Revision efad4e475c312456edb3c789d0996d12ed744c13 authored by Michal Hocko on 01 February 2019, 22:20:34 UTC, committed by Linus Torvalds on 01 February 2019, 23:46:23 UTC
Patch series "mm, memory_hotplug: fix uninitialized pages fallouts", v2. Mikhail Zaslonko has posted fixes for the two bugs quite some time ago [1]. I have pushed back on those fixes because I believed that it is much better to plug the problem at the initialization time rather than play whack-a-mole all over the hotplug code and find all the places which expect the full memory section to be initialized. We have ended up with commit 2830bf6f05fb ("mm, memory_hotplug: initialize struct pages for the full memory section") merged and cause a regression [2][3]. The reason is that there might be memory layouts when two NUMA nodes share the same memory section so the merged fix is simply incorrect. In order to plug this hole we really have to be zone range aware in those handlers. I have split up the original patch into two. One is unchanged (patch 2) and I took a different approach for `removable' crash. [1] http://lkml.kernel.org/r/20181105150401.97287-2-zaslonko@linux.ibm.com [2] https://bugzilla.redhat.com/show_bug.cgi?id=1666948 [3] http://lkml.kernel.org/r/20190125163938.GA20411@dhcp22.suse.cz This patch (of 2): Mikhail has reported the following VM_BUG_ON triggered when reading sysfs removable state of a memory block: page:000003d08300c000 is uninitialized and poisoned page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p)) Call Trace: is_mem_section_removable+0xb4/0x190 show_mem_removable+0x9a/0xd8 dev_attr_show+0x34/0x70 sysfs_kf_seq_show+0xc8/0x148 seq_read+0x204/0x480 __vfs_read+0x32/0x178 vfs_read+0x82/0x138 ksys_read+0x5a/0xb0 system_call+0xdc/0x2d8 Last Breaking-Event-Address: is_mem_section_removable+0xb4/0x190 Kernel panic - not syncing: Fatal exception: panic_on_oops The reason is that the memory block spans the zone boundary and we are stumbling over an unitialized struct page. Fix this by enforcing zone range in is_mem_section_removable so that we never run away from a zone. Link: http://lkml.kernel.org/r/20190128144506.15603-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Reported-by: Mikhail Zaslonko <zaslonko@linux.ibm.com> Debugged-by: Mikhail Zaslonko <zaslonko@linux.ibm.com> Tested-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> Tested-by: Mikhail Gavrilov <mikhail.v.gavrilov@gmail.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 9bcdeb5
ucount.c
/*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation, version 2 of the
* License.
*/
#include <linux/stat.h>
#include <linux/sysctl.h>
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/hash.h>
#include <linux/kmemleak.h>
#include <linux/user_namespace.h>
#define UCOUNTS_HASHTABLE_BITS 10
static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)];
static DEFINE_SPINLOCK(ucounts_lock);
#define ucounts_hashfn(ns, uid) \
hash_long((unsigned long)__kuid_val(uid) + (unsigned long)(ns), \
UCOUNTS_HASHTABLE_BITS)
#define ucounts_hashentry(ns, uid) \
(ucounts_hashtable + ucounts_hashfn(ns, uid))
#ifdef CONFIG_SYSCTL
static struct ctl_table_set *
set_lookup(struct ctl_table_root *root)
{
return ¤t_user_ns()->set;
}
static int set_is_seen(struct ctl_table_set *set)
{
return ¤t_user_ns()->set == set;
}
static int set_permissions(struct ctl_table_header *head,
struct ctl_table *table)
{
struct user_namespace *user_ns =
container_of(head->set, struct user_namespace, set);
int mode;
/* Allow users with CAP_SYS_RESOURCE unrestrained access */
if (ns_capable(user_ns, CAP_SYS_RESOURCE))
mode = (table->mode & S_IRWXU) >> 6;
else
/* Allow all others at most read-only access */
mode = table->mode & S_IROTH;
return (mode << 6) | (mode << 3) | mode;
}
static struct ctl_table_root set_root = {
.lookup = set_lookup,
.permissions = set_permissions,
};
static int zero = 0;
static int int_max = INT_MAX;
#define UCOUNT_ENTRY(name) \
{ \
