Merge git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc-merge

Documentation/powerpc/00-INDEX

@@ -8,12 +8,18 @@ please mail me.
 cpu_features.txt
 	- info on how we support a variety of CPUs with minimal compile-time
 	options.
+eeh-pci-error-recovery.txt
+	- info on PCI Bus EEH Error Recovery
+hvcs.txt
+	- IBM "Hypervisor Virtual Console Server" Installation Guide
+mpc52xx.txt
+	- Linux 2.6.x on MPC52xx family
 ppc_htab.txt
 	- info about the Linux/PPC /proc/ppc_htab entry
-smp.txt
-	- use and state info about Linux/PPC on MP machines
 SBC8260_memory_mapping.txt
 	- EST SBC8260 board info
+smp.txt
+	- use and state info about Linux/PPC on MP machines
 sound.txt
 	- info on sound support under Linux/PPC
 zImage_layout.txt

arch/powerpc/Kconfig

@@ -47,7 +47,7 @@ config PPC
 
 config EARLY_PRINTK
 	bool
-	default y if PPC64
+	default y
 
 config COMPAT
 	bool
@@ -297,6 +297,7 @@ config PPC_PMAC64
 	bool
 	depends on PPC_PMAC && POWER4
 	select U3_DART
+	select MPIC_BROKEN_U3
 	select GENERIC_TBSYNC
 	default y
 
@@ -325,9 +326,7 @@ config PPC_CELL
 	select MMIO_NVRAM
 
 config PPC_OF
-	bool
-	depends on PPC_MULTIPLATFORM	# for now
-	default y
+	def_bool y
 
 config XICS
 	depends on PPC_PSERIES
@@ -376,11 +375,28 @@ config CELL_IIC
 	bool
 	default y
 
+config CRASH_DUMP
+	bool "kernel crash dumps (EXPERIMENTAL)"
+	depends on PPC_MULTIPLATFORM
+	depends on EXPERIMENTAL
+	help
+	  Build a kernel suitable for use as a kdump capture kernel.
+	  The kernel will be linked at a different address than normal, and
+	  so can only be used for Kdump.
+
+	  Don't change this unless you know what you are doing.
+
 config IBMVIO
 	depends on PPC_PSERIES || PPC_ISERIES
 	bool
 	default y
 
+config IBMEBUS
+	depends on PPC_PSERIES
+	bool "Support for GX bus based adapters"
+	help
+	  Bus device driver for GX bus based adapters.
+
 config PPC_MPC106
 	bool
 	default n
@@ -472,6 +488,7 @@ source arch/powerpc/platforms/embedded6xx/Kconfig
 source arch/powerpc/platforms/4xx/Kconfig
 source arch/powerpc/platforms/85xx/Kconfig
 source arch/powerpc/platforms/8xx/Kconfig
+source arch/powerpc/platforms/cell/Kconfig
 
 menu "Kernel options"
 
@@ -575,11 +592,12 @@ config ARCH_SELECT_MEMORY_MODEL
 	depends on PPC64
 
 config ARCH_FLATMEM_ENABLE
-       def_bool y
-       depends on PPC64 && !NUMA
+	def_bool y
+	depends on (PPC64 && !NUMA) || PPC32
 
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
+	depends on PPC64
 
 config ARCH_SPARSEMEM_DEFAULT
 	def_bool y

arch/powerpc/Makefile

@@ -151,7 +151,7 @@ CPPFLAGS_vmlinux.lds	:= -Upowerpc
 # All the instructions talk about "make bzImage".
 bzImage: zImage
 
-BOOT_TARGETS = zImage zImage.initrd znetboot znetboot.initrd vmlinux.sm
+BOOT_TARGETS = zImage zImage.initrd znetboot znetboot.initrd vmlinux.sm uImage
 
 .PHONY: $(BOOT_TARGETS)
 

arch/powerpc/boot/Makefile

@@ -143,6 +143,36 @@ $(obj)/zImage.initrd: $(obj)/zImage.initrd.vmode $(obj)/addnote
 	@cp -f $< $@
 	$(call if_changed,addnote)
 
+#-----------------------------------------------------------
+# build u-boot images
+#-----------------------------------------------------------
+quiet_cmd_mygzip = GZIP $@
+cmd_mygzip = gzip -f -9 < $< > $@.$$$$ && mv $@.$$$$ $@
+
+quiet_cmd_objbin = OBJCOPY $@
+      cmd_objbin = $(OBJCOPY) -O binary $< $@
+
+quiet_cmd_uimage = UIMAGE $@
+      cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A ppc -O linux -T kernel \
+               -C gzip -a 00000000 -e 00000000 -n 'Linux-$(KERNELRELEASE)' \
+               -d $< $@
+
+MKIMAGE		:= $(srctree)/scripts/mkuboot.sh
+targets		+= uImage
+extra-y		+= vmlinux.bin vmlinux.gz
+
+$(obj)/vmlinux.bin: vmlinux FORCE
+	$(call if_changed,objbin)
+
+$(obj)/vmlinux.gz: $(obj)/vmlinux.bin FORCE
+	$(call if_changed,mygzip)
+
+$(obj)/uImage: $(obj)/vmlinux.gz
+	$(Q)rm -f $@
+	$(call cmd,uimage)
+	@echo -n '  Image: $@ '
+	@if [ -f $@ ]; then echo 'is ready' ; else echo 'not made'; fi
+
 install: $(CONFIGURE) $(BOOTIMAGE)
 	sh -x $(srctree)/$(src)/install.sh "$(KERNELRELEASE)" vmlinux System.map "$(INSTALL_PATH)" "$(BOOTIMAGE)"
 

arch/powerpc/kernel/Makefile

@@ -17,11 +17,11 @@ obj-y				+= vdso32/
 obj-$(CONFIG_PPC64)		+= setup_64.o binfmt_elf32.o sys_ppc32.o \
 				   signal_64.o ptrace32.o systbl.o \
 				   paca.o ioctl32.o cpu_setup_power4.o \
-				   firmware.o sysfs.o udbg.o idle_64.o
+				   firmware.o sysfs.o idle_64.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
 obj-$(CONFIG_POWER4)		+= idle_power4.o
-obj-$(CONFIG_PPC_OF)		+= of_device.o
+obj-$(CONFIG_PPC_OF)		+= of_device.o prom_parse.o
 procfs-$(CONFIG_PPC64)		:= proc_ppc64.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
 rtaspci-$(CONFIG_PPC64)		:= rtas_pci.o
@@ -30,12 +30,10 @@ obj-$(CONFIG_RTAS_FLASH)	+= rtas_flash.o
 obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
 obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
+obj-$(CONFIG_IBMEBUS)           += ibmebus.o
 obj-$(CONFIG_GENERIC_TBSYNC)	+= smp-tbsync.o
-obj-$(CONFIG_PPC_PSERIES)	+= udbg_16550.o
-obj-$(CONFIG_PPC_MAPLE)		+= udbg_16550.o
-udbgscc-$(CONFIG_PPC64)		:= udbg_scc.o
-obj-$(CONFIG_PPC_PMAC)		+= $(udbgscc-y)
 obj64-$(CONFIG_PPC_MULTIPLATFORM) += nvram_64.o
+obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 
 ifeq ($(CONFIG_PPC_MERGE),y)
 
@@ -48,25 +46,25 @@ extra-$(CONFIG_8xx)		:= head_8xx.o
 extra-y				+= vmlinux.lds
 
 obj-y				+= process.o init_task.o time.o \
-				   prom.o traps.o setup-common.o
+				   prom.o traps.o setup-common.o udbg.o
 obj-$(CONFIG_PPC32)		+= entry_32.o setup_32.o misc_32.o systbl.o
 obj-$(CONFIG_PPC64)		+= misc_64.o dma_64.o iommu.o
-obj-$(CONFIG_PPC_OF)		+= prom_init.o
+obj-$(CONFIG_PPC_MULTIPLATFORM)	+= prom_init.o
 obj-$(CONFIG_MODULES)		+= ppc_ksyms.o
 obj-$(CONFIG_BOOTX_TEXT)	+= btext.o
 obj-$(CONFIG_6xx)		+= idle_6xx.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
-
+obj-$(CONFIG_SERIAL_8250)	+= legacy_serial.o udbg_16550.o
 module-$(CONFIG_PPC64)		+= module_64.o
 obj-$(CONFIG_MODULES)		+= $(module-y)
 
 pci64-$(CONFIG_PPC64)		+= pci_64.o pci_dn.o pci_iommu.o \
 				   pci_direct_iommu.o iomap.o
 obj-$(CONFIG_PCI)		+= $(pci64-y)
-
-kexec64-$(CONFIG_PPC64)		+= machine_kexec_64.o
-obj-$(CONFIG_KEXEC)		+= $(kexec64-y)
+kexec-$(CONFIG_PPC64)		:= machine_kexec_64.o
+kexec-$(CONFIG_PPC32)		:= machine_kexec_32.o
+obj-$(CONFIG_KEXEC)		+= machine_kexec.o crash.o $(kexec-y)
 
 ifeq ($(CONFIG_PPC_ISERIES),y)
 $(obj)/head_64.o: $(obj)/lparmap.s

arch/powerpc/kernel/asm-offsets.c

@@ -92,9 +92,9 @@ int main(void)
 
 	DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
 	DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
-	DEFINE(TI_SC_NOERR, offsetof(struct thread_info, syscall_noerror));
-#ifdef CONFIG_PPC32
+	DEFINE(TI_SIGFRAME, offsetof(struct thread_info, nvgprs_frame));
 	DEFINE(TI_TASK, offsetof(struct thread_info, task));
+#ifdef CONFIG_PPC32
 	DEFINE(TI_EXECDOMAIN, offsetof(struct thread_info, exec_domain));
 	DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
 #endif /* CONFIG_PPC32 */
@@ -131,11 +131,9 @@ int main(void)
 	DEFINE(PACALOWHTLBAREAS, offsetof(struct paca_struct, context.low_htlb_areas));
 	DEFINE(PACAHIGHHTLBAREAS, offsetof(struct paca_struct, context.high_htlb_areas));
 #endif /* CONFIG_HUGETLB_PAGE */
-	DEFINE(PACADEFAULTDECR, offsetof(struct paca_struct, default_decr));
 	DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
 	DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));
 	DEFINE(PACA_EXSLB, offsetof(struct paca_struct, exslb));
-	DEFINE(PACA_EXDSI, offsetof(struct paca_struct, exdsi));
 	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
 	DEFINE(PACALPPACA, offsetof(struct paca_struct, lppaca));
 	DEFINE(PACAHWCPUID, offsetof(struct paca_struct, hw_cpu_id));

arch/powerpc/kernel/btext.c

@@ -31,15 +31,18 @@ static void draw_byte_32(unsigned char *bits, unsigned int *base, int rb);
 static void draw_byte_16(unsigned char *bits, unsigned int *base, int rb);
 static void draw_byte_8(unsigned char *bits, unsigned int *base, int rb);
 
-static int g_loc_X;
-static int g_loc_Y;
-static int g_max_loc_X;
-static int g_max_loc_Y;
+#define __force_data __attribute__((__section__(".data")))
 
-static int dispDeviceRowBytes;
-static int dispDeviceDepth;
-static int dispDeviceRect[4];
-static unsigned char *dispDeviceBase, *logicalDisplayBase;
+static int g_loc_X __force_data;
+static int g_loc_Y __force_data;
+static int g_max_loc_X __force_data;
+static int g_max_loc_Y __force_data;
+
+static int dispDeviceRowBytes __force_data;
+static int dispDeviceDepth  __force_data;
+static int dispDeviceRect[4] __force_data;
+static unsigned char *dispDeviceBase __force_data;
+static unsigned char *logicalDisplayBase __force_data;
 
 unsigned long disp_BAT[2] __initdata = {0, 0};
 
@@ -47,7 +50,7 @@ unsigned long disp_BAT[2] __initdata = {0, 0};
 
 static unsigned char vga_font[cmapsz];
 
-int boot_text_mapped;
+int boot_text_mapped __force_data = 0;
 int force_printk_to_btext = 0;
 
 #ifdef CONFIG_PPC32
@@ -57,7 +60,7 @@ int force_printk_to_btext = 0;
  *
  * The display is mapped to virtual address 0xD0000000, rather
  * than 1:1, because some some CHRP machines put the frame buffer
- * in the region starting at 0xC0000000 (KERNELBASE).
+ * in the region starting at 0xC0000000 (PAGE_OFFSET).
  * This mapping is temporary and will disappear as soon as the
  * setup done by MMU_Init() is applied.
  *
@@ -66,10 +69,9 @@ int force_printk_to_btext = 0;
  * is really badly aligned, but I didn't encounter this case
  * yet.
  */
-void __init
-btext_prepare_BAT(void)
+void __init btext_prepare_BAT(void)
 {
-	unsigned long vaddr = KERNELBASE + 0x10000000;
+	unsigned long vaddr = PAGE_OFFSET + 0x10000000;
 	unsigned long addr;
 	unsigned long lowbits;
 
