From bbcef208c5da076d8316a07b44c5ecd3a6e23eff Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Fri, 8 May 2026 17:17:56 -0400 Subject: [PATCH] mm, swap: speed up hibernation allocation and writeout [ Upstream commit 396f57b5720024638dbb503f6a4abd988a49d815 ] Since commit 0ff67f990bd4 ("mm, swap: remove swap slot cache"), hibernation has been using the swap slot slow allocation path for simplification, which turns out might cause regression for some devices because the allocator now rotates clusters too often, leading to slower allocation and more random distribution of data. Fast allocation is not complex, so implement hibernation support as well. Test result with Samsung SSD 830 Series (SATA II, 3.0 Gbps) shows the performance is several times better [1]: 6.19: 324 seconds After this series: 35 seconds Link: https://lkml.kernel.org/r/20260216-hibernate-perf-v4-1-1ba9f0bf1ec9@tencent.com Link: https://lore.kernel.org/linux-mm/8b4bdcfa-ce3f-4e23-839f-31367df7c18f@gmx.de/ [1] Signed-off-by: Kairui Song Fixes: 0ff67f990bd4 ("mm, swap: remove swap slot cache") Reported-by: Carsten Grohmann Closes: https://lore.kernel.org/linux-mm/20260206121151.dea3633d1f0ded7bbf49c22e@linux-foundation.org/ Cc: Baoquan He Cc: Barry Song Cc: Chris Li Cc: Kemeng Shi Cc: Nhat Pham Cc: Signed-off-by: Andrew Morton [ adjusted helper signatures ] Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- mm/swapfile.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/mm/swapfile.c b/mm/swapfile.c index 89746abc4737..ca0298a840cd 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2014,8 +2014,9 @@ out: swp_entry_t get_swap_page_of_type(int type) { - struct swap_info_struct *si = swap_type_to_info(type); - unsigned long offset; + struct swap_info_struct *pcp_si, *si = swap_type_to_info(type); + unsigned long pcp_offset, offset = SWAP_ENTRY_INVALID; + struct swap_cluster_info *ci; swp_entry_t entry = {0}; if (!si) @@ -2025,11 +2026,21 @@ swp_entry_t get_swap_page_of_type(int type) if (get_swap_device_info(si)) { if (si->flags & SWP_WRITEOK) { /* - * Grab the local lock to be complaint - * with swap table allocation. + * Try the local cluster first if it matches the device. If + * not, try grab a new cluster and override local cluster. */ local_lock(&percpu_swap_cluster.lock); - offset = cluster_alloc_swap_entry(si, 0, 1); + pcp_si = this_cpu_read(percpu_swap_cluster.si[0]); + pcp_offset = this_cpu_read(percpu_swap_cluster.offset[0]); + if (pcp_si == si && pcp_offset) { + ci = swap_cluster_lock(si, pcp_offset); + if (cluster_is_usable(ci, 0)) + offset = alloc_swap_scan_cluster(si, ci, pcp_offset, 0, 1); + else + swap_cluster_unlock(ci); + } + if (!offset) + offset = cluster_alloc_swap_entry(si, 0, 1); local_unlock(&percpu_swap_cluster.lock); if (offset) entry = swp_entry(si->type, offset);