Merge tag 'loongarch-kvm-6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson into HEAD

LoongArch KVM changes for v6.8

1. Optimization for memslot hugepage checking.
2. Cleanup and fix some HW/SW timer issues.
3. Add LSX/LASX (128bit/256bit SIMD) support.

17 files changed, 82 insertions, 53 deletions

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 76db82542519c..797ae590ebdba 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -460,6 +460,7 @@ config MACH_LOONGSON2EF
 
 config MACH_LOONGSON64
 	bool "Loongson 64-bit family of machines"
+	select ARCH_DMA_DEFAULT_COHERENT
 	select ARCH_SPARSEMEM_ENABLE
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
@@ -1251,6 +1252,7 @@ config CPU_LOONGSON64
 	select CPU_SUPPORTS_MSA
 	select CPU_DIEI_BROKEN if !LOONGSON3_ENHANCEMENT
 	select CPU_MIPSR2_IRQ_VI
+	select DMA_NONCOHERENT
 	select WEAK_ORDERING
 	select WEAK_REORDERING_BEYOND_LLSC
 	select MIPS_ASID_BITS_VARIABLE
diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
index f878f47e4501b..ee3e2153dd13f 100644
--- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
+++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
@@ -130,8 +130,7 @@
 				compatible = "pci0014,7a03.0",
 						   "pci0014,7a03",
 						   "pciclass0c0320",
-						   "pciclass0c03",
-						   "loongson, pci-gmac";
+						   "pciclass0c03";
 
 				reg = <0x1800 0x0 0x0 0x0 0x0>;
 				interrupts = <12 IRQ_TYPE_LEVEL_LOW>,
diff --git a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
index 7c69e8245c2f1..cce9428afc41f 100644
--- a/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
+++ b/arch/mips/boot/dts/loongson/ls7a-pch.dtsi
@@ -193,8 +193,7 @@
 				compatible = "pci0014,7a03.0",
 						   "pci0014,7a03",
 						   "pciclass020000",
-						   "pciclass0200",
-						   "loongson, pci-gmac";
+						   "pciclass0200";
 
 				reg = <0x1800 0x0 0x0 0x0 0x0>;
 				interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 33c09688210ff..08ea2cde1eb5b 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -422,7 +422,7 @@ static const struct plat_smp_ops octeon_smp_ops = {
 	.cpu_disable		= octeon_cpu_disable,
 	.cpu_die		= octeon_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
@@ -502,7 +502,7 @@ static const struct plat_smp_ops octeon_78xx_smp_ops = {
 	.cpu_disable		= octeon_cpu_disable,
 	.cpu_die		= octeon_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
diff --git a/arch/mips/include/asm/kexec.h b/arch/mips/include/asm/kexec.h
index d6d5fa5cc31dd..69e579e41e662 100644
--- a/arch/mips/include/asm/kexec.h
+++ b/arch/mips/include/asm/kexec.h
@@ -31,7 +31,7 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
 		prepare_frametrace(newregs);
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 struct kimage;
 extern unsigned long kexec_args[4];
 extern int (*_machine_kexec_prepare)(struct kimage *);
diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h
index 035b1a69e2d00..e007edd6b60a7 100644
--- a/arch/mips/include/asm/mach-loongson64/boot_param.h
+++ b/arch/mips/include/asm/mach-loongson64/boot_param.h
@@ -14,7 +14,11 @@
 #define ADAPTER_ROM		8
 #define ACPI_TABLE		9
 #define SMBIOS_TABLE		10
-#define MAX_MEMORY_TYPE		11
+#define UMA_VIDEO_RAM		11
+#define VUMA_VIDEO_RAM		12
+#define MAX_MEMORY_TYPE		13
+
+#define MEM_SIZE_IS_IN_BYTES	(1 << 31)
 
