Merge branch 'vexpress-v3.4' of git://git.linaro.org/people/pawelmoll/linux into late/soc

A few device tree updates and an include file fix for versatile.

* 'vexpress-v3.4' of git://git.linaro.org/people/pawelmoll/linux:
  ARM: vexpress: Remove twice included header files
  ARM: vexpress: Device Tree updates
  + update to 3.4

Signed-off-by: Olof Johansson <olof@lixom.net>

34 files changed, 424 insertions, 187 deletions

diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
index 941b161ab78c..7e1091d91af8 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15-tc1.dts
@@ -73,7 +73,10 @@
 		#address-cells = <0>;
 		interrupt-controller;
 		reg = <0x2c001000 0x1000>,
-		      <0x2c002000 0x100>;
+		      <0x2c002000 0x1000>,
+		      <0x2c004000 0x2000>,
+		      <0x2c006000 0x2000>;
+		interrupts = <1 9 0xf04>;
 	};
 
 	memory-controller@7ffd0000 {
@@ -93,6 +96,14 @@
 			     <0 91 4>;
 	};
 
+	timer {
+		compatible = "arm,armv7-timer";
+		interrupts = <1 13 0xf08>,
+			     <1 14 0xf08>,
+			     <1 11 0xf08>,
+			     <1 10 0xf08>;
+	};
+
 	pmu {
 		compatible = "arm,cortex-a15-pmu", "arm,cortex-a9-pmu";
 		interrupts = <0 68 4>,
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
index 6905e66d4748..18917a0f8604 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca5s.dts
@@ -77,13 +77,18 @@
 
 	timer@2c000600 {
 		compatible = "arm,cortex-a5-twd-timer";
-		reg = <0x2c000600 0x38>;
-		interrupts = <1 2 0x304>,
-			     <1 3 0x304>;
+		reg = <0x2c000600 0x20>;
+		interrupts = <1 13 0x304>;
+	};
+
+	watchdog@2c000620 {
+		compatible = "arm,cortex-a5-twd-wdt";
+		reg = <0x2c000620 0x20>;
+		interrupts = <1 14 0x304>;
 	};
 
 	gic: interrupt-controller@2c001000 {
-		compatible = "arm,corex-a5-gic", "arm,cortex-a9-gic";
+		compatible = "arm,cortex-a5-gic", "arm,cortex-a9-gic";
 		#interrupt-cells = <3>;
 		#address-cells = <0>;
 		interrupt-controller;
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
index da778693be54..3f0c736d31d6 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts
@@ -105,8 +105,13 @@
 	timer@1e000600 {
 		compatible = "arm,cortex-a9-twd-timer";
 		reg = <0x1e000600 0x20>;
-		interrupts = <1 2 0xf04>,
-			     <1 3 0xf04>;
+		interrupts = <1 13 0xf04>;
+	};
+
+	watchdog@1e000620 {
+		compatible = "arm,cortex-a9-twd-wdt";
+		reg = <0x1e000620 0x20>;
+		interrupts = <1 14 0xf04>;
 	};
 
 	gic: interrupt-controller@1e001000 {
diff --git a/arch/arm/mach-prima2/irq.c b/arch/arm/mach-prima2/irq.c
index 37c2de9b6f26..a7b9415d30f8 100644
--- a/arch/arm/mach-prima2/irq.c
+++ b/arch/arm/mach-prima2/irq.c
@@ -42,7 +42,8 @@ sirfsoc_alloc_gc(void __iomem *base, unsigned int irq_start, unsigned int num)
 static __init void sirfsoc_irq_init(void)
 {
 	sirfsoc_alloc_gc(sirfsoc_intc_base, 0, 32);
-	sirfsoc_alloc_gc(sirfsoc_intc_base + 4, 32, SIRFSOC_INTENAL_IRQ_END - 32);
+	sirfsoc_alloc_gc(sirfsoc_intc_base + 4, 32,
+			SIRFSOC_INTENAL_IRQ_END + 1 - 32);
 
 	writel_relaxed(0, sirfsoc_intc_base + SIRFSOC_INT_RISC_LEVEL0);
 	writel_relaxed(0, sirfsoc_intc_base + SIRFSOC_INT_RISC_LEVEL1);
@@ -68,7 +69,8 @@ void __init sirfsoc_of_irq_init(void)
 	if (!sirfsoc_intc_base)
 		panic("unable to map intc cpu registers\n");
 
-	irq_domain_add_legacy(np, 32, 0, 0, &irq_domain_simple_ops, NULL);
+	irq_domain_add_legacy(np, SIRFSOC_INTENAL_IRQ_END + 1, 0, 0,
+		&irq_domain_simple_ops, NULL);
 
 	of_node_put(np);
 
diff --git a/arch/arm/mach-tegra/flowctrl.c b/arch/arm/mach-tegra/flowctrl.c
index fef66a7486ed..f07488e0bd32 100644
--- a/arch/arm/mach-tegra/flowctrl.c
+++ b/arch/arm/mach-tegra/flowctrl.c
@@ -53,10 +53,10 @@ static void flowctrl_update(u8 offset, u32 value)
 
 void flowctrl_write_cpu_csr(unsigned int cpuid, u32 value)
 {
-	return flowctrl_update(flowctrl_offset_halt_cpu[cpuid], value);
+	return flowctrl_update(flowctrl_offset_cpu_csr[cpuid], value);
 }
 
 void flowctrl_write_cpu_halt(unsigned int cpuid, u32 value)
 {
-	return flowctrl_update(flowctrl_offset_cpu_csr[cpuid], value);
+	return flowctrl_update(flowctrl_offset_halt_cpu[cpuid], value);
 }
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 47cdcca5a7e7..e769ab612627 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -14,7 +14,6 @@
 #include <linux/ata_platform.h>
 #include <linux/smsc911x.h>
 #include <linux/spinlock.h>
-#include <linux/device.h>
 #include <linux/usb/isp1760.h>
 #include <linux/clkdev.h>
 #include <linux/mtd/physmap.h>
@@ -29,7 +28,6 @@
 #include <asm/hardware/gic.h>
 #include <asm/hardware/timer-sp.h>
 #include <asm/hardware/sp810.h>
-#include <asm/hardware/gic.h>
 
