On Wed, Oct 12, 2022 at 10:45:46AM -0600, Jason A. Donenfeld wrote: > On Wed, Oct 12, 2022 at 09:49:26AM -0600, Jason A. Donenfeld wrote: > > On Wed, Oct 12, 2022 at 07:18:27AM -0700, Guenter Roeck wrote: > > > NIP [c000000000031630] .replay_soft_interrupts+0x60/0x300 > > > LR [c000000000031964] .arch_local_irq_restore+0x94/0x1c0 > > > Call Trace: > > > [c000000007df3870] [c000000000031964] .arch_local_irq_restore+0x94/0x1c0 > > > (unreliable) > > > [c000000007df38f0] [c000000000f8a444] .__schedule+0x664/0xa50 > > > [c000000007df39d0] [c000000000f8a8b0] .schedule+0x80/0x140 > > > [c000000007df3a50] [c00000000092f0dc] .try_to_generate_entropy+0x118/0x174 > > > [c000000007df3b40] [c00000000092e2e4] .urandom_read_iter+0x74/0x140 > > > [c000000007df3bc0] [c0000000003b0044] .vfs_read+0x284/0x2d0 > > > [c000000007df3cd0] [c0000000003b0d2c] .ksys_read+0xdc/0x130 > > > [c000000007df3d80] [c00000000002a88c] .system_call_exception+0x19c/0x330 > > > [c000000007df3e10] [c00000000000c1d4] system_call_common+0xf4/0x258 > > > > Obviously the first couple lines of this concern me a bit. But I think > > actually this might just be a catalyst for another bug. You could view > > that function as basically just: > > > > while (something) > > schedule(); > > > > And I guess in the process of calling the scheduler a lot, which toggles > > interrupts a lot, something got wedged. > > > > Curious, though, I did try to reproduce this, to no avail. My .config is > > https://xn--4db.cc/rBvHWfDZ . What's yours? > > I also just tried using your github linux-build-test scripts as a guide > for construction a config -- https://xn--4db.cc/B0HpEQDQ -- and loaded > up your rootfs over sdhci and such, and still couldn't manage to > reproduce. I tried commenting out the line "if (!bits)" in > _credit_init_bits(), so that the rng would never initialize, so that the > schedule() loop would just keep on running indefinitely, but still no > dice. > > But also, I'm running Linus' tree. From your log, I see > "6.0.0-rc2-00163-ga5edf9815dd7". So maybe these bugs got fixed > elsewhere? >
Blame me for not attaching the latest crash report. Guenter --- BUG: soft lockup - CPU#0 stuck for 23s! [dd:111] Modules linked in: CPU: 0 PID: 111 Comm: dd Not tainted 6.0.0-11414-g49da07006239 #1 Hardware name: PowerMac3,1 PPC970FX 0x3c0301 PowerMac NIP: c000000000031630 LR: c000000000031964 CTR: 0000000000000000 REGS: c000000007d5b6a8 TRAP: 0900 Not tainted (6.0.0-11414-g49da07006239) MSR: 8000000000009032 <SF,EE,ME,IR,DR,RI> CR: 28002228 XER: 00000000 IRQMASK: 0 GPR00: c000000000031964 c000000007d5b870 c0000000013e5500 c000000007d5b6a8 GPR04: c00000000125e1c0 0000000000000000 c000000007d5b814 c00000000291d018 GPR08: c000000002d4bbb8 0000000000000000 c000000007356400 c000000002d21098 GPR12: 0000000028002222 c000000002e20000 00000000100d32e0 00000000100d32b4 GPR16: 00000000100d3301 00000000100d32b9 00000000100d3358 00000000100d32bf GPR20: 0000000000002000 00000000100d3372 00000000100d331e c000000007356c18 GPR24: 0000000000000000 0000000000000e60 0000000000000900 0000000000000500 GPR28: 0000000000000a00 0000000000000f00 0000000000000002 0000000000000003 NIP [c000000000031630] .replay_soft_interrupts+0x60/0x300 LR [c000000000031964] .arch_local_irq_restore+0x94/0x1c0 Call Trace: [c000000007d5b870] [c000000000031964] .arch_local_irq_restore+0x94/0x1c0 (unreliable) [c000000007d5b8f0] [c000000000f8bac4] .