From 28f65c11f2ffb3957259dece647a24f8ad2e241b Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 9 Jun 2011 09:13:32 -0700 Subject: treewide: Convert uses of struct resource to resource_size(ptr) Several fixes as well where the +1 was missing. Done via coccinelle scripts like: @@ struct resource *ptr; @@ - ptr->end - ptr->start + 1 + resource_size(ptr) and some grep and typing. Mostly uncompiled, no cross-compilers. Signed-off-by: Joe Perches Signed-off-by: Jiri Kosina --- kernel/kexec.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/kexec.c b/kernel/kexec.c index 8d814cbc8109..296fbc84d659 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1095,7 +1095,7 @@ size_t crash_get_memory_size(void) size_t size = 0; mutex_lock(&kexec_mutex); if (crashk_res.end != crashk_res.start) - size = crashk_res.end - crashk_res.start + 1; + size = resource_size(&crashk_res); mutex_unlock(&kexec_mutex); return size; } -- cgit v1.2.3 From d8bf4ca9ca9576548628344c9725edd3786e90b1 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 8 Jul 2011 14:39:41 +0200 Subject: rcu: treewide: Do not use rcu_read_lock_held when calling rcu_dereference_check Since ca5ecddf (rcu: define __rcu address space modifier for sparse) rcu_dereference_check use rcu_read_lock_held as a part of condition automatically so callers do not have to do that as well. Signed-off-by: Michal Hocko Acked-by: Paul E. McKenney Signed-off-by: Jiri Kosina --- kernel/cgroup.c | 8 ++------ kernel/exit.c | 1 - kernel/pid.c | 1 - kernel/rcutorture.c | 2 -- kernel/sched.c | 1 - 5 files changed, 2 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2731d115d725..5ae71d6e274b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1697,7 +1697,6 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) { char *start; struct dentry *dentry = rcu_dereference_check(cgrp->dentry, - rcu_read_lock_held() || cgroup_lock_is_held()); if (!dentry || cgrp == dummytop) { @@ -1723,7 +1722,6 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen) break; dentry = rcu_dereference_check(cgrp->dentry, - rcu_read_lock_held() || cgroup_lock_is_held()); if (!cgrp->parent) continue; @@ -4813,8 +4811,7 @@ unsigned short css_id(struct cgroup_subsys_state *css) * on this or this is under rcu_read_lock(). Once css->id is allocated, * it's unchanged until freed. */ - cssid = rcu_dereference_check(css->id, - rcu_read_lock_held() || atomic_read(&css->refcnt)); + cssid = rcu_dereference_check(css->id, atomic_read(&css->refcnt)); if (cssid) return cssid->id; @@ -4826,8 +4823,7 @@ unsigned short css_depth(struct cgroup_subsys_state *css) { struct css_id *cssid; - cssid = rcu_dereference_check(css->id, - rcu_read_lock_held() || atomic_read(&css->refcnt)); + cssid = rcu_dereference_check(css->id, atomic_read(&css->refcnt)); if (cssid) return cssid->depth; diff --git a/kernel/exit.c b/kernel/exit.c index 20a406471525..07dc154fc799 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -85,7 +85,6 @@ static void __exit_signal(struct task_struct *tsk) struct tty_struct *uninitialized_var(tty); sighand = rcu_dereference_check(tsk->sighand, - rcu_read_lock_held() || lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); diff --git a/kernel/pid.c b/kernel/pid.c index 57a8346a270e..e432057f3b21 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -405,7 +405,6 @@ struct task_struct *pid_task(struct pid *pid, enum pid_type type) if (pid) { struct hlist_node *first; first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), - rcu_read_lock_held() || lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pids[(type)].node); diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 2e138db03382..ced72102adc2 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -941,7 +941,6 @@ static void rcu_torture_timer(unsigned long unused) idx = cur_ops->readlock(); completed = cur_ops->completed(); p = rcu_dereference_check(rcu_torture_current, - rcu_read_lock_held() || rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || srcu_read_lock_held(&srcu_ctl)); @@ -1002,7 +1001,6 @@ rcu_torture_reader(void *arg) idx = cur_ops->readlock(); completed = cur_ops->completed(); p = rcu_dereference_check(rcu_torture_current, - rcu_read_lock_held() || rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || srcu_read_lock_held(&srcu_ctl)); diff --git a/kernel/sched.c b/kernel/sched.c index 3f2e502d609b..71e5a25a8a58 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -581,7 +581,6 @@ static inline int cpu_of(struct rq *rq) #define rcu_dereference_check_sched_domain(p) \ rcu_dereference_check((p), \ - rcu_read_lock_held() || \ lockdep_is_held(&sched_domains_mutex)) /* -- cgit v1.2.3 From 2dc98fd3206f8106520eced769781a21a20707ca Mon Sep 17 00:00:00 2001 From: Michael Witten Date: Fri, 8 Jul 2011 21:11:16 +0000 Subject: doc: Konfig: Documentation/power/{pm => apm-acpi}.txt Signed-off-by: Michael Witten Signed-off-by: Jiri Kosina --- kernel/power/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 87f4d24b55b0..bcd8fce351b7 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -193,8 +193,8 @@ config APM_EMULATION notification of APM "events" (e.g. battery status change). In order to use APM, you will need supporting software. For location - and more information, read and the - Battery Powered Linux mini-HOWTO, available from + and more information, read + and the Battery Powered Linux mini-HOWTO, available from . This driver does not spin down disk drives (see the hdparm(8) -- cgit v1.2.3 From 4aede84b33d6beb401136a3deca0651ae07c5e99 Mon Sep 17 00:00:00 2001 From: Justin TerAvest Date: Tue, 12 Jul 2011 08:31:45 +0200 Subject: fixlet: Remove fs_excl from struct task. fs_excl is a poor man's priority inheritance for filesystems to hint to the block layer that an operation is important. It was never clearly specified, not widely adopted, and will not prevent starvation in many cases (like across cgroups). fs_excl was introduced with the time sliced CFQ IO scheduler, to indicate when a process held FS exclusive resources and thus needed a boost. It doesn't cover all file systems, and it was never fully complete. Lets kill it. Signed-off-by: Justin TerAvest Signed-off-by: Jens Axboe --- kernel/exit.c | 1 - kernel/fork.c | 1 - 2 files changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/exit.c b/kernel/exit.c index f2b321bae440..b412df45ea6c 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -906,7 +906,6 @@ NORET_TYPE void do_exit(long code) profile_task_exit(tsk); - WARN_ON(atomic_read(&tsk->fs_excl)); WARN_ON(blk_needs_flush_plug(tsk)); if (unlikely(in_interrupt())) diff --git a/kernel/fork.c b/kernel/fork.c index 0276c30401a0..30a0e8607223 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -291,7 +291,6 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) /* One for us, one for whoever does the "release_task()" (usually parent) */ atomic_set(&tsk->usage,2); - atomic_set(&tsk->fs_excl, 0); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif -- cgit v1.2.3 From e78e8f2d8318851d0911039999c903a6082bef2e Mon Sep 17 00:00:00 2001 From: Peter Foley Date: Tue, 5 Jul 2011 19:42:18 -0400 Subject: kernel: prevent unnecessary rebuilding due to config_data.gz When IKCONFIG is built-in make oldconfig will cause the kernel to be relinked even if .config didn't change. This happens because of a config_data.gz dependency on .config. This patch changes the if_changed to a filechk so that config_data.h is only rebuilt when the contents have actually changed. Signed-off-by: Peter Foley Signed-off-by: Michal Marek --- kernel/Makefile | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/Makefile b/kernel/Makefile index 2d64cfcc8b42..d06467fc8f7c 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -125,11 +125,10 @@ targets += config_data.gz $(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE $(call if_changed,gzip) -quiet_cmd_ikconfiggz = IKCFG $@ - cmd_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;") > $@ + filechk_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;") targets += config_data.h $(obj)/config_data.h: $(obj)/config_data.gz FORCE - $(call if_changed,ikconfiggz) + $(call filechk,ikconfiggz) $(obj)/time.o: $(obj)/timeconst.h -- cgit v1.2.3 From 2efaca927f5cd7ecd0f1554b8f9b6a9a2c329c03 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Mon, 25 Jul 2011 17:12:32 -0700 Subject: mm/futex: fix futex writes on archs with SW tracking of dirty & young I haven't reproduced it myself but the fail scenario is that on such machines (notably ARM and some embedded powerpc), if you manage to hit that futex path on a writable page whose dirty bit has gone from the PTE, you'll livelock inside the kernel from what I can tell. It will go in a loop of trying the atomic access, failing, trying gup to "fix it up", getting succcess from gup, go back to the atomic access, failing again because dirty wasn't fixed etc... So I think you essentially hang in the kernel. The scenario is probably rare'ish because affected architecture are embedded and tend to not swap much (if at all) so we probably rarely hit the case where dirty is missing or young is missing, but I think Shan has a piece of SW that can reliably reproduce it using a shared writable mapping & fork or something like that. On archs who use SW tracking of dirty & young, a page without dirty is effectively mapped read-only and a page without young unaccessible in the PTE. Additionally, some architectures might lazily flush the TLB when relaxing write protection (by doing only a local flush), and expect a fault to invalidate the stale entry if it's still present on another processor. The futex code assumes that if the "in_atomic()" access -EFAULT's, it can "fix it up" by causing get_user_pages() which would then be equivalent to taking the fault. However that isn't the case. get_user_pages() will not call handle_mm_fault() in the case where the PTE seems to have the right permissions, regardless of the dirty and young state. It will eventually update those bits ... in the struct page, but not in the PTE. Additionally, it will not handle the lazy TLB flushing that can be required by some architectures in the fault case. Basically, gup is the wrong interface for the job. The patch provides a more appropriate one which boils down to just calling handle_mm_fault() since what we are trying to do is simulate a real page fault. The futex code currently attempts to write to user memory within a pagefault disabled section, and if that fails, tries to fix it up using get_user_pages(). This doesn't work on archs where the dirty and young bits are maintained by software, since they will gate access permission in the TLB, and will not be updated by gup(). In addition, there's an expectation on some archs that a spurious write fault triggers a local TLB flush, and that is missing from the picture as well. I decided that adding those "features" to gup() would be too much for this already too complex function, and instead added a new simpler fixup_user_fault() which is essentially a wrapper around handle_mm_fault() which the futex code can call. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix some nits Darren saw, fiddle comment layout] Signed-off-by: Benjamin Herrenschmidt Reported-by: Shan Hai Tested-by: Shan Hai Cc: David Laight Acked-by: Peter Zijlstra Cc: Darren Hart Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/futex.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 3fbc76cbb9aa..0a308970c24a 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -355,8 +355,8 @@ static int fault_in_user_writeable(u32 __user *uaddr) int ret; down_read(&mm->mmap_sem); - ret = get_user_pages(current, mm, (unsigned long)uaddr, - 1, 1, 0, NULL, NULL); + ret = fixup_user_fault(current, mm, (unsigned long)uaddr, + FAULT_FLAG_WRITE); up_read(&mm->mmap_sem); return ret < 0 ? ret : 0; -- cgit v1.2.3 From ae891a1b93bf62e9aaa116a7a71312375047fc9f Mon Sep 17 00:00:00 2001 From: Maxin B John Date: Mon, 25 Jul 2011 17:12:59 -0700 Subject: devres: fix possible use after free devres uses the pointer value as key after it's freed, which is safe but triggers spurious use-after-free warnings on some static analysis tools. Rearrange code to avoid such warnings. Signed-off-by: Maxin B. John Reviewed-by: Rolf Eike Beer Acked-by: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/irq/devres.