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 <tobias@waldekranz.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
parent
0da8aa00bf
commit
35da1dfd94
2 changed files with 19 additions and 5 deletions
|
@ -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");
|
||||
|
|
|
@ -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;
|
||||
|
|
Loading…
Add table
Reference in a new issue