6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Waiman Long longman@redhat.com
commit d75abd0d0bc29e6ebfebbf76d11b4067b35844af upstream.
The memory_failure_cpu structure is a per-cpu structure. Access to its content requires the use of get_cpu_var() to lock in the current CPU and disable preemption. The use of a regular spinlock_t for locking purpose is fine for a non-RT kernel.
Since the integration of RT spinlock support into the v5.15 kernel, a spinlock_t in a RT kernel becomes a sleeping lock and taking a sleeping lock in a preemption disabled context is illegal resulting in the following kind of warning.
[12135.732244] BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48 [12135.732248] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 270076, name: kworker/0:0 [12135.732252] preempt_count: 1, expected: 0 [12135.732255] RCU nest depth: 2, expected: 2 : [12135.732420] Hardware name: Dell Inc. PowerEdge R640/0HG0J8, BIOS 2.10.2 02/24/2021 [12135.732423] Workqueue: kacpi_notify acpi_os_execute_deferred [12135.732433] Call Trace: [12135.732436] <TASK> [12135.732450] dump_stack_lvl+0x57/0x81 [12135.732461] __might_resched.cold+0xf4/0x12f [12135.732479] rt_spin_lock+0x4c/0x100 [12135.732491] memory_failure_queue+0x40/0xe0 [12135.732503] ghes_do_memory_failure+0x53/0x390 [12135.732516] ghes_do_proc.constprop.0+0x229/0x3e0 [12135.732575] ghes_proc+0xf9/0x1a0 [12135.732591] ghes_notify_hed+0x6a/0x150 [12135.732602] notifier_call_chain+0x43/0xb0 [12135.732626] blocking_notifier_call_chain+0x43/0x60 [12135.732637] acpi_ev_notify_dispatch+0x47/0x70 [12135.732648] acpi_os_execute_deferred+0x13/0x20 [12135.732654] process_one_work+0x41f/0x500 [12135.732695] worker_thread+0x192/0x360 [12135.732715] kthread+0x111/0x140 [12135.732733] ret_from_fork+0x29/0x50 [12135.732779] </TASK>
Fix it by using a raw_spinlock_t for locking instead.
Also move the pr_err() out of the lock critical section and after put_cpu_ptr() to avoid indeterminate latency and the possibility of sleep with this call.
[longman@redhat.com: don't hold percpu ref across pr_err(), per Miaohe] Link: https://lkml.kernel.org/r/20240807181130.1122660-1-longman@redhat.com Link: https://lkml.kernel.org/r/20240806164107.1044956-1-longman@redhat.com Fixes: 0f383b6dc96e ("locking/spinlock: Provide RT variant") Signed-off-by: Waiman Long longman@redhat.com Acked-by: Miaohe Lin linmiaohe@huawei.com Cc: "Huang, Ying" ying.huang@intel.com Cc: Juri Lelli juri.lelli@redhat.com Cc: Len Brown len.brown@intel.com Cc: Naoya Horiguchi nao.horiguchi@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/memory-failure.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)
--- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2395,7 +2395,7 @@ struct memory_failure_entry { struct memory_failure_cpu { DECLARE_KFIFO(fifo, struct memory_failure_entry, MEMORY_FAILURE_FIFO_SIZE); - spinlock_t lock; + raw_spinlock_t lock; struct work_struct work; };
@@ -2421,20 +2421,22 @@ void memory_failure_queue(unsigned long { struct memory_failure_cpu *mf_cpu; unsigned long proc_flags; + bool buffer_overflow; struct memory_failure_entry entry = { .pfn = pfn, .flags = flags, };
mf_cpu = &get_cpu_var(memory_failure_cpu); - spin_lock_irqsave(&mf_cpu->lock, proc_flags); - if (kfifo_put(&mf_cpu->fifo, entry)) + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); + buffer_overflow = !kfifo_put(&mf_cpu->fifo, entry); + if (!buffer_overflow) schedule_work_on(smp_processor_id(), &mf_cpu->work); - else + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + put_cpu_var(memory_failure_cpu); + if (buffer_overflow) pr_err("buffer overflow when queuing memory failure at %#lx\n", pfn); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); - put_cpu_var(memory_failure_cpu); } EXPORT_SYMBOL_GPL(memory_failure_queue);
@@ -2447,9 +2449,9 @@ static void memory_failure_work_func(str
mf_cpu = container_of(work, struct memory_failure_cpu, work); for (;;) { - spin_lock_irqsave(&mf_cpu->lock, proc_flags); + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); gotten = kfifo_get(&mf_cpu->fifo, &entry); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); if (!gotten) break; if (entry.flags & MF_SOFT_OFFLINE) @@ -2479,7 +2481,7 @@ static int __init memory_failure_init(vo
for_each_possible_cpu(cpu) { mf_cpu = &per_cpu(memory_failure_cpu, cpu); - spin_lock_init(&mf_cpu->lock); + raw_spin_lock_init(&mf_cpu->lock); INIT_KFIFO(mf_cpu->fifo); INIT_WORK(&mf_cpu->work, memory_failure_work_func); }