#include <linux/slab.h> /* For kmalloc() */
#include <linux/smp.h>
#include <linux/cpumask.h>
+#include <linux/pfn.h>
#include <asm/percpu.h>
+#ifndef PER_CPU_BASE_SECTION
#ifdef CONFIG_SMP
-#define DEFINE_PER_CPU(type, name) \
- __attribute__((__section__(".data.percpu"))) \
+#define PER_CPU_BASE_SECTION ".data.percpu"
+#else
+#define PER_CPU_BASE_SECTION ".data"
+#endif
+#endif
+
+#ifdef CONFIG_SMP
+
+#ifdef MODULE
+#define PER_CPU_SHARED_ALIGNED_SECTION ""
+#else
+#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned"
+#endif
+#define PER_CPU_FIRST_SECTION ".first"
+
+#else
+
+#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__(".data.percpu.shared_aligned"))) \
- PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name \
+ DEFINE_PER_CPU_SECTION(type, name, PER_CPU_SHARED_ALIGNED_SECTION) \
____cacheline_aligned_in_smp
-#else
-#define DEFINE_PER_CPU(type, name) \
- PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
-#define DEFINE_PER_CPU_SHARED_ALIGNED(type, name) \
- DEFINE_PER_CPU(type, name)
-#endif
+#define DEFINE_PER_CPU_PAGE_ALIGNED(type, name) \
+ DEFINE_PER_CPU_SECTION(type, name, ".page_aligned")
+
+#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)
-/* Enough to cover all DEFINE_PER_CPUs in kernel, including modules. */
-#ifndef PERCPU_ENOUGH_ROOM
+/* enough to cover all DEFINE_PER_CPUs in modules */
#ifdef CONFIG_MODULES
-#define PERCPU_MODULE_RESERVE 8192
+#define PERCPU_MODULE_RESERVE (8 << 10)
#else
-#define PERCPU_MODULE_RESERVE 0
+#define PERCPU_MODULE_RESERVE 0
#endif
+#ifndef PERCPU_ENOUGH_ROOM
#define PERCPU_ENOUGH_ROOM \
- (__per_cpu_end - __per_cpu_start + PERCPU_MODULE_RESERVE)
-#endif /* PERCPU_ENOUGH_ROOM */
+ (ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES) + \
+ PERCPU_MODULE_RESERVE)
+#endif
/*
* Must be an lvalue. Since @var must be a simple identifier,
#ifdef CONFIG_SMP
+#ifdef CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
+
+/* minimum unit size, also is the maximum supported allocation size */
+#define PCPU_MIN_UNIT_SIZE PFN_ALIGN(64 << 10)
+
+/*
+ * PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy
+ * back on the first chunk for dynamic percpu allocation if arch is
+ * manually allocating and mapping it for faster access (as a part of
+ * large page mapping for example).
+ *
+ * The following values give between one and two pages of free space
+ * after typical minimal boot (2-way SMP, single disk and NIC) with
+ * both defconfig and a distro config on x86_64 and 32. More
+ * intelligent way to determine this would be nice.
+ */
+#if BITS_PER_LONG > 32
+#define PERCPU_DYNAMIC_RESERVE (20 << 10)
+#else
+#define PERCPU_DYNAMIC_RESERVE (12 << 10)
+#endif
+
+extern void *pcpu_base_addr;
+
+typedef struct page * (*pcpu_get_page_fn_t)(unsigned int cpu, int pageno);
+typedef void (*pcpu_populate_pte_fn_t)(unsigned long addr);
+
+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 unit_size, ssize_t dyn_size,
+ void *base_addr,
+ pcpu_populate_pte_fn_t populate_pte_fn);
+
+/*
+ * Use this to get to a cpu's version of the per-cpu object
+ * dynamically allocated. Non-atomic access to the current CPU's
+ * version should probably be combined with get_cpu()/put_cpu().
+ */
+#define per_cpu_ptr(ptr, cpu) SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
+
+extern void *__alloc_reserved_percpu(size_t size, size_t align);
+
+#else /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
+
struct percpu_data {
void *ptrs[1];
};
#define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
-/*
- * Use this to get to a cpu's version of the per-cpu object dynamically
- * allocated. Non-atomic access to the current CPU's version should
- * probably be combined with get_cpu()/put_cpu().
- */
-#define percpu_ptr(ptr, cpu) \
-({ \
- struct percpu_data *__p = __percpu_disguise(ptr); \
- (__typeof__(ptr))__p->ptrs[(cpu)]; \
-})
-
-extern void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu);
-extern void percpu_depopulate(void *__pdata, int cpu);
-extern int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
- cpumask_t *mask);
-extern void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask);
-extern void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask);
-extern void percpu_free(void *__pdata);
-
-#else /* CONFIG_SMP */
-#define percpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
+#define per_cpu_ptr(ptr, cpu) \
+({ \
+ struct percpu_data *__p = __percpu_disguise(ptr); \
+ (__typeof__(ptr))__p->ptrs[(cpu)]; \
+})
-static inline void percpu_depopulate(void *__pdata, int cpu)
-{
-}
+#endif /* CONFIG_HAVE_DYNAMIC_PER_CPU_AREA */
-static inline void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask)
-{
-}
+extern void *__alloc_percpu(size_t size, size_t align);
+extern void free_percpu(void *__pdata);
-static inline void *percpu_populate(void *__pdata, size_t size, gfp_t gfp,
- int cpu)
-{
- return percpu_ptr(__pdata, cpu);
-}
+#else /* CONFIG_SMP */
-static inline int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
- cpumask_t *mask)
-{
- return 0;
-}
+#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
-static __always_inline void *__percpu_alloc_mask(size_t size, gfp_t gfp, cpumask_t *mask)
+static inline void *__alloc_percpu(size_t size, size_t align)
{
- return kzalloc(size, gfp);
+ /*
+ * 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 kzalloc(size, GFP_KERNEL);
}
-static inline void percpu_free(void *__pdata)
+static inline void free_percpu(void *p)
{
- kfree(__pdata);
+ kfree(p);
}
#endif /* CONFIG_SMP */
-#define percpu_populate_mask(__pdata, size, gfp, mask) \
- __percpu_populate_mask((__pdata), (size), (gfp), &(mask))
-#define percpu_depopulate_mask(__pdata, mask) \
- __percpu_depopulate_mask((__pdata), &(mask))
-#define percpu_alloc_mask(size, gfp, mask) \
- __percpu_alloc_mask((size), (gfp), &(mask))
-
-#define percpu_alloc(size, gfp) percpu_alloc_mask((size), (gfp), cpu_online_map)
-
-/* (legacy) interface for use without CPU hotplug handling */
-
-#define __alloc_percpu(size) percpu_alloc_mask((size), GFP_KERNEL, \
- cpu_possible_map)
-#define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type))
-#define free_percpu(ptr) percpu_free((ptr))
-#define per_cpu_ptr(ptr, cpu) percpu_ptr((ptr), (cpu))
+#define alloc_percpu(type) (type *)__alloc_percpu(sizeof(type), \
+ __alignof__(type))
#endif /* __LINUX_PERCPU_H */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff