From: Huang Ying ying.huang@intel.com
mainline inclusion from mainline-v6.7-rc1 commit 94a3bfe4073cd88b05f7fb201ea7bf9dfa2cf5d5 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8JXIR
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
This can be used to estimate the size of the data cache slice that can be used by one CPU under ideal circumstances. Both DATA caches and UNIFIED caches are used in calculation. So, the users need to consider the impact of the code cache usage.
Because the cache inclusive/non-inclusive information isn't available now, we just use the size of the per-CPU slice of LLC to make the result more predictable across architectures. This may be improved when more cache information is available in the future.
A brute-force algorithm to iterate all online CPUs is used to avoid to allocate an extra cpumask, especially in offline callback.
Link: https://lkml.kernel.org/r/20231016053002.756205-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" ying.huang@intel.com Acked-by: Mel Gorman mgorman@techsingularity.net Cc: Sudeep Holla sudeep.holla@arm.com Cc: Vlastimil Babka vbabka@suse.cz Cc: David Hildenbrand david@redhat.com Cc: Johannes Weiner jweiner@redhat.com Cc: Dave Hansen dave.hansen@linux.intel.com Cc: Michal Hocko mhocko@suse.com Cc: Pavel Tatashin pasha.tatashin@soleen.com Cc: Matthew Wilcox willy@infradead.org Cc: Christoph Lameter cl@linux.com Cc: Arjan van de Ven arjan@linux.intel.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Ze Zuo zuoze1@huawei.com --- drivers/base/cacheinfo.c | 49 ++++++++++++++++++++++++++++++++++++++- include/linux/cacheinfo.h | 1 + 2 files changed, 49 insertions(+), 1 deletion(-)
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index cbae8be1fe52..585c66fce9d9 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -898,6 +898,48 @@ static int cache_add_dev(unsigned int cpu) return rc; }
+/* + * Calculate the size of the per-CPU data cache slice. This can be + * used to estimate the size of the data cache slice that can be used + * by one CPU under ideal circumstances. UNIFIED caches are counted + * in addition to DATA caches. So, please consider code cache usage + * when use the result. + * + * Because the cache inclusive/non-inclusive information isn't + * available, we just use the size of the per-CPU slice of LLC to make + * the result more predictable across architectures. + */ +static void update_per_cpu_data_slice_size_cpu(unsigned int cpu) +{ + struct cpu_cacheinfo *ci; + struct cacheinfo *llc; + unsigned int nr_shared; + + if (!last_level_cache_is_valid(cpu)) + return; + + ci = ci_cacheinfo(cpu); + llc = per_cpu_cacheinfo_idx(cpu, cache_leaves(cpu) - 1); + + if (llc->type != CACHE_TYPE_DATA && llc->type != CACHE_TYPE_UNIFIED) + return; + + nr_shared = cpumask_weight(&llc->shared_cpu_map); + if (nr_shared) + ci->per_cpu_data_slice_size = llc->size / nr_shared; +} + +static void update_per_cpu_data_slice_size(bool cpu_online, unsigned int cpu) +{ + unsigned int icpu; + + for_each_online_cpu(icpu) { + if (!cpu_online && icpu == cpu) + continue; + update_per_cpu_data_slice_size_cpu(icpu); + } +} + static int cacheinfo_cpu_online(unsigned int cpu) { int rc = detect_cache_attributes(cpu); @@ -906,7 +948,11 @@ static int cacheinfo_cpu_online(unsigned int cpu) return rc; rc = cache_add_dev(cpu); if (rc) - free_cache_attributes(cpu); + goto err; + update_per_cpu_data_slice_size(true, cpu); + return 0; +err: + free_cache_attributes(cpu); return rc; }
@@ -916,6 +962,7 @@ static int cacheinfo_cpu_pre_down(unsigned int cpu) cpu_cache_sysfs_exit(cpu);
free_cache_attributes(cpu); + update_per_cpu_data_slice_size(false, cpu); return 0; }
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index a5cfd44fab45..d504eb4b49ab 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -73,6 +73,7 @@ struct cacheinfo {
struct cpu_cacheinfo { struct cacheinfo *info_list; + unsigned int per_cpu_data_slice_size; unsigned int num_levels; unsigned int num_leaves; bool cpu_map_populated;