From e22f628395432b967f2f505858c64450f7835365 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Sun, 6 Sep 2009 23:31:25 +0000
Subject: [PATCH 001/151] Convert /proc/device-tree/ to seq_file

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 fs/proc/proc_devtree.c | 41 +++++++++++++++++++++--------------------
 1 file changed, 21 insertions(+), 20 deletions(-)

diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c
index 7ba79a54948c..123257bb356b 100644
--- a/fs/proc/proc_devtree.c
+++ b/fs/proc/proc_devtree.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/time.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/stat.h>
 #include <linux/string.h>
 #include <asm/prom.h>
@@ -25,26 +26,27 @@ static struct proc_dir_entry *proc_device_tree;
 /*
  * Supply data on a read from /proc/device-tree/node/property.
  */
-static int property_read_proc(char *page, char **start, off_t off,
-			      int count, int *eof, void *data)
+static int property_proc_show(struct seq_file *m, void *v)
 {
-	struct property *pp = data;
-	int n;
+	struct property *pp = m->private;
 
-	if (off >= pp->length) {
-		*eof = 1;
-		return 0;
-	}
-	n = pp->length - off;
-	if (n > count)
-		n = count;
-	else
-		*eof = 1;
-	memcpy(page, (char *)pp->value + off, n);
-	*start = page;
-	return n;
+	seq_write(m, pp->value, pp->length);
+	return 0;
 }
 
+static int property_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, property_proc_show, PDE(inode)->data);
+}
+
+static const struct file_operations property_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= property_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 /*
  * For a node with a name like "gc@10", we make symlinks called "gc"
  * and "@10" to it.
@@ -63,10 +65,9 @@ __proc_device_tree_add_prop(struct proc_dir_entry *de, struct property *pp,
 	 * Unfortunately proc_register puts each new entry
 	 * at the beginning of the list.  So we rearrange them.
 	 */
-	ent = create_proc_read_entry(name,
-				     strncmp(name, "security-", 9)
-				     ? S_IRUGO : S_IRUSR, de,
-				     property_read_proc, pp);
+	ent = proc_create_data(name,
+			       strncmp(name, "security-", 9) ? S_IRUGO : S_IRUSR,
+			       de, &property_proc_fops, pp);
 	if (ent == NULL)
 		return NULL;
 

From 7424639af480a05cac428ec7e7e38a11d6ff5734 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Mon, 22 Jun 2009 15:56:39 +0000
Subject: [PATCH 002/151] powerpc/ps3: Use pr_devel() in ps3/mm.c

The non-debug case in ps3/mm.c uses pr_debug(), so that the compiler
still does type checks etc. and doesn't complain about unused
variables in the non-debug case.

However with DEBUG=n and CONFIG_DYNAMIC_DEBUG=y there's still code
generated for those pr_debugs().

size before:
   text    data     bss     dec     hex filename
  17553	   4112	     88	  21753	   54f9	arch/powerpc/platforms/ps3/mm.o

size after:
   text    data     bss     dec     hex filename
   7377	    776	     88	   8241	   2031	arch/powerpc/platforms/ps3/mm.o

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Geoff Levand <geoffrey.levand@am.sony.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/ps3/mm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c
index 189a25b80735..e81b028a2a48 100644
--- a/arch/powerpc/platforms/ps3/mm.c
+++ b/arch/powerpc/platforms/ps3/mm.c
@@ -34,7 +34,7 @@
 #if defined(DEBUG)
 #define DBG udbg_printf
 #else
-#define DBG pr_debug
+#define DBG pr_devel
 #endif
 
 enum {

From 64eb38a6e9732f45d518b9e522d613195c930e8f Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Mon, 5 Oct 2009 07:44:27 +0000
Subject: [PATCH 003/151] powerpc: Make it possible to select hibernation on
 all PowerPCs

Just as with kexec, hibernation may fail even on well-tested platforms:
some PCI device, a driver of which doesn't play well with hibernation,
is enough to break resuming.

Hibernation code is not much platform dependent, and hiding features only
because these were not verified on a particular hardware is
counterproductive: we just prevent the features from being widely tested.

For example, with this patch I just tested hibernation on a MPC83xx
board, and it works quite well, modulo a few drivers that need some
fixing.

So, let's make it possible to select hibernation support for all
PowerPCs, then let's wait for any possible bug reports, and actually fix
(or just collect ;-) the bugs instead of hiding them. If some platforms
really can't stand hibernation, we can make a blacklist, with proper
comments why exactly hibernation doesn't work, whether it is possible to
fix, and what needs to be done to fix it.

CONFIG_HIBERNATION is still =n by default, so the commit doesn't change
anything apart from ability to set it to =y.

I'm not sure if EXPERIMENTAL dependency is needed, I'd rather not add it
for a few reasons:

1) It doesn't matter much, for distro kernels user has no clue that some
   feature is experimental. Majority of defconfigs enable EXPERIMENTAL
   anyway (90 vs. 4, which, btw, means that EXPERIMENTAL is overused
   in Kconfigs);

2) EXPERIMENTAL is a good thing for features that change default
   behaviour of a kernel, while for hibernation user has to explicitly
   issue 'echo disk > /sys/power/state' to trigger any hibernation bugs;

3) Per init/Kconfig, EXPERIMENTAL is a good thing to scare and discourage
   users from 'widespread use of a feature', while we want to encourage
   that use.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/Kconfig | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2ba14e77296c..c01580d86fdd 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -199,19 +199,8 @@ config DEFAULT_UIMAGE
 config REDBOOT
 	bool
 
-config HIBERNATE_32
-	bool
-	depends on (PPC_PMAC && !SMP) || BROKEN
-	default y
-
-config HIBERNATE_64
-	bool
-	depends on BROKEN || (PPC_PMAC64 && EXPERIMENTAL)
-	default y
-
 config ARCH_HIBERNATION_POSSIBLE
 	bool
-	depends on (PPC64 && HIBERNATE_64) || (PPC32 && HIBERNATE_32)
 	default y
 
 config ARCH_SUSPEND_POSSIBLE

From 188917e183cf9ad0374b571006d0fc6d48a7f447 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 24 Sep 2009 19:29:13 +0000
Subject: [PATCH 004/151] powerpc: Move /proc/ppc64 to /proc/powerpc and add
 symlink

Some of the stuff in /proc/ppc64 such as the RTAS bits are actually
useful to some 32-bit platforms. Rename the file, and create a
symlink on 64-bit for backward compatibility

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/Makefile                  |   2 +-
 arch/powerpc/kernel/lparcfg.c                 |   4 +-
 .../kernel/{proc_ppc64.c => proc_powerpc.c}   | 102 +++++++++---------
 arch/powerpc/kernel/rtas_flash.c              |  10 +-
 arch/powerpc/platforms/pseries/reconfig.c     |   6 +-
 arch/powerpc/platforms/pseries/scanlog.c      |   4 +-
 6 files changed, 66 insertions(+), 62 deletions(-)
 rename arch/powerpc/kernel/{proc_ppc64.c => proc_powerpc.c} (87%)

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index b23664a0b86c..3faa39114219 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -42,7 +42,7 @@ obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
 obj-$(CONFIG_PPC_OF)		+= of_device.o of_platform.o prom_parse.o
 obj-$(CONFIG_PPC_CLOCK)		+= clock.o
-procfs-$(CONFIG_PPC64)		:= proc_ppc64.o
+procfs-y			:= proc_powerpc.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
 rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI)	:= rtas_pci.o
 obj-$(CONFIG_PPC_RTAS)		+= rtas.o rtas-rtc.o $(rtaspci-y-y)
diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c
index ed0ac4e4b8d8..79a00bb9c64c 100644
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -781,9 +781,9 @@ static int __init lparcfg_init(void)
 			!firmware_has_feature(FW_FEATURE_ISERIES))
 		mode |= S_IWUSR;
 
-	ent = proc_create("ppc64/lparcfg", mode, NULL, &lparcfg_fops);
+	ent = proc_create("powerpc/lparcfg", mode, NULL, &lparcfg_fops);
 	if (!ent) {
-		printk(KERN_ERR "Failed to create ppc64/lparcfg\n");
+		printk(KERN_ERR "Failed to create powerpc/lparcfg\n");
 		return -EIO;
 	}
 
diff --git a/arch/powerpc/kernel/proc_ppc64.c b/arch/powerpc/kernel/proc_powerpc.c
similarity index 87%
rename from arch/powerpc/kernel/proc_ppc64.c
rename to arch/powerpc/kernel/proc_powerpc.c
index c647ddef40dc..1ed3b8d7981e 100644
--- a/arch/powerpc/kernel/proc_ppc64.c
+++ b/arch/powerpc/kernel/proc_powerpc.c
@@ -28,55 +28,7 @@
 #include <asm/uaccess.h>
 #include <asm/prom.h>
 
-static loff_t  page_map_seek( struct file *file, loff_t off, int whence);
-static ssize_t page_map_read( struct file *file, char __user *buf, size_t nbytes,
-			      loff_t *ppos);
-static int     page_map_mmap( struct file *file, struct vm_area_struct *vma );
-
-static const struct file_operations page_map_fops = {
-	.llseek	= page_map_seek,
-	.read	= page_map_read,
-	.mmap	= page_map_mmap
-};
-
-/*
- * Create the ppc64 and ppc64/rtas directories early. This allows us to
- * assume that they have been previously created in drivers.
- */
-static int __init proc_ppc64_create(void)
-{
-	struct proc_dir_entry *root;
-
-	root = proc_mkdir("ppc64", NULL);
-	if (!root)
-		return 1;
-
-	if (!of_find_node_by_path("/rtas"))
-		return 0;
-
-	if (!proc_mkdir("rtas", root))
-		return 1;
-
-	if (!proc_symlink("rtas", NULL, "ppc64/rtas"))
-		return 1;
-
-	return 0;
-}
-core_initcall(proc_ppc64_create);
-
-static int __init proc_ppc64_init(void)
-{
-	struct proc_dir_entry *pde;
-
-	pde = proc_create_data("ppc64/systemcfg", S_IFREG|S_IRUGO, NULL,
-			       &page_map_fops, vdso_data);
-	if (!pde)
-		return 1;
-	pde->size = PAGE_SIZE;
-
-	return 0;
-}
-__initcall(proc_ppc64_init);
+#ifdef CONFIG_PPC64
 
 static loff_t page_map_seek( struct file *file, loff_t off, int whence)
 {
@@ -120,3 +72,55 @@ static int page_map_mmap( struct file *file, struct vm_area_struct *vma )
 	return 0;
 }
 
+static const struct file_operations page_map_fops = {
+	.llseek	= page_map_seek,
+	.read	= page_map_read,
+	.mmap	= page_map_mmap
+};
+
+
+static int __init proc_ppc64_init(void)
+{
+	struct proc_dir_entry *pde;
+
+	pde = proc_create_data("powerpc/systemcfg", S_IFREG|S_IRUGO, NULL,
+			       &page_map_fops, vdso_data);
+	if (!pde)
+		return 1;
+	pde->size = PAGE_SIZE;
+
+	return 0;
+}
+__initcall(proc_ppc64_init);
+
+#endif /* CONFIG_PPC64 */
+
+/*
+ * Create the ppc64 and ppc64/rtas directories early. This allows us to
+ * assume that they have been previously created in drivers.
+ */
+static int __init proc_ppc64_create(void)
+{
+	struct proc_dir_entry *root;
+
+	root = proc_mkdir("powerpc", NULL);
+	if (!root)
+		return 1;
+
+#ifdef CONFIG_PPC64
+	if (!proc_symlink("ppc64", NULL, "powerpc"))
+		pr_err("Failed to create link /proc/ppc64 -> /proc/powerpc\n");
+#endif
+
+	if (!of_find_node_by_path("/rtas"))
+		return 0;
+
+	if (!proc_mkdir("rtas", root))
+		return 1;
+
+	if (!proc_symlink("rtas", NULL, "powerpc/rtas"))
+		return 1;
+
+	return 0;
+}
+core_initcall(proc_ppc64_create);
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 13011a96a977..a85117d5c9a4 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -6,7 +6,7 @@
  *      as published by the Free Software Foundation; either version
  *      2 of the License, or (at your option) any later version.
  *
- * /proc/ppc64/rtas/firmware_flash interface
+ * /proc/powerpc/rtas/firmware_flash interface
  *
  * This file implements a firmware_flash interface to pump a firmware
  * image into the kernel.  At reboot time rtas_restart() will see the
@@ -740,7 +740,7 @@ static int __init rtas_flash_init(void)
 		return 1;
 	}
 
-	firmware_flash_pde = create_flash_pde("ppc64/rtas/"
+	firmware_flash_pde = create_flash_pde("powerpc/rtas/"
 					      FIRMWARE_FLASH_NAME,
 					      &rtas_flash_operations);
 	if (firmware_flash_pde == NULL) {
@@ -754,7 +754,7 @@ static int __init rtas_flash_init(void)
 	if (rc != 0)
 		goto cleanup;
 
-	firmware_update_pde = create_flash_pde("ppc64/rtas/"
+	firmware_update_pde = create_flash_pde("powerpc/rtas/"
 					       FIRMWARE_UPDATE_NAME,
 					       &rtas_flash_operations);
 	if (firmware_update_pde == NULL) {
@@ -768,7 +768,7 @@ static int __init rtas_flash_init(void)
 	if (rc != 0)
 		goto cleanup;
 
-	validate_pde = create_flash_pde("ppc64/rtas/" VALIDATE_FLASH_NAME,
+	validate_pde = create_flash_pde("powerpc/rtas/" VALIDATE_FLASH_NAME,
 			      		&validate_flash_operations);
 	if (validate_pde == NULL) {
 		rc = -ENOMEM;
@@ -781,7 +781,7 @@ static int __init rtas_flash_init(void)
 	if (rc != 0)
 		goto cleanup;
 
-	manage_pde = create_flash_pde("ppc64/rtas/" MANAGE_FLASH_NAME,
+	manage_pde = create_flash_pde("powerpc/rtas/" MANAGE_FLASH_NAME,
 				      &manage_flash_operations);
 	if (manage_pde == NULL) {
 		rc = -ENOMEM;
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 2e2bbe120b90..5182d2b992c6 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -184,7 +184,7 @@ static int pSeries_reconfig_remove_node(struct device_node *np)
 }
 
 /*
- * /proc/ppc64/ofdt - yucky binary interface for adding and removing
+ * /proc/powerpc/ofdt - yucky binary interface for adding and removing
  * OF device nodes.  Should be deprecated as soon as we get an
  * in-kernel wrapper for the RTAS ibm,configure-connector call.
  */
@@ -543,7 +543,7 @@ static const struct file_operations ofdt_fops = {
 	.write = ofdt_write
 };
 
-/* create /proc/ppc64/ofdt write-only by root */
+/* create /proc/powerpc/ofdt write-only by root */
 static int proc_ppc64_create_ofdt(void)
 {
 	struct proc_dir_entry *ent;
@@ -551,7 +551,7 @@ static int proc_ppc64_create_ofdt(void)
 	if (!machine_is(pseries))
 		return 0;
 
-	ent = proc_create("ppc64/ofdt", S_IWUSR, NULL, &ofdt_fops);
+	ent = proc_create("powerpc/ofdt", S_IWUSR, NULL, &ofdt_fops);
 	if (ent)
 		ent->size = 0;
 
diff --git a/arch/powerpc/platforms/pseries/scanlog.c b/arch/powerpc/platforms/pseries/scanlog.c
index 417eca79df69..1b45c458f952 100644
--- a/arch/powerpc/platforms/pseries/scanlog.c
+++ b/arch/powerpc/platforms/pseries/scanlog.c
@@ -13,7 +13,7 @@
  * of this data using this driver.  A dump exists if the device-tree
  * /chosen/ibm,scan-log-data property exists.
  *
- * This driver exports /proc/ppc64/scan-log-dump which can be read.
+ * This driver exports /proc/powerpc/scan-log-dump which can be read.
  * The driver supports only sequential reads.
  *
  * The driver looks at a write to the driver for the single word "reset".
@@ -186,7 +186,7 @@ static int __init scanlog_init(void)
 	if (!data)
 		goto err;
 
-	ent = proc_create_data("ppc64/rtas/scan-log-dump", S_IRUSR, NULL,
+	ent = proc_create_data("powerpc/rtas/scan-log-dump", S_IRUSR, NULL,
 			       &scanlog_fops, data);
 	if (!ent)
 		goto err;

From 3d541c4b7f6efd55a98189afd1b2f1c9d048c1b3 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 24 Sep 2009 19:30:05 +0000
Subject: [PATCH 005/151] powerpc/chrp: Use the same RTAS daemon as pSeries

The CHRP code has some fishy timer based code to scan the RTAS event
log, which uses a 1KB stack buffer and doesn't even use the results.

The pSeries code as a nicer daemon that allows userspace to read the
event log and basically uses the same RTAS interface

This patch moves rtasd.c out of platform/pseries and makes it usable
by CHRP, after removing the old crufty event log mechanism in there.

The nvram logging part of the daemon is still only available on 64-bit
since the underlying nvram management routines aren't currently shared.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/Makefile                  |  1 +
 .../{platforms/pseries => kernel}/rtasd.c     | 48 ++++++++++++------
 arch/powerpc/platforms/Kconfig                |  5 ++
 arch/powerpc/platforms/chrp/Kconfig           |  2 +
 arch/powerpc/platforms/chrp/setup.c           | 50 -------------------
 arch/powerpc/platforms/pseries/Kconfig        |  1 +
 arch/powerpc/platforms/pseries/Makefile       |  2 +-
 7 files changed, 44 insertions(+), 65 deletions(-)
 rename arch/powerpc/{platforms/pseries => kernel}/rtasd.c (95%)

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 3faa39114219..c002b0410219 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -46,6 +46,7 @@ procfs-y			:= proc_powerpc.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
 rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI)	:= rtas_pci.o
 obj-$(CONFIG_PPC_RTAS)		+= rtas.o rtas-rtc.o $(rtaspci-y-y)
+obj-$(CONFIG_PPC_RTAS_DAEMON)	+= rtasd.o
 obj-$(CONFIG_RTAS_FLASH)	+= rtas_flash.o
 obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
 obj-$(CONFIG_LPARCFG)		+= lparcfg.o
diff --git a/arch/powerpc/platforms/pseries/rtasd.c b/arch/powerpc/kernel/rtasd.c
similarity index 95%
rename from arch/powerpc/platforms/pseries/rtasd.c
rename to arch/powerpc/kernel/rtasd.c
index b3cbac855924..2e4832ab2108 100644
--- a/arch/powerpc/platforms/pseries/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -39,6 +39,7 @@ static unsigned long rtas_log_start;
 static unsigned long rtas_log_size;
 
 static int surveillance_timeout = -1;
+
 static unsigned int rtas_error_log_max;
 static unsigned int rtas_error_log_buffer_max;
 
@@ -213,9 +214,11 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
 		return;
 	}
 
+#ifdef CONFIG_PPC64
 	/* Write error to NVRAM */
 	if (logging_enabled && !(err_type & ERR_FLAG_BOOT))
 		nvram_write_error_log(buf, len, err_type, error_log_cnt);
+#endif /* CONFIG_PPC64 */
 
 	/*
 	 * rtas errors can occur during boot, and we do want to capture
@@ -264,7 +267,6 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal)
 
 }
 
-
 static int rtas_log_open(struct inode * inode, struct file * file)
 {
 	return 0;
@@ -300,6 +302,7 @@ static ssize_t rtas_log_read(struct file * file, char __user * buf,
 		return -ENOMEM;
 
 	spin_lock_irqsave(&rtasd_log_lock, s);
+
 	/* if it's 0, then we know we got the last one (the one in NVRAM) */
 	while (rtas_log_size == 0) {
 		if (file->f_flags & O_NONBLOCK) {
@@ -313,7 +316,9 @@ static ssize_t rtas_log_read(struct file * file, char __user * buf,
 			error = -ENODATA;
 			goto out;
 		}
+#ifdef CONFIG_PPC64
 		nvram_clear_error_log();
+#endif /* CONFIG_PPC64 */
 
 		spin_unlock_irqrestore(&rtasd_log_lock, s);
 		error = wait_event_interruptible(rtas_log_wait, rtas_log_size);
@@ -427,14 +432,11 @@ static void rtas_event_scan(struct work_struct *w)
 	put_online_cpus();
 }
 
-static void start_event_scan(void)
+#ifdef CONFIG_PPC64
+static void retreive_nvram_error_log(void)
 {
-	unsigned int err_type;
-	int rc;
-
-	printk(KERN_DEBUG "RTAS daemon started\n");
-	pr_debug("rtasd: will sleep for %d milliseconds\n",
-		 (30000 / rtas_event_scan_rate));
+	unsigned int err_type ;
+	int rc ;
 
 	/* See if we have any error stored in NVRAM */
 	memset(logdata, 0, rtas_error_log_max);
@@ -442,12 +444,26 @@ static void start_event_scan(void)
 	                          &err_type, &error_log_cnt);
 	/* We can use rtas_log_buf now */
 	logging_enabled = 1;
-
 	if (!rc) {
 		if (err_type != ERR_FLAG_ALREADY_LOGGED) {
 			pSeries_log_error(logdata, err_type | ERR_FLAG_BOOT, 0);
 		}
 	}
+}
+#else /* CONFIG_PPC64 */
+static void retreive_nvram_error_log(void)
+{
+}
+#endif /* CONFIG_PPC64 */
+
+static void start_event_scan(void)
+{
+	printk(KERN_DEBUG "RTAS daemon started\n");
+	pr_debug("rtasd: will sleep for %d milliseconds\n",
+		 (30000 / rtas_event_scan_rate));
+
+	/* Retreive errors from nvram if any */
+	retreive_nvram_error_log();
 
 	schedule_delayed_work_on(first_cpu(cpu_online_map), &event_scan_work,
 				 event_scan_delay);
@@ -457,13 +473,13 @@ static int __init rtas_init(void)
 {
 	struct proc_dir_entry *entry;
 
-	if (!machine_is(pseries))
+	if (!machine_is(pseries) && !machine_is(chrp))
 		return 0;
 
 	/* No RTAS */
 	event_scan = rtas_token("event-scan");
 	if (event_scan == RTAS_UNKNOWN_SERVICE) {
-		printk(KERN_DEBUG "rtasd: no event-scan on system\n");
+		printk(KERN_INFO "rtasd: No event-scan on system\n");
 		return -ENODEV;
 	}
 
@@ -483,7 +499,7 @@ static int __init rtas_init(void)
 		return -ENOMEM;
 	}
 
-	entry = proc_create("ppc64/rtas/error_log", S_IRUSR, NULL,
+	entry = proc_create("powerpc/rtas/error_log", S_IRUSR, NULL,
 			    &proc_rtas_log_operations);
 	if (!entry)
 		printk(KERN_ERR "Failed to create error_log proc entry\n");
@@ -492,11 +508,16 @@ static int __init rtas_init(void)
 
 	return 0;
 }
+__initcall(rtas_init);
 
 static int __init surveillance_setup(char *str)
 {
 	int i;
 
+	/* We only do surveillance on pseries */
+	if (!machine_is(pseries))
+		return 0;
+
 	if (get_option(&str,&i)) {
 		if (i >= 0 && i <= 255)
 			surveillance_timeout = i;
@@ -504,6 +525,7 @@ static int __init surveillance_setup(char *str)
 
 	return 1;
 }
+__setup("surveillance=", surveillance_setup);
 
 static int __init rtasmsgs_setup(char *str)
 {
@@ -514,6 +536,4 @@ static int __init rtasmsgs_setup(char *str)
 
 	return 1;
 }
-__initcall(rtas_init);
-__setup("surveillance=", surveillance_setup);
 __setup("rtasmsgs=", rtasmsgs_setup);
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 04a8061045c4..56bf12692f37 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -86,6 +86,11 @@ config RTAS_ERROR_LOGGING
 	depends on PPC_RTAS
 	default n
 
+config PPC_RTAS_DAEMON
+	bool
+	depends on PPC_RTAS
+	default n
+
 config RTAS_PROC
 	bool "Proc interface to RTAS"
 	depends on PPC_RTAS
diff --git a/arch/powerpc/platforms/chrp/Kconfig b/arch/powerpc/platforms/chrp/Kconfig
index 37d438bd5b7a..bc0b0efdc5fe 100644
--- a/arch/powerpc/platforms/chrp/Kconfig
+++ b/arch/powerpc/platforms/chrp/Kconfig
@@ -5,6 +5,8 @@ config PPC_CHRP
 	select PPC_I8259
 	select PPC_INDIRECT_PCI
 	select PPC_RTAS
+	select PPC_RTAS_DAEMON
+	select RTAS_ERROR_LOGGING
 	select PPC_MPC106
 	select PPC_UDBG_16550
 	select PPC_NATIVE
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index cd4ad9aea760..52f3df3b4ca0 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -364,19 +364,6 @@ void __init chrp_setup_arch(void)
 	if (ppc_md.progress) ppc_md.progress("Linux/PPC "UTS_RELEASE"\n", 0x0);
 }
 
-void
-chrp_event_scan(unsigned long unused)
-{
-	unsigned char log[1024];
-	int ret = 0;
-
-	/* XXX: we should loop until the hardware says no more error logs -- Cort */
-	rtas_call(rtas_token("event-scan"), 4, 1, &ret, 0xffffffff, 0,
-		  __pa(log), 1024);
-	mod_timer(&__get_cpu_var(heartbeat_timer),
-		  jiffies + event_scan_interval);
-}
-
 static void chrp_8259_cascade(unsigned int irq, struct irq_desc *desc)
 {
 	unsigned int cascade_irq = i8259_irq();
@@ -568,9 +555,6 @@ void __init chrp_init_IRQ(void)
 void __init
 chrp_init2(void)
 {
-	struct device_node *device;
-	const unsigned int *p = NULL;
-
 #ifdef CONFIG_NVRAM
 	chrp_nvram_init();
 #endif
@@ -582,40 +566,6 @@ chrp_init2(void)
 	request_region(0x80,0x10,"dma page reg");
 	request_region(0xc0,0x20,"dma2");
 
-	/* Get the event scan rate for the rtas so we know how
-	 * often it expects a heartbeat. -- Cort
-	 */
-	device = of_find_node_by_name(NULL, "rtas");
-	if (device)
-		p = of_get_property(device, "rtas-event-scan-rate", NULL);
-	if (p && *p) {
-		/*
-		 * Arrange to call chrp_event_scan at least *p times
-		 * per minute.  We use 59 rather than 60 here so that
-		 * the rate will be slightly higher than the minimum.
-		 * This all assumes we don't do hotplug CPU on any
-		 * machine that needs the event scans done.
-		 */
-		unsigned long interval, offset;
-		int cpu, ncpus;
-		struct timer_list *timer;
-
-		interval = HZ * 59 / *p;
-		offset = HZ;
-		ncpus = num_online_cpus();
-		event_scan_interval = ncpus * interval;
-		for (cpu = 0; cpu < ncpus; ++cpu) {
-			timer = &per_cpu(heartbeat_timer, cpu);
-			setup_timer(timer, chrp_event_scan, 0);
-			timer->expires = jiffies + offset;
-			add_timer_on(timer, cpu);
-			offset += interval;
-		}
-		printk("RTAS Event Scan Rate: %u (%lu jiffies)\n",
-		       *p, interval);
-	}
-	of_node_put(device);
-
 	if (ppc_md.progress)
 		ppc_md.progress("  Have fun!    ", 0x7777);
 }
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index f0e6f28427bd..26a24bd92623 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -4,6 +4,7 @@ config PPC_PSERIES
 	select MPIC
 	select PPC_I8259
 	select PPC_RTAS
+	select PPC_RTAS_DAEMON
 	select RTAS_ERROR_LOGGING
 	select PPC_UDBG_16550
 	select PPC_NATIVE
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 790c0b872d4f..4b1c422b8145 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -7,7 +7,7 @@ EXTRA_CFLAGS		+= -DDEBUG
 endif
 
 obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
-			   setup.o iommu.o ras.o rtasd.o \
+			   setup.o iommu.o ras.o \
 			   firmware.o power.o
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_XICS)	+= xics.o

From d35ef90bf9e7cab9aa85e9c0724bd1ac6f784601 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Mon, 12 Oct 2009 05:50:41 +0000
Subject: [PATCH 006/151] of/platform: Implement support for dev_pm_ops

Linux power management subsystem supports vast amount of new PM
callbacks that are crucial for proper suspend and hibernation support
in drivers.

This patch implements support for dev_pm_ops, preserving support
for legacy callbacks.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 drivers/of/platform.c | 323 ++++++++++++++++++++++++++++++++++++++----
 1 file changed, 299 insertions(+), 24 deletions(-)

diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 298de0f95d70..d58ade170c4b 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -65,28 +65,6 @@ static int of_platform_device_remove(struct device *dev)
 	return 0;
 }
 
-static int of_platform_device_suspend(struct device *dev, pm_message_t state)
-{
-	struct of_device *of_dev = to_of_device(dev);
-	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
-	int error = 0;
-
-	if (dev->driver && drv->suspend)
-		error = drv->suspend(of_dev, state);
-	return error;
-}
-
-static int of_platform_device_resume(struct device * dev)
-{
-	struct of_device *of_dev = to_of_device(dev);
-	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
-	int error = 0;
-
-	if (dev->driver && drv->resume)
-		error = drv->resume(of_dev);
-	return error;
-}
-
 static void of_platform_device_shutdown(struct device *dev)
 {
 	struct of_device *of_dev = to_of_device(dev);
@@ -96,16 +74,313 @@ static void of_platform_device_shutdown(struct device *dev)
 		drv->shutdown(of_dev);
 }
 
+#ifdef CONFIG_PM_SLEEP
+
+static int of_platform_legacy_suspend(struct device *dev, pm_message_t mesg)
+{
+	struct of_device *of_dev = to_of_device(dev);
+	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
+	int ret = 0;
+
+	if (dev->driver && drv->suspend)
+		ret = drv->suspend(of_dev, mesg);
+	return ret;
+}
+
+static int of_platform_legacy_resume(struct device *dev)
+{
+	struct of_device *of_dev = to_of_device(dev);
+	struct of_platform_driver *drv = to_of_platform_driver(dev->driver);
+	int ret = 0;
+
+	if (dev->driver && drv->resume)
+		ret = drv->resume(of_dev);
+	return ret;
+}
+
+static int of_platform_pm_prepare(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (drv && drv->pm && drv->pm->prepare)
+		ret = drv->pm->prepare(dev);
+
+	return ret;
+}
+
+static void of_platform_pm_complete(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+
+	if (drv && drv->pm && drv->pm->complete)
+		drv->pm->complete(dev);
+}
+
+#ifdef CONFIG_SUSPEND
+
+static int of_platform_pm_suspend(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->suspend)
+			ret = drv->pm->suspend(dev);
+	} else {
+		ret = of_platform_legacy_suspend(dev, PMSG_SUSPEND);
+	}
+
+	return ret;
+}
+
+static int of_platform_pm_suspend_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->suspend_noirq)
+			ret = drv->pm->suspend_noirq(dev);
+	}
+
+	return ret;
+}
+
+static int of_platform_pm_resume(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->resume)
+			ret = drv->pm->resume(dev);
+	} else {
+		ret = of_platform_legacy_resume(dev);
+	}
+
+	return ret;
+}
+
+static int of_platform_pm_resume_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->resume_noirq)
+			ret = drv->pm->resume_noirq(dev);
+	}
+
+	return ret;
+}
+
+#else /* !CONFIG_SUSPEND */
+
+#define of_platform_pm_suspend		NULL
+#define of_platform_pm_resume		NULL
+#define of_platform_pm_suspend_noirq	NULL
+#define of_platform_pm_resume_noirq	NULL
+
+#endif /* !CONFIG_SUSPEND */
+
+#ifdef CONFIG_HIBERNATION
+
+static int of_platform_pm_freeze(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->freeze)
+			ret = drv->pm->freeze(dev);
+	} else {
+		ret = of_platform_legacy_suspend(dev, PMSG_FREEZE);
+	}
+
+	return ret;
+}
+
+static int of_platform_pm_freeze_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->freeze_noirq)
+			ret = drv->pm->freeze_noirq(dev);
+	}
+
+	return ret;
+}
+
+static int of_platform_pm_thaw(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->thaw)
+			ret = drv->pm->thaw(dev);
+	} else {
+		ret = of_platform_legacy_resume(dev);
+	}
+
+	return ret;
+}
+
+static int of_platform_pm_thaw_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->thaw_noirq)
+			ret = drv->pm->thaw_noirq(dev);
+	}
+
+	return ret;
+}
+
+static int of_platform_pm_poweroff(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->poweroff)
+			ret = drv->pm->poweroff(dev);
+	} else {
+		ret = of_platform_legacy_suspend(dev, PMSG_HIBERNATE);
+	}
+
+	return ret;
+}
+
+static int of_platform_pm_poweroff_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->poweroff_noirq)
+			ret = drv->pm->poweroff_noirq(dev);
+	}
+
+	return ret;
+}
+
+static int of_platform_pm_restore(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->restore)
+			ret = drv->pm->restore(dev);
+	} else {
+		ret = of_platform_legacy_resume(dev);
+	}
+
+	return ret;
+}
+
+static int of_platform_pm_restore_noirq(struct device *dev)
+{
+	struct device_driver *drv = dev->driver;
+	int ret = 0;
+
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
+		if (drv->pm->restore_noirq)
+			ret = drv->pm->restore_noirq(dev);
+	}
+
+	return ret;
+}
+
+#else /* !CONFIG_HIBERNATION */
+
+#define of_platform_pm_freeze		NULL
+#define of_platform_pm_thaw		NULL
+#define of_platform_pm_poweroff		NULL
+#define of_platform_pm_restore		NULL
+#define of_platform_pm_freeze_noirq	NULL
+#define of_platform_pm_thaw_noirq		NULL
+#define of_platform_pm_poweroff_noirq	NULL
+#define of_platform_pm_restore_noirq	NULL
+
+#endif /* !CONFIG_HIBERNATION */
+
+static struct dev_pm_ops of_platform_dev_pm_ops = {
+	.prepare = of_platform_pm_prepare,
+	.complete = of_platform_pm_complete,
+	.suspend = of_platform_pm_suspend,
+	.resume = of_platform_pm_resume,
+	.freeze = of_platform_pm_freeze,
+	.thaw = of_platform_pm_thaw,
+	.poweroff = of_platform_pm_poweroff,
+	.restore = of_platform_pm_restore,
+	.suspend_noirq = of_platform_pm_suspend_noirq,
+	.resume_noirq = of_platform_pm_resume_noirq,
+	.freeze_noirq = of_platform_pm_freeze_noirq,
+	.thaw_noirq = of_platform_pm_thaw_noirq,
+	.poweroff_noirq = of_platform_pm_poweroff_noirq,
+	.restore_noirq = of_platform_pm_restore_noirq,
+};
+
+#define OF_PLATFORM_PM_OPS_PTR	(&of_platform_dev_pm_ops)
+
+#else /* !CONFIG_PM_SLEEP */
+
+#define OF_PLATFORM_PM_OPS_PTR	NULL
+
+#endif /* !CONFIG_PM_SLEEP */
+
 int of_bus_type_init(struct bus_type *bus, const char *name)
 {
 	bus->name = name;
 	bus->match = of_platform_bus_match;
 	bus->probe = of_platform_device_probe;
 	bus->remove = of_platform_device_remove;
-	bus->suspend = of_platform_device_suspend;
-	bus->resume = of_platform_device_resume;
 	bus->shutdown = of_platform_device_shutdown;
 	bus->dev_attrs = of_platform_device_attrs;
+	bus->pm = OF_PLATFORM_PM_OPS_PTR;
 	return bus_register(bus);
 }
 

From 551b81f26ffc2135b8490babad1a9ab12d617e8d Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Tue, 13 Oct 2009 19:44:44 +0000
Subject: [PATCH 007/151] powerpc: Make NR_IRQS a CONFIG option

The irq_desc array consumes quite a lot of space, and for systems
that don't need or can't have 512 irqs it's just wasted space.

The first 16 are reserved for ISA, so the minimum of 32 is really
16 - and no one has asked for more than 512 so leave that as the
maximum.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/Kconfig           | 10 ++++++++++
 arch/powerpc/include/asm/irq.h |  4 ++--
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c01580d86fdd..3aa79f8e39e4 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -56,6 +56,16 @@ config IRQ_PER_CPU
 	bool
 	default y
 
+config NR_IRQS
+	int "Number of virtual interrupt numbers"
+	range 32 512
+	default "512"
+	help
+	  This defines the number of virtual interrupt numbers the kernel
+	  can manage. Virtual interrupt numbers are what you see in
+	  /proc/interrupts. If you configure your system to have too few,
+	  drivers will fail to load or worse - handle with care.
+
 config STACKTRACE_SUPPORT
 	bool
 	default y
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index bbcd1aaf3dfd..b83fcc81faed 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -34,8 +34,8 @@ extern atomic_t ppc_n_lost_interrupts;
  */
 #define NO_IRQ_IGNORE		((unsigned int)-1)
 
-/* Total number of virq in the platform (make it a CONFIG_* option ? */
-#define NR_IRQS		512
+/* Total number of virq in the platform */
+#define NR_IRQS		CONFIG_NR_IRQS
 
 /* Number of irqs reserved for the legacy controller */
 #define NUM_ISA_INTERRUPTS	16

From 59e3f837023d446924791f76fbdd4bcf8e09efcc Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Tue, 13 Oct 2009 19:44:47 +0000
Subject: [PATCH 008/151] powerpc/pseries: Use irq_has_action() in
 eeh_disable_irq()

Rather than open-coding our own check, use irq_has_action()
to check if an irq has an action - ie. is "in use".

irq_has_action() doesn't take the descriptor lock, but it
shouldn't matter - we're just using it as an indicator
that the irq is in use. disable_irq_nosync() will take
the descriptor lock before doing anything also.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/eeh_driver.c | 18 +-----------------
 1 file changed, 1 insertion(+), 17 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/eeh_driver.c b/arch/powerpc/platforms/pseries/eeh_driver.c
index 0e8db6771252..ef8e45448480 100644
--- a/arch/powerpc/platforms/pseries/eeh_driver.c
+++ b/arch/powerpc/platforms/pseries/eeh_driver.c
@@ -63,22 +63,6 @@ static void print_device_node_tree(struct pci_dn *pdn, int dent)
 }
 #endif
 
-/** 
- * irq_in_use - return true if this irq is being used 
- */
-static int irq_in_use(unsigned int irq)
-{
-	int rc = 0;
-	unsigned long flags;
-   struct irq_desc *desc = irq_desc + irq;
-
-	spin_lock_irqsave(&desc->lock, flags);
-	if (desc->action)
-		rc = 1;
-	spin_unlock_irqrestore(&desc->lock, flags);
-	return rc;
-}
-
 /**
  * eeh_disable_irq - disable interrupt for the recovering device
  */
@@ -93,7 +77,7 @@ static void eeh_disable_irq(struct pci_dev *dev)
 	if (dev->msi_enabled || dev->msix_enabled)
 		return;
 
-	if (!irq_in_use(dev->irq))
+	if (!irq_has_action(dev->irq))
 		return;
 
 	PCI_DN(dn)->eeh_mode |= EEH_MODE_IRQ_DISABLED;

From 6cff46f4bc6cc4a8a4154b0b6a2e669db08e8fd2 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Tue, 13 Oct 2009 19:44:51 +0000
Subject: [PATCH 009/151] powerpc: Remove get_irq_desc()

get_irq_desc() is a powerpc-specific version of irq_to_desc(). That
is reason enough to remove it, but it also doesn't know about sparse
irq_desc support which irq_to_desc() does (when we enable it).

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/irq.h                |  2 --
 arch/powerpc/kernel/crash.c                   |  2 +-
 arch/powerpc/kernel/irq.c                     | 28 ++++++++++---------
 .../powerpc/platforms/512x/mpc5121_ads_cpld.c |  2 +-
 arch/powerpc/platforms/52xx/media5200.c       |  2 +-
 arch/powerpc/platforms/82xx/pq2ads-pci-pic.c  |  2 +-
 .../platforms/85xx/socrates_fpga_pic.c        |  2 +-
 arch/powerpc/platforms/86xx/gef_pic.c         |  2 +-
 arch/powerpc/platforms/cell/beat_interrupt.c  |  2 +-
 arch/powerpc/platforms/cell/spider-pic.c      |  4 +--
 arch/powerpc/platforms/iseries/irq.c          |  2 +-
 arch/powerpc/platforms/powermac/pic.c         |  8 +++---
 arch/powerpc/platforms/pseries/xics.c         |  8 +++---
 arch/powerpc/sysdev/cpm1.c                    |  2 +-
 arch/powerpc/sysdev/cpm2_pic.c                | 10 ++++---
 arch/powerpc/sysdev/fsl_msi.c                 |  2 +-
 arch/powerpc/sysdev/i8259.c                   |  4 +--
 arch/powerpc/sysdev/ipic.c                    |  2 +-
 arch/powerpc/sysdev/mpc8xx_pic.c              |  2 +-
 arch/powerpc/sysdev/mpic.c                    | 18 ++++++------
 arch/powerpc/sysdev/mv64x60_pic.c             |  2 +-
 arch/powerpc/sysdev/qe_lib/qe_ic.c            |  4 +--
 arch/powerpc/sysdev/tsi108_pci.c              |  2 +-
 arch/powerpc/sysdev/uic.c                     |  6 ++--
 arch/powerpc/sysdev/xilinx_intc.c             |  2 +-
 25 files changed, 62 insertions(+), 60 deletions(-)

diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index b83fcc81faed..03dc28cdb4da 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -17,8 +17,6 @@
 #include <asm/atomic.h>
 
 
-#define get_irq_desc(irq) (&irq_desc[(irq)])
-
 /* Define a way to iterate across irqs. */
 #define for_each_irq(i) \
 	for ((i) = 0; (i) < NR_IRQS; ++(i))
diff --git a/arch/powerpc/kernel/crash.c b/arch/powerpc/kernel/crash.c
index 0a8439aafdd1..6f4613dd05ef 100644
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -373,7 +373,7 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	hard_irq_disable();
 
 	for_each_irq(i) {
-		struct irq_desc *desc = irq_desc + i;
+		struct irq_desc *desc = irq_to_desc(i);
 
 		if (desc->status & IRQ_INPROGRESS)
 			desc->chip->eoi(i);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index e5d121177984..65632215f020 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -190,7 +190,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	if (i < NR_IRQS) {
-		desc = get_irq_desc(i);
+		desc = irq_to_desc(i);
 		spin_lock_irqsave(&desc->lock, flags);
 		action = desc->action;
 		if (!action || !action->handler)
@@ -230,23 +230,25 @@ skip:
 #ifdef CONFIG_HOTPLUG_CPU
 void fixup_irqs(cpumask_t map)
 {
+	struct irq_desc *desc;
 	unsigned int irq;
 	static int warned;
 
 	for_each_irq(irq) {
 		cpumask_t mask;
 
-		if (irq_desc[irq].status & IRQ_PER_CPU)
+		desc = irq_to_desc(irq);
+		if (desc && desc->status & IRQ_PER_CPU)
 			continue;
 
-		cpumask_and(&mask, irq_desc[irq].affinity, &map);
+		cpumask_and(&mask, desc->affinity, &map);
 		if (any_online_cpu(mask) == NR_CPUS) {
 			printk("Breaking affinity for irq %i\n", irq);
 			mask = map;
 		}
-		if (irq_desc[irq].chip->set_affinity)
-			irq_desc[irq].chip->set_affinity(irq, &mask);
-		else if (irq_desc[irq].action && !(warned++))
+		if (desc->chip->set_affinity)
+			desc->chip->set_affinity(irq, &mask);
+		else if (desc->action && !(warned++))
 			printk("Cannot set affinity for irq %i\n", irq);
 	}
 
@@ -273,7 +275,7 @@ static inline void handle_one_irq(unsigned int irq)
 		return;
 	}
 
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 	saved_sp_limit = current->thread.ksp_limit;
 
 	irqtp->task = curtp->task;
@@ -535,7 +537,7 @@ struct irq_host *irq_alloc_host(struct device_node *of_node,
 			smp_wmb();
 
 			/* Clear norequest flags */
-			get_irq_desc(i)->status &= ~IRQ_NOREQUEST;
+			irq_to_desc(i)->status &= ~IRQ_NOREQUEST;
 
 			/* Legacy flags are left to default at this point,
 			 * one can then use irq_create_mapping() to
@@ -602,7 +604,7 @@ static int irq_setup_virq(struct irq_host *host, unsigned int virq,
 			    irq_hw_number_t hwirq)
 {
 	/* Clear IRQ_NOREQUEST flag */
-	get_irq_desc(virq)->status &= ~IRQ_NOREQUEST;
+	irq_to_desc(virq)->status &= ~IRQ_NOREQUEST;
 
 	/* map it */
 	smp_wmb();
@@ -732,7 +734,7 @@ unsigned int irq_create_of_mapping(struct device_node *controller,
 
 	/* Set type if specified and different than the current one */
 	if (type != IRQ_TYPE_NONE &&
-	    type != (get_irq_desc(virq)->status & IRQF_TRIGGER_MASK))
+	    type != (irq_to_desc(virq)->status & IRQF_TRIGGER_MASK))
 		set_irq_type(virq, type);
 	return virq;
 }
@@ -804,7 +806,7 @@ void irq_dispose_mapping(unsigned int virq)
 	irq_map[virq].hwirq = host->inval_irq;
 
 	/* Set some flags */
-	get_irq_desc(virq)->status |= IRQ_NOREQUEST;
+	irq_to_desc(virq)->status |= IRQ_NOREQUEST;
 
 	/* Free it */
 	irq_free_virt(virq, 1);
@@ -1001,7 +1003,7 @@ void irq_early_init(void)
 	unsigned int i;
 
 	for (i = 0; i < NR_IRQS; i++)
-		get_irq_desc(i)->status |= IRQ_NOREQUEST;
+		irq_to_desc(i)->status |= IRQ_NOREQUEST;
 }
 
 /* We need to create the radix trees late */
@@ -1064,7 +1066,7 @@ static int virq_debug_show(struct seq_file *m, void *private)
 		      "chip name", "host name");
 
 	for (i = 1; i < NR_IRQS; i++) {
-		desc = get_irq_desc(i);
+		desc = irq_to_desc(i);
 		spin_lock_irqsave(&desc->lock, flags);
 
 		if (desc->action && desc->action->handler) {
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index a6ce80566625..cd70ee1667fa 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -132,7 +132,7 @@ static int
 cpld_pic_host_map(struct irq_host *h, unsigned int virq,
 			     irq_hw_number_t hw)
 {
-	get_irq_desc(virq)->status |= IRQ_LEVEL;
+	irq_to_desc(virq)->status |= IRQ_LEVEL;
 	set_irq_chip_and_handler(virq, &cpld_pic, handle_level_irq);
 	return 0;
 }
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 68e4f1696d14..478020358748 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -114,7 +114,7 @@ void media5200_irq_cascade(unsigned int virq, struct irq_desc *desc)
 static int media5200_irq_map(struct irq_host *h, unsigned int virq,
 			     irq_hw_number_t hw)
 {
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 
 	pr_debug("%s: h=%p, virq=%i, hwirq=%i\n", __func__, h, virq, (int)hw);
 	set_irq_chip_data(virq, &media5200_irq);
diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
index 7ee979f323d1..a682331ba0ff 100644
--- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
+++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
@@ -107,7 +107,7 @@ static void pq2ads_pci_irq_demux(unsigned int irq, struct irq_desc *desc)
 static int pci_pic_host_map(struct irq_host *h, unsigned int virq,
 			    irq_hw_number_t hw)
 {
-	get_irq_desc(virq)->status |= IRQ_LEVEL;
+	irq_to_desc(virq)->status |= IRQ_LEVEL;
 	set_irq_chip_data(virq, h->host_data);
 	set_irq_chip_and_handler(virq, &pq2ads_pci_ic, handle_level_irq);
 	return 0;
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index 60edf63d0157..e59920aa6668 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -245,7 +245,7 @@ static int socrates_fpga_pic_host_map(struct irq_host *h, unsigned int virq,
 		irq_hw_number_t hwirq)
 {
 	/* All interrupts are LEVEL sensitive */
-	get_irq_desc(virq)->status |= IRQ_LEVEL;
+	irq_to_desc(virq)->status |= IRQ_LEVEL;
 	set_irq_chip_and_handler(virq, &socrates_fpga_pic_chip,
 			handle_fasteoi_irq);
 
diff --git a/arch/powerpc/platforms/86xx/gef_pic.c b/arch/powerpc/platforms/86xx/gef_pic.c
index 50d0a2b63809..978d6cb37516 100644
--- a/arch/powerpc/platforms/86xx/gef_pic.c
+++ b/arch/powerpc/platforms/86xx/gef_pic.c
@@ -163,7 +163,7 @@ static int gef_pic_host_map(struct irq_host *h, unsigned int virq,
 			  irq_hw_number_t hwirq)
 {
 	/* All interrupts are LEVEL sensitive */
-	get_irq_desc(virq)->status |= IRQ_LEVEL;
+	irq_to_desc(virq)->status |= IRQ_LEVEL;
 	set_irq_chip_and_handler(virq, &gef_pic_chip, handle_level_irq);
 
 	return 0;
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index 72254848a228..4a2bbff57698 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -136,7 +136,7 @@ static void beatic_pic_host_unmap(struct irq_host *h, unsigned int virq)
 static int beatic_pic_host_map(struct irq_host *h, unsigned int virq,
 			       irq_hw_number_t hw)
 {
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 	int64_t	err;
 
 	err = beat_construct_and_connect_irq_plug(virq, hw);
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 4e5655624ae8..9dd63c5d11a8 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -102,7 +102,7 @@ static void spider_ack_irq(unsigned int virq)
 
 	/* Reset edge detection logic if necessary
 	 */
-	if (get_irq_desc(virq)->status & IRQ_LEVEL)
+	if (irq_to_desc(virq)->status & IRQ_LEVEL)
 		return;
 
 	/* Only interrupts 47 to 50 can be set to edge */
@@ -119,7 +119,7 @@ static int spider_set_irq_type(unsigned int virq, unsigned int type)
 	struct spider_pic *pic = spider_virq_to_pic(virq);
 	unsigned int hw = irq_map[virq].hwirq;
 	void __iomem *cfg = spider_get_irq_config(pic, hw);
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 	u32 old_mask;
 	u32 ic;
 
diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c
index 94f444758836..f8446ea31189 100644
--- a/arch/powerpc/platforms/iseries/irq.c
+++ b/arch/powerpc/platforms/iseries/irq.c
@@ -214,7 +214,7 @@ void __init iSeries_activate_IRQs()
 	unsigned long flags;
 
 	for_each_irq (irq) {
-		struct irq_desc *desc = get_irq_desc(irq);
+		struct irq_desc *desc = irq_to_desc(irq);
 
 		if (desc && desc->chip && desc->chip->startup) {
 			spin_lock_irqsave(&desc->lock, flags);
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index d212006a5b3c..484d21e55c61 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -152,12 +152,12 @@ static unsigned int pmac_startup_irq(unsigned int virq)
         unsigned long bit = 1UL << (src & 0x1f);
         int i = src >> 5;
 
-  	spin_lock_irqsave(&pmac_pic_lock, flags);
-	if ((irq_desc[virq].status & IRQ_LEVEL) == 0)
+	spin_lock_irqsave(&pmac_pic_lock, flags);
+	if ((irq_to_desc(virq)->status & IRQ_LEVEL) == 0)
 		out_le32(&pmac_irq_hw[i]->ack, bit);
         __set_bit(src, ppc_cached_irq_mask);
         __pmac_set_irq_mask(src, 0);
-  	spin_unlock_irqrestore(&pmac_pic_lock, flags);
+	spin_unlock_irqrestore(&pmac_pic_lock, flags);
 
 	return 0;
 }
@@ -285,7 +285,7 @@ static int pmac_pic_host_match(struct irq_host *h, struct device_node *node)
 static int pmac_pic_host_map(struct irq_host *h, unsigned int virq,
 			     irq_hw_number_t hw)
 {
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 	int level;
 
 	if (hw >= max_irqs)
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 419f8a637ffe..75935ae1a941 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -156,7 +156,7 @@ static int get_irq_server(unsigned int virq, unsigned int strict_check)
 	cpumask_t cpumask;
 	cpumask_t tmp = CPU_MASK_NONE;
 
-	cpumask_copy(&cpumask, irq_desc[virq].affinity);
+	cpumask_copy(&cpumask, irq_to_desc(virq)->affinity);
 	if (!distribute_irqs)
 		return default_server;
 
@@ -419,7 +419,7 @@ static int xics_host_map(struct irq_host *h, unsigned int virq,
 	/* Insert the interrupt mapping into the radix tree for fast lookup */
 	irq_radix_revmap_insert(xics_host, virq, hw);
 
-	get_irq_desc(virq)->status |= IRQ_LEVEL;
+	irq_to_desc(virq)->status |= IRQ_LEVEL;
 	set_irq_chip_and_handler(virq, xics_irq_chip, handle_fasteoi_irq);
 	return 0;
 }
@@ -843,7 +843,7 @@ void xics_migrate_irqs_away(void)
 		/* We need to get IPIs still. */
 		if (irq == XICS_IPI || irq == XICS_IRQ_SPURIOUS)
 			continue;
-		desc = get_irq_desc(virq);
+		desc = irq_to_desc(virq);
 
 		/* We only need to migrate enabled IRQS */
 		if (desc == NULL || desc->chip == NULL
@@ -872,7 +872,7 @@ void xics_migrate_irqs_away(void)
 		       virq, cpu);
 
 		/* Reset affinity to all cpus */
-		cpumask_setall(irq_desc[virq].affinity);
+		cpumask_setall(irq_to_desc(virq)->affinity);
 		desc->chip->set_affinity(virq, cpu_all_mask);
 unlock:
 		spin_unlock_irqrestore(&desc->lock, flags);
diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c
index 82424cd7e128..523537300ad5 100644
--- a/arch/powerpc/sysdev/cpm1.c
+++ b/arch/powerpc/sysdev/cpm1.c
@@ -102,7 +102,7 @@ static int cpm_pic_host_map(struct irq_host *h, unsigned int virq,
 {
 	pr_debug("cpm_pic_host_map(%d, 0x%lx)\n", virq, hw);
 
-	get_irq_desc(virq)->status |= IRQ_LEVEL;
+	irq_to_desc(virq)->status |= IRQ_LEVEL;
 	set_irq_chip_and_handler(virq, &cpm_pic, handle_fasteoi_irq);
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index 78f1f7cca0a0..722cf72e190d 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -115,11 +115,13 @@ static void cpm2_ack(unsigned int virq)
 
 static void cpm2_end_irq(unsigned int virq)
 {
+	struct irq_desc *desc;
 	int	bit, word;
 	unsigned int irq_nr = virq_to_hw(virq);
 
-	if (!(irq_desc[irq_nr].status & (IRQ_DISABLED|IRQ_INPROGRESS))
-			&& irq_desc[irq_nr].action) {
+	desc = irq_to_desc(irq_nr);
+	if (!(desc->status & (IRQ_DISABLED|IRQ_INPROGRESS))
+			&& desc->action) {
 
 		bit = irq_to_siubit[irq_nr];
 		word = irq_to_siureg[irq_nr];
@@ -138,7 +140,7 @@ static void cpm2_end_irq(unsigned int virq)
 static int cpm2_set_irq_type(unsigned int virq, unsigned int flow_type)
 {
 	unsigned int src = virq_to_hw(virq);
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 	unsigned int vold, vnew, edibit;
 
 	if (flow_type == IRQ_TYPE_NONE)
@@ -210,7 +212,7 @@ static int cpm2_pic_host_map(struct irq_host *h, unsigned int virq,
 {
 	pr_debug("cpm2_pic_host_map(%d, 0x%lx)\n", virq, hw);
 
-	get_irq_desc(virq)->status |= IRQ_LEVEL;
+	irq_to_desc(virq)->status |= IRQ_LEVEL;
 	set_irq_chip_and_handler(virq, &cpm2_pic, handle_level_irq);
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index da38a1ff97bb..7174374f90ff 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -55,7 +55,7 @@ static int fsl_msi_host_map(struct irq_host *h, unsigned int virq,
 {
 	struct irq_chip *chip = &fsl_msi_chip;
 
-	get_irq_desc(virq)->status |= IRQ_TYPE_EDGE_FALLING;
+	irq_to_desc(virq)->status |= IRQ_TYPE_EDGE_FALLING;
 
 	set_irq_chip_and_handler(virq, chip, handle_edge_irq);
 
diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
index a96584ab33dd..78ed945453db 100644
--- a/arch/powerpc/sysdev/i8259.c
+++ b/arch/powerpc/sysdev/i8259.c
@@ -175,12 +175,12 @@ static int i8259_host_map(struct irq_host *h, unsigned int virq,
 
 	/* We block the internal cascade */
 	if (hw == 2)
-		get_irq_desc(virq)->status |= IRQ_NOREQUEST;
+		irq_to_desc(virq)->status |= IRQ_NOREQUEST;
 
 	/* We use the level handler only for now, we might want to
 	 * be more cautious here but that works for now
 	 */
-	get_irq_desc(virq)->status |= IRQ_LEVEL;
+	irq_to_desc(virq)->status |= IRQ_LEVEL;
 	set_irq_chip_and_handler(virq, &i8259_pic, handle_level_irq);
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index cb7689c4bfbd..f042c1d69002 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -605,7 +605,7 @@ static int ipic_set_irq_type(unsigned int virq, unsigned int flow_type)
 {
 	struct ipic *ipic = ipic_from_irq(virq);
 	unsigned int src = ipic_irq_to_hw(virq);
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 	unsigned int vold, vnew, edibit;
 
 	if (flow_type == IRQ_TYPE_NONE)
diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c
index 5d2d5522ef41..01179587df2a 100644
--- a/arch/powerpc/sysdev/mpc8xx_pic.c
+++ b/arch/powerpc/sysdev/mpc8xx_pic.c
@@ -72,7 +72,7 @@ static void mpc8xx_end_irq(unsigned int virq)
 
 static int mpc8xx_set_irq_type(unsigned int virq, unsigned int flow_type)
 {
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 
 	desc->status &= ~(IRQ_TYPE_SENSE_MASK | IRQ_LEVEL);
 	desc->status |= flow_type & IRQ_TYPE_SENSE_MASK;
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 30c44e6b0413..4fd57ab956bf 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -572,7 +572,7 @@ static int irq_choose_cpu(unsigned int virt_irq)
 	cpumask_t mask;
 	int cpuid;
 
-	cpumask_copy(&mask, irq_desc[virt_irq].affinity);
+	cpumask_copy(&mask, irq_to_desc(virt_irq)->affinity);
 	if (cpus_equal(mask, CPU_MASK_ALL)) {
 		static int irq_rover;
 		static DEFINE_SPINLOCK(irq_rover_lock);
@@ -621,7 +621,7 @@ static struct mpic *mpic_find(unsigned int irq)
 	if (irq < NUM_ISA_INTERRUPTS)
 		return NULL;
 
-	return irq_desc[irq].chip_data;
+	return irq_to_desc(irq)->chip_data;
 }
 
 /* Determine if the linux irq is an IPI */
@@ -648,14 +648,14 @@ static inline u32 mpic_physmask(u32 cpumask)
 /* Get the mpic structure from the IPI number */
 static inline struct mpic * mpic_from_ipi(unsigned int ipi)
 {
-	return irq_desc[ipi].chip_data;
+	return irq_to_desc(ipi)->chip_data;
 }
 #endif
 
 /* Get the mpic structure from the irq number */
 static inline struct mpic * mpic_from_irq(unsigned int irq)
 {
-	return irq_desc[irq].chip_data;
+	return irq_to_desc(irq)->chip_data;
 }
 
 /* Send an EOI */
@@ -735,7 +735,7 @@ static void mpic_unmask_ht_irq(unsigned int irq)
 
 	mpic_unmask_irq(irq);
 
-	if (irq_desc[irq].status & IRQ_LEVEL)
+	if (irq_to_desc(irq)->status & IRQ_LEVEL)
 		mpic_ht_end_irq(mpic, src);
 }
 
@@ -745,7 +745,7 @@ static unsigned int mpic_startup_ht_irq(unsigned int irq)
 	unsigned int src = mpic_irq_to_hw(irq);
 
 	mpic_unmask_irq(irq);
-	mpic_startup_ht_interrupt(mpic, src, irq_desc[irq].status);
+	mpic_startup_ht_interrupt(mpic, src, irq_to_desc(irq)->status);
 
 	return 0;
 }
@@ -755,7 +755,7 @@ static void mpic_shutdown_ht_irq(unsigned int irq)
 	struct mpic *mpic = mpic_from_irq(irq);
 	unsigned int src = mpic_irq_to_hw(irq);
 
-	mpic_shutdown_ht_interrupt(mpic, src, irq_desc[irq].status);
+	mpic_shutdown_ht_interrupt(mpic, src, irq_to_desc(irq)->status);
 	mpic_mask_irq(irq);
 }
 
@@ -772,7 +772,7 @@ static void mpic_end_ht_irq(unsigned int irq)
 	 * latched another edge interrupt coming in anyway
 	 */
 
-	if (irq_desc[irq].status & IRQ_LEVEL)
+	if (irq_to_desc(irq)->status & IRQ_LEVEL)
 		mpic_ht_end_irq(mpic, src);
 	mpic_eoi(mpic);
 }
@@ -856,7 +856,7 @@ int mpic_set_irq_type(unsigned int virq, unsigned int flow_type)
 {
 	struct mpic *mpic = mpic_from_irq(virq);
 	unsigned int src = mpic_irq_to_hw(virq);
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 	unsigned int vecpri, vold, vnew;
 
 	DBG("mpic: set_irq_type(mpic:@%p,virq:%d,src:0x%x,type:0x%x)\n",
diff --git a/arch/powerpc/sysdev/mv64x60_pic.c b/arch/powerpc/sysdev/mv64x60_pic.c
index 2aa4ed066db1..485b92477d7c 100644
--- a/arch/powerpc/sysdev/mv64x60_pic.c
+++ b/arch/powerpc/sysdev/mv64x60_pic.c
@@ -213,7 +213,7 @@ static int mv64x60_host_map(struct irq_host *h, unsigned int virq,
 {
 	int level1;
 
-	get_irq_desc(virq)->status |= IRQ_LEVEL;
+	irq_to_desc(virq)->status |= IRQ_LEVEL;
 
 	level1 = (hwirq & MV64x60_LEVEL1_MASK) >> MV64x60_LEVEL1_OFFSET;
 	BUG_ON(level1 > MV64x60_LEVEL1_GPP);
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index 3faa42e03a85..fc098744ad82 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -189,7 +189,7 @@ static inline void qe_ic_write(volatile __be32  __iomem * base, unsigned int reg
 
 static inline struct qe_ic *qe_ic_from_irq(unsigned int virq)
 {
-	return irq_desc[virq].chip_data;
+	return irq_to_desc(virq)->chip_data;
 }
 
 #define virq_to_hw(virq)	((unsigned int)irq_map[virq].hwirq)
@@ -263,7 +263,7 @@ static int qe_ic_host_map(struct irq_host *h, unsigned int virq,
 	chip = &qe_ic->hc_irq;
 
 	set_irq_chip_data(virq, qe_ic);
-	get_irq_desc(virq)->status |= IRQ_LEVEL;
+	irq_to_desc(virq)->status |= IRQ_LEVEL;
 
 	set_irq_chip_and_handler(virq, chip, handle_level_irq);
 
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index cf244a419e96..02f600991dce 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -398,7 +398,7 @@ static int pci_irq_host_map(struct irq_host *h, unsigned int virq,
 	DBG("%s(%d, 0x%lx)\n", __func__, virq, hw);
 	if ((virq >= 1) && (virq <= 4)){
 		irq = virq + IRQ_PCI_INTAD_BASE - 1;
-		get_irq_desc(irq)->status |= IRQ_LEVEL;
+		irq_to_desc(irq)->status |= IRQ_LEVEL;
 		set_irq_chip(irq, &tsi108_pci_irq);
 	}
 	return 0;
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index 466ce9ace127..cf97935863c8 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -57,7 +57,7 @@ struct uic {
 
 static void uic_unmask_irq(unsigned int virq)
 {
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 	struct uic *uic = get_irq_chip_data(virq);
 	unsigned int src = uic_irq_to_hw(virq);
 	unsigned long flags;
@@ -101,7 +101,7 @@ static void uic_ack_irq(unsigned int virq)
 
 static void uic_mask_ack_irq(unsigned int virq)
 {
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 	struct uic *uic = get_irq_chip_data(virq);
 	unsigned int src = uic_irq_to_hw(virq);
 	unsigned long flags;
@@ -129,7 +129,7 @@ static int uic_set_irq_type(unsigned int virq, unsigned int flow_type)
 {
 	struct uic *uic = get_irq_chip_data(virq);
 	unsigned int src = uic_irq_to_hw(virq);
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 	unsigned long flags;
 	int trigger, polarity;
 	u32 tr, pr, mask;
diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c
index 40edad520770..ab743718876b 100644
--- a/arch/powerpc/sysdev/xilinx_intc.c
+++ b/arch/powerpc/sysdev/xilinx_intc.c
@@ -79,7 +79,7 @@ static void xilinx_intc_mask(unsigned int virq)
 
 static int xilinx_intc_set_type(unsigned int virq, unsigned int flow_type)
 {
-	struct irq_desc *desc = get_irq_desc(virq);
+	struct irq_desc *desc = irq_to_desc(virq);
 
 	desc->status &= ~(IRQ_TYPE_SENSE_MASK | IRQ_LEVEL);
 	desc->status |= flow_type & IRQ_TYPE_SENSE_MASK;

From 8be8cf5b47f72096e42bf88cc3afff7a942a346c Mon Sep 17 00:00:00 2001
From: Brian King <brking@linux.vnet.ibm.com>
Date: Mon, 19 Oct 2009 05:51:34 +0000
Subject: [PATCH 010/151] powerpc: Add kdump support to Collaborative Memory
 Manager

When running Active Memory Sharing, the Collaborative Memory Manager (CMM)
may mark some pages as "loaned" with the hypervisor. Periodically, the
CMM will query the hypervisor for a loan request, which is a single signed
value. When kexec'ing into a kdump kernel, the CMM driver in the kdump
kernel is not aware of the pages the previous kernel had marked as "loaned",
so the hypervisor and the CMM driver are out of sync. Fix the CMM driver
to handle this scenario by ignoring requests to decrease the number of loaned
pages if we don't think we have any pages loaned. Pages that are marked as
"loaned" which are not in the balloon will automatically get switched to "active"
the next time we touch the page. This also fixes the case where totalram_pages
is smaller than min_mem_mb, which can occur during kdump.

Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/Kconfig |  2 +-
 arch/powerpc/platforms/pseries/cmm.c   | 29 +++++++++++++++++---------
 2 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 26a24bd92623..27554c807fd5 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -60,7 +60,7 @@ config PPC_SMLPAR
 
 config CMM
 	tristate "Collaborative memory management"
-	depends on PPC_SMLPAR && !CRASH_DUMP
+	depends on PPC_SMLPAR
 	default y
 	help
 	  Select this option, if you want to enable the kernel interface
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index 6567439fe78d..bcdcf0ccc8d7 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -229,8 +229,9 @@ static void cmm_get_mpp(void)
 {
 	int rc;
 	struct hvcall_mpp_data mpp_data;
-	unsigned long active_pages_target;
-	signed long page_loan_request;
+	signed long active_pages_target, page_loan_request, target;
+	signed long total_pages = totalram_pages + loaned_pages;
+	signed long min_mem_pages = (min_mem_mb * 1024 * 1024) / PAGE_SIZE;
 
 	rc = h_get_mpp(&mpp_data);
 
@@ -238,17 +239,25 @@ static void cmm_get_mpp(void)
 		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;
+	target = page_loan_request + (signed long)loaned_pages;
+
+	if (target < 0 || total_pages < min_mem_pages)
+		target = 0;
+
+	if (target > oom_freed_pages)
+		target -= oom_freed_pages;
 	else
-		loaned_pages_target = 0;
+		target = 0;
 
-	active_pages_target = totalram_pages + loaned_pages - loaned_pages_target;
+	active_pages_target = total_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);
+	if (min_mem_pages > active_pages_target)
+		target = total_pages - min_mem_pages;
+
+	if (target < 0)
+		target = 0;
+
+	loaned_pages_target = target;
 
 	cmm_dbg("delta = %ld, loaned = %lu, target = %lu, oom = %lu, totalram = %lu\n",
 		page_loan_request, loaned_pages, loaned_pages_target,

From f71dc176aa06359681c30ba6877ffccab6fba3a6 Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Mon, 26 Oct 2009 19:24:31 +0000
Subject: [PATCH 011/151] powerpc/mm: Make hpte_need_flush() correctly mask for
 multiple page sizes

Currently, hpte_need_flush() only correctly flushes the given address
for normal pages.  Callers for hugepages are required to mask the
address themselves.

But hpte_need_flush() already looks up the page sizes for its own
reasons, so this is a rather silly imposition on the callers.  This
patch alters it to mask based on the pagesize it has looked up itself,
and removes the awkward masking code in the hugepage caller.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/mm/hugetlbpage.c | 6 +-----
 arch/powerpc/mm/tlb_hash64.c  | 8 +++-----
 2 files changed, 4 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 90df6ffe3a43..3d542a9732ae 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -445,11 +445,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		 * necessary anymore if we make hpte_need_flush() get the
 		 * page size from the slices
 		 */
-		unsigned int psize = get_slice_psize(mm, addr);
-		unsigned int shift = mmu_psize_to_shift(psize);
-		unsigned long sz = ((1UL) << shift);
-		struct hstate *hstate = size_to_hstate(sz);
-		pte_update(mm, addr & hstate->mask, ptep, ~0UL, 1);
+		pte_update(mm, addr, ptep, ~0UL, 1);
 	}
 	*ptep = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
 }
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 2b2f35f6985e..282d9306361f 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -53,11 +53,6 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 
 	i = batch->index;
 
-	/* We mask the address for the base page size. Huge pages will
-	 * have applied their own masking already
-	 */
-	addr &= PAGE_MASK;
-
 	/* Get page size (maybe move back to caller).
 	 *
 	 * NOTE: when using special 64K mappings in 4K environment like
@@ -75,6 +70,9 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 	} else
 		psize = pte_pagesize_index(mm, addr, pte);
 
+	/* Mask the address for the correct page size */
+	addr &= ~((1UL << mmu_psize_defs[psize].shift) - 1);
+
 	/* Build full vaddr */
 	if (!is_kernel_addr(addr)) {
 		ssize = user_segment_size(addr);

From a0668cdc154e54bf0c85182e0535eea237d53146 Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Wed, 28 Oct 2009 16:27:18 +0000
Subject: [PATCH 012/151] powerpc/mm: Cleanup management of kmem_caches for
 pagetables

Currently we have a fair bit of rather fiddly code to manage the
various kmem_caches used to store page tables of various levels.  We
generally have two caches holding some combination of PGD, PUD and PMD
tables, plus several more for the special hugepage pagetables.

This patch cleans this all up by taking a different approach.  Rather
than the caches being designated as for PUDs or for hugeptes for 16M
pages, the caches are simply allocated to be a specific size.  Thus
sharing of caches between different types/levels of pagetables happens
naturally.  The pagetable size, where needed, is passed around encoded
in the same way as {PGD,PUD,PMD}_INDEX_SIZE; that is n where the
pagetable contains 2^n pointers.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pgalloc-32.h    | 10 ++--
 arch/powerpc/include/asm/pgalloc-64.h    | 60 ++++++++++++---------
 arch/powerpc/include/asm/pgalloc.h       | 30 ++---------
 arch/powerpc/include/asm/pgtable-ppc64.h |  1 +
 arch/powerpc/mm/hugetlbpage.c            | 51 ++++++------------
 arch/powerpc/mm/init_64.c                | 68 +++++++++++++++++-------
 arch/powerpc/mm/pgtable.c                | 25 +++++----
 7 files changed, 124 insertions(+), 121 deletions(-)

diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h
index c9500d666a1d..580cf73b96e8 100644
--- a/arch/powerpc/include/asm/pgalloc-32.h
+++ b/arch/powerpc/include/asm/pgalloc-32.h
@@ -3,7 +3,8 @@
 
 #include <linux/threads.h>
 
-#define PTE_NONCACHE_NUM	0  /* dummy for now to share code w/ppc64 */
+/* For 32-bit, all levels of page tables are just drawn from get_free_page() */
+#define MAX_PGTABLE_INDEX_SIZE	0
 
 extern void __bad_pte(pmd_t *pmd);
 
@@ -36,11 +37,10 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
 extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
 
-static inline void pgtable_free(pgtable_free_t pgf)
+static inline void pgtable_free(void *table, unsigned index_size)
 {
-	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
-
-	free_page((unsigned long)p);
+	BUG_ON(index_size); /* 32-bit doesn't use this */
+	free_page((unsigned long)table);
 }
 
 #define check_pgt_cache()	do { } while (0)
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index e6f069c4f713..5c1cd73dafa8 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -11,27 +11,39 @@
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
 
+/*
+ * Functions that deal with pagetables that could be at any level of
+ * the table need to be passed an "index_size" so they know how to
+ * handle allocation.  For PTE pages (which are linked to a struct
+ * page for now, and drawn from the main get_free_pages() pool), the
+ * allocation size will be (2^index_size * sizeof(pointer)) and
+ * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
+ *
+ * The maximum index size needs to be big enough to allow any
+ * pagetable sizes we need, but small enough to fit in the low bits of
+ * any page table pointer.  In other words all pagetables, even tiny
+ * ones, must be aligned to allow at least enough low 0 bits to
+ * contain this value.  This value is also used as a mask, so it must
+ * be one less than a power of two.
+ */
+#define MAX_PGTABLE_INDEX_SIZE	0xf
+
 #ifndef CONFIG_PPC_SUBPAGE_PROT
 static inline void subpage_prot_free(pgd_t *pgd) {}
 #endif
 
 extern struct kmem_cache *pgtable_cache[];
-
-#define PGD_CACHE_NUM		0
-#define PUD_CACHE_NUM		1
-#define PMD_CACHE_NUM		1
-#define HUGEPTE_CACHE_NUM	2
-#define PTE_NONCACHE_NUM	7  /* from GFP rather than kmem_cache */
+#define PGT_CACHE(shift) (pgtable_cache[(shift)-1])
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return kmem_cache_alloc(pgtable_cache[PGD_CACHE_NUM], GFP_KERNEL);
+	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 	subpage_prot_free(pgd);
-	kmem_cache_free(pgtable_cache[PGD_CACHE_NUM], pgd);
+	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
 }
 
 #ifndef CONFIG_PPC_64K_PAGES
@@ -40,13 +52,13 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache[PUD_CACHE_NUM],
+	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
 				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 {
-	kmem_cache_free(pgtable_cache[PUD_CACHE_NUM], pud);
+	kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud);
 }
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
@@ -78,13 +90,13 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache[PMD_CACHE_NUM],
+	return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
 				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	kmem_cache_free(pgtable_cache[PMD_CACHE_NUM], pmd);
+	kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
@@ -107,24 +119,22 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	return page;
 }
 
-static inline void pgtable_free(pgtable_free_t pgf)
+static inline void pgtable_free(void *table, unsigned index_size)
 {
-	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
-	int cachenum = pgf.val & PGF_CACHENUM_MASK;
-
-	if (cachenum == PTE_NONCACHE_NUM)
-		free_page((unsigned long)p);
-	else
-		kmem_cache_free(pgtable_cache[cachenum], p);
+	if (!index_size)
+		free_page((unsigned long)table);
+	else {
+		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(index_size), table);
+	}
 }
 
-#define __pmd_free_tlb(tlb, pmd,addr)		      \
-	pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
-		PMD_CACHE_NUM, PMD_TABLE_SIZE-1))
+#define __pmd_free_tlb(tlb, pmd, addr)		      \
+	pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
 #ifndef CONFIG_PPC_64K_PAGES
 #define __pud_free_tlb(tlb, pud, addr)		      \
-	pgtable_free_tlb(tlb, pgtable_free_cache(pud, \
-		PUD_CACHE_NUM, PUD_TABLE_SIZE-1))
+	pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
+
 #endif /* CONFIG_PPC_64K_PAGES */
 
 #define check_pgt_cache()	do { } while (0)
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index f2e812de7c3c..abe8532bd14e 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -24,25 +24,6 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 	__free_page(ptepage);
 }
 
-typedef struct pgtable_free {
-	unsigned long val;
-} pgtable_free_t;
-
-/* This needs to be big enough to allow for MMU_PAGE_COUNT + 2 to be stored
- * and small enough to fit in the low bits of any naturally aligned page
- * table cache entry. Arbitrarily set to 0x1f, that should give us some
- * room to grow
- */
-#define PGF_CACHENUM_MASK	0x1f
-
-static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
-						unsigned long mask)
-{
-	BUG_ON(cachenum > PGF_CACHENUM_MASK);
-
-	return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
-}
-
 #ifdef CONFIG_PPC64
 #include <asm/pgalloc-64.h>
 #else
@@ -50,12 +31,12 @@ static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
 #endif
 
 #ifdef CONFIG_SMP
-extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
+extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift);
 extern void pte_free_finish(void);
 #else /* CONFIG_SMP */
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf)
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
 {
-	pgtable_free(pgf);
+	pgtable_free(table, shift);
 }
 static inline void pte_free_finish(void) { }
 #endif /* !CONFIG_SMP */
@@ -63,12 +44,9 @@ static inline void pte_free_finish(void) { }
 static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
 				  unsigned long address)
 {
-	pgtable_free_t pgf = pgtable_free_cache(page_address(ptepage),
-						PTE_NONCACHE_NUM,
-						PTE_TABLE_SIZE-1);
 	tlb_flush_pgtable(tlb, address);
 	pgtable_page_dtor(ptepage);
-	pgtable_free_tlb(tlb, pgf);
+	pgtable_free_tlb(tlb, page_address(ptepage), 0);
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 806abe7a3fa5..8697d6555090 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -354,6 +354,7 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 #define pgoff_to_pte(off)	((pte_t) {((off) << PTE_RPN_SHIFT)|_PAGE_FILE})
 #define PTE_FILE_MAX_BITS	(BITS_PER_LONG - PTE_RPN_SHIFT)
 
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
 void pgtable_cache_init(void);
 
 /*
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 3d542a9732ae..7230d7a4fbd9 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -43,26 +43,14 @@ static unsigned nr_gpages;
 unsigned int mmu_huge_psizes[MMU_PAGE_COUNT] = { }; /* initialize all to 0 */
 
 #define hugepte_shift			mmu_huge_psizes
-#define PTRS_PER_HUGEPTE(psize)		(1 << hugepte_shift[psize])
-#define HUGEPTE_TABLE_SIZE(psize)	(sizeof(pte_t) << hugepte_shift[psize])
+#define HUGEPTE_INDEX_SIZE(psize)	(mmu_huge_psizes[(psize)])
+#define PTRS_PER_HUGEPTE(psize)		(1 << mmu_huge_psizes[psize])
 
 #define HUGEPD_SHIFT(psize)		(mmu_psize_to_shift(psize) \
-						+ hugepte_shift[psize])
+					 + HUGEPTE_INDEX_SIZE(psize))
 #define HUGEPD_SIZE(psize)		(1UL << HUGEPD_SHIFT(psize))
 #define HUGEPD_MASK(psize)		(~(HUGEPD_SIZE(psize)-1))
 
-/* Subtract one from array size because we don't need a cache for 4K since
- * is not a huge page size */
-#define HUGE_PGTABLE_INDEX(psize)	(HUGEPTE_CACHE_NUM + psize - 1)
-#define HUGEPTE_CACHE_NAME(psize)	(huge_pgtable_cache_name[psize])
-
-static const char *huge_pgtable_cache_name[MMU_PAGE_COUNT] = {
-	[MMU_PAGE_64K]	= "hugepte_cache_64K",
-	[MMU_PAGE_1M]	= "hugepte_cache_1M",
-	[MMU_PAGE_16M]	= "hugepte_cache_16M",
-	[MMU_PAGE_16G]	= "hugepte_cache_16G",
-};
-
 /* Flag to mark huge PD pointers.  This means pmd_bad() and pud_bad()
  * will choke on pointers to hugepte tables, which is handy for
  * catching screwups early. */
@@ -114,15 +102,15 @@ static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
 static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 			   unsigned long address, unsigned int psize)
 {
-	pte_t *new = kmem_cache_zalloc(pgtable_cache[HUGE_PGTABLE_INDEX(psize)],
-				      GFP_KERNEL|__GFP_REPEAT);
+	pte_t *new = kmem_cache_zalloc(PGT_CACHE(hugepte_shift[psize]),
+				       GFP_KERNEL|__GFP_REPEAT);
 
 	if (! new)
 		return -ENOMEM;
 
 	spin_lock(&mm->page_table_lock);
 	if (!hugepd_none(*hpdp))
-		kmem_cache_free(pgtable_cache[HUGE_PGTABLE_INDEX(psize)], new);
+		kmem_cache_free(PGT_CACHE(hugepte_shift[psize]), new);
 	else
 		hpdp->pd = (unsigned long)new | HUGEPD_OK;
 	spin_unlock(&mm->page_table_lock);
@@ -271,9 +259,7 @@ static void free_hugepte_range(struct mmu_gather *tlb, hugepd_t *hpdp,
 
 	hpdp->pd = 0;
 	tlb->need_flush = 1;
-	pgtable_free_tlb(tlb, pgtable_free_cache(hugepte,
-						 HUGEPTE_CACHE_NUM+psize-1,
-						 PGF_CACHENUM_MASK));
+	pgtable_free_tlb(tlb, hugepte, hugepte_shift[psize]);
 }
 
 static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
@@ -698,8 +684,6 @@ static void __init set_huge_psize(int psize)
 		if (mmu_huge_psizes[psize] ||
 		   mmu_psize_defs[psize].shift == PAGE_SHIFT)
 			return;
-		if (WARN_ON(HUGEPTE_CACHE_NAME(psize) == NULL))
-			return;
 		hugetlb_add_hstate(mmu_psize_defs[psize].shift - PAGE_SHIFT);
 
 		switch (mmu_psize_defs[psize].shift) {
@@ -753,9 +737,9 @@ static int __init hugetlbpage_init(void)
 	if (!cpu_has_feature(CPU_FTR_16M_PAGE))
 		return -ENODEV;
 
-	/* Add supported huge page sizes.  Need to change HUGE_MAX_HSTATE
-	 * and adjust PTE_NONCACHE_NUM if the number of supported huge page
-	 * sizes changes.
+	/* Add supported huge page sizes.  Need to change
+	 *  HUGE_MAX_HSTATE if the number of supported huge page sizes
+	 *  changes.
 	 */
 	set_huge_psize(MMU_PAGE_16M);
 	set_huge_psize(MMU_PAGE_16G);
@@ -769,16 +753,11 @@ static int __init hugetlbpage_init(void)
 
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
 		if (mmu_huge_psizes[psize]) {
-			pgtable_cache[HUGE_PGTABLE_INDEX(psize)] =
-				kmem_cache_create(
-					HUGEPTE_CACHE_NAME(psize),
-					HUGEPTE_TABLE_SIZE(psize),
-					HUGEPTE_TABLE_SIZE(psize),
-					0,
-					NULL);
-			if (!pgtable_cache[HUGE_PGTABLE_INDEX(psize)])
-				panic("hugetlbpage_init(): could not create %s"\
-				      "\n", HUGEPTE_CACHE_NAME(psize));
+			pgtable_cache_add(hugepte_shift[psize], NULL);
+			if (!PGT_CACHE(hugepte_shift[psize]))
+				panic("hugetlbpage_init(): could not create "
+				      "pgtable cache for %d bit pagesize\n",
+				      mmu_psize_to_shift(psize));
 		}
 	}
 
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 335c578b9cc3..82ac61dcd3af 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -119,30 +119,58 @@ static void pmd_ctor(void *addr)
 	memset(addr, 0, PMD_TABLE_SIZE);
 }
 
-static const unsigned int pgtable_cache_size[2] = {
-	PGD_TABLE_SIZE, PMD_TABLE_SIZE
-};
-static const char *pgtable_cache_name[ARRAY_SIZE(pgtable_cache_size)] = {
-#ifdef CONFIG_PPC_64K_PAGES
-	"pgd_cache", "pmd_cache",
-#else
-	"pgd_cache", "pud_pmd_cache",
-#endif /* CONFIG_PPC_64K_PAGES */
-};
+struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
+
+/*
+ * Create a kmem_cache() for pagetables.  This is not used for PTE
+ * pages - they're linked to struct page, come from the normal free
+ * pages pool and have a different entry size (see real_pte_t) to
+ * everything else.  Caches created by this function are used for all
+ * the higher level pagetables, and for hugepage pagetables.
+ */
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
+{
+	char *name;
+	unsigned long table_size = sizeof(void *) << shift;
+	unsigned long align = table_size;
+
+	/* When batching pgtable pointers for RCU freeing, we store
+	 * the index size in the low bits.  Table alignment must be
+	 * big enough to fit it */
+	unsigned long minalign = MAX_PGTABLE_INDEX_SIZE + 1;
+	struct kmem_cache *new;
+
+	/* It would be nice if this was a BUILD_BUG_ON(), but at the
+	 * moment, gcc doesn't seem to recognize is_power_of_2 as a
+	 * constant expression, so so much for that. */
+	BUG_ON(!is_power_of_2(minalign));
+	BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE));
+
+	if (PGT_CACHE(shift))
+		return; /* Already have a cache of this size */
+
+	align = max_t(unsigned long, align, minalign);
+	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
+	new = kmem_cache_create(name, table_size, align, 0, ctor);
+	PGT_CACHE(shift) = new;
+
+	pr_debug("Allocated pgtable cache for order %d\n", shift);
+}
 
-#ifdef CONFIG_HUGETLB_PAGE
-/* Hugepages need an extra cache per hugepagesize, initialized in
- * hugetlbpage.c.  We can't put into the tables above, because HPAGE_SHIFT
- * is not compile time constant. */
-struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)+MMU_PAGE_COUNT];
-#else
-struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)];
-#endif
 
 void pgtable_cache_init(void)
 {
-	pgtable_cache[0] = kmem_cache_create(pgtable_cache_name[0], PGD_TABLE_SIZE, PGD_TABLE_SIZE, SLAB_PANIC, pgd_ctor);
-	pgtable_cache[1] = kmem_cache_create(pgtable_cache_name[1], PMD_TABLE_SIZE, PMD_TABLE_SIZE, SLAB_PANIC, pmd_ctor);
+	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
+	pgtable_cache_add(PMD_INDEX_SIZE, pmd_ctor);
+	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_INDEX_SIZE))
+		panic("Couldn't allocate pgtable caches");
+
+	/* In all current configs, when the PUD index exists it's the
+	 * same size as either the pgd or pmd index.  Verify that the
+	 * initialization above has also created a PUD cache.  This
+	 * will need re-examiniation if we add new possibilities for
+	 * the pagetable layout. */
+	BUG_ON(PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE));
 }
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 53040931de32..99df697c601a 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -49,12 +49,12 @@ struct pte_freelist_batch
 {
 	struct rcu_head	rcu;
 	unsigned int	index;
-	pgtable_free_t	tables[0];
+	unsigned long	tables[0];
 };
 
 #define PTE_FREELIST_SIZE \
 	((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
-	  / sizeof(pgtable_free_t))
+	  / sizeof(unsigned long))
 
 static void pte_free_smp_sync(void *arg)
 {
@@ -64,13 +64,13 @@ static void pte_free_smp_sync(void *arg)
 /* This is only called when we are critically out of memory
  * (and fail to get a page in pte_free_tlb).
  */
-static void pgtable_free_now(pgtable_free_t pgf)
+static void pgtable_free_now(void *table, unsigned shift)
 {
 	pte_freelist_forced_free++;
 
 	smp_call_function(pte_free_smp_sync, NULL, 1);
 
-	pgtable_free(pgf);
+	pgtable_free(table, shift);
 }
 
 static void pte_free_rcu_callback(struct rcu_head *head)
@@ -79,8 +79,12 @@ static void pte_free_rcu_callback(struct rcu_head *head)
 		container_of(head, struct pte_freelist_batch, rcu);
 	unsigned int i;
 
-	for (i = 0; i < batch->index; i++)
-		pgtable_free(batch->tables[i]);
+	for (i = 0; i < batch->index; i++) {
+		void *table = (void *)(batch->tables[i] & ~MAX_PGTABLE_INDEX_SIZE);
+		unsigned shift = batch->tables[i] & MAX_PGTABLE_INDEX_SIZE;
+
+		pgtable_free(table, shift);
+	}
 
 	free_page((unsigned long)batch);
 }
@@ -91,25 +95,28 @@ static void pte_free_submit(struct pte_freelist_batch *batch)
 	call_rcu(&batch->rcu, pte_free_rcu_callback);
 }
 
-void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf)
+void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
 {
 	/* This is safe since tlb_gather_mmu has disabled preemption */
 	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
+	unsigned long pgf;
 
 	if (atomic_read(&tlb->mm->mm_users) < 2 ||
 	    cpumask_equal(mm_cpumask(tlb->mm), cpumask_of(smp_processor_id()))){
-		pgtable_free(pgf);
+		pgtable_free(table, shift);
 		return;
 	}
 
 	if (*batchp == NULL) {
 		*batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
 		if (*batchp == NULL) {
-			pgtable_free_now(pgf);
+			pgtable_free_now(table, shift);
 			return;
 		}
 		(*batchp)->index = 0;
 	}
+	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+	pgf = (unsigned long)table | shift;
 	(*batchp)->tables[(*batchp)->index++] = pgf;
 	if ((*batchp)->index == PTE_FREELIST_SIZE) {
 		pte_free_submit(*batchp);

From a4fe3ce7699bfe1bd88f816b55d42d8fe1dac655 Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Mon, 26 Oct 2009 19:24:31 +0000
Subject: [PATCH 013/151] powerpc/mm: Allow more flexible layouts for hugepage
 pagetables

Currently each available hugepage size uses a slightly different
pagetable layout: that is, the bottem level table of pointers to
hugepages is a different size, and may branch off from the normal page
tables at a different level.  Every hugepage aware path that needs to
walk the pagetables must therefore look up the hugepage size from the
slice info first, and work out the correct way to walk the pagetables
accordingly.  Future hardware is likely to add more possible hugepage
sizes, more layout options and more mess.

This patch, therefore reworks the handling of hugepage pagetables to
reduce this complexity.  In the new scheme, instead of having to
consult the slice mask, pagetable walking code can check a flag in the
PGD/PUD/PMD entries to see where to branch off to hugepage pagetables,
and the entry also contains the information (eseentially hugepage
shift) necessary to then interpret that table without recourse to the
slice mask.  This scheme can be extended neatly to handle multiple
levels of self-describing "special" hugepage pagetables, although for
now we assume only one level exists.

This approach means that only the pagetable allocation path needs to
know how the pagetables should be set out.  All other (hugepage)
pagetable walking paths can just interpret the structure as they go.

There already was a flag bit in PGD/PUD/PMD entries for hugepage
directory pointers, but it was only used for debug.  We alter that
flag bit to instead be a 0 in the MSB to indicate a hugepage pagetable
pointer (normally it would be 1 since the pointer lies in the linear
mapping).  This means that asm pagetable walking can test for (and
punt on) hugepage pointers with the same test that checks for
unpopulated page directory entries (beq becomes bge), since hugepage
pointers will always be positive, and normal pointers always negative.

While we're at it, we get rid of the confusing (and grep defeating)
#defining of hugepte_shift to be the same thing as mmu_huge_psizes.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/hugetlb.h       |   1 -
 arch/powerpc/include/asm/mmu-hash64.h    |  14 +-
 arch/powerpc/include/asm/page.h          |  14 +
 arch/powerpc/include/asm/pgtable-ppc64.h |  13 +-
 arch/powerpc/include/asm/pgtable.h       |   3 +
 arch/powerpc/kernel/perf_callchain.c     |  20 +-
 arch/powerpc/mm/gup.c                    | 145 ++-----
 arch/powerpc/mm/hash_utils_64.c          |  26 +-
 arch/powerpc/mm/hugetlbpage.c            | 475 +++++++++++------------
 arch/powerpc/mm/init_64.c                |  10 +-
 10 files changed, 312 insertions(+), 409 deletions(-)

diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index b1dafb6a9743..a4f08f10fe1f 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -3,7 +3,6 @@
 
 #include <asm/page.h>
 
-
 int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 			   unsigned long len);
 
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index bebe31c2e907..dd50ea15e648 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -173,14 +173,6 @@ extern unsigned long tce_alloc_start, tce_alloc_end;
  */
 extern int mmu_ci_restrictions;
 
-#ifdef CONFIG_HUGETLB_PAGE
-/*
- * The page size indexes of the huge pages for use by hugetlbfs
- */
-extern unsigned int mmu_huge_psizes[MMU_PAGE_COUNT];
-
-#endif /* CONFIG_HUGETLB_PAGE */
-
 /*
  * This function sets the AVPN and L fields of the HPTE  appropriately
  * for the page size
@@ -254,9 +246,9 @@ extern int __hash_page_64K(unsigned long ea, unsigned long access,
 			   unsigned int local, int ssize);
 struct mm_struct;
 extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap);
-extern int hash_huge_page(struct mm_struct *mm, unsigned long access,
-			  unsigned long ea, unsigned long vsid, int local,
-			  unsigned long trap);
+int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
+		     pte_t *ptep, unsigned long trap, int local, int ssize,
+		     unsigned int shift, unsigned int mmu_psize);
 
 extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 			     unsigned long pstart, unsigned long prot,
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index ff24254990e1..e96d52a516ba 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -229,6 +229,20 @@ typedef unsigned long pgprot_t;
 
 #endif
 
+typedef struct { signed long pd; } hugepd_t;
+#define HUGEPD_SHIFT_MASK     0x3f
+
+#ifdef CONFIG_HUGETLB_PAGE
+static inline int hugepd_ok(hugepd_t hpd)
+{
+	return (hpd.pd > 0);
+}
+
+#define is_hugepd(pdep)               (hugepd_ok(*((hugepd_t *)(pdep))))
+#else /* CONFIG_HUGETLB_PAGE */
+#define is_hugepd(pdep)			0
+#endif /* CONFIG_HUGETLB_PAGE */
+
 struct page;
 extern void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
 extern void copy_user_page(void *to, void *from, unsigned long vaddr,
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 8697d6555090..49865045d56f 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -379,7 +379,18 @@ void pgtable_cache_init(void);
 	return pt;
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long address);
+#ifdef CONFIG_HUGETLB_PAGE
+pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
+				 unsigned *shift);
+#else
+static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
+					       unsigned *shift)
+{
+	if (shift)
+		*shift = 0;
+	return find_linux_pte(pgdir, ea);
+}
+#endif /* !CONFIG_HUGETLB_PAGE */
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 2a5da069714e..21207e54825b 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -211,6 +211,9 @@ extern void paging_init(void);
  */
 extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t);
 
+extern int gup_hugepd(hugepd_t *hugepd, unsigned pdshift, unsigned long addr,
+		      unsigned long end, int write, struct page **pages, int *nr);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/perf_callchain.c b/arch/powerpc/kernel/perf_callchain.c
index 0a03cf70d247..936f04dbfc6f 100644
--- a/arch/powerpc/kernel/perf_callchain.c
+++ b/arch/powerpc/kernel/perf_callchain.c
@@ -119,13 +119,6 @@ static void perf_callchain_kernel(struct pt_regs *regs,
 }
 
 #ifdef CONFIG_PPC64
-
-#ifdef CONFIG_HUGETLB_PAGE
-#define is_huge_psize(pagesize)	(HPAGE_SHIFT && mmu_huge_psizes[pagesize])
-#else
-#define is_huge_psize(pagesize)	0
-#endif
-
 /*
  * On 64-bit we don't want to invoke hash_page on user addresses from
  * interrupt context, so if the access faults, we read the page tables
@@ -135,7 +128,7 @@ static int read_user_stack_slow(void __user *ptr, void *ret, int nb)
 {
 	pgd_t *pgdir;
 	pte_t *ptep, pte;
-	int pagesize;
+	unsigned shift;
 	unsigned long addr = (unsigned long) ptr;
 	unsigned long offset;
 	unsigned long pfn;
@@ -145,17 +138,14 @@ static int read_user_stack_slow(void __user *ptr, void *ret, int nb)
 	if (!pgdir)
 		return -EFAULT;
 
-	pagesize = get_slice_psize(current->mm, addr);
+	ptep = find_linux_pte_or_hugepte(pgdir, addr, &shift);
+	if (!shift)
+		shift = PAGE_SHIFT;
 
 	/* align address to page boundary */
-	offset = addr & ((1ul << mmu_psize_defs[pagesize].shift) - 1);
+	offset = addr & ((1UL << shift) - 1);
 	addr -= offset;
 
-	if (is_huge_psize(pagesize))
-		ptep = huge_pte_offset(current->mm, addr);
-	else
-		ptep = find_linux_pte(pgdir, addr);
-
 	if (ptep == NULL)
 		return -EFAULT;
 	pte = *ptep;
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
index bc122a120bf0..d7efdbf640c7 100644
--- a/arch/powerpc/mm/gup.c
+++ b/arch/powerpc/mm/gup.c
@@ -55,57 +55,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 	return 1;
 }
 
-#ifdef CONFIG_HUGETLB_PAGE
-static noinline int gup_huge_pte(pte_t *ptep, struct hstate *hstate,
-				 unsigned long *addr, unsigned long end,
-				 int write, struct page **pages, int *nr)
-{
-	unsigned long mask;
-	unsigned long pte_end;
-	struct page *head, *page;
-	pte_t pte;
-	int refs;
-
-	pte_end = (*addr + huge_page_size(hstate)) & huge_page_mask(hstate);
-	if (pte_end < end)
-		end = pte_end;
-
-	pte = *ptep;
-	mask = _PAGE_PRESENT|_PAGE_USER;
-	if (write)
-		mask |= _PAGE_RW;
-	if ((pte_val(pte) & mask) != mask)
-		return 0;
-	/* hugepages are never "special" */
-	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
-	refs = 0;
-	head = pte_page(pte);
-	page = head + ((*addr & ~huge_page_mask(hstate)) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (*addr += PAGE_SIZE, *addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		/* Could be optimized better */
-		while (*nr) {
-			put_page(page);
-			(*nr)--;
-		}
-	}
-
-	return 1;
-}
-#endif /* CONFIG_HUGETLB_PAGE */
-
 static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		int write, struct page **pages, int *nr)
 {
@@ -119,7 +68,11 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		next = pmd_addr_end(addr, end);
 		if (pmd_none(pmd))
 			return 0;
-		if (!gup_pte_range(pmd, addr, next, write, pages, nr))
+		if (is_hugepd(pmdp)) {
+			if (!gup_hugepd((hugepd_t *)pmdp, PMD_SHIFT,
+					addr, next, write, pages, nr))
+				return 0;
+		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
 			return 0;
 	} while (pmdp++, addr = next, addr != end);
 
@@ -139,7 +92,11 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 		next = pud_addr_end(addr, end);
 		if (pud_none(pud))
 			return 0;
-		if (!gup_pmd_range(pud, addr, next, write, pages, nr))
+		if (is_hugepd(pudp)) {
+			if (!gup_hugepd((hugepd_t *)pudp, PUD_SHIFT,
+					addr, next, write, pages, nr))
+				return 0;
+		} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
 			return 0;
 	} while (pudp++, addr = next, addr != end);
 
@@ -154,10 +111,6 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	unsigned long next;
 	pgd_t *pgdp;
 	int nr = 0;
-#ifdef CONFIG_PPC64
-	unsigned int shift;
-	int psize;
-#endif
 
 	pr_devel("%s(%lx,%x,%s)\n", __func__, start, nr_pages, write ? "write" : "read");
 
@@ -172,25 +125,6 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 
 	pr_devel("  aligned: %lx .. %lx\n", start, end);
 
-#ifdef CONFIG_HUGETLB_PAGE
-	/* We bail out on slice boundary crossing when hugetlb is
-	 * enabled in order to not have to deal with two different
-	 * page table formats
-	 */
-	if (addr < SLICE_LOW_TOP) {
-		if (end > SLICE_LOW_TOP)
-			goto slow_irqon;
-
-		if (unlikely(GET_LOW_SLICE_INDEX(addr) !=
-			     GET_LOW_SLICE_INDEX(end - 1)))
-			goto slow_irqon;
-	} else {
-		if (unlikely(GET_HIGH_SLICE_INDEX(addr) !=
-			     GET_HIGH_SLICE_INDEX(end - 1)))
-			goto slow_irqon;
-	}
-#endif /* CONFIG_HUGETLB_PAGE */
-
 	/*
 	 * XXX: batch / limit 'nr', to avoid large irq off latency
 	 * needs some instrumenting to determine the common sizes used by
@@ -210,54 +144,23 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	 */
 	local_irq_disable();
 
-#ifdef CONFIG_PPC64
-	/* Those bits are related to hugetlbfs implementation and only exist
-	 * on 64-bit for now
-	 */
-	psize = get_slice_psize(mm, addr);
-	shift = mmu_psize_defs[psize].shift;
-#endif /* CONFIG_PPC64 */
+	pgdp = pgd_offset(mm, addr);
+	do {
+		pgd_t pgd = *pgdp;
 
-#ifdef CONFIG_HUGETLB_PAGE
-	if (unlikely(mmu_huge_psizes[psize])) {
-		pte_t *ptep;
-		unsigned long a = addr;
-		unsigned long sz = ((1UL) << shift);
-		struct hstate *hstate = size_to_hstate(sz);
-
-		BUG_ON(!hstate);
-		/*
-		 * XXX: could be optimized to avoid hstate
-		 * lookup entirely (just use shift)
-		 */
-
-		do {
-			VM_BUG_ON(shift != mmu_psize_defs[get_slice_psize(mm, a)].shift);
-			ptep = huge_pte_offset(mm, a);
-			pr_devel(" %016lx: huge ptep %p\n", a, ptep);
-			if (!ptep || !gup_huge_pte(ptep, hstate, &a, end, write, pages,
-						   &nr))
+		pr_devel("  %016lx: normal pgd %p\n", addr,
+			 (void *)pgd_val(pgd));
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(pgd))
+			goto slow;
+		if (is_hugepd(pgdp)) {
+			if (!gup_hugepd((hugepd_t *)pgdp, PGDIR_SHIFT,
+					addr, next, write, pages, &nr))
 				goto slow;
-		} while (a != end);
-	} else
-#endif /* CONFIG_HUGETLB_PAGE */
-	{
-		pgdp = pgd_offset(mm, addr);
-		do {
-			pgd_t pgd = *pgdp;
+		} else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+			goto slow;
+	} while (pgdp++, addr = next, addr != end);
 
-#ifdef CONFIG_PPC64
-			VM_BUG_ON(shift != mmu_psize_defs[get_slice_psize(mm, addr)].shift);
-#endif
-			pr_devel("  %016lx: normal pgd %p\n", addr,
-				 (void *)pgd_val(pgd));
-			next = pgd_addr_end(addr, end);
-			if (pgd_none(pgd))
-				goto slow;
-			if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
-				goto slow;
-		} while (pgdp++, addr = next, addr != end);
-	}
 	local_irq_enable();
 
 	VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 1ade7eb6ae00..485dcd197a61 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -891,6 +891,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 	unsigned long vsid;
 	struct mm_struct *mm;
 	pte_t *ptep;
+	unsigned hugeshift;
 	const struct cpumask *tmp;
 	int rc, user_region = 0, local = 0;
 	int psize, ssize;
@@ -943,30 +944,31 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap)
 	if (user_region && cpumask_equal(mm_cpumask(mm), tmp))
 		local = 1;
 
-#ifdef CONFIG_HUGETLB_PAGE
-	/* Handle hugepage regions */
-	if (HPAGE_SHIFT && mmu_huge_psizes[psize]) {
-		DBG_LOW(" -> huge page !\n");
-		return hash_huge_page(mm, access, ea, vsid, local, trap);
-	}
-#endif /* CONFIG_HUGETLB_PAGE */
-
 #ifndef CONFIG_PPC_64K_PAGES
-	/* If we use 4K pages and our psize is not 4K, then we are hitting
-	 * a special driver mapping, we need to align the address before
-	 * we fetch the PTE
+	/* If we use 4K pages and our psize is not 4K, then we might
+	 * be hitting a special driver mapping, and need to align the
+	 * address before we fetch the PTE.
+	 *
+	 * It could also be a hugepage mapping, in which case this is
+	 * not necessary, but it's not harmful, either.
 	 */
 	if (psize != MMU_PAGE_4K)
 		ea &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
 #endif /* CONFIG_PPC_64K_PAGES */
 
 	/* Get PTE and page size from page tables */
-	ptep = find_linux_pte(pgdir, ea);
+	ptep = find_linux_pte_or_hugepte(pgdir, ea, &hugeshift);
 	if (ptep == NULL || !pte_present(*ptep)) {
 		DBG_LOW(" no PTE !\n");
 		return 1;
 	}
 
+#ifdef CONFIG_HUGETLB_PAGE
+	if (hugeshift)
+		return __hash_page_huge(ea, access, vsid, ptep, trap, local,
+					ssize, hugeshift, psize);
+#endif /* CONFIG_HUGETLB_PAGE */
+
 #ifndef CONFIG_PPC_64K_PAGES
 	DBG_LOW(" i-pte: %016lx\n", pte_val(*ptep));
 #else
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 7230d7a4fbd9..95220a5dee58 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -40,25 +40,11 @@ static unsigned nr_gpages;
 /* Array of valid huge page sizes - non-zero value(hugepte_shift) is
  * stored for the huge page sizes that are valid.
  */
-unsigned int mmu_huge_psizes[MMU_PAGE_COUNT] = { }; /* initialize all to 0 */
-
-#define hugepte_shift			mmu_huge_psizes
-#define HUGEPTE_INDEX_SIZE(psize)	(mmu_huge_psizes[(psize)])
-#define PTRS_PER_HUGEPTE(psize)		(1 << mmu_huge_psizes[psize])
-
-#define HUGEPD_SHIFT(psize)		(mmu_psize_to_shift(psize) \
-					 + HUGEPTE_INDEX_SIZE(psize))
-#define HUGEPD_SIZE(psize)		(1UL << HUGEPD_SHIFT(psize))
-#define HUGEPD_MASK(psize)		(~(HUGEPD_SIZE(psize)-1))
+static unsigned int mmu_huge_psizes[MMU_PAGE_COUNT] = { }; /* initialize all to 0 */
 
 /* Flag to mark huge PD pointers.  This means pmd_bad() and pud_bad()
  * will choke on pointers to hugepte tables, which is handy for
  * catching screwups early. */
-#define HUGEPD_OK	0x1
-
-typedef struct { unsigned long pd; } hugepd_t;
-
-#define hugepd_none(hpd)	((hpd).pd == 0)
 
 static inline int shift_to_mmu_psize(unsigned int shift)
 {
@@ -82,71 +68,126 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
 	BUG();
 }
 
+#define hugepd_none(hpd)	((hpd).pd == 0)
+
 static inline pte_t *hugepd_page(hugepd_t hpd)
 {
-	BUG_ON(!(hpd.pd & HUGEPD_OK));
-	return (pte_t *)(hpd.pd & ~HUGEPD_OK);
+	BUG_ON(!hugepd_ok(hpd));
+	return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | 0xc000000000000000);
 }
 
-static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
-				    struct hstate *hstate)
+static inline unsigned int hugepd_shift(hugepd_t hpd)
 {
-	unsigned int shift = huge_page_shift(hstate);
-	int psize = shift_to_mmu_psize(shift);
-	unsigned long idx = ((addr >> shift) & (PTRS_PER_HUGEPTE(psize)-1));
+	return hpd.pd & HUGEPD_SHIFT_MASK;
+}
+
+static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, unsigned pdshift)
+{
+	unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
 	pte_t *dir = hugepd_page(*hpdp);
 
 	return dir + idx;
 }
 
-static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
-			   unsigned long address, unsigned int psize)
+pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
 {
-	pte_t *new = kmem_cache_zalloc(PGT_CACHE(hugepte_shift[psize]),
+	pgd_t *pg;
+	pud_t *pu;
+	pmd_t *pm;
+	hugepd_t *hpdp = NULL;
+	unsigned pdshift = PGDIR_SHIFT;
+
+	if (shift)
+		*shift = 0;
+
+	pg = pgdir + pgd_index(ea);
+	if (is_hugepd(pg)) {
+		hpdp = (hugepd_t *)pg;
+	} else if (!pgd_none(*pg)) {
+		pdshift = PUD_SHIFT;
+		pu = pud_offset(pg, ea);
+		if (is_hugepd(pu))
+			hpdp = (hugepd_t *)pu;
+		else if (!pud_none(*pu)) {
+			pdshift = PMD_SHIFT;
+			pm = pmd_offset(pu, ea);
+			if (is_hugepd(pm))
+				hpdp = (hugepd_t *)pm;
+			else if (!pmd_none(*pm)) {
+				return pte_offset_map(pm, ea);
+			}
+		}
+	}
+
+	if (!hpdp)
+		return NULL;
+
+	if (shift)
+		*shift = hugepd_shift(*hpdp);
+	return hugepte_offset(hpdp, ea, pdshift);
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+	return find_linux_pte_or_hugepte(mm->pgd, addr, NULL);
+}
+
+static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
+			   unsigned long address, unsigned pdshift, unsigned pshift)
+{
+	pte_t *new = kmem_cache_zalloc(PGT_CACHE(pdshift - pshift),
 				       GFP_KERNEL|__GFP_REPEAT);
 
+	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
+	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
+
 	if (! new)
 		return -ENOMEM;
 
 	spin_lock(&mm->page_table_lock);
 	if (!hugepd_none(*hpdp))
-		kmem_cache_free(PGT_CACHE(hugepte_shift[psize]), new);
+		kmem_cache_free(PGT_CACHE(pdshift - pshift), new);
 	else
-		hpdp->pd = (unsigned long)new | HUGEPD_OK;
+		hpdp->pd = ((unsigned long)new & ~0x8000000000000000) | pshift;
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
 
+pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
+{
+	pgd_t *pg;
+	pud_t *pu;
+	pmd_t *pm;
+	hugepd_t *hpdp = NULL;
+	unsigned pshift = __ffs(sz);
+	unsigned pdshift = PGDIR_SHIFT;
 
-static pud_t *hpud_offset(pgd_t *pgd, unsigned long addr, struct hstate *hstate)
-{
-	if (huge_page_shift(hstate) < PUD_SHIFT)
-		return pud_offset(pgd, addr);
-	else
-		return (pud_t *) pgd;
-}
-static pud_t *hpud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long addr,
-			 struct hstate *hstate)
-{
-	if (huge_page_shift(hstate) < PUD_SHIFT)
-		return pud_alloc(mm, pgd, addr);
-	else
-		return (pud_t *) pgd;
-}
-static pmd_t *hpmd_offset(pud_t *pud, unsigned long addr, struct hstate *hstate)
-{
-	if (huge_page_shift(hstate) < PMD_SHIFT)
-		return pmd_offset(pud, addr);
-	else
-		return (pmd_t *) pud;
-}
-static pmd_t *hpmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long addr,
-			 struct hstate *hstate)
-{
-	if (huge_page_shift(hstate) < PMD_SHIFT)
-		return pmd_alloc(mm, pud, addr);
-	else
-		return (pmd_t *) pud;
+	addr &= ~(sz-1);
+
+	pg = pgd_offset(mm, addr);
+	if (pshift >= PUD_SHIFT) {
+		hpdp = (hugepd_t *)pg;
+	} else {
+		pdshift = PUD_SHIFT;
+		pu = pud_alloc(mm, pg, addr);
+		if (pshift >= PMD_SHIFT) {
+			hpdp = (hugepd_t *)pu;
+		} else {
+			pdshift = PMD_SHIFT;
+			pm = pmd_alloc(mm, pu, addr);
+			hpdp = (hugepd_t *)pm;
+		}
+	}
+
+	if (!hpdp)
+		return NULL;
+
+	BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
+
+	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift))
+		return NULL;
+
+	return hugepte_offset(hpdp, addr, pdshift);
 }
 
 /* Build list of addresses of gigantic pages.  This function is used in early
@@ -180,92 +221,38 @@ int alloc_bootmem_huge_page(struct hstate *hstate)
 	return 1;
 }
 
-
-/* Modelled after find_linux_pte() */
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
-{
-	pgd_t *pg;
-	pud_t *pu;
-	pmd_t *pm;
-
-	unsigned int psize;
-	unsigned int shift;
-	unsigned long sz;
-	struct hstate *hstate;
-	psize = get_slice_psize(mm, addr);
-	shift = mmu_psize_to_shift(psize);
-	sz = ((1UL) << shift);
-	hstate = size_to_hstate(sz);
-
-	addr &= hstate->mask;
-
-	pg = pgd_offset(mm, addr);
-	if (!pgd_none(*pg)) {
-		pu = hpud_offset(pg, addr, hstate);
-		if (!pud_none(*pu)) {
-			pm = hpmd_offset(pu, addr, hstate);
-			if (!pmd_none(*pm))
-				return hugepte_offset((hugepd_t *)pm, addr,
-						      hstate);
-		}
-	}
-
-	return NULL;
-}
-
-pte_t *huge_pte_alloc(struct mm_struct *mm,
-			unsigned long addr, unsigned long sz)
-{
-	pgd_t *pg;
-	pud_t *pu;
-	pmd_t *pm;
-	hugepd_t *hpdp = NULL;
-	struct hstate *hstate;
-	unsigned int psize;
-	hstate = size_to_hstate(sz);
-
-	psize = get_slice_psize(mm, addr);
-	BUG_ON(!mmu_huge_psizes[psize]);
-
-	addr &= hstate->mask;
-
-	pg = pgd_offset(mm, addr);
-	pu = hpud_alloc(mm, pg, addr, hstate);
-
-	if (pu) {
-		pm = hpmd_alloc(mm, pu, addr, hstate);
-		if (pm)
-			hpdp = (hugepd_t *)pm;
-	}
-
-	if (! hpdp)
-		return NULL;
-
-	if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, psize))
-		return NULL;
-
-	return hugepte_offset(hpdp, addr, hstate);
-}
-
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
 {
 	return 0;
 }
 
-static void free_hugepte_range(struct mmu_gather *tlb, hugepd_t *hpdp,
-			       unsigned int psize)
+static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift,
+			      unsigned long start, unsigned long end,
+			      unsigned long floor, unsigned long ceiling)
 {
 	pte_t *hugepte = hugepd_page(*hpdp);
+	unsigned shift = hugepd_shift(*hpdp);
+	unsigned long pdmask = ~((1UL << pdshift) - 1);
+
+	start &= pdmask;
+	if (start < floor)
+		return;
+	if (ceiling) {
+		ceiling &= pdmask;
+		if (! ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		return;
 
 	hpdp->pd = 0;
 	tlb->need_flush = 1;
-	pgtable_free_tlb(tlb, hugepte, hugepte_shift[psize]);
+	pgtable_free_tlb(tlb, hugepte, pdshift - shift);
 }
 
 static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 				   unsigned long addr, unsigned long end,
-				   unsigned long floor, unsigned long ceiling,
-				   unsigned int psize)
+				   unsigned long floor, unsigned long ceiling)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -277,7 +264,8 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 		next = pmd_addr_end(addr, end);
 		if (pmd_none(*pmd))
 			continue;
-		free_hugepte_range(tlb, (hugepd_t *)pmd, psize);
+		free_hugepd_range(tlb, (hugepd_t *)pmd, PMD_SHIFT,
+				  addr, next, floor, ceiling);
 	} while (pmd++, addr = next, addr != end);
 
 	start &= PUD_MASK;
@@ -303,23 +291,19 @@ static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	pud_t *pud;
 	unsigned long next;
 	unsigned long start;
-	unsigned int shift;
-	unsigned int psize = get_slice_psize(tlb->mm, addr);
-	shift = mmu_psize_to_shift(psize);
 
 	start = addr;
 	pud = pud_offset(pgd, addr);
 	do {
 		next = pud_addr_end(addr, end);
-		if (shift < PMD_SHIFT) {
+		if (!is_hugepd(pud)) {
 			if (pud_none_or_clear_bad(pud))
 				continue;
 			hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
-					       ceiling, psize);
+					       ceiling);
 		} else {
-			if (pud_none(*pud))
-				continue;
-			free_hugepte_range(tlb, (hugepd_t *)pud, psize);
+			free_hugepd_range(tlb, (hugepd_t *)pud, PUD_SHIFT,
+					  addr, next, floor, ceiling);
 		}
 	} while (pud++, addr = next, addr != end);
 
@@ -350,74 +334,34 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 {
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long start;
 
 	/*
-	 * Comments below take from the normal free_pgd_range().  They
-	 * apply here too.  The tests against HUGEPD_MASK below are
-	 * essential, because we *don't* test for this at the bottom
-	 * level.  Without them we'll attempt to free a hugepte table
-	 * when we unmap just part of it, even if there are other
-	 * active mappings using it.
+	 * Because there are a number of different possible pagetable
+	 * layouts for hugepage ranges, we limit knowledge of how
+	 * things should be laid out to the allocation path
+	 * (huge_pte_alloc(), above).  Everything else works out the
+	 * structure as it goes from information in the hugepd
+	 * pointers.  That means that we can't here use the
+	 * optimization used in the normal page free_pgd_range(), of
+	 * checking whether we're actually covering a large enough
+	 * range to have to do anything at the top level of the walk
+	 * instead of at the bottom.
 	 *
-	 * The next few lines have given us lots of grief...
-	 *
-	 * Why are we testing HUGEPD* at this top level?  Because
-	 * often there will be no work to do at all, and we'd prefer
-	 * not to go all the way down to the bottom just to discover
-	 * that.
-	 *
-	 * Why all these "- 1"s?  Because 0 represents both the bottom
-	 * of the address space and the top of it (using -1 for the
-	 * top wouldn't help much: the masks would do the wrong thing).
-	 * The rule is that addr 0 and floor 0 refer to the bottom of
-	 * the address space, but end 0 and ceiling 0 refer to the top
-	 * Comparisons need to use "end - 1" and "ceiling - 1" (though
-	 * that end 0 case should be mythical).
-	 *
-	 * Wherever addr is brought up or ceiling brought down, we
-	 * must be careful to reject "the opposite 0" before it
-	 * confuses the subsequent tests.  But what about where end is
-	 * brought down by HUGEPD_SIZE below? no, end can't go down to
-	 * 0 there.
-	 *
-	 * Whereas we round start (addr) and ceiling down, by different
-	 * masks at different levels, in order to test whether a table
-	 * now has no other vmas using it, so can be freed, we don't
-	 * bother to round floor or end up - the tests don't need that.
+	 * To make sense of this, you should probably go read the big
+	 * block comment at the top of the normal free_pgd_range(),
+	 * too.
 	 */
-	unsigned int psize = get_slice_psize(tlb->mm, addr);
 
-	addr &= HUGEPD_MASK(psize);
-	if (addr < floor) {
-		addr += HUGEPD_SIZE(psize);
-		if (!addr)
-			return;
-	}
-	if (ceiling) {
-		ceiling &= HUGEPD_MASK(psize);
-		if (!ceiling)
-			return;
-	}
-	if (end - 1 > ceiling - 1)
-		end -= HUGEPD_SIZE(psize);
-	if (addr > end - 1)
-		return;
-
-	start = addr;
 	pgd = pgd_offset(tlb->mm, addr);
 	do {
-		psize = get_slice_psize(tlb->mm, addr);
-		BUG_ON(!mmu_huge_psizes[psize]);
 		next = pgd_addr_end(addr, end);
-		if (mmu_psize_to_shift(psize) < PUD_SHIFT) {
+		if (!is_hugepd(pgd)) {
 			if (pgd_none_or_clear_bad(pgd))
 				continue;
 			hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
 		} else {
-			if (pgd_none(*pgd))
-				continue;
-			free_hugepte_range(tlb, (hugepd_t *)pgd, psize);
+			free_hugepd_range(tlb, (hugepd_t *)pgd, PGDIR_SHIFT,
+					  addr, next, floor, ceiling);
 		}
 	} while (pgd++, addr = next, addr != end);
 }
@@ -448,19 +392,19 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 {
 	pte_t *ptep;
 	struct page *page;
-	unsigned int mmu_psize = get_slice_psize(mm, address);
+	unsigned shift;
+	unsigned long mask;
+
+	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
 
 	/* Verify it is a huge page else bail. */
-	if (!mmu_huge_psizes[mmu_psize])
+	if (!ptep || !shift)
 		return ERR_PTR(-EINVAL);
 
-	ptep = huge_pte_offset(mm, address);
+	mask = (1UL << shift) - 1;
 	page = pte_page(*ptep);
-	if (page) {
-		unsigned int shift = mmu_psize_to_shift(mmu_psize);
-		unsigned long sz = ((1UL) << shift);
-		page += (address % sz) / PAGE_SIZE;
-	}
+	if (page)
+		page += (address & mask) / PAGE_SIZE;
 
 	return page;
 }
@@ -483,6 +427,73 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 	return NULL;
 }
 
+static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+		       unsigned long end, int write, struct page **pages, int *nr)
+{
+	unsigned long mask;
+	unsigned long pte_end;
+	struct page *head, *page;
+	pte_t pte;
+	int refs;
+
+	pte_end = (addr + sz) & ~(sz-1);
+	if (pte_end < end)
+		end = pte_end;
+
+	pte = *ptep;
+	mask = _PAGE_PRESENT | _PAGE_USER;
+	if (write)
+		mask |= _PAGE_RW;
+
+	if ((pte_val(pte) & mask) != mask)
+		return 0;
+
+	/* hugepages are never "special" */
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+
+	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+
+	if (!page_cache_add_speculative(head, refs)) {
+		*nr -= refs;
+		return 0;
+	}
+
+	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+		/* Could be optimized better */
+		while (*nr) {
+			put_page(page);
+			(*nr)--;
+		}
+	}
+
+	return 1;
+}
+
+int gup_hugepd(hugepd_t *hugepd, unsigned pdshift,
+	       unsigned long addr, unsigned long end,
+	       int write, struct page **pages, int *nr)
+{
+	pte_t *ptep;
+	unsigned long sz = 1UL << hugepd_shift(*hugepd);
+
+	ptep = hugepte_offset(hugepd, addr, pdshift);
+	do {
+		if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
+			return 0;
+	} while (ptep++, addr += sz, addr != end);
+
+	return 1;
+}
 
 unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 					unsigned long len, unsigned long pgoff,
@@ -530,34 +541,20 @@ static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags,
 	return rflags;
 }
 
-int hash_huge_page(struct mm_struct *mm, unsigned long access,
-		   unsigned long ea, unsigned long vsid, int local,
-		   unsigned long trap)
+int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
+		     pte_t *ptep, unsigned long trap, int local, int ssize,
+		     unsigned int shift, unsigned int mmu_psize)
 {
-	pte_t *ptep;
 	unsigned long old_pte, new_pte;
 	unsigned long va, rflags, pa, sz;
 	long slot;
 	int err = 1;
-	int ssize = user_segment_size(ea);
-	unsigned int mmu_psize;
-	int shift;
-	mmu_psize = get_slice_psize(mm, ea);
 
-	if (!mmu_huge_psizes[mmu_psize])
-		goto out;
-	ptep = huge_pte_offset(mm, ea);
+	BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
 
 	/* Search the Linux page table for a match with va */
 	va = hpt_va(ea, vsid, ssize);
 
-	/*
-	 * If no pte found or not present, send the problem up to
-	 * do_page_fault
-	 */
-	if (unlikely(!ptep || pte_none(*ptep)))
-		goto out;
-
 	/* 
 	 * Check the user's access rights to the page.  If access should be
 	 * prevented then send the problem up to do_page_fault.
@@ -588,7 +585,6 @@ int hash_huge_page(struct mm_struct *mm, unsigned long access,
 	rflags = 0x2 | (!(new_pte & _PAGE_RW));
  	/* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */
 	rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N);
-	shift = mmu_psize_to_shift(mmu_psize);
 	sz = ((1UL) << shift);
 	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
 		/* No CPU has hugepages but lacks no execute, so we
@@ -672,6 +668,8 @@ repeat:
 
 static void __init set_huge_psize(int psize)
 {
+	unsigned pdshift;
+
 	/* Check that it is a page size supported by the hardware and
 	 * that it fits within pagetable limits. */
 	if (mmu_psize_defs[psize].shift &&
@@ -686,29 +684,14 @@ static void __init set_huge_psize(int psize)
 			return;
 		hugetlb_add_hstate(mmu_psize_defs[psize].shift - PAGE_SHIFT);
 
-		switch (mmu_psize_defs[psize].shift) {
-		case PAGE_SHIFT_64K:
-		    /* We only allow 64k hpages with 4k base page,
-		     * which was checked above, and always put them
-		     * at the PMD */
-		    hugepte_shift[psize] = PMD_SHIFT;
-		    break;
-		case PAGE_SHIFT_16M:
-		    /* 16M pages can be at two different levels
-		     * of pagestables based on base page size */
-		    if (PAGE_SHIFT == PAGE_SHIFT_64K)
-			    hugepte_shift[psize] = PMD_SHIFT;
-		    else /* 4k base page */
-			    hugepte_shift[psize] = PUD_SHIFT;
-		    break;
-		case PAGE_SHIFT_16G:
-		    /* 16G pages are always at PGD level */
-		    hugepte_shift[psize] = PGDIR_SHIFT;
-		    break;
-		}
-		hugepte_shift[psize] -= mmu_psize_defs[psize].shift;
-	} else
-		hugepte_shift[psize] = 0;
+		if (mmu_psize_defs[psize].shift < PMD_SHIFT)
+			pdshift = PMD_SHIFT;
+		else if (mmu_psize_defs[psize].shift < PUD_SHIFT)
+			pdshift = PUD_SHIFT;
+		else
+			pdshift = PGDIR_SHIFT;
+		mmu_huge_psizes[psize] = pdshift - mmu_psize_defs[psize].shift;
+	}
 }
 
 static int __init hugepage_setup_sz(char *str)
@@ -732,7 +715,7 @@ __setup("hugepagesz=", hugepage_setup_sz);
 
 static int __init hugetlbpage_init(void)
 {
-	unsigned int psize;
+	int psize;
 
 	if (!cpu_has_feature(CPU_FTR_16M_PAGE))
 		return -ENODEV;
@@ -753,8 +736,8 @@ static int __init hugetlbpage_init(void)
 
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
 		if (mmu_huge_psizes[psize]) {
-			pgtable_cache_add(hugepte_shift[psize], NULL);
-			if (!PGT_CACHE(hugepte_shift[psize]))
+			pgtable_cache_add(mmu_huge_psizes[psize], NULL);
+			if (!PGT_CACHE(mmu_huge_psizes[psize]))
 				panic("hugetlbpage_init(): could not create "
 				      "pgtable cache for %d bit pagesize\n",
 				      mmu_psize_to_shift(psize));
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 82ac61dcd3af..776f28d02b6b 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -41,6 +41,7 @@
 #include <linux/module.h>
 #include <linux/poison.h>
 #include <linux/lmb.h>
+#include <linux/hugetlb.h>
 
 #include <asm/pgalloc.h>
 #include <asm/page.h>
@@ -136,8 +137,13 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
 
 	/* When batching pgtable pointers for RCU freeing, we store
 	 * the index size in the low bits.  Table alignment must be
-	 * big enough to fit it */
-	unsigned long minalign = MAX_PGTABLE_INDEX_SIZE + 1;
+	 * big enough to fit it.
+	 *
+	 * Likewise, hugeapge pagetable pointers contain a (different)
+	 * shift value in the low bits.  All tables must be aligned so
+	 * as to leave enough 0 bits in the address to contain it. */
+	unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
+				     HUGEPD_SHIFT_MASK + 1);
 	struct kmem_cache *new;
 
