Revision 9c29bcd189f4ab1644b7125713602532d0aefdb7 authored by Eric Dumazet on 21 September 2018, 22:27:48 UTC, committed by David S. Miller on 24 September 2018, 04:55:25 UTC
As diagnosed by Song Liu, ndo_poll_controller() can
be very dangerous on loaded hosts, since the cpu
calling ndo_poll_controller() might steal all NAPI
contexts (for all RX/TX queues of the NIC). This capture
can last for unlimited amount of time, since one
cpu is generally not able to drain all the queues under load.

mlx5 uses NAPI for TX completions, so we better let core
networking stack call the napi->poll() to avoid the capture.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
1 parent a24b66c
Raw File
msgutil.c
/*
 * linux/ipc/msgutil.c
 * Copyright (C) 1999, 2004 Manfred Spraul
 *
 * This file is released under GNU General Public Licence version 2 or
 * (at your option) any later version.
 *
 * See the file COPYING for more details.
 */

#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/ipc.h>
#include <linux/msg.h>
#include <linux/ipc_namespace.h>
#include <linux/utsname.h>
#include <linux/proc_ns.h>
#include <linux/uaccess.h>

#include "util.h"

DEFINE_SPINLOCK(mq_lock);

/*
 * The next 2 defines are here bc this is the only file
 * compiled when either CONFIG_SYSVIPC and CONFIG_POSIX_MQUEUE
 * and not CONFIG_IPC_NS.
 */
struct ipc_namespace init_ipc_ns = {
	.count		= REFCOUNT_INIT(1),
	.user_ns = &init_user_ns,
	.ns.inum = PROC_IPC_INIT_INO,
#ifdef CONFIG_IPC_NS
	.ns.ops = &ipcns_operations,
#endif
};

struct msg_msgseg {
	struct msg_msgseg *next;
	/* the next part of the message follows immediately */
};

#define DATALEN_MSG	((size_t)PAGE_SIZE-sizeof(struct msg_msg))
#define DATALEN_SEG	((size_t)PAGE_SIZE-sizeof(struct msg_msgseg))


static struct msg_msg *alloc_msg(size_t len)
{
	struct msg_msg *msg;
	struct msg_msgseg **pseg;
	size_t alen;

	alen = min(len, DATALEN_MSG);
	msg = kmalloc(sizeof(*msg) + alen, GFP_KERNEL_ACCOUNT);
	if (msg == NULL)
		return NULL;

	msg->next = NULL;
	msg->security = NULL;

	len -= alen;
	pseg = &msg->next;
	while (len > 0) {
		struct msg_msgseg *seg;
		alen = min(len, DATALEN_SEG);
		seg = kmalloc(sizeof(*seg) + alen, GFP_KERNEL_ACCOUNT);
		if (seg == NULL)
			goto out_err;
		*pseg = seg;
		seg->next = NULL;
		pseg = &seg->next;
		len -= alen;
	}

	return msg;

out_err:
	free_msg(msg);
	return NULL;
}

struct msg_msg *load_msg(const void __user *src, size_t len)
{
	struct msg_msg *msg;
	struct msg_msgseg *seg;
	int err = -EFAULT;
	size_t alen;

	msg = alloc_msg(len);
	if (msg == NULL)
		return ERR_PTR(-ENOMEM);

	alen = min(len, DATALEN_MSG);
	if (copy_from_user(msg + 1, src, alen))
		goto out_err;

	for (seg = msg->next; seg != NULL; seg = seg->next) {
		len -= alen;
		src = (char __user *)src + alen;
		alen = min(len, DATALEN_SEG);
		if (copy_from_user(seg + 1, src, alen))
			goto out_err;
	}

	err = security_msg_msg_alloc(msg);
	if (err)
		goto out_err;

	return msg;

out_err:
	free_msg(msg);
	return ERR_PTR(err);
}
#ifdef CONFIG_CHECKPOINT_RESTORE
struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
{
	struct msg_msgseg *dst_pseg, *src_pseg;
	size_t len = src->m_ts;
	size_t alen;

	if (src->m_ts > dst->m_ts)
		return ERR_PTR(-EINVAL);

	alen = min(len, DATALEN_MSG);
	memcpy(dst + 1, src + 1, alen);

	for (dst_pseg = dst->next, src_pseg = src->next;
	     src_pseg != NULL;
	     dst_pseg = dst_pseg->next, src_pseg = src_pseg->next) {

		len -= alen;
		alen = min(len, DATALEN_SEG);
		memcpy(dst_pseg + 1, src_pseg + 1, alen);
	}

	dst->m_type = src->m_type;
	dst->m_ts = src->m_ts;

	return dst;
}
#else
struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst)
{
	return ERR_PTR(-ENOSYS);
}
#endif
int store_msg(void __user *dest, struct msg_msg *msg, size_t len)
{
	size_t alen;
	struct msg_msgseg *seg;

	alen = min(len, DATALEN_MSG);
	if (copy_to_user(dest, msg + 1, alen))
		return -1;

	for (seg = msg->next; seg != NULL; seg = seg->next) {
		len -= alen;
		dest = (char __user *)dest + alen;
		alen = min(len, DATALEN_SEG);
		if (copy_to_user(dest, seg + 1, alen))
			return -1;
	}
	return 0;
}

void free_msg(struct msg_msg *msg)
{
	struct msg_msgseg *seg;

	security_msg_msg_free(msg);

	seg = msg->next;
	kfree(msg);
	while (seg != NULL) {
		struct msg_msgseg *tmp = seg->next;
		kfree(seg);
		seg = tmp;
	}
}
back to top