Revision 35bf49e054214a0c7d3b0a0f8606f753f3f6ae96 authored by Lu Baolu on 23 August 2022, 06:15:57 UTC, committed by Joerg Roedel on 07 September 2022, 13:14:57 UTC
With CONFIG_INTEL_IOMMU_DEBUGFS enabled, below lockdep splat are seen
when an I/O fault occurs on a machine with an Intel IOMMU in it.

 DMAR: DRHD: handling fault status reg 3
 DMAR: [DMA Write NO_PASID] Request device [00:1a.0] fault addr 0x0
       [fault reason 0x05] PTE Write access is not set
 DMAR: Dump dmar0 table entries for IOVA 0x0
 DMAR: root entry: 0x0000000127f42001
 DMAR: context entry: hi 0x0000000000001502, low 0x000000012d8ab001
 ================================
 WARNING: inconsistent lock state
 5.20.0-0.rc0.20220812git7ebfc85e2cd7.10.fc38.x86_64 #1 Not tainted
 --------------------------------
 inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
 rngd/1006 [HC1[1]:SC0[0]:HE0:SE1] takes:
 ff177021416f2d78 (&k->k_lock){?.+.}-{2:2}, at: klist_next+0x1b/0x160
 {HARDIRQ-ON-W} state was registered at:
   lock_acquire+0xce/0x2d0
   _raw_spin_lock+0x33/0x80
   klist_add_tail+0x46/0x80
   bus_add_device+0xee/0x150
   device_add+0x39d/0x9a0
   add_memory_block+0x108/0x1d0
   memory_dev_init+0xe1/0x117
   driver_init+0x43/0x4d
   kernel_init_freeable+0x1c2/0x2cc
   kernel_init+0x16/0x140
   ret_from_fork+0x1f/0x30
 irq event stamp: 7812
 hardirqs last  enabled at (7811): [<ffffffff85000e86>] asm_sysvec_apic_timer_interrupt+0x16/0x20
 hardirqs last disabled at (7812): [<ffffffff84f16894>] irqentry_enter+0x54/0x60
 softirqs last  enabled at (7794): [<ffffffff840ff669>] __irq_exit_rcu+0xf9/0x170
 softirqs last disabled at (7787): [<ffffffff840ff669>] __irq_exit_rcu+0xf9/0x170

The klist iterator functions using spin_*lock_irq*() but the klist
insertion functions using spin_*lock(), combined with the Intel DMAR
IOMMU driver iterating over klists from atomic (hardirq) context, where
pci_get_domain_bus_and_slot() calls into bus_find_device() which iterates
over klists.

As currently there's no plan to fix the klist to make it safe to use in
atomic context, this fixes the lockdep splat by avoid calling
pci_get_domain_bus_and_slot() in the hardirq context.

Fixes: 8ac0b64b9735 ("iommu/vt-d: Use pci_get_domain_bus_and_slot() in pgtable_walk()")
Reported-by: Lennert Buytenhek <buytenh@wantstofly.org>
Link: https://lore.kernel.org/linux-iommu/Yvo2dfpEh%2FWC+Wrr@wantstofly.org/
Link: https://lore.kernel.org/linux-iommu/YvyBdPwrTuHHbn5X@wantstofly.org/
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20220819015949.4795-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
1 parent a349ffc
Raw File
rose_timer.c
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *
 * Copyright (C) Jonathan Naylor G4KLX (g4klx@g4klx.demon.co.uk)
 * Copyright (C) 2002 Ralf Baechle DO1GRB (ralf@gnu.org)
 */
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/jiffies.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <net/ax25.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <net/rose.h>

static void rose_heartbeat_expiry(struct timer_list *t);
static void rose_timer_expiry(struct timer_list *);
static void rose_idletimer_expiry(struct timer_list *);

void rose_start_heartbeat(struct sock *sk)
{
	sk_stop_timer(sk, &sk->sk_timer);

	sk->sk_timer.function = rose_heartbeat_expiry;
	sk->sk_timer.expires  = jiffies + 5 * HZ;

	sk_reset_timer(sk, &sk->sk_timer, sk->sk_timer.expires);
}

void rose_start_t1timer(struct sock *sk)
{
	struct rose_sock *rose = rose_sk(sk);

	sk_stop_timer(sk, &rose->timer);

	rose->timer.function = rose_timer_expiry;
	rose->timer.expires  = jiffies + rose->t1;

	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}

void rose_start_t2timer(struct sock *sk)
{
	struct rose_sock *rose = rose_sk(sk);

	sk_stop_timer(sk, &rose->timer);

	rose->timer.function = rose_timer_expiry;
	rose->timer.expires  = jiffies + rose->t2;

