mm: embed the memcg pointer directly into struct page

Memory cgroups used to have 5 per-page pointers.  To allow users to
disable that amount of overhead during runtime, those pointers were
allocated in a separate array, with a translation layer between them and
struct page.

There is now only one page pointer remaining: the memcg pointer, that
indicates which cgroup the page is associated with when charged.  The
complexity of runtime allocation and the runtime translation overhead is
no longer justified to save that *potential* 0.19% of memory.  With
CONFIG_SLUB, page->mem_cgroup actually sits in the doubleword padding
after the page->private member and doesn't even increase struct page,
and then this patch actually saves space.  Remaining users that care can
still compile their kernels without CONFIG_MEMCG.

     text    data     bss     dec     hex     filename
  8828345 1725264  983040 11536649 b00909  vmlinux.old
  8827425 1725264  966656 11519345 afc571  vmlinux.new

[mhocko@suse.cz: update Documentation/cgroups/memory.txt]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vladimir Davydov <vdavydov@parallels.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Acked-by: Konstantin Khlebnikov <koct9i@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 0 insertions, 319 deletions

diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 5331c2bd85a2..f0f31c1d4d0c 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -1,326 +1,7 @@
 #include <linux/mm.h>
-#include <linux/mmzone.h>
-#include <linux/bootmem.h>
-#include <linux/bit_spinlock.h>
 #include <linux/page_cgroup.h>
-#include <linux/hash.h>
-#include <linux/slab.h>
-#include <linux/memory.h>
 #include <linux/vmalloc.h>
-#include <linux/cgroup.h>
 #include <linux/swapops.h>
-#include <linux/kmemleak.h>
-
-static unsigned long total_usage;
-
-#if !defined(CONFIG_SPARSEMEM)
-
-
-void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
-{
-	pgdat->node_page_cgroup = NULL;
-}
-
-struct page_cgroup *lookup_page_cgroup(struct page *page)
-{
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long offset;
-	struct page_cgroup *base;
-
-	base = NODE_DATA(page_to_nid(page))->node_page_cgroup;
-#ifdef CONFIG_DEBUG_VM
-	/*
-	 * The sanity checks the page allocator does upon freeing a
-	 * page can reach here before the page_cgroup arrays are
-	 * allocated when feeding a range of pages to the allocator
-	 * for the first time during bootup or memory hotplug.
-	 */
-	if (unlikely(!base))
-		return NULL;
-#endif
-	offset = pfn - NODE_DATA(page_to_nid(page))->node_start_pfn;
-	return base + offset;
-}
-
-static int __init alloc_node_page_cgroup(int nid)
-{
-	struct page_cgroup *base;
-	unsigned long table_size;
-	unsigned long nr_pages;
-
-	nr_pages = NODE_DATA(nid)->node_spanned_pages;
-	if (!nr_pages)
-		return 0;
-
-	table_size = sizeof(struct page_cgroup) * nr_pages;
-
-	base = memblock_virt_alloc_try_nid_nopanic(
-			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
-			BOOTMEM_ALLOC_ACCESSIBLE, nid);
-	if (!base)
-		return -ENOMEM;
-	NODE_DATA(nid)->node_page_cgroup = base;
-	total_usage += table_size;
-	return 0;
-}
-
-void __init page_cgroup_init_flatmem(void)
-{
-
-	int nid, fail;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	for_each_online_node(nid)  {
-		fail = alloc_node_page_cgroup(nid);
-		if (fail)
-			goto fail;
-	}
-	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you"
-	" don't want memory cgroups\n");
-	return;
-fail:
-	printk(KERN_CRIT "allocation of page_cgroup failed.\n");
-	printk(KERN_CRIT "please try 'cgroup_disable=memory' boot option\n");
-	panic("Out of memory");
-}
-
-#else /* CONFIG_FLAT_NODE_MEM_MAP */
-
-struct page_cgroup *lookup_page_cgroup(struct page *page)
-{
-	unsigned long pfn = page_to_pfn(page);
-	struct mem_section *section = __pfn_to_section(pfn);
-#ifdef CONFIG_DEBUG_VM
-	/*
-	 * The sanity checks the page allocator does upon freeing a
-	 * page can reach here before the page_cgroup arrays are
-	 * allocated when feeding a range of pages to the allocator
-	 * for the first time during bootup or memory hotplug.
-	 */
-	if (!section->page_cgroup)
-		return NULL;
-#endif
-	return section->page_cgroup + pfn;
-}
-
-static void *__meminit alloc_page_cgroup(size_t size, int nid)
-{
-	gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN;
-	void *addr = NULL;
-
-	addr = alloc_pages_exact_nid(nid, size, flags);
-	if (addr) {
-		kmemleak_alloc(addr, size, 1, flags);
-		return addr;
-	}
-
-	if (node_state(nid, N_HIGH_MEMORY))
-		addr = vzalloc_node(size, nid);
-	else
-		addr = vzalloc(size);
-
-	return addr;
-}
-
-static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
