Merge branch 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull genirq updates from Thomas Gleixner:
 "The irq departement provides:

   - A synchronization fix for free_irq() to synchronize just the
     removed interrupt thread on shared interrupt lines.

   - Consolidate the multi low level interrupt entry handling and mvoe
     it to the generic code instead of adding yet another copy for
     RISC-V

   - Refactoring of the ARM LPI allocator and LPI exposure to the
     hypervisor

   - Yet another interrupt chip driver for the JZ4725B SoC

   - Speed up for /proc/interrupts as people seem to love reading this
     file with high frequency

   - Miscellaneous fixes and updates"

* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  irqchip/gic-v3-its: Make its_lock a raw_spin_lock_t
  genirq/irqchip: Remove MULTI_IRQ_HANDLER as it's now obselete
  openrisc: Use the new GENERIC_IRQ_MULTI_HANDLER
  arm64: Use the new GENERIC_IRQ_MULTI_HANDLER
  ARM: Convert to GENERIC_IRQ_MULTI_HANDLER
  irqchip: Port the ARM IRQ drivers to GENERIC_IRQ_MULTI_HANDLER
  irqchip/gic-v3-its: Reduce minimum LPI allocation to 1 for PCI devices
  dt-bindings: irqchip: renesas-irqc: Document r8a77980 support
  dt-bindings: irqchip: renesas-irqc: Document r8a77470 support
  irqchip/ingenic: Add support for the JZ4725B SoC
  irqchip/stm32: Add exti0 translation for stm32mp1
  genirq: Remove redundant NULL pointer check in __free_irq()
  irqchip/gic-v3-its: Honor hypervisor enforced LPI range
  irqchip/gic-v3: Expose GICD_TYPER in the rdist structure
  irqchip/gic-v3-its: Drop chunk allocation compatibility
  irqchip/gic-v3-its: Move minimum LPI requirements to individual busses
  irqchip/gic-v3-its: Use full range of LPIs
  irqchip/gic-v3-its: Refactor LPI allocator
  genirq: Synchronize only with single thread on free_irq()
  genirq: Update code comments wrt recycled thread_mask
  ...

Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt

@@ -4,6 +4,7 @@ Required properties:
 
 - compatible : should be "ingenic,<socname>-intc". Valid strings are:
     ingenic,jz4740-intc
+    ingenic,jz4725b-intc
     ingenic,jz4770-intc
     ingenic,jz4775-intc
     ingenic,jz4780-intc

Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt

@@ -7,6 +7,7 @@ Required properties:
     - "renesas,irqc-r8a73a4" (R-Mobile APE6)
     - "renesas,irqc-r8a7743" (RZ/G1M)
     - "renesas,irqc-r8a7745" (RZ/G1E)
+    - "renesas,irqc-r8a77470" (RZ/G1C)
     - "renesas,irqc-r8a7790" (R-Car H2)
     - "renesas,irqc-r8a7791" (R-Car M2-W)
     - "renesas,irqc-r8a7792" (R-Car V2H)
@@ -16,6 +17,7 @@ Required properties:
     - "renesas,intc-ex-r8a7796" (R-Car M3-W)
     - "renesas,intc-ex-r8a77965" (R-Car M3-N)
     - "renesas,intc-ex-r8a77970" (R-Car V3M)
+    - "renesas,intc-ex-r8a77980" (R-Car V3H)
     - "renesas,intc-ex-r8a77995" (R-Car D3)
 - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
   interrupts.txt in this directory

arch/arm/Kconfig

@@ -337,8 +337,8 @@ config ARCH_MULTIPLATFORM
 	select TIMER_OF
 	select COMMON_CLK
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select MIGHT_HAVE_PCI
-	select MULTI_IRQ_HANDLER
 	select PCI_DOMAINS if PCI
 	select SPARSE_IRQ
 	select USE_OF
@@ -465,9 +465,9 @@ config ARCH_DOVE
 	bool "Marvell Dove"
 	select CPU_PJ4
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select MIGHT_HAVE_PCI
-	select MULTI_IRQ_HANDLER
 	select MVEBU_MBUS
 	select PINCTRL
 	select PINCTRL_DOVE
@@ -512,8 +512,8 @@ config ARCH_LPC32XX
 	select COMMON_CLK
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
-	select MULTI_IRQ_HANDLER
 	select SPARSE_IRQ
 	select USE_OF
 	help
@@ -532,11 +532,11 @@ config ARCH_PXA
 	select TIMER_OF
 	select CPU_XSCALE if !CPU_XSC3
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIO_PXA
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
 	select PLAT_PXA
 	select SPARSE_IRQ
 	help
@@ -572,11 +572,11 @@ config ARCH_SA1100
 	select CPU_FREQ
 	select CPU_SA1100
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
 	select ISA
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_MEMORY_H
 	select SPARSE_IRQ
 	help
@@ -590,10 +590,10 @@ config ARCH_S3C24XX
 	select GENERIC_CLOCKEVENTS
 	select GPIO_SAMSUNG
 	select GPIOLIB
+	select GENERIC_IRQ_MULTI_HANDLER
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select HAVE_S3C_RTC if RTC_CLASS
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_IO_H
 	select SAMSUNG_ATAGS
 	select USE_OF
@@ -627,10 +627,10 @@ config ARCH_OMAP1
 	select CLKSRC_MMIO
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_CHIP
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_IO_H if PCCARD
 	select NEED_MACH_MEMORY_H
 	select SPARSE_IRQ
@@ -921,11 +921,6 @@ config IWMMXT
 	  Enable support for iWMMXt context switching at run time if
 	  running on a CPU that supports it.
 
