Skip to content
Snippets Groups Projects
  • Mimi Zohar's avatar
    c09c59e6
    ima: replace GFP_KERNEL with GFP_NOFS · c09c59e6
    Mimi Zohar authored
    
    While running fsstress tests on the NFSv4 mounted ext3 and ext4
    filesystem, the following call trace was generated on the nfs
    server machine.
    
    Replace GFP_KERNEL with GFP_NOFS in ima_iint_insert() to avoid a
    potential deadlock.
    
         =================================
        [ INFO: inconsistent lock state ]
        2.6.31-31.el6.x86_64 #1
        ---------------------------------
        inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage.
        kswapd2/75 [HC0[0]:SC0[0]:HE1:SE1] takes:
         (jbd2_handle){+.+.?.}, at: [<ffffffff811edd5e>] jbd2_journal_start+0xfe/0x13f
        {RECLAIM_FS-ON-W} state was registered at:
          [<ffffffff81091e40>] mark_held_locks+0x65/0x99
          [<ffffffff81091f31>] lockdep_trace_alloc+0xbd/0xf5
          [<ffffffff81126fdd>] kmem_cache_alloc+0x40/0x185
          [<ffffffff812344d7>] ima_iint_insert+0x3d/0xf1
          [<ffffffff812345b0>] ima_inode_alloc+0x25/0x44
          [<ffffffff811484ac>] inode_init_always+0xec/0x271
          [<ffffffff81148682>] alloc_inode+0x51/0xa1
          [<ffffffff81148700>] new_inode+0x2e/0x94
          [<ffffffff811b2f08>] ext4_new_inode+0xb8/0xdc9
          [<ffffffff811be611>] ext4_create+0xcf/0x175
          [<ffffffff8113e2cd>] vfs_create+0x82/0xb8
          [<ffffffff8113f337>] do_filp_open+0x32c/0x9ee
          [<ffffffff811309b9>] do_sys_open+0x6c/0x12c
          [<ffffffff81130adc>] sys_open+0x2e/0x44
          [<ffffffff81011e42>] system_call_fastpath+0x16/0x1b
          [<ffffffffffffffff>] 0xffffffffffffffff
        irq event stamp: 90371
        hardirqs last  enabled at (90371): [<ffffffff8112708d>]
        kmem_cache_alloc+0xf0/0x185
        hardirqs last disabled at (90370): [<ffffffff81127026>]
        kmem_cache_alloc+0x89/0x185
        softirqs last  enabled at (89492): [<ffffffff81068ecf>]
        __do_softirq+0x1bf/0x1eb
        softirqs last disabled at (89477): [<ffffffff8101312c>] call_softirq+0x1c/0x30
    
        other info that might help us debug this:
        2 locks held by kswapd2/75:
         #0:  (shrinker_rwsem){++++..}, at: [<ffffffff810f98ba>] shrink_slab+0x44/0x177
         #1:  (&type->s_umount_key#25){++++..}, at: [<ffffffff811450ba>]
    
    Reported-by: default avatarMuni P. Beerakam <mbeeraka@in.ibm.com>
    Reported-by: default avatarAmit K. Arora <amitarora@in.ibm.com>
    Cc: stable@kernel.org
    Signed-off-by: default avatarMimi Zohar <zohar@us.ibm.com>
    Signed-off-by: default avatarJames Morris <jmorris@namei.org>
    c09c59e6
    History
    ima: replace GFP_KERNEL with GFP_NOFS
    Mimi Zohar authored
    
    While running fsstress tests on the NFSv4 mounted ext3 and ext4
    filesystem, the following call trace was generated on the nfs
    server machine.
    
    Replace GFP_KERNEL with GFP_NOFS in ima_iint_insert() to avoid a
    potential deadlock.
    
