1 files changed, 570 insertions, 305 deletions

diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 5eb55ef1c91..f2f40e64658 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -16,9 +16,6 @@
  * bootup setup stuff..
  */
 
-#undef DEBUG
-
-#include <linux/config.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
@@ -26,9 +23,7 @@
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
-#include <linux/slab.h>
 #include <linux/user.h>
-#include <linux/a.out.h>
 #include <linux/tty.h>
 #include <linux/major.h>
 #include <linux/interrupt.h>
@@ -39,11 +34,13 @@
 #include <linux/pci.h>
 #include <linux/utsname.h>
 #include <linux/adb.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/root_dev.h>
+#include <linux/of.h>
+#include <linux/kexec.h>
 
 #include <asm/mmu.h>
 #include <asm/processor.h>
@@ -56,35 +53,30 @@
 #include <asm/dma.h>
 #include <asm/machdep.h>
 #include <asm/irq.h>
-#include <asm/kexec.h>
 #include <asm/time.h>
 #include <asm/nvram.h>
-#include "xics.h"
 #include <asm/pmc.h>
 #include <asm/mpic.h>
+#include <asm/xics.h>
 #include <asm/ppc-pci.h>
 #include <asm/i8259.h>
 #include <asm/udbg.h>
 #include <asm/smp.h>
+#include <asm/firmware.h>
+#include <asm/eeh.h>
+#include <asm/reg.h>
+#include <asm/plpar_wrappers.h>
 
-#include "plpar_wrappers.h"
-#include "ras.h"
-#include "firmware.h"
+#include "pseries.h"
 
-#ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
-extern void find_udbg_vterm(void);
+int CMO_PrPSP = -1;
+int CMO_SecPSP = -1;
+unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K);
+EXPORT_SYMBOL(CMO_PageSize);
 
 int fwnmi_active;  /* TRUE if an FWNMI handler is present */
 
-static void pseries_shared_idle_sleep(void);
-static void pseries_dedicated_idle_sleep(void);
-
-struct mpic *pSeries_mpic;
+static struct device_node *pSeries_mpic_node;
 
 static void pSeries_show_cpuinfo(struct seq_file *m)
 {
@@ -93,7 +85,7 @@ static void pSeries_show_cpuinfo(struct seq_file *m)
 
 	root = of_find_node_by_path("/");
 	if (root)
-		model = get_property(root, "model", NULL);
+		model = of_get_property(root, "model", NULL);
 	seq_printf(m, "machine\t\t: CHRP %s\n", model);
 	of_node_put(root);
 }
@@ -119,97 +111,363 @@ static void __init fwnmi_init(void)
 		fwnmi_active = 1;
 }
 
-static void __init pSeries_init_mpic(void)
+static void pseries_8259_cascade(unsigned int irq, struct irq_desc *desc)
 {
-        unsigned int *addrp;
-	struct device_node *np;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned int cascade_irq = i8259_irq();
+
+	if (cascade_irq != NO_IRQ)
+		generic_handle_irq(cascade_irq);
+
+	chip->irq_eoi(&desc->irq_data);
+}
+
+static void __init pseries_setup_i8259_cascade(void)
+{
+	struct device_node *np, *old, *found = NULL;
+	unsigned int cascade;
+	const u32 *addrp;
 	unsigned long intack = 0;
+	int naddr;
 
-	/* All ISUs are setup, complete initialization */
-	mpic_init(pSeries_mpic);
-
-	/* Check what kind of cascade ACK we have */
-        if (!(np = of_find_node_by_name(NULL, "pci"))
-            || !(addrp = (unsigned int *)
-                 get_property(np, "8259-interrupt-acknowledge", NULL)))
-                printk(KERN_ERR "Cannot find pci to get ack address\n");
-        else
-		intack = addrp[prom_n_addr_cells(np)-1];
-	of_node_put(np);
+	for_each_node_by_type(np, "interrupt-controller") {
+		if (of_device_is_compatible(np, "chrp,iic")) {
+			found = np;
+			break;
+		}
+	}
 
-	/* Setup the legacy interrupts & controller */
-	i8259_init(intack, 0);
+	if (found == NULL) {
+		printk(KERN_DEBUG "pic: no ISA interrupt controller\n");
+		return;
+	}
+
+	cascade = irq_of_parse_and_map(found, 0);
+	if (cascade == NO_IRQ) {
+		printk(KERN_ERR "pic: failed to map cascade interrupt");
+		return;
+	}
+	pr_debug("pic: cascade mapped to irq %d\n", cascade);
 
