Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (185 commits)
  powerpc: fix compile error with 85xx/p1010rdb.c
  powerpc: fix compile error with 85xx/p1023_rds.c
  powerpc/fsl: add MSI support for the Freescale hypervisor
  arch/powerpc/sysdev/fsl_rmu.c: introduce missing kfree
  powerpc/fsl: Add support for Integrated Flash Controller
  powerpc/fsl: update compatiable on fsl 16550 uart nodes
  powerpc/85xx: fix PCI and localbus properties in p1022ds.dts
  powerpc/85xx: re-enable ePAPR byte channel driver in corenet32_smp_defconfig
  powerpc/fsl: Update defconfigs to enable some standard FSL HW features
  powerpc: Add TBI PHY node to first MDIO bus
  sbc834x: put full compat string in board match check
  powerpc/fsl-pci: Allow 64-bit PCIe devices to DMA to any memory address
  powerpc: Fix unpaired probe_hcall_entry and probe_hcall_exit
  offb: Fix setting of the pseudo-palette for >8bpp
  offb: Add palette hack for qemu "standard vga" framebuffer
  offb: Fix bug in calculating requested vram size
  powerpc/boot: Change the WARN to INFO for boot wrapper overlap message
  powerpc/44x: Fix build error on currituck platform
  powerpc/boot: Change the load address for the wrapper to fit the kernel
  powerpc/44x: Enable CRASH_DUMP for 440x
  ...

Fix up a trivial conflict in arch/powerpc/include/asm/cputime.h due to
the additional sparse-checking code for cputime_t.

26 files changed, 772 insertions, 334 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index ce4f7f17911..ee728e433aa 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -85,6 +85,8 @@ extra-$(CONFIG_FSL_BOOKE)	:= head_fsl_booke.o
 extra-$(CONFIG_8xx)		:= head_8xx.o
 extra-y				+= vmlinux.lds
 
+obj-$(CONFIG_RELOCATABLE_PPC32)	+= reloc_32.o
+
 obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o
 obj-$(CONFIG_PPC64)		+= dma-iommu.o iommu.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 7c5324f1ec9..04caee7d9bc 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -208,6 +208,7 @@ int main(void)
 	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
 	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
+	DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost));
 #endif /* CONFIG_PPC64 */
 
 	/* RTAS */
diff --git a/arch/powerpc/kernel/cpu_setup_a2.S b/arch/powerpc/kernel/cpu_setup_a2.S
index 7f818feaa7a..ebc62f42a23 100644
--- a/arch/powerpc/kernel/cpu_setup_a2.S
+++ b/arch/powerpc/kernel/cpu_setup_a2.S
@@ -41,11 +41,16 @@ _GLOBAL(__setup_cpu_a2)
 	 * core local but doing it always won't hurt
 	 */
 
-#ifdef CONFIG_PPC_WSP_COPRO
+#ifdef CONFIG_PPC_ICSWX
 	/* Make sure ACOP starts out as zero */
 	li	r3,0
 	mtspr   SPRN_ACOP,r3
 
+	/* Skip the following if we are in Guest mode */
+	mfmsr	r3
+	andis.	r0,r3,MSR_GS@h
+	bne	_icswx_skip_guest
+
 	/* Enable icswx instruction */
 	mfspr   r3,SPRN_A2_CCR2
 	ori     r3,r3,A2_CCR2_ENABLE_ICSWX
@@ -54,7 +59,8 @@ _GLOBAL(__setup_cpu_a2)
 	/* Unmask all CTs in HACOP */
 	li      r3,-1
 	mtspr   SPRN_HACOP,r3
-#endif /* CONFIG_PPC_WSP_COPRO */
+_icswx_skip_guest:
+#endif /* CONFIG_PPC_ICSWX */
 
 	/* Enable doorbell */
 	mfspr   r3,SPRN_A2_CCR2
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index edae5bb06f1..81db9e2a8a2 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -1505,6 +1505,19 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check		= machine_check_4xx,
 		.platform		= "ppc405",
 	},
+	{	/* APM8018X */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x7ff11432,
+		.cpu_name		= "APM8018X",
+		.cpu_features		= CPU_FTRS_40X,
+		.cpu_user_features	= PPC_FEATURE_32 |
+			PPC_FEATURE_HAS_MMU | PPC_FEATURE_HAS_4xxMAC,
+		.mmu_features		= MMU_FTR_TYPE_40x,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 32,
+		.machine_check		= machine_check_4xx,
+		.platform		= "ppc405",
+	},
 	{	/* default match */
 		.pvr_mask		= 0x00000000,
 		.pvr_value		= 0x00000000,
@@ -1830,6 +1843,20 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check		= machine_check_47x,
 		.platform		= "ppc470",
 	},
+	{ /* 476fpe */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x7ff50000,
+		.cpu_name		= "476fpe",
+		.cpu_features		= CPU_FTRS_47X | CPU_FTR_476_DD2,
+		.cpu_user_features	= COMMON_USER_BOOKE |
+			PPC_FEATURE_HAS_FPU,
+		.mmu_features		= MMU_FTR_TYPE_47x |
+			MMU_FTR_USE_TLBIVAX_BCAST | MMU_FTR_LOCK_BCAST_INVAL,
+		.icache_bsize		= 32,
+		.dcache_bsize		= 128,
+		.machine_check		= machine_check_47x,
+		.platform		= "ppc470",
+	},
 	{ /* 476 iss */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x00050000,
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index d879809d5c4..28be3452e67 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -10,85 +10,85 @@
  *
  */
 
-#undef DEBUG
-
 #include <linux/kernel.h>
 #include <linux/smp.h>
 #include <linux/reboot.h>
 #include <linux/kexec.h>
-#include <linux/bootmem.h>
 #include <linux/export.h>
 #include <linux/crash_dump.h>
 #include <linux/delay.h>
-#include <linux/elf.h>
-#include <linux/elfcore.h>
 #include <linux/init.h>
 #include <linux/irq.h>
 #include <linux/types.h>
-#include <linux/memblock.h>
 
 #include <asm/processor.h>
 #include <asm/machdep.h>
 #include <asm/kexec.h>
 #include <asm/kdump.h>
 #include <asm/prom.h>
-#include <asm/firmware.h>
 #include <asm/smp.h>
 #include <asm/system.h>
 #include <asm/setjmp.h>
 
-#ifdef DEBUG
-#include <asm/udbg.h>
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
+/*
+ * The primary CPU waits a while for all secondary CPUs to enter. This is to
+ * avoid sending an IPI if the secondary CPUs are entering
+ * crash_kexec_secondary on their own (eg via a system reset).
+ *
+ * The secondary timeout has to be longer than the primary. Both timeouts are
+ * in milliseconds.
+ */
+#define PRIMARY_TIMEOUT		500
+#define SECONDARY_TIMEOUT	1000
 
-/* This keeps a track of which one is crashing cpu. */
+#define IPI_TIMEOUT		10000
+#define REAL_MODE_TIMEOUT	10000
+
+/* This keeps a track of which one is the crashing cpu. */
 int crashing_cpu = -1;
-static cpumask_t cpus_in_crash = CPU_MASK_NONE;
-cpumask_t cpus_in_sr = CPU_MASK_NONE;
+static atomic_t cpus_in_crash;
+static int time_to_dump;
 
 #define CRASH_HANDLER_MAX 3
 /* NULL terminated list of shutdown handles */
 static crash_shutdown_t crash_shutdown_handles[CRASH_HANDLER_MAX+1];
 static DEFINE_SPINLOCK(crash_handlers_lock);
 
+static unsigned long crash_shutdown_buf[JMP_BUF_LEN];
+static int crash_shutdown_cpu = -1;
+
+static int handle_fault(struct pt_regs *regs)
+{
+	if (crash_shutdown_cpu == smp_processor_id())
+		longjmp(crash_shutdown_buf, 1);
+	return 0;
+}
+
 #ifdef CONFIG_SMP
-static atomic_t enter_on_soft_reset = ATOMIC_INIT(0);
 
 void crash_ipi_callback(struct pt_regs *regs)
 {
+	static cpumask_t cpus_state_saved = CPU_MASK_NONE;
+
 	int cpu = smp_processor_id();
 
 	if (!cpu_online(cpu))
 		return;
 
 	hard_irq_disable();
-	if (!cpumask_test_cpu(cpu, &cpus_in_crash))
+	if (!cpumask_test_cpu(cpu, &cpus_state_saved)) {
 		crash_save_cpu(regs, cpu);
-	cpumask_set_cpu(cpu, &cpus_in_crash);
-
-	/*
-	 * Entered via soft-reset - could be the kdump
-	 * process is invoked using soft-reset or user activated
-	 * it if some CPU did not respond to an IPI.
-	 * For soft-reset, the secondary CPU can enter this func
-	 * twice. 1 - using IPI, and 2. soft-reset.
-	 * Tell the kexec CPU that entered via soft-reset and ready
-	 * to go down.
-	 */
-	if (cpumask_test_cpu(cpu, &cpus_in_sr)) {
-		cpumask_clear_cpu(cpu, &cpus_in_sr);
-		atomic_inc(&enter_on_soft_reset);
+		cpumask_set_cpu(cpu, &cpus_state_saved);
 	}
 
