Merge branch 'percpu-cpumask-x86-for-linus-2' of git://git.kernel.org…

…/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'percpu-cpumask-x86-for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (682 commits)
  percpu: fix spurious alignment WARN in legacy SMP percpu allocator
  percpu: generalize embedding first chunk setup helper
  percpu: more flexibility for @dyn_size of pcpu_setup_first_chunk()
  percpu: make x86 addr <-> pcpu ptr conversion macros generic
  linker script: define __per_cpu_load on all SMP capable archs
  x86: UV: remove uv_flush_tlb_others() WARN_ON
  percpu: finer grained locking to break deadlock and allow atomic free
  percpu: move fully free chunk reclamation into a work
  percpu: move chunk area map extension out of area allocation
  percpu: replace pcpu_realloc() with pcpu_mem_alloc() and pcpu_mem_free()
  x86, percpu: setup reserved percpu area for x86_64
  percpu, module: implement reserved allocation and use it for module percpu variables
  percpu: add an indirection ptr for chunk page map access
  x86: make embedding percpu allocator return excessive free space
  percpu: use negative for auto for pcpu_setup_first_chunk() arguments
  percpu: improve first chunk initial area map handling
  percpu: cosmetic renames in pcpu_setup_first_chunk()
  percpu: clean up percpu constants
  x86: un-__init fill_pud/pmd/pte
  x86: remove vestigial fix_ioremap prototypes
  ...

Manually merge conflicts in arch/ia64/kernel/irq_ia64.c

Documentation/cputopology.txt

@@ -18,11 +18,11 @@ For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
-#define topology_thread_siblings(cpu)
-#define topology_core_siblings(cpu)
+#define topology_thread_cpumask(cpu)
+#define topology_core_cpumask(cpu)
 
 The type of **_id is int.
-The type of siblings is cpumask_t.
+The type of siblings is (const) struct cpumask *.
 
 To be consistent on all architectures, include/linux/topology.h
 provides default definitions for any of the above macros that are

Documentation/kernel-parameters.txt

@@ -1325,8 +1325,13 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	memtest=	[KNL,X86] Enable memtest
 			Format: <integer>
-			range: 0,4 : pattern number
 			default : 0 <disable>
+			Specifies the number of memtest passes to be
+			performed. Each pass selects another test
+			pattern from a given set of patterns. Memtest
+			fills the memory with this pattern, validates
+			memory contents and reserves bad memory
+			regions that are detected.
 
 	meye.*=		[HW] Set MotionEye Camera parameters
 			See Documentation/video4linux/meye.txt.

Documentation/x86/boot.txt

@@ -158,7 +158,7 @@ Offset	Proto	Name		Meaning
 0202/4	2.00+	header		Magic signature "HdrS"
 0206/2	2.00+	version		Boot protocol version supported
 0208/4	2.00+	realmode_swtch	Boot loader hook (see below)
-020C/2	2.00+	start_sys	The load-low segment (0x1000) (obsolete)
+020C/2	2.00+	start_sys_seg	The load-low segment (0x1000) (obsolete)
 020E/2	2.00+	kernel_version	Pointer to kernel version string
 0210/1	2.00+	type_of_loader	Boot loader identifier
 0211/1	2.00+	loadflags	Boot protocol option flags
@@ -170,10 +170,11 @@ Offset	Proto	Name		Meaning
 0224/2	2.01+	heap_end_ptr	Free memory after setup end
 0226/2	N/A	pad1		Unused
 0228/4	2.02+	cmd_line_ptr	32-bit pointer to the kernel command line
-022C/4	2.03+	initrd_addr_max	Highest legal initrd address
+022C/4	2.03+	ramdisk_max	Highest legal initrd address
 0230/4	2.05+	kernel_alignment Physical addr alignment required for kernel
 0234/1	2.05+	relocatable_kernel Whether kernel is relocatable or not
-0235/3	N/A	pad2		Unused
+0235/1	N/A	pad2		Unused
+0236/2	N/A	pad3		Unused
 0238/4	2.06+	cmdline_size	Maximum size of the kernel command line
 023C/4	2.07+	hardware_subarch Hardware subarchitecture
 0240/8	2.07+	hardware_subarch_data Subarchitecture-specific data
@@ -299,14 +300,14 @@ Protocol:	2.00+
   e.g. 0x0204 for version 2.04, and 0x0a11 for a hypothetical version
   10.17.
 
-Field name:	readmode_swtch
+Field name:	realmode_swtch
 Type:		modify (optional)
 Offset/size:	0x208/4
 Protocol:	2.00+
 
   Boot loader hook (see ADVANCED BOOT LOADER HOOKS below.)
 
