Merge branch 'akpm' (incoming from Andrew)

Merge first patch-bomb from Andrew Morton: - a couple of misc things - inotify/fsnotify work from Jan - ocfs2 updates (partial) - about half of MM * emailed patches from Andrew Morton <[email protected]>: (117 commits) mm/migrate: remove unused function, fail_migrate_page() mm/migrate: remove putback_lru_pages, fix comment on putback_movable_pages mm/migrate: correct failure handling if !hugepage_migration_support() mm/migrate: add comment about permanent failure path mm, page_alloc: warn for non-blockable __GFP_NOFAIL allocation failure mm: compaction: reset scanner positions immediately when they meet mm: compaction: do not mark unmovable pageblocks as skipped in async compaction mm: compaction: detect when scanners meet in isolate_freepages mm: compaction: reset cached scanner pfn's before reading them mm: compaction: encapsulate defer reset logic mm: compaction: trace compaction begin and end memcg, oom: lock mem_cgroup_print_oom_info sched: add tracepoints related to NUMA task migration mm: numa: do not automatically migrate KSM pages mm: numa: trace tasks that fail migration due to rate limiting mm: numa: limit scope of lock for NUMA migrate rate limiting mm: numa: make NUMA-migrate related functions static lib/show_mem.c: show num_poisoned_pages when oom mm/hwpoison: add '#' to hwpoison_inject mm/memblock: use WARN_ONCE when MAX_NUMNODES passed as input parameter ...
CamonZ · Jan 22, 2014 · df32e43 · df32e43
2 parents fbd918a + 78d5506
commit df32e43
Show file tree

Hide file tree

Showing 139 changed files with 2,902 additions and 2,512 deletions.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
@@ -767,6 +767,7 @@ The "Locked" indicates whether the mapping is locked in memory or not.
 
 MemTotal:     16344972 kB
 MemFree:      13634064 kB
+MemAvailable: 14836172 kB
 Buffers:          3656 kB
 Cached:        1195708 kB
 SwapCached:          0 kB
@@ -799,6 +800,14 @@ AnonHugePages:   49152 kB
     MemTotal: Total usable ram (i.e. physical ram minus a few reserved
               bits and the kernel binary code)
      MemFree: The sum of LowFree+HighFree
+MemAvailable: An estimate of how much memory is available for starting new
+              applications, without swapping. Calculated from MemFree,
+              SReclaimable, the size of the file LRU lists, and the low
+              watermarks in each zone.
+              The estimate takes into account that the system needs some
+              page cache to function well, and that not all reclaimable
+              slab will be reclaimable, due to items being in use. The
+              impact of those factors will vary from system to system.
      Buffers: Relatively temporary storage for raw disk blocks
               shouldn't get tremendously large (20MB or so)
       Cached: in-memory cache for files read from the disk (the

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
@@ -47,6 +47,7 @@ Currently, these files are in /proc/sys/vm:
 - numa_zonelist_order
 - oom_dump_tasks
 - oom_kill_allocating_task
+- overcommit_kbytes
 - overcommit_memory
 - overcommit_ratio
 - page-cluster
@@ -574,6 +575,17 @@ The default value is 0.
 
 ==============================================================
 
+overcommit_kbytes:
+
+When overcommit_memory is set to 2, the committed address space is not
+permitted to exceed swap plus this amount of physical RAM. See below.
+
+Note: overcommit_kbytes is the counterpart of overcommit_ratio. Only one
+of them may be specified at a time. Setting one disables the other (which
+then appears as 0 when read).
+
+==============================================================
+
 overcommit_memory:
 
 This value contains a flag that enables memory overcommitment.

diff --git a/Documentation/vm/overcommit-accounting b/Documentation/vm/overcommit-accounting
@@ -14,8 +14,8 @@ The Linux kernel supports the following overcommit handling modes
 
 2	-	Don't overcommit. The total address space commit
 		for the system is not permitted to exceed swap + a
-		configurable percentage (default is 50) of physical RAM.
-		Depending on the percentage you use, in most situations
+		configurable amount (default is 50%) of physical RAM.
+		Depending on the amount you use, in most situations
 		this means a process will not be killed while accessing
 		pages but will receive errors on memory allocation as
 		appropriate.
@@ -26,7 +26,8 @@ The Linux kernel supports the following overcommit handling modes
 
 The overcommit policy is set via the sysctl `vm.overcommit_memory'.
 