+	atomic_inc(&cpus_in_crash);
+	smp_mb__after_atomic_inc();
+
 	/*
 	 * Starting the kdump boot.
 	 * This barrier is needed to make sure that all CPUs are stopped.
-	 * If not, soft-reset will be invoked to bring other CPUs.
 	 */
-	while (!cpumask_test_cpu(crashing_cpu, &cpus_in_crash))
+	while (!time_to_dump)
 		cpu_relax();
 
 	if (ppc_md.kexec_cpu_down)
@@ -103,106 +103,99 @@ void crash_ipi_callback(struct pt_regs *regs)
 	/* NOTREACHED */
 }
 
-/*
- * Wait until all CPUs are entered via soft-reset.
- */
-static void crash_soft_reset_check(int cpu)
-{
-	unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */
-
-	cpumask_clear_cpu(cpu, &cpus_in_sr);
-	while (atomic_read(&enter_on_soft_reset) != ncpus)
-		cpu_relax();
-}
-
-
 static void crash_kexec_prepare_cpus(int cpu)
 {
 	unsigned int msecs;
-
 	unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */
+	int tries = 0;
+	int (*old_handler)(struct pt_regs *regs);
+
+	printk(KERN_EMERG "Sending IPI to other CPUs\n");
 
 	crash_send_ipi(crash_ipi_callback);
 	smp_wmb();
 
+again:
 	/*
 	 * FIXME: Until we will have the way to stop other CPUs reliably,
 	 * the crash CPU will send an IPI and wait for other CPUs to
 	 * respond.
-	 * Delay of at least 10 seconds.
 	 */
-	printk(KERN_EMERG "Sending IPI to other cpus...\n");
-	msecs = 10000;
-	while ((cpumask_weight(&cpus_in_crash) < ncpus) && (--msecs > 0)) {
-		cpu_relax();
+	msecs = IPI_TIMEOUT;
+	while ((atomic_read(&cpus_in_crash) < ncpus) && (--msecs > 0))
 		mdelay(1);
-	}
 
 	/* Would it be better to replace the trap vector here? */
 
+	if (atomic_read(&cpus_in_crash) >= ncpus) {
+		printk(KERN_EMERG "IPI complete\n");
+		return;
+	}
+
+	printk(KERN_EMERG "ERROR: %d cpu(s) not responding\n",
+		ncpus - atomic_read(&cpus_in_crash));
+
 	/*
-	 * FIXME: In case if we do not get all CPUs, one possibility: ask the
-	 * user to do soft reset such that we get all.
-	 * Soft-reset will be used until better mechanism is implemented.
+	 * If we have a panic timeout set then we can't wait indefinitely
+	 * for someone to activate system reset. We also give up on the
+	 * second time through if system reset fail to work.
 	 */
-	if (cpumask_weight(&cpus_in_crash) < ncpus) {
-		printk(KERN_EMERG "done waiting: %d cpu(s) not responding\n",
-			ncpus - cpumask_weight(&cpus_in_crash));
-		printk(KERN_EMERG "Activate soft-reset to stop other cpu(s)\n");
-		cpumask_clear(&cpus_in_sr);
-		atomic_set(&enter_on_soft_reset, 0);
-		while (cpumask_weight(&cpus_in_crash) < ncpus)
-			cpu_relax();
-	}
+	if ((panic_timeout > 0) || (tries > 0))
+		return;
+
 	/*
-	 * Make sure all CPUs are entered via soft-reset if the kdump is
-	 * invoked using soft-reset.
+	 * A system reset will cause all CPUs to take an 0x100 exception.
+	 * The primary CPU returns here via setjmp, and the secondary
+	 * CPUs reexecute the crash_kexec_secondary path.
 	 */
-	if (cpumask_test_cpu(cpu, &cpus_in_sr))
-		crash_soft_reset_check(cpu);
-	/* Leave the IPI callback set */
+	old_handler = __debugger;
+	__debugger = handle_fault;
+	crash_shutdown_cpu = smp_processor_id();
+
+	if (setjmp(crash_shutdown_buf) == 0) {
+		printk(KERN_EMERG "Activate system reset (dumprestart) "
+				  "to stop other cpu(s)\n");
+
+		/*
+		 * A system reset will force all CPUs to execute the
+		 * crash code again. We need to reset cpus_in_crash so we
+		 * wait for everyone to do this.
+		 */
+		atomic_set(&cpus_in_crash, 0);
+		smp_mb();
+
+		while (atomic_read(&cpus_in_crash) < ncpus)
+			cpu_relax();
+	}
+
+	crash_shutdown_cpu = -1;
+	__debugger = old_handler;
+
+	tries++;
+	goto again;
 }
 
 /*
- * This function will be called by secondary cpus or by kexec cpu
- * if soft-reset is activated to stop some CPUs.
+ * This function will be called by secondary cpus.
  */
 void crash_kexec_secondary(struct pt_regs *regs)
 {
-	int cpu = smp_processor_id();
 	unsigned long flags;
-	int msecs = 5;
+	int msecs = SECONDARY_TIMEOUT;
 
 	local_irq_save(flags);
-	/* Wait 5ms if the kexec CPU is not entered yet. */
+
+	/* Wait for the primary crash CPU to signal its progress */
 	while (crashing_cpu < 0) {
 		if (--msecs < 0) {
-			/*
-			 * Either kdump image is not loaded or
-			 * kdump process is not started - Probably xmon
-			 * exited using 'x'(exit and recover) or
-			 * kexec_should_crash() failed for all running tasks.
-			 */
-			cpumask_clear_cpu(cpu, &cpus_in_sr);
+			/* No response, kdump image may not have been loaded */
 			local_irq_restore(flags);
 			return;
 		}
+
 		mdelay(1);
-		cpu_relax();
-	}
-	if (cpu == crashing_cpu) {
-		/*
-		 * Panic CPU will enter this func only via soft-reset.
-		 * Wait until all secondary CPUs entered and
-		 * then start kexec boot.
-		 */
-		crash_soft_reset_check(cpu);
-		cpumask_set_cpu(crashing_cpu, &cpus_in_crash);
-		if (ppc_md.kexec_cpu_down)
-			ppc_md.kexec_cpu_down(1, 0);
-		machine_kexec(kexec_crash_image);
-		/* NOTREACHED */
 	}
+
 	crash_ipi_callback(regs);
 }
 
@@ -211,7 +204,7 @@ void crash_kexec_secondary(struct pt_regs *regs)
 static void crash_kexec_prepare_cpus(int cpu)
 {
 	/*
-	 * move the secondarys to us so that we can copy
+	 * move the secondaries to us so that we can copy
 	 * the new kernel 0-0x100 safely
 	 *
 	 * do this if kexec in setup.c ?
@@ -225,7 +218,6 @@ static void crash_kexec_prepare_cpus(int cpu)
 
 void crash_kexec_secondary(struct pt_regs *regs)
 {
-	cpumask_clear(&cpus_in_sr);
 }
 #endif	/* CONFIG_SMP */
 
@@ -236,7 +228,7 @@ static void crash_kexec_wait_realmode(int cpu)
 	unsigned int msecs;
 	int i;
 
-	msecs = 10000;
+	msecs = REAL_MODE_TIMEOUT;
 	for (i=0; i < nr_cpu_ids && msecs > 0; i++) {
 		if (i == cpu)
 			continue;
@@ -308,22 +300,11 @@ int crash_shutdown_unregister(crash_shutdown_t handler)
 }
 EXPORT_SYMBOL(crash_shutdown_unregister);
 
-static unsigned long crash_shutdown_buf[JMP_BUF_LEN];
-static int crash_shutdown_cpu = -1;
-
-static int handle_fault(struct pt_regs *regs)
-{
-	if (crash_shutdown_cpu == smp_processor_id())
-		longjmp(crash_shutdown_buf, 1);
-	return 0;
-}
-
 void default_machine_crash_shutdown(struct pt_regs *regs)
 {
 	unsigned int i;
 	int (*old_handler)(struct pt_regs *regs);
 
-
 	/*
 	 * This function is only called after the system
 	 * has panicked or is otherwise in a critical state.
@@ -341,15 +322,26 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	 * such that another IPI will not be sent.
 	 */
 	crashing_cpu = smp_processor_id();
-	crash_save_cpu(regs, crashing_cpu);
+
+	/*
+	 * If we came in via system reset, wait a while for the secondary
+	 * CPUs to enter.
+	 */
+	if (TRAP(regs) == 0x100)
+		mdelay(PRIMARY_TIMEOUT);
+
 	crash_kexec_prepare_cpus(crashing_cpu);
-	cpumask_set_cpu(crashing_cpu, &cpus_in_crash);
+
+	crash_save_cpu(regs, crashing_cpu);
+
+	time_to_dump = 1;
+
 	crash_kexec_wait_realmode(crashing_cpu);
 
 	machine_kexec_mask_interrupts();
 
 	/*
-	 * Call registered shutdown routines savely.  Swap out
+	 * Call registered shutdown routines safely.  Swap out
 	 * __debugger_fault_handler, and replace on exit.
 	 */
 	old_handler = __debugger_fault_handler;
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 424afb6b8fb..b3ba5163eae 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -28,7 +28,7 @@
 #define DBG(fmt...)
 #endif
 
