Automatic merge with /usr/src/ntfs-2.6.git.

5 files changed, 63 insertions, 45 deletions

diff --git a/arch/ia64/kernel/domain.c b/arch/ia64/kernel/domain.c
index fe532c970438..d65e87b6394f 100644
--- a/arch/ia64/kernel/domain.c
+++ b/arch/ia64/kernel/domain.c
@@ -14,7 +14,7 @@
 #include <linux/topology.h>
 #include <linux/nodemask.h>
 
-#define SD_NODES_PER_DOMAIN 6
+#define SD_NODES_PER_DOMAIN 16
 
 #ifdef CONFIG_NUMA
 /**
@@ -27,7 +27,7 @@
  *
  * Should use nodemask_t.
  */
-static int __devinit find_next_best_node(int node, unsigned long *used_nodes)
+static int find_next_best_node(int node, unsigned long *used_nodes)
 {
         int i, n, val, min_val, best_node = 0;
 
@@ -66,7 +66,7 @@ static int __devinit find_next_best_node(int node, unsigned long *used_nodes)
  * should be one that prevents unnecessary balancing, but also spreads tasks
  * out optimally.
  */
-static cpumask_t __devinit sched_domain_node_span(int node)
+static cpumask_t sched_domain_node_span(int node)
 {
         int i;
         cpumask_t span, nodemask;
@@ -96,7 +96,7 @@ static cpumask_t __devinit sched_domain_node_span(int node)
 #ifdef CONFIG_SCHED_SMT
 static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
 static struct sched_group sched_group_cpus[NR_CPUS];
-static int __devinit cpu_to_cpu_group(int cpu)
+static int cpu_to_cpu_group(int cpu)
 {
         return cpu;
 }
@@ -104,7 +104,7 @@ static int __devinit cpu_to_cpu_group(int cpu)
 
 static DEFINE_PER_CPU(struct sched_domain, phys_domains);
 static struct sched_group sched_group_phys[NR_CPUS];
-static int __devinit cpu_to_phys_group(int cpu)
+static int cpu_to_phys_group(int cpu)
 {
 #ifdef CONFIG_SCHED_SMT
         return first_cpu(cpu_sibling_map[cpu]);
@@ -125,44 +125,36 @@ static struct sched_group *sched_group_nodes[MAX_NUMNODES];
 static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
 static struct sched_group sched_group_allnodes[MAX_NUMNODES];
 
-static int __devinit cpu_to_allnodes_group(int cpu)
+static int cpu_to_allnodes_group(int cpu)
 {
         return cpu_to_node(cpu);
 }
 #endif
 
 /*
- * Set up scheduler domains and groups.  Callers must hold the hotplug lock.
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
  */
-void __devinit arch_init_sched_domains(void)
+void build_sched_domains(const cpumask_t *cpu_map)
 {
         int i;
-        cpumask_t cpu_default_map;
 
         /*
-         * Setup mask for cpus without special case scheduling requirements.
-         * For now this just excludes isolated cpus, but could be used to
-         * exclude other special cases in the future.
+         * Set up domains for cpus specified by the cpu_map.
          */
-        cpus_complement(cpu_default_map, cpu_isolated_map);
-        cpus_and(cpu_default_map, cpu_default_map, cpu_online_map);
-
-        /*
-         * Set up domains. Isolated domains just stay on the dummy domain.
-         */
-        for_each_cpu_mask(i, cpu_default_map) {
+        for_each_cpu_mask(i, *cpu_map) {
                 int group;
                 struct sched_domain *sd = NULL, *p;
                 cpumask_t nodemask = node_to_cpumask(cpu_to_node(i));
 
-                cpus_and(nodemask, nodemask, cpu_default_map);
+                cpus_and(nodemask, nodemask, *cpu_map);
 
