https://github.com/torvalds/linux
Revision 69ad4ef868c1fc7609daa235dfa46d28ba7a3ba3 authored by Matt Lupfer on 08 March 2022, 15:27:02 UTC, committed by Martin K. Petersen on 15 March 2022, 03:45:19 UTC
A page fault was encountered in mpt3sas on a LUN reset error path:

[  145.763216] mpt3sas_cm1: Task abort tm failed: handle(0x0002),timeout(30) tr_method(0x0) smid(3) msix_index(0)
[  145.778932] scsi 1:0:0:0: task abort: FAILED scmd(0x0000000024ba29a2)
[  145.817307] scsi 1:0:0:0: attempting device reset! scmd(0x0000000024ba29a2)
[  145.827253] scsi 1:0:0:0: [sg1] tag#2 CDB: Receive Diagnostic 1c 01 01 ff fc 00
[  145.837617] scsi target1:0:0: handle(0x0002), sas_address(0x500605b0000272b9), phy(0)
[  145.848598] scsi target1:0:0: enclosure logical id(0x500605b0000272b8), slot(0)
[  149.858378] mpt3sas_cm1: Poll ReplyDescriptor queues for completion of smid(0), task_type(0x05), handle(0x0002)
[  149.875202] BUG: unable to handle page fault for address: 00000007fffc445d
[  149.885617] #PF: supervisor read access in kernel mode
[  149.894346] #PF: error_code(0x0000) - not-present page
[  149.903123] PGD 0 P4D 0
[  149.909387] Oops: 0000 [#1] PREEMPT SMP NOPTI
[  149.917417] CPU: 24 PID: 3512 Comm: scsi_eh_1 Kdump: loaded Tainted: G S         O      5.10.89-altav-1 #1
[  149.934327] Hardware name: DDN           200NVX2             /200NVX2-MB          , BIOS ATHG2.2.02.01 09/10/2021
[  149.951871] RIP: 0010:_base_process_reply_queue+0x4b/0x900 [mpt3sas]
[  149.961889] Code: 0f 84 22 02 00 00 8d 48 01 49 89 fd 48 8d 57 38 f0 0f b1 4f 38 0f 85 d8 01 00 00 49 8b 45 10 45 31 e4 41 8b 55 0c 48 8d 1c d0 <0f> b6 03 83 e0 0f 3c 0f 0f 85 a2 00 00 00 e9 e6 01 00 00 0f b7 ee
[  149.991952] RSP: 0018:ffffc9000f1ebcb8 EFLAGS: 00010246
[  150.000937] RAX: 0000000000000055 RBX: 00000007fffc445d RCX: 000000002548f071
[  150.011841] RDX: 00000000ffff8881 RSI: 0000000000000001 RDI: ffff888125ed50d8
[  150.022670] RBP: 0000000000000000 R08: 0000000000000000 R09: c0000000ffff7fff
[  150.033445] R10: ffffc9000f1ebb68 R11: ffffc9000f1ebb60 R12: 0000000000000000
[  150.044204] R13: ffff888125ed50d8 R14: 0000000000000080 R15: 34cdc00034cdea80
[  150.054963] FS:  0000000000000000(0000) GS:ffff88dfaf200000(0000) knlGS:0000000000000000
[  150.066715] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  150.076078] CR2: 00000007fffc445d CR3: 000000012448a006 CR4: 0000000000770ee0
[  150.086887] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  150.097670] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  150.108323] PKRU: 55555554
[  150.114690] Call Trace:
[  150.120497]  ? printk+0x48/0x4a
[  150.127049]  mpt3sas_scsih_issue_tm.cold.114+0x2e/0x2b3 [mpt3sas]
[  150.136453]  mpt3sas_scsih_issue_locked_tm+0x86/0xb0 [mpt3sas]
[  150.145759]  scsih_dev_reset+0xea/0x300 [mpt3sas]
[  150.153891]  scsi_eh_ready_devs+0x541/0x9e0 [scsi_mod]
[  150.162206]  ? __scsi_host_match+0x20/0x20 [scsi_mod]
[  150.170406]  ? scsi_try_target_reset+0x90/0x90 [scsi_mod]
[  150.178925]  ? blk_mq_tagset_busy_iter+0x45/0x60
[  150.186638]  ? scsi_try_target_reset+0x90/0x90 [scsi_mod]
[  150.195087]  scsi_error_handler+0x3a5/0x4a0 [scsi_mod]
[  150.203206]  ? __schedule+0x1e9/0x610
[  150.209783]  ? scsi_eh_get_sense+0x210/0x210 [scsi_mod]
[  150.217924]  kthread+0x12e/0x150
[  150.224041]  ? kthread_worker_fn+0x130/0x130
[  150.231206]  ret_from_fork+0x1f/0x30

This is caused by mpt3sas_base_sync_reply_irqs() using an invalid reply_q
pointer outside of the list_for_each_entry() loop. At the end of the full
list traversal the pointer is invalid.

