From d8e8ed95cda1dfd6813588333d36552935eba4a1 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 15 Dec 2011 13:43:24 +1030 Subject: rcu: Make rcutorture bool parameters really bool (core code) module_param(bool) used to counter-intuitively take an int. In fddd5201 (mid-2009) we allowed bool or int/unsigned int using a messy trick. It's time to remove the int/unsigned int option. For this version it'll simply give a warning, but it'll break next kernel version. This commit makes this change to rcutorture. Signed-off-by: Rusty Russell Signed-off-by: Paul E. McKenney --- kernel/rcutorture.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 88f17b8a3b1..e29edc374ce 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -56,8 +56,8 @@ static int nreaders = -1; /* # reader threads, defaults to 2*ncpus */ static int nfakewriters = 4; /* # fake writer threads */ static int stat_interval; /* Interval between stats, in seconds. */ /* Defaults to "only at end of test". */ -static int verbose; /* Print more debug info. */ -static int test_no_idle_hz; /* Test RCU's support for tickless idle CPUs. */ +static bool verbose; /* Print more debug info. */ +static bool test_no_idle_hz; /* Test RCU's support for tickless idle CPUs. */ static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/ static int stutter = 5; /* Start/stop testing interval (in sec) */ static int irqreader = 1; /* RCU readers from irq (timers). */ -- cgit v1.2.3-70-g09d2 From 4410030646be072b82ec1892ad5cc7d91af384d8 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 27 Dec 2011 15:04:26 +0100 Subject: rcu: Add missing __cpuinit annotation in rcutorture code "rcu: Add rcutorture CPU-hotplug capability" adds cpu hotplug operations to the rcutorture code but produces a false positive warning about section mismatches: WARNING: vmlinux.o(.text+0x1e420c): Section mismatch in reference from the function rcu_torture_onoff() to the function .cpuinit.text:cpu_up() The function rcu_torture_onoff() references the function __cpuinit cpu_up(). This is often because rcu_torture_onoff lacks a __cpuinit annotation or the annotation of cpu_up is wrong. This commit therefore adds a __cpuinit annotation so the warning goes away. Signed-off-by: Heiko Carstens Signed-off-by: Paul E. McKenney --- kernel/rcutorture.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index e29edc374ce..a58ac285fc6 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -1399,7 +1399,7 @@ rcu_torture_shutdown(void *arg) * Execute random CPU-hotplug operations at the interval specified * by the onoff_interval. */ -static int +static int __cpuinit rcu_torture_onoff(void *arg) { int cpu; @@ -1447,7 +1447,7 @@ rcu_torture_onoff(void *arg) return 0; } -static int +static int __cpuinit rcu_torture_onoff_init(void) { if (onoff_interval <= 0) -- cgit v1.2.3-70-g09d2 From 160cb5a97daef0cb894685d84c9d4700bb7cccb4 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 19 Jan 2012 23:23:10 +0100 Subject: PM / Hibernate: Correct additional pages number calculation The struct bm_block is allocated by chain_alloc(), so it'd better counting it in LINKED_PAGE_DATA_SIZE. Signed-off-by: Namhyung Kim Signed-off-by: Rafael J. Wysocki --- kernel/power/snapshot.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 1cf88900ec4..6a768e53700 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -812,7 +812,8 @@ unsigned int snapshot_additional_pages(struct zone *zone) unsigned int res; res = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK); - res += DIV_ROUND_UP(res * sizeof(struct bm_block), PAGE_SIZE); + res += DIV_ROUND_UP(res * sizeof(struct bm_block), + LINKED_PAGE_DATA_SIZE); return 2 * res; } -- cgit v1.2.3-70-g09d2 From fd45c15f13e754f3c106427e857310f3e0813951 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 20 Jan 2012 10:12:45 +0900 Subject: perf: Don't call release_callchain_buffers() if allocation fails When alloc_callchain_buffers() fails, it frees all of entries before return. In addition, calling the release_callchain_buffers() will cause a NULL pointer dereference since callchain_cpu_entries is not set. Signed-off-by: Namhyung Kim Acked-by: Frederic Weisbecker Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/1327021966-27688-1-git-send-email-namhyung.kim@lge.com Signed-off-by: Ingo Molnar --- kernel/events/callchain.