[PATCH 04/14] powerpc/perf/vpa-dtl: Add support to setup and free aux buffer for capturing DTL data

[Athira Rajeev]

vpa dtl pmu has one hrtimer added per vpa-dtl pmu thread. When the
hrtimer expires, in the timer handler, code is added to save the DTL
data to perf event record. DTL (Dispatch Trace Log) contains information
about dispatch/preempt, enqueue time etc. We directly copy the DTL
buffer data as part of auxiliary buffer and it will be postprocessed
later. To enable the support for aux buffer, add the PMU callbacks for
setup_aux and free_aux.

In setup_aux, set up pmu-private data structures for an AUX
area. rb_alloc_aux uses "alloc_pages_node" and returns pointer to each
page address. Map these pages to contiguous space using vmap and use
that as base address. The aux private data structure ie,
"struct vpa_pmu_buf" mainly saves:
1. buf->base: aux buffer base address
2. buf->head: offset from base address where data will be written to.
3. buf->size: Size of allocated memory

free_aux will free pmu-private AUX data structures.

Signed-off-by: Athira Rajeev <atrajeev at linux.ibm.com>
---
 arch/powerpc/perf/vpa-dtl.c | 77 +++++++++++++++++++++++++++++++++++++
 1 file changed, 77 insertions(+)

diff --git a/arch/powerpc/perf/vpa-dtl.c b/arch/powerpc/perf/vpa-dtl.c
index e92756f88801..364242cbfa8a 100644
--- a/arch/powerpc/perf/vpa-dtl.c
+++ b/arch/powerpc/perf/vpa-dtl.c
@@ -11,6 +11,7 @@
 #include <asm/dtl.h>
 #include <linux/perf_event.h>
 #include <asm/plpar_wrappers.h>
+#include <linux/vmalloc.h>
 
 #define EVENT(_name, _code)     enum{_name = _code}
 
@@ -75,6 +76,19 @@ struct vpa_dtl {
 	bool			active_lock;
 };
 
+struct vpa_pmu_ctx {
+	struct perf_output_handle handle;
+};
+
+struct vpa_pmu_buf {
+	int     nr_pages;
+	bool    snapshot;
+	u64     *base;
+	u64     size;
+	u64     head;
+};
+
+static DEFINE_PER_CPU(struct vpa_pmu_ctx, vpa_pmu_ctx);
 static DEFINE_PER_CPU(struct vpa_dtl, vpa_dtl_cpu);
 
 /* variable to capture reference count for the active dtl threads */
@@ -311,6 +325,67 @@ static void vpa_dtl_event_read(struct perf_event *event)
 {
 }
 
+/*
+ * Set up pmu-private data structures for an AUX area
+ * **pages contains the aux buffer allocated for this event
+ * for the corresponding cpu. rb_alloc_aux uses "alloc_pages_node"
+ * and returns pointer to each page address. Map these pages to
+ * contiguous space using vmap and use that as base address.
+ *
+ * The aux private data structure ie, "struct vpa_pmu_buf" mainly
+ * saves
+ * - buf->base: aux buffer base address
+ * - buf->head: offset from base address where data will be written to.
+ * - buf->size: Size of allocated memory
+ */
+static void *vpa_dtl_setup_aux(struct perf_event *event, void **pages,
+		int nr_pages, bool snapshot)
+{
+	int i, cpu = event->cpu;
+	struct vpa_pmu_buf *buf __free(kfree) = NULL;
+	struct page **pglist __free(kfree) = NULL;
+
+	/* We need at least one page for this to work. */
+	if (!nr_pages)
+		return NULL;
+
+	if (cpu == -1)
+		cpu = raw_smp_processor_id();
+
+	buf = kzalloc_node(sizeof(*buf), GFP_KERNEL, cpu_to_node(cpu));
+	if (!buf)
+		return NULL;
+
+	pglist = kcalloc(nr_pages, sizeof(*pglist), GFP_KERNEL);
+	if (!pglist)
+		return NULL;
+
+	for (i = 0; i < nr_pages; ++i)
+		pglist[i] = virt_to_page(pages[i]);
+
+	buf->base = vmap(pglist, nr_pages, VM_MAP, PAGE_KERNEL);
+	if (!buf->base)
+		return NULL;
+
+	buf->nr_pages = nr_pages;
+	buf->snapshot = false;
+
+	buf->size = nr_pages << PAGE_SHIFT;
+	buf->head = 0;
+	return no_free_ptr(buf);
+}
+
+/*
+ * free pmu-private AUX data structures
+ */
+static void vpa_dtl_free_aux(void *aux)
+{
+	struct vpa_pmu_buf *buf = aux;
+
+	vunmap(buf->base);
+	kfree(buf);
+}
+
 static struct pmu vpa_dtl_pmu = {
 	.task_ctx_nr = perf_invalid_context,
 
@@ -320,6 +395,8 @@ static struct pmu vpa_dtl_pmu = {
 	.add         = vpa_dtl_event_add,
 	.del         = vpa_dtl_event_del,
 	.read        = vpa_dtl_event_read,
+	.setup_aux   = vpa_dtl_setup_aux,
+	.free_aux    = vpa_dtl_free_aux,
 	.capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_EXCLUSIVE,
 };
 
-- 
2.47.1