-{
-	struct mem_section *section;
-	struct page_cgroup *base;
-	unsigned long table_size;
-
-	section = __pfn_to_section(pfn);
-
-	if (section->page_cgroup)
-		return 0;
-
-	table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-	base = alloc_page_cgroup(table_size, nid);
-
-	/*
-	 * The value stored in section->page_cgroup is (base - pfn)
-	 * and it does not point to the memory block allocated above,
-	 * causing kmemleak false positives.
-	 */
-	kmemleak_not_leak(base);
-
-	if (!base) {
-		printk(KERN_ERR "page cgroup allocation failure\n");
-		return -ENOMEM;
-	}
-
-	/*
-	 * The passed "pfn" may not be aligned to SECTION.  For the calculation
-	 * we need to apply a mask.
-	 */
-	pfn &= PAGE_SECTION_MASK;
-	section->page_cgroup = base - pfn;
-	total_usage += table_size;
-	return 0;
-}
-#ifdef CONFIG_MEMORY_HOTPLUG
-static void free_page_cgroup(void *addr)
-{
-	if (is_vmalloc_addr(addr)) {
-		vfree(addr);
-	} else {
-		struct page *page = virt_to_page(addr);
-		size_t table_size =
-			sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-
-		BUG_ON(PageReserved(page));
-		kmemleak_free(addr);
-		free_pages_exact(addr, table_size);
-	}
-}
-
-static void __free_page_cgroup(unsigned long pfn)
-{
-	struct mem_section *ms;
-	struct page_cgroup *base;
-
-	ms = __pfn_to_section(pfn);
-	if (!ms || !ms->page_cgroup)
-		return;
-	base = ms->page_cgroup + pfn;
-	free_page_cgroup(base);
-	ms->page_cgroup = NULL;
-}
-
-static int __meminit online_page_cgroup(unsigned long start_pfn,
-				unsigned long nr_pages,
-				int nid)
-{
-	unsigned long start, end, pfn;
-	int fail = 0;
-
-	start = SECTION_ALIGN_DOWN(start_pfn);
-	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
-
-	if (nid == -1) {
-		/*
-		 * In this case, "nid" already exists and contains valid memory.
-		 * "start_pfn" passed to us is a pfn which is an arg for
-		 * online__pages(), and start_pfn should exist.
-		 */
-		nid = pfn_to_nid(start_pfn);
-		VM_BUG_ON(!node_state(nid, N_ONLINE));
-	}
-
-	for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
-		if (!pfn_present(pfn))
-			continue;
-		fail = init_section_page_cgroup(pfn, nid);
-	}
-	if (!fail)
-		return 0;
-
-	/* rollback */
-	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
-		__free_page_cgroup(pfn);
-
-	return -ENOMEM;
-}
-
-static int __meminit offline_page_cgroup(unsigned long start_pfn,
-				unsigned long nr_pages, int nid)
-{
-	unsigned long start, end, pfn;
-
-	start = SECTION_ALIGN_DOWN(start_pfn);
-	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
-
-	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
-		__free_page_cgroup(pfn);
-	return 0;
-
-}
-
-static int __meminit page_cgroup_callback(struct notifier_block *self,
-			       unsigned long action, void *arg)
-{
-	struct memory_notify *mn = arg;
-	int ret = 0;
-	switch (action) {
-	case MEM_GOING_ONLINE:
-		ret = online_page_cgroup(mn->start_pfn,
-				   mn->nr_pages, mn->status_change_nid);
-		break;
-	case MEM_OFFLINE:
-		offline_page_cgroup(mn->start_pfn,
-				mn->nr_pages, mn->status_change_nid);
-		break;
-	case MEM_CANCEL_ONLINE:
-		offline_page_cgroup(mn->start_pfn,
-				mn->nr_pages, mn->status_change_nid);
-		break;
-	case MEM_GOING_OFFLINE:
-		break;
-	case MEM_ONLINE:
-	case MEM_CANCEL_OFFLINE:
-		break;
-	}
-
-	return notifier_from_errno(ret);
-}
-
-#endif
-
-void __init page_cgroup_init(void)
-{
-	unsigned long pfn;
-	int nid;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	for_each_node_state(nid, N_MEMORY) {
-		unsigned long start_pfn, end_pfn;
-
-		start_pfn = node_start_pfn(nid);
-		end_pfn = node_end_pfn(nid);
-		/*
-		 * start_pfn and end_pfn may not be aligned to SECTION and the
-		 * page->flags of out of node pages are not initialized.  So we
-		 * scan [start_pfn, the biggest section's pfn < end_pfn) here.
-		 */
-		for (pfn = start_pfn;
-		     pfn < end_pfn;
-                     pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {
-
-			if (!pfn_valid(pfn))
-				continue;
-			/*
-			 * Nodes's pfns can be overlapping.
-			 * We know some arch can have a nodes layout such as
-			 * -------------pfn-------------->
-			 * N0 | N1 | N2 | N0 | N1 | N2|....
-			 */
-			if (pfn_to_nid(pfn) != nid)
-				continue;
-			if (init_section_page_cgroup(pfn, nid))
-				goto oom;
-		}
-	}
-	hotplug_memory_notifier(page_cgroup_callback, 0);
-	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you "
-			 "don't want memory cgroups\n");
-	return;
-oom:
-	printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
-	panic("Out of memory");
-}
-
-void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
-{
-	return;
-}
-
-#endif
-
 
 #ifdef CONFIG_MEMCG_SWAP