 	/* It would be nice if this was a BUILD_BUG_ON(), but at the

From d1837cba5d5d5458c09f0a2849db2d3c203cb8e9 Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Mon, 26 Oct 2009 19:24:31 +0000
Subject: [PATCH 014/151] powerpc/mm: Cleanup initialization of hugepages on
 powerpc

This patch simplifies the logic used to initialize hugepages on
powerpc.  The somewhat oddly named set_huge_psize() is renamed to
add_huge_page_size() and now does all necessary verification of
whether it's given a valid hugepage sizes (instead of just some) and
instantiates the generic hstate structure (but no more).

hugetlbpage_init() now steps through the available pagesizes, checks
if they're valid for hugepages by calling add_huge_page_size() and
initializes the kmem_caches for the hugepage pagetables.  This means
we can now eliminate the mmu_huge_psizes array, since we no longer
need to pass the sizing information for the pagetable caches from
set_huge_psize() into hugetlbpage_init()

Determination of the default huge page size is also moved from the
hash code into the general hugepage code.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/page_64.h |   2 +-
 arch/powerpc/mm/hash_utils_64.c    |  10 ---
 arch/powerpc/mm/hugetlbpage.c      | 130 ++++++++++++++---------------
 3 files changed, 64 insertions(+), 78 deletions(-)

diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 3f17b83f55a1..bfc4e027e2ad 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -90,7 +90,7 @@ extern unsigned int HPAGE_SHIFT;
 #define HPAGE_SIZE		((1UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
-#define HUGE_MAX_HSTATE		3
+#define HUGE_MAX_HSTATE		(MMU_PAGE_COUNT-1)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 485dcd197a61..ef1f047f5431 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -481,16 +481,6 @@ static void __init htab_init_page_sizes(void)
 #ifdef CONFIG_HUGETLB_PAGE
 	/* Reserve 16G huge page memory sections for huge pages */
 	of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL);
-
-/* Set default large page size. Currently, we pick 16M or 1M depending
-	 * on what is available
-	 */
-	if (mmu_psize_defs[MMU_PAGE_16M].shift)
-		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_16M].shift;
-	/* With 4k/4level pagetables, we can't (for now) cope with a
-	 * huge page size < PMD_SIZE */
-	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
-		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_1M].shift;
 #endif /* CONFIG_HUGETLB_PAGE */
 }
 
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 95220a5dee58..a7161c07886d 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -37,27 +37,17 @@
 static unsigned long gpage_freearray[MAX_NUMBER_GPAGES];
 static unsigned nr_gpages;
 
-/* Array of valid huge page sizes - non-zero value(hugepte_shift) is
- * stored for the huge page sizes that are valid.
- */
-static unsigned int mmu_huge_psizes[MMU_PAGE_COUNT] = { }; /* initialize all to 0 */
-
 /* Flag to mark huge PD pointers.  This means pmd_bad() and pud_bad()
  * will choke on pointers to hugepte tables, which is handy for
  * catching screwups early. */
 
 static inline int shift_to_mmu_psize(unsigned int shift)
 {
-	switch (shift) {
-#ifndef CONFIG_PPC_64K_PAGES
-	case PAGE_SHIFT_64K:
-	    return MMU_PAGE_64K;
-#endif
-	case PAGE_SHIFT_16M:
-	    return MMU_PAGE_16M;
-	case PAGE_SHIFT_16G:
-	    return MMU_PAGE_16G;
-	}
+	int psize;
+
+	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)
+		if (mmu_psize_defs[psize].shift == shift)
+			return psize;
 	return -1;
 }
 
@@ -502,8 +492,6 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	struct hstate *hstate = hstate_file(file);
 	int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
 
-	if (!mmu_huge_psizes[mmu_psize])
-		return -EINVAL;
 	return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0);
 }
 
@@ -666,47 +654,46 @@ repeat:
 	return err;
 }
 
-static void __init set_huge_psize(int psize)
+static int __init add_huge_page_size(unsigned long long size)
 {
-	unsigned pdshift;
+	int shift = __ffs(size);
+	int mmu_psize;
 
 	/* Check that it is a page size supported by the hardware and
-	 * that it fits within pagetable limits. */
-	if (mmu_psize_defs[psize].shift &&
-		mmu_psize_defs[psize].shift < SID_SHIFT_1T &&
-		(mmu_psize_defs[psize].shift > MIN_HUGEPTE_SHIFT ||
-		 mmu_psize_defs[psize].shift == PAGE_SHIFT_64K ||
-		 mmu_psize_defs[psize].shift == PAGE_SHIFT_16G)) {
-		/* Return if huge page size has already been setup or is the
-		 * same as the base page size. */
-		if (mmu_huge_psizes[psize] ||
-		   mmu_psize_defs[psize].shift == PAGE_SHIFT)
-			return;
-		hugetlb_add_hstate(mmu_psize_defs[psize].shift - PAGE_SHIFT);
+	 * that it fits within pagetable and slice limits. */
+	if (!is_power_of_2(size)
+	    || (shift > SLICE_HIGH_SHIFT) || (shift <= PAGE_SHIFT))
+		return -EINVAL;
 
-		if (mmu_psize_defs[psize].shift < PMD_SHIFT)
-			pdshift = PMD_SHIFT;
-		else if (mmu_psize_defs[psize].shift < PUD_SHIFT)
-			pdshift = PUD_SHIFT;
-		else
-			pdshift = PGDIR_SHIFT;
-		mmu_huge_psizes[psize] = pdshift - mmu_psize_defs[psize].shift;
-	}
+	if ((mmu_psize = shift_to_mmu_psize(shift)) < 0)
+		return -EINVAL;
+
+#ifdef CONFIG_SPU_FS_64K_LS
+	/* Disable support for 64K huge pages when 64K SPU local store
+	 * support is enabled as the current implementation conflicts.
+	 */
+	if (shift == PAGE_SHIFT_64K)
+		return -EINVAL;
+#endif /* CONFIG_SPU_FS_64K_LS */
+
+	BUG_ON(mmu_psize_defs[mmu_psize].shift != shift);
+
+	/* Return if huge page size has already been setup */
+	if (size_to_hstate(size))
+		return 0;
+
+	hugetlb_add_hstate(shift - PAGE_SHIFT);
+
+	return 0;
 }
 
 static int __init hugepage_setup_sz(char *str)
 {
 	unsigned long long size;
-	int mmu_psize;
-	int shift;
 
 	size = memparse(str, &str);
 
-	shift = __ffs(size);
-	mmu_psize = shift_to_mmu_psize(shift);
-	if (mmu_psize >= 0 && mmu_psize_defs[mmu_psize].shift)
-		set_huge_psize(mmu_psize);
-	else
+	if (add_huge_page_size(size) != 0)
 		printk(KERN_WARNING "Invalid huge page size specified(%llu)\n", size);
 
 	return 1;
@@ -720,30 +707,39 @@ static int __init hugetlbpage_init(void)
 	if (!cpu_has_feature(CPU_FTR_16M_PAGE))
 		return -ENODEV;
 
-	/* Add supported huge page sizes.  Need to change
-	 *  HUGE_MAX_HSTATE if the number of supported huge page sizes
-	 *  changes.
-	 */
-	set_huge_psize(MMU_PAGE_16M);
-	set_huge_psize(MMU_PAGE_16G);
-
-	/* Temporarily disable support for 64K huge pages when 64K SPU local
-	 * store support is enabled as the current implementation conflicts.
-	 */
-#ifndef CONFIG_SPU_FS_64K_LS
-	set_huge_psize(MMU_PAGE_64K);
-#endif
-
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
-		if (mmu_huge_psizes[psize]) {
-			pgtable_cache_add(mmu_huge_psizes[psize], NULL);
-			if (!PGT_CACHE(mmu_huge_psizes[psize]))
-				panic("hugetlbpage_init(): could not create "
-				      "pgtable cache for %d bit pagesize\n",
-				      mmu_psize_to_shift(psize));
-		}
+		unsigned shift;
+		unsigned pdshift;
+
+		if (!mmu_psize_defs[psize].shift)
+			continue;
+
+		shift = mmu_psize_to_shift(psize);
+
+		if (add_huge_page_size(1ULL << shift) < 0)
+			continue;
+
+		if (shift < PMD_SHIFT)
+			pdshift = PMD_SHIFT;
+		else if (shift < PUD_SHIFT)
+			pdshift = PUD_SHIFT;
+		else
+			pdshift = PGDIR_SHIFT;
+
+		pgtable_cache_add(pdshift - shift, NULL);
+		if (!PGT_CACHE(pdshift - shift))
+			panic("hugetlbpage_init(): could not create "
+			      "pgtable cache for %d bit pagesize\n", shift);
 	}
 
+	/* Set default large page size. Currently, we pick 16M or 1M
+	 * depending on what is available
+	 */
+	if (mmu_psize_defs[MMU_PAGE_16M].shift)
+		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_16M].shift;
+	else if (mmu_psize_defs[MMU_PAGE_1M].shift)
+		HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_1M].shift;
+
 	return 0;
 }
 

From 883a3e523672ebba2ec3969837ba02af4f70fae2 Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Mon, 26 Oct 2009 19:24:31 +0000
Subject: [PATCH 015/151] powerpc/mm: Split hash MMU specific hugepage code
 into a new file

This patch separates the parts of hugetlbpage.c which are inherently
specific to the hash MMU into a new hugelbpage-hash64.c file.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/hugetlb.h   |   3 +
 arch/powerpc/mm/Makefile             |   5 +-
 arch/powerpc/mm/hugetlbpage-hash64.c | 167 ++++++++++++++++++++++++++
 arch/powerpc/mm/hugetlbpage.c        | 168 +--------------------------
 4 files changed, 176 insertions(+), 167 deletions(-)
 create mode 100644 arch/powerpc/mm/hugetlbpage-hash64.c

diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index a4f08f10fe1f..038886834da5 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -3,6 +3,9 @@
 
 #include <asm/page.h>
 
+pte_t *huge_pte_offset_and_shift(struct mm_struct *mm,
+				 unsigned long addr, unsigned *shift);
+
 int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 			   unsigned long len);
 
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 6fb8fc8d2fea..ce68708bbad5 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -28,7 +28,10 @@ obj-$(CONFIG_44x)		+= 44x_mmu.o
 obj-$(CONFIG_FSL_BOOKE)		+= fsl_booke_mmu.o
 obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
 obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
-obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
+ifeq ($(CONFIG_HUGETLB_PAGE),y)
+obj-y				+= hugetlbpage.o
+obj-$(CONFIG_PPC_STD_MMU_64)	+= hugetlbpage-hash64.o
+endif
 obj-$(CONFIG_PPC_SUBPAGE_PROT)	+= subpage-prot.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
new file mode 100644
index 000000000000..1508ffc1e1e1
--- /dev/null
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -0,0 +1,167 @@
+/*
+ * PPC64 Huge TLB Page Support for hash based MMUs (POWER4 and later)
+ *
+ * Copyright (C) 2003 David Gibson, IBM Corporation.
+ *
+ * Based on the IA-32 version:
+ * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/cacheflush.h>
+#include <asm/machdep.h>
+
+/*
+ * Called by asm hashtable.S for doing lazy icache flush
+ */
+static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags,
+					pte_t pte, int trap, unsigned long sz)
+{
+	struct page *page;
+	int i;
+
+	if (!pfn_valid(pte_pfn(pte)))
+		return rflags;
+
+	page = pte_page(pte);
+
+	/* page is dirty */
+	if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
+		if (trap == 0x400) {
+			for (i = 0; i < (sz / PAGE_SIZE); i++)
+				__flush_dcache_icache(page_address(page+i));
+			set_bit(PG_arch_1, &page->flags);
+		} else {
+			rflags |= HPTE_R_N;
+		}
+	}
+	return rflags;
+}
+
+int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
+		     pte_t *ptep, unsigned long trap, int local, int ssize,
+		     unsigned int shift, unsigned int mmu_psize)
+{
+	unsigned long old_pte, new_pte;
+	unsigned long va, rflags, pa, sz;
+	long slot;
+	int err = 1;
+
+	BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
+
+	/* Search the Linux page table for a match with va */
+	va = hpt_va(ea, vsid, ssize);
+
+	/*
+	 * Check the user's access rights to the page.  If access should be
+	 * prevented then send the problem up to do_page_fault.
+	 */
+	if (unlikely(access & ~pte_val(*ptep)))
+		goto out;
+	/*
+	 * At this point, we have a pte (old_pte) which can be used to build
+	 * or update an HPTE. There are 2 cases:
+	 *
+	 * 1. There is a valid (present) pte with no associated HPTE (this is
+	 *	the most common case)
+	 * 2. There is a valid (present) pte with an associated HPTE. The
+	 *	current values of the pp bits in the HPTE prevent access
+	 *	because we are doing software DIRTY bit management and the
+	 *	page is currently not DIRTY.
+	 */
+
+
+	do {
+		old_pte = pte_val(*ptep);
+		if (old_pte & _PAGE_BUSY)
+			goto out;
+		new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED;
+	} while(old_pte != __cmpxchg_u64((unsigned long *)ptep,
+					 old_pte, new_pte));
+
+	rflags = 0x2 | (!(new_pte & _PAGE_RW));
+	/* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */
+	rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N);
+	sz = ((1UL) << shift);
+	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
+		/* No CPU has hugepages but lacks no execute, so we
+		 * don't need to worry about that case */
+		rflags = hash_huge_page_do_lazy_icache(rflags, __pte(old_pte),
+						       trap, sz);
+
+	/* Check if pte already has an hpte (case 2) */
+	if (unlikely(old_pte & _PAGE_HASHPTE)) {
+		/* There MIGHT be an HPTE for this pte */
+		unsigned long hash, slot;
+
+		hash = hpt_hash(va, shift, ssize);
+		if (old_pte & _PAGE_F_SECOND)
+			hash = ~hash;
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += (old_pte & _PAGE_F_GIX) >> 12;
+
+		if (ppc_md.hpte_updatepp(slot, rflags, va, mmu_psize,
+					 ssize, local) == -1)
+			old_pte &= ~_PAGE_HPTEFLAGS;
+	}
+
+	if (likely(!(old_pte & _PAGE_HASHPTE))) {
+		unsigned long hash = hpt_hash(va, shift, ssize);
+		unsigned long hpte_group;
+
+		pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT;
+
+repeat:
+		hpte_group = ((hash & htab_hash_mask) *
+			      HPTES_PER_GROUP) & ~0x7UL;
+
+		/* clear HPTE slot informations in new PTE */
+#ifdef CONFIG_PPC_64K_PAGES
+		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0;
+#else
+		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+#endif
+		/* Add in WIMG bits */
+		rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
+				      _PAGE_COHERENT | _PAGE_GUARDED));
+
+		/* Insert into the hash table, primary slot */
+		slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0,
+					  mmu_psize, ssize);
+
+		/* Primary is full, try the secondary */
+		if (unlikely(slot == -1)) {
+			hpte_group = ((~hash & htab_hash_mask) *
+				      HPTES_PER_GROUP) & ~0x7UL;
+			slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags,
+						  HPTE_V_SECONDARY,
+						  mmu_psize, ssize);
+			if (slot == -1) {
+				if (mftb() & 0x1)
+					hpte_group = ((hash & htab_hash_mask) *
+						      HPTES_PER_GROUP)&~0x7UL;
+
+				ppc_md.hpte_remove(hpte_group);
+				goto repeat;
+                        }
+		}
+
+		if (unlikely(slot == -2))
+			panic("hash_huge_page: pte_insert failed\n");
+
+		new_pte |= (slot << 12) & (_PAGE_F_SECOND | _PAGE_F_GIX);
+	}
+
+	/*
+	 * No need to use ldarx/stdcx here
+	 */
+	*ptep = __pte(new_pte & ~_PAGE_BUSY);
+
+	err = 0;
+
+ out:
+	return err;
+}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index a7161c07886d..1bf065546fa1 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -7,29 +7,17 @@
  * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
  */
 
-#include <linux/init.h>
-#include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/io.h>
 #include <linux/hugetlb.h>
-#include <linux/pagemap.h>
-#include <linux/slab.h>
-#include <linux/err.h>
-#include <linux/sysctl.h>
-#include <asm/mman.h>
+#include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
-#include <asm/tlbflush.h>
-#include <asm/mmu_context.h>
-#include <asm/machdep.h>
-#include <asm/cputable.h>
-#include <asm/spu.h>
 
 #define PAGE_SHIFT_64K	16
 #define PAGE_SHIFT_16M	24
 #define PAGE_SHIFT_16G	34
 
-#define NUM_LOW_AREAS	(0x100000000UL >> SID_SHIFT)
-#define NUM_HIGH_AREAS	(PGTABLE_RANGE >> HTLB_AREA_SHIFT)
 #define MAX_NUMBER_GPAGES	1024
 
 /* Tracks the 16G pages after the device tree is scanned and before the
@@ -502,158 +490,6 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 	return 1UL << mmu_psize_to_shift(psize);
 }
 
-/*
- * Called by asm hashtable.S for doing lazy icache flush
- */
-static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags,
-					pte_t pte, int trap, unsigned long sz)
-{
-	struct page *page;
-	int i;
-
-	if (!pfn_valid(pte_pfn(pte)))
-		return rflags;
-
-	page = pte_page(pte);
-
-	/* page is dirty */
-	if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
-		if (trap == 0x400) {
-			for (i = 0; i < (sz / PAGE_SIZE); i++)
-				__flush_dcache_icache(page_address(page+i));
-			set_bit(PG_arch_1, &page->flags);
-		} else {
-			rflags |= HPTE_R_N;
-		}
-	}
-	return rflags;
-}
-
-int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
-		     pte_t *ptep, unsigned long trap, int local, int ssize,
-		     unsigned int shift, unsigned int mmu_psize)
-{
-	unsigned long old_pte, new_pte;
-	unsigned long va, rflags, pa, sz;
-	long slot;
-	int err = 1;
-
-	BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
-
-	/* Search the Linux page table for a match with va */
-	va = hpt_va(ea, vsid, ssize);
-
-	/* 
-	 * Check the user's access rights to the page.  If access should be
-	 * prevented then send the problem up to do_page_fault.
-	 */
-	if (unlikely(access & ~pte_val(*ptep)))
-		goto out;
-	/*
-	 * At this point, we have a pte (old_pte) which can be used to build
-	 * or update an HPTE. There are 2 cases:
-	 *
-	 * 1. There is a valid (present) pte with no associated HPTE (this is 
-	 *	the most common case)
-	 * 2. There is a valid (present) pte with an associated HPTE. The
-	 *	current values of the pp bits in the HPTE prevent access
-	 *	because we are doing software DIRTY bit management and the
-	 *	page is currently not DIRTY. 
-	 */
-
-
-	do {
-		old_pte = pte_val(*ptep);
-		if (old_pte & _PAGE_BUSY)
-			goto out;
-		new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED;
-	} while(old_pte != __cmpxchg_u64((unsigned long *)ptep,
-					 old_pte, new_pte));
-
-	rflags = 0x2 | (!(new_pte & _PAGE_RW));
- 	/* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */
-	rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N);
-	sz = ((1UL) << shift);
-	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
-		/* No CPU has hugepages but lacks no execute, so we
-		 * don't need to worry about that case */
-		rflags = hash_huge_page_do_lazy_icache(rflags, __pte(old_pte),
-						       trap, sz);
-
-	/* Check if pte already has an hpte (case 2) */
-	if (unlikely(old_pte & _PAGE_HASHPTE)) {
-		/* There MIGHT be an HPTE for this pte */
-		unsigned long hash, slot;
-
-		hash = hpt_hash(va, shift, ssize);
-		if (old_pte & _PAGE_F_SECOND)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += (old_pte & _PAGE_F_GIX) >> 12;
-
-		if (ppc_md.hpte_updatepp(slot, rflags, va, mmu_psize,
-					 ssize, local) == -1)
-			old_pte &= ~_PAGE_HPTEFLAGS;
-	}
-
-	if (likely(!(old_pte & _PAGE_HASHPTE))) {
-		unsigned long hash = hpt_hash(va, shift, ssize);
-		unsigned long hpte_group;
-
-		pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT;
-
-repeat:
-		hpte_group = ((hash & htab_hash_mask) *
-			      HPTES_PER_GROUP) & ~0x7UL;
-
-		/* clear HPTE slot informations in new PTE */
-#ifdef CONFIG_PPC_64K_PAGES
-		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0;
-#else
-		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
-#endif
-		/* Add in WIMG bits */
-		rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
-				      _PAGE_COHERENT | _PAGE_GUARDED));
-
-		/* Insert into the hash table, primary slot */
-		slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0,
-					  mmu_psize, ssize);
-
-		/* Primary is full, try the secondary */
-		if (unlikely(slot == -1)) {
-			hpte_group = ((~hash & htab_hash_mask) *
-				      HPTES_PER_GROUP) & ~0x7UL; 
-			slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags,
-						  HPTE_V_SECONDARY,
-						  mmu_psize, ssize);
-			if (slot == -1) {
-				if (mftb() & 0x1)
-					hpte_group = ((hash & htab_hash_mask) *
-						      HPTES_PER_GROUP)&~0x7UL;
-
-				ppc_md.hpte_remove(hpte_group);
-				goto repeat;
-                        }
-		}
-
-		if (unlikely(slot == -2))
-			panic("hash_huge_page: pte_insert failed\n");
-
-		new_pte |= (slot << 12) & (_PAGE_F_SECOND | _PAGE_F_GIX);
-	}
-
-	/*
-	 * No need to use ldarx/stdcx here
-	 */
-	*ptep = __pte(new_pte & ~_PAGE_BUSY);
-
-	err = 0;
-
- out:
-	return err;
-}
-
 static int __init add_huge_page_size(unsigned long long size)
 {
 	int shift = __ffs(size);

From 0895ecda79428df48501e48dd0a868e0c8e1aae2 Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Mon, 26 Oct 2009 19:24:31 +0000
Subject: [PATCH 016/151] powerpc/mm: Bring hugepage PTE accessor functions
 back into sync with normal accessors

The hugepage arch code provides a number of hook functions/macros
which mirror the functionality of various normal page pte access
functions.  Various changes in the normal page accessors (in
particular BenH's recent changes to the handling of lazy icache
flushing and PAGE_EXEC) have caused the hugepage versions to get out
of sync with the originals.  In some cases, this is a bug, at least on
some MMU types.

One of the reasons that some hooks were not identical to the normal
page versions, is that the fact we're dealing with a hugepage needed
to be passed down do use the correct dcache-icache flush function.
This patch makes the main flush_dcache_icache_page() function hugepage
aware (by checking for the PageCompound flag).  That in turn means we
can make set_huge_pte_at() just a call to set_pte_at() bringing it
back into sync.  As a bonus, this lets us remove the
hash_huge_page_do_lazy_icache() function, replacing it with a call to
the hash_page_do_lazy_icache() function it was based on.

Some other hugepage pte access hooks - huge_ptep_get_and_clear() and
huge_ptep_clear_flush() - are not so easily unified, but this patch at
least brings them back into sync with the current versions of the
corresponding normal page functions.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/hugetlb.h    | 25 +++++++++++++++------
 arch/powerpc/include/asm/mmu-hash64.h |  1 +
 arch/powerpc/mm/hash_utils_64.c       |  2 +-
 arch/powerpc/mm/hugetlbpage-hash64.c  | 30 +-------------------------
 arch/powerpc/mm/hugetlbpage.c         | 31 +++++++++------------------
 arch/powerpc/mm/mem.c                 | 17 +++++++++++----
 6 files changed, 45 insertions(+), 61 deletions(-)

diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 038886834da5..5856a66ab404 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -6,6 +6,8 @@
 pte_t *huge_pte_offset_and_shift(struct mm_struct *mm,
 				 unsigned long addr, unsigned *shift);
 
+void flush_dcache_icache_hugepage(struct page *page);
+
 int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
 			   unsigned long len);
 
@@ -13,12 +15,6 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t pte);
-
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
-
 /*
  * The version of vma_mmu_pagesize() in arch/powerpc/mm/hugetlbpage.c needs
  * to override the version in mm/hugetlb.c
@@ -44,9 +40,26 @@ static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm)
 {
 }
 
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep)
+{
+	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 1);
+	return __pte(old);
+}
+
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
+	pte_t pte;
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	flush_tlb_page(vma, addr);
 }
 
 static inline int huge_pte_none(pte_t pte)
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index dd50ea15e648..7514ec2f8540 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -245,6 +245,7 @@ extern int __hash_page_64K(unsigned long ea, unsigned long access,
 			   unsigned long vsid, pte_t *ptep, unsigned long trap,
 			   unsigned int local, int ssize);
 struct mm_struct;
+unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap);
 extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap);
 int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		     pte_t *ptep, unsigned long trap, int local, int ssize,
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index ef1f047f5431..fa251f8c2f82 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -775,7 +775,7 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
 	/* page is dirty */
 	if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
 		if (trap == 0x400) {
-			__flush_dcache_icache(page_address(page));
+			flush_dcache_icache_page(page);
 			set_bit(PG_arch_1, &page->flags);
 		} else
 			pp |= HPTE_R_N;
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index 1508ffc1e1e1..199539882f92 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -14,33 +14,6 @@
 #include <asm/cacheflush.h>
 #include <asm/machdep.h>
 
-/*
- * Called by asm hashtable.S for doing lazy icache flush
- */
-static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags,
-					pte_t pte, int trap, unsigned long sz)
-{
-	struct page *page;
-	int i;
-
-	if (!pfn_valid(pte_pfn(pte)))
-		return rflags;
-
-	page = pte_page(pte);
-
-	/* page is dirty */
-	if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
-		if (trap == 0x400) {
-			for (i = 0; i < (sz / PAGE_SIZE); i++)
-				__flush_dcache_icache(page_address(page+i));
-			set_bit(PG_arch_1, &page->flags);
-		} else {
-			rflags |= HPTE_R_N;
-		}
-	}
-	return rflags;
-}
-
 int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		     pte_t *ptep, unsigned long trap, int local, int ssize,
 		     unsigned int shift, unsigned int mmu_psize)
@@ -89,8 +62,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
 		/* No CPU has hugepages but lacks no execute, so we
 		 * don't need to worry about that case */
-		rflags = hash_huge_page_do_lazy_icache(rflags, __pte(old_pte),
-						       trap, sz);
+		rflags = hash_page_do_lazy_icache(rflags, __pte(old_pte), trap);
 
 	/* Check if pte already has an hpte (case 2) */
 	if (unlikely(old_pte & _PAGE_HASHPTE)) {
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 1bf065546fa1..53b200abb025 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -344,27 +344,6 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 	} while (pgd++, addr = next, addr != end);
 }
 
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t pte)
-{
-	if (pte_present(*ptep)) {
-		/* We open-code pte_clear because we need to pass the right
-		 * argument to hpte_need_flush (huge / !huge). Might not be
-		 * necessary anymore if we make hpte_need_flush() get the
-		 * page size from the slices
-		 */
-		pte_update(mm, addr, ptep, ~0UL, 1);
-	}
-	*ptep = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
-}
-
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
-{
-	unsigned long old = pte_update(mm, addr, ptep, ~0UL, 1);
-	return __pte(old);
-}
-
 struct page *
 follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
 {
@@ -580,3 +559,13 @@ static int __init hugetlbpage_init(void)
 }
 
 module_init(hugetlbpage_init);
+
+void flush_dcache_icache_hugepage(struct page *page)
+{
+	int i;
+
+	BUG_ON(!PageCompound(page));
+
+	for (i = 0; i < (1UL << compound_order(page)); i++)
+		__flush_dcache_icache(page_address(page+i));
+}
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 59736317bf0e..b9b152558f9c 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -32,6 +32,7 @@
 #include <linux/pagemap.h>
 #include <linux/suspend.h>
 #include <linux/lmb.h>
+#include <linux/hugetlb.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -417,18 +418,26 @@ EXPORT_SYMBOL(flush_dcache_page);
 
 void flush_dcache_icache_page(struct page *page)
 {
+#ifdef CONFIG_HUGETLB_PAGE
+	if (PageCompound(page)) {
+		flush_dcache_icache_hugepage(page);
+		return;
+	}
+#endif
 #ifdef CONFIG_BOOKE
-	void *start = kmap_atomic(page, KM_PPC_SYNC_ICACHE);
-	__flush_dcache_icache(start);
-	kunmap_atomic(start, KM_PPC_SYNC_ICACHE);
+	{
+		void *start = kmap_atomic(page, KM_PPC_SYNC_ICACHE);
+		__flush_dcache_icache(start);
+		kunmap_atomic(start, KM_PPC_SYNC_ICACHE);
+	}
 #elif defined(CONFIG_8xx) || defined(CONFIG_PPC64)
 	/* On 8xx there is no need to kmap since highmem is not supported */
 	__flush_dcache_icache(page_address(page)); 
 #else
 	__flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT);
 #endif
-
 }
+
 void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
 {
 	clear_page(page);

From 0682d6c1044e8a54aafdc6282d44c0c436da208f Mon Sep 17 00:00:00 2001
From: Michael Neuling <mikey@neuling.org>
Date: Wed, 21 Oct 2009 20:15:43 +0000
Subject: [PATCH 017/151] powerpc: Fix potential compile error
 irqs_disabled_flags

irqs_disabled_flags is #defined in linux/irqflags.h when
CONFIG_TRACE_IRQFLAGS_SUPPORT is enabled.  64 and 32 bit always have
CONFIG_TRACE_IRQFLAGS_SUPPORT enabled so just remove
irqs_disabled_flags.

This fixes the case when someone needs to include both linux/irqflags.h
and asm/hw_irq.h.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/hw_irq.h | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index abbc2aaaced5..9f4c9d4f5803 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -64,11 +64,6 @@ extern void iseries_handle_interrupts(void);
 		get_paca()->hard_enabled = 0;	\
 	} while(0)
 
-static inline int irqs_disabled_flags(unsigned long flags)
-{
-	return flags == 0;
-}
-
 #else
 
 #if defined(CONFIG_BOOKE)

From ae7dd0208f62f1d6db4c49b85e54fa7bbed0ea4e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 14 Oct 2009 22:54:36 +0000
Subject: [PATCH 018/151] powerpc/nvram_64: Remove unused code

nvram_find_partition() has no user. The call site was removed in the
arch/powerpc move, but the function stayed. Remove it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/nvram.h |  1 -
 arch/powerpc/kernel/nvram_64.c   | 25 -------------------------
 2 files changed, 26 deletions(-)

diff --git a/arch/powerpc/include/asm/nvram.h b/arch/powerpc/include/asm/nvram.h
index 6c587eddee59..850b72f27445 100644
--- a/arch/powerpc/include/asm/nvram.h
+++ b/arch/powerpc/include/asm/nvram.h
@@ -73,7 +73,6 @@ extern int nvram_write_error_log(char * buff, int length,
 extern int nvram_read_error_log(char * buff, int length,
 					 unsigned int * err_type, unsigned int *err_seq);
 extern int nvram_clear_error_log(void);
-extern struct nvram_partition *nvram_find_partition(int sig, const char *name);
 
 extern int pSeries_nvram_init(void);
 
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 0ed31f220482..c67e0102df96 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -228,31 +228,6 @@ static unsigned char nvram_checksum(struct nvram_header *p)
 	return c_sum;
 }
 
-
-/*
- * Find an nvram partition, sig can be 0 for any
- * partition or name can be NULL for any name, else
- * tries to match both
- */
-struct nvram_partition *nvram_find_partition(int sig, const char *name)
-{
-	struct nvram_partition * part;
-	struct list_head * p;
-
-	list_for_each(p, &nvram_part->partition) {
-		part = list_entry(p, struct nvram_partition, partition);
-
-		if (sig && part->header.signature != sig)
-			continue;
-		if (name && 0 != strncmp(name, part->header.name, 12))
-			continue;
-		return part; 
-	}
-	return NULL;
-}
-EXPORT_SYMBOL(nvram_find_partition);
-
-
 static int nvram_remove_os_partition(void)
 {
 	struct list_head *i;

From fd62c6c448669a946e94fbb0ad179918b2233e3d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 14 Oct 2009 22:54:40 +0000
Subject: [PATCH 019/151] powerpc/nvram_64: Check nvram_error_log_index in
 nvram_clear_error_log()

nvram_clear_error_log() calls ppc_md.nvram_write() even when
nvram_error_log_index is -1 (invalid). The nvram_write() function does
not check for a negative offset.

Check nvram_error_log_index as the other nvram log functions do.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/nvram_64.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index c67e0102df96..89d4af2a13ef 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -681,6 +681,9 @@ int nvram_clear_error_log(void)
 	int clear_word = ERR_FLAG_ALREADY_LOGGED;
 	int rc;
 
+	if (nvram_error_log_index == -1)
+		return -1;
+
 	tmp_index = nvram_error_log_index;
 	
 	rc = ppc_md.nvram_write((char *)&clear_word, sizeof(int), &tmp_index);

From 32c105c3781d32c55429fbac493602028913390a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 14 Oct 2009 22:54:46 +0000
Subject: [PATCH 020/151] powerpc/nvram_64: Mark init code __init

Mark all functions which are only called from nvram_init() __init.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/nvram_64.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 89d4af2a13ef..a8f9251f4cac 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -184,7 +184,7 @@ static struct miscdevice nvram_dev = {
 
 
 #ifdef DEBUG_NVRAM
-static void nvram_print_partitions(char * label)
+static void __init nvram_print_partitions(char * label)
 {
 	struct list_head * p;
 	struct nvram_partition * tmp_part;
@@ -202,7 +202,7 @@ static void nvram_print_partitions(char * label)
 #endif
 
 
-static int nvram_write_header(struct nvram_partition * part)
+static int __init nvram_write_header(struct nvram_partition * part)
 {
 	loff_t tmp_index;
 	int rc;
@@ -214,7 +214,7 @@ static int nvram_write_header(struct nvram_partition * part)
 }
 
 
-static unsigned char nvram_checksum(struct nvram_header *p)
+static unsigned char __init nvram_checksum(struct nvram_header *p)
 {
 	unsigned int c_sum, c_sum2;
 	unsigned short *sp = (unsigned short *)p->name; /* assume 6 shorts */
@@ -228,7 +228,7 @@ static unsigned char nvram_checksum(struct nvram_header *p)
 	return c_sum;
 }
 
-static int nvram_remove_os_partition(void)
+static int __init nvram_remove_os_partition(void)
 {
 	struct list_head *i;
 	struct list_head *j;
@@ -294,7 +294,7 @@ static int nvram_remove_os_partition(void)
  * Will create a partition starting at the first free
  * space found if space has enough room.
  */
-static int nvram_create_os_partition(void)
+static int __init nvram_create_os_partition(void)
 {
 	struct nvram_partition *part;
 	struct nvram_partition *new_part;
@@ -397,7 +397,7 @@ static int nvram_create_os_partition(void)
  * 5.) If the max chunk cannot be allocated then try finding a chunk
  * that will satisfy the minum needed (NVRAM_MIN_REQ).
  */
-static int nvram_setup_partition(void)
+static int __init nvram_setup_partition(void)
 {
 	struct list_head * p;
 	struct nvram_partition * part;
@@ -455,7 +455,7 @@ static int nvram_setup_partition(void)
 }
 
 
-static int nvram_scan_partitions(void)
+static int __init nvram_scan_partitions(void)
 {
 	loff_t cur_index = 0;
 	struct nvram_header phead;

From 76f1d94f3ebdee0d14cab4d87bdeed1cf9badb17 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Tue, 13 Oct 2009 19:44:56 +0000
Subject: [PATCH 021/151] powerpc: Make virq_debug_show() cope with sparse
 irq_descs

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/irq.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 65632215f020..baa49eb93228 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -1065,8 +1065,11 @@ static int virq_debug_show(struct seq_file *m, void *private)
 	seq_printf(m, "%-5s  %-7s  %-15s  %s\n", "virq", "hwirq",
 		      "chip name", "host name");
 
-	for (i = 1; i < NR_IRQS; i++) {
+	for (i = 1; i < nr_irqs; i++) {
 		desc = irq_to_desc(i);
+		if (!desc)
+			continue;
+
 		spin_lock_irqsave(&desc->lock, flags);
 
 		if (desc->action && desc->action->handler) {

From 750ab112919220a1d14491ae210b689bcb7d6d66 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Tue, 13 Oct 2009 19:45:00 +0000
Subject: [PATCH 022/151] powerpc: Rearrange and fix show_interrupts() for
 sparse irq_descs

Move the default case out of the if, ie. when we're just displaying
an irq. And consolidate all the odd cases at the top, ie. printing
the header and footer.

And in the process cope with sparse irq_descs.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/irq.c | 64 ++++++++++++++++++++++-----------------
 1 file changed, 37 insertions(+), 27 deletions(-)

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index baa49eb93228..63e27d5c52de 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -187,33 +187,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "CPU%d       ", j);
 		seq_putc(p, '\n');
-	}
-
-	if (i < NR_IRQS) {
-		desc = irq_to_desc(i);
-		spin_lock_irqsave(&desc->lock, flags);
-		action = desc->action;
-		if (!action || !action->handler)
-			goto skip;
-		seq_printf(p, "%3d: ", i);
-#ifdef CONFIG_SMP
-		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-#else
-		seq_printf(p, "%10u ", kstat_irqs(i));
-#endif /* CONFIG_SMP */
-		if (desc->chip)
-			seq_printf(p, " %s ", desc->chip->typename);
-		else
-			seq_puts(p, "  None      ");
-		seq_printf(p, "%s", (desc->status & IRQ_LEVEL) ? "Level " : "Edge  ");
-		seq_printf(p, "    %s", action->name);
-		for (action = action->next; action; action = action->next)
-			seq_printf(p, ", %s", action->name);
-		seq_putc(p, '\n');
-skip:
-		spin_unlock_irqrestore(&desc->lock, flags);
-	} else if (i == NR_IRQS) {
+	} else if (i == nr_irqs) {
 #if defined(CONFIG_PPC32) && defined(CONFIG_TAU_INT)
 		if (tau_initialized){
 			seq_puts(p, "TAU: ");
@@ -223,7 +197,43 @@ skip:
 		}
 #endif /* CONFIG_PPC32 && CONFIG_TAU_INT*/
 		seq_printf(p, "BAD: %10u\n", ppc_spurious_interrupts);
+
+		return 0;
 	}
+
+	desc = irq_to_desc(i);
+	if (!desc)
+		return 0;
+
+	spin_lock_irqsave(&desc->lock, flags);
+
+	action = desc->action;
+	if (!action || !action->handler)
+		goto skip;
+
+	seq_printf(p, "%3d: ", i);
+#ifdef CONFIG_SMP
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+#else
+	seq_printf(p, "%10u ", kstat_irqs(i));
+#endif /* CONFIG_SMP */
+
+	if (desc->chip)
+		seq_printf(p, " %s ", desc->chip->typename);
+	else
+		seq_puts(p, "  None      ");
+
+	seq_printf(p, "%s", (desc->status & IRQ_LEVEL) ? "Level " : "Edge  ");
+	seq_printf(p, "    %s", action->name);
+
+	for (action = action->next; action; action = action->next)
+		seq_printf(p, ", %s", action->name);
+	seq_putc(p, '\n');
+
+skip:
+	spin_unlock_irqrestore(&desc->lock, flags);
+
 	return 0;
 }
 

From cd015707176820b86d07b5dffdecfefdd539a497 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <michael@ellerman.id.au>
Date: Tue, 13 Oct 2009 19:45:03 +0000
Subject: [PATCH 023/151] powerpc: Enable sparse irq_descs on powerpc

Defining CONFIG_SPARSE_IRQ enables generic code that gets rid of the
static irq_desc array, and replaces it with an array of pointers to
irq_descs.

It also allows node local allocation of irq_descs, however we
currently don't have the information available to do that, so we just
allocate them on all on node 0.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/Kconfig            | 13 +++++++++++
 arch/powerpc/include/asm/irq.h  |  3 +++
 arch/powerpc/kernel/irq.c       | 40 +++++++++++++++++++++++++++------
 arch/powerpc/kernel/ppc_ksyms.c |  1 -
 arch/powerpc/kernel/setup_64.c  |  5 -----
 5 files changed, 49 insertions(+), 13 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 3aa79f8e39e4..61abde11a45e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -377,6 +377,19 @@ config IRQ_ALL_CPUS
 	  CPU.  Generally saying Y is safe, although some problems have been
 	  reported with SMP Power Macintoshes with this option enabled.
 
+config SPARSE_IRQ
+	bool "Support sparse irq numbering"
+	default y
+	help
+	  This enables support for sparse irqs. This is useful for distro
+	  kernels that want to define a high CONFIG_NR_CPUS value but still
+	  want to have low kernel memory footprint on smaller machines.
+
+	  ( Sparse IRQs can also be beneficial on NUMA boxes, as they spread
+	    out the irq_desc[] array in a more NUMA-friendly way. )
+
+	  If you don't know what to do here, say Y.
+
 config NUMA
 	bool "NUMA support"
 	depends on PPC64
diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 03dc28cdb4da..c85a32f1a17f 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -38,6 +38,9 @@ extern atomic_t ppc_n_lost_interrupts;
 /* Number of irqs reserved for the legacy controller */
 #define NUM_ISA_INTERRUPTS	16
 
+/* Same thing, used by the generic IRQ code */
+#define NR_IRQS_LEGACY		NUM_ISA_INTERRUPTS
+
 /* This type is the placeholder for a hardware interrupt number. It has to
  * be big enough to enclose whatever representation is used by a given
  * platform.
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 63e27d5c52de..eba53923630f 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -85,7 +85,10 @@ extern int tau_interrupts(int);
 #endif /* CONFIG_PPC32 */
 
 #ifdef CONFIG_PPC64
+
+#ifndef CONFIG_SPARSE_IRQ
 EXPORT_SYMBOL(irq_desc);
+#endif
 
 int distribute_irqs = 1;
 
@@ -613,8 +616,16 @@ void irq_set_virq_count(unsigned int count)
 static int irq_setup_virq(struct irq_host *host, unsigned int virq,
 			    irq_hw_number_t hwirq)
 {
+	struct irq_desc *desc;
+
+	desc = irq_to_desc_alloc_node(virq, 0);
+	if (!desc) {
+		pr_debug("irq: -> allocating desc failed\n");
+		goto error;
+	}
+
 	/* Clear IRQ_NOREQUEST flag */
-	irq_to_desc(virq)->status &= ~IRQ_NOREQUEST;
+	desc->status &= ~IRQ_NOREQUEST;
 
 	/* map it */
 	smp_wmb();
@@ -623,11 +634,14 @@ static int irq_setup_virq(struct irq_host *host, unsigned int virq,
 
 	if (host->ops->map(host, virq, hwirq)) {
 		pr_debug("irq: -> mapping failed, freeing\n");
-		irq_free_virt(virq, 1);
-		return -1;
+		goto error;
 	}
 
 	return 0;
+
+error:
+	irq_free_virt(virq, 1);
+	return -1;
 }
 
 unsigned int irq_create_direct_mapping(struct irq_host *host)
@@ -1008,12 +1022,24 @@ void irq_free_virt(unsigned int virq, unsigned int count)
 	spin_unlock_irqrestore(&irq_big_lock, flags);
 }
 
-void irq_early_init(void)
+int arch_early_irq_init(void)
 {
-	unsigned int i;
+	struct irq_desc *desc;
+	int i;
 
-	for (i = 0; i < NR_IRQS; i++)
-		irq_to_desc(i)->status |= IRQ_NOREQUEST;
+	for (i = 0; i < NR_IRQS; i++) {
+		desc = irq_to_desc(i);
+		if (desc)
+			desc->status |= IRQ_NOREQUEST;
+	}
+
+	return 0;
+}
+
+int arch_init_chip_data(struct irq_desc *desc, int node)
+{
+	desc->status |= IRQ_NOREQUEST;
+	return 0;
 }
 
 /* We need to create the radix trees late */
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index c8b27bb4dbde..07115d6cd4ba 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -162,7 +162,6 @@ EXPORT_SYMBOL(screen_info);
 
 #ifdef CONFIG_PPC32
 EXPORT_SYMBOL(timer_interrupt);
-EXPORT_SYMBOL(irq_desc);
 EXPORT_SYMBOL(tb_ticks_per_jiffy);
 EXPORT_SYMBOL(cacheable_memcpy);
 EXPORT_SYMBOL(cacheable_memzero);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 04f638d82fb3..fd785f7a279b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -356,11 +356,6 @@ void __init setup_system(void)
 	 */
 	initialize_cache_info();
 
-	/*
-	 * Initialize irq remapping subsystem
-	 */
-	irq_early_init();
-
 #ifdef CONFIG_PPC_RTAS
 	/*
 	 * Initialize RTAS if available

From 99ca177ae4d31c3fbbea7ffb213b9724e4c26233 Mon Sep 17 00:00:00 2001
From: Jean Delvare <khali@linux-fr.org>
Date: Wed, 14 Oct 2009 05:31:32 +0000
Subject: [PATCH 024/151] powerpc/therm_adt746x: Don't access non-existing
 register

The ADT746x don't have any register at sub-address 0, so better use an
existing register for the initial test read.

Signed-off-by: Jean Delvare <khali@linux-fr.org>
Cc: Colin Leroy <colin@colino.net>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 drivers/macintosh/therm_adt746x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/macintosh/therm_adt746x.c b/drivers/macintosh/therm_adt746x.c
index 556f0feaa4df..95b676a19be7 100644
--- a/drivers/macintosh/therm_adt746x.c
+++ b/drivers/macintosh/therm_adt746x.c
@@ -387,7 +387,7 @@ static int probe_thermostat(struct i2c_client *client,
 	i2c_set_clientdata(client, th);
 	th->clt = client;
 
-	rc = read_reg(th, 0);
+	rc = read_reg(th, CONFIG_REG);
 	if (rc < 0) {
 		dev_err(&client->dev, "Thermostat failed to read config!\n");
 		kfree(th);

From cc393317c42ab75cc3ac36548a6b85ce60460c3f Mon Sep 17 00:00:00 2001
From: Olof Johansson <olof@lixom.net>
Date: Tue, 6 Oct 2009 05:52:50 +0000
Subject: [PATCH 025/151] powerpc: pasemi_defconfig update

pasemi_defconfig hasn't been updated for a year.

Mostly a refresh of defaults, but this also disables 64K pages.

Signed-off-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/configs/pasemi_defconfig | 630 +++++++++++++++++++-------
 1 file changed, 462 insertions(+), 168 deletions(-)

diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig
index 4f8681cc8d77..20ba0cfff8ba 100644
--- a/arch/powerpc/configs/pasemi_defconfig
+++ b/arch/powerpc/configs/pasemi_defconfig
@@ -1,49 +1,58 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.26-rc3
-# Tue May 27 16:08:06 2008
+# Linux kernel version: 2.6.32-rc3
+# Tue Oct  6 10:27:18 2009
 #
 CONFIG_PPC64=y
 
 #
 # Processor support
 #
+CONFIG_PPC_BOOK3S_64=y
+# CONFIG_PPC_BOOK3E_64 is not set
+CONFIG_PPC_BOOK3S=y
 CONFIG_POWER4_ONLY=y
 CONFIG_POWER4=y
 # CONFIG_TUNE_CELL is not set
 CONFIG_PPC_FPU=y
 CONFIG_ALTIVEC=y
+# CONFIG_VSX is not set
 CONFIG_PPC_STD_MMU=y
+CONFIG_PPC_STD_MMU_64=y
 CONFIG_PPC_MM_SLICES=y
 # CONFIG_VIRT_CPU_ACCOUNTING is not set
+CONFIG_PPC_HAVE_PMU_SUPPORT=y
+CONFIG_PPC_PERF_CTRS=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=2
 CONFIG_64BIT=y
 CONFIG_WORD_SIZE=64
-CONFIG_PPC_MERGE=y
+CONFIG_ARCH_PHYS_ADDR_T_64BIT=y
 CONFIG_MMU=y
 CONFIG_GENERIC_CMOS_UPDATE=y
 CONFIG_GENERIC_TIME=y
 CONFIG_GENERIC_TIME_VSYSCALL=y
 CONFIG_GENERIC_CLOCKEVENTS=y
 CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
 CONFIG_HAVE_SETUP_PER_CPU_AREA=y
+CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK=y
 CONFIG_IRQ_PER_CPU=y
 CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
 CONFIG_TRACE_IRQFLAGS_SUPPORT=y
 CONFIG_LOCKDEP_SUPPORT=y
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 CONFIG_ARCH_HAS_ILOG2_U32=y
 CONFIG_ARCH_HAS_ILOG2_U64=y
 CONFIG_GENERIC_HWEIGHT=y
-CONFIG_GENERIC_CALIBRATE_DELAY=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_ARCH_NO_VIRT_TO_BUS=y
 CONFIG_PPC=y
 CONFIG_EARLY_PRINTK=y
 CONFIG_COMPAT=y
 CONFIG_SYSVIPC_COMPAT=y
-CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
+CONFIG_SCHED_OMIT_FRAME_POINTER=y
 CONFIG_ARCH_MAY_HAVE_PC_FDC=y
 CONFIG_PPC_OF=y
 CONFIG_OF=y
@@ -51,11 +60,14 @@ CONFIG_PPC_UDBG_16550=y
 # CONFIG_GENERIC_TBSYNC is not set
 CONFIG_AUDIT_ARCH=y
 CONFIG_GENERIC_BUG=y
+CONFIG_DTC=y
 # CONFIG_DEFAULT_UIMAGE is not set
 # CONFIG_PPC_DCR_NATIVE is not set
 # CONFIG_PPC_DCR_MMIO is not set
 # CONFIG_PPC_OF_PLATFORM_PCI is not set
+CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC=y
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+CONFIG_CONSTRUCTORS=y
 
 #
 # General setup
@@ -72,10 +84,20 @@ CONFIG_SYSVIPC_SYSCTL=y
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
 # CONFIG_AUDIT is not set
+
+#
+# RCU Subsystem
+#
+CONFIG_TREE_RCU=y
+# CONFIG_TREE_PREEMPT_RCU is not set
+# CONFIG_RCU_TRACE is not set
+CONFIG_RCU_FANOUT=64
+# CONFIG_RCU_FANOUT_EXACT is not set
+# CONFIG_TREE_RCU_TRACE is not set
 # CONFIG_IKCONFIG is not set
 CONFIG_LOG_BUF_SHIFT=17
-# CONFIG_CGROUPS is not set
 # CONFIG_GROUP_SCHED is not set
+# CONFIG_CGROUPS is not set
 CONFIG_SYSFS_DEPRECATED=y
 CONFIG_SYSFS_DEPRECATED_V2=y
 # CONFIG_RELAY is not set
@@ -84,13 +106,17 @@ CONFIG_NAMESPACES=y
 # CONFIG_IPC_NS is not set
 # CONFIG_USER_NS is not set
 # CONFIG_PID_NS is not set
+# CONFIG_NET_NS is not set
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_INITRAMFS_SOURCE=""
+CONFIG_RD_GZIP=y
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
+CONFIG_ANON_INODES=y
 # CONFIG_EMBEDDED is not set
 CONFIG_SYSCTL_SYSCALL=y
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
@@ -98,32 +124,52 @@ CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
-CONFIG_COMPAT_BRK=y
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
-CONFIG_ANON_INODES=y
 CONFIG_EPOLL=y
 CONFIG_SIGNALFD=y
 CONFIG_TIMERFD=y
 CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
+CONFIG_AIO=y
+CONFIG_HAVE_PERF_EVENTS=y
+
+#
+# Kernel Performance Events And Counters
+#
+CONFIG_PERF_EVENTS=y
+CONFIG_EVENT_PROFILE=y
+# CONFIG_PERF_COUNTERS is not set
 CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_PCI_QUIRKS=y
 CONFIG_SLUB_DEBUG=y
+CONFIG_COMPAT_BRK=y
 # CONFIG_SLAB is not set
 CONFIG_SLUB=y
 # CONFIG_SLOB is not set
 CONFIG_PROFILING=y
-# CONFIG_MARKERS is not set
+CONFIG_TRACEPOINTS=y
 CONFIG_OPROFILE=y
 CONFIG_HAVE_OPROFILE=y
 # CONFIG_KPROBES is not set
+CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y
+CONFIG_HAVE_SYSCALL_WRAPPERS=y
+CONFIG_HAVE_IOREMAP_PROT=y
 CONFIG_HAVE_KPROBES=y
 CONFIG_HAVE_KRETPROBES=y
-# CONFIG_HAVE_DMA_ATTRS is not set
-CONFIG_PROC_PAGE_MONITOR=y
+CONFIG_HAVE_ARCH_TRACEHOOK=y
+CONFIG_HAVE_DMA_ATTRS=y
+CONFIG_USE_GENERIC_SMP_HELPERS=y
+CONFIG_HAVE_DMA_API_DEBUG=y
+
+#
+# GCOV-based kernel profiling
+#
+# CONFIG_GCOV_KERNEL is not set
+# CONFIG_SLOW_WORK is not set
+# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
 CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
-# CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
 CONFIG_MODULES=y
 # CONFIG_MODULE_FORCE_LOAD is not set
@@ -131,11 +177,10 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_FORCE_UNLOAD is not set
 # CONFIG_MODVERSIONS is not set
 # CONFIG_MODULE_SRCVERSION_ALL is not set
-# CONFIG_KMOD is not set
 CONFIG_STOP_MACHINE=y
 CONFIG_BLOCK=y
-# CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
 CONFIG_BLOCK_COMPAT=y
 
 #
@@ -150,19 +195,14 @@ CONFIG_DEFAULT_AS=y
 # CONFIG_DEFAULT_CFQ is not set
 # CONFIG_DEFAULT_NOOP is not set
 CONFIG_DEFAULT_IOSCHED="anticipatory"
-CONFIG_CLASSIC_RCU=y
+# CONFIG_FREEZER is not set
+CONFIG_PPC_MSI_BITMAP=y
 
 #
 # Platform support
 #
-CONFIG_PPC_MULTIPLATFORM=y
-# CONFIG_PPC_82xx is not set
-# CONFIG_PPC_83xx is not set
-# CONFIG_PPC_86xx is not set
 # CONFIG_PPC_PSERIES is not set
 # CONFIG_PPC_ISERIES is not set
-# CONFIG_PPC_MPC512x is not set
-# CONFIG_PPC_MPC5121 is not set
 # CONFIG_PPC_PMAC is not set
 # CONFIG_PPC_MAPLE is not set
 CONFIG_PPC_PASEMI=y
@@ -178,8 +218,10 @@ CONFIG_PPC_PASEMI_MDIO=y
 # CONFIG_PPC_CELL_NATIVE is not set
 # CONFIG_PPC_IBM_CELL_BLADE is not set
 # CONFIG_PPC_CELLEB is not set
+# CONFIG_PPC_CELL_QPACE is not set
 # CONFIG_PQ2ADS is not set
 CONFIG_PPC_NATIVE=y
+CONFIG_PPC_OF_BOOT_TRAMPOLINE=y
 # CONFIG_IPIC is not set
 CONFIG_MPIC=y
 # CONFIG_MPIC_WEIRD is not set
@@ -213,6 +255,7 @@ CONFIG_CPU_FREQ_GOV_ONDEMAND=y
 #
 CONFIG_PPC_PASEMI_CPUFREQ=y
 # CONFIG_FSL_ULI1575 is not set
+# CONFIG_SIMPLE_GPIO is not set
 
 #
 # Kernel options
@@ -226,16 +269,19 @@ CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 # CONFIG_HZ_300 is not set
 CONFIG_HZ_1000=y
 CONFIG_HZ=1000
-# CONFIG_SCHED_HRTICK is not set
+CONFIG_SCHED_HRTICK=y
 CONFIG_PREEMPT_NONE=y
 # CONFIG_PREEMPT_VOLUNTARY is not set
 # CONFIG_PREEMPT is not set
 CONFIG_BINFMT_ELF=y
 CONFIG_COMPAT_BINFMT_ELF=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_HAVE_AOUT is not set
 # CONFIG_BINFMT_MISC is not set
 CONFIG_HUGETLB_PAGE_SIZE_VARIABLE=y
 CONFIG_IOMMU_VMERGE=y
 CONFIG_IOMMU_HELPER=y
+# CONFIG_SWIOTLB is not set
 CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
 CONFIG_ARCH_HAS_WALK_MEMORY=y
 CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y
@@ -243,6 +289,7 @@ CONFIG_ARCH_ENABLE_MEMORY_HOTREMOVE=y
 # CONFIG_CRASH_DUMP is not set
 # CONFIG_IRQ_ALL_CPUS is not set
 # CONFIG_NUMA is not set
+CONFIG_MAX_ACTIVE_REGIONS=256
 CONFIG_ARCH_SELECT_MEMORY_MODEL=y
 CONFIG_ARCH_FLATMEM_ENABLE=y
 CONFIG_ARCH_SPARSEMEM_ENABLE=y
@@ -253,20 +300,28 @@ CONFIG_FLATMEM_MANUAL=y
 # CONFIG_SPARSEMEM_MANUAL is not set
 CONFIG_FLATMEM=y
 CONFIG_FLAT_NODE_MEM_MAP=y
-# CONFIG_SPARSEMEM_STATIC is not set
 CONFIG_SPARSEMEM_VMEMMAP_ENABLE=y
 CONFIG_PAGEFLAGS_EXTENDED=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
-CONFIG_RESOURCES_64BIT=y
+CONFIG_MIGRATION=y
+CONFIG_PHYS_ADDR_T_64BIT=y
 CONFIG_ZONE_DMA_FLAG=1
 CONFIG_BOUNCE=y
+CONFIG_HAVE_MLOCK=y
+CONFIG_HAVE_MLOCKED_PAGE_BIT=y
+# CONFIG_KSM is not set
+CONFIG_DEFAULT_MMAP_MIN_ADDR=4096
 CONFIG_PPC_HAS_HASH_64K=y
+# CONFIG_PPC_4K_PAGES is not set
+# CONFIG_PPC_16K_PAGES is not set
 CONFIG_PPC_64K_PAGES=y
+# CONFIG_PPC_256K_PAGES is not set
 CONFIG_FORCE_MAX_ZONEORDER=9
 # CONFIG_PPC_SUBPAGE_PROT is not set
 # CONFIG_SCHED_SMT is not set
 CONFIG_PROC_DEVICETREE=y
 # CONFIG_CMDLINE_BOOL is not set
+CONFIG_EXTRA_TARGETS=""
 # CONFIG_PM is not set
 # CONFIG_SECCOMP is not set
 CONFIG_ISA_DMA_API=y
@@ -285,6 +340,8 @@ CONFIG_ARCH_SUPPORTS_MSI=y
 CONFIG_PCI_MSI=y
 CONFIG_PCI_LEGACY=y
 # CONFIG_PCI_DEBUG is not set
+# CONFIG_PCI_STUB is not set
+# CONFIG_PCI_IOV is not set
 CONFIG_PCCARD=y
 CONFIG_PCMCIA_DEBUG=y
 CONFIG_PCMCIA=y
@@ -301,13 +358,10 @@ CONFIG_CARDBUS=y
 CONFIG_ELECTRA_CF=y
 # CONFIG_HOTPLUG_PCI is not set
 # CONFIG_HAS_RAPIDIO is not set
+# CONFIG_RELOCATABLE is not set
 CONFIG_PAGE_OFFSET=0xc000000000000000
 CONFIG_KERNEL_START=0xc000000000000000
 CONFIG_PHYSICAL_START=0x00000000
-
-#
-# Networking
-#
 CONFIG_NET=y
 
 #
@@ -356,9 +410,11 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_NETFILTER is not set
 # CONFIG_IP_DCCP is not set
 # CONFIG_IP_SCTP is not set
+# CONFIG_RDS is not set
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
 # CONFIG_BRIDGE is not set
+# CONFIG_NET_DSA is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
 # CONFIG_LLC2 is not set
@@ -368,25 +424,32 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
+# CONFIG_PHONET is not set
+# CONFIG_IEEE802154 is not set
 # CONFIG_NET_SCHED is not set
+# CONFIG_DCB is not set
 
 #
 # Network testing
 #
 # CONFIG_NET_PKTGEN is not set
+# CONFIG_NET_DROP_MONITOR is not set
 # CONFIG_HAMRADIO is not set
 # CONFIG_CAN is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
+CONFIG_WIRELESS=y
+# CONFIG_CFG80211 is not set
+CONFIG_CFG80211_DEFAULT_PS_VALUE=0
+# CONFIG_WIRELESS_OLD_REGULATORY is not set
+# CONFIG_WIRELESS_EXT is not set
+# CONFIG_LIB80211 is not set
 
 #
-# Wireless
+# CFG80211 needs to be enabled for MAC80211
 #
-# CONFIG_CFG80211 is not set
-# CONFIG_WIRELESS_EXT is not set
-# CONFIG_MAC80211 is not set
-# CONFIG_IEEE80211 is not set
+# CONFIG_WIMAX is not set
 # CONFIG_RFKILL is not set
 # CONFIG_NET_9P is not set
 
@@ -398,15 +461,19 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # Generic Driver Options
 #
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+# CONFIG_DEVTMPFS is not set
 CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
 CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
 # CONFIG_DEBUG_DRIVER is not set
 # CONFIG_DEBUG_DEVRES is not set
 # CONFIG_SYS_HYPERVISOR is not set
 # CONFIG_CONNECTOR is not set
 CONFIG_MTD=y
 # CONFIG_MTD_DEBUG is not set
+# CONFIG_MTD_TESTS is not set
 CONFIG_MTD_CONCAT=y
 # CONFIG_MTD_PARTITIONS is not set
 
@@ -477,12 +544,18 @@ CONFIG_MTD_NAND_PASEMI=y
 # CONFIG_MTD_NAND_FSL_ELBC is not set
 # CONFIG_MTD_ONENAND is not set
 
+#
+# LPDDR flash memory drivers
+#
+# CONFIG_MTD_LPDDR is not set
+
 #
 # UBI - Unsorted block images
 #
 # CONFIG_MTD_UBI is not set
 CONFIG_OF_DEVICE=y
 CONFIG_OF_I2C=y
+CONFIG_OF_MDIO=y
 # CONFIG_PARPORT is not set
 CONFIG_BLK_DEV=y
 # CONFIG_BLK_DEV_FD is not set
@@ -501,29 +574,41 @@ CONFIG_BLK_DEV_RAM_SIZE=16384
 # CONFIG_BLK_DEV_XIP is not set
 # CONFIG_CDROM_PKTCDVD is not set
 # CONFIG_ATA_OVER_ETH is not set
+# CONFIG_BLK_DEV_HD is not set
 CONFIG_MISC_DEVICES=y
 # CONFIG_PHANTOM is not set
-# CONFIG_EEPROM_93CX6 is not set
 # CONFIG_SGI_IOC4 is not set
 # CONFIG_TIFM_CORE is not set
+# CONFIG_ICS932S401 is not set
 # CONFIG_ENCLOSURE_SERVICES is not set
+# CONFIG_HP_ILO is not set
+# CONFIG_ISL29003 is not set
+# CONFIG_C2PORT is not set
+
+#
+# EEPROM support
+#
+# CONFIG_EEPROM_AT24 is not set
+CONFIG_EEPROM_LEGACY=y
+# CONFIG_EEPROM_MAX6875 is not set
+# CONFIG_EEPROM_93CX6 is not set
+# CONFIG_CB710_CORE is not set
 CONFIG_HAVE_IDE=y
 CONFIG_IDE=y
-CONFIG_BLK_DEV_IDE=y
 
 #
 # Please see Documentation/ide/ide.txt for help/info on IDE drives
 #
+CONFIG_IDE_ATAPI=y
 # CONFIG_BLK_DEV_IDE_SATA is not set
-CONFIG_BLK_DEV_IDEDISK=y
-CONFIG_IDEDISK_MULTI_MODE=y
+CONFIG_IDE_GD=y
+CONFIG_IDE_GD_ATA=y
+# CONFIG_IDE_GD_ATAPI is not set
 # CONFIG_BLK_DEV_IDECS is not set
 # CONFIG_BLK_DEV_DELKIN is not set
 CONFIG_BLK_DEV_IDECD=y
 CONFIG_BLK_DEV_IDECD_VERBOSE_ERRORS=y
 # CONFIG_BLK_DEV_IDETAPE is not set
-# CONFIG_BLK_DEV_IDEFLOPPY is not set
-CONFIG_BLK_DEV_IDESCSI=y
 CONFIG_IDE_TASK_IOCTL=y
 CONFIG_IDE_PROC_FS=y
 
@@ -542,14 +627,13 @@ CONFIG_IDE_PROC_FS=y
 # CONFIG_BLK_DEV_AMD74XX is not set
 # CONFIG_BLK_DEV_CMD64X is not set
 # CONFIG_BLK_DEV_TRIFLEX is not set
-# CONFIG_BLK_DEV_CY82C693 is not set
 # CONFIG_BLK_DEV_CS5520 is not set
 # CONFIG_BLK_DEV_CS5530 is not set
-# CONFIG_BLK_DEV_HPT34X is not set
 # CONFIG_BLK_DEV_HPT366 is not set
 # CONFIG_BLK_DEV_JMICRON is not set
 # CONFIG_BLK_DEV_SC1200 is not set
 # CONFIG_BLK_DEV_PIIX is not set
+# CONFIG_BLK_DEV_IT8172 is not set
 # CONFIG_BLK_DEV_IT8213 is not set
 # CONFIG_BLK_DEV_IT821X is not set
 # CONFIG_BLK_DEV_NS87415 is not set
@@ -563,8 +647,6 @@ CONFIG_IDE_PROC_FS=y
 # CONFIG_BLK_DEV_VIA82CXXX is not set
 # CONFIG_BLK_DEV_TC86C001 is not set
 # CONFIG_BLK_DEV_IDEDMA is not set
-# CONFIG_BLK_DEV_HD_ONLY is not set
-# CONFIG_BLK_DEV_HD is not set
 
 #
 # SCSI device support
@@ -586,10 +668,6 @@ CONFIG_BLK_DEV_SR=y
 CONFIG_BLK_DEV_SR_VENDOR=y
 CONFIG_CHR_DEV_SG=y
 CONFIG_CHR_DEV_SCH=y
-
-#
-# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
-#
 CONFIG_SCSI_MULTI_LUN=y
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
@@ -606,6 +684,8 @@ CONFIG_SCSI_WAIT_SCAN=m
 # CONFIG_SCSI_SRP_ATTRS is not set
 CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_ISCSI_TCP is not set
+# CONFIG_SCSI_CXGB3_ISCSI is not set
+# CONFIG_SCSI_BNX2_ISCSI is not set
 # CONFIG_BLK_DEV_3W_XXXX_RAID is not set
 # CONFIG_SCSI_3W_9XXX is not set
 # CONFIG_SCSI_ACARD is not set
@@ -614,11 +694,16 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_AIC7XXX_OLD is not set
 # CONFIG_SCSI_AIC79XX is not set
 # CONFIG_SCSI_AIC94XX is not set
+# CONFIG_SCSI_MVSAS is not set
 # CONFIG_SCSI_ARCMSR is not set
 # CONFIG_MEGARAID_NEWGEN is not set
 # CONFIG_MEGARAID_LEGACY is not set
 # CONFIG_MEGARAID_SAS is not set
+# CONFIG_SCSI_MPT2SAS is not set
 # CONFIG_SCSI_HPTIOP is not set
+# CONFIG_LIBFC is not set
+# CONFIG_LIBFCOE is not set
+# CONFIG_FCOE is not set
 # CONFIG_SCSI_DMX3191D is not set
 # CONFIG_SCSI_EATA is not set
 # CONFIG_SCSI_FUTURE_DOMAIN is not set
@@ -626,7 +711,6 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_IPS is not set
 # CONFIG_SCSI_INITIO is not set
 # CONFIG_SCSI_INIA100 is not set
-# CONFIG_SCSI_MVSAS is not set
 # CONFIG_SCSI_STEX is not set
 # CONFIG_SCSI_SYM53C8XX_2 is not set
 # CONFIG_SCSI_IPR is not set
@@ -637,10 +721,14 @@ CONFIG_SCSI_LOWLEVEL=y
 # CONFIG_SCSI_DC395x is not set
 # CONFIG_SCSI_DC390T is not set
 # CONFIG_SCSI_DEBUG is not set
+# CONFIG_SCSI_PMCRAID is not set
 # CONFIG_SCSI_SRP is not set
 # CONFIG_SCSI_LOWLEVEL_PCMCIA is not set
+# CONFIG_SCSI_DH is not set
+# CONFIG_SCSI_OSD_INITIATOR is not set
 CONFIG_ATA=y
 # CONFIG_ATA_NONSTANDARD is not set
+CONFIG_ATA_VERBOSE_ERROR=y
 CONFIG_SATA_PMP=y
 # CONFIG_SATA_AHCI is not set
 CONFIG_SATA_SIL24=y
@@ -662,6 +750,7 @@ CONFIG_SATA_MV=y
 # CONFIG_PATA_ALI is not set
 # CONFIG_PATA_AMD is not set
 # CONFIG_PATA_ARTOP is not set
+# CONFIG_PATA_ATP867X is not set
 # CONFIG_PATA_ATIIXP is not set
 # CONFIG_PATA_CMD640_PCI is not set
 # CONFIG_PATA_CMD64X is not set
@@ -690,6 +779,7 @@ CONFIG_ATA_GENERIC=y
 CONFIG_PATA_PCMCIA=y
 # CONFIG_PATA_PDC_OLD is not set
 # CONFIG_PATA_RADISYS is not set
+# CONFIG_PATA_RDC is not set
 # CONFIG_PATA_RZ1000 is not set
 # CONFIG_PATA_SC1200 is not set
 # CONFIG_PATA_SERVERWORKS is not set
@@ -703,12 +793,15 @@ CONFIG_PATA_OF_PLATFORM=y
 # CONFIG_PATA_SCH is not set
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
+CONFIG_MD_AUTODETECT=y
 CONFIG_MD_LINEAR=y
 CONFIG_MD_RAID0=y
 CONFIG_MD_RAID1=y
 CONFIG_MD_RAID10=y
 CONFIG_MD_RAID456=y
-CONFIG_MD_RAID5_RESHAPE=y
+# CONFIG_MULTICORE_RAID456 is not set
+CONFIG_MD_RAID6_PQ=y
+# CONFIG_ASYNC_RAID6_TEST is not set
 # CONFIG_MD_MULTIPATH is not set
 # CONFIG_MD_FAULTY is not set
 CONFIG_BLK_DEV_DM=y
@@ -725,12 +818,19 @@ CONFIG_DM_CRYPT=y
 #
 # IEEE 1394 (FireWire) support
 #
+
+#
+# You can enable one or both FireWire driver stacks.
+#
+
+#
+# See the help texts for more information.
+#
 # CONFIG_FIREWIRE is not set
 # CONFIG_IEEE1394 is not set
 # CONFIG_I2O is not set
 # CONFIG_MACINTOSH_DRIVERS is not set
 CONFIG_NETDEVICES=y
-# CONFIG_NETDEVICES_MULTIQUEUE is not set
 CONFIG_DUMMY=y
 # CONFIG_BONDING is not set
 # CONFIG_MACVLAN is not set
@@ -753,6 +853,9 @@ CONFIG_MARVELL_PHY=y
 # CONFIG_BROADCOM_PHY is not set
 # CONFIG_ICPLUS_PHY is not set
 # CONFIG_REALTEK_PHY is not set
+# CONFIG_NATIONAL_PHY is not set
+# CONFIG_STE10XP is not set
+# CONFIG_LSI_ET1011C_PHY is not set
 # CONFIG_FIXED_PHY is not set
 # CONFIG_MDIO_BITBANG is not set
 CONFIG_NET_ETHERNET=y
@@ -761,19 +864,23 @@ CONFIG_MII=y
 # CONFIG_SUNGEM is not set
 # CONFIG_CASSINI is not set
 # CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_ETHOC is not set
+# CONFIG_DNET is not set
 # CONFIG_NET_TULIP is not set
 # CONFIG_HP100 is not set
 # CONFIG_IBM_NEW_EMAC_ZMII is not set
 # CONFIG_IBM_NEW_EMAC_RGMII is not set
 # CONFIG_IBM_NEW_EMAC_TAH is not set
 # CONFIG_IBM_NEW_EMAC_EMAC4 is not set
+# CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
+# CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
+# CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
 CONFIG_NET_PCI=y
 # CONFIG_PCNET32 is not set
 # CONFIG_AMD8111_ETH is not set
 # CONFIG_ADAPTEC_STARFIRE is not set
 # CONFIG_B44 is not set
 # CONFIG_FORCEDETH is not set
-# CONFIG_EEPRO100 is not set
 # CONFIG_E100 is not set
 # CONFIG_FEALNX is not set
 # CONFIG_NATSEMI is not set
@@ -783,19 +890,22 @@ CONFIG_NET_PCI=y
 # CONFIG_R6040 is not set
 # CONFIG_SIS900 is not set
 # CONFIG_EPIC100 is not set
+# CONFIG_SMSC9420 is not set
 # CONFIG_SUNDANCE is not set
+# CONFIG_TLAN is not set
+# CONFIG_KS8842 is not set
+# CONFIG_KS8851_MLL is not set
 # CONFIG_VIA_RHINE is not set
 # CONFIG_SC92031 is not set
+# CONFIG_ATL2 is not set
 CONFIG_NETDEV_1000=y
 # CONFIG_ACENIC is not set
 # CONFIG_DL2K is not set
 CONFIG_E1000=y
-CONFIG_E1000_NAPI=y
-# CONFIG_E1000_DISABLE_PACKET_SPLIT is not set
 # CONFIG_E1000E is not set
-# CONFIG_E1000E_ENABLED is not set
 # CONFIG_IP1000 is not set
 # CONFIG_IGB is not set
+# CONFIG_IGBVF is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -806,30 +916,40 @@ CONFIG_E1000_NAPI=y
 # CONFIG_VIA_VELOCITY is not set
 CONFIG_TIGON3=y
 # CONFIG_BNX2 is not set
+# CONFIG_CNIC is not set
 # CONFIG_QLA3XXX is not set
 # CONFIG_ATL1 is not set
+# CONFIG_ATL1E is not set
+# CONFIG_ATL1C is not set
+# CONFIG_JME is not set
 CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T1 is not set
+CONFIG_CHELSIO_T3_DEPENDS=y
 # CONFIG_CHELSIO_T3 is not set
+# CONFIG_ENIC is not set
 # CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
+# CONFIG_VXGE is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
 # CONFIG_NIU is not set
 CONFIG_PASEMI_MAC=y
+# CONFIG_MLX4_EN is not set
 # CONFIG_MLX4_CORE is not set
 # CONFIG_TEHUTI is not set
 # CONFIG_BNX2X is not set
+# CONFIG_QLGE is not set
 # CONFIG_SFC is not set
+# CONFIG_BE2NET is not set
 # CONFIG_TR is not set
-
-#
-# Wireless LAN
-#
+CONFIG_WLAN=y
 # CONFIG_WLAN_PRE80211 is not set
 # CONFIG_WLAN_80211 is not set
-# CONFIG_IWLWIFI_LEDS is not set
+
+#
+# Enable WiMAX (Networking options) to see the WiMAX drivers
+#
 
 #
 # USB Network Adapters
@@ -874,17 +994,23 @@ CONFIG_INPUT_EVDEV=y
 # Input Device Drivers
 #
 CONFIG_INPUT_KEYBOARD=y
+# CONFIG_KEYBOARD_ADP5588 is not set
 # CONFIG_KEYBOARD_ATKBD is not set
-# CONFIG_KEYBOARD_SUNKBD is not set
+# CONFIG_QT2160 is not set
 # CONFIG_KEYBOARD_LKKBD is not set
-# CONFIG_KEYBOARD_XTKBD is not set
+# CONFIG_KEYBOARD_MAX7359 is not set
 # CONFIG_KEYBOARD_NEWTON is not set
+# CONFIG_KEYBOARD_OPENCORES is not set
 # CONFIG_KEYBOARD_STOWAWAY is not set
+# CONFIG_KEYBOARD_SUNKBD is not set
+# CONFIG_KEYBOARD_XTKBD is not set
 CONFIG_INPUT_MOUSE=y
 # CONFIG_MOUSE_PS2 is not set
 # CONFIG_MOUSE_SERIAL is not set
 # CONFIG_MOUSE_APPLETOUCH is not set
+# CONFIG_MOUSE_BCM5974 is not set
 # CONFIG_MOUSE_VSXXXAA is not set
+# CONFIG_MOUSE_SYNAPTICS_I2C is not set
 # CONFIG_INPUT_JOYSTICK is not set
 # CONFIG_INPUT_TABLET is not set
 # CONFIG_INPUT_TOUCHSCREEN is not set
@@ -900,6 +1026,7 @@ CONFIG_INPUT_MOUSE=y
 # Character devices
 #
 CONFIG_VT=y
+CONFIG_CONSOLE_TRANSLATIONS=y
 CONFIG_VT_CONSOLE=y
 CONFIG_HW_CONSOLE=y
 # CONFIG_VT_HW_CONSOLE_BINDING is not set
@@ -926,10 +1053,13 @@ CONFIG_SERIAL_CORE_CONSOLE=y
 # CONFIG_SERIAL_JSM is not set
 # CONFIG_SERIAL_OF_PLATFORM is not set
 CONFIG_UNIX98_PTYS=y
+# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=4
+# CONFIG_HVC_UDBG is not set
 # CONFIG_IPMI_HANDLER is not set
 CONFIG_HW_RANDOM=y
+# CONFIG_HW_RANDOM_TIMERIOMEM is not set
 CONFIG_HW_RANDOM_PASEMI=y
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
@@ -948,57 +1078,85 @@ CONFIG_MAX_RAW_DEVS=256
 CONFIG_DEVPORT=y
 CONFIG_I2C=y
 CONFIG_I2C_BOARDINFO=y
+CONFIG_I2C_COMPAT=y
 CONFIG_I2C_CHARDEV=y
+CONFIG_I2C_HELPER_AUTO=y
 CONFIG_I2C_ALGOBIT=y
 
 #
 # I2C Hardware Bus support
 #
+
+#
+# PC SMBus host controller drivers
+#
 # CONFIG_I2C_ALI1535 is not set
 # CONFIG_I2C_ALI1563 is not set
 # CONFIG_I2C_ALI15X3 is not set
 # CONFIG_I2C_AMD756 is not set
 # CONFIG_I2C_AMD8111 is not set
 # CONFIG_I2C_I801 is not set
-# CONFIG_I2C_I810 is not set
+# CONFIG_I2C_ISCH is not set
 # CONFIG_I2C_PIIX4 is not set
 # CONFIG_I2C_NFORCE2 is not set
-# CONFIG_I2C_OCORES is not set
-# CONFIG_I2C_PARPORT_LIGHT is not set
-CONFIG_I2C_PASEMI=y
-# CONFIG_I2C_PROSAVAGE is not set
-# CONFIG_I2C_SAVAGE4 is not set
-# CONFIG_I2C_SIMTEC is not set
 # CONFIG_I2C_SIS5595 is not set
 # CONFIG_I2C_SIS630 is not set
 # CONFIG_I2C_SIS96X is not set
-# CONFIG_I2C_TAOS_EVM is not set
-# CONFIG_I2C_STUB is not set
-# CONFIG_I2C_TINY_USB is not set
 # CONFIG_I2C_VIA is not set
 # CONFIG_I2C_VIAPRO is not set
+
+#
+# I2C system bus drivers (mostly embedded / system-on-chip)
+#
+# CONFIG_I2C_OCORES is not set
+CONFIG_I2C_PASEMI=y
+# CONFIG_I2C_SIMTEC is not set
+
+#
+# External I2C/SMBus adapter drivers
+#
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_TAOS_EVM is not set
+# CONFIG_I2C_TINY_USB is not set
+
+#
+# Graphics adapter I2C/DDC channel drivers
+#
 # CONFIG_I2C_VOODOO3 is not set
+
+#
+# Other I2C/SMBus bus drivers
+#
 # CONFIG_I2C_PCA_PLATFORM is not set
+# CONFIG_I2C_STUB is not set
 
 #
 # Miscellaneous I2C Chip support
 #
 # CONFIG_DS1682 is not set
-CONFIG_EEPROM_LEGACY=y
-# CONFIG_SENSORS_PCF8574 is not set
-# CONFIG_PCF8575 is not set
-# CONFIG_SENSORS_PCF8591 is not set
-# CONFIG_SENSORS_MAX6875 is not set
 # CONFIG_SENSORS_TSL2550 is not set
 # CONFIG_I2C_DEBUG_CORE is not set
 # CONFIG_I2C_DEBUG_ALGO is not set
 # CONFIG_I2C_DEBUG_BUS is not set
 # CONFIG_I2C_DEBUG_CHIP is not set
 # CONFIG_SPI is not set
+
+#
+# PPS support
+#
+# CONFIG_PPS is not set
+CONFIG_ARCH_WANT_OPTIONAL_GPIOLIB=y
+# CONFIG_GPIOLIB is not set
 # CONFIG_W1 is not set
 # CONFIG_POWER_SUPPLY is not set
 CONFIG_HWMON=y
 CONFIG_HWMON_VID=y
+# CONFIG_HWMON_DEBUG_CHIP is not set
+
+#
+# Native drivers
+#
+# CONFIG_SENSORS_AD7414 is not set
 # CONFIG_SENSORS_AD7418 is not set
 # CONFIG_SENSORS_ADM1021 is not set
 # CONFIG_SENSORS_ADM1025 is not set
@@ -1006,14 +1164,17 @@ CONFIG_HWMON_VID=y
 # CONFIG_SENSORS_ADM1029 is not set
 # CONFIG_SENSORS_ADM1031 is not set
 # CONFIG_SENSORS_ADM9240 is not set
+# CONFIG_SENSORS_ADT7462 is not set
 # CONFIG_SENSORS_ADT7470 is not set
 # CONFIG_SENSORS_ADT7473 is not set
+# CONFIG_SENSORS_ADT7475 is not set
 # CONFIG_SENSORS_ATXP1 is not set
 # CONFIG_SENSORS_DS1621 is not set
 # CONFIG_SENSORS_I5K_AMB is not set
 # CONFIG_SENSORS_F71805F is not set
 # CONFIG_SENSORS_F71882FG is not set
 # CONFIG_SENSORS_F75375S is not set
+# CONFIG_SENSORS_G760A is not set
 # CONFIG_SENSORS_GL518SM is not set
 # CONFIG_SENSORS_GL520SM is not set
 # CONFIG_SENSORS_IT87 is not set
@@ -1028,10 +1189,14 @@ CONFIG_SENSORS_LM85=y
 CONFIG_SENSORS_LM90=y
 # CONFIG_SENSORS_LM92 is not set
 # CONFIG_SENSORS_LM93 is not set
+# CONFIG_SENSORS_LTC4215 is not set
+# CONFIG_SENSORS_LTC4245 is not set
+# CONFIG_SENSORS_LM95241 is not set
 # CONFIG_SENSORS_MAX1619 is not set
 # CONFIG_SENSORS_MAX6650 is not set
 # CONFIG_SENSORS_PC87360 is not set
 # CONFIG_SENSORS_PC87427 is not set
+# CONFIG_SENSORS_PCF8591 is not set
 # CONFIG_SENSORS_SIS5595 is not set
 # CONFIG_SENSORS_DME1737 is not set
 # CONFIG_SENSORS_SMSC47M1 is not set
@@ -1039,6 +1204,8 @@ CONFIG_SENSORS_LM90=y
 # CONFIG_SENSORS_SMSC47B397 is not set
 # CONFIG_SENSORS_ADS7828 is not set
 # CONFIG_SENSORS_THMC50 is not set
+# CONFIG_SENSORS_TMP401 is not set
+# CONFIG_SENSORS_TMP421 is not set
 # CONFIG_SENSORS_VIA686A is not set
 # CONFIG_SENSORS_VT1211 is not set
 # CONFIG_SENSORS_VT8231 is not set
@@ -1050,44 +1217,40 @@ CONFIG_SENSORS_LM90=y
 # CONFIG_SENSORS_W83L786NG is not set
 # CONFIG_SENSORS_W83627HF is not set
 # CONFIG_SENSORS_W83627EHF is not set
-# CONFIG_HWMON_DEBUG_CHIP is not set
 # CONFIG_THERMAL is not set
 # CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
 
 #
 # Sonics Silicon Backplane
 #
-CONFIG_SSB_POSSIBLE=y
 # CONFIG_SSB is not set
 
 #
 # Multifunction device drivers
 #
+# CONFIG_MFD_CORE is not set
 # CONFIG_MFD_SM501 is not set
 # CONFIG_HTC_PASIC3 is not set
-
-#
-# Multimedia devices
-#
-
-#
-# Multimedia core support
-#
-# CONFIG_VIDEO_DEV is not set
-# CONFIG_DVB_CORE is not set
-# CONFIG_VIDEO_MEDIA is not set
-
-#
-# Multimedia drivers
-#
-CONFIG_DAB=y
-# CONFIG_USB_DABUSB is not set
+# CONFIG_TWL4030_CORE is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_PMIC_DA903X is not set
+# CONFIG_MFD_WM8400 is not set
+# CONFIG_MFD_WM831X is not set
+# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_MFD_PCF50633 is not set
+# CONFIG_AB3100_CORE is not set
+# CONFIG_REGULATOR is not set
+# CONFIG_MEDIA_SUPPORT is not set
 
 #
 # Graphics support
 #
 # CONFIG_AGP is not set
+CONFIG_VGA_ARB=y
 CONFIG_DRM=y
+CONFIG_DRM_KMS_HELPER=y
+CONFIG_DRM_TTM=y
 # CONFIG_DRM_TDFX is not set
 # CONFIG_DRM_R128 is not set
 CONFIG_DRM_RADEON=y
@@ -1099,6 +1262,7 @@ CONFIG_VGASTATE=y
 CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_DDC=y
+# CONFIG_FB_BOOT_VESA_SUPPORT is not set
 CONFIG_FB_CFB_FILLRECT=y
 CONFIG_FB_CFB_COPYAREA=y
 CONFIG_FB_CFB_IMAGEBLIT=y
@@ -1140,6 +1304,7 @@ CONFIG_FB_RADEON_BACKLIGHT=y
 # CONFIG_FB_S3 is not set
 # CONFIG_FB_SAVAGE is not set
 # CONFIG_FB_SIS is not set
+# CONFIG_FB_VIA is not set
 # CONFIG_FB_NEOMAGIC is not set
 # CONFIG_FB_KYRO is not set
 # CONFIG_FB_3DFX is not set
@@ -1148,12 +1313,16 @@ CONFIG_FB_RADEON_BACKLIGHT=y
 # CONFIG_FB_TRIDENT is not set
 # CONFIG_FB_ARK is not set
 # CONFIG_FB_PM3 is not set
+# CONFIG_FB_CARMINE is not set
 # CONFIG_FB_IBM_GXT4500 is not set
 # CONFIG_FB_VIRTUAL is not set
+# CONFIG_FB_METRONOME is not set
+# CONFIG_FB_MB862XX is not set
+# CONFIG_FB_BROADSHEET is not set
 CONFIG_BACKLIGHT_LCD_SUPPORT=y
 # CONFIG_LCD_CLASS_DEVICE is not set
 CONFIG_BACKLIGHT_CLASS_DEVICE=y
-# CONFIG_BACKLIGHT_CORGI is not set
+CONFIG_BACKLIGHT_GENERIC=y
 
 #
 # Display device support
@@ -1177,15 +1346,9 @@ CONFIG_LOGO=y
 CONFIG_LOGO_LINUX_MONO=y
 CONFIG_LOGO_LINUX_VGA16=y
 CONFIG_LOGO_LINUX_CLUT224=y
-
-#
-# Sound
-#
 CONFIG_SOUND=y
-
-#
-# Advanced Linux Sound Architecture
-#
+CONFIG_SOUND_OSS_CORE=y
+CONFIG_SOUND_OSS_CORE_PRECLAIM=y
 CONFIG_SND=y
 CONFIG_SND_TIMER=y
 CONFIG_SND_PCM=y
@@ -1198,24 +1361,24 @@ CONFIG_SND_MIXER_OSS=y
 CONFIG_SND_PCM_OSS=y
 CONFIG_SND_PCM_OSS_PLUGINS=y
 CONFIG_SND_SEQUENCER_OSS=y
+# CONFIG_SND_HRTIMER is not set
 # CONFIG_SND_DYNAMIC_MINORS is not set
 CONFIG_SND_SUPPORT_OLD_API=y
 CONFIG_SND_VERBOSE_PROCFS=y
 # CONFIG_SND_VERBOSE_PRINTK is not set
 # CONFIG_SND_DEBUG is not set
-
-#
-# Generic devices
-#
+CONFIG_SND_RAWMIDI_SEQ=y
+# CONFIG_SND_OPL3_LIB_SEQ is not set
+# CONFIG_SND_OPL4_LIB_SEQ is not set
+# CONFIG_SND_SBAWE_SEQ is not set
+# CONFIG_SND_EMU10K1_SEQ is not set
+CONFIG_SND_DRIVERS=y
 # CONFIG_SND_DUMMY is not set
 # CONFIG_SND_VIRMIDI is not set
 # CONFIG_SND_MTPAV is not set
 # CONFIG_SND_SERIAL_U16550 is not set
 # CONFIG_SND_MPU401 is not set
-
-#
-# PCI devices
-#
+CONFIG_SND_PCI=y
 # CONFIG_SND_AD1889 is not set
 # CONFIG_SND_ALS300 is not set
 # CONFIG_SND_ALS4000 is not set
@@ -1234,6 +1397,7 @@ CONFIG_SND_VERBOSE_PROCFS=y
 # CONFIG_SND_CS4281 is not set
 # CONFIG_SND_CS46XX is not set
 # CONFIG_SND_CS5530 is not set
+# CONFIG_SND_CTXFI is not set
 # CONFIG_SND_DARLA20 is not set
 # CONFIG_SND_GINA20 is not set
 # CONFIG_SND_LAYLA20 is not set
@@ -1246,6 +1410,8 @@ CONFIG_SND_VERBOSE_PROCFS=y
 # CONFIG_SND_INDIGO is not set
 # CONFIG_SND_INDIGOIO is not set
 # CONFIG_SND_INDIGODJ is not set
+# CONFIG_SND_INDIGOIOX is not set
+# CONFIG_SND_INDIGODJX is not set
 # CONFIG_SND_EMU10K1 is not set
 # CONFIG_SND_EMU10K1X is not set
 # CONFIG_SND_ENS1370 is not set
@@ -1262,6 +1428,7 @@ CONFIG_SND_VERBOSE_PROCFS=y
 # CONFIG_SND_INTEL8X0 is not set
 # CONFIG_SND_INTEL8X0M is not set
 # CONFIG_SND_KORG1212 is not set
+# CONFIG_SND_LX6464ES is not set
 # CONFIG_SND_MAESTRO3 is not set
 # CONFIG_SND_MIXART is not set
 # CONFIG_SND_NM256 is not set
@@ -1277,57 +1444,64 @@ CONFIG_SND_VERBOSE_PROCFS=y
 # CONFIG_SND_VIRTUOSO is not set
 # CONFIG_SND_VX222 is not set
 # CONFIG_SND_YMFPCI is not set
-
-#
-# ALSA PowerMac devices
-#
-
-#
-# ALSA PowerPC devices
-#
-
-#
-# USB devices
-#
+CONFIG_SND_PPC=y
+CONFIG_SND_USB=y
 CONFIG_SND_USB_AUDIO=y
 CONFIG_SND_USB_USX2Y=y
 # CONFIG_SND_USB_CAIAQ is not set
-
-#
-# PCMCIA devices
-#
+CONFIG_SND_PCMCIA=y
 # CONFIG_SND_VXPOCKET is not set
 # CONFIG_SND_PDAUDIOCF is not set
-
-#
-# System on Chip audio support
-#
 # CONFIG_SND_SOC is not set
-
-#
-# ALSA SoC audio for Freescale SOCs
-#
-
-#
-# SoC Audio for the Texas Instruments OMAP
-#
-
-#
-# Open Sound System
-#
 # CONFIG_SOUND_PRIME is not set
 CONFIG_HID_SUPPORT=y
 CONFIG_HID=y
-# CONFIG_HID_DEBUG is not set
 # CONFIG_HIDRAW is not set
 
 #
 # USB Input Devices
 #
 CONFIG_USB_HID=y
-# CONFIG_USB_HIDINPUT_POWERBOOK is not set
-# CONFIG_HID_FF is not set
+# CONFIG_HID_PID is not set
 # CONFIG_USB_HIDDEV is not set
+
+#
+# Special HID drivers
+#
+CONFIG_HID_A4TECH=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DRAGONRISE=y
+# CONFIG_DRAGONRISE_FF is not set
+CONFIG_HID_EZKEY=y
+CONFIG_HID_KYE=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_TWINHAN=y
+CONFIG_HID_KENSINGTON=y
+CONFIG_HID_LOGITECH=y
+# CONFIG_LOGITECH_FF is not set
+# CONFIG_LOGIRUMBLEPAD2_FF is not set
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_NTRIG=y
+CONFIG_HID_PANTHERLORD=y
+# CONFIG_PANTHERLORD_FF is not set
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SUNPLUS=y
+CONFIG_HID_GREENASIA=y
+# CONFIG_GREENASIA_FF is not set
+CONFIG_HID_SMARTJOYPLUS=y
+# CONFIG_SMARTJOYPLUS_FF is not set
+CONFIG_HID_TOPSEED=y
+CONFIG_HID_THRUSTMASTER=y
+# CONFIG_THRUSTMASTER_FF is not set
+CONFIG_HID_ZEROPLUS=y
+# CONFIG_ZEROPLUS_FF is not set
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
@@ -1343,18 +1517,26 @@ CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DEVICE_CLASS is not set
 # CONFIG_USB_DYNAMIC_MINORS is not set
 # CONFIG_USB_OTG is not set
+# CONFIG_USB_MON is not set
+# CONFIG_USB_WUSB is not set
+# CONFIG_USB_WUSB_CBAF is not set
 
 #
 # USB Host Controller Drivers
 #
 # CONFIG_USB_C67X00_HCD is not set
+# CONFIG_USB_XHCI_HCD is not set
 CONFIG_USB_EHCI_HCD=y
 # CONFIG_USB_EHCI_ROOT_HUB_TT is not set
 # CONFIG_USB_EHCI_TT_NEWSCHED is not set
 CONFIG_USB_EHCI_HCD_PPC_OF=y
+# CONFIG_USB_OXU210HP_HCD is not set
 # CONFIG_USB_ISP116X_HCD is not set
 # CONFIG_USB_ISP1760_HCD is not set
+# CONFIG_USB_ISP1362_HCD is not set
 CONFIG_USB_OHCI_HCD=y
+# CONFIG_USB_OHCI_HCD_PPC_OF_BE is not set
+# CONFIG_USB_OHCI_HCD_PPC_OF_LE is not set
 # CONFIG_USB_OHCI_HCD_PPC_OF is not set
 # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
 # CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set
@@ -1363,6 +1545,8 @@ CONFIG_USB_UHCI_HCD=y
 CONFIG_USB_SL811_HCD=y
 # CONFIG_USB_SL811_CS is not set
 # CONFIG_USB_R8A66597_HCD is not set
+# CONFIG_USB_WHCI_HCD is not set
+# CONFIG_USB_HWA_HCD is not set
 
 #
 # USB Device Class drivers
@@ -1370,20 +1554,20 @@ CONFIG_USB_SL811_HCD=y
 # CONFIG_USB_ACM is not set
 # CONFIG_USB_PRINTER is not set
 # CONFIG_USB_WDM is not set
+# CONFIG_USB_TMC is not set
 
 #
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may
 #
 
 #
-# may also be needed; see USB_STORAGE Help for more information
+# also be needed; see USB_STORAGE Help for more info
 #
 CONFIG_USB_STORAGE=y
 # CONFIG_USB_STORAGE_DEBUG is not set
 # CONFIG_USB_STORAGE_DATAFAB is not set
 # CONFIG_USB_STORAGE_FREECOM is not set
 # CONFIG_USB_STORAGE_ISD200 is not set
-# CONFIG_USB_STORAGE_DPCM is not set
 # CONFIG_USB_STORAGE_USBAT is not set
 # CONFIG_USB_STORAGE_SDDR09 is not set
 # CONFIG_USB_STORAGE_SDDR55 is not set
@@ -1399,7 +1583,6 @@ CONFIG_USB_LIBUSUAL=y
 #
 # CONFIG_USB_MDC800 is not set
 # CONFIG_USB_MICROTEK is not set
-# CONFIG_USB_MON is not set
 
 #
 # USB port drivers
@@ -1412,7 +1595,7 @@ CONFIG_USB_LIBUSUAL=y
 # CONFIG_USB_EMI62 is not set
 # CONFIG_USB_EMI26 is not set
 # CONFIG_USB_ADUTUX is not set
-# CONFIG_USB_AUERSWALD is not set
+# CONFIG_USB_SEVSEG is not set
 # CONFIG_USB_RIO500 is not set
 # CONFIG_USB_LEGOTOWER is not set
 # CONFIG_USB_LCD is not set
@@ -1420,7 +1603,6 @@ CONFIG_USB_LIBUSUAL=y
 # CONFIG_USB_LED is not set
 # CONFIG_USB_CYPRESS_CY7C63 is not set
 # CONFIG_USB_CYTHERM is not set
-# CONFIG_USB_PHIDGET is not set
 # CONFIG_USB_IDMOUSE is not set
 # CONFIG_USB_FTDI_ELAN is not set
 # CONFIG_USB_APPLEDISPLAY is not set
@@ -1429,7 +1611,15 @@ CONFIG_USB_LIBUSUAL=y
 # CONFIG_USB_TRANCEVIBRATOR is not set
 # CONFIG_USB_IOWARRIOR is not set
 # CONFIG_USB_TEST is not set
+# CONFIG_USB_ISIGHTFW is not set
+# CONFIG_USB_VST is not set
 # CONFIG_USB_GADGET is not set
+
+#
+# OTG and related infrastructure
+#
+# CONFIG_NOP_USB_XCEIV is not set
+# CONFIG_UWB is not set
 # CONFIG_MMC is not set
 # CONFIG_MEMSTICK is not set
 # CONFIG_NEW_LEDS is not set
@@ -1443,6 +1633,7 @@ CONFIG_EDAC=y
 # CONFIG_EDAC_DEBUG is not set
 CONFIG_EDAC_MM_EDAC=y
 CONFIG_EDAC_PASEMI=y
+# CONFIG_EDAC_CPC925 is not set
 CONFIG_RTC_LIB=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_HCTOSYS=y
@@ -1472,6 +1663,9 @@ CONFIG_RTC_DRV_DS1307=y
 # CONFIG_RTC_DRV_PCF8583 is not set
 # CONFIG_RTC_DRV_M41T80 is not set
 # CONFIG_RTC_DRV_S35390A is not set
+# CONFIG_RTC_DRV_FM3130 is not set
+# CONFIG_RTC_DRV_RX8581 is not set
+# CONFIG_RTC_DRV_RX8025 is not set
 
 #
 # SPI RTC drivers
@@ -1481,20 +1675,30 @@ CONFIG_RTC_DRV_DS1307=y
 # Platform RTC drivers
 #
 # CONFIG_RTC_DRV_CMOS is not set
+# CONFIG_RTC_DRV_DS1286 is not set
 # CONFIG_RTC_DRV_DS1511 is not set
 # CONFIG_RTC_DRV_DS1553 is not set
 # CONFIG_RTC_DRV_DS1742 is not set
 # CONFIG_RTC_DRV_STK17TA8 is not set
 # CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T35 is not set
 # CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_BQ4802 is not set
 # CONFIG_RTC_DRV_V3020 is not set
 
 #
 # on-CPU RTC drivers
 #
+# CONFIG_RTC_DRV_GENERIC is not set
 # CONFIG_DMADEVICES is not set
+# CONFIG_AUXDISPLAY is not set
 # CONFIG_UIO is not set
 
+#
+# TI VLYNQ
+#
+# CONFIG_STAGING is not set
+
 #
 # File systems
 #
@@ -1504,11 +1708,13 @@ CONFIG_EXT2_FS_POSIX_ACL=y
 # CONFIG_EXT2_FS_SECURITY is not set
 # CONFIG_EXT2_FS_XIP is not set
 CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
-# CONFIG_EXT4DEV_FS is not set
+# CONFIG_EXT4_FS is not set
 CONFIG_JBD=y
+# CONFIG_JBD_DEBUG is not set
 CONFIG_FS_MBCACHE=y
 # CONFIG_REISERFS_FS is not set
 # CONFIG_JFS_FS is not set
@@ -1516,6 +1722,10 @@ CONFIG_FS_POSIX_ACL=y
 # CONFIG_XFS_FS is not set
 # CONFIG_GFS2_FS is not set
 # CONFIG_OCFS2_FS is not set
+# CONFIG_BTRFS_FS is not set
+# CONFIG_NILFS2_FS is not set
+CONFIG_FILE_LOCKING=y
+CONFIG_FSNOTIFY=y
 CONFIG_DNOTIFY=y
 CONFIG_INOTIFY=y
 CONFIG_INOTIFY_USER=y
@@ -1524,6 +1734,11 @@ CONFIG_AUTOFS_FS=y
 CONFIG_AUTOFS4_FS=y
 # CONFIG_FUSE_FS is not set
 
+#
+# Caches
+#
+# CONFIG_FSCACHE is not set
+
 #
 # CD-ROM/DVD Filesystems
 #
@@ -1549,16 +1764,14 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
 CONFIG_PROC_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
 # CONFIG_TMPFS_POSIX_ACL is not set
 CONFIG_HUGETLBFS=y
 CONFIG_HUGETLB_PAGE=y
 CONFIG_CONFIGFS_FS=y
-
-#
-# Miscellaneous filesystems
-#
+CONFIG_MISC_FILESYSTEMS=y
 # CONFIG_ADFS_FS is not set
 # CONFIG_AFFS_FS is not set
 # CONFIG_HFS_FS is not set
@@ -1578,8 +1791,10 @@ CONFIG_JFFS2_ZLIB=y
 CONFIG_JFFS2_RTIME=y
 # CONFIG_JFFS2_RUBIN is not set
 # CONFIG_CRAMFS is not set
+# CONFIG_SQUASHFS is not set
 # CONFIG_VXFS_FS is not set
 # CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
 # CONFIG_ROMFS_FS is not set
@@ -1590,18 +1805,17 @@ CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
 # CONFIG_NFS_V3_ACL is not set
 # CONFIG_NFS_V4 is not set
+CONFIG_ROOT_NFS=y
 CONFIG_NFSD=y
 CONFIG_NFSD_V3=y
 # CONFIG_NFSD_V3_ACL is not set
 CONFIG_NFSD_V4=y
-CONFIG_ROOT_NFS=y
 CONFIG_LOCKD=y
 CONFIG_LOCKD_V4=y
 CONFIG_EXPORTFS=y
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=y
 CONFIG_SUNRPC_GSS=y
-# CONFIG_SUNRPC_BIND34 is not set
 CONFIG_RPCSEC_GSS_KRB5=y
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
@@ -1672,25 +1886,30 @@ CONFIG_NLS_ISO8859_1=y
 # CONFIG_NLS_KOI8_U is not set
 # CONFIG_NLS_UTF8 is not set
 # CONFIG_DLM is not set
+CONFIG_BINARY_PRINTF=y
 
 #
 # Library routines
 #
 CONFIG_BITREVERSE=y
-# CONFIG_GENERIC_FIND_FIRST_BIT is not set
+CONFIG_GENERIC_FIND_LAST_BIT=y
 CONFIG_CRC_CCITT=y
 # CONFIG_CRC16 is not set
+# CONFIG_CRC_T10DIF is not set
 CONFIG_CRC_ITU_T=y
 CONFIG_CRC32=y
 # CONFIG_CRC7 is not set
-CONFIG_LIBCRC32C=m
+# CONFIG_LIBCRC32C is not set
 CONFIG_ZLIB_INFLATE=y
 CONFIG_ZLIB_DEFLATE=y
-CONFIG_PLIST=y
+CONFIG_DECOMPRESS_GZIP=y
+CONFIG_DECOMPRESS_BZIP2=y
+CONFIG_DECOMPRESS_LZMA=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
 CONFIG_HAS_DMA=y
 CONFIG_HAVE_LMB=y
+CONFIG_NLATTR=y
 
 #
 # Kernel hacking
@@ -1700,18 +1919,25 @@ CONFIG_ENABLE_WARN_DEPRECATED=y
 CONFIG_ENABLE_MUST_CHECK=y
 CONFIG_FRAME_WARN=2048
 CONFIG_MAGIC_SYSRQ=y
+# CONFIG_STRIP_ASM_SYMS is not set
 # CONFIG_UNUSED_SYMBOLS is not set
-# CONFIG_DEBUG_FS is not set
+CONFIG_DEBUG_FS=y
 # CONFIG_HEADERS_CHECK is not set
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_DEBUG_SHIRQ is not set
 CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+CONFIG_DETECT_HUNG_TASK=y
+# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set
+CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE=0
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
 # CONFIG_DEBUG_OBJECTS is not set
 # CONFIG_SLUB_DEBUG_ON is not set
 # CONFIG_SLUB_STATS is not set
+# CONFIG_DEBUG_KMEMLEAK is not set
 # CONFIG_DEBUG_RT_MUTEXES is not set
 # CONFIG_RT_MUTEX_TESTER is not set
 # CONFIG_DEBUG_SPINLOCK is not set
@@ -1721,26 +1947,71 @@ CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_LOCK_STAT is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+CONFIG_STACKTRACE=y
 # CONFIG_DEBUG_KOBJECT is not set
 CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_INFO is not set
 # CONFIG_DEBUG_VM is not set
 # CONFIG_DEBUG_WRITECOUNT is not set
+CONFIG_DEBUG_MEMORY_INIT=y
 # CONFIG_DEBUG_LIST is not set
 # CONFIG_DEBUG_SG is not set
-# CONFIG_BOOT_PRINTK_DELAY is not set
+# CONFIG_DEBUG_NOTIFIERS is not set
+# CONFIG_DEBUG_CREDENTIALS is not set
 # CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 # CONFIG_BACKTRACE_SELF_TEST is not set
+# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
+# CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set
 # CONFIG_FAULT_INJECTION is not set
+# CONFIG_LATENCYTOP is not set
+CONFIG_SYSCTL_SYSCALL_CHECK=y
+# CONFIG_DEBUG_PAGEALLOC is not set
+CONFIG_NOP_TRACER=y
+CONFIG_HAVE_FUNCTION_TRACER=y
+CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+CONFIG_RING_BUFFER=y
+CONFIG_EVENT_TRACING=y
+CONFIG_CONTEXT_SWITCH_TRACER=y
+CONFIG_RING_BUFFER_ALLOW_SWAP=y
+CONFIG_TRACING=y
+CONFIG_TRACING_SUPPORT=y
+CONFIG_FTRACE=y
+# CONFIG_FUNCTION_TRACER is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_ENABLE_DEFAULT_TRACERS is not set
+# CONFIG_BOOT_TRACER is not set
+CONFIG_BRANCH_PROFILE_NONE=y
+# CONFIG_PROFILE_ANNOTATED_BRANCHES is not set
+# CONFIG_PROFILE_ALL_BRANCHES is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_KMEMTRACE is not set
+# CONFIG_WORKQUEUE_TRACER is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_RING_BUFFER_BENCHMARK is not set
+# CONFIG_DYNAMIC_DEBUG is not set
+# CONFIG_DMA_API_DEBUG is not set
 # CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_KGDB is not set
+# CONFIG_PPC_DISABLE_WERROR is not set
+CONFIG_PPC_WERROR=y
+CONFIG_PRINT_STACK_DEPTH=64
 # CONFIG_DEBUG_STACKOVERFLOW is not set
 # CONFIG_DEBUG_STACK_USAGE is not set
-# CONFIG_DEBUG_PAGEALLOC is not set
-CONFIG_DEBUGGER=y
+# CONFIG_PPC_EMULATED_STATS is not set
+# CONFIG_CODE_PATCHING_SELFTEST is not set
+# CONFIG_FTR_FIXUP_SELFTEST is not set
+# CONFIG_MSI_BITMAP_SELFTEST is not set
 CONFIG_XMON=y
 CONFIG_XMON_DEFAULT=y
 CONFIG_XMON_DISASSEMBLY=y
+CONFIG_DEBUGGER=y
 # CONFIG_IRQSTACKS is not set
+# CONFIG_VIRQ_DEBUG is not set
 # CONFIG_BOOTX_TEXT is not set
 # CONFIG_PPC_EARLY_DEBUG is not set
 
@@ -1749,23 +2020,34 @@ CONFIG_XMON_DISASSEMBLY=y
 #
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
+# CONFIG_SECURITYFS is not set
 # CONFIG_SECURITY_FILE_CAPABILITIES is not set
 CONFIG_XOR_BLOCKS=y
 CONFIG_ASYNC_CORE=y
 CONFIG_ASYNC_MEMCPY=y
 CONFIG_ASYNC_XOR=y
+CONFIG_ASYNC_PQ=y
+CONFIG_ASYNC_RAID6_RECOV=y
 CONFIG_CRYPTO=y
 
 #
 # Crypto core or helper
 #
 CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_ALGAPI2=y
 CONFIG_CRYPTO_AEAD=y
+CONFIG_CRYPTO_AEAD2=y
 CONFIG_CRYPTO_BLKCIPHER=y
+CONFIG_CRYPTO_BLKCIPHER2=y
 CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_HASH2=y
+CONFIG_CRYPTO_RNG2=y
+CONFIG_CRYPTO_PCOMP=y
 CONFIG_CRYPTO_MANAGER=y
+CONFIG_CRYPTO_MANAGER2=y
 # CONFIG_CRYPTO_GF128MUL is not set
 # CONFIG_CRYPTO_NULL is not set
+CONFIG_CRYPTO_WORKQUEUE=y
 # CONFIG_CRYPTO_CRYPTD is not set
 CONFIG_CRYPTO_AUTHENC=y
 # CONFIG_CRYPTO_TEST is not set
@@ -1793,14 +2075,20 @@ CONFIG_CRYPTO_CBC=y
 #
 CONFIG_CRYPTO_HMAC=y
 # CONFIG_CRYPTO_XCBC is not set
+# CONFIG_CRYPTO_VMAC is not set
 
 #
 # Digest
 #
 # CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_GHASH is not set
 CONFIG_CRYPTO_MD4=y
 CONFIG_CRYPTO_MD5=y
 # CONFIG_CRYPTO_MICHAEL_MIC is not set
+# CONFIG_CRYPTO_RMD128 is not set
+# CONFIG_CRYPTO_RMD160 is not set
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
 CONFIG_CRYPTO_SHA1=y
 CONFIG_CRYPTO_SHA256=y
 CONFIG_CRYPTO_SHA512=y
@@ -1830,7 +2118,13 @@ CONFIG_CRYPTO_DES=y
 # Compression
 #
 # CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_ZLIB is not set
 # CONFIG_CRYPTO_LZO is not set
+
+#
+# Random Number Generation
+#
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
 # CONFIG_CRYPTO_DEV_HIFN_795X is not set
 # CONFIG_PPC_CLOCK is not set

From 588e050887c5f00a39b056848ea58c8b496beab0 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Fri, 30 Oct 2009 16:59:44 +1100
Subject: [PATCH 026/151] powerpc/8xx: Fix build breakage with sparse irq
 changes

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/8xx/m8xx_setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c
index 385acfc48397..242954c4293f 100644
--- a/arch/powerpc/platforms/8xx/m8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/m8xx_setup.c
@@ -222,7 +222,7 @@ static void cpm_cascade(unsigned int irq, struct irq_desc *desc)
 	int cascade_irq;
 
 	if ((cascade_irq = cpm_get_irq()) >= 0) {
-		struct irq_desc *cdesc = irq_desc + cascade_irq;
+		struct irq_desc *cdesc = irq_to_desc(cascade_irq);
 
 		generic_handle_irq(cascade_irq);
 		cdesc->chip->eoi(cascade_irq);

From 835ad8e76ca75483d53d625b61b937c234cfeedf Mon Sep 17 00:00:00 2001
From: Dave Mitchell <dmitchell@appliedmicro.com>
Date: Thu, 8 Oct 2009 06:33:29 +0000
Subject: [PATCH 027/151] powerpc/4xx: Add 16K FIFO size DTS entries on
 supported platforms

Adding tx/rx-fifo-size-gige to EMAC fields for evaluation kit DTS
files where appropriate.

Signed-off-by: Dave Mitchell <dmitchell@appliedmicro.com>
Acked-by: Prodyut Hazarika <phazarika@appliedmicro.com>
Acked-by: Victor Gallardo <vgallardo@appliedmicro.com>
Acked-by: Loc Ho <lho@appliedmicro.com>
Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
---
 arch/powerpc/boot/dts/canyonlands.dts | 2 ++
 arch/powerpc/boot/dts/eiger.dts       | 6 ++++++
 arch/powerpc/boot/dts/glacier.dts     | 6 ++++++
 arch/powerpc/boot/dts/haleakala.dts   | 2 ++
 arch/powerpc/boot/dts/kilauea.dts     | 4 ++++
 arch/powerpc/boot/dts/makalu.dts      | 4 ++++
 arch/powerpc/boot/dts/redwood.dts     | 1 +
 7 files changed, 25 insertions(+)

diff --git a/arch/powerpc/boot/dts/canyonlands.dts b/arch/powerpc/boot/dts/canyonlands.dts
index c920170b7dfe..cd56bb5b347b 100644
--- a/arch/powerpc/boot/dts/canyonlands.dts
+++ b/arch/powerpc/boot/dts/canyonlands.dts
@@ -352,6 +352,7 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII0>;
@@ -381,6 +382,7 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII0>;
diff --git a/arch/powerpc/boot/dts/eiger.dts b/arch/powerpc/boot/dts/eiger.dts
index c4a934f2e886..48bcf7187924 100644
--- a/arch/powerpc/boot/dts/eiger.dts
+++ b/arch/powerpc/boot/dts/eiger.dts
@@ -316,6 +316,7 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII0>;
@@ -345,6 +346,7 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII0>;
@@ -375,6 +377,8 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
+				tx-fifo-size-gige = <16384>; /* emac2&3 only */
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII1>;
@@ -403,6 +407,8 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
+				tx-fifo-size-gige = <16384>; /* emac2&3 only */
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII1>;
diff --git a/arch/powerpc/boot/dts/glacier.dts b/arch/powerpc/boot/dts/glacier.dts
index f3787a27f634..f6f618939293 100644
--- a/arch/powerpc/boot/dts/glacier.dts
+++ b/arch/powerpc/boot/dts/glacier.dts
@@ -292,6 +292,7 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII0>;
@@ -321,6 +322,7 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII0>;
@@ -351,6 +353,8 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
+				tx-fifo-size-gige = <16384>; /* emac2&3 only */
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII1>;
@@ -379,6 +383,8 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
+				tx-fifo-size-gige = <16384>; /* emac2&3 only */
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII1>;
diff --git a/arch/powerpc/boot/dts/haleakala.dts b/arch/powerpc/boot/dts/haleakala.dts
index 5b2a4947bf82..2b256694eca6 100644
--- a/arch/powerpc/boot/dts/haleakala.dts
+++ b/arch/powerpc/boot/dts/haleakala.dts
@@ -226,6 +226,8 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
+				tx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII0>;
diff --git a/arch/powerpc/boot/dts/kilauea.dts b/arch/powerpc/boot/dts/kilauea.dts
index c46561456ede..083e68eeaca4 100644
--- a/arch/powerpc/boot/dts/kilauea.dts
+++ b/arch/powerpc/boot/dts/kilauea.dts
@@ -272,6 +272,8 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
+				tx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII0>;
@@ -300,6 +302,8 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
+				tx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII0>;
diff --git a/arch/powerpc/boot/dts/makalu.dts b/arch/powerpc/boot/dts/makalu.dts
index ffc246e72670..63d48b632c84 100644
--- a/arch/powerpc/boot/dts/makalu.dts
+++ b/arch/powerpc/boot/dts/makalu.dts
@@ -227,6 +227,8 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
+				tx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x0000003f>;	/* Start at 6 */
 				rgmii-device = <&RGMII0>;
@@ -255,6 +257,8 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+                                rx-fifo-size-gige = <16384>;
+                                tx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII0>;
diff --git a/arch/powerpc/boot/dts/redwood.dts b/arch/powerpc/boot/dts/redwood.dts
index ad402c488741..d2af32e2bf7a 100644
--- a/arch/powerpc/boot/dts/redwood.dts
+++ b/arch/powerpc/boot/dts/redwood.dts
@@ -226,6 +226,7 @@
 				max-frame-size = <9000>;
 				rx-fifo-size = <4096>;
 				tx-fifo-size = <2048>;
+				rx-fifo-size-gige = <16384>;
 				phy-mode = "rgmii";
 				phy-map = <0x00000000>;
 				rgmii-device = <&RGMII0>;

From 59e1d4952d4cb81ee9a4c22c6cfa23604c5e1ea1 Mon Sep 17 00:00:00 2001
From: Stefan Roese <sr@denx.de>
Date: Thu, 22 Oct 2009 21:14:03 +0000
Subject: [PATCH 028/151] powerpc/44x: Enable 64bit (>= 4GB) memory size in
 Katmai dts

Additionally to increasing #size-cells to in the root node, we also
need to explicitly define the ranges property in the plb node, because
of the different #size-cells between child and parent.

Signed-off-by: Stefan Roese <sr@denx.de>
Cc: Josh Boyer <jwboyer@linux.vnet.ibm.com>
Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
---
 arch/powerpc/boot/dts/katmai.dts | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/boot/dts/katmai.dts b/arch/powerpc/boot/dts/katmai.dts
index 077819bc3cbd..b8cd97c5c74e 100644
--- a/arch/powerpc/boot/dts/katmai.dts
+++ b/arch/powerpc/boot/dts/katmai.dts
@@ -16,7 +16,7 @@
 
 / {
 	#address-cells = <2>;
-	#size-cells = <1>;
+	#size-cells = <2>;
 	model = "amcc,katmai";
 	compatible = "amcc,katmai";
 	dcr-parent = <&{/cpus/cpu@0}>;
@@ -49,7 +49,7 @@
 
 	memory {
 		device_type = "memory";
-		reg = <0x00000000 0x00000000 0x00000000>; /* Filled in by zImage */
+		reg = <0x0 0x00000000 0x0 0x00000000>; /* Filled in by U-Boot */
 	};
 
 	UIC0: interrupt-controller0 {
@@ -112,7 +112,15 @@
 		compatible = "ibm,plb-440spe", "ibm,plb-440gp", "ibm,plb4";
 		#address-cells = <2>;
 		#size-cells = <1>;
-		ranges;
+		/*        addr-child     addr-parent    size */
+		ranges = <0x4 0xe0000000 0x4 0xe0000000 0x20000000
+			  0xc 0x00000000 0xc 0x00000000 0x20000000
+			  0xd 0x00000000 0xd 0x00000000 0x80000000
+			  0xd 0x80000000 0xd 0x80000000 0x80000000
+			  0xe 0x00000000 0xe 0x00000000 0x80000000
+			  0xe 0x80000000 0xe 0x80000000 0x80000000
+			  0xf 0x00000000 0xf 0x00000000 0x80000000
+			  0xf 0x80000000 0xf 0x80000000 0x80000000>;
 		clock-frequency = <0>; /* Filled in by zImage */
 
 		SDRAM0: sdram {

From ad6577629acf8a3f47165248ca7ccc0d94673ada Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@secretlab.ca>
Date: Wed, 4 Nov 2009 15:23:37 -0700
Subject: [PATCH 029/151] spi/mpc5200: Register SPI devices described in device
 tree

Add call to of_register_spi_devices() to register SPI devices described
in the OF device tree.

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Acked-by: Wolfram Sang <w.sang@pengutronix.de>
---
 drivers/spi/mpc52xx_psc_spi.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/mpc52xx_psc_spi.c b/drivers/spi/mpc52xx_psc_spi.c
index 1b74d5ca03f3..a14e9fdc0065 100644
--- a/drivers/spi/mpc52xx_psc_spi.c
+++ b/drivers/spi/mpc52xx_psc_spi.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/interrupt.h>
 #include <linux/of_platform.h>
+#include <linux/of_spi.h>
 #include <linux/workqueue.h>
 #include <linux/completion.h>
 #include <linux/io.h>
@@ -464,6 +465,7 @@ static int __init mpc52xx_psc_spi_of_probe(struct of_device *op,
 	const u32 *regaddr_p;
 	u64 regaddr64, size64;
 	s16 id = -1;
+	int rc;
 
 	regaddr_p = of_get_address(op->node, 0, &size64, NULL);
 	if (!regaddr_p) {
@@ -485,8 +487,12 @@ static int __init mpc52xx_psc_spi_of_probe(struct of_device *op,
 		id = *psc_nump + 1;
 	}
 
-	return mpc52xx_psc_spi_do_probe(&op->dev, (u32)regaddr64, (u32)size64,
+	rc = mpc52xx_psc_spi_do_probe(&op->dev, (u32)regaddr64, (u32)size64,
 					irq_of_parse_and_map(op->node, 0), id);
+	if (rc == 0)
+		of_register_spi_devices(dev_get_drvdata(&op->dev), op->node);
+
+	return rc;
 }
 
 static int __exit mpc52xx_psc_spi_of_remove(struct of_device *op)

From 42bbb70980f3720b0ae6da6af862af0e95a04351 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@secretlab.ca>
Date: Wed, 4 Nov 2009 15:34:18 -0700
Subject: [PATCH 030/151] powerpc/5200: Add mpc5200-spi (non-PSC) device driver

Adds support for the dedicated SPI device on the Freescale MPC5200(b)
SoC.

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 drivers/spi/Kconfig             |   8 +
 drivers/spi/Makefile            |   1 +
 drivers/spi/mpc52xx_spi.c       | 520 ++++++++++++++++++++++++++++++++
 include/linux/spi/mpc52xx_spi.h |  10 +
 4 files changed, 539 insertions(+)
 create mode 100644 drivers/spi/mpc52xx_spi.c
 create mode 100644 include/linux/spi/mpc52xx_spi.h

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 4b6f7cba3b3d..2a4ba1993083 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -133,6 +133,14 @@ config SPI_LM70_LLP
 	  which interfaces to an LM70 temperature sensor using
 	  a parallel port.
 
