Merge branch 'for_2.6.40/pm-cleanup' of ssh://master.kernel.org/pub/scm/linux/kernel/git/khilman/linux-omap-pm into omap-for-linus

15 files changed, 204 insertions, 173 deletions

diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index d87988bacf3e..34595d5e1038 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -78,6 +78,7 @@
 #define         APIC_DEST_LOGICAL       0x00800
 #define         APIC_DEST_PHYSICAL      0x00000
 #define         APIC_DM_FIXED           0x00000
+#define         APIC_DM_FIXED_MASK      0x00700
 #define         APIC_DM_LOWEST          0x00100
 #define         APIC_DM_SMI             0x00200
 #define         APIC_DM_REMRD           0x00300
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 7db7723d1f32..d56187c6b838 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -299,6 +299,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 /* Install a pte for a particular vaddr in kernel space. */
 void set_pte_vaddr(unsigned long vaddr, pte_t pte);
 
+extern void native_pagetable_reserve(u64 start, u64 end);
 #ifdef CONFIG_X86_32
 extern void native_pagetable_setup_start(pgd_t *base);
 extern void native_pagetable_setup_done(pgd_t *base);
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 3e094af443c3..130f1eeee5fe 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -94,6 +94,8 @@
 /* after this # consecutive successes, bump up the throttle if it was lowered */
 #define COMPLETE_THRESHOLD 5
 
+#define UV_LB_SUBNODEID 0x10
+
 /*
  * number of entries in the destination side payload queue
  */
@@ -124,7 +126,7 @@
  * The distribution specification (32 bytes) is interpreted as a 256-bit
  * distribution vector. Adjacent bits correspond to consecutive even numbered
  * nodeIDs. The result of adding the index of a given bit to the 15-bit
- * 'base_dest_nodeid' field of the header corresponds to the
+ * 'base_dest_nasid' field of the header corresponds to the
  * destination nodeID associated with that specified bit.
  */
 struct bau_target_uvhubmask {
@@ -176,7 +178,7 @@ struct bau_msg_payload {
 struct bau_msg_header {
         unsigned int dest_subnodeid:6;  /* must be 0x10, for the LB */
         /* bits 5:0 */
-        unsigned int base_dest_nodeid:15; /* nasid of the */
+        unsigned int base_dest_nasid:15; /* nasid of the */
         /* bits 20:6 */                   /* first bit in uvhub map */
         unsigned int command:8; /* message type */
         /* bits 28:21 */
@@ -378,6 +380,10 @@ struct ptc_stats {
         unsigned long d_rcanceled; /* number of messages canceled by resets */
 };
 
+struct hub_and_pnode {
+        short uvhub;
+        short pnode;
+};
 /*
  * one per-cpu; to locate the software tables
  */
@@ -399,10 +405,12 @@ struct bau_control {
         int baudisabled;
         int set_bau_off;
         short cpu;
+        short osnode;
         short uvhub_cpu;
         short uvhub;
         short cpus_in_socket;
         short cpus_in_uvhub;
+        short partition_base_pnode;
         unsigned short message_number;
         unsigned short uvhub_quiesce;
         short socket_acknowledge_count[DEST_Q_SIZE];
@@ -422,15 +430,16 @@ struct bau_control {
         int congested_period;
         cycles_t period_time;
         long period_requests;
+        struct hub_and_pnode *target_hub_and_pnode;
 };
 
