15 files changed, 764 insertions, 83 deletions

diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 07fe5b69b9e2..97619fd51e39 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -7,6 +7,7 @@ config PPC_PSERIES
 	select RTAS_ERROR_LOGGING
 	select PPC_UDBG_16550
 	select PPC_NATIVE
+	select PPC_PCI_CHOICE if EMBEDDED
 	default y
 
 config PPC_SPLPAR
@@ -39,3 +40,26 @@ config PPC_PSERIES_DEBUG
 	depends on PPC_PSERIES && PPC_EARLY_DEBUG
 	bool "Enable extra debug logging in platforms/pseries"
 	default y
+
+config PPC_SMLPAR
+	bool "Support for shared-memory logical partitions"
+	depends on PPC_PSERIES
+	select LPARCFG
+	default n
+	help
+	  Select this option to enable shared memory partition support.
+	  With this option a system running in an LPAR can be given more
+	  memory than physically available and will allow firmware to
+	  balance memory across many LPARs.
+
+config CMM
+	tristate "Collaborative memory management"
+	depends on PPC_SMLPAR
+	default y
+	help
+	  Select this option, if you want to enable the kernel interface
+	  to reduce the memory size of the system. This is accomplished
+	  by allocating pages of memory and put them "on hold". This only
+	  makes sense for a system running in an LPAR where the unused pages
+	  will be reused for other LPARs. The interface allows firmware to
+	  balance memory across many LPARs.
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 554c6e42ef2a..dfe574af2dc0 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -24,3 +24,4 @@ obj-$(CONFIG_HVC_CONSOLE)	+= hvconsole.o
 obj-$(CONFIG_HVCS)		+= hvcserver.o
 obj-$(CONFIG_HCALL_STATS)	+= hvCall_inst.o
 obj-$(CONFIG_PHYP_DUMP)	+= phyp_dump.o
+obj-$(CONFIG_CMM)		+= cmm.o
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
new file mode 100644
index 000000000000..c6b3be03168b
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -0,0 +1,468 @@
+/*
+ * Collaborative memory management interface.
+ *
+ * Copyright (C) 2008 IBM Corporation
+ * Author(s): Brian King (brking@linux.vnet.ibm.com),
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include <linux/ctype.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/oom.h>
+#include <linux/sched.h>
+#include <linux/stringify.h>
+#include <linux/swap.h>
+#include <linux/sysdev.h>
+#include <asm/firmware.h>
+#include <asm/hvcall.h>
+#include <asm/mmu.h>
+#include <asm/pgalloc.h>
+#include <asm/uaccess.h>
+
+#include "plpar_wrappers.h"
+
+#define CMM_DRIVER_VERSION	"1.0.0"
+#define CMM_DEFAULT_DELAY	1
+#define CMM_DEBUG			0
+#define CMM_DISABLE		0
+#define CMM_OOM_KB		1024
+#define CMM_MIN_MEM_MB		256
+#define KB2PAGES(_p)		((_p)>>(PAGE_SHIFT-10))
+#define PAGES2KB(_p)		((_p)<<(PAGE_SHIFT-10))
+
+static unsigned int delay = CMM_DEFAULT_DELAY;
+static unsigned int oom_kb = CMM_OOM_KB;
+static unsigned int cmm_debug = CMM_DEBUG;
+static unsigned int cmm_disabled = CMM_DISABLE;
+static unsigned long min_mem_mb = CMM_MIN_MEM_MB;
+static struct sys_device cmm_sysdev;
+
+MODULE_AUTHOR("Brian King <brking@linux.vnet.ibm.com>");
+MODULE_DESCRIPTION("IBM System p Collaborative Memory Manager");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(CMM_DRIVER_VERSION);
+
+module_param_named(delay, delay, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(delay, "Delay (in seconds) between polls to query hypervisor paging requests. "
+		 "[Default=" __stringify(CMM_DEFAULT_DELAY) "]");
+module_param_named(oom_kb, oom_kb, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(oom_kb, "Amount of memory in kb to free on OOM. "
+		 "[Default=" __stringify(CMM_OOM_KB) "]");
+module_param_named(min_mem_mb, min_mem_mb, ulong, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(min_mem_mb, "Minimum amount of memory (in MB) to not balloon. "
+		 "[Default=" __stringify(CMM_MIN_MEM_MB) "]");
+module_param_named(debug, cmm_debug, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(debug, "Enable module debugging logging. Set to 1 to enable. "
+		 "[Default=" __stringify(CMM_DEBUG) "]");
+
+#define CMM_NR_PAGES ((PAGE_SIZE - sizeof(void *) - sizeof(unsigned long)) / sizeof(unsigned long))
+
+#define cmm_dbg(...) if (cmm_debug) { printk(KERN_INFO "cmm: "__VA_ARGS__); }
+
+struct cmm_page_array {
+	struct cmm_page_array *next;
+	unsigned long index;
+	unsigned long page[CMM_NR_PAGES];
+};
+
+static unsigned long loaned_pages;
+static unsigned long loaned_pages_target;
+static unsigned long oom_freed_pages;
+
+static struct cmm_page_array *cmm_page_list;
