Merge branch 'topic/of-graph' of git://git.pengutronix.de/git/pza/linux into imx-drm-staging

Merge the of-graph dependency for imx-drm.  These will be the basis of
the new DT bindings for imx-drm.

44 files changed, 598 insertions, 470 deletions

diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 1d8248e..bd18bb8 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -878,7 +878,8 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
 				    unsigned long cmd,
 				    void *v)
 {
-	if (cmd == CPU_PM_EXIT) {
+	if (cmd == CPU_PM_EXIT &&
+	    __hyp_get_vectors() == hyp_default_vectors) {
 		cpu_init_hyp_mode(NULL);
 		return NOTIFY_OK;
 	}
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index ddc1553..0d68d40 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -220,6 +220,10 @@ after_vfp_restore:
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
  * passed in r0 and r1.
  *
+ * A function pointer with a value of 0xffffffff has a special meaning,
+ * and is used to implement __hyp_get_vectors in the same way as in
+ * arch/arm/kernel/hyp_stub.S.
+ *
  * The calling convention follows the standard AAPCS:
  *   r0 - r3: caller save
  *   r12:     caller save
@@ -363,6 +367,11 @@ hyp_hvc:
 host_switch_to_hyp:
 	pop	{r0, r1, r2}
 
+	/* Check for __hyp_get_vectors */
+	cmp	r0, #-1
+	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
+	beq	1f
+
 	push	{lr}
 	mrs	lr, SPSR
 	push	{lr}
@@ -378,7 +387,7 @@ THUMB(	orr	lr, #1)
 	pop	{lr}
 	msr	SPSR_csxf, lr
 	pop	{lr}
-	eret
+1:	eret
 
 guest_trap:
 	load_vcpu			@ Load VCPU pointer to r0
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 13fb0b3..453a179 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
+#ifdef CONFIG_SMP
+
 static inline void set_my_cpu_offset(unsigned long off)
 {
 	asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
@@ -36,6 +38,12 @@ static inline unsigned long __my_cpu_offset(void)
 }
 #define __my_cpu_offset __my_cpu_offset()
 
+#else	/* !CONFIG_SMP */
+
+#define set_my_cpu_offset(x)	do { } while (0)
+
+#endif /* CONFIG_SMP */
+
 #include <asm-generic/percpu.h>
 
 #endif /* __ASM_PERCPU_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b524dcd..aa3917c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -136,11 +136,11 @@ extern struct page *empty_zero_page;
 /*
  * The following only work if pte_present(). Undefined behaviour otherwise.
  */
-#define pte_present(pte)	(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))
-#define pte_dirty(pte)		(pte_val(pte) & PTE_DIRTY)
-#define pte_young(pte)		(pte_val(pte) & PTE_AF)
-#define pte_special(pte)	(pte_val(pte) & PTE_SPECIAL)
-#define pte_write(pte)		(pte_val(pte) & PTE_WRITE)
+#define pte_present(pte)	(!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)))
+#define pte_dirty(pte)		(!!(pte_val(pte) & PTE_DIRTY))
+#define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
+#define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
+#define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 
 #define pte_valid_user(pte) \
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index c3b6c63..38f0558 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -48,7 +48,11 @@ int unwind_frame(struct stackframe *frame)
 
 	frame->sp = fp + 0x10;
 	frame->fp = *(unsigned long *)(fp);
-	frame->pc = *(unsigned long *)(fp + 8);
+	/*
+	 * -4 here because we care about the PC at time of bl,
+	 * not where the return will go.
+	 */
+	frame->pc = *(unsigned long *)(fp + 8) - 4;
 
 	return 0;
 }
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 3b47c36..2c56012 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -694,6 +694,24 @@ __hyp_panic_str:
 
 	.align	2
 
+/*
+ * u64 kvm_call_hyp(void *hypfn, ...);
+ *
+ * This is not really a variadic function in the classic C-way and care must
+ * be taken when calling this to ensure parameters are passed in registers
+ * only, since the stack will change between the caller and the callee.
+ *
+ * Call the function with the first argument containing a pointer to the
+ * function you wish to call in Hyp mode, and subsequent arguments will be
+ * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the
+ * function pointer can be passed).  The function being called must be mapped
+ * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
+ * passed in r0 and r1.
+ *
+ * A function pointer with a value of 0 has a special meaning, and is
+ * used to implement __hyp_get_vectors in the same way as in
+ * arch/arm64/kernel/hyp_stub.S.
+ */
 ENTRY(kvm_call_hyp)
 	hvc	#0
 	ret
@@ -737,7 +755,12 @@ el1_sync:					// Guest trapped into EL2
 	pop	x2, x3
 	pop	x0, x1
 
-	push	lr, xzr
+	/* Check for __hyp_get_vectors */
+	cbnz	x0, 1f
+	mrs	x0, vbar_el2
+	b	2f
+
+1:	push	lr, xzr
 
 	/*
 	 * Compute the function address in EL2, and shuffle the parameters.
@@ -750,7 +773,7 @@ el1_sync:					// Guest trapped into EL2
 	blr	lr
 
 	pop	lr, xzr
-	eret
+2:	eret
 
 el1_trap:
 	/*
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 7cc8c36..6fb9e81 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,4 +1,4 @@
-
+generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
 generic-y += cputime.h
@@ -6,6 +6,7 @@ generic-y += device.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
@@ -18,6 +19,7 @@ generic-y += local.h
 generic-y += mman.h
 generic-y += mutex.h
 generic-y += percpu.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sections.h
@@ -31,5 +33,3 @@ generic-y += trace_clock.h
 generic-y += types.h
 generic-y += word-at-a-time.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/m68k/include/asm/barrier.h b/arch/m68k/include/asm/barrier.h
deleted file mode 100644
index 15c5f77..0000000
--- a/arch/m68k/include/asm/barrier.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _M68K_BARRIER_H
-#define _M68K_BARRIER_H
-
-#define nop()		do { asm volatile ("nop"); barrier(); } while (0)
-
-#include <asm-generic/barrier.h>
-
-#endif /* _M68K_BARRIER_H */
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 014f288..9d38b73 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		349
+#define NR_syscalls		351
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 625f321..b932dd4 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -354,5 +354,7 @@
 #define __NR_process_vm_writev	346
 #define __NR_kcmp		347
 #define __NR_finit_module	348
+#define __NR_sched_setattr	349
+#define __NR_sched_getattr	350
 
 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 3f04ea0..b6223dc4 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -369,4 +369,6 @@ ENTRY(sys_call_table)
 	.long sys_process_vm_writev
 	.long sys_kcmp
 	.long sys_finit_module
+	.long sys_sched_setattr
+	.long sys_sched_getattr		/* 350 */
 
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 84fdf68..a613d2c 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -200,10 +200,11 @@ static inline void __user *arch_compat_alloc_user_space(long len)
 
 	/*
 	 * We can't access below the stack pointer in the 32bit ABI and
-	 * can access 288 bytes in the 64bit ABI
+	 * can access 288 bytes in the 64bit big-endian ABI,
+	 * or 512 bytes with the new ELFv2 little-endian ABI.
 	 */
 	if (!is_32bit_task())
-		usp -= 288;
+		usp -= USER_REDZONE_SIZE;
 
 	return (void __user *) (usp - len);
 }
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 40157e2..ed82142 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -816,8 +816,8 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
 int64_t opal_pci_poll(uint64_t phb_id);
 int64_t opal_return_cpu(void);
 
-int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val);
-int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
+int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val);
+int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val);
 
 int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
 		       uint32_t addr, uint32_t data, uint32_t sz);
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index becc08e..279b80f 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -28,11 +28,23 @@
 
