Merge tag 'loongarch-kvm-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson into HEAD

LoongArch KVM changes for v6.9

* Set reserved bits as zero in CPUCFG.
* Start SW timer only when vcpu is blocking.
* Do not restart SW timer when it is expired.
* Remove unnecessary CSR register saving during enter guest.

30 files changed, 262 insertions, 96 deletions

diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index 1ebd2ca97f12..107fc5a48456 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -20,14 +20,6 @@
 #ifndef __ASSEMBLY__
 extern void _mcount(void);
 
-static inline unsigned long ftrace_call_adjust(unsigned long addr)
-{
-	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
-		addr += MCOUNT_INSN_SIZE;
-
-	return addr;
-}
-
 unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
 				    unsigned long sp);
 
@@ -142,8 +134,10 @@ static inline u8 this_cpu_get_ftrace_enabled(void) { return 1; }
 #ifdef CONFIG_FUNCTION_TRACER
 extern unsigned int ftrace_tramp_text[], ftrace_tramp_init[];
 void ftrace_free_init_tramp(void);
+unsigned long ftrace_call_adjust(unsigned long addr);
 #else
 static inline void ftrace_free_init_tramp(void) { }
+static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; }
 #endif
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/papr-sysparm.h b/arch/powerpc/include/asm/papr-sysparm.h
index 0dbbff59101d..c3cd5b131033 100644
--- a/arch/powerpc/include/asm/papr-sysparm.h
+++ b/arch/powerpc/include/asm/papr-sysparm.h
@@ -32,7 +32,7 @@ typedef struct {
  */
 struct papr_sysparm_buf {
 	__be16 len;
-	char val[PAPR_SYSPARM_MAX_OUTPUT];
+	u8 val[PAPR_SYSPARM_MAX_OUTPUT];
 };
 
 struct papr_sysparm_buf *papr_sysparm_buf_alloc(void);
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index ce2b1b5eebdd..a8b7e8682f5b 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -30,6 +30,16 @@ void *pci_traverse_device_nodes(struct device_node *start,
 				void *data);
 extern void pci_devs_phb_init_dynamic(struct pci_controller *phb);
 
+#if defined(CONFIG_IOMMU_API) && (defined(CONFIG_PPC_PSERIES) || \
+				  defined(CONFIG_PPC_POWERNV))
+extern void ppc_iommu_register_device(struct pci_controller *phb);
+extern void ppc_iommu_unregister_device(struct pci_controller *phb);
+#else
+static inline void ppc_iommu_register_device(struct pci_controller *phb) { }
+static inline void ppc_iommu_unregister_device(struct pci_controller *phb) { }
+#endif
+
+
 /* From rtas_pci.h */
 extern void init_pci_config_tokens (void);
 extern unsigned long get_phb_buid (struct device_node *);
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 7fd09f25452d..bb47af9054a9 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -617,6 +617,8 @@
 #endif
 #define SPRN_HID2	0x3F8		/* Hardware Implementation Register 2 */
 #define SPRN_HID2_GEKKO	0x398		/* Gekko HID2 Register */
+#define SPRN_HID2_G2_LE	0x3F3		/* G2_LE HID2 Register */
+#define  HID2_G2_LE_HBE	(1<<18)		/* High BAT Enable (G2_LE) */
 #define SPRN_IABR	0x3F2	/* Instruction Address Breakpoint Register */
 #define SPRN_IABR2	0x3FA		/* 83xx */
 #define SPRN_IBCR	0x135		/* 83xx Insn Breakpoint Control Reg */
diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h
index 9bb2210c8d44..065ffd1b2f8a 100644
--- a/arch/powerpc/include/asm/rtas.h
+++ b/arch/powerpc/include/asm/rtas.h
@@ -69,7 +69,7 @@ enum rtas_function_index {
 	RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE,
 	RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2,
 	RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW,
-	RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS,
+	RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW,
 	RTAS_FNIDX__IBM_SCAN_LOG_DUMP,
 	RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR,
 	RTAS_FNIDX__IBM_SET_EEH_OPTION,
@@ -164,7 +164,7 @@ typedef struct {
 #define RTAS_FN_IBM_READ_SLOT_RESET_STATE         rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE)
 #define RTAS_FN_IBM_READ_SLOT_RESET_STATE2        rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2)
 #define RTAS_FN_IBM_REMOVE_PE_DMA_WINDOW          rtas_fn_handle(RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW)
-#define RTAS_FN_IBM_RESET_PE_DMA_WINDOWS          rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS)
+#define RTAS_FN_IBM_RESET_PE_DMA_WINDOW           rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW)
 #define RTAS_FN_IBM_SCAN_LOG_DUMP                 rtas_fn_handle(RTAS_FNIDX__IBM_SCAN_LOG_DUMP)
 #define RTAS_FN_IBM_SET_DYNAMIC_INDICATOR         rtas_fn_handle(RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR)
 #define RTAS_FN_IBM_SET_EEH_OPTION                rtas_fn_handle(RTAS_FNIDX__IBM_SET_EEH_OPTION)
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index ea26665f82cf..f43f3a6b0051 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -14,6 +14,7 @@ typedef struct func_desc func_desc_t;
 
