On Mon, Feb 19, 2024 at 05:45:08PM -0800, Andrew Morton wrote: > On Mon, 19 Feb 2024 16:43:36 +0800 "Huang, Ying" <ying.huang@xxxxxxxxx> wrote: > > > > + /* > > > + * Cannot migrate to memoryless nodes. > > > + */ > > > + if (!node_state(dst_nid, N_MEMORY)) > > > + return false; > > > + > > > /* > > > * The pages in slow memory node should be migrated according > > > * to hot/cold instead of private/shared. > > > > Good catch! > > > > IIUC, you will use patch as fix to the issue in > > > > https://lore.kernel.org/lkml/20240216111502.79759-1-byungchul@xxxxxx/ > > > > If so, we need the Fixes: tag to make it land in -stable properly. > > Yes, this changelog is missing rather a lot of important information. > > I pulled together the below, please check. To make it more clear, I need to explain it more. I posted the following two patches while resolving the oops issue. However, two are going on for different purposes. 1) https://lkml.kernel.org/r/20240219041920.1183-1-byungchul@xxxxxx I started this patch as the fix for the oops. However, I found the root cause comes from using -1 as an array index. So let the root cause fix go with another thread, 2). Nevertheless, 1) is still necessary as a *reasonable optimization* but not the real fix any more. 2) https://lkml.kernel.org/r/20240216111502.79759-1-byungchul@xxxxxx I found the root cause of the oops comes from using -1 as an array index. So moved all the oops message, Fixes: tag, and cc stable to here. Long story short, 2) is the *real fix* for the oops. Byungchul > From: Byungchul Park <byungchul@xxxxxx> > Subject: sched/numa, mm: do not try to migrate memory to memoryless nodes > Date: Mon, 19 Feb 2024 13:10:47 +0900 > > With numa balancing on, when a numa system is running where a numa node > doesn't have its local memory so it has no managed zones, the following > oops has been observed. It's because wakeup_kswapd() is called with a > wrong zone index, -1. Fixed it by checking the index before calling > wakeup_kswapd(). > > > BUG: unable to handle page fault for address: 00000000000033f3 > > #PF: supervisor read access in kernel mode > > #PF: error_code(0x0000) - not-present page > > PGD 0 P4D 0 > > Oops: 0000 [#1] PREEMPT SMP NOPTI > > CPU: 2 PID: 895 Comm: masim Not tainted 6.6.0-dirty #255 > > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS > > rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 > > RIP: 0010:wakeup_kswapd (./linux/mm/vmscan.c:7812) > > Code: (omitted) > > RSP: 0000:ffffc90004257d58 EFLAGS: 00010286 > > RAX: ffffffffffffffff RBX: ffff88883fff0480 RCX: 0000000000000003 > > RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88883fff0480 > > RBP: ffffffffffffffff R08: ff0003ffffffffff R09: ffffffffffffffff > > R10: ffff888106c95540 R11: 0000000055555554 R12: 0000000000000003 > > R13: 0000000000000000 R14: 0000000000000000 R15: ffff88883fff0940 > > FS: 00007fc4b8124740(0000) GS:ffff888827c00000(0000) knlGS:0000000000000000 > > CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 > > CR2: 00000000000033f3 CR3: 000000026cc08004 CR4: 0000000000770ee0 > > DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 > > DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 > > PKRU: 55555554 > > Call Trace: > > <TASK> > > ? __die > > ? page_fault_oops > > ? __pte_offset_map_lock > > ? exc_page_fault > > ? asm_exc_page_fault > > ? wakeup_kswapd > > migrate_misplaced_page > > __handle_mm_fault > > handle_mm_fault > > do_user_addr_fault > > exc_page_fault > > asm_exc_page_fault > > RIP: 0033:0x55b897ba0808 > > Code: (omitted) > > RSP: 002b:00007ffeefa821a0 EFLAGS: 00010287 > > RAX: 000055b89983acd0 RBX: 00007ffeefa823f8 RCX: 000055b89983acd0 > > RDX: 00007fc2f8122010 RSI: 0000000000020000 RDI: 000055b89983acd0 > > RBP: 00007ffeefa821a0 R08: 0000000000000037 R09: 0000000000000075 > > R10: 0000000000000000 R11: 0000000000000202 R12: 0000000000000000 > > R13: 00007ffeefa82410 R14: 000055b897ba5dd8 R15: 00007fc4b8340000 > > </TASK> > > Fix this by avoiding any attempt to migrate memory to memoryless nodes. > > Link: https://lkml.kernel.org/r/20240219041920.1183-1-byungchul@xxxxxx > Link: https://lkml.kernel.org/r/20240216111502.79759-1-byungchul@xxxxxx > Fixes: c574bbe917036 ("NUMA balancing: optimize page placement for memory tiering system") > Signed-off-by: Byungchul Park <byungchul@xxxxxx> > Reviewed-by: Oscar Salvador <osalvador@xxxxxxx> > Reviewed-by: "Huang, Ying" <ying.huang@xxxxxxxxx> > Reviewed-by: Phil Auld <pauld@xxxxxxxxxx> > Cc: Benjamin Segall <bsegall@xxxxxxxxxx> > Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx> > Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx> > Cc: Ingo Molnar <mingo@xxxxxxxxxx> > Cc: Juri Lelli <juri.lelli@xxxxxxxxxx> > Cc: Mel Gorman <mgorman@xxxxxxx> > Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> > Cc: Steven Rostedt <rostedt@xxxxxxxxxxx> > Cc: Valentin Schneider <vschneid@xxxxxxxxxx> > Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx> > Cc: <stable@xxxxxxxxxxxxxxx> > Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> > --- > > kernel/sched/fair.c | 6 ++++++ > 1 file changed, 6 insertions(+) > > --- a/kernel/sched/fair.c~sched-numa-mm-do-not-try-to-migrate-memory-to-memoryless-nodes > +++ a/kernel/sched/fair.c > @@ -1831,6 +1831,12 @@ bool should_numa_migrate_memory(struct t > int last_cpupid, this_cpupid; > > /* > + * Cannot migrate to memoryless nodes. > + */ > + if (!node_state(dst_nid, N_MEMORY)) > + return false; > + > + /* > * The pages in slow memory node should be migrated according > * to hot/cold instead of private/shared. > */ > _
