Merge tag 'powerpc-5.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "A pretty small batch for us, and apologies for it being a bit late, I
  wanted to sneak Christophe's user_access_begin() series in.

  Summary:

   - Implement user_access_begin() and friends for our platforms that
     support controlling kernel access to userspace.

   - Enable CONFIG_VMAP_STACK on 32-bit Book3S and 8xx.

   - Some tweaks to our pseries IOMMU code to allow SVMs ("secure"
     virtual machines) to use the IOMMU.

   - Add support for CLOCK_{REALTIME/MONOTONIC}_COARSE to the 32-bit
     VDSO, and some other improvements.

   - A series to use the PCI hotplug framework to control opencapi
     card's so that they can be reset and re-read after flashing a new
     FPGA image.

  As well as other minor fixes and improvements as usual.

  Thanks to: Alastair D'Silva, Alexandre Ghiti, Alexey Kardashevskiy,
  Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Bai Yingjie, Chen
  Zhou, Christophe Leroy, Frederic Barrat, Greg Kurz, Jason A.
  Donenfeld, Joel Stanley, Jordan Niethe, Julia Lawall, Krzysztof
  Kozlowski, Laurent Dufour, Laurentiu Tudor, Linus Walleij, Michael
  Bringmann, Nathan Chancellor, Nicholas Piggin, Nick Desaulniers,
  Oliver O'Halloran, Peter Ujfalusi, Pingfan Liu, Ram Pai, Randy Dunlap,
  Russell Currey, Sam Bobroff, Sebastian Andrzej Siewior, Shawn
  Anastasio, Stephen Rothwell, Steve Best, Sukadev Bhattiprolu, Thiago
  Jung Bauermann, Tyrel Datwyler, Vaibhav Jain"

* tag 'powerpc-5.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (131 commits)
  powerpc: configs: Cleanup old Kconfig options
  powerpc/configs/skiroot: Enable some more hardening options
  powerpc/configs/skiroot: Disable xmon default & enable reboot on panic
  powerpc/configs/skiroot: Enable security features
  powerpc/configs/skiroot: Update for symbol movement only
  powerpc/configs/skiroot: Drop default n CONFIG_CRYPTO_ECHAINIV
  powerpc/configs/skiroot: Drop HID_LOGITECH
  powerpc/configs: Drop NET_VENDOR_HP which moved to staging
  powerpc/configs: NET_CADENCE became NET_VENDOR_CADENCE
  powerpc/configs: Drop CONFIG_QLGE which moved to staging
  powerpc: Do not consider weak unresolved symbol relocations as bad
  powerpc/32s: Fix kasan_early_hash_table() for CONFIG_VMAP_STACK
  powerpc: indent to improve Kconfig readability
  powerpc: Provide initial documentation for PAPR hcalls
  powerpc: Implement user_access_save() and user_access_restore()
  powerpc: Implement user_access_begin and friends
  powerpc/32s: Prepare prevent_user_access() for user_access_end()
  powerpc/32s: Drop NULL addr verification
  powerpc/kuap: Fix set direction in allow/prevent_user_access()
  powerpc/32s: Fix bad_kuap_fault()
  ...

40 files changed, 689 insertions, 509 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 157b0147921f..78a1b22d4fd8 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -62,8 +62,7 @@ obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
-obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
-obj-$(CONFIG_PPC_P7_NAP)	+= idle_book3s.o
+obj-$(CONFIG_PPC_BOOK3S_IDLE)	+= idle_book3s.o
 procfs-y			:= proc_powerpc.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
 rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI)	:= rtas_pci.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 3d47aec7becf..c25e562f1cd9 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -127,6 +127,12 @@ int main(void)
 	OFFSET(KSP_VSID, thread_struct, ksp_vsid);
 #else /* CONFIG_PPC64 */
 	OFFSET(PGDIR, thread_struct, pgdir);
+#ifdef CONFIG_VMAP_STACK
+	OFFSET(SRR0, thread_struct, srr0);
+	OFFSET(SRR1, thread_struct, srr1);
+	OFFSET(DAR, thread_struct, dar);
+	OFFSET(DSISR, thread_struct, dsisr);
+#endif
 #ifdef CONFIG_SPE
 	OFFSET(THREAD_EVR0, thread_struct, evr[0]);
 	OFFSET(THREAD_ACC, thread_struct, acc);
@@ -389,11 +395,11 @@ int main(void)
 	OFFSET(STAMP_XTIME_NSEC, vdso_data, stamp_xtime_nsec);
 	OFFSET(STAMP_SEC_FRAC, vdso_data, stamp_sec_fraction);
 	OFFSET(CLOCK_HRTIMER_RES, vdso_data, hrtimer_res);
+#ifdef CONFIG_PPC64
 	OFFSET(CFG_ICACHE_BLOCKSZ, vdso_data, icache_block_size);
 	OFFSET(CFG_DCACHE_BLOCKSZ, vdso_data, dcache_block_size);
 	OFFSET(CFG_ICACHE_LOGBLOCKSZ, vdso_data, icache_log_block_size);
 	OFFSET(CFG_DCACHE_LOGBLOCKSZ, vdso_data, dcache_log_block_size);
-#ifdef CONFIG_PPC64
 	OFFSET(CFG_SYSCALL_MAP64, vdso_data, syscall_map_64);
 	OFFSET(TVAL64_TV_SEC, __kernel_old_timeval, tv_sec);
 	OFFSET(TVAL64_TV_USEC, __kernel_old_timeval, tv_usec);
@@ -413,7 +419,10 @@ int main(void)
 	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
 	DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
 	DEFINE(CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE);
+	DEFINE(CLOCK_MAX, CLOCK_TAI);
 	DEFINE(NSEC_PER_SEC, NSEC_PER_SEC);
+	DEFINE(EINVAL, EINVAL);
+	DEFINE(KTIME_LOW_RES, KTIME_LOW_RES);
 
 #ifdef CONFIG_BUG
 	DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry));
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 180b3a5d1001..182b4047c1ef 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -727,17 +727,20 @@ static __init void cpufeatures_cpu_quirks(void)
 	/*
 	 * Not all quirks can be derived from the cpufeatures device tree.
 	 */
-	if ((version & 0xffffefff) == 0x004e0200)
-		; /* DD2.0 has no feature flag */
-	else if ((version & 0xffffefff) == 0x004e0201)
+	if ((version & 0xffffefff) == 0x004e0200) {
+		/* DD2.0 has no feature flag */
+		cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG;
+	} else if ((version & 0xffffefff) == 0x004e0201) {
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
-	else if ((version & 0xffffefff) == 0x004e0202) {
+		cur_cpu_spec->cpu_features |= CPU_FTR_P9_RADIX_PREFETCH_BUG;
+	} else if ((version & 0xffffefff) == 0x004e0202) {
 		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_HV_ASSIST;
 		cur_cpu_spec->cpu_features |= CPU_FTR_P9_TM_XER_SO_BUG;
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
-	} else if ((version & 0xffff0000) == 0x004e0000)
+	} else if ((version & 0xffff0000) == 0x004e0000) {
 		/* DD2.1 and up have DD2_1 */
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
+	}
 
 	if ((version & 0xffff0000) == 0x004e0000) {
 		cur_cpu_spec->cpu_features &= ~(CPU_FTR_DAWR);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index bc8a551013be..17cb3e9b5697 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -503,7 +503,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	rc = 1;
 	if (pe->state & EEH_PE_ISOLATED) {
 		pe->check_count++;
-		if (pe->check_count % EEH_MAX_FAILS == 0) {
+		if (pe->check_count == EEH_MAX_FAILS) {
 			dn = pci_device_to_OF_node(dev);
 			if (dn)
 				location = of_get_property(dn, "ibm,loc-code",
@@ -1191,7 +1191,6 @@ void eeh_add_device_late(struct pci_dev *dev)
 		eeh_rmv_from_parent_pe(edev);
 		eeh_addr_cache_rmv_dev(edev->pdev);
 		eeh_sysfs_remove_device(edev->pdev);
-		edev->mode &= ~EEH_DEV_SYSFS;
 
 		/*
 		 * We definitely should have the PCI device removed
@@ -1296,17 +1295,11 @@ void eeh_remove_device(struct pci_dev *dev)
 	edev->pdev = NULL;
 
 	/*
-	 * The flag "in_error" is used to trace EEH devices for VFs
-	 * in error state or not. It's set in eeh_report_error(). If
-	 * it's not set, eeh_report_{reset,resume}() won't be called
-	 * for the VF EEH device.
+	 * eeh_sysfs_remove_device() uses pci_dev_to_eeh_dev() so we need to
+	 * remove the sysfs files before clearing dev.archdata.edev
 	 */
-	edev->in_error = false;
-	dev->dev.archdata.edev = NULL;
-	if (!(edev->pe->state & EEH_PE_KEEP))
-		eeh_rmv_from_parent_pe(edev);
-	else
-		edev->mode |= EEH_DEV_DISCONNECTED;
+	if (edev->mode & EEH_DEV_SYSFS)
+		eeh_sysfs_remove_device(dev);
 
 	/*
 	 * We're removing from the PCI subsystem, that means
@@ -1317,8 +1310,19 @@ void eeh_remove_device(struct pci_dev *dev)
 	edev->mode |= EEH_DEV_NO_HANDLER;
 
 	eeh_addr_cache_rmv_dev(dev);
-	eeh_sysfs_remove_device(dev);
-	edev->mode &= ~EEH_DEV_SYSFS;
+
+	/*
+	 * The flag "in_error" is used to trace EEH devices for VFs
+	 * in error state or not. It's set in eeh_report_error(). If
+	 * it's not set, eeh_report_{reset,resume}() won't be called
+	 * for the VF EEH device.
+	 */
+	edev->in_error = false;
+	dev->dev.archdata.edev = NULL;
+	if (!(edev->pe->state & EEH_PE_KEEP))
+		eeh_rmv_from_parent_pe(edev);
+	else
+		edev->mode |= EEH_DEV_DISCONNECTED;
 }
 
 int eeh_unfreeze_pe(struct eeh_pe *pe)
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index cf11277ebd02..6b50bf15d8c1 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -159,18 +159,10 @@ eeh_addr_cache_insert(struct pci_dev *dev, resource_size_t alo,
 
 static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
 {
-	struct pci_dn *pdn;
 	struct eeh_dev *edev;
 	int i;
 
-	pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
-	if (!pdn) {
-		pr_warn("PCI: no pci dn found for dev=%s\n",
-			pci_name(dev));
-		return;
-	}
-
-	edev = pdn_to_eeh_dev(pdn);
+	edev = pci_dev_to_eeh_dev(dev);
 	if (!edev) {
 		pr_warn("PCI: no EEH dev found for %s\n",
 			pci_name(dev));
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 3dd1a422fc29..a1eaffe868de 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -525,12 +525,6 @@ static void eeh_rmv_device(struct eeh_dev *edev, void *userdata)
 
 		pci_iov_remove_virtfn(edev->physfn, pdn->vf_index);
 		edev->pdev = NULL;
-
-		/*
-		 * We have to set the VF PE number to invalid one, which is
-		 * required to plug the VF successfully.
-		 */
-		pdn->pe_number = IODA_INVALID_PE;
 #endif
 		if (rmv_data)
 			list_add(&edev->rmv_entry, &rmv_data->removed_vf_list);
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index ab44d965a53c..4fb0f1e1017a 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -14,7 +14,7 @@
 /**
  * EEH_SHOW_ATTR -- Create sysfs entry for eeh statistic
  * @_name: name of file in sysfs directory
- * @_memb: name of member in struct pci_dn to access
+ * @_memb: name of member in struct eeh_dev to access
  * @_format: printf format for display
  *
  * All of the attributes look very similar, so just
@@ -75,7 +75,7 @@ static ssize_t eeh_pe_state_store(struct device *dev,
 
 static DEVICE_ATTR_RW(eeh_pe_state);
 
