diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/Makefile | 22 | ||||
| -rw-r--r-- | kernel/cgroup.c | 248 | ||||
| -rw-r--r-- | kernel/cpu.c | 29 | ||||
| -rw-r--r-- | kernel/delayacct.c | 7 | ||||
| -rw-r--r-- | kernel/elfcore.c | 10 | ||||
| -rw-r--r-- | kernel/events/core.c | 3 | ||||
| -rw-r--r-- | kernel/futex.c | 2 | ||||
| -rw-r--r-- | kernel/gcov/Kconfig | 30 | ||||
| -rw-r--r-- | kernel/gcov/Makefile | 32 | ||||
| -rw-r--r-- | kernel/gcov/base.c | 32 | ||||
| -rw-r--r-- | kernel/gcov/fs.c | 52 | ||||
| -rw-r--r-- | kernel/gcov/gcc_3_4.c | 115 | ||||
| -rw-r--r-- | kernel/gcov/gcc_4_7.c | 560 | ||||
| -rw-r--r-- | kernel/gcov/gcov.h | 65 | ||||
| -rw-r--r-- | kernel/hung_task.c | 6 | ||||
| -rw-r--r-- | kernel/irq/irqdomain.c | 13 | ||||
| -rw-r--r-- | kernel/jump_label.c | 5 | ||||
| -rw-r--r-- | kernel/kprobes.c | 4 | ||||
| -rw-r--r-- | kernel/kthread.c | 73 | ||||
| -rw-r--r-- | kernel/locking/Makefile | 25 | ||||
| -rw-r--r-- | kernel/locking/lglock.c (renamed from kernel/lglock.c) | 0 | ||||
| -rw-r--r-- | kernel/locking/lockdep.c (renamed from kernel/lockdep.c) | 4 | ||||
| -rw-r--r-- | kernel/locking/lockdep_internals.h (renamed from kernel/lockdep_internals.h) | 0 | ||||
| -rw-r--r-- | kernel/locking/lockdep_proc.c (renamed from kernel/lockdep_proc.c) | 15 | ||||
| -rw-r--r-- | kernel/locking/lockdep_states.h (renamed from kernel/lockdep_states.h) | 0 | ||||
| -rw-r--r-- | kernel/locking/mutex-debug.c (renamed from kernel/mutex-debug.c) | 0 | ||||
| -rw-r--r-- | kernel/locking/mutex-debug.h (renamed from kernel/mutex-debug.h) | 0 | ||||
| -rw-r--r-- | kernel/locking/mutex.c (renamed from kernel/mutex.c) | 2 | ||||
| -rw-r--r-- | kernel/locking/mutex.h (renamed from kernel/mutex.h) | 0 | ||||
| -rw-r--r-- | kernel/locking/percpu-rwsem.c | 165 | ||||
| -rw-r--r-- | kernel/locking/rtmutex-debug.c (renamed from kernel/rtmutex-debug.c) | 0 | ||||
| -rw-r--r-- | kernel/locking/rtmutex-debug.h (renamed from kernel/rtmutex-debug.h) | 0 | ||||
| -rw-r--r-- | kernel/locking/rtmutex-tester.c (renamed from kernel/rtmutex-tester.c) | 0 | ||||
| -rw-r--r-- | kernel/locking/rtmutex.c (renamed from kernel/rtmutex.c) | 0 | ||||
| -rw-r--r-- | kernel/locking/rtmutex.h (renamed from kernel/rtmutex.h) | 0 | ||||
| -rw-r--r-- | kernel/locking/rtmutex_common.h (renamed from kernel/rtmutex_common.h) | 0 | ||||
| -rw-r--r-- | kernel/locking/rwsem-spinlock.c | 296 | ||||
| -rw-r--r-- | kernel/locking/rwsem-xadd.c | 293 | ||||
| -rw-r--r-- | kernel/locking/rwsem.c (renamed from kernel/rwsem.c) | 0 | ||||
| -rw-r--r-- | kernel/locking/semaphore.c (renamed from kernel/semaphore.c) | 0 | ||||
| -rw-r--r-- | kernel/locking/spinlock.c (renamed from kernel/spinlock.c) | 0 | ||||
| -rw-r--r-- | kernel/locking/spinlock_debug.c | 302 | ||||
| -rw-r--r-- | kernel/module.c | 103 | ||||
| -rw-r--r-- | kernel/panic.c | 2 | ||||
| -rw-r--r-- | kernel/pid_namespace.c | 8 | ||||
| -rw-r--r-- | kernel/power/Kconfig | 16 | ||||
| -rw-r--r-- | kernel/power/qos.c | 26 | ||||
| -rw-r--r-- | kernel/power/snapshot.c | 6 | ||||
| -rw-r--r-- | kernel/power/user.c | 20 | ||||
| -rw-r--r-- | kernel/printk/printk.c | 35 | ||||
| -rw-r--r-- | kernel/ptrace.c | 3 | ||||
| -rw-r--r-- | kernel/rcu/tree_plugin.h | 2 | ||||
| -rw-r--r-- | kernel/signal.c | 2 | ||||
| -rw-r--r-- | kernel/smp.c | 7 | ||||
| -rw-r--r-- | kernel/sys.c | 1 | ||||
| -rw-r--r-- | kernel/sysctl.c | 10 | ||||
| -rw-r--r-- | kernel/sysctl_binary.c | 6 | ||||
| -rw-r--r-- | kernel/taskstats.c | 16 | ||||
| -rw-r--r-- | kernel/trace/blktrace.c | 36 |
59 files changed, 2133 insertions, 576 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index a4d1aa8da9b..09a9c94f42b 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -7,22 +7,19 @@ obj-y = fork.o exec_domain.o panic.o \ sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o task_work.o \ extable.o params.o posix-timers.o \ - kthread.o sys_ni.o posix-cpu-timers.o mutex.o \ - hrtimer.o rwsem.o nsproxy.o semaphore.o \ + kthread.o sys_ni.o posix-cpu-timers.o \ + hrtimer.o nsproxy.o \ notifier.o ksysfs.o cred.o reboot.o \ - async.o range.o groups.o lglock.o smpboot.o + async.o range.o groups.o smpboot.o ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files -CFLAGS_REMOVE_lockdep.o = -pg -CFLAGS_REMOVE_lockdep_proc.o = -pg -CFLAGS_REMOVE_mutex-debug.o = -pg -CFLAGS_REMOVE_rtmutex-debug.o = -pg CFLAGS_REMOVE_cgroup-debug.o = -pg CFLAGS_REMOVE_irq_work.o = -pg endif obj-y += sched/ +obj-y += locking/ obj-y += power/ obj-y += printk/ obj-y += cpu/ @@ -34,26 +31,15 @@ obj-$(CONFIG_FREEZER) += freezer.o obj-$(CONFIG_PROFILING) += profile.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ -obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o -obj-$(CONFIG_LOCKDEP) += lockdep.o -ifeq ($(CONFIG_PROC_FS),y) -obj-$(CONFIG_LOCKDEP) += lockdep_proc.o -endif obj-$(CONFIG_FUTEX) += futex.o ifeq ($(CONFIG_COMPAT),y) obj-$(CONFIG_FUTEX) += futex_compat.o endif -obj-$(CONFIG_RT_MUTEXES) += rtmutex.o -obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o -obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += smp.o ifneq ($(CONFIG_SMP),y) obj-y += up.o endif -obj-$(CONFIG_SMP) += spinlock.o -obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o -obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_UID16) += uid16.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o modsign_certificate.o diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 8bd9cfdc70d..e0839bcd48c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -125,38 +125,6 @@ struct cfent { }; /* - * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when - * cgroup_subsys->use_id != 0. - */ -#define CSS_ID_MAX (65535) -struct css_id { - /* - * The css to which this ID points. This pointer is set to valid value - * after cgroup is populated. If cgroup is removed, this will be NULL. - * This pointer is expected to be RCU-safe because destroy() - * is called after synchronize_rcu(). But for safe use, css_tryget() - * should be used for avoiding race. - */ - struct cgroup_subsys_state __rcu *css; - /* - * ID of this css. - */ - unsigned short id; - /* - * Depth in hierarchy which this ID belongs to. - */ - unsigned short depth; - /* - * ID is freed by RCU. (and lookup routine is RCU safe.) - */ - struct rcu_head rcu_head; - /* - * Hierarchy of CSS ID belongs to. - */ - unsigned short stack[0]; /* Array of Length (depth+1) */ -}; - -/* * cgroup_event represents events which userspace want to receive. */ struct cgroup_event { @@ -387,9 +355,6 @@ struct cgrp_cset_link { static struct css_set init_css_set; static struct cgrp_cset_link init_cgrp_cset_link; -static int cgroup_init_idr(struct cgroup_subsys *ss, - struct cgroup_subsys_state *css); - /* * css_set_lock protects the list of css_set objects, and the chain of * tasks off each css_set. Nests outside task->alloc_lock due to @@ -841,8 +806,6 @@ static struct backing_dev_info cgroup_backing_dev_info = { .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; -static int alloc_css_id(struct cgroup_subsys_state *child_css); - static struct inode *cgroup_new_inode(umode_t mode, struct super_block *sb) { struct inode *inode = new_inode(sb); @@ -4240,21 +4203,6 @@ static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask) goto err; } } - - /* This cgroup is ready now */ - for_each_root_subsys(cgrp->root, ss) { - struct cgroup_subsys_state *css = cgroup_css(cgrp, ss); - struct css_id *id = rcu_dereference_protected(css->id, true); - - /* - * Update id->css pointer and make this css visible from - * CSS ID functions. This pointer will be dereferened - * from RCU-read-side without locks. - */ - if (id) - rcu_assign_pointer(id->css, css); - } - return 0; err: cgroup_clear_dir(cgrp, subsys_mask); @@ -4323,7 +4271,6 @@ static void init_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss, css->cgroup = cgrp; css->ss = ss; css->flags = 0; - css->id = NULL; if (cgrp->parent) css->parent = cgroup_css(cgrp->parent, ss); @@ -4455,12 +4402,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, goto err_free_all; init_css(css, ss, cgrp); - - if (ss->use_id) { - err = alloc_css_id(css); - if (err) - goto err_free_all; - } } /* @@ -4925,12 +4866,6 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) /* our new subsystem will be attached to the dummy hierarchy. */ init_css(css, ss, cgroup_dummy_top); - /* init_idr must be after init_css() because it sets css->id. */ - if (ss->use_id) { - ret = cgroup_init_idr(ss, css); - if (ret) - goto err_unload; - } /* * Now we need to entangle the css into the existing css_sets. unlike @@ -4996,9 +4931,6 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss) offline_css(cgroup_css(cgroup_dummy_top, ss)); - if (ss->use_id) - idr_destroy(&ss->idr); - /* deassign the subsys_id */ cgroup_subsys[ss->subsys_id] = NULL; @@ -5025,8 +4957,7 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss) /* * remove subsystem's css from the cgroup_dummy_top and free it - * need to free before marking as null because ss->css_free needs - * the cgrp->subsys pointer to find their state. note that this - * also takes care of freeing the css_id. + * the cgrp->subsys pointer to find their state. */ ss->css_free(cgroup_css(cgroup_dummy_top, ss)); RCU_INIT_POINTER(cgroup_dummy_top->subsys[ss->subsys_id], NULL); @@ -5097,8 +5028,6 @@ int __init cgroup_init(void) for_each_builtin_subsys(ss, i) { if (!ss->early_init) cgroup_init_subsys(ss); - if (ss->use_id) - cgroup_init_idr(ss, init_css_set.subsys[ss->subsys_id]); } /* allocate id for the dummy hierarchy */ @@ -5518,181 +5447,6 @@ static int __init cgroup_disable(char *str) } __setup("cgroup_disable=", cgroup_disable); -/* - * Functons for CSS ID. - */ - -/* to get ID other than 0, this should be called when !cgroup_is_dead() */ -unsigned short css_id(struct cgroup_subsys_state *css) -{ - struct css_id *cssid; - - /* - * This css_id() can return correct value when somone has refcnt - * on this or this is under rcu_read_lock(). Once css->id is allocated, - * it's unchanged until freed. - */ - cssid = rcu_dereference_raw(css->id); - - if (cssid) - return cssid->id; - return 0; -} -EXPORT_SYMBOL_GPL(css_id); - -/** - * css_is_ancestor - test "root" css is an ancestor of "child" - * @child: the css to be tested. - * @root: the css supporsed to be an ancestor of the child. - * - * Returns true if "root" is an ancestor of "child" in its hierarchy. Because - * this function reads css->id, the caller must hold rcu_read_lock(). - * But, considering usual usage, the csses should be valid objects after test. - * Assuming that the caller will do some action to the child if this returns - * returns true, the caller must take "child";s reference count. - * If "child" is valid object and this returns true, "root" is valid, too. - */ - -bool css_is_ancestor(struct cgroup_subsys_state *child, - const struct cgroup_subsys_state *root) -{ - struct css_id *child_id; - struct css_id *root_id; - - child_id = rcu_dereference(child->id); - if (!child_id) - return false; - root_id = rcu_dereference(root->id); - if (!root_id) - return false; - if (child_id->depth < root_id->depth) - return false; - if (child_id->stack[root_id->depth] != root_id->id) - return false; - return true; -} - -void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css) -{ - struct css_id *id = rcu_dereference_protected(css->id, true); - - /* When this is called before css_id initialization, id can be NULL */ - if (!id) - return; - - BUG_ON(!ss->use_id); - - rcu_assign_pointer(id->css, NULL); - rcu_assign_pointer(css->id, NULL); - spin_lock(&ss->id_lock); - idr_remove(&ss->idr, id->id); - spin_unlock(&ss->id_lock); - kfree_rcu(id, rcu_head); -} -EXPORT_SYMBOL_GPL(free_css_id); - -/* - * This is called by init or create(). Then, calls to this function are - * always serialized (By cgroup_mutex() at create()). - */ - -static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth) -{ - struct css_id *newid; - int ret, size; - - BUG_ON(!ss->use_id); - - size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1); - newid = kzalloc(size, GFP_KERNEL); - if (!newid) - return ERR_PTR(-ENOMEM); - - idr_preload(GFP_KERNEL); - spin_lock(&ss->id_lock); - /* Don't use 0. allocates an ID of 1-65535 */ - ret = idr_alloc(&ss->idr, newid, 1, CSS_ID_MAX + 1, GFP_NOWAIT); - spin_unlock(&ss->id_lock); - idr_preload_end(); - - /* Returns error when there are no free spaces for new ID.