Merge branch 'for-next/perf' into for-next/core

* for-next/perf: (41 commits)
  arm64: Add USER_STACKTRACE support
  drivers/perf: hisi: hns3: Actually use devm_add_action_or_reset()
  drivers/perf: hisi: hns3: Fix out-of-bound access when valid event group
  drivers/perf: hisi_pcie: Fix out-of-bound access when valid event group
  perf/arm-spe: Assign parents for event_source device
  perf/arm-smmuv3: Assign parents for event_source device
  perf/arm-dsu: Assign parents for event_source device
  perf/arm-dmc620: Assign parents for event_source device
  perf/arm-ccn: Assign parents for event_source device
  perf/arm-cci: Assign parents for event_source device
  perf/alibaba_uncore: Assign parents for event_source device
  perf/arm_pmu: Assign parents for event_source devices
  perf/imx_ddr: Assign parents for event_source devices
  perf/qcom: Assign parents for event_source devices
  Documentation: qcom-pmu: Use /sys/bus/event_source/devices paths
  perf/riscv: Assign parents for event_source devices
  perf/thunderx2: Assign parents for event_source devices
  Documentation: thunderx2-pmu: Use /sys/bus/event_source/devices paths
  perf/xgene: Assign parents for event_source devices
  Documentation: xgene-pmu: Use /sys/bus/event_source/devices paths
  ...

34 files changed, 253 insertions, 203 deletions

diff --git a/Documentation/admin-guide/perf/hisi-pmu.rst b/Documentation/admin-guide/perf/hisi-pmu.rst
index e0174d20809a..5cc248d18c63 100644
--- a/Documentation/admin-guide/perf/hisi-pmu.rst
+++ b/Documentation/admin-guide/perf/hisi-pmu.rst
@@ -20,7 +20,6 @@ interrupt, and the PMU driver shall register perf PMU drivers like L3C,
 HHA and DDRC etc. The available events and configuration options shall
 be described in the sysfs, see:
 
-/sys/devices/hisi_sccl{X}_<l3c{Y}/hha{Y}/ddrc{Y}>/, or
 /sys/bus/event_source/devices/hisi_sccl{X}_<l3c{Y}/hha{Y}/ddrc{Y}>.
 The "perf list" command shall list the available events from sysfs.
 
diff --git a/Documentation/admin-guide/perf/hns3-pmu.rst b/Documentation/admin-guide/perf/hns3-pmu.rst
index 75a40846d47f..1195e570f2d6 100644
--- a/Documentation/admin-guide/perf/hns3-pmu.rst
+++ b/Documentation/admin-guide/perf/hns3-pmu.rst
@@ -16,7 +16,7 @@ HNS3 PMU driver
 
 The HNS3 PMU driver registers a perf PMU with the name of its sicl id.::
 
-  /sys/devices/hns3_pmu_sicl_<sicl_id>
+  /sys/bus/event_source/devices/hns3_pmu_sicl_<sicl_id>
 
 PMU driver provides description of available events, filter modes, format,
 identifier and cpumask in sysfs.
@@ -40,9 +40,9 @@ device.
 
 Example usage of checking event code and subevent code::
 
-  $# cat /sys/devices/hns3_pmu_sicl_0/events/dly_tx_normal_to_mac_time
+  $# cat /sys/bus/event_source/devices/hns3_pmu_sicl_0/events/dly_tx_normal_to_mac_time
   config=0x00204
-  $# cat /sys/devices/hns3_pmu_sicl_0/events/dly_tx_normal_to_mac_packet_num
+  $# cat /sys/bus/event_source/devices/hns3_pmu_sicl_0/events/dly_tx_normal_to_mac_packet_num
   config=0x10204
 
 Each performance statistic has a pair of events to get two values to
@@ -60,7 +60,7 @@ computation to calculate real performance data is:::
 
 Example usage of checking supported filter mode::
 
-  $# cat /sys/devices/hns3_pmu_sicl_0/filtermode/bw_ssu_rpu_byte_num
+  $# cat /sys/bus/event_source/devices/hns3_pmu_sicl_0/filtermode/bw_ssu_rpu_byte_num
   filter mode supported: global/port/port-tc/func/func-queue/
 
 Example usage of perf::
diff --git a/Documentation/admin-guide/perf/qcom_l2_pmu.rst b/Documentation/admin-guide/perf/qcom_l2_pmu.rst
index c130178a4a55..c37c6be9b8d8 100644
--- a/Documentation/admin-guide/perf/qcom_l2_pmu.rst
+++ b/Documentation/admin-guide/perf/qcom_l2_pmu.rst
@@ -10,7 +10,7 @@ There is one logical L2 PMU exposed, which aggregates the results from
 the physical PMUs.
 
 The driver provides a description of its available events and configuration
-options in sysfs, see /sys/devices/l2cache_0.
+options in sysfs, see /sys/bus/event_source/devices/l2cache_0.
 
 The "format" directory describes the format of the events.
 
diff --git a/Documentation/admin-guide/perf/qcom_l3_pmu.rst b/Documentation/admin-guide/perf/qcom_l3_pmu.rst
index a3d014a46bfd..a66556b7e985 100644
--- a/Documentation/admin-guide/perf/qcom_l3_pmu.rst
+++ b/Documentation/admin-guide/perf/qcom_l3_pmu.rst
@@ -9,7 +9,7 @@ PMU with device name l3cache_<socket>_<instance>. User space is responsible
 for aggregating across slices.
 
