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:
  percpu: update comments to reflect that percpu allocations are always zero-filled
  percpu: Optimize __get_cpu_var()
  x86, percpu: Optimize this_cpu_ptr
  percpu: clear memory allocated with the km allocator
  percpu: fix build breakage on s390 and cleanup build configuration tests
  percpu: use percpu allocator on UP too
  percpu: reduce PCPU_MIN_UNIT_SIZE to 32k
  vmalloc: pcpu_get/free_vm_areas() aren't needed on UP

Fixed up trivial conflicts in include/linux/percpu.h

arch/x86/include/asm/percpu.h

@@ -47,6 +47,20 @@
 #ifdef CONFIG_SMP
 #define __percpu_arg(x)		"%%"__stringify(__percpu_seg)":%P" #x
 #define __my_cpu_offset		percpu_read(this_cpu_off)
+
+/*
+ * Compared to the generic __my_cpu_offset version, the following
+ * saves one instruction and avoids clobbering a temp register.
+ */
+#define __this_cpu_ptr(ptr)				\
+({							\
+	unsigned long tcp_ptr__;			\
+	__verify_pcpu_ptr(ptr);				\
+	asm volatile("add " __percpu_arg(1) ", %0"	\
+		     : "=r" (tcp_ptr__)			\
+		     : "m" (this_cpu_off), "0" (ptr));	\
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;	\
+})
 #else
 #define __percpu_arg(x)		"%P" #x
 #endif

include/asm-generic/percpu.h

@@ -55,14 +55,18 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
  */
 #define per_cpu(var, cpu) \
 	(*SHIFT_PERCPU_PTR(&(var), per_cpu_offset(cpu)))
-#define __get_cpu_var(var) \
-	(*SHIFT_PERCPU_PTR(&(var), my_cpu_offset))
-#define __raw_get_cpu_var(var) \
-	(*SHIFT_PERCPU_PTR(&(var), __my_cpu_offset))
 
-#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+#ifndef __this_cpu_ptr
 #define __this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
+#endif
+#ifdef CONFIG_DEBUG_PREEMPT
+#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+#else
+#define this_cpu_ptr(ptr) __this_cpu_ptr(ptr)
+#endif
 
+#define __get_cpu_var(var) (*this_cpu_ptr(&(var)))
+#define __raw_get_cpu_var(var) (*__this_cpu_ptr(&(var)))
 
 #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
 extern void setup_per_cpu_areas(void);

include/linux/percpu.h

@@ -48,10 +48,8 @@
 	preempt_enable();				\
 } while (0)
 
-#ifdef CONFIG_SMP
-
 /* minimum unit size, also is the maximum supported allocation size */
-#define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(64 << 10)
+#define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(32 << 10)
 
 /*
  * Percpu allocator can serve percpu allocations before slab is
@@ -146,37 +144,20 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size,
  * dynamically allocated. Non-atomic access to the current CPU's
  * version should probably be combined with get_cpu()/put_cpu().
  */
+#ifdef CONFIG_SMP
 #define per_cpu_ptr(ptr, cpu)	SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
+#else
+#define per_cpu_ptr(ptr, cpu)	({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); })
+#endif
 
 extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
 extern bool is_kernel_percpu_address(unsigned long addr);
 
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
+#if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
 extern void __init setup_per_cpu_areas(void);
 #endif
 extern void __init percpu_init_late(void);
 
-#else /* CONFIG_SMP */
-
-#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); })
-
-/* can't distinguish from other static vars, always false */
-static inline bool is_kernel_percpu_address(unsigned long addr)
-{
-	return false;
-}
-
-static inline void __init setup_per_cpu_areas(void) { }
-
-static inline void __init percpu_init_late(void) { }
-
-static inline void *pcpu_lpage_remapped(void *kaddr)
-{
-	return NULL;
-}
-
-#endif /* CONFIG_SMP */
-
 extern void __percpu *__alloc_percpu(size_t size, size_t align);
 extern void free_percpu(void __percpu *__pdata);
 extern phys_addr_t per_cpu_ptr_to_phys(void *addr);

include/linux/vmalloc.h

@@ -117,10 +117,12 @@ extern rwlock_t vmlist_lock;
 extern struct vm_struct *vmlist;
 extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
 
+#ifdef CONFIG_SMP
 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
 
 #endif /* _LINUX_VMALLOC_H */

mm/Kconfig

@@ -301,3 +301,11 @@ config NOMMU_INITIAL_TRIM_EXCESS
 	  of 1 says that all excess pages should be trimmed.
 
 	  See Documentation/nommu-mmap.txt for more information.
+
+#
+# UP and nommu archs use km based percpu allocator
+#
+config NEED_PER_CPU_KM
+	depends on !SMP
+	bool
+	default y

mm/Makefile

@@ -11,7 +11,7 @@ obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
-			   page_isolation.o mm_init.o mmu_context.o \
+			   page_isolation.o mm_init.o mmu_context.o percpu.o \
 			   $(mmu-y)
 obj-y += init-mm.o
 
@@ -36,11 +36,6 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
-ifdef CONFIG_SMP
-obj-y += percpu.o
-else
-obj-y += percpu_up.o
-endif
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o

mm/percpu-km.c

@@ -27,7 +27,7 @@
  *   chunk size is not aligned.  percpu-km code will whine about it.
  */
 
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+#if defined(CONFIG_SMP) && defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
 #error "contiguous percpu allocation is incompatible with paged first chunk"
 #endif
 
@@ -35,7 +35,11 @@
 
 static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
 {
-	/* noop */
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
+
 	return 0;
 }
 

mm/percpu_up.c

-/*
- * mm/percpu_up.c - dummy percpu memory allocator implementation for UP
- */
-
-#include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/slab.h>
-
-void __percpu *__alloc_percpu(size_t size, size_t align)
-{
-	/*
-	 * Can't easily make larger alignment work with kmalloc.  WARN
-	 * on it.  Larger alignment should only be used for module
-	 * percpu sections on SMP for which this path isn't used.
-	 */
-	WARN_ON_ONCE(align > SMP_CACHE_BYTES);
-	return (void __percpu __force *)kzalloc(size, GFP_KERNEL);
-}
-EXPORT_SYMBOL_GPL(__alloc_percpu);
-
-void free_percpu(void __percpu *p)
-{
-	kfree(this_cpu_ptr(p));
-}
-EXPORT_SYMBOL_GPL(free_percpu);
-
-phys_addr_t per_cpu_ptr_to_phys(void *addr)
-{
-	return __pa(addr);
-}

mm/vmalloc.c

@@ -2065,6 +2065,7 @@ void free_vm_area(struct vm_struct *area)
 }
 EXPORT_SYMBOL_GPL(free_vm_area);
 
+#ifdef CONFIG_SMP
 static struct vmap_area *node_to_va(struct rb_node *n)
 {
 	return n ? rb_entry(n, struct vmap_area, rb_node) : NULL;
@@ -2345,6 +2346,7 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
 		free_vm_area(vms[i]);
 	kfree(vms);
 }
+#endif	/* CONFIG_SMP */
 
 #ifdef CONFIG_PROC_FS
 static void *s_start(struct seq_file *m, loff_t *pos)