-#ifndef CONFIG_RELOCATABLE
+#ifndef CONFIG_NONSTATIC_KERNEL
 void __init reserve_kdump_trampoline(void)
 {
 	memblock_reserve(0, KDUMP_RESERVE_LIMIT);
@@ -67,7 +67,7 @@ void __init setup_kdump_trampoline(void)
 
 	DBG(" <- setup_kdump_trampoline()\n");
 }
-#endif /* CONFIG_RELOCATABLE */
+#endif /* CONFIG_NONSTATIC_KERNEL */
 
 static int __init parse_savemaxmem(char *p)
 {
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index cf9c69b9189..d4be7bb3dbd 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -65,7 +65,7 @@ BEGIN_FTR_SECTION
 	lbz	r0,PACAPROCSTART(r13)
 	cmpwi	r0,0x80
 	bne	1f
-	li	r0,0
+	li	r0,1
 	stb	r0,PACAPROCSTART(r13)
 	b	kvm_start_guest
 1:
diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
index b725dab0f88..7dd2981bcc5 100644
--- a/arch/powerpc/kernel/head_44x.S
+++ b/arch/powerpc/kernel/head_44x.S
@@ -64,6 +64,35 @@ _ENTRY(_start);
 	mr	r31,r3		/* save device tree ptr */
 	li	r24,0		/* CPU number */
 
+#ifdef CONFIG_RELOCATABLE
+/*
+ * Relocate ourselves to the current runtime address.
+ * This is called only by the Boot CPU.
+ * "relocate" is called with our current runtime virutal
+ * address.
+ * r21 will be loaded with the physical runtime address of _stext
+ */
+	bl	0f				/* Get our runtime address */
+0:	mflr	r21				/* Make it accessible */
+	addis	r21,r21,(_stext - 0b)@ha
+	addi	r21,r21,(_stext - 0b)@l 	/* Get our current runtime base */
+
+	/*
+	 * We have the runtime (virutal) address of our base.
+	 * We calculate our shift of offset from a 256M page.
+	 * We could map the 256M page we belong to at PAGE_OFFSET and
+	 * get going from there.
+	 */
+	lis	r4,KERNELBASE@h
+	ori	r4,r4,KERNELBASE@l
+	rlwinm	r6,r21,0,4,31			/* r6 = PHYS_START % 256M */
+	rlwinm	r5,r4,0,4,31			/* r5 = KERNELBASE % 256M */
+	subf	r3,r5,r6			/* r3 = r6 - r5 */
+	add	r3,r4,r3			/* Required Virutal Address */
+
+	bl	relocate
+#endif
+
 	bl	init_cpu_state
 
 	/*
@@ -88,6 +117,65 @@ _ENTRY(_start);
 
 #ifdef CONFIG_RELOCATABLE
 	/*
+	 * Relocatable kernel support based on processing of dynamic
+	 * relocation entries.
+	 *
+	 * r25 will contain RPN/ERPN for the start address of memory
+	 * r21 will contain the current offset of _stext
+	 */
+	lis	r3,kernstart_addr@ha
+	la	r3,kernstart_addr@l(r3)
+
+	/*
+	 * Compute the kernstart_addr.
+	 * kernstart_addr => (r6,r8)
+	 * kernstart_addr & ~0xfffffff => (r6,r7)
+	 */
+	rlwinm	r6,r25,0,28,31	/* ERPN. Bits 32-35 of Address */
+	rlwinm	r7,r25,0,0,3	/* RPN - assuming 256 MB page size */
+	rlwinm	r8,r21,0,4,31	/* r8 = (_stext & 0xfffffff) */
+	or	r8,r7,r8	/* Compute the lower 32bit of kernstart_addr */
+
+	/* Store kernstart_addr */
+	stw	r6,0(r3)	/* higher 32bit */
+	stw	r8,4(r3)	/* lower 32bit  */
+
+	/*
+	 * Compute the virt_phys_offset :
+	 * virt_phys_offset = stext.run - kernstart_addr
+	 *
+	 * stext.run = (KERNELBASE & ~0xfffffff) + (kernstart_addr & 0xfffffff)
+	 * When we relocate, we have :
+	 *
+	 *	(kernstart_addr & 0xfffffff) = (stext.run & 0xfffffff)
+	 *
+	 * hence:
+	 *  virt_phys_offset = (KERNELBASE & ~0xfffffff) - (kernstart_addr & ~0xfffffff)
+	 *
+	 */
+
+	/* KERNELBASE&~0xfffffff => (r4,r5) */
+	li	r4, 0		/* higer 32bit */
+	lis	r5,KERNELBASE@h
+	rlwinm	r5,r5,0,0,3	/* Align to 256M, lower 32bit */
+
+	/*
+	 * 64bit subtraction.
+	 */
+	subfc	r5,r7,r5
+	subfe	r4,r6,r4
+
+	/* Store virt_phys_offset */
+	lis	r3,virt_phys_offset@ha
+	la	r3,virt_phys_offset@l(r3)
+
+	stw	r4,0(r3)
+	stw	r5,4(r3)
+
+#elif defined(CONFIG_DYNAMIC_MEMSTART)
+	/*
+	 * Mapping based, page aligned dynamic kernel loading.
+	 *
 	 * r25 will contain RPN/ERPN for the start address of memory
 	 *
 	 * Add the difference between KERNELBASE and PAGE_OFFSET to the
@@ -732,6 +820,8 @@ _GLOBAL(init_cpu_state)
 	/* We use the PVR to differenciate 44x cores from 476 */
 	mfspr	r3,SPRN_PVR
 	srwi	r3,r3,16
+	cmplwi	cr0,r3,PVR_476FPE@h
+	beq	head_start_47x
 	cmplwi	cr0,r3,PVR_476@h
 	beq	head_start_47x
 	cmplwi	cr0,r3,PVR_476_ISS@h
@@ -800,12 +890,29 @@ skpinv:	addi	r4,r4,1				/* Increment */
 /*
  * Configure and load pinned entry into TLB slot 63.
  */
+#ifdef CONFIG_NONSTATIC_KERNEL
+	/*
+	 * In case of a NONSTATIC_KERNEL we reuse the TLB XLAT
+	 * entries of the initial mapping set by the boot loader.
+	 * The XLAT entry is stored in r25
+	 */
+
+	/* Read the XLAT entry for our current mapping */
+	tlbre	r25,r23,PPC44x_TLB_XLAT
+
+	lis	r3,KERNELBASE@h
+	ori	r3,r3,KERNELBASE@l
+
+	/* Use our current RPN entry */
+	mr	r4,r25
+#else
 
 	lis	r3,PAGE_OFFSET@h
 	ori	r3,r3,PAGE_OFFSET@l
 
 	/* Kernel is at the base of RAM */
 	li r4, 0			/* Load the kernel physical address */
+#endif
 
 	/* Load the kernel PID = 0 */
 	li	r0,0
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 9f5d210ddf3..d5d78c4ceef 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -197,7 +197,7 @@ _ENTRY(__early_start)
 
 	bl	early_init
 
-#ifdef CONFIG_RELOCATABLE
+#ifdef CONFIG_DYNAMIC_MEMSTART
 	lis	r3,kernstart_addr@ha
 	la	r3,kernstart_addr@l(r3)
 #ifdef CONFIG_PHYS_64BIT
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 9c3cd490b1b..7c66ce13da8 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -39,9 +39,13 @@
 #define cpu_should_die()	0
 #endif
 
+unsigned long cpuidle_disable = IDLE_NO_OVERRIDE;
+EXPORT_SYMBOL(cpuidle_disable);
+
 static int __init powersave_off(char *arg)
 {
 	ppc_md.power_save = NULL;
+	cpuidle_disable = IDLE_POWERSAVE_OFF;
 	return 0;
 }
 __setup("powersave=off", powersave_off);
@@ -113,6 +117,29 @@ void cpu_idle(void)
 	}
 }
 
+
+/*
+ * cpu_idle_wait - Used to ensure that all the CPUs come out of the old
+ * idle loop and start using the new idle loop.
+ * Required while changing idle handler on SMP systems.
+ * Caller must have changed idle handler to the new value before the call.
+ * This window may be larger on shared systems.
+ */
+void cpu_idle_wait(void)
+{
+	int cpu;
+	smp_mb();
+
+	/* kick all the CPUs so that they exit out of old idle routine */
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		if (cpu != smp_processor_id())
+			smp_send_reschedule(cpu);
+	}
+	put_online_cpus();
+}
+EXPORT_SYMBOL_GPL(cpu_idle_wait);
+
 int powersave_nap;
 
 #ifdef CONFIG_SYSCTL
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 3a70845a51c..fcdff198da4 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -54,6 +54,7 @@ _GLOBAL(power7_idle)
 	li	r0,0
 	stb	r0,PACASOFTIRQEN(r13)	/* we'll hard-enable shortly */
 	stb	r0,PACAHARDIRQEN(r13)
+	stb	r0,PACA_NAPSTATELOST(r13)
 
 	/* Continue saving state */
 	SAVE_GPR(2, r1)
@@ -86,6 +87,9 @@ _GLOBAL(power7_wakeup_loss)
 	rfid
 
