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
Tip revision: 69ad4ef868c1fc7609daa235dfa46d28ba7a3ba3 authored by Matt Lupfer on 08 March 2022, 15:27:02 UTC
scsi: mpt3sas: Page fault in reply q processing
scsi: mpt3sas: Page fault in reply q processing
Tip revision: 69ad4ef
notifier.c
// SPDX-License-Identifier: GPL-2.0-only
#include <linux/kdebug.h>
#include <linux/kprobes.h>
#include <linux/export.h>
#include <linux/notifier.h>
#include <linux/rcupdate.h>
#include <linux/vmalloc.h>
#include <linux/reboot.h>
/*
* Notifier list for kernel code which wants to be called
* at shutdown. This is used to stop any idling DMA operations
* and the like.
*/
BLOCKING_NOTIFIER_HEAD(reboot_notifier_list);
/*
* Notifier chain core routines. The exported routines below
* are layered on top of these, with appropriate locking added.
*/
static int notifier_chain_register(struct notifier_block **nl,
struct notifier_block *n)
{
while ((*nl) != NULL) {
if (unlikely((*nl) == n)) {
WARN(1, "notifier callback %ps already registered",
n->notifier_call);
return -EEXIST;
}
if (n->priority > (*nl)->priority)
break;
nl = &((*nl)->next);
}
n->next = *nl;
rcu_assign_pointer(*nl, n);
return 0;
}
static int notifier_chain_unregister(struct notifier_block **nl,
struct notifier_block *n)
{
while ((*nl) != NULL) {
if ((*nl) == n) {
rcu_assign_pointer(*nl, n->next);
return 0;
}
nl = &((*nl)->next);
}
return -ENOENT;
}
/**
* notifier_call_chain - Informs the registered notifiers about an event.
* @nl: Pointer to head of the blocking notifier chain
* @val: Value passed unmodified to notifier function
* @v: Pointer passed unmodified to notifier function
* @nr_to_call: Number of notifier functions to be called. Don't care
* value of this parameter is -1.
* @nr_calls: Records the number of notifications sent. Don't care
* value of this field is NULL.
* @returns: notifier_call_chain returns the value returned by the
* last notifier function called.
*/
static int notifier_call_chain(struct notifier_block **nl,
unsigned long val, void *v,
int nr_to_call, int *nr_calls)
{
int ret = NOTIFY_DONE;
struct notifier_block *nb, *next_nb;
nb = rcu_dereference_raw(*nl);
while (nb && nr_to_call) {
next_nb = rcu_dereference_raw(nb->next);
#ifdef CONFIG_DEBUG_NOTIFIERS
if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) {
WARN(1, "Invalid notifier called!");
nb = next_nb;
continue;
}
#endif
ret = nb->notifier_call(nb, val, v);
if (nr_calls)
(*nr_calls)++;
if (ret & NOTIFY_STOP_MASK)
break;
nb = next_nb;
nr_to_call--;
}
return ret;
}
NOKPROBE_SYMBOL(notifier_call_chain);
/**
* notifier_call_chain_robust - Inform the registered notifiers about an event
* and rollback on error.
* @nl: Pointer to head of the blocking notifier chain
* @val_up: Value passed unmodified to the notifier function
* @val_down: Value passed unmodified to the notifier function when recovering
* from an error on @val_up
* @v Pointer passed unmodified to the notifier function
*
* NOTE: It is important the @nl chain doesn't change between the two
* invocations of notifier_call_chain() such that we visit the
* exact same notifier callbacks; this rules out any RCU usage.
*
* Returns: the return value of the @val_up call.
*/
static int notifier_call_chain_robust(struct notifier_block **nl,
unsigned long val_up, unsigned long val_down,
void *v)
{
int ret, nr = 0;
ret = notifier_call_chain(nl, val_up, v, -1, &nr);
if (ret & NOTIFY_STOP_MASK)
notifier_call_chain(nl, val_down, v, nr-1, NULL);
return ret;
}
/*
* Atomic notifier chain routines. Registration and unregistration
* use a spinlock, and call_chain is synchronized by RCU (no locks).
*/
/**
* atomic_notifier_chain_register - Add notifier to an atomic notifier chain
* @nh: Pointer to head of the atomic notifier chain
* @n: New entry in notifier chain
*
* Adds a notifier to an atomic notifier chain.
