OpenCloudOS-Kernel/drivers/char/ipmi/ipmi_si_intf.c

2319 lines
59 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0+
/*
* ipmi_si.c
*
* The interface to the IPMI driver for the system interfaces (KCS, SMIC,
* BT).
*
* Author: MontaVista Software, Inc.
* Corey Minyard <minyard@mvista.com>
* source@mvista.com
*
* Copyright 2002 MontaVista Software Inc.
* Copyright 2006 IBM Corp., Christian Krafft <krafft@de.ibm.com>
*/
/*
* This file holds the "policy" for the interface to the SMI state
* machine. It does the configuration, handles timers and interrupts,
* and drives the real SMI state machine.
*/
#define pr_fmt(fmt) "ipmi_si: " fmt
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/timer.h>
#include <linux/errno.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/list.h>
#include <linux/notifier.h>
#include <linux/mutex.h>
#include <linux/kthread.h>
#include <asm/irq.h>
#include <linux/interrupt.h>
#include <linux/rcupdate.h>
#include <linux/ipmi.h>
#include <linux/ipmi_smi.h>
#include "ipmi_si.h"
#include "ipmi_si_sm.h"
#include <linux/string.h>
#include <linux/ctype.h>
/* Measure times between events in the driver. */
#undef DEBUG_TIMING
/* Call every 10 ms. */
#define SI_TIMEOUT_TIME_USEC 10000
#define SI_USEC_PER_JIFFY (1000000/HZ)
#define SI_TIMEOUT_JIFFIES (SI_TIMEOUT_TIME_USEC/SI_USEC_PER_JIFFY)
#define SI_SHORT_TIMEOUT_USEC 250 /* .25ms when the SM request a
short timeout */
enum si_intf_state {
SI_NORMAL,
SI_GETTING_FLAGS,
SI_GETTING_EVENTS,
SI_CLEARING_FLAGS,
SI_GETTING_MESSAGES,
SI_CHECKING_ENABLES,
SI_SETTING_ENABLES
/* FIXME - add watchdog stuff. */
};
/* Some BT-specific defines we need here. */
#define IPMI_BT_INTMASK_REG 2
#define IPMI_BT_INTMASK_CLEAR_IRQ_BIT 2
#define IPMI_BT_INTMASK_ENABLE_IRQ_BIT 1
static const char * const si_to_str[] = { "invalid", "kcs", "smic", "bt" };
static bool initialized;
/*
* Indexes into stats[] in smi_info below.
*/
enum si_stat_indexes {
/*
* Number of times the driver requested a timer while an operation
* was in progress.
*/
SI_STAT_short_timeouts = 0,
/*
* Number of times the driver requested a timer while nothing was in
* progress.
*/
SI_STAT_long_timeouts,
/* Number of times the interface was idle while being polled. */
SI_STAT_idles,
/* Number of interrupts the driver handled. */
SI_STAT_interrupts,
/* Number of time the driver got an ATTN from the hardware. */
SI_STAT_attentions,
/* Number of times the driver requested flags from the hardware. */
SI_STAT_flag_fetches,
/* Number of times the hardware didn't follow the state machine. */
SI_STAT_hosed_count,
/* Number of completed messages. */
SI_STAT_complete_transactions,
/* Number of IPMI events received from the hardware. */
SI_STAT_events,
/* Number of watchdog pretimeouts. */
SI_STAT_watchdog_pretimeouts,
/* Number of asynchronous messages received. */
SI_STAT_incoming_messages,
/* This *must* remain last, add new values above this. */
SI_NUM_STATS
};
struct smi_info {
int si_num;
struct ipmi_smi *intf;
struct si_sm_data *si_sm;
const struct si_sm_handlers *handlers;
spinlock_t si_lock;
struct ipmi_smi_msg *waiting_msg;
struct ipmi_smi_msg *curr_msg;
enum si_intf_state si_state;
/*
* Used to handle the various types of I/O that can occur with
* IPMI
*/
struct si_sm_io io;
/*
* Per-OEM handler, called from handle_flags(). Returns 1
* when handle_flags() needs to be re-run or 0 indicating it
* set si_state itself.
*/
int (*oem_data_avail_handler)(struct smi_info *smi_info);
/*
* Flags from the last GET_MSG_FLAGS command, used when an ATTN
* is set to hold the flags until we are done handling everything
* from the flags.
*/
#define RECEIVE_MSG_AVAIL 0x01
#define EVENT_MSG_BUFFER_FULL 0x02
#define WDT_PRE_TIMEOUT_INT 0x08
#define OEM0_DATA_AVAIL 0x20
#define OEM1_DATA_AVAIL 0x40
#define OEM2_DATA_AVAIL 0x80
#define OEM_DATA_AVAIL (OEM0_DATA_AVAIL | \
OEM1_DATA_AVAIL | \
OEM2_DATA_AVAIL)
unsigned char msg_flags;
/* Does the BMC have an event buffer? */
bool has_event_buffer;
/*
* If set to true, this will request events the next time the
* state machine is idle.
*/
atomic_t req_events;
/*
* If true, run the state machine to completion on every send
* call. Generally used after a panic to make sure stuff goes
* out.
*/
bool run_to_completion;
/* The timer for this si. */
struct timer_list si_timer;
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
/* This flag is set, if the timer can be set */
bool timer_can_start;
/* This flag is set, if the timer is running (timer_pending() isn't enough) */
bool timer_running;
/* The time (in jiffies) the last timeout occurred at. */
unsigned long last_timeout_jiffies;
/* Are we waiting for the events, pretimeouts, received msgs? */
atomic_t need_watch;
/*
* The driver will disable interrupts when it gets into a
* situation where it cannot handle messages due to lack of
* memory. Once that situation clears up, it will re-enable
* interrupts.
*/
bool interrupt_disabled;
/*
* Does the BMC support events?
*/
bool supports_event_msg_buff;
/*
* Can we disable interrupts the global enables receive irq
* bit? There are currently two forms of brokenness, some
* systems cannot disable the bit (which is technically within
* the spec but a bad idea) and some systems have the bit
* forced to zero even though interrupts work (which is
* clearly outside the spec). The next bool tells which form
* of brokenness is present.
*/
bool cannot_disable_irq;
/*
* Some systems are broken and cannot set the irq enable
* bit, even if they support interrupts.
*/
bool irq_enable_broken;
/* Is the driver in maintenance mode? */
bool in_maintenance_mode;
/*
* Did we get an attention that we did not handle?
*/
bool got_attn;
/* From the get device id response... */
struct ipmi_device_id device_id;
/* Have we added the device group to the device? */
bool dev_group_added;
/* Counters and things for the proc filesystem. */
atomic_t stats[SI_NUM_STATS];
struct task_struct *thread;
struct list_head link;
};
#define smi_inc_stat(smi, stat) \
atomic_inc(&(smi)->stats[SI_STAT_ ## stat])
#define smi_get_stat(smi, stat) \
((unsigned int) atomic_read(&(smi)->stats[SI_STAT_ ## stat]))
#define IPMI_MAX_INTFS 4
static int force_kipmid[IPMI_MAX_INTFS];
static int num_force_kipmid;
static unsigned int kipmid_max_busy_us[IPMI_MAX_INTFS] = { 1, 1, 1, 1 };
static int num_max_busy_us;
static bool unload_when_empty = true;
static int try_smi_init(struct smi_info *smi);
static void cleanup_one_si(struct smi_info *smi_info);
static void cleanup_ipmi_si(void);
#ifdef DEBUG_TIMING
void debug_timestamp(char *msg)
{
struct timespec t;
ktime_get_ts(&t);
pr_debug("**%s: %ld.%9.9ld\n", msg, (long) t.tv_sec, t.tv_nsec);
}
#else
#define debug_timestamp(x)
#endif
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 17:16:30 +08:00
static ATOMIC_NOTIFIER_HEAD(xaction_notifier_list);
static int register_xaction_notifier(struct notifier_block *nb)
{
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 17:16:30 +08:00
return atomic_notifier_chain_register(&xaction_notifier_list, nb);
}
static void deliver_recv_msg(struct smi_info *smi_info,
struct ipmi_smi_msg *msg)
{
/* Deliver the message to the upper layer. */
ipmi_smi_msg_received(smi_info->intf, msg);
}
static void return_hosed_msg(struct smi_info *smi_info, int cCode)
{
struct ipmi_smi_msg *msg = smi_info->curr_msg;
if (cCode < 0 || cCode > IPMI_ERR_UNSPECIFIED)
cCode = IPMI_ERR_UNSPECIFIED;
/* else use it as is */
/* Make it a response */
msg->rsp[0] = msg->data[0] | 4;
msg->rsp[1] = msg->data[1];
msg->rsp[2] = cCode;
msg->rsp_size = 3;
smi_info->curr_msg = NULL;
deliver_recv_msg(smi_info, msg);
}
static enum si_sm_result start_next_msg(struct smi_info *smi_info)
{
int rv;
if (!smi_info->waiting_msg) {
smi_info->curr_msg = NULL;
rv = SI_SM_IDLE;
} else {
int err;
smi_info->curr_msg = smi_info->waiting_msg;
smi_info->waiting_msg = NULL;
debug_timestamp("Start2");
[PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com> Signed-off-by: Jes Sorensen <jes@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-27 17:16:30 +08:00
err = atomic_notifier_call_chain(&xaction_notifier_list,
0, smi_info);
if (err & NOTIFY_STOP_MASK) {
rv = SI_SM_CALL_WITHOUT_DELAY;
goto out;
}
err = smi_info->handlers->start_transaction(
smi_info->si_sm,
smi_info->curr_msg->data,
smi_info->curr_msg->data_size);
if (err)
return_hosed_msg(smi_info, err);
rv = SI_SM_CALL_WITHOUT_DELAY;
}
out:
return rv;
}
static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
{
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
if (!smi_info->timer_can_start)
return;
smi_info->last_timeout_jiffies = jiffies;
mod_timer(&smi_info->si_timer, new_val);
smi_info->timer_running = true;
}
/*
* Start a new message and (re)start the timer and thread.
*/
static void start_new_msg(struct smi_info *smi_info, unsigned char *msg,
unsigned int size)
{
smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
if (smi_info->thread)
wake_up_process(smi_info->thread);
smi_info->handlers->start_transaction(smi_info->si_sm, msg, size);
}
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
static void start_check_enables(struct smi_info *smi_info)
{
unsigned char msg[2];
msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD;
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
start_new_msg(smi_info, msg, 2);
smi_info->si_state = SI_CHECKING_ENABLES;
}
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
static void start_clear_flags(struct smi_info *smi_info)
{
unsigned char msg[3];
/* Make sure the watchdog pre-timeout flag is not set at startup. */
msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
msg[1] = IPMI_CLEAR_MSG_FLAGS_CMD;
msg[2] = WDT_PRE_TIMEOUT_INT;
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
start_new_msg(smi_info, msg, 3);
smi_info->si_state = SI_CLEARING_FLAGS;
}
static void start_getting_msg_queue(struct smi_info *smi_info)
{
smi_info->curr_msg->data[0] = (IPMI_NETFN_APP_REQUEST << 2);
smi_info->curr_msg->data[1] = IPMI_GET_MSG_CMD;
smi_info->curr_msg->data_size = 2;
start_new_msg(smi_info, smi_info->curr_msg->data,
smi_info->curr_msg->data_size);
smi_info->si_state = SI_GETTING_MESSAGES;
}
static void start_getting_events(struct smi_info *smi_info)
{
smi_info->curr_msg->data[0] = (IPMI_NETFN_APP_REQUEST << 2);
smi_info->curr_msg->data[1] = IPMI_READ_EVENT_MSG_BUFFER_CMD;
smi_info->curr_msg->data_size = 2;
start_new_msg(smi_info, smi_info->curr_msg->data,
smi_info->curr_msg->data_size);
smi_info->si_state = SI_GETTING_EVENTS;
}
/*
* When we have a situtaion where we run out of memory and cannot
* allocate messages, we just leave them in the BMC and run the system
* polled until we can allocate some memory. Once we have some
* memory, we will re-enable the interrupt.
*
* Note that we cannot just use disable_irq(), since the interrupt may
* be shared.
