Merge branch 'perf/urgent' into perf/core

Merge reason: queue up dependent patch, update to -rc4

Signed-off-by: Ingo Molnar <mingo@elte.hu>

19 files changed, 54 insertions, 127 deletions

diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index e7cbaa02cd0..475e2725fbd 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -103,4 +103,4 @@ archprepare: make_nr_irqs_h FORCE
 PHONY += make_nr_irqs_h FORCE
 
 make_nr_irqs_h: FORCE
-	$(Q)$(MAKE) $(build)=arch/ia64/kernel include/asm-ia64/nr-irqs.h
+	$(Q)$(MAKE) $(build)=arch/ia64/kernel include/generated/nr-irqs.h
diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h
index 91df9686a0d..7ae58892ba8 100644
--- a/arch/ia64/include/asm/acpi.h
+++ b/arch/ia64/include/asm/acpi.h
@@ -132,6 +132,12 @@ extern int __devinitdata pxm_to_nid_map[MAX_PXM_DOMAINS];
 extern int __initdata nid_to_pxm_map[MAX_NUMNODES];
 #endif
 
+static inline bool arch_has_acpi_pdc(void) { return true; }
+static inline void arch_acpi_set_pdc_bits(u32 *buf)
+{
+	buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP;
+}
+
 #define acpi_unlazy_tlb(x)
 
 #ifdef CONFIG_ACPI_NUMA
diff --git a/arch/ia64/include/asm/asm-offsets.h b/arch/ia64/include/asm/asm-offsets.h
new file mode 100644
index 00000000000..d370ee36a18
--- /dev/null
+++ b/arch/ia64/include/asm/asm-offsets.h
@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>
diff --git a/arch/ia64/include/asm/ftrace.h b/arch/ia64/include/asm/ftrace.h
index d20db3c2a65..fbd1a2470ca 100644
--- a/arch/ia64/include/asm/ftrace.h
+++ b/arch/ia64/include/asm/ftrace.h
@@ -8,7 +8,6 @@
 extern void _mcount(unsigned long pfs, unsigned long r1, unsigned long b0, unsigned long r0);
 #define mcount _mcount
 
-#include <asm/kprobes.h>
 /* In IA64, MCOUNT_ADDR is set in link time, so it's not a constant at compile time */
 #define MCOUNT_ADDR (((struct fnptr *)mcount)->ip)
 #define FTRACE_ADDR (((struct fnptr *)ftrace_caller)->ip)
diff --git a/arch/ia64/include/asm/irq.h b/arch/ia64/include/asm/irq.h
index 5282546cdf8..91b920fd7d5 100644
--- a/arch/ia64/include/asm/irq.h
+++ b/arch/ia64/include/asm/irq.h
@@ -13,7 +13,7 @@
 
 #include <linux/types.h>
 #include <linux/cpumask.h>
-#include <asm-ia64/nr-irqs.h>
+#include <generated/nr-irqs.h>
 
 static __inline__ int
 irq_canonicalize (int irq)
diff --git a/arch/ia64/include/asm/kprobes.h b/arch/ia64/include/asm/kprobes.h
index dbf83fb28db..d5505d6f238 100644
--- a/arch/ia64/include/asm/kprobes.h
+++ b/arch/ia64/include/asm/kprobes.h
@@ -103,11 +103,6 @@ typedef struct kprobe_opcode {
 	bundle_t bundle;
 } kprobe_opcode_t;
 
-struct fnptr {
-	unsigned long ip;
-	unsigned long gp;
-};
-
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
 	/* copy of the instruction to be emulated */
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 85d965cb19a..23cce999eb1 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -74,7 +74,7 @@ struct ia64_tr_entry {
 extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size);
 extern void ia64_ptr_entry(u64 target_mask, int slot);
 
-extern struct ia64_tr_entry __per_cpu_idtrs[NR_CPUS][2][IA64_TR_ALLOC_MAX];
+extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
 