*
* Returns 0 on success, %-EEXIST on error.
*/
int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
struct notifier_block *n)
{
unsigned long flags;
int ret;
spin_lock_irqsave(&nh->lock, flags);
ret = notifier_chain_register(&nh->head, n);
spin_unlock_irqrestore(&nh->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(atomic_notifier_chain_register);
/**
* atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain
* @nh: Pointer to head of the atomic notifier chain
* @n: Entry to remove from notifier chain
*
* Removes a notifier from an atomic notifier chain.
*
* Returns zero on success or %-ENOENT on failure.
*/
int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh,
struct notifier_block *n)
{
unsigned long flags;
int ret;
spin_lock_irqsave(&nh->lock, flags);
ret = notifier_chain_unregister(&nh->head, n);
spin_unlock_irqrestore(&nh->lock, flags);
synchronize_rcu();
return ret;
}
EXPORT_SYMBOL_GPL(atomic_notifier_chain_unregister);
/**
* atomic_notifier_call_chain - Call functions in an atomic notifier chain
* @nh: Pointer to head of the atomic notifier chain
* @val: Value passed unmodified to notifier function
* @v: Pointer passed unmodified to notifier function
*
* Calls each function in a notifier chain in turn. The functions
* run in an atomic context, so they must not block.
* This routine uses RCU to synchronize with changes to the chain.
*
* If the return value of the notifier can be and'ed
* with %NOTIFY_STOP_MASK then atomic_notifier_call_chain()
* will return immediately, with the return value of
* the notifier function which halted execution.
* Otherwise the return value is the return value
* of the last notifier function called.
*/
int atomic_notifier_call_chain(struct atomic_notifier_head *nh,
unsigned long val, void *v)
{
int ret;
rcu_read_lock();
ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
rcu_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(atomic_notifier_call_chain);
NOKPROBE_SYMBOL(atomic_notifier_call_chain);
/*
* Blocking notifier chain routines. All access to the chain is
* synchronized by an rwsem.
*/
/**
* blocking_notifier_chain_register - Add notifier to a blocking notifier chain
* @nh: Pointer to head of the blocking notifier chain
* @n: New entry in notifier chain
*
* Adds a notifier to a blocking notifier chain.
* Must be called in process context.
*
* Returns 0 on success, %-EEXIST on error.
*/
int blocking_notifier_chain_register(struct blocking_notifier_head *nh,
struct notifier_block *n)
{
int ret;
/*
* This code gets used during boot-up, when task switching is
* not yet working and interrupts must remain disabled. At
* such times we must not call down_write().
*/
if (unlikely(system_state == SYSTEM_BOOTING))
return notifier_chain_register(&nh->head, n);
down_write(&nh->rwsem);
ret = notifier_chain_register(&nh->head, n);
up_write(&nh->rwsem);
return ret;
}
EXPORT_SYMBOL_GPL(blocking_notifier_chain_register);
/**
* blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain
* @nh: Pointer to head of the blocking notifier chain
* @n: Entry to remove from notifier chain
*
* Removes a notifier from a blocking notifier chain.
* Must be called from process context.
*
* Returns zero on success or %-ENOENT on failure.
*/
int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh,
struct notifier_block *n)
{
int ret;
/*
* This code gets used during boot-up, when task switching is
* not yet working and interrupts must remain disabled. At
* such times we must not call down_write().
*/
if (unlikely(system_state == SYSTEM_BOOTING))
return notifier_chain_unregister(&nh->head, n);
down_write(&nh->rwsem);
ret = notifier_chain_unregister(&nh->head, n);
up_write(&nh->rwsem);
return ret;
}
EXPORT_SYMBOL_GPL(blocking_notifier_chain_unregister);
int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh,
unsigned long val_up, unsigned long val_down, void *v)
{
int ret = NOTIFY_DONE;
/*
* We check the head outside the lock, but if this access is
* racy then it does not matter what the result of the test
* is, we re-check the list after having taken the lock anyway:
*/
if (rcu_access_pointer(nh->head)) {
down_read(&nh->rwsem);
ret = notifier_call_chain_robust(&nh->head, val_up, val_down, v);
up_read(&nh->rwsem);
}
return ret;
}
EXPORT_SYMBOL_GPL(blocking_notifier_call_chain_robust);
/**
* blocking_notifier_call_chain - Call functions in a blocking notifier chain
* @nh: Pointer to head of the blocking notifier chain
* @val: Value passed unmodified to notifier function
* @v: Pointer passed unmodified to notifier function
*
* Calls each function in a notifier chain in turn. The functions
* run in a process context, so they are allowed to block.