-#ifdef CONFIG_PCI_IOV
+#if defined(CONFIG_PCI_IOV) && defined(CONFIG_PPC_PSERIES)
 static ssize_t eeh_notify_resume_show(struct device *dev,
 				      struct device_attribute *attr, char *buf)
 {
@@ -86,7 +86,6 @@ static ssize_t eeh_notify_resume_show(struct device *dev,
 	if (!edev || !edev->pe)
 		return -ENODEV;
 
-	pdn = pci_get_pdn(pdev);
 	return sprintf(buf, "%d\n", pdn->last_allow_rc);
 }
 
@@ -132,7 +131,7 @@ static void eeh_notify_resume_remove(struct pci_dev *pdev)
 #else
 static inline int eeh_notify_resume_add(struct pci_dev *pdev) { return 0; }
 static inline void eeh_notify_resume_remove(struct pci_dev *pdev) { }
-#endif /* CONFIG_PCI_IOV */
+#endif /* CONFIG_PCI_IOV && CONFIG PPC_PSERIES*/
 
 void eeh_sysfs_add_device(struct pci_dev *pdev)
 {
@@ -160,22 +159,23 @@ void eeh_sysfs_remove_device(struct pci_dev *pdev)
 {
 	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
 
+	if (!edev) {
+		WARN_ON(eeh_enabled());
+		return;
+	}
+
+	edev->mode &= ~EEH_DEV_SYSFS;
+
 	/*
 	 * The parent directory might have been removed. We needn't
 	 * continue for that case.
 	 */
-	if (!pdev->dev.kobj.sd) {
-		if (edev)
-			edev->mode &= ~EEH_DEV_SYSFS;
+	if (!pdev->dev.kobj.sd)
 		return;
-	}
 
 	device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_state);
 
 	eeh_notify_resume_remove(pdev);
-
-	if (edev)
-		edev->mode &= ~EEH_DEV_SYSFS;
 }
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e1a4c39b83b8..77abbc34bbe0 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -140,6 +140,7 @@ transfer_to_handler:
 	stw	r12,_CTR(r11)
 	stw	r2,_XER(r11)
 	mfspr	r12,SPRN_SPRG_THREAD
+	tovirt_vmstack r12, r12
 	beq	2f			/* if from user, fix up THREAD.regs */
 	addi	r2, r12, -THREAD
 	addi	r11,r1,STACK_FRAME_OVERHEAD
@@ -179,11 +180,13 @@ transfer_to_handler:
 2:	/* if from kernel, check interrupted DOZE/NAP mode and
          * check for stack overflow
          */
-	kuap_save_and_lock r11, r12, r9, r2, r0
+	kuap_save_and_lock r11, r12, r9, r2, r6
 	addi	r2, r12, -THREAD
+#ifndef CONFIG_VMAP_STACK
 	lwz	r9,KSP_LIMIT(r12)
 	cmplw	r1,r9			/* if r1 <= ksp_limit */
 	ble-	stack_ovf		/* then the kernel stack overflowed */
+#endif
 5:
 #if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500)
 	lwz	r12,TI_LOCAL_FLAGS(r2)
@@ -195,7 +198,8 @@ transfer_to_handler:
 transfer_to_handler_cont:
 3:
 	mflr	r9
-	tovirt(r2, r2)			/* set r2 to current */
+	tovirt_novmstack r2, r2 	/* set r2 to current */
+	tovirt_vmstack r9, r9
 	lwz	r11,0(r9)		/* virtual address of handler */
 	lwz	r9,4(r9)		/* where to go when done */
 #if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
@@ -284,9 +288,11 @@ reenable_mmu:
 	rlwinm	r9,r9,0,~MSR_EE
 	lwz	r12,_LINK(r11)		/* and return to address in LR */
 	kuap_restore r11, r2, r3, r4, r5
+	lwz	r2, GPR2(r11)
 	b	fast_exception_return
 #endif
 
+#ifndef CONFIG_VMAP_STACK
 /*
  * On kernel stack overflow, load up an initial stack pointer
  * and call StackOverflow(regs), which should not return.
@@ -312,6 +318,7 @@ stack_ovf:
 	mtspr	SPRN_SRR1,r10
 	SYNC
 	RFI
+#endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 trace_syscall_entry_irq_off:
@@ -397,7 +404,7 @@ ret_from_syscall:
 	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
 	/* Note: We don't bother telling lockdep about it */
 	SYNC
-	MTMSRD(r10)
+	mtmsr	r10
 	lwz	r9,TI_FLAGS(r2)
 	li	r8,-MAX_ERRNO
 	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
@@ -554,7 +561,7 @@ syscall_exit_work:
 	 */
 	ori	r10,r10,MSR_EE
 	SYNC
-	MTMSRD(r10)
+	mtmsr	r10
 
 	/* Save NVGPRS if they're not saved already */
 	lwz	r4,_TRAP(r1)
@@ -621,7 +628,6 @@ ppc_swapcontext:
  */
 	.globl	handle_page_fault
 handle_page_fault:
-	stw	r4,_DAR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_PPC_BOOK3S_32
 	andis.  r0,r5,DSISR_DABRMATCH@h
@@ -697,7 +703,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPE)
 	and.	r0,r0,r11	/* FP or altivec or SPE enabled? */
 	beq+	1f
 	andc	r11,r11,r0
-	MTMSRD(r11)
+	mtmsr	r11
 	isync
 1:	stw	r11,_MSR(r1)
 	mfcr	r10
@@ -831,7 +837,7 @@ ret_from_except:
 	/* Note: We don't bother telling lockdep about it */
 	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
 	SYNC			/* Some chip revs have problems here... */
-	MTMSRD(r10)		/* disable interrupts */
+	mtmsr	r10		/* disable interrupts */
 
 	lwz	r3,_MSR(r1)	/* Returning to user mode? */
 	andi.	r0,r3,MSR_PR
@@ -998,7 +1004,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	 */
 	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL & ~MSR_RI)
 	SYNC
-	MTMSRD(r10)		/* clear the RI bit */
+	mtmsr	r10		/* clear the RI bit */
 	.globl exc_exit_restart
 exc_exit_restart:
 	lwz	r12,_NIP(r1)
@@ -1234,7 +1240,7 @@ do_resched:			/* r10 contains MSR_KERNEL here */
 #endif
 	ori	r10,r10,MSR_EE
 	SYNC
-	MTMSRD(r10)		/* hard-enable interrupts */
+	mtmsr	r10		/* hard-enable interrupts */
 	bl	schedule
 recheck:
 	/* Note: And we don't tell it we are disabling them again
@@ -1243,7 +1249,7 @@ recheck:
 	 */
 	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
 	SYNC
-	MTMSRD(r10)		/* disable interrupts */
+	mtmsr	r10		/* disable interrupts */
 	lwz	r9,TI_FLAGS(r2)
 	andi.	r0,r9,_TIF_NEED_RESCHED
 	bne-	do_resched
@@ -1252,7 +1258,7 @@ recheck:
 do_user_signal:			/* r10 contains MSR_KERNEL here */
 	ori	r10,r10,MSR_EE
 	SYNC
-	MTMSRD(r10)		/* hard-enable interrupts */
+	mtmsr	r10		/* hard-enable interrupts */
 	/* save r13-r31 in the exception frame, if not already done */
 	lwz	r3,_TRAP(r1)
 	andi.	r0,r3,1
@@ -1334,14 +1340,14 @@ _GLOBAL(enter_rtas)
 	lis	r6,1f@ha	/* physical return address for rtas */
 	addi	r6,r6,1f@l
 	tophys(r6,r6)
-	tophys(r7,r1)
+	tophys_novmstack r7, r1
 	lwz	r8,RTASENTRY(r4)
 	lwz	r4,RTASBASE(r4)
 	mfmsr	r9
 	stw	r9,8(r1)
 	LOAD_REG_IMMEDIATE(r0,MSR_KERNEL)
 	SYNC			/* disable interrupts so SRR0/1 */
-	MTMSRD(r0)		/* don't get trashed */
+	mtmsr	r0		/* don't get trashed */
 	li	r9,MSR_KERNEL & ~(MSR_IR|MSR_DR)
 	mtlr	r6
 	stw	r7, THREAD + RTAS_SP(r2)
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index a9a1d3cdb523..6ba675b0cf7d 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -597,8 +597,7 @@ _GLOBAL(_switch)
 	std	r0,16(r1)
 	stdu	r1,-SWITCH_FRAME_SIZE(r1)
 	/* r3-r13 are caller saved -- Cort */
-	SAVE_8GPRS(14, r1)
-	SAVE_10GPRS(22, r1)
+	SAVE_NVGPRS(r1)
 	std	r0,_NIP(r1)	/* Return to switch caller */
 	mfcr	r23
 	std	r23,_CCR(r1)
@@ -722,8 +721,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	mtcrf	0xFF,r6
 
 	/* r3-r13 are destroyed -- Cort */
-	REST_8GPRS(14, r1)
-	REST_10GPRS(22, r1)
+	REST_NVGPRS(r1)
 
 	/* convert old thread to its task_struct for return value */
 	addi	r3,r3,-THREAD
@@ -1155,8 +1153,7 @@ _GLOBAL(enter_rtas)
    	 */
 	SAVE_GPR(2, r1)			/* Save the TOC */
 	SAVE_GPR(13, r1)		/* Save paca */
-	SAVE_8GPRS(14, r1)		/* Save the non-volatiles */
-	SAVE_10GPRS(22, r1)		/* ditto */
+	SAVE_NVGPRS(r1)			/* Save the non-volatiles */
 
 	mfcr	r4
 	std	r4,_CCR(r1)
@@ -1263,8 +1260,7 @@ rtas_restore_regs:
 	/* relocation is on at this point */
 	REST_GPR(2, r1)			/* Restore the TOC */
 	REST_GPR(13, r1)		/* Restore paca */
-	REST_8GPRS(14, r1)		/* Restore the non-volatiles */
-	REST_10GPRS(22, r1)		/* ditto */
+	REST_NVGPRS(r1)			/* Restore the non-volatiles */
 
 	GET_PACA(r13)
 
@@ -1298,8 +1294,7 @@ _GLOBAL(enter_prom)
    	 */
 	SAVE_GPR(2, r1)
 	SAVE_GPR(13, r1)
-	SAVE_8GPRS(14, r1)
-	SAVE_10GPRS(22, r1)
+	SAVE_NVGPRS(r1)
 	mfcr	r10
 	mfmsr	r11
 	std	r10,_CCR(r1)
@@ -1343,8 +1338,7 @@ _GLOBAL(enter_prom)
 	/* Restore other registers */
 	REST_GPR(2, r1)
 	REST_GPR(13, r1)
-	REST_8GPRS(14, r1)
-	REST_10GPRS(22, r1)
+	REST_NVGPRS(r1)
 	ld	r4,_CCR(r1)
 	mtcr	r4
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 46508b148e16..ffc15f4f079d 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1408,22 +1408,9 @@ EXC_VIRT_NONE(0x4b00, 0x100)
  *
  * Call convention:
  *
- * syscall register convention is in Documentation/powerpc/syscall64-abi.rst
- *
- * For hypercalls, the register convention is as follows:
- * r0 volatile
- * r1-2 nonvolatile
- * r3 volatile parameter and return value for status
- * r4-r10 volatile input and output value
- * r11 volatile hypercall number and output value
- * r12 volatile input and output value
- * r13-r31 nonvolatile
- * LR nonvolatile
- * CTR volatile
- * XER volatile
- * CR0-1 CR5-7 volatile
- * CR2-4 nonvolatile
- * Other registers nonvolatile
+ * syscall and hypercalls register conventions are documented in
+ * Documentation/powerpc/syscall64-abi.rst and
+ * Documentation/powerpc/papr_hcalls.rst respectively.
  *
  * The intersection of volatile registers that don't contain possible
  * inputs is: cr0, xer, ctr. We may use these as scratch regs upon entry
@@ -2208,11 +2195,20 @@ __end_interrupts:
 DEFINE_FIXED_SYMBOL(__end_interrupts)
 