+config SPI_MPC52xx
+	tristate "Freescale MPC52xx SPI (non-PSC) controller support"
+	depends on PPC_MPC52xx && SPI
+	select SPI_MASTER_OF
+	help
+	  This drivers supports the MPC52xx SPI controller in master SPI
+	  mode.
+
 config SPI_MPC52xx_PSC
 	tristate "Freescale MPC52xx PSC SPI controller"
 	depends on PPC_MPC52xx && EXPERIMENTAL
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 21a118269cac..e3f092a9afa5 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_SPI_OMAP24XX)		+= omap2_mcspi.o
 obj-$(CONFIG_SPI_ORION)			+= orion_spi.o
 obj-$(CONFIG_SPI_PL022)			+= amba-pl022.o
 obj-$(CONFIG_SPI_MPC52xx_PSC)		+= mpc52xx_psc_spi.o
+obj-$(CONFIG_SPI_MPC52xx)		+= mpc52xx_spi.o
 obj-$(CONFIG_SPI_MPC8xxx)		+= spi_mpc8xxx.o
 obj-$(CONFIG_SPI_PPC4xx)		+= spi_ppc4xx.o
 obj-$(CONFIG_SPI_S3C24XX_GPIO)		+= spi_s3c24xx_gpio.o
diff --git a/drivers/spi/mpc52xx_spi.c b/drivers/spi/mpc52xx_spi.c
new file mode 100644
index 000000000000..ef8379b2c172
--- /dev/null
+++ b/drivers/spi/mpc52xx_spi.c
@@ -0,0 +1,520 @@
+/*
+ * MPC52xx SPI bus driver.
+ *
+ * Copyright (C) 2008 Secret Lab Technologies Ltd.
+ *
+ * This file is released under the GPLv2
+ *
+ * This is the driver for the MPC5200's dedicated SPI controller.
+ *
+ * Note: this driver does not support the MPC5200 PSC in SPI mode.  For
+ * that driver see drivers/spi/mpc52xx_psc_spi.c
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/of_platform.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/mpc52xx_spi.h>
+#include <linux/of_spi.h>
+#include <linux/io.h>
+#include <asm/time.h>
+#include <asm/mpc52xx.h>
+
+MODULE_AUTHOR("Grant Likely <grant.likely@secretlab.ca>");
+MODULE_DESCRIPTION("MPC52xx SPI (non-PSC) Driver");
+MODULE_LICENSE("GPL");
+
+/* Register offsets */
+#define SPI_CTRL1	0x00
+#define SPI_CTRL1_SPIE		(1 << 7)
+#define SPI_CTRL1_SPE		(1 << 6)
+#define SPI_CTRL1_MSTR		(1 << 4)
+#define SPI_CTRL1_CPOL		(1 << 3)
+#define SPI_CTRL1_CPHA		(1 << 2)
+#define SPI_CTRL1_SSOE		(1 << 1)
+#define SPI_CTRL1_LSBFE		(1 << 0)
+
+#define SPI_CTRL2	0x01
+#define SPI_BRR		0x04
+
+#define SPI_STATUS	0x05
+#define SPI_STATUS_SPIF		(1 << 7)
+#define SPI_STATUS_WCOL		(1 << 6)
+#define SPI_STATUS_MODF		(1 << 4)
+
+#define SPI_DATA	0x09
+#define SPI_PORTDATA	0x0d
+#define SPI_DATADIR	0x10
+
+/* FSM state return values */
+#define FSM_STOP	0	/* Nothing more for the state machine to */
+				/* do.  If something interesting happens */
+				/* then and IRQ will be received */
+#define FSM_POLL	1	/* need to poll for completion, an IRQ is */
+				/* not expected */
+#define FSM_CONTINUE	2	/* Keep iterating the state machine */
+
+/* Driver internal data */
+struct mpc52xx_spi {
+	struct spi_master *master;
+	u32 sysclk;
+	void __iomem *regs;
+	int irq0;	/* MODF irq */
+	int irq1;	/* SPIF irq */
+	int ipb_freq;
+
+	/* Statistics */
+	int msg_count;
+	int wcol_count;
+	int wcol_ticks;
+	u32 wcol_tx_timestamp;
+	int modf_count;
+	int byte_count;
+
+	struct list_head queue;		/* queue of pending messages */
+	spinlock_t lock;
+	struct work_struct work;
+
+
+	/* Details of current transfer (length, and buffer pointers) */
+	struct spi_message *message;	/* current message */
+	struct spi_transfer *transfer;	/* current transfer */
+	int (*state)(int irq, struct mpc52xx_spi *ms, u8 status, u8 data);
+	int len;
+	int timestamp;
+	u8 *rx_buf;
+	const u8 *tx_buf;
+	int cs_change;
+};
+
+/*
+ * CS control function
+ */
+static void mpc52xx_spi_chipsel(struct mpc52xx_spi *ms, int value)
+{
+	out_8(ms->regs + SPI_PORTDATA, value ? 0 : 0x08);
+}
+
+/*
+ * Start a new transfer.  This is called both by the idle state
+ * for the first transfer in a message, and by the wait state when the
+ * previous transfer in a message is complete.
+ */
+static void mpc52xx_spi_start_transfer(struct mpc52xx_spi *ms)
+{
+	ms->rx_buf = ms->transfer->rx_buf;
+	ms->tx_buf = ms->transfer->tx_buf;
+	ms->len = ms->transfer->len;
+
+	/* Activate the chip select */
+	if (ms->cs_change)
+		mpc52xx_spi_chipsel(ms, 1);
+	ms->cs_change = ms->transfer->cs_change;
+
+	/* Write out the first byte */
+	ms->wcol_tx_timestamp = get_tbl();
+	if (ms->tx_buf)
+		out_8(ms->regs + SPI_DATA, *ms->tx_buf++);
+	else
+		out_8(ms->regs + SPI_DATA, 0);
+}
+
+/* Forward declaration of state handlers */
+static int mpc52xx_spi_fsmstate_transfer(int irq, struct mpc52xx_spi *ms,
+					 u8 status, u8 data);
+static int mpc52xx_spi_fsmstate_wait(int irq, struct mpc52xx_spi *ms,
+				     u8 status, u8 data);
+
+/*
+ * IDLE state
+ *
+ * No transfers are in progress; if another transfer is pending then retrieve
+ * it and kick it off.  Otherwise, stop processing the state machine
+ */
+static int
+mpc52xx_spi_fsmstate_idle(int irq, struct mpc52xx_spi *ms, u8 status, u8 data)
+{
+	struct spi_device *spi;
+	int spr, sppr;
+	u8 ctrl1;
+
+	if (status && (irq != NO_IRQ))
+		dev_err(&ms->master->dev, "spurious irq, status=0x%.2x\n",
+			status);
+
+	/* Check if there is another transfer waiting. */
+	if (list_empty(&ms->queue))
+		return FSM_STOP;
+
+	/* get the head of the queue */
+	ms->message = list_first_entry(&ms->queue, struct spi_message, queue);
+	list_del_init(&ms->message->queue);
+
+	/* Setup the controller parameters */
+	ctrl1 = SPI_CTRL1_SPIE | SPI_CTRL1_SPE | SPI_CTRL1_MSTR;
+	spi = ms->message->spi;
+	if (spi->mode & SPI_CPHA)
+		ctrl1 |= SPI_CTRL1_CPHA;
+	if (spi->mode & SPI_CPOL)
+		ctrl1 |= SPI_CTRL1_CPOL;
+	if (spi->mode & SPI_LSB_FIRST)
+		ctrl1 |= SPI_CTRL1_LSBFE;
+	out_8(ms->regs + SPI_CTRL1, ctrl1);
+
+	/* Setup the controller speed */
+	/* minimum divider is '2'.  Also, add '1' to force rounding the
+	 * divider up. */
+	sppr = ((ms->ipb_freq / ms->message->spi->max_speed_hz) + 1) >> 1;
+	spr = 0;
+	if (sppr < 1)
+		sppr = 1;
+	while (((sppr - 1) & ~0x7) != 0) {
+		sppr = (sppr + 1) >> 1; /* add '1' to force rounding up */
+		spr++;
+	}
+	sppr--;		/* sppr quantity in register is offset by 1 */
+	if (spr > 7) {
+		/* Don't overrun limits of SPI baudrate register */
+		spr = 7;
+		sppr = 7;
+	}
+	out_8(ms->regs + SPI_BRR, sppr << 4 | spr); /* Set speed */
+
+	ms->cs_change = 1;
+	ms->transfer = container_of(ms->message->transfers.next,
+				    struct spi_transfer, transfer_list);
+
+	mpc52xx_spi_start_transfer(ms);
+	ms->state = mpc52xx_spi_fsmstate_transfer;
+
+	return FSM_CONTINUE;
+}
+
+/*
+ * TRANSFER state
+ *
+ * In the middle of a transfer.  If the SPI core has completed processing
+ * a byte, then read out the received data and write out the next byte
+ * (unless this transfer is finished; in which case go on to the wait
+ * state)
+ */
+static int mpc52xx_spi_fsmstate_transfer(int irq, struct mpc52xx_spi *ms,
+					 u8 status, u8 data)
+{
+	if (!status)
+		return ms->irq0 ? FSM_STOP : FSM_POLL;
+
+	if (status & SPI_STATUS_WCOL) {
+		/* The SPI controller is stoopid.  At slower speeds, it may
+		 * raise the SPIF flag before the state machine is actually
+		 * finished, which causes a collision (internal to the state
+		 * machine only).  The manual recommends inserting a delay
+		 * between receiving the interrupt and sending the next byte,
+		 * but it can also be worked around simply by retrying the
+		 * transfer which is what we do here. */
+		ms->wcol_count++;
+		ms->wcol_ticks += get_tbl() - ms->wcol_tx_timestamp;
+		ms->wcol_tx_timestamp = get_tbl();
+		data = 0;
+		if (ms->tx_buf)
+			data = *(ms->tx_buf-1);
+		out_8(ms->regs + SPI_DATA, data); /* try again */
+		return FSM_CONTINUE;
+	} else if (status & SPI_STATUS_MODF) {
+		ms->modf_count++;
+		dev_err(&ms->master->dev, "mode fault\n");
+		mpc52xx_spi_chipsel(ms, 0);
+		ms->message->status = -EIO;
+		ms->message->complete(ms->message->context);
+		ms->state = mpc52xx_spi_fsmstate_idle;
+		return FSM_CONTINUE;
+	}
+
+	/* Read data out of the spi device */
+	ms->byte_count++;
+	if (ms->rx_buf)
+		*ms->rx_buf++ = data;
+
+	/* Is the transfer complete? */
+	ms->len--;
+	if (ms->len == 0) {
+		ms->timestamp = get_tbl();
+		ms->timestamp += ms->transfer->delay_usecs * tb_ticks_per_usec;
+		ms->state = mpc52xx_spi_fsmstate_wait;
+		return FSM_CONTINUE;
+	}
+
+	/* Write out the next byte */
+	ms->wcol_tx_timestamp = get_tbl();
+	if (ms->tx_buf)
+		out_8(ms->regs + SPI_DATA, *ms->tx_buf++);
+	else
+		out_8(ms->regs + SPI_DATA, 0);
+
+	return FSM_CONTINUE;
+}
+
+/*
+ * WAIT state
+ *
+ * A transfer has completed; need to wait for the delay period to complete
+ * before starting the next transfer
+ */
+static int
+mpc52xx_spi_fsmstate_wait(int irq, struct mpc52xx_spi *ms, u8 status, u8 data)
+{
+	if (status && irq)
+		dev_err(&ms->master->dev, "spurious irq, status=0x%.2x\n",
+			status);
+
+	if (((int)get_tbl()) - ms->timestamp < 0)
+		return FSM_POLL;
+
+	ms->message->actual_length += ms->transfer->len;
+
+	/* Check if there is another transfer in this message.  If there
+	 * aren't then deactivate CS, notify sender, and drop back to idle
+	 * to start the next message. */
+	if (ms->transfer->transfer_list.next == &ms->message->transfers) {
+		ms->msg_count++;
+		mpc52xx_spi_chipsel(ms, 0);
+		ms->message->status = 0;
+		ms->message->complete(ms->message->context);
+		ms->state = mpc52xx_spi_fsmstate_idle;
+		return FSM_CONTINUE;
+	}
+
+	/* There is another transfer; kick it off */
+
+	if (ms->cs_change)
+		mpc52xx_spi_chipsel(ms, 0);
+
+	ms->transfer = container_of(ms->transfer->transfer_list.next,
+				    struct spi_transfer, transfer_list);
+	mpc52xx_spi_start_transfer(ms);
+	ms->state = mpc52xx_spi_fsmstate_transfer;
+	return FSM_CONTINUE;
+}
+
+/**
+ * mpc52xx_spi_fsm_process - Finite State Machine iteration function
+ * @irq: irq number that triggered the FSM or 0 for polling
+ * @ms: pointer to mpc52xx_spi driver data
+ */
+static void mpc52xx_spi_fsm_process(int irq, struct mpc52xx_spi *ms)
+{
+	int rc = FSM_CONTINUE;
+	u8 status, data;
+
+	while (rc == FSM_CONTINUE) {
+		/* Interrupt cleared by read of STATUS followed by
+		 * read of DATA registers */
+		status = in_8(ms->regs + SPI_STATUS);
+		data = in_8(ms->regs + SPI_DATA);
+		rc = ms->state(irq, ms, status, data);
+	}
+
+	if (rc == FSM_POLL)
+		schedule_work(&ms->work);
+}
+
+/**
+ * mpc52xx_spi_irq - IRQ handler
+ */
+static irqreturn_t mpc52xx_spi_irq(int irq, void *_ms)
+{
+	struct mpc52xx_spi *ms = _ms;
+	spin_lock(&ms->lock);
+	mpc52xx_spi_fsm_process(irq, ms);
+	spin_unlock(&ms->lock);
+	return IRQ_HANDLED;
+}
+
+/**
+ * mpc52xx_spi_wq - Workqueue function for polling the state machine
+ */
+static void mpc52xx_spi_wq(struct work_struct *work)
+{
+	struct mpc52xx_spi *ms = container_of(work, struct mpc52xx_spi, work);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ms->lock, flags);
+	mpc52xx_spi_fsm_process(0, ms);
+	spin_unlock_irqrestore(&ms->lock, flags);
+}
+
+/*
+ * spi_master ops
+ */
+
+static int mpc52xx_spi_setup(struct spi_device *spi)
+{
+	if (spi->bits_per_word % 8)
+		return -EINVAL;
+
+	if (spi->mode & ~(SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST))
+		return -EINVAL;
+
+	if (spi->chip_select >= spi->master->num_chipselect)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int mpc52xx_spi_transfer(struct spi_device *spi, struct spi_message *m)
+{
+	struct mpc52xx_spi *ms = spi_master_get_devdata(spi->master);
+	unsigned long flags;
+
+	m->actual_length = 0;
+	m->status = -EINPROGRESS;
+
+	spin_lock_irqsave(&ms->lock, flags);
+	list_add_tail(&m->queue, &ms->queue);
+	spin_unlock_irqrestore(&ms->lock, flags);
+	schedule_work(&ms->work);
+
+	return 0;
+}
+
+/*
+ * OF Platform Bus Binding
+ */
+static int __devinit mpc52xx_spi_probe(struct of_device *op,
+				       const struct of_device_id *match)
+{
+	struct spi_master *master;
+	struct mpc52xx_spi *ms;
+	void __iomem *regs;
+	int rc;
+
+	/* MMIO registers */
+	dev_dbg(&op->dev, "probing mpc5200 SPI device\n");
+	regs = of_iomap(op->node, 0);
+	if (!regs)
+		return -ENODEV;
+
+	/* initialize the device */
+	out_8(regs+SPI_CTRL1, SPI_CTRL1_SPIE | SPI_CTRL1_SPE | SPI_CTRL1_MSTR);
+	out_8(regs + SPI_CTRL2, 0x0);
+	out_8(regs + SPI_DATADIR, 0xe);	/* Set output pins */
+	out_8(regs + SPI_PORTDATA, 0x8);	/* Deassert /SS signal */
+
+	/* Clear the status register and re-read it to check for a MODF
+	 * failure.  This driver cannot currently handle multiple masters
+	 * on the SPI bus.  This fault will also occur if the SPI signals
+	 * are not connected to any pins (port_config setting) */
+	in_8(regs + SPI_STATUS);
+	in_8(regs + SPI_DATA);
+	if (in_8(regs + SPI_STATUS) & SPI_STATUS_MODF) {
+		dev_err(&op->dev, "mode fault; is port_config correct?\n");
+		rc = -EIO;
+		goto err_init;
+	}
+
+	dev_dbg(&op->dev, "allocating spi_master struct\n");
+	master = spi_alloc_master(&op->dev, sizeof *ms);
+	if (!master) {
+		rc = -ENOMEM;
+		goto err_alloc;
+	}
+	master->bus_num = -1;
+	master->num_chipselect = 1;
+	master->setup = mpc52xx_spi_setup;
+	master->transfer = mpc52xx_spi_transfer;
+	dev_set_drvdata(&op->dev, master);
+
+	ms = spi_master_get_devdata(master);
+	ms->master = master;
+	ms->regs = regs;
+	ms->irq0 = irq_of_parse_and_map(op->node, 0);
+	ms->irq1 = irq_of_parse_and_map(op->node, 1);
+	ms->state = mpc52xx_spi_fsmstate_idle;
+	ms->ipb_freq = mpc5xxx_get_bus_frequency(op->node);
+	spin_lock_init(&ms->lock);
+	INIT_LIST_HEAD(&ms->queue);
+	INIT_WORK(&ms->work, mpc52xx_spi_wq);
+
+	/* Decide if interrupts can be used */
+	if (ms->irq0 && ms->irq1) {
+		rc = request_irq(ms->irq0, mpc52xx_spi_irq, IRQF_SAMPLE_RANDOM,
+				  "mpc5200-spi-modf", ms);
+		rc |= request_irq(ms->irq1, mpc52xx_spi_irq, IRQF_SAMPLE_RANDOM,
+				  "mpc5200-spi-spiF", ms);
+		if (rc) {
+			free_irq(ms->irq0, ms);
+			free_irq(ms->irq1, ms);
+			ms->irq0 = ms->irq1 = 0;
+		}
+	} else {
+		/* operate in polled mode */
+		ms->irq0 = ms->irq1 = 0;
+	}
+
+	if (!ms->irq0)
+		dev_info(&op->dev, "using polled mode\n");
+
+	dev_dbg(&op->dev, "registering spi_master struct\n");
+	rc = spi_register_master(master);
+	if (rc)
+		goto err_register;
+
+	of_register_spi_devices(master, op->node);
+	dev_info(&ms->master->dev, "registered MPC5200 SPI bus\n");
+
+	return rc;
+
+ err_register:
+	dev_err(&ms->master->dev, "initialization failed\n");
+	spi_master_put(master);
+ err_alloc:
+ err_init:
+	iounmap(regs);
+	return rc;
+}
+
+static int __devexit mpc52xx_spi_remove(struct of_device *op)
+{
+	struct spi_master *master = dev_get_drvdata(&op->dev);
+	struct mpc52xx_spi *ms = spi_master_get_devdata(master);
+
+	free_irq(ms->irq0, ms);
+	free_irq(ms->irq1, ms);
+
+	spi_unregister_master(master);
+	spi_master_put(master);
+	iounmap(ms->regs);
+
+	return 0;
+}
+
+static struct of_device_id mpc52xx_spi_match[] __devinitdata = {
+	{ .compatible = "fsl,mpc5200-spi", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mpc52xx_spi_match);
+
+static struct of_platform_driver mpc52xx_spi_of_driver = {
+	.owner = THIS_MODULE,
+	.name = "mpc52xx-spi",
+	.match_table = mpc52xx_spi_match,
+	.probe = mpc52xx_spi_probe,
+	.remove = __exit_p(mpc52xx_spi_remove),
+};
+
+static int __init mpc52xx_spi_init(void)
+{
+	return of_register_platform_driver(&mpc52xx_spi_of_driver);
+}
+module_init(mpc52xx_spi_init);
+
+static void __exit mpc52xx_spi_exit(void)
+{
+	of_unregister_platform_driver(&mpc52xx_spi_of_driver);
+}
+module_exit(mpc52xx_spi_exit);
+
diff --git a/include/linux/spi/mpc52xx_spi.h b/include/linux/spi/mpc52xx_spi.h
new file mode 100644
index 000000000000..d1004cf09241
--- /dev/null
+++ b/include/linux/spi/mpc52xx_spi.h
@@ -0,0 +1,10 @@
+
+#ifndef INCLUDE_MPC5200_SPI_H
+#define INCLUDE_MPC5200_SPI_H
+
+extern void mpc52xx_spi_set_premessage_hook(struct spi_master *master,
+					    void (*hook)(struct spi_message *m,
+							 void *context),
+					    void *hook_context);
+
+#endif

From 4f59ecfa9b87da09bdc346f2c443e25fa2c0674c Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@secretlab.ca>
Date: Wed, 4 Nov 2009 16:42:33 -0700
Subject: [PATCH 031/151] powerpc/5200: add general purpose timer API for the
 MPC5200

This patch adds an interface for controlling the timer function of the
MPC5200 GPT devices.

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 arch/powerpc/include/asm/mpc52xx.h        |   7 ++
 arch/powerpc/platforms/52xx/mpc52xx_gpt.c | 133 ++++++++++++++++++++--
 2 files changed, 130 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h
index 1b4f697abbdd..671685011a23 100644
--- a/arch/powerpc/include/asm/mpc52xx.h
+++ b/arch/powerpc/include/asm/mpc52xx.h
@@ -276,6 +276,13 @@ extern int mpc52xx_set_psc_clkdiv(int psc_id, int clkdiv);
 extern unsigned int mpc52xx_get_xtal_freq(struct device_node *node);
 extern void mpc52xx_restart(char *cmd);
 
+/* mpc52xx_gpt.c */
+struct mpc52xx_gpt_priv;
+extern struct mpc52xx_gpt_priv *mpc52xx_gpt_from_irq(int irq);
+extern int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, int period,
+                            int continuous);
+extern void mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt);
+
 /* mpc52xx_pic.c */
 extern void mpc52xx_init_irq(void);
 extern unsigned int mpc52xx_get_irq(void);
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index bfbcd418e690..2c3fa13571ce 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -46,13 +46,17 @@
  * the output mode.  This driver does not change the output mode setting.
  */
 
+#include <linux/device.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/of_gpio.h>
 #include <linux/kernel.h>
+#include <asm/div64.h>
 #include <asm/mpc52xx.h>
 
 MODULE_DESCRIPTION("Freescale MPC52xx gpt driver");
@@ -68,16 +72,21 @@ MODULE_LICENSE("GPL");
  * @irqhost: Pointer to irq_host instance; used when IRQ mode is supported
  */
 struct mpc52xx_gpt_priv {
+	struct list_head list;		/* List of all GPT devices */
 	struct device *dev;
 	struct mpc52xx_gpt __iomem *regs;
 	spinlock_t lock;
 	struct irq_host *irqhost;
+	u32 ipb_freq;
 
 #if defined(CONFIG_GPIOLIB)
 	struct of_gpio_chip of_gc;
 #endif
 };
 
+LIST_HEAD(mpc52xx_gpt_list);
+DEFINE_MUTEX(mpc52xx_gpt_list_mutex);
+
 #define MPC52xx_GPT_MODE_MS_MASK	(0x07)
 #define MPC52xx_GPT_MODE_MS_IC		(0x01)
 #define MPC52xx_GPT_MODE_MS_OC		(0x02)
@@ -88,6 +97,9 @@ struct mpc52xx_gpt_priv {
 #define MPC52xx_GPT_MODE_GPIO_OUT_LOW	(0x20)
 #define MPC52xx_GPT_MODE_GPIO_OUT_HIGH	(0x30)
 
+#define MPC52xx_GPT_MODE_COUNTER_ENABLE	(0x1000)
+#define MPC52xx_GPT_MODE_CONTINUOUS	(0x0400)
+#define MPC52xx_GPT_MODE_OPEN_DRAIN	(0x0200)
 #define MPC52xx_GPT_MODE_IRQ_EN		(0x0100)
 
 #define MPC52xx_GPT_MODE_ICT_MASK	(0x030000)
@@ -190,7 +202,7 @@ static int mpc52xx_gpt_irq_xlate(struct irq_host *h, struct device_node *ct,
 
 	dev_dbg(gpt->dev, "%s: flags=%i\n", __func__, intspec[0]);
 
-	if ((intsize < 1) || (intspec[0] < 1) || (intspec[0] > 3)) {
+	if ((intsize < 1) || (intspec[0] > 3)) {
 		dev_err(gpt->dev, "bad irq specifier in %s\n", ct->full_name);
 		return -EINVAL;
 	}
@@ -211,13 +223,11 @@ mpc52xx_gpt_irq_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node)
 {
 	int cascade_virq;
 	unsigned long flags;
-
-	/* Only setup cascaded IRQ if device tree claims the GPT is
-	 * an interrupt controller */
-	if (!of_find_property(node, "interrupt-controller", NULL))
-		return;
+	u32 mode;
 
 	cascade_virq = irq_of_parse_and_map(node, 0);
+	if (!cascade_virq)
+		return;
 
 	gpt->irqhost = irq_alloc_host(node, IRQ_HOST_MAP_LINEAR, 1,
 				      &mpc52xx_gpt_irq_ops, -1);
@@ -227,14 +237,16 @@ mpc52xx_gpt_irq_setup(struct mpc52xx_gpt_priv *gpt, struct device_node *node)
 	}
 
 	gpt->irqhost->host_data = gpt;
-
 	set_irq_data(cascade_virq, gpt);
 	set_irq_chained_handler(cascade_virq, mpc52xx_gpt_irq_cascade);
 
-	/* Set to Input Capture mode */
+	/* If the GPT is currently disabled, then change it to be in Input
+	 * Capture mode.  If the mode is non-zero, then the pin could be
+	 * already in use for something. */
 	spin_lock_irqsave(&gpt->lock, flags);
-	clrsetbits_be32(&gpt->regs->mode, MPC52xx_GPT_MODE_MS_MASK,
-			MPC52xx_GPT_MODE_MS_IC);
+	mode = in_be32(&gpt->regs->mode);
+	if ((mode & MPC52xx_GPT_MODE_MS_MASK) == 0)
+		out_be32(&gpt->regs->mode, mode | MPC52xx_GPT_MODE_MS_IC);
 	spin_unlock_irqrestore(&gpt->lock, flags);
 
 	dev_dbg(gpt->dev, "%s() complete. virq=%i\n", __func__, cascade_virq);
@@ -335,6 +347,102 @@ static void
 mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *p, struct device_node *np) { }
 #endif /* defined(CONFIG_GPIOLIB) */
 
+/***********************************************************************
+ * Timer API
+ */
+
+/**
+ * mpc52xx_gpt_from_irq - Return the GPT device associated with an IRQ number
+ * @irq: irq of timer.
+ */
+struct mpc52xx_gpt_priv *mpc52xx_gpt_from_irq(int irq)
+{
+	struct mpc52xx_gpt_priv *gpt;
+	struct list_head *pos;
+
+	/* Iterate over the list of timers looking for a matching device */
+	mutex_lock(&mpc52xx_gpt_list_mutex);
+	list_for_each(pos, &mpc52xx_gpt_list) {
+		gpt = container_of(pos, struct mpc52xx_gpt_priv, list);
+		if (gpt->irqhost && irq == irq_linear_revmap(gpt->irqhost, 0)) {
+			mutex_unlock(&mpc52xx_gpt_list_mutex);
+			return gpt;
+		}
+	}
+	mutex_unlock(&mpc52xx_gpt_list_mutex);
+
+	return NULL;
+}
+EXPORT_SYMBOL(mpc52xx_gpt_from_irq);
+
+/**
+ * mpc52xx_gpt_start_timer - Set and enable the GPT timer
+ * @gpt: Pointer to gpt private data structure
+ * @period: period of timer
+ * @continuous: set to 1 to make timer continuous free running
+ *
+ * An interrupt will be generated every time the timer fires
+ */
+int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, int period,
+                            int continuous)
+{
+	u32 clear, set;
+	u64 clocks;
+	u32 prescale;
+	unsigned long flags;
+
+	clear = MPC52xx_GPT_MODE_MS_MASK | MPC52xx_GPT_MODE_CONTINUOUS;
+	set = MPC52xx_GPT_MODE_MS_GPIO | MPC52xx_GPT_MODE_COUNTER_ENABLE;
+	if (continuous)
+		set |= MPC52xx_GPT_MODE_CONTINUOUS;
+
+	/* Determine the number of clocks in the requested period.  64 bit
+	 * arithmatic is done here to preserve the precision until the value
+	 * is scaled back down into the u32 range.  Period is in 'ns', bus
+	 * frequency is in Hz. */
+	clocks = (u64)period * (u64)gpt->ipb_freq;
+	do_div(clocks, 1000000000); /* Scale it down to ns range */
+
+	/* This device cannot handle a clock count greater than 32 bits */
+	if (clocks > 0xffffffff)
+		return -EINVAL;
+
+	/* Calculate the prescaler and count values from the clocks value.
+	 * 'clocks' is the number of clock ticks in the period.  The timer
+	 * has 16 bit precision and a 16 bit prescaler.  Prescaler is
+	 * calculated by integer dividing the clocks by 0x10000 (shifting
+	 * down 16 bits) to obtain the smallest possible divisor for clocks
+	 * to get a 16 bit count value.
+	 *
+	 * Note: the prescale register is '1' based, not '0' based.  ie. a
+	 * value of '1' means divide the clock by one.  0xffff divides the
+	 * clock by 0xffff.  '0x0000' does not divide by zero, but wraps
+	 * around and divides by 0x10000.  That is why prescale must be
+	 * a u32 variable, not a u16, for this calculation. */
+	prescale = (clocks >> 16) + 1;
+	do_div(clocks, prescale);
+	if (clocks > 0xffff) {
+		pr_err("calculation error; prescale:%x clocks:%llx\n",
+		       prescale, clocks);
+		return -EINVAL;
+	}
+
+	/* Set and enable the timer */
+	spin_lock_irqsave(&gpt->lock, flags);
+	out_be32(&gpt->regs->count, prescale << 16 | clocks);
+	clrsetbits_be32(&gpt->regs->mode, clear, set);
+	spin_unlock_irqrestore(&gpt->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(mpc52xx_gpt_start_timer);
+
+void mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt)
+{
+	clrbits32(&gpt->regs->mode, MPC52xx_GPT_MODE_COUNTER_ENABLE);
+}
+EXPORT_SYMBOL(mpc52xx_gpt_stop_timer);
+
 /* ---------------------------------------------------------------------
  * of_platform bus binding code
  */
@@ -349,6 +457,7 @@ static int __devinit mpc52xx_gpt_probe(struct of_device *ofdev,
 
 	spin_lock_init(&gpt->lock);
 	gpt->dev = &ofdev->dev;
+	gpt->ipb_freq = mpc5xxx_get_bus_frequency(ofdev->node);
 	gpt->regs = of_iomap(ofdev->node, 0);
 	if (!gpt->regs) {
 		kfree(gpt);
@@ -360,6 +469,10 @@ static int __devinit mpc52xx_gpt_probe(struct of_device *ofdev,
 	mpc52xx_gpt_gpio_setup(gpt, ofdev->node);
 	mpc52xx_gpt_irq_setup(gpt, ofdev->node);
 
+	mutex_lock(&mpc52xx_gpt_list_mutex);
+	list_add(&gpt->list, &mpc52xx_gpt_list);
+	mutex_unlock(&mpc52xx_gpt_list_mutex);
+
 	return 0;
 }
 

From 3c9059d79f5eea6b8b75ddac97693127c3c41db4 Mon Sep 17 00:00:00 2001
From: John Bonesio <bones@secretlab.ca>
Date: Tue, 29 Sep 2009 10:43:42 +0000
Subject: [PATCH 032/151] powerpc/5200: add LocalPlus bus FIFO device driver

This is a driver for the FIFO device on the LocalPlus bus on an mpc5200 system.
The driver supports programmed I/O through the FIFO as well as setting up DMA
via the BestComm engine through the FIFO.

Signed-off-by: John Bonesio <bones@secretlab.ca>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 arch/powerpc/include/asm/mpc52xx.h            |  39 ++
 arch/powerpc/platforms/52xx/Kconfig           |   5 +
 arch/powerpc/platforms/52xx/Makefile          |   1 +
 arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c | 560 ++++++++++++++++++
 4 files changed, 605 insertions(+)
 create mode 100644 arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c

diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h
index 671685011a23..707ab7590cfb 100644
--- a/arch/powerpc/include/asm/mpc52xx.h
+++ b/arch/powerpc/include/asm/mpc52xx.h
@@ -283,6 +283,45 @@ extern int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, int period,
                             int continuous);
 extern void mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt);
 
+/* mpc52xx_lpbfifo.c */
+#define MPC52XX_LPBFIFO_FLAG_READ		(0)
+#define MPC52XX_LPBFIFO_FLAG_WRITE		(1<<0)
+#define MPC52XX_LPBFIFO_FLAG_NO_INCREMENT	(1<<1)
+#define MPC52XX_LPBFIFO_FLAG_NO_DMA		(1<<2)
+#define MPC52XX_LPBFIFO_FLAG_POLL_DMA		(1<<3)
+
+struct mpc52xx_lpbfifo_request {
+	struct list_head list;
+
+	/* localplus bus address */
+	unsigned int cs;
+	size_t offset;
+
+	/* Memory address */
+	void *data;
+	phys_addr_t data_phys;
+
+	/* Details of transfer */
+	size_t size;
+	size_t pos;	/* current position of transfer */
+	int flags;
+
+	/* What to do when finished */
+	void (*callback)(struct mpc52xx_lpbfifo_request *);
+
+	void *priv;		/* Driver private data */
+
+	/* statistics */
+	int irq_count;
+	int irq_ticks;
+	u8 last_byte;
+	int buffer_not_done_cnt;
+};
+
+extern int mpc52xx_lpbfifo_submit(struct mpc52xx_lpbfifo_request *req);
+extern void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req);
+extern void mpc52xx_lpbfifo_poll(void);
+
 /* mpc52xx_pic.c */
 extern void mpc52xx_init_irq(void);
 extern unsigned int mpc52xx_get_irq(void);
diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig
index 8b8e9560a315..47ea1be1481b 100644
--- a/arch/powerpc/platforms/52xx/Kconfig
+++ b/arch/powerpc/platforms/52xx/Kconfig
@@ -62,3 +62,8 @@ config PPC_MPC5200_GPIO
 	select GENERIC_GPIO
 	help
 	  Enable gpiolib support for mpc5200 based boards
+
+config PPC_MPC5200_LPBFIFO
+	tristate "MPC5200 LocalPlus bus FIFO driver"
+	depends on PPC_MPC52xx
+	select PPC_BESTCOMM_GEN_BD
diff --git a/arch/powerpc/platforms/52xx/Makefile b/arch/powerpc/platforms/52xx/Makefile
index bfd4f52cf3dd..2bc8cd0c5cfc 100644
--- a/arch/powerpc/platforms/52xx/Makefile
+++ b/arch/powerpc/platforms/52xx/Makefile
@@ -15,3 +15,4 @@ ifeq ($(CONFIG_PPC_LITE5200),y)
 endif
 
 obj-$(CONFIG_PPC_MPC5200_GPIO)	+= mpc52xx_gpio.o
+obj-$(CONFIG_PPC_MPC5200_LPBFIFO)	+= mpc52xx_lpbfifo.o
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
new file mode 100644
index 000000000000..929d017535a3
--- /dev/null
+++ b/arch/powerpc/platforms/52xx/mpc52xx_lpbfifo.c
@@ -0,0 +1,560 @@
+/*
+ * LocalPlus Bus FIFO driver for the Freescale MPC52xx.
+ *
+ * Copyright (C) 2009 Secret Lab Technologies Ltd.
+ *
+ * This file is released under the GPLv2
+ *
+ * Todo:
+ * - Add support for multiple requests to be queued.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/spinlock.h>
+#include <asm/io.h>
+#include <asm/prom.h>
+#include <asm/mpc52xx.h>
+#include <asm/time.h>
+
+#include <sysdev/bestcomm/bestcomm.h>
+#include <sysdev/bestcomm/bestcomm_priv.h>
+#include <sysdev/bestcomm/gen_bd.h>
+
+MODULE_AUTHOR("Grant Likely <grant.likely@secretlab.ca>");
+MODULE_DESCRIPTION("MPC5200 LocalPlus FIFO device driver");
+MODULE_LICENSE("GPL");
+
+#define LPBFIFO_REG_PACKET_SIZE		(0x00)
+#define LPBFIFO_REG_START_ADDRESS	(0x04)
+#define LPBFIFO_REG_CONTROL		(0x08)
+#define LPBFIFO_REG_ENABLE		(0x0C)
+#define LPBFIFO_REG_BYTES_DONE_STATUS	(0x14)
+#define LPBFIFO_REG_FIFO_DATA		(0x40)
+#define LPBFIFO_REG_FIFO_STATUS		(0x44)
+#define LPBFIFO_REG_FIFO_CONTROL	(0x48)
+#define LPBFIFO_REG_FIFO_ALARM		(0x4C)
+
+struct mpc52xx_lpbfifo {
+	struct device *dev;
+	phys_addr_t regs_phys;
+	void __iomem *regs;
+	int irq;
+	spinlock_t lock;
+
+	struct bcom_task *bcom_tx_task;
+	struct bcom_task *bcom_rx_task;
+	struct bcom_task *bcom_cur_task;
+
+	/* Current state data */
+	struct mpc52xx_lpbfifo_request *req;
+	int dma_irqs_enabled;
+};
+
+/* The MPC5200 has only one fifo, so only need one instance structure */
+static struct mpc52xx_lpbfifo lpbfifo;
+
+/**
+ * mpc52xx_lpbfifo_kick - Trigger the next block of data to be transfered
+ */
+static void mpc52xx_lpbfifo_kick(struct mpc52xx_lpbfifo_request *req)
+{
+	size_t transfer_size = req->size - req->pos;
+	struct bcom_bd *bd;
+	void __iomem *reg;
+	u32 *data;
+	int i;
+	int bit_fields;
+	int dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA);
+	int write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE;
+	int poll_dma = req->flags & MPC52XX_LPBFIFO_FLAG_POLL_DMA;
+
+	/* Set and clear the reset bits; is good practice in User Manual */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
+
+	/* set master enable bit */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x00000001);
+	if (!dma) {
+		/* While the FIFO can be setup for transfer sizes as large as
+		 * 16M-1, the FIFO itself is only 512 bytes deep and it does
+		 * not generate interrupts for FIFO full events (only transfer
+		 * complete will raise an IRQ).  Therefore when not using
+		 * Bestcomm to drive the FIFO it needs to either be polled, or
+		 * transfers need to constrained to the size of the fifo.
+		 *
+		 * This driver restricts the size of the transfer
+		 */
+		if (transfer_size > 512)
+			transfer_size = 512;
+
+		/* Load the FIFO with data */
+		if (write) {
+			reg = lpbfifo.regs + LPBFIFO_REG_FIFO_DATA;
+			data = req->data + req->pos;
+			for (i = 0; i < transfer_size; i += 4)
+				out_be32(reg, *data++);
+		}
+
+		/* Unmask both error and completion irqs */
+		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x00000301);
+	} else {
+		/* Choose the correct direction
+		 *
+		 * Configure the watermarks so DMA will always complete correctly.
+		 * It may be worth experimenting with the ALARM value to see if
+		 * there is a performance impacit.  However, if it is wrong there
+		 * is a risk of DMA not transferring the last chunk of data
+		 */
+		if (write) {
+			out_be32(lpbfifo.regs + LPBFIFO_REG_FIFO_ALARM, 0x1e4);
+			out_8(lpbfifo.regs + LPBFIFO_REG_FIFO_CONTROL, 7);
+			lpbfifo.bcom_cur_task = lpbfifo.bcom_tx_task;
+		} else {
+			out_be32(lpbfifo.regs + LPBFIFO_REG_FIFO_ALARM, 0x1ff);
+			out_8(lpbfifo.regs + LPBFIFO_REG_FIFO_CONTROL, 0);
+			lpbfifo.bcom_cur_task = lpbfifo.bcom_rx_task;
+
+			if (poll_dma) {
+				if (lpbfifo.dma_irqs_enabled) {
+					disable_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task));
+					lpbfifo.dma_irqs_enabled = 0;
+				}
+			} else {
+				if (!lpbfifo.dma_irqs_enabled) {
+					enable_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task));
+					lpbfifo.dma_irqs_enabled = 1;
+				}
+			}
+		}
+
+		bd = bcom_prepare_next_buffer(lpbfifo.bcom_cur_task);
+		bd->status = transfer_size;
+		if (!write) {
+			/*
+			 * In the DMA read case, the DMA doesn't complete,
+			 * possibly due to incorrect watermarks in the ALARM
+			 * and CONTROL regs. For now instead of trying to
+			 * determine the right watermarks that will make this
+			 * work, just increase the number of bytes the FIFO is
+			 * expecting.
+			 *
+			 * When submitting another operation, the FIFO will get
+			 * reset, so the condition of the FIFO waiting for a
+			 * non-existent 4 bytes will get cleared.
+			 */
+			transfer_size += 4; /* BLECH! */
+		}
+		bd->data[0] = req->data_phys + req->pos;
+		bcom_submit_next_buffer(lpbfifo.bcom_cur_task, NULL);
+
+		/* error irq & master enabled bit */
+		bit_fields = 0x00000201;
+
+		/* Unmask irqs */
+		if (write && (!poll_dma))
+			bit_fields |= 0x00000100; /* completion irq too */
+		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, bit_fields);
+	}
+
+	/* Set transfer size, width, chip select and READ mode */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_START_ADDRESS,
+		 req->offset + req->pos);
+	out_be32(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, transfer_size);
+
+	bit_fields = req->cs << 24 | 0x000008;
+	if (!write)
+		bit_fields |= 0x010000; /* read mode */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_CONTROL, bit_fields);
+
+	/* Kick it off */
+	out_8(lpbfifo.regs + LPBFIFO_REG_PACKET_SIZE, 0x01);
+	if (dma)
+		bcom_enable(lpbfifo.bcom_cur_task);
+}
+
+/**
+ * mpc52xx_lpbfifo_irq - IRQ handler for LPB FIFO
+ *
+ * On transmit, the dma completion irq triggers before the fifo completion
+ * triggers.  Handle the dma completion here instead of the LPB FIFO Bestcomm
+ * task completion irq becuase everyting is not really done until the LPB FIFO
+ * completion irq triggers.
+ *
+ * In other words:
+ * For DMA, on receive, the "Fat Lady" is the bestcom completion irq. on
+ * transmit, the fifo completion irq is the "Fat Lady". The opera (or in this
+ * case the DMA/FIFO operation) is not finished until the "Fat Lady" sings.
+ *
+ * Reasons for entering this routine:
+ * 1) PIO mode rx and tx completion irq
+ * 2) DMA interrupt mode tx completion irq
+ * 3) DMA polled mode tx
+ *
+ * Exit conditions:
+ * 1) Transfer aborted
+ * 2) FIFO complete without DMA; more data to do
+ * 3) FIFO complete without DMA; all data transfered
+ * 4) FIFO complete using DMA
+ *
+ * Condition 1 can occur regardless of whether or not DMA is used.
+ * It requires executing the callback to report the error and exiting
+ * immediately.
+ *
+ * Condition 2 requires programming the FIFO with the next block of data
+ *
+ * Condition 3 requires executing the callback to report completion
+ *
+ * Condition 4 means the same as 3, except that we also retrieve the bcom
+ * buffer so DMA doesn't get clogged up.
+ *
+ * To make things trickier, the spinlock must be dropped before
+ * executing the callback, otherwise we could end up with a deadlock
+ * or nested spinlock condition.  The out path is non-trivial, so
+ * extra fiddling is done to make sure all paths lead to the same
+ * outbound code.
+ */
+static irqreturn_t mpc52xx_lpbfifo_irq(int irq, void *dev_id)
+{
+	struct mpc52xx_lpbfifo_request *req;
+	u32 status = in_8(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS);
+	void __iomem *reg;
+	u32 *data;
+	int count, i;
+	int do_callback = 0;
+	u32 ts;
+	unsigned long flags;
+	int dma, write, poll_dma;
+
+	spin_lock_irqsave(&lpbfifo.lock, flags);
+	ts = get_tbl();
+
+	req = lpbfifo.req;
+	if (!req) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+		pr_err("bogus LPBFIFO IRQ\n");
+		return IRQ_HANDLED;
+	}
+
+	dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA);
+	write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE;
+	poll_dma = req->flags & MPC52XX_LPBFIFO_FLAG_POLL_DMA;
+
+	if (dma && !write) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+		pr_err("bogus LPBFIFO IRQ (dma and not writting)\n");
+		return IRQ_HANDLED;
+	}
+
+	if ((status & 0x01) == 0) {
+		goto out;
+	}
+
+	/* check abort bit */
+	if (status & 0x10) {
+		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
+		do_callback = 1;
+		goto out;
+	}
+
+	/* Read result from hardware */
+	count = in_be32(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS);
+	count &= 0x00ffffff;
+
+	if (!dma && !write) {
+		/* copy the data out of the FIFO */
+		reg = lpbfifo.regs + LPBFIFO_REG_FIFO_DATA;
+		data = req->data + req->pos;
+		for (i = 0; i < count; i += 4)
+			*data++ = in_be32(reg);
+	}
+
+	/* Update transfer position and count */
+	req->pos += count;
+
+	/* Decide what to do next */
+	if (req->size - req->pos)
+		mpc52xx_lpbfifo_kick(req); /* more work to do */
+	else
+		do_callback = 1;
+
+ out:
+	/* Clear the IRQ */
+	out_8(lpbfifo.regs + LPBFIFO_REG_BYTES_DONE_STATUS, 0x01);
+
+	if (dma && (status & 0x11)) {
+		/*
+		 * Count the DMA as complete only when the FIFO completion
+		 * status or abort bits are set.
+		 *
+		 * (status & 0x01) should always be the case except sometimes
+		 * when using polled DMA.
+		 *
+		 * (status & 0x10) {transfer aborted}: This case needs more
+		 * testing.
+		 */
+		bcom_retrieve_buffer(lpbfifo.bcom_cur_task, &status, NULL);
+	}
+	req->last_byte = ((u8 *)req->data)[req->size - 1];
+
+	/* When the do_callback flag is set; it means the transfer is finished
+	 * so set the FIFO as idle */
+	if (do_callback)
+		lpbfifo.req = NULL;
+
+	if (irq != 0) /* don't increment on polled case */
+		req->irq_count++;
+
+	req->irq_ticks += get_tbl() - ts;
+	spin_unlock_irqrestore(&lpbfifo.lock, flags);
+
+	/* Spinlock is released; it is now safe to call the callback */
+	if (do_callback && req->callback)
+		req->callback(req);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * mpc52xx_lpbfifo_bcom_irq - IRQ handler for LPB FIFO Bestcomm task
+ *
+ * Only used when receiving data.
+ */
+static irqreturn_t mpc52xx_lpbfifo_bcom_irq(int irq, void *dev_id)
+{
+	struct mpc52xx_lpbfifo_request *req;
+	unsigned long flags;
+	u32 status;
+	u32 ts;
+
+	spin_lock_irqsave(&lpbfifo.lock, flags);
+	ts = get_tbl();
+
+	req = lpbfifo.req;
+	if (!req || (req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA)) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+		return IRQ_HANDLED;
+	}
+
+	if (irq != 0) /* don't increment on polled case */
+		req->irq_count++;
+
+	if (!bcom_buffer_done(lpbfifo.bcom_cur_task)) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+
+		req->buffer_not_done_cnt++;
+		if ((req->buffer_not_done_cnt % 1000) == 0)
+			pr_err("transfer stalled\n");
+
+		return IRQ_HANDLED;
+	}
+
+	bcom_retrieve_buffer(lpbfifo.bcom_cur_task, &status, NULL);
+
+	req->last_byte = ((u8 *)req->data)[req->size - 1];
+
+	req->pos = status & 0x00ffffff;
+
+	/* Mark the FIFO as idle */
+	lpbfifo.req = NULL;
+
+	/* Release the lock before calling out to the callback. */
+	req->irq_ticks += get_tbl() - ts;
+	spin_unlock_irqrestore(&lpbfifo.lock, flags);
+
+	if (req->callback)
+		req->callback(req);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * mpc52xx_lpbfifo_bcom_poll - Poll for DMA completion
+ */
+void mpc52xx_lpbfifo_poll(void)
+{
+	struct mpc52xx_lpbfifo_request *req = lpbfifo.req;
+	int dma = !(req->flags & MPC52XX_LPBFIFO_FLAG_NO_DMA);
+	int write = req->flags & MPC52XX_LPBFIFO_FLAG_WRITE;
+
+	/*
+	 * For more information, see comments on the "Fat Lady" 
+	 */
+	if (dma && write)
+		mpc52xx_lpbfifo_irq(0, NULL);
+	else 
+		mpc52xx_lpbfifo_bcom_irq(0, NULL);
+}
+EXPORT_SYMBOL(mpc52xx_lpbfifo_poll);
+
+/**
+ * mpc52xx_lpbfifo_submit - Submit an LPB FIFO transfer request.
+ * @req: Pointer to request structure
+ */
+int mpc52xx_lpbfifo_submit(struct mpc52xx_lpbfifo_request *req)
+{
+	unsigned long flags;
+
+	if (!lpbfifo.regs)
+		return -ENODEV;
+
+	spin_lock_irqsave(&lpbfifo.lock, flags);
+
+	/* If the req pointer is already set, then a transfer is in progress */
+	if (lpbfifo.req) {
+		spin_unlock_irqrestore(&lpbfifo.lock, flags);
+		return -EBUSY;
+	}
+
+	/* Setup the transfer */
+	lpbfifo.req = req;
+	req->irq_count = 0;
+	req->irq_ticks = 0;
+	req->buffer_not_done_cnt = 0;
+	req->pos = 0;
+
+	mpc52xx_lpbfifo_kick(req);
+	spin_unlock_irqrestore(&lpbfifo.lock, flags);
+	return 0;
+}
+EXPORT_SYMBOL(mpc52xx_lpbfifo_submit);
+
+void mpc52xx_lpbfifo_abort(struct mpc52xx_lpbfifo_request *req)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&lpbfifo.lock, flags);
+	if (lpbfifo.req == req) {
+		/* Put it into reset and clear the state */
+		bcom_gen_bd_rx_reset(lpbfifo.bcom_rx_task);
+		bcom_gen_bd_tx_reset(lpbfifo.bcom_tx_task);
+		out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
+		lpbfifo.req = NULL;
+	}
+	spin_unlock_irqrestore(&lpbfifo.lock, flags);
+}
+EXPORT_SYMBOL(mpc52xx_lpbfifo_abort);
+
+static int __devinit
+mpc52xx_lpbfifo_probe(struct of_device *op, const struct of_device_id *match)
+{
+	struct resource res;
+	int rc = -ENOMEM;
+
+	if (lpbfifo.dev != NULL)
+		return -ENOSPC;
+
+	lpbfifo.irq = irq_of_parse_and_map(op->node, 0);
+	if (!lpbfifo.irq)
+		return -ENODEV;
+
+	if (of_address_to_resource(op->node, 0, &res))
+		return -ENODEV;
+	lpbfifo.regs_phys = res.start;
+	lpbfifo.regs = of_iomap(op->node, 0);
+	if (!lpbfifo.regs)
+		return -ENOMEM;
+
+	spin_lock_init(&lpbfifo.lock);
+
+	/* Put FIFO into reset */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
+
+	/* Register the interrupt handler */
+	rc = request_irq(lpbfifo.irq, mpc52xx_lpbfifo_irq, 0,
+			 "mpc52xx-lpbfifo", &lpbfifo);
+	if (rc)
+		goto err_irq;
+
+	/* Request the Bestcomm receive (fifo --> memory) task and IRQ */
+	lpbfifo.bcom_rx_task =
+		bcom_gen_bd_rx_init(2, res.start + LPBFIFO_REG_FIFO_DATA,
+				    BCOM_INITIATOR_SCLPC, BCOM_IPR_SCLPC,
+				    16*1024*1024);
+	if (!lpbfifo.bcom_rx_task)
+		goto err_bcom_rx;
+
+	rc = request_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task),
+			 mpc52xx_lpbfifo_bcom_irq, 0,
+			 "mpc52xx-lpbfifo-rx", &lpbfifo);
+	if (rc)
+		goto err_bcom_rx_irq;
+
+	/* Request the Bestcomm transmit (memory --> fifo) task and IRQ */
+	lpbfifo.bcom_tx_task =
+		bcom_gen_bd_tx_init(2, res.start + LPBFIFO_REG_FIFO_DATA,
+				    BCOM_INITIATOR_SCLPC, BCOM_IPR_SCLPC);
+	if (!lpbfifo.bcom_tx_task)
+		goto err_bcom_tx;
+
+	lpbfifo.dev = &op->dev;
+	return 0;
+
+ err_bcom_tx:
+	free_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task), &lpbfifo);
+ err_bcom_rx_irq:
+	bcom_gen_bd_rx_release(lpbfifo.bcom_rx_task);
+ err_bcom_rx:
+ err_irq:
+	iounmap(lpbfifo.regs);
+	lpbfifo.regs = NULL;
+
+	dev_err(&op->dev, "mpc52xx_lpbfifo_probe() failed\n");
+	return -ENODEV;
+}
+
+
+static int __devexit mpc52xx_lpbfifo_remove(struct of_device *op)
+{
+	if (lpbfifo.dev != &op->dev)
+		return 0;
+
+	/* Put FIFO in reset */
+	out_be32(lpbfifo.regs + LPBFIFO_REG_ENABLE, 0x01010000);
+
+	/* Release the bestcomm transmit task */
+	free_irq(bcom_get_task_irq(lpbfifo.bcom_tx_task), &lpbfifo);
+	bcom_gen_bd_tx_release(lpbfifo.bcom_tx_task);
+	
+	/* Release the bestcomm receive task */
+	free_irq(bcom_get_task_irq(lpbfifo.bcom_rx_task), &lpbfifo);
+	bcom_gen_bd_rx_release(lpbfifo.bcom_rx_task);
+
+	free_irq(lpbfifo.irq, &lpbfifo);
+	iounmap(lpbfifo.regs);
+	lpbfifo.regs = NULL;
+	lpbfifo.dev = NULL;
+
+	return 0;
+}
+
+static struct of_device_id mpc52xx_lpbfifo_match[] __devinitconst = {
+	{ .compatible = "fsl,mpc5200-lpbfifo", },
+	{},
+};
+
+static struct of_platform_driver mpc52xx_lpbfifo_driver = {
+	.owner = THIS_MODULE,
+	.name = "mpc52xx-lpbfifo",
+	.match_table = mpc52xx_lpbfifo_match,
+	.probe = mpc52xx_lpbfifo_probe,
+	.remove = __devexit_p(mpc52xx_lpbfifo_remove),
+};
+
+/***********************************************************************
+ * Module init/exit
+ */
+static int __init mpc52xx_lpbfifo_init(void)
+{
+	pr_debug("Registering LocalPlus bus FIFO driver\n");
+	return of_register_platform_driver(&mpc52xx_lpbfifo_driver);
+}
+module_init(mpc52xx_lpbfifo_init);
+
+static void __exit mpc52xx_lpbfifo_exit(void)
+{
+	pr_debug("Unregistering LocalPlus bus FIFO driver\n");
+	of_unregister_platform_driver(&mpc52xx_lpbfifo_driver);
+}
+module_exit(mpc52xx_lpbfifo_exit);

From f856cf01787354fb3c8cde0a80de606f368b21ed Mon Sep 17 00:00:00 2001
From: Wolfram Sang <w.sang@pengutronix.de>
Date: Mon, 2 Nov 2009 03:53:11 +0000
Subject: [PATCH 033/151] spi/mpc52xx-psc-spi: check for valid PSC

This driver calls mpc52xx_set_psc_clkdiv() but doesn't check its return value
to see if the PSC is actually valid for SPI use. Add the check and a hint for
the user.

Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 drivers/spi/mpc52xx_psc_spi.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/spi/mpc52xx_psc_spi.c b/drivers/spi/mpc52xx_psc_spi.c
index a14e9fdc0065..2193d908cad6 100644
--- a/drivers/spi/mpc52xx_psc_spi.c
+++ b/drivers/spi/mpc52xx_psc_spi.c
@@ -314,11 +314,13 @@ static int mpc52xx_psc_spi_port_config(int psc_id, struct mpc52xx_psc_spi *mps)
 	struct mpc52xx_psc __iomem *psc = mps->psc;
 	struct mpc52xx_psc_fifo __iomem *fifo = mps->fifo;
 	u32 mclken_div;
-	int ret = 0;
+	int ret;
 
 	/* default sysclk is 512MHz */
 	mclken_div = (mps->sysclk ? mps->sysclk : 512000000) / MCLK;
-	mpc52xx_set_psc_clkdiv(psc_id, mclken_div);
+	ret = mpc52xx_set_psc_clkdiv(psc_id, mclken_div);
+	if (ret)
+		return ret;
 
 	/* Reset the PSC into a known state */
 	out_8(&psc->command, MPC52xx_PSC_RST_RX);
@@ -342,7 +344,7 @@ static int mpc52xx_psc_spi_port_config(int psc_id, struct mpc52xx_psc_spi *mps)
 
 	mps->bits_per_word = 8;
 
-	return ret;
+	return 0;
 }
 
 static irqreturn_t mpc52xx_psc_spi_isr(int irq, void *dev_id)
@@ -411,8 +413,10 @@ static int __init mpc52xx_psc_spi_do_probe(struct device *dev, u32 regaddr,
 		goto free_master;
 
 	ret = mpc52xx_psc_spi_port_config(master->bus_num, mps);
-	if (ret < 0)
+	if (ret < 0) {
+		dev_err(dev, "can't configure PSC! Is it capable of SPI?\n");
 		goto free_irq;
+	}
 
 	spin_lock_init(&mps->lock);
 	init_completion(&mps->done);

From 1a8d3b777dd71813b87c66c0eb161cc87f042126 Mon Sep 17 00:00:00 2001
From: John Linn <john.linn@xilinx.com>
Date: Mon, 14 Sep 2009 08:17:05 +0000
Subject: [PATCH 034/151] Xilinx: SPI: Fix bits_per_word for transfers

The bits_per_word value can be set for each transfer, or can
be set to zero in each transfer in which case it should default
to the value in the driver.

The driver was fixed to properly check the bits_per_word in
the transfer that is passed in.

Signed-off-by: John Linn <john.linn@xilinx.com>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 drivers/spi/xilinx_spi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/xilinx_spi.c b/drivers/spi/xilinx_spi.c
index 46b8c5c2f45e..5a143b9f6361 100644
--- a/drivers/spi/xilinx_spi.c
+++ b/drivers/spi/xilinx_spi.c
@@ -148,7 +148,8 @@ static int xilinx_spi_setup_transfer(struct spi_device *spi,
 {
 	u8 bits_per_word;
 
-	bits_per_word = (t) ? t->bits_per_word : spi->bits_per_word;
+	bits_per_word = (t && t->bits_per_word)
+			 ? t->bits_per_word : spi->bits_per_word;
 	if (bits_per_word != 8) {
 		dev_err(&spi->dev, "%s, unsupported bits_per_word=%d\n",
 			__func__, bits_per_word);

From 5cc17d7e01abd77eda1267a75748cfc84c92a523 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <w.sang@pengutronix.de>
Date: Tue, 3 Nov 2009 23:49:20 +0000
Subject: [PATCH 035/151] spi/mpc52xx: replace printk with dev_err

To easily identify which device has problems.

Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 drivers/spi/mpc52xx_psc_spi.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/spi/mpc52xx_psc_spi.c b/drivers/spi/mpc52xx_psc_spi.c
index 2193d908cad6..f50c81df336a 100644
--- a/drivers/spi/mpc52xx_psc_spi.c
+++ b/drivers/spi/mpc52xx_psc_spi.c
@@ -473,7 +473,7 @@ static int __init mpc52xx_psc_spi_of_probe(struct of_device *op,
 
 	regaddr_p = of_get_address(op->node, 0, &size64, NULL);
 	if (!regaddr_p) {
-		printk(KERN_ERR "Invalid PSC address\n");
+		dev_err(&op->dev, "Invalid PSC address\n");
 		return -EINVAL;
 	}
 	regaddr64 = of_translate_address(op->node, regaddr_p);
@@ -484,8 +484,7 @@ static int __init mpc52xx_psc_spi_of_probe(struct of_device *op,
 
 		psc_nump = of_get_property(op->node, "cell-index", NULL);
 		if (!psc_nump || *psc_nump > 5) {
-			printk(KERN_ERR "mpc52xx_psc_spi: Device node %s has invalid "
-					"cell-index property\n", op->node->full_name);
+			dev_err(&op->dev, "Invalid cell-index property\n");
 			return -EINVAL;
 		}
 		id = *psc_nump + 1;

From a22c65f81ae28656b80d2acc687cf6318eb15bba Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Albrecht=20Dre=C3=9F?= <albrecht.dress@arcor.de>
Date: Wed, 4 Nov 2009 16:43:12 -0700
Subject: [PATCH 036/151] powerpc: tiny memcpy_(to|from)io optimisation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This trivial patch changes memcpy_(to|from)io as to transfer as many
32-bit words as possible in 32-bit accesses (in the current solution,
the last 32-bit word was transferred as 4 byte accesses).

Signed-off-by: Albrecht Dreß <albrecht.dress@arcor.de>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 arch/powerpc/kernel/io.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/kernel/io.c b/arch/powerpc/kernel/io.c
index 1882bf419fa6..8dc7547c2377 100644
--- a/arch/powerpc/kernel/io.c
+++ b/arch/powerpc/kernel/io.c
@@ -161,7 +161,7 @@ void _memcpy_fromio(void *dest, const volatile void __iomem *src,
 		dest++;
 		n--;
 	}
-	while(n > 4) {
+	while(n >= 4) {
 		*((u32 *)dest) = *((volatile u32 *)vsrc);
 		eieio();
 		vsrc += 4;
@@ -190,7 +190,7 @@ void _memcpy_toio(volatile void __iomem *dest, const void *src, unsigned long n)
 		vdest++;
 		n--;
 	}
-	while(n > 4) {
+	while(n >= 4) {
 		*((volatile u32 *)vdest) = *((volatile u32 *)src);
 		src += 4;
 		vdest += 4;

From 02d9e58e464b8aeed9a9cba951c3ae3c6bd06e30 Mon Sep 17 00:00:00 2001
From: Grant Likely <grant.likely@secretlab.ca>
Date: Wed, 4 Nov 2009 22:43:35 -0700
Subject: [PATCH 037/151] mmc: fix missing module license declaration in
 of_mmc_spi.c

Driver cannot be used as a module without this patch.

Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 drivers/mmc/host/of_mmc_spi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/mmc/host/of_mmc_spi.c b/drivers/mmc/host/of_mmc_spi.c
index 0c44d560bf1a..0c7a63c1f12f 100644
--- a/drivers/mmc/host/of_mmc_spi.c
+++ b/drivers/mmc/host/of_mmc_spi.c
@@ -22,6 +22,8 @@
 #include <linux/mmc/core.h>
 #include <linux/mmc/host.h>
 
+MODULE_LICENSE("GPL");
+
 enum {
 	CD_GPIO = 0,
 	WP_GPIO,

From 4e755758cbbeb0afe44556c1ce52ea6f590ed5bf Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:01 +0000
Subject: [PATCH 038/151] Move dirty logging code to sub-arch

PowerPC code handles dirty logging in the generic parts atm. While this
is great for "return -ENOTSUPP", we need to be rather target specific
when actually implementing it.

So let's split it to implementation specific code, so we can implement
it for book3s.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/booke.c   | 5 +++++
 arch/powerpc/kvm/powerpc.c | 5 -----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index e7bf4d029484..06f5a9ecc42c 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -520,6 +520,11 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 	return kvmppc_core_vcpu_translate(vcpu, tr);
 }
 
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
+{
+	return -ENOTSUPP;
+}
+
 int __init kvmppc_booke_init(void)
 {
 	unsigned long ivor[16];
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 2a4551f78f60..a06ecc3401fd 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -409,11 +409,6 @@ out:
 	return r;
 }
 
-int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
-{
-	return -ENOTSUPP;
-}
-
 long kvm_arch_vm_ioctl(struct file *filp,
                        unsigned int ioctl, unsigned long arg)
 {

From ec3c11aa5f9d0a7f48f46d6790c33ccc654fd6ec Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:02 +0000
Subject: [PATCH 039/151] Pass PVR in sregs

Right now sregs is unused on PPC, so we can use it for initialization
of the CPU.

KVM on BookE always virtualizes the host CPU. On Book3s we go a step further
and take the PVR from userspace that tells us what kind of CPU we are supposed
to virtualize, because we support Book3s_32 and Book3s_64 guests.

In order to get that information, we use the sregs ioctl, because we don't
want to reset the guest CPU on every normal register set.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/kvm.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index bb2de6aa5ce0..c9ca97f43bc1 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -46,6 +46,8 @@ struct kvm_regs {
 };
 
 struct kvm_sregs {
+	__u32 pvr;
+	char pad[1020];
 };
 
 struct kvm_fpu {

From 83cd259d8e5b9878be0535f7ddd326676172279a Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:03 +0000
Subject: [PATCH 040/151] Add Book3s definitions

We need quite a bunch of new constants for KVM on Book3s,
so let's define them now.

These constants will be used in later patches.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/kvm_asm.h | 39 ++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 56bfae59837f..19ddb352fd0f 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -49,6 +49,45 @@
 #define BOOKE_INTERRUPT_SPE_FP_ROUND 34
 #define BOOKE_INTERRUPT_PERFORMANCE_MONITOR 35
 
+/* book3s */
+
+#define BOOK3S_INTERRUPT_SYSTEM_RESET	0x100
+#define BOOK3S_INTERRUPT_MACHINE_CHECK	0x200
+#define BOOK3S_INTERRUPT_DATA_STORAGE	0x300
+#define BOOK3S_INTERRUPT_DATA_SEGMENT	0x380
+#define BOOK3S_INTERRUPT_INST_STORAGE	0x400
+#define BOOK3S_INTERRUPT_INST_SEGMENT	0x480
+#define BOOK3S_INTERRUPT_EXTERNAL	0x500
+#define BOOK3S_INTERRUPT_ALIGNMENT	0x600
+#define BOOK3S_INTERRUPT_PROGRAM	0x700
+#define BOOK3S_INTERRUPT_FP_UNAVAIL	0x800
+#define BOOK3S_INTERRUPT_DECREMENTER	0x900
+#define BOOK3S_INTERRUPT_SYSCALL	0xc00
+#define BOOK3S_INTERRUPT_TRACE		0xd00
+#define BOOK3S_INTERRUPT_PERFMON	0xf00
+#define BOOK3S_INTERRUPT_ALTIVEC	0xf20
+#define BOOK3S_INTERRUPT_VSX		0xf40
+
+#define BOOK3S_IRQPRIO_SYSTEM_RESET		0
+#define BOOK3S_IRQPRIO_DATA_SEGMENT		1
+#define BOOK3S_IRQPRIO_INST_SEGMENT		2
+#define BOOK3S_IRQPRIO_DATA_STORAGE		3
+#define BOOK3S_IRQPRIO_INST_STORAGE		4
+#define BOOK3S_IRQPRIO_ALIGNMENT		5
+#define BOOK3S_IRQPRIO_PROGRAM			6
+#define BOOK3S_IRQPRIO_FP_UNAVAIL		7
+#define BOOK3S_IRQPRIO_ALTIVEC			8
+#define BOOK3S_IRQPRIO_VSX			9
+#define BOOK3S_IRQPRIO_SYSCALL			10
+#define BOOK3S_IRQPRIO_MACHINE_CHECK		11
+#define BOOK3S_IRQPRIO_DEBUG			12
+#define BOOK3S_IRQPRIO_EXTERNAL			13
+#define BOOK3S_IRQPRIO_DECREMENTER		14
+#define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR	15
+#define BOOK3S_IRQPRIO_MAX			16
+
+#define BOOK3S_HFLAG_DCBZ32			0x1
+
 #define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */
 

From ca95150b3a9f3f3146a686296f2156a7ec6e98e9 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:04 +0000
Subject: [PATCH 041/151] Add Book3s fields to vcpu structs

We need to store more information than we currently have for vcpus
when running on Book3s.

So let's extend the internal struct definitions.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/kvm_host.h | 73 ++++++++++++++++++++++++++++-
 1 file changed, 72 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index c9c930ed11d7..2cff5fe0cbe6 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -37,6 +37,8 @@
 #define KVM_NR_PAGE_SIZES	1
 #define KVM_PAGES_PER_HPAGE(x)	(1UL<<31)
 
+#define HPTEG_CACHE_NUM 1024
+
 struct kvm;
 struct kvm_run;
 struct kvm_vcpu;
@@ -63,6 +65,17 @@ struct kvm_vcpu_stat {
 	u32 dec_exits;
 	u32 ext_intr_exits;
 	u32 halt_wakeup;
+#ifdef CONFIG_PPC64
+	u32 pf_storage;
+	u32 pf_instruc;
+	u32 sp_storage;
+	u32 sp_instruc;
+	u32 queue_intr;
+	u32 ld;
+	u32 ld_slow;
+	u32 st;
+	u32 st_slow;
+#endif
 };
 
 enum kvm_exit_types {
@@ -109,9 +122,53 @@ struct kvmppc_exit_timing {
 struct kvm_arch {
 };
 
+struct kvmppc_pte {
+	u64 eaddr;
+	u64 vpage;
+	u64 raddr;
+	bool may_read;
+	bool may_write;
+	bool may_execute;
+};
+
+struct kvmppc_mmu {
+	/* book3s_64 only */
+	void (*slbmte)(struct kvm_vcpu *vcpu, u64 rb, u64 rs);
+	u64  (*slbmfee)(struct kvm_vcpu *vcpu, u64 slb_nr);
+	u64  (*slbmfev)(struct kvm_vcpu *vcpu, u64 slb_nr);
+	void (*slbie)(struct kvm_vcpu *vcpu, u64 slb_nr);
+	void (*slbia)(struct kvm_vcpu *vcpu);
+	/* book3s */
+	void (*mtsrin)(struct kvm_vcpu *vcpu, u32 srnum, ulong value);
+	u32  (*mfsrin)(struct kvm_vcpu *vcpu, u32 srnum);
+	int  (*xlate)(struct kvm_vcpu *vcpu, gva_t eaddr, struct kvmppc_pte *pte, bool data);
+	void (*reset_msr)(struct kvm_vcpu *vcpu);
+	void (*tlbie)(struct kvm_vcpu *vcpu, ulong addr, bool large);
+	int  (*esid_to_vsid)(struct kvm_vcpu *vcpu, u64 esid, u64 *vsid);
+	u64  (*ea_to_vp)(struct kvm_vcpu *vcpu, gva_t eaddr, bool data);
+	bool (*is_dcbz32)(struct kvm_vcpu *vcpu);
+};
+
+struct hpte_cache {
+	u64 host_va;
+	u64 pfn;
+	ulong slot;
+	struct kvmppc_pte pte;
+};
+
 struct kvm_vcpu_arch {
-	u32 host_stack;
+	ulong host_stack;
 	u32 host_pid;
+#ifdef CONFIG_PPC64
+	ulong host_msr;
+	ulong host_r2;
+	void *host_retip;
+	ulong trampoline_lowmem;
+	ulong trampoline_enter;
+	ulong highmem_handler;
+	ulong host_paca_phys;
+	struct kvmppc_mmu mmu;
+#endif
 
 	u64 fpr[32];
 	ulong gpr[32];
@@ -123,6 +180,10 @@ struct kvm_vcpu_arch {
 	ulong xer;
 
 	ulong msr;
+#ifdef CONFIG_PPC64
+	ulong shadow_msr;
+	ulong hflags;
+#endif
 	u32 mmucr;
 	ulong sprg0;
 	ulong sprg1;
@@ -149,6 +210,7 @@ struct kvm_vcpu_arch {
 	u32 ivor[64];
 	ulong ivpr;
 	u32 pir;
+	u32 pvr;
 
 	u32 shadow_pid;
 	u32 pid;
@@ -174,6 +236,9 @@ struct kvm_vcpu_arch {
 #endif
 
 	u32 last_inst;
+#ifdef CONFIG_PPC64
+	ulong fault_dsisr;
+#endif
 	ulong fault_dear;
 	ulong fault_esr;
 	gpa_t paddr_accessed;
@@ -186,7 +251,13 @@ struct kvm_vcpu_arch {
 	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
 
 	struct timer_list dec_timer;
+	u64 dec_jiffies;
 	unsigned long pending_exceptions;
+
+#ifdef CONFIG_PPC64
+	struct hpte_cache hpte_cache[HPTEG_CACHE_NUM];
+	int hpte_cache_offset;
+#endif
 };
 
 #endif /* __POWERPC_KVM_HOST_H__ */

From 4e342025e625a7271be0a9e2d20b7caf1ab70e8a Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:05 +0000
Subject: [PATCH 042/151] Add asm/kvm_book3s.h

This adds the book3s specific header file that contains structs that
are only valid on book3s specific code.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/kvm_book3s.h | 136 ++++++++++++++++++++++++++
 1 file changed, 136 insertions(+)
 create mode 100644 arch/powerpc/include/asm/kvm_book3s.h

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
new file mode 100644
index 000000000000..c6011336371e
--- /dev/null
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -0,0 +1,136 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#ifndef __ASM_KVM_BOOK3S_H__
+#define __ASM_KVM_BOOK3S_H__
+
+#include <linux/types.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_ppc.h>
+
+struct kvmppc_slb {
+	u64 esid;
+	u64 vsid;
+	u64 orige;
+	u64 origv;
+	bool valid;
+	bool Ks;
+	bool Kp;
+	bool nx;
+	bool large;
+	bool class;
+};
+
+struct kvmppc_sr {
+	u32 raw;
+	u32 vsid;
+	bool Ks;
+	bool Kp;
+	bool nx;
+};
+
+struct kvmppc_bat {
+	u32 bepi;
+	u32 bepi_mask;
+	bool vs;
+	bool vp;
+	u32 brpn;
+	u8 wimg;
+	u8 pp;
+};
+
+struct kvmppc_sid_map {
+	u64 guest_vsid;
+	u64 guest_esid;
+	u64 host_vsid;
+	bool valid;
+};
+
+#define SID_MAP_BITS    9
+#define SID_MAP_NUM     (1 << SID_MAP_BITS)
+#define SID_MAP_MASK    (SID_MAP_NUM - 1)
+
+struct kvmppc_vcpu_book3s {
+	struct kvm_vcpu vcpu;
+	struct kvmppc_sid_map sid_map[SID_MAP_NUM];
+	struct kvmppc_slb slb[64];
+	struct {
+		u64 esid;
+		u64 vsid;
+	} slb_shadow[64];
+	u8 slb_shadow_max;
+	struct kvmppc_sr sr[16];
+	struct kvmppc_bat ibat[8];
+	struct kvmppc_bat dbat[8];
+	u64 hid[6];
+	int slb_nr;
+	u64 sdr1;
+	u64 dsisr;
+	u64 hior;
+	u64 msr_mask;
+	u64 vsid_first;
+	u64 vsid_next;
+	u64 vsid_max;
+	int context_id;
+};
+
+#define CONTEXT_HOST		0
+#define CONTEXT_GUEST		1
+#define CONTEXT_GUEST_END	2
+
+#define VSID_REAL	0xfffffffffff00000
+#define VSID_REAL_DR	0xffffffffffe00000
+#define VSID_REAL_IR	0xffffffffffd00000
+#define VSID_BAT	0xffffffffffc00000
+#define VSID_PR		0x8000000000000000
+
+extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, u64 ea, u64 ea_mask);
+extern void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 vp, u64 vp_mask);
+extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, u64 pa_start, u64 pa_end);
+extern void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 new_msr);
+extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu);
+extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu);
+extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
+extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr);
+extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu);
+extern struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, bool data);
+extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr, bool data);
+extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr);
+extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec);
+
+extern u32 kvmppc_trampoline_lowmem;
+extern u32 kvmppc_trampoline_enter;
+
+static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
+{
+	return container_of(vcpu, struct kvmppc_vcpu_book3s, vcpu);
+}
+
+static inline ulong dsisr(void)
+{
+	ulong r;
+	asm ( "mfdsisr %0 " : "=r" (r) );
+	return r;
+}
+
+extern void kvm_return_point(void);
+
+#define INS_DCBZ			0x7c0007ec
+
+#endif /* __ASM_KVM_BOOK3S_H__ */

From 3cea8c435d0b142eb2b3dd2c411a24aa1b32bfe4 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:06 +0000
Subject: [PATCH 043/151] Add Book3s_64 intercept helpers

We need to intercept interrupt vectors. To do that, let's add a file
we can always include which only activates the intercepts when we have
then configured.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/kvm_book3s_64_asm.h | 58 ++++++++++++++++++++
 1 file changed, 58 insertions(+)
 create mode 100644 arch/powerpc/include/asm/kvm_book3s_64_asm.h

diff --git a/arch/powerpc/include/asm/kvm_book3s_64_asm.h b/arch/powerpc/include/asm/kvm_book3s_64_asm.h
new file mode 100644
index 000000000000..2e06ee8184ef
--- /dev/null
+++ b/arch/powerpc/include/asm/kvm_book3s_64_asm.h
@@ -0,0 +1,58 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#ifndef __ASM_KVM_BOOK3S_ASM_H__
+#define __ASM_KVM_BOOK3S_ASM_H__
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+
+#include <asm/kvm_asm.h>
+
+.macro DO_KVM intno
+	.if (\intno == BOOK3S_INTERRUPT_SYSTEM_RESET) || \
+	    (\intno == BOOK3S_INTERRUPT_MACHINE_CHECK) || \
+	    (\intno == BOOK3S_INTERRUPT_DATA_STORAGE) || \
+	    (\intno == BOOK3S_INTERRUPT_INST_STORAGE) || \
+	    (\intno == BOOK3S_INTERRUPT_DATA_SEGMENT) || \
+	    (\intno == BOOK3S_INTERRUPT_INST_SEGMENT) || \
+	    (\intno == BOOK3S_INTERRUPT_EXTERNAL) || \
+	    (\intno == BOOK3S_INTERRUPT_ALIGNMENT) || \
+	    (\intno == BOOK3S_INTERRUPT_PROGRAM) || \
+	    (\intno == BOOK3S_INTERRUPT_FP_UNAVAIL) || \
+	    (\intno == BOOK3S_INTERRUPT_DECREMENTER) || \
+	    (\intno == BOOK3S_INTERRUPT_SYSCALL) || \
+	    (\intno == BOOK3S_INTERRUPT_TRACE) || \
+	    (\intno == BOOK3S_INTERRUPT_PERFMON) || \
+	    (\intno == BOOK3S_INTERRUPT_ALTIVEC) || \
+	    (\intno == BOOK3S_INTERRUPT_VSX)
+
+	b	kvmppc_trampoline_\intno
+kvmppc_resume_\intno:
+
+	.endif
+.endm
+
+#else
+
+.macro DO_KVM intno
+.endm
+
+#endif /* CONFIG_KVM_BOOK3S_64_HANDLER */
+
+#endif /* __ASM_KVM_BOOK3S_ASM_H__ */

From 29eb61bca1e82dc59e4d9c575e6f21ce7a36d61d Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:07 +0000
Subject: [PATCH 044/151] Add book3s_64 highmem asm code

This is the of entry / exit code. In order to switch between host and guest
context, we need to switch register state and call the exit code handler on
exit.

This assembly file does exactly that. To finally enter the guest it calls
into book3s_64_slb.S. On exit it gets jumped at from book3s_64_slb.S too.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/kvm_ppc.h      |   1 +
 arch/powerpc/kvm/book3s_64_interrupts.S | 392 ++++++++++++++++++++++++
 2 files changed, 393 insertions(+)
 create mode 100644 arch/powerpc/kvm/book3s_64_interrupts.S

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 2c6ee349df5e..269ee46ab028 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -39,6 +39,7 @@ enum emulation_result {
 extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
 extern char kvmppc_handlers_start[];
 extern unsigned long kvmppc_handler_len;
+extern void kvmppc_handler_highmem(void);
 
 extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu);
 extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_64_interrupts.S
new file mode 100644
index 000000000000..7b55d8094c8b
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_interrupts.S
@@ -0,0 +1,392 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/asm-offsets.h>
+#include <asm/exception-64s.h>
+
+#define KVMPPC_HANDLE_EXIT .kvmppc_handle_exit
+#define ULONG_SIZE 8
+#define VCPU_GPR(n)     (VCPU_GPRS + (n * ULONG_SIZE))
+
+.macro mfpaca tmp_reg, src_reg, offset, vcpu_reg
+	ld	\tmp_reg, (PACA_EXMC+\offset)(r13)
+	std	\tmp_reg, VCPU_GPR(\src_reg)(\vcpu_reg)
+.endm
+
+.macro DISABLE_INTERRUPTS
+       mfmsr   r0
+       rldicl  r0,r0,48,1
+       rotldi  r0,r0,16
+       mtmsrd  r0,1
+.endm
+
+/*****************************************************************************
+ *                                                                           *
+ *     Guest entry / exit code that is in kernel module memory (highmem)     *
+ *                                                                           *
+ ****************************************************************************/
+
+/* Registers:
+ *  r3: kvm_run pointer
+ *  r4: vcpu pointer
+ */
+_GLOBAL(__kvmppc_vcpu_entry)
+
+kvm_start_entry:
+	/* Write correct stack frame */
+	mflr    r0
+	std     r0,16(r1)
+
+	/* Save host state to the stack */
+	stdu	r1, -SWITCH_FRAME_SIZE(r1)
+
+	/* Save r3 (kvm_run) and r4 (vcpu) */
+	SAVE_2GPRS(3, r1)
+
+	/* Save non-volatile registers (r14 - r31) */
+	SAVE_NVGPRS(r1)
+
+	/* Save LR */
+	mflr	r14
+	std	r14, _LINK(r1)
+
+/* XXX optimize non-volatile loading away */
+kvm_start_lightweight:
+
+	DISABLE_INTERRUPTS
+
+	/* Save R1/R2 in the PACA */
+	std	r1, PACAR1(r13)
+	std	r2, (PACA_EXMC+EX_SRR0)(r13)
+	ld	r3, VCPU_HIGHMEM_HANDLER(r4)
+	std	r3, PACASAVEDMSR(r13)
+
+	/* Load non-volatile guest state from the vcpu */
+	ld	r14, VCPU_GPR(r14)(r4)
+	ld	r15, VCPU_GPR(r15)(r4)
+	ld	r16, VCPU_GPR(r16)(r4)
+	ld	r17, VCPU_GPR(r17)(r4)
+	ld	r18, VCPU_GPR(r18)(r4)
+	ld	r19, VCPU_GPR(r19)(r4)
+	ld	r20, VCPU_GPR(r20)(r4)
+	ld	r21, VCPU_GPR(r21)(r4)
+	ld	r22, VCPU_GPR(r22)(r4)
+	ld	r23, VCPU_GPR(r23)(r4)
+	ld	r24, VCPU_GPR(r24)(r4)
+	ld	r25, VCPU_GPR(r25)(r4)
+	ld	r26, VCPU_GPR(r26)(r4)
+	ld	r27, VCPU_GPR(r27)(r4)
+	ld	r28, VCPU_GPR(r28)(r4)
+	ld	r29, VCPU_GPR(r29)(r4)
+	ld	r30, VCPU_GPR(r30)(r4)
+	ld	r31, VCPU_GPR(r31)(r4)
+
+	ld	r9, VCPU_PC(r4)			/* r9 = vcpu->arch.pc */
+	ld	r10, VCPU_SHADOW_MSR(r4)	/* r10 = vcpu->arch.shadow_msr */
+
+	ld	r3, VCPU_TRAMPOLINE_ENTER(r4)
+	mtsrr0	r3
+
+	LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR))
+	mtsrr1	r3
+
+	/* Load guest state in the respective registers */
+	lwz	r3, VCPU_CR(r4)		/* r3 = vcpu->arch.cr */
+	stw	r3, (PACA_EXMC + EX_CCR)(r13)
+
+	ld	r3, VCPU_CTR(r4)	/* r3 = vcpu->arch.ctr */
+	mtctr	r3			/* CTR = r3 */
+
+	ld	r3, VCPU_LR(r4)		/* r3 = vcpu->arch.lr */
+	mtlr	r3			/* LR = r3 */
+
+	ld	r3, VCPU_XER(r4)	/* r3 = vcpu->arch.xer */
+	std	r3, (PACA_EXMC + EX_R3)(r13)
+
+	/* Some guests may need to have dcbz set to 32 byte length.
+	 *
+	 * Usually we ensure that by patching the guest's instructions
+	 * to trap on dcbz and emulate it in the hypervisor.
+	 *
+	 * If we can, we should tell the CPU to use 32 byte dcbz though,
+	 * because that's a lot faster.
+	 */
+
+	ld	r3, VCPU_HFLAGS(r4)
+	rldicl.	r3, r3, 0, 63		/* CR = ((r3 & 1) == 0) */
+	beq	no_dcbz32_on
+
+	mfspr   r3,SPRN_HID5
+	ori     r3, r3, 0x80		/* XXX HID5_dcbz32 = 0x80 */
+	mtspr   SPRN_HID5,r3
+
+no_dcbz32_on:
+	/*	Load guest GPRs */
+
+	ld	r3, VCPU_GPR(r9)(r4)
+	std	r3, (PACA_EXMC + EX_R9)(r13)
+	ld	r3, VCPU_GPR(r10)(r4)
+	std	r3, (PACA_EXMC + EX_R10)(r13)
+	ld	r3, VCPU_GPR(r11)(r4)
+	std	r3, (PACA_EXMC + EX_R11)(r13)
+	ld	r3, VCPU_GPR(r12)(r4)
+	std	r3, (PACA_EXMC + EX_R12)(r13)
+	ld	r3, VCPU_GPR(r13)(r4)
+	std	r3, (PACA_EXMC + EX_R13)(r13)
+
+	ld	r0, VCPU_GPR(r0)(r4)
+	ld	r1, VCPU_GPR(r1)(r4)
+	ld	r2, VCPU_GPR(r2)(r4)
+	ld	r3, VCPU_GPR(r3)(r4)
+	ld	r5, VCPU_GPR(r5)(r4)
+	ld	r6, VCPU_GPR(r6)(r4)
+	ld	r7, VCPU_GPR(r7)(r4)
+	ld	r8, VCPU_GPR(r8)(r4)
+	ld	r4, VCPU_GPR(r4)(r4)
+
+	/* This sets the Magic value for the trampoline */
+
+	li	r11, 1
+	stb	r11, PACA_KVM_IN_GUEST(r13)
+
+	/* Jump to SLB patching handlder and into our guest */
+	RFI
+
+/*
+ * This is the handler in module memory. It gets jumped at from the
+ * lowmem trampoline code, so it's basically the guest exit code.
+ *
+ */
+
+.global kvmppc_handler_highmem
+kvmppc_handler_highmem:
+
+	/*
+	 * Register usage at this point:
+	 *
+	 * R00   = guest R13
+	 * R01   = host R1
+	 * R02   = host R2
+	 * R10   = guest PC
+	 * R11   = guest MSR
+	 * R12   = exit handler id
+	 * R13   = PACA
+	 * PACA.exmc.R9    = guest R1
+	 * PACA.exmc.R10   = guest R10
+	 * PACA.exmc.R11   = guest R11
+	 * PACA.exmc.R12   = guest R12
+	 * PACA.exmc.R13   = guest R2
+	 * PACA.exmc.DAR   = guest DAR
+	 * PACA.exmc.DSISR = guest DSISR
+	 * PACA.exmc.LR    = guest instruction
+	 * PACA.exmc.CCR   = guest CR
+	 * PACA.exmc.SRR0  = guest R0
+	 *
+	 */
+
+	std	r3, (PACA_EXMC+EX_R3)(r13)
+
+	/* save the exit id in R3 */
+	mr	r3, r12
+
+	/* R12 = vcpu */
+	ld	r12, GPR4(r1)
+
+	/* Now save the guest state */
+
+	std	r0, VCPU_GPR(r13)(r12)
+	std	r4, VCPU_GPR(r4)(r12)
+	std	r5, VCPU_GPR(r5)(r12)
+	std	r6, VCPU_GPR(r6)(r12)
+	std	r7, VCPU_GPR(r7)(r12)
+	std	r8, VCPU_GPR(r8)(r12)
+	std	r9, VCPU_GPR(r9)(r12)
+
+	/* get registers from PACA */
+	mfpaca	r5, r0, EX_SRR0, r12
+	mfpaca	r5, r3, EX_R3, r12
+	mfpaca	r5, r1, EX_R9, r12
+	mfpaca	r5, r10, EX_R10, r12
+	mfpaca	r5, r11, EX_R11, r12
+	mfpaca	r5, r12, EX_R12, r12
+	mfpaca	r5, r2, EX_R13, r12
+
+	lwz	r5, (PACA_EXMC+EX_LR)(r13)
+	stw	r5, VCPU_LAST_INST(r12)
+
+	lwz	r5, (PACA_EXMC+EX_CCR)(r13)
+	stw	r5, VCPU_CR(r12)
+
+	ld	r5, VCPU_HFLAGS(r12)
+	rldicl.	r5, r5, 0, 63		/* CR = ((r5 & 1) == 0) */
+	beq	no_dcbz32_off
+
+	mfspr   r5,SPRN_HID5
+	rldimi  r5,r5,6,56
+	mtspr   SPRN_HID5,r5
+
+no_dcbz32_off:
+
+	/* XXX maybe skip on lightweight? */
+	std	r14, VCPU_GPR(r14)(r12)
+	std	r15, VCPU_GPR(r15)(r12)
+	std	r16, VCPU_GPR(r16)(r12)
+	std	r17, VCPU_GPR(r17)(r12)
+	std	r18, VCPU_GPR(r18)(r12)
+	std	r19, VCPU_GPR(r19)(r12)
+	std	r20, VCPU_GPR(r20)(r12)
+	std	r21, VCPU_GPR(r21)(r12)
+	std	r22, VCPU_GPR(r22)(r12)
+	std	r23, VCPU_GPR(r23)(r12)
+	std	r24, VCPU_GPR(r24)(r12)
+	std	r25, VCPU_GPR(r25)(r12)
+	std	r26, VCPU_GPR(r26)(r12)
+	std	r27, VCPU_GPR(r27)(r12)
+	std	r28, VCPU_GPR(r28)(r12)
+	std	r29, VCPU_GPR(r29)(r12)
+	std	r30, VCPU_GPR(r30)(r12)
+	std	r31, VCPU_GPR(r31)(r12)
+
+	/* Restore non-volatile host registers (r14 - r31) */
+	REST_NVGPRS(r1)
+
+	/* Save guest PC (R10) */
+	std	r10, VCPU_PC(r12)
+
+	/* Save guest msr (R11) */
+	std	r11, VCPU_SHADOW_MSR(r12)
+
+	/* Save guest CTR (in R12) */
+	mfctr	r5
+	std	r5, VCPU_CTR(r12)
+
+	/* Save guest LR */
+	mflr	r5
+	std	r5, VCPU_LR(r12)
+
+	/* Save guest XER */
+	mfxer	r5
+	std	r5, VCPU_XER(r12)
+
+	/* Save guest DAR */
+	ld	r5, (PACA_EXMC+EX_DAR)(r13)
+	std	r5, VCPU_FAULT_DEAR(r12)
+
+	/* Save guest DSISR */
+	lwz	r5, (PACA_EXMC+EX_DSISR)(r13)
+	std	r5, VCPU_FAULT_DSISR(r12)
+
+	/* Restore host msr -> SRR1 */
+	ld	r7, VCPU_HOST_MSR(r12)
+	mtsrr1	r7
+
+	/* Restore host IP -> SRR0 */
+	ld	r6, VCPU_HOST_RETIP(r12)
+	mtsrr0	r6
+
+	/*
+	 * For some interrupts, we need to call the real Linux
+	 * handler, so it can do work for us. This has to happen
+	 * as if the interrupt arrived from the kernel though,
+	 * so let's fake it here where most state is restored.
+	 *
+	 * Call Linux for hardware interrupts/decrementer
+	 * r3 = address of interrupt handler (exit reason)
+	 */
+
+	cmpwi	r3, BOOK3S_INTERRUPT_EXTERNAL
+	beq	call_linux_handler
+	cmpwi	r3, BOOK3S_INTERRUPT_DECREMENTER
+	beq	call_linux_handler
+
+	/* Back to Interruptable Mode! (goto kvm_return_point) */
+	RFI
+
+call_linux_handler:
+
+	/*
+	 * If we land here we need to jump back to the handler we
+	 * came from.
+	 *
+	 * We have a page that we can access from real mode, so let's
+	 * jump back to that and use it as a trampoline to get back into the
+	 * interrupt handler!
+	 *
+	 * R3 still contains the exit code,
+	 * R6 VCPU_HOST_RETIP and
+	 * R7 VCPU_HOST_MSR
+	 */
+
+	mtlr	r3
+
+	ld	r5, VCPU_TRAMPOLINE_LOWMEM(r12)
+	mtsrr0	r5
+	LOAD_REG_IMMEDIATE(r5, MSR_KERNEL & ~(MSR_IR | MSR_DR))
+	mtsrr1	r5
+
+	RFI
+
+.global kvm_return_point
+kvm_return_point:
+
+	/* Jump back to lightweight entry if we're supposed to */
+	/* go back into the guest */
+	mr	r5, r3
+	/* Restore r3 (kvm_run) and r4 (vcpu) */
+	REST_2GPRS(3, r1)
+	bl	KVMPPC_HANDLE_EXIT
+
+#if 0 /* XXX get lightweight exits back */
+	cmpwi	r3, RESUME_GUEST
+	bne	kvm_exit_heavyweight
+
+	/* put VCPU and KVM_RUN back into place and roll again! */
+	REST_2GPRS(3, r1)
+	b	kvm_start_lightweight
+
+kvm_exit_heavyweight:
+	/* Restore non-volatile host registers */
+	ld	r14, _LINK(r1)
+	mtlr	r14
+	REST_NVGPRS(r1)
+
+	addi    r1, r1, SWITCH_FRAME_SIZE
+#else
+	ld	r4, _LINK(r1)
+	mtlr	r4
+
+	cmpwi	r3, RESUME_GUEST
+	bne	kvm_exit_heavyweight
+
+	REST_2GPRS(3, r1)
+
+	addi    r1, r1, SWITCH_FRAME_SIZE
+
+	b	kvm_start_entry
+
+kvm_exit_heavyweight:
+
+	addi    r1, r1, SWITCH_FRAME_SIZE
+#endif
+
+	blr

From 5126ed37603ae3a5ec764d99d77430a179021699 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Nov 2009 12:02:29 +0000
Subject: [PATCH 045/151] Add SLB switching code for entry/exit

This is the really low level of guest entry/exit code.

Book3s_64 has an SLB, which stores all ESID -> VSID mappings we're
currently aware of.

The segments in the guest differ from the ones on the host, so we need
to switch the SLB to tell the MMU that we're in a new context.

So we store a shadow of the guest's SLB in the PACA, switch to that on
entry and only restore bolted entries on exit, leaving the rest to the
Linux SLB fault handler.

That way we get a really clean way of switching the SLB.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/book3s_64_slb.S | 262 +++++++++++++++++++++++++++++++
 1 file changed, 262 insertions(+)
 create mode 100644 arch/powerpc/kvm/book3s_64_slb.S

diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S
new file mode 100644
index 000000000000..ecd237a03fd0
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_slb.S
@@ -0,0 +1,262 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#define SHADOW_SLB_ESID(num)	(SLBSHADOW_SAVEAREA + (num * 0x10))
+#define SHADOW_SLB_VSID(num)	(SLBSHADOW_SAVEAREA + (num * 0x10) + 0x8)
+#define UNBOLT_SLB_ENTRY(num) \
+	ld	r9, SHADOW_SLB_ESID(num)(r12); \
+	/* Invalid? Skip. */; \
+	rldicl. r0, r9, 37, 63; \
+	beq	slb_entry_skip_ ## num; \
+	xoris	r9, r9, SLB_ESID_V@h; \
+	std	r9, SHADOW_SLB_ESID(num)(r12); \
+  slb_entry_skip_ ## num:
+
+#define REBOLT_SLB_ENTRY(num) \
+	ld	r10, SHADOW_SLB_ESID(num)(r11); \
+	cmpdi	r10, 0; \
+	beq	slb_exit_skip_1; \
+	oris	r10, r10, SLB_ESID_V@h; \
+	ld	r9, SHADOW_SLB_VSID(num)(r11); \
+	slbmte	r9, r10; \
+	std	r10, SHADOW_SLB_ESID(num)(r11); \
+slb_exit_skip_ ## num:
+
+/******************************************************************************
+ *                                                                            *
+ *                               Entry code                                   *
+ *                                                                            *
+ *****************************************************************************/
+
+.global kvmppc_handler_trampoline_enter
+kvmppc_handler_trampoline_enter:
+
+	/* Required state:
+	 *
+	 * MSR = ~IR|DR
+	 * R13 = PACA
+	 * R9 = guest IP
+	 * R10 = guest MSR
+	 * R11 = free
+	 * R12 = free
+	 * PACA[PACA_EXMC + EX_R9] = guest R9
+	 * PACA[PACA_EXMC + EX_R10] = guest R10
+	 * PACA[PACA_EXMC + EX_R11] = guest R11
+	 * PACA[PACA_EXMC + EX_R12] = guest R12
+	 * PACA[PACA_EXMC + EX_R13] = guest R13
+	 * PACA[PACA_EXMC + EX_CCR] = guest CR
+	 * PACA[PACA_EXMC + EX_R3] = guest XER
+	 */
+
+	mtsrr0	r9
+	mtsrr1	r10
+
+	mtspr	SPRN_SPRG_SCRATCH0, r0
+
+	/* Remove LPAR shadow entries */
+
+#if SLB_NUM_BOLTED == 3
+
+	ld	r12, PACA_SLBSHADOWPTR(r13)
+
+	/* Save off the first entry so we can slbie it later */
+	ld	r10, SHADOW_SLB_ESID(0)(r12)
+	ld	r11, SHADOW_SLB_VSID(0)(r12)
+
+	/* Remove bolted entries */
+	UNBOLT_SLB_ENTRY(0)
+	UNBOLT_SLB_ENTRY(1)
+	UNBOLT_SLB_ENTRY(2)
+	
+#else
+#error unknown number of bolted entries
+#endif
+
+	/* Flush SLB */
+
+	slbia
+
+	/* r0 = esid & ESID_MASK */
+	rldicr  r10, r10, 0, 35
+	/* r0 |= CLASS_BIT(VSID) */
+	rldic   r12, r11, 56 - 36, 36
+	or      r10, r10, r12
+	slbie	r10
+
+	isync
+
+	/* Fill SLB with our shadow */
+
+	lbz	r12, PACA_KVM_SLB_MAX(r13)
+	mulli	r12, r12, 16
+	addi	r12, r12, PACA_KVM_SLB
+	add	r12, r12, r13
+
+	/* for (r11 = kvm_slb; r11 < kvm_slb + kvm_slb_size; r11+=slb_entry) */
+	li	r11, PACA_KVM_SLB
+	add	r11, r11, r13
+
+slb_loop_enter:
+
+	ld	r10, 0(r11)
+
+	rldicl. r0, r10, 37, 63
+	beq	slb_loop_enter_skip
+
+	ld	r9, 8(r11)
+	slbmte	r9, r10
+
+slb_loop_enter_skip:
+	addi	r11, r11, 16
+	cmpd	cr0, r11, r12
+	blt	slb_loop_enter
+
+slb_do_enter:
+
+	/* Enter guest */
+
+	mfspr	r0, SPRN_SPRG_SCRATCH0
+
+	ld	r9, (PACA_EXMC+EX_R9)(r13)
+	ld	r10, (PACA_EXMC+EX_R10)(r13)
+	ld	r12, (PACA_EXMC+EX_R12)(r13)
+
+	lwz	r11, (PACA_EXMC+EX_CCR)(r13)
+	mtcr	r11
+
+	ld	r11, (PACA_EXMC+EX_R3)(r13)
+	mtxer	r11
+
+	ld	r11, (PACA_EXMC+EX_R11)(r13)
+	ld	r13, (PACA_EXMC+EX_R13)(r13)
+
+	RFI
+kvmppc_handler_trampoline_enter_end:
+
+
+
+/******************************************************************************
+ *                                                                            *
+ *                               Exit code                                    *
+ *                                                                            *
+ *****************************************************************************/
+
+.global kvmppc_handler_trampoline_exit
+kvmppc_handler_trampoline_exit:
+
+	/* Register usage at this point:
+	 *
+	 * SPRG_SCRATCH0 = guest R13
+	 * R01           = host R1
+	 * R02           = host R2
+	 * R10           = guest PC
+	 * R11           = guest MSR
+	 * R12           = exit handler id
+	 * R13           = PACA
+	 * PACA.exmc.CCR  = guest CR
+	 * PACA.exmc.R9  = guest R1
+	 * PACA.exmc.R10 = guest R10
+	 * PACA.exmc.R11 = guest R11
+	 * PACA.exmc.R12 = guest R12
+	 * PACA.exmc.R13 = guest R2
+	 *
+	 */
+
+	/* Save registers */
+
+	std	r0, (PACA_EXMC+EX_SRR0)(r13)
+	std	r9, (PACA_EXMC+EX_R3)(r13)
+	std	r10, (PACA_EXMC+EX_LR)(r13)
+	std	r11, (PACA_EXMC+EX_DAR)(r13)
+
+	/*
+	 * In order for us to easily get the last instruction,
+	 * we got the #vmexit at, we exploit the fact that the
+	 * virtual layout is still the same here, so we can just
+	 * ld from the guest's PC address
+	 */
+
+	/* We only load the last instruction when it's safe */
+	cmpwi	r12, BOOK3S_INTERRUPT_DATA_STORAGE
+	beq	ld_last_inst
+	cmpwi	r12, BOOK3S_INTERRUPT_PROGRAM
+	beq	ld_last_inst
+
+	b	no_ld_last_inst
+
+ld_last_inst:
+	/* Save off the guest instruction we're at */
+	/*    1) enable paging for data */
+	mfmsr	r9
+	ori	r11, r9, MSR_DR			/* Enable paging for data */
+	mtmsr	r11
+	/*    2) fetch the instruction */
+	lwz	r0, 0(r10)
+	/*    3) disable paging again */
+	mtmsr	r9
+
+no_ld_last_inst:
+
+	/* Restore bolted entries from the shadow and fix it along the way */
+
+	/* We don't store anything in entry 0, so we don't need to take care of it */
+	slbia
+	isync
+
+#if SLB_NUM_BOLTED == 3
+
+	ld	r11, PACA_SLBSHADOWPTR(r13)
+
+	REBOLT_SLB_ENTRY(0)
+	REBOLT_SLB_ENTRY(1)
+	REBOLT_SLB_ENTRY(2)
+	
+#else
+#error unknown number of bolted entries
+#endif
+
+slb_do_exit:
+
+	/* Restore registers */
+
+	ld	r11, (PACA_EXMC+EX_DAR)(r13)
+	ld	r10, (PACA_EXMC+EX_LR)(r13)
+	ld	r9, (PACA_EXMC+EX_R3)(r13)
+
+	/* Save last inst */
+	stw	r0, (PACA_EXMC+EX_LR)(r13)
+
+	/* Save DAR and DSISR before going to paged mode */
+	mfdar	r0
+	std	r0, (PACA_EXMC+EX_DAR)(r13)
+	mfdsisr	r0
+	stw	r0, (PACA_EXMC+EX_DSISR)(r13)
+
+	/* RFI into the highmem handler */
+	mfmsr	r0
+	ori	r0, r0, MSR_IR|MSR_DR|MSR_RI	/* Enable paging */
+	mtsrr1	r0
+	ld	r0, PACASAVEDMSR(r13)		/* Highmem handler address */
+	mtsrr0	r0
+
+	mfspr	r0, SPRN_SPRG_SCRATCH0
+
+	RFI
+kvmppc_handler_trampoline_exit_end:
+

From c862125c8ae4c261ecbb096ab12b1fa55fcfce8d Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:09 +0000
Subject: [PATCH 046/151] Add interrupt handling code

Getting from host state to the guest is only half the story. We also need
to return to our host context and handle whatever happened to get us out of
the guest.

On PowerPC every guest exit is an interrupt. So all we need to do is trap
the host's interrupt handlers and get into our #VMEXIT code to handle it.

PowerPCs also have a register that can add an offset to the interrupt handlers'
adresses which is what the booke KVM code uses. Unfortunately that is a
hypervisor ressource and we also want to be able to run KVM when we're running
in an LPAR. So we have to hook into the Linux interrupt handlers.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/book3s_64_rmhandlers.S | 131 ++++++++++++++++++++++++
 1 file changed, 131 insertions(+)
 create mode 100644 arch/powerpc/kvm/book3s_64_rmhandlers.S

diff --git a/arch/powerpc/kvm/book3s_64_rmhandlers.S b/arch/powerpc/kvm/book3s_64_rmhandlers.S
new file mode 100644
index 000000000000..fb7dd2e9ac88
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_rmhandlers.S
@@ -0,0 +1,131 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/asm-offsets.h>
+#include <asm/exception-64s.h>
+
+/*****************************************************************************
+ *                                                                           *
+ *        Real Mode handlers that need to be in low physical memory          *
+ *                                                                           *
+ ****************************************************************************/
+
+
+.macro INTERRUPT_TRAMPOLINE intno
+
+.global kvmppc_trampoline_\intno
+kvmppc_trampoline_\intno:
+
+	mtspr	SPRN_SPRG_SCRATCH0, r13		/* Save r13 */
+
+	/*
+	 * First thing to do is to find out if we're coming
+	 * from a KVM guest or a Linux process.
+	 *
+	 * To distinguish, we check a magic byte in the PACA
+	 */
+	mfspr	r13, SPRN_SPRG_PACA		/* r13 = PACA */
+	std	r12, (PACA_EXMC + EX_R12)(r13)
+	mfcr	r12
+	stw	r12, (PACA_EXMC + EX_CCR)(r13)
+	lbz	r12, PACA_KVM_IN_GUEST(r13)
+	cmpwi	r12, 0
+	bne	..kvmppc_handler_hasmagic_\intno
+	/* No KVM guest? Then jump back to the Linux handler! */
+	lwz	r12, (PACA_EXMC + EX_CCR)(r13)
+	mtcr	r12
+	ld	r12, (PACA_EXMC + EX_R12)(r13)
+	mfspr	r13, SPRN_SPRG_SCRATCH0		/* r13 = original r13 */
+	b	kvmppc_resume_\intno		/* Get back original handler */
+
+	/* Now we know we're handling a KVM guest */
+..kvmppc_handler_hasmagic_\intno:
+	/* Unset guest state */
+	li	r12, 0
+	stb	r12, PACA_KVM_IN_GUEST(r13)
+
+	std	r1, (PACA_EXMC+EX_R9)(r13)
+	std	r10, (PACA_EXMC+EX_R10)(r13)
+	std	r11, (PACA_EXMC+EX_R11)(r13)
+	std	r2, (PACA_EXMC+EX_R13)(r13)
+
+	mfsrr0	r10
+	mfsrr1	r11
+
+	/* Restore R1/R2 so we can handle faults */
+	ld	r1, PACAR1(r13)
+	ld	r2, (PACA_EXMC+EX_SRR0)(r13)
+
+	/* Let's store which interrupt we're handling */
+	li	r12, \intno
+
+	/* Jump into the SLB exit code that goes to the highmem handler */
+	b	kvmppc_handler_trampoline_exit
+
+.endm
+
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_SYSTEM_RESET
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_MACHINE_CHECK
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_DATA_STORAGE
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_DATA_SEGMENT
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_INST_STORAGE
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_INST_SEGMENT
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_EXTERNAL
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_ALIGNMENT
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_PROGRAM
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_FP_UNAVAIL
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_DECREMENTER
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_SYSCALL
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_TRACE
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_PERFMON
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_ALTIVEC
+INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_VSX
+
+/*
+ * This trampoline brings us back to a real mode handler
+ *
+ * Input Registers:
+ *
+ * R6 = SRR0
+ * R7 = SRR1
+ * LR = real-mode IP
+ *
+ */
+.global kvmppc_handler_lowmem_trampoline
+kvmppc_handler_lowmem_trampoline:
+
+	mtsrr0	r6
+	mtsrr1	r7
+	blr
+kvmppc_handler_lowmem_trampoline_end:
+
+.global kvmppc_trampoline_lowmem
+kvmppc_trampoline_lowmem:
+	.long kvmppc_handler_lowmem_trampoline - _stext
+
+.global kvmppc_trampoline_enter
+kvmppc_trampoline_enter:
+	.long kvmppc_handler_trampoline_enter - _stext
+
+#include "book3s_64_slb.S"
+

From 2f4cf5e42d13974763276e918618f76a4188e391 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:10 +0000
Subject: [PATCH 047/151] Add book3s.c

This adds the book3s core handling file. Here everything that is generic to
desktop PowerPC cores is handled, including interrupt injections, MSR settings,
etc.

It basically takes over the same role as booke.c for embedded PowerPCs.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/book3s.c | 925 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 925 insertions(+)
 create mode 100644 arch/powerpc/kvm/book3s.c

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
new file mode 100644
index 000000000000..42037d46a416
--- /dev/null
+++ b/arch/powerpc/kvm/book3s.c
@@ -0,0 +1,925 @@
+/*
+ * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved.
+ *
+ * Authors:
+ *    Alexander Graf <agraf@suse.de>
+ *    Kevin Wolf <mail@kevin-wolf.de>
+ *
+ * Description:
+ * This file is derived from arch/powerpc/kvm/44x.c,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+
+#include <asm/reg.h>
+#include <asm/cputable.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu_context.h>
+#include <linux/sched.h>
+#include <linux/vmalloc.h>
+
+#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+
+/* #define EXIT_DEBUG */
+/* #define EXIT_DEBUG_SIMPLE */
+
+/* Without AGGRESSIVE_DEC we only fire off a DEC interrupt when DEC turns 0.
+ * When set, we retrigger a DEC interrupt after that if DEC <= 0.
+ * PPC32 Linux runs faster without AGGRESSIVE_DEC, PPC64 Linux requires it. */
+
+/* #define AGGRESSIVE_DEC */
+
+struct kvm_stats_debugfs_item debugfs_entries[] = {
+	{ "exits",       VCPU_STAT(sum_exits) },
+	{ "mmio",        VCPU_STAT(mmio_exits) },
+	{ "sig",         VCPU_STAT(signal_exits) },
+	{ "sysc",        VCPU_STAT(syscall_exits) },
+	{ "inst_emu",    VCPU_STAT(emulated_inst_exits) },
+	{ "dec",         VCPU_STAT(dec_exits) },
+	{ "ext_intr",    VCPU_STAT(ext_intr_exits) },
+	{ "queue_intr",  VCPU_STAT(queue_intr) },
+	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
+	{ "pf_storage",  VCPU_STAT(pf_storage) },
+	{ "sp_storage",  VCPU_STAT(sp_storage) },
+	{ "pf_instruc",  VCPU_STAT(pf_instruc) },
+	{ "sp_instruc",  VCPU_STAT(sp_instruc) },
+	{ "ld",          VCPU_STAT(ld) },
+	{ "ld_slow",     VCPU_STAT(ld_slow) },
+	{ "st",          VCPU_STAT(st) },
+	{ "st_slow",     VCPU_STAT(st_slow) },
+	{ NULL }
+};
+
+void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	memcpy(get_paca()->kvm_slb, to_book3s(vcpu)->slb_shadow, sizeof(get_paca()->kvm_slb));
+	get_paca()->kvm_slb_max = to_book3s(vcpu)->slb_shadow_max;
+}
+
+void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	memcpy(to_book3s(vcpu)->slb_shadow, get_paca()->kvm_slb, sizeof(get_paca()->kvm_slb));
+	to_book3s(vcpu)->slb_shadow_max = get_paca()->kvm_slb_max;
+}
+
+#if defined(AGGRESSIVE_DEC) || defined(EXIT_DEBUG)
+static u32 kvmppc_get_dec(struct kvm_vcpu *vcpu)
+{
+	u64 jd = mftb() - vcpu->arch.dec_jiffies;
+	return vcpu->arch.dec - jd;
+}
+#endif
+
+void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
+{
+	ulong old_msr = vcpu->arch.msr;
+
+#ifdef EXIT_DEBUG
+	printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr);
+#endif
+	msr &= to_book3s(vcpu)->msr_mask;
+	vcpu->arch.msr = msr;
+	vcpu->arch.shadow_msr = msr | MSR_USER32;
+	vcpu->arch.shadow_msr &= ( MSR_VEC | MSR_VSX | MSR_FP | MSR_FE0 |
+				   MSR_USER64 | MSR_SE | MSR_BE | MSR_DE |
+				   MSR_FE1);
+
+	if (msr & (MSR_WE|MSR_POW)) {
+		if (!vcpu->arch.pending_exceptions) {
+			kvm_vcpu_block(vcpu);
+			vcpu->stat.halt_wakeup++;
+		}
+	}
+
+	if (((vcpu->arch.msr & (MSR_IR|MSR_DR)) != (old_msr & (MSR_IR|MSR_DR))) ||
+	    (vcpu->arch.msr & MSR_PR) != (old_msr & MSR_PR)) {
+		kvmppc_mmu_flush_segments(vcpu);
+		kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc);
+	}
+}
+
+void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
+{
+	vcpu->arch.srr0 = vcpu->arch.pc;
+	vcpu->arch.srr1 = vcpu->arch.msr | flags;
+	vcpu->arch.pc = to_book3s(vcpu)->hior + vec;
+	vcpu->arch.mmu.reset_msr(vcpu);
+}
+
+void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
+{
+	unsigned int prio;
+
+	vcpu->stat.queue_intr++;
+	switch (vec) {
+	case 0x100: prio = BOOK3S_IRQPRIO_SYSTEM_RESET;		break;
+	case 0x200: prio = BOOK3S_IRQPRIO_MACHINE_CHECK;	break;
+	case 0x300: prio = BOOK3S_IRQPRIO_DATA_STORAGE;		break;
+	case 0x380: prio = BOOK3S_IRQPRIO_DATA_SEGMENT;		break;
+	case 0x400: prio = BOOK3S_IRQPRIO_INST_STORAGE;		break;
+	case 0x480: prio = BOOK3S_IRQPRIO_INST_SEGMENT;		break;
+	case 0x500: prio = BOOK3S_IRQPRIO_EXTERNAL;		break;
+	case 0x600: prio = BOOK3S_IRQPRIO_ALIGNMENT;		break;
+	case 0x700: prio = BOOK3S_IRQPRIO_PROGRAM;		break;
+	case 0x800: prio = BOOK3S_IRQPRIO_FP_UNAVAIL;		break;
+	case 0x900: prio = BOOK3S_IRQPRIO_DECREMENTER;		break;
+	case 0xc00: prio = BOOK3S_IRQPRIO_SYSCALL;		break;
+	case 0xd00: prio = BOOK3S_IRQPRIO_DEBUG;		break;
+	case 0xf20: prio = BOOK3S_IRQPRIO_ALTIVEC;		break;
+	case 0xf40: prio = BOOK3S_IRQPRIO_VSX;			break;
+	default:    prio = BOOK3S_IRQPRIO_MAX;			break;
+	}
+
+	set_bit(prio, &vcpu->arch.pending_exceptions);
+#ifdef EXIT_DEBUG
+	printk(KERN_INFO "Queueing interrupt %x\n", vec);
+#endif
+}
+
+
+void kvmppc_core_queue_program(struct kvm_vcpu *vcpu)
+{
+	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_PROGRAM);
+}
+
+void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
+{
+	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
+}
+
+int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu)
+{
+	return test_bit(BOOK3S_INTERRUPT_DECREMENTER >> 7, &vcpu->arch.pending_exceptions);
+}
+
+void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
+                                struct kvm_interrupt *irq)
+{
+	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
+}
+
+int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
+{
+	int deliver = 1;
+	int vec = 0;
+
+	switch (priority) {
+	case BOOK3S_IRQPRIO_DECREMENTER:
+		deliver = vcpu->arch.msr & MSR_EE;
+		vec = BOOK3S_INTERRUPT_DECREMENTER;
+		break;
+	case BOOK3S_IRQPRIO_EXTERNAL:
+		deliver = vcpu->arch.msr & MSR_EE;
+		vec = BOOK3S_INTERRUPT_EXTERNAL;
+		break;
+	case BOOK3S_IRQPRIO_SYSTEM_RESET:
+		vec = BOOK3S_INTERRUPT_SYSTEM_RESET;
+		break;
+	case BOOK3S_IRQPRIO_MACHINE_CHECK:
+		vec = BOOK3S_INTERRUPT_MACHINE_CHECK;
+		break;
+	case BOOK3S_IRQPRIO_DATA_STORAGE:
+		vec = BOOK3S_INTERRUPT_DATA_STORAGE;
+		break;
+	case BOOK3S_IRQPRIO_INST_STORAGE:
+		vec = BOOK3S_INTERRUPT_INST_STORAGE;
+		break;
+	case BOOK3S_IRQPRIO_DATA_SEGMENT:
+		vec = BOOK3S_INTERRUPT_DATA_SEGMENT;
+		break;
+	case BOOK3S_IRQPRIO_INST_SEGMENT:
+		vec = BOOK3S_INTERRUPT_INST_SEGMENT;
+		break;
+	case BOOK3S_IRQPRIO_ALIGNMENT:
+		vec = BOOK3S_INTERRUPT_ALIGNMENT;
+		break;
+	case BOOK3S_IRQPRIO_PROGRAM:
+		vec = BOOK3S_INTERRUPT_PROGRAM;
+		break;
+	case BOOK3S_IRQPRIO_VSX:
+		vec = BOOK3S_INTERRUPT_VSX;
+		break;
+	case BOOK3S_IRQPRIO_ALTIVEC:
+		vec = BOOK3S_INTERRUPT_ALTIVEC;
+		break;
+	case BOOK3S_IRQPRIO_FP_UNAVAIL:
+		vec = BOOK3S_INTERRUPT_FP_UNAVAIL;
+		break;
+	case BOOK3S_IRQPRIO_SYSCALL:
+		vec = BOOK3S_INTERRUPT_SYSCALL;
+		break;
+	case BOOK3S_IRQPRIO_DEBUG:
+		vec = BOOK3S_INTERRUPT_TRACE;
+		break;
+	case BOOK3S_IRQPRIO_PERFORMANCE_MONITOR:
+		vec = BOOK3S_INTERRUPT_PERFMON;
+		break;
+	default:
+		deliver = 0;
+		printk(KERN_ERR "KVM: Unknown interrupt: 0x%x\n", priority);
+		break;
+	}
+
+#if 0
+	printk(KERN_INFO "Deliver interrupt 0x%x? %x\n", vec, deliver);
+#endif
+
+	if (deliver)
+		kvmppc_inject_interrupt(vcpu, vec, 0ULL);
+
+	return deliver;
+}
+
+void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
+{
+	unsigned long *pending = &vcpu->arch.pending_exceptions;
+	unsigned int priority;
+
+	/* XXX be more clever here - no need to mftb() on every entry */
+	/* Issue DEC again if it's still active */
+#ifdef AGGRESSIVE_DEC
+	if (vcpu->arch.msr & MSR_EE)
+		if (kvmppc_get_dec(vcpu) & 0x80000000)
+			kvmppc_core_queue_dec(vcpu);
+#endif
+
+#ifdef EXIT_DEBUG
+	if (vcpu->arch.pending_exceptions)
+		printk(KERN_EMERG "KVM: Check pending: %lx\n", vcpu->arch.pending_exceptions);
+#endif
+	priority = __ffs(*pending);
+	while (priority <= (sizeof(unsigned int) * 8)) {
+		if (kvmppc_book3s_irqprio_deliver(vcpu, priority)) {
+			clear_bit(priority, &vcpu->arch.pending_exceptions);
+			break;
+		}
+
+		priority = find_next_bit(pending,
+					 BITS_PER_BYTE * sizeof(*pending),
+					 priority + 1);
+	}
+}
+
+void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
+{
+	vcpu->arch.pvr = pvr;
+	if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
+		kvmppc_mmu_book3s_64_init(vcpu);
+		to_book3s(vcpu)->hior = 0xfff00000;
+		to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
+	} else {
+		kvmppc_mmu_book3s_32_init(vcpu);
+		to_book3s(vcpu)->hior = 0;
+		to_book3s(vcpu)->msr_mask = 0xffffffffULL;
+	}
+
+	/* If we are in hypervisor level on 970, we can tell the CPU to
+	 * treat DCBZ as 32 bytes store */
+	vcpu->arch.hflags &= ~BOOK3S_HFLAG_DCBZ32;
+	if (vcpu->arch.mmu.is_dcbz32(vcpu) && (mfmsr() & MSR_HV) &&
+	    !strcmp(cur_cpu_spec->platform, "ppc970"))
+		vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
+
+}
+
+/* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To
+ * make Book3s_32 Linux work on Book3s_64, we have to make sure we trap dcbz to
+ * emulate 32 bytes dcbz length.
+ *
+ * The Book3s_64 inventors also realized this case and implemented a special bit
+ * in the HID5 register, which is a hypervisor ressource. Thus we can't use it.
+ *
+ * My approach here is to patch the dcbz instruction on executing pages.
+ */
+static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
+{
+	bool touched = false;
+	hva_t hpage;
+	u32 *page;
+	int i;
+
+	hpage = gfn_to_hva(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
+	if (kvm_is_error_hva(hpage))
+		return;
+
+	hpage |= pte->raddr & ~PAGE_MASK;
+	hpage &= ~0xFFFULL;
+
+	page = vmalloc(HW_PAGE_SIZE);
+
+	if (copy_from_user(page, (void __user *)hpage, HW_PAGE_SIZE))
+		goto out;
+
+	for (i=0; i < HW_PAGE_SIZE / 4; i++)
+		if ((page[i] & 0xff0007ff) == INS_DCBZ) {
+			page[i] &= 0xfffffff7; // reserved instruction, so we trap
+			touched = true;
+		}
+
+	if (touched)
+		copy_to_user((void __user *)hpage, page, HW_PAGE_SIZE);
+
+out:
+	vfree(page);
+}
+
+static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
+			 struct kvmppc_pte *pte)
+{
+	int relocated = (vcpu->arch.msr & (data ? MSR_DR : MSR_IR));
+	int r;
+
+	if (relocated) {
+		r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data);
+	} else {
+		pte->eaddr = eaddr;
+		pte->raddr = eaddr & 0xffffffff;
+		pte->vpage = eaddr >> 12;
+		switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+		case 0:
+			pte->vpage |= VSID_REAL;
+		case MSR_DR:
+			pte->vpage |= VSID_REAL_DR;
+		case MSR_IR:
+			pte->vpage |= VSID_REAL_IR;
+		}
+		pte->may_read = true;
+		pte->may_write = true;
+		pte->may_execute = true;
+		r = 0;
+	}
+
+	return r;
+}
+
+static hva_t kvmppc_bad_hva(void)
+{
+	return PAGE_OFFSET;
+}
+
+static hva_t kvmppc_pte_to_hva(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte,
+			       bool read)
+{
+	hva_t hpage;
+
+	if (read && !pte->may_read)
+		goto err;
+
+	if (!read && !pte->may_write)
+		goto err;
+
+	hpage = gfn_to_hva(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
+	if (kvm_is_error_hva(hpage))
+		goto err;
+
+	return hpage | (pte->raddr & ~PAGE_MASK);
+err:
+	return kvmppc_bad_hva();
+}
+
+int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr)
+{
+	struct kvmppc_pte pte;
+	hva_t hva = eaddr;
+
+	vcpu->stat.st++;
+
+	if (kvmppc_xlate(vcpu, eaddr, false, &pte))
+		goto err;
+
+	hva = kvmppc_pte_to_hva(vcpu, &pte, false);
+	if (kvm_is_error_hva(hva))
+		goto err;
+
+	if (copy_to_user((void __user *)hva, ptr, size)) {
+		printk(KERN_INFO "kvmppc_st at 0x%lx failed\n", hva);
+		goto err;
+	}
+
+	return 0;
+
+err:
+	return -ENOENT;
+}
+
+int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr,
+		      bool data)
+{
+	struct kvmppc_pte pte;
+	hva_t hva = eaddr;
+
+	vcpu->stat.ld++;
+
+	if (kvmppc_xlate(vcpu, eaddr, data, &pte))
+		goto err;
+
+	hva = kvmppc_pte_to_hva(vcpu, &pte, true);
+	if (kvm_is_error_hva(hva))
+		goto err;
+
+	if (copy_from_user(ptr, (void __user *)hva, size)) {
+		printk(KERN_INFO "kvmppc_ld at 0x%lx failed\n", hva);
+		goto err;
+	}
+
+	return 0;
+
+err:
+	return -ENOENT;
+}
+
+static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	return kvm_is_visible_gfn(vcpu->kvm, gfn);
+}
+
+int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			    ulong eaddr, int vec)
+{
+	bool data = (vec == BOOK3S_INTERRUPT_DATA_STORAGE);
+	int r = RESUME_GUEST;
+	int relocated;
+	int page_found = 0;
+	struct kvmppc_pte pte;
+	bool is_mmio = false;
+
+	if ( vec == BOOK3S_INTERRUPT_DATA_STORAGE ) {
+		relocated = (vcpu->arch.msr & MSR_DR);
+	} else {
+		relocated = (vcpu->arch.msr & MSR_IR);
+	}
+
+	/* Resolve real address if translation turned on */
+	if (relocated) {
+		page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data);
+	} else {
+		pte.may_execute = true;
+		pte.may_read = true;
+		pte.may_write = true;
+		pte.raddr = eaddr & 0xffffffff;
+		pte.eaddr = eaddr;
+		pte.vpage = eaddr >> 12;
+		switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+		case 0:
+			pte.vpage |= VSID_REAL;
+		case MSR_DR:
+			pte.vpage |= VSID_REAL_DR;
+		case MSR_IR:
+			pte.vpage |= VSID_REAL_IR;
+		}
+	}
+
+	if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
+	   (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
+		/*
+		 * If we do the dcbz hack, we have to NX on every execution,
+		 * so we can patch the executing code. This renders our guest
+		 * NX-less.
+		 */
+		pte.may_execute = !data;
+	}
+
+	if (page_found == -ENOENT) {
+		/* Page not found in guest PTE entries */
+		vcpu->arch.dear = vcpu->arch.fault_dear;
+		to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr;
+		vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL);
+		kvmppc_book3s_queue_irqprio(vcpu, vec);
+	} else if (page_found == -EPERM) {
+		/* Storage protection */
+		vcpu->arch.dear = vcpu->arch.fault_dear;
+		to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE;
+		to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT;
+		vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL);
+		kvmppc_book3s_queue_irqprio(vcpu, vec);
+	} else if (page_found == -EINVAL) {
+		/* Page not found in guest SLB */
+		vcpu->arch.dear = vcpu->arch.fault_dear;
+		kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
+	} else if (!is_mmio &&
+		   kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) {
+		/* The guest's PTE is not mapped yet. Map on the host */
+		kvmppc_mmu_map_page(vcpu, &pte);
+		if (data)
+			vcpu->stat.sp_storage++;
+		else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
+			(!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32)))
+			kvmppc_patch_dcbz(vcpu, &pte);
+	} else {
+		/* MMIO */
+		vcpu->stat.mmio_exits++;
+		vcpu->arch.paddr_accessed = pte.raddr;
+		r = kvmppc_emulate_mmio(run, vcpu);
+		if ( r == RESUME_HOST_NV )
+			r = RESUME_HOST;
+		if ( r == RESUME_GUEST_NV )
+			r = RESUME_GUEST;
+	}
+
+	return r;
+}
+
+int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                       unsigned int exit_nr)
+{
+	int r = RESUME_HOST;
+
+	vcpu->stat.sum_exits++;
+
+	run->exit_reason = KVM_EXIT_UNKNOWN;
+	run->ready_for_interrupt_injection = 1;
+#ifdef EXIT_DEBUG
+	printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | dec=0x%x | msr=0x%lx\n",
+		exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear,
+		kvmppc_get_dec(vcpu), vcpu->arch.msr);
+#elif defined (EXIT_DEBUG_SIMPLE)
+	if ((exit_nr != 0x900) && (exit_nr != 0x500))
+		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | msr=0x%lx\n",
+			exit_nr, vcpu->arch.pc, vcpu->arch.fault_dear,
+			vcpu->arch.msr);
+#endif
+	kvm_resched(vcpu);
+	switch (exit_nr) {
+	case BOOK3S_INTERRUPT_INST_STORAGE:
+		vcpu->stat.pf_instruc++;
+		/* only care about PTEG not found errors, but leave NX alone */
+		if (vcpu->arch.shadow_msr & 0x40000000) {
+			r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.pc, exit_nr);
+			vcpu->stat.sp_instruc++;
+		} else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
+			  (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
+			/*
+			 * XXX If we do the dcbz hack we use the NX bit to flush&patch the page,
+			 *     so we can't use the NX bit inside the guest. Let's cross our fingers,
+			 *     that no guest that needs the dcbz hack does NX.
+			 */
+			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL);
+		} else {
+			vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x58000000);
+			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL);
+			r = RESUME_GUEST;
+		}
+		break;
+	case BOOK3S_INTERRUPT_DATA_STORAGE:
+		vcpu->stat.pf_storage++;
+		/* The only case we need to handle is missing shadow PTEs */
+		if (vcpu->arch.fault_dsisr & DSISR_NOHPTE) {
+			r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.fault_dear, exit_nr);
+		} else {
+			vcpu->arch.dear = vcpu->arch.fault_dear;
+			to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr;
+			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFULL);
+			r = RESUME_GUEST;
+		}
+		break;
+	case BOOK3S_INTERRUPT_DATA_SEGMENT:
+		if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.fault_dear) < 0) {
+			vcpu->arch.dear = vcpu->arch.fault_dear;
+			kvmppc_book3s_queue_irqprio(vcpu,
+				BOOK3S_INTERRUPT_DATA_SEGMENT);
+		}
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_INST_SEGMENT:
+		if (kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc) < 0) {
+			kvmppc_book3s_queue_irqprio(vcpu,
+				BOOK3S_INTERRUPT_INST_SEGMENT);
+		}
+		r = RESUME_GUEST;
+		break;
+	/* We're good on these - the host merely wanted to get our attention */
+	case BOOK3S_INTERRUPT_DECREMENTER:
+		vcpu->stat.dec_exits++;
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_EXTERNAL:
+		vcpu->stat.ext_intr_exits++;
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_PROGRAM:
+	{
+		enum emulation_result er;
+
+		if (vcpu->arch.msr & MSR_PR) {
+#ifdef EXIT_DEBUG
+			printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", vcpu->arch.pc, vcpu->arch.last_inst);
+#endif
+			if ((vcpu->arch.last_inst & 0xff0007ff) !=
+			    (INS_DCBZ & 0xfffffff7)) {
+				kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+				r = RESUME_GUEST;
+				break;
+			}
+		}
+
+		vcpu->stat.emulated_inst_exits++;
+		er = kvmppc_emulate_instruction(run, vcpu);
+		switch (er) {
+		case EMULATE_DONE:
+			r = RESUME_GUEST;
+			break;
+		case EMULATE_FAIL:
+			printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
+			       __func__, vcpu->arch.pc, vcpu->arch.last_inst);
+			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+			r = RESUME_GUEST;
+			break;
+		default:
+			BUG();
+		}
+		break;
+	}
+	case BOOK3S_INTERRUPT_SYSCALL:
+#ifdef EXIT_DEBUG
+		printk(KERN_INFO "Syscall Nr %d\n", (int)vcpu->arch.gpr[0]);
+#endif
+		vcpu->stat.syscall_exits++;
+		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_MACHINE_CHECK:
+	case BOOK3S_INTERRUPT_FP_UNAVAIL:
+	case BOOK3S_INTERRUPT_TRACE:
+	case BOOK3S_INTERRUPT_ALTIVEC:
+	case BOOK3S_INTERRUPT_VSX:
+		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+		r = RESUME_GUEST;
+		break;
+	default:
+		/* Ugh - bork here! What did we get? */
+		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n", exit_nr, vcpu->arch.pc, vcpu->arch.shadow_msr);
+		r = RESUME_HOST;
+		BUG();
+		break;
+	}
+
+
+	if (!(r & RESUME_HOST)) {
+		/* To avoid clobbering exit_reason, only check for signals if
+		 * we aren't already exiting to userspace for some other
+		 * reason. */
+		if (signal_pending(current)) {
+#ifdef EXIT_DEBUG
+			printk(KERN_EMERG "KVM: Going back to host\n");
+#endif
+			vcpu->stat.signal_exits++;
+			run->exit_reason = KVM_EXIT_INTR;
+			r = -EINTR;
+		} else {
+			/* In case an interrupt came in that was triggered
+			 * from userspace (like DEC), we need to check what
+			 * to inject now! */
+			kvmppc_core_deliver_interrupts(vcpu);
+		}
+	}
+
+#ifdef EXIT_DEBUG
+	printk(KERN_EMERG "KVM exit: vcpu=0x%p pc=0x%lx r=0x%x\n", vcpu, vcpu->arch.pc, r);
+#endif
+
+	return r;
+}
+
+int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	int i;
+
+	regs->pc = vcpu->arch.pc;
+	regs->cr = vcpu->arch.cr;
+	regs->ctr = vcpu->arch.ctr;
+	regs->lr = vcpu->arch.lr;
+	regs->xer = vcpu->arch.xer;
+	regs->msr = vcpu->arch.msr;
+	regs->srr0 = vcpu->arch.srr0;
+	regs->srr1 = vcpu->arch.srr1;
+	regs->pid = vcpu->arch.pid;
+	regs->sprg0 = vcpu->arch.sprg0;
+	regs->sprg1 = vcpu->arch.sprg1;
+	regs->sprg2 = vcpu->arch.sprg2;
+	regs->sprg3 = vcpu->arch.sprg3;
+	regs->sprg5 = vcpu->arch.sprg4;
+	regs->sprg6 = vcpu->arch.sprg5;
+	regs->sprg7 = vcpu->arch.sprg6;
+
+	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
+		regs->gpr[i] = vcpu->arch.gpr[i];
+
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	int i;
+
+	vcpu->arch.pc = regs->pc;
+	vcpu->arch.cr = regs->cr;
+	vcpu->arch.ctr = regs->ctr;
+	vcpu->arch.lr = regs->lr;
+	vcpu->arch.xer = regs->xer;
+	kvmppc_set_msr(vcpu, regs->msr);
+	vcpu->arch.srr0 = regs->srr0;
+	vcpu->arch.srr1 = regs->srr1;
+	vcpu->arch.sprg0 = regs->sprg0;
+	vcpu->arch.sprg1 = regs->sprg1;
+	vcpu->arch.sprg2 = regs->sprg2;
+	vcpu->arch.sprg3 = regs->sprg3;
+	vcpu->arch.sprg5 = regs->sprg4;
+	vcpu->arch.sprg6 = regs->sprg5;
+	vcpu->arch.sprg7 = regs->sprg6;
+
+	for (i = 0; i < ARRAY_SIZE(vcpu->arch.gpr); i++)
+		vcpu->arch.gpr[i] = regs->gpr[i];
+
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+                                  struct kvm_sregs *sregs)
+{
+	sregs->pvr = vcpu->arch.pvr;
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+                                  struct kvm_sregs *sregs)
+{
+	kvmppc_set_pvr(vcpu, sregs->pvr);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	return -ENOTSUPP;
+}
+
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	return -ENOTSUPP;
+}
+
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+                                  struct kvm_translation *tr)
+{
+	return 0;
+}
+
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+				      struct kvm_dirty_log *log)
+{
+	struct kvm_memory_slot *memslot;
+	struct kvm_vcpu *vcpu;
+	ulong ga, ga_end;
+	int is_dirty = 0;
+	int r, n;
+
+	down_write(&kvm->slots_lock);
+
+	r = kvm_get_dirty_log(kvm, log, &is_dirty);
+	if (r)
+		goto out;
+
+	/* If nothing is dirty, don't bother messing with page tables. */
+	if (is_dirty) {
+		memslot = &kvm->memslots[log->slot];
+
+		ga = memslot->base_gfn << PAGE_SHIFT;
+		ga_end = ga + (memslot->npages << PAGE_SHIFT);
+
+		kvm_for_each_vcpu(n, vcpu, kvm)
+			kvmppc_mmu_pte_pflush(vcpu, ga, ga_end);
+
+		n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+		memset(memslot->dirty_bitmap, 0, n);
+	}
+
+	r = 0;
+out:
+	up_write(&kvm->slots_lock);
+	return r;
+}
+
+int kvmppc_core_check_processor_compat(void)
+{
+	return 0;
+}
+
+struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s;
+	struct kvm_vcpu *vcpu;
+	int err;
+
+	vcpu_book3s = (struct kvmppc_vcpu_book3s *)__get_free_pages( GFP_KERNEL | __GFP_ZERO,
+			get_order(sizeof(struct kvmppc_vcpu_book3s)));
+	if (!vcpu_book3s) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	vcpu = &vcpu_book3s->vcpu;
+	err = kvm_vcpu_init(vcpu, kvm, id);
+	if (err)
+		goto free_vcpu;
+
+	vcpu->arch.host_retip = kvm_return_point;
+	vcpu->arch.host_msr = mfmsr();
+	/* default to book3s_64 (970fx) */
+	vcpu->arch.pvr = 0x3C0301;
+	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
+	vcpu_book3s->slb_nr = 64;
+
+	/* remember where some real-mode handlers are */
+	vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem;
+	vcpu->arch.trampoline_enter = kvmppc_trampoline_enter;
+	vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem;
+
+	vcpu->arch.shadow_msr = MSR_USER64;
+
+	err = __init_new_context();
+	if (err < 0)
+		goto free_vcpu;
+	vcpu_book3s->context_id = err;
+
+	vcpu_book3s->vsid_max = ((vcpu_book3s->context_id + 1) << USER_ESID_BITS) - 1;
+	vcpu_book3s->vsid_first = vcpu_book3s->context_id << USER_ESID_BITS;
+	vcpu_book3s->vsid_next = vcpu_book3s->vsid_first;
+
+	return vcpu;
+
+free_vcpu:
+	free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s)));
+out:
+	return ERR_PTR(err);
+}
+
+void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+
+	__destroy_context(vcpu_book3s->context_id);
+	kvm_vcpu_uninit(vcpu);
+	free_pages((long)vcpu_book3s, get_order(sizeof(struct kvmppc_vcpu_book3s)));
+}
+
+extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
+int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	/* No need to go into the guest when all we do is going out */
+	if (signal_pending(current)) {
+		kvm_run->exit_reason = KVM_EXIT_INTR;
+		return -EINTR;
+	}
+
+	/* XXX we get called with irq disabled - change that! */
+	local_irq_enable();
+
+	ret = __kvmppc_vcpu_entry(kvm_run, vcpu);
+
+	local_irq_disable();
+
+	return ret;
+}
+
+static int kvmppc_book3s_init(void)
+{
+	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), THIS_MODULE);
+}
+
+static void kvmppc_book3s_exit(void)
+{
+	kvm_exit();
+}
+
+module_init(kvmppc_book3s_init);
+module_exit(kvmppc_book3s_exit);

From 0d8dc681c84aa88ddc3d2fe5b6029f8eb3d11ecf Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:11 +0000
Subject: [PATCH 048/151] Add book3s_64 Host MMU handling

We designed the Book3S port of KVM as modular as possible. Most
of the code could be easily used on a Book3S_32 host as well.