 #include <mach/ct-ca9x4.h>
 #include <mach/motherboard.h>
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index f07467533365..5bb48356d217 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -247,7 +247,9 @@ good_area:
 	return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags);
 
 check_stack:
-	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
+	/* Don't allow expansion below FIRST_USER_ADDRESS */
+	if (vma->vm_flags & VM_GROWSDOWN &&
+	    addr >= FIRST_USER_ADDRESS && !expand_stack(vma, addr))
 		goto good_area;
 out:
 	return fault;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 2c7cf2f9c837..aa78de8bfdd3 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -489,7 +489,8 @@ static void __init build_mem_type_table(void)
 	 */
 	for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
 		mem_types[i].prot_pte |= PTE_EXT_AF;
-		mem_types[i].prot_sect |= PMD_SECT_AF;
+		if (mem_types[i].prot_sect)
+			mem_types[i].prot_sect |= PMD_SECT_AF;
 	}
 	kern_pgprot |= PTE_EXT_AF;
 	vecs_pgprot |= PTE_EXT_AF;
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index bc683b8219b5..b0197b2c857d 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <linux/cpu.h>
 #include <linux/cpu_pm.h>
+#include <linux/hardirq.h>
 #include <linux/kernel.h>
 #include <linux/notifier.h>
 #include <linux/signal.h>
@@ -432,7 +433,10 @@ void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
 
 static void vfp_enable(void *unused)
 {
-	u32 access = get_copro_access();
+	u32 access;
+
+	BUG_ON(preemptible());
+	access = get_copro_access();
 
 	/*
 	 * Enable full access to VFP (cp10 and cp11)
@@ -573,12 +577,6 @@ int vfp_preserve_user_clear_hwstate(struct user_vfp __user *ufp,
 	 * entry.
 	 */
 	hwstate->fpscr &= ~(FPSCR_LENGTH_MASK | FPSCR_STRIDE_MASK);
-
-	/*
-	 * Disable VFP in the hwstate so that we can detect if it gets
-	 * used.
-	 */
-	hwstate->fpexc &= ~FPEXC_EN;
 	return 0;
 }
 
@@ -591,12 +589,8 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
 	unsigned long fpexc;
 	int err = 0;
 
-	/*
-	 * If VFP has been used, then disable it to avoid corrupting
-	 * the new thread state.
-	 */
-	if (hwstate->fpexc & FPEXC_EN)
-		vfp_flush_hwstate(thread);
+	/* Disable VFP to avoid corrupting the new thread state. */
+	vfp_flush_hwstate(thread);
 
 	/*
 	 * Copy the floating point registers. There can be unused
@@ -657,7 +651,7 @@ static int __init vfp_init(void)
 	unsigned int cpu_arch = cpu_architecture();
 
 	if (cpu_arch >= CPU_ARCH_ARMv6)
-		vfp_enable(NULL);
+		on_each_cpu(vfp_enable, NULL, 1);
 
 	/*
 	 * First check that there is a VFP that we can use.
@@ -678,8 +672,6 @@ static int __init vfp_init(void)
 	} else {
 		hotcpu_notifier(vfp_hotplug, 0);
 
-		smp_call_function(vfp_enable, NULL, 1);
-
 		VFP_arch = (vfpsid & FPSID_ARCH_MASK) >> FPSID_ARCH_BIT;  /* Extract the architecture version */
 		printk("implementor %02x architecture %d part %02x variant %x rev %x\n",
 			(vfpsid & FPSID_IMPLEMENTER_MASK) >> FPSID_IMPLEMENTER_BIT,
diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h
index 81c2e271d620..9b1a92b73f60 100644
--- a/arch/frv/include/asm/processor.h
+++ b/arch/frv/include/asm/processor.h
@@ -135,10 +135,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define	KSTK_EIP(tsk)	((tsk)->thread.frame0->pc)
 #define	KSTK_ESP(tsk)	((tsk)->thread.frame0->sp)
 
-/* Allocation and freeing of basic task resources. */
-extern struct task_struct *alloc_task_struct_node(int node);
-extern void free_task_struct(struct task_struct *p);
-
 #define cpu_relax()    barrier()
 
 /* data cache prefetch */
diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c
index 910dddf65e44..9cd69ad6aa02 100644
--- a/arch/mn10300/kernel/smp.c
+++ b/arch/mn10300/kernel/smp.c
@@ -24,6 +24,7 @@
 #include <linux/sched.h>
 #include <linux/profile.h>
 #include <linux/smp.h>
+#include <linux/cpu.h>
 #include <asm/tlbflush.h>
 #include <asm/bitops.h>
 #include <asm/processor.h>
@@ -38,7 +39,6 @@
 #include "internal.h"
 
 #ifdef CONFIG_HOTPLUG_CPU
-#include <linux/cpu.h>
 #include <asm/cacheflush.h>
 
 static unsigned long sleep_mode[NR_CPUS];
@@ -874,10 +874,13 @@ static void __init smp_online(void)
 
 	cpu = smp_processor_id();
 
-	local_irq_enable();
+	notify_cpu_starting(cpu);
 
+	ipi_call_lock();
 	set_cpu_online(cpu, true);
-	smp_wmb();
+	ipi_call_unlock();
+
+	local_irq_enable();
 }
 
 /**
diff --git a/arch/parisc/include/asm/prefetch.h b/arch/parisc/include/asm/prefetch.h
index c5edc60c059f..1ee7c82672c1 100644
--- a/arch/parisc/include/asm/prefetch.h
+++ b/arch/parisc/include/asm/prefetch.h
@@ -21,7 +21,12 @@
 #define ARCH_HAS_PREFETCH
 static inline void prefetch(const void *addr)
 {
-	__asm__("ldw 0(%0), %%r0" : : "r" (addr));
+	__asm__(
+#ifndef CONFIG_PA20
+		/* Need to avoid prefetch of NULL on PA7300LC */
+		"	extrw,u,= %0,31,32,%%r0\n"
+#endif
+		"	ldw 0(%0), %%r0" : : "r" (addr));
 }
 
 /* LDD is a PA2.0 addition. */
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 6f0594439143..535034217021 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -581,7 +581,11 @@
 	 */
 	cmpiclr,=	0x01,\tmp,%r0
 	ldi		(_PAGE_DIRTY|_PAGE_READ|_PAGE_WRITE),\prot
+#ifdef CONFIG_64BIT
 	depd,z		\prot,8,7,\prot
+#else
+	depw,z		\prot,8,7,\prot
+#endif
 	/*
 	 * OK, it is in the temp alias region, check whether "from" or "to".
 	 * Check "subtle" note in pacache.S re: r23/r26.
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 93ff3d90edd1..5d7218ad885c 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -692,7 +692,7 @@ ENTRY(flush_icache_page_asm)
 
