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
capability.c
// SPDX-License-Identifier: GPL-2.0
/*
* linux/kernel/capability.c
*
* Copyright (C) 1997 Andrew Main <zefram@fysh.org>
*
* Integrated into 2.1.97+, Andrew G. Morgan <morgan@kernel.org>
* 30 May 2002: Cleanup, Robert M. Love <rml@tech9.net>
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/uaccess.h>
/*
* Leveraged for setting/resetting capabilities
*/
const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET;
EXPORT_SYMBOL(__cap_empty_set);
int file_caps_enabled = 1;
static int __init file_caps_disable(char *str)
{
file_caps_enabled = 0;
return 1;
}
__setup("no_file_caps", file_caps_disable);
#ifdef CONFIG_MULTIUSER
/*
* More recent versions of libcap are available from:
*
* http://www.kernel.org/pub/linux/libs/security/linux-privs/
*/
static void warn_legacy_capability_use(void)
{
char name[sizeof(current->comm)];
pr_info_once("warning: `%s' uses 32-bit capabilities (legacy support in use)\n",
get_task_comm(name, current));
}
/*
* Version 2 capabilities worked fine, but the linux/capability.h file
* that accompanied their introduction encouraged their use without
* the necessary user-space source code changes. As such, we have
* created a version 3 with equivalent functionality to version 2, but
* with a header change to protect legacy source code from using
* version 2 when it wanted to use version 1. If your system has code
* that trips the following warning, it is using version 2 specific
* capabilities and may be doing so insecurely.
*
* The remedy is to either upgrade your version of libcap (to 2.10+,
* if the application is linked against it), or recompile your
* application with modern kernel headers and this warning will go
* away.
*/
static void warn_deprecated_v2(void)
{
char name[sizeof(current->comm)];
pr_info_once("warning: `%s' uses deprecated v2 capabilities in a way that may be insecure\n",
get_task_comm(name, current));
}
/*
* Version check. Return the number of u32s in each capability flag
* array, or a negative value on error.
*/
static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy)
{
__u32 version;
if (get_user(version, &header->version))
return -EFAULT;
switch (version) {
case _LINUX_CAPABILITY_VERSION_1:
warn_legacy_capability_use();
*tocopy = _LINUX_CAPABILITY_U32S_1;
break;
case _LINUX_CAPABILITY_VERSION_2:
warn_deprecated_v2();
fallthrough; /* v3 is otherwise equivalent to v2 */
case _LINUX_CAPABILITY_VERSION_3:
*tocopy = _LINUX_CAPABILITY_U32S_3;
break;
default:
if (put_user((u32)_KERNEL_CAPABILITY_VERSION, &header->version))
return -EFAULT;
return -EINVAL;
}
return 0;
}
/*
* The only thing that can change the capabilities of the current
* process is the current process. As such, we can't be in this code
* at the same time as we are in the process of setting capabilities
* in this process. The net result is that we can limit our use of
* locks to when we are reading the caps of another process.
*/
static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp,
kernel_cap_t *pIp, kernel_cap_t *pPp)
{
int ret;
if (pid && (pid != task_pid_vnr(current))) {
struct task_struct *target;
rcu_read_lock();
target = find_task_by_vpid(pid);
if (!target)
ret = -ESRCH;
else
ret = security_capget(target, pEp, pIp, pPp);
rcu_read_unlock();
} else
ret = security_capget(current, pEp, pIp, pPp);
return ret;
}
/**
* sys_capget - get the capabilities of a given process.
* @header: pointer to struct that contains capability version and
* target pid data
* @dataptr: pointer to struct that contains the effective, permitted,
* and inheritable capabilities that are returned
*
* Returns 0 on success and < 0 on error.
*/
SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr)
{
int ret = 0;
pid_t pid;
unsigned tocopy;
kernel_cap_t pE, pI, pP;
ret = cap_validate_magic(header, &tocopy);
if ((dataptr == NULL) || (ret != 0))
return ((dataptr == NULL) && (ret == -EINVAL)) ? 0 : ret;
if (get_user(pid, &header->pid))
return -EFAULT;
if (pid < 0)
return -EINVAL;
ret = cap_get_target_pid(pid, &pE, &pI, &pP);
if (!ret) {
struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
unsigned i;
for (i = 0; i < tocopy; i++) {
kdata[i].effective = pE.cap[i];
kdata[i].permitted = pP.cap[i];
kdata[i].inheritable = pI.cap[i];
}
/*
* Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S,
* we silently drop the upper capabilities here. This
* has the effect of making older libcap
* implementations implicitly drop upper capability
* bits when they perform a: capget/modify/capset
* sequence.
*
* This behavior is considered fail-safe
* behavior. Upgrading the application to a newer
* version of libcap will enable access to the newer
* capabilities.