 /*
  region register macros
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index 3ddb4e709db..d323071d0f9 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -33,7 +33,9 @@
 /*
  * Returns a bitmask of CPUs on Node 'node'.
  */
-#define cpumask_of_node(node) (&node_to_cpu_mask[node])
+#define cpumask_of_node(node) ((node) == -1 ?				\
+			       cpu_all_mask :				\
+			       &node_to_cpu_mask[node])
 
 /*
  * Returns the number of the node containing Node 'nid'.
diff --git a/arch/ia64/include/asm/types.h b/arch/ia64/include/asm/types.h
index bcd260e597d..93773fd37be 100644
--- a/arch/ia64/include/asm/types.h
+++ b/arch/ia64/include/asm/types.h
@@ -35,6 +35,11 @@ typedef unsigned int umode_t;
  */
 # ifdef __KERNEL__
 
+struct fnptr {
+	unsigned long ip;
+	unsigned long gp;
+};
+
 /* DMA addresses are 64-bits wide, in general.  */
 typedef u64 dma_addr_t;
 
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 6b7edcab0cb..e1236349c99 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -18,10 +18,6 @@ obj-$(CONFIG_IA64_GENERIC)	+= acpi-ext.o
 obj-$(CONFIG_IA64_HP_ZX1)	+= acpi-ext.o
 obj-$(CONFIG_IA64_HP_ZX1_SWIOTLB) += acpi-ext.o
 
-ifneq ($(CONFIG_ACPI_PROCESSOR),)
-obj-y				+= acpi-processor.o
-endif
-
 obj-$(CONFIG_IA64_PALINFO)	+= palinfo.o
 obj-$(CONFIG_IOSAPIC)		+= iosapic.o
 obj-$(CONFIG_MODULES)		+= module.o
@@ -81,17 +77,14 @@ define cmd_nr_irqs
 endef
 
 # We use internal kbuild rules to avoid the "is up to date" message from make
-arch/$(SRCARCH)/kernel/nr-irqs.s: $(srctree)/arch/$(SRCARCH)/kernel/nr-irqs.c \
-				$(wildcard $(srctree)/include/asm-ia64/*/irq.h)
+arch/$(SRCARCH)/kernel/nr-irqs.s: arch/$(SRCARCH)/kernel/nr-irqs.c
 	$(Q)mkdir -p $(dir $@)
 	$(call if_changed_dep,cc_s_c)
 
-include/asm-ia64/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
+include/generated/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
 	$(Q)mkdir -p $(dir $@)
 	$(call cmd,nr_irqs)
 
-clean-files += $(objtree)/include/asm-ia64/nr-irqs.h
-
 #
 # native ivt.S, entry.S and fsys.S
 #
diff --git a/arch/ia64/kernel/acpi-processor.c b/arch/ia64/kernel/acpi-processor.c
deleted file mode 100644
index dbda7bde611..00000000000
--- a/arch/ia64/kernel/acpi-processor.c
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * arch/ia64/kernel/acpi-processor.c
- *
- * Copyright (C) 2005 Intel Corporation
- * 	Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
- * 	- Added _PDC for platforms with Intel CPUs
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/acpi.h>
-
-#include <acpi/processor.h>
-#include <asm/acpi.h>
-
-static void init_intel_pdc(struct acpi_processor *pr)
-{
-	struct acpi_object_list *obj_list;
-	union acpi_object *obj;
-	u32 *buf;
-
-	/* allocate and initialize pdc. It will be used later. */
-	obj_list = kmalloc(sizeof(struct acpi_object_list), GFP_KERNEL);
-	if (!obj_list) {
-		printk(KERN_ERR "Memory allocation error\n");
-		return;
-	}
-
-	obj = kmalloc(sizeof(union acpi_object), GFP_KERNEL);
-	if (!obj) {
-		printk(KERN_ERR "Memory allocation error\n");
-		kfree(obj_list);
-		return;
-	}
-
-	buf = kmalloc(12, GFP_KERNEL);
-	if (!buf) {
-		printk(KERN_ERR "Memory allocation error\n");
-		kfree(obj);
-		kfree(obj_list);
-		return;
-	}
-
-	buf[0] = ACPI_PDC_REVISION_ID;
-	buf[1] = 1;
-	buf[2] = ACPI_PDC_EST_CAPABILITY_SMP;
-	/*
-	 * The default of PDC_SMP_T_SWCOORD bit is set for IA64 cpu so
-	 * that OSPM is capable of native ACPI throttling software
-	 * coordination using BIOS supplied _TSD info.
-	 */
-	buf[2] |= ACPI_PDC_SMP_T_SWCOORD;
-
-	obj->type = ACPI_TYPE_BUFFER;
-	obj->buffer.length = 12;
-	obj->buffer.pointer = (u8 *) buf;
-	obj_list->count = 1;
-	obj_list->pointer = obj;
-	pr->pdc = obj_list;
-
-	return;
-}
-
-/* Initialize _PDC data based on the CPU vendor */
-void arch_acpi_processor_init_pdc(struct acpi_processor *pr)
-{
-	pr->pdc = NULL;
-	init_intel_pdc(pr);
-	return;
-}
-
-EXPORT_SYMBOL(arch_acpi_processor_init_pdc);
-
-void arch_acpi_processor_cleanup_pdc(struct acpi_processor *pr)
-{
-	if (pr->pdc) {
-		kfree(pr->pdc->pointer->buffer.pointer);
-		kfree(pr->pdc->pointer);
-		kfree(pr->pdc);
-		pr->pdc = NULL;
-	}
-}
-
-EXPORT_SYMBOL(arch_acpi_processor_cleanup_pdc);
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 32f2639e9b0..378b4833024 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1225,9 +1225,12 @@ static void mca_insert_tr(u64 iord)
 	unsigned long psr;
 	int cpu = smp_processor_id();
 
