1 files changed, 320 insertions, 136 deletions

diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index ca5f2e10972..f2f40e64658 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -23,7 +23,6 @@
 #include <linux/mm.h>
 #include <linux/stddef.h>
 #include <linux/unistd.h>
-#include <linux/slab.h>
 #include <linux/user.h>
 #include <linux/tty.h>
 #include <linux/major.h>
@@ -35,11 +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>
@@ -54,30 +55,27 @@
 #include <asm/irq.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/pSeries_reconfig.h>
+#include <asm/reg.h>
+#include <asm/plpar_wrappers.h>
 
-#include "plpar_wrappers.h"
 #include "pseries.h"
 
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;
-unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT);
+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);
-
 static struct device_node *pSeries_mpic_node;
 
 static void pSeries_show_cpuinfo(struct seq_file *m)
@@ -115,10 +113,13 @@ static void __init fwnmi_init(void)
 
 static void pseries_8259_cascade(unsigned int irq, struct irq_desc *desc)
 {
+	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);
-	desc->chip->eoi(irq);
+
+	chip->irq_eoi(&desc->irq_data);
 }
 
 static void __init pseries_setup_i8259_cascade(void)
@@ -167,7 +168,7 @@ static void __init pseries_setup_i8259_cascade(void)
 		printk(KERN_DEBUG "pic: PCI 8259 intack at 0x%016lx\n", intack);
 	i8259_init(found, intack);
 	of_node_put(found);
-	set_irq_chained_handler(cascade, pseries_8259_cascade);
+	irq_set_chained_handler(cascade, pseries_8259_cascade);
 }
 
 static void __init pseries_mpic_init_IRQ(void)
@@ -181,7 +182,7 @@ static void __init pseries_mpic_init_IRQ(void)
 	np = of_find_node_by_path("/");
 	naddr = of_n_addr_cells(np);
 	opprop = of_get_property(np, "platform-open-pic", &opplen);
-	if (opprop != 0) {
+	if (opprop != NULL) {
 		openpic_addr = of_read_number(opprop, naddr);
 		printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr);
 	}
@@ -191,9 +192,7 @@ static void __init pseries_mpic_init_IRQ(void)
 
 	/* Setup the openpic driver */
 	mpic = mpic_alloc(pSeries_mpic_node, openpic_addr,
-			  MPIC_PRIMARY,
-			  16, 250, /* isu size, irq count */
-			  " MPIC     ");
+			MPIC_NO_RESET, 16, 0, " MPIC     ");
 	BUG_ON(mpic == NULL);
 
 	/* Add ISUs */
@@ -203,6 +202,9 @@ static void __init pseries_mpic_init_IRQ(void)
 		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);
 
@@ -212,7 +214,7 @@ static void __init pseries_mpic_init_IRQ(void)
 
 static void __init pseries_xics_init_IRQ(void)
 {
-	xics_init_IRQ();
+	xics_init();
 	pseries_setup_i8259_cascade();
 }
 
@@ -236,7 +238,6 @@ static void __init pseries_discover_pic(void)
 		if (strstr(typep, "open-pic")) {
 			pSeries_mpic_node = of_node_get(np);
 			ppc_md.init_IRQ       = pseries_mpic_init_IRQ;
-			ppc_md.get_irq        = mpic_get_irq;
 			setup_kexec_cpu_down_mpic();
 			smp_init_pseries_mpic();
 			return;
@@ -258,10 +259,14 @@ static int pci_dn_reconfig_notifier(struct notifier_block *nb, unsigned long act
 	int err = NOTIFY_OK;
 
 	switch (action) {
-	case PSERIES_RECONFIG_ADD:
+	case OF_RECONFIG_ATTACH_NODE:
 		pci = np->parent->data;
-		if (pci)
+		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;
@@ -274,8 +279,192 @@ 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;
+
+	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();
 
@@ -288,59 +477,87 @@ static void __init pSeries_setup_arch(void)
 
 	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();
-	pSeries_reconfig_notifier_register(&pci_dn_reconfig_nb);
-	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_DEBUG "Using shared processor idle loop\n");
-			ppc_md.power_save = pseries_shared_idle_sleep;
-		} else {
-			printk(KERN_DEBUG "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_DEBUG "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);
+#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 int pseries_set_dabr(unsigned long dabr)
+static int pseries_set_dabr(unsigned long dabr, unsigned long dabrx)
 {
 	return plpar_hcall_norets(H_SET_DABR, dabr);
 }
 
-static int pseries_set_xdabr(unsigned long dabr)
+static int pseries_set_xdabr(unsigned long dabr, unsigned long dabrx)
 {
-	/* We want to catch accesses from kernel and userspace */
-	return plpar_hcall_norets(H_SET_XDABR, dabr,
-			H_DABRX_KERNEL | H_DABRX_USER);
+	/* 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 int pseries_set_dawr(unsigned long dawr, unsigned long dawrx)
+{
+	/* PAPR says we can't set HYP */
+	dawrx &= ~DAWRX_HYP;
+
+	return  plapr_set_watchpoint0(dawr, dawrx);
 }
 