 #ifdef __powerpc64__
 
+/*
+ * Size of redzone that userspace is allowed to use below the stack
+ * pointer.  This is 288 in the 64-bit big-endian ELF ABI, and 512 in
+ * the new ELFv2 little-endian ABI, so we allow the larger amount.
+ *
+ * For kernel code we allow a 288-byte redzone, in order to conserve
+ * kernel stack space; gcc currently only uses 288 bytes, and will
+ * hopefully allow explicit control of the redzone size in future.
+ */
+#define USER_REDZONE_SIZE	512
+#define KERNEL_REDZONE_SIZE	288
+
 #define STACK_FRAME_OVERHEAD	112	/* size of minimum stack frame */
 #define STACK_FRAME_LR_SAVE	2	/* Location of LR in stack frame */
 #define STACK_FRAME_REGS_MARKER	ASM_CONST(0x7265677368657265)
 #define STACK_INT_FRAME_SIZE	(sizeof(struct pt_regs) + \
-					STACK_FRAME_OVERHEAD + 288)
+				 STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE)
 #define STACK_FRAME_MARKER	12
 
 /* Size of dummy stack frame allocated when calling signal handler. */
@@ -41,6 +53,8 @@
 
 #else /* __powerpc64__ */
 
+#define USER_REDZONE_SIZE	0
+#define KERNEL_REDZONE_SIZE	0
 #define STACK_FRAME_OVERHEAD	16	/* size of minimum stack frame */
 #define STACK_FRAME_LR_SAVE	1	/* Location of LR in stack frame */
 #define STACK_FRAME_REGS_MARKER	ASM_CONST(0x72656773)
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 11c1d06..7a13f37 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -98,17 +98,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 			size_t csize, unsigned long offset, int userbuf)
 {
 	void  *vaddr;
+	phys_addr_t paddr;
 
 	if (!csize)
 		return 0;
 
 	csize = min_t(size_t, csize, PAGE_SIZE);
+	paddr = pfn << PAGE_SHIFT;
 
-	if ((min_low_pfn < pfn) && (pfn < max_pfn)) {
-		vaddr = __va(pfn << PAGE_SHIFT);
+	if (memblock_is_region_memory(paddr, csize)) {
+		vaddr = __va(paddr);
 		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
 	} else {
-		vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0);
+		vaddr = __ioremap(paddr, PAGE_SIZE, 0);
 		csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
 		iounmap(vaddr);
 	}
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 9b27b29..b0ded97 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -74,6 +74,7 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
  */
 static int test_24bit_addr(unsigned long ip, unsigned long addr)
 {
+	addr = ppc_function_entry((void *)addr);
 
 	/* use the create_branch to verify that this offset can be branched */
 	return create_branch((unsigned int *)ip, addr, 0);
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index e35bf77..8d253c2 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -65,8 +65,8 @@ struct rt_sigframe {
 	struct siginfo __user *pinfo;
 	void __user *puc;
 	struct siginfo info;
-	/* 64 bit ABI allows for 288 bytes below sp before decrementing it. */
-	char abigap[288];
+	/* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */
+	char abigap[USER_REDZONE_SIZE];
 } __attribute__ ((aligned (16)));
 
 static const char fmt32[] = KERN_INFO \
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index f514743..253fefe 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -114,6 +114,7 @@ DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get,
 			ioda_eeh_inbB_dbgfs_set, "0x%llx\n");
 #endif /* CONFIG_DEBUG_FS */
 
+
 /**
  * ioda_eeh_post_init - Chip dependent post initialization
  * @hose: PCI controller
@@ -221,6 +222,22 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
 	return ret;
 }
 
+static void ioda_eeh_phb_diag(struct pci_controller *hose)
+{
+	struct pnv_phb *phb = hose->private_data;
+	long rc;
+
+	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+					 PNV_PCI_DIAG_BUF_SIZE);
+	if (rc != OPAL_SUCCESS) {
+		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
+			    __func__, hose->global_number, rc);
+		return;
+	}
+
+	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
+}
+
 /**
  * ioda_eeh_get_state - Retrieve the state of PE
  * @pe: EEH PE
@@ -272,6 +289,9 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
 			result |= EEH_STATE_DMA_ACTIVE;
 			result |= EEH_STATE_MMIO_ENABLED;
 			result |= EEH_STATE_DMA_ENABLED;
+		} else if (!(pe->state & EEH_PE_ISOLATED)) {
+			eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+			ioda_eeh_phb_diag(hose);
 		}
 
 		return result;
@@ -315,6 +335,15 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
 			   __func__, fstate, hose->global_number, pe_no);
 	}
 
+	/* Dump PHB diag-data for frozen PE */
+	if (result != EEH_STATE_NOT_SUPPORT &&
+	    (result & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) !=
+	    (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) &&
+	    !(pe->state & EEH_PE_ISOLATED)) {
+		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+		ioda_eeh_phb_diag(hose);
+	}
+
 	return result;
 }
 
@@ -530,42 +559,6 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 }
 
 /**
- * ioda_eeh_get_log - Retrieve error log
- * @pe: EEH PE
- * @severity: Severity level of the log
- * @drv_log: buffer to store the log
- * @len: space of the log buffer
- *
- * The function is used to retrieve error log from P7IOC.
- */
-static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
-			    char *drv_log, unsigned long len)
-{
-	s64 ret;
-	unsigned long flags;
-	struct pci_controller *hose = pe->phb;
-	struct pnv_phb *phb = hose->private_data;
-
-	spin_lock_irqsave(&phb->lock, flags);
-
-	ret = opal_pci_get_phb_diag_data2(phb->opal_id,
-			phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
-	if (ret) {
-		spin_unlock_irqrestore(&phb->lock, flags);
-		pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n",
-			   __func__, hose->global_number, pe->addr, ret);
-		return -EIO;
-	}
-
-	/* The PHB diag-data is always indicative */
-	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-
-	spin_unlock_irqrestore(&phb->lock, flags);
-
-	return 0;
-}
-
-/**
  * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
  * @pe: EEH PE
  *
@@ -646,22 +639,6 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose)
 	}
 }
 
-static void ioda_eeh_phb_diag(struct pci_controller *hose)
-{
-	struct pnv_phb *phb = hose->private_data;
-	long rc;
-
-	rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
-					 PNV_PCI_DIAG_BUF_SIZE);
-	if (rc != OPAL_SUCCESS) {
-		pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
-			    __func__, hose->global_number, rc);
-		return;
-	}
-
-	pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-}
-
 static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
 			       struct eeh_pe **pe)
 {
@@ -835,6 +812,20 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 		}
 
 		/*
+		 * EEH core will try recover from fenced PHB or
+		 * frozen PE. In the time for frozen PE, EEH core
+		 * enable IO path for that before collecting logs,
+		 * but it ruins the site. So we have to dump the
+		 * log in advance here.
+		 */
+		if ((ret == EEH_NEXT_ERR_FROZEN_PE  ||
+		    ret == EEH_NEXT_ERR_FENCED_PHB) &&
+		    !((*pe)->state & EEH_PE_ISOLATED)) {
+			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+			ioda_eeh_phb_diag(hose);
+		}
+
+		/*
 		 * If we have no errors on the specific PHB or only
 		 * informative error there, we continue poking it.
 		 * Otherwise, we need actions to be taken by upper
@@ -852,7 +843,6 @@ struct pnv_eeh_ops ioda_eeh_ops = {
 	.set_option		= ioda_eeh_set_option,
 	.get_state		= ioda_eeh_get_state,
 	.reset			= ioda_eeh_reset,
-	.get_log		= ioda_eeh_get_log,
 	.configure_bridge	= ioda_eeh_configure_bridge,
 	.next_error		= ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 4fbf276..4cd2ea6 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -71,11 +71,11 @@ static int opal_xscom_err_xlate(int64_t rc)
 	}
 }
 