@@ -95,12 +97,13 @@ btext_prepare_BAT(void)
 }
 #endif
 
-/* This function will enable the early boot text when doing OF booting. This
- * way, xmon output should work too
+
+/* This function can be used to enable the early boot text when doing
+ * OF booting or within bootx init. It must be followed by a btext_unmap()
+ * call before the logical address becomes unuseable
  */
-void __init
-btext_setup_display(int width, int height, int depth, int pitch,
-		    unsigned long address)
+void __init btext_setup_display(int width, int height, int depth, int pitch,
+				unsigned long address)
 {
 	g_loc_X = 0;
 	g_loc_Y = 0;
@@ -116,6 +119,11 @@ btext_setup_display(int width, int height, int depth, int pitch,
 	boot_text_mapped = 1;
 }
 
+void __init btext_unmap(void)
+{
+	boot_text_mapped = 0;
+}
+
 /* Here's a small text engine to use during early boot
  * or for debugging purposes
  *
@@ -127,7 +135,7 @@ btext_setup_display(int width, int height, int depth, int pitch,
  *    changes.
  */
 
-void map_boot_text(void)
+static void map_boot_text(void)
 {
 	unsigned long base, offset, size;
 	unsigned char *vbase;
@@ -175,8 +183,9 @@ int btext_initialize(struct device_node *np)
 	if (prop)
 		address = *prop;
 
-	/* FIXME: Add support for PCI reg properties */
-
+	/* FIXME: Add support for PCI reg properties. Right now, only
+	 * reliable on macs
+	 */
 	if (address == 0)
 		return -EINVAL;
 
@@ -184,7 +193,6 @@ int btext_initialize(struct device_node *np)
 	g_loc_Y = 0;
 	g_max_loc_X = width / 8;
 	g_max_loc_Y = height / 16;
-	logicalDisplayBase = (unsigned char *)address;
 	dispDeviceBase = (unsigned char *)address;
 	dispDeviceRowBytes = pitch;
 	dispDeviceDepth = depth;
@@ -197,14 +205,12 @@ int btext_initialize(struct device_node *np)
 	return 0;
 }
 
-void __init init_boot_display(void)
+int __init btext_find_display(int allow_nonstdout)
 {
 	char *name;
 	struct device_node *np = NULL; 
 	int rc = -ENODEV;
 
-	printk("trying to initialize btext ...\n");
-
 	name = (char *)get_property(of_chosen, "linux,stdout-path", NULL);
 	if (name != NULL) {
 		np = of_find_node_by_path(name);
@@ -218,8 +224,8 @@ void __init init_boot_display(void)
 	}
 	if (np)
 		rc = btext_initialize(np);
-	if (rc == 0)
-		return;
+	if (rc == 0 || !allow_nonstdout)
+		return rc;
 
 	for (np = NULL; (np = of_find_node_by_type(np, "display"));) {
 		if (get_property(np, "linux,opened", NULL)) {
@@ -228,8 +234,9 @@ void __init init_boot_display(void)
 			printk("result: %d\n", rc);
 		}
 		if (rc == 0)
-			return;
+			break;
 	}
+	return rc;
 }
 
 /* Calc the base address of a given point (x,y) */
@@ -277,44 +284,83 @@ EXPORT_SYMBOL(btext_update_display);
 
 void btext_clearscreen(void)
 {
-	unsigned long *base	= (unsigned long *)calc_base(0, 0);
+	unsigned int *base	= (unsigned int *)calc_base(0, 0);
 	unsigned long width 	= ((dispDeviceRect[2] - dispDeviceRect[0]) *
-					(dispDeviceDepth >> 3)) >> 3;
+					(dispDeviceDepth >> 3)) >> 2;
 	int i,j;
 
 	for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1]); i++)
 	{
-		unsigned long *ptr = base;
+		unsigned int *ptr = base;
 		for(j=width; j; --j)
 			*(ptr++) = 0;
-		base += (dispDeviceRowBytes >> 3);
+		base += (dispDeviceRowBytes >> 2);
 	}
 }
 
+void btext_flushscreen(void)
+{
+	unsigned int *base	= (unsigned int *)calc_base(0, 0);
+	unsigned long width 	= ((dispDeviceRect[2] - dispDeviceRect[0]) *
+					(dispDeviceDepth >> 3)) >> 2;
+	int i,j;
+
+	for (i=0; i < (dispDeviceRect[3] - dispDeviceRect[1]); i++)
+	{
+		unsigned int *ptr = base;
+		for(j = width; j > 0; j -= 8) {
+			__asm__ __volatile__ ("dcbst 0,%0" :: "r" (ptr));
+			ptr += 8;
+		}
+		base += (dispDeviceRowBytes >> 2);
+	}
+	__asm__ __volatile__ ("sync" ::: "memory");
+}
+
+void btext_flushline(void)
+{
+	unsigned int *base	= (unsigned int *)calc_base(0, g_loc_Y << 4);
+	unsigned long width 	= ((dispDeviceRect[2] - dispDeviceRect[0]) *
+					(dispDeviceDepth >> 3)) >> 2;
+	int i,j;
+
+	for (i=0; i < 16; i++)
+	{
+		unsigned int *ptr = base;
+		for(j = width; j > 0; j -= 8) {
+			__asm__ __volatile__ ("dcbst 0,%0" :: "r" (ptr));
+			ptr += 8;
+		}
+		base += (dispDeviceRowBytes >> 2);
+	}
+	__asm__ __volatile__ ("sync" ::: "memory");
+}
+
+
 #ifndef NO_SCROLL
 static void scrollscreen(void)
 {
-	unsigned long *src     	= (unsigned long *)calc_base(0,16);
-	unsigned long *dst     	= (unsigned long *)calc_base(0,0);
+	unsigned int *src     	= (unsigned int *)calc_base(0,16);
+	unsigned int *dst     	= (unsigned int *)calc_base(0,0);
 	unsigned long width    	= ((dispDeviceRect[2] - dispDeviceRect[0]) *
-				   (dispDeviceDepth >> 3)) >> 3;
+				   (dispDeviceDepth >> 3)) >> 2;
 	int i,j;
 
 	for (i=0; i<(dispDeviceRect[3] - dispDeviceRect[1] - 16); i++)
 	{
-		unsigned long *src_ptr = src;
-		unsigned long *dst_ptr = dst;
+		unsigned int *src_ptr = src;
+		unsigned int *dst_ptr = dst;
 		for(j=width; j; --j)
 			*(dst_ptr++) = *(src_ptr++);
-		src += (dispDeviceRowBytes >> 3);
-		dst += (dispDeviceRowBytes >> 3);
+		src += (dispDeviceRowBytes >> 2);
+		dst += (dispDeviceRowBytes >> 2);
 	}
 	for (i=0; i<16; i++)
 	{
-		unsigned long *dst_ptr = dst;
+		unsigned int *dst_ptr = dst;
 		for(j=width; j; --j)
 			*(dst_ptr++) = 0;
-		dst += (dispDeviceRowBytes >> 3);
+		dst += (dispDeviceRowBytes >> 2);
 	}
 }
 #endif /* ndef NO_SCROLL */
@@ -377,6 +423,14 @@ void btext_drawstring(const char *c)
 		btext_drawchar(*c++);
 }
 
+void btext_drawtext(const char *c, unsigned int len)
+{
+	if (!boot_text_mapped)
+		return;
+	while (len--)
+		btext_drawchar(*c++);
+}
+
 void btext_drawhex(unsigned long v)
 {
 	char *hex_table = "0123456789abcdef";

arch/powerpc/kernel/cputable.c

@@ -78,10 +78,8 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
 		.cpu_setup		= __setup_cpu_power3,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/power3",
-		.oprofile_model		= &op_model_rs64,
-#endif
+		.oprofile_type		= RS64,
 	},
 	{	/* Power3+ */
 		.pvr_mask		= 0xffff0000,
@@ -93,10 +91,8 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
 		.cpu_setup		= __setup_cpu_power3,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/power3",
-		.oprofile_model		= &op_model_rs64,
-#endif
+		.oprofile_type		= RS64,
 	},
 	{	/* Northstar */
 		.pvr_mask		= 0xffff0000,
@@ -108,10 +104,8 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
 		.cpu_setup		= __setup_cpu_power3,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/rs64",
-		.oprofile_model		= &op_model_rs64,
-#endif
+		.oprofile_type		= RS64,
 	},
 	{	/* Pulsar */
 		.pvr_mask		= 0xffff0000,
@@ -123,10 +117,8 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
 		.cpu_setup		= __setup_cpu_power3,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/rs64",
-		.oprofile_model		= &op_model_rs64,
-#endif
+		.oprofile_type		= RS64,
 	},
 	{	/* I-star */
 		.pvr_mask		= 0xffff0000,
@@ -138,10 +130,8 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
 		.cpu_setup		= __setup_cpu_power3,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/rs64",
-		.oprofile_model		= &op_model_rs64,
-#endif
+		.oprofile_type		= RS64,
 	},
 	{	/* S-star */
 		.pvr_mask		= 0xffff0000,
@@ -153,10 +143,8 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
 		.cpu_setup		= __setup_cpu_power3,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/rs64",
-		.oprofile_model		= &op_model_rs64,
-#endif
+		.oprofile_type		= RS64,
 	},
 	{	/* Power4 */
 		.pvr_mask		= 0xffff0000,
@@ -168,10 +156,8 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
 		.cpu_setup		= __setup_cpu_power4,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/power4",
-		.oprofile_model		= &op_model_rs64,
-#endif
+		.oprofile_type		= POWER4,
 	},
 	{	/* Power4+ */
 		.pvr_mask		= 0xffff0000,
@@ -183,10 +169,8 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
 		.cpu_setup		= __setup_cpu_power4,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/power4",
-		.oprofile_model		= &op_model_power4,
-#endif
+		.oprofile_type		= POWER4,
 	},
 	{	/* PPC970 */
 		.pvr_mask		= 0xffff0000,
@@ -199,10 +183,8 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
 		.cpu_setup		= __setup_cpu_ppc970,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/970",
-		.oprofile_model		= &op_model_power4,
-#endif
+		.oprofile_type		= POWER4,
 	},
 #endif /* CONFIG_PPC64 */
 #if defined(CONFIG_PPC64) || defined(CONFIG_POWER4)
@@ -221,10 +203,8 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
 		.cpu_setup		= __setup_cpu_ppc970,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/970",
-		.oprofile_model		= &op_model_power4,
-#endif
+		.oprofile_type		= POWER4,
 	},
 #endif /* defined(CONFIG_PPC64) || defined(CONFIG_POWER4) */
 #ifdef CONFIG_PPC64
@@ -238,10 +218,8 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.cpu_setup		= __setup_cpu_ppc970,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/970",
-		.oprofile_model		= &op_model_power4,
-#endif
+		.oprofile_type		= POWER4,
 	},
 	{	/* Power5 GR */
 		.pvr_mask		= 0xffff0000,
@@ -253,27 +231,23 @@ struct cpu_spec	cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
 		.cpu_setup		= __setup_cpu_power4,
-#ifdef CONFIG_OPROFILE
 		.oprofile_cpu_type	= "ppc64/power5",
-		.oprofile_model		= &op_model_power4,
-#endif
+		.oprofile_type		= POWER4,
 	},
 	{	/* Power5 GS */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x003b0000,
-		.cpu_name		= "POWER5 (gs)",
+		.cpu_name		= "POWER5+ (gs)",
 		.cpu_features		= CPU_FTRS_POWER5,
 		.cpu_user_features	= COMMON_USER_POWER5_PLUS,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
 		.cpu_setup		= __setup_cpu_power4,
-#ifdef CONFIG_OPROFILE
-		.oprofile_cpu_type	= "ppc64/power5",
-		.oprofile_model		= &op_model_power4,
-#endif
+		.oprofile_cpu_type	= "ppc64/power5+",
+		.oprofile_type		= POWER4,
 	},
-	{	/* BE DD1.x */
+	{	/* Cell Broadband Engine */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x00700000,
 		.cpu_name		= "Cell Broadband Engine",
@@ -545,7 +519,9 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
-		.cpu_setup		= __setup_cpu_745x
+		.cpu_setup		= __setup_cpu_745x,
+		.oprofile_cpu_type      = "ppc/7450",
+		.oprofile_type		= G4,
 	},
 	{	/* 7450 2.1 */
 		.pvr_mask		= 0xffffffff,
@@ -556,7 +532,9 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
-		.cpu_setup		= __setup_cpu_745x
+		.cpu_setup		= __setup_cpu_745x,
+		.oprofile_cpu_type      = "ppc/7450",
+		.oprofile_type		= G4,
 	},
 	{	/* 7450 2.3 and newer */
 		.pvr_mask		= 0xffff0000,
@@ -567,7 +545,9 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
-		.cpu_setup		= __setup_cpu_745x
+		.cpu_setup		= __setup_cpu_745x,
+		.oprofile_cpu_type      = "ppc/7450",
+		.oprofile_type		= G4,
 	},
 	{	/* 7455 rev 1.x */
 		.pvr_mask		= 0xffffff00,
@@ -578,7 +558,9 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
-		.cpu_setup		= __setup_cpu_745x
+		.cpu_setup		= __setup_cpu_745x,
+		.oprofile_cpu_type      = "ppc/7450",
+		.oprofile_type		= G4,
 	},
 	{	/* 7455 rev 2.0 */
 		.pvr_mask		= 0xffffffff,
@@ -589,7 +571,9 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
-		.cpu_setup		= __setup_cpu_745x
+		.cpu_setup		= __setup_cpu_745x,
+		.oprofile_cpu_type      = "ppc/7450",
+		.oprofile_type		= G4,
 	},
 	{	/* 7455 others */
 		.pvr_mask		= 0xffff0000,
@@ -600,7 +584,9 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
-		.cpu_setup		= __setup_cpu_745x
+		.cpu_setup		= __setup_cpu_745x,
+		.oprofile_cpu_type      = "ppc/7450",
+		.oprofile_type		= G4,
 	},
 	{	/* 7447/7457 Rev 1.0 */
 		.pvr_mask		= 0xffffffff,
@@ -611,7 +597,9 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
-		.cpu_setup		= __setup_cpu_745x
+		.cpu_setup		= __setup_cpu_745x,
+		.oprofile_cpu_type      = "ppc/7450",
+		.oprofile_type		= G4,
 	},
 	{	/* 7447/7457 Rev 1.1 */
 		.pvr_mask		= 0xffffffff,
@@ -622,7 +610,9 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
-		.cpu_setup		= __setup_cpu_745x
+		.cpu_setup		= __setup_cpu_745x,
+		.oprofile_cpu_type      = "ppc/7450",
+		.oprofile_type		= G4,
 	},
 	{	/* 7447/7457 Rev 1.2 and later */
 		.pvr_mask		= 0xffff0000,
@@ -633,7 +623,9 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
-		.cpu_setup		= __setup_cpu_745x
+		.cpu_setup		= __setup_cpu_745x,
+		.oprofile_cpu_type      = "ppc/7450",
+		.oprofile_type		= G4,
 	},
 	{	/* 7447A */
 		.pvr_mask		= 0xffff0000,
@@ -644,7 +636,9 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
-		.cpu_setup		= __setup_cpu_745x
+		.cpu_setup		= __setup_cpu_745x,
+		.oprofile_cpu_type      = "ppc/7450",
+		.oprofile_type		= G4,
 	},
 	{	/* 7448 */
 		.pvr_mask		= 0xffff0000,
@@ -655,7 +649,9 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 6,
-		.cpu_setup		= __setup_cpu_745x
+		.cpu_setup		= __setup_cpu_745x,
+		.oprofile_cpu_type      = "ppc/7450",
+		.oprofile_type		= G4,
 	},
 	{	/* 82xx (8240, 8245, 8260 are all 603e cores) */
 		.pvr_mask		= 0x7fff0000,
@@ -979,6 +975,8 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.oprofile_cpu_type	= "ppc/e500",
+		.oprofile_type		= BOOKE,
 	},
 	{	/* e500v2 */
 		.pvr_mask		= 0xffff0000,
@@ -992,6 +990,8 @@ struct cpu_spec	cpu_specs[] = {
 		.icache_bsize		= 32,
 		.dcache_bsize		= 32,
 		.num_pmcs		= 4,
+		.oprofile_cpu_type	= "ppc/e500",
+		.oprofile_type		= BOOKE,
 	},
 #endif
 #if !CLASSIC_PPC