	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}

void rose_start_t3timer(struct sock *sk)
{
	struct rose_sock *rose = rose_sk(sk);

	sk_stop_timer(sk, &rose->timer);

	rose->timer.function = rose_timer_expiry;
	rose->timer.expires  = jiffies + rose->t3;

	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}

void rose_start_hbtimer(struct sock *sk)
{
	struct rose_sock *rose = rose_sk(sk);

	sk_stop_timer(sk, &rose->timer);

	rose->timer.function = rose_timer_expiry;
	rose->timer.expires  = jiffies + rose->hb;

	sk_reset_timer(sk, &rose->timer, rose->timer.expires);
}

void rose_start_idletimer(struct sock *sk)
{
	struct rose_sock *rose = rose_sk(sk);

	sk_stop_timer(sk, &rose->idletimer);

	if (rose->idle > 0) {
		rose->idletimer.function = rose_idletimer_expiry;
		rose->idletimer.expires  = jiffies + rose->idle;

		sk_reset_timer(sk, &rose->idletimer, rose->idletimer.expires);
	}
}

void rose_stop_heartbeat(struct sock *sk)
{
	sk_stop_timer(sk, &sk->sk_timer);
}

void rose_stop_timer(struct sock *sk)
{
	sk_stop_timer(sk, &rose_sk(sk)->timer);
}

void rose_stop_idletimer(struct sock *sk)
{
	sk_stop_timer(sk, &rose_sk(sk)->idletimer);
}

static void rose_heartbeat_expiry(struct timer_list *t)
{
	struct sock *sk = from_timer(sk, t, sk_timer);
	struct rose_sock *rose = rose_sk(sk);

	bh_lock_sock(sk);
	switch (rose->state) {
	case ROSE_STATE_0:
		/* Magic here: If we listen() and a new link dies before it
		   is accepted() it isn't 'dead' so doesn't get removed. */
		if (sock_flag(sk, SOCK_DESTROY) ||
		    (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
			bh_unlock_sock(sk);
			rose_destroy_socket(sk);
			sock_put(sk);
			return;
		}
		break;

	case ROSE_STATE_3:
		/*
		 * Check for the state of the receive buffer.
		 */
		if (atomic_read(&sk->sk_rmem_alloc) < (sk->sk_rcvbuf / 2) &&
		    (rose->condition & ROSE_COND_OWN_RX_BUSY)) {
			rose->condition &= ~ROSE_COND_OWN_RX_BUSY;
			rose->condition &= ~ROSE_COND_ACK_PENDING;
			rose->vl         = rose->vr;
			rose_write_internal(sk, ROSE_RR);
			rose_stop_timer(sk);	/* HB */
			break;
		}
		break;
	}

	rose_start_heartbeat(sk);
	bh_unlock_sock(sk);
	sock_put(sk);
}

static void rose_timer_expiry(struct timer_list *t)
{
	struct rose_sock *rose = from_timer(rose, t, timer);
	struct sock *sk = &rose->sock;

	bh_lock_sock(sk);
	switch (rose->state) {
	case ROSE_STATE_1:	/* T1 */
	case ROSE_STATE_4:	/* T2 */
		rose_write_internal(sk, ROSE_CLEAR_REQUEST);
		rose->state = ROSE_STATE_2;
		rose_start_t3timer(sk);
		break;

	case ROSE_STATE_2:	/* T3 */
		rose->neighbour->use--;
		rose_disconnect(sk, ETIMEDOUT, -1, -1);
		break;

	case ROSE_STATE_3:	/* HB */
		if (rose->condition & ROSE_COND_ACK_PENDING) {
			rose->condition &= ~ROSE_COND_ACK_PENDING;
			rose_enquiry_response(sk);
		}
		break;
	}
	bh_unlock_sock(sk);
	sock_put(sk);
}

static void rose_idletimer_expiry(struct timer_list *t)
{
	struct rose_sock *rose = from_timer(rose, t, idletimer);
	struct sock *sk = &rose->sock;

	bh_lock_sock(sk);
	rose_clear_queues(sk);

	rose_write_internal(sk, ROSE_CLEAR_REQUEST);
	rose_sk(sk)->state = ROSE_STATE_2;

	rose_start_t3timer(sk);

	sk->sk_state     = TCP_CLOSE;
	sk->sk_err       = 0;
	sk->sk_shutdown |= SEND_SHUTDOWN;

	if (!sock_flag(sk, SOCK_DEAD)) {
		sk->sk_state_change(sk);
		sock_set_flag(sk, SOCK_DEAD);
	}
	bh_unlock_sock(sk);
	sock_put(sk);
}
back to top