aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc
diff options
context:
space:
mode:
authorAlan Stern <stern@rowland.harvard.edu>2006-03-27 04:16:30 -0500
committerLinus Torvalds <torvalds@g5.osdl.org>2006-03-27 11:44:50 -0500
commite041c683412d5bf44dc2b109053e3b837b71742d (patch)
tree9d271066ef379da0c0fb3b8cb4137abd5d2ebba0 /arch/powerpc
parent76b81e2b0e2241accebcc68e126bc5ab958661b9 (diff)
[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>
Diffstat (limited to 'arch/powerpc')
-rw-r--r--arch/powerpc/kernel/setup_64.c3
-rw-r--r--arch/powerpc/kernel/traps.c16
-rw-r--r--arch/powerpc/platforms/pseries/reconfig.c10
3 files changed, 15 insertions, 14 deletions
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 2f3fdad35594..e20c1fae3423 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -579,7 +579,8 @@ void __init setup_arch(char **cmdline_p)
579 panic_timeout = 180; 579 panic_timeout = 180;
580 580
581 if (ppc_md.panic) 581 if (ppc_md.panic)
582 notifier_chain_register(&panic_notifier_list, &ppc64_panic_block); 582 atomic_notifier_chain_register(&panic_notifier_list,
583 &ppc64_panic_block);
583 584
584 init_mm.start_code = PAGE_OFFSET; 585 init_mm.start_code = PAGE_OFFSET;
585 init_mm.end_code = (unsigned long) _etext; 586 init_mm.end_code = (unsigned long) _etext;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 98660aedeeb7..9763faab6739 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -74,19 +74,19 @@ EXPORT_SYMBOL(__debugger_dabr_match);
74EXPORT_SYMBOL(__debugger_fault_handler); 74EXPORT_SYMBOL(__debugger_fault_handler);
75#endif 75#endif
76 76
77struct notifier_block *powerpc_die_chain; 77ATOMIC_NOTIFIER_HEAD(powerpc_die_chain);
78static DEFINE_SPINLOCK(die_notifier_lock);
79 78
80int register_die_notifier(struct notifier_block *nb) 79int register_die_notifier(struct notifier_block *nb)
81{ 80{
82 int err = 0; 81 return atomic_notifier_chain_register(&powerpc_die_chain, nb);
83 unsigned long flags; 82}
83EXPORT_SYMBOL(register_die_notifier);
84 84
85 spin_lock_irqsave(&die_notifier_lock, flags); 85int unregister_die_notifier(struct notifier_block *nb)
86 err = notifier_chain_register(&powerpc_die_chain, nb); 86{
87 spin_unlock_irqrestore(&die_notifier_lock, flags); 87 return atomic_notifier_chain_unregister(&powerpc_die_chain, nb);
88 return err;
89} 88}
89EXPORT_SYMBOL(unregister_die_notifier);
90 90
91/* 91/*
92 * Trap & Exception support 92 * Trap & Exception support
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 86cfa6ecdcf3..5ad90676567a 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -94,16 +94,16 @@ static struct device_node *derive_parent(const char *path)
94 return parent; 94 return parent;
95} 95}
96 96
97static struct notifier_block *pSeries_reconfig_chain; 97static BLOCKING_NOTIFIER_HEAD(pSeries_reconfig_chain);
98 98
99int pSeries_reconfig_notifier_register(struct notifier_block *nb) 99int pSeries_reconfig_notifier_register(struct notifier_block *nb)
100{ 100{
101 return notifier_chain_register(&pSeries_reconfig_chain, nb); 101 return blocking_notifier_chain_register(&pSeries_reconfig_chain, nb);
102} 102}
103 103
104void pSeries_reconfig_notifier_unregister(struct notifier_block *nb) 104void pSeries_reconfig_notifier_unregister(struct notifier_block *nb)
105{ 105{
106 notifier_chain_unregister(&pSeries_reconfig_chain, nb); 106 blocking_notifier_chain_unregister(&pSeries_reconfig_chain, nb);
107} 107}
108 108
109static int pSeries_reconfig_add_node(const char *path, struct property *proplist) 109static int pSeries_reconfig_add_node(const char *path, struct property *proplist)
@@ -131,7 +131,7 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist
131 goto out_err; 131 goto out_err;
132 } 132 }
133 133
134 err = notifier_call_chain(&pSeries_reconfig_chain, 134 err = blocking_notifier_call_chain(&pSeries_reconfig_chain,
135 PSERIES_RECONFIG_ADD, np); 135 PSERIES_RECONFIG_ADD, np);
136 if (err == NOTIFY_BAD) { 136 if (err == NOTIFY_BAD) {
137 printk(KERN_ERR "Failed to add device node %s\n", path); 137 printk(KERN_ERR "Failed to add device node %s\n", path);
@@ -171,7 +171,7 @@ static int pSeries_reconfig_remove_node(struct device_node *np)
171 171
172 remove_node_proc_entries(np); 172 remove_node_proc_entries(np);
173 173
174 notifier_call_chain(&pSeries_reconfig_chain, 174 blocking_notifier_call_chain(&pSeries_reconfig_chain,
175 PSERIES_RECONFIG_REMOVE, np); 175 PSERIES_RECONFIG_REMOVE, np);
176 of_detach_node(np); 176 of_detach_node(np);
177 177