 #ifdef CONFIG_PPC_970_NAP
+	/*
+	 * Called by exception entry code if _TLF_NAPPING was set, this clears
+	 * the NAPPING flag, and redirects the exception exit to
+	 * power4_fixup_nap_return.
+	 */
+	.globl power4_fixup_nap
 EXC_COMMON_BEGIN(power4_fixup_nap)
 	andc	r9,r9,r10
 	std	r9,TI_LOCAL_FLAGS(r11)
-	ld	r10,_LINK(r1)		/* make idle task do the */
-	std	r10,_NIP(r1)		/* equivalent of a blr */
+	LOAD_REG_ADDR(r10, power4_idle_nap_return)
+	std	r10,_NIP(r1)
+	blr
+
+power4_idle_nap_return:
 	blr
 #endif
 
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 0bb991ddd264..3235a8da6af7 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -94,6 +94,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	/* enable use of FP after return */
 #ifdef CONFIG_PPC32
 	mfspr	r5,SPRN_SPRG_THREAD	/* current task's THREAD (phys) */
+#ifdef CONFIG_VMAP_STACK
+	tovirt(r5, r5)
+#endif
 	lwz	r4,THREAD_FPEXC_MODE(r5)
 	ori	r9,r9,MSR_FP		/* enable FP for current */
 	or	r9,r9,r4
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 4a24f8f026c7..0493fcac6409 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -272,16 +272,21 @@ __secondary_hold_acknowledge:
  */
 	. = 0x200
 	DO_KVM  0x200
-	mtspr	SPRN_SPRG_SCRATCH0,r10
-	mtspr	SPRN_SPRG_SCRATCH1,r11
-	mfcr	r10
+MachineCheck:
+	EXCEPTION_PROLOG_0
+#ifdef CONFIG_VMAP_STACK
+	li	r11, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
+	mtmsr	r11
+	isync
+#endif
 #ifdef CONFIG_PPC_CHRP
 	mfspr	r11, SPRN_SPRG_THREAD
+	tovirt_vmstack r11, r11
 	lwz	r11, RTAS_SP(r11)
 	cmpwi	cr1, r11, 0
 	bne	cr1, 7f
 #endif /* CONFIG_PPC_CHRP */
-	EXCEPTION_PROLOG_1
+	EXCEPTION_PROLOG_1 for_rtas=1
 7:	EXCEPTION_PROLOG_2
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_PPC_CHRP
@@ -296,24 +301,21 @@ __secondary_hold_acknowledge:
 	. = 0x300
 	DO_KVM  0x300
 DataAccess:
-	EXCEPTION_PROLOG
-	mfspr	r10,SPRN_DSISR
-	stw	r10,_DSISR(r11)
+	EXCEPTION_PROLOG handle_dar_dsisr=1
+	get_and_save_dar_dsisr_on_stack	r4, r5, r11
+BEGIN_MMU_FTR_SECTION
 #ifdef CONFIG_PPC_KUAP
-	andis.	r0,r10,(DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h
+	andis.	r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH | DSISR_PROTFAULT)@h
 #else
-	andis.	r0,r10,(DSISR_BAD_FAULT_32S|DSISR_DABRMATCH)@h
+	andis.	r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h
 #endif
-	bne	1f			/* if not, try to put a PTE */
-	mfspr	r4,SPRN_DAR		/* into the hash table */
-	rlwinm	r3,r10,32-15,21,21	/* DSISR_STORE -> _PAGE_RW */
-BEGIN_MMU_FTR_SECTION
+	bne	handle_page_fault_tramp_2	/* if not, try to put a PTE */
+	rlwinm	r3, r5, 32 - 15, 21, 21		/* DSISR_STORE -> _PAGE_RW */
 	bl	hash_page
-END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
-1:	lwz	r5,_DSISR(r11)		/* get DSISR value */
-	mfspr	r4,SPRN_DAR
-	EXC_XFER_LITE(0x300, handle_page_fault)
-
+	b	handle_page_fault_tramp_1
+FTR_SECTION_ELSE
+	b	handle_page_fault_tramp_2
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE)
 
 /* Instruction access exception. */
 	. = 0x400
@@ -329,6 +331,7 @@ BEGIN_MMU_FTR_SECTION
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
 1:	mr	r4,r12
 	andis.	r5,r9,DSISR_SRR1_MATCH_32S@h /* Filter relevant SRR1 bits */
+	stw	r4, _DAR(r11)
 	EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* External interrupt */
@@ -338,11 +341,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
 	. = 0x600
 	DO_KVM  0x600
 Alignment:
-	EXCEPTION_PROLOG
-	mfspr	r4,SPRN_DAR
-	stw	r4,_DAR(r11)
-	mfspr	r5,SPRN_DSISR
-	stw	r5,_DSISR(r11)
+	EXCEPTION_PROLOG handle_dar_dsisr=1
+	save_dar_dsisr_on_stack r4, r5, r11
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	EXC_XFER_STD(0x600, alignment_exception)
 
@@ -645,6 +645,16 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU)
 
 	. = 0x3000
 
+handle_page_fault_tramp_1:
+	lwz	r4, _DAR(r11)
+	lwz	r5, _DSISR(r11)
+	/* fall through */
+handle_page_fault_tramp_2:
+	EXC_XFER_LITE(0x300, handle_page_fault)
+
+stack_overflow:
+	vmap_stack_overflow_exception
+
 AltiVecUnavailable:
 	EXCEPTION_PROLOG
 #ifdef CONFIG_ALTIVEC
@@ -917,6 +927,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
 	ori	r4,r4,2f@l
 	tophys(r4,r4)
 	li	r3,MSR_KERNEL & ~(MSR_IR|MSR_DR)
+
+	.align	4
 	mtspr	SPRN_SRR0,r4
 	mtspr	SPRN_SRR1,r3
 	SYNC
@@ -1058,6 +1070,8 @@ _ENTRY(update_bats)
 	rlwinm	r0, r6, 0, ~MSR_RI
 	rlwinm	r0, r0, 0, ~MSR_EE
 	mtmsr	r0
+
+	.align	4
 	mtspr	SPRN_SRR0, r4
 	mtspr	SPRN_SRR1, r3
 	SYNC
@@ -1097,6 +1111,8 @@ mmu_off:
 	andi.	r0,r3,MSR_DR|MSR_IR		/* MMU enabled? */
 	beqlr
 	andc	r3,r3,r0
+
+	.align	4
 	mtspr	SPRN_SRR0,r4
 	mtspr	SPRN_SRR1,r3
 	sync
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 8abc7783dbe5..a6a5fbbf8504 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -10,28 +10,60 @@
  * We assume sprg3 has the physical address of the current
  * task's thread_struct.
  */
+.macro EXCEPTION_PROLOG handle_dar_dsisr=0
+	EXCEPTION_PROLOG_0	handle_dar_dsisr=\handle_dar_dsisr
+	EXCEPTION_PROLOG_1
+	EXCEPTION_PROLOG_2	handle_dar_dsisr=\handle_dar_dsisr
+.endm
 
-.macro EXCEPTION_PROLOG
+.macro EXCEPTION_PROLOG_0 handle_dar_dsisr=0
 	mtspr	SPRN_SPRG_SCRATCH0,r10
 	mtspr	SPRN_SPRG_SCRATCH1,r11
+#ifdef CONFIG_VMAP_STACK
+	mfspr	r10, SPRN_SPRG_THREAD
+	.if	\handle_dar_dsisr
+	mfspr	r11, SPRN_DAR
+	stw	r11, DAR(r10)
+	mfspr	r11, SPRN_DSISR
+	stw	r11, DSISR(r10)
+	.endif
+	mfspr	r11, SPRN_SRR0
+	stw	r11, SRR0(r10)
+#endif
+	mfspr	r11, SPRN_SRR1		/* check whether user or kernel */
+#ifdef CONFIG_VMAP_STACK
+	stw	r11, SRR1(r10)
+#endif
 	mfcr	r10
-	EXCEPTION_PROLOG_1
-	EXCEPTION_PROLOG_2
+	andi.	r11, r11, MSR_PR
 .endm
 
-.macro EXCEPTION_PROLOG_1
-	mfspr	r11,SPRN_SRR1		/* check whether user or kernel */
-	andi.	r11,r11,MSR_PR
+.macro EXCEPTION_PROLOG_1 for_rtas=0
+#ifdef CONFIG_VMAP_STACK
+	.ifeq	\for_rtas
+	li	r11, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
+	mtmsr	r11
+	isync
+	.endif
+	subi	r11, r1, INT_FRAME_SIZE		/* use r1 if kernel */
+#else
 	tophys(r11,r1)			/* use tophys(r1) if kernel */
+	subi	r11, r11, INT_FRAME_SIZE	/* alloc exc. frame */
+#endif
 	beq	1f
 	mfspr	r11,SPRN_SPRG_THREAD
+	tovirt_vmstack r11, r11
 	lwz	r11,TASK_STACK-THREAD(r11)
-	addi	r11,r11,THREAD_SIZE
-	tophys(r11,r11)
-1:	subi	r11,r11,INT_FRAME_SIZE	/* alloc exc. frame */
+	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
+	tophys_novmstack r11, r11
+1:
+#ifdef CONFIG_VMAP_STACK
+	mtcrf	0x7f, r11
+	bt	32 - THREAD_ALIGN_SHIFT, stack_overflow
+#endif
 .endm
 
-.macro EXCEPTION_PROLOG_2
+.macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0
 	stw	r10,_CCR(r11)		/* save registers */
 	stw	r12,GPR12(r11)
 	stw	r9,GPR9(r11)
@@ -41,16 +73,33 @@
 	stw	r12,GPR11(r11)
 	mflr	r10
 	stw	r10,_LINK(r11)
+#ifdef CONFIG_VMAP_STACK
+	mfspr	r12, SPRN_SPRG_THREAD
+	tovirt(r12, r12)
+	.if	\handle_dar_dsisr
+	lwz	r10, DAR(r12)
+	stw	r10, _DAR(r11)
+	lwz	r10, DSISR(r12)
+	stw	r10, _DSISR(r11)
+	.endif
+	lwz	r9, SRR1(r12)
+	lwz	r12, SRR0(r12)
+#else
 	mfspr	r12,SPRN_SRR0
 	mfspr	r9,SPRN_SRR1
+#endif
 	stw	r1,GPR1(r11)
 	stw	r1,0(r11)
-	tovirt(r1,r11)			/* set new kernel sp */
+	tovirt_novmstack r1, r11	/* set new kernel sp */
 #ifdef CONFIG_40x
 	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?) */
 #else
+#ifdef CONFIG_VMAP_STACK
+	li	r10, MSR_KERNEL & ~MSR_IR /* can take exceptions */
+#else
 	li	r10,MSR_KERNEL & ~(MSR_IR|MSR_DR) /* can take exceptions */
-	MTMSRD(r10)			/* (except for mach check in rtas) */
+#endif
+	mtmsr	r10			/* (except for mach check in rtas) */
 #endif
 	stw	r0,GPR0(r11)
 	lis	r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
@@ -62,25 +111,46 @@
 