-	/* Hook cascade to mpic */
-	mpic_setup_cascade(NUM_ISA_INTERRUPTS, i8259_irq_cascade, NULL);
+	for (old = of_node_get(found); old != NULL ; old = np) {
+		np = of_get_parent(old);
+		of_node_put(old);
+		if (np == NULL)
+			break;
+		if (strcmp(np->name, "pci") != 0)
+			continue;
+		addrp = of_get_property(np, "8259-interrupt-acknowledge", NULL);
+		if (addrp == NULL)
+			continue;
+		naddr = of_n_addr_cells(np);
+		intack = addrp[naddr-1];
+		if (naddr > 1)
+			intack |= ((unsigned long)addrp[naddr-2]) << 32;
+	}
+	if (intack)
+		printk(KERN_DEBUG "pic: PCI 8259 intack at 0x%016lx\n", intack);
+	i8259_init(found, intack);
+	of_node_put(found);
+	irq_set_chained_handler(cascade, pseries_8259_cascade);
 }
 
-static void __init pSeries_setup_mpic(void)
+static void __init pseries_mpic_init_IRQ(void)
 {
-	unsigned int *opprop;
+	struct device_node *np;
+	const unsigned int *opprop;
 	unsigned long openpic_addr = 0;
-        unsigned char senses[NR_IRQS - NUM_ISA_INTERRUPTS];
-        struct device_node *root;
-	int irq_count;
-
-	/* Find the Open PIC if present */
-	root = of_find_node_by_path("/");
-	opprop = (unsigned int *) get_property(root, "platform-open-pic", NULL);
-	if (opprop != 0) {
-		int n = prom_n_addr_cells(root);
-
-		for (openpic_addr = 0; n > 0; --n)
-			openpic_addr = (openpic_addr << 32) + *opprop++;
+	int naddr, n, i, opplen;
+	struct mpic *mpic;
+
+	np = of_find_node_by_path("/");
+	naddr = of_n_addr_cells(np);
+	opprop = of_get_property(np, "platform-open-pic", &opplen);
+	if (opprop != NULL) {
+		openpic_addr = of_read_number(opprop, naddr);
 		printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr);
 	}
-	of_node_put(root);
+	of_node_put(np);
 
 	BUG_ON(openpic_addr == 0);
 
-	/* Get the sense values from OF */
-	prom_get_irq_senses(senses, NUM_ISA_INTERRUPTS, NR_IRQS);
-	
 	/* Setup the openpic driver */
-	irq_count = NR_IRQS - NUM_ISA_INTERRUPTS - 4; /* leave room for IPIs */
-	pSeries_mpic = mpic_alloc(openpic_addr, MPIC_PRIMARY,
-				  16, 16, irq_count, /* isu size, irq offset, irq count */ 
-				  NR_IRQS - 4, /* ipi offset */
-				  senses, irq_count, /* sense & sense size */
-				  " MPIC     ");
+	mpic = mpic_alloc(pSeries_mpic_node, openpic_addr,
+			MPIC_NO_RESET, 16, 0, " MPIC     ");
+	BUG_ON(mpic == NULL);
+
+	/* Add ISUs */
+	opplen /= sizeof(u32);
+	for (n = 0, i = naddr; i < opplen; i += naddr, n++) {
+		unsigned long isuaddr = of_read_number(opprop + i, naddr);
+		mpic_assign_isu(mpic, n, isuaddr);
+	}
+
+	/* Setup top-level get_irq */
+	ppc_md.get_irq = mpic_get_irq;
+
+	/* All ISUs are setup, complete initialization */
+	mpic_init(mpic);
+
+	/* Look for cascade */
+	pseries_setup_i8259_cascade();
+}
+
+static void __init pseries_xics_init_IRQ(void)
+{
+	xics_init();
+	pseries_setup_i8259_cascade();
 }
 
 static void pseries_lpar_enable_pmcs(void)
 {
 	unsigned long set, reset;
 
-	power4_enable_pmcs();
-
 	set = 1UL << 63;
 	reset = 0;
 	plpar_hcall_norets(H_PERFMON, set, reset);
+}
 
-	/* instruct hypervisor to maintain PMCs */
-	if (firmware_has_feature(FW_FEATURE_SPLPAR))
-		get_lppaca()->pmcregs_in_use = 1;
+static void __init pseries_discover_pic(void)
+{
+	struct device_node *np;
+	const char *typep;
+
+	for (np = NULL; (np = of_find_node_by_name(np,
+						   "interrupt-controller"));) {
+		typep = of_get_property(np, "compatible", NULL);
+		if (strstr(typep, "open-pic")) {
+			pSeries_mpic_node = of_node_get(np);
+			ppc_md.init_IRQ       = pseries_mpic_init_IRQ;
+			setup_kexec_cpu_down_mpic();
+			smp_init_pseries_mpic();
+			return;
+		} else if (strstr(typep, "ppc-xicp")) {
+			ppc_md.init_IRQ       = pseries_xics_init_IRQ;
+			setup_kexec_cpu_down_xics();
+			smp_init_pseries_xics();
+			return;
+		}
+	}
+	printk(KERN_ERR "pSeries_discover_pic: failed to recognize"
+	       " interrupt-controller\n");
 }
 