-The overcommit percentage is set via `vm.overcommit_ratio'.
+The overcommit amount can be set via `vm.overcommit_ratio' (percentage)
+or `vm.overcommit_kbytes' (absolute value).
 
 The current overcommit limit and amount committed are viewable in
 /proc/meminfo as CommitLimit and Committed_AS respectively.

diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h
@@ -8,8 +8,8 @@
 #define MAX_DMA_ADDRESS	0xffffffffUL
 #else
 #define MAX_DMA_ADDRESS	({ \
-	extern unsigned long arm_dma_zone_size; \
-	arm_dma_zone_size ? \
+	extern phys_addr_t arm_dma_zone_size; \
+	arm_dma_zone_size && arm_dma_zone_size < (0x10000000 - PAGE_OFFSET) ? \
 		(PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; })
 #endif
 

diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
@@ -33,7 +33,7 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 
 void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 {
-	return alloc_bootmem_align(size, align);
+	return memblock_virt_alloc(size, align);
 }
 
 void __init arm_dt_memblock_reserve(void)

diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
@@ -717,7 +717,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
 	kernel_data.end     = virt_to_phys(_end - 1);
 
 	for_each_memblock(memory, region) {
-		res = alloc_bootmem_low(sizeof(*res));
+		res = memblock_virt_alloc(sizeof(*res), 0);
 		res->name  = "System RAM";
 		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
 		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;

diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2791,9 +2791,7 @@ static int __init _alloc_links(struct omap_hwmod_link **ml,
 	sz = sizeof(struct omap_hwmod_link) * LINKS_PER_OCP_IF;
 
 	*sl = NULL;
-	*ml = alloc_bootmem(sz);
-
-	memset(*ml, 0, sz);
+	*ml = memblock_virt_alloc(sz, 0);
 
 	*sl = (void *)(*ml) + sizeof(struct omap_hwmod_link);
 
@@ -2912,9 +2910,7 @@ static int __init _alloc_linkspace(struct omap_hwmod_ocp_if **ois)
 	pr_debug("omap_hwmod: %s: allocating %d byte linkspace (%d links)\n",
 		 __func__, sz, max_ls);
 
-	linkspace = alloc_bootmem(sz);
-
-	memset(linkspace, 0, sz);
+	linkspace = memblock_virt_alloc(sz, 0);
 
 	return 0;
 }

diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
@@ -92,9 +92,6 @@ void show_mem(unsigned int filter)
 	printk("Mem-info:\n");
 	show_free_areas(filter);
 
-	if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
-		return;
-
 	for_each_bank (i, mi) {
 		struct membank *bank = &mi->bank[i];
 		unsigned int pfn1, pfn2;
@@ -461,7 +458,7 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 	 * free the section of the memmap array.
 	 */
 	if (pg < pgend)
-		free_bootmem(pg, pgend - pg);
+		memblock_free_early(pg, pgend - pg);
 }
 
 /*

diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
@@ -31,74 +31,6 @@
 static unsigned long max_gap;
 #endif
 