 	/* Purge any old translation */
 
-	pitlb		(%sr0,%r28)
+	pitlb		(%sr4,%r28)
 
 	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r1
@@ -706,27 +706,29 @@ ENTRY(flush_icache_page_asm)
 	sub		%r25, %r1, %r25
 
 
-1:      fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
-	fic,m		%r1(%r28)
+	/* fic only has the type 26 form on PA1.1, requiring an
+	 * explicit space specification, so use %sr4 */
+1:      fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
+	fic,m		%r1(%sr4,%r28)
 	cmpb,COND(<<)		%r28, %r25,1b
-	fic,m		%r1(%r28)
+	fic,m		%r1(%sr4,%r28)
 
 	sync
 	bv		%r0(%r2)
-	pitlb		(%sr0,%r25)
+	pitlb		(%sr4,%r25)
 	.exit
 
 	.procend
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 0bb1d63907f8..4dc7b7942b4c 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -31,6 +31,7 @@
 #include <linux/delay.h>
 #include <linux/bitops.h>
 #include <linux/ftrace.h>
+#include <linux/cpu.h>
 
 #include <linux/atomic.h>
 #include <asm/current.h>
@@ -295,8 +296,13 @@ smp_cpu_init(int cpunum)
 
 		printk(KERN_CRIT "CPU#%d already initialized!\n", cpunum);
 		machine_halt();
-	}  
+	}
+
+	notify_cpu_starting(cpunum);
+
+	ipi_call_lock();
 	set_cpu_online(cpunum, true);
+	ipi_call_unlock();
 
 	/* Initialise the idle task for this CPU */
 	atomic_inc(&init_mm.mm_count);
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index aa795ccef294..fd07f43d6622 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -81,12 +81,13 @@ struct kvmppc_vcpu_book3s {
 	u64 sdr1;
 	u64 hior;
 	u64 msr_mask;
-	u64 vsid_next;
 #ifdef CONFIG_PPC_BOOK3S_32
 	u32 vsid_pool[VSID_POOL_SIZE];
+	u32 vsid_next;
 #else
-	u64 vsid_first;
-	u64 vsid_max;
+	u64 proto_vsid_first;
+	u64 proto_vsid_max;
+	u64 proto_vsid_next;
 #endif
 	int context_id[SID_CONTEXTS];
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 6f87f39a1ac2..10fc8ec9d2a8 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -194,14 +194,14 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 	backwards_map = !backwards_map;
 
 	/* Uh-oh ... out of mappings. Let's flush! */
-	if (vcpu_book3s->vsid_next == vcpu_book3s->vsid_max) {
-		vcpu_book3s->vsid_next = vcpu_book3s->vsid_first;
+	if (vcpu_book3s->proto_vsid_next == vcpu_book3s->proto_vsid_max) {
+		vcpu_book3s->proto_vsid_next = vcpu_book3s->proto_vsid_first;
 		memset(vcpu_book3s->sid_map, 0,
 		       sizeof(struct kvmppc_sid_map) * SID_MAP_NUM);
 		kvmppc_mmu_pte_flush(vcpu, 0, 0);
 		kvmppc_mmu_flush_segments(vcpu);
 	}
-	map->host_vsid = vcpu_book3s->vsid_next++;
+	map->host_vsid = vsid_scramble(vcpu_book3s->proto_vsid_next++, 256M);
 
 	map->guest_vsid = gvsid;
 	map->valid = true;
@@ -319,9 +319,10 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
 		return -1;
 	vcpu3s->context_id[0] = err;
 
-	vcpu3s->vsid_max = ((vcpu3s->context_id[0] + 1) << USER_ESID_BITS) - 1;
-	vcpu3s->vsid_first = vcpu3s->context_id[0] << USER_ESID_BITS;
-	vcpu3s->vsid_next = vcpu3s->vsid_first;
+	vcpu3s->proto_vsid_max = ((vcpu3s->context_id[0] + 1)
+				  << USER_ESID_BITS) - 1;
+	vcpu3s->proto_vsid_first = vcpu3s->context_id[0] << USER_ESID_BITS;
+	vcpu3s->proto_vsid_next = vcpu3s->proto_vsid_first;
 
 	kvmppc_mmu_hpte_init(vcpu);
 
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index def880aea63a..cec4daddbf31 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -463,6 +463,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 				/* insert R and C bits from PTE */
 				rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
 				args[j] |= rcbits << (56 - 5);
+				hp[0] = 0;
 				continue;
 			}
 
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 0676ae249b9f..6e6e9cef34a8 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -197,7 +197,8 @@ kvmppc_interrupt:
 	/* Save guest PC and MSR */
 #ifdef CONFIG_PPC64
 BEGIN_FTR_SECTION
-	andi.	r0,r12,0x2
+	andi.	r0, r12, 0x2
+	cmpwi	cr1, r0, 0
 	beq	1f
 	mfspr	r3,SPRN_HSRR0
 	mfspr	r4,SPRN_HSRR1
@@ -250,6 +251,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	beq	ld_last_prev_inst
 	cmpwi	r12, BOOK3S_INTERRUPT_ALIGNMENT
 	beq-	ld_last_inst
+#ifdef CONFIG_PPC64
+BEGIN_FTR_SECTION
+	cmpwi	r12, BOOK3S_INTERRUPT_H_EMUL_ASSIST
+	beq-	ld_last_inst
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+#endif
 
 	b	no_ld_last_inst
 
@@ -316,23 +323,17 @@ no_dcbz32_off:
 	 * Having set up SRR0/1 with the address where we want
 	 * to continue with relocation on (potentially in module
 	 * space), we either just go straight there with rfi[d],
-	 * or we jump to an interrupt handler with bctr if there
-	 * is an interrupt to be handled first.  In the latter
-	 * case, the rfi[d] at the end of the interrupt handler
-	 * will get us back to where we want to continue.
+	 * or we jump to an interrupt handler if there is an
+	 * interrupt to be handled first.  In the latter case,
+	 * the rfi[d] at the end of the interrupt handler will
+	 * get us back to where we want to continue.
 	 */
 