+	if (!ia64_idtrs[cpu])
+		return;
+
 	psr = ia64_clear_ic();
 	for (i = IA64_TR_ALLOC_BASE; i < IA64_TR_ALLOC_MAX; i++) {
-		p = &__per_cpu_idtrs[cpu][iord-1][i];
+		p = ia64_idtrs[cpu] + (iord - 1) * IA64_TR_ALLOC_MAX;
 		if (p->pte & 0x1) {
 			old_rr = ia64_get_rr(p->ifa);
 			if (old_rr != p->rr) {
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 5246285a95f..6bcbe215b9a 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2293,7 +2293,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	 * if ((mm->total_vm << PAGE_SHIFT) + len> task->rlim[RLIMIT_AS].rlim_cur)
 	 * 	return -ENOMEM;
 	 */
-	if (size > task->signal->rlim[RLIMIT_MEMLOCK].rlim_cur)
+	if (size > task_rlimit(task, RLIMIT_MEMLOCK))
 		return -ENOMEM;
 
 	/*
diff --git a/arch/ia64/kvm/asm-offsets.c b/arch/ia64/kvm/asm-offsets.c
index 0c3564a7a03..9324c875caf 100644
--- a/arch/ia64/kvm/asm-offsets.c
+++ b/arch/ia64/kvm/asm-offsets.c
@@ -22,7 +22,6 @@
  *
  */
 
-#include <linux/autoconf.h>
 #include <linux/kvm_host.h>
 #include <linux/kbuild.h>
 
diff --git a/arch/ia64/kvm/vcpu.h b/arch/ia64/kvm/vcpu.h
index 360724d3ae6..988911b4cc7 100644
--- a/arch/ia64/kvm/vcpu.h
+++ b/arch/ia64/kvm/vcpu.h
@@ -388,6 +388,9 @@ static inline u64 __gpfn_is_io(u64 gpfn)
 #define _vmm_raw_spin_lock(x)	 do {}while(0)
 #define _vmm_raw_spin_unlock(x) do {}while(0)
 #else
+typedef struct {
+	volatile unsigned int lock;
+} vmm_spinlock_t;
 #define _vmm_raw_spin_lock(x)						\
 	do {								\
 		__u32 *ia64_spinlock_ptr = (__u32 *) (x);		\
@@ -405,12 +408,12 @@ static inline u64 __gpfn_is_io(u64 gpfn)
 
 #define _vmm_raw_spin_unlock(x)				\
 	do { barrier();				\
-		((spinlock_t *)x)->raw_lock.lock = 0; } \
+		((vmm_spinlock_t *)x)->lock = 0; } \
 while (0)
 #endif
 