arch/powerpc/kernel/crash.c

+/*
+ * Architecture specific (PPC64) functions for kexec based crash dumps.
+ *
+ * Copyright (C) 2005, IBM Corp.
+ *
+ * Created by: Haren Myneni
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ *
+ */
+
+#undef DEBUG
+
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/reboot.h>
+#include <linux/kexec.h>
+#include <linux/bootmem.h>
+#include <linux/crash_dump.h>
+#include <linux/irq.h>
+#include <linux/delay.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/init.h>
+#include <linux/types.h>
+
+#include <asm/processor.h>
+#include <asm/machdep.h>
+#include <asm/kdump.h>
+#include <asm/lmb.h>
+#include <asm/firmware.h>
+
+#ifdef DEBUG
+#include <asm/udbg.h>
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+/* This keeps a track of which one is crashing cpu. */
+int crashing_cpu = -1;
+
+static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
+							       size_t data_len)
+{
+	struct elf_note note;
+
+	note.n_namesz = strlen(name) + 1;
+	note.n_descsz = data_len;
+	note.n_type   = type;
+	memcpy(buf, &note, sizeof(note));
+	buf += (sizeof(note) +3)/4;
+	memcpy(buf, name, note.n_namesz);
+	buf += (note.n_namesz + 3)/4;
+	memcpy(buf, data, note.n_descsz);
+	buf += (note.n_descsz + 3)/4;
+
+	return buf;
+}
+
+static void final_note(u32 *buf)
+{
+	struct elf_note note;
+
+	note.n_namesz = 0;
+	note.n_descsz = 0;
+	note.n_type   = 0;
+	memcpy(buf, &note, sizeof(note));
+}
+
+static void crash_save_this_cpu(struct pt_regs *regs, int cpu)
+{
+	struct elf_prstatus prstatus;
+	u32 *buf;
+
+	if ((cpu < 0) || (cpu >= NR_CPUS))
+		return;
+
+	/* Using ELF notes here is opportunistic.
+	 * I need a well defined structure format
+	 * for the data I pass, and I need tags
+	 * on the data to indicate what information I have
+	 * squirrelled away.  ELF notes happen to provide
+	 * all of that that no need to invent something new.
+	 */
+	buf = &crash_notes[cpu][0];
+	memset(&prstatus, 0, sizeof(prstatus));
+	prstatus.pr_pid = current->pid;
+	elf_core_copy_regs(&prstatus.pr_reg, regs);
+	buf = append_elf_note(buf, "CORE", NT_PRSTATUS, &prstatus,
+			sizeof(prstatus));
+	final_note(buf);
+}
+
+/* FIXME Merge this with xmon_save_regs ?? */
+static inline void crash_get_current_regs(struct pt_regs *regs)
+{
+	unsigned long tmp1, tmp2;
+
+	__asm__ __volatile__ (
+		"std    0,0(%2)\n"
+		"std    1,8(%2)\n"
+		"std    2,16(%2)\n"
+		"std    3,24(%2)\n"
+		"std    4,32(%2)\n"
+		"std    5,40(%2)\n"
+		"std    6,48(%2)\n"
+		"std    7,56(%2)\n"
+		"std    8,64(%2)\n"
+		"std    9,72(%2)\n"
+		"std    10,80(%2)\n"
+		"std    11,88(%2)\n"
+		"std    12,96(%2)\n"
+		"std    13,104(%2)\n"
+		"std    14,112(%2)\n"
+		"std    15,120(%2)\n"
+		"std    16,128(%2)\n"
+		"std    17,136(%2)\n"
+		"std    18,144(%2)\n"
+		"std    19,152(%2)\n"
+		"std    20,160(%2)\n"
+		"std    21,168(%2)\n"
+		"std    22,176(%2)\n"
+		"std    23,184(%2)\n"
+		"std    24,192(%2)\n"
+		"std    25,200(%2)\n"
+		"std    26,208(%2)\n"
+		"std    27,216(%2)\n"
+		"std    28,224(%2)\n"
+		"std    29,232(%2)\n"
+		"std    30,240(%2)\n"
+		"std    31,248(%2)\n"
+		"mfmsr  %0\n"
+		"std    %0, 264(%2)\n"
+		"mfctr  %0\n"
+		"std    %0, 280(%2)\n"
+		"mflr   %0\n"
+		"std    %0, 288(%2)\n"
+		"bl     1f\n"
+	"1:      mflr   %1\n"
+		"std    %1, 256(%2)\n"
+		"mtlr   %0\n"
+		"mfxer  %0\n"
+		"std    %0, 296(%2)\n"
+		: "=&r" (tmp1), "=&r" (tmp2)
+		: "b" (regs));
+}
+
+/* We may have saved_regs from where the error came from
+ * or it is NULL if via a direct panic().
+ */
+static void crash_save_self(struct pt_regs *saved_regs)
+{
+	struct pt_regs regs;
+	int cpu;
+
+	cpu = smp_processor_id();
+	if (saved_regs)
+		memcpy(&regs, saved_regs, sizeof(regs));
+	else
+		crash_get_current_regs(&regs);
+	crash_save_this_cpu(&regs, cpu);
+}
+
+#ifdef CONFIG_SMP
+static atomic_t waiting_for_crash_ipi;
+
+void crash_ipi_callback(struct pt_regs *regs)
+{
+	int cpu = smp_processor_id();
+
+	if (cpu == crashing_cpu)
+		return;
+
+	if (!cpu_online(cpu))
+		return;
+
+	if (ppc_md.kexec_cpu_down)
+		ppc_md.kexec_cpu_down(1, 1);
+
+	local_irq_disable();
+
+	crash_save_this_cpu(regs, cpu);
+	atomic_dec(&waiting_for_crash_ipi);
+	kexec_smp_wait();
+	/* NOTREACHED */
+}
+
+static void crash_kexec_prepare_cpus(void)
+{
+	unsigned int msecs;
+
+	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+
+	crash_send_ipi(crash_ipi_callback);
+	smp_wmb();
+
+	/*
+	 * FIXME: Until we will have the way to stop other CPUSs reliabally,
+	 * the crash CPU will send an IPI and wait for other CPUs to
+	 * respond. If not, proceed the kexec boot even though we failed to
+	 * capture other CPU states.
+	 */
+	msecs = 1000000;
+	while ((atomic_read(&waiting_for_crash_ipi) > 0) && (--msecs > 0)) {
+		barrier();
+		mdelay(1);
+	}
+
+	/* Would it be better to replace the trap vector here? */
+
+	/*
+	 * FIXME: In case if we do not get all CPUs, one possibility: ask the
+	 * user to do soft reset such that we get all.
+	 * IPI handler is already set by the panic cpu initially. Therefore,
+	 * all cpus could invoke this handler from die() and the panic CPU
+	 * will call machine_kexec() directly from this handler to do
+	 * kexec boot.
+	 */
+	if (atomic_read(&waiting_for_crash_ipi))
+		printk(KERN_ALERT "done waiting: %d cpus not responding\n",
+			atomic_read(&waiting_for_crash_ipi));
+	/* Leave the IPI callback set */
+}
+#else
+static void crash_kexec_prepare_cpus(void)
+{
+	/*
+	 * move the secondarys to us so that we can copy
+	 * the new kernel 0-0x100 safely
+	 *
+	 * do this if kexec in setup.c ?
+	 */
+	smp_release_cpus();
+}
+
+#endif
+
+void default_machine_crash_shutdown(struct pt_regs *regs)
+{
+	/*
+	 * This function is only called after the system
+	 * has paniced or is otherwise in a critical state.
+	 * The minimum amount of code to allow a kexec'd kernel
+	 * to run successfully needs to happen here.
+	 *
+	 * In practice this means stopping other cpus in
+	 * an SMP system.
+	 * The kernel is broken so disable interrupts.
+	 */
+	local_irq_disable();
+
+	if (ppc_md.kexec_cpu_down)
+		ppc_md.kexec_cpu_down(1, 0);
+
+	/*
+	 * Make a note of crashing cpu. Will be used in machine_kexec
+	 * such that another IPI will not be sent.
+	 */
+	crashing_cpu = smp_processor_id();
+	crash_kexec_prepare_cpus();
+	crash_save_self(regs);
+}

