Merge tag 'irq-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull irq updates from Thomas Gleixner:
 "Updates for the interrupt subsystem:

  Core:

   - Move the interrupt affinity spreading mechanism into lib/group_cpus
     so it can be used for similar spreading requirements, e.g. in the
     block multi-queue code

     This also contains a first usecase in the block multi-queue code
     which Jens asked to take along with the librarization

   - Improve irqdomain locking to close a number race conditions which
     can be observed with massive parallel device driver probing

   - Enforce and document the semantics of disable_irq() which cannot be
     invoked safely from non-sleepable context

   - Move the IPI multiplexing code from the Apple AIC driver into the
     core, so it can be reused by RISCV

  Drivers:

   - Plug OF node refcounting leaks in various drivers

   - Correctly mark level triggered interrupts in the Broadcom L2
     drivers

   - The usual small fixes and improvements

   - No new drivers for the record!"

* tag 'irq-core-2023-02-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (42 commits)
  irqchip/irq-bcm7120-l2: Set IRQ_LEVEL for level triggered interrupts
  irqchip/irq-brcmstb-l2: Set IRQ_LEVEL for level triggered interrupts
  irqdomain: Switch to per-domain locking
  irqchip/mvebu-odmi: Use irq_domain_create_hierarchy()
  irqchip/loongson-pch-msi: Use irq_domain_create_hierarchy()
  irqchip/gic-v3-mbi: Use irq_domain_create_hierarchy()
  irqchip/gic-v3-its: Use irq_domain_create_hierarchy()
  irqchip/gic-v2m: Use irq_domain_create_hierarchy()
  irqchip/alpine-msi: Use irq_domain_add_hierarchy()
  x86/uv: Use irq_domain_create_hierarchy()
  x86/ioapic: Use irq_domain_create_hierarchy()
  irqdomain: Clean up irq_domain_push/pop_irq()
  irqdomain: Drop leftover brackets
  irqdomain: Drop dead domain-name assignment
  irqdomain: Drop revmap mutex
  irqdomain: Fix domain registration race
  irqdomain: Fix mapping-creation race
  irqdomain: Refactor __irq_domain_alloc_irqs()
  irqdomain: Look for existing mapping only once
  irqdomain: Drop bogus fwspec-mapping error handling
  ...

6 files changed, 470 insertions, 560 deletions

diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index b64c44ae4c25..2531f3496ab6 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -86,6 +86,11 @@ config GENERIC_IRQ_IPI
 	depends on SMP
 	select IRQ_DOMAIN_HIERARCHY
 
