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
audit.h
/* SPDX-License-Identifier: GPL-2.0-or-later */
/* audit -- definition of audit_context structure and supporting types
 *
 * Copyright 2003-2004 Red Hat, Inc.
 * Copyright 2005 Hewlett-Packard Development Company, L.P.
 * Copyright 2005 IBM Corporation
 */

#ifndef _KERNEL_AUDIT_H_
#define _KERNEL_AUDIT_H_

#include <linux/fs.h>
#include <linux/audit.h>
#include <linux/skbuff.h>
#include <uapi/linux/mqueue.h>
#include <linux/tty.h>
#include <uapi/linux/openat2.h> // struct open_how

/* AUDIT_NAMES is the number of slots we reserve in the audit_context
 * for saving names from getname().  If we get more names we will allocate
 * a name dynamically and also add those to the list anchored by names_list. */
#define AUDIT_NAMES	5

/* At task start time, the audit_state is set in the audit_context using
   a per-task filter.  At syscall entry, the audit_state is augmented by
   the syscall filter. */
enum audit_state {
	AUDIT_STATE_DISABLED,	/* Do not create per-task audit_context.
				 * No syscall-specific audit records can
				 * be generated. */
	AUDIT_STATE_BUILD,	/* Create the per-task audit_context,
				 * and fill it in at syscall
				 * entry time.  This makes a full
				 * syscall record available if some
				 * other part of the kernel decides it
				 * should be recorded. */
	AUDIT_STATE_RECORD	/* Create the per-task audit_context,
				 * always fill it in at syscall entry
				 * time, and always write out the audit
				 * record at syscall exit time.  */
};

/* Rule lists */
struct audit_watch;
struct audit_fsnotify_mark;
struct audit_tree;
struct audit_chunk;

struct audit_entry {
	struct list_head	list;
	struct rcu_head		rcu;
	struct audit_krule	rule;
};

struct audit_cap_data {
	kernel_cap_t		permitted;
	kernel_cap_t		inheritable;
	union {
		unsigned int	fE;		/* effective bit of file cap */
		kernel_cap_t	effective;	/* effective set of process */
	};
	kernel_cap_t		ambient;
	kuid_t			rootid;
};

/* When fs/namei.c:getname() is called, we store the pointer in name and bump
 * the refcnt in the associated filename struct.
 *
 * Further, in fs/namei.c:path_lookup() we store the inode and device.
 */
struct audit_names {
	struct list_head	list;		/* audit_context->names_list */

	struct filename		*name;
	int			name_len;	/* number of chars to log */
	bool			hidden;		/* don't log this record */

	unsigned long		ino;
	dev_t			dev;
	umode_t			mode;
	kuid_t			uid;
	kgid_t			gid;
	dev_t			rdev;
	u32			osid;
	struct audit_cap_data	fcap;
	unsigned int		fcap_ver;
	unsigned char		type;		/* record type */
	/*
	 * This was an allocated audit_names and not from the array of
	 * names allocated in the task audit context.  Thus this name
	 * should be freed on syscall exit.
	 */
	bool			should_free;
};

struct audit_proctitle {
	int	len;	/* length of the cmdline field. */
	char	*value;	/* the cmdline field */
};

/* The per-task audit context. */
struct audit_context {
	int		    dummy;	/* must be the first element */
	enum {
		AUDIT_CTX_UNUSED,	/* audit_context is currently unused */
		AUDIT_CTX_SYSCALL,	/* in use by syscall */
		AUDIT_CTX_URING,	/* in use by io_uring */
	} context;
	enum audit_state    state, current_state;
	unsigned int	    serial;     /* serial number for record */
	int		    major;      /* syscall number */
	int		    uring_op;   /* uring operation */
	struct timespec64   ctime;      /* time of syscall entry */
	unsigned long	    argv[4];    /* syscall arguments */
	long		    return_code;/* syscall return code */
	u64		    prio;
	int		    return_valid; /* return code is valid */
	/*
	 * The names_list is the list of all audit_names collected during this
	 * syscall.  The first AUDIT_NAMES entries in the names_list will
	 * actually be from the preallocated_names array for performance
	 * reasons.  Except during allocation they should never be referenced
	 * through the preallocated_names array and should only be found/used
	 * by running the names_list.
	 */
	struct audit_names  preallocated_names[AUDIT_NAMES];
	int		    name_count; /* total records in names_list */
	struct list_head    names_list;	/* struct audit_names->list anchor */
	char		    *filterkey;	/* key for rule that triggered record */
	struct path	    pwd;
	struct audit_aux_data *aux;
	struct audit_aux_data *aux_pids;
	struct sockaddr_storage *sockaddr;
	size_t sockaddr_len;
				/* Save things to print about task_struct */
	pid_t		    pid, ppid;
	kuid_t		    uid, euid, suid, fsuid;
	kgid_t		    gid, egid, sgid, fsgid;
	unsigned long	    personality;
	int		    arch;

