFACE_MODE_1000BASEX:
case PHY_INTERFACE_MODE_2500BASEX:
return priv->ports[port].sgmii_pcs;
default:
return NULL;
}
}
static void
mt753x_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode,
const struct phylink_link_state *state)
{
struct mt7530_priv *priv = ds->priv;
u32 mcr_cur, mcr_new;
switch (port) {
case 0 ... 4: /* Internal phy */
if (state->interface != PHY_INTERFACE_MODE_GMII &&
state->interface != PHY_INTERFACE_MODE_INTERNAL)
goto unsupported;
break;
case 5: /* 2nd cpu port with phy of port 0 or 4 / external phy */
if (priv->p5_interface == state->interface)
break;
if (mt753x_mac_config(ds, port, mode, state) < 0)
goto unsupported;
if (priv->p5_intf_sel != P5_DISABLED)
priv->p5_interface = state->interface;
break;
case 6: /* 1st cpu port */
if (priv->p6_interface == state->interface)
break;
mt753x_pad_setup(ds, state);
if (mt753x_mac_config(ds, port, mode, state) < 0)
goto unsupported;
priv->p6_interface = state->interface;
break;
default:
unsupported:
dev_err(ds->dev, "%s: unsupported %s port: %i\n",
__func__, phy_modes(state->interface), port);
return;
}
mcr_cur = mt7530_read(priv, MT7530_PMCR_P(port));
mcr_new = mcr_cur;
mcr_new &= ~PMCR_LINK_SETTINGS_MASK;
mcr_new |= PMCR_IFG_XMIT(1) | PMCR_MAC_MODE | PMCR_BACKOFF_EN |
PMCR_BACKPR_EN | PMCR_FORCE_MODE_ID(priv->id);
/* Are we connected to external phy */
if (port == 5 && dsa_is_user_port(ds, 5))
mcr_new |= PMCR_EXT_PHY;
if (mcr_new != mcr_cur)
mt7530_write(priv, MT7530_PMCR_P(port), mcr_new);
}
static void mt753x_phylink_mac_link_down(struct dsa_switch *ds, int port,
unsigned int mode,
phy_interface_t interface)
{
struct mt7530_priv *priv = ds->priv;
mt7530_clear(priv, MT7530_PMCR_P(port), PMCR_LINK_SETTINGS_MASK);
}
static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port,
unsigned int mode,
phy_interface_t interface,
struct phy_device *phydev,
int speed, int duplex,
bool tx_pause, bool rx_pause)
{
struct mt7530_priv *priv = ds->priv;
u32 mcr;
mcr = PMCR_RX_EN | PMCR_TX_EN | PMCR_FORCE_LNK;
/* MT753x MAC works in 1G full duplex mode for all up-clocked
* variants.
*/
if (interface == PHY_INTERFACE_MODE_TRGMII ||
(phy_interface_mode_is_8023z(interface))) {
speed = SPEED_1000;
duplex = DUPLEX_FULL;
}
switch (speed) {
case SPEED_1000:
mcr |= PMCR_FORCE_SPEED_1000;
break;
case SPEED_100:
mcr |= PMCR_FORCE_SPEED_100;
break;
}
if (duplex == DUPLEX_FULL) {
mcr |= PMCR_FORCE_FDX;
if (tx_pause)
mcr |= PMCR_TX_FC_EN;
if (rx_pause)
mcr |= PMCR_RX_FC_EN;
}
if (mode == MLO_AN_PHY && phydev && phy_init_eee(phydev, false) >= 0) {
switch (speed) {
case SPEED_1000:
mcr |= PMCR_FORCE_EEE1G;
break;
case SPEED_100:
mcr |= PMCR_FORCE_EEE100;
break;
}
}
mt7530_set(priv, MT7530_PMCR_P(port), mcr);
}
static int
mt7531_cpu_port_config(struct dsa_switch *ds, int port)
{
struct mt7530_priv *priv = ds->priv;
phy_interface_t interface;
int speed;
int ret;
switch (port) {
case 5:
if (mt7531_is_rgmii_port(priv, port))
interface = PHY_INTERFACE_MODE_RGMII;
else
interface = PHY_INTERFACE_MODE_2500BASEX;
priv->p5_interface = interface;
break;
case 6:
interface = PHY_INTERFACE_MODE_2500BASEX;
priv->p6_interface = interface;
break;
default:
return -EINVAL;
}
if (interface == PHY_INTERFACE_MODE_2500BASEX)
speed = SPEED_2500;
else
speed = SPEED_1000;
ret = mt7531_mac_config(ds, port, MLO_AN_FIXED, interface);