 .macro SYSCALL_ENTRY trapno
 	mfspr	r12,SPRN_SPRG_THREAD
+#ifdef CONFIG_VMAP_STACK
+	mfspr	r9, SPRN_SRR0
+	mfspr	r11, SPRN_SRR1
+	stw	r9, SRR0(r12)
+	stw	r11, SRR1(r12)
+#endif
 	mfcr	r10
 	lwz	r11,TASK_STACK-THREAD(r12)
-	mflr	r9
-	addi	r11,r11,THREAD_SIZE - INT_FRAME_SIZE
 	rlwinm	r10,r10,0,4,2	/* Clear SO bit in CR */
-	tophys(r11,r11)
+	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
+#ifdef CONFIG_VMAP_STACK
+	li	r9, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */
+	mtmsr	r9
+	isync
+#endif
+	tovirt_vmstack r12, r12
+	tophys_novmstack r11, r11
+	mflr	r9
 	stw	r10,_CCR(r11)		/* save registers */
+	stw	r9, _LINK(r11)
+#ifdef CONFIG_VMAP_STACK
+	lwz	r10, SRR0(r12)
+	lwz	r9, SRR1(r12)
+#else
 	mfspr	r10,SPRN_SRR0
-	stw	r9,_LINK(r11)
 	mfspr	r9,SPRN_SRR1
+#endif
 	stw	r1,GPR1(r11)
 	stw	r1,0(r11)
-	tovirt(r1,r11)			/* set new kernel sp */
+	tovirt_novmstack r1, r11	/* set new kernel sp */
 	stw	r10,_NIP(r11)
 #ifdef CONFIG_40x
 	rlwinm	r9,r9,0,14,12		/* clear MSR_WE (necessary?) */
 #else
+#ifdef CONFIG_VMAP_STACK
+	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~MSR_IR) /* can take exceptions */
+#else
 	LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~(MSR_IR|MSR_DR)) /* can take exceptions */
-	MTMSRD(r10)			/* (except for mach check in rtas) */
+#endif
+	mtmsr	r10			/* (except for mach check in rtas) */
 #endif
 	lis	r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
 	stw	r2,GPR2(r11)
@@ -118,7 +188,7 @@
 #endif
 
 3:
-	tovirt(r2, r2)			/* set r2 to current */
+	tovirt_novmstack r2, r2 	/* set r2 to current */
 	lis	r11, transfer_to_syscall@h
 	ori	r11, r11, transfer_to_syscall@l
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -141,6 +211,54 @@
 	RFI				/* jump to handler, enable MMU */
 .endm
 
+.macro save_dar_dsisr_on_stack reg1, reg2, sp
+#ifndef CONFIG_VMAP_STACK
+	mfspr	\reg1, SPRN_DAR
+	mfspr	\reg2, SPRN_DSISR
+	stw	\reg1, _DAR(\sp)
+	stw	\reg2, _DSISR(\sp)
+#endif
+.endm
+
+.macro get_and_save_dar_dsisr_on_stack reg1, reg2, sp
+#ifdef CONFIG_VMAP_STACK
+	lwz	\reg1, _DAR(\sp)
+	lwz	\reg2, _DSISR(\sp)
+#else
+	save_dar_dsisr_on_stack \reg1, \reg2, \sp
+#endif
+.endm
+
+.macro tovirt_vmstack dst, src
+#ifdef CONFIG_VMAP_STACK
+	tovirt(\dst, \src)
+#else
+	.ifnc	\dst, \src
+	mr	\dst, \src
+	.endif
+#endif
+.endm
+
+.macro tovirt_novmstack dst, src
+#ifndef CONFIG_VMAP_STACK
+	tovirt(\dst, \src)
+#else
+	.ifnc	\dst, \src
+	mr	\dst, \src
+	.endif
+#endif
+.endm
+
+.macro tophys_novmstack dst, src
+#ifndef CONFIG_VMAP_STACK
+	tophys(\dst, \src)
+#else
+	.ifnc	\dst, \src
+	mr	\dst, \src
+	.endif
+#endif
+.endm
+
 /*
  * Note: code which follows this uses cr0.eq (set if from kernel),
  * r11, r12 (SRR0), and r9 (SRR1).
@@ -187,4 +305,28 @@ label:
 	EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, transfer_to_handler, \
 			  ret_from_except)
 
+.macro vmap_stack_overflow_exception
+#ifdef CONFIG_VMAP_STACK
+#ifdef CONFIG_SMP
+	mfspr	r11, SPRN_SPRG_THREAD
+	tovirt(r11, r11)
+	lwz	r11, TASK_CPU - THREAD(r11)
+	slwi	r11, r11, 3
+	addis	r11, r11, emergency_ctx@ha
+#else
+	lis	r11, emergency_ctx@ha
+#endif
+	lwz	r11, emergency_ctx@l(r11)
+	cmpwi	cr1, r11, 0
+	bne	cr1, 1f
+	lis	r11, init_thread_union@ha
+	addi	r11, r11, init_thread_union@l
+1:	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
+	EXCEPTION_PROLOG_2
+	SAVE_NVGPRS(r11)
+	addi	r3, r1, STACK_FRAME_OVERHEAD
+	EXC_XFER_STD(0, stack_overflow_exception)
+#endif
+.endm
+
 #endif /* __HEAD_32_H__ */
diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S
index 585ea1976550..9bb663977e84 100644
--- a/arch/powerpc/kernel/head_40x.S
+++ b/arch/powerpc/kernel/head_40x.S
@@ -313,6 +313,7 @@ _ENTRY(saved_ksp_limit)
 	START_EXCEPTION(0x0400, InstructionAccess)
 	EXCEPTION_PROLOG
 	mr	r4,r12			/* Pass SRR0 as arg2 */
+	stw	r4, _DEAR(r11)
 	li	r5,0			/* Pass zero as arg3 */
 	EXC_XFER_LITE(0x400, handle_page_fault)
 
@@ -676,6 +677,7 @@ DataAccess:
 	mfspr	r5,SPRN_ESR		/* Grab the ESR, save it, pass arg3 */
 	stw	r5,_ESR(r11)
 	mfspr	r4,SPRN_DEAR		/* Grab the DEAR, save it, pass arg2 */
+	stw	r4, _DEAR(r11)
 	EXC_XFER_LITE(0x300, handle_page_fault)
 
 /* Other PowerPC processors, namely those derived from the 6xx-series
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 19f583e18402..9922306ae512 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -127,56 +127,36 @@ instruction_counter:
 /* Machine check */
 	. = 0x200
 MachineCheck:
-	EXCEPTION_PROLOG
-	mfspr r4,SPRN_DAR
-	stw r4,_DAR(r11)
-	li r5,RPN_PATTERN
-	mtspr SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
-	mfspr r5,SPRN_DSISR
-	stw r5,_DSISR(r11)
+	EXCEPTION_PROLOG handle_dar_dsisr=1
+	save_dar_dsisr_on_stack r4, r5, r11
+	li	r6, RPN_PATTERN
+	mtspr	SPRN_DAR, r6	/* Tag DAR, to be used in DTLB Error */
 	addi r3,r1,STACK_FRAME_OVERHEAD
 	EXC_XFER_STD(0x200, machine_check_exception)
 
-/* Data access exception.
- * This is "never generated" by the MPC8xx.
- */
-	. = 0x300
-DataAccess:
-
-/* Instruction access exception.
- * This is "never generated" by the MPC8xx.
- */
-	. = 0x400
-InstructionAccess:
-
 /* External interrupt */
 	EXCEPTION(0x500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE)
 
 /* Alignment exception */
 	. = 0x600
 Alignment:
-	EXCEPTION_PROLOG
-	mfspr	r4,SPRN_DAR
-	stw	r4,_DAR(r11)
-	li	r5,RPN_PATTERN
-	mtspr	SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
-	mfspr	r5,SPRN_DSISR
-	stw	r5,_DSISR(r11)
+	EXCEPTION_PROLOG handle_dar_dsisr=1
+	save_dar_dsisr_on_stack r4, r5, r11
+	li	r6, RPN_PATTERN
+	mtspr	SPRN_DAR, r6	/* Tag DAR, to be used in DTLB Error */
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_STD(0x600, alignment_exception)
+	b	.Lalignment_exception_ool
 
 /* Program check exception */
 	EXCEPTION(0x700, ProgramCheck, program_check_exception, EXC_XFER_STD)
 
-/* No FPU on MPC8xx.  This exception is not supposed to happen.
-*/
-	EXCEPTION(0x800, FPUnavailable, unknown_exception, EXC_XFER_STD)
-
 /* Decrementer */
 	EXCEPTION(0x900, Decrementer, timer_interrupt, EXC_XFER_LITE)
 
-	EXCEPTION(0xa00, Trap_0a, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0xb00, Trap_0b, unknown_exception, EXC_XFER_STD)
+	/* With VMAP_STACK there's not enough room for this at 0x600 */
+	. = 0xa00
+.Lalignment_exception_ool:
+	EXC_XFER_STD(0x600, alignment_exception)
 
 /* System call */
 	. = 0xc00
@@ -185,25 +165,12 @@ SystemCall:
 
 /* Single step - not used on 601 */
 	EXCEPTION(0xd00, SingleStep, single_step_exception, EXC_XFER_STD)
-	EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0xf00, Trap_0f, unknown_exception, EXC_XFER_STD)
 
 /* On the MPC8xx, this is a software emulation interrupt.  It occurs
  * for all unimplemented and illegal instructions.
  */
 	EXCEPTION(0x1000, SoftEmu, program_check_exception, EXC_XFER_STD)
 
-/* Called from DataStoreTLBMiss when perf TLB misses events are activated */
-#ifdef CONFIG_PERF_EVENTS
-	patch_site	0f, patch__dtlbmiss_perf
-0:	lwz	r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
-	addi	r10, r10, 1
-	stw	r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
-	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
-	rfi
-#endif
-
 	. = 0x1100
 /*
  * For the MPC8xx, this is a software tablewalk to load the instruction
@@ -343,8 +310,8 @@ ITLBMissLinear:
 
 	. = 0x1200
 DataStoreTLBMiss:
-	mtspr	SPRN_SPRG_SCRATCH0, r10
-	mtspr	SPRN_SPRG_SCRATCH1, r11
+	mtspr	SPRN_DAR, r10
+	mtspr	SPRN_M_TW, r11
 	mfcr	r11
 
 	/* If we are faulting a kernel address, we have to use the
@@ -409,10 +376,10 @@ DataStoreTLBMiss:
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
 
 	/* Restore registers */
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
 
-0:	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
+0:	mfspr	r10, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r11, SPRN_M_TW
 	rfi
 	patch_site	0b, patch__dtlbmiss_exit_1
 
@@ -428,10 +395,10 @@ DTLBMissIMMR:
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
 
 	li	r11, RPN_PATTERN
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
 
-0:	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
+0:	mfspr	r10, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r11, SPRN_M_TW
 	rfi
 	patch_site	0b, patch__dtlbmiss_exit_2
 
@@ -465,10 +432,10 @@ DTLBMissLinear:
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
 
 	li	r11, RPN_PATTERN
-	mtspr	SPRN_DAR, r11	/* Tag DAR */
 
-0:	mfspr	r10, SPRN_SPRG_SCRATCH0
-	mfspr	r11, SPRN_SPRG_SCRATCH1
+0:	mfspr	r10, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r11, SPRN_M_TW
 	rfi
 	patch_site	0b, patch__dtlbmiss_exit_3
 
@@ -486,6 +453,7 @@ InstructionTLBError:
 	tlbie	r4
 	/* 0x400 is InstructionAccess exception, needed by bad_page_fault() */
 .Litlbie:
+	stw	r4, _DAR(r11)
 	EXC_XFER_LITE(0x400, handle_page_fault)
 
 /* This is the data TLB error on the MPC8xx.  This could be due to
@@ -494,58 +462,69 @@ InstructionTLBError:
  */
 	. = 0x1400
 DataTLBError:
-	mtspr	SPRN_SPRG_SCRATCH0, r10
-	mtspr	SPRN_SPRG_SCRATCH1, r11
-	mfcr	r10
-
+	EXCEPTION_PROLOG_0 handle_dar_dsisr=1
 	mfspr	r11, SPRN_DAR
-	cmpwi	cr0, r11, RPN_PATTERN
-	beq-	FixupDAR	/* must be a buggy dcbX, icbi insn. */
+	cmpwi	cr1, r11, RPN_PATTERN
+	beq-	cr1, FixupDAR	/* must be a buggy dcbX, icbi insn. */
 DARFixed:/* Return from dcbx instruction bug workaround */
+#ifdef CONFIG_VMAP_STACK
+	li	r11, RPN_PATTERN
+	mtspr	SPRN_DAR, r11	/* Tag DAR, to be used in DTLB Error */
+#endif
 	EXCEPTION_PROLOG_1
-	EXCEPTION_PROLOG_2
-	mfspr	r5,SPRN_DSISR
-	stw	r5,_DSISR(r11)
-	mfspr	r4,SPRN_DAR
+	EXCEPTION_PROLOG_2 handle_dar_dsisr=1
+	get_and_save_dar_dsisr_on_stack r4, r5, r11
 	andis.	r10,r5,DSISR_NOHPTE@h
 	beq+	.Ldtlbie
 	tlbie	r4
 .Ldtlbie:
+#ifndef CONFIG_VMAP_STACK
 	li	r10,RPN_PATTERN
 	mtspr	SPRN_DAR,r10	/* Tag DAR, to be used in DTLB Error */
+#endif
 	/* 0x300 is DataAccess exception, needed by bad_page_fault() */
 	EXC_XFER_LITE(0x300, handle_page_fault)
 
