Merge branch 'core/percpu' into x86/core

Conflicts:
	kernel/irq/handle.c

include/asm-generic/percpu.h

@@ -80,4 +80,56 @@ extern void setup_per_cpu_areas(void);
 #define DECLARE_PER_CPU(type, name) extern PER_CPU_ATTRIBUTES \
 					__typeof__(type) per_cpu_var(name)
 
+/*
+ * Optional methods for optimized non-lvalue per-cpu variable access.
+ *
+ * @var can be a percpu variable or a field of it and its size should
+ * equal char, int or long.  percpu_read() evaluates to a lvalue and
+ * all others to void.
+ *
+ * These operations are guaranteed to be atomic w.r.t. preemption.
+ * The generic versions use plain get/put_cpu_var().  Archs are
+ * encouraged to implement single-instruction alternatives which don't
+ * require preemption protection.
+ */
+#ifndef percpu_read
+# define percpu_read(var)						\
+  ({									\
+	typeof(per_cpu_var(var)) __tmp_var__;				\
+	__tmp_var__ = get_cpu_var(var);					\
+	put_cpu_var(var);						\
+	__tmp_var__;							\
+  })
+#endif
+
+#define __percpu_generic_to_op(var, val, op)				\
+do {									\
+	get_cpu_var(var) op val;					\
+	put_cpu_var(var);						\
+} while (0)
+
+#ifndef percpu_write
+# define percpu_write(var, val)		__percpu_generic_to_op(var, (val), =)
+#endif
+
+#ifndef percpu_add
+# define percpu_add(var, val)		__percpu_generic_to_op(var, (val), +=)
+#endif
+
+#ifndef percpu_sub
+# define percpu_sub(var, val)		__percpu_generic_to_op(var, (val), -=)
+#endif
+
+#ifndef percpu_and
+# define percpu_and(var, val)		__percpu_generic_to_op(var, (val), &=)
+#endif
+
+#ifndef percpu_or
+# define percpu_or(var, val)		__percpu_generic_to_op(var, (val), |=)
+#endif
+
+#ifndef percpu_xor
+# define percpu_xor(var, val)		__percpu_generic_to_op(var, (val), ^=)
+#endif
+
 #endif /* _ASM_GENERIC_PERCPU_H_ */

include/asm-generic/sections.h

@@ -9,7 +9,7 @@ extern char __bss_start[], __bss_stop[];
 extern char __init_begin[], __init_end[];
 extern char _sinittext[], _einittext[];
 extern char _end[];
-extern char __per_cpu_start[], __per_cpu_end[];
+extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __start_rodata[], __end_rodata[];

include/asm-generic/vmlinux.lds.h

@@ -430,12 +430,48 @@
   	*(.initcall7.init)						\
   	*(.initcall7s.init)
 
-#define PERCPU(align)							\
-	. = ALIGN(align);						\
-	VMLINUX_SYMBOL(__per_cpu_start) = .;				\
-	.data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {		\
+/**
+ * PERCPU_VADDR - define output section for percpu area
+ * @vaddr: explicit base address (optional)
+ * @phdr: destination PHDR (optional)
+ *
+ * Macro which expands to output section for percpu area.  If @vaddr
+ * is not blank, it specifies explicit base address and all percpu
+ * symbols will be offset from the given address.  If blank, @vaddr
+ * always equals @laddr + LOAD_OFFSET.
+ *
+ * @phdr defines the output PHDR to use if not blank.  Be warned that
+ * output PHDR is sticky.  If @phdr is specified, the next output
+ * section in the linker script will go there too.  @phdr should have
+ * a leading colon.
+ *
+ * This macro defines three symbols, __per_cpu_load, __per_cpu_start
+ * and __per_cpu_end.  The first one is the vaddr of loaded percpu
+ * init data.  __per_cpu_start equals @vaddr and __per_cpu_end is the
+ * end offset.
+ */
+#define PERCPU_VADDR(vaddr, phdr)					\
+	VMLINUX_SYMBOL(__per_cpu_load_abs) = .;				\
+	.data.percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load_abs)	\
+				- LOAD_OFFSET) {			\
+		VMLINUX_SYMBOL(__per_cpu_start) = .;			\
+		VMLINUX_SYMBOL(__per_cpu_load) = LOADADDR(.data.percpu) + LOAD_OFFSET;\
+		*(.data.percpu.first)					\
 		*(.data.percpu.page_aligned)				\
 		*(.data.percpu)						\
 		*(.data.percpu.shared_aligned)				\
-	}								\
-	VMLINUX_SYMBOL(__per_cpu_end) = .;
+		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
+	} phdr								\
+	. = VMLINUX_SYMBOL(__per_cpu_load_abs) + SIZEOF(.data.percpu);
+
+/**
+ * PERCPU - define output section for percpu area, simple version
+ * @align: required alignment
+ *
+ * Align to @align and outputs output section for percpu area.  This
+ * macro doesn't maniuplate @vaddr or @phdr and __per_cpu_load and
+ * __per_cpu_start will be identical.
+ */
+#define PERCPU(align)							\
+	. = ALIGN(align);						\
+	PERCPU_VADDR( , )