-Field name:	start_sys
+Field name:	start_sys_seg
 Type:		read
 Offset/size:	0x20c/2
 Protocol:	2.00+
@@ -468,7 +469,7 @@ Protocol:	2.02+
   zero, the kernel will assume that your boot loader does not support
   the 2.02+ protocol.
 
-Field name:	initrd_addr_max
+Field name:	ramdisk_max
 Type:		read
 Offset/size:	0x22c/4
 Protocol:	2.03+
@@ -542,7 +543,10 @@ Protocol:	2.08+
 
   The payload may be compressed. The format of both the compressed and
   uncompressed data should be determined using the standard magic
-  numbers. Currently only gzip compressed ELF is used.
+  numbers.  The currently supported compression formats are gzip
+  (magic numbers 1F 8B or 1F 9E), bzip2 (magic number 42 5A) and LZMA
+  (magic number 5D 00).  The uncompressed payload is currently always ELF
+  (magic number 7F 45 4C 46).
 
 Field name:	payload_length
 Type:		read

Makefile

@@ -533,8 +533,9 @@ KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN})
 endif
 
 # Force gcc to behave correct even for buggy distributions
-# Arch Makefiles may override this setting
+ifndef CONFIG_CC_STACKPROTECTOR
 KBUILD_CFLAGS += $(call cc-option, -fno-stack-protector)
+endif
 
 ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS	+= -fno-omit-frame-pointer -fno-optimize-sibling-calls

arch/alpha/kernel/irq.c

@@ -55,7 +55,7 @@ int irq_select_affinity(unsigned int irq)
 		cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0);
 	last_cpu = cpu;
 
-	irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+	cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
 	irq_desc[irq].chip->set_affinity(irq, cpumask_of(cpu));
 	return 0;
 }

arch/alpha/mm/init.c

@@ -189,9 +189,21 @@ callback_init(void * kernel_end)
 
 	if (alpha_using_srm) {
 		static struct vm_struct console_remap_vm;
-		unsigned long vaddr = VMALLOC_START;
+		unsigned long nr_pages = 0;
+		unsigned long vaddr;
 		unsigned long i, j;
 
+		/* calculate needed size */
+		for (i = 0; i < crb->map_entries; ++i)
+			nr_pages += crb->map[i].count;
+
+		/* register the vm area */
+		console_remap_vm.flags = VM_ALLOC;
+		console_remap_vm.size = nr_pages << PAGE_SHIFT;
+		vm_area_register_early(&console_remap_vm, PAGE_SIZE);
+
+		vaddr = (unsigned long)console_remap_vm.addr;
+
 		/* Set up the third level PTEs and update the virtual
 		   addresses of the CRB entries.  */
 		for (i = 0; i < crb->map_entries; ++i) {
@@ -213,12 +225,6 @@ callback_init(void * kernel_end)
 				vaddr += PAGE_SIZE;
 			}
 		}
-
-		/* Let vmalloc know that we've allocated some space.  */
-		console_remap_vm.flags = VM_ALLOC;
-		console_remap_vm.addr = (void *) VMALLOC_START;
-		console_remap_vm.size = vaddr - VMALLOC_START;
-		vmlist = &console_remap_vm;
 	}
 
 	callback_init_done = 1;

arch/arm/kernel/irq.c

@@ -104,6 +104,11 @@ static struct irq_desc bad_irq_desc = {
 	.lock = __SPIN_LOCK_UNLOCKED(bad_irq_desc.lock),
 };
 
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* We are not allocating bad_irq_desc.affinity or .pending_mask */
+#error "ARM architecture does not support CONFIG_CPUMASK_OFFSTACK."
+#endif
+
 /*
  * do_IRQ handles all hardware IRQ's.  Decoded IRQs should not
  * come via this function.  Instead, they should provide their
@@ -161,7 +166,7 @@ void __init init_IRQ(void)
 		irq_desc[irq].status |= IRQ_NOREQUEST | IRQ_NOPROBE;
 
 #ifdef CONFIG_SMP
-	bad_irq_desc.affinity = CPU_MASK_ALL;
+	cpumask_setall(bad_irq_desc.affinity);
 	bad_irq_desc.cpu = smp_processor_id();
 #endif
 	init_arch_irq();
@@ -191,15 +196,16 @@ void migrate_irqs(void)
 		struct irq_desc *desc = irq_desc + i;
 
 		if (desc->cpu == cpu) {
-			unsigned int newcpu = any_online_cpu(desc->affinity);
-
-			if (newcpu == NR_CPUS) {
+			unsigned int newcpu = cpumask_any_and(desc->affinity,
+							      cpu_online_mask);
+			if (newcpu >= nr_cpu_ids) {
 				if (printk_ratelimit())
 					printk(KERN_INFO "IRQ%u no longer affine to CPU%u\n",
 					       i, cpu);
 