-	EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1a00, Trap_1a, unknown_exception, EXC_XFER_STD)
-	EXCEPTION(0x1b00, Trap_1b, unknown_exception, EXC_XFER_STD)
+/* Called from DataStoreTLBMiss when perf TLB misses events are activated */
+#ifdef CONFIG_PERF_EVENTS
+	patch_site	0f, patch__dtlbmiss_perf
+0:	lwz	r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+	addi	r10, r10, 1
+	stw	r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+	mfspr	r10, SPRN_DAR
+	mtspr	SPRN_DAR, r11	/* Tag DAR */
+	mfspr	r11, SPRN_M_TW
+	rfi
+#endif
+
+stack_overflow:
+	vmap_stack_overflow_exception
 
 /* On the MPC8xx, these next four traps are used for development
  * support of breakpoints and such.  Someday I will get around to
  * using them.
  */
-	. = 0x1c00
-DataBreakpoint:
-	mtspr	SPRN_SPRG_SCRATCH0, r10
-	mtspr	SPRN_SPRG_SCRATCH1, r11
-	mfcr	r10
-	mfspr	r11, SPRN_SRR0
-	cmplwi	cr0, r11, (.Ldtlbie - PAGE_OFFSET)@l
-	cmplwi	cr7, r11, (.Litlbie - PAGE_OFFSET)@l
-	beq-	cr0, 11f
-	beq-	cr7, 11f
+do_databreakpoint:
 	EXCEPTION_PROLOG_1
-	EXCEPTION_PROLOG_2
+	EXCEPTION_PROLOG_2 handle_dar_dsisr=1
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	mfspr	r4,SPRN_BAR
 	stw	r4,_DAR(r11)
+#ifdef CONFIG_VMAP_STACK
+	lwz	r5,_DSISR(r11)
+#else
 	mfspr	r5,SPRN_DSISR
+#endif
 	EXC_XFER_STD(0x1c00, do_break)
-11:
+
+	. = 0x1c00
+DataBreakpoint:
+	EXCEPTION_PROLOG_0 handle_dar_dsisr=1
+	mfspr	r11, SPRN_SRR0
+	cmplwi	cr1, r11, (.Ldtlbie - PAGE_OFFSET)@l
+	cmplwi	cr7, r11, (.Litlbie - PAGE_OFFSET)@l
+	cror	4*cr1+eq, 4*cr1+eq, 4*cr7+eq
+	bne	cr1, do_databreakpoint
 	mtcr	r10
 	mfspr	r10, SPRN_SPRG_SCRATCH0
 	mfspr	r11, SPRN_SPRG_SCRATCH1
@@ -581,9 +560,9 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	mfspr	r10, SPRN_SRR0
 	mtspr	SPRN_MD_EPN, r10
 	rlwinm	r11, r10, 16, 0xfff8
-	cmpli	cr0, r11, PAGE_OFFSET@h
+	cmpli	cr1, r11, PAGE_OFFSET@h
 	mfspr	r11, SPRN_M_TWB	/* Get level 1 table */
-	blt+	3f
+	blt+	cr1, 3f
 	rlwinm	r11, r10, 16, 0xfff8
 
 0:	cmpli	cr7, r11, (PAGE_OFFSET + 0x1800000)@h
@@ -598,7 +577,7 @@ FixupDAR:/* Entry point for dcbx workaround. */
 3:
 	lwz	r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11)	/* Get the level 1 entry */
 	mtspr	SPRN_MD_TWC, r11
-	mtcr	r11
+	mtcrf	0x01, r11
 	mfspr	r11, SPRN_MD_TWC
 	lwz	r11, 0(r11)	/* Get the pte */
 	bt	28,200f		/* bit 28 = Large page (8M) */
@@ -611,16 +590,16 @@ FixupDAR:/* Entry point for dcbx workaround. */
  * no need to include them here */
 	xoris	r10, r11, 0x7c00	/* check if major OP code is 31 */
 	rlwinm	r10, r10, 0, 21, 5
-	cmpwi	cr0, r10, 2028	/* Is dcbz? */
-	beq+	142f
-	cmpwi	cr0, r10, 940	/* Is dcbi? */
-	beq+	142f
-	cmpwi	cr0, r10, 108	/* Is dcbst? */
-	beq+	144f		/* Fix up store bit! */
-	cmpwi	cr0, r10, 172	/* Is dcbf? */
-	beq+	142f
-	cmpwi	cr0, r10, 1964	/* Is icbi? */
-	beq+	142f
+	cmpwi	cr1, r10, 2028	/* Is dcbz? */
+	beq+	cr1, 142f
+	cmpwi	cr1, r10, 940	/* Is dcbi? */
+	beq+	cr1, 142f
+	cmpwi	cr1, r10, 108	/* Is dcbst? */
+	beq+	cr1, 144f		/* Fix up store bit! */
+	cmpwi	cr1, r10, 172	/* Is dcbf? */
+	beq+	cr1, 142f
+	cmpwi	cr1, r10, 1964	/* Is icbi? */
+	beq+	cr1, 142f
 141:	mfspr	r10,SPRN_M_TW
 	b	DARFixed	/* Nope, go back to normal TLB processing */
 
@@ -679,8 +658,9 @@ FixupDAR:/* Entry point for dcbx workaround. */
 	add	r10, r10, r30	;b	151f
 	add	r10, r10, r31
 151:
-	rlwinm. r11,r11,19,24,28	/* offset into jump table for reg RA */
-	beq	152f			/* if reg RA is zero, don't add it */
+	rlwinm	r11,r11,19,24,28	/* offset into jump table for reg RA */
+	cmpwi	cr1, r11, 0
+	beq	cr1, 152f		/* if reg RA is zero, don't add it */
 	addi	r11, r11, 150b@l	/* add start of table */
 	mtctr	r11			/* load ctr with jump address */
 	rlwinm	r11,r11,0,16,10		/* make sure we don't execute this more than once */
@@ -688,7 +668,14 @@ FixupDAR:/* Entry point for dcbx workaround. */
 152:
 	mfdar	r11
 	mtctr	r11			/* restore ctr reg from DAR */
+#ifdef CONFIG_VMAP_STACK
+	mfspr	r11, SPRN_SPRG_THREAD
+	stw	r10, DAR(r11)
+	mfspr	r10, SPRN_DSISR
+	stw	r10, DSISR(r11)
+#else
 	mtdar	r10			/* save fault EA to DAR */
+#endif
 	mfspr	r10,SPRN_M_TW
 	b	DARFixed		/* Go back to normal TLB handling */
 
diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h
index 2ae635df9026..37fc84ed90e3 100644
--- a/arch/powerpc/kernel/head_booke.h
+++ b/arch/powerpc/kernel/head_booke.h
@@ -467,6 +467,7 @@ label:
 	mfspr	r5,SPRN_ESR;		/* Grab the ESR and save it */	      \
 	stw	r5,_ESR(r11);						      \
 	mfspr	r4,SPRN_DEAR;		/* Grab the DEAR */		      \
+	stw	r4, _DEAR(r11);						      \
 	EXC_XFER_LITE(0x0300, handle_page_fault)
 
 #define INSTRUCTION_STORAGE_EXCEPTION					      \
@@ -475,6 +476,7 @@ label:
 	mfspr	r5,SPRN_ESR;		/* Grab the ESR and save it */	      \
 	stw	r5,_ESR(r11);						      \
 	mr      r4,r12;                 /* Pass SRR0 as arg2 */		      \
+	stw	r4, _DEAR(r11);						      \
 	li      r5,0;                   /* Pass zero as arg3 */		      \
 	EXC_XFER_LITE(0x0400, handle_page_fault)
 
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 6f7a3a7162c5..840af004041e 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -378,6 +378,7 @@ interrupt_base:
 	mfspr	r4,SPRN_DEAR		/* Grab the DEAR, save it, pass arg2 */
 	andis.	r10,r5,(ESR_ILK|ESR_DLK)@h
 	bne	1f
+	stw	r4, _DEAR(r11)
 	EXC_XFER_LITE(0x0300, handle_page_fault)
 1:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 58ce3d37c2a3..2462cd7c565c 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -160,6 +160,9 @@ static int hw_breakpoint_validate_len(struct arch_hw_breakpoint *hw)
 		/* DAWR region can't cross 512 bytes boundary */
 		if ((start_addr >> 9) != (end_addr >> 9))
 			return -EINVAL;
+	} else if (IS_ENABLED(CONFIG_PPC_8xx)) {
+		/* 8xx can setup a range without limitation */
+		max_len = U16_MAX;
 	}
 
 	if (hw_len > max_len)
@@ -328,13 +331,11 @@ int hw_breakpoint_handler(struct die_args *args)
 	}
 
 	info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
-	if (IS_ENABLED(CONFIG_PPC_8xx)) {
-		if (!dar_within_range(regs->dar, info))
-			info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
-	} else {
-		if (!stepping_handler(regs, bp, info))
-			goto out;
-	}
+	if (!dar_within_range(regs->dar, info))
+		info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
+
+	if (!IS_ENABLED(CONFIG_PPC_8xx) && !stepping_handler(regs, bp, info))
+		goto out;
 
 	/*
 	 * As a policy, the callback is invoked in a 'trigger-after-execute'
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index a36fd053c3db..422e31d2f5a2 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -77,6 +77,31 @@ void arch_cpu_idle(void)
 
 int powersave_nap;
 
+#ifdef CONFIG_PPC_970_NAP
+void power4_idle(void)
+{
+	if (!cpu_has_feature(CPU_FTR_CAN_NAP))
+		return;
+
+	if (!powersave_nap)
+		return;
+
+	if (!prep_irq_for_idle())
+		return;
+
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		asm volatile("DSSALL ; sync" ::: "memory");
+
+	power4_idle_nap();
+
+	/*
+	 * power4_idle_nap returns with interrupts enabled (soft and hard).
+	 * to our caller with interrupts enabled (soft and hard). Our caller
+	 * can cope with either interrupts disabled or enabled upon return.
+	 */
+}
+#endif
+
 #ifdef CONFIG_SYSCTL
 /*
  * Register the sysctl to set/clear powersave_nap.
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index d32751994a62..22f249b6f58d 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -15,7 +15,9 @@
 #include <asm/asm-offsets.h>
 #include <asm/ppc-opcode.h>
 #include <asm/cpuidle.h>
+#include <asm/thread_info.h> /* TLF_NAPPING */
 
+#ifdef CONFIG_PPC_P7_NAP
 /*
  * Desired PSSCR in r3
  *
@@ -181,4 +183,22 @@ _GLOBAL(isa206_idle_insn_mayloss)
 	bne	2f
 	IDLE_STATE_ENTER_SEQ_NORET(PPC_SLEEP)
 2:	IDLE_STATE_ENTER_SEQ_NORET(PPC_WINKLE)
+#endif
 