 static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp)
 {
         return constant_test_bit(uvhub, &dstp->bits[0]);
 }
-static inline void bau_uvhub_set(int uvhub, struct bau_target_uvhubmask *dstp)
+static inline void bau_uvhub_set(int pnode, struct bau_target_uvhubmask *dstp)
 {
-        __set_bit(uvhub, &dstp->bits[0]);
+        __set_bit(pnode, &dstp->bits[0]);
 }
 static inline void bau_uvhubs_clear(struct bau_target_uvhubmask *dstp,
                                     int nbits)
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index a501741c2335..4298002d0c83 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -398,6 +398,8 @@ struct uv_blade_info {
         unsigned short  nr_online_cpus;
         unsigned short  pnode;
         short           memory_nid;
+        spinlock_t      nmi_lock;
+        unsigned long   nmi_count;
 };
 extern struct uv_blade_info *uv_blade_info;
 extern short *uv_node_to_blade;
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index 20cafeac7455..f5bb64a823d7 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -5,7 +5,7 @@
  *
  * SGI UV MMR definitions
  *
- * Copyright (C) 2007-2010 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2011 Silicon Graphics, Inc. All rights reserved.
  */
 
 #ifndef _ASM_X86_UV_UV_MMRS_H
@@ -1099,5 +1099,19 @@ union uvh_rtc1_int_config_u {
     } s;
 };
 
+/* ========================================================================= */
+/*                               UVH_SCRATCH5                                */
+/* ========================================================================= */
+#define UVH_SCRATCH5 0x2d0200UL
+#define UVH_SCRATCH5_32 0x00778
+
+#define UVH_SCRATCH5_SCRATCH5_SHFT 0
+#define UVH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL
+union uvh_scratch5_u {
+    unsigned long       v;
+    struct uvh_scratch5_s {
+        unsigned long   scratch5 : 64;  /* RW, W1CS */
+    } s;
+};
 
 #endif /* __ASM_UV_MMRS_X86_H__ */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 643ebf2e2ad8..d3d859035af9 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -68,6 +68,17 @@ struct x86_init_oem {
 };
 
 /**
+ * struct x86_init_mapping - platform specific initial kernel pagetable setup
+ * @pagetable_reserve:  reserve a range of addresses for kernel pagetable usage
+ *
+ * For more details on the purpose of this hook, look in
+ * init_memory_mapping and the commit that added it.
+ */
+struct x86_init_mapping {
+        void (*pagetable_reserve)(u64 start, u64 end);
+};
+
+/**
  * struct x86_init_paging - platform specific paging functions
  * @pagetable_setup_start:      platform specific pre paging_init() call
  * @pagetable_setup_done:       platform specific post paging_init() call
@@ -123,6 +134,7 @@ struct x86_init_ops {
         struct x86_init_mpparse         mpparse;
         struct x86_init_irqs            irqs;
         struct x86_init_oem             oem;
+        struct x86_init_mapping         mapping;
         struct x86_init_paging          paging;
         struct x86_init_timers          timers;
         struct x86_init_iommu           iommu;
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 33b10a0fc095..7acd2d2ac965 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -37,6 +37,13 @@
 #include <asm/smp.h>
 #include <asm/x86_init.h>
 #include <asm/emergency-restart.h>
+#include <asm/nmi.h>
+
+/* BMC sets a bit this MMR non-zero before sending an NMI */
+#define UVH_NMI_MMR                             UVH_SCRATCH5
+#define UVH_NMI_MMR_CLEAR                       (UVH_NMI_MMR + 8)
+#define UV_NMI_PENDING_MASK                     (1UL << 63)
+DEFINE_PER_CPU(unsigned long, cpu_last_nmi_count);
 
 DEFINE_PER_CPU(int, x2apic_extra_bits);
 
@@ -642,18 +649,46 @@ void __cpuinit uv_cpu_init(void)
  */
 int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 {
+        unsigned long real_uv_nmi;
+        int bid;
+
         if (reason != DIE_NMIUNKNOWN)
                 return NOTIFY_OK;
 