-config MULTI_IRQ_HANDLER
-	bool
-	help
-	  Allow each machine to specify it's own IRQ handler at run time.
-
 if !MMU
 source "arch/arm/Kconfig-nommu"
 endif

arch/arm/include/asm/irq.h

@@ -31,11 +31,6 @@ extern void asm_do_IRQ(unsigned int, struct pt_regs *);
 void handle_IRQ(unsigned int, struct pt_regs *);
 void init_IRQ(void);
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-extern void (*handle_arch_irq)(struct pt_regs *);
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-#endif
-
 #ifdef CONFIG_SMP
 extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
 					   bool exclude_self);

arch/arm/include/asm/mach/arch.h

@@ -59,7 +59,7 @@ struct machine_desc {
 	void			(*init_time)(void);
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	void			(*handle_irq)(struct pt_regs *);
 #endif
 	void			(*restart)(enum reboot_mode, const char *);

arch/arm/kernel/entry-armv.S

@@ -22,7 +22,7 @@
 #include <asm/glue-df.h>
 #include <asm/glue-pf.h>
 #include <asm/vfpmacros.h>
-#ifndef CONFIG_MULTI_IRQ_HANDLER
+#ifndef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 #include <mach/entry-macro.S>
 #endif
 #include <asm/thread_notify.h>
@@ -39,7 +39,7 @@
  * Interrupt handling.
  */
 	.macro	irq_handler
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	ldr	r1, =handle_arch_irq
 	mov	r0, sp
 	badr	lr, 9997f
@@ -1226,9 +1226,3 @@ vector_addrexcptn:
 	.globl	cr_alignment
 cr_alignment:
 	.space	4
-
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-	.globl	handle_arch_irq
-handle_arch_irq:
-	.space	4
-#endif

arch/arm/kernel/irq.c

@@ -102,16 +102,6 @@ void __init init_IRQ(void)
 	uniphier_cache_init();
 }
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	if (handle_arch_irq)
-		return;
-
-	handle_arch_irq = handle_irq;
-}
-#endif
-
 #ifdef CONFIG_SPARSE_IRQ
 int __init arch_probe_nr_irqs(void)
 {

arch/arm/kernel/setup.c

@@ -1145,7 +1145,7 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_crashkernel();
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	handle_arch_irq = mdesc->handle_irq;
 #endif
 

arch/arm64/Kconfig

@@ -74,6 +74,7 @@ config ARM64
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
@@ -264,9 +265,6 @@ config ARCH_SUPPORTS_UPROBES
 config ARCH_PROC_KCORE_TEXT
 	def_bool y
 
-config MULTI_IRQ_HANDLER
-	def_bool y
-
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/arm64/include/asm/irq.h

@@ -8,8 +8,6 @@
 
 struct pt_regs;
 
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-
 static inline int nr_legacy_irqs(void)
 {
 	return 0;

arch/arm64/kernel/irq.c

@@ -42,16 +42,6 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	return 0;
 }
 
-void (*handle_arch_irq)(struct pt_regs *) = NULL;
-
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	if (handle_arch_irq)
-		return;
-
-	handle_arch_irq = handle_irq;
-}
-
 #ifdef CONFIG_VMAP_STACK
 static void init_irq_stacks(void)
 {

arch/openrisc/Kconfig

@@ -27,7 +27,6 @@ config OPENRISC
 	select GENERIC_STRNLEN_USER
 	select GENERIC_SMP_IDLE_THREAD
 	select MODULES_USE_ELF_RELA
-	select MULTI_IRQ_HANDLER
 	select HAVE_DEBUG_STACKOVERFLOW
 	select OR1K_PIC
 	select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1
@@ -36,6 +35,7 @@ config OPENRISC
 	select ARCH_USE_QUEUED_RWLOCKS
 	select OMPIC if SMP
 	select ARCH_WANT_FRAME_POINTERS
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config CPU_BIG_ENDIAN
 	def_bool y
@@ -69,9 +69,6 @@ config STACKTRACE_SUPPORT
 config LOCKDEP_SUPPORT
 	def_bool  y
 