*/ - if (ret < 0) - goto err_out; - - newid->id = ret; - newid->depth = depth; - return newid; -err_out: - kfree(newid); - return ERR_PTR(ret); - -} - -static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss, - struct cgroup_subsys_state *rootcss) -{ - struct css_id *newid; - - spin_lock_init(&ss->id_lock); - idr_init(&ss->idr); - - newid = get_new_cssid(ss, 0); - if (IS_ERR(newid)) - return PTR_ERR(newid); - - newid->stack[0] = newid->id; - RCU_INIT_POINTER(newid->css, rootcss); - RCU_INIT_POINTER(rootcss->id, newid); - return 0; -} - -static int alloc_css_id(struct cgroup_subsys_state *child_css) -{ - struct cgroup_subsys_state *parent_css = css_parent(child_css); - struct css_id *child_id, *parent_id; - int i, depth; - - parent_id = rcu_dereference_protected(parent_css->id, true); - depth = parent_id->depth + 1; - - child_id = get_new_cssid(child_css->ss, depth); - if (IS_ERR(child_id)) - return PTR_ERR(child_id); - - for (i = 0; i < depth; i++) - child_id->stack[i] = parent_id->stack[i]; - child_id->stack[depth] = child_id->id; - /* - * child_id->css pointer will be set after this cgroup is available - * see cgroup_populate_dir() - */ - rcu_assign_pointer(child_css->id, child_id); - - return 0; -} - -/** - * css_lookup - lookup css by id - * @ss: cgroup subsys to be looked into. - * @id: the id - * - * Returns pointer to cgroup_subsys_state if there is valid one with id. - * NULL if not. Should be called under rcu_read_lock() - */ -struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id) -{ - struct css_id *cssid = NULL; - - BUG_ON(!ss->use_id); - cssid = idr_find(&ss->idr, id); - - if (unlikely(!cssid)) - return NULL; - - return rcu_dereference(cssid->css); -} -EXPORT_SYMBOL_GPL(css_lookup); - /** * css_from_dir - get corresponding css from the dentry of a cgroup dir * @dentry: directory dentry of interest diff --git a/kernel/cpu.c b/kernel/cpu.c index 2227b58734a..deff2e69376 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -440,11 +440,6 @@ int cpu_up(unsigned int cpu) { int err = 0; -#ifdef CONFIG_MEMORY_HOTPLUG - int nid; - pg_data_t *pgdat; -#endif - if (!cpu_possible(cpu)) { printk(KERN_ERR "can't online cpu %d because it is not " "configured as may-hotadd at boot time\n", cpu); @@ -455,27 +450,9 @@ int cpu_up(unsigned int cpu) return -EINVAL; } -#ifdef CONFIG_MEMORY_HOTPLUG - nid = cpu_to_node(cpu); - if (!node_online(nid)) { - err = mem_online_node(nid); - if (err) - return err; - } - - pgdat = NODE_DATA(nid); - if (!pgdat) { - printk(KERN_ERR - "Can't online cpu %d due to NULL pgdat\n", cpu); - return -ENOMEM; - } - - if (pgdat->node_zonelists->_zonerefs->zone == NULL) { - mutex_lock(&zonelists_mutex); - build_all_zonelists(NULL, NULL); - mutex_unlock(&zonelists_mutex); - } -#endif + err = try_online_node(cpu_to_node(cpu)); + if (err) + return err; cpu_maps_update_begin(); diff --git a/kernel/delayacct.c b/kernel/delayacct.c index d473988c1d0..54996b71e66 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -108,12 +108,6 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) struct timespec ts; cputime_t utime, stime, stimescaled, utimescaled; - /* Though tsk->delays accessed later, early exit avoids - * unnecessary returning of other data - */ - if (!tsk->delays) - goto done; - tmp = (s64)d->cpu_run_real_total; task_cputime(tsk, &utime, &stime); cputime_to_timespec(utime + stime, &ts); @@ -158,7 +152,6 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->freepages_count += tsk->delays->freepages_count; spin_unlock_irqrestore(&tsk->delays->lock, flags); -done: return 0; } diff --git a/kernel/elfcore.c b/kernel/elfcore.c index ff915efef66..e556751d15d 100644 --- a/kernel/elfcore.c +++ b/kernel/elfcore.c @@ -1,23 +1,19 @@ #include <linux/elf.h> #include <linux/fs.h> #include <linux/mm.h> - -#include <asm/elf.h> - +#include <linux/binfmts.h> Elf_Half __weak elf_core_extra_phdrs(void) { return 0; } -int __weak elf_core_write_extra_phdrs(struct file *file, loff_t offset, size_t *size, - unsigned long limit) +int __weak elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { return 1; } -int __weak elf_core_write_extra_data(struct file *file, size_t *size, - unsigned long limit) +int __weak elf_core_write_extra_data(struct coredump_params *cprm) { return 1; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 8c875ef6e12..d724e7757cd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2234,9 +2234,6 @@ static void __perf_event_sync_stat(struct perf_event *event, perf_event_update_userpage(next_event); } -#define list_next_entry(pos, member) \ - list_entry(pos->member.next, typeof(*pos), member) - static void perf_event_sync_stat(struct perf_event_context *ctx, struct perf_event_context *next_ctx) { diff --git a/kernel/futex.c b/kernel/futex.c index c3a1a55a521..80ba086f021 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -66,7 +66,7 @@ #include <asm/futex.h> -#include "rtmutex_common.h" +#include "locking/rtmutex_common.h" int __read_mostly futex_cmpxchg_enabled; diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index d4da55d1fb6..d04ce8ac439 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -46,4 +46,34 @@ config GCOV_PROFILE_ALL larger and run slower. Also be sure to exclude files from profiling which are not linked to the kernel image to prevent linker errors. +choice + prompt "Specify GCOV format" + depends on GCOV_KERNEL + default GCOV_FORMAT_AUTODETECT + ---help--- + The gcov format is usually determined by the GCC version, but there are + exceptions where format changes are integrated in lower-version GCCs. + In such a case use this option to adjust the format used in the kernel + accordingly. + + If unsure, choose "Autodetect". + +config GCOV_FORMAT_AUTODETECT + bool "Autodetect" + ---help--- + Select this option to use the format that corresponds to your GCC + version. + +config GCOV_FORMAT_3_4 + bool "GCC 3.4 format" + ---help--- + Select this option to use the format defined by GCC 3.4. + +config GCOV_FORMAT_4_7 + bool "GCC 4.7 format" + ---help--- + Select this option to use the format defined by GCC 4.7. + +endchoice + endmenu diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile index e97ca59e252..52aa7e8de92 100644 --- a/kernel/gcov/Makefile +++ b/kernel/gcov/Makefile @@ -1,3 +1,33 @@ ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"' -obj-$(CONFIG_GCOV_KERNEL) := base.o fs.o gcc_3_4.o +# if-lt +# Usage VAR := $(call if-lt, $(a), $(b)) +# Returns 1 if (a < b) +if-lt = $(shell [ $(1) -lt $(2) ] && echo 1) + +ifeq ($(CONFIG_GCOV_FORMAT_3_4),y) + cc-ver := 0304 +else ifeq ($(CONFIG_GCOV_FORMAT_4_7),y) + cc-ver := 0407 +else +# Use cc-version if available, otherwise set 0 +# +# scripts/Kbuild.include, which contains cc-version function, is not included +# during make clean "make -f scripts/Makefile.clean obj=kernel/gcov" +# Meaning cc-ver is empty causing if-lt test to fail with +# "/bin/sh: line 0: [: -lt: unary operator expected" error mesage. +# This has no affect on the clean phase, but the error message could be +# confusing/annoying. So this dummy workaround sets cc-ver to zero if cc-version +# is not available. We can probably move if-lt to Kbuild.include, so it's also +# not defined during clean or to include Kbuild.include in +# scripts/Makefile.clean. But the following workaround seems least invasive. + cc-ver := $(if $(call cc-version),$(call cc-version),0) +endif + +obj-$(CONFIG_GCOV_KERNEL) := base.o fs.o + +ifeq ($(call if-lt, $(cc-ver), 0407),1) + obj-$(CONFIG_GCOV_KERNEL) += gcc_3_4.o +else + obj-$(CONFIG_GCOV_KERNEL) += gcc_4_7.o +endif diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c index 9b22d03cc58..f45b75b713c 100644 --- a/kernel/gcov/base.c +++ b/kernel/gcov/base.c @@ -20,7 +20,6 @@ #include <linux/mutex.h> #include "gcov.h" -static struct gcov_info *gcov_info_head; static int gcov_events_enabled; static DEFINE_MUTEX(gcov_lock); @@ -34,7 +33,7 @@ void __gcov_init(struct gcov_info *info) mutex_lock(&gcov_lock); if (gcov_version == 0) { - gcov_version = info->version; + gcov_version = gcov_info_version(info); /* * Printing gcc's version magic may prove useful for debugging * incompatibility reports. @@ -45,8 +44,7 @@ void __gcov_init(struct gcov_info *info) * Add new profiling data structure to list and inform event * listener. */ - info->next = gcov_info_head; - gcov_info_head = info; + gcov_info_link(info); if (gcov_events_enabled) gcov_event(GCOV_ADD, info); mutex_unlock(&gcov_lock); @@ -81,6 +79,12 @@ void __gcov_merge_delta(gcov_type *counters, unsigned int n_counters) } EXPORT_SYMBOL(__gcov_merge_delta); +void __gcov_merge_ior(gcov_type *counters, unsigned int n_counters) +{ + /* Unused. */ +} +EXPORT_SYMBOL(__gcov_merge_ior); + /** * gcov_enable_events - enable event reporting through gcov_event() * @@ -91,13 +95,15 @@ EXPORT_SYMBOL(__gcov_merge_delta); */ void gcov_enable_events(void) { - struct gcov_info *info; + struct gcov_info *info = NULL; mutex_lock(&gcov_lock); gcov_events_enabled = 1; + /* Perform event callback for previously registered entries. */ - for (info = gcov_info_head; info; info = info->next) + while ((info = gcov_info_next(info))) gcov_event(GCOV_ADD, info); + mutex_unlock(&gcov_lock); } @@ -112,25 +118,23 @@ static int gcov_module_notifier(struct notifier_block *nb, unsigned long event, void *data) { struct module *mod = data; - struct gcov_info *info; - struct gcov_info *prev; + struct gcov_info *info = NULL; + struct gcov_info *prev = NULL; if (event != MODULE_STATE_GOING) return NOTIFY_OK; mutex_lock(&gcov_lock); - prev = NULL; + /* Remove entries located in module from linked list. */ - for (info = gcov_info_head; info; info = info->next) { + while ((info = gcov_info_next(info))) { if (within(info, mod->module_core, mod->core_size)) { - if (prev) - prev->next = info->next; - else - gcov_info_head = info->next; + gcov_info_unlink(prev, info); if (gcov_events_enabled) gcov_event(GCOV_REMOVE, info); } else prev = info; } + mutex_unlock(&gcov_lock); return NOTIFY_OK; diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c index 7a7d2ee96d4..15ff01a7637 100644 --- a/kernel/gcov/fs.c +++ b/kernel/gcov/fs.c @@ -75,7 +75,7 @@ static int __init gcov_persist_setup(char *str) unsigned long val; if (kstrtoul(str, 0, &val)) { - pr_warning("invalid gcov_persist parameter '%s'\n", str); + pr_warn("invalid gcov_persist parameter '%s'\n", str); return 0; } gcov_persist = val; @@ -242,7 +242,7 @@ static struct gcov_node *get_node_by_name(const char *name) list_for_each_entry(node, &all_head, all) { info = get_node_info(node); - if (info && (strcmp(info->filename, name) == 0)) + if (info && (strcmp(gcov_info_filename(info), name) == 0)) return node; } @@ -279,7 +279,7 @@ static ssize_t gcov_seq_write(struct file *file, const char __user *addr, seq = file->private_data; info = gcov_iter_get_info(seq->private); mutex_lock(&node_lock); - node = get_node_by_name(info->filename); + node = get_node_by_name(gcov_info_filename(info)); if (node) { /* Reset counts or remove node for unloaded modules. */ if (node->num_loaded == 0) @@ -365,7 +365,7 @@ static const char *deskew(const char *basename) */ static void add_links(struct gcov_node *node, struct dentry *parent) { - char *basename; + const char *basename; char *target; int num; int i; @@ -376,14 +376,14 @@ static void add_links(struct gcov_node *node, struct dentry *parent) if (!node->links) return; for (i = 0; i < num; i++) { - target = get_link_target(get_node_info(node)->filename, - &gcov_link[i]); + target = get_link_target( + gcov_info_filename(get_node_info(node)), + &gcov_link[i]); if (!target) goto out_err; - basename = strrchr(target, '/'); - if (!basename) + basename = kbasename(target); + if (basename == target) goto out_err; - basename++; node->links[i] = debugfs_create_symlink(deskew(basename), parent, target); if (!node->links[i]) @@ -450,7 +450,7 @@ static struct gcov_node *new_node(struct gcov_node *parent, } else node->dentry = debugfs_create_dir(node->name, parent->dentry); if (!node->dentry) { - pr_warning("could not create file\n"); + pr_warn("could not create file\n"); kfree(node); return NULL; } @@ -463,7 +463,7 @@ static struct gcov_node *new_node(struct gcov_node *parent, err_nomem: kfree(node); - pr_warning("out of memory\n"); + pr_warn("out of memory\n"); return NULL; } @@ -576,7 +576,7 @@ static void add_node(struct gcov_info *info) struct gcov_node *parent; struct gcov_node *node; - filename = kstrdup(info->filename, GFP_KERNEL); + filename = kstrdup(gcov_info_filename(info), GFP_KERNEL); if (!filename) return; parent = &root_node; @@ -630,8 +630,8 @@ static void add_info(struct gcov_node *node, struct gcov_info *info) */ loaded_info = kcalloc(num + 1, sizeof(struct gcov_info *), GFP_KERNEL); if (!loaded_info) { - pr_warning("could not add '%s' (out of memory)\n", - info->filename); + pr_warn("could not add '%s' (out of memory)\n", + gcov_info_filename(info)); return; } memcpy(loaded_info, node->loaded_info, @@ -644,8 +644,9 @@ static void add_info(struct gcov_node *node, struct gcov_info *info) * data set replaces the copy of the last one. */ if (!gcov_info_is_compatible(node->unloaded_info, info)) { - pr_warning("discarding saved data for %s " - "(incompatible version)\n", info->filename); + pr_warn("discarding saved data for %s " + "(incompatible version)\n", + gcov_info_filename(info)); gcov_info_free(node->unloaded_info); node->unloaded_info = NULL; } @@ -655,8 +656,8 @@ static void add_info(struct gcov_node *node, struct gcov_info *info) * The initial one takes precedence. */ if (!gcov_info_is_compatible(node->loaded_info[0], info)) { - pr_warning("could not add '%s' (incompatible " - "version)\n", info->filename); + pr_warn("could not add '%s' (incompatible " + "version)\n", gcov_info_filename(info)); kfree(loaded_info); return; } @@ -691,8 +692,9 @@ static void save_info(struct gcov_node *node, struct gcov_info *info) else { node->unloaded_info = gcov_info_dup(info); if (!node->unloaded_info) { - pr_warning("could not save data for '%s' " - "(out of memory)\n", info->filename); + pr_warn("could not save data for '%s' " + "(out of memory)\n", + gcov_info_filename(info)); } } } @@ -707,8 +709,8 @@ static void remove_info(struct gcov_node *node, struct gcov_info *info) i = get_info_index(node, info); if (i < 0) { - pr_warning("could not remove '%s' (not found)\n", - info->filename); + pr_warn("could not remove '%s' (not found)\n", + gcov_info_filename(info)); return; } if (gcov_persist) @@ -735,7 +737,7 @@ void gcov_event(enum gcov_action action, struct gcov_info *info) struct gcov_node *node; mutex_lock(&node_lock); - node = get_node_by_name(info->filename); + node = get_node_by_name(gcov_info_filename(info)); switch (action) { case GCOV_ADD: if (node) @@ -747,8 +749,8 @@ void gcov_event(enum gcov_action action, struct gcov_info *info) if (node) remove_info(node, info); else { - pr_warning("could not remove '%s' (not found)\n", - info->filename); + pr_warn("could not remove '%s' (not found)\n", + gcov_info_filename(info)); } break; } diff --git a/kernel/gcov/gcc_3_4.c b/kernel/gcov/gcc_3_4.c index ae5bb426003..27bc88a3501 100644 --- a/kernel/gcov/gcc_3_4.c +++ b/kernel/gcov/gcc_3_4.c @@ -21,6 +21,121 @@ #include <linux/vmalloc.h> #include "gcov.h" +#define GCOV_COUNTERS 5 + +static struct gcov_info *gcov_info_head; + +/** + * struct gcov_fn_info - profiling meta data per function + * @ident: object file-unique function identifier + * @checksum: function checksum + * @n_ctrs: number of values per counter type belonging to this function + * + * This data is generated by gcc during compilation and doesn't change + * at run-time. + */ +struct gcov_fn_info { + unsigned int ident; + unsigned int checksum; + unsigned int n_ctrs[0]; +}; + +/** + * struct gcov_ctr_info - profiling data per counter type + * @num: number of counter values for this type + * @values: array of counter values for this type + * @merge: merge function for counter values of this type (unused) + * + * This data is generated by gcc during compilation and doesn't change + * at run-time with the exception of the values array. + */ +struct gcov_ctr_info { + unsigned int num; + gcov_type *values; + void (*merge)(gcov_type *, unsigned int); +}; + +/** + * struct gcov_info - profiling data per object file + * @version: gcov version magic indicating the gcc version used for compilation + * @next: list head for a