 extern char __head_end[];
 extern char __srwx_boundary[];
+extern char __exittext_begin[], __exittext_end[];
 
 /* Patch sites */
 extern s32 patch__call_flush_branch_caches1;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index bf5dde1a4114..15c5691dd218 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -14,7 +14,7 @@
 
 #ifdef __KERNEL__
 
-#ifdef CONFIG_KASAN
+#if defined(CONFIG_KASAN) && CONFIG_THREAD_SHIFT < 15
 #define MIN_THREAD_SHIFT	(CONFIG_THREAD_SHIFT + 1)
 #else
 #define MIN_THREAD_SHIFT	CONFIG_THREAD_SHIFT
diff --git a/arch/powerpc/include/uapi/asm/papr-sysparm.h b/arch/powerpc/include/uapi/asm/papr-sysparm.h
index 9f9a0f267ea5..f733467b1534 100644
--- a/arch/powerpc/include/uapi/asm/papr-sysparm.h
+++ b/arch/powerpc/include/uapi/asm/papr-sysparm.h
@@ -14,7 +14,7 @@ enum {
 struct papr_sysparm_io_block {
 	__u32 parameter;
 	__u16 length;
-	char data[PAPR_SYSPARM_MAX_OUTPUT];
+	__u8 data[PAPR_SYSPARM_MAX_OUTPUT];
 };
 
 /**
diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S
index f29ce3dd6140..bfd3f442e5eb 100644
--- a/arch/powerpc/kernel/cpu_setup_6xx.S
+++ b/arch/powerpc/kernel/cpu_setup_6xx.S
@@ -26,6 +26,15 @@ BEGIN_FTR_SECTION
 	bl	__init_fpu_registers
 END_FTR_SECTION_IFCLR(CPU_FTR_FPU_UNAVAILABLE)
 	bl	setup_common_caches
+
+	/*
+	 * This assumes that all cores using __setup_cpu_603 with
+	 * MMU_FTR_USE_HIGH_BATS are G2_LE compatible
+	 */
+BEGIN_MMU_FTR_SECTION
+	bl      setup_g2_le_hid2
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+
 	mtlr	r5
 	blr
 _GLOBAL(__setup_cpu_604)
@@ -115,6 +124,16 @@ SYM_FUNC_START_LOCAL(setup_604_hid0)
 	blr
 SYM_FUNC_END(setup_604_hid0)
 
+/* Enable high BATs for G2_LE and derivatives like e300cX */
+SYM_FUNC_START_LOCAL(setup_g2_le_hid2)
+	mfspr	r11,SPRN_HID2_G2_LE
+	oris	r11,r11,HID2_G2_LE_HBE@h
+	mtspr	SPRN_HID2_G2_LE,r11
+	sync
+	isync
+	blr
+SYM_FUNC_END(setup_g2_le_hid2)
+
 /* 7400 <= rev 2.7 and 7410 rev = 1.0 suffer from some
  * erratas we work around here.
  * Moto MPC710CE.pdf describes them, those are errata
@@ -495,4 +514,3 @@ _GLOBAL(__restore_cpu_setup)
 	mtcr	r7
 	blr
 _ASM_NOKPROBE_SYMBOL(__restore_cpu_setup)
-
diff --git a/arch/powerpc/kernel/cpu_specs_e500mc.h b/arch/powerpc/kernel/cpu_specs_e500mc.h
index ceb06b109f83..2ae8e9a7b461 100644
--- a/arch/powerpc/kernel/cpu_specs_e500mc.h
+++ b/arch/powerpc/kernel/cpu_specs_e500mc.h
@@ -8,7 +8,8 @@
 
