Merge branch 'akpm' (aka "Andrew's patch-bomb, take two")

Andrew explains:

 - various misc stuff

 - Most of the rest of MM: memcg, threaded hugepages, others.

 - cpumask

 - kexec

 - kdump

 - some direct-io performance tweaking

 - radix-tree optimisations

 - new selftests code

   A note on this: often people will develop a new userspace-visible
   feature and will develop userspace code to exercise/test that
   feature.  Then they merge the patch and the selftest code dies.
   Sometimes we paste it into the changelog.  Sometimes the code gets
   thrown into Documentation/(!).

   This saddens me.  So this patch creates a bare-bones framework which
   will henceforth allow me to ask people to include their test apps in
   the kernel tree so we can keep them alive.  Then when people enhance
   or fix the feature, I can ask them to update the test app too.

   The infrastruture is terribly trivial at present - let's see how it
   evolves.

 - checkpoint/restart feature work.

   A note on this: this is a project by various mad Russians to perform
   c/r mainly from userspace, with various oddball helper code added
   into the kernel where the need is demonstrated.

   So rather than some large central lump of code, what we have is
   little bits and pieces popping up in various places which either
   expose something new or which permit something which is normally
   kernel-private to be modified.

   The overall project is an ongoing thing.  I've judged that the size
   and scope of the thing means that we're more likely to be successful
   with it if we integrate the support into mainline piecemeal rather
   than allowing it all to develop out-of-tree.

   However I'm less confident than the developers that it will all
   eventually work! So what I'm asking them to do is to wrap each piece
   of new code inside CONFIG_CHECKPOINT_RESTORE.  So if it all
   eventually comes to tears and the project as a whole fails, it should
   be a simple matter to go through and delete all trace of it.

This lot pretty much wraps up the -rc1 merge for me.

* akpm: (96 commits)
  unlzo: fix input buffer free
  ramoops: update parameters only after successful init
  ramoops: fix use of rounddown_pow_of_two()
  c/r: prctl: add PR_SET_MM codes to set up mm_struct entries
  c/r: procfs: add start_data, end_data, start_brk members to /proc/$pid/stat v4
  c/r: introduce CHECKPOINT_RESTORE symbol
  selftests: new x86 breakpoints selftest
  selftests: new very basic kernel selftests directory
  radix_tree: take radix_tree_path off stack
  radix_tree: remove radix_tree_indirect_to_ptr()
  dio: optimize cache misses in the submission path
  vfs: cache request_queue in struct block_device
  fs/direct-io.c: calculate fs_count correctly in get_more_blocks()
  drivers/parport/parport_pc.c: fix warnings
  panic: don't print redundant backtraces on oops
  sysctl: add the kernel.ns_last_pid control
  kdump: add udev events for memory online/offline
  include/linux/crash_dump.h needs elf.h
  kdump: fix crash_kexec()/smp_send_stop() race in panic()
  kdump: crashk_res init check for /sys/kernel/kexec_crash_size
  ...

1 files changed, 57 insertions, 107 deletions

diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 2d123f94a8d..de1616aa9b1 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -11,13 +11,6 @@
 #include <linux/swapops.h>
 #include <linux/kmemleak.h>
 
-static void __meminit init_page_cgroup(struct page_cgroup *pc, unsigned long id)
-{
-	pc->flags = 0;
-	set_page_cgroup_array_id(pc, id);
-	pc->mem_cgroup = NULL;
-	INIT_LIST_HEAD(&pc->lru);
-}
 static unsigned long total_usage;
 
 #if !defined(CONFIG_SPARSEMEM)
@@ -35,35 +28,27 @@ struct page_cgroup *lookup_page_cgroup(struct page *page)
 	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;
 }
 
-struct page *lookup_cgroup_page(struct page_cgroup *pc)
-{
-	unsigned long pfn;
-	struct page *page;
-	pg_data_t *pgdat;
-
-	pgdat = NODE_DATA(page_cgroup_array_id(pc));
-	pfn = pc - pgdat->node_page_cgroup + pgdat->node_start_pfn;
-	page = pfn_to_page(pfn);
-	VM_BUG_ON(pc != lookup_page_cgroup(page));
-	return page;
-}
-
 static int __init alloc_node_page_cgroup(int nid)
 {
-	struct page_cgroup *base, *pc;
+	struct page_cgroup *base;
 	unsigned long table_size;
-	unsigned long start_pfn, nr_pages, index;
+	unsigned long nr_pages;
 
-	start_pfn = NODE_DATA(nid)->node_start_pfn;
 	nr_pages = NODE_DATA(nid)->node_spanned_pages;
-
 	if (!nr_pages)
 		return 0;
 
@@ -73,10 +58,6 @@ static int __init alloc_node_page_cgroup(int nid)
 			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
 	if (!base)
 		return -ENOMEM;
-	for (index = 0; index < nr_pages; index++) {
-		pc = base + index;
-		init_page_cgroup(pc, nid);
-	}
 	NODE_DATA(nid)->node_page_cgroup = base;
 	total_usage += table_size;
 	return 0;
@@ -111,29 +92,23 @@ 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;
 }
 
