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
do_mounts_initrd.c
// SPDX-License-Identifier: GPL-2.0
#include <linux/unistd.h>
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/minix_fs.h>
#include <linux/romfs_fs.h>
#include <linux/initrd.h>
#include <linux/sched.h>
#include <linux/freezer.h>
#include <linux/kmod.h>
#include <uapi/linux/mount.h>

#include "do_mounts.h"

unsigned long initrd_start, initrd_end;
int initrd_below_start_ok;
static unsigned int real_root_dev;	/* do_proc_dointvec cannot handle kdev_t */
static int __initdata mount_initrd = 1;

phys_addr_t phys_initrd_start __initdata;
unsigned long phys_initrd_size __initdata;

#ifdef CONFIG_SYSCTL
static struct ctl_table kern_do_mounts_initrd_table[] = {
	{
		.procname       = "real-root-dev",
		.data           = &real_root_dev,
		.maxlen         = sizeof(int),
		.mode           = 0644,
		.proc_handler   = proc_dointvec,
	},
	{ }
};

static __init int kernel_do_mounts_initrd_sysctls_init(void)
{
	register_sysctl_init("kernel", kern_do_mounts_initrd_table);
	return 0;
}
late_initcall(kernel_do_mounts_initrd_sysctls_init);
#endif /* CONFIG_SYSCTL */

static int __init no_initrd(char *str)
{
	mount_initrd = 0;
	return 1;
}

__setup("noinitrd", no_initrd);

static int __init early_initrdmem(char *p)
{
	phys_addr_t start;
	unsigned long size;
	char *endp;

	start = memparse(p, &endp);
	if (*endp == ',') {
		size = memparse(endp + 1, NULL);

		phys_initrd_start = start;
		phys_initrd_size = size;
	}
	return 0;
}
early_param("initrdmem", early_initrdmem);

static int __init early_initrd(char *p)
{
	return early_initrdmem(p);
}
early_param("initrd", early_initrd);

static int __init init_linuxrc(struct subprocess_info *info, struct cred *new)
{
	ksys_unshare(CLONE_FS | CLONE_FILES);
	console_on_rootfs();
	/* move initrd over / and chdir/chroot in initrd root */
	init_chdir("/root");
	init_mount(".", "/", NULL, MS_MOVE, NULL);
	init_chroot(".");
	ksys_setsid();
	return 0;
}

static void __init handle_initrd(void)
{
	struct subprocess_info *info;
	static char *argv[] = { "linuxrc", NULL, };
	extern char *envp_init[];
	int error;

	pr_warn("using deprecated initrd support, will be removed in 2021.\n");

	real_root_dev = new_encode_dev(ROOT_DEV);
	create_dev("/dev/root.old", Root_RAM0);
	/* mount initrd on rootfs' /root */
	mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY);
	init_mkdir("/old", 0700);
	init_chdir("/old");

	/*
	 * In case that a resume from disk is carried out by linuxrc or one of
	 * its children, we need to tell the freezer not to wait for us.
	 */
	current->flags |= PF_FREEZER_SKIP;

	info = call_usermodehelper_setup("/linuxrc", argv, envp_init,
					 GFP_KERNEL, init_linuxrc, NULL, NULL);
	if (!info)
		return;
	call_usermodehelper_exec(info, UMH_WAIT_PROC);

	current->flags &= ~PF_FREEZER_SKIP;

	/* move initrd to rootfs' /old */
	init_mount("..", ".", NULL, MS_MOVE, NULL);
	/* switch root and cwd back to / of rootfs */
	init_chroot("..");

	if (new_decode_dev(real_root_dev) == Root_RAM0) {
		init_chdir("/old");
		return;
	}

	init_chdir("/");
	ROOT_DEV = new_decode_dev(real_root_dev);
	mount_root();

	printk(KERN_NOTICE "Trying to move old root to /initrd ... ");
	error = init_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL);
	if (!error)
		printk("okay\n");
	else {
		if (error == -ENOENT)
			printk("/initrd does not exist. Ignored.\n");
		else
			printk("failed\n");
		printk(KERN_NOTICE "Unmounting old root\n");
		init_umount("/old", MNT_DETACH);
	}
}

bool __init initrd_load(void)
{
	if (mount_initrd) {
		create_dev("/dev/ram", Root_RAM0);
		/*
		 * Load the initrd data into /dev/ram0. Execute it as initrd
		 * unless /dev/ram0 is supposed to be our actual root device,
		 * in that case the ram disk is just set up here, and gets
		 * mounted in the normal path.
		 */
		if (rd_load_image("/initrd.image") && ROOT_DEV != Root_RAM0) {
			init_unlink("/initrd.image");
			handle_initrd();
			return true;
		}
	}
	init_unlink("/initrd.image");
	return false;
}
back to top