*
* An alternative would be to return an error here
* (-ERANGE), but that causes legacy applications to
* unexpectedly fail; the capget/modify/capset aborts
* before modification is attempted and the application
* fails.
*/
if (copy_to_user(dataptr, kdata, tocopy
* sizeof(struct __user_cap_data_struct))) {
return -EFAULT;
}
}
return ret;
}
/**
* sys_capset - set capabilities for a process or (*) a group of processes
* @header: pointer to struct that contains capability version and
* target pid data
* @data: pointer to struct that contains the effective, permitted,
* and inheritable capabilities
*
* Set capabilities for the current process only. The ability to any other
* process(es) has been deprecated and removed.
*
* The restrictions on setting capabilities are specified as:
*
* I: any raised capabilities must be a subset of the old permitted
* P: any raised capabilities must be a subset of the old permitted
* E: must be set to a subset of new permitted
*
* Returns 0 on success and < 0 on error.
*/
SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data)
{
struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S];
unsigned i, tocopy, copybytes;
kernel_cap_t inheritable, permitted, effective;
struct cred *new;
int ret;
pid_t pid;
ret = cap_validate_magic(header, &tocopy);
if (ret != 0)
return ret;
if (get_user(pid, &header->pid))
return -EFAULT;
/* may only affect current now */
if (pid != 0 && pid != task_pid_vnr(current))
return -EPERM;
copybytes = tocopy * sizeof(struct __user_cap_data_struct);
if (copybytes > sizeof(kdata))
return -EFAULT;
if (copy_from_user(&kdata, data, copybytes))
return -EFAULT;
for (i = 0; i < tocopy; i++) {
effective.cap[i] = kdata[i].effective;
permitted.cap[i] = kdata[i].permitted;
inheritable.cap[i] = kdata[i].inheritable;
}
while (i < _KERNEL_CAPABILITY_U32S) {
effective.cap[i] = 0;
permitted.cap[i] = 0;
inheritable.cap[i] = 0;
i++;
}
effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
new = prepare_creds();
if (!new)
return -ENOMEM;
ret = security_capset(new, current_cred(),
&effective, &inheritable, &permitted);
if (ret < 0)
goto error;
audit_log_capset(new, current_cred());
return commit_creds(new);
error:
abort_creds(new);
return ret;
}
/**
* has_ns_capability - Does a task have a capability in a specific user ns
* @t: The task in question
* @ns: target user namespace
* @cap: The capability to be tested for
*
* Return true if the specified task has the given superior capability
* currently in effect to the specified user namespace, false if not.
*
* Note that this does not set PF_SUPERPRIV on the task.
*/
bool has_ns_capability(struct task_struct *t,
struct user_namespace *ns, int cap)
{
int ret;
rcu_read_lock();
ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NONE);
rcu_read_unlock();
return (ret == 0);
}
/**
* has_capability - Does a task have a capability in init_user_ns
* @t: The task in question
* @cap: The capability to be tested for
*
* Return true if the specified task has the given superior capability
* currently in effect to the initial user namespace, false if not.
*
* Note that this does not set PF_SUPERPRIV on the task.
*/
bool has_capability(struct task_struct *t, int cap)
{
return has_ns_capability(t, &init_user_ns, cap);
}
EXPORT_SYMBOL(has_capability);
/**
* has_ns_capability_noaudit - Does a task have a capability (unaudited)
* in a specific user ns.
* @t: The task in question
* @ns: target user namespace
* @cap: The capability to be tested for
*
* Return true if the specified task has the given superior capability
* currently in effect to the specified user namespace, false if not.
* Do not write an audit message for the check.
*
* Note that this does not set PF_SUPERPRIV on the task.
*/
bool has_ns_capability_noaudit(struct task_struct *t,
struct user_namespace *ns, int cap)
{
int ret;
rcu_read_lock();
ret = security_capable(__task_cred(t), ns, cap, CAP_OPT_NOAUDIT);
rcu_read_unlock();
return (ret == 0);
}
/**
* has_capability_noaudit - Does a task have a capability (unaudited) in the
* initial user ns
* @t: The task in question
* @cap: The capability to be tested for
*
* Return true if the specified task has the given superior capability
* currently in effect to init_user_ns, false if not. Don't write an
* audit message for the check.
*
* Note that this does not set PF_SUPERPRIV on the task.