         if (in_crash_kexec)
                 /* do nothing if entering the crash kernel */
                 return NOTIFY_OK;
+
         /*
-         * Use a lock so only one cpu prints at a time
-         * to prevent intermixed output.
+         * Each blade has an MMR that indicates when an NMI has been sent
+         * to cpus on the blade. If an NMI is detected, atomically
+         * clear the MMR and update a per-blade NMI count used to
+         * cause each cpu on the blade to notice a new NMI.
+         */
+        bid = uv_numa_blade_id();
+        real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK);
+
+        if (unlikely(real_uv_nmi)) {
+                spin_lock(&uv_blade_info[bid].nmi_lock);
+                real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK);
+                if (real_uv_nmi) {
+                        uv_blade_info[bid].nmi_count++;
+                        uv_write_local_mmr(UVH_NMI_MMR_CLEAR, UV_NMI_PENDING_MASK);
+                }
+                spin_unlock(&uv_blade_info[bid].nmi_lock);
+        }
+
+        if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count))
+                return NOTIFY_DONE;
+
+        __get_cpu_var(cpu_last_nmi_count) = uv_blade_info[bid].nmi_count;
+
+        /*
+         * Use a lock so only one cpu prints at a time.
+         * This prevents intermixed output.
          */
         spin_lock(&uv_nmi_lock);
-        pr_info("NMI stack dump cpu %u:\n", smp_processor_id());
+        pr_info("UV NMI stack dump cpu %u:\n", smp_processor_id());
         dump_stack();
         spin_unlock(&uv_nmi_lock);
 
@@ -661,7 +696,8 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 }
 
 static struct notifier_block uv_dump_stack_nmi_nb = {
-        .notifier_call  = uv_handle_nmi
+        .notifier_call  = uv_handle_nmi,
+        .priority = NMI_LOCAL_LOW_PRIOR - 1,
 };
 
 void uv_register_nmi_notifier(void)
@@ -720,8 +756,9 @@ void __init uv_system_init(void)
         printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades());
 
         bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
-        uv_blade_info = kmalloc(bytes, GFP_KERNEL);
+        uv_blade_info = kzalloc(bytes, GFP_KERNEL);
         BUG_ON(!uv_blade_info);
+
         for (blade = 0; blade < uv_num_possible_blades(); blade++)
                 uv_blade_info[blade].memory_nid = -1;
 
@@ -747,6 +784,7 @@ void __init uv_system_init(void)
                         uv_blade_info[blade].pnode = pnode;
                         uv_blade_info[blade].nr_possible_cpus = 0;
                         uv_blade_info[blade].nr_online_cpus = 0;
+                        spin_lock_init(&uv_blade_info[blade].nmi_lock);
                         max_pnode = max(pnode, max_pnode);
                         blade++;
                 }
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index bb9eb29a52dd..6f9d1f6063e9 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -613,7 +613,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 #endif
 
         /* As a rule processors have APIC timer running in deep C states */
-        if (c->x86 >= 0xf && !cpu_has_amd_erratum(amd_erratum_400))
+        if (c->x86 > 0xf && !cpu_has_amd_erratum(amd_erratum_400))
                 set_cpu_cap(c, X86_FEATURE_ARAT);
 
         /*
@@ -698,7 +698,7 @@ cpu_dev_register(amd_cpu_dev);
  */
 
 const int amd_erratum_400[] =
-        AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0x0f, 0x4, 0x2, 0xff, 0xf),
+        AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf),
                             AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf));
 EXPORT_SYMBOL_GPL(amd_erratum_400);
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 167f97b5596e..bb0adad35143 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -509,6 +509,7 @@ recurse:
 out_free:
         if (b) {
                 kobject_put(&b->kobj);
+                list_del(&b->miscj);
                 kfree(b);
         }
         return err;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 6f8c5e9da97f..0f034460260d 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -446,18 +446,20 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
          */
         rdmsr(MSR_IA32_MISC_ENABLE, l, h);
 