-config MULTI_IRQ_HANDLER
-	def_bool y
-
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"

arch/openrisc/include/asm/irq.h

@@ -24,6 +24,4 @@
 
 #define NO_IRQ		(-1)
 
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-
 #endif /* __ASM_OPENRISC_IRQ_H__ */

arch/openrisc/kernel/irq.c

@@ -41,13 +41,6 @@ void __init init_IRQ(void)
 	irqchip_init();
 }
 
-static void (*handle_arch_irq)(struct pt_regs *);
-
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	handle_arch_irq = handle_irq;
-}
-
 void __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	handle_arch_irq(regs);

drivers/irqchip/Kconfig

@@ -8,7 +8,7 @@ config ARM_GIC
 	bool
 	select IRQ_DOMAIN
 	select IRQ_DOMAIN_HIERARCHY
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
 
 config ARM_GIC_PM
@@ -34,7 +34,7 @@ config GIC_NON_BANKED
 config ARM_GIC_V3
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select IRQ_DOMAIN_HIERARCHY
 	select PARTITION_PERCPU
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
@@ -66,7 +66,7 @@ config ARM_NVIC
 config ARM_VIC
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config ARM_VIC_NR
 	int
@@ -93,14 +93,14 @@ config ATMEL_AIC_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config ATMEL_AIC5_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config I8259
@@ -137,7 +137,7 @@ config DW_APB_ICTL
 config FARADAY_FTINTC010
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config HISILICON_IRQ_MBIGEN
@@ -162,7 +162,7 @@ config CLPS711X_IRQCHIP
 	bool
 	depends on ARCH_CLPS711X
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 	default y
 
@@ -181,7 +181,7 @@ config OMAP_IRQCHIP
 config ORION_IRQCHIP
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config PIC32_EVIC
 	bool

drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c

@@ -45,6 +45,9 @@ static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain,
 	 */
 	info->scratchpad[0].ul = mc_bus_dev->icid;
 	msi_info = msi_get_domain_info(msi_domain->parent);
+
+	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
 	return msi_info->ops->msi_prepare(msi_domain->parent, dev, nvec, info);
 }
 

drivers/irqchip/irq-gic-v3-its-pci-msi.c

@@ -66,7 +66,7 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 {
 	struct pci_dev *pdev, *alias_dev;
 	struct msi_domain_info *msi_info;
-	int alias_count = 0;
+	int alias_count = 0, minnvec = 1;
 
 	if (!dev_is_pci(dev))
 		return -EINVAL;
@@ -86,8 +86,18 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain, pdev);
 
-	return msi_info->ops->msi_prepare(domain->parent,
-					  dev, max(nvec, alias_count), info);
+	/*
+	 * Always allocate a power of 2, and special case device 0 for
+	 * broken systems where the DevID is not wired (and all devices
+	 * appear as DevID 0). For that reason, we generously allocate a
+	 * minimum of 32 MSIs for DevID 0. If you want more because all
+	 * your devices are aliasing to DevID 0, consider fixing your HW.
+	 */
+	nvec = max(nvec, alias_count);
+	if (!info->scratchpad[0].ul)
+		minnvec = 32;
+	nvec = max_t(int, minnvec, roundup_pow_of_two(nvec));
+	return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info);
 }
 
 static struct msi_domain_ops its_pci_msi_ops = {

drivers/irqchip/irq-gic-v3-its-platform-msi.c

@@ -73,6 +73,8 @@ static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = dev_id;
 
+	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
 	return msi_info->ops->msi_prepare(domain->parent,
 					  dev, nvec, info);
 }

drivers/irqchip/irq-gic-v3-its.c

@@ -23,6 +23,8 @@
 #include <linux/dma-iommu.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
+#include <linux/list.h>
+#include <linux/list_sort.h>
 #include <linux/log2.h>
 #include <linux/mm.h>
 #include <linux/msi.h>
@@ -160,7 +162,7 @@ static struct {
 } vpe_proxy;
 
 static LIST_HEAD(its_nodes);
-static DEFINE_SPINLOCK(its_lock);
+static DEFINE_RAW_SPINLOCK(its_lock);
 static struct rdists *gic_rdists;
 static struct irq_domain *its_parent;
 
