Re: [RFC v2 PATCH 2/2] mm: mmap: zap pages with read mmap_sem for large mapping

[Yang Shi <yang.shi@linux.alibaba.com>]

On 6/19/18 3:02 AM, Peter Zijlstra wrote:
> On Tue, Jun 19, 2018 at 07:34:16AM +0800, Yang Shi wrote:
>
>> diff --git a/mm/mmap.c b/mm/mmap.c
>> index fc41c05..e84f80c 100644
>> --- a/mm/mmap.c
>> +++ b/mm/mmap.c
>> @@ -2686,6 +2686,141 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
>>   	return __split_vma(mm, vma, addr, new_below);
>>   }
>>   
>> +/* Consider PUD size or 1GB mapping as large mapping */
>> +#ifdef HPAGE_PUD_SIZE
>> +#define LARGE_MAP_THRESH	HPAGE_PUD_SIZE
>> +#else
>> +#define LARGE_MAP_THRESH	(1 * 1024 * 1024 * 1024)
>> +#endif
>> +
>> +/* Unmap large mapping early with acquiring read mmap_sem */
>> +static int do_munmap_zap_early(struct mm_struct *mm, unsigned long start,
>> +			       size_t len, struct list_head *uf)
>> +{
>> +	unsigned long end = 0;
>> +	struct vm_area_struct *vma = NULL, *prev, *last, *tmp;
>> +	bool success = false;
>> +	int ret = 0;
>> +
>> +	if ((offset_in_page(start)) || start > TASK_SIZE || len > TASK_SIZE - start)
>> +		return -EINVAL;
>> +
>> +	len = (PAGE_ALIGN(len));
>> +	if (len == 0)
>> +		return -EINVAL;
>> +
>> +	/* Just deal with uf in regular path */
>> +	if (unlikely(uf))
>> +		goto regular_path;
>> +
>> +	if (len >= LARGE_MAP_THRESH) {
>> +		down_read(&mm->mmap_sem);
>> +		vma = find_vma(mm, start);
>> +		if (!vma) {
>> +			up_read(&mm->mmap_sem);
>> +			return 0;
>> +		}
>> +
>> +		prev = vma->vm_prev;
>> +
>> +		end = start + len;
>> +		if (vma->vm_start > end) {
>> +			up_read(&mm->mmap_sem);
>> +			return 0;
>> +		}
>> +
>> +		if (start > vma->vm_start) {
>> +			int error;
>> +
>> +			if (end < vma->vm_end &&
>> +			    mm->map_count > sysctl_max_map_count) {
>> +				up_read(&mm->mmap_sem);
>> +				return -ENOMEM;
>> +			}
>> +
>> +			error = __split_vma(mm, vma, start, 0);
>> +			if (error) {
>> +				up_read(&mm->mmap_sem);
>> +				return error;
>> +			}
>> +			prev = vma;
>> +		}
>> +
>> +		last = find_vma(mm, end);
>> +		if (last && end > last->vm_start) {
>> +			int error = __split_vma(mm, last, end, 1);
>> +
>> +			if (error) {
>> +				up_read(&mm->mmap_sem);
>> +				return error;
>> +			}
>> +		}
>> +		vma = prev ? prev->vm_next : mm->mmap;
> Hold up, two things: you having to copy most of do_munmap() didn't seem
> to suggest a helper function? And second, since when are we allowed to

Yes, they will be extracted into a helper function in the next version.

May bad, I don't think it is allowed. We could reform this to:

acquire write mmap_sem
vma lookup (split vmas)
release write mmap_sem

acquire read mmap_sem
zap pages
release read mmap_sem

I'm supposed this is safe as what Michal said before.

Thanks,
Yang

> split VMAs under a read lock?