Merge branch 'topic/slab/earlyboot' of...

Merge branch 'topic/slab/earlyboot' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6

* 'topic/slab/earlyboot' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6:
  vgacon: use slab allocator instead of the bootmem allocator
  irq: use kcalloc() instead of the bootmem allocator
  sched: use slab in cpupri_init()
  sched: use alloc_cpumask_var() instead of alloc_bootmem_cpumask_var()
  memcg: don't use bootmem allocator in setup code
  irq/cpumask: make memoryless node zero happy
  x86: remove some alloc_bootmem_cpumask_var calling
  vt: use kzalloc() instead of the bootmem allocator
  sched: use kzalloc() instead of the bootmem allocator
  init: introduce mm_init()
  vmalloc: use kzalloc() instead of alloc_bootmem()
  slab: setup allocators earlier in the boot sequence
  bootmem: fix slab fallback on numa
  bootmem: use slab if bootmem is no longer available

arch/x86/kernel/apic/io_apic.c

@@ -177,16 +177,18 @@ int __init arch_early_irq_init(void)
 	struct irq_cfg *cfg;
 	struct irq_desc *desc;
 	int count;
+	int node;
 	int i;
 
 	cfg = irq_cfgx;
 	count = ARRAY_SIZE(irq_cfgx);
+	node= cpu_to_node(boot_cpu_id);
 
 	for (i = 0; i < count; i++) {
 		desc = irq_to_desc(i);
 		desc->chip_data = &cfg[i];
-		alloc_bootmem_cpumask_var(&cfg[i].domain);
-		alloc_bootmem_cpumask_var(&cfg[i].old_domain);
+		alloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node);
+		alloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node);
 		if (i < NR_IRQS_LEGACY)
 			cpumask_setall(cfg[i].domain);
 	}

drivers/char/vt.c

@@ -95,7 +95,6 @@
 #include <linux/timer.h>
 #include <linux/interrupt.h>
 #include <linux/workqueue.h>
-#include <linux/bootmem.h>
 #include <linux/pm.h>
 #include <linux/font.h>
 #include <linux/bitops.h>
@@ -2875,14 +2874,11 @@ static int __init con_init(void)
 		mod_timer(&console_timer, jiffies + blankinterval);
 	}
 
-	/*
-	 * kmalloc is not running yet - we use the bootmem allocator.
-	 */
 	for (currcons = 0; currcons < MIN_NR_CONSOLES; currcons++) {
-		vc_cons[currcons].d = vc = alloc_bootmem(sizeof(struct vc_data));
+		vc_cons[currcons].d = vc = kzalloc(sizeof(struct vc_data), GFP_NOWAIT);
 		INIT_WORK(&vc_cons[currcons].SAK_work, vc_SAK);
 		visual_init(vc, currcons, 1);
-		vc->vc_screenbuf = (unsigned short *)alloc_bootmem(vc->vc_screenbuf_size);
+		vc->vc_screenbuf = kzalloc(vc->vc_screenbuf_size, GFP_NOWAIT);
 		vc->vc_kmalloced = 0;
 		vc_init(vc, vc->vc_rows, vc->vc_cols,
 			currcons || !vc->vc_sw->con_save_screen);

drivers/video/console/vgacon.c

@@ -180,7 +180,7 @@ static inline void vga_set_mem_top(struct vc_data *c)
 }
 
 #ifdef CONFIG_VGACON_SOFT_SCROLLBACK
-#include <linux/bootmem.h>
+#include <linux/slab.h>
 /* software scrollback */
 static void *vgacon_scrollback;
 static int vgacon_scrollback_tail;
@@ -210,8 +210,7 @@ static void vgacon_scrollback_init(int pitch)
  */
 static void __init_refok vgacon_scrollback_startup(void)
 {
-	vgacon_scrollback = alloc_bootmem(CONFIG_VGACON_SOFT_SCROLLBACK_SIZE
-					  * 1024);
+	vgacon_scrollback = kcalloc(CONFIG_VGACON_SOFT_SCROLLBACK_SIZE, 1024, GFP_NOWAIT);
 	vgacon_scrollback_init(vga_video_num_columns * 2);
 }
 

include/linux/irq.h

@@ -430,23 +430,19 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
  * Returns true if successful (or not required).
  */
 static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
-								bool boot)
+							bool boot)
 {
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	if (boot) {
-		alloc_bootmem_cpumask_var(&desc->affinity);
+	gfp_t gfp = GFP_ATOMIC;
 
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-		alloc_bootmem_cpumask_var(&desc->pending_mask);
-#endif
-		return true;
-	}
+	if (boot)
+		gfp = GFP_NOWAIT;
 
