From: Youngjun Park From: Youngjun Park find_next_to_unuse() walks every offset from 0 to si->max, and swapoff restarts that walk on each retry, so the cost scales with the size of the device rather than with the few slots the shmem and mmlist passes could not free. It has caused stalls before. The flat walk predates the swap table. Slot state now lives in a per cluster table, and wait_for_allocation() stops all allocation before try_to_unuse() runs, so a cluster that holds no slot in use stays that way. Skip such a cluster with cluster_is_empty() instead of reading all of its entries. Commit dc644a073769 ("mm: add three more cond_resched() in swapoff") answered those stalls with a cond_resched() every 256 offsets. A walk bounded by one cluster no longer needs that counter. The loop now runs at most SWAPFILE_CLUSTER times before it returns or reschedules, the same bound swap_reclaim_full_clusters() already scans between cond_resched() calls. cluster_is_empty() reads ci->count without ci->lock, like the rest of this scan. A slot stops being counted only after its folio has left the swap cache, so an empty cluster holds nothing for try_to_unuse() to act on and skipping it loses no work. Signed-off-by: Youngjun Park --- mm/swapfile.c | 39 ++++++++++++++++++++++++++------------- 1 file changed, 26 insertions(+), 13 deletions(-) diff --git a/mm/swapfile.c b/mm/swapfile.c index 5d15913dcf86..230abb276ceb 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -370,8 +370,6 @@ static void discard_swap_cluster(struct swap_info_struct *si, } } -#define LATENCY_LIMIT 256 - static inline bool cluster_is_empty(struct swap_cluster_info *info) { return info->count == 0; @@ -2763,7 +2761,9 @@ static int unuse_mm(struct mm_struct *mm, unsigned int type) static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev) { - unsigned int i; + struct swap_cluster_info *ci; + unsigned long i, end; + unsigned int ci_off; unsigned long swp_tb; /* @@ -2772,19 +2772,32 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ - for (i = prev + 1; i < si->max; i++) { - swp_tb = swap_table_get(__swap_offset_to_cluster(si, i), - i % SWAPFILE_CLUSTER); - if (!swp_tb_is_null(swp_tb) && !swp_tb_is_bad(swp_tb)) - break; - if ((i % LATENCY_LIMIT) == 0) + i = prev + 1; + while (i < si->max) { + ci = __swap_offset_to_cluster(si, i); + ci_off = i % SWAPFILE_CLUSTER; + end = min(si->max, i - ci_off + SWAPFILE_CLUSTER); + + /* + * An empty cluster has no slot in use, so skip it whole. + * A slot is uncounted only after its folio left the swap + * cache, so there is nothing here for try_to_unuse() to act on. + */ + if (cluster_is_empty(ci)) { + i = end; cond_resched(); - } + continue; + } - if (i == si->max) - i = 0; + for (; i < end; ci_off++, i++) { + swp_tb = swap_table_get(ci, ci_off); + if (!swp_tb_is_null(swp_tb) && !swp_tb_is_bad(swp_tb)) + return i; + } + cond_resched(); + } - return i; + return 0; } static int try_to_unuse(unsigned int type) -- 2.48.1