+# Generic IRQ IPI Mux support
+config GENERIC_IRQ_IPI_MUX
+	bool
+	depends on SMP
+
 # Generic MSI hierarchical interrupt domain support
 config GENERIC_MSI_IRQ
 	bool
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index b4f53717d143..f19d3080bf11 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_GENERIC_IRQ_MIGRATION) += cpuhotplug.o
 obj-$(CONFIG_PM_SLEEP) += pm.o
 obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o
 obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o
+obj-$(CONFIG_GENERIC_IRQ_IPI_MUX) += ipi-mux.o
 obj-$(CONFIG_SMP) += affinity.o
 obj-$(CONFIG_GENERIC_IRQ_DEBUGFS) += debugfs.o
 obj-$(CONFIG_GENERIC_IRQ_MATRIX_ALLOCATOR) += matrix.o
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index d9a5c1d65a79..44a4eba80315 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -7,398 +7,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
-#include <linux/sort.h>
-
-static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
-				unsigned int cpus_per_vec)
-{
-	const struct cpumask *siblmsk;
-	int cpu, sibl;
-
-	for ( ; cpus_per_vec > 0; ) {
-		cpu = cpumask_first(nmsk);
-
-		/* Should not happen, but I'm too lazy to think about it */
-		if (cpu >= nr_cpu_ids)
-			return;
-
-		cpumask_clear_cpu(cpu, nmsk);
-		cpumask_set_cpu(cpu, irqmsk);
-		cpus_per_vec--;
-
-		/* If the cpu has siblings, use them first */
-		siblmsk = topology_sibling_cpumask(cpu);
-		for (sibl = -1; cpus_per_vec > 0; ) {
-			sibl = cpumask_next(sibl, siblmsk);
-			if (sibl >= nr_cpu_ids)
-				break;
-			if (!cpumask_test_and_clear_cpu(sibl, nmsk))
-				continue;
-			cpumask_set_cpu(sibl, irqmsk);
-			cpus_per_vec--;
-		}
-	}
-}
-
-static cpumask_var_t *alloc_node_to_cpumask(void)
-{
-	cpumask_var_t *masks;
-	int node;
-
-	masks = kcalloc(nr_node_ids, sizeof(cpumask_var_t), GFP_KERNEL);
-	if (!masks)
-		return NULL;
-
-	for (node = 0; node < nr_node_ids; node++) {
-		if (!zalloc_cpumask_var(&masks[node], GFP_KERNEL))
-			goto out_unwind;
-	}
-
-	return masks;
-
-out_unwind:
-	while (--node >= 0)
-		free_cpumask_var(masks[node]);
-	kfree(masks);
-	return NULL;
-}
-
-static void free_node_to_cpumask(cpumask_var_t *masks)
-{
-	int node;
-
-	for (node = 0; node < nr_node_ids; node++)
-		free_cpumask_var(masks[node]);
-	kfree(masks);
-}
-
-static void build_node_to_cpumask(cpumask_var_t *masks)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		cpumask_set_cpu(cpu, masks[cpu_to_node(cpu)]);
-}
-
-static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask,
-				const struct cpumask *mask, nodemask_t *nodemsk)
-{
-	int n, nodes = 0;
-
-	/* Calculate the number of nodes in the supplied affinity mask */
-	for_each_node(n) {
-		if (cpumask_intersects(mask, node_to_cpumask[n])) {
-			node_set(n, *nodemsk);
-			nodes++;
-		}
-	}
-	return nodes;
-}
-
-struct node_vectors {
-	unsigned id;
-
-	union {
-		unsigned nvectors;
-		unsigned ncpus;
-	};
-};
-
-static int ncpus_cmp_func(const void *l, const void *r)
-{
-	const struct node_vectors *ln = l;
-	const struct node_vectors *rn = r;
-
-	return ln->ncpus - rn->ncpus;
-}
-
-/*
- * Allocate vector number for each node, so that for each node:
- *
- * 1) the allocated number is >= 1
- *
- * 2) the allocated numbver is <= active CPU number of this node
- *
- * The actual allocated total vectors may be less than @numvecs when
- * active total CPU number is less than @numvecs.
- *
- * Active CPUs means the CPUs in '@cpu_mask AND @node_to_cpumask[]'
- * for each node.
- */
-static void alloc_nodes_vectors(unsigned int numvecs,
-				cpumask_var_t *node_to_cpumask,
-				const struct cpumask *cpu_mask,
-				const nodemask_t nodemsk,
-				struct cpumask *nmsk,
-				struct node_vectors *node_vectors)
-{
-	unsigned n, remaining_ncpus = 0;
-
-	for (n = 0; n < nr_node_ids; n++) {
-		node_vectors[n].id = n;
-		node_vectors[n].ncpus = UINT_MAX;
-	}
-
-	for_each_node_mask(n, nodemsk) {
-		unsigned ncpus;
-
-		cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
-		ncpus = cpumask_weight(nmsk);
-
-		if (!ncpus)
-			continue;
-		remaining_ncpus += ncpus;
-		node_vectors[n].ncpus = ncpus;
-	}
-
-	numvecs = min_t(unsigned, remaining_ncpus, numvecs);
-
-	sort(node_vectors, nr_node_ids, sizeof(node_vectors[0]),
-	     ncpus_cmp_func, NULL);
-
-	/*
-	 * Allocate vectors for each node according to the ratio of this
-	 * node's nr_cpus to remaining un-assigned ncpus. 'numvecs' is
-	 * bigger than number of active numa nodes. Always start the
-	 * allocation from the node with minimized nr_cpus.
-	 *
-	 * This way guarantees that each active node gets allocated at
-	 * least one vector, and the theory is simple: over-allocation
-	 * is only done when this node is assigned by one vector, so
-	 * other nodes will be allocated >= 1 vector, since 'numvecs' is
-	 * bigger than number of numa nodes.
-	 *
-	 * One perfect invariant is that number of allocated vectors for
-	 * each node is <= CPU count of this node:
-	 *
-	 * 1) suppose there are two nodes: A and B
-	 * 	ncpu(X) is CPU count of node X
-	 * 	vecs(X) is the vector count allocated to node X via this
-	 * 	algorithm
-	 *
-	 * 	ncpu(A) <= ncpu(B)
-	 * 	ncpu(A) + ncpu(B) = N
-	 * 	vecs(A) + vecs(B) = V
-	 *
-	 * 	vecs(A) = max(1, round_down(V * ncpu(A) / N))
-	 * 	vecs(B) = V - vecs(A)
-	 *
-	 * 	both N and V are integer, and 2 <= V <= N, suppose
-	 * 	V = N - delta, and 0 <= delta <= N - 2
-	 *
-	 * 2) obviously vecs(A) <= ncpu(A) because:
-	 *
-	 * 	if vecs(A) is 1, then vecs(A) <= ncpu(A) given
-	 * 	ncpu(A) >= 1
-	 *
-	 * 	otherwise,
-	 * 		vecs(A) <= V * ncpu(A) / N <= ncpu(A), given V <= N
-	 *
-	 * 3) prove how vecs(B) <= ncpu(B):