-	if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	if (!alloc_cpumask_var_node(&desc->affinity, gfp, node))
 		return false;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) {
+	if (!alloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
 		free_cpumask_var(desc->affinity);
 		return false;
 	}

init/main.c

@@ -533,6 +533,16 @@ void __init __weak thread_info_cache_init(void)
 {
 }
 
+/*
+ * Set up kernel memory allocators
+ */
+static void __init mm_init(void)
+{
+	mem_init();
+	kmem_cache_init();
+	vmalloc_init();
+}
+
 asmlinkage void __init start_kernel(void)
 {
 	char * command_line;
@@ -574,6 +584,23 @@ asmlinkage void __init start_kernel(void)
 	setup_nr_cpu_ids();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
 
+	build_all_zonelists();
+	page_alloc_init();
+
+	printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
+	parse_early_param();
+	parse_args("Booting kernel", static_command_line, __start___param,
+		   __stop___param - __start___param,
+		   &unknown_bootoption);
+	/*
+	 * These use large bootmem allocations and must precede
+	 * kmem_cache_init()
+	 */
+	pidhash_init();
+	vfs_caches_init_early();
+	sort_main_extable();
+	trap_init();
+	mm_init();
 	/*
 	 * Set up the scheduler prior starting any interrupts (such as the
 	 * timer interrupt). Full topology setup happens at smp_init()
@@ -585,25 +612,15 @@ asmlinkage void __init start_kernel(void)
 	 * fragile until we cpu_idle() for the first time.
 	 */
 	preempt_disable();
-	build_all_zonelists();
-	page_alloc_init();
-	printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
-	parse_early_param();
-	parse_args("Booting kernel", static_command_line, __start___param,
-		   __stop___param - __start___param,
-		   &unknown_bootoption);
 	if (!irqs_disabled()) {
 		printk(KERN_WARNING "start_kernel(): bug: interrupts were "
 				"enabled *very* early, fixing it\n");
 		local_irq_disable();
 	}
-	sort_main_extable();
-	trap_init();
 	rcu_init();
 	/* init some links before init_ISA_irqs() */
 	early_irq_init();
 	init_IRQ();
-	pidhash_init();
 	init_timers();
 	hrtimers_init();
 	softirq_init();
@@ -645,14 +662,10 @@ asmlinkage void __init start_kernel(void)
 		initrd_start = 0;
 	}
 #endif
-	vmalloc_init();
-	vfs_caches_init_early();
 	cpuset_init_early();
 	page_cgroup_init();
-	mem_init();
 	enable_debug_pagealloc();
 	cpu_hotplug_init();
-	kmem_cache_init();
 	kmemtrace_init();
 	debug_objects_mem_init();
 	idr_init_cache();

kernel/cpuset.c

@@ -1857,7 +1857,7 @@ struct cgroup_subsys cpuset_subsys = {
 
 int __init cpuset_init_early(void)
 {
-	alloc_bootmem_cpumask_var(&top_cpuset.cpus_allowed);
+	alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_NOWAIT);
 
 	top_cpuset.mems_generation = cpuset_mems_generation++;
 	return 0;

kernel/irq/handle.c

@@ -150,6 +150,7 @@ int __init early_irq_init(void)
 {
 	struct irq_desc *desc;
 	int legacy_count;
+	int node;
 	int i;
 
 	init_irq_default_affinity();
@@ -160,20 +161,20 @@ int __init early_irq_init(void)
 
 	desc = irq_desc_legacy;
 	legacy_count = ARRAY_SIZE(irq_desc_legacy);
+ 	node = first_online_node;
 
 	/* allocate irq_desc_ptrs array based on nr_irqs */
-	irq_desc_ptrs = alloc_bootmem(nr_irqs * sizeof(void *));
+	irq_desc_ptrs = kcalloc(nr_irqs, sizeof(void *), GFP_NOWAIT);
 
 	/* allocate based on nr_cpu_ids */
-	/* FIXME: invert kstat_irgs, and it'd be a per_cpu_alloc'd thing */
-	kstat_irqs_legacy = alloc_bootmem(NR_IRQS_LEGACY * nr_cpu_ids *
-					  sizeof(int));
+	kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids *
+					  sizeof(int), GFP_NOWAIT, node);
 
 	for (i = 0; i < legacy_count; i++) {
 		desc[i].irq = i;
 		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-		alloc_desc_masks(&desc[i], 0, true);
+		alloc_desc_masks(&desc[i], node, true);
 		init_desc_masks(&desc[i]);
 		irq_desc_ptrs[i] = desc + i;
 	}