 The driver provides a description of its available events and configuration
-options in sysfs, see /sys/devices/l3cache*. Given that these are uncore PMUs
+options in sysfs, see /sys/bus/event_source/devices/l3cache*. Given that these are uncore PMUs
 the driver also exposes a "cpumask" sysfs attribute which contains a mask
 consisting of one CPU per socket which will be used to handle all the PMU
 events on that socket.
diff --git a/Documentation/admin-guide/perf/thunderx2-pmu.rst b/Documentation/admin-guide/perf/thunderx2-pmu.rst
index 01f158238ae1..9255f7bf9452 100644
--- a/Documentation/admin-guide/perf/thunderx2-pmu.rst
+++ b/Documentation/admin-guide/perf/thunderx2-pmu.rst
@@ -22,7 +22,7 @@ The thunderx2_pmu driver registers per-socket perf PMUs for the DMC and
 L3C devices.  Each PMU can be used to count up to 4 (DMC/L3C) or up to 8
 (CCPI2) events simultaneously. The PMUs provide a description of their
 available events and configuration options under sysfs, see
-/sys/devices/uncore_<l3c_S/dmc_S/ccpi2_S/>; S is the socket id.
+/sys/bus/event_source/devices/uncore_<l3c_S/dmc_S/ccpi2_S/>; S is the socket id.
 
 The driver does not support sampling, therefore "perf record" will not
 work. Per-task perf sessions are also not supported.
diff --git a/Documentation/admin-guide/perf/xgene-pmu.rst b/Documentation/admin-guide/perf/xgene-pmu.rst
index 644f8ed89152..98ccb8e777c4 100644
--- a/Documentation/admin-guide/perf/xgene-pmu.rst
+++ b/Documentation/admin-guide/perf/xgene-pmu.rst
@@ -13,7 +13,7 @@ PMU (perf) driver
 
 The xgene-pmu driver registers several perf PMU drivers. Each of the perf
 driver provides description of its available events and configuration options
-in sysfs, see /sys/devices/<l3cX/iobX/mcbX/mcX>/.
+in sysfs, see /sys/bus/event_source/devices/<l3cX/iobX/mcbX/mcX>/.
 
 The "format" directory describes format of the config (event ID),
 config1 (agent ID) fields of the perf_event_attr structure. The "events"
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 763e221f2169..a04059c31aba 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -259,6 +259,7 @@ config ARM64
 	select TRACE_IRQFLAGS_SUPPORT
 	select TRACE_IRQFLAGS_NMI_SUPPORT
 	select HAVE_SOFTIRQ_ON_OWN_STACK
+	select USER_STACKTRACE_SUPPORT
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 6f9ad2d2bb40..bc0b0d75acef 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -476,9 +476,10 @@ alternative_endif
  */
 	.macro	reset_pmuserenr_el0, tmpreg
 	mrs	\tmpreg, id_aa64dfr0_el1
-	sbfx	\tmpreg, \tmpreg, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
-	cmp	\tmpreg, #1			// Skip if no PMU present
-	b.lt	9000f
+	ubfx	\tmpreg, \tmpreg, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
+	cmp	\tmpreg, #ID_AA64DFR0_EL1_PMUVer_NI
+	ccmp	\tmpreg, #ID_AA64DFR0_EL1_PMUVer_IMP_DEF, #4, ne
+	b.eq	9000f				// Skip if no PMU present or IMP_DEF
 	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
 9000:
 	.endm
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index b7afaa026842..e4546b29dd0c 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -59,13 +59,14 @@
 
 .macro __init_el2_debug
 	mrs	x1, id_aa64dfr0_el1
-	sbfx	x0, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
-	cmp	x0, #1
-	b.lt	.Lskip_pmu_\@			// Skip if no PMU present
+	ubfx	x0, x1, #ID_AA64DFR0_EL1_PMUVer_SHIFT, #4
+	cmp	x0, #ID_AA64DFR0_EL1_PMUVer_NI
+	ccmp	x0, #ID_AA64DFR0_EL1_PMUVer_IMP_DEF, #4, ne
+	b.eq	.Lskip_pmu_\@			// Skip if no PMU present or IMP_DEF
 	mrs	x0, pmcr_el0			// Disable debug access traps
 	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
 .Lskip_pmu_\@:
-	csel	x2, xzr, x0, lt			// all PMU counters from EL1
+	csel	x2, xzr, x0, eq			// all PMU counters from EL1
 
 	/* Statistical profiling */
 	ubfx	x0, x1, #ID_AA64DFR0_EL1_PMSVer_SHIFT, #4
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 6d157f32187b..e8ed5673f481 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -10,94 +10,12 @@
 