singly-linked list + * @stamp: time stamp + * @filename: name of the associated gcov data file + * @n_functions: number of instrumented functions + * @functions: function data + * @ctr_mask: mask specifying which counter types are active + * @counts: counter data per counter type + * + * This data is generated by gcc during compilation and doesn't change + * at run-time with the exception of the next pointer. + */ +struct gcov_info { + unsigned int version; + struct gcov_info *next; + unsigned int stamp; + const char *filename; + unsigned int n_functions; + const struct gcov_fn_info *functions; + unsigned int ctr_mask; + struct gcov_ctr_info counts[0]; +}; + +/** + * gcov_info_filename - return info filename + * @info: profiling data set + */ +const char *gcov_info_filename(struct gcov_info *info) +{ + return info->filename; +} + +/** + * gcov_info_version - return info version + * @info: profiling data set + */ +unsigned int gcov_info_version(struct gcov_info *info) +{ + return info->version; +} + +/** + * gcov_info_next - return next profiling data set + * @info: profiling data set + * + * Returns next gcov_info following @info or first gcov_info in the chain if + * @info is %NULL. + */ +struct gcov_info *gcov_info_next(struct gcov_info *info) +{ + if (!info) + return gcov_info_head; + + return info->next; +} + +/** + * gcov_info_link - link/add profiling data set to the list + * @info: profiling data set + */ +void gcov_info_link(struct gcov_info *info) +{ + info->next = gcov_info_head; + gcov_info_head = info; +} + +/** + * gcov_info_unlink - unlink/remove profiling data set from the list + * @prev: previous profiling data set + * @info: profiling data set + */ +void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info) +{ + if (prev) + prev->next = info->next; + else + gcov_info_head = info->next; +} + /* Symbolic links to be created for each profiling data file. */ const struct gcov_link gcov_link[] = { { OBJ_TREE, "gcno" }, /* Link to .gcno file in $(objtree). */ diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c new file mode 100644 index 00000000000..2c6e4631c81 --- /dev/null +++ b/kernel/gcov/gcc_4_7.c @@ -0,0 +1,560 @@ +/* + * This code provides functions to handle gcc's profiling data format + * introduced with gcc 4.7. + * + * This file is based heavily on gcc_3_4.c file. + * + * For a better understanding, refer to gcc source: + * gcc/gcov-io.h + * libgcc/libgcov.c + * + * Uses gcc-internal data definitions. + */ + +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/seq_file.h> +#include <linux/vmalloc.h> +#include "gcov.h" + +#define GCOV_COUNTERS 8 +#define GCOV_TAG_FUNCTION_LENGTH 3 + +static struct gcov_info *gcov_info_head; + +/** + * struct gcov_ctr_info - information about counters for a single function + * @num: number of counter values for this type + * @values: array of counter values for this type + * + * This data is generated by gcc during compilation and doesn't change + * at run-time with the exception of the values array. + */ +struct gcov_ctr_info { + unsigned int num; + gcov_type *values; +}; + +/** + * struct gcov_fn_info - profiling meta data per function + * @key: comdat key + * @ident: unique ident of function + * @lineno_checksum: function lineo_checksum + * @cfg_checksum: function cfg checksum + * @ctrs: instrumented counters + * + * This data is generated by gcc during compilation and doesn't change + * at run-time. + * + * Information about a single function. This uses the trailing array + * idiom. The number of counters is determined from the merge pointer + * array in gcov_info. The key is used to detect which of a set of + * comdat functions was selected -- it points to the gcov_info object + * of the object file containing the selected comdat function. + */ +struct gcov_fn_info { + const struct gcov_info *key; + unsigned int ident; + unsigned int lineno_checksum; + unsigned int cfg_checksum; + struct gcov_ctr_info ctrs[0]; +}; + +/** + * struct gcov_info - profiling data per object file + * @version: gcov version magic indicating the gcc version used for compilation + * @next: list head for a singly-linked list + * @stamp: uniquifying time stamp + * @filename: name of the associated gcov data file + * @merge: merge functions (null for unused counter type) + * @n_functions: number of instrumented functions + * @functions: pointer to pointers to function information + * + * This data is generated by gcc during compilation and doesn't change + * at run-time with the exception of the next pointer. + */ +struct gcov_info { + unsigned int version; + struct gcov_info *next; + unsigned int stamp; + const char *filename; + void (*merge[GCOV_COUNTERS])(gcov_type *, unsigned int); + unsigned int n_functions; + struct gcov_fn_info **functions; +}; + +/** + * gcov_info_filename - return info filename + * @info: profiling data set + */ +const char *gcov_info_filename(struct gcov_info *info) +{ + return info->filename; +} + +/** + * gcov_info_version - return info version + * @info: profiling data set + */ +unsigned int gcov_info_version(struct gcov_info *info) +{ + return info->version; +} + +/** + * gcov_info_next - return next profiling data set + * @info: profiling data set + * + * Returns next gcov_info following @info or first gcov_info in the chain if + * @info is %NULL. + */ +struct gcov_info *gcov_info_next(struct gcov_info *info) +{ + if (!info) + return gcov_info_head; + + return info->next; +} + +/** + * gcov_info_link - link/add profiling data set to the list + * @info: profiling data set + */ +void gcov_info_link(struct gcov_info *info) +{ + info->next = gcov_info_head; + gcov_info_head = info; +} + +/** + * gcov_info_unlink - unlink/remove profiling data set from the list + * @prev: previous profiling data set + * @info: profiling data set + */ +void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info) +{ + if (prev) + prev->next = info->next; + else + gcov_info_head = info->next; +} + +/* Symbolic links to be created for each profiling data file. */ +const struct gcov_link gcov_link[] = { + { OBJ_TREE, "gcno" }, /* Link to .gcno file in $(objtree). */ + { 0, NULL}, +}; + +/* + * Determine whether a counter is active. Doesn't change at run-time. + */ +static int counter_active(struct gcov_info *info, unsigned int type) +{ + return info->merge[type] ? 1 : 0; +} + +/* Determine number of active counters. Based on gcc magic. */ +static unsigned int num_counter_active(struct gcov_info *info) +{ + unsigned int i; + unsigned int result = 0; + + for (i = 0; i < GCOV_COUNTERS; i++) { + if (counter_active(info, i)) + result++; + } + return result; +} + +/** + * gcov_info_reset - reset profiling data to zero + * @info: profiling data set + */ +void gcov_info_reset(struct gcov_info *info) +{ + struct gcov_ctr_info *ci_ptr; + unsigned int fi_idx; + unsigned int ct_idx; + + for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) { + ci_ptr = info->functions[fi_idx]->ctrs; + + for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) { + if (!counter_active(info, ct_idx)) + continue; + + memset(ci_ptr->values, 0, + sizeof(gcov_type) * ci_ptr->num); + ci_ptr++; + } + } +} + +/** + * gcov_info_is_compatible - check if profiling data can be added + * @info1: first profiling data set + * @info2: second profiling data set + * + * Returns non-zero if profiling data can be added, zero otherwise. + */ +int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2) +{ + return (info1->stamp == info2->stamp); +} + +/** + * gcov_info_add - add up profiling data + * @dest: profiling data set to which data is added + * @source: profiling data set which is added + * + * Adds profiling counts of @source to @dest. + */ +void gcov_info_add(struct gcov_info *dst, struct gcov_info *src) +{ + struct gcov_ctr_info *dci_ptr; + struct gcov_ctr_info *sci_ptr; + unsigned int fi_idx; + unsigned int ct_idx; + unsigned int val_idx; + + for (fi_idx = 0; fi_idx < src->n_functions; fi_idx++) { + dci_ptr = dst->functions[fi_idx]->ctrs; + sci_ptr = src->functions[fi_idx]->ctrs; + + for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) { + if (!counter_active(src, ct_idx)) + continue; + + for (val_idx = 0; val_idx < sci_ptr->num; val_idx++) + dci_ptr->values[val_idx] += + sci_ptr->values[val_idx]; + + dci_ptr++; + sci_ptr++; + } + } +} + +/** + * gcov_info_dup - duplicate profiling data set + * @info: profiling data set to duplicate + * + * Return newly allocated duplicate on success, %NULL on error. + */ +struct gcov_info *gcov_info_dup(struct gcov_info *info) +{ + struct gcov_info *dup; + struct gcov_ctr_info *dci_ptr; /* dst counter info */ + struct gcov_ctr_info *sci_ptr; /* src counter info */ + unsigned int active; + unsigned int fi_idx; /* function info idx */ + unsigned int ct_idx; /* counter type idx */ + size_t fi_size; /* function info size */ + size_t cv_size; /* counter values size */ + + dup = kmemdup(info, sizeof(*dup), GFP_KERNEL); + if (!dup) + return NULL; + + dup->next = NULL; + dup->filename = NULL; + dup->functions = NULL; + + dup->filename = kstrdup(info->filename, GFP_KERNEL); + if (!dup->filename) + goto err_free; + + dup->functions = kcalloc(info->n_functions, + sizeof(struct gcov_fn_info *), GFP_KERNEL); + if (!dup->functions) + goto err_free; + + active = num_counter_active(info); + fi_size = sizeof(struct gcov_fn_info); + fi_size += sizeof(struct gcov_ctr_info) * active; + + for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) { + dup->functions[fi_idx] = kzalloc(fi_size, GFP_KERNEL); + if (!dup->functions[fi_idx]) + goto err_free; + + *(dup->functions[fi_idx]) = *(info->functions[fi_idx]); + + sci_ptr = info->functions[fi_idx]->ctrs; + dci_ptr = dup->functions[fi_idx]->ctrs; + + for (ct_idx = 0; ct_idx < active; ct_idx++) { + + cv_size = sizeof(gcov_type) * sci_ptr->num; + + dci_ptr->values = vmalloc(cv_size); + + if (!dci_ptr->values) + goto err_free; + + dci_ptr->num = sci_ptr->num; + memcpy(dci_ptr->values, sci_ptr->values, cv_size); + + sci_ptr++; + dci_ptr++; + } + } + + return dup; +err_free: + gcov_info_free(dup); + return NULL; +} + +/** + * gcov_info_free - release memory for profiling data set duplicate + * @info: profiling data set duplicate to free + */ +void gcov_info_free(struct gcov_info *info) +{ + unsigned int active; + unsigned int fi_idx; + unsigned int ct_idx; + struct gcov_ctr_info *ci_ptr; + + if (!info->functions) + goto free_info; + + active = num_counter_active(info); + + for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) { + if (!info->functions[fi_idx]) + continue; + + ci_ptr = info->functions[fi_idx]->ctrs; + + for (ct_idx = 0; ct_idx < active; ct_idx++, ci_ptr++) + vfree(ci_ptr->values); + + kfree(info->functions[fi_idx]); + } + +free_info: + kfree(info->functions); + kfree(info->filename); + kfree(info); +} + +#define ITER_STRIDE PAGE_SIZE + +/** + * struct gcov_iterator - specifies current file position in logical records + * @info: associated profiling data + * @buffer: buffer containing file data + * @size: size of buffer + * @pos: current position in file + */ +struct gcov_iterator { + struct gcov_info *info; + void *buffer; + size_t size; + loff_t pos; +}; + +/** + * store_gcov_u32 - store 32 bit number in gcov format to buffer + * @buffer: target buffer or NULL + * @off: offset into the buffer + * @v: value to be stored + * + * Number format defined by gcc: numbers are recorded in the 32 bit + * unsigned binary form of the endianness of the machine generating the + * file. Returns the number of bytes stored. If @buffer is %NULL, doesn't + * store anything. + */ +static size_t store_gcov_u32(void *buffer, size_t off, u32 v) +{ + u32 *data; + + if (buffer) { + data = buffer + off; + *data = v; + } + + return sizeof(*data); +} + +/** + * store_gcov_u64 - store 64 bit number in gcov format to buffer + * @buffer: target buffer or NULL + * @off: offset into the buffer + * @v: value to be stored + * + * Number format defined by gcc: numbers are recorded in the 32 bit + * unsigned binary form of the endianness of the machine generating the + * file. 64 bit numbers are stored as two 32 bit numbers, the low part + * first. Returns the number of bytes stored. If @buffer is %NULL, doesn't store + * anything. + */ +static size_t store_gcov_u64(void *buffer, size_t off, u64 v) +{ + u32 *data; + + if (buffer) { + data = buffer + off; + + data[0] = (v & 0xffffffffUL); + data[1] = (v >> 32); + } + + return sizeof(*data) * 2; +} + +/** + * convert_to_gcda - convert profiling data set to gcda file format + * @buffer: the buffer to store file data or %NULL if no data should be stored + * @info: profiling data set to be converted + * + * Returns the number of bytes that were/would have been stored into the buffer. + */ +static size_t convert_to_gcda(char *buffer, struct gcov_info *info) +{ + struct gcov_fn_info *fi_ptr; + struct gcov_ctr_info *ci_ptr; + unsigned int fi_idx; + unsigned int ct_idx; + unsigned int cv_idx; + size_t pos = 0; + + /* File header. */ + pos += store_gcov_u32(buffer, pos, GCOV_DATA_MAGIC); + pos += store_gcov_u32(buffer, pos, info->version); + pos += store_gcov_u32(buffer, pos, info->stamp); + + for (fi_idx = 0; fi_idx < info->n_functions; fi_idx++) { + fi_ptr = info->functions[fi_idx]; + + /* Function record. */ + pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION); + pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION_LENGTH); + pos += store_gcov_u32(buffer, pos, fi_ptr->ident); + pos += store_gcov_u32(buffer, pos, fi_ptr->lineno_checksum); + pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum); + + ci_ptr = fi_ptr->ctrs; + + for (ct_idx = 0; ct_idx < GCOV_COUNTERS; ct_idx++) { + if (!counter_active(info, ct_idx)) + continue; + + /* Counter record. */ + pos += store_gcov_u32(buffer, pos, + GCOV_TAG_FOR_COUNTER(ct_idx)); + pos += store_gcov_u32(buffer, pos, ci_ptr->num * 2); + + for (cv_idx = 0; cv_idx < ci_ptr->num; cv_idx++) { + pos += store_gcov_u64(buffer, pos, + ci_ptr->values[cv_idx]); + } + + ci_ptr++; + } + } + + return pos; +} + +/** + * gcov_iter_new - allocate and initialize profiling data iterator + * @info: profiling data set to be iterated + * + * Return file iterator on success, %NULL otherwise. + */ +struct gcov_iterator *gcov_iter_new(struct gcov_info *info) +{ + struct gcov_iterator *iter; + + iter = kzalloc(sizeof(struct gcov_iterator), GFP_KERNEL); + if (!iter) + goto err_free; + + iter->info = info; + /* Dry-run to get the actual buffer size. */ + iter->size = convert_to_gcda(NULL, info); + iter->buffer = vmalloc(iter->size); + if (!iter->buffer) + goto err_free; + + convert_to_gcda(iter->buffer, info); + + return iter; + +err_free: + kfree(iter); + return NULL; +} + + +/** + * gcov_iter_get_info - return profiling data set for given file iterator + * @iter: file iterator + */ +void gcov_iter_free(struct gcov_iterator *iter) +{ + vfree(iter->buffer); + kfree(iter); +} + +/** + * gcov_iter_get_info - return profiling data set for given file iterator + * @iter: file iterator + */ +struct gcov_info *gcov_iter_get_info(struct gcov_iterator *iter) +{ + return iter->info; +} + +/** + * gcov_iter_start - reset file iterator to starting position + * @iter: file iterator + */ +void gcov_iter_start(struct gcov_iterator *iter) +{ + iter->pos = 0; +} + +/** + * gcov_iter_next - advance file iterator to next logical record + * @iter: file iterator + * + * Return zero if new position is valid, non-zero if iterator has reached end. + */ +int gcov_iter_next(struct gcov_iterator *iter) +{ + if (iter->pos < iter->size) + iter->pos += ITER_STRIDE; + + if (iter->pos >= iter->size) + return -EINVAL; + + return 0; +} + +/** + * gcov_iter_write - write data for current pos to seq_file + * @iter: file iterator + * @seq: seq_file handle + * + * Return zero on success, non-zero otherwise. + */ +int gcov_iter_write(struct gcov_iterator *iter, struct seq_file *seq) +{ + size_t len; + + if (iter->pos >= iter->size) + return -EINVAL; + + len = ITER_STRIDE; + if (iter->pos + len > iter->size) + len = iter->size - iter->pos; + + seq_write(seq, iter->buffer + iter->pos, len); + + return 0; +} diff --git a/kernel/gcov/gcov.h b/kernel/gcov/gcov.h index 060073ebf7a..92c8e22a29e 100644 --- a/kernel/gcov/gcov.h +++ b/kernel/gcov/gcov.h @@ -21,7 +21,6 @@ * gcc and need to be kept as close to the original definition as possible to * remain compatible. */ -#define GCOV_COUNTERS 5 #define GCOV_DATA_MAGIC ((unsigned int) 0x67636461) #define GCOV_TAG_FUNCTION ((unsigned int) 0x01000000) #define GCOV_TAG_COUNTER_BASE ((unsigned int) 0x01a10000) @@ -34,60 +33,18 @@ typedef long gcov_type; typedef long long gcov_type; #endif -/** - * struct gcov_fn_info - profiling meta data per function - * @ident: object file-unique function identifier - * @checksum: function checksum - * @n_ctrs: number of values per counter type belonging to this function - * - * This data is generated by gcc during compilation and doesn't change - * at run-time. - */ -struct gcov_fn_info { - unsigned int ident; - unsigned int checksum; - unsigned int n_ctrs[0]; -}; - -/** - * struct gcov_ctr_info - profiling data per counter type - * @num: number of counter values for this type - * @values: array of counter values for this type - * @merge: merge function for counter values of this type (unused) - * - * This data is generated by gcc during compilation and doesn't change - * at run-time with the exception of the values array. - */ -struct gcov_ctr_info { - unsigned int num; - gcov_type *values; - void (*merge)(gcov_type *, unsigned int); -}; +/* Opaque gcov_info. The gcov structures can change as for example in gcc 4.7 so + * we cannot use full definition here and they need to be placed in gcc specific + * implementation of gcov. This also means no direct access to the members in + * generic code and usage of the interface below.*/ +struct gcov_info; -/** - * struct gcov_info - profiling data per object file - * @version: gcov version magic indicating the gcc version used for compilation - * @next: list head for a singly-linked list - * @stamp: time stamp - * @filename: name of the associated gcov data file - * @n_functions: number of instrumented functions - * @functions: function data - * @ctr_mask: mask specifying which counter types are active - * @counts: counter data per counter type - * - * This data is generated by gcc during compilation and doesn't change - * at run-time with the exception of the next pointer. - */ -struct gcov_info { - unsigned int version; - struct gcov_info *next; - unsigned int stamp; - const char *filename; - unsigned int n_functions; - const struct gcov_fn_info *functions; - unsigned int ctr_mask; - struct gcov_ctr_info counts[0]; -}; +/* Interface to access gcov_info data */ +const char *gcov_info_filename(struct gcov_info *info); +unsigned int gcov_info_version(struct gcov_info *info); +struct gcov_info *gcov_info_next(struct gcov_info *info); +void gcov_info_link(struct gcov_info *info); +void gcov_info_unlink(struct gcov_info *prev, struct gcov_info *info); /* Base interface. */ enum gcov_action { diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 3e97fb126e6..8807061ca00 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -16,11 +16,12 @@ #include <linux/export.h> #include <linux/sysctl.h> #include <linux/utsname.h> +#include <trace/events/sched.h> /* * The number of tasks checked: */ -unsigned long __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT; +int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT; /* * Limit number of tasks checked in a batch. @@ -92,6 +93,9 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) t->last_switch_count = switch_count; return; } + + trace_sched_process_hang(t); + if (!sysctl_hung_task_warnings) return; sysctl_hung_task_warnings--; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 706724e9835..cf68bb36fe5 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -465,27 +465,26 @@ int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base, } EXPORT_SYMBOL_GPL(irq_create_strict_mappings); -unsigned int irq_create_of_mapping(struct device_node *controller, - const u32 *intspec, unsigned int intsize) +unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) { struct irq_domain *domain; irq_hw_number_t hwirq; unsigned int type = IRQ_TYPE_NONE; unsigned int virq; - domain = controller ? irq_find_host(controller) : irq_default_domain; + domain = irq_data->np ? irq_find_host(irq_data->np) : irq_default_domain; if (!domain) { pr_warn("no irq domain found for %s !\n", - of_node_full_name(controller)); + of_node_full_name(irq_data->np)); return 0; } /* If domain has no translation, then we assume interrupt line */ if (domain->ops->xlate == NULL) - hwirq = intspec[0]; + hwirq = irq_data->args[0]; else { - if (domain->ops->xlate(domain, controller, intspec, intsize, - &hwirq, &type)) + if (domain->ops->xlate(domain, irq_data->np, irq_data->args, + irq_data->args_count, &hwirq, &type)) return 0; } diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 297a9247a3b..9019f15deab 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -58,6 +58,7 @@ static void jump_label_update(struct static_key *key, int enable); void static_key_slow_inc(struct static_key *key) { + STATIC_KEY_CHECK_USE(); if (atomic_inc_not_zero(&key->enabled)) return; @@ -103,12 +104,14 @@ static void jump_label_update_timeout(struct work_struct *work) void static_key_slow_dec(struct static_key *key) { + STATIC_KEY_CHECK_USE(); __static_key_slow_dec(key, 0, NULL); } EXPORT_SYMBOL_GPL(static_key_slow_dec); void static_key_slow_dec_deferred(struct static_key_deferred *key) { + STATIC_KEY_CHECK_USE(); __static_key_slow_dec(&key->key, key->timeout, &key->work); } EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred); @@ -116,6 +119,7 @@ EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred); void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { + STATIC_KEY_CHECK_USE(); key->timeout = rl; INIT_DELAYED_WORK(&key->work, jump_label_update_timeout); } @@ -212,6 +216,7 @@ void __init jump_label_init(void) key->next = NULL; #endif } + static_key_initialized = true; jump_label_unlock(); } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index a0d367a4912..ceeadfcabb7 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2066,7 +2066,7 @@ static int __init init_kprobes(void) { int i, err = 0; unsigned long offset = 0, size = 0; - char *modname, namebuf[128]; + char *modname, namebuf[KSYM_NAME_LEN]; const char *symbol_name; void *addr; struct kprobe_blackpoint *kb; @@ -2192,7 +2192,7 @@ static int __kprobes show_kprobe_addr(struct seq_file *pi, void *v) const char *sym = NULL; unsigned int i = *(loff_t *) v; unsigned long offset = 0; - char *modname, namebuf[128]; + char *modname, namebuf[KSYM_NAME_LEN]; head = &kprobe_table[i]; preempt_disable(); diff --git a/kernel/kthread.c b/kernel/kthread.c index 760e86df8c2..b5ae3ee860a 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -33,7 +33,7 @@ struct kthread_create_info /* Result passed back to kthread_create() from kthreadd. */ struct task_struct *result; - struct completion done; + struct completion *done; struct list_head list; }; @@ -178,6 +178,7 @@ static int kthread(void *_create) struct kthread_create_info *create = _create; int (*threadfn)(void *data) = create->threadfn; void *data = create->data; + struct completion *done; struct kthread self; int ret; @@ -187,10 +188,16 @@ static int kthread(void *_create) init_completion(&self.parked); current->vfork_done = &self.exited; + /* If user was SIGKILLed, I release the structure. */ + done = xchg(&create->done, NULL); + if (!done) { + kfree(create); + do_exit(-EINTR); + } /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); create->result = current; - complete(&create->done); + complete(done); schedule(); ret = -EINTR; @@ -223,8 +230,15 @@ static void create_kthread(struct kthread_create_info *create) /* We want our own signal handler (we take no signals by default). */ pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD); if (pid < 0) { + /* If user was SIGKILLed, I release the structure. */ + struct completion *done = xchg(&create->done, NULL); + + if (!done) { + kfree(create); + return; + } create->result = ERR_PTR(pid); - complete(&create->done); + complete(done); } } @@ -255,36 +269,59 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), const char namefmt[], ...) { - struct kthread_create_info create; - - create.threadfn = threadfn; - create.data = data; - create.node = node; - init_completion(&create.done); + DECLARE_COMPLETION_ONSTACK(done); + struct task_struct *task; + struct kthread_create_info *create = kmalloc(sizeof(*create), + GFP_KERNEL); + + if (!create) + return ERR_PTR(-ENOMEM); + create->threadfn = threadfn; + create->data = data; + create->node = node; + create->done = &done; spin_lock(&kthread_create_lock); - list_add_tail(&create.list, &kthread_create_list); + list_add_tail(&create->list, &kthread_create_list); spin_unlock(&kthread_create_lock); wake_up_process(kthreadd_task); - wait_for_completion(&create.done); - - if (!IS_ERR(create.result)) { + /* + * Wait for completion in killable state, for I might be chosen by + * the OOM killer while kthreadd is trying to allocate memory for + * new kernel thread. + */ + if (unlikely(wait_for_completion_killable(&done))) { + /* + * If I was SIGKILLed before kthreadd (or new kernel thread) + * calls complete(), leave the cleanup of this structure to + * that thread. + */ + if (xchg(&create->done, NULL)) + return ERR_PTR(-ENOMEM); + /* + * kthreadd (or new kernel thread) will call complete() + * shortly. + */ + wait_for_completion(&done); + } + task = create->result; + if (!IS_ERR(task)) { static const struct sched_param param = { .sched_priority = 0 }; va_list args; va_start(args, namefmt); - vsnprintf(create.result->comm, sizeof(create.result->comm), - namefmt, args); + vsnprintf(task->comm, sizeof(task->comm), namefmt, args); va_end(args); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. */ - sched_setscheduler_nocheck(create.result, SCHED_NORMAL, ¶m); - set_cpus_allowed_ptr(create.result, cpu_all_mask); + sched_setscheduler_nocheck(task, SCHED_NORMAL, ¶m); + set_cpus_allowed_ptr(task, cpu_all_mask); } - return create.result; + kfree(create); + return task; } EXPORT_SYMBOL(kthread_create_on_node); diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile new file mode 100644 index 00000000000..baab8e5e7f6 --- /dev/null +++ b/kernel/locking/Makefile @@ -0,0 +1,25 @@ + +obj-y += mutex.o semaphore.o rwsem.o lglock.o + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_lockdep.o = -pg +CFLAGS_REMOVE_lockdep_proc.o = -pg +CFLAGS_REMOVE_mutex-debug.o = -pg +CFLAGS_REMOVE_rtmutex-debug.o = -pg +endif + +obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o +obj-$(CONFIG_LOCKDEP) += lockdep.o +ifeq ($(CONFIG_PROC_FS),y) +obj-$(CONFIG_LOCKDEP) += lockdep_proc.o +endif +obj-$(CONFIG_SMP) += spinlock.o +obj-$(CONFIG_PROVE_LOCKING) += spinlock.o +obj-$(CONFIG_RT_MUTEXES) += rtmutex.o +obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o +obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o +obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o +obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o +obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o +obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o +obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o diff --git a/kernel/lglock.c b/kernel/locking/lglock.c index 86ae2aebf00..86ae2aebf00 100644 --- a/kernel/lglock.c +++ b/kernel/locking/lglock.c diff --git a/kernel/lockdep.c b/kernel/locking/lockdep.c index 4e8e14c34e4..576ba756a32 100644 --- a/kernel/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1232,7 +1232,7 @@ static int noop_count(struct lock_list *entry, void *data) return 0; } -unsigned long __lockdep_count_forward_deps(struct lock_list *this) +static unsigned long __lockdep_count_forward_deps(struct lock_list *this) { unsigned long count = 0; struct lock_list *uninitialized_var(target_entry); @@ -1258,7 +1258,7 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class) return ret; } -unsigned long __lockdep_count_backward_deps(struct lock_list *this) +static unsigned long __lockdep_count_backward_deps(struct lock_list *this) { unsigned long count = 0; struct lock_list *uninitialized_var(target_entry); diff --git a/kernel/lockdep_internals.h b/kernel/locking/lockdep_internals.h index 4f560cfedc8..4f560cfedc8 100644 --- a/kernel/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h diff --git a/kernel/lockdep_proc.c b/kernel/locking/lockdep_proc.c index b2c71c5873e..ef43ac4bafb 100644 --- a/kernel/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -421,6 +421,7 @@ static void seq_lock_time(struct seq_file *m, struct lock_time *lt) seq_time(m, lt->min); seq_time(m, lt->max); seq_time(m, lt->total); + seq_time(m, lt->nr ? div_s64(lt->total, lt->nr) : 0); } static void seq_stats(struct seq_file *m, struct lock_stat_data *data) @@ -518,20 +519,20 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data) } if (i) { seq_puts(m, "\n"); - seq_line(m, '.', 0, 40 + 1 + 10 * (14 + 1)); + seq_line(m, '.', 0, 40 + 1 + 12 * (14 + 1)); seq_puts(m, "\n"); } } static void seq_header(struct seq_file *m) { - seq_printf(m, "lock_stat version 0.3\n"); + seq_puts(m, "lock_stat version 0.4\n"); if (unlikely(!debug_locks)) seq_printf(m, "*WARNING* lock debugging disabled!! - possibly due to a lockdep warning\n"); - seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1)); - seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s " + seq_line(m, '-', 0, 40 + 1 + 12 * (14 + 1)); + seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s %14s %14s " "%14s %14s\n", "class name", "con-bounces", @@ -539,12 +540,14 @@ static void seq_header(struct seq_file *m) "waittime-min", "waittime-max", "waittime-total", + "waittime-avg", "acq-bounces", "acquisitions", "holdtime-min", "holdtime-max", - "holdtime-total"); - seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1)); + "holdtime-total", + "holdtime-avg"); + seq_line(m, '-', 0, 40 + 1 + 12 * (14 + 1)); seq_printf(m, "\n"); } diff --git a/kernel/lockdep_states.h b/kernel/locking/lockdep_states.h index 995b0cc2b84..995b0cc2b84 100644 --- a/kernel/lockdep_states.h +++ b/kernel/locking/lockdep_states.h diff --git a/kernel/mutex-debug.c b/kernel/locking/mutex-debug.c index 7e3443fe1f4..7e3443fe1f4 100644 --- a/kernel/mutex-debug.c +++ b/kernel/locking/mutex-debug.c diff --git a/kernel/mutex-debug.h b/kernel/locking/mutex-debug.h index 0799fd3e4cf..0799fd3e4cf 100644 --- a/kernel/mutex-debug.h +++ b/kernel/locking/mutex-debug.h diff --git a/kernel/mutex.c b/kernel/locking/mutex.c index d24105b1b79..4dd6e4c219d 100644 --- a/kernel/mutex.c +++ b/kernel/locking/mutex.c @@ -1,5 +1,5 @@ /* - * kernel/mutex.c + * kernel/locking/mutex.c * * Mutexes: blocking mutual exclusion locks * diff --git a/kernel/mutex.h b/kernel/locking/mutex.h index 4115fbf83b1..4115fbf83b1 100644 --- a/kernel/mutex.h +++ b/kernel/locking/mutex.h diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c new file mode 100644 index 00000000000..652a8ee8efe --- /dev/null +++ b/kernel/locking/percpu-rwsem.c @@ -0,0 +1,165 @@ +#include <linux/atomic.h> +#include <linux/rwsem.h> +#include <linux/percpu.h> +#include <linux/wait.h> +#include <linux/lockdep.h> +#include <linux/percpu-rwsem.h> +#include <linux/rcupdate.h> +#include <linux/sched.h> +#include <linux/errno.h> + +int __percpu_init_rwsem(struct percpu_rw_semaphore *brw, + const char *name, struct lock_class_key *rwsem_key) +{ + brw->fast_read_ctr = alloc_percpu(int); + if (unlikely(!brw->fast_read_ctr)) + return -ENOMEM; + + /* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */ + __init_rwsem(&brw->rw_sem, name, rwsem_key); + atomic_set(&brw->write_ctr, 0); + atomic_set(&brw->slow_read_ctr, 0); + init_waitqueue_head(&brw->write_waitq); + return 0; +} + +void percpu_free_rwsem(struct percpu_rw_semaphore *brw) +{ + free_percpu(brw->fast_read_ctr); + brw->fast_read_ctr = NULL; /* catch use after free bugs */ +} + +/* + * This is the fast-path for down_read/up_read, it only needs to ensure + * there is no pending writer (atomic_read(write_ctr) == 0) and inc/dec the + * fast per-cpu counter. The writer uses synchronize_sched_expedited() to + * serialize with the preempt-disabled section below. + * + * The nontrivial part is that we should guarantee acquire/release semantics + * in case when + * + * R_W: down_write() comes after up_read(), the writer should see all + * changes done by the reader + * or + * W_R: down_read() comes after up_write(), the reader should see all + * changes done by the writer + * + * If this helper fails the callers rely on the normal rw_semaphore and + * atomic_dec_and_test(), so in this case we have the necessary barriers. + * + * But if it succeeds we do not have any barriers, atomic_read(write_ctr) or + * __this_cpu_add() below can be reordered with any LOAD/STORE done by the + * reader inside the critical section. See the comments in down_write and + * up_write below. + */ +static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val) +{ + bool success = false; + + preempt_disable(); + if (likely(!atomic_read(&brw->write_ctr))) { + __this_cpu_add(*brw->fast_read_ctr, val); + success = true; + } + preempt_enable(); + + return success; +} + +/* + * Like the normal down_read() this is not recursive, the writer can + * come after the first percpu_down_read() and create the deadlock. + * + * Note: returns with lock_is_held(brw->rw_sem) == T for lockdep, + * percpu_up_read() does rwsem_release(). This pairs with the usage + * of ->rw_sem in percpu_down/up_write(). + */ +void percpu_down_read(struct percpu_rw_semaphore *brw) +{ + might_sleep(); + if (likely(update_fast_ctr(brw, +1))) { + rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_); + return; + } + + down_read(&brw->rw_sem); + atomic_inc(&brw->slow_read_ctr); + /* avoid up_read()->rwsem_release() */ + __up_read(&brw->rw_sem); +} + +void percpu_up_read(struct percpu_rw_semaphore *brw) +{ + rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_); + + if (likely(update_fast_ctr(brw, -1))) + return; + + /* false-positive is possible but harmless */ + if (atomic_dec_and_test(&brw->slow_read_ctr)) + wake_up_all(&brw->write_waitq); +} + +static int clear_fast_ctr(struct percpu_rw_semaphore *brw) +{ + unsigned int sum = 0; + int cpu; + + for_each_possible_cpu(cpu) { + sum += per_cpu(*brw->fast_read_ctr, cpu); + per_cpu(*brw->fast_read_ctr, cpu) = 0; + } + + return sum; +} + +/* + * A writer increments ->write_ctr to force the readers to switch to the + * slow mode, note the atomic_read() check in update_fast_ctr(). + * + * After that the readers can only inc/dec the slow ->slow_read_ctr counter, + * ->fast_read_ctr is stable. Once the writer moves its sum into the slow + * counter it represents the number of active readers. + * + * Finally the writer takes ->rw_sem for writing and blocks the new readers, + * then waits until the slow counter becomes zero. + */ +void percpu_down_write(struct percpu_rw_semaphore *brw) +{ + /* tell update_fast_ctr() there is a pending writer */ + atomic_inc(&brw->write_ctr); + /* + * 1. Ensures that write_ctr != 0 is visible to any down_read/up_read + * so that update_fast_ctr() can't succeed. + * + * 2. Ensures we see the result of every previous this_cpu_add() in + * update_fast_ctr(). + * + * 3. Ensures that if any reader has exited its critical section via + * fast-path, it executes a full memory barrier before we return. + * See R_W case in the comment above update_fast_ctr(). + */ + synchronize_sched_expedited(); + + /* exclude other writers, and block the new readers completely */ + down_write(&brw->rw_sem); + + /* nobody can use fast_read_ctr, move its sum into slow_read_ctr */ + atomic_add(clear_fast_ctr(brw), &brw->slow_read_ctr); + + /* wait for all readers to complete their percpu_up_read() */ + wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr)); +} + +void percpu_up_write(struct percpu_rw_semaphore *brw) +{ + /* release the lock, but the readers can't use the fast-path */ + up_write(&brw->rw_sem); + /* + * Insert the barrier before the next fast-path in down_read, + * see W_R case in the comment above update_fast_ctr(). + */ + synchronize_sched_expedited(); + /* the last writer unblocks update_fast_ctr() */ + atomic_dec(&brw->write_ctr); +} diff --git a/kernel/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c index 13b243a323f..13b243a323f 100644 --- a/kernel/rtmutex-debug.c +++ b/kernel/locking/rtmutex-debug.c diff --git a/kernel/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h index 14193d596d7..14193d596d7 100644 --- a/kernel/rtmutex-debug.h +++ b/kernel/locking/rtmutex-debug.h diff --git a/kernel/rtmutex-tester.c b/kernel/locking/rtmutex-tester.c index 1d96dd0d93c..1d96dd0d93c 100644 --- a/kernel/rtmutex-tester.c +++ b/kernel/locking/rtmutex-tester.c diff --git a/kernel/rtmutex.c b/kernel/locking/rtmutex.c index 0dd6aec1cb6..0dd6aec1cb6 100644 --- a/kernel/rtmutex.c +++ b/kernel/locking/rtmutex.c diff --git a/kernel/rtmutex.h b/kernel/locking/rtmutex.h index a1a1dd06421..a1a1dd06421 100644 --- a/kernel/rtmutex.h +++ b/kernel/locking/rtmutex.h diff --git a/kernel/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 53a66c85261..53a66c85261 100644 --- a/kernel/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c new file mode 100644 index 00000000000..9be8a914497 --- /dev/null +++ b/kernel/locking/rwsem-spinlock.c @@ -0,0 +1,296 @@ +/* rwsem-spinlock.c: R/W semaphores: contention handling functions for + * generic spinlock implementation + * + * Copyright (c) 2001 David Howells (dhowells@redhat.com). + * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de> + * - Derived also from comments by Linus + */ +#include <linux/rwsem.h> +#include <linux/sched.h> +#include <linux/export.h> + +enum rwsem_waiter_type { + RWSEM_WAITING_FOR_WRITE, + RWSEM_WAITING_FOR_READ +}; + +struct rwsem_waiter { + struct list_head list; + struct task_struct *task; + enum rwsem_waiter_type type; +}; + +int rwsem_is_locked(struct rw_semaphore *sem) +{ + int ret = 1; + unsigned long flags; + + if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) { + ret = (sem->activity != 0); + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + } + return ret; +} +EXPORT_SYMBOL(rwsem_is_locked); + +/* + * initialise the semaphore + */ +void __init_rwsem(struct rw_semaphore *sem, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held semaphore: + */ + debug_check_no_locks_freed((void *)sem, sizeof(*sem)); + lockdep_init_map(&sem->dep_map, name, key, 0); +#endif + sem->activity = 0; + raw_spin_lock_init(&sem->wait_lock); + INIT_LIST_HEAD(&sem->wait_list); +} +EXPORT_SYMBOL(__init_rwsem); + +/* + * handle the lock release when processes blocked on it that can now run + * - if we come here, then: + * - the 'active count' _reached_ zero + * - the 'waiting count' is non-zero + * - the spinlock must be held by the caller + * - woken process blocks are discarded from the list after having task zeroed + * - writers are only woken if wakewrite is non-zero + */ +static inline struct rw_semaphore * +__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite) +{ + struct rwsem_waiter *waiter; + struct task_struct *tsk; + int woken; + + waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); + + if (waiter->type == RWSEM_WAITING_FOR_WRITE) { + if (wakewrite) + /* Wake up a writer. Note that we do not grant it the + * lock - it will have to acquire it when it runs. */ + wake_up_process(waiter->task); + goto out; + } + + /* grant an infinite number of read locks to the front of the queue */ + woken = 0; + do { + struct list_head *next = waiter->list.next; + + list_del(&waiter->list); + tsk = waiter->task; + smp_mb(); + waiter->task = NULL; + wake_up_process(tsk); + put_task_struct(tsk); + woken++; + if (next == &sem->wait_list) + break; + waiter = list_entry(next, struct rwsem_waiter, list); + } while (waiter->type != RWSEM_WAITING_FOR_WRITE); + + sem->activity += woken; + + out: + return sem; +} + +/* + * wake a single writer + */ +static inline struct rw_semaphore * +__rwsem_wake_one_writer(struct rw_semaphore *sem) +{ + struct rwsem_waiter *waiter; + + waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); + wake_up_process(waiter->task); + + return sem; +} + +/* + * get a read lock on the semaphore + */ +void __sched __down_read(struct rw_semaphore *sem) +{ + struct rwsem_waiter waiter; + struct task_struct *tsk; + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + if (sem->activity >= 0 && list_empty(&sem->wait_list)) { + /* granted */ + sem->activity++; + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + goto out; + } + + tsk = current; + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + + /* set up my own style of waitqueue */ + waiter.task = tsk; + waiter.type = RWSEM_WAITING_FOR_READ; + get_task_struct(tsk); + + list_add_tail(&waiter.list, &sem->wait_list); + + /* we don't need to touch the semaphore struct anymore */ + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + /* wait to be given the lock */ + for (;;) { + if (!waiter.task) + break; + schedule(); + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + } + + tsk->state = TASK_RUNNING; + out: + ; +} + +/* + * trylock for reading -- returns 1 if successful, 0 if contention + */ +int __down_read_trylock(struct rw_semaphore *sem) +{ + unsigned long flags; + int ret = 0; + + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + if (sem->activity >= 0 && list_empty(&sem->wait_list)) { + /* granted */ + sem->activity++; + ret = 1; + } + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return ret; +} + +/* + * get a write lock on the semaphore + */ +void __sched __down_write_nested(struct rw_semaphore *sem, int subclass) +{ + struct rwsem_waiter waiter; + struct task_struct *tsk; + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + /* set up my own style of waitqueue */ + tsk = current; + waiter.task = tsk; + waiter.type = RWSEM_WAITING_FOR_WRITE; + list_add_tail(&waiter.list, &sem->wait_list); + + /* wait for someone to release the lock */ + for (;;) { + /* + * That is the key to support write lock stealing: allows the + * task already on CPU to get the lock soon rather than put + * itself into sleep and waiting for system woke it or someone + * else in the head of the wait list up. + */ + if (sem->activity == 0) + break; + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + schedule(); + raw_spin_lock_irqsave(&sem->wait_lock, flags); + } + /* got the lock */ + sem->activity = -1; + list_del(&waiter.list); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); +} + +void __sched __down_write(struct rw_semaphore *sem) +{ + __down_write_nested(sem, 0); +} + +/* + * trylock for writing -- returns 1 if successful, 0 if contention + */ +int __down_write_trylock(struct rw_semaphore *sem) +{ + unsigned long flags; + int ret = 0; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + if (sem->activity == 0) { + /* got the lock */ + sem->activity = -1; + ret = 1; + } + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return ret; +} + +/* + * release a read lock on the semaphore + */ +void __up_read(struct rw_semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + if (--sem->activity == 0 && !list_empty(&sem->wait_list)) + sem = __rwsem_wake_one_writer(sem); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); +} + +/* + * release a write lock on the semaphore + */ +void __up_write(struct rw_semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + sem->activity = 0; + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, 1); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); +} + +/* + * downgrade a write lock into a read lock + * - just wake up any readers at the front of the queue + */ +void __downgrade_write(struct rw_semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + sem->activity = 1; + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, 0); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); +} + diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c new file mode 100644 index 00000000000..19c5fa95e0b --- /dev/null +++ b/kernel/locking/rwsem-xadd.c @@ -0,0 +1,293 @@ +/* rwsem.c: R/W semaphores: contention handling functions + * + * Written by David Howells (dhowells@redhat.com). + * Derived from arch/i386/kernel/semaphore.c + * + * Writer lock-stealing by Alex Shi <alex.shi@intel.com> + * and Michel Lespinasse <walken@google.com> + */ +#include <linux/rwsem.