if (ret)
return ret;
mt7530_write(priv, MT7530_PMCR_P(port),
PMCR_CPU_PORT_SETTING(priv->id));
mt753x_phylink_mac_link_up(ds, port, MLO_AN_FIXED, interface, NULL,
speed, DUPLEX_FULL, true, true);
return 0;
}
static int
mt7988_cpu_port_config(struct dsa_switch *ds, int port)
{
struct mt7530_priv *priv = ds->priv;
mt7530_write(priv, MT7530_PMCR_P(port),
PMCR_CPU_PORT_SETTING(priv->id));
mt753x_phylink_mac_link_up(ds, port, MLO_AN_FIXED,
PHY_INTERFACE_MODE_INTERNAL, NULL,
SPEED_10000, DUPLEX_FULL, true, true);
return 0;
}
static void mt753x_phylink_get_caps(struct dsa_switch *ds, int port,
struct phylink_config *config)
{
struct mt7530_priv *priv = ds->priv;
/* This switch only supports full-duplex at 1Gbps */
config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
MAC_10 | MAC_100 | MAC_1000FD;
priv->info->mac_port_get_caps(ds, port, config);
}
static int mt753x_pcs_validate(struct phylink_pcs *pcs,
unsigned long *supported,
const struct phylink_link_state *state)
{
/* Autonegotiation is not supported in TRGMII nor 802.3z modes */
if (state->interface == PHY_INTERFACE_MODE_TRGMII ||
phy_interface_mode_is_8023z(state->interface))
phylink_clear(supported, Autoneg);
return 0;
}
static void mt7530_pcs_get_state(struct phylink_pcs *pcs,
struct phylink_link_state *state)
{
struct mt7530_priv *priv = pcs_to_mt753x_pcs(pcs)->priv;
int port = pcs_to_mt753x_pcs(pcs)->port;
u32 pmsr;
pmsr = mt7530_read(priv, MT7530_PMSR_P(port));
state->link = (pmsr & PMSR_LINK);
state->an_complete = state->link;
state->duplex = !!(pmsr & PMSR_DPX);
switch (pmsr & PMSR_SPEED_MASK) {
case PMSR_SPEED_10:
state->speed = SPEED_10;
break;
case PMSR_SPEED_100:
state->speed = SPEED_100;
break;
case PMSR_SPEED_1000:
state->speed = SPEED_1000;
break;
default:
state->speed = SPEED_UNKNOWN;
break;
}
state->pause &= ~(MLO_PAUSE_RX | MLO_PAUSE_TX);
if (pmsr & PMSR_RX_FC)
state->pause |= MLO_PAUSE_RX;
if (pmsr & PMSR_TX_FC)
state->pause |= MLO_PAUSE_TX;
}
static int mt753x_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
phy_interface_t interface,
const unsigned long *advertising,
bool permit_pause_to_mac)
{
return 0;
}
static void mt7530_pcs_an_restart(struct phylink_pcs *pcs)
{
}
static const struct phylink_pcs_ops mt7530_pcs_ops = {
.pcs_validate = mt753x_pcs_validate,
.pcs_get_state = mt7530_pcs_get_state,
.pcs_config = mt753x_pcs_config,
.pcs_an_restart = mt7530_pcs_an_restart,
};
static int
mt753x_setup(struct dsa_switch *ds)
{
struct mt7530_priv *priv = ds->priv;
net: dsa: mt753x: fix pcs conversion regression Daniel Golle reports that the conversion of mt753x to phylink PCS caused an oops as below. The problem is with the placement of the PCS initialisation, which occurs after mt7531_setup() has been called. However, burited in this function is a call to setup the CPU port, which requires the PCS structure to be already setup. Fix this by changing the initialisation order. Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 Mem abort info: ESR = 0x96000005 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x05: level 1 translation fault Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 user pgtable: 4k pages, 39-bit VAs, pgdp=0000000046057000 [0000000000000020] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000 Internal error: Oops: 96000005 [#1] SMP Modules linked in: CPU: 0 PID: 32 Comm: kworker/u4:1 Tainted: G S 5.18.0-rc3-next-20220422+ #0 Hardware name: Bananapi BPI-R64 (DT) Workqueue: events_unbound deferred_probe_work_func pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : mt7531_cpu_port_config+0xcc/0x1b0 lr : mt7531_cpu_port_config+0xc0/0x1b0 sp : ffffffc008d5b980 x29: ffffffc008d5b990 x28: ffffff80060562c8 x27: 00000000f805633b x26: ffffff80001a8880 x25: 00000000000009c4 x24: 0000000000000016 x23: ffffff8005eb6470 x22: 0000000000003600 x21: ffffff8006948080 x20: 0000000000000000 x19: 0000000000000006 x18: 0000000000000000 x17: 0000000000000001 x16: 0000000000000001 x15: 02963607fcee069e x14: 0000000000000000 x13: 0000000000000030 x12: 0101010101010101 x11: ffffffc037302000 x10: 0000000000000870 x9 : ffffffc008d5b800 x8 : ffffff800028f950 x7 : 0000000000000001 x6 : 00000000662b3000 x5 : 00000000000002f0 x4 : 0000000000000000 x3 : ffffff800028f080 x2 : 0000000000000000 x1 : ffffff800028f080 x0 : 0000000000000000 Call trace: mt7531_cpu_port_config+0xcc/0x1b0 mt753x_cpu_port_enable+0x24/0x1f0 mt7531_setup+0x49c/0x5c0 mt753x_setup+0x20/0x31c dsa_register_switch+0x8bc/0x1020 mt7530_probe+0x118/0x200 mdio_probe+0x30/0x64 really_probe.part.0+0x98/0x280 __driver_probe_device+0x94/0x140 driver_probe_device+0x40/0x114 __device_attach_driver+0xb0/0x10c bus_for_each_drv+0x64/0xa0 __device_attach+0xa8/0x16c device_initial_probe+0x10/0x20 bus_probe_device+0x94/0x9c deferred_probe_work_func+0x80/0xb4 process_one_work+0x200/0x3a0 worker_thread+0x260/0x4c0 kthread+0xd4/0xe0 ret_from_fork+0x10/0x20 Code: 9409e911 937b7e60 8b0002a0 f9405800 (f9401005) ---[ end trace 0000000000000000 ]--- Reported-by: Daniel Golle <daniel@makrotopia.org> Tested-by: Daniel Golle <daniel@makrotopia.org> Fixes: cbd1f243bc41 ("net: dsa: mt7530: partially convert to phylink_pcs") Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/E1nj6FW-007WZB-5Y@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-04-25 21:28:02 +00:00
int i, ret;
/* Initialise the PCS devices */
for (i = 0; i < priv->ds->num_ports; i++) {
priv->pcs[i].pcs.ops = priv->info->pcs_ops;
priv->pcs[i].pcs.neg_mode = true;
net: dsa: mt753x: fix pcs conversion regression Daniel Golle reports that the conversion of mt753x to phylink PCS caused an oops as below. The problem is with the placement of the PCS initialisation, which occurs after mt7531_setup() has been called. However, burited in this function is a call to setup the CPU port, which requires the PCS structure to be already setup. Fix this by changing the initialisation order. Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 Mem abort info: ESR = 0x96000005 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x05: level 1 translation fault Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 user pgtable: 4k pages, 39-bit VAs, pgdp=0000000046057000 [0000000000000020] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000 Internal error: Oops: 96000005 [#1] SMP Modules linked in: CPU: 0 PID: 32 Comm: kworker/u4:1 Tainted: G S 5.18.0-rc3-next-20220422+ #0 Hardware name: Bananapi BPI-R64 (DT) Workqueue: events_unbound deferred_probe_work_func pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : mt7531_cpu_port_config+0xcc/0x1b0 lr : mt7531_cpu_port_config+0xc0/0x1b0 sp : ffffffc008d5b980 x29: ffffffc008d5b990 x28: ffffff80060562c8 x27: 00000000f805633b x26: ffffff80001a8880 x25: 00000000000009c4 x24: 0000000000000016 x23: ffffff8005eb6470 x22: 0000000000003600 x21: ffffff8006948080 x20: 0000000000000000 x19: 0000000000000006 x18: 0000000000000000 x17: 0000000000000001 x16: 0000000000000001 x15: 02963607fcee069e x14: 0000000000000000 x13: 0000000000000030 x12: 0101010101010101 x11: ffffffc037302000 x10: 0000000000000870 x9 : ffffffc008d5b800 x8 : ffffff800028f950 x7 : 0000000000000001 x6 : 00000000662b3000 x5 : 00000000000002f0 x4 : 0000000000000000 x3 : ffffff800028f080 x2 : 0000000000000000 x1 : ffffff800028f080 x0 : 0000000000000000 Call trace: mt7531_cpu_port_config+0xcc/0x1b0 mt753x_cpu_port_enable+0x24/0x1f0 mt7531_setup+0x49c/0x5c0 mt753x_setup+0x20/0x31c dsa_register_switch+0x8bc/0x1020 mt7530_probe+0x118/0x200 mdio_probe+0x30/0x64 really_probe.part.0+0x98/0x280 __driver_probe_device+0x94/0x140 driver_probe_device+0x40/0x114 __device_attach_driver+0xb0/0x10c bus_for_each_drv+0x64/0xa0 __device_attach+0xa8/0x16c device_initial_probe+0x10/0x20 bus_probe_device+0x94/0x9c deferred_probe_work_func+0x80/0xb4 process_one_work+0x200/0x3a0 worker_thread+0x260/0x4c0 kthread+0xd4/0xe0 ret_from_fork+0x10/0x20 Code: 9409e911 937b7e60 8b0002a0 f9405800 (f9401005) ---[ end trace 0000000000000000 ]--- Reported-by: Daniel Golle <daniel@makrotopia.org> Tested-by: Daniel Golle <daniel@makrotopia.org> Fixes: cbd1f243bc41 ("net: dsa: mt7530: partially convert to phylink_pcs") Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/E1nj6FW-007WZB-5Y@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-04-25 21:28:02 +00:00
priv->pcs[i].priv = priv;
priv->pcs[i].port = i;
}
net: dsa: mt753x: fix pcs conversion regression Daniel Golle reports that the conversion of mt753x to phylink PCS caused an oops as below. The problem is with the placement of the PCS initialisation, which occurs after mt7531_setup() has been called. However, burited in this function is a call to setup the CPU port, which requires the PCS structure to be already setup. Fix this by changing the initialisation order. Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020 Mem abort info: ESR = 0x96000005 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x05: level 1 translation fault Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 user pgtable: 4k pages, 39-bit VAs, pgdp=0000000046057000 [0000000000000020] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000 Internal error: Oops: 96000005 [#1] SMP Modules linked in: CPU: 0 PID: 32 Comm: kworker/u4:1 Tainted: G S 5.18.0-rc3-next-20220422+ #0 Hardware name: Bananapi BPI-R64 (DT) Workqueue: events_unbound deferred_probe_work_func pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : mt7531_cpu_port_config+0xcc/0x1b0 lr : mt7531_cpu_port_config+0xc0/0x1b0 sp : ffffffc008d5b980 x29: ffffffc008d5b990 x28: ffffff80060562c8 x27: 00000000f805633b x26: ffffff80001a8880 x25: 00000000000009c4 x24: 0000000000000016 x23: ffffff8005eb6470 x22: 0000000000003600 x21: ffffff8006948080 x20: 0000000000000000 x19: 0000000000000006 x18: 0000000000000000 x17: 0000000000000001 x16: 0000000000000001 x15: 02963607fcee069e x14: 0000000000000000 x13: 0000000000000030 x12: 0101010101010101 