@@ -1421,112 +1423,176 @@ static struct irq_chip its_irq_chip = {
 	.irq_set_vcpu_affinity	= its_irq_set_vcpu_affinity,
 };
 
+
 /*
  * How we allocate LPIs:
  *
- * The GIC has id_bits bits for interrupt identifiers. From there, we
- * must subtract 8192 which are reserved for SGIs/PPIs/SPIs. Then, as
- * we allocate LPIs by chunks of 32, we can shift the whole thing by 5
- * bits to the right.
+ * lpi_range_list contains ranges of LPIs that are to available to
+ * allocate from. To allocate LPIs, just pick the first range that
+ * fits the required allocation, and reduce it by the required
+ * amount. Once empty, remove the range from the list.
+ *
+ * To free a range of LPIs, add a free range to the list, sort it and
+ * merge the result if the new range happens to be adjacent to an
+ * already free block.
  *
- * This gives us (((1UL << id_bits) - 8192) >> 5) possible allocations.
+ * The consequence of the above is that allocation is cost is low, but
+ * freeing is expensive. We assumes that freeing rarely occurs.
  */
-#define IRQS_PER_CHUNK_SHIFT	5
-#define IRQS_PER_CHUNK		(1UL << IRQS_PER_CHUNK_SHIFT)
-#define ITS_MAX_LPI_NRBITS	16 /* 64K LPIs */
 
-static unsigned long *lpi_bitmap;
-static u32 lpi_chunks;
-static DEFINE_SPINLOCK(lpi_lock);
+static DEFINE_MUTEX(lpi_range_lock);
+static LIST_HEAD(lpi_range_list);
+
+struct lpi_range {
+	struct list_head	entry;
+	u32			base_id;
+	u32			span;
+};
 
-static int its_lpi_to_chunk(int lpi)
+static struct lpi_range *mk_lpi_range(u32 base, u32 span)
 {
-	return (lpi - 8192) >> IRQS_PER_CHUNK_SHIFT;
+	struct lpi_range *range;
+
+	range = kzalloc(sizeof(*range), GFP_KERNEL);
+	if (range) {
+		INIT_LIST_HEAD(&range->entry);
+		range->base_id = base;
+		range->span = span;
+	}
+
+	return range;
 }
 
-static int its_chunk_to_lpi(int chunk)
+static int lpi_range_cmp(void *priv, struct list_head *a, struct list_head *b)
 {
-	return (chunk << IRQS_PER_CHUNK_SHIFT) + 8192;
+	struct lpi_range *ra, *rb;
+
+	ra = container_of(a, struct lpi_range, entry);
+	rb = container_of(b, struct lpi_range, entry);
+
+	return rb->base_id - ra->base_id;
 }
 
-static int __init its_lpi_init(u32 id_bits)
+static void merge_lpi_ranges(void)
 {
-	lpi_chunks = its_lpi_to_chunk(1UL << id_bits);
+	struct lpi_range *range, *tmp;
 
-	lpi_bitmap = kcalloc(BITS_TO_LONGS(lpi_chunks), sizeof(long),
-			     GFP_KERNEL);
-	if (!lpi_bitmap) {
-		lpi_chunks = 0;
-		return -ENOMEM;
+	list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+		if (!list_is_last(&range->entry, &lpi_range_list) &&
+		    (tmp->base_id == (range->base_id + range->span))) {
+			tmp->base_id = range->base_id;
+			tmp->span += range->span;
+			list_del(&range->entry);
+			kfree(range);
+		}
 	}
+}
 
-	pr_info("ITS: Allocated %d chunks for LPIs\n", (int)lpi_chunks);
-	return 0;
+static int alloc_lpi_range(u32 nr_lpis, u32 *base)
+{
+	struct lpi_range *range, *tmp;
+	int err = -ENOSPC;
+
+	mutex_lock(&lpi_range_lock);
+
+	list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+		if (range->span >= nr_lpis) {
+			*base = range->base_id;
+			range->base_id += nr_lpis;
+			range->span -= nr_lpis;
+
+			if (range->span == 0) {
+				list_del(&range->entry);
+				kfree(range);
+			}
+
+			err = 0;
+			break;
+		}
+	}
+
+	mutex_unlock(&lpi_range_lock);
+
+	pr_debug("ITS: alloc %u:%u\n", *base, nr_lpis);
+	return err;
 }
 