*
* If the return value of the notifier can be and'ed
* with %NOTIFY_STOP_MASK then blocking_notifier_call_chain()
* will return immediately, with the return value of
* the notifier function which halted execution.
* Otherwise the return value is the return value
* of the last notifier function called.
*/
int blocking_notifier_call_chain(struct blocking_notifier_head *nh,
unsigned long val, void *v)
{
int ret = NOTIFY_DONE;
/*
* We check the head outside the lock, but if this access is
* racy then it does not matter what the result of the test
* is, we re-check the list after having taken the lock anyway:
*/
if (rcu_access_pointer(nh->head)) {
down_read(&nh->rwsem);
ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
up_read(&nh->rwsem);
}
return ret;
}
EXPORT_SYMBOL_GPL(blocking_notifier_call_chain);
/*
* Raw notifier chain routines. There is no protection;
* the caller must provide it. Use at your own risk!
*/
/**
* raw_notifier_chain_register - Add notifier to a raw notifier chain
* @nh: Pointer to head of the raw notifier chain
* @n: New entry in notifier chain
*
* Adds a notifier to a raw notifier chain.
* All locking must be provided by the caller.
*
* Returns 0 on success, %-EEXIST on error.
*/
int raw_notifier_chain_register(struct raw_notifier_head *nh,
struct notifier_block *n)
{
return notifier_chain_register(&nh->head, n);
}
EXPORT_SYMBOL_GPL(raw_notifier_chain_register);
/**
* raw_notifier_chain_unregister - Remove notifier from a raw notifier chain
* @nh: Pointer to head of the raw notifier chain
* @n: Entry to remove from notifier chain
*
* Removes a notifier from a raw notifier chain.
* All locking must be provided by the caller.
*
* Returns zero on success or %-ENOENT on failure.
*/
int raw_notifier_chain_unregister(struct raw_notifier_head *nh,
struct notifier_block *n)
{
return notifier_chain_unregister(&nh->head, n);
}
EXPORT_SYMBOL_GPL(raw_notifier_chain_unregister);
int raw_notifier_call_chain_robust(struct raw_notifier_head *nh,
unsigned long val_up, unsigned long val_down, void *v)
{
return notifier_call_chain_robust(&nh->head, val_up, val_down, v);
}
EXPORT_SYMBOL_GPL(raw_notifier_call_chain_robust);
/**
* raw_notifier_call_chain - Call functions in a raw notifier chain
* @nh: Pointer to head of the raw notifier chain
* @val: Value passed unmodified to notifier function
* @v: Pointer passed unmodified to notifier function
*
* Calls each function in a notifier chain in turn. The functions
* run in an undefined context.
* All locking must be provided by the caller.
*
* If the return value of the notifier can be and'ed
* with %NOTIFY_STOP_MASK then raw_notifier_call_chain()
* will return immediately, with the return value of
* the notifier function which halted execution.
* Otherwise the return value is the return value
* of the last notifier function called.
*/
int raw_notifier_call_chain(struct raw_notifier_head *nh,
unsigned long val, void *v)
{
return notifier_call_chain(&nh->head, val, v, -1, NULL);
}
EXPORT_SYMBOL_GPL(raw_notifier_call_chain);
#ifdef CONFIG_SRCU
/*
* SRCU notifier chain routines. Registration and unregistration
* use a mutex, and call_chain is synchronized by SRCU (no locks).
*/
/**
* srcu_notifier_chain_register - Add notifier to an SRCU notifier chain
* @nh: Pointer to head of the SRCU notifier chain
* @n: New entry in notifier chain
*
* Adds a notifier to an SRCU notifier chain.
* Must be called in process context.
*
* Returns 0 on success, %-EEXIST on error.
*/
int srcu_notifier_chain_register(struct srcu_notifier_head *nh,
struct notifier_block *n)
{
int ret;
/*
* This code gets used during boot-up, when task switching is
* not yet working and interrupts must remain disabled. At
* such times we must not call mutex_lock().
