Merge branch 'akpm' (Andrew's patch-bomb)

Merge misc VM changes from Andrew Morton: "The rest of most-of-MM. The other MM bits await a slab merge. This patch includes the addition of a huge zero_page. Not a performance boost but it an save large amounts of physical memory in some situations. Also a bunch of Fujitsu engineers are working on memory hotplug. Which, as it turns out, was badly broken. About half of their patches are included here; the remainder are 3.8 material." However, this merge disables CONFIG_MOVABLE_NODE, which was totally broken. We don't add new features with "default y", nor do we add Kconfig questions that are incomprehensible to most people without any help text. Does the feature even make sense without compaction or memory hotplug? * akpm: (54 commits) mm/bootmem.c: remove unused wrapper function reserve_bootmem_generic() mm/memory.c: remove unused code from do_wp_page() asm-generic, mm: pgtable: consolidate zero page helpers mm/hugetlb.c: fix warning on freeing hwpoisoned hugepage hwpoison, hugetlbfs: fix RSS-counter warning hwpoison, hugetlbfs: fix "bad pmd" warning in unmapping hwpoisoned hugepage mm: protect against concurrent vma expansion memcg: do not check for mm in __mem_cgroup_count_vm_event tmpfs: support SEEK_DATA and SEEK_HOLE (reprise) mm: provide more accurate estimation of pages occupied by memmap fs/buffer.c: remove redundant initialization in alloc_page_buffers() fs/buffer.c: do not inline exported function writeback: fix a typo in comment mm: introduce new field "managed_pages" to struct zone mm, oom: remove statically defined arch functions of same name mm, oom: remove redundant sleep in pagefault oom handler mm, oom: cleanup pagefault oom handler memory_hotplug: allow online/offline memory to result movable node numa: add CONFIG_MOVABLE_NODE for movable-dedicated node mm, memcg: avoid unnecessary function call when memcg is disabled ...
sanyoo · Dec 13, 2012 · f6e858a · f6e858a
2 parents 193c0d6 + 9887090
commit f6e858a
Show file tree

Hide file tree

Showing 52 changed files with 996 additions and 422 deletions.
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
@@ -218,7 +218,7 @@ and name space for cpusets, with a minimum of additional kernel code.
 The cpus and mems files in the root (top_cpuset) cpuset are
 read-only.  The cpus file automatically tracks the value of
 cpu_online_mask using a CPU hotplug notifier, and the mems file
-automatically tracks the value of node_states[N_HIGH_MEMORY]--i.e.,
+automatically tracks the value of node_states[N_MEMORY]--i.e.,
 nodes with memory--using the cpuset_track_online_nodes() hook.
 
 

diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
@@ -390,14 +390,17 @@ struct memory_notify {
        unsigned long start_pfn;
        unsigned long nr_pages;
        int status_change_nid_normal;
+       int status_change_nid_high;
        int status_change_nid;
 }
 
 start_pfn is start_pfn of online/offline memory.
 nr_pages is # of pages of online/offline memory.
 status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask
 is (will be) set/clear, if this is -1, then nodemask status is not changed.
-status_change_nid is set node id when N_HIGH_MEMORY of nodemask is (will be)
+status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask
+is (will be) set/clear, if this is -1, then nodemask status is not changed.
+status_change_nid is set node id when N_MEMORY of nodemask is (will be)
 set/clear. It means a new(memoryless) node gets new memory by online and a
 node loses all memory. If this is -1, then nodemask status is not changed.
 If status_changed_nid* >= 0, callback should create/discard structures for the

diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
@@ -116,6 +116,13 @@ echo always >/sys/kernel/mm/transparent_hugepage/defrag
 echo madvise >/sys/kernel/mm/transparent_hugepage/defrag
 echo never >/sys/kernel/mm/transparent_hugepage/defrag
 
+By default kernel tries to use huge zero page on read page fault.
+It's possible to disable huge zero page by writing 0 or enable it
+back by writing 1:
+
+echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page
+echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page
+
 khugepaged will be automatically started when
 transparent_hugepage/enabled is set to "always" or "madvise, and it'll
 be automatically shutdown if it's set to "never".
@@ -197,6 +204,14 @@ thp_split is incremented every time a huge page is split into base
 	pages. This can happen for a variety of reasons but a common
 	reason is that a huge page is old and is being reclaimed.
 
