[RFC PATCH] percpu: kill legacy percpu allocator

From: Tejun Heo
Date: Tue Jul 21 2009 - 08:24:18 EST


With ia64 converted, there's no arch left which still uses legacy
percpu allocator. Kill it.

NOT_SIGNED_OFF_YET
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
---

This patch is not ready yet. The following ia64 patch needs to be
verified and included before this one.

http://article.gmane.org/gmane.linux.kernel.cross-arch/4132

This patch is available in the following git tree.

git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git review-kill-legacy

After this patch gets included, we can finally proceed with
Christoph's this_cpu patches and other goodies. :-)

Thanks.

include/linux/percpu.h | 24 ------
kernel/module.c | 150 -----------------------------------------
mm/Makefile | 4 -
mm/allocpercpu.c | 177 -------------------------------------------------
mm/percpu.c | 2
5 files changed, 357 deletions(-)

Index: work/include/linux/percpu.h
===================================================================
--- work.orig/include/linux/percpu.h
+++ work/include/linux/percpu.h
@@ -34,8 +34,6 @@

#ifdef CONFIG_SMP

-#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)

@@ -130,28 +128,6 @@ extern int __init pcpu_page_first_chunk(
#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_LEGACY_PER_CPU_AREA */
-
-struct percpu_data {
- void *ptrs[1];
-};
-
-/* pointer disguising messes up the kmemleak objects tracking */
-#ifndef CONFIG_DEBUG_KMEMLEAK
-#define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
-#else
-#define __percpu_disguise(pdata) (struct percpu_data *)(pdata)
-#endif
-
-#define per_cpu_ptr(ptr, cpu) \
-({ \
- struct percpu_data *__p = __percpu_disguise(ptr); \
- (__typeof__(ptr))__p->ptrs[(cpu)]; \
-})
-
-#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
extern void *__alloc_percpu(size_t size, size_t align);
extern void free_percpu(void *__pdata);