-void vmm_spin_lock(spinlock_t *lock);
-void vmm_spin_unlock(spinlock_t *lock);
+void vmm_spin_lock(vmm_spinlock_t *lock);
+void vmm_spin_unlock(vmm_spinlock_t *lock);
 enum {
 	I_TLB = 1,
 	D_TLB = 2
diff --git a/arch/ia64/kvm/vmm.c b/arch/ia64/kvm/vmm.c
index f4b4c899bb6..7a62f75778c 100644
--- a/arch/ia64/kvm/vmm.c
+++ b/arch/ia64/kvm/vmm.c
@@ -60,12 +60,12 @@ static void __exit kvm_vmm_exit(void)
 	return ;
 }
 
-void vmm_spin_lock(spinlock_t *lock)
+void vmm_spin_lock(vmm_spinlock_t *lock)
 {
 	_vmm_raw_spin_lock(lock);
 }
 
-void vmm_spin_unlock(spinlock_t *lock)
+void vmm_spin_unlock(vmm_spinlock_t *lock)
 {
 	_vmm_raw_spin_unlock(lock);
 }
diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c
index 20b3852f7a6..4332f7ee520 100644
--- a/arch/ia64/kvm/vtlb.c
+++ b/arch/ia64/kvm/vtlb.c
@@ -182,7 +182,7 @@ void mark_pages_dirty(struct kvm_vcpu *v, u64 pte, u64 ps)
 {
 	u64 i, dirty_pages = 1;
 	u64 base_gfn = (pte&_PAGE_PPN_MASK) >> PAGE_SHIFT;
-	spinlock_t *lock = __kvm_va(v->arch.dirty_log_lock_pa);
+	vmm_spinlock_t *lock = __kvm_va(v->arch.dirty_log_lock_pa);
 	void *dirty_bitmap = (void *)KVM_MEM_DIRTY_LOG_BASE;
 
 	dirty_pages <<= ps <= PAGE_SHIFT ? 0 : ps - PAGE_SHIFT;
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index b9609c69343..7c0d4814a68 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -91,7 +91,7 @@ dma_mark_clean(void *addr, size_t size)
 inline void
 ia64_set_rbs_bot (void)
 {
-	unsigned long stack_size = current->signal->rlim[RLIMIT_STACK].rlim_max & -16;
+	unsigned long stack_size = rlimit_max(RLIMIT_STACK) & -16;
 
 	if (stack_size > MAX_USER_STACK_SIZE)
 		stack_size = MAX_USER_STACK_SIZE;
diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c
index ee09d261f2e..f3de9d7a98b 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -48,7 +48,7 @@ DEFINE_PER_CPU(u8, ia64_need_tlb_flush);
 DEFINE_PER_CPU(u8, ia64_tr_num);  /*Number of TR slots in current processor*/
 DEFINE_PER_CPU(u8, ia64_tr_used); /*Max Slot number used by kernel*/
 
-struct ia64_tr_entry __per_cpu_idtrs[NR_CPUS][2][IA64_TR_ALLOC_MAX];
+struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
 
 /*
  * Initializes the ia64_ctx.bitmap array based on max_ctx+1.
@@ -429,10 +429,16 @@ int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size)
 	struct ia64_tr_entry *p;
 	int cpu = smp_processor_id();
 