*/
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
static inline bool disable_si_irq(struct smi_info *smi_info)
{
if ((smi_info->io.irq) && (!smi_info->interrupt_disabled)) {
smi_info->interrupt_disabled = true;
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
start_check_enables(smi_info);
return true;
}
return false;
}
static inline bool enable_si_irq(struct smi_info *smi_info)
{
if ((smi_info->io.irq) && (smi_info->interrupt_disabled)) {
smi_info->interrupt_disabled = false;
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
start_check_enables(smi_info);
return true;
}
return false;
}
/*
* Allocate a message. If unable to allocate, start the interrupt
* disable process and return NULL. If able to allocate but
* interrupts are disabled, free the message and return NULL after
* starting the interrupt enable process.
*/
static struct ipmi_smi_msg *alloc_msg_handle_irq(struct smi_info *smi_info)
{
struct ipmi_smi_msg *msg;
msg = ipmi_alloc_smi_msg();
if (!msg) {
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
if (!disable_si_irq(smi_info))
smi_info->si_state = SI_NORMAL;
} else if (enable_si_irq(smi_info)) {
ipmi_free_smi_msg(msg);
msg = NULL;
}
return msg;
}
static void handle_flags(struct smi_info *smi_info)
{
retry:
if (smi_info->msg_flags & WDT_PRE_TIMEOUT_INT) {
/* Watchdog pre-timeout */
smi_inc_stat(smi_info, watchdog_pretimeouts);
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
start_clear_flags(smi_info);
smi_info->msg_flags &= ~WDT_PRE_TIMEOUT_INT;
ipmi_smi_watchdog_pretimeout(smi_info->intf);
} else if (smi_info->msg_flags & RECEIVE_MSG_AVAIL) {
/* Messages available. */
smi_info->curr_msg = alloc_msg_handle_irq(smi_info);
if (!smi_info->curr_msg)
return;
start_getting_msg_queue(smi_info);
} else if (smi_info->msg_flags & EVENT_MSG_BUFFER_FULL) {
/* Events available. */
smi_info->curr_msg = alloc_msg_handle_irq(smi_info);
if (!smi_info->curr_msg)
return;
start_getting_events(smi_info);
} else if (smi_info->msg_flags & OEM_DATA_AVAIL &&
smi_info->oem_data_avail_handler) {
if (smi_info->oem_data_avail_handler(smi_info))
goto retry;
} else
smi_info->si_state = SI_NORMAL;
}
/*
* Global enables we care about.
*/
#define GLOBAL_ENABLES_MASK (IPMI_BMC_EVT_MSG_BUFF | IPMI_BMC_RCV_MSG_INTR | \
IPMI_BMC_EVT_MSG_INTR)
static u8 current_global_enables(struct smi_info *smi_info, u8 base,
bool *irq_on)
{
u8 enables = 0;
if (smi_info->supports_event_msg_buff)
enables |= IPMI_BMC_EVT_MSG_BUFF;
if (((smi_info->io.irq && !smi_info->interrupt_disabled) ||
smi_info->cannot_disable_irq) &&
!smi_info->irq_enable_broken)
enables |= IPMI_BMC_RCV_MSG_INTR;
if (smi_info->supports_event_msg_buff &&
smi_info->io.irq && !smi_info->interrupt_disabled &&
!smi_info->irq_enable_broken)
enables |= IPMI_BMC_EVT_MSG_INTR;
*irq_on = enables & (IPMI_BMC_EVT_MSG_INTR | IPMI_BMC_RCV_MSG_INTR);
return enables;
}
static void check_bt_irq(struct smi_info *smi_info, bool irq_on)
{
u8 irqstate = smi_info->io.inputb(&smi_info->io, IPMI_BT_INTMASK_REG);
irqstate &= IPMI_BT_INTMASK_ENABLE_IRQ_BIT;
if ((bool)irqstate == irq_on)
return;
if (irq_on)
smi_info->io.outputb(&smi_info->io, IPMI_BT_INTMASK_REG,
IPMI_BT_INTMASK_ENABLE_IRQ_BIT);
else
smi_info->io.outputb(&smi_info->io, IPMI_BT_INTMASK_REG, 0);
}
static void handle_transaction_done(struct smi_info *smi_info)
{
struct ipmi_smi_msg *msg;
debug_timestamp("Done");
switch (smi_info->si_state) {
case SI_NORMAL:
if (!smi_info->curr_msg)
break;
smi_info->curr_msg->rsp_size
= smi_info->handlers->get_result(
smi_info->si_sm,
smi_info->curr_msg->rsp,
IPMI_MAX_MSG_LENGTH);
/*
* Do this here becase deliver_recv_msg() releases the
* lock, and a new message can be put in during the
* time the lock is released.
*/
msg = smi_info->curr_msg;
smi_info->curr_msg = NULL;
deliver_recv_msg(smi_info, msg);
break;
case SI_GETTING_FLAGS:
{
unsigned char msg[4];
unsigned int len;
/* We got the flags from the SMI, now handle them. */
len = smi_info->handlers->get_result(smi_info->si_sm, msg, 4);
if (msg[2] != 0) {
/* Error fetching flags, just give up for now. */
smi_info->si_state = SI_NORMAL;
} else if (len < 4) {
/*
* Hmm, no flags. That's technically illegal, but
* don't use uninitialized data.
*/
smi_info->si_state = SI_NORMAL;
} else {
smi_info->msg_flags = msg[3];
handle_flags(smi_info);
}
break;
}
case SI_CLEARING_FLAGS:
{
unsigned char msg[3];
/* We cleared the flags. */
smi_info->handlers->get_result(smi_info->si_sm, msg, 3);
if (msg[2] != 0) {
/* Error clearing flags */
dev_warn(smi_info->io.dev,
"Error clearing flags: %2.2x\n", msg[2]);
}
smi_info->si_state = SI_NORMAL;
break;
}
case SI_GETTING_EVENTS:
{
smi_info->curr_msg->rsp_size
= smi_info->handlers->get_result(
smi_info->si_sm,
smi_info->curr_msg->rsp,
IPMI_MAX_MSG_LENGTH);
/*
* Do this here becase deliver_recv_msg() releases the
* lock, and a new message can be put in during the
* time the lock is released.
*/
msg = smi_info->curr_msg;
smi_info->curr_msg = NULL;
if (msg->rsp[2] != 0) {
/* Error getting event, probably done. */
msg->done(msg);
/* Take off the event flag. */
smi_info->msg_flags &= ~EVENT_MSG_BUFFER_FULL;
handle_flags(smi_info);
} else {
smi_inc_stat(smi_info, events);
/*
* Do this before we deliver the message
* because delivering the message releases the
* lock and something else can mess with the
* state.
*/
handle_flags(smi_info);
deliver_recv_msg(smi_info, msg);
}
break;
}
case SI_GETTING_MESSAGES:
{
smi_info->curr_msg->rsp_size
= smi_info->handlers->get_result(
smi_info->si_sm,
smi_info->curr_msg->rsp,
IPMI_MAX_MSG_LENGTH);
/*
* Do this here becase deliver_recv_msg() releases the
* lock, and a new message can be put in during the
* time the lock is released.
*/
msg = smi_info->curr_msg;
smi_info->curr_msg = NULL;
if (msg->rsp[2] != 0) {
/* Error getting event, probably done. */
msg->done(msg);
/* Take off the msg flag. */
smi_info->msg_flags &= ~RECEIVE_MSG_AVAIL;
handle_flags(smi_info);
} else {
smi_inc_stat(smi_info, incoming_messages);
/*
* Do this before we deliver the message
* because delivering the message releases the
* lock and something else can mess with the
* state.
*/
handle_flags(smi_info);
deliver_recv_msg(smi_info, msg);
}
break;
}
case SI_CHECKING_ENABLES:
{
unsigned char msg[4];
u8 enables;
bool irq_on;
/* We got the flags from the SMI, now handle them. */
smi_info->handlers->get_result(smi_info->si_sm, msg, 4);
if (msg[2] != 0) {
dev_warn(smi_info->io.dev,
"Couldn't get irq info: %x.\n", msg[2]);
dev_warn(smi_info->io.dev,
"Maybe ok, but ipmi might run very slowly.\n");
smi_info->si_state = SI_NORMAL;
break;
}
enables = current_global_enables(smi_info, 0, &irq_on);
if (smi_info->io.si_type == SI_BT)
/* BT has its own interrupt enable bit. */
check_bt_irq(smi_info, irq_on);
if (enables != (msg[3] & GLOBAL_ENABLES_MASK)) {
/* Enables are not correct, fix them. */
msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
msg[1] = IPMI_SET_BMC_GLOBAL_ENABLES_CMD;
msg[2] = enables | (msg[3] & ~GLOBAL_ENABLES_MASK);
smi_info->handlers->start_transaction(
smi_info->si_sm, msg, 3);
smi_info->si_state = SI_SETTING_ENABLES;
} else if (smi_info->supports_event_msg_buff) {
smi_info->curr_msg = ipmi_alloc_smi_msg();
if (!smi_info->curr_msg) {
smi_info->si_state = SI_NORMAL;
break;
}
start_getting_events(smi_info);
} else {
smi_info->si_state = SI_NORMAL;
}
break;
}
case SI_SETTING_ENABLES:
{
unsigned char msg[4];
smi_info->handlers->get_result(smi_info->si_sm, msg, 4);
if (msg[2] != 0)
dev_warn(smi_info->io.dev,
"Could not set the global enables: 0x%x.\n",
msg[2]);
if (smi_info->supports_event_msg_buff) {
smi_info->curr_msg = ipmi_alloc_smi_msg();
if (!smi_info->curr_msg) {
smi_info->si_state = SI_NORMAL;
break;
}
start_getting_events(smi_info);
} else {
smi_info->si_state = SI_NORMAL;
}
break;
}
}
}
/*
* Called on timeouts and events. Timeouts should pass the elapsed
* time, interrupts should pass in zero. Must be called with
* si_lock held and interrupts disabled.
*/
static enum si_sm_result smi_event_handler(struct smi_info *smi_info,
int time)
{
enum si_sm_result si_sm_result;
restart:
/*
* There used to be a loop here that waited a little while
* (around 25us) before giving up. That turned out to be
* pointless, the minimum delays I was seeing were in the 300us
* range, which is far too long to wait in an interrupt. So
* we just run until the state machine tells us something
* happened or it needs a delay.
*/
si_sm_result = smi_info->handlers->event(smi_info->si_sm, time);
time = 0;
while (si_sm_result == SI_SM_CALL_WITHOUT_DELAY)
si_sm_result = smi_info->handlers->event(smi_info->si_sm, 0);
if (si_sm_result == SI_SM_TRANSACTION_COMPLETE) {
smi_inc_stat(smi_info, complete_transactions);
handle_transaction_done(smi_info);
goto restart;
} else if (si_sm_result == SI_SM_HOSED) {
smi_inc_stat(smi_info, hosed_count);
/*
* Do the before return_hosed_msg, because that
* releases the lock.
*/
smi_info->si_state = SI_NORMAL;
if (smi_info->curr_msg != NULL) {
/*
* If we were handling a user message, format
* a response to send to the upper layer to
* tell it about the error.
*/
return_hosed_msg(smi_info, IPMI_ERR_UNSPECIFIED);
}
goto restart;
}
/*
* We prefer handling attn over new messages. But don't do
* this if there is not yet an upper layer to handle anything.
*/
if (si_sm_result == SI_SM_ATTN || smi_info->got_attn) {
unsigned char msg[2];
if (smi_info->si_state != SI_NORMAL) {
/*
* We got an ATTN, but we are doing something else.
* Handle the ATTN later.
*/
smi_info->got_attn = true;
} else {
smi_info->got_attn = false;
smi_inc_stat(smi_info, attentions);
/*
* Got a attn, send down a get message flags to see
* what's causing it. It would be better to handle
* this in the upper layer, but due to the way
* interrupts work with the SMI, that's not really
* possible.
