Loongarch: Support loongarch avec

Introduce the advanced extended interrupt controllers. This feature will
allow each core to have 256 independent interrupt vectors and MSI
interrupts can be independently routed to any vector on any CPU.

[ tglx: Fixed up coding style. Made on/offline functions void ]
Co-developed-by: Jianmin Lv <lvjianmin@loongson.cn>
Signed-off-by: Jianmin Lv <lvjianmin@loongson.cn>
Co-developed-by: Liupu Wang <wangliupu@loongson.cn>
Signed-off-by: Liupu Wang <wangliupu@loongson.cn>
Signed-off-by: Tianyang Zhang <zhangtianyang@loongson.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20240604125026.18745-1-zhangtianyang@loongson.cn

arch/loongarch/Kconfig

@@ -83,6 +83,7 @@ config LOONGARCH
 	select GENERIC_ENTRY
 	select GENERIC_GETTIMEOFDAY
 	select GENERIC_IOREMAP if !ARCH_IOREMAP
+	select GENERIC_IRQ_MATRIX_ALLOCATOR
 	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW

arch/loongarch/include/asm/cpu-features.h

@@ -65,5 +65,6 @@
 #define cpu_has_guestid		cpu_opt(LOONGARCH_CPU_GUESTID)
 #define cpu_has_hypervisor	cpu_opt(LOONGARCH_CPU_HYPERVISOR)
 #define cpu_has_ptw		cpu_opt(LOONGARCH_CPU_PTW)
+#define cpu_has_avecint		cpu_opt(LOONGARCH_CPU_AVECINT)
 
 #endif /* __ASM_CPU_FEATURES_H */

arch/loongarch/include/asm/cpu.h

@@ -99,6 +99,7 @@ enum cpu_type_enum {
 #define CPU_FEATURE_GUESTID		24	/* CPU has GuestID feature */
 #define CPU_FEATURE_HYPERVISOR		25	/* CPU has hypervisor (running in VM) */
 #define CPU_FEATURE_PTW			26	/* CPU has hardware page table walker */
+#define CPU_FEATURE_AVECINT		27	/* CPU has avec interrupt */
 
 #define LOONGARCH_CPU_CPUCFG		BIT_ULL(CPU_FEATURE_CPUCFG)
 #define LOONGARCH_CPU_LAM		BIT_ULL(CPU_FEATURE_LAM)
@@ -127,5 +128,6 @@ enum cpu_type_enum {
 #define LOONGARCH_CPU_GUESTID		BIT_ULL(CPU_FEATURE_GUESTID)
 #define LOONGARCH_CPU_HYPERVISOR	BIT_ULL(CPU_FEATURE_HYPERVISOR)
 #define LOONGARCH_CPU_PTW		BIT_ULL(CPU_FEATURE_PTW)
+#define LOONGARCH_CPU_AVECINT		BIT_ULL(CPU_FEATURE_AVECINT)
 
 #endif /* _ASM_CPU_H */

arch/loongarch/include/asm/hw_irq.h

@@ -9,6 +9,16 @@
 
 extern atomic_t irq_err_count;
 
+/*
+ * 256 vectors Map:
+ *
+ * 0 - 15: mapping legacy IPs, e.g. IP0-12.
+ * 16 - 255: mapping a vector for external IRQ.
+ *
+ */
+#define NR_VECTORS		256
+#define IRQ_MATRIX_BITS		NR_VECTORS
+#define NR_LEGACY_VECTORS	16
 /*
  * interrupt-retrigger: NOP for now. This may not be appropriate for all
  * machines, we'll see ...

arch/loongarch/include/asm/irq.h

@@ -65,7 +65,7 @@ extern struct acpi_vector_group msi_group[MAX_IO_PICS];
 #define LOONGSON_LPC_LAST_IRQ		(LOONGSON_LPC_IRQ_BASE + 15)
 
 #define LOONGSON_CPU_IRQ_BASE		16
-#define LOONGSON_CPU_LAST_IRQ		(LOONGSON_CPU_IRQ_BASE + 14)
+#define LOONGSON_CPU_LAST_IRQ		(LOONGSON_CPU_IRQ_BASE + 15)
 
