The patch titled
Subject: cacheinfo: calculate size of per-CPU data cache slice
has been added to the -mm mm-unstable branch. Its filename is
cacheinfo-calculate-size-of-per-cpu-data-cache-slice.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/cacheinfo-calculate-size-of-per-cpu-data-cache-slice.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: Huang Ying <ying.huang@xxxxxxxxx>
Subject: cacheinfo: calculate size of per-CPU data cache slice
Date: Mon, 16 Oct 2023 13:29:55 +0800
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@xxxxxxxxx
Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: Sudeep Holla <sudeep.holla@xxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Johannes Weiner <jweiner@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/base/cacheinfo.c | 49 +++++++++++++++++++++++++++++++++++-
include/linux/cacheinfo.h | 1
2 files changed, 49 insertions(+), 1 deletion(-)
--- a/drivers/base/cacheinfo.c~cacheinfo-calculate-size-of-per-cpu-data-cache-slice
+++ a/drivers/base/cacheinfo.c
@@ -898,6 +898,48 @@ err:
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
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(unsign
cpu_cache_sysfs_exit(cpu);
free_cache_attributes(cpu);
+ update_per_cpu_data_slice_size(false, cpu);
return 0;
}
--- a/include/linux/cacheinfo.h~cacheinfo-calculate-size-of-per-cpu-data-cache-slice
+++ a/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;
_
Patches currently in -mm which might be from ying.huang@xxxxxxxxx are
mm-fix-draining-remote-pageset.patch
mm-pcp-avoid-to-drain-pcp-when-process-exit.patch
cacheinfo-calculate-size-of-per-cpu-data-cache-slice.patch
mm-pcp-reduce-lock-contention-for-draining-high-order-pages.patch
mm-restrict-the-pcp-batch-scale-factor-to-avoid-too-long-latency.patch
mm-page_alloc-scale-the-number-of-pages-that-are-batch-allocated.patch
mm-add-framework-for-pcp-high-auto-tuning.patch
mm-tune-pcp-high-automatically.patch
mm-pcp-decrease-pcp-high-if-free-pages-high-watermark.patch
mm-pcp-reduce-detecting-time-of-consecutive-high-order-page-freeing.patch
