Re: [PATCH v3 0/6] mm: Further memory block device cleanups

[Qian Cai]

On Fri, 2019-06-21 at 20:56 +0200, David Hildenbrand wrote:
> On 21.06.19 20:24, David Hildenbrand wrote:
> > On 21.06.19 17:15, Qian Cai wrote:
> > > On Thu, 2019-06-20 at 20:31 +0200, David Hildenbrand wrote:
> > > > @Andrew: Only patch 1, 4 and 6 changed compared to v1.
> > > > 
> > > > Some further cleanups around memory block devices. Especially, clean up
> > > > and simplify walk_memory_range(). Including some other minor cleanups.
> > > > 
> > > > Compiled + tested on x86 with DIMMs under QEMU. Compile-tested on ppc64.
> > > > 
> > > > v2 -> v3:
> > > > - "mm/memory_hotplug: Rename walk_memory_range() and pass start+size .."
> > > > -- Avoid warning on ppc.
> > > > - "drivers/base/memory.c: Get rid of find_memory_block_hinted()"
> > > > -- Fixup a comment regarding hinted devices.
> > > > 
> > > > v1 -> v2:
> > > > - "mm: Section numbers use the type "unsigned long""
> > > > -- "unsigned long i" -> "unsigned long nr", in one case -> "int i"
> > > > - "drivers/base/memory.c: Get rid of find_memory_block_hinted("
> > > > -- Fix compilation error
> > > > -- Get rid of the "hint" parameter completely
> > > > 
> > > > David Hildenbrand (6):
> > > > Â mm: Section numbers use the type "unsigned long"
> > > > Â drivers/base/memory: Use "unsigned long" for block ids
> > > > Â mm: Make register_mem_sect_under_node() static
> > > > Â mm/memory_hotplug: Rename walk_memory_range() and pass start+size
> > > > ÂÂÂÂinstead of pfns
> > > > Â mm/memory_hotplug: Move and simplify walk_memory_blocks()
> > > > Â drivers/base/memory.c: Get rid of find_memory_block_hinted()
> > > > 
> > > > Âarch/powerpc/platforms/powernv/memtrace.c |ÂÂ23 ++---
> > > > Âdrivers/acpi/acpi_memhotplug.cÂÂÂÂÂÂÂÂÂÂÂÂ|ÂÂ19 +---
> > > > Âdrivers/base/memory.cÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ| 120 +++++++++++++---------
> > > > Âdrivers/base/node.cÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ|ÂÂÂ8 +-
> > > > Âinclude/linux/memory.hÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ|ÂÂÂ5 +-
> > > > Âinclude/linux/memory_hotplug.hÂÂÂÂÂÂÂÂÂÂÂÂ|ÂÂÂ2 -
> > > > Âinclude/linux/mmzone.hÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ|ÂÂÂ4 +-
> > > > Âinclude/linux/node.hÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ|ÂÂÂ7 --
> > > > Âmm/memory_hotplug.cÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ|ÂÂ57 +---------
> > > > Âmm/sparse.cÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ|ÂÂ12 +--
> > > > Â10 files changed, 106 insertions(+), 151 deletions(-)
> > > > 
> > > 
> > > This series causes a few machines are unable to boot triggering endless
> > > soft
> > > lockups. Reverted those commits fixed the issue.
> > > 
> > > 97f4217d1da0 Revert "mm/memory_hotplug: rename walk_memory_range() and
> > > pass
> > > start+size instead of pfns"
> > > c608eebf33c6 Revert "mm-memory_hotplug-rename-walk_memory_range-and-pass-
> > > startsize-instead-of-pfns-fix"
> > > 34b5e4ab7558 Revert "mm/memory_hotplug: move and simplify
> > > walk_memory_blocks()"
> > > 59a9f3eec5d1 Revert "drivers/base/memory.c: Get rid of
> > > find_memory_block_hinted()"
> > > 5cfcd52288b6 Revert "drivers-base-memoryc-get-rid-of-
> > > find_memory_block_hinted-
> > > v3"
> > > 
> > > [ÂÂÂÂ4.582081][ÂÂÂÂT1] ACPI FADT declares the system doesn't support PCIe
> > > ASPM,
> > > so disable it
> > > [ÂÂÂÂ4.590405][ÂÂÂÂT1] ACPI: bus type PCI registered
> > > [ÂÂÂÂ4.592908][ÂÂÂÂT1] PCI: MMCONFIG for domain 0000 [bus 00-ff] at [mem
> > > 0x80000000-0x8fffffff] (base 0x80000000)
> > > [ÂÂÂÂ4.601860][ÂÂÂÂT1] PCI: MMCONFIG at [mem 0x80000000-0x8fffffff]
> > > reserved in
> > > E820
> > > [ÂÂÂÂ4.601860][ÂÂÂÂT1] PCI: Using configuration type 1 for base access
> > > [ÂÂÂ28.661336][ÂÂÂC16] watchdog: BUG: soft lockup - CPU#16 stuck for 22s!
