From e041c683412d5bf44dc2b109053e3b837b71742d Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 27 Mar 2006 01:16:30 -0800 Subject: [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 Signed-off-by: Chandra Seetharaman Signed-off-by: Jes Sorensen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/macintosh/adb.c | 11 +++++++---- drivers/macintosh/adbhid.c | 3 ++- drivers/macintosh/via-pmu.c | 2 +- drivers/macintosh/via-pmu68k.c | 7 ++++--- drivers/macintosh/windfarm_core.c | 8 ++++---- 5 files changed, 18 insertions(+), 13 deletions(-) (limited to 'drivers/macintosh') diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c index d2ead1776c16..34fcabac5fdb 100644 --- a/drivers/macintosh/adb.c +++ b/drivers/macintosh/adb.c @@ -80,7 +80,7 @@ static struct adb_driver *adb_driver_list[] = { static struct class *adb_dev_class; struct adb_driver *adb_controller; -struct notifier_block *adb_client_list = NULL; +BLOCKING_NOTIFIER_HEAD(adb_client_list); static int adb_got_sleep; static int adb_inited; static pid_t adb_probe_task_pid; @@ -354,7 +354,8 @@ adb_notify_sleep(struct pmu_sleep_notifier *self, int when) /* Stop autopoll */ if (adb_controller->autopoll) adb_controller->autopoll(0); - ret = notifier_call_chain(&adb_client_list, ADB_MSG_POWERDOWN, NULL); + ret = blocking_notifier_call_chain(&adb_client_list, + ADB_MSG_POWERDOWN, NULL); if (ret & NOTIFY_STOP_MASK) { up(&adb_probe_mutex); return PBOOK_SLEEP_REFUSE; @@ -391,7 +392,8 @@ do_adb_reset_bus(void) if (adb_controller->autopoll) adb_controller->autopoll(0); - nret = notifier_call_chain(&adb_client_list, ADB_MSG_PRE_RESET, NULL); + nret = blocking_notifier_call_chain(&adb_client_list, + ADB_MSG_PRE_RESET, NULL); if (nret & NOTIFY_STOP_MASK) { if (adb_controller->autopoll) adb_controller->autopoll(autopoll_devs); @@ -426,7 +428,8 @@ do_adb_reset_bus(void) } up(&adb_handler_sem); - nret = notifier_call_chain(&adb_client_list, ADB_MSG_POST_RESET, NULL); + nret = blocking_notifier_call_chain(&adb_client_list, + ADB_MSG_POST_RESET, NULL); if (nret & NOTIFY_STOP_MASK) return -EBUSY; diff --git a/drivers/macintosh/adbhid.c b/drivers/macintosh/adbhid.c index c0b46bceb5df..f5779a73184d 100644 --- a/drivers/macintosh/adbhid.c +++ b/drivers/macintosh/adbhid.c @@ -1214,7 +1214,8 @@ static int __init adbhid_init(void) adbhid_probe(); - notifier_chain_register(&adb_client_list, &adbhid_adb_notifier); + blocking_notifier_chain_register(&adb_client_list, + &adbhid_adb_notifier); return 0; } diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c index 4f5f3abc9cb3..0b5ff553e39a 100644 --- a/drivers/macintosh/via-pmu.c +++ b/drivers/macintosh/via-pmu.c @@ -187,7 +187,7 @@ extern int disable_kernel_backlight; int __fake_sleep; int asleep; -struct notifier_block *sleep_notifier_list; +BLOCKING_NOTIFIER_HEAD(sleep_notifier_list); #ifdef CONFIG_ADB static int adb_dev_map = 0; diff --git a/drivers/macintosh/via-pmu68k.c b/drivers/macintosh/via-pmu68k.c index f08e52f2107b..35b70323e7e3 100644 --- a/drivers/macintosh/via-pmu68k.c +++ b/drivers/macintosh/via-pmu68k.c @@ -102,7 +102,7 @@ static int pmu_kind = PMU_UNKNOWN; static int pmu_fully_inited = 0; int asleep; -struct notifier_block *sleep_notifier_list; +BLOCKING_NOTIFIER_HEAD(sleep_notifier_list); static int pmu_probe(void); static int pmu_init(void); @@ -913,7 +913,8 @@ int powerbook_sleep(void) struct adb_request sleep_req; /* Notify device drivers */ - ret = notifier_call_chain(&sleep_notifier_list, PBOOK_SLEEP, NULL); + ret = blocking_notifier_call_chain(&sleep_notifier_list, + PBOOK_SLEEP, NULL); if (ret & NOTIFY_STOP_MASK) return -EBUSY; @@ -984,7 +985,7 @@ int powerbook_sleep(void) enable_irq(i); /* Notify drivers */ - notifier_call_chain(&sleep_notifier_list, PBOOK_WAKE, NULL); + blocking_notifier_call_chain(&sleep_notifier_list, PBOOK_WAKE, NULL); /* reenable ADB autopoll */ pmu_adb_autopoll(adb_dev_map); diff --git a/drivers/macintosh/windfarm_core.c b/drivers/macintosh/windfarm_core.c index 6c0ba04bc57a..ab3faa702d58 100644 --- a/drivers/macintosh/windfarm_core.c +++ b/drivers/macintosh/windfarm_core.c @@ -52,7 +52,7 @@ static LIST_HEAD(wf_controls); static LIST_HEAD(wf_sensors); static DEFINE_MUTEX(wf_lock); -static struct notifier_block *wf_client_list; +static BLOCKING_NOTIFIER_HEAD(wf_client_list); static int wf_client_count; static unsigned int wf_overtemp; static unsigned int wf_overtemp_counter; @@ -68,7 +68,7 @@ static struct platform_device wf_platform_device = { static inline void wf_notify(int event, void *param) { - notifier_call_chain(&wf_client_list, event, param); + blocking_notifier_call_chain(&wf_client_list, event, param); } int wf_critical_overtemp(void) @@ -398,7 +398,7 @@ int wf_register_client(struct notifier_block *nb) struct wf_sensor *sr; mutex_lock(&wf_lock); - rc = notifier_chain_register(&wf_client_list, nb); + rc = blocking_notifier_chain_register(&wf_client_list, nb); if (rc != 0) goto bail; wf_client_count++; @@ -417,7 +417,7 @@ EXPORT_SYMBOL_GPL(wf_register_client); int wf_unregister_client(struct notifier_block *nb) { mutex_lock(&wf_lock); - notifier_chain_unregister(&wf_client_list, nb); + blocking_notifier_chain_unregister(&wf_client_list, nb); wf_client_count++; if (wf_client_count == 0) wf_stop_thread(); -- cgit v1.2.2