*/
msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
msg[1] = IPMI_GET_MSG_FLAGS_CMD;
start_new_msg(smi_info, msg, 2);
smi_info->si_state = SI_GETTING_FLAGS;
goto restart;
}
}
/* If we are currently idle, try to start the next message. */
if (si_sm_result == SI_SM_IDLE) {
smi_inc_stat(smi_info, idles);
si_sm_result = start_next_msg(smi_info);
if (si_sm_result != SI_SM_IDLE)
goto restart;
}
if ((si_sm_result == SI_SM_IDLE)
&& (atomic_read(&smi_info->req_events))) {
/*
* We are idle and the upper layer requested that I fetch
* events, so do so.
*/
atomic_set(&smi_info->req_events, 0);
/*
* Take this opportunity to check the interrupt and
* message enable state for the BMC. The BMC can be
* asynchronously reset, and may thus get interrupts
* disable and messages disabled.
*/
if (smi_info->supports_event_msg_buff || smi_info->io.irq) {
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
start_check_enables(smi_info);
} else {
smi_info->curr_msg = alloc_msg_handle_irq(smi_info);
if (!smi_info->curr_msg)
goto out;
start_getting_events(smi_info);
}
goto restart;
}
if (si_sm_result == SI_SM_IDLE && smi_info->timer_running) {
/* Ok it if fails, the timer will just go off. */
if (del_timer(&smi_info->si_timer))
smi_info->timer_running = false;
}
out:
return si_sm_result;
}
static void check_start_timer_thread(struct smi_info *smi_info)
{
if (smi_info->si_state == SI_NORMAL && smi_info->curr_msg == NULL) {
smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
if (smi_info->thread)
wake_up_process(smi_info->thread);
start_next_msg(smi_info);
smi_event_handler(smi_info, 0);
}
}
static void flush_messages(void *send_info)
{
struct smi_info *smi_info = send_info;
enum si_sm_result result;
/*
* Currently, this function is called only in run-to-completion
* mode. This means we are single-threaded, no need for locks.
*/
result = smi_event_handler(smi_info, 0);
while (result != SI_SM_IDLE) {
udelay(SI_SHORT_TIMEOUT_USEC);
result = smi_event_handler(smi_info, SI_SHORT_TIMEOUT_USEC);
}
}
static void sender(void *send_info,
struct ipmi_smi_msg *msg)
{
struct smi_info *smi_info = send_info;
unsigned long flags;
debug_timestamp("Enqueue");
if (smi_info->run_to_completion) {
/*
* If we are running to completion, start it. Upper
* layer will call flush_messages to clear it out.
*/
smi_info->waiting_msg = msg;
return;
}
spin_lock_irqsave(&smi_info->si_lock, flags);
/*
* The following two lines don't need to be under the lock for
* the lock's sake, but they do need SMP memory barriers to
* avoid getting things out of order. We are already claiming
* the lock, anyway, so just do it under the lock to avoid the
* ordering problem.
*/
BUG_ON(smi_info->waiting_msg);
smi_info->waiting_msg = msg;
check_start_timer_thread(smi_info);
spin_unlock_irqrestore(&smi_info->si_lock, flags);
}
static void set_run_to_completion(void *send_info, bool i_run_to_completion)
{
struct smi_info *smi_info = send_info;
smi_info->run_to_completion = i_run_to_completion;
if (i_run_to_completion)
flush_messages(smi_info);
}
/*
* Use -1 in the nsec value of the busy waiting timespec to tell that
* we are spinning in kipmid looking for something and not delaying
* between checks
*/
static inline void ipmi_si_set_not_busy(struct timespec *ts)
{
ts->tv_nsec = -1;
}
static inline int ipmi_si_is_busy(struct timespec *ts)
{
return ts->tv_nsec != -1;
}
static inline bool ipmi_thread_busy_wait(enum si_sm_result smi_result,
const struct smi_info *smi_info,
struct timespec *busy_until)
{
unsigned int max_busy_us = 0;
if (smi_info->si_num < num_max_busy_us)
max_busy_us = kipmid_max_busy_us[smi_info->si_num];
if (max_busy_us == 0 || smi_result != SI_SM_CALL_WITH_DELAY)
ipmi_si_set_not_busy(busy_until);
else if (!ipmi_si_is_busy(busy_until)) {
ktime_get_ts(busy_until);
timespec_add_ns(busy_until, max_busy_us * NSEC_PER_USEC);
} else {
struct timespec now;
ktime_get_ts(&now);
if (unlikely(timespec_compare(&now, busy_until) > 0)) {
ipmi_si_set_not_busy(busy_until);
return false;
}
}
return true;
}
/*
* A busy-waiting loop for speeding up IPMI operation.
*
* Lousy hardware makes this hard. This is only enabled for systems
* that are not BT and do not have interrupts. It starts spinning
* when an operation is complete or until max_busy tells it to stop
* (if that is enabled). See the paragraph on kimid_max_busy_us in
* Documentation/IPMI.txt for details.
*/
static int ipmi_thread(void *data)
{
struct smi_info *smi_info = data;
unsigned long flags;
enum si_sm_result smi_result;
struct timespec busy_until = { 0, 0 };
ipmi_si_set_not_busy(&busy_until);
set_user_nice(current, MAX_NICE);
while (!kthread_should_stop()) {
int busy_wait;
spin_lock_irqsave(&(smi_info->si_lock), flags);
smi_result = smi_event_handler(smi_info, 0);
/*
* If the driver is doing something, there is a possible
* race with the timer. If the timer handler see idle,
* and the thread here sees something else, the timer
* handler won't restart the timer even though it is
* required. So start it here if necessary.
*/
if (smi_result != SI_SM_IDLE && !smi_info->timer_running)
smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
spin_unlock_irqrestore(&(smi_info->si_lock), flags);
busy_wait = ipmi_thread_busy_wait(smi_result, smi_info,
&busy_until);
if (smi_result == SI_SM_CALL_WITHOUT_DELAY) {
; /* do nothing */
} else if (smi_result == SI_SM_CALL_WITH_DELAY && busy_wait) {
/*
* In maintenance mode we run as fast as
* possible to allow firmware updates to
* complete as fast as possible, but normally
* don't bang on the scheduler.
*/
if (smi_info->in_maintenance_mode)
schedule();
else
usleep_range(100, 200);
} else if (smi_result == SI_SM_IDLE) {
if (atomic_read(&smi_info->need_watch)) {
schedule_timeout_interruptible(100);
} else {
/* Wait to be woken up when we are needed. */
__set_current_state(TASK_INTERRUPTIBLE);
schedule();
}
} else {
schedule_timeout_interruptible(1);
}
}
return 0;
}
static void poll(void *send_info)
{
struct smi_info *smi_info = send_info;
unsigned long flags = 0;
bool run_to_completion = smi_info->run_to_completion;
/*
* Make sure there is some delay in the poll loop so we can
* drive time forward and timeout things.
*/
udelay(10);
if (!run_to_completion)
spin_lock_irqsave(&smi_info->si_lock, flags);
smi_event_handler(smi_info, 10);
if (!run_to_completion)
spin_unlock_irqrestore(&smi_info->si_lock, flags);
}
static void request_events(void *send_info)
{
struct smi_info *smi_info = send_info;
if (!smi_info->has_event_buffer)
return;
atomic_set(&smi_info->req_events, 1);
}
static void set_need_watch(void *send_info, unsigned int watch_mask)
{
struct smi_info *smi_info = send_info;
unsigned long flags;
int enable;
enable = !!watch_mask;
atomic_set(&smi_info->need_watch, enable);
spin_lock_irqsave(&smi_info->si_lock, flags);
check_start_timer_thread(smi_info);
spin_unlock_irqrestore(&smi_info->si_lock, flags);
}
treewide: setup_timer() -> timer_setup() This converts all remaining cases of the old setup_timer() API into using timer_setup(), where the callback argument is the structure already holding the struct timer_list. These should have no behavioral changes, since they just change which pointer is passed into the callback with the same available pointers after conversion. It handles the following examples, in addition to some other variations. Casting from unsigned long: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... setup_timer(&ptr->my_timer, my_callback, ptr); and forced object casts: void my_callback(struct something *ptr) { ... } ... setup_timer(&ptr->my_timer, my_callback, (unsigned long)ptr); become: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... timer_setup(&ptr->my_timer, my_callback, 0); Direct function assignments: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... ptr->my_timer.function = my_callback; have a temporary cast added, along with converting the args: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... ptr->my_timer.function = (TIMER_FUNC_TYPE)my_callback; And finally, callbacks without a data assignment: void my_callback(unsigned long data) { ... } ... setup_timer(&ptr->my_timer, my_callback, 0); have their argument renamed to verify they're unused during conversion: void my_callback(struct timer_list *unused) { ... } ... timer_setup(&ptr->my_timer, my_callback, 0); The conversion is done with the following Coccinelle script: spatch --very-quiet --all-includes --include-headers \ -I ./arch/x86/include -I ./arch/x86/include/generated \ -I ./include -I ./arch/x86/include/uapi \ -I ./arch/x86/include/generated/uapi -I ./include/uapi \ -I ./include/generated/uapi --include ./include/linux/kconfig.h \ --dir . \ --cocci-file ~/src/data/timer_setup.cocci @fix_address_of@ expression e; @@ setup_timer( -&(e) +&e , ...) // Update any raw setup_timer() usages that have a NULL callback, but // would otherwise match change_timer_function_usage, since the latter // will update all function assignments done in the face of a NULL // function initialization in setup_timer(). @change_timer_function_usage_NULL@ expression _E; identifier _timer; type _cast_data; @@ ( -setup_timer(&_E->_timer, NULL, _E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E->_timer, NULL, (_cast_data)_E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E._timer, NULL, &_E); +timer_setup(&_E._timer, NULL, 0); | -setup_timer(&_E._timer, NULL, (_cast_data)&_E); +timer_setup(&_E._timer, NULL, 0); ) @change_timer_function_usage@ expression _E; identifier _timer; struct timer_list _stl; identifier _callback; type _cast_func, _cast_data; @@ ( -setup_timer(&_E->_timer, _callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | _E->_timer@_stl.function = _callback; | _E->_timer@_stl.function = &_callback; | _E->_timer@_stl.function = (_cast_func)_callback; | _E->_timer@_stl.function = (_cast_func)&_callback; | _E._timer@_stl.function = _callback; | _E._timer@_stl.function = &_callback; | _E._timer@_stl.function = (_cast_func)_callback; | _E._timer@_stl.function = (_cast_func)&_callback; ) // callback(unsigned long arg) @change_callback_handle_cast depends on change_timer_function_usage@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; identifier _handle; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { ( ... when != _origarg _handletype *_handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg ) } // callback(unsigned long arg) without existing variable @change_callback_handle_cast_no_arg depends on change_timer_function_usage && !change_callback_handle_cast@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { + _handletype *_origarg = from_timer(_origarg, t, _timer); + ... when != _origarg - (_handletype *)_origarg + _origarg ... when != _origarg } // Avoid already converted callbacks. @match_callback_converted depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier t; @@ void _callback(struct timer_list *t) { ... } // callback(struct something *handle) @change_callback_handle_arg depends on change_timer_function_usage && !match_callback_converted && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; @@ void _callback( -_handletype *_handle +struct timer_list *t ) { + _handletype *_handle = from_timer(_handle, t, _timer); ... } // If change_callback_handle_arg ran on an empty function, remove // the added handler. @unchange_callback_handle_arg depends on change_timer_function_usage && change_callback_handle_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; identifier t; @@ void _callback(struct timer_list *t) { - _handletype *_handle = from_timer(_handle, t, _timer); } // We only want to refactor the setup_timer() data argument if we've found // the matching callback. This undoes changes in change_timer_function_usage. @unchange_timer_function_usage depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg && !change_callback_handle_arg@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type change_timer_function_usage._cast_data; @@ ( -timer_setup(&_E->_timer, _callback, 0); +setup_timer(&_E->_timer, _callback, (_cast_data)_E); | -timer_setup(&_E._timer, _callback, 0); +setup_timer(&_E._timer, _callback, (_cast_data)&_E); ) // If we fixed a callback from a .function assignment, fix the // assignment cast now. @change_timer_function_assignment depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_func; typedef TIMER_FUNC_TYPE; @@ ( _E->_timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -&_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)_callback; +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -&_callback; +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; ) // Sometimes timer functions are called directly. Replace matched args. @change_timer_function_calls depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression _E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_data; @@ _callback( ( -(_cast_data)_E +&_E->_timer | -(_cast_data)&_E +&_E._timer | -_E +&_E->_timer ) ) // If a timer has been configured without a data argument, it can be // converted without regard to the callback argument, since it is unused. @match_timer_function_unused_data@ expression _E; identifier _timer; identifier _callback; @@ ( -setup_timer(&_E->_timer, _callback, 0); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0L); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0UL); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0L); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0UL); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_timer, _callback, 0); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0L); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0UL); +timer_setup(&_timer, _callback, 0); | -setup_timer(_timer, _callback, 0); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0L); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0UL); +timer_setup(_timer, _callback, 0); ) @change_callback_unused_data depends on match_timer_function_unused_data@ identifier match_timer_function_unused_data._callback; type _origtype; identifier _origarg; @@ void _callback( -_origtype _origarg +struct timer_list *unused ) { ... when != _origarg } Signed-off-by: Kees Cook <keescook@chromium.org>