 #include <asm/pointer_auth.h>
 
-struct frame_tail {
-	struct frame_tail	__user *fp;
-	unsigned long		lr;
-} __attribute__((packed));
-
-/*
- * Get the return address for a single stackframe and return a pointer to the
- * next frame tail.
- */
-static struct frame_tail __user *
-user_backtrace(struct frame_tail __user *tail,
-	       struct perf_callchain_entry_ctx *entry)
-{
-	struct frame_tail buftail;
-	unsigned long err;
-	unsigned long lr;
-
-	/* Also check accessibility of one struct frame_tail beyond */
-	if (!access_ok(tail, sizeof(buftail)))
-		return NULL;
-
-	pagefault_disable();
-	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
-	pagefault_enable();
-
-	if (err)
-		return NULL;
-
-	lr = ptrauth_strip_user_insn_pac(buftail.lr);
-
-	perf_callchain_store(entry, lr);
-
-	/*
-	 * Frame pointers should strictly progress back up the stack
-	 * (towards higher addresses).
-	 */
-	if (tail >= buftail.fp)
-		return NULL;
-
-	return buftail.fp;
-}
-
-#ifdef CONFIG_COMPAT
-/*
- * The registers we're interested in are at the end of the variable
- * length saved register structure. The fp points at the end of this
- * structure so the address of this struct is:
- * (struct compat_frame_tail *)(xxx->fp)-1
- *
- * This code has been adapted from the ARM OProfile support.
- */
-struct compat_frame_tail {
-	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
-	u32		sp;
-	u32		lr;
-} __attribute__((packed));
-
-static struct compat_frame_tail __user *
-compat_user_backtrace(struct compat_frame_tail __user *tail,
-		      struct perf_callchain_entry_ctx *entry)
+static bool callchain_trace(void *data, unsigned long pc)
 {
-	struct compat_frame_tail buftail;
-	unsigned long err;
-
-	/* Also check accessibility of one struct frame_tail beyond */
-	if (!access_ok(tail, sizeof(buftail)))
-		return NULL;
-
-	pagefault_disable();
-	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
-	pagefault_enable();
-
-	if (err)
-		return NULL;
-
-	perf_callchain_store(entry, buftail.lr);
-
-	/*
-	 * Frame pointers should strictly progress back up the stack
-	 * (towards higher addresses).
-	 */
-	if (tail + 1 >= (struct compat_frame_tail __user *)
-			compat_ptr(buftail.fp))
-		return NULL;
+	struct perf_callchain_entry_ctx *entry = data;
 
-	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+	return perf_callchain_store(entry, pc) == 0;
 }
-#endif /* CONFIG_COMPAT */
 
 void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 			 struct pt_regs *regs)
@@ -107,35 +25,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
 		return;
 	}
 
-	perf_callchain_store(entry, regs->pc);
-
-	if (!compat_user_mode(regs)) {
-		/* AARCH64 mode */
-		struct frame_tail __user *tail;
-
-		tail = (struct frame_tail __user *)regs->regs[29];
-
-		while (entry->nr < entry->max_stack &&
-		       tail && !((unsigned long)tail & 0x7))
-			tail = user_backtrace(tail, entry);
-	} else {
-#ifdef CONFIG_COMPAT
-		/* AARCH32 compat mode */
-		struct compat_frame_tail __user *tail;
-
-		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
-
-		while ((entry->nr < entry->max_stack) &&
-			tail && !((unsigned long)tail & 0x3))
-			tail = compat_user_backtrace(tail, entry);
-#endif
-	}
-}
-
-static bool callchain_trace(void *data, unsigned long pc)
-{
-	struct perf_callchain_entry_ctx *entry = data;
-	return perf_callchain_store(entry, pc) == 0;
+	arch_stack_walk_user(callchain_trace, entry, regs);
 }
 
 void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 684c26511696..6b3258860377 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -324,3 +324,123 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 	dump_backtrace(NULL, tsk, loglvl);
 	barrier();
 }
+
+/*
+ * The struct defined for userspace stack frame in AARCH64 mode.
+ */
+struct frame_tail {
+	struct frame_tail	__user *fp;
+	unsigned long		lr;
+} __attribute__((packed));
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static struct frame_tail __user *
+unwind_user_frame(struct frame_tail __user *tail, void *cookie,
+	       stack_trace_consume_fn consume_entry)
+{
+	struct frame_tail buftail;
+	unsigned long err;
+	unsigned long lr;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	lr = ptrauth_strip_user_insn_pac(buftail.lr);
+
+	if (!consume_entry(cookie, lr))
+		return NULL;
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail >= buftail.fp)
+		return NULL;
+
+	return buftail.fp;
+}
+
+#ifdef CONFIG_COMPAT
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct compat_frame_tail *)(xxx->fp)-1
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct compat_frame_tail {
+	compat_uptr_t	fp; /* a (struct compat_frame_tail *) in compat mode */
+	u32		sp;
+	u32		lr;
+} __attribute__((packed));
+
+static struct compat_frame_tail __user *
+unwind_compat_user_frame(struct compat_frame_tail __user *tail, void *cookie,
+				stack_trace_consume_fn consume_entry)
+{
+	struct compat_frame_tail buftail;
+	unsigned long err;
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(tail, sizeof(buftail)))
+		return NULL;
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
+		return NULL;
+
+	if (!consume_entry(cookie, buftail.lr))
+		return NULL;
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail + 1 >= (struct compat_frame_tail __user *)
+			compat_ptr(buftail.fp))
+		return NULL;
+
+	return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+}
+#endif /* CONFIG_COMPAT */
+
+
+void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+					const struct pt_regs *regs)
+{
+	if (!consume_entry(cookie, regs->pc))
+		return;
+
+	if (!compat_user_mode(regs)) {
+		/* AARCH64 mode */
+		struct frame_tail __user *tail;
+
+		tail = (struct frame_tail __user *)regs->regs[29];
+		while (tail && !((unsigned long)tail & 0x7))
+			tail = unwind_user_frame(tail, cookie, consume_entry);
+	} else {
+#ifdef CONFIG_COMPAT
+		/* AARCH32 compat mode */
+		struct compat_frame_tail __user *tail;
+
+		tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
+		while (tail && !((unsigned long)tail & 0x3))
+			tail = unwind_compat_user_frame(tail, cookie, consume_entry);
+#endif
+	}
+}
diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c
index a9277dcf90ce..89dd38343f93 100644
--- a/drivers/perf/alibaba_uncore_drw_pmu.c
+++ b/drivers/perf/alibaba_uncore_drw_pmu.c
@@ -709,6 +709,7 @@ static int ali_drw_pmu_probe(struct platform_device *pdev)
 