arch/powerpc/kernel/crash_dump.c

+/*
+ * Routines for doing kexec-based kdump.
+ *
+ * Copyright (C) 2005, IBM Corp.
+ *
+ * Created by: Michael Ellerman
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#undef DEBUG
+
+#include <linux/crash_dump.h>
+#include <linux/bootmem.h>
+#include <asm/kdump.h>
+#include <asm/lmb.h>
+#include <asm/firmware.h>
+#include <asm/uaccess.h>
+
+#ifdef DEBUG
+#include <asm/udbg.h>
+#define DBG(fmt...) udbg_printf(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+static void __init create_trampoline(unsigned long addr)
+{
+	/* The maximum range of a single instruction branch, is the current
+	 * instruction's address + (32 MB - 4) bytes. For the trampoline we
+	 * need to branch to current address + 32 MB. So we insert a nop at
+	 * the trampoline address, then the next instruction (+ 4 bytes)
+	 * does a branch to (32 MB - 4). The net effect is that when we
+	 * branch to "addr" we jump to ("addr" + 32 MB). Although it requires
+	 * two instructions it doesn't require any registers.
+	 */
+	create_instruction(addr, 0x60000000); /* nop */
+	create_branch(addr + 4, addr + PHYSICAL_START, 0);
+}
+
+void __init kdump_setup(void)
+{
+	unsigned long i;
+
+	DBG(" -> kdump_setup()\n");
+
+	for (i = KDUMP_TRAMPOLINE_START; i < KDUMP_TRAMPOLINE_END; i += 8) {
+		create_trampoline(i);
+	}
+
+	create_trampoline(__pa(system_reset_fwnmi) - PHYSICAL_START);
+	create_trampoline(__pa(machine_check_fwnmi) - PHYSICAL_START);
+
+	DBG(" <- kdump_setup()\n");
+}
+
+static int __init parse_elfcorehdr(char *p)
+{
+	if (p)
+		elfcorehdr_addr = memparse(p, &p);
+
+	return 0;
+}
+__setup("elfcorehdr=", parse_elfcorehdr);
+
+static int __init parse_savemaxmem(char *p)
+{
+	if (p)
+		saved_max_pfn = (memparse(p, &p) >> PAGE_SHIFT) - 1;
+
+	return 0;
+}
+__setup("savemaxmem=", parse_savemaxmem);
+
+/*
+ * copy_oldmem_page - copy one page from "oldmem"
+ * @pfn: page frame number to be copied
+ * @buf: target memory address for the copy; this can be in kernel address
+ *      space or user address space (see @userbuf)
+ * @csize: number of bytes to copy
+ * @offset: offset in bytes into the page (based on pfn) to begin the copy
+ * @userbuf: if set, @buf is in user address space, use copy_to_user(),
+ *      otherwise @buf is in kernel address space, use memcpy().
+ *
+ * Copy a page from "oldmem". For this page, there is no pte mapped
+ * in the current kernel. We stitch up a pte, similar to kmap_atomic.
+ */
+ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
+			size_t csize, unsigned long offset, int userbuf)
+{
+	void  *vaddr;
+
+	if (!csize)
+		return 0;
+
+	vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0);
+
+	if (userbuf) {
+		if (copy_to_user((char __user *)buf, (vaddr + offset), csize)) {
+			iounmap(vaddr);
+			return -EFAULT;
+		}
+	} else
+		memcpy(buf, (vaddr + offset), csize);
+
+	iounmap(vaddr);
+	return csize;
+}

arch/powerpc/kernel/dma_64.c

@@ -10,6 +10,7 @@
 /* Include the busses we support */
 #include <linux/pci.h>
 #include <asm/vio.h>
+#include <asm/ibmebus.h>
 #include <asm/scatterlist.h>
 #include <asm/bug.h>
 
@@ -22,6 +23,10 @@ static struct dma_mapping_ops *get_dma_ops(struct device *dev)
 #ifdef CONFIG_IBMVIO
 	if (dev->bus == &vio_bus_type)
 		return &vio_dma_ops;
+#endif
+#ifdef CONFIG_IBMEBUS
+	if (dev->bus == &ibmebus_bus_type)
+		return &ibmebus_dma_ops;
 #endif
 	return NULL;
 }
@@ -47,6 +52,10 @@ int dma_set_mask(struct device *dev, u64 dma_mask)
 	if (dev->bus == &vio_bus_type)
 		return -EIO;
 #endif /* CONFIG_IBMVIO */
+#ifdef CONFIG_IBMEBUS
+	if (dev->bus == &ibmebus_bus_type)
+		return -EIO;
+#endif
 	BUG();
 	return 0;
 }

arch/powerpc/kernel/entry_32.S

@@ -200,8 +200,6 @@ _GLOBAL(DoSyscall)
 	bl	do_show_syscall
 #endif /* SHOW_SYSCALLS */
 	rlwinm	r10,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
-	li	r11,0
-	stb	r11,TI_SC_NOERR(r10)
 	lwz	r11,TI_FLAGS(r10)
 	andi.	r11,r11,_TIF_SYSCALL_T_OR_A
 	bne-	syscall_dotrace
@@ -222,25 +220,21 @@ ret_from_syscall:
 	bl	do_show_syscall_exit
 #endif
 	mr	r6,r3
-	li	r11,-_LAST_ERRNO
-	cmplw	0,r3,r11
 	rlwinm	r12,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
-	blt+	30f
-	lbz	r11,TI_SC_NOERR(r12)
-	cmpwi	r11,0
-	bne	30f
-	neg	r3,r3
-	lwz	r10,_CCR(r1)	/* Set SO bit in CR */
-	oris	r10,r10,0x1000
-	stw	r10,_CCR(r1)
-
 	/* disable interrupts so current_thread_info()->flags can't change */
-30:	LOAD_MSR_KERNEL(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
+	LOAD_MSR_KERNEL(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
 	SYNC
 	MTMSRD(r10)
 	lwz	r9,TI_FLAGS(r12)
-	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SIGPENDING|_TIF_NEED_RESCHED)
+	li	r8,-_LAST_ERRNO
+	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SIGPENDING|_TIF_NEED_RESCHED|_TIF_RESTOREALL)
 	bne-	syscall_exit_work
+	cmplw	0,r3,r8
+	blt+	syscall_exit_cont
+	lwz	r11,_CCR(r1)			/* Load CR */
+	neg	r3,r3
+	oris	r11,r11,0x1000	/* Set SO bit in CR */
+	stw	r11,_CCR(r1)
 syscall_exit_cont:
 #if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
 	/* If the process has its own DBCR0 value, load it up.  The single
@@ -292,46 +286,113 @@ syscall_dotrace:
 	b	syscall_dotrace_cont
 
 syscall_exit_work:
-	stw	r6,RESULT(r1)	/* Save result */
+	andi.	r0,r9,_TIF_RESTOREALL
+	bne-	2f
+	cmplw	0,r3,r8
+	blt+	1f
+	andi.	r0,r9,_TIF_NOERROR
+	bne-	1f
+	lwz	r11,_CCR(r1)			/* Load CR */
+	neg	r3,r3
+	oris	r11,r11,0x1000	/* Set SO bit in CR */
+	stw	r11,_CCR(r1)
+
+1:	stw	r6,RESULT(r1)	/* Save result */
 	stw	r3,GPR3(r1)	/* Update return value */
-	andi.	r0,r9,_TIF_SYSCALL_T_OR_A
-	beq	5f
-	ori	r10,r10,MSR_EE
-	SYNC
-	MTMSRD(r10)		/* re-enable interrupts */
+2:	andi.	r0,r9,(_TIF_PERSYSCALL_MASK)
+	beq	4f
+
+	/* Clear per-syscall TIF flags if any are set, but _leave_
+	_TIF_SAVE_NVGPRS set in r9 since we haven't dealt with that
+	yet.  */
+
+	li	r11,_TIF_PERSYSCALL_MASK
+	addi	r12,r12,TI_FLAGS
+3:	lwarx	r8,0,r12
+	andc	r8,r8,r11
+#ifdef CONFIG_IBM405_ERR77
+	dcbt	0,r12
+#endif
+	stwcx.	r8,0,r12
+	bne-	3b
+	subi	r12,r12,TI_FLAGS
+	
+4:	/* Anything which requires enabling interrupts? */
+	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP|_TIF_SAVE_NVGPRS)
+	beq	7f
+
+	/* Save NVGPRS if they're not saved already */
 	lwz	r4,_TRAP(r1)
 	andi.	r4,r4,1
-	beq	4f
+	beq	5f
 	SAVE_NVGPRS(r1)
 	li	r4,0xc00
 	stw	r4,_TRAP(r1)
-4:
+
+	/* Re-enable interrupts */
+5:	ori	r10,r10,MSR_EE
+	SYNC
+	MTMSRD(r10)
+
+	andi.	r0,r9,_TIF_SAVE_NVGPRS
+	bne	save_user_nvgprs
+
+save_user_nvgprs_cont:
+	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
+	beq	7f
+
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_syscall_trace_leave
 	REST_NVGPRS(r1)
-2:
-	lwz	r3,GPR3(r1)
+
+6:	lwz	r3,GPR3(r1)
 	LOAD_MSR_KERNEL(r10,MSR_KERNEL)	/* doesn't include MSR_EE */
 	SYNC
 	MTMSRD(r10)		/* disable interrupts again */
 	rlwinm	r12,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
 	lwz	r9,TI_FLAGS(r12)
-5:
+7:
 	andi.	r0,r9,_TIF_NEED_RESCHED
-	bne	1f
+	bne	8f
 	lwz	r5,_MSR(r1)
 	andi.	r5,r5,MSR_PR
-	beq	syscall_exit_cont
+	beq	ret_from_except
 	andi.	r0,r9,_TIF_SIGPENDING
-	beq	syscall_exit_cont
+	beq	ret_from_except
 	b	do_user_signal
-1:
+8:
 	ori	r10,r10,MSR_EE
 	SYNC
 	MTMSRD(r10)		/* re-enable interrupts */
 	bl	schedule
-	b	2b
+	b	6b
+
+save_user_nvgprs:
+	lwz	r8,TI_SIGFRAME(r12)
+
+.macro savewords start, end
+  1:	stw \start,4*(\start)(r8)
+	.section __ex_table,"a"
+	.align	2
+	.long	1b,save_user_nvgprs_fault
+	.previous
+	.if \end - \start
+	savewords "(\start+1)",\end
+	.endif
+.endm	
+	savewords 14,31
+	b	save_user_nvgprs_cont
+
+	
+save_user_nvgprs_fault:
+	li	r3,11		/* SIGSEGV */
+	lwz	r4,TI_TASK(r12)
+	bl	force_sigsegv
 
+	rlwinm	r12,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
+	lwz	r9,TI_FLAGS(r12)
+	b	save_user_nvgprs_cont
+	
 #ifdef SHOW_SYSCALLS
 do_show_syscall:
 #ifdef SHOW_SYSCALLS_TASK
@@ -401,28 +462,10 @@ show_syscalls_task:
 #endif /* SHOW_SYSCALLS */
 
 /*
- * The sigsuspend and rt_sigsuspend system calls can call do_signal
- * and thus put the process into the stopped state where we might
- * want to examine its user state with ptrace.  Therefore we need
- * to save all the nonvolatile registers (r13 - r31) before calling
- * the C code.
+ * The fork/clone functions need to copy the full register set into
+ * the child process. Therefore we need to save all the nonvolatile
+ * registers (r13 - r31) before calling the C code.
  */
-	.globl	ppc_sigsuspend
-ppc_sigsuspend:
-	SAVE_NVGPRS(r1)
-	lwz	r0,_TRAP(r1)
-	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
-	stw	r0,_TRAP(r1)		/* register set saved */
-	b	sys_sigsuspend
-
-	.globl	ppc_rt_sigsuspend
-ppc_rt_sigsuspend:
-	SAVE_NVGPRS(r1)
-	lwz	r0,_TRAP(r1)
-	rlwinm	r0,r0,0,0,30
-	stw	r0,_TRAP(r1)
-	b	sys_rt_sigsuspend
-
 	.globl	ppc_fork
 ppc_fork:
 	SAVE_NVGPRS(r1)
@@ -447,14 +490,6 @@ ppc_clone:
 	stw	r0,_TRAP(r1)		/* register set saved */
 	b	sys_clone
 
-	.globl	ppc_swapcontext
-ppc_swapcontext:
-	SAVE_NVGPRS(r1)
-	lwz	r0,_TRAP(r1)
-	rlwinm	r0,r0,0,0,30		/* clear LSB to indicate full */
-	stw	r0,_TRAP(r1)		/* register set saved */
-	b	sys_swapcontext
-
 /*
  * Top-level page fault handling.
  * This is in assembler because if do_page_fault tells us that
@@ -626,16 +661,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_601)
 	.long	ret_from_except
 #endif
 