 #ifdef CONFIG_PPC64
 #define COMMON_USER_BOOKE	(PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
-				 PPC_FEATURE_HAS_FPU | PPC_FEATURE_64)
+				 PPC_FEATURE_HAS_FPU | PPC_FEATURE_64 | \
+				 PPC_FEATURE_BOOKE)
 #else
 #define COMMON_USER_BOOKE	(PPC_FEATURE_32 | PPC_FEATURE_HAS_MMU | \
 				 PPC_FEATURE_BOOKE)
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index bd863702d812..1ad059a9e2fe 100644
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -52,7 +52,8 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
-	std	r11,_NIP(r1)
+	std	r11,_LINK(r1)
+	std	r11,_NIP(r1)	/* Saved LR is also the next instruction */
 	std	r12,_MSR(r1)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
@@ -70,7 +71,6 @@ _ASM_NOKPROBE_SYMBOL(system_call_vectored_\name)
 	std	r9,GPR13(r1)
 	SAVE_NVGPRS(r1)
 	std	r11,_XER(r1)
-	std	r11,_LINK(r1)
 	std	r11,_CTR(r1)
 
 	li	r11,\trapnr
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index d71eac3b2887..1185efebf032 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -1289,8 +1289,10 @@ spapr_tce_platform_iommu_attach_dev(struct iommu_domain *platform_domain,
 	struct iommu_table_group *table_group;
 
 	/* At first attach the ownership is already set */
-	if (!domain)
+	if (!domain) {
+		iommu_group_put(grp);
 		return 0;
+	}
 
 	table_group = iommu_group_get_iommudata(grp);
 	/*
@@ -1358,7 +1360,7 @@ static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev)
 	struct pci_controller *hose;
 
 	if (!dev_is_pci(dev))
-		return ERR_PTR(-EPERM);
+		return ERR_PTR(-ENODEV);
 
 	pdev = to_pci_dev(dev);
 	hose = pdev->bus->sysdata;
@@ -1407,6 +1409,21 @@ static const struct attribute_group *spapr_tce_iommu_groups[] = {
 	NULL,
 };
 
+void ppc_iommu_register_device(struct pci_controller *phb)
+{
+	iommu_device_sysfs_add(&phb->iommu, phb->parent,
+				spapr_tce_iommu_groups, "iommu-phb%04x",
+				phb->global_number);
+	iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops,
+				phb->parent);
+}
+
+void ppc_iommu_unregister_device(struct pci_controller *phb)
+{
+	iommu_device_unregister(&phb->iommu);
+	iommu_device_sysfs_remove(&phb->iommu);
+}
+
 /*
  * This registers IOMMU devices of PHBs. This needs to happen
  * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and
@@ -1417,11 +1434,7 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void)
 	struct pci_controller *hose;
 
 	list_for_each_entry(hose, &hose_list, list_node) {
-		iommu_device_sysfs_add(&hose->iommu, hose->parent,
-				       spapr_tce_iommu_groups, "iommu-phb%04x",
-				       hose->global_number);
-		iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops,
-				      hose->parent);
+		ppc_iommu_register_device(hose);
 	}
 	return 0;
 }
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 7e793b503e29..8064d9c3de86 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -375,8 +375,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = {
 	[RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = {
 		.name = "ibm,remove-pe-dma-window",
 	},
-	[RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS] = {
-		.name = "ibm,reset-pe-dma-windows",
+	[RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW] = {
+		/*
+		 * Note: PAPR+ v2.13 7.3.31.4.1 spells this as
+		 * "ibm,reset-pe-dma-windows" (plural), but RTAS
+		 * implementations use the singular form in practice.
+		 */
+		.name = "ibm,reset-pe-dma-window",
 	},
 	[RTAS_FNIDX__IBM_SCAN_LOG_DUMP] = {
 		.name = "ibm,scan-log-dump",
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 82010629cf88..d8d6b4fd9a14 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -27,10 +27,22 @@
 #include <asm/ftrace.h>
 #include <asm/syscall.h>
 #include <asm/inst.h>
+#include <asm/sections.h>
 
