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
ast.c
// SPDX-License-Identifier: GPL-2.0-only
/******************************************************************************
*******************************************************************************
**
**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
**  Copyright (C) 2004-2010 Red Hat, Inc.  All rights reserved.
**
**
*******************************************************************************
******************************************************************************/

#include <trace/events/dlm.h>

#include "dlm_internal.h"
#include "lock.h"
#include "user.h"
#include "ast.h"

static uint64_t dlm_cb_seq;
static DEFINE_SPINLOCK(dlm_cb_seq_spin);

static void dlm_dump_lkb_callbacks(struct dlm_lkb *lkb)
{
	int i;

	log_print("last_bast %x %llu flags %x mode %d sb %d %x",
		  lkb->lkb_id,
		  (unsigned long long)lkb->lkb_last_bast.seq,
		  lkb->lkb_last_bast.flags,
		  lkb->lkb_last_bast.mode,
		  lkb->lkb_last_bast.sb_status,
		  lkb->lkb_last_bast.sb_flags);

	log_print("last_cast %x %llu flags %x mode %d sb %d %x",
		  lkb->lkb_id,
		  (unsigned long long)lkb->lkb_last_cast.seq,
		  lkb->lkb_last_cast.flags,
		  lkb->lkb_last_cast.mode,
		  lkb->lkb_last_cast.sb_status,
		  lkb->lkb_last_cast.sb_flags);

	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
		log_print("cb %x %llu flags %x mode %d sb %d %x",
			  lkb->lkb_id,
			  (unsigned long long)lkb->lkb_callbacks[i].seq,
			  lkb->lkb_callbacks[i].flags,
			  lkb->lkb_callbacks[i].mode,
			  lkb->lkb_callbacks[i].sb_status,
			  lkb->lkb_callbacks[i].sb_flags);
	}
}

int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
			 int status, uint32_t sbflags, uint64_t seq)
{
	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
	uint64_t prev_seq;
	int prev_mode;
	int i, rv;

	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
		if (lkb->lkb_callbacks[i].seq)
			continue;

		/*
		 * Suppress some redundant basts here, do more on removal.
		 * Don't even add a bast if the callback just before it
		 * is a bast for the same mode or a more restrictive mode.
		 * (the addional > PR check is needed for PR/CW inversion)
		 */

		if ((i > 0) && (flags & DLM_CB_BAST) &&
		    (lkb->lkb_callbacks[i-1].flags & DLM_CB_BAST)) {

			prev_seq = lkb->lkb_callbacks[i-1].seq;
			prev_mode = lkb->lkb_callbacks[i-1].mode;

			if ((prev_mode == mode) ||
			    (prev_mode > mode && prev_mode > DLM_LOCK_PR)) {

				log_debug(ls, "skip %x add bast %llu mode %d "
					  "for bast %llu mode %d",
					  lkb->lkb_id,
					  (unsigned long long)seq,
					  mode,
					  (unsigned long long)prev_seq,
					  prev_mode);
				rv = 0;
				goto out;
			}
		}

		lkb->lkb_callbacks[i].seq = seq;
		lkb->lkb_callbacks[i].flags = flags;
		lkb->lkb_callbacks[i].mode = mode;
		lkb->lkb_callbacks[i].sb_status = status;
		lkb->lkb_callbacks[i].sb_flags = (sbflags & 0x000000FF);
		rv = 0;
		break;
	}

	if (i == DLM_CALLBACKS_SIZE) {
		log_error(ls, "no callbacks %x %llu flags %x mode %d sb %d %x",
			  lkb->lkb_id, (unsigned long long)seq,
			  flags, mode, status, sbflags);
		dlm_dump_lkb_callbacks(lkb);
		rv = -1;
		goto out;
	}
 out:
	return rv;
}

int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb,
			 struct dlm_callback *cb, int *resid)
{
	int i, rv;

	*resid = 0;

	if (!lkb->lkb_callbacks[0].seq) {
		rv = -ENOENT;
		goto out;
	}

	/* oldest undelivered cb is callbacks[0] */

	memcpy(cb, &lkb->lkb_callbacks[0], sizeof(struct dlm_callback));
	memset(&lkb->lkb_callbacks[0], 0, sizeof(struct dlm_callback));

	/* shift others down */

	for (i = 1; i < DLM_CALLBACKS_SIZE; i++) {
		if (!lkb->lkb_callbacks[i].seq)
			break;
		memcpy(&lkb->lkb_callbacks[i-1], &lkb->lkb_callbacks[i],
		       sizeof(struct dlm_callback));
		memset(&lkb->lkb_callbacks[i], 0, sizeof(struct dlm_callback));
		(*resid)++;
	}

	/* if cb is a bast, it should be skipped if the blocking mode is
	   compatible with the last granted mode */

	if ((cb->flags & DLM_CB_BAST) && lkb->lkb_last_cast.seq) {
		if (dlm_modes_compat(cb->mode, lkb->lkb_last_cast.mode)) {
			cb->flags |= DLM_CB_SKIP;

			log_debug(ls, "skip %x bast %llu mode %d "
				  "for cast %llu mode %d",
				  lkb->lkb_id,
				  (unsigned long long)cb->seq,
				  cb->mode,
				  (unsigned long long)lkb->lkb_last_cast.seq,
				  lkb->lkb_last_cast.mode);
			rv = 0;
			goto out;
		}
	}

	if (cb->flags & DLM_CB_CAST) {
		memcpy(&lkb->lkb_last_cast, cb, sizeof(struct dlm_callback));
		lkb->lkb_last_cast_time = ktime_get();
	}