 #define LOONGSON3_BOOT_MEM_MAP_MAX 128
 struct efi_memory_map_loongson {
@@ -117,7 +121,8 @@ struct irq_source_routing_table {
 	u64 pci_io_start_addr;
 	u64 pci_io_end_addr;
 	u64 pci_config_addr;
-	u32 dma_mask_bits;
+	u16 dma_mask_bits;
+	u16 dma_noncoherent;
 } __packed;
 
 struct interface_info {
diff --git a/arch/mips/include/asm/smp-ops.h b/arch/mips/include/asm/smp-ops.h
index 5719ff49eff1c..0c59e168f8008 100644
--- a/arch/mips/include/asm/smp-ops.h
+++ b/arch/mips/include/asm/smp-ops.h
@@ -35,7 +35,7 @@ struct plat_smp_ops {
 	void (*cpu_die)(unsigned int cpu);
 	void (*cleanup_dead_cpu)(unsigned cpu);
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	void (*kexec_nonboot_cpu)(void);
 #endif
 };
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index a40d8c0e4b879..901bc61fa7ae9 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -93,7 +93,7 @@ static inline void __cpu_die(unsigned int cpu)
 extern void __noreturn play_dead(void);
 #endif
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 static inline void kexec_nonboot_cpu(void)
 {
 	extern const struct plat_smp_ops *mp_ops;	/* private */
diff --git a/arch/mips/kernel/Makefile b/arch/mips/kernel/Makefile
index 853a43ee4b446..ecf3278a32f70 100644
--- a/arch/mips/kernel/Makefile
+++ b/arch/mips/kernel/Makefile
@@ -90,7 +90,7 @@ obj-$(CONFIG_GPIO_TXX9)		+= gpio_txx9.o
 
 obj-$(CONFIG_RELOCATABLE)	+= relocate.o
 
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o crash.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_EARLY_PRINTK_8250)	+= early_printk_8250.o
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 5387ed0a51862..b630604c577f9 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -121,6 +121,19 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	/*  Put the stack after the struct pt_regs.  */
 	childksp = (unsigned long) childregs;
 	p->thread.cp0_status = (read_c0_status() & ~(ST0_CU2|ST0_CU1)) | ST0_KERNEL_CUMASK;
+
+	/*
+	 * New tasks lose permission to use the fpu. This accelerates context
+	 * switching for most programs since they don't use the fpu.
+	 */
+	clear_tsk_thread_flag(p, TIF_USEDFPU);
+	clear_tsk_thread_flag(p, TIF_USEDMSA);
+	clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE);
+
+#ifdef CONFIG_MIPS_MT_FPAFF
+	clear_tsk_thread_flag(p, TIF_FPUBOUND);
+#endif /* CONFIG_MIPS_MT_FPAFF */
+
 	if (unlikely(args->fn)) {
 		/* kernel thread */
 		unsigned long status = p->thread.cp0_status;
@@ -149,20 +162,8 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	p->thread.reg29 = (unsigned long) childregs;
 	p->thread.reg31 = (unsigned long) ret_from_fork;
 
-	/*
-	 * New tasks lose permission to use the fpu. This accelerates context
-	 * switching for most programs since they don't use the fpu.
-	 */
 	childregs->cp0_status &= ~(ST0_CU2|ST0_CU1);
 
-	clear_tsk_thread_flag(p, TIF_USEDFPU);
-	clear_tsk_thread_flag(p, TIF_USEDMSA);
-	clear_tsk_thread_flag(p, TIF_MSA_CTX_LIVE);
-
-#ifdef CONFIG_MIPS_MT_FPAFF
-	clear_tsk_thread_flag(p, TIF_FPUBOUND);
-#endif /* CONFIG_MIPS_MT_FPAFF */
-
 #ifdef CONFIG_MIPS_FP_SUPPORT
 	atomic_set(&p->thread.bd_emu_frame, BD_EMUFRAME_NONE);
 #endif
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index c074ecce3fbf2..b3dbf9ecb0d63 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -434,7 +434,7 @@ const struct plat_smp_ops bmips43xx_smp_ops = {
 	.cpu_disable		= bmips_cpu_disable,
 	.cpu_die		= bmips_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
@@ -451,7 +451,7 @@ const struct plat_smp_ops bmips5000_smp_ops = {
 	.cpu_disable		= bmips_cpu_disable,
 	.cpu_die		= bmips_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= kexec_nonboot_cpu_jump,
 #endif
 };
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index dd55d59b88db3..f6c37d407f365 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -392,7 +392,7 @@ static void cps_smp_finish(void)
 	local_irq_enable();
 }
 