 #define	NUM_FTRACE_TRAMPS	2
 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
 
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	if (addr >= (unsigned long)__exittext_begin && addr < (unsigned long)__exittext_end)
+		return 0;
+
+	if (IS_ENABLED(CONFIG_ARCH_USING_PATCHABLE_FUNCTION_ENTRY))
+		addr += MCOUNT_INSN_SIZE;
+
+	return addr;
+}
+
 static ppc_inst_t ftrace_create_branch_inst(unsigned long ip, unsigned long addr, int link)
 {
 	ppc_inst_t op;
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
index 7b85c3b460a3..12fab1803bcf 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.c
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -37,6 +37,11 @@
 #define	NUM_FTRACE_TRAMPS	8
 static unsigned long ftrace_tramps[NUM_FTRACE_TRAMPS];
 
+unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	return addr;
+}
+
 static ppc_inst_t
 ftrace_call_replace(unsigned long ip, unsigned long addr, int link)
 {
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 1c5970df3233..f420df7888a7 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -281,7 +281,9 @@ SECTIONS
 	 * to deal with references from __bug_table
 	 */
 	.exit.text : AT(ADDR(.exit.text) - LOAD_OFFSET) {
+		__exittext_begin = .;
 		EXIT_TEXT
+		__exittext_end = .;
 	}
 
 	. = ALIGN(PAGE_SIZE);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 52427fc2a33f..0b921704da45 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -391,6 +391,24 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
 /* Dummy value used in computing PCR value below */
 #define PCR_ARCH_31    (PCR_ARCH_300 << 1)
 
+static inline unsigned long map_pcr_to_cap(unsigned long pcr)
+{
+	unsigned long cap = 0;
+
+	switch (pcr) {
+	case PCR_ARCH_300:
+		cap = H_GUEST_CAP_POWER9;
+		break;
+	case PCR_ARCH_31:
+		cap = H_GUEST_CAP_POWER10;
+		break;
+	default:
+		break;
+	}
+
+	return cap;
+}
+
 static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 {
 	unsigned long host_pcr_bit = 0, guest_pcr_bit = 0, cap = 0;
@@ -424,11 +442,9 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 			break;
 		case PVR_ARCH_300:
 			guest_pcr_bit = PCR_ARCH_300;
-			cap = H_GUEST_CAP_POWER9;
 			break;
 		case PVR_ARCH_31:
 			guest_pcr_bit = PCR_ARCH_31;
-			cap = H_GUEST_CAP_POWER10;
 			break;
 		default:
 			return -EINVAL;
@@ -440,6 +456,12 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 		return -EINVAL;
 
 	if (kvmhv_on_pseries() && kvmhv_is_nestedv2()) {
+		/*
+		 * 'arch_compat == 0' would mean the guest should default to
+		 * L1's compatibility. In this case, the guest would pick
+		 * host's PCR and evaluate the corresponding capabilities.
+		 */
+		cap = map_pcr_to_cap(guest_pcr_bit);
 		if (!(cap & nested_capabilities))
 			return -EINVAL;
 	}
diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
index 5378eb40b162..8e6f5355f08b 100644
--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
+++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
@@ -138,6 +138,7 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
 	vector128 v;
 	int rc, i;
 	u16 iden;
+	u32 arch_compat = 0;
 
 	vcpu = gsm->data;
 