2017-10-17 05:43:17 +08:00
static void smi_timeout(struct timer_list *t)
{
treewide: setup_timer() -> timer_setup() This converts all remaining cases of the old setup_timer() API into using timer_setup(), where the callback argument is the structure already holding the struct timer_list. These should have no behavioral changes, since they just change which pointer is passed into the callback with the same available pointers after conversion. It handles the following examples, in addition to some other variations. Casting from unsigned long: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... setup_timer(&ptr->my_timer, my_callback, ptr); and forced object casts: void my_callback(struct something *ptr) { ... } ... setup_timer(&ptr->my_timer, my_callback, (unsigned long)ptr); become: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... timer_setup(&ptr->my_timer, my_callback, 0); Direct function assignments: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... ptr->my_timer.function = my_callback; have a temporary cast added, along with converting the args: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... ptr->my_timer.function = (TIMER_FUNC_TYPE)my_callback; And finally, callbacks without a data assignment: void my_callback(unsigned long data) { ... } ... setup_timer(&ptr->my_timer, my_callback, 0); have their argument renamed to verify they're unused during conversion: void my_callback(struct timer_list *unused) { ... } ... timer_setup(&ptr->my_timer, my_callback, 0); The conversion is done with the following Coccinelle script: spatch --very-quiet --all-includes --include-headers \ -I ./arch/x86/include -I ./arch/x86/include/generated \ -I ./include -I ./arch/x86/include/uapi \ -I ./arch/x86/include/generated/uapi -I ./include/uapi \ -I ./include/generated/uapi --include ./include/linux/kconfig.h \ --dir . \ --cocci-file ~/src/data/timer_setup.cocci @fix_address_of@ expression e; @@ setup_timer( -&(e) +&e , ...) // Update any raw setup_timer() usages that have a NULL callback, but // would otherwise match change_timer_function_usage, since the latter // will update all function assignments done in the face of a NULL // function initialization in setup_timer(). @change_timer_function_usage_NULL@ expression _E; identifier _timer; type _cast_data; @@ ( -setup_timer(&_E->_timer, NULL, _E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E->_timer, NULL, (_cast_data)_E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E._timer, NULL, &_E); +timer_setup(&_E._timer, NULL, 0); | -setup_timer(&_E._timer, NULL, (_cast_data)&_E); +timer_setup(&_E._timer, NULL, 0); ) @change_timer_function_usage@ expression _E; identifier _timer; struct timer_list _stl; identifier _callback; type _cast_func, _cast_data; @@ ( -setup_timer(&_E->_timer, _callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | _E->_timer@_stl.function = _callback; | _E->_timer@_stl.function = &_callback; | _E->_timer@_stl.function = (_cast_func)_callback; | _E->_timer@_stl.function = (_cast_func)&_callback; | _E._timer@_stl.function = _callback; | _E._timer@_stl.function = &_callback; | _E._timer@_stl.function = (_cast_func)_callback; | _E._timer@_stl.function = (_cast_func)&_callback; ) // callback(unsigned long arg) @change_callback_handle_cast depends on change_timer_function_usage@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; identifier _handle; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { ( ... when != _origarg _handletype *_handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg ) } // callback(unsigned long arg) without existing variable @change_callback_handle_cast_no_arg depends on change_timer_function_usage && !change_callback_handle_cast@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { + _handletype *_origarg = from_timer(_origarg, t, _timer); + ... when != _origarg - (_handletype *)_origarg + _origarg ... when != _origarg } // Avoid already converted callbacks. @match_callback_converted depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier t; @@ void _callback(struct timer_list *t) { ... } // callback(struct something *handle) @change_callback_handle_arg depends on change_timer_function_usage && !match_callback_converted && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; @@ void _callback( -_handletype *_handle +struct timer_list *t ) { + _handletype *_handle = from_timer(_handle, t, _timer); ... } // If change_callback_handle_arg ran on an empty function, remove // the added handler. @unchange_callback_handle_arg depends on change_timer_function_usage && change_callback_handle_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; identifier t; @@ void _callback(struct timer_list *t) { - _handletype *_handle = from_timer(_handle, t, _timer); } // We only want to refactor the setup_timer() data argument if we've found // the matching callback. This undoes changes in change_timer_function_usage. @unchange_timer_function_usage depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg && !change_callback_handle_arg@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type change_timer_function_usage._cast_data; @@ ( -timer_setup(&_E->_timer, _callback, 0); +setup_timer(&_E->_timer, _callback, (_cast_data)_E); | -timer_setup(&_E._timer, _callback, 0); +setup_timer(&_E._timer, _callback, (_cast_data)&_E); ) // If we fixed a callback from a .function assignment, fix the // assignment cast now. @change_timer_function_assignment depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_func; typedef TIMER_FUNC_TYPE; @@ ( _E->_timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -&_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)_callback; +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -&_callback; +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; ) // Sometimes timer functions are called directly. Replace matched args. @change_timer_function_calls depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression _E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_data; @@ _callback( ( -(_cast_data)_E +&_E->_timer | -(_cast_data)&_E +&_E._timer | -_E +&_E->_timer ) ) // If a timer has been configured without a data argument, it can be // converted without regard to the callback argument, since it is unused. @match_timer_function_unused_data@ expression _E; identifier _timer; identifier _callback; @@ ( -setup_timer(&_E->_timer, _callback, 0); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0L); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0UL); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0L); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0UL); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_timer, _callback, 0); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0L); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0UL); +timer_setup(&_timer, _callback, 0); | -setup_timer(_timer, _callback, 0); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0L); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0UL); +timer_setup(_timer, _callback, 0); ) @change_callback_unused_data depends on match_timer_function_unused_data@ identifier match_timer_function_unused_data._callback; type _origtype; identifier _origarg; @@ void _callback( -_origtype _origarg +struct timer_list *unused ) { ... when != _origarg } Signed-off-by: Kees Cook <keescook@chromium.org>
2017-10-17 05:43:17 +08:00
struct smi_info *smi_info = from_timer(smi_info, t, si_timer);
enum si_sm_result smi_result;
unsigned long flags;
unsigned long jiffies_now;
2005-11-07 16:59:56 +08:00
long time_diff;
long timeout;
spin_lock_irqsave(&(smi_info->si_lock), flags);
debug_timestamp("Timer");
jiffies_now = jiffies;
2005-11-07 16:59:56 +08:00
time_diff = (((long)jiffies_now - (long)smi_info->last_timeout_jiffies)
* SI_USEC_PER_JIFFY);
smi_result = smi_event_handler(smi_info, time_diff);
if ((smi_info->io.irq) && (!smi_info->interrupt_disabled)) {
/* Running with interrupts, only do long timeouts. */
timeout = jiffies + SI_TIMEOUT_JIFFIES;
smi_inc_stat(smi_info, long_timeouts);
goto do_mod_timer;
}
/*
* If the state machine asks for a short delay, then shorten
* the timer timeout.
*/
if (smi_result == SI_SM_CALL_WITH_DELAY) {
smi_inc_stat(smi_info, short_timeouts);
timeout = jiffies + 1;
} else {
smi_inc_stat(smi_info, long_timeouts);
timeout = jiffies + SI_TIMEOUT_JIFFIES;
}
do_mod_timer:
if (smi_result != SI_SM_IDLE)
smi_mod_timer(smi_info, timeout);
else
smi_info->timer_running = false;
spin_unlock_irqrestore(&(smi_info->si_lock), flags);
}
irqreturn_t ipmi_si_irq_handler(int irq, void *data)
{
struct smi_info *smi_info = data;
unsigned long flags;
if (smi_info->io.si_type == SI_BT)
/* We need to clear the IRQ flag for the BT interface. */
smi_info->io.outputb(&smi_info->io, IPMI_BT_INTMASK_REG,
IPMI_BT_INTMASK_CLEAR_IRQ_BIT
| IPMI_BT_INTMASK_ENABLE_IRQ_BIT);
spin_lock_irqsave(&(smi_info->si_lock), flags);
smi_inc_stat(smi_info, interrupts);
debug_timestamp("Interrupt");
smi_event_handler(smi_info, 0);
spin_unlock_irqrestore(&(smi_info->si_lock), flags);
return IRQ_HANDLED;
}
static int smi_start_processing(void *send_info,
struct ipmi_smi *intf)
{
struct smi_info *new_smi = send_info;
int enable = 0;
new_smi->intf = intf;
/* Set up the timer that drives the interface. */
treewide: setup_timer() -> timer_setup() This converts all remaining cases of the old setup_timer() API into using timer_setup(), where the callback argument is the structure already holding the struct timer_list. These should have no behavioral changes, since they just change which pointer is passed into the callback with the same available pointers after conversion. It handles the following examples, in addition to some other variations. Casting from unsigned long: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... setup_timer(&ptr->my_timer, my_callback, ptr); and forced object casts: void my_callback(struct something *ptr) { ... } ... setup_timer(&ptr->my_timer, my_callback, (unsigned long)ptr); become: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... timer_setup(&ptr->my_timer, my_callback, 0); Direct function assignments: void my_callback(unsigned long data) { struct something *ptr = (struct something *)data; ... } ... ptr->my_timer.function = my_callback; have a temporary cast added, along with converting the args: void my_callback(struct timer_list *t) { struct something *ptr = from_timer(ptr, t, my_timer); ... } ... ptr->my_timer.function = (TIMER_FUNC_TYPE)my_callback; And finally, callbacks without a data assignment: void my_callback(unsigned long data) { ... } ... setup_timer(&ptr->my_timer, my_callback, 0); have their argument renamed to verify they're unused during conversion: void my_callback(struct timer_list *unused) { ... } ... timer_setup(&ptr->my_timer, my_callback, 0); The conversion is done with the following Coccinelle script: spatch --very-quiet --all-includes --include-headers \ -I ./arch/x86/include -I ./arch/x86/include/generated \ -I ./include -I ./arch/x86/include/uapi \ -I ./arch/x86/include/generated/uapi -I ./include/uapi \ -I ./include/generated/uapi --include ./include/linux/kconfig.h \ --dir . \ --cocci-file ~/src/data/timer_setup.cocci @fix_address_of@ expression e; @@ setup_timer( -&(e) +&e , ...) // Update any raw setup_timer() usages that have a NULL callback, but // would otherwise match change_timer_function_usage, since the latter // will update all function