 	drw_pmu->pmu = (struct pmu) {
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= ali_drw_pmu_event_init,
 		.add		= ali_drw_pmu_add,
@@ -746,18 +747,14 @@ static int ali_drw_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	struct ali_drw_pmu_irq *irq;
 	struct ali_drw_pmu *drw_pmu;
 	unsigned int target;
-	int ret;
-	cpumask_t node_online_cpus;
 
 	irq = hlist_entry_safe(node, struct ali_drw_pmu_irq, node);
 	if (cpu != irq->cpu)
 		return 0;
 
-	ret = cpumask_and(&node_online_cpus,
-			  cpumask_of_node(cpu_to_node(cpu)), cpu_online_mask);
-	if (ret)
-		target = cpumask_any_but(&node_online_cpus, cpu);
-	else
+	target = cpumask_any_and_but(cpumask_of_node(cpu_to_node(cpu)),
+				     cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
 
 	if (target >= nr_cpu_ids)
diff --git a/drivers/perf/amlogic/meson_ddr_pmu_core.c b/drivers/perf/amlogic/meson_ddr_pmu_core.c
index bbc7285fd934..07446d784a1a 100644
--- a/drivers/perf/amlogic/meson_ddr_pmu_core.c
+++ b/drivers/perf/amlogic/meson_ddr_pmu_core.c
@@ -492,6 +492,7 @@ int meson_ddr_pmu_create(struct platform_device *pdev)
 	*pmu = (struct ddr_pmu) {
 		.pmu = {
 			.module		= THIS_MODULE,
+			.parent		= &pdev->dev,
 			.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 			.task_ctx_nr	= perf_invalid_context,
 			.attr_groups	= attr_groups,
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 6be03f81ae5d..a7fd80677919 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1409,6 +1409,7 @@ static int cci_pmu_init(struct cci_pmu *cci_pmu, struct platform_device *pdev)
 
 	cci_pmu->pmu = (struct pmu) {
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.name		= cci_pmu->model->name,
 		.task_ctx_nr	= perf_invalid_context,
 		.pmu_enable	= cci_pmu_enable,
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 641471bd5eff..f4495ff6525f 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1265,6 +1265,7 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	/* Perf driver registration */
 	ccn->dt.pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent = ccn->dev,
 		.attr_groups = arm_ccn_pmu_attr_groups,
 		.task_ctx_nr = perf_invalid_context,
 		.event_init = arm_ccn_pmu_event_init,
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index 7ef9c7e4836b..e26ad1d3ed0b 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -1950,20 +1950,20 @@ static int arm_cmn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_no
 	struct arm_cmn *cmn;
 	unsigned int target;
 	int node;
-	cpumask_t mask;
 
 	cmn = hlist_entry_safe(cpuhp_node, struct arm_cmn, cpuhp_node);
 	if (cpu != cmn->cpu)
 		return 0;
 
 	node = dev_to_node(cmn->dev);
-	if (cpumask_and(&mask, cpumask_of_node(node), cpu_online_mask) &&
-	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
-		target = cpumask_any(&mask);
-	else
+
+	target = cpumask_any_and_but(cpumask_of_node(node), cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
+
 	if (target < nr_cpu_ids)
 		arm_cmn_migrate(cmn, target);
+
 	return 0;
 }
 
@@ -2482,6 +2482,7 @@ static int arm_cmn_probe(struct platform_device *pdev)
 	cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev));
 	cmn->pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent = cmn->dev,
 		.attr_groups = arm_cmn_attr_groups,
 		.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 		.task_ctx_nr = perf_invalid_context,
diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c
index b9a252272f1e..ba0cf2f466ef 100644
--- a/drivers/perf/arm_cspmu/arm_cspmu.c
+++ b/drivers/perf/arm_cspmu/arm_cspmu.c
@@ -1206,6 +1206,7 @@ static int arm_cspmu_register_pmu(struct arm_cspmu *cspmu)
 	cspmu->pmu = (struct pmu){
 		.task_ctx_nr	= perf_invalid_context,
 		.module		= cspmu->impl.module,
+		.parent		= cspmu->dev,
 		.pmu_enable	= arm_cspmu_enable,
 		.pmu_disable	= arm_cspmu_disable,
 		.event_init	= arm_cspmu_event_init,
@@ -1322,8 +1323,7 @@ static int arm_cspmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 
 static int arm_cspmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
 {
-	int dst;
-	struct cpumask online_supported;
+	unsigned int dst;
 
 	struct arm_cspmu *cspmu =
 		hlist_entry_safe(node, struct arm_cspmu, cpuhp_node);
@@ -1333,9 +1333,8 @@ static int arm_cspmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
 		return 0;
 