-	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
-	beq	1f
-	cmpwi	r12, BOOK3S_INTERRUPT_DECREMENTER
-	beq	1f
-	cmpwi	r12, BOOK3S_INTERRUPT_PERFMON
-1:	mtctr	r12
-
 	/* Register usage at this point:
 	 *
 	 * R1       = host R1
 	 * R2       = host R2
+	 * R10      = raw exit handler id
 	 * R12      = exit handler id
 	 * R13      = shadow vcpu (32-bit) or PACA (64-bit)
 	 * SVCPU.*  = guest *
@@ -342,12 +343,25 @@ no_dcbz32_off:
 	PPC_LL	r6, HSTATE_HOST_MSR(r13)
 	PPC_LL	r8, HSTATE_VMHANDLER(r13)
 
-	/* Restore host msr -> SRR1 */
+#ifdef CONFIG_PPC64
+BEGIN_FTR_SECTION
+	beq	cr1, 1f
+	mtspr	SPRN_HSRR1, r6
+	mtspr	SPRN_HSRR0, r8
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
+#endif
+1:	/* Restore host msr -> SRR1 */
 	mtsrr1	r6
 	/* Load highmem handler address */
 	mtsrr0	r8
 
 	/* RFI into the highmem handler, or jump to interrupt handler */
-	beqctr
+	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
+	beqa	BOOK3S_INTERRUPT_EXTERNAL
+	cmpwi	r12, BOOK3S_INTERRUPT_DECREMENTER
+	beqa	BOOK3S_INTERRUPT_DECREMENTER
+	cmpwi	r12, BOOK3S_INTERRUPT_PERFMON
+	beqa	BOOK3S_INTERRUPT_PERFMON
+
 	RFI
 kvmppc_handler_trampoline_exit_end:
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 96033e2d6845..74239dd77e06 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -11,6 +11,7 @@ config TILE
 	select GENERIC_IRQ_PROBE
 	select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_IRQ_SHOW
+	select HAVE_SYSCALL_WRAPPERS if TILEGX
 	select SYS_HYPERVISOR
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 
diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h
index bc4f562bd459..7594764d8a69 100644
--- a/arch/tile/include/asm/thread_info.h
+++ b/arch/tile/include/asm/thread_info.h
@@ -100,9 +100,14 @@ extern void cpu_idle_on_new_stack(struct thread_info *old_ti,
 
 #else /* __ASSEMBLY__ */
 
-/* how to get the thread information struct from ASM */
+/*
+ * How to get the thread information struct from assembly.
+ * Note that we use different macros since different architectures
+ * have different semantics in their "mm" instruction and we would
+ * like to guarantee that the macro expands to exactly one instruction.
+ */
 #ifdef __tilegx__
-#define GET_THREAD_INFO(reg) move reg, sp; mm reg, zero, LOG2_THREAD_SIZE, 63
+#define EXTRACT_THREAD_INFO(reg) mm reg, zero, LOG2_THREAD_SIZE, 63
 #else
 #define GET_THREAD_INFO(reg) mm reg, sp, zero, LOG2_THREAD_SIZE, 31
 #endif
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index 77763ccd5a7d..cdef6e5ec022 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -403,19 +403,17 @@ int compat_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	 * Set up registers for signal handler.
 	 * Registers that we don't modify keep the value they had from
 	 * user-space at the time we took the signal.
+	 * We always pass siginfo and mcontext, regardless of SA_SIGINFO,
+	 * since some things rely on this (e.g. glibc's debug/segfault.c).
 	 */
 	regs->pc = ptr_to_compat_reg(ka->sa.sa_handler);
 	regs->ex1 = PL_ICS_EX1(USER_PL, 1); /* set crit sec in handler */
 	regs->sp = ptr_to_compat_reg(frame);
 	regs->lr = restorer;
 	regs->regs[0] = (unsigned long) usig;
-
-	if (ka->sa.sa_flags & SA_SIGINFO) {
-		/* Need extra arguments, so mark to restore caller-saves. */
-		regs->regs[1] = ptr_to_compat_reg(&frame->info);
-		regs->regs[2] = ptr_to_compat_reg(&frame->uc);
-		regs->flags |= PT_FLAGS_CALLER_SAVES;
-	}
+	regs->regs[1] = ptr_to_compat_reg(&frame->info);
+	regs->regs[2] = ptr_to_compat_reg(&frame->uc);
+	regs->flags |= PT_FLAGS_CALLER_SAVES;
 
 	/*
 	 * Notify any tracer that was single-stepping it.
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index 5d56a1ef5ba5..6943515100f8 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -839,6 +839,18 @@ STD_ENTRY(interrupt_return)
 	FEEDBACK_REENTER(interrupt_return)
 
 	/*
+	 * Use r33 to hold whether we have already loaded the callee-saves
+	 * into ptregs.  We don't want to do it twice in this loop, since
+	 * then we'd clobber whatever changes are made by ptrace, etc.
+	 * Get base of stack in r32.
+	 */
+	{
+	 GET_THREAD_INFO(r32)
+	 movei  r33, 0
+	}
+
+.Lretry_work_pending:
+	/*
 	 * Disable interrupts so as to make sure we don't
 	 * miss an interrupt that sets any of the thread flags (like
 	 * need_resched or sigpending) between sampling and the iret.
@@ -848,9 +860,6 @@ STD_ENTRY(interrupt_return)
 	IRQ_DISABLE(r20, r21)
 	TRACE_IRQS_OFF  /* Note: clobbers registers r0-r29 */
 
-	/* Get base of stack in r32; note r30/31 are used as arguments here. */
-	GET_THREAD_INFO(r32)
-
 
 	/* Check to see if there is any work to do before returning to user. */
 	{
@@ -866,16 +875,18 @@ STD_ENTRY(interrupt_return)
 
 	/*
 	 * Make sure we have all the registers saved for signal
-	 * handling or single-step.  Call out to C code to figure out
-	 * exactly what we need to do for each flag bit, then if
-	 * necessary, reload the flags and recheck.
+	 * handling, notify-resume, or single-step.  Call out to C
+	 * code to figure out exactly what we need to do for each flag bit,
+	 * then if necessary, reload the flags and recheck.
 	 */
-	push_extra_callee_saves r0
 	{
 	 PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
-	 jal    do_work_pending
+	 bnz    r33, 1f
 	}
-	bnz     r0, .Lresume_userspace
+	push_extra_callee_saves r0
+	movei   r33, 1
+1:	jal     do_work_pending
+	bnz     r0, .Lretry_work_pending
 