-	.globl	sigreturn_exit
-sigreturn_exit:
-	subi	r1,r3,STACK_FRAME_OVERHEAD
-	rlwinm	r12,r1,0,0,(31-THREAD_SHIFT)	/* current_thread_info() */
-	lwz	r9,TI_FLAGS(r12)
-	andi.	r0,r9,_TIF_SYSCALL_T_OR_A
-	beq+	ret_from_except_full
-	bl	do_syscall_trace_leave
-	/* fall through */
-
 	.globl	ret_from_except_full
 ret_from_except_full:
 	REST_NVGPRS(r1)
@@ -658,7 +683,7 @@ user_exc_return:		/* r10 contains MSR_KERNEL here */
 	/* Check current_thread_info()->flags */
 	rlwinm	r9,r1,0,0,(31-THREAD_SHIFT)
 	lwz	r9,TI_FLAGS(r9)
-	andi.	r0,r9,(_TIF_SIGPENDING|_TIF_NEED_RESCHED)
+	andi.	r0,r9,(_TIF_SIGPENDING|_TIF_NEED_RESCHED|_TIF_RESTOREALL)
 	bne	do_work
 
 restore_user:

arch/powerpc/kernel/entry_64.S

@@ -113,9 +113,7 @@ system_call_common:
 	addi	r9,r1,STACK_FRAME_OVERHEAD
 #endif
 	clrrdi	r11,r1,THREAD_SHIFT
-	li	r12,0
 	ld	r10,TI_FLAGS(r11)
-	stb	r12,TI_SC_NOERR(r11)
 	andi.	r11,r10,_TIF_SYSCALL_T_OR_A
 	bne-	syscall_dotrace
 syscall_dotrace_cont:
@@ -144,24 +142,12 @@ system_call:			/* label this so stack traces look sane */
 	bctrl			/* Call handler */
 
 syscall_exit:
+	std	r3,RESULT(r1)
 #ifdef SHOW_SYSCALLS
-	std	r3,GPR3(r1)
 	bl	.do_show_syscall_exit
-	ld	r3,GPR3(r1)
+	ld	r3,RESULT(r1)
 #endif
-	std	r3,RESULT(r1)
-	ld	r5,_CCR(r1)
-	li	r10,-_LAST_ERRNO
-	cmpld	r3,r10
 	clrrdi	r12,r1,THREAD_SHIFT
-	bge-	syscall_error
-syscall_error_cont:
-
-	/* check for syscall tracing or audit */
-	ld	r9,TI_FLAGS(r12)
-	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
-	bne-	syscall_exit_trace
-syscall_exit_trace_cont:
 
 	/* disable interrupts so current_thread_info()->flags can't change,
 	   and so that we don't get interrupted after loading SRR0/1. */
@@ -173,8 +159,13 @@ syscall_exit_trace_cont:
 	rotldi	r10,r10,16
 	mtmsrd	r10,1
 	ld	r9,TI_FLAGS(r12)
-	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SIGPENDING|_TIF_NEED_RESCHED)
+	li	r11,-_LAST_ERRNO
+	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP|_TIF_SIGPENDING|_TIF_NEED_RESCHED|_TIF_RESTOREALL|_TIF_SAVE_NVGPRS|_TIF_NOERROR)
 	bne-	syscall_exit_work
+	cmpld	r3,r11
+	ld	r5,_CCR(r1)
+	bge-	syscall_error
+syscall_error_cont:
 	ld	r7,_NIP(r1)
 	stdcx.	r0,0,r1			/* to clear the reservation */
 	andi.	r6,r8,MSR_PR
@@ -193,21 +184,12 @@ syscall_exit_trace_cont:
 	rfid
 	b	.	/* prevent speculative execution */
 
-syscall_enosys:
-	li	r3,-ENOSYS
-	std	r3,RESULT(r1)
-	clrrdi	r12,r1,THREAD_SHIFT
-	ld	r5,_CCR(r1)
-
-syscall_error:
-	lbz	r11,TI_SC_NOERR(r12)
-	cmpwi	0,r11,0
-	bne-	syscall_error_cont
-	neg	r3,r3
+syscall_error:	
 	oris	r5,r5,0x1000	/* Set SO bit in CR */
+	neg	r3,r3
 	std	r5,_CCR(r1)
 	b	syscall_error_cont
-        
+	
 /* Traced system call support */
 syscall_dotrace:
 	bl	.save_nvgprs
@@ -225,21 +207,69 @@ syscall_dotrace:
 	ld	r10,TI_FLAGS(r10)
 	b	syscall_dotrace_cont
 
-syscall_exit_trace:
-	std	r3,GPR3(r1)
-	bl	.save_nvgprs
+syscall_enosys:
+	li	r3,-ENOSYS
+	b	syscall_exit
+	
+syscall_exit_work:
+	/* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr.
+	 If TIF_NOERROR is set, just save r3 as it is. */
+
+	andi.	r0,r9,_TIF_RESTOREALL
+	bne-	2f
+	cmpld	r3,r11		/* r10 is -LAST_ERRNO */
+	blt+	1f
+	andi.	r0,r9,_TIF_NOERROR
+	bne-	1f
+	ld	r5,_CCR(r1)
+	neg	r3,r3
+	oris	r5,r5,0x1000	/* Set SO bit in CR */
+	std	r5,_CCR(r1)
+1:	std	r3,GPR3(r1)
+2:	andi.	r0,r9,(_TIF_PERSYSCALL_MASK)
+	beq	4f
+
+	/* Clear per-syscall TIF flags if any are set, but _leave_
+	_TIF_SAVE_NVGPRS set in r9 since we haven't dealt with that
+	yet.  */
+
+	li	r11,_TIF_PERSYSCALL_MASK
+	addi	r12,r12,TI_FLAGS
+3:	ldarx	r10,0,r12
+	andc	r10,r10,r11
+	stdcx.	r10,0,r12
+	bne-	3b
+	subi	r12,r12,TI_FLAGS
+	
+4:	bl	.save_nvgprs
+	/* Anything else left to do? */
+	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP|_TIF_SAVE_NVGPRS)
+	beq	.ret_from_except_lite
+
+	/* Re-enable interrupts */
+	mfmsr	r10
+	ori	r10,r10,MSR_EE
+	mtmsrd	r10,1
+
+	andi.	r0,r9,_TIF_SAVE_NVGPRS
+	bne	save_user_nvgprs
+
+	/* If tracing, re-enable interrupts and do it */
+save_user_nvgprs_cont:	
+	andi.	r0,r9,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
+	beq	5f
+	
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	.do_syscall_trace_leave
 	REST_NVGPRS(r1)
-	ld	r3,GPR3(r1)
-	ld	r5,_CCR(r1)
 	clrrdi	r12,r1,THREAD_SHIFT
-	b	syscall_exit_trace_cont
 
-/* Stuff to do on exit from a system call. */
-syscall_exit_work:
-	std	r3,GPR3(r1)
-	std	r5,_CCR(r1)
+	/* Disable interrupts again and handle other work if any */
+5:	mfmsr	r10
+	rldicl	r10,r10,48,1
+	rotldi	r10,r10,16
+	mtmsrd	r10,1
+
 	b	.ret_from_except_lite
 
 /* Save non-volatile GPRs, if not already saved. */
@@ -252,6 +282,52 @@ _GLOBAL(save_nvgprs)
 	std	r0,_TRAP(r1)
 	blr
 
+
+save_user_nvgprs:
+	ld	r10,TI_SIGFRAME(r12)
+	andi.	r0,r9,_TIF_32BIT
+	beq-	save_user_nvgprs_64
+
+	/* 32-bit save to userspace */
+
+.macro savewords start, end
+  1:	stw \start,4*(\start)(r10)
+	.section __ex_table,"a"
+	.align	3
+	.llong	1b,save_user_nvgprs_fault
+	.previous
+	.if \end - \start
+	savewords "(\start+1)",\end
+	.endif
+.endm	
+	savewords 14,31
+	b	save_user_nvgprs_cont
+
+save_user_nvgprs_64:
+	/* 64-bit save to userspace */
+
+.macro savelongs start, end
+  1:	std \start,8*(\start)(r10)
+	.section __ex_table,"a"
+	.align	3
+	.llong	1b,save_user_nvgprs_fault
+	.previous
+	.if \end - \start
+	savelongs "(\start+1)",\end
+	.endif
+.endm	
+	savelongs 14,31
+	b	save_user_nvgprs_cont
+
+save_user_nvgprs_fault:
+	li	r3,11		/* SIGSEGV */
+	ld	r4,TI_TASK(r12)
+	bl	.force_sigsegv
+
+	clrrdi	r12,r1,THREAD_SHIFT
+	ld	r9,TI_FLAGS(r12)
+	b	save_user_nvgprs_cont
+	
 /*
  * The sigsuspend and rt_sigsuspend system calls can call do_signal
  * and thus put the process into the stopped state where we might
@@ -260,35 +336,6 @@ _GLOBAL(save_nvgprs)
  * the C code.  Similarly, fork, vfork and clone need the full
  * register state on the stack so that it can be copied to the child.
  */
-_GLOBAL(ppc32_sigsuspend)
-	bl	.save_nvgprs
-	bl	.compat_sys_sigsuspend
-	b	70f
-
-_GLOBAL(ppc64_rt_sigsuspend)
-	bl	.save_nvgprs
-	bl	.sys_rt_sigsuspend
-	b	70f
-
-_GLOBAL(ppc32_rt_sigsuspend)
-	bl	.save_nvgprs
-	bl	.compat_sys_rt_sigsuspend
-70:	cmpdi	0,r3,0
-	/* If it returned an error, we need to return via syscall_exit to set
-	   the SO bit in cr0 and potentially stop for ptrace. */
-	bne	syscall_exit
-	/* If sigsuspend() returns zero, we are going into a signal handler. We
-	   may need to call audit_syscall_exit() to mark the exit from sigsuspend() */
-#ifdef CONFIG_AUDITSYSCALL
-	ld	r3,PACACURRENT(r13)
-	ld	r4,AUDITCONTEXT(r3)
-	cmpdi	0,r4,0
-	beq	.ret_from_except	/* No audit_context: Leave immediately. */
-	li	r4, 2			/* AUDITSC_FAILURE */
-	li	r5,-4			/* It's always -EINTR */
-	bl	.audit_syscall_exit
-#endif
-	b	.ret_from_except
 
 _GLOBAL(ppc_fork)
 	bl	.save_nvgprs
@@ -305,37 +352,6 @@ _GLOBAL(ppc_clone)
 	bl	.sys_clone
 	b	syscall_exit
 
-_GLOBAL(ppc32_swapcontext)
-	bl	.save_nvgprs
-	bl	.compat_sys_swapcontext
-	b	80f
-	
-_GLOBAL(ppc64_swapcontext)
-	bl	.save_nvgprs
-	bl	.sys_swapcontext
-	b	80f
-
-_GLOBAL(ppc32_sigreturn)
-	bl	.compat_sys_sigreturn
-	b	80f
-
-_GLOBAL(ppc32_rt_sigreturn)
-	bl	.compat_sys_rt_sigreturn
-	b	80f
-
-_GLOBAL(ppc64_rt_sigreturn)
-	bl	.sys_rt_sigreturn
-
-80:	cmpdi	0,r3,0
-	blt	syscall_exit
-	clrrdi	r4,r1,THREAD_SHIFT
-	ld	r4,TI_FLAGS(r4)
-	andi.	r4,r4,(_TIF_SYSCALL_T_OR_A|_TIF_SINGLESTEP)
-	beq+	81f
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.do_syscall_trace_leave
-81:	b	.ret_from_except
-
 _GLOBAL(ret_from_fork)
 	bl	.schedule_tail
 	REST_NVGPRS(r1)
@@ -674,7 +690,7 @@ _GLOBAL(enter_rtas)
 
 	/* Setup our real return addr */	
 	SET_REG_TO_LABEL(r4,.rtas_return_loc)
-	SET_REG_TO_CONST(r9,KERNELBASE)
+	SET_REG_TO_CONST(r9,PAGE_OFFSET)
 	sub	r4,r4,r9
        	mtlr	r4
 
@@ -702,7 +718,7 @@ _GLOBAL(enter_rtas)
 _STATIC(rtas_return_loc)
 	/* relocation is off at this point */
 	mfspr	r4,SPRN_SPRG3	        /* Get PACA */
-	SET_REG_TO_CONST(r5, KERNELBASE)
+	SET_REG_TO_CONST(r5, PAGE_OFFSET)
         sub     r4,r4,r5                /* RELOC the PACA base pointer */
 
 	mfmsr   r6

arch/powerpc/kernel/head_32.S

@@ -120,10 +120,25 @@ __start:
  * because OF may have I/O devices mapped into that area
  * (particularly on CHRP).
  */
+#ifdef CONFIG_PPC_MULTIPLATFORM
 	cmpwi	0,r5,0
 	beq	1f
 	bl	prom_init
 	trap
+#endif
+
+/*
+ * Check for BootX signature when supporting PowerMac and branch to
+ * appropriate trampoline if it's present
+ */
+#ifdef CONFIG_PPC_PMAC
+1:	lis	r31,0x426f
+	ori	r31,r31,0x6f58
+	cmpw	0,r3,r31
+	bne	1f
+	bl	bootx_init
+	trap
+#endif /* CONFIG_PPC_PMAC */
 