-static unsigned long *its_lpi_alloc_chunks(int nr_irqs, int *base, int *nr_ids)
+static int free_lpi_range(u32 base, u32 nr_lpis)
 {
-	unsigned long *bitmap = NULL;
-	int chunk_id;
-	int nr_chunks;
-	int i;
+	struct lpi_range *new;
+	int err = 0;
+
+	mutex_lock(&lpi_range_lock);
+
+	new = mk_lpi_range(base, nr_lpis);
+	if (!new) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	list_add(&new->entry, &lpi_range_list);
+	list_sort(NULL, &lpi_range_list, lpi_range_cmp);
+	merge_lpi_ranges();
+out:
+	mutex_unlock(&lpi_range_lock);
+	return err;
+}
+
+static int __init its_lpi_init(u32 id_bits)
+{
+	u32 lpis = (1UL << id_bits) - 8192;
+	u32 numlpis;
+	int err;
+
+	numlpis = 1UL << GICD_TYPER_NUM_LPIS(gic_rdists->gicd_typer);
+
+	if (numlpis > 2 && !WARN_ON(numlpis > lpis)) {
+		lpis = numlpis;
+		pr_info("ITS: Using hypervisor restricted LPI range [%u]\n",
+			lpis);
+	}
 
-	nr_chunks = DIV_ROUND_UP(nr_irqs, IRQS_PER_CHUNK);
+	/*
+	 * Initializing the allocator is just the same as freeing the
+	 * full range of LPIs.
+	 */
+	err = free_lpi_range(8192, lpis);
+	pr_debug("ITS: Allocator initialized for %u LPIs\n", lpis);
+	return err;
+}
 
-	spin_lock(&lpi_lock);
+static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids)
+{
+	unsigned long *bitmap = NULL;
+	int err = 0;
 
 	do {
-		chunk_id = bitmap_find_next_zero_area(lpi_bitmap, lpi_chunks,
-						      0, nr_chunks, 0);
-		if (chunk_id < lpi_chunks)
+		err = alloc_lpi_range(nr_irqs, base);
+		if (!err)
 			break;
 
-		nr_chunks--;
-	} while (nr_chunks > 0);
+		nr_irqs /= 2;
+	} while (nr_irqs > 0);
 
-	if (!nr_chunks)
+	if (err)
 		goto out;
 
-	bitmap = kcalloc(BITS_TO_LONGS(nr_chunks * IRQS_PER_CHUNK),
-			 sizeof(long),
-			 GFP_ATOMIC);
+	bitmap = kcalloc(BITS_TO_LONGS(nr_irqs), sizeof (long), GFP_ATOMIC);
 	if (!bitmap)
 		goto out;
 
-	for (i = 0; i < nr_chunks; i++)
-		set_bit(chunk_id + i, lpi_bitmap);
-
-	*base = its_chunk_to_lpi(chunk_id);
-	*nr_ids = nr_chunks * IRQS_PER_CHUNK;
+	*nr_ids = nr_irqs;
 
 out:
-	spin_unlock(&lpi_lock);
-
 	if (!bitmap)
 		*base = *nr_ids = 0;
 
 	return bitmap;
 }
 
-static void its_lpi_free_chunks(unsigned long *bitmap, int base, int nr_ids)
+static void its_lpi_free(unsigned long *bitmap, u32 base, u32 nr_ids)
 {
-	int lpi;
-
-	spin_lock(&lpi_lock);
-
-	for (lpi = base; lpi < (base + nr_ids); lpi += IRQS_PER_CHUNK) {
-		int chunk = its_lpi_to_chunk(lpi);
-
-		BUG_ON(chunk > lpi_chunks);
-		if (test_bit(chunk, lpi_bitmap)) {
-			clear_bit(chunk, lpi_bitmap);
-		} else {
-			pr_err("Bad LPI chunk %d\n", chunk);
-		}
-	}
-
-	spin_unlock(&lpi_lock);
-
+	WARN_ON(free_lpi_range(base, nr_ids));
 	kfree(bitmap);
 }
 
@@ -1559,7 +1625,7 @@ static int __init its_alloc_lpi_tables(void)
 {
 	phys_addr_t paddr;
 
-	lpi_id_bits = min_t(u32, gic_rdists->id_bits, ITS_MAX_LPI_NRBITS);
+	lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer);
 	gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT);
 	if (!gic_rdists->prop_page) {
 		pr_err("Failed to allocate PROPBASE\n");
@@ -1997,12 +2063,12 @@ static void its_cpu_init_collections(void)
 {
 	struct its_node *its;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 
 	list_for_each_entry(its, &its_nodes, entry)
 		its_cpu_init_collection(its);
 
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 }
 
 static struct its_device *its_find_device(struct its_node *its, u32 dev_id)
@@ -2134,17 +2200,20 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	if (!its_alloc_device_table(its, dev_id))
 		return NULL;
 