 #define LOONGSON_PCH_IRQ_BASE		64
 #define LOONGSON_PCH_ACPI_IRQ		(LOONGSON_PCH_IRQ_BASE + 47)
@@ -101,6 +101,16 @@ int pch_msi_acpi_init(struct irq_domain *parent,
 					struct acpi_madt_msi_pic *acpi_pchmsi);
 int pch_pic_acpi_init(struct irq_domain *parent,
 					struct acpi_madt_bio_pic *acpi_pchpic);
+
+#ifdef CONFIG_ACPI
+int __init pch_msi_acpi_init_v2(struct irq_domain *parent,
+		struct acpi_madt_msi_pic *pch_msi_entry);
+int __init loongarch_avec_acpi_init(struct irq_domain *parent);
+void complete_irq_moving(void);
+void loongarch_avec_offline_cpu(unsigned int cpu);
+void loongarch_avec_online_cpu(unsigned int cpu);
+#endif
+
 int find_pch_pic(u32 gsi);
 struct fwnode_handle *get_pch_msi_handle(int pci_segment);
 

arch/loongarch/include/asm/loongarch.h

@@ -72,7 +72,6 @@
 #define  CPUCFG1_RPLV			BIT(23)
 #define  CPUCFG1_HUGEPG			BIT(24)
 #define  CPUCFG1_CRC32			BIT(25)
-#define  CPUCFG1_MSGINT			BIT(26)
 
 #define LOONGARCH_CPUCFG2		0x2
 #define  CPUCFG2_FP			BIT(0)
@@ -252,8 +251,8 @@
 #define  CSR_ESTAT_EXC_WIDTH		6
 #define  CSR_ESTAT_EXC			(_ULCAST_(0x3f) << CSR_ESTAT_EXC_SHIFT)
 #define  CSR_ESTAT_IS_SHIFT		0
-#define  CSR_ESTAT_IS_WIDTH		14
-#define  CSR_ESTAT_IS			(_ULCAST_(0x3fff) << CSR_ESTAT_IS_SHIFT)
+#define  CSR_ESTAT_IS_WIDTH		15
+#define  CSR_ESTAT_IS			(_ULCAST_(0x7fff) << CSR_ESTAT_IS_SHIFT)
 
 #define LOONGARCH_CSR_ERA		0x6	/* ERA */
 
@@ -999,10 +998,18 @@
 #define CSR_FWPC_SKIP_SHIFT		16
 #define CSR_FWPC_SKIP			(_ULCAST_(1) << CSR_FWPC_SKIP_SHIFT)
 
+#define LOONGARCH_CSR_IRR0		0xa0
+#define LOONGARCH_CSR_IRR1		0xa1
+#define LOONGARCH_CSR_IRR2		0xa2
+#define LOONGARCH_CSR_IRR3		0xa3
+#define LOONGARCH_CSR_IRR_BASE		LOONGARCH_CSR_IRR0
+
+#define	LOONGARCH_CSR_ILR		0xa4
+
 /*
  * CSR_ECFG IM
  */
-#define ECFG0_IM		0x00001fff
+#define ECFG0_IM		0x00005fff
 #define ECFGB_SIP0		0
 #define ECFGF_SIP0		(_ULCAST_(1) << ECFGB_SIP0)
 #define ECFGB_SIP1		1
@@ -1045,6 +1052,7 @@
 #define  IOCSRF_EIODECODE		BIT_ULL(9)
 #define  IOCSRF_FLATMODE		BIT_ULL(10)
 #define  IOCSRF_VM			BIT_ULL(11)
+#define  IOCSRF_AVEC			BIT_ULL(15)
 
 #define LOONGARCH_IOCSR_VENDOR		0x10
 
@@ -1055,6 +1063,7 @@
 #define LOONGARCH_IOCSR_MISC_FUNC	0x420
 #define  IOCSR_MISC_FUNC_TIMER_RESET	BIT_ULL(21)
 #define  IOCSR_MISC_FUNC_EXT_IOI_EN	BIT_ULL(48)
+#define  IOCSR_MISC_FUNC_AVEC_EN	BIT_ULL(51)
 