+static DEFINE_SPINLOCK(cmm_lock);
+
+static struct task_struct *cmm_thread_ptr;
+
+/**
+ * cmm_alloc_pages - Allocate pages and mark them as loaned
+ * @nr:	number of pages to allocate
+ *
+ * Return value:
+ * 	number of pages requested to be allocated which were not
+ **/
+static long cmm_alloc_pages(long nr)
+{
+	struct cmm_page_array *pa, *npa;
+	unsigned long addr;
+	long rc;
+
+	cmm_dbg("Begin request for %ld pages\n", nr);
+
+	while (nr) {
+		addr = __get_free_page(GFP_NOIO | __GFP_NOWARN |
+				       __GFP_NORETRY | __GFP_NOMEMALLOC);
+		if (!addr)
+			break;
+		spin_lock(&cmm_lock);
+		pa = cmm_page_list;
+		if (!pa || pa->index >= CMM_NR_PAGES) {
+			/* Need a new page for the page list. */
+			spin_unlock(&cmm_lock);
+			npa = (struct cmm_page_array *)__get_free_page(GFP_NOIO | __GFP_NOWARN |
+								       __GFP_NORETRY | __GFP_NOMEMALLOC);
+			if (!npa) {
+				pr_info("%s: Can not allocate new page list\n", __FUNCTION__);
+				free_page(addr);
+				break;
+			}
+			spin_lock(&cmm_lock);
+			pa = cmm_page_list;
+
+			if (!pa || pa->index >= CMM_NR_PAGES) {
+				npa->next = pa;
+				npa->index = 0;
+				pa = npa;
+				cmm_page_list = pa;
+			} else
+				free_page((unsigned long) npa);
+		}
+
+		if ((rc = plpar_page_set_loaned(__pa(addr)))) {
+			pr_err("%s: Can not set page to loaned. rc=%ld\n", __FUNCTION__, rc);
+			spin_unlock(&cmm_lock);
+			free_page(addr);
+			break;
+		}
+
+		pa->page[pa->index++] = addr;
+		loaned_pages++;
+		totalram_pages--;
+		spin_unlock(&cmm_lock);
+		nr--;
+	}
+
+	cmm_dbg("End request with %ld pages unfulfilled\n", nr);
+	return nr;
+}
+
+/**
+ * cmm_free_pages - Free pages and mark them as active
+ * @nr:	number of pages to free
+ *
+ * Return value:
+ * 	number of pages requested to be freed which were not
+ **/
+static long cmm_free_pages(long nr)
+{
+	struct cmm_page_array *pa;
+	unsigned long addr;
+
+	cmm_dbg("Begin free of %ld pages.\n", nr);
+	spin_lock(&cmm_lock);
+	pa = cmm_page_list;
+	while (nr) {
+		if (!pa || pa->index <= 0)
+			break;
+		addr = pa->page[--pa->index];
+
+		if (pa->index == 0) {
+			pa = pa->next;
+			free_page((unsigned long) cmm_page_list);
+			cmm_page_list = pa;
+		}
+
+		plpar_page_set_active(__pa(addr));
+		free_page(addr);
+		loaned_pages--;
+		nr--;
+		totalram_pages++;
+	}
+	spin_unlock(&cmm_lock);
+	cmm_dbg("End request with %ld pages unfulfilled\n", nr);
+	return nr;
+}
+
+/**
+ * cmm_oom_notify - OOM notifier
+ * @self:	notifier block struct
+ * @dummy:	not used
+ * @parm:	returned - number of pages freed
+ *
+ * Return value:
+ * 	NOTIFY_OK
+ **/
+static int cmm_oom_notify(struct notifier_block *self,
+			  unsigned long dummy, void *parm)
+{
+	unsigned long *freed = parm;
+	long nr = KB2PAGES(oom_kb);
+
+	cmm_dbg("OOM processing started\n");
+	nr = cmm_free_pages(nr);
+	loaned_pages_target = loaned_pages;
+	*freed += KB2PAGES(oom_kb) - nr;
+	oom_freed_pages += KB2PAGES(oom_kb) - nr;
+	cmm_dbg("OOM processing complete\n");
+	return NOTIFY_OK;
+}
+
+/**
+ * cmm_get_mpp - Read memory performance parameters
+ *
+ * Makes hcall to query the current page loan request from the hypervisor.
+ *
+ * Return value:
+ * 	nothing
+ **/
+static void cmm_get_mpp(void)
+{
+	int rc;
+	struct hvcall_mpp_data mpp_data;
+	unsigned long active_pages_target;
+	signed long page_loan_request;
+
+	rc = h_get_mpp(&mpp_data);
+
+	if (rc != H_SUCCESS)
+		return;
+
+	page_loan_request = div_s64((s64)mpp_data.loan_request, PAGE_SIZE);
+	loaned_pages_target = page_loan_request + loaned_pages;
+	if (loaned_pages_target > oom_freed_pages)
+		loaned_pages_target -= oom_freed_pages;
+	else
+		loaned_pages_target = 0;
+
+	active_pages_target = totalram_pages + loaned_pages - loaned_pages_target;
+
+	if ((min_mem_mb * 1024 * 1024) > (active_pages_target * PAGE_SIZE))
+		loaned_pages_target = totalram_pages + loaned_pages -
+			((min_mem_mb * 1024 * 1024) / PAGE_SIZE);
+
+	cmm_dbg("delta = %ld, loaned = %lu, target = %lu, oom = %lu, totalram = %lu\n",
+		page_loan_request, loaned_pages, loaned_pages_target,
+		oom_freed_pages, totalram_pages);
+}
+
+static struct notifier_block cmm_oom_nb = {
+	.notifier_call = cmm_oom_notify
+};
+
+/**
+ * cmm_thread - CMM task thread
+ * @dummy:	not used
+ *
+ * Return value:
+ * 	0
+ **/
+static int cmm_thread(void *dummy)
+{
+	unsigned long timeleft;
+
+	while (1) {
+		timeleft = msleep_interruptible(delay * 1000);
+
+		if (kthread_should_stop() || timeleft) {
+			loaned_pages_target = loaned_pages;
+			break;
+		}
+
