linux/arch/powerpc/platforms/pseries/reconfig.c

561 lines
12 KiB
C
Raw Normal View History

/*
* pSeries_reconfig.c - support for dynamic reconfiguration (including PCI
* Hotplug and Dynamic Logical Partitioning on RPA platforms).
*
* Copyright (C) 2005 Nathan Lynch
* Copyright (C) 2005 IBM Corporation
*
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License version
* 2 as published by the Free Software Foundation.
*/
#include <linux/kernel.h>
#include <linux/kref.h>
#include <linux/notifier.h>
#include <linux/proc_fs.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <asm/prom.h>
#include <asm/machdep.h>
#include <asm/uaccess.h>
#include <asm/pSeries_reconfig.h>
#include <asm/mmu.h>
/*
* Routines for "runtime" addition and removal of device tree nodes.
*/
#ifdef CONFIG_PROC_DEVICETREE
/*
* Add a node to /proc/device-tree.
*/
static void add_node_proc_entries(struct device_node *np)
{
struct proc_dir_entry *ent;
ent = proc_mkdir(strrchr(np->full_name, '/') + 1, np->parent->pde);
if (ent)
proc_device_tree_add_node(np, ent);
}
static void remove_node_proc_entries(struct device_node *np)
{
struct property *pp = np->properties;
struct device_node *parent = np->parent;
while (pp) {
remove_proc_entry(pp->name, np->pde);
pp = pp->next;
}
if (np->pde)
remove_proc_entry(np->pde->name, parent->pde);
}
#else /* !CONFIG_PROC_DEVICETREE */
static void add_node_proc_entries(struct device_node *np)
{
return;
}
static void remove_node_proc_entries(struct device_node *np)
{
return;
}
#endif /* CONFIG_PROC_DEVICETREE */
/**
* derive_parent - basically like dirname(1)
* @path: the full_name of a node to be added to the tree
*
* Returns the node which should be the parent of the node
* described by path. E.g., for path = "/foo/bar", returns
* the node with full_name = "/foo".
*/
static struct device_node *derive_parent(const char *path)
{
struct device_node *parent = NULL;
char *parent_path = "/";
size_t parent_path_len = strrchr(path, '/') - path + 1;
/* reject if path is "/" */
if (!strcmp(path, "/"))
return ERR_PTR(-EINVAL);
if (strrchr(path, '/') != path) {
parent_path = kmalloc(parent_path_len, GFP_KERNEL);
if (!parent_path)
return ERR_PTR(-ENOMEM);
strlcpy(parent_path, path, parent_path_len);
}
parent = of_find_node_by_path(parent_path);
if (!parent)
return ERR_PTR(-EINVAL);
if (strcmp(parent_path, "/"))
kfree(parent_path);
return parent;
}
BLOCKING_NOTIFIER_HEAD(pSeries_reconfig_chain);
int pSeries_reconfig_notifier_register(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 blocking_notifier_chain_register(&pSeries_reconfig_chain, nb);
}
void pSeries_reconfig_notifier_unregister(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
blocking_notifier_chain_unregister(&pSeries_reconfig_chain, nb);
}
static int pSeries_reconfig_add_node(const char *path, struct property *proplist)
{
struct device_node *np;
int err = -ENOMEM;
np = kzalloc(sizeof(*np), GFP_KERNEL);
if (!np)
goto out_err;
np->full_name = kstrdup(path, GFP_KERNEL);
if (!np->full_name)
goto out_err;
np->properties = proplist;
of_node_set_flag(np, OF_DYNAMIC);
kref_init(&np->kref);
np->parent = derive_parent(path);
if (IS_ERR(np->parent)) {
err = PTR_ERR(np->parent);
goto out_err;
}
[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 = blocking_notifier_call_chain(&pSeries_reconfig_chain,
PSERIES_RECONFIG_ADD, np);
if (err == NOTIFY_BAD) {
printk(KERN_ERR "Failed to add device node %s\n", path);
err = -ENOMEM; /* For now, safe to assume kmalloc failure */
goto out_err;
}
of_attach_node(np);
add_node_proc_entries(np);
of_node_put(np->parent);
return 0;
out_err:
if (np) {
of_node_put(np->parent);
kfree(np->full_name);
kfree(np);
}
return err;
}
static int pSeries_reconfig_remove_node(struct device_node *np)
{
struct device_node *parent, *child;
parent = of_get_parent(np);
if (!parent)
return -EINVAL;
if ((child = of_get_next_child(np, NULL))) {
of_node_put(child);
of_node_put(parent);
return -EBUSY;
}
remove_node_proc_entries(np);
[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
blocking_notifier_call_chain(&pSeries_reconfig_chain,
PSERIES_RECONFIG_REMOVE, np);
of_detach_node(np);
of_node_put(parent);
of_node_put(np); /* Must decrement the refcount */
return 0;
}
/*
* /proc/powerpc/ofdt - yucky binary interface for adding and removing
* OF device nodes. Should be deprecated as soon as we get an
* in-kernel wrapper for the RTAS ibm,configure-connector call.