-static u64 opal_scom_unmangle(u64 reg)
+static u64 opal_scom_unmangle(u64 addr)
 {
 	/*
 	 * XSCOM indirect addresses have the top bit set. Additionally
-	 * the reset of the top 3 nibbles is always 0.
+	 * the rest of the top 3 nibbles is always 0.
 	 *
 	 * Because the debugfs interface uses signed offsets and shifts
 	 * the address left by 3, we basically cannot use the top 4 bits
@@ -86,10 +86,13 @@ static u64 opal_scom_unmangle(u64 reg)
 	 * conversion here. To leave room for further xscom address
 	 * expansion, we only clear out the top byte
 	 *
+	 * For in-kernel use, we also support the real indirect bit, so
+	 * we test for any of the top 5 bits
+	 *
 	 */
-	if (reg & (1ull << 59))
-		reg = (reg & ~(0xffull << 56)) | (1ull << 63);
-	return reg;
+	if (addr & (0x1full << 59))
+		addr = (addr & ~(0xffull << 56)) | (1ull << 63);
+	return addr;
 }
 
 static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
@@ -98,8 +101,8 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
 	int64_t rc;
 	__be64 v;
 
-	reg = opal_scom_unmangle(reg);
-	rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+	reg = opal_scom_unmangle(m->addr + reg);
+	rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v));
 	*value = be64_to_cpu(v);
 	return opal_xscom_err_xlate(rc);
 }
@@ -109,8 +112,8 @@ static int opal_scom_write(scom_map_t map, u64 reg, u64 value)
 	struct opal_scom_map *m = map;
 	int64_t rc;
 
-	reg = opal_scom_unmangle(reg);
-	rc = opal_xscom_write(m->chip, m->addr + reg, value);
+	reg = opal_scom_unmangle(m->addr + reg);
+	rc = opal_xscom_write(m->chip, reg, value);
 	return opal_xscom_err_xlate(rc);
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 95633d7..8518817 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -134,57 +134,72 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose,
 	pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n",
 		hose->global_number, common->version);
 
-	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-	pr_info("  slotStatus:           %08x\n", data->slotStatus);
-	pr_info("  linkStatus:           %08x\n", data->linkStatus);
-	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-	pr_info("  sourceId:             %08x\n", data->sourceId);
-	pr_info("  errorClass:           %016llx\n", data->errorClass);
-	pr_info("  correlator:           %016llx\n", data->correlator);
-	pr_info("  p7iocPlssr:           %016llx\n", data->p7iocPlssr);
-	pr_info("  p7iocCsr:             %016llx\n", data->p7iocCsr);
-	pr_info("  lemFir:               %016llx\n", data->lemFir);
-	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+	if (data->brdgCtl)
+		pr_info("  brdgCtl:     %08x\n",
+			data->brdgCtl);
+	if (data->portStatusReg || data->rootCmplxStatus ||
+	    data->busAgentStatus)
+		pr_info("  UtlSts:      %08x %08x %08x\n",
+			data->portStatusReg, data->rootCmplxStatus,
+			data->busAgentStatus);
+	if (data->deviceStatus || data->slotStatus   ||
+	    data->linkStatus   || data->devCmdStatus ||
+	    data->devSecStatus)
+		pr_info("  RootSts:     %08x %08x %08x %08x %08x\n",
+			data->deviceStatus, data->slotStatus,
+			data->linkStatus, data->devCmdStatus,
+			data->devSecStatus);
+	if (data->rootErrorStatus   || data->uncorrErrorStatus ||
+	    data->corrErrorStatus)
+		pr_info("  RootErrSts:  %08x %08x %08x\n",
+			data->rootErrorStatus, data->uncorrErrorStatus,
+			data->corrErrorStatus);
+	if (data->tlpHdr1 || data->tlpHdr2 ||
+	    data->tlpHdr3 || data->tlpHdr4)
+		pr_info("  RootErrLog:  %08x %08x %08x %08x\n",
+			data->tlpHdr1, data->tlpHdr2,
+			data->tlpHdr3, data->tlpHdr4);
+	if (data->sourceId || data->errorClass ||
+	    data->correlator)
+		pr_info("  RootErrLog1: %08x %016llx %016llx\n",
+			data->sourceId, data->errorClass,
+			data->correlator);
+	if (data->p7iocPlssr || data->p7iocCsr)
+		pr_info("  PhbSts:      %016llx %016llx\n",
+			data->p7iocPlssr, data->p7iocCsr);
+	if (data->lemFir || data->lemErrorMask ||
+	    data->lemWOF)
+		pr_info("  Lem:         %016llx %016llx %016llx\n",
+			data->lemFir, data->lemErrorMask,
+			data->lemWOF);
+	if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+	    data->phbErrorLog0   || data->phbErrorLog1)
+		pr_info("  PhbErr:      %016llx %016llx %016llx %016llx\n",
+			data->phbErrorStatus, data->phbFirstErrorStatus,
+			data->phbErrorLog0, data->phbErrorLog1);
+	if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+	    data->mmioErrorLog0   || data->mmioErrorLog1)
+		pr_info("  OutErr:      %016llx %016llx %016llx %016llx\n",
+			data->mmioErrorStatus, data->mmioFirstErrorStatus,
+			data->mmioErrorLog0, data->mmioErrorLog1);
+	if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+	    data->dma0ErrorLog0   || data->dma0ErrorLog1)
+		pr_info("  InAErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+			data->dma0ErrorLog0, data->dma0ErrorLog1);
+	if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+	    data->dma1ErrorLog0   || data->dma1ErrorLog1)
+		pr_info("  InBErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+			data->dma1ErrorLog0, data->dma1ErrorLog1);
 
 	for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
 		if ((data->pestA[i] >> 63) == 0 &&
 		    (data->pestB[i] >> 63) == 0)
 			continue;
 
-		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+		pr_info("  PE[%3d] A/B: %016llx %016llx\n",
+			i, data->pestA[i], data->pestB[i]);
 	}
 }
 
@@ -197,62 +212,77 @@ static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose,
 	data = (struct OpalIoPhb3ErrorData*)common;
 	pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n",
 		hose->global_number, common->version);
-
-	pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-	pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-	pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-	pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-	pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-	pr_info("  slotStatus:           %08x\n", data->slotStatus);
-	pr_info("  linkStatus:           %08x\n", data->linkStatus);
-	pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-	pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-	pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-	pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-	pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-	pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-	pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-	pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-	pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-	pr_info("  sourceId:             %08x\n", data->sourceId);
-	pr_info("  errorClass:           %016llx\n", data->errorClass);
-	pr_info("  correlator:           %016llx\n", data->correlator);
-
-	pr_info("  nFir:                 %016llx\n", data->nFir);
-	pr_info("  nFirMask:             %016llx\n", data->nFirMask);
-	pr_info("  nFirWOF:              %016llx\n", data->nFirWOF);
-	pr_info("  PhbPlssr:             %016llx\n", data->phbPlssr);
-	pr_info("  PhbCsr:               %016llx\n", data->phbCsr);
-	pr_info("  lemFir:               %016llx\n", data->lemFir);
-	pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-	pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-	pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-	pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-	pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-	pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-	pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-	pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-	pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-	pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-	pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-	pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-	pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-	pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-	pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-	pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-	pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-	pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+	if (data->brdgCtl)
+		pr_info("  brdgCtl:     %08x\n",
+			data->brdgCtl);
+	if (data->portStatusReg || data->rootCmplxStatus ||
+	    data->busAgentStatus)
+		pr_info("  UtlSts:      %08x %08x %08x\n",
+			data->portStatusReg, data->rootCmplxStatus,
+			data->busAgentStatus);
+	if (data->deviceStatus || data->slotStatus   ||
+	    data->linkStatus   || data->devCmdStatus ||
+	    data->devSecStatus)
+		pr_info("  RootSts:     %08x %08x %08x %08x %08x\n",
+			data->deviceStatus, data->slotStatus,
+			data->linkStatus, data->devCmdStatus,
+			data->devSecStatus);
+	if (data->rootErrorStatus || data->uncorrErrorStatus ||
+	    data->corrErrorStatus)
+		pr_info("  RootErrSts:  %08x %08x %08x\n",
+			data->rootErrorStatus, data->uncorrErrorStatus,
+			data->corrErrorStatus);
+	if (data->tlpHdr1 || data->tlpHdr2 ||
+	    data->tlpHdr3 || data->tlpHdr4)
+		pr_info("  RootErrLog:  %08x %08x %08x %08x\n",
+			data->tlpHdr1, data->tlpHdr2,
+			data->tlpHdr3, data->tlpHdr4);
+	if (data->sourceId || data->errorClass ||
+	    data->correlator)
+		pr_info("  RootErrLog1: %08x %016llx %016llx\n",
+			data->sourceId, data->errorClass,
+			data->correlator);
+	if (data->nFir || data->nFirMask ||
+	    data->nFirWOF)
+		pr_info("  nFir:        %016llx %016llx %016llx\n",
+			data->nFir, data->nFirMask,
+			data->nFirWOF);
+	if (data->phbPlssr || data->phbCsr)
+		pr_info("  PhbSts:      %016llx %016llx\n",
+			data->phbPlssr, data->phbCsr);
+	if (data->lemFir || data->lemErrorMask ||
+	    data->lemWOF)
+		pr_info("  Lem:         %016llx %016llx %016llx\n",
+			data->lemFir, data->lemErrorMask,
+			data->lemWOF);
+	if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+	    data->phbErrorLog0   || data->phbErrorLog1)
+		pr_info("  PhbErr:      %016llx %016llx %016llx %016llx\n",
+			data->phbErrorStatus, data->phbFirstErrorStatus,
+			data->phbErrorLog0, data->phbErrorLog1);
+	if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+	    data->mmioErrorLog0   || data->mmioErrorLog1)
+		pr_info("  OutErr:      %016llx %016llx %016llx %016llx\n",
+			data->mmioErrorStatus, data->mmioFirstErrorStatus,
+			data->mmioErrorLog0, data->mmioErrorLog1);
+	if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+	    data->dma0ErrorLog0   || data->dma0ErrorLog1)
+		pr_info("  InAErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+			data->dma0ErrorLog0, data->dma0ErrorLog1);
+	if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+	    data->dma1ErrorLog0   || data->dma1ErrorLog1)
+		pr_info("  InBErr:      %016llx %016llx %016llx %016llx\n",
+			data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+			data->dma1ErrorLog0, data->dma1ErrorLog1);
 