> > > [swapper/0:1]
> > > [ÂÂÂ28.671351][ÂÂÂC16] Modules linked in:
> > > [ÂÂÂ28.671354][ÂÂÂC16] CPU: 16 PID: 1 Comm: swapper/0 Not tainted 5.2.0-
> > > rc5-
> > > next-20190621+ #1
> > > [ÂÂÂ28.681366][ÂÂÂC16] Hardware name: HPE ProLiant DL385 Gen10/ProLiant
> > > DL385
> > > Gen10, BIOS A40 03/09/2018
> > > [ÂÂÂ28.691334][ÂÂÂC16] RIP: 0010:_raw_spin_unlock_irqrestore+0x2f/0x40
> > > [ÂÂÂ28.701334][ÂÂÂC16] Code: 55 48 89 e5 41 54 49 89 f4 be 01 00 00 00 53
> > > 48 8b
> > > 55 08 48 89 fb 48 8d 7f 18 e8 4c 89 7d ff 48 89 df e8 94 f9 7d ff 41 54 9d
> > > <65>
> > > ff 0d c2 44 8d 48 5b 41 5c 5d c3 0f 1f 44 00 00 0f 1f 44 00 00
> > > [ÂÂÂ28.711354][ÂÂÂC16] RSP: 0018:ffff888205b27bf8 EFLAGS: 00000246
> > > ORIG_RAX:
> > > ffffffffffffff13
> > > [ÂÂÂ28.721372][ÂÂÂC16] RAX: 0000000000000000 RBX: ffff8882053d6138 RCX:
> > > ffffffffb6f2a3b8
> > > [ÂÂÂ28.731371][ÂÂÂC16] RDX: 1ffff11040a7ac27 RSI: dffffc0000000000 RDI:
> > > ffff8882053d6138
> > > [ÂÂÂ28.741371][ÂÂÂC16] RBP: ffff888205b27c08 R08: ffffed1040a7ac28 R09:
> > > ffffed1040a7ac27
> > > [ÂÂÂ28.751334][ÂÂÂC16] R10: ffffed1040a7ac27 R11: ffff8882053d613b R12:
> > > 0000000000000246
> > > [ÂÂÂ28.751370][ÂÂÂC16] R13: ffff888205b27c98 R14: ffff8884504d0a20 R15:
> > > 0000000000000000
> > > [ÂÂÂ28.761368][ÂÂÂC16] FS:ÂÂ0000000000000000(0000)
> > > GS:ffff888454500000(0000)
> > > knlGS:0000000000000000
> > > [ÂÂÂ28.771373][ÂÂÂC16] CS:ÂÂ0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > > [ÂÂÂ28.781334][ÂÂÂC16] CR2: 0000000000000000 CR3: 00000007c9012000 CR4:
> > > 00000000001406a0
> > > [ÂÂÂ28.791333][ÂÂÂC16] Call Trace:
> > > [ÂÂÂ28.791374][ÂÂÂC16]ÂÂklist_next+0xd8/0x1c0
> > > [ÂÂÂ28.791374][ÂÂÂC16]ÂÂsubsys_find_device_by_id+0x13b/0x1f0
> > > [ÂÂÂ28.801334][ÂÂÂC16]ÂÂ? bus_find_device_by_name+0x20/0x20
> > > [ÂÂÂ28.801370][ÂÂÂC16]ÂÂ? kobject_put+0x23/0x250
> > > [ÂÂÂ28.811333][ÂÂÂC16]ÂÂwalk_memory_blocks+0x6c/0xb8
> > > [ÂÂÂ28.811353][ÂÂÂC16]ÂÂ? write_policy_show+0x40/0x40
> > > [ÂÂÂ28.821334][ÂÂÂC16]ÂÂlink_mem_sections+0x7e/0xa0
> > > [ÂÂÂ28.821369][ÂÂÂC16]ÂÂ? unregister_memory_block_under_nodes+0x210/0x210
> > > [ÂÂÂ28.831353][ÂÂÂC16]ÂÂ? __register_one_node+0x3bd/0x600
