| From c18df0adabf8400c1825b90382d06df5edc303fa Mon Sep 17 00:00:00 2001 |
| From: David Daney <david.daney@cavium.com> |
| Date: Tue, 20 Sep 2016 11:46:35 -0700 |
| Subject: arm64: Call numa_store_cpu_info() earlier. |
| |
| From: David Daney <david.daney@cavium.com> |
| |
| commit c18df0adabf8400c1825b90382d06df5edc303fa upstream. |
| |
| The wq_numa_init() function makes a private CPU to node map by calling |
| cpu_to_node() early in the boot process, before the non-boot CPUs are |
| brought online. Since the default implementation of cpu_to_node() |
| returns zero for CPUs that have never been brought online, the |
| workqueue system's view is that *all* CPUs are on node zero. |
| |
| When the unbound workqueue for a non-zero node is created, the |
| tsk_cpus_allowed() for the worker threads is the empty set because |
| there are, in the view of the workqueue system, no CPUs on non-zero |
| nodes. The code in try_to_wake_up() using this empty cpumask ends up |
| using the cpumask empty set value of NR_CPUS as an index into the |
| per-CPU area pointer array, and gets garbage as it is one past the end |
| of the array. This results in: |
| |
| [ 0.881970] Unable to handle kernel paging request at virtual address fffffb1008b926a4 |
| [ 1.970095] pgd = fffffc00094b0000 |
| [ 1.973530] [fffffb1008b926a4] *pgd=0000000000000000, *pud=0000000000000000, *pmd=0000000000000000 |
| [ 1.982610] Internal error: Oops: 96000004 [#1] SMP |
| [ 1.987541] Modules linked in: |
| [ 1.990631] CPU: 48 PID: 295 Comm: cpuhp/48 Tainted: G W 4.8.0-rc6-preempt-vol+ #9 |
| [ 1.999435] Hardware name: Cavium ThunderX CN88XX board (DT) |
| [ 2.005159] task: fffffe0fe89cc300 task.stack: fffffe0fe8b8c000 |
| [ 2.011158] PC is at try_to_wake_up+0x194/0x34c |
| [ 2.015737] LR is at try_to_wake_up+0x150/0x34c |
| [ 2.020318] pc : [<fffffc00080e7468>] lr : [<fffffc00080e7424>] pstate: 600000c5 |
| [ 2.027803] sp : fffffe0fe8b8fb10 |
| [ 2.031149] x29: fffffe0fe8b8fb10 x28: 0000000000000000 |
| [ 2.036522] x27: fffffc0008c63bc8 x26: 0000000000001000 |
| [ 2.041896] x25: fffffc0008c63c80 x24: fffffc0008bfb200 |
| [ 2.047270] x23: 00000000000000c0 x22: 0000000000000004 |
| [ 2.052642] x21: fffffe0fe89d25bc x20: 0000000000001000 |
| [ 2.058014] x19: fffffe0fe89d1d00 x18: 0000000000000000 |
| [ 2.063386] x17: 0000000000000000 x16: 0000000000000000 |
| [ 2.068760] x15: 0000000000000018 x14: 0000000000000000 |
| [ 2.074133] x13: 0000000000000000 x12: 0000000000000000 |
| [ 2.079505] x11: 0000000000000000 x10: 0000000000000000 |
| [ 2.084879] x9 : 0000000000000000 x8 : 0000000000000000 |
| [ 2.090251] x7 : 0000000000000040 x6 : 0000000000000000 |
| [ 2.095621] x5 : ffffffffffffffff x4 : 0000000000000000 |
| [ 2.100991] x3 : 0000000000000000 x2 : 0000000000000000 |
| [ 2.106364] x1 : fffffc0008be4c24 x0 : ffffff0ffffada80 |
| [ 2.111737] |
| [ 2.113236] Process cpuhp/48 (pid: 295, stack limit = 0xfffffe0fe8b8c020) |
| [ 2.120102] Stack: (0xfffffe0fe8b8fb10 to 0xfffffe0fe8b90000) |
| [ 2.125914] fb00: fffffe0fe8b8fb80 fffffc00080e7648 |
| . |
| . |
| . |
| [ 2.442859] Call trace: |
| [ 2.445327] Exception stack(0xfffffe0fe8b8f940 to 0xfffffe0fe8b8fa70) |
| [ 2.451843] f940: fffffe0fe89d1d00 0000040000000000 fffffe0fe8b8fb10 fffffc00080e7468 |
| [ 2.459767] f960: fffffe0fe8b8f980 fffffc00080e4958 ffffff0ff91ab200 fffffc00080e4b64 |
| [ 2.467690] f980: fffffe0fe8b8f9d0 fffffc00080e515c fffffe0fe8b8fa80 0000000000000000 |
| [ 2.475614] f9a0: fffffe0fe8b8f9d0 fffffc00080e58e4 fffffe0fe8b8fa80 0000000000000000 |