 	/*
 	 * In the NMI case we
@@ -1180,10 +1191,12 @@ handle_syscall:
 	add     r20, r20, tp
 	lw      r21, r20
 	addi    r21, r21, 1
-	sw      r20, r21
+	{
+	 sw     r20, r21
+	 GET_THREAD_INFO(r31)
+	}
 
 	/* Trace syscalls, if requested. */
-	GET_THREAD_INFO(r31)
 	addi	r31, r31, THREAD_INFO_FLAGS_OFFSET
 	lw	r30, r31
 	andi    r30, r30, _TIF_SYSCALL_TRACE
@@ -1362,7 +1375,10 @@ handle_ill:
 3:
 	/* set PC and continue */
 	lw      r26, r24
-	sw      r28, r26
+	{
+	 sw     r28, r26
+	 GET_THREAD_INFO(r0)
+	}
 
 	/*
 	 * Clear TIF_SINGLESTEP to prevent recursion if we execute an ill.
@@ -1370,7 +1386,6 @@ handle_ill:
 	 * need to clear it here and can't really impose on all other arches.
 	 * So what's another write between friends?
 	 */
-	GET_THREAD_INFO(r0)
 
 	addi    r1, r0, THREAD_INFO_FLAGS_OFFSET
 	{
diff --git a/arch/tile/kernel/intvec_64.S b/arch/tile/kernel/intvec_64.S
index 49d9d6621682..30ae76e50c44 100644
--- a/arch/tile/kernel/intvec_64.S
+++ b/arch/tile/kernel/intvec_64.S
@@ -647,6 +647,20 @@ STD_ENTRY(interrupt_return)
 	FEEDBACK_REENTER(interrupt_return)
 
 	/*
+	 * Use r33 to hold whether we have already loaded the callee-saves
+	 * into ptregs.  We don't want to do it twice in this loop, since
+	 * then we'd clobber whatever changes are made by ptrace, etc.
+	 */
+	{
+	 movei  r33, 0
+	 move   r32, sp
+	}
+
+	/* Get base of stack in r32. */
+	EXTRACT_THREAD_INFO(r32)
+
+.Lretry_work_pending:
+	/*
 	 * Disable interrupts so as to make sure we don't
 	 * miss an interrupt that sets any of the thread flags (like
 	 * need_resched or sigpending) between sampling and the iret.
@@ -656,9 +670,6 @@ STD_ENTRY(interrupt_return)
 	IRQ_DISABLE(r20, r21)
 	TRACE_IRQS_OFF  /* Note: clobbers registers r0-r29 */
 
-	/* Get base of stack in r32; note r30/31 are used as arguments here. */
-	GET_THREAD_INFO(r32)
-
 
 	/* Check to see if there is any work to do before returning to user. */
 	{
@@ -674,16 +685,18 @@ STD_ENTRY(interrupt_return)
 
 	/*
 	 * Make sure we have all the registers saved for signal
-	 * handling or single-step.  Call out to C code to figure out
+	 * handling or notify-resume.  Call out to C code to figure out
 	 * exactly what we need to do for each flag bit, then if
 	 * necessary, reload the flags and recheck.
 	 */
-	push_extra_callee_saves r0
 	{
 	 PTREGS_PTR(r0, PTREGS_OFFSET_BASE)
-	 jal    do_work_pending
+	 bnez   r33, 1f
 	}
-	bnez    r0, .Lresume_userspace
+	push_extra_callee_saves r0
+	movei   r33, 1
+1:	jal     do_work_pending
+	bnez    r0, .Lretry_work_pending
 
 	/*
 	 * In the NMI case we
@@ -968,11 +981,16 @@ handle_syscall:
 	shl16insli r20, r20, hw0(irq_stat + IRQ_CPUSTAT_SYSCALL_COUNT_OFFSET)
 	add     r20, r20, tp
 	ld4s    r21, r20
-	addi    r21, r21, 1
-	st4     r20, r21
+	{
+	 addi   r21, r21, 1
+	 move   r31, sp
+	}
+	{
+	 st4    r20, r21
+	 EXTRACT_THREAD_INFO(r31)
+	}
 
 	/* Trace syscalls, if requested. */
-	GET_THREAD_INFO(r31)
 	addi	r31, r31, THREAD_INFO_FLAGS_OFFSET
 	ld	r30, r31
 	andi    r30, r30, _TIF_SYSCALL_TRACE
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 2d5ef617bb39..54e6c64b85cc 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -567,6 +567,10 @@ struct task_struct *__sched _switch_to(struct task_struct *prev,
  */
 int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
 {
+	/* If we enter in kernel mode, do nothing and exit the caller loop. */
+	if (!user_mode(regs))
+		return 0;
+
 	if (thread_info_flags & _TIF_NEED_RESCHED) {
 		schedule();
 		return 1;
@@ -589,8 +593,7 @@ int do_work_pending(struct pt_regs *regs, u32 thread_info_flags)
 		return 1;
 	}
 	if (thread_info_flags & _TIF_SINGLESTEP) {
-		if ((regs->ex1 & SPR_EX_CONTEXT_1_1__PL_MASK) == 0)
-			single_step_once(regs);
+		single_step_once(regs);
 		return 0;
 	}
 	panic("work_pending: bad flags %#x\n", thread_info_flags);
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 41a7237606a3..94e91e401da9 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -134,6 +134,9 @@ KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
 KBUILD_CFLAGS += $(mflags-y)
 KBUILD_AFLAGS += $(mflags-y)
 
+archscripts:
+	$(Q)$(MAKE) $(build)=arch/x86/tools relocs
+
 ###
 # Syscall table generation
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index fd55a2ff3ad8..e398bb5d63bb 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -40,13 +40,12 @@ OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
+targets += vmlinux.bin.all vmlinux.relocs
 
-targets += vmlinux.bin.all vmlinux.relocs relocs
-hostprogs-$(CONFIG_X86_NEED_RELOCS) += relocs
-
+CMD_RELOCS = arch/x86/tools/relocs
 quiet_cmd_relocs = RELOCS  $@
-      cmd_relocs = $(obj)/relocs $< > $@;$(obj)/relocs --abs-relocs $<
-$(obj)/vmlinux.relocs: vmlinux $(obj)/relocs FORCE
+      cmd_relocs = $(CMD_RELOCS) $< > $@;$(CMD_RELOCS) --abs-relocs $<
+$(obj)/vmlinux.relocs: vmlinux FORCE
 	$(call if_changed,relocs)
 
 vmlinux.bin.all-y := $(obj)/vmlinux.bin
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 734c3767cfac..183922e13de1 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -170,6 +170,9 @@ static inline int kvm_para_available(void)
 	unsigned int eax, ebx, ecx, edx;
 	char signature[13];
 