 #ifdef CONFIG_NUMA
                 if (num_online_cpus()
                                 > SD_NODES_PER_DOMAIN*cpus_weight(nodemask)) {
                         sd = &per_cpu(allnodes_domains, i);
                         *sd = SD_ALLNODES_INIT;
-                        sd->span = cpu_default_map;
+                        sd->span = *cpu_map;
                         group = cpu_to_allnodes_group(i);
                         sd->groups = &sched_group_allnodes[group];
                         p = sd;
@@ -173,7 +165,7 @@ void __devinit arch_init_sched_domains(void)
                 *sd = SD_NODE_INIT;
                 sd->span = sched_domain_node_span(cpu_to_node(i));
                 sd->parent = p;
-                cpus_and(sd->span, sd->span, cpu_default_map);
+                cpus_and(sd->span, sd->span, *cpu_map);
 #endif
 
                 p = sd;
@@ -190,7 +182,7 @@ void __devinit arch_init_sched_domains(void)
                 group = cpu_to_cpu_group(i);
                 *sd = SD_SIBLING_INIT;
                 sd->span = cpu_sibling_map[i];
-                cpus_and(sd->span, sd->span, cpu_default_map);
+                cpus_and(sd->span, sd->span, *cpu_map);
                 sd->parent = p;
                 sd->groups = &sched_group_cpus[group];
 #endif
@@ -198,9 +190,9 @@ void __devinit arch_init_sched_domains(void)
 
 #ifdef CONFIG_SCHED_SMT
         /* Set up CPU (sibling) groups */
-        for_each_cpu_mask(i, cpu_default_map) {
+        for_each_cpu_mask(i, *cpu_map) {
                 cpumask_t this_sibling_map = cpu_sibling_map[i];
-                cpus_and(this_sibling_map, this_sibling_map, cpu_default_map);
+                cpus_and(this_sibling_map, this_sibling_map, *cpu_map);
                 if (i != first_cpu(this_sibling_map))
                         continue;
 
@@ -213,7 +205,7 @@ void __devinit arch_init_sched_domains(void)
         for (i = 0; i < MAX_NUMNODES; i++) {
                 cpumask_t nodemask = node_to_cpumask(i);
 
-                cpus_and(nodemask, nodemask, cpu_default_map);
+                cpus_and(nodemask, nodemask, *cpu_map);
                 if (cpus_empty(nodemask))
                         continue;
 
@@ -222,7 +214,7 @@ void __devinit arch_init_sched_domains(void)
         }
 
 #ifdef CONFIG_NUMA
-        init_sched_build_groups(sched_group_allnodes, cpu_default_map,
+        init_sched_build_groups(sched_group_allnodes, *cpu_map,
                                 &cpu_to_allnodes_group);
 
         for (i = 0; i < MAX_NUMNODES; i++) {
@@ -233,12 +225,12 @@ void __devinit arch_init_sched_domains(void)
                 cpumask_t covered = CPU_MASK_NONE;
                 int j;
 
-                cpus_and(nodemask, nodemask, cpu_default_map);
+                cpus_and(nodemask, nodemask, *cpu_map);
                 if (cpus_empty(nodemask))
                         continue;
 
                 domainspan = sched_domain_node_span(i);
-                cpus_and(domainspan, domainspan, cpu_default_map);
+                cpus_and(domainspan, domainspan, *cpu_map);
 
                 sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
                 sched_group_nodes[i] = sg;
@@ -266,7 +258,7 @@ void __devinit arch_init_sched_domains(void)
                         int n = (i + j) % MAX_NUMNODES;
 
                         cpus_complement(notcovered, covered);
-                        cpus_and(tmp, notcovered, cpu_default_map);
+                        cpus_and(tmp, notcovered, *cpu_map);
                         cpus_and(tmp, tmp, domainspan);
                         if (cpus_empty(tmp))
                                 break;
@@ -293,7 +285,7 @@ void __devinit arch_init_sched_domains(void)
 #endif
 
         /* Calculate CPU power for physical packages and nodes */
-        for_each_cpu_mask(i, cpu_default_map) {
+        for_each_cpu_mask(i, *cpu_map) {
                 int power;
                 struct sched_domain *sd;
 #ifdef CONFIG_SCHED_SMT
@@ -359,13 +351,35 @@ next_sg:
                 cpu_attach_domain(sd, i);
         }
 }
+/*
+ * Set up scheduler domains and groups.  Callers must hold the hotplug lock.
+ */
+void arch_init_sched_domains(const cpumask_t *cpu_map)
+{
+        cpumask_t cpu_default_map;
+
+        /*
+         * Setup mask for cpus without special case scheduling requirements.
+         * For now this just excludes isolated cpus, but could be used to
+         * exclude other special cases in the future.
+         */
+        cpus_andnot(cpu_default_map, *cpu_map, cpu_isolated_map);
+
+        build_sched_domains(&cpu_default_map);
+}
 