 	for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
 		if ((data->pestA[i] >> 63) == 0 &&
 		    (data->pestB[i] >> 63) == 0)
 			continue;
 
-		pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-		pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+		pr_info("  PE[%3d] A/B: %016llx %016llx\n",
+			i, data->pestA[i], data->pestB[i]);
 	}
 }
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 82789e7..0ea99e3 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -35,12 +35,7 @@
 #include "offline_states.h"
 
 /* This version can't take the spinlock, because it never returns */
-static struct rtas_args rtas_stop_self_args = {
-	.token = RTAS_UNKNOWN_SERVICE,
-	.nargs = 0,
-	.nret = 1,
-	.rets = &rtas_stop_self_args.args[0],
-};
+static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE;
 
 static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) =
 							CPU_STATE_OFFLINE;
@@ -93,15 +88,20 @@ void set_default_offline_state(int cpu)
 
 static void rtas_stop_self(void)
 {
-	struct rtas_args *args = &rtas_stop_self_args;
+	struct rtas_args args = {
+		.token = cpu_to_be32(rtas_stop_self_token),
+		.nargs = 0,
+		.nret = 1,
+		.rets = &args.args[0],
+	};
 
 	local_irq_disable();
 
-	BUG_ON(args->token == RTAS_UNKNOWN_SERVICE);
+	BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
 
 	printk("cpu %u (hwid %u) Ready to die...\n",
 	       smp_processor_id(), hard_smp_processor_id());
-	enter_rtas(__pa(args));
+	enter_rtas(__pa(&args));
 
 	panic("Alas, I survived.\n");
 }
@@ -392,10 +392,10 @@ static int __init pseries_cpu_hotplug_init(void)
 		}
 	}
 
-	rtas_stop_self_args.token = rtas_token("stop-self");
+	rtas_stop_self_token = rtas_token("stop-self");
 	qcss_tok = rtas_token("query-cpu-stopped-state");
 
-	if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE ||
+	if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE ||
 			qcss_tok == RTAS_UNKNOWN_SERVICE) {
 		printk(KERN_INFO "CPU Hotplug not supported by firmware "
 				"- disabling.\n");
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 59c8efc..0248949 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -1421,5 +1421,5 @@ ENTRY(sys_sched_setattr_wrapper)
 ENTRY(sys_sched_getattr_wrapper)
 	lgfr	%r2,%r2			# pid_t
 	llgtr	%r3,%r3			# const char __user *
-	llgfr	%r3,%r3			# unsigned int
+	llgfr	%r4,%r4			# unsigned int
 	jg	sys_sched_getattr
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 60c11a6..f91c031 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -206,11 +206,13 @@ static void dma_cleanup_tables(struct zpci_dev *zdev)
 	zdev->dma_table = NULL;
 }
 
-static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev, unsigned long start,
-				   int size)
+static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev,
+				       unsigned long start, int size)
 {
-	unsigned long boundary_size = 0x1000000;
+	unsigned long boundary_size;
 
+	boundary_size = ALIGN(dma_get_seg_boundary(&zdev->pdev->dev) + 1,
+			      PAGE_SIZE) >> PAGE_SHIFT;
 	return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
 				start, size, 0, boundary_size, 0);
 }
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 90a21f4..4dbf967 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -111,7 +111,7 @@ struct mem_vector {
 };
 
 #define MEM_AVOID_MAX 5
-struct mem_vector mem_avoid[MEM_AVOID_MAX];
+static struct mem_vector mem_avoid[MEM_AVOID_MAX];
 
 static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
 {
@@ -180,7 +180,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 }
 
 /* Does this memory vector overlap a known avoided area? */
-bool mem_avoid_overlap(struct mem_vector *img)
+static bool mem_avoid_overlap(struct mem_vector *img)
 {
 	int i;
 
@@ -192,8 +192,9 @@ bool mem_avoid_overlap(struct mem_vector *img)
 	return false;
 }
 
-unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN];
-unsigned long slot_max = 0;
+static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+			   CONFIG_PHYSICAL_ALIGN];
+static unsigned long slot_max;
 
 static void slots_append(unsigned long addr)
 {
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 895604f..79f9f84 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1192,6 +1192,9 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	for (i = 0; i < cpuc->n_events; i++) {
 		if (event == cpuc->event_list[i]) {
 
+			if (i >= cpuc->n_events - cpuc->n_added)
+				--cpuc->n_added;
+
 			if (x86_pmu.put_event_constraints)
 				x86_pmu.put_event_constraints(cpuc, event);
 
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 4eabc16..679cef0 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -279,5 +279,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(node_data);
 	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
 #endif
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
+			      (unsigned long)&_text - __START_KERNEL);
 }
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e50425d..9b53135 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2672,6 +2672,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 			break;
 		}
 
+		drop_large_spte(vcpu, iterator.sptep);
 		if (!is_shadow_present_pte(*iterator.sptep)) {
 			u64 base_addr = iterator.addr;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a06f101..3927528 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6688,7 +6688,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		else if (is_page_fault(intr_info))
 			return enable_ept;
 		else if (is_no_device(intr_info) &&
-			 !(nested_read_cr0(vmcs12) & X86_CR0_TS))
+			 !(vmcs12->guest_cr0 & X86_CR0_TS))
 			return 0;
 		return vmcs12->exception_bitmap &
 				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 39c28f09..2b85784 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6186,7 +6186,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 		frag->len -= len;
 	}
 
-	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+	if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
 