-struct page *lookup_cgroup_page(struct page_cgroup *pc)
-{
-	struct mem_section *section;
-	struct page *page;
-	unsigned long nr;
-
-	nr = page_cgroup_array_id(pc);
-	section = __nr_to_section(nr);
-	page = pfn_to_page(pc - section->page_cgroup);
-	VM_BUG_ON(pc != lookup_page_cgroup(page));
-	return page;
-}
-
 static void *__meminit alloc_page_cgroup(size_t size, int nid)
 {
+	gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN;
 	void *addr = NULL;
-	gfp_t flags = GFP_KERNEL | __GFP_NOWARN;
 
 	addr = alloc_pages_exact_nid(nid, size, flags);
 	if (addr) {
@@ -142,39 +117,20 @@ static void *__meminit alloc_page_cgroup(size_t size, int nid)
 	}
 
 	if (node_state(nid, N_HIGH_MEMORY))
-		addr = vmalloc_node(size, nid);
+		addr = vzalloc_node(size, nid);
 	else
-		addr = vmalloc(size);
+		addr = vzalloc(size);
 
 	return addr;
 }
 
-#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));
-		free_pages_exact(addr, table_size);
-	}
-}
-#endif
-
 static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
 {
-	struct page_cgroup *base, *pc;
 	struct mem_section *section;
+	struct page_cgroup *base;
 	unsigned long table_size;
-	unsigned long nr;
-	int index;
 
-	nr = pfn_to_section_nr(pfn);
-	section = __nr_to_section(nr);
+	section = __pfn_to_section(pfn);
 
 	if (section->page_cgroup)
 		return 0;
@@ -194,10 +150,6 @@ static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
 		return -ENOMEM;
 	}
 
-	for (index = 0; index < PAGES_PER_SECTION; index++) {
-		pc = base + index;
-		init_page_cgroup(pc, nr);
-	}
 	/*
 	 * The passed "pfn" may not be aligned to SECTION.  For the calculation
 	 * we need to apply a mask.
@@ -208,6 +160,20 @@ static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
 	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));
+		free_pages_exact(addr, table_size);
+	}
+}
+
 void __free_page_cgroup(unsigned long pfn)
 {
 	struct mem_section *ms;
@@ -366,7 +332,6 @@ struct swap_cgroup {
 	unsigned short		id;
 };
 #define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
-#define SC_POS_MASK	(SC_PER_PAGE - 1)
 
 /*
  * SwapCgroup implements "lookup" and "exchange" operations.
@@ -408,6 +373,21 @@ not_enough_page:
 	return -ENOMEM;
 }
 
+static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
+					struct swap_cgroup_ctrl **ctrlp)
+{
+	pgoff_t offset = swp_offset(ent);
+	struct swap_cgroup_ctrl *ctrl;
+	struct page *mappage;
+
+	ctrl = &swap_cgroup_ctrl[swp_type(ent)];
+	if (ctrlp)
+		*ctrlp = ctrl;
+
+	mappage = ctrl->map[offset / SC_PER_PAGE];
+	return page_address(mappage) + offset % SC_PER_PAGE;
+}
+
 /**
  * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
  * @end: swap entry to be cmpxchged
@@ -420,21 +400,13 @@ not_enough_page:
 unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
 					unsigned short old, unsigned short new)
 {
-	int type = swp_type(ent);
-	unsigned long offset = swp_offset(ent);
-	unsigned long idx = offset / SC_PER_PAGE;
-	unsigned long pos = offset & SC_POS_MASK;
 	struct swap_cgroup_ctrl *ctrl;
-	struct page *mappage;
 	struct swap_cgroup *sc;
 	unsigned long flags;
 	unsigned short retval;
 
-	ctrl = &swap_cgroup_ctrl[type];
+	sc = lookup_swap_cgroup(ent, &ctrl);
 
-	mappage = ctrl->map[idx];
-	sc = page_address(mappage);
-	sc += pos;
 	spin_lock_irqsave(&ctrl->lock, flags);
 	retval = sc->id;
 	if (retval == old)
@@ -455,21 +427,13 @@ unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
  */
 unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
 {
-	int type = swp_type(ent);
-	unsigned long offset = swp_offset(ent);
-	unsigned long idx = offset / SC_PER_PAGE;
-	unsigned long pos = offset & SC_POS_MASK;
 	struct swap_cgroup_ctrl *ctrl;
-	struct page *mappage;
 	struct swap_cgroup *sc;
 	unsigned short old;
 	unsigned long flags;
 
-	ctrl = &swap_cgroup_ctrl[type];
+	sc = lookup_swap_cgroup(ent, &ctrl);
 
-	mappage = ctrl->map[idx];
-	sc = page_address(mappage);
-	sc += pos;
 	spin_lock_irqsave(&ctrl->lock, flags);
 	old = sc->id;
 	sc->id = id;
@@ -479,28 +443,14 @@ unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
 }
 
 /**
- * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
+ * lookup_swap_cgroup_id - lookup mem_cgroup id tied to swap entry
  * @ent: swap entry to be looked up.
  *
  * Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
  */
-unsigned short lookup_swap_cgroup(swp_entry_t ent)
+unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
 {
-	int type = swp_type(ent);
-	unsigned long offset = swp_offset(ent);
-	unsigned long idx = offset / SC_PER_PAGE;
-	unsigned long pos = offset & SC_POS_MASK;
-	struct swap_cgroup_ctrl *ctrl;
-	struct page *mappage;
-	struct swap_cgroup *sc;
-	unsigned short ret;
-
-	ctrl = &swap_cgroup_ctrl[type];
-	mappage = ctrl->map[idx];
-	sc = page_address(mappage);
-	sc += pos;
-	ret = sc->id;
-	return ret;
+	return lookup_swap_cgroup(ent, NULL)->id;
 }
 
 int swap_cgroup_swapon(int type, unsigned long max_pages)