*/
if (unlikely(system_state == SYSTEM_BOOTING))
return notifier_chain_register(&nh->head, n);
mutex_lock(&nh->mutex);
ret = notifier_chain_register(&nh->head, n);
mutex_unlock(&nh->mutex);
return ret;
}
EXPORT_SYMBOL_GPL(srcu_notifier_chain_register);
/**
* srcu_notifier_chain_unregister - Remove notifier from an SRCU notifier chain
* @nh: Pointer to head of the SRCU notifier chain
* @n: Entry to remove from notifier chain
*
* Removes a notifier from an SRCU notifier chain.
* Must be called from process context.
*
* Returns zero on success or %-ENOENT on failure.
*/
int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh,
struct notifier_block *n)
{
int ret;
/*
* This code gets used during boot-up, when task switching is
* not yet working and interrupts must remain disabled. At
* such times we must not call mutex_lock().
*/
if (unlikely(system_state == SYSTEM_BOOTING))
return notifier_chain_unregister(&nh->head, n);
mutex_lock(&nh->mutex);
ret = notifier_chain_unregister(&nh->head, n);
mutex_unlock(&nh->mutex);
synchronize_srcu(&nh->srcu);
return ret;
}
EXPORT_SYMBOL_GPL(srcu_notifier_chain_unregister);
/**
* srcu_notifier_call_chain - Call functions in an SRCU notifier chain
* @nh: Pointer to head of the SRCU notifier chain
* @val: Value passed unmodified to notifier function
* @v: Pointer passed unmodified to notifier function
*
* Calls each function in a notifier chain in turn. The functions
* run in a process context, so they are allowed to block.
*
* If the return value of the notifier can be and'ed
* with %NOTIFY_STOP_MASK then srcu_notifier_call_chain()
* will return immediately, with the return value of
* the notifier function which halted execution.
* Otherwise the return value is the return value
* of the last notifier function called.
*/
int srcu_notifier_call_chain(struct srcu_notifier_head *nh,
unsigned long val, void *v)
{
int ret;
int idx;
idx = srcu_read_lock(&nh->srcu);
ret = notifier_call_chain(&nh->head, val, v, -1, NULL);
srcu_read_unlock(&nh->srcu, idx);
return ret;
}
EXPORT_SYMBOL_GPL(srcu_notifier_call_chain);
/**
* srcu_init_notifier_head - Initialize an SRCU notifier head
* @nh: Pointer to head of the srcu notifier chain
*
* Unlike other sorts of notifier heads, SRCU notifier heads require
* dynamic initialization. Be sure to call this routine before
* calling any of the other SRCU notifier routines for this head.
*
* If an SRCU notifier head is deallocated, it must first be cleaned
* up by calling srcu_cleanup_notifier_head(). Otherwise the head's
* per-cpu data (used by the SRCU mechanism) will leak.
*/
void srcu_init_notifier_head(struct srcu_notifier_head *nh)
{
mutex_init(&nh->mutex);
if (init_srcu_struct(&nh->srcu) < 0)
BUG();
nh->head = NULL;
}
EXPORT_SYMBOL_GPL(srcu_init_notifier_head);
#endif /* CONFIG_SRCU */
static ATOMIC_NOTIFIER_HEAD(die_chain);
int notrace notify_die(enum die_val val, const char *str,
struct pt_regs *regs, long err, int trap, int sig)
{
struct die_args args = {
.regs = regs,
.str = str,
.err = err,
.trapnr = trap,
.signr = sig,
};
RCU_LOCKDEP_WARN(!rcu_is_watching(),
"notify_die called but RCU thinks we're quiescent");
return atomic_notifier_call_chain(&die_chain, val, &args);
}
NOKPROBE_SYMBOL(notify_die);
int register_die_notifier(struct notifier_block *nb)
{
return atomic_notifier_chain_register(&die_chain, nb);
}
EXPORT_SYMBOL_GPL(register_die_notifier);
int unregister_die_notifier(struct notifier_block *nb)
{
return atomic_notifier_chain_unregister(&die_chain, nb);
}
EXPORT_SYMBOL_GPL(unregister_die_notifier);
Computing file changes ...