+thp_zero_page_alloc is incremented every time a huge zero page is
+	successfully allocated. It includes allocations which where
+	dropped due race with other allocation. Note, it doesn't count
+	every map of the huge zero page, only its allocation.
+
+thp_zero_page_alloc_failed is incremented if kernel fails to allocate
+	huge zero page and falls back to using small pages.
+
 As the system ages, allocating huge pages may be expensive as the
 system uses memory compaction to copy data around memory to free a
 huge page for use. There are some counters in /proc/vmstat to help
@@ -276,7 +291,7 @@ unaffected. libhugetlbfs will also work fine as usual.
 == Graceful fallback ==
 
 Code walking pagetables but unware about huge pmds can simply call
-split_huge_page_pmd(mm, pmd) where the pmd is the one returned by
+split_huge_page_pmd(vma, addr, pmd) where the pmd is the one returned by
 pmd_offset. It's trivial to make the code transparent hugepage aware
 by just grepping for "pmd_offset" and adding split_huge_page_pmd where
 missing after pmd_offset returns the pmd. Thanks to the graceful
@@ -299,7 +314,7 @@ diff --git a/mm/mremap.c b/mm/mremap.c
 		return NULL;
 
 	pmd = pmd_offset(pud, addr);
-+	split_huge_page_pmd(mm, pmd);
++	split_huge_page_pmd(vma, addr, pmd);
 	if (pmd_none_or_clear_bad(pmd))
 		return NULL;
 

diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
@@ -76,16 +76,7 @@ extern unsigned long zero_page_mask;
 
 #define ZERO_PAGE(vaddr) \
 	(virt_to_page((void *)(empty_zero_page + (((unsigned long)(vaddr)) & zero_page_mask))))
-
-#define is_zero_pfn is_zero_pfn
-static inline int is_zero_pfn(unsigned long pfn)
-{
-	extern unsigned long zero_pfn;
-	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
-	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
-}
-
-#define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))
+#define __HAVE_COLOR_ZERO_PAGE
 
 extern void paging_init(void);
 

diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
@@ -113,19 +113,6 @@ static int store_updates_sp(struct pt_regs *regs)
 #define MM_FAULT_CONTINUE	-1
 #define MM_FAULT_ERR(sig)	(sig)
 
-static int out_of_memory(struct pt_regs *regs)
-{
-	/*
-	 * We ran out of memory, or some other thing happened to us that made
-	 * us unable to handle the page fault gracefully.
-	 */
-	up_read(&current->mm->mmap_sem);
-	if (!user_mode(regs))
-		return MM_FAULT_ERR(SIGKILL);
-	pagefault_out_of_memory();
-	return MM_FAULT_RETURN;
-}
-
 static int do_sigbus(struct pt_regs *regs, unsigned long address)
 {
 	siginfo_t info;
@@ -169,8 +156,18 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
 		return MM_FAULT_CONTINUE;
 
 	/* Out of memory */
-	if (fault & VM_FAULT_OOM)
-		return out_of_memory(regs);
+	if (fault & VM_FAULT_OOM) {
+		up_read(&current->mm->mmap_sem);
+
+		/*
+		 * We ran out of memory, or some other thing happened to us that
+		 * made us unable to handle the page fault gracefully.
+		 */
+		if (!user_mode(regs))
+			return MM_FAULT_ERR(SIGKILL);
+		pagefault_out_of_memory();
+		return MM_FAULT_RETURN;
+	}
 
 	/* Bus error. x86 handles HWPOISON here, we'll add this if/when
 	 * we support the feature in HW

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
@@ -55,16 +55,7 @@ extern unsigned long zero_page_mask;
 #define ZERO_PAGE(vaddr) \
 	(virt_to_page((void *)(empty_zero_page + \
 	 (((unsigned long)(vaddr)) &zero_page_mask))))
-
-#define is_zero_pfn is_zero_pfn
-static inline int is_zero_pfn(unsigned long pfn)
-{
-	extern unsigned long zero_pfn;
-	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
-	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
-}
-
-#define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))
+#define __HAVE_COLOR_ZERO_PAGE
 
