14 files changed, 106 insertions, 105 deletions

diff --git a/arch/ppc64/kernel/LparData.c b/arch/ppc64/kernel/LparData.c
index 76cfd1449d52..1c11031c838e 100644
--- a/arch/ppc64/kernel/LparData.c
+++ b/arch/ppc64/kernel/LparData.c
@@ -32,32 +32,12 @@
 /* The HvReleaseData is the root of the information shared between 
  * the hypervisor and Linux.  
  */
-
-/*
- * WARNING - magic here
- *
- * Ok, this is a horrid hack below, but marginally better than the
- * alternatives.  What we really want is just to initialize
- * hvReleaseData in C as in the #if 0 section here.  However, gcc
- * refuses to believe that (u32)&x is a constant expression, so will
- * not allow the xMsNucDataOffset field to be properly initialized.
- * So, we declare hvReleaseData in inline asm instead.  We use inline
- * asm, rather than a .S file, because the assembler won't generate
- * the necessary relocation for the LparMap either, unless that symbol
- * is declared in the same source file.  Finally, we put the asm in a
- * dummy, attribute-used function, instead of at file scope, because
- * file scope asms don't allow contraints.  We want to use the "i"
- * constraints to put sizeof() and offsetof() expressions in there,
- * because including asm/offsets.h in C code then stringifying causes
- * all manner of warnings.
- */
-#if 0
 struct HvReleaseData hvReleaseData = {
 	.xDesc = 0xc8a5d9c4,	/* "HvRD" ebcdic */
 	.xSize = sizeof(struct HvReleaseData),
 	.xVpdAreasPtrOffset = offsetof(struct naca_struct, xItVpdAreas),
 	.xSlicNacaAddr = &naca,		/* 64-bit Naca address */
-	.xMsNucDataOffset = (u32)((unsigned long)&xLparMap - KERNELBASE),
+	.xMsNucDataOffset = LPARMAP_PHYS,
 	.xFlags = HVREL_TAGSINACTIVE	/* tags inactive       */
 					/* 64 bit              */
 					/* shared processors   */
@@ -70,63 +50,6 @@ struct HvReleaseData hvReleaseData = {
 		0xa7, 0x40, 0xf2, 0x4b,
 		0xf4, 0x4b, 0xf6, 0xf4 },
 };
-#endif
-
-
-extern struct HvReleaseData hvReleaseData;
-
-static void __attribute_used__ hvReleaseData_wrapper(void)
-{
-	/* This doesn't appear to need any alignment (even 4 byte) */
-	asm volatile (
-		"	lparMapPhys = xLparMap - %3\n"
-		"	.data\n"
-		"	.globl	hvReleaseData\n"
-		"hvReleaseData:\n"
-		"	.long	0xc8a5d9c4\n"	/* xDesc */
-						/* "HvRD" in ebcdic */
-		"	.short	%0\n"		/* xSize */
-		"	.short	%1\n"		/* xVpdAreasPtrOffset */
-		"	.llong	naca\n"		/* xSlicNacaAddr */
-		"	.long	lparMapPhys\n"	/* xMsNucDataOffset */
-		"	.long	0\n"		/* xRsvd1 */
-		"	.short	%2\n"		/* xFlags */
-		"	.short	4\n"	/* xVrmIndex  - v5r2m0 */
-		"	.short	3\n"	/* xMinSupportedPlicVrmIndex - v5r1m0 */
-		"	.short	3\n"	/* xMinCompatablePlicVrmIndex - v5r1m0 */
-		"	.long	0xd38995a4\n"	/* xVrmName */
-		"	.long	0xa740f24b\n"	/*   "Linux 2.4.64" ebcdic */
-		"	.long	0xf44bf6f4\n"
-		"	. = hvReleaseData + %0\n"
-		"	.previous\n"
-		: : "i"(sizeof(hvReleaseData)),
-		"i"(offsetof(struct naca_struct, xItVpdAreas)),
-		"i"(HVREL_TAGSINACTIVE /* tags inactive, 64 bit, */
-				       /* shared processors, HMT allowed */
-		    | 6), /* TEMP: This allows non-GA drivers */
-		"i"(KERNELBASE)
-		);
-}
-
-struct LparMap __attribute__((aligned (16))) xLparMap = {
-	.xNumberEsids = HvEsidsToMap,
-	.xNumberRanges = HvRangesToMap,
-	.xSegmentTableOffs = STAB0_PAGE,
-
-	.xEsids = {
-		{ .xKernelEsid = GET_ESID(KERNELBASE),
-		  .xKernelVsid = KERNEL_VSID(KERNELBASE), },
-		{ .xKernelEsid = GET_ESID(VMALLOCBASE),
-		  .xKernelVsid = KERNEL_VSID(VMALLOCBASE), },
-	},
-
-	.xRanges = {
-		{ .xPages = HvPagesToMap,
-		  .xOffset = 0,
-		  .xVPN = KERNEL_VSID(KERNELBASE) << (SID_SHIFT - PAGE_SHIFT),
-		},
-	},
-};
 
