From 35da1dfd94847c5f1ac04ce5b5002b888c3f36ec Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Fri, 28 Jan 2022 17:26:49 +0100 Subject: [PATCH 1/2] net: dsa: mv88e6xxx: Improve performance of busy bit polling Avoid a long delay when a busy bit is still set and has to be polled again. Measurements on a system with 2 Opals (6097F) and one Agate (6352) show that even with this much tighter loop, we have about a 50% chance of the bit being cleared on the first poll, all other accesses see the bit being cleared on the second poll. On a standard MDIO bus running MDC at 2.5MHz, a single access with 32 bits of preamble plus 32 bits of data takes 64*(1/2.5MHz) = 25.6us. This means that mv88e6xxx_smi_direct_wait took 26us + CPU overhead in the fast scenario, but 26us + 1500us + 26us + CPU overhead in the slow case - bringing the average close to 1ms. With this change in place, the slow case is closer to 2*26us + CPU overhead, with the average well below 100us - a 10x improvement. This translates to real-world winnings. On a 3-chip 20-port system, the modprobe time drops by 88%: Before: root@coronet:~# time modprobe mv88e6xxx real 0m 15.99s user 0m 0.00s sys 0m 1.52s After: root@coronet:~# time modprobe mv88e6xxx real 0m 2.21s user 0m 0.00s sys 0m 1.54s Signed-off-by: Tobias Waldekranz Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 13 ++++++++++--- drivers/net/dsa/mv88e6xxx/smi.c | 11 +++++++++-- 2 files changed, 19 insertions(+), 5 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 58ca684d73f7..1023e4549359 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -86,12 +86,16 @@ int mv88e6xxx_write(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val) int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask, u16 val) { + const unsigned long timeout = jiffies + msecs_to_jiffies(50); u16 data; int err; int i; - /* There's no bus specific operation to wait for a mask */ - for (i = 0; i < 16; i++) { + /* There's no bus specific operation to wait for a mask. Even + * if the initial poll takes longer than 50ms, always do at + * least one more attempt. + */ + for (i = 0; time_before(jiffies, timeout) || (i < 2); i++) { err = mv88e6xxx_read(chip, addr, reg, &data); if (err) return err; @@ -99,7 +103,10 @@ int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, if ((data & mask) == val) return 0; - usleep_range(1000, 2000); + if (i < 2) + cpu_relax(); + else + usleep_range(1000, 2000); } dev_err(chip->dev, "Timeout while waiting for switch\n"); diff --git a/drivers/net/dsa/mv88e6xxx/smi.c b/drivers/net/dsa/mv88e6xxx/smi.c index 282fe08db050..728ef3f54ec5 100644 --- a/drivers/net/dsa/mv88e6xxx/smi.c +++ b/drivers/net/dsa/mv88e6xxx/smi.c @@ -55,11 +55,15 @@ static int mv88e6xxx_smi_direct_write(struct mv88e6xxx_chip *chip, static int mv88e6xxx_smi_direct_wait(struct mv88e6xxx_chip *chip, int dev, int reg, int bit, int val) { + const unsigned long timeout = jiffies + msecs_to_jiffies(50); u16 data; int err; int i; - for (i = 0; i < 16; i++) { + /* Even if the initial poll takes longer than 50ms, always do + * at least one more attempt. + */ + for (i = 0; time_before(jiffies, timeout) || (i < 2); i++) { err = mv88e6xxx_smi_direct_read(chip, dev, reg, &data); if (err) return err; @@ -67,7 +71,10 @@ static int mv88e6xxx_smi_direct_wait(struct mv88e6xxx_chip *chip, if (!!(data & BIT(bit)) == !!val) return 0; - usleep_range(1000, 2000); + if (i < 2) + cpu_relax(); + else + usleep_range(1000, 2000); } return -ETIMEDOUT; From 7bca16b22e6a126f66f7d8d551be10815ba46fdb Mon Sep 17 00:00:00 2001 From: Tobias Waldekranz Date: Fri, 28 Jan 2022 17:26:50 +0100 Subject: [PATCH 2/2] net: dsa: mv88e6xxx: Improve indirect addressing performance Before this change, both the read and write callback would start out by asserting that the chip's busy flag was cleared. However, both callbacks also made sure to wait for the clearing of the busy bit before returning - making the initial check superfluous. The only time that would ever have an effect was if the busy bit was initially set for some reason. With that in mind, make sure to perform an initial check of the busy bit, after which both read and write can rely the previous operation to have waited for the bit to clear. This cuts the number of operations on the underlying MDIO bus by 25% Signed-off-by: Tobias Waldekranz Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.h | 1 + drivers/net/dsa/mv88e6xxx/smi.c | 24 ++++++++++++++---------- 2 files changed, 15 insertions(+), 10 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 8271b8aa7b71..438cee853d07 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -392,6 +392,7 @@ struct mv88e6xxx_chip { struct mv88e6xxx_bus_ops { int (*read)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 *val); int (*write)(struct mv88e6xxx_chip *chip, int addr, int reg, u16 val); + int (*init)(struct mv88e6xxx_chip *chip); }; struct mv88e6xxx_mdio_bus { diff --git a/drivers/net/dsa/mv88e6xxx/smi.c b/drivers/net/dsa/mv88e6xxx/smi.c index 728ef3f54ec5..a990271b7482 100644 --- a/drivers/net/dsa/mv88e6xxx/smi.c +++ b/drivers/net/dsa/mv88e6xxx/smi.c @@ -111,11 +111,6 @@ static int mv88e6xxx_smi_indirect_read(struct mv88e6xxx_chip *chip, { int err; - err = mv88e6xxx_smi_direct_wait(chip, chip->sw_addr, - MV88E6XXX_SMI_CMD, 15, 0); - if (err) - return err; - err = mv88e6xxx_smi_direct_write(chip, chip->sw_addr, MV88E6XXX_SMI_CMD, MV88E6XXX_SMI_CMD_BUSY | @@ -139,11 +134,6 @@ static int mv88e6xxx_smi_indirect_write(struct mv88e6xxx_chip *chip, { int err; - err = mv88e6xxx_smi_direct_wait(chip, chip->sw_addr, - MV88E6XXX_SMI_CMD, 15, 0); - if (err) - return err; - err = mv88e6xxx_smi_direct_write(chip, chip->sw_addr, MV88E6XXX_SMI_DATA, data); if (err) @@ -162,9 +152,20 @@ static int mv88e6xxx_smi_indirect_write(struct mv88e6xxx_chip *chip, MV88E6XXX_SMI_CMD, 15, 0); } +static int mv88e6xxx_smi_indirect_init(struct mv88e6xxx_chip *chip) +{ + /* Ensure that the chip starts out in the ready state. As both + * reads and writes always ensure this on return, they can + * safely depend on the chip not being busy on entry. + */ + return mv88e6xxx_smi_direct_wait(chip, chip->sw_addr, + MV88E6XXX_SMI_CMD, 15, 0); +} + static const struct mv88e6xxx_bus_ops mv88e6xxx_smi_indirect_ops = { .read = mv88e6xxx_smi_indirect_read, .write = mv88e6xxx_smi_indirect_write, + .init = mv88e6xxx_smi_indirect_init, }; int mv88e6xxx_smi_init(struct mv88e6xxx_chip *chip, @@ -182,5 +183,8 @@ int mv88e6xxx_smi_init(struct mv88e6xxx_chip *chip, chip->bus = bus; chip->sw_addr = sw_addr; + if (chip->smi_ops->init) + return chip->smi_ops->init(chip); + return 0; }