-static void __init pSeries_setup_arch(void)
+static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long action, void *node)
 {
-	/* Fixup ppc_md depending on the type of interrupt controller */
-	if (ppc64_interrupt_controller == IC_OPEN_PIC) {
-		ppc_md.init_IRQ       = pSeries_init_mpic;
-		ppc_md.get_irq        = mpic_get_irq;
-		/* Allocate the mpic now, so that find_and_init_phbs() can
-		 * fill the ISUs */
-		pSeries_setup_mpic();
-	} else {
-		ppc_md.init_IRQ       = xics_init_IRQ;
-		ppc_md.get_irq        = xics_get_irq;
+	struct device_node *np = node;
+	struct pci_dn *pci = NULL;
+	int err = NOTIFY_OK;
+
+	switch (action) {
+	case OF_RECONFIG_ATTACH_NODE:
+		pci = np->parent->data;
+		if (pci) {
+			update_dn_pci_info(np, pci->phb);
+
+			/* Create EEH device for the OF node */
+			eeh_dev_init(np, pci->phb);
+		}
+		break;
+	default:
+		err = NOTIFY_DONE;
+		break;
 	}
+	return err;
+}
+
+static struct notifier_block pci_dn_reconfig_nb = {
+	.notifier_call = pci_dn_reconfig_notifier,
+};
+
+struct kmem_cache *dtl_cache;
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+/*
+ * Allocate space for the dispatch trace log for all possible cpus
+ * and register the buffers with the hypervisor.  This is used for
+ * computing time stolen by the hypervisor.
+ */
+static int alloc_dispatch_logs(void)
+{
+	int cpu, ret;
+	struct paca_struct *pp;
+	struct dtl_entry *dtl;
+
+	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+		return 0;
 
-#ifdef CONFIG_SMP
-	smp_init_pSeries();
+	if (!dtl_cache)
+		return 0;
+
+	for_each_possible_cpu(cpu) {
+		pp = &paca[cpu];
+		dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL);
+		if (!dtl) {
+			pr_warn("Failed to allocate dispatch trace log for cpu %d\n",
+				cpu);
+			pr_warn("Stolen time statistics will be unreliable\n");
+			break;
+		}
+
+		pp->dtl_ridx = 0;
+		pp->dispatch_log = dtl;
+		pp->dispatch_log_end = dtl + N_DISPATCH_LOG;
+		pp->dtl_curr = dtl;
+	}
+
+	/* Register the DTL for the current (boot) cpu */
+	dtl = get_paca()->dispatch_log;
+	get_paca()->dtl_ridx = 0;
+	get_paca()->dtl_curr = dtl;
+	get_paca()->lppaca_ptr->dtl_idx = 0;
+
+	/* hypervisor reads buffer length from this field */
+	dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
+	ret = register_dtl(hard_smp_processor_id(), __pa(dtl));
+	if (ret)
+		pr_err("WARNING: DTL registration of cpu %d (hw %d) failed "
+		       "with %d\n", smp_processor_id(),
+		       hard_smp_processor_id(), ret);
+	get_paca()->lppaca_ptr->dtl_enable_mask = 2;
+
+	return 0;
+}
+#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+static inline int alloc_dispatch_logs(void)
+{
+	return 0;
+}
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+
+static int alloc_dispatch_log_kmem_cache(void)
+{
+	dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES,
+						DISPATCH_LOG_BYTES, 0, NULL);
+	if (!dtl_cache) {
+		pr_warn("Failed to create dispatch trace log buffer cache\n");
+		pr_warn("Stolen time statistics will be unreliable\n");
+		return 0;
+	}
+
+	return alloc_dispatch_logs();
+}
+early_initcall(alloc_dispatch_log_kmem_cache);
+
+static void pseries_lpar_idle(void)
+{
+	/*
+	 * Default handler to go into low thread priority and possibly
+	 * low power mode by cedeing processor to hypervisor
+	 */
+
+	/* Indicate to hypervisor that we are idle. */
+	get_lppaca()->idle = 1;
+
+	/*
+	 * Yield the processor to the hypervisor.  We return if
+	 * an external interrupt occurs (which are driven prior
+	 * to returning here) or if a prod occurs from another
+	 * processor. When returning here, external interrupts
+	 * are enabled.
+	 */
+	cede_processor();
+
+	get_lppaca()->idle = 0;
+}
+
+/*
+ * Enable relocation on during exceptions. This has partition wide scope and
+ * may take a while to complete, if it takes longer than one second we will
+ * just give up rather than wasting any more time on this - if that turns out
+ * to ever be a problem in practice we can move this into a kernel thread to
+ * finish off the process later in boot.
+ */
+long pSeries_enable_reloc_on_exc(void)
+{
+	long rc;
+	unsigned int delay, total_delay = 0;
+
+	while (1) {
+		rc = enable_reloc_on_exceptions();
+		if (!H_IS_LONG_BUSY(rc))
+			return rc;
+
+		delay = get_longbusy_msecs(rc);
+		total_delay += delay;
+		if (total_delay > 1000) {
+			pr_warn("Warning: Giving up waiting to enable "
+				"relocation on exceptions (%u msec)!\n",
+				total_delay);
+			return rc;
+		}
+
+		mdelay(delay);
+	}
+}
+EXPORT_SYMBOL(pSeries_enable_reloc_on_exc);
+
+long pSeries_disable_reloc_on_exc(void)
+{
+	long rc;
+
+	while (1) {
+		rc = disable_reloc_on_exceptions();
+		if (!H_IS_LONG_BUSY(rc))
+			return rc;
+		mdelay(get_longbusy_msecs(rc));
+	}
+}
+EXPORT_SYMBOL(pSeries_disable_reloc_on_exc);
+
+#ifdef CONFIG_KEXEC
+static void pSeries_machine_kexec(struct kimage *image)
+{
+	long rc;
+
+	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
+		rc = pSeries_disable_reloc_on_exc();
+		if (rc != H_SUCCESS)
+			pr_warning("Warning: Failed to disable relocation on "
+				   "exceptions: %ld\n", rc);
+	}
+
+	default_machine_kexec(image);
+}
+#endif
+
+#ifdef __LITTLE_ENDIAN__
+long pseries_big_endian_exceptions(void)
+{
+	long rc;
+
+	while (1) {
+		rc = enable_big_endian_exceptions();
+		if (!H_IS_LONG_BUSY(rc))
+			return rc;
+		mdelay(get_longbusy_msecs(rc));
+	}
+}
+
+static long pseries_little_endian_exceptions(void)
+{
+	long rc;
+
+	while (1) {
+		rc = enable_little_endian_exceptions();
+		if (!H_IS_LONG_BUSY(rc))
+			return rc;
+		mdelay(get_longbusy_msecs(rc));
+	}
+}
 #endif
+
+static void __init pSeries_setup_arch(void)
+{
+	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
+
+	/* Discover PIC type and setup ppc_md accordingly */
+	pseries_discover_pic();
+
 	/* openpic global configuration register (64-bit format). */
 	/* openpic Interrupt Source Unit pointer (64-bit format). */
 	/* python0 facility area (mmio) (64-bit format) REAL address. */
@@ -217,101 +475,164 @@ static void __init pSeries_setup_arch(void)
 	/* init to some ~sane value until calibrate_delay() runs */
 	loops_per_jiffy = 50000000;
 