 _GLOBAL(power7_wakeup_noloss)
+	lbz	r0,PACA_NAPSTATELOST(r13)
+	cmpwi	r0,0
+	bne	.power7_wakeup_loss
 	ld	r1,PACAR1(r13)
 	ld	r4,_MSR(r1)
 	ld	r5,_NIP(r1)
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 5c3c46948d9..701d4aceb4f 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -115,6 +115,15 @@ static inline notrace void set_soft_enabled(unsigned long enable)
 	: : "r" (enable), "i" (offsetof(struct paca_struct, soft_enabled)));
 }
 
+static inline notrace void decrementer_check_overflow(void)
+{
+	u64 now = get_tb_or_rtc();
+	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+
+	if (now >= *next_tb)
+		set_dec(1);
+}
+
 notrace void arch_local_irq_restore(unsigned long en)
 {
 	/*
@@ -164,24 +173,21 @@ notrace void arch_local_irq_restore(unsigned long en)
 	 */
 	local_paca->hard_enabled = en;
 
-#ifndef CONFIG_BOOKE
-	/* On server, re-trigger the decrementer if it went negative since
-	 * some processors only trigger on edge transitions of the sign bit.
-	 *
-	 * BookE has a level sensitive decrementer (latches in TSR) so we
-	 * don't need that
+	/*
+	 * Trigger the decrementer if we have a pending event. Some processors
+	 * only trigger on edge transitions of the sign bit. We might also
+	 * have disabled interrupts long enough that the decrementer wrapped
+	 * to positive.
 	 */
-	if ((int)mfspr(SPRN_DEC) < 0)
-		mtspr(SPRN_DEC, 1);
-#endif /* CONFIG_BOOKE */
+	decrementer_check_overflow();
 
 	/*
 	 * Force the delivery of pending soft-disabled interrupts on PS3.
 	 * Any HV call will have this side effect.
 	 */
 	if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
-		u64 tmp;
-		lv1_get_version_info(&tmp);
+		u64 tmp, tmp2;
+		lv1_get_version_info(&tmp, &tmp2);
 	}
 
 	__hard_irq_enable();
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index a2158a395d9..c957b1202bd 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -125,7 +125,7 @@ void __init reserve_crashkernel(void)
 
 	crash_size = resource_size(&crashk_res);
 
-#ifndef CONFIG_RELOCATABLE
+#ifndef CONFIG_NONSTATIC_KERNEL
 	if (crashk_res.start != KDUMP_KERNELBASE)
 		printk("Crash kernel location must be 0x%x\n",
 				KDUMP_KERNELBASE);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 458ed3bee66..fa4a573d671 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -214,7 +214,7 @@ char __devinit *pcibios_setup(char *str)
  * If the interrupt is used, then gets the interrupt line from the
  * openfirmware and sets it in the pci_dev and pci_config line.
  */
-int pci_read_irq_line(struct pci_dev *pci_dev)
+static int pci_read_irq_line(struct pci_dev *pci_dev)
 {
 	struct of_irq oirq;
 	unsigned int virq;
@@ -283,7 +283,6 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
 
 	return 0;
 }
-EXPORT_SYMBOL(pci_read_irq_line);
 
 /*
  * Platform support for /proc/bus/pci/X/Y mmap()s,
@@ -921,18 +920,22 @@ static void __devinit pcibios_fixup_resources(struct pci_dev *dev)
 		struct resource *res = dev->resource + i;
 		if (!res->flags)
 			continue;
-		/* On platforms that have PCI_PROBE_ONLY set, we don't
-		 * consider 0 as an unassigned BAR value. It's technically
-		 * a valid value, but linux doesn't like it... so when we can
-		 * re-assign things, we do so, but if we can't, we keep it
-		 * around and hope for the best...
+
+		/* If we're going to re-assign everything, we mark all resources
+		 * as unset (and 0-base them). In addition, we mark BARs starting
+		 * at 0 as unset as well, except if PCI_PROBE_ONLY is also set
+		 * since in that case, we don't want to re-assign anything
 		 */
-		if (res->start == 0 && !pci_has_flag(PCI_PROBE_ONLY)) {
-			pr_debug("PCI:%s Resource %d %016llx-%016llx [%x] is unassigned\n",
-				 pci_name(dev), i,
-				 (unsigned long long)res->start,
-				 (unsigned long long)res->end,
-				 (unsigned int)res->flags);
+		if (pci_has_flag(PCI_REASSIGN_ALL_RSRC) ||
+		    (res->start == 0 && !pci_has_flag(PCI_PROBE_ONLY))) {
+			/* Only print message if not re-assigning */
+			if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC))
+				pr_debug("PCI:%s Resource %d %016llx-%016llx [%x] "
+					 "is unassigned\n",
+					 pci_name(dev), i,
+					 (unsigned long long)res->start,
+					 (unsigned long long)res->end,
+					 (unsigned int)res->flags);
 			res->end -= res->start;
 			res->start = 0;
 			res->flags |= IORESOURCE_UNSET;
@@ -1042,6 +1045,16 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus)
 		if (i >= 3 && bus->self->transparent)
 			continue;
 
+		/* If we are going to re-assign everything, mark the resource
+		 * as unset and move it down to 0
+		 */
+		if (pci_has_flag(PCI_REASSIGN_ALL_RSRC)) {
+			res->flags |= IORESOURCE_UNSET;
+			res->end -= res->start;
+			res->start = 0;
+			continue;
+		}
+
 		pr_debug("PCI:%s Bus rsrc %d %016llx-%016llx [%x] fixup...\n",
 			 pci_name(dev), i,
 			 (unsigned long long)res->start,\
@@ -1262,18 +1275,15 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus)
 	pci_bus_for_each_resource(bus, res, i) {
 		if (!res || !res->flags || res->start > res->end || res->parent)
 			continue;
+
+		/* If the resource was left unset at this point, we clear it */
+		if (res->flags & IORESOURCE_UNSET)
+			goto clear_resource;
+
 		if (bus->parent == NULL)
 			pr = (res->flags & IORESOURCE_IO) ?
 				&ioport_resource : &iomem_resource;
 		else {
-			/* Don't bother with non-root busses when
-			 * re-assigning all resources. We clear the
-			 * resource flags as if they were colliding
-			 * and as such ensure proper re-allocation
-			 * later.
-			 */
-			if (pci_has_flag(PCI_REASSIGN_ALL_RSRC))
-				goto clear_resource;
 			pr = pci_find_parent_resource(bus->self, res);
 			if (pr == res) {
 				/* this happens when the generic PCI
@@ -1304,9 +1314,9 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			if (reparent_resources(pr, res) == 0)
 				continue;
 		}
-		printk(KERN_WARNING "PCI: Cannot allocate resource region "
-		       "%d of PCI bridge %d, will remap\n", i, bus->number);
-clear_resource:
+		pr_warning("PCI: Cannot allocate resource region "
+			   "%d of PCI bridge %d, will remap\n", i, bus->number);
+	clear_resource:
 		res->start = res->end = 0;
 		res->flags = 0;
 	}
@@ -1451,16 +1461,11 @@ void __init pcibios_resource_survey(void)
 {
 	struct pci_bus *b;
 
-	/* Allocate and assign resources. If we re-assign everything, then
-	 * we skip the allocate phase
-	 */
+	/* Allocate and assign resources */
 	list_for_each_entry(b, &pci_root_buses, node)
 		pcibios_allocate_bus_resources(b);
-
-	if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC)) {
-		pcibios_allocate_resources(0);
-		pcibios_allocate_resources(1);
-	}
+	pcibios_allocate_resources(0);
+	pcibios_allocate_resources(1);
 
 	/* Before we start assigning unassigned resource, we try to reserve
 	 * the low IO area and the VGA memory area if they intersect the
@@ -1732,6 +1737,12 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose)
 	if (mode == PCI_PROBE_NORMAL)
 		hose->last_busno = bus->subordinate = pci_scan_child_bus(bus);
 
