diff options
Diffstat (limited to 'kernel')
102 files changed, 3308 insertions, 1290 deletions
diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz index 94fabd534b0..2a202a84675 100644 --- a/kernel/Kconfig.hz +++ b/kernel/Kconfig.hz @@ -55,4 +55,4 @@ config HZ default 1000 if HZ_1000 config SCHED_HRTICK - def_bool HIGH_RES_TIMERS && (!SMP || USE_GENERIC_SMP_HELPERS) + def_bool HIGH_RES_TIMERS diff --git a/kernel/Makefile b/kernel/Makefile index a4d1aa8da9b..bbaf7d59c1b 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/ @@ -34,29 +31,19 @@ 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-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o modsign_certificate.o +obj-$(CONFIG_MODULE_SIG) += module_signing.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o obj-$(CONFIG_KEXEC) += kexec.o @@ -136,19 +123,52 @@ targets += timeconst.h $(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE $(call if_changed,bc) -ifeq ($(CONFIG_MODULE_SIG),y) +############################################################################### +# +# Roll all the X.509 certificates that we can find together and pull them into +# the kernel so that they get loaded into the system trusted keyring during +# boot. # -# Pull the signing certificate and any extra certificates into the kernel +# We look in the source root and the build root for all files whose name ends +# in ".x509". Unfortunately, this will generate duplicate filenames, so we +# have make canonicalise the pathnames and then sort them to discard the +# duplicates. # +############################################################################### +ifeq ($(CONFIG_SYSTEM_TRUSTED_KEYRING),y) +X509_CERTIFICATES-y := $(wildcard *.x509) $(wildcard $(srctree)/*.x509) +X509_CERTIFICATES-$(CONFIG_MODULE_SIG) += signing_key.x509 +X509_CERTIFICATES := $(sort $(foreach CERT,$(X509_CERTIFICATES-y), \ + $(or $(realpath $(CERT)),$(CERT)))) + +ifeq ($(X509_CERTIFICATES),) +$(warning *** No X.509 certificates found ***) +endif -quiet_cmd_touch = TOUCH $@ - cmd_touch = touch $@ +ifneq ($(wildcard $(obj)/.x509.list),) +ifneq ($(shell cat $(obj)/.x509.list),$(X509_CERTIFICATES)) +$(info X.509 certificate list changed) +$(shell rm $(obj)/.x509.list) +endif +endif + +kernel/system_certificates.o: $(obj)/x509_certificate_list + +quiet_cmd_x509certs = CERTS $@ + cmd_x509certs = cat $(X509_CERTIFICATES) /dev/null >$@ $(foreach X509,$(X509_CERTIFICATES),; echo " - Including cert $(X509)") -extra_certificates: - $(call cmd,touch) +targets += $(obj)/x509_certificate_list +$(obj)/x509_certificate_list: $(X509_CERTIFICATES) $(obj)/.x509.list + $(call if_changed,x509certs) -kernel/modsign_certificate.o: signing_key.x509 extra_certificates +targets += $(obj)/.x509.list +$(obj)/.x509.list: + @echo $(X509_CERTIFICATES) >$@ +clean-files := x509_certificate_list .x509.list +endif + +ifeq ($(CONFIG_MODULE_SIG),y) ############################################################################### # # If module signing is requested, say by allyesconfig, but a key has not been diff --git a/kernel/audit.c b/kernel/audit.c index 7b0e23a740c..906ae5a0233 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -60,7 +60,6 @@ #ifdef CONFIG_SECURITY #include <linux/security.h> #endif -#include <net/netlink.h> #include <linux/freezer.h> #include <linux/tty.h> #include <linux/pid_namespace.h> @@ -140,6 +139,17 @@ static struct task_struct *kauditd_task; static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait); static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait); +static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION, + .mask = -1, + .features = 0, + .lock = 0,}; + +static char *audit_feature_names[2] = { + "only_unset_loginuid", + "loginuid_immutable", +}; + + /* Serialize requests from userspace. */ DEFINE_MUTEX(audit_cmd_mutex); @@ -584,6 +594,8 