summaryrefslogtreecommitdiffstats
path: root/mm/mm_init.c
blob: 4e0e26591dfaa6f242c4514fd83bdb54f7194b43 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
/*
 * mm_init.c - Memory initialisation verification and debugging
 *
 * Copyright 2008 IBM Corporation, 2008
 * Author Mel Gorman <mel@csn.ul.ie>
 *
 */
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/kobject.h>
#include <linux/module.h>
#include "internal.h"

#ifdef CONFIG_DEBUG_MEMORY_INIT
int mminit_loglevel;

#ifndef SECTIONS_SHIFT
#define SECTIONS_SHIFT	0
#endif

/* The zonelists are simply reported, validation is manual. */
void mminit_verify_zonelist(void)
{
	int nid;

	if (mminit_loglevel < MMINIT_VERIFY)
		return;

	for_each_online_node(nid) {
		pg_data_t *pgdat = NODE_DATA(nid);
		struct zone *zone;
		struct zoneref *z;
		struct zonelist *zonelist;
		int i, listid, zoneid;

		BUG_ON(MAX_ZONELISTS > 2);
		for (i = 0; i < MAX_ZONELISTS * MAX_NR_ZONES; i++) {

			/* Identify the zone and nodelist */
			zoneid = i % MAX_NR_ZONES;
			listid = i / MAX_NR_ZONES;
			zonelist = &pgdat->node_zonelists[listid];
			zone = &pgdat->node_zones[zoneid];
			if (!populated_zone(zone))
				continue;

			/* Print information about the zonelist */
			printk(KERN_DEBUG "mminit::zonelist %s %d:%s = ",
				listid > 0 ? "thisnode" : "general", nid,
				zone->name);

			/* Iterate the zonelist */
			for_each_zone_zonelist(zone, z, zonelist, zoneid) {
#ifdef CONFIG_NUMA
				printk(KERN_CONT "%d:%s ",
					zone->node, zone->name);
#else
				printk(KERN_CONT "0:%s ", zone->name);
#endif /* CONFIG_NUMA */
			}
			printk(KERN_CONT "\n");
		}
	}
}

void __init mminit_verify_pageflags_layout(void)
{
	int shift, width;
	unsigned long or_mask, add_mask;

	shift = 8 * sizeof(unsigned long);
	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH;
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
		"Section %d Node %d Zone %d Flags %d\n",
		SECTIONS_WIDTH,
		NODES_WIDTH,
		ZONES_WIDTH,
		NR_PAGEFLAGS);
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
		"Section %d Node %d Zone %d\n",
		SECTIONS_SHIFT,
		NODES_SHIFT,
		ZONES_SHIFT);
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_offsets",
		"Section %lu Node %lu Zone %lu\n",
		(unsigned long)SECTIONS_PGSHIFT,
		(unsigned long)NODES_PGSHIFT,
		(unsigned long)ZONES_PGSHIFT);
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_zoneid",
		"Zone ID: %lu -> %lu\n",
		(unsigned long)ZONEID_PGOFF,
		(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT));
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_usage",
		"location: %d -> %d unused %d -> %d flags %d -> %d\n",
		shift, width, width, NR_PAGEFLAGS, NR_PAGEFLAGS, 0);
#ifdef NODE_NOT_IN_PAGE_FLAGS
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
		"Node not in page flags");
#endif

	if (SECTIONS_WIDTH) {
		shift -= SECTIONS_WIDTH;
		BUG_ON(shift != SECTIONS_PGSHIFT);
	}
	if (NODES_WIDTH) {
		shift -= NODES_WIDTH;
		BUG_ON(shift != NODES_PGSHIFT);
	}
	if (ZONES_WIDTH) {
		shift -= ZONES_WIDTH;
		BUG_ON(shift != ZONES_PGSHIFT);
	}

	/* Check for bitmask overlaps */
	or_mask = (ZONES_MASK << ZONES_PGSHIFT) |
			(NODES_MASK << NODES_PGSHIFT) |
			(SECTIONS_MASK << SECTIONS_PGSHIFT);
	add_mask = (ZONES_MASK << ZONES_PGSHIFT) +
			(NODES_MASK << NODES_PGSHIFT) +
			(SECTIONS_MASK << SECTIONS_PGSHIFT);
	BUG_ON(or_mask != add_mask);
}

void __meminit mminit_verify_page_links(struct page *page, enum zone_type zone,
			unsigned long nid, unsigned long pfn)
{
	BUG_ON(page_to_nid(page) != nid);
	BUG_ON(page_zonenum(page) != zone);
	BUG_ON(page_to_pfn(page) != pfn);
}