x11: ffffffc037302000 x10: 0000000000000870 x9 : ffffffc008d5b800 x8 : ffffff800028f950 x7 : 0000000000000001 x6 : 00000000662b3000 x5 : 00000000000002f0 x4 : 0000000000000000 x3 : ffffff800028f080 x2 : 0000000000000000 x1 : ffffff800028f080 x0 : 0000000000000000 Call trace: mt7531_cpu_port_config+0xcc/0x1b0 mt753x_cpu_port_enable+0x24/0x1f0 mt7531_setup+0x49c/0x5c0 mt753x_setup+0x20/0x31c dsa_register_switch+0x8bc/0x1020 mt7530_probe+0x118/0x200 mdio_probe+0x30/0x64 really_probe.part.0+0x98/0x280 __driver_probe_device+0x94/0x140 driver_probe_device+0x40/0x114 __device_attach_driver+0xb0/0x10c bus_for_each_drv+0x64/0xa0 __device_attach+0xa8/0x16c device_initial_probe+0x10/0x20 bus_probe_device+0x94/0x9c deferred_probe_work_func+0x80/0xb4 process_one_work+0x200/0x3a0 worker_thread+0x260/0x4c0 kthread+0xd4/0xe0 ret_from_fork+0x10/0x20 Code: 9409e911 937b7e60 8b0002a0 f9405800 (f9401005) ---[ end trace 0000000000000000 ]--- Reported-by: Daniel Golle <daniel@makrotopia.org> Tested-by: Daniel Golle <daniel@makrotopia.org> Fixes: cbd1f243bc41 ("net: dsa: mt7530: partially convert to phylink_pcs") Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/E1nj6FW-007WZB-5Y@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-04-25 21:28:02 +00:00
ret = priv->info->sw_setup(ds);
if (ret)
return ret;
ret = mt7530_setup_irq(priv);
if (ret)
return ret;
ret = mt7530_setup_mdio(priv);
if (ret && priv->irq)
mt7530_free_irq_common(priv);
if (priv->create_sgmii) {
ret = priv->create_sgmii(priv, mt7531_dual_sgmii_supported(priv));
if (ret && priv->irq)
mt7530_free_irq(priv);
}
return ret;
}
static int mt753x_get_mac_eee(struct dsa_switch *ds, int port,
struct ethtool_eee *e)
{
struct mt7530_priv *priv = ds->priv;
u32 eeecr = mt7530_read(priv, MT7530_PMEEECR_P(port));
e->tx_lpi_enabled = !(eeecr & LPI_MODE_EN);
e->tx_lpi_timer = GET_LPI_THRESH(eeecr);
return 0;
}
static int mt753x_set_mac_eee(struct dsa_switch *ds, int port,
struct ethtool_eee *e)
{
struct mt7530_priv *priv = ds->priv;
u32 set, mask = LPI_THRESH_MASK | LPI_MODE_EN;
if (e->tx_lpi_timer > 0xFFF)
return -EINVAL;
set = SET_LPI_THRESH(e->tx_lpi_timer);
if (!e->tx_lpi_enabled)
/* Force LPI Mode without a delay */
set |= LPI_MODE_EN;
mt7530_rmw(priv, MT7530_PMEEECR_P(port), mask, set);
return 0;
}
static int mt7988_pad_setup(struct dsa_switch *ds, phy_interface_t interface)
{
return 0;
}
static int mt7988_setup(struct dsa_switch *ds)
{
struct mt7530_priv *priv = ds->priv;
/* Reset the switch */
reset_control_assert(priv->rstc);
usleep_range(20, 50);
reset_control_deassert(priv->rstc);
usleep_range(20, 50);
/* Reset the switch PHYs */
mt7530_write(priv, MT7530_SYS_CTRL, SYS_CTRL_PHY_RST);
return mt7531_setup_common(ds);
}
const struct dsa_switch_ops mt7530_switch_ops = {
.get_tag_protocol = mtk_get_tag_protocol,
.setup = mt753x_setup,