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) return -EOPNOTSUPP; case AUDIT_GET: case AUDIT_SET: + case AUDIT_GET_FEATURE: + case AUDIT_SET_FEATURE: case AUDIT_LIST_RULES: case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: @@ -613,7 +625,7 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type) int rc = 0; uid_t uid = from_kuid(&init_user_ns, current_uid()); - if (!audit_enabled) { + if (!audit_enabled && msg_type != AUDIT_USER_AVC) { *ab = NULL; return rc; } @@ -628,6 +640,94 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type) return rc; } +int is_audit_feature_set(int i) +{ + return af.features & AUDIT_FEATURE_TO_MASK(i); +} + + +static int audit_get_feature(struct sk_buff *skb) +{ + u32 seq; + + seq = nlmsg_hdr(skb)->nlmsg_seq; + + audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0, + &af, sizeof(af)); + + return 0; +} + +static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature, + u32 old_lock, u32 new_lock, int res) +{ + struct audit_buffer *ab; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_FEATURE_CHANGE); + audit_log_format(ab, "feature=%s new=%d old=%d old_lock=%d new_lock=%d res=%d", + audit_feature_names[which], !!old_feature, !!new_feature, + !!old_lock, !!new_lock, res); + audit_log_end(ab); +} + +static int audit_set_feature(struct sk_buff *skb) +{ + struct audit_features *uaf; + int i; + + BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > sizeof(audit_feature_names)/sizeof(audit_feature_names[0])); + uaf = nlmsg_data(nlmsg_hdr(skb)); + + /* if there is ever a version 2 we should handle that here */ + + for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { + u32 feature = AUDIT_FEATURE_TO_MASK(i); + u32 old_feature, new_feature, old_lock, new_lock; + + /* if we are not changing this feature, move along */ + if (!(feature & uaf->mask)) + continue; + + old_feature = af.features & feature; + new_feature = uaf->features & feature; + new_lock = (uaf->lock | af.lock) & feature; + old_lock = af.lock & feature; + + /* are we changing a locked feature? */ + if ((af.lock & feature) && (new_feature != old_feature)) { + audit_log_feature_change(i, old_feature, new_feature, + old_lock, new_lock, 0); + return -EPERM; + } + } + /* nothing invalid, do the changes */ + for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { + u32 feature = AUDIT_FEATURE_TO_MASK(i); + u32 old_feature, new_feature, old_lock, new_lock; + + /* if we are not changing this feature, move along */ + if (!(feature & uaf->mask)) + continue; + + old_feature = af.features & feature; + new_feature = uaf->features & feature; + old_lock = af.lock & feature; + new_lock = (uaf->lock | af.lock) & feature; + + if (new_feature != old_feature) + audit_log_feature_change(i, old_feature, new_feature, + old_lock, new_lock, 1); + + if (new_feature) + af.features |= feature; + else + af.features &= ~feature; + af.lock |= new_lock; + } + + return 0; +} + static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { u32 seq; @@ -659,6 +759,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) switch (msg_type) { case AUDIT_GET: + memset(&status_set, 0, sizeof(status_set)); status_set.enabled = audit_enabled; status_set.failure = audit_failure; status_set.pid = audit_pid; @@ -670,7 +771,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) &status_set, sizeof(status_set)); break; case AUDIT_SET: - if (nlh->nlmsg_len < sizeof(struct audit_status)) + if (nlmsg_len(nlh) < sizeof(struct audit_status)) return -EINVAL; status_get = (struct audit_status *)data; if (status_get->mask & AUDIT_STATUS_ENABLED) { @@ -699,6 +800,16 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (status_get->mask & AUDIT_STATUS_BACKLOG_LIMIT) err = audit_set_backlog_limit(status_get->backlog_limit); break; + case AUDIT_GET_FEATURE: + err = audit_get_feature(skb); + if (err) + return err; + break; + case AUDIT_SET_FEATURE: + err = audit_set_feature(skb); + if (err) + return err; + break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: @@ -715,7 +826,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } audit_log_common_recv_msg(&ab, msg_type); if (msg_type != AUDIT_USER_TTY) - audit_log_format(ab, " msg='%.1024s'", + audit_log_format(ab, " msg='%.