13 files changed, 150 insertions, 88 deletions

diff --git a/arch/ppc64/kernel/LparData.c b/arch/ppc64/kernel/LparData.c
index 6ffcf67dd507..76cfd1449d52 100644
--- a/arch/ppc64/kernel/LparData.c
+++ b/arch/ppc64/kernel/LparData.c
@@ -33,17 +33,36 @@
  * 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 = 0x4800,     /* offset of LparMap within loadarea (see head.S) */
-        .xTagsMode = 1,                 /* tags inactive       */
-        .xAddressSize = 0,              /* 64 bit              */
-        .xNoSharedProcs = 0,            /* shared processors   */
-        .xNoHMT = 0,                    /* HMT allowed         */
-        .xRsvd2 = 6,                    /* TEMP: This allows non-GA driver */
+        .xMsNucDataOffset = (u32)((unsigned long)&xLparMap - KERNELBASE),
+        .xFlags = HVREL_TAGSINACTIVE    /* tags inactive       */
+                                        /* 64 bit              */
+                                        /* shared processors   */
+                                        /* HMT allowed         */
+                  | 6,                  /* TEMP: This allows non-GA driver */
         .xVrmIndex = 4,                 /* We are v5r2m0               */
         .xMinSupportedPlicVrmIndex = 3,         /* v5r1m0 */
         .xMinCompatablePlicVrmIndex = 3,        /* v5r1m0 */
@@ -51,6 +70,63 @@ 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/head.S b/arch/ppc64/kernel/head.S
index 93ebcac0d5a2..784f56d4684c 100644
--- a/arch/ppc64/kernel/head.S
+++ b/arch/ppc64/kernel/head.S
@@ -522,36 +522,9 @@ __end_interrupts:
 #ifdef CONFIG_PPC_ISERIES
         .globl naca
 naca:
-        .llong itVpdAreas
-
-        /*
-         * The iSeries LPAR map is at this fixed address
-         * so that the HvReleaseData structure can address
-         * it with a 32-bit offset.
-         *
-         * The VSID values below are dependent on the
-         * VSID generation algorithm.  See include/asm/mmu_context.h.
-         */
-
-        . = 0x4800
-
-        .llong  2               /* # ESIDs to be mapped by hypervisor    */
-        .llong  1               /* # memory ranges to be mapped by hypervisor */
-        .llong  STAB0_PAGE      /* Page # of segment table within load area     */
-        .llong  0               /* Reserved */
-        .llong  0               /* Reserved */
-        .llong  0               /* Reserved */
-        .llong  0               /* Reserved */
-        .llong  0               /* Reserved */
-        .llong  (KERNELBASE>>SID_SHIFT)
-        .llong  0x408f92c94     /* KERNELBASE VSID */
-        /* We have to list the bolted VMALLOC segment here, too, so that it
-         * will be restored on shared processor switch */
-        .llong  (VMALLOCBASE>>SID_SHIFT)
-        .llong  0xf09b89af5     /* VMALLOCBASE VSID */
-        .llong  8192            /* # pages to map (32 MB) */
-        .llong  0               /* Offset from start of loadarea to start of map */
-        .llong  0x408f92c940000 /* VPN of first page to map */
+        .llong  itVpdAreas
+        .llong  0               /* xRamDisk */
+        .llong  0               /* xRamDiskSize */
 
         . = 0x6100
 
@@ -2098,7 +2071,7 @@ _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
@@ -2131,13 +2104,6 @@ empty_zero_page:
 swapper_pg_dir:
         .space  4096
 
-#ifdef CONFIG_SMP
-/* 1 page segment table per cpu (max 48, cpu0 allocated at STAB0_PHYS_ADDR) */
-        .globl  stab_array
-stab_array:
-        .space  4096 * 48
-#endif
-        
 /*
  * This space gets a copy of optional info passed to us by the bootstrap
  * Used to pass parameters into the kernel like root=/dev/sda1, etc.
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/pmac_setup.c b/arch/ppc64/kernel/pmac_setup.c
index 3013cdb5f933..e40877fa67cd 100644
--- a/arch/ppc64/kernel/pmac_setup.c
+++ b/arch/ppc64/kernel/pmac_setup.c
@@ -97,7 +97,7 @@ EXPORT_SYMBOL(smu_cmdbuf_abs);
 
 extern void udbg_init_scc(struct device_node *np);
 