+	/* Platform gets a chance to do some global fixups before
+	 * we proceed to resource allocation
+	 */
+	if (ppc_md.pcibios_fixup_phb)
+		ppc_md.pcibios_fixup_phb(hose);
+
 	/* Configure PCI Express settings */
 	if (bus && !pci_has_flag(PCI_PROBE_ONLY)) {
 		struct pci_bus *child;
@@ -1747,10 +1758,13 @@ void __devinit pcibios_scan_phb(struct pci_controller *hose)
 static void fixup_hide_host_resource_fsl(struct pci_dev *dev)
 {
 	int i, class = dev->class >> 8;
+	/* When configured as agent, programing interface = 1 */
+	int prog_if = dev->class & 0xf;
 
 	if ((class == PCI_CLASS_PROCESSOR_POWERPC ||
 	     class == PCI_CLASS_BRIDGE_OTHER) &&
 		(dev->hdr_type == PCI_HEADER_TYPE_NORMAL) &&
+		(prog_if == 0) &&
 		(dev->bus->parent == NULL)) {
 		for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
 			dev->resource[i].start = 0;
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 4e69deb89b3..dd9e4a04bf7 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -50,6 +50,9 @@ void * __devinit update_dn_pci_info(struct device_node *dn, void *data)
 	dn->data = pdn;
 	pdn->node = dn;
 	pdn->phb = phb;
+#ifdef CONFIG_PPC_POWERNV
+	pdn->pe_number = IODA_INVALID_PE;
+#endif
 	regs = of_get_property(dn, "reg", NULL);
 	if (regs) {
 		/* First register entry is addr (00BBSS00)  */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 6457574c0b2..ebe5766781a 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -584,16 +584,32 @@ static struct regbit {
 	unsigned long bit;
 	const char *name;
 } msr_bits[] = {
+#if defined(CONFIG_PPC64) && !defined(CONFIG_BOOKE)
+	{MSR_SF,	"SF"},
+	{MSR_HV,	"HV"},
+#endif
+	{MSR_VEC,	"VEC"},
+	{MSR_VSX,	"VSX"},
+#ifdef CONFIG_BOOKE
+	{MSR_CE,	"CE"},
+#endif
 	{MSR_EE,	"EE"},
 	{MSR_PR,	"PR"},
 	{MSR_FP,	"FP"},
-	{MSR_VEC,	"VEC"},
-	{MSR_VSX,	"VSX"},
 	{MSR_ME,	"ME"},
-	{MSR_CE,	"CE"},
+#ifdef CONFIG_BOOKE
 	{MSR_DE,	"DE"},
+#else
+	{MSR_SE,	"SE"},
+	{MSR_BE,	"BE"},
+#endif
 	{MSR_IR,	"IR"},
 	{MSR_DR,	"DR"},
+	{MSR_PMM,	"PMM"},
+#ifndef CONFIG_BOOKE
+	{MSR_RI,	"RI"},
+	{MSR_LE,	"LE"},
+#endif
 	{0,		NULL}
 };
 
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index cc584865b3d..eca626ea3f2 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -742,7 +742,7 @@ static unsigned char ibm_architecture_vec[] = {
 	W(0xffffffff),			/* virt_base */
 	W(0xffffffff),			/* virt_size */
 	W(0xffffffff),			/* load_base */
-	W(64),				/* 64MB min RMA */
+	W(256),				/* 256MB min RMA */
 	W(0xffffffff),			/* full client load */
 	0,				/* min RMA percentage of total RAM */
 	48,				/* max log_2(hash table size) */
@@ -1224,14 +1224,6 @@ static void __init prom_init_mem(void)
 
 	RELOC(alloc_bottom) = PAGE_ALIGN((unsigned long)&RELOC(_end) + 0x4000);
 
-	/* Check if we have an initrd after the kernel, if we do move our bottom
-	 * point to after it
-	 */
-	if (RELOC(prom_initrd_start)) {
-		if (RELOC(prom_initrd_end) > RELOC(alloc_bottom))
-			RELOC(alloc_bottom) = PAGE_ALIGN(RELOC(prom_initrd_end));
-	}
-
 	/*
 	 * If prom_memory_limit is set we reduce the upper limits *except* for
 	 * alloc_top_high. This must be the real top of RAM so we can put
@@ -1269,6 +1261,15 @@ static void __init prom_init_mem(void)
 	RELOC(alloc_top) = RELOC(rmo_top);
 	RELOC(alloc_top_high) = RELOC(ram_top);
 
+	/*
+	 * Check if we have an initrd after the kernel but still inside
+	 * the RMO.  If we do move our bottom point to after it.
+	 */
+	if (RELOC(prom_initrd_start) &&
+	    RELOC(prom_initrd_start) < RELOC(rmo_top) &&
+	    RELOC(prom_initrd_end) > RELOC(alloc_bottom))
+		RELOC(alloc_bottom) = PAGE_ALIGN(RELOC(prom_initrd_end));
+
 	prom_printf("memory layout at init:\n");
 	prom_printf("  memory_limit : %x (16 MB aligned)\n", RELOC(prom_memory_limit));
 	prom_printf("  alloc_bottom : %x\n", RELOC(alloc_bottom));
@@ -2079,7 +2080,7 @@ static void __init prom_check_displays(void)
 		/* Setup a usable color table when the appropriate
 		 * method is available. Should update this to set-colors */
 		clut = RELOC(default_colors);
-		for (i = 0; i < 32; i++, clut += 3)
+		for (i = 0; i < 16; i++, clut += 3)
 			if (prom_set_color(ih, i, clut[0], clut[1],
 					   clut[2]) != 0)
 				break;
@@ -2844,7 +2845,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	RELOC(of_platform) = prom_find_machine_type();
 	prom_printf("Detected machine type: %x\n", RELOC(of_platform));
 
-#ifndef CONFIG_RELOCATABLE
+#ifndef CONFIG_NONSTATIC_KERNEL
 	/* Bail if this is a kdump kernel. */
 	if (PHYSICAL_START > 0)
 		prom_panic("Error: You can't boot a kdump kernel from OF!\n");
@@ -2969,9 +2970,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	/*
 	 * in case stdin is USB and still active on IBM machines...
 	 * Unfortunately quiesce crashes on some powermacs if we have
-	 * closed stdin already (in particular the powerbook 101).
+	 * closed stdin already (in particular the powerbook 101). It
+	 * appears that the OPAL version of OFW doesn't like it either.
 	 */
-	if (RELOC(of_platform) != PLATFORM_POWERMAC)
+	if (RELOC(of_platform) != PLATFORM_POWERMAC &&
+	    RELOC(of_platform) != PLATFORM_OPAL)
 		prom_close_stdin();
 
 	/*
@@ -2987,8 +2990,12 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 * is common to us and kexec
 	 */
 	hdr = RELOC(dt_header_start);
-	prom_printf("returning from prom_init\n");
-	prom_debug("->dt_header_start=0x%x\n", hdr);
+
+	/* Don't print anything after quiesce under OPAL, it crashes OFW */
+	if (RELOC(of_platform) != PLATFORM_OPAL) {
+		prom_printf("returning from prom_init\n");
+		prom_debug("->dt_header_start=0x%x\n", hdr);
+	}
 