 	/* Choose a new CPU to migrate ownership of the PMU to */
-	cpumask_and(&online_supported, &cspmu->associated_cpus,
-		    cpu_online_mask);
-	dst = cpumask_any_but(&online_supported, cpu);
+	dst = cpumask_any_and_but(&cspmu->associated_cpus,
+				  cpu_online_mask, cpu);
 	if (dst >= nr_cpu_ids)
 		return 0;
 
diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c
index 8a81be2dd5ec..2ec96e204c40 100644
--- a/drivers/perf/arm_dmc620_pmu.c
+++ b/drivers/perf/arm_dmc620_pmu.c
@@ -673,6 +673,7 @@ static int dmc620_pmu_device_probe(struct platform_device *pdev)
 
 	dmc620_pmu->pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent		= &pdev->dev,
 		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= dmc620_pmu_event_init,
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index bae3ca37f846..92248a24a1aa 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -230,15 +230,6 @@ static const struct attribute_group *dsu_pmu_attr_groups[] = {
 	NULL,
 };
 
-static int dsu_pmu_get_online_cpu_any_but(struct dsu_pmu *dsu_pmu, int cpu)
-{
-	struct cpumask online_supported;
-
-	cpumask_and(&online_supported,
-			 &dsu_pmu->associated_cpus, cpu_online_mask);
-	return cpumask_any_but(&online_supported, cpu);
-}
-
 static inline bool dsu_pmu_counter_valid(struct dsu_pmu *dsu_pmu, u32 idx)
 {
 	return (idx < dsu_pmu->num_counters) ||
@@ -751,6 +742,7 @@ static int dsu_pmu_device_probe(struct platform_device *pdev)
 
 	dsu_pmu->pmu = (struct pmu) {
 		.task_ctx_nr	= perf_invalid_context,
+		.parent		= &pdev->dev,
 		.module		= THIS_MODULE,
 		.pmu_enable	= dsu_pmu_enable,
 		.pmu_disable	= dsu_pmu_disable,
@@ -827,14 +819,16 @@ static int dsu_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 
 static int dsu_pmu_cpu_teardown(unsigned int cpu, struct hlist_node *node)
 {
-	int dst;
-	struct dsu_pmu *dsu_pmu = hlist_entry_safe(node, struct dsu_pmu,
-						   cpuhp_node);
+	struct dsu_pmu *dsu_pmu;
+	unsigned int dst;
+
+	dsu_pmu = hlist_entry_safe(node, struct dsu_pmu, cpuhp_node);
 
 	if (!cpumask_test_and_clear_cpu(cpu, &dsu_pmu->active_cpu))
 		return 0;
 
-	dst = dsu_pmu_get_online_cpu_any_but(dsu_pmu, cpu);
+	dst = cpumask_any_and_but(&dsu_pmu->associated_cpus,
+				  cpu_online_mask, cpu);
 	/* If there are no active CPUs in the DSU, leave IRQ disabled */
 	if (dst >= nr_cpu_ids)
 		return 0;
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 3596db36cbff..4b1a9a92ea11 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -196,6 +196,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 	if (!pmu)
 		return -ENOMEM;
 
+	pmu->pmu.parent = &pdev->dev;
 	pmu->plat_device = pdev;
 
 	ret = pmu_parse_irqs(pmu);
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index 719aa953a1c4..d5fa92ba8373 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -860,6 +860,7 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 
 	smmu_pmu->pmu = (struct pmu) {
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.task_ctx_nr    = perf_invalid_context,
 		.pmu_enable	= smmu_pmu_enable,
 		.pmu_disable	= smmu_pmu_disable,
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index 35f0de03416f..9100d82bfabc 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -932,6 +932,7 @@ static int arm_spe_pmu_perf_init(struct arm_spe_pmu *spe_pmu)
 
 	spe_pmu->pmu = (struct pmu) {
 		.module = THIS_MODULE,
+		.parent		= &spe_pmu->pdev->dev,
 		.capabilities	= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE,
 		.attr_groups	= arm_spe_pmu_attr_groups,
 		/*
diff --git a/drivers/perf/dwc_pcie_pmu.c b/drivers/perf/dwc_pcie_pmu.c
index 957058ad0099..c5e328f23841 100644
--- a/drivers/perf/dwc_pcie_pmu.c
+++ b/drivers/perf/dwc_pcie_pmu.c
@@ -690,9 +690,8 @@ static int dwc_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_n
 {
 	struct dwc_pcie_pmu *pcie_pmu;
 	struct pci_dev *pdev;
-	int node;
-	cpumask_t mask;
 	unsigned int target;
+	int node;
 
