From: Leo Yan leo.yan@linaro.org
[ Upstream commit dce088ab0d51ae3b14fb2bd608e9c649aadfe5dc ]
Commit 11e9734bcb6a7361 ("mm/slab_common: unify NUMA and UMA version of tracepoints") adds the field "node" into the tracepoints 'kmalloc' and 'kmem_cache_alloc', so this patch modifies the event process function to support the field "node".
If field "node" is detected by checking function evsel__field(), it stats the cross allocation.
When the "node" value is NUMA_NO_NODE (-1), it means the memory can be allocated from any memory node, in this case, we don't account it as a cross allocation.
Fixes: 11e9734bcb6a7361 ("mm/slab_common: unify NUMA and UMA version of tracepoints") Reported-by: Ravi Bangoria ravi.bangoria@amd.com Reviewed-by: James Clark james.clark@arm.com Signed-off-by: Leo Yan leo.yan@linaro.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Hyeonggon Yoo 42.hyeyoo@gmail.com Cc: Ingo Molnar mingo@redhat.com Cc: Jiri Olsa jolsa@kernel.org Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Vlastimil Babka vbabka@suse.cz Link: https://lore.kernel.org/r/20230108062400.250690-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/builtin-kmem.c | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 63c759edb8bc..40dd52acc48a 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -26,6 +26,7 @@ #include "util/string2.h"
#include <linux/kernel.h> +#include <linux/numa.h> #include <linux/rbtree.h> #include <linux/string.h> #include <linux/zalloc.h> @@ -184,22 +185,33 @@ static int evsel__process_alloc_event(struct evsel *evsel, struct perf_sample *s total_allocated += bytes_alloc;
nr_allocs++; - return 0; -}
-static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_sample *sample) -{ - int ret = evsel__process_alloc_event(evsel, sample); + /* + * Commit 11e9734bcb6a ("mm/slab_common: unify NUMA and UMA + * version of tracepoints") adds the field "node" into the + * tracepoints 'kmalloc' and 'kmem_cache_alloc'. + * + * The legacy tracepoints 'kmalloc_node' and 'kmem_cache_alloc_node' + * also contain the field "node". + * + * If the tracepoint contains the field "node" the tool stats the + * cross allocation. + */ + if (evsel__field(evsel, "node")) { + int node1, node2;
- if (!ret) { - int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}), - node2 = evsel__intval(evsel, sample, "node"); + node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}); + node2 = evsel__intval(evsel, sample, "node");
- if (node1 != node2) + /* + * If the field "node" is NUMA_NO_NODE (-1), we don't take it + * as a cross allocation. + */ + if ((node2 != NUMA_NO_NODE) && (node1 != node2)) nr_cross_allocs++; }
- return ret; + return 0; }
static int ptr_cmp(void *, void *); @@ -1368,8 +1380,8 @@ static int __cmd_kmem(struct perf_session *session) /* slab allocator */ { "kmem:kmalloc", evsel__process_alloc_event, }, { "kmem:kmem_cache_alloc", evsel__process_alloc_event, }, - { "kmem:kmalloc_node", evsel__process_alloc_node_event, }, - { "kmem:kmem_cache_alloc_node", evsel__process_alloc_node_event, }, + { "kmem:kmalloc_node", evsel__process_alloc_event, }, + { "kmem:kmem_cache_alloc_node", evsel__process_alloc_event, }, { "kmem:kfree", evsel__process_free_event, }, { "kmem:kmem_cache_free", evsel__process_free_event, }, /* page allocator */