-#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC)
+#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_KEXEC_CORE)
 
 enum cpu_death {
 	CPU_DEATH_HALT,
@@ -429,7 +429,7 @@ static void cps_shutdown_this_cpu(enum cpu_death death)
 	}
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 static void cps_kexec_nonboot_cpu(void)
 {
@@ -439,9 +439,9 @@ static void cps_kexec_nonboot_cpu(void)
 		cps_shutdown_this_cpu(CPU_DEATH_POWER);
 }
 
-#endif /* CONFIG_KEXEC */
+#endif /* CONFIG_KEXEC_CORE */
 
-#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC */
+#endif /* CONFIG_HOTPLUG_CPU || CONFIG_KEXEC_CORE */
 
 #ifdef CONFIG_HOTPLUG_CPU
 
@@ -610,7 +610,7 @@ static const struct plat_smp_ops cps_smp_ops = {
 	.cpu_die		= cps_cpu_die,
 	.cleanup_dead_cpu	= cps_cleanup_dead_cpu,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu	= cps_kexec_nonboot_cpu,
 #endif
 };
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 8fbef537fb885..82e2e051b4161 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -351,10 +351,11 @@ early_initcall(mips_smp_ipi_init);
  */
 asmlinkage void start_secondary(void)
 {
-	unsigned int cpu;
+	unsigned int cpu = raw_smp_processor_id();
 
 	cpu_probe();
 	per_cpu_trap_init(false);
+	rcutree_report_cpu_starting(cpu);
 	mips_clockevent_init();
 	mp_ops->init_secondary();
 	cpu_report();
@@ -366,7 +367,6 @@ asmlinkage void start_secondary(void)
 	 */
 
 	calibrate_delay();
-	cpu = smp_processor_id();
 	cpu_data[cpu].udelay_val = loops_per_jiffy;
 
 	set_cpu_sibling_map(cpu);
diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c
index c961e2999f15a..ef3750a6ffacf 100644
--- a/arch/mips/loongson64/env.c
+++ b/arch/mips/loongson64/env.c
@@ -13,6 +13,8 @@
  * Copyright (C) 2009 Lemote Inc.
  * Author: Wu Zhangjin, wuzhangjin@gmail.com
  */
+
+#include <linux/dma-map-ops.h>
 #include <linux/export.h>
 #include <linux/pci_ids.h>
 #include <asm/bootinfo.h>
@@ -147,8 +149,14 @@ void __init prom_lefi_init_env(void)
 
 	loongson_sysconf.dma_mask_bits = eirq_source->dma_mask_bits;
 	if (loongson_sysconf.dma_mask_bits < 32 ||
-		loongson_sysconf.dma_mask_bits > 64)
+			loongson_sysconf.dma_mask_bits > 64) {
 		loongson_sysconf.dma_mask_bits = 32;
+		dma_default_coherent = true;
+	} else {
+		dma_default_coherent = !eirq_source->dma_noncoherent;
+	}
+
+	pr_info("Firmware: Coherent DMA: %s\n", dma_default_coherent ? "on" : "off");
 
 	loongson_sysconf.restart_addr = boot_p->reset_system.ResetWarm;
 	loongson_sysconf.poweroff_addr = boot_p->reset_system.Shutdown;
diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c
index ee8de1735b7c0..f25caa6aa9d30 100644
--- a/arch/mips/loongson64/init.c
+++ b/arch/mips/loongson64/init.c
@@ -49,8 +49,7 @@ void virtual_early_config(void)
 void __init szmem(unsigned int node)
 {
 	u32 i, mem_type;
-	static unsigned long num_physpages;
-	u64 node_id, node_psize, start_pfn, end_pfn, mem_start, mem_size;
+	phys_addr_t node_id, mem_start, mem_size;
 