+	if (WARN_ON(!is_power_of_2(nvecs)))
+		nvecs = roundup_pow_of_two(nvecs);
+
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	/*
-	 * We allocate at least one chunk worth of LPIs bet device,
-	 * and thus that many ITEs. The device may require less though.
+	 * Even if the device wants a single LPI, the ITT must be
+	 * sized as a power of two (and you need at least one bit...).
 	 */
-	nr_ites = max(IRQS_PER_CHUNK, roundup_pow_of_two(nvecs));
+	nr_ites = max(2, nvecs);
 	sz = nr_ites * its->ite_size;
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
 	itt = kzalloc(sz, GFP_KERNEL);
 	if (alloc_lpis) {
-		lpi_map = its_lpi_alloc_chunks(nvecs, &lpi_base, &nr_lpis);
+		lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
 		if (lpi_map)
 			col_map = kcalloc(nr_lpis, sizeof(*col_map),
 					  GFP_KERNEL);
@@ -2379,9 +2448,9 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 	/* If all interrupts have been freed, start mopping the floor */
 	if (bitmap_empty(its_dev->event_map.lpi_map,
 			 its_dev->event_map.nr_lpis)) {
-		its_lpi_free_chunks(its_dev->event_map.lpi_map,
-				    its_dev->event_map.lpi_base,
-				    its_dev->event_map.nr_lpis);
+		its_lpi_free(its_dev->event_map.lpi_map,
+			     its_dev->event_map.lpi_base,
+			     its_dev->event_map.nr_lpis);
 		kfree(its_dev->event_map.col_map);
 
 		/* Unmap device/itt */
@@ -2780,7 +2849,7 @@ static void its_vpe_irq_domain_free(struct irq_domain *domain,
 	}
 
 	if (bitmap_empty(vm->db_bitmap, vm->nr_db_lpis)) {
-		its_lpi_free_chunks(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
+		its_lpi_free(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
 		its_free_prop_table(vm->vprop_page);
 	}
 }
@@ -2795,18 +2864,18 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 
 	BUG_ON(!vm);
 
-	bitmap = its_lpi_alloc_chunks(nr_irqs, &base, &nr_ids);
+	bitmap = its_lpi_alloc(roundup_pow_of_two(nr_irqs), &base, &nr_ids);
 	if (!bitmap)
 		return -ENOMEM;
 
 	if (nr_ids < nr_irqs) {
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		return -ENOMEM;
 	}
 
 	vprop_page = its_allocate_prop_table(GFP_KERNEL);
 	if (!vprop_page) {
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		return -ENOMEM;
 	}
 
@@ -2833,7 +2902,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 		if (i > 0)
 			its_vpe_irq_domain_free(domain, virq, i - 1);
 
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		its_free_prop_table(vprop_page);
 	}
 
@@ -3070,7 +3139,7 @@ static int its_save_disable(void)
 	struct its_node *its;
 	int err = 0;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_for_each_entry(its, &its_nodes, entry) {
 		void __iomem *base;
 
@@ -3102,7 +3171,7 @@ static int its_save_disable(void)
 			writel_relaxed(its->ctlr_save, base + GITS_CTLR);
 		}
 	}
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 
 	return err;
 }
@@ -3112,7 +3181,7 @@ static void its_restore_enable(void)
 	struct its_node *its;
 	int ret;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_for_each_entry(its, &its_nodes, entry) {
 		void __iomem *base;
 		int i;
@@ -3164,7 +3233,7 @@ static void its_restore_enable(void)
 		    GITS_TYPER_HCC(gic_read_typer(base + GITS_TYPER)))
 			its_cpu_init_collection(its);
 	}
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 }
 
 static struct syscore_ops its_syscore_ops = {
@@ -3398,9 +3467,9 @@ static int __init its_probe_one(struct resource *res,
 	if (err)
 		goto out_free_tables;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_add(&its->entry, &its_nodes);
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 
 	return 0;
 

drivers/irqchip/irq-gic-v3.c

@@ -877,7 +877,7 @@ static struct irq_chip gic_eoimode1_chip = {
 	.flags			= IRQCHIP_SET_TYPE_MASKED,
 };
 
-#define GIC_ID_NR		(1U << gic_data.rdists.id_bits)
+#define GIC_ID_NR	(1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer))
 