*s'", + AUDIT_MESSAGE_TEXT_MAX, (char *)data); else { int size; @@ -818,7 +930,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) struct task_struct *tsk = current; spin_lock(&tsk->sighand->siglock); - s.enabled = tsk->signal->audit_tty != 0; + s.enabled = tsk->signal->audit_tty; s.log_passwd = tsk->signal->audit_tty_log_passwd; spin_unlock(&tsk->sighand->siglock); @@ -832,7 +944,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min(sizeof(s), (size_t)nlh->nlmsg_len)); + memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); if ((s.enabled != 0 && s.enabled != 1) || (s.log_passwd != 0 && s.log_passwd != 1)) return -EINVAL; @@ -1067,13 +1179,6 @@ static void wait_for_auditd(unsigned long sleep_time) remove_wait_queue(&audit_backlog_wait, &wait); } -/* Obtain an audit buffer. This routine does locking to obtain the - * audit buffer, but then no locking is required for calls to - * audit_log_*format. If the tsk is a task that is currently in a - * syscall, then the syscall is marked as auditable and an audit record - * will be written at syscall exit. If there is no associated task, tsk - * should be NULL. */ - /** * audit_log_start - obtain an audit buffer * @ctx: audit_context (may be NULL) @@ -1389,7 +1494,7 @@ void audit_log_session_info(struct audit_buffer *ab) u32 sessionid = audit_get_sessionid(current); uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current)); - audit_log_format(ab, " auid=%u ses=%u\n", auid, sessionid); + audit_log_format(ab, " auid=%u ses=%u", auid, sessionid); } void audit_log_key(struct audit_buffer *ab, char *key) @@ -1536,6 +1641,26 @@ void audit_log_name(struct audit_context *context, struct audit_names *n, } } + /* log the audit_names record type */ + audit_log_format(ab, " nametype="); + switch(n->type) { + case AUDIT_TYPE_NORMAL: + audit_log_format(ab, "NORMAL"); + break; + case AUDIT_TYPE_PARENT: + audit_log_format(ab, "PARENT"); + break; + case AUDIT_TYPE_CHILD_DELETE: + audit_log_format(ab, "DELETE"); + break; + case AUDIT_TYPE_CHILD_CREATE: + audit_log_format(ab, "CREATE"); + break; + default: + audit_log_format(ab, "UNKNOWN"); + break; + } + audit_log_fcaps(ab, n); audit_log_end(ab); } diff --git a/kernel/audit.h b/kernel/audit.h index 123c9b7c397..b779642b29a 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -197,6 +197,9 @@ struct audit_context { int fd; int flags; } mmap; + struct { + int argc; + } execve; }; int fds[2]; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index f7aee8be7fb..51f3fd4c1ed 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -343,6 +343,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) case AUDIT_DEVMINOR: case AUDIT_EXIT: case AUDIT_SUCCESS: + case AUDIT_INODE: /* bit ops are only useful on syscall args */ if (f->op == Audit_bitmask || f->op == Audit_bittest) return -EINVAL; @@ -423,7 +424,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, f->lsm_rule = NULL; /* Support legacy tests for a valid loginuid */ - if ((f->type == AUDIT_LOGINUID) && (f->val == ~0U)) { + if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; f->val = 0; } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 9845cb32b60..90594c9f755 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -95,13 +95,6 @@ struct audit_aux_data { /* Number of target pids per aux struct. */ #define AUDIT_AUX_PIDS 16 -struct audit_aux_data_execve { - struct audit_aux_data d; - int argc; - int envc; - struct mm_struct *mm; -}; - struct audit_aux_data_pids { struct audit_aux_data d; pid_t