 1:	mr	r31,r3			/* save parameters */
 	mr	r30,r4
@@ -153,6 +168,9 @@ __after_mmu_off:
 	bl	flush_tlbs
 
 	bl	initial_bats
+#if !defined(CONFIG_APUS) && defined(CONFIG_BOOTX_TEXT)
+	bl	setup_disp_bat
+#endif
 
 /*
  * Call setup_cpu for CPU 0 and initialize 6xx Idle
@@ -450,16 +468,11 @@ SystemCall:
  * by executing an altivec instruction.
  */
 	. = 0xf00
-	b	Trap_0f
+	b	PerformanceMonitor
 
 	. = 0xf20
 	b	AltiVecUnavailable
 
-Trap_0f:
-	EXCEPTION_PROLOG
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_EE(0xf00, unknown_exception)
-
 /*
  * Handle TLB miss for instruction on 603/603e.
  * Note: we get an alternate set of r0 - r3 to use automatically.
@@ -703,6 +716,11 @@ AltiVecUnavailable:
 #endif /* CONFIG_ALTIVEC */
 	EXC_XFER_EE_LITE(0xf20, altivec_unavailable_exception)
 
+PerformanceMonitor:
+	EXCEPTION_PROLOG
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	EXC_XFER_STD(0xf00, performance_monitor_exception)
+
 #ifdef CONFIG_ALTIVEC
 /* Note that the AltiVec support is closely modeled after the FP
  * support.  Changes to one are likely to be applicable to the
@@ -1306,6 +1324,32 @@ initial_bats:
 	blr
 
 
+#if !defined(CONFIG_APUS) && defined(CONFIG_BOOTX_TEXT)
+setup_disp_bat:
+	/*
+	 * setup the display bat prepared for us in prom.c
+	 */
+	mflr	r8
+	bl	reloc_offset
+	mtlr	r8
+	addis	r8,r3,disp_BAT@ha
+	addi	r8,r8,disp_BAT@l
+	cmpwi	cr0,r8,0
+	beqlr
+	lwz	r11,0(r8)
+	lwz	r8,4(r8)
+	mfspr	r9,SPRN_PVR
+	rlwinm	r9,r9,16,16,31		/* r9 = 1 for 601, 4 for 604 */
+	cmpwi	0,r9,1
+	beq	1f
+	mtspr	SPRN_DBAT3L,r8
+	mtspr	SPRN_DBAT3U,r11
+	blr
+1:	mtspr	SPRN_IBAT3L,r8
+	mtspr	SPRN_IBAT3U,r11
+	blr
+#endif /* !defined(CONFIG_APUS) && defined(CONFIG_BOOTX_TEXT) */
+
 #ifdef CONFIG_8260
 /* Jump into the system reset for the rom.
  * We first disable the MMU, and then jump to the ROM reset address.

arch/powerpc/kernel/head_64.S

@@ -154,11 +154,15 @@ _GLOBAL(__secondary_hold)
 	bne	100b
 
 #ifdef CONFIG_HMT
-	b	.hmt_init
+	LOADADDR(r4, .hmt_init)
+	mtctr	r4
+	bctr
 #else
 #ifdef CONFIG_SMP
+	LOADADDR(r4, .pSeries_secondary_smp_init)
+	mtctr	r4
 	mr	r3,r24
-	b	.pSeries_secondary_smp_init
+	bctr
 #else
 	BUG_OPCODE
 #endif
@@ -200,6 +204,20 @@ exception_marker:
 #define EX_R3		64
 #define EX_LR		72
 
+/*
+ * We're short on space and time in the exception prolog, so we can't use
+ * the normal LOADADDR macro. Normally we just need the low halfword of the
+ * address, but for Kdump we need the whole low word.
+ */
+#ifdef CONFIG_CRASH_DUMP
+#define LOAD_HANDLER(reg, label)					\
+	oris	reg,reg,(label)@h;	/* virt addr of handler ... */	\
+	ori	reg,reg,(label)@l;	/* .. and the rest */
+#else
+#define LOAD_HANDLER(reg, label)					\
+	ori	reg,reg,(label)@l;	/* virt addr of handler ... */
+#endif
+
 #define EXCEPTION_PROLOG_PSERIES(area, label)				\
 	mfspr	r13,SPRN_SPRG3;		/* get paca address into r13 */	\
 	std	r9,area+EX_R9(r13);	/* save r9 - r12 */		\
@@ -212,7 +230,7 @@ exception_marker:
 	clrrdi	r12,r13,32;		/* get high part of &label */	\
 	mfmsr	r10;							\
 	mfspr	r11,SPRN_SRR0;		/* save SRR0 */			\
-	ori	r12,r12,(label)@l;	/* virt addr of handler */	\
+	LOAD_HANDLER(r12,label)						\
 	ori	r10,r10,MSR_IR|MSR_DR|MSR_RI;				\
 	mtspr	SPRN_SRR0,r12;						\
 	mfspr	r12,SPRN_SRR1;		/* and SRR1 */			\
@@ -553,6 +571,7 @@ slb_miss_user_pseries:
  * Vectors for the FWNMI option.  Share common code.
  */
 	.globl system_reset_fwnmi
+      .align 7
 system_reset_fwnmi:
 	HMT_MEDIUM
 	mtspr	SPRN_SPRG1,r13		/* save r13 */
@@ -560,6 +579,7 @@ system_reset_fwnmi:
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common)
 
 	.globl machine_check_fwnmi
+      .align 7
 machine_check_fwnmi:
 	HMT_MEDIUM
 	mtspr	SPRN_SPRG1,r13		/* save r13 */
@@ -726,7 +746,8 @@ iSeries_secondary_smp_loop:
 decrementer_iSeries_masked:
 	li	r11,1
 	stb	r11,PACALPPACA+LPPACADECRINT(r13)
-	lwz	r12,PACADEFAULTDECR(r13)
+	LOADBASE(r12,tb_ticks_per_jiffy)
+	lwz	r12,OFF(tb_ticks_per_jiffy)(r12)
 	mtspr	SPRN_DEC,r12
 	/* fall through */
 
@@ -1345,7 +1366,7 @@ _GLOBAL(do_stab_bolted)
  * fixed address (the linker can't compute (u64)&initial_stab >>
  * PAGE_SHIFT).
  */
-	. = STAB0_PHYS_ADDR	/* 0x6000 */
+	. = STAB0_OFFSET	/* 0x6000 */
 	.globl initial_stab
 initial_stab:
 	.space	4096
@@ -1485,11 +1506,13 @@ _STATIC(__mmu_off)
  *
  */
 _GLOBAL(__start_initialization_multiplatform)
+#ifdef CONFIG_PPC_MULTIPLATFORM
 	/*
 	 * Are we booted from a PROM Of-type client-interface ?
 	 */
 	cmpldi	cr0,r5,0
 	bne	.__boot_from_prom		/* yes -> prom */
+#endif
 
 	/* Save parameters */
 	mr	r31,r3
@@ -1510,6 +1533,7 @@ _GLOBAL(__start_initialization_multiplatform)
 	bl	.__mmu_off
 	b	.__after_prom_start
 
+#ifdef CONFIG_PPC_MULTIPLATFORM
 _STATIC(__boot_from_prom)
 	/* Save parameters */
 	mr	r31,r3
@@ -1542,6 +1566,7 @@ _STATIC(__boot_from_prom)
 	bl	.prom_init
 	/* We never return */
 	trap
+#endif
 
 /*
  * At this point, r3 contains the physical address we are running at,
@@ -1550,7 +1575,7 @@ _STATIC(__boot_from_prom)
 _STATIC(__after_prom_start)
 
 /*
- * We need to run with __start at physical address 0.
+ * We need to run with __start at physical address PHYSICAL_START.
  * This will leave some code in the first 256B of
  * real memory, which are reserved for software use.
  * The remainder of the first page is loaded with the fixed
@@ -1565,7 +1590,7 @@ _STATIC(__after_prom_start)
 	mr	r26,r3
 	SET_REG_TO_CONST(r27,KERNELBASE)
 
-	li	r3,0			/* target addr */
+	LOADADDR(r3, PHYSICAL_START)	/* target addr */
 
 	// XXX FIXME: Use phys returned by OF (r30)
 	add	r4,r27,r26 		/* source addr			 */
@@ -1846,7 +1871,7 @@ _STATIC(start_here_multiplatform)
 	mulli	r13,r27,PACA_SIZE	/* Calculate vaddr of right paca */
 	add	r13,r13,r24		/* for this processor.		 */
 	add	r13,r13,r26		/* convert to physical addr	 */
-	mtspr	SPRN_SPRG3,r13		/* PPPBBB: Temp... -Peter */
+	mtspr	SPRN_SPRG3,r13
 	
 	/* Do very early kernel initializations, including initial hash table,
 	 * stab and slb setup before we turn on relocation.	*/