+#ifdef CONFIG_PPC_970_NAP
+_GLOBAL(power4_idle_nap)
+	LOAD_REG_IMMEDIATE(r7, MSR_KERNEL|MSR_EE|MSR_POW)
+	ld	r9,PACA_THREAD_INFO(r13)
+	ld	r8,TI_LOCAL_FLAGS(r9)
+	ori	r8,r8,_TLF_NAPPING
+	std	r8,TI_LOCAL_FLAGS(r9)
+	/*
+	 * NAPPING bit is set, from this point onward power4_fixup_nap
+	 * will cause exceptions to return to power4_idle_nap_return.
+	 */
+1:	sync
+	isync
+	mtmsrd	r7
+	isync
+	b	1b
+#endif
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
deleted file mode 100644
index 33c625329078..000000000000
--- a/arch/powerpc/kernel/idle_power4.S
+++ /dev/null
@@ -1,83 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  This file contains the power_save function for 970-family CPUs.
- */
-
-#include <linux/threads.h>
-#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/cputable.h>
-#include <asm/thread_info.h>
-#include <asm/ppc_asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/irqflags.h>
-#include <asm/hw_irq.h>
-#include <asm/feature-fixups.h>
-
-#undef DEBUG
-
-	.text
-
-_GLOBAL(power4_idle)
-BEGIN_FTR_SECTION
-	blr
-END_FTR_SECTION_IFCLR(CPU_FTR_CAN_NAP)
-	/* Now check if user or arch enabled NAP mode */
-	LOAD_REG_ADDRBASE(r3,powersave_nap)
-	lwz	r4,ADDROFF(powersave_nap)(r3)
-	cmpwi	0,r4,0
-	beqlr
-
-	/* This sequence is similar to prep_irq_for_idle() */
-
-	/* Hard disable interrupts */
-	mfmsr	r7
-	rldicl	r0,r7,48,1
-	rotldi	r0,r0,16
-	mtmsrd	r0,1
-
-	/* Check if something happened while soft-disabled */
-	lbz	r0,PACAIRQHAPPENED(r13)
-	cmpwi	cr0,r0,0
-	bne-	2f
-
-	/*
-	 * Soft-enable interrupts. This will make power4_fixup_nap return
-	 * to our caller with interrupts enabled (soft and hard). The caller
-	 * can cope with either interrupts disabled or enabled upon return.
-	 */
-#ifdef CONFIG_TRACE_IRQFLAGS
-	/* Tell the tracer interrupts are on, because idle responds to them. */
-	mflr	r0
-	std	r0,16(r1)
-	stdu    r1,-128(r1)
-	bl	trace_hardirqs_on
-	addi    r1,r1,128
-	ld	r0,16(r1)
-	mtlr	r0
-	mfmsr	r7
-#endif /* CONFIG_TRACE_IRQFLAGS */
-
-	li	r0,IRQS_ENABLED
-	stb	r0,PACAIRQSOFTMASK(r13)	/* we'll hard-enable shortly */
-BEGIN_FTR_SECTION
-	DSSALL
-	sync
-END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
-	ld	r9, PACA_THREAD_INFO(r13)
-	ld	r8,TI_LOCAL_FLAGS(r9)	/* set napping bit */
-	ori	r8,r8,_TLF_NAPPING	/* so when we take an exception */
-	std	r8,TI_LOCAL_FLAGS(r9)	/* it will return to our caller */
-	ori	r7,r7,MSR_EE
-	oris	r7,r7,MSR_POW@h
-1:	sync
-	isync
-	mtmsrd	r7
-	isync
-	b	1b
-
-2:	/* Return if an interrupt had happened while soft disabled */
-	/* Set the HARD_DIS flag because interrupts are now hard disabled */
-	ori	r0,r0,PACA_IRQ_HARD_DIS
-	stb	r0,PACAIRQHAPPENED(r13)
-	blr
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index add67498c126..5c9b11878555 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -50,6 +50,7 @@
 #include <linux/debugfs.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
+#include <linux/vmalloc.h>
 
 #include <linux/uaccess.h>
 #include <asm/io.h>
@@ -664,8 +665,29 @@ void do_IRQ(struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
+static void *__init alloc_vm_stack(void)
+{
+	return __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START,
+				    VMALLOC_END, THREADINFO_GFP, PAGE_KERNEL,
+				     0, NUMA_NO_NODE, (void*)_RET_IP_);
+}
+
+static void __init vmap_irqstack_init(void)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		softirq_ctx[i] = alloc_vm_stack();
+		hardirq_ctx[i] = alloc_vm_stack();
+	}
+}
+
+
 void __init init_IRQ(void)
 {
+	if (IS_ENABLED(CONFIG_VMAP_STACK))
+		vmap_irqstack_init();
+
 	if (ppc_md.init_IRQ)
 		ppc_md.init_IRQ();
 }
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 1c448cf25506..c6c03416a151 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -261,12 +261,6 @@ int pcibios_sriov_disable(struct pci_dev *pdev)
 
 #endif /* CONFIG_PCI_IOV */
 
-void pcibios_bus_add_device(struct pci_dev *pdev)
-{
-	if (ppc_md.pcibios_bus_add_device)
-		ppc_md.pcibios_bus_add_device(pdev);
-}
-
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
 {
 #ifdef CONFIG_PPC64
@@ -964,7 +958,7 @@ void pcibios_setup_bus_self(struct pci_bus *bus)
 		phb->controller_ops.dma_bus_setup(bus);
 }
 
-static void pcibios_setup_device(struct pci_dev *dev)
+void pcibios_bus_add_device(struct pci_dev *dev)
 {
 	struct pci_controller *phb;
 	/* Fixup NUMA node as it may not be setup yet by the generic
@@ -985,17 +979,13 @@ static void pcibios_setup_device(struct pci_dev *dev)
 	pci_read_irq_line(dev);
 	if (ppc_md.pci_irq_fixup)
 		ppc_md.pci_irq_fixup(dev);
+
+	if (ppc_md.pcibios_bus_add_device)
+		ppc_md.pcibios_bus_add_device(dev);
 }
 
 int pcibios_add_device(struct pci_dev *dev)
 {
-	/*
-	 * We can only call pcibios_setup_device() after bus setup is complete,
-	 * since some of the platform specific DMA setup code depends on it.
-	 */
-	if (dev->bus->is_added)
-		pcibios_setup_device(dev);
-
 #ifdef CONFIG_PCI_IOV
 	if (ppc_md.pcibios_fixup_sriov)
 		ppc_md.pcibios_fixup_sriov(dev);
@@ -1004,24 +994,6 @@ int pcibios_add_device(struct pci_dev *dev)
 	return 0;
 }
 
-void pcibios_setup_bus_devices(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	pr_debug("PCI: Fixup bus devices %d (%s)\n",
-		 bus->number, bus->self ? pci_name(bus->self) : "PHB");
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		/* Cardbus can call us to add new devices to a bus, so ignore
-		 * those who are already fully discovered
-		 */
-		if (pci_dev_is_added(dev))
-			continue;
-
-		pcibios_setup_device(dev);
-	}
-}
-
 void pcibios_set_master(struct pci_dev *dev)
 {
 	/* No special bus mastering setup handling */
@@ -1037,19 +1009,9 @@ void pcibios_fixup_bus(struct pci_bus *bus)
 
 	/* Now fixup the bus bus */
 	pcibios_setup_bus_self(bus);
-
-	/* Now fixup devices on that bus */
-	pcibios_setup_bus_devices(bus);
 }
 EXPORT_SYMBOL(pcibios_fixup_bus);
 
-void pci_fixup_cardbus(struct pci_bus *bus)
-{
-	/* Now fixup devices on that bus */
-	pcibios_setup_bus_devices(bus);
-}
-
-
 static int skip_isa_ioresource_align(struct pci_dev *dev)
 {
 	if (pci_has_flag(PCI_CAN_SKIP_ISA_ALIGN) &&
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index fc62c4bc47b1..d6a67f814983 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -134,7 +134,6 @@ void pci_hp_add_devices(struct pci_bus *bus)
 		 */
 		slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
 		pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
-		pcibios_setup_bus_devices(bus);
 		max = bus->busn_res.start;
 		/*
 		 * Scan bridges that are already configured. We don't touch
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 9524009ca1ae..4e654df55969 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -125,7 +125,7 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
 }
 
 #ifdef CONFIG_PCI_IOV
-static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
+static struct pci_dn *add_one_sriov_vf_pdn(struct pci_dn *parent,
 					   int vf_index,
 					   int busno, int devfn)
 {
@@ -151,17 +151,15 @@ static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
 
 	return pdn;
 }
-#endif
 
-struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
+struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev)
 {
-#ifdef CONFIG_PCI_IOV
 	struct pci_dn *parent, *pdn;
 	int i;
 
 	/* Only support IOV for now */
-	if (!pdev->is_physfn)
-		return pci_get_pdn(pdev);
+	if (WARN_ON(!pdev->is_physfn))
+		return NULL;
 
 	/* Check if VFs have been populated */
 	pdn = pci_get_pdn(pdev);
@@ -176,7 +174,7 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
 	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
 		struct eeh_dev *edev __maybe_unused;
 
-		pdn = add_one_dev_pci_data(parent, i,
+		pdn = add_one_sriov_vf_pdn(parent, i,
 					   pci_iov_virtfn_bus(pdev, i),
 					   pci_iov_virtfn_devfn(pdev, i));
 		if (!pdn) {
@@ -192,31 +190,17 @@ struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
 		edev->physfn = pdev;
 #endif /* CONFIG_EEH */
 	}
-#endif /* CONFIG_PCI_IOV */
-
 	return pci_get_pdn(pdev);
 }
 
-void remove_dev_pci_data(struct pci_dev *pdev)
+void remove_sriov_vf_pdns(struct pci_dev *pdev)
 {
-#ifdef CONFIG_PCI_IOV
 	struct pci_dn *parent;
 	struct pci_dn *pdn, *tmp;
 	int i;
 
-	/*
-	 * VF and VF PE are created/released dynamically, so we need to
-	 * bind/unbind them.  Otherwise the VF and VF PE would be mismatched
-	 * when re-enabling SR-IOV.
-	 */
-	if (pdev->is_virtfn) {
-		pdn = pci_get_pdn(pdev);
-		pdn->pe_number = IODA_INVALID_PE;
-		return;
-	}
-
 	/* Only support IOV PF for now */
-	if (!pdev->is_physfn)
+	if (WARN_ON(!pdev->is_physfn))
 		return;
 
 	/* Check if VFs have been populated */
@@ -244,9 +228,22 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 				continue;
 
 #ifdef CONFIG_EEH
-			/* Release EEH device for the VF */
+			/*
+			 * Release EEH state for this VF. The PCI core
+			 * has already torn down the pci_dev for this VF, but
+			 * we're responsible to removing the eeh_dev since it
+			 * has the same lifetime as the pci_dn that spawned it.
+			 */
 			edev = pdn_to_eeh_dev(pdn);
 			if (edev) {
+				/*
+				 * We allocate pci_dn's for the totalvfs count,
+				 * but only only the vfs that were activated
+				 * have a configured PE.
+				 */
+				if (edev->pe)
+					eeh_rmv_from_parent_pe(edev);
+
 				pdn->edev = NULL;
 				kfree(edev);
 			}
@@ -258,8 +255,8 @@ void remove_dev_pci_data(struct pci_dev *pdev)
 			kfree(pdn);
 		}
 	}
-#endif /* CONFIG_PCI_IOV */
 }
+#endif /* CONFIG_PCI_IOV */
 
 struct pci_dn *pci_add_device_node_info(struct pci_controller *hose,
 					struct device_node *dn)
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index f91d7e94872e..c3024f104765 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -414,7 +414,6 @@ static void __of_scan_bus(struct device_node *node, struct pci_bus *bus,
 	 */
 	if (!rescan_existing)
 		pcibios_setup_bus_self(bus);
-	pcibios_setup_bus_devices(bus);
 