__schedule+0x664/0xa50 [c000000007d5b9d0] [c000000000f8bf30] .schedule+0x80/0x140 [c000000007d5ba50] [c00000000093085c] .try_to_generate_entropy+0x118/0x174 [c000000007d5bb40] [c00000000092fa64] .urandom_read_iter+0x74/0x140 [c000000007d5bbc0] [c0000000003b0044] .vfs_read+0x284/0x2d0 [c000000007d5bcd0] [c0000000003b0d2c] .ksys_read+0xdc/0x130 [c000000007d5bd80] [c00000000002a88c] .system_call_exception+0x19c/0x330 [c000000007d5be10] [c00000000000c1d4] system_call_common+0xf4/0x258 --- interrupt: c00 at 0x7fffb5c9d49c NIP: 00007fffb5c9d49c LR: 000000001000da90 CTR: 0000000000000000 REGS: c000000007d5be80 TRAP: 0c00 Not tainted (6.0.0-11414-g49da07006239) MSR: 800000000000f032 <SF,EE,PR,FP,ME,IR,DR,RI> CR: 22002422 XER: 00000000 IRQMASK: 0 GPR00: 0000000000000003 00007ffff6dcc220 00007fffb5d97300 0000000000000000 GPR04: 00000000101102a0 0000000000000020 0000000000000000 0000000000000000 GPR08: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR12: 0000000000000000 00007fffb5e6aac0 00000000100d32e0 00000000100d32b4 GPR16: 00000000100d3301 00000000100d32b9 00000000100d3358 00000000100d32bf GPR20: 0000000000002000 00000000100d3372 00000000100d331e 0000000000000000 GPR24: 7fffffffffffffff 00000000100b3a9c 00000000101102a0 0000000000000020 GPR28: 00000000101025c0 0000000000000020 0000000000000000 0000000000000000 NIP [00007fffb5c9d49c] 0x7fffb5c9d49c LR [000000001000da90] 0x1000da90 --- interrupt: c00 Instruction dump: 3b600500 3b800a00 3ba00f00 f8010010 f821fdc1 60000000 60000000 38610078 e92d0af8 f92101f8 39200000 48039745 <60000000> 39000000 e9410180 892d0933 Kernel panic - not syncing: softlockup: hung tasks CPU: 0 PID: 111 Comm: dd Tainted: G L 6.0.0-11414-g49da07006239 #1 Hardware name: PowerMac3,1 PPC970FX 0x3c0301 PowerMac Call Trace: [c000000007d5b180] [c000000000f59b40] .dump_stack_lvl+0x7c/0xc4 (unreliable) [c000000007d5b210] [c0000000000d5b58] .panic+0x174/0x42c [c000000007d5b2c0] [c000000000231054] .watchdog_timer_fn+0x3a4/0x3e0 [c000000007d5b380] [c0000000001cc65c] .__hrtimer_run_queues+0x1fc/0x650 [c000000007d5b490] [c0000000001cd5cc] .hrtimer_interrupt+0x11c/0x320 [c000000007d5b550] [c000000000021f5c] .timer_interrupt+0x1cc/0x600 [c000000007d5b630] [c0000000000316c8] .replay_soft_interrupts+0xf8/0x300 [c000000007d5b870] [c000000000031964] .arch_local_irq_restore+0x94/0x1c0 [c000000007d5b8f0] [c000000000f8bac4] .__schedule+0x664/0xa50 [c000000007d5b9d0] [c000000000f8bf30] .schedule+0x80/0x140 [c000000007d5ba50] [c00000000093085c] .try_to_generate_entropy+0x118/0x174 [c000000007d5bb40] [c00000000092fa64] .urandom_read_iter+0x74/0x140 [c000000007d5bbc0] [c0000000003b0044] .vfs_read+0x284/0x2d0 [c000000007d5bcd0] [c0000000003b0d2c] .ksys_read+0xdc/0x130 [c000000007d5bd80] [c00000000002a88c] .system_call_exception+0x19c/0x330 [c000000007d5be10] [c00000000000c1d4] system_call_common+0xf4/0x258 --- interrupt: c00 at 0x7fffb5c9d49c NIP: 00007fffb5c9d49c LR: 000000001000da90 CTR: 0000000000000000 REGS: c000000007d5be80 TRAP: 0c00 Tainted: G L (6.0.0-11414-g49da07006239) MSR: 800000000000f032 <SF,EE,PR,FP,ME,IR,DR,RI> CR: 22002422 XER: 00000000 IRQMASK: 0 GPR00: 0000000000000003 00007ffff6dcc220 00007fffb5d97300 0000000000000000 GPR04: 00000000101102a0 0000000000000020 0000000000000000 0000000000000000 GPR08: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 GPR12: 0000000000000000 00007fffb5e6aac0 00000000100d32e0 00000000100d32b4 GPR16: 00000000100d3301 00000000100d32b9 00000000100d3358 00000000100d32bf GPR20: 0000000000002000 00000000100d3372 00000000100d331e 0000000000000000 GPR24: 7fffffffffffffff 00000000100b3a9c 00000000101102a0 0000000000000020 GPR28: 00000000101025c0 0000000000000020 0000000000000000 0000000000000000 NIP [00007fffb5c9d49c] 0x7fffb5c9d49c LR [000000001000da90] 0x1000da90 --- interrupt: c00