 	pcie_pmu = hlist_entry_safe(cpuhp_node, struct dwc_pcie_pmu, cpuhp_node);
 	/* Nothing to do if this CPU doesn't own the PMU */
@@ -702,10 +701,9 @@ static int dwc_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *cpuhp_n
 	pcie_pmu->on_cpu = -1;
 	pdev = pcie_pmu->pdev;
 	node = dev_to_node(&pdev->dev);
-	if (cpumask_and(&mask, cpumask_of_node(node), cpu_online_mask) &&
-	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
-		target = cpumask_any(&mask);
-	else
+
+	target = cpumask_any_and_but(cpumask_of_node(node), cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
 
 	if (target >= nr_cpu_ids) {
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index 4e8fa5a48fcf..1bbdb29743c4 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -651,6 +651,7 @@ static int ddr_perf_init(struct ddr_pmu *pmu, void __iomem *base,
 	*pmu = (struct ddr_pmu) {
 		.pmu = (struct pmu) {
 			.module	      = THIS_MODULE,
+			.parent      = dev,
 			.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 			.task_ctx_nr = perf_invalid_context,
 			.attr_groups = attr_groups,
diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c
index 5d1f0e9fdb08..03c506aa3853 100644
--- a/drivers/perf/hisilicon/hisi_pcie_pmu.c
+++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c
@@ -350,15 +350,27 @@ static bool hisi_pcie_pmu_validate_event_group(struct perf_event *event)
 			return false;
 
 		for (num = 0; num < counters; num++) {
+			/*
+			 * If we find a related event, then it's a valid group
+			 * since we don't need to allocate a new counter for it.
+			 */
 			if (hisi_pcie_pmu_cmp_event(event_group[num], sibling))
 				break;
 		}
 
+		/*
+		 * Otherwise it's a new event but if there's no available counter,
+		 * fail the check since we cannot schedule all the events in
+		 * the group simultaneously.
+		 */
+		if (num == HISI_PCIE_MAX_COUNTERS)
+			return false;
+
 		if (num == counters)
 			event_group[counters++] = sibling;
 	}
 
-	return counters <= HISI_PCIE_MAX_COUNTERS;
+	return true;
 }
 
 static int hisi_pcie_pmu_event_init(struct perf_event *event)
@@ -673,7 +685,6 @@ static int hisi_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	struct hisi_pcie_pmu *pcie_pmu = hlist_entry_safe(node, struct hisi_pcie_pmu, node);
 	unsigned int target;
-	cpumask_t mask;
 	int numa_node;
 
 	/* Nothing to do if this CPU doesn't own the PMU */
@@ -684,10 +695,10 @@ static int hisi_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 
 	/* Choose a local CPU from all online cpus. */
 	numa_node = dev_to_node(&pcie_pmu->pdev->dev);
-	if (cpumask_and(&mask, cpumask_of_node(numa_node), cpu_online_mask) &&
-	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
-		target = cpumask_any(&mask);
-	else
+
+	target = cpumask_any_and_but(cpumask_of_node(numa_node),
+				     cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
 		target = cpumask_any_but(cpu_online_mask, cpu);
 
 	if (target >= nr_cpu_ids) {
@@ -807,6 +818,7 @@ static int hisi_pcie_alloc_pmu(struct pci_dev *pdev, struct hisi_pcie_pmu *pcie_
 	pcie_pmu->pmu = (struct pmu) {
 		.name		= name,
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.event_init	= hisi_pcie_pmu_event_init,
 		.pmu_enable	= hisi_pcie_pmu_enable,
 		.pmu_disable	= hisi_pcie_pmu_disable,
diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 04031450d5fe..a60e4c966098 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -504,7 +504,6 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	struct hisi_pmu *hisi_pmu = hlist_entry_safe(node, struct hisi_pmu,
 						     node);
-	cpumask_t pmu_online_cpus;
 	unsigned int target;
 
 	if (!cpumask_test_and_clear_cpu(cpu, &hisi_pmu->associated_cpus))
@@ -518,9 +517,8 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	hisi_pmu->on_cpu = -1;
 
 	/* Choose a new CPU to migrate ownership of the PMU to */
-	cpumask_and(&pmu_online_cpus, &hisi_pmu->associated_cpus,
-		    cpu_online_mask);
-	target = cpumask_any_but(&pmu_online_cpus, cpu);
+	target = cpumask_any_and_but(&hisi_pmu->associated_cpus,
+				     cpu_online_mask, cpu);
 	if (target >= nr_cpu_ids)
 		return 0;
 