-	 *
-	 * 	if round_down(V * ncpu(A) / N) == 0, vecs(B) won't be
-	 * 	over-allocated, so vecs(B) <= ncpu(B),
-	 *
-	 * 	otherwise:
-	 *
-	 * 	vecs(A) =
-	 * 		round_down(V * ncpu(A) / N) =
-	 * 		round_down((N - delta) * ncpu(A) / N) =
-	 * 		round_down((N * ncpu(A) - delta * ncpu(A)) / N)	 >=
-	 * 		round_down((N * ncpu(A) - delta * N) / N)	 =
-	 * 		cpu(A) - delta
-	 *
-	 * 	then:
-	 *
-	 * 	vecs(A) - V >= ncpu(A) - delta - V
-	 * 	=>
-	 * 	V - vecs(A) <= V + delta - ncpu(A)
-	 * 	=>
-	 * 	vecs(B) <= N - ncpu(A)
-	 * 	=>
-	 * 	vecs(B) <= cpu(B)
-	 *
-	 * For nodes >= 3, it can be thought as one node and another big
-	 * node given that is exactly what this algorithm is implemented,
-	 * and we always re-calculate 'remaining_ncpus' & 'numvecs', and
-	 * finally for each node X: vecs(X) <= ncpu(X).
-	 *
-	 */
-	for (n = 0; n < nr_node_ids; n++) {
-		unsigned nvectors, ncpus;
-
-		if (node_vectors[n].ncpus == UINT_MAX)
-			continue;
-
-		WARN_ON_ONCE(numvecs == 0);
-
-		ncpus = node_vectors[n].ncpus;
-		nvectors = max_t(unsigned, 1,
-				 numvecs * ncpus / remaining_ncpus);
-		WARN_ON_ONCE(nvectors > ncpus);
-
-		node_vectors[n].nvectors = nvectors;
-
-		remaining_ncpus -= ncpus;
-		numvecs -= nvectors;
-	}
-}
-
-static int __irq_build_affinity_masks(unsigned int startvec,
-				      unsigned int numvecs,
-				      unsigned int firstvec,
-				      cpumask_var_t *node_to_cpumask,
-				      const struct cpumask *cpu_mask,
-				      struct cpumask *nmsk,
-				      struct irq_affinity_desc *masks)
-{
-	unsigned int i, n, nodes, cpus_per_vec, extra_vecs, done = 0;
-	unsigned int last_affv = firstvec + numvecs;
-	unsigned int curvec = startvec;
-	nodemask_t nodemsk = NODE_MASK_NONE;
-	struct node_vectors *node_vectors;
-
-	if (cpumask_empty(cpu_mask))
-		return 0;
-
-	nodes = get_nodes_in_cpumask(node_to_cpumask, cpu_mask, &nodemsk);
-
-	/*
-	 * If the number of nodes in the mask is greater than or equal the
-	 * number of vectors we just spread the vectors across the nodes.
-	 */
-	if (numvecs <= nodes) {
-		for_each_node_mask(n, nodemsk) {
-			/* Ensure that only CPUs which are in both masks are set */
-			cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
-			cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk);
-			if (++curvec == last_affv)
-				curvec = firstvec;
-		}
-		return numvecs;
-	}
-
-	node_vectors = kcalloc(nr_node_ids,
-			       sizeof(struct node_vectors),
-			       GFP_KERNEL);
-	if (!node_vectors)
-		return -ENOMEM;
-
-	/* allocate vector number for each node */
-	alloc_nodes_vectors(numvecs, node_to_cpumask, cpu_mask,
-			    nodemsk, nmsk, node_vectors);
-
-	for (i = 0; i < nr_node_ids; i++) {
-		unsigned int ncpus, v;
-		struct node_vectors *nv = &node_vectors[i];
-
-		if (nv->nvectors == UINT_MAX)
-			continue;
-
-		/* Get the cpus on this node which are in the mask */
-		cpumask_and(nmsk, cpu_mask, node_to_cpumask[nv->id]);
-		ncpus = cpumask_weight(nmsk);
-		if (!ncpus)
-			continue;
-
-		WARN_ON_ONCE(nv->nvectors > ncpus);
-
-		/* Account for rounding errors */
-		extra_vecs = ncpus - nv->nvectors * (ncpus / nv->nvectors);
-
-		/* Spread allocated vectors on CPUs of the current node */
-		for (v = 0; v < nv->nvectors; v++, curvec++) {
-			cpus_per_vec = ncpus / nv->nvectors;
-
-			/* Account for extra vectors to compensate rounding errors */
-			if (extra_vecs) {
-				cpus_per_vec++;
-				--extra_vecs;
-			}
-
-			/*
-			 * wrapping has to be considered given 'startvec'
-			 * may start anywhere
-			 */
-			if (curvec >= last_affv)
-				curvec = firstvec;
-			irq_spread_init_one(&masks[curvec].mask, nmsk,
-						cpus_per_vec);
-		}
-		done += nv->nvectors;
-	}
-	kfree(node_vectors);
-	return done;
-}
-
-/*
- * build affinity in two stages:
- *	1) spread present CPU on these vectors
- *	2) spread other possible CPUs on these vectors
- */
-static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs,
-				    unsigned int firstvec,
-				    struct irq_affinity_desc *masks)
-{
-	unsigned int curvec = startvec, nr_present = 0, nr_others = 0;
-	cpumask_var_t *node_to_cpumask;
-	cpumask_var_t nmsk, npresmsk;
-	int ret = -ENOMEM;
-
-	if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
-		return ret;
-
-	if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL))
-		goto fail_nmsk;
-
-	node_to_cpumask = alloc_node_to_cpumask();
-	if (!node_to_cpumask)
-		goto fail_npresmsk;
-
-	/* Stabilize the cpumasks */
-	cpus_read_lock();
-	build_node_to_cpumask(node_to_cpumask);
-
-	/* Spread on present CPUs starting from affd->pre_vectors */
-	ret = __irq_build_affinity_masks(curvec, numvecs, firstvec,
-					 node_to_cpumask, cpu_present_mask,
-					 nmsk, masks);
-	if (ret < 0)
-		goto fail_build_affinity;
-	nr_present = ret;
-
-	/*
-	 * Spread on non present CPUs starting from the next vector to be
-	 * handled. If the spreading of present CPUs already exhausted the
-	 * vector space, assign the non present CPUs to the already spread
-	 * out vectors.
-	 */
-	if (nr_present >= numvecs)
-		curvec = firstvec;
-	else
-		curvec = firstvec + nr_present;
-	cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
-	ret = __irq_build_affinity_masks(curvec, numvecs, firstvec,
-					 node_to_cpumask, npresmsk, nmsk,
-					 masks);
-	if (ret >= 0)
-		nr_others = ret;
-
- fail_build_affinity:
-	cpus_read_unlock();
-
-	if (ret >= 0)
-		WARN_ON(nr_present + nr_others < numvecs);
-
-	free_node_to_cpumask(node_to_cpumask);
-
- fail_npresmsk:
-	free_cpumask_var(npresmsk);
-
- fail_nmsk:
-	free_cpumask_var(nmsk);
-	return ret < 0 ? ret : 0;
-}
+#include <linux/group_cpus.h>
 