> > > [ÂÂÂ28.831353][ÂÂÂC16]ÂÂtopology_init+0xbf/0x126
> > > [ÂÂÂ28.841364][ÂÂÂC16]ÂÂ? enable_cpu0_hotplug+0x1a/0x1a
> > > [ÂÂÂ28.841368][ÂÂÂC16]ÂÂdo_one_initcall+0xfe/0x45a
> > > [ÂÂÂ28.851334][ÂÂÂC16]ÂÂ? initcall_blacklisted+0x150/0x150
> > > [ÂÂÂ28.851353][ÂÂÂC16]ÂÂ? kasan_check_write+0x14/0x20
> > > [ÂÂÂ28.861333][ÂÂÂC16]ÂÂ? up_write+0x75/0x140
> > > [ÂÂÂ28.861369][ÂÂÂC16]ÂÂkernel_init_freeable+0x619/0x6ac
> > > [ÂÂÂ28.871333][ÂÂÂC16]ÂÂ? rest_init+0x188/0x188
> > > [ÂÂÂ28.871353][ÂÂÂC16]ÂÂkernel_init+0x11/0x138
> > > [ÂÂÂ28.881363][ÂÂÂC16]ÂÂ? rest_init+0x188/0x188
> > > [ÂÂÂ28.881363][ÂÂÂC16]ÂÂret_from_fork+0x22/0x40
> > > [ÂÂÂ56.661336][ÂÂÂC16] watchdog: BUG: soft lockup - CPU#16 stuck for 22s!
> > > [swapper/0:1]
> > > [ÂÂÂ56.671352][ÂÂÂC16] Modules linked in:
> > > [ÂÂÂ56.671354][ÂÂÂC16] CPU: 16 PID: 1 Comm: swapper/0 Tainted:
> > > GÂÂÂÂÂÂÂÂÂÂÂÂÂLÂÂÂÂ5.2.0-rc5-next-20190621+ #1
> > > [ÂÂÂ56.681357][ÂÂÂC16] Hardware name: HPE ProLiant DL385 Gen10/ProLiant
> > > DL385
> > > Gen10, BIOS A40 03/09/2018
> > > [ÂÂÂ56.691356][ÂÂÂC16] RIP: 0010:subsys_find_device_by_id+0x168/0x1f0
> > > [ÂÂÂ56.701334][ÂÂÂC16] Code: 48 85 c0 74 3e 48 8d 78 58 e8 14 77 ca ff 4d
> > > 8b 7e
> > > 58 4d 85 ff 74 2c 49 8d bf a0 03 00 00 e8 bf 75 ca ff 45 39 a7 a0 03 00 00
> > > <75>
> > > c9 4c 89 ff e8 0e 89 ff ff 48 85 c0 74 bc 48 89 df e8 21 3b 24
> > > [ÂÂÂ56.721333][ÂÂÂC16] RSP: 0018:ffff888205b27c68 EFLAGS: 00000287
> > > ORIG_RAX:
> > > ffffffffffffff13
> > > [ÂÂÂ56.721370][ÂÂÂC16] RAX: 0000000000000000 RBX: ffff888205b27c90 RCX:
> > > ffffffffb74c9dc1
> > > [ÂÂÂ56.731370][ÂÂÂC16] RDX: 0000000000000003 RSI: dffffc0000000000 RDI:
> > > ffff8888774ec3e0
> > > [ÂÂÂ56.741371][ÂÂÂC16] RBP: ffff888205b27cf8 R08: ffffed1040a7ac28 R09:
> > > ffffed1040a7ac27
> > > [ÂÂÂ56.751335][ÂÂÂC16] R10: ffffed1040a7ac27 R11: ffff8882053d613b R12:
> > > 0000000000085c1b
> > > [ÂÂÂ56.761334][ÂÂÂC16] R13: 1ffff11040b64f8e R14: ffff888450de4a20 R15:
> > > ffff8888774ec040
> > > [ÂÂÂ56.761372][ÂÂÂC16] FS:ÂÂ0000000000000000(0000)
> > > GS:ffff888454500000(0000)
> > > knlGS:0000000000000000
