Merge branch 'core/percpu' into stackprotector

Conflicts:
	arch/x86/include/asm/pda.h
	arch/x86/include/asm/system.h

Also, moved include/asm-x86/stackprotector.h to arch/x86/include/asm.

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

12 files changed, 159 insertions, 23 deletions

diff --git a/include/asm-generic/bitops/__ffs.h b/include/asm-generic/bitops/__ffs.h
index 9a3274aecf83..937d7c435575 100644
--- a/include/asm-generic/bitops/__ffs.h
+++ b/include/asm-generic/bitops/__ffs.h
@@ -9,7 +9,7 @@
  *
  * Undefined if no bit exists, so code should check against 0 first.
  */
-static inline unsigned long __ffs(unsigned long word)
+static __always_inline unsigned long __ffs(unsigned long word)
 {
 	int num = 0;
 
diff --git a/include/asm-generic/bitops/__fls.h b/include/asm-generic/bitops/__fls.h
index be24465403d6..a60a7ccb6782 100644
--- a/include/asm-generic/bitops/__fls.h
+++ b/include/asm-generic/bitops/__fls.h
@@ -9,7 +9,7 @@
  *
  * Undefined if no set bit exists, so code should check against 0 first.
  */
-static inline unsigned long __fls(unsigned long word)
+static __always_inline unsigned long __fls(unsigned long word)
 {
 	int num = BITS_PER_LONG - 1;
 
diff --git a/include/asm-generic/bitops/fls.h b/include/asm-generic/bitops/fls.h
index 850859bc5069..0576d1f42f43 100644
--- a/include/asm-generic/bitops/fls.h
+++ b/include/asm-generic/bitops/fls.h
@@ -9,7 +9,7 @@
  * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
  */
 
-static inline int fls(int x)
+static __always_inline int fls(int x)
 {
 	int r = 32;
 
diff --git a/include/asm-generic/bitops/fls64.h b/include/asm-generic/bitops/fls64.h
index 86d403f8b256..b097cf8444e3 100644
--- a/include/asm-generic/bitops/fls64.h
+++ b/include/asm-generic/bitops/fls64.h
@@ -15,7 +15,7 @@
  * at position 64.
  */
 #if BITS_PER_LONG == 32
-static inline int fls64(__u64 x)
+static __always_inline int fls64(__u64 x)
 {
 	__u32 h = x >> 32;
 	if (h)
@@ -23,7 +23,7 @@ static inline int fls64(__u64 x)
 	return fls(x);
 }
 #elif BITS_PER_LONG == 64
-static inline int fls64(__u64 x)
+static __always_inline int fls64(__u64 x)
 {
 	if (x == 0)
 		return 0;
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 8af276361bf2..37b82cb96c89 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -28,6 +28,17 @@ struct bug_entry {
 #define BUGFLAG_WARNING	(1<<0)
 #endif	/* CONFIG_GENERIC_BUG */
 
+/*
+ * Don't use BUG() or BUG_ON() unless there's really no way out; one
+ * example might be detecting data structure corruption in the middle
+ * of an operation that can't be backed out of.  If the (sub)system
+ * can somehow continue operating, perhaps with reduced functionality,
+ * it's probably not BUG-worthy.
+ *
+ * If you're tempted to BUG(), think again:  is completely giving up
+ * really the *only* solution?  There are usually better options, where
+ * users don't need to reboot ASAP and can mostly shut down cleanly.
+ */
 #ifndef HAVE_ARCH_BUG
 #define BUG() do { \
 	printk("BUG: failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); \
@@ -39,6 +50,12 @@ struct bug_entry {
 #define BUG_ON(condition) do { if (unlikely(condition)) BUG(); } while(0)
 #endif
 
+/*
+ * WARN(), WARN_ON(), WARN_ON_ONCE, and so on can be used to report
+ * significant issues that need prompt attention if they should ever
+ * appear at runtime.  Use the versions with printk format strings
+ * to provide better diagnostics.
+ */
 #ifndef __WARN
 #ifndef __ASSEMBLY__
 extern void warn_slowpath(const char *file, const int line,
diff --git a/include/asm-generic/local.h b/include/asm-generic/local.h
index 33d7d04e4119..dbd6150763e9 100644
--- a/include/asm-generic/local.h
+++ b/include/asm-generic/local.h
@@ -2,7 +2,6 @@
 #define _ASM_GENERIC_LOCAL_H
 
 #include <linux/percpu.h>
-#include <linux/hardirq.h>
 #include <asm/atomic.h>
 #include <asm/types.h>
 
diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h
index 36fa286adad5..4c8d0afae711 100644
--- a/include/asm-generic/memory_model.h
+++ b/include/asm-generic/memory_model.h
@@ -69,15 +69,8 @@
 })
 #endif /* CONFIG_FLATMEM/DISCONTIGMEM/SPARSEMEM */
 