@@ -347,8 +348,23 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
 			break;
 		}
 		case KVMPPC_GSID_LOGICAL_PVR:
-			rc = kvmppc_gse_put_u32(gsb, iden,
-						vcpu->arch.vcore->arch_compat);
+			/*
+			 * Though 'arch_compat == 0' would mean the default
+			 * compatibility, arch_compat, being a Guest Wide
+			 * Element, cannot be filled with a value of 0 in GSB
+			 * as this would result into a kernel trap.
+			 * Hence, when `arch_compat == 0`, arch_compat should
+			 * default to L1's PVR.
+			 */
+			if (!vcpu->arch.vcore->arch_compat) {
+				if (cpu_has_feature(CPU_FTR_ARCH_31))
+					arch_compat = PVR_ARCH_31;
+				else if (cpu_has_feature(CPU_FTR_ARCH_300))
+					arch_compat = PVR_ARCH_300;
+			} else {
+				arch_compat = vcpu->arch.vcore->arch_compat;
+			}
+			rc = kvmppc_gse_put_u32(gsb, iden, arch_compat);
 			break;
 		}
 
diff --git a/arch/powerpc/mm/kasan/init_32.c b/arch/powerpc/mm/kasan/init_32.c
index a70828a6d935..aa9aa11927b2 100644
--- a/arch/powerpc/mm/kasan/init_32.c
+++ b/arch/powerpc/mm/kasan/init_32.c
@@ -64,6 +64,7 @@ int __init __weak kasan_init_region(void *start, size_t size)
 	if (ret)
 		return ret;
 
+	k_start = k_start & PAGE_MASK;
 	block = memblock_alloc(k_end - k_start, PAGE_SIZE);
 	if (!block)
 		return -ENOMEM;
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index e966b2ad8ecd..b3327a358eb4 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -27,7 +27,7 @@
 
 #include "mpc85xx.h"
 
-void __init mpc8536_ds_pic_init(void)
+static void __init mpc8536_ds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
 			0, 256, " OpenPIC  ");
diff --git a/arch/powerpc/platforms/85xx/mvme2500.c b/arch/powerpc/platforms/85xx/mvme2500.c
index 1b59e45a0c64..19122daadb55 100644
--- a/arch/powerpc/platforms/85xx/mvme2500.c
+++ b/arch/powerpc/platforms/85xx/mvme2500.c
@@ -21,7 +21,7 @@
 
 #include "mpc85xx.h"
 
-void __init mvme2500_pic_init(void)
+static void __init mvme2500_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0,
 		  MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1010rdb.c b/arch/powerpc/platforms/85xx/p1010rdb.c
index 10d6f1fa3327..491895ac8bcf 100644
--- a/arch/powerpc/platforms/85xx/p1010rdb.c
+++ b/arch/powerpc/platforms/85xx/p1010rdb.c
@@ -24,7 +24,7 @@
 
 #include "mpc85xx.h"
 
-void __init p1010_rdb_pic_init(void)
+static void __init p1010_rdb_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 	  MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 0dd786a061a6..adc3a2ee1415 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -370,7 +370,7 @@ exit:
  *
  * @pixclock: the wavelength, in picoseconds, of the clock
  */
-void p1022ds_set_pixel_clock(unsigned int pixclock)
+static void p1022ds_set_pixel_clock(unsigned int pixclock)
 {
 	struct device_node *guts_np = NULL;
 	struct ccsr_guts __iomem *guts;
@@ -418,7 +418,7 @@ void p1022ds_set_pixel_clock(unsigned int pixclock)
 /**
  * p1022ds_valid_monitor_port: set the monitor port for sysfs
  */
-enum fsl_diu_monitor_port
+static enum fsl_diu_monitor_port
 p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
 	switch (port) {
@@ -432,7 +432,7 @@ p1022ds_valid_monitor_port(enum fsl_diu_monitor_port port)
 
 #endif
 
-void __init p1022_ds_pic_init(void)
+static void __init p1022_ds_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 		MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/p1022_rdk.c b/arch/powerpc/platforms/85xx/p1022_rdk.c
index 25ab6e9c1470..6198299d95b1 100644
--- a/arch/powerpc/platforms/85xx/p1022_rdk.c
+++ b/arch/powerpc/platforms/85xx/p1022_rdk.c
@@ -40,7 +40,7 @@
  *
  * @pixclock: the wavelength, in picoseconds, of the clock
  */
-void p1022rdk_set_pixel_clock(unsigned int pixclock)
+static void p1022rdk_set_pixel_clock(unsigned int pixclock)
 {
 	struct device_node *guts_np = NULL;
 	struct ccsr_guts __iomem *guts;
@@ -88,7 +88,7 @@ void p1022rdk_set_pixel_clock(unsigned int pixclock)
 /**
  * p1022rdk_valid_monitor_port: set the monitor port for sysfs
  */
-enum fsl_diu_monitor_port
+static enum fsl_diu_monitor_port
 p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port)
 {
 	return FSL_DIU_PORT_DVI;
@@ -96,7 +96,7 @@ p1022rdk_valid_monitor_port(enum fsl_diu_monitor_port port)
 