 static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs)
 {
@@ -461,14 +70,18 @@ irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
 	 */
 	for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) {
 		unsigned int this_vecs = affd->set_size[i];
-		int ret;
+		int j;
+		struct cpumask *result = group_cpus_evenly(this_vecs);
 
-		ret = irq_build_affinity_masks(curvec, this_vecs,
-					       curvec, masks);
-		if (ret) {
+		if (!result) {
 			kfree(masks);
 			return NULL;
 		}
+
+		for (j = 0; j < this_vecs; j++)
+			cpumask_copy(&masks[curvec + j].mask, &result[j]);
+		kfree(result);
+
 		curvec += this_vecs;
 		usedvecs += this_vecs;
 	}
diff --git a/kernel/irq/ipi-mux.c b/kernel/irq/ipi-mux.c
new file mode 100644
index 000000000000..fa4fc18c6131
--- /dev/null
+++ b/kernel/irq/ipi-mux.c
@@ -0,0 +1,206 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Multiplex several virtual IPIs over a single HW IPI.
+ *
+ * Copyright The Asahi Linux Contributors
+ * Copyright (c) 2022 Ventana Micro Systems Inc.
+ */
+
+#define pr_fmt(fmt) "ipi-mux: " fmt
+#include <linux/cpu.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/jump_label.h>
+#include <linux/percpu.h>
+#include <linux/smp.h>
+
+struct ipi_mux_cpu {
+	atomic_t			enable;
+	atomic_t			bits;
+};
+
+static struct ipi_mux_cpu __percpu *ipi_mux_pcpu;
+static struct irq_domain *ipi_mux_domain;
+static void (*ipi_mux_send)(unsigned int cpu);
+
+static void ipi_mux_mask(struct irq_data *d)
+{
+	struct ipi_mux_cpu *icpu = this_cpu_ptr(ipi_mux_pcpu);
+
+	atomic_andnot(BIT(irqd_to_hwirq(d)), &icpu->enable);
+}
+
+static void ipi_mux_unmask(struct irq_data *d)
+{
+	struct ipi_mux_cpu *icpu = this_cpu_ptr(ipi_mux_pcpu);
+	u32 ibit = BIT(irqd_to_hwirq(d));
+
+	atomic_or(ibit, &icpu->enable);
+
+	/*
+	 * The atomic_or() above must complete before the atomic_read()
+	 * below to avoid racing ipi_mux_send_mask().
+	 */
+	smp_mb__after_atomic();
+
+	/* If a pending IPI was unmasked, raise a parent IPI immediately. */
+	if (atomic_read(&icpu->bits) & ibit)
+		ipi_mux_send(smp_processor_id());
+}
+
+static void ipi_mux_send_mask(struct irq_data *d, const struct cpumask *mask)
+{
+	struct ipi_mux_cpu *icpu = this_cpu_ptr(ipi_mux_pcpu);
+	u32 ibit = BIT(irqd_to_hwirq(d));
+	unsigned long pending;
+	int cpu;
+
+	for_each_cpu(cpu, mask) {
+		icpu = per_cpu_ptr(ipi_mux_pcpu, cpu);
+
+		/*
+		 * This sequence is the mirror of the one in ipi_mux_unmask();
+		 * see the comment there. Additionally, release semantics
+		 * ensure that the vIPI flag set is ordered after any shared
+		 * memory accesses that precede it. This therefore also pairs
+		 * with the atomic_fetch_andnot in ipi_mux_process().
+		 */
+		pending = atomic_fetch_or_release(ibit, &icpu->bits);
+
+		/*
+		 * The atomic_fetch_or_release() above must complete
+		 * before the atomic_read() below to avoid racing with
+		 * ipi_mux_unmask().
+		 */
+		smp_mb__after_atomic();
+
+		/*
+		 * The flag writes must complete before the physical IPI is
+		 * issued to another CPU. This is implied by the control
+		 * dependency on the result of atomic_read() below, which is
+		 * itself already ordered after the vIPI flag write.
+		 */
+		if (!(pending & ibit) && (atomic_read(&icpu->enable) & ibit))
+			ipi_mux_send(cpu);
+	}
+}
+
+static const struct irq_chip ipi_mux_chip = {
+	.name		= "IPI Mux",
+	.irq_mask	= ipi_mux_mask,
+	.irq_unmask	= ipi_mux_unmask,
+	.ipi_send_mask	= ipi_mux_send_mask,
+};
+
+static int ipi_mux_domain_alloc(struct irq_domain *d, unsigned int virq,
+				unsigned int nr_irqs, void *arg)
+{
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_set_percpu_devid(virq + i);
+		irq_domain_set_info(d, virq + i, i, &ipi_mux_chip, NULL,
+				    handle_percpu_devid_irq, NULL, NULL);
+	}
+
+	return 0;
+}
+
+static const struct irq_domain_ops ipi_mux_domain_ops = {
+	.alloc		= ipi_mux_domain_alloc,
+	.free		= irq_domain_free_irqs_top,
+};
+
+/**
+ * ipi_mux_process - Process multiplexed virtual IPIs
+ */
+void ipi_mux_process(void)
+{
+	struct ipi_mux_cpu *icpu = this_cpu_ptr(ipi_mux_pcpu);
+	irq_hw_number_t hwirq;
+	unsigned long ipis;
+	unsigned int en;
+
+	/*
+	 * Reading enable mask does not need to be ordered as long as
+	 * this function is called from interrupt handler because only
+	 * the CPU itself can change it's own enable mask.
+	 */
+	en = atomic_read(&icpu->enable);
+
+	/*
+	 * Clear the IPIs we are about to handle. This pairs with the
+	 * atomic_fetch_or_release() in ipi_mux_send_mask().
+	 */
+	ipis = atomic_fetch_andnot(en, &icpu->bits) & en;
+
+	for_each_set_bit(hwirq, &ipis, BITS_PER_TYPE(int))
+		generic_handle_domain_irq(ipi_mux_domain, hwirq);
+}
+
+/**
+ * ipi_mux_create - Create virtual IPIs multiplexed on top of a single
+ * parent IPI.
+ * @nr_ipi:		number of virtual IPIs to create. This should
+ *			be <= BITS_PER_TYPE(int)
+ * @mux_send:		callback to trigger parent IPI for a particular CPU
+ *
+ * Returns first virq of the newly created virtual IPIs upon success
+ * or <=0 upon failure
+ */
+int ipi_mux_create(unsigned int nr_ipi, void (*mux_send)(unsigned int cpu))
+{
+	struct fwnode_handle *fwnode;
+	struct irq_domain *domain;
+	int rc;
+
+	if (ipi_mux_domain)
+		return -EEXIST;
+
+	if (BITS_PER_TYPE(int) < nr_ipi || !mux_send)
+		return -EINVAL;
+
+	ipi_mux_pcpu = alloc_percpu(typeof(*ipi_mux_pcpu));
+	if (!ipi_mux_pcpu)
+		return -ENOMEM;
+
+	fwnode = irq_domain_alloc_named_fwnode("IPI-Mux");
+	if (!fwnode) {
+		pr_err("unable to create IPI Mux fwnode\n");
+		rc = -ENOMEM;
+		goto fail_free_cpu;
+	}
+
+	domain = irq_domain_create_linear(fwnode, nr_ipi,
+					  &ipi_mux_domain_ops, NULL);
+	if (!domain) {
+		pr_err("unable to add IPI Mux domain\n");
+		rc = -ENOMEM;
+		goto fail_free_fwnode;
+	}
+
+	domain->flags |= IRQ_DOMAIN_FLAG_IPI_SINGLE;
+	irq_domain_update_bus_token(domain, DOMAIN_BUS_IPI);
+
+	rc = irq_domain_alloc_irqs(domain, nr_ipi, NUMA_NO_NODE, NULL);
+	if (rc <= 0) {
+		pr_err("unable to alloc IRQs from IPI Mux domain\n");
+		goto fail_free_domain;
+	}
+
+	ipi_mux_domain = domain;
+	ipi_mux_send = mux_send;
+
+	return rc;
+
+fail_free_domain:
+	irq_domain_remove(domain);
+fail_free_fwnode:
+	irq_domain_free_fwnode(fwnode);
+fail_free_cpu:
+	free_percpu(ipi_mux_pcpu);
+	return rc;
+}
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 798a9042421f..aa5b7eeeceb8 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -25,6 +25,9 @@ static DEFINE_MUTEX(irq_domain_mutex);
 
 static struct irq_domain *irq_default_domain;
 
+static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base,
+					unsigned int nr_irqs, int node, void *arg,
+					bool realloc, const struct irq_affinity_desc *affinity);
 static void irq_domain_check_hierarchy(struct irq_domain *domain);
 
 struct irqchip_fwid {
@@ -123,23 +126,12 @@ void irq_domain_free_fwnode(struct fwnode_handle *fwnode)
 }
 EXPORT_SYMBOL_GPL(irq_domain_free_fwnode);
 
-/**
- * __irq_domain_add() - Allocate a new irq_domain data structure
- * @fwnode: firmware node for the interrupt controller
- * @size: Size of linear map; 0 for radix mapping only
- * @hwirq_max: Maximum number of interrupts supported by controller
- * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no
- *              direct mapping
- * @ops: domain callbacks
- * @host_data: Controller private data pointer
- *
- * Allocates and initializes an irq_domain structure.
- * Returns pointer to IRQ domain, or NULL on failure.
- */
-struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size,
-				    irq_hw_number_t hwirq_max, int direct_max,
-				    const struct irq_domain_ops *ops,
-				    void *host_data)
+static struct irq_domain *__irq_domain_create(struct fwnode_handle *fwnode,
+					      unsigned int size,
+					      irq_hw_number_t hwirq_max,
+					      int direct_max,
+					      const struct irq_domain_ops *ops,
+					      void *host_data)
 {
 	struct irqchip_fwid *fwid;
 	struct irq_domain *domain;
@@ -214,25 +206,66 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int s
 
