SBI v2.0 SBI introduced PMU snapshot feature which adds the following
features.
1. Read counter values directly from the shared memory instead of
csr read.
2. Start multiple counters with initial values with one SBI call.
These functionalities optimizes the number of traps to the higher
privilege mode. If the kernel is in VS mode while the hypervisor
deploy trap & emulate method, this would minimize all the hpmcounter
CSR read traps. If the kernel is running in S-mode, the benefits
reduced to CSR latency vs DRAM/cache latency as there is no trap
involved while accessing the hpmcounter CSRs.
In both modes, it does saves the number of ecalls while starting
multiple counter together with an initial values. This is a likely
scenario if multiple counters overflow at the same time.
Acked-by: Palmer Dabbelt <palmer@xxxxxxxxxxxx>
Reviewed-by: Anup Patel <anup@xxxxxxxxxxxxxx>
Reviewed-by: Conor Dooley <conor.dooley@xxxxxxxxxxxxx>
Signed-off-by: Atish Patra <atishp@xxxxxxxxxxxx>
---
drivers/perf/riscv_pmu.c | 1 +
drivers/perf/riscv_pmu_sbi.c | 224 +++++++++++++++++++++++++++++++--
include/linux/perf/riscv_pmu.h | 6 +
3 files changed, 219 insertions(+), 12 deletions(-)
diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c
index b4efdddb2ad9..36d348753d05 100644
--- a/drivers/perf/riscv_pmu.c
+++ b/drivers/perf/riscv_pmu.c
@@ -408,6 +408,7 @@ struct riscv_pmu *riscv_pmu_alloc(void)
cpuc->n_events = 0;
for (i = 0; i < RISCV_MAX_COUNTERS; i++)
cpuc->events[i] = NULL;
+ cpuc->snapshot_addr = NULL;
}
pmu->pmu = (struct pmu) {
.event_init = riscv_pmu_event_init,
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index f23501898657..e2881415ca0a 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -58,6 +58,9 @@ PMU_FORMAT_ATTR(event, "config:0-47");
PMU_FORMAT_ATTR(firmware, "config:63");
static bool sbi_v2_available;
+static DEFINE_STATIC_KEY_FALSE(sbi_pmu_snapshot_available);
+#define sbi_pmu_snapshot_available() \
+ static_branch_unlikely(&sbi_pmu_snapshot_available)
static struct attribute *riscv_arch_formats_attr[] = {
&format_attr_event.attr,
@@ -508,14 +511,109 @@ static int pmu_sbi_event_map(struct perf_event *event, u64 *econfig)
return ret;
}
+static void pmu_sbi_snapshot_free(struct riscv_pmu *pmu)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct cpu_hw_events *cpu_hw_evt = per_cpu_ptr(pmu->hw_events, cpu);
+
+ if (!cpu_hw_evt->snapshot_addr)
+ continue;
+
+ free_page((unsigned long)cpu_hw_evt->snapshot_addr);
+ cpu_hw_evt->snapshot_addr = NULL;
+ cpu_hw_evt->snapshot_addr_phys = 0;
+ }
+}
+
+static int pmu_sbi_snapshot_alloc(struct riscv_pmu *pmu)
+{
+ int cpu;
+ struct page *snapshot_page;
+
+ for_each_possible_cpu(cpu) {
+ struct cpu_hw_events *cpu_hw_evt = per_cpu_ptr(pmu->hw_events, cpu);
+
+ if (cpu_hw_evt->snapshot_addr)
+ continue;
+
+ snapshot_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+ if (!snapshot_page) {
+ pmu_sbi_snapshot_free(pmu);
+ return -ENOMEM;
+ }
+ cpu_hw_evt->snapshot_addr = page_to_virt(snapshot_page);
+ cpu_hw_evt->snapshot_addr_phys = page_to_phys(snapshot_page);
+ }
+
+ return 0;
+}
+
+static int pmu_sbi_snapshot_disable(void)
+{
+ struct sbiret ret;
+
+ ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_SNAPSHOT_SET_SHMEM, -1,
+ -1, 0, 0, 0, 0);