-				cpus_setall(desc->affinity);
-				newcpu = any_online_cpu(desc->affinity);
+				cpumask_setall(desc->affinity);
+				newcpu = cpumask_any_and(desc->affinity,
+							 cpu_online_mask);
 			}
 
 			route_irq(desc, i, newcpu);

arch/arm/kernel/vmlinux.lds.S

@@ -64,7 +64,9 @@ SECTIONS
 		__initramfs_end = .;
 #endif
 		. = ALIGN(4096);
+		__per_cpu_load = .;
 		__per_cpu_start = .;
+			*(.data.percpu.page_aligned)
 			*(.data.percpu)
 			*(.data.percpu.shared_aligned)
 		__per_cpu_end = .;

arch/arm/oprofile/op_model_mpcore.c

@@ -263,7 +263,7 @@ static void em_route_irq(int irq, unsigned int cpu)
 	const struct cpumask *mask = cpumask_of(cpu);
 
 	spin_lock_irq(&desc->lock);
-	desc->affinity = *mask;
+	cpumask_copy(desc->affinity, mask);
 	desc->chip->set_affinity(irq, mask);
 	spin_unlock_irq(&desc->lock);
 }

arch/avr32/Kconfig

@@ -181,7 +181,7 @@ source "kernel/Kconfig.preempt"
 config QUICKLIST
 	def_bool y
 
-config HAVE_ARCH_BOOTMEM_NODE
+config HAVE_ARCH_BOOTMEM
 	def_bool n
 
 config ARCH_HAVE_MEMORY_PRESENT

arch/blackfin/include/asm/percpu.h

@@ -3,14 +3,4 @@
 
 #include <asm-generic/percpu.h>
 
-#ifdef CONFIG_MODULES
-#define PERCPU_MODULE_RESERVE 8192
-#else
-#define PERCPU_MODULE_RESERVE 0
-#endif
-
-#define PERCPU_ENOUGH_ROOM \
-	(ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \
-	 PERCPU_MODULE_RESERVE)
-
 #endif	/* __ARCH_BLACKFIN_PERCPU__ */

arch/blackfin/kernel/irqchip.c

@@ -70,6 +70,11 @@ static struct irq_desc bad_irq_desc = {
 #endif
 };
 
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* We are not allocating a variable-sized bad_irq_desc.affinity */
+#error "Blackfin architecture does not support CONFIG_CPUMASK_OFFSTACK."
+#endif
+
 int show_interrupts(struct seq_file *p, void *v)
 {
 	int i = *(loff_t *) v, j;

arch/ia64/include/asm/percpu.h

@@ -27,12 +27,12 @@ extern void *per_cpu_init(void);
 
 #else /* ! SMP */
 
-#define PER_CPU_ATTRIBUTES	__attribute__((__section__(".data.percpu")))
-
 #define per_cpu_init()				(__phys_per_cpu_start)
 
 #endif	/* SMP */
 
+#define PER_CPU_BASE_SECTION ".data.percpu"
+
 /*
  * Be extremely careful when taking the address of this variable!  Due to virtual
  * remapping, it is different from the canonical address returned by __get_cpu_var(var)!

arch/ia64/include/asm/topology.h

@@ -84,7 +84,7 @@ void build_cpu_to_node_map(void);
 	.child			= NULL,			\
 	.groups			= NULL,			\
 	.min_interval		= 8,			\
-	.max_interval		= 8*(min(num_online_cpus(), 32)), \
+	.max_interval		= 8*(min(num_online_cpus(), 32U)), \
 	.busy_factor		= 64,			\
 	.imbalance_pct		= 125,			\
 	.cache_nice_tries	= 2,			\

arch/ia64/include/asm/uv/uv.h

@@ -0,0 +1,13 @@
+#ifndef _ASM_IA64_UV_UV_H
+#define _ASM_IA64_UV_UV_H
+
+#include <asm/system.h>
+#include <asm/sn/simulator.h>
+
+static inline int is_uv_system(void)
+{
+	/* temporary support for running on hardware simulator */
+	return IS_MEDUSA() || ia64_platform_is("uv");
+}
+
+#endif	/* _ASM_IA64_UV_UV_H */

arch/ia64/kernel/acpi.c

@@ -199,6 +199,10 @@ char *__init __acpi_map_table(unsigned long phys_addr, unsigned long size)
 	return __va(phys_addr);
 }
 