target_pid[AUDIT_AUX_PIDS]; @@ -121,12 +114,6 @@ struct audit_aux_data_bprm_fcaps { struct audit_cap_data new_pcap; }; -struct audit_aux_data_capset { - struct audit_aux_data d; - pid_t pid; - struct audit_cap_data cap; -}; - struct audit_tree_refs { struct audit_tree_refs *next; struct audit_chunk *c[31]; @@ -566,7 +553,7 @@ static int audit_filter_rules(struct task_struct *tsk, break; case AUDIT_INODE: if (name) - result = (name->ino == f->val); + result = audit_comparator(name->ino, f->op, f->val); else if (ctx) { list_for_each_entry(n, &ctx->names_list, list) { if (audit_comparator(n->ino, f->op, f->val)) { @@ -943,8 +930,10 @@ int audit_alloc(struct task_struct *tsk) return 0; /* Return if not auditing. */ state = audit_filter_task(tsk, &key); - if (state == AUDIT_DISABLED) + if (state == AUDIT_DISABLED) { + clear_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT); return 0; + } if (!(context = audit_alloc_context(state))) { kfree(key); @@ -1149,20 +1138,16 @@ static int audit_log_single_execve_arg(struct audit_context *context, } static void audit_log_execve_info(struct audit_context *context, - struct audit_buffer **ab, - struct audit_aux_data_execve *axi) + struct audit_buffer **ab) { int i, len; size_t len_sent = 0; const char __user *p; char *buf; - if (axi->mm != current->mm) - return; /* execve failed, no additional info */ - - p = (const char __user *)axi->mm->arg_start; + p = (const char __user *)current->mm->arg_start; - audit_log_format(*ab, "argc=%d", axi->argc); + audit_log_format(*ab, "argc=%d", context->execve.argc); /* * we need some kernel buffer to hold the userspace args. Just @@ -1176,7 +1161,7 @@ static void audit_log_execve_info(struct audit_context *context, return; } - for (i = 0; i < axi->argc; i++) { + for (i = 0; i < context->execve.argc; i++) { len = audit_log_single_execve_arg(context, ab, i, &len_sent, p, buf); if (len <= 0) @@ -1279,6 +1264,9 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd, context->mmap.flags); break; } + case AUDIT_EXECVE: { + audit_log_execve_info(context, &ab); + break; } } audit_log_end(ab); } @@ -1325,11 +1313,6 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts switch (aux->type) { - case AUDIT_EXECVE: { - struct audit_aux_data_execve *axi = (void *)aux; - audit_log_execve_info(context, &ab, axi); - break; } - case AUDIT_BPRM_FCAPS: { struct audit_aux_data_bprm_fcaps *axs = (void *)aux; audit_log_format(ab, "fver=%x", axs->fcap_ver); @@ -1964,6 +1947,43 @@ int auditsc_get_stamp(struct audit_context *ctx, /* global counter which is incremented every time something logs in */ static atomic_t session_id = ATOMIC_INIT(0); +static int audit_set_loginuid_perm(kuid_t loginuid) +{ + /* if we are unset, we don't need privs */ + if (!audit_loginuid_set(current)) + return 0; + /* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/ + if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE)) + return -EPERM; + /* it is set, you need permission */ + if (!capable(CAP_AUDIT_CONTROL)) + return -EPERM; + /* reject if this is not an unset and we don't allow that */ + if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid)) + return -EPERM; + return 0; +} + +static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, + unsigned int oldsessionid, unsigned int sessionid, + int rc) +{ + struct audit_buffer *ab; + uid_t uid, ologinuid, nloginuid; + + uid = from_kuid(&init_user_ns, task_uid(current)); + ologinuid = from_kuid(&init_user_ns, koldloginuid); + nloginuid = from_kuid(&init_user_ns, kloginuid), + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); + if (!ab) + return; + audit_log_format(ab, "pid=%d uid=%u old auid=%u new auid=%u old " + "ses=%u new ses=%u res=%d", current->pid, uid, ologinuid, + nloginuid, oldsessionid, sessionid, !rc); + audit_log_end(ab); +} + /** * audit_set_loginuid - set current task's audit_context