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c index 1ef4ffcdfa55..bd8e788d71e0 100644 --- a/kernel/irq/devres.c +++ b/kernel/irq/devres.c @@ -87,8 +87,8 @@ void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id) { struct irq_devres match_data = { irq, dev_id }; - free_irq(irq, dev_id); WARN_ON(devres_destroy(dev, devm_irq_release, devm_irq_match, &match_data)); + free_irq(irq, dev_id); } EXPORT_SYMBOL(devm_free_irq); -- cgit v1.2.3 From c5f41752fd37979dbaec61dc59c7ece0606ddf7e Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Mon, 25 Jul 2011 17:13:10 -0700 Subject: notifiers: sys: move reboot notifiers into reboot.h It is not necessary to share the same notifier.h. This patch already moves register_reboot_notifier() and unregister_reboot_notifier() from kernel/notifier.c to kernel/sys.c. [amwang@redhat.com: make allyesconfig succeed on ppc64] Signed-off-by: WANG Cong Cc: David Miller Cc: "Rafael J. Wysocki" Cc: Greg KH Signed-off-by: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/notifier.c | 31 ------------------------------- kernel/sys.c | 32 +++++++++++++++++++++++++++++++- 2 files changed, 31 insertions(+), 32 deletions(-) (limited to 'kernel') diff --git a/kernel/notifier.c b/kernel/notifier.c index 2488ba7eb568..8d7b435806c9 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -525,37 +525,6 @@ void srcu_init_notifier_head(struct srcu_notifier_head *nh) } EXPORT_SYMBOL_GPL(srcu_init_notifier_head); -/** - * register_reboot_notifier - Register function to be called at reboot time - * @nb: Info about notifier function to be called - * - * Registers a function with the list of functions - * to be called at reboot time. - * - * Currently always returns zero, as blocking_notifier_chain_register() - * always returns zero. - */ -int register_reboot_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_register(&reboot_notifier_list, nb); -} -EXPORT_SYMBOL(register_reboot_notifier); - -/** - * unregister_reboot_notifier - Unregister previously registered reboot notifier - * @nb: Hook to be unregistered - * - * Unregisters a previously registered reboot - * notifier function. - * - * Returns zero on success, or %-ENOENT on failure. - */ -int unregister_reboot_notifier(struct notifier_block *nb) -{ - return blocking_notifier_chain_unregister(&reboot_notifier_list, nb); -} -EXPORT_SYMBOL(unregister_reboot_notifier); - static ATOMIC_NOTIFIER_HEAD(die_chain); int notrace __kprobes notify_die(enum die_val val, const char *str, diff --git a/kernel/sys.c b/kernel/sys.c index e4128b278f23..a101ba36c444 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -8,7 +8,6 @@ #include #include #include -#include #include #include #include @@ -319,6 +318,37 @@ void kernel_restart_prepare(char *cmd) syscore_shutdown(); } +/** + * register_reboot_notifier - Register function to be called at reboot time + * @nb: Info about notifier function to be called + * + * Registers a function with the list of functions + * to be called at reboot time. + * + * Currently always returns zero, as blocking_notifier_chain_register() + * always returns zero. + */ +int register_reboot_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&reboot_notifier_list, nb); +} +EXPORT_SYMBOL(register_reboot_notifier); + +/** + * unregister_reboot_notifier - Unregister previously registered reboot notifier + * @nb: Hook to be unregistered + * + * Unregisters a previously registered reboot + * notifier function. + * + * Returns zero on success, or %-ENOENT on failure. + */ +int unregister_reboot_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&reboot_notifier_list, nb); +} +EXPORT_SYMBOL(unregister_reboot_notifier); + /** * kernel_restart - reboot the system * @cmd: pointer to buffer containing command to execute for restart -- cgit v1.2.3 From 626a0312514a121a90b4478cbde111ffc6826ae2 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 25 Jul 2011 17:13:12 -0700 Subject: kernel/configs.c: include MODULE_*() when CONFIG_IKCONFIG_PROC=n If CONFIG_IKCONFIG=m but CONFIG_IKCONFIG_PROC=n we get a module that has no MODULE_LICENSE definition. Move the MODULE_*() definitions outside the CONFIG_IKCONFIG_PROC #ifdef to prevent this configuration from tainting the kernel. Signed-off-by: Stephen Boyd Acked-by: Randy Dunlap Acked-by: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/configs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/configs.c b/kernel/configs.c index b4066b44a99d..42e8fa075eed 100644 --- a/kernel/configs.c +++ b/kernel/configs.c @@ -92,8 +92,8 @@ static void __exit ikconfig_cleanup(void) module_init(ikconfig_init); module_exit(ikconfig_cleanup); +#endif /* CONFIG_IKCONFIG_PROC */ + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Randy Dunlap"); MODULE_DESCRIPTION("Echo the kernel .config file used to build the kernel"); - -#endif /* CONFIG_IKCONFIG_PROC */ -- cgit v1.2.3 From 778d3b0ff0654ad7092bf823fd32010066b12365 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 26 Jul 2011 16:08:30 -0700 Subject: cpusets: randomize node rotor used in cpuset_mem_spread_node() [ This patch has already been accepted as commit 0ac0c0d0f837 but later reverted (commit 35926ff5fba8) because it itroduced arch specific __node_random which was defined only for x86 code so it broke other archs. This is a followup without any arch specific code. Other than that there are no functional changes.] Some workloads that create a large number of small files tend to assign too many pages to node 0 (multi-node systems). Part of the reason is that the rotor (in cpuset_mem_spread_node()) used to assign nodes starts at node 0 for newly created tasks. This patch changes the rotor to be initialized to a random node number of the cpuset. [akpm@linux-foundation.org: fix layout] [Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration] [mhocko@suse.cz: Make it arch independent] [akpm@linux-foundation.org: fix CONFIG_NUMA=y, MAX_NUMNODES>1 build] Signed-off-by: Jack Steiner Signed-off-by: Lee Schermerhorn Signed-off-by: Michal Hocko Reviewed-by: KOSAKI Motohiro Cc: Christoph Lameter Cc: Pekka Enberg Cc: Paul Menage Cc: Jack Steiner Cc: Robin Holt Cc: David Rientjes Cc: Christoph Lameter Cc: David Rientjes Cc: Jack Steiner Cc: KOSAKI Motohiro Cc: Lee Schermerhorn Cc: Michal Hocko Cc: Paul Menage Cc: Pekka Enberg Cc: Robin Holt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 8 ++++++++ kernel/fork.c | 4 ++++ 2 files changed, 12 insertions(+) (limited to 'kernel') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 9c9b7545c810..f8bc977ccbbe 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2460,11 +2460,19 @@ static int cpuset_spread_node(int *rotor) int cpuset_mem_spread_node(void) { + if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) + current->cpuset_mem_spread_rotor = + node_random(¤t->mems_allowed); + return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } int cpuset_slab_spread_node(void) { + if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) + current->cpuset_slab_spread_rotor = + node_random(¤t->mems_allowed); + return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); } diff --git a/kernel/fork.c b/kernel/fork.c index 17bf7c8d6511..e33177edb3bf 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1173,6 +1173,10 @@ static struct task_struct *copy_process(unsigned long clone_flags, } mpol_fix_fork_child_flag(p); #endif +#ifdef CONFIG_CPUSETS + p->cpuset_mem_spread_rotor = NUMA_NO_NODE; + p->cpuset_slab_spread_rotor = NUMA_NO_NODE; +#endif #ifdef CONFIG_TRACE_IRQFLAGS p->irq_events = 0; #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW -- cgit v1.2.3 From fb0a685cb95a0267a96153af2f72486f27be5847 Mon Sep 17 00:00:00 2001 From: Daniel Rebelo de Oliveira Date: Tue, 26 Jul 2011 16:08:39 -0700 Subject: kernel/fork.c: fix a few coding style issues Signed-off-by: Daniel Rebelo de Oliveira Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 83 ++++++++++++++++++++++++++++++++++------------------------- 1 file changed, 48 insertions(+), 35 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index e33177edb3bf..e7ceaca89609 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -80,7 +80,7 @@ * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ -int nr_threads; /* The idle threads do not count.. */ +int nr_threads; /* The idle threads do not count.. */ int max_threads; /* tunable limit on nr_threads */ @@ -232,7 +232,7 @@ void __init fork_init(unsigned long mempages) /* * we need to allow at least 20 threads to boot a system */ - if(max_threads < 20) + if (max_threads < 20) max_threads = 20; init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; @@ -268,7 +268,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) return NULL; } - err = arch_dup_task_struct(tsk, orig); + err = arch_dup_task_struct(tsk, orig); if (err) goto out; @@ -288,8 +288,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) tsk->stack_canary = get_random_int(); #endif - /* One for us, one for whoever does the "release_task()" (usually parent) */ - atomic_set(&tsk->usage,2); + /* + * One for us, one for whoever does the "release_task()" (usually + * parent) + */ + atomic_set(&tsk->usage, 2); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif @@ -437,7 +440,7 @@ fail_nomem: goto out; } -static inline int mm_alloc_pgd(struct mm_struct * mm) +static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) @@ -445,7 +448,7 @@ static inline int mm_alloc_pgd(struct mm_struct * mm) return 0; } -static inline void mm_free_pgd(struct mm_struct * mm) +static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } @@ -482,7 +485,7 @@ static void mm_init_aio(struct mm_struct *mm) #endif } -static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) +static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) { atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); @@ -513,9 +516,9 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) /* * Allocate and initialize an mm_struct. */ -struct mm_struct * mm_alloc(void) +struct mm_struct *mm_alloc(void) { - struct mm_struct * mm; + struct mm_struct *mm; mm = allocate_mm(); if (!mm) @@ -583,7 +586,7 @@ void added_exe_file_vma(struct mm_struct *mm) void removed_exe_file_vma(struct mm_struct *mm) { mm->num_exe_file_vmas--; - if ((mm->num_exe_file_vmas == 0) && mm->exe_file){ + if ((mm->num_exe_file_vmas == 0) && mm->exe_file) { fput(mm->exe_file); mm->exe_file = NULL; } @@ -775,9 +778,9 @@ fail_nocontext: return NULL; } -static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) +static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { - struct mm_struct * mm, *oldmm; + struct mm_struct *mm, *oldmm; int retval; tsk->min_flt = tsk->maj_flt = 0; @@ -844,7 +847,7 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) return 0; } -static int copy_files(unsigned long clone_flags, struct task_struct * tsk) +static int copy_files(unsigned long clone_flags, struct task_struct *tsk) { struct files_struct *oldf, *newf; int error = 0; @@ -1166,11 +1169,11 @@ static struct task_struct *copy_process(unsigned long clone_flags, cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); - if (IS_ERR(p->mempolicy)) { - retval = PTR_ERR(p->mempolicy); - p->mempolicy = NULL; - goto bad_fork_cleanup_cgroup; - } + if (IS_ERR(p->mempolicy)) { + retval = PTR_ERR(p->mempolicy); + p->mempolicy = NULL; + goto bad_fork_cleanup_cgroup; + } mpol_fix_fork_child_flag(p); #endif #ifdef CONFIG_CPUSETS @@ -1216,25 +1219,33 @@ static struct task_struct *copy_process(unsigned long clone_flags, retval = perf_event_init_task(p); if (retval) goto bad_fork_cleanup_policy; - - if ((retval = audit_alloc(p))) + retval = audit_alloc(p); + if (retval) goto bad_fork_cleanup_policy; /* copy all the process information */ - if ((retval = copy_semundo(clone_flags, p))) + retval = copy_semundo(clone_flags, p); + if (retval) goto bad_fork_cleanup_audit; - if ((retval = copy_files(clone_flags, p))) + retval = copy_files(clone_flags, p); + if (retval) goto bad_fork_cleanup_semundo; - if ((retval = copy_fs(clone_flags, p))) + retval = copy_fs(clone_flags, p); + if (retval) goto bad_fork_cleanup_files; - if ((retval = copy_sighand(clone_flags, p))) + retval = copy_sighand(clone_flags, p); + if (retval) goto bad_fork_cleanup_fs; - if ((retval = copy_signal(clone_flags, p))) + retval = copy_signal(clone_flags, p); + if (retval) goto bad_fork_cleanup_sighand; - if ((retval = copy_mm(clone_flags, p))) + retval = copy_mm(clone_flags, p); + if (retval) goto bad_fork_cleanup_signal; - if ((retval = copy_namespaces(clone_flags, p))) + retval = copy_namespaces(clone_flags, p); + if (retval) goto bad_fork_cleanup_mm; - if ((retval = copy_io(clone_flags, p))) + retval = copy_io(clone_flags, p); + if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(clone_flags, stack_start, stack_size, p, regs); if (retval) @@ -1256,7 +1267,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, /* * Clear TID on mm_release()? */ - p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL; + p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; #ifdef CONFIG_BLOCK p->plug = NULL; #endif @@ -1324,7 +1335,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, * it's process group. * A fatal signal pending means that current will exit, so the new * thread can't slip out of an OOM kill (or normal SIGKILL). - */ + */ recalc_sigpending(); if (signal_pending(current)) { spin_unlock(¤t->sighand->siglock); @@ -1685,12 +1696,14 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; - if ((err = unshare_fs(unshare_flags, &new_fs))) + err = unshare_fs(unshare_flags, &new_fs); + if (err) goto bad_unshare_out; - if ((err = unshare_fd(unshare_flags, &new_fd))) + err = unshare_fd(unshare_flags, &new_fd); + if (err) goto bad_unshare_cleanup_fs; - if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, - new_fs))) + err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_fs); + if (err) goto bad_unshare_cleanup_fd; if (new_fs || new_fd || do_sysvsem || new_nsproxy) { -- cgit v1.2.3 From b34a6b1da371ed8af1221459a18c67970f7e3d53 Mon Sep 17 00:00:00 2001 From: Vasiliy Kulikov Date: Tue, 26 Jul 2011 16:08:48 -0700 Subject: ipc: introduce shm_rmid_forced sysctl Add support for the shm_rmid_forced sysctl. If set to 1, all shared memory objects in current ipc namespace will be automatically forced to use IPC_RMID. The POSIX way of handling shmem allows one to create shm objects and call shmdt(), leaving shm object associated with no process, thus consuming memory not counted via rlimits. With shm_rmid_forced=1 the shared memory object is counted at least for one process, so OOM killer may effectively kill the fat process holding the shared memory. It obviously breaks POSIX - some programs relying on the feature would stop working. So set shm_rmid_forced=1 only if you're sure nobody uses "orphaned" memory. Use shm_rmid_forced=0 by default for compatability reasons. The feature was previously impemented in -ow as a configure option. [akpm@linux-foundation.org: fix documentation, per Randy] [akpm@linux-foundation.org: fix warning] [akpm@linux-foundation.org: readability/conventionality tweaks] [akpm@linux-foundation.org: fix shm_rmid_forced/shm_forced_rmid confusion, use standard comment layout] Signed-off-by: Vasiliy Kulikov Cc: Randy Dunlap Cc: "Eric W. Biederman" Cc: "Serge E. Hallyn" Cc: Daniel Lezcano Cc: Oleg Nesterov Cc: Tejun Heo Cc: Ingo Molnar Cc: Alan Cox Cc: Solar Designer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/exit.c b/kernel/exit.c index 9ee58bb9e60f..2913b3509d42 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -980,6 +980,7 @@ NORET_TYPE void do_exit(long code) trace_sched_process_exit(tsk); exit_sem(tsk); + exit_shm(tsk); exit_files(tsk); exit_fs(tsk); check_stack_usage(); -- cgit v1.2.3 From 947be5dfdaaef01b43a3d5444688ebef2bd263d4 Mon Sep 17 00:00:00 2001 From: Vitaliy Ivanov Date: Tue, 26 Jul 2011 16:08:49 -0700 Subject: gcov: disable CONSTRUCTORS for UML Selecting GCOV for UML causing configuration mismatch: warning: (GCOV_KERNEL) selects CONSTRUCTORS which has unmet direct dependencies (!UML) Constructors are not needed for UML. Signed-off-by: Vitaliy Ivanov Cc: Peter Oberparleiter Acked-by: Richard Weinberger Acked-by: WANG Cong Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/gcov/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index 5bf924d80b5c..a92028196cc1 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -3,7 +3,7 @@ menu "GCOV-based kernel profiling" config GCOV_KERNEL bool "Enable gcov-based kernel profiling" depends on DEBUG_FS - select CONSTRUCTORS + select CONSTRUCTORS if !UML default n ---help--- This option enables gcov-based code profiling (e.g. for code coverage -- cgit v1.2.3 From 4302fbc8ec2ccae279c939f241bf8ce64e1a0bb7 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 26 Jul 2011 16:08:52 -0700 Subject: panic: panic=-1 for immediate reboot When a kernel BUG or oops occurs, ChromeOS intends to panic and immediately reboot, with stacktrace and other messages preserved in RAM across reboot. But the longer we delay, the more likely the user is to poweroff and lose the info. panic_timeout (seconds before rebooting) is set by panic= boot option or sysctl or /proc/sys/kernel/panic; but 0 means wait forever, so at present we have to delay at least 1 second. Let a negative number mean reboot immediately (with the small cosmetic benefit of suppressing that newline-less "Rebooting in %d seconds.." message). Signed-off-by: Hugh Dickins Signed-off-by: Mandeep Singh Baines Cc: Huang Ying Cc: Andi Kleen Cc: Hugh Dickins Cc: Olaf Hering Cc: Jesse Barnes Cc: Dave Airlie Cc: Greg Kroah-Hartman Cc: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/panic.