 #endif /* !__ASSEMBLY__ */
 

diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
@@ -301,17 +301,6 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
 	__bad_area(regs, error_code, address, SEGV_ACCERR);
 }
 
-static void out_of_memory(void)
-{
-	/*
-	 * We ran out of memory, call the OOM killer, and return the userspace
-	 * (which will retry the fault, or kill us if we got oom-killed):
-	 */
-	up_read(&current->mm->mmap_sem);
-
-	pagefault_out_of_memory();
-}
-
 static void
 do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
 {
@@ -353,8 +342,14 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 			no_context(regs, error_code, address);
 			return 1;
 		}
+		up_read(&current->mm->mmap_sem);
 
-		out_of_memory();
+		/*
+		 * We ran out of memory, call the OOM killer, and return the
+		 * userspace (which will retry the fault, or kill us if we got
+		 * oom-killed):
+		 */
+		pagefault_out_of_memory();
 	} else {
 		if (fault & VM_FAULT_SIGBUS)
 			do_sigbus(regs, error_code, address);

diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
@@ -182,7 +182,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	if (pud_none_or_clear_bad(pud))
 		goto out;
 	pmd = pmd_offset(pud, 0xA0000);
-	split_huge_page_pmd(mm, pmd);
+	split_huge_page_pmd_mm(mm, 0xA0000, pmd);
 	if (pmd_none_or_clear_bad(pmd))
 		goto out;
 	pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl);

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
@@ -803,20 +803,6 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
 	__bad_area(regs, error_code, address, SEGV_ACCERR);
 }
 
-/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */
-static void
-out_of_memory(struct pt_regs *regs, unsigned long error_code,
-	      unsigned long address)
-{
-	/*
-	 * We ran out of memory, call the OOM killer, and return the userspace
-	 * (which will retry the fault, or kill us if we got oom-killed):
-	 */
-	up_read(&current->mm->mmap_sem);
-
-	pagefault_out_of_memory();
-}
-
 static void
 do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
 	  unsigned int fault)
@@ -879,7 +865,14 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 			return 1;
 		}
 
-		out_of_memory(regs, error_code, address);
+		up_read(&current->mm->mmap_sem);
+
+		/*
+		 * We ran out of memory, call the OOM killer, and return the
+		 * userspace (which will retry the fault, or kill us if we got
+		 * oom-killed):
+		 */
+		pagefault_out_of_memory();
 	} else {
 		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
 			     VM_FAULT_HWPOISON_LARGE))

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
@@ -630,7 +630,9 @@ void __init paging_init(void)
 	 *	 numa support is not compiled in, and later node_set_state
 	 *	 will not set it back.
 	 */
-	node_clear_state(0, N_NORMAL_MEMORY);
+	node_clear_state(0, N_MEMORY);
+	if (N_MEMORY != N_NORMAL_MEMORY)
+		node_clear_state(0, N_NORMAL_MEMORY);
 
 	zone_sizes_init();
 }

diff --git a/drivers/base/node.c b/drivers/base/node.c
@@ -227,7 +227,7 @@ static node_registration_func_t __hugetlb_unregister_node;
 static inline bool hugetlb_register_node(struct node *node)
 {
 	if (__hugetlb_register_node &&
-			node_state(node->dev.id, N_HIGH_MEMORY)) {
+			node_state(node->dev.id, N_MEMORY)) {
 		__hugetlb_register_node(node);
 		return true;
 	}
@@ -643,6 +643,9 @@ static struct node_attr node_state_attr[] = {
 	[N_NORMAL_MEMORY] = _NODE_ATTR(has_normal_memory, N_NORMAL_MEMORY),
 #ifdef CONFIG_HIGHMEM
 	[N_HIGH_MEMORY] = _NODE_ATTR(has_high_memory, N_HIGH_MEMORY),
+#endif
+#ifdef CONFIG_MOVABLE_NODE
+	[N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY),
 #endif
 	[N_CPU] = _NODE_ATTR(has_cpu, N_CPU),
 };
@@ -653,6 +656,9 @@ static struct attribute *node_state_attrs[] = {
 	&node_state_attr[N_NORMAL_MEMORY].attr.attr,
 #ifdef CONFIG_HIGHMEM
 	&node_state_attr[N_HIGH_MEMORY].attr.attr,
+#endif
+#ifdef CONFIG_MOVABLE_NODE
+	&node_state_attr[N_MEMORY].attr.attr,
 #endif
 	&node_state_attr[N_CPU].attr.attr,
 	NULL

diff --git a/fs/buffer.c b/fs/buffer.c
@@ -46,8 +46,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
 