 extern void system_reset_iSeries(void);
 extern void machine_check_iSeries(void);
diff --git a/arch/ppc64/kernel/Makefile b/arch/ppc64/kernel/Makefile
index d9b2660ef221..2ecccb6b4f8c 100644
--- a/arch/ppc64/kernel/Makefile
+++ b/arch/ppc64/kernel/Makefile
@@ -73,3 +73,8 @@ obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 
 CFLAGS_ioctl32.o += -Ifs/
+
+ifeq ($(CONFIG_PPC_ISERIES),y)
+arch/ppc64/kernel/head.o: arch/ppc64/kernel/lparmap.s
+AFLAGS_head.o += -Iarch/ppc64/kernel
+endif
diff --git a/arch/ppc64/kernel/head.S b/arch/ppc64/kernel/head.S
index 74fc3bc68604..accaa052d31f 100644
--- a/arch/ppc64/kernel/head.S
+++ b/arch/ppc64/kernel/head.S
@@ -38,6 +38,7 @@
 #include <asm/cputable.h>
 #include <asm/setup.h>
 #include <asm/hvcall.h>
+#include <asm/iSeries/LparMap.h>
 
 #ifdef CONFIG_PPC_ISERIES
 #define DO_SOFT_DISABLE
@@ -679,6 +680,11 @@ hardware_interrupt_iSeries_masked:
 	.globl fwnmi_data_area
 fwnmi_data_area:
 
+#ifdef CONFIG_PPC_ISERIES
+	. = LPARMAP_PHYS
+#include "lparmap.s"
+#endif /* CONFIG_PPC_ISERIES */
+
 /*
  * Vectors for the FWNMI option.  Share common code.
  */
@@ -2071,7 +2077,7 @@ _GLOBAL(hmt_start_secondary)
 	blr
 #endif
 
-#if defined(CONFIG_SMP) && !defined(CONFIG_PPC_ISERIES)
+#if defined(CONFIG_KEXEC) || (defined(CONFIG_SMP) && !defined(CONFIG_PPC_ISERIES))
 _GLOBAL(smp_release_cpus)
 	/* All secondary cpus are spinning on a common
 	 * spinloop, release them all now so they can start
diff --git a/arch/ppc64/kernel/iommu.c b/arch/ppc64/kernel/iommu.c
index 8316426ccaf6..845eebd1e28d 100644
--- a/arch/ppc64/kernel/iommu.c
+++ b/arch/ppc64/kernel/iommu.c
@@ -242,7 +242,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 	dma_addr_t dma_next = 0, dma_addr;
 	unsigned long flags;
 	struct scatterlist *s, *outs, *segstart;
-	int outcount;
+	int outcount, incount;
 	unsigned long handle;
 
 	BUG_ON(direction == DMA_NONE);
@@ -252,6 +252,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 
 	outs = s = segstart = &sglist[0];
 	outcount = 1;
+	incount = nelems;
 	handle = 0;
 
 	/* Init first segment length for backout at failure */
@@ -338,10 +339,10 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 
 	DBG("mapped %d elements:\n", outcount);
 
-	/* For the sake of iommu_free_sg, we clear out the length in the
+	/* For the sake of iommu_unmap_sg, we clear out the length in the
 	 * next entry of the sglist if we didn't fill the list completely
 	 */
-	if (outcount < nelems) {
+	if (outcount < incount) {
 		outs++;
 		outs->dma_address = DMA_ERROR_CODE;
 		outs->dma_length = 0;
diff --git a/arch/ppc64/kernel/lparmap.c b/arch/ppc64/kernel/lparmap.c
new file mode 100644
index 000000000000..b81de286df5e
--- /dev/null
+++ b/arch/ppc64/kernel/lparmap.c
@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) 2005  Stephen Rothwell  IBM Corp.
+ *
+ * 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 <asm/mmu.h>
+#include <asm/page.h>
+#include <asm/iSeries/LparMap.h>
+
+const struct LparMap __attribute__((__section__(".text"))) xLparMap = {
+	.xNumberEsids = HvEsidsToMap,
+	.xNumberRanges = HvRangesToMap,
+	.xSegmentTableOffs = STAB0_PAGE,
+
+	.xEsids = {
+		{ .xKernelEsid = GET_ESID(KERNELBASE),
+		  .xKernelVsid = KERNEL_VSID(KERNELBASE), },
+		{ .xKernelEsid = GET_ESID(VMALLOCBASE),
+		  .xKernelVsid = KERNEL_VSID(VMALLOCBASE), },
+	},
+
+	.xRanges = {
+		{ .xPages = HvPagesToMap,
+		  .xOffset = 0,
+		  .xVPN = KERNEL_VSID(KERNELBASE) << (SID_SHIFT - PAGE_SHIFT),
+		},
+	},
+};
diff --git a/arch/ppc64/kernel/machine_kexec.c b/arch/ppc64/kernel/machine_kexec.c
index fdb2fc649d72..4775f12a013c 100644
--- a/arch/ppc64/kernel/machine_kexec.c
+++ b/arch/ppc64/kernel/machine_kexec.c
@@ -185,7 +185,7 @@ void kexec_copy_flush(struct kimage *image)
 void kexec_smp_down(void *arg)
 {
 	if (ppc_md.cpu_irq_down)
-		ppc_md.cpu_irq_down();
+		ppc_md.cpu_irq_down(1);
 
