On Friday, May 1, 2020 6:45:41 PM CEST James Morse wrote:
> The GHES code calls memory_failure_queue() from IRQ context to schedule
> work on the current CPU so that memory_failure() can sleep.
>
> For synchronous memory errors the arch code needs to know any signals
> that memory_failure() will trigger are pending before it returns to
> user-space, possibly when exiting from the IRQ.
>
> Add a helper to kick the memory failure queue, to ensure the scheduled
> work has happened. This has to be called from process context, so may
> have been migrated from the original cpu. Pass the cpu the work was
> queued on.
>
> Change memory_failure_work_func() to permit being called on the 'wrong'
> cpu.
>
> Signed-off-by: James Morse <james.morse@xxxxxxx>
> Tested-by: Tyler Baicar <baicar@xxxxxxxxxxxxxxxxxxxxxx>
> ---
> include/linux/mm.h | 1 +
> mm/memory-failure.c | 15 ++++++++++++++-
> 2 files changed, 15 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 5a323422d783..c606dbbfa5e1 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -3012,6 +3012,7 @@ enum mf_flags {
> };
> extern int memory_failure(unsigned long pfn, int flags);
> extern void memory_failure_queue(unsigned long pfn, int flags);
> +extern void memory_failure_queue_kick(int cpu);
> extern int unpoison_memory(unsigned long pfn);
> extern int get_hwpoison_page(struct page *page);
> #define put_hwpoison_page(page) put_page(page)
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index a96364be8ab4..c4afb407bf0f 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -1493,7 +1493,7 @@ static void memory_failure_work_func(struct work_struct *work)
> unsigned long proc_flags;
> int gotten;
>
> - mf_cpu = this_cpu_ptr(&memory_failure_cpu);
> + mf_cpu = container_of(work, struct memory_failure_cpu, work);
> for (;;) {
> spin_lock_irqsave(&mf_cpu->lock, proc_flags);
> gotten = kfifo_get(&mf_cpu->fifo, &entry);
> @@ -1507,6 +1507,19 @@ static void memory_failure_work_func(struct work_struct *work)
> }
> }
>
> +/*
> + * Process memory_failure work queued on the specified CPU.
> + * Used to avoid return-to-userspace racing with the memory_failure workqueue.
> + */
> +void memory_failure_queue_kick(int cpu)
> +{
> + struct memory_failure_cpu *mf_cpu;
> +
> + mf_cpu = &per_cpu(memory_failure_cpu, cpu);
> + cancel_work_sync(&mf_cpu->work);
> + memory_failure_work_func(&mf_cpu->work);
> +}
> +
> static int __init memory_failure_init(void)
> {
> struct memory_failure_cpu *mf_cpu;
>
I could apply this provided an ACK from the mm people.
Thanks!