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/panic.c b/kernel/panic.c index 69231670eb95..d7bb6974efb5 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -119,6 +119,8 @@ NORET_TYPE void panic(const char * fmt, ...) } mdelay(PANIC_TIMER_STEP); } + } + if (panic_timeout != 0) { /* * This will not be a clean reboot, with everything * shutting down. But if there is a chance of -- cgit v1.2.3 From 60063497a95e716c9a689af3be2687d261f115b4 Mon Sep 17 00:00:00 2001 From: Arun Sharma Date: Tue, 26 Jul 2011 16:09:06 -0700 Subject: atomic: use This allows us to move duplicated code in (atomic_inc_not_zero() for now) to Signed-off-by: Arun Sharma Reviewed-by: Eric Dumazet Cc: Ingo Molnar Cc: David Miller Cc: Eric Dumazet Acked-by: Mike Frysinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/audit.c | 2 +- kernel/auditsc.c | 2 +- kernel/cgroup.c | 2 +- kernel/cpuset.c | 2 +- kernel/debug/debug_core.c | 2 +- kernel/rcupdate.c | 2 +- kernel/rcutorture.c | 2 +- kernel/rcutree_trace.c | 2 +- kernel/rwsem.c | 2 +- kernel/stop_machine.c | 2 +- kernel/taskstats.c | 2 +- kernel/trace/trace.h | 2 +- kernel/trace/trace_mmiotrace.c | 2 +- 13 files changed, 13 insertions(+), 13 deletions(-) (limited to 'kernel') diff --git a/kernel/audit.c b/kernel/audit.c index 52501b5d4902..0a1355ca3d79 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -43,7 +43,7 @@ #include #include -#include +#include #include #include #include diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 00d79df03e76..ce4b054acee5 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -44,7 +44,7 @@ #include #include -#include +#include #include #include #include diff --git a/kernel/cgroup.c b/kernel/cgroup.c index a63507b92ca4..984458035d4a 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -59,7 +59,7 @@ #include #include /* used in cgroup_attach_proc */ -#include +#include static DEFINE_MUTEX(cgroup_mutex); diff --git a/kernel/cpuset.c b/kernel/cpuset.c index f8bc977ccbbe..10131fdaff70 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -55,7 +55,7 @@ #include #include -#include +#include #include #include #include diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index bad6786dee88..0d7c08784efb 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -51,7 +51,7 @@ #include #include -#include +#include #include #include "debug_core.h" diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 7784bd216b6a..ddddb320be61 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -37,7 +37,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index ced72102adc2..98f51b13bb7e 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 4e144876dc68..3b0c0986afc0 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -31,7 +31,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/kernel/rwsem.c b/kernel/rwsem.c index 176e5e56ffab..9f48f3d82e9b 100644 --- a/kernel/rwsem.c +++ b/kernel/rwsem.c @@ -11,7 +11,7 @@ #include #include -#include +#include /* * lock for reading diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index c1124752e1d3..ba5070ce5765 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -19,7 +19,7 @@ #include #include -#include +#include /* * Structure to determine completion condition and record errors. May diff --git a/kernel/taskstats.c b/kernel/taskstats.c index fc0f22005417..d1db2880d1cf 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include /* * Maximum length of a cpumask that can be specified in diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3f381d0b20a8..616846bcfee5 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -2,7 +2,7 @@ #define _LINUX_KERNEL_TRACE_H #include -#include +#include #include #include #include diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 017fa376505d..fd3c8aae55e5 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -12,7 +12,7 @@ #include #include -#include +#include #include "trace.h" #include "trace_output.h" -- cgit v1.2.3