 	/* Fill structure */
 	INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL);
-	mutex_init(&domain->revmap_mutex);
 	domain->ops = ops;
 	domain->host_data = host_data;
 	domain->hwirq_max = hwirq_max;
 
-	if (direct_max) {
+	if (direct_max)
 		domain->flags |= IRQ_DOMAIN_FLAG_NO_MAP;
-	}
 
 	domain->revmap_size = size;
 
+	/*
+	 * Hierarchical domains use the domain lock of the root domain
+	 * (innermost domain).
+	 *
+	 * For non-hierarchical domains (as for root domains), the root
+	 * pointer is set to the domain itself so that &domain->root->mutex
+	 * always points to the right lock.
+	 */
+	mutex_init(&domain->mutex);
+	domain->root = domain;
+
 	irq_domain_check_hierarchy(domain);
 
+	return domain;
+}
+
+static void __irq_domain_publish(struct irq_domain *domain)
+{
 	mutex_lock(&irq_domain_mutex);
 	debugfs_add_domain_dir(domain);
 	list_add(&domain->link, &irq_domain_list);
 	mutex_unlock(&irq_domain_mutex);
 
 	pr_debug("Added domain %s\n", domain->name);
+}
+
+/**
+ * __irq_domain_add() - Allocate a new irq_domain data structure
+ * @fwnode: firmware node for the interrupt controller
+ * @size: Size of linear map; 0 for radix mapping only
+ * @hwirq_max: Maximum number of interrupts supported by controller
+ * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no
+ *              direct mapping
+ * @ops: domain callbacks
+ * @host_data: Controller private data pointer
+ *
+ * Allocates and initializes an irq_domain structure.
+ * Returns pointer to IRQ domain, or NULL on failure.
+ */
+struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size,
+				    irq_hw_number_t hwirq_max, int direct_max,
+				    const struct irq_domain_ops *ops,
+				    void *host_data)
+{
+	struct irq_domain *domain;
+
+	domain = __irq_domain_create(fwnode, size, hwirq_max, direct_max,
+				     ops, host_data);
+	if (domain)
+		__irq_domain_publish(domain);
+
 	return domain;
 }
 EXPORT_SYMBOL_GPL(__irq_domain_add);
@@ -502,30 +535,34 @@ static bool irq_domain_is_nomap(struct irq_domain *domain)
 static void irq_domain_clear_mapping(struct irq_domain *domain,
 				     irq_hw_number_t hwirq)
 {
+	lockdep_assert_held(&domain->root->mutex);
+
 	if (irq_domain_is_nomap(domain))
 		return;
 
-	mutex_lock(&domain->revmap_mutex);
 	if (hwirq < domain->revmap_size)
 		rcu_assign_pointer(domain->revmap[hwirq], NULL);
 	else
 		radix_tree_delete(&domain->revmap_tree, hwirq);
-	mutex_unlock(&domain->revmap_mutex);
 }
 
 static void irq_domain_set_mapping(struct irq_domain *domain,
 				   irq_hw_number_t hwirq,
 				   struct irq_data *irq_data)
 {
+	/*
+	 * This also makes sure that all domains point to the same root when
+	 * called from irq_domain_insert_irq() for each domain in a hierarchy.
+	 */
+	lockdep_assert_held(&domain->root->mutex);
+
 	if (irq_domain_is_nomap(domain))
 		return;
 
-	mutex_lock(&domain->revmap_mutex);
 	if (hwirq < domain->revmap_size)
 		rcu_assign_pointer(domain->revmap[hwirq], irq_data);
 	else
 		radix_tree_insert(&domain->revmap_tree, hwirq, irq_data);
-	mutex_unlock(&domain->revmap_mutex);
 }
 
 static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq)
@@ -538,6 +575,9 @@ static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq)
 		return;
 
 	hwirq = irq_data->hwirq;
+
+	mutex_lock(&domain->root->mutex);
+
 	irq_set_status_flags(irq, IRQ_NOREQUEST);
 
 	/* remove chip and handler */
@@ -557,10 +597,12 @@ static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq)
 
 	/* Clear reverse map for this hwirq */
 	irq_domain_clear_mapping(domain, hwirq);
+
+	mutex_unlock(&domain->root->mutex);
 }
 
-int irq_domain_associate(struct irq_domain *domain, unsigned int virq,
-			 irq_hw_number_t hwirq)
+static int irq_domain_associate_locked(struct irq_domain *domain, unsigned int virq,
+				       irq_hw_number_t hwirq)
 {
 	struct irq_data *irq_data = irq_get_irq_data(virq);
 	int ret;
@@ -573,7 +615,6 @@ int irq_domain_associate(struct irq_domain *domain, unsigned int virq,
 	if (WARN(irq_data->domain, "error: virq%i is already associated", virq))
 		return -EINVAL;
 
-	mutex_lock(&irq_domain_mutex);
 	irq_data->hwirq = hwirq;
 	irq_data->domain = domain;
 	if (domain->ops->map) {
@@ -590,23 +631,29 @@ int irq_domain_associate(struct irq_domain *domain, unsigned int virq,
 			}
 			irq_data->domain = NULL;
 			irq_data->hwirq = 0;
-			mutex_unlock(&irq_domain_mutex);
 			return ret;
 		}
-
-		/* If not already assigned, give the domain the chip's name */
-		if (!domain->name && irq_data->chip)
-			domain->name = irq_data->chip->name;
 	}
 
 	domain->mapcount++;
 	irq_domain_set_mapping(domain, hwirq, irq_data);
-	mutex_unlock(&irq_domain_mutex);
 
 	irq_clear_status_flags(virq, IRQ_NOREQUEST);
 
 	return 0;
 }
+
+int irq_domain_associate(struct irq_domain *domain, unsigned int virq,
+			 irq_hw_number_t hwirq)
+{
+	int ret;
+
+	mutex_lock(&domain->root->mutex);
+	ret = irq_domain_associate_locked(domain, virq, hwirq);
+	mutex_unlock(&domain->root->mutex);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(irq_domain_associate);
 
 void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base,
@@ -619,9 +666,8 @@ void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base,
 	pr_debug("%s(%s, irqbase=%i, hwbase=%i, count=%i)\n", __func__,
 		of_node_full_name(of_node), irq_base, (int)hwirq_base, count);
 
