percpu: add tracepoint support for percpu memory

Add support for tracepoints to the following events: chunk allocation,
chunk free, area allocation, area free, and area allocation failure.
This should let us replay percpu memory requests and evaluate
corresponding decisions.

Signed-off-by: Dennis Zhou <dennisz@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

3 files changed, 16 insertions, 0 deletions

diff --git a/mm/percpu-km.c b/mm/percpu-km.c
index 3bbfa0c..2b79e43 100644
--- a/mm/percpu-km.c
+++ b/mm/percpu-km.c
@@ -73,6 +73,7 @@ static struct pcpu_chunk *pcpu_create_chunk(void)
 	spin_unlock_irq(&pcpu_lock);
 
 	pcpu_stats_chunk_alloc();
+	trace_percpu_create_chunk(chunk->base_addr);
 
 	return chunk;
 }
@@ -82,6 +83,7 @@ static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
 	const int nr_pages = pcpu_group_sizes[0] >> PAGE_SHIFT;
 
 	pcpu_stats_chunk_dealloc();
+	trace_percpu_destroy_chunk(chunk->base_addr);
 
 	if (chunk && chunk->data)
 		__free_pages(chunk->data, order_base_2(nr_pages));
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 5915a22..7ad9d94 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -345,6 +345,7 @@ static struct pcpu_chunk *pcpu_create_chunk(void)
 	chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0];
 
 	pcpu_stats_chunk_alloc();
+	trace_percpu_create_chunk(chunk->base_addr);
 
 	return chunk;
 }
@@ -352,6 +353,7 @@ static struct pcpu_chunk *pcpu_create_chunk(void)
 static void pcpu_destroy_chunk(struct pcpu_chunk *chunk)
 {
 	pcpu_stats_chunk_dealloc();
+	trace_percpu_destroy_chunk(chunk->base_addr);
 
 	if (chunk && chunk->data)
 		pcpu_free_vm_areas(chunk->data, pcpu_nr_groups);
diff --git a/mm/percpu.c b/mm/percpu.c
index 44a1cad..a5bc363 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -76,6 +76,9 @@
 #include <asm/tlbflush.h>
 #include <asm/io.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/percpu.h>
+
 #include "percpu-internal.h"
 
 #define PCPU_SLOT_BASE_SHIFT		5	/* 1-31 shares the same slot */
@@ -1015,11 +1018,17 @@ area_found:
 
 	ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
 	kmemleak_alloc_percpu(ptr, size, gfp);
+
+	trace_percpu_alloc_percpu(reserved, is_atomic, size, align,
+			chunk->base_addr, off, ptr);
+
 	return ptr;
 
 fail_unlock:
 	spin_unlock_irqrestore(&pcpu_lock, flags);
 fail:
+	trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align);
+
 	if (!is_atomic && warn_limit) {
 		pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
 			size, align, is_atomic, err);
@@ -1269,6 +1278,8 @@ void free_percpu(void __percpu *ptr)
 			}
 	}
 
+	trace_percpu_free_percpu(chunk->base_addr, off, ptr);
+
 	spin_unlock_irqrestore(&pcpu_lock, flags);
 }
 EXPORT_SYMBOL_GPL(free_percpu);
@@ -1719,6 +1730,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	pcpu_chunk_relocate(pcpu_first_chunk, -1);
 
 	pcpu_stats_chunk_alloc();
+	trace_percpu_create_chunk(base_addr);
 
 	/* we're done */
 	pcpu_base_addr = base_addr;