| [ 2.483540] f9c0: fffffe0fe8d10000 0000000000000040 fffffe0fe8b8fa50 fffffc00080e5ac4 |
| [ 2.491465] f9e0: ffffff0ffffada80 fffffc0008be4c24 0000000000000000 0000000000000000 |
| [ 2.499387] fa00: 0000000000000000 ffffffffffffffff 0000000000000000 0000000000000040 |
| [ 2.507309] fa20: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 |
| [ 2.515233] fa40: 0000000000000000 0000000000000000 0000000000000000 0000000000000018 |
| [ 2.523156] fa60: 0000000000000000 0000000000000000 |
| [ 2.528089] [<fffffc00080e7468>] try_to_wake_up+0x194/0x34c |
| [ 2.533723] [<fffffc00080e7648>] wake_up_process+0x28/0x34 |
| [ 2.539275] [<fffffc00080d3764>] create_worker+0x110/0x19c |
| [ 2.544824] [<fffffc00080d69dc>] alloc_unbound_pwq+0x3cc/0x4b0 |
| [ 2.550724] [<fffffc00080d6bcc>] wq_update_unbound_numa+0x10c/0x1e4 |
| [ 2.557066] [<fffffc00080d7d78>] workqueue_online_cpu+0x220/0x28c |
| [ 2.563234] [<fffffc00080bd288>] cpuhp_invoke_callback+0x6c/0x168 |
| [ 2.569398] [<fffffc00080bdf74>] cpuhp_up_callbacks+0x44/0xe4 |
| [ 2.575210] [<fffffc00080be194>] cpuhp_thread_fun+0x13c/0x148 |
| [ 2.581027] [<fffffc00080dfbac>] smpboot_thread_fn+0x19c/0x1a8 |
| [ 2.586929] [<fffffc00080dbd64>] kthread+0xdc/0xf0 |
| [ 2.591776] [<fffffc0008083380>] ret_from_fork+0x10/0x50 |
| [ 2.597147] Code: b00057e1 91304021 91005021 b8626822 (b8606821) |
| [ 2.603464] ---[ end trace 58c0cd36b88802bc ]--- |
| [ 2.608138] Kernel panic - not syncing: Fatal exception |
| |
| Fix by moving call to numa_store_cpu_info() for all CPUs into |
| smp_prepare_cpus(), which happens before wq_numa_init(). Since |
| smp_store_cpu_info() now contains only a single function call, |
| simplify by removing the function and out-lining its contents. |
| |
| Suggested-by: Robert Richter <rric@kernel.org> |
| Fixes: 1a2db300348b ("arm64, numa: Add NUMA support for arm64 platforms.") |
| Signed-off-by: David Daney <david.daney@cavium.com> |
| Reviewed-by: Robert Richter <rrichter@cavium.com> |
| Tested-by: Yisheng Xie <xieyisheng1@huawei.com> |
| Signed-off-by: Catalin Marinas <catalin.marinas@arm.com> |
| Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
| |
| --- |
| arch/arm64/kernel/smp.c | 14 ++++++-------- |
| 1 file changed, 6 insertions(+), 8 deletions(-) |
| |
| --- a/arch/arm64/kernel/smp.c |
| +++ b/arch/arm64/kernel/smp.c |
| @@ -201,12 +201,6 @@ int __cpu_up(unsigned int cpu, struct ta |
| return ret; |
| } |
| |
| -static void smp_store_cpu_info(unsigned int cpuid) |
| -{ |
| - store_cpu_topology(cpuid); |
| - numa_store_cpu_info(cpuid); |
| -} |
| - |
| /* |
| * This is the secondary CPU boot entry. We're using this CPUs |
| * idle thread stack, but a set of temporary page tables. |
| @@ -254,7 +248,7 @@ asmlinkage void secondary_start_kernel(v |
| */ |
| notify_cpu_starting(cpu); |
| |
| - smp_store_cpu_info(cpu); |
| + store_cpu_topology(cpu); |
| |
| /* |
| * OK, now it's safe to let the boot CPU continue. Wait for |
| @@ -687,10 +681,13 @@ void __init smp_prepare_cpus(unsigned in |
| { |
| int err; |
| unsigned int cpu; |
| + unsigned int this_cpu; |
| |
| init_cpu_topology(); |
| |
| - smp_store_cpu_info(smp_processor_id()); |
| + this_cpu = smp_processor_id(); |
| + store_cpu_topology(this_cpu); |
| + numa_store_cpu_info(this_cpu); |
| |
| /* |
| * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set |
| @@ -717,6 +714,7 @@ void __init smp_prepare_cpus(unsigned in |
| continue; |
| |
| set_cpu_present(cpu, true); |
| + numa_store_cpu_info(cpu); |
| } |
| } |
| |