[linux-6.6.y] LoongArch: Fix some issues and new feature support

Documentation/arch/loongarch/irq-chip-model.rst

@@ -85,6 +85,38 @@ to CPUINTC directly::
     | Devices |
     +---------+
 
+Advanced Extended IRQ model
+===========================
+
+In this model, IPI (Inter-Processor Interrupt) and CPU Local Timer interrupt go
+to CPUINTC directly, CPU UARTS interrupts go to LIOINTC, PCH-MSI interrupts go
+to AVECINTC, and then go to CPUINTC directly, while all other devices interrupts
+go to PCH-PIC/PCH-LPC and gathered by EIOINTC, and then go to CPUINTC directly::
+
+ +-----+     +-----------------------+     +-------+
+ | IPI | --> |        CPUINTC        | <-- | Timer |
+ +-----+     +-----------------------+     +-------+
+              ^          ^          ^
+              |          |          |
+       +---------+ +----------+ +---------+     +-------+
+       | EIOINTC | | AVECINTC | | LIOINTC | <-- | UARTs |
+       +---------+ +----------+ +---------+     +-------+
+            ^            ^
+            |            |
+       +---------+  +---------+
+       | PCH-PIC |  | PCH-MSI |
+       +---------+  +---------+
+         ^     ^           ^
+         |     |           |
+ +---------+ +---------+ +---------+
+ | Devices | | PCH-LPC | | Devices |
+ +---------+ +---------+ +---------+
+                  ^
+                  |
+             +---------+
+             | Devices |
+             +---------+
+
 ACPI-related definitions
 ========================
 

Documentation/translations/zh_CN/arch/loongarch/irq-chip-model.rst

@@ -87,6 +87,38 @@ PCH-LPC/PCH-MSI，然后被EIOINTC统一收集，再直接到达CPUINTC::
     | Devices |
     +---------+
 
+高级扩展IRQ模型
+===============
+
+在这种模型里面，IPI（Inter-Processor Interrupt）和CPU本地时钟中断直接发送到CPUINTC，
+CPU串口（UARTs）中断发送到LIOINTC，PCH-MSI中断发送到AVECINTC，而后通过AVECINTC直接
+送达CPUINTC，而其他所有设备的中断则分别发送到所连接的PCH-PIC/PCH-LPC，然后由EIOINTC
+统一收集，再直接到达CPUINTC::
+
+ +-----+     +-----------------------+     +-------+
+ | IPI | --> |        CPUINTC        | <-- | Timer |
+ +-----+     +-----------------------+     +-------+
+              ^          ^          ^
+              |          |          |
+       +---------+ +----------+ +---------+     +-------+
+       | EIOINTC | | AVECINTC | | LIOINTC | <-- | UARTs |
+       +---------+ +----------+ +---------+     +-------+
+            ^            ^
+            |            |
+       +---------+  +---------+
+       | PCH-PIC |  | PCH-MSI |
+       +---------+  +---------+
+         ^     ^           ^
+         |     |           |
+ +---------+ +---------+ +---------+
+ | Devices | | PCH-LPC | | Devices |
+ +---------+ +---------+ +---------+
+                  ^
+                  |
+             +---------+
+             | Devices |
+             +---------+
+
 ACPI相关的定义
 ==============
 

MAINTAINERS

@@ -12390,6 +12390,7 @@ F:	Documentation/arch/loongarch/
 F:	Documentation/translations/zh_CN/arch/loongarch/
 F:	arch/loongarch/
 F:	drivers/*/*loongarch*
+F:	drivers/*/*loongson*
 