+        h = lvtthmr_init;
         /*
          * The initial value of thermal LVT entries on all APs always reads
          * 0x10000 because APs are woken up by BSP issuing INIT-SIPI-SIPI
          * sequence to them and LVT registers are reset to 0s except for
          * the mask bits which are set to 1s when APs receive INIT IPI.
-         * Always restore the value that BIOS has programmed on AP based on
-         * BSP's info we saved since BIOS is always setting the same value
-         * for all threads/cores
+         * If BIOS takes over the thermal interrupt and sets its interrupt
+         * delivery mode to SMI (not fixed), it restores the value that the
+         * BIOS has programmed on AP based on BSP's info we saved since BIOS
+         * is always setting the same value for all threads/cores.
          */
-        apic_write(APIC_LVTTHMR, lvtthmr_init);
+        if ((h & APIC_DM_FIXED_MASK) != APIC_DM_FIXED)
+                apic_write(APIC_LVTTHMR, lvtthmr_init);
 
-        h = lvtthmr_init;
 
         if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
                 printk(KERN_DEBUG
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index c969fd9d1566..f1a6244d7d93 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -1183,12 +1183,13 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
                                          struct pt_regs *regs)
 {
         struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
+        unsigned long flags;
 
         /* This is possible if op is under delayed unoptimizing */
         if (kprobe_disabled(&op->kp))
                 return;
 
-        preempt_disable();
+        local_irq_save(flags);
         if (kprobe_running()) {
                 kprobes_inc_nmissed_count(&op->kp);
         } else {
@@ -1207,7 +1208,7 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
                 opt_pre_handler(&op->kp, regs);
                 __this_cpu_write(current_kprobe, NULL);
         }
-        preempt_enable_no_resched();
+        local_irq_restore(flags);
 }
 
 static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src)
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index c11514e9128b..75ef4b18e9b7 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -61,6 +61,10 @@ struct x86_init_ops x86_init __initdata = {
                 .banner                 = default_banner,
         },
 
+        .mapping = {
+                .pagetable_reserve              = native_pagetable_reserve,
+        },
+
         .paging = {
                 .pagetable_setup_start  = native_pagetable_setup_start,
                 .pagetable_setup_done   = native_pagetable_setup_done,
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 286d289b039b..37b8b0fe8320 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -81,6 +81,11 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
                 end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
 }
 
+void __init native_pagetable_reserve(u64 start, u64 end)
+{
+        memblock_x86_reserve_range(start, end, "PGTABLE");
+}
+
 struct map_range {
         unsigned long start;
         unsigned long end;
@@ -272,9 +277,24 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 
         __flush_tlb_all();
 
+        /*
+         * Reserve the kernel pagetable pages we used (pgt_buf_start -
+         * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top)
+         * so that they can be reused for other purposes.
+         *
+         * On native it just means calling memblock_x86_reserve_range, on Xen it
+         * also means marking RW the pagetable pages that we allocated before
+         * but that haven't been used.
+         *
+         * In fact on xen we mark RO the whole range pgt_buf_start -
+         * pgt_buf_top, because we have to make sure that when
+         * init_memory_mapping reaches the pagetable pages area, it maps
+         * RO all the pagetable pages, including the ones that are beyond
+         * pgt_buf_end at that time.
+         */
         if (!after_bootmem && pgt_buf_end > pgt_buf_start)
-                memblock_x86_reserve_range(pgt_buf_start << PAGE_SHIFT,
-                                 pgt_buf_end << PAGE_SHIFT, "PGTABLE");
+                x86_init.mapping.pagetable_reserve(PFN_PHYS(pgt_buf_start),
+                                PFN_PHYS(pgt_buf_end));
 
         if (!after_bootmem)
                 early_memtest(start, end);
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 7cb6424317f6..c58e0ea39ef5 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -699,16 +699,17 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
                                           struct mm_struct *mm,
                                           unsigned long va, unsigned int cpu)
 {
-        int tcpu;
-        int uvhub;
         int locals = 0;
         int remotes = 0;
         int hubs = 0;
+        int tcpu;
+        int tpnode;
         struct bau_desc *bau_desc;
         struct cpumask *flush_mask;
         struct ptc_stats *stat;
         struct bau_control *bcp;
         struct bau_control *tbcp;
+        struct hub_and_pnode *hpp;
 
         /* kernel was booted 'nobau' */
         if (nobau)
@@ -750,11 +751,18 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
         bau_desc += UV_ITEMS_PER_DESCRIPTOR * bcp->uvhub_cpu;
         bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
 
