From: Ryan Roberts ryan.roberts@arm.com
next inclusion from next-20240510 commit 14c62da21b2b865f4fc0c49edd74ed7299927d35 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9OCYO CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
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/20240408183946.2991168-4-ryan.roberts@arm.com Signed-off-by: Ryan Roberts ryan.roberts@arm.com Reviewed-by: "Huang, Ying" ying.huang@intel.com Cc: Barry Song 21cnbao@gmail.com Cc: Barry Song v-songbaohua@oppo.com Cc: Chris Li chrisl@kernel.org Cc: David Hildenbrand david@redhat.com Cc: Gao Xiang xiang@kernel.org Cc: Kefeng Wang wangkefeng.wang@huawei.com Cc: Lance Yang ioworker0@gmail.com Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: Michal Hocko mhocko@suse.com Cc: Yang Shi shy828301@gmail.com Cc: Yu Zhao yuzhao@google.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Liu Shixin liushixin2@huawei.com --- include/linux/swap.h | 9 ++++++++- mm/swapfile.c | 22 +++++++++++----------- 2 files changed, 19 insertions(+), 12 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h index 90d546caa0ec..bb5de1f0eeb9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -272,13 +272,20 @@ struct swap_cluster_info { #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #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 */ };
diff --git a/mm/swapfile.c b/mm/swapfile.c index beaef7521469..ae9660cf3676 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -608,7 +608,7 @@ scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, return false;
percpu_cluster = this_cpu_ptr(si->percpu_cluster); - cluster_set_null(&percpu_cluster->index); + percpu_cluster->next = SWAP_NEXT_INVALID; return true; }
@@ -621,14 +621,14 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, { 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)) { /* @@ -648,9 +648,7 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, * 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) { @@ -661,12 +659,13 @@ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, 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; }
@@ -3244,8 +3243,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) } 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);