The main difference between 32 and 64 bit cores is the MMU. To keep
things well separated, we treat the book3s_64 MMU as one possible compile
option.

This patch adds all the MMU helpers the rest of the code needs in
order to modify the host's MMU, like setting PTEs and segments.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/book3s_64_mmu_host.c | 408 ++++++++++++++++++++++++++
 1 file changed, 408 insertions(+)
 create mode 100644 arch/powerpc/kvm/book3s_64_mmu_host.c

diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
new file mode 100644
index 000000000000..f2899b297ffd
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -0,0 +1,408 @@
+/*
+ * Copyright (C) 2009 SUSE Linux Products GmbH. All rights reserved.
+ *
+ * Authors:
+ *     Alexander Graf <agraf@suse.de>
+ *     Kevin Wolf <mail@kevin-wolf.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu-hash64.h>
+#include <asm/machdep.h>
+#include <asm/mmu_context.h>
+#include <asm/hw_irq.h>
+
+#define PTE_SIZE 12
+#define VSID_ALL 0
+
+/* #define DEBUG_MMU */
+/* #define DEBUG_SLB */
+
+#ifdef DEBUG_MMU
+#define dprintk_mmu(a, ...) printk(KERN_INFO a, __VA_ARGS__)
+#else
+#define dprintk_mmu(a, ...) do { } while(0)
+#endif
+
+#ifdef DEBUG_SLB
+#define dprintk_slb(a, ...) printk(KERN_INFO a, __VA_ARGS__)
+#else
+#define dprintk_slb(a, ...) do { } while(0)
+#endif
+
+static void invalidate_pte(struct hpte_cache *pte)
+{
+	dprintk_mmu("KVM: Flushing SPT %d: 0x%llx (0x%llx) -> 0x%llx\n",
+		    i, pte->pte.eaddr, pte->pte.vpage, pte->host_va);
+
+	ppc_md.hpte_invalidate(pte->slot, pte->host_va,
+			       MMU_PAGE_4K, MMU_SEGSIZE_256M,
+			       false);
+	pte->host_va = 0;
+	kvm_release_pfn_dirty(pte->pfn);
+}
+
+void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, u64 guest_ea, u64 ea_mask)
+{
+	int i;
+
+	dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%llx & 0x%llx\n",
+		    vcpu->arch.hpte_cache_offset, guest_ea, ea_mask);
+	BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM);
+
+	guest_ea &= ea_mask;
+	for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) {
+		struct hpte_cache *pte;
+
+		pte = &vcpu->arch.hpte_cache[i];
+		if (!pte->host_va)
+			continue;
+
+		if ((pte->pte.eaddr & ea_mask) == guest_ea) {
+			invalidate_pte(pte);
+		}
+	}
+
+	/* Doing a complete flush -> start from scratch */
+	if (!ea_mask)
+		vcpu->arch.hpte_cache_offset = 0;
+}
+
+void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
+{
+	int i;
+
+	dprintk_mmu("KVM: Flushing %d Shadow vPTEs: 0x%llx & 0x%llx\n",
+		    vcpu->arch.hpte_cache_offset, guest_vp, vp_mask);
+	BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM);
+
+	guest_vp &= vp_mask;
+	for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) {
+		struct hpte_cache *pte;
+
+		pte = &vcpu->arch.hpte_cache[i];
+		if (!pte->host_va)
+			continue;
+
+		if ((pte->pte.vpage & vp_mask) == guest_vp) {
+			invalidate_pte(pte);
+		}
+	}
+}
+
+void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, u64 pa_start, u64 pa_end)
+{
+	int i;
+
+	dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%llx & 0x%llx\n",
+		    vcpu->arch.hpte_cache_offset, guest_pa, pa_mask);
+	BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM);
+
+	for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) {
+		struct hpte_cache *pte;
+
+		pte = &vcpu->arch.hpte_cache[i];
+		if (!pte->host_va)
+			continue;
+
+		if ((pte->pte.raddr >= pa_start) &&
+		    (pte->pte.raddr < pa_end)) {
+			invalidate_pte(pte);
+		}
+	}
+}
+
+struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, bool data)
+{
+	int i;
+	u64 guest_vp;
+
+	guest_vp = vcpu->arch.mmu.ea_to_vp(vcpu, ea, false);
+	for (i=0; i<vcpu->arch.hpte_cache_offset; i++) {
+		struct hpte_cache *pte;
+
+		pte = &vcpu->arch.hpte_cache[i];
+		if (!pte->host_va)
+			continue;
+
+		if (pte->pte.vpage == guest_vp)
+			return &pte->pte;
+	}
+
+	return NULL;
+}
+
+static int kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.hpte_cache_offset == HPTEG_CACHE_NUM)
+		kvmppc_mmu_pte_flush(vcpu, 0, 0);
+
+	return vcpu->arch.hpte_cache_offset++;
+}
+
+/* We keep 512 gvsid->hvsid entries, mapping the guest ones to the array using
+ * a hash, so we don't waste cycles on looping */
+static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid)
+{
+	return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 5)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 4)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 3)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 2)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 1)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 0)) & SID_MAP_MASK));
+}
+
+
+static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
+{
+	struct kvmppc_sid_map *map;
+	u16 sid_map_mask;
+
+	if (vcpu->arch.msr & MSR_PR)
+		gvsid |= VSID_PR;
+
+	sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
+	map = &to_book3s(vcpu)->sid_map[sid_map_mask];
+	if (map->guest_vsid == gvsid) {
+		dprintk_slb("SLB: Searching 0x%llx -> 0x%llx\n",
+			    gvsid, map->host_vsid);
+		return map;
+	}
+
+	map = &to_book3s(vcpu)->sid_map[SID_MAP_MASK - sid_map_mask];
+	if (map->guest_vsid == gvsid) {
+		dprintk_slb("SLB: Searching 0x%llx -> 0x%llx\n",
+			    gvsid, map->host_vsid);
+		return map;
+	}
+
+	dprintk_slb("SLB: Searching 0x%llx -> not found\n", gvsid);
+	return NULL;
+}
+
+int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
+{
+	pfn_t hpaddr;
+	ulong hash, hpteg, va;
+	u64 vsid;
+	int ret;
+	int rflags = 0x192;
+	int vflags = 0;
+	int attempt = 0;
+	struct kvmppc_sid_map *map;
+
+	/* Get host physical address for gpa */
+	hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
+	if (kvm_is_error_hva(hpaddr)) {
+		printk(KERN_INFO "Couldn't get guest page for gfn %llx!\n", orig_pte->eaddr);
+		return -EINVAL;
+	}
+	hpaddr <<= PAGE_SHIFT;
+#if PAGE_SHIFT == 12
+#elif PAGE_SHIFT == 16
+	hpaddr |= orig_pte->raddr & 0xf000;
+#else
+#error Unknown page size
+#endif
+
+	/* and write the mapping ea -> hpa into the pt */
+	vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid);
+	map = find_sid_vsid(vcpu, vsid);
+	if (!map) {
+		kvmppc_mmu_map_segment(vcpu, orig_pte->eaddr);
+		map = find_sid_vsid(vcpu, vsid);
+	}
+	BUG_ON(!map);
+
+	vsid = map->host_vsid;
+	va = hpt_va(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M);
+
+	if (!orig_pte->may_write)
+		rflags |= HPTE_R_PP;
+	else
+		mark_page_dirty(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
+
+	if (!orig_pte->may_execute)
+		rflags |= HPTE_R_N;
+
+	hash = hpt_hash(va, PTE_SIZE, MMU_SEGSIZE_256M);
+
+map_again:
+	hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
+
+	/* In case we tried normal mapping already, let's nuke old entries */
+	if (attempt > 1)
+		if (ppc_md.hpte_remove(hpteg) < 0)
+			return -1;
+
+	ret = ppc_md.hpte_insert(hpteg, va, hpaddr, rflags, vflags, MMU_PAGE_4K, MMU_SEGSIZE_256M);
+
+	if (ret < 0) {
+		/* If we couldn't map a primary PTE, try a secondary */
+#ifdef USE_SECONDARY
+		hash = ~hash;
+		attempt++;
+		if (attempt % 2)
+			vflags = HPTE_V_SECONDARY;
+		else
+			vflags = 0;
+#else
+		attempt = 2;
+#endif
+		goto map_again;
+	} else {
+		int hpte_id = kvmppc_mmu_hpte_cache_next(vcpu);
+		struct hpte_cache *pte = &vcpu->arch.hpte_cache[hpte_id];
+
+		dprintk_mmu("KVM: %c%c Map 0x%llx: [%lx] 0x%lx (0x%llx) -> %lx\n",
+			    ((rflags & HPTE_R_PP) == 3) ? '-' : 'w',
+			    (rflags & HPTE_R_N) ? '-' : 'x',
+			    orig_pte->eaddr, hpteg, va, orig_pte->vpage, hpaddr);
+
+		pte->slot = hpteg + (ret & 7);
+		pte->host_va = va;
+		pte->pte = *orig_pte;
+		pte->pfn = hpaddr >> PAGE_SHIFT;
+	}
+
+	return 0;
+}
+
+static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
+{
+	struct kvmppc_sid_map *map;
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+	u16 sid_map_mask;
+	static int backwards_map = 0;
+
+	if (vcpu->arch.msr & MSR_PR)
+		gvsid |= VSID_PR;
+
+	/* We might get collisions that trap in preceding order, so let's
+	   map them differently */
+
+	sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
+	if (backwards_map)
+		sid_map_mask = SID_MAP_MASK - sid_map_mask;
+
+	map = &to_book3s(vcpu)->sid_map[sid_map_mask];
+
+	/* Make sure we're taking the other map next time */
+	backwards_map = !backwards_map;
+
+	/* Uh-oh ... out of mappings. Let's flush! */
+	if (vcpu_book3s->vsid_next == vcpu_book3s->vsid_max) {
+		vcpu_book3s->vsid_next = vcpu_book3s->vsid_first;
+		memset(vcpu_book3s->sid_map, 0,
+		       sizeof(struct kvmppc_sid_map) * SID_MAP_NUM);
+		kvmppc_mmu_pte_flush(vcpu, 0, 0);
+		kvmppc_mmu_flush_segments(vcpu);
+	}
+	map->host_vsid = vcpu_book3s->vsid_next++;
+
+	map->guest_vsid = gvsid;
+	map->valid = true;
+
+	return map;
+}
+
+static int kvmppc_mmu_next_segment(struct kvm_vcpu *vcpu, ulong esid)
+{
+	int i;
+	int max_slb_size = 64;
+	int found_inval = -1;
+	int r;
+
+	if (!get_paca()->kvm_slb_max)
+		get_paca()->kvm_slb_max = 1;
+
+	/* Are we overwriting? */
+	for (i = 1; i < get_paca()->kvm_slb_max; i++) {
+		if (!(get_paca()->kvm_slb[i].esid & SLB_ESID_V))
+			found_inval = i;
+		else if ((get_paca()->kvm_slb[i].esid & ESID_MASK) == esid)
+			return i;
+	}
+
+	/* Found a spare entry that was invalidated before */
+	if (found_inval > 0)
+		return found_inval;
+
+	/* No spare invalid entry, so create one */
+
+	if (mmu_slb_size < 64)
+		max_slb_size = mmu_slb_size;
+
+	/* Overflowing -> purge */
+	if ((get_paca()->kvm_slb_max) == max_slb_size)
+		kvmppc_mmu_flush_segments(vcpu);
+
+	r = get_paca()->kvm_slb_max;
+	get_paca()->kvm_slb_max++;
+
+	return r;
+}
+
+int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
+{
+	u64 esid = eaddr >> SID_SHIFT;
+	u64 slb_esid = (eaddr & ESID_MASK) | SLB_ESID_V;
+	u64 slb_vsid = SLB_VSID_USER;
+	u64 gvsid;
+	int slb_index;
+	struct kvmppc_sid_map *map;
+
+	slb_index = kvmppc_mmu_next_segment(vcpu, eaddr & ESID_MASK);
+
+	if (vcpu->arch.mmu.esid_to_vsid(vcpu, esid, &gvsid)) {
+		/* Invalidate an entry */
+		get_paca()->kvm_slb[slb_index].esid = 0;
+		return -ENOENT;
+	}
+
+	map = find_sid_vsid(vcpu, gvsid);
+	if (!map)
+		map = create_sid_map(vcpu, gvsid);
+
+	map->guest_esid = esid;
+
+	slb_vsid |= (map->host_vsid << 12);
+	slb_vsid &= ~SLB_VSID_KP;
+	slb_esid |= slb_index;
+
+	get_paca()->kvm_slb[slb_index].esid = slb_esid;
+	get_paca()->kvm_slb[slb_index].vsid = slb_vsid;
+
+	dprintk_slb("slbmte %#llx, %#llx\n", slb_vsid, slb_esid);
+
+	return 0;
+}
+
+void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
+{
+	get_paca()->kvm_slb_max = 1;
+	get_paca()->kvm_slb[0].esid = 0;
+}
+
+void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+{
+	kvmppc_mmu_pte_flush(vcpu, 0, 0);
+}

From e71b2a39afff245c3a93809e62d35a90726f8d3e Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:12 +0000
Subject: [PATCH 049/151] Add book3s_64 guest MMU

To be able to run a guest, we also need to implement a guest MMU.

This patch adds MMU handling for Book3s_64 guests.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/book3s_64_mmu.c | 476 +++++++++++++++++++++++++++++++
 1 file changed, 476 insertions(+)
 create mode 100644 arch/powerpc/kvm/book3s_64_mmu.c

diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
new file mode 100644
index 000000000000..a31f9c677d23
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -0,0 +1,476 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+
+#include <asm/tlbflush.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+
+/* #define DEBUG_MMU */
+
+#ifdef DEBUG_MMU
+#define dprintk(X...) printk(KERN_INFO X)
+#else
+#define dprintk(X...) do { } while(0)
+#endif
+
+static void kvmppc_mmu_book3s_64_reset_msr(struct kvm_vcpu *vcpu)
+{
+	kvmppc_set_msr(vcpu, MSR_SF);
+}
+
+static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe(
+				struct kvmppc_vcpu_book3s *vcpu_book3s,
+				gva_t eaddr)
+{
+	int i;
+	u64 esid = GET_ESID(eaddr);
+	u64 esid_1t = GET_ESID_1T(eaddr);
+
+	for (i = 0; i < vcpu_book3s->slb_nr; i++) {
+		u64 cmp_esid = esid;
+
+		if (!vcpu_book3s->slb[i].valid)
+			continue;
+
+		if (vcpu_book3s->slb[i].large)
+			cmp_esid = esid_1t;
+
+		if (vcpu_book3s->slb[i].esid == cmp_esid)
+			return &vcpu_book3s->slb[i];
+	}
+
+	dprintk("KVM: No SLB entry found for 0x%lx [%llx | %llx]\n",
+		eaddr, esid, esid_1t);
+	for (i = 0; i < vcpu_book3s->slb_nr; i++) {
+	    if (vcpu_book3s->slb[i].vsid)
+		dprintk("  %d: %c%c %llx %llx\n", i,
+			vcpu_book3s->slb[i].valid ? 'v' : ' ',
+			vcpu_book3s->slb[i].large ? 'l' : ' ',
+			vcpu_book3s->slb[i].esid,
+			vcpu_book3s->slb[i].vsid);
+	}
+
+	return NULL;
+}
+
+static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
+					 bool data)
+{
+	struct kvmppc_slb *slb;
+
+	slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), eaddr);
+	if (!slb)
+		return 0;
+
+	if (slb->large)
+		return (((u64)eaddr >> 12) & 0xfffffff) |
+		       (((u64)slb->vsid) << 28);
+
+	return (((u64)eaddr >> 12) & 0xffff) | (((u64)slb->vsid) << 16);
+}
+
+static int kvmppc_mmu_book3s_64_get_pagesize(struct kvmppc_slb *slbe)
+{
+	return slbe->large ? 24 : 12;
+}
+
+static u32 kvmppc_mmu_book3s_64_get_page(struct kvmppc_slb *slbe, gva_t eaddr)
+{
+	int p = kvmppc_mmu_book3s_64_get_pagesize(slbe);
+	return ((eaddr & 0xfffffff) >> p);
+}
+
+static hva_t kvmppc_mmu_book3s_64_get_pteg(
+				struct kvmppc_vcpu_book3s *vcpu_book3s,
+				struct kvmppc_slb *slbe, gva_t eaddr,
+				bool second)
+{
+	u64 hash, pteg, htabsize;
+	u32 page;
+	hva_t r;
+
+	page = kvmppc_mmu_book3s_64_get_page(slbe, eaddr);
+	htabsize = ((1 << ((vcpu_book3s->sdr1 & 0x1f) + 11)) - 1);
+
+	hash = slbe->vsid ^ page;
+	if (second)
+		hash = ~hash;
+	hash &= ((1ULL << 39ULL) - 1ULL);
+	hash &= htabsize;
+	hash <<= 7ULL;
+
+	pteg = vcpu_book3s->sdr1 & 0xfffffffffffc0000ULL;
+	pteg |= hash;
+
+	dprintk("MMU: page=0x%x sdr1=0x%llx pteg=0x%llx vsid=0x%llx\n",
+		page, vcpu_book3s->sdr1, pteg, slbe->vsid);
+
+	r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT);
+	if (kvm_is_error_hva(r))
+		return r;
+	return r | (pteg & ~PAGE_MASK);
+}
+
+static u64 kvmppc_mmu_book3s_64_get_avpn(struct kvmppc_slb *slbe, gva_t eaddr)
+{
+	int p = kvmppc_mmu_book3s_64_get_pagesize(slbe);
+	u64 avpn;
+
+	avpn = kvmppc_mmu_book3s_64_get_page(slbe, eaddr);
+	avpn |= slbe->vsid << (28 - p);
+
+	if (p < 24)
+		avpn >>= ((80 - p) - 56) - 8;
+	else
+		avpn <<= 8;
+
+	return avpn;
+}
+
+static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
+				struct kvmppc_pte *gpte, bool data)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+	struct kvmppc_slb *slbe;
+	hva_t ptegp;
+	u64 pteg[16];
+	u64 avpn = 0;
+	int i;
+	u8 key = 0;
+	bool found = false;
+	bool perm_err = false;
+	int second = 0;
+
+	slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu_book3s, eaddr);
+	if (!slbe)
+		goto no_seg_found;
+
+do_second:
+	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second);
+	if (kvm_is_error_hva(ptegp))
+		goto no_page_found;
+
+	avpn = kvmppc_mmu_book3s_64_get_avpn(slbe, eaddr);
+
+	if(copy_from_user(pteg, (void __user *)ptegp, sizeof(pteg))) {
+		printk(KERN_ERR "KVM can't copy data from 0x%lx!\n", ptegp);
+		goto no_page_found;
+	}
+
+	if ((vcpu->arch.msr & MSR_PR) && slbe->Kp)
+		key = 4;
+	else if (!(vcpu->arch.msr & MSR_PR) && slbe->Ks)
+		key = 4;
+
+	for (i=0; i<16; i+=2) {
+		u64 v = pteg[i];
+		u64 r = pteg[i+1];
+
+		/* Valid check */
+		if (!(v & HPTE_V_VALID))
+			continue;
+		/* Hash check */
+		if ((v & HPTE_V_SECONDARY) != second)
+			continue;
+
+		/* AVPN compare */
+		if (HPTE_V_AVPN_VAL(avpn) == HPTE_V_AVPN_VAL(v)) {
+			u8 pp = (r & HPTE_R_PP) | key;
+			int eaddr_mask = 0xFFF;
+
+			gpte->eaddr = eaddr;
+			gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu,
+								    eaddr,
+								    data);
+			if (slbe->large)
+				eaddr_mask = 0xFFFFFF;
+			gpte->raddr = (r & HPTE_R_RPN) | (eaddr & eaddr_mask);
+			gpte->may_execute = ((r & HPTE_R_N) ? false : true);
+			gpte->may_read = false;
+			gpte->may_write = false;
+
+			switch (pp) {
+			case 0:
+			case 1:
+			case 2:
+			case 6:
+				gpte->may_write = true;
+				/* fall through */
+			case 3:
+			case 5:
+			case 7:
+				gpte->may_read = true;
+				break;
+			}
+
+			if (!gpte->may_read) {
+				perm_err = true;
+				continue;
+			}
+
+			dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx "
+				"-> 0x%llx\n",
+				eaddr, avpn, gpte->vpage, gpte->raddr);
+			found = true;
+			break;
+		}
+	}
+
+	/* Update PTE R and C bits, so the guest's swapper knows we used the
+	 * page */
+	if (found) {
+		u32 oldr = pteg[i+1];
+
+		if (gpte->may_read) {
+			/* Set the accessed flag */
+			pteg[i+1] |= HPTE_R_R;
+		}
+		if (gpte->may_write) {
+			/* Set the dirty flag */
+			pteg[i+1] |= HPTE_R_C;
+		} else {
+			dprintk("KVM: Mapping read-only page!\n");
+		}
+
+		/* Write back into the PTEG */
+		if (pteg[i+1] != oldr)
+			copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
+
+		return 0;
+	} else {
+		dprintk("KVM MMU: No PTE found (ea=0x%lx sdr1=0x%llx "
+			"ptegp=0x%lx)\n",
+			eaddr, to_book3s(vcpu)->sdr1, ptegp);
+		for (i = 0; i < 16; i += 2)
+			dprintk("   %02d: 0x%llx - 0x%llx (0x%llx)\n",
+				i, pteg[i], pteg[i+1], avpn);
+
+		if (!second) {
+			second = HPTE_V_SECONDARY;
+			goto do_second;
+		}
+	}
+
+
+no_page_found:
+
+
+	if (perm_err)
+		return -EPERM;
+
+	return -ENOENT;
+
+no_seg_found:
+
+	dprintk("KVM MMU: Trigger segment fault\n");
+	return -EINVAL;
+}
+
+static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s;
+	u64 esid, esid_1t;
+	int slb_nr;
+	struct kvmppc_slb *slbe;
+
+	dprintk("KVM MMU: slbmte(0x%llx, 0x%llx)\n", rs, rb);
+
+	vcpu_book3s = to_book3s(vcpu);
+
+	esid = GET_ESID(rb);
+	esid_1t = GET_ESID_1T(rb);
+	slb_nr = rb & 0xfff;
+
+	if (slb_nr > vcpu_book3s->slb_nr)
+		return;
+
+	slbe = &vcpu_book3s->slb[slb_nr];
+
+	slbe->large = (rs & SLB_VSID_L) ? 1 : 0;
+	slbe->esid  = slbe->large ? esid_1t : esid;
+	slbe->vsid  = rs >> 12;
+	slbe->valid = (rb & SLB_ESID_V) ? 1 : 0;
+	slbe->Ks    = (rs & SLB_VSID_KS) ? 1 : 0;
+	slbe->Kp    = (rs & SLB_VSID_KP) ? 1 : 0;
+	slbe->nx    = (rs & SLB_VSID_N) ? 1 : 0;
+	slbe->class = (rs & SLB_VSID_C) ? 1 : 0;
+
+	slbe->orige = rb & (ESID_MASK | SLB_ESID_V);
+	slbe->origv = rs;
+
+	/* Map the new segment */
+	kvmppc_mmu_map_segment(vcpu, esid << SID_SHIFT);
+}
+
+static u64 kvmppc_mmu_book3s_64_slbmfee(struct kvm_vcpu *vcpu, u64 slb_nr)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+	struct kvmppc_slb *slbe;
+
+	if (slb_nr > vcpu_book3s->slb_nr)
+		return 0;
+
+	slbe = &vcpu_book3s->slb[slb_nr];
+
+	return slbe->orige;
+}
+
+static u64 kvmppc_mmu_book3s_64_slbmfev(struct kvm_vcpu *vcpu, u64 slb_nr)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+	struct kvmppc_slb *slbe;
+
+	if (slb_nr > vcpu_book3s->slb_nr)
+		return 0;
+
+	slbe = &vcpu_book3s->slb[slb_nr];
+
+	return slbe->origv;
+}
+
+static void kvmppc_mmu_book3s_64_slbie(struct kvm_vcpu *vcpu, u64 ea)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+	struct kvmppc_slb *slbe;
+
+	dprintk("KVM MMU: slbie(0x%llx)\n", ea);
+
+	slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu_book3s, ea);
+
+	if (!slbe)
+		return;
+
+	dprintk("KVM MMU: slbie(0x%llx, 0x%llx)\n", ea, slbe->esid);
+
+	slbe->valid = false;
+
+	kvmppc_mmu_map_segment(vcpu, ea);
+}
+
+static void kvmppc_mmu_book3s_64_slbia(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+	int i;
+
+	dprintk("KVM MMU: slbia()\n");
+
+	for (i = 1; i < vcpu_book3s->slb_nr; i++)
+		vcpu_book3s->slb[i].valid = false;
+
+	if (vcpu->arch.msr & MSR_IR) {
+		kvmppc_mmu_flush_segments(vcpu);
+		kvmppc_mmu_map_segment(vcpu, vcpu->arch.pc);
+	}
+}
+
+static void kvmppc_mmu_book3s_64_mtsrin(struct kvm_vcpu *vcpu, u32 srnum,
+					ulong value)
+{
+	u64 rb = 0, rs = 0;
+
+	/* ESID = srnum */
+	rb |= (srnum & 0xf) << 28;
+	/* Set the valid bit */
+	rb |= 1 << 27;
+	/* Index = ESID */
+	rb |= srnum;
+
+	/* VSID = VSID */
+	rs |= (value & 0xfffffff) << 12;
+	/* flags = flags */
+	rs |= ((value >> 27) & 0xf) << 9;
+
+	kvmppc_mmu_book3s_64_slbmte(vcpu, rs, rb);
+}
+
+static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va,
+				       bool large)
+{
+	u64 mask = 0xFFFFFFFFFULL;
+
+	dprintk("KVM MMU: tlbie(0x%lx)\n", va);
+
+	if (large)
+		mask = 0xFFFFFF000ULL;
+	kvmppc_mmu_pte_vflush(vcpu, va >> 12, mask);
+}
+
+static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, u64 esid,
+					     u64 *vsid)
+{
+	switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+	case 0:
+		*vsid = (VSID_REAL >> 16) | esid;
+		break;
+	case MSR_IR:
+		*vsid = (VSID_REAL_IR >> 16) | esid;
+		break;
+	case MSR_DR:
+		*vsid = (VSID_REAL_DR >> 16) | esid;
+		break;
+	case MSR_DR|MSR_IR:
+	{
+		ulong ea;
+		struct kvmppc_slb *slb;
+		ea = esid << SID_SHIFT;
+		slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea);
+		if (slb)
+			*vsid = slb->vsid;
+		else
+			return -ENOENT;
+
+		break;
+	}
+	default:
+		BUG();
+		break;
+	}
+
+	return 0;
+}
+
+static bool kvmppc_mmu_book3s_64_is_dcbz32(struct kvm_vcpu *vcpu)
+{
+	return (to_book3s(vcpu)->hid[5] & 0x80);
+}
+
+void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_mmu *mmu = &vcpu->arch.mmu;
+
+	mmu->mfsrin = NULL;
+	mmu->mtsrin = kvmppc_mmu_book3s_64_mtsrin;
+	mmu->slbmte = kvmppc_mmu_book3s_64_slbmte;
+	mmu->slbmfee = kvmppc_mmu_book3s_64_slbmfee;
+	mmu->slbmfev = kvmppc_mmu_book3s_64_slbmfev;
+	mmu->slbie = kvmppc_mmu_book3s_64_slbie;
+	mmu->slbia = kvmppc_mmu_book3s_64_slbia;
+	mmu->xlate = kvmppc_mmu_book3s_64_xlate;
+	mmu->reset_msr = kvmppc_mmu_book3s_64_reset_msr;
+	mmu->tlbie = kvmppc_mmu_book3s_64_tlbie;
+	mmu->esid_to_vsid = kvmppc_mmu_book3s_64_esid_to_vsid;
+	mmu->ea_to_vp = kvmppc_mmu_book3s_64_ea_to_vp;
+	mmu->is_dcbz32 = kvmppc_mmu_book3s_64_is_dcbz32;
+}

From 012351808174120b2e1839d48e2f0678808b2367 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:13 +0000
Subject: [PATCH 050/151] Add book3s_32 guest MMU

This patch adds an implementation for a G3/G4 MMU, so we can run G3 and
G4 guests in KVM on Book3s_64.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/book3s_32_mmu.c | 372 +++++++++++++++++++++++++++++++
 1 file changed, 372 insertions(+)
 create mode 100644 arch/powerpc/kvm/book3s_32_mmu.c

diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
new file mode 100644
index 000000000000..faf99f20d993
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -0,0 +1,372 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+
+#include <asm/tlbflush.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+
+/* #define DEBUG_MMU */
+/* #define DEBUG_MMU_PTE */
+/* #define DEBUG_MMU_PTE_IP 0xfff14c40 */
+
+#ifdef DEBUG_MMU
+#define dprintk(X...) printk(KERN_INFO X)
+#else
+#define dprintk(X...) do { } while(0)
+#endif
+
+#ifdef DEBUG_PTE
+#define dprintk_pte(X...) printk(KERN_INFO X)
+#else
+#define dprintk_pte(X...) do { } while(0)
+#endif
+
+#define PTEG_FLAG_ACCESSED	0x00000100
+#define PTEG_FLAG_DIRTY		0x00000080
+
+static inline bool check_debug_ip(struct kvm_vcpu *vcpu)
+{
+#ifdef DEBUG_MMU_PTE_IP
+	return vcpu->arch.pc == DEBUG_MMU_PTE_IP;
+#else
+	return true;
+#endif
+}
+
+static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
+					  struct kvmppc_pte *pte, bool data);
+
+static struct kvmppc_sr *find_sr(struct kvmppc_vcpu_book3s *vcpu_book3s, gva_t eaddr)
+{
+	return &vcpu_book3s->sr[(eaddr >> 28) & 0xf];
+}
+
+static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
+					 bool data)
+{
+	struct kvmppc_sr *sre = find_sr(to_book3s(vcpu), eaddr);
+	struct kvmppc_pte pte;
+
+	if (!kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, &pte, data))
+		return pte.vpage;
+
+	return (((u64)eaddr >> 12) & 0xffff) | (((u64)sre->vsid) << 16);
+}
+
+static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu)
+{
+	kvmppc_set_msr(vcpu, 0);
+}
+
+static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3s,
+				      struct kvmppc_sr *sre, gva_t eaddr,
+				      bool primary)
+{
+	u32 page, hash, pteg, htabmask;
+	hva_t r;
+
+	page = (eaddr & 0x0FFFFFFF) >> 12;
+	htabmask = ((vcpu_book3s->sdr1 & 0x1FF) << 16) | 0xFFC0;
+
+	hash = ((sre->vsid ^ page) << 6);
+	if (!primary)
+		hash = ~hash;
+	hash &= htabmask;
+
+	pteg = (vcpu_book3s->sdr1 & 0xffff0000) | hash;
+
+	dprintk("MMU: pc=0x%lx eaddr=0x%lx sdr1=0x%llx pteg=0x%x vsid=0x%x\n",
+		vcpu_book3s->vcpu.arch.pc, eaddr, vcpu_book3s->sdr1, pteg,
+		sre->vsid);
+
+	r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT);
+	if (kvm_is_error_hva(r))
+		return r;
+	return r | (pteg & ~PAGE_MASK);
+}
+
+static u32 kvmppc_mmu_book3s_32_get_ptem(struct kvmppc_sr *sre, gva_t eaddr,
+				    bool primary)
+{
+	return ((eaddr & 0x0fffffff) >> 22) | (sre->vsid << 7) |
+	       (primary ? 0 : 0x40) | 0x80000000;
+}
+
+static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
+					  struct kvmppc_pte *pte, bool data)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+	struct kvmppc_bat *bat;
+	int i;
+
+	for (i = 0; i < 8; i++) {
+		if (data)
+			bat = &vcpu_book3s->dbat[i];
+		else
+			bat = &vcpu_book3s->ibat[i];
+
+		if (vcpu->arch.msr & MSR_PR) {
+			if (!bat->vp)
+				continue;
+		} else {
+			if (!bat->vs)
+				continue;
+		}
+
+		if (check_debug_ip(vcpu))
+		{
+			dprintk_pte("%cBAT %02d: 0x%lx - 0x%x (0x%x)\n",
+				    data ? 'd' : 'i', i, eaddr, bat->bepi,
+				    bat->bepi_mask);
+		}
+		if ((eaddr & bat->bepi_mask) == bat->bepi) {
+			pte->raddr = bat->brpn | (eaddr & ~bat->bepi_mask);
+			pte->vpage = (eaddr >> 12) | VSID_BAT;
+			pte->may_read = bat->pp;
+			pte->may_write = bat->pp > 1;
+			pte->may_execute = true;
+			if (!pte->may_read) {
+				printk(KERN_INFO "BAT is not readable!\n");
+				continue;
+			}
+			if (!pte->may_write) {
+				/* let's treat r/o BATs as not-readable for now */
+				dprintk_pte("BAT is read-only!\n");
+				continue;
+			}
+
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
+static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
+				     struct kvmppc_pte *pte, bool data,
+				     bool primary)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+	struct kvmppc_sr *sre;
+	hva_t ptegp;
+	u32 pteg[16];
+	u64 ptem = 0;
+	int i;
+	int found = 0;
+
+	sre = find_sr(vcpu_book3s, eaddr);
+
+	dprintk_pte("SR 0x%lx: vsid=0x%x, raw=0x%x\n", eaddr >> 28,
+		    sre->vsid, sre->raw);
+
+	pte->vpage = kvmppc_mmu_book3s_32_ea_to_vp(vcpu, eaddr, data);
+
+	ptegp = kvmppc_mmu_book3s_32_get_pteg(vcpu_book3s, sre, eaddr, primary);
+	if (kvm_is_error_hva(ptegp)) {
+		printk(KERN_INFO "KVM: Invalid PTEG!\n");
+		goto no_page_found;
+	}
+
+	ptem = kvmppc_mmu_book3s_32_get_ptem(sre, eaddr, primary);
+
+	if(copy_from_user(pteg, (void __user *)ptegp, sizeof(pteg))) {
+		printk(KERN_ERR "KVM: Can't copy data from 0x%lx!\n", ptegp);
+		goto no_page_found;
+	}
+
+	for (i=0; i<16; i+=2) {
+		if (ptem == pteg[i]) {
+			u8 pp;
+
+			pte->raddr = (pteg[i+1] & ~(0xFFFULL)) | (eaddr & 0xFFF);
+			pp = pteg[i+1] & 3;
+
+			if ((sre->Kp &&  (vcpu->arch.msr & MSR_PR)) ||
+			    (sre->Ks && !(vcpu->arch.msr & MSR_PR)))
+				pp |= 4;
+
+			pte->may_write = false;
+			pte->may_read = false;
+			pte->may_execute = true;
+			switch (pp) {
+				case 0:
+				case 1:
+				case 2:
+				case 6:
+					pte->may_write = true;
+				case 3:
+				case 5:
+				case 7:
+					pte->may_read = true;
+					break;
+			}
+
+			if ( !pte->may_read )
+				continue;
+
+			dprintk_pte("MMU: Found PTE -> %x %x - %x\n",
+				    pteg[i], pteg[i+1], pp);
+			found = 1;
+			break;
+		}
+	}
+
+	/* Update PTE C and A bits, so the guest's swapper knows we used the
+	   page */
+	if (found) {
+		u32 oldpte = pteg[i+1];
+
+		if (pte->may_read)
+			pteg[i+1] |= PTEG_FLAG_ACCESSED;
+		if (pte->may_write)
+			pteg[i+1] |= PTEG_FLAG_DIRTY;
+		else
+			dprintk_pte("KVM: Mapping read-only page!\n");
+
+		/* Write back into the PTEG */
+		if (pteg[i+1] != oldpte)
+			copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
+
+		return 0;
+	}
+
+no_page_found:
+
+	if (check_debug_ip(vcpu)) {
+		dprintk_pte("KVM MMU: No PTE found (sdr1=0x%llx ptegp=0x%lx)\n",
+			    to_book3s(vcpu)->sdr1, ptegp);
+		for (i=0; i<16; i+=2) {
+			dprintk_pte("   %02d: 0x%x - 0x%x (0x%llx)\n",
+				    i, pteg[i], pteg[i+1], ptem);
+		}
+	}
+
+	return -ENOENT;
+}
+
+static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
+				      struct kvmppc_pte *pte, bool data)
+{
+	int r;
+
+	pte->eaddr = eaddr;
+	r = kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, pte, data);
+	if (r < 0)
+	       r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, true);
+	if (r < 0)
+	       r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, false);
+
+	return r;
+}
+
+
+static u32 kvmppc_mmu_book3s_32_mfsrin(struct kvm_vcpu *vcpu, u32 srnum)
+{
+	return to_book3s(vcpu)->sr[srnum].raw;
+}
+
+static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum,
+					ulong value)
+{
+	struct kvmppc_sr *sre;
+
+	sre = &to_book3s(vcpu)->sr[srnum];
+
+	/* Flush any left-over shadows from the previous SR */
+
+	/* XXX Not necessary? */
+	/* kvmppc_mmu_pte_flush(vcpu, ((u64)sre->vsid) << 28, 0xf0000000ULL); */
+
+	/* And then put in the new SR */
+	sre->raw = value;
+	sre->vsid = (value & 0x0fffffff);
+	sre->Ks = (value & 0x40000000) ? true : false;
+	sre->Kp = (value & 0x20000000) ? true : false;
+	sre->nx = (value & 0x10000000) ? true : false;
+
+	/* Map the new segment */
+	kvmppc_mmu_map_segment(vcpu, srnum << SID_SHIFT);
+}
+
+static void kvmppc_mmu_book3s_32_tlbie(struct kvm_vcpu *vcpu, ulong ea, bool large)
+{
+	kvmppc_mmu_pte_flush(vcpu, ea, ~0xFFFULL);
+}
+
+static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, u64 esid,
+					     u64 *vsid)
+{
+	/* In case we only have one of MSR_IR or MSR_DR set, let's put
+	   that in the real-mode context (and hope RM doesn't access
+	   high memory) */
+	switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+	case 0:
+		*vsid = (VSID_REAL >> 16) | esid;
+		break;
+	case MSR_IR:
+		*vsid = (VSID_REAL_IR >> 16) | esid;
+		break;
+	case MSR_DR:
+		*vsid = (VSID_REAL_DR >> 16) | esid;
+		break;
+	case MSR_DR|MSR_IR:
+	{
+		ulong ea;
+		ea = esid << SID_SHIFT;
+		*vsid = find_sr(to_book3s(vcpu), ea)->vsid;
+		break;
+	}
+	default:
+		BUG();
+	}
+
+	return 0;
+}
+
+static bool kvmppc_mmu_book3s_32_is_dcbz32(struct kvm_vcpu *vcpu)
+{
+	return true;
+}
+
+
+void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_mmu *mmu = &vcpu->arch.mmu;
+
+	mmu->mtsrin = kvmppc_mmu_book3s_32_mtsrin;
+	mmu->mfsrin = kvmppc_mmu_book3s_32_mfsrin;
+	mmu->xlate = kvmppc_mmu_book3s_32_xlate;
+	mmu->reset_msr = kvmppc_mmu_book3s_32_reset_msr;
+	mmu->tlbie = kvmppc_mmu_book3s_32_tlbie;
+	mmu->esid_to_vsid = kvmppc_mmu_book3s_32_esid_to_vsid;
+	mmu->ea_to_vp = kvmppc_mmu_book3s_32_ea_to_vp;
+	mmu->is_dcbz32 = kvmppc_mmu_book3s_32_is_dcbz32;
+
+	mmu->slbmte = NULL;
+	mmu->slbmfee = NULL;
+	mmu->slbmfev = NULL;
+	mmu->slbie = NULL;
+	mmu->slbia = NULL;
+}

From c215c6e49fef6c79a5b98f66f11cc6b1e395cb59 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:14 +0000
Subject: [PATCH 051/151] Add book3s_64 specific opcode emulation

There are generic parts of PowerPC that can be shared across all
implementations and specific parts that only apply to BookE or desktop PPCs.

This patch adds emulation for desktop specific opcodes that don't apply
to BookE CPUs.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/book3s_64_emulate.c | 337 +++++++++++++++++++++++++++
 1 file changed, 337 insertions(+)
 create mode 100644 arch/powerpc/kvm/book3s_64_emulate.c

diff --git a/arch/powerpc/kvm/book3s_64_emulate.c b/arch/powerpc/kvm/book3s_64_emulate.c
new file mode 100644
index 000000000000..c343e67306e0
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_emulate.c
@@ -0,0 +1,337 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <asm/kvm_ppc.h>
+#include <asm/disassemble.h>
+#include <asm/kvm_book3s.h>
+#include <asm/reg.h>
+
+#define OP_19_XOP_RFID		18
+#define OP_19_XOP_RFI		50
+
+#define OP_31_XOP_MFMSR		83
+#define OP_31_XOP_MTMSR		146
+#define OP_31_XOP_MTMSRD	178
+#define OP_31_XOP_MTSRIN	242
+#define OP_31_XOP_TLBIEL	274
+#define OP_31_XOP_TLBIE		306
+#define OP_31_XOP_SLBMTE	402
+#define OP_31_XOP_SLBIE		434
+#define OP_31_XOP_SLBIA		498
+#define OP_31_XOP_MFSRIN	659
+#define OP_31_XOP_SLBMFEV	851
+#define OP_31_XOP_EIOIO		854
+#define OP_31_XOP_SLBMFEE	915
+
+/* DCBZ is actually 1014, but we patch it to 1010 so we get a trap */
+#define OP_31_XOP_DCBZ		1010
+
+int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                           unsigned int inst, int *advance)
+{
+	int emulated = EMULATE_DONE;
+
+	switch (get_op(inst)) {
+	case 19:
+		switch (get_xop(inst)) {
+		case OP_19_XOP_RFID:
+		case OP_19_XOP_RFI:
+			vcpu->arch.pc = vcpu->arch.srr0;
+			kvmppc_set_msr(vcpu, vcpu->arch.srr1);
+			*advance = 0;
+			break;
+
+		default:
+			emulated = EMULATE_FAIL;
+			break;
+		}
+		break;
+	case 31:
+		switch (get_xop(inst)) {
+		case OP_31_XOP_MFMSR:
+			vcpu->arch.gpr[get_rt(inst)] = vcpu->arch.msr;
+			break;
+		case OP_31_XOP_MTMSRD:
+		{
+			ulong rs = vcpu->arch.gpr[get_rs(inst)];
+			if (inst & 0x10000) {
+				vcpu->arch.msr &= ~(MSR_RI | MSR_EE);
+				vcpu->arch.msr |= rs & (MSR_RI | MSR_EE);
+			} else
+				kvmppc_set_msr(vcpu, rs);
+			break;
+		}
+		case OP_31_XOP_MTMSR:
+			kvmppc_set_msr(vcpu, vcpu->arch.gpr[get_rs(inst)]);
+			break;
+		case OP_31_XOP_MFSRIN:
+		{
+			int srnum;
+
+			srnum = (vcpu->arch.gpr[get_rb(inst)] >> 28) & 0xf;
+			if (vcpu->arch.mmu.mfsrin) {
+				u32 sr;
+				sr = vcpu->arch.mmu.mfsrin(vcpu, srnum);
+				vcpu->arch.gpr[get_rt(inst)] = sr;
+			}
+			break;
+		}
+		case OP_31_XOP_MTSRIN:
+			vcpu->arch.mmu.mtsrin(vcpu,
+				(vcpu->arch.gpr[get_rb(inst)] >> 28) & 0xf,
+				vcpu->arch.gpr[get_rs(inst)]);
+			break;
+		case OP_31_XOP_TLBIE:
+		case OP_31_XOP_TLBIEL:
+		{
+			bool large = (inst & 0x00200000) ? true : false;
+			ulong addr = vcpu->arch.gpr[get_rb(inst)];
+			vcpu->arch.mmu.tlbie(vcpu, addr, large);
+			break;
+		}
+		case OP_31_XOP_EIOIO:
+			break;
+		case OP_31_XOP_SLBMTE:
+			if (!vcpu->arch.mmu.slbmte)
+				return EMULATE_FAIL;
+
+			vcpu->arch.mmu.slbmte(vcpu, vcpu->arch.gpr[get_rs(inst)],
+						vcpu->arch.gpr[get_rb(inst)]);
+			break;
+		case OP_31_XOP_SLBIE:
+			if (!vcpu->arch.mmu.slbie)
+				return EMULATE_FAIL;
+
+			vcpu->arch.mmu.slbie(vcpu, vcpu->arch.gpr[get_rb(inst)]);
+			break;
+		case OP_31_XOP_SLBIA:
+			if (!vcpu->arch.mmu.slbia)
+				return EMULATE_FAIL;
+
+			vcpu->arch.mmu.slbia(vcpu);
+			break;
+		case OP_31_XOP_SLBMFEE:
+			if (!vcpu->arch.mmu.slbmfee) {
+				emulated = EMULATE_FAIL;
+			} else {
+				ulong t, rb;
+
+				rb = vcpu->arch.gpr[get_rb(inst)];
+				t = vcpu->arch.mmu.slbmfee(vcpu, rb);
+				vcpu->arch.gpr[get_rt(inst)] = t;
+			}
+			break;
+		case OP_31_XOP_SLBMFEV:
+			if (!vcpu->arch.mmu.slbmfev) {
+				emulated = EMULATE_FAIL;
+			} else {
+				ulong t, rb;
+
+				rb = vcpu->arch.gpr[get_rb(inst)];
+				t = vcpu->arch.mmu.slbmfev(vcpu, rb);
+				vcpu->arch.gpr[get_rt(inst)] = t;
+			}
+			break;
+		case OP_31_XOP_DCBZ:
+		{
+			ulong rb =  vcpu->arch.gpr[get_rb(inst)];
+			ulong ra = 0;
+			ulong addr;
+			u32 zeros[8] = { 0, 0, 0, 0, 0, 0, 0, 0 };
+
+			if (get_ra(inst))
+				ra = vcpu->arch.gpr[get_ra(inst)];
+
+			addr = (ra + rb) & ~31ULL;
+			if (!(vcpu->arch.msr & MSR_SF))
+				addr &= 0xffffffff;
+
+			if (kvmppc_st(vcpu, addr, 32, zeros)) {
+				vcpu->arch.dear = addr;
+				vcpu->arch.fault_dear = addr;
+				to_book3s(vcpu)->dsisr = DSISR_PROTFAULT |
+						      DSISR_ISSTORE;
+				kvmppc_book3s_queue_irqprio(vcpu,
+					BOOK3S_INTERRUPT_DATA_STORAGE);
+				kvmppc_mmu_pte_flush(vcpu, addr, ~0xFFFULL);
+			}
+
+			break;
+		}
+		default:
+			emulated = EMULATE_FAIL;
+		}
+		break;
+	default:
+		emulated = EMULATE_FAIL;
+	}
+
+	return emulated;
+}
+
+static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u64 val)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+	struct kvmppc_bat *bat;
+
+	switch (sprn) {
+	case SPRN_IBAT0U ... SPRN_IBAT3L:
+		bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT0U) / 2];
+		break;
+	case SPRN_IBAT4U ... SPRN_IBAT7L:
+		bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT4U) / 2];
+		break;
+	case SPRN_DBAT0U ... SPRN_DBAT3L:
+		bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT0U) / 2];
+		break;
+	case SPRN_DBAT4U ... SPRN_DBAT7L:
+		bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT4U) / 2];
+		break;
+	default:
+		BUG();
+	}
+
+	if (!(sprn % 2)) {
+		/* Upper BAT */
+		u32 bl = (val >> 2) & 0x7ff;
+		bat->bepi_mask = (~bl << 17);
+		bat->bepi = val & 0xfffe0000;
+		bat->vs = (val & 2) ? 1 : 0;
+		bat->vp = (val & 1) ? 1 : 0;
+	} else {
+		/* Lower BAT */
+		bat->brpn = val & 0xfffe0000;
+		bat->wimg = (val >> 3) & 0xf;
+		bat->pp = val & 3;
+	}
+}
+
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+{
+	int emulated = EMULATE_DONE;
+
+	switch (sprn) {
+	case SPRN_SDR1:
+		to_book3s(vcpu)->sdr1 = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_DSISR:
+		to_book3s(vcpu)->dsisr = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_DAR:
+		vcpu->arch.dear = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_HIOR:
+		to_book3s(vcpu)->hior = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_IBAT0U ... SPRN_IBAT3L:
+	case SPRN_IBAT4U ... SPRN_IBAT7L:
+	case SPRN_DBAT0U ... SPRN_DBAT3L:
+	case SPRN_DBAT4U ... SPRN_DBAT7L:
+		kvmppc_write_bat(vcpu, sprn, vcpu->arch.gpr[rs]);
+		/* BAT writes happen so rarely that we're ok to flush
+		 * everything here */
+		kvmppc_mmu_pte_flush(vcpu, 0, 0);
+		break;
+	case SPRN_HID0:
+		to_book3s(vcpu)->hid[0] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_HID1:
+		to_book3s(vcpu)->hid[1] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_HID2:
+		to_book3s(vcpu)->hid[2] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_HID4:
+		to_book3s(vcpu)->hid[4] = vcpu->arch.gpr[rs];
+		break;
+	case SPRN_HID5:
+		to_book3s(vcpu)->hid[5] = vcpu->arch.gpr[rs];
+		/* guest HID5 set can change is_dcbz32 */
+		if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
+		    (mfmsr() & MSR_HV))
+			vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
+		break;
+	case SPRN_ICTC:
+	case SPRN_THRM1:
+	case SPRN_THRM2:
+	case SPRN_THRM3:
+	case SPRN_CTRLF:
+	case SPRN_CTRLT:
+		break;
+	default:
+		printk(KERN_INFO "KVM: invalid SPR write: %d\n", sprn);
+#ifndef DEBUG_SPR
+		emulated = EMULATE_FAIL;
+#endif
+		break;
+	}
+
+	return emulated;
+}
+
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+{
+	int emulated = EMULATE_DONE;
+
+	switch (sprn) {
+	case SPRN_SDR1:
+		vcpu->arch.gpr[rt] = to_book3s(vcpu)->sdr1;
+		break;
+	case SPRN_DSISR:
+		vcpu->arch.gpr[rt] = to_book3s(vcpu)->dsisr;
+		break;
+	case SPRN_DAR:
+		vcpu->arch.gpr[rt] = vcpu->arch.dear;
+		break;
+	case SPRN_HIOR:
+		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hior;
+		break;
+	case SPRN_HID0:
+		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[0];
+		break;
+	case SPRN_HID1:
+		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[1];
+		break;
+	case SPRN_HID2:
+		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[2];
+		break;
+	case SPRN_HID4:
+		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[4];
+		break;
+	case SPRN_HID5:
+		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[5];
+		break;
+	case SPRN_THRM1:
+	case SPRN_THRM2:
+	case SPRN_THRM3:
+	case SPRN_CTRLF:
+	case SPRN_CTRLT:
+		vcpu->arch.gpr[rt] = 0;
+		break;
+	default:
+		printk(KERN_INFO "KVM: invalid SPR read: %d\n", sprn);
+#ifndef DEBUG_SPR
+		emulated = EMULATE_FAIL;
+#endif
+		break;
+	}
+
+	return emulated;
+}
+

From 9a7a9b09fee8487003df012d9af4b227b3661e4d Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:15 +0000
Subject: [PATCH 052/151] Add mfdec emulation

We support setting the DEC to a certain value right now. Doing that basically
triggers the CPU local timer.

But there's also an mfdec command that enabled the OS to read the decrementor.

This is required at least by all desktop and server PowerPC Linux kernels. It
can't really hurt to allow embedded ones to do it as well though.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/emulate.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 7737146af3fb..50d411d946eb 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -66,12 +66,14 @@
 
 void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 {
+	unsigned long nr_jiffies;
+
 	if (vcpu->arch.tcr & TCR_DIE) {
 		/* The decrementer ticks at the same rate as the timebase, so
 		 * that's how we convert the guest DEC value to the number of
 		 * host ticks. */
-		unsigned long nr_jiffies;
 
+		vcpu->arch.dec_jiffies = mftb();
 		nr_jiffies = vcpu->arch.dec / tb_ticks_per_jiffy;
 		mod_timer(&vcpu->arch.dec_timer,
 		          get_jiffies_64() + nr_jiffies);
@@ -211,6 +213,15 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			/* Note: SPRG4-7 are user-readable, so we don't get
 			 * a trap. */
 
+			case SPRN_DEC:
+			{
+				u64 jd = mftb() - vcpu->arch.dec_jiffies;
+				vcpu->arch.gpr[rt] = vcpu->arch.dec - jd;
+#ifdef DEBUG_EMUL
+				printk(KERN_INFO "mfDEC: %x - %llx = %lx\n", vcpu->arch.dec, jd, vcpu->arch.gpr[rt]);
+#endif
+				break;
+			}
 			default:
 				emulated = kvmppc_core_emulate_mfspr(vcpu, sprn, rt);
 				if (emulated == EMULATE_FAIL) {

From 513579e3a391a3874c478a8493080822069976e8 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:16 +0000
Subject: [PATCH 053/151] Add desktop PowerPC specific emulation

Little opcodes behave differently on desktop and embedded PowerPC cores.
In order to reflect those differences, let's add some #ifdef code to emulate.c.

We could probably also handle them in the core specific emulation files, but I
would prefer to reuse as much code as possible.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/emulate.c | 49 ++++++++++++++++++++++++++++++--------
 1 file changed, 39 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 50d411d946eb..1ec5e07b81eb 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -32,6 +32,7 @@
 #include "trace.h"
 
 #define OP_TRAP 3
+#define OP_TRAP_64 2
 
 #define OP_31_XOP_LWZX      23
 #define OP_31_XOP_LBZX      87
@@ -64,16 +65,36 @@
 #define OP_STH  44
 #define OP_STHU 45
 
+#ifdef CONFIG_PPC64
+static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu)
+{
+	return 1;
+}
+#else
+static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.tcr & TCR_DIE;
+}
+#endif
+
 void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr_jiffies;
 
-	if (vcpu->arch.tcr & TCR_DIE) {
+#ifdef CONFIG_PPC64
+	/* POWER4+ triggers a dec interrupt if the value is < 0 */
+	if (vcpu->arch.dec & 0x80000000) {
+		del_timer(&vcpu->arch.dec_timer);
+		kvmppc_core_queue_dec(vcpu);
+		return;
+	}
+#endif
+	if (kvmppc_dec_enabled(vcpu)) {
 		/* The decrementer ticks at the same rate as the timebase, so
 		 * that's how we convert the guest DEC value to the number of
 		 * host ticks. */
 
-		vcpu->arch.dec_jiffies = mftb();
+		vcpu->arch.dec_jiffies = get_tb();
 		nr_jiffies = vcpu->arch.dec / tb_ticks_per_jiffy;
 		mod_timer(&vcpu->arch.dec_timer,
 		          get_jiffies_64() + nr_jiffies);
@@ -113,9 +134,15 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	/* this default type might be overwritten by subcategories */
 	kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS);
 
+	pr_debug(KERN_INFO "Emulating opcode %d / %d\n", get_op(inst), get_xop(inst));
+
 	switch (get_op(inst)) {
 	case OP_TRAP:
+#ifdef CONFIG_PPC64
+	case OP_TRAP_64:
+#else
 		vcpu->arch.esr |= ESR_PTR;
+#endif
 		kvmppc_core_queue_program(vcpu);
 		advance = 0;
 		break;
@@ -190,17 +217,19 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			case SPRN_SRR1:
 				vcpu->arch.gpr[rt] = vcpu->arch.srr1; break;
 			case SPRN_PVR:
-				vcpu->arch.gpr[rt] = mfspr(SPRN_PVR); break;
+				vcpu->arch.gpr[rt] = vcpu->arch.pvr; break;
 			case SPRN_PIR:
-				vcpu->arch.gpr[rt] = mfspr(SPRN_PIR); break;
+				vcpu->arch.gpr[rt] = vcpu->vcpu_id; break;
+			case SPRN_MSSSR0:
+				vcpu->arch.gpr[rt] = 0; break;
 
 			/* Note: mftb and TBRL/TBWL are user-accessible, so
 			 * the guest can always access the real TB anyways.
 			 * In fact, we probably will never see these traps. */
 			case SPRN_TBWL:
-				vcpu->arch.gpr[rt] = mftbl(); break;
+				vcpu->arch.gpr[rt] = get_tb() >> 32; break;
 			case SPRN_TBWU:
-				vcpu->arch.gpr[rt] = mftbu(); break;
+				vcpu->arch.gpr[rt] = get_tb(); break;
 
 			case SPRN_SPRG0:
 				vcpu->arch.gpr[rt] = vcpu->arch.sprg0; break;
@@ -215,11 +244,9 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 			case SPRN_DEC:
 			{
-				u64 jd = mftb() - vcpu->arch.dec_jiffies;
+				u64 jd = get_tb() - vcpu->arch.dec_jiffies;
 				vcpu->arch.gpr[rt] = vcpu->arch.dec - jd;
-#ifdef DEBUG_EMUL
-				printk(KERN_INFO "mfDEC: %x - %llx = %lx\n", vcpu->arch.dec, jd, vcpu->arch.gpr[rt]);
-#endif
+				pr_debug(KERN_INFO "mfDEC: %x - %llx = %lx\n", vcpu->arch.dec, jd, vcpu->arch.gpr[rt]);
 				break;
 			}
 			default:
@@ -271,6 +298,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			case SPRN_TBWL: break;
 			case SPRN_TBWU: break;
 
+			case SPRN_MSSSR0: break;
+
 			case SPRN_DEC:
 				vcpu->arch.dec = vcpu->arch.gpr[rs];
 				kvmppc_emulate_dec(vcpu);

From 842f2fedcdc4f9ea8e6ac5b2222971c31666dd3e Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:17 +0000
Subject: [PATCH 054/151] Make head_64.S aware of KVM real mode code

We need to run some KVM trampoline code in real mode. Unfortunately, real mode
only covers 8MB on Cell so we need to squeeze ourselves as low as possible.

Also, we need to trap interrupts to get us back from guest state to host state
without telling Linux about it.

This patch adds interrupt traps and includes the KVM code that requires real
mode in the real mode parts of Linux.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/exception-64s.h | 2 ++
 arch/powerpc/kernel/exceptions-64s.S     | 8 ++++++++
 arch/powerpc/kernel/head_64.S            | 7 +++++++
 3 files changed, 17 insertions(+)

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index a98653b26231..57c400071995 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -147,6 +147,7 @@
 	.globl label##_pSeries;				\
 label##_pSeries:					\
 	HMT_MEDIUM;					\
+	DO_KVM	n;					\
 	mtspr	SPRN_SPRG_SCRATCH0,r13;		/* save r13 */	\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common)
 
@@ -170,6 +171,7 @@ label##_pSeries:					\
 	.globl label##_pSeries;						\
 label##_pSeries:							\
 	HMT_MEDIUM;							\
+	DO_KVM	n;							\
 	mtspr	SPRN_SPRG_SCRATCH0,r13;	/* save r13 */			\
 	mfspr	r13,SPRN_SPRG_PACA;	/* get paca address into r13 */	\
 	std	r9,PACA_EXGEN+EX_R9(r13);	/* save r9, r10 */	\
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 1808876edcc9..fc3ead066cec 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -41,6 +41,7 @@ __start_interrupts:
 	. = 0x200
 _machine_check_pSeries:
 	HMT_MEDIUM
+	DO_KVM	0x200
 	mtspr	SPRN_SPRG_SCRATCH0,r13		/* save r13 */
 	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common)
 
@@ -48,6 +49,7 @@ _machine_check_pSeries:
 	.globl data_access_pSeries
 data_access_pSeries:
 	HMT_MEDIUM
+	DO_KVM	0x300
 	mtspr	SPRN_SPRG_SCRATCH0,r13
 BEGIN_FTR_SECTION
 	mfspr	r13,SPRN_SPRG_PACA
@@ -77,6 +79,7 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_SLB)
 	.globl data_access_slb_pSeries
 data_access_slb_pSeries:
 	HMT_MEDIUM
+	DO_KVM	0x380
 	mtspr	SPRN_SPRG_SCRATCH0,r13
 	mfspr	r13,SPRN_SPRG_PACA		/* get paca address into r13 */
 	std	r3,PACA_EXSLB+EX_R3(r13)
@@ -115,6 +118,7 @@ data_access_slb_pSeries:
 	.globl instruction_access_slb_pSeries
 instruction_access_slb_pSeries:
 	HMT_MEDIUM
+	DO_KVM	0x480
 	mtspr	SPRN_SPRG_SCRATCH0,r13
 	mfspr	r13,SPRN_SPRG_PACA		/* get paca address into r13 */
 	std	r3,PACA_EXSLB+EX_R3(r13)
@@ -154,6 +158,7 @@ instruction_access_slb_pSeries:
 	.globl	system_call_pSeries
 system_call_pSeries:
 	HMT_MEDIUM
+	DO_KVM	0xc00
 BEGIN_FTR_SECTION
 	cmpdi	r0,0x1ebe
 	beq-	1f
@@ -186,12 +191,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	 * trickery is thus necessary
 	 */
 	. = 0xf00
+	DO_KVM	0xf00
 	b	performance_monitor_pSeries
 
 	. = 0xf20
+	DO_KVM	0xf20
 	b	altivec_unavailable_pSeries
 
 	. = 0xf40
+	DO_KVM	0xf40
 	b	vsx_unavailable_pSeries
 
 #ifdef CONFIG_CBE_RAS
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index c38afdb45d7b..925807488022 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -37,6 +37,7 @@
 #include <asm/firmware.h>
 #include <asm/page_64.h>
 #include <asm/irqflags.h>
+#include <asm/kvm_book3s_64_asm.h>
 
 /* The physical memory is layed out such that the secondary processor
  * spin code sits at 0x0000...0x00ff. On server, the vectors follow
@@ -165,6 +166,12 @@ exception_marker:
 #include "exceptions-64s.S"
 #endif
 
+/* KVM trampoline code needs to be close to the interrupt handlers */
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#include "../kvm/book3s_64_rmhandlers.S"
+#endif
+
 _GLOBAL(generic_secondary_thread_init)
 	mr	r24,r3
 

From 62908905b2fd98c11bd472c1e617d35eff33fc84 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:18 +0000
Subject: [PATCH 055/151] Add Book3s_64 offsets to asm-offsets.c

We need to access some VCPU fields from assembly code. In order to get
the proper offsets, we have to define them in asm-offsets.c.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/asm-offsets.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0812b0f414bb..aba3ea64661e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -398,6 +398,19 @@ int main(void)
 	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
 	DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
 	DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
+
+	/* book3s_64 */
+#ifdef CONFIG_PPC64
+	DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr));
+	DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip));
+	DEFINE(VCPU_HOST_R2, offsetof(struct kvm_vcpu, arch.host_r2));
+	DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr));
+	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
+	DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem));
+	DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter));
+	DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
+	DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
+#endif
 #endif
 #ifdef CONFIG_44x
 	DEFINE(PGD_T_LOG2, PGD_T_LOG2);

From 4ab79aa801b6b4f2e2fb508d6107cdd9320d682d Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:19 +0000
Subject: [PATCH 056/151] Export symbols for KVM module

We want to be able to build KVM as a module. To enable us doing so, we
need some more exports from core Linux parts.

This patch exports all functions and variables that are required for KVM.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/time.c      | 1 +
 arch/powerpc/mm/hash_utils_64.c | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 92dc844299b6..e05f6af64353 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -268,6 +268,7 @@ void account_system_vtime(struct task_struct *tsk)
 	per_cpu(cputime_scaled_last_delta, smp_processor_id()) = deltascaled;
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL_GPL(account_system_vtime);
 
 /*
  * Transfer the user and system times accumulated in the paca
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index fa251f8c2f82..6810128aba30 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -92,6 +92,7 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
 struct hash_pte *htab_address;
 unsigned long htab_size_bytes;
 unsigned long htab_hash_mask;
+EXPORT_SYMBOL_GPL(htab_hash_mask);
 int mmu_linear_psize = MMU_PAGE_4K;
 int mmu_virtual_psize = MMU_PAGE_4K;
 int mmu_vmalloc_psize = MMU_PAGE_4K;
@@ -102,6 +103,7 @@ int mmu_io_psize = MMU_PAGE_4K;
 int mmu_kernel_ssize = MMU_SEGSIZE_256M;
 int mmu_highuser_ssize = MMU_SEGSIZE_256M;
 u16 mmu_slb_size = 64;
+EXPORT_SYMBOL_GPL(mmu_slb_size);
 #ifdef CONFIG_HUGETLB_PAGE
 unsigned int HPAGE_SHIFT;
 #endif

From e85a47106abb928e048d89d7fa48f982fcb018aa Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Nov 2009 12:02:30 +0000
Subject: [PATCH 057/151] Split init_new_context and destroy_context

For KVM we need to allocate a new context id, but don't really care about
all the mm context around it.

So let's split the alloc and destroy functions for the context id, so we can
grab one without allocating an mm context.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/mmu_context.h |  2 ++
 arch/powerpc/mm/mmu_context_hash64.c   | 24 +++++++++++++++++++++---
 2 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index b34e94d94435..26383e0778aa 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -23,6 +23,8 @@ extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
 extern void set_context(unsigned long id, pgd_t *pgd);
 
 #ifdef CONFIG_PPC_BOOK3S_64
+extern int __init_new_context(void);
+extern void __destroy_context(int context_id);
 static inline void mmu_context_init(void) { }
 #else
 extern void mmu_context_init(void);
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index dbeb86ac90cd..b9e4cc2c2057 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -18,6 +18,7 @@
 #include <linux/mm.h>
 #include <linux/spinlock.h>
 #include <linux/idr.h>
+#include <linux/module.h>
 
 #include <asm/mmu_context.h>
 
@@ -32,7 +33,7 @@ static DEFINE_IDR(mmu_context_idr);
 #define NO_CONTEXT	0
 #define MAX_CONTEXT	((1UL << 19) - 1)
 
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+int __init_new_context(void)
 {
 	int index;
 	int err;
@@ -57,6 +58,18 @@ again:
 		return -ENOMEM;
 	}
 
+	return index;
+}
+EXPORT_SYMBOL_GPL(__init_new_context);
+
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+	int index;
+
+	index = __init_new_context();
+	if (index < 0)
+		return index;
+
 	/* The old code would re-promote on fork, we don't do that
 	 * when using slices as it could cause problem promoting slices
 	 * that have been forced down to 4K
@@ -68,11 +81,16 @@ again:
 	return 0;
 }
 
-void destroy_context(struct mm_struct *mm)
+void __destroy_context(int context_id)
 {
 	spin_lock(&mmu_context_lock);
-	idr_remove(&mmu_context_idr, mm->context.id);
+	idr_remove(&mmu_context_idr, context_id);
 	spin_unlock(&mmu_context_lock);
+}
+EXPORT_SYMBOL_GPL(__destroy_context);
 
+void destroy_context(struct mm_struct *mm)
+{
+	__destroy_context(mm->context.id);
 	mm->context.id = NO_CONTEXT;
 }

From 0186fd0373d9684145046a60c688b913cb9bd181 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:21 +0000
Subject: [PATCH 058/151] Export KVM symbols for module

To be able to keep KVM as module, we need to export the SLB trampoline
addresses to the module, so it knows where to jump to.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/book3s_64_exports.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)
 create mode 100644 arch/powerpc/kvm/book3s_64_exports.c

diff --git a/arch/powerpc/kvm/book3s_64_exports.c b/arch/powerpc/kvm/book3s_64_exports.c
new file mode 100644
index 000000000000..5b2db38ed86c
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_exports.c
@@ -0,0 +1,24 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * 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, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <linux/module.h>
+#include <asm/kvm_book3s.h>
+
+EXPORT_SYMBOL_GPL(kvmppc_trampoline_enter);
+EXPORT_SYMBOL_GPL(kvmppc_trampoline_lowmem);

From 4b7ae55df3621dd9eef56a6fde953ec9c73ac596 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:22 +0000
Subject: [PATCH 059/151] Add fields to PACA

For KVM we need to store some information in the PACA, so we
need to extend it.

This patch adds KVM SLB shadow related entries to the PACA and
a field that indicates if we're inside a guest.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/paca.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 7d8514ceceae..5e9b4ef71415 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -129,6 +129,15 @@ struct paca_struct {
 	u64 system_time;		/* accumulated system TB ticks */
 	u64 startpurr;			/* PURR/TB value snapshot */
 	u64 startspurr;			/* SPURR value snapshot */
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+	struct  {
+		u64     esid;
+		u64     vsid;
+	} kvm_slb[64];			/* guest SLB */
+	u8 kvm_slb_max;			/* highest used guest slb entry */
+	u8 kvm_in_guest;		/* are we inside the guest? */
+#endif
 };
 
 extern struct paca_struct paca[];

From 55c758840a2ab0aa31530aca982dd5e9281a169c Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:23 +0000
Subject: [PATCH 060/151] Export new PACA constants in asm-offsets

In order to access fields in the PACA from assembly code, we need
to generate offsets using asm-offsets.c.

So let's add the new PACA related bits, we just introduced!

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/asm-offsets.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index aba3ea64661e..e2e2082acf29 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -190,6 +190,11 @@ int main(void)
 	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
 	DEFINE(PACA_DATA_OFFSET, offsetof(struct paca_struct, data_offset));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+	DEFINE(PACA_KVM_IN_GUEST, offsetof(struct paca_struct, kvm_in_guest));
+	DEFINE(PACA_KVM_SLB, offsetof(struct paca_struct, kvm_slb));
+	DEFINE(PACA_KVM_SLB_MAX, offsetof(struct paca_struct, kvm_slb_max));
+#endif
 #endif /* CONFIG_PPC64 */
 
 	/* RTAS */

From c4f9c779f1019c7d5c61961a7c0aaaf1420d8f90 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:24 +0000
Subject: [PATCH 061/151] Include Book3s_64 target in buildsystem

Now we have everything in place to be able to build KVM, so let's add it
as config option and in the Makefile.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/Kconfig  | 17 +++++++++++++++++
 arch/powerpc/kvm/Makefile | 27 +++++++++++++++++++++++----
 2 files changed, 40 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index c29926846613..07703f72330e 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -21,6 +21,23 @@ config KVM
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 
+config KVM_BOOK3S_64_HANDLER
+	bool
+
+config KVM_BOOK3S_64
+	tristate "KVM support for PowerPC book3s_64 processors"
+	depends on EXPERIMENTAL && PPC64
+	select KVM
+	select KVM_BOOK3S_64_HANDLER
+	---help---
+	  Support running unmodified book3s_64 and book3s_32 guest kernels
+	  in virtual machines on book3s_64 host processors.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
 config KVM_440
 	bool "KVM support for PowerPC 440 processors"
 	depends on EXPERIMENTAL && 44x
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 37655fe19f2f..56484d652377 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -12,26 +12,45 @@ CFLAGS_44x_tlb.o  := -I.
 CFLAGS_e500_tlb.o := -I.
 CFLAGS_emulate.o  := -I.
 
-kvm-objs := $(common-objs-y) powerpc.o emulate.o
+common-objs-y += powerpc.o emulate.o
 obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o
-obj-$(CONFIG_KVM) += kvm.o
+obj-$(CONFIG_KVM_BOOK3S_64_HANDLER) += book3s_64_exports.o
 
 AFLAGS_booke_interrupts.o := -I$(obj)
 
 kvm-440-objs := \
+	$(common-objs-y) \
 	booke.o \
 	booke_emulate.o \
 	booke_interrupts.o \
 	44x.o \
 	44x_tlb.o \
 	44x_emulate.o
-obj-$(CONFIG_KVM_440) += kvm-440.o
+kvm-objs-$(CONFIG_KVM_440) := $(kvm-440-objs)
 
 kvm-e500-objs := \
+	$(common-objs-y) \
 	booke.o \
 	booke_emulate.o \
 	booke_interrupts.o \
 	e500.o \
 	e500_tlb.o \
 	e500_emulate.o
-obj-$(CONFIG_KVM_E500) += kvm-e500.o
+kvm-objs-$(CONFIG_KVM_E500) := $(kvm-e500-objs)
+
+kvm-book3s_64-objs := \
+	$(common-objs-y) \
+	book3s.o \
+	book3s_64_emulate.o \
+	book3s_64_interrupts.o \
+	book3s_64_mmu_host.o \
+	book3s_64_mmu.o \
+	book3s_32_mmu.o
+kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-objs)
+
+kvm-objs := $(kvm-objs-m) $(kvm-objs-y)
+
+obj-$(CONFIG_KVM_440) += kvm.o
+obj-$(CONFIG_KVM_E500) += kvm.o
+obj-$(CONFIG_KVM_BOOK3S_64) += kvm.o
+

From 346b2762a72c60e97d2825e60423c84a869f3266 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:25 +0000
Subject: [PATCH 062/151] Fix trace.h

It looks like the variable "pc" is defined. At least the current code always
failed on me stating that "pc" is already defined somewhere else.

Let's use _pc instead, because that doesn't collide.

Is this the right approach? Does it break on 440 too? If not, why not?

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/trace.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index 67f219de0455..a8e840018052 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -12,8 +12,8 @@
  * Tracepoint for guest mode entry.
  */
 TRACE_EVENT(kvm_ppc_instr,
-	TP_PROTO(unsigned int inst, unsigned long pc, unsigned int emulate),
-	TP_ARGS(inst, pc, emulate),
+	TP_PROTO(unsigned int inst, unsigned long _pc, unsigned int emulate),
+	TP_ARGS(inst, _pc, emulate),
 
 	TP_STRUCT__entry(
 		__field(	unsigned int,	inst		)
@@ -23,7 +23,7 @@ TRACE_EVENT(kvm_ppc_instr,
 
 	TP_fast_assign(
 		__entry->inst		= inst;
-		__entry->pc		= pc;
+		__entry->pc		= _pc;
 		__entry->emulate	= emulate;
 	),
 

From c8240bd6f0b4b1b21ffd36dd44114d05c7afe0c0 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 30 Oct 2009 05:47:26 +0000
Subject: [PATCH 063/151] Use Little Endian for Dirty Bitmap

We currently use host endian long types to store information
in the dirty bitmap.

This works reasonably well on Little Endian targets, because the
u32 after the first contains the next 32 bits. On Big Endian this
breaks completely though, forcing us to be inventive here.

So Ben suggested to always use Little Endian, which looks reasonable.

We only have dirty bitmap implemented in Little Endian targets so far
and since PowerPC would be the first Big Endian platform, we can just
as well switch to Little Endian always with little effort without
breaking existing targets.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 virt/kvm/kvm_main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7495ce347344..cdca63917e77 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -48,6 +48,7 @@
 #include <asm/io.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
+#include <asm-generic/bitops/le.h>
 
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 #include "coalesced_mmio.h"
@@ -1665,8 +1666,8 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
 
 		/* avoid RMW */
-		if (!test_bit(rel_gfn, memslot->dirty_bitmap))
-			set_bit(rel_gfn, memslot->dirty_bitmap);
+		if (!generic_test_le_bit(rel_gfn, memslot->dirty_bitmap))
+			generic___set_le_bit(rel_gfn, memslot->dirty_bitmap);
 	}
 }
 

From 544c6761bb05a1dd19a39cb9bed096273f9bdb36 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Nov 2009 12:02:31 +0000
Subject: [PATCH 064/151] Use hrtimers for the decrementer

Following S390's good example we should use hrtimers for the decrementer too!
This patch converts the timer from the old mechanism to hrtimers.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/kvm_host.h |  6 ++++--
 arch/powerpc/kvm/emulate.c          | 18 +++++++++++-------
 arch/powerpc/kvm/powerpc.c          | 20 ++++++++++++++++++--
 3 files changed, 33 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 2cff5fe0cbe6..1201f62d0d73 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -21,7 +21,8 @@
 #define __POWERPC_KVM_HOST_H__
 
 #include <linux/mutex.h>
-#include <linux/timer.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
 #include <linux/types.h>
 #include <linux/kvm_types.h>
 #include <asm/kvm_asm.h>
@@ -250,7 +251,8 @@ struct kvm_vcpu_arch {
 
 	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
 
-	struct timer_list dec_timer;
+	struct hrtimer dec_timer;
+	struct tasklet_struct tasklet;
 	u64 dec_jiffies;
 	unsigned long pending_exceptions;
 
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 1ec5e07b81eb..4a9ac6640fad 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -18,7 +18,7 @@
  */
 
 #include <linux/jiffies.h>
-#include <linux/timer.h>
+#include <linux/hrtimer.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/kvm_host.h>
@@ -79,12 +79,13 @@ static int kvmppc_dec_enabled(struct kvm_vcpu *vcpu)
 
 void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 {
-	unsigned long nr_jiffies;
+	unsigned long dec_nsec;
 
+	pr_debug("mtDEC: %x\n", vcpu->arch.dec);
 #ifdef CONFIG_PPC64
 	/* POWER4+ triggers a dec interrupt if the value is < 0 */
 	if (vcpu->arch.dec & 0x80000000) {
-		del_timer(&vcpu->arch.dec_timer);
+		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
 		kvmppc_core_queue_dec(vcpu);
 		return;
 	}
@@ -94,12 +95,15 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 		 * that's how we convert the guest DEC value to the number of
 		 * host ticks. */
 
+		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
+		dec_nsec = vcpu->arch.dec;
+		dec_nsec *= 1000;
+		dec_nsec /= tb_ticks_per_usec;
+		hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
+			      HRTIMER_MODE_REL);
 		vcpu->arch.dec_jiffies = get_tb();
-		nr_jiffies = vcpu->arch.dec / tb_ticks_per_jiffy;
-		mod_timer(&vcpu->arch.dec_timer,
-		          get_jiffies_64() + nr_jiffies);
 	} else {
-		del_timer(&vcpu->arch.dec_timer);
+		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
 	}
 }
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index a06ecc3401fd..692c3709011e 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -23,6 +23,7 @@
 #include <linux/kvm_host.h>
 #include <linux/module.h>
 #include <linux/vmalloc.h>
+#include <linux/hrtimer.h>
 #include <linux/fs.h>
 #include <asm/cputable.h>
 #include <asm/uaccess.h>
@@ -208,10 +209,25 @@ static void kvmppc_decrementer_func(unsigned long data)
 	}
 }
 
+/*
+ * low level hrtimer wake routine. Because this runs in hardirq context
+ * we schedule a tasklet to do the real work.
+ */
+enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
+{
+	struct kvm_vcpu *vcpu;
+
+	vcpu = container_of(timer, struct kvm_vcpu, arch.dec_timer);
+	tasklet_schedule(&vcpu->arch.tasklet);
+
+	return HRTIMER_NORESTART;
+}
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
-	setup_timer(&vcpu->arch.dec_timer, kvmppc_decrementer_func,
-	            (unsigned long)vcpu);
+	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
+	tasklet_init(&vcpu->arch.tasklet, kvmppc_decrementer_func, (ulong)vcpu);
+	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
 
 	return 0;
 }

From 41c8c46bfe52488779e227b77222402579573ccf Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 5 Nov 2009 17:10:34 +1100
Subject: [PATCH 065/151] powerpc/kvm: Remove problematic BUILD_BUG_ON
 statement

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/timing.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h
index bb13b1f3cd5a..806ef67868bd 100644
--- a/arch/powerpc/kvm/timing.h
+++ b/arch/powerpc/kvm/timing.h
@@ -48,7 +48,11 @@ static inline void kvmppc_set_exit_type(struct kvm_vcpu *vcpu, int type) {}
 static inline void kvmppc_account_exit_stat(struct kvm_vcpu *vcpu, int type)
 {
 	/* type has to be known at build time for optimization */
+
+	/* The BUILD_BUG_ON below breaks in funny ways, commented out
+	 * for now ... -BenH
 	BUILD_BUG_ON(__builtin_constant_p(type));
+	*/
 	switch (type) {
 	case EXT_INTR_EXITS:
 		vcpu->stat.ext_intr_exits++;

From e0ea8b2c0677e6cc44a0e5b867be48867f91de5b Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Thu, 5 Nov 2009 17:17:12 +1100
Subject: [PATCH 066/151] powerpc/kvm: Fix non-modular build

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kvm/timing.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/powerpc/kvm/timing.c b/arch/powerpc/kvm/timing.c
index 2aa371e30079..70378551c0cc 100644
--- a/arch/powerpc/kvm/timing.c
+++ b/arch/powerpc/kvm/timing.c
@@ -23,6 +23,7 @@
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
+#include <linux/module.h>
 
 #include <asm/time.h>
 #include <asm-generic/div64.h>

From 98eaa0987afdcab0929dc205edb5c492cf66a370 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Thu, 27 Aug 2009 21:30:11 +0400
Subject: [PATCH 067/151] powerpc/qe: Increase MAX_QE_RISC to 4

MPC8569 CPUs have four QE RISCs, so we need to increase MAX_QE_RISC
constant, otherwise qe_upload_firmware() fails at sanity checking.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Acked-by: Timur Tabi <timur@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/sysdev/qe_lib/qe.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index 464271bea6c9..fff2701b90df 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -349,7 +349,7 @@ static int qe_sdma_init(void)
 }
 
 /* The maximum number of RISCs we support */
-#define MAX_QE_RISC     2
+#define MAX_QE_RISC     4
 
 /* Firmware information stored here for qe_get_firmware_info() */
 static struct qe_firmware_info qe_firmware_info;

From b79ddf2c2dba44114d150c7758002ef29e693086 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Thu, 27 Aug 2009 21:30:19 +0400
Subject: [PATCH 068/151] powerpc/qe: Add qe_upload_firmware() stub for non-QE
 builds

This is needed to avoid #ifdefs in MPC85xx suspend/resume code.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/include/asm/qe.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/powerpc/include/asm/qe.h b/arch/powerpc/include/asm/qe.h
index f388f0ab193f..28fee3b7887a 100644
--- a/arch/powerpc/include/asm/qe.h
+++ b/arch/powerpc/include/asm/qe.h
@@ -210,8 +210,15 @@ struct qe_firmware_info {
 	u64 extended_modes;	/* Extended modes */
 };
 
+#ifdef CONFIG_QUICC_ENGINE
 /* Upload a firmware to the QE */
 int qe_upload_firmware(const struct qe_firmware *firmware);
+#else
+static inline int qe_upload_firmware(const struct qe_firmware *firmware)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_QUICC_ENGINE */
 
 /* Obtain information on the uploaded firmware */
 struct qe_firmware_info *qe_get_firmware_info(void);

From dc2e673dbcbaebdf84c09956b85c3be3a8b7bd02 Mon Sep 17 00:00:00 2001
From: Poonam Aggrwal <poonam.aggrwal@freescale.com>
Date: Sat, 19 Sep 2009 22:43:56 +0530
Subject: [PATCH 069/151] powerpc/85xx: Create dts for each core in CAMP mode
 for P2020RDB

This patch creates the dts files for each core and splits the devices
between the two cores for P2020RDB.

core0 has memory, L2, i2c, spi, dma1, usb, eth0, eth1, crypto,
		global-util, pci0,
core1 has L2, dma2, eth0, pci1, msi.

MPIC is shared between two cores but each core will protect its
interrupts from other core by using "protected-sources" of mpic.

Signed-off-by: Poonam Aggrwal <poonam.aggrwal@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/boot/dts/p2020rdb_camp_core0.dts | 363 ++++++++++++++++++
 arch/powerpc/boot/dts/p2020rdb_camp_core1.dts | 184 +++++++++
 arch/powerpc/platforms/85xx/mpc85xx_rdb.c     |  10 +-
 3 files changed, 556 insertions(+), 1 deletion(-)
 create mode 100644 arch/powerpc/boot/dts/p2020rdb_camp_core0.dts
 create mode 100644 arch/powerpc/boot/dts/p2020rdb_camp_core1.dts

diff --git a/arch/powerpc/boot/dts/p2020rdb_camp_core0.dts b/arch/powerpc/boot/dts/p2020rdb_camp_core0.dts
new file mode 100644
index 000000000000..0fe93d0c8b2e
--- /dev/null
+++ b/arch/powerpc/boot/dts/p2020rdb_camp_core0.dts
@@ -0,0 +1,363 @@
+/*
+ * P2020 RDB  Core0 Device Tree Source in CAMP mode.
+ *
+ * In CAMP mode, each core needs to have its own dts. Only mpic and L2 cache
+ * can be shared, all the other devices must be assigned to one core only.
+ * This dts file allows core0 to have memory, l2, i2c, spi, gpio, dma1, usb,
+ * eth1, eth2, sdhc, crypto, global-util, pci0.
+ *
+ * Copyright 2009 Freescale Semiconductor Inc.
+ *
+ * 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.
+ */
+
+/dts-v1/;
+/ {
+	model = "fsl,P2020";
+	compatible = "fsl,P2020RDB", "fsl,MPC85XXRDB-CAMP";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		ethernet1 = &enet1;
+		ethernet2 = &enet2;
+		serial0 = &serial0;
+		pci0 = &pci0;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		PowerPC,P2020@0 {
+			device_type = "cpu";
+			reg = <0x0>;
+			next-level-cache = <&L2>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+	};
+
+	soc@ffe00000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		device_type = "soc";
+		compatible = "fsl,p2020-immr", "simple-bus";
+		ranges = <0x0  0x0 0xffe00000 0x100000>;
+		bus-frequency = <0>;		// Filled out by uboot.
+
+		ecm-law@0 {
+			compatible = "fsl,ecm-law";
+			reg = <0x0 0x1000>;
+			fsl,num-laws = <12>;
+		};
+
+		ecm@1000 {
+			compatible = "fsl,p2020-ecm", "fsl,ecm";
+			reg = <0x1000 0x1000>;
+			interrupts = <17 2>;
+			interrupt-parent = <&mpic>;
+		};
+
+		memory-controller@2000 {
+			compatible = "fsl,p2020-memory-controller";
+			reg = <0x2000 0x1000>;
+			interrupt-parent = <&mpic>;
+			interrupts = <18 2>;
+		};
+
+		i2c@3000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <0>;
+			compatible = "fsl-i2c";
+			reg = <0x3000 0x100>;
+			interrupts = <43 2>;
+			interrupt-parent = <&mpic>;
+			dfsrr;
+			rtc@68 {
+				compatible = "dallas,ds1339";
+				reg = <0x68>;
+			};
+		};
+
+		i2c@3100 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <1>;
+			compatible = "fsl-i2c";
+			reg = <0x3100 0x100>;
+			interrupts = <43 2>;
+			interrupt-parent = <&mpic>;
+			dfsrr;
+		};
+
+		serial0: serial@4500 {
+			cell-index = <0>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x4500 0x100>;
+			clock-frequency = <0>;
+		};
+
+		spi@7000 {
+			cell-index = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl,espi";
+			reg = <0x7000 0x1000>;
+			interrupts = <59 0x2>;
+			interrupt-parent = <&mpic>;
+			mode = "cpu";
+
+			fsl_m25p80@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "fsl,espi-flash";
+				reg = <0>;
+				linux,modalias = "fsl_m25p80";
+				modal = "s25sl128b";
+				spi-max-frequency = <50000000>;
+				mode = <0>;
+
+				partition@0 {
+					/* 512KB for u-boot Bootloader Image */
+					reg = <0x0 0x00080000>;
+					label = "SPI (RO) U-Boot Image";
+					read-only;
+				};
+
+				partition@80000 {
+					/* 512KB for DTB Image */
+					reg = <0x00080000 0x00080000>;
+					label = "SPI (RO) DTB Image";
+					read-only;
+				};
+
+				partition@100000 {
+					/* 4MB for Linux Kernel Image */
+					reg = <0x00100000 0x00400000>;
+					label = "SPI (RO) Linux Kernel Image";
+					read-only;
+				};
+
+				partition@500000 {
+					/* 4MB for Compressed RFS Image */
+					reg = <0x00500000 0x00400000>;
+					label = "SPI (RO) Compressed RFS Image";
+					read-only;
+				};
+
+				partition@900000 {
+					/* 7MB for JFFS2 based RFS */
+					reg = <0x00900000 0x00700000>;
+					label = "SPI (RW) JFFS2 RFS";
+				};
+			};
+		};
+
+		gpio: gpio-controller@f000 {
+			#gpio-cells = <2>;
+			compatible = "fsl,mpc8572-gpio";
+			reg = <0xf000 0x100>;
+			interrupts = <47 0x2>;
+			interrupt-parent = <&mpic>;
+			gpio-controller;
+		};
+
+		L2: l2-cache-controller@20000 {
+			compatible = "fsl,p2020-l2-cache-controller";
+			reg = <0x20000 0x1000>;
+			cache-line-size = <32>;	// 32 bytes
+			cache-size = <0x80000>; // L2,512K
+			interrupt-parent = <&mpic>;
+			interrupts = <16 2>;
+		};
+
+		dma@21300 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,eloplus-dma";
+			reg = <0x21300 0x4>;
+			ranges = <0x0 0x21100 0x200>;
+			cell-index = <0>;
+			dma-channel@0 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x0 0x80>;
+				cell-index = <0>;
+				interrupt-parent = <&mpic>;
+				interrupts = <20 2>;
+			};
+			dma-channel@80 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x80 0x80>;
+				cell-index = <1>;
+				interrupt-parent = <&mpic>;
+				interrupts = <21 2>;
+			};
+			dma-channel@100 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x100 0x80>;
+				cell-index = <2>;
+				interrupt-parent = <&mpic>;
+				interrupts = <22 2>;
+			};
+			dma-channel@180 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x180 0x80>;
+				cell-index = <3>;
+				interrupt-parent = <&mpic>;
+				interrupts = <23 2>;
+			};
+		};
+
+		usb@22000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl-usb2-dr";
+			reg = <0x22000 0x1000>;
+			interrupt-parent = <&mpic>;
+			interrupts = <28 0x2>;
+			phy_type = "ulpi";
+		};
+
+		mdio@24520 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl,gianfar-mdio";
+			reg = <0x24520 0x20>;
+
+			phy0: ethernet-phy@0 {
+				interrupt-parent = <&mpic>;
+				interrupts = <3 1>;
+				reg = <0x0>;
+			};
+			phy1: ethernet-phy@1 {
+				interrupt-parent = <&mpic>;
+				interrupts = <3 1>;
+				reg = <0x1>;
+			};
+		};
+
+		mdio@25520 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl,gianfar-tbi";
+			reg = <0x26520 0x20>;
+
+			tbi0: tbi-phy@11 {
+				reg = <0x11>;
+				device_type = "tbi-phy";
+			};
+		};
+
+		enet1: ethernet@25000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			cell-index = <1>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "gianfar";
+			reg = <0x25000 0x1000>;
+			ranges = <0x0 0x25000 0x1000>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupts = <35 2 36 2 40 2>;
+			interrupt-parent = <&mpic>;
+			tbi-handle = <&tbi0>;
+			phy-handle = <&phy0>;
+			phy-connection-type = "sgmii";
+
+		};
+
+		enet2: ethernet@26000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			cell-index = <2>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "gianfar";
+			reg = <0x26000 0x1000>;
+			ranges = <0x0 0x26000 0x1000>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupts = <31 2 32 2 33 2>;
+			interrupt-parent = <&mpic>;
+			phy-handle = <&phy1>;
+			phy-connection-type = "rgmii-id";
+		};
+
+		sdhci@2e000 {
+			compatible = "fsl,p2020-esdhc", "fsl,esdhc";
+			reg = <0x2e000 0x1000>;
+			interrupts = <72 0x2>;
+			interrupt-parent = <&mpic>;
+			/* Filled in by U-Boot */
+			clock-frequency = <0>;
+		};
+
+		crypto@30000 {
+			compatible = "fsl,sec3.1", "fsl,sec3.0", "fsl,sec2.4",
+				     "fsl,sec2.2", "fsl,sec2.1", "fsl,sec2.0";
+			reg = <0x30000 0x10000>;
+			interrupts = <45 2 58 2>;
+			interrupt-parent = <&mpic>;
+			fsl,num-channels = <4>;
+			fsl,channel-fifo-len = <24>;
+			fsl,exec-units-mask = <0xbfe>;
+			fsl,descriptor-types-mask = <0x3ab0ebf>;
+		};
+
+		mpic: pic@40000 {
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <2>;
+			reg = <0x40000 0x40000>;
+			compatible = "chrp,open-pic";
+			device_type = "open-pic";
+			protected-sources = <
+			42 76 77 78 79 /* serial1 , dma2 */
+			29 30 34 26 /* enet0, pci1 */
+			0xe0 0xe1 0xe2 0xe3 /* msi */
+			0xe4 0xe5 0xe6 0xe7
+			>;
+		};
+
+		global-utilities@e0000 {
+			compatible = "fsl,p2020-guts";
+			reg = <0xe0000 0x1000>;
+			fsl,has-rstcr;
+		};
+	};
+
+	pci0: pcie@ffe09000 {
+		compatible = "fsl,mpc8548-pcie";
+		device_type = "pci";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0 0xffe09000 0 0x1000>;
+		bus-range = <0 255>;
+		ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0 0xffc30000 0x0 0x10000>;
+		clock-frequency = <33333333>;
+		interrupt-parent = <&mpic>;
+		interrupts = <25 2>;
+		pcie@0 {
+			reg = <0x0 0x0 0x0 0x0 0x0>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			ranges = <0x2000000 0x0 0xa0000000
+				  0x2000000 0x0 0xa0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/p2020rdb_camp_core1.dts b/arch/powerpc/boot/dts/p2020rdb_camp_core1.dts
new file mode 100644
index 000000000000..e95a51285328
--- /dev/null
+++ b/arch/powerpc/boot/dts/p2020rdb_camp_core1.dts
@@ -0,0 +1,184 @@
+/*
+ * P2020 RDB Core1 Device Tree Source in CAMP mode.
+ *
+ * In CAMP mode, each core needs to have its own dts. Only mpic and L2 cache
+ * can be shared, all the other devices must be assigned to one core only.
+ * This dts allows core1 to have l2, dma2, eth0, pci1, msi.
+ *
+ * Please note to add "-b 1" for core1's dts compiling.
+ *
+ * Copyright 2009 Freescale Semiconductor Inc.
+ *
+ * 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.
+ */
+
+/dts-v1/;
+/ {
+	model = "fsl,P2020";
+	compatible = "fsl,P2020RDB", "fsl,MPC85XXRDB-CAMP";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		ethernet0 = &enet0;
+		serial0 = &serial0;
+		pci1 = &pci1;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		PowerPC,P2020@1 {
+			device_type = "cpu";
+			reg = <0x1>;
+			next-level-cache = <&L2>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+	};
+
+	soc@ffe00000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		device_type = "soc";
+		compatible = "fsl,p2020-immr", "simple-bus";
+		ranges = <0x0  0x0 0xffe00000 0x100000>;
+		bus-frequency = <0>;		// Filled out by uboot.
+
+		serial0: serial@4600 {
+			cell-index = <1>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x4600 0x100>;
+			clock-frequency = <0>;
+		};
+
+		dma@c300 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,eloplus-dma";
+			reg = <0xc300 0x4>;
+			ranges = <0x0 0xc100 0x200>;
+			cell-index = <1>;
+			dma-channel@0 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x0 0x80>;
+				cell-index = <0>;
+				interrupt-parent = <&mpic>;
+				interrupts = <76 2>;
+			};
+			dma-channel@80 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x80 0x80>;
+				cell-index = <1>;
+				interrupt-parent = <&mpic>;
+				interrupts = <77 2>;
+			};
+			dma-channel@100 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x100 0x80>;
+				cell-index = <2>;
+				interrupt-parent = <&mpic>;
+				interrupts = <78 2>;
+			};
+			dma-channel@180 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x180 0x80>;
+				cell-index = <3>;
+				interrupt-parent = <&mpic>;
+				interrupts = <79 2>;
+			};
+		};
+
+		L2: l2-cache-controller@20000 {
+			compatible = "fsl,p2020-l2-cache-controller";
+			reg = <0x20000 0x1000>;
+			cache-line-size = <32>;	// 32 bytes
+			cache-size = <0x80000>; // L2,512K
+			interrupt-parent = <&mpic>;
+		};
+
+
+		enet0: ethernet@24000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			cell-index = <0>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "gianfar";
+			reg = <0x24000 0x1000>;
+			ranges = <0x0 0x24000 0x1000>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupts = <29 2 30 2 34 2>;
+			interrupt-parent = <&mpic>;
+			fixed-link = <1 1 1000 0 0>;
+			phy-connection-type = "rgmii-id";
+
+		};
+
+		mpic: pic@40000 {
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <2>;
+			reg = <0x40000 0x40000>;
+			compatible = "chrp,open-pic";
+			device_type = "open-pic";
+			protected-sources = <
+			17 18 43 42 59 47 /*ecm, mem, i2c, serial0, spi,gpio */
+			16 20 21 22 23 28 	/* L2, dma1, USB */
+			03 35 36 40 31 32 33 	/* mdio, enet1, enet2 */
+			72 45 58 25 		/* sdhci, crypto , pci */
+			>;
+		};
+
+		msi@41600 {
+			compatible = "fsl,p2020-msi", "fsl,mpic-msi";
+			reg = <0x41600 0x80>;
+			msi-available-ranges = <0 0x100>;
+			interrupts = <
+				0xe0 0
+				0xe1 0
+				0xe2 0
+				0xe3 0
+				0xe4 0
+				0xe5 0
+				0xe6 0
+				0xe7 0>;
+			interrupt-parent = <&mpic>;
+		};
+	};
+
+	pci1: pcie@ffe0a000 {
+		compatible = "fsl,mpc8548-pcie";
+		device_type = "pci";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0 0xffe0a000 0 0x1000>;
+		bus-range = <0 255>;
+		ranges = <0x2000000 0x0 0xc0000000 0 0xc0000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0 0xffc20000 0x0 0x10000>;
+		clock-frequency = <33333333>;
+		interrupt-parent = <&mpic>;
+		interrupts = <26 2>;
+		pcie@0 {
+			reg = <0x0 0x0 0x0 0x0 0x0>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			ranges = <0x2000000 0x0 0xc0000000
+				  0x2000000 0x0 0xc0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index c8468de4acf6..d173164a924e 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -44,6 +44,7 @@ void __init mpc85xx_rdb_pic_init(void)
 	struct mpic *mpic;
 	struct resource r;
 	struct device_node *np;
+	unsigned long root = of_get_flat_dt_root();
 
 	np = of_find_node_by_type(NULL, "open-pic");
 	if (np == NULL) {
@@ -57,11 +58,18 @@ void __init mpc85xx_rdb_pic_init(void)
 		return;
 	}
 
-	mpic = mpic_alloc(np, r.start,
+	if (of_flat_dt_is_compatible(root, "fsl,85XXRDB-CAMP")) {
+		mpic = mpic_alloc(np, r.start,
+			MPIC_PRIMARY |
+			MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS,
+			0, 256, " OpenPIC  ");
+	} else {
+		mpic = mpic_alloc(np, r.start,
 		  MPIC_PRIMARY | MPIC_WANTS_RESET |
 		  MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
 		  MPIC_SINGLE_DEST_CPU,
 		  0, 256, " OpenPIC  ");
+	}
 
 	BUG_ON(mpic == NULL);
 	of_node_put(np);

From 0c7b87b0857f0e17be982fd840046444a83c3996 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Wed, 16 Sep 2009 01:43:52 +0400
Subject: [PATCH 070/151] powerpc/qe: Make qe_reset() code path safe for
 repeated invocation

For MPC8569 CPUs we'll need to reset QE after each suspend, so make
qe_reset() code path suitable for repeated invocation, that is:

- Don't initialize rheap structures if already initialized;
- Don't allocate muram for SDMA if already allocated, just reinitialize
  registers with previously allocated muram offset;
- Remove __init attributes from qe_reset() and cpm_muram_init();

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/include/asm/qe.h    |  2 +-
 arch/powerpc/sysdev/cpm_common.c |  5 ++++-
 arch/powerpc/sysdev/qe_lib/qe.c  | 12 +++++++-----
 3 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/qe.h b/arch/powerpc/include/asm/qe.h
index 28fee3b7887a..908f0b75745b 100644
--- a/arch/powerpc/include/asm/qe.h
+++ b/arch/powerpc/include/asm/qe.h
@@ -87,7 +87,7 @@ extern spinlock_t cmxgcr_lock;
 
 /* Export QE common operations */
 #ifdef CONFIG_QUICC_ENGINE
-extern void __init qe_reset(void);
+extern void qe_reset(void);
 #else
 static inline void qe_reset(void) {}
 #endif
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index e4b6d66d93de..9de72c96e6d1 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -72,7 +72,7 @@ static phys_addr_t muram_pbase;
 /* Max address size we deal with */
 #define OF_MAX_ADDR_CELLS	4
 
-int __init cpm_muram_init(void)
+int cpm_muram_init(void)
 {
 	struct device_node *np;
 	struct resource r;
@@ -81,6 +81,9 @@ int __init cpm_muram_init(void)
 	int i = 0;
 	int ret = 0;
 
+	if (muram_pbase)
+		return 0;
+
 	spin_lock_init(&cpm_muram_lock);
 	/* initialize the info header */
 	rh_init(&cpm_muram_info, 1,
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index fff2701b90df..1ed1a9fd9bcf 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -104,7 +104,7 @@ phys_addr_t get_qe_base(void)
 
 EXPORT_SYMBOL(get_qe_base);
 
-void __init qe_reset(void)
+void qe_reset(void)
 {
 	if (qe_immr == NULL)
 		qe_immr = ioremap(get_qe_base(), QE_IMMAP_SIZE);
@@ -330,16 +330,18 @@ EXPORT_SYMBOL(qe_put_snum);
 static int qe_sdma_init(void)
 {
 	struct sdma __iomem *sdma = &qe_immr->sdma;
-	unsigned long sdma_buf_offset;
+	static unsigned long sdma_buf_offset = (unsigned long)-ENOMEM;
 
 	if (!sdma)
 		return -ENODEV;
 
 	/* allocate 2 internal temporary buffers (512 bytes size each) for
 	 * the SDMA */
- 	sdma_buf_offset = qe_muram_alloc(512 * 2, 4096);
-	if (IS_ERR_VALUE(sdma_buf_offset))
-		return -ENOMEM;
+	if (IS_ERR_VALUE(sdma_buf_offset)) {
+		sdma_buf_offset = qe_muram_alloc(512 * 2, 4096);
+		if (IS_ERR_VALUE(sdma_buf_offset))
+			return -ENOMEM;
+	}
 
 	out_be32(&sdma->sdebcr, (u32) sdma_buf_offset & QE_SDEBCR_BA_MASK);
  	out_be32(&sdma->sdmr, (QE_SDMR_GLB_1_MSK |

From 46d2293470c18c1bb632083bf0b589deff30ccae Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Wed, 16 Sep 2009 01:43:54 +0400
Subject: [PATCH 071/151] powerpc/qe: QE also shuts down on MPC8568

It appears that QE shuts down on all MPC85xx CPUs (i.e. MPC8568 and
MPC8569) and thus needs reset upon resume.

So modify qe_alive_during_sleep() to account that.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/include/asm/qe.h   | 23 ++++++++++++++++++++++-
 arch/powerpc/sysdev/qe_lib/qe.c | 13 -------------
 2 files changed, 22 insertions(+), 14 deletions(-)

diff --git a/arch/powerpc/include/asm/qe.h b/arch/powerpc/include/asm/qe.h
index 908f0b75745b..5e0e8b2b0aa1 100644
--- a/arch/powerpc/include/asm/qe.h
+++ b/arch/powerpc/include/asm/qe.h
@@ -154,7 +154,28 @@ int qe_get_snum(void);
 void qe_put_snum(u8 snum);
 unsigned int qe_get_num_of_risc(void);
 unsigned int qe_get_num_of_snums(void);
-int qe_alive_during_sleep(void);
+
+static inline int qe_alive_during_sleep(void)
+{
+	/*
+	 * MPC8568E reference manual says:
+	 *
+	 * "...power down sequence waits for all I/O interfaces to become idle.
+	 *  In some applications this may happen eventually without actively
+	 *  shutting down interfaces, but most likely, software will have to
+	 *  take steps to shut down the eTSEC, QUICC Engine Block, and PCI
+	 *  interfaces before issuing the command (either the write to the core
+	 *  MSR[WE] as described above or writing to POWMGTCSR) to put the
+	 *  device into sleep state."
+	 *
+	 * MPC8569E reference manual has a similar paragraph.
+	 */
+#ifdef CONFIG_PPC_85xx
+	return 0;
+#else
+	return 1;
+#endif
+}
 
 /* we actually use cpm_muram implementation, define this for convenience */
 #define qe_muram_init cpm_muram_init
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index 1ed1a9fd9bcf..4eaf2a962914 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -65,19 +65,6 @@ static unsigned int qe_num_of_snum;
 
 static phys_addr_t qebase = -1;
 
-int qe_alive_during_sleep(void)
-{
-	static int ret = -1;
-
-	if (ret != -1)
-		return ret;
-
-	ret = !of_find_compatible_node(NULL, NULL, "fsl,mpc8569-pmc");
-
-	return ret;
-}
-EXPORT_SYMBOL(qe_alive_during_sleep);
-
 phys_addr_t get_qe_base(void)
 {
 	struct device_node *qe;

From 52dffd7fbf3d7e29fccfd4896a812d358177dc58 Mon Sep 17 00:00:00 2001
From: Poonam Aggrwal <poonam.aggrwal@freescale.com>
Date: Fri, 25 Sep 2009 09:50:28 +0530
Subject: [PATCH 072/151] powerpc/85xx: Added P1020RDB Platform support.

P1020 is another member of Freescale QorIQ series of processors.
It is an e500 based dual core SOC.
Being a scaled down version of P2020 it has following differences from P2020:
- 533MHz - 800MHz core frequency.
- 256Kbyte L2 cache
- Ethernet controllers with classification capabilities(new controller).

From board perspective P1020RDB is same as P2020RDB.

Signed-off-by: Poonam Aggrwal <poonam.aggrwal@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/boot/dts/p1020rdb.dts        | 477 ++++++++++++++++++++++
 arch/powerpc/platforms/85xx/mpc85xx_rdb.c |  24 ++
 2 files changed, 501 insertions(+)
 create mode 100644 arch/powerpc/boot/dts/p1020rdb.dts

diff --git a/arch/powerpc/boot/dts/p1020rdb.dts b/arch/powerpc/boot/dts/p1020rdb.dts
new file mode 100644
index 000000000000..df5269093af8
--- /dev/null
+++ b/arch/powerpc/boot/dts/p1020rdb.dts
@@ -0,0 +1,477 @@
+/*
+ * P1020 RDB Device Tree Source
+ *
+ * Copyright 2009 Freescale Semiconductor Inc.
+ *
+ * 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.
+ */
+
+/dts-v1/;
+/ {
+	model = "fsl,P1020";
+	compatible = "fsl,P1020RDB";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		serial0 = &serial0;
+		serial1 = &serial1;
+		pci0 = &pci0;
+		pci1 = &pci1;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		PowerPC,P1020@0 {
+			device_type = "cpu";
+			reg = <0x0>;
+			next-level-cache = <&L2>;
+		};
+
+		PowerPC,P1020@1 {
+			device_type = "cpu";
+			reg = <0x1>;
+			next-level-cache = <&L2>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+	};
+
+	localbus@ffe05000 {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		compatible = "fsl,p1020-elbc", "fsl,elbc", "simple-bus";
+		reg = <0 0xffe05000 0 0x1000>;
+		interrupts = <19 2>;
+		interrupt-parent = <&mpic>;
+
+		/* NOR, NAND Flashes and Vitesse 5 port L2 switch */
+		ranges = <0x0 0x0 0x0 0xef000000 0x01000000
+			  0x1 0x0 0x0 0xffa00000 0x00040000
+			  0x2 0x0 0x0 0xffb00000 0x00020000>;
+
+		nor@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x1000000>;
+			bank-width = <2>;
+			device-width = <1>;
+
+			partition@0 {
+				/* This location must not be altered  */
+				/* 256KB for Vitesse 7385 Switch firmware */
+				reg = <0x0 0x00040000>;
+				label = "NOR (RO) Vitesse-7385 Firmware";
+				read-only;
+			};
+
+			partition@40000 {
+				/* 256KB for DTB Image */
+				reg = <0x00040000 0x00040000>;
+				label = "NOR (RO) DTB Image";
+				read-only;
+			};
+
+			partition@80000 {
+				/* 3.5 MB for Linux Kernel Image */
+				reg = <0x00080000 0x00380000>;
+				label = "NOR (RO) Linux Kernel Image";
+				read-only;
+			};
+
+			partition@400000 {
+				/* 11MB for JFFS2 based Root file System */
+				reg = <0x00400000 0x00b00000>;
+				label = "NOR (RW) JFFS2 Root File System";
+			};
+
+			partition@f00000 {
+				/* This location must not be altered  */
+				/* 512KB for u-boot Bootloader Image */
+				/* 512KB for u-boot Environment Variables */
+				reg = <0x00f00000 0x00100000>;
+				label = "NOR (RO) U-Boot Image";
+				read-only;
+			};
+		};
+
+		nand@1,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,p1020-fcm-nand",
+				     "fsl,elbc-fcm-nand";
+			reg = <0x1 0x0 0x40000>;
+
+			partition@0 {
+				/* This location must not be altered  */
+				/* 1MB for u-boot Bootloader Image */
+				reg = <0x0 0x00100000>;
+				label = "NAND (RO) U-Boot Image";
+				read-only;
+			};
+
+			partition@100000 {
+				/* 1MB for DTB Image */
+				reg = <0x00100000 0x00100000>;
+				label = "NAND (RO) DTB Image";
+				read-only;
+			};
+
+			partition@200000 {
+				/* 4MB for Linux Kernel Image */
+				reg = <0x00200000 0x00400000>;
+				label = "NAND (RO) Linux Kernel Image";
+				read-only;
+			};
+
+			partition@600000 {
+				/* 4MB for Compressed Root file System Image */
+				reg = <0x00600000 0x00400000>;
+				label = "NAND (RO) Compressed RFS Image";
+				read-only;
+			};
+
+			partition@a00000 {
+				/* 7MB for JFFS2 based Root file System */
+				reg = <0x00a00000 0x00700000>;
+				label = "NAND (RW) JFFS2 Root File System";
+			};
+
+			partition@1100000 {
+				/* 15MB for JFFS2 based Root file System */
+				reg = <0x01100000 0x00f00000>;
+				label = "NAND (RW) Writable User area";
+			};
+		};
+
+		L2switch@2,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "vitesse-7385";
+			reg = <0x2 0x0 0x20000>;
+		};
+
+	};
+
+	soc@ffe00000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		device_type = "soc";
+		compatible = "fsl,p1020-immr", "simple-bus";
+		ranges = <0x0  0x0 0xffe00000 0x100000>;
+		bus-frequency = <0>;		// Filled out by uboot.
+
+		ecm-law@0 {
+			compatible = "fsl,ecm-law";
+			reg = <0x0 0x1000>;
+			fsl,num-laws = <12>;
+		};
+
+		ecm@1000 {
+			compatible = "fsl,p1020-ecm", "fsl,ecm";
+			reg = <0x1000 0x1000>;
+			interrupts = <16 2>;
+			interrupt-parent = <&mpic>;
+		};
+
+		memory-controller@2000 {
+			compatible = "fsl,p1020-memory-controller";
+			reg = <0x2000 0x1000>;
+			interrupt-parent = <&mpic>;
+			interrupts = <16 2>;
+		};
+
+		i2c@3000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <0>;
+			compatible = "fsl-i2c";
+			reg = <0x3000 0x100>;
+			interrupts = <43 2>;
+			interrupt-parent = <&mpic>;
+			dfsrr;
+			rtc@68 {
+				compatible = "dallas,ds1339";
+				reg = <0x68>;
+			};
+		};
+
+		i2c@3100 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <1>;
+			compatible = "fsl-i2c";
+			reg = <0x3100 0x100>;
+			interrupts = <43 2>;
+			interrupt-parent = <&mpic>;
+			dfsrr;
+		};
+
+		serial0: serial@4500 {
+			cell-index = <0>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x4500 0x100>;
+			clock-frequency = <0>;
+			interrupts = <42 2>;
+			interrupt-parent = <&mpic>;
+		};
+
+		serial1: serial@4600 {
+			cell-index = <1>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x4600 0x100>;
+			clock-frequency = <0>;
+			interrupts = <42 2>;
+			interrupt-parent = <&mpic>;
+		};
+
+		spi@7000 {
+			cell-index = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl,espi";
+			reg = <0x7000 0x1000>;
+			interrupts = <59 0x2>;
+			interrupt-parent = <&mpic>;
+			mode = "cpu";
+
+			fsl_m25p80@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "fsl,espi-flash";
+				reg = <0>;
+				linux,modalias = "fsl_m25p80";
+				modal = "s25sl128b";
+				spi-max-frequency = <50000000>;
+				mode = <0>;
+
+				partition@0 {
+					/* 512KB for u-boot Bootloader Image */
+					reg = <0x0 0x00080000>;
+					label = "SPI (RO) U-Boot Image";
+					read-only;
+				};
+
+				partition@80000 {
+					/* 512KB for DTB Image */
+					reg = <0x00080000 0x00080000>;
+					label = "SPI (RO) DTB Image";
+					read-only;
+				};
+
+				partition@100000 {
+					/* 4MB for Linux Kernel Image */
+					reg = <0x00100000 0x00400000>;
+					label = "SPI (RO) Linux Kernel Image";
+					read-only;
+				};
+
+				partition@500000 {
+					/* 4MB for Compressed RFS Image */
+					reg = <0x00500000 0x00400000>;
+					label = "SPI (RO) Compressed RFS Image";
+					read-only;
+				};
+
+				partition@900000 {
+					/* 7MB for JFFS2 based RFS */
+					reg = <0x00900000 0x00700000>;
+					label = "SPI (RW) JFFS2 RFS";
+				};
+			};
+		};
+
+		gpio: gpio-controller@f000 {
+			#gpio-cells = <2>;
+			compatible = "fsl,mpc8572-gpio";
+			reg = <0xf000 0x100>;
+			interrupts = <47 0x2>;
+			interrupt-parent = <&mpic>;
+			gpio-controller;
+		};
+
+		L2: l2-cache-controller@20000 {
+			compatible = "fsl,p1020-l2-cache-controller";
+			reg = <0x20000 0x1000>;
+			cache-line-size = <32>;	// 32 bytes
+			cache-size = <0x40000>; // L2,256K
+			interrupt-parent = <&mpic>;
+			interrupts = <16 2>;
+		};
+
+		dma@21300 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,eloplus-dma";
+			reg = <0x21300 0x4>;
+			ranges = <0x0 0x21100 0x200>;
+			cell-index = <0>;
+			dma-channel@0 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x0 0x80>;
+				cell-index = <0>;
+				interrupt-parent = <&mpic>;
+				interrupts = <20 2>;
+			};
+			dma-channel@80 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x80 0x80>;
+				cell-index = <1>;
+				interrupt-parent = <&mpic>;
+				interrupts = <21 2>;
+			};
+			dma-channel@100 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x100 0x80>;
+				cell-index = <2>;
+				interrupt-parent = <&mpic>;
+				interrupts = <22 2>;
+			};
+			dma-channel@180 {
+				compatible = "fsl,eloplus-dma-channel";
+				reg = <0x180 0x80>;
+				cell-index = <3>;
+				interrupt-parent = <&mpic>;
+				interrupts = <23 2>;
+			};
+		};
+
+		usb@22000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl-usb2-dr";
+			reg = <0x22000 0x1000>;
+			interrupt-parent = <&mpic>;
+			interrupts = <28 0x2>;
+			phy_type = "ulpi";
+		};
+
+		usb@23000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl-usb2-dr";
+			reg = <0x23000 0x1000>;
+			interrupt-parent = <&mpic>;
+			interrupts = <46 0x2>;
+			phy_type = "ulpi";
+		};
+
+		sdhci@2e000 {
+			compatible = "fsl,p1020-esdhc", "fsl,esdhc";
+			reg = <0x2e000 0x1000>;
+			interrupts = <72 0x2>;
+			interrupt-parent = <&mpic>;
+			/* Filled in by U-Boot */
+			clock-frequency = <0>;
+		};
+
+		crypto@30000 {
+			compatible = "fsl,sec3.1", "fsl,sec3.0", "fsl,sec2.4",
+				     "fsl,sec2.2", "fsl,sec2.1", "fsl,sec2.0";
+			reg = <0x30000 0x10000>;
+			interrupts = <45 2 58 2>;
+			interrupt-parent = <&mpic>;
+			fsl,num-channels = <4>;
+			fsl,channel-fifo-len = <24>;
+			fsl,exec-units-mask = <0xbfe>;
+			fsl,descriptor-types-mask = <0x3ab0ebf>;
+		};
+
+		mpic: pic@40000 {
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <2>;
+			reg = <0x40000 0x40000>;
+			compatible = "chrp,open-pic";
+			device_type = "open-pic";
+		};
+
+		msi@41600 {
+			compatible = "fsl,p1020-msi", "fsl,mpic-msi";
+			reg = <0x41600 0x80>;
+			msi-available-ranges = <0 0x100>;
+			interrupts = <
+				0xe0 0
+				0xe1 0
+				0xe2 0
+				0xe3 0
+				0xe4 0
+				0xe5 0
+				0xe6 0
+				0xe7 0>;
+			interrupt-parent = <&mpic>;
+		};
+
+		global-utilities@e0000 {	//global utilities block
+			compatible = "fsl,p1020-guts";
+			reg = <0xe0000 0x1000>;
+			fsl,has-rstcr;
+		};
+	};
+
+	pci0: pcie@ffe09000 {
+		compatible = "fsl,mpc8548-pcie";
+		device_type = "pci";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0 0xffe09000 0 0x1000>;
+		bus-range = <0 255>;
+		ranges = <0x2000000 0x0 0xa0000000 0 0xa0000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0 0xffc30000 0x0 0x10000>;
+		clock-frequency = <33333333>;
+		interrupt-parent = <&mpic>;
+		interrupts = <16 2>;
+		pcie@0 {
+			reg = <0x0 0x0 0x0 0x0 0x0>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			ranges = <0x2000000 0x0 0xa0000000
+				  0x2000000 0x0 0xa0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+
+	pci1: pcie@ffe0a000 {
+		compatible = "fsl,mpc8548-pcie";
+		device_type = "pci";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0 0xffe0a000 0 0x1000>;
+		bus-range = <0 255>;
+		ranges = <0x2000000 0x0 0xc0000000 0 0xc0000000 0x0 0x20000000
+			  0x1000000 0x0 0x00000000 0 0xffc20000 0x0 0x10000>;
+		clock-frequency = <33333333>;
+		interrupt-parent = <&mpic>;
+		interrupts = <16 2>;
+		pcie@0 {
+			reg = <0x0 0x0 0x0 0x0 0x0>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			ranges = <0x2000000 0x0 0xc0000000
+				  0x2000000 0x0 0xc0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
index d173164a924e..088f30b0c088 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_rdb.c
@@ -121,6 +121,7 @@ static int __init mpc85xxrdb_publish_devices(void)
 	return of_platform_bus_probe(NULL, mpc85xxrdb_ids, NULL);
 }
 machine_device_initcall(p2020_rdb, mpc85xxrdb_publish_devices);
+machine_device_initcall(p1020_rdb, mpc85xxrdb_publish_devices);
 
 /*
  * Called very early, device-tree isn't unflattened
@@ -134,6 +135,15 @@ static int __init p2020_rdb_probe(void)
 	return 0;
 }
 
+static int __init p1020_rdb_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	if (of_flat_dt_is_compatible(root, "fsl,P1020RDB"))
+		return 1;
+	return 0;
+}
+
 define_machine(p2020_rdb) {
 	.name			= "P2020 RDB",
 	.probe			= p2020_rdb_probe,
@@ -147,3 +157,17 @@ define_machine(p2020_rdb) {
 	.calibrate_decr		= generic_calibrate_decr,
 	.progress		= udbg_progress,
 };
+
+define_machine(p1020_rdb) {
+	.name			= "P1020 RDB",
+	.probe			= p1020_rdb_probe,
+	.setup_arch		= mpc85xx_rdb_setup_arch,
+	.init_IRQ		= mpc85xx_rdb_pic_init,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+	.get_irq		= mpic_get_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};

From 644b2a680ccc51a9ec4d6beb12e9d47d2dee98e2 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Mon, 12 Oct 2009 20:49:13 +0400
Subject: [PATCH 073/151] powerpc/cpm: Remove SPI defines and spi structs

When cpm2.h included into spi_mpc8xxx driver, the SPI defines
in the header conflict with defines in the driver.