static __init int set_mminit_loglevel(char *str)
{
	get_option(&str, &mminit_loglevel);
	return 0;
}
early_param("mminit_loglevel", set_mminit_loglevel);
#endif /* CONFIG_DEBUG_MEMORY_INIT */

struct kobject *mm_kobj;
EXPORT_SYMBOL_GPL(mm_kobj);

static int __init mm_sysfs_init(void)
{
	mm_kobj = kobject_create_and_add("mm", kernel_kobj);
	if (!mm_kobj)
		return -ENOMEM;

	return 0;
}

__initcall(mm_sysfs_init);
pan class="hl opt">; if (kobject_actions[action][count] != '\0') continue; *type = action; ret = 0; break; } out: return ret; } #ifdef CONFIG_NET static int kobj_bcast_filter(struct sock *dsk, struct sk_buff *skb, void *data) { struct kobject *kobj = data; const struct kobj_ns_type_operations *ops; ops = kobj_ns_ops(kobj); if (ops) { const void *sock_ns, *ns; ns = kobj->ktype->namespace(kobj); sock_ns = ops->netlink_ns(dsk); return sock_ns != ns; } return 0; } #endif static int kobj_usermode_filter(struct kobject *kobj) { const struct kobj_ns_type_operations *ops; ops = kobj_ns_ops(kobj); if (ops) { const void *init_ns, *ns; ns = kobj->ktype->namespace(kobj); init_ns = ops->initial_ns(); return ns != init_ns; } return 0; } /** * kobject_uevent_env - send an uevent with environmental data * * @action: action that is happening * @kobj: struct kobject that the action is happening to * @envp_ext: pointer to environmental data * * Returns 0 if kobject_uevent_env() is completed with success or the * corresponding error when it fails. */ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp_ext[]) { struct kobj_uevent_env *env; const char *action_string = kobject_actions[action]; const char *devpath = NULL; const char *subsystem; struct kobject *top_kobj; struct kset *kset; const struct kset_uevent_ops *uevent_ops; int i = 0; int retval = 0; #ifdef CONFIG_NET struct uevent_sock *ue_sk; #endif pr_debug("kobject: '%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); /* search the kset we belong to */ top_kobj = kobj; while (!top_kobj->kset && top_kobj->parent) top_kobj = top_kobj->parent; if (!top_kobj->kset) { pr_debug("kobject: '%s' (%p): %s: attempted to send uevent " "without kset!\n", kobject_name(kobj), kobj, __func__); return -EINVAL; } kset = top_kobj->kset; uevent_ops = kset->uevent_ops; /* skip the event, if uevent_suppress is set*/ if (kobj->uevent_suppress) { pr_debug("kobject: '%s' (%p): %s: uevent_suppress " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* skip the event, if the filter returns zero. */ if (uevent_ops && uevent_ops->filter) if (!uevent_ops->filter(kset, kobj)) { pr_debug("kobject: '%s' (%p): %s: filter function " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* originating subsystem */ if (uevent_ops && uevent_ops->name) subsystem = uevent_ops->name(kset, kobj); else subsystem = kobject_name(&kset->kobj); if (!subsystem) { pr_debug("kobject: '%s' (%p): %s: unset subsystem caused the " "event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* environment buffer */ env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL); if (!env) return -ENOMEM; /* complete object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { retval = -ENOENT; goto exit; } /* default keys */ retval = add_uevent_var(env, "ACTION=%s", action_string); if (retval) goto exit; retval = add_uevent_var(env, "DEVPATH=%s", devpath); if (retval) goto exit; retval = add_uevent_var(env, "SUBSYSTEM=%s", subsystem); if (retval) goto exit; /* keys passed in from the caller */ if (envp_ext) { for (i = 0; envp_ext[i]; i++) { retval = add_uevent_var(env, "%s", envp_ext[i]); if (retval) goto exit; } } /* let the kset specific function add its stuff */ if (uevent_ops && uevent_ops->uevent) { retval = uevent_ops->uevent(kset, kobj, env); if (retval) { pr_debug("kobject: '%s' (%p): %s: uevent() returned " "%d\n", kobject_name(kobj), kobj, __func__, retval); goto exit; } } /* * Mark "add" and "remove" events in the object to ensure proper * events to userspace during automatic cleanup. If the object did * send an "add" event, "remove" will automatically generated by * the core, if not already done by the caller. */ if (action == KOBJ_ADD) kobj->state_add_uevent_sent = 1; else if (action == KOBJ_REMOVE) kobj->state_remove_uevent_sent = 1; mutex_lock(&uevent_sock_mutex); /* we will send an event, so request a new sequence number */ retval = add_uevent_var(env, "SEQNUM=%llu", (unsigned long long)++uevent_seqnum); if (retval) { mutex_unlock(&uevent_sock_mutex); goto exit; } #if defined(CONFIG_NET) /* send netlink message */ list_for_each_entry(ue_sk, &uevent_sock_list, list) { struct sock *uevent_sock = ue_sk->sk; struct sk_buff *skb; size_t len; if (!netlink_has_listeners(uevent_sock, 1)) continue; /* allocate message with the maximum possible size */ len = strlen(action_string) + strlen(devpath) + 2; skb = alloc_skb(len + env->buflen, GFP_KERNEL); if (skb) { char *scratch; /* add header */ scratch = skb_put(skb, len); sprintf(scratch, "%s@%s", action_string, devpath); /* copy keys to our continuous event payload buffer */ for (i = 0; i < env->envp_idx; i++) { len = strlen(env->envp[i]) + 1; scratch = skb_put(skb, len); strcpy(scratch, env->envp[i]); } NETLINK_CB(skb).dst_group = 1; retval = netlink_broadcast_filtered(uevent_sock, skb, 0, 1, GFP_KERNEL, kobj_bcast_filter, kobj); /* ENOBUFS should be handled in userspace */ if (retval == -ENOBUFS || retval == -ESRCH) retval = 0; } else retval = -ENOMEM; } #endif mutex_unlock(&uevent_sock_mutex); /* call uevent_helper, usually only enabled during early boot */ if (uevent_helper[0] && !kobj_usermode_filter(kobj)) { char *argv [3]; argv [0] = uevent_helper; argv [1] = (char *)subsystem; argv [2] = NULL; retval = add_uevent_var(env, "HOME=/"); if (retval) goto exit; retval = add_uevent_var(env, "PATH=/sbin:/bin:/usr/sbin:/usr/bin"); if (retval) goto exit; retval = call_usermodehelper(argv[0], argv, env->envp, UMH_WAIT_EXEC); } exit: kfree(devpath); kfree(env); return retval; } EXPORT_SYMBOL_GPL(kobject_uevent_env); /** * kobject_uevent - notify userspace by sending an uevent * * @action: action that is happening * @kobj: struct kobject that the action is happening to * * Returns 0 if kobject_uevent() is completed with success or the * corresponding error when it fails. */ int kobject_uevent(struct kobject *kobj, enum kobject_action action) { return kobject_uevent_env(kobj, action, NULL); } EXPORT_SYMBOL_GPL(kobject_uevent); /** * add_uevent_var - add key value string to the environment buffer * @env: environment buffer structure * @format: printf format for the key=value pair * * Returns 0 if environment variable was added successfully or -ENOMEM * if no space was available. */ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) { va_list args; int len; if (env->envp_idx >= ARRAY_SIZE(env->envp)) { WARN(1, KERN_ERR "add_uevent_var: too many keys\n"); return -ENOMEM; } va_start(args, format); len = vsnprintf(&env->buf[env->buflen], sizeof(env->buf) - env->buflen, format, args); va_end(args); if (len >= (sizeof(env->buf) - env->buflen)) { WARN(1, KERN_ERR "add_uevent_var: buffer size too small\n"); return -ENOMEM; } env->envp[env->envp_idx++] = &env->buf[env->buflen]; env->buflen += len + 1; return 0; } EXPORT_SYMBOL_GPL(add_uevent_var); #if defined(CONFIG_NET) static int uevent_net_init(struct net *net) { struct uevent_sock *ue_sk; struct netlink_kernel_cfg cfg = { .groups = 1, .flags = NL_CFG_F_NONROOT_RECV, }; ue_sk = kzalloc(sizeof(*ue_sk), GFP_KERNEL); if (!ue_sk) return -ENOMEM; ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, &cfg); if (!ue_sk->sk) { printk(KERN_ERR "kobject_uevent: unable to create netlink socket!\n"); kfree(ue_sk); return -ENODEV; } mutex_lock(&uevent_sock_mutex); list_add_tail(&ue_sk->list, &uevent_sock_list); mutex_unlock(&uevent_sock_mutex); return 0; } static void uevent_net_exit(struct net *net) { struct uevent_sock *ue_sk; mutex_lock(&uevent_sock_mutex); list_for_each_entry(ue_sk, &uevent_sock_list, list) { if (sock_net(ue_sk->sk) == net) goto found; } mutex_unlock(&uevent_sock_mutex); return; found: list_del(&ue_sk->list); mutex_unlock(&uevent_sock_mutex); netlink_kernel_release(ue_sk->sk); kfree(ue_sk); } static struct pernet_operations uevent_net_ops = { .init = uevent_net_init, .exit = uevent_net_exit, }; static int __init kobject_uevent_init(void) { return register_pernet_subsys(&uevent_net_ops); } postcore_initcall(kobject_uevent_init); #endif