-void __devinit arch_destroy_sched_domains(void)
+void arch_destroy_sched_domains(const cpumask_t *cpu_map)
 {
 #ifdef CONFIG_NUMA
         int i;
         for (i = 0; i < MAX_NUMNODES; i++) {
+                cpumask_t nodemask = node_to_cpumask(i);
                 struct sched_group *oldsg, *sg = sched_group_nodes[i];
+
+                cpus_and(nodemask, nodemask, *cpu_map);
+                if (cpus_empty(nodemask))
+                        continue;
+
                 if (sg == NULL)
                         continue;
                 sg = sg->next;
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 3865f088ffa2..623b0a546709 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -346,6 +346,7 @@ smp_callin (void)
         lock_ipi_calllock();
         cpu_set(cpuid, cpu_online_map);
         unlock_ipi_calllock();
+        per_cpu(cpu_state, cpuid) = CPU_ONLINE;
 
         smp_setup_percpu_timer();
 
@@ -611,6 +612,7 @@ void __devinit smp_prepare_boot_cpu(void)
 {
         cpu_set(smp_processor_id(), cpu_online_map);
         cpu_set(smp_processor_id(), cpu_callin_map);
+        per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
 }
 
 /*
@@ -688,6 +690,7 @@ int __cpu_disable(void)
                 return -EBUSY;
 
         remove_siblinginfo(cpu);
+        cpu_clear(cpu, cpu_online_map);
         fixup_irqs();
         local_flush_tlb_all();
         cpu_clear(cpu, cpu_callin_map);
@@ -774,6 +777,7 @@ __cpu_up (unsigned int cpu)
         if (cpu_isset(cpu, cpu_callin_map))
                 return -EINVAL;
 
+        per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
         /* Processor goes to start_secondary(), sets online flag */
         ret = do_boot_cpu(sapicid, cpu);
         if (ret < 0)
diff --git a/arch/ia64/sn/kernel/xpc.h b/arch/ia64/sn/kernel/xpc.h
index 1a0aed8490d1..d0ee635daf2e 100644
--- a/arch/ia64/sn/kernel/xpc.h
+++ b/arch/ia64/sn/kernel/xpc.h
@@ -87,7 +87,7 @@ struct xpc_rsvd_page {
         u8 partid;              /* partition ID from SAL */
         u8 version;
         u8 pad[6];              /* pad to u64 align */
-        u64 vars_pa;
+        volatile u64 vars_pa;
         u64 part_nasids[XP_NASID_MASK_WORDS] ____cacheline_aligned;
         u64 mach_nasids[XP_NASID_MASK_WORDS] ____cacheline_aligned;
 };
@@ -138,7 +138,7 @@ struct xpc_vars {
  * occupies half a cacheline.
  */
 struct xpc_vars_part {
-        u64 magic;
+        volatile u64 magic;
 
         u64 openclose_args_pa;  /* physical address of open and close args */
         u64 GPs_pa;             /* physical address of Get/Put values */
@@ -185,8 +185,8 @@ struct xpc_vars_part {
  * Define a Get/Put value pair (pointers) used with a message queue.
  */
 struct xpc_gp {
-        s64 get;        /* Get value */
-        s64 put;        /* Put value */
+        volatile s64 get;       /* Get value */
+        volatile s64 put;       /* Put value */
 };
 
 #define XPC_GP_SIZE \
@@ -231,7 +231,7 @@ struct xpc_openclose_args {
  */
 struct xpc_notify {
         struct semaphore sema;          /* notify semaphore */
-        u8 type;                        /* type of notification */
+        volatile u8 type;                       /* type of notification */
 
         /* the following two fields are only used if type == XPC_N_CALL */
         xpc_notify_func func;           /* user's notify function */
@@ -439,7 +439,7 @@ struct xpc_partition {
 