@@ -538,6 +536,7 @@ void hisi_pmu_init(struct hisi_pmu *hisi_pmu, struct module *module)
 	struct pmu *pmu = &hisi_pmu->pmu;
 
 	pmu->module             = module;
+	pmu->parent             = hisi_pmu->dev;
 	pmu->task_ctx_nr        = perf_invalid_context;
 	pmu->event_init         = hisi_uncore_pmu_event_init;
 	pmu->pmu_enable         = hisi_uncore_pmu_enable;
diff --git a/drivers/perf/hisilicon/hns3_pmu.c b/drivers/perf/hisilicon/hns3_pmu.c
index 16869bf5bf4c..e900f8e00b18 100644
--- a/drivers/perf/hisilicon/hns3_pmu.c
+++ b/drivers/perf/hisilicon/hns3_pmu.c
@@ -1085,15 +1085,27 @@ static bool hns3_pmu_validate_event_group(struct perf_event *event)
 			return false;
 
 		for (num = 0; num < counters; num++) {
+			/*
+			 * If we find a related event, then it's a valid group
+			 * since we don't need to allocate a new counter for it.
+			 */
 			if (hns3_pmu_cmp_event(event_group[num], sibling))
 				break;
 		}
 
+		/*
+		 * Otherwise it's a new event but if there's no available counter,
+		 * fail the check since we cannot schedule all the events in
+		 * the group simultaneously.
+		 */
+		if (num == HNS3_PMU_MAX_HW_EVENTS)
+			return false;
+
 		if (num == counters)
 			event_group[counters++] = sibling;
 	}
 
-	return counters <= HNS3_PMU_MAX_HW_EVENTS;
+	return true;
 }
 
 static u32 hns3_pmu_get_filter_condition(struct perf_event *event)
@@ -1419,6 +1431,7 @@ static int hns3_pmu_alloc_pmu(struct pci_dev *pdev, struct hns3_pmu *hns3_pmu)
 	hns3_pmu->pmu = (struct pmu) {
 		.name		= name,
 		.module		= THIS_MODULE,
+		.parent		= &pdev->dev,
 		.event_init	= hns3_pmu_event_init,
 		.pmu_enable	= hns3_pmu_enable,
 		.pmu_disable	= hns3_pmu_disable,
@@ -1515,7 +1528,7 @@ static int hns3_pmu_irq_register(struct pci_dev *pdev,
 		return ret;
 	}
 
-	ret = devm_add_action(&pdev->dev, hns3_pmu_free_irq, pdev);
+	ret = devm_add_action_or_reset(&pdev->dev, hns3_pmu_free_irq, pdev);
 	if (ret) {
 		pci_err(pdev, "failed to add free irq action, ret = %d.\n", ret);
 		return ret;
diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c
index 148df5ae8ef8..980e3051edd7 100644
--- a/drivers/perf/qcom_l2_pmu.c
+++ b/drivers/perf/qcom_l2_pmu.c
@@ -801,9 +801,8 @@ static int l2cache_pmu_online_cpu(unsigned int cpu, struct hlist_node *node)
 
 static int l2cache_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
-	struct cluster_pmu *cluster;
 	struct l2cache_pmu *l2cache_pmu;
-	cpumask_t cluster_online_cpus;
+	struct cluster_pmu *cluster;
 	unsigned int target;
 
 	l2cache_pmu = hlist_entry_safe(node, struct l2cache_pmu, node);
@@ -820,9 +819,8 @@ static int l2cache_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	cluster->on_cpu = -1;
 
 	/* Any other CPU for this cluster which is still online */
-	cpumask_and(&cluster_online_cpus, &cluster->cluster_cpus,
-		    cpu_online_mask);
-	target = cpumask_any_but(&cluster_online_cpus, cpu);
+	target = cpumask_any_and_but(&cluster->cluster_cpus,
+				     cpu_online_mask, cpu);
 	if (target >= nr_cpu_ids) {
 		disable_irq(cluster->irq);
 		return 0;
@@ -904,6 +902,7 @@ static int l2_cache_pmu_probe(struct platform_device *pdev)
 	l2cache_pmu->pmu = (struct pmu) {
 		/* suffix is instance id for future use with multiple sockets */
 		.name		= "l2cache_0",
+		.parent		= &pdev->dev,
 		.task_ctx_nr    = perf_invalid_context,
 		.pmu_enable	= l2_cache_pmu_enable,
 		.pmu_disable	= l2_cache_pmu_disable,
diff --git a/drivers/perf/qcom_l3_pmu.c b/drivers/perf/qcom_l3_pmu.c
index f16783d03db7..37786e88514e 100644
--- a/drivers/perf/qcom_l3_pmu.c
+++ b/drivers/perf/qcom_l3_pmu.c
@@ -748,6 +748,7 @@ static int qcom_l3_cache_pmu_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	l3pmu->pmu = (struct pmu) {
+		.parent		= &pdev->dev,
 		.task_ctx_nr	= perf_invalid_context,
 
 		.pmu_enable	= qcom_l3_cache__pmu_enable,
diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c
index fa0bccf4edf2..04487ad7fba0 100644
--- a/drivers/perf/riscv_pmu_legacy.c
+++ b/drivers/perf/riscv_pmu_legacy.c
@@ -136,6 +136,7 @@ static int pmu_legacy_device_probe(struct platform_device *pdev)
 	pmu = riscv_pmu_alloc();
 	if (!pmu)
 		return -ENOMEM;
+	pmu->pmu.parent = &pdev->dev;
 	pmu_legacy_init(pmu);
 
 	return 0;
diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
index 8cbe6e5f9c39..82636273d726 100644
--- a/drivers/perf/riscv_pmu_sbi.c
+++ b/drivers/perf/riscv_pmu_sbi.c
@@ -1043,7 +1043,6 @@ static struct ctl_table sbi_pmu_sysctl_table[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_TWO,
 	},
-	{ }
 };
 