+		cmm_get_mpp();
+
+		if (loaned_pages_target > loaned_pages) {
+			if (cmm_alloc_pages(loaned_pages_target - loaned_pages))
+				loaned_pages_target = loaned_pages;
+		} else if (loaned_pages_target < loaned_pages)
+			cmm_free_pages(loaned_pages - loaned_pages_target);
+	}
+	return 0;
+}
+
+#define CMM_SHOW(name, format, args...)			\
+	static ssize_t show_##name(struct sys_device *dev, char *buf)	\
+	{							\
+		return sprintf(buf, format, ##args);		\
+	}							\
+	static SYSDEV_ATTR(name, S_IRUGO, show_##name, NULL)
+
+CMM_SHOW(loaned_kb, "%lu\n", PAGES2KB(loaned_pages));
+CMM_SHOW(loaned_target_kb, "%lu\n", PAGES2KB(loaned_pages_target));
+
+static ssize_t show_oom_pages(struct sys_device *dev, char *buf)
+{
+	return sprintf(buf, "%lu\n", PAGES2KB(oom_freed_pages));
+}
+
+static ssize_t store_oom_pages(struct sys_device *dev,
+			       const char *buf, size_t count)
+{
+	unsigned long val = simple_strtoul (buf, NULL, 10);
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (val != 0)
+		return -EBADMSG;
+
+	oom_freed_pages = 0;
+	return count;
+}
+
+static SYSDEV_ATTR(oom_freed_kb, S_IWUSR| S_IRUGO,
+		   show_oom_pages, store_oom_pages);
+
+static struct sysdev_attribute *cmm_attrs[] = {
+	&attr_loaned_kb,
+	&attr_loaned_target_kb,
+	&attr_oom_freed_kb,
+};
+
+static struct sysdev_class cmm_sysdev_class = {
+	.name = "cmm",
+};
+
+/**
+ * cmm_sysfs_register - Register with sysfs
+ *
+ * Return value:
+ * 	0 on success / other on failure
+ **/
+static int cmm_sysfs_register(struct sys_device *sysdev)
+{
+	int i, rc;
+
+	if ((rc = sysdev_class_register(&cmm_sysdev_class)))
+		return rc;
+
+	sysdev->id = 0;
+	sysdev->cls = &cmm_sysdev_class;
+
+	if ((rc = sysdev_register(sysdev)))
+		goto class_unregister;
+
+	for (i = 0; i < ARRAY_SIZE(cmm_attrs); i++) {
+		if ((rc = sysdev_create_file(sysdev, cmm_attrs[i])))
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	while (--i >= 0)
+		sysdev_remove_file(sysdev, cmm_attrs[i]);
+	sysdev_unregister(sysdev);
+class_unregister:
+	sysdev_class_unregister(&cmm_sysdev_class);
+	return rc;
+}
+
+/**
+ * cmm_unregister_sysfs - Unregister from sysfs
+ *
+ **/
+static void cmm_unregister_sysfs(struct sys_device *sysdev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cmm_attrs); i++)
+		sysdev_remove_file(sysdev, cmm_attrs[i]);
+	sysdev_unregister(sysdev);
+	sysdev_class_unregister(&cmm_sysdev_class);
+}
+
+/**
+ * cmm_init - Module initialization
+ *
+ * Return value:
+ * 	0 on success / other on failure
+ **/
+static int cmm_init(void)
+{
+	int rc = -ENOMEM;
+
+	if (!firmware_has_feature(FW_FEATURE_CMO))
+		return -EOPNOTSUPP;
+
+	if ((rc = register_oom_notifier(&cmm_oom_nb)) < 0)
+		return rc;
+
+	if ((rc = cmm_sysfs_register(&cmm_sysdev)))
+		goto out_oom_notifier;
+
+	if (cmm_disabled)
+		return rc;
+
+	cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread");
+	if (IS_ERR(cmm_thread_ptr)) {
+		rc = PTR_ERR(cmm_thread_ptr);
+		goto out_unregister_sysfs;
+	}
+
+	return rc;
+
+out_unregister_sysfs:
+	cmm_unregister_sysfs(&cmm_sysdev);
+out_oom_notifier:
+	unregister_oom_notifier(&cmm_oom_nb);
+	return rc;
+}
+
+/**
+ * cmm_exit - Module exit
+ *
+ * Return value:
+ * 	nothing
+ **/
+static void cmm_exit(void)
+{
+	if (cmm_thread_ptr)
+		kthread_stop(cmm_thread_ptr);
+	unregister_oom_notifier(&cmm_oom_nb);
+	cmm_free_pages(loaned_pages);
+	cmm_unregister_sysfs(&cmm_sysdev);
+}
+
+/**
+ * cmm_set_disable - Disable/Enable CMM
+ *
+ * Return value:
+ * 	0 on success / other on failure
+ **/
+static int cmm_set_disable(const char *val, struct kernel_param *kp)
+{
+	int disable = simple_strtoul(val, NULL, 10);
+
+	if (disable != 0 && disable != 1)
+		return -EINVAL;
+
+	if (disable && !cmm_disabled) {
+		if (cmm_thread_ptr)
+			kthread_stop(cmm_thread_ptr);
+		cmm_thread_ptr = NULL;
+		cmm_free_pages(loaned_pages);
+	} else if (!disable && cmm_disabled) {
+		cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread");
+		if (IS_ERR(cmm_thread_ptr))
+			return PTR_ERR(cmm_thread_ptr);
+	}
+
+	cmm_disabled = disable;
+	return 0;
+}
+
+module_param_call(disable, cmm_set_disable, param_get_uint,
+		  &cmm_disabled, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(disable, "Disable CMM. Set to 1 to disable. "
+		 "[Default=" __stringify(CMM_DISABLE) "]");
+
+module_init(cmm_init);
+module_exit(cmm_exit);
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 6f544ba4b37f..54816d75b578 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -75,9 +75,9 @@
  */
 
