Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (46 commits)
  powerpc64: convert to dynamic percpu allocator
  sparc64: use embedding percpu first chunk allocator
  percpu: kill lpage first chunk allocator
  x86,percpu: use embedding for 64bit NUMA and page for 32bit NUMA
  percpu: update embedding first chunk allocator to handle sparse units
  percpu: use group information to allocate vmap areas sparsely
  vmalloc: implement pcpu_get_vm_areas()
  vmalloc: separate out insert_vmalloc_vm()
  percpu: add chunk->base_addr
  percpu: add pcpu_unit_offsets[]
  percpu: introduce pcpu_alloc_info and pcpu_group_info
  percpu: move pcpu_lpage_build_unit_map() and pcpul_lpage_dump_cfg() upward
  percpu: add @align to pcpu_fc_alloc_fn_t
  percpu: make @dyn_size mandatory for pcpu_setup_first_chunk()
  percpu: drop @static_size from first chunk allocators
  percpu: generalize first chunk allocator selection
  percpu: build first chunk allocators selectively
  percpu: rename 4k first chunk allocator to page
  percpu: improve boot messages
  percpu: fix pcpu_reclaim() locking
  ...

Fix trivial conflict as by Tejun Heo in kernel/sched.c

3 files changed, 138 insertions, 22 deletions

diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 0761491b3ee..9bd03193ecd 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -10,22 +10,70 @@
 /*
  * Base implementations of per-CPU variable declarations and definitions, where
  * the section in which the variable is to be placed is provided by the
- * 'section' argument.  This may be used to affect the parameters governing the
+ * 'sec' argument.  This may be used to affect the parameters governing the
  * variable's storage.
  *
  * NOTE!  The sections for the DECLARE and for the DEFINE must match, lest
  * linkage errors occur due the compiler generating the wrong code to access
  * that section.
  */
-#define DECLARE_PER_CPU_SECTION(type, name, section)			\
-	extern								\
-	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
-	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
-
-#define DEFINE_PER_CPU_SECTION(type, name, section)			\
-	__attribute__((__section__(PER_CPU_BASE_SECTION section)))	\
-	PER_CPU_ATTRIBUTES PER_CPU_DEF_ATTRIBUTES			\
+#define __PCPU_ATTRS(sec)						\
+	__attribute__((section(PER_CPU_BASE_SECTION sec)))		\
+	PER_CPU_ATTRIBUTES
+
+#define __PCPU_DUMMY_ATTRS						\
+	__attribute__((section(".discard"), unused))
+
+/*
+ * s390 and alpha modules require percpu variables to be defined as
+ * weak to force the compiler to generate GOT based external
+ * references for them.  This is necessary because percpu sections
+ * will be located outside of the usually addressable area.
+ *
+ * This definition puts the following two extra restrictions when
+ * defining percpu variables.
+ *
+ * 1. The symbol must be globally unique, even the static ones.
+ * 2. Static percpu variables cannot be defined inside a function.
+ *
+ * Archs which need weak percpu definitions should define
+ * ARCH_NEEDS_WEAK_PER_CPU in asm/percpu.h when necessary.
+ *
+ * To ensure that the generic code observes the above two
+ * restrictions, if CONFIG_DEBUG_FORCE_WEAK_PER_CPU is set weak
+ * definition is used for all cases.
+ */
+#if defined(ARCH_NEEDS_WEAK_PER_CPU) || defined(CONFIG_DEBUG_FORCE_WEAK_PER_CPU)
+/*
+ * __pcpu_scope_* dummy variable is used to enforce scope.  It
+ * receives the static modifier when it's used in front of
+ * DEFINE_PER_CPU() and will trigger build failure if
+ * DECLARE_PER_CPU() is used for the same variable.
+ *
+ * __pcpu_unique_* dummy variable is used to enforce symbol uniqueness
+ * such that hidden weak symbol collision, which will cause unrelated
+ * variables to share the same address, can be detected during build.
+ */
+#define DECLARE_PER_CPU_SECTION(type, name, sec)			\
+	extern __PCPU_DUMMY_ATTRS char __pcpu_scope_##name;		\
+	extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name
+
+#define DEFINE_PER_CPU_SECTION(type, name, sec)				\
+	__PCPU_DUMMY_ATTRS char __pcpu_scope_##name;			\
+	__PCPU_DUMMY_ATTRS char __pcpu_unique_##name;			\
+	__PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak			\
+	__typeof__(type) per_cpu__##name
+#else
+/*
+ * Normal declaration and definition macros.
+ */
+#define DECLARE_PER_CPU_SECTION(type, name, sec)			\
+	extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name
+
+#define DEFINE_PER_CPU_SECTION(type, name, sec)				\
+	__PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES			\
 	__typeof__(type) per_cpu__##name
+#endif
 