 static int pmu_sbi_device_probe(struct platform_device *pdev)
@@ -1081,6 +1080,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
 	}
 
 	pmu->pmu.attr_groups = riscv_pmu_attr_groups;
+	pmu->pmu.parent = &pdev->dev;
 	pmu->cmask = cmask;
 	pmu->ctr_start = pmu_sbi_ctr_start;
 	pmu->ctr_stop = pmu_sbi_ctr_stop;
diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c
index e16d10c763de..faf763d2c95c 100644
--- a/drivers/perf/thunderx2_pmu.c
+++ b/drivers/perf/thunderx2_pmu.c
@@ -504,24 +504,19 @@ static void tx2_uncore_event_update(struct perf_event *event)
 
 static enum tx2_uncore_type get_tx2_pmu_type(struct acpi_device *adev)
 {
-	int i = 0;
-	struct acpi_tx2_pmu_device {
-		__u8 id[ACPI_ID_LEN];
-		enum tx2_uncore_type type;
-	} devices[] = {
+	struct acpi_device_id devices[] = {
 		{"CAV901D", PMU_TYPE_L3C},
 		{"CAV901F", PMU_TYPE_DMC},
 		{"CAV901E", PMU_TYPE_CCPI2},
-		{"", PMU_TYPE_INVALID}
+		{}
 	};
+	const struct acpi_device_id *id;
 
-	while (devices[i].type != PMU_TYPE_INVALID) {
-		if (!strcmp(acpi_device_hid(adev), devices[i].id))
-			break;
-		i++;
-	}
+	id = acpi_match_acpi_device(devices, adev);
+	if (!id)
+		return PMU_TYPE_INVALID;
 
-	return devices[i].type;
+	return (enum tx2_uncore_type)id->driver_data;
 }
 
 static bool tx2_uncore_validate_event(struct pmu *pmu,
@@ -729,6 +724,7 @@ static int tx2_uncore_pmu_register(
 	/* Perf event registration */
 	tx2_pmu->pmu = (struct pmu) {
 		.module         = THIS_MODULE,
+		.parent		= tx2_pmu->dev,
 		.attr_groups	= tx2_pmu->attr_groups,
 		.task_ctx_nr	= perf_invalid_context,
 		.event_init	= tx2_uncore_event_init,
@@ -932,9 +928,8 @@ static int tx2_uncore_pmu_online_cpu(unsigned int cpu,
 static int tx2_uncore_pmu_offline_cpu(unsigned int cpu,
 		struct hlist_node *hpnode)
 {
-	int new_cpu;
 	struct tx2_uncore_pmu *tx2_pmu;
-	struct cpumask cpu_online_mask_temp;
+	unsigned int new_cpu;
 
 	tx2_pmu = hlist_entry_safe(hpnode,
 			struct tx2_uncore_pmu, hpnode);
@@ -945,11 +940,8 @@ static int tx2_uncore_pmu_offline_cpu(unsigned int cpu,
 	if (tx2_pmu->hrtimer_callback)
 		hrtimer_cancel(&tx2_pmu->hrtimer);
 
-	cpumask_copy(&cpu_online_mask_temp, cpu_online_mask);
-	cpumask_clear_cpu(cpu, &cpu_online_mask_temp);
-	new_cpu = cpumask_any_and(
-			cpumask_of_node(tx2_pmu->node),
-			&cpu_online_mask_temp);
+	new_cpu = cpumask_any_and_but(cpumask_of_node(tx2_pmu->node),
+				      cpu_online_mask, cpu);
 
 	tx2_pmu->cpu = new_cpu;
 	if (new_cpu >= nr_cpu_ids)
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index 0d49343d704b..8823b4c6b556 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1102,6 +1102,7 @@ static int xgene_init_perf(struct xgene_pmu_dev *pmu_dev, char *name)
 
 	/* Perf driver registration */
 	pmu_dev->pmu = (struct pmu) {
+		.parent		= pmu_dev->parent->dev,
 		.attr_groups	= pmu_dev->attr_groups,
 		.task_ctx_nr	= perf_invalid_context,
 		.pmu_enable	= xgene_perf_pmu_enable,
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 1c29947db848..121f3ac757ff 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -389,6 +389,29 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 }
 
 /**
+ * cpumask_any_and_but - pick a "random" cpu from *mask1 & *mask2, but not this one.
+ * @mask1: the first input cpumask
+ * @mask2: the second input cpumask
+ * @cpu: the cpu to ignore
+ *
+ * Returns >= nr_cpu_ids if no cpus set.
+ */
+static inline
+unsigned int cpumask_any_and_but(const struct cpumask *mask1,
+				 const struct cpumask *mask2,
+				 unsigned int cpu)
+{
+	unsigned int i;
+
+	cpumask_check(cpu);
+	i = cpumask_first_and(mask1, mask2);
+	if (i != cpu)
+		return i;
+
+	return cpumask_next_and(cpu, mask1, mask2);
+}
+
+/**
  * cpumask_nth - get the Nth cpu in a cpumask
  * @srcp: the cpumask pointer
  * @cpu: the Nth cpu to find, starting from 0