[PATCH v3 4/4] perf: RISC-V: add support for SSE event

["Clément Léger" <cleger@rivosinc.com>]

In order to use SSE within PMU drivers, register a SSE handler for the
local PMU event. Reuse the existing overflow IRQ handler and pass
appropriate pt_regs.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
---
 drivers/perf/riscv_pmu_sbi.c | 51 +++++++++++++++++++++++++++++-------
 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 1aa303f76cc7..bd7ab15483db 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -17,6 +17,7 @@
 #include <linux/irqdomain.h>
 #include <linux/of_irq.h>
 #include <linux/of.h>
+#include <linux/riscv_sse.h>
 #include <linux/cpu_pm.h>
 #include <linux/sched/clock.h>
 #include <linux/soc/andes/irq.h>
@@ -946,10 +947,10 @@ static void pmu_sbi_start_overflow_mask(struct riscv_pmu *pmu,
 		pmu_sbi_start_ovf_ctrs_sbi(cpu_hw_evt, ctr_ovf_mask);
 }
 
-static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
+static irqreturn_t pmu_sbi_ovf_handler(struct cpu_hw_events *cpu_hw_evt,
+				       struct pt_regs *regs, bool from_sse)
 {
 	struct perf_sample_data data;
-	struct pt_regs *regs;
 	struct hw_perf_event *hw_evt;
 	union sbi_pmu_ctr_info *info;
 	int lidx, hidx, fidx;
@@ -957,7 +958,6 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 	struct perf_event *event;
 	u64 overflow;
 	u64 overflowed_ctrs = 0;
-	struct cpu_hw_events *cpu_hw_evt = dev;
 	u64 start_clock = sched_clock();
 	struct riscv_pmu_snapshot_data *sdata = cpu_hw_evt->snapshot_addr;
 
@@ -967,13 +967,15 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 	/* Firmware counter don't support overflow yet */
 	fidx = find_first_bit(cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS);
 	if (fidx == RISCV_MAX_COUNTERS) {
-		csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num));
+		if (!from_sse)
+			csr_clear(CSR_SIP, BIT(riscv_pmu_irq_num));
 		return IRQ_NONE;
 	}
 
 	event = cpu_hw_evt->events[fidx];
 	if (!event) {
-		ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask);
+		if (!from_sse)
+			ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask);
 		return IRQ_NONE;
 	}
 
@@ -988,16 +990,16 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 
 	/*
 	 * Overflow interrupt pending bit should only be cleared after stopping
-	 * all the counters to avoid any race condition.
+	 * all the counters to avoid any race condition. When using SSE,
+	 * interrupt is cleared when stopping counters.
 	 */
-	ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask);
+	if (!from_sse)
+		ALT_SBI_PMU_OVF_CLEAR_PENDING(riscv_pmu_irq_mask);
 
 	/* No overflow bit is set */
 	if (!overflow)
 		return IRQ_NONE;
 
-	regs = get_irq_regs();
-
 	for_each_set_bit(lidx, cpu_hw_evt->used_hw_ctrs, RISCV_MAX_COUNTERS) {
 		struct perf_event *event = cpu_hw_evt->events[lidx];
 
@@ -1053,6 +1055,22 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t pmu_sbi_ovf_irq_handler(int irq, void *dev)
+{
+	return pmu_sbi_ovf_handler(dev, get_irq_regs(), false);
+}
+
+static int pmu_sbi_ovf_sse_handler(uint32_t evt, void *arg,
+				   struct pt_regs *regs)
+{
+	struct cpu_hw_events __percpu *hw_events = arg;
+	struct cpu_hw_events *hw_event = raw_cpu_ptr(hw_events);
+
+	pmu_sbi_ovf_handler(hw_event, regs, true);
+
+	return 0;
+}
+
 static int pmu_sbi_starting_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	struct riscv_pmu *pmu = hlist_entry_safe(node, struct riscv_pmu, node);
@@ -1100,9 +1118,22 @@ static int pmu_sbi_dying_cpu(unsigned int cpu, struct hlist_node *node)
 static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pdev)
 {
 	int ret;
+	struct sse_event *evt;
 	struct cpu_hw_events __percpu *hw_events = pmu->hw_events;
 	struct irq_domain *domain = NULL;
 
+	evt = sse_event_register(SBI_SSE_EVENT_LOCAL_PMU, 0,
+				 pmu_sbi_ovf_sse_handler, hw_events);
+	if (!IS_ERR(evt)) {
+		ret = sse_event_enable(evt);
+		if (!ret) {
+			pr_info("using SSE for PMU event delivery\n");
+			return 0;
+		}
+
+		sse_event_unregister(evt);
+	}
+
 	if (riscv_isa_extension_available(NULL, SSCOFPMF)) {
 		riscv_pmu_irq_num = RV_IRQ_PMU;
 		riscv_pmu_use_irq = true;
@@ -1137,7 +1168,7 @@ static int pmu_sbi_setup_irqs(struct riscv_pmu *pmu, struct platform_device *pde
 		return -ENODEV;
 	}
 
-	ret = request_percpu_irq(riscv_pmu_irq, pmu_sbi_ovf_handler, "riscv-pmu", hw_events);
+	ret = request_percpu_irq(riscv_pmu_irq, pmu_sbi_ovf_irq_handler, "riscv-pmu", hw_events);
 	if (ret) {
 		pr_err("registering percpu irq failed [%d]\n", ret);
 		return ret;
-- 
2.45.2