Index: work/mm/allocpercpu.c
===================================================================
--- work.orig/mm/allocpercpu.c
+++ /dev/null
@@ -1,177 +0,0 @@
-/*
- * linux/mm/allocpercpu.c
- *
- * Separated from slab.c August 11, 2006 Christoph Lameter
- */
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/bootmem.h>
-#include <asm/sections.h>
-
-#ifndef cache_line_size
-#define cache_line_size() L1_CACHE_BYTES
-#endif
-
-/**
- * percpu_depopulate - depopulate per-cpu data for given cpu
- * @__pdata: per-cpu data to depopulate
- * @cpu: depopulate per-cpu data for this cpu
- *
- * Depopulating per-cpu data for a cpu going offline would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- */
-static void percpu_depopulate(void *__pdata, int cpu)
-{
- struct percpu_data *pdata = __percpu_disguise(__pdata);
-
- kfree(pdata->ptrs[cpu]);
- pdata->ptrs[cpu] = NULL;
-}
-
-/**
- * percpu_depopulate_mask - depopulate per-cpu data for some cpu's
- * @__pdata: per-cpu data to depopulate
- * @mask: depopulate per-cpu data for cpu's selected through mask bits
- */
-static void __percpu_depopulate_mask(void *__pdata, const cpumask_t *mask)
-{
- int cpu;
- for_each_cpu_mask_nr(cpu, *mask)
- percpu_depopulate(__pdata, cpu);
-}
-
-#define percpu_depopulate_mask(__pdata, mask) \
- __percpu_depopulate_mask((__pdata), &(mask))
-
-/**
- * percpu_populate - populate per-cpu data for given cpu
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @cpu: populate per-data for this cpu
- *
- * Populating per-cpu data for a cpu coming online would be a typical
- * use case. You need to register a cpu hotplug handler for that purpose.
- * Per-cpu object is populated with zeroed buffer.
- */
-static void *percpu_populate(void *__pdata, size_t size, gfp_t gfp, int cpu)
-{
- struct percpu_data *pdata = __percpu_disguise(__pdata);
- int node = cpu_to_node(cpu);
-
- /*
- * We should make sure each CPU gets private memory.
- */
- size = roundup(size, cache_line_size());
-
- BUG_ON(pdata->ptrs[cpu]);
- if (node_online(node))
- pdata->ptrs[cpu] = kmalloc_node(size, gfp|__GFP_ZERO, node);
- else
- pdata->ptrs[cpu] = kzalloc(size, gfp);
- return pdata->ptrs[cpu];
-}
-
-/**
- * percpu_populate_mask - populate per-cpu data for more cpu's
- * @__pdata: per-cpu data to populate further
- * @size: size of per-cpu object
- * @gfp: may sleep or not etc.
- * @mask: populate per-cpu data for cpu's selected through mask bits
- *
- * Per-cpu objects are populated with zeroed buffers.
- */
-static int __percpu_populate_mask(void *__pdata, size_t size, gfp_t gfp,
- cpumask_t *mask)
-{
- cpumask_t populated;
- int cpu;
-
- cpus_clear(populated);
- for_each_cpu_mask_nr(cpu, *mask)
- if (unlikely(!percpu_populate(__pdata, size, gfp, cpu))) {
- __percpu_depopulate_mask(__pdata, &populated);
- return -ENOMEM;
- } else
- cpu_set(cpu, populated);
- return 0;
-}
-
-#define percpu_populate_mask(__pdata, size, gfp, mask) \
- __percpu_populate_mask((__pdata), (size), (gfp), &(mask))
-
-/**
- * alloc_percpu - initial setup of per-cpu data
- * @size: size of per-cpu object
- * @align: alignment
- *
- * Allocate dynamic percpu area. Percpu objects are populated with
- * zeroed buffers.
- */
-void *__alloc_percpu(size_t size, size_t align)
-{
- /*
- * We allocate whole cache lines to avoid false sharing
- */
- size_t sz = roundup(nr_cpu_ids * sizeof(void *), cache_line_size());
- void *pdata = kzalloc(sz, GFP_KERNEL);
- void *__pdata = __percpu_disguise(pdata);
-
- /*
- * 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);
-
- if (unlikely(!pdata))
- return NULL;
- if (likely(!__percpu_populate_mask(__pdata, size, GFP_KERNEL,
- &cpu_possible_map)))
- return __pdata;
- kfree(pdata);
- return NULL;
-}
-EXPORT_SYMBOL_GPL(__alloc_percpu);
-
-/**
- * free_percpu - final cleanup of per-cpu data
- * @__pdata: object to clean up
- *
- * We simply clean up any per-cpu object left. No need for the client to
- * track and specify through a bis mask which per-cpu objects are to free.
- */
-void free_percpu(void *__pdata)
-{
- if (unlikely(!__pdata))
- return;
- __percpu_depopulate_mask(__pdata, cpu_possible_mask);
- kfree(__percpu_disguise(__pdata));
-}
-EXPORT_SYMBOL_GPL(free_percpu);
-
-/*
- * Generic percpu area setup.
- */
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
-unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-
-EXPORT_SYMBOL(__per_cpu_offset);
-
-void __init setup_per_cpu_areas(void)
-{
- unsigned long size, i;
- char *ptr;
- unsigned long nr_possible_cpus = num_possible_cpus();
-
- /* Copy section for each CPU (we discard the original) */
- size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
- ptr = alloc_bootmem_pages(size * nr_possible_cpus);
-
- for_each_possible_cpu(i) {
- __per_cpu_offset[i] = ptr - __per_cpu_start;
- memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
- ptr += size;
- }
-}
-#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
Index: work/kernel/module.c
===================================================================
--- work.orig/kernel/module.c
+++ work/kernel/module.c
@@ -364,8 +364,6 @@ EXPORT_SYMBOL_GPL(find_module);

#ifdef CONFIG_SMP

-#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
-
static void *percpu_modalloc(unsigned long size, unsigned long align,
const char *name)
{
@@ -389,154 +387,6 @@ static void percpu_modfree(void *freeme)
free_percpu(freeme);
}