	if (cb->flags & DLM_CB_BAST) {
		memcpy(&lkb->lkb_last_bast, cb, sizeof(struct dlm_callback));
		lkb->lkb_last_bast_time = ktime_get();
	}
	rv = 0;
 out:
	return rv;
}

void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
		uint32_t sbflags)
{
	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
	uint64_t new_seq, prev_seq;
	int rv;

	spin_lock(&dlm_cb_seq_spin);
	new_seq = ++dlm_cb_seq;
	if (!dlm_cb_seq)
		new_seq = ++dlm_cb_seq;
	spin_unlock(&dlm_cb_seq_spin);

	if (lkb->lkb_flags & DLM_IFL_USER) {
		dlm_user_add_ast(lkb, flags, mode, status, sbflags, new_seq);
		return;
	}

	mutex_lock(&lkb->lkb_cb_mutex);
	prev_seq = lkb->lkb_callbacks[0].seq;

	rv = dlm_add_lkb_callback(lkb, flags, mode, status, sbflags, new_seq);
	if (rv < 0)
		goto out;

	if (!prev_seq) {
		kref_get(&lkb->lkb_ref);

		if (test_bit(LSFL_CB_DELAY, &ls->ls_flags)) {
			mutex_lock(&ls->ls_cb_mutex);
			list_add(&lkb->lkb_cb_list, &ls->ls_cb_delay);
			mutex_unlock(&ls->ls_cb_mutex);
		} else {
			queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
		}
	}
 out:
	mutex_unlock(&lkb->lkb_cb_mutex);
}

void dlm_callback_work(struct work_struct *work)
{
	struct dlm_lkb *lkb = container_of(work, struct dlm_lkb, lkb_cb_work);
	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
	void (*castfn) (void *astparam);
	void (*bastfn) (void *astparam, int mode);
	struct dlm_callback callbacks[DLM_CALLBACKS_SIZE];
	int i, rv, resid;

	memset(&callbacks, 0, sizeof(callbacks));

	mutex_lock(&lkb->lkb_cb_mutex);
	if (!lkb->lkb_callbacks[0].seq) {
		/* no callback work exists, shouldn't happen */
		log_error(ls, "dlm_callback_work %x no work", lkb->lkb_id);
		dlm_print_lkb(lkb);
		dlm_dump_lkb_callbacks(lkb);
	}

	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
		rv = dlm_rem_lkb_callback(ls, lkb, &callbacks[i], &resid);
		if (rv < 0)
			break;
	}

	if (resid) {
		/* cbs remain, loop should have removed all, shouldn't happen */
		log_error(ls, "dlm_callback_work %x resid %d", lkb->lkb_id,
			  resid);
		dlm_print_lkb(lkb);
		dlm_dump_lkb_callbacks(lkb);
	}
	mutex_unlock(&lkb->lkb_cb_mutex);

	castfn = lkb->lkb_astfn;
	bastfn = lkb->lkb_bastfn;

	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
		if (!callbacks[i].seq)
			break;
		if (callbacks[i].flags & DLM_CB_SKIP) {
			continue;
		} else if (callbacks[i].flags & DLM_CB_BAST) {
			trace_dlm_bast(ls, lkb, callbacks[i].mode);
			bastfn(lkb->lkb_astparam, callbacks[i].mode);
		} else if (callbacks[i].flags & DLM_CB_CAST) {
			lkb->lkb_lksb->sb_status = callbacks[i].sb_status;
			lkb->lkb_lksb->sb_flags = callbacks[i].sb_flags;
			trace_dlm_ast(ls, lkb);
			castfn(lkb->lkb_astparam);
		}
	}

	/* undo kref_get from dlm_add_callback, may cause lkb to be freed */
	dlm_put_lkb(lkb);
}

int dlm_callback_start(struct dlm_ls *ls)
{
	ls->ls_callback_wq = alloc_workqueue("dlm_callback",
					     WQ_HIGHPRI | WQ_MEM_RECLAIM, 0);
	if (!ls->ls_callback_wq) {
		log_print("can't start dlm_callback workqueue");
		return -ENOMEM;
	}
	return 0;
}

void dlm_callback_stop(struct dlm_ls *ls)
{
	if (ls->ls_callback_wq)
		destroy_workqueue(ls->ls_callback_wq);
}

void dlm_callback_suspend(struct dlm_ls *ls)
{
	set_bit(LSFL_CB_DELAY, &ls->ls_flags);

	if (ls->ls_callback_wq)
		flush_workqueue(ls->ls_callback_wq);
}

#define MAX_CB_QUEUE 25

void dlm_callback_resume(struct dlm_ls *ls)
{
	struct dlm_lkb *lkb, *safe;
	int count = 0, sum = 0;
	bool empty;

	clear_bit(LSFL_CB_DELAY, &ls->ls_flags);

	if (!ls->ls_callback_wq)
		return;

more:
	mutex_lock(&ls->ls_cb_mutex);
	list_for_each_entry_safe(lkb, safe, &ls->ls_cb_delay, lkb_cb_list) {
		list_del_init(&lkb->lkb_cb_list);
		queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
		count++;
		if (count == MAX_CB_QUEUE)
			break;
	}
	empty = list_empty(&ls->ls_cb_delay);
	mutex_unlock(&ls->ls_cb_mutex);

	sum += count;
	if (!empty) {
		count = 0;
		cond_resched();
		goto more;
	}

	if (sum)
		log_rinfo(ls, "%s %d", __func__, sum);
}

back to top