assignments done in the face of a NULL // function initialization in setup_timer(). @change_timer_function_usage_NULL@ expression _E; identifier _timer; type _cast_data; @@ ( -setup_timer(&_E->_timer, NULL, _E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E->_timer, NULL, (_cast_data)_E); +timer_setup(&_E->_timer, NULL, 0); | -setup_timer(&_E._timer, NULL, &_E); +timer_setup(&_E._timer, NULL, 0); | -setup_timer(&_E._timer, NULL, (_cast_data)&_E); +timer_setup(&_E._timer, NULL, 0); ) @change_timer_function_usage@ expression _E; identifier _timer; struct timer_list _stl; identifier _callback; type _cast_func, _cast_data; @@ ( -setup_timer(&_E->_timer, _callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, &_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, _E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, &_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)_E); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, (_cast_func)&_callback, (_cast_data)&_E); +timer_setup(&_E._timer, _callback, 0); | _E->_timer@_stl.function = _callback; | _E->_timer@_stl.function = &_callback; | _E->_timer@_stl.function = (_cast_func)_callback; | _E->_timer@_stl.function = (_cast_func)&_callback; | _E._timer@_stl.function = _callback; | _E._timer@_stl.function = &_callback; | _E._timer@_stl.function = (_cast_func)_callback; | _E._timer@_stl.function = (_cast_func)&_callback; ) // callback(unsigned long arg) @change_callback_handle_cast depends on change_timer_function_usage@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; identifier _handle; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { ( ... when != _origarg _handletype *_handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(_handletype *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg | ... when != _origarg _handletype *_handle; ... when != _handle _handle = -(void *)_origarg; +from_timer(_handle, t, _timer); ... when != _origarg ) } // callback(unsigned long arg) without existing variable @change_callback_handle_cast_no_arg depends on change_timer_function_usage && !change_callback_handle_cast@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _origtype; identifier _origarg; type _handletype; @@ void _callback( -_origtype _origarg +struct timer_list *t ) { + _handletype *_origarg = from_timer(_origarg, t, _timer); + ... when != _origarg - (_handletype *)_origarg + _origarg ... when != _origarg } // Avoid already converted callbacks. @match_callback_converted depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier t; @@ void _callback(struct timer_list *t) { ... } // callback(struct something *handle) @change_callback_handle_arg depends on change_timer_function_usage && !match_callback_converted && !change_callback_handle_cast && !change_callback_handle_cast_no_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; @@ void _callback( -_handletype *_handle +struct timer_list *t ) { + _handletype *_handle = from_timer(_handle, t, _timer); ... } // If change_callback_handle_arg ran on an empty function, remove // the added handler. @unchange_callback_handle_arg depends on change_timer_function_usage && change_callback_handle_arg@ identifier change_timer_function_usage._callback; identifier change_timer_function_usage._timer; type _handletype; identifier _handle; identifier t; @@ void _callback(struct timer_list *t) { - _handletype *_handle = from_timer(_handle, t, _timer); } // We only want to refactor the setup_timer() data argument if we've found // the matching callback. This undoes changes in change_timer_function_usage. @unchange_timer_function_usage depends on change_timer_function_usage && !change_callback_handle_cast && !change_callback_handle_cast_no_arg && !change_callback_handle_arg@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type change_timer_function_usage._cast_data; @@ ( -timer_setup(&_E->_timer, _callback, 0); +setup_timer(&_E->_timer, _callback, (_cast_data)_E); | -timer_setup(&_E._timer, _callback, 0); +setup_timer(&_E._timer, _callback, (_cast_data)&_E); ) // If we fixed a callback from a .function assignment, fix the // assignment cast now. @change_timer_function_assignment depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression change_timer_function_usage._E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_func; typedef TIMER_FUNC_TYPE; @@ ( _E->_timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -&_callback +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)_callback; +(TIMER_FUNC_TYPE)_callback ; | _E->_timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -&_callback; +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)_callback +(TIMER_FUNC_TYPE)_callback ; | _E._timer.function = -(_cast_func)&_callback +(TIMER_FUNC_TYPE)_callback ; ) // Sometimes timer functions are called directly. Replace matched args. @change_timer_function_calls depends on change_timer_function_usage && (change_callback_handle_cast || change_callback_handle_cast_no_arg || change_callback_handle_arg)@ expression _E; identifier change_timer_function_usage._timer; identifier change_timer_function_usage._callback; type _cast_data; @@ _callback( ( -(_cast_data)_E +&_E->_timer | -(_cast_data)&_E +&_E._timer | -_E +&_E->_timer ) ) // If a timer has been configured without a data argument, it can be // converted without regard to the callback argument, since it is unused. @match_timer_function_unused_data@ expression _E; identifier _timer; identifier _callback; @@ ( -setup_timer(&_E->_timer, _callback, 0); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0L); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E->_timer, _callback, 0UL); +timer_setup(&_E->_timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0L); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_E._timer, _callback, 0UL); +timer_setup(&_E._timer, _callback, 0); | -setup_timer(&_timer, _callback, 0); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0L); +timer_setup(&_timer, _callback, 0); | -setup_timer(&_timer, _callback, 0UL); +timer_setup(&_timer, _callback, 0); | -setup_timer(_timer, _callback, 0); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0L); +timer_setup(_timer, _callback, 0); | -setup_timer(_timer, _callback, 0UL); +timer_setup(_timer, _callback, 0); ) @change_callback_unused_data depends on match_timer_function_unused_data@ identifier match_timer_function_unused_data._callback; type _origtype; identifier _origarg; @@ void _callback( -_origtype _origarg +struct timer_list *unused ) { ... when != _origarg } Signed-off-by: Kees Cook <keescook@chromium.org>
2017-10-17 05:43:17 +08:00
timer_setup(&new_smi->si_timer, smi_timeout, 0);
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
new_smi->timer_can_start = true;
smi_mod_timer(new_smi, jiffies + SI_TIMEOUT_JIFFIES);
/* Try to claim any interrupts. */
if (new_smi->io.irq_setup) {
new_smi->io.irq_handler_data = new_smi;
new_smi->io.irq_setup(&new_smi->io);
}
/*
* Check if the user forcefully enabled the daemon.
*/
if (new_smi->si_num < num_force_kipmid)
enable = force_kipmid[new_smi->si_num];
/*
* The BT interface is efficient enough to not need a thread,
* and there is no need for a thread if we have interrupts.
*/
else if ((new_smi->io.si_type != SI_BT) && (!new_smi->io.irq))
enable = 1;
if (enable) {
new_smi->thread = kthread_run(ipmi_thread, new_smi,
"kipmi%d", new_smi->si_num);
if (IS_ERR(new_smi->thread)) {
dev_notice(new_smi->io.dev, "Could not start"
" kernel thread due to error %ld, only using"
" timers to drive the interface\n",
PTR_ERR(new_smi->thread));
new_smi->thread = NULL;
}
}
return 0;
}
static int get_smi_info(void *send_info, struct ipmi_smi_info *data)
{
struct smi_info *smi = send_info;
data->addr_src = smi->io.addr_source;
data->dev = smi->io.dev;
data->addr_info = smi->io.addr_info;
get_device(smi->io.dev);
return 0;
}
static void set_maintenance_mode(void *send_info, bool enable)
{
struct smi_info *smi_info = send_info;
if (!enable)
atomic_set(&smi_info->req_events, 0);
smi_info->in_maintenance_mode = enable;
}
static void shutdown_smi(void *send_info);
static const struct ipmi_smi_handlers handlers = {
.owner = THIS_MODULE,
.start_processing = smi_start_processing,
.shutdown = shutdown_smi,
.get_smi_info = get_smi_info,
.sender = sender,
.request_events = request_events,
.set_need_watch = set_need_watch,
.set_maintenance_mode = set_maintenance_mode,
.set_run_to_completion = set_run_to_completion,
.flush_messages = flush_messages,
.poll = poll,
};
static LIST_HEAD(smi_infos);
static DEFINE_MUTEX(smi_infos_lock);
static int smi_num; /* Used to sequence the SMIs */
static const char * const addr_space_to_str[] = { "i/o", "mem" };
module_param_array(force_kipmid, int, &num_force_kipmid, 0);
MODULE_PARM_DESC(force_kipmid, "Force the kipmi daemon to be enabled (1) or"
" disabled(0). Normally the IPMI driver auto-detects"
" this, but the value may be overridden by this parm.");
module_param(unload_when_empty, bool, 0);
MODULE_PARM_DESC(unload_when_empty, "Unload the module if no interfaces are"
" specified or found, default is 1. Setting to 0"
" is useful for hot add of devices using hotmod.");
module_param_array(kipmid_max_busy_us, uint, &num_max_busy_us, 0644);
MODULE_PARM_DESC(kipmid_max_busy_us,
"Max time (in microseconds) to busy-wait for IPMI data before"
" sleeping. 0 (default) means to wait forever. Set to 100-500"
" if kipmid is using up a lot of CPU time.");
void ipmi_irq_finish_setup(struct si_sm_io *io)
{
if (io->si_type == SI_BT)
/* Enable the interrupt in the BT interface. */
io->outputb(io, IPMI_BT_INTMASK_REG,
IPMI_BT_INTMASK_ENABLE_IRQ_BIT);
}
void ipmi_irq_start_cleanup(struct si_sm_io *io)
{
if (io->si_type == SI_BT)
/* Disable the interrupt in the BT interface. */
io->outputb(io, IPMI_BT_INTMASK_REG, 0);
}
static void std_irq_cleanup(struct si_sm_io *io)
{
ipmi_irq_start_cleanup(io);
free_irq(io->irq, io->irq_handler_data);
}
int ipmi_std_irq_setup(struct si_sm_io *io)
{
int rv;
if (!io->irq)
return 0;
rv = request_irq(io->irq,
ipmi_si_irq_handler,
IRQF_SHARED,
SI_DEVICE_NAME,
io->irq_handler_data);
if (rv) {
dev_warn(io->dev, "%s unable to claim interrupt %d,"
" running polled\n",
SI_DEVICE_NAME, io->irq);
io->irq = 0;
} else {
io->irq_cleanup = std_irq_cleanup;
ipmi_irq_finish_setup(io);
dev_info(io->dev, "Using irq %d\n", io->irq);
}
return rv;
}
static int wait_for_msg_done(struct smi_info *smi_info)
{
enum si_sm_result smi_result;
smi_result = smi_info->handlers->event(smi_info->si_sm, 0);
for (;;) {
if (smi_result == SI_SM_CALL_WITH_DELAY ||
smi_result == SI_SM_CALL_WITH_TICK_DELAY) {
schedule_timeout_uninterruptible(1);
smi_result = smi_info->handlers->event(
smi_info->si_sm, jiffies_to_usecs(1));
} else if (smi_result == SI_SM_CALL_WITHOUT_DELAY) {
smi_result = smi_info->handlers->event(
smi_info->si_sm, 0);
} else
break;
}
if (smi_result == SI_SM_HOSED)
/*
* We couldn't get the state machine to run, so whatever's at
* the port is probably not an IPMI SMI interface.
*/
return -ENODEV;
return 0;
}
static int try_get_dev_id(struct smi_info *smi_info)
{
unsigned char msg[2];
unsigned char *resp;
unsigned long resp_len;
int rv = 0;
resp = kmalloc(IPMI_MAX_MSG_LENGTH, GFP_KERNEL);
if (!resp)
return -ENOMEM;
/*
* Do a Get Device ID command, since it comes back with some
* useful info.
*/
msg[0] = IPMI_NETFN_APP_REQUEST << 2;
msg[1] = IPMI_GET_DEVICE_ID_CMD;
smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
rv = wait_for_msg_done(smi_info);
if (rv)
goto out;
resp_len = smi_info->handlers->get_result(smi_info->si_sm,
resp, IPMI_MAX_MSG_LENGTH);
/* Check and record info from the get device id, in case we need it. */
rv = ipmi_demangle_device_id(resp[0] >> 2, resp[1],
resp + 2, resp_len - 2, &smi_info->device_id);
out:
kfree(resp);
return rv;
}
static int get_global_enables(struct smi_info *smi_info, u8 *enables)
{
unsigned char msg[3];
unsigned char *resp;
unsigned long resp_len;
int rv;
resp = kmalloc(IPMI_MAX_MSG_LENGTH, GFP_KERNEL);
if (!resp)
return -ENOMEM;
msg[0] = IPMI_NETFN_APP_REQUEST << 2;
msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD;
smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
rv = wait_for_msg_done(smi_info);
if (rv) {
dev_warn(smi_info->io.dev,
"Error getting response from get global enables command: %d\n",
rv);
goto out;
}
resp_len = smi_info->handlers->get_result(smi_info->si_sm,
resp, IPMI_MAX_MSG_LENGTH);
if (resp_len < 4 ||
resp[0] != (IPMI_NETFN_APP_REQUEST | 1) << 2 ||
resp[1] != IPMI_GET_BMC_GLOBAL_ENABLES_CMD ||
resp[2] != 0) {
dev_warn(smi_info->io.dev,
"Invalid return from get global enables command: %ld %x %x %x\n",
resp_len, resp[0], resp[1], resp[2]);
rv = -EINVAL;
goto out;
} else {
*enables = resp[3];
}
out:
kfree(resp);
return rv;
}
/*
* Returns 1 if it gets an error from the command.