 	local_irq_disable();
 	kexec_smp_wait();
@@ -232,7 +232,7 @@ static void kexec_prepare_cpus(void)
 
 	/* after we tell the others to go down */
 	if (ppc_md.cpu_irq_down)
-		ppc_md.cpu_irq_down();
+		ppc_md.cpu_irq_down(0);
 
 	put_cpu();
 
@@ -243,15 +243,19 @@ static void kexec_prepare_cpus(void)
 
 static void kexec_prepare_cpus(void)
 {
+	extern void smp_release_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 ?
+	 *
+	 * We need to release the cpus if we are ever going from an
+	 * UP to an SMP kernel.
 	 */
-	smp_relase_cpus();
+	smp_release_cpus();
 	if (ppc_md.cpu_irq_down)
-		ppc_md.cpu_irq_down();
+		ppc_md.cpu_irq_down(0);
 	local_irq_disable();
 }
 
diff --git a/arch/ppc64/kernel/misc.S b/arch/ppc64/kernel/misc.S
index 59f4f9973818..a05b50b738e9 100644
--- a/arch/ppc64/kernel/misc.S
+++ b/arch/ppc64/kernel/misc.S
@@ -1129,6 +1129,9 @@ _GLOBAL(sys_call_table32)
 	.llong .compat_sys_waitid
 	.llong .sys32_ioprio_set
 	.llong .sys32_ioprio_get
+	.llong .sys_inotify_init	/* 275 */
+	.llong .sys_inotify_add_watch
+	.llong .sys_inotify_rm_watch
 
 	.balign 8
 _GLOBAL(sys_call_table)
@@ -1407,3 +1410,6 @@ _GLOBAL(sys_call_table)
 	.llong .sys_waitid
 	.llong .sys_ioprio_set
 	.llong .sys_ioprio_get
+	.llong .sys_inotify_init	/* 275 */
+	.llong .sys_inotify_add_watch
+	.llong .sys_inotify_rm_watch
diff --git a/arch/ppc64/kernel/mpic.c b/arch/ppc64/kernel/mpic.c
index e8fbab1df37f..cc262a05ddb4 100644
--- a/arch/ppc64/kernel/mpic.c
+++ b/arch/ppc64/kernel/mpic.c
@@ -794,10 +794,10 @@ void mpic_setup_this_cpu(void)
 
 /*
  * XXX: someone who knows mpic should check this.
- * do we need to eoi the ipi here (see xics comments)?
+ * do we need to eoi the ipi including for kexec cpu here (see xics comments)?
  * or can we reset the mpic in the new kernel?
  */
-void mpic_teardown_this_cpu(void)
+void mpic_teardown_this_cpu(int secondary)
 {
 	struct mpic *mpic = mpic_primary;
 	unsigned long flags;
diff --git a/arch/ppc64/kernel/mpic.h b/arch/ppc64/kernel/mpic.h
index 99fbbc9a084c..ca78a7f10528 100644
--- a/arch/ppc64/kernel/mpic.h
+++ b/arch/ppc64/kernel/mpic.h
@@ -256,7 +256,7 @@ extern unsigned int mpic_irq_get_priority(unsigned int irq);
 extern void mpic_setup_this_cpu(void);
 
 /* Clean up for kexec (or cpu offline or ...) */
-extern void mpic_teardown_this_cpu(void);
+extern void mpic_teardown_this_cpu(int secondary);
 
 /* Request IPIs on primary mpic */
 extern void mpic_request_ipis(void);
diff --git a/arch/ppc64/kernel/pci.c b/arch/ppc64/kernel/pci.c
index ae6f579d3fa0..d0d55c7908ef 100644
--- a/arch/ppc64/kernel/pci.c
+++ b/arch/ppc64/kernel/pci.c
@@ -108,8 +108,28 @@ void  pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region
 	region->end = res->end - offset;
 }
 