 /* If a device driver keeps reading an MMIO register in an interrupt
- * handler after a slot isolation event has occurred, we assume it
- * is broken and panic.  This sets the threshold for how many read
- * attempts we allow before panicking.
+ * handler after a slot isolation event, it might be broken.
+ * This sets the threshold for how many read attempts we allow
+ * before printing an error message.
  */
 #define EEH_MAX_FAILS	2100000
 
@@ -470,6 +470,7 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
 	unsigned long flags;
 	struct pci_dn *pdn;
 	int rc = 0;
+	const char *location;
 
 	total_mmio_ffs++;
 
@@ -509,18 +510,15 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
 	rc = 1;
 	if (pdn->eeh_mode & EEH_MODE_ISOLATED) {
 		pdn->eeh_check_count ++;
-		if (pdn->eeh_check_count >= EEH_MAX_FAILS) {
-			printk (KERN_ERR "EEH: Device driver ignored %d bad reads, panicing\n",
-			        pdn->eeh_check_count);
+		if (pdn->eeh_check_count % EEH_MAX_FAILS == 0) {
+			location = of_get_property(dn, "ibm,loc-code", NULL);
+			printk (KERN_ERR "EEH: %d reads ignored for recovering device at "
+				"location=%s driver=%s pci addr=%s\n",
+				pdn->eeh_check_count, location,
+				dev->driver->name, pci_name(dev));
+			printk (KERN_ERR "EEH: Might be infinite loop in %s driver\n",
+				dev->driver->name);
 			dump_stack();
-			msleep(5000);
-			
-			/* re-read the slot reset state */
-			if (read_slot_reset_state(pdn, rets) != 0)
-				rets[0] = -1;	/* reset state unknown */
-
-			/* If we are here, then we hit an infinite loop. Stop. */
-			panic("EEH: MMIO halt (%d) on device:%s\n", rets[0], pci_name(dev));
 		}
 		goto dn_unlock;
 	}
@@ -812,6 +810,7 @@ int rtas_set_slot_reset(struct pci_dn *pdn)
 static inline void __restore_bars (struct pci_dn *pdn)
 {
 	int i;
+	u32 cmd;
 
 	if (NULL==pdn->phb) return;
 	for (i=4; i<10; i++) {
@@ -832,6 +831,19 @@ static inline void __restore_bars (struct pci_dn *pdn)
 
 	/* max latency, min grant, interrupt pin and line */
 	rtas_write_config(pdn, 15*4, 4, pdn->config_space[15]);
+
+	/* Restore PERR & SERR bits, some devices require it,
+	   don't touch the other command bits */
+	rtas_read_config(pdn, PCI_COMMAND, 4, &cmd);
+	if (pdn->config_space[1] & PCI_COMMAND_PARITY)
+		cmd |= PCI_COMMAND_PARITY;
+	else
+		cmd &= ~PCI_COMMAND_PARITY;
+	if (pdn->config_space[1] & PCI_COMMAND_SERR)
+		cmd |= PCI_COMMAND_SERR;
+	else
+		cmd &= ~PCI_COMMAND_SERR;
+	rtas_write_config(pdn, PCI_COMMAND, 4, cmd);
 }
 