 		/* FIXME: return into emulator if single-stepping.  */
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index ba56e11..c87ae7c 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -20,6 +20,7 @@ config XTENSA
 	select HAVE_FUNCTION_TRACER
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_PERF_EVENTS
+	select COMMON_CLK
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica
 	  primarily for embedded systems.  These processors are both
@@ -80,7 +81,6 @@ choice
 config XTENSA_VARIANT_FSF
 	bool "fsf - default (not generic) configuration"
 	select MMU
-	select HAVE_XTENSA_GPIO32
 
 config XTENSA_VARIANT_DC232B
 	bool "dc232b - Diamond 232L Standard Core Rev.B (LE)"
@@ -135,7 +135,6 @@ config HAVE_SMP
 config SMP
 	bool "Enable Symmetric multi-processing support"
 	depends on HAVE_SMP
-	select USE_GENERIC_SMP_HELPERS
 	select GENERIC_SMP_IDLE_THREAD
 	help
 	  Enabled SMP Software; allows more than one CPU/CORE
diff --git a/arch/xtensa/boot/dts/xtfpga.dtsi b/arch/xtensa/boot/dts/xtfpga.dtsi
index 46b4f5e..e7370b1 100644
--- a/arch/xtensa/boot/dts/xtfpga.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga.dtsi
@@ -35,6 +35,13 @@
 		interrupt-controller;
 	};
 
+	clocks {
+		osc: main-oscillator {
+			#clock-cells = <0>;
+			compatible = "fixed-clock";
+		};
+	};
+
 	serial0: serial@fd050020 {
 		device_type = "serial";
 		compatible = "ns16550a";
@@ -42,9 +49,7 @@
 		reg = <0xfd050020 0x20>;
 		reg-shift = <2>;
 		interrupts = <0 1>; /* external irq 0 */
-		/* Filled in by platform_setup from FPGA register
-		 * clock-frequency = <100000000>;
-		 */
+		clocks = <&osc>;
 	};
 
 	enet0: ethoc@fd030000 {
@@ -52,5 +57,6 @@
 		reg = <0xfd030000 0x4000 0xfd800000 0x4000>;
 		interrupts = <1 1>; /* external irq 1 */
 		local-mac-address = [00 50 c2 13 6f 00];
+		clocks = <&osc>;
 	};
 };
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index 2a042d4..7494420 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -25,7 +25,7 @@
 
 #ifdef CONFIG_MMU
 
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 extern unsigned long xtensa_kio_paddr;
 
 static inline unsigned long xtensa_get_kio_paddr(void)
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 8c194f6..677bfcf 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -23,25 +23,37 @@ void secondary_trap_init(void);
 
 static inline void spill_registers(void)
 {
-
+#if XCHAL_NUM_AREGS > 16
 	__asm__ __volatile__ (
-		"movi	a14, "__stringify((1 << PS_EXCM_BIT) | LOCKLEVEL)"\n\t"
-		"mov	a12, a0\n\t"
-		"rsr	a13, sar\n\t"
-		"xsr	a14, ps\n\t"
-		"movi	a0, _spill_registers\n\t"
-		"rsync\n\t"
-		"callx0 a0\n\t"
-		"mov	a0, a12\n\t"
-		"wsr	a13, sar\n\t"
-		"wsr	a14, ps\n\t"
-		: :
-#if defined(CONFIG_FRAME_POINTER)
-		: "a2", "a3", "a4",       "a11", "a12", "a13", "a14", "a15",
+		"	call12	1f\n"
+		"	_j	2f\n"
+		"	retw\n"
+		"	.align	4\n"
+		"1:\n"
+		"	_entry	a1, 48\n"
+		"	addi	a12, a0, 3\n"
+#if XCHAL_NUM_AREGS > 32
+		"	.rept	(" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n"
+		"	_entry	a1, 48\n"
+		"	mov	a12, a0\n"
+		"	.endr\n"
+#endif
+		"	_entry	a1, 48\n"
+#if XCHAL_NUM_AREGS % 12 == 0
+		"	mov	a8, a8\n"
+#elif XCHAL_NUM_AREGS % 12 == 4
+		"	mov	a12, a12\n"
+#elif XCHAL_NUM_AREGS % 12 == 8
+		"	mov	a4, a4\n"
+#endif
+		"	retw\n"
+		"2:\n"
+		: : : "a12", "a13", "memory");
 #else
-		: "a2", "a3", "a4", "a7", "a11", "a12", "a13", "a14", "a15",
+	__asm__ __volatile__ (
+		"	mov	a12, a12\n"
+		: : : "memory");
 #endif
-		  "memory");
 }
 
 #endif /* _XTENSA_TRAPS_H */
diff --git a/arch/xtensa/include/asm/vectors.h b/arch/xtensa/include/asm/vectors.h
index 5791b45..f74ddfb 100644
--- a/arch/xtensa/include/asm/vectors.h
+++ b/arch/xtensa/include/asm/vectors.h
@@ -25,7 +25,7 @@
 #define XCHAL_KIO_DEFAULT_PADDR		0xf0000000
 #define XCHAL_KIO_SIZE			0x10000000
 
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 #define XCHAL_KIO_PADDR			xtensa_get_kio_paddr()
 #else
 #define XCHAL_KIO_PADDR			XCHAL_KIO_DEFAULT_PADDR
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index 51940fe..b939552 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -734,7 +734,12 @@ __SYSCALL(332, sys_finit_module, 3)
 #define __NR_accept4				333
 __SYSCALL(333, sys_accept4, 4)
 
-#define __NR_syscall_count			334
+#define __NR_sched_setattr			334
+__SYSCALL(334, sys_sched_setattr, 2)
+#define __NR_sched_getattr			335
+__SYSCALL(335, sys_sched_getattr, 3)
+
+#define __NR_syscall_count			336
 
 /*
  * sysxtensa syscall handler
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 21dbe6b..ef7f499 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1081,196 +1081,53 @@ ENTRY(fast_syscall_spill_registers)
 
 	rsr	a0, sar
 	s32i	a3, a2, PT_AREG3
-	s32i	a4, a2, PT_AREG4
-	s32i	a0, a2, PT_AREG5	# store SAR to PT_AREG5
+	s32i	a0, a2, PT_SAR
 
-	/* The spill routine might clobber a7, a11, and a15. */
+	/* The spill routine might clobber a4, a7, a8, a11, a12, and a15. */
 
+	s32i	a4, a2, PT_AREG4
 	s32i	a7, a2, PT_AREG7
+	s32i	a8, a2, PT_AREG8
 	s32i	a11, a2, PT_AREG11
+	s32i	a12, a2, PT_AREG12
 	s32i	a15, a2, PT_AREG15
 