 #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
 
-inline void
-init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private)
+void init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private)
 {
 	bh->b_end_io = handler;
 	bh->b_private = private;
@@ -850,13 +849,10 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
 		if (!bh)
 			goto no_grow;
 
-		bh->b_bdev = NULL;
 		bh->b_this_page = head;
 		bh->b_blocknr = -1;
 		head = bh;
 
-		bh->b_state = 0;
-		atomic_set(&bh->b_count, 0);
 		bh->b_size = size;
 
 		/* Link the buffer to its page */

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
@@ -1034,7 +1034,7 @@ int bdi_writeback_thread(void *data)
 	while (!kthread_freezable_should_stop(NULL)) {
 		/*
 		 * Remove own delayed wake-up timer, since we are already awake
-		 * and we'll take care of the preriodic write-back.
+		 * and we'll take care of the periodic write-back.
 		 */
 		del_timer(&wb->wakeup_timer);
 

diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
@@ -249,7 +249,7 @@ static int kcore_update_ram(void)
 	/* Not inialized....update now */
 	/* find out "max pfn" */
 	end_pfn = 0;
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		unsigned long node_end;
 		node_end  = NODE_DATA(nid)->node_start_pfn +
 			NODE_DATA(nid)->node_spanned_pages;

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
@@ -643,7 +643,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	spinlock_t *ptl;
 	struct page *page;
 
-	split_huge_page_pmd(walk->mm, pmd);
+	split_huge_page_pmd(vma, addr, pmd);
 	if (pmd_trans_unstable(pmd))
 		return 0;
 
@@ -1126,7 +1126,7 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
 		return NULL;
 
 	nid = page_to_nid(page);
-	if (!node_isset(nid, node_states[N_HIGH_MEMORY]))
+	if (!node_isset(nid, node_states[N_MEMORY]))
 		return NULL;
 
 	return page;
@@ -1279,7 +1279,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 	if (md->writeback)
 		seq_printf(m, " writeback=%lu", md->writeback);
 
-	for_each_node_state(n, N_HIGH_MEMORY)
+	for_each_node_state(n, N_MEMORY)
 		if (md->node[n])
 			seq_printf(m, " N%d=%lu", n, md->node[n]);
 out:

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
@@ -449,6 +449,32 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size);
 #endif
 
+#ifdef __HAVE_COLOR_ZERO_PAGE
+static inline int is_zero_pfn(unsigned long pfn)
+{
+	extern unsigned long zero_pfn;
+	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
+	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
+}
+
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+	return page_to_pfn(ZERO_PAGE(addr));
+}
+#else
+static inline int is_zero_pfn(unsigned long pfn)
+{
+	extern unsigned long zero_pfn;
+	return pfn == zero_pfn;
+}
+
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+	extern unsigned long zero_pfn;
+	return zero_pfn;
+}
+#endif
+
 #ifdef CONFIG_MMU
 
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE

diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
@@ -137,9 +137,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
 #define alloc_bootmem_low_pages_node(pgdat, x) \
 	__alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0)
 
-extern int reserve_bootmem_generic(unsigned long addr, unsigned long size,
-				   int flags);
-
 #ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP
 extern void *alloc_remap(int nid, unsigned long size);
 #else

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
@@ -144,7 +144,7 @@ static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
 	return node_possible_map;
 }
 
-#define cpuset_current_mems_allowed (node_states[N_HIGH_MEMORY])
+#define cpuset_current_mems_allowed (node_states[N_MEMORY])
 static inline void cpuset_init_current_mems_allowed(void) {}
 
 static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)