include/linux/interrupt.h

@@ -467,6 +467,7 @@ int show_interrupts(struct seq_file *p, void *v);
 struct irq_desc;
 
 extern int early_irq_init(void);
+extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
 extern int arch_init_chip_data(struct irq_desc *desc, int cpu);
 

include/linux/irq.h

@@ -182,11 +182,11 @@ struct irq_desc {
 	unsigned int		irqs_unhandled;
 	spinlock_t		lock;
 #ifdef CONFIG_SMP
-	cpumask_t		affinity;
+	cpumask_var_t		affinity;
 	unsigned int		cpu;
-#endif
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_t		pending_mask;
+	cpumask_var_t		pending_mask;
+#endif
 #endif
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry	*dir;
@@ -422,4 +422,84 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 
 #endif /* !CONFIG_S390 */
 
+#ifdef CONFIG_SMP
+/**
+ * init_alloc_desc_masks - allocate cpumasks for irq_desc
+ * @desc:	pointer to irq_desc struct
+ * @cpu:	cpu which will be handling the cpumasks
+ * @boot:	true if need bootmem
+ *
+ * Allocates affinity and pending_mask cpumask if required.
+ * Returns true if successful (or not required).
+ * Side effect: affinity has all bits set, pending_mask has all bits clear.
+ */
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+								bool boot)
+{
+	int node;
+
+	if (boot) {
+		alloc_bootmem_cpumask_var(&desc->affinity);
+		cpumask_setall(desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+		alloc_bootmem_cpumask_var(&desc->pending_mask);
+		cpumask_clear(desc->pending_mask);
+#endif
+		return true;
+	}
+
+	node = cpu_to_node(cpu);
+
+	if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
+		return false;
+	cpumask_setall(desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) {
+		free_cpumask_var(desc->affinity);
+		return false;
+	}
+	cpumask_clear(desc->pending_mask);
+#endif
+	return true;
+}
+
+/**
+ * init_copy_desc_masks - copy cpumasks for irq_desc
+ * @old_desc:	pointer to old irq_desc struct
+ * @new_desc:	pointer to new irq_desc struct
+ *
+ * Insures affinity and pending_masks are copied to new irq_desc.
+ * If !CONFIG_CPUMASKS_OFFSTACK the cpumasks are embedded in the
+ * irq_desc struct so the copy is redundant.
+ */
+
+static inline void init_copy_desc_masks(struct irq_desc *old_desc,
+					struct irq_desc *new_desc)
+{
+#ifdef CONFIG_CPUMASKS_OFFSTACK
+	cpumask_copy(new_desc->affinity, old_desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_copy(new_desc->pending_mask, old_desc->pending_mask);
+#endif
+#endif
+}
+
+#else /* !CONFIG_SMP */
+
+static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+								bool boot)
+{
+	return true;
+}
+
+static inline void init_copy_desc_masks(struct irq_desc *old_desc,
+					struct irq_desc *new_desc)
+{
+}
+
+#endif	/* CONFIG_SMP */
+
 #endif /* _LINUX_IRQ_H */

include/linux/irqnr.h

@@ -20,6 +20,7 @@
 
 # define for_each_irq_desc_reverse(irq, desc)                          \
 	for (irq = nr_irqs - 1; irq >= 0; irq--)
+
 #else /* CONFIG_GENERIC_HARDIRQS */
 
 extern int nr_irqs;

include/linux/magic.h

@@ -49,4 +49,5 @@
 #define FUTEXFS_SUPER_MAGIC	0xBAD1DEA
 #define INOTIFYFS_SUPER_MAGIC	0x2BAD1DEA
 