-	call0	_spill_registers	# destroys a3, a4, and SAR
-
-	/* Advance PC, restore registers and SAR, and return from exception. */
-
-	l32i	a3, a2, PT_AREG5
-	l32i	a4, a2, PT_AREG4
-	l32i	a0, a2, PT_AREG0
-	wsr	a3, sar
-	l32i	a3, a2, PT_AREG3
-
-	/* Restore clobbered registers. */
-
-	l32i	a7, a2, PT_AREG7
-	l32i	a11, a2, PT_AREG11
-	l32i	a15, a2, PT_AREG15
-
-	movi	a2, 0
-	rfe
-
-ENDPROC(fast_syscall_spill_registers)
-
-/* Fixup handler.
- *
- * We get here if the spill routine causes an exception, e.g. tlb miss.
- * We basically restore WINDOWBASE and WINDOWSTART to the condition when
- * we entered the spill routine and jump to the user exception handler.
- *
- * a0: value of depc, original value in depc
- * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
- * a3: exctable, original value in excsave1
- */
-
-ENTRY(fast_syscall_spill_registers_fixup)
-
-	rsr	a2, windowbase	# get current windowbase (a2 is saved)
-	xsr	a0, depc	# restore depc and a0
-	ssl	a2		# set shift (32 - WB)
-
-	/* We need to make sure the current registers (a0-a3) are preserved.
-	 * To do this, we simply set the bit for the current window frame
-	 * in WS, so that the exception handlers save them to the task stack.
-	 */
-
-	xsr	a3, excsave1	# get spill-mask
-	slli	a3, a3, 1	# shift left by one
-
-	slli	a2, a3, 32-WSBITS
-	src	a2, a3, a2	# a2 = xxwww1yyxxxwww1yy......
-	wsr	a2, windowstart	# set corrected windowstart
-
-	srli	a3, a3, 1
-	rsr	a2, excsave1
-	l32i	a2, a2, EXC_TABLE_DOUBLE_SAVE	# restore a2
-	xsr	a2, excsave1
-	s32i	a3, a2, EXC_TABLE_DOUBLE_SAVE	# save a3
-	l32i	a3, a2, EXC_TABLE_PARAM	# original WB (in user task)
-	xsr	a2, excsave1
-
-	/* Return to the original (user task) WINDOWBASE.
-	 * We leave the following frame behind:
-	 * a0, a1, a2	same
-	 * a3:		trashed (saved in EXC_TABLE_DOUBLE_SAVE)
-	 * depc:	depc (we have to return to that address)
-	 * excsave_1:	exctable
-	 */
-
-	wsr	a3, windowbase
-	rsync
-
-	/* We are now in the original frame when we entered _spill_registers:
-	 *  a0: return address
-	 *  a1: used, stack pointer
-	 *  a2: kernel stack pointer
-	 *  a3: available
-	 *  depc: exception address
-	 *  excsave: exctable
-	 * Note: This frame might be the same as above.
-	 */
-
-	/* Setup stack pointer. */
-
-	addi	a2, a2, -PT_USER_SIZE
-	s32i	a0, a2, PT_AREG0
-
-	/* Make sure we return to this fixup handler. */
-
-	movi	a3, fast_syscall_spill_registers_fixup_return
-	s32i	a3, a2, PT_DEPC		# setup depc
-
-	/* Jump to the exception handler. */
-
-	rsr	a3, excsave1
-	rsr	a0, exccause
-	addx4	a0, a0, a3              	# find entry in table
-	l32i	a0, a0, EXC_TABLE_FAST_USER     # load handler
-	l32i	a3, a3, EXC_TABLE_DOUBLE_SAVE
-	jx	a0
-
-ENDPROC(fast_syscall_spill_registers_fixup)
-
-ENTRY(fast_syscall_spill_registers_fixup_return)
-
-	/* When we return here, all registers have been restored (a2: DEPC) */
-
-	wsr	a2, depc		# exception address
-
-	/* Restore fixup handler. */
-
-	rsr	a2, excsave1
-	s32i	a3, a2, EXC_TABLE_DOUBLE_SAVE
-	movi	a3, fast_syscall_spill_registers_fixup
-	s32i	a3, a2, EXC_TABLE_FIXUP
-	rsr	a3, windowbase
-	s32i	a3, a2, EXC_TABLE_PARAM
-	l32i	a2, a2, EXC_TABLE_KSTK
-
-	/* Load WB at the time the exception occurred. */
-
-	rsr	a3, sar			# WB is still in SAR
-	neg	a3, a3
-	wsr	a3, windowbase
-	rsync
-
-	rsr	a3, excsave1
-	l32i	a3, a3, EXC_TABLE_DOUBLE_SAVE
-
-	rfde
-
-ENDPROC(fast_syscall_spill_registers_fixup_return)
-
-/*
- * spill all registers.
- *
- * This is not a real function. The following conditions must be met:
- *
- *  - must be called with call0.
- *  - uses a3, a4 and SAR.
- *  - the last 'valid' register of each frame are clobbered.
- *  - the caller must have registered a fixup handler
- *    (or be inside a critical section)
- *  - PS_EXCM must be set (PS_WOE cleared?)
- */
-
-ENTRY(_spill_registers)
-
 	/*
 	 * Rotate ws so that the current windowbase is at bit 0.
 	 * Assume ws = xxxwww1yy (www1 current window frame).
 	 * Rotate ws right so that a4 = yyxxxwww1.
 	 */
 
-	rsr	a4, windowbase
+	rsr	a0, windowbase
 	rsr	a3, windowstart		# a3 = xxxwww1yy
-	ssr	a4			# holds WB
-	slli	a4, a3, WSBITS
-	or	a3, a3, a4		# a3 = xxxwww1yyxxxwww1yy
+	ssr	a0			# holds WB
+	slli	a0, a3, WSBITS
+	or	a3, a3, a0		# a3 = xxxwww1yyxxxwww1yy
 	srl	a3, a3			# a3 = 00xxxwww1yyxxxwww1
 
 	/* We are done if there are no more than the current register frame. */
 
 	extui	a3, a3, 1, WSBITS-1	# a3 = 0yyxxxwww
-	movi	a4, (1 << (WSBITS-1))
+	movi	a0, (1 << (WSBITS-1))
 	_beqz	a3, .Lnospill		# only one active frame? jump
 
 	/* We want 1 at the top, so that we return to the current windowbase */
 
-	or	a3, a3, a4		# 1yyxxxwww
+	or	a3, a3, a0		# 1yyxxxwww
 
 	/* Skip empty frames - get 'oldest' WINDOWSTART-bit. */
 
 	wsr	a3, windowstart		# save shifted windowstart
-	neg	a4, a3
-	and	a3, a4, a3		# first bit set from right: 000010000
+	neg	a0, a3
+	and	a3, a0, a3		# first bit set from right: 000010000
 
-	ffs_ws	a4, a3			# a4: shifts to skip empty frames
+	ffs_ws	a0, a3			# a0: shifts to skip empty frames
 	movi	a3, WSBITS
-	sub	a4, a3, a4		# WSBITS-a4:number of 0-bits from right
-	ssr	a4			# save in SAR for later.
+	sub	a0, a3, a0		# WSBITS-a0:number of 0-bits from right
+	ssr	a0			# save in SAR for later.
 
 	rsr	a3, windowbase
-	add	a3, a3, a4
+	add	a3, a3, a0
 	wsr	a3, windowbase
 	rsync
 
@@ -1285,22 +1142,6 @@ ENTRY(_spill_registers)
 	 * we have to save 4,8. or 12 registers.
 	 */
 
-	_bbsi.l	a3, 1, .Lc4
-	_bbsi.l	a3, 2, .Lc8
-
-	/* Special case: we have a call12-frame starting at a4. */
-
-	_bbci.l	a3, 3, .Lc12	# bit 3 shouldn't be zero! (Jump to Lc12 first)
-
-	s32e	a4, a1, -16	# a1 is valid with an empty spill area
-	l32e	a4, a5, -12
-	s32e	a8, a4, -48
-	mov	a8, a4
-	l32e	a4, a1, -16
-	j	.Lc12c
-
-.Lnospill:
-	ret
 
 .Lloop: _bbsi.l	a3, 1, .Lc4
 	_bbci.l	a3, 2, .Lc12
@@ -1314,20 +1155,10 @@ ENTRY(_spill_registers)
 	s32e	a9, a4, -28
 	s32e	a10, a4, -24
 	s32e	a11, a4, -20
-
 	srli	a11, a3, 2		# shift windowbase by 2
 	rotw	2
 	_bnei	a3, 1, .Lloop
-
-.Lexit: /* Done. Do the final rotation, set WS, and return. */
-
-	rotw	1
-	rsr	a3, windowbase
-	ssl	a3
-	movi	a3, 1
-	sll	a3, a3
-	wsr	a3, windowstart
-	ret
+	j	.Lexit
 
 .Lc4:	s32e	a4, a9, -16
 	s32e	a5, a9, -12
@@ -1343,11 +1174,11 @@ ENTRY(_spill_registers)
 
 	/* 12-register frame (call12) */
 
-	l32e	a2, a5, -12
-	s32e	a8, a2, -48
-	mov	a8, a2
+	l32e	a0, a5, -12
+	s32e	a8, a0, -48
+	mov	a8, a0
 
-.Lc12c: s32e	a9, a8, -44
+	s32e	a9, a8, -44
 	s32e	a10, a8, -40
 	s32e	a11, a8, -36
 	s32e	a12, a8, -32
@@ -1367,30 +1198,54 @@ ENTRY(_spill_registers)
 	 */
 
 	rotw	1
-	mov	a5, a13
+	mov	a4, a13
 	rotw	-1
 
-	s32e	a4, a9, -16
-	s32e	a5, a9, -12
-	s32e	a6, a9, -8
-	s32e	a7, a9, -4
+	s32e	a4, a8, -16
+	s32e	a5, a8, -12
+	s32e	a6, a8, -8
+	s32e	a7, a8, -4
 
 	rotw	3
 
 	_beqi	a3, 1, .Lexit
 	j	.Lloop
 
-.Linvalid_mask:
+.Lexit:
 