*/
static void release_prop_list(const struct property *prop)
{
struct property *next;
for (; prop; prop = next) {
next = prop->next;
kfree(prop->name);
kfree(prop->value);
kfree(prop);
}
}
/**
* parse_next_property - process the next property from raw input buffer
* @buf: input buffer, must be nul-terminated
* @end: end of the input buffer + 1, for validation
* @name: return value; set to property name in buf
* @length: return value; set to length of value
* @value: return value; set to the property value in buf
*
* Note that the caller must make copies of the name and value returned,
* this function does no allocation or copying of the data. Return value
* is set to the next name in buf, or NULL on error.
*/
static char * parse_next_property(char *buf, char *end, char **name, int *length,
unsigned char **value)
{
char *tmp;
*name = buf;
tmp = strchr(buf, ' ');
if (!tmp) {
printk(KERN_ERR "property parse failed in %s at line %d\n",
__func__, __LINE__);
return NULL;
}
*tmp = '\0';
if (++tmp >= end) {
printk(KERN_ERR "property parse failed in %s at line %d\n",
__func__, __LINE__);
return NULL;
}
/* now we're on the length */
*length = -1;
*length = simple_strtoul(tmp, &tmp, 10);
if (*length == -1) {
printk(KERN_ERR "property parse failed in %s at line %d\n",
__func__, __LINE__);
return NULL;
}
if (*tmp != ' ' || ++tmp >= end) {
printk(KERN_ERR "property parse failed in %s at line %d\n",
__func__, __LINE__);
return NULL;
}
/* now we're on the value */
*value = tmp;
tmp += *length;
if (tmp > end) {
printk(KERN_ERR "property parse failed in %s at line %d\n",
__func__, __LINE__);
return NULL;
}
else if (tmp < end && *tmp != ' ' && *tmp != '\0') {
printk(KERN_ERR "property parse failed in %s at line %d\n",
__func__, __LINE__);
return NULL;
}
tmp++;
/* and now we should be on the next name, or the end */
return tmp;
}
static struct property *new_property(const char *name, const int length,
const unsigned char *value, struct property *last)
{
struct property *new = kzalloc(sizeof(*new), GFP_KERNEL);
if (!new)
return NULL;
if (!(new->name = kmalloc(strlen(name) + 1, GFP_KERNEL)))
goto cleanup;
if (!(new->value = kmalloc(length + 1, GFP_KERNEL)))
goto cleanup;
strcpy(new->name, name);
memcpy(new->value, value, length);
*(((char *)new->value) + length) = 0;
new->length = length;
new->next = last;
return new;
cleanup:
kfree(new->name);
kfree(new->value);
kfree(new);
return NULL;
}
static int do_add_node(char *buf, size_t bufsize)
{
char *path, *end, *name;
struct device_node *np;
struct property *prop = NULL;
unsigned char* value;
int length, rv = 0;
end = buf + bufsize;
path = buf;
buf = strchr(buf, ' ');
if (!buf)
return -EINVAL;
*buf = '\0';
buf++;
if ((np = of_find_node_by_path(path))) {
of_node_put(np);
return -EINVAL;
}
/* rv = build_prop_list(tmp, bufsize - (tmp - buf), &proplist); */
while (buf < end &&
(buf = parse_next_property(buf, end, &name, &length, &value))) {
struct property *last = prop;
prop = new_property(name, length, value, last);
if (!prop) {
rv = -ENOMEM;
prop = last;
goto out;
}
}
if (!buf) {
rv = -EINVAL;
goto out;
}
rv = pSeries_reconfig_add_node(path, prop);
out:
if (rv)
release_prop_list(prop);
return rv;
}
static int do_remove_node(char *buf)
{
struct device_node *node;
int rv = -ENODEV;
if ((node = of_find_node_by_path(buf)))
rv = pSeries_reconfig_remove_node(node);
of_node_put(node);
return rv;
}
static char *parse_node(char *buf, size_t bufsize, struct device_node **npp)
{
char *handle_str;
phandle handle;
*npp = NULL;
handle_str = buf;
buf = strchr(buf, ' ');
if (!buf)
return NULL;
*buf = '\0';
buf++;
handle = simple_strtoul(handle_str, NULL, 0);
*npp = of_find_node_by_phandle(handle);
return buf;
}
static int do_add_property(char *buf, size_t bufsize)
{
struct property *prop = NULL;
struct device_node *np;
unsigned char *value;
