Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "A bunch of good stuff in here. Worth noting is that we've pulled in
  the x86/mm branch from -tip so that we can make use of the core
  ioremap changes which allow us to put down huge mappings in the
  vmalloc area without screwing up the TLB. Much of the positive
  diffstat is because of the rseq selftest for arm64.

  Summary:

   - Wire up support for qspinlock, replacing our trusty ticket lock
     code

   - Add an IPI to flush_icache_range() to ensure that stale
     instructions fetched into the pipeline are discarded along with the
     I-cache lines

   - Support for the GCC "stackleak" plugin

   - Support for restartable sequences, plus an arm64 port for the
     selftest

   - Kexec/kdump support on systems booting with ACPI

   - Rewrite of our syscall entry code in C, which allows us to zero the
     GPRs on entry from userspace

   - Support for chained PMU counters, allowing 64-bit event counters to
     be constructed on current CPUs

   - Ensure scheduler topology information is kept up-to-date with CPU
     hotplug events

   - Re-enable support for huge vmalloc/IO mappings now that the core
     code has the correct hooks to use break-before-make sequences

   - Miscellaneous, non-critical fixes and cleanups"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (90 commits)
  arm64: alternative: Use true and false for boolean values
  arm64: kexec: Add comment to explain use of __flush_icache_range()
  arm64: sdei: Mark sdei stack helper functions as static
  arm64, kaslr: export offset in VMCOREINFO ELF notes
  arm64: perf: Add cap_user_time aarch64
  efi/libstub: Only disable stackleak plugin for arm64
  arm64: drop unused kernel_neon_begin_partial() macro
  arm64: kexec: machine_kexec should call __flush_icache_range
  arm64: svc: Ensure hardirq tracing is updated before return
  arm64: mm: Export __sync_icache_dcache() for xen-privcmd
  drivers/perf: arm-ccn: Use devm_ioremap_resource() to map memory
  arm64: Add support for STACKLEAK gcc plugin
  arm64: Add stack information to on_accessible_stack
  drivers/perf: hisi: update the sccl_id/ccl_id when MT is supported
  arm64: fix ACPI dependencies
  rseq/selftests: Add support for arm64
  arm64: acpi: fix alignment fault in accessing ACPI
  efi/arm: map UEFI memory map even w/o runtime services enabled
  efi/arm: preserve early mapping of UEFI memory map longer for BGRT
  drivers: acpi: add dependency of EFI for arm64
  ...

1 files changed, 22 insertions, 16 deletions

diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index a6347d487635..7f01f6f60b87 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -28,6 +28,14 @@
 static DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu);
 static DEFINE_PER_CPU(int, cpu_irq);
 
+static inline u64 arm_pmu_event_max_period(struct perf_event *event)
+{
+	if (event->hw.flags & ARMPMU_EVT_64BIT)
+		return GENMASK_ULL(63, 0);
+	else
+		return GENMASK_ULL(31, 0);
+}
+
 static int
 armpmu_map_cache_event(const unsigned (*cache_map)
 				      [PERF_COUNT_HW_CACHE_MAX]
@@ -114,8 +122,10 @@ int armpmu_event_set_period(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	s64 left = local64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
+	u64 max_period;
 	int ret = 0;
 
+	max_period = arm_pmu_event_max_period(event);
 	if (unlikely(left <= -period)) {
 		left = period;
 		local64_set(&hwc->period_left, left);
@@ -136,12 +146,12 @@ int armpmu_event_set_period(struct perf_event *event)
 	 * effect we are reducing max_period to account for
 	 * interrupt latency (and we are being very conservative).
 	 */
-	if (left > (armpmu->max_period >> 1))
-		left = armpmu->max_period >> 1;
+	if (left > (max_period >> 1))
+		left = (max_period >> 1);
 
 	local64_set(&hwc->prev_count, (u64)-left);
 
-	armpmu->write_counter(event, (u64)(-left) & 0xffffffff);
+	armpmu->write_counter(event, (u64)(-left) & max_period);
 
 	perf_event_update_userpage(event);
 
@@ -153,6 +163,7 @@ u64 armpmu_event_update(struct perf_event *event)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 delta, prev_raw_count, new_raw_count;
+	u64 max_period = arm_pmu_event_max_period(event);
 
 again:
 	prev_raw_count = local64_read(&hwc->prev_count);
@@ -162,7 +173,7 @@ again:
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
-	delta = (new_raw_count - prev_raw_count) & armpmu->max_period;
+	delta = (new_raw_count - prev_raw_count) & max_period;
 
 	local64_add(delta, &event->count);
 	local64_sub(delta, &hwc->period_left);
@@ -227,11 +238,10 @@ armpmu_del(struct perf_event *event, int flags)
 
 	armpmu_stop(event, PERF_EF_UPDATE);
 	hw_events->events[idx] = NULL;
-	clear_bit(idx, hw_events->used_mask);
-	if (armpmu->clear_event_idx)
-		armpmu->clear_event_idx(hw_events, event);
-
+	armpmu->clear_event_idx(hw_events, event);
 	perf_event_update_userpage(event);
+	/* Clear the allocated counter */
+	hwc->idx = -1;
 }
 
 static int
@@ -360,6 +370,7 @@ __hw_perf_event_init(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int mapping;
 
+	hwc->flags = 0;
 	mapping = armpmu->map_event(event);
 
 	if (mapping < 0) {
@@ -402,7 +413,7 @@ __hw_perf_event_init(struct perf_event *event)
 		 * is far less likely to overtake the previous one unless
 		 * you have some serious IRQ latency issues.
 		 */
-		hwc->sample_period  = armpmu->max_period >> 1;
+		hwc->sample_period  = arm_pmu_event_max_period(event) >> 1;
 		hwc->last_period    = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
 	}
@@ -654,14 +665,9 @@ static void cpu_pm_pmu_setup(struct arm_pmu *armpmu, unsigned long cmd)
 	int idx;
 
 	for (idx = 0; idx < armpmu->num_events; idx++) {
-		/*
-		 * If the counter is not used skip it, there is no
-		 * need of stopping/restarting it.
-		 */
-		if (!test_bit(idx, hw_events->used_mask))
-			continue;
-
 		event = hw_events->events[idx];
+		if (!event)
+			continue;
 
 		switch (cmd) {
 		case CPU_PM_ENTER: