Skip to main content

Browse the archive

Revision 9e368259ad988356c4c95150fafd1a06af095d98 authored by Andrea Arcangeli on 30 November 2018, 22:09:25 UTC, committed by Linus Torvalds on 30 November 2018, 22:56:14 UTC 
userfaultfd: use ENOENT instead of EFAULT if the atomic copy user fails
 
Patch series "userfaultfd shmem updates".

Jann found two bugs in the userfaultfd shmem MAP_SHARED backend: the
lack of the VM_MAYWRITE check and the lack of i_size checks.

Then looking into the above we also fixed the MAP_PRIVATE case.

Hugh by source review also found a data loss source if UFFDIO_COPY is
used on shmem MAP_SHARED PROT_READ mappings (the production usages
incidentally run with PROT_READ|PROT_WRITE, so the data loss couldn't
happen in those production usages like with QEMU).

The whole patchset is marked for stable.

We verified QEMU postcopy live migration with guest running on shmem
MAP_PRIVATE run as well as before after the fix of shmem MAP_PRIVATE.
Regardless if it's shmem or hugetlbfs or MAP_PRIVATE or MAP_SHARED, QEMU
unconditionally invokes a punch hole if the guest mapping is filebacked
and a MADV_DONTNEED too (needed to get rid of the MAP_PRIVATE COWs and
for the anon backend).

This patch (of 5):

We internally used EFAULT to communicate with the caller, switch to
ENOENT, so EFAULT can be used as a non internal retval.

Link: http://lkml.kernel.org/r/20181126173452.26955-2-aarcange@redhat.com
Fixes: 4c27fe4c4c84 ("userfaultfd: shmem: add shmem_mcopy_atomic_pte for userfaultfd support")
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Hugh Dickins <hughd@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Jann Horn <jannh@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: <stable@vger.kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 5618cf0
Raw File
netlink.c 
// SPDX-License-Identifier: GPL-2.0
#include <linux/cred.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/quotaops.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <net/netlink.h>
#include <net/genetlink.h>

static const struct genl_multicast_group quota_mcgrps[] = {
	{ .name = "events", },
};

/* Netlink family structure for quota */
static struct genl_family quota_genl_family __ro_after_init = {
	.module = THIS_MODULE,
	.hdrsize = 0,
	.name = "VFS_DQUOT",
	.version = 1,
	.maxattr = QUOTA_NL_A_MAX,
	.mcgrps = quota_mcgrps,
	.n_mcgrps = ARRAY_SIZE(quota_mcgrps),
};

/**
 * quota_send_warning - Send warning to userspace about exceeded quota
 * @qid: The kernel internal quota identifier.
 * @dev: The device on which the fs is mounted (sb->s_dev)
 * @warntype: The type of the warning: QUOTA_NL_...
 *
 * This can be used by filesystems (including those which don't use
 * dquot) to send a message to userspace relating to quota limits.
 *
 */

void quota_send_warning(struct kqid qid, dev_t dev,
			const char warntype)
{
	static atomic_t seq;
	struct sk_buff *skb;
	void *msg_head;
	int ret;
	int msg_size = 4 * nla_total_size(sizeof(u32)) +
		       2 * nla_total_size_64bit(sizeof(u64));

	/* We have to allocate using GFP_NOFS as we are called from a
	 * filesystem performing write and thus further recursion into
	 * the fs to free some data could cause deadlocks. */
	skb = genlmsg_new(msg_size, GFP_NOFS);
	if (!skb) {
		printk(KERN_ERR
		  "VFS: Not enough memory to send quota warning.\n");
		return;
	}
	msg_head = genlmsg_put(skb, 0, atomic_add_return(1, &seq),
			&quota_genl_family, 0, QUOTA_NL_C_WARNING);
	if (!msg_head) {
		printk(KERN_ERR
		  "VFS: Cannot store netlink header in quota warning.\n");
		goto err_out;
	}
	ret = nla_put_u32(skb, QUOTA_NL_A_QTYPE, qid.type);
	if (ret)
		goto attr_err_out;
	ret = nla_put_u64_64bit(skb, QUOTA_NL_A_EXCESS_ID,
				from_kqid_munged(&init_user_ns, qid),
				QUOTA_NL_A_PAD);
	if (ret)
		goto attr_err_out;
	ret = nla_put_u32(skb, QUOTA_NL_A_WARNING, warntype);
	if (ret)
		goto attr_err_out;
	ret = nla_put_u32(skb, QUOTA_NL_A_DEV_MAJOR, MAJOR(dev));
	if (ret)
		goto attr_err_out;
	ret = nla_put_u32(skb, QUOTA_NL_A_DEV_MINOR, MINOR(dev));
	if (ret)
		goto attr_err_out;
	ret = nla_put_u64_64bit(skb, QUOTA_NL_A_CAUSED_ID,
				from_kuid_munged(&init_user_ns, current_uid()),
				QUOTA_NL_A_PAD);
	if (ret)
		goto attr_err_out;
	genlmsg_end(skb, msg_head);

	genlmsg_multicast(&quota_genl_family, skb, 0, 0, GFP_NOFS);
	return;
attr_err_out:
	printk(KERN_ERR "VFS: Not enough space to compose quota message!\n");
err_out:
	kfree_skb(skb);
}
EXPORT_SYMBOL(quota_send_warning);

static int __init quota_init(void)
{
	if (genl_register_family(&quota_genl_family) != 0)
		printk(KERN_ERR
		       "VFS: Failed to create quota netlink interface.\n");
	return 0;
};
fs_initcall(quota_init);
back to top