 #ifdef CONFIG_PPC32
 	reloc_got2(-offset);
diff --git a/arch/powerpc/kernel/reloc_32.S b/arch/powerpc/kernel/reloc_32.S
new file mode 100644
index 00000000000..ef46ba6e094
--- /dev/null
+++ b/arch/powerpc/kernel/reloc_32.S
@@ -0,0 +1,208 @@
+/*
+ * Code to process dynamic relocations for PPC32.
+ *
+ * Copyrights (C) IBM Corporation, 2011.
+ *	Author: Suzuki Poulose <suzuki@in.ibm.com>
+ *
+ *  - Based on ppc64 code - reloc_64.S
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/ppc_asm.h>
+
+/* Dynamic section table entry tags */
+DT_RELA = 7			/* Tag for Elf32_Rela section */
+DT_RELASZ = 8			/* Size of the Rela relocs */
+DT_RELAENT = 9			/* Size of one Rela reloc entry */
+
+STN_UNDEF = 0			/* Undefined symbol index */
+STB_LOCAL = 0			/* Local binding for the symbol */
+
+R_PPC_ADDR16_LO = 4		/* Lower half of (S+A) */
+R_PPC_ADDR16_HI = 5		/* Upper half of (S+A) */
+R_PPC_ADDR16_HA = 6		/* High Adjusted (S+A) */
+R_PPC_RELATIVE = 22
+
+/*
+ * r3 = desired final address
+ */
+
+_GLOBAL(relocate)
+
+	mflr	r0		/* Save our LR */
+	bl	0f		/* Find our current runtime address */
+0:	mflr	r12		/* Make it accessible */
+	mtlr	r0
+
+	lwz	r11, (p_dyn - 0b)(r12)
+	add	r11, r11, r12	/* runtime address of .dynamic section */
+	lwz	r9, (p_rela - 0b)(r12)
+	add	r9, r9, r12	/* runtime address of .rela.dyn section */
+	lwz	r10, (p_st - 0b)(r12)
+	add	r10, r10, r12	/* runtime address of _stext section */
+	lwz	r13, (p_sym - 0b)(r12)
+	add	r13, r13, r12	/* runtime address of .dynsym section */
+
+	/*
+	 * Scan the dynamic section for RELA, RELASZ entries
+	 */
+	li	r6, 0
+	li	r7, 0
+	li	r8, 0
+1:	lwz	r5, 0(r11)	/* ELF_Dyn.d_tag */
+	cmpwi	r5, 0		/* End of ELF_Dyn[] */
+	beq	eodyn
+	cmpwi	r5, DT_RELA
+	bne	relasz
+	lwz	r7, 4(r11)	/* r7 = rela.link */
+	b	skip
+relasz:
+	cmpwi	r5, DT_RELASZ
+	bne	relaent
+	lwz	r8, 4(r11)	/* r8 = Total Rela relocs size */
+	b	skip
+relaent:
+	cmpwi	r5, DT_RELAENT
+	bne	skip
+	lwz	r6, 4(r11)	/* r6 = Size of one Rela reloc */
+skip:
+	addi	r11, r11, 8
+	b	1b
+eodyn:				/* End of Dyn Table scan */
+
+	/* Check if we have found all the entries */
+	cmpwi	r7, 0
+	beq	done
+	cmpwi	r8, 0
+	beq	done
+	cmpwi	r6, 0
+	beq	done
+
+
+	/*
+	 * Work out the current offset from the link time address of .rela
+	 * section.
+	 *  cur_offset[r7] = rela.run[r9] - rela.link [r7]
+	 *  _stext.link[r12] = _stext.run[r10] - cur_offset[r7]
+	 *  final_offset[r3] = _stext.final[r3] - _stext.link[r12]
+	 */
+	subf	r7, r7, r9	/* cur_offset */
+	subf	r12, r7, r10
+	subf	r3, r12, r3	/* final_offset */
+
+	subf	r8, r6, r8	/* relaz -= relaent */
+	/*
+	 * Scan through the .rela table and process each entry
+	 * r9	- points to the current .rela table entry
+	 * r13	- points to the symbol table
+	 */
+
+	/*
+	 * Check if we have a relocation based on symbol
+	 * r5 will hold the value of the symbol.
+	 */
+applyrela:
+	lwz	r4, 4(r9)		/* r4 = rela.r_info */
+	srwi	r5, r4, 8		/* ELF32_R_SYM(r_info) */
+	cmpwi	r5, STN_UNDEF	/* sym == STN_UNDEF ? */
+	beq	get_type	/* value = 0 */
+	/* Find the value of the symbol at index(r5) */
+	slwi	r5, r5, 4		/* r5 = r5 * sizeof(Elf32_Sym) */
+	add	r12, r13, r5	/* r12 = &__dyn_sym[Index] */
+
+	/*
+	 * GNU ld has a bug, where dynamic relocs based on
+	 * STB_LOCAL symbols, the value should be assumed
+	 * to be zero. - Alan Modra
+	 */
+	/* XXX: Do we need to check if we are using GNU ld ? */
+	lbz	r5, 12(r12)	/* r5 = dyn_sym[Index].st_info */
+	extrwi	r5, r5, 4, 24	/* r5 = ELF32_ST_BIND(r5) */
+	cmpwi	r5, STB_LOCAL	/* st_value = 0, ld bug */
+	beq	get_type	/* We have r5 = 0 */
+	lwz	r5, 4(r12)	/* r5 = __dyn_sym[Index].st_value */
+
+get_type:
+	/* Load the relocation type to r4 */
+	extrwi	r4, r4, 8, 24	/* r4 = ELF32_R_TYPE(r_info) = ((char*)r4)[3] */
+
+	/* R_PPC_RELATIVE */
+	cmpwi	r4, R_PPC_RELATIVE
+	bne	hi16
+	lwz	r4, 0(r9)	/* r_offset */
+	lwz	r0, 8(r9)	/* r_addend */
+	add	r0, r0, r3	/* final addend */
+	stwx	r0, r4, r7	/* memory[r4+r7]) = (u32)r0 */
+	b	nxtrela		/* continue */
+
+	/* R_PPC_ADDR16_HI */
+hi16:
+	cmpwi	r4, R_PPC_ADDR16_HI
+	bne	ha16
+	lwz	r4, 0(r9)	/* r_offset */
+	lwz	r0, 8(r9)	/* r_addend */
+	add	r0, r0, r3
+	add	r0, r0, r5	/* r0 = (S+A+Offset) */
+	extrwi	r0, r0, 16, 0	/* r0 = (r0 >> 16) */
+	b	store_half
+
+	/* R_PPC_ADDR16_HA */
+ha16:
+	cmpwi	r4, R_PPC_ADDR16_HA
+	bne	lo16
+	lwz	r4, 0(r9)	/* r_offset */
+	lwz	r0, 8(r9)	/* r_addend */
+	add	r0, r0, r3
+	add	r0, r0, r5	/* r0 = (S+A+Offset) */
+	extrwi	r5, r0, 1, 16	/* Extract bit 16 */
+	extrwi	r0, r0, 16, 0	/* r0 = (r0 >> 16) */
+	add	r0, r0, r5	/* Add it to r0 */
+	b	store_half
+
+	/* R_PPC_ADDR16_LO */
+lo16:
+	cmpwi	r4, R_PPC_ADDR16_LO
+	bne	nxtrela
+	lwz	r4, 0(r9)	/* r_offset */
+	lwz	r0, 8(r9)	/* r_addend */
+	add	r0, r0, r3
+	add	r0, r0, r5	/* r0 = (S+A+Offset) */
+	extrwi	r0, r0, 16, 16	/* r0 &= 0xffff */
+	/* Fall through to */
+
+	/* Store half word */
+store_half:
+	sthx	r0, r4, r7	/* memory[r4+r7] = (u16)r0 */
+
+nxtrela:
+	/*
+	 * We have to flush the modified instructions to the
+	 * main storage from the d-cache. And also, invalidate the
+	 * cached instructions in i-cache which has been modified.
+	 *
+	 * We delay the sync / isync operation till the end, since
+	 * we won't be executing the modified instructions until
+	 * we return from here.
+	 */
+	dcbst	r4,r7
+	sync			/* Ensure the data is flushed before icbi */
+	icbi	r4,r7
+	cmpwi	r8, 0		/* relasz = 0 ? */
+	ble	done
+	add	r9, r9, r6	/* move to next entry in the .rela table */
+	subf	r8, r6, r8	/* relasz -= relaent */
+	b	applyrela
+
+done:
+	sync			/* Wait for the flush to finish */
+	isync			/* Discard prefetched instructions */
+	blr
+
+p_dyn:		.long	__dynamic_start - 0b
+p_rela:		.long	__rela_dyn_start - 0b
+p_sym:		.long	__dynamic_symtab - 0b
+p_st:		.long	_stext - 0b
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index e037c7494fd..4174b4b2324 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -568,6 +568,12 @@ static void rtas_flash_firmware(int reboot_type)
 	}
 
 	/*
+	 * Just before starting the firmware flash, cancel the event scan work
+	 * to avoid any soft lockup issues.
+	 */
+	rtas_cancel_event_scan();
+
+	/*
 	 * NOTE: the "first" block must be under 4GB, so we create
 	 * an entry with no data blocks in the reserved buffer in
 	 * the kernel data segment.
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 481ef064c8f..1045ff49cc6 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -472,6 +472,13 @@ static void start_event_scan(void)
 				 &event_scan_work, event_scan_delay);
 }
 
+/* Cancel the rtas event scan work */
+void rtas_cancel_event_scan(void)
+{
+	cancel_delayed_work_sync(&event_scan_work);
+}
+EXPORT_SYMBOL_GPL(rtas_cancel_event_scan);
+
 static int __init rtas_init(void)
 {
 	struct proc_dir_entry *entry;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index fb9bb46e7e8..4cb8f1e9d04 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -35,6 +35,8 @@
 #include <linux/pci.h>
 #include <linux/lockdep.h>
 #include <linux/memblock.h>
+#include <linux/hugetlb.h>
+
 #include <asm/io.h>
 #include <asm/kdump.h>
 #include <asm/prom.h>
@@ -64,6 +66,7 @@
 #include <asm/mmu_context.h>
 #include <asm/code-patching.h>
 #include <asm/kvm_ppc.h>
+#include <asm/hugetlb.h>
 
 #include "setup.h"
 
@@ -217,6 +220,13 @@ void __init early_setup(unsigned long dt_ptr)
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu();
 
+	/*
+	 * Reserve any gigantic pages requested on the command line.
+	 * memblock needs to have been initialized by the time this is
+	 * called since this will reserve memory.
+	 */
+	reserve_hugetlb_gpages();
+
 	DBG(" <- early_setup()\n");
 }
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 6df70907d60..f0abe92f63f 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -187,7 +187,8 @@ int smp_request_message_ipi(int virq, int msg)
 		return 1;
 	}
 #endif
-	err = request_irq(virq, smp_ipi_action[msg], IRQF_PERCPU,
+	err = request_irq(virq, smp_ipi_action[msg],
+			  IRQF_PERCPU | IRQF_NO_THREAD,
 			  smp_ipi_name[msg], 0);
 	WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
 		virq, smp_ipi_name[msg], err);
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index ce035c1905f..6fdf5ffe8c4 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -18,6 +18,7 @@
 #include <asm/machdep.h>
 #include <asm/smp.h>
 #include <asm/pmc.h>
+#include <asm/system.h>
 
 #include "cacheinfo.h"
 
