On Mon, 12 Aug 2024, Baolin Wang wrote:
> Now the swap device can only swap-in order 0 folio, even though a large
> folio is swapped out. This requires us to split the large entry previously
> saved in the shmem pagecache to support the swap in of small folios.
>
> Signed-off-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
> ---
> mm/shmem.c | 100 +++++++++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 100 insertions(+)
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 345e25425e37..996062dc196b 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1990,6 +1990,81 @@ static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index,
> swap_free_nr(swap, nr_pages);
> }
>
> +static int shmem_split_large_entry(struct inode *inode, pgoff_t index,
> + swp_entry_t swap, int new_order, gfp_t gfp)
> +{
> + struct address_space *mapping = inode->i_mapping;
> + XA_STATE_ORDER(xas, &mapping->i_pages, index, new_order);
> + void *alloced_shadow = NULL;
> + int alloced_order = 0, i;
gfp needs to be adjusted: see fix patch below.
> +
> + for (;;) {
> + int order = -1, split_order = 0;
> + void *old = NULL;
> +
> + xas_lock_irq(&xas);
> + old = xas_load(&xas);
> + if (!xa_is_value(old) || swp_to_radix_entry(swap) != old) {
> + xas_set_err(&xas, -EEXIST);
> + goto unlock;
> + }
> +
> + order = xas_get_order(&xas);
> +
> + /* Swap entry may have changed before we re-acquire the lock */
> + if (alloced_order &&
> + (old != alloced_shadow || order != alloced_order)) {
> + xas_destroy(&xas);
> + alloced_order = 0;
> + }
> +
> + /* Try to split large swap entry in pagecache */
> + if (order > 0 && order > new_order) {
I have not even attempted to understand all the manipulations of order and
new_order and alloced_order and split_order. And further down it turns out
that this is only ever called with new_order 0.
You may be wanting to cater for more generality in future, but for now
please cut this down to the new_order 0 case, and omit that parameter.
It will be easier for us to think about the xa_get_order() races if
the possibilities are more limited.
> + if (!alloced_order) {
> + split_order = order;
> + goto unlock;
> + }
> + xas_split(&xas, old, order);
> +
> + /*
> + * Re-set the swap entry after splitting, and the swap
> + * offset of the original large entry must be continuous.
> + */
> + for (i = 0; i < 1 << order; i += (1 << new_order)) {
> + pgoff_t aligned_index = round_down(index, 1 << order);
> + swp_entry_t tmp;
> +
> + tmp = swp_entry(swp_type(swap), swp_offset(swap) + i);
> + __xa_store(&mapping->i_pages, aligned_index + i,
> + swp_to_radix_entry(tmp), 0);
> + }
So that is done under xas lock: good. But is the intermediate state
visible to RCU readers, and could that be a problem?
> + }
> +
> +unlock:
> + xas_unlock_irq(&xas);
> +
> + /* split needed, alloc here and retry. */
> + if (split_order) {
> + xas_split_alloc(&xas, old, split_order, gfp);
> + if (xas_error(&xas))
> + goto error;
> + alloced_shadow = old;
> + alloced_order = split_order;
> + xas_reset(&xas);
> + continue;
> + }
> +
> + if (!xas_nomem(&xas, gfp))
> + break;
> + }
> +
> +error:
> + if (xas_error(&xas))
> + return xas_error(&xas);
> +
> + return alloced_order;
> +}
> +
> /*
> * Swap in the folio pointed to by *foliop.
> * Caller has to make sure that *foliop contains a valid swapped folio.
> @@ -2026,12 +2101,37 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
> /* Look it up and read it in.. */
> folio = swap_cache_get_folio(swap, NULL, 0);
> if (!folio) {
> + int split_order;
> +
> /* Or update major stats only when swapin succeeds?? */
> if (fault_type) {
> *fault_type |= VM_FAULT_MAJOR;
> count_vm_event(PGMAJFAULT);
> count_memcg_event_mm(fault_mm, PGMAJFAULT);
> }
> +
> + /*
> + * Now swap device can only swap in order 0 folio, then we
> + * should split the large swap entry stored in the pagecache
> + * if necessary.
> + */
> + split_order = shmem_split_large_entry(inode, index, swap, 0, gfp);
> + if (split_order < 0) {
> + error = split_order;
> + goto failed;
> + }
> +
> + /*
> + * If the large swap entry has already been split, it is
> + * necessary to recalculate the new swap entry based on
> + * the old order alignment.
> + */
> + if (split_order > 0) {
> + pgoff_t offset = index - round_down(index, 1 << split_order);
> +
> + swap = swp_entry(swp_type(swap), swp_offset(swap) + offset);
> + }
> +
> /* Here we actually start the io */
> folio = shmem_swapin_cluster(swap, gfp, info, index);
> if (!folio) {
> --
[PATCH] mm: shmem: split large entry if the swapin folio is not large fix
Fix all the
Unexpected gfp: 0x2 (__GFP_HIGHMEM). Fixing up to gfp: 0x1120d0
(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_HARDWALL|__GFP_RECLAIMABLE).
Fix your code!
warnings from kmalloc_fix_flags() from xas_split_alloc() from
shmem_split_large_entry().
Fixes: a960844d5ac9 ("mm: shmem: split large entry if the swapin folio is not large")
Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
---
mm/shmem.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/mm/shmem.c b/mm/shmem.c
index ae2245dce8ae..85e3bd3e709e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1999,6 +1999,9 @@ static int shmem_split_large_entry(struct inode *inode, pgoff_t index,
void *alloced_shadow = NULL;
int alloced_order = 0, i;
+ /* Convert user data gfp flags to xarray node gfp flags */
+ gfp &= GFP_RECLAIM_MASK;
+
for (;;) {
int order = -1, split_order = 0;
void *old = NULL;
--
2.35.3