 /**
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index 9d3a40f45974..5a707da3f5c2 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -26,6 +26,7 @@
 #include <asm/prom.h>
 #include <asm/udbg.h>
 
+#include "pseries.h"
 
 typedef struct {
     unsigned long val;
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 3c5727dd5aa5..a1a368dd2d99 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -15,34 +15,13 @@
 #include <asm/machdep.h>
 #include <asm/pSeries_reconfig.h>
 
-static int pseries_remove_memory(struct device_node *np)
+static int pseries_remove_lmb(unsigned long base, unsigned int lmb_size)
 {
-	const char *type;
-	const unsigned int *my_index;
-	const unsigned int *regs;
-	u64 start_pfn, start;
+	unsigned long start, start_pfn;
 	struct zone *zone;
-	int ret = -EINVAL;
-
-	/*
-	 * Check to see if we are actually removing memory
-	 */
-	type = of_get_property(np, "device_type", NULL);
-	if (type == NULL || strcmp(type, "memory") != 0)
-		return 0;
+	int ret;
 
-	/*
-	 * Find the memory index and size of the removing section
-	 */
-	my_index = of_get_property(np, "ibm,my-drc-index", NULL);
-	if (!my_index)
-		return ret;
-
-	regs = of_get_property(np, "reg", NULL);
-	if (!regs)
-		return ret;
-
-	start_pfn = section_nr_to_pfn(*my_index & 0xffff);
+	start_pfn = base >> PFN_SECTION_SHIFT;
 	zone = page_zone(pfn_to_page(start_pfn));
 
 	/*
@@ -54,56 +33,111 @@ static int pseries_remove_memory(struct device_node *np)
 	 * to sysfs "state" file and we can't remove sysfs entries
 	 * while writing to it. So we have to defer it to here.
 	 */
-	ret = __remove_pages(zone, start_pfn, regs[3] >> PAGE_SHIFT);
+	ret = __remove_pages(zone, start_pfn, lmb_size >> PAGE_SHIFT);
 	if (ret)
 		return ret;
 
 	/*
 	 * Update memory regions for memory remove
 	 */
-	lmb_remove(start_pfn << PAGE_SHIFT, regs[3]);
+	lmb_remove(base, lmb_size);
 
 	/*
 	 * Remove htab bolted mappings for this section of memory
 	 */
-	start = (unsigned long)__va(start_pfn << PAGE_SHIFT);
-	ret = remove_section_mapping(start, start + regs[3]);
+	start = (unsigned long)__va(base);
+	ret = remove_section_mapping(start, start + lmb_size);
 	return ret;
 }
 
-static int pseries_add_memory(struct device_node *np)
+static int pseries_remove_memory(struct device_node *np)
 {
 	const char *type;
-	const unsigned int *my_index;
 	const unsigned int *regs;
-	u64 start_pfn;
+	unsigned long base;
+	unsigned int lmb_size;
 	int ret = -EINVAL;
 
 	/*
-	 * Check to see if we are actually adding memory
+	 * Check to see if we are actually removing memory
 	 */
 	type = of_get_property(np, "device_type", NULL);
 	if (type == NULL || strcmp(type, "memory") != 0)
 		return 0;
 
 	/*
-	 * Find the memory index and size of the added section
+	 * Find the bae address and size of the lmb
 	 */
-	my_index = of_get_property(np, "ibm,my-drc-index", NULL);
-	if (!my_index)
+	regs = of_get_property(np, "reg", NULL);
+	if (!regs)
 		return ret;
 
+	base = *(unsigned long *)regs;
+	lmb_size = regs[3];
+
+	ret = pseries_remove_lmb(base, lmb_size);
+	return ret;
+}
+
+static int pseries_add_memory(struct device_node *np)
+{
+	const char *type;
+	const unsigned int *regs;
+	unsigned long base;
+	unsigned int lmb_size;
+	int ret = -EINVAL;
+
+	/*
+	 * Check to see if we are actually adding memory
+	 */
+	type = of_get_property(np, "device_type", NULL);
+	if (type == NULL || strcmp(type, "memory") != 0)
+		return 0;
+
+	/*
+	 * Find the base and size of the lmb
+	 */
 	regs = of_get_property(np, "reg", NULL);
 	if (!regs)
 		return ret;
 
-	start_pfn = section_nr_to_pfn(*my_index & 0xffff);
+	base = *(unsigned long *)regs;
+	lmb_size = regs[3];
 