We don't need them in the header file, so remove them. Plus
remove "struct spi", we'll use a better version in the driver.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/include/asm/cpm1.h | 45 ---------------------------------
 arch/powerpc/include/asm/cpm2.h | 39 ----------------------------
 2 files changed, 84 deletions(-)

diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h
index 7685ffde8821..81b01192f440 100644
--- a/arch/powerpc/include/asm/cpm1.h
+++ b/arch/powerpc/include/asm/cpm1.h
@@ -478,51 +478,6 @@ typedef struct iic {
 	char	res2[2];	/* Reserved */
 } iic_t;
 
-/* SPI parameter RAM.
-*/
-typedef struct spi {
-	ushort	spi_rbase;	/* Rx Buffer descriptor base address */
-	ushort	spi_tbase;	/* Tx Buffer descriptor base address */
-	u_char	spi_rfcr;	/* Rx function code */
-	u_char	spi_tfcr;	/* Tx function code */
-	ushort	spi_mrblr;	/* Max receive buffer length */
-	uint	spi_rstate;	/* Internal */
-	uint	spi_rdp;	/* Internal */
-	ushort	spi_rbptr;	/* Internal */
-	ushort	spi_rbc;	/* Internal */
-	uint	spi_rxtmp;	/* Internal */
-	uint	spi_tstate;	/* Internal */
-	uint	spi_tdp;	/* Internal */
-	ushort	spi_tbptr;	/* Internal */
-	ushort	spi_tbc;	/* Internal */
-	uint	spi_txtmp;	/* Internal */
-	uint	spi_res;
-	ushort	spi_rpbase;	/* Relocation pointer */
-	ushort	spi_res2;
-} spi_t;
-
-/* SPI Mode register.
-*/
-#define SPMODE_LOOP	((ushort)0x4000)	/* Loopback */
-#define SPMODE_CI	((ushort)0x2000)	/* Clock Invert */
-#define SPMODE_CP	((ushort)0x1000)	/* Clock Phase */
-#define SPMODE_DIV16	((ushort)0x0800)	/* BRG/16 mode */
-#define SPMODE_REV	((ushort)0x0400)	/* Reversed Data */
-#define SPMODE_MSTR	((ushort)0x0200)	/* SPI Master */
-#define SPMODE_EN	((ushort)0x0100)	/* Enable */
-#define SPMODE_LENMSK	((ushort)0x00f0)	/* character length */
-#define SPMODE_LEN4	((ushort)0x0030)	/*  4 bits per char */
-#define SPMODE_LEN8	((ushort)0x0070)	/*  8 bits per char */
-#define SPMODE_LEN16	((ushort)0x00f0)	/* 16 bits per char */
-#define SPMODE_PMMSK	((ushort)0x000f)	/* prescale modulus */
-
-/* SPIE fields */
-#define SPIE_MME	0x20
-#define SPIE_TXE	0x10
-#define SPIE_BSY	0x04
-#define SPIE_TXB	0x02
-#define SPIE_RXB	0x01
-
 /*
  * RISC Controller Configuration Register definitons
  */
diff --git a/arch/powerpc/include/asm/cpm2.h b/arch/powerpc/include/asm/cpm2.h
index 990ff191da8b..236cfa344a7c 100644
--- a/arch/powerpc/include/asm/cpm2.h
+++ b/arch/powerpc/include/asm/cpm2.h
@@ -654,45 +654,6 @@ typedef struct iic {
 	uint	iic_txtmp;	/* Internal */
 } iic_t;
 
-/* SPI parameter RAM.
-*/
-typedef struct spi {
-	ushort	spi_rbase;	/* Rx Buffer descriptor base address */
-	ushort	spi_tbase;	/* Tx Buffer descriptor base address */
-	u_char	spi_rfcr;	/* Rx function code */
-	u_char	spi_tfcr;	/* Tx function code */
-	ushort	spi_mrblr;	/* Max receive buffer length */
-	uint	spi_rstate;	/* Internal */
-	uint	spi_rdp;	/* Internal */
-	ushort	spi_rbptr;	/* Internal */
-	ushort	spi_rbc;	/* Internal */
-	uint	spi_rxtmp;	/* Internal */
-	uint	spi_tstate;	/* Internal */
-	uint	spi_tdp;	/* Internal */
-	ushort	spi_tbptr;	/* Internal */
-	ushort	spi_tbc;	/* Internal */
-	uint	spi_txtmp;	/* Internal */
-	uint	spi_res;	/* Tx temp. */
-	uint	spi_res1[4];	/* SDMA temp. */
-} spi_t;
-
-/* SPI Mode register.
-*/
-#define SPMODE_LOOP	((ushort)0x4000)	/* Loopback */
-#define SPMODE_CI	((ushort)0x2000)	/* Clock Invert */
-#define SPMODE_CP	((ushort)0x1000)	/* Clock Phase */
-#define SPMODE_DIV16	((ushort)0x0800)	/* BRG/16 mode */
-#define SPMODE_REV	((ushort)0x0400)	/* Reversed Data */
-#define SPMODE_MSTR	((ushort)0x0200)	/* SPI Master */
-#define SPMODE_EN	((ushort)0x0100)	/* Enable */
-#define SPMODE_LENMSK	((ushort)0x00f0)	/* character length */
-#define SPMODE_PMMSK	((ushort)0x000f)	/* prescale modulus */
-
-#define SPMODE_LEN(x)	((((x)-1)&0xF)<<4)
-#define SPMODE_PM(x)	((x) &0xF)
-
-#define SPI_EB		((u_char)0x10)		/* big endian byte order */
-
 /* IDMA parameter RAM
 */
 typedef struct idma {

From 80952988a2c6f0aa73e9ec6554084446da8d8791 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Mon, 12 Oct 2009 20:49:16 +0400
Subject: [PATCH 074/151] powerpc/qe&cpm2: Avoid redefinitions in CPM2 and QE
 headers

struct mcc defined in both immap_qe.h and immap_cpm2.h, so they will
conflic when included in a single file. The mcc struct is easy to deal
with, since it isn't used in any driver (yet), so let's just rename QE
version to qe_mcc.

The ucb_ctlr is a bit trickier, since it is used by fsl_qe_udc driver,
and the driver supports both CPM and QE UDCs, plus the QE version is
used to form a bigger immap struct.

I don't want to touch too much of USB code in this series, so for now
let's just copy most generic version into the common cpm.h header,
later we'll create cpm_usb.h where we'll place common USB structs that
are used by QE/CPM UDC and QE Host drivers (FHCI).

And as for the structs in qe.h and cpm2.h, just prefix them with qe_
and cpm_.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/include/asm/cpm.h        | 22 ++++++++++++++++++++++
 arch/powerpc/include/asm/immap_cpm2.h |  2 +-
 arch/powerpc/include/asm/immap_qe.h   |  8 ++++----
 3 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/include/asm/cpm.h b/arch/powerpc/include/asm/cpm.h
index 24d79e3abd8e..b5f15340dc22 100644
--- a/arch/powerpc/include/asm/cpm.h
+++ b/arch/powerpc/include/asm/cpm.h
@@ -5,6 +5,28 @@
 #include <linux/types.h>
 #include <linux/of.h>
 
+/*
+ * USB Controller pram common to QE and CPM.
+ */
+struct usb_ctlr {
+	u8	usb_usmod;
+	u8	usb_usadr;
+	u8	usb_uscom;
+	u8	res1[1];
+	__be16	usb_usep[4];
+	u8	res2[4];
+	__be16	usb_usber;
+	u8	res3[2];
+	__be16	usb_usbmr;
+	u8	res4[1];
+	u8	usb_usbs;
+	/* Fields down below are QE-only */
+	__be16	usb_ussft;
+	u8	res5[2];
+	__be16	usb_usfrn;
+	u8	res6[0x22];
+} __attribute__ ((packed));
+
 /* Opcodes common to CPM1 and CPM2
 */
 #define CPM_CR_INIT_TRX		((ushort)0x0000)
diff --git a/arch/powerpc/include/asm/immap_cpm2.h b/arch/powerpc/include/asm/immap_cpm2.h
index d4f069bf0e57..7c64fda5357b 100644
--- a/arch/powerpc/include/asm/immap_cpm2.h
+++ b/arch/powerpc/include/asm/immap_cpm2.h
@@ -549,7 +549,7 @@ typedef struct comm_proc {
 
 /* USB Controller.
 */
-typedef struct usb_ctlr {
+typedef struct cpm_usb_ctlr {
 	u8	usb_usmod;
 	u8	usb_usadr;
 	u8	usb_uscom;
diff --git a/arch/powerpc/include/asm/immap_qe.h b/arch/powerpc/include/asm/immap_qe.h
index c346d0bcd230..4e10f508570a 100644
--- a/arch/powerpc/include/asm/immap_qe.h
+++ b/arch/powerpc/include/asm/immap_qe.h
@@ -210,7 +210,7 @@ struct sir {
 } __attribute__ ((packed));
 
 /* USB Controller */
-struct usb_ctlr {
+struct qe_usb_ctlr {
 	u8	usb_usmod;
 	u8	usb_usadr;
 	u8	usb_uscom;
@@ -229,7 +229,7 @@ struct usb_ctlr {
 } __attribute__ ((packed));
 
 /* MCC */
-struct mcc {
+struct qe_mcc {
 	__be32	mcce;		/* MCC event register */
 	__be32	mccm;		/* MCC mask register */
 	__be32	mccf;		/* MCC configuration register */
@@ -431,9 +431,9 @@ struct qe_immap {
 	struct qe_mux		qmx;		/* QE Multiplexer */
 	struct qe_timers	qet;		/* QE Timers */
 	struct spi		spi[0x2];	/* spi */
-	struct mcc		mcc;		/* mcc */
+	struct qe_mcc		mcc;		/* mcc */
 	struct qe_brg		brg;		/* brg */
-	struct usb_ctlr		usb;		/* USB */
+	struct qe_usb_ctlr	usb;		/* USB */
 	struct si1		si1;		/* SI */
 	u8			res11[0x800];
 	struct sir		sir;		/* SI Routing Tables */

From 71d94fe842c34fb93eb32ae20207bea757292b79 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Mon, 12 Oct 2009 20:49:18 +0400
Subject: [PATCH 075/151] powerpc/cpm: Move CPMFCR_* defines into cpm.h

The bits are generic to CPM devices, so let's move them to the
common header file, so drivers won't need to privately reintroduce
another bunch of the same bits (as we can't include cpm2.h header
together with cpm1.h).

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/include/asm/cpm.h  | 16 ++++++++++++++++
 arch/powerpc/include/asm/cpm2.h |  8 --------
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/include/asm/cpm.h b/arch/powerpc/include/asm/cpm.h
index b5f15340dc22..ea3fdb9fe257 100644
--- a/arch/powerpc/include/asm/cpm.h
+++ b/arch/powerpc/include/asm/cpm.h
@@ -27,6 +27,22 @@ struct usb_ctlr {
 	u8	res6[0x22];
 } __attribute__ ((packed));
 
+/*
+ * Function code bits, usually generic to devices.
+ */
+#ifdef CONFIG_CPM1
+#define CPMFCR_GBL	((u_char)0x00)	/* Flag doesn't exist in CPM1 */
+#define CPMFCR_TC2	((u_char)0x00)	/* Flag doesn't exist in CPM1 */
+#define CPMFCR_DTB	((u_char)0x00)	/* Flag doesn't exist in CPM1 */
+#define CPMFCR_BDB	((u_char)0x00)	/* Flag doesn't exist in CPM1 */
+#else
+#define CPMFCR_GBL	((u_char)0x20)	/* Set memory snooping */
+#define CPMFCR_TC2	((u_char)0x04)	/* Transfer code 2 value */
+#define CPMFCR_DTB	((u_char)0x02)	/* Use local bus for data when set */
+#define CPMFCR_BDB	((u_char)0x01)	/* Use local bus for BD when set */
+#endif
+#define CPMFCR_EB	((u_char)0x10)	/* Set big endian byte order */
+
 /* Opcodes common to CPM1 and CPM2
 */
 #define CPM_CR_INIT_TRX		((ushort)0x0000)
diff --git a/arch/powerpc/include/asm/cpm2.h b/arch/powerpc/include/asm/cpm2.h
index 236cfa344a7c..f42e9baf3a4e 100644
--- a/arch/powerpc/include/asm/cpm2.h
+++ b/arch/powerpc/include/asm/cpm2.h
@@ -124,14 +124,6 @@ static inline void cpm2_fastbrg(uint brg, uint rate, int div16)
 	__cpm2_setbrg(brg, rate, CPM2_BRG_INT_CLK, div16, CPM_BRG_EXTC_INT);
 }
 
-/* Function code bits, usually generic to devices.
-*/
-#define CPMFCR_GBL	((u_char)0x20)	/* Set memory snooping */
-#define CPMFCR_EB	((u_char)0x10)	/* Set big endian byte order */
-#define CPMFCR_TC2	((u_char)0x04)	/* Transfer code 2 value */
-#define CPMFCR_DTB	((u_char)0x02)	/* Use local bus for data when set */
-#define CPMFCR_BDB	((u_char)0x01)	/* Use local bus for BD when set */
-
 /* Parameter RAM offsets from the base.
 */
 #define PROFF_SCC1		((uint)0x8000)

From 58c12bdc5d924e4bca60c2660df2a71be4953ac9 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Mon, 12 Oct 2009 20:49:20 +0400
Subject: [PATCH 076/151] powerpc/qe&cpm: Implement static inline stubs for
 non-QE/CPM builds

This is needed to avoid ugly #ifdefs in drivers. Also update fsl_qe_udc
driver so that now it doesn't define its own versions that cause build
breakage when the generic stubs are used.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/include/asm/cpm.h  | 44 +++++++++++++++++++++++++++++++++
 arch/powerpc/include/asm/qe.h   | 11 ++++++++-
 drivers/usb/gadget/fsl_qe_udc.h | 15 -----------
 3 files changed, 54 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/include/asm/cpm.h b/arch/powerpc/include/asm/cpm.h
index ea3fdb9fe257..0835eb977ba9 100644
--- a/arch/powerpc/include/asm/cpm.h
+++ b/arch/powerpc/include/asm/cpm.h
@@ -3,6 +3,7 @@
 
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include <linux/errno.h>
 #include <linux/of.h>
 
 /*
@@ -131,13 +132,56 @@ typedef struct cpm_buf_desc {
 #define BD_I2C_START		(0x0400)
 
 int cpm_muram_init(void);
+
+#if defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE)
 unsigned long cpm_muram_alloc(unsigned long size, unsigned long align);
 int cpm_muram_free(unsigned long offset);
 unsigned long cpm_muram_alloc_fixed(unsigned long offset, unsigned long size);
 void __iomem *cpm_muram_addr(unsigned long offset);
 unsigned long cpm_muram_offset(void __iomem *addr);
 dma_addr_t cpm_muram_dma(void __iomem *addr);
+#else
+static inline unsigned long cpm_muram_alloc(unsigned long size,
+					    unsigned long align)
+{
+	return -ENOSYS;
+}
+
+static inline int cpm_muram_free(unsigned long offset)
+{
+	return -ENOSYS;
+}
+
+static inline unsigned long cpm_muram_alloc_fixed(unsigned long offset,
+						  unsigned long size)
+{
+	return -ENOSYS;
+}
+
+static inline void __iomem *cpm_muram_addr(unsigned long offset)
+{
+	return NULL;
+}
+
+static inline unsigned long cpm_muram_offset(void __iomem *addr)
+{
+	return -ENOSYS;
+}
+
+static inline dma_addr_t cpm_muram_dma(void __iomem *addr)
+{
+	return 0;
+}
+#endif /* defined(CONFIG_CPM) || defined(CONFIG_QUICC_ENGINE) */
+
+#ifdef CONFIG_CPM
 int cpm_command(u32 command, u8 opcode);
+#else
+static inline int cpm_command(u32 command, u8 opcode)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_CPM */
 
 int cpm2_gpiochip_add32(struct device_node *np);
 
diff --git a/arch/powerpc/include/asm/qe.h b/arch/powerpc/include/asm/qe.h
index 5e0e8b2b0aa1..0947b36e534c 100644
--- a/arch/powerpc/include/asm/qe.h
+++ b/arch/powerpc/include/asm/qe.h
@@ -145,8 +145,17 @@ static inline void qe_pin_set_gpio(struct qe_pin *qe_pin) {}
 static inline void qe_pin_set_dedicated(struct qe_pin *pin) {}
 #endif /* CONFIG_QE_GPIO */
 
-/* QE internal API */
+#ifdef CONFIG_QUICC_ENGINE
 int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol, u32 cmd_input);
+#else
+static inline int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol,
+			       u32 cmd_input)
+{
+	return -ENOSYS;
+}
+#endif /* CONFIG_QUICC_ENGINE */
+
+/* QE internal API */
 enum qe_clock qe_clock_source(const char *source);
 unsigned int qe_get_brg_clk(void);
 int qe_setbrg(enum qe_clock brg, unsigned int rate, unsigned int multiplier);
diff --git a/drivers/usb/gadget/fsl_qe_udc.h b/drivers/usb/gadget/fsl_qe_udc.h
index 31b2710882e4..bea5b827bebe 100644
--- a/drivers/usb/gadget/fsl_qe_udc.h
+++ b/drivers/usb/gadget/fsl_qe_udc.h
@@ -419,19 +419,4 @@ struct qe_udc {
 #define CPM_USB_RESTART_TX_OPCODE 0x0b
 #define CPM_USB_EP_SHIFT 5
 
-#ifndef CONFIG_CPM
-inline int cpm_command(u32 command, u8 opcode)
-{
-	return -EOPNOTSUPP;
-}
-#endif
-
-#ifndef CONFIG_QUICC_ENGINE
-inline int qe_issue_cmd(u32 cmd, u32 device, u8 mcn_protocol,
-	u32 cmd_input)
-{
-	return -EOPNOTSUPP;
-}
-#endif
-
 #endif  /* __FSL_QE_UDC_H */

From 783058fd582a1d8afbbf1d4e9b7918614a4550ff Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Mon, 12 Oct 2009 20:49:22 +0400
Subject: [PATCH 077/151] spi_mpc8xxx: Fix uninitialized variable

This patch fixes the following warning:

CC      drivers/spi/spi_mpc8xxx.o
  spi_mpc8xxx.c: In function 'of_mpc8xxx_spi_probe':
  spi_mpc8xxx.c:681: warning: 'ret' may be used uninitialized in this function

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Acked-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 drivers/spi/spi_mpc8xxx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/spi/spi_mpc8xxx.c b/drivers/spi/spi_mpc8xxx.c
index 0fd0ec4d3a7d..518671b8afe5 100644
--- a/drivers/spi/spi_mpc8xxx.c
+++ b/drivers/spi/spi_mpc8xxx.c
@@ -709,6 +709,7 @@ static int of_mpc8xxx_spi_get_chipselects(struct device *dev)
 		gpio = of_get_gpio_flags(np, i, &flags);
 		if (!gpio_is_valid(gpio)) {
 			dev_err(dev, "invalid gpio #%d: %d\n", i, gpio);
+			ret = gpio;
 			goto err_loop;
 		}
 

From a35c1710956f7aef06f58d22d343d7b948fbc272 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Mon, 12 Oct 2009 20:49:24 +0400
Subject: [PATCH 078/151] spi_mpc8xxx: Factor out SPI mode change steps into a
 call

We'll add more steps soon, so get rid of the duplication.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Acked-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 drivers/spi/spi_mpc8xxx.c | 52 +++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 30 deletions(-)

diff --git a/drivers/spi/spi_mpc8xxx.c b/drivers/spi/spi_mpc8xxx.c
index 518671b8afe5..4b119eaf4e6b 100644
--- a/drivers/spi/spi_mpc8xxx.c
+++ b/drivers/spi/spi_mpc8xxx.c
@@ -155,6 +155,26 @@ MPC83XX_SPI_TX_BUF(u8)
 MPC83XX_SPI_TX_BUF(u16)
 MPC83XX_SPI_TX_BUF(u32)
 
+static void mpc8xxx_spi_change_mode(struct spi_device *spi)
+{
+	struct mpc8xxx_spi *mspi = spi_master_get_devdata(spi->master);
+	struct spi_mpc8xxx_cs *cs = spi->controller_state;
+	__be32 __iomem *mode = &mspi->base->mode;
+	unsigned long flags;
+
+	if (cs->hw_mode == mpc8xxx_spi_read_reg(mode))
+		return;
+
+	/* Turn off IRQs locally to minimize time that SPI is disabled. */
+	local_irq_save(flags);
+
+	/* Turn off SPI unit prior changing mode */
+	mpc8xxx_spi_write_reg(mode, cs->hw_mode & ~SPMODE_ENABLE);
+	mpc8xxx_spi_write_reg(mode, cs->hw_mode);
+
+	local_irq_restore(flags);
+}
+
 static void mpc8xxx_spi_chipselect(struct spi_device *spi, int value)
 {
 	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
@@ -168,27 +188,13 @@ static void mpc8xxx_spi_chipselect(struct spi_device *spi, int value)
 	}
 
 	if (value == BITBANG_CS_ACTIVE) {
-		u32 regval = mpc8xxx_spi_read_reg(&mpc8xxx_spi->base->mode);
-
 		mpc8xxx_spi->rx_shift = cs->rx_shift;
 		mpc8xxx_spi->tx_shift = cs->tx_shift;
 		mpc8xxx_spi->get_rx = cs->get_rx;
 		mpc8xxx_spi->get_tx = cs->get_tx;
 
-		if (cs->hw_mode != regval) {
-			unsigned long flags;
-			__be32 __iomem *mode = &mpc8xxx_spi->base->mode;
+		mpc8xxx_spi_change_mode(spi);
 
-			regval = cs->hw_mode;
-			/* Turn off IRQs locally to minimize time that
-			 * SPI is disabled
-			 */
-			local_irq_save(flags);
-			/* Turn off SPI unit prior changing mode */
-			mpc8xxx_spi_write_reg(mode, regval & ~SPMODE_ENABLE);
-			mpc8xxx_spi_write_reg(mode, regval);
-			local_irq_restore(flags);
-		}
 		if (pdata->cs_control)
 			pdata->cs_control(spi, pol);
 	}
@@ -198,7 +204,6 @@ static
 int mpc8xxx_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 {
 	struct mpc8xxx_spi *mpc8xxx_spi;
-	u32 regval;
 	u8 bits_per_word, pm;
 	u32 hz;
 	struct spi_mpc8xxx_cs	*cs = spi->controller_state;
@@ -286,21 +291,8 @@ int mpc8xxx_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 		pm--;
 
 	cs->hw_mode |= SPMODE_PM(pm);
-	regval =  mpc8xxx_spi_read_reg(&mpc8xxx_spi->base->mode);
-	if (cs->hw_mode != regval) {
-		unsigned long flags;
-		__be32 __iomem *mode = &mpc8xxx_spi->base->mode;
 
-		regval = cs->hw_mode;
-		/* Turn off IRQs locally to minimize time
-		 * that SPI is disabled
-		 */
-		local_irq_save(flags);
-		/* Turn off SPI unit prior changing mode */
-		mpc8xxx_spi_write_reg(mode, regval & ~SPMODE_ENABLE);
-		mpc8xxx_spi_write_reg(mode, regval);
-		local_irq_restore(flags);
-	}
+	mpc8xxx_spi_change_mode(spi);
 	return 0;
 }
 

From 87ec0e98cfdd8b68da6a7f9e70142ffc0e404fbb Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Mon, 12 Oct 2009 20:49:25 +0400
Subject: [PATCH 079/151] spi_mpc8xxx: Turn qe_mode into flags

Soon there will be more flags introduced in subsequent patches, so
let's turn qe_mode into flags.

Also introduce mpc8xxx_spi_strmode() and print current SPI mode.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Acked-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 drivers/spi/spi_mpc8xxx.c   | 30 +++++++++++++++++++-----------
 include/linux/fsl_devices.h |  2 +-
 2 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/drivers/spi/spi_mpc8xxx.c b/drivers/spi/spi_mpc8xxx.c
index 4b119eaf4e6b..80374dfa9708 100644
--- a/drivers/spi/spi_mpc8xxx.c
+++ b/drivers/spi/spi_mpc8xxx.c
@@ -96,7 +96,8 @@ struct mpc8xxx_spi {
 	u32 rx_shift;		/* RX data reg shift when in qe mode */
 	u32 tx_shift;		/* TX data reg shift when in qe mode */
 
-	bool qe_mode;
+	unsigned int flags;
+#define SPI_QE_CPU_MODE		(1 << 0) /* QE CPU ("PIO") mode */
 
 	struct workqueue_struct *workqueue;
 	struct work_struct work;
@@ -235,14 +236,14 @@ int mpc8xxx_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 	if (bits_per_word <= 8) {
 		cs->get_rx = mpc8xxx_spi_rx_buf_u8;
 		cs->get_tx = mpc8xxx_spi_tx_buf_u8;
-		if (mpc8xxx_spi->qe_mode) {
+		if (mpc8xxx_spi->flags & SPI_QE_CPU_MODE) {
 			cs->rx_shift = 16;
 			cs->tx_shift = 24;
 		}
 	} else if (bits_per_word <= 16) {
 		cs->get_rx = mpc8xxx_spi_rx_buf_u16;
 		cs->get_tx = mpc8xxx_spi_tx_buf_u16;
-		if (mpc8xxx_spi->qe_mode) {
+		if (mpc8xxx_spi->flags & SPI_QE_CPU_MODE) {
 			cs->rx_shift = 16;
 			cs->tx_shift = 16;
 		}
@@ -252,7 +253,8 @@ int mpc8xxx_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 	} else
 		return -EINVAL;
 
-	if (mpc8xxx_spi->qe_mode && spi->mode & SPI_LSB_FIRST) {
+	if (mpc8xxx_spi->flags & SPI_QE_CPU_MODE &&
+			spi->mode & SPI_LSB_FIRST) {
 		cs->tx_shift = 0;
 		if (bits_per_word <= 8)
 			cs->rx_shift = 8;
@@ -518,6 +520,13 @@ static void mpc8xxx_spi_cleanup(struct spi_device *spi)
 	kfree(spi->controller_state);
 }
 
+static const char *mpc8xxx_spi_strmode(unsigned int flags)
+{
+	if (flags & SPI_QE_CPU_MODE)
+		return "QE CPU";
+	return "CPU";
+}
+
 static struct spi_master * __devinit
 mpc8xxx_spi_probe(struct device *dev, struct resource *mem, unsigned int irq)
 {
@@ -544,14 +553,14 @@ mpc8xxx_spi_probe(struct device *dev, struct resource *mem, unsigned int irq)
 	master->cleanup = mpc8xxx_spi_cleanup;
 
 	mpc8xxx_spi = spi_master_get_devdata(master);
-	mpc8xxx_spi->qe_mode = pdata->qe_mode;
 	mpc8xxx_spi->get_rx = mpc8xxx_spi_rx_buf_u8;
 	mpc8xxx_spi->get_tx = mpc8xxx_spi_tx_buf_u8;
+	mpc8xxx_spi->flags = pdata->flags;
 	mpc8xxx_spi->spibrg = pdata->sysclk;
 
 	mpc8xxx_spi->rx_shift = 0;
 	mpc8xxx_spi->tx_shift = 0;
-	if (mpc8xxx_spi->qe_mode) {
+	if (mpc8xxx_spi->flags & SPI_QE_CPU_MODE) {
 		mpc8xxx_spi->rx_shift = 16;
 		mpc8xxx_spi->tx_shift = 24;
 	}
@@ -584,7 +593,7 @@ mpc8xxx_spi_probe(struct device *dev, struct resource *mem, unsigned int irq)
 
 	/* Enable SPI interface */
 	regval = pdata->initial_spmode | SPMODE_INIT_VAL | SPMODE_ENABLE;
-	if (pdata->qe_mode)
+	if (mpc8xxx_spi->flags & SPI_QE_CPU_MODE)
 		regval |= SPMODE_OP;
 
 	mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->mode, regval);
@@ -604,9 +613,8 @@ mpc8xxx_spi_probe(struct device *dev, struct resource *mem, unsigned int irq)
 	if (ret < 0)
 		goto unreg_master;
 
-	printk(KERN_INFO
-	       "%s: MPC8xxx SPI Controller driver at 0x%p (irq = %d)\n",
-	       dev_name(dev), mpc8xxx_spi->base, mpc8xxx_spi->irq);
+	dev_info(dev, "at 0x%p (irq = %d), %s mode\n", mpc8xxx_spi->base,
+		 mpc8xxx_spi->irq, mpc8xxx_spi_strmode(mpc8xxx_spi->flags));
 
 	return master;
 
@@ -797,7 +805,7 @@ static int __devinit of_mpc8xxx_spi_probe(struct of_device *ofdev,
 
 	prop = of_get_property(np, "mode", NULL);
 	if (prop && !strcmp(prop, "cpu-qe"))
-		pdata->qe_mode = 1;
+		pdata->flags = SPI_QE_CPU_MODE;
 
 	ret = of_mpc8xxx_spi_get_chipselects(dev);
 	if (ret)
diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h
index 43fc95d822d5..39fd94681e74 100644
--- a/include/linux/fsl_devices.h
+++ b/include/linux/fsl_devices.h
@@ -74,7 +74,7 @@ struct spi_device;
 struct fsl_spi_platform_data {
 	u32 	initial_spmode;	/* initial SPMODE value */
 	s16	bus_num;
-	bool	qe_mode;
+	unsigned int flags;
 	/* board specific information */
 	u16	max_chipselect;
 	void	(*cs_control)(struct spi_device *spi, bool on);

From 4c1fba442960cfa2fd6333b9fec7d5b85c5fa29f Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Mon, 12 Oct 2009 20:49:27 +0400
Subject: [PATCH 080/151] spi_mpc8xxx: Add support for QE DMA mode and
 CPM1/CPM2 chips

This patch adds QE buffer descriptors mode support for the
spi_mpc8xxx driver, and as a side effect we now support CPM1
and CPM2 SPI controllers.

That means that today we support almost all MPC SPI controllers:

- MPC834x-style controllers (support PIO mode only);
- CPM1 and CPM2 controllers (support DMA mode only);
- QE SPI controllers in CPU mode (PIO mode with shift quirks);
- QE SPI controllers in buffer descriptors (DMA) mode;

The only controller we don't currently support is a newer eSPI
(with a dedicated chip selects and a bit different registers map).

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Acked-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 drivers/spi/Kconfig       |   3 -
 drivers/spi/spi_mpc8xxx.c | 556 ++++++++++++++++++++++++++++++++++----
 2 files changed, 508 insertions(+), 51 deletions(-)

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 4b6f7cba3b3d..94058c62620a 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -147,9 +147,6 @@ config SPI_MPC8xxx
 	  This enables using the Freescale MPC8xxx SPI controllers in master
 	  mode.
 
-	  This driver uses a simple set of shift registers for data (opposed
-	  to the CPM based descriptor model).
-
 config SPI_OMAP_UWIRE
 	tristate "OMAP1 MicroWire"
 	depends on ARCH_OMAP1
diff --git a/drivers/spi/spi_mpc8xxx.c b/drivers/spi/spi_mpc8xxx.c
index 80374dfa9708..394b6581e17f 100644
--- a/drivers/spi/spi_mpc8xxx.c
+++ b/drivers/spi/spi_mpc8xxx.c
@@ -5,6 +5,10 @@
  *
  * Copyright (C) 2006 Polycom, Inc.
  *
+ * CPM SPI and QE buffer descriptors mode support:
+ * Copyright (c) 2009  MontaVista Software, Inc.
+ * Author: Anton Vorontsov <avorontsov@ru.mvista.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
@@ -27,6 +31,9 @@
 #include <linux/spi/spi_bitbang.h>
 #include <linux/platform_device.h>
 #include <linux/fsl_devices.h>
+#include <linux/dma-mapping.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/gpio.h>
@@ -34,8 +41,19 @@
 #include <linux/of_spi.h>
 
 #include <sysdev/fsl_soc.h>
+#include <asm/cpm.h>
+#include <asm/qe.h>
 #include <asm/irq.h>
 
+/* CPM1 and CPM2 are mutually exclusive. */
+#ifdef CONFIG_CPM1
+#include <asm/cpm1.h>
+#define CPM_SPI_CMD mk_cr_cmd(CPM_CR_CH_SPI, 0)
+#else
+#include <asm/cpm2.h>
+#define CPM_SPI_CMD mk_cr_cmd(CPM_CR_SPI_PAGE, CPM_CR_SPI_SBLOCK, 0, 0)
+#endif
+
 /* SPI Controller registers */
 struct mpc8xxx_spi_reg {
 	u8 res1[0x20];
@@ -47,6 +65,28 @@ struct mpc8xxx_spi_reg {
 	__be32 receive;
 };
 
+/* SPI Parameter RAM */
+struct spi_pram {
+	__be16	rbase;	/* Rx Buffer descriptor base address */
+	__be16	tbase;	/* Tx Buffer descriptor base address */
+	u8	rfcr;	/* Rx function code */
+	u8	tfcr;	/* Tx function code */
+	__be16	mrblr;	/* Max receive buffer length */
+	__be32	rstate;	/* Internal */
+	__be32	rdp;	/* Internal */
+	__be16	rbptr;	/* Internal */
+	__be16	rbc;	/* Internal */
+	__be32	rxtmp;	/* Internal */
+	__be32	tstate;	/* Internal */
+	__be32	tdp;	/* Internal */
+	__be16	tbptr;	/* Internal */
+	__be16	tbc;	/* Internal */
+	__be32	txtmp;	/* Internal */
+	__be32	res;	/* Tx temp. */
+	__be16  rpbase;	/* Relocation pointer (CPM1 only) */
+	__be16	res1;	/* Reserved */
+};
+
 /* SPI Controller mode register definitions */
 #define	SPMODE_LOOP		(1 << 30)
 #define	SPMODE_CI_INACTIVEHIGH	(1 << 29)
@@ -75,14 +115,40 @@ struct mpc8xxx_spi_reg {
 #define	SPIM_NE		0x00000200	/* Not empty */
 #define	SPIM_NF		0x00000100	/* Not full */
 
+#define	SPIE_TXB	0x00000200	/* Last char is written to tx fifo */
+#define	SPIE_RXB	0x00000100	/* Last char is written to rx buf */
+
+/* SPCOM register values */
+#define	SPCOM_STR	(1 << 23)	/* Start transmit */
+
+#define	SPI_PRAM_SIZE	0x100
+#define	SPI_MRBLR	((unsigned int)PAGE_SIZE)
+
 /* SPI Controller driver's private data. */
 struct mpc8xxx_spi {
+	struct device *dev;
 	struct mpc8xxx_spi_reg __iomem *base;
 
 	/* rx & tx bufs from the spi_transfer */
 	const void *tx;
 	void *rx;
 
+	int subblock;
+	struct spi_pram __iomem *pram;
+	struct cpm_buf_desc __iomem *tx_bd;
+	struct cpm_buf_desc __iomem *rx_bd;
+
+	struct spi_transfer *xfer_in_progress;
+
+	/* dma addresses for CPM transfers */
+	dma_addr_t tx_dma;
+	dma_addr_t rx_dma;
+	bool map_tx_dma;
+	bool map_rx_dma;
+
+	dma_addr_t dma_dummy_tx;
+	dma_addr_t dma_dummy_rx;
+
 	/* functions to deal with different sized buffers */
 	void (*get_rx) (u32 rx_data, struct mpc8xxx_spi *);
 	u32(*get_tx) (struct mpc8xxx_spi *);
@@ -98,6 +164,10 @@ struct mpc8xxx_spi {
 
 	unsigned int flags;
 #define SPI_QE_CPU_MODE		(1 << 0) /* QE CPU ("PIO") mode */
+#define SPI_CPM_MODE		(1 << 1) /* CPM/QE ("DMA") mode */
+#define SPI_CPM1		(1 << 2) /* SPI unit is in CPM1 block */
+#define SPI_CPM2		(1 << 3) /* SPI unit is in CPM2 block */
+#define SPI_QE			(1 << 4) /* SPI unit is in QE block */
 
 	struct workqueue_struct *workqueue;
 	struct work_struct work;
@@ -108,6 +178,10 @@ struct mpc8xxx_spi {
 	struct completion done;
 };
 
+static void *mpc8xxx_dummy_rx;
+static DEFINE_MUTEX(mpc8xxx_dummy_rx_lock);
+static int mpc8xxx_dummy_rx_refcnt;
+
 struct spi_mpc8xxx_cs {
 	/* functions to deal with different sized buffers */
 	void (*get_rx) (u32 rx_data, struct mpc8xxx_spi *);
@@ -173,6 +247,22 @@ static void mpc8xxx_spi_change_mode(struct spi_device *spi)
 	mpc8xxx_spi_write_reg(mode, cs->hw_mode & ~SPMODE_ENABLE);
 	mpc8xxx_spi_write_reg(mode, cs->hw_mode);
 
+	/* When in CPM mode, we need to reinit tx and rx. */
+	if (mspi->flags & SPI_CPM_MODE) {
+		if (mspi->flags & SPI_QE) {
+			qe_issue_cmd(QE_INIT_TX_RX, mspi->subblock,
+				     QE_CR_PROTOCOL_UNSPECIFIED, 0);
+		} else {
+			cpm_command(CPM_SPI_CMD, CPM_CR_INIT_TRX);
+			if (mspi->flags & SPI_CPM1) {
+				out_be16(&mspi->pram->rbptr,
+					 in_be16(&mspi->pram->rbase));
+				out_be16(&mspi->pram->tbptr,
+					 in_be16(&mspi->pram->tbase));
+			}
+		}
+	}
+
 	local_irq_restore(flags);
 }
 
@@ -298,19 +388,133 @@ int mpc8xxx_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 	return 0;
 }
 
-static int mpc8xxx_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
+static void mpc8xxx_spi_cpm_bufs_start(struct mpc8xxx_spi *mspi)
 {
-	struct mpc8xxx_spi *mpc8xxx_spi;
-	u32 word, len, bits_per_word;
+	struct cpm_buf_desc __iomem *tx_bd = mspi->tx_bd;
+	struct cpm_buf_desc __iomem *rx_bd = mspi->rx_bd;
+	unsigned int xfer_len = min(mspi->count, SPI_MRBLR);
+	unsigned int xfer_ofs;
 
-	mpc8xxx_spi = spi_master_get_devdata(spi->master);
+	xfer_ofs = mspi->xfer_in_progress->len - mspi->count;
+
+	out_be32(&rx_bd->cbd_bufaddr, mspi->rx_dma + xfer_ofs);
+	out_be16(&rx_bd->cbd_datlen, 0);
+	out_be16(&rx_bd->cbd_sc, BD_SC_EMPTY | BD_SC_INTRPT | BD_SC_WRAP);
+
+	out_be32(&tx_bd->cbd_bufaddr, mspi->tx_dma + xfer_ofs);
+	out_be16(&tx_bd->cbd_datlen, xfer_len);
+	out_be16(&tx_bd->cbd_sc, BD_SC_READY | BD_SC_INTRPT | BD_SC_WRAP |
+				 BD_SC_LAST);
+
+	/* start transfer */
+	mpc8xxx_spi_write_reg(&mspi->base->command, SPCOM_STR);
+}
+
+static int mpc8xxx_spi_cpm_bufs(struct mpc8xxx_spi *mspi,
+				struct spi_transfer *t, bool is_dma_mapped)
+{
+	struct device *dev = mspi->dev;
+
+	if (is_dma_mapped) {
+		mspi->map_tx_dma = 0;
+		mspi->map_rx_dma = 0;
+	} else {
+		mspi->map_tx_dma = 1;
+		mspi->map_rx_dma = 1;
+	}
+
+	if (!t->tx_buf) {
+		mspi->tx_dma = mspi->dma_dummy_tx;
+		mspi->map_tx_dma = 0;
+	}
+
+	if (!t->rx_buf) {
+		mspi->rx_dma = mspi->dma_dummy_rx;
+		mspi->map_rx_dma = 0;
+	}
+
+	if (mspi->map_tx_dma) {
+		void *nonconst_tx = (void *)mspi->tx; /* shut up gcc */
+
+		mspi->tx_dma = dma_map_single(dev, nonconst_tx, t->len,
+					      DMA_TO_DEVICE);
+		if (dma_mapping_error(dev, mspi->tx_dma)) {
+			dev_err(dev, "unable to map tx dma\n");
+			return -ENOMEM;
+		}
+	} else {
+		mspi->tx_dma = t->tx_dma;
+	}
+
+	if (mspi->map_rx_dma) {
+		mspi->rx_dma = dma_map_single(dev, mspi->rx, t->len,
+					      DMA_FROM_DEVICE);
+		if (dma_mapping_error(dev, mspi->rx_dma)) {
+			dev_err(dev, "unable to map rx dma\n");
+			goto err_rx_dma;
+		}
+	} else {
+		mspi->rx_dma = t->rx_dma;
+	}
+
+	/* enable rx ints */
+	mpc8xxx_spi_write_reg(&mspi->base->mask, SPIE_RXB);
+
+	mspi->xfer_in_progress = t;
+	mspi->count = t->len;
+
+	/* start CPM transfers */
+	mpc8xxx_spi_cpm_bufs_start(mspi);
+
+	return 0;
+
+err_rx_dma:
+	if (mspi->map_tx_dma)
+		dma_unmap_single(dev, mspi->tx_dma, t->len, DMA_TO_DEVICE);
+	return -ENOMEM;
+}
+
+static void mpc8xxx_spi_cpm_bufs_complete(struct mpc8xxx_spi *mspi)
+{
+	struct device *dev = mspi->dev;
+	struct spi_transfer *t = mspi->xfer_in_progress;
+
+	if (mspi->map_tx_dma)
+		dma_unmap_single(dev, mspi->tx_dma, t->len, DMA_TO_DEVICE);
+	if (mspi->map_tx_dma)
+		dma_unmap_single(dev, mspi->rx_dma, t->len, DMA_FROM_DEVICE);
+	mspi->xfer_in_progress = NULL;
+}
+
+static int mpc8xxx_spi_cpu_bufs(struct mpc8xxx_spi *mspi,
+				struct spi_transfer *t, unsigned int len)
+{
+	u32 word;
+
+	mspi->count = len;
+
+	/* enable rx ints */
+	mpc8xxx_spi_write_reg(&mspi->base->mask, SPIM_NE);
+
+	/* transmit word */
+	word = mspi->get_tx(mspi);
+	mpc8xxx_spi_write_reg(&mspi->base->transmit, word);
+
+	return 0;
+}
+
+static int mpc8xxx_spi_bufs(struct spi_device *spi, struct spi_transfer *t,
+			    bool is_dma_mapped)
+{
+	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
+	unsigned int len = t->len;
+	u8 bits_per_word;
+	int ret;
 
-	mpc8xxx_spi->tx = t->tx_buf;
-	mpc8xxx_spi->rx = t->rx_buf;
 	bits_per_word = spi->bits_per_word;
 	if (t->bits_per_word)
 		bits_per_word = t->bits_per_word;
-	len = t->len;
+
 	if (bits_per_word > 8) {
 		/* invalid length? */
 		if (len & 1)
@@ -323,22 +527,27 @@ static int mpc8xxx_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
 			return -EINVAL;
 		len /= 2;
 	}
-	mpc8xxx_spi->count = len;
+
+	mpc8xxx_spi->tx = t->tx_buf;
+	mpc8xxx_spi->rx = t->rx_buf;
 
 	INIT_COMPLETION(mpc8xxx_spi->done);
 
-	/* enable rx ints */
-	mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->mask, SPIM_NE);
-
-	/* transmit word */
-	word = mpc8xxx_spi->get_tx(mpc8xxx_spi);
-	mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->transmit, word);
+	if (mpc8xxx_spi->flags & SPI_CPM_MODE)
+		ret = mpc8xxx_spi_cpm_bufs(mpc8xxx_spi, t, is_dma_mapped);
+	else
+		ret = mpc8xxx_spi_cpu_bufs(mpc8xxx_spi, t, len);
+	if (ret)
+		return ret;
 
 	wait_for_completion(&mpc8xxx_spi->done);
 
 	/* disable rx ints */
 	mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->mask, 0);
 
+	if (mpc8xxx_spi->flags & SPI_CPM_MODE)
+		mpc8xxx_spi_cpm_bufs_complete(mpc8xxx_spi);
+
 	return mpc8xxx_spi->count;
 }
 
@@ -369,7 +578,7 @@ static void mpc8xxx_spi_do_one_msg(struct spi_message *m)
 		}
 		cs_change = t->cs_change;
 		if (t->len)
-			status = mpc8xxx_spi_bufs(spi, t);
+			status = mpc8xxx_spi_bufs(spi, t, m->is_dma_mapped);
 		if (status) {
 			status = -EMSGSIZE;
 			break;
@@ -458,45 +667,80 @@ static int mpc8xxx_spi_setup(struct spi_device *spi)
 	return 0;
 }
 
-static irqreturn_t mpc8xxx_spi_irq(s32 irq, void *context_data)
+static void mpc8xxx_spi_cpm_irq(struct mpc8xxx_spi *mspi, u32 events)
 {
-	struct mpc8xxx_spi *mpc8xxx_spi = context_data;
-	u32 event;
-	irqreturn_t ret = IRQ_NONE;
+	u16 len;
 
-	/* Get interrupt events(tx/rx) */
-	event = mpc8xxx_spi_read_reg(&mpc8xxx_spi->base->event);
+	dev_dbg(mspi->dev, "%s: bd datlen %d, count %d\n", __func__,
+		in_be16(&mspi->rx_bd->cbd_datlen), mspi->count);
 
-	/* We need handle RX first */
-	if (event & SPIE_NE) {
-		u32 rx_data = mpc8xxx_spi_read_reg(&mpc8xxx_spi->base->receive);
-
-		if (mpc8xxx_spi->rx)
-			mpc8xxx_spi->get_rx(rx_data, mpc8xxx_spi);
-
-		ret = IRQ_HANDLED;
-	}
-
-	if ((event & SPIE_NF) == 0)
-		/* spin until TX is done */
-		while (((event =
-			 mpc8xxx_spi_read_reg(&mpc8xxx_spi->base->event)) &
-						SPIE_NF) == 0)
-			cpu_relax();
-
-	mpc8xxx_spi->count -= 1;
-	if (mpc8xxx_spi->count) {
-		u32 word = mpc8xxx_spi->get_tx(mpc8xxx_spi);
-		mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->transmit, word);
-	} else {
-		complete(&mpc8xxx_spi->done);
+	len = in_be16(&mspi->rx_bd->cbd_datlen);
+	if (len > mspi->count) {
+		WARN_ON(1);
+		len = mspi->count;
 	}
 
 	/* Clear the events */
-	mpc8xxx_spi_write_reg(&mpc8xxx_spi->base->event, event);
+	mpc8xxx_spi_write_reg(&mspi->base->event, events);
+
+	mspi->count -= len;
+	if (mspi->count)
+		mpc8xxx_spi_cpm_bufs_start(mspi);
+	else
+		complete(&mspi->done);
+}
+
+static void mpc8xxx_spi_cpu_irq(struct mpc8xxx_spi *mspi, u32 events)
+{
+	/* We need handle RX first */
+	if (events & SPIE_NE) {
+		u32 rx_data = mpc8xxx_spi_read_reg(&mspi->base->receive);
+
+		if (mspi->rx)
+			mspi->get_rx(rx_data, mspi);
+	}
+
+	if ((events & SPIE_NF) == 0)
+		/* spin until TX is done */
+		while (((events =
+			mpc8xxx_spi_read_reg(&mspi->base->event)) &
+						SPIE_NF) == 0)
+			cpu_relax();
+
+	/* Clear the events */
+	mpc8xxx_spi_write_reg(&mspi->base->event, events);
+
+	mspi->count -= 1;
+	if (mspi->count) {
+		u32 word = mspi->get_tx(mspi);
+
+		mpc8xxx_spi_write_reg(&mspi->base->transmit, word);
+	} else {
+		complete(&mspi->done);
+	}
+}
+
+static irqreturn_t mpc8xxx_spi_irq(s32 irq, void *context_data)
+{
+	struct mpc8xxx_spi *mspi = context_data;
+	irqreturn_t ret = IRQ_NONE;
+	u32 events;
+
+	/* Get interrupt events(tx/rx) */
+	events = mpc8xxx_spi_read_reg(&mspi->base->event);
+	if (events)
+		ret = IRQ_HANDLED;
+
+	dev_dbg(mspi->dev, "%s: events %x\n", __func__, events);
+
+	if (mspi->flags & SPI_CPM_MODE)
+		mpc8xxx_spi_cpm_irq(mspi, events);
+	else
+		mpc8xxx_spi_cpu_irq(mspi, events);
 
 	return ret;
 }
+
 static int mpc8xxx_spi_transfer(struct spi_device *spi,
 				struct spi_message *m)
 {
@@ -520,10 +764,212 @@ static void mpc8xxx_spi_cleanup(struct spi_device *spi)
 	kfree(spi->controller_state);
 }
 
+static void *mpc8xxx_spi_alloc_dummy_rx(void)
+{
+	mutex_lock(&mpc8xxx_dummy_rx_lock);
+
+	if (!mpc8xxx_dummy_rx)
+		mpc8xxx_dummy_rx = kmalloc(SPI_MRBLR, GFP_KERNEL);
+	if (mpc8xxx_dummy_rx)
+		mpc8xxx_dummy_rx_refcnt++;
+
+	mutex_unlock(&mpc8xxx_dummy_rx_lock);
+
+	return mpc8xxx_dummy_rx;
+}
+
+static void mpc8xxx_spi_free_dummy_rx(void)
+{
+	mutex_lock(&mpc8xxx_dummy_rx_lock);
+
+	switch (mpc8xxx_dummy_rx_refcnt) {
+	case 0:
+		WARN_ON(1);
+		break;
+	case 1:
+		kfree(mpc8xxx_dummy_rx);
+		mpc8xxx_dummy_rx = NULL;
+		/* fall through */
+	default:
+		mpc8xxx_dummy_rx_refcnt--;
+		break;
+	}
+
+	mutex_unlock(&mpc8xxx_dummy_rx_lock);
+}
+
+static unsigned long mpc8xxx_spi_cpm_get_pram(struct mpc8xxx_spi *mspi)
+{
+	struct device *dev = mspi->dev;
+	struct device_node *np = dev_archdata_get_node(&dev->archdata);
+	const u32 *iprop;
+	int size;
+	unsigned long spi_base_ofs;
+	unsigned long pram_ofs = -ENOMEM;
+
+	/* Can't use of_address_to_resource(), QE muram isn't at 0. */
+	iprop = of_get_property(np, "reg", &size);
+
+	/* QE with a fixed pram location? */
+	if (mspi->flags & SPI_QE && iprop && size == sizeof(*iprop) * 4)
+		return cpm_muram_alloc_fixed(iprop[2], SPI_PRAM_SIZE);
+
+	/* QE but with a dynamic pram location? */
+	if (mspi->flags & SPI_QE) {
+		pram_ofs = cpm_muram_alloc(SPI_PRAM_SIZE, 64);
+		qe_issue_cmd(QE_ASSIGN_PAGE_TO_DEVICE, mspi->subblock,
+				QE_CR_PROTOCOL_UNSPECIFIED, pram_ofs);
+		return pram_ofs;
+	}
+
+	/* CPM1 and CPM2 pram must be at a fixed addr. */
+	if (!iprop || size != sizeof(*iprop) * 4)
+		return -ENOMEM;
+
+	spi_base_ofs = cpm_muram_alloc_fixed(iprop[2], 2);
+	if (IS_ERR_VALUE(spi_base_ofs))
+		return -ENOMEM;
+
+	if (mspi->flags & SPI_CPM2) {
+		pram_ofs = cpm_muram_alloc(SPI_PRAM_SIZE, 64);
+		if (!IS_ERR_VALUE(pram_ofs)) {
+			u16 __iomem *spi_base = cpm_muram_addr(spi_base_ofs);
+
+			out_be16(spi_base, pram_ofs);
+		}
+	} else {
+		struct spi_pram __iomem *pram = cpm_muram_addr(spi_base_ofs);
+		u16 rpbase = in_be16(&pram->rpbase);
+
+		/* Microcode relocation patch applied? */
+		if (rpbase)
+			pram_ofs = rpbase;
+		else
+			return spi_base_ofs;
+	}
+
+	cpm_muram_free(spi_base_ofs);
+	return pram_ofs;
+}
+
+static int mpc8xxx_spi_cpm_init(struct mpc8xxx_spi *mspi)
+{
+	struct device *dev = mspi->dev;
+	struct device_node *np = dev_archdata_get_node(&dev->archdata);
+	const u32 *iprop;
+	int size;
+	unsigned long pram_ofs;
+	unsigned long bds_ofs;
+
+	if (!(mspi->flags & SPI_CPM_MODE))
+		return 0;
+
+	if (!mpc8xxx_spi_alloc_dummy_rx())
+		return -ENOMEM;
+
+	if (mspi->flags & SPI_QE) {
+		iprop = of_get_property(np, "cell-index", &size);
+		if (iprop && size == sizeof(*iprop))
+			mspi->subblock = *iprop;
+
+		switch (mspi->subblock) {
+		default:
+			dev_warn(dev, "cell-index unspecified, assuming SPI1");
+			/* fall through */
+		case 0:
+			mspi->subblock = QE_CR_SUBBLOCK_SPI1;
+			break;
+		case 1:
+			mspi->subblock = QE_CR_SUBBLOCK_SPI2;
+			break;
+		}
+	}
+
+	pram_ofs = mpc8xxx_spi_cpm_get_pram(mspi);
+	if (IS_ERR_VALUE(pram_ofs)) {
+		dev_err(dev, "can't allocate spi parameter ram\n");
+		goto err_pram;
+	}
+
+	bds_ofs = cpm_muram_alloc(sizeof(*mspi->tx_bd) +
+				  sizeof(*mspi->rx_bd), 8);
+	if (IS_ERR_VALUE(bds_ofs)) {
+		dev_err(dev, "can't allocate bds\n");
+		goto err_bds;
+	}
+
+	mspi->dma_dummy_tx = dma_map_single(dev, empty_zero_page, PAGE_SIZE,
+					    DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, mspi->dma_dummy_tx)) {
+		dev_err(dev, "unable to map dummy tx buffer\n");
+		goto err_dummy_tx;
+	}
+
+	mspi->dma_dummy_rx = dma_map_single(dev, mpc8xxx_dummy_rx, SPI_MRBLR,
+					    DMA_FROM_DEVICE);
+	if (dma_mapping_error(dev, mspi->dma_dummy_rx)) {
+		dev_err(dev, "unable to map dummy rx buffer\n");
+		goto err_dummy_rx;
+	}
+
+	mspi->pram = cpm_muram_addr(pram_ofs);
+
+	mspi->tx_bd = cpm_muram_addr(bds_ofs);
+	mspi->rx_bd = cpm_muram_addr(bds_ofs + sizeof(*mspi->tx_bd));
+
+	/* Initialize parameter ram. */
+	out_be16(&mspi->pram->tbase, cpm_muram_offset(mspi->tx_bd));
+	out_be16(&mspi->pram->rbase, cpm_muram_offset(mspi->rx_bd));
+	out_8(&mspi->pram->tfcr, CPMFCR_EB | CPMFCR_GBL);
+	out_8(&mspi->pram->rfcr, CPMFCR_EB | CPMFCR_GBL);
+	out_be16(&mspi->pram->mrblr, SPI_MRBLR);
+	out_be32(&mspi->pram->rstate, 0);
+	out_be32(&mspi->pram->rdp, 0);
+	out_be16(&mspi->pram->rbptr, 0);
+	out_be16(&mspi->pram->rbc, 0);
+	out_be32(&mspi->pram->rxtmp, 0);
+	out_be32(&mspi->pram->tstate, 0);
+	out_be32(&mspi->pram->tdp, 0);
+	out_be16(&mspi->pram->tbptr, 0);
+	out_be16(&mspi->pram->tbc, 0);
+	out_be32(&mspi->pram->txtmp, 0);
+
+	return 0;
+
+err_dummy_rx:
+	dma_unmap_single(dev, mspi->dma_dummy_tx, PAGE_SIZE, DMA_TO_DEVICE);
+err_dummy_tx:
+	cpm_muram_free(bds_ofs);
+err_bds:
+	cpm_muram_free(pram_ofs);
+err_pram:
+	mpc8xxx_spi_free_dummy_rx();
+	return -ENOMEM;
+}
+
+static void mpc8xxx_spi_cpm_free(struct mpc8xxx_spi *mspi)
+{
+	struct device *dev = mspi->dev;
+
+	dma_unmap_single(dev, mspi->dma_dummy_rx, SPI_MRBLR, DMA_FROM_DEVICE);
+	dma_unmap_single(dev, mspi->dma_dummy_tx, PAGE_SIZE, DMA_TO_DEVICE);
+	cpm_muram_free(cpm_muram_offset(mspi->tx_bd));
+	cpm_muram_free(cpm_muram_offset(mspi->pram));
+	mpc8xxx_spi_free_dummy_rx();
+}
+
 static const char *mpc8xxx_spi_strmode(unsigned int flags)
 {
-	if (flags & SPI_QE_CPU_MODE)
+	if (flags & SPI_QE_CPU_MODE) {
 		return "QE CPU";
+	} else if (flags & SPI_CPM_MODE) {
+		if (flags & SPI_QE)
+			return "QE";
+		else if (flags & SPI_CPM2)
+			return "CPM2";
+		else
+			return "CPM1";
+	}
 	return "CPU";
 }
 
@@ -553,11 +999,16 @@ mpc8xxx_spi_probe(struct device *dev, struct resource *mem, unsigned int irq)
 	master->cleanup = mpc8xxx_spi_cleanup;
 
 	mpc8xxx_spi = spi_master_get_devdata(master);
+	mpc8xxx_spi->dev = dev;
 	mpc8xxx_spi->get_rx = mpc8xxx_spi_rx_buf_u8;
 	mpc8xxx_spi->get_tx = mpc8xxx_spi_tx_buf_u8;
 	mpc8xxx_spi->flags = pdata->flags;
 	mpc8xxx_spi->spibrg = pdata->sysclk;
 
+	ret = mpc8xxx_spi_cpm_init(mpc8xxx_spi);
+	if (ret)
+		goto err_cpm_init;
+
 	mpc8xxx_spi->rx_shift = 0;
 	mpc8xxx_spi->tx_shift = 0;
 	if (mpc8xxx_spi->flags & SPI_QE_CPU_MODE) {
@@ -570,7 +1021,7 @@ mpc8xxx_spi_probe(struct device *dev, struct resource *mem, unsigned int irq)
 	mpc8xxx_spi->base = ioremap(mem->start, mem->end - mem->start + 1);
 	if (mpc8xxx_spi->base == NULL) {
 		ret = -ENOMEM;
-		goto put_master;
+		goto err_ioremap;
 	}
 
 	mpc8xxx_spi->irq = irq;
@@ -624,7 +1075,9 @@ free_irq:
 	free_irq(mpc8xxx_spi->irq, mpc8xxx_spi);
 unmap_io:
 	iounmap(mpc8xxx_spi->base);
-put_master:
+err_ioremap:
+	mpc8xxx_spi_cpm_free(mpc8xxx_spi);
+err_cpm_init:
 	spi_master_put(master);
 err:
 	return ERR_PTR(ret);
@@ -644,6 +1097,7 @@ static int __devexit mpc8xxx_spi_remove(struct device *dev)
 
 	free_irq(mpc8xxx_spi->irq, mpc8xxx_spi);
 	iounmap(mpc8xxx_spi->base);
+	mpc8xxx_spi_cpm_free(mpc8xxx_spi);
 
 	return 0;
 }
@@ -806,6 +1260,12 @@ static int __devinit of_mpc8xxx_spi_probe(struct of_device *ofdev,
 	prop = of_get_property(np, "mode", NULL);
 	if (prop && !strcmp(prop, "cpu-qe"))
 		pdata->flags = SPI_QE_CPU_MODE;
+	else if (prop && !strcmp(prop, "qe"))
+		pdata->flags = SPI_CPM_MODE | SPI_QE;
+	else if (of_device_is_compatible(np, "fsl,cpm2-spi"))
+		pdata->flags = SPI_CPM_MODE | SPI_CPM2;
+	else if (of_device_is_compatible(np, "fsl,cpm1-spi"))
+		pdata->flags = SPI_CPM_MODE | SPI_CPM1;
 
 	ret = of_mpc8xxx_spi_get_chipselects(dev);
 	if (ret)

From fdfde24e108b49373f8702d5b9981217f35315d8 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Wed, 16 Sep 2009 01:43:55 +0400
Subject: [PATCH 081/151] powerpc/qe: Implement QE driver for handling resume
 on MPC85xx

So far the driver is used to reset QE upon resume, which is needed on
85xx. Later we can move some QE initialization steps into probe().

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/sysdev/qe_lib/qe.c | 34 +++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index 4eaf2a962914..149393c02c3f 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -27,6 +27,8 @@
 #include <linux/delay.h>
 #include <linux/ioport.h>
 #include <linux/crc32.h>
+#include <linux/mod_devicetable.h>
+#include <linux/of_platform.h>
 #include <asm/irq.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -647,3 +649,35 @@ unsigned int qe_get_num_of_snums(void)
 	return num_of_snums;
 }
 EXPORT_SYMBOL(qe_get_num_of_snums);
+
+#if defined(CONFIG_SUSPEND) && defined(CONFIG_PPC_85xx)
+static int qe_resume(struct of_device *ofdev)
+{
+	if (!qe_alive_during_sleep())
+		qe_reset();
+	return 0;
+}
+
+static int qe_probe(struct of_device *ofdev, const struct of_device_id *id)
+{
+	return 0;
+}
+
+static const struct of_device_id qe_ids[] = {
+	{ .compatible = "fsl,qe", },
+	{ },
+};
+
+static struct of_platform_driver qe_driver = {
+	.driver.name = "fsl-qe",
+	.match_table = qe_ids,
+	.probe = qe_probe,
+	.resume = qe_resume,
+};
+
+static int __init qe_drv_init(void)
+{
+	return of_register_platform_driver(&qe_driver);
+}
+device_initcall(qe_drv_init);
+#endif /* defined(CONFIG_SUSPEND) && defined(CONFIG_PPC_85xx) */

From 4ffd6952a078015fd0bb5905a6ba7cd592f1b817 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Wed, 16 Sep 2009 01:43:57 +0400
Subject: [PATCH 082/151] powerpc/85xx/86xx: Add suspend/resume support

This patch adds suspend/resume support for MPC8540 and MPC8641D-
compatible CPUs. To reach sleep state, we just write the SLP bit
into the PM control and status register.

So far we don't support Deep Sleep mode as found in newer MPC85xx
CPUs (i.e. MPC8536). It can be relatively easy implemented though,
and for it we reserve 'mem' suspend type.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Acked-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/Kconfig          | 11 ++++-
 arch/powerpc/sysdev/Makefile  |  1 +
 arch/powerpc/sysdev/fsl_pmc.c | 88 +++++++++++++++++++++++++++++++++++
 3 files changed, 99 insertions(+), 1 deletion(-)
 create mode 100644 arch/powerpc/sysdev/fsl_pmc.c

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 61abde11a45e..5dbd375a3f2a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -215,7 +215,8 @@ config ARCH_HIBERNATION_POSSIBLE
 
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
-	depends on ADB_PMU || PPC_EFIKA || PPC_LITE5200 || PPC_83xx
+	depends on ADB_PMU || PPC_EFIKA || PPC_LITE5200 || PPC_83xx || \
+		   PPC_85xx || PPC_86xx
 
 config PPC_DCR_NATIVE
 	bool
@@ -664,6 +665,14 @@ config FSL_PCI
 	select PPC_INDIRECT_PCI
 	select PCI_QUIRKS
 
+config FSL_PMC
+	bool
+	default y
+	depends on SUSPEND && (PPC_85xx || PPC_86xx)
+	help
+	  Freescale MPC85xx/MPC86xx power management controller support
+	  (suspend/resume). For MPC83xx see platforms/83xx/suspend.c
+
 config 4xx_SOC
 	bool
 
diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile
index 9d4b17462f13..5642924fb9fb 100644
--- a/arch/powerpc/sysdev/Makefile
+++ b/arch/powerpc/sysdev/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_U3_DART)		+= dart_iommu.o
 obj-$(CONFIG_MMIO_NVRAM)	+= mmio_nvram.o
 obj-$(CONFIG_FSL_SOC)		+= fsl_soc.o
 obj-$(CONFIG_FSL_PCI)		+= fsl_pci.o $(fsl-msi-obj-y)
+obj-$(CONFIG_FSL_PMC)		+= fsl_pmc.o
 obj-$(CONFIG_FSL_LBC)		+= fsl_lbc.o
 obj-$(CONFIG_FSL_GTM)		+= fsl_gtm.o
 obj-$(CONFIG_MPC8xxx_GPIO)	+= mpc8xxx_gpio.o
diff --git a/arch/powerpc/sysdev/fsl_pmc.c b/arch/powerpc/sysdev/fsl_pmc.c
new file mode 100644
index 000000000000..a7635a993dca
--- /dev/null
+++ b/arch/powerpc/sysdev/fsl_pmc.c
@@ -0,0 +1,88 @@
+/*
+ * Suspend/resume support
+ *
+ * Copyright 2009  MontaVista Software, Inc.
+ *
+ * Author: Anton Vorontsov <avorontsov@ru.mvista.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.
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/suspend.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/of_platform.h>
+
+struct pmc_regs {
+	__be32 devdisr;
+	__be32 devdisr2;
+	__be32 :32;
+	__be32 :32;
+	__be32 pmcsr;
+#define PMCSR_SLP	(1 << 17)
+};
+
+static struct device *pmc_dev;
+static struct pmc_regs __iomem *pmc_regs;
+
+static int pmc_suspend_enter(suspend_state_t state)
+{
+	int ret;
+
+	setbits32(&pmc_regs->pmcsr, PMCSR_SLP);
+	/* At this point, the CPU is asleep. */
+
+	/* Upon resume, wait for SLP bit to be clear. */
+	ret = spin_event_timeout((in_be32(&pmc_regs->pmcsr) & PMCSR_SLP) == 0,
+				 10000, 10) ? 0 : -ETIMEDOUT;
+	if (ret)
+		dev_err(pmc_dev, "tired waiting for SLP bit to clear\n");
+	return ret;
+}
+
+static int pmc_suspend_valid(suspend_state_t state)
+{
+	if (state != PM_SUSPEND_STANDBY)
+		return 0;
+	return 1;
+}
+
+static struct platform_suspend_ops pmc_suspend_ops = {
+	.valid = pmc_suspend_valid,
+	.enter = pmc_suspend_enter,
+};
+
+static int pmc_probe(struct of_device *ofdev, const struct of_device_id *id)
+{
+	pmc_regs = of_iomap(ofdev->node, 0);
+	if (!pmc_regs)
+		return -ENOMEM;
+
+	pmc_dev = &ofdev->dev;
+	suspend_set_ops(&pmc_suspend_ops);
+	return 0;
+}
+
+static const struct of_device_id pmc_ids[] = {
+	{ .compatible = "fsl,mpc8548-pmc", },
+	{ .compatible = "fsl,mpc8641d-pmc", },
+	{ },
+};
+
+static struct of_platform_driver pmc_driver = {
+	.driver.name = "fsl-pmc",
+	.match_table = pmc_ids,
+	.probe = pmc_probe,
+};
+
+static int __init pmc_init(void)
+{
+	return of_register_platform_driver(&pmc_driver);
+}
+device_initcall(pmc_init);

From 3cfee0aaa1c7767e1b85272a0621e3a78ece7879 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Wed, 16 Sep 2009 01:43:59 +0400
Subject: [PATCH 083/151] powerpc/85xx: Add power management support for
 MPC85xxMDS boards

- Add power management controller nodes;
- Add interrupts for RTC nodes, the RTC interrupt may be used as a
  wakeup source;
- Add sleep properties (DEVDISR bit mask) and sleep-nexus nodes.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Acked-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/boot/dts/mpc8568mds.dts      | 119 ++++++++++++++--------
 arch/powerpc/boot/dts/mpc8569mds.dts      | 111 +++++++++++++-------
 arch/powerpc/platforms/85xx/mpc85xx_mds.c |   1 +
 3 files changed, 153 insertions(+), 78 deletions(-)

diff --git a/arch/powerpc/boot/dts/mpc8568mds.dts b/arch/powerpc/boot/dts/mpc8568mds.dts
index 00c2bbda7013..6d892ba74e55 100644
--- a/arch/powerpc/boot/dts/mpc8568mds.dts
+++ b/arch/powerpc/boot/dts/mpc8568mds.dts
@@ -40,6 +40,8 @@
 			i-cache-line-size = <32>;	// 32 bytes
 			d-cache-size = <0x8000>;		// L1, 32K
 			i-cache-size = <0x8000>;		// L1, 32K
+			sleep = <&pmc 0x00008000	// core
+				 &pmc 0x00004000>;	// timebase
 			timebase-frequency = <0>;
 			bus-frequency = <0>;
 			clock-frequency = <0>;
@@ -94,31 +96,41 @@
 			interrupts = <16 2>;
 		};
 
-		i2c@3000 {
+		i2c-sleep-nexus {
 			#address-cells = <1>;
-			#size-cells = <0>;
-			cell-index = <0>;
-			compatible = "fsl-i2c";
-			reg = <0x3000 0x100>;
-			interrupts = <43 2>;
-			interrupt-parent = <&mpic>;
-			dfsrr;
+			#size-cells = <1>;
+			compatible = "simple-bus";
+			sleep = <&pmc 0x00000004>;
+			ranges;
 
-			rtc@68 {
-				compatible = "dallas,ds1374";
-				reg = <0x68>;
+			i2c@3000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				cell-index = <0>;
+				compatible = "fsl-i2c";
+				reg = <0x3000 0x100>;
+				interrupts = <43 2>;
+				interrupt-parent = <&mpic>;
+				dfsrr;
+
+				rtc@68 {
+					compatible = "dallas,ds1374";
+					reg = <0x68>;
+					interrupts = <3 1>;
+					interrupt-parent = <&mpic>;
+				};
 			};
-		};
 
-		i2c@3100 {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			cell-index = <1>;
-			compatible = "fsl-i2c";
-			reg = <0x3100 0x100>;
-			interrupts = <43 2>;
-			interrupt-parent = <&mpic>;
-			dfsrr;
+			i2c@3100 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				cell-index = <1>;
+				compatible = "fsl-i2c";
+				reg = <0x3100 0x100>;
+				interrupts = <43 2>;
+				interrupt-parent = <&mpic>;
+				dfsrr;
+			};
 		};
 
 		dma@21300 {
@@ -128,6 +140,8 @@
 			reg = <0x21300 0x4>;
 			ranges = <0x0 0x21100 0x200>;
 			cell-index = <0>;
+			sleep = <&pmc 0x00000400>;
+
 			dma-channel@0 {
 				compatible = "fsl,mpc8568-dma-channel",
 						"fsl,eloplus-dma-channel";
@@ -176,6 +190,7 @@
 			interrupt-parent = <&mpic>;
 			tbi-handle = <&tbi0>;
 			phy-handle = <&phy2>;
+			sleep = <&pmc 0x00000080>;
 
 			mdio@520 {
 				#address-cells = <1>;
@@ -228,6 +243,7 @@
 			interrupt-parent = <&mpic>;
 			tbi-handle = <&tbi1>;
 			phy-handle = <&phy3>;
+			sleep = <&pmc 0x00000040>;
 
 			mdio@520 {
 				#address-cells = <1>;
@@ -242,30 +258,47 @@
 			};
 		};
 
-		serial0: serial@4500 {
-			cell-index = <0>;
-			device_type = "serial";
-			compatible = "ns16550";
-			reg = <0x4500 0x100>;
-			clock-frequency = <0>;
-			interrupts = <42 2>;
-			interrupt-parent = <&mpic>;
+		duart-sleep-nexus {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "simple-bus";
+			sleep = <&pmc 0x00000002>;
+			ranges;
+
+			serial0: serial@4500 {
+				cell-index = <0>;
+				device_type = "serial";
+				compatible = "ns16550";
+				reg = <0x4500 0x100>;
+				clock-frequency = <0>;
+				interrupts = <42 2>;
+				interrupt-parent = <&mpic>;
+			};
+
+			serial1: serial@4600 {
+				cell-index = <1>;
+				device_type = "serial";
+				compatible = "ns16550";
+				reg = <0x4600 0x100>;
+				clock-frequency = <0>;
+				interrupts = <42 2>;
+				interrupt-parent = <&mpic>;
+			};
 		};
 
-		global-utilities@e0000 {	//global utilities block
-			compatible = "fsl,mpc8548-guts";
+		global-utilities@e0000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,mpc8568-guts", "fsl,mpc8548-guts";
 			reg = <0xe0000 0x1000>;
+			ranges = <0 0xe0000 0x1000>;
 			fsl,has-rstcr;
-		};
 
-		serial1: serial@4600 {
-			cell-index = <1>;
-			device_type = "serial";
-			compatible = "ns16550";
-			reg = <0x4600 0x100>;
-			clock-frequency = <0>;
-			interrupts = <42 2>;
-			interrupt-parent = <&mpic>;
+			pmc: power@70 {
+				compatible = "fsl,mpc8568-pmc",
+					     "fsl,mpc8548-pmc";
+				reg = <0x70 0x20>;
+			};
 		};
 
 		crypto@30000 {
@@ -277,6 +310,7 @@
 			fsl,channel-fifo-len = <24>;
 			fsl,exec-units-mask = <0xfe>;
 			fsl,descriptor-types-mask = <0x12b0ebf>;
+			sleep = <&pmc 0x01000000>;
 		};
 
 		mpic: pic@40000 {
@@ -376,6 +410,7 @@
 		compatible = "fsl,qe";
 		ranges = <0x0 0xe0080000 0x40000>;
 		reg = <0xe0080000 0x480>;
+		sleep = <&pmc 0x00000800>;
 		brg-frequency = <0>;
 		bus-frequency = <396000000>;
 		fsl,qe-num-riscs = <2>;
@@ -509,6 +544,7 @@
 		bus-range = <0 255>;
 		ranges = <0x2000000 0x0 0x80000000 0x80000000 0x0 0x20000000
 			  0x1000000 0x0 0x0 0xe2000000 0x0 0x800000>;
+		sleep = <&pmc 0x80000000>;
 		clock-frequency = <66666666>;
 		#interrupt-cells = <1>;
 		#size-cells = <2>;
@@ -534,6 +570,7 @@
 		bus-range = <0 255>;
 		ranges = <0x2000000 0x0 0xa0000000 0xa0000000 0x0 0x10000000
 			  0x1000000 0x0 0x0 0xe2800000 0x0 0x800000>;
+		sleep = <&pmc 0x20000000>;
 		clock-frequency = <33333333>;
 		#interrupt-cells = <1>;
 		#size-cells = <2>;
@@ -570,5 +607,7 @@
 			      55 2 /* msg2_tx   */
 			      56 2 /* msg2_rx   */>;
 		interrupt-parent = <&mpic>;
+		sleep = <&pmc 0x00080000   /* controller */
+			 &pmc 0x00040000>; /* message unit */
 	};
 };
diff --git a/arch/powerpc/boot/dts/mpc8569mds.dts b/arch/powerpc/boot/dts/mpc8569mds.dts
index 1e3ec8f059bf..795eb362fcf9 100644
--- a/arch/powerpc/boot/dts/mpc8569mds.dts
+++ b/arch/powerpc/boot/dts/mpc8569mds.dts
@@ -41,6 +41,8 @@
 			i-cache-line-size = <32>;	// 32 bytes
 			d-cache-size = <0x8000>;		// L1, 32K
 			i-cache-size = <0x8000>;		// L1, 32K
+			sleep = <&pmc 0x00008000	// core
+				 &pmc 0x00004000>;	// timebase
 			timebase-frequency = <0>;
 			bus-frequency = <0>;
 			clock-frequency = <0>;
@@ -59,6 +61,7 @@
 		reg = <0xe0005000 0x1000>;
 		interrupts = <19 2>;
 		interrupt-parent = <&mpic>;
+		sleep = <&pmc 0x08000000>;
 
 		ranges = <0x0 0x0 0xfe000000 0x02000000
 			  0x1 0x0 0xf8000000 0x00008000
@@ -158,51 +161,69 @@
 			interrupts = <18 2>;
 		};
 
-		i2c@3000 {
+		i2c-sleep-nexus {
 			#address-cells = <1>;
-			#size-cells = <0>;
-			cell-index = <0>;
-			compatible = "fsl-i2c";
-			reg = <0x3000 0x100>;
-			interrupts = <43 2>;
-			interrupt-parent = <&mpic>;
-			dfsrr;
+			#size-cells = <1>;
+			compatible = "simple-bus";
+			sleep = <&pmc 0x00000004>;
+			ranges;
 
-			rtc@68 {
-				compatible = "dallas,ds1374";
-				reg = <0x68>;
+			i2c@3000 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				cell-index = <0>;
+				compatible = "fsl-i2c";
+				reg = <0x3000 0x100>;
+				interrupts = <43 2>;
+				interrupt-parent = <&mpic>;
+				dfsrr;
+
+				rtc@68 {
+					compatible = "dallas,ds1374";
+					reg = <0x68>;
+					interrupts = <3 1>;
+					interrupt-parent = <&mpic>;
+				};
+			};
+
+			i2c@3100 {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				cell-index = <1>;
+				compatible = "fsl-i2c";
+				reg = <0x3100 0x100>;
+				interrupts = <43 2>;
+				interrupt-parent = <&mpic>;
+				dfsrr;
 			};
 		};
 
-		i2c@3100 {
+		duart-sleep-nexus {
 			#address-cells = <1>;
-			#size-cells = <0>;
-			cell-index = <1>;
-			compatible = "fsl-i2c";
-			reg = <0x3100 0x100>;
-			interrupts = <43 2>;
-			interrupt-parent = <&mpic>;
-			dfsrr;
-		};
+			#size-cells = <1>;
+			compatible = "simple-bus";
+			sleep = <&pmc 0x00000002>;
+			ranges;
 
-		serial0: serial@4500 {
-			cell-index = <0>;
-			device_type = "serial";
-			compatible = "ns16550";
-			reg = <0x4500 0x100>;
-			clock-frequency = <0>;
-			interrupts = <42 2>;
-			interrupt-parent = <&mpic>;
-		};
+			serial0: serial@4500 {
+				cell-index = <0>;
+				device_type = "serial";
+				compatible = "ns16550";
+				reg = <0x4500 0x100>;
+				clock-frequency = <0>;
+				interrupts = <42 2>;
+				interrupt-parent = <&mpic>;
+			};
 
-		serial1: serial@4600 {
-			cell-index = <1>;
-			device_type = "serial";
-			compatible = "ns16550";
-			reg = <0x4600 0x100>;
-			clock-frequency = <0>;
-			interrupts = <42 2>;
-			interrupt-parent = <&mpic>;
+			serial1: serial@4600 {
+				cell-index = <1>;
+				device_type = "serial";
+				compatible = "ns16550";
+				reg = <0x4600 0x100>;
+				clock-frequency = <0>;
+				interrupts = <42 2>;
+				interrupt-parent = <&mpic>;
+			};
 		};
 
 		L2: l2-cache-controller@20000 {
@@ -260,6 +281,7 @@
 			reg = <0x2e000 0x1000>;
 			interrupts = <72 0x8>;
 			interrupt-parent = <&mpic>;
+			sleep = <&pmc 0x00200000>;
 			/* Filled in by U-Boot */
 			clock-frequency = <0>;
 			status = "disabled";
@@ -276,6 +298,7 @@
 			fsl,channel-fifo-len = <24>;
 			fsl,exec-units-mask = <0xbfe>;
 			fsl,descriptor-types-mask = <0x3ab0ebf>;
+			sleep = <&pmc 0x01000000>;
 		};
 
 		mpic: pic@40000 {
@@ -304,9 +327,18 @@
 		};
 
 		global-utilities@e0000 {
-			compatible = "fsl,mpc8569-guts";
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,mpc8569-guts", "fsl,mpc8548-guts";
 			reg = <0xe0000 0x1000>;
+			ranges = <0 0xe0000 0x1000>;
 			fsl,has-rstcr;
+
+			pmc: power@70 {
+				compatible = "fsl,mpc8569-pmc",
+					     "fsl,mpc8548-pmc";
+				reg = <0x70 0x20>;
+			};
 		};
 
 		par_io@e0100 {
@@ -422,6 +454,7 @@
 		compatible = "fsl,qe";
 		ranges = <0x0 0xe0080000 0x40000>;
 		reg = <0xe0080000 0x480>;
+		sleep = <&pmc 0x00000800>;
 		brg-frequency = <0>;
 		bus-frequency = <0>;
 		fsl,qe-num-riscs = <4>;
@@ -684,6 +717,7 @@
 		bus-range = <0 255>;
 		ranges = <0x2000000 0x0 0xa0000000 0xa0000000 0x0 0x10000000
 			  0x1000000 0x0 0x00000000 0xe2800000 0x0 0x00800000>;
+		sleep = <&pmc 0x20000000>;
 		clock-frequency = <33333333>;
 		pcie@0 {
 			reg = <0x0 0x0 0x0 0x0 0x0>;
@@ -714,5 +748,6 @@
 			      55 2 /* msg2_tx   */
 			      56 2 /* msg2_rx   */>;
 		interrupt-parent = <&mpic>;
+		sleep = <&pmc 0x00080000>;
 	};
 };
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index 3909d57b86e3..c5028a2e5a58 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -301,6 +301,7 @@ static struct of_device_id mpc85xx_ids[] = {
 	{ .compatible = "fsl,qe", },
 	{ .compatible = "gianfar", },
 	{ .compatible = "fsl,rapidio-delta", },
+	{ .compatible = "fsl,mpc8548-guts", },
 	{},
 };
 

From 8c68e2f7885b22f0a63bf087752a46b690d6b6ea Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Wed, 16 Sep 2009 01:44:00 +0400
Subject: [PATCH 084/151] powerpc/86xx: Add power management support for
 MPC8610HPCD boards

This patch adds needed nodes and properties to support suspend/resume
on the MPC8610HPCD boards.

There is a dedicated switch (SW9) that is used to wake up the boards.
By default the SW9 button is routed to IRQ8, but could be re-routed
(via PIXIS) to sreset.

With 'no_console_suspend' kernel command line argument specified, the
board is also able to wakeup upon serial port input.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Acked-by: Scott Wood <scottwood@freescale.com> [dts]
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 .../powerpc/dts-bindings/fsl/board.txt        |  4 ++
 arch/powerpc/boot/dts/mpc8610_hpcd.dts        | 26 ++++++++++
 arch/powerpc/platforms/86xx/mpc8610_hpcd.c    | 48 +++++++++++++++++--
 3 files changed, 74 insertions(+), 4 deletions(-)

diff --git a/Documentation/powerpc/dts-bindings/fsl/board.txt b/Documentation/powerpc/dts-bindings/fsl/board.txt
index e8b5bc24d0ac..39e941515a36 100644
--- a/Documentation/powerpc/dts-bindings/fsl/board.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/board.txt
@@ -20,12 +20,16 @@ Required properities:
 - compatible : should be "fsl,fpga-pixis".
 - reg : should contain the address and the length of the FPPGA register
   set.
+- interrupt-parent: should specify phandle for the interrupt controller.
+- interrupts : should specify event (wakeup) IRQ.
 
 Example (MPC8610HPCD):
 
 	board-control@e8000000 {
 		compatible = "fsl,fpga-pixis";
 		reg = <0xe8000000 32>;
+		interrupt-parent = <&mpic>;
+		interrupts = <8 8>;
 	};
 
 * Freescale BCSR GPIO banks
diff --git a/arch/powerpc/boot/dts/mpc8610_hpcd.dts b/arch/powerpc/boot/dts/mpc8610_hpcd.dts
index f468d215f716..9535ce68caae 100644
--- a/arch/powerpc/boot/dts/mpc8610_hpcd.dts
+++ b/arch/powerpc/boot/dts/mpc8610_hpcd.dts
@@ -35,6 +35,8 @@
 			i-cache-line-size = <32>;
 			d-cache-size = <32768>;		// L1
 			i-cache-size = <32768>;		// L1
+			sleep = <&pmc 0x00008000 0	// core
+				 &pmc 0x00004000 0>;	// timebase
 			timebase-frequency = <0>;	// From uboot
 			bus-frequency = <0>;		// From uboot
 			clock-frequency = <0>;		// From uboot
@@ -60,6 +62,7 @@
 			  5 0 0xe8480000 0x00008000
 			  6 0 0xe84c0000 0x00008000
 			  3 0 0xe8000000 0x00000020>;
+		sleep = <&pmc 0x08000000 0>;
 
 		flash@0,0 {
 			compatible = "cfi-flash";
@@ -105,6 +108,8 @@
 			compatible = "fsl,fpga-pixis";
 			reg = <3 0 0x20>;
 			ranges = <0 3 0 0x20>;
+			interrupt-parent = <&mpic>;
+			interrupts = <8 8>;
 
 			sdcsr_pio: gpio-controller@a {
 				#gpio-cells = <2>;
@@ -163,6 +168,7 @@
 			reg = <0x3100 0x100>;
 			interrupts = <43 2>;
 			interrupt-parent = <&mpic>;
+			sleep = <&pmc 0x00000004 0>;
 			dfsrr;
 		};
 
@@ -174,6 +180,7 @@
 			clock-frequency = <0>;
 			interrupts = <42 2>;
 			interrupt-parent = <&mpic>;
+			sleep = <&pmc 0x00000002 0>;
 		};
 
 		serial1: serial@4600 {
@@ -184,6 +191,7 @@
 			clock-frequency = <0>;
 			interrupts = <42 2>;
 			interrupt-parent = <&mpic>;
+			sleep = <&pmc 0x00000008 0>;
 		};
 
 		spi@7000 {
@@ -196,6 +204,7 @@
 			interrupt-parent = <&mpic>;
 			mode = "cpu";
 			gpios = <&sdcsr_pio 7 0>;
+			sleep = <&pmc 0x00000800 0>;
 
 			mmc-slot@0 {
 				compatible = "fsl,mpc8610hpcd-mmc-slot",
@@ -213,6 +222,7 @@
 			reg = <0x2c000 100>;
 			interrupts = <72 2>;
 			interrupt-parent = <&mpic>;
+			sleep = <&pmc 0x04000000 0>;
 		};
 
 		mpic: interrupt-controller@40000 {
@@ -241,9 +251,18 @@
 		};
 
 		global-utilities@e0000 {
+			#address-cells = <1>;
+			#size-cells = <1>;
 			compatible = "fsl,mpc8610-guts";
 			reg = <0xe0000 0x1000>;
+			ranges = <0 0xe0000 0x1000>;
 			fsl,has-rstcr;
+
+			pmc: power@70 {
+				compatible = "fsl,mpc8610-pmc",
+					     "fsl,mpc8641d-pmc";
+				reg = <0x70 0x20>;
+			};
 		};
 
 		wdt@e4000 {
@@ -262,6 +281,7 @@
 			fsl,playback-dma = <&dma00>;
 			fsl,capture-dma = <&dma01>;
 			fsl,fifo-depth = <8>;
+			sleep = <&pmc 0 0x08000000>;
 		};
 
 		ssi@16100 {
@@ -271,6 +291,7 @@
 			interrupt-parent = <&mpic>;
 			interrupts = <63 2>;
 			fsl,fifo-depth = <8>;
+			sleep = <&pmc 0 0x04000000>;
 		};
 
 		dma@21300 {
@@ -280,6 +301,7 @@
 			cell-index = <0>;
 			reg = <0x21300 0x4>; /* DMA general status register */
 			ranges = <0x0 0x21100 0x200>;
+			sleep = <&pmc 0x00000400 0>;
 
 			dma00: dma-channel@0 {
 				compatible = "fsl,mpc8610-dma-channel",
@@ -322,6 +344,7 @@
 			cell-index = <1>;
 			reg = <0xc300 0x4>; /* DMA general status register */
 			ranges = <0x0 0xc100 0x200>;
+			sleep = <&pmc 0x00000200 0>;
 
 			dma-channel@0 {
 				compatible = "fsl,mpc8610-dma-channel",
@@ -369,6 +392,7 @@
 		bus-range = <0 0>;
 		ranges = <0x02000000 0x0 0x80000000 0x80000000 0x0 0x10000000
 			  0x01000000 0x0 0x00000000 0xe1000000 0x0 0x00100000>;
+		sleep = <&pmc 0x80000000 0>;
 		clock-frequency = <33333333>;
 		interrupt-parent = <&mpic>;
 		interrupts = <24 2>;
@@ -398,6 +422,7 @@
 		bus-range = <1 3>;
 		ranges = <0x02000000 0x0 0xa0000000 0xa0000000 0x0 0x10000000
 			  0x01000000 0x0 0x00000000 0xe3000000 0x0 0x00100000>;
+		sleep = <&pmc 0x40000000 0>;
 		clock-frequency = <33333333>;
 		interrupt-parent = <&mpic>;
 		interrupts = <26 2>;
@@ -474,6 +499,7 @@
 				 0x0000 0 0 4 &mpic 7 1>;
 		interrupt-parent = <&mpic>;
 		interrupts = <25 2>;
+		sleep = <&pmc 0x20000000 0>;
 		clock-frequency = <33333333>;
 	};
 };
diff --git a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
index 627908a4cd77..5abe137f6309 100644
--- a/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
+++ b/arch/powerpc/platforms/86xx/mpc8610_hpcd.c
@@ -19,6 +19,7 @@
 #include <linux/stddef.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
+#include <linux/interrupt.h>
 #include <linux/kdev_t.h>
 #include <linux/delay.h>
 #include <linux/seq_file.h>
@@ -41,10 +42,46 @@
 
 #include "mpc86xx.h"
 
+static struct device_node *pixis_node;
 static unsigned char *pixis_bdcfg0, *pixis_arch;
 
+#ifdef CONFIG_SUSPEND
+static irqreturn_t mpc8610_sw9_irq(int irq, void *data)
+{
+	pr_debug("%s: PIXIS' event (sw9/wakeup) IRQ handled\n", __func__);
+	return IRQ_HANDLED;
+}
+
+static void __init mpc8610_suspend_init(void)
+{
+	int irq;
+	int ret;
+
+	if (!pixis_node)
+		return;
+
+	irq = irq_of_parse_and_map(pixis_node, 0);
+	if (!irq) {
+		pr_err("%s: can't map pixis event IRQ.\n", __func__);
+		return;
+	}
+
+	ret = request_irq(irq, mpc8610_sw9_irq, 0, "sw9/wakeup", NULL);
+	if (ret) {
+		pr_err("%s: can't request pixis event IRQ: %d\n",
+		       __func__, ret);
+		irq_dispose_mapping(irq);
+	}
+
+	enable_irq_wake(irq);
+}
+#else
+static inline void mpc8610_suspend_init(void) { }
+#endif /* CONFIG_SUSPEND */
+
 static struct of_device_id __initdata mpc8610_ids[] = {
 	{ .compatible = "fsl,mpc8610-immr", },
+	{ .compatible = "fsl,mpc8610-guts", },
 	{ .compatible = "simple-bus", },
 	{ .compatible = "gianfar", },
 	{}
@@ -55,6 +92,9 @@ static int __init mpc8610_declare_of_platform_devices(void)
 	/* Firstly, register PIXIS GPIOs. */
 	simple_gpiochip_init("fsl,fpga-pixis-gpio-bank");
 
+	/* Enable wakeup on PIXIS' event IRQ. */
+	mpc8610_suspend_init();
+
 	/* Without this call, the SSI device driver won't get probed. */
 	of_platform_bus_probe(NULL, mpc8610_ids, NULL);
 
@@ -250,10 +290,10 @@ static void __init mpc86xx_hpcd_setup_arch(void)
 	diu_ops.set_sysfs_monitor_port	= mpc8610hpcd_set_sysfs_monitor_port;
 #endif
 
-	np = of_find_compatible_node(NULL, NULL, "fsl,fpga-pixis");
-	if (np) {
-		of_address_to_resource(np, 0, &r);
-		of_node_put(np);
+	pixis_node = of_find_compatible_node(NULL, NULL, "fsl,fpga-pixis");
+	if (pixis_node) {
+		of_address_to_resource(pixis_node, 0, &r);
+		of_node_put(pixis_node);
 		pixis = ioremap(r.start, 32);
 		if (!pixis) {
 			printk(KERN_ERR "Err: can't map FPGA cfg register!\n");

From 1f8a25d4a461865c7f38e93dcecbee63b3968d21 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Wed, 16 Sep 2009 01:44:02 +0400
Subject: [PATCH 085/151] powerpc/83xx: Add power management support for
 MPC83xx QE boards

Simply add power management controller nodes and sleep properties.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Acked-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/boot/dts/kmeter1.dts     | 7 +++++++
 arch/powerpc/boot/dts/mpc832x_mds.dts | 9 +++++++++
 arch/powerpc/boot/dts/mpc832x_rdb.dts | 9 +++++++++
 arch/powerpc/boot/dts/mpc836x_mds.dts | 9 +++++++++
 arch/powerpc/boot/dts/mpc836x_rdk.dts | 9 +++++++++
 5 files changed, 43 insertions(+)

diff --git a/arch/powerpc/boot/dts/kmeter1.dts b/arch/powerpc/boot/dts/kmeter1.dts
index 167044f7de1d..65b8b4f27efe 100644
--- a/arch/powerpc/boot/dts/kmeter1.dts
+++ b/arch/powerpc/boot/dts/kmeter1.dts
@@ -59,6 +59,13 @@
 		reg = <0xe0000000 0x00000200>;
 		bus-frequency = <0>;	/* Filled in by U-Boot */
 
+		pmc: power@b00 {
+			compatible = "fsl,mpc8360-pmc", "fsl,mpc8349-pmc";
+			reg = <0xb00 0x100 0xa00 0x100>;
+			interrupts = <80 0x8>;
+			interrupt-parent = <&ipic>;
+		};
+
 		i2c@3000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
diff --git a/arch/powerpc/boot/dts/mpc832x_mds.dts b/arch/powerpc/boot/dts/mpc832x_mds.dts
index 436c9c671dd9..05ad8c98e527 100644
--- a/arch/powerpc/boot/dts/mpc832x_mds.dts
+++ b/arch/powerpc/boot/dts/mpc832x_mds.dts
@@ -79,6 +79,13 @@
 			reg = <0x200 0x100>;
 		};
 
+		pmc: power@b00 {
+			compatible = "fsl,mpc8323-pmc", "fsl,mpc8349-pmc";
+			reg = <0xb00 0x100 0xa00 0x100>;
+			interrupts = <80 0x8>;
+			interrupt-parent = <&ipic>;
+		};
+
 		i2c@3000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -163,6 +170,7 @@
 			fsl,channel-fifo-len = <24>;
 			fsl,exec-units-mask = <0x4c>;
 			fsl,descriptor-types-mask = <0x0122003f>;
+			sleep = <&pmc 0x03000000>;
 		};
 
 		ipic: pic@700 {
@@ -428,5 +436,6 @@
 		       0xe0008300 0x8>;		/* config space access registers */
 		compatible = "fsl,mpc8349-pci";
 		device_type = "pci";
+		sleep = <&pmc 0x00010000>;
 	};
 };
diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts
index 9a0952f74b81..f4fadb23ad6f 100644
--- a/arch/powerpc/boot/dts/mpc832x_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc832x_rdb.dts
@@ -62,6 +62,13 @@
 			reg = <0x200 0x100>;
 		};
 
+		pmc: power@b00 {
+			compatible = "fsl,mpc8323-pmc", "fsl,mpc8349-pmc";
+			reg = <0xb00 0x100 0xa00 0x100>;
+			interrupts = <80 0x8>;
+			interrupt-parent = <&ipic>;
+		};
+
 		i2c@3000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -141,6 +148,7 @@
 			fsl,channel-fifo-len = <24>;
 			fsl,exec-units-mask = <0x4c>;
 			fsl,descriptor-types-mask = <0x0122003f>;
+			sleep = <&pmc 0x03000000>;
 		};
 
 		ipic:pic@700 {
@@ -360,5 +368,6 @@
 		       0xe0008300 0x8>;		/* config space access registers */
 		compatible = "fsl,mpc8349-pci";
 		device_type = "pci";
+		sleep = <&pmc 0x00010000>;
 	};
 };
diff --git a/arch/powerpc/boot/dts/mpc836x_mds.dts b/arch/powerpc/boot/dts/mpc836x_mds.dts
index 39ff4c829caf..45cfa1c50a2a 100644
--- a/arch/powerpc/boot/dts/mpc836x_mds.dts
+++ b/arch/powerpc/boot/dts/mpc836x_mds.dts
@@ -99,6 +99,13 @@
 			reg = <0x200 0x100>;
 		};
 
+		pmc: power@b00 {
+			compatible = "fsl,mpc8360-pmc", "fsl,mpc8349-pmc";
+			reg = <0xb00 0x100 0xa00 0x100>;
+			interrupts = <80 0x8>;
+			interrupt-parent = <&ipic>;
+		};
+
 		i2c@3000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -194,6 +201,7 @@
 			fsl,channel-fifo-len = <24>;
 			fsl,exec-units-mask = <0x7e>;
 			fsl,descriptor-types-mask = <0x01010ebf>;
+			sleep = <&pmc 0x03000000>;
 		};
 
 		ipic: pic@700 {
@@ -470,5 +478,6 @@
 		       0xe0008300 0x8>;		/* config space access registers */
 		compatible = "fsl,mpc8349-pci";
 		device_type = "pci";
+		sleep = <&pmc 0x00010000>;
 	};
 };
diff --git a/arch/powerpc/boot/dts/mpc836x_rdk.dts b/arch/powerpc/boot/dts/mpc836x_rdk.dts
index 6315d6fcc58a..bdf4459677b1 100644
--- a/arch/powerpc/boot/dts/mpc836x_rdk.dts
+++ b/arch/powerpc/boot/dts/mpc836x_rdk.dts
@@ -71,6 +71,13 @@
 			reg = <0x200 0x100>;
 		};
 
+		pmc: power@b00 {
+			compatible = "fsl,mpc8360-pmc", "fsl,mpc8349-pmc";
+			reg = <0xb00 0x100 0xa00 0x100>;
+			interrupts = <80 0x8>;
+			interrupt-parent = <&ipic>;
+		};
+
 		i2c@3000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
@@ -161,6 +168,7 @@
 			fsl,channel-fifo-len = <24>;
 			fsl,exec-units-mask = <0x7e>;
 			fsl,descriptor-types-mask = <0x01010ebf>;
+			sleep = <&pmc 0x03000000>;
 		};
 
 		ipic: interrupt-controller@700 {
@@ -455,6 +463,7 @@
 				 0xa800 0 0 2 &ipic 20 8
 				 0xa800 0 0 3 &ipic 21 8
 				 0xa800 0 0 4 &ipic 18 8>;
+		sleep = <&pmc 0x00010000>;
 		/* filled by u-boot */
 		bus-range = <0 0>;
 		clock-frequency = <0>;

From 2e9d546eda5888962a441da1e96bbf92cb5b1cbb Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Wed, 23 Sep 2009 22:52:38 +0400
Subject: [PATCH 086/151] powerpc/fsl: Make fsl_deep_sleep() usable w/ modules
 and non-83xx builds

Export is needed for modular builds, and a static inline stub is needed
for non-MPC83xx builds.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/platforms/83xx/suspend.c | 1 +
 include/linux/fsl_devices.h           | 4 ++++
 2 files changed, 5 insertions(+)

diff --git a/arch/powerpc/platforms/83xx/suspend.c b/arch/powerpc/platforms/83xx/suspend.c
index 08e65fc8b98c..d306f07b9aa1 100644
--- a/arch/powerpc/platforms/83xx/suspend.c
+++ b/arch/powerpc/platforms/83xx/suspend.c
@@ -96,6 +96,7 @@ int fsl_deep_sleep(void)
 {
 	return deep_sleeping;
 }
+EXPORT_SYMBOL(fsl_deep_sleep);
 
 static int mpc83xx_change_state(void)
 {
diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h
index 39fd94681e74..47188d512b8f 100644
--- a/include/linux/fsl_devices.h
+++ b/include/linux/fsl_devices.h
@@ -90,6 +90,10 @@ struct mpc8xx_pcmcia_ops {
  * lead to a deep sleep (i.e. power removed from the core,
  * instead of just the clock).
  */
+#if defined(CONFIG_PPC_83xx) && defined(CONFIG_SUSPEND)
 int fsl_deep_sleep(void);
+#else
+static inline int fsl_deep_sleep(void) { return 0; }
+#endif
 
 #endif /* _FSL_DEVICE_H_ */

From 690b846aa1b42b4f35bfac0022b75a288d97fd13 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Albrecht=20Dre=C3=9F?= <albrecht.dress@arcor.de>
Date: Thu, 12 Nov 2009 13:31:35 -0700
Subject: [PATCH 087/151] mpc5200/gpt: tiny fix for gpt period limitation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch changes the period parameter of mpc52xx_gpt_start_timer to
a u64 to support larger timeout periods.

Signed-off-by: Albrecht Dreß <albrecht.dress@arcor.de>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 arch/powerpc/include/asm/mpc52xx.h        | 2 +-
 arch/powerpc/platforms/52xx/mpc52xx_gpt.c | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h
index 707ab7590cfb..933fb8f6e797 100644
--- a/arch/powerpc/include/asm/mpc52xx.h
+++ b/arch/powerpc/include/asm/mpc52xx.h
@@ -279,7 +279,7 @@ extern void mpc52xx_restart(char *cmd);
 /* mpc52xx_gpt.c */
 struct mpc52xx_gpt_priv;
 extern struct mpc52xx_gpt_priv *mpc52xx_gpt_from_irq(int irq);
-extern int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, int period,
+extern int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period,
                             int continuous);
 extern void mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt);
 
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 2c3fa13571ce..77572abca6c3 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -378,12 +378,12 @@ EXPORT_SYMBOL(mpc52xx_gpt_from_irq);
 /**
  * mpc52xx_gpt_start_timer - Set and enable the GPT timer
  * @gpt: Pointer to gpt private data structure
- * @period: period of timer
+ * @period: period of timer in ns; max. ~130s @ 33MHz IPB clock
  * @continuous: set to 1 to make timer continuous free running
  *
  * An interrupt will be generated every time the timer fires
  */
-int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, int period,
+int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period,
                             int continuous)
 {
 	u32 clear, set;
@@ -400,7 +400,7 @@ int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, int period,
 	 * arithmatic is done here to preserve the precision until the value
 	 * is scaled back down into the u32 range.  Period is in 'ns', bus
 	 * frequency is in Hz. */
-	clocks = (u64)period * (u64)gpt->ipb_freq;
+	clocks = period * (u64)gpt->ipb_freq;
 	do_div(clocks, 1000000000); /* Scale it down to ns range */
 
 	/* This device cannot handle a clock count greater than 32 bits */

From 13b600b59df287a175b1476d2d588ab935092b58 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Albrecht=20Dre=C3=9F?= <albrecht.dress@arcor.de>
Date: Fri, 13 Nov 2009 11:09:30 -0700
Subject: [PATCH 088/151] mpc52xx/wdt: OF property to enable the WDT on boot
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the "fsl,wdt-on-boot" OF property as to reserve a GPT as WDT which may
be a requirement in safety-related (e.g. ISO/EN 61508) applications.

Signed-off-by: Albrecht Dreß <albrecht.dress@arcor.de>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 .../powerpc/dts-bindings/fsl/mpc5200.txt        | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt b/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
index 8447fd7090d0..ddd5ee32ea63 100644
--- a/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/mpc5200.txt
@@ -103,7 +103,22 @@ fsl,mpc5200-gpt nodes
 ---------------------
 On the mpc5200 and 5200b, GPT0 has a watchdog timer function.  If the board
 design supports the internal wdt, then the device node for GPT0 should
-include the empty property 'fsl,has-wdt'.
+include the empty property 'fsl,has-wdt'.  Note that this does not activate
+the watchdog.  The timer will function as a GPT if the timer api is used, and
+it will function as watchdog if the watchdog device is used.  The watchdog
+mode has priority over the gpt mode, i.e. if the watchdog is activated, any
+gpt api call to this timer will fail with -EBUSY.
+
+If you add the property
+	fsl,wdt-on-boot = <n>;
+GPT0 will be marked as in-use watchdog, i.e. blocking every gpt access to it.
+If n>0, the watchdog is started with a timeout of n seconds.  If n=0, the
+configuration of the watchdog is not touched.  This is useful in two cases:
+- just mark GPT0 as watchdog, blocking gpt accesses, and configure it later;
+- do not touch a configuration assigned by the boot loader which supervises
+  the boot process itself.
+
+The watchdog will respect the CONFIG_WATCHDOG_NOWAYOUT option.
 
 An mpc5200-gpt can be used as a single line GPIO controller.  To do so,
 add the following properties to the gpt node:

From eda43d16ef3d0bd59e3b762de3ffc73bab02efe9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Albrecht=20Dre=C3=9F?= <albrecht.dress@arcor.de>
Date: Fri, 13 Nov 2009 11:09:31 -0700
Subject: [PATCH 089/151] mpc52xx/wdt: merge WDT code into the GPT driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Merge the WDT code into the GPT interface.

Signed-off-by: Albrecht Dreß <albrecht.dress@arcor.de>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 arch/powerpc/include/asm/mpc52xx.h        |   3 +-
 arch/powerpc/platforms/52xx/mpc52xx_gpt.c | 321 ++++++++++++++++++++--
 2 files changed, 307 insertions(+), 17 deletions(-)

diff --git a/arch/powerpc/include/asm/mpc52xx.h b/arch/powerpc/include/asm/mpc52xx.h
index 933fb8f6e797..b664ce79a172 100644
--- a/arch/powerpc/include/asm/mpc52xx.h
+++ b/arch/powerpc/include/asm/mpc52xx.h
@@ -281,7 +281,8 @@ struct mpc52xx_gpt_priv;
 extern struct mpc52xx_gpt_priv *mpc52xx_gpt_from_irq(int irq);
 extern int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period,
                             int continuous);
-extern void mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt);
+extern u64 mpc52xx_gpt_timer_period(struct mpc52xx_gpt_priv *gpt);
+extern int mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt);
 
 /* mpc52xx_lpbfifo.c */
 #define MPC52XX_LPBFIFO_FLAG_READ		(0)
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 77572abca6c3..7085e4c60ba1 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -16,8 +16,14 @@
  * output signals or measure input signals.
  *
  * This driver supports the GPIO and IRQ controller functions of the GPT
- * device.  Timer functions are not yet supported, nor is the watchdog
- * timer.
+ * device.  Timer functions are not yet supported.
+ *
+ * The timer gpt0 can be used as watchdog (wdt).  If the wdt mode is used,
+ * this prevents the use of any gpt0 gpt function (i.e. they will fail with
+ * -EBUSY).  Thus, the safety wdt function always has precedence over the gpt
+ * function.  If the kernel has been compiled with CONFIG_WATCHDOG_NOWAYOUT,
+ * this means that gpt0 is locked in wdt mode until the next reboot - this
+ * may be a requirement in safety applications.
  *
  * To use the GPIO function, the following two properties must be added
  * to the device tree node for the gpt device (typically in the .dts file
@@ -56,11 +62,14 @@
 #include <linux/of_platform.h>
 #include <linux/of_gpio.h>
 #include <linux/kernel.h>
+#include <linux/watchdog.h>
+#include <linux/miscdevice.h>
+#include <linux/uaccess.h>
 #include <asm/div64.h>
 #include <asm/mpc52xx.h>
 
 MODULE_DESCRIPTION("Freescale MPC52xx gpt driver");
-MODULE_AUTHOR("Sascha Hauer, Grant Likely");
+MODULE_AUTHOR("Sascha Hauer, Grant Likely, Albrecht Dreß");
 MODULE_LICENSE("GPL");
 
 /**
@@ -70,6 +79,9 @@ MODULE_LICENSE("GPL");
  * @lock: spinlock to coordinate between different functions.
  * @of_gc: of_gpio_chip instance structure; used when GPIO is enabled
  * @irqhost: Pointer to irq_host instance; used when IRQ mode is supported
+ * @wdt_mode: only relevant for gpt0: bit 0 (MPC52xx_GPT_CAN_WDT) indicates
+ *   if the gpt may be used as wdt, bit 1 (MPC52xx_GPT_IS_WDT) indicates
+ *   if the timer is actively used as wdt which blocks gpt functions
  */
 struct mpc52xx_gpt_priv {
 	struct list_head list;		/* List of all GPT devices */
@@ -78,6 +90,7 @@ struct mpc52xx_gpt_priv {
 	spinlock_t lock;
 	struct irq_host *irqhost;
 	u32 ipb_freq;
+	u8 wdt_mode;
 
 #if defined(CONFIG_GPIOLIB)
 	struct of_gpio_chip of_gc;
@@ -101,14 +114,21 @@ DEFINE_MUTEX(mpc52xx_gpt_list_mutex);
 #define MPC52xx_GPT_MODE_CONTINUOUS	(0x0400)
 #define MPC52xx_GPT_MODE_OPEN_DRAIN	(0x0200)
 #define MPC52xx_GPT_MODE_IRQ_EN		(0x0100)
+#define MPC52xx_GPT_MODE_WDT_EN		(0x8000)
 
 #define MPC52xx_GPT_MODE_ICT_MASK	(0x030000)
 #define MPC52xx_GPT_MODE_ICT_RISING	(0x010000)
 #define MPC52xx_GPT_MODE_ICT_FALLING	(0x020000)
 #define MPC52xx_GPT_MODE_ICT_TOGGLE	(0x030000)
 
+#define MPC52xx_GPT_MODE_WDT_PING	(0xa5)
+
 #define MPC52xx_GPT_STATUS_IRQMASK	(0x000f)
 
+#define MPC52xx_GPT_CAN_WDT		(1 << 0)
+#define MPC52xx_GPT_IS_WDT		(1 << 1)
+
+
 /* ---------------------------------------------------------------------
  * Cascaded interrupt controller hooks
  */
@@ -375,16 +395,8 @@ struct mpc52xx_gpt_priv *mpc52xx_gpt_from_irq(int irq)
 }
 EXPORT_SYMBOL(mpc52xx_gpt_from_irq);
 
-/**
- * mpc52xx_gpt_start_timer - Set and enable the GPT timer
- * @gpt: Pointer to gpt private data structure
- * @period: period of timer in ns; max. ~130s @ 33MHz IPB clock
- * @continuous: set to 1 to make timer continuous free running
- *
- * An interrupt will be generated every time the timer fires
- */
-int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period,
-                            int continuous)
+static int mpc52xx_gpt_do_start(struct mpc52xx_gpt_priv *gpt, u64 period,
+				int continuous, int as_wdt)
 {
 	u32 clear, set;
 	u64 clocks;
@@ -393,7 +405,10 @@ int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period,
 
 	clear = MPC52xx_GPT_MODE_MS_MASK | MPC52xx_GPT_MODE_CONTINUOUS;
 	set = MPC52xx_GPT_MODE_MS_GPIO | MPC52xx_GPT_MODE_COUNTER_ENABLE;
-	if (continuous)
+	if (as_wdt) {
+		clear |= MPC52xx_GPT_MODE_IRQ_EN;
+		set |= MPC52xx_GPT_MODE_WDT_EN;
+	} else if (continuous)
 		set |= MPC52xx_GPT_MODE_CONTINUOUS;
 
 	/* Determine the number of clocks in the requested period.  64 bit
@@ -427,22 +442,279 @@ int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period,
 		return -EINVAL;
 	}
 
-	/* Set and enable the timer */
+	/* Set and enable the timer, reject an attempt to use a wdt as gpt */
 	spin_lock_irqsave(&gpt->lock, flags);
+	if (as_wdt)
+		gpt->wdt_mode |= MPC52xx_GPT_IS_WDT;
+	else if ((gpt->wdt_mode & MPC52xx_GPT_IS_WDT) != 0) {
+		spin_unlock_irqrestore(&gpt->lock, flags);
+		return -EBUSY;
+	}
 	out_be32(&gpt->regs->count, prescale << 16 | clocks);
 	clrsetbits_be32(&gpt->regs->mode, clear, set);
 	spin_unlock_irqrestore(&gpt->lock, flags);
 
 	return 0;
 }
+
+/**
+ * mpc52xx_gpt_start_timer - Set and enable the GPT timer
+ * @gpt: Pointer to gpt private data structure
+ * @period: period of timer in ns; max. ~130s @ 33MHz IPB clock
+ * @continuous: set to 1 to make timer continuous free running
+ *
+ * An interrupt will be generated every time the timer fires
+ */
+int mpc52xx_gpt_start_timer(struct mpc52xx_gpt_priv *gpt, u64 period,
+                            int continuous)
+{
+	return mpc52xx_gpt_do_start(gpt, period, continuous, 0);
+}
 EXPORT_SYMBOL(mpc52xx_gpt_start_timer);
 
-void mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt)
+/**
+ * mpc52xx_gpt_stop_timer - Stop a gpt
+ * @gpt: Pointer to gpt private data structure
+ *
+ * Returns an error if attempting to stop a wdt
+ */
+int mpc52xx_gpt_stop_timer(struct mpc52xx_gpt_priv *gpt)
 {
+	unsigned long flags;
+
+	/* reject the operation if the timer is used as watchdog (gpt 0 only) */
+	spin_lock_irqsave(&gpt->lock, flags);
+	if ((gpt->wdt_mode & MPC52xx_GPT_IS_WDT) != 0) {
+		spin_unlock_irqrestore(&gpt->lock, flags);
+		return -EBUSY;
+	}
+
 	clrbits32(&gpt->regs->mode, MPC52xx_GPT_MODE_COUNTER_ENABLE);
+	spin_unlock_irqrestore(&gpt->lock, flags);
+	return 0;
 }
 EXPORT_SYMBOL(mpc52xx_gpt_stop_timer);
 
+/**
+ * mpc52xx_gpt_timer_period - Read the timer period
+ * @gpt: Pointer to gpt private data structure
+ *
+ * Returns the timer period in ns
+ */
+u64 mpc52xx_gpt_timer_period(struct mpc52xx_gpt_priv *gpt)
+{
+	u64 period;
+	u64 prescale;
+	unsigned long flags;
+
+	spin_lock_irqsave(&gpt->lock, flags);
+	period = in_be32(&gpt->regs->count);
+	spin_unlock_irqrestore(&gpt->lock, flags);
+
+	prescale = period >> 16;
+	period &= 0xffff;
+	if (prescale == 0)
+		prescale = 0x10000;
+	period = period * prescale * 1000000000ULL;
+	do_div(period, (u64)gpt->ipb_freq);
+	return period;
+}
+EXPORT_SYMBOL(mpc52xx_gpt_timer_period);
+
+#if defined(CONFIG_MPC5200_WDT)
+/***********************************************************************
+ * Watchdog API for gpt0
+ */
+
+#define WDT_IDENTITY	    "mpc52xx watchdog on GPT0"
+
+/* wdt_is_active stores wether or not the /dev/watchdog device is opened */
+static unsigned long wdt_is_active;
+
+/* wdt-capable gpt */
+static struct mpc52xx_gpt_priv *mpc52xx_gpt_wdt;
+
+/* low-level wdt functions */
+static inline void mpc52xx_gpt_wdt_ping(struct mpc52xx_gpt_priv *gpt_wdt)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&gpt_wdt->lock, flags);
+	out_8((u8 *) &gpt_wdt->regs->mode, MPC52xx_GPT_MODE_WDT_PING);
+	spin_unlock_irqrestore(&gpt_wdt->lock, flags);
+}
+
+/* wdt misc device api */
+static ssize_t mpc52xx_wdt_write(struct file *file, const char __user *data,
+				 size_t len, loff_t *ppos)
+{
+	struct mpc52xx_gpt_priv *gpt_wdt = file->private_data;
+	mpc52xx_gpt_wdt_ping(gpt_wdt);
+	return 0;
+}
+
+static struct watchdog_info mpc5200_wdt_info = {
+	.options	= WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING,
+	.identity	= WDT_IDENTITY,
+};
+
+static long mpc52xx_wdt_ioctl(struct file *file, unsigned int cmd,
+			      unsigned long arg)
+{
+	struct mpc52xx_gpt_priv *gpt_wdt = file->private_data;
+	int __user *data = (int __user *)arg;
+	int timeout;
+	u64 real_timeout;
+	int ret = 0;
+
+	switch (cmd) {
+	case WDIOC_GETSUPPORT:
+		ret = copy_to_user(data, &mpc5200_wdt_info,
+				   sizeof(mpc5200_wdt_info));
+		if (ret)
+			ret = -EFAULT;
+		break;
+
+	case WDIOC_GETSTATUS:
+	case WDIOC_GETBOOTSTATUS:
+		ret = put_user(0, data);
+		break;
+
+	case WDIOC_KEEPALIVE:
+		mpc52xx_gpt_wdt_ping(gpt_wdt);
+		break;
+
+	case WDIOC_SETTIMEOUT:
+		ret = get_user(timeout, data);
+		if (ret)
+			break;
+		real_timeout = (u64) timeout * 1000000000ULL;
+		ret = mpc52xx_gpt_do_start(gpt_wdt, real_timeout, 0, 1);
+		if (ret)
+			break;
+		/* fall through and return the timeout */
+
+	case WDIOC_GETTIMEOUT:
+		/* we need to round here as to avoid e.g. the following
+		 * situation:
+		 * - timeout requested is 1 second;
+		 * - real timeout @33MHz is 999997090ns
+		 * - the int divide by 10^9 will return 0.
+		 */
+		real_timeout =
+			mpc52xx_gpt_timer_period(gpt_wdt) + 500000000ULL;
+		do_div(real_timeout, 1000000000ULL);
+		timeout = (int) real_timeout;
+		ret = put_user(timeout, data);
+		break;
+
+	default:
+		ret = -ENOTTY;
+	}
+	return ret;
+}
+
+static int mpc52xx_wdt_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	/* sanity check */
+	if (!mpc52xx_gpt_wdt)
+		return -ENODEV;
+
+	/* /dev/watchdog can only be opened once */
+	if (test_and_set_bit(0, &wdt_is_active))
+		return -EBUSY;
+
+	/* Set and activate the watchdog with 30 seconds timeout */
+	ret = mpc52xx_gpt_do_start(mpc52xx_gpt_wdt, 30ULL * 1000000000ULL,
+				   0, 1);
+	if (ret) {
+		clear_bit(0, &wdt_is_active);
+		return ret;
+	}
+
+	file->private_data = mpc52xx_gpt_wdt;
+	return nonseekable_open(inode, file);
+}
+
+static int mpc52xx_wdt_release(struct inode *inode, struct file *file)
+{
+	/* note: releasing the wdt in NOWAYOUT-mode does not stop it */
+#if !defined(CONFIG_WATCHDOG_NOWAYOUT)
+	struct mpc52xx_gpt_priv *gpt_wdt = file->private_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&gpt_wdt->lock, flags);
+	clrbits32(&gpt_wdt->regs->mode,
+		  MPC52xx_GPT_MODE_COUNTER_ENABLE | MPC52xx_GPT_MODE_WDT_EN);
+	gpt_wdt->wdt_mode &= ~MPC52xx_GPT_IS_WDT;
+	spin_unlock_irqrestore(&gpt_wdt->lock, flags);
+#endif
+	clear_bit(0, &wdt_is_active);
+	return 0;
+}
+
+
+static const struct file_operations mpc52xx_wdt_fops = {
+	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
+	.write		= mpc52xx_wdt_write,
+	.unlocked_ioctl = mpc52xx_wdt_ioctl,
+	.open		= mpc52xx_wdt_open,
+	.release	= mpc52xx_wdt_release,
+};
+
+static struct miscdevice mpc52xx_wdt_miscdev = {
+	.minor		= WATCHDOG_MINOR,
+	.name		= "watchdog",
+	.fops		= &mpc52xx_wdt_fops,
+};
+
+static int __devinit mpc52xx_gpt_wdt_init(void)
+{
+	int err;
+
+	/* try to register the watchdog misc device */
+	err = misc_register(&mpc52xx_wdt_miscdev);
+	if (err)
+		pr_err("%s: cannot register watchdog device\n", WDT_IDENTITY);
+	else
+		pr_info("%s: watchdog device registered\n", WDT_IDENTITY);
+	return err;
+}
+
+static int mpc52xx_gpt_wdt_setup(struct mpc52xx_gpt_priv *gpt,
+				 const u32 *period)
+{
+	u64 real_timeout;
+
+	/* remember the gpt for the wdt operation */
+	mpc52xx_gpt_wdt = gpt;
+
+	/* configure the wdt if the device tree contained a timeout */
+	if (!period || *period == 0)
+		return 0;
+
+	real_timeout = (u64) *period * 1000000000ULL;
+	if (mpc52xx_gpt_do_start(gpt, real_timeout, 0, 1))
+		dev_warn(gpt->dev, "starting as wdt failed\n");
+	else
+		dev_info(gpt->dev, "watchdog set to %us timeout\n", *period);
+	return 0;
+}
+
+#else
+
+static int __devinit mpc52xx_gpt_wdt_init(void)
+{
+	return 0;
+}
+
+#define mpc52xx_gpt_wdt_setup(x, y)		(0)
+
+#endif	/*  CONFIG_MPC5200_WDT	*/
+
 /* ---------------------------------------------------------------------
  * of_platform bus binding code
  */
@@ -473,6 +745,22 @@ static int __devinit mpc52xx_gpt_probe(struct of_device *ofdev,
 	list_add(&gpt->list, &mpc52xx_gpt_list);
 	mutex_unlock(&mpc52xx_gpt_list_mutex);
 
+	/* check if this device could be a watchdog */
+	if (of_get_property(ofdev->node, "fsl,has-wdt", NULL) ||
+	    of_get_property(ofdev->node, "has-wdt", NULL)) {
+		const u32 *on_boot_wdt;
+
+		gpt->wdt_mode = MPC52xx_GPT_CAN_WDT;
+		on_boot_wdt = of_get_property(ofdev->node, "fsl,wdt-on-boot",
+					      NULL);
+		if (on_boot_wdt) {
+			dev_info(gpt->dev, "used as watchdog\n");
+			gpt->wdt_mode |= MPC52xx_GPT_IS_WDT;
+		} else
+			dev_info(gpt->dev, "can function as watchdog\n");
+		mpc52xx_gpt_wdt_setup(gpt, on_boot_wdt);
+	}
+
 	return 0;
 }
 
@@ -507,3 +795,4 @@ static int __init mpc52xx_gpt_init(void)
 
 /* Make sure GPIOs and IRQs get set up before anyone tries to use them */
 subsys_initcall(mpc52xx_gpt_init);
+device_initcall(mpc52xx_gpt_wdt_init);

From 5753c082f66eca5be81f6bda85c1718c5eea6ada Mon Sep 17 00:00:00 2001
From: Kumar Gala <galak@kernel.crashing.org>
Date: Fri, 16 Oct 2009 18:31:48 -0500
Subject: [PATCH 090/151] powerpc/85xx: Kconfig cleanup

Introduce new FSL_SOC_BOOKE Kconfig to handle both 85xx and QorIQ
based chips.

Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/platforms/85xx/Kconfig    | 11 ++++++-----
 arch/powerpc/platforms/Kconfig         |  4 ++--
 arch/powerpc/platforms/Kconfig.cputype | 17 ++++++++---------
 arch/powerpc/platforms/Makefile        |  2 +-
 arch/powerpc/sysdev/fsl_pci.c          |  4 ++--
 arch/powerpc/sysdev/fsl_soc.c          |  2 +-
 6 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index d3a975e8fd3e..5de0d633836c 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -1,6 +1,7 @@
-menuconfig MPC85xx
-	bool "Machine Type"
-	depends on PPC_85xx
+menuconfig FSL_SOC_BOOKE
+	bool "Freescale Book-E Machine Type"
+	depends on PPC_85xx || PPC_BOOK3E
+	select FSL_SOC
 	select PPC_UDBG_16550
 	select MPIC
 	select PPC_PCI_CHOICE
@@ -8,7 +9,7 @@ menuconfig MPC85xx
 	select SERIAL_8250_SHARE_IRQ if SERIAL_8250
 	default y
 
-if MPC85xx
+if FSL_SOC_BOOKE
 
 config MPC8540_ADS
 	bool "Freescale MPC8540 ADS"
@@ -144,7 +145,7 @@ config SBC8560
 	help
 	  This option enables support for the Wind River SBC8560 board
 
-endif # MPC85xx
+endif # FSL_SOC_BOOKE
 
 config TQM85xx
 	bool
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 56bf12692f37..d1663db7810f 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -260,7 +260,7 @@ config QE_GPIO
 
 config CPM2
 	bool "Enable support for the CPM2 (Communications Processor Module)"
-	depends on MPC85xx || 8260
+	depends on (FSL_SOC_BOOKE && PPC32) || 8260
 	select CPM
 	select PPC_LIB_RHEAP
 	select PPC_PCI_CHOICE
@@ -305,7 +305,7 @@ source "arch/powerpc/sysdev/bestcomm/Kconfig"
 
 config MPC8xxx_GPIO
 	bool "MPC8xxx GPIO support"
-	depends on PPC_MPC831x || PPC_MPC834x || PPC_MPC837x || PPC_85xx || PPC_86xx
+	depends on PPC_MPC831x || PPC_MPC834x || PPC_MPC837x || FSL_SOC_BOOKE || PPC_86xx
 	select GENERIC_GPIO
 	select ARCH_REQUIRE_GPIOLIB
 	help
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index e382cae678b8..2eab27a94cc9 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -28,8 +28,6 @@ config PPC_BOOK3S_32
 config PPC_85xx
 	bool "Freescale 85xx"
 	select E500
-	select FSL_SOC
-	select MPC85xx
 
 config PPC_8xx
 	bool "Freescale 8xx"
@@ -138,6 +136,14 @@ config PPC_FPU
 	bool
 	default y if PPC64
 
+config FSL_EMB_PERFMON
+	bool "Freescale Embedded Perfmon"
+	depends on E500 || PPC_83xx
+	help
+	  This is the Performance Monitor support found on the e500 core
+	  and some e300 cores (c3 and c4).  Select this only if your
+	  core supports the Embedded Performance Monitor APU
+
 config 4xx
 	bool
 	depends on 40x || 44x
@@ -153,13 +159,6 @@ config FSL_BOOKE
 	depends on E200 || E500
 	default y
 
-config FSL_EMB_PERFMON
-	bool "Freescale Embedded Perfmon"
-	depends on E500 || PPC_83xx
-	help
-	  This is the Performance Monitor support found on the e500 core
-	  and some e300 cores (c3 and c4).  Select this only if your
-	  core supports the Embedded Performance Monitor APU
 
 config PTE_64BIT
 	bool
diff --git a/arch/powerpc/platforms/Makefile b/arch/powerpc/platforms/Makefile
index a6812ee00100..fdb9f0b0d7a8 100644
--- a/arch/powerpc/platforms/Makefile
+++ b/arch/powerpc/platforms/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_PPC_MPC52xx)	+= 52xx/
 obj-$(CONFIG_PPC_8xx)		+= 8xx/
 obj-$(CONFIG_PPC_82xx)		+= 82xx/
 obj-$(CONFIG_PPC_83xx)		+= 83xx/
-obj-$(CONFIG_PPC_85xx)		+= 85xx/
+obj-$(CONFIG_FSL_SOC_BOOKE)	+= 85xx/
 obj-$(CONFIG_PPC_86xx)		+= 86xx/
 obj-$(CONFIG_PPC_PSERIES)	+= pseries/
 obj-$(CONFIG_PPC_ISERIES)	+= iseries/
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index ae88b1448018..cf57a42c72af 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -56,7 +56,7 @@ static int __init fsl_pcie_check_link(struct pci_controller *hose)
 	return 0;
 }
 
-#if defined(CONFIG_PPC_85xx) || defined(CONFIG_PPC_86xx)
+#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
 static int __init setup_one_atmu(struct ccsr_pci __iomem *pci,
 	unsigned int index, const struct resource *res,
 	resource_size_t offset)
@@ -394,7 +394,7 @@ DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_MPC8641D, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_MPC8610, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2020E, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2020, quirk_fsl_pcie_header);
-#endif /* CONFIG_PPC_85xx || CONFIG_PPC_86xx */
+#endif /* CONFIG_FSL_SOC_BOOKE || CONFIG_PPC_86xx */
 
 #if defined(CONFIG_PPC_83xx) || defined(CONFIG_PPC_MPC512x)
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_MPC8314E, quirk_fsl_pcie_header);
diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c
index adca4affcf1f..b91f7acdda6f 100644
--- a/arch/powerpc/sysdev/fsl_soc.c
+++ b/arch/powerpc/sysdev/fsl_soc.c
@@ -372,7 +372,7 @@ err:
 
 arch_initcall(fsl_usb_of_init);
 
-#if defined(CONFIG_PPC_85xx) || defined(CONFIG_PPC_86xx)
+#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
 static __be32 __iomem *rstcr;
 
 static int __init setup_rstcr(void)

From 8b27f0b61db57f5555fc2d3fc95c3ea9fd1a9d6c Mon Sep 17 00:00:00 2001
From: Kumar Gala <galak@kernel.crashing.org>
Date: Thu, 15 Oct 2009 12:49:01 -0500
Subject: [PATCH 091/151] powerpc/fsl-booke: Rework TLB CAM code

Re-write the code so its more standalone and fixed some issues:
* Bump'd # of CAM entries to 64 to support e500mc
* Make the code handle MAS7 properly
* Use pr_cont instead of creating a string as we go

Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/kernel/asm-offsets.c    |   3 -
 arch/powerpc/kernel/head_fsl_booke.S |  22 -----
 arch/powerpc/mm/fsl_booke_mmu.c      | 132 +++++++++++++++------------
 arch/powerpc/mm/mmu_decl.h           |  11 ---
 4 files changed, 74 insertions(+), 94 deletions(-)

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index e2e2082acf29..a6c2b63227b3 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -421,9 +421,6 @@ int main(void)
 	DEFINE(PGD_T_LOG2, PGD_T_LOG2);
 	DEFINE(PTE_T_LOG2, PTE_T_LOG2);
 #endif
-#ifdef CONFIG_FSL_BOOKE
-	DEFINE(TLBCAM_SIZE, sizeof(struct tlbcam));
-#endif
 
 #ifdef CONFIG_KVM_EXIT_TIMING
 	DEFINE(VCPU_TIMING_EXIT_TBU, offsetof(struct kvm_vcpu,
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 975788ca05d2..7f4bd7f3b6af 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -943,28 +943,6 @@ _GLOBAL(__setup_e500mc_ivors)
 	sync
 	blr
 
-/*
- * extern void loadcam_entry(unsigned int index)
- *
- * Load TLBCAM[index] entry in to the L2 CAM MMU
- */
-_GLOBAL(loadcam_entry)
-	lis	r4,TLBCAM@ha
-	addi	r4,r4,TLBCAM@l
-	mulli	r5,r3,TLBCAM_SIZE
-	add	r3,r5,r4
-	lwz	r4,0(r3)
-	mtspr	SPRN_MAS0,r4
-	lwz	r4,4(r3)
-	mtspr	SPRN_MAS1,r4
-	lwz	r4,8(r3)
-	mtspr	SPRN_MAS2,r4
-	lwz	r4,12(r3)
-	mtspr	SPRN_MAS3,r4
-	tlbwe
-	isync
-	blr
-
 /*
  * extern void giveup_altivec(struct task_struct *prev)
  *
diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c
index dc93e95b256e..fcfcb6e976c7 100644
--- a/arch/powerpc/mm/fsl_booke_mmu.c
+++ b/arch/powerpc/mm/fsl_booke_mmu.c
@@ -54,26 +54,35 @@
 
 #include "mmu_decl.h"
 
-extern void loadcam_entry(unsigned int index);
 unsigned int tlbcam_index;
-static unsigned long cam[CONFIG_LOWMEM_CAM_NUM];
 
-#define NUM_TLBCAMS	(16)
+#define NUM_TLBCAMS	(64)
 
 #if defined(CONFIG_LOWMEM_CAM_NUM_BOOL) && (CONFIG_LOWMEM_CAM_NUM >= NUM_TLBCAMS)
 #error "LOWMEM_CAM_NUM must be less than NUM_TLBCAMS"
 #endif
 
-struct tlbcam TLBCAM[NUM_TLBCAMS];
+struct tlbcam {
+	u32	MAS0;
+	u32	MAS1;
+	unsigned long	MAS2;
+	u32	MAS3;
+	u32	MAS7;
+} TLBCAM[NUM_TLBCAMS];
 
 struct tlbcamrange {
-   	unsigned long start;
+	unsigned long start;
 	unsigned long limit;
 	phys_addr_t phys;
 } tlbcam_addrs[NUM_TLBCAMS];
 
 extern unsigned int tlbcam_index;
 
+unsigned long tlbcam_sz(int idx)
+{
+	return tlbcam_addrs[idx].limit - tlbcam_addrs[idx].start + 1;
+}
+
 /*
  * Return PA for this VA if it is mapped by a CAM, or 0
  */
@@ -94,23 +103,36 @@ unsigned long p_mapped_by_tlbcam(phys_addr_t pa)
 	int b;
 	for (b = 0; b < tlbcam_index; ++b)
 		if (pa >= tlbcam_addrs[b].phys
-	    	    && pa < (tlbcam_addrs[b].limit-tlbcam_addrs[b].start)
+			&& pa < (tlbcam_addrs[b].limit-tlbcam_addrs[b].start)
 		              +tlbcam_addrs[b].phys)
 			return tlbcam_addrs[b].start+(pa-tlbcam_addrs[b].phys);
 	return 0;
 }
 
+void loadcam_entry(int idx)
+{
+	mtspr(SPRN_MAS0, TLBCAM[idx].MAS0);
+	mtspr(SPRN_MAS1, TLBCAM[idx].MAS1);
+	mtspr(SPRN_MAS2, TLBCAM[idx].MAS2);
+	mtspr(SPRN_MAS3, TLBCAM[idx].MAS3);
+
+	if (cur_cpu_spec->cpu_features & MMU_FTR_BIG_PHYS)
+		mtspr(SPRN_MAS7, TLBCAM[idx].MAS7);
+
+	asm volatile("isync;tlbwe;isync" : : : "memory");
+}
+
 /*
  * Set up one of the I/D BAT (block address translation) register pairs.
  * The parameters are not checked; in particular size must be a power
  * of 4 between 4k and 256M.
  */
-void settlbcam(int index, unsigned long virt, phys_addr_t phys,
-		unsigned int size, int flags, unsigned int pid)
+static void settlbcam(int index, unsigned long virt, phys_addr_t phys,
+		unsigned long size, unsigned long flags, unsigned int pid)
 {
 	unsigned int tsize, lz;
 
-	asm ("cntlzw %0,%1" : "=r" (lz) : "r" (size));
+	asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (size));
 	tsize = 21 - lz;
 
 #ifdef CONFIG_SMP
@@ -128,8 +150,10 @@ void settlbcam(int index, unsigned long virt, phys_addr_t phys,
 	TLBCAM[index].MAS2 |= (flags & _PAGE_GUARDED) ? MAS2_G : 0;
 	TLBCAM[index].MAS2 |= (flags & _PAGE_ENDIAN) ? MAS2_E : 0;
 
-	TLBCAM[index].MAS3 = (phys & PAGE_MASK) | MAS3_SX | MAS3_SR;
+	TLBCAM[index].MAS3 = (phys & MAS3_RPN) | MAS3_SX | MAS3_SR;
 	TLBCAM[index].MAS3 |= ((flags & _PAGE_RW) ? MAS3_SW : 0);
+	if (cur_cpu_spec->cpu_features & MMU_FTR_BIG_PHYS)
+		TLBCAM[index].MAS7 = (u64)phys >> 32;
 
 #ifndef CONFIG_KGDB /* want user access for breakpoints */
 	if (flags & _PAGE_USER) {
@@ -148,27 +172,44 @@ void settlbcam(int index, unsigned long virt, phys_addr_t phys,
 	loadcam_entry(index);
 }
 
-void invalidate_tlbcam_entry(int index)
+unsigned long map_mem_in_cams(unsigned long ram, int max_cam_idx)
 {
-	TLBCAM[index].MAS0 = MAS0_TLBSEL(1) | MAS0_ESEL(index);
-	TLBCAM[index].MAS1 = ~MAS1_VALID;
+	int i;
+	unsigned long virt = PAGE_OFFSET;
+	phys_addr_t phys = memstart_addr;
+	unsigned long amount_mapped = 0;
+	unsigned long max_cam = (mfspr(SPRN_TLB1CFG) >> 16) & 0xf;
 
-	loadcam_entry(index);
+	/* Convert (4^max) kB to (2^max) bytes */
+	max_cam = max_cam * 2 + 10;
+
+	/* Calculate CAM values */
+	for (i = 0; ram && i < max_cam_idx; i++) {
+		unsigned int camsize = __ilog2(ram) & ~1U;
+		unsigned int align = __ffs(virt | phys) & ~1U;
+		unsigned long cam_sz;
+
+		if (camsize > align)
+			camsize = align;
+		if (camsize > max_cam)
+			camsize = max_cam;
+
+		cam_sz = 1UL << camsize;
+		settlbcam(i, virt, phys, cam_sz, PAGE_KERNEL_X, 0);
+
+		ram -= cam_sz;
+		amount_mapped += cam_sz;
+		virt += cam_sz;
+		phys += cam_sz;
+	}
+	tlbcam_index = i;
+
+	return amount_mapped;
 }
 
 unsigned long __init mmu_mapin_ram(void)
 {
-	unsigned long virt = PAGE_OFFSET;
-	phys_addr_t phys = memstart_addr;
-
-	while (tlbcam_index < ARRAY_SIZE(cam) && cam[tlbcam_index]) {
-		settlbcam(tlbcam_index, virt, phys, cam[tlbcam_index], PAGE_KERNEL_X, 0);
-		virt += cam[tlbcam_index];
-		phys += cam[tlbcam_index];
-		tlbcam_index++;
-	}
-
-	return virt - PAGE_OFFSET;
+	return tlbcam_addrs[tlbcam_index - 1].limit - PAGE_OFFSET + 1;
 }
 
 /*
@@ -179,46 +220,21 @@ void __init MMU_init_hw(void)
 	flush_instruction_cache();
 }
 
-void __init
-adjust_total_lowmem(void)
+void __init adjust_total_lowmem(void)
 {
-	phys_addr_t ram;
-	unsigned int max_cam = (mfspr(SPRN_TLB1CFG) >> 16) & 0xff;
-	char buf[ARRAY_SIZE(cam) * 5 + 1], *p = buf;
+	unsigned long ram;
 	int i;
-	unsigned long virt = PAGE_OFFSET & 0xffffffffUL;
-	unsigned long phys = memstart_addr & 0xffffffffUL;
-
-	/* Convert (4^max) kB to (2^max) bytes */
-	max_cam = max_cam * 2 + 10;
 
 	/* adjust lowmem size to __max_low_memory */
 	ram = min((phys_addr_t)__max_low_memory, (phys_addr_t)total_lowmem);
 
-	/* Calculate CAM values */
-	__max_low_memory = 0;
-	for (i = 0; ram && i < ARRAY_SIZE(cam); i++) {
-		unsigned int camsize = __ilog2(ram) & ~1U;
-		unsigned int align = __ffs(virt | phys) & ~1U;
+	__max_low_memory = map_mem_in_cams(ram, CONFIG_LOWMEM_CAM_NUM);
 
-		if (camsize > align)
-			camsize = align;
-		if (camsize > max_cam)
-			camsize = max_cam;
-
-		cam[i] = 1UL << camsize;
-		ram -= cam[i];
-		__max_low_memory += cam[i];
-		virt += cam[i];
-		phys += cam[i];
-
-		p += sprintf(p, "%lu/", cam[i] >> 20);
-	}
-	for (; i < ARRAY_SIZE(cam); i++)
-		p += sprintf(p, "0/");
-	p[-1] = '\0';
-
-	pr_info("Memory CAM mapping: %s Mb, residual: %dMb\n", buf,
+	pr_info("Memory CAM mapping: ");
+	for (i = 0; i < tlbcam_index - 1; i++)
+		pr_cont("%lu/", tlbcam_sz(i) >> 20);
+	pr_cont("%lu Mb, residual: %dMb\n", tlbcam_sz(tlbcam_index - 1) >> 20,
 	        (unsigned int)((total_lowmem - __max_low_memory) >> 20));
+
 	__initial_memory_limit_addr = memstart_addr + __max_low_memory;
 }
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index d2e5321d5ea6..e27a990af42d 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -98,21 +98,10 @@ extern void _tlbia(void);
 
 #ifdef CONFIG_PPC32
 
-struct tlbcam {
-	u32	MAS0;
-	u32	MAS1;
-	u32	MAS2;
-	u32	MAS3;
-	u32	MAS7;
-};
-
 extern void mapin_ram(void);
 extern int map_page(unsigned long va, phys_addr_t pa, int flags);
 extern void setbat(int index, unsigned long virt, phys_addr_t phys,
 		   unsigned int size, int flags);
-extern void settlbcam(int index, unsigned long virt, phys_addr_t phys,
-		      unsigned int size, int flags, unsigned int pid);
-extern void invalidate_tlbcam_entry(int index);
 
 extern int __map_without_bats;
 extern unsigned long ioremap_base;

From a3f62bd2b20c769ddc989b242ddd274179e19ee6 Mon Sep 17 00:00:00 2001
From: Kumar Gala <galak@kernel.crashing.org>
Date: Sun, 18 Oct 2009 13:55:55 -0500
Subject: [PATCH 092/151] powerpc/fsl: Add PCI device ids for new QoirQ chips

Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/sysdev/fsl_pci.c | 14 ++++++++++++++
 include/linux/pci_ids.h       | 14 ++++++++++++++
 2 files changed, 28 insertions(+)

diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index cf57a42c72af..4e3a3e345ab3 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -392,8 +392,22 @@ DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_MPC8536, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_MPC8641, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_MPC8641D, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_MPC8610, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1011E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1011, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1013E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1013, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1020E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1020, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1022E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1022, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2010E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2010, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2020E, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2020, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P4040E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P4040, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P4080E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P4080, quirk_fsl_pcie_header);
 #endif /* CONFIG_FSL_SOC_BOOKE || CONFIG_PPC_86xx */
 
 #if defined(CONFIG_PPC_83xx) || defined(CONFIG_PPC_MPC512x)
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 9ceb392cb984..f988a0d68636 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2288,6 +2288,20 @@
 #define PCI_DEVICE_ID_MPC8536		0x0051
 #define PCI_DEVICE_ID_P2020E		0x0070
 #define PCI_DEVICE_ID_P2020		0x0071
+#define PCI_DEVICE_ID_P2010E		0x0078
+#define PCI_DEVICE_ID_P2010		0x0079
+#define PCI_DEVICE_ID_P1020E		0x0100
+#define PCI_DEVICE_ID_P1020		0x0101
+#define PCI_DEVICE_ID_P1011E		0x0108
+#define PCI_DEVICE_ID_P1011		0x0109
+#define PCI_DEVICE_ID_P1022E		0x0110
+#define PCI_DEVICE_ID_P1022		0x0111
+#define PCI_DEVICE_ID_P1013E		0x0118
+#define PCI_DEVICE_ID_P1013		0x0119
+#define PCI_DEVICE_ID_P4080E		0x0400
+#define PCI_DEVICE_ID_P4080		0x0401
+#define PCI_DEVICE_ID_P4040E		0x0408
+#define PCI_DEVICE_ID_P4040		0x0409
 #define PCI_DEVICE_ID_MPC8641		0x7010
 #define PCI_DEVICE_ID_MPC8641D		0x7011
 #define PCI_DEVICE_ID_MPC8610		0x7018

From 0d81df8701d0972117008911bf00ebb1eef1471f Mon Sep 17 00:00:00 2001
From: Martyn Welch <martyn.welch@gefanuc.com>
Date: Thu, 2 Jul 2009 17:12:31 +0100
Subject: [PATCH 093/151] powerpc/86xx: Enable NVRAM on GE Fanuc's SBC610

This patch enables the NVRAM found on the GE Fanuc SBC610

Signed-off-by: Martyn Welch <martyn.welch@gefanuc.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/boot/dts/gef_sbc610.dts           | 6 ++++++
 arch/powerpc/configs/86xx/gef_sbc610_defconfig | 4 ++--
 arch/powerpc/platforms/86xx/Kconfig            | 1 +
 arch/powerpc/platforms/86xx/gef_sbc610.c       | 5 +++++
 4 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/boot/dts/gef_sbc610.dts b/arch/powerpc/boot/dts/gef_sbc610.dts
index 35a63183eecc..30911adefc8e 100644
--- a/arch/powerpc/boot/dts/gef_sbc610.dts
+++ b/arch/powerpc/boot/dts/gef_sbc610.dts
@@ -84,6 +84,12 @@
 			  6 0 0xfd000000 0x00800000     // IO FPGA (8-bit)
 			  7 0 0xfd800000 0x00800000>;   // IO FPGA (32-bit)
 
+		nvram@3,0 {
+			device_type = "nvram";
+			compatible = "simtek,stk14ca8";
+			reg = <0x3 0x0 0x20000>;
+		};
+
 		fpga@4,0 {
 			compatible = "gef,fpga-regs";
 			reg = <0x4 0x0 0x40>;
diff --git a/arch/powerpc/configs/86xx/gef_sbc610_defconfig b/arch/powerpc/configs/86xx/gef_sbc610_defconfig
index 3b0fbfb28efd..1975d41e0763 100644
--- a/arch/powerpc/configs/86xx/gef_sbc610_defconfig
+++ b/arch/powerpc/configs/86xx/gef_sbc610_defconfig
@@ -219,7 +219,7 @@ CONFIG_MPIC=y
 # CONFIG_MPIC_WEIRD is not set
 # CONFIG_PPC_I8259 is not set
 # CONFIG_PPC_RTAS is not set
-# CONFIG_MMIO_NVRAM is not set
+CONFIG_MMIO_NVRAM=y
 # CONFIG_PPC_MPC106 is not set
 # CONFIG_PPC_970_NAP is not set
 # CONFIG_PPC_INDIRECT_IO is not set
@@ -1124,7 +1124,7 @@ CONFIG_UNIX98_PTYS=y
 # CONFIG_IPMI_HANDLER is not set
 CONFIG_HW_RANDOM=y
 # CONFIG_HW_RANDOM_TIMERIOMEM is not set
-# CONFIG_NVRAM is not set
+CONFIG_NVRAM=y
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
 # CONFIG_RAW_DRIVER is not set
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 9c7b64a3402b..9d02dea19bd8 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -51,6 +51,7 @@ config GEF_SBC310
 config GEF_SBC610
 	bool "GE Fanuc SBC610"
 	select DEFAULT_UIMAGE
+	select MMIO_NVRAM
 	select GENERIC_GPIO
 	select ARCH_REQUIRE_GPIOLIB
 	select HAS_RAPIDIO
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index 72b31a6010a0..e10688a0fc4e 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -33,6 +33,7 @@
 #include <asm/udbg.h>
 
 #include <asm/mpic.h>
+#include <asm/nvram.h>
 
 #include <sysdev/fsl_pci.h>
 #include <sysdev/fsl_soc.h>
@@ -95,6 +96,10 @@ static void __init gef_sbc610_setup_arch(void)
 			printk(KERN_WARNING "Unable to map board registers\n");
 		of_node_put(regs);
 	}
+
+#if defined(CONFIG_MMIO_NVRAM)
+	mmio_nvram_init();
+#endif
 }
 
 /* Return the PCB revision */

From 9093067ad11b22c967b0cbf5532ecb25b0d7d983 Mon Sep 17 00:00:00 2001
From: Martyn Welch <martyn.welch@gefanuc.com>
Date: Thu, 2 Jul 2009 17:12:37 +0100
Subject: [PATCH 094/151] powerpc/86xx: Support for NVRAM on GE Fanuc's SBC310

Add support for NVRAM on GE Fanuc's SBC310.

Signed-off-by: Martyn Welch <martyn.welch@gefanuc.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/boot/dts/gef_sbc310.dts           | 6 ++++++
 arch/powerpc/configs/86xx/gef_sbc310_defconfig | 2 +-
 arch/powerpc/platforms/86xx/Kconfig            | 1 +
 arch/powerpc/platforms/86xx/gef_sbc310.c       | 5 +++++
 4 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/boot/dts/gef_sbc310.dts b/arch/powerpc/boot/dts/gef_sbc310.dts
index 2107d3c7cfe1..820c2b355ab1 100644
--- a/arch/powerpc/boot/dts/gef_sbc310.dts
+++ b/arch/powerpc/boot/dts/gef_sbc310.dts
@@ -115,6 +115,12 @@
 			};
 		};
 
+		nvram@3,0 {
+			device_type = "nvram";
+			compatible = "simtek,stk14ca8";
+			reg = <0x3 0x0 0x20000>;
+		};
+
 		fpga@4,0 {
 			compatible = "gef,fpga-regs";
 			reg = <0x4 0x0 0x40>;
diff --git a/arch/powerpc/configs/86xx/gef_sbc310_defconfig b/arch/powerpc/configs/86xx/gef_sbc310_defconfig
index e199d1cacbaf..a6a3768f7304 100644
--- a/arch/powerpc/configs/86xx/gef_sbc310_defconfig
+++ b/arch/powerpc/configs/86xx/gef_sbc310_defconfig
@@ -218,7 +218,7 @@ CONFIG_MPIC=y
 # CONFIG_MPIC_WEIRD is not set
 # CONFIG_PPC_I8259 is not set
 # CONFIG_PPC_RTAS is not set
-# CONFIG_MMIO_NVRAM is not set
+CONFIG_MMIO_NVRAM=y
 # CONFIG_PPC_MPC106 is not set
 # CONFIG_PPC_970_NAP is not set
 # CONFIG_PPC_INDIRECT_IO is not set
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 9d02dea19bd8..6012022dcf79 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -43,6 +43,7 @@ config GEF_PPC9A
 config GEF_SBC310
 	bool "GE Fanuc SBC310"
 	select DEFAULT_UIMAGE
+	select MMIO_NVRAM
 	select GENERIC_GPIO
 	select ARCH_REQUIRE_GPIOLIB
 	help
diff --git a/arch/powerpc/platforms/86xx/gef_sbc310.c b/arch/powerpc/platforms/86xx/gef_sbc310.c
index 90754e752bd8..6a1a613836c2 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc310.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc310.c
@@ -33,6 +33,7 @@
 #include <asm/udbg.h>
 
 #include <asm/mpic.h>
+#include <asm/nvram.h>
 
 #include <sysdev/fsl_pci.h>
 #include <sysdev/fsl_soc.h>
@@ -95,6 +96,10 @@ static void __init gef_sbc310_setup_arch(void)
 			printk(KERN_WARNING "Unable to map board registers\n");
 		of_node_put(regs);
 	}
+
+#if defined(CONFIG_MMIO_NVRAM)
+	mmio_nvram_init();
+#endif
 }
 
 /* Return the PCB revision */

From 3bc265627a0e163acebd35235454c525ea020804 Mon Sep 17 00:00:00 2001
From: Martyn Welch <martyn.welch@gefanuc.com>
Date: Thu, 2 Jul 2009 17:12:44 +0100
Subject: [PATCH 095/151] powerpc/86xx: Support for NVRAM on GE Fanuc's PPC9A

Add support for NVRAM on GE Fanuc's PPC9A.

Signed-off-by: Martyn Welch <martyn.welch@gefanuc.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/boot/dts/gef_ppc9a.dts           | 6 ++++++
 arch/powerpc/configs/86xx/gef_ppc9a_defconfig | 2 +-
 arch/powerpc/platforms/86xx/Kconfig           | 1 +
 arch/powerpc/platforms/86xx/gef_ppc9a.c       | 5 +++++
 4 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/boot/dts/gef_ppc9a.dts b/arch/powerpc/boot/dts/gef_ppc9a.dts
index 910944edd886..c86114e93f1e 100644
--- a/arch/powerpc/boot/dts/gef_ppc9a.dts
+++ b/arch/powerpc/boot/dts/gef_ppc9a.dts
@@ -118,6 +118,12 @@
 			};
 		};
 
+		nvram@3,0 {
+			device_type = "nvram";
+			compatible = "simtek,stk14ca8";
+			reg = <0x3 0x0 0x20000>;
+		};
+
 		fpga@4,0 {
 			compatible = "gef,ppc9a-fpga-regs";
 			reg = <0x4 0x0 0x40>;
diff --git a/arch/powerpc/configs/86xx/gef_ppc9a_defconfig b/arch/powerpc/configs/86xx/gef_ppc9a_defconfig
index 28980738776c..6cd2cd65c2cd 100644
--- a/arch/powerpc/configs/86xx/gef_ppc9a_defconfig
+++ b/arch/powerpc/configs/86xx/gef_ppc9a_defconfig
@@ -218,7 +218,7 @@ CONFIG_MPIC=y
 # CONFIG_MPIC_WEIRD is not set
 # CONFIG_PPC_I8259 is not set
 # CONFIG_PPC_RTAS is not set
-# CONFIG_MMIO_NVRAM is not set
+CONFIG_MMIO_NVRAM=y
 # CONFIG_PPC_MPC106 is not set
 # CONFIG_PPC_970_NAP is not set
 # CONFIG_PPC_INDIRECT_IO is not set
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 6012022dcf79..2bbfd530d6d8 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -35,6 +35,7 @@ config MPC8610_HPCD
 config GEF_PPC9A
 	bool "GE Fanuc PPC9A"
 	select DEFAULT_UIMAGE
+	select MMIO_NVRAM
 	select GENERIC_GPIO
 	select ARCH_REQUIRE_GPIOLIB
 	help
diff --git a/arch/powerpc/platforms/86xx/gef_ppc9a.c b/arch/powerpc/platforms/86xx/gef_ppc9a.c
index 287f7bd17dd9..a792e5d85813 100644
--- a/arch/powerpc/platforms/86xx/gef_ppc9a.c
+++ b/arch/powerpc/platforms/86xx/gef_ppc9a.c
@@ -33,6 +33,7 @@
 #include <asm/udbg.h>
 
 #include <asm/mpic.h>
+#include <asm/nvram.h>
 
 #include <sysdev/fsl_pci.h>
 #include <sysdev/fsl_soc.h>
@@ -95,6 +96,10 @@ static void __init gef_ppc9a_setup_arch(void)
 			printk(KERN_WARNING "Unable to map board registers\n");
 		of_node_put(regs);
 	}
+
+#if defined(CONFIG_MMIO_NVRAM)
+	mmio_nvram_init();
+#endif
 }
 
 /* Return the PCB revision */

From ab2f489294b69e6d736efa7a57dcf286cd9662a0 Mon Sep 17 00:00:00 2001
From: Kumar Gala <galak@kernel.crashing.org>
Date: Thu, 22 Oct 2009 16:35:07 -0500
Subject: [PATCH 096/151] powerpc/p4080: Add basic support for p4080ds platform

Add basic support for the P4080 DS reference board.  None of the data
path devices (ethernet, crypto, pme) are support at this time.

Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
---
 arch/powerpc/boot/dts/p4080ds.dts        | 554 +++++++++++++++++++++++
 arch/powerpc/platforms/85xx/Kconfig      |  12 +
 arch/powerpc/platforms/85xx/Makefile     |   1 +
 arch/powerpc/platforms/85xx/corenet_ds.c | 125 +++++
 arch/powerpc/platforms/85xx/corenet_ds.h |  19 +
 arch/powerpc/platforms/85xx/p4080_ds.c   |  74 +++
 6 files changed, 785 insertions(+)
 create mode 100644 arch/powerpc/boot/dts/p4080ds.dts
 create mode 100644 arch/powerpc/platforms/85xx/corenet_ds.c
 create mode 100644 arch/powerpc/platforms/85xx/corenet_ds.h
 create mode 100644 arch/powerpc/platforms/85xx/p4080_ds.c

diff --git a/arch/powerpc/boot/dts/p4080ds.dts b/arch/powerpc/boot/dts/p4080ds.dts
new file mode 100644
index 000000000000..6b29eab05362
--- /dev/null
+++ b/arch/powerpc/boot/dts/p4080ds.dts
@@ -0,0 +1,554 @@
+/*
+ * P4080DS Device Tree Source
+ *
+ * Copyright 2009 Freescale Semiconductor Inc.
+ *
+ * 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.
+ */
+
+/dts-v1/;
+
+/ {
+	model = "fsl,P4080DS";
+	compatible = "fsl,P4080DS";
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	aliases {
+		ccsr = &soc;
+
+		serial0 = &serial0;
+		serial1 = &serial1;
+		serial2 = &serial2;
+		serial3 = &serial3;
+		pci0 = &pci0;
+		pci1 = &pci1;
+		pci2 = &pci2;
+		usb0 = &usb0;
+		usb1 = &usb1;
+		dma0 = &dma0;
+		dma1 = &dma1;
+		sdhc = &sdhc;
+
+		rio0 = &rapidio0;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		cpu0: PowerPC,4080@0 {
+			device_type = "cpu";
+			reg = <0>;
+			next-level-cache = <&L2_0>;
+			L2_0: l2-cache {
+			};
+		};
+		cpu1: PowerPC,4080@1 {
+			device_type = "cpu";
+			reg = <1>;
+			next-level-cache = <&L2_1>;
+			L2_1: l2-cache {
+			};
+		};
+		cpu2: PowerPC,4080@2 {
+			device_type = "cpu";
+			reg = <2>;
+			next-level-cache = <&L2_2>;
+			L2_2: l2-cache {
+			};
+		};
+		cpu3: PowerPC,4080@3 {
+			device_type = "cpu";
+			reg = <3>;
+			next-level-cache = <&L2_3>;
+			L2_3: l2-cache {
+			};
+		};
+		cpu4: PowerPC,4080@4 {
+			device_type = "cpu";
+			reg = <4>;
+			next-level-cache = <&L2_4>;
+			L2_4: l2-cache {
+			};
+		};
+		cpu5: PowerPC,4080@5 {
+			device_type = "cpu";
+			reg = <5>;
+			next-level-cache = <&L2_5>;
+			L2_5: l2-cache {
+			};
+		};
+		cpu6: PowerPC,4080@6 {
+			device_type = "cpu";
+			reg = <6>;
+			next-level-cache = <&L2_6>;
+			L2_6: l2-cache {
+			};
+		};
+		cpu7: PowerPC,4080@7 {
+			device_type = "cpu";
+			reg = <7>;
+			next-level-cache = <&L2_7>;
+			L2_7: l2-cache {
+			};
+		};
+	};
+
+	memory {
+		device_type = "memory";
+	};
+
+	soc: soc@ffe000000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		device_type = "soc";
+		compatible = "simple-bus";
+		ranges = <0x00000000 0xf 0xfe000000 0x1000000>;
+		reg = <0xf 0xfe000000 0 0x00001000>;
+
+		corenet-law@0 {
+			compatible = "fsl,corenet-law";
+			reg = <0x0 0x1000>;
+			fsl,num-laws = <32>;
+		};
+
+		memory-controller@8000 {
+			compatible = "fsl,p4080-memory-controller";
+			reg = <0x8000 0x1000>;
+			interrupt-parent = <&mpic>;
+			interrupts = <0x12 2>;
+		};
+
+		memory-controller@9000 {
+			compatible = "fsl,p4080-memory-controller";
+			reg = <0x9000 0x1000>;
+			interrupt-parent = <&mpic>;
+			interrupts = <0x12 2>;
+		};
+
+		corenet-cf@18000 {
+			compatible = "fsl,corenet-cf";
+			reg = <0x18000 0x1000>;
+			fsl,ccf-num-csdids = <32>;
+			fsl,ccf-num-snoopids = <32>;
+		};
+
+		iommu@20000 {
+			compatible = "fsl,p4080-pamu";
+			reg = <0x20000 0x10000>;
+			interrupts = <24 2>;
+			interrupt-parent = <&mpic>;
+		};
+
+		mpic: pic@40000 {
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <2>;
+			reg = <0x40000 0x40000>;
+			compatible = "chrp,open-pic";
+			device_type = "open-pic";
+		};
+
+		dma0: dma@100300 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,p4080-dma", "fsl,eloplus-dma";
+			reg = <0x100300 0x4>;
+			ranges = <0x0 0x100100 0x200>;
+			cell-index = <0>;
+			dma-channel@0 {
+				compatible = "fsl,p4080-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x0 0x80>;
+				cell-index = <0>;
+				interrupt-parent = <&mpic>;
+				interrupts = <28 2>;
+			};
+			dma-channel@80 {
+				compatible = "fsl,p4080-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x80 0x80>;
+				cell-index = <1>;
+				interrupt-parent = <&mpic>;
+				interrupts = <29 2>;
+			};
+			dma-channel@100 {
+				compatible = "fsl,p4080-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x100 0x80>;
+				cell-index = <2>;
+				interrupt-parent = <&mpic>;
+				interrupts = <30 2>;
+			};
+			dma-channel@180 {
+				compatible = "fsl,p4080-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x180 0x80>;
+				cell-index = <3>;
+				interrupt-parent = <&mpic>;
+				interrupts = <31 2>;
+			};
+		};
+
+		dma1: dma@101300 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,p4080-dma", "fsl,eloplus-dma";
+			reg = <0x101300 0x4>;
+			ranges = <0x0 0x101100 0x200>;
+			cell-index = <1>;
+			dma-channel@0 {
+				compatible = "fsl,p4080-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x0 0x80>;
+				cell-index = <0>;
+				interrupt-parent = <&mpic>;
+				interrupts = <32 2>;
+			};
+			dma-channel@80 {
+				compatible = "fsl,p4080-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x80 0x80>;
+				cell-index = <1>;
+				interrupt-parent = <&mpic>;
+				interrupts = <33 2>;
+			};
+			dma-channel@100 {
+				compatible = "fsl,p4080-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x100 0x80>;
+				cell-index = <2>;
+				interrupt-parent = <&mpic>;
+				interrupts = <34 2>;
+			};
+			dma-channel@180 {
+				compatible = "fsl,p4080-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x180 0x80>;
+				cell-index = <3>;
+				interrupt-parent = <&mpic>;
+				interrupts = <35 2>;
+			};
+		};
+
+		spi@110000 {
+			cell-index = <0>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl,espi";
+			reg = <0x110000 0x1000>;
+			interrupts = <53 0x2>;
+			interrupt-parent = <&mpic>;
+			espi,num-ss-bits = <4>;
+			mode = "cpu";
+
+			fsl_m25p80@0 {
+				#address-cells = <1>;
+				#size-cells = <1>;
+				compatible = "fsl,espi-flash";
+				reg = <0>;
+				linux,modalias = "fsl_m25p80";
+				spi-max-frequency = <40000000>; /* input clock */
+				partition@u-boot {
+					label = "u-boot";
+					reg = <0x00000000 0x00100000>;
+					read-only;
+				};
+				partition@kernel {
+					label = "kernel";
+					reg = <0x00100000 0x00500000>;
+					read-only;
+				};
+				partition@dtb {
+					label = "dtb";
+					reg = <0x00600000 0x00100000>;
+					read-only;
+				};
+				partition@fs {
+					label = "file system";
+					reg = <0x00700000 0x00900000>;
+				};
+			};
+		};
+
+		sdhc: sdhc@114000 {
+			compatible = "fsl,p4080-esdhc", "fsl,esdhc";
+			reg = <0x114000 0x1000>;
+			interrupts = <48 2>;
+			interrupt-parent = <&mpic>;
+		};
+
+		i2c@118000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <0>;
+			compatible = "fsl-i2c";
+			reg = <0x118000 0x100>;
+			interrupts = <38 2>;
+			interrupt-parent = <&mpic>;
+			dfsrr;
+		};
+
+		i2c@118100 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <1>;
+			compatible = "fsl-i2c";
+			reg = <0x118100 0x100>;
+			interrupts = <38 2>;
+			interrupt-parent = <&mpic>;
+			dfsrr;
+			eeprom@51 {
+				compatible = "at24,24c256";
+				reg = <0x51>;
+			};
+			eeprom@52 {
+				compatible = "at24,24c256";
+				reg = <0x52>;
+			};
+			rtc@68 {
+				compatible = "dallas,ds3232";
+				reg = <0x68>;
+				interrupts = <0 0x1>;
+				interrupt-parent = <&mpic>;
+			};
+		};
+
+		i2c@119000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <2>;
+			compatible = "fsl-i2c";
+			reg = <0x119000 0x100>;
+			interrupts = <39 2>;
+			interrupt-parent = <&mpic>;
+			dfsrr;
+		};
+
+		i2c@119100 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <3>;
+			compatible = "fsl-i2c";
+			reg = <0x119100 0x100>;
+			interrupts = <39 2>;
+			interrupt-parent = <&mpic>;
+			dfsrr;
+		};
+
+		serial0: serial@11c500 {
+			cell-index = <0>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x11c500 0x100>;
+			clock-frequency = <0>;
+			interrupts = <36 2>;
+			interrupt-parent = <&mpic>;
+		};
+
+		serial1: serial@11c600 {
+			cell-index = <1>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x11c600 0x100>;
+			clock-frequency = <0>;
+			interrupts = <36 2>;
+			interrupt-parent = <&mpic>;
+		};
+
+		serial2: serial@11d500 {
+			cell-index = <2>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x11d500 0x100>;
+			clock-frequency = <0>;
+			interrupts = <37 2>;
+			interrupt-parent = <&mpic>;
+		};
+
+		serial3: serial@11d600 {
+			cell-index = <3>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x11d600 0x100>;
+			clock-frequency = <0>;
+			interrupts = <37 2>;
+			interrupt-parent = <&mpic>;
+		};
+
+		gpio0: gpio@130000 {
+			compatible = "fsl,p4080-gpio";
+			reg = <0x130000 0x1000>;
+			interrupts = <55 2>;
+			interrupt-parent = <&mpic>;
+			#gpio-cells = <2>;
+			gpio-controller;
+		};
+
+		usb0: usb@210000 {
+			compatible = "fsl,p4080-usb2-mph",
+					"fsl,mpc85xx-usb2-mph", "fsl-usb2-mph";
+			reg = <0x210000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupt-parent = <&mpic>;
+			interrupts = <44 0x2>;
+			phy_type = "ulpi";
+		};
+
+		usb1: usb@211000 {
+			compatible = "fsl,p4080-usb2-dr",
+					"fsl,mpc85xx-usb2-dr", "fsl-usb2-dr";
+			reg = <0x211000 0x1000>;
+			#address-cells = <1>;
+			#size-cells = <0>;
+			interrupt-parent = <&mpic>;
+			interrupts = <45 0x2>;
+			dr_mode = "host";
+			phy_type = "ulpi";
+		};
+	};
+
+	rapidio0: rapidio@ffe0c0000 {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		compatible = "fsl,rapidio-delta";
+		reg = <0xf 0xfe0c0000 0 0x20000>;
+		ranges = <0 0 0xf 0xf5000000 0 0x01000000>;
+		interrupt-parent = <&mpic>;
+		/* err_irq bell_outb_irq bell_inb_irq
+			msg1_tx_irq msg1_rx_irq	msg2_tx_irq msg2_rx_irq */
+		interrupts = <16 2 56 2 57 2 60 2 61 2 62 2 63 2>;
+	};
+
+	localbus@ffe124000 {
+		compatible = "fsl,p4080-elbc", "fsl,elbc", "simple-bus";
+		reg = <0xf 0xfe124000 0 0x1000>;
+		interrupts = <25 2>;
+		#address-cells = <2>;
+		#size-cells = <1>;
+
+		ranges = <0 0 0xf 0xe8000000 0x08000000>;
+
+		flash@0,0 {
+			compatible = "cfi-flash";
+			reg = <0 0 0x08000000>;
+			bank-width = <2>;
+			device-width = <2>;
+		};
+	};
+
+	pci0: pcie@ffe200000 {
+		compatible = "fsl,p4080-pcie";
+		device_type = "pci";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0xf 0xfe200000 0 0x1000>;
+		bus-range = <0x0 0xff>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x00000000 0x0 0x20000000
+			  0x01000000 0 0x00000000 0xf 0xf8000000 0x0 0x00010000>;
+		clock-frequency = <0x1fca055>;
+		interrupt-parent = <&mpic>;
+		interrupts = <16 2>;
+
+		interrupt-map-mask = <0xf800 0 0 7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0 0 1 &mpic 40 1
+			0000 0 0 2 &mpic 1 1
+			0000 0 0 3 &mpic 2 1
+			0000 0 0 4 &mpic 3 1
+			>;
+		pcie@0 {
+			reg = <0 0 0 0 0>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x20000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci1: pcie@ffe201000 {
+		compatible = "fsl,p4080-pcie";
+		device_type = "pci";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0xf 0xfe201000 0 0x1000>;
+		bus-range = <0 0xff>;
+		ranges = <0x02000000 0x0 0xe0000000 0xc 0x20000000 0x0 0x20000000
+			  0x01000000 0x0 0x00000000 0xf 0xf8010000 0x0 0x00010000>;
+		clock-frequency = <0x1fca055>;
+		interrupt-parent = <&mpic>;
+		interrupts = <16 2>;
+		interrupt-map-mask = <0xf800 0 0 7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0 0 1 &mpic 41 1
+			0000 0 0 2 &mpic 5 1
+			0000 0 0 3 &mpic 6 1
+			0000 0 0 4 &mpic 7 1
+			>;
+		pcie@0 {
+			reg = <0 0 0 0 0>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x20000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+	pci2: pcie@ffe202000 {
+		compatible = "fsl,p4080-pcie";
+		device_type = "pci";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0xf 0xfe202000 0 0x1000>;
+		bus-range = <0x0 0xff>;
+		ranges = <0x02000000 0 0xe0000000 0xc 0x40000000 0 0x20000000
+			  0x01000000 0 0x00000000 0xf 0xf8020000 0 0x00010000>;
+		clock-frequency = <0x1fca055>;
+		interrupt-parent = <&mpic>;
+		interrupts = <16 2>;
+		interrupt-map-mask = <0xf800 0 0 7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0 0 1 &mpic 42 1
+			0000 0 0 2 &mpic 9 1
+			0000 0 0 3 &mpic 10 1
+			0000 0 0 4 &mpic 11 1
+			>;
+		pcie@0 {
+			reg = <0 0 0 0 0>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			ranges = <0x02000000 0 0xe0000000
+				  0x02000000 0 0xe0000000
+				  0 0x20000000
+
+				  0x01000000 0 0x00000000
+				  0x01000000 0 0x00000000
+				  0 0x00010000>;
+		};
+	};
+
+};
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 5de0d633836c..d95121894eb7 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -145,6 +145,18 @@ config SBC8560
 	help
 	  This option enables support for the Wind River SBC8560 board
 
+config P4080_DS
+	bool "Freescale P4080 DS"
+	select DEFAULT_UIMAGE
+	select PPC_FSL_BOOK3E
+	select PPC_E500MC
+	select PHYS_64BIT
+	select SWIOTLB
+	select MPC8xxx_GPIO
+	select HAS_RAPIDIO
+	help
+	  This option enables support for the P4080 DS board
+
 endif # FSL_SOC_BOOKE
 
 config TQM85xx
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index 9098aea0cf32..387c128f2c8c 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_MPC8536_DS)  += mpc8536_ds.o
 obj-$(CONFIG_MPC85xx_DS)  += mpc85xx_ds.o
 obj-$(CONFIG_MPC85xx_MDS) += mpc85xx_mds.o
 obj-$(CONFIG_MPC85xx_RDB) += mpc85xx_rdb.o
+obj-$(CONFIG_P4080_DS)    += p4080_ds.o corenet_ds.o
 obj-$(CONFIG_STX_GP3)	  += stx_gp3.o
 obj-$(CONFIG_TQM85xx)	  += tqm85xx.o
 obj-$(CONFIG_SBC8560)     += sbc8560.o
diff --git a/arch/powerpc/platforms/85xx/corenet_ds.c b/arch/powerpc/platforms/85xx/corenet_ds.c
new file mode 100644
index 000000000000..534c2ecc89d9
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/corenet_ds.c
@@ -0,0 +1,125 @@
+/*
+ * Corenet based SoC DS Setup
+ *
+ * Maintained by Kumar Gala (see MAINTAINERS for contact information)
+ *
+ * Copyright 2009 Freescale Semiconductor Inc.
+ *
+ * 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 <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/kdev_t.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/lmb.h>
+
+#include <asm/system.h>
+#include <asm/time.h>
+#include <asm/machdep.h>
+#include <asm/pci-bridge.h>
+#include <mm/mmu_decl.h>
+#include <asm/prom.h>
+#include <asm/udbg.h>
+#include <asm/mpic.h>
+
+#include <linux/of_platform.h>
+#include <sysdev/fsl_soc.h>
+#include <sysdev/fsl_pci.h>
+
+void __init corenet_ds_pic_init(void)
+{
+	struct mpic *mpic;
+	struct resource r;
+	struct device_node *np = NULL;
+	unsigned int flags = MPIC_PRIMARY | MPIC_BIG_ENDIAN |
+				MPIC_BROKEN_FRR_NIRQS | MPIC_SINGLE_DEST_CPU;
+
+	np = of_find_node_by_type(np, "open-pic");
+
+	if (np == NULL) {
+		printk(KERN_ERR "Could not find open-pic node\n");
+		return;
+	}
+
+	if (of_address_to_resource(np, 0, &r)) {
+		printk(KERN_ERR "Failed to map mpic register space\n");
+		of_node_put(np);
+		return;
+	}
+
+	if (ppc_md.get_irq == mpic_get_coreint_irq)
+		flags |= MPIC_ENABLE_COREINT;
+
+	mpic = mpic_alloc(np, r.start, flags, 0, 256, " OpenPIC  ");
+	BUG_ON(mpic == NULL);
+
+	mpic_init(mpic);
+}
+
+#ifdef CONFIG_PCI
+static int primary_phb_addr;
+#endif
+
+/*
+ * Setup the architecture
+ */
+#ifdef CONFIG_SMP
+void __init mpc85xx_smp_init(void);
+#endif
+
+void __init corenet_ds_setup_arch(void)
+{
+#ifdef CONFIG_PCI
+	struct device_node *np;
+	struct pci_controller *hose;
+#endif
+	dma_addr_t max = 0xffffffff;
+
+#ifdef CONFIG_SMP
+	mpc85xx_smp_init();
+#endif
+
+#ifdef CONFIG_PCI
+	for_each_compatible_node(np, "pci", "fsl,p4080-pcie") {
+		struct resource rsrc;
+		of_address_to_resource(np, 0, &rsrc);
+		if ((rsrc.start & 0xfffff) == primary_phb_addr)
+			fsl_add_bridge(np, 1);
+		else
+			fsl_add_bridge(np, 0);
+
+		hose = pci_find_hose_for_OF_device(np);
+		max = min(max, hose->dma_window_base_cur +
+				hose->dma_window_size);
+	}
+#endif
+
+#ifdef CONFIG_SWIOTLB
+	if (lmb_end_of_DRAM() > max) {
+		ppc_swiotlb_enable = 1;
+		set_pci_dma_ops(&swiotlb_dma_ops);
+		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
+	}
+#endif
+	pr_info("%s board from Freescale Semiconductor\n", ppc_md.name);
+}
+
+static const struct of_device_id of_device_ids[] __devinitconst = {
+	{
+		.compatible	= "simple-bus"
+	},
+	{
+		.compatible	= "fsl,rapidio-delta",
+	},
+	{}
+};
+
+int __init corenet_ds_publish_devices(void)
+{
+	return of_platform_bus_probe(NULL, of_device_ids, NULL);
+}
diff --git a/arch/powerpc/platforms/85xx/corenet_ds.h b/arch/powerpc/platforms/85xx/corenet_ds.h
new file mode 100644
index 000000000000..ddd700b23031
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/corenet_ds.h
@@ -0,0 +1,19 @@
+/*
+ * Corenet based SoC DS Setup
+ *
+ * Copyright 2009 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef CORENET_DS_H
+#define CORENET_DS_H
+
+extern void __init corenet_ds_pic_init(void);
+extern void __init corenet_ds_setup_arch(void);
+extern int __init corenet_ds_publish_devices(void);
+
+#endif
diff --git a/arch/powerpc/platforms/85xx/p4080_ds.c b/arch/powerpc/platforms/85xx/p4080_ds.c
new file mode 100644
index 000000000000..84170460497b
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/p4080_ds.c
@@ -0,0 +1,74 @@
+/*
+ * P4080 DS Setup
+ *
+ * Maintained by Kumar Gala (see MAINTAINERS for contact information)
+ *
+ * Copyright 2009 Freescale Semiconductor Inc.
+ *
+ * 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 <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/kdev_t.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+
+#include <asm/system.h>
+#include <asm/time.h>
+#include <asm/machdep.h>
+#include <asm/pci-bridge.h>
+#include <mm/mmu_decl.h>
+#include <asm/prom.h>
+#include <asm/udbg.h>
+#include <asm/mpic.h>
+
+#include <linux/of_platform.h>
+#include <sysdev/fsl_soc.h>
+#include <sysdev/fsl_pci.h>
+
+#include "corenet_ds.h"
+
+#ifdef CONFIG_PCI
+static int primary_phb_addr;
+#endif
+
+/*
+ * Called very early, device-tree isn't unflattened
+ */
+static int __init p4080_ds_probe(void)
+{
+	unsigned long root = of_get_flat_dt_root();
+
+	if (of_flat_dt_is_compatible(root, "fsl,P4080DS")) {
+#ifdef CONFIG_PCI
+		/* treat PCIe1 as primary,
+		 * shouldn't matter as we have no ISA on the board
+		 */
+		primary_phb_addr = 0x0000;
+#endif
+		return 1;
+	} else {
+		return 0;
+	}
+}
+
+define_machine(p4080_ds) {
+	.name			= "P4080 DS",
+	.probe			= p4080_ds_probe,
+	.setup_arch		= corenet_ds_setup_arch,
+	.init_IRQ		= corenet_ds_pic_init,
+#ifdef CONFIG_PCI
+	.pcibios_fixup_bus	= fsl_pcibios_fixup_bus,
+#endif
+	.get_irq		= mpic_get_coreint_irq,
+	.restart		= fsl_rstcr_restart,
+	.calibrate_decr		= generic_calibrate_decr,
+	.progress		= udbg_progress,
+};
+
+machine_device_initcall(p4080_ds, corenet_ds_publish_devices);
+machine_arch_initcall(p4080_ds, swiotlb_setup_bus_notifier);

From 17e376756169af818c2e1c230502167cd1571a6c Mon Sep 17 00:00:00 2001
From: roel kluin <roel.kluin@gmail.com>
Date: Wed, 14 Oct 2009 05:32:28 +0000
Subject: [PATCH 097/151] powerpc/spufs: Fix test in spufs_switch_log_read()

size_t len cannot be less than 0.

Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Acked-by: Jeremy Kerr <jk@ozlabs.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/cell/spufs/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 884e8bcec499..64a4c2d85f7c 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -2494,7 +2494,7 @@ static ssize_t spufs_switch_log_read(struct file *file, char __user *buf,
 	struct spu_context *ctx = SPUFS_I(inode)->i_ctx;
 	int error = 0, cnt = 0;
 
-	if (!buf || len < 0)
+	if (!buf)
 		return -EINVAL;
 
 	error = spu_acquire(ctx);

From 3b03fecd12c4f2a0a3ea33612606320ad23e64fe Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 14 Oct 2009 22:42:28 +0000
Subject: [PATCH 098/151] powerpc: Use unlocked ioctl in nvram_64

The ioctl is only used for powermac systems and reads a partition
number from an array which is initialized at boot time way before the
nvram code is initialized. So it's safe to switch to unlocked_ioctl.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/nvram_64.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index a8f9251f4cac..ad461e735aec 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -139,8 +139,8 @@ out:
 
 }
 
-static int dev_nvram_ioctl(struct inode *inode, struct file *file,
-	unsigned int cmd, unsigned long arg)
+static long dev_nvram_ioctl(struct file *file, unsigned int cmd,
+			    unsigned long arg)
 {
 	switch(cmd) {
 #ifdef CONFIG_PPC_PMAC
@@ -169,11 +169,11 @@ static int dev_nvram_ioctl(struct inode *inode, struct file *file,
 }
 
 const struct file_operations nvram_fops = {
-	.owner =	THIS_MODULE,
-	.llseek =	dev_nvram_llseek,
-	.read =		dev_nvram_read,
-	.write =	dev_nvram_write,
-	.ioctl =	dev_nvram_ioctl,
+	.owner		= THIS_MODULE,
+	.llseek		= dev_nvram_llseek,
+	.read		= dev_nvram_read,
+	.write		= dev_nvram_write,
+	.unlocked_ioctl	= dev_nvram_ioctl,
 };
 
 static struct miscdevice nvram_dev = {

From 0b048c7a1d7f65e3e3f77834c03237be9d6d94b7 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 15 Oct 2009 10:28:38 +0000
Subject: [PATCH 099/151] macintosh: Remove BKL from nvram driver

Drop the bkl from nvram_llseek() as it obviously protects nothing. The
file offset is safe in essence.

The ioctl can be converted to unlocked_ioctl because it just calls
pmac_get_partition() which reads a value from an array which was
initialized at early boot time. No need for serialization.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 drivers/macintosh/nvram.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/macintosh/nvram.c b/drivers/macintosh/nvram.c
index b195d753d2ed..c876349c32de 100644
--- a/drivers/macintosh/nvram.c
+++ b/drivers/macintosh/nvram.c
@@ -13,7 +13,6 @@
 #include <linux/fcntl.h>
 #include <linux/nvram.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 #include <asm/nvram.h>
 
@@ -21,7 +20,6 @@
 
 static loff_t nvram_llseek(struct file *file, loff_t offset, int origin)
 {
-	lock_kernel();
 	switch (origin) {
 	case 1:
 		offset += file->f_pos;
@@ -30,12 +28,10 @@ static loff_t nvram_llseek(struct file *file, loff_t offset, int origin)
 		offset += NVRAM_SIZE;
 		break;
 	}
-	if (offset < 0) {
-		unlock_kernel();
+	if (offset < 0)
 		return -EINVAL;
-	}
+
 	file->f_pos = offset;
-	unlock_kernel();
 	return file->f_pos;
 }
 
@@ -76,8 +72,7 @@ static ssize_t write_nvram(struct file *file, const char __user *buf,
 	return p - buf;
 }
 
-static int nvram_ioctl(struct inode *inode, struct file *file,
-	unsigned int cmd, unsigned long arg)
+static long nvram_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	switch(cmd) {
 		case PMAC_NVRAM_GET_OFFSET:

From 293cfa44c3a861d63c77923667206356c4756ae0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 6 Nov 2009 12:41:46 +0000
Subject: [PATCH 100/151] powerpc: Replace old style lock initializer

SPIN_LOCK_UNLOCKED is deprecated. Init the lock array at runtime
instead.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org
Tested-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/iseries/htab.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/platforms/iseries/htab.c b/arch/powerpc/platforms/iseries/htab.c
index f99c6c4b6985..3ae66ab9d5e7 100644
--- a/arch/powerpc/platforms/iseries/htab.c
+++ b/arch/powerpc/platforms/iseries/htab.c
@@ -19,8 +19,7 @@
 
 #include "call_hpt.h"
 
-static spinlock_t iSeries_hlocks[64] __cacheline_aligned_in_smp =
-	{ [0 ... 63] = SPIN_LOCK_UNLOCKED};
+static spinlock_t iSeries_hlocks[64] __cacheline_aligned_in_smp;
 
 /*
  * Very primitive algorithm for picking up a lock
@@ -245,6 +244,11 @@ static void iSeries_hpte_invalidate(unsigned long slot, unsigned long va,
 
 void __init hpte_init_iSeries(void)
 {
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(iSeries_hlocks); i++)
+		spin_lock_init(&iSeries_hlocks[i]);
+
 	ppc_md.hpte_invalidate	= iSeries_hpte_invalidate;
 	ppc_md.hpte_updatepp	= iSeries_hpte_updatepp;
 	ppc_md.hpte_updateboltedpp = iSeries_hpte_updateboltedpp;

From b27df67248d3ae61d7814f18e363954254935090 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 18 Nov 2009 23:44:21 +0000
Subject: [PATCH 101/151] powerpc: Fixup last users of irq_chip->typename

The typename member of struct irq_chip was kept for migration purposes
and is obsolete since more than 2 years. Fix up the leftovers.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linuxppc-dev@ozlabs.org
Acked-by: Geoff Levand <geoffrey.levand@am.sony.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/irq.c                       | 6 +++---
 arch/powerpc/platforms/512x/mpc5121_ads_cpld.c  | 2 +-
 arch/powerpc/platforms/52xx/media5200.c         | 2 +-
 arch/powerpc/platforms/52xx/mpc52xx_gpt.c       | 2 +-
 arch/powerpc/platforms/52xx/mpc52xx_pic.c       | 8 ++++----
 arch/powerpc/platforms/82xx/pq2ads-pci-pic.c    | 1 -
 arch/powerpc/platforms/85xx/socrates_fpga_pic.c | 2 +-
 arch/powerpc/platforms/86xx/gef_pic.c           | 2 +-
 arch/powerpc/platforms/cell/axon_msi.c          | 2 +-
 arch/powerpc/platforms/cell/beat_interrupt.c    | 2 +-
 arch/powerpc/platforms/cell/interrupt.c         | 4 ++--
 arch/powerpc/platforms/cell/spider-pic.c        | 2 +-
 arch/powerpc/platforms/iseries/irq.c            | 2 +-
 arch/powerpc/platforms/powermac/pic.c           | 2 +-
 arch/powerpc/platforms/ps3/interrupt.c          | 2 +-
 arch/powerpc/platforms/pseries/xics.c           | 4 ++--
 arch/powerpc/sysdev/cpm1.c                      | 2 +-
 arch/powerpc/sysdev/cpm2_pic.c                  | 2 +-
 arch/powerpc/sysdev/fsl_msi.c                   | 2 +-
 arch/powerpc/sysdev/i8259.c                     | 2 +-
 arch/powerpc/sysdev/ipic.c                      | 4 ++--
 arch/powerpc/sysdev/mpc8xx_pic.c                | 2 +-
 arch/powerpc/sysdev/mpic.c                      | 6 +++---
 arch/powerpc/sysdev/mpic_pasemi_msi.c           | 2 +-
 arch/powerpc/sysdev/mpic_u3msi.c                | 2 +-
 arch/powerpc/sysdev/qe_lib/qe_ic.c              | 2 +-
 arch/powerpc/sysdev/tsi108_pci.c                | 2 +-
 arch/powerpc/sysdev/uic.c                       | 2 +-
 arch/powerpc/sysdev/xilinx_intc.c               | 4 ++--
 29 files changed, 39 insertions(+), 40 deletions(-)

diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index eba53923630f..a31176ace02b 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -223,7 +223,7 @@ int show_interrupts(struct seq_file *p, void *v)
 #endif /* CONFIG_SMP */
 
 	if (desc->chip)
-		seq_printf(p, " %s ", desc->chip->typename);
+		seq_printf(p, " %s ", desc->chip->name);
 	else
 		seq_puts(p, "  None      ");
 
@@ -1112,8 +1112,8 @@ static int virq_debug_show(struct seq_file *m, void *private)
 			seq_printf(m, "%5d  ", i);
 			seq_printf(m, "0x%05lx  ", virq_to_hw(i));
 
-			if (desc->chip && desc->chip->typename)
-				p = desc->chip->typename;
+			if (desc->chip && desc->chip->name)
+				p = desc->chip->name;
 			else
 				p = none;
 			seq_printf(m, "%-15s  ", p);
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index cd70ee1667fa..da9b20a63769 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -79,7 +79,7 @@ cpld_unmask_irq(unsigned int irq)
 }
 
 static struct irq_chip cpld_pic = {
-	.typename = " CPLD PIC ",
+	.name = " CPLD PIC ",
 	.mask = cpld_mask_irq,
 	.ack = cpld_mask_irq,
 	.unmask = cpld_unmask_irq,
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 478020358748..85001a4cbdff 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -74,7 +74,7 @@ static void media5200_irq_mask(unsigned int virq)
 }
 
 static struct irq_chip media5200_irq_chip = {
-	.typename = "Media5200 FPGA",
+	.name = "Media5200 FPGA",
 	.unmask = media5200_irq_unmask,
 	.mask = media5200_irq_mask,
 	.mask_ack = media5200_irq_mask,
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index bfbcd418e690..4d76b7f2336c 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -149,7 +149,7 @@ static int mpc52xx_gpt_irq_set_type(unsigned int virq, unsigned int flow_type)
 }
 
 static struct irq_chip mpc52xx_gpt_irq_chip = {
-	.typename = "MPC52xx GPT",
+	.name = "MPC52xx GPT",
 	.unmask = mpc52xx_gpt_irq_unmask,
 	.mask = mpc52xx_gpt_irq_mask,
 	.ack = mpc52xx_gpt_irq_ack,
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index 480f806fd0a9..a3122d163b6a 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -220,7 +220,7 @@ static int mpc52xx_extirq_set_type(unsigned int virq, unsigned int flow_type)
 }
 
 static struct irq_chip mpc52xx_extirq_irqchip = {
-	.typename = "MPC52xx External",
+	.name = "MPC52xx External",
 	.mask = mpc52xx_extirq_mask,
 	.unmask = mpc52xx_extirq_unmask,
 	.ack = mpc52xx_extirq_ack,
@@ -258,7 +258,7 @@ static void mpc52xx_main_unmask(unsigned int virq)
 }
 
 static struct irq_chip mpc52xx_main_irqchip = {
-	.typename = "MPC52xx Main",
+	.name = "MPC52xx Main",
 	.mask = mpc52xx_main_mask,
 	.mask_ack = mpc52xx_main_mask,
 	.unmask = mpc52xx_main_unmask,
@@ -291,7 +291,7 @@ static void mpc52xx_periph_unmask(unsigned int virq)
 }
 
 static struct irq_chip mpc52xx_periph_irqchip = {
-	.typename = "MPC52xx Peripherals",
+	.name = "MPC52xx Peripherals",
 	.mask = mpc52xx_periph_mask,
 	.mask_ack = mpc52xx_periph_mask,
 	.unmask = mpc52xx_periph_unmask,
@@ -335,7 +335,7 @@ static void mpc52xx_sdma_ack(unsigned int virq)
 }
 
 static struct irq_chip mpc52xx_sdma_irqchip = {
-	.typename = "MPC52xx SDMA",
+	.name = "MPC52xx SDMA",
 	.mask = mpc52xx_sdma_mask,
 	.unmask = mpc52xx_sdma_unmask,
 	.ack = mpc52xx_sdma_ack,
diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
index a682331ba0ff..9d962d7c72c1 100644
--- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
+++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
@@ -69,7 +69,6 @@ static void pq2ads_pci_unmask_irq(unsigned int virq)
 }
 
 static struct irq_chip pq2ads_pci_ic = {
-	.typename = "PQ2 ADS PCI",
 	.name = "PQ2 ADS PCI",
 	.end = pq2ads_pci_unmask_irq,
 	.mask = pq2ads_pci_mask_irq,
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index e59920aa6668..37a2e5f60af9 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -232,7 +232,7 @@ static int socrates_fpga_pic_set_type(unsigned int virq,
 }
 
 static struct irq_chip socrates_fpga_pic_chip = {
-	.typename       = " FPGA-PIC ",
+	.name		= " FPGA-PIC ",
 	.ack		= socrates_fpga_pic_ack,
 	.mask           = socrates_fpga_pic_mask,
 	.mask_ack       = socrates_fpga_pic_mask_ack,
diff --git a/arch/powerpc/platforms/86xx/gef_pic.c b/arch/powerpc/platforms/86xx/gef_pic.c
index 978d6cb37516..e1d5d36995df 100644
--- a/arch/powerpc/platforms/86xx/gef_pic.c
+++ b/arch/powerpc/platforms/86xx/gef_pic.c
@@ -149,7 +149,7 @@ static void gef_pic_unmask(unsigned int virq)
 }
 
 static struct irq_chip gef_pic_chip = {
-	.typename	= "gefp",
+	.name		= "gefp",
 	.mask		= gef_pic_mask,
 	.mask_ack	= gef_pic_mask_ack,
 	.unmask		= gef_pic_unmask,
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index a86c34b3bb84..96fe896f6df3 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -312,7 +312,7 @@ static struct irq_chip msic_irq_chip = {
 	.mask		= mask_msi_irq,
 	.unmask		= unmask_msi_irq,
 	.shutdown	= unmask_msi_irq,
-	.typename	= "AXON-MSI",
+	.name		= "AXON-MSI",
 };
 
 static int msic_host_map(struct irq_host *h, unsigned int virq,
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index 4a2bbff57698..c3479a47d45a 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -110,7 +110,7 @@ static void beatic_end_irq(unsigned int irq_plug)
 }
 
 static struct irq_chip beatic_pic = {
-	.typename = " CELL-BEAT ",
+	.name = " CELL-BEAT ",
 	.unmask = beatic_unmask_irq,
 	.mask = beatic_mask_irq,
 	.eoi = beatic_end_irq,
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 882e47080e74..3b67afba3f9b 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -88,7 +88,7 @@ static void iic_eoi(unsigned int irq)
 }
 
 static struct irq_chip iic_chip = {
-	.typename = " CELL-IIC ",
+	.name = " CELL-IIC ",
 	.mask = iic_mask,
 	.unmask = iic_unmask,
 	.eoi = iic_eoi,
@@ -133,7 +133,7 @@ static void iic_ioexc_cascade(unsigned int irq, struct irq_desc *desc)
 
 
 static struct irq_chip iic_ioexc_chip = {
-	.typename = " CELL-IOEX",
+	.name = " CELL-IOEX",
 	.mask = iic_mask,
 	.unmask = iic_unmask,
 	.eoi = iic_ioexc_eoi,
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 9dd63c5d11a8..167dedaada76 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -168,7 +168,7 @@ static int spider_set_irq_type(unsigned int virq, unsigned int type)
 }
 
 static struct irq_chip spider_pic = {
-	.typename = " SPIDER   ",
+	.name = " SPIDER   ",
 	.unmask = spider_unmask_irq,
 	.mask = spider_mask_irq,
 	.ack = spider_ack_irq,
diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c
index f8446ea31189..07762259c60a 100644
--- a/arch/powerpc/platforms/iseries/irq.c
+++ b/arch/powerpc/platforms/iseries/irq.c
@@ -273,7 +273,7 @@ static void iseries_end_IRQ(unsigned int irq)
 }
 
 static struct irq_chip iseries_pic = {
-	.typename	= "iSeries irq controller",
+	.name	= "iSeries irq controller",
 	.startup	= iseries_startup_IRQ,
 	.shutdown	= iseries_shutdown_IRQ,
 	.unmask		= iseries_enable_IRQ,
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 484d21e55c61..99d0b313e9a5 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -195,7 +195,7 @@ static int pmac_retrigger(unsigned int virq)
 }
 
 static struct irq_chip pmac_pic = {
-	.typename	= " PMAC-PIC ",
+	.name		= " PMAC-PIC ",
 	.startup	= pmac_startup_irq,
 	.mask		= pmac_mask_irq,
 	.ack		= pmac_ack_irq,
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 8ec5ccf76b19..59d9712d7364 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -152,7 +152,7 @@ static void ps3_chip_eoi(unsigned int virq)
  */
 
 static struct irq_chip ps3_irq_chip = {
-	.typename = "ps3",
+	.name = "ps3",
 	.mask = ps3_chip_mask,
 	.unmask = ps3_chip_unmask,
 	.eoi = ps3_chip_eoi,
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 097e8a2a3c5d..6592becd4410 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -388,7 +388,7 @@ static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
 }
 
 static struct irq_chip xics_pic_direct = {
-	.typename = " XICS     ",
+	.name = " XICS     ",
 	.startup = xics_startup,
 	.mask = xics_mask_irq,
 	.unmask = xics_unmask_irq,
@@ -397,7 +397,7 @@ static struct irq_chip xics_pic_direct = {
 };
 
 static struct irq_chip xics_pic_lpar = {
-	.typename = " XICS     ",
+	.name = " XICS     ",
 	.startup = xics_startup,
 	.mask = xics_mask_irq,
 	.unmask = xics_unmask_irq,
diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c
index 523537300ad5..a4b41dbde128 100644
--- a/arch/powerpc/sysdev/cpm1.c
+++ b/arch/powerpc/sysdev/cpm1.c
@@ -77,7 +77,7 @@ static void cpm_end_irq(unsigned int irq)
 }
 
 static struct irq_chip cpm_pic = {
-	.typename = " CPM PIC ",
+	.name = " CPM PIC ",
 	.mask = cpm_mask_irq,
 	.unmask = cpm_unmask_irq,
 	.eoi = cpm_end_irq,
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index 722cf72e190d..059ea4e5e25f 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -184,7 +184,7 @@ static int cpm2_set_irq_type(unsigned int virq, unsigned int flow_type)
 }
 
 static struct irq_chip cpm2_pic = {
-	.typename = " CPM2 SIU ",
+	.name = " CPM2 SIU ",
 	.mask = cpm2_mask_irq,
 	.unmask = cpm2_unmask_irq,
 	.ack = cpm2_ack,
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 7174374f90ff..62e50258cdef 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -47,7 +47,7 @@ static struct irq_chip fsl_msi_chip = {
 	.mask		= mask_msi_irq,
 	.unmask		= unmask_msi_irq,
 	.ack		= fsl_msi_end_irq,
-	.typename	= " FSL-MSI  ",
+	.name	= " FSL-MSI  ",
 };
 
 static int fsl_msi_host_map(struct irq_host *h, unsigned int virq,
diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
index 78ed945453db..ba8f1f708992 100644
--- a/arch/powerpc/sysdev/i8259.c
+++ b/arch/powerpc/sysdev/i8259.c
@@ -135,7 +135,7 @@ static void i8259_unmask_irq(unsigned int irq_nr)
 }
 
 static struct irq_chip i8259_pic = {
-	.typename	= " i8259    ",
+	.name		= " i8259    ",
 	.mask		= i8259_mask_irq,
 	.disable	= i8259_mask_irq,
 	.unmask		= i8259_unmask_irq,
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index f042c1d69002..c89d78075ba0 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -660,7 +660,7 @@ static int ipic_set_irq_type(unsigned int virq, unsigned int flow_type)
 
 /* level interrupts and edge interrupts have different ack operations */
 static struct irq_chip ipic_level_irq_chip = {
-	.typename	= " IPIC  ",
+	.name		= " IPIC  ",
 	.unmask		= ipic_unmask_irq,
 	.mask		= ipic_mask_irq,
 	.mask_ack	= ipic_mask_irq,
@@ -668,7 +668,7 @@ static struct irq_chip ipic_level_irq_chip = {
 };
 
 static struct irq_chip ipic_edge_irq_chip = {
-	.typename	= " IPIC  ",
+	.name		= " IPIC  ",
 	.unmask		= ipic_unmask_irq,
 	.mask		= ipic_mask_irq,
 	.mask_ack	= ipic_mask_irq_and_ack,
diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c
index 01179587df2a..db0a712f6075 100644
--- a/arch/powerpc/sysdev/mpc8xx_pic.c
+++ b/arch/powerpc/sysdev/mpc8xx_pic.c
@@ -94,7 +94,7 @@ static int mpc8xx_set_irq_type(unsigned int virq, unsigned int flow_type)
 }
 
 static struct irq_chip mpc8xx_pic = {
-	.typename = " MPC8XX SIU ",
+	.name = " MPC8XX SIU ",
 	.unmask = mpc8xx_unmask_irq,
 	.mask = mpc8xx_mask_irq,
 	.ack = mpc8xx_ack,
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 4fd57ab956bf..7a64bc5808da 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1062,19 +1062,19 @@ struct mpic * __init mpic_alloc(struct device_node *node,
 	mpic->name = name;
 
 	mpic->hc_irq = mpic_irq_chip;
-	mpic->hc_irq.typename = name;
+	mpic->hc_irq.name = name;
 	if (flags & MPIC_PRIMARY)
 		mpic->hc_irq.set_affinity = mpic_set_affinity;
 #ifdef CONFIG_MPIC_U3_HT_IRQS
 	mpic->hc_ht_irq = mpic_irq_ht_chip;
-	mpic->hc_ht_irq.typename = name;
+	mpic->hc_ht_irq.name = name;
 	if (flags & MPIC_PRIMARY)
 		mpic->hc_ht_irq.set_affinity = mpic_set_affinity;
 #endif /* CONFIG_MPIC_U3_HT_IRQS */
 
 #ifdef CONFIG_SMP
 	mpic->hc_ipi = mpic_ipi_chip;
-	mpic->hc_ipi.typename = name;
+	mpic->hc_ipi.name = name;
 #endif /* CONFIG_SMP */
 
 	mpic->flags = flags;
diff --git a/arch/powerpc/sysdev/mpic_pasemi_msi.c b/arch/powerpc/sysdev/mpic_pasemi_msi.c
index 656cb772b691..0f6ab06f8474 100644
--- a/arch/powerpc/sysdev/mpic_pasemi_msi.c
+++ b/arch/powerpc/sysdev/mpic_pasemi_msi.c
@@ -60,7 +60,7 @@ static struct irq_chip mpic_pasemi_msi_chip = {
 	.eoi		= mpic_end_irq,
 	.set_type	= mpic_set_irq_type,
 	.set_affinity	= mpic_set_affinity,
-	.typename	= "PASEMI-MSI ",
+	.name		= "PASEMI-MSI ",
 };
 
 static int pasemi_msi_check_device(struct pci_dev *pdev, int nvec, int type)
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index 0a8f5a9e87c9..d3caf23e6312 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -42,7 +42,7 @@ static struct irq_chip mpic_u3msi_chip = {
 	.eoi		= mpic_end_irq,
 	.set_type	= mpic_set_irq_type,
 	.set_affinity	= mpic_set_affinity,
-	.typename	= "MPIC-U3MSI",
+	.name		= "MPIC-U3MSI",
 };
 
 static u64 read_ht_magic_addr(struct pci_dev *pdev, unsigned int pos)
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index fc098744ad82..c1e17b3d3982 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -237,7 +237,7 @@ static void qe_ic_mask_irq(unsigned int virq)
 }
 
 static struct irq_chip qe_ic_irq_chip = {
-	.typename = " QEIC  ",
+	.name = " QEIC  ",
 	.unmask = qe_ic_unmask_irq,
 	.mask = qe_ic_mask_irq,
 	.mask_ack = qe_ic_mask_irq,
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index 02f600991dce..47769d2359d6 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -376,7 +376,7 @@ static void tsi108_pci_irq_end(u_int irq)
  */
 
 static struct irq_chip tsi108_pci_irq = {
-	.typename = "tsi108_PCI_int",
+	.name = "tsi108_PCI_int",
 	.mask = tsi108_pci_irq_disable,
 	.ack = tsi108_pci_irq_ack,
 	.end = tsi108_pci_irq_end,
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index cf97935863c8..c907601e44db 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -177,7 +177,7 @@ static int uic_set_irq_type(unsigned int virq, unsigned int flow_type)
 }
 
 static struct irq_chip uic_irq_chip = {
-	.typename	= " UIC  ",
+	.name		= " UIC  ",
 	.unmask		= uic_unmask_irq,
 	.mask		= uic_mask_irq,
  	.mask_ack	= uic_mask_ack_irq,
diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c
index ab743718876b..45eb225ec25e 100644
--- a/arch/powerpc/sysdev/xilinx_intc.c
+++ b/arch/powerpc/sysdev/xilinx_intc.c
@@ -106,7 +106,7 @@ static void xilinx_intc_level_unmask(unsigned int virq)
 }
 
 static struct irq_chip xilinx_intc_level_irqchip = {
-	.typename = "Xilinx Level INTC",
+	.name = "Xilinx Level INTC",
 	.mask = xilinx_intc_mask,
 	.mask_ack = xilinx_intc_mask,
 	.unmask = xilinx_intc_level_unmask,
@@ -133,7 +133,7 @@ static void xilinx_intc_edge_ack(unsigned int virq)
 }
 
 static struct irq_chip xilinx_intc_edge_irqchip = {
-	.typename = "Xilinx Edge  INTC",
+	.name = "Xilinx Edge  INTC",
 	.mask = xilinx_intc_mask,
 	.unmask = xilinx_intc_edge_unmask,
 	.ack = xilinx_intc_edge_ack,

From d95cacc599a79d87052b3975f60cae62c04dc01f Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Tue, 20 Oct 2009 20:06:21 +0000
Subject: [PATCH 102/151] powerpc: Move ehea hcall definitions into hvcall.h

Move ehea hcall definitions into hvcall.h.

Signed-off-by: Anton Blanchard <anton@samba.org>
Acked-by: Thomas Klein <tklein@de.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/hvcall.h | 13 ++++++++
 drivers/net/ehea/ehea_hcall.h     | 51 -------------------------------
 drivers/net/ehea/ehea_phyp.h      |  1 -
 3 files changed, 13 insertions(+), 52 deletions(-)
 delete mode 100644 drivers/net/ehea/ehea_hcall.h

diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 6251a4b10be7..3bf38af7c834 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -212,6 +212,19 @@
 #define H_QUERY_INT_STATE       0x1E4
 #define H_POLL_PENDING		0x1D8
 #define H_ILLAN_ATTRIBUTES	0x244
+#define H_MODIFY_HEA_QP		0x250
+#define H_QUERY_HEA_QP		0x254
+#define H_QUERY_HEA		0x258
+#define H_QUERY_HEA_PORT	0x25C
+#define H_MODIFY_HEA_PORT	0x260
+#define H_REG_BCMC		0x264
+#define H_DEREG_BCMC		0x268
+#define H_REGISTER_HEA_RPAGES	0x26C
+#define H_DISABLE_AND_GET_HEA	0x270
+#define H_GET_HEA_INFO		0x274
+#define H_ALLOC_HEA_RESOURCE	0x278
+#define H_ADD_CONN		0x284
+#define H_DEL_CONN		0x288
 #define H_JOIN			0x298
 #define H_VASI_STATE            0x2A4
 #define H_ENABLE_CRQ		0x2B0
diff --git a/drivers/net/ehea/ehea_hcall.h b/drivers/net/ehea/ehea_hcall.h
deleted file mode 100644
index 8e7d1c3edc60..000000000000
--- a/drivers/net/ehea/ehea_hcall.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/*
- *  linux/drivers/net/ehea/ehea_hcall.h
- *
- *  eHEA ethernet device driver for IBM eServer System p
- *
- *  (C) Copyright IBM Corp. 2006
- *
- *  Authors:
- *       Christoph Raisch <raisch@de.ibm.com>
- *       Jan-Bernd Themann <themann@de.ibm.com>
- *       Thomas Klein <tklein@de.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, 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., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#ifndef __EHEA_HCALL_H__
-#define __EHEA_HCALL_H__
-
-/**
- * This file contains HCALL defines that are to be included in the appropriate
- * kernel files later
- */
-
-#define H_ALLOC_HEA_RESOURCE   0x278
-#define H_MODIFY_HEA_QP        0x250
-#define H_QUERY_HEA_QP         0x254
-#define H_QUERY_HEA            0x258
-#define H_QUERY_HEA_PORT       0x25C
-#define H_MODIFY_HEA_PORT      0x260
-#define H_REG_BCMC             0x264
-#define H_DEREG_BCMC           0x268
-#define H_REGISTER_HEA_RPAGES  0x26C
-#define H_DISABLE_AND_GET_HEA  0x270
-#define H_GET_HEA_INFO         0x274
-#define H_ADD_CONN             0x284
-#define H_DEL_CONN             0x288
-
-#endif	/* __EHEA_HCALL_H__ */
diff --git a/drivers/net/ehea/ehea_phyp.h b/drivers/net/ehea/ehea_phyp.h
index f3628c803567..2f8174c248bc 100644
--- a/drivers/net/ehea/ehea_phyp.h
+++ b/drivers/net/ehea/ehea_phyp.h
@@ -33,7 +33,6 @@
 #include <asm/hvcall.h>
 #include "ehea.h"
 #include "ehea_hw.h"
-#include "ehea_hcall.h"
 
 /* Some abbreviations used here:
  *

From 69ddb57cbea0b3dd851ea5f1edd1e609ad4da04e Mon Sep 17 00:00:00 2001
From: Gautham R Shenoy <ego@in.ibm.com>
Date: Thu, 29 Oct 2009 19:22:48 +0000
Subject: [PATCH 103/151] powerpc/pseries: Add extended_cede_processor() helper
 function.

This patch provides an extended_cede_processor() helper function
which takes the cede latency hint as an argument. This hint is to be passed
on to the hypervisor to cede to the corresponding state on platforms
which support it.

Signed-off-by: Gautham R Shenoy <ego@in.ibm.com>
Signed-off-by: Arun R Bharadwaj <arun@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/lppaca.h             |  9 +++++++-
 .../platforms/pseries/plpar_wrappers.h        | 22 +++++++++++++++++++
 arch/powerpc/xmon/xmon.c                      |  3 ++-
 3 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index f78f65c38f05..14b592dfb4e8 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -100,7 +100,14 @@ struct lppaca {
 	// Used to pass parms from the OS to PLIC for SetAsrAndRfid
 	u64	saved_gpr3;		// Saved GPR3                   x20-x27
 	u64	saved_gpr4;		// Saved GPR4                   x28-x2F
-	u64	saved_gpr5;		// Saved GPR5                   x30-x37
+	union {
+		u64	saved_gpr5;	/* Saved GPR5               x30-x37 */
+		struct {
+			u8	cede_latency_hint;  /*			x30 */
+			u8	reserved[7];        /*		    x31-x36 */
+		} fields;
+	} gpr5_dword;
+
 
 	u8	dtl_enable_mask;	// Dispatch Trace Log mask	x38-x38
 	u8	donate_dedicated_cpu;	// Donate dedicated CPU cycles  x39-x39
diff --git a/arch/powerpc/platforms/pseries/plpar_wrappers.h b/arch/powerpc/platforms/pseries/plpar_wrappers.h
index a24a6b2333b2..0603c91538ae 100644
--- a/arch/powerpc/platforms/pseries/plpar_wrappers.h
+++ b/arch/powerpc/platforms/pseries/plpar_wrappers.h
@@ -9,11 +9,33 @@ static inline long poll_pending(void)
 	return plpar_hcall_norets(H_POLL_PENDING);
 }
 
+static inline u8 get_cede_latency_hint(void)
+{
+	return get_lppaca()->gpr5_dword.fields.cede_latency_hint;
+}
+
+static inline void set_cede_latency_hint(u8 latency_hint)
+{
+	get_lppaca()->gpr5_dword.fields.cede_latency_hint = latency_hint;
+}
+
 static inline long cede_processor(void)
 {
 	return plpar_hcall_norets(H_CEDE);
 }
 
+static inline long extended_cede_processor(unsigned long latency_hint)
+{
+	long rc;
+	u8 old_latency_hint = get_cede_latency_hint();
+
+	set_cede_latency_hint(latency_hint);
+	rc = cede_processor();
+	set_cede_latency_hint(old_latency_hint);
+
+	return rc;
+}
+
 static inline long vpa_call(unsigned long flags, unsigned long cpu,
 		unsigned long vpa)
 {
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index bdbe96c8a7e4..4e6152c13764 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -1641,7 +1641,8 @@ static void super_regs(void)
 			       ptrLpPaca->saved_srr0, ptrLpPaca->saved_srr1);
 			printf("    Saved Gpr3=%.16lx  Saved Gpr4=%.16lx \n",
 			       ptrLpPaca->saved_gpr3, ptrLpPaca->saved_gpr4);
-			printf("    Saved Gpr5=%.16lx \n", ptrLpPaca->saved_gpr5);
+			printf("    Saved Gpr5=%.16lx \n",
+				ptrLpPaca->gpr5_dword.saved_gpr5);
 		}
 #endif
 

From 3aa565f53c396914a9406388efaa238e9c937fc6 Mon Sep 17 00:00:00 2001
From: Gautham R Shenoy <ego@in.ibm.com>
Date: Thu, 29 Oct 2009 19:22:53 +0000
Subject: [PATCH 104/151] powerpc/pseries: Add hooks to put the CPU into an
 appropriate offline state

When a CPU is offlined on POWER currently, we call rtas_stop_self() and hand
the CPU back to the resource pool. This path is used for DLPAR which will
cause a change in the LPAR configuration which will be visible outside.

This patch changes the default state a CPU is put into when it is offlined.
On platforms which support ceding the processor to the hypervisor with
latency hint specifier value, during a cpu offline operation,
instead of calling rtas_stop_self(), we cede the vCPU to the hypervisor
while passing a latency hint specifier value. The Hypervisor can use this hint
to provide better energy savings. Also, during the offline
operation, the control of the vCPU remains with the LPAR as oppposed to
returning it to the resource pool.

The patch achieves this by creating an infrastructure to set the
preferred_offline_state() which can be either
- CPU_STATE_OFFLINE: which is the current behaviour of calling
  rtas_stop_self()

- CPU_STATE_INACTIVE: which cedes the vCPU to the hypervisor with the latency
  hint specifier.

The codepath which wants to perform a DLPAR operation can set the
preferred_offline_state() of a CPU to CPU_STATE_OFFLINE before invoking
cpu_down().

The patch also provides a boot-time command line argument to disable/enable
CPU_STATE_INACTIVE.

Signed-off-by: Gautham R Shenoy <ego@in.ibm.com>
Signed-off-by: Nathan Fontenot <nfont@austin.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 Documentation/cpu-hotplug.txt                 |   6 +
 arch/powerpc/platforms/pseries/hotplug-cpu.c  | 182 +++++++++++++++++-
 .../platforms/pseries/offline_states.h        |  18 ++
 arch/powerpc/platforms/pseries/smp.c          |  19 ++
 4 files changed, 216 insertions(+), 9 deletions(-)
 create mode 100644 arch/powerpc/platforms/pseries/offline_states.h

diff --git a/Documentation/cpu-hotplug.txt b/Documentation/cpu-hotplug.txt
index 9d620c153b04..4d4a644b505e 100644
--- a/Documentation/cpu-hotplug.txt
+++ b/Documentation/cpu-hotplug.txt
@@ -49,6 +49,12 @@ maxcpus=n    Restrict boot time cpus to n. Say if you have 4 cpus, using
 additional_cpus=n (*)	Use this to limit hotpluggable cpus. This option sets
   			cpu_possible_map = cpu_present_map + additional_cpus
 
+cede_offline={"off","on"}  Use this option to disable/enable putting offlined
+		            processors to an extended H_CEDE state on
+			    supported pseries platforms.
+			    If nothing is specified,
+			    cede_offline is set to "on".
+
 (*) Option valid only for following architectures
 - ia64
 
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index ebff6d9a4e39..6ea4698d9176 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -30,6 +30,7 @@
 #include <asm/pSeries_reconfig.h>
 #include "xics.h"
 #include "plpar_wrappers.h"
+#include "offline_states.h"
 
 /* This version can't take the spinlock, because it never returns */
 static struct rtas_args rtas_stop_self_args = {
@@ -39,6 +40,55 @@ static struct rtas_args rtas_stop_self_args = {
 	.rets = &rtas_stop_self_args.args[0],
 };
 
+static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) =
+							CPU_STATE_OFFLINE;
+static DEFINE_PER_CPU(enum cpu_state_vals, current_state) = CPU_STATE_OFFLINE;
+
+static enum cpu_state_vals default_offline_state = CPU_STATE_OFFLINE;
+
+static int cede_offline_enabled __read_mostly = 1;
+
+/*
+ * Enable/disable cede_offline when available.
+ */
+static int __init setup_cede_offline(char *str)
+{
+	if (!strcmp(str, "off"))
+		cede_offline_enabled = 0;
+	else if (!strcmp(str, "on"))
+		cede_offline_enabled = 1;
+	else
+		return 0;
+	return 1;
+}
+
+__setup("cede_offline=", setup_cede_offline);
+
+enum cpu_state_vals get_cpu_current_state(int cpu)
+{
+	return per_cpu(current_state, cpu);
+}
+
+void set_cpu_current_state(int cpu, enum cpu_state_vals state)
+{
+	per_cpu(current_state, cpu) = state;
+}
+
+enum cpu_state_vals get_preferred_offline_state(int cpu)
+{
+	return per_cpu(preferred_offline_state, cpu);
+}
+
+void set_preferred_offline_state(int cpu, enum cpu_state_vals state)
+{
+	per_cpu(preferred_offline_state, cpu) = state;
+}
+
+void set_default_offline_state(int cpu)
+{
+	per_cpu(preferred_offline_state, cpu) = default_offline_state;
+}
+
 static void rtas_stop_self(void)
 {
 	struct rtas_args *args = &rtas_stop_self_args;
@@ -56,11 +106,61 @@ static void rtas_stop_self(void)
 
 static void pseries_mach_cpu_die(void)
 {
+	unsigned int cpu = smp_processor_id();
+	unsigned int hwcpu = hard_smp_processor_id();
+	u8 cede_latency_hint = 0;
+
 	local_irq_disable();
 	idle_task_exit();
 	xics_teardown_cpu();
-	unregister_slb_shadow(hard_smp_processor_id(), __pa(get_slb_shadow()));
-	rtas_stop_self();
+
+	if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
+		set_cpu_current_state(cpu, CPU_STATE_INACTIVE);
+		cede_latency_hint = 2;
+
+		get_lppaca()->idle = 1;
+		if (!get_lppaca()->shared_proc)
+			get_lppaca()->donate_dedicated_cpu = 1;
+
+		printk(KERN_INFO
+			"cpu %u (hwid %u) ceding for offline with hint %d\n",
+			cpu, hwcpu, cede_latency_hint);
+		while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
+			extended_cede_processor(cede_latency_hint);
+			printk(KERN_INFO "cpu %u (hwid %u) returned from cede.\n",
+				cpu, hwcpu);
+			printk(KERN_INFO
+			"Decrementer value = %x Timebase value = %llx\n",
+			get_dec(), get_tb());
+		}
+
+		printk(KERN_INFO "cpu %u (hwid %u) got prodded to go online\n",
+			cpu, hwcpu);
+
+		if (!get_lppaca()->shared_proc)
+			get_lppaca()->donate_dedicated_cpu = 0;
+		get_lppaca()->idle = 0;
+	}
+
+	if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) {
+		unregister_slb_shadow(hwcpu, __pa(get_slb_shadow()));
+
+		/*
+		 * NOTE: Calling start_secondary() here for now to
+		 * start new context.
+		 * However, need to do it cleanly by resetting the
+		 * stack pointer.
+		 */
+		start_secondary();
+
+	} else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) {
+
+		set_cpu_current_state(cpu, CPU_STATE_OFFLINE);
+		unregister_slb_shadow(hard_smp_processor_id(),
+					__pa(get_slb_shadow()));
+		rtas_stop_self();
+	}
+
 	/* Should never get here... */
 	BUG();
 	for(;;);
@@ -106,18 +206,43 @@ static int pseries_cpu_disable(void)
 	return 0;
 }
 
+/*
+ * pseries_cpu_die: Wait for the cpu to die.
+ * @cpu: logical processor id of the CPU whose death we're awaiting.
+ *
+ * This function is called from the context of the thread which is performing
+ * the cpu-offline. Here we wait for long enough to allow the cpu in question
+ * to self-destroy so that the cpu-offline thread can send the CPU_DEAD
+ * notifications.
+ *
+ * OTOH, pseries_mach_cpu_die() is called by the @cpu when it wants to
+ * self-destruct.
+ */
 static void pseries_cpu_die(unsigned int cpu)
 {
 	int tries;
-	int cpu_status;
+	int cpu_status = 1;
 	unsigned int pcpu = get_hard_smp_processor_id(cpu);
 
-	for (tries = 0; tries < 25; tries++) {
-		cpu_status = query_cpu_stopped(pcpu);
-		if (cpu_status == 0 || cpu_status == -1)
-			break;
-		cpu_relax();
+	if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) {
+		cpu_status = 1;
+		for (tries = 0; tries < 1000; tries++) {
+			if (get_cpu_current_state(cpu) == CPU_STATE_INACTIVE) {
+				cpu_status = 0;
+				break;
+			}
+			cpu_relax();
+		}
+	} else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) {
+
+		for (tries = 0; tries < 25; tries++) {
+			cpu_status = query_cpu_stopped(pcpu);
+			if (cpu_status == 0 || cpu_status == -1)
+				break;
+			cpu_relax();
+		}
 	}
+
 	if (cpu_status != 0) {
 		printk("Querying DEAD? cpu %i (%i) shows %i\n",
 		       cpu, pcpu, cpu_status);
@@ -252,10 +377,41 @@ static struct notifier_block pseries_smp_nb = {
 	.notifier_call = pseries_smp_notifier,
 };
 
+#define MAX_CEDE_LATENCY_LEVELS		4
+#define	CEDE_LATENCY_PARAM_LENGTH	10
+#define CEDE_LATENCY_PARAM_MAX_LENGTH	\
+	(MAX_CEDE_LATENCY_LEVELS * CEDE_LATENCY_PARAM_LENGTH * sizeof(char))
+#define CEDE_LATENCY_TOKEN		45
+
+static char cede_parameters[CEDE_LATENCY_PARAM_MAX_LENGTH];
+
+static int parse_cede_parameters(void)
+{
+	int call_status;
+
+	memset(cede_parameters, 0, CEDE_LATENCY_PARAM_MAX_LENGTH);
+	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+				NULL,
+				CEDE_LATENCY_TOKEN,
+				__pa(cede_parameters),
+				CEDE_LATENCY_PARAM_MAX_LENGTH);
+
+	if (call_status != 0)
+		printk(KERN_INFO "CEDE_LATENCY: \
+			%s %s Error calling get-system-parameter(0x%x)\n",
+			__FILE__, __func__, call_status);
+	else
+		printk(KERN_INFO "CEDE_LATENCY: \
+			get-system-parameter successful.\n");
+
+	return call_status;
+}
+
 static int __init pseries_cpu_hotplug_init(void)
 {
 	struct device_node *np;
 	const char *typep;
+	int cpu;
 
 	for_each_node_by_name(np, "interrupt-controller") {
 		typep = of_get_property(np, "compatible", NULL);
@@ -283,8 +439,16 @@ static int __init pseries_cpu_hotplug_init(void)
 	smp_ops->cpu_die = pseries_cpu_die;
 
 	/* Processors can be added/removed only on LPAR */
-	if (firmware_has_feature(FW_FEATURE_LPAR))
+	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		pSeries_reconfig_notifier_register(&pseries_smp_nb);
+		cpu_maps_update_begin();
+		if (cede_offline_enabled && parse_cede_parameters() == 0) {
+			default_offline_state = CPU_STATE_INACTIVE;
+			for_each_online_cpu(cpu)
+				set_default_offline_state(cpu);
+		}
+		cpu_maps_update_done();
+	}
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/pseries/offline_states.h b/arch/powerpc/platforms/pseries/offline_states.h
new file mode 100644
index 000000000000..22574e0d9d91
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/offline_states.h
@@ -0,0 +1,18 @@
+#ifndef _OFFLINE_STATES_H_
+#define _OFFLINE_STATES_H_
+
+/* Cpu offline states go here */
+enum cpu_state_vals {
+	CPU_STATE_OFFLINE,
+	CPU_STATE_INACTIVE,
+	CPU_STATE_ONLINE,
+	CPU_MAX_OFFLINE_STATES
+};
+
+extern enum cpu_state_vals get_cpu_current_state(int cpu);
+extern void set_cpu_current_state(int cpu, enum cpu_state_vals state);
+extern enum cpu_state_vals get_preferred_offline_state(int cpu);
+extern void set_preferred_offline_state(int cpu, enum cpu_state_vals state);
+extern void set_default_offline_state(int cpu);
+extern int start_secondary(void);
+#endif
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 440000cc7130..8868c012268a 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -48,6 +48,7 @@
 #include "plpar_wrappers.h"
 #include "pseries.h"
 #include "xics.h"
+#include "offline_states.h"
 
 
 /*
@@ -84,6 +85,9 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu)
 	/* Fixup atomic count: it exited inside IRQ handler. */
 	task_thread_info(paca[lcpu].__current)->preempt_count	= 0;
 
+	if (get_cpu_current_state(lcpu) == CPU_STATE_INACTIVE)
+		goto out;
+
 	/* 
 	 * If the RTAS start-cpu token does not exist then presume the
 	 * cpu is already spinning.
@@ -98,6 +102,7 @@ static inline int __devinit smp_startup_cpu(unsigned int lcpu)
 		return 0;
 	}
 
+out:
 	return 1;
 }
 
@@ -111,12 +116,16 @@ static void __devinit smp_xics_setup_cpu(int cpu)
 		vpa_init(cpu);
 
 	cpu_clear(cpu, of_spin_map);
+	set_cpu_current_state(cpu, CPU_STATE_ONLINE);
+	set_default_offline_state(cpu);
 
 }
 #endif /* CONFIG_XICS */
 
 static void __devinit smp_pSeries_kick_cpu(int nr)
 {
+	long rc;
+	unsigned long hcpuid;
 	BUG_ON(nr < 0 || nr >= NR_CPUS);
 
 	if (!smp_startup_cpu(nr))
@@ -128,6 +137,16 @@ static void __devinit smp_pSeries_kick_cpu(int nr)
 	 * the processor will continue on to secondary_start
 	 */
 	paca[nr].cpu_start = 1;
+
+	set_preferred_offline_state(nr, CPU_STATE_ONLINE);
+
+	if (get_cpu_current_state(nr) == CPU_STATE_INACTIVE) {
+		hcpuid = get_hard_smp_processor_id(nr);
+		rc = plpar_hcall_norets(H_PROD, hcpuid);
+		if (rc != H_SUCCESS)
+			panic("Error: Prod to wake up processor %d Ret= %ld\n",
+				nr, rc);
+	}
 }
 
 static int smp_pSeries_cpu_bootable(unsigned int nr)

From a0592d42fe3e12966db02f5c41f1edae2e59c490 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 10 Nov 2009 15:13:15 +0000
Subject: [PATCH 105/151] powerpc: kill the obsolete code under
 is_global_init()

The code under "if (is_global_init())" is bogus, and is_global_init()
itself is not right in mt case.

Contrary to what the comment says, nowadays force_sig_info() does kill
init even if the handler is SIG_DFL. Note that force_sig_info() clears
SIGNAL_UNKILLABLE exactly for this case.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/traps.c | 22 ----------------------
 1 file changed, 22 deletions(-)

diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 6f0ae1a9bfae..a81c7438d341 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -198,28 +198,6 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
 	info.si_code = code;
 	info.si_addr = (void __user *) addr;
 	force_sig_info(signr, &info, current);
-
-	/*
-	 * Init gets no signals that it doesn't have a handler for.
-	 * That's all very well, but if it has caused a synchronous
-	 * exception and we ignore the resulting signal, it will just
-	 * generate the same exception over and over again and we get
-	 * nowhere.  Better to kill it and let the kernel panic.
-	 */
-	if (is_global_init(current)) {
-		__sighandler_t handler;
-
-		spin_lock_irq(&current->sighand->siglock);
-		handler = current->sighand->action[signr-1].sa.sa_handler;
-		spin_unlock_irq(&current->sighand->siglock);
-		if (handler == SIG_DFL) {
-			/* init has generated a synchronous exception
-			   and it doesn't have a handler for the signal */
-			printk(KERN_CRIT "init has generated signal %d "
-			       "but has no handler for it\n", signr);
-			do_exit(signr);
-		}
-	}
 }
 
 #ifdef CONFIG_PPC64

From c38c2044b2b49820a09ac904bdb6f03cdda6e885 Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Thu, 12 Nov 2009 18:54:13 +1100
Subject: [PATCH 106/151] powerpc: do not export pci_alloc/free_consistent

Since they are static inline functions.

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/ppc_ksyms.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 07115d6cd4ba..425451453e96 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -96,8 +96,6 @@ EXPORT_SYMBOL(copy_4K_page);
 EXPORT_SYMBOL(isa_io_base);
 EXPORT_SYMBOL(isa_mem_base);
 EXPORT_SYMBOL(pci_dram_offset);
-EXPORT_SYMBOL(pci_alloc_consistent);
-EXPORT_SYMBOL(pci_free_consistent);
 #endif /* CONFIG_PCI */
 
 EXPORT_SYMBOL(start_thread);

From 7c31629fd60037c5eb2b8fd0e6def9fe097fa28e Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Date: Sat, 14 Nov 2009 03:31:43 +0000
Subject: [PATCH 107/151] powerpc: Kill unused swiotlb variable

We can kill unused swiotlb variable.

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/dma-swiotlb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index e96cbbd9b449..59c928564a03 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -21,7 +21,6 @@
 #include <asm/dma.h>
 #include <asm/abs_addr.h>
 
-int swiotlb __read_mostly;
 unsigned int ppc_swiotlb_enable;
 
 /*

From 2d7cf3ef879b22bdfd271aa3b66733c53279e813 Mon Sep 17 00:00:00 2001
From: Becky Bruce <beckyb@kernel.crashing.org>
Date: Mon, 23 Nov 2009 12:28:53 +0000
Subject: [PATCH 108/151] powerpc: Fix DEBUG_HIGHMEM build break from
 d4515646699

Code was added to mm/higmem.c that depends on several
kmap types that powerpc does not support.  We add dummy
invalid definitions for KM_NMI, KM_NM_PTE, and KM_IRQ_PTE.

According to list discussion, this fix should not be needed
anymore starting with 2.6.33.  The code is commented to this
effect so hopefully we will remember to remove this.

Signed-off-by: Becky Bruce <beckyb@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/kmap_types.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h
index b6bac6f61c16..916369575c97 100644
--- a/arch/powerpc/include/asm/kmap_types.h
+++ b/arch/powerpc/include/asm/kmap_types.h
@@ -29,5 +29,16 @@ enum km_type {
 	KM_TYPE_NR
 };
 
+/*
+ * This is a temporary build fix that (so they say on lkml....) should no longer
+ * be required after 2.6.33, because of changes planned to the kmap code.
+ * Let's try to remove this cruft then.
+ */
+#ifdef CONFIG_DEBUG_HIGHMEM
+#define KM_NMI		(-1)
+#define KM_NMI_PTE	(-1)
+#define KM_IRQ_PTE	(-1)
+#endif
+
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_KMAP_TYPES_H */

From dad2f2fb0fc74afb634beba8c57bb34bb862d4c6 Mon Sep 17 00:00:00 2001
From: "arnd@arndb.de" <arnd@arndb.de>
Date: Mon, 23 Nov 2009 03:25:06 +0000
Subject: [PATCH 109/151] powerpc: Fix wrong error code from ppc32 select
 syscall

This patch was submitted, discussed, and eventually Acked by everyone, yet
still isn't in the tree.  See:

http://patchwork.ozlabs.org/patch/1240/

Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
Cc: Arnd Bergmann <arnd@anrdb.de>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/systbl.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index c7d671a7d9a1..07d2d19ab5e9 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -145,7 +145,7 @@ SYSCALL_SPU(setfsuid)
 SYSCALL_SPU(setfsgid)
 SYSCALL_SPU(llseek)
 COMPAT_SYS_SPU(getdents)
-SYSX_SPU(sys_select,ppc32_select,ppc_select)
+SYSX_SPU(sys_select,ppc32_select,sys_select)
 SYSCALL_SPU(flock)
 SYSCALL_SPU(msync)
 COMPAT_SYS_SPU(readv)

From 7d6709a20866a885916214590b7c394a21be9e25 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 24 Nov 2009 16:06:48 +1100
Subject: [PATCH 110/151] powerpc: Fix build of some FSL platforms

Commit 87ec0e98cfdd8b68da6a7f9e70142ffc0e404fbb in kumar's next branch
broke one of my test configs since it looks like Anton forgot about
that mpc832x_rdb platform which still uses the old style probing for
the SPI stuff.

I'll let them do a cleaner fix that probably involves changing the
probing method and getting rid of the platform device but for now
this will do to fix it.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/83xx/mpc832x_rdb.c | 2 +-
 drivers/spi/spi_mpc8xxx.c                 | 5 -----
 include/linux/fsl_devices.h               | 5 +++++
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/platforms/83xx/mpc832x_rdb.c b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
index 567ded7c3b9b..17f99745f0e4 100644
--- a/arch/powerpc/platforms/83xx/mpc832x_rdb.c
+++ b/arch/powerpc/platforms/83xx/mpc832x_rdb.c
@@ -74,7 +74,7 @@ static int __init of_fsl_spi_probe(char *type, char *compatible, u32 sysclk,
 
 		prop = of_get_property(np, "mode", NULL);
 		if (prop && !strcmp(prop, "cpu-qe"))
-			pdata.qe_mode = 1;
+			pdata.flags = SPI_QE_CPU_MODE;
 
 		for (j = 0; j < num_board_infos; j++) {
 			if (board_infos[j].bus_num == pdata.bus_num)
diff --git a/drivers/spi/spi_mpc8xxx.c b/drivers/spi/spi_mpc8xxx.c
index 394b6581e17f..930135dc73ba 100644
--- a/drivers/spi/spi_mpc8xxx.c
+++ b/drivers/spi/spi_mpc8xxx.c
@@ -163,11 +163,6 @@ struct mpc8xxx_spi {
 	u32 tx_shift;		/* TX data reg shift when in qe mode */
 
 	unsigned int flags;
-#define SPI_QE_CPU_MODE		(1 << 0) /* QE CPU ("PIO") mode */
-#define SPI_CPM_MODE		(1 << 1) /* CPM/QE ("DMA") mode */
-#define SPI_CPM1		(1 << 2) /* SPI unit is in CPM1 block */
-#define SPI_CPM2		(1 << 3) /* SPI unit is in CPM2 block */
-#define SPI_QE			(1 << 4) /* SPI unit is in QE block */
 
 	struct workqueue_struct *workqueue;
 	struct work_struct work;
diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h
index 47188d512b8f..28e33fea5107 100644
--- a/include/linux/fsl_devices.h
+++ b/include/linux/fsl_devices.h
@@ -75,6 +75,11 @@ struct fsl_spi_platform_data {
 	u32 	initial_spmode;	/* initial SPMODE value */
 	s16	bus_num;
 	unsigned int flags;
+#define SPI_QE_CPU_MODE		(1 << 0) /* QE CPU ("PIO") mode */
+#define SPI_CPM_MODE		(1 << 1) /* CPM/QE ("DMA") mode */
+#define SPI_CPM1		(1 << 2) /* SPI unit is in CPM1 block */
+#define SPI_CPM2		(1 << 3) /* SPI unit is in CPM2 block */
+#define SPI_QE			(1 << 4) /* SPI unit is in QE block */
 	/* board specific information */
 	u16	max_chipselect;
 	void	(*cs_control)(struct spi_device *spi, bool on);

From c045256d146800ea1d741a8e9e377dada6b7e195 Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Mon, 23 Nov 2009 19:31:14 +0000
Subject: [PATCH 111/151] powerpc/mm: Fix bug in pagetable cache cleanup with
 CONFIG_PPC_SUBPAGE_PROT

Commit a0668cdc154e54bf0c85182e0535eea237d53146 cleans up the handling
of kmem_caches for allocating various levels of pagetables.
Unfortunately, it conflicts badly with CONFIG_PPC_SUBPAGE_PROT, due to
the latter's cleverly hidden technique of adding some extra allocation
space to the top level page directory to store the extra information
it needs.

Since that extra allocation really doesn't fit into the cleaned up
page directory allocating scheme, this patch alters
CONFIG_PPC_SUBPAGE_PROT to instead allocate its struct
subpage_prot_table as part of the mm_context_t.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/mmu-hash64.h     | 35 +++++++++++++++++++++
 arch/powerpc/include/asm/pgalloc-64.h     |  5 ---
 arch/powerpc/include/asm/pte-hash64-64k.h | 37 -----------------------
 arch/powerpc/mm/hash_utils_64.c           |  6 ++--
 arch/powerpc/mm/mmu_context_hash64.c      |  2 ++
 arch/powerpc/mm/subpage-prot.c            | 15 ++++++---
 6 files changed, 51 insertions(+), 49 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 7514ec2f8540..9d9551840f4a 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -373,6 +373,38 @@ extern void slb_set_size(u16 size);
 
 #ifndef __ASSEMBLY__
 
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+/*
+ * For the sub-page protection option, we extend the PGD with one of
+ * these.  Basically we have a 3-level tree, with the top level being
+ * the protptrs array.  To optimize speed and memory consumption when
+ * only addresses < 4GB are being protected, pointers to the first
+ * four pages of sub-page protection words are stored in the low_prot
+ * array.
+ * Each page of sub-page protection words protects 1GB (4 bytes
+ * protects 64k).  For the 3-level tree, each page of pointers then
+ * protects 8TB.
+ */
+struct subpage_prot_table {
+	unsigned long maxaddr;	/* only addresses < this are protected */
+	unsigned int **protptrs[2];
+	unsigned int *low_prot[4];
+};
+
+#define SBP_L1_BITS		(PAGE_SHIFT - 2)
+#define SBP_L2_BITS		(PAGE_SHIFT - 3)
+#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
+#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
+#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
+#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
+
+extern void subpage_prot_free(struct mm_struct *mm);
+extern void subpage_prot_init_new_context(struct mm_struct *mm);
+#else
+static inline void subpage_prot_free(pgd_t *pgd) {}
+static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
+
 typedef unsigned long mm_context_id_t;
 
 typedef struct {
@@ -386,6 +418,9 @@ typedef struct {
 	u16 sllp;		/* SLB page size encoding */
 #endif
 	unsigned long vdso_base;
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+	struct subpage_prot_table spt;
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
 } mm_context_t;
 
 
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 5c1cd73dafa8..605f5c5398d1 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -28,10 +28,6 @@
  */
 #define MAX_PGTABLE_INDEX_SIZE	0xf
 
-#ifndef CONFIG_PPC_SUBPAGE_PROT
-static inline void subpage_prot_free(pgd_t *pgd) {}
-#endif
-
 extern struct kmem_cache *pgtable_cache[];
 #define PGT_CACHE(shift) (pgtable_cache[(shift)-1])
 
@@ -42,7 +38,6 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-	subpage_prot_free(pgd);
 	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
 }
 
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index 82b72207c51c..c4490f9c67c4 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -76,41 +76,4 @@
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE,		\
 			__pgprot(pgprot_val((prot)) | _PAGE_4K_PFN))
 
-
-#ifdef CONFIG_PPC_SUBPAGE_PROT
-/*
- * For the sub-page protection option, we extend the PGD with one of
- * these.  Basically we have a 3-level tree, with the top level being
- * the protptrs array.  To optimize speed and memory consumption when
- * only addresses < 4GB are being protected, pointers to the first
- * four pages of sub-page protection words are stored in the low_prot
- * array.
- * Each page of sub-page protection words protects 1GB (4 bytes
- * protects 64k).  For the 3-level tree, each page of pointers then
- * protects 8TB.
- */
-struct subpage_prot_table {
-	unsigned long maxaddr;	/* only addresses < this are protected */
-	unsigned int **protptrs[2];
-	unsigned int *low_prot[4];
-};
-
-#undef PGD_TABLE_SIZE
-#define PGD_TABLE_SIZE		((sizeof(pgd_t) << PGD_INDEX_SIZE) + \
-				 sizeof(struct subpage_prot_table))
-
-#define SBP_L1_BITS		(PAGE_SHIFT - 2)
-#define SBP_L2_BITS		(PAGE_SHIFT - 3)
-#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
-#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
-#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
-#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
-
-extern void subpage_prot_free(pgd_t *pgd);
-
-static inline struct subpage_prot_table *pgd_subpage_prot(pgd_t *pgd)
-{
-	return (struct subpage_prot_table *)(pgd + PTRS_PER_PGD);
-}
-#endif /* CONFIG_PPC_SUBPAGE_PROT */
 #endif	/* __ASSEMBLY__ */
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 6810128aba30..50f867d657df 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -835,9 +835,9 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
  * Result is 0: full permissions, _PAGE_RW: read-only,
  * _PAGE_USER or _PAGE_USER|_PAGE_RW: no access.
  */
-static int subpage_protection(pgd_t *pgdir, unsigned long ea)
+static int subpage_protection(struct mm_struct *mm, unsigned long ea)
 {
-	struct subpage_prot_table *spt = pgd_subpage_prot(pgdir);
+	struct subpage_prot_table *spt = &mm->context.spt;
 	u32 spp = 0;
 	u32 **sbpm, *sbpp;
 
@@ -865,7 +865,7 @@ static int subpage_protection(pgd_t *pgdir, unsigned long ea)
 }
 
 #else /* CONFIG_PPC_SUBPAGE_PROT */
-static inline int subpage_protection(pgd_t *pgdir, unsigned long ea)
+static inline int subpage_protection(struct mm_struct *mm, unsigned long ea)
 {
 	return 0;
 }
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index b9e4cc2c2057..b910d37aea1a 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -76,6 +76,7 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	 */
 	if (slice_mm_new_context(mm))
 		slice_set_user_psize(mm, mmu_virtual_psize);
+	subpage_prot_init_new_context(mm);
 	mm->context.id = index;
 
 	return 0;
@@ -92,5 +93,6 @@ EXPORT_SYMBOL_GPL(__destroy_context);
 void destroy_context(struct mm_struct *mm)
 {
 	__destroy_context(mm->context.id);
+	subpage_prot_free(mm);
 	mm->context.id = NO_CONTEXT;
 }
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index 4cafc0c33d0a..a040b81e93bd 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -24,9 +24,9 @@
  * Also makes sure that the subpage_prot_table structure is
  * reinitialized for the next user.
  */
-void subpage_prot_free(pgd_t *pgd)
+void subpage_prot_free(struct mm_struct *mm)
 {
-	struct subpage_prot_table *spt = pgd_subpage_prot(pgd);
+	struct subpage_prot_table *spt = &mm->context.spt;
 	unsigned long i, j, addr;
 	u32 **p;
 
@@ -51,6 +51,13 @@ void subpage_prot_free(pgd_t *pgd)
 	spt->maxaddr = 0;
 }
 
+void subpage_prot_init_new_context(struct mm_struct *mm)
+{
+	struct subpage_prot_table *spt = &mm->context.spt;
+
+	memset(spt, 0, sizeof(*spt));
+}
+
 static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
 			     int npages)
 {
@@ -87,7 +94,7 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
 static void subpage_prot_clear(unsigned long addr, unsigned long len)
 {
 	struct mm_struct *mm = current->mm;
-	struct subpage_prot_table *spt = pgd_subpage_prot(mm->pgd);
+	struct subpage_prot_table *spt = &mm->context.spt;
 	u32 **spm, *spp;
 	int i, nw;
 	unsigned long next, limit;
@@ -136,7 +143,7 @@ static void subpage_prot_clear(unsigned long addr, unsigned long len)
 long sys_subpage_prot(unsigned long addr, unsigned long len, u32 __user *map)
 {
 	struct mm_struct *mm = current->mm;
-	struct subpage_prot_table *spt = pgd_subpage_prot(mm->pgd);
+	struct subpage_prot_table *spt = &mm->context.spt;
 	u32 **spm, *spp;
 	int i, nw;
 	unsigned long next, limit;

From 39adfa540fa0b32e41b2a5a9e225384009ae6128 Mon Sep 17 00:00:00 2001
From: David Gibson <david@gibson.dropbear.id.au>
Date: Mon, 23 Nov 2009 20:03:40 +0000
Subject: [PATCH 112/151] powerpc/mm: Fix bug in gup_hugepd()

Commit a4fe3ce7699bfe1bd88f816b55d42d8fe1dac655 introduced a new
get_user_pages() path for hugepages on powerpc.  Unfortunately, there
is a bug in it's loop logic, which can cause it to overrun the end of
the intended region.  This came about by copying the logic from the
normal page path, which assumes the address and end parameters have
been pagesize aligned at the top-level.  Since they're not *hugepage*
size aligned, the simplistic logic could step over the end of the gup
region without triggering the loop end condition.

This patch fixes the bug by using the technique that the normal page
path uses in levels above the lowest to truncate the ending address to
something we know we'll match with.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/mm/hugetlbpage.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 53b200abb025..123f7070238a 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -436,18 +436,27 @@ static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long add
 	return 1;
 }
 
+static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
+				      unsigned long sz)
+{
+	unsigned long __boundary = (addr + sz) & ~(sz-1);
+	return (__boundary - 1 < end - 1) ? __boundary : end;
+}
+
 int gup_hugepd(hugepd_t *hugepd, unsigned pdshift,
 	       unsigned long addr, unsigned long end,
 	       int write, struct page **pages, int *nr)
 {
 	pte_t *ptep;
 	unsigned long sz = 1UL << hugepd_shift(*hugepd);
+	unsigned long next;
 
 	ptep = hugepte_offset(hugepd, addr, pdshift);
 	do {
+		next = hugepte_addr_end(addr, end, sz);
 		if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
 			return 0;
-	} while (ptep++, addr += sz, addr != end);
+	} while (ptep++, addr = next, addr != end);
 
 	return 1;
 }

From 86f9e097f340fd0fbd37afe92bd5453f5a84cbca Mon Sep 17 00:00:00 2001
From: Michal Simek <monstr@monstr.eu>
Date: Tue, 24 Nov 2009 00:22:41 +0000
Subject: [PATCH 113/151] powerpc/of_serial: Add missing ns16550a id

Many boards have a bug-free ns16550 compatible serial port, which we should
register as PORT_16550A. This introduces a new value "ns16550a" for the
compatible property of of_serial to let a firmware choose that model instead
of using the crippled PORT_16550 mode.

Reported-by: Alon Ziv <alonz@nolaviz.org>
Signed-off-by: Michal Simek <monstr@monstr.eu>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 drivers/serial/of_serial.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/serial/of_serial.c b/drivers/serial/of_serial.c
index 02406ba6da1c..cdf172eda2e3 100644
--- a/drivers/serial/of_serial.c
+++ b/drivers/serial/of_serial.c
@@ -161,6 +161,7 @@ static int of_platform_serial_remove(struct of_device *ofdev)
 static struct of_device_id __devinitdata of_platform_serial_table[] = {
 	{ .type = "serial", .compatible = "ns8250",   .data = (void *)PORT_8250, },
 	{ .type = "serial", .compatible = "ns16450",  .data = (void *)PORT_16450, },
+	{ .type = "serial", .compatible = "ns16550a", .data = (void *)PORT_16550A, },
 	{ .type = "serial", .compatible = "ns16550",  .data = (void *)PORT_16550, },
 	{ .type = "serial", .compatible = "ns16750",  .data = (void *)PORT_16750, },
 	{ .type = "serial", .compatible = "ns16850",  .data = (void *)PORT_16850, },

From 5a7b4193e564d1611ecf1cd859aed60d5612d78f Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Wed, 2 Dec 2009 09:28:35 +1100
Subject: [PATCH 114/151] Revert "powerpc/mm: Fix bug in pagetable cache
 cleanup with CONFIG_PPC_SUBPAGE_PROT"

This reverts commit c045256d146800ea1d741a8e9e377dada6b7e195.

It breaks build when CONFIG_PPC_SUBPAGE_PROT is not set. I will
commit a fixed version separately

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/mmu-hash64.h     | 35 ---------------------
 arch/powerpc/include/asm/pgalloc-64.h     |  5 +++
 arch/powerpc/include/asm/pte-hash64-64k.h | 37 +++++++++++++++++++++++
 arch/powerpc/mm/hash_utils_64.c           |  6 ++--
 arch/powerpc/mm/mmu_context_hash64.c      |  2 --
 arch/powerpc/mm/subpage-prot.c            | 15 +++------
 6 files changed, 49 insertions(+), 51 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 9d9551840f4a..7514ec2f8540 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -373,38 +373,6 @@ extern void slb_set_size(u16 size);
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_PPC_SUBPAGE_PROT
-/*
- * For the sub-page protection option, we extend the PGD with one of
- * these.  Basically we have a 3-level tree, with the top level being
- * the protptrs array.  To optimize speed and memory consumption when
- * only addresses < 4GB are being protected, pointers to the first
- * four pages of sub-page protection words are stored in the low_prot
- * array.
- * Each page of sub-page protection words protects 1GB (4 bytes
- * protects 64k).  For the 3-level tree, each page of pointers then
- * protects 8TB.
- */
-struct subpage_prot_table {
-	unsigned long maxaddr;	/* only addresses < this are protected */
-	unsigned int **protptrs[2];
-	unsigned int *low_prot[4];
-};
-
-#define SBP_L1_BITS		(PAGE_SHIFT - 2)
-#define SBP_L2_BITS		(PAGE_SHIFT - 3)
-#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
-#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
-#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
-#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
-
-extern void subpage_prot_free(struct mm_struct *mm);
-extern void subpage_prot_init_new_context(struct mm_struct *mm);
-#else
-static inline void subpage_prot_free(pgd_t *pgd) {}
-static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
-#endif /* CONFIG_PPC_SUBPAGE_PROT */
-
 typedef unsigned long mm_context_id_t;
 
 typedef struct {
@@ -418,9 +386,6 @@ typedef struct {
 	u16 sllp;		/* SLB page size encoding */
 #endif
 	unsigned long vdso_base;
-#ifdef CONFIG_PPC_SUBPAGE_PROT
-	struct subpage_prot_table spt;
-#endif /* CONFIG_PPC_SUBPAGE_PROT */
 } mm_context_t;
 
 
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 605f5c5398d1..5c1cd73dafa8 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -28,6 +28,10 @@
  */
 #define MAX_PGTABLE_INDEX_SIZE	0xf
 
+#ifndef CONFIG_PPC_SUBPAGE_PROT
+static inline void subpage_prot_free(pgd_t *pgd) {}
+#endif
+
 extern struct kmem_cache *pgtable_cache[];
 #define PGT_CACHE(shift) (pgtable_cache[(shift)-1])
 
@@ -38,6 +42,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
+	subpage_prot_free(pgd);
 	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
 }
 
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index c4490f9c67c4..82b72207c51c 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -76,4 +76,41 @@
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE,		\
 			__pgprot(pgprot_val((prot)) | _PAGE_4K_PFN))
 
+
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+/*
+ * For the sub-page protection option, we extend the PGD with one of
+ * these.  Basically we have a 3-level tree, with the top level being
+ * the protptrs array.  To optimize speed and memory consumption when
+ * only addresses < 4GB are being protected, pointers to the first
+ * four pages of sub-page protection words are stored in the low_prot
+ * array.
+ * Each page of sub-page protection words protects 1GB (4 bytes
+ * protects 64k).  For the 3-level tree, each page of pointers then
+ * protects 8TB.
+ */
+struct subpage_prot_table {
+	unsigned long maxaddr;	/* only addresses < this are protected */
+	unsigned int **protptrs[2];
+	unsigned int *low_prot[4];
+};
+
+#undef PGD_TABLE_SIZE
+#define PGD_TABLE_SIZE		((sizeof(pgd_t) << PGD_INDEX_SIZE) + \
+				 sizeof(struct subpage_prot_table))
+
+#define SBP_L1_BITS		(PAGE_SHIFT - 2)
+#define SBP_L2_BITS		(PAGE_SHIFT - 3)
+#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
+#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
+#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
+#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
+
+extern void subpage_prot_free(pgd_t *pgd);
+
+static inline struct subpage_prot_table *pgd_subpage_prot(pgd_t *pgd)
+{
+	return (struct subpage_prot_table *)(pgd + PTRS_PER_PGD);
+}
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
 #endif	/* __ASSEMBLY__ */
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 50f867d657df..6810128aba30 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -835,9 +835,9 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
  * Result is 0: full permissions, _PAGE_RW: read-only,
  * _PAGE_USER or _PAGE_USER|_PAGE_RW: no access.
  */
-static int subpage_protection(struct mm_struct *mm, unsigned long ea)
+static int subpage_protection(pgd_t *pgdir, unsigned long ea)
 {
-	struct subpage_prot_table *spt = &mm->context.spt;
+	struct subpage_prot_table *spt = pgd_subpage_prot(pgdir);
 	u32 spp = 0;
 	u32 **sbpm, *sbpp;
 
@@ -865,7 +865,7 @@ static int subpage_protection(struct mm_struct *mm, unsigned long ea)
 }
 
 #else /* CONFIG_PPC_SUBPAGE_PROT */
-static inline int subpage_protection(struct mm_struct *mm, unsigned long ea)
+static inline int subpage_protection(pgd_t *pgdir, unsigned long ea)
 {
 	return 0;
 }
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index b910d37aea1a..b9e4cc2c2057 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -76,7 +76,6 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	 */
 	if (slice_mm_new_context(mm))
 		slice_set_user_psize(mm, mmu_virtual_psize);
-	subpage_prot_init_new_context(mm);
 	mm->context.id = index;
 
 	return 0;
@@ -93,6 +92,5 @@ EXPORT_SYMBOL_GPL(__destroy_context);
 void destroy_context(struct mm_struct *mm)
 {
 	__destroy_context(mm->context.id);
-	subpage_prot_free(mm);
 	mm->context.id = NO_CONTEXT;
 }
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index a040b81e93bd..4cafc0c33d0a 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -24,9 +24,9 @@
  * Also makes sure that the subpage_prot_table structure is
  * reinitialized for the next user.
  */
-void subpage_prot_free(struct mm_struct *mm)
+void subpage_prot_free(pgd_t *pgd)
 {
-	struct subpage_prot_table *spt = &mm->context.spt;
+	struct subpage_prot_table *spt = pgd_subpage_prot(pgd);
 	unsigned long i, j, addr;
 	u32 **p;
 
@@ -51,13 +51,6 @@ void subpage_prot_free(struct mm_struct *mm)
 	spt->maxaddr = 0;
 }
 
-void subpage_prot_init_new_context(struct mm_struct *mm)
-{
-	struct subpage_prot_table *spt = &mm->context.spt;
-
-	memset(spt, 0, sizeof(*spt));
-}
-
 static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
 			     int npages)
 {
@@ -94,7 +87,7 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
 static void subpage_prot_clear(unsigned long addr, unsigned long len)
 {
 	struct mm_struct *mm = current->mm;
-	struct subpage_prot_table *spt = &mm->context.spt;
+	struct subpage_prot_table *spt = pgd_subpage_prot(mm->pgd);
 	u32 **spm, *spp;
 	int i, nw;
 	unsigned long next, limit;
@@ -143,7 +136,7 @@ static void subpage_prot_clear(unsigned long addr, unsigned long len)
 long sys_subpage_prot(unsigned long addr, unsigned long len, u32 __user *map)
 {
 	struct mm_struct *mm = current->mm;
-	struct subpage_prot_table *spt = &mm->context.spt;
+	struct subpage_prot_table *spt = pgd_subpage_prot(mm->pgd);
 	u32 **spm, *spp;
 	int i, nw;
 	unsigned long next, limit;

From 2e991cfa9b9b508725a7b56174b6aade895772b2 Mon Sep 17 00:00:00 2001
From: "pbathija@amcc.com" <pbathija@amcc.com>
Date: Mon, 23 Nov 2009 13:06:13 +0000
Subject: [PATCH 115/151] powerpc/44x: Fix DMA ranges in DTS file for Katmai
 board.

Set PCI-E node inbound DMA ranges size to 4GB for correct boot up of Katmai.

Signed-off-by: Pravin Bathija <pbathija@amcc.com>
Acked-by: Feng Kan <fkan@amcc.com>
Acked-by: Prodyut Hazarika <phazarika@amcc.com>
Acked-by: Loc Ho <lho@amcc.com>
Acked-by: Tirumala Reddy Marri <tmarri@amcc.com>
Acked-by: Victor Gallardo <vgallardo@amcc.com>
Acked-by: Stefan Roese <sr@denx.de>
Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
---
 arch/powerpc/boot/dts/katmai.dts | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/arch/powerpc/boot/dts/katmai.dts b/arch/powerpc/boot/dts/katmai.dts
index b8cd97c5c74e..51eb6ed5da2d 100644
--- a/arch/powerpc/boot/dts/katmai.dts
+++ b/arch/powerpc/boot/dts/katmai.dts
@@ -253,8 +253,8 @@
 			ranges = <0x02000000 0x00000000 0x80000000 0x0000000d 0x80000000 0x00000000 0x80000000
 				  0x01000000 0x00000000 0x00000000 0x0000000c 0x08000000 0x00000000 0x00010000>;
 
-			/* Inbound 2GB range starting at 0 */
-			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x0 0x80000000>;
+			/* Inbound 4GB range starting at 0 */
+			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x1 0x00000000>;
 
 			/* This drives busses 0 to 0xf */
 			bus-range = <0x0 0xf>;
@@ -297,10 +297,10 @@
 			ranges = <0x02000000 0x00000000 0x80000000 0x0000000e 0x00000000 0x00000000 0x80000000
 				  0x01000000 0x00000000 0x00000000 0x0000000f 0x80000000 0x00000000 0x00010000>;
 
-			/* Inbound 2GB range starting at 0 */
-			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x0 0x80000000>;
+			/* Inbound 4GB range starting at 0 */
+			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x1 0x00000000>;
 
-			/* This drives busses 10 to 0x1f */
+			/* This drives busses 0x10 to 0x1f */
 			bus-range = <0x10 0x1f>;
 
 			/* Legacy interrupts (note the weird polarity, the bridge seems
@@ -338,10 +338,10 @@
 			ranges = <0x02000000 0x00000000 0x80000000 0x0000000e 0x80000000 0x00000000 0x80000000
 				  0x01000000 0x00000000 0x00000000 0x0000000f 0x80010000 0x00000000 0x00010000>;
 
-			/* Inbound 2GB range starting at 0 */
-			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x0 0x80000000>;
+			/* Inbound 4GB range starting at 0 */
+			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x1 0x00000000>;
 
-			/* This drives busses 10 to 0x1f */
+			/* This drives busses 0x20 to 0x2f */
 			bus-range = <0x20 0x2f>;
 
 			/* Legacy interrupts (note the weird polarity, the bridge seems
@@ -379,10 +379,10 @@
 			ranges = <0x02000000 0x00000000 0x80000000 0x0000000f 0x00000000 0x00000000 0x80000000
 				  0x01000000 0x00000000 0x00000000 0x0000000f 0x80020000 0x00000000 0x00010000>;
 
-			/* Inbound 2GB range starting at 0 */
-			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x0 0x80000000>;
+			/* Inbound 4GB range starting at 0 */
+			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x1 0x00000000>;
 
-			/* This drives busses 10 to 0x1f */
+			/* This drives busses 0x30 to 0x3f */
 			bus-range = <0x30 0x3f>;
 
 			/* Legacy interrupts (note the weird polarity, the bridge seems

From 06a5bad898b332b8c6525fc8c4d1c1c9a8df65de Mon Sep 17 00:00:00 2001
From: Curtis Wald <cwald@watchguardvideo.com>
Date: Fri, 4 Dec 2009 07:10:26 -0500
Subject: [PATCH 116/151] powerpc/44x: Fix PCI node in Yosemite DTS

The stanza for PCI was copied from Bamboo which has four PCI slots.  Yosemite
only has one PCI slot which is mapped to IDSEL 12, ADDR 22, IRQ2 Vector 25,
INTA.