+	if (boot_cpu_data.cpuid_level < 0)
+		return 0;	/* So we don't blow up on old processors */
+
 	cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
 	memcpy(signature + 0, &ebx, 4);
 	memcpy(signature + 4, &ecx, 4);
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index a415b1f44365..7c439fe4941b 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -593,7 +593,7 @@ void __init acpi_set_irq_model_ioapic(void)
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 #include <acpi/processor.h>
 
-static void __cpuinitdata acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
+static void __cpuinit acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 {
 #ifdef CONFIG_ACPI_NUMA
 	int nid;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d086a09c087d..11c9166c3337 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -945,9 +945,10 @@ struct mce_info {
 	atomic_t		inuse;
 	struct task_struct	*t;
 	__u64			paddr;
+	int			restartable;
 } mce_info[MCE_INFO_MAX];
 
-static void mce_save_info(__u64 addr)
+static void mce_save_info(__u64 addr, int c)
 {
 	struct mce_info *mi;
 
@@ -955,6 +956,7 @@ static void mce_save_info(__u64 addr)
 		if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
 			mi->t = current;
 			mi->paddr = addr;
+			mi->restartable = c;
 			return;
 		}
 	}
@@ -1130,7 +1132,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 			mce_panic("Fatal machine check on current CPU", &m, msg);
 		if (worst == MCE_AR_SEVERITY) {
 			/* schedule action before return to userland */
-			mce_save_info(m.addr);
+			mce_save_info(m.addr, m.mcgstatus & MCG_STATUS_RIPV);
 			set_thread_flag(TIF_MCE_NOTIFY);
 		} else if (kill_it) {
 			force_sig(SIGBUS, current);
@@ -1179,7 +1181,13 @@ void mce_notify_process(void)
 
 	pr_err("Uncorrected hardware memory error in user-access at %llx",
 		 mi->paddr);
-	if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0) {
+	/*
+	 * We must call memory_failure() here even if the current process is
+	 * doomed. We still need to mark the page as poisoned and alert any
+	 * other users of the page.
+	 */
+	if (memory_failure(pfn, MCE_VECTOR, MF_ACTION_REQUIRED) < 0 ||
+			   mi->restartable == 0) {
 		pr_err("Memory error not recovered");
 		force_sig(SIGBUS, current);
 	}
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 3ca42d0e43a2..0327e2b3c408 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -147,12 +147,6 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 
 	memset(csig, 0, sizeof(*csig));
 
-	if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
-	    cpu_has(c, X86_FEATURE_IA64)) {
-		pr_err("CPU%d not a capable Intel processor\n", cpu_num);
-		return -1;
-	}
-
 	csig->sig = cpuid_eax(0x00000001);
 
 	if ((c->x86_model >= 5) || (c->x86 > 6)) {
@@ -463,6 +457,14 @@ static struct microcode_ops microcode_intel_ops = {
 
 struct microcode_ops * __init init_intel_microcode(void)
 {
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
+	    cpu_has(c, X86_FEATURE_IA64)) {
+		pr_err("Intel CPU family 0x%x not supported\n", c->x86);
+		return NULL;
+	}
+
 	return &microcode_intel_ops;
 }
 
diff --git a/arch/x86/tools/.gitignore b/arch/x86/tools/.gitignore
new file mode 100644
index 000000000000..be0ed065249b
--- /dev/null
+++ b/arch/x86/tools/.gitignore
@@ -0,0 +1 @@
+relocs
diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile
index d511aa97533a..733057b435b0 100644
--- a/arch/x86/tools/Makefile
+++ b/arch/x86/tools/Makefile
@@ -36,3 +36,7 @@ HOSTCFLAGS_insn_sanity.o := -Wall -I$(objtree)/arch/x86/lib/ -I$(srctree)/arch/x
 $(obj)/test_get_len.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
 
 $(obj)/insn_sanity.o: $(srctree)/arch/x86/lib/insn.c $(srctree)/arch/x86/lib/inat.c $(srctree)/arch/x86/include/asm/inat_types.h $(srctree)/arch/x86/include/asm/inat.h $(srctree)/arch/x86/include/asm/insn.h $(objtree)/arch/x86/lib/inat-tables.c
+
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include
+hostprogs-y	+= relocs
+relocs: $(obj)/relocs
diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/tools/relocs.c
index fb7117a4ade1..b43cfcd9bf40 100644
--- a/arch/x86/boot/compressed/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -18,6 +18,8 @@ static void die(char *fmt, ...);
 static Elf32_Ehdr ehdr;
 static unsigned long reloc_count, reloc_idx;
 static unsigned long *relocs;
+static unsigned long reloc16_count, reloc16_idx;
+static unsigned long *relocs16;
 
 struct section {
 	Elf32_Shdr     shdr;
@@ -28,52 +30,86 @@ struct section {
 };
 static struct section *secs;
 
+enum symtype {
+	S_ABS,
+	S_REL,
+	S_SEG,
+	S_LIN,
+	S_NSYMTYPES
+};
+
+static const char * const sym_regex_kernel[S_NSYMTYPES] = {
 /*
  * Following symbols have been audited. There values are constant and do
  * not change if bzImage is loaded at a different physical address than
  * the address for which it has been compiled. Don't warn user about
  * absolute relocations present w.r.t these symbols.
  */
-static const char abs_sym_regex[] =
+	[S_ABS] =
 	"^(xen_irq_disable_direct_reloc$|"
 	"xen_save_fl_direct_reloc$|"
 	"VDSO|"
-	"__crc_)";
-static regex_t abs_sym_regex_c;
-static int is_abs_reloc(const char *sym_name)
-{
-	return !regexec(&abs_sym_regex_c, sym_name, 0, NULL, 0);
-}
+	"__crc_)",
 