net: dsa: introduce preferred_default_local_cpu_port and use on MT7530 Since the introduction of the OF bindings, DSA has always had a policy that in case multiple CPU ports are present in the device tree, the numerically smallest one is always chosen. The MT7530 switch family, except the switch on the MT7988 SoC, has 2 CPU ports, 5 and 6, where port 6 is preferable on the MT7531BE switch because it has higher bandwidth. The MT7530 driver developers had 3 options: - to modify DSA when the MT7531 switch support was introduced, such as to prefer the better port - to declare both CPU ports in device trees as CPU ports, and live with the sub-optimal performance resulting from not preferring the better port - to declare just port 6 in the device tree as a CPU port Of course they chose the path of least resistance (3rd option), kicking the can down the road. The hardware description in the device tree is supposed to be stable - developers are not supposed to adopt the strategy of piecemeal hardware description, where the device tree is updated in lockstep with the features that the kernel currently supports. Now, as a result of the fact that they did that, any attempts to modify the device tree and describe both CPU ports as CPU ports would make DSA change its default selection from port 6 to 5, effectively resulting in a performance degradation visible to users with the MT7531BE switch as can be seen below. Without preferring port 6: [ ID][Role] Interval Transfer Bitrate Retr [ 5][TX-C] 0.00-20.00 sec 374 MBytes 157 Mbits/sec 734 sender [ 5][TX-C] 0.00-20.00 sec 373 MBytes 156 Mbits/sec receiver [ 7][RX-C] 0.00-20.00 sec 1.81 GBytes 778 Mbits/sec 0 sender [ 7][RX-C] 0.00-20.00 sec 1.81 GBytes 777 Mbits/sec receiver With preferring port 6: [ ID][Role] Interval Transfer Bitrate Retr [ 5][TX-C] 0.00-20.00 sec 1.99 GBytes 856 Mbits/sec 273 sender [ 5][TX-C] 0.00-20.00 sec 1.99 GBytes 855 Mbits/sec receiver [ 7][RX-C] 0.00-20.00 sec 1.72 GBytes 737 Mbits/sec 15 sender [ 7][RX-C] 0.00-20.00 sec 1.71 GBytes 736 Mbits/sec receiver Using one port for WAN and the other ports for LAN is a very popular use case which is what this test emulates. As such, this change proposes that we retroactively modify stable kernels (which don't support the modification of the CPU port assignments, so as to let user space fix the problem and restore the throughput) to keep the mt7530 driver preferring port 6 even with device trees where the hardware is more fully described. Fixes: c288575f7810 ("net: dsa: mt7530: Add the support of MT7531 switch") Signed-off-by: Vladimir Oltean <olteanv@gmail.com> Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com> Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-17 06:26:48 +00:00
.preferred_default_local_cpu_port = mt753x_preferred_default_local_cpu_port,
.get_strings = mt7530_get_strings,
.get_ethtool_stats = mt7530_get_ethtool_stats,
.get_sset_count = mt7530_get_sset_count,
.set_ageing_time = mt7530_set_ageing_time,
.port_enable = mt7530_port_enable,
.port_disable = mt7530_port_disable,
.port_change_mtu = mt7530_port_change_mtu,
.port_max_mtu = mt7530_port_max_mtu,
.port_stp_state_set = mt7530_stp_state_set,
.port_pre_bridge_flags = mt7530_port_pre_bridge_flags,
.port_bridge_flags = mt7530_port_bridge_flags,
.port_bridge_join = mt7530_port_bridge_join,
.port_bridge_leave = mt7530_port_bridge_leave,
.port_fdb_add = mt7530_port_fdb_add,
.port_fdb_del = mt7530_port_fdb_del,
.port_fdb_dump = mt7530_port_fdb_dump,
.port_mdb_add = mt7530_port_mdb_add,
.port_mdb_del = mt7530_port_mdb_del,
.port_vlan_filtering = mt7530_port_vlan_filtering,
.port_vlan_add = mt7530_port_vlan_add,
.port_vlan_del = mt7530_port_vlan_del,
.port_mirror_add = mt753x_port_mirror_add,