-	for (i = 0; i < count; i++) {
+	for (i = 0; i < count; i++)
 		irq_domain_associate(domain, irq_base + i, hwirq_base + i);
-	}
 }
 EXPORT_SYMBOL_GPL(irq_domain_associate_many);
 
@@ -668,6 +714,34 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
 EXPORT_SYMBOL_GPL(irq_create_direct_mapping);
 #endif
 
+static unsigned int irq_create_mapping_affinity_locked(struct irq_domain *domain,
+						       irq_hw_number_t hwirq,
+						       const struct irq_affinity_desc *affinity)
+{
+	struct device_node *of_node = irq_domain_get_of_node(domain);
+	int virq;
+
+	pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
+
+	/* Allocate a virtual interrupt number */
+	virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node),
+				      affinity);
+	if (virq <= 0) {
+		pr_debug("-> virq allocation failed\n");
+		return 0;
+	}
+
+	if (irq_domain_associate_locked(domain, virq, hwirq)) {
+		irq_free_desc(virq);
+		return 0;
+	}
+
+	pr_debug("irq %lu on domain %s mapped to virtual irq %u\n",
+		hwirq, of_node_full_name(of_node), virq);
+
+	return virq;
+}
+
 /**
  * irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space
  * @domain: domain owning this hardware interrupt or NULL for default domain
@@ -680,14 +754,11 @@ EXPORT_SYMBOL_GPL(irq_create_direct_mapping);
  * on the number returned from that call.
  */
 unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
-				       irq_hw_number_t hwirq,
-				       const struct irq_affinity_desc *affinity)
+					 irq_hw_number_t hwirq,
+					 const struct irq_affinity_desc *affinity)
 {
-	struct device_node *of_node;
 	int virq;
 
-	pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
-
 	/* Look for default domain if necessary */
 	if (domain == NULL)
 		domain = irq_default_domain;
@@ -695,32 +766,19 @@ unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
 		WARN(1, "%s(, %lx) called with NULL domain\n", __func__, hwirq);
 		return 0;
 	}
-	pr_debug("-> using domain @%p\n", domain);
 
-	of_node = irq_domain_get_of_node(domain);
+	mutex_lock(&domain->root->mutex);
 
 	/* Check if mapping already exists */
 	virq = irq_find_mapping(domain, hwirq);
 	if (virq) {
-		pr_debug("-> existing mapping on virq %d\n", virq);
-		return virq;
-	}
-
-	/* Allocate a virtual interrupt number */
-	virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node),
-				      affinity);
-	if (virq <= 0) {
-		pr_debug("-> virq allocation failed\n");
-		return 0;
-	}
-
-	if (irq_domain_associate(domain, virq, hwirq)) {
-		irq_free_desc(virq);
-		return 0;
+		pr_debug("existing mapping on virq %d\n", virq);
+		goto out;
 	}
 
-	pr_debug("irq %lu on domain %s mapped to virtual irq %u\n",
-		hwirq, of_node_full_name(of_node), virq);
+	virq = irq_create_mapping_affinity_locked(domain, hwirq, affinity);
+out:
+	mutex_unlock(&domain->root->mutex);
 
 	return virq;
 }
@@ -789,6 +847,8 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
 	if (WARN_ON(type & ~IRQ_TYPE_SENSE_MASK))
 		type &= IRQ_TYPE_SENSE_MASK;
 
+	mutex_lock(&domain->root->mutex);
+
 	/*
 	 * If we've already configured this interrupt,
 	 * don't do it again, or hell will break loose.
@@ -801,7 +861,7 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
 		 * interrupt number.
 		 */
 		if (type == IRQ_TYPE_NONE || type == irq_get_trigger_type(virq))
-			return virq;
+			goto out;
 
 		/*
 		 * If the trigger type has not been set yet, then set
@@ -809,40 +869,45 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
 		 */
 		if (irq_get_trigger_type(virq) == IRQ_TYPE_NONE) {
 			irq_data = irq_get_irq_data(virq);
-			if (!irq_data)
-				return 0;
+			if (!irq_data) {
+				virq = 0;
+				goto out;
+			}
 
 			irqd_set_trigger_type(irq_data, type);
-			return virq;
+			goto out;
 		}
 
 		pr_warn("type mismatch, failed to map hwirq-%lu for %s!\n",
 			hwirq, of_node_full_name(to_of_node(fwspec->fwnode)));
-		return 0;
+		virq = 0;
+		goto out;
 	}
 
 	if (irq_domain_is_hierarchy(domain)) {
-		virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, fwspec);
-		if (virq <= 0)
-			return 0;
+		virq = irq_domain_alloc_irqs_locked(domain, -1, 1, NUMA_NO_NODE,
+						    fwspec, false, NULL);
+		if (virq <= 0) {
+			virq = 0;
+			goto out;
+		}
 	} else {
 		/* Create mapping */
-		virq = irq_create_mapping(domain, hwirq);
+		virq = irq_create_mapping_affinity_locked(domain, hwirq, NULL);
 		if (!virq)
-			return virq;
+			goto out;
 	}
 
 	irq_data = irq_get_irq_data(virq);
-	if (!irq_data) {
-		if (irq_domain_is_hierarchy(domain))
-			irq_domain_free_irqs(virq, 1);
-		else
-			irq_dispose_mapping(virq);
-		return 0;
+	if (WARN_ON(!irq_data)) {
+		virq = 0;
+		goto out;
 	}
 
 	/* Store trigger type */
 	irqd_set_trigger_type(irq_data, type);
+out:
+	mutex_unlock(&domain->root->mutex);
 
 	return virq;
 }
@@ -1102,12 +1167,16 @@ struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent,
 	struct irq_domain *domain;
 
 	if (size)
-		domain = irq_domain_create_linear(fwnode, size, ops, host_data);
+		domain = __irq_domain_create(fwnode, size, size, 0, ops, host_data);
 	else
-		domain = irq_domain_create_tree(fwnode, ops, host_data);
+		domain = __irq_domain_create(fwnode, 0, ~0, 0, ops, host_data);
+
 	if (domain) {
+		domain->root = parent->root;
 		domain->parent = parent;
 		domain->flags |= flags;
+
+		__irq_domain_publish(domain);
 	}
 
 	return domain;
@@ -1123,10 +1192,6 @@ static void irq_domain_insert_irq(int virq)
 
 		domain->mapcount++;
 		irq_domain_set_mapping(domain, data->hwirq, data);
-
-		/* If not already assigned, give the domain the chip's name */
-		if (!domain->name && data->chip)
-			domain->name = data->chip->name;
 	}
 
 	irq_clear_status_flags(virq, IRQ_NOREQUEST);
@@ -1426,40 +1491,12 @@ int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
 	return domain->ops->alloc(domain, irq_base, nr_irqs, arg);
 }
 
-/**
- * __irq_domain_alloc_irqs - Allocate IRQs from domain
- * @domain:	domain to allocate from
- * @irq_base:	allocate specified IRQ number if irq_base >= 0
- * @nr_irqs:	number of IRQs to allocate
- * @node:	NUMA node id for memory allocation
- * @arg:	domain specific argument
- * @realloc:	IRQ descriptors have already been allocated if true
- * @affinity:	Optional irq affinity mask for multiqueue devices
- *
- * Allocate IRQ numbers and initialized all data structures to support
- * hierarchy IRQ domains.
- * Parameter @realloc is mainly to support legacy IRQs.
- * Returns error code or allocated IRQ number
- *
- * The whole process to setup an IRQ has been split into two steps.
- * The first step, __irq_domain_alloc_irqs(), is to allocate IRQ
- * descriptor and required hardware resources. The second step,
- * irq_domain_activate_irq(), is to program the hardware with preallocated
- * resources. In this way, it's easier to rollback when failing to
- * allocate resources.
- */
-int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
-			    unsigned int nr_irqs, int node, void *arg,
-			    bool realloc, const struct irq_affinity_desc *affinity)
+static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base,
+					unsigned int nr_irqs, int node, void *arg,
+					bool realloc, const struct irq_affinity_desc *affinity)
 {
 	int i, ret, virq;
 
-	if (domain == NULL) {
-		domain = irq_default_domain;
-		if (WARN(!domain, "domain is NULL; cannot allocate IRQ\n"))
-			return -EINVAL;
-	}
-
 	if (realloc && irq_base >= 0) {
 		virq = irq_base;
 	} else {
@@ -1478,24 +1515,18 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
 		goto out_free_desc;
 	}
 
-	mutex_lock(&irq_domain_mutex);
 	ret = irq_domain_alloc_irqs_hierarchy(domain, virq, nr_irqs, arg);
-	if (ret < 0) {
-		mutex_unlock(&irq_domain_mutex);
+	if (ret < 0)
 		goto out_free_irq_data;
-	}
 
 	for (i = 0; i < nr_irqs; i++) {
 		ret = irq_domain_trim_hierarchy(virq + i);
-		if (ret) {
-			mutex_unlock(&irq_domain_mutex);
+		if (ret)
 			goto out_free_irq_data;
-		}
 	}
-	
+
 	for (i = 0; i < nr_irqs; i++)
 		irq_domain_insert_irq(virq + i);
-	mutex_unlock(&irq_domain_mutex);
 
 	return virq;
 
@@ -1505,6 +1536,48 @@ out_free_desc:
 	irq_free_descs(virq, nr_irqs);
 	return ret;
 }
+
+/**
+ * __irq_domain_alloc_irqs - Allocate IRQs from domain
+ * @domain:	domain to allocate from
+ * @irq_base:	allocate specified IRQ number if irq_base >= 0
+ * @nr_irqs:	number of IRQs to allocate
+ * @node:	NUMA node id for memory allocation
+ * @arg:	domain specific argument
+ * @realloc:	IRQ descriptors have already been allocated if true
+ * @affinity:	Optional irq affinity mask for multiqueue devices
+ *
+ * Allocate IRQ numbers and initialized all data structures to support
+ * hierarchy IRQ domains.
+ * Parameter @realloc is mainly to support legacy IRQs.
+ * Returns error code or allocated IRQ number
+ *
+ * The whole process to setup an IRQ has been split into two steps.
+ * The first step, __irq_domain_alloc_irqs(), is to allocate IRQ
+ * descriptor and required hardware resources. The second step,
+ * irq_domain_activate_irq(), is to program the hardware with preallocated
+ * resources. In this way, it's easier to rollback when failing to
+ * allocate resources.
+ */
+int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
+			    unsigned int nr_irqs, int node, void *arg,
+			    bool realloc, const struct irq_affinity_desc *affinity)
+{
+	int ret;
+
+	if (domain == NULL) {
+		domain = irq_default_domain;
+		if (WARN(!domain, "domain is NULL; cannot allocate IRQ\n"))
+			return -EINVAL;
+	}
+
+	mutex_lock(&domain->root->mutex);
+	ret = irq_domain_alloc_irqs_locked(domain, irq_base, nr_irqs, node, arg,
+					   realloc, affinity);
+	mutex_unlock(&domain->root->mutex);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(__irq_domain_alloc_irqs);
 
 /* The irq_data was moved, fix the revmap to refer to the new location */
@@ -1512,11 +1585,12 @@ static void irq_domain_fix_revmap(struct irq_data *d)
 {
 	void __rcu **slot;
 
+	lockdep_assert_held(&d->domain->root->mutex);
+
 	if (irq_domain_is_nomap(d->domain))
 		return;
 
 	/* Fix up the revmap. */
-	mutex_lock(&d->domain->revmap_mutex);
 	if (d->hwirq < d->domain->revmap_size) {
 		/* Not using radix tree */
 		rcu_assign_pointer(d->domain->revmap[d->hwirq], d);
@@ -1525,7 +1599,6 @@ static void irq_domain_fix_revmap(struct irq_data *d)
 		if (slot)
 			radix_tree_replace_slot(&d->domain->revmap_tree, slot, d);
 	}
-	mutex_unlock(&d->domain->revmap_mutex);
 }
 
 /**
@@ -1541,8 +1614,8 @@ static void irq_domain_fix_revmap(struct irq_data *d)
  */
 int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg)
 {
-	struct irq_data *child_irq_data;
-	struct irq_data *root_irq_data = irq_get_irq_data(virq);
+	struct irq_data *irq_data = irq_get_irq_data(virq);
+	struct irq_data *parent_irq_data;
 	struct irq_desc *desc;
 	int rv = 0;
 
@@ -1567,47 +1640,46 @@ int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg)
 	if (WARN_ON(!irq_domain_is_hierarchy(domain)))
 		return -EINVAL;
 
-	if (!root_irq_data)
+	if (!irq_data)
 		return -EINVAL;
 
-	if (domain->parent != root_irq_data->domain)
+	if (domain->parent != irq_data->domain)
 		return -EINVAL;
 