arch/powerpc/kernel/ibmebus.c

+/*
+ * IBM PowerPC IBM eBus Infrastructure Support.
+ *
+ * Copyright (c) 2005 IBM Corporation
+ *  Heiko J Schick <schickhj@de.ibm.com>
+ *    
+ * All rights reserved.
+ *
+ * This source code is distributed under a dual license of GPL v2.0 and OpenIB 
+ * BSD. 
+ *
+ * OpenIB BSD License
+ *
+ * Redistribution and use in source and binary forms, with or without 
+ * modification, are permitted provided that the following conditions are met: 
+ *
+ * Redistributions of source code must retain the above copyright notice, this 
+ * list of conditions and the following disclaimer. 
+ *
+ * Redistributions in binary form must reproduce the above copyright notice, 
+ * this list of conditions and the following disclaimer in the documentation 
+ * and/or other materials
+ * provided with the distribution. 
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" 
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE 
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR 
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF 
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER
+ * IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) 
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/init.h>
+#include <linux/console.h>
+#include <linux/kobject.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <asm/ibmebus.h>
+#include <asm/abs_addr.h>
+
+static struct ibmebus_dev ibmebus_bus_device = { /* fake "parent" device */
+	.name = ibmebus_bus_device.ofdev.dev.bus_id,
+	.ofdev.dev.bus_id = "ibmebus",
+	.ofdev.dev.bus    = &ibmebus_bus_type,
+};
+
+static void *ibmebus_alloc_coherent(struct device *dev,
+				    size_t size,
+				    dma_addr_t *dma_handle,
+				    gfp_t flag)
+{
+	void *mem;
+	
+	mem = kmalloc(size, flag);
+	*dma_handle = (dma_addr_t)mem;
+
+	return mem;
+}
+
+static void ibmebus_free_coherent(struct device *dev,
+				  size_t size, void *vaddr, 
+				  dma_addr_t dma_handle)
+{
+	kfree(vaddr);
+}
+
+static dma_addr_t ibmebus_map_single(struct device *dev,
+				     void *ptr,
+				     size_t size,
+				     enum dma_data_direction direction)
+{
+	return (dma_addr_t)(ptr);
+}
+
+static void ibmebus_unmap_single(struct device *dev,
+				 dma_addr_t dma_addr,
+				 size_t size, 
+				 enum dma_data_direction direction)
+{
+	return;
+}
+
+static int ibmebus_map_sg(struct device *dev,
+			  struct scatterlist *sg,
+			  int nents, enum dma_data_direction direction)
+{
+	int i;
+	
+	for (i = 0; i < nents; i++) {
+		sg[i].dma_address = (dma_addr_t)page_address(sg[i].page) 
+			+ sg[i].offset;
+		sg[i].dma_length = sg[i].length;
+	}
+	
+	return nents;
+}
+
+static void ibmebus_unmap_sg(struct device *dev,
+			     struct scatterlist *sg,
+			     int nents, enum dma_data_direction direction)
+{
+	return;
+}
+
+static int ibmebus_dma_supported(struct device *dev, u64 mask)
+{
+	return 1;
+}
+
+struct dma_mapping_ops ibmebus_dma_ops = {
+	.alloc_coherent = ibmebus_alloc_coherent,
+	.free_coherent  = ibmebus_free_coherent,
+	.map_single     = ibmebus_map_single,
+	.unmap_single   = ibmebus_unmap_single,
+	.map_sg         = ibmebus_map_sg,
+	.unmap_sg       = ibmebus_unmap_sg,
+	.dma_supported  = ibmebus_dma_supported,
+};
+
+static int ibmebus_bus_probe(struct device *dev)
+{
+	struct ibmebus_dev *ibmebusdev    = to_ibmebus_dev(dev);
+	struct ibmebus_driver *ibmebusdrv = to_ibmebus_driver(dev->driver);
+	const struct of_device_id *id;
+	int error = -ENODEV;
+	
+	if (!ibmebusdrv->probe)
+		return error;
+	
+	id = of_match_device(ibmebusdrv->id_table, &ibmebusdev->ofdev);
+	if (id) {
+		error = ibmebusdrv->probe(ibmebusdev, id);
+	}
+	
+	return error;
+}
+
+static int ibmebus_bus_remove(struct device *dev)
+{
+	struct ibmebus_dev *ibmebusdev    = to_ibmebus_dev(dev);
+	struct ibmebus_driver *ibmebusdrv = to_ibmebus_driver(dev->driver);
+	
+	if (ibmebusdrv->remove) {
+		return ibmebusdrv->remove(ibmebusdev);
+	}
+	
+	return 0;
+}
+
+static void __devinit ibmebus_dev_release(struct device *dev)
+{
+	of_node_put(to_ibmebus_dev(dev)->ofdev.node);
+	kfree(to_ibmebus_dev(dev));
+}
+
+static ssize_t ibmebusdev_show_name(struct device *dev, 
+				    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%s\n", to_ibmebus_dev(dev)->name);
+}
+static DEVICE_ATTR(name, S_IRUSR | S_IRGRP | S_IROTH, ibmebusdev_show_name, 
+		   NULL);
+
+static struct ibmebus_dev* __devinit ibmebus_register_device_common(
+	struct ibmebus_dev *dev, char *name)
+{
+	int err = 0;
+
+	dev->name = name;
+	dev->ofdev.dev.parent  = &ibmebus_bus_device.ofdev.dev;
+	dev->ofdev.dev.bus     = &ibmebus_bus_type;
+	dev->ofdev.dev.release = ibmebus_dev_release;
+
+	/* An ibmebusdev is based on a of_device. We have to change the
+	 * bus type to use our own DMA mapping operations. 
+	 */       
+	if ((err = of_device_register(&dev->ofdev)) != 0) {
+		printk(KERN_ERR "%s: failed to register device (%d).\n",
+		       __FUNCTION__, err);
+		return NULL;
+	}
+	
+	device_create_file(&dev->ofdev.dev, &dev_attr_name);
+	
+	return dev;
+}
+
+static struct ibmebus_dev* __devinit ibmebus_register_device_node(
+	struct device_node *dn)
+{
+	struct ibmebus_dev *dev;
+	char *loc_code;
+	int length;
+
+	loc_code = (char *)get_property(dn, "ibm,loc-code", NULL);
+	if (!loc_code) {
+                printk(KERN_WARNING "%s: node %s missing 'ibm,loc-code'\n",
+		       __FUNCTION__, dn->name ? dn->name : "<unknown>");
+		return NULL;
+        }
+	
+	if (strlen(loc_code) == 0) {
+	        printk(KERN_WARNING "%s: 'ibm,loc-code' is invalid\n",
+		       __FUNCTION__);
+		return NULL;
+	}
+
+	dev = kmalloc(sizeof(struct ibmebus_dev), GFP_KERNEL);
+	if (!dev) {
+		return NULL;
+	}
+	memset(dev, 0, sizeof(struct ibmebus_dev));
+
+	dev->ofdev.node = of_node_get(dn);
+       
+	length = strlen(loc_code);
+	memcpy(dev->ofdev.dev.bus_id, loc_code 
+		+ (length - min(length, BUS_ID_SIZE - 1)), 
+		min(length, BUS_ID_SIZE - 1));
+
+	/* Register with generic device framework. */
+	if (ibmebus_register_device_common(dev, dn->name) == NULL) {
+		kfree(dev);
+		return NULL;
+	}
+
+	return dev;
+}
+
+static void ibmebus_probe_of_nodes(char* name)
+{
+	struct device_node *dn = NULL;
+	
+	while ((dn = of_find_node_by_name(dn, name))) {
+		if (ibmebus_register_device_node(dn) == NULL) {
+			of_node_put(dn);
+			
+			return;
+		}
+	}
+	
+	of_node_put(dn);
+	
+	return;
+}
+
+static void ibmebus_add_devices_by_id(struct of_device_id *idt)
+{
+	while (strlen(idt->name) > 0) {
+		ibmebus_probe_of_nodes(idt->name);
+		idt++;
+	}
+
+	return;
+}
+
+static int ibmebus_match_helper(struct device *dev, void *data)
+{
+	if (strcmp((char*)data, to_ibmebus_dev(dev)->name) == 0)
+		return 1;
+	
+	return 0;
+}
+
+static int ibmebus_unregister_device(struct device *dev)
+{
+	device_remove_file(dev, &dev_attr_name);
+	of_device_unregister(to_of_device(dev));
+
+	return 0;
+}
+
+static void ibmebus_remove_devices_by_id(struct of_device_id *idt)
+{
+	struct device *dev;
+	
+	while (strlen(idt->name) > 0) {
+		while ((dev = bus_find_device(&ibmebus_bus_type, NULL, 
+					      (void*)idt->name,
+					      ibmebus_match_helper))) {
+			ibmebus_unregister_device(dev);
+		}
+		idt++;
+		
+	}
+	
+	return;
+}
+
+int ibmebus_register_driver(struct ibmebus_driver *drv)
+{
+	int err = 0;
+
+	drv->driver.name   = drv->name;
+	drv->driver.bus    = &ibmebus_bus_type;
+	drv->driver.probe  = ibmebus_bus_probe;
+	drv->driver.remove = ibmebus_bus_remove;
+
+	if ((err = driver_register(&drv->driver) != 0))
+		return err;
+
+	ibmebus_add_devices_by_id(drv->id_table);
+	
+	return 0;
+}
+EXPORT_SYMBOL(ibmebus_register_driver);
+
+void ibmebus_unregister_driver(struct ibmebus_driver *drv)
+{	
+	driver_unregister(&drv->driver);
+	ibmebus_remove_devices_by_id(drv->id_table);
+}
+EXPORT_SYMBOL(ibmebus_unregister_driver);
+
+int ibmebus_request_irq(struct ibmebus_dev *dev,
+			u32 ist, 
+			irqreturn_t (*handler)(int, void*, struct pt_regs *),
+			unsigned long irq_flags, const char * devname,
+			void *dev_id)
+{
+	unsigned int irq = virt_irq_create_mapping(ist);
+	
+	if (irq == NO_IRQ)
+		return -EINVAL;
+	
+	irq = irq_offset_up(irq);
+	
+	return request_irq(irq, handler,
+			   irq_flags, devname, dev_id);
+}
+EXPORT_SYMBOL(ibmebus_request_irq);
+
+void ibmebus_free_irq(struct ibmebus_dev *dev, u32 ist, void *dev_id)
+{
+	unsigned int irq = virt_irq_create_mapping(ist);
+	
+	irq = irq_offset_up(irq);
+	free_irq(irq, dev_id);
+	
+	return;
+}
+EXPORT_SYMBOL(ibmebus_free_irq);
+
+static int ibmebus_bus_match(struct device *dev, struct device_driver *drv)
+{	
+	const struct ibmebus_dev *ebus_dev = to_ibmebus_dev(dev);
+	struct ibmebus_driver *ebus_drv    = to_ibmebus_driver(drv);
+	const struct of_device_id *ids     = ebus_drv->id_table;
+	const struct of_device_id *found_id;
+	
+	if (!ids)
+		return 0;
+	
+	found_id = of_match_device(ids, &ebus_dev->ofdev);
+	if (found_id)
+		return 1;
+	
+	return 0;
+}
+
+struct bus_type ibmebus_bus_type = {
+	.name = "ibmebus",
+	.match = ibmebus_bus_match,
+};
+EXPORT_SYMBOL(ibmebus_bus_type);
+
+static int __init ibmebus_bus_init(void)
+{
+	int err;
+	
+	printk(KERN_INFO "IBM eBus Device Driver\n");
+	
+	err = bus_register(&ibmebus_bus_type);
+	if (err) {
+		printk(KERN_ERR ":%s: failed to register IBM eBus.\n",
+		       __FUNCTION__);
+		return err;
+	}
+	
+	err = device_register(&ibmebus_bus_device.ofdev.dev);
+	if (err) {
+		printk(KERN_WARNING "%s: device_register returned %i\n", 
+		       __FUNCTION__, err);
+		bus_unregister(&ibmebus_bus_type);
+
+		return err;
+	}
+	
+	return 0;
+}
+__initcall(ibmebus_bus_init);

arch/powerpc/kernel/irq.c

@@ -31,7 +31,6 @@
  * to reduce code space and undefined function references.
  */
 
-#include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/threads.h>
 #include <linux/kernel_stat.h>
@@ -44,18 +43,12 @@
 #include <linux/config.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/pci.h>
 #include <linux/delay.h>
 #include <linux/irq.h>
-#include <linux/proc_fs.h>
-#include <linux/random.h>
 #include <linux/seq_file.h>
 #include <linux/cpumask.h>
 #include <linux/profile.h>
 #include <linux/bitops.h>
-#ifdef CONFIG_PPC64
-#include <linux/kallsyms.h>
-#endif
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -66,8 +59,7 @@
 #include <asm/prom.h>
 #include <asm/ptrace.h>
 #include <asm/machdep.h>
-#ifdef CONFIG_PPC64
-#include <asm/iseries/it_lp_queue.h>
+#ifdef CONFIG_PPC_ISERIES
 #include <asm/paca.h>
 #endif
 
@@ -78,10 +70,6 @@ EXPORT_SYMBOL(__irq_offset_value);
 
 static int ppc_spurious_interrupts;
 
-#if defined(CONFIG_PPC_ISERIES) && defined(CONFIG_SMP)
-extern void iSeries_smp_message_recv(struct pt_regs *);
-#endif
-
 #ifdef CONFIG_PPC32
 #define NR_MASK_WORDS	((NR_IRQS + 31) / 32)
 
@@ -195,49 +183,6 @@ void fixup_irqs(cpumask_t map)
 }
 #endif
 
-#ifdef CONFIG_PPC_ISERIES
-void do_IRQ(struct pt_regs *regs)
-{
-	struct paca_struct *lpaca;
-
-	irq_enter();
-
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
-	/* Debugging check for stack overflow: is there less than 2KB free? */
-	{
-		long sp;
-
-		sp = __get_SP() & (THREAD_SIZE-1);
-
-		if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
-			printk("do_IRQ: stack overflow: %ld\n",
-				sp - sizeof(struct thread_info));
-			dump_stack();
-		}
-	}
-#endif
-
-	lpaca = get_paca();
-#ifdef CONFIG_SMP
-	if (lpaca->lppaca.int_dword.fields.ipi_cnt) {
-		lpaca->lppaca.int_dword.fields.ipi_cnt = 0;
-		iSeries_smp_message_recv(regs);
-	}
-#endif /* CONFIG_SMP */
-	if (hvlpevent_is_pending())
-		process_hvlpevents(regs);
-
-	irq_exit();
-
-	if (lpaca->lppaca.int_dword.fields.decr_int) {
-		lpaca->lppaca.int_dword.fields.decr_int = 0;
-		/* Signal a fake decrementer interrupt */
-		timer_interrupt(regs);
-	}
-}
-
-#else	/* CONFIG_PPC_ISERIES */
-
 void do_IRQ(struct pt_regs *regs)
 {
 	int irq;
@@ -286,16 +231,24 @@ void do_IRQ(struct pt_regs *regs)
 		} else
 #endif
 			__do_IRQ(irq, regs);
-	} else
-#ifdef CONFIG_PPC32
-		if (irq != -2)
-#endif
-			/* That's not SMP safe ... but who cares ? */
-			ppc_spurious_interrupts++;
+	} else if (irq != -2)
+		/* That's not SMP safe ... but who cares ? */
+		ppc_spurious_interrupts++;
+
         irq_exit();
-}
 
-#endif	/* CONFIG_PPC_ISERIES */
+#ifdef CONFIG_PPC_ISERIES
+	{
+		struct paca_struct *lpaca = get_paca();
+
+		if (lpaca->lppaca.int_dword.fields.decr_int) {
+			lpaca->lppaca.int_dword.fields.decr_int = 0;
+			/* Signal a fake decrementer interrupt */
+			timer_interrupt(regs);
+		}
+	}
+#endif
+}
 
 void __init init_IRQ(void)
 {

arch/powerpc/kernel/lparmap.c

@@ -7,7 +7,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 #include <asm/mmu.h>
-#include <asm/page.h>
+#include <asm/pgtable.h>
 #include <asm/iseries/lpar_map.h>
 
 const struct LparMap __attribute__((__section__(".text"))) xLparMap = {
@@ -16,16 +16,16 @@ const struct LparMap __attribute__((__section__(".text"))) xLparMap = {
 	.xSegmentTableOffs = STAB0_PAGE,
 