         =================================
        [ INFO: inconsistent lock state ]
        2.6.31-31.el6.x86_64 #1
        ---------------------------------
        inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage.
        kswapd2/75 [HC0[0]:SC0[0]:HE1:SE1] takes:
         (jbd2_handle){+.+.?.}, at: [<ffffffff811edd5e>] jbd2_journal_start+0xfe/0x13f
        {RECLAIM_FS-ON-W} state was registered at:
          [<ffffffff81091e40>] mark_held_locks+0x65/0x99
          [<ffffffff81091f31>] lockdep_trace_alloc+0xbd/0xf5
          [<ffffffff81126fdd>] kmem_cache_alloc+0x40/0x185
          [<ffffffff812344d7>] ima_iint_insert+0x3d/0xf1
          [<ffffffff812345b0>] ima_inode_alloc+0x25/0x44
          [<ffffffff811484ac>] inode_init_always+0xec/0x271
          [<ffffffff81148682>] alloc_inode+0x51/0xa1
          [<ffffffff81148700>] new_inode+0x2e/0x94
          [<ffffffff811b2f08>] ext4_new_inode+0xb8/0xdc9
          [<ffffffff811be611>] ext4_create+0xcf/0x175
          [<ffffffff8113e2cd>] vfs_create+0x82/0xb8
          [<ffffffff8113f337>] do_filp_open+0x32c/0x9ee
          [<ffffffff811309b9>] do_sys_open+0x6c/0x12c
          [<ffffffff81130adc>] sys_open+0x2e/0x44
          [<ffffffff81011e42>] system_call_fastpath+0x16/0x1b
          [<ffffffffffffffff>] 0xffffffffffffffff
        irq event stamp: 90371
        hardirqs last  enabled at (90371): [<ffffffff8112708d>]
        kmem_cache_alloc+0xf0/0x185
        hardirqs last disabled at (90370): [<ffffffff81127026>]
        kmem_cache_alloc+0x89/0x185
        softirqs last  enabled at (89492): [<ffffffff81068ecf>]
        __do_softirq+0x1bf/0x1eb
        softirqs last disabled at (89477): [<ffffffff8101312c>] call_softirq+0x1c/0x30
    
        other info that might help us debug this:
        2 locks held by kswapd2/75:
         #0:  (shrinker_rwsem){++++..}, at: [<ffffffff810f98ba>] shrink_slab+0x44/0x177
         #1:  (&type->s_umount_key#25){++++..}, at: [<ffffffff811450ba>]
    
    Reported-by: default avatarMuni P. Beerakam <mbeeraka@in.ibm.com>
    Reported-by: default avatarAmit K. Arora <amitarora@in.ibm.com>
    Cc: stable@kernel.org
    Signed-off-by: default avatarMimi Zohar <zohar@us.ibm.com>
    Signed-off-by: default avatarJames Morris <jmorris@namei.org>
ima_iint.c 4.82 KiB
/*
 * Copyright (C) 2008 IBM Corporation
 *
 * Authors:
 * Mimi Zohar <zohar@us.ibm.com>
 *
 * 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.
 *
 * File: ima_iint.c
 * 	- implements the IMA hooks: ima_inode_alloc, ima_inode_free
 *	- cache integrity information associated with an inode
 *	  using a radix tree.
 */
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/radix-tree.h>
#include "ima.h"

#define ima_iint_delete ima_inode_free

RADIX_TREE(ima_iint_store, GFP_ATOMIC);
DEFINE_SPINLOCK(ima_iint_lock);

static struct kmem_cache *iint_cache __read_mostly;

/* ima_iint_find_get - return the iint associated with an inode
 *
 * ima_iint_find_get gets a reference to the iint. Caller must
 * remember to put the iint reference.
 */
struct ima_iint_cache *ima_iint_find_get(struct inode *inode)
{
	struct ima_iint_cache *iint;

	rcu_read_lock();
	iint = radix_tree_lookup(&ima_iint_store, (unsigned long)inode);
	if (!iint)
		goto out;
	kref_get(&iint->refcount);
out:
	rcu_read_unlock();
	return iint;
}