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 057e24b665c..6581a040f39 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -115,8 +115,6 @@ int get_callchain_buffers(void) } err = alloc_callchain_buffers(); - if (err) - release_callchain_buffers(); exit: mutex_unlock(&callchain_mutex); -- cgit v1.2.3-70-g09d2 From 46cd6a7f680d14f6f80ede9f04aeb70fa83bd266 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Fri, 20 Jan 2012 10:12:46 +0900 Subject: perf: Call perf_cgroup_event_time() directly The perf_event_time() will call perf_cgroup_event_time() if @event is a cgroup event. Just do it directly and avoid the extra check.. Signed-off-by: Namhyung Kim Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/1327021966-27688-2-git-send-email-namhyung.kim@lge.com Signed-off-by: Ingo Molnar --- kernel/events/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index a8f4ac001a0..32b48c88971 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -815,7 +815,7 @@ static void update_event_times(struct perf_event *event) * here. */ if (is_cgroup_event(event)) - run_end = perf_event_time(event); + run_end = perf_cgroup_event_time(event); else if (ctx->is_active) run_end = ctx->time; else -- cgit v1.2.3-70-g09d2 From 0e90b31f4ba77027a7c21cbfc66404df0851ca21 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Fri, 20 Jan 2012 04:57:16 +0000 Subject: net: introduce res_counter_charge_nofail() for socket allocations There is a case in __sk_mem_schedule(), where an allocation is beyond the maximum, but yet we are allowed to proceed. It happens under the following condition: sk->sk_wmem_queued + size >= sk->sk_sndbuf The network code won't revert the allocation in this case, meaning that at some point later it'll try to do it. Since this is never communicated to the underlying res_counter code, there is an inbalance in res_counter uncharge operation. I see two ways of fixing this: 1) storing the information about those allocations somewhere in memcg, and then deducting from that first, before we start draining the res_counter, 2) providing a slightly different allocation function for the res_counter, that matches the original behavior of the network code more closely. I decided to go for #2 here, believing it to be more elegant, since #1 would require us to do basically that, but in a more obscure way. Signed-off-by: Glauber Costa Cc: KAMEZAWA Hiroyuki Cc: Johannes Weiner Cc: Michal Hocko CC: Tejun Heo CC: Li Zefan CC: Laurent Chavey Acked-by: Tejun Heo Signed-off-by: David S. Miller --- include/linux/res_counter.h | 6 ++++++ include/net/sock.h | 10 ++++------ kernel/res_counter.c | 25 +++++++++++++++++++++++++ net/core/sock.c | 4 ++-- 4 files changed, 37 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index d06d014afda..da81af086ea 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -109,12 +109,18 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent); * * returns 0 on success and <0 if the counter->usage will exceed the * counter->limit _locked call expects the counter->lock to be taken + * + * charge_nofail works the same, except that it charges the resource + * counter unconditionally, and returns < 0 if the after the current + * charge we are over limit. */ int __must_check res_counter_charge_locked(struct res_counter *counter, unsigned long val); int __must_check res_counter_charge(struct res_counter *counter, unsigned long val, struct res_counter **limit_fail_at); +int __must_check res_counter_charge_nofail(struct res_counter *counter, + unsigned long val, struct res_counter **limit_fail_at); /* * uncharge - tell that some portion of the resource is released diff --git a/include/net/sock.h b/include/net/sock.h index 0e7a9b05f92..4c69ac165e6 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1008,9 +1008,8 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot, struct res_counter *fail; int ret; - ret = res_counter_charge(prot->memory_allocated, - amt << PAGE_SHIFT, &fail); - + ret = res_counter_charge_nofail(prot->memory_allocated, + amt << PAGE_SHIFT, &fail); if (ret < 0) *parent_status = OVER_LIMIT; } @@ -1054,12 +1053,11 @@ sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status) } static inline void -sk_memory_allocated_sub(struct sock *sk, int amt, int parent_status) +sk_memory_allocated_sub(struct sock *sk, int amt) { struct proto *prot = sk->sk_prot; - if (mem_cgroup_sockets_enabled && sk->sk_cgrp && - parent_status != OVER_LIMIT) /* Otherwise was uncharged already */ + if (mem_cgroup_sockets_enabled && sk->sk_cgrp) memcg_memory_allocated_sub(sk->sk_cgrp, amt); atomic_long_sub(amt, prot->memory_allocated); diff --git a/kernel/res_counter.c b/kernel/res_counter.c index 6d269cce7aa..d508363858b 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -66,6 +66,31 @@ done: return ret; } +int res_counter_charge_nofail(struct res_counter *counter, unsigned long val, + struct res_counter **limit_fail_at) +{ + int ret, r; + unsigned long flags; + struct res_counter *c; + + r = ret = 0; + *limit_fail_at = NULL; + local_irq_save(flags); + for (c = counter; c != NULL; c = c->parent) { + spin_lock(&c->lock); + r = res_counter_charge_locked(c, val); + if (r) + c->usage += val; + spin_unlock(&c->lock); + if (r < 0 && ret == 0) { + *limit_fail_at = c; + ret = r; + } + } + local_irq_restore(flags); + + return ret; +} void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) { if (WARN_ON(counter->usage < val)) diff --git a/net/core/sock.c b/net/core/sock.c index 5c5af9988f9..3e81fd2e3c7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1827,7 +1827,7 @@ suppress_allocation: /* Alas. Undo changes. */ sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM; - sk_memory_allocated_sub(sk, amt, parent_status); + sk_memory_allocated_sub(sk, amt); return 0; } @@ -1840,7 +1840,7 @@ EXPORT_SYMBOL(__sk_mem_schedule); void __sk_mem_reclaim(struct sock *sk) { sk_memory_allocated_sub(sk, - sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, 0); + sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT); sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1; if (sk_under_memory_pressure(sk) && -- cgit v1.2.3-70-g09d2 From d496aab567e7e52b3e974c9192a5de6e77dce32c Mon Sep 17 00:00:00 2001 From: Ananth N Mavinakayanahalli Date: Fri, 20 Jan 2012 14:34:04 -0800 Subject: kprobes: initialize before using a hlist Commit ef53d9c5e ("kprobes: improve kretprobe scalability with hashed locking") introduced a bug where we can potentially leak kretprobe_instances since we initialize a hlist head after having used it. Initialize the hlist head before using it. Reported by: Jim Keniston Acked-by: Jim Keniston Signed-off-by: Ananth N Mavinakayanahalli Acked-by: Masami Hiramatsu Cc: Srinivasa D S Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/kprobes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 95dd7212e61..29f5b65bee2 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1077,6 +1077,7 @@ void __kprobes kprobe_flush_task(struct task_struct *tk) /* Early boot. kretprobe_table_locks not yet initialized. */ return; + INIT_HLIST_HEAD(&empty_rp); hash = hash_ptr(tk, KPROBE_HASH_BITS); head = &kretprobe_inst_table[hash]; kretprobe_table_lock(hash, &flags); @@ -1085,7 +1086,6 @@ void __kprobes kprobe_flush_task(struct task_struct *tk) recycle_rp_inst(ri, &empty_rp); } kretprobe_table_unlock(hash, &flags); - INIT_HLIST_HEAD(&empty_rp); hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); -- cgit v1.2.3-70-g09d2 From 42ae610c1a820ddecb80943d4ccfc936f7772535 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 21 Jan 2012 11:02:24 -0800 Subject: kernel-doc: fix new warnings in auditsc.c Fix new kernel-doc warnings in auditsc.c: Warning(kernel/auditsc.c:1875): No description found for parameter 'success' Warning(kernel/auditsc.c:1875): No description found for parameter 'return_code' Warning(kernel/auditsc.c:1875): Excess function parameter 'pt_regs' description in '__audit_syscall_exit' Signed-off-by: Randy Dunlap Cc: Al Viro Cc: Eric Paris Signed-off-by: Linus Torvalds --- kernel/auditsc.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/auditsc.c b/kernel/auditsc.c index caaea6e944f..af1de0f34ea 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1863,11 +1863,12 @@ void __audit_syscall_entry(int arch, int major, /** * audit_syscall_exit - deallocate audit context after a system call - * @pt_regs: syscall registers + * @success: success value of the syscall + * @return_code: return value of the syscall * * Tear down after system call. If the audit context has been marked as * auditable (either because of the AUDIT_RECORD_CONTEXT state from - * filtering, or because some other part of the kernel write an audit + * filtering, or because some other part of the kernel wrote an audit * message), then write out the syscall information. In call cases, * free the names stored from getname(). */ -- cgit v1.2.3-70-g09d2 From fa757281a08799fd6c0f7ec6f111d1cd66afc97b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sat, 21 Jan 2012 11:03:13 -0800 Subject: kernel-doc: fix kernel-doc warnings in sched Fix new kernel-doc notation warnings: Warning(include/linux/sched.h:2094): No description found for parameter 'p' Warning(include/linux/sched.h:2094): Excess function parameter 'tsk' description in 'is_idle_task' Warning(kernel/sched/cpupri.c:139): No description found for parameter 'newpri' Warning(kernel/sched/cpupri.c:139): Excess function parameter 'pri' description in 'cpupri_set' Warning(kernel/sched/cpupri.c:208): Excess function parameter 'bootmem' description in 'cpupri_init' Signed-off-by: Randy Dunlap Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Linus Torvalds --- include/linux/sched.h | 2 +- kernel/sched/cpupri.c | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4032ec1cf83..513f5245987 