 	/*
 	 * Update memory region to represent the memory add
 	 */
-	lmb_add(start_pfn << PAGE_SHIFT, regs[3]);
-	return 0;
+	ret = lmb_add(base, lmb_size);
+	return (ret < 0) ? -EINVAL : 0;
+}
+
+static int pseries_drconf_memory(unsigned long *base, unsigned int action)
+{
+	struct device_node *np;
+	const unsigned long *lmb_size;
+	int rc;
+
+	np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
+	if (!np)
+		return -EINVAL;
+
+	lmb_size = of_get_property(np, "ibm,lmb-size", NULL);
+	if (!lmb_size) {
+		of_node_put(np);
+		return -EINVAL;
+	}
+
+	if (action == PSERIES_DRCONF_MEM_ADD) {
+		rc = lmb_add(*base, *lmb_size);
+		rc = (rc < 0) ? -EINVAL : 0;
+	} else if (action == PSERIES_DRCONF_MEM_REMOVE) {
+		rc = pseries_remove_lmb(*base, *lmb_size);
+	} else {
+		rc = -EINVAL;
+	}
+
+	of_node_put(np);
+	return rc;
 }
 
 static int pseries_memory_notifier(struct notifier_block *nb,
@@ -120,6 +154,11 @@ static int pseries_memory_notifier(struct notifier_block *nb,
 		if (pseries_remove_memory(node))
 			err = NOTIFY_BAD;
 		break;
+	case PSERIES_DRCONF_MEM_ADD:
+	case PSERIES_DRCONF_MEM_REMOVE:
+		if (pseries_drconf_memory(node, action))
+			err = NOTIFY_BAD;
+		break;
 	default:
 		err = NOTIFY_DONE;
 		break;
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 176f1f39d2d5..a8c446697f9e 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -48,9 +48,10 @@
 #include "plpar_wrappers.h"
 
 
-static void tce_build_pSeries(struct iommu_table *tbl, long index,
+static int tce_build_pSeries(struct iommu_table *tbl, long index,
 			      long npages, unsigned long uaddr,
-			      enum dma_data_direction direction)
+			      enum dma_data_direction direction,
+			      struct dma_attrs *attrs)
 {
 	u64 proto_tce;
 	u64 *tcep;
@@ -71,6 +72,7 @@ static void tce_build_pSeries(struct iommu_table *tbl, long index,
 		uaddr += TCE_PAGE_SIZE;
 		tcep++;
 	}
+	return 0;
 }
 
 
@@ -93,13 +95,19 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
 	return *tcep;
 }
 
-static void tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
+static void tce_free_pSeriesLP(struct iommu_table*, long, long);
+static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long);
+
+static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				long npages, unsigned long uaddr,
-				enum dma_data_direction direction)
+				enum dma_data_direction direction,
+				struct dma_attrs *attrs)
 {
-	u64 rc;
+	u64 rc = 0;
 	u64 proto_tce, tce;
 	u64 rpn;
+	int ret = 0;
+	long tcenum_start = tcenum, npages_start = npages;
 
 	rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
 	proto_tce = TCE_PCI_READ;
@@ -110,6 +118,13 @@ static void tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tce = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
 		rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, tce);
 
+		if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
+			ret = (int)rc;
+			tce_free_pSeriesLP(tbl, tcenum_start,
+			                   (npages_start - (npages + 1)));
+			break;
+		}
+
 		if (rc && printk_ratelimit()) {
 			printk("tce_build_pSeriesLP: plpar_tce_put failed. rc=%ld\n", rc);
 			printk("\tindex   = 0x%lx\n", (u64)tbl->it_index);
@@ -121,23 +136,28 @@ static void tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcenum++;
 		rpn++;
 	}
+	return ret;
 }
 
 static DEFINE_PER_CPU(u64 *, tce_page) = NULL;
 
-static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
+static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				     long npages, unsigned long uaddr,
-				     enum dma_data_direction direction)
+				     enum dma_data_direction direction,
+				     struct dma_attrs *attrs)
 {
-	u64 rc;
+	u64 rc = 0;
 	u64 proto_tce;
 	u64 *tcep;
 	u64 rpn;
 	long l, limit;
+	long tcenum_start = tcenum, npages_start = npages;
+	int ret = 0;
 
-	if (npages == 1)
+	if (npages == 1) {
 		return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
-					   direction);
+		                           direction, attrs);
+	}
 
 	tcep = __get_cpu_var(tce_page);
 
@@ -147,9 +167,10 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 	if (!tcep) {
 		tcep = (u64 *)__get_free_page(GFP_ATOMIC);
 		/* If allocation fails, fall back to the loop implementation */
-		if (!tcep)
-			return tce_build_pSeriesLP(tbl, tcenum, npages,
-						   uaddr, direction);
+		if (!tcep) {
+			return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
+					    direction, attrs);
+		}
 		__get_cpu_var(tce_page) = tcep;
 	}
 
@@ -180,6 +201,13 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcenum += limit;
 	} while (npages > 0 && !rc);
 