 #define LOONGARCH_IOCSR_CPUTEMP		0x428
 
@@ -1375,9 +1384,10 @@ __BUILD_CSR_OP(tlbidx)
 #define INT_TI		11	/* Timer */
 #define INT_IPI		12
 #define INT_NMI		13
+#define INT_AVEC	14
 
 /* ExcCodes corresponding to interrupts */
-#define EXCCODE_INT_NUM		(INT_NMI + 1)
+#define EXCCODE_INT_NUM		(INT_AVEC + 1)
 #define EXCCODE_INT_START	64
 #define EXCCODE_INT_END		(EXCCODE_INT_START + EXCCODE_INT_NUM - 1)
 

arch/loongarch/include/asm/smp.h

@@ -69,9 +69,11 @@ extern int __cpu_logical_map[NR_CPUS];
 #define ACTION_BOOT_CPU	0
 #define ACTION_RESCHEDULE	1
 #define ACTION_CALL_FUNCTION	2
+#define ACTION_CLEAR_VECT	3
 #define SMP_BOOT_CPU		BIT(ACTION_BOOT_CPU)
 #define SMP_RESCHEDULE		BIT(ACTION_RESCHEDULE)
 #define SMP_CALL_FUNCTION	BIT(ACTION_CALL_FUNCTION)
+#define SMP_CLEAR_VECT		BIT(ACTION_CLEAR_VECT)
 
 struct secondary_data {
 	unsigned long stack;

arch/loongarch/kernel/cpu-probe.c

@@ -106,7 +106,6 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c)
 		elf_hwcap |= HWCAP_LOONGARCH_CRC32;
 	}
 
-
 	config = read_cpucfg(LOONGARCH_CPUCFG2);
 	if (config & CPUCFG2_LAM) {
 		c->options |= LOONGARCH_CPU_LAM;
@@ -176,6 +175,8 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c)
 		c->options |= LOONGARCH_CPU_EIODECODE;
 	if (config & IOCSRF_VM)
 		c->options |= LOONGARCH_CPU_HYPERVISOR;
+	if (config & IOCSRF_AVEC)
+		c->options |= LOONGARCH_CPU_AVECINT;
 
 	config = csr_read32(LOONGARCH_CSR_ASID);
 	config = (config & CSR_ASID_BIT) >> CSR_ASID_BIT_SHIFT;

arch/loongarch/kernel/smp.c

@@ -234,6 +234,9 @@ static irqreturn_t loongson_ipi_interrupt(int irq, void *dev)
 		per_cpu(irq_stat, cpu).ipi_irqs[IPI_CALL_FUNCTION]++;
 	}
 
+	if (action & SMP_CLEAR_VECT)
+		complete_irq_moving();
+
 	return IRQ_HANDLED;
 }
 
@@ -388,6 +391,7 @@ int loongson_cpu_disable(void)
 	irq_migrate_all_off_this_cpu();
 	clear_csr_ecfg(ECFG0_IM);
 	local_irq_restore(flags);
+	loongarch_avec_offline_cpu(cpu);
 	local_flush_tlb_all();
 
 	return 0;
@@ -566,6 +570,7 @@ asmlinkage void start_secondary(void)
 	 * early is dangerous.
 	 */
 	WARN_ON_ONCE(!irqs_disabled());
+	loongarch_avec_online_cpu(cpu);
 	loongson_smp_finish();
 