*/
static int set_global_enables(struct smi_info *smi_info, u8 enables)
{
unsigned char msg[3];
unsigned char *resp;
unsigned long resp_len;
int rv;
resp = kmalloc(IPMI_MAX_MSG_LENGTH, GFP_KERNEL);
if (!resp)
return -ENOMEM;
msg[0] = IPMI_NETFN_APP_REQUEST << 2;
msg[1] = IPMI_SET_BMC_GLOBAL_ENABLES_CMD;
msg[2] = enables;
smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3);
rv = wait_for_msg_done(smi_info);
if (rv) {
dev_warn(smi_info->io.dev,
"Error getting response from set global enables command: %d\n",
rv);
goto out;
}
resp_len = smi_info->handlers->get_result(smi_info->si_sm,
resp, IPMI_MAX_MSG_LENGTH);
if (resp_len < 3 ||
resp[0] != (IPMI_NETFN_APP_REQUEST | 1) << 2 ||
resp[1] != IPMI_SET_BMC_GLOBAL_ENABLES_CMD) {
dev_warn(smi_info->io.dev,
"Invalid return from set global enables command: %ld %x %x\n",
resp_len, resp[0], resp[1]);
rv = -EINVAL;
goto out;
}
if (resp[2] != 0)
rv = 1;
out:
kfree(resp);
return rv;
}
/*
* Some BMCs do not support clearing the receive irq bit in the global
* enables (even if they don't support interrupts on the BMC). Check
* for this and handle it properly.
*/
static void check_clr_rcv_irq(struct smi_info *smi_info)
{
u8 enables = 0;
int rv;
rv = get_global_enables(smi_info, &enables);
if (!rv) {
if ((enables & IPMI_BMC_RCV_MSG_INTR) == 0)
/* Already clear, should work ok. */
return;
enables &= ~IPMI_BMC_RCV_MSG_INTR;
rv = set_global_enables(smi_info, enables);
}
if (rv < 0) {
dev_err(smi_info->io.dev,
"Cannot check clearing the rcv irq: %d\n", rv);
return;
}
if (rv) {
/*
* An error when setting the event buffer bit means
* clearing the bit is not supported.
*/
dev_warn(smi_info->io.dev,
"The BMC does not support clearing the recv irq bit, compensating, but the BMC needs to be fixed.\n");
smi_info->cannot_disable_irq = true;
}
}
/*
* Some BMCs do not support setting the interrupt bits in the global
* enables even if they support interrupts. Clearly bad, but we can
* compensate.
*/
static void check_set_rcv_irq(struct smi_info *smi_info)
{
u8 enables = 0;
int rv;
if (!smi_info->io.irq)
return;
rv = get_global_enables(smi_info, &enables);
if (!rv) {
enables |= IPMI_BMC_RCV_MSG_INTR;
rv = set_global_enables(smi_info, enables);
}
if (rv < 0) {
dev_err(smi_info->io.dev,
"Cannot check setting the rcv irq: %d\n", rv);
return;
}
if (rv) {
/*
* An error when setting the event buffer bit means
* setting the bit is not supported.
*/
dev_warn(smi_info->io.dev,
"The BMC does not support setting the recv irq bit, compensating, but the BMC needs to be fixed.\n");
smi_info->cannot_disable_irq = true;
smi_info->irq_enable_broken = true;
}
}
static int try_enable_event_buffer(struct smi_info *smi_info)
{
unsigned char msg[3];
unsigned char *resp;
unsigned long resp_len;
int rv = 0;
resp = kmalloc(IPMI_MAX_MSG_LENGTH, GFP_KERNEL);
if (!resp)
return -ENOMEM;
msg[0] = IPMI_NETFN_APP_REQUEST << 2;
msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD;
smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
rv = wait_for_msg_done(smi_info);
if (rv) {
pr_warn("Error getting response from get global enables command, the event buffer is not enabled\n");
goto out;
}
resp_len = smi_info->handlers->get_result(smi_info->si_sm,
resp, IPMI_MAX_MSG_LENGTH);
if (resp_len < 4 ||
resp[0] != (IPMI_NETFN_APP_REQUEST | 1) << 2 ||
resp[1] != IPMI_GET_BMC_GLOBAL_ENABLES_CMD ||
resp[2] != 0) {
pr_warn("Invalid return from get global enables command, cannot enable the event buffer\n");
rv = -EINVAL;
goto out;
}
if (resp[3] & IPMI_BMC_EVT_MSG_BUFF) {
/* buffer is already enabled, nothing to do. */
smi_info->supports_event_msg_buff = true;
goto out;
}
msg[0] = IPMI_NETFN_APP_REQUEST << 2;
msg[1] = IPMI_SET_BMC_GLOBAL_ENABLES_CMD;
msg[2] = resp[3] | IPMI_BMC_EVT_MSG_BUFF;
smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3);
rv = wait_for_msg_done(smi_info);
if (rv) {
pr_warn("Error getting response from set global, enables command, the event buffer is not enabled\n");
goto out;
}
resp_len = smi_info->handlers->get_result(smi_info->si_sm,
resp, IPMI_MAX_MSG_LENGTH);
if (resp_len < 3 ||
resp[0] != (IPMI_NETFN_APP_REQUEST | 1) << 2 ||
resp[1] != IPMI_SET_BMC_GLOBAL_ENABLES_CMD) {
pr_warn("Invalid return from get global, enables command, not enable the event buffer\n");
rv = -EINVAL;
goto out;
}
if (resp[2] != 0)
/*
* An error when setting the event buffer bit means
* that the event buffer is not supported.
*/
rv = -ENOENT;
else
smi_info->supports_event_msg_buff = true;
out:
kfree(resp);
return rv;
}
#define IPMI_SI_ATTR(name) \
static ssize_t name##_show(struct device *dev, \
struct device_attribute *attr, \
char *buf) \
{ \
struct smi_info *smi_info = dev_get_drvdata(dev); \
\
return snprintf(buf, 10, "%u\n", smi_get_stat(smi_info, name)); \
} \
static DEVICE_ATTR(name, 0444, name##_show, NULL)
static ssize_t type_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct smi_info *smi_info = dev_get_drvdata(dev);
return snprintf(buf, 10, "%s\n", si_to_str[smi_info->io.si_type]);
}
static DEVICE_ATTR(type, 0444, type_show, NULL);
static ssize_t interrupts_enabled_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct smi_info *smi_info = dev_get_drvdata(dev);
int enabled = smi_info->io.irq && !smi_info->interrupt_disabled;
return snprintf(buf, 10, "%d\n", enabled);
}
static DEVICE_ATTR(interrupts_enabled, 0444,
interrupts_enabled_show, NULL);
IPMI_SI_ATTR(short_timeouts);
IPMI_SI_ATTR(long_timeouts);
IPMI_SI_ATTR(idles);
IPMI_SI_ATTR(interrupts);
IPMI_SI_ATTR(attentions);
IPMI_SI_ATTR(flag_fetches);
IPMI_SI_ATTR(hosed_count);
IPMI_SI_ATTR(complete_transactions);
IPMI_SI_ATTR(events);
IPMI_SI_ATTR(watchdog_pretimeouts);
IPMI_SI_ATTR(incoming_messages);
static ssize_t params_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct smi_info *smi_info = dev_get_drvdata(dev);
return snprintf(buf, 200,
"%s,%s,0x%lx,rsp=%d,rsi=%d,rsh=%d,irq=%d,ipmb=%d\n",
si_to_str[smi_info->io.si_type],
addr_space_to_str[smi_info->io.addr_space],
smi_info->io.addr_data,
smi_info->io.regspacing,
smi_info->io.regsize,
smi_info->io.regshift,
smi_info->io.irq,
smi_info->io.slave_addr);
}
static DEVICE_ATTR(params, 0444, params_show, NULL);
static struct attribute *ipmi_si_dev_attrs[] = {
&dev_attr_type.attr,
&dev_attr_interrupts_enabled.attr,
&dev_attr_short_timeouts.attr,
&dev_attr_long_timeouts.attr,
&dev_attr_idles.attr,
&dev_attr_interrupts.attr,
&dev_attr_attentions.attr,
&dev_attr_flag_fetches.attr,
&dev_attr_hosed_count.attr,
&dev_attr_complete_transactions.attr,
&dev_attr_events.attr,
&dev_attr_watchdog_pretimeouts.attr,
&dev_attr_incoming_messages.attr,
&dev_attr_params.attr,
NULL
};
static const struct attribute_group ipmi_si_dev_attr_group = {
.attrs = ipmi_si_dev_attrs,
};
/*
* oem_data_avail_to_receive_msg_avail
* @info - smi_info structure with msg_flags set
*
* Converts flags from OEM_DATA_AVAIL to RECEIVE_MSG_AVAIL
* Returns 1 indicating need to re-run handle_flags().
*/
static int oem_data_avail_to_receive_msg_avail(struct smi_info *smi_info)
{
smi_info->msg_flags = ((smi_info->msg_flags & ~OEM_DATA_AVAIL) |
RECEIVE_MSG_AVAIL);
return 1;
}
/*
* setup_dell_poweredge_oem_data_handler
* @info - smi_info.device_id must be populated
*
* Systems that match, but have firmware version < 1.40 may assert
* OEM0_DATA_AVAIL on their own, without being told via Set Flags that
* it's safe to do so. Such systems will de-assert OEM1_DATA_AVAIL
* upon receipt of IPMI_GET_MSG_CMD, so we should treat these flags
* as RECEIVE_MSG_AVAIL instead.
*
* As Dell has no plans to release IPMI 1.5 firmware that *ever*
* assert the OEM[012] bits, and if it did, the driver would have to
* change to handle that properly, we don't actually check for the
* firmware version.
* Device ID = 0x20 BMC on PowerEdge 8G servers
* Device Revision = 0x80
* Firmware Revision1 = 0x01 BMC version 1.40
* Firmware Revision2 = 0x40 BCD encoded
* IPMI Version = 0x51 IPMI 1.5
* Manufacturer ID = A2 02 00 Dell IANA
*
* Additionally, PowerEdge systems with IPMI < 1.5 may also assert
* OEM0_DATA_AVAIL and needs to be treated as RECEIVE_MSG_AVAIL.
*
*/
#define DELL_POWEREDGE_8G_BMC_DEVICE_ID 0x20
#define DELL_POWEREDGE_8G_BMC_DEVICE_REV 0x80
#define DELL_POWEREDGE_8G_BMC_IPMI_VERSION 0x51
#define DELL_IANA_MFR_ID 0x0002a2
static void setup_dell_poweredge_oem_data_handler(struct smi_info *smi_info)
{
struct ipmi_device_id *id = &smi_info->device_id;
if (id->manufacturer_id == DELL_IANA_MFR_ID) {
if (id->device_id == DELL_POWEREDGE_8G_BMC_DEVICE_ID &&
id->device_revision == DELL_POWEREDGE_8G_BMC_DEVICE_REV &&
id->ipmi_version == DELL_POWEREDGE_8G_BMC_IPMI_VERSION) {
smi_info->oem_data_avail_handler =
oem_data_avail_to_receive_msg_avail;
} else if (ipmi_version_major(id) < 1 ||
(ipmi_version_major(id) == 1 &&
ipmi_version_minor(id) < 5)) {
smi_info->oem_data_avail_handler =
oem_data_avail_to_receive_msg_avail;
}
}
}
#define CANNOT_RETURN_REQUESTED_LENGTH 0xCA
static void return_hosed_msg_badsize(struct smi_info *smi_info)
{
struct ipmi_smi_msg *msg = smi_info->curr_msg;
/* Make it a response */
msg->rsp[0] = msg->data[0] | 4;
msg->rsp[1] = msg->data[1];
msg->rsp[2] = CANNOT_RETURN_REQUESTED_LENGTH;
msg->rsp_size = 3;
smi_info->curr_msg = NULL;
deliver_recv_msg(smi_info, msg);
}
/*
* dell_poweredge_bt_xaction_handler
* @info - smi_info.device_id must be populated
*
* Dell PowerEdge servers with the BT interface (x6xx and 1750) will
* not respond to a Get SDR command if the length of the data
* requested is exactly 0x3A, which leads to command timeouts and no
* data returned. This intercepts such commands, and causes userspace
* callers to try again with a different-sized buffer, which succeeds.