-	if (ROOT_DEV == 0) {
-		printk("No ramdisk, default root is /dev/sda2\n");
-		ROOT_DEV = Root_SDA2;
-	}
-
 	fwnmi_init();
 
+	/* By default, only probe PCI (can be overriden by rtas_pci) */
+	pci_add_flags(PCI_PROBE_ONLY);
+
 	/* Find and initialize PCI host bridges */
 	init_pci_config_tokens();
 	find_and_init_phbs();
-	eeh_init();
+	of_reconfig_notifier_register(&pci_dn_reconfig_nb);
 
 	pSeries_nvram_init();
 
-	/* Choose an idle loop */
-	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		vpa_init(boot_cpuid);
-		if (get_lppaca()->shared_proc) {
-			printk(KERN_INFO "Using shared processor idle loop\n");
-			ppc_md.power_save = pseries_shared_idle_sleep;
-		} else {
-			printk(KERN_INFO "Using dedicated idle loop\n");
-			ppc_md.power_save = pseries_dedicated_idle_sleep;
-		}
+		ppc_md.power_save = pseries_lpar_idle;
+		ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
 	} else {
-		printk(KERN_INFO "Using default idle loop\n");
+		/* No special idle routine */
+		ppc_md.enable_pmcs = power4_enable_pmcs;
 	}
 
-	if (firmware_has_feature(FW_FEATURE_LPAR))
-		ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
-	else
-		ppc_md.enable_pmcs = power4_enable_pmcs;
+	ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
+
+	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
+		long rc;
+		if ((rc = pSeries_enable_reloc_on_exc()) != H_SUCCESS) {
+			pr_warn("Unable to enable relocation on exceptions: "
+				"%ld\n", rc);
+		}
+	}
 }
 
 static int __init pSeries_init_panel(void)
 {
 	/* Manually leave the kernel version on the panel. */
+#ifdef __BIG_ENDIAN__
 	ppc_md.progress("Linux ppc64\n", 0);
-	ppc_md.progress(system_utsname.version, 0);
+#else
+	ppc_md.progress("Linux ppc64le\n", 0);
+#endif
+	ppc_md.progress(init_utsname()->version, 0);
 
 	return 0;
 }
-arch_initcall(pSeries_init_panel);
+machine_arch_initcall(pseries, pSeries_init_panel);
 
