hwrng: bcm2835 - Fix hwrng throughput regression

The last RCU stall fix caused a massive throughput regression of the
hwrng on Raspberry Pi 0 - 3. hwrng_msleep doesn't sleep precisely enough
and usleep_range doesn't allow scheduling. So try to restore the
best possible throughput by introducing hwrng_yield which interruptable
sleeps for one jiffy.

Some performance measurements on Raspberry Pi 3B+ (arm64/defconfig):

sudo dd if=/dev/hwrng of=/dev/null count=1 bs=10000

cpu_relax              ~138025 Bytes / sec
hwrng_msleep(1000)         ~13 Bytes / sec
hwrng_yield              ~2510 Bytes / sec

Fixes: 96cb9d0554 ("hwrng: bcm2835 - use hwrng_msleep() instead of cpu_relax()")
Link: https://lore.kernel.org/linux-arm-kernel/bc97ece5-44a3-4c4e-77da-2db3eb66b128@gmx.net/
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
This commit is contained in:
Stefan Wahren 2023-09-06 01:27:57 +02:00 committed by Herbert Xu
parent c977950146
commit b58a36008b
3 changed files with 8 additions and 1 deletions

View File

@ -70,7 +70,7 @@ static int bcm2835_rng_read(struct hwrng *rng, void *buf, size_t max,
while ((rng_readl(priv, RNG_STATUS) >> 24) == 0) {
if (!wait)
return 0;
hwrng_msleep(rng, 1000);
hwrng_yield(rng);
}
num_words = rng_readl(priv, RNG_STATUS) >> 24;

View File

@ -678,6 +678,12 @@ long hwrng_msleep(struct hwrng *rng, unsigned int msecs)
}
EXPORT_SYMBOL_GPL(hwrng_msleep);
long hwrng_yield(struct hwrng *rng)
{
return wait_for_completion_interruptible_timeout(&rng->dying, 1);
}
EXPORT_SYMBOL_GPL(hwrng_yield);
static int __init hwrng_modinit(void)
{
int ret;

View File

@ -63,5 +63,6 @@ extern void hwrng_unregister(struct hwrng *rng);
extern void devm_hwrng_unregister(struct device *dve, struct hwrng *rng);
extern long hwrng_msleep(struct hwrng *rng, unsigned int msecs);
extern long hwrng_yield(struct hwrng *rng);
#endif /* LINUX_HWRANDOM_H_ */