.port_mirror_del = mt753x_port_mirror_del,
.phylink_get_caps = mt753x_phylink_get_caps,
.phylink_mac_select_pcs = mt753x_phylink_mac_select_pcs,
.phylink_mac_config = mt753x_phylink_mac_config,
.phylink_mac_link_down = mt753x_phylink_mac_link_down,
.phylink_mac_link_up = mt753x_phylink_mac_link_up,
.get_mac_eee = mt753x_get_mac_eee,
.set_mac_eee = mt753x_set_mac_eee,
};
EXPORT_SYMBOL_GPL(mt7530_switch_ops);
const struct mt753x_info mt753x_table[] = {
[ID_MT7621] = {
.id = ID_MT7621,
.pcs_ops = &mt7530_pcs_ops,
.sw_setup = mt7530_setup,
.phy_read_c22 = mt7530_phy_read_c22,
.phy_write_c22 = mt7530_phy_write_c22,
.phy_read_c45 = mt7530_phy_read_c45,
.phy_write_c45 = mt7530_phy_write_c45,
.pad_setup = mt7530_pad_clk_setup,
.mac_port_get_caps = mt7530_mac_port_get_caps,
.mac_port_config = mt7530_mac_config,
},
[ID_MT7530] = {
.id = ID_MT7530,
.pcs_ops = &mt7530_pcs_ops,
.sw_setup = mt7530_setup,
.phy_read_c22 = mt7530_phy_read_c22,
.phy_write_c22 = mt7530_phy_write_c22,
.phy_read_c45 = mt7530_phy_read_c45,
.phy_write_c45 = mt7530_phy_write_c45,
.pad_setup = mt7530_pad_clk_setup,
.mac_port_get_caps = mt7530_mac_port_get_caps,
.mac_port_config = mt7530_mac_config,
},
[ID_MT7531] = {
.id = ID_MT7531,
.pcs_ops = &mt7530_pcs_ops,
.sw_setup = mt7531_setup,
.phy_read_c22 = mt7531_ind_c22_phy_read,
.phy_write_c22 = mt7531_ind_c22_phy_write,
.phy_read_c45 = mt7531_ind_c45_phy_read,
.phy_write_c45 = mt7531_ind_c45_phy_write,
.pad_setup = mt7531_pad_setup,
.cpu_port_config = mt7531_cpu_port_config,
.mac_port_get_caps = mt7531_mac_port_get_caps,
.mac_port_config = mt7531_mac_config,
},
[ID_MT7988] = {
.id = ID_MT7988,
.pcs_ops = &mt7530_pcs_ops,
.sw_setup = mt7988_setup,
.phy_read_c22 = mt7531_ind_c22_phy_read,
.phy_write_c22 = mt7531_ind_c22_phy_write,
.phy_read_c45 = mt7531_ind_c45_phy_read,
.phy_write_c45 = mt7531_ind_c45_phy_write,
.pad_setup = mt7988_pad_setup,
.cpu_port_config = mt7988_cpu_port_config,
.mac_port_get_caps = mt7988_mac_port_get_caps,
.mac_port_config = mt7988_mac_config,
},
};
EXPORT_SYMBOL_GPL(mt753x_table);
int
mt7530_probe_common(struct mt7530_priv *priv)
{
struct device *dev = priv->dev;
priv->ds = devm_kzalloc(dev, sizeof(*priv->ds), GFP_KERNEL);
if (!priv->ds)
return -ENOMEM;
priv->ds->dev = dev;
priv->ds->num_ports = MT7530_NUM_PORTS;
/* Get the hardware identifier from the devicetree node.
* We will need it for some of the clock and regulator setup.
*/
priv->info = of_device_get_match_data(dev);
if (!priv->info)
return -EINVAL;
/* Sanity check if these required device operations are filled
* properly.
*/
if (!priv->info->sw_setup || !priv->info->pad_setup ||
!priv->info->phy_read_c22 || !priv->info->phy_write_c22 ||
!priv->info->mac_port_get_caps ||
!priv->info->mac_port_config)
return -EINVAL;
priv->id = priv->info->id;
priv->dev = dev;
priv->ds->priv = priv;
priv->ds->ops = &mt7530_switch_ops;
mutex_init(&priv->reg_mutex);
dev_set_drvdata(dev, priv);
return 0;
}
EXPORT_SYMBOL_GPL(mt7530_probe_common);
void
mt7530_remove_common(struct mt7530_priv *priv)
{
if (priv->irq)
mt7530_free_irq(priv);
dsa_unregister_switch(priv->ds);
mutex_destroy(&priv->reg_mutex);
}
EXPORT_SYMBOL_GPL(mt7530_remove_common);
MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
MODULE_DESCRIPTION("Driver for Mediatek MT7530 Switch");
MODULE_LICENSE("GPL");