@@ -918,13 +918,16 @@ EXPORT_SYMBOL_GPL(unregister_random_vmfork_notifier);
#endif
struct fast_pool {
- struct work_struct mix;
+ struct tasklet_struct mix;
unsigned long pool[4];
unsigned long last;
unsigned int count;
};
+static void mix_interrupt_randomness(struct tasklet_struct *work);
+
static DEFINE_PER_CPU(struct fast_pool, irq_randomness) = {
+ .mix = { .use_callback = true, .callback = mix_interrupt_randomness },
#ifdef CONFIG_64BIT
#define FASTMIX_PERM SIPHASH_PERMUTATION
.pool = { SIPHASH_CONST_0, SIPHASH_CONST_1, SIPHASH_CONST_2, SIPHASH_CONST_3 }
@@ -973,7 +976,7 @@ int __cold random_online_cpu(unsigned int cpu)
}
#endif
-static void mix_interrupt_randomness(struct work_struct *work)
+static void mix_interrupt_randomness(struct tasklet_struct *work)
{
struct fast_pool *fast_pool = container_of(work, struct fast_pool, mix);
/*
@@ -1027,10 +1030,8 @@ void add_interrupt_randomness(int irq)
if (new_count < 1024 && !time_is_before_jiffies(fast_pool->last + HZ))
return;
- if (unlikely(!fast_pool->mix.func))
- INIT_WORK(&fast_pool->mix, mix_interrupt_randomness);
fast_pool->count |= MIX_INFLIGHT;
- queue_work_on(raw_smp_processor_id(), system_highpri_wq, &fast_pool->mix);
+ tasklet_hi_schedule(&fast_pool->mix);
}
EXPORT_SYMBOL_GPL(add_interrupt_randomness);
Previously, the fast pool was dumped into the main pool peroidically in the fast pool's hard IRQ handler. This worked fine and there weren't problems with it, until RT came around. Since RT converts spinlocks into sleeping locks, problems cropped up. Rather than switching to raw spinlocks, the RT developers preferred we make the transformation from originally doing: do_some_stuff() spin_lock() do_some_other_stuff() spin_unlock() to doing: do_some_stuff() queue_work_on(some_other_stuff_worker) This is an ordinary pattern done all over the kernel. However, Sherry noticed a 10% performance regression in qperf TCP over a 40gbps InfiniBand card. Quoting her message: > MT27500 Family [ConnectX-3] cards: > Infiniband device 'mlx4_0' port 1 status: > default gid: fe80:0000:0000:0000:0010:e000:0178:9eb1 > base lid: 0x6 > sm lid: 0x1 > state: 4: ACTIVE > phys state: 5: LinkUp > rate: 40 Gb/sec (4X QDR) > link_layer: InfiniBand > > Cards are configured with IP addresses on private subnet for IPoIB > performance testing. > Regression identified in this bug is in TCP latency in this stack as reported > by qperf tcp_lat metric: > > We have one system listen as a qperf server: > [root@yourQperfServer ~]# qperf > > Have the other system connect to qperf server as a client (in this > case, it’s X7 server with Mellanox card): > [root@yourQperfClient ~]# numactl -m0 -N0 qperf 20.20.20.101 -v -uu -ub --time 60 --wait_server 20 -oo msg_size:4K:1024K:*2 tcp_lat Rather than incur the scheduling latency from queue_work_on, we can instead switch to a tasklet, which will run on the same core -- exactly what we want -- and happen during context transition without additional scheduling latency, and minimized logic in the enqueuing path. Hopefully this restores performance from prior to the RT changes. Reported-by: Sherry Yang <sherry.yang@oracle.com> Suggested-by: Sultan Alsawaf <sultan@kerneltoast.com> Fixes: 58340f8e952b ("random: defer fast pool mixing to worker") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/lkml/YyuREcGAXV9828w5@zx2c4.com/ Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> --- Hi Sherry, I'm not going to commit to this until I receive your `Tested-by:`, so please let me know if this fixes the problem. If not, we'll try something else. Thanks, Jason drivers/char/random.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)