-static  void __init pSeries_discover_pic(void)
+static int pseries_set_dabr(unsigned long dabr, unsigned long dabrx)
 {
-	struct device_node *np;
-	char *typep;
+	return plpar_hcall_norets(H_SET_DABR, dabr);
+}
 
-	/*
-	 * Setup interrupt mapping options that are needed for finish_device_tree
-	 * to properly parse the OF interrupt tree & do the virtual irq mapping
-	 */
-	__irq_offset_value = NUM_ISA_INTERRUPTS;
-	ppc64_interrupt_controller = IC_INVALID;
-	for (np = NULL; (np = of_find_node_by_name(np, "interrupt-controller"));) {
-		typep = (char *)get_property(np, "compatible", NULL);
-		if (strstr(typep, "open-pic")) {
-			ppc64_interrupt_controller = IC_OPEN_PIC;
-			break;
-		} else if (strstr(typep, "ppc-xicp")) {
-			ppc64_interrupt_controller = IC_PPC_XIC;
-			break;
-		}
-	}
-	if (ppc64_interrupt_controller == IC_INVALID)
-		printk("pSeries_discover_pic: failed to recognize"
-			" interrupt-controller\n");
+static int pseries_set_xdabr(unsigned long dabr, unsigned long dabrx)
+{
+	/* Have to set at least one bit in the DABRX according to PAPR */
+	if (dabrx == 0 && dabr == 0)
+		dabrx = DABRX_USER;
+	/* PAPR says we can only set kernel and user bits */
+	dabrx &= DABRX_KERNEL | DABRX_USER;
 
+	return plpar_hcall_norets(H_SET_XDABR, dabr, dabrx);
 }
 
-static void pSeries_mach_cpu_die(void)
+static int pseries_set_dawr(unsigned long dawr, unsigned long dawrx)
 {
-	local_irq_disable();
-	idle_task_exit();
-	/* Some hardware requires clearing the CPPR, while other hardware does not
-	 * it is safe either way
-	 */
-	pSeriesLP_cppr_info(0, 0);
-	rtas_stop_self();
-	/* Should never get here... */
-	BUG();
-	for(;;);
+	/* PAPR says we can't set HYP */
+	dawrx &= ~DAWRX_HYP;
+
+	return  plapr_set_watchpoint0(dawr, dawrx);
 }
 
-static int pseries_set_dabr(unsigned long dabr)
+#define CMO_CHARACTERISTICS_TOKEN 44
+#define CMO_MAXLENGTH 1026
+
+void pSeries_coalesce_init(void)
 {
-	return plpar_hcall_norets(H_SET_DABR, dabr);
+	struct hvcall_mpp_x_data mpp_x_data;
+
+	if (firmware_has_feature(FW_FEATURE_CMO) && !h_get_mpp_x(&mpp_x_data))
+		powerpc_firmware_features |= FW_FEATURE_XCMO;
+	else
+		powerpc_firmware_features &= ~FW_FEATURE_XCMO;
 }
 