-        /* cpu statistics */
         for_each_cpu(tcpu, flush_mask) {
-                uvhub = uv_cpu_to_blade_id(tcpu);
-                bau_uvhub_set(uvhub, &bau_desc->distribution);
-                if (uvhub == bcp->uvhub)
+                /*
+                 * The distribution vector is a bit map of pnodes, relative
+                 * to the partition base pnode (and the partition base nasid
+                 * in the header).
+                 * Translate cpu to pnode and hub using an array stored
+                 * in local memory.
+                 */
+                hpp = &bcp->socket_master->target_hub_and_pnode[tcpu];
+                tpnode = hpp->pnode - bcp->partition_base_pnode;
+                bau_uvhub_set(tpnode, &bau_desc->distribution);
+                if (hpp->uvhub == bcp->uvhub)
                         locals++;
                 else
                         remotes++;
@@ -855,7 +863,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
  * an interrupt, but causes an error message to be returned to
  * the sender.
  */
-static void uv_enable_timeouts(void)
+static void __init uv_enable_timeouts(void)
 {
         int uvhub;
         int nuvhubs;
@@ -1326,10 +1334,10 @@ static int __init uv_ptc_init(void)
 }
 
 /*
- * initialize the sending side's sending buffers
+ * Initialize the sending side's sending buffers.
  */
 static void
-uv_activation_descriptor_init(int node, int pnode)
+uv_activation_descriptor_init(int node, int pnode, int base_pnode)
 {
         int i;
         int cpu;
@@ -1352,11 +1360,11 @@ uv_activation_descriptor_init(int node, int pnode)
         n = pa >> uv_nshift;
         m = pa & uv_mmask;
 
+        /* the 14-bit pnode */
         uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE,
                               (n << UV_DESC_BASE_PNODE_SHIFT | m));
-
         /*
-         * initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
+         * Initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
          * cpu even though we only use the first one; one descriptor can
          * describe a broadcast to 256 uv hubs.
          */
@@ -1365,12 +1373,13 @@ uv_activation_descriptor_init(int node, int pnode)
                 memset(bd2, 0, sizeof(struct bau_desc));
                 bd2->header.sw_ack_flag = 1;
                 /*
-                 * base_dest_nodeid is the nasid of the first uvhub
-                 * in the partition. The bit map will indicate uvhub numbers,
-                 * which are 0-N in a partition. Pnodes are unique system-wide.
+                 * The base_dest_nasid set in the message header is the nasid
+                 * of the first uvhub in the partition. The bit map will
+                 * indicate destination pnode numbers relative to that base.
+                 * They may not be consecutive if nasid striding is being used.
                  */
-                bd2->header.base_dest_nodeid = UV_PNODE_TO_NASID(uv_partition_base_pnode);
-                bd2->header.dest_subnodeid = 0x10; /* the LB */
+                bd2->header.base_dest_nasid = UV_PNODE_TO_NASID(base_pnode);
+                bd2->header.dest_subnodeid = UV_LB_SUBNODEID;
                 bd2->header.command = UV_NET_ENDPOINT_INTD;
                 bd2->header.int_both = 1;
                 /*
@@ -1442,7 +1451,7 @@ uv_payload_queue_init(int node, int pnode)
 /*
  * Initialization of each UV hub's structures
  */
-static void __init uv_init_uvhub(int uvhub, int vector)
+static void __init uv_init_uvhub(int uvhub, int vector, int base_pnode)
 {
         int node;
         int pnode;
@@ -1450,11 +1459,11 @@ static void __init uv_init_uvhub(int uvhub, int vector)
 
