On 04/20/2018 07:45 PM, Yury Norov wrote: > On Fri, Apr 20, 2018 at 05:08:23PM +0300, Andrey Ryabinin wrote: >> >> >> On 04/19/2018 06:01 AM, Fengguang Wu wrote: >>> Hello, >>> >>> FYI this happens in mainline kernel 4.17.0-rc1. >>> It at least dates back to v4.8 . >>> >>> [ 25.697463] >>> [ 25.697463] Start testing find_bit() with random-filled bitmap >>> [ 25.736615] find_next_bit: 30203201 ns, 163965 iterations >>> [ 25.783266] find_next_zero_bit: 45554622 ns, 163716 iterations >>> [ 25.832480] find_last_bit: 48003878 ns, 163965 iterations >>> [ 52.050031] watchdog: BUG: soft lockup - CPU#0 stuck for 22s! >>> [swapper/0:1] >>> [ 52.050031] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.17.0-rc1 #210 >>> [ 52.050031] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS >>> 1.10.2-1 04/01/2014 >>> [ 52.050031] RIP: 0010:__sanitizer_cov_trace_pc+0x65/0x66: >>> __sanitizer_cov_trace_pc at >>> kernel/kcov.c:111 >>> [ 52.050031] RSP: 0000:ffff88000fd43e40 EFLAGS: 00000246 ORIG_RAX: >>> ffffffffffffff13 >>> [ 52.050031] RAX: 0000000000000000 RBX: 0000000000000000 RCX: >>> 0000000000000017 >>> [ 52.050031] RDX: 0000000000000000 RSI: ffff88000fd3e000 RDI: >>> 0000000000000002 >>> [ 52.050031] RBP: 0000000000050000 R08: 0000000000000008 R09: >>> 0000000000000000 >>> [ 52.050031] R10: ffff88000fd3e000 R11: 00000000222e2c32 R12: >>> ffffffff85565d90 >>> [ 52.050031] R13: 0000000000030f80 R14: 0000000000030f80 R15: >>> 0000000000000000 >>> [ 52.050031] FS: 0000000000000000(0000) GS:ffff88001f600000(0000) >>> knlGS:0000000000000000 >>> [ 52.050031] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 >>> [ 52.050031] CR2: 0000000000000000 CR3: 0000000003c6a000 CR4: >>> 00000000000006b0 >>> [ 52.050031] Call Trace: >>> [ 52.050031] find_first_bit+0x66/0x7c: >>> find_first_bit at >>> lib/find_bit.c:106 (discriminator 1) >>> [ 52.050031] test_find_first_bit+0x3a/0x93 >> >> >> I suppose test_find_first_bit() needs a little more than zero cond_resched() >> calls. > > Or just decrease length of bitmap in this test. find_first_bit() takes > lion's share of time of the test. >
Yeah, that would be better. > Start testing find_bit() with random-filled bitmap > find_next_bit: 240043 cycles, 164062 iterations > find_next_zero_bit: 312848 cycles, 163619 iterations > find_last_bit: 193748 cycles, 164062 iterations > find_first_bit: 177720874 cycles, 164062 iterations > > I'll test the patch and send it soon if you OK with it. > > Yury >