*/
bool has_capability_noaudit(struct task_struct *t, int cap)
{
return has_ns_capability_noaudit(t, &init_user_ns, cap);
}
static bool ns_capable_common(struct user_namespace *ns,
int cap,
unsigned int opts)
{
int capable;
if (unlikely(!cap_valid(cap))) {
pr_crit("capable() called with invalid cap=%u\n", cap);
BUG();
}
capable = security_capable(current_cred(), ns, cap, opts);
if (capable == 0) {
current->flags |= PF_SUPERPRIV;
return true;
}
return false;
}
/**
* ns_capable - Determine if the current task has a superior capability in effect
* @ns: The usernamespace we want the capability in
* @cap: The capability to be tested for
*
* Return true if the current task has the given superior capability currently
* available for use, false if not.
*
* This sets PF_SUPERPRIV on the task if the capability is available on the
* assumption that it's about to be used.
*/
bool ns_capable(struct user_namespace *ns, int cap)
{
return ns_capable_common(ns, cap, CAP_OPT_NONE);
}
EXPORT_SYMBOL(ns_capable);
/**
* ns_capable_noaudit - Determine if the current task has a superior capability
* (unaudited) in effect
* @ns: The usernamespace we want the capability in
* @cap: The capability to be tested for
*
* Return true if the current task has the given superior capability currently
* available for use, false if not.
*
* This sets PF_SUPERPRIV on the task if the capability is available on the
* assumption that it's about to be used.
*/
bool ns_capable_noaudit(struct user_namespace *ns, int cap)
{
return ns_capable_common(ns, cap, CAP_OPT_NOAUDIT);
}
EXPORT_SYMBOL(ns_capable_noaudit);
/**
* ns_capable_setid - Determine if the current task has a superior capability
* in effect, while signalling that this check is being done from within a
* setid or setgroups syscall.
* @ns: The usernamespace we want the capability in
* @cap: The capability to be tested for
*
* Return true if the current task has the given superior capability currently
* available for use, false if not.
*
* This sets PF_SUPERPRIV on the task if the capability is available on the
* assumption that it's about to be used.
*/
bool ns_capable_setid(struct user_namespace *ns, int cap)
{
return ns_capable_common(ns, cap, CAP_OPT_INSETID);
}
EXPORT_SYMBOL(ns_capable_setid);
/**
* capable - Determine if the current task has a superior capability in effect
* @cap: The capability to be tested for
*
* Return true if the current task has the given superior capability currently
* available for use, false if not.
*
* This sets PF_SUPERPRIV on the task if the capability is available on the
* assumption that it's about to be used.
*/
bool capable(int cap)
{
return ns_capable(&init_user_ns, cap);
}
EXPORT_SYMBOL(capable);
#endif /* CONFIG_MULTIUSER */
/**
* file_ns_capable - Determine if the file's opener had a capability in effect
* @file: The file we want to check
* @ns: The usernamespace we want the capability in
* @cap: The capability to be tested for
*
* Return true if task that opened the file had a capability in effect
* when the file was opened.
*
* This does not set PF_SUPERPRIV because the caller may not
* actually be privileged.
*/
bool file_ns_capable(const struct file *file, struct user_namespace *ns,
int cap)
{
if (WARN_ON_ONCE(!cap_valid(cap)))
return false;
if (security_capable(file->f_cred, ns, cap, CAP_OPT_NONE) == 0)
return true;
return false;
}
EXPORT_SYMBOL(file_ns_capable);
/**
* privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode?
* @ns: The user namespace in question
* @inode: The inode in question
*
* Return true if the inode uid and gid are within the namespace.
*/
bool privileged_wrt_inode_uidgid(struct user_namespace *ns,
struct user_namespace *mnt_userns,
const struct inode *inode)
{
return kuid_has_mapping(ns, i_uid_into_mnt(mnt_userns, inode)) &&
kgid_has_mapping(ns, i_gid_into_mnt(mnt_userns, inode));
}
/**
* capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped
* @inode: The inode in question
* @cap: The capability in question
*
* Return true if the current task has the given capability targeted at
* its own user namespace and that the given inode's uid and gid are
* mapped into the current user namespace.
*/
bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns,
const struct inode *inode, int cap)
{
struct user_namespace *ns = current_user_ns();
return ns_capable(ns, cap) &&
privileged_wrt_inode_uidgid(ns, mnt_userns, inode);
}
EXPORT_SYMBOL(capable_wrt_inode_uidgid);
/**
* ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace
* @tsk: The task that may be ptraced
* @ns: The user namespace to search for CAP_SYS_PTRACE in
*
* Return true if the task that is ptracing the current task had CAP_SYS_PTRACE
* in the specified user namespace.
*/
bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns)
{
int ret = 0; /* An absent tracer adds no restrictions */
const struct cred *cred;
rcu_read_lock();
cred = rcu_dereference(tsk->ptracer_cred);
if (cred)
ret = security_capable(cred, ns, CAP_SYS_PTRACE,
CAP_OPT_NOAUDIT);
rcu_read_unlock();
return (ret == 0);
}
Computing file changes ...