 LOONGSON GPIO DRIVER
 M:	Yinbo Zhu <zhuyinbo@loongson.cn>

arch/loongarch/Kconfig

@@ -75,6 +75,7 @@ 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
@@ -147,6 +148,7 @@ config LOONGARCH
 	select HAVE_SETUP_PER_CPU_AREA if NUMA
 	select HAVE_STACK_VALIDATION if HAVE_OBJTOOL
 	select HAVE_STACKPROTECTOR
+	select ARCH_HAS_PHYS_TO_DMA
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_TIF_NOHZ
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN if !SMP

arch/loongarch/configs/loongson3_defconfig

@@ -1476,7 +1476,7 @@ CONFIG_DRM_AST=y
 CONFIG_DRM_MGAG200=m
 CONFIG_DRM_QXL=m
 CONFIG_DRM_VIRTIO_GPU=m
-CONFIG_DRM_LOONGSON=y
+CONFIG_DRM_LOONGSON=m
 CONFIG_DRM_BOCHS=m
 CONFIG_DRM_CIRRUS_QEMU=m
 CONFIG_FB=y
@@ -1674,6 +1674,8 @@ CONFIG_HID_ALPS=m
 CONFIG_HID_PID=y
 CONFIG_USB_HIDDEV=y
 CONFIG_I2C_HID=m
+CONFIG_I2C_HID_ACPI=m
+CONFIG_I2C_HID_OF=m
 CONFIG_USB_LED_TRIG=y
 CONFIG_USB=y
 CONFIG_USB_ANNOUNCE_NEW_DEVICES=y

arch/loongarch/include/asm/addrspace.h

@@ -36,6 +36,10 @@ extern unsigned long vm_map_base;
 #define UNCACHE_BASE		CSR_DMW0_BASE
 #endif
 
+#ifndef WRITECOMBINE_BASE
+#define WRITECOMBINE_BASE	CSR_DMW2_BASE
+#endif
+
 #define DMW_PABITS	48
 #define TO_PHYS_MASK	((1ULL << DMW_PABITS) - 1)
 

arch/loongarch/include/asm/atomic.h

@@ -15,13 +15,15 @@
 #define __LL		"ll.w	"
 #define __SC		"sc.w	"
 #define __AMADD		"amadd.w	"
+#define __AMOR		"amor.w		"
 #define __AMAND_DB	"amand_db.w	"
 #define __AMOR_DB	"amor_db.w	"
 #define __AMXOR_DB	"amxor_db.w	"
 #elif __SIZEOF_LONG__ == 8
 #define __LL		"ll.d	"
 #define __SC		"sc.d	"
 #define __AMADD		"amadd.d	"
+#define __AMOR		"amor.d		"
 #define __AMAND_DB	"amand_db.d	"
 #define __AMOR_DB	"amor_db.d	"
 #define __AMXOR_DB	"amxor_db.d	"

arch/loongarch/include/asm/cacheflush.h

@@ -37,8 +37,6 @@ void local_flush_icache_range(unsigned long start, unsigned long end);
 #define flush_icache_range	local_flush_icache_range
 #define flush_icache_user_range	local_flush_icache_range
 
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
-
 #define flush_cache_all()				do { } while (0)
 #define flush_cache_mm(mm)				do { } while (0)
 #define flush_cache_dup_mm(mm)				do { } while (0)
@@ -47,7 +45,6 @@ void local_flush_icache_range(unsigned long start, unsigned long end);
 #define flush_cache_vmap(start, end)			do { } while (0)
 #define flush_cache_vunmap(start, end)			do { } while (0)
 #define flush_icache_user_page(vma, page, addr, len)	do { } while (0)
-#define flush_dcache_page(page)				do { } while (0)
 #define flush_dcache_mmap_lock(mapping)			do { } while (0)
 #define flush_dcache_mmap_unlock(mapping)		do { } while (0)
 

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/dma-direct.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_LOONGARCH_DMA_DIRECT_H
+#define _ASM_LOONGARCH_DMA_DIRECT_H
+
+extern int node_id_offset;
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	long nid = (paddr >> 44) & 0xf;
+
+	return ((nid << 44) ^ paddr) | (nid << node_id_offset);
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+	long nid = (daddr >> node_id_offset) & 0xf;
+
+	return ((nid << node_id_offset) ^ daddr) | (nid << 44);
+}
+
+#endif /* _ASM_LOONGARCH_DMA_DIRECT_H */

arch/loongarch/include/asm/hardirq.h

@@ -15,8 +15,9 @@ extern void ack_bad_irq(unsigned int irq);
 enum ipi_msg_type {
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNCTION,
+	IPI_CLEAR_VECTOR,
 };
-#define NR_IPI	2
+#define NR_IPI	3
 