 	/* Otherwise come from DTB */
 	if (loongson_sysconf.fw_interface != LOONGSON_LEFI)
@@ -64,30 +63,46 @@ void __init szmem(unsigned int node)
 
 		mem_type = loongson_memmap->map[i].mem_type;
 		mem_size = loongson_memmap->map[i].mem_size;
-		mem_start = loongson_memmap->map[i].mem_start;
+
+		/* Memory size comes in MB if MEM_SIZE_IS_IN_BYTES not set */
+		if (mem_size & MEM_SIZE_IS_IN_BYTES)
+			mem_size &= ~MEM_SIZE_IS_IN_BYTES;
+		else
+			mem_size = mem_size << 20;
+
+		mem_start = (node_id << 44) | loongson_memmap->map[i].mem_start;
 
 		switch (mem_type) {
 		case SYSTEM_RAM_LOW:
 		case SYSTEM_RAM_HIGH:
-			start_pfn = ((node_id << 44) + mem_start) >> PAGE_SHIFT;
-			node_psize = (mem_size << 20) >> PAGE_SHIFT;
-			end_pfn  = start_pfn + node_psize;
-			num_physpages += node_psize;
-			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
-				(u32)node_id, mem_type, mem_start, mem_size);
-			pr_info("       start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
-				start_pfn, end_pfn, num_physpages);
-			memblock_add_node(PFN_PHYS(start_pfn),
-					  PFN_PHYS(node_psize), node,
+		case UMA_VIDEO_RAM:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes usable\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
+			memblock_add_node(mem_start, mem_size, node,
 					  MEMBLOCK_NONE);
 			break;
 		case SYSTEM_RAM_RESERVED:
-			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
-				(u32)node_id, mem_type, mem_start, mem_size);
-			memblock_reserve(((node_id << 44) + mem_start), mem_size << 20);
+		case VIDEO_ROM:
+		case ADAPTER_ROM:
+		case ACPI_TABLE:
+		case SMBIOS_TABLE:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes reserved\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
+			memblock_reserve(mem_start, mem_size);
+			break;
+		/* We should not reserve VUMA_VIDEO_RAM as it overlaps with MMIO */
+		case VUMA_VIDEO_RAM:
+		default:
+			pr_info("Node %d, mem_type:%d\t[%pa], %pa bytes unhandled\n",
+				(u32)node_id, mem_type, &mem_start, &mem_size);
 			break;
 		}
 	}
+
+	/* Reserve vgabios if it comes from firmware */
+	if (loongson_sysconf.vgabios_addr)
+		memblock_reserve(virt_to_phys((void *)loongson_sysconf.vgabios_addr),
+				SZ_256K);
 }
 
 #ifndef CONFIG_NUMA
diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c
index e420800043b08..e01c8d4a805a9 100644
--- a/arch/mips/loongson64/reset.c
+++ b/arch/mips/loongson64/reset.c
@@ -53,7 +53,7 @@ static void loongson_halt(void)
 	}
 }
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 
 /* 0X80000000~0X80200000 is safe */
 #define MAX_ARGS	64
@@ -158,7 +158,7 @@ static int __init mips_reboot_setup(void)
 	_machine_halt = loongson_halt;
 	pm_power_off = loongson_poweroff;
 
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	kexec_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL);
 	if (WARN_ON(!kexec_argv))
 		return -ENOMEM;
diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c
index e015a26a40f7a..498bdc1bb0ede 100644
--- a/arch/mips/loongson64/smp.c
+++ b/arch/mips/loongson64/smp.c
@@ -864,7 +864,7 @@ const struct plat_smp_ops loongson3_smp_ops = {
 	.cpu_disable = loongson3_cpu_disable,
 	.cpu_die = loongson3_cpu_die,
 #endif
-#ifdef CONFIG_KEXEC
+#ifdef CONFIG_KEXEC_CORE
 	.kexec_nonboot_cpu = kexec_nonboot_cpu_jump,
 #endif
 };