kernel/profile.c

@@ -111,12 +111,6 @@ int __ref profile_init(void)
 	/* only text is profiled */
 	prof_len = (_etext - _stext) >> prof_shift;
 	buffer_bytes = prof_len*sizeof(atomic_t);
-	if (!slab_is_available()) {
-		prof_buffer = alloc_bootmem(buffer_bytes);
-		alloc_bootmem_cpumask_var(&prof_cpu_mask);
-		cpumask_copy(prof_cpu_mask, cpu_possible_mask);
-		return 0;
-	}
 
 	if (!alloc_cpumask_var(&prof_cpu_mask, GFP_KERNEL))
 		return -ENOMEM;

kernel/sched.c

@@ -68,7 +68,6 @@
 #include <linux/pagemap.h>
 #include <linux/hrtimer.h>
 #include <linux/tick.h>
-#include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
@@ -7782,24 +7781,21 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 
 static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
 {
+	gfp_t gfp = GFP_KERNEL;
+
 	memset(rd, 0, sizeof(*rd));
 
-	if (bootmem) {
-		alloc_bootmem_cpumask_var(&def_root_domain.span);
-		alloc_bootmem_cpumask_var(&def_root_domain.online);
-		alloc_bootmem_cpumask_var(&def_root_domain.rto_mask);
-		cpupri_init(&rd->cpupri, true);
-		return 0;
-	}
+	if (bootmem)
+		gfp = GFP_NOWAIT;
 
-	if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+	if (!alloc_cpumask_var(&rd->span, gfp))
 		goto out;
-	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+	if (!alloc_cpumask_var(&rd->online, gfp))
 		goto free_span;
-	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+	if (!alloc_cpumask_var(&rd->rto_mask, gfp))
 		goto free_online;
 
-	if (cpupri_init(&rd->cpupri, false) != 0)
+	if (cpupri_init(&rd->cpupri, bootmem) != 0)
 		goto free_rto_mask;
 	return 0;
 
@@ -9123,7 +9119,7 @@ void __init sched_init(void)
 	 * we use alloc_bootmem().
 	 */
 	if (alloc_size) {
-		ptr = (unsigned long)alloc_bootmem(alloc_size);
+		ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		init_task_group.se = (struct sched_entity **)ptr;
@@ -9314,13 +9310,13 @@ void __init sched_init(void)
 	current->sched_class = &fair_sched_class;
 
 	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
-	alloc_bootmem_cpumask_var(&nohz_cpu_mask);
+	alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ
-	alloc_bootmem_cpumask_var(&nohz.cpu_mask);
-	alloc_bootmem_cpumask_var(&nohz.ilb_grp_nohz_mask);
+	alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+	alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
 #endif
-	alloc_bootmem_cpumask_var(&cpu_isolated_map);
+	alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 #endif /* SMP */
 
 	scheduler_running = 1;

kernel/sched_cpupri.c

@@ -154,8 +154,12 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
  */
 int __init_refok cpupri_init(struct cpupri *cp, bool bootmem)
 {
+	gfp_t gfp = GFP_KERNEL;
 	int i;
 
+	if (bootmem)
+		gfp = GFP_NOWAIT;
+
 	memset(cp, 0, sizeof(*cp));
 
 	for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
@@ -163,9 +167,7 @@ int __init_refok cpupri_init(struct cpupri *cp, bool bootmem)
 
 		spin_lock_init(&vec->lock);
 		vec->count = 0;
-		if (bootmem)
-			alloc_bootmem_cpumask_var(&vec->mask);
-		else if (!zalloc_cpumask_var(&vec->mask, GFP_KERNEL))
+		if (!zalloc_cpumask_var(&vec->mask, gfp))
 			goto cleanup;
 	}
 

lib/cpumask.c

@@ -92,15 +92,8 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
  */
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 {
-	if (likely(slab_is_available()))
-		*mask = kmalloc_node(cpumask_size(), flags, node);
-	else {
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-		printk(KERN_ERR
-			"=> alloc_cpumask_var: kmalloc not available!\n");
-#endif
-		*mask = NULL;
-	}
+	*mask = kmalloc_node(cpumask_size(), flags, node);
+
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 	if (!*mask) {
 		printk(KERN_ERR "=> alloc_cpumask_var: failed!\n");

mm/bootmem.c

@@ -532,6 +532,9 @@ static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata,
 					unsigned long size, unsigned long align,
 					unsigned long goal, unsigned long limit)
 {
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc(size, GFP_NOWAIT);
+
 #ifdef CONFIG_HAVE_ARCH_BOOTMEM
 	bootmem_data_t *p_bdata;
 
@@ -662,6 +665,9 @@ static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata,
 void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
 {
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
 	return ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0);
 }
 
@@ -693,6 +699,9 @@ void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
 {
 	void *ptr;
 