	pid_t		    target_pid;
	kuid_t		    target_auid;
	kuid_t		    target_uid;
	unsigned int	    target_sessionid;
	u32		    target_sid;
	char		    target_comm[TASK_COMM_LEN];

	struct audit_tree_refs *trees, *first_trees;
	struct list_head killed_trees;
	int tree_count;

	int type;
	union {
		struct {
			int nargs;
			long args[6];
		} socketcall;
		struct {
			kuid_t			uid;
			kgid_t			gid;
			umode_t			mode;
			u32			osid;
			int			has_perm;
			uid_t			perm_uid;
			gid_t			perm_gid;
			umode_t			perm_mode;
			unsigned long		qbytes;
		} ipc;
		struct {
			mqd_t			mqdes;
			struct mq_attr		mqstat;
		} mq_getsetattr;
		struct {
			mqd_t			mqdes;
			int			sigev_signo;
		} mq_notify;
		struct {
			mqd_t			mqdes;
			size_t			msg_len;
			unsigned int		msg_prio;
			struct timespec64	abs_timeout;
		} mq_sendrecv;
		struct {
			int			oflag;
			umode_t			mode;
			struct mq_attr		attr;
		} mq_open;
		struct {
			pid_t			pid;
			struct audit_cap_data	cap;
		} capset;
		struct {
			int			fd;
			int			flags;
		} mmap;
		struct open_how openat2;
		struct {
			int			argc;
		} execve;
		struct {
			char			*name;
		} module;
	};
	int fds[2];
	struct audit_proctitle proctitle;
};

extern bool audit_ever_enabled;

extern void audit_log_session_info(struct audit_buffer *ab);

extern int auditd_test_task(struct task_struct *task);

#define AUDIT_INODE_BUCKETS	32
extern struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS];

static inline int audit_hash_ino(u32 ino)
{
	return (ino & (AUDIT_INODE_BUCKETS-1));
}

/* Indicates that audit should log the full pathname. */
#define AUDIT_NAME_FULL -1

extern int audit_match_class(int class, unsigned syscall);
extern int audit_comparator(const u32 left, const u32 op, const u32 right);
extern int audit_uid_comparator(kuid_t left, u32 op, kuid_t right);
extern int audit_gid_comparator(kgid_t left, u32 op, kgid_t right);
extern int parent_len(const char *path);
extern int audit_compare_dname_path(const struct qstr *dname, const char *path, int plen);
extern struct sk_buff *audit_make_reply(int seq, int type, int done, int multi,
					const void *payload, int size);
extern void		    audit_panic(const char *message);

struct audit_netlink_list {
	__u32 portid;
	struct net *net;
	struct sk_buff_head q;
};

int audit_send_list_thread(void *_dest);

extern int selinux_audit_rule_update(void);

extern struct mutex audit_filter_mutex;
extern int audit_del_rule(struct audit_entry *entry);
extern void audit_free_rule_rcu(struct rcu_head *head);
extern struct list_head audit_filter_list[];

extern struct audit_entry *audit_dupe_rule(struct audit_krule *old);

extern void audit_log_d_path_exe(struct audit_buffer *ab,
				 struct mm_struct *mm);

extern struct tty_struct *audit_get_tty(void);
extern void audit_put_tty(struct tty_struct *tty);