 #endif
 
-void __init p1022_rdk_pic_init(void)
+static void __init p1022_rdk_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
 		MPIC_SINGLE_DEST_CPU,
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index baa12eff6d5d..60e0b8947ce6 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -8,6 +8,8 @@
 #include <linux/of_irq.h>
 #include <linux/io.h>
 
+#include "socrates_fpga_pic.h"
+
 /*
  * The FPGA supports 9 interrupt sources, which can be routed to 3
  * interrupt request lines of the MPIC. The line to be used can be
diff --git a/arch/powerpc/platforms/85xx/xes_mpc85xx.c b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
index 45f257fc1ade..2582427d8d01 100644
--- a/arch/powerpc/platforms/85xx/xes_mpc85xx.c
+++ b/arch/powerpc/platforms/85xx/xes_mpc85xx.c
@@ -37,7 +37,7 @@
 #define MPC85xx_L2CTL_L2I		0x40000000 /* L2 flash invalidate */
 #define MPC85xx_L2CTL_L2SIZ_MASK	0x30000000 /* L2 SRAM size (R/O) */
 
-void __init xes_mpc85xx_pic_init(void)
+static void __init xes_mpc85xx_pic_init(void)
 {
 	struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
 			0, 256, " OpenPIC  ");
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 496e16c588aa..e8c4129697b1 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -574,29 +574,6 @@ static void iommu_table_setparms(struct pci_controller *phb,
 
 struct iommu_table_ops iommu_table_lpar_multi_ops;
 
-/*
- * iommu_table_setparms_lpar
- *
- * Function: On pSeries LPAR systems, return TCE table info, given a pci bus.
- */
-static void iommu_table_setparms_lpar(struct pci_controller *phb,
-				      struct device_node *dn,
-				      struct iommu_table *tbl,
-				      struct iommu_table_group *table_group,
-				      const __be32 *dma_window)
-{
-	unsigned long offset, size, liobn;
-
-	of_parse_dma_window(dn, dma_window, &liobn, &offset, &size);
-
-	iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL,
-				    &iommu_table_lpar_multi_ops);
-
-
-	table_group->tce32_start = offset;
-	table_group->tce32_size = size;
-}
-
 struct iommu_table_ops iommu_table_pseries_ops = {
 	.set = tce_build_pSeries,
 	.clear = tce_free_pSeries,
@@ -724,26 +701,71 @@ struct iommu_table_ops iommu_table_lpar_multi_ops = {
  * dynamic 64bit DMA window, walking up the device tree.
  */
 static struct device_node *pci_dma_find(struct device_node *dn,
-					const __be32 **dma_window)
+					struct dynamic_dma_window_prop *prop)
 {
-	const __be32 *dw = NULL;
+	const __be32 *default_prop = NULL;
+	const __be32 *ddw_prop = NULL;
+	struct device_node *rdn = NULL;
+	bool default_win = false, ddw_win = false;
 
 	for ( ; dn && PCI_DN(dn); dn = dn->parent) {
-		dw = of_get_property(dn, "ibm,dma-window", NULL);
-		if (dw) {
-			if (dma_window)
-				*dma_window = dw;
-			return dn;
+		default_prop = of_get_property(dn, "ibm,dma-window", NULL);
+		if (default_prop) {
+			rdn = dn;
+			default_win = true;
+		}
+		ddw_prop = of_get_property(dn, DIRECT64_PROPNAME, NULL);
+		if (ddw_prop) {
+			rdn = dn;
+			ddw_win = true;
+			break;
+		}
+		ddw_prop = of_get_property(dn, DMA64_PROPNAME, NULL);
+		if (ddw_prop) {
+			rdn = dn;
+			ddw_win = true;
+			break;
 		}
-		dw = of_get_property(dn, DIRECT64_PROPNAME, NULL);
-		if (dw)
-			return dn;
-		dw = of_get_property(dn, DMA64_PROPNAME, NULL);
-		if (dw)
-			return dn;
+
+		/* At least found default window, which is the case for normal boot */
+		if (default_win)
+			break;
 	}
 