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 			      irq_hw_number_t hw)
@@ -1091,7 +1091,7 @@ static int __init gic_init_bases(void __iomem *dist_base,
 	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
 	 */
 	typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);
-	gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer);
+	gic_data.rdists.gicd_typer = typer;
 	gic_irqs = GICD_TYPER_IRQS(typer);
 	if (gic_irqs > 1020)
 		gic_irqs = 1020;

drivers/irqchip/irq-ingenic.c

@@ -165,6 +165,7 @@ static int __init intc_1chip_of_init(struct device_node *node,
 	return ingenic_intc_of_init(node, 1);
 }
 IRQCHIP_DECLARE(jz4740_intc, "ingenic,jz4740-intc", intc_1chip_of_init);
+IRQCHIP_DECLARE(jz4725b_intc, "ingenic,jz4725b-intc", intc_1chip_of_init);
 
 static int __init intc_2chip_of_init(struct device_node *node,
 	struct device_node *parent)

drivers/irqchip/irq-stm32-exti.c

@@ -159,6 +159,7 @@ static const struct stm32_exti_bank *stm32mp1_exti_banks[] = {
 };
 
 static const struct stm32_desc_irq stm32mp1_desc_irq[] = {
+	{ .exti = 0, .irq_parent = 6 },
 	{ .exti = 1, .irq_parent = 7 },
 	{ .exti = 2, .irq_parent = 8 },
 	{ .exti = 3, .irq_parent = 9 },

include/linux/irqchip/arm-gic-v3.h

@@ -73,6 +73,7 @@
 #define GICD_TYPER_MBIS			(1U << 16)
 
 #define GICD_TYPER_ID_BITS(typer)	((((typer) >> 19) & 0x1f) + 1)
+#define GICD_TYPER_NUM_LPIS(typer)	((((typer) >> 11) & 0x1f) + 1)
 #define GICD_TYPER_IRQS(typer)		((((typer) & 0x1f) + 1) * 32)
 
 #define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
@@ -576,8 +577,8 @@ struct rdists {
 		phys_addr_t	phys_base;
 	} __percpu		*rdist;
 	struct page		*prop_page;
-	int			id_bits;
 	u64			flags;
+	u32			gicd_typer;
 	bool			has_vlpis;
 	bool			has_direct_lpi;
 };

kernel/irq/Kconfig

@@ -134,7 +134,6 @@ config GENERIC_IRQ_DEBUGFS
 endmenu
 
 config GENERIC_IRQ_MULTI_HANDLER
-	depends on !MULTI_IRQ_HANDLER
 	bool
 	help
 	  Allow to specify the low level IRQ handler at run time.

kernel/irq/irqdesc.c

@@ -443,6 +443,7 @@ static void free_desc(unsigned int irq)
 	 * We free the descriptor, masks and stat fields via RCU. That
 	 * allows demultiplex interrupts to do rcu based management of
 	 * the child interrupts.
+	 * This also allows us to use rcu in kstat_irqs_usr().
 	 */
 	call_rcu(&desc->rcu, delayed_free_desc);
 }
@@ -928,17 +929,17 @@ unsigned int kstat_irqs(unsigned int irq)
  * kstat_irqs_usr - Get the statistics for an interrupt
  * @irq:	The interrupt number
  *
- * Returns the sum of interrupt counts on all cpus since boot for
- * @irq. Contrary to kstat_irqs() this can be called from any
- * preemptible context. It's protected against concurrent removal of
- * an interrupt descriptor when sparse irqs are enabled.
+ * Returns the sum of interrupt counts on all cpus since boot for @irq.
+ * Contrary to kstat_irqs() this can be called from any context.
+ * It uses rcu since a concurrent removal of an interrupt descriptor is
+ * observing an rcu grace period before delayed_free_desc()/irq_kobj_release().
  */
 unsigned int kstat_irqs_usr(unsigned int irq)
 {
 	unsigned int sum;
 
-	irq_lock_sparse();
+	rcu_read_lock();
 	sum = kstat_irqs(irq);
-	irq_unlock_sparse();
+	rcu_read_unlock();
 	return sum;
 }

kernel/irq/manage.c

@@ -790,9 +790,19 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
 
 static int irq_wait_for_interrupt(struct irqaction *action)
 {
-	set_current_state(TASK_INTERRUPTIBLE);
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
 
-	while (!kthread_should_stop()) {
+		if (kthread_should_stop()) {
+			/* may need to run one last time */
+			if (test_and_clear_bit(IRQTF_RUNTHREAD,
+					       &action->thread_flags)) {
+				__set_current_state(TASK_RUNNING);
+				return 0;
+			}
+			__set_current_state(TASK_RUNNING);
+			return -1;
+		}
 
 		if (test_and_clear_bit(IRQTF_RUNTHREAD,
 				       &action->thread_flags)) {
@@ -800,10 +810,7 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 			return 0;
 		}
 		schedule();
-		set_current_state(TASK_INTERRUPTIBLE);
 	}
-	__set_current_state(TASK_RUNNING);
-	return -1;
 }
 
