On Thu, Jan 02, 2025 at 04:40:17PM +0800, Baolin Wang wrote: > With fast swap devices (such as zram), swapin latency is crucial to applications. > For shmem swapin, similar to anonymous memory swapin, we can skip the swapcache > operation to improve swapin latency. OK, but now we have more complexity. Why can't we always skip the swapcache on swapin? (Actually, I think we can always skip the swapcache on swapout too, but that's a different matter). > +static struct folio *shmem_swap_alloc_folio(struct inode *inode, struct vm_area_struct *vma, > + pgoff_t index, swp_entry_t entry, int order, gfp_t gfp) Please wrap at 80 columns and use two tabs for indenting subsequent lines. ie: static struct folio *shmem_swap_alloc_folio(struct inode *inode, struct vm_area_struct *vma, pgoff_t index, swp_entry_t entry, int order, gfp_t gfp)