Move the _base_process_reply_queue() call inside of the loop.

Link: https://lore.kernel.org/r/d625deae-a958-0ace-2ba3-0888dd0a415b@ddn.com
Fixes: 711a923c14d9 ("scsi: mpt3sas: Postprocessing of target and LUN reset")
Cc: stable@vger.kernel.org
Acked-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Signed-off-by: Matt Lupfer <mlupfer@ddn.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
1 parent 10af115
Raw File
Tip revision: 69ad4ef868c1fc7609daa235dfa46d28ba7a3ba3 authored by Matt Lupfer on 08 March 2022, 15:27:02 UTC
scsi: mpt3sas: Page fault in reply q processing
Tip revision: 69ad4ef
ksysfs.c
// SPDX-License-Identifier: GPL-2.0-only
/*
 * kernel/ksysfs.c - sysfs attributes in /sys/kernel, which
 * 		     are not related to any other subsystem
 *
 * Copyright (C) 2004 Kay Sievers <kay.sievers@vrfy.org>
 */

#include <linux/kobject.h>
#include <linux/string.h>
#include <linux/sysfs.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/kexec.h>
#include <linux/profile.h>
#include <linux/stat.h>
#include <linux/sched.h>
#include <linux/capability.h>
#include <linux/compiler.h>

#include <linux/rcupdate.h>	/* rcu_expedited and rcu_normal */

#define KERNEL_ATTR_RO(_name) \
static struct kobj_attribute _name##_attr = __ATTR_RO(_name)

#define KERNEL_ATTR_RW(_name) \
static struct kobj_attribute _name##_attr = \
	__ATTR(_name, 0644, _name##_show, _name##_store)

/* current uevent sequence number */
static ssize_t uevent_seqnum_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%llu\n", (unsigned long long)uevent_seqnum);
}
KERNEL_ATTR_RO(uevent_seqnum);

#ifdef CONFIG_UEVENT_HELPER
/* uevent helper program, used during early boot */
static ssize_t uevent_helper_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%s\n", uevent_helper);
}
static ssize_t uevent_helper_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	if (count+1 > UEVENT_HELPER_PATH_LEN)
		return -ENOENT;
	memcpy(uevent_helper, buf, count);
	uevent_helper[count] = '\0';
	if (count && uevent_helper[count-1] == '\n')
		uevent_helper[count-1] = '\0';
	return count;
}
KERNEL_ATTR_RW(uevent_helper);
#endif

#ifdef CONFIG_PROFILING
static ssize_t profiling_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", prof_on);
}
static ssize_t profiling_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	int ret;

	if (prof_on)
		return -EEXIST;
	/*
	 * This eventually calls into get_option() which
	 * has a ton of callers and is not const.  It is
	 * easiest to cast it away here.
	 */
	profile_setup((char *)buf);
	ret = profile_init();
	if (ret)
		return ret;
	ret = create_proc_profile();
	if (ret)
		return ret;
	return count;
}
KERNEL_ATTR_RW(profiling);
#endif

#ifdef CONFIG_KEXEC_CORE
static ssize_t kexec_loaded_show(struct kobject *kobj,
				 struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", !!kexec_image);
}
KERNEL_ATTR_RO(kexec_loaded);

static ssize_t kexec_crash_loaded_show(struct kobject *kobj,
				       struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", kexec_crash_loaded());
}
KERNEL_ATTR_RO(kexec_crash_loaded);

static ssize_t kexec_crash_size_show(struct kobject *kobj,
				       struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%zu\n", crash_get_memory_size());
}
static ssize_t kexec_crash_size_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	unsigned long cnt;
	int ret;

	if (kstrtoul(buf, 0, &cnt))
		return -EINVAL;

	ret = crash_shrink_memory(cnt);
	return ret < 0 ? ret : count;
}
KERNEL_ATTR_RW(kexec_crash_size);