-static int pseries_set_xdabr(unsigned long dabr)
+/**
+ * fw_cmo_feature_init - FW_FEATURE_CMO is not stored in ibm,hypertas-functions,
+ * handle that here. (Stolen from parse_system_parameter_string)
+ */
+void pSeries_cmo_feature_init(void)
 {
-	/* We want to catch accesses from kernel and userspace */
-	return plpar_hcall_norets(H_SET_XDABR, dabr,
-			H_DABRX_KERNEL | H_DABRX_USER);
+	char *ptr, *key, *value, *end;
+	int call_status;
+	int page_order = IOMMU_PAGE_SHIFT_4K;
+
+	pr_debug(" -> fw_cmo_feature_init()\n");
+	spin_lock(&rtas_data_buf_lock);
+	memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE);
+	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+				NULL,
+				CMO_CHARACTERISTICS_TOKEN,
+				__pa(rtas_data_buf),
+				RTAS_DATA_BUF_SIZE);
+
+	if (call_status != 0) {
+		spin_unlock(&rtas_data_buf_lock);
+		pr_debug("CMO not available\n");
+		pr_debug(" <- fw_cmo_feature_init()\n");
+		return;
+	}
+
+	end = rtas_data_buf + CMO_MAXLENGTH - 2;
+	ptr = rtas_data_buf + 2;	/* step over strlen value */
+	key = value = ptr;
+
+	while (*ptr && (ptr <= end)) {
+		/* Separate the key and value by replacing '=' with '\0' and
+		 * point the value at the string after the '='
+		 */
+		if (ptr[0] == '=') {
+			ptr[0] = '\0';
+			value = ptr + 1;
+		} else if (ptr[0] == '\0' || ptr[0] == ',') {
+			/* Terminate the string containing the key/value pair */
+			ptr[0] = '\0';
+
+			if (key == value) {
+				pr_debug("Malformed key/value pair\n");
+				/* Never found a '=', end processing */
+				break;
+			}
+
+			if (0 == strcmp(key, "CMOPageSize"))
+				page_order = simple_strtol(value, NULL, 10);
+			else if (0 == strcmp(key, "PrPSP"))
+				CMO_PrPSP = simple_strtol(value, NULL, 10);
+			else if (0 == strcmp(key, "SecPSP"))
+				CMO_SecPSP = simple_strtol(value, NULL, 10);
+			value = key = ptr + 1;
+		}
+		ptr++;
+	}
+
+	/* Page size is returned as the power of 2 of the page size,
+	 * convert to the page size in bytes before returning
+	 */
+	CMO_PageSize = 1 << page_order;
+	pr_debug("CMO_PageSize = %lu\n", CMO_PageSize);
+
+	if (CMO_PrPSP != -1 || CMO_SecPSP != -1) {
+		pr_info("CMO enabled\n");
+		pr_debug("CMO enabled, PrPSP=%d, SecPSP=%d\n", CMO_PrPSP,
+		         CMO_SecPSP);
+		powerpc_firmware_features |= FW_FEATURE_CMO;
+		pSeries_coalesce_init();
+	} else
+		pr_debug("CMO not enabled, PrPSP=%d, SecPSP=%d\n", CMO_PrPSP,
+		         CMO_SecPSP);
+	spin_unlock(&rtas_data_buf_lock);
+	pr_debug(" <- fw_cmo_feature_init()\n");
 }
 
 /*
@@ -319,176 +640,112 @@ static int pseries_set_xdabr(unsigned long dabr)
  */
 static void __init pSeries_init_early(void)
 {
-	DBG(" -> pSeries_init_early()\n");
-
-	fw_feature_init();
-	
-	if (firmware_has_feature(FW_FEATURE_LPAR))
-		hpte_init_lpar();
-	else
-		hpte_init_native();
+	pr_debug(" -> pSeries_init_early()\n");
 
+#ifdef CONFIG_HVC_CONSOLE
 	if (firmware_has_feature(FW_FEATURE_LPAR))
-		find_udbg_vterm();
-
-	if (firmware_has_feature(FW_FEATURE_DABR))
-		ppc_md.set_dabr = pseries_set_dabr;
-	else if (firmware_has_feature(FW_FEATURE_XDABR))
+		hvc_vio_init_early();
+#endif
+	if (firmware_has_feature(FW_FEATURE_XDABR))
 		ppc_md.set_dabr = pseries_set_xdabr;
+	else if (firmware_has_feature(FW_FEATURE_DABR))
+		ppc_md.set_dabr = pseries_set_dabr;
 
-	iommu_init_early_pSeries();
+	if (firmware_has_feature(FW_FEATURE_SET_MODE))
+		ppc_md.set_dawr = pseries_set_dawr;
 
-	pSeries_discover_pic();
+	pSeries_cmo_feature_init();
+	iommu_init_early_pSeries();
 
-	DBG(" <- pSeries_init_early()\n");
+	pr_debug(" <- pSeries_init_early()\n");
 }
 
+/*
+ * Called very early, MMU is off, device-tree isn't unflattened
+ */
 
-static int pSeries_check_legacy_ioport(unsigned int baseport)
+static int __init pseries_probe_fw_features(unsigned long node,
+					    const char *uname, int depth,
+					    void *data)
 {
-	struct device_node *np;
+	const char *prop;
+	int len;
+	static int hypertas_found;
+	static int vec5_found;
 
-#define I8042_DATA_REG	0x60
-#define FDC_BASE	0x3f0
+	if (depth != 1)
+		return 0;
 
+	if (!strcmp(uname, "rtas") || !strcmp(uname, "rtas@0")) {
+		prop = of_get_flat_dt_prop(node, "ibm,hypertas-functions",
+					   &len);
+		if (prop) {
+			powerpc_firmware_features |= FW_FEATURE_LPAR;
+			fw_hypertas_feature_init(prop, len);
+		}
 
-	switch(baseport) {
-	case I8042_DATA_REG:
-		np = of_find_node_by_type(NULL, "8042");
-		if (np == NULL)
-			return -ENODEV;
-		of_node_put(np);
-		break;
-	case FDC_BASE:
-		np = of_find_node_by_type(NULL, "fdc");
-		if (np == NULL)
-			return -ENODEV;
-		of_node_put(np);
-		break;
+		hypertas_found = 1;
 	}
-	return 0;
-}
 