         /* XPC infrastructure referencing and teardown control */
 
-        u8 setup_state;                 /* infrastructure setup state */
+        volatile u8 setup_state;                        /* infrastructure setup state */
         wait_queue_head_t teardown_wq;  /* kthread waiting to teardown infra */
         atomic_t references;            /* #of references to infrastructure */
 
diff --git a/arch/ia64/sn/kernel/xpc_channel.c b/arch/ia64/sn/kernel/xpc_channel.c
index 0bf6fbcc46d2..6d02dac8056f 100644
--- a/arch/ia64/sn/kernel/xpc_channel.c
+++ b/arch/ia64/sn/kernel/xpc_channel.c
@@ -209,7 +209,7 @@ xpc_setup_infrastructure(struct xpc_partition *part)
          * With the setting of the partition setup_state to XPC_P_SETUP, we're
          * declaring that this partition is ready to go.
          */
-        (volatile u8) part->setup_state = XPC_P_SETUP;
+        part->setup_state = XPC_P_SETUP;
 
 
         /*
@@ -227,7 +227,7 @@ xpc_setup_infrastructure(struct xpc_partition *part)
         xpc_vars_part[partid].IPI_phys_cpuid =
                                         cpu_physical_id(smp_processor_id());
         xpc_vars_part[partid].nchannels = part->nchannels;
-        (volatile u64) xpc_vars_part[partid].magic = XPC_VP_MAGIC1;
+        xpc_vars_part[partid].magic = XPC_VP_MAGIC1;
 
         return xpcSuccess;
 }
@@ -355,7 +355,7 @@ xpc_pull_remote_vars_part(struct xpc_partition *part)
 
                 /* let the other side know that we've pulled their variables */
 
-                (volatile u64) xpc_vars_part[partid].magic = XPC_VP_MAGIC2;
+                xpc_vars_part[partid].magic = XPC_VP_MAGIC2;
         }
 
         if (pulled_entry->magic == XPC_VP_MAGIC1) {
@@ -1183,7 +1183,7 @@ xpc_process_msg_IPI(struct xpc_partition *part, int ch_number)
                  */
                 xpc_clear_local_msgqueue_flags(ch);
 
-                (volatile s64) ch->w_remote_GP.get = ch->remote_GP.get;
+                ch->w_remote_GP.get = ch->remote_GP.get;
 
                 dev_dbg(xpc_chan, "w_remote_GP.get changed to %ld, partid=%d, "
                         "channel=%d\n", ch->w_remote_GP.get, ch->partid,
@@ -1211,7 +1211,7 @@ xpc_process_msg_IPI(struct xpc_partition *part, int ch_number)
                  */
                 xpc_clear_remote_msgqueue_flags(ch);
 
-                (volatile s64) ch->w_remote_GP.put = ch->remote_GP.put;
+                ch->w_remote_GP.put = ch->remote_GP.put;
 
                 dev_dbg(xpc_chan, "w_remote_GP.put changed to %ld, partid=%d, "
                         "channel=%d\n", ch->w_remote_GP.put, ch->partid,
@@ -1875,7 +1875,7 @@ xpc_send_msg(struct xpc_channel *ch, struct xpc_msg *msg, u8 notify_type,
                 notify = &ch->notify_queue[msg_number % ch->local_nentries];
                 notify->func = func;
                 notify->key = key;
-                (volatile u8) notify->type = notify_type;
+                notify->type = notify_type;
 
                 // >>> is a mb() needed here?
 
diff --git a/arch/ia64/sn/kernel/xpc_partition.c b/arch/ia64/sn/kernel/xpc_partition.c
index cd7ed73f0e7a..578265ea9e67 100644
--- a/arch/ia64/sn/kernel/xpc_partition.c
+++ b/arch/ia64/sn/kernel/xpc_partition.c
@@ -253,7 +253,7 @@ xpc_rsvd_page_init(void)
          * This signifies to the remote partition that our reserved
          * page is initialized.
          */
-        (volatile u64) rp->vars_pa = __pa(xpc_vars);
+        rp->vars_pa = __pa(xpc_vars);
 
         return rp;
 }