Revision 8f8ba75ee2065738644382667f833a4eb6f6db1d authored by Linus Torvalds on 21 August 2012, 23:46:08 UTC, committed by Linus Torvalds on 21 August 2012, 23:46:08 UTC
Pull networking update from David Miller:
 "A couple weeks of bug fixing in there.  The largest chunk is all the
  broken crap Amerigo Wang found in the netpoll layer."

 1) netpoll and it's users has several serious bugs:
    a) uses GFP_KERNEL with locks held
    b) interfaces requiring interrupts disabled are called with them
       enabled
    c) and vice versa
    d) VLAN tag demuxing, as per all other RX packet input paths, is not
       applied

    All from Amerigo Wang.

 2) Hopefully cure the ipv4 mapped ipv6 address TCP early demux bugs for
    good, from Neal Cardwell.

 3) Unlike AF_UNIX, AF_PACKET sockets don't set a default credentials
    when the user doesn't specify one explicitly during sendmsg().
    Instead we attach an empty (zero) SCM credential block which is
    definitely not what we want.  Fix from Eric Dumazet.

 4) IPv6 illegally invokes netdevice notifiers with RCU lock held, fix
    from Ben Hutchings.

 5) inet_csk_route_child_sock() checks wrong inet options pointer, fix
    from Christoph Paasch.

 6) When AF_PACKET is used for transmit, packet loopback doesn't behave
    properly when a socket fanout is enabled, from Eric Leblond.

 7) On bluetooth l2cap channel create failure, we leak the socket, from
    Jaganath Kanakkassery.

 8) Fix all the netprio file handling bugs found by Al Viro, from John
    Fastabend.

 9) Several error return and NULL deref bug fixes in networking drivers
    from Julia Lawall.

10) A large smattering of struct padding et al.  kernel memory leaks to
    userspace found of Mathias Krause.

11) Conntrack expections in netfilter can access an uninitialized timer,
    fix from Pablo Neira Ayuso.

12) Several netfilter SIP tracker bug fixes from Patrick McHardy.

13) IPSEC ipv6 routes are not initialized correctly all the time,
    resulting in an OOPS in inet_putpeer().  Also from Patrick McHardy.

14) Bridging does rcu_dereference() outside of RCU protected area, from
    Stephen Hemminger.

15) Fix routing cache removal performance regression when looking up
    output routes that have a local destination.  From Zheng Yan.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
  af_netlink: force credentials passing [CVE-2012-3520]
  ipv4: fix ip header ident selection in __ip_make_skb()
  ipv4: Use newinet->inet_opt in inet_csk_route_child_sock()
  tcp: fix possible socket refcount problem
  net: tcp: move sk_rx_dst_set call after tcp_create_openreq_child()
  net/core/dev.c: fix kernel-doc warning
  netconsole: remove a redundant netconsole_target_put()
  net: ipv6: fix oops in inet_putpeer()
  net/stmmac: fix issue of clk_get for Loongson1B.
  caif: Do not dereference NULL in chnl_recv_cb()
  af_packet: don't emit packet on orig fanout group
  drivers/net/irda: fix error return code
  drivers/net/wan/dscc4.c: fix error return code
  drivers/net/wimax/i2400m/fw.c: fix error return code
  smsc75xx: add missing entry to MAINTAINERS
  net: qmi_wwan: new devices: UML290 and K5006-Z
  net: sh_eth: Add eth support for R8A7779 device
  netdev/phy: skip disabled mdio-mux nodes
  dt: introduce for_each_available_child_of_node, of_get_next_available_child
  net: netprio: fix cgrp create and write priomap race
  ...
2 parent s 1456c75 + e0e3cea
Raw File
blk-softirq.c
/*
 * Functions related to softirq rq completions
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/interrupt.h>
#include <linux/cpu.h>
#include <linux/sched.h>

#include "blk.h"

static DEFINE_PER_CPU(struct list_head, blk_cpu_done);

/*
 * Softirq action handler - move entries to local list and loop over them
 * while passing them to the queue registered handler.
 */
static void blk_done_softirq(struct softirq_action *h)
{
	struct list_head *cpu_list, local_list;

	local_irq_disable();
	cpu_list = &__get_cpu_var(blk_cpu_done);
	list_replace_init(cpu_list, &local_list);
	local_irq_enable();

	while (!list_empty(&local_list)) {
		struct request *rq;

		rq = list_entry(local_list.next, struct request, csd.list);
		list_del_init(&rq->csd.list);
		rq->q->softirq_done_fn(rq);
	}
}