/* Allocate memory for the iint associated with the inode
 * from the iint_cache slab, initialize the iint, and
 * insert it into the radix tree.
 *
 * On success return a pointer to the iint; on failure return NULL.
 */
struct ima_iint_cache *ima_iint_insert(struct inode *inode)
{
	struct ima_iint_cache *iint = NULL;
	int rc = 0;

	if (!ima_initialized)
		return iint;
	iint = kmem_cache_alloc(iint_cache, GFP_NOFS);
	if (!iint)
		return iint;

	rc = radix_tree_preload(GFP_NOFS);
	if (rc < 0)
		goto out;

	spin_lock(&ima_iint_lock);
	rc = radix_tree_insert(&ima_iint_store, (unsigned long)inode, iint);
	spin_unlock(&ima_iint_lock);
out:
	if (rc < 0) {
		kmem_cache_free(iint_cache, iint);
		if (rc == -EEXIST) {
			spin_lock(&ima_iint_lock);
			iint = radix_tree_lookup(&ima_iint_store,
						 (unsigned long)inode);
			spin_unlock(&ima_iint_lock);
		} else
			iint = NULL;
	}
	radix_tree_preload_end();
	return iint;
}

/**
 * ima_inode_alloc - allocate an iint associated with an inode
 * @inode: pointer to the inode
 *
 * Return 0 on success, 1 on failure.
 */
int ima_inode_alloc(struct inode *inode)
{
	struct ima_iint_cache *iint;

	if (!ima_initialized)
		return 0;

	iint = ima_iint_insert(inode);
	if (!iint)
		return 1;
	return 0;
}

/* ima_iint_find_insert_get - get the iint associated with an inode
 *
 * Most insertions are done at inode_alloc, except those allocated
 * before late_initcall. When the iint does not exist, allocate it,
 * initialize and insert it, and increment the iint refcount.
 *
 * (Can't initialize at security_initcall before any inodes are
 * allocated, got to wait at least until proc_init.)
 *
 *  Return the iint.
 */
struct ima_iint_cache *ima_iint_find_insert_get(struct inode *inode)
{
	struct ima_iint_cache *iint = NULL;

	iint = ima_iint_find_get(inode);
	if (iint)
		return iint;

	iint = ima_iint_insert(inode);
	if (iint)
		kref_get(&iint->refcount);

	return iint;
}
EXPORT_SYMBOL_GPL(ima_iint_find_insert_get);

/* iint_free - called when the iint refcount goes to zero */
void iint_free(struct kref *kref)
{
	struct ima_iint_cache *iint = container_of(kref, struct ima_iint_cache,
						   refcount);
	iint->version = 0;
	iint->flags = 0UL;
	if (iint->readcount != 0) {
		printk(KERN_INFO "%s: readcount: %ld\n", __FUNCTION__,
		       iint->readcount);
		iint->readcount = 0;
	}
	if (iint->writecount != 0) {
		printk(KERN_INFO "%s: writecount: %ld\n", __FUNCTION__,
		       iint->writecount);
		iint->writecount = 0;
	}
	if (iint->opencount != 0) {
		printk(KERN_INFO "%s: opencount: %ld\n", __FUNCTION__,
		       iint->opencount);
		iint->opencount = 0;
	}
	kref_set(&iint->refcount, 1);
	kmem_cache_free(iint_cache, iint);
}

void iint_rcu_free(struct rcu_head *rcu_head)
{
	struct ima_iint_cache *iint = container_of(rcu_head,
						   struct ima_iint_cache, rcu);
	kref_put(&iint->refcount, iint_free);
}

/**
 * ima_iint_delete - called on integrity_inode_free
 * @inode: pointer to the inode
 *
 * Free the integrity information(iint) associated with an inode.
 */
void ima_iint_delete(struct inode *inode)
{
	struct ima_iint_cache *iint;

	if (!ima_initialized)
		return;
	spin_lock(&ima_iint_lock);
	iint = radix_tree_delete(&ima_iint_store, (unsigned long)inode);
	spin_unlock(&ima_iint_lock);
	if (iint)
		call_rcu(&iint->rcu, iint_rcu_free);
}

static void init_once(void *foo)
{
	struct ima_iint_cache *iint = foo;

	memset(iint, 0, sizeof *iint);
	iint->version = 0;
	iint->flags = 0UL;
	mutex_init(&iint->mutex);
	iint->readcount = 0;
	iint->writecount = 0;
	iint->opencount = 0;
	kref_set(&iint->refcount, 1);
}

void __init ima_iintcache_init(void)
{
	iint_cache =
	    kmem_cache_create("iint_cache", sizeof(struct ima_iint_cache), 0,
			      SLAB_PANIC, init_once);
}