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/export.h> + +/* + * Initialize an rwsem: + */ +void __init_rwsem(struct rw_semaphore *sem, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held semaphore: + */ + debug_check_no_locks_freed((void *)sem, sizeof(*sem)); + lockdep_init_map(&sem->dep_map, name, key, 0); +#endif + sem->count = RWSEM_UNLOCKED_VALUE; + raw_spin_lock_init(&sem->wait_lock); + INIT_LIST_HEAD(&sem->wait_list); +} + +EXPORT_SYMBOL(__init_rwsem); + +enum rwsem_waiter_type { + RWSEM_WAITING_FOR_WRITE, + RWSEM_WAITING_FOR_READ +}; + +struct rwsem_waiter { + struct list_head list; + struct task_struct *task; + enum rwsem_waiter_type type; +}; + +enum rwsem_wake_type { + RWSEM_WAKE_ANY, /* Wake whatever's at head of wait list */ + RWSEM_WAKE_READERS, /* Wake readers only */ + RWSEM_WAKE_READ_OWNED /* Waker thread holds the read lock */ +}; + +/* + * handle the lock release when processes blocked on it that can now run + * - if we come here from up_xxxx(), then: + * - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed) + * - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so) + * - there must be someone on the queue + * - the spinlock must be held by the caller + * - woken process blocks are discarded from the list after having task zeroed + * - writers are only woken if downgrading is false + */ +static struct rw_semaphore * +__rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type) +{ + struct rwsem_waiter *waiter; + struct task_struct *tsk; + struct list_head *next; + long oldcount, woken, loop, adjustment; + + waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); + if (waiter->type == RWSEM_WAITING_FOR_WRITE) { + if (wake_type == RWSEM_WAKE_ANY) + /* Wake writer at the front of the queue, but do not + * grant it the lock yet as we want other writers + * to be able to steal it. Readers, on the other hand, + * will block as they will notice the queued writer. + */ + wake_up_process(waiter->task); + goto out; + } + + /* Writers might steal the lock before we grant it to the next reader. + * We prefer to do the first reader grant before counting readers + * so we can bail out early if a writer stole the lock. + */ + adjustment = 0; + if (wake_type != RWSEM_WAKE_READ_OWNED) { + adjustment = RWSEM_ACTIVE_READ_BIAS; + try_reader_grant: + oldcount = rwsem_atomic_update(adjustment, sem) - adjustment; + if (unlikely(oldcount < RWSEM_WAITING_BIAS)) { + /* A writer stole the lock. Undo our reader grant. */ + if (rwsem_atomic_update(-adjustment, sem) & + RWSEM_ACTIVE_MASK) + goto out; + /* Last active locker left. Retry waking readers. */ + goto try_reader_grant; + } + } + + /* Grant an infinite number of read locks to the readers at the front + * of the queue. Note we increment the 'active part' of the count by + * the number of readers before waking any processes up. + */ + woken = 0; + do { + woken++; + + if (waiter->list.next == &sem->wait_list) + break; + + waiter = list_entry(waiter->list.next, + struct rwsem_waiter, list); + + } while (waiter->type != RWSEM_WAITING_FOR_WRITE); + + adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment; + if (waiter->type != RWSEM_WAITING_FOR_WRITE) + /* hit end of list above */ + adjustment -= RWSEM_WAITING_BIAS; + + if (adjustment) + rwsem_atomic_add(adjustment, sem); + + next = sem->wait_list.next; + loop = woken; + do { + waiter = list_entry(next, struct rwsem_waiter, list); + next = waiter->list.next; + tsk = waiter->task; + smp_mb(); + waiter->task = NULL; + wake_up_process(tsk); + put_task_struct(tsk); + } while (--loop); + + sem->wait_list.next = next; + next->prev = &sem->wait_list; + + out: + return sem; +} + +/* + * wait for the read lock to be granted + */ +struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) +{ + long count, adjustment = -RWSEM_ACTIVE_READ_BIAS; + struct rwsem_waiter waiter; + struct task_struct *tsk = current; + + /* set up my own style of waitqueue */ + waiter.task = tsk; + waiter.type = RWSEM_WAITING_FOR_READ; + get_task_struct(tsk); + + raw_spin_lock_irq(&sem->wait_lock); + if (list_empty(&sem->wait_list)) + adjustment += RWSEM_WAITING_BIAS; + list_add_tail(&waiter.list, &sem->wait_list); + + /* we're now waiting on the lock, but no longer actively locking */ + count = rwsem_atomic_update(adjustment, sem); + + /* If there are no active locks, wake the front queued process(es). + * + * If there are no writers and we are first in the queue, + * wake our own waiter to join the existing active readers ! + */ + if (count == RWSEM_WAITING_BIAS || + (count > RWSEM_WAITING_BIAS && + adjustment != -RWSEM_ACTIVE_READ_BIAS)) + sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY); + + raw_spin_unlock_irq(&sem->wait_lock); + + /* wait to be given the lock */ + while (true) { + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + if (!waiter.task) + break; + schedule(); + } + + tsk->state = TASK_RUNNING; + + return sem; +} + +/* + * wait until we successfully acquire the write lock + */ +struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem) +{ + long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS; + struct rwsem_waiter waiter; + struct task_struct *tsk = current; + + /* set up my own style of waitqueue */ + waiter.task = tsk; + waiter.type = RWSEM_WAITING_FOR_WRITE; + + raw_spin_lock_irq(&sem->wait_lock); + if (list_empty(&sem->wait_list)) + adjustment += RWSEM_WAITING_BIAS; + list_add_tail(&waiter.list, &sem->wait_list); + + /* we're now waiting on the lock, but no longer actively locking */ + count = rwsem_atomic_update(adjustment, sem); + + /* If there were already threads queued before us and there are no + * active writers, the lock must be read owned; so we try to wake + * any read locks that were queued ahead of us. */ + if (count > RWSEM_WAITING_BIAS && + adjustment == -RWSEM_ACTIVE_WRITE_BIAS) + sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS); + + /* wait until we successfully acquire the lock */ + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + while (true) { + if (!(count & RWSEM_ACTIVE_MASK)) { + /* Try acquiring the write lock. */ + count = RWSEM_ACTIVE_WRITE_BIAS; + if (!list_is_singular(&sem->wait_list)) + count += RWSEM_WAITING_BIAS; + + if (sem->count == RWSEM_WAITING_BIAS && + cmpxchg(&sem->count, RWSEM_WAITING_BIAS, count) == + RWSEM_WAITING_BIAS) + break; + } + + raw_spin_unlock_irq(&sem->wait_lock); + + /* Block until there are no active lockers. */ + do { + schedule(); + set_task_state(tsk, TASK_UNINTERRUPTIBLE); + } while ((count = sem->count) & RWSEM_ACTIVE_MASK); + + raw_spin_lock_irq(&sem->wait_lock); + } + + list_del(&waiter.list); + raw_spin_unlock_irq(&sem->wait_lock); + tsk->state = TASK_RUNNING; + + return sem; +} + +/* + * handle waking up a waiter on the semaphore + * - up_read/up_write has decremented the active part of count if we come here + */ +struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + /* do nothing if list empty */ + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return sem; +} + +/* + * downgrade a write lock into a read lock + * - caller incremented waiting part of count and discovered it still negative + * - just wake up any readers at the front of the queue + */ +struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&sem->wait_lock, flags); + + /* do nothing if list empty */ + if (!list_empty(&sem->wait_list)) + sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED); + + raw_spin_unlock_irqrestore(&sem->wait_lock, flags); + + return sem; +} + +EXPORT_SYMBOL(rwsem_down_read_failed); +EXPORT_SYMBOL(rwsem_down_write_failed); +EXPORT_SYMBOL(rwsem_wake); +EXPORT_SYMBOL(rwsem_downgrade_wake); diff --git a/kernel/rwsem.c b/kernel/locking/rwsem.c index cfff1435bdf..cfff1435bdf 100644 --- a/kernel/rwsem.c +++ b/kernel/locking/rwsem.c diff --git a/kernel/semaphore.c b/kernel/locking/semaphore.c index 6815171a4ff..6815171a4ff 100644 --- a/kernel/semaphore.c +++ b/kernel/locking/semaphore.c diff --git a/kernel/spinlock.c b/kernel/locking/spinlock.c index 4b082b5cac9..4b082b5cac9 100644 --- a/kernel/spinlock.c +++ b/kernel/locking/spinlock.c diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c new file mode 100644 index 00000000000..0374a596cff --- /dev/null +++ b/kernel/locking/spinlock_debug.c @@ -0,0 +1,302 @@ +/* + * Copyright 2005, Red Hat, Inc., Ingo Molnar + * Released under the General Public License (GPL). + * + * This file contains the spinlock/rwlock implementations for + * DEBUG_SPINLOCK. + */ + +#include <linux/spinlock.h> +#include <linux/nmi.h> +#include <linux/interrupt.h> +#include <linux/debug_locks.h> +#include <linux/delay.h> +#include <linux/export.h> + +void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif + lock->raw_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; + lock->magic = SPINLOCK_MAGIC; + lock->owner = SPINLOCK_OWNER_INIT; + lock->owner_cpu = -1; +} + +EXPORT_SYMBOL(__raw_spin_lock_init); + +void __rwlock_init(rwlock_t *lock, const char *name, + struct lock_class_key *key) +{ +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)lock, sizeof(*lock)); + lockdep_init_map(&lock->dep_map, name, key, 0); +#endif + lock->raw_lock = (arch_rwlock_t) __ARCH_RW_LOCK_UNLOCKED; + lock->magic = RWLOCK_MAGIC; + lock->owner = SPINLOCK_OWNER_INIT; + lock->owner_cpu = -1; +} + +EXPORT_SYMBOL(__rwlock_init); + +static void spin_dump(raw_spinlock_t *lock, const char *msg) +{ + struct task_struct *owner = NULL; + + if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT) + owner = lock->owner; + printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n", + msg, raw_smp_processor_id(), + current->comm, task_pid_nr(current)); + printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, " + ".owner_cpu: %d\n", + lock, lock->magic, + owner ? owner->comm : "<none>", + owner ? task_pid_nr(owner) : -1, + lock->owner_cpu); + dump_stack(); +} + +static void spin_bug(raw_spinlock_t *lock, const char *msg) +{ + if (!debug_locks_off()) + return; + + spin_dump(lock, msg); +} + +#define SPIN_BUG_ON(cond, lock, msg) if (unlikely(cond)) spin_bug(lock, msg) + +static inline void +debug_spin_lock_before(raw_spinlock_t *lock) +{ + SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic"); + SPIN_BUG_ON(lock->owner == current, lock, "recursion"); + SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(), + lock, "cpu recursion"); +} + +static inline void debug_spin_lock_after(raw_spinlock_t *lock) +{ + lock->owner_cpu = raw_smp_processor_id(); + lock->owner = current; +} + +static inline void debug_spin_unlock(raw_spinlock_t *lock) +{ + SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic"); + SPIN_BUG_ON(!raw_spin_is_locked(lock), lock, "already unlocked"); + SPIN_BUG_ON(lock->owner != current, lock, "wrong owner"); + SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), + lock, "wrong CPU"); + lock->owner = SPINLOCK_OWNER_INIT; + lock->owner_cpu = -1; +} + +static void __spin_lock_debug(raw_spinlock_t *lock) +{ + u64 i; + u64 loops = loops_per_jiffy * HZ; + + for (i = 0; i < loops; i++) { + if (arch_spin_trylock(&lock->raw_lock)) + return; + __delay(1); + } + /* lockup suspected: */ + spin_dump(lock, "lockup suspected"); +#ifdef CONFIG_SMP + trigger_all_cpu_backtrace(); +#endif + + /* + * The trylock above was causing a livelock. Give the lower level arch + * specific lock code a chance to acquire the lock. We have already + * printed a warning/backtrace at this point. The non-debug arch + * specific code might actually succeed in acquiring the lock. If it is + * not successful, the end-result is the same - there is no forward + * progress. + */ + arch_spin_lock(&lock->raw_lock); +} + +void do_raw_spin_lock(raw_spinlock_t *lock) +{ + debug_spin_lock_before(lock); + if (unlikely(!arch_spin_trylock(&lock->raw_lock))) + __spin_lock_debug(lock); + debug_spin_lock_after(lock); +} + +int do_raw_spin_trylock(raw_spinlock_t *lock) +{ + int ret = arch_spin_trylock(&lock->raw_lock); + + if (ret) + debug_spin_lock_after(lock); +#ifndef CONFIG_SMP + /* + * Must not happen on UP: + */ + SPIN_BUG_ON(!ret, lock, "trylock failure on UP"); +#endif + return ret; +} + +void do_raw_spin_unlock(raw_spinlock_t *lock) +{ + debug_spin_unlock(lock); + arch_spin_unlock(&lock->raw_lock); +} + +static void rwlock_bug(rwlock_t *lock, const char *msg) +{ + if (!debug_locks_off()) + return; + + printk(KERN_EMERG "BUG: rwlock %s on CPU#%d, %s/%d, %p\n", + msg, raw_smp_processor_id(), current->comm, + task_pid_nr(current), lock); + dump_stack(); +} + +#define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg) + +#if 0 /* __write_lock_debug() can lock up - maybe this can too? */ +static void __read_lock_debug(rwlock_t *lock) +{ + u64 i; + u64 loops = loops_per_jiffy * HZ; + int print_once = 1; + + for (;;) { + for (i = 0; i < loops; i++) { + if (arch_read_trylock(&lock->raw_lock)) + return; + __delay(1); + } + /* lockup suspected: */ + if (print_once) { + print_once = 0; + printk(KERN_EMERG "BUG: read-lock lockup on CPU#%d, " + "%s/%d, %p\n", + raw_smp_processor_id(), current->comm, + current->pid, lock); + dump_stack(); + } + } +} +#endif + +void do_raw_read_lock(rwlock_t *lock) +{ + RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic"); + arch_read_lock(&lock->raw_lock); +} + +int do_raw_read_trylock(rwlock_t *lock) +{ + int ret = arch_read_trylock(&lock->raw_lock); + +#ifndef CONFIG_SMP + /* + * Must not happen on UP: + */ + RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP"); +#endif + return ret; +} + +void do_raw_read_unlock(rwlock_t *lock) +{ + RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic"); + arch_read_unlock(&lock->raw_lock); +} + +static inline void debug_write_lock_before(rwlock_t *lock) +{ + RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic"); + RWLOCK_BUG_ON(lock->owner == current, lock, "recursion"); + RWLOCK_BUG_ON(lock->owner_cpu == raw_smp_processor_id(), + lock, "cpu recursion"); +} + +static inline void debug_write_lock_after(rwlock_t *lock) +{ + lock->owner_cpu = raw_smp_processor_id(); + lock->owner = current; +} + +static inline void debug_write_unlock(rwlock_t *lock) +{ + RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic"); + RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner"); + RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(), + lock, "wrong CPU"); + lock->owner = SPINLOCK_OWNER_INIT; + lock->owner_cpu = -1; +} + +#if 0 /* This can cause lockups */ +static void __write_lock_debug(rwlock_t *lock) +{ + u64 i; + u64 loops = loops_per_jiffy * HZ; + int print_once = 1; + + for (;;) { + for (i = 0; i < loops; i++) { + if (arch_write_trylock(&lock->raw_lock)) + return; + __delay(1); + } + /* lockup suspected: */ + if (print_once) { + print_once = 0; + printk(KERN_EMERG "BUG: write-lock lockup on CPU#%d, " + "%s/%d, %p\n", + raw_smp_processor_id(), current->comm, + current->pid, lock); + dump_stack(); + } + } +} +#endif + +void do_raw_write_lock(rwlock_t *lock) +{ + debug_write_lock_before(lock); + arch_write_lock(&lock->raw_lock); + debug_write_lock_after(lock); +} + +int do_raw_write_trylock(rwlock_t *lock) +{ + int ret = arch_write_trylock(&lock->raw_lock); + + if (ret) + debug_write_lock_after(lock); +#ifndef CONFIG_SMP + /* + * Must not happen on UP: + */ + RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP"); +#endif + return ret; +} + +void do_raw_write_unlock(rwlock_t *lock) +{ + debug_write_unlock(lock); + arch_write_unlock(&lock->raw_lock); +} diff --git a/kernel/module.c b/kernel/module.c index dc582749fa1..af5ebd21d77 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -378,23 +378,21 @@ static bool check_symbol(const struct symsearch *syms, if (syms->licence == GPL_ONLY) return false; if (syms->licence == WILL_BE_GPL_ONLY && fsa->warn) { - printk(KERN_WARNING "Symbol %s is being used " - "by a non-GPL module, which will not " - "be allowed in the future\n", fsa->name); + pr_warn("Symbol %s is being used by a non-GPL module, " + "which will not be allowed in the future\n", + fsa->name); } } #ifdef CONFIG_UNUSED_SYMBOLS if (syms->unused && fsa->warn) { - printk(KERN_WARNING "Symbol %s is marked as UNUSED, " - "however this module is using it.\n", fsa->name); - printk(KERN_WARNING - "This symbol will go away in the future.\n"); - printk(KERN_WARNING - "Please evalute if this is the right api to use and if " - "it really is, submit a report the linux kernel " - "mailinglist together with submitting your code for " - "inclusion.\n"); + pr_warn("Symbol %s is marked as UNUSED, however this module is " + "using it.\n", fsa->name); + pr_warn("This symbol will go away in the future.\n"); + pr_warn("Please evalute if this is the right api to use and if " + "it really is, submit a report the linux kernel " + "mailinglist together with submitting your code for " + "inclusion.\n"); } #endif @@ -492,16 +490,15 @@ static int percpu_modalloc(struct module *mod, struct load_info *info) return 0; if (align > PAGE_SIZE) { - printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n", - mod->name, align, PAGE_SIZE); + pr_warn("%s: per-cpu alignment %li > %li\n", + mod->name, align, PAGE_SIZE); align = PAGE_SIZE; } mod->percpu = __alloc_reserved_percpu(pcpusec->sh_size, align); if (!mod->percpu) { - printk(KERN_WARNING - "%s: Could not allocate %lu bytes percpu data\n", - mod->name, (unsigned long)pcpusec->sh_size); + pr_warn("%s: Could not allocate %lu bytes percpu data\n", + mod->name, (unsigned long)pcpusec->sh_size); return -ENOMEM; } mod->percpu_size = pcpusec->sh_size; @@ -679,7 +676,7 @@ static int add_module_usage(struct module *a, struct module *b) pr_debug("Allocating new usage for %s.\n", a->name); use = kmalloc(sizeof(*use), GFP_ATOMIC); if (!use) { - printk(KERN_WARNING "%s: out of memory loading\n", a->name); + pr_warn("%s: out of memory loading\n", a->name); return -ENOMEM; } @@ -1145,8 +1142,7 @@ static int try_to_force_load(struct module *mod, const char *reason) { #ifdef CONFIG_MODULE_FORCE_LOAD if (!test_taint(TAINT_FORCED_MODULE)) - printk(KERN_WARNING "%s: %s: kernel tainted.\n", - mod->name, reason); + pr_warn("%s: %s: kernel tainted.\n", mod->name, reason); add_taint_module(mod, TAINT_FORCED_MODULE, LOCKDEP_NOW_UNRELIABLE); return 0; #else @@ -1199,8 +1195,7 @@ static int check_version(Elf_Shdr *sechdrs, goto bad_version; } - printk(KERN_WARNING "%s: no symbol version for %s\n", - mod->name, symname); + pr_warn("%s: no symbol version for %s\n", mod->name, symname); return 0; bad_version: @@ -1309,8 +1304,8 @@ resolve_symbol_wait(struct module *mod, !IS_ERR(ksym = resolve_symbol(mod, info, name, owner)) || PTR_ERR(ksym) != -EBUSY, 30 * HZ) <= 0) { - printk(KERN_WARNING "%s: gave up waiting for init of module %s.\n", - mod->name, owner); + pr_warn("%s: gave up waiting for init of module %s.\n", + mod->name, owner); } return ksym; } @@ -1626,15 +1621,14 @@ static int mod_sysfs_init(struct module *mod) struct kobject *kobj; if (!module_sysfs_initialized) { - printk(KERN_ERR "%s: module sysfs not initialized\n", - mod->name); + pr_err("%s: module sysfs not initialized\n", mod->name); err = -EINVAL; goto out; } kobj = kset_find_obj(module_kset, mod->name); if (kobj) { - printk(KERN_ERR "%s: module is already loaded\n", mod->name); + pr_err("%s: module is already loaded\n", mod->name); kobject_put(kobj); err = -EINVAL; goto out; @@ -1961,8 +1955,7 @@ static int verify_export_symbols(struct module *mod) for (i = 0; i < ARRAY_SIZE(arr); i++) { for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) { if (find_symbol(s->name, &owner, NULL, true, false)) { - printk(KERN_ERR - "%s: exports duplicate symbol %s" + pr_err("%s: exports duplicate symbol %s" " (owned by %s)\n", mod->name, s->name, module_name(owner)); return -ENOEXEC; @@ -2013,8 +2006,8 @@ static int simplify_symbols(struct module *mod, const struct load_info *info) if (!ksym && ELF_ST_BIND(sym[i].st_info) == STB_WEAK) break; - printk(KERN_WARNING "%s: Unknown symbol %s (err %li)\n", - mod->name, name, PTR_ERR(ksym)); + pr_warn("%s: Unknown symbol %s (err %li)\n", + mod->name, name, PTR_ERR(ksym)); ret = PTR_ERR(ksym) ?: -ENOENT; break; @@ -2168,8 +2161,8 @@ static void set_license(struct module *mod, const char *license) if (!license_is_gpl_compatible(license)) { if (!test_taint(TAINT_PROPRIETARY_MODULE)) - printk(KERN_WARNING "%s: module license '%s' taints " - "kernel.\n", mod->name, license); + pr_warn("%s: module license '%s' taints kernel.\n", + mod->name, license); add_taint_module(mod, TAINT_PROPRIETARY_MODULE, LOCKDEP_NOW_UNRELIABLE); } @@ -2405,8 +2398,8 @@ static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num) return; #ifdef CONFIG_DYNAMIC_DEBUG if (ddebug_add_module(debug, num, debug->modname)) - printk(KERN_ERR "dynamic debug error adding module: %s\n", - debug->modname); + pr_err("dynamic debug error adding module: %s\n", + debug->modname); #endif } @@ -2619,8 +2612,7 @@ static int rewrite_section_headers(struct load_info *info, int flags) Elf_Shdr *shdr = &info->sechdrs[i]; if (shdr->sh_type != SHT_NOBITS && info->len < shdr->sh_offset + shdr->sh_size) { - printk(KERN_ERR "Module len %lu truncated\n", - info->len); + pr_err("Module len %lu truncated\n", info->len); return -ENOEXEC; } @@ -2682,15 +2674,14 @@ static struct module *setup_load_info(struct load_info *info, int flags) info->index.mod = find_sec(info, ".gnu.linkonce.this_module"); if (!info->index.mod) { - printk(KERN_WARNING "No module found in object\n"); + pr_warn("No module found in object\n"); return ERR_PTR(-ENOEXEC); } /* This is temporary: point mod into copy of data. */ mod = (void *)info->sechdrs[info->index.mod].sh_addr; if (info->index.sym == 0) { - printk(KERN_WARNING "%s: module has no symbols (stripped?)\n", - mod->name); + pr_warn("%s: module has no symbols (stripped?)\n", mod->name); return ERR_PTR(-ENOEXEC); } @@ -2717,7 +2708,7 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) if (err) return err; } else if (!same_magic(modmagic, vermagic, info->index.vers)) { - printk(KERN_ERR "%s: version magic '%s' should be '%s'\n", + pr_err("%s: version magic '%s' should be '%s'\n", mod->name, modmagic, vermagic); return -ENOEXEC; } @@ -2727,9 +2718,8 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) if (get_modinfo(info, "staging")) { add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK); - printk(KERN_WARNING "%s: module is from the staging directory," - " the quality is unknown, you have been warned.\n", - mod->name); + pr_warn("%s: module is from the staging directory, the quality " + "is unknown, you have been warned.\n", mod->name); } /* Set up license info based on the info section */ @@ -2801,8 +2791,7 @@ static void find_module_sections(struct module *mod, struct load_info *info) sizeof(*mod->extable), &mod->num_exentries); if (section_addr(info, "__obsparm")) - printk(KERN_WARNING "%s: Ignoring obsolete parameters\n", - mod->name); + pr_warn("%s: Ignoring obsolete parameters\n", mod->name); info->debug = section_objs(info, "__verbose", sizeof(*info->debug), &info->num_debug); @@ -3078,11 +3067,10 @@ static int do_init_module(struct module *mod) return ret; } if (ret > 0) { - printk(KERN_WARNING -"%s: '%s'->init suspiciously returned %d, it should follow 0/-E convention\n" -"%s: loading module anyway...\n", - __func__, mod->name, ret, - __func__); + pr_warn("%s: '%s'->init suspiciously returned %d, it should " + "follow 0/-E convention\n" + "%s: loading module anyway...\n", + __func__, mod->name, ret, __func__); dump_stack(); } @@ -3205,10 +3193,8 @@ static int unknown_module_param_cb(char *param, char *val, const char *modname) { /* Check for magic 'dyndbg' arg */ int ret = ddebug_dyndbg_module_param_cb(param, val, modname); - if (ret != 0) { - printk(KERN_WARNING "%s: unknown parameter '%s' ignored\n", - modname, param); - } + if (ret != 0) + pr_warn("%s: unknown parameter '%s' ignored\n", modname, param); return 0; } @@ -3243,10 +3229,9 @@ static int load_module(struct load_info *info, const char __user *uargs, #ifdef CONFIG_MODULE_SIG mod->sig_ok = info->sig_ok; if (!mod->sig_ok) { - printk_once(KERN_NOTICE - "%s: module verification failed: signature and/or" - " required key missing - tainting kernel\n", - mod->name); + pr_notice_once("%s: module verification failed: signature " + "and/or required key missing - tainting " + "kernel\n", mod->name); add_taint_module(mod, TAINT_FORCED_MODULE, LOCKDEP_STILL_OK); } #endif diff --git a/kernel/panic.c b/kernel/panic.c index b6c482ccc5d..c00b4ceb39e 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -233,7 +233,7 @@ static const struct tnt tnts[] = { */ const char *print_tainted(void) { - static char buf[ARRAY_SIZE(tnts) + sizeof("Tainted: ") + 1]; + static char buf[ARRAY_SIZE(tnts) + sizeof("Tainted: ")]; if (tainted_mask) { char *s; diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 42086551a24..06c62de9c71 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -132,6 +132,12 @@ out: return ERR_PTR(err); } +static void delayed_free_pidns(struct rcu_head *p) +{ + kmem_cache_free(pid_ns_cachep, + container_of(p, struct pid_namespace, rcu)); +} + static void destroy_pid_namespace(struct pid_namespace *ns) { int i; @@ -140,7 +146,7 @@ static void destroy_pid_namespace(struct pid_namespace *ns) for (i = 0; i < PIDMAP_ENTRIES; i++) kfree(ns->pidmap[i].page); put_user_ns(ns->user_ns); - kmem_cache_free(pid_ns_cachep, ns); + call_rcu(&ns->rcu, delayed_free_pidns); } struct pid_namespace *copy_pid_ns(unsigned long flags, diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index d444c4e834f..2fac9cc79b3 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -178,6 +178,22 @@ config PM_SLEEP_DEBUG def_bool y depends on PM_DEBUG && PM_SLEEP +config DPM_WATCHDOG + bool "Device suspend/resume watchdog" + depends on PM_DEBUG && PSTORE + ---help--- + Sets up a watchdog timer to capture drivers that are + locked up attempting to suspend/resume a device. + A detected lockup causes system panic with message + captured in pstore device for inspection in subsequent + boot session. + +config DPM_WATCHDOG_TIMEOUT + int "Watchdog timeout in seconds" + range 1 120 + default 12 + depends on DPM_WATCHDOG + config PM_TRACE bool help diff --git a/kernel/power/qos.c b/kernel/power/qos.c index a394297f8b2..8dff9b48075 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -558,30 +558,12 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, if (count == sizeof(s32)) { if (copy_from_user(&value, buf, sizeof(s32))) return -EFAULT; - } else if (count <= 11) { /* ASCII perhaps? */ - char ascii_value[11]; - unsigned long int ulval; + } else { int ret; - if (copy_from_user(ascii_value, buf, count)) - return -EFAULT; - - if (count > 10) { - if (ascii_value[10] == '\n') - ascii_value[10] = '\0'; - else - return -EINVAL; - } else { - ascii_value[count] = '\0'; - } - ret = kstrtoul(ascii_value, 16, &ulval); - if (ret) { - pr_debug("%s, 0x%lx, 0x%x\n", ascii_value, ulval, ret); - return -EINVAL; - } - value = (s32)lower_32_bits(ulval); - } else { - return -EINVAL; + ret = kstrtos32_from_user(buf, count, 16, &value); + if (ret) + return ret; } req = filp->private_data; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 98c3b34a4cf..10c22cae83a 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1402,7 +1402,11 @@ int hibernate_preallocate_memory(void) * highmem and non-highmem zones separately. */ pages_highmem = preallocate_image_highmem(highmem / 2); - alloc = (count - max_size) - pages_highmem; + alloc = count - max_size; + if (alloc > pages_highmem) + alloc -= pages_highmem; + else + alloc = 0; pages = preallocate_image_memory(alloc, avail_normal); if (pages < alloc) { /* We have exhausted non-highmem pages, try highmem. */ diff --git a/kernel/power/user.c b/kernel/power/user.c index 957f06164ad..24850270c80 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -36,9 +36,9 @@ static struct snapshot_data { struct snapshot_handle handle; int swap; int mode; - char frozen; - char ready; - char platform_support; + bool frozen; + bool ready; + bool platform_support; bool free_bitmaps; } snapshot_state; @@ -93,9 +93,9 @@ static int snapshot_open(struct inode *inode, struct file *filp) if (error) atomic_inc(&snapshot_device_available); - data->frozen = 0; - data->ready = 0; - data->platform_support = 0; + data->frozen = false; + data->ready = false; + data->platform_support = false; Unlock: unlock_system_sleep(); @@ -229,7 +229,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, if (error) thaw_processes(); else - data->frozen = 1; + data->frozen = true; break; @@ -240,7 +240,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, free_basic_memory_bitmaps(); data->free_bitmaps = false; thaw_processes(); - data->frozen = 0; + data->frozen = false; break; case SNAPSHOT_CREATE_IMAGE: @@ -270,7 +270,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, case SNAPSHOT_FREE: swsusp_free(); memset(&data->handle, 0, sizeof(struct snapshot_handle)); - data->ready = 0; + data->ready = false; /* * It is necessary to thaw kernel threads here, because * SNAPSHOT_CREATE_IMAGE may be invoked directly after @@ -334,7 +334,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, * PM_HIBERNATION_PREPARE */ error = suspend_devices_and_enter(PM_SUSPEND_MEM); - data->ready = 0; + data->ready = false; break; case SNAPSHOT_PLATFORM_SUPPORT: diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index b4e8500afdb..be7c86bae57 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -705,9 +705,9 @@ const struct file_operations kmsg_fops = { #ifdef CONFIG_KEXEC /* - * This appends the listed symbols to /proc/vmcoreinfo + * This appends the listed symbols to /proc/vmcore * - * /proc/vmcoreinfo is used by various utiilties, like crash and makedumpfile to + * /proc/vmcore is used by various utilities, like crash and makedumpfile to * obtain access to symbols that are otherwise very difficult to locate. These * symbols are specifically used so that utilities can access and extract the * dmesg log from a vmcore file after a crash. @@ -791,7 +791,7 @@ static bool __read_mostly ignore_loglevel; static int __init ignore_loglevel_setup(char *str) { ignore_loglevel = 1; - printk(KERN_INFO "debug: ignoring loglevel setting.\n"); + pr_info("debug: ignoring loglevel setting.\n"); return 0; } @@ -820,9 +820,9 @@ static int __init boot_delay_setup(char *str) pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, " "HZ: %d, loops_per_msec: %llu\n", boot_delay, preset_lpj, lpj, HZ, loops_per_msec); - return 1; + return 0; } -__setup("boot_delay=", boot_delay_setup); +early_param("boot_delay", boot_delay_setup); static void boot_delay_msec(int level) { @@ -2193,7 +2193,7 @@ static int __read_mostly keep_bootcon; static int __init keep_bootcon_setup(char *str) { keep_bootcon = 1; - printk(KERN_INFO "debug: skip boot console de-registration.\n"); + pr_info("debug: skip boot console de-registration.\n"); return 0; } @@ -2241,7 +2241,7 @@ void register_console(struct console *newcon) /* find the last or real console */ for_each_console(bcon) { if (!(bcon->flags & CON_BOOT)) { - printk(KERN_INFO "Too late to register bootconsole %s%d\n", + pr_info("Too late to register bootconsole %s%d\n", newcon->name, newcon->index); return; } @@ -2358,21 +2358,18 @@ void register_console(struct console *newcon) * users know there might be something in the kernel's log buffer that * went to the bootconsole (that they do not see on the real console) */ + pr_info("%sconsole [%s%d] enabled\n", + (newcon->flags & CON_BOOT) ? "boot" : "" , + newcon->name, newcon->index); if (bcon && ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) && !keep_bootcon) { - /* we need to iterate through twice, to make sure we print - * everything out, before we unregister the console(s) + /* We need to iterate through all boot consoles, to make + * sure we print everything out, before we unregister them. */ - printk(KERN_INFO "console [%s%d] enabled, bootconsole disabled\n", - newcon->name, newcon->index); for_each_console(bcon) if (bcon->flags & CON_BOOT) unregister_console(bcon); - } else { - printk(KERN_INFO "%sconsole [%s%d] enabled\n", - (newcon->flags & CON_BOOT) ? "boot" : "" , - newcon->name, newcon->index); } } EXPORT_SYMBOL(register_console); @@ -2382,6 +2379,10 @@ int unregister_console(struct console *console) struct console *a, *b; int res; + pr_info("%sconsole [%s%d] disabled\n", + (console->flags & CON_BOOT) ? "boot" : "" , + console->name, console->index); + res = _braille_unregister_console(console); if (res) return res; @@ -2421,8 +2422,6 @@ static int __init printk_late_init(void) for_each_console(con) { if (!keep_bootcon && con->flags & CON_BOOT) { - printk(KERN_INFO "turn off boot console %s%d\n", - con->name, con->index); unregister_console(con); } } @@ -2449,7 +2448,7 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) if (pending & PRINTK_PENDING_SCHED) { char *buf = __get_cpu_var(printk_sched_buf); - printk(KERN_WARNING "[sched_delayed] %s", buf); + pr_warn("[sched_delayed] %s", buf); } if (pending & PRINTK_PENDING_WAKEUP) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index dd562e9aa2c..1f4bcb3cc21 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -257,7 +257,8 @@ ok: if (task->mm) dumpable = get_dumpable(task->mm); rcu_read_lock(); - if (!dumpable && !ptrace_has_cap(__task_cred(task)->user_ns, mode)) { + if (dumpable != SUID_DUMP_USER && + !ptrace_has_cap(__task_cred(task)->user_ns, mode)) { rcu_read_unlock(); return -EPERM; } diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 3822ac0c4b2..6abb03dff5c 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1133,7 +1133,7 @@ void exit_rcu(void) #ifdef CONFIG_RCU_BOOST -#include "../rtmutex_common.h" +#include "../locking/rtmutex_common.h" #ifdef CONFIG_RCU_TRACE diff --git a/kernel/signal.c b/kernel/signal.c index ded28b91fa5..940b30ee9a3 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2723,7 +2723,7 @@ COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset, #ifndef HAVE_ARCH_COPY_SIGINFO_TO_USER -int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from) +int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) { int err; diff --git a/kernel/smp.c b/kernel/smp.c index f5768b0c816..46116100f0e 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -18,6 +18,7 @@ #ifdef CONFIG_USE_GENERIC_SMP_HELPERS enum { CSD_FLAG_LOCK = 0x01, + CSD_FLAG_WAIT = 0x02, }; struct call_function_data { @@ -124,7 +125,7 @@ static void csd_lock(struct call_single_data *csd) static void csd_unlock(struct call_single_data *csd) { - WARN_ON(!(csd->flags & CSD_FLAG_LOCK)); + WARN_ON((csd->flags & CSD_FLAG_WAIT) && !(csd->flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: @@ -146,6 +147,9 @@ void generic_exec_single(int cpu, struct call_single_data *csd, int wait) unsigned long flags; int ipi; + if (wait) + csd->flags |= CSD_FLAG_WAIT; + raw_spin_lock_irqsave(&dst->lock, flags); ipi = list_empty(&dst->list); list_add_tail(&csd->list, &dst->list); @@ -340,6 +344,7 @@ void __smp_call_function_single(int cpu, struct call_single_data *csd, } put_cpu(); } +EXPORT_SYMBOL_GPL(__smp_call_function_single); /** * smp_call_function_many(): Run a function on a set of other CPUs. diff --git a/kernel/sys.c b/kernel/sys.c index c18ecca575b..c72311324ea 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -16,7 +16,6 @@ #include <linux/perf_event.h> #include <linux/resource.h> #include <linux/kernel.h> -#include <linux/kexec.h> #include <linux/workqueue.h> #include <linux/capability.h> #include <linux/device.h> diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 36547dddcdb..34a604726d0 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -969,9 +969,10 @@ static struct ctl_table kern_table[] = { { .procname = "hung_task_check_count", .data = &sysctl_hung_task_check_count, - .maxlen = sizeof(unsigned long), + .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_doulongvec_minmax, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, }, { .procname = "hung_task_timeout_secs", @@ -2222,8 +2223,11 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int *i = val; } else { val = convdiv * (*i) / convmul; - if (!first) + if (!first) { err = proc_put_char(&buffer, &left, '\t'); + if (err) + break; + } err = proc_put_long(&buffer, &left, val, false); if (err) break; diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index b609213ca9a..653cbbd9e7a 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1024,7 +1024,7 @@ static ssize_t bin_intvec(struct file *file, if (get_user(value, vec + i)) goto out_kfree; - str += snprintf(str, end - str, "%lu\t", value); + str += scnprintf(str, end - str, "%lu\t", value); } result = kernel_write(file, buffer, str - buffer, 0); @@ -1095,7 +1095,7 @@ static ssize_t bin_ulongvec(struct file *file, if (get_user(value, vec + i)) goto out_kfree; - str += snprintf(str, end - str, "%lu\t", value); + str += scnprintf(str, end - str, "%lu\t", value); } result = kernel_write(file, buffer, str - buffer, 0); @@ -1205,7 +1205,7 @@ static ssize_t bin_dn_node_address(struct file *file, if (get_user(dnaddr, (__le16 __user *)newval)) goto out; - len = snprintf(buf, sizeof(buf), "%hu.%hu", + len = scnprintf(buf, sizeof(buf), "%hu.%hu", le16_to_cpu(dnaddr) >> 10, le16_to_cpu(dnaddr) & 0x3ff); diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 145bb4d3bd4..9f4618eb51c 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -290,6 +290,7 @@ static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) struct listener_list *listeners; struct listener *s, *tmp, *s2; unsigned int cpu; + int ret = 0; if (!cpumask_subset(mask, cpu_possible_mask)) return -EINVAL; @@ -304,9 +305,10 @@ static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) for_each_cpu(cpu, mask) { s = kmalloc_node(sizeof(struct listener), GFP_KERNEL, cpu_to_node(cpu)); - if (!s) + if (!s) { + ret = -ENOMEM; goto cleanup; - + } s->pid = pid; s->valid = 1; @@ -339,7 +341,7 @@ cleanup: } up_write(&listeners->sem); } - return 0; + return ret; } static int parse(struct nlattr *na, struct cpumask *mask) @@ -404,11 +406,15 @@ static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) if (!na) goto err; - if (nla_put(skb, type, sizeof(pid), &pid) < 0) + if (nla_put(skb, type, sizeof(pid), &pid) < 0) { + nla_nest_cancel(skb, na); goto err; + } ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats)); - if (!ret) + if (!ret) { + nla_nest_cancel(skb, na); goto err; + } nla_nest_end(skb, na); return nla_data(ret); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index b8b8560bfb9..f785aef6579 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -26,6 +26,7 @@ #include <linux/export.h> #include <linux/time.h> #include <linux/uaccess.h> +#include <linux/list.h> #include <trace/events/block.h> @@ -38,6 +39,9 @@ static unsigned int blktrace_seq __read_mostly = 1; static struct trace_array *blk_tr; static bool blk_tracer_enabled __read_mostly; +static LIST_HEAD(running_trace_list); +static __cacheline_aligned_in_smp DEFINE_SPINLOCK(running_trace_lock); + /* Select an alternative, minimalistic output than the original one */ #define TRACE_BLK_OPT_CLASSIC 0x1 @@ -107,10 +111,18 @@ record_it: * Send out a notify for this process, if we haven't done so since a trace * started */ -static void trace_note_tsk(struct blk_trace *bt, struct task_struct *tsk) +static void trace_note_tsk(struct task_struct *tsk) { + unsigned long flags; + struct blk_trace *bt; + tsk->btrace_seq = blktrace_seq; - trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm)); + spin_lock_irqsave(&running_trace_lock, flags); + list_for_each_entry(bt, &running_trace_list, running_list) { + trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, + sizeof(tsk->comm)); + } + spin_unlock_irqrestore(&running_trace_lock, flags); } static void trace_note_time(struct blk_trace *bt) @@ -229,16 +241,15 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, goto record_it; } + if (unlikely(tsk->btrace_seq != blktrace_seq)) + trace_note_tsk(tsk); + /* * A word about the locking here - we disable interrupts to reserve * some space in the relay per-cpu buffer, to prevent an irq * from coming in and stepping on our toes. */ local_irq_save(flags); - - if (unlikely(tsk->btrace_seq != blktrace_seq)) - trace_note_tsk(bt, tsk); - t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len); if (t) { sequence = per_cpu_ptr(bt->sequence, cpu); @@ -477,6 +488,7 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, bt->dir = dir; bt->dev = dev; atomic_set(&bt->dropped, 0); + INIT_LIST_HEAD(&bt->running_list); ret = -EIO; bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt, @@ -567,13 +579,12 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name, .end_lba = cbuts.end_lba, .pid = cbuts.pid, }; - memcpy(&buts.name, &cbuts.name, 32); ret = do_blk_trace_setup(q, name, dev, bdev, &buts); if (ret) return ret; - if (copy_to_user(arg, &buts.name, 32)) { + if (copy_to_user(arg, &buts.name, ARRAY_SIZE(buts.name))) { blk_trace_remove(q); return -EFAULT; } @@ -601,6 +612,9 @@ int blk_trace_startstop(struct request_queue *q, int start) blktrace_seq++; smp_mb(); bt->trace_state = Blktrace_running; + spin_lock_irq(&running_trace_lock); + list_add(&bt->running_list, &running_trace_list); + spin_unlock_irq(&running_trace_lock); trace_note_time(bt); ret = 0; @@ -608,6 +622,9 @@ int blk_trace_startstop(struct request_queue *q, int start) } else { if (bt->trace_state == Blktrace_running) { bt->trace_state = Blktrace_stopped; + spin_lock_irq(&running_trace_lock); + list_del_init(&bt->running_list); + spin_unlock_irq(&running_trace_lock); relay_flush(bt->rchan); ret = 0; } @@ -1472,6 +1489,9 @@ static int blk_trace_remove_queue(struct request_queue *q) if (atomic_dec_and_test(&blk_probes_ref)) blk_unregister_tracepoints(); + spin_lock_irq(&running_trace_lock); + list_del(&bt->running_list); + spin_unlock_irq(&running_trace_lock); blk_trace_free(bt); return 0; } |