+void pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
+			      struct pci_bus_region *region)
+{
+	unsigned long offset = 0;
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+
+	if (!hose)
+		return;
+
+	if (res->flags & IORESOURCE_IO)
+	        offset = (unsigned long)hose->io_base_virt - pci_io_base;
+
+	if (res->flags & IORESOURCE_MEM)
+		offset = hose->pci_mem_offset;
+
+	res->start = region->start + offset;
+	res->end = region->end + offset;
+}
+
 #ifdef CONFIG_HOTPLUG
 EXPORT_SYMBOL(pcibios_resource_to_bus);
+EXPORT_SYMBOL(pcibios_bus_to_resource);
 #endif
 
 /*
diff --git a/arch/ppc64/kernel/prom.c b/arch/ppc64/kernel/prom.c
index 47727a6f7346..5aca01ddd81f 100644
--- a/arch/ppc64/kernel/prom.c
+++ b/arch/ppc64/kernel/prom.c
@@ -916,6 +916,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 		}
 	}
 
+#ifdef CONFIG_ALTIVEC
 	/* Check if we have a VMX and eventually update CPU features */
 	prop = (u32 *)get_flat_dt_prop(node, "ibm,vmx", NULL);
 	if (prop && (*prop) > 0) {
@@ -929,6 +930,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 		cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC;
 		cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC;
 	}
+#endif /* CONFIG_ALTIVEC */
 
 	/*
 	 * Check for an SMT capable CPU and set the CPU feature. We do
diff --git a/arch/ppc64/kernel/prom_init.c b/arch/ppc64/kernel/prom_init.c
index e248a7950aeb..dbbe6c79d8da 100644
--- a/arch/ppc64/kernel/prom_init.c
+++ b/arch/ppc64/kernel/prom_init.c
@@ -1803,7 +1803,7 @@ static void __init fixup_device_tree(void)
 	if (prom_getprop(u3, "device-rev", &u3_rev, sizeof(u3_rev))
 	    == PROM_ERROR)
 		return;
-	if (u3_rev != 0x35)
+	if (u3_rev != 0x35 && u3_rev != 0x37)
 		return;
 	/* does it need fixup ? */
 	if (prom_getproplen(i2c, "interrupts") > 0)
diff --git a/arch/ppc64/kernel/setup.c b/arch/ppc64/kernel/setup.c
index 687e85595208..e9c24d2dbd91 100644
--- a/arch/ppc64/kernel/setup.c
+++ b/arch/ppc64/kernel/setup.c
@@ -706,6 +706,8 @@ void machine_power_off(void)
 	local_irq_disable();
 	while (1) ;
 }
+/* Used by the G5 thermal driver */
+EXPORT_SYMBOL_GPL(machine_power_off);
 
 void machine_halt(void)
 {
diff --git a/arch/ppc64/kernel/xics.c b/arch/ppc64/kernel/xics.c
index 677c4450984a..d9dc6f28d050 100644
--- a/arch/ppc64/kernel/xics.c
+++ b/arch/ppc64/kernel/xics.c
@@ -647,29 +647,30 @@ static void xics_set_affinity(unsigned int virq, cpumask_t cpumask)
 	}
 }
 
-void xics_teardown_cpu(void)
+void xics_teardown_cpu(int secondary)
 {
 	int cpu = smp_processor_id();
-	int status;
 
 	ops->cppr_info(cpu, 0x00);
 	iosync();
 
 	/*
-	 * we need to EOI the IPI if we got here from kexec down IPI
-	 *
-	 * xics doesn't care if we duplicate an EOI as long as we
-	 * don't EOI and raise priority.
-	 *
-	 * probably need to check all the other interrupts too
-	 * should we be flagging idle loop instead?
-	 * or creating some task to be scheduled?
+	 * Some machines need to have at least one cpu in the GIQ,
+	 * so leave the master cpu in the group.
 	 */
-	ops->xirr_info_set(cpu, XICS_IPI);
-
-	status = rtas_set_indicator(GLOBAL_INTERRUPT_QUEUE,
-		(1UL << interrupt_server_size) - 1 - default_distrib_server, 0);
-	WARN_ON(status != 0);
+	if (secondary) {
+		/*
+		 * we need to EOI the IPI if we got here from kexec down IPI
+		 *
+		 * probably need to check all the other interrupts too
+		 * should we be flagging idle loop instead?
+		 * or creating some task to be scheduled?
+		 */
+		ops->xirr_info_set(cpu, XICS_IPI);
+		rtas_set_indicator(GLOBAL_INTERRUPT_QUEUE,
+			(1UL << interrupt_server_size) - 1 -
+			default_distrib_server, 0);
+	}
 }
 
 #ifdef CONFIG_HOTPLUG_CPU