+	if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
+		ret = (int)rc;
+		tce_freemulti_pSeriesLP(tbl, tcenum_start,
+		                        (npages_start - (npages + limit)));
+		return ret;
+	}
+
 	if (rc && printk_ratelimit()) {
 		printk("tce_buildmulti_pSeriesLP: plpar_tce_put failed. rc=%ld\n", rc);
 		printk("\tindex   = 0x%lx\n", (u64)tbl->it_index);
@@ -187,6 +215,7 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		printk("\ttce[0] val = 0x%lx\n", tcep[0]);
 		show_stack(current, (unsigned long *)__get_SP());
 	}
+	return ret;
 }
 
 static void tce_free_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages)
diff --git a/arch/powerpc/platforms/pseries/kexec.c b/arch/powerpc/platforms/pseries/kexec.c
index e9dd5fe081c9..53cbd53d8740 100644
--- a/arch/powerpc/platforms/pseries/kexec.c
+++ b/arch/powerpc/platforms/pseries/kexec.c
@@ -70,4 +70,4 @@ static int __init pseries_kexec_setup(void)
 
 	return 0;
 }
-__initcall(pseries_kexec_setup);
+machine_device_initcall(pseries, pseries_kexec_setup);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 2cbaedb17f3e..52a80e5840e8 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -52,7 +52,7 @@ EXPORT_SYMBOL(plpar_hcall_norets);
 extern void pSeries_find_serial_port(void);
 
 
-int vtermno;	/* virtual terminal# for udbg  */
+static int vtermno;	/* virtual terminal# for udbg  */
 
 #define __ALIGNED__ __attribute__((__aligned__(sizeof(long))))
 static void udbg_hvsi_putc(char c)
@@ -305,7 +305,7 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
 	flags = 0;
 
 	/* Make pHyp happy */
-	if (rflags & (_PAGE_GUARDED|_PAGE_NO_CACHE))
+	if ((rflags & _PAGE_NO_CACHE) & !(rflags & _PAGE_WRITETHRU))
 		hpte_r &= ~_PAGE_COHERENT;
 
 	lpar_rc = plpar_pte_enter(flags, hpte_group, hpte_v, hpte_r, &slot);
diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h
index d8680b589dc9..a437267c6bf8 100644
--- a/arch/powerpc/platforms/pseries/plpar_wrappers.h
+++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h
@@ -42,6 +42,16 @@ static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa)
 	return vpa_call(0x3, cpu, vpa);
 }
 
+static inline long plpar_page_set_loaned(unsigned long vpa)
+{
+	return plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, vpa, 0);
+}
+
+static inline long plpar_page_set_active(unsigned long vpa)
+{
+	return plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, vpa, 0);
+}
+
 extern void vpa_init(int cpu);
 
 static inline long plpar_pte_enter(unsigned long flags,
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 2b548afd1003..d20b96e22c2e 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -55,7 +55,7 @@
 static unsigned char ras_log_buf[RTAS_ERROR_LOG_MAX];
 static DEFINE_SPINLOCK(ras_log_buf_lock);
 
-char mce_data_buf[RTAS_ERROR_LOG_MAX];
+static char mce_data_buf[RTAS_ERROR_LOG_MAX];
 
 static int ras_get_sensor_state_token;
 static int ras_check_exception_token;
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 75769aae41d5..7637bd38c795 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -365,7 +365,7 @@ static char *parse_node(char *buf, size_t bufsize, struct device_node **npp)
 	*buf = '\0';
 	buf++;
 
-	handle = simple_strtoul(handle_str, NULL, 10);
+	handle = simple_strtoul(handle_str, NULL, 0);
 
 	*npp = of_find_node_by_phandle(handle);
 	return buf;
@@ -422,8 +422,8 @@ static int do_update_property(char *buf, size_t bufsize)
 {
 	struct device_node *np;
 	unsigned char *value;
-	char *name, *end;
-	int length;
+	char *name, *end, *next_prop;
+	int rc, length;
 	struct property *newprop, *oldprop;
 	buf = parse_node(buf, bufsize, &np);
 	end = buf + bufsize;
@@ -431,7 +431,8 @@ static int do_update_property(char *buf, size_t bufsize)
 	if (!np)
 		return -ENODEV;
 
-	if (parse_next_property(buf, end, &name, &length, &value) == NULL)
+	next_prop = parse_next_property(buf, end, &name, &length, &value);
+	if (!next_prop)
 		return -EINVAL;
 
 	newprop = new_property(name, length, value, NULL);
@@ -442,7 +443,34 @@ static int do_update_property(char *buf, size_t bufsize)
 	if (!oldprop)
 		return -ENODEV;
 
-	return prom_update_property(np, newprop, oldprop);
+	rc = prom_update_property(np, newprop, oldprop);
+	if (rc)
+		return rc;
+
+	/* For memory under the ibm,dynamic-reconfiguration-memory node
+	 * of the device tree, adding and removing memory is just an update
+	 * to the ibm,dynamic-memory property instead of adding/removing a
+	 * memory node in the device tree.  For these cases we still need to
+	 * involve the notifier chain.
+	 */
+	if (!strcmp(name, "ibm,dynamic-memory")) {
+		int action;
+
+		next_prop = parse_next_property(next_prop, end, &name,
+						&length, &value);
+		if (!next_prop)
+			return -EINVAL;
+
+		if (!strcmp(name, "add"))
+			action = PSERIES_DRCONF_MEM_ADD;
+		else
+			action = PSERIES_DRCONF_MEM_REMOVE;
+
+		blocking_notifier_call_chain(&pSeries_reconfig_chain,
+					     action, value);
+	}
+
+	return 0;
 }
 
