The patch titled Subject: mm: swap: simplify struct percpu_cluster has been added to the -mm mm-unstable branch. Its filename is mm-swap-simplify-struct-percpu_cluster.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-swap-simplify-struct-percpu_cluster.patch This patch will later appear in the mm-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Ryan Roberts <ryan.roberts@xxxxxxx> Subject: mm: swap: simplify struct percpu_cluster Date: Wed, 27 Mar 2024 14:45:34 +0000 struct percpu_cluster stores the index of cpu's current cluster and the offset of the next entry that will be allocated for the cpu. These two pieces of information are redundant because the cluster index is just (offset / SWAPFILE_CLUSTER). The only reason for explicitly keeping the cluster index is because the structure used for it also has a flag to indicate "no cluster". However this data structure also contains a spin lock, which is never used in this context, as a side effect the code copies the spinlock_t structure, which is questionable coding practice in my view. So let's clean this up and store only the next offset, and use a sentinal value (SWAP_NEXT_INVALID) to indicate "no cluster". SWAP_NEXT_INVALID is chosen to be 0, because 0 will never be seen legitimately; The first page in the swap file is the swap header, which is always marked bad to prevent it from being allocated as an entry. This also prevents the cluster to which it belongs being marked free, so it will never appear on the free list. This change saves 16 bytes per cpu. And given we are shortly going to extend this mechanism to be per-cpu-AND-per-order, we will end up saving 16 * 9 = 144 bytes per cpu, which adds up if you have 256 cpus in the system. Link: https://lkml.kernel.org/r/20240327144537.4165578-4-ryan.roberts@xxxxxxx Signed-off-by: Ryan Roberts <ryan.roberts@xxxxxxx> Reviewed-by: "Huang, Ying" <ying.huang@xxxxxxxxx> Cc: Barry Song <21cnbao@xxxxxxxxx> Cc: Barry Song <v-songbaohua@xxxxxxxx> Cc: Chris Li <chrisl@xxxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: Gao Xiang <xiang@xxxxxxxxxx> Cc: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx> Cc: Lance Yang <ioworker0@xxxxxxxxx> Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxx> Cc: Yang Shi <shy828301@xxxxxxxxx> Cc: Yu Zhao <yuzhao@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/swap.h | 9 ++++++++- mm/swapfile.c | 22 +++++++++++----------- 2 files changed, 19 insertions(+), 12 deletions(-) --- a/include/linux/swap.h~mm-swap-simplify-struct-percpu_cluster +++ a/include/linux/swap.h @@ -261,12 +261,19 @@ struct swap_cluster_info { #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ /* + * The first page in the swap file is the swap header, which is always marked + * bad to prevent it from being allocated as an entry. This also prevents the + * cluster to which it belongs being marked free. Therefore 0 is safe to use as + * a sentinel to indicate next is not valid in percpu_cluster. + */ +#define SWAP_NEXT_INVALID 0 + +/* * We assign a cluster to each CPU, so each CPU can allocate swap entry from * its own cluster and swapout sequentially. The purpose is to optimize swapout * throughput. */ struct percpu_cluster { - struct swap_cluster_info index; /* Current cluster index */ unsigned int next; /* Likely next allocation offset */ }; --- a/mm/swapfile.c~mm-swap-simplify-struct-percpu_cluster +++ a/mm/swapfile.c @@ -609,7 +609,7 @@ scan_swap_map_ssd_cluster_conflict(struc return false; percpu_cluster = this_cpu_ptr(si->percpu_cluster); - cluster_set_null(&percpu_cluster->index); + percpu_cluster->next = SWAP_NEXT_INVALID; return true; } @@ -622,14 +622,14 @@ static bool scan_swap_map_try_ssd_cluste { struct percpu_cluster *cluster; struct swap_cluster_info *ci; - unsigned long tmp, max; + unsigned int tmp, max; new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); - if (cluster_is_null(&cluster->index)) { + tmp = cluster->next; + if (tmp == SWAP_NEXT_INVALID) { if (!cluster_list_empty(&si->free_clusters)) { - cluster->index = si->free_clusters.head; - cluster->next = cluster_next(&cluster->index) * + tmp = cluster_next(&si->free_clusters.head) * SWAPFILE_CLUSTER; } else if (!cluster_list_empty(&si->discard_clusters)) { /* @@ -649,9 +649,7 @@ new_cluster: * Other CPUs can use our cluster if they can't find a free cluster, * check if there is still free entry in the cluster */ - tmp = cluster->next; - max = min_t(unsigned long, si->max, - (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER); + max = min_t(unsigned long, si->max, ALIGN(tmp + 1, SWAPFILE_CLUSTER)); if (tmp < max) { ci = lock_cluster(si, tmp); while (tmp < max) { @@ -662,12 +660,13 @@ new_cluster: unlock_cluster(ci); } if (tmp >= max) { - cluster_set_null(&cluster->index); + cluster->next = SWAP_NEXT_INVALID; goto new_cluster; } - cluster->next = tmp + 1; *offset = tmp; *scan_base = tmp; + tmp += 1; + cluster->next = tmp < max ? tmp : SWAP_NEXT_INVALID; return true; } @@ -3138,8 +3137,9 @@ SYSCALL_DEFINE2(swapon, const char __use } for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; + cluster = per_cpu_ptr(p->percpu_cluster, cpu); - cluster_set_null(&cluster->index); + cluster->next = SWAP_NEXT_INVALID; } } else { atomic_inc(&nr_rotate_swap); _ Patches currently in -mm which might be from ryan.roberts@xxxxxxx are mm-swap-remove-cluster_flag_huge-from-swap_cluster_info-flags.patch mm-swap-free_swap_and_cache_nr-as-batched-free_swap_and_cache.patch mm-swap-simplify-struct-percpu_cluster.patch mm-swap-allow-storage-of-all-mthp-orders.patch mm-vmscan-avoid-split-during-shrink_folio_list.patch mm-madvise-avoid-split-during-madv_pageout-and-madv_cold.patch