         node = uvhub_to_first_node(uvhub);
         pnode = uv_blade_to_pnode(uvhub);
-        uv_activation_descriptor_init(node, pnode);
+        uv_activation_descriptor_init(node, pnode, base_pnode);
         uv_payload_queue_init(node, pnode);
         /*
-         * the below initialization can't be in firmware because the
-         * messaging IRQ will be determined by the OS
+         * The below initialization can't be in firmware because the
+         * messaging IRQ will be determined by the OS.
          */
         apicid = uvhub_to_first_apicid(uvhub) | uv_apicid_hibits;
         uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
@@ -1491,10 +1500,11 @@ calculate_destination_timeout(void)
 /*
  * initialize the bau_control structure for each cpu
  */
-static int __init uv_init_per_cpu(int nuvhubs)
+static int __init uv_init_per_cpu(int nuvhubs, int base_part_pnode)
 {
         int i;
         int cpu;
+        int tcpu;
         int pnode;
         int uvhub;
         int have_hmaster;
@@ -1528,6 +1538,15 @@ static int __init uv_init_per_cpu(int nuvhubs)
                 bcp = &per_cpu(bau_control, cpu);
                 memset(bcp, 0, sizeof(struct bau_control));
                 pnode = uv_cpu_hub_info(cpu)->pnode;
+                if ((pnode - base_part_pnode) >= UV_DISTRIBUTION_SIZE) {
+                        printk(KERN_EMERG
+                                "cpu %d pnode %d-%d beyond %d; BAU disabled\n",
+                                cpu, pnode, base_part_pnode,
+                                UV_DISTRIBUTION_SIZE);
+                        return 1;
+                }
+                bcp->osnode = cpu_to_node(cpu);
+                bcp->partition_base_pnode = uv_partition_base_pnode;
                 uvhub = uv_cpu_hub_info(cpu)->numa_blade_id;
                 *(uvhub_mask + (uvhub/8)) |= (1 << (uvhub%8));
                 bdp = &uvhub_descs[uvhub];
@@ -1536,7 +1555,7 @@ static int __init uv_init_per_cpu(int nuvhubs)
                 bdp->pnode = pnode;
                 /* kludge: 'assuming' one node per socket, and assuming that
                    disabling a socket just leaves a gap in node numbers */
-                socket = (cpu_to_node(cpu) & 1);
+                socket = bcp->osnode & 1;
                 bdp->socket_mask |= (1 << socket);
                 sdp = &bdp->socket[socket];
                 sdp->cpu_number[sdp->num_cpus] = cpu;
@@ -1585,6 +1604,20 @@ static int __init uv_init_per_cpu(int nuvhubs)
 nextsocket:
                         socket++;
                         socket_mask = (socket_mask >> 1);
+                        /* each socket gets a local array of pnodes/hubs */
+                        bcp = smaster;
+                        bcp->target_hub_and_pnode = kmalloc_node(
+                                sizeof(struct hub_and_pnode) *
+                                num_possible_cpus(), GFP_KERNEL, bcp->osnode);
+                        memset(bcp->target_hub_and_pnode, 0,
+                                sizeof(struct hub_and_pnode) *
+                                num_possible_cpus());
+                        for_each_present_cpu(tcpu) {
+                                bcp->target_hub_and_pnode[tcpu].pnode =
+                                        uv_cpu_hub_info(tcpu)->pnode;
+                                bcp->target_hub_and_pnode[tcpu].uvhub =
+                                        uv_cpu_hub_info(tcpu)->numa_blade_id;
+                        }
                 }
         }
         kfree(uvhub_descs);
@@ -1637,21 +1670,22 @@ static int __init uv_bau_init(void)
         spin_lock_init(&disable_lock);
         congested_cycles = microsec_2_cycles(congested_response_us);
 