-	/* We get here because of an unrecoverable error in the window
-	 * registers. If we are in user space, we kill the application,
-	 * however, this condition is unrecoverable in kernel space.
-	 */
+	/* Done. Do the final rotation and set WS */
+
+	rotw	1
+	rsr	a3, windowbase
+	ssl	a3
+	movi	a3, 1
+	sll	a3, a3
+	wsr	a3, windowstart
+.Lnospill:
+
+	/* Advance PC, restore registers and SAR, and return from exception. */
+
+	l32i	a3, a2, PT_SAR
+	l32i	a0, a2, PT_AREG0
+	wsr	a3, sar
+	l32i	a3, a2, PT_AREG3
 
-	rsr	a0, ps
-	_bbci.l	a0, PS_UM_BIT, 1f
+	/* Restore clobbered registers. */
 
-	/* User space: Setup a dummy frame and kill application.
+	l32i	a4, a2, PT_AREG4
+	l32i	a7, a2, PT_AREG7
+	l32i	a8, a2, PT_AREG8
+	l32i	a11, a2, PT_AREG11
+	l32i	a12, a2, PT_AREG12
+	l32i	a15, a2, PT_AREG15
+
+	movi	a2, 0
+	rfe
+
+.Linvalid_mask:
+
+	/* We get here because of an unrecoverable error in the window
+	 * registers, so set up a dummy frame and kill the user application.
 	 * Note: We assume EXC_TABLE_KSTK contains a valid stack pointer.
 	 */
 
@@ -1414,14 +1269,136 @@ ENTRY(_spill_registers)
 	movi	a4, do_exit
 	callx4	a4
 
-1:	/* Kernel space: PANIC! */
+	/* shouldn't return, so panic */
 
 	wsr	a0, excsave1
 	movi	a0, unrecoverable_exception
 	callx0	a0		# should not return
 1:	j	1b
 
-ENDPROC(_spill_registers)
+
+ENDPROC(fast_syscall_spill_registers)
+
+/* Fixup handler.
+ *
+ * We get here if the spill routine causes an exception, e.g. tlb miss.
+ * We basically restore WINDOWBASE and WINDOWSTART to the condition when
+ * we entered the spill routine and jump to the user exception handler.
+ *
+ * Note that we only need to restore the bits in windowstart that have not
+ * been spilled yet by the _spill_register routine. Luckily, a3 contains a
+ * rotated windowstart with only those bits set for frames that haven't been
+ * spilled yet. Because a3 is rotated such that bit 0 represents the register
+ * frame for the current windowbase - 1, we need to rotate a3 left by the
+ * value of the current windowbase + 1 and move it to windowstart.
+ *
+ * a0: value of depc, original value in depc
+ * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
+ * a3: exctable, original value in excsave1
+ */
+
+ENTRY(fast_syscall_spill_registers_fixup)
+
+	rsr	a2, windowbase	# get current windowbase (a2 is saved)
+	xsr	a0, depc	# restore depc and a0
+	ssl	a2		# set shift (32 - WB)
+
+	/* We need to make sure the current registers (a0-a3) are preserved.
+	 * To do this, we simply set the bit for the current window frame
+	 * in WS, so that the exception handlers save them to the task stack.
+	 *
+	 * Note: we use a3 to set the windowbase, so we take a special care
+	 * of it, saving it in the original _spill_registers frame across
+	 * the exception handler call.
+	 */
+
+	xsr	a3, excsave1	# get spill-mask
+	slli	a3, a3, 1	# shift left by one
+	addi	a3, a3, 1	# set the bit for the current window frame
+
+	slli	a2, a3, 32-WSBITS
+	src	a2, a3, a2	# a2 = xxwww1yyxxxwww1yy......
+	wsr	a2, windowstart	# set corrected windowstart
+
+	srli	a3, a3, 1
+	rsr	a2, excsave1
+	l32i	a2, a2, EXC_TABLE_DOUBLE_SAVE	# restore a2
+	xsr	a2, excsave1
+	s32i	a3, a2, EXC_TABLE_DOUBLE_SAVE	# save a3
+	l32i	a3, a2, EXC_TABLE_PARAM	# original WB (in user task)
+	xsr	a2, excsave1
+
+	/* Return to the original (user task) WINDOWBASE.
+	 * We leave the following frame behind:
+	 * a0, a1, a2	same
+	 * a3:		trashed (saved in EXC_TABLE_DOUBLE_SAVE)
+	 * depc:	depc (we have to return to that address)
+	 * excsave_1:	exctable
+	 */
+
+	wsr	a3, windowbase
+	rsync
+
+	/* We are now in the original frame when we entered _spill_registers:
+	 *  a0: return address
+	 *  a1: used, stack pointer
+	 *  a2: kernel stack pointer
+	 *  a3: available
+	 *  depc: exception address
+	 *  excsave: exctable
+	 * Note: This frame might be the same as above.
+	 */
+
+	/* Setup stack pointer. */
+
+	addi	a2, a2, -PT_USER_SIZE
+	s32i	a0, a2, PT_AREG0
+
+	/* Make sure we return to this fixup handler. */
+
+	movi	a3, fast_syscall_spill_registers_fixup_return
+	s32i	a3, a2, PT_DEPC		# setup depc
+
+	/* Jump to the exception handler. */
+
+	rsr	a3, excsave1
+	rsr	a0, exccause
+	addx4	a0, a0, a3              	# find entry in table
+	l32i	a0, a0, EXC_TABLE_FAST_USER     # load handler
+	l32i	a3, a3, EXC_TABLE_DOUBLE_SAVE
+	jx	a0
+
+ENDPROC(fast_syscall_spill_registers_fixup)
+
+ENTRY(fast_syscall_spill_registers_fixup_return)
+
+	/* When we return here, all registers have been restored (a2: DEPC) */
+
+	wsr	a2, depc		# exception address
+
+	/* Restore fixup handler. */
+
+	rsr	a2, excsave1
+	s32i	a3, a2, EXC_TABLE_DOUBLE_SAVE
+	movi	a3, fast_syscall_spill_registers_fixup
+	s32i	a3, a2, EXC_TABLE_FIXUP
+	rsr	a3, windowbase
+	s32i	a3, a2, EXC_TABLE_PARAM
+	l32i	a2, a2, EXC_TABLE_KSTK
+
+	/* Load WB at the time the exception occurred. */
+
+	rsr	a3, sar			# WB is still in SAR
+	neg	a3, a3
+	wsr	a3, windowbase
+	rsync
+
+	rsr	a3, excsave1
+	l32i	a3, a3, EXC_TABLE_DOUBLE_SAVE
+
+	rfde
+
+ENDPROC(fast_syscall_spill_registers_fixup_return)
 
 #ifdef CONFIG_MMU
 /*
@@ -1794,6 +1771,43 @@ ENTRY(system_call)
 
 ENDPROC(system_call)
 
+/*
+ * Spill live registers on the kernel stack macro.
+ *
+ * Entry condition: ps.woe is set, ps.excm is cleared
+ * Exit condition: windowstart has single bit set
+ * May clobber: a12, a13
+ */
+	.macro	spill_registers_kernel
+
+#if XCHAL_NUM_AREGS > 16
+	call12	1f
+	_j	2f
+	retw
+	.align	4
+1:
+	_entry	a1, 48
+	addi	a12, a0, 3
+#if XCHAL_NUM_AREGS > 32
+	.rept	(XCHAL_NUM_AREGS - 32) / 12
+	_entry	a1, 48
+	mov	a12, a0
+	.endr
+#endif
+	_entry	a1, 48
+#if XCHAL_NUM_AREGS % 12 == 0
+	mov	a8, a8
+#elif XCHAL_NUM_AREGS % 12 == 4
+	mov	a12, a12
+#elif XCHAL_NUM_AREGS % 12 == 8
+	mov	a4, a4
+#endif
+	retw
+2:
+#else
+	mov	a12, a12
+#endif
+	.endm
 