 typedef struct {
 	unsigned int ipi_irqs[NR_IPI];

arch/loongarch/include/asm/hugetlb.h

@@ -44,7 +44,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
 	pte_t clear;
-	pte_t pte = *ptep;
+	pte_t pte = ptep_get(ptep);
 
 	pte_val(clear) = (unsigned long)invalid_pte_table;
 	set_pte_at(mm, addr, ptep, clear);
@@ -75,7 +75,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     pte_t *ptep, pte_t pte,
 					     int dirty)
 {
-	int changed = !pte_same(*ptep, pte);
+	int changed = !pte_same(ptep_get(ptep), pte);
 
 	if (changed) {
 		set_pte_at(vma->vm_mm, addr, ptep, pte);

arch/loongarch/include/asm/io.h

@@ -30,10 +30,16 @@ extern void __init early_iounmap(void __iomem *addr, unsigned long size);
 static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
 					 unsigned long prot_val)
 {
-	if (prot_val & _CACHE_CC)
+	switch (prot_val & _CACHE_MASK) {
+	case _CACHE_CC:
 		return (void __iomem *)(unsigned long)(CACHE_BASE + offset);
-	else
+	case _CACHE_SUC:
 		return (void __iomem *)(unsigned long)(UNCACHE_BASE + offset);
+	case _CACHE_WUC:
+		return (void __iomem *)(unsigned long)(WRITECOMBINE_BASE + offset);
+	default:
+		return NULL;
+	}
 }
 
 #define ioremap(offset, size)		\

arch/loongarch/include/asm/irq.h

@@ -39,6 +39,17 @@ void spurious_interrupt(void);
 
 #define NR_IRQS_LEGACY 16
 
+/*
+ * 256 Vectors Mapping for AVECINTC:
+ *
+ * 0 - 15: Mapping classic IPs, e.g. IP0-12.
+ * 16 - 255: Mapping vectors for external IRQ.
+ *
+ */
+#define NR_VECTORS		256
+#define NR_LEGACY_VECTORS	16
+#define IRQ_MATRIX_BITS		NR_VECTORS
+
 #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
 void arch_trigger_cpumask_backtrace(const struct cpumask *mask, int exclude_cpu);
 
@@ -65,7 +76,7 @@ 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)
@@ -88,20 +99,8 @@ struct acpi_madt_bio_pic;
 struct acpi_madt_msi_pic;
 struct acpi_madt_lpc_pic;
 
-int liointc_acpi_init(struct irq_domain *parent,
-					struct acpi_madt_lio_pic *acpi_liointc);
-int eiointc_acpi_init(struct irq_domain *parent,
-					struct acpi_madt_eio_pic *acpi_eiointc);
-
-int htvec_acpi_init(struct irq_domain *parent,
-					struct acpi_madt_ht_pic *acpi_htvec);
-int pch_lpc_acpi_init(struct irq_domain *parent,
-					struct acpi_madt_lpc_pic *acpi_pchlpc);
-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);
-int find_pch_pic(u32 gsi);
+void complete_irq_moving(void);
+
 struct fwnode_handle *get_pch_msi_handle(int pci_segment);
 
 extern struct acpi_madt_lio_pic *acpi_liointc;

arch/loongarch/include/asm/kfence.h

@@ -43,13 +43,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
 {
 	pte_t *pte = virt_to_kpte(addr);
 
-	if (WARN_ON(!pte) || pte_none(*pte))
+	if (WARN_ON(!pte) || pte_none(ptep_get(pte)))
 		return false;
 
 	if (protect)
-		set_pte(pte, __pte(pte_val(*pte) & ~(_PAGE_VALID | _PAGE_PRESENT)));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~(_PAGE_VALID | _PAGE_PRESENT)));
 	else
-		set_pte(pte, __pte(pte_val(*pte) | (_PAGE_VALID | _PAGE_PRESENT)));
+		set_pte(pte, __pte(pte_val(ptep_get(pte)) | (_PAGE_VALID | _PAGE_PRESENT)));
 
 	preempt_disable();
 	local_flush_tlb_one(addr);