-        if (uv_init_per_cpu(nuvhubs)) {
-                nobau = 1;
-                return 0;
-        }
-
         uv_partition_base_pnode = 0x7fffffff;
-        for (uvhub = 0; uvhub < nuvhubs; uvhub++)
+        for (uvhub = 0; uvhub < nuvhubs; uvhub++) {
                 if (uv_blade_nr_possible_cpus(uvhub) &&
                         (uv_blade_to_pnode(uvhub) < uv_partition_base_pnode))
                         uv_partition_base_pnode = uv_blade_to_pnode(uvhub);
+        }
+
+        if (uv_init_per_cpu(nuvhubs, uv_partition_base_pnode)) {
+                nobau = 1;
+                return 0;
+        }
 
         vector = UV_BAU_MESSAGE;
         for_each_possible_blade(uvhub)
                 if (uv_blade_nr_possible_cpus(uvhub))
-                        uv_init_uvhub(uvhub, vector);
+                        uv_init_uvhub(uvhub, vector, uv_partition_base_pnode);
 
         uv_enable_timeouts();
         alloc_intr_gate(vector, uv_bau_message_intr1);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 55c965b38c27..0684f3c74d53 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1275,6 +1275,20 @@ static __init void xen_pagetable_setup_start(pgd_t *base)
 {
 }
 
+static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
+{
+        /* reserve the range used */
+        native_pagetable_reserve(start, end);
+
+        /* set as RW the rest */
+        printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", end,
+                        PFN_PHYS(pgt_buf_top));
+        while (end < PFN_PHYS(pgt_buf_top)) {
+                make_lowmem_page_readwrite(__va(end));
+                end += PAGE_SIZE;
+        }
+}
+
 static void xen_post_allocator_init(void);
 
 static __init void xen_pagetable_setup_done(pgd_t *base)
@@ -1463,119 +1477,6 @@ static int xen_pgd_alloc(struct mm_struct *mm)
         return ret;
 }
 