 /*
  * Task switch.
@@ -1806,21 +1820,20 @@ ENTRY(_switch_to)
 
 	entry	a1, 16
 
-	mov	a12, a2			# preserve 'prev' (a2)
-	mov	a13, a3			# and 'next' (a3)
+	mov	a10, a2			# preserve 'prev' (a2)
+	mov	a11, a3			# and 'next' (a3)
 
 	l32i	a4, a2, TASK_THREAD_INFO
 	l32i	a5, a3, TASK_THREAD_INFO
 
-	save_xtregs_user a4 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+	save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
-	s32i	a0, a12, THREAD_RA	# save return address
-	s32i	a1, a12, THREAD_SP	# save stack pointer
+	s32i	a0, a10, THREAD_RA	# save return address
+	s32i	a1, a10, THREAD_SP	# save stack pointer
 
 	/* Disable ints while we manipulate the stack pointer. */
 
-	movi	a14, (1 << PS_EXCM_BIT) | LOCKLEVEL
-	xsr	a14, ps
+	rsil	a14, LOCKLEVEL
 	rsr	a3, excsave1
 	rsync
 	s32i	a3, a3, EXC_TABLE_FIXUP	/* enter critical section */
@@ -1835,7 +1848,7 @@ ENTRY(_switch_to)
 
 	/* Flush register file. */
 
-	call0	_spill_registers	# destroys a3, a4, and SAR
+	spill_registers_kernel
 
 	/* Set kernel stack (and leave critical section)
 	 * Note: It's save to set it here. The stack will not be overwritten
@@ -1851,13 +1864,13 @@ ENTRY(_switch_to)
 
 	/* restore context of the task 'next' */
 
-	l32i	a0, a13, THREAD_RA	# restore return address
-	l32i	a1, a13, THREAD_SP	# restore stack pointer
+	l32i	a0, a11, THREAD_RA	# restore return address
+	l32i	a1, a11, THREAD_SP	# restore stack pointer
 
-	load_xtregs_user a5 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+	load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
 	wsr	a14, ps
-	mov	a2, a12			# return 'prev'
+	mov	a2, a10			# return 'prev'
 	rsync
 
 	retw
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 7d12af1..84fe931 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -22,6 +22,7 @@
 #include <linux/bootmem.h>
 #include <linux/kernel.h>
 #include <linux/percpu.h>
+#include <linux/clk-provider.h>
 #include <linux/cpu.h>
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
@@ -276,6 +277,7 @@ void __init early_init_devtree(void *params)
 
 static int __init xtensa_device_probe(void)
 {
+	of_clk_init(NULL);
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	return 0;
 }
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 08b769d..2a1823d 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -30,6 +30,7 @@
 #include <asm/platform.h>
 
 unsigned long ccount_freq;		/* ccount Hz */
+EXPORT_SYMBOL(ccount_freq);
 
 static cycle_t ccount_read(struct clocksource *cs)
 {
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index cb8fd44..f9e1ec3 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -235,7 +235,7 @@ ENTRY(_DoubleExceptionVector)
 
 	/* Check for overflow/underflow exception, jump if overflow. */
 
-	_bbci.l	a0, 6, _DoubleExceptionVector_WindowOverflow
+	bbci.l	a0, 6, _DoubleExceptionVector_WindowOverflow
 
 	/*
 	 * Restart window underflow exception.
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 74a60c7..80b33ed 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -122,9 +122,7 @@ EXPORT_SYMBOL(insw);
 EXPORT_SYMBOL(insl);
 
 extern long common_exception_return;
-extern long _spill_registers;
 EXPORT_SYMBOL(common_exception_return);
-EXPORT_SYMBOL(_spill_registers);
 
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 479d753..aff108d 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -90,7 +90,7 @@ int __init mem_reserve(unsigned long start, unsigned long end, int must_exist)
 
 
 /*
- * Initialize the bootmem system and give it all the memory we have available.
+ * Initialize the bootmem system and give it all low memory we have available.
  */
 
 void __init bootmem_init(void)
@@ -142,9 +142,14 @@ void __init bootmem_init(void)
 
 	/* Add all remaining memory pieces into the bootmem map */
 
-	for (i=0; i<sysmem.nr_banks; i++)
-		free_bootmem(sysmem.bank[i].start,
-			     sysmem.bank[i].end - sysmem.bank[i].start);
+	for (i = 0; i < sysmem.nr_banks; i++) {
+		if (sysmem.bank[i].start >> PAGE_SHIFT < max_low_pfn) {
+			unsigned long end = min(max_low_pfn << PAGE_SHIFT,
+						sysmem.bank[i].end);
+			free_bootmem(sysmem.bank[i].start,
+				     end - sysmem.bank[i].start);
+		}
+	}
 
 }
 
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index 36ec171..861203e 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -39,7 +39,7 @@ void init_mmu(void)
 	set_itlbcfg_register(0);
 	set_dtlbcfg_register(0);
 #endif
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 	/*
 	 * Update the IO area mapping in case xtensa_kio_paddr has changed
 	 */
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index 8002278..57fd08b 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -135,11 +135,11 @@ static void __init update_local_mac(struct device_node *node)
 
 static int __init machine_setup(void)
 {
-	struct device_node *serial;
+	struct device_node *clock;
 	struct device_node *eth = NULL;
 
-	for_each_compatible_node(serial, NULL, "ns16550a")
-		update_clock_frequency(serial);
+	for_each_node_by_name(clock, "main-oscillator")
+		update_clock_frequency(clock);
 
 	if ((eth = of_find_compatible_node(eth, NULL, "opencores,ethoc")))
 		update_local_mac(eth);
@@ -290,6 +290,7 @@ static int __init xtavnet_init(void)
 	 * knows whether they set it correctly on the DIP switches.
 	 */
 	pr_info("XTFPGA: Ethernet MAC %pM\n", ethoc_pdata.hwaddr);
+	ethoc_pdata.eth_clkfreq = *(long *)XTFPGA_CLKFRQ_VADDR;
 
 	return 0;
 }
diff --git a/arch/xtensa/variants/fsf/include/variant/tie.h b/arch/xtensa/variants/fsf/include/variant/tie.h
index bf40201..244cdea 100644
--- a/arch/xtensa/variants/fsf/include/variant/tie.h
+++ b/arch/xtensa/variants/fsf/include/variant/tie.h
@@ -18,13 +18,6 @@
 #define XCHAL_CP_MASK			0x00	/* bitmask of all CPs by ID */
 #define XCHAL_CP_PORT_MASK		0x00	/* bitmask of only port CPs */
 
-/*  Basic parameters of each coprocessor:  */
-#define XCHAL_CP7_NAME			"XTIOP"
-#define XCHAL_CP7_IDENT			XTIOP
-#define XCHAL_CP7_SA_SIZE		0	/* size of state save area */
-#define XCHAL_CP7_SA_ALIGN		1	/* min alignment of save area */
-#define XCHAL_CP_ID_XTIOP		7	/* coprocessor ID (0..7) */
-
 /*  Filler info for unassigned coprocessors, to simplify arrays etc:  */
 #define XCHAL_NCP_SA_SIZE		0
 #define XCHAL_NCP_SA_ALIGN		1
@@ -42,6 +35,8 @@
 #define XCHAL_CP5_SA_ALIGN		1
 #define XCHAL_CP6_SA_SIZE		0
 #define XCHAL_CP6_SA_ALIGN		1
+#define XCHAL_CP7_SA_SIZE		0
+#define XCHAL_CP7_SA_ALIGN		1
 
 /*  Save area for non-coprocessor optional and custom (TIE) state:  */
 #define XCHAL_NCP_SA_SIZE		0