-void __pmac pmac_show_cpuinfo(struct seq_file *m)
+static void __pmac pmac_show_cpuinfo(struct seq_file *m)
 {
         struct device_node *np;
         char *pp;
@@ -144,7 +144,7 @@ void __pmac pmac_show_cpuinfo(struct seq_file *m)
 }
 
 
-void __init pmac_setup_arch(void)
+static void __init pmac_setup_arch(void)
 {
         /* init to some ~sane value until calibrate_delay() runs */
         loops_per_jiffy = 50000000;
@@ -230,7 +230,7 @@ void __pmac note_bootable_part(dev_t dev, int part, int goodness)
         }
 }
 
-void __pmac pmac_restart(char *cmd)
+static void __pmac pmac_restart(char *cmd)
 {
         switch(sys_ctrler) {
 #ifdef CONFIG_ADB_PMU
@@ -249,7 +249,7 @@ void __pmac pmac_restart(char *cmd)
         }
 }
 
-void __pmac pmac_power_off(void)
+static void __pmac pmac_power_off(void)
 {
         switch(sys_ctrler) {
 #ifdef CONFIG_ADB_PMU
@@ -267,7 +267,7 @@ void __pmac pmac_power_off(void)
         }
 }
 
-void __pmac pmac_halt(void)
+static void __pmac pmac_halt(void)
 {
         pmac_power_off();
 }
@@ -327,7 +327,7 @@ static void __init init_boot_display(void)
 /* 
  * Early initialization.
  */
-void __init pmac_init_early(void)
+static void __init pmac_init_early(void)
 {
         DBG(" -> pmac_init_early\n");
 
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/setup.c b/arch/ppc64/kernel/setup.c
index e80f10c89824..687e85595208 100644
--- a/arch/ppc64/kernel/setup.c
+++ b/arch/ppc64/kernel/setup.c
@@ -1068,6 +1068,8 @@ void __init setup_arch(char **cmdline_p)
         irqstack_early_init();
         emergency_stack_init();
 
+        stabs_alloc();
+
         /* set up the bootmem stuff with available memory */
         do_init_bootmem();
         sparse_init();
diff --git a/arch/ppc64/kernel/smp.c b/arch/ppc64/kernel/smp.c
index 2fcddfcb594d..793b562da653 100644
--- a/arch/ppc64/kernel/smp.c
+++ b/arch/ppc64/kernel/smp.c
@@ -65,8 +65,6 @@ struct smp_ops_t *smp_ops;
 
 static volatile unsigned int cpu_callin_map[NR_CPUS];
 
-extern unsigned char stab_array[];
-
 void smp_call_function_interrupt(void);
 
 int smt_enabled_at_boot = 1;
@@ -492,19 +490,6 @@ int __devinit __cpu_up(unsigned int cpu)
 
         paca[cpu].default_decr = tb_ticks_per_jiffy;
 
-        if (!cpu_has_feature(CPU_FTR_SLB)) {
-                void *tmp;
-
-                /* maximum of 48 CPUs on machines with a segment table */
-                if (cpu >= 48)
-                        BUG();
-
-                tmp = &stab_array[PAGE_SIZE * cpu];
-                memset(tmp, 0, PAGE_SIZE); 
-                paca[cpu].stab_addr = (unsigned long)tmp;
-                paca[cpu].stab_real = virt_to_abs(tmp);
-        }
-
         /* Make sure callin-map entry is 0 (can be leftover a CPU
          * hotplug
          */
diff --git a/arch/ppc64/kernel/udbg.c b/arch/ppc64/kernel/udbg.c
index d4ccd6f1ef47..c0da45540f0f 100644
--- a/arch/ppc64/kernel/udbg.c
+++ b/arch/ppc64/kernel/udbg.c
@@ -141,7 +141,7 @@ void udbg_init_scc(struct device_node *np)
 
 #endif /* CONFIG_PPC_PMAC */
 
-#if CONFIG_PPC_PMAC
+#ifdef CONFIG_PPC_PMAC
 static void udbg_real_putc(unsigned char c)
 {
         while ((real_readb(sccc) & SCC_TXRDY) == 0)
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