 	/* Now scan child busses */
 	for_each_pci_bridge(dev, bus)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 4df94b6e2f32..fad50db9dcf2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -740,28 +740,6 @@ static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
 		mtspr(SPRN_DABRX, dabrx);
 	return 0;
 }
-#elif defined(CONFIG_PPC_8xx)
-static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
-{
-	unsigned long addr = dabr & ~HW_BRK_TYPE_DABR;
-	unsigned long lctrl1 = 0x90000000; /* compare type: equal on E & F */
-	unsigned long lctrl2 = 0x8e000002; /* watchpoint 1 on cmp E | F */
-
-	if ((dabr & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_READ)
-		lctrl1 |= 0xa0000;
-	else if ((dabr & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_WRITE)
-		lctrl1 |= 0xf0000;
-	else if ((dabr & HW_BRK_TYPE_RDWR) == 0)
-		lctrl2 = 0;
-
-	mtspr(SPRN_LCTRL2, 0);
-	mtspr(SPRN_CMPE, addr);
-	mtspr(SPRN_CMPF, addr + 4);
-	mtspr(SPRN_LCTRL1, lctrl1);
-	mtspr(SPRN_LCTRL2, lctrl2);
-
-	return 0;
-}
 #else
 static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
 {
@@ -782,6 +760,39 @@ static inline int set_dabr(struct arch_hw_breakpoint *brk)
 	return __set_dabr(dabr, dabrx);
 }
 
+static inline int set_breakpoint_8xx(struct arch_hw_breakpoint *brk)
+{
+	unsigned long lctrl1 = LCTRL1_CTE_GT | LCTRL1_CTF_LT | LCTRL1_CRWE_RW |
+			       LCTRL1_CRWF_RW;
+	unsigned long lctrl2 = LCTRL2_LW0EN | LCTRL2_LW0LADC | LCTRL2_SLW0EN;
+	unsigned long start_addr = brk->address & ~HW_BREAKPOINT_ALIGN;
+	unsigned long end_addr = (brk->address + brk->len - 1) | HW_BREAKPOINT_ALIGN;
+
+	if (start_addr == 0)
+		lctrl2 |= LCTRL2_LW0LA_F;
+	else if (end_addr == ~0U)
+		lctrl2 |= LCTRL2_LW0LA_E;
+	else
+		lctrl2 |= LCTRL2_LW0LA_EandF;
+
+	mtspr(SPRN_LCTRL2, 0);
+
+	if ((brk->type & HW_BRK_TYPE_RDWR) == 0)
+		return 0;
+
+	if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_READ)
+		lctrl1 |= LCTRL1_CRWE_RO | LCTRL1_CRWF_RO;
+	if ((brk->type & HW_BRK_TYPE_RDWR) == HW_BRK_TYPE_WRITE)
+		lctrl1 |= LCTRL1_CRWE_WO | LCTRL1_CRWF_WO;
+
+	mtspr(SPRN_CMPE, start_addr - 1);
+	mtspr(SPRN_CMPF, end_addr + 1);
+	mtspr(SPRN_LCTRL1, lctrl1);
+	mtspr(SPRN_LCTRL2, lctrl2);
+
+	return 0;
+}
+
 void __set_breakpoint(struct arch_hw_breakpoint *brk)
 {
 	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
@@ -789,6 +800,8 @@ void __set_breakpoint(struct arch_hw_breakpoint *brk)
 	if (dawr_enabled())
 		// Power8 or later
 		set_dawr(brk);
+	else if (IS_ENABLED(CONFIG_PPC_8xx))
+		set_breakpoint_8xx(brk);
 	else if (!cpu_has_feature(CPU_FTR_ARCH_207S))
 		// Power7 or earlier
 		set_dabr(brk);
@@ -1264,16 +1277,6 @@ void show_user_instructions(struct pt_regs *regs)
 
 	pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int));
 
-	/*
-	 * Make sure the NIP points at userspace, not kernel text/data or
-	 * elsewhere.
-	 */
-	if (!__access_ok(pc, NR_INSN_TO_PRINT * sizeof(int), USER_DS)) {
-		pr_info("%s[%d]: Bad NIP, not dumping instructions.\n",
-			current->comm, current->pid);
-		return;
-	}
-
 	seq_buf_init(&s, buf, sizeof(buf));
 
 	while (n) {
@@ -1284,7 +1287,7 @@ void show_user_instructions(struct pt_regs *regs)
 		for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) {
 			int instr;
 
-			if (probe_kernel_address((const void *)pc, instr)) {
+			if (probe_user_read(&instr, (void __user *)pc, sizeof(instr))) {
 				seq_buf_printf(&s, "XXXXXXXX ");
 				continue;
 			}
diff --git a/arch/powerpc/kernel/setup.h b/arch/powerpc/kernel/setup.h
index c82577c4b15d..2dd0d9cb5a20 100644
--- a/arch/powerpc/kernel/setup.h
+++ b/arch/powerpc/kernel/setup.h
@@ -35,7 +35,7 @@ void exc_lvl_early_init(void);
 static inline void exc_lvl_early_init(void) { };
 #endif
 
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) || defined(CONFIG_VMAP_STACK)
 void emergency_stack_init(void);
 #else
 static inline void emergency_stack_init(void) { };
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index dcffe927f5b9..5b49b26eb154 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -140,7 +140,7 @@ arch_initcall(ppc_init);
 
 static void *__init alloc_stack(void)
 {
-	void *ptr = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
+	void *ptr = memblock_alloc(THREAD_SIZE, THREAD_ALIGN);
 
 	if (!ptr)
 		panic("cannot allocate %d bytes for stack at %pS\n",
@@ -153,6 +153,9 @@ void __init irqstack_early_init(void)
 {
 	unsigned int i;
 
+	if (IS_ENABLED(CONFIG_VMAP_STACK))
+		return;
+
 	/* interrupt stacks must be in lowmem, we get that for free on ppc32
 	 * as the memblock is limited to lowmem by default */
 	for_each_possible_cpu(i) {
@@ -161,6 +164,18 @@ void __init irqstack_early_init(void)
 	}
 }
 
+#ifdef CONFIG_VMAP_STACK
+void *emergency_ctx[NR_CPUS] __ro_after_init;
+
+void __init emergency_stack_init(void)
+{
+	unsigned int i;
+
+	for_each_possible_cpu(i)
+		emergency_ctx[i] = alloc_stack();
+}
+#endif
+
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
 void __init exc_lvl_early_init(void)
 {
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 6104917a282d..e05e6dd67ae6 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -633,7 +633,7 @@ static void *__init alloc_stack(unsigned long limit, int cpu)
 
 	BUILD_BUG_ON(STACK_INT_FRAME_SIZE % 16);
 
-	ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_SIZE,
+	ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_ALIGN,
 				     MEMBLOCK_LOW_LIMIT, limit,
 				     early_cpu_to_node(cpu));
 	if (!ptr)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 014ff0701f24..82a3438300fd 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1637,6 +1637,15 @@ void StackOverflow(struct pt_regs *regs)
 	panic("kernel stack overflow");
 }
 
+void stack_overflow_exception(struct pt_regs *regs)
+{
+	enum ctx_state prev_state = exception_enter();
+
+	die("Kernel stack overflow", regs, SIGSEGV);
+
+	exception_exit(prev_state);
+}
+
 void kernel_fp_unavailable_exception(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index eae9ddaecbcf..b9a108411c0d 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -728,11 +728,6 @@ static int __init vdso_init(void)
 	 */
 	vdso64_pages = (&vdso64_end - &vdso64_start) >> PAGE_SHIFT;
 	DBG("vdso64_kbase: %p, 0x%x pages\n", vdso64_kbase, vdso64_pages);
-#else
-	vdso_data->dcache_block_size = L1_CACHE_BYTES;
-	vdso_data->dcache_log_block_size = L1_CACHE_SHIFT;
-	vdso_data->icache_block_size = L1_CACHE_BYTES;
-	vdso_data->icache_log_block_size = L1_CACHE_SHIFT;
 #endif /* CONFIG_PPC64 */
 
 
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index 06f54d947057..e147bbdc12cd 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -2,9 +2,7 @@
 
 # List of files in the vdso, has to be asm only for now
 
-obj-vdso32-$(CONFIG_PPC64) = getcpu.o
-obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o \
-		$(obj-vdso32-y)
+obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o
 
 # Build rules
 
diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso32/cacheflush.S
index 7f882e7b9f43..3440ddf21c8b 100644
--- a/arch/powerpc/kernel/vdso32/cacheflush.S
+++ b/arch/powerpc/kernel/vdso32/cacheflush.S
@@ -8,7 +8,9 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
 #include <asm/asm-offsets.h>
+#include <asm/cache.h>
 
 	.text
 
@@ -22,42 +24,62 @@
  */
 V_FUNCTION_BEGIN(__kernel_sync_dicache)
   .cfi_startproc
+#ifdef CONFIG_PPC64
 	mflr	r12
   .cfi_register lr,r12
-	mr	r11,r3
-	bl	__get_datapage@local
+	get_datapage	r10, r0
 	mtlr	r12
-	mr	r10,r3
+#endif
 
+#ifdef CONFIG_PPC64
 	lwz	r7,CFG_DCACHE_BLOCKSZ(r10)
 	addi	r5,r7,-1
-	andc	r6,r11,r5		/* round low to line bdy */
+#else
+	li	r5, L1_CACHE_BYTES - 1
+#endif
+	andc	r6,r3,r5		/* round low to line bdy */
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5		/* ensure we get enough */
+#ifdef CONFIG_PPC64
 	lwz	r9,CFG_DCACHE_LOGBLOCKSZ(r10)
 	srw.	r8,r8,r9		/* compute line count */
+#else
+	srwi.	r8, r8, L1_CACHE_SHIFT
+	mr	r7, r6
+#endif
 	crclr	cr0*4+so
 	beqlr				/* nothing to do? */
 	mtctr	r8
 1:	dcbst	0,r6
+#ifdef CONFIG_PPC64
 	add	r6,r6,r7
+#else
+	addi	r6, r6, L1_CACHE_BYTES
+#endif
 	bdnz	1b
 	sync
 
 /* Now invalidate the instruction cache */
 
+#ifdef CONFIG_PPC64
 	lwz	r7,CFG_ICACHE_BLOCKSZ(r10)
 	addi	r5,r7,-1
-	andc	r6,r11,r5		/* round low to line bdy */
+	andc	r6,r3,r5		/* round low to line bdy */
 	subf	r8,r6,r4		/* compute length */
 	add	r8,r8,r5
 	lwz	r9,CFG_ICACHE_LOGBLOCKSZ(r10)
 	srw.	r8,r8,r9		/* compute line count */
 	crclr	cr0*4+so
 	beqlr				/* nothing to do? */
+#endif
 	mtctr	r8
+#ifdef CONFIG_PPC64
 2:	icbi	0,r6
 	add	r6,r6,r7
+#else
+2:	icbi	0, r7
+	addi	r7, r7, L1_CACHE_BYTES
+#endif
 	bdnz	2b
 	isync
 	li	r3,0
diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S
index 6c7401bd284e..217bb630f8f9 100644
--- a/arch/powerpc/kernel/vdso32/datapage.S
+++ b/arch/powerpc/kernel/vdso32/datapage.S
@@ -10,35 +10,13 @@
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 #include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
 