-	child_irq_data = kzalloc_node(sizeof(*child_irq_data), GFP_KERNEL,
-				      irq_data_get_node(root_irq_data));
-	if (!child_irq_data)
+	parent_irq_data = kzalloc_node(sizeof(*parent_irq_data), GFP_KERNEL,
+				       irq_data_get_node(irq_data));
+	if (!parent_irq_data)
 		return -ENOMEM;
 
-	mutex_lock(&irq_domain_mutex);
+	mutex_lock(&domain->root->mutex);
 
 	/* Copy the original irq_data. */
-	*child_irq_data = *root_irq_data;
+	*parent_irq_data = *irq_data;
 
 	/*
-	 * Overwrite the root_irq_data, which is embedded in struct
-	 * irq_desc, with values for this domain.
+	 * Overwrite the irq_data, which is embedded in struct irq_desc, with
+	 * values for this domain.
 	 */
-	root_irq_data->parent_data = child_irq_data;
-	root_irq_data->domain = domain;
-	root_irq_data->mask = 0;
-	root_irq_data->hwirq = 0;
-	root_irq_data->chip = NULL;
-	root_irq_data->chip_data = NULL;
+	irq_data->parent_data = parent_irq_data;
+	irq_data->domain = domain;
+	irq_data->mask = 0;
+	irq_data->hwirq = 0;
+	irq_data->chip = NULL;
+	irq_data->chip_data = NULL;
 
 	/* May (probably does) set hwirq, chip, etc. */
 	rv = irq_domain_alloc_irqs_hierarchy(domain, virq, 1, arg);
 	if (rv) {
 		/* Restore the original irq_data. */
-		*root_irq_data = *child_irq_data;
-		kfree(child_irq_data);
+		*irq_data = *parent_irq_data;
+		kfree(parent_irq_data);
 		goto error;
 	}
 
-	irq_domain_fix_revmap(child_irq_data);
-	irq_domain_set_mapping(domain, root_irq_data->hwirq, root_irq_data);
-
+	irq_domain_fix_revmap(parent_irq_data);
+	irq_domain_set_mapping(domain, irq_data->hwirq, irq_data);
 error:
-	mutex_unlock(&irq_domain_mutex);
+	mutex_unlock(&domain->root->mutex);
 
 	return rv;
 }
@@ -1623,8 +1695,8 @@ EXPORT_SYMBOL_GPL(irq_domain_push_irq);
  */
 int irq_domain_pop_irq(struct irq_domain *domain, int virq)
 {
-	struct irq_data *root_irq_data = irq_get_irq_data(virq);
-	struct irq_data *child_irq_data;
+	struct irq_data *irq_data = irq_get_irq_data(virq);
+	struct irq_data *parent_irq_data;
 	struct irq_data *tmp_irq_data;
 	struct irq_desc *desc;
 
@@ -1646,37 +1718,37 @@ int irq_domain_pop_irq(struct irq_domain *domain, int virq)
 	if (domain == NULL)
 		return -EINVAL;
 
-	if (!root_irq_data)
+	if (!irq_data)
 		return -EINVAL;
 
 	tmp_irq_data = irq_domain_get_irq_data(domain, virq);
 
 	/* We can only "pop" if this domain is at the top of the list */
-	if (WARN_ON(root_irq_data != tmp_irq_data))
+	if (WARN_ON(irq_data != tmp_irq_data))
 		return -EINVAL;
 
-	if (WARN_ON(root_irq_data->domain != domain))
+	if (WARN_ON(irq_data->domain != domain))
 		return -EINVAL;
 
-	child_irq_data = root_irq_data->parent_data;
-	if (WARN_ON(!child_irq_data))
+	parent_irq_data = irq_data->parent_data;
+	if (WARN_ON(!parent_irq_data))
 		return -EINVAL;
 
-	mutex_lock(&irq_domain_mutex);
+	mutex_lock(&domain->root->mutex);
 
-	root_irq_data->parent_data = NULL;
+	irq_data->parent_data = NULL;
 
-	irq_domain_clear_mapping(domain, root_irq_data->hwirq);
+	irq_domain_clear_mapping(domain, irq_data->hwirq);
 	irq_domain_free_irqs_hierarchy(domain, virq, 1);
 
 	/* Restore the original irq_data. */
-	*root_irq_data = *child_irq_data;
+	*irq_data = *parent_irq_data;
 
-	irq_domain_fix_revmap(root_irq_data);
+	irq_domain_fix_revmap(irq_data);
 
-	mutex_unlock(&irq_domain_mutex);
+	mutex_unlock(&domain->root->mutex);
 
-	kfree(child_irq_data);
+	kfree(parent_irq_data);
 
 	return 0;
 }
@@ -1690,17 +1762,20 @@ EXPORT_SYMBOL_GPL(irq_domain_pop_irq);
 void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs)
 {
 	struct irq_data *data = irq_get_irq_data(virq);
+	struct irq_domain *domain;
 	int i;
 
 	if (WARN(!data || !data->domain || !data->domain->ops->free,
 		 "NULL pointer, cannot free irq\n"))
 		return;
 
-	mutex_lock(&irq_domain_mutex);
+	domain = data->domain;
+
+	mutex_lock(&domain->root->mutex);
 	for (i = 0; i < nr_irqs; i++)
 		irq_domain_remove_irq(virq + i);
-	irq_domain_free_irqs_hierarchy(data->domain, virq, nr_irqs);
-	mutex_unlock(&irq_domain_mutex);
+	irq_domain_free_irqs_hierarchy(domain, virq, nr_irqs);
+	mutex_unlock(&domain->root->mutex);
 
 	irq_domain_free_irq_data(virq, nr_irqs);
 	irq_free_descs(virq, nr_irqs);
@@ -1865,6 +1940,13 @@ void irq_domain_set_info(struct irq_domain *domain, unsigned int virq,
 	irq_set_handler_data(virq, handler_data);
 }
 
+static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base,
+					unsigned int nr_irqs, int node, void *arg,
+					bool realloc, const struct irq_affinity_desc *affinity)
+{
+	return -EINVAL;
+}
+
 static void irq_domain_check_hierarchy(struct irq_domain *domain)
 {
 }
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 5b7cf28df290..8ce75495e04f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -723,10 +723,13 @@ EXPORT_SYMBOL(disable_irq_nosync);
  *	to complete before returning. If you use this function while
  *	holding a resource the IRQ handler may need you will deadlock.
  *
- *	This function may be called - with care - from IRQ context.
+ *	Can only be called from preemptible code as it might sleep when
+ *	an interrupt thread is associated to @irq.
+ *
  */
 void disable_irq(unsigned int irq)
 {
+	might_sleep();
 	if (!__disable_irq_nosync(irq))
 		synchronize_irq(irq);
 }