-	return NULL;
+	/* For PCI devices there will always be a DMA window, either on the device
+	 * or parent bus
+	 */
+	WARN_ON(!(default_win | ddw_win));
+
+	/* caller doesn't want to get DMA window property */
+	if (!prop)
+		return rdn;
+
+	/* parse DMA window property. During normal system boot, only default
+	 * DMA window is passed in OF. But, for kdump, a dedicated adapter might
+	 * have both default and DDW in FDT. In this scenario, DDW takes precedence
+	 * over default window.
+	 */
+	if (ddw_win) {
+		struct dynamic_dma_window_prop *p;
+
+		p = (struct dynamic_dma_window_prop *)ddw_prop;
+		prop->liobn = p->liobn;
+		prop->dma_base = p->dma_base;
+		prop->tce_shift = p->tce_shift;
+		prop->window_shift = p->window_shift;
+	} else if (default_win) {
+		unsigned long offset, size, liobn;
+
+		of_parse_dma_window(rdn, default_prop, &liobn, &offset, &size);
+
+		prop->liobn = cpu_to_be32((u32)liobn);
+		prop->dma_base = cpu_to_be64(offset);
+		prop->tce_shift = cpu_to_be32(IOMMU_PAGE_SHIFT_4K);
+		prop->window_shift = cpu_to_be32(order_base_2(size));
+	}
+
+	return rdn;
 }
 
 static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
@@ -751,17 +773,20 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	struct iommu_table *tbl;
 	struct device_node *dn, *pdn;
 	struct pci_dn *ppci;
-	const __be32 *dma_window = NULL;
+	struct dynamic_dma_window_prop prop;
 
 	dn = pci_bus_to_OF_node(bus);
 
 	pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n",
 		 dn);
 
-	pdn = pci_dma_find(dn, &dma_window);
+	pdn = pci_dma_find(dn, &prop);
 
-	if (dma_window == NULL)
-		pr_debug("  no ibm,dma-window property !\n");
+	/* In PPC architecture, there will always be DMA window on bus or one of the
+	 * parent bus. During reboot, there will be ibm,dma-window property to
+	 * define DMA window. For kdump, there will at least be default window or DDW
+	 * or both.
+	 */
 
 	ppci = PCI_DN(pdn);
 
@@ -771,13 +796,24 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus)
 	if (!ppci->table_group) {
 		ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node);
 		tbl = ppci->table_group->tables[0];
-		if (dma_window) {
-			iommu_table_setparms_lpar(ppci->phb, pdn, tbl,
-						  ppci->table_group, dma_window);
 
-			if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
-				panic("Failed to initialize iommu table");
-		}
+		iommu_table_setparms_common(tbl, ppci->phb->bus->number,
+				be32_to_cpu(prop.liobn),
+				be64_to_cpu(prop.dma_base),
+				1ULL << be32_to_cpu(prop.window_shift),
+				be32_to_cpu(prop.tce_shift), NULL,
+				&iommu_table_lpar_multi_ops);
+
+		/* Only for normal boot with default window. Doesn't matter even
+		 * if we set these with DDW which is 64bit during kdump, since
+		 * these will not be used during kdump.
+		 */
+		ppci->table_group->tce32_start = be64_to_cpu(prop.dma_base);
+		ppci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
+
+		if (!iommu_init_table(tbl, ppci->phb->node, 0, 0))
+			panic("Failed to initialize iommu table");
+
 		iommu_register_group(ppci->table_group,
 				pci_domain_nr(bus), 0);
 		pr_debug("  created table: %p\n", ppci->table_group);
@@ -968,6 +1004,12 @@ static void find_existing_ddw_windows_named(const char *name)
 			continue;
 		}
 