.procname = name, \
.maxlen = sizeof(int), \
.mode = 0644, \
.proc_handler = proc_dointvec_minmax, \
.extra1 = &zero, \
.extra2 = &int_max, \
}
static struct ctl_table user_table[] = {
UCOUNT_ENTRY("max_user_namespaces"),
UCOUNT_ENTRY("max_pid_namespaces"),
UCOUNT_ENTRY("max_uts_namespaces"),
UCOUNT_ENTRY("max_ipc_namespaces"),
UCOUNT_ENTRY("max_net_namespaces"),
UCOUNT_ENTRY("max_mnt_namespaces"),
UCOUNT_ENTRY("max_cgroup_namespaces"),
#ifdef CONFIG_INOTIFY_USER
UCOUNT_ENTRY("max_inotify_instances"),
UCOUNT_ENTRY("max_inotify_watches"),
#endif
{ }
};
#endif /* CONFIG_SYSCTL */
bool setup_userns_sysctls(struct user_namespace *ns)
{
#ifdef CONFIG_SYSCTL
struct ctl_table *tbl;
setup_sysctl_set(&ns->set, &set_root, set_is_seen);
tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL);
if (tbl) {
int i;
for (i = 0; i < UCOUNT_COUNTS; i++) {
tbl[i].data = &ns->ucount_max[i];
}
ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl);
}
if (!ns->sysctls) {
kfree(tbl);
retire_sysctl_set(&ns->set);
return false;
}
#endif
return true;
}
void retire_userns_sysctls(struct user_namespace *ns)
{
#ifdef CONFIG_SYSCTL
struct ctl_table *tbl;
tbl = ns->sysctls->ctl_table_arg;
unregister_sysctl_table(ns->sysctls);
retire_sysctl_set(&ns->set);
kfree(tbl);
#endif
}
static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struct hlist_head *hashent)
{
struct ucounts *ucounts;
hlist_for_each_entry(ucounts, hashent, node) {
if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns))
return ucounts;
}
return NULL;
}
static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
{
struct hlist_head *hashent = ucounts_hashentry(ns, uid);
struct ucounts *ucounts, *new;
spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
if (!ucounts) {
spin_unlock_irq(&ucounts_lock);
new = kzalloc(sizeof(*new), GFP_KERNEL);
if (!new)
return NULL;
new->ns = ns;
new->uid = uid;
new->count = 0;
spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
if (ucounts) {
kfree(new);
} else {
hlist_add_head(&new->node, hashent);
ucounts = new;
}
}
if (ucounts->count == INT_MAX)
ucounts = NULL;
else
ucounts->count += 1;
spin_unlock_irq(&ucounts_lock);
return ucounts;
}
static void put_ucounts(struct ucounts *ucounts)
{
unsigned long flags;
spin_lock_irqsave(&ucounts_lock, flags);
ucounts->count -= 1;
if (!ucounts->count)
hlist_del_init(&ucounts->node);
else
ucounts = NULL;
spin_unlock_irqrestore(&ucounts_lock, flags);
kfree(ucounts);
}
static inline bool atomic_inc_below(atomic_t *v, int u)
{
int c, old;
c = atomic_read(v);
for (;;) {
if (unlikely(c >= u))
return false;
old = atomic_cmpxchg(v, c, c+1);
if (likely(old == c))
return true;
c = old;
}
}
struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid,
enum ucount_type type)
{
struct ucounts *ucounts, *iter, *bad;
struct user_namespace *tns;
ucounts = get_ucounts(ns, uid);
for (iter = ucounts; iter; iter = tns->ucounts) {
int max;
tns = iter->ns;
max = READ_ONCE(tns->ucount_max[type]);
if (!atomic_inc_below(&iter->ucount[type], max))
goto fail;
}
return ucounts;
fail:
bad = iter;
for (iter = ucounts; iter != bad; iter = iter->ns->ucounts)
atomic_dec(&iter->ucount[type]);
put_ucounts(ucounts);
return NULL;
}
void dec_ucount(struct ucounts *ucounts, enum ucount_type type)
{
struct ucounts *iter;
for (iter = ucounts; iter; iter = iter->ns->ucounts) {
int dec = atomic_dec_if_positive(&iter->ucount[type]);
WARN_ON_ONCE(dec < 0);
}
put_ucounts(ucounts);
}
static __init int user_namespace_sysctl_init(void)
{
#ifdef CONFIG_SYSCTL
static struct ctl_table_header *user_header;
static struct ctl_table empty[1];
/*
* It is necessary to register the user directory in the
* default set so that registrations in the child sets work
* properly.
*/
user_header = register_sysctl("user", empty);
kmemleak_ignore(user_header);
BUG_ON(!user_header);
BUG_ON(!setup_userns_sysctls(&init_user_ns));
#endif
return 0;
}
subsys_initcall(user_namespace_sysctl_init);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...