Signed-off-by: Curtis Wald <cwald@watchguardvideo.com>
Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
---
 arch/powerpc/boot/dts/yosemite.dts | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/boot/dts/yosemite.dts b/arch/powerpc/boot/dts/yosemite.dts
index 1fa3cb4c4ebb..64923245f0e5 100644
--- a/arch/powerpc/boot/dts/yosemite.dts
+++ b/arch/powerpc/boot/dts/yosemite.dts
@@ -282,20 +282,10 @@
 			/* Inbound 2GB range starting at 0 */
 			dma-ranges = <0x42000000 0x0 0x0 0x0 0x0 0x0 0x80000000>;
 
-			/* Bamboo has all 4 IRQ pins tied together per slot */
 			interrupt-map-mask = <0xf800 0x0 0x0 0x0>;
 			interrupt-map = <
-				/* IDSEL 1 */
-				0x800 0x0 0x0 0x0 &UIC0 0x1c 0x8
-
-				/* IDSEL 2 */
-				0x1000 0x0 0x0 0x0 &UIC0 0x1b 0x8
-
-				/* IDSEL 3 */
-				0x1800 0x0 0x0 0x0 &UIC0 0x1a 0x8
-
-				/* IDSEL 4 */
-				0x2000 0x0 0x0 0x0 &UIC0 0x19 0x8
+				/* IDSEL 12 */
+				0x6000 0x0 0x0 0x0 &UIC0 0x19 0x8
 			>;
 		};
 	};

From d28513bc7f675d28b479db666d572e078ecf182d Mon Sep 17 00:00:00 2001
From: David Gibson <dwg@au1.ibm.com>
Date: Thu, 26 Nov 2009 18:56:04 +0000
Subject: [PATCH 117/151] powerpc/mm: Fix pgtable cache cleanup with
 CONFIG_PPC_SUBPAGE_PROT

Commit a0668cdc154e54bf0c85182e0535eea237d53146 cleans up the handling
of kmem_caches for allocating various levels of pagetables.
Unfortunately, it conflicts badly with CONFIG_PPC_SUBPAGE_PROT, due to
the latter's cleverly hidden technique of adding some extra allocation
space to the top level page directory to store the extra information
it needs.

Since that extra allocation really doesn't fit into the cleaned up
page directory allocating scheme, this patch alters
CONFIG_PPC_SUBPAGE_PROT to instead allocate its struct
subpage_prot_table as part of the mm_context_t.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/mmu-hash64.h     | 35 +++++++++++++++++++++
 arch/powerpc/include/asm/pgalloc-64.h     |  5 ---
 arch/powerpc/include/asm/pte-hash64-64k.h | 37 -----------------------
 arch/powerpc/mm/hash_utils_64.c           |  6 ++--
 arch/powerpc/mm/mmu_context_hash64.c      |  2 ++
 arch/powerpc/mm/subpage-prot.c            | 15 ++++++---
 6 files changed, 51 insertions(+), 49 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 7514ec2f8540..2102b214a87c 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -373,6 +373,38 @@ extern void slb_set_size(u16 size);
 
 #ifndef __ASSEMBLY__
 
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+/*
+ * For the sub-page protection option, we extend the PGD with one of
+ * these.  Basically we have a 3-level tree, with the top level being
+ * the protptrs array.  To optimize speed and memory consumption when
+ * only addresses < 4GB are being protected, pointers to the first
+ * four pages of sub-page protection words are stored in the low_prot
+ * array.
+ * Each page of sub-page protection words protects 1GB (4 bytes
+ * protects 64k).  For the 3-level tree, each page of pointers then
+ * protects 8TB.
+ */
+struct subpage_prot_table {
+	unsigned long maxaddr;	/* only addresses < this are protected */
+	unsigned int **protptrs[2];
+	unsigned int *low_prot[4];
+};
+
+#define SBP_L1_BITS		(PAGE_SHIFT - 2)
+#define SBP_L2_BITS		(PAGE_SHIFT - 3)
+#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
+#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
+#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
+#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
+
+extern void subpage_prot_free(struct mm_struct *mm);
+extern void subpage_prot_init_new_context(struct mm_struct *mm);
+#else
+static inline void subpage_prot_free(struct mm_struct *mm) {}
+static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
+
 typedef unsigned long mm_context_id_t;
 
 typedef struct {
@@ -386,6 +418,9 @@ typedef struct {
 	u16 sllp;		/* SLB page size encoding */
 #endif
 	unsigned long vdso_base;
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+	struct subpage_prot_table spt;
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
 } mm_context_t;
 
 
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 5c1cd73dafa8..605f5c5398d1 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -28,10 +28,6 @@
  */
 #define MAX_PGTABLE_INDEX_SIZE	0xf
 
-#ifndef CONFIG_PPC_SUBPAGE_PROT
-static inline void subpage_prot_free(pgd_t *pgd) {}
-#endif
-
 extern struct kmem_cache *pgtable_cache[];
 #define PGT_CACHE(shift) (pgtable_cache[(shift)-1])
 
@@ -42,7 +38,6 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-	subpage_prot_free(pgd);
 	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
 }
 
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index 82b72207c51c..c4490f9c67c4 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -76,41 +76,4 @@
 	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE,		\
 			__pgprot(pgprot_val((prot)) | _PAGE_4K_PFN))
 
-
-#ifdef CONFIG_PPC_SUBPAGE_PROT
-/*
- * For the sub-page protection option, we extend the PGD with one of
- * these.  Basically we have a 3-level tree, with the top level being
- * the protptrs array.  To optimize speed and memory consumption when
- * only addresses < 4GB are being protected, pointers to the first
- * four pages of sub-page protection words are stored in the low_prot
- * array.
- * Each page of sub-page protection words protects 1GB (4 bytes
- * protects 64k).  For the 3-level tree, each page of pointers then
- * protects 8TB.
- */
-struct subpage_prot_table {
-	unsigned long maxaddr;	/* only addresses < this are protected */
-	unsigned int **protptrs[2];
-	unsigned int *low_prot[4];
-};
-
-#undef PGD_TABLE_SIZE
-#define PGD_TABLE_SIZE		((sizeof(pgd_t) << PGD_INDEX_SIZE) + \
-				 sizeof(struct subpage_prot_table))
-
-#define SBP_L1_BITS		(PAGE_SHIFT - 2)
-#define SBP_L2_BITS		(PAGE_SHIFT - 3)
-#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
-#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
-#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
-#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
-
-extern void subpage_prot_free(pgd_t *pgd);
-
-static inline struct subpage_prot_table *pgd_subpage_prot(pgd_t *pgd)
-{
-	return (struct subpage_prot_table *)(pgd + PTRS_PER_PGD);
-}
-#endif /* CONFIG_PPC_SUBPAGE_PROT */
 #endif	/* __ASSEMBLY__ */
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 6810128aba30..50f867d657df 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -835,9 +835,9 @@ void demote_segment_4k(struct mm_struct *mm, unsigned long addr)
  * Result is 0: full permissions, _PAGE_RW: read-only,
  * _PAGE_USER or _PAGE_USER|_PAGE_RW: no access.
  */
-static int subpage_protection(pgd_t *pgdir, unsigned long ea)
+static int subpage_protection(struct mm_struct *mm, unsigned long ea)
 {
-	struct subpage_prot_table *spt = pgd_subpage_prot(pgdir);
+	struct subpage_prot_table *spt = &mm->context.spt;
 	u32 spp = 0;
 	u32 **sbpm, *sbpp;
 
@@ -865,7 +865,7 @@ static int subpage_protection(pgd_t *pgdir, unsigned long ea)
 }
 
 #else /* CONFIG_PPC_SUBPAGE_PROT */
-static inline int subpage_protection(pgd_t *pgdir, unsigned long ea)
+static inline int subpage_protection(struct mm_struct *mm, unsigned long ea)
 {
 	return 0;
 }
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index b9e4cc2c2057..b910d37aea1a 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -76,6 +76,7 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	 */
 	if (slice_mm_new_context(mm))
 		slice_set_user_psize(mm, mmu_virtual_psize);
+	subpage_prot_init_new_context(mm);
 	mm->context.id = index;
 
 	return 0;
@@ -92,5 +93,6 @@ EXPORT_SYMBOL_GPL(__destroy_context);
 void destroy_context(struct mm_struct *mm)
 {
 	__destroy_context(mm->context.id);
+	subpage_prot_free(mm);
 	mm->context.id = NO_CONTEXT;
 }
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index 4cafc0c33d0a..a040b81e93bd 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -24,9 +24,9 @@
  * Also makes sure that the subpage_prot_table structure is
  * reinitialized for the next user.
  */
-void subpage_prot_free(pgd_t *pgd)
+void subpage_prot_free(struct mm_struct *mm)
 {
-	struct subpage_prot_table *spt = pgd_subpage_prot(pgd);
+	struct subpage_prot_table *spt = &mm->context.spt;
 	unsigned long i, j, addr;
 	u32 **p;
 
@@ -51,6 +51,13 @@ void subpage_prot_free(pgd_t *pgd)
 	spt->maxaddr = 0;
 }
 
+void subpage_prot_init_new_context(struct mm_struct *mm)
+{
+	struct subpage_prot_table *spt = &mm->context.spt;
+
+	memset(spt, 0, sizeof(*spt));
+}
+
 static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
 			     int npages)
 {
@@ -87,7 +94,7 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
 static void subpage_prot_clear(unsigned long addr, unsigned long len)
 {
 	struct mm_struct *mm = current->mm;
-	struct subpage_prot_table *spt = pgd_subpage_prot(mm->pgd);
+	struct subpage_prot_table *spt = &mm->context.spt;
 	u32 **spm, *spp;
 	int i, nw;
 	unsigned long next, limit;
@@ -136,7 +143,7 @@ static void subpage_prot_clear(unsigned long addr, unsigned long len)
 long sys_subpage_prot(unsigned long addr, unsigned long len, u32 __user *map)
 {
 	struct mm_struct *mm = current->mm;
-	struct subpage_prot_table *spt = pgd_subpage_prot(mm->pgd);
+	struct subpage_prot_table *spt = &mm->context.spt;
 	u32 **spm, *spp;
 	int i, nw;
 	unsigned long next, limit;

From 9d2f7342d08896338890904351490739c1035d43 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Thu, 26 Nov 2009 20:53:06 +0000
Subject: [PATCH 118/151] powerpc/via-pmu: Convert to proc_fops/seq_file

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 drivers/macintosh/via-pmu.c | 160 ++++++++++++++++++++----------------
 1 file changed, 91 insertions(+), 69 deletions(-)

diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index 6f308a4757ee..db379c381432 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -36,6 +36,7 @@
 #include <linux/spinlock.h>
 #include <linux/pm.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/device.h>
@@ -186,17 +187,11 @@ static int init_pmu(void);
 static void pmu_start(void);
 static irqreturn_t via_pmu_interrupt(int irq, void *arg);
 static irqreturn_t gpio1_interrupt(int irq, void *arg);
-static int proc_get_info(char *page, char **start, off_t off,
-			  int count, int *eof, void *data);
-static int proc_get_irqstats(char *page, char **start, off_t off,
-			  int count, int *eof, void *data);
+static const struct file_operations pmu_info_proc_fops;
+static const struct file_operations pmu_irqstats_proc_fops;
 static void pmu_pass_intr(unsigned char *data, int len);
-static int proc_get_batt(char *page, char **start, off_t off,
-			int count, int *eof, void *data);
-static int proc_read_options(char *page, char **start, off_t off,
-			int count, int *eof, void *data);
-static int proc_write_options(struct file *file, const char __user *buffer,
-			unsigned long count, void *data);
+static const struct file_operations pmu_battery_proc_fops;
+static const struct file_operations pmu_options_proc_fops;
 
 #ifdef CONFIG_ADB
 struct adb_driver via_pmu_driver = {
@@ -507,19 +502,15 @@ static int __init via_pmu_dev_init(void)
 		for (i=0; i<pmu_battery_count; i++) {
 			char title[16];
 			sprintf(title, "battery_%ld", i);
-			proc_pmu_batt[i] = create_proc_read_entry(title, 0, proc_pmu_root,
-						proc_get_batt, (void *)i);
+			proc_pmu_batt[i] = proc_create_data(title, 0, proc_pmu_root,
+					&pmu_battery_proc_fops, (void *)i);
 		}
 
-		proc_pmu_info = create_proc_read_entry("info", 0, proc_pmu_root,
-					proc_get_info, NULL);
-		proc_pmu_irqstats = create_proc_read_entry("interrupts", 0, proc_pmu_root,
-					proc_get_irqstats, NULL);
-		proc_pmu_options = create_proc_entry("options", 0600, proc_pmu_root);
-		if (proc_pmu_options) {
-			proc_pmu_options->read_proc = proc_read_options;
-			proc_pmu_options->write_proc = proc_write_options;
-		}
+		proc_pmu_info = proc_create("info", 0, proc_pmu_root, &pmu_info_proc_fops);
+		proc_pmu_irqstats = proc_create("interrupts", 0, proc_pmu_root,
+						&pmu_irqstats_proc_fops);
+		proc_pmu_options = proc_create("options", 0600, proc_pmu_root,
+						&pmu_options_proc_fops);
 	}
 	return 0;
 }
@@ -799,27 +790,33 @@ query_battery_state(void)
 			2, PMU_SMART_BATTERY_STATE, pmu_cur_battery+1);
 }
 
-static int
-proc_get_info(char *page, char **start, off_t off,
-		int count, int *eof, void *data)
+static int pmu_info_proc_show(struct seq_file *m, void *v)
 {
-	char* p = page;
-
-	p += sprintf(p, "PMU driver version     : %d\n", PMU_DRIVER_VERSION);
-	p += sprintf(p, "PMU firmware version   : %02x\n", pmu_version);
-	p += sprintf(p, "AC Power               : %d\n",
+	seq_printf(m, "PMU driver version     : %d\n", PMU_DRIVER_VERSION);
+	seq_printf(m, "PMU firmware version   : %02x\n", pmu_version);
+	seq_printf(m, "AC Power               : %d\n",
 		((pmu_power_flags & PMU_PWR_AC_PRESENT) != 0) || pmu_battery_count == 0);
-	p += sprintf(p, "Battery count          : %d\n", pmu_battery_count);
+	seq_printf(m, "Battery count          : %d\n", pmu_battery_count);
 
-	return p - page;
+	return 0;
 }
 
-static int
-proc_get_irqstats(char *page, char **start, off_t off,
-		  int count, int *eof, void *data)
+static int pmu_info_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, pmu_info_proc_show, NULL);
+}
+
+static const struct file_operations pmu_info_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= pmu_info_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int pmu_irqstats_proc_show(struct seq_file *m, void *v)
 {
 	int i;
-	char* p = page;
 	static const char *irq_names[] = {
 		"Total CB1 triggered events",
 		"Total GPIO1 triggered events",
@@ -835,60 +832,76 @@ proc_get_irqstats(char *page, char **start, off_t off,
         };
 
 	for (i=0; i<11; i++) {
-		p += sprintf(p, " %2u: %10u (%s)\n",
+		seq_printf(m, " %2u: %10u (%s)\n",
 			     i, pmu_irq_stats[i], irq_names[i]);
 	}
-	return p - page;
+	return 0;
 }
 
-static int
-proc_get_batt(char *page, char **start, off_t off,
-		int count, int *eof, void *data)
+static int pmu_irqstats_proc_open(struct inode *inode, struct file *file)
 {
-	long batnum = (long)data;
-	char *p = page;
+	return single_open(file, pmu_irqstats_proc_show, NULL);
+}
+
+static const struct file_operations pmu_irqstats_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= pmu_irqstats_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int pmu_battery_proc_show(struct seq_file *m, void *v)
+{
+	long batnum = (long)m->private;
 	
-	p += sprintf(p, "\n");
-	p += sprintf(p, "flags      : %08x\n",
-		pmu_batteries[batnum].flags);
-	p += sprintf(p, "charge     : %d\n",
-		pmu_batteries[batnum].charge);
-	p += sprintf(p, "max_charge : %d\n",
-		pmu_batteries[batnum].max_charge);
-	p += sprintf(p, "current    : %d\n",
-		pmu_batteries[batnum].amperage);
-	p += sprintf(p, "voltage    : %d\n",
-		pmu_batteries[batnum].voltage);
-	p += sprintf(p, "time rem.  : %d\n",
-		pmu_batteries[batnum].time_remaining);
-
-	return p - page;
+	seq_putc(m, '\n');
+	seq_printf(m, "flags      : %08x\n", pmu_batteries[batnum].flags);
+	seq_printf(m, "charge     : %d\n", pmu_batteries[batnum].charge);
+	seq_printf(m, "max_charge : %d\n", pmu_batteries[batnum].max_charge);
+	seq_printf(m, "current    : %d\n", pmu_batteries[batnum].amperage);
+	seq_printf(m, "voltage    : %d\n", pmu_batteries[batnum].voltage);
+	seq_printf(m, "time rem.  : %d\n", pmu_batteries[batnum].time_remaining);
+	return 0;
 }
 
-static int
-proc_read_options(char *page, char **start, off_t off,
-			int count, int *eof, void *data)
+static int pmu_battery_proc_open(struct inode *inode, struct file *file)
 {
-	char *p = page;
+	return single_open(file, pmu_battery_proc_show, PDE(inode)->data);
+}
 
+static const struct file_operations pmu_battery_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= pmu_battery_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int pmu_options_proc_show(struct seq_file *m, void *v)
+{
 #if defined(CONFIG_SUSPEND) && defined(CONFIG_PPC32)
 	if (pmu_kind == PMU_KEYLARGO_BASED &&
 	    pmac_call_feature(PMAC_FTR_SLEEP_STATE,NULL,0,-1) >= 0)
-		p += sprintf(p, "lid_wakeup=%d\n", option_lid_wakeup);
+		seq_printf(m, "lid_wakeup=%d\n", option_lid_wakeup);
 #endif
 	if (pmu_kind == PMU_KEYLARGO_BASED)
-		p += sprintf(p, "server_mode=%d\n", option_server_mode);
+		seq_printf(m, "server_mode=%d\n", option_server_mode);
 
-	return p - page;
+	return 0;
 }
-			
-static int
-proc_write_options(struct file *file, const char __user *buffer,
-			unsigned long count, void *data)
+
+static int pmu_options_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, pmu_options_proc_show, NULL);
+}
+
+static ssize_t pmu_options_proc_write(struct file *file,
+		const char __user *buffer, size_t count, loff_t *pos)
 {
 	char tmp[33];
 	char *label, *val;
-	unsigned long fcount = count;
+	size_t fcount = count;
 	
 	if (!count)
 		return -EINVAL;
@@ -927,6 +940,15 @@ proc_write_options(struct file *file, const char __user *buffer,
 	return fcount;
 }
 
+static const struct file_operations pmu_options_proc_fops = {
+	.owner		= THIS_MODULE,
+	.open		= pmu_options_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+	.write		= pmu_options_proc_write,
+};
+
 #ifdef CONFIG_ADB
 /* Send an ADB command */
 static int pmu_send_request(struct adb_request *req, int sync)

From 529586dc39b0ec47c6290c4e7bed6ea3ffd1d8fb Mon Sep 17 00:00:00 2001
From: Bolko Maass <krautilein@gmx.de>
Date: Fri, 27 Nov 2009 05:44:33 +0000
Subject: [PATCH 119/151] powerpc/windfarm: Add detection for second cpu pump

Windfarm SMU control is explicitly missing support for a second CPU pump in G5 PowerMacs. Such machines actually exist  (specifically Quads with a second pump), so this patch adds detection for it.

Signed-off by: Bolko Maass <bmaass@math.uni-bremen.de>
CC: <stable@kernel.org>

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 drivers/macintosh/windfarm_smu_controls.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/macintosh/windfarm_smu_controls.c b/drivers/macintosh/windfarm_smu_controls.c
index 961fa0e7c2cf..6c68b9e5f5c4 100644
--- a/drivers/macintosh/windfarm_smu_controls.c
+++ b/drivers/macintosh/windfarm_smu_controls.c
@@ -202,6 +202,8 @@ static struct smu_fan_control *smu_fan_create(struct device_node *node,
 		fct->ctrl.name = "cpu-front-fan-1";
 	else if (!strcmp(l, "CPU A PUMP"))
 		fct->ctrl.name = "cpu-pump-0";
+	else if (!strcmp(l, "CPU B PUMP"))
+		fct->ctrl.name = "cpu-pump-1";
 	else if (!strcmp(l, "Slots Fan") || !strcmp(l, "Slots fan") ||
 		 !strcmp(l, "EXPANSION SLOTS INTAKE"))
 		fct->ctrl.name = "slots-fan";

From c0cefebc0b6ae1bc4c92672223a54e1ee96ea7f0 Mon Sep 17 00:00:00 2001
From: Amit Shah <amit.shah@redhat.com>
Date: Fri, 27 Nov 2009 20:50:49 +0000
Subject: [PATCH 120/151] hvc_console: Export (GPL'ed) hvc_remove

The virtio console, which uses hvc, will get the ability to hot-unplug
ports. Export hvc_remove so that virtio_console can disassociate with
hvc.

Signed-off-by: Amit Shah <amit.shah@redhat.com>
Cc: linuxppc-dev@ozlabs.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 drivers/char/hvc_console.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/char/hvc_console.c b/drivers/char/hvc_console.c
index a632f25f144a..416d3423150d 100644
--- a/drivers/char/hvc_console.c
+++ b/drivers/char/hvc_console.c
@@ -832,6 +832,7 @@ int hvc_remove(struct hvc_struct *hp)
 		tty_hangup(tty);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(hvc_remove);
 
 /* Driver initialization: called as soon as someone uses hvc_alloc(). */
 static int hvc_init(void)

From e15a113700324f7fdcee95589875daed2b98a2fe Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 30 Nov 2009 03:02:02 +0000
Subject: [PATCH 121/151] powerpc/kvm: Sync guest visible MMU state

Currently userspace has no chance to find out which virtual address space we're
in and resolve addresses. While that is a big problem for migration, it's also
unpleasent when debugging, as gdb and the monitor don't work on virtual
addresses.

This patch exports enough of the MMU segment state to userspace to make
debugging work and thus also includes the groundwork for migration.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/kvm.h        | 18 +++++++++-
 arch/powerpc/include/asm/kvm_asm.h    |  1 +
 arch/powerpc/include/asm/kvm_book3s.h |  3 ++
 arch/powerpc/kvm/book3s.c             | 49 +++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_64_emulate.c  | 38 +++++++++++++--------
 arch/powerpc/kvm/book3s_64_mmu.c      |  2 ++
 arch/powerpc/kvm/powerpc.c            |  3 ++
 include/linux/kvm.h                   |  3 ++
 8 files changed, 101 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index c9ca97f43bc1..81f3b0b5601e 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -47,7 +47,23 @@ struct kvm_regs {
 
 struct kvm_sregs {
 	__u32 pvr;
-	char pad[1020];
+	union {
+		struct {
+			__u64 sdr1;
+			struct {
+				struct {
+					__u64 slbe;
+					__u64 slbv;
+				} slb[64];
+			} ppc64;
+			struct {
+				__u32 sr[16];
+				__u64 ibat[8]; 
+				__u64 dbat[8]; 
+			} ppc32;
+		} s;
+		__u8 pad[1020];
+	} u;
 };
 
 struct kvm_fpu {
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 19ddb352fd0f..af2abe74f544 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -87,6 +87,7 @@
 #define BOOK3S_IRQPRIO_MAX			16
 
 #define BOOK3S_HFLAG_DCBZ32			0x1
+#define BOOK3S_HFLAG_SLB			0x2
 
 #define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index c6011336371e..74b7369770d0 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -46,6 +46,7 @@ struct kvmppc_sr {
 };
 
 struct kvmppc_bat {
+	u64 raw;
 	u32 bepi;
 	u32 bepi_mask;
 	bool vs;
@@ -113,6 +114,8 @@ extern struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, boo
 extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr, bool data);
 extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong eaddr, int size, void *ptr);
 extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec);
+extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
+			   bool upper, u32 val);
 
 extern u32 kvmppc_trampoline_lowmem;
 extern u32 kvmppc_trampoline_enter;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 42037d46a416..3e294bd9b8c6 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -281,6 +281,7 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 
 void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 {
+	vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB;
 	vcpu->arch.pvr = pvr;
 	if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
 		kvmppc_mmu_book3s_64_init(vcpu);
@@ -762,14 +763,62 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
                                   struct kvm_sregs *sregs)
 {
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
+	int i;
+
 	sregs->pvr = vcpu->arch.pvr;
+
+	sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1;
+	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
+		for (i = 0; i < 64; i++) {
+			sregs->u.s.ppc64.slb[i].slbe = vcpu3s->slb[i].orige | i;
+			sregs->u.s.ppc64.slb[i].slbv = vcpu3s->slb[i].origv;
+		}
+	} else {
+		for (i = 0; i < 16; i++) {
+			sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw;
+			sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw;
+		}
+		for (i = 0; i < 8; i++) {
+			sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw;
+			sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw;
+		}
+	}
 	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
                                   struct kvm_sregs *sregs)
 {
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
+	int i;
+
 	kvmppc_set_pvr(vcpu, sregs->pvr);
+
+	vcpu3s->sdr1 = sregs->u.s.sdr1;
+	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
+		for (i = 0; i < 64; i++) {
+			vcpu->arch.mmu.slbmte(vcpu, sregs->u.s.ppc64.slb[i].slbv,
+						    sregs->u.s.ppc64.slb[i].slbe);
+		}
+	} else {
+		for (i = 0; i < 16; i++) {
+			vcpu->arch.mmu.mtsrin(vcpu, i, sregs->u.s.ppc32.sr[i]);
+		}
+		for (i = 0; i < 8; i++) {
+			kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), false,
+				       (u32)sregs->u.s.ppc32.ibat[i]);
+			kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), true,
+				       (u32)(sregs->u.s.ppc32.ibat[i] >> 32));
+			kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), false,
+				       (u32)sregs->u.s.ppc32.dbat[i]);
+			kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), true,
+				       (u32)(sregs->u.s.ppc32.dbat[i] >> 32));
+		}
+	}
+
+	/* Flush the MMU after messing with the segments */
+	kvmppc_mmu_pte_flush(vcpu, 0, 0);
 	return 0;
 }
 
diff --git a/arch/powerpc/kvm/book3s_64_emulate.c b/arch/powerpc/kvm/book3s_64_emulate.c
index c343e67306e0..1027eac6d474 100644
--- a/arch/powerpc/kvm/book3s_64_emulate.c
+++ b/arch/powerpc/kvm/book3s_64_emulate.c
@@ -185,7 +185,27 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return emulated;
 }
 
-static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u64 val)
+void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper,
+                    u32 val)
+{
+	if (upper) {
+		/* Upper BAT */
+		u32 bl = (val >> 2) & 0x7ff;
+		bat->bepi_mask = (~bl << 17);
+		bat->bepi = val & 0xfffe0000;
+		bat->vs = (val & 2) ? 1 : 0;
+		bat->vp = (val & 1) ? 1 : 0;
+		bat->raw = (bat->raw & 0xffffffff00000000ULL) | val;
+	} else {
+		/* Lower BAT */
+		bat->brpn = val & 0xfffe0000;
+		bat->wimg = (val >> 3) & 0xf;
+		bat->pp = val & 3;
+		bat->raw = (bat->raw & 0x00000000ffffffffULL) | ((u64)val << 32);
+	}
+}
+
+static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	struct kvmppc_bat *bat;
@@ -207,19 +227,7 @@ static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u64 val)
 		BUG();
 	}
 
-	if (!(sprn % 2)) {
-		/* Upper BAT */
-		u32 bl = (val >> 2) & 0x7ff;
-		bat->bepi_mask = (~bl << 17);
-		bat->bepi = val & 0xfffe0000;
-		bat->vs = (val & 2) ? 1 : 0;
-		bat->vp = (val & 1) ? 1 : 0;
-	} else {
-		/* Lower BAT */
-		bat->brpn = val & 0xfffe0000;
-		bat->wimg = (val >> 3) & 0xf;
-		bat->pp = val & 3;
-	}
+	kvmppc_set_bat(vcpu, bat, !(sprn % 2), val);
 }
 
 int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
@@ -243,7 +251,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_IBAT4U ... SPRN_IBAT7L:
 	case SPRN_DBAT0U ... SPRN_DBAT3L:
 	case SPRN_DBAT4U ... SPRN_DBAT7L:
-		kvmppc_write_bat(vcpu, sprn, vcpu->arch.gpr[rs]);
+		kvmppc_write_bat(vcpu, sprn, (u32)vcpu->arch.gpr[rs]);
 		/* BAT writes happen so rarely that we're ok to flush
 		 * everything here */
 		kvmppc_mmu_pte_flush(vcpu, 0, 0);
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index a31f9c677d23..5598f88f142e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -473,4 +473,6 @@ void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu)
 	mmu->esid_to_vsid = kvmppc_mmu_book3s_64_esid_to_vsid;
 	mmu->ea_to_vp = kvmppc_mmu_book3s_64_ea_to_vp;
 	mmu->is_dcbz32 = kvmppc_mmu_book3s_64_is_dcbz32;
+
+	vcpu->arch.hflags |= BOOK3S_HFLAG_SLB;
 }
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 692c3709011e..d82551efbfbf 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -144,6 +144,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	int r;
 
 	switch (ext) {
+	case KVM_CAP_PPC_SEGSTATE:
+		r = 1;
+		break;
 	case KVM_CAP_COALESCED_MMIO:
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
 		break;
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index f8f8900fc5ec..caf6173bd2e8 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -436,6 +436,9 @@ struct kvm_ioeventfd {
 #endif
 #define KVM_CAP_IOEVENTFD 36
 #define KVM_CAP_SET_IDENTITY_MAP_ADDR 37
+/* KVM upstream has more features, but we synched this number.
+   Linux, please remove this comment on rebase. */
+#define KVM_CAP_PPC_SEGSTATE 43
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

From 7fb19ea054a0cdf1a4d935e68d51bde4d3725414 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 1 Dec 2009 14:36:26 +0000
Subject: [PATCH 122/151] powerpc/macio: Add devres support to macio_device

This adds some basic devres support. When enabled via macio_enable_devres()
resources requested by drivers will be automatically released.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/macio.h |  2 ++
 drivers/macintosh/macio_asic.c   | 47 ++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+)

diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h
index 079c06eae446..2b7b39294a6a 100644
--- a/arch/powerpc/include/asm/macio.h
+++ b/arch/powerpc/include/asm/macio.h
@@ -78,6 +78,8 @@ static inline unsigned long macio_resource_len(struct macio_dev *dev, int resour
 	return res->end - res->start + 1;
 }
 
+extern int macio_enable_devres(struct macio_dev *dev);
+
 extern int macio_request_resource(struct macio_dev *dev, int resource_no, const char *name);
 extern void macio_release_resource(struct macio_dev *dev, int resource_no);
 extern int macio_request_resources(struct macio_dev *dev, const char *name);
diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c
index 588a5b0bc4b5..5200acfc9d38 100644
--- a/drivers/macintosh/macio_asic.c
+++ b/drivers/macintosh/macio_asic.c
@@ -538,6 +538,42 @@ void macio_unregister_driver(struct macio_driver *drv)
 	driver_unregister(&drv->driver);
 }
 
+/* Managed MacIO resources */
+struct macio_devres {
+	u32	res_mask;
+};
+
+static void maciom_release(struct device *gendev, void *res)
+{
+	struct macio_dev *dev = to_macio_device(gendev);
+	struct macio_devres *dr = res;
+	int i, max;
+
+	max = min(dev->n_resources, 32);
+	for (i = 0; i < max; i++) {
+		if (dr->res_mask & (1 << i))
+			macio_release_resource(dev, i);
+	}
+}
+
+int macio_enable_devres(struct macio_dev *dev)
+{
+	struct macio_devres *dr;
+
+	dr = devres_find(&dev->ofdev.dev, maciom_release, NULL, NULL);
+	if (!dr) {
+		dr = devres_alloc(maciom_release, sizeof(*dr), GFP_KERNEL);
+		if (!dr)
+			return -ENOMEM;
+	}
+	return devres_get(&dev->ofdev.dev, dr, NULL, NULL) != NULL;
+}
+
+static struct macio_devres * find_macio_dr(struct macio_dev *dev)
+{
+	return devres_find(&dev->ofdev.dev, maciom_release, NULL, NULL);
+}
+
 /**
  *	macio_request_resource - Request an MMIO resource
  * 	@dev: pointer to the device holding the resource
@@ -555,6 +591,8 @@ void macio_unregister_driver(struct macio_driver *drv)
 int macio_request_resource(struct macio_dev *dev, int resource_no,
 			   const char *name)
 {
+	struct macio_devres *dr = find_macio_dr(dev);
+
 	if (macio_resource_len(dev, resource_no) == 0)
 		return 0;
 		
@@ -562,6 +600,9 @@ int macio_request_resource(struct macio_dev *dev, int resource_no,
 				macio_resource_len(dev, resource_no),
 				name))
 		goto err_out;
+
+	if (dr && resource_no < 32)
+		dr->res_mask |= 1 << resource_no;
 	
 	return 0;
 
@@ -582,10 +623,14 @@ err_out:
  */
 void macio_release_resource(struct macio_dev *dev, int resource_no)
 {
+	struct macio_devres *dr = find_macio_dr(dev);
+
 	if (macio_resource_len(dev, resource_no) == 0)
 		return;
 	release_mem_region(macio_resource_start(dev, resource_no),
 			   macio_resource_len(dev, resource_no));
+	if (dr && resource_no < 32)
+		dr->res_mask &= ~(1 << resource_no);
 }
 
 /**
@@ -744,3 +789,5 @@ EXPORT_SYMBOL(macio_request_resource);
 EXPORT_SYMBOL(macio_release_resource);
 EXPORT_SYMBOL(macio_request_resources);
 EXPORT_SYMBOL(macio_release_resources);
+EXPORT_SYMBOL(macio_enable_devres);
+

From 128b4a0ef74e8d48033513e41a413087ba30e36b Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 1 Dec 2009 14:36:27 +0000
Subject: [PATCH 123/151] powerpc/macio: Add dma_parms support to macio

This adds dma_parms to macio devices and initializes them with
default values. This will allow pata_macio to setup the appropriate
max segment size for the block layer.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/macio.h | 1 +
 drivers/macintosh/macio_asic.c   | 5 +++++
 2 files changed, 6 insertions(+)

diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h
index 2b7b39294a6a..86d5fed1c49f 100644
--- a/arch/powerpc/include/asm/macio.h
+++ b/arch/powerpc/include/asm/macio.h
@@ -39,6 +39,7 @@ struct macio_dev
 	struct macio_bus	*bus;		/* macio bus this device is on */
 	struct macio_dev	*media_bay;	/* Device is part of a media bay */
 	struct of_device	ofdev;
+	struct device_dma_parameters dma_parms; /* ide needs that */
 	int			n_resources;
 	struct resource		resource[MACIO_DEV_COUNT_RESOURCES];
 	int			n_interrupts;
diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c
index 5200acfc9d38..26a303a1d1ab 100644
--- a/drivers/macintosh/macio_asic.c
+++ b/drivers/macintosh/macio_asic.c
@@ -379,6 +379,11 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
 	dev->ofdev.dev.parent = parent;
 	dev->ofdev.dev.bus = &macio_bus_type;
 	dev->ofdev.dev.release = macio_release_dev;
+	dev->ofdev.dev.dma_parms = &dev->dma_parms;
+
+	/* Standard DMA paremeters */
+	dma_set_max_seg_size(&dev->ofdev.dev, 65536);
+	dma_set_seg_boundary(&dev->ofdev.dev, 0xffffffff);
 
 #ifdef CONFIG_PCI
 	/* Set the DMA ops to the ones from the PCI device, this could be

From 6d5355998a757a16815d58da4a739b15a6efbfba Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Albrecht=20Dre=C3=9F?= <albrecht.dress@arcor.de>
Date: Fri, 13 Nov 2009 18:09:31 -0700
Subject: [PATCH 124/151] mpc52xx/wdt: remove obsolete old WDT implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the old WDT implementation.

Signed-off-by: Albrecht Dreß <albrecht.dress@arcor.de>
Acked-by: Wim Van Sebroeck <wim@iguana.be>
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
---
 drivers/watchdog/Kconfig       |   4 +-
 drivers/watchdog/Makefile      |   1 -
 drivers/watchdog/mpc5200_wdt.c | 293 ---------------------------------
 3 files changed, 3 insertions(+), 295 deletions(-)
 delete mode 100644 drivers/watchdog/mpc5200_wdt.c

diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 3711b888d482..d958b76430a2 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -861,8 +861,10 @@ config GEF_WDT
 	  Watchdog timer found in a number of GE Fanuc single board computers.
 
 config MPC5200_WDT
-	tristate "MPC5200 Watchdog Timer"
+	bool "MPC52xx Watchdog Timer"
 	depends on PPC_MPC52xx
+	help
+	  Use General Purpose Timer (GPT) 0 on the MPC5200 as Watchdog.
 
 config 8xxx_WDT
 	tristate "MPC8xxx Platform Watchdog Timer"
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index 699199b1baa6..89c045dc468e 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -118,7 +118,6 @@ obj-$(CONFIG_TXX9_WDT) += txx9wdt.o
 
 # POWERPC Architecture
 obj-$(CONFIG_GEF_WDT) += gef_wdt.o
-obj-$(CONFIG_MPC5200_WDT) += mpc5200_wdt.o
 obj-$(CONFIG_8xxx_WDT) += mpc8xxx_wdt.o
 obj-$(CONFIG_MV64X60_WDT) += mv64x60_wdt.o
 obj-$(CONFIG_PIKA_WDT) += pika_wdt.o
diff --git a/drivers/watchdog/mpc5200_wdt.c b/drivers/watchdog/mpc5200_wdt.c
deleted file mode 100644
index fa9c47ce0ae7..000000000000
--- a/drivers/watchdog/mpc5200_wdt.c
+++ /dev/null
@@ -1,293 +0,0 @@
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/miscdevice.h>
-#include <linux/watchdog.h>
-#include <linux/io.h>
-#include <linux/spinlock.h>
-#include <linux/of_platform.h>
-#include <linux/uaccess.h>
-#include <asm/mpc52xx.h>
-
-
-#define GPT_MODE_WDT		(1 << 15)
-#define GPT_MODE_CE		(1 << 12)
-#define GPT_MODE_MS_TIMER	(0x4)
-
-
-struct mpc5200_wdt {
-	unsigned count;	/* timer ticks before watchdog kicks in */
-	long ipb_freq;
-	struct miscdevice miscdev;
-	struct resource mem;
-	struct mpc52xx_gpt __iomem *regs;
-	spinlock_t io_lock;
-};
-
-/* is_active stores wether or not the /dev/watchdog device is opened */
-static unsigned long is_active;
-
-/* misc devices don't provide a way, to get back to 'dev' or 'miscdev' from
- * file operations, which sucks. But there can be max 1 watchdog anyway, so...
- */
-static struct mpc5200_wdt *wdt_global;
-
-
-/* helper to calculate timeout in timer counts */
-static void mpc5200_wdt_set_timeout(struct mpc5200_wdt *wdt, int timeout)
-{
-	/* use biggest prescaler of 64k */
-	wdt->count = (wdt->ipb_freq + 0xffff) / 0x10000 * timeout;
-
-	if (wdt->count > 0xffff)
-		wdt->count = 0xffff;
-}
-/* return timeout in seconds (calculated from timer count) */
-static int mpc5200_wdt_get_timeout(struct mpc5200_wdt *wdt)
-{
-	return wdt->count * 0x10000 / wdt->ipb_freq;
-}
-
-
-/* watchdog operations */
-static int mpc5200_wdt_start(struct mpc5200_wdt *wdt)
-{
-	spin_lock(&wdt->io_lock);
-	/* disable */
-	out_be32(&wdt->regs->mode, 0);
-	/* set timeout, with maximum prescaler */
-	out_be32(&wdt->regs->count, 0x0 | wdt->count);
-	/* enable watchdog */
-	out_be32(&wdt->regs->mode, GPT_MODE_CE | GPT_MODE_WDT |
-						GPT_MODE_MS_TIMER);
-	spin_unlock(&wdt->io_lock);
-
-	return 0;
-}
-static int mpc5200_wdt_ping(struct mpc5200_wdt *wdt)
-{
-	spin_lock(&wdt->io_lock);
-	/* writing A5 to OCPW resets the watchdog */
-	out_be32(&wdt->regs->mode, 0xA5000000 |
-				(0xffffff & in_be32(&wdt->regs->mode)));
-	spin_unlock(&wdt->io_lock);
-	return 0;
-}
-static int mpc5200_wdt_stop(struct mpc5200_wdt *wdt)
-{
-	spin_lock(&wdt->io_lock);
-	/* disable */
-	out_be32(&wdt->regs->mode, 0);
-	spin_unlock(&wdt->io_lock);
-	return 0;
-}
-
-
-/* file operations */
-static ssize_t mpc5200_wdt_write(struct file *file, const char __user *data,
-		size_t len, loff_t *ppos)
-{
-	struct mpc5200_wdt *wdt = file->private_data;
-	mpc5200_wdt_ping(wdt);
-	return 0;
-}
-static struct watchdog_info mpc5200_wdt_info = {
-	.options	= WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING,
-	.identity	= "mpc5200 watchdog on GPT0",
-};
-static long mpc5200_wdt_ioctl(struct file *file, unsigned int cmd,
-							unsigned long arg)
-{
-	struct mpc5200_wdt *wdt = file->private_data;
-	int __user *data = (int __user *)arg;
-	int timeout;
-	int ret = 0;
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		ret = copy_to_user(data, &mpc5200_wdt_info,
-						sizeof(mpc5200_wdt_info));
-		if (ret)
-			ret = -EFAULT;
-		break;
-
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		ret = put_user(0, data);
-		break;
-
-	case WDIOC_KEEPALIVE:
-		mpc5200_wdt_ping(wdt);
-		break;
-
-	case WDIOC_SETTIMEOUT:
-		ret = get_user(timeout, data);
-		if (ret)
-			break;
-		mpc5200_wdt_set_timeout(wdt, timeout);
-		mpc5200_wdt_start(wdt);
-		/* fall through and return the timeout */
-
-	case WDIOC_GETTIMEOUT:
-		timeout = mpc5200_wdt_get_timeout(wdt);
-		ret = put_user(timeout, data);
-		break;
-
-	default:
-		ret = -ENOTTY;
-	}
-	return ret;
-}
-
-static int mpc5200_wdt_open(struct inode *inode, struct file *file)
-{
-	/* /dev/watchdog can only be opened once */
-	if (test_and_set_bit(0, &is_active))
-		return -EBUSY;
-
-	/* Set and activate the watchdog */
-	mpc5200_wdt_set_timeout(wdt_global, 30);
-	mpc5200_wdt_start(wdt_global);
-	file->private_data = wdt_global;
-	return nonseekable_open(inode, file);
-}
-static int mpc5200_wdt_release(struct inode *inode, struct file *file)
-{
-#if WATCHDOG_NOWAYOUT == 0
-	struct mpc5200_wdt *wdt = file->private_data;
-	mpc5200_wdt_stop(wdt);
-	wdt->count = 0;		/* == disabled */
-#endif
-	clear_bit(0, &is_active);
-	return 0;
-}
-
-static const struct file_operations mpc5200_wdt_fops = {
-	.owner	= THIS_MODULE,
-	.write	= mpc5200_wdt_write,
-	.unlocked_ioctl	= mpc5200_wdt_ioctl,
-	.open	= mpc5200_wdt_open,
-	.release = mpc5200_wdt_release,
-};
-
-/* module operations */
-static int mpc5200_wdt_probe(struct of_device *op,
-					const struct of_device_id *match)
-{
-	struct mpc5200_wdt *wdt;
-	int err;
-	const void *has_wdt;
-	int size;
-
-	has_wdt = of_get_property(op->node, "has-wdt", NULL);
-	if (!has_wdt)
-		has_wdt = of_get_property(op->node, "fsl,has-wdt", NULL);
-	if (!has_wdt)
-		return -ENODEV;
-
-	wdt = kzalloc(sizeof(*wdt), GFP_KERNEL);
-	if (!wdt)
-		return -ENOMEM;
-
-	wdt->ipb_freq = mpc5xxx_get_bus_frequency(op->node);
-
-	err = of_address_to_resource(op->node, 0, &wdt->mem);
-	if (err)
-		goto out_free;
-	size = wdt->mem.end - wdt->mem.start + 1;
-	if (!request_mem_region(wdt->mem.start, size, "mpc5200_wdt")) {
-		err = -ENODEV;
-		goto out_free;
-	}
-	wdt->regs = ioremap(wdt->mem.start, size);
-	if (!wdt->regs) {
-		err = -ENODEV;
-		goto out_release;
-	}
-
-	dev_set_drvdata(&op->dev, wdt);
-	spin_lock_init(&wdt->io_lock);
-
-	wdt->miscdev = (struct miscdevice) {
-		.minor	= WATCHDOG_MINOR,
-		.name	= "watchdog",
-		.fops	= &mpc5200_wdt_fops,
-		.parent = &op->dev,
-	};
-	wdt_global = wdt;
-	err = misc_register(&wdt->miscdev);
-	if (!err)
-		return 0;
-
-	iounmap(wdt->regs);
-out_release:
-	release_mem_region(wdt->mem.start, size);
-out_free:
-	kfree(wdt);
-	return err;
-}
-
-static int mpc5200_wdt_remove(struct of_device *op)
-{
-	struct mpc5200_wdt *wdt = dev_get_drvdata(&op->dev);
-
-	mpc5200_wdt_stop(wdt);
-	misc_deregister(&wdt->miscdev);
-	iounmap(wdt->regs);
-	release_mem_region(wdt->mem.start, wdt->mem.end - wdt->mem.start + 1);
-	kfree(wdt);
-
-	return 0;
-}
-static int mpc5200_wdt_suspend(struct of_device *op, pm_message_t state)
-{
-	struct mpc5200_wdt *wdt = dev_get_drvdata(&op->dev);
-	mpc5200_wdt_stop(wdt);
-	return 0;
-}
-static int mpc5200_wdt_resume(struct of_device *op)
-{
-	struct mpc5200_wdt *wdt = dev_get_drvdata(&op->dev);
-	if (wdt->count)
-		mpc5200_wdt_start(wdt);
-	return 0;
-}
-static int mpc5200_wdt_shutdown(struct of_device *op)
-{
-	struct mpc5200_wdt *wdt = dev_get_drvdata(&op->dev);
-	mpc5200_wdt_stop(wdt);
-	return 0;
-}
-
-static struct of_device_id mpc5200_wdt_match[] = {
-	{ .compatible = "mpc5200-gpt", },
-	{ .compatible = "fsl,mpc5200-gpt", },
-	{},
-};
-static struct of_platform_driver mpc5200_wdt_driver = {
-	.owner		= THIS_MODULE,
-	.name		= "mpc5200-gpt-wdt",
-	.match_table	= mpc5200_wdt_match,
-	.probe		= mpc5200_wdt_probe,
-	.remove		= mpc5200_wdt_remove,
-	.suspend	= mpc5200_wdt_suspend,
-	.resume		= mpc5200_wdt_resume,
-	.shutdown	= mpc5200_wdt_shutdown,
-};
-
-
-static int __init mpc5200_wdt_init(void)
-{
-	return of_register_platform_driver(&mpc5200_wdt_driver);
-}
-
-static void __exit mpc5200_wdt_exit(void)
-{
-	of_unregister_platform_driver(&mpc5200_wdt_driver);
-}
-
-module_init(mpc5200_wdt_init);
-module_exit(mpc5200_wdt_exit);
-
-MODULE_AUTHOR("Domen Puncer <domen.puncer@telargo.com>");
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);

From d58b0c39e32f1b410af4d070f9d1a1416057c166 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 1 Dec 2009 14:36:28 +0000
Subject: [PATCH 125/151] powerpc/macio: Rework hotplug media bay support

The hotplug mediabay has tendrils deep into drivers/ide code
which makes a libata port reather difficult. In addition it's
ugly and could be done better.

This reworks the interface between the mediabay and the rest
of the world so that:

   - Any macio_driver can now have a mediabay_event callback
which will be called when that driver sits on a mediabay and
it's been either plugged or unplugged. The device type is
passed as an argument. We can now move all the IDE cruft
into the IDE driver itself

   - A check_media_bay() function can be used to take a peek
at the type of device currently in the bay if any, a cleaner
variant of the previous function with the same name.

   - A pair of lock/unlock functions are exposed to allow the
IDE driver to block the hotplug callbacks during the initial
setup and probing of the bay in order to avoid nasty race
conditions.

   - The mediabay code no longer needs to spin on the status
register of the IDE interface when it detects an IDE device,
this is done just fine by the IDE code itself

Overall, less code, simpler, and allows for another driver
than our old drivers/ide based one.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/macio.h    |   3 +
 arch/powerpc/include/asm/mediabay.h |  27 ++-
 drivers/block/swim3.c               |  39 ++--
 drivers/ide/pmac.c                  |  94 +++++---
 drivers/macintosh/mediabay.c        | 330 +++++++++++-----------------
 5 files changed, 216 insertions(+), 277 deletions(-)

diff --git a/arch/powerpc/include/asm/macio.h b/arch/powerpc/include/asm/macio.h
index 86d5fed1c49f..a062c57696d0 100644
--- a/arch/powerpc/include/asm/macio.h
+++ b/arch/powerpc/include/asm/macio.h
@@ -134,6 +134,9 @@ struct macio_driver
 	int	(*resume)(struct macio_dev* dev);
 	int	(*shutdown)(struct macio_dev* dev);
 
+#ifdef CONFIG_PMAC_MEDIABAY
+	void	(*mediabay_event)(struct macio_dev* dev, int mb_state);
+#endif
 	struct device_driver	driver;
 };
 #define	to_macio_driver(drv) container_of(drv,struct macio_driver, driver)
diff --git a/arch/powerpc/include/asm/mediabay.h b/arch/powerpc/include/asm/mediabay.h
index b2efb3325808..11037a4133ee 100644
--- a/arch/powerpc/include/asm/mediabay.h
+++ b/arch/powerpc/include/asm/mediabay.h
@@ -17,26 +17,31 @@
 #define MB_POWER	6	/* media bay contains a Power device (???) */
 #define MB_NO		7	/* media bay contains nothing */
 
-/* Number of bays in the machine or 0 */
-extern int media_bay_count;
+struct macio_dev;
 
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
-#include <linux/ide.h>
+#ifdef CONFIG_PMAC_MEDIABAY
 
-int check_media_bay_by_base(unsigned long base, int what);
-/* called by IDE PMAC host driver to register IDE controller for media bay */
-int media_bay_set_ide_infos(struct device_node *which_bay, unsigned long base,
-			    int irq, ide_hwif_t *hwif);
+/* Check the content type of the bay, returns MB_NO if the bay is still
+ * transitionning
+ */
+extern int check_media_bay(struct macio_dev *bay);
 
-int check_media_bay(struct device_node *which_bay, int what);
+/* The ATA driver uses the calls below to temporarily hold on the
+ * media bay callbacks while initializing the interface
+ */
+extern void lock_media_bay(struct macio_dev *bay);
+extern void unlock_media_bay(struct macio_dev *bay);
 
 #else
 
-static inline int check_media_bay(struct device_node *which_bay, int what)
+static inline int check_media_bay(struct macio_dev *bay)
 {
-	return -ENODEV;
+	return MB_NO;
 }
 
+static inline void lock_media_bay(struct macio_dev *bay) { }
+static inline void unlock_media_bay(struct macio_dev *bay) { }
+
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 6380ad8d91bd..59ca2b77b574 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -200,7 +200,7 @@ struct floppy_state {
 	int	ejected;
 	wait_queue_head_t wait;
 	int	wanted;
-	struct device_node*	media_bay; /* NULL when not in bay */
+	struct macio_dev *mdev;
 	char	dbdma_cmd_space[5 * sizeof(struct dbdma_cmd)];
 };
 
@@ -303,14 +303,13 @@ static int swim3_readbit(struct floppy_state *fs, int bit)
 static void do_fd_request(struct request_queue * q)
 {
 	int i;
-	for(i=0;i<floppy_count;i++)
-	{
-#ifdef CONFIG_PMAC_MEDIABAY
-		if (floppy_states[i].media_bay &&
-			check_media_bay(floppy_states[i].media_bay, MB_FD))
+
+	for(i=0; i<floppy_count; i++) {
+		struct floppy_state *fs = &floppy_states[i];
+		if (fs->mdev->media_bay &&
+		    check_media_bay(fs->mdev->media_bay) != MB_FD)
 			continue;
-#endif /* CONFIG_PMAC_MEDIABAY */
-		start_request(&floppy_states[i]);
+		start_request(fs);
 	}
 }
 
@@ -849,10 +848,9 @@ static int floppy_ioctl(struct block_device *bdev, fmode_t mode,
 	if ((cmd & 0x80) && !capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-#ifdef CONFIG_PMAC_MEDIABAY
-	if (fs->media_bay && check_media_bay(fs->media_bay, MB_FD))
+	if (fs->mdev->media_bay &&
+	    check_media_bay(fs->mdev->media_bay) != MB_FD)
 		return -ENXIO;
-#endif
 
 	switch (cmd) {
 	case FDEJECT:
@@ -876,10 +874,9 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
 	int n, err = 0;
 
 	if (fs->ref_count == 0) {
-#ifdef CONFIG_PMAC_MEDIABAY
-		if (fs->media_bay && check_media_bay(fs->media_bay, MB_FD))
+		if (fs->mdev->media_bay &&
+		    check_media_bay(fs->mdev->media_bay) != MB_FD)
 			return -ENXIO;
-#endif
 		out_8(&sw->setup, S_IBM_DRIVE | S_FCLK_DIV2);
 		out_8(&sw->control_bic, 0xff);
 		out_8(&sw->mode, 0x95);
@@ -963,10 +960,9 @@ static int floppy_revalidate(struct gendisk *disk)
 	struct swim3 __iomem *sw;
 	int ret, n;
 
-#ifdef CONFIG_PMAC_MEDIABAY
-	if (fs->media_bay && check_media_bay(fs->media_bay, MB_FD))
+	if (fs->mdev->media_bay &&
+	    check_media_bay(fs->mdev->media_bay) != MB_FD)
 		return -ENXIO;
-#endif
 
 	sw = fs->swim3;
 	grab_drive(fs, revalidating, 0);
@@ -1009,7 +1005,6 @@ static const struct block_device_operations floppy_fops = {
 static int swim3_add_device(struct macio_dev *mdev, int index)
 {
 	struct device_node *swim = mdev->ofdev.node;
-	struct device_node *mediabay;
 	struct floppy_state *fs = &floppy_states[index];
 	int rc = -EBUSY;
 
@@ -1036,9 +1031,7 @@ static int swim3_add_device(struct macio_dev *mdev, int index)
 	}
 	dev_set_drvdata(&mdev->ofdev.dev, fs);
 
-	mediabay = (strcasecmp(swim->parent->type, "media-bay") == 0) ?
-		swim->parent : NULL;
-	if (mediabay == NULL)
+	if (mdev->media_bay == NULL)
 		pmac_call_feature(PMAC_FTR_SWIM3_ENABLE, swim, 0, 1);
 	
 	memset(fs, 0, sizeof(*fs));
@@ -1068,7 +1061,7 @@ static int swim3_add_device(struct macio_dev *mdev, int index)
 	fs->secpercyl = 36;
 	fs->secpertrack = 18;
 	fs->total_secs = 2880;
-	fs->media_bay = mediabay;
+	fs->mdev = mdev;
 	init_waitqueue_head(&fs->wait);
 
 	fs->dma_cmd = (struct dbdma_cmd *) DBDMA_ALIGN(fs->dbdma_cmd_space);
@@ -1093,7 +1086,7 @@ static int swim3_add_device(struct macio_dev *mdev, int index)
 	init_timer(&fs->timeout);
 
 	printk(KERN_INFO "fd%d: SWIM3 floppy controller %s\n", floppy_count,
-		mediabay ? "in media bay" : "");
+		mdev->media_bay ? "in media bay" : "");
 
 	return 0;
 
diff --git a/drivers/ide/pmac.c b/drivers/ide/pmac.c
index 97642a7a79c4..7a4e788cab2f 100644
--- a/drivers/ide/pmac.c
+++ b/drivers/ide/pmac.c
@@ -43,10 +43,7 @@
 #include <asm/pmac_feature.h>
 #include <asm/sections.h>
 #include <asm/irq.h>
-
-#ifndef CONFIG_PPC64
 #include <asm/mediabay.h>
-#endif
 
 #define DRV_NAME "ide-pmac"
 
@@ -59,13 +56,14 @@ typedef struct pmac_ide_hwif {
 	int				irq;
 	int				kind;
 	int				aapl_bus_id;
-	unsigned			mediabay : 1;
 	unsigned			broken_dma : 1;
 	unsigned			broken_dma_warn : 1;
 	struct device_node*		node;
 	struct macio_dev		*mdev;
 	u32				timings[4];
 	volatile u32 __iomem *		*kauai_fcr;
+	ide_hwif_t			*hwif;
+
 	/* Those fields are duplicating what is in hwif. We currently
 	 * can't use the hwif ones because of some assumptions that are
 	 * beeing done by the generic code about the kind of dma controller
@@ -854,6 +852,11 @@ sanitize_timings(pmac_ide_hwif_t *pmif)
 	pmif->timings[2] = pmif->timings[3] = value2;
 }
 
+static int on_media_bay(pmac_ide_hwif_t *pmif)
+{
+	return pmif->mdev && pmif->mdev->media_bay != NULL;
+}
+
 /* Suspend call back, should be called after the child devices
  * have actually been suspended
  */
@@ -866,7 +869,7 @@ static int pmac_ide_do_suspend(pmac_ide_hwif_t *pmif)
 	disable_irq(pmif->irq);
 
 	/* The media bay will handle itself just fine */
-	if (pmif->mediabay)
+	if (on_media_bay(pmif))
 		return 0;
 	
 	/* Kauai has bus control FCRs directly here */
@@ -889,7 +892,7 @@ static int pmac_ide_do_suspend(pmac_ide_hwif_t *pmif)
 static int pmac_ide_do_resume(pmac_ide_hwif_t *pmif)
 {
 	/* Hard reset & re-enable controller (do we really need to reset ? -BenH) */
-	if (!pmif->mediabay) {
+	if (!on_media_bay(pmif)) {
 		ppc_md.feature_call(PMAC_FTR_IDE_RESET, pmif->node, pmif->aapl_bus_id, 1);
 		ppc_md.feature_call(PMAC_FTR_IDE_ENABLE, pmif->node, pmif->aapl_bus_id, 1);
 		msleep(10);
@@ -950,13 +953,11 @@ static void pmac_ide_init_dev(ide_drive_t *drive)
 	pmac_ide_hwif_t *pmif =
 		(pmac_ide_hwif_t *)dev_get_drvdata(hwif->gendev.parent);
 
-	if (pmif->mediabay) {
-#ifdef CONFIG_PMAC_MEDIABAY
-		if (check_media_bay_by_base(pmif->regbase, MB_CD) == 0) {
+	if (on_media_bay(pmif)) {
+		if (check_media_bay(pmif->mdev->media_bay) == MB_CD) {
 			drive->dev_flags &= ~IDE_DFLAG_NOPROBE;
 			return;
 		}
-#endif
 		drive->dev_flags |= IDE_DFLAG_NOPROBE;
 	}
 }
@@ -1072,26 +1073,23 @@ static int __devinit pmac_ide_setup_device(pmac_ide_hwif_t *pmif,
 		writel(KAUAI_FCR_UATA_MAGIC |
 		       KAUAI_FCR_UATA_RESET_N |
 		       KAUAI_FCR_UATA_ENABLE, pmif->kauai_fcr);
-
-	pmif->mediabay = 0;
 	
 	/* Make sure we have sane timings */
 	sanitize_timings(pmif);
 
-	host = ide_host_alloc(&d, hws, 1);
-	if (host == NULL)
-		return -ENOMEM;
-	hwif = host->ports[0];
+	/* If we are on a media bay, wait for it to settle and lock it */
+	if (pmif->mdev)
+		lock_media_bay(pmif->mdev->media_bay);
 
-#ifndef CONFIG_PPC64
-	/* XXX FIXME: Media bay stuff need re-organizing */
-	if (np->parent && np->parent->name
-	    && strcasecmp(np->parent->name, "media-bay") == 0) {
-#ifdef CONFIG_PMAC_MEDIABAY
-		media_bay_set_ide_infos(np->parent, pmif->regbase, pmif->irq,
-					hwif);
-#endif /* CONFIG_PMAC_MEDIABAY */
-		pmif->mediabay = 1;
+	host = ide_host_alloc(&d, hws, 1);
+	if (host == NULL) {
+		rc = -ENOMEM;
+		goto bail;
+	}
+	hwif = pmif->hwif = host->ports[0];
+
+	if (on_media_bay(pmif)) {
+		/* Fixup bus ID for media bay */
 		if (!bidp)
 			pmif->aapl_bus_id = 1;
 	} else if (pmif->kind == controller_ohare) {
@@ -1100,9 +1098,7 @@ static int __devinit pmac_ide_setup_device(pmac_ide_hwif_t *pmif,
 		 * units, I keep the old way
 		 */
 		ppc_md.feature_call(PMAC_FTR_IDE_ENABLE, np, 0, 1);
-	} else
-#endif
-	{
+	} else {
  		/* This is necessary to enable IDE when net-booting */
 		ppc_md.feature_call(PMAC_FTR_IDE_RESET, np, pmif->aapl_bus_id, 1);
 		ppc_md.feature_call(PMAC_FTR_IDE_ENABLE, np, pmif->aapl_bus_id, 1);
@@ -1112,17 +1108,21 @@ static int __devinit pmac_ide_setup_device(pmac_ide_hwif_t *pmif,
 	}
 
 	printk(KERN_INFO DRV_NAME ": Found Apple %s controller (%s), "
-			 "bus ID %d%s, irq %d\n", model_name[pmif->kind],
-			 pmif->mdev ? "macio" : "PCI", pmif->aapl_bus_id,
-			 pmif->mediabay ? " (mediabay)" : "", hw->irq);
+	       "bus ID %d%s, irq %d\n", model_name[pmif->kind],
+	       pmif->mdev ? "macio" : "PCI", pmif->aapl_bus_id,
+	       on_media_bay(pmif) ? " (mediabay)" : "", hw->irq);
 
 	rc = ide_host_register(host, &d, hws);
-	if (rc) {
-		ide_host_free(host);
-		return rc;
-	}
+	if (rc)
+		pmif->hwif = NULL;
 
-	return 0;
+	if (pmif->mdev)
+		unlock_media_bay(pmif->mdev->media_bay);
+
+ bail:
+	if (rc && host)
+		ide_host_free(host);
+	return rc;
 }
 
 static void __devinit pmac_ide_init_ports(struct ide_hw *hw, unsigned long base)
@@ -1362,6 +1362,25 @@ pmac_ide_pci_resume(struct pci_dev *pdev)
 	return rc;
 }
 
+#ifdef CONFIG_PMAC_MEDIABAY
+static void pmac_ide_macio_mb_event(struct macio_dev* mdev, int mb_state)
+{
+	pmac_ide_hwif_t *pmif =
+		(pmac_ide_hwif_t *)dev_get_drvdata(&mdev->ofdev.dev);
+
+	switch(mb_state) {
+	case MB_CD:
+		if (!pmif->hwif->present)
+			ide_port_scan(pmif->hwif);
+		break;
+	default:
+		if (pmif->hwif->present)
+			ide_port_unregister_devices(pmif->hwif);
+	}
+}
+#endif /* CONFIG_PMAC_MEDIABAY */
+
+
 static struct of_device_id pmac_ide_macio_match[] = 
 {
 	{
@@ -1386,6 +1405,9 @@ static struct macio_driver pmac_ide_macio_driver =
 	.probe		= pmac_ide_macio_attach,
 	.suspend	= pmac_ide_macio_suspend,
 	.resume		= pmac_ide_macio_resume,
+#ifdef CONFIG_PMAC_MEDIABAY
+	.mediabay_event	= pmac_ide_macio_mb_event,
+#endif
 };
 
 static const struct pci_device_id pmac_ide_pci_match[] = {
diff --git a/drivers/macintosh/mediabay.c b/drivers/macintosh/mediabay.c
index 029ad8ce8a7e..08002b88f342 100644
--- a/drivers/macintosh/mediabay.c
+++ b/drivers/macintosh/mediabay.c
@@ -33,15 +33,6 @@
 #include <linux/adb.h>
 #include <linux/pmu.h>
 
-
-#define MB_DEBUG
-
-#ifdef MB_DEBUG
-#define MBDBG(fmt, arg...)	printk(KERN_INFO fmt , ## arg)
-#else
-#define MBDBG(fmt, arg...)	do { } while (0)
-#endif
-
 #define MB_FCR32(bay, r)	((bay)->base + ((r) >> 2))
 #define MB_FCR8(bay, r)		(((volatile u8 __iomem *)((bay)->base)) + (r))
 
@@ -76,28 +67,14 @@ struct media_bay_info {
 	int				index;
 	int				cached_gpio;
 	int				sleeping;
+	int				user_lock;
 	struct mutex			lock;
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
-	ide_hwif_t			*cd_port;
-	void __iomem			*cd_base;
-	int				cd_irq;
-	int				cd_retry;
-#endif
-#if defined(CONFIG_BLK_DEV_IDE_PMAC)
-	int 				cd_index;
-#endif
 };
 
 #define MAX_BAYS	2
 
 static struct media_bay_info media_bays[MAX_BAYS];
-int media_bay_count = 0;
-
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
-/* check the busy bit in the media-bay ide interface
-   (assumes the media-bay contains an ide device) */
-#define MB_IDE_READY(i)	((readb(media_bays[i].cd_base + 0x70) & 0x80) == 0)
-#endif
+static int media_bay_count = 0;
 
 /*
  * Wait that number of ms between each step in normal polling mode
@@ -130,20 +107,10 @@ int media_bay_count = 0;
 
 /*
  * Wait this many ticks after an IDE device (e.g. CD-ROM) is inserted
- * (or until the device is ready) before waiting for busy bit to disappear
+ * (or until the device is ready) before calling into the driver
  */
 #define MB_IDE_WAIT	1000
 
-/*
- * Timeout waiting for busy bit of an IDE device to go down
- */
-#define MB_IDE_TIMEOUT	5000
-
-/*
- * Max retries of the full power up/down sequence for an IDE device
- */
-#define MAX_CD_RETRIES	3
-
 /*
  * States of a media bay
  */
@@ -153,7 +120,6 @@ enum {
 	mb_enabling_bay,	/* enable bits set, waiting MB_RESET_DELAY */
 	mb_resetting,		/* reset bit unset, waiting MB_SETUP_DELAY */
 	mb_ide_resetting,	/* IDE reset bit unser, waiting MB_IDE_WAIT */
-	mb_ide_waiting,		/* Waiting for BUSY bit to go away until MB_IDE_TIMEOUT */
 	mb_up,			/* Media bay full */
 	mb_powering_down	/* Powering down (avoid too fast down/up) */
 };
@@ -373,12 +339,12 @@ static inline void set_mb_power(struct media_bay_info* bay, int onoff)
 	if (onoff) {
 		bay->ops->power(bay, 1);
 		bay->state = mb_powering_up;
-		MBDBG("mediabay%d: powering up\n", bay->index);
+		pr_debug("mediabay%d: powering up\n", bay->index);
 	} else { 
 		/* Make sure everything is powered down & disabled */
 		bay->ops->power(bay, 0);
 		bay->state = mb_powering_down;
-		MBDBG("mediabay%d: powering down\n", bay->index);
+		pr_debug("mediabay%d: powering down\n", bay->index);
 	}
 	bay->timer = msecs_to_jiffies(MB_POWER_DELAY);
 }
@@ -387,107 +353,118 @@ static void poll_media_bay(struct media_bay_info* bay)
 {
 	int id = bay->ops->content(bay);
 
-	if (id == bay->last_value) {
-		if (id != bay->content_id) {
-			bay->value_count += msecs_to_jiffies(MB_POLL_DELAY);
-			if (bay->value_count >= msecs_to_jiffies(MB_STABLE_DELAY)) {
-				/* If the device type changes without going thru
-				 * "MB_NO", we force a pass by "MB_NO" to make sure
-				 * things are properly reset
-				 */
-				if ((id != MB_NO) && (bay->content_id != MB_NO)) {
-					id = MB_NO;
-					MBDBG("mediabay%d: forcing MB_NO\n", bay->index);
-				}
-				MBDBG("mediabay%d: switching to %d\n", bay->index, id);
-				set_mb_power(bay, id != MB_NO);
-				bay->content_id = id;
-				if (id == MB_NO) {
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
-					bay->cd_retry = 0;
-#endif
-					printk(KERN_INFO "media bay %d is empty\n", bay->index);
-				}
-			}
-		}
-	} else {
+	static char *mb_content_types[] = {
+		"a floppy drive",
+		"a floppy drive",
+		"an unsuported audio device",
+		"an ATA device",
+		"an unsupported PCI device",
+		"an unknown device",
+	};
+
+	if (id != bay->last_value) {
 		bay->last_value = id;
 		bay->value_count = 0;
+		return;
+	}
+	if (id == bay->content_id)
+		return;
+
+	bay->value_count += msecs_to_jiffies(MB_POLL_DELAY);
+	if (bay->value_count >= msecs_to_jiffies(MB_STABLE_DELAY)) {
+		/* If the device type changes without going thru
+		 * "MB_NO", we force a pass by "MB_NO" to make sure
+		 * things are properly reset
+		 */
+		if ((id != MB_NO) && (bay->content_id != MB_NO)) {
+			id = MB_NO;
+			pr_debug("mediabay%d: forcing MB_NO\n", bay->index);
+		}
+		pr_debug("mediabay%d: switching to %d\n", bay->index, id);
+		set_mb_power(bay, id != MB_NO);
+		bay->content_id = id;
+		if (id >= MB_NO || id < 0)
+			printk(KERN_INFO "mediabay%d: Bay is now empty\n", bay->index);
+		else
+			printk(KERN_INFO "mediabay%d: Bay contains %s\n",
+			       bay->index, mb_content_types[id]);
 	}
 }
 
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
-int check_media_bay(struct device_node *which_bay, int what)
+int check_media_bay(struct macio_dev *baydev)
 {
-	int	i;
+	struct media_bay_info* bay;
+	int id;
 
-	for (i=0; i<media_bay_count; i++)
-		if (media_bays[i].mdev && which_bay == media_bays[i].mdev->ofdev.node) {
-			if ((what == media_bays[i].content_id) && media_bays[i].state == mb_up)
-				return 0;
-			media_bays[i].cd_index = -1;
-			return -EINVAL;
-		}
-	return -ENODEV;
+	if (baydev == NULL)
+		return MB_NO;
+
+	/* This returns an instant snapshot, not locking, sine
+	 * we may be called with the bay lock held. The resulting
+	 * fuzzyness of the result if called at the wrong time is
+	 * not actually a huge deal
+	 */
+	bay = macio_get_drvdata(baydev);
+	if (bay == NULL)
+		return MB_NO;
+	id = bay->content_id;
+	if (bay->state != mb_up)
+		return MB_NO;
+	if (id == MB_FD1)
+		return MB_FD;
+	return id;
 }
-EXPORT_SYMBOL(check_media_bay);
+EXPORT_SYMBOL_GPL(check_media_bay);
 
-int check_media_bay_by_base(unsigned long base, int what)
+void lock_media_bay(struct macio_dev *baydev)
 {
-	int	i;
+	struct media_bay_info* bay;
 
-	for (i=0; i<media_bay_count; i++)
-		if (media_bays[i].mdev && base == (unsigned long) media_bays[i].cd_base) {
-			if ((what == media_bays[i].content_id) && media_bays[i].state == mb_up)
-				return 0;
-			media_bays[i].cd_index = -1;
-			return -EINVAL;
-		} 
-
-	return -ENODEV;
+	if (baydev == NULL)
+		return;
+	bay = macio_get_drvdata(baydev);
+	if (bay == NULL)
+		return;
+	mutex_lock(&bay->lock);
+	bay->user_lock = 1;
 }
-EXPORT_SYMBOL_GPL(check_media_bay_by_base);
+EXPORT_SYMBOL_GPL(lock_media_bay);
 
-int media_bay_set_ide_infos(struct device_node* which_bay, unsigned long base,
-			    int irq, ide_hwif_t *hwif)
+void unlock_media_bay(struct macio_dev *baydev)
 {
-	int	i;
+	struct media_bay_info* bay;
 
-	for (i=0; i<media_bay_count; i++) {
-		struct media_bay_info* bay = &media_bays[i];
-
-		if (bay->mdev && which_bay == bay->mdev->ofdev.node) {
-			int timeout = 5000, index = hwif->index;
-			
-			mutex_lock(&bay->lock);
-
-			bay->cd_port	= hwif;
- 			bay->cd_base	= (void __iomem *) base;
-			bay->cd_irq	= irq;
-
-			if ((MB_CD != bay->content_id) || bay->state != mb_up) {
-				mutex_unlock(&bay->lock);
-				return 0;
-			}
-			printk(KERN_DEBUG "Registered ide%d for media bay %d\n", index, i);
-			do {
-				if (MB_IDE_READY(i)) {
-					bay->cd_index	= index;
-					mutex_unlock(&bay->lock);
-					return 0;
-				}
-				mdelay(1);
-			} while(--timeout);
-			printk(KERN_DEBUG "Timeount waiting IDE in bay %d\n", i);
-			mutex_unlock(&bay->lock);
-			return -ENODEV;
-		}
+	if (baydev == NULL)
+		return;
+	bay = macio_get_drvdata(baydev);
+	if (bay == NULL)
+		return;
+	if (bay->user_lock) {
+		bay->user_lock = 0;
+		mutex_unlock(&bay->lock);
 	}
-
-	return -ENODEV;
 }
-EXPORT_SYMBOL_GPL(media_bay_set_ide_infos);
-#endif /* CONFIG_BLK_DEV_IDE_PMAC */
+EXPORT_SYMBOL_GPL(unlock_media_bay);
+
+static int mb_broadcast_hotplug(struct device *dev, void *data)
+{
+	struct media_bay_info* bay = data;
+	struct macio_dev *mdev;
+	struct macio_driver *drv;
+	int state;
+
+	if (dev->bus != &macio_bus_type)
+		return 0;
+
+	state = bay->state == mb_up ? bay->content_id : MB_NO;
+	if (state == MB_FD1)
+		state = MB_FD;
+	mdev = to_macio_device(dev);
+	drv = to_macio_driver(dev->driver);
+	if (dev->driver && drv->mediabay_event)
+		drv->mediabay_event(mdev, state);
+	return 0;
+}
 
 static void media_bay_step(int i)
 {
@@ -497,8 +474,8 @@ static void media_bay_step(int i)
 	if (bay->state != mb_powering_down)
 	    poll_media_bay(bay);
 
-	/* If timer expired or polling IDE busy, run state machine */
-	if ((bay->state != mb_ide_waiting) && (bay->timer != 0)) {
+	/* If timer expired run state machine */
+	if (bay->timer != 0) {
 		bay->timer -= msecs_to_jiffies(MB_POLL_DELAY);
 		if (bay->timer > 0)
 			return;
@@ -508,100 +485,50 @@ static void media_bay_step(int i)
 	switch(bay->state) {
 	case mb_powering_up:
 	    	if (bay->ops->setup_bus(bay, bay->last_value) < 0) {
-			MBDBG("mediabay%d: device not supported (kind:%d)\n", i, bay->content_id);
+			pr_debug("mediabay%d: device not supported (kind:%d)\n",
+				 i, bay->content_id);
 	    		set_mb_power(bay, 0);
 	    		break;
 	    	}
 	    	bay->timer = msecs_to_jiffies(MB_RESET_DELAY);
 	    	bay->state = mb_enabling_bay;
-		MBDBG("mediabay%d: enabling (kind:%d)\n", i, bay->content_id);
+		pr_debug("mediabay%d: enabling (kind:%d)\n", i, bay->content_id);
 		break;
 	case mb_enabling_bay:
 		bay->ops->un_reset(bay);
 	    	bay->timer = msecs_to_jiffies(MB_SETUP_DELAY);
 	    	bay->state = mb_resetting;
-		MBDBG("mediabay%d: waiting reset (kind:%d)\n", i, bay->content_id);
+		pr_debug("mediabay%d: releasing bay reset (kind:%d)\n",
+			 i, bay->content_id);
 	    	break;
 	case mb_resetting:
 		if (bay->content_id != MB_CD) {
-			MBDBG("mediabay%d: bay is up (kind:%d)\n", i, bay->content_id);
+			pr_debug("mediabay%d: bay is up (kind:%d)\n", i,
+				 bay->content_id);
 			bay->state = mb_up;
+			device_for_each_child(&bay->mdev->ofdev.dev,
+					      bay, mb_broadcast_hotplug);
 			break;
 	    	}
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
-		MBDBG("mediabay%d: waiting IDE reset (kind:%d)\n", i, bay->content_id);
+		pr_debug("mediabay%d: releasing ATA reset (kind:%d)\n",
+			 i, bay->content_id);
 		bay->ops->un_reset_ide(bay);
 	    	bay->timer = msecs_to_jiffies(MB_IDE_WAIT);
 	    	bay->state = mb_ide_resetting;
-#else
-		printk(KERN_DEBUG "media-bay %d is ide (not compiled in kernel)\n", i);
-		set_mb_power(bay, 0);
-#endif /* CONFIG_BLK_DEV_IDE_PMAC */
 	    	break;
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
+
 	case mb_ide_resetting:
-	    	bay->timer = msecs_to_jiffies(MB_IDE_TIMEOUT);
-	    	bay->state = mb_ide_waiting;
-		MBDBG("mediabay%d: waiting IDE ready (kind:%d)\n", i, bay->content_id);
+		pr_debug("mediabay%d: bay is up (kind:%d)\n", i, bay->content_id);
+		bay->state = mb_up;
+		device_for_each_child(&bay->mdev->ofdev.dev,
+				      bay, mb_broadcast_hotplug);
 	    	break;
-	case mb_ide_waiting:
-		if (bay->cd_base == NULL) {
-			bay->timer = 0;
-			bay->state = mb_up;
-			MBDBG("mediabay%d: up before IDE init\n", i);
-			break;
-		} else if (MB_IDE_READY(i)) {
-			bay->timer = 0;
-			bay->state = mb_up;
-			if (bay->cd_index < 0) {
-				printk("mediabay %d, registering IDE...\n", i);
-				pmu_suspend();
-				ide_port_scan(bay->cd_port);
-				if (bay->cd_port->present)
-					bay->cd_index = bay->cd_port->index;
-				pmu_resume();
-			}
-			if (bay->cd_index == -1) {
-				/* We eventually do a retry */
-				bay->cd_retry++;
-				printk("IDE register error\n");
-				set_mb_power(bay, 0);
-			} else {
-				printk(KERN_DEBUG "media-bay %d is ide%d\n", i, bay->cd_index);
-				MBDBG("mediabay %d IDE ready\n", i);
-			}
-			break;
-	    	} else if (bay->timer > 0)
-			bay->timer -= msecs_to_jiffies(MB_POLL_DELAY);
-	    	if (bay->timer <= 0) {
-			printk("\nIDE Timeout in bay %d !, IDE state is: 0x%02x\n",
-			       i, readb(bay->cd_base + 0x70));
-			MBDBG("mediabay%d: nIDE Timeout !\n", i);
-			set_mb_power(bay, 0);
-			bay->timer = 0;
-	    	}
-		break;
-#endif /* CONFIG_BLK_DEV_IDE_PMAC */
+
 	case mb_powering_down:
 	    	bay->state = mb_empty;
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
-    	        if (bay->cd_index >= 0) {
-			printk(KERN_DEBUG "Unregistering mb %d ide, index:%d\n", i,
-			       bay->cd_index);
-			ide_port_unregister_devices(bay->cd_port);
-			bay->cd_index = -1;
-		}
-	    	if (bay->cd_retry) {
-			if (bay->cd_retry > MAX_CD_RETRIES) {
-				/* Should add an error sound (sort of beep in dmasound) */
-				printk("\nmedia-bay %d, IDE device badly inserted or unrecognised\n", i);
-			} else {
-				/* Force a new power down/up sequence */
-				bay->content_id = MB_NO;
-			}
-	    	}
-#endif /* CONFIG_BLK_DEV_IDE_PMAC */
-		MBDBG("mediabay%d: end of power down\n", i);
+		device_for_each_child(&bay->mdev->ofdev.dev,
+				      bay, mb_broadcast_hotplug);
+		pr_debug("mediabay%d: end of power down\n", i);
 	    	break;
 	}
 }
@@ -676,11 +603,6 @@ static int __devinit media_bay_attach(struct macio_dev *mdev, const struct of_de
 	bay->last_value = bay->ops->content(bay);
 	bay->value_count = msecs_to_jiffies(MB_STABLE_DELAY);
 	bay->state = mb_empty;
-	do {
-		msleep(MB_POLL_DELAY);
-		media_bay_step(i);
-	} while((bay->state != mb_empty) &&
-		(bay->state != mb_up));
 
 	/* Mark us ready by filling our mdev data */
 	macio_set_drvdata(mdev, bay);
@@ -725,7 +647,7 @@ static int media_bay_resume(struct macio_dev *mdev)
 	       	set_mb_power(bay, 0);
 		msleep(MB_POWER_DELAY);
 	       	if (bay->ops->content(bay) != bay->content_id) {
-			printk("mediabay%d: content changed during sleep...\n", bay->index);
+			printk("mediabay%d: Content changed during sleep...\n", bay->index);
 			mutex_unlock(&bay->lock);
 	       		return 0;
 		}
@@ -733,9 +655,6 @@ static int media_bay_resume(struct macio_dev *mdev)
 	       	bay->last_value = bay->content_id;
 	       	bay->value_count = msecs_to_jiffies(MB_STABLE_DELAY);
 	       	bay->timer = msecs_to_jiffies(MB_POWER_DELAY);
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
-	       	bay->cd_retry = 0;
-#endif
 	       	do {
 			msleep(MB_POLL_DELAY);
 	       		media_bay_step(bay->index);
@@ -823,9 +742,6 @@ static int __init media_bay_init(void)
 	for (i=0; i<MAX_BAYS; i++) {
 		memset((char *)&media_bays[i], 0, sizeof(struct media_bay_info));
 		media_bays[i].content_id	= -1;
-#ifdef CONFIG_BLK_DEV_IDE_PMAC
-		media_bays[i].cd_index		= -1;
-#endif
 	}
 	if (!machine_is(powermac))
 		return 0;

From f0353813afe784330622596ff141e7525ccd99de Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 1 Dec 2009 14:36:28 +0000
Subject: [PATCH 126/151] libata/sff: Use ops->bmdma_stop instead of
 ata_bmdma_stop()

In libata-sff, ata_sff_post_internal_cmd() directly calls ata_bmdma_stop()
instead of ap->ops->bmdma_stop(). This can be a problem for controllers
that use their own bmdma_stop for which the generic sff one isn't suitable

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/libata-sff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index bbbb1fab1755..51eb1e298601 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -2384,7 +2384,7 @@ void ata_sff_post_internal_cmd(struct ata_queued_cmd *qc)
 	ap->hsm_task_state = HSM_ST_IDLE;
 
 	if (ap->ioaddr.bmdma_addr)
-		ata_bmdma_stop(qc);
+		ap->ops->bmdma_stop(qc);
 
 	spin_unlock_irqrestore(ap->lock, flags);
 }

From 88358ab08944da726e948d216977ad499dfc15c6 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 1 Dec 2009 14:36:29 +0000
Subject: [PATCH 127/151] libata/drivers: Add driver for Apple "MacIO" IDE
 controller

This is a libata driver for the "macio" IDE controller used on most Apple
PowerMac and PowerBooks. It's a libata equivalent of drivers/ide/ppc/pmac.c

It supports all the features of its predecessor, including mediabay hotplug
and suspend/resume. It should also support module load/unload.

The timing calculations have been simplified to use pre-calculated tables
compared to drivers/ide/pmac.c and it uses the new mediabay interface
provided by a previous patch.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Tejun Heo <tj@kernel.org>
---
 drivers/ata/Kconfig      |   10 +
 drivers/ata/Makefile     |    1 +
 drivers/ata/pata_macio.c | 1427 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 1438 insertions(+)
 create mode 100644 drivers/ata/pata_macio.c

diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index f2df6e2a224c..51eea3000b55 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -781,5 +781,15 @@ config PATA_BF54X
 
 	  If unsure, say N.
 
+config PATA_MACIO
+	tristate "Apple PowerMac/PowerBook internal 'MacIO' IDE"
+	depends on PPC_PMAC
+	help
+	  Most IDE capable PowerMacs have IDE busses driven by a variant
+          of this controller which is part of the Apple chipset used on
+          most PowerMac models. Some models have multiple busses using
+          different chipsets, though generally, MacIO is one of them.
+
+
 endif # ATA_SFF
 endif # ATA
diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile
index 01e126f343b3..e439141d423e 100644
--- a/drivers/ata/Makefile
+++ b/drivers/ata/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_SATA_MV)		+= sata_mv.o
 obj-$(CONFIG_SATA_INIC162X)	+= sata_inic162x.o
 obj-$(CONFIG_PDC_ADMA)		+= pdc_adma.o
 obj-$(CONFIG_SATA_FSL)		+= sata_fsl.o
+obj-$(CONFIG_PATA_MACIO)	+= pata_macio.o
 
 obj-$(CONFIG_PATA_ALI)		+= pata_ali.o
 obj-$(CONFIG_PATA_AMD)		+= pata_amd.o
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
new file mode 100644
index 000000000000..4cc7bbd10ec2
--- /dev/null
+++ b/drivers/ata/pata_macio.c
@@ -0,0 +1,1427 @@
+/*
+ * Libata based driver for Apple "macio" family of PATA controllers
+ *
+ * Copyright 2008/2009 Benjamin Herrenschmidt, IBM Corp
+ *                     <benh@kernel.crashing.org>
+ *
+ * Some bits and pieces from drivers/ide/ppc/pmac.c
+ *
+ */
+
+#undef DEBUG
+#undef DEBUG_DMA
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/blkdev.h>
+#include <linux/ata.h>
+#include <linux/libata.h>
+#include <linux/adb.h>
+#include <linux/pmu.h>
+#include <linux/scatterlist.h>
+#include <linux/of.h>
+
+#include <scsi/scsi.h>
+#include <scsi/scsi_host.h>
+#include <scsi/scsi_device.h>
+
+#include <asm/macio.h>
+#include <asm/io.h>
+#include <asm/dbdma.h>
+#include <asm/pci-bridge.h>
+#include <asm/machdep.h>
+#include <asm/pmac_feature.h>
+#include <asm/mediabay.h>
+
+#ifdef DEBUG_DMA
+#define dev_dbgdma(dev, format, arg...)		\
+	dev_printk(KERN_DEBUG , dev , format , ## arg)
+#else
+#define dev_dbgdma(dev, format, arg...)		\
+	({ if (0) dev_printk(KERN_DEBUG, dev, format, ##arg); 0; })
+#endif
+
+#define DRV_NAME	"pata_macio"
+#define DRV_VERSION	"0.9"
+
+/* Models of macio ATA controller */
+enum {
+	controller_ohare,	/* OHare based */
+	controller_heathrow,	/* Heathrow/Paddington */
+	controller_kl_ata3,	/* KeyLargo ATA-3 */
+	controller_kl_ata4,	/* KeyLargo ATA-4 */
+	controller_un_ata6,	/* UniNorth2 ATA-6 */
+	controller_k2_ata6,	/* K2 ATA-6 */
+	controller_sh_ata6,	/* Shasta ATA-6 */
+};
+
+static const char* macio_ata_names[] = {
+	"OHare ATA",		/* OHare based */
+	"Heathrow ATA",		/* Heathrow/Paddington */
+	"KeyLargo ATA-3",	/* KeyLargo ATA-3 (MDMA only) */
+	"KeyLargo ATA-4",	/* KeyLargo ATA-4 (UDMA/66) */
+	"UniNorth ATA-6",	/* UniNorth2 ATA-6 (UDMA/100) */
+	"K2 ATA-6",		/* K2 ATA-6 (UDMA/100) */
+	"Shasta ATA-6",		/* Shasta ATA-6 (UDMA/133) */
+};
+
+/*
+ * Extra registers, both 32-bit little-endian
+ */
+#define IDE_TIMING_CONFIG	0x200
+#define IDE_INTERRUPT		0x300
+
+/* Kauai (U2) ATA has different register setup */
+#define IDE_KAUAI_PIO_CONFIG	0x200
+#define IDE_KAUAI_ULTRA_CONFIG	0x210
+#define IDE_KAUAI_POLL_CONFIG	0x220
+
+/*
+ * Timing configuration register definitions
+ */
+
+/* Number of IDE_SYSCLK_NS ticks, argument is in nanoseconds */
+#define SYSCLK_TICKS(t)		(((t) + IDE_SYSCLK_NS - 1) / IDE_SYSCLK_NS)
+#define SYSCLK_TICKS_66(t)	(((t) + IDE_SYSCLK_66_NS - 1) / IDE_SYSCLK_66_NS)
+#define IDE_SYSCLK_NS		30	/* 33Mhz cell */
+#define IDE_SYSCLK_66_NS	15	/* 66Mhz cell */
+
+/* 133Mhz cell, found in shasta.
+ * See comments about 100 Mhz Uninorth 2...
+ * Note that PIO_MASK and MDMA_MASK seem to overlap, that's just
+ * weird and I don't now why .. at this stage
+ */
+#define TR_133_PIOREG_PIO_MASK		0xff000fff
+#define TR_133_PIOREG_MDMA_MASK		0x00fff800
+#define TR_133_UDMAREG_UDMA_MASK	0x0003ffff
+#define TR_133_UDMAREG_UDMA_EN		0x00000001
+
+/* 100Mhz cell, found in Uninorth 2 and K2. It appears as a pci device
+ * (106b/0033) on uninorth or K2 internal PCI bus and it's clock is
+ * controlled like gem or fw. It appears to be an evolution of keylargo
+ * ATA4 with a timing register extended to 2x32bits registers (one
+ * for PIO & MWDMA and one for UDMA, and a similar DBDMA channel.
+ * It has it's own local feature control register as well.
+ *
+ * After scratching my mind over the timing values, at least for PIO
+ * and MDMA, I think I've figured the format of the timing register,
+ * though I use pre-calculated tables for UDMA as usual...
+ */
+#define TR_100_PIO_ADDRSETUP_MASK	0xff000000 /* Size of field unknown */
+#define TR_100_PIO_ADDRSETUP_SHIFT	24
+#define TR_100_MDMA_MASK		0x00fff000
+#define TR_100_MDMA_RECOVERY_MASK	0x00fc0000
+#define TR_100_MDMA_RECOVERY_SHIFT	18
+#define TR_100_MDMA_ACCESS_MASK		0x0003f000
+#define TR_100_MDMA_ACCESS_SHIFT	12
+#define TR_100_PIO_MASK			0xff000fff
+#define TR_100_PIO_RECOVERY_MASK	0x00000fc0
+#define TR_100_PIO_RECOVERY_SHIFT	6
+#define TR_100_PIO_ACCESS_MASK		0x0000003f
+#define TR_100_PIO_ACCESS_SHIFT		0
+
+#define TR_100_UDMAREG_UDMA_MASK	0x0000ffff
+#define TR_100_UDMAREG_UDMA_EN		0x00000001
+
+
+/* 66Mhz cell, found in KeyLargo. Can do ultra mode 0 to 2 on
+ * 40 connector cable and to 4 on 80 connector one.
+ * Clock unit is 15ns (66Mhz)
+ *
+ * 3 Values can be programmed:
+ *  - Write data setup, which appears to match the cycle time. They
+ *    also call it DIOW setup.
+ *  - Ready to pause time (from spec)
+ *  - Address setup. That one is weird. I don't see where exactly
+ *    it fits in UDMA cycles, I got it's name from an obscure piece
+ *    of commented out code in Darwin. They leave it to 0, we do as
+ *    well, despite a comment that would lead to think it has a
+ *    min value of 45ns.
+ * Apple also add 60ns to the write data setup (or cycle time ?) on
+ * reads.
+ */
+#define TR_66_UDMA_MASK			0xfff00000
+#define TR_66_UDMA_EN			0x00100000 /* Enable Ultra mode for DMA */
+#define TR_66_PIO_ADDRSETUP_MASK	0xe0000000 /* Address setup */
+#define TR_66_PIO_ADDRSETUP_SHIFT	29
+#define TR_66_UDMA_RDY2PAUS_MASK	0x1e000000 /* Ready 2 pause time */
+#define TR_66_UDMA_RDY2PAUS_SHIFT	25
+#define TR_66_UDMA_WRDATASETUP_MASK	0x01e00000 /* Write data setup time */
+#define TR_66_UDMA_WRDATASETUP_SHIFT	21
+#define TR_66_MDMA_MASK			0x000ffc00
+#define TR_66_MDMA_RECOVERY_MASK	0x000f8000
+#define TR_66_MDMA_RECOVERY_SHIFT	15
+#define TR_66_MDMA_ACCESS_MASK		0x00007c00
+#define TR_66_MDMA_ACCESS_SHIFT		10
+#define TR_66_PIO_MASK			0xe00003ff
+#define TR_66_PIO_RECOVERY_MASK		0x000003e0
+#define TR_66_PIO_RECOVERY_SHIFT	5
+#define TR_66_PIO_ACCESS_MASK		0x0000001f
+#define TR_66_PIO_ACCESS_SHIFT		0
+
+/* 33Mhz cell, found in OHare, Heathrow (& Paddington) and KeyLargo
+ * Can do pio & mdma modes, clock unit is 30ns (33Mhz)
+ *
+ * The access time and recovery time can be programmed. Some older
+ * Darwin code base limit OHare to 150ns cycle time. I decided to do
+ * the same here fore safety against broken old hardware ;)
+ * The HalfTick bit, when set, adds half a clock (15ns) to the access
+ * time and removes one from recovery. It's not supported on KeyLargo
+ * implementation afaik. The E bit appears to be set for PIO mode 0 and
+ * is used to reach long timings used in this mode.
+ */
+#define TR_33_MDMA_MASK			0x003ff800
+#define TR_33_MDMA_RECOVERY_MASK	0x001f0000
+#define TR_33_MDMA_RECOVERY_SHIFT	16
+#define TR_33_MDMA_ACCESS_MASK		0x0000f800
+#define TR_33_MDMA_ACCESS_SHIFT		11
+#define TR_33_MDMA_HALFTICK		0x00200000
+#define TR_33_PIO_MASK			0x000007ff
+#define TR_33_PIO_E			0x00000400
+#define TR_33_PIO_RECOVERY_MASK		0x000003e0
+#define TR_33_PIO_RECOVERY_SHIFT	5
+#define TR_33_PIO_ACCESS_MASK		0x0000001f
+#define TR_33_PIO_ACCESS_SHIFT		0
+
+/*
+ * Interrupt register definitions. Only present on newer cells
+ * (Keylargo and later afaik) so we don't use it.
+ */
+#define IDE_INTR_DMA			0x80000000
+#define IDE_INTR_DEVICE			0x40000000
+
+/*
+ * FCR Register on Kauai. Not sure what bit 0x4 is  ...
+ */
+#define KAUAI_FCR_UATA_MAGIC		0x00000004
+#define KAUAI_FCR_UATA_RESET_N		0x00000002
+#define KAUAI_FCR_UATA_ENABLE		0x00000001
+
+
+/* Allow up to 256 DBDMA commands per xfer */
+#define MAX_DCMDS		256
+
+/* Don't let a DMA segment go all the way to 64K */
+#define MAX_DBDMA_SEG		0xff00
+
+
+/*
+ * Wait 1s for disk to answer on IDE bus after a hard reset
+ * of the device (via GPIO/FCR).
+ *
+ * Some devices seem to "pollute" the bus even after dropping
+ * the BSY bit (typically some combo drives slave on the UDMA
+ * bus) after a hard reset. Since we hard reset all drives on
+ * KeyLargo ATA66, we have to keep that delay around. I may end
+ * up not hard resetting anymore on these and keep the delay only
+ * for older interfaces instead (we have to reset when coming
+ * from MacOS...) --BenH.
+ */
+#define IDE_WAKEUP_DELAY_MS	1000
+
+struct pata_macio_timing;
+
+struct pata_macio_priv {
+	int				kind;
+	int				aapl_bus_id;
+	int				mediabay : 1;
+	struct device_node		*node;
+	struct macio_dev		*mdev;
+	struct pci_dev			*pdev;
+	struct device			*dev;
+	int				irq;
+	u32				treg[2][2];
+	void __iomem			*tfregs;
+	void __iomem			*kauai_fcr;
+	struct dbdma_cmd *		dma_table_cpu;
+	dma_addr_t			dma_table_dma;
+	struct ata_host			*host;
+	const struct pata_macio_timing	*timings;
+};
+
+/* Previous variants of this driver used to calculate timings
+ * for various variants of the chip and use tables for others.
+ *
+ * Not only was this confusing, but in addition, it isn't clear
+ * whether our calculation code was correct. It didn't entirely
+ * match the darwin code and whatever documentation I could find
+ * on these cells
+ *
+ * I decided to entirely rely on a table instead for this version
+ * of the driver. Also, because I don't really care about derated
+ * modes and really old HW other than making it work, I'm not going
+ * to calculate / snoop timing values for something else than the
+ * standard modes.
+ */
+struct pata_macio_timing {
+	int	mode;
+	u32	reg1;	/* Bits to set in first timing reg */
+	u32	reg2;	/* Bits to set in second timing reg */
+};
+
+static const struct pata_macio_timing pata_macio_ohare_timings[] = {
+	{ XFER_PIO_0,		0x00000526,	0, },
+	{ XFER_PIO_1,		0x00000085,	0, },
+	{ XFER_PIO_2,		0x00000025,	0, },
+	{ XFER_PIO_3,		0x00000025,	0, },
+	{ XFER_PIO_4,		0x00000025,	0, },
+	{ XFER_MW_DMA_0,	0x00074000,	0, },
+	{ XFER_MW_DMA_1,	0x00221000,	0, },
+	{ XFER_MW_DMA_2,	0x00211000,	0, },
+	{ -1, 0, 0 }
+};
+
+static const struct pata_macio_timing pata_macio_heathrow_timings[] = {
+	{ XFER_PIO_0,		0x00000526,	0, },
+	{ XFER_PIO_1,		0x00000085,	0, },
+	{ XFER_PIO_2,		0x00000025,	0, },
+	{ XFER_PIO_3,		0x00000025,	0, },
+	{ XFER_PIO_4,		0x00000025,	0, },
+	{ XFER_MW_DMA_0,	0x00074000,	0, },
+	{ XFER_MW_DMA_1,	0x00221000,	0, },
+	{ XFER_MW_DMA_2,	0x00211000,	0, },
+	{ -1, 0, 0 }
+};
+
+static const struct pata_macio_timing pata_macio_kl33_timings[] = {
+	{ XFER_PIO_0,		0x00000526,	0, },
+	{ XFER_PIO_1,		0x00000085,	0, },
+	{ XFER_PIO_2,		0x00000025,	0, },
+	{ XFER_PIO_3,		0x00000025,	0, },
+	{ XFER_PIO_4,		0x00000025,	0, },
+	{ XFER_MW_DMA_0,	0x00084000,	0, },
+	{ XFER_MW_DMA_1,	0x00021800,	0, },
+	{ XFER_MW_DMA_2,	0x00011800,	0, },
+	{ -1, 0, 0 }
+};
+
+static const struct pata_macio_timing pata_macio_kl66_timings[] = {
+	{ XFER_PIO_0,		0x0000038c,	0, },
+	{ XFER_PIO_1,		0x0000020a,	0, },
+	{ XFER_PIO_2,		0x00000127,	0, },
+	{ XFER_PIO_3,		0x000000c6,	0, },
+	{ XFER_PIO_4,		0x00000065,	0, },
+	{ XFER_MW_DMA_0,	0x00084000,	0, },
+	{ XFER_MW_DMA_1,	0x00029800,	0, },
+	{ XFER_MW_DMA_2,	0x00019400,	0, },
+	{ XFER_UDMA_0,		0x19100000,	0, },
+	{ XFER_UDMA_1,		0x14d00000,	0, },
+	{ XFER_UDMA_2,		0x10900000,	0, },
+	{ XFER_UDMA_3,		0x0c700000,	0, },
+	{ XFER_UDMA_4,		0x0c500000,	0, },
+	{ -1, 0, 0 }
+};
+
+static const struct pata_macio_timing pata_macio_kauai_timings[] = {
+	{ XFER_PIO_0,		0x08000a92,	0, },
+	{ XFER_PIO_1,		0x0800060f,	0, },
+	{ XFER_PIO_2,		0x0800038b,	0, },
+	{ XFER_PIO_3,		0x05000249,	0, },
+	{ XFER_PIO_4,		0x04000148,	0, },
+	{ XFER_MW_DMA_0,	0x00618000,	0, },
+	{ XFER_MW_DMA_1,	0x00209000,	0, },
+	{ XFER_MW_DMA_2,	0x00148000,	0, },
+	{ XFER_UDMA_0,		         0,	0x000070c1, },
+	{ XFER_UDMA_1,		         0,	0x00005d81, },
+	{ XFER_UDMA_2,		         0,	0x00004a61, },
+	{ XFER_UDMA_3,		         0,	0x00003a51, },
+	{ XFER_UDMA_4,		         0,	0x00002a31, },
+	{ XFER_UDMA_5,		         0,	0x00002921, },
+	{ -1, 0, 0 }
+};
+
+static const struct pata_macio_timing pata_macio_shasta_timings[] = {
+	{ XFER_PIO_0,		0x0a000c97,	0, },
+	{ XFER_PIO_1,		0x07000712,	0, },
+	{ XFER_PIO_2,		0x040003cd,	0, },
+	{ XFER_PIO_3,		0x0500028b,	0, },
+	{ XFER_PIO_4,		0x0400010a,	0, },
+	{ XFER_MW_DMA_0,	0x00820800,	0, },
+	{ XFER_MW_DMA_1,	0x0028b000,	0, },
+	{ XFER_MW_DMA_2,	0x001ca000,	0, },
+	{ XFER_UDMA_0,		         0,	0x00035901, },
+	{ XFER_UDMA_1,		         0,	0x000348b1, },
+	{ XFER_UDMA_2,		         0,	0x00033881, },
+	{ XFER_UDMA_3,		         0,	0x00033861, },
+	{ XFER_UDMA_4,		         0,	0x00033841, },
+	{ XFER_UDMA_5,		         0,	0x00033031, },
+	{ XFER_UDMA_6,		         0,	0x00033021, },
+	{ -1, 0, 0 }
+};
+
+static const struct pata_macio_timing *pata_macio_find_timing(
+					    struct pata_macio_priv *priv,
+					    int mode)
+{
+	int i;
+
+	for (i = 0; priv->timings[i].mode > 0; i++) {
+		if (priv->timings[i].mode == mode)
+			return &priv->timings[i];
+	}
+	return NULL;
+}
+
+
+static void pata_macio_apply_timings(struct ata_port *ap, unsigned int device)
+{
+	struct pata_macio_priv *priv = ap->private_data;
+	void __iomem *rbase = ap->ioaddr.cmd_addr;
+
+	if (priv->kind == controller_sh_ata6 ||
+	    priv->kind == controller_un_ata6 ||
+	    priv->kind == controller_k2_ata6) {
+		writel(priv->treg[device][0], rbase + IDE_KAUAI_PIO_CONFIG);
+		writel(priv->treg[device][1], rbase + IDE_KAUAI_ULTRA_CONFIG);
+	} else
+		writel(priv->treg[device][0], rbase + IDE_TIMING_CONFIG);
+}
+
+static void pata_macio_dev_select(struct ata_port *ap, unsigned int device)
+{
+	ata_sff_dev_select(ap, device);
+
+	/* Apply timings */
+	pata_macio_apply_timings(ap, device);
+}
+
+static void pata_macio_set_timings(struct ata_port *ap,
+				   struct ata_device *adev)
+{
+	struct pata_macio_priv *priv = ap->private_data;
+	const struct pata_macio_timing *t;
+
+	dev_dbg(priv->dev, "Set timings: DEV=%d,PIO=0x%x (%s),DMA=0x%x (%s)\n",
+		adev->devno,
+		adev->pio_mode,
+		ata_mode_string(ata_xfer_mode2mask(adev->pio_mode)),
+		adev->dma_mode,
+		ata_mode_string(ata_xfer_mode2mask(adev->dma_mode)));
+
+	/* First clear timings */
+	priv->treg[adev->devno][0] = priv->treg[adev->devno][1] = 0;
+
+	/* Now get the PIO timings */
+	t = pata_macio_find_timing(priv, adev->pio_mode);
+	if (t == NULL) {
+		dev_warn(priv->dev, "Invalid PIO timing requested: 0x%x\n",
+			 adev->pio_mode);
+		t = pata_macio_find_timing(priv, XFER_PIO_0);
+	}
+	BUG_ON(t == NULL);
+
+	/* PIO timings only ever use the first treg */
+	priv->treg[adev->devno][0] |= t->reg1;
+
+	/* Now get DMA timings */
+	t = pata_macio_find_timing(priv, adev->dma_mode);
+	if (t == NULL || (t->reg1 == 0 && t->reg2 == 0)) {
+		dev_dbg(priv->dev, "DMA timing not set yet, using MW_DMA_0\n");
+		t = pata_macio_find_timing(priv, XFER_MW_DMA_0);
+	}
+	BUG_ON(t == NULL);
+
+	/* DMA timings can use both tregs */
+	priv->treg[adev->devno][0] |= t->reg1;
+	priv->treg[adev->devno][1] |= t->reg2;
+
+	dev_dbg(priv->dev, " -> %08x %08x\n",
+		priv->treg[adev->devno][0],
+		priv->treg[adev->devno][1]);
+
+	/* Apply to hardware */
+	pata_macio_apply_timings(ap, adev->devno);
+}
+
+/*
+ * Blast some well known "safe" values to the timing registers at init or
+ * wakeup from sleep time, before we do real calculation
+ */
+static void pata_macio_default_timings(struct pata_macio_priv *priv)
+{
+	unsigned int value, value2 = 0;
+
+	switch(priv->kind) {
+		case controller_sh_ata6:
+			value = 0x0a820c97;
+			value2 = 0x00033031;
+			break;
+		case controller_un_ata6:
+		case controller_k2_ata6:
+			value = 0x08618a92;
+			value2 = 0x00002921;
+			break;
+		case controller_kl_ata4:
+			value = 0x0008438c;
+			break;
+		case controller_kl_ata3:
+			value = 0x00084526;
+			break;
+		case controller_heathrow:
+		case controller_ohare:
+		default:
+			value = 0x00074526;
+			break;
+	}
+	priv->treg[0][0] = priv->treg[1][0] = value;
+	priv->treg[0][1] = priv->treg[1][1] = value2;
+}
+
+static int pata_macio_cable_detect(struct ata_port *ap)
+{
+	struct pata_macio_priv *priv = ap->private_data;
+
+	/* Get cable type from device-tree */
+	if (priv->kind == controller_kl_ata4 ||
+	    priv->kind == controller_un_ata6 ||
+	    priv->kind == controller_k2_ata6 ||
+	    priv->kind == controller_sh_ata6) {
+		const char* cable = of_get_property(priv->node, "cable-type",
+						    NULL);
+		struct device_node *root = of_find_node_by_path("/");
+		const char *model = of_get_property(root, "model", NULL);
+
+		if (cable && !strncmp(cable, "80-", 3)) {
+			/* Some drives fail to detect 80c cable in PowerBook
+			 * These machine use proprietary short IDE cable
+			 * anyway
+			 */
+			if (!strncmp(model, "PowerBook", 9))
+				return ATA_CBL_PATA40_SHORT;
+			else
+				return ATA_CBL_PATA80;
+		}
+	}
+
+	/* G5's seem to have incorrect cable type in device-tree.
+	 * Let's assume they always have a 80 conductor cable, this seem to
+	 * be always the case unless the user mucked around
+	 */
+	if (of_device_is_compatible(priv->node, "K2-UATA") ||
+	    of_device_is_compatible(priv->node, "shasta-ata"))
+		return ATA_CBL_PATA80;
+
+	/* Anything else is 40 connectors */
+	return ATA_CBL_PATA40;
+}
+
+static void pata_macio_qc_prep(struct ata_queued_cmd *qc)
+{
+	unsigned int write = (qc->tf.flags & ATA_TFLAG_WRITE);
+	struct ata_port *ap = qc->ap;
+	struct pata_macio_priv *priv = ap->private_data;
+	struct scatterlist *sg;
+	struct dbdma_cmd *table;
+	unsigned int si, pi;
+
+	dev_dbgdma(priv->dev, "%s: qc %p flags %lx, write %d dev %d\n",
+		   __func__, qc, qc->flags, write, qc->dev->devno);
+
+	if (!(qc->flags & ATA_QCFLAG_DMAMAP))
+		return;
+
+	table = (struct dbdma_cmd *) priv->dma_table_cpu;
+
+	pi = 0;
+	for_each_sg(qc->sg, sg, qc->n_elem, si) {
+		u32 addr, sg_len, len;
+
+		/* determine if physical DMA addr spans 64K boundary.
+		 * Note h/w doesn't support 64-bit, so we unconditionally
+		 * truncate dma_addr_t to u32.
+		 */
+		addr = (u32) sg_dma_address(sg);
+		sg_len = sg_dma_len(sg);
+
+		while (sg_len) {
+			/* table overflow should never happen */
+			BUG_ON (pi++ >= MAX_DCMDS);
+
+			len = (sg_len < MAX_DBDMA_SEG) ? sg_len : MAX_DBDMA_SEG;
+			st_le16(&table->command, write ? OUTPUT_MORE: INPUT_MORE);
+			st_le16(&table->req_count, len);
+			st_le32(&table->phy_addr, addr);
+			table->cmd_dep = 0;
+			table->xfer_status = 0;
+			table->res_count = 0;
+			addr += len;
+			sg_len -= len;
+			++table;
+		}
+	}
+
+	/* Should never happen according to Tejun */
+	BUG_ON(!pi);
+
+	/* Convert the last command to an input/output */
+	table--;
+	st_le16(&table->command, write ? OUTPUT_LAST: INPUT_LAST);
+	table++;
+
+	/* Add the stop command to the end of the list */
+	memset(table, 0, sizeof(struct dbdma_cmd));
+	st_le16(&table->command, DBDMA_STOP);
+
+	dev_dbgdma(priv->dev, "%s: %d DMA list entries\n", __func__, pi);
+}
+
+
+static void pata_macio_freeze(struct ata_port *ap)
+{
+	struct dbdma_regs __iomem *dma_regs = ap->ioaddr.bmdma_addr;
+
+	if (dma_regs) {
+		unsigned int timeout = 1000000;
+
+		/* Make sure DMA controller is stopped */
+		writel((RUN|PAUSE|FLUSH|WAKE|DEAD) << 16, &dma_regs->control);
+		while (--timeout && (readl(&dma_regs->status) & RUN))
+			udelay(1);
+	}
+
+	ata_sff_freeze(ap);
+}
+
+
+static void pata_macio_bmdma_setup(struct ata_queued_cmd *qc)
+{
+	struct ata_port *ap = qc->ap;
+	struct pata_macio_priv *priv = ap->private_data;
+	struct dbdma_regs __iomem *dma_regs = ap->ioaddr.bmdma_addr;
+	int dev = qc->dev->devno;
+
+	dev_dbgdma(priv->dev, "%s: qc %p\n", __func__, qc);
+
+	/* Make sure DMA commands updates are visible */
+	writel(priv->dma_table_dma, &dma_regs->cmdptr);
+
+	/* On KeyLargo 66Mhz cell, we need to add 60ns to wrDataSetup on
+	 * UDMA reads
+	 */
+	if (priv->kind == controller_kl_ata4 &&
+	    (priv->treg[dev][0] & TR_66_UDMA_EN)) {
+		void __iomem *rbase = ap->ioaddr.cmd_addr;
+		u32 reg = priv->treg[dev][0];
+
+		if (!(qc->tf.flags & ATA_TFLAG_WRITE))
+			reg += 0x00800000;
+		writel(reg, rbase + IDE_TIMING_CONFIG);
+	}
+
+	/* issue r/w command */
+	ap->ops->sff_exec_command(ap, &qc->tf);
+}
+
+static void pata_macio_bmdma_start(struct ata_queued_cmd *qc)
+{
+	struct ata_port *ap = qc->ap;
+	struct pata_macio_priv *priv = ap->private_data;
+	struct dbdma_regs __iomem *dma_regs = ap->ioaddr.bmdma_addr;
+
+	dev_dbgdma(priv->dev, "%s: qc %p\n", __func__, qc);
+
+	writel((RUN << 16) | RUN, &dma_regs->control);
+	/* Make sure it gets to the controller right now */
+	(void)readl(&dma_regs->control);
+}
+
+static void pata_macio_bmdma_stop(struct ata_queued_cmd *qc)
+{
+	struct ata_port *ap = qc->ap;
+	struct pata_macio_priv *priv = ap->private_data;
+	struct dbdma_regs __iomem *dma_regs = ap->ioaddr.bmdma_addr;
+	unsigned int timeout = 1000000;
+
+	dev_dbgdma(priv->dev, "%s: qc %p\n", __func__, qc);
+
+	/* Stop the DMA engine and wait for it to full halt */
+	writel (((RUN|WAKE|DEAD) << 16), &dma_regs->control);
+	while (--timeout && (readl(&dma_regs->status) & RUN))
+		udelay(1);
+}
+
+static u8 pata_macio_bmdma_status(struct ata_port *ap)
+{
+	struct pata_macio_priv *priv = ap->private_data;
+	struct dbdma_regs __iomem *dma_regs = ap->ioaddr.bmdma_addr;
+	u32 dstat, rstat = ATA_DMA_INTR;
+	unsigned long timeout = 0;
+
+	dstat = readl(&dma_regs->status);
+
+	dev_dbgdma(priv->dev, "%s: dstat=%x\n", __func__, dstat);
+
+	/* We have two things to deal with here:
+	 *
+	 * - The dbdma won't stop if the command was started
+	 * but completed with an error without transferring all
+	 * datas. This happens when bad blocks are met during
+	 * a multi-block transfer.
+	 *
+	 * - The dbdma fifo hasn't yet finished flushing to
+	 * to system memory when the disk interrupt occurs.
+	 *
+	 */
+
+	/* First check for errors */
+	if ((dstat & (RUN|DEAD)) != RUN)
+		rstat |= ATA_DMA_ERR;
+
+	/* If ACTIVE is cleared, the STOP command has been hit and
+	 * the transfer is complete. If not, we have to flush the
+	 * channel.
+	 */
+	if ((dstat & ACTIVE) == 0)
+		return rstat;
+
+	dev_dbgdma(priv->dev, "%s: DMA still active, flushing...\n", __func__);
+
+	/* If dbdma didn't execute the STOP command yet, the
+	 * active bit is still set. We consider that we aren't
+	 * sharing interrupts (which is hopefully the case with
+	 * those controllers) and so we just try to flush the
+	 * channel for pending data in the fifo
+	 */
+	udelay(1);
+	writel((FLUSH << 16) | FLUSH, &dma_regs->control);
+	for (;;) {
+		udelay(1);
+		dstat = readl(&dma_regs->status);
+		if ((dstat & FLUSH) == 0)
+			break;
+		if (++timeout > 1000) {
+			dev_warn(priv->dev, "timeout flushing DMA\n");
+			rstat |= ATA_DMA_ERR;
+			break;
+		}
+	}
+	return rstat;
+}
+
+/* port_start is when we allocate the DMA command list */
+static int pata_macio_port_start(struct ata_port *ap)
+{
+	struct pata_macio_priv *priv = ap->private_data;
+
+	if (ap->ioaddr.bmdma_addr == NULL)
+		return 0;
+
+	/* Allocate space for the DBDMA commands.
+	 *
+	 * The +2 is +1 for the stop command and +1 to allow for
+	 * aligning the start address to a multiple of 16 bytes.
+	 */
+	priv->dma_table_cpu =
+		dmam_alloc_coherent(priv->dev,
+				    (MAX_DCMDS + 2) * sizeof(struct dbdma_cmd),
+				    &priv->dma_table_dma, GFP_KERNEL);
+	if (priv->dma_table_cpu == NULL) {
+		dev_err(priv->dev, "Unable to allocate DMA command list\n");
+		ap->ioaddr.bmdma_addr = NULL;
+	}
+	return 0;
+}
+
+static void pata_macio_irq_clear(struct ata_port *ap)
+{
+	struct pata_macio_priv *priv = ap->private_data;
+
+	/* Nothing to do here */
+
+	dev_dbgdma(priv->dev, "%s\n", __func__);
+}
+
+static void pata_macio_reset_hw(struct pata_macio_priv *priv, int resume)
+{
+	dev_dbg(priv->dev, "Enabling & resetting... \n");
+
+	if (priv->mediabay)
+		return;
+
+	if (priv->kind == controller_ohare && !resume) {
+		/* The code below is having trouble on some ohare machines
+		 * (timing related ?). Until I can put my hand on one of these
+		 * units, I keep the old way
+		 */
+		ppc_md.feature_call(PMAC_FTR_IDE_ENABLE, priv->node, 0, 1);
+	} else {
+		int rc;
+
+ 		/* Reset and enable controller */
+		rc = ppc_md.feature_call(PMAC_FTR_IDE_RESET,
+					 priv->node, priv->aapl_bus_id, 1);
+		ppc_md.feature_call(PMAC_FTR_IDE_ENABLE,
+				    priv->node, priv->aapl_bus_id, 1);
+		msleep(10);
+		/* Only bother waiting if there's a reset control */
+		if (rc == 0) {
+			ppc_md.feature_call(PMAC_FTR_IDE_RESET,
+					    priv->node, priv->aapl_bus_id, 0);
+			msleep(IDE_WAKEUP_DELAY_MS);
+		}
+	}
+
+	/* If resuming a PCI device, restore the config space here */
+	if (priv->pdev && resume) {
+		int rc;
+
+		pci_restore_state(priv->pdev);
+		rc = pcim_enable_device(priv->pdev);
+		if (rc)
+			dev_printk(KERN_ERR, &priv->pdev->dev,
+				   "Failed to enable device after resume (%d)\n", rc);
+		else
+			pci_set_master(priv->pdev);
+	}
+
+	/* On Kauai, initialize the FCR. We don't perform a reset, doesn't really
+	 * seem necessary and speeds up the boot process
+	 */
+	if (priv->kauai_fcr)
+		writel(KAUAI_FCR_UATA_MAGIC |
+		       KAUAI_FCR_UATA_RESET_N |
+		       KAUAI_FCR_UATA_ENABLE, priv->kauai_fcr);
+}
+
+/* Hook the standard slave config to fixup some HW related alignment
+ * restrictions
+ */
+static int pata_macio_slave_config(struct scsi_device *sdev)
+{
+	struct ata_port *ap = ata_shost_to_port(sdev->host);
+	struct pata_macio_priv *priv = ap->private_data;
+	struct ata_device *dev;
+	u16 cmd;
+	int rc;
+
+	/* First call original */
+	rc = ata_scsi_slave_config(sdev);
+	if (rc)
+		return rc;
+
+	/* This is lifted from sata_nv */
+	dev = &ap->link.device[sdev->id];
+
+	/* OHare has issues with non cache aligned DMA on some chipsets */
+	if (priv->kind == controller_ohare) {
+		blk_queue_update_dma_alignment(sdev->request_queue, 31);
+		blk_queue_update_dma_pad(sdev->request_queue, 31);
+
+		/* Tell the world about it */
+		ata_dev_printk(dev, KERN_INFO, "OHare alignment limits applied\n");
+		return 0;
+	}
+
+	/* We only have issues with ATAPI */
+	if (dev->class != ATA_DEV_ATAPI)
+		return 0;
+
+	/* Shasta and K2 seem to have "issues" with reads ... */
+	if (priv->kind == controller_sh_ata6 || priv->kind == controller_k2_ata6) {
+		/* Allright these are bad, apply restrictions */
+		blk_queue_update_dma_alignment(sdev->request_queue, 15);
+		blk_queue_update_dma_pad(sdev->request_queue, 15);
+
+		/* We enable MWI and hack cache line size directly here, this
+		 * is specific to this chipset and not normal values, we happen
+		 * to somewhat know what we are doing here (which is basically
+		 * to do the same Apple does and pray they did not get it wrong :-)
+		 */
+		BUG_ON(!priv->pdev);
+		pci_write_config_byte(priv->pdev, PCI_CACHE_LINE_SIZE, 0x08);
+		pci_read_config_word(priv->pdev, PCI_COMMAND, &cmd);
+		pci_write_config_word(priv->pdev, PCI_COMMAND,
+				      cmd | PCI_COMMAND_INVALIDATE);
+
+		/* Tell the world about it */
+		ata_dev_printk(dev, KERN_INFO,
+			       "K2/Shasta alignment limits applied\n");
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+
+static int pata_macio_do_suspend(struct pata_macio_priv *priv, pm_message_t mesg)
+{
+	int rc;
+
+	/* First, core libata suspend to do most of the work */
+	rc = ata_host_suspend(priv->host, mesg);
+	if (rc)
+		return rc;
+
+	/* Restore to default timings */
+	pata_macio_default_timings(priv);
+
+	/* Mask interrupt. Not strictly necessary but old driver did
+	 * it and I'd rather not change that here */
+	disable_irq(priv->irq);
+
+	/* The media bay will handle itself just fine */
+	if (priv->mediabay)
+		return 0;
+
+	/* Kauai has bus control FCRs directly here */
+	if (priv->kauai_fcr) {
+		u32 fcr = readl(priv->kauai_fcr);
+		fcr &= ~(KAUAI_FCR_UATA_RESET_N | KAUAI_FCR_UATA_ENABLE);
+		writel(fcr, priv->kauai_fcr);
+	}
+
+	/* For PCI, save state and disable DMA. No need to call
+	 * pci_set_power_state(), the HW doesn't do D states that
+	 * way, the platform code will take care of suspending the
+	 * ASIC properly
+	 */
+	if (priv->pdev) {
+		pci_save_state(priv->pdev);
+		pci_disable_device(priv->pdev);
+	}
+
+	/* Disable the bus on older machines and the cell on kauai */
+	ppc_md.feature_call(PMAC_FTR_IDE_ENABLE, priv->node,
+			    priv->aapl_bus_id, 0);
+
+	return 0;
+}
+
+static int pata_macio_do_resume(struct pata_macio_priv *priv)
+{
+	/* Reset and re-enable the HW */
+	pata_macio_reset_hw(priv, 1);
+
+	/* Sanitize drive timings */
+	pata_macio_apply_timings(priv->host->ports[0], 0);
+
+	/* We want our IRQ back ! */
+	enable_irq(priv->irq);
+
+	/* Let the libata core take it from there */
+	ata_host_resume(priv->host);
+
+	return 0;
+}
+
+#endif /* CONFIG_PM */
+
+static struct scsi_host_template pata_macio_sht = {
+	ATA_BASE_SHT(DRV_NAME),
+	.sg_tablesize		= MAX_DCMDS,
+	/* We may not need that strict one */
+	.dma_boundary		= ATA_DMA_BOUNDARY,
+	.slave_configure	= pata_macio_slave_config,
+};
+
+static struct ata_port_operations pata_macio_ops = {
+	.inherits		= &ata_sff_port_ops,
+
+	.freeze			= pata_macio_freeze,
+	.set_piomode		= pata_macio_set_timings,
+	.set_dmamode		= pata_macio_set_timings,
+	.cable_detect		= pata_macio_cable_detect,
+	.sff_dev_select		= pata_macio_dev_select,
+	.qc_prep		= pata_macio_qc_prep,
+	.mode_filter		= ata_bmdma_mode_filter,
+	.bmdma_setup		= pata_macio_bmdma_setup,
+	.bmdma_start		= pata_macio_bmdma_start,
+	.bmdma_stop		= pata_macio_bmdma_stop,
+	.bmdma_status		= pata_macio_bmdma_status,
+	.port_start		= pata_macio_port_start,
+	.sff_irq_clear		= pata_macio_irq_clear,
+};
+
+static void __devinit pata_macio_invariants(struct pata_macio_priv *priv)
+{
+	const int *bidp;
+
+	/* Identify the type of controller */
+	if (of_device_is_compatible(priv->node, "shasta-ata")) {
+		priv->kind = controller_sh_ata6;
+	        priv->timings = pata_macio_shasta_timings;
+	} else if (of_device_is_compatible(priv->node, "kauai-ata")) {
+		priv->kind = controller_un_ata6;
+	        priv->timings = pata_macio_kauai_timings;
+	} else if (of_device_is_compatible(priv->node, "K2-UATA")) {
+		priv->kind = controller_k2_ata6;
+	        priv->timings = pata_macio_kauai_timings;
+	} else if (of_device_is_compatible(priv->node, "keylargo-ata")) {
+		if (strcmp(priv->node->name, "ata-4") == 0) {
+			priv->kind = controller_kl_ata4;
+			priv->timings = pata_macio_kl66_timings;
+		} else {
+			priv->kind = controller_kl_ata3;
+			priv->timings = pata_macio_kl33_timings;
+		}
+	} else if (of_device_is_compatible(priv->node, "heathrow-ata")) {
+		priv->kind = controller_heathrow;
+		priv->timings = pata_macio_heathrow_timings;
+	} else {
+		priv->kind = controller_ohare;
+		priv->timings = pata_macio_ohare_timings;
+	}
+
+	/* XXX FIXME --- setup priv->mediabay here */
+
+	/* Get Apple bus ID (for clock and ASIC control) */
+	bidp = of_get_property(priv->node, "AAPL,bus-id", NULL);
+	priv->aapl_bus_id =  bidp ? *bidp : 0;
+
+	/* Fixup missing Apple bus ID in case of media-bay */
+	if (priv->mediabay && bidp == 0)
+		priv->aapl_bus_id = 1;
+}
+
+static void __devinit pata_macio_setup_ios(struct ata_ioports *ioaddr,
+					   void __iomem * base,
+					   void __iomem * dma)
+{
+	/* cmd_addr is the base of regs for that port */
+	ioaddr->cmd_addr	= base;
+
+	/* taskfile registers */
+	ioaddr->data_addr	= base + (ATA_REG_DATA    << 4);
+	ioaddr->error_addr	= base + (ATA_REG_ERR     << 4);
+	ioaddr->feature_addr	= base + (ATA_REG_FEATURE << 4);
+	ioaddr->nsect_addr	= base + (ATA_REG_NSECT   << 4);
+	ioaddr->lbal_addr	= base + (ATA_REG_LBAL    << 4);
+	ioaddr->lbam_addr	= base + (ATA_REG_LBAM    << 4);
+	ioaddr->lbah_addr	= base + (ATA_REG_LBAH    << 4);
+	ioaddr->device_addr	= base + (ATA_REG_DEVICE  << 4);
+	ioaddr->status_addr	= base + (ATA_REG_STATUS  << 4);
+	ioaddr->command_addr	= base + (ATA_REG_CMD     << 4);
+	ioaddr->altstatus_addr	= base + 0x160;
+	ioaddr->ctl_addr	= base + 0x160;
+	ioaddr->bmdma_addr	= dma;
+}
+
+static void __devinit pmac_macio_calc_timing_masks(struct pata_macio_priv *priv,
+						   struct ata_port_info   *pinfo)
+{
+	int i = 0;
+
+	pinfo->pio_mask		= 0;
+	pinfo->mwdma_mask	= 0;
+	pinfo->udma_mask	= 0;
+
+	while (priv->timings[i].mode > 0) {
+		unsigned int mask = 1U << (priv->timings[i].mode & 0x0f);
+		switch(priv->timings[i].mode & 0xf0) {
+		case 0x00: /* PIO */
+			pinfo->pio_mask |= (mask >> 8);
+			break;
+		case 0x20: /* MWDMA */
+			pinfo->mwdma_mask |= mask;
+			break;
+		case 0x40: /* UDMA */
+			pinfo->udma_mask |= mask;
+			break;
+		}
+		i++;
+	}
+	dev_dbg(priv->dev, "Supported masks: PIO=%lx, MWDMA=%lx, UDMA=%lx\n",
+		pinfo->pio_mask, pinfo->mwdma_mask, pinfo->udma_mask);
+}
+
+static int __devinit pata_macio_common_init(struct pata_macio_priv	*priv,
+					    resource_size_t		tfregs,
+					    resource_size_t		dmaregs,
+					    resource_size_t		fcregs,
+					    unsigned long		irq)
+{
+	struct ata_port_info		pinfo;
+	const struct ata_port_info	*ppi[] = { &pinfo, NULL };
+	void __iomem			*dma_regs = NULL;
+
+	/* Fill up privates with various invariants collected from the
+	 * device-tree
+	 */
+	pata_macio_invariants(priv);
+
+	/* Make sure we have sane initial timings in the cache */
+	pata_macio_default_timings(priv);
+
+	/* Not sure what the real max is but we know it's less than 64K, let's
+	 * use 64K minus 256
+	 */
+	dma_set_max_seg_size(priv->dev, MAX_DBDMA_SEG);
+
+	/* Allocate libata host for 1 port */
+	memset(&pinfo, 0, sizeof(struct ata_port_info));
+	pmac_macio_calc_timing_masks(priv, &pinfo);
+	pinfo.flags		= ATA_FLAG_SLAVE_POSS | ATA_FLAG_MMIO |
+				  ATA_FLAG_NO_LEGACY;
+	pinfo.port_ops		= &pata_macio_ops;
+	pinfo.private_data	= priv;
+
+	priv->host = ata_host_alloc_pinfo(priv->dev, ppi, 1);
+	if (priv->host == NULL) {
+		dev_err(priv->dev, "Failed to allocate ATA port structure\n");
+		return -ENOMEM;
+	}
+
+	/* Setup the private data in host too */
+	priv->host->private_data = priv;
+
+	/* Map base registers */
+	priv->tfregs = devm_ioremap(priv->dev, tfregs, 0x100);
+	if (priv->tfregs == NULL) {
+		dev_err(priv->dev, "Failed to map ATA ports\n");
+		return -ENOMEM;
+	}
+	priv->host->iomap = &priv->tfregs;
+
+	/* Map DMA regs */
+	if (dmaregs != 0) {
+		dma_regs = devm_ioremap(priv->dev, dmaregs,
+					sizeof(struct dbdma_regs));
+		if (dma_regs == NULL)
+			dev_warn(priv->dev, "Failed to map ATA DMA registers\n");
+	}
+
+	/* If chip has local feature control, map those regs too */
+	if (fcregs != 0) {
+		priv->kauai_fcr = devm_ioremap(priv->dev, fcregs, 4);
+		if (priv->kauai_fcr == NULL) {
+			dev_err(priv->dev, "Failed to map ATA FCR register\n");
+			return -ENOMEM;
+		}
+	}
+
+	/* Setup port data structure */
+	pata_macio_setup_ios(&priv->host->ports[0]->ioaddr,
+			     priv->tfregs, dma_regs);
+	priv->host->ports[0]->private_data = priv;
+
+	/* hard-reset the controller */
+	pata_macio_reset_hw(priv, 0);
+	pata_macio_apply_timings(priv->host->ports[0], 0);
+
+	/* Enable bus master if necessary */
+	if (priv->pdev && dma_regs)
+		pci_set_master(priv->pdev);
+
+	dev_info(priv->dev, "Activating pata-macio chipset %s, Apple bus ID %d\n",
+		 macio_ata_names[priv->kind], priv->aapl_bus_id);
+
+	/* Start it up */
+	priv->irq = irq;
+	return ata_host_activate(priv->host, irq, ata_sff_interrupt, 0,
+				 &pata_macio_sht);
+}
+
+static int __devinit pata_macio_attach(struct macio_dev *mdev,
+				       const struct of_device_id *match)
+{
+	struct pata_macio_priv	*priv;
+	resource_size_t		tfregs, dmaregs = 0;
+	unsigned long		irq;
+	int			rc;
+
+	/* Check for broken device-trees */
+	if (macio_resource_count(mdev) == 0) {
+		dev_err(&mdev->ofdev.dev,
+			"No addresses for controller\n");
+		return -ENXIO;
+	}
+
+	/* Enable managed resources */
+	macio_enable_devres(mdev);
+
+	/* Allocate and init private data structure */
+	priv = devm_kzalloc(&mdev->ofdev.dev,
+			    sizeof(struct pata_macio_priv), GFP_KERNEL);
+	if (priv == NULL) {
+		dev_err(&mdev->ofdev.dev,
+			"Failed to allocate private memory\n");
+		return -ENOMEM;
+	}
+	priv->node = of_node_get(mdev->ofdev.node);
+	priv->mdev = mdev;
+	priv->dev = &mdev->ofdev.dev;
+
+	/* Request memory resource for taskfile registers */
+	if (macio_request_resource(mdev, 0, "pata-macio")) {
+		dev_err(&mdev->ofdev.dev,
+			"Cannot obtain taskfile resource\n");
+		return -EBUSY;
+	}
+	tfregs = macio_resource_start(mdev, 0);
+
+	/* Request resources for DMA registers if any */
+	if (macio_resource_count(mdev) >= 2) {
+		if (macio_request_resource(mdev, 1, "pata-macio-dma"))
+			dev_err(&mdev->ofdev.dev,
+				"Cannot obtain DMA resource\n");
+		else
+			dmaregs = macio_resource_start(mdev, 1);
+	}
+
+	/*
+	 * Fixup missing IRQ for some old implementations with broken
+	 * device-trees.
+	 *
+	 * This is a bit bogus, it should be fixed in the device-tree itself,
+	 * via the existing macio fixups, based on the type of interrupt
+	 * controller in the machine. However, I have no test HW for this case,
+	 * and this trick works well enough on those old machines...
+	 */
+	if (macio_irq_count(mdev) == 0) {
+		dev_warn(&mdev->ofdev.dev,
+			 "No interrupts for controller, using 13\n");
+		irq = irq_create_mapping(NULL, 13);
+	} else
+		irq = macio_irq(mdev, 0);
+
+	/* Prevvent media bay callbacks until fully registered */
+	lock_media_bay(priv->mdev->media_bay);
+
+	/* Get register addresses and call common initialization */
+	rc = pata_macio_common_init(priv,
+				    tfregs,		/* Taskfile regs */
+				    dmaregs,		/* DBDMA regs */
+				    0,			/* Feature control */
+				    irq);
+	unlock_media_bay(priv->mdev->media_bay);
+
+	return rc;
+}
+
+static int __devexit pata_macio_detach(struct macio_dev *mdev)
+{
+	struct ata_host *host = macio_get_drvdata(mdev);
+	struct pata_macio_priv *priv = host->private_data;
+
+	lock_media_bay(priv->mdev->media_bay);
+
+	/* Make sure the mediabay callback doesn't try to access
+	 * dead stuff
+	 */
+	priv->host->private_data = NULL;
+
+	ata_host_detach(host);
+
+	unlock_media_bay(priv->mdev->media_bay);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+
+static int pata_macio_suspend(struct macio_dev *mdev, pm_message_t mesg)
+{
+	struct ata_host *host = macio_get_drvdata(mdev);
+
+	return pata_macio_do_suspend(host->private_data, mesg);
+}
+
+static int pata_macio_resume(struct macio_dev *mdev)
+{
+	struct ata_host *host = macio_get_drvdata(mdev);
+
+	return pata_macio_do_resume(host->private_data);
+}
+
+#endif /* CONFIG_PM */
+
+#ifdef CONFIG_PMAC_MEDIABAY
+static void pata_macio_mb_event(struct macio_dev* mdev, int mb_state)
+{
+	struct ata_host *host = macio_get_drvdata(mdev);
+	struct ata_port *ap;
+	struct ata_eh_info *ehi;
+	struct ata_device *dev;
+	unsigned long flags;
+
+	if (!host || !host->private_data)
+		return;
+	ap = host->ports[0];
+	spin_lock_irqsave(ap->lock, flags);
+	ehi = &ap->link.eh_info;
+	if (mb_state == MB_CD) {
+		ata_ehi_push_desc(ehi, "mediabay plug");
+		ata_ehi_hotplugged(ehi);
+		ata_port_freeze(ap);
+	} else {
+		ata_ehi_push_desc(ehi, "mediabay unplug");
+		ata_for_each_dev(dev, &ap->link, ALL)
+			dev->flags |= ATA_DFLAG_DETACH;
+		ata_port_abort(ap);
+	}
+	spin_unlock_irqrestore(ap->lock, flags);
+
+}
+#endif /* CONFIG_PMAC_MEDIABAY */
+
+
+static int __devinit pata_macio_pci_attach(struct pci_dev *pdev,
+					   const struct pci_device_id *id)
+{
+	struct pata_macio_priv	*priv;
+	struct device_node	*np;
+	resource_size_t		rbase;
+
+	/* We cannot use a MacIO controller without its OF device node */
+	np = pci_device_to_OF_node(pdev);
+	if (np == NULL) {
+		dev_err(&pdev->dev,
+			"Cannot find OF device node for controller\n");
+		return -ENODEV;
+	}
+
+	/* Check that it can be enabled */
+	if (pcim_enable_device(pdev)) {
+		dev_err(&pdev->dev,
+			"Cannot enable controller PCI device\n");
+		return -ENXIO;
+	}
+
+	/* Allocate and init private data structure */
+	priv = devm_kzalloc(&pdev->dev,
+			    sizeof(struct pata_macio_priv), GFP_KERNEL);
+	if (priv == NULL) {
+		dev_err(&pdev->dev,
+			"Failed to allocate private memory\n");
+		return -ENOMEM;
+	}
+	priv->node = of_node_get(np);
+	priv->pdev = pdev;
+	priv->dev = &pdev->dev;
+
+	/* Get MMIO regions */
+	if (pci_request_regions(pdev, "pata-macio")) {
+		dev_err(&pdev->dev,
+			"Cannot obtain PCI resources\n");
+		return -EBUSY;
+	}
+
+	/* Get register addresses and call common initialization */
+	rbase = pci_resource_start(pdev, 0);
+	if (pata_macio_common_init(priv,
+				   rbase + 0x2000,	/* Taskfile regs */
+				   rbase + 0x1000,	/* DBDMA regs */
+				   rbase,		/* Feature control */
+				   pdev->irq))
+		return -ENXIO;
+
+	return 0;
+}
+
+static void __devexit pata_macio_pci_detach(struct pci_dev *pdev)
+{
+	struct ata_host *host = dev_get_drvdata(&pdev->dev);
+
+	ata_host_detach(host);
+}
+
+#ifdef CONFIG_PM
+
+static int pata_macio_pci_suspend(struct pci_dev *pdev, pm_message_t mesg)
+{
+	struct ata_host *host = dev_get_drvdata(&pdev->dev);
+
+	return pata_macio_do_suspend(host->private_data, mesg);
+}
+
+static int pata_macio_pci_resume(struct pci_dev *pdev)
+{
+	struct ata_host *host = dev_get_drvdata(&pdev->dev);
+
+	return pata_macio_do_resume(host->private_data);
+}
+
+#endif /* CONFIG_PM */
+
+static struct of_device_id pata_macio_match[] =
+{
+	{
+	.name 		= "IDE",
+	},
+	{
+	.name 		= "ATA",
+	},
+	{
+	.type		= "ide",
+	},
+	{
+	.type		= "ata",
+	},
+	{},
+};
+
+static struct macio_driver pata_macio_driver =
+{
+	.name 		= "pata-macio",
+	.match_table	= pata_macio_match,
+	.probe		= pata_macio_attach,
+	.remove		= pata_macio_detach,
+#ifdef CONFIG_PM
+	.suspend	= pata_macio_suspend,
+	.resume		= pata_macio_resume,
+#endif
+#ifdef CONFIG_PMAC_MEDIABAY
+	.mediabay_event	= pata_macio_mb_event,
+#endif
+	.driver = {
+		.owner		= THIS_MODULE,
+	},
+};
+
+static const struct pci_device_id pata_macio_pci_match[] = {
+	{ PCI_VDEVICE(APPLE, PCI_DEVICE_ID_APPLE_UNI_N_ATA),	0 },
+	{ PCI_VDEVICE(APPLE, PCI_DEVICE_ID_APPLE_IPID_ATA100),	0 },
+	{ PCI_VDEVICE(APPLE, PCI_DEVICE_ID_APPLE_K2_ATA100),	0 },
+	{ PCI_VDEVICE(APPLE, PCI_DEVICE_ID_APPLE_SH_ATA),	0 },
+	{ PCI_VDEVICE(APPLE, PCI_DEVICE_ID_APPLE_IPID2_ATA),	0 },
+	{},
+};
+
+static struct pci_driver pata_macio_pci_driver = {
+	.name		= "pata-pci-macio",
+	.id_table	= pata_macio_pci_match,
+	.probe		= pata_macio_pci_attach,
+	.remove		= pata_macio_pci_detach,
+#ifdef CONFIG_PM
+	.suspend	= pata_macio_pci_suspend,
+	.resume		= pata_macio_pci_resume,
+#endif
+	.driver = {
+		.owner		= THIS_MODULE,
+	},
+};
+MODULE_DEVICE_TABLE(pci, pata_macio_pci_match);
+
+
+static int __init pata_macio_init(void)
+{
+	int rc;
+
+	if (!machine_is(powermac))
+		return -ENODEV;
+
+	rc = pci_register_driver(&pata_macio_pci_driver);
+	if (rc)
+		return rc;
+	rc = macio_register_driver(&pata_macio_driver);
+	if (rc) {
+		pci_unregister_driver(&pata_macio_pci_driver);
+		return rc;
+	}
+	return 0;
+}
+
+static void __exit pata_macio_exit(void)
+{
+	macio_unregister_driver(&pata_macio_driver);
+	pci_unregister_driver(&pata_macio_pci_driver);
+}
+
+module_init(pata_macio_init);
+module_exit(pata_macio_exit);
+
+MODULE_AUTHOR("Benjamin Herrenschmidt");
+MODULE_DESCRIPTION("Apple MacIO PATA driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_VERSION);

From ceae8cbe94f3127253110e2d01b9334069e93177 Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@ppcg5.localdomain>
Date: Sun, 6 Dec 2009 20:01:26 +0000
Subject: [PATCH 128/151] offb: Add support for framebuffer handoff to offb.