-/**
- * show_mem - give short summary of memory stats
- *
- * Shows a simple page count of reserved and used pages in the system.
- * For discontig machines, it does this on a per-pgdat basis.
- */
-void show_mem(unsigned int filter)
-{
-	int i, total_reserved = 0;
-	int total_shared = 0, total_cached = 0;
-	unsigned long total_present = 0;
-	pg_data_t *pgdat;
-
-	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas(filter);
-	printk(KERN_INFO "Node memory in pages:\n");
-	if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
-		return;
-	for_each_online_pgdat(pgdat) {
-		unsigned long present;
-		unsigned long flags;
-		int shared = 0, cached = 0, reserved = 0;
-		int nid = pgdat->node_id;
-
-		if (skip_free_areas_node(filter, nid))
-			continue;
-		pgdat_resize_lock(pgdat, &flags);
-		present = pgdat->node_present_pages;
-		for(i = 0; i < pgdat->node_spanned_pages; i++) {
-			struct page *page;
-			if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
-				touch_nmi_watchdog();
-			if (pfn_valid(pgdat->node_start_pfn + i))
-				page = pfn_to_page(pgdat->node_start_pfn + i);
-			else {
-#ifdef CONFIG_VIRTUAL_MEM_MAP
-				if (max_gap < LARGE_GAP)
-					continue;
-#endif
-				i = vmemmap_find_next_valid_pfn(nid, i) - 1;
-				continue;
-			}
-			if (PageReserved(page))
-				reserved++;
-			else if (PageSwapCache(page))
-				cached++;
-			else if (page_count(page))
-				shared += page_count(page)-1;
-		}
-		pgdat_resize_unlock(pgdat, &flags);
-		total_present += present;
-		total_reserved += reserved;
-		total_cached += cached;
-		total_shared += shared;
-		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
-		       "shrd: %10d, swpd: %10d\n", nid,
-		       present, reserved, shared, cached);
-	}
-	printk(KERN_INFO "%ld pages of RAM\n", total_present);
-	printk(KERN_INFO "%d reserved pages\n", total_reserved);
-	printk(KERN_INFO "%d pages shared\n", total_shared);
-	printk(KERN_INFO "%d pages swap cached\n", total_cached);
-	printk(KERN_INFO "Total of %ld pages in page table cache\n",
-	       quicklist_total_size());
-	printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages());
-}
-
-
 /* physical address where the bootmem map is located */
 unsigned long bootmap_start;
 

diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
@@ -607,69 +607,6 @@ void *per_cpu_init(void)
 }
 #endif /* CONFIG_SMP */
 
-/**
- * show_mem - give short summary of memory stats
- *
- * Shows a simple page count of reserved and used pages in the system.
- * For discontig machines, it does this on a per-pgdat basis.
- */
-void show_mem(unsigned int filter)
-{
-	int i, total_reserved = 0;
-	int total_shared = 0, total_cached = 0;
-	unsigned long total_present = 0;
-	pg_data_t *pgdat;
-
-	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas(filter);
-	if (filter & SHOW_MEM_FILTER_PAGE_COUNT)
-		return;
-	printk(KERN_INFO "Node memory in pages:\n");
-	for_each_online_pgdat(pgdat) {
-		unsigned long present;
-		unsigned long flags;
-		int shared = 0, cached = 0, reserved = 0;
-		int nid = pgdat->node_id;
-
-		if (skip_free_areas_node(filter, nid))
-			continue;
-		pgdat_resize_lock(pgdat, &flags);
-		present = pgdat->node_present_pages;
-		for(i = 0; i < pgdat->node_spanned_pages; i++) {
-			struct page *page;
-			if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
-				touch_nmi_watchdog();
-			if (pfn_valid(pgdat->node_start_pfn + i))
-				page = pfn_to_page(pgdat->node_start_pfn + i);
-			else {
-				i = vmemmap_find_next_valid_pfn(nid, i) - 1;
-				continue;
-			}
-			if (PageReserved(page))
-				reserved++;
-			else if (PageSwapCache(page))
-				cached++;
-			else if (page_count(page))
-				shared += page_count(page)-1;
-		}
-		pgdat_resize_unlock(pgdat, &flags);
-		total_present += present;
-		total_reserved += reserved;
-		total_cached += cached;
-		total_shared += shared;
-		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, "
-		       "shrd: %10d, swpd: %10d\n", nid,
-		       present, reserved, shared, cached);
-	}
-	printk(KERN_INFO "%ld pages of RAM\n", total_present);
-	printk(KERN_INFO "%d reserved pages\n", total_reserved);
-	printk(KERN_INFO "%d pages shared\n", total_shared);
-	printk(KERN_INFO "%d pages swap cached\n", total_cached);
-	printk(KERN_INFO "Total of %ld pages in page table cache\n",
-	       quicklist_total_size());
-	printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages());
-}
-
 /**
  * call_pernode_memory - use SRAT to call callback functions with node info
  * @start: physical start of range

diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
@@ -684,3 +684,51 @@ per_linux32_init(void)
 }
 
 __initcall(per_linux32_init);
+
+/**
+ * show_mem - give short summary of memory stats
+ *
+ * Shows a simple page count of reserved and used pages in the system.
+ * For discontig machines, it does this on a per-pgdat basis.
+ */
+void show_mem(unsigned int filter)
+{
+	int total_reserved = 0;
+	unsigned long total_present = 0;
+	pg_data_t *pgdat;
+
+	printk(KERN_INFO "Mem-info:\n");
+	show_free_areas(filter);
+	printk(KERN_INFO "Node memory in pages:\n");
+	for_each_online_pgdat(pgdat) {
+		unsigned long present;
+		unsigned long flags;
+		int reserved = 0;
+		int nid = pgdat->node_id;
+		int zoneid;
+
+		if (skip_free_areas_node(filter, nid))
+			continue;
+		pgdat_resize_lock(pgdat, &flags);
+
+		for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+			struct zone *zone = &pgdat->node_zones[zoneid];
+			if (!populated_zone(zone))
+				continue;
+
+			reserved += zone->present_pages - zone->managed_pages;
+		}
+		present = pgdat->node_present_pages;
+
+		pgdat_resize_unlock(pgdat, &flags);
+		total_present += present;
+		total_reserved += reserved;
+		printk(KERN_INFO "Node %4d:  RAM: %11ld, rsvd: %8d, ",
+		       nid, present, reserved);
+	}
+	printk(KERN_INFO "%ld pages of RAM\n", total_present);
+	printk(KERN_INFO "%d reserved pages\n", total_reserved);
+	printk(KERN_INFO "Total of %ld pages in page table cache\n",
+	       quicklist_total_size());
+	printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages());
+}
diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c
@@ -204,7 +204,8 @@ static void __init do_init_bootmem(void)
 		start_pfn = memblock_region_memory_base_pfn(reg);
 		end_pfn = memblock_region_memory_end_pfn(reg);
 		memblock_set_node(PFN_PHYS(start_pfn),
-				  PFN_PHYS(end_pfn - start_pfn), 0);
+				  PFN_PHYS(end_pfn - start_pfn),
+				  &memblock.memory, 0);
 	}
 
 	/* All of system RAM sits in node 0 for the non-NUMA case */

diff --git a/arch/metag/mm/numa.c b/arch/metag/mm/numa.c
@@ -42,7 +42,8 @@ void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
 	memblock_add(start, end - start);
 
 	memblock_set_node(PFN_PHYS(start_pfn),
-			  PFN_PHYS(end_pfn - start_pfn), nid);
+			  PFN_PHYS(end_pfn - start_pfn),
+			  &memblock.memory, nid);
 
 	/* Node-local pgdat */
 	pgdat_paddr = memblock_alloc_base(sizeof(struct pglist_data),

diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
@@ -192,7 +192,8 @@ void __init setup_memory(void)
 		start_pfn = memblock_region_memory_base_pfn(reg);
 		end_pfn = memblock_region_memory_end_pfn(reg);
 		memblock_set_node(start_pfn << PAGE_SHIFT,
-					(end_pfn - start_pfn) << PAGE_SHIFT, 0);
+				  (end_pfn - start_pfn) << PAGE_SHIFT,
+				  &memblock.memory, 0);
 	}
 
 	/* free bootmem is whole main memory */