+	if (!ia64_idtrs[cpu]) {
+		ia64_idtrs[cpu] = kmalloc(2 * IA64_TR_ALLOC_MAX *
+				sizeof (struct ia64_tr_entry), GFP_KERNEL);
+		if (!ia64_idtrs[cpu])
+			return -ENOMEM;
+	}
 	r = -EINVAL;
 	/*Check overlap with existing TR entries*/
 	if (target_mask & 0x1) {
-		p = &__per_cpu_idtrs[cpu][0][0];
+		p = ia64_idtrs[cpu];
 		for (i = IA64_TR_ALLOC_BASE; i <= per_cpu(ia64_tr_used, cpu);
 								i++, p++) {
 			if (p->pte & 0x1)
@@ -444,7 +450,7 @@ int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size)
 		}
 	}
 	if (target_mask & 0x2) {
-		p = &__per_cpu_idtrs[cpu][1][0];
+		p = ia64_idtrs[cpu] + IA64_TR_ALLOC_MAX;
 		for (i = IA64_TR_ALLOC_BASE; i <= per_cpu(ia64_tr_used, cpu);
 								i++, p++) {
 			if (p->pte & 0x1)
@@ -459,16 +465,16 @@ int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size)
 	for (i = IA64_TR_ALLOC_BASE; i < per_cpu(ia64_tr_num, cpu); i++) {
 		switch (target_mask & 0x3) {
 		case 1:
-			if (!(__per_cpu_idtrs[cpu][0][i].pte & 0x1))
+			if (!((ia64_idtrs[cpu] + i)->pte & 0x1))
 				goto found;
 			continue;
 		case 2:
-			if (!(__per_cpu_idtrs[cpu][1][i].pte & 0x1))
+			if (!((ia64_idtrs[cpu] + IA64_TR_ALLOC_MAX + i)->pte & 0x1))
 				goto found;
 			continue;
 		case 3:
-			if (!(__per_cpu_idtrs[cpu][0][i].pte & 0x1) &&
-				!(__per_cpu_idtrs[cpu][1][i].pte & 0x1))
+			if (!((ia64_idtrs[cpu] + i)->pte & 0x1) &&
+			    !((ia64_idtrs[cpu] + IA64_TR_ALLOC_MAX + i)->pte & 0x1))
 				goto found;
 			continue;
 		default:
@@ -488,7 +494,7 @@ found:
 	if (target_mask & 0x1) {
 		ia64_itr(0x1, i, va, pte, log_size);
 		ia64_srlz_i();
-		p = &__per_cpu_idtrs[cpu][0][i];
+		p = ia64_idtrs[cpu] + i;
 		p->ifa = va;
 		p->pte = pte;
 		p->itir = log_size << 2;
@@ -497,7 +503,7 @@ found:
 	if (target_mask & 0x2) {
 		ia64_itr(0x2, i, va, pte, log_size);
 		ia64_srlz_i();
-		p = &__per_cpu_idtrs[cpu][1][i];
+		p = ia64_idtrs[cpu] + IA64_TR_ALLOC_MAX + i;
 		p->ifa = va;
 		p->pte = pte;
 		p->itir = log_size << 2;
@@ -528,7 +534,7 @@ void ia64_ptr_entry(u64 target_mask, int slot)
 		return;
 
 	if (target_mask & 0x1) {
-		p = &__per_cpu_idtrs[cpu][0][slot];
+		p = ia64_idtrs[cpu] + slot;
 		if ((p->pte&0x1) && is_tr_overlap(p, p->ifa, p->itir>>2)) {
 			p->pte = 0;
 			ia64_ptr(0x1, p->ifa, p->itir>>2);
@@ -537,7 +543,7 @@ void ia64_ptr_entry(u64 target_mask, int slot)
 	}
 
 	if (target_mask & 0x2) {
-		p = &__per_cpu_idtrs[cpu][1][slot];
+		p = ia64_idtrs[cpu] + IA64_TR_ALLOC_MAX + slot;
 		if ((p->pte & 0x1) && is_tr_overlap(p, p->ifa, p->itir>>2)) {
 			p->pte = 0;
 			ia64_ptr(0x2, p->ifa, p->itir>>2);
@@ -546,8 +552,8 @@ void ia64_ptr_entry(u64 target_mask, int slot)
 	}
 
 	for (i = per_cpu(ia64_tr_used, cpu); i >= IA64_TR_ALLOC_BASE; i--) {
-		if ((__per_cpu_idtrs[cpu][0][i].pte & 0x1) ||
-				(__per_cpu_idtrs[cpu][1][i].pte & 0x1))
+		if (((ia64_idtrs[cpu] + i)->pte & 0x1) ||
+		    ((ia64_idtrs[cpu] + IA64_TR_ALLOC_MAX + i)->pte & 0x1))
 			break;
 	}
 	per_cpu(ia64_tr_used, cpu) = i;