> > > [ÂÂÂ56.771374][ÂÂÂC16] CS:ÂÂ0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> > > [ÂÂÂ56.781370][ÂÂÂC16] CR2: 0000000000000000 CR3: 00000007c9012000 CR4:
> > > 00000000001406a0
> > > [ÂÂÂ56.791373][ÂÂÂC16] Call Trace:
> > > [ÂÂÂ56.791373][ÂÂÂC16]ÂÂ? bus_find_device_by_name+0x20/0x20
> > > [ÂÂÂ56.801334][ÂÂÂC16]ÂÂ? kobject_put+0x23/0x250
> > > [ÂÂÂ56.801334][ÂÂÂC16]ÂÂwalk_memory_blocks+0x6c/0xb8
> > > [ÂÂÂ56.811333][ÂÂÂC16]ÂÂ? write_policy_show+0x40/0x40
> > > [ÂÂÂ56.811353][ÂÂÂC16]ÂÂlink_mem_sections+0x7e/0xa0
> > > [ÂÂÂ56.811353][ÂÂÂC16]ÂÂ? unregister_memory_block_under_nodes+0x210/0x210
> > > [ÂÂÂ56.821333][ÂÂÂC16]ÂÂ? __register_one_node+0x3bd/0x600
> > > [ÂÂÂ56.831333][ÂÂÂC16]ÂÂtopology_init+0xbf/0x126
> > > [ÂÂÂ56.831355][ÂÂÂC16]ÂÂ? enable_cpu0_hotplug+0x1a/0x1a
> > > [ÂÂÂ56.841334][ÂÂÂC16]ÂÂdo_one_initcall+0xfe/0x45a
> > > [ÂÂÂ56.841334][ÂÂÂC16]ÂÂ? initcall_blacklisted+0x150/0x150
> > > [ÂÂÂ56.851333][ÂÂÂC16]ÂÂ? kasan_check_write+0x14/0x20
> > > [ÂÂÂ56.851354][ÂÂÂC16]ÂÂ? up_write+0x75/0x140
> > > [ÂÂÂ56.861333][ÂÂÂC16]ÂÂkernel_init_freeable+0x619/0x6ac
> > > [ÂÂÂ56.861333][ÂÂÂC16]ÂÂ? rest_init+0x188/0x188
> > > [ÂÂÂ56.861369][ÂÂÂC16]ÂÂkernel_init+0x11/0x138
> > > [ÂÂÂ56.871333][ÂÂÂC16]ÂÂ? rest_init+0x188/0x188
> > > [ÂÂÂ56.871354][ÂÂÂC16]ÂÂret_from_fork+0x22/0x40
> > > [ÂÂÂ64.601362][ÂÂÂC16] rcu: INFO: rcu_sched self-detected stall on CPU
> > > [ÂÂÂ64.611335][ÂÂÂC16] rcu:Â	16-....: (5958 ticks this GP)
> > > idle=37e/1/0x4000000000000002 softirq=27/27 fqs=3000Â
> > > [ÂÂÂ64.621334][ÂÂÂC16]Â	(t=6002 jiffies g=-1079 q=25)
> > > [ÂÂÂ64.621334][ÂÂÂC16] NMI backtrace for cpu 16
> > > [ÂÂÂ64.621374][ÂÂÂC16] CPU: 16 PID: 1 Comm: swapper/0 Tainted:
> > > GÂÂÂÂÂÂÂÂÂÂÂÂÂLÂÂÂÂ5.2.0-rc5-next-20190621+ #1
> > > [ÂÂÂ64.631372][ÂÂÂC16] Hardware name: HPE ProLiant DL385 Gen10/ProLiant
> > > DL385
> > > Gen10, BIOS A40 03/09/2018
> > > [ÂÂÂ64.641371][ÂÂÂC16] Call Trace:
> > > [ÂÂÂ64.651337][ÂÂÂC16]ÂÂ<IRQ>
> > > [ÂÂÂ64.651376][ÂÂÂC16]ÂÂdump_stack+0x62/0x9a
> > > [ÂÂÂ64.651376][ÂÂÂC16]ÂÂnmi_cpu_backtrace.cold.0+0x2e/0x33
> > > [ÂÂÂ64.661337][ÂÂÂC16]ÂÂ? nmi_cpu_backtrace_handler+0x20/0x20
> > > [ÂÂÂ64.661337][ÂÂÂC16]ÂÂnmi_trigger_cpumask_backtrace+0x1a6/0x1b9