-/*
- * Called very early, MMU is off, device-tree isn't unflattened
- */
-
-static int __init pSeries_probe_hypertas(unsigned long node,
-					 const char *uname, int depth,
-					 void *data)
-{
-	if (depth != 1 ||
-	    (strcmp(uname, "rtas") != 0 && strcmp(uname, "rtas@0") != 0))
- 		return 0;
+	if (!strcmp(uname, "chosen")) {
+		prop = of_get_flat_dt_prop(node, "ibm,architecture-vec-5",
+					   &len);
+		if (prop)
+			fw_vec5_feature_init(prop, len);
 
-	if (of_get_flat_dt_prop(node, "ibm,hypertas-functions", NULL) != NULL)
- 		powerpc_firmware_features |= FW_FEATURE_LPAR;
+		vec5_found = 1;
+	}
 
- 	return 1;
+	return hypertas_found && vec5_found;
 }
 
 static int __init pSeries_probe(void)
 {
- 	char *dtype = of_get_flat_dt_prop(of_get_flat_dt_root(),
- 					  "device_type", NULL);
+	unsigned long root = of_get_flat_dt_root();
+	const char *dtype = of_get_flat_dt_prop(root, "device_type", NULL);
+
  	if (dtype == NULL)
  		return 0;
  	if (strcmp(dtype, "chrp"))
 		return 0;
 
-	DBG("pSeries detected, looking for LPAR capability...\n");
-
-	/* Now try to figure out if we are running on LPAR */
-	of_scan_flat_dt(pSeries_probe_hypertas, NULL);
-
-	DBG("Machine is%s LPAR !\n",
-	    (powerpc_firmware_features & FW_FEATURE_LPAR) ? "" : " not");
-
-	return 1;
-}
-
-
-DECLARE_PER_CPU(unsigned long, smt_snooze_delay);
-
-static void pseries_dedicated_idle_sleep(void)
-{ 
-	unsigned int cpu = smp_processor_id();
-	unsigned long start_snooze;
-	unsigned long *smt_snooze_delay = &__get_cpu_var(smt_snooze_delay);
-
-	/*
-	 * Indicate to the HV that we are idle. Now would be
-	 * a good time to find other work to dispatch.
+	/* Cell blades firmware claims to be chrp while it's not. Until this
+	 * is fixed, we need to avoid those here.
 	 */
-	get_lppaca()->idle = 1;
+	if (of_flat_dt_is_compatible(root, "IBM,CPBW-1.0") ||
+	    of_flat_dt_is_compatible(root, "IBM,CBEA"))
+		return 0;
 
-	/*
-	 * We come in with interrupts disabled, and need_resched()
-	 * has been checked recently.  If we should poll for a little
-	 * while, do so.
-	 */
-	if (*smt_snooze_delay) {
-		start_snooze = get_tb() +
-			*smt_snooze_delay * tb_ticks_per_usec;
-		local_irq_enable();
-		set_thread_flag(TIF_POLLING_NRFLAG);
-
-		while (get_tb() < start_snooze) {
-			if (need_resched() || cpu_is_offline(cpu))
-				goto out;
-			ppc64_runlatch_off();
-			HMT_low();
-			HMT_very_low();
-		}
+	pr_debug("pSeries detected, looking for LPAR capability...\n");
 
-		HMT_medium();
-		clear_thread_flag(TIF_POLLING_NRFLAG);
-		smp_mb();
-		local_irq_disable();
-		if (need_resched() || cpu_is_offline(cpu))
-			goto out;
+	/* Now try to figure out if we are running on LPAR */
+	of_scan_flat_dt(pseries_probe_fw_features, NULL);
+
+#ifdef __LITTLE_ENDIAN__
+	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
+		long rc;
+		/*
+		 * Tell the hypervisor that we want our exceptions to
+		 * be taken in little endian mode. If this fails we don't
+		 * want to use BUG() because it will trigger an exception.
+		 */
+		rc = pseries_little_endian_exceptions();
+		if (rc) {
+			ppc_md.progress("H_SET_MODE LE exception fail", 0);
+			panic("Could not enable little endian exceptions");
+		}
 	}
+#endif
 
-	/*
-	 * Cede if the other thread is not idle, so that it can
-	 * go single-threaded.  If the other thread is idle,
-	 * we ask the hypervisor if it has pending work it
-	 * wants to do and cede if it does.  Otherwise we keep
-	 * polling in order to reduce interrupt latency.
-	 *
-	 * Doing the cede when the other thread is active will
-	 * result in this thread going dormant, meaning the other
-	 * thread gets to run in single-threaded (ST) mode, which
-	 * is slightly faster than SMT mode with this thread at
-	 * very low priority.  The cede enables interrupts, which
-	 * doesn't matter here.
-	 */
-	if (!lppaca[cpu ^ 1].idle || poll_pending() == H_PENDING)
-		cede_processor();
-
-out:
-	HMT_medium();
-	get_lppaca()->idle = 0;
-}
-
-static void pseries_shared_idle_sleep(void)
-{
-	/*
-	 * Indicate to the HV that we are idle. Now would be
-	 * a good time to find other work to dispatch.
-	 */
-	get_lppaca()->idle = 1;
+	if (firmware_has_feature(FW_FEATURE_LPAR))
+		hpte_init_lpar();
+	else
+		hpte_init_native();
 