@@ -51,6 +52,7 @@ static ssize_t store_smt_snooze_delay(struct sys_device *dev,
 		return -EINVAL;
 
 	per_cpu(smt_snooze_delay, cpu->sysdev.id) = snooze;
+	update_smt_snooze_delay(snooze);
 
 	return count;
 }
@@ -177,11 +179,13 @@ SYSFS_PMCSETUP(mmcra, SPRN_MMCRA);
 SYSFS_PMCSETUP(purr, SPRN_PURR);
 SYSFS_PMCSETUP(spurr, SPRN_SPURR);
 SYSFS_PMCSETUP(dscr, SPRN_DSCR);
+SYSFS_PMCSETUP(pir, SPRN_PIR);
 
 static SYSDEV_ATTR(mmcra, 0600, show_mmcra, store_mmcra);
 static SYSDEV_ATTR(spurr, 0600, show_spurr, NULL);
 static SYSDEV_ATTR(dscr, 0600, show_dscr, store_dscr);
 static SYSDEV_ATTR(purr, 0600, show_purr, store_purr);
+static SYSDEV_ATTR(pir, 0400, show_pir, NULL);
 
 unsigned long dscr_default = 0;
 EXPORT_SYMBOL(dscr_default);
@@ -392,6 +396,9 @@ static void __cpuinit register_cpu_online(unsigned int cpu)
 
 	if (cpu_has_feature(CPU_FTR_DSCR))
 		sysdev_create_file(s, &attr_dscr);
+
+	if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2))
+		sysdev_create_file(s, &attr_pir);
 #endif /* CONFIG_PPC64 */
 
 	cacheinfo_cpu_online(cpu);
@@ -462,6 +469,9 @@ static void unregister_cpu_online(unsigned int cpu)
 
 	if (cpu_has_feature(CPU_FTR_DSCR))
 		sysdev_remove_file(s, &attr_dscr);
+
+	if (cpu_has_feature(CPU_FTR_PPCAS_ARCH_V2))
+		sysdev_remove_file(s, &attr_pir);
 #endif /* CONFIG_PPC64 */
 
 	cacheinfo_cpu_offline(cpu);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 522bb1dfc35..567dd7c3ac2 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -86,8 +86,6 @@ static struct clocksource clocksource_rtc = {
 	.rating       = 400,
 	.flags        = CLOCK_SOURCE_IS_CONTINUOUS,
 	.mask         = CLOCKSOURCE_MASK(64),
-	.shift        = 22,
-	.mult         = 0,	/* To be filled in */
 	.read         = rtc_read,
 };
 
@@ -97,8 +95,6 @@ static struct clocksource clocksource_timebase = {
 	.rating       = 400,
 	.flags        = CLOCK_SOURCE_IS_CONTINUOUS,
 	.mask         = CLOCKSOURCE_MASK(64),
-	.shift        = 22,
-	.mult         = 0,	/* To be filled in */
 	.read         = timebase_read,
 };
 
@@ -110,22 +106,16 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 				 struct clock_event_device *dev);
 
 static struct clock_event_device decrementer_clockevent = {
-       .name           = "decrementer",
-       .rating         = 200,
-       .shift          = 0,	/* To be filled in */
-       .mult           = 0,	/* To be filled in */
-       .irq            = 0,
-       .set_next_event = decrementer_set_next_event,
-       .set_mode       = decrementer_set_mode,
-       .features       = CLOCK_EVT_FEAT_ONESHOT,
+	.name           = "decrementer",
+	.rating         = 200,
+	.irq            = 0,
+	.set_next_event = decrementer_set_next_event,
+	.set_mode       = decrementer_set_mode,
+	.features       = CLOCK_EVT_FEAT_ONESHOT,
 };
 
-struct decrementer_clock {
-	struct clock_event_device event;
-	u64 next_tb;
-};
-
-static DEFINE_PER_CPU(struct decrementer_clock, decrementers);
+DEFINE_PER_CPU(u64, decrementers_next_tb);
+static DEFINE_PER_CPU(struct clock_event_device, decrementers);
 
 #ifdef CONFIG_PPC_ISERIES
 static unsigned long __initdata iSeries_recal_titan;
@@ -168,13 +158,13 @@ EXPORT_SYMBOL_GPL(ppc_tb_freq);
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 /*
  * Factors for converting from cputime_t (timebase ticks) to
- * jiffies, milliseconds, seconds, and clock_t (1/USER_HZ seconds).
+ * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds).
  * These are all stored as 0.64 fixed-point binary fractions.
  */
 u64 __cputime_jiffies_factor;
 EXPORT_SYMBOL(__cputime_jiffies_factor);
-u64 __cputime_msec_factor;
-EXPORT_SYMBOL(__cputime_msec_factor);
+u64 __cputime_usec_factor;
+EXPORT_SYMBOL(__cputime_usec_factor);
 u64 __cputime_sec_factor;
 EXPORT_SYMBOL(__cputime_sec_factor);
 u64 __cputime_clockt_factor;
@@ -192,8 +182,8 @@ static void calc_cputime_factors(void)
 
 	div128_by_32(HZ, 0, tb_ticks_per_sec, &res);
 	__cputime_jiffies_factor = res.result_low;
-	div128_by_32(1000, 0, tb_ticks_per_sec, &res);
-	__cputime_msec_factor = res.result_low;
+	div128_by_32(1000000, 0, tb_ticks_per_sec, &res);
+	__cputime_usec_factor = res.result_low;
 	div128_by_32(1, 0, tb_ticks_per_sec, &res);
 	__cputime_sec_factor = res.result_low;
 	div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res);
@@ -441,7 +431,7 @@ EXPORT_SYMBOL(profile_pc);
 /* 
  * This function recalibrates the timebase based on the 49-bit time-of-day
  * value in the Titan chip.  The Titan is much more accurate than the value
- * returned by the service processor for the timebase frequency.  
+ * returned by the service processor for the timebase frequency.
  */
 
 static int __init iSeries_tb_recal(void)
@@ -576,9 +566,8 @@ void arch_irq_work_raise(void)
 void timer_interrupt(struct pt_regs * regs)
 {
 	struct pt_regs *old_regs;
-	struct decrementer_clock *decrementer =  &__get_cpu_var(decrementers);
-	struct clock_event_device *evt = &decrementer->event;
-	u64 now;
+	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	struct clock_event_device *evt = &__get_cpu_var(decrementers);
 
 	/* Ensure a positive value is written to the decrementer, or else
 	 * some CPUs will continue to take decrementer exceptions.
@@ -613,16 +602,9 @@ void timer_interrupt(struct pt_regs * regs)
 		get_lppaca()->int_dword.fields.decr_int = 0;
 #endif
 
-	now = get_tb_or_rtc();
-	if (now >= decrementer->next_tb) {
-		decrementer->next_tb = ~(u64)0;
-		if (evt->event_handler)
-			evt->event_handler(evt);
-	} else {
-		now = decrementer->next_tb - now;
-		if (now <= DECREMENTER_MAX)
-			set_dec((int)now);
-	}
+	*next_tb = ~(u64)0;
+	if (evt->event_handler)
+		evt->event_handler(evt);
 
 #ifdef CONFIG_PPC_ISERIES
 	if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending())
@@ -650,9 +632,9 @@ static void generic_suspend_disable_irqs(void)
 	 * with suspending.
 	 */
 
-	set_dec(0x7fffffff);
+	set_dec(DECREMENTER_MAX);
 	local_irq_disable();
-	set_dec(0x7fffffff);
+	set_dec(DECREMENTER_MAX);
 }
 
 static void generic_suspend_enable_irqs(void)
@@ -824,9 +806,8 @@ void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
 	++vdso_data->tb_update_count;
 	smp_mb();
 
-	/* XXX this assumes clock->shift == 22 */
-	/* 4611686018 ~= 2^(20+64-22) / 1e9 */
-	new_tb_to_xs = (u64) mult * 4611686018ULL;
+	/* 19342813113834067 ~= 2^(20+64) / 1e9 */
+	new_tb_to_xs = (u64) mult * (19342813113834067ULL >> clock->shift);
 	new_stamp_xsec = (u64) wall_time->tv_nsec * XSEC_PER_SEC;
 	do_div(new_stamp_xsec, 1000000000);
 	new_stamp_xsec += (u64) wall_time->tv_sec * XSEC_PER_SEC;
@@ -877,9 +858,7 @@ static void __init clocksource_init(void)
 	else
 		clock = &clocksource_timebase;
 
-	clock->mult = clocksource_hz2mult(tb_ticks_per_sec, clock->shift);
-
-	if (clocksource_register(clock)) {
+	if (clocksource_register_hz(clock, tb_ticks_per_sec)) {
 		printk(KERN_ERR "clocksource: %s is already registered\n",
 		       clock->name);
 		return;
@@ -892,7 +871,7 @@ static void __init clocksource_init(void)
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {
-	__get_cpu_var(decrementers).next_tb = get_tb_or_rtc() + evt;
+	__get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt;
 	set_dec(evt);
 	return 0;
 }
@@ -904,34 +883,9 @@ static void decrementer_set_mode(enum clock_event_mode mode,
 		decrementer_set_next_event(DECREMENTER_MAX, dev);
 }
 
-static inline uint64_t div_sc64(unsigned long ticks, unsigned long nsec,
-				int shift)
-{
-	uint64_t tmp = ((uint64_t)ticks) << shift;
-
-	do_div(tmp, nsec);
-	return tmp;
-}
-
-static void __init setup_clockevent_multiplier(unsigned long hz)
-{
-	u64 mult, shift = 32;
-
-	while (1) {
-		mult = div_sc64(hz, NSEC_PER_SEC, shift);
-		if (mult && (mult >> 32UL) == 0UL)
-			break;
-
-		shift--;
-	}
-
-	decrementer_clockevent.shift = shift;
-	decrementer_clockevent.mult = mult;
-}
-
 static void register_decrementer_clockevent(int cpu)
 {
-	struct clock_event_device *dec = &per_cpu(decrementers, cpu).event;
+	struct clock_event_device *dec = &per_cpu(decrementers, cpu);
 