 #define CMO_CHARACTERISTICS_TOKEN 44
 #define CMO_MAXLENGTH 1026
 
+void pSeries_coalesce_init(void)
+{
+	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;
+}
+
 /**
  * fw_cmo_feature_init - FW_FEATURE_CMO is not stored in ibm,hypertas-functions,
  * handle that here. (Stolen from parse_system_parameter_string)
@@ -349,7 +566,7 @@ void pSeries_cmo_feature_init(void)
 {
 	char *ptr, *key, *value, *end;
 	int call_status;
-	int page_order = IOMMU_PAGE_SHIFT;
+	int page_order = IOMMU_PAGE_SHIFT_4K;
 
 	pr_debug(" -> fw_cmo_feature_init()\n");
 	spin_lock(&rtas_data_buf_lock);
@@ -410,6 +627,7 @@ void pSeries_cmo_feature_init(void)
 		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);
@@ -424,13 +642,17 @@ static void __init pSeries_init_early(void)
 {
 	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;
+
+	if (firmware_has_feature(FW_FEATURE_SET_MODE))
+		ppc_md.set_dawr = pseries_set_dawr;
 
 	pSeries_cmo_feature_init();
 	iommu_init_early_pSeries();
@@ -442,31 +664,45 @@ static void __init pSeries_init_early(void)
  * 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)
+static int __init pseries_probe_fw_features(unsigned long node,
+					    const char *uname, int depth,
+					    void *data)
 {
-	const char *hypertas;
-	unsigned long len;
+	const char *prop;
+	int len;
+	static int hypertas_found;
+	static int vec5_found;
 
-	if (depth != 1 ||
-	    (strcmp(uname, "rtas") != 0 && strcmp(uname, "rtas@0") != 0))
+	if (depth != 1)
 		return 0;
 
-	hypertas = of_get_flat_dt_prop(node, "ibm,hypertas-functions", &len);
-	if (!hypertas)
-		return 1;
+	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);
+		}
 
-	powerpc_firmware_features |= FW_FEATURE_LPAR;
-	fw_feature_init(hypertas, len);
+		hypertas_found = 1;
+	}
 
-	return 1;
+	if (!strcmp(uname, "chosen")) {
+		prop = of_get_flat_dt_prop(node, "ibm,architecture-vec-5",
+					   &len);
+		if (prop)
+			fw_vec5_feature_init(prop, len);
+
+		vec5_found = 1;
+	}
+
+	return hypertas_found && vec5_found;
 }
 
 static int __init pSeries_probe(void)
 {
 	unsigned long root = of_get_flat_dt_root();
- 	char *dtype = of_get_flat_dt_prop(root, "device_type", NULL);
+	const char *dtype = of_get_flat_dt_prop(root, "device_type", NULL);
 
  	if (dtype == NULL)
  		return 0;
@@ -483,7 +719,23 @@ static int __init pSeries_probe(void)
 	pr_debug("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);
+	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
 
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		hpte_init_lpar();
@@ -496,80 +748,6 @@ static int __init pSeries_probe(void)
 	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 in_purr, out_purr;
-
-	/*
-	 * Indicate to the HV that we are idle. Now would be
-	 * a good time to find other work to dispatch.
-	 */
-	get_lppaca()->idle = 1;
-	get_lppaca()->donate_dedicated_cpu = 1;
-	in_purr = mfspr(SPRN_PURR);
-
-	/*
-	 * We come in with interrupts disabled, and need_resched()
-	 * has been checked recently.  If we should poll for a little
-	 * while, do so.
-	 */
-	if (__get_cpu_var(smt_snooze_delay)) {
-		start_snooze = get_tb() +
-			__get_cpu_var(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();
-		}
-
-		HMT_medium();
-		clear_thread_flag(TIF_POLLING_NRFLAG);
-		smp_mb();
-		local_irq_disable();
-		if (need_resched() || cpu_is_offline(cpu))
-			goto out;
-	}
-
-	cede_processor();
-
-out:
-	HMT_medium();
-	out_purr = mfspr(SPRN_PURR);
-	get_lppaca()->wait_state_cycles += out_purr - in_purr;
-	get_lppaca()->donate_dedicated_cpu = 0;
-	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;
-
-	/*
-	 * 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;
-}
-
 static int pSeries_pci_probe_mode(struct pci_bus *bus)
 {
 	if (firmware_has_feature(FW_FEATURE_LPAR))
@@ -629,4 +807,10 @@ define_machine(pseries) {
 	.progress		= rtas_progress,
 	.system_reset_exception = pSeries_system_reset_exception,
 	.machine_check_exception = pSeries_machine_check_exception,
+#ifdef CONFIG_KEXEC
+	.machine_kexec          = pSeries_machine_kexec,
+#endif
+#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
+	.memory_block_size	= pseries_memory_block_size,
+#endif
 };