 	.text
 	.global	__kernel_datapage_offset;
 __kernel_datapage_offset:
 	.long	0
 
-V_FUNCTION_BEGIN(__get_datapage)
-  .cfi_startproc
-	/* We don't want that exposed or overridable as we want other objects
-	 * to be able to bl directly to here
-	 */
-	.protected __get_datapage
-	.hidden __get_datapage
-
-	mflr	r0
-  .cfi_register lr,r0
-
-	bcl	20,31,data_page_branch
-data_page_branch:
-	mflr	r3
-	mtlr	r0
-	addi	r3, r3, __kernel_datapage_offset-data_page_branch
-	lwz	r0,0(r3)
-  .cfi_restore lr
-	add	r3,r0,r3
-	blr
-  .cfi_endproc
-V_FUNCTION_END(__get_datapage)
-
 /*
  * void *__kernel_get_syscall_map(unsigned int *syscall_count) ;
  *
@@ -52,11 +30,10 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map)
   .cfi_startproc
 	mflr	r12
   .cfi_register lr,r12
-	mr	r4,r3
-	bl	__get_datapage@local
+	mr.	r4,r3
+	get_datapage	r3, r0
 	mtlr	r12
 	addi	r3,r3,CFG_SYSCALL_MAP32
-	cmpli	cr0,r4,0
 	beqlr
 	li	r0,NR_syscalls
 	stw	r0,0(r4)
@@ -75,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq)
   .cfi_startproc
 	mflr	r12
   .cfi_register lr,r12
-	bl	__get_datapage@local
+	get_datapage	r3, r0
 	lwz	r4,(CFG_TB_TICKS_PER_SEC + 4)(r3)
 	lwz	r3,CFG_TB_TICKS_PER_SEC(r3)
 	mtlr	r12
diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso32/getcpu.S
index 63e914539e1a..ff5e214fec41 100644
--- a/arch/powerpc/kernel/vdso32/getcpu.S
+++ b/arch/powerpc/kernel/vdso32/getcpu.S
@@ -15,6 +15,7 @@
  * int __kernel_getcpu(unsigned *cpu, unsigned *node);
  *
  */
+#if defined(CONFIG_PPC64)
 V_FUNCTION_BEGIN(__kernel_getcpu)
   .cfi_startproc
 	mfspr	r5,SPRN_SPRG_VDSO_READ
@@ -24,10 +25,26 @@ V_FUNCTION_BEGIN(__kernel_getcpu)
 	rlwinm  r7,r5,16,31-15,31-0
 	beq	cr0,1f
 	stw	r6,0(r3)
-1:	beq	cr1,2f
-	stw	r7,0(r4)
-2:	crclr	cr0*4+so
+1:	crclr	cr0*4+so
 	li	r3,0			/* always success */
+	beqlr	cr1
+	stw	r7,0(r4)
+	blr
+  .cfi_endproc
+V_FUNCTION_END(__kernel_getcpu)
+#elif !defined(CONFIG_SMP)
+V_FUNCTION_BEGIN(__kernel_getcpu)
+  .cfi_startproc
+	cmpwi	cr0, r3, 0
+	cmpwi	cr1, r4, 0
+	li	r5, 0
+	beq	cr0, 1f
+	stw	r5, 0(r3)
+1:	li	r3, 0			/* always success */
+	crclr	cr0*4+so
+	beqlr	cr1
+	stw	r5, 0(r4)
 	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_getcpu)
+#endif
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 3306672f57a9..a3951567118a 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -9,6 +9,7 @@
 #include <asm/processor.h>
 #include <asm/ppc_asm.h>
 #include <asm/vdso.h>
+#include <asm/vdso_datapage.h>
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 
@@ -31,28 +32,26 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday)
 	mflr	r12
   .cfi_register lr,r12
 
-	mr	r10,r3			/* r10 saves tv */
+	mr.	r10,r3			/* r10 saves tv */
 	mr	r11,r4			/* r11 saves tz */
-	bl	__get_datapage@local	/* get data page */
-	mr	r9, r3			/* datapage ptr in r9 */
-	cmplwi	r10,0			/* check if tv is NULL */
+	get_datapage	r9, r0
 	beq	3f
-	lis	r7,1000000@ha		/* load up USEC_PER_SEC */
-	addi	r7,r7,1000000@l		/* so we get microseconds in r4 */
+	LOAD_REG_IMMEDIATE(r7, 1000000)	/* load up USEC_PER_SEC */
 	bl	__do_get_tspec@local	/* get sec/usec from tb & kernel */
 	stw	r3,TVAL32_TV_SEC(r10)
 	stw	r4,TVAL32_TV_USEC(r10)
 
 3:	cmplwi	r11,0			/* check if tz is NULL */
-	beq	1f
+	mtlr	r12
+	crclr	cr0*4+so
+	li	r3,0
+	beqlr
+
 	lwz	r4,CFG_TZ_MINUTEWEST(r9)/* fill tz */
 	lwz	r5,CFG_TZ_DSTTIME(r9)
 	stw	r4,TZONE_TZ_MINWEST(r11)
 	stw	r5,TZONE_TZ_DSTTIME(r11)
 
-1:	mtlr	r12
-	crclr	cr0*4+so
-	li	r3,0
 	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_gettimeofday)
@@ -69,17 +68,23 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	cmpli	cr0,r3,CLOCK_REALTIME
 	cmpli	cr1,r3,CLOCK_MONOTONIC
 	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
-	bne	cr0,99f
+
+	cmpli	cr5,r3,CLOCK_REALTIME_COARSE
+	cmpli	cr6,r3,CLOCK_MONOTONIC_COARSE
+	cror	cr5*4+eq,cr5*4+eq,cr6*4+eq
+
+	cror	cr0*4+eq,cr0*4+eq,cr5*4+eq
+	bne	cr0, .Lgettime_fallback
 
 	mflr	r12			/* r12 saves lr */
   .cfi_register lr,r12
 	mr	r11,r4			/* r11 saves tp */
-	bl	__get_datapage@local	/* get data page */
-	mr	r9,r3			/* datapage ptr in r9 */
-	lis	r7,NSEC_PER_SEC@h	/* want nanoseconds */
-	ori	r7,r7,NSEC_PER_SEC@l
-50:	bl	__do_get_tspec@local	/* get sec/nsec from tb & kernel */
-	bne	cr1,80f			/* not monotonic -> all done */
+	get_datapage	r9, r0
+	LOAD_REG_IMMEDIATE(r7, NSEC_PER_SEC)	/* load up NSEC_PER_SEC */
+	beq	cr5, .Lcoarse_clocks
+.Lprecise_clocks:
+	bl	__do_get_tspec@local	/* get sec/nsec from tb & kernel */
+	bne	cr1, .Lfinish		/* not monotonic -> all done */
 
 	/*
 	 * CLOCK_MONOTONIC
@@ -103,12 +108,53 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	add	r9,r9,r0
 	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
         cmpl    cr0,r8,r0		/* check if updated */
-	bne-	50b
+	bne-	.Lprecise_clocks
+	b	.Lfinish_monotonic
+
+	/*
+	 * For coarse clocks we get data directly from the vdso data page, so
+	 * we don't need to call __do_get_tspec, but we still need to do the
+	 * counter trick.
+	 */
+.Lcoarse_clocks:
+	lwz	r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+	andi.	r0,r8,1                 /* pending update ? loop */
+	bne-	.Lcoarse_clocks
+	add	r9,r9,r0		/* r0 is already 0 */
+
+	/*
+	 * CLOCK_REALTIME_COARSE, below values are needed for MONOTONIC_COARSE
+	 * too
+	 */
+	lwz	r3,STAMP_XTIME_SEC+LOPART(r9)
+	lwz	r4,STAMP_XTIME_NSEC+LOPART(r9)
+	bne	cr6,1f
+
+	/* CLOCK_MONOTONIC_COARSE */
+	lwz	r5,(WTOM_CLOCK_SEC+LOPART)(r9)
+	lwz	r6,WTOM_CLOCK_NSEC(r9)
+
+	/* check if counter has updated */
+	or	r0,r6,r5
+1:	or	r0,r0,r3
+	or	r0,r0,r4
+	xor	r0,r0,r0
+	add	r3,r3,r0
+	lwz	r0,CFG_TB_UPDATE_COUNT+LOPART(r9)
+	cmpl	cr0,r0,r8               /* check if updated */
+	bne-	.Lcoarse_clocks
+
+	/* Counter has not updated, so continue calculating proper values for
+	 * sec and nsec if monotonic coarse, or just return with the proper
+	 * values for realtime.
+	 */
+	bne	cr6, .Lfinish
 
 	/* Calculate and store result. Note that this mimics the C code,
 	 * which may cause funny results if nsec goes negative... is that
 	 * possible at all ?
 	 */
+.Lfinish_monotonic:
 	add	r3,r3,r5
 	add	r4,r4,r6
 	cmpw	cr0,r4,r7
@@ -116,11 +162,12 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	blt	1f
 	subf	r4,r7,r4
 	addi	r3,r3,1
-1:	bge	cr1,80f
+1:	bge	cr1, .Lfinish
 	addi	r3,r3,-1
 	add	r4,r4,r7
 
-80:	stw	r3,TSPC32_TV_SEC(r11)
+.Lfinish:
+	stw	r3,TSPC32_TV_SEC(r11)
 	stw	r4,TSPC32_TV_NSEC(r11)
 
 	mtlr	r12
@@ -131,7 +178,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	/*
 	 * syscall fallback
 	 */
-99:
+.Lgettime_fallback:
 	li	r0,__NR_clock_gettime
   .cfi_restore lr
 	sc
@@ -149,17 +196,20 @@ V_FUNCTION_END(__kernel_clock_gettime)
 V_FUNCTION_BEGIN(__kernel_clock_getres)
   .cfi_startproc
 	/* Check for supported clock IDs */
-	cmpwi	cr0,r3,CLOCK_REALTIME
-	cmpwi	cr1,r3,CLOCK_MONOTONIC
-	cror	cr0*4+eq,cr0*4+eq,cr1*4+eq
-	bne	cr0,99f
+	cmplwi	cr0, r3, CLOCK_MAX
+	cmpwi	cr1, r3, CLOCK_REALTIME_COARSE
+	cmpwi	cr7, r3, CLOCK_MONOTONIC_COARSE
+	bgt	cr0, 99f
+	LOAD_REG_IMMEDIATE(r5, KTIME_LOW_RES)
+	beq	cr1, 1f
+	beq	cr7, 1f
 
 	mflr	r12
   .cfi_register lr,r12
-	bl	__get_datapage@local	/* get data page */
+	get_datapage	r3, r0
 	lwz	r5, CLOCK_HRTIMER_RES(r3)
 	mtlr	r12
-	li	r3,0
+1:	li	r3,0
 	cmpli	cr0,r4,0
 	crclr	cr0*4+so
 	beqlr
@@ -168,11 +218,11 @@ V_FUNCTION_BEGIN(__kernel_clock_getres)
 	blr
 
 	/*
-	 * syscall fallback
+	 * invalid clock
 	 */
 99:
-	li	r0,__NR_clock_getres
-	sc
+	li	r3, EINVAL
+	crset	so
 	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_clock_getres)
@@ -190,16 +240,15 @@ V_FUNCTION_BEGIN(__kernel_time)
   .cfi_register lr,r12
 
 	mr	r11,r3			/* r11 holds t */
-	bl	__get_datapage@local
-	mr	r9, r3			/* datapage ptr in r9 */
+	get_datapage	r9, r0
 
 	lwz	r3,STAMP_XTIME_SEC+LOPART(r9)
 
 	cmplwi	r11,0			/* check if t is NULL */
-	beq	2f
-	stw	r3,0(r11)		/* store result at *t */
-2:	mtlr	r12
+	mtlr	r12
 	crclr	cr0*4+so
+	beqlr
+	stw	r3,0(r11)		/* store result at *t */
 	blr
   .cfi_endproc
 V_FUNCTION_END(__kernel_time)
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index 00c025ba4a92..5206c2eb2a1d 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -155,7 +155,7 @@ VERSION
 		__kernel_sync_dicache_p5;
 		__kernel_sigtramp32;
 		__kernel_sigtramp_rt32;
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) || !defined(CONFIG_SMP)
 		__kernel_getcpu;
 #endif
 
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 8eb867dbad5f..25c14a0981bf 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -67,6 +67,9 @@ _GLOBAL(load_up_altivec)
 #ifdef CONFIG_PPC32
 	mfspr	r5,SPRN_SPRG_THREAD		/* current task's THREAD (phys) */
 	oris	r9,r9,MSR_VEC@h
+#ifdef CONFIG_VMAP_STACK
+	tovirt(r5, r5)
+#endif
 #else
 	ld	r4,PACACURRENT(r13)
 	addi	r5,r4,THREAD		/* Get THREAD */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 8834220036a5..b4c89a1acebb 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -323,7 +323,7 @@ SECTIONS
 #endif
 
 	/* The initial task and kernel stack */
-	INIT_TASK_DATA_SECTION(THREAD_SIZE)
+	INIT_TASK_DATA_SECTION(THREAD_ALIGN)
 
 	.data..page_aligned : AT(ADDR(.data..page_aligned) - LOAD_OFFSET) {
 		PAGE_ALIGNED_DATA(PAGE_SIZE)