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2088,7 +2088,7 @@ extern int sched_setscheduler_nocheck(struct task_struct *, int, extern struct task_struct *idle_task(int cpu); /** * is_idle_task - is the specified task an idle task? - * @tsk: the task in question. + * @p: the task in question. */ static inline bool is_idle_task(struct task_struct *p) { diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index b0d798eaf13..d72586fdf66 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -129,7 +129,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, * cpupri_set - update the cpu priority setting * @cp: The cpupri context * @cpu: The target cpu - * @pri: The priority (INVALID-RT99) to assign to this CPU + * @newpri: The priority (INVALID-RT99) to assign to this CPU * * Note: Assumes cpu_rq(cpu)->lock is locked * @@ -200,7 +200,6 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) /** * cpupri_init - initialize the cpupri structure * @cp: The cpupri context - * @bootmem: true if allocations need to use bootmem * * Returns: -ENOMEM if memory fails. */ -- cgit v1.2.3-70-g09d2 From 181e9bdef37bfcaa41f3ab6c948a2a0d60a268b5 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 29 Jan 2012 20:35:52 +0100 Subject: PM / Hibernate: Fix s2disk regression related to freezing workqueues Commit 2aede851ddf08666f68ffc17be446420e9d2a056 PM / Hibernate: Freeze kernel threads after preallocating memory introduced a mechanism by which kernel threads were frozen after the preallocation of hibernate image memory to avoid problems with frozen kernel threads not responding to memory freeing requests. However, it overlooked the s2disk code path in which the SNAPSHOT_CREATE_IMAGE ioctl was run directly after SNAPSHOT_FREE, which caused freeze_workqueues_begin() to BUG(), because it saw that worqueues had been already frozen. Although in principle this issue might be addressed by removing the relevant BUG_ON() from freeze_workqueues_begin(), that would reintroduce the very problem that commit 2aede851ddf08666f68ffc17be4 attempted to avoid into that particular code path. For this reason, to fix the issue at hand, introduce thaw_kernel_threads() and make the SNAPSHOT_FREE ioctl execute it. Special thanks to Srivatsa S. Bhat for detailed analysis of the problem. Reported-and-tested-by: Jiri Slaby Signed-off-by: Rafael J. Wysocki Acked-by: Srivatsa S. Bhat Cc: stable@kernel.org --- include/linux/freezer.h | 2 ++ kernel/power/process.c | 19 +++++++++++++++++++ kernel/power/user.c | 9 +++++++++ 3 files changed, 30 insertions(+) (limited to 'kernel') diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 0ab54e16a91..d09af4b67cf 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -39,6 +39,7 @@ extern bool __refrigerator(bool check_kthr_stop); extern int freeze_processes(void); extern int freeze_kernel_threads(void); extern void thaw_processes(void); +extern void thaw_kernel_threads(void); static inline bool try_to_freeze(void) { @@ -174,6 +175,7 @@ static inline bool __refrigerator(bool check_kthr_stop) { return false; } static inline int freeze_processes(void) { return -ENOSYS; } static inline int freeze_kernel_threads(void) { return -ENOSYS; } static inline void thaw_processes(void) {} +static inline void thaw_kernel_threads(void) {} static inline bool try_to_freeze(void) { return false; } diff --git a/kernel/power/process.c b/kernel/power/process.c index 77274c9ba2f..eeca00311f3 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -188,3 +188,22 @@ void thaw_processes(void) printk("done.\n"); } +void thaw_kernel_threads(void) +{ + struct task_struct *g, *p; + + pm_nosig_freezing = false; + printk("Restarting kernel threads ... "); + + thaw_workqueues(); + + read_lock(&tasklist_lock); + do_each_thread(g, p) { + if (p->flags & (PF_KTHREAD | PF_WQ_WORKER)) + __thaw_task(p); + } while_each_thread(g, p); + read_unlock(&tasklist_lock); + + schedule(); + printk("done.\n"); +} diff --git a/kernel/power/user.c b/kernel/power/user.c index 6b1ab7a8852..e5a21a85730 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -274,6 +274,15 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, swsusp_free(); memset(&data->handle, 0, sizeof(struct snapshot_handle)); data->ready = 0; + /* + * It is necessary to thaw kernel threads here, because + * SNAPSHOT_CREATE_IMAGE may be invoked directly after + * SNAPSHOT_FREE. In that case, if kernel threads were not + * thawed, the preallocation of memory carried out by + * hibernation_snapshot() might run into problems (i.e. it + * might fail or even deadlock). + */ + thaw_kernel_threads(); break; case SNAPSHOT_PREF_IMAGE_SIZE: -- cgit v1.2.3-70-g09d2