-	/*
-	 * Yield the processor to the hypervisor.  We return if
-	 * an external interrupt occurs (which are driven prior
-	 * to returning here) or if a prod occurs from another
-	 * processor. When returning here, external interrupts
-	 * are enabled.
-	 */
-	cede_processor();
+	pr_debug("Machine is%s LPAR !\n",
+	         (powerpc_firmware_features & FW_FEATURE_LPAR) ? "" : " not");
 
-	get_lppaca()->idle = 0;
+	return 1;
 }
 
 static int pSeries_pci_probe_mode(struct pci_bus *bus)
@@ -498,25 +755,36 @@ static int pSeries_pci_probe_mode(struct pci_bus *bus)
 	return PCI_PROBE_NORMAL;
 }
 
-#ifdef CONFIG_KEXEC
-static void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
+/**
+ * pSeries_power_off - tell firmware about how to power off the system.
+ *
+ * This function calls either the power-off rtas token in normal cases
+ * or the ibm,power-off-ups token (if present & requested) in case of
+ * a power failure. If power-off token is used, power on will only be
+ * possible with power button press. If ibm,power-off-ups token is used
+ * it will allow auto poweron after power is restored.
+ */
+static void pSeries_power_off(void)
 {
-	/* Don't risk a hypervisor call if we're crashing */
-	if (firmware_has_feature(FW_FEATURE_SPLPAR) && !crash_shutdown) {
-		unsigned long vpa = __pa(get_lppaca());
-
-		if (unregister_vpa(hard_smp_processor_id(), vpa)) {
-			printk("VPA deregistration of cpu %u (hw_cpu_id %d) "
-					"failed\n", smp_processor_id(),
-					hard_smp_processor_id());
-		}
-	}
+	int rc;
+	int rtas_poweroff_ups_token = rtas_token("ibm,power-off-ups");
 
-	if (ppc64_interrupt_controller == IC_OPEN_PIC)
-		mpic_teardown_this_cpu(secondary);
-	else
-		xics_teardown_cpu(secondary);
+	if (rtas_flash_term_hook)
+		rtas_flash_term_hook(SYS_POWER_OFF);
+
+	if (rtas_poweron_auto == 0 ||
+		rtas_poweroff_ups_token == RTAS_UNKNOWN_SERVICE) {
+		rc = rtas_call(rtas_token("power-off"), 2, 1, NULL, -1, -1);
+		printk(KERN_INFO "RTAS power-off returned %d\n", rc);
+	} else {
+		rc = rtas_call(rtas_poweroff_ups_token, 0, 1, NULL);
+		printk(KERN_INFO "RTAS ibm,power-off-ups returned %d\n", rc);
+	}
+	for (;;);
 }
+
+#ifndef CONFIG_PCI
+void pSeries_final_fixup(void) { }
 #endif
 
 define_machine(pseries) {
@@ -528,24 +796,21 @@ define_machine(pseries) {
 	.log_error		= pSeries_log_error,
 	.pcibios_fixup		= pSeries_final_fixup,
 	.pci_probe_mode		= pSeries_pci_probe_mode,
-	.irq_bus_setup		= pSeries_irq_bus_setup,
 	.restart		= rtas_restart,
-	.power_off		= rtas_power_off,
+	.power_off		= pSeries_power_off,
 	.halt			= rtas_halt,
 	.panic			= rtas_os_term,
-	.cpu_die		= pSeries_mach_cpu_die,
 	.get_boot_time		= rtas_get_boot_time,
 	.get_rtc_time		= rtas_get_rtc_time,
 	.set_rtc_time		= rtas_set_rtc_time,
 	.calibrate_decr		= generic_calibrate_decr,
 	.progress		= rtas_progress,
-	.check_legacy_ioport	= pSeries_check_legacy_ioport,
 	.system_reset_exception = pSeries_system_reset_exception,
 	.machine_check_exception = pSeries_machine_check_exception,
 #ifdef CONFIG_KEXEC
-	.kexec_cpu_down		= pseries_kexec_cpu_down,
-	.machine_kexec		= default_machine_kexec,
-	.machine_kexec_prepare	= default_machine_kexec_prepare,
-	.machine_crash_shutdown	= default_machine_crash_shutdown,
+	.machine_kexec          = pSeries_machine_kexec,
+#endif
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+	.memory_block_size	= pseries_memory_block_size,
 #endif
 };