This allows offb to be used for initial framebuffer,
and a kms driver to take over later in the boot sequence.

Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 drivers/video/offb.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/video/offb.c b/drivers/video/offb.c
index 4d8c54c23dd7..b043ac83c412 100644
--- a/drivers/video/offb.c
+++ b/drivers/video/offb.c
@@ -282,8 +282,17 @@ static int offb_set_par(struct fb_info *info)
 	return 0;
 }
 
+static void offb_destroy(struct fb_info *info)
+{
+	if (info->screen_base)
+		iounmap(info->screen_base);
+	release_mem_region(info->aperture_base, info->aperture_size);
+	framebuffer_release(info);
+}
+
 static struct fb_ops offb_ops = {
 	.owner		= THIS_MODULE,
+	.fb_destroy	= offb_destroy,
 	.fb_setcolreg	= offb_setcolreg,
 	.fb_set_par	= offb_set_par,
 	.fb_blank	= offb_blank,
@@ -482,10 +491,14 @@ static void __init offb_init_fb(const char *name, const char *full_name,
 	var->sync = 0;
 	var->vmode = FB_VMODE_NONINTERLACED;
 
+	/* set offb aperture size for generic probing */
+	info->aperture_base = address;
+	info->aperture_size = fix->smem_len;
+
 	info->fbops = &offb_ops;
 	info->screen_base = ioremap(address, fix->smem_len);
 	info->pseudo_palette = (void *) (info + 1);
-	info->flags = FBINFO_DEFAULT | foreign_endian;
+	info->flags = FBINFO_DEFAULT | FBINFO_MISC_FIRMWARE | foreign_endian;
 
 	fb_alloc_cmap(&info->cmap, 256, 0);
 

From 3fc3a6b476581d9b47b33fc1349817ce7b66433e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michel=20D=C3=A4nzer?= <daenzer@vmware.com>
Date: Sun, 6 Dec 2009 02:15:55 +0000
Subject: [PATCH 129/151] agp/uninorth: Also handle user memory types in
 u3_remove_memory().
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Also short-circuit empty updates.

Signed-off-by: Michel Dänzer <daenzer@vmware.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 drivers/char/agp/uninorth-agp.c | 29 ++++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 7 deletions(-)

diff --git a/drivers/char/agp/uninorth-agp.c b/drivers/char/agp/uninorth-agp.c
index 703959eba45a..4e05021f3f18 100644
--- a/drivers/char/agp/uninorth-agp.c
+++ b/drivers/char/agp/uninorth-agp.c
@@ -151,9 +151,6 @@ static int uninorth_insert_memory(struct agp_memory *mem, off_t pg_start,
 	void *temp;
 	int mask_type;
 
-	temp = agp_bridge->current_size;
-	num_entries = A_SIZE_32(temp)->num_entries;
-
 	if (type != mem->type)
 		return -EINVAL;
 
@@ -163,6 +160,12 @@ static int uninorth_insert_memory(struct agp_memory *mem, off_t pg_start,
 		return -EINVAL;
 	}
 
+	if (mem->page_count == 0)
+		return 0;
+
+	temp = agp_bridge->current_size;
+	num_entries = A_SIZE_32(temp)->num_entries;
+
 	if ((pg_start + mem->page_count) > num_entries)
 		return -EINVAL;
 
@@ -194,9 +197,6 @@ static int u3_insert_memory(struct agp_memory *mem, off_t pg_start, int type)
 	u32 *gp;
 	int mask_type;
 
-	temp = agp_bridge->current_size;
-	num_entries = A_SIZE_32(temp)->num_entries;
-
 	if (type != mem->type)
 		return -EINVAL;
 
@@ -206,6 +206,12 @@ static int u3_insert_memory(struct agp_memory *mem, off_t pg_start, int type)
 		return -EINVAL;
 	}
 
+	if (mem->page_count == 0)
+		return 0;
+
+	temp = agp_bridge->current_size;
+	num_entries = A_SIZE_32(temp)->num_entries;
+
 	if ((pg_start + mem->page_count) > num_entries)
 		return -EINVAL;
 
@@ -234,10 +240,19 @@ int u3_remove_memory(struct agp_memory *mem, off_t pg_start, int type)
 {
 	size_t i;
 	u32 *gp;
+	int mask_type;
 
-	if (type != 0 || mem->type != 0)
+	if (type != mem->type)
+		return -EINVAL;
+
+	mask_type = agp_bridge->driver->agp_type_to_mask_type(agp_bridge, type);
+	if (mask_type != 0) {
 		/* We know nothing of memory types */
 		return -EINVAL;
+	}
+
+	if (mem->page_count == 0)
+		return 0;
 
 	gp = (u32 *) &agp_bridge->gatt_table[pg_start];
 	for (i = 0; i < mem->page_count; ++i)

From 37580f3f229fa72f2ef73ea7df0a1d28a9dab36d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michel=20D=C3=A4nzer?= <daenzer@vmware.com>
Date: Sun, 6 Dec 2009 02:15:56 +0000
Subject: [PATCH 130/151] agp/uninorth: Unify U3 and pre-U3 insert_memory and
 remove_memory hooks.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michel Dänzer <daenzer@vmware.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 drivers/char/agp/uninorth-agp.c | 64 ++++++---------------------------
 1 file changed, 11 insertions(+), 53 deletions(-)

diff --git a/drivers/char/agp/uninorth-agp.c b/drivers/char/agp/uninorth-agp.c
index 4e05021f3f18..d89da4ac061f 100644
--- a/drivers/char/agp/uninorth-agp.c
+++ b/drivers/char/agp/uninorth-agp.c
@@ -144,53 +144,7 @@ static int uninorth_configure(void)
 	return 0;
 }
 
-static int uninorth_insert_memory(struct agp_memory *mem, off_t pg_start,
-				int type)
-{
-	int i, j, num_entries;
-	void *temp;
-	int mask_type;
-
-	if (type != mem->type)
-		return -EINVAL;
-
-	mask_type = agp_bridge->driver->agp_type_to_mask_type(agp_bridge, type);
-	if (mask_type != 0) {
-		/* We know nothing of memory types */
-		return -EINVAL;
-	}
-
-	if (mem->page_count == 0)
-		return 0;
-
-	temp = agp_bridge->current_size;
-	num_entries = A_SIZE_32(temp)->num_entries;
-
-	if ((pg_start + mem->page_count) > num_entries)
-		return -EINVAL;
-
-	j = pg_start;
-
-	while (j < (pg_start + mem->page_count)) {
-		if (agp_bridge->gatt_table[j])
-			return -EBUSY;
-		j++;
-	}
-
-	for (i = 0, j = pg_start; i < mem->page_count; i++, j++) {
-		agp_bridge->gatt_table[j] =
-			cpu_to_le32((page_to_phys(mem->pages[i]) & 0xFFFFF000UL) | 0x1UL);
-		flush_dcache_range((unsigned long)__va(page_to_phys(mem->pages[i])),
-				   (unsigned long)__va(page_to_phys(mem->pages[i]))+0x1000);
-	}
-	(void)in_le32((volatile u32*)&agp_bridge->gatt_table[pg_start]);
-	mb();
-
-	uninorth_tlbflush(mem);
-	return 0;
-}
-
-static int u3_insert_memory(struct agp_memory *mem, off_t pg_start, int type)
+static int uninorth_insert_memory(struct agp_memory *mem, off_t pg_start, int type)
 {
 	int i, num_entries;
 	void *temp;
@@ -219,14 +173,18 @@ static int u3_insert_memory(struct agp_memory *mem, off_t pg_start, int type)
 	for (i = 0; i < mem->page_count; ++i) {
 		if (gp[i]) {
 			dev_info(&agp_bridge->dev->dev,
-				 "u3_insert_memory: entry 0x%x occupied (%x)\n",
+				 "uninorth_insert_memory: entry 0x%x occupied (%x)\n",
 				 i, gp[i]);
 			return -EBUSY;
 		}
 	}
 
 	for (i = 0; i < mem->page_count; i++) {
-		gp[i] = (page_to_phys(mem->pages[i]) >> PAGE_SHIFT) | 0x80000000UL;
+		if (is_u3)
+			gp[i] = (page_to_phys(mem->pages[i]) >> PAGE_SHIFT) | 0x80000000UL;
+		else
+			gp[i] =	cpu_to_le32((page_to_phys(mem->pages[i]) & 0xFFFFF000UL) |
+					    0x1UL);
 		flush_dcache_range((unsigned long)__va(page_to_phys(mem->pages[i])),
 				   (unsigned long)__va(page_to_phys(mem->pages[i]))+0x1000);
 	}
@@ -236,7 +194,7 @@ static int u3_insert_memory(struct agp_memory *mem, off_t pg_start, int type)
 	return 0;
 }
 
-int u3_remove_memory(struct agp_memory *mem, off_t pg_start, int type)
+int uninorth_remove_memory(struct agp_memory *mem, off_t pg_start, int type)
 {
 	size_t i;
 	u32 *gp;
@@ -551,7 +509,7 @@ const struct agp_bridge_driver uninorth_agp_driver = {
 	.create_gatt_table	= uninorth_create_gatt_table,
 	.free_gatt_table	= uninorth_free_gatt_table,
 	.insert_memory		= uninorth_insert_memory,
-	.remove_memory		= agp_generic_remove_memory,
+	.remove_memory		= uninorth_remove_memory,
 	.alloc_by_type		= agp_generic_alloc_by_type,
 	.free_by_type		= agp_generic_free_by_type,
 	.agp_alloc_page		= agp_generic_alloc_page,
@@ -577,8 +535,8 @@ const struct agp_bridge_driver u3_agp_driver = {
 	.agp_enable		= uninorth_agp_enable,
 	.create_gatt_table	= uninorth_create_gatt_table,
 	.free_gatt_table	= uninorth_free_gatt_table,
-	.insert_memory		= u3_insert_memory,
-	.remove_memory		= u3_remove_memory,
+	.insert_memory		= uninorth_insert_memory,
+	.remove_memory		= uninorth_remove_memory,
 	.alloc_by_type		= agp_generic_alloc_by_type,
 	.free_by_type		= agp_generic_free_by_type,
 	.agp_alloc_page		= agp_generic_alloc_page,

From 1496e89ae2a0962748e55165a590fa3209c6f158 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@us.ibm.com>
Date: Thu, 3 Dec 2009 16:19:59 +0000
Subject: [PATCH 131/151] powerpc/therm_adt746x: Record pwm invert bit at
 module load time]

In commit 0512a9a8e277a9de2820211eef964473b714ae65, we unilaterally zero the
"pwm invert" bit in the fan behavior configuration register.  On my PowerBook
G4, this results in the fans going to full speed at low temperature and
shutting off at high temperature because the pwm invert bit is supposed to be
set.

Therefore, record the pwm invert bit at driver load time, and write the bit
into the fan behavior control register.  This restores correct behavior on my
PBG4 and should work around the bit being set to the wrong value after
suspend/resume (which is what the original patch was trying to fix).  It also
fixes a minor omission where the pwm invert bit correction is NOT performed
when switching into automatic mode.

Signed-off-by: Darrick J. Wong <djwong@us.ibm.com>
CC: <stable@kernel.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 drivers/macintosh/therm_adt746x.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/macintosh/therm_adt746x.c b/drivers/macintosh/therm_adt746x.c
index 95b676a19be7..5ff47ba7f2d0 100644
--- a/drivers/macintosh/therm_adt746x.c
+++ b/drivers/macintosh/therm_adt746x.c
@@ -79,6 +79,7 @@ struct thermostat {
 	u8			limits[3];
 	int			last_speed[2];
 	int			last_var[2];
+	int			pwm_inv[2];
 };
 
 static enum {ADT7460, ADT7467} therm_type;
@@ -229,19 +230,23 @@ static void write_fan_speed(struct thermostat *th, int speed, int fan)
 	
 	if (speed >= 0) {
 		manual = read_reg(th, MANUAL_MODE[fan]);
+		manual &= ~INVERT_MASK;
 		write_reg(th, MANUAL_MODE[fan],
-			(manual|MANUAL_MASK) & (~INVERT_MASK));
+			manual | MANUAL_MASK | th->pwm_inv[fan]);
 		write_reg(th, FAN_SPD_SET[fan], speed);
 	} else {
 		/* back to automatic */
 		if(therm_type == ADT7460) {
 			manual = read_reg(th,
 				MANUAL_MODE[fan]) & (~MANUAL_MASK);
-
+			manual &= ~INVERT_MASK;
+			manual |= th->pwm_inv[fan];
 			write_reg(th,
 				MANUAL_MODE[fan], manual|REM_CONTROL[fan]);
 		} else {
 			manual = read_reg(th, MANUAL_MODE[fan]);
+			manual &= ~INVERT_MASK;
+			manual |= th->pwm_inv[fan];
 			write_reg(th, MANUAL_MODE[fan], manual&(~AUTO_MASK));
 		}
 	}
@@ -418,6 +423,10 @@ static int probe_thermostat(struct i2c_client *client,
 
 	thermostat = th;
 
+	/* record invert bit status because fw can corrupt it after suspend */
+	th->pwm_inv[0] = read_reg(th, MANUAL_MODE[0]) & INVERT_MASK;
+	th->pwm_inv[1] = read_reg(th, MANUAL_MODE[1]) & INVERT_MASK;
+
 	/* be sure to really write fan speed the first time */
 	th->last_speed[0] = -2;
 	th->last_speed[1] = -2;

From ab519a011caa5ec47d992cb8a4fc8e7af9b9e3f8 Mon Sep 17 00:00:00 2001
From: Nathan Fontenot <nfont@austin.ibm.com>
Date: Tue, 24 Nov 2009 21:10:49 +0000
Subject: [PATCH 132/151] powerpc/pseries: Kernel DLPAR Infrastructure

The Dynamic Logical Partitioning capabilities of the powerpc pseries platform
allows for the addition and removal of resources (i.e. CPU's, memory, and PCI
devices) from a partition. The removal of a resource involves
removing the resource's node from the device tree and then returning the
resource to firmware via the rtas set-indicator call.  To add a resource, it
is first obtained from firmware via the rtas set-indicator call and then a
new device tree node is created using the ibm,configure-coinnector rtas call
and added to the device tree.

This patch provides the kernel DLPAR infrastructure in a new filed named
dlpar.c.  The functionality provided is for acquiring and releasing a resource
from firmware and the parsing of information returned from the
ibm,configure-connector rtas call.  Additionally this exports the pSeries
reconfiguration notifier chain so that it can be invoked when device tree
updates are made.

Signed-off-by: Nathan Fontenot <nfont@austin.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pSeries_reconfig.h |   1 +
 arch/powerpc/platforms/pseries/Makefile     |   2 +-
 arch/powerpc/platforms/pseries/dlpar.c      | 344 ++++++++++++++++++++
 arch/powerpc/platforms/pseries/reconfig.c   |   2 +-
 4 files changed, 347 insertions(+), 2 deletions(-)
 create mode 100644 arch/powerpc/platforms/pseries/dlpar.c

diff --git a/arch/powerpc/include/asm/pSeries_reconfig.h b/arch/powerpc/include/asm/pSeries_reconfig.h
index e482e5352e69..d4b4bfa26fb3 100644
--- a/arch/powerpc/include/asm/pSeries_reconfig.h
+++ b/arch/powerpc/include/asm/pSeries_reconfig.h
@@ -17,6 +17,7 @@
 #ifdef CONFIG_PPC_PSERIES
 extern int pSeries_reconfig_notifier_register(struct notifier_block *);
 extern void pSeries_reconfig_notifier_unregister(struct notifier_block *);
+extern struct blocking_notifier_head pSeries_reconfig_chain;
 #else /* !CONFIG_PPC_PSERIES */
 static inline int pSeries_reconfig_notifier_register(struct notifier_block *nb)
 {
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 4b1c422b8145..0ff5174ae4f5 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -8,7 +8,7 @@ endif
 
 obj-y			:= lpar.o hvCall.o nvram.o reconfig.o \
 			   setup.o iommu.o ras.o \
-			   firmware.o power.o
+			   firmware.o power.o dlpar.o
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_XICS)	+= xics.o
 obj-$(CONFIG_SCANLOG)	+= scanlog.o
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
new file mode 100644
index 000000000000..c80e8ef0eb58
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -0,0 +1,344 @@
+/*
+ * Support for dynamic reconfiguration for PCI, Memory, and CPU
+ * Hotplug and Dynamic Logical Partitioning on RPA platforms.
+ *
+ * Copyright (C) 2009 Nathan Fontenot
+ * Copyright (C) 2009 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kref.h>
+#include <linux/notifier.h>
+#include <linux/proc_fs.h>
+#include <linux/spinlock.h>
+#include <linux/cpu.h>
+
+#include <asm/prom.h>
+#include <asm/machdep.h>
+#include <asm/uaccess.h>
+#include <asm/rtas.h>
+#include <asm/pSeries_reconfig.h>
+
+struct cc_workarea {
+	u32	drc_index;
+	u32	zero;
+	u32	name_offset;
+	u32	prop_length;
+	u32	prop_offset;
+};
+
+static void dlpar_free_cc_property(struct property *prop)
+{
+	kfree(prop->name);
+	kfree(prop->value);
+	kfree(prop);
+}
+
+static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa)
+{
+	struct property *prop;
+	char *name;
+	char *value;
+
+	prop = kzalloc(sizeof(*prop), GFP_KERNEL);
+	if (!prop)
+		return NULL;
+
+	name = (char *)ccwa + ccwa->name_offset;
+	prop->name = kstrdup(name, GFP_KERNEL);
+
+	prop->length = ccwa->prop_length;
+	value = (char *)ccwa + ccwa->prop_offset;
+	prop->value = kzalloc(prop->length, GFP_KERNEL);
+	if (!prop->value) {
+		dlpar_free_cc_property(prop);
+		return NULL;
+	}
+
+	memcpy(prop->value, value, prop->length);
+	return prop;
+}
+
+static struct device_node *dlpar_parse_cc_node(struct cc_workarea *ccwa)
+{
+	struct device_node *dn;
+	char *name;
+
+	dn = kzalloc(sizeof(*dn), GFP_KERNEL);
+	if (!dn)
+		return NULL;
+
+	/* The configure connector reported name does not contain a
+	 * preceeding '/', so we allocate a buffer large enough to
+	 * prepend this to the full_name.
+	 */
+	name = (char *)ccwa + ccwa->name_offset;
+	dn->full_name = kmalloc(strlen(name) + 2, GFP_KERNEL);
+	if (!dn->full_name) {
+		kfree(dn);
+		return NULL;
+	}
+
+	sprintf(dn->full_name, "/%s", name);
+	return dn;
+}
+
+static void dlpar_free_one_cc_node(struct device_node *dn)
+{
+	struct property *prop;
+
+	while (dn->properties) {
+		prop = dn->properties;
+		dn->properties = prop->next;
+		dlpar_free_cc_property(prop);
+	}
+
+	kfree(dn->full_name);
+	kfree(dn);
+}
+
+static void dlpar_free_cc_nodes(struct device_node *dn)
+{
+	if (dn->child)
+		dlpar_free_cc_nodes(dn->child);
+
+	if (dn->sibling)
+		dlpar_free_cc_nodes(dn->sibling);
+
+	dlpar_free_one_cc_node(dn);
+}
+
+#define NEXT_SIBLING    1
+#define NEXT_CHILD      2
+#define NEXT_PROPERTY   3
+#define PREV_PARENT     4
+#define MORE_MEMORY     5
+#define CALL_AGAIN	-2
+#define ERR_CFG_USE     -9003
+
+struct device_node *dlpar_configure_connector(u32 drc_index)
+{
+	struct device_node *dn;
+	struct device_node *first_dn = NULL;
+	struct device_node *last_dn = NULL;
+	struct property *property;
+	struct property *last_property = NULL;
+	struct cc_workarea *ccwa;
+	int cc_token;
+	int rc;
+
+	cc_token = rtas_token("ibm,configure-connector");
+	if (cc_token == RTAS_UNKNOWN_SERVICE)
+		return NULL;
+
+	spin_lock(&rtas_data_buf_lock);
+	ccwa = (struct cc_workarea *)&rtas_data_buf[0];
+	ccwa->drc_index = drc_index;
+	ccwa->zero = 0;
+
+	rc = rtas_call(cc_token, 2, 1, NULL, rtas_data_buf, NULL);
+	while (rc) {
+		switch (rc) {
+		case NEXT_SIBLING:
+			dn = dlpar_parse_cc_node(ccwa);
+			if (!dn)
+				goto cc_error;
+
+			dn->parent = last_dn->parent;
+			last_dn->sibling = dn;
+			last_dn = dn;
+			break;
+
+		case NEXT_CHILD:
+			dn = dlpar_parse_cc_node(ccwa);
+			if (!dn)
+				goto cc_error;
+
+			if (!first_dn)
+				first_dn = dn;
+			else {
+				dn->parent = last_dn;
+				if (last_dn)
+					last_dn->child = dn;
+			}
+
+			last_dn = dn;
+			break;
+
+		case NEXT_PROPERTY:
+			property = dlpar_parse_cc_property(ccwa);
+			if (!property)
+				goto cc_error;
+
+			if (!last_dn->properties)
+				last_dn->properties = property;
+			else
+				last_property->next = property;
+
+			last_property = property;
+			break;
+
+		case PREV_PARENT:
+			last_dn = last_dn->parent;
+			break;
+
+		case CALL_AGAIN:
+			break;
+
+		case MORE_MEMORY:
+		case ERR_CFG_USE:
+		default:
+			printk(KERN_ERR "Unexpected Error (%d) "
+			       "returned from configure-connector\n", rc);
+			goto cc_error;
+		}
+
+		rc = rtas_call(cc_token, 2, 1, NULL, rtas_data_buf, NULL);
+	}
+
+	spin_unlock(&rtas_data_buf_lock);
+	return first_dn;
+
+cc_error:
+	if (first_dn)
+		dlpar_free_cc_nodes(first_dn);
+	spin_unlock(&rtas_data_buf_lock);
+	return NULL;
+}
+
+static struct device_node *derive_parent(const char *path)
+{
+	struct device_node *parent;
+	char *last_slash;
+
+	last_slash = strrchr(path, '/');
+	if (last_slash == path) {
+		parent = of_find_node_by_path("/");
+	} else {
+		char *parent_path;
+		int parent_path_len = last_slash - path + 1;
+		parent_path = kmalloc(parent_path_len, GFP_KERNEL);
+		if (!parent_path)
+			return NULL;
+
+		strlcpy(parent_path, path, parent_path_len);
+		parent = of_find_node_by_path(parent_path);
+		kfree(parent_path);
+	}
+
+	return parent;
+}
+
+int dlpar_attach_node(struct device_node *dn)
+{
+	struct proc_dir_entry *ent;
+	int rc;
+
+	of_node_set_flag(dn, OF_DYNAMIC);
+	kref_init(&dn->kref);
+	dn->parent = derive_parent(dn->full_name);
+	if (!dn->parent)
+		return -ENOMEM;
+
+	rc = blocking_notifier_call_chain(&pSeries_reconfig_chain,
+					  PSERIES_RECONFIG_ADD, dn);
+	if (rc == NOTIFY_BAD) {
+		printk(KERN_ERR "Failed to add device node %s\n",
+		       dn->full_name);
+		return -ENOMEM; /* For now, safe to assume kmalloc failure */
+	}
+
+	of_attach_node(dn);
+
+#ifdef CONFIG_PROC_DEVICETREE
+	ent = proc_mkdir(strrchr(dn->full_name, '/') + 1, dn->parent->pde);
+	if (ent)
+		proc_device_tree_add_node(dn, ent);
+#endif
+
+	of_node_put(dn->parent);
+	return 0;
+}
+
+int dlpar_detach_node(struct device_node *dn)
+{
+	struct device_node *parent = dn->parent;
+	struct property *prop = dn->properties;
+
+#ifdef CONFIG_PROC_DEVICETREE
+	while (prop) {
+		remove_proc_entry(prop->name, dn->pde);
+		prop = prop->next;
+	}
+
+	if (dn->pde)
+		remove_proc_entry(dn->pde->name, parent->pde);
+#endif
+
+	blocking_notifier_call_chain(&pSeries_reconfig_chain,
+			    PSERIES_RECONFIG_REMOVE, dn);
+	of_detach_node(dn);
+	of_node_put(dn); /* Must decrement the refcount */
+
+	return 0;
+}
+
+#define DR_ENTITY_SENSE		9003
+#define DR_ENTITY_PRESENT	1
+#define DR_ENTITY_UNUSABLE	2
+#define ALLOCATION_STATE	9003
+#define ALLOC_UNUSABLE		0
+#define ALLOC_USABLE		1
+#define ISOLATION_STATE		9001
+#define ISOLATE			0
+#define UNISOLATE		1
+
+int dlpar_acquire_drc(u32 drc_index)
+{
+	int dr_status, rc;
+
+	rc = rtas_call(rtas_token("get-sensor-state"), 2, 2, &dr_status,
+		       DR_ENTITY_SENSE, drc_index);
+	if (rc || dr_status != DR_ENTITY_UNUSABLE)
+		return -1;
+
+	rc = rtas_set_indicator(ALLOCATION_STATE, drc_index, ALLOC_USABLE);
+	if (rc)
+		return rc;
+
+	rc = rtas_set_indicator(ISOLATION_STATE, drc_index, UNISOLATE);
+	if (rc) {
+		rtas_set_indicator(ALLOCATION_STATE, drc_index, ALLOC_UNUSABLE);
+		return rc;
+	}
+
+	return 0;
+}
+
+int dlpar_release_drc(u32 drc_index)
+{
+	int dr_status, rc;
+
+	rc = rtas_call(rtas_token("get-sensor-state"), 2, 2, &dr_status,
+		       DR_ENTITY_SENSE, drc_index);
+	if (rc || dr_status != DR_ENTITY_PRESENT)
+		return -1;
+
+	rc = rtas_set_indicator(ISOLATION_STATE, drc_index, ISOLATE);
+	if (rc)
+		return rc;
+
+	rc = rtas_set_indicator(ALLOCATION_STATE, drc_index, ALLOC_UNUSABLE);
+	if (rc) {
+		rtas_set_indicator(ISOLATION_STATE, drc_index, UNISOLATE);
+		return rc;
+	}
+
+	return 0;
+}
+
+
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 5182d2b992c6..a2305d29bbbd 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -96,7 +96,7 @@ static struct device_node *derive_parent(const char *path)
 	return parent;
 }
 
-static BLOCKING_NOTIFIER_HEAD(pSeries_reconfig_chain);
+BLOCKING_NOTIFIER_HEAD(pSeries_reconfig_chain);
 
 int pSeries_reconfig_notifier_register(struct notifier_block *nb)
 {

From 12633e803a2a556f6469e0933d08233d0844a2d9 Mon Sep 17 00:00:00 2001
From: Nathan Fontenot <nfont@austin.ibm.com>
Date: Wed, 25 Nov 2009 17:23:25 +0000
Subject: [PATCH 133/151] sysfs/cpu: Add probe/release files

Version 3 of this patch is updated with documentation added to
Documentation/ABI.  There are no changes to any of the C code from v2
of the patch.

In order to support kernel DLPAR of CPU resources we need to provide an
interface to add (probe) and remove (release) the resource from the system.
This patch Creates new generic probe and release sysfs files to facilitate
cpu probe/release.  The probe/release interface provides for allowing each
arch to supply their own routines for implementing the backend of adding
and removing cpus to/from the system.

This also creates the powerpc specific stubs to handle the arch callouts
from writes to the sysfs files.

The creation and use of these files is regulated by the
CONFIG_ARCH_CPU_PROBE_RELEASE option so that only architectures that need the
capability will have the files created.

Signed-off-by: Nathan Fontenot <nfont@austin.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 .../ABI/testing/sysfs-devices-system-cpu      | 15 +++++++++
 arch/powerpc/Kconfig                          |  4 +++
 arch/powerpc/include/asm/machdep.h            |  5 +++
 arch/powerpc/kernel/sysfs.c                   | 19 +++++++++++
 drivers/base/cpu.c                            | 32 +++++++++++++++++++
 include/linux/cpu.h                           |  2 ++
 6 files changed, 77 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index a703b9e9aeb9..d868a11c94a5 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -62,6 +62,21 @@ Description:	CPU topology files that describe kernel limits related to
 		See Documentation/cputopology.txt for more information.
 
 
+What:		/sys/devices/system/cpu/probe
+		/sys/devices/system/cpu/release
+Date:		November 2009
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Dynamic addition and removal of CPU's.  This is not hotplug
+		removal, this is meant complete removal/addition of the CPU
+		from the system.
+
+		probe: writes to this file will dynamically add a CPU to the
+		system.  Information written to the file to add CPU's is
+		architecture specific.
+
+		release: writes to this file dynamically remove a CPU from
+		the system.  Information writtento the file to remove CPU's
+		is architecture specific.
 
 What:		/sys/devices/system/cpu/cpu#/node
 Date:		October 2009
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 5dbd375a3f2a..0df57466e783 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -320,6 +320,10 @@ config HOTPLUG_CPU
 
 	  Say N if you are unsure.
 
+config ARCH_CPU_PROBE_RELEASE
+	def_bool y
+	depends on HOTPLUG_CPU
+
 config ARCH_ENABLE_MEMORY_HOTPLUG
 	def_bool y
 
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 9efa2be78331..9f0fc9e6ce0d 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -266,6 +266,11 @@ struct machdep_calls {
 	void (*suspend_disable_irqs)(void);
 	void (*suspend_enable_irqs)(void);
 #endif
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+	ssize_t (*cpu_probe)(const char *, size_t);
+	ssize_t (*cpu_release)(const char *, size_t);
+#endif
 };
 
 extern void e500_idle(void);
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 956ab33fd73f..e235e52dc4fe 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -461,6 +461,25 @@ static void unregister_cpu_online(unsigned int cpu)
 
 	cacheinfo_cpu_offline(cpu);
 }
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+ssize_t arch_cpu_probe(const char *buf, size_t count)
+{
+	if (ppc_md.cpu_probe)
+		return ppc_md.cpu_probe(buf, count);
+
+	return -EINVAL;
+}
+
+ssize_t arch_cpu_release(const char *buf, size_t count)
+{
+	if (ppc_md.cpu_release)
+		return ppc_md.cpu_release(buf, count);
+
+	return -EINVAL;
+}
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
+
 #endif /* CONFIG_HOTPLUG_CPU */
 
 static int __cpuinit sysfs_cpu_notify(struct notifier_block *self,
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index e62a4ccea54d..7c03af7b84a9 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -72,6 +72,38 @@ void unregister_cpu(struct cpu *cpu)
 	per_cpu(cpu_sys_devices, logical_cpu) = NULL;
 	return;
 }
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+static ssize_t cpu_probe_store(struct class *class, const char *buf,
+			       size_t count)
+{
+	return arch_cpu_probe(buf, count);
+}
+
+static ssize_t cpu_release_store(struct class *class, const char *buf,
+				 size_t count)
+{
+	return arch_cpu_release(buf, count);
+}
+
+static CLASS_ATTR(probe, S_IWUSR, NULL, cpu_probe_store);
+static CLASS_ATTR(release, S_IWUSR, NULL, cpu_release_store);
+
+int __init cpu_probe_release_init(void)
+{
+	int rc;
+
+	rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
+			       &class_attr_probe.attr);
+	if (!rc)
+		rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
+				       &class_attr_release.attr);
+
+	return rc;
+}
+device_initcall(cpu_probe_release_init);
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
+
 #else /* ... !CONFIG_HOTPLUG_CPU */
 static inline void register_cpu_control(struct cpu *cpu)
 {
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 47536197ffdd..c972f7ccb7d3 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -43,6 +43,8 @@ extern int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls);
 
 #ifdef CONFIG_HOTPLUG_CPU
 extern void unregister_cpu(struct cpu *cpu);
+extern ssize_t arch_cpu_probe(const char *, size_t);
+extern ssize_t arch_cpu_release(const char *, size_t);
 #endif
 struct notifier_block;
 

From 1a8061c46c46c960f715c597b9d279ea2ba42bd9 Mon Sep 17 00:00:00 2001
From: Nathan Fontenot <nfont@austin.ibm.com>
Date: Tue, 24 Nov 2009 21:13:32 +0000
Subject: [PATCH 134/151] powerpc/pseries: Add kernel based CPU DLPAR handling

This patch adds the specific routines to probe and release (add and remove)
cpu resource for the powerpc pseries platform and registers these handlers
with the ppc_md callout structure.

Signed-off-by: Nathan Fontenot <nfont@austin.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/dlpar.c | 88 ++++++++++++++++++++++++++
 1 file changed, 88 insertions(+)

diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index c80e8ef0eb58..fe8d4b3c50cd 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -341,4 +341,92 @@ int dlpar_release_drc(u32 drc_index)
 	return 0;
 }
 
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
 
+static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
+{
+	struct device_node *dn;
+	unsigned long drc_index;
+	char *cpu_name;
+	int rc;
+
+	rc = strict_strtoul(buf, 0, &drc_index);
+	if (rc)
+		return -EINVAL;
+
+	dn = dlpar_configure_connector(drc_index);
+	if (!dn)
+		return -EINVAL;
+
+	/* configure-connector reports cpus as living in the base
+	 * directory of the device tree.  CPUs actually live in the
+	 * cpus directory so we need to fixup the full_name.
+	 */
+	cpu_name = kzalloc(strlen(dn->full_name) + strlen("/cpus") + 1,
+			   GFP_KERNEL);
+	if (!cpu_name) {
+		dlpar_free_cc_nodes(dn);
+		return -ENOMEM;
+	}
+
+	sprintf(cpu_name, "/cpus%s", dn->full_name);
+	kfree(dn->full_name);
+	dn->full_name = cpu_name;
+
+	rc = dlpar_acquire_drc(drc_index);
+	if (rc) {
+		dlpar_free_cc_nodes(dn);
+		return -EINVAL;
+	}
+
+	rc = dlpar_attach_node(dn);
+	if (rc) {
+		dlpar_release_drc(drc_index);
+		dlpar_free_cc_nodes(dn);
+	}
+
+	return rc ? rc : count;
+}
+
+static ssize_t dlpar_cpu_release(const char *buf, size_t count)
+{
+	struct device_node *dn;
+	const u32 *drc_index;
+	int rc;
+
+	dn = of_find_node_by_path(buf);
+	if (!dn)
+		return -EINVAL;
+
+	drc_index = of_get_property(dn, "ibm,my-drc-index", NULL);
+	if (!drc_index) {
+		of_node_put(dn);
+		return -EINVAL;
+	}
+
+	rc = dlpar_release_drc(*drc_index);
+	if (rc) {
+		of_node_put(dn);
+		return -EINVAL;
+	}
+
+	rc = dlpar_detach_node(dn);
+	if (rc) {
+		dlpar_acquire_drc(*drc_index);
+		return rc;
+	}
+
+	of_node_put(dn);
+	return count;
+}
+
+static int __init pseries_dlpar_init(void)
+{
+	ppc_md.cpu_probe = dlpar_cpu_probe;
+	ppc_md.cpu_release = dlpar_cpu_release;
+
+	return 0;
+}
+machine_device_initcall(pseries, pseries_dlpar_init);
+
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */

From 8389b37dffdc695b4fb363ebe0ed9748bb3b48d0 Mon Sep 17 00:00:00 2001
From: Valentine Barshak <vbarshak@ru.mvista.com>
Date: Wed, 25 Nov 2009 11:48:52 +0000
Subject: [PATCH 135/151] powerpc: stop_this_cpu: remove the cpu from the
 online map.

Remove the CPU from the online map to prevent smp_call_function
from sending messages to a stopped CPU.

Signed-off-by: Valentine Barshak <vbarshak@ru.mvista.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/smp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 9b86a74d2815..97196eefef3e 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -218,6 +218,9 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
 
 static void stop_this_cpu(void *dummy)
 {
+	/* Remove this CPU */
+	set_cpu_online(smp_processor_id(), false);
+
 	local_irq_disable();
 	while (1)
 		;

From b6db63d1a7f0138f348ba7a648df35ac6365988e Mon Sep 17 00:00:00 2001
From: Gautham R Shenoy <ego@in.ibm.com>
Date: Thu, 26 Nov 2009 09:58:55 +0000
Subject: [PATCH 136/151] pseries/pseries: Add code to online/offline CPUs of a
 DLPAR node

Currently the cpu-allocation/deallocation on pSeries is a
two step process from the Userspace.

- Set the indicators and update the device tree by writing to the sysfs
  tunable "probe" during allocation and "release" during deallocation.
- Online / Offline the CPUs of the allocated/would_be_deallocated node by
  writing to the sysfs tunable "online".

This patch adds kernel code to online/offline the CPUs soon_after/just_before
they have been allocated/would_be_deallocated. This way, the userspace tool
that performs DLPAR operations would only have to deal with one set of sysfs
tunables namely "probe" and release".

Signed-off-by: Gautham R Shenoy <ego@in.ibm.com>
Signed-off-by: Nathan Fontenot <nfont@austin.ibm.com>
Acked-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/dlpar.c | 101 +++++++++++++++++++++++++
 1 file changed, 101 insertions(+)

diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index fe8d4b3c50cd..642e1b2e5c42 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -16,6 +16,7 @@
 #include <linux/proc_fs.h>
 #include <linux/spinlock.h>
 #include <linux/cpu.h>
+#include "offline_states.h"
 
 #include <asm/prom.h>
 #include <asm/machdep.h>
@@ -287,6 +288,98 @@ int dlpar_detach_node(struct device_node *dn)
 	return 0;
 }
 
+int online_node_cpus(struct device_node *dn)
+{
+	int rc = 0;
+	unsigned int cpu;
+	int len, nthreads, i;
+	const u32 *intserv;
+
+	intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
+	if (!intserv)
+		return -EINVAL;
+
+	nthreads = len / sizeof(u32);
+
+	cpu_maps_update_begin();
+	for (i = 0; i < nthreads; i++) {
+		for_each_present_cpu(cpu) {
+			if (get_hard_smp_processor_id(cpu) != intserv[i])
+				continue;
+			BUG_ON(get_cpu_current_state(cpu)
+					!= CPU_STATE_OFFLINE);
+			cpu_maps_update_done();
+			rc = cpu_up(cpu);
+			if (rc)
+				goto out;
+			cpu_maps_update_begin();
+
+			break;
+		}
+		if (cpu == num_possible_cpus())
+			printk(KERN_WARNING "Could not find cpu to online "
+			       "with physical id 0x%x\n", intserv[i]);
+	}
+	cpu_maps_update_done();
+
+out:
+	return rc;
+
+}
+
+int offline_node_cpus(struct device_node *dn)
+{
+	int rc = 0;
+	unsigned int cpu;
+	int len, nthreads, i;
+	const u32 *intserv;
+
+	intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
+	if (!intserv)
+		return -EINVAL;
+
+	nthreads = len / sizeof(u32);
+
+	cpu_maps_update_begin();
+	for (i = 0; i < nthreads; i++) {
+		for_each_present_cpu(cpu) {
+			if (get_hard_smp_processor_id(cpu) != intserv[i])
+				continue;
+
+			if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE)
+				break;
+
+			if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
+				cpu_maps_update_done();
+				rc = cpu_down(cpu);
+				if (rc)
+					goto out;
+				cpu_maps_update_begin();
+				break;
+
+			}
+
+			/*
+			 * The cpu is in CPU_STATE_INACTIVE.
+			 * Upgrade it's state to CPU_STATE_OFFLINE.
+			 */
+			set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
+			BUG_ON(plpar_hcall_norets(H_PROD, intserv[i])
+								!= H_SUCCESS);
+			__cpu_die(cpu);
+			break;
+		}
+		if (cpu == num_possible_cpus())
+			printk(KERN_WARNING "Could not find cpu to offline "
+			       "with physical id 0x%x\n", intserv[i]);
+	}
+	cpu_maps_update_done();
+
+out:
+	return rc;
+
+}
+
 #define DR_ENTITY_SENSE		9003
 #define DR_ENTITY_PRESENT	1
 #define DR_ENTITY_UNUSABLE	2
@@ -385,6 +478,8 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 		dlpar_free_cc_nodes(dn);
 	}
 
+	rc = online_node_cpus(dn);
+
 	return rc ? rc : count;
 }
 
@@ -404,6 +499,12 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count)
 		return -EINVAL;
 	}
 
+	rc = offline_node_cpus(dn);
+	if (rc) {
+		of_node_put(dn);
+		return -EINVAL;
+	}
+
 	rc = dlpar_release_drc(*drc_index);
 	if (rc) {
 		of_node_put(dn);

From 51badebdcf394cc5fd574a524b55b3f6085e5e9c Mon Sep 17 00:00:00 2001
From: Gautham R Shenoy <ego@in.ibm.com>
Date: Thu, 26 Nov 2009 09:59:05 +0000
Subject: [PATCH 137/151] powerpc/pseries: Serialize cpu hotplug operations
 during deactivate Vs deallocate

Currently the cpu-allocation/deallocation process comprises of two steps:
- Set the indicators and to update the device tree with DLPAR node
  information.

- Online/offline the allocated/deallocated CPU.

This is achieved by writing to the sysfs tunables "probe" during allocation
and "release" during deallocation.

At the sametime, the userspace can independently online/offline the CPUs of
the system using the sysfs tunable "online".

It is quite possible that when a userspace tool offlines a CPU
for the purpose of deallocation and is in the process of updating the device
tree, some other userspace tool could bring the CPU back online by writing to
the "online" sysfs tunable thereby causing the deallocate process to fail.

The solution to this is to serialize writes to the "probe/release" sysfs
tunable with the writes to the "online" sysfs tunable.

This patch employs a mutex to provide this serialization, which is a no-op on
all architectures except PPC_PSERIES

Signed-off-by: Gautham R Shenoy <ego@in.ibm.com>
Acked-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/dlpar.c | 45 ++++++++++++++++++++------
 drivers/base/cpu.c                     |  2 ++
 include/linux/cpu.h                    | 13 ++++++++
 3 files changed, 50 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 642e1b2e5c42..fd2f0afeb4de 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -436,6 +436,18 @@ int dlpar_release_drc(u32 drc_index)
 
 #ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
 
+static DEFINE_MUTEX(pseries_cpu_hotplug_mutex);
+
+void cpu_hotplug_driver_lock()
+{
+	mutex_lock(&pseries_cpu_hotplug_mutex);
+}
+
+void cpu_hotplug_driver_unlock()
+{
+	mutex_unlock(&pseries_cpu_hotplug_mutex);
+}
+
 static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 {
 	struct device_node *dn;
@@ -443,13 +455,18 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 	char *cpu_name;
 	int rc;
 
+	cpu_hotplug_driver_lock();
 	rc = strict_strtoul(buf, 0, &drc_index);
-	if (rc)
-		return -EINVAL;
+	if (rc) {
+		rc = -EINVAL;
+		goto out;
+	}
 
 	dn = dlpar_configure_connector(drc_index);
-	if (!dn)
-		return -EINVAL;
+	if (!dn) {
+		rc = -EINVAL;
+		goto out;
+	}
 
 	/* configure-connector reports cpus as living in the base
 	 * directory of the device tree.  CPUs actually live in the
@@ -459,7 +476,8 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 			   GFP_KERNEL);
 	if (!cpu_name) {
 		dlpar_free_cc_nodes(dn);
-		return -ENOMEM;
+		rc = -ENOMEM;
+		goto out;
 	}
 
 	sprintf(cpu_name, "/cpus%s", dn->full_name);
@@ -469,7 +487,8 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 	rc = dlpar_acquire_drc(drc_index);
 	if (rc) {
 		dlpar_free_cc_nodes(dn);
-		return -EINVAL;
+		rc = -EINVAL;
+		goto out;
 	}
 
 	rc = dlpar_attach_node(dn);
@@ -479,6 +498,8 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 	}
 
 	rc = online_node_cpus(dn);
+out:
+	cpu_hotplug_driver_unlock();
 
 	return rc ? rc : count;
 }
@@ -499,26 +520,30 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count)
 		return -EINVAL;
 	}
 
+	cpu_hotplug_driver_lock();
 	rc = offline_node_cpus(dn);
 	if (rc) {
 		of_node_put(dn);
-		return -EINVAL;
+		rc = -EINVAL;
+		goto out;
 	}
 
 	rc = dlpar_release_drc(*drc_index);
 	if (rc) {
 		of_node_put(dn);
-		return -EINVAL;
+		goto out;
 	}
 
 	rc = dlpar_detach_node(dn);
 	if (rc) {
 		dlpar_acquire_drc(*drc_index);
-		return rc;
+		goto out;
 	}
 
 	of_node_put(dn);
-	return count;
+out:
+	cpu_hotplug_driver_unlock();
+	return rc ? rc : count;
 }
 
 static int __init pseries_dlpar_init(void)
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 7c03af7b84a9..27fd775375b0 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -35,6 +35,7 @@ static ssize_t __ref store_online(struct sys_device *dev, struct sysdev_attribut
 	struct cpu *cpu = container_of(dev, struct cpu, sysdev);
 	ssize_t ret;
 
+	cpu_hotplug_driver_lock();
 	switch (buf[0]) {
 	case '0':
 		ret = cpu_down(cpu->sysdev.id);
@@ -49,6 +50,7 @@ static ssize_t __ref store_online(struct sys_device *dev, struct sysdev_attribut
 	default:
 		ret = -EINVAL;
 	}
+	cpu_hotplug_driver_unlock();
 
 	if (ret >= 0)
 		ret = count;
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index c972f7ccb7d3..e287863ac053 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -117,6 +117,19 @@ extern void put_online_cpus(void);
 #define unregister_hotcpu_notifier(nb)	unregister_cpu_notifier(nb)
 int cpu_down(unsigned int cpu);
 
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+extern void cpu_hotplug_driver_lock(void);
+extern void cpu_hotplug_driver_unlock(void);
+#else
+static inline void cpu_hotplug_driver_lock(void)
+{
+}
+
+static inline void cpu_hotplug_driver_unlock(void)
+{
+}
+#endif
+
 #else		/* CONFIG_HOTPLUG_CPU */
 
 #define get_online_cpus()	do { } while (0)

From 5efab4a02c89c252fb4cce097aafde5f8208dbfe Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@transmode.se>
Date: Fri, 20 Nov 2009 00:21:02 +0000
Subject: [PATCH 138/151] powerpc/8xx: Invalidate non present TLBs

8xx sometimes need to load a invalid/non-present TLBs in
it DTLB asm handler.

These must be invalidated separaly as linux mm don't.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/mm/fault.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index e7dae82c1285..26fb6b990b0a 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -40,7 +40,7 @@
 #include <asm/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/siginfo.h>
-
+#include <mm/mmu_decl.h>
 
 #ifdef CONFIG_KPROBES
 static inline int notify_page_fault(struct pt_regs *regs)
@@ -246,6 +246,12 @@ good_area:
 		goto bad_area;
 #endif /* CONFIG_6xx */
 #if defined(CONFIG_8xx)
+	/* 8xx sometimes need to load a invalid/non-present TLBs.
+	 * These must be invalidated separately as linux mm don't.
+	 */
+	if (error_code & 0x40000000) /* no translation? */
+		_tlbil_va(address, 0, 0, 0);
+
         /* The MPC8xx seems to always set 0x80000000, which is
          * "undefined".  Of those that can be set, this is the only
          * one which seems bad.

From fe11dc3f9628e5393e932567b7e29d35cbbad136 Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@transmode.se>
Date: Fri, 20 Nov 2009 00:21:03 +0000
Subject: [PATCH 139/151] powerpc/8xx: Update TLB asm so it behaves as linux mm
 expects.

Update the TLB asm to make proper use of _PAGE_DIRY and _PAGE_ACCESSED.
Get rid of _PAGE_HWWRITE too.
Pros:
 - I/D TLB Miss never needs to write to the linux pte.
 - _PAGE_ACCESSED is only set on TLB Error fixing accounting
 - _PAGE_DIRTY is mapped to 0x100, the changed bit, and is set directly
    when a page has been made dirty.
 - Proper RO/RW mapping of user space.
 - Free up 2 SW TLB bits in the linux pte(add back _PAGE_WRITETHRU ?)
 - kernel RO/user NA support.
Cons:
 - A few more instructions in the TLB Miss routines.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pte-8xx.h | 13 ++--
 arch/powerpc/kernel/head_8xx.S     | 99 +++++++++++++++---------------
 2 files changed, 57 insertions(+), 55 deletions(-)

diff --git a/arch/powerpc/include/asm/pte-8xx.h b/arch/powerpc/include/asm/pte-8xx.h
index dd5ea95fe61e..68ba861331ee 100644
--- a/arch/powerpc/include/asm/pte-8xx.h
+++ b/arch/powerpc/include/asm/pte-8xx.h
@@ -33,21 +33,20 @@
 #define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
 #define _PAGE_SHARED	0x0004	/* No ASID (context) compare */
 #define _PAGE_SPECIAL	0x0008	/* SW entry, forced to 0 by the TLB miss */
+#define _PAGE_DIRTY	0x0100	/* C: page changed */
 
-/* These five software bits must be masked out when the entry is loaded
- * into the TLB.
+/* These 3 software bits must be masked out when the entry is loaded
+ * into the TLB, 2 SW bits left.
  */
 #define _PAGE_GUARDED	0x0010	/* software: guarded access */
-#define _PAGE_DIRTY	0x0020	/* software: page changed */
-#define _PAGE_RW	0x0040	/* software: user write access allowed */
-#define _PAGE_ACCESSED	0x0080	/* software: page referenced */
+#define _PAGE_ACCESSED	0x0020	/* software: page referenced */
 
 /* Setting any bits in the nibble with the follow two controls will
  * require a TLB exception handler change.  It is assumed unused bits
  * are always zero.
  */
-#define _PAGE_HWWRITE	0x0100	/* h/w write enable: never set in Linux PTE */
-#define _PAGE_USER	0x0800	/* One of the PP bits, the other is USER&~RW */
+#define _PAGE_RW	0x0400	/* lsb PP bits, inverted in HW */
+#define _PAGE_USER	0x0800	/* msb PP bits */
 
 #define _PMD_PRESENT	0x0001
 #define _PMD_BAD	0x0ff0
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 6ded19d01891..97bd523a0278 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -333,26 +333,20 @@ InstructionTLBMiss:
 	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
 	lwz	r10, 0(r11)	/* Get the pte */
 
-#ifdef CONFIG_SWAP
-	/* do not set the _PAGE_ACCESSED bit of a non-present page */
-	andi.	r11, r10, _PAGE_PRESENT
-	beq	4f
-	ori	r10, r10, _PAGE_ACCESSED
-	mfspr	r11, SPRN_MD_TWC	/* get the pte address again */
-	stw	r10, 0(r11)
-4:
-#else
-	ori	r10, r10, _PAGE_ACCESSED
-	stw	r10, 0(r11)
-#endif
+	andi.	r11, r10, _PAGE_ACCESSED | _PAGE_PRESENT
+	cmpwi	cr0, r11, _PAGE_ACCESSED | _PAGE_PRESENT
+	bne-	cr0, 2f
+
+	/* Clear PP lsb, 0x400 */
+	rlwinm 	r10, r10, 0, 22, 20
 
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
+	 * Software indicator bits 22 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-2:	li	r11, 0x00f0
+	li	r11, 0x00f0
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
 	DO_8xx_CPU6(0x2d80, r3)
 	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */
@@ -365,6 +359,22 @@ InstructionTLBMiss:
 	lwz	r3, 8(r0)
 #endif
 	rfi
+2:
+	mfspr	r11, SPRN_SRR1
+	/* clear all error bits as TLB Miss
+	 * sets a few unconditionally
+	*/
+	rlwinm	r11, r11, 0, 0xffff
+	mtspr	SPRN_SRR1, r11
+
+	mfspr	r10, SPRN_M_TW	/* Restore registers */
+	lwz	r11, 0(r0)
+	mtcr	r11
+	lwz	r11, 4(r0)
+#ifdef CONFIG_8xx_CPU6
+	lwz	r3, 8(r0)
+#endif
+	b	InstructionAccess
 
 	. = 0x1200
 DataStoreTLBMiss:
@@ -409,21 +419,27 @@ DataStoreTLBMiss:
 	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	SPRN_MD_TWC, r11
 
-#ifdef CONFIG_SWAP
-	/* do not set the _PAGE_ACCESSED bit of a non-present page */
-	andi.	r11, r10, _PAGE_PRESENT
-	beq	4f
-	ori	r10, r10, _PAGE_ACCESSED
-4:
-	/* and update pte in table */
-#else
-	ori	r10, r10, _PAGE_ACCESSED
-#endif
-	mfspr	r11, SPRN_MD_TWC	/* get the pte address again */
-	stw	r10, 0(r11)
+	/* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set.
+	 * We also need to know if the insn is a load/store, so:
+	 * Clear _PAGE_PRESENT and load that which will
+	 * trap into DTLB Error with store bit set accordinly.
+	 */
+	/* PRESENT=0x1, ACCESSED=0x20
+	 * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
+	 * r10 = (r10 & ~PRESENT) | r11;
+	 */
+	rlwinm	r11, r10, 32-5, 31, 31
+	and	r11, r11, r10
+	rlwimi	r10, r11, 0, 31, 31
+
+	/* Honour kernel RO, User NA */
+	andi.	r11, r10, _PAGE_USER | _PAGE_RW
+	bne-	cr0, 5f
+	ori	r10,r10, 0x200 /* Extended encoding, bit 22 */
+5:	xori	r10, r10, _PAGE_RW  /* invert RW bit */
 
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
+	 * Software indicator bits 22 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
@@ -469,11 +485,12 @@ DataTLBError:
 	stw	r10, 0(r0)
 	stw	r11, 4(r0)
 
-	/* First, make sure this was a store operation.
+	mfspr	r11, SPRN_DSISR
+	andis.	r11, r11, 0x4800	/* !translation or protection */
+	bne	2f	/* branch if either is set */
+	/* Only Change bit left now, do it here as it is faster
+	 * than trapping to the C fault handler.
 	*/
-	mfspr	r10, SPRN_DSISR
-	andis.	r11, r10, 0x0200	/* If set, indicates store op */
-	beq	2f
 
 	/* The EA of a data TLB miss is automatically stored in the MD_EPN
 	 * register.  The EA of a data TLB error is automatically stored in
@@ -522,26 +539,12 @@ DataTLBError:
 	mfspr	r11, SPRN_MD_TWC		/* ....and get the pte address */
 	lwz	r10, 0(r11)		/* Get the pte */
 
-	andi.	r11, r10, _PAGE_RW	/* Is it writeable? */
-	beq	2f			/* Bail out if not */
-
-	/* Update 'changed', among others.
-	*/
-#ifdef CONFIG_SWAP
-	ori	r10, r10, _PAGE_DIRTY|_PAGE_HWWRITE
-	/* do not set the _PAGE_ACCESSED bit of a non-present page */
-	andi.	r11, r10, _PAGE_PRESENT
-	beq	4f
-	ori	r10, r10, _PAGE_ACCESSED
-4:
-#else
-	ori	r10, r10, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
-#endif
-	mfspr	r11, SPRN_MD_TWC		/* Get pte address again */
+	ori	r10, r10, _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_HWWRITE
 	stw	r10, 0(r11)		/* and update pte in table */
+	xori	r10, r10, _PAGE_RW	/* RW bit is inverted */
 
 	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 21, 22 and 28 must be clear.
+	 * Software indicator bits 22 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.

From 60e071fee994ff98c37d03a4a7c5a3f8b1e3b8e5 Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@transmode.se>
Date: Fri, 20 Nov 2009 00:21:04 +0000
Subject: [PATCH 140/151] powerpc/8xx: Tag DAR with 0x00f0 to catch buggy
 instructions.

dcbz, dcbf, dcbi, dcbst and icbi do not set DAR when they
cause a DTLB Error. Dectect this by tagging DAR with 0x00f0
at every exception exit that modifies DAR.
Test for DAR=0x00f0 in DataTLBError and bail
to handle_page_fault().

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/head_8xx.S | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 97bd523a0278..a9f1ace484d5 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -206,6 +206,8 @@ MachineCheck:
 	EXCEPTION_PROLOG
 	mfspr r4,SPRN_DAR
 	stw r4,_DAR(r11)
+	li r5,0x00f0
+	mtspr SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
 	mfspr r5,SPRN_DSISR
 	stw r5,_DSISR(r11)
 	addi r3,r1,STACK_FRAME_OVERHEAD
@@ -222,6 +224,8 @@ DataAccess:
 	stw	r10,_DSISR(r11)
 	mr	r5,r10
 	mfspr	r4,SPRN_DAR
+	li	r10,0x00f0
+	mtspr	SPRN_DAR,r10	/* Tag DAR, to be used in DTLB Error */
 	EXC_XFER_EE_LITE(0x300, handle_page_fault)
 
 /* Instruction access exception.
@@ -244,6 +248,8 @@ Alignment:
 	EXCEPTION_PROLOG
 	mfspr	r4,SPRN_DAR
 	stw	r4,_DAR(r11)
+	li	r5,0x00f0
+	mtspr	SPRN_DAR,r5	/* Tag DAR, to be used in DTLB Error */
 	mfspr	r5,SPRN_DSISR
 	stw	r5,_DSISR(r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
@@ -445,6 +451,7 @@ DataStoreTLBMiss:
 	 * of the MMU.
 	 */
 2:	li	r11, 0x00f0
+	mtspr	SPRN_DAR,r11	/* Tag DAR */
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
 	DO_8xx_CPU6(0x3d80, r3)
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
@@ -485,6 +492,10 @@ DataTLBError:
 	stw	r10, 0(r0)
 	stw	r11, 4(r0)
 
+	mfspr	r10, SPRN_DAR
+	cmpwi	cr0, r10, 0x00f0
+	beq-	2f	/* must be a buggy dcbX, icbi insn. */
+
 	mfspr	r11, SPRN_DSISR
 	andis.	r11, r11, 0x4800	/* !translation or protection */
 	bne	2f	/* branch if either is set */
@@ -508,7 +519,8 @@ DataTLBError:
 	 * are initialized in mapin_ram().  This will avoid the problem,
 	 * assuming we only use the dcbi instruction on kernel addresses.
 	 */
-	mfspr	r10, SPRN_DAR
+
+	/* DAR is in r10 already */
 	rlwinm	r11, r10, 0, 0, 19
 	ori	r11, r11, MD_EVALID
 	mfspr	r10, SPRN_M_CASID
@@ -550,6 +562,7 @@ DataTLBError:
 	 * of the MMU.
 	 */
 	li	r11, 0x00f0
+	mtspr	SPRN_DAR,r11	/* Tag DAR */
 	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
 	DO_8xx_CPU6(0x3d80, r3)
 	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */

From 0a2ab51ffb8dfdf51402dcfb446629648c96bc78 Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@transmode.se>
Date: Fri, 20 Nov 2009 00:21:06 +0000
Subject: [PATCH 141/151] powerpc/8xx: Fixup DAR from buggy dcbX instructions.

This is an assembler version to fixup DAR not being set
by dcbX, icbi instructions. There are two versions, one
uses selfmodifing code, the other uses a
jump table but is much bigger(default).

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/head_8xx.S | 147 ++++++++++++++++++++++++++++++++-
 1 file changed, 143 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index a9f1ace484d5..c00120d56f8f 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -494,11 +494,16 @@ DataTLBError:
 
 	mfspr	r10, SPRN_DAR
 	cmpwi	cr0, r10, 0x00f0
-	beq-	2f	/* must be a buggy dcbX, icbi insn. */
-
+	beq-	FixupDAR	/* must be a buggy dcbX, icbi insn. */
+DARFixed:/* Return from dcbx instruction bug workaround, r10 holds value of DAR */
 	mfspr	r11, SPRN_DSISR
-	andis.	r11, r11, 0x4800	/* !translation or protection */
-	bne	2f	/* branch if either is set */
+	/* As the DAR fixup may clear store we may have all 3 states zero.
+	 * Make sure only 0x0200(store) falls down into DIRTY handling
+	 */
+	andis.	r11, r11, 0x4a00	/* !translation, protection or store */
+	srwi	r11, r11, 16
+	cmpwi	cr0, r11, 0x0200	/* just store ? */
+	bne	2f
 	/* Only Change bit left now, do it here as it is faster
 	 * than trapping to the C fault handler.
 	*/
@@ -604,6 +609,140 @@ DataTLBError:
 
 	. = 0x2000
 
+/* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions
+ * by decoding the registers used by the dcbx instruction and adding them.
+ * DAR is set to the calculated address and r10 also holds the EA on exit.
+ */
+ /* define if you don't want to use self modifying code */
+#define NO_SELF_MODIFYING_CODE
+FixupDAR:/* Entry point for dcbx workaround. */
+	/* fetch instruction from memory. */
+	mfspr	r10, SPRN_SRR0
+	DO_8xx_CPU6(0x3780, r3)
+	mtspr	SPRN_MD_EPN, r10
+	mfspr	r11, SPRN_M_TWB	/* Get level 1 table entry address */
+	cmplwi	cr0, r11, 0x0800
+	blt-	3f		/* Branch if user space */
+	lis	r11, (swapper_pg_dir-PAGE_OFFSET)@h
+	ori	r11, r11, (swapper_pg_dir-PAGE_OFFSET)@l
+	rlwimi	r11, r10, 32-20, 0xffc /* r11 = r11&~0xffc|(r10>>20)&0xffc */
+3:	lwz	r11, 0(r11)	/* Get the level 1 entry */
+	DO_8xx_CPU6(0x3b80, r3)
+	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
+	mfspr	r11, SPRN_MD_TWC	/* ....and get the pte address */
+	lwz	r11, 0(r11)	/* Get the pte */
+	/* concat physical page address(r11) and page offset(r10) */
+	rlwimi	r11, r10, 0, 20, 31
+	lwz	r11,0(r11)
+/* Check if it really is a dcbx instruction. */
+/* dcbt and dcbtst does not generate DTLB Misses/Errors,
+ * no need to include them here */
+	srwi	r10, r11, 26	/* check if major OP code is 31 */
+	cmpwi	cr0, r10, 31
+	bne-	141f
+	rlwinm	r10, r11, 0, 21, 30
+	cmpwi	cr0, r10, 2028	/* Is dcbz? */
+	beq+	142f
+	cmpwi	cr0, r10, 940	/* Is dcbi? */
+	beq+	142f
+	cmpwi	cr0, r10, 108	/* Is dcbst? */
+	beq+	144f		/* Fix up store bit! */
+	cmpwi	cr0, r10, 172	/* Is dcbf? */
+	beq+	142f
+	cmpwi	cr0, r10, 1964	/* Is icbi? */
+	beq+	142f
+141:	mfspr	r10, SPRN_DAR	/* r10 must hold DAR at exit */
+	b	DARFixed	/* Nope, go back to normal TLB processing */
+
+144:	mfspr	r10, SPRN_DSISR
+	rlwinm	r10, r10,0,7,5	/* Clear store bit for buggy dcbst insn */
+	mtspr	SPRN_DSISR, r10
+142:	/* continue, it was a dcbx, dcbi instruction. */
+#ifdef CONFIG_8xx_CPU6
+	lwz	r3, 8(r0)	/* restore r3 from memory */
+#endif
+#ifndef NO_SELF_MODIFYING_CODE
+	andis.	r10,r11,0x1f	/* test if reg RA is r0 */
+	li	r10,modified_instr@l
+	dcbtst	r0,r10		/* touch for store */
+	rlwinm	r11,r11,0,0,20	/* Zero lower 10 bits */
+	oris	r11,r11,640	/* Transform instr. to a "add r10,RA,RB" */
+	ori	r11,r11,532
+	stw	r11,0(r10)	/* store add/and instruction */
+	dcbf	0,r10		/* flush new instr. to memory. */
+	icbi	0,r10		/* invalidate instr. cache line */
+	lwz	r11, 4(r0)	/* restore r11 from memory */
+	mfspr	r10, SPRN_M_TW	/* restore r10 from M_TW */
+	isync			/* Wait until new instr is loaded from memory */
+modified_instr:
+	.space	4		/* this is where the add instr. is stored */
+	bne+	143f
+	subf	r10,r0,r10	/* r10=r10-r0, only if reg RA is r0 */
+143:	mtdar	r10		/* store faulting EA in DAR */
+	b	DARFixed	/* Go back to normal TLB handling */
+#else
+	mfctr	r10
+	mtdar	r10			/* save ctr reg in DAR */
+	rlwinm	r10, r11, 24, 24, 28	/* offset into jump table for reg RB */
+	addi	r10, r10, 150f@l	/* add start of table */
+	mtctr	r10			/* load ctr with jump address */
+	xor	r10, r10, r10		/* sum starts at zero */
+	bctr				/* jump into table */
+150:
+	add	r10, r10, r0	;b	151f
+	add	r10, r10, r1	;b	151f
+	add	r10, r10, r2	;b	151f
+	add	r10, r10, r3	;b	151f
+	add	r10, r10, r4	;b	151f
+	add	r10, r10, r5	;b	151f
+	add	r10, r10, r6	;b	151f
+	add	r10, r10, r7	;b	151f
+	add	r10, r10, r8	;b	151f
+	add	r10, r10, r9	;b	151f
+	mtctr	r11	;b	154f	/* r10 needs special handling */
+	mtctr	r11	;b	153f	/* r11 needs special handling */
+	add	r10, r10, r12	;b	151f
+	add	r10, r10, r13	;b	151f
+	add	r10, r10, r14	;b	151f
+	add	r10, r10, r15	;b	151f
+	add	r10, r10, r16	;b	151f
+	add	r10, r10, r17	;b	151f
+	add	r10, r10, r18	;b	151f
+	add	r10, r10, r19	;b	151f
+	add	r10, r10, r20	;b	151f
+	add	r10, r10, r21	;b	151f
+	add	r10, r10, r22	;b	151f
+	add	r10, r10, r23	;b	151f
+	add	r10, r10, r24	;b	151f
+	add	r10, r10, r25	;b	151f
+	add	r10, r10, r26	;b	151f
+	add	r10, r10, r27	;b	151f
+	add	r10, r10, r28	;b	151f
+	add	r10, r10, r29	;b	151f
+	add	r10, r10, r30	;b	151f
+	add	r10, r10, r31
+151:
+	rlwinm. r11,r11,19,24,28	/* offset into jump table for reg RA */
+	beq	152f			/* if reg RA is zero, don't add it */
+	addi	r11, r11, 150b@l	/* add start of table */
+	mtctr	r11			/* load ctr with jump address */
+	rlwinm	r11,r11,0,16,10		/* make sure we don't execute this more than once */
+	bctr				/* jump into table */
+152:
+	mfdar	r11
+	mtctr	r11			/* restore ctr reg from DAR */
+	mtdar	r10			/* save fault EA to DAR */
+	b	DARFixed		/* Go back to normal TLB handling */
+
+	/* special handling for r10,r11 since these are modified already */
+153:	lwz	r11, 4(r0)	/* load r11 from memory */
+	b	155f
+154:	mfspr	r11, SPRN_M_TW	/* load r10 from M_TW */
+155:	add	r10, r10, r11	/* add it */
+	mfctr	r11		/* restore r11 */
+	b	151b
+#endif
+
 	.globl	giveup_fpu
 giveup_fpu:
 	blr

From 4a280a413c0c0da03936483384c9e5142966635e Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@transmode.se>
Date: Fri, 20 Nov 2009 00:21:07 +0000
Subject: [PATCH 142/151] powerpc/8xx: Add missing Guarded setting in DTLB
 Error.

only DTLB Miss did set this bit, DTLB Error needs too otherwise
the setting is lost when the page becomes dirty.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/head_8xx.S | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index c00120d56f8f..1a28ee8ca318 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -552,9 +552,16 @@ DARFixed:/* Return from dcbx instruction bug workaround, r10 holds value of DAR
 	 */
 	ori	r11, r11, 1		/* Set valid bit in physical L2 page */
 	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11		/* Load pte table base address */
-	mfspr	r11, SPRN_MD_TWC		/* ....and get the pte address */
-	lwz	r10, 0(r11)		/* Get the pte */
+	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
+	mfspr	r10, SPRN_MD_TWC	/* ....and get the pte address */
+	lwz	r10, 0(r10)		/* Get the pte */
+	/* Insert the Guarded flag into the TWC from the Linux PTE.
+	 * It is bit 27 of both the Linux PTE and the TWC
+	 */
+	rlwimi	r11, r10, 0, 27, 27
+	DO_8xx_CPU6(0x3b80, r3)
+	mtspr	SPRN_MD_TWC, r11
+	mfspr	r11, SPRN_MD_TWC	/* get the pte address again */
 
 	ori	r10, r10, _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_HWWRITE
 	stw	r10, 0(r11)		/* and update pte in table */

From 0c4661698c58db2a9efc44f403b893bd4d98f348 Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@transmode.se>
Date: Fri, 20 Nov 2009 00:21:08 +0000
Subject: [PATCH 143/151] powerpc/8xx: Restore _PAGE_WRITETHRU

8xx has not had WRITETHRU due to lack of bits in the pte.
After the recent rewrite of the 8xx TLB code, there are
two bits left. Use one of them to WRITETHRU.

Perhaps use the last SW bit to PAGE_SPECIAL or PAGE_FILE?

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/pte-8xx.h | 5 +++--
 arch/powerpc/kernel/head_8xx.S     | 8 ++++++++
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/pte-8xx.h b/arch/powerpc/include/asm/pte-8xx.h
index 68ba861331ee..d44826e4ff97 100644
--- a/arch/powerpc/include/asm/pte-8xx.h
+++ b/arch/powerpc/include/asm/pte-8xx.h
@@ -35,11 +35,12 @@
 #define _PAGE_SPECIAL	0x0008	/* SW entry, forced to 0 by the TLB miss */
 #define _PAGE_DIRTY	0x0100	/* C: page changed */
 
-/* These 3 software bits must be masked out when the entry is loaded
- * into the TLB, 2 SW bits left.
+/* These 4 software bits must be masked out when the entry is loaded
+ * into the TLB, 1 SW bit left(0x0080).
  */
 #define _PAGE_GUARDED	0x0010	/* software: guarded access */
 #define _PAGE_ACCESSED	0x0020	/* software: page referenced */
+#define _PAGE_WRITETHRU	0x0040	/* software: caching is write through */
 
 /* Setting any bits in the nibble with the follow two controls will
  * require a TLB exception handler change.  It is assumed unused bits
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 1a28ee8ca318..c4ae85b8f8c0 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -422,6 +422,10 @@ DataStoreTLBMiss:
 	 * above.
 	 */
 	rlwimi	r11, r10, 0, 27, 27
+	/* Insert the WriteThru flag into the TWC from the Linux PTE.
+	 * It is bit 25 in the Linux PTE and bit 30 in the TWC
+	 */
+	rlwimi	r11, r10, 32-5, 30, 30
 	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	SPRN_MD_TWC, r11
 
@@ -559,6 +563,10 @@ DARFixed:/* Return from dcbx instruction bug workaround, r10 holds value of DAR
 	 * It is bit 27 of both the Linux PTE and the TWC
 	 */
 	rlwimi	r11, r10, 0, 27, 27
+	/* Insert the WriteThru flag into the TWC from the Linux PTE.
+	 * It is bit 25 in the Linux PTE and bit 30 in the TWC
+	 */
+	rlwimi	r11, r10, 32-5, 30, 30
 	DO_8xx_CPU6(0x3b80, r3)
 	mtspr	SPRN_MD_TWC, r11
 	mfspr	r11, SPRN_MD_TWC	/* get the pte address again */

From 15d914d72a3f4f1531c41c084cb556be22aa1d2e Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@transmode.se>
Date: Fri, 20 Nov 2009 00:21:09 +0000
Subject: [PATCH 144/151] powerpc/8xx: Start using dcbX instructions in various
 copy routines

Now that 8xx can fixup dcbX instructions, start using them
where possible like every other PowerPc arch do.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/misc_32.S | 18 ------------------
 arch/powerpc/lib/copy_32.S    | 24 ------------------------
 2 files changed, 42 deletions(-)

diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index da9c0c4c10f3..8649f536f8df 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -502,15 +502,7 @@ _GLOBAL(clear_pages)
 	li	r0,PAGE_SIZE/L1_CACHE_BYTES
 	slw	r0,r0,r4
 	mtctr	r0
-#ifdef CONFIG_8xx
-	li	r4, 0
-1:	stw	r4, 0(r3)
-	stw	r4, 4(r3)
-	stw	r4, 8(r3)
-	stw	r4, 12(r3)
-#else
 1:	dcbz	0,r3
-#endif
 	addi	r3,r3,L1_CACHE_BYTES
 	bdnz	1b
 	blr
@@ -535,15 +527,6 @@ _GLOBAL(copy_page)
 	addi	r3,r3,-4
 	addi	r4,r4,-4
 
-#ifdef CONFIG_8xx
-	/* don't use prefetch on 8xx */
-    	li	r0,4096/L1_CACHE_BYTES
-	mtctr	r0
-1:	COPY_16_BYTES
-	bdnz	1b
-	blr
-
-#else	/* not 8xx, we can prefetch */
 	li	r5,4
 
 #if MAX_COPY_PREFETCH > 1
@@ -584,7 +567,6 @@ _GLOBAL(copy_page)
 	li	r0,MAX_COPY_PREFETCH
 	li	r11,4
 	b	2b
-#endif	/* CONFIG_8xx */
 
 /*
  * void atomic_clear_mask(atomic_t mask, atomic_t *addr)
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index c657de59abca..74a7f4130b4c 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -98,20 +98,7 @@ _GLOBAL(cacheable_memzero)
 	bdnz	4b
 3:	mtctr	r9
 	li	r7,4
-#if !defined(CONFIG_8xx)
 10:	dcbz	r7,r6
-#else
-10:	stw	r4, 4(r6)
-	stw	r4, 8(r6)
-	stw	r4, 12(r6)
-	stw	r4, 16(r6)
-#if CACHE_LINE_SIZE >= 32
-	stw	r4, 20(r6)
-	stw	r4, 24(r6)
-	stw	r4, 28(r6)
-	stw	r4, 32(r6)
-#endif /* CACHE_LINE_SIZE */
-#endif
 	addi	r6,r6,CACHELINE_BYTES
 	bdnz	10b
 	clrlwi	r5,r8,32-LG_CACHELINE_BYTES
@@ -200,9 +187,7 @@ _GLOBAL(cacheable_memcpy)
 	mtctr	r0
 	beq	63f
 53:
-#if !defined(CONFIG_8xx)
 	dcbz	r11,r6
-#endif
 	COPY_16_BYTES
 #if L1_CACHE_BYTES >= 32
 	COPY_16_BYTES
@@ -356,14 +341,6 @@ _GLOBAL(__copy_tofrom_user)
 	li	r11,4
 	beq	63f
 
-#ifdef CONFIG_8xx
-	/* Don't use prefetch on 8xx */
-	mtctr	r0
-	li	r0,0
-53:	COPY_16_BYTES_WITHEX(0)
-	bdnz	53b
-
-#else /* not CONFIG_8xx */
 	/* Here we decide how far ahead to prefetch the source */
 	li	r3,4
 	cmpwi	r0,1
@@ -416,7 +393,6 @@ _GLOBAL(__copy_tofrom_user)
 	li	r3,4
 	li	r7,0
 	bne	114b
-#endif /* CONFIG_8xx */
 
 63:	srwi.	r0,r5,2
 	mtctr	r0

From 2321f33790a6c5b80322d907a92d5739e7521a13 Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@transmode.se>
Date: Fri, 20 Nov 2009 00:21:10 +0000
Subject: [PATCH 145/151] powerpc/8xx: Remove DIRTY pte handling in DTLB Error.

There is no need to do set the DIRTY bit directly in DTLB Error.
Trap to do_page_fault() and let the generic MM code do the work.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/head_8xx.S | 96 ----------------------------------
 1 file changed, 96 deletions(-)

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index c4ae85b8f8c0..f2de8e8a825c 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -500,102 +500,6 @@ DataTLBError:
 	cmpwi	cr0, r10, 0x00f0
 	beq-	FixupDAR	/* must be a buggy dcbX, icbi insn. */
 DARFixed:/* Return from dcbx instruction bug workaround, r10 holds value of DAR */
-	mfspr	r11, SPRN_DSISR
-	/* As the DAR fixup may clear store we may have all 3 states zero.
-	 * Make sure only 0x0200(store) falls down into DIRTY handling
-	 */
-	andis.	r11, r11, 0x4a00	/* !translation, protection or store */
-	srwi	r11, r11, 16
-	cmpwi	cr0, r11, 0x0200	/* just store ? */
-	bne	2f
-	/* Only Change bit left now, do it here as it is faster
-	 * than trapping to the C fault handler.
-	*/
-
-	/* The EA of a data TLB miss is automatically stored in the MD_EPN
-	 * register.  The EA of a data TLB error is automatically stored in
-	 * the DAR, but not the MD_EPN register.  We must copy the 20 most
-	 * significant bits of the EA from the DAR to MD_EPN before we
-	 * start walking the page tables.  We also need to copy the CASID
-	 * value from the M_CASID register.
-	 * Addendum:  The EA of a data TLB error is _supposed_ to be stored
-	 * in DAR, but it seems that this doesn't happen in some cases, such
-	 * as when the error is due to a dcbi instruction to a page with a
-	 * TLB that doesn't have the changed bit set.  In such cases, there
-	 * does not appear to be any way  to recover the EA of the error
-	 * since it is neither in DAR nor MD_EPN.  As a workaround, the
-	 * _PAGE_HWWRITE bit is set for all kernel data pages when the PTEs
-	 * are initialized in mapin_ram().  This will avoid the problem,
-	 * assuming we only use the dcbi instruction on kernel addresses.
-	 */
-
-	/* DAR is in r10 already */
-	rlwinm	r11, r10, 0, 0, 19
-	ori	r11, r11, MD_EVALID
-	mfspr	r10, SPRN_M_CASID
-	rlwimi	r11, r10, 0, 28, 31
-	DO_8xx_CPU6(0x3780, r3)
-	mtspr	SPRN_MD_EPN, r11
-
-	mfspr	r10, SPRN_M_TWB	/* Get level 1 table entry address */
-
-	/* If we are faulting a kernel address, we have to use the
-	 * kernel page tables.
-	 */
-	andi.	r11, r10, 0x0800
-	beq	3f
-	lis	r11, swapper_pg_dir@h
-	ori	r11, r11, swapper_pg_dir@l
-	rlwimi	r10, r11, 0, 2, 19
-3:
-	lwz	r11, 0(r10)	/* Get the level 1 entry */
-	rlwinm.	r10, r11,0,0,19	/* Extract page descriptor page address */
-	beq	2f		/* If zero, bail */
-
-	/* We have a pte table, so fetch the pte from the table.
-	 */
-	ori	r11, r11, 1		/* Set valid bit in physical L2 page */
-	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11	/* Load pte table base address */
-	mfspr	r10, SPRN_MD_TWC	/* ....and get the pte address */
-	lwz	r10, 0(r10)		/* Get the pte */
-	/* Insert the Guarded flag into the TWC from the Linux PTE.
-	 * It is bit 27 of both the Linux PTE and the TWC
-	 */
-	rlwimi	r11, r10, 0, 27, 27
-	/* Insert the WriteThru flag into the TWC from the Linux PTE.
-	 * It is bit 25 in the Linux PTE and bit 30 in the TWC
-	 */
-	rlwimi	r11, r10, 32-5, 30, 30
-	DO_8xx_CPU6(0x3b80, r3)
-	mtspr	SPRN_MD_TWC, r11
-	mfspr	r11, SPRN_MD_TWC	/* get the pte address again */
-
-	ori	r10, r10, _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_HWWRITE
-	stw	r10, 0(r11)		/* and update pte in table */
-	xori	r10, r10, _PAGE_RW	/* RW bit is inverted */
-
-	/* The Linux PTE won't go exactly into the MMU TLB.
-	 * Software indicator bits 22 and 28 must be clear.
-	 * Software indicator bits 24, 25, 26, and 27 must be
-	 * set.  All other Linux PTE bits control the behavior
-	 * of the MMU.
-	 */
-	li	r11, 0x00f0
-	mtspr	SPRN_DAR,r11	/* Tag DAR */
-	rlwimi	r10, r11, 0, 24, 28	/* Set 24-27, clear 28 */
-	DO_8xx_CPU6(0x3d80, r3)
-	mtspr	SPRN_MD_RPN, r10	/* Update TLB entry */
-
-	mfspr	r10, SPRN_M_TW	/* Restore registers */
-	lwz	r11, 0(r0)
-	mtcr	r11
-	lwz	r11, 4(r0)
-#ifdef CONFIG_8xx_CPU6
-	lwz	r3, 8(r0)
-#endif
-	rfi
-2:
 	mfspr	r10, SPRN_M_TW	/* Restore registers */
 	lwz	r11, 0(r0)
 	mtcr	r11

From 990d89c6636c1be300a4f2f914b95200b237d017 Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@transmode.se>
Date: Fri, 20 Nov 2009 00:21:11 +0000
Subject: [PATCH 146/151] powerpc/8xx: DTLB Miss cleanup

Use symbolic constant for PRESENT and avoid branching.

Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/kernel/head_8xx.S | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index f2de8e8a825c..678f98cd5e64 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -438,15 +438,20 @@ DataStoreTLBMiss:
 	 * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
 	 * r10 = (r10 & ~PRESENT) | r11;
 	 */
-	rlwinm	r11, r10, 32-5, 31, 31
+	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
 	and	r11, r11, r10
-	rlwimi	r10, r11, 0, 31, 31
+	rlwimi	r10, r11, 0, _PAGE_PRESENT
 
 	/* Honour kernel RO, User NA */
-	andi.	r11, r10, _PAGE_USER | _PAGE_RW
-	bne-	cr0, 5f
-	ori	r10,r10, 0x200 /* Extended encoding, bit 22 */
-5:	xori	r10, r10, _PAGE_RW  /* invert RW bit */
+	/* 0x200 == Extended encoding, bit 22 */
+	/* r11 =  (r10 & _PAGE_USER) >> 2 */
+	rlwinm	r11, r10, 32-2, 0x200
+	or	r10, r11, r10
+	/* r11 =  (r10 & _PAGE_RW) >> 1 */
+	rlwinm	r11, r10, 32-1, 0x200
+	or	r10, r11, r10
+	/* invert RW and 0x200 bits */
+	xori	r10, r10, _PAGE_RW | 0x200
 
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 22 and 28 must be clear.

From 40d50cf7ca956183f3a573bc21082e1c7d04fa7b Mon Sep 17 00:00:00 2001
From: Roman Fietze <roman.fietze@telemotive.de>
Date: Tue, 8 Dec 2009 02:39:50 +0000
Subject: [PATCH 147/151] powerpc: Make "intspec" pointers in irq_host->xlate()
 const

Writing a driver using SCLPC on the MPC5200B I detected, that the
intspec arrays to map irqs to Linux virq cannot be const, because the
mapping and xlate functions only take non const pointers. All those
functions do not modify the intspec, so a const pointer could be used.

Signed-off-by: Roman Fietze <roman.fietze@telemotive.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/include/asm/irq.h                  | 4 ++--
 arch/powerpc/kernel/irq.c                       | 2 +-
 arch/powerpc/platforms/52xx/media5200.c         | 2 +-
 arch/powerpc/platforms/52xx/mpc52xx_gpt.c       | 2 +-
 arch/powerpc/platforms/52xx/mpc52xx_pic.c       | 2 +-
 arch/powerpc/platforms/85xx/socrates_fpga_pic.c | 2 +-
 arch/powerpc/platforms/86xx/gef_pic.c           | 2 +-
 arch/powerpc/platforms/cell/beat_interrupt.c    | 4 ++--
 arch/powerpc/platforms/cell/interrupt.c         | 2 +-
 arch/powerpc/platforms/cell/spider-pic.c        | 2 +-
 arch/powerpc/platforms/powermac/pic.c           | 2 +-
 arch/powerpc/platforms/pseries/xics.c           | 2 +-
 arch/powerpc/sysdev/cpm2_pic.c                  | 2 +-
 arch/powerpc/sysdev/i8259.c                     | 2 +-
 arch/powerpc/sysdev/ipic.c                      | 2 +-
 arch/powerpc/sysdev/mpc8xx_pic.c                | 2 +-
 arch/powerpc/sysdev/mpic.c                      | 2 +-
 arch/powerpc/sysdev/qe_lib/qe_ic.c              | 2 +-
 arch/powerpc/sysdev/tsi108_pci.c                | 2 +-
 arch/powerpc/sysdev/uic.c                       | 2 +-
 arch/powerpc/sysdev/xilinx_intc.c               | 2 +-
 21 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index c85a32f1a17f..e054baef1845 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -100,7 +100,7 @@ struct irq_host_ops {
 	 * interrupt controller has for that line)
 	 */
 	int (*xlate)(struct irq_host *h, struct device_node *ctrler,
-		     u32 *intspec, unsigned int intsize,
+		     const u32 *intspec, unsigned int intsize,
 		     irq_hw_number_t *out_hwirq, unsigned int *out_type);
 };
 
@@ -314,7 +314,7 @@ extern void irq_free_virt(unsigned int virq, unsigned int count);
  * of the of_irq_map_*() functions.
  */
 extern unsigned int irq_create_of_mapping(struct device_node *controller,
-					  u32 *intspec, unsigned int intsize);
+					  const u32 *intspec, unsigned int intsize);
 
 /**
  * irq_of_parse_and_map - Parse and Map an interrupt into linux virq space
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index a31176ace02b..042a53009701 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -725,7 +725,7 @@ unsigned int irq_create_mapping(struct irq_host *host,
 EXPORT_SYMBOL_GPL(irq_create_mapping);
 
 unsigned int irq_create_of_mapping(struct device_node *controller,
-				   u32 *intspec, unsigned int intsize)
+				   const u32 *intspec, unsigned int intsize)
 {
 	struct irq_host *host;
 	irq_hw_number_t hwirq;
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 85001a4cbdff..cc0c854291d7 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -127,7 +127,7 @@ static int media5200_irq_map(struct irq_host *h, unsigned int virq,
 }
 
 static int media5200_irq_xlate(struct irq_host *h, struct device_node *ct,
-				 u32 *intspec, unsigned int intsize,
+				 const u32 *intspec, unsigned int intsize,
 				 irq_hw_number_t *out_hwirq,
 				 unsigned int *out_flags)
 {
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 17ecdf4c87ae..6f8ebe1085b3 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -214,7 +214,7 @@ static int mpc52xx_gpt_irq_map(struct irq_host *h, unsigned int virq,
 }
 
 static int mpc52xx_gpt_irq_xlate(struct irq_host *h, struct device_node *ct,
-				 u32 *intspec, unsigned int intsize,
+				 const u32 *intspec, unsigned int intsize,
 				 irq_hw_number_t *out_hwirq,
 				 unsigned int *out_flags)
 {
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index a3122d163b6a..4bf4bf7b063e 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -355,7 +355,7 @@ static int mpc52xx_is_extirq(int l1, int l2)
  * mpc52xx_irqhost_xlate - translate virq# from device tree interrupts property
  */
 static int mpc52xx_irqhost_xlate(struct irq_host *h, struct device_node *ct,
-				 u32 *intspec, unsigned int intsize,
+				 const u32 *intspec, unsigned int intsize,
 				 irq_hw_number_t *out_hwirq,
 				 unsigned int *out_flags)
 {
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index 37a2e5f60af9..e5da5f62b24a 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -253,7 +253,7 @@ static int socrates_fpga_pic_host_map(struct irq_host *h, unsigned int virq,
 }
 
 static int socrates_fpga_pic_host_xlate(struct irq_host *h,
-		struct device_node *ct,	u32 *intspec, unsigned int intsize,
+		struct device_node *ct,	const u32 *intspec, unsigned int intsize,
 		irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 {
 	struct socrates_fpga_irq_info *fpga_irq = &fpga_irqs[intspec[0]];
diff --git a/arch/powerpc/platforms/86xx/gef_pic.c b/arch/powerpc/platforms/86xx/gef_pic.c
index e1d5d36995df..0110a8736d33 100644
--- a/arch/powerpc/platforms/86xx/gef_pic.c
+++ b/arch/powerpc/platforms/86xx/gef_pic.c
@@ -170,7 +170,7 @@ static int gef_pic_host_map(struct irq_host *h, unsigned int virq,
 }
 
 static int gef_pic_host_xlate(struct irq_host *h, struct device_node *ct,
-			    u32 *intspec, unsigned int intsize,
+			    const u32 *intspec, unsigned int intsize,
 			    irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 {
 
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index c3479a47d45a..36052a9ebcda 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -166,11 +166,11 @@ static void beatic_pic_host_remap(struct irq_host *h, unsigned int virq,
  * Note: We have only 1 entry to translate.
  */
 static int beatic_pic_host_xlate(struct irq_host *h, struct device_node *ct,
-				 u32 *intspec, unsigned int intsize,
+				 const u32 *intspec, unsigned int intsize,
 				 irq_hw_number_t *out_hwirq,
 				 unsigned int *out_flags)
 {
-	u64 *intspec2 = (u64 *)intspec;
+	const u64 *intspec2 = (const u64 *)intspec;
 
 	*out_hwirq = *intspec2;
 	*out_flags |= IRQ_TYPE_LEVEL_LOW;
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 3b67afba3f9b..f9dbf76a763f 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -297,7 +297,7 @@ static int iic_host_map(struct irq_host *h, unsigned int virq,
 }
 
 static int iic_host_xlate(struct irq_host *h, struct device_node *ct,
-			   u32 *intspec, unsigned int intsize,
+			   const u32 *intspec, unsigned int intsize,
 			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
 {
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 167dedaada76..01244f254a11 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -187,7 +187,7 @@ static int spider_host_map(struct irq_host *h, unsigned int virq,
 }
 
 static int spider_host_xlate(struct irq_host *h, struct device_node *ct,
-			   u32 *intspec, unsigned int intsize,
+			   const u32 *intspec, unsigned int intsize,
 			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
 {
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 99d0b313e9a5..09e827296276 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -303,7 +303,7 @@ static int pmac_pic_host_map(struct irq_host *h, unsigned int virq,
 }
 
 static int pmac_pic_host_xlate(struct irq_host *h, struct device_node *ct,
-			       u32 *intspec, unsigned int intsize,
+			       const u32 *intspec, unsigned int intsize,
 			       irq_hw_number_t *out_hwirq,
 			       unsigned int *out_flags)
 
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 6592becd4410..690f87584f6b 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -434,7 +434,7 @@ static int xics_host_map(struct irq_host *h, unsigned int virq,
 }
 
 static int xics_host_xlate(struct irq_host *h, struct device_node *ct,
-			   u32 *intspec, unsigned int intsize,
+			   const u32 *intspec, unsigned int intsize,
 			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
 {
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index 059ea4e5e25f..971483f0dfac 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -218,7 +218,7 @@ static int cpm2_pic_host_map(struct irq_host *h, unsigned int virq,
 }
 
 static int cpm2_pic_host_xlate(struct irq_host *h, struct device_node *ct,
-			    u32 *intspec, unsigned int intsize,
+			    const u32 *intspec, unsigned int intsize,
 			    irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 {
 	*out_hwirq = intspec[0];
diff --git a/arch/powerpc/sysdev/i8259.c b/arch/powerpc/sysdev/i8259.c
index ba8f1f708992..0a55db8a5a29 100644
--- a/arch/powerpc/sysdev/i8259.c
+++ b/arch/powerpc/sysdev/i8259.c
@@ -198,7 +198,7 @@ static void i8259_host_unmap(struct irq_host *h, unsigned int virq)
 }
 
 static int i8259_host_xlate(struct irq_host *h, struct device_node *ct,
-			    u32 *intspec, unsigned int intsize,
+			    const u32 *intspec, unsigned int intsize,
 			    irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 {
 	static unsigned char map_isa_senses[4] = {
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index c89d78075ba0..28cdddd2f89e 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -697,7 +697,7 @@ static int ipic_host_map(struct irq_host *h, unsigned int virq,
 }
 
 static int ipic_host_xlate(struct irq_host *h, struct device_node *ct,
-			   u32 *intspec, unsigned int intsize,
+			   const u32 *intspec, unsigned int intsize,
 			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
 {
diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c
index db0a712f6075..69bd6f4dff83 100644
--- a/arch/powerpc/sysdev/mpc8xx_pic.c
+++ b/arch/powerpc/sysdev/mpc8xx_pic.c
@@ -130,7 +130,7 @@ static int mpc8xx_pic_host_map(struct irq_host *h, unsigned int virq,
 
 
 static int mpc8xx_pic_host_xlate(struct irq_host *h, struct device_node *ct,
-			    u32 *intspec, unsigned int intsize,
+			    const u32 *intspec, unsigned int intsize,
 			    irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 {
 	static unsigned char map_pic_senses[4] = {
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 7a64bc5808da..aa9d06e5925b 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -994,7 +994,7 @@ static int mpic_host_map(struct irq_host *h, unsigned int virq,
 }
 
 static int mpic_host_xlate(struct irq_host *h, struct device_node *ct,
-			   u32 *intspec, unsigned int intsize,
+			   const u32 *intspec, unsigned int intsize,
 			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 
 {
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index c1e17b3d3982..2acc928d1920 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -271,7 +271,7 @@ static int qe_ic_host_map(struct irq_host *h, unsigned int virq,
 }
 
 static int qe_ic_host_xlate(struct irq_host *h, struct device_node *ct,
-			    u32 * intspec, unsigned int intsize,
+			    const u32 * intspec, unsigned int intsize,
 			    irq_hw_number_t * out_hwirq,
 			    unsigned int *out_flags)
 {
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index 47769d2359d6..595034cfb85a 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -384,7 +384,7 @@ static struct irq_chip tsi108_pci_irq = {
 };
 
 static int pci_irq_host_xlate(struct irq_host *h, struct device_node *ct,
-			    u32 *intspec, unsigned int intsize,
+			    const u32 *intspec, unsigned int intsize,
 			    irq_hw_number_t *out_hwirq, unsigned int *out_flags)
 {
 	*out_hwirq = intspec[0];
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index c907601e44db..7d10074b3304 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -202,7 +202,7 @@ static int uic_host_map(struct irq_host *h, unsigned int virq,
 }
 
 static int uic_host_xlate(struct irq_host *h, struct device_node *ct,
-			  u32 *intspec, unsigned int intsize,
+			  const u32 *intspec, unsigned int intsize,
 			  irq_hw_number_t *out_hwirq, unsigned int *out_type)
 
 {
diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c
index 45eb225ec25e..1e0ccfaf403e 100644
--- a/arch/powerpc/sysdev/xilinx_intc.c
+++ b/arch/powerpc/sysdev/xilinx_intc.c
@@ -148,7 +148,7 @@ static struct irq_chip xilinx_intc_edge_irqchip = {
  * xilinx_intc_xlate - translate virq# from device tree interrupts property
  */
 static int xilinx_intc_xlate(struct irq_host *h, struct device_node *ct,
-				u32 *intspec, unsigned int intsize,
+				const u32 *intspec, unsigned int intsize,
 				irq_hw_number_t *out_hwirq,
 				unsigned int *out_flags)
 {

From 275a64f6040073254fa15eaf6e4e720f77d531d6 Mon Sep 17 00:00:00 2001
From: Nathan Fontenot <nfont@austin.ibm.com>
Date: Tue, 8 Dec 2009 09:48:44 +0000
Subject: [PATCH 148/151] powerpc/pseries: Correct pseries/dlpar.c build break
 without CONFIG_SMP

The recent patch to add cpu offline/online as part of the DLPAR
process for pseries causes a build break if CONFIG_SMP is not
defined.  Original patch here;
http://lists.ozlabs.org/pipermail/linuxppc-dev/2009-November/078299.html

This corrects the build break by moving the online_node_cpus
and offline_node_cpus under the #ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
portions of dlpar.c.

This patch also slightly modifies the online_node_cpus and offline_node_cpus
routines to prepend dlpar_ to the them and make them static.  These two
routine are only used in the dlpar add/remove of cpus and these changes
should help clarify that.

Signed-off-by: Nathan Fontenot <nfont@austin.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/dlpar.c | 188 ++++++++++++-------------
 1 file changed, 94 insertions(+), 94 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index fd2f0afeb4de..12df9e8812a9 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -288,98 +288,6 @@ int dlpar_detach_node(struct device_node *dn)
 	return 0;
 }
 
-int online_node_cpus(struct device_node *dn)
-{
-	int rc = 0;
-	unsigned int cpu;
-	int len, nthreads, i;
-	const u32 *intserv;
-
-	intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
-	if (!intserv)
-		return -EINVAL;
-
-	nthreads = len / sizeof(u32);
-
-	cpu_maps_update_begin();
-	for (i = 0; i < nthreads; i++) {
-		for_each_present_cpu(cpu) {
-			if (get_hard_smp_processor_id(cpu) != intserv[i])
-				continue;
-			BUG_ON(get_cpu_current_state(cpu)
-					!= CPU_STATE_OFFLINE);
-			cpu_maps_update_done();
-			rc = cpu_up(cpu);
-			if (rc)
-				goto out;
-			cpu_maps_update_begin();
-
-			break;
-		}
-		if (cpu == num_possible_cpus())
-			printk(KERN_WARNING "Could not find cpu to online "
-			       "with physical id 0x%x\n", intserv[i]);
-	}
-	cpu_maps_update_done();
-
-out:
-	return rc;
-
-}
-
-int offline_node_cpus(struct device_node *dn)
-{
-	int rc = 0;
-	unsigned int cpu;
-	int len, nthreads, i;
-	const u32 *intserv;
-
-	intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
-	if (!intserv)
-		return -EINVAL;
-
-	nthreads = len / sizeof(u32);
-
-	cpu_maps_update_begin();
-	for (i = 0; i < nthreads; i++) {
-		for_each_present_cpu(cpu) {
-			if (get_hard_smp_processor_id(cpu) != intserv[i])
-				continue;
-
-			if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE)
-				break;
-
-			if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
-				cpu_maps_update_done();
-				rc = cpu_down(cpu);
-				if (rc)
-					goto out;
-				cpu_maps_update_begin();
-				break;
-
-			}
-
-			/*
-			 * The cpu is in CPU_STATE_INACTIVE.
-			 * Upgrade it's state to CPU_STATE_OFFLINE.
-			 */
-			set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
-			BUG_ON(plpar_hcall_norets(H_PROD, intserv[i])
-								!= H_SUCCESS);
-			__cpu_die(cpu);
-			break;
-		}
-		if (cpu == num_possible_cpus())
-			printk(KERN_WARNING "Could not find cpu to offline "
-			       "with physical id 0x%x\n", intserv[i]);
-	}
-	cpu_maps_update_done();
-
-out:
-	return rc;
-
-}
-
 #define DR_ENTITY_SENSE		9003
 #define DR_ENTITY_PRESENT	1
 #define DR_ENTITY_UNUSABLE	2
@@ -448,6 +356,45 @@ void cpu_hotplug_driver_unlock()
 	mutex_unlock(&pseries_cpu_hotplug_mutex);
 }
 
+static int dlpar_online_cpu(struct device_node *dn)
+{
+	int rc = 0;
+	unsigned int cpu;
+	int len, nthreads, i;
+	const u32 *intserv;
+
+	intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
+	if (!intserv)
+		return -EINVAL;
+
+	nthreads = len / sizeof(u32);
+
+	cpu_maps_update_begin();
+	for (i = 0; i < nthreads; i++) {
+		for_each_present_cpu(cpu) {
+			if (get_hard_smp_processor_id(cpu) != intserv[i])
+				continue;
+			BUG_ON(get_cpu_current_state(cpu)
+					!= CPU_STATE_OFFLINE);
+			cpu_maps_update_done();
+			rc = cpu_up(cpu);
+			if (rc)
+				goto out;
+			cpu_maps_update_begin();
+
+			break;
+		}
+		if (cpu == num_possible_cpus())
+			printk(KERN_WARNING "Could not find cpu to online "
+			       "with physical id 0x%x\n", intserv[i]);
+	}
+	cpu_maps_update_done();
+
+out:
+	return rc;
+
+}
+
 static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 {
 	struct device_node *dn;
@@ -497,13 +444,66 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 		dlpar_free_cc_nodes(dn);
 	}
 
-	rc = online_node_cpus(dn);
+	rc = dlpar_online_cpu(dn);
 out:
 	cpu_hotplug_driver_unlock();
 
 	return rc ? rc : count;
 }
 
+static int dlpar_offline_cpu(struct device_node *dn)
+{
+	int rc = 0;
+	unsigned int cpu;
+	int len, nthreads, i;
+	const u32 *intserv;
+
+	intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len);
+	if (!intserv)
+		return -EINVAL;
+
+	nthreads = len / sizeof(u32);
+
+	cpu_maps_update_begin();
+	for (i = 0; i < nthreads; i++) {
+		for_each_present_cpu(cpu) {
+			if (get_hard_smp_processor_id(cpu) != intserv[i])
+				continue;
+
+			if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE)
+				break;
+
+			if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) {
+				cpu_maps_update_done();
+				rc = cpu_down(cpu);
+				if (rc)
+					goto out;
+				cpu_maps_update_begin();
+				break;
+
+			}
+
+			/*
+			 * The cpu is in CPU_STATE_INACTIVE.
+			 * Upgrade it's state to CPU_STATE_OFFLINE.
+			 */
+			set_preferred_offline_state(cpu, CPU_STATE_OFFLINE);
+			BUG_ON(plpar_hcall_norets(H_PROD, intserv[i])
+								!= H_SUCCESS);
+			__cpu_die(cpu);
+			break;
+		}
+		if (cpu == num_possible_cpus())
+			printk(KERN_WARNING "Could not find cpu to offline "
+			       "with physical id 0x%x\n", intserv[i]);
+	}
+	cpu_maps_update_done();
+
+out:
+	return rc;
+
+}
+
 static ssize_t dlpar_cpu_release(const char *buf, size_t count)
 {
 	struct device_node *dn;
@@ -521,7 +521,7 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count)
 	}
 
 	cpu_hotplug_driver_lock();
-	rc = offline_node_cpus(dn);
+	rc = dlpar_offline_cpu(dn);
 	if (rc) {
 		of_node_put(dn);
 		rc = -EINVAL;

From 49bd3647134ea47420067aea8d1401e722bf2aac Mon Sep 17 00:00:00 2001
From: Mark Nelson <markn@au1.ibm.com>
Date: Mon, 7 Dec 2009 20:32:17 +0000
Subject: [PATCH 149/151] powerpc/pseries: Track previous CPPR values to
 correctly EOI interrupts

At the moment when we EOI an interrupt we set the CPPR back to 0xFF
regardless of its previous value. This could lead to problems if we
take an interrupt with a priority of 5, but before EOIing it we get
an IPI which has a priority of 4. The problem is that at the moment
when we EOI the IPI we will set the CPPR to 0xFF, but it should
really be set back to 5 (the previous priority).

To keep track of the previous CPPR values we create the xics_cppr
structure that has an array for CPPR values and an index pointing
to the current priority. This can easily grow if new priorities get
added in the future.

This will also be useful because the partition adjunct option of
upcoming machines will update the H_XIRR hcall to accept the CPPR
as a parameter.

Signed-off-by: Mark Nelson <markn@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/platforms/pseries/xics.c | 56 ++++++++++++++++++++++++---
 1 file changed, 51 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 690f87584f6b..7d01b58f3989 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -20,6 +20,7 @@
 #include <linux/cpu.h>
 #include <linux/msi.h>
 #include <linux/of.h>
+#include <linux/percpu.h>
 
 #include <asm/firmware.h>
 #include <asm/io.h>
@@ -46,6 +47,12 @@ static struct irq_host *xics_host;
  */
 #define IPI_PRIORITY		4
 
+/* The least favored priority */
+#define LOWEST_PRIORITY		0xFF
+
+/* The number of priorities defined above */
+#define MAX_NUM_PRIORITIES	3
+
 static unsigned int default_server = 0xFF;
 static unsigned int default_distrib_server = 0;
 static unsigned int interrupt_server_size = 8;
@@ -56,6 +63,12 @@ static int ibm_set_xive;
 static int ibm_int_on;
 static int ibm_int_off;
 
+struct xics_cppr {
+	unsigned char stack[MAX_NUM_PRIORITIES];
+	int index;
+};
+
+static DEFINE_PER_CPU(struct xics_cppr, xics_cppr);
 
 /* Direct hardware low level accessors */
 
@@ -284,6 +297,19 @@ static inline unsigned int xics_xirr_vector(unsigned int xirr)
 	return xirr & 0x00ffffff;
 }
 
+static void push_cppr(unsigned int vec)
+{
+	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+
+	if (WARN_ON(os_cppr->index >= MAX_NUM_PRIORITIES - 1))
+		return;
+
+	if (vec == XICS_IPI)
+		os_cppr->stack[++os_cppr->index] = IPI_PRIORITY;
+	else
+		os_cppr->stack[++os_cppr->index] = DEFAULT_PRIORITY;
+}
+
 static unsigned int xics_get_irq_direct(void)
 {
 	unsigned int xirr = direct_xirr_info_get();
@@ -294,8 +320,10 @@ static unsigned int xics_get_irq_direct(void)
 		return NO_IRQ;
 
 	irq = irq_radix_revmap_lookup(xics_host, vec);
-	if (likely(irq != NO_IRQ))
+	if (likely(irq != NO_IRQ)) {
+		push_cppr(vec);
 		return irq;
+	}
 
 	/* We don't have a linux mapping, so have rtas mask it. */
 	xics_mask_unknown_vec(vec);
@@ -315,8 +343,10 @@ static unsigned int xics_get_irq_lpar(void)
 		return NO_IRQ;
 
 	irq = irq_radix_revmap_lookup(xics_host, vec);
-	if (likely(irq != NO_IRQ))
+	if (likely(irq != NO_IRQ)) {
+		push_cppr(vec);
 		return irq;
+	}
 
 	/* We don't have a linux mapping, so have RTAS mask it. */
 	xics_mask_unknown_vec(vec);
@@ -326,12 +356,22 @@ static unsigned int xics_get_irq_lpar(void)
 	return NO_IRQ;
 }
 
+static unsigned char pop_cppr(void)
+{
+	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+
+	if (WARN_ON(os_cppr->index < 1))
+		return LOWEST_PRIORITY;
+
+	return os_cppr->stack[--os_cppr->index];
+}
+
 static void xics_eoi_direct(unsigned int virq)
 {
 	unsigned int irq = (unsigned int)irq_map[virq].hwirq;
 
 	iosync();
-	direct_xirr_info_set((0xff << 24) | irq);
+	direct_xirr_info_set((pop_cppr() << 24) | irq);
 }
 
 static void xics_eoi_lpar(unsigned int virq)
@@ -339,7 +379,7 @@ static void xics_eoi_lpar(unsigned int virq)
 	unsigned int irq = (unsigned int)irq_map[virq].hwirq;
 
 	iosync();
-	lpar_xirr_info_set((0xff << 24) | irq);
+	lpar_xirr_info_set((pop_cppr() << 24) | irq);
 }
 
 static int xics_set_affinity(unsigned int virq, const struct cpumask *cpumask)
@@ -746,6 +786,12 @@ void __init xics_init_IRQ(void)
 
 static void xics_set_cpu_priority(unsigned char cppr)
 {
+	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
+
+	BUG_ON(os_cppr->index != 0);
+
+	os_cppr->stack[os_cppr->index] = cppr;
+
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		lpar_cppr_info(cppr);
 	else
@@ -772,7 +818,7 @@ static void xics_set_cpu_giq(unsigned int gserver, unsigned int join)
 
 void xics_setup_cpu(void)
 {
-	xics_set_cpu_priority(0xff);
+	xics_set_cpu_priority(LOWEST_PRIORITY);
 
 	xics_set_cpu_giq(default_distrib_server, 1);
 }

From 11c34c7deaeeebcee342cbc35e1bb2a6711b2431 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 4 Dec 2009 07:16:59 +0000
Subject: [PATCH 150/151] MAINTAINERS: Add PowerPC patterns

On Fri, 2009-12-04 at 20:59 +1100, Benjamin Herrenschmidt wrote:
> On Fri, 2009-12-04 at 10:34 +0100, Jean Delvare wrote:
> > I've sent it to linuxppc-dev@ozlabs.org on October 14th. This is the
> > address which is listed 22 times in MAINTAINERS. If it isn't correct,
> > then please update MAINTAINERS.
> No it's fine both shoul work. Your patches are there, just waiting for
> me to pick them up, I was just firing a reminder to the rest of the CC
> list :-) (and I do remember fwd'ing a couple of your patches to the
> list, for some reason they didn't make it to patchwork back then, that
> was a few month ago).
> Anyways, I've been stretched thin with all sort of stuff lately, so bear
> with me if I'm a bit slow at taking or testing stuff, I'm doing my best.

Adding patterns to the PowerPC sections of MAINTAINERS is useful.

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
Acked-by: Grant Likely <grant.likely@secretlab.ca>
Acked-by: Olof Johansson <olof@lixom.net>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 MAINTAINERS | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index c824b4d62754..5dd672213903 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3168,6 +3168,7 @@ LINUX FOR IBM pSERIES (RS/6000)
 M:	Paul Mackerras <paulus@au.ibm.com>
 W:	http://www.ibm.com/linux/ltc/projects/ppc
 S:	Supported
+F:	arch/powerpc/boot/rs6000.h
 
 LINUX FOR POWERPC (32-BIT AND 64-BIT)
 M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
@@ -3176,18 +3177,24 @@ W:	http://www.penguinppc.org/
 L:	linuxppc-dev@ozlabs.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.git
 S:	Supported
+F:	Documentation/powerpc/
+F:	arch/powerpc/
 
 LINUX FOR POWER MACINTOSH
 M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
 W:	http://www.penguinppc.org/
 L:	linuxppc-dev@ozlabs.org
 S:	Maintained
+F:	arch/powerpc/platforms/powermac/
+F:	drivers/macintosh/
 
 LINUX FOR POWERPC EMBEDDED MPC5XXX
 M:	Grant Likely <grant.likely@secretlab.ca>
 L:	linuxppc-dev@ozlabs.org
 T:	git git://git.secretlab.ca/git/linux-2.6.git
 S:	Maintained
+F:	arch/powerpc/platforms/512x/
+F:	arch/powerpc/platforms/52xx/
 
 LINUX FOR POWERPC EMBEDDED PPC4XX
 M:	Josh Boyer <jwboyer@linux.vnet.ibm.com>
@@ -3196,6 +3203,8 @@ W:	http://www.penguinppc.org/
 L:	linuxppc-dev@ozlabs.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jwboyer/powerpc-4xx.git
 S:	Maintained
+F:	arch/powerpc/platforms/40x/
+F:	arch/powerpc/platforms/44x/
 
 LINUX FOR POWERPC EMBEDDED XILINX VIRTEX
 M:	Grant Likely <grant.likely@secretlab.ca>
@@ -3203,6 +3212,8 @@ W:	http://wiki.secretlab.ca/index.php/Linux_on_Xilinx_Virtex
 L:	linuxppc-dev@ozlabs.org
 T:	git git://git.secretlab.ca/git/linux-2.6.git
 S:	Maintained
+F:	arch/powerpc/*/*virtex*
+F:	arch/powerpc/*/*/*virtex*
 
 LINUX FOR POWERPC EMBEDDED PPC8XX
 M:	Vitaly Bordug <vitb@kernel.crashing.org>
@@ -3216,12 +3227,16 @@ M:	Kumar Gala <galak@kernel.crashing.org>
 W:	http://www.penguinppc.org/
 L:	linuxppc-dev@ozlabs.org
 S:	Maintained
+F:	arch/powerpc/platforms/83xx/
 
 LINUX FOR POWERPC PA SEMI PWRFICIENT
 M:	Olof Johansson <olof@lixom.net>
 W:	http://www.pasemi.com/
 L:	linuxppc-dev@ozlabs.org
 S:	Supported
+F:	arch/powerpc/platforms/pasemi/
+F:	drivers/*/*pasemi*
+F:	drivers/*/*/*pasemi*
 
 LINUX SECURITY MODULE (LSM) FRAMEWORK
 M:	Chris Wright <chrisw@sous-sol.org>

From e090aa80321b64c3b793f3b047e31ecf1af9538d Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 8 Dec 2009 18:45:45 +0000
Subject: [PATCH 151/151] powerpc: Fix usage of 64-bit instruction in 32-bit
 altivec code

e821ea70f3b4873b50056a1e0f74befed1014c09 introduced a bug by copying
some 64-bit originated code as-is to be used by both 32 and 64-bit
but this code contains a 64-bit ony "cmpdi" instruction.

This changes it to cmpwi, which is fine since VRSAVE can only contains
a 32-bit value anyway.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@kernel.org>
---
 arch/powerpc/kernel/vector.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 67b6916f0e94..fe460482fa68 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -58,7 +58,7 @@ _GLOBAL(load_up_altivec)
 	 * all 1's
 	 */
 	mfspr	r4,SPRN_VRSAVE
-	cmpdi	0,r4,0
+	cmpwi	0,r4,0
 	bne+	1f
 	li	r4,-1
 	mtspr	SPRN_VRSAVE,r4