 	*dec = decrementer_clockevent;
 	dec->cpumask = cpumask_of(cpu);
@@ -946,7 +900,8 @@ static void __init init_decrementer_clockevent(void)
 {
 	int cpu = smp_processor_id();
 
-	setup_clockevent_multiplier(ppc_tb_freq);
+	clockevents_calc_mult_shift(&decrementer_clockevent, ppc_tb_freq, 4);
+
 	decrementer_clockevent.max_delta_ns =
 		clockevent_delta2ns(DECREMENTER_MAX, &decrementer_clockevent);
 	decrementer_clockevent.min_delta_ns =
@@ -1014,10 +969,10 @@ void __init time_init(void)
 	boot_tb = get_tb_or_rtc();
 
 	/* If platform provided a timezone (pmac), we correct the time */
-        if (timezone_offset) {
+	if (timezone_offset) {
 		sys_tz.tz_minuteswest = -timezone_offset / 60;
 		sys_tz.tz_dsttime = 0;
-        }
+	}
 
 	vdso_data->tb_update_count = 0;
 	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 5459d148a0f..c091527efd8 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -98,18 +98,14 @@ static void pmac_backlight_unblank(void)
 static inline void pmac_backlight_unblank(void) { }
 #endif
 
-int die(const char *str, struct pt_regs *regs, long err)
+static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+static int die_owner = -1;
+static unsigned int die_nest_count;
+static int die_counter;
+
+static unsigned __kprobes long oops_begin(struct pt_regs *regs)
 {
-	static struct {
-		raw_spinlock_t lock;
-		u32 lock_owner;
-		int lock_owner_depth;
-	} die = {
-		.lock =			__RAW_SPIN_LOCK_UNLOCKED(die.lock),
-		.lock_owner =		-1,
-		.lock_owner_depth =	0
-	};
-	static int die_counter;
+	int cpu;
 	unsigned long flags;
 
 	if (debugger(regs))
@@ -117,66 +113,109 @@ int die(const char *str, struct pt_regs *regs, long err)
 
 	oops_enter();
 
-	if (die.lock_owner != raw_smp_processor_id()) {
-		console_verbose();
-		raw_spin_lock_irqsave(&die.lock, flags);
-		die.lock_owner = smp_processor_id();
-		die.lock_owner_depth = 0;
-		bust_spinlocks(1);
-		if (machine_is(powermac))
-			pmac_backlight_unblank();
-	} else {
-		local_save_flags(flags);
+	/* racy, but better than risking deadlock. */
+	raw_local_irq_save(flags);
+	cpu = smp_processor_id();
+	if (!arch_spin_trylock(&die_lock)) {
+		if (cpu == die_owner)
+			/* nested oops. should stop eventually */;
+		else
+			arch_spin_lock(&die_lock);
 	}
+	die_nest_count++;
+	die_owner = cpu;
+	console_verbose();
+	bust_spinlocks(1);
+	if (machine_is(powermac))
+		pmac_backlight_unblank();
+	return flags;
+}
 
-	if (++die.lock_owner_depth < 3) {
-		printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
-#ifdef CONFIG_PREEMPT
-		printk("PREEMPT ");
-#endif
-#ifdef CONFIG_SMP
-		printk("SMP NR_CPUS=%d ", NR_CPUS);
-#endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-		printk("DEBUG_PAGEALLOC ");
-#endif
-#ifdef CONFIG_NUMA
-		printk("NUMA ");
-#endif
-		printk("%s\n", ppc_md.name ? ppc_md.name : "");
+static void __kprobes oops_end(unsigned long flags, struct pt_regs *regs,
+			       int signr)
+{
+	bust_spinlocks(0);
+	die_owner = -1;
+	add_taint(TAINT_DIE);
+	die_nest_count--;
+	oops_exit();
+	printk("\n");
+	if (!die_nest_count)
+		/* Nest count reaches zero, release the lock. */
+		arch_spin_unlock(&die_lock);
+	raw_local_irq_restore(flags);
 
-		if (notify_die(DIE_OOPS, str, regs, err, 255,
-			       SIGSEGV) == NOTIFY_STOP)
-			return 1;
+	/*
+	 * A system reset (0x100) is a request to dump, so we always send
+	 * it through the crashdump code.
+	 */
+	if (kexec_should_crash(current) || (TRAP(regs) == 0x100)) {
+		crash_kexec(regs);
 
-		print_modules();
-		show_regs(regs);
-	} else {
-		printk("Recursive die() failure, output suppressed\n");
+		/*
+		 * We aren't the primary crash CPU. We need to send it
+		 * to a holding pattern to avoid it ending up in the panic
+		 * code.
+		 */
+		crash_kexec_secondary(regs);
 	}
 
-	bust_spinlocks(0);
-	die.lock_owner = -1;
-	add_taint(TAINT_DIE);
-	raw_spin_unlock_irqrestore(&die.lock, flags);
+	if (!signr)
+		return;
 
-	if (kexec_should_crash(current) ||
-		kexec_sr_activated(smp_processor_id()))
-		crash_kexec(regs);
-	crash_kexec_secondary(regs);
+	/*
+	 * While our oops output is serialised by a spinlock, output
+	 * from panic() called below can race and corrupt it. If we
+	 * know we are going to panic, delay for 1 second so we have a
+	 * chance to get clean backtraces from all CPUs that are oopsing.
+	 */
+	if (in_interrupt() || panic_on_oops || !current->pid ||
+	    is_global_init(current)) {
+		mdelay(MSEC_PER_SEC);
+	}
 
 	if (in_interrupt())
 		panic("Fatal exception in interrupt");
-
 	if (panic_on_oops)
 		panic("Fatal exception");
+	do_exit(signr);
+}
 
-	oops_exit();
-	do_exit(err);
+static int __kprobes __die(const char *str, struct pt_regs *regs, long err)
+{
+	printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
+#ifdef CONFIG_PREEMPT
+	printk("PREEMPT ");
+#endif
+#ifdef CONFIG_SMP
+	printk("SMP NR_CPUS=%d ", NR_CPUS);
+#endif
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	printk("DEBUG_PAGEALLOC ");
+#endif
+#ifdef CONFIG_NUMA
+	printk("NUMA ");
+#endif
+	printk("%s\n", ppc_md.name ? ppc_md.name : "");
+
+	if (notify_die(DIE_OOPS, str, regs, err, 255, SIGSEGV) == NOTIFY_STOP)
+		return 1;
+
+	print_modules();
+	show_regs(regs);
 
 	return 0;
 }
 
+void die(const char *str, struct pt_regs *regs, long err)
+{
+	unsigned long flags = oops_begin(regs);
+
+	if (__die(str, regs, err))
+		err = 0;
+	oops_end(flags, regs, err);
+}
+
 void user_single_step_siginfo(struct task_struct *tsk,
 				struct pt_regs *regs, siginfo_t *info)
 {
@@ -195,10 +234,11 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
 			"at %016lx nip %016lx lr %016lx code %x\n";
 
 	if (!user_mode(regs)) {
-		if (die("Exception in kernel mode", regs, signr))
-			return;
-	} else if (show_unhandled_signals &&
-		   unhandled_signal(current, signr)) {
+		die("Exception in kernel mode", regs, signr);
+		return;
+	}
+
+	if (show_unhandled_signals && unhandled_signal(current, signr)) {
 		printk_ratelimited(regs->msr & MSR_64BIT ? fmt64 : fmt32,
 				   current->comm, current->pid, signr,
 				   addr, regs->nip, regs->link, code);
@@ -220,25 +260,8 @@ void system_reset_exception(struct pt_regs *regs)
 			return;
 	}
 
-#ifdef CONFIG_KEXEC
-	cpumask_set_cpu(smp_processor_id(), &cpus_in_sr);
-#endif
-
 	die("System Reset", regs, SIGABRT);
 
-	/*
-	 * Some CPUs when released from the debugger will execute this path.
-	 * These CPUs entered the debugger via a soft-reset. If the CPU was
-	 * hung before entering the debugger it will return to the hung
-	 * state when exiting this function.  This causes a problem in
-	 * kdump since the hung CPU(s) will not respond to the IPI sent
-	 * from kdump. To prevent the problem we call crash_kexec_secondary()
-	 * here. If a kdump had not been initiated or we exit the debugger
-	 * with the "exit and recover" command (x) crash_kexec_secondary()
-	 * will return after 5ms and the CPU returns to its previous state.
-	 */
-	crash_kexec_secondary(regs);
-
 	/* Must die if the interrupt is not recoverable */
 	if (!(regs->msr & MSR_RI))
 		panic("Unrecoverable System Reset");
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 920276c0f6a..710a54005df 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -170,7 +170,13 @@ SECTIONS
 	}
 #ifdef CONFIG_RELOCATABLE
 	. = ALIGN(8);
-	.dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET) { *(.dynsym) }
+	.dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET)
+	{
+#ifdef CONFIG_RELOCATABLE_PPC32
+		__dynamic_symtab = .;
+#endif
+		*(.dynsym)
+	}
 	.dynstr : AT(ADDR(.dynstr) - LOAD_OFFSET) { *(.dynstr) }
 	.dynamic : AT(ADDR(.dynamic) - LOAD_OFFSET)
 	{