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);

drivers/irqchip/Makefile

@@ -109,7 +109,7 @@ obj-$(CONFIG_LS1X_IRQ)			+= irq-ls1x.o
 obj-$(CONFIG_TI_SCI_INTR_IRQCHIP)	+= irq-ti-sci-intr.o
 obj-$(CONFIG_TI_SCI_INTA_IRQCHIP)	+= irq-ti-sci-inta.o
 obj-$(CONFIG_TI_PRUSS_INTC)		+= irq-pruss-intc.o
-obj-$(CONFIG_IRQ_LOONGARCH_CPU)		+= irq-loongarch-cpu.o
+obj-$(CONFIG_IRQ_LOONGARCH_CPU)		+= irq-loongarch-cpu.o irq-loongarch-avec.o
 obj-$(CONFIG_LOONGSON_LIOINTC)		+= irq-loongson-liointc.o
 obj-$(CONFIG_LOONGSON_EIOINTC)		+= irq-loongson-eiointc.o
 obj-$(CONFIG_LOONGSON_HTPIC)		+= irq-loongson-htpic.o

drivers/irqchip/irq-loongarch-cpu.c

@@ -138,7 +138,9 @@ static int __init acpi_cascade_irqdomain_init(void)
 	if (r < 0)
 		return r;
 
-	return 0;
+	if (cpu_has_avecint)
+		r = loongarch_avec_acpi_init(irq_domain);
+	return r;
 }
 
 static int __init cpuintc_acpi_init(union acpi_subtable_headers *header,

drivers/irqchip/irq-loongson-eiointc.c

@@ -359,6 +359,9 @@ static int __init acpi_cascade_irqdomain_init(void)
 	if (r < 0)
 		return r;
 
+	if (cpu_has_avecint)
+		return 0;
+
 	r = acpi_table_parse_madt(ACPI_MADT_TYPE_MSI_PIC, pch_msi_parse_madt, 1);
 	if (r < 0)
 		return r;

drivers/irqchip/irq-loongson-pch-msi.c

@@ -16,7 +16,6 @@
 #include <linux/slab.h>
 
 static int nr_pics;
-
 struct pch_msi_data {
 	struct mutex	msi_map_lock;
 	phys_addr_t	doorbell;
@@ -100,6 +99,17 @@ static struct irq_chip middle_irq_chip = {
 	.irq_compose_msi_msg	= pch_msi_compose_msi_msg,
 };
 
+static struct irq_chip pch_msi_irq_chip_v2 = {
+	.name			= "MSI",
+	.irq_ack		= irq_chip_ack_parent,
+};
+
+static struct msi_domain_info pch_msi_domain_info_v2 = {
+	.flags		= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+			MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX,
+	.chip	= &pch_msi_irq_chip_v2,
+};
+
 static int pch_msi_parent_domain_alloc(struct irq_domain *domain,
 					unsigned int virq, int hwirq)
 {
@@ -268,6 +278,9 @@ struct fwnode_handle *get_pch_msi_handle(int pci_segment)
 {
 	int i;
 
+	if (cpu_has_avecint)
+		return pch_msi_handle[0];
+
 	for (i = 0; i < MAX_IO_PICS; i++) {
 		if (msi_group[i].pci_segment == pci_segment)
 			return pch_msi_handle[i];
@@ -289,4 +302,32 @@ int __init pch_msi_acpi_init(struct irq_domain *parent,
 
 	return ret;
 }
+
+int __init pch_msi_acpi_init_v2(struct irq_domain *parent,
+		struct acpi_madt_msi_pic *msi_entry)
+{
+	struct irq_domain *msi_domain;
+
+	if (pch_msi_handle[0])
+		return 0;
+
+	pch_msi_handle[0] = irq_domain_alloc_named_fwnode("msipic-v2");
+	if (!pch_msi_handle[0]) {
+		pr_err("Unable to allocate domain handle\n");
+		kfree(pch_msi_handle[0]);
+		return -ENOMEM;
+	}
+
+	msi_domain = pci_msi_create_irq_domain(pch_msi_handle[0],
+			&pch_msi_domain_info_v2,
+			parent);
+	if (!msi_domain) {
+		pr_err("Failed to create PCI MSI domain\n");
+		kfree(pch_msi_handle[0]);
+		return -ENOMEM;
+	}
+
+	pr_info("IRQ domain MSIPIC-V2 init done.\n");
+	return 0;
+}
 #endif