 /*
  * These symbols are known to be relative, even if the linker marks them
  * as absolute (typically defined outside any section in the linker script.)
  */
-static const char rel_sym_regex[] =
-	"^_end$";
-static regex_t rel_sym_regex_c;
-static int is_rel_reloc(const char *sym_name)
+	[S_REL] =
+	"^(__init_(begin|end)|"
+	"__x86_cpu_dev_(start|end)|"
+	"(__parainstructions|__alt_instructions)(|_end)|"
+	"(__iommu_table|__apicdrivers|__smp_locks)(|_end)|"
+	"_end)$"
+};
+
+
+static const char * const sym_regex_realmode[S_NSYMTYPES] = {
+/*
+ * These are 16-bit segment symbols when compiling 16-bit code.
+ */
+	[S_SEG] =
+	"^real_mode_seg$",
+
+/*
+ * These are offsets belonging to segments, as opposed to linear addresses,
+ * when compiling 16-bit code.
+ */
+	[S_LIN] =
+	"^pa_",
+};
+
+static const char * const *sym_regex;
+
+static regex_t sym_regex_c[S_NSYMTYPES];
+static int is_reloc(enum symtype type, const char *sym_name)
 {
-	return !regexec(&rel_sym_regex_c, sym_name, 0, NULL, 0);
+	return sym_regex[type] &&
+		!regexec(&sym_regex_c[type], sym_name, 0, NULL, 0);
 }
 
-static void regex_init(void)
+static void regex_init(int use_real_mode)
 {
         char errbuf[128];
         int err;
-	
-        err = regcomp(&abs_sym_regex_c, abs_sym_regex,
-                      REG_EXTENDED|REG_NOSUB);
-        if (err) {
-                regerror(err, &abs_sym_regex_c, errbuf, sizeof errbuf);
-                die("%s", errbuf);
-        }
+	int i;
+
+	if (use_real_mode)
+		sym_regex = sym_regex_realmode;
+	else
+		sym_regex = sym_regex_kernel;
 
-        err = regcomp(&rel_sym_regex_c, rel_sym_regex,
-                      REG_EXTENDED|REG_NOSUB);
-        if (err) {
-                regerror(err, &rel_sym_regex_c, errbuf, sizeof errbuf);
-                die("%s", errbuf);
+	for (i = 0; i < S_NSYMTYPES; i++) {
+		if (!sym_regex[i])
+			continue;
+
+		err = regcomp(&sym_regex_c[i], sym_regex[i],
+			      REG_EXTENDED|REG_NOSUB);
+
+		if (err) {
+			regerror(err, &sym_regex_c[i], errbuf, sizeof errbuf);
+			die("%s", errbuf);
+		}
         }
 }
 
@@ -154,6 +190,10 @@ static const char *rel_type(unsigned type)
 		REL_TYPE(R_386_RELATIVE),
 		REL_TYPE(R_386_GOTOFF),
 		REL_TYPE(R_386_GOTPC),
+		REL_TYPE(R_386_8),
+		REL_TYPE(R_386_PC8),
+		REL_TYPE(R_386_16),
+		REL_TYPE(R_386_PC16),
 #undef REL_TYPE
 	};
 	const char *name = "unknown type rel type name";
@@ -189,7 +229,7 @@ static const char *sym_name(const char *sym_strtab, Elf32_Sym *sym)
 		name = sym_strtab + sym->st_name;
 	}
 	else {
-		name = sec_name(secs[sym->st_shndx].shdr.sh_name);
+		name = sec_name(sym->st_shndx);
 	}
 	return name;
 }
@@ -472,7 +512,7 @@ static void print_absolute_relocs(void)
 			 * Before warning check if this absolute symbol
 			 * relocation is harmless.
 			 */
-			if (is_abs_reloc(name) || is_rel_reloc(name))
+			if (is_reloc(S_ABS, name) || is_reloc(S_REL, name))
 				continue;
 
 			if (!printed) {
@@ -496,7 +536,8 @@ static void print_absolute_relocs(void)
 		printf("\n");
 }
 
-static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym))
+static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym),
+			int use_real_mode)
 {
 	int i;
 	/* Walk through the relocations */
@@ -521,30 +562,67 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym))
 			Elf32_Rel *rel;
 			Elf32_Sym *sym;
 			unsigned r_type;
+			const char *symname;
+			int shn_abs;
+
 			rel = &sec->reltab[j];
 			sym = &sh_symtab[ELF32_R_SYM(rel->r_info)];
 			r_type = ELF32_R_TYPE(rel->r_info);
-			/* Don't visit relocations to absolute symbols */
-			if (sym->st_shndx == SHN_ABS &&
-			    !is_rel_reloc(sym_name(sym_strtab, sym))) {
-				continue;
-			}
+
+			shn_abs = sym->st_shndx == SHN_ABS;
+
 			switch (r_type) {
 			case R_386_NONE:
 			case R_386_PC32:
+			case R_386_PC16:
+			case R_386_PC8:
 				/*
 				 * NONE can be ignored and and PC relative
 				 * relocations don't need to be adjusted.
 				 */
 				break;
+
+			case R_386_16:
+				symname = sym_name(sym_strtab, sym);
+				if (!use_real_mode)
+					goto bad;
+				if (shn_abs) {
+					if (is_reloc(S_ABS, symname))
+						break;
+					else if (!is_reloc(S_SEG, symname))
+						goto bad;
+				} else {
+					if (is_reloc(S_LIN, symname))
+						goto bad;
+					else
+						break;
+				}
+				visit(rel, sym);
+				break;
+
 			case R_386_32:
-				/* Visit relocations that need to be adjusted */
+				symname = sym_name(sym_strtab, sym);
+				if (shn_abs) {
+					if (is_reloc(S_ABS, symname))
+						break;
+					else if (!is_reloc(S_REL, symname))
+						goto bad;
+				} else {
+					if (use_real_mode &&
+					    !is_reloc(S_LIN, symname))
+						break;
+				}
 				visit(rel, sym);
 				break;
 			default:
 				die("Unsupported relocation type: %s (%d)\n",
 				    rel_type(r_type), r_type);
 				break;
+			bad:
+				symname = sym_name(sym_strtab, sym);
+				die("Invalid %s %s relocation: %s\n",
+				    shn_abs ? "absolute" : "relative",
+				    rel_type(r_type), symname);
 			}
 		}
 	}
@@ -552,13 +630,19 @@ static void walk_relocs(void (*visit)(Elf32_Rel *rel, Elf32_Sym *sym))
 
 static void count_reloc(Elf32_Rel *rel, Elf32_Sym *sym)
 {
-	reloc_count += 1;
+	if (ELF32_R_TYPE(rel->r_info) == R_386_16)
+		reloc16_count++;
+	else
+		reloc_count++;
 }
 
 static void collect_reloc(Elf32_Rel *rel, Elf32_Sym *sym)
 {
 	/* Remember the address that needs to be adjusted. */
-	relocs[reloc_idx++] = rel->r_offset;
+	if (ELF32_R_TYPE(rel->r_info) == R_386_16)
+		relocs16[reloc16_idx++] = rel->r_offset;
+	else
+		relocs[reloc_idx++] = rel->r_offset;
 }
 
 static int cmp_relocs(const void *va, const void *vb)
@@ -568,23 +652,41 @@ static int cmp_relocs(const void *va, const void *vb)
 	return (*a == *b)? 0 : (*a > *b)? 1 : -1;
 }
 