-#else /* ... CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
-/* Number of blocks used and allocated. */
-static unsigned int pcpu_num_used, pcpu_num_allocated;
-/* Size of each block. -ve means used. */
-static int *pcpu_size;
-
-static int split_block(unsigned int i, unsigned short size)
-{
- /* Reallocation required? */
- if (pcpu_num_used + 1 > pcpu_num_allocated) {
- int *new;
-
- new = krealloc(pcpu_size, sizeof(new[0])*pcpu_num_allocated*2,
- GFP_KERNEL);
- if (!new)
- return 0;
-
- pcpu_num_allocated *= 2;
- pcpu_size = new;
- }
-
- /* Insert a new subblock */
- memmove(&pcpu_size[i+1], &pcpu_size[i],
- sizeof(pcpu_size[0]) * (pcpu_num_used - i));
- pcpu_num_used++;
-
- pcpu_size[i+1] -= size;
- pcpu_size[i] = size;
- return 1;
-}
-
-static inline unsigned int block_size(int val)
-{
- if (val < 0)
- return -val;
- return val;
-}
-
-static void *percpu_modalloc(unsigned long size, unsigned long align,
- const char *name)
-{
- unsigned long extra;
- unsigned int i;
- void *ptr;
- int cpu;
-
- if (align > PAGE_SIZE) {
- printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
- name, align, PAGE_SIZE);
- align = PAGE_SIZE;
- }
-
- ptr = __per_cpu_start;
- for (i = 0; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
- /* Extra for alignment requirement. */
- extra = ALIGN((unsigned long)ptr, align) - (unsigned long)ptr;
- BUG_ON(i == 0 && extra != 0);
-
- if (pcpu_size[i] < 0 || pcpu_size[i] < extra + size)
- continue;
-
- /* Transfer extra to previous block. */
- if (pcpu_size[i-1] < 0)
- pcpu_size[i-1] -= extra;
- else
- pcpu_size[i-1] += extra;
- pcpu_size[i] -= extra;
- ptr += extra;
-
- /* Split block if warranted */
- if (pcpu_size[i] - size > sizeof(unsigned long))
- if (!split_block(i, size))
- return NULL;
-
- /* add the per-cpu scanning areas */
- for_each_possible_cpu(cpu)
- kmemleak_alloc(ptr + per_cpu_offset(cpu), size, 0,
- GFP_KERNEL);
-
- /* Mark allocated */
- pcpu_size[i] = -pcpu_size[i];
- return ptr;
- }
-
- printk(KERN_WARNING "Could not allocate %lu bytes percpu data\n",
- size);
- return NULL;
-}
-
-static void percpu_modfree(void *freeme)
-{
- unsigned int i;
- void *ptr = __per_cpu_start + block_size(pcpu_size[0]);
- int cpu;
-
- /* First entry is core kernel percpu data. */
- for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
- if (ptr == freeme) {
- pcpu_size[i] = -pcpu_size[i];
- goto free;
- }
- }
- BUG();
-
- free:
- /* remove the per-cpu scanning areas */
- for_each_possible_cpu(cpu)
- kmemleak_free(freeme + per_cpu_offset(cpu));
-
- /* Merge with previous? */
- if (pcpu_size[i-1] >= 0) {
- pcpu_size[i-1] += pcpu_size[i];
- pcpu_num_used--;
- memmove(&pcpu_size[i], &pcpu_size[i+1],
- (pcpu_num_used - i) * sizeof(pcpu_size[0]));
- i--;
- }
- /* Merge with next? */
- if (i+1 < pcpu_num_used && pcpu_size[i+1] >= 0) {
- pcpu_size[i] += pcpu_size[i+1];
- pcpu_num_used--;
- memmove(&pcpu_size[i+1], &pcpu_size[i+2],
- (pcpu_num_used - (i+1)) * sizeof(pcpu_size[0]));
- }
-}
-
-static int percpu_modinit(void)
-{
- pcpu_num_used = 2;
- pcpu_num_allocated = 2;
- pcpu_size = kmalloc(sizeof(pcpu_size[0]) * pcpu_num_allocated,
- GFP_KERNEL);
- /* Static in-kernel percpu data (used). */
- pcpu_size[0] = -(__per_cpu_end-__per_cpu_start);
- /* Free room. */
- pcpu_size[1] = PERCPU_ENOUGH_ROOM + pcpu_size[0];
- if (pcpu_size[1] < 0) {
- printk(KERN_ERR "No per-cpu room for modules.\n");
- pcpu_num_used = 1;
- }
-
- return 0;
-}
-__initcall(percpu_modinit);
-
-#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
static unsigned int find_pcpusec(Elf_Ehdr *hdr,
Elf_Shdr *sechdrs,
const char *secstrings)
Index: work/mm/percpu.c
===================================================================
--- work.orig/mm/percpu.c
+++ work/mm/percpu.c
@@ -46,8 +46,6 @@
*
* To use this allocator, arch code should do the followings.
*
- * - drop CONFIG_HAVE_LEGACY_PER_CPU_AREA
- *
* - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
* regular address to percpu pointer and back if they need to be
* different from the default
Index: work/mm/Makefile
===================================================================
--- work.orig/mm/Makefile
+++ work/mm/Makefile
@@ -33,11 +33,7 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
obj-$(CONFIG_FS_XIP) += filemap_xip.o
obj-$(CONFIG_MIGRATION) += migrate.o
-ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
obj-$(CONFIG_SMP) += percpu.o
-else
-obj-$(CONFIG_SMP) += allocpercpu.o
-endif
obj-$(CONFIG_QUICKLIST) += quicklist.o
obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/