 /*
  * Variant on the per-CPU variable declaration/definition theme used for
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 26fd9d12f05..878836ca999 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -34,7 +34,7 @@
 
 #ifdef CONFIG_SMP
 
-#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
 
 /* minimum unit size, also is the maximum supported allocation size */
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(64 << 10)
@@ -57,19 +57,70 @@
 #endif
 
 extern void *pcpu_base_addr;
+extern const unsigned long *pcpu_unit_offsets;
 
-typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno);
-typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr);
+struct pcpu_group_info {
+	int			nr_units;	/* aligned # of units */
+	unsigned long		base_offset;	/* base address offset */
+	unsigned int		*cpu_map;	/* unit->cpu map, empty
+						 * entries contain NR_CPUS */
+};
+
+struct pcpu_alloc_info {
+	size_t			static_size;
+	size_t			reserved_size;
+	size_t			dyn_size;
+	size_t			unit_size;
+	size_t			atom_size;
+	size_t			alloc_size;
+	size_t			__ai_size;	/* internal, don't use */
+	int			nr_groups;	/* 0 if grouping unnecessary */
+	struct pcpu_group_info	groups[];
+};
 
-extern size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
-				size_t static_size, size_t reserved_size,
-				ssize_t dyn_size, ssize_t unit_size,
-				void *base_addr,
-				pcpu_populate_pte_fn_t populate_pte_fn);
+enum pcpu_fc {
+	PCPU_FC_AUTO,
+	PCPU_FC_EMBED,
+	PCPU_FC_PAGE,
 
-extern ssize_t __init pcpu_embed_first_chunk(
-				size_t static_size, size_t reserved_size,
-				ssize_t dyn_size, ssize_t unit_size);
+	PCPU_FC_NR,
+};
+extern const char *pcpu_fc_names[PCPU_FC_NR];
+
+extern enum pcpu_fc pcpu_chosen_fc;
+
+typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size,
+				     size_t align);
+typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size);
+typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr);
+typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to);
+
+extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
+							     int nr_units);
+extern void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai);
+
+extern struct pcpu_alloc_info * __init pcpu_build_alloc_info(
+				size_t reserved_size, ssize_t dyn_size,
+				size_t atom_size,
+				pcpu_fc_cpu_distance_fn_t cpu_distance_fn);
+
+extern int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
+					 void *base_addr);
+
+#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
+extern int __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size,
+				size_t atom_size,
+				pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
+				pcpu_fc_alloc_fn_t alloc_fn,
+				pcpu_fc_free_fn_t free_fn);
+#endif
+
+#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+extern int __init pcpu_page_first_chunk(size_t reserved_size,
+				pcpu_fc_alloc_fn_t alloc_fn,
+				pcpu_fc_free_fn_t free_fn,
+				pcpu_fc_populate_pte_fn_t populate_pte_fn);
+#endif
 
 /*
  * Use this to get to a cpu's version of the per-cpu object
@@ -80,7 +131,7 @@ extern ssize_t __init pcpu_embed_first_chunk(
 
 extern void *__alloc_reserved_percpu(size_t size, size_t align);
 
-#else /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#else /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 struct percpu_data {
 	void *ptrs[1];
@@ -99,11 +150,15 @@ struct percpu_data {
         (__typeof__(ptr))__p->ptrs[(cpu)];				\
 })
 
-#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
 
 extern void *__alloc_percpu(size_t size, size_t align);
 extern void free_percpu(void *__pdata);
 
+#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+extern void __init setup_per_cpu_areas(void);
+#endif
+
 #else /* CONFIG_SMP */
 
 #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
@@ -124,6 +179,13 @@ static inline void free_percpu(void *p)
 	kfree(p);
 }
 
+static inline void __init setup_per_cpu_areas(void) { }
+
+static inline void *pcpu_lpage_remapped(void *kaddr)
+{
+	return NULL;
+}
+
 #endif /* CONFIG_SMP */
 
 #define alloc_percpu(type)	(type *)__alloc_percpu(sizeof(type), \
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index a43ebec3a7b..227c2a585e4 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -115,4 +115,10 @@ extern rwlock_t vmlist_lock;
 extern struct vm_struct *vmlist;
 extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
 
+struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
+				     const size_t *sizes, int nr_vms,
+				     size_t align, gfp_t gfp_mask);
+
+void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms);
+
 #endif /* _LINUX_VMALLOC_H */