 	.xEsids = {
-		{ .xKernelEsid = GET_ESID(KERNELBASE),
-		  .xKernelVsid = KERNEL_VSID(KERNELBASE), },
-		{ .xKernelEsid = GET_ESID(VMALLOCBASE),
-		  .xKernelVsid = KERNEL_VSID(VMALLOCBASE), },
+		{ .xKernelEsid = GET_ESID(PAGE_OFFSET),
+		  .xKernelVsid = KERNEL_VSID(PAGE_OFFSET), },
+		{ .xKernelEsid = GET_ESID(VMALLOC_START),
+		  .xKernelVsid = KERNEL_VSID(VMALLOC_START), },
 	},
 
 	.xRanges = {
 		{ .xPages = HvPagesToMap,
 		  .xOffset = 0,
-		  .xVPN = KERNEL_VSID(KERNELBASE) << (SID_SHIFT - HW_PAGE_SHIFT),
+		  .xVPN = KERNEL_VSID(PAGE_OFFSET) << (SID_SHIFT - HW_PAGE_SHIFT),
 		},
 	},
 };

arch/powerpc/kernel/machine_kexec.c

+/*
+ * Code to handle transition of Linux booting another kernel.
+ *
+ * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
+ * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
+ * Copyright (C) 2005 IBM Corporation.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#include <linux/kexec.h>
+#include <linux/reboot.h>
+#include <linux/threads.h>
+#include <asm/machdep.h>
+
+/*
+ * Provide a dummy crash_notes definition until crash dump is implemented.
+ * This prevents breakage of crash_notes attribute in kernel/ksysfs.c.
+ */
+note_buf_t crash_notes[NR_CPUS];
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+	if (ppc_md.machine_crash_shutdown)
+		ppc_md.machine_crash_shutdown(regs);
+}
+
+/*
+ * Do what every setup is needed on image and the
+ * reboot code buffer to allow us to avoid allocations
+ * later.
+ */
+int machine_kexec_prepare(struct kimage *image)
+{
+	if (ppc_md.machine_kexec_prepare)
+		return ppc_md.machine_kexec_prepare(image);
+	/*
+	 * Fail if platform doesn't provide its own machine_kexec_prepare
+	 * implementation.
+	 */
+	return -ENOSYS;
+}
+
+void machine_kexec_cleanup(struct kimage *image)
+{
+	if (ppc_md.machine_kexec_cleanup)
+		ppc_md.machine_kexec_cleanup(image);
+}
+
+/*
+ * Do not allocate memory (or fail in any way) in machine_kexec().
+ * We are past the point of no return, committed to rebooting now.
+ */
+NORET_TYPE void machine_kexec(struct kimage *image)
+{
+	if (ppc_md.machine_kexec)
+		ppc_md.machine_kexec(image);
+	else {
+		/*
+		 * Fall back to normal restart if platform doesn't provide
+		 * its own kexec function, and user insist to kexec...
+		 */
+		machine_restart(NULL);
+	}
+	for(;;);
+}

arch/powerpc/kernel/machine_kexec_32.c

+/*
+ * PPC32 code to handle Linux booting another kernel.
+ *
+ * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
+ * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
+ * Copyright (C) 2005 IBM Corporation.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#include <linux/kexec.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <asm/cacheflush.h>
+#include <asm/hw_irq.h>
+#include <asm/io.h>
+
+typedef NORET_TYPE void (*relocate_new_kernel_t)(
+				unsigned long indirection_page,
+				unsigned long reboot_code_buffer,
+				unsigned long start_address) ATTRIB_NORET;
+
+/*
+ * This is a generic machine_kexec function suitable at least for
+ * non-OpenFirmware embedded platforms.
+ * It merely copies the image relocation code to the control page and
+ * jumps to it.
+ * A platform specific function may just call this one.
+ */
+void default_machine_kexec(struct kimage *image)
+{
+	const extern unsigned char relocate_new_kernel[];
+	const extern unsigned int relocate_new_kernel_size;
+	unsigned long page_list;
+	unsigned long reboot_code_buffer, reboot_code_buffer_phys;
+	relocate_new_kernel_t rnk;
+
+	/* Interrupts aren't acceptable while we reboot */
+	local_irq_disable();
+
+	page_list = image->head;
+
+	/* we need both effective and real address here */
+	reboot_code_buffer =
+			(unsigned long)page_address(image->control_code_page);
+	reboot_code_buffer_phys = virt_to_phys((void *)reboot_code_buffer);
+
+	/* copy our kernel relocation code to the control code page */
+	memcpy((void *)reboot_code_buffer, relocate_new_kernel,
+						relocate_new_kernel_size);
+
+	flush_icache_range(reboot_code_buffer,
+				reboot_code_buffer + KEXEC_CONTROL_CODE_SIZE);
+	printk(KERN_INFO "Bye!\n");
+
+	/* now call it */
+	rnk = (relocate_new_kernel_t) reboot_code_buffer;
+	(*rnk)(page_list, reboot_code_buffer_phys, image->start);
+}
+
+int default_machine_kexec_prepare(struct kimage *image)
+{
+	return 0;
+}

arch/powerpc/kernel/machine_kexec_64.c

 /*
- * machine_kexec.c - handle transition of Linux booting another kernel
+ * PPC64 code to handle Linux booting another kernel.
  *
  * Copyright (C) 2004-2005, IBM Corp.
  *
@@ -28,21 +28,7 @@
 
 #define HASH_GROUP_SIZE 0x80	/* size of each hash group, asm/mmu.h */
 
-/* Have this around till we move it into crash specific file */
-note_buf_t crash_notes[NR_CPUS];
-
-/* Dummy for now. Not sure if we need to have a crash shutdown in here
- * and if what it will achieve. Letting it be now to compile the code
- * in generic kexec environment
- */
-void machine_crash_shutdown(struct pt_regs *regs)
-{
-	/* do nothing right now */
-	/* smp_relase_cpus() if we want smp on panic kernel */
-	/* cpu_irq_down to isolate us until we are ready */
-}
-
-int machine_kexec_prepare(struct kimage *image)
+int default_machine_kexec_prepare(struct kimage *image)
 {
 	int i;
 	unsigned long begin, end;	/* limits of segment */
@@ -111,11 +97,6 @@ int machine_kexec_prepare(struct kimage *image)
 	return 0;
 }
 
-void machine_kexec_cleanup(struct kimage *image)
-{
-	/* we do nothing in prepare that needs to be undone */
-}
-
 #define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE)
 
 static void copy_segments(unsigned long ind)
@@ -172,9 +153,8 @@ void kexec_copy_flush(struct kimage *image)
 	 * including ones that were in place on the original copy
 	 */
 	for (i = 0; i < nr_segments; i++)
-		flush_icache_range(ranges[i].mem + KERNELBASE,
-				ranges[i].mem + KERNELBASE +
-				ranges[i].memsz);
+		flush_icache_range((unsigned long)__va(ranges[i].mem),
+			(unsigned long)__va(ranges[i].mem + ranges[i].memsz));
 }
 
 #ifdef CONFIG_SMP
@@ -283,13 +263,20 @@ extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long start,
 					void (*clear_all)(void)) ATTRIB_NORET;
 
 /* too late to fail here */
-void machine_kexec(struct kimage *image)
+void default_machine_kexec(struct kimage *image)
 {
-
 	/* prepare control code if any */
 
-	/* shutdown other cpus into our wait loop and quiesce interrupts */
-	kexec_prepare_cpus();
+	/*
+        * If the kexec boot is the normal one, need to shutdown other cpus
+        * into our wait loop and quiesce interrupts.
+        * Otherwise, in the case of crashed mode (crashing_cpu >= 0),
+        * stopping other CPUs and collecting their pt_regs is done before
+        * using debugger IPI.
+        */
+
+       if (crashing_cpu == -1)
+               kexec_prepare_cpus();
 
 	/* switch to a staticly allocated stack.  Based on irq stack code.
 	 * XXX: the task struct will likely be invalid once we do the copy!

arch/powerpc/kernel/paca.c

@@ -17,6 +17,7 @@
 #include <asm/page.h>
 #include <asm/lppaca.h>
 #include <asm/iseries/it_lp_queue.h>
+#include <asm/iseries/it_lp_reg_save.h>
 #include <asm/paca.h>
 
 
@@ -26,8 +27,7 @@ extern unsigned long __toc_start;
 
 /* The Paca is an array with one entry per processor.  Each contains an
  * lppaca, which contains the information shared between the
- * hypervisor and Linux.  Each also contains an ItLpRegSave area which
- * is used by the hypervisor to save registers.
+ * hypervisor and Linux.
  * On systems with hardware multi-threading, there are two threads
  * per processor.  The Paca array must contain an entry for each thread.
  * The VPD Areas will give a max logical processors = 2 * max physical
@@ -37,7 +37,6 @@ extern unsigned long __toc_start;
 #define PACA_INIT_COMMON(number, start, asrr, asrv)			    \
 	.lock_token = 0x8000,						    \
 	.paca_index = (number),		/* Paca Index */		    \
-	.default_decr = 0x00ff0000,	/* Initial Decr */		    \
 	.kernel_toc = (unsigned long)(&__toc_start) + 0x8000UL,		    \
 	.stab_real = (asrr), 		/* Real pointer to segment table */ \
 	.stab_addr = (asrv),		/* Virt pointer to segment table */ \
@@ -57,11 +56,7 @@ extern unsigned long __toc_start;
 #ifdef CONFIG_PPC_ISERIES
 #define PACA_INIT_ISERIES(number)					    \
 	.lppaca_ptr = &paca[number].lppaca,				    \
-	.reg_save_ptr = &paca[number].reg_save,				    \
-	.reg_save = {							    \
-		.xDesc = 0xd397d9e2,	/* "LpRS" */			    \
-		.xSize = sizeof(struct ItLpRegSave)			    \
-	}
+	.reg_save_ptr = &iseries_reg_save[number],
 
 #define PACA_INIT(number)						    \
 {									    \

arch/powerpc/kernel/pmc.c

@@ -43,8 +43,13 @@ static void dummy_perf(struct pt_regs *regs)
 	mtspr(SPRN_MMCR0, mmcr0);
 }
 #else
+/* Ensure exceptions are disabled */
 static void dummy_perf(struct pt_regs *regs)
 {
+	unsigned int mmcr0 = mfspr(SPRN_MMCR0);
+
+	mmcr0 &= ~(MMCR0_PMXE);
+	mtspr(SPRN_MMCR0, mmcr0);
 }
 #endif
 

arch/powerpc/kernel/ppc_ksyms.c

@@ -76,11 +76,6 @@ EXPORT_SYMBOL(single_step_exception);
 EXPORT_SYMBOL(sys_sigreturn);
 #endif
 
-#if defined(CONFIG_PPC_PREP)
-EXPORT_SYMBOL(_prep_type);
-EXPORT_SYMBOL(ucSystemType);
-#endif
-
 EXPORT_SYMBOL(strcpy);
 EXPORT_SYMBOL(strncpy);
 EXPORT_SYMBOL(strcat);

arch/powerpc/kernel/time.c

@@ -699,10 +699,6 @@ void __init time_init(void)
 	div128_by_32(1024*1024, 0, tb_ticks_per_sec, &res);
 	tb_to_xs = res.result_low;
 
-#ifdef CONFIG_PPC64
-	get_paca()->default_decr = tb_ticks_per_jiffy;
-#endif
-
 	/*
 	 * Compute scale factor for sched_clock.
 	 * The calibrate_decr() function has set tb_ticks_per_sec,

arch/powerpc/mm/imalloc.c

@@ -107,6 +107,7 @@ static int im_region_status(unsigned long v_addr, unsigned long size,
 		if (v_addr < (unsigned long) tmp->addr + tmp->size)
 			break;
 
+	*vm = NULL;
 	if (tmp) {
 		if (im_region_overlaps(v_addr, size, tmp))
 			return IM_REGION_OVERLAP;
@@ -127,7 +128,6 @@ static int im_region_status(unsigned long v_addr, unsigned long size,
 		}
 	}
 
-	*vm = NULL;
 	return IM_REGION_UNUSED;
 }
 

arch/powerpc/oprofile/Makefile

@@ -9,3 +9,4 @@ DRIVER_OBJS := $(addprefix ../../../drivers/oprofile/, \
 oprofile-y := $(DRIVER_OBJS) common.o
 oprofile-$(CONFIG_PPC64) += op_model_rs64.o op_model_power4.o
 oprofile-$(CONFIG_FSL_BOOKE) += op_model_fsl_booke.o
+oprofile-$(CONFIG_PPC32) += op_model_7450.o