*/
#define STORAGE_NETFN 0x0A
#define STORAGE_CMD_GET_SDR 0x23
static int dell_poweredge_bt_xaction_handler(struct notifier_block *self,
unsigned long unused,
void *in)
{
struct smi_info *smi_info = in;
unsigned char *data = smi_info->curr_msg->data;
unsigned int size = smi_info->curr_msg->data_size;
if (size >= 8 &&
(data[0]>>2) == STORAGE_NETFN &&
data[1] == STORAGE_CMD_GET_SDR &&
data[7] == 0x3A) {
return_hosed_msg_badsize(smi_info);
return NOTIFY_STOP;
}
return NOTIFY_DONE;
}
static struct notifier_block dell_poweredge_bt_xaction_notifier = {
.notifier_call = dell_poweredge_bt_xaction_handler,
};
/*
* setup_dell_poweredge_bt_xaction_handler
* @info - smi_info.device_id must be filled in already
*
* Fills in smi_info.device_id.start_transaction_pre_hook
* when we know what function to use there.
*/
static void
setup_dell_poweredge_bt_xaction_handler(struct smi_info *smi_info)
{
struct ipmi_device_id *id = &smi_info->device_id;
if (id->manufacturer_id == DELL_IANA_MFR_ID &&
smi_info->io.si_type == SI_BT)
register_xaction_notifier(&dell_poweredge_bt_xaction_notifier);
}
/*
* setup_oem_data_handler
* @info - smi_info.device_id must be filled in already
*
* Fills in smi_info.device_id.oem_data_available_handler
* when we know what function to use there.
*/
static void setup_oem_data_handler(struct smi_info *smi_info)
{
setup_dell_poweredge_oem_data_handler(smi_info);
}
static void setup_xaction_handlers(struct smi_info *smi_info)
{
setup_dell_poweredge_bt_xaction_handler(smi_info);
}
static void check_for_broken_irqs(struct smi_info *smi_info)
{
check_clr_rcv_irq(smi_info);
check_set_rcv_irq(smi_info);
}
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
static inline void stop_timer_and_thread(struct smi_info *smi_info)
{
if (smi_info->thread != NULL) {
kthread_stop(smi_info->thread);
smi_info->thread = NULL;
}
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
smi_info->timer_can_start = false;
del_timer_sync(&smi_info->si_timer);
}
static struct smi_info *find_dup_si(struct smi_info *info)
{
struct smi_info *e;
list_for_each_entry(e, &smi_infos, link) {
if (e->io.addr_space != info->io.addr_space)
continue;
if (e->io.addr_data == info->io.addr_data) {
/*
* This is a cheap hack, ACPI doesn't have a defined
* slave address but SMBIOS does. Pick it up from
* any source that has it available.
*/
if (info->io.slave_addr && !e->io.slave_addr)
e->io.slave_addr = info->io.slave_addr;
return e;
}
}
return NULL;
}
int ipmi_si_add_smi(struct si_sm_io *io)
{
int rv = 0;
struct smi_info *new_smi, *dup;
/*
* If the user gave us a hard-coded device at the same
* address, they presumably want us to use it and not what is
* in the firmware.
*/
if (io->addr_source != SI_HARDCODED && io->addr_source != SI_HOTMOD &&
ipmi_si_hardcode_match(io->addr_space, io->addr_data)) {
dev_info(io->dev,
"Hard-coded device at this address already exists");
return -ENODEV;
}
if (!io->io_setup) {
if (io->addr_space == IPMI_IO_ADDR_SPACE) {
io->io_setup = ipmi_si_port_setup;
} else if (io->addr_space == IPMI_MEM_ADDR_SPACE) {
io->io_setup = ipmi_si_mem_setup;
} else {
return -EINVAL;
}
}
new_smi = kzalloc(sizeof(*new_smi), GFP_KERNEL);
if (!new_smi)
return -ENOMEM;
spin_lock_init(&new_smi->si_lock);
new_smi->io = *io;
mutex_lock(&smi_infos_lock);
dup = find_dup_si(new_smi);
if (dup) {
if (new_smi->io.addr_source == SI_ACPI &&
dup->io.addr_source == SI_SMBIOS) {
/* We prefer ACPI over SMBIOS. */
dev_info(dup->io.dev,
"Removing SMBIOS-specified %s state machine in favor of ACPI\n",
si_to_str[new_smi->io.si_type]);
cleanup_one_si(dup);
} else {
dev_info(new_smi->io.dev,
"%s-specified %s state machine: duplicate\n",
ipmi_addr_src_to_str(new_smi->io.addr_source),
si_to_str[new_smi->io.si_type]);
rv = -EBUSY;
kfree(new_smi);
goto out_err;
}
}
pr_info("Adding %s-specified %s state machine\n",
ipmi_addr_src_to_str(new_smi->io.addr_source),
si_to_str[new_smi->io.si_type]);
list_add_tail(&new_smi->link, &smi_infos);
if (initialized)
rv = try_smi_init(new_smi);
out_err:
mutex_unlock(&smi_infos_lock);
return rv;
}
/*
* Try to start up an interface. Must be called with smi_infos_lock
* held, primarily to keep smi_num consistent, we only one to do these
* one at a time.
*/
static int try_smi_init(struct smi_info *new_smi)
{
int rv = 0;
int i;
pr_info("Trying %s-specified %s state machine at %s address 0x%lx, slave address 0x%x, irq %d\n",
ipmi_addr_src_to_str(new_smi->io.addr_source),
si_to_str[new_smi->io.si_type],
addr_space_to_str[new_smi->io.addr_space],
new_smi->io.addr_data,
new_smi->io.slave_addr, new_smi->io.irq);
switch (new_smi->io.si_type) {
case SI_KCS:
new_smi->handlers = &kcs_smi_handlers;
break;
case SI_SMIC:
new_smi->handlers = &smic_smi_handlers;
break;
case SI_BT:
new_smi->handlers = &bt_smi_handlers;
break;
default:
/* No support for anything else yet. */
rv = -EIO;
goto out_err;
}
new_smi->si_num = smi_num;
/* Do this early so it's available for logs. */
if (!new_smi->io.dev) {
pr_err("IPMI interface added with no device\n");
rv = -EIO;
goto out_err;
}
/* Allocate the state machine's data and initialize it. */
new_smi->si_sm = kmalloc(new_smi->handlers->size(), GFP_KERNEL);
if (!new_smi->si_sm) {
rv = -ENOMEM;
goto out_err;
}
new_smi->io.io_size = new_smi->handlers->init_data(new_smi->si_sm,
&new_smi->io);
/* Now that we know the I/O size, we can set up the I/O. */
rv = new_smi->io.io_setup(&new_smi->io);
if (rv) {
dev_err(new_smi->io.dev, "Could not set up I/O space\n");
goto out_err;
}
/* Do low-level detection first. */
if (new_smi->handlers->detect(new_smi->si_sm)) {
if (new_smi->io.addr_source)
dev_err(new_smi->io.dev,
"Interface detection failed\n");
rv = -ENODEV;
goto out_err;
}
/*
* Attempt a get device id command. If it fails, we probably
* don't have a BMC here.
*/
rv = try_get_dev_id(new_smi);
if (rv) {
if (new_smi->io.addr_source)
dev_err(new_smi->io.dev,
"There appears to be no BMC at this location\n");
goto out_err;
}
setup_oem_data_handler(new_smi);
setup_xaction_handlers(new_smi);
check_for_broken_irqs(new_smi);
new_smi->waiting_msg = NULL;
new_smi->curr_msg = NULL;
atomic_set(&new_smi->req_events, 0);
new_smi->run_to_completion = false;
for (i = 0; i < SI_NUM_STATS; i++)
atomic_set(&new_smi->stats[i], 0);
new_smi->interrupt_disabled = true;
atomic_set(&new_smi->need_watch, 0);
rv = try_enable_event_buffer(new_smi);
if (rv == 0)
new_smi->has_event_buffer = true;
/*
* Start clearing the flags before we enable interrupts or the
* timer to avoid racing with the timer.
*/
ipmi: Stop timers before cleaning up the module System may crash after unloading ipmi_si.ko module because a timer may remain and fire after the module cleaned up resources. cleanup_one_si() contains the following processing. /* * Make sure that interrupts, the timer and the thread are * stopped and will not run again. */ if (to_clean->irq_cleanup) to_clean->irq_cleanup(to_clean); wait_for_timer_and_thread(to_clean); /* * Timeouts are stopped, now make sure the interrupts are off * in the BMC. Note that timers and CPU interrupts are off, * so no need for locks. */ while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) { poll(to_clean); schedule_timeout_uninterruptible(1); } si_state changes as following in the while loop calling poll(to_clean). SI_GETTING_MESSAGES => SI_CHECKING_ENABLES => SI_SETTING_ENABLES => SI_GETTING_EVENTS => SI_NORMAL As written in the code comments above, timers are expected to stop before the polling loop and not to run again. But the timer is set again in the following process when si_state becomes SI_SETTING_ENABLES. => poll => smi_event_handler => handle_transaction_done // smi_info->si_state == SI_SETTING_ENABLES => start_getting_events => start_new_msg => smi_mod_timer => mod_timer As a result, before the timer set in start_new_msg() expires, the polling loop may see si_state becoming SI_NORMAL and the module clean-up finishes. For example, hard LOCKUP and panic occurred as following. smi_timeout was called after smi_event_handler, kcs_event and hangs at port_inb() trying to access I/O port after release. [exception RIP: port_inb+19] RIP: ffffffffc0473053 RSP: ffff88069fdc3d80 RFLAGS: 00000006 RAX: ffff8806800f8e00 RBX: ffff880682bd9400 RCX: 0000000000000000 RDX: 0000000000000ca3 RSI: 0000000000000ca3 RDI: ffff8806800f8e40 RBP: ffff88069fdc3d80 R8: ffffffff81d86dfc R9: ffffffff81e36426 R10: 00000000000509f0 R11: 0000000000100000 R12: 0000000000]:000000 R13: 0000000000000000 R14: 0000000000000246 R15: ffff8806800f8e00 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0000 --- <NMI exception stack> --- To fix the problem I defined a flag, timer_can_start, as member of struct smi_info. The flag is enabled immediately after initializing the timer and disabled immediately before waiting for timer deletion. Fixes: 0cfec916e86d ("ipmi: Start the timer and thread on internal msgs") Signed-off-by: Yamazaki Masamitsu <m-yamazaki@ah.jp.nec.com> [Adjusted for recent changes in the driver.] Signed-off-by: Corey Minyard <cminyard@mvista.com>
2017-11-15 15:33:14 +08:00
start_clear_flags(new_smi);
/*
* IRQ is defined to be set when non-zero. req_events will
* cause a global flags check that will enable interrupts.