 /**
diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/platforms/pseries/rtasd.c
index 7d3e2b0bd4d2..c9ffd8c225f1 100644
--- a/arch/powerpc/platforms/pseries/rtasd.c
+++ b/arch/powerpc/platforms/pseries/rtasd.c
@@ -32,7 +32,7 @@
 
 static DEFINE_SPINLOCK(rtasd_log_lock);
 
-DECLARE_WAIT_QUEUE_HEAD(rtas_log_wait);
+static DECLARE_WAIT_QUEUE_HEAD(rtas_log_wait);
 
 static char *rtas_log_buf;
 static unsigned long rtas_log_start;
@@ -329,7 +329,7 @@ static unsigned int rtas_log_poll(struct file *file, poll_table * wait)
 	return 0;
 }
 
-const struct file_operations proc_rtas_log_operations = {
+static const struct file_operations proc_rtas_log_operations = {
 	.read =		rtas_log_read,
 	.poll =		rtas_log_poll,
 	.open =		rtas_log_open,
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index f5d29f5b13c1..063a0d2fba30 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -109,7 +109,7 @@ static void __init fwnmi_init(void)
 		fwnmi_active = 1;
 }
 
-void pseries_8259_cascade(unsigned int irq, struct irq_desc *desc)
+static void pseries_8259_cascade(unsigned int irq, struct irq_desc *desc)
 {
 	unsigned int cascade_irq = i8259_irq();
 	if (cascade_irq != NO_IRQ)
@@ -314,6 +314,76 @@ static int pseries_set_xdabr(unsigned long dabr)
 			H_DABRX_KERNEL | H_DABRX_USER);
 }
 
+#define CMO_CHARACTERISTICS_TOKEN 44
+#define CMO_MAXLENGTH 1026
+
+/**
+ * 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)
+{
+	char *ptr, *key, *value, *end;
+	int call_status;
+	int PrPSP = -1;
+	int SecPSP = -1;
+
+	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, "PrPSP"))
+				PrPSP = simple_strtol(value, NULL, 10);
+			else if (0 == strcmp(key, "SecPSP"))
+				SecPSP = simple_strtol(value, NULL, 10);
+			value = key = ptr + 1;
+		}
+		ptr++;
+	}
+
+	if (PrPSP != -1 || SecPSP != -1) {
+		pr_info("CMO enabled\n");
+		pr_debug("CMO enabled, PrPSP=%d, SecPSP=%d\n", PrPSP, SecPSP);
+		powerpc_firmware_features |= FW_FEATURE_CMO;
+	} else
+		pr_debug("CMO not enabled, PrPSP=%d, SecPSP=%d\n", PrPSP, SecPSP);
+	spin_unlock(&rtas_data_buf_lock);
+	pr_debug(" <- fw_cmo_feature_init()\n");
+}
+
 /*
  * Early initialization.  Relocation is on but do not reference unbolted pages
  */
@@ -329,6 +399,7 @@ static void __init pSeries_init_early(void)
 	else if (firmware_has_feature(FW_FEATURE_XDABR))
 		ppc_md.set_dabr = pseries_set_xdabr;
 
+	pSeries_cmo_feature_init();
 	iommu_init_early_pSeries();
 
 	pr_debug(" <- pSeries_init_early()\n");
@@ -482,7 +553,7 @@ static int pSeries_pci_probe_mode(struct pci_bus *bus)
  * possible with power button press. If ibm,power-off-ups token is used
  * it will allow auto poweron after power is restored.
  */
-void pSeries_power_off(void)
+static void pSeries_power_off(void)
 {
 	int rc;
 	int rtas_poweroff_ups_token = rtas_token("ibm,power-off-ups");
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index ebebc28fe895..0fc830f576f5 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -383,13 +383,11 @@ static irqreturn_t xics_ipi_dispatch(int cpu)
 			mb();
 			smp_message_recv(PPC_MSG_RESCHEDULE);
 		}
-#if 0
-		if (test_and_clear_bit(PPC_MSG_MIGRATE_TASK,
+		if (test_and_clear_bit(PPC_MSG_CALL_FUNC_SINGLE,
 				       &xics_ipi_message[cpu].value)) {
 			mb();
-			smp_message_recv(PPC_MSG_MIGRATE_TASK);
+			smp_message_recv(PPC_MSG_CALL_FUNC_SINGLE);
 		}
-#endif
 #if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
 		if (test_and_clear_bit(PPC_MSG_DEBUGGER_BREAK,
 				       &xics_ipi_message[cpu].value)) {