-static void emit_relocs(int as_text)
+static int write32(unsigned int v, FILE *f)
+{
+	unsigned char buf[4];
+
+	put_unaligned_le32(v, buf);
+	return fwrite(buf, 1, 4, f) == 4 ? 0 : -1;
+}
+
+static void emit_relocs(int as_text, int use_real_mode)
 {
 	int i;
 	/* Count how many relocations I have and allocate space for them. */
 	reloc_count = 0;
-	walk_relocs(count_reloc);
+	walk_relocs(count_reloc, use_real_mode);
 	relocs = malloc(reloc_count * sizeof(relocs[0]));
 	if (!relocs) {
 		die("malloc of %d entries for relocs failed\n",
 			reloc_count);
 	}
+
+	relocs16 = malloc(reloc16_count * sizeof(relocs[0]));
+	if (!relocs16) {
+		die("malloc of %d entries for relocs16 failed\n",
+			reloc16_count);
+	}
 	/* Collect up the relocations */
 	reloc_idx = 0;
-	walk_relocs(collect_reloc);
+	walk_relocs(collect_reloc, use_real_mode);
+
+	if (reloc16_count && !use_real_mode)
+		die("Segment relocations found but --realmode not specified\n");
 
 	/* Order the relocations for more efficient processing */
 	qsort(relocs, reloc_count, sizeof(relocs[0]), cmp_relocs);
+	qsort(relocs16, reloc16_count, sizeof(relocs16[0]), cmp_relocs);
 
 	/* Print the relocations */
 	if (as_text) {
@@ -593,58 +695,83 @@ static void emit_relocs(int as_text)
 		 */
 		printf(".section \".data.reloc\",\"a\"\n");
 		printf(".balign 4\n");
-		for (i = 0; i < reloc_count; i++) {
-			printf("\t .long 0x%08lx\n", relocs[i]);
+		if (use_real_mode) {
+			printf("\t.long %lu\n", reloc16_count);
+			for (i = 0; i < reloc16_count; i++)
+				printf("\t.long 0x%08lx\n", relocs16[i]);
+			printf("\t.long %lu\n", reloc_count);
+			for (i = 0; i < reloc_count; i++) {
+				printf("\t.long 0x%08lx\n", relocs[i]);
+			}
+		} else {
+			/* Print a stop */
+			printf("\t.long 0x%08lx\n", (unsigned long)0);
+			for (i = 0; i < reloc_count; i++) {
+				printf("\t.long 0x%08lx\n", relocs[i]);
+			}
 		}
+
 		printf("\n");
 	}
 	else {
-		unsigned char buf[4];
-		/* Print a stop */
-		fwrite("\0\0\0\0", 4, 1, stdout);
-		/* Now print each relocation */
-		for (i = 0; i < reloc_count; i++) {
-			put_unaligned_le32(relocs[i], buf);
-			fwrite(buf, 4, 1, stdout);
+		if (use_real_mode) {
+			write32(reloc16_count, stdout);
+			for (i = 0; i < reloc16_count; i++)
+				write32(relocs16[i], stdout);
+			write32(reloc_count, stdout);
+
+			/* Now print each relocation */
+			for (i = 0; i < reloc_count; i++)
+				write32(relocs[i], stdout);
+		} else {
+			/* Print a stop */
+			write32(0, stdout);
+
+			/* Now print each relocation */
+			for (i = 0; i < reloc_count; i++) {
+				write32(relocs[i], stdout);
+			}
 		}
 	}
 }
 
 static void usage(void)
 {
-	die("relocs [--abs-syms |--abs-relocs | --text] vmlinux\n");
+	die("relocs [--abs-syms|--abs-relocs|--text|--realmode] vmlinux\n");
 }
 
 int main(int argc, char **argv)
 {
 	int show_absolute_syms, show_absolute_relocs;
-	int as_text;
+	int as_text, use_real_mode;
 	const char *fname;
 	FILE *fp;
 	int i;
 
-	regex_init();
-
 	show_absolute_syms = 0;
 	show_absolute_relocs = 0;
 	as_text = 0;
+	use_real_mode = 0;
 	fname = NULL;
 	for (i = 1; i < argc; i++) {
 		char *arg = argv[i];
 		if (*arg == '-') {
-			if (strcmp(argv[1], "--abs-syms") == 0) {
+			if (strcmp(arg, "--abs-syms") == 0) {
 				show_absolute_syms = 1;
 				continue;
 			}
-
-			if (strcmp(argv[1], "--abs-relocs") == 0) {
+			if (strcmp(arg, "--abs-relocs") == 0) {
 				show_absolute_relocs = 1;
 				continue;
 			}
-			else if (strcmp(argv[1], "--text") == 0) {
+			if (strcmp(arg, "--text") == 0) {
 				as_text = 1;
 				continue;
 			}
+			if (strcmp(arg, "--realmode") == 0) {
+				use_real_mode = 1;
+				continue;
+			}
 		}
 		else if (!fname) {
 			fname = arg;
@@ -655,6 +782,7 @@ int main(int argc, char **argv)
 	if (!fname) {
 		usage();
 	}
+	regex_init(use_real_mode);
 	fp = fopen(fname, "r");
 	if (!fp) {
 		die("Cannot open %s: %s\n",
@@ -673,6 +801,6 @@ int main(int argc, char **argv)
 		print_absolute_relocs();
 		return 0;
 	}
-	emit_relocs(as_text);
+	emit_relocs(as_text, use_real_mode);
 	return 0;
 }