[RFC 6/7] arm64: perf: Enable pmu counter direct access for perf event on armv8

[Raphael Gault]

Keep track of event opened with direct access to the hardware counters
and modify permissions while they are open.

The strategy used here is the same which x86 uses: everytime an event
is mapped, the permissions are set if required. The atomic field added
in the mm_context helps keep track of the different event opened and
de-activate the permissions when all are unmapped.
We also need to update the permissions in the context switch code so
that tasks keep the right permissions.

Signed-off-by: Raphael Gault <raphael.gault@xxxxxxx>
---
 arch/arm64/include/asm/mmu.h         |  6 +++++
 arch/arm64/include/asm/mmu_context.h |  2 ++
 arch/arm64/include/asm/perf_event.h  | 14 ++++++++++
 drivers/perf/arm_pmu.c               | 38 ++++++++++++++++++++++++++++
 4 files changed, 60 insertions(+)

diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 67ef25d037ea..9de4cf0b17c7 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -29,6 +29,12 @@
 
 typedef struct {
 	atomic64_t	id;
+
+	/*
+	 * non-zero if userspace have access to hardware
+	 * counters directly.
+	 */
+	atomic_t	pmu_direct_access;
 	void		*vdso;
 	unsigned long	flags;
 } mm_context_t;
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 2da3e478fd8f..33494af613d8 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -32,6 +32,7 @@
 #include <asm-generic/mm_hooks.h>
 #include <asm/cputype.h>
 #include <asm/pgtable.h>
+#include <asm/perf_event.h>
 #include <asm/sysreg.h>
 #include <asm/tlbflush.h>
 
@@ -235,6 +236,7 @@ static inline void __switch_mm(struct mm_struct *next)
 	}
 
 	check_and_switch_context(next, cpu);
+	perf_switch_user_access(next);
 }
 
 static inline void
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index c593761ba61c..32a6d604bb3b 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -19,6 +19,7 @@
 
 #include <asm/stack_pointer.h>
 #include <asm/ptrace.h>
+#include <linux/mm_types.h>
 
 #define	ARMV8_PMU_MAX_COUNTERS	32
 #define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
@@ -234,4 +235,17 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 	(regs)->pstate = PSR_MODE_EL1h;	\
 }
 
+static inline void perf_switch_user_access(struct mm_struct *mm)
+{
+	if (!IS_ENABLED(CONFIG_PERF_EVENTS))
+		return;
+
+	if (atomic_read(&mm->context.pmu_direct_access)) {
+		write_sysreg(ARMV8_PMU_USERENR_ER|ARMV8_PMU_USERENR_CR,
+			     pmuserenr_el0);
+	} else {
+		write_sysreg(0, pmuserenr_el0);
+	}
+}
+
 #endif
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index eec75b97e7ea..0e5588cd2f39 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -24,6 +24,7 @@
 #include <linux/irqdesc.h>
 
 #include <asm/irq_regs.h>
+#include <asm/mmu_context.h>
 
 static DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu);
 static DEFINE_PER_CPU(int, cpu_irq);
@@ -777,6 +778,41 @@ static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
 					    &cpu_pmu->node);
 }
 
+static void refresh_pmuserenr(void *mm)
+{
+	perf_switch_user_access(mm);
+}
+
+static void armpmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (!(event->hw.flags & ARMPMU_EL0_RD_CNTR))
+		return;
+
+	/*
+	 * This function relies on not being called concurrently in two
+	 * tasks in the same mm.  Otherwise one task could observe
+	 * pmu_direct_access > 1 and return all the way back to
+	 * userspace with user access disabled while another task is still
+	 * doing on_each_cpu_mask() to enable user access.
+	 *
+	 * For now, this can't happen because all callers hold mmap_sem
+	 * for write.  If this changes, we'll need a different solution.
+	 */
+	lockdep_assert_held_exclusive(&mm->mmap_sem);
+
+	if (atomic_inc_return(&mm->context.pmu_direct_access) == 1)
+		on_each_cpu(refresh_pmuserenr, mm, 1);
+}
+
+static void armpmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
+{
+	if (!(event->hw.flags & ARMPMU_EL0_RD_CNTR))
+		return;
+
+	if (atomic_dec_and_test(&mm->context.pmu_direct_access))
+		on_each_cpu_mask(mm_cpumask(mm), refresh_pmuserenr, NULL, 1);
+}
+
 static struct arm_pmu *__armpmu_alloc(gfp_t flags)
 {
 	struct arm_pmu *pmu;
@@ -798,6 +834,8 @@ static struct arm_pmu *__armpmu_alloc(gfp_t flags)
 		.pmu_enable	= armpmu_enable,
 		.pmu_disable	= armpmu_disable,
 		.event_init	= armpmu_event_init,
+		.event_mapped	= armpmu_event_mapped,
+		.event_unmapped	= armpmu_event_unmapped,
 		.add		= armpmu_add,
 		.del		= armpmu_del,
 		.start		= armpmu_start,
-- 
2.17.1