#endif /* CONFIG_KEXEC_CORE */

#ifdef CONFIG_CRASH_CORE

static ssize_t vmcoreinfo_show(struct kobject *kobj,
			       struct kobj_attribute *attr, char *buf)
{
	phys_addr_t vmcore_base = paddr_vmcoreinfo_note();
	return sprintf(buf, "%pa %x\n", &vmcore_base,
			(unsigned int)VMCOREINFO_NOTE_SIZE);
}
KERNEL_ATTR_RO(vmcoreinfo);

#endif /* CONFIG_CRASH_CORE */

/* whether file capabilities are enabled */
static ssize_t fscaps_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", file_caps_enabled);
}
KERNEL_ATTR_RO(fscaps);

#ifndef CONFIG_TINY_RCU
int rcu_expedited;
static ssize_t rcu_expedited_show(struct kobject *kobj,
				  struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", READ_ONCE(rcu_expedited));
}
static ssize_t rcu_expedited_store(struct kobject *kobj,
				   struct kobj_attribute *attr,
				   const char *buf, size_t count)
{
	if (kstrtoint(buf, 0, &rcu_expedited))
		return -EINVAL;

	return count;
}
KERNEL_ATTR_RW(rcu_expedited);

int rcu_normal;
static ssize_t rcu_normal_show(struct kobject *kobj,
			       struct kobj_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", READ_ONCE(rcu_normal));
}
static ssize_t rcu_normal_store(struct kobject *kobj,
				struct kobj_attribute *attr,
				const char *buf, size_t count)
{
	if (kstrtoint(buf, 0, &rcu_normal))
		return -EINVAL;

	return count;
}
KERNEL_ATTR_RW(rcu_normal);
#endif /* #ifndef CONFIG_TINY_RCU */

/*
 * Make /sys/kernel/notes give the raw contents of our kernel .notes section.
 */
extern const void __start_notes __weak;
extern const void __stop_notes __weak;
#define	notes_size (&__stop_notes - &__start_notes)

static ssize_t notes_read(struct file *filp, struct kobject *kobj,
			  struct bin_attribute *bin_attr,
			  char *buf, loff_t off, size_t count)
{
	memcpy(buf, &__start_notes + off, count);
	return count;
}

static struct bin_attribute notes_attr __ro_after_init  = {
	.attr = {
		.name = "notes",
		.mode = S_IRUGO,
	},
	.read = &notes_read,
};

struct kobject *kernel_kobj;
EXPORT_SYMBOL_GPL(kernel_kobj);

static struct attribute * kernel_attrs[] = {
	&fscaps_attr.attr,
	&uevent_seqnum_attr.attr,
#ifdef CONFIG_UEVENT_HELPER
	&uevent_helper_attr.attr,
#endif
#ifdef CONFIG_PROFILING
	&profiling_attr.attr,
#endif
#ifdef CONFIG_KEXEC_CORE
	&kexec_loaded_attr.attr,
	&kexec_crash_loaded_attr.attr,
	&kexec_crash_size_attr.attr,
#endif
#ifdef CONFIG_CRASH_CORE
	&vmcoreinfo_attr.attr,
#endif
#ifndef CONFIG_TINY_RCU
	&rcu_expedited_attr.attr,
	&rcu_normal_attr.attr,
#endif
	NULL
};

static const struct attribute_group kernel_attr_group = {
	.attrs = kernel_attrs,
};

static int __init ksysfs_init(void)
{
	int error;

	kernel_kobj = kobject_create_and_add("kernel", NULL);
	if (!kernel_kobj) {
		error = -ENOMEM;
		goto exit;
	}
	error = sysfs_create_group(kernel_kobj, &kernel_attr_group);
	if (error)
		goto kset_exit;

	if (notes_size > 0) {
		notes_attr.size = notes_size;
		error = sysfs_create_bin_file(kernel_kobj, &notes_attr);
		if (error)
			goto group_exit;
	}

	return 0;

group_exit:
	sysfs_remove_group(kernel_kobj, &kernel_attr_group);
kset_exit:
	kobject_put(kernel_kobj);
exit:
	return error;
}

core_initcall(ksysfs_init);
back to top