+#define STACK_END_MAGIC		0x57AC6E9D
 #endif /* __LINUX_MAGIC_H__ */

include/linux/percpu.h

@@ -9,34 +9,39 @@
 #include <asm/percpu.h>
 
 #ifdef CONFIG_SMP
-#define DEFINE_PER_CPU(type, name)					\
-	__attribute__((__section__(".data.percpu")))			\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+#define PER_CPU_BASE_SECTION ".data.percpu"
 
 #ifdef MODULE
-#define SHARED_ALIGNED_SECTION ".data.percpu"
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
 #else
-#define SHARED_ALIGNED_SECTION ".data.percpu.shared_aligned"
+#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned"
 #endif
+#define PER_CPU_FIRST_SECTION ".first"
+
+#else
+
+#define PER_CPU_BASE_SECTION ".data"
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
+#define PER_CPU_FIRST_SECTION ""
+
+#endif
+
+#define DEFINE_PER_CPU_SECTION(type, name, section)			\
+	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
+	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+
+#define DEFINE_PER_CPU(type, name)					\
+	DEFINE_PER_CPU_SECTION(type, name, "")
 
 #define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)			\
-	__attribute__((__section__(SHARED_ALIGNED_SECTION)))		\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name		\
+	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
 	____cacheline_aligned_in_smp
 
-#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)			\
-	__attribute__((__section__(".data.percpu.page_aligned")))	\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
-#else
-#define DEFINE_PER_CPU(type, name)					\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)				\
+	DEFINE_PER_CPU_SECTION(type, name, ".page_aligned")
 
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name)		      \
-	DEFINE_PER_CPU(type, name)
-
-#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)		      \
-	DEFINE_PER_CPU(type, name)
-#endif
+#define DEFINE_PER_CPU_FIRST(type, name)				\
+	DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
 
 #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
 #define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)

include/linux/sched.h

@@ -1161,10 +1161,9 @@ struct task_struct {
 	pid_t pid;
 	pid_t tgid;
 
-#ifdef CONFIG_CC_STACKPROTECTOR
 	/* Canary value for the -fstack-protector gcc feature */
 	unsigned long stack_canary;
-#endif
+
 	/* 
 	 * pointers to (original) parent process, youngest child, younger sibling,
 	 * older sibling, respectively.  (p->father can be replaced with 
@@ -2070,6 +2069,19 @@ static inline int object_is_on_stack(void *obj)
 
 extern void thread_info_cache_init(void);
 
+#ifdef CONFIG_DEBUG_STACK_USAGE
+static inline unsigned long stack_not_used(struct task_struct *p)
+{
+	unsigned long *n = end_of_stack(p);
+
+	do { 	/* Skip over canary */
+		n++;
+	} while (!*n);
+
+	return (unsigned long)n - (unsigned long)end_of_stack(p);
+}
+#endif
+
 /* set thread flags in other task's structures
  * - see asm/thread_info.h for TIF_xxxx flags available
  */

include/linux/stackprotector.h

@@ -0,0 +1,16 @@
+#ifndef _LINUX_STACKPROTECTOR_H
+#define _LINUX_STACKPROTECTOR_H 1
+
+#include <linux/compiler.h>
+#include <linux/sched.h>
+#include <linux/random.h>
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+# include <asm/stackprotector.h>
+#else
+static inline void boot_init_stack_canary(void)
+{
+}
+#endif
+
+#endif

include/linux/topology.h

@@ -193,5 +193,11 @@ int arch_update_cpu_topology(void);
 #ifndef topology_core_siblings
 #define topology_core_siblings(cpu)		cpumask_of_cpu(cpu)
 #endif
+#ifndef topology_thread_cpumask
+#define topology_thread_cpumask(cpu)		cpumask_of(cpu)
+#endif
+#ifndef topology_core_cpumask
+#define topology_core_cpumask(cpu)		cpumask_of(cpu)
+#endif
 
 #endif /* _LINUX_TOPOLOGY_H */