+void __init __acpi_unmap_table(char *map, unsigned long size)
+{
+}
+
 /* --------------------------------------------------------------------------
                             Boot-time Table Parsing
    -------------------------------------------------------------------------- */

arch/ia64/kernel/iosapic.c

@@ -880,7 +880,7 @@ iosapic_unregister_intr (unsigned int gsi)
 	if (iosapic_intr_info[irq].count == 0) {
 #ifdef CONFIG_SMP
 		/* Clear affinity */
-		cpus_setall(idesc->affinity);
+		cpumask_setall(idesc->affinity);
 #endif
 		/* Clear the interrupt information */
 		iosapic_intr_info[irq].dest = 0;

arch/ia64/kernel/irq.c

@@ -103,7 +103,7 @@ static char irq_redir [NR_IRQS]; // = { [0 ... NR_IRQS-1] = 1 };
 void set_irq_affinity_info (unsigned int irq, int hwid, int redir)
 {
 	if (irq < NR_IRQS) {
-		cpumask_copy(&irq_desc[irq].affinity,
+		cpumask_copy(irq_desc[irq].affinity,
 			     cpumask_of(cpu_logical_id(hwid)));
 		irq_redir[irq] = (char) (redir & 0xff);
 	}
@@ -148,7 +148,7 @@ static void migrate_irqs(void)
 		if (desc->status == IRQ_PER_CPU)
 			continue;
 
-		if (cpumask_any_and(&irq_desc[irq].affinity, cpu_online_mask)
+		if (cpumask_any_and(irq_desc[irq].affinity, cpu_online_mask)
 		    >= nr_cpu_ids) {
 			/*
 			 * Save it for phase 2 processing

arch/ia64/kernel/irq_ia64.c

@@ -493,16 +493,15 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs)
 	saved_tpr = ia64_getreg(_IA64_REG_CR_TPR);
 	ia64_srlz_d();
 	while (vector != IA64_SPURIOUS_INT_VECTOR) {
-		struct irq_desc *desc;
 		int irq = local_vector_to_irq(vector);
+		struct irq_desc *desc = irq_to_desc(irq);
 
-		desc = irq_desc + irq;
 		if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
 			smp_local_flush_tlb();
 			kstat_incr_irqs_this_cpu(irq, desc);
-		} else if (unlikely(IS_RESCHEDULE(vector)))
+		} else if (unlikely(IS_RESCHEDULE(vector))) {
 			kstat_incr_irqs_this_cpu(irq, desc);
-		else {
+		} else {
 			ia64_setreg(_IA64_REG_CR_TPR, vector);
 			ia64_srlz_d();
 
@@ -553,16 +552,15 @@ void ia64_process_pending_intr(void)
 	  * Perform normal interrupt style processing
 	  */
 	while (vector != IA64_SPURIOUS_INT_VECTOR) {
-		struct irq_desc *desc;
 		int irq = local_vector_to_irq(vector);
-		desc = irq_desc + irq;
+		struct irq_desc *desc = irq_to_desc(irq);
 
 		if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
 			smp_local_flush_tlb();
 			kstat_incr_irqs_this_cpu(irq, desc);
-		} else if (unlikely(IS_RESCHEDULE(vector)))
+		} else if (unlikely(IS_RESCHEDULE(vector))) {
 			kstat_incr_irqs_this_cpu(irq, desc);
-		else {
+		} else {
 			struct pt_regs *old_regs = set_irq_regs(NULL);
 
 			ia64_setreg(_IA64_REG_CR_TPR, vector);

arch/ia64/kernel/msi_ia64.c

@@ -38,7 +38,7 @@ static void ia64_set_msi_irq_affinity(unsigned int irq,
 	msg.data = data;
 
 	write_msi_msg(irq, &msg);
-	irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+	cpumask_copy(irq_desc[irq].affinity, cpumask_of(cpu));
 }
 #endif /* CONFIG_SMP */
 
@@ -150,7 +150,7 @@ static void dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID_CPU(cpu_physical_id(cpu));
 
 	dmar_msi_write(irq, &msg);
-	irq_desc[irq].affinity = *mask;
+	cpumask_copy(irq_desc[irq].affinity, mask);
 }
 #endif /* CONFIG_SMP */
 

arch/ia64/kernel/vmlinux.lds.S

@@ -213,16 +213,9 @@ SECTIONS
         { *(.data.cacheline_aligned) }
 
   /* Per-cpu data: */
-  percpu : { } :percpu
   . = ALIGN(PERCPU_PAGE_SIZE);
-  __phys_per_cpu_start = .;
-  .data.percpu PERCPU_ADDR : AT(__phys_per_cpu_start - LOAD_OFFSET)
-	{
-		__per_cpu_start = .;
-		*(.data.percpu)
-		*(.data.percpu.shared_aligned)
-		__per_cpu_end = .;
-	}
+  PERCPU_VADDR(PERCPU_ADDR, :percpu)
+  __phys_per_cpu_start = __per_cpu_load;
   . = __phys_per_cpu_start + PERCPU_PAGE_SIZE;	/* ensure percpu data fits
   						 * into percpu page size
 						 */