-#ifdef CONFIG_X86_64
-static __initdata u64 __last_pgt_set_rw = 0;
-static __initdata u64 __pgt_buf_start = 0;
-static __initdata u64 __pgt_buf_end = 0;
-static __initdata u64 __pgt_buf_top = 0;
-/*
- * As a consequence of the commit:
- * 
- * commit 4b239f458c229de044d6905c2b0f9fe16ed9e01e
- * Author: Yinghai Lu <yinghai@kernel.org>
- * Date:   Fri Dec 17 16:58:28 2010 -0800
- * 
- *     x86-64, mm: Put early page table high
- * 
- * at some point init_memory_mapping is going to reach the pagetable pages
- * area and map those pages too (mapping them as normal memory that falls
- * in the range of addresses passed to init_memory_mapping as argument).
- * Some of those pages are already pagetable pages (they are in the range
- * pgt_buf_start-pgt_buf_end) therefore they are going to be mapped RO and
- * everything is fine.
- * Some of these pages are not pagetable pages yet (they fall in the range
- * pgt_buf_end-pgt_buf_top; for example the page at pgt_buf_end) so they
- * are going to be mapped RW.  When these pages become pagetable pages and
- * are hooked into the pagetable, xen will find that the guest has already
- * a RW mapping of them somewhere and fail the operation.
- * The reason Xen requires pagetables to be RO is that the hypervisor needs
- * to verify that the pagetables are valid before using them. The validation
- * operations are called "pinning".
- * 
- * In order to fix the issue we mark all the pages in the entire range
- * pgt_buf_start-pgt_buf_top as RO, however when the pagetable allocation
- * is completed only the range pgt_buf_start-pgt_buf_end is reserved by
- * init_memory_mapping. Hence the kernel is going to crash as soon as one
- * of the pages in the range pgt_buf_end-pgt_buf_top is reused (b/c those
- * ranges are RO).
- * 
- * For this reason, 'mark_rw_past_pgt' is introduced which is called _after_
- * the init_memory_mapping has completed (in a perfect world we would
- * call this function from init_memory_mapping, but lets ignore that).
- * 
- * Because we are called _after_ init_memory_mapping the pgt_buf_[start,
- * end,top] have all changed to new values (b/c init_memory_mapping
- * is called and setting up another new page-table). Hence, the first time
- * we enter this function, we save away the pgt_buf_start value and update
- * the pgt_buf_[end,top].
- * 
- * When we detect that the "old" pgt_buf_start through pgt_buf_end
- * PFNs have been reserved (so memblock_x86_reserve_range has been called),
- * we immediately set out to RW the "old" pgt_buf_end through pgt_buf_top.
- * 
- * And then we update those "old" pgt_buf_[end|top] with the new ones
- * so that we can redo this on the next pagetable.
- */
-static __init void mark_rw_past_pgt(void) {
-
-        if (pgt_buf_end > pgt_buf_start) {
-                u64 addr, size;
-
-                /* Save it away. */
-                if (!__pgt_buf_start) {
-                        __pgt_buf_start = pgt_buf_start;
-                        __pgt_buf_end = pgt_buf_end;
-                        __pgt_buf_top = pgt_buf_top;
-                        return;
-                }
-                /* If we get the range that starts at __pgt_buf_end that means
-                 * the range is reserved, and that in 'init_memory_mapping'
-                 * the 'memblock_x86_reserve_range' has been called with the
-                 * outdated __pgt_buf_start, __pgt_buf_end (the "new"
-                 * pgt_buf_[start|end|top] refer now to a new pagetable.
-                 * Note: we are called _after_ the pgt_buf_[..] have been
-                 * updated.*/
-
-                addr = memblock_x86_find_in_range_size(PFN_PHYS(__pgt_buf_start),
-                                                       &size, PAGE_SIZE);
-
-                /* Still not reserved, meaning 'memblock_x86_reserve_range'
-                 * hasn't been called yet. Update the _end and _top.*/
-                if (addr == PFN_PHYS(__pgt_buf_start)) {
-                        __pgt_buf_end = pgt_buf_end;
-                        __pgt_buf_top = pgt_buf_top;
-                        return;
-                }
-
-                /* OK, the area is reserved, meaning it is time for us to
-                 * set RW for the old end->top PFNs. */
-
-                /* ..unless we had already done this. */
-                if (__pgt_buf_end == __last_pgt_set_rw)
-                        return;
-
-                addr = PFN_PHYS(__pgt_buf_end);
-                
-                /* set as RW the rest */
-                printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n",
-                        PFN_PHYS(__pgt_buf_end), PFN_PHYS(__pgt_buf_top));
-                
-                while (addr < PFN_PHYS(__pgt_buf_top)) {
-                        make_lowmem_page_readwrite(__va(addr));
-                        addr += PAGE_SIZE;
-                }
-                /* And update everything so that we are ready for the next
-                 * pagetable (the one created for regions past 4GB) */
-                __last_pgt_set_rw = __pgt_buf_end;
-                __pgt_buf_start = pgt_buf_start;
-                __pgt_buf_end = pgt_buf_end;
-                __pgt_buf_top = pgt_buf_top;
-        }
-        return;
-}
-#else
-static __init void mark_rw_past_pgt(void) { }
-#endif
 static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 #ifdef CONFIG_X86_64
@@ -1602,14 +1503,6 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
         unsigned long pfn = pte_pfn(pte);
 
         /*
-         * A bit of optimization. We do not need to call the workaround
-         * when xen_set_pte_init is called with a PTE with 0 as PFN.
-         * That is b/c the pagetable at that point are just being populated
-         * with empty values and we can save some cycles by not calling
-         * the 'memblock' code.*/
-        if (pfn)
-                mark_rw_past_pgt();
-        /*
          * If the new pfn is within the range of the newly allocated
          * kernel pagetable, and it isn't being mapped into an
          * early_ioremap fixmap slot as a freshly allocated page, make sure
@@ -2118,8 +2011,6 @@ __init void xen_ident_map_ISA(void)
 
 static __init void xen_post_allocator_init(void)
 {
-        mark_rw_past_pgt();
-
 #ifdef CONFIG_XEN_DEBUG
         pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
 #endif
@@ -2228,6 +2119,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 void __init xen_init_mmu_ops(void)
 {
+        x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
         x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
         x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
         pv_mmu_ops = xen_mmu_ops;