#if defined(CONFIG_SMP) && defined(CONFIG_USE_GENERIC_SMP_HELPERS)
static void trigger_softirq(void *data)
{
	struct request *rq = data;
	unsigned long flags;
	struct list_head *list;

	local_irq_save(flags);
	list = &__get_cpu_var(blk_cpu_done);
	list_add_tail(&rq->csd.list, list);

	if (list->next == &rq->csd.list)
		raise_softirq_irqoff(BLOCK_SOFTIRQ);

	local_irq_restore(flags);
}

/*
 * Setup and invoke a run of 'trigger_softirq' on the given cpu.
 */
static int raise_blk_irq(int cpu, struct request *rq)
{
	if (cpu_online(cpu)) {
		struct call_single_data *data = &rq->csd;

		data->func = trigger_softirq;
		data->info = rq;
		data->flags = 0;

		__smp_call_function_single(cpu, data, 0);
		return 0;
	}

	return 1;
}
#else /* CONFIG_SMP && CONFIG_USE_GENERIC_SMP_HELPERS */
static int raise_blk_irq(int cpu, struct request *rq)
{
	return 1;
}
#endif

static int __cpuinit blk_cpu_notify(struct notifier_block *self,
				    unsigned long action, void *hcpu)
{
	/*
	 * If a CPU goes away, splice its entries to the current CPU
	 * and trigger a run of the softirq
	 */
	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
		int cpu = (unsigned long) hcpu;

		local_irq_disable();
		list_splice_init(&per_cpu(blk_cpu_done, cpu),
				 &__get_cpu_var(blk_cpu_done));
		raise_softirq_irqoff(BLOCK_SOFTIRQ);
		local_irq_enable();
	}

	return NOTIFY_OK;
}

static struct notifier_block __cpuinitdata blk_cpu_notifier = {
	.notifier_call	= blk_cpu_notify,
};

void __blk_complete_request(struct request *req)
{
	int ccpu, cpu;
	struct request_queue *q = req->q;
	unsigned long flags;
	bool shared = false;

	BUG_ON(!q->softirq_done_fn);

	local_irq_save(flags);
	cpu = smp_processor_id();

	/*
	 * Select completion CPU
	 */
	if (req->cpu != -1) {
		ccpu = req->cpu;
		if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
			shared = cpus_share_cache(cpu, ccpu);
	} else
		ccpu = cpu;

	/*
	 * If current CPU and requested CPU share a cache, run the softirq on
	 * the current CPU. One might concern this is just like
	 * QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is
	 * running in interrupt handler, and currently I/O controller doesn't
	 * support multiple interrupts, so current CPU is unique actually. This
	 * avoids IPI sending from current CPU to the first CPU of a group.
	 */
	if (ccpu == cpu || shared) {
		struct list_head *list;
do_local:
		list = &__get_cpu_var(blk_cpu_done);
		list_add_tail(&req->csd.list, list);

		/*
		 * if the list only contains our just added request,
		 * signal a raise of the softirq. If there are already
		 * entries there, someone already raised the irq but it
		 * hasn't run yet.
		 */
		if (list->next == &req->csd.list)
			raise_softirq_irqoff(BLOCK_SOFTIRQ);
	} else if (raise_blk_irq(ccpu, req))
		goto do_local;

	local_irq_restore(flags);
}

/**
 * blk_complete_request - end I/O on a request
 * @req:      the request being processed
 *
 * Description:
 *     Ends all I/O on a request. It does not handle partial completions,
 *     unless the driver actually implements this in its completion callback
 *     through requeueing. The actual completion happens out-of-order,
 *     through a softirq handler. The user must have registered a completion
 *     callback through blk_queue_softirq_done().
 **/
void blk_complete_request(struct request *req)
{
	if (unlikely(blk_should_fake_timeout(req->q)))
		return;
	if (!blk_mark_rq_complete(req))
		__blk_complete_request(req);
}
EXPORT_SYMBOL(blk_complete_request);

static __init int blk_softirq_init(void)
{
	int i;

	for_each_possible_cpu(i)
		INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));

	open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
	register_hotcpu_notifier(&blk_cpu_notifier);
	return 0;
}
subsys_initcall(blk_softirq_init);
back to top