char *name, *end;
int length;
end = buf + bufsize;
buf = parse_node(buf, bufsize, &np);
if (!np)
return -ENODEV;
if (parse_next_property(buf, end, &name, &length, &value) == NULL)
return -EINVAL;
prop = new_property(name, length, value, NULL);
if (!prop)
return -ENOMEM;
prom_add_property(np, prop);
return 0;
}
static int do_remove_property(char *buf, size_t bufsize)
{
struct device_node *np;
char *tmp;
struct property *prop;
buf = parse_node(buf, bufsize, &np);
if (!np)
return -ENODEV;
tmp = strchr(buf,' ');
if (tmp)
*tmp = '\0';
if (strlen(buf) == 0)
return -EINVAL;
prop = of_find_property(np, buf, NULL);
return prom_remove_property(np, prop);
}
static int do_update_property(char *buf, size_t bufsize)
{
struct device_node *np;
unsigned char *value;
char *name, *end, *next_prop;
int rc, length;
struct property *newprop, *oldprop;
buf = parse_node(buf, bufsize, &np);
end = buf + bufsize;
if (!np)
return -ENODEV;
next_prop = parse_next_property(buf, end, &name, &length, &value);
if (!next_prop)
return -EINVAL;
newprop = new_property(name, length, value, NULL);
if (!newprop)
return -ENOMEM;
if (!strcmp(name, "slb-size") || !strcmp(name, "ibm,slb-size"))
slb_set_size(*(int *)value);
oldprop = of_find_property(np, name,NULL);
if (!oldprop) {
if (strlen(name))
return prom_add_property(np, newprop);
return -ENODEV;
}
rc = prom_update_property(np, newprop, oldprop);
if (rc)
return rc;
/* For memory under the ibm,dynamic-reconfiguration-memory node
* of the device tree, adding and removing memory is just an update
* to the ibm,dynamic-memory property instead of adding/removing a
* memory node in the device tree. For these cases we still need to
* involve the notifier chain.
*/
if (!strcmp(name, "ibm,dynamic-memory")) {
int action;
next_prop = parse_next_property(next_prop, end, &name,
&length, &value);
if (!next_prop)
return -EINVAL;
if (!strcmp(name, "add"))
action = PSERIES_DRCONF_MEM_ADD;
else
action = PSERIES_DRCONF_MEM_REMOVE;
rc = blocking_notifier_call_chain(&pSeries_reconfig_chain,
action, value);
if (rc == NOTIFY_BAD) {
rc = prom_update_property(np, oldprop, newprop);
return -ENOMEM;
}
}
return 0;
}
/**
* ofdt_write - perform operations on the Open Firmware device tree
*
* @file: not used
* @buf: command and arguments
* @count: size of the command buffer
* @off: not used
*
* Operations supported at this time are addition and removal of
* whole nodes along with their properties. Operations on individual
* properties are not implemented (yet).
*/
static ssize_t ofdt_write(struct file *file, const char __user *buf, size_t count,
loff_t *off)
{
int rv = 0;
char *kbuf;
char *tmp;
if (!(kbuf = kmalloc(count + 1, GFP_KERNEL))) {
rv = -ENOMEM;
goto out;
}
if (copy_from_user(kbuf, buf, count)) {
rv = -EFAULT;
goto out;
}
kbuf[count] = '\0';
tmp = strchr(kbuf, ' ');
if (!tmp) {
rv = -EINVAL;
goto out;
}
*tmp = '\0';
tmp++;
if (!strcmp(kbuf, "add_node"))
rv = do_add_node(tmp, count - (tmp - kbuf));
else if (!strcmp(kbuf, "remove_node"))
rv = do_remove_node(tmp);
else if (!strcmp(kbuf, "add_property"))
rv = do_add_property(tmp, count - (tmp - kbuf));
else if (!strcmp(kbuf, "remove_property"))
rv = do_remove_property(tmp, count - (tmp - kbuf));
else if (!strcmp(kbuf, "update_property"))
rv = do_update_property(tmp, count - (tmp - kbuf));
else
rv = -EINVAL;
out:
kfree(kbuf);
return rv ? rv : count;
}
static const struct file_operations ofdt_fops = {
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-16 00:52:59 +08:00
.write = ofdt_write,
.llseek = noop_llseek,
};
/* create /proc/powerpc/ofdt write-only by root */
static int proc_ppc64_create_ofdt(void)
{
struct proc_dir_entry *ent;
if (!machine_is(pseries))
return 0;
ent = proc_create("powerpc/ofdt", S_IWUSR, NULL, &ofdt_fops);
if (ent)
ent->size = 0;
return 0;
}
__initcall(proc_ppc64_create_ofdt);