*/
if (new_smi->io.irq) {
new_smi->interrupt_disabled = false;
atomic_set(&new_smi->req_events, 1);
}
dev_set_drvdata(new_smi->io.dev, new_smi);
rv = device_add_group(new_smi->io.dev, &ipmi_si_dev_attr_group);
if (rv) {
dev_err(new_smi->io.dev,
"Unable to add device attributes: error %d\n",
rv);
goto out_err;
}
new_smi->dev_group_added = true;
rv = ipmi_register_smi(&handlers,
new_smi,
new_smi->io.dev,
new_smi->io.slave_addr);
if (rv) {
dev_err(new_smi->io.dev,
"Unable to register device: error %d\n",
rv);
goto out_err;
}
/* Don't increment till we know we have succeeded. */
smi_num++;
dev_info(new_smi->io.dev, "IPMI %s interface initialized\n",
si_to_str[new_smi->io.si_type]);
WARN_ON(new_smi->io.dev->init_name != NULL);
out_err:
ipmi_si: fix use-after-free of resource->name When we excute the following commands, we got oops rmmod ipmi_si cat /proc/ioports [ 1623.482380] Unable to handle kernel paging request at virtual address ffff00000901d478 [ 1623.482382] Mem abort info: [ 1623.482383] ESR = 0x96000007 [ 1623.482385] Exception class = DABT (current EL), IL = 32 bits [ 1623.482386] SET = 0, FnV = 0 [ 1623.482387] EA = 0, S1PTW = 0 [ 1623.482388] Data abort info: [ 1623.482389] ISV = 0, ISS = 0x00000007 [ 1623.482390] CM = 0, WnR = 0 [ 1623.482393] swapper pgtable: 4k pages, 48-bit VAs, pgdp = 00000000d7d94a66 [ 1623.482395] [ffff00000901d478] pgd=000000dffbfff003, pud=000000dffbffe003, pmd=0000003f5d06e003, pte=0000000000000000 [ 1623.482399] Internal error: Oops: 96000007 [#1] SMP [ 1623.487407] Modules linked in: ipmi_si(E) nls_utf8 isofs rpcrdma ib_iser ib_srpt target_core_mod ib_srp scsi_transport_srp ib_ipoib rdma_ucm ib_umad rdma_cm ib_cm dm_mirror dm_region_hash dm_log iw_cm dm_mod aes_ce_blk crypto_simd cryptd aes_ce_cipher ses ghash_ce sha2_ce enclosure sha256_arm64 sg sha1_ce hisi_sas_v2_hw hibmc_drm sbsa_gwdt hisi_sas_main ip_tables mlx5_ib ib_uverbs marvell ib_core mlx5_core ixgbe mdio hns_dsaf ipmi_devintf hns_enet_drv ipmi_msghandler hns_mdio [last unloaded: ipmi_si] [ 1623.532410] CPU: 30 PID: 11438 Comm: cat Kdump: loaded Tainted: G E 5.0.0-rc3+ #168 [ 1623.541498] Hardware name: Huawei TaiShan 2280 /BC11SPCD, BIOS 1.37 11/21/2017 [ 1623.548822] pstate: a0000005 (NzCv daif -PAN -UAO) [ 1623.553684] pc : string+0x28/0x98 [ 1623.557040] lr : vsnprintf+0x368/0x5e8 [ 1623.560837] sp : ffff000013213a80 [ 1623.564191] x29: ffff000013213a80 x28: ffff00001138abb5 [ 1623.569577] x27: ffff000013213c18 x26: ffff805f67d06049 [ 1623.574963] x25: 0000000000000000 x24: ffff00001138abb5 [ 1623.580349] x23: 0000000000000fb7 x22: ffff0000117ed000 [ 1623.585734] x21: ffff000011188fd8 x20: ffff805f67d07000 [ 1623.591119] x19: ffff805f67d06061 x18: ffffffffffffffff [ 1623.596505] x17: 0000000000000200 x16: 0000000000000000 [ 1623.601890] x15: ffff0000117ed748 x14: ffff805f67d07000 [ 1623.607276] x13: ffff805f67d0605e x12: 0000000000000000 [ 1623.612661] x11: 0000000000000000 x10: 0000000000000000 [ 1623.618046] x9 : 0000000000000000 x8 : 000000000000000f [ 1623.623432] x7 : ffff805f67d06061 x6 : fffffffffffffffe [ 1623.628817] x5 : 0000000000000012 x4 : ffff00000901d478 [ 1623.634203] x3 : ffff0a00ffffff04 x2 : ffff805f67d07000 [ 1623.639588] x1 : ffff805f67d07000 x0 : ffffffffffffffff [ 1623.644974] Process cat (pid: 11438, stack limit = 0x000000008d4cbc10) [ 1623.651592] Call trace: [ 1623.654068] string+0x28/0x98 [ 1623.657071] vsnprintf+0x368/0x5e8 [ 1623.660517] seq_vprintf+0x70/0x98 [ 1623.668009] seq_printf+0x7c/0xa0 [ 1623.675530] r_show+0xc8/0xf8 [ 1623.682558] seq_read+0x330/0x440 [ 1623.689877] proc_reg_read+0x78/0xd0 [ 1623.697346] __vfs_read+0x60/0x1a0 [ 1623.704564] vfs_read+0x94/0x150 [ 1623.711339] ksys_read+0x6c/0xd8 [ 1623.717939] __arm64_sys_read+0x24/0x30 [ 1623.725077] el0_svc_common+0x120/0x148 [ 1623.732035] el0_svc_handler+0x30/0x40 [ 1623.738757] el0_svc+0x8/0xc [ 1623.744520] Code: d1000406 aa0103e2 54000149 b4000080 (39400085) [ 1623.753441] ---[ end trace f91b6a4937de9835 ]--- [ 1623.760871] Kernel panic - not syncing: Fatal exception [ 1623.768935] SMP: stopping secondary CPUs [ 1623.775718] Kernel Offset: disabled [ 1623.781998] CPU features: 0x002,21006008 [ 1623.788777] Memory Limit: none [ 1623.798329] Starting crashdump kernel... [ 1623.805202] Bye! If io_setup is called successful in try_smi_init() but try_smi_init() goes out_err before calling ipmi_register_smi(), so ipmi_unregister_smi() will not be called while removing module. It leads to the resource that allocated in io_setup() can not be freed, but the name(DEVICE_NAME) of resource is freed while removing the module. It causes use-after-free when cat /proc/ioports. Fix this by calling io_cleanup() while try_smi_init() goes to out_err. and don't call io_cleanup() until io_setup() returns successful to avoid warning prints. Fixes: 93c303d2045b ("ipmi_si: Clean up shutdown a bit") Cc: stable@vger.kernel.org Reported-by: NuoHan Qiao <qiaonuohan@huawei.com> Suggested-by: Corey Minyard <cminyard@mvista.com> Signed-off-by: Yang Yingliang <yangyingliang@huawei.com> Signed-off-by: Corey Minyard <cminyard@mvista.com>
2019-01-28 11:08:54 +08:00
if (rv && new_smi->io.io_cleanup) {
new_smi->io.io_cleanup(&new_smi->io);
new_smi->io.io_cleanup = NULL;
}
return rv;
}
static int __init init_ipmi_si(void)
{
struct smi_info *e;
enum ipmi_addr_src type = SI_INVALID;
if (initialized)
return 0;
ipmi_hardcode_init();
pr_info("IPMI System Interface driver\n");
ipmi_si_platform_init();
ipmi_si_pci_init();
ipmi_si_parisc_init();
/* We prefer devices with interrupts, but in the case of a machine
with multiple BMCs we assume that there will be several instances
of a given type so if we succeed in registering a type then also
try to register everything else of the same type */
mutex_lock(&smi_infos_lock);
list_for_each_entry(e, &smi_infos, link) {
/* Try to register a device if it has an IRQ and we either
haven't successfully registered a device yet or this
device has the same type as one we successfully registered */
if (e->io.irq && (!type || e->io.addr_source == type)) {
if (!try_smi_init(e)) {
type = e->io.addr_source;
}
}
}
/* type will only have been set if we successfully registered an si */
if (type)
goto skip_fallback_noirq;
/* Fall back to the preferred device */
list_for_each_entry(e, &smi_infos, link) {
if (!e->io.irq && (!type || e->io.addr_source == type)) {
if (!try_smi_init(e)) {
type = e->io.addr_source;
}
}
}
skip_fallback_noirq:
initialized = true;
mutex_unlock(&smi_infos_lock);
if (type)
return 0;
mutex_lock(&smi_infos_lock);
if (unload_when_empty && list_empty(&smi_infos)) {
mutex_unlock(&smi_infos_lock);
cleanup_ipmi_si();
pr_warn("Unable to find any System Interface(s)\n");
return -ENODEV;
} else {
mutex_unlock(&smi_infos_lock);
return 0;
}
}
module_init(init_ipmi_si);
static void wait_msg_processed(struct smi_info *smi_info)
{
unsigned long jiffies_now;
long time_diff;
while (smi_info->curr_msg || (smi_info->si_state != SI_NORMAL)) {
jiffies_now = jiffies;
time_diff = (((long)jiffies_now - (long)smi_info->last_timeout_jiffies)
* SI_USEC_PER_JIFFY);
smi_event_handler(smi_info, time_diff);
schedule_timeout_uninterruptible(1);
}
}
static void shutdown_smi(void *send_info)
{
struct smi_info *smi_info = send_info;
if (smi_info->dev_group_added) {
device_remove_group(smi_info->io.dev, &ipmi_si_dev_attr_group);
smi_info->dev_group_added = false;
}
if (smi_info->io.dev)
dev_set_drvdata(smi_info->io.dev, NULL);
/*
* Make sure that interrupts, the timer and the thread are
* stopped and will not run again.
*/
smi_info->interrupt_disabled = true;
if (smi_info->io.irq_cleanup) {
smi_info->io.irq_cleanup(&smi_info->io);
smi_info->io.irq_cleanup = NULL;
}
stop_timer_and_thread(smi_info);
/*
* Wait until we know that we are out of any interrupt
* handlers might have been running before we freed the
* interrupt.
*/
synchronize_rcu();
/*
* Timeouts are stopped, now make sure the interrupts are off
* in the BMC. Note that timers and CPU interrupts are off,
* so no need for locks.
*/
wait_msg_processed(smi_info);
if (smi_info->handlers)
disable_si_irq(smi_info);
wait_msg_processed(smi_info);
if (smi_info->handlers)
smi_info->handlers->cleanup(smi_info->si_sm);
if (smi_info->io.addr_source_cleanup) {
smi_info->io.addr_source_cleanup(&smi_info->io);
smi_info->io.addr_source_cleanup = NULL;
}
if (smi_info->io.io_cleanup) {
smi_info->io.io_cleanup(&smi_info->io);
smi_info->io.io_cleanup = NULL;
}
kfree(smi_info->si_sm);
smi_info->si_sm = NULL;
smi_info->intf = NULL;
}
/*
* Must be called with smi_infos_lock held, to serialize the
* smi_info->intf check.
*/
static void cleanup_one_si(struct smi_info *smi_info)
{
if (!smi_info)
return;
list_del(&smi_info->link);
if (smi_info->intf)
ipmi_unregister_smi(smi_info->intf);
kfree(smi_info);
}
int ipmi_si_remove_by_dev(struct device *dev)
{
struct smi_info *e;
int rv = -ENOENT;
mutex_lock(&smi_infos_lock);
list_for_each_entry(e, &smi_infos, link) {
if (e->io.dev == dev) {
cleanup_one_si(e);
rv = 0;
break;
}
}
mutex_unlock(&smi_infos_lock);
return rv;
}
struct device *ipmi_si_remove_by_data(int addr_space, enum si_type si_type,
unsigned long addr)
{
/* remove */
struct smi_info *e, *tmp_e;
struct device *dev = NULL;
mutex_lock(&smi_infos_lock);
list_for_each_entry_safe(e, tmp_e, &smi_infos, link) {
if (e->io.addr_space != addr_space)
continue;
if (e->io.si_type != si_type)
continue;
if (e->io.addr_data == addr) {
dev = get_device(e->io.dev);
cleanup_one_si(e);
}
}
mutex_unlock(&smi_infos_lock);
return dev;
}
static void cleanup_ipmi_si(void)
{
struct smi_info *e, *tmp_e;
if (!initialized)
return;
ipmi_si_pci_shutdown();
ipmi_si_parisc_shutdown();
ipmi_si_platform_shutdown();
mutex_lock(&smi_infos_lock);
list_for_each_entry_safe(e, tmp_e, &smi_infos, link)
cleanup_one_si(e);
mutex_unlock(&smi_infos_lock);
ipmi_si_hardcode_exit();
ipmi_si_hotmod_exit();
}
module_exit(cleanup_ipmi_si);
MODULE_ALIAS("platform:dmi-ipmi-si");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Corey Minyard <minyard@mvista.com>");
MODULE_DESCRIPTION("Interface to the IPMI driver for the KCS, SMIC, and BT"
" system interfaces.");