 /*
@@ -1024,11 +1031,8 @@ static int irq_thread(void *data)
 	/*
 	 * This is the regular exit path. __free_irq() is stopping the
 	 * thread via kthread_stop() after calling
-	 * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
-	 * oneshot mask bit can be set. We cannot verify that as we
-	 * cannot touch the oneshot mask at this point anymore as
-	 * __setup_irq() might have given out currents thread_mask
-	 * again.
+	 * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the
+	 * oneshot mask bit can be set.
 	 */
 	task_work_cancel(current, irq_thread_dtor);
 	return 0;
@@ -1251,8 +1255,10 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	/*
 	 * Protects against a concurrent __free_irq() call which might wait
-	 * for synchronize_irq() to complete without holding the optional
-	 * chip bus lock and desc->lock.
+	 * for synchronize_hardirq() to complete without holding the optional
+	 * chip bus lock and desc->lock. Also protects against handing out
+	 * a recycled oneshot thread_mask bit while it's still in use by
+	 * its previous owner.
 	 */
 	mutex_lock(&desc->request_mutex);
 
@@ -1571,9 +1577,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 
 	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
 
-	if (!desc)
-		return NULL;
-
 	mutex_lock(&desc->request_mutex);
 	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
@@ -1620,11 +1623,11 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	/*
 	 * Drop bus_lock here so the changes which were done in the chip
 	 * callbacks above are synced out to the irq chips which hang
-	 * behind a slow bus (I2C, SPI) before calling synchronize_irq().
+	 * behind a slow bus (I2C, SPI) before calling synchronize_hardirq().
 	 *
 	 * Aside of that the bus_lock can also be taken from the threaded
 	 * handler in irq_finalize_oneshot() which results in a deadlock
-	 * because synchronize_irq() would wait forever for the thread to
+	 * because kthread_stop() would wait forever for the thread to
 	 * complete, which is blocked on the bus lock.
 	 *
 	 * The still held desc->request_mutex() protects against a
@@ -1636,7 +1639,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	unregister_handler_proc(irq, action);
 
 	/* Make sure it's not being used on another CPU: */
-	synchronize_irq(irq);
+	synchronize_hardirq(irq);
 
 #ifdef CONFIG_DEBUG_SHIRQ
 	/*
@@ -1645,7 +1648,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	 * is so by doing an extra call to the handler ....
 	 *
 	 * ( We do this after actually deregistering it, to make sure that a
-	 *   'real' IRQ doesn't run in * parallel with our fake. )
+	 *   'real' IRQ doesn't run in parallel with our fake. )
 	 */
 	if (action->flags & IRQF_SHARED) {
 		local_irq_save(flags);
@@ -1654,6 +1657,12 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	}
 #endif
 
+	/*
+	 * The action has already been removed above, but the thread writes
+	 * its oneshot mask bit when it completes. Though request_mutex is
+	 * held across this which prevents __setup_irq() from handing out
+	 * the same bit to a newly requested action.
+	 */
 	if (action->thread) {
 		kthread_stop(action->thread);
 		put_task_struct(action->thread);

kernel/irq/proc.c

@@ -475,22 +475,24 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
-	irq_lock_sparse();
+	rcu_read_lock();
 	desc = irq_to_desc(i);
 	if (!desc)
 		goto outsparse;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	for_each_online_cpu(j)
-		any_count |= kstat_irqs_cpu(i, j);
-	action = desc->action;
-	if ((!action || irq_desc_is_chained(desc)) && !any_count)
-		goto out;
+	if (desc->kstat_irqs)
+		for_each_online_cpu(j)
+			any_count |= *per_cpu_ptr(desc->kstat_irqs, j);
+
+	if ((!desc->action || irq_desc_is_chained(desc)) && !any_count)
+		goto outsparse;
 
 	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+		seq_printf(p, "%10u ", desc->kstat_irqs ?
+					*per_cpu_ptr(desc->kstat_irqs, j) : 0);
 
+	raw_spin_lock_irqsave(&desc->lock, flags);
 	if (desc->irq_data.chip) {
 		if (desc->irq_data.chip->irq_print_chip)
 			desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
@@ -511,6 +513,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (desc->name)
 		seq_printf(p, "-%-8s", desc->name);
 
+	action = desc->action;
 	if (action) {
 		seq_printf(p, "  %s", action->name);
 		while ((action = action->next) != NULL)
@@ -518,10 +521,9 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	seq_putc(p, '\n');
-out:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 outsparse:
-	irq_unlock_sparse();
+	rcu_read_unlock();
 	return 0;
 }
 #endif