+		/* If at the time of system initialization, there are DDWs in OF,
+		 * it means this is during kexec. DDW could be direct or dynamic.
+		 * We will just mark DDWs as "dynamic" since this is kdump path,
+		 * no need to worry about perforance. ddw_list_new_entry() will
+		 * set window->direct = false.
+		 */
 		window = ddw_list_new_entry(pdn, dma64);
 		if (!window) {
 			of_node_put(pdn);
@@ -1524,8 +1566,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 {
 	struct device_node *pdn, *dn;
 	struct iommu_table *tbl;
-	const __be32 *dma_window = NULL;
 	struct pci_dn *pci;
+	struct dynamic_dma_window_prop prop;
 
 	pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev));
 
@@ -1538,7 +1580,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	dn = pci_device_to_OF_node(dev);
 	pr_debug("  node is %pOF\n", dn);
 
-	pdn = pci_dma_find(dn, &dma_window);
+	pdn = pci_dma_find(dn, &prop);
 	if (!pdn || !PCI_DN(pdn)) {
 		printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: "
 		       "no DMA window found for pci dev=%s dn=%pOF\n",
@@ -1551,8 +1593,20 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
 	if (!pci->table_group) {
 		pci->table_group = iommu_pseries_alloc_group(pci->phb->node);
 		tbl = pci->table_group->tables[0];
-		iommu_table_setparms_lpar(pci->phb, pdn, tbl,
-				pci->table_group, dma_window);
+
+		iommu_table_setparms_common(tbl, pci->phb->bus->number,
+				be32_to_cpu(prop.liobn),
+				be64_to_cpu(prop.dma_base),
+				1ULL << be32_to_cpu(prop.window_shift),
+				be32_to_cpu(prop.tce_shift), NULL,
+				&iommu_table_lpar_multi_ops);
+
+		/* Only for normal boot with default window. Doesn't matter even
+		 * if we set these with DDW which is 64bit during kdump, since
+		 * these will not be used during kdump.
+		 */
+		pci->table_group->tce32_start = be64_to_cpu(prop.dma_base);
+		pci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift);
 
 		iommu_init_table(tbl, pci->phb->node, 0, 0);
 		iommu_register_group(pci->table_group,
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 4561667832ed..4e9916bb03d7 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -662,8 +662,12 @@ u64 pseries_paravirt_steal_clock(int cpu)
 {
 	struct lppaca *lppaca = &lppaca_of(cpu);
 
-	return be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
-		be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb));
+	/*
+	 * VPA steal time counters are reported at TB frequency. Hence do a
+	 * conversion to ns before returning
+	 */
+	return tb_to_ns(be64_to_cpu(READ_ONCE(lppaca->enqueue_dispatch_tb)) +
+			be64_to_cpu(READ_ONCE(lppaca->ready_enqueue_tb)));
 }
 #endif
 
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 4ba824568119..4448386268d9 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -35,6 +35,8 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn)
 
 	pseries_msi_allocate_domains(phb);
 
+	ppc_iommu_register_device(phb);
+
 	/* Create EEH devices for the PHB */
 	eeh_phb_pe_create(phb);
 
@@ -76,6 +78,8 @@ int remove_phb_dynamic(struct pci_controller *phb)
 		}
 	}
 
+	ppc_iommu_unregister_device(phb);
+
 	pseries_msi_free_domains(phb);
 
 	/* Keep a reference so phb isn't freed yet */
diff --git a/arch/powerpc/sysdev/udbg_memcons.c b/arch/powerpc/sysdev/udbg_memcons.c
index 5020044400dc..4de57ba52236 100644
--- a/arch/powerpc/sysdev/udbg_memcons.c
+++ b/arch/powerpc/sysdev/udbg_memcons.c
@@ -41,7 +41,7 @@ struct memcons memcons = {
 	.input_end = &memcons_input[CONFIG_PPC_MEMCONS_INPUT_SIZE],
 };
 
-void memcons_putc(char c)
+static void memcons_putc(char c)
 {
 	char *new_output_pos;
 
@@ -54,7 +54,7 @@ void memcons_putc(char c)
 	memcons.output_pos = new_output_pos;
 }
 
-int memcons_getc_poll(void)
+static int memcons_getc_poll(void)
 {
 	char c;
 	char *new_input_pos;
@@ -77,7 +77,7 @@ int memcons_getc_poll(void)
 	return -1;
 }
 
-int memcons_getc(void)
+static int memcons_getc(void)
 {
 	int c;