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
 	ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size, align, goal, 0);
 	if (ptr)
 		return ptr;
@@ -745,6 +754,9 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 				       unsigned long align, unsigned long goal)
 {
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
 	return ___alloc_bootmem_node(pgdat->bdata, size, align,
 				goal, ARCH_LOW_ADDRESS_LIMIT);
 }

mm/page_cgroup.c

@@ -47,6 +47,8 @@ static int __init alloc_node_page_cgroup(int nid)
 	struct page_cgroup *base, *pc;
 	unsigned long table_size;
 	unsigned long start_pfn, nr_pages, index;
+	struct page *page;
+	unsigned int order;
 
 	start_pfn = NODE_DATA(nid)->node_start_pfn;
 	nr_pages = NODE_DATA(nid)->node_spanned_pages;
@@ -55,11 +57,13 @@ static int __init alloc_node_page_cgroup(int nid)
 		return 0;
 
 	table_size = sizeof(struct page_cgroup) * nr_pages;
-
-	base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
-			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
-	if (!base)
+	order = get_order(table_size);
+	page = alloc_pages_node(nid, GFP_NOWAIT | __GFP_ZERO, order);
+	if (!page)
+		page = alloc_pages_node(-1, GFP_NOWAIT | __GFP_ZERO, order);
+	if (!page)
 		return -ENOMEM;
+	base = page_address(page);
 	for (index = 0; index < nr_pages; index++) {
 		pc = base + index;
 		__init_page_cgroup(pc, start_pfn + index);

mm/slub.c

@@ -2557,13 +2557,16 @@ static struct kmem_cache *create_kmalloc_cache(struct kmem_cache *s,
 	if (gfp_flags & SLUB_DMA)
 		flags = SLAB_CACHE_DMA;
 
-	down_write(&slub_lock);
+	/*
+	 * This function is called with IRQs disabled during early-boot on
+	 * single CPU so there's no need to take slub_lock here.
+	 */
 	if (!kmem_cache_open(s, gfp_flags, name, size, ARCH_KMALLOC_MINALIGN,
 								flags, NULL))
 		goto panic;
 
 	list_add(&s->list, &slab_caches);
-	up_write(&slub_lock);
+
 	if (sysfs_slab_add(s))
 		goto panic;
 	return s;
@@ -3021,7 +3024,7 @@ void __init kmem_cache_init(void)
 	 * kmem_cache_open for slab_state == DOWN.
 	 */
 	create_kmalloc_cache(&kmalloc_caches[0], "kmem_cache_node",
-		sizeof(struct kmem_cache_node), GFP_KERNEL);
+		sizeof(struct kmem_cache_node), GFP_NOWAIT);
 	kmalloc_caches[0].refcount = -1;
 	caches++;
 
@@ -3034,16 +3037,16 @@ void __init kmem_cache_init(void)
 	/* Caches that are not of the two-to-the-power-of size */
 	if (KMALLOC_MIN_SIZE <= 64) {
 		create_kmalloc_cache(&kmalloc_caches[1],
-				"kmalloc-96", 96, GFP_KERNEL);
+				"kmalloc-96", 96, GFP_NOWAIT);
 		caches++;
 		create_kmalloc_cache(&kmalloc_caches[2],
-				"kmalloc-192", 192, GFP_KERNEL);
+				"kmalloc-192", 192, GFP_NOWAIT);
 		caches++;
 	}
 
 	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
 		create_kmalloc_cache(&kmalloc_caches[i],
-			"kmalloc", 1 << i, GFP_KERNEL);
+			"kmalloc", 1 << i, GFP_NOWAIT);
 		caches++;
 	}
 
@@ -3080,7 +3083,7 @@ void __init kmem_cache_init(void)
 	/* Provide the correct kmalloc names now that the caches are up */
 	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++)
 		kmalloc_caches[i]. name =
-			kasprintf(GFP_KERNEL, "kmalloc-%d", 1 << i);
+			kasprintf(GFP_NOWAIT, "kmalloc-%d", 1 << i);
 
 #ifdef CONFIG_SMP
 	register_cpu_notifier(&slab_notifier);

mm/vmalloc.c

@@ -23,7 +23,6 @@
 #include <linux/rbtree.h>
 #include <linux/radix-tree.h>
 #include <linux/rcupdate.h>
-#include <linux/bootmem.h>
 #include <linux/pfn.h>
 
 #include <asm/atomic.h>
@@ -1032,7 +1031,7 @@ void __init vmalloc_init(void)
 
 	/* Import existing vmlist entries. */
 	for (tmp = vmlist; tmp; tmp = tmp->next) {
-		va = alloc_bootmem(sizeof(struct vmap_area));
+		va = kzalloc(sizeof(struct vmap_area), GFP_NOWAIT);
 		va->flags = tmp->flags | VM_VM_AREA;
 		va->va_start = (unsigned long)tmp->addr;
 		va->va_end = va->va_start + tmp->size;