> > > [ÂÂÂ64.671353][ÂÂÂC16]ÂÂarch_trigger_cpumask_backtrace+0x19/0x20
> > > [ÂÂÂ64.681366][ÂÂÂC16]ÂÂrcu_dump_cpu_stacks+0x18b/0x1d6
> > > [ÂÂÂ64.681366][ÂÂÂC16]ÂÂrcu_sched_clock_irq.cold.64+0x368/0x791
> > > [ÂÂÂ64.691336][ÂÂÂC16]ÂÂ? kasan_check_read+0x11/0x20
> > > [ÂÂÂ64.691354][ÂÂÂC16]ÂÂ? __raise_softirq_irqoff+0x66/0x150
> > > [ÂÂÂ64.701336][ÂÂÂC16]ÂÂupdate_process_times+0x2f/0x60
> > > [ÂÂÂ64.701362][ÂÂÂC16]ÂÂtick_periodic+0x38/0xe0
> > > [ÂÂÂ64.711334][ÂÂÂC16]ÂÂtick_handle_periodic+0x2e/0x80
> > > [ÂÂÂ64.711353][ÂÂÂC16]ÂÂsmp_apic_timer_interrupt+0xfb/0x370
> > > [ÂÂÂ64.721367][ÂÂÂC16]ÂÂapic_timer_interrupt+0xf/0x20
> > > [ÂÂÂ64.721367][ÂÂÂC16]ÂÂ</IRQ>
> > > [ÂÂÂ64.721367][ÂÂÂC16] RIP: 0010:_raw_spin_unlock_irqrestore+0x2f/0x40
> > > [ÂÂÂ64.731370][ÂÂÂC16] Code: 55 48 89 e5 41 54 49 89 f4 be 01 00 00 00 53Â
> > > 
> > 
> > @Qian Cai, unfortunately I can't reproduce.
> > 
> > If you get the chance, it would be great if you could retry with
> > 
> > diff --git a/drivers/base/memory.c b/drivers/base/memory.c
> > index 972c5336bebf..742f99ddd148 100644
> > --- a/drivers/base/memory.c
> > +++ b/drivers/base/memory.c
> > @@ -868,6 +868,9 @@ int walk_memory_blocks(unsigned long start, unsigned
> > long size,
> > ÂÂÂÂÂÂÂÂunsigned long block_id;
> > ÂÂÂÂÂÂÂÂint ret = 0;
> > 
> > +ÂÂÂÂÂÂÂif (!size)
> > +ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂreturn;
> > +
> > ÂÂÂÂÂÂÂÂfor (block_id = start_block_id; block_id <= end_block_id;
> > block_id++) {
> > ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂmem = find_memory_block_by_id(block_id);
> > ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂif (!mem)
> > 
> > 
> > 
> > If both, start and size are 0, we would get a veeeery long loop. This
> > would mean that we have an online node that does not span any pages at
> > all (pgdat->node_start_pfn = 0, start_pfn + pgdat->node_spanned_pages = 0).
> > 
> 
> 
> ...trying to reproduce with QEMU (setting 0MB for the second node):
> 
> qemu-system-x86_64 --enable-kvm -m 4G,maxmem=20G,slots=2 \
> 	-smp sockets=2,cores=1 \
> 	-numa node,nodeid=0,cpus=0,mem=4G \
> 	-numa node,nodeid=1,cpus=1,mem=0 ...