/* audit watch/mark/tree functions */
#ifdef CONFIG_AUDITSYSCALL
extern unsigned int audit_serial(void);
extern int auditsc_get_stamp(struct audit_context *ctx,
			      struct timespec64 *t, unsigned int *serial);

extern void audit_put_watch(struct audit_watch *watch);
extern void audit_get_watch(struct audit_watch *watch);
extern int audit_to_watch(struct audit_krule *krule, char *path, int len,
			  u32 op);
extern int audit_add_watch(struct audit_krule *krule, struct list_head **list);
extern void audit_remove_watch_rule(struct audit_krule *krule);
extern char *audit_watch_path(struct audit_watch *watch);
extern int audit_watch_compare(struct audit_watch *watch, unsigned long ino,
			       dev_t dev);

extern struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule,
						    char *pathname, int len);
extern char *audit_mark_path(struct audit_fsnotify_mark *mark);
extern void audit_remove_mark(struct audit_fsnotify_mark *audit_mark);
extern void audit_remove_mark_rule(struct audit_krule *krule);
extern int audit_mark_compare(struct audit_fsnotify_mark *mark,
			      unsigned long ino, dev_t dev);
extern int audit_dupe_exe(struct audit_krule *new, struct audit_krule *old);
extern int audit_exe_compare(struct task_struct *tsk,
			     struct audit_fsnotify_mark *mark);

extern struct audit_chunk *audit_tree_lookup(const struct inode *inode);
extern void audit_put_chunk(struct audit_chunk *chunk);
extern bool audit_tree_match(struct audit_chunk *chunk,
			     struct audit_tree *tree);
extern int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op);
extern int audit_add_tree_rule(struct audit_krule *rule);
extern int audit_remove_tree_rule(struct audit_krule *rule);
extern void audit_trim_trees(void);
extern int audit_tag_tree(char *old, char *new);
extern const char *audit_tree_path(struct audit_tree *tree);
extern void audit_put_tree(struct audit_tree *tree);
extern void audit_kill_trees(struct audit_context *context);

extern int audit_signal_info_syscall(struct task_struct *t);
extern void audit_filter_inodes(struct task_struct *tsk,
				struct audit_context *ctx);
extern struct list_head *audit_killed_trees(void);
#else /* CONFIG_AUDITSYSCALL */
#define auditsc_get_stamp(c, t, s) 0
#define audit_put_watch(w) do { } while (0)
#define audit_get_watch(w) do { } while (0)
#define audit_to_watch(k, p, l, o) (-EINVAL)
#define audit_add_watch(k, l) (-EINVAL)
#define audit_remove_watch_rule(k) BUG()
#define audit_watch_path(w) ""
#define audit_watch_compare(w, i, d) 0

#define audit_alloc_mark(k, p, l) (ERR_PTR(-EINVAL))
#define audit_mark_path(m) ""
#define audit_remove_mark(m) do { } while (0)
#define audit_remove_mark_rule(k) do { } while (0)
#define audit_mark_compare(m, i, d) 0
#define audit_exe_compare(t, m) (-EINVAL)
#define audit_dupe_exe(n, o) (-EINVAL)

#define audit_remove_tree_rule(rule) BUG()
#define audit_add_tree_rule(rule) -EINVAL
#define audit_make_tree(rule, str, op) -EINVAL
#define audit_trim_trees() do { } while (0)
#define audit_put_tree(tree) do { } while (0)
#define audit_tag_tree(old, new) -EINVAL
#define audit_tree_path(rule) ""	/* never called */
#define audit_kill_trees(context) BUG()

static inline int audit_signal_info_syscall(struct task_struct *t)
{
	return 0;
}

#define audit_filter_inodes(t, c) AUDIT_STATE_DISABLED
#endif /* CONFIG_AUDITSYSCALL */

extern char *audit_unpack_string(void **bufp, size_t *remain, size_t len);

extern int audit_filter(int msgtype, unsigned int listtype);

extern void audit_ctl_lock(void);
extern void audit_ctl_unlock(void);

#endif
back to top