-#ifdef CONFIG_OUT_OF_LINE_PFN_TO_PAGE
-struct page;
-/* this is useful when inlined pfn_to_page is too big */
-extern struct page *pfn_to_page(unsigned long pfn);
-extern unsigned long page_to_pfn(struct page *page);
-#else
 #define page_to_pfn __page_to_pfn
 #define pfn_to_page __pfn_to_page
-#endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index b0e63c672ebd..00f45ff081a6 100644
--- a/include/asm-generic/percpu.h
+++ b/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_ */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 72ebe91005a8..8e6d0ca70aba 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -301,7 +301,7 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
  * track_pfn_vma_new is called when a _new_ pfn mapping is being established
  * for physical range indicated by pfn and size.
  */
-static inline int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+static inline int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
 					unsigned long pfn, unsigned long size)
 {
 	return 0;
@@ -332,7 +332,7 @@ static inline void untrack_pfn_vma(struct vm_area_struct *vma,
 {
 }
 #else
-extern int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+extern int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
 				unsigned long pfn, unsigned long size);
 extern int track_pfn_vma_copy(struct vm_area_struct *vma);
 extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 79a7ff925bf8..4ce48e878530 100644
--- a/include/asm-generic/sections.h
+++ b/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[];
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 54bbf6e04ee8..0e9e2bc0ee96 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -40,6 +40,9 @@
 #ifndef node_to_cpumask
 #define node_to_cpumask(node)	((void)node, cpu_online_map)
 #endif
+#ifndef cpumask_of_node
+#define cpumask_of_node(node)	((void)node, cpu_online_mask)
+#endif
 #ifndef node_to_first_cpu
 #define node_to_first_cpu(node)	((void)(node),0)
 #endif
@@ -54,9 +57,18 @@
 				)
 #endif
 
+#ifndef cpumask_of_pcibus
+#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
+				 cpu_all_mask :				\
+				 cpumask_of_node(pcibus_to_node(bus)))
+#endif
+
 #endif	/* CONFIG_NUMA */
 
-/* returns pointer to cpumask for specified node */
+/*
+ * returns pointer to cpumask for specified node
+ * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
+ */
 #ifndef node_to_cpumask_ptr
 
 #define	node_to_cpumask_ptr(v, node) 					\
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index c61fab1dd2f8..aa6b9b1b30b5 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -430,12 +430,75 @@
   	*(.initcall7.init)						\
   	*(.initcall7s.init)
 
-#define PERCPU(align)							\
-	. = ALIGN(align);						\
-	VMLINUX_SYMBOL(__per_cpu_start) = .;				\
-	.data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) {		\
+#define PERCPU_PROLOG(vaddr)						\
+	VMLINUX_SYMBOL(__per_cpu_load) = .;				\
+	.data.percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load)		\
+				- LOAD_OFFSET) {			\
+		VMLINUX_SYMBOL(__per_cpu_start) = .;
+
+#define PERCPU_EPILOG(phdr)						\
+		VMLINUX_SYMBOL(__per_cpu_end) = .;			\
+	} phdr								\
+	. = VMLINUX_SYMBOL(__per_cpu_load) + SIZEOF(.data.percpu);
+
+/**
+ * PERCPU_VADDR_PREALLOC - define output section for percpu area with prealloc
+ * @vaddr: explicit base address (optional)
+ * @phdr: destination PHDR (optional)
+ * @prealloc: the size of prealloc area
+ *
+ * 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.
+ *
+ * If @prealloc is non-zero, the specified number of bytes will be
+ * reserved at the start of percpu area.  As the prealloc area is
+ * likely to break alignment, this macro puts areas in increasing
+ * alignment order.
+ *
+ * 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_PREALLOC(vaddr, segment, prealloc)			\
+	PERCPU_PROLOG(vaddr)						\
+		. += prealloc;						\
+		*(.data.percpu)						\
+		*(.data.percpu.shared_aligned)				\
+		*(.data.percpu.page_aligned)				\
+	PERCPU_EPILOG(segment)
+
+/**
+ * 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.  Mostly
+ * identical to PERCPU_VADDR_PREALLOC(@vaddr, @phdr, 0) other than
+ * using slighly different layout.
+ */
+#define PERCPU_VADDR(vaddr, phdr)					\
+	PERCPU_PROLOG(vaddr)						\
 		*(.data.percpu.page_aligned)				\
 		*(.data.percpu)						\
 		*(.data.percpu.shared_aligned)				\
-	}								\
-	VMLINUX_SYMBOL(__per_cpu_end) = .;
+	PERCPU_EPILOG(phdr)
+
+/**
+ * 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( , )