> 
> I can indeed see that the node is online and
> "pgdat->node_start_pfn == 0 && start_pfn + pgdat->node_spanned_pages == 0".
> 
> However, the kernel segfaults in an unrelated code path, so I can't
> verify if this solves this problem:
> 
> [ÂÂÂÂ0.313284] BUG: kernel NULL pointer dereference, address: 00000000000000a0
> [ÂÂÂÂ0.313479] #PF: supervisor read access in kernel mode
> [ÂÂÂÂ0.313479] #PF: error_code(0x0000) - not-present page
> [ÂÂÂÂ0.313479] PGD 0 P4D 0Â
> [ÂÂÂÂ0.313479] Oops: 0000 [#1] SMP PTI
> [ÂÂÂÂ0.313479] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.2.0-rc5-next-
> 20190620+ #56
> [ÂÂÂÂ0.313479] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
> rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.4
> [ÂÂÂÂ0.313479] RIP: 0010:bus_add_device+0x59/0x110
> [ÂÂÂÂ0.313479] Code: 20 48 89 df e8 f8 b4 ff ff 41 89 c4 85 c0 0f 85 81 00 00
> 00 48 8b 53 50 48 85 d2 75 03 48 8b 135
> [ÂÂÂÂ0.313479] RSP: 0000:ffffb4a6c0013e20 EFLAGS: 00010246
> [ÂÂÂÂ0.313479] RAX: 0000000000000000 RBX: ffff8b61bac23800 RCX:
> 0000000000000000
> [ÂÂÂÂ0.313479] RDX: ffff8b61bac29038 RSI: ffff8b61bac23800 RDI:
> ffff8b61bac23800
> [ÂÂÂÂ0.313479] RBP: ffffffff9d2f4500 R08: 0000000000000000 R09:
> 0000000000000001
> [ÂÂÂÂ0.313479] R10: 0000000000000000 R11: ffff8b61bad20878 R12:
> 0000000000000000
> [ÂÂÂÂ0.313479] R13: 0000000000000000 R14: 0000000000000000 R15:
> 0000000000000000
> [ÂÂÂÂ0.313479] FS:ÂÂ0000000000000000(0000) GS:ffff8b61bba00000(0000)
> knlGS:0000000000000000
> [ÂÂÂÂ0.313479] CS:ÂÂ0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ÂÂÂÂ0.313479] CR2: 00000000000000a0 CR3: 0000000013c24000 CR4:
> 00000000000006f0
> [ÂÂÂÂ0.313479] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
> 0000000000000000
> [ÂÂÂÂ0.313479] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
> 0000000000000400
> [ÂÂÂÂ0.313479] Call Trace:
> [ÂÂÂÂ0.313479]ÂÂdevice_add+0x304/0x660
> [ÂÂÂÂ0.313479]ÂÂ? __init_waitqueue_head+0x31/0x50
> [ÂÂÂÂ0.313479]ÂÂ__register_one_node+0x67/0x170
> [ÂÂÂÂ0.313479]ÂÂ__try_online_node.cold+0x3e/0x78
> [ÂÂÂÂ0.313479]ÂÂtry_online_node+0x25/0x40
> [ÂÂÂÂ0.313479]ÂÂdo_cpu_up+0x36/0xc0
> [ÂÂÂÂ0.313479]ÂÂsmp_init+0x59/0xb3
> [ÂÂÂÂ0.313479]ÂÂkernel_init_freeable+0x11a/0x247
> [ÂÂÂÂ0.313479]ÂÂ? rest_init+0x23f/0x23f
> [ÂÂÂÂ0.313479]ÂÂkernel_init+0x5/0xf1
> [ÂÂÂÂ0.313479]ÂÂret_from_fork+0x3a/0x50
> [ÂÂÂÂ0.313479] Modules linked in:
> 
> Figuring out what goes wrong here (maybe QEMU creating a weird
> system configuration) is a different journey :)
> 

That is a separate issue need to revert,

"x86, numa: always initialize all possible nodes"

and then, you should be able to reproduce.