loginuid * @loginuid: loginuid value @@ -1975,37 +1995,26 @@ static atomic_t session_id = ATOMIC_INIT(0); int audit_set_loginuid(kuid_t loginuid) { struct task_struct *task = current; - struct audit_context *context = task->audit_context; - unsigned int sessionid; + unsigned int oldsessionid, sessionid = (unsigned int)-1; + kuid_t oldloginuid; + int rc; -#ifdef CONFIG_AUDIT_LOGINUID_IMMUTABLE - if (audit_loginuid_set(task)) - return -EPERM; -#else /* CONFIG_AUDIT_LOGINUID_IMMUTABLE */ - if (!capable(CAP_AUDIT_CONTROL)) - return -EPERM; -#endif /* CONFIG_AUDIT_LOGINUID_IMMUTABLE */ + oldloginuid = audit_get_loginuid(current); + oldsessionid = audit_get_sessionid(current); - sessionid = atomic_inc_return(&session_id); - if (context && context->in_syscall) { - struct audit_buffer *ab; + rc = audit_set_loginuid_perm(loginuid); + if (rc) + goto out; + + /* are we setting or clearing? */ + if (uid_valid(loginuid)) + sessionid = atomic_inc_return(&session_id); - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_LOGIN); - if (ab) { - audit_log_format(ab, "login pid=%d uid=%u " - "old auid=%u new auid=%u" - " old ses=%u new ses=%u", - task->pid, - from_kuid(&init_user_ns, task_uid(task)), - from_kuid(&init_user_ns, task->loginuid), - from_kuid(&init_user_ns, loginuid), - task->sessionid, sessionid); - audit_log_end(ab); - } - } task->sessionid = sessionid; task->loginuid = loginuid; - return 0; +out: + audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc); + return rc; } /** @@ -2126,22 +2135,12 @@ void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mo context->ipc.has_perm = 1; } -int __audit_bprm(struct linux_binprm *bprm) +void __audit_bprm(struct linux_binprm *bprm) { - struct audit_aux_data_execve *ax; struct audit_context *context = current->audit_context; - ax = kmalloc(sizeof(*ax), GFP_KERNEL); - if (!ax) - return -ENOMEM; - - ax->argc = bprm->argc; - ax->envc = bprm->envc; - ax->mm = bprm->mm; - ax->d.type = AUDIT_EXECVE; - ax->d.next = context->aux; - context->aux = (void *)ax; - return 0; + context->type = AUDIT_EXECVE; + context->execve.argc = bprm->argc; } diff --git a/kernel/bounds.c b/kernel/bounds.c index e8ca97b5c38..5253204afdc 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -11,6 +11,7 @@ #include <linux/kbuild.h> #include <linux/page_cgroup.h> #include <linux/log2.h> +#include <linux/spinlock_types.h> void foo(void) { @@ -21,5 +22,6 @@ void foo(void) #ifdef CONFIG_SMP DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS)); #endif + DEFINE(BLOATED_SPINLOCKS, sizeof(spinlock_t) > sizeof(int)); /* End of constants */ } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 8bd9cfdc70d..8b729c278b6 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -90,6 +90,14 @@ static DEFINE_MUTEX(cgroup_mutex); static DEFINE_MUTEX(cgroup_root_mutex); /* + * cgroup destruction makes heavy use of work items and there can be a lot + * of concurrent destructions. Use a separate workqueue so that cgroup + * destruction work items don't end up filling up max_active of system_wq + * which may lead to deadlock. + */ +static struct workqueue_struct *cgroup_destroy_wq; + +/* * Generate an array of cgroup subsystem pointers. At boot time, this is * populated with the built in subsystems, and modular subsystems are * registered after that. The mutable section of this array is protected by @@ -125,38 +133,6 @@ 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 { @@ -223,6 +199,7 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp); static int cgroup_destroy_locked(struct cgroup *cgrp); static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[], bool is_add); +static int cgroup_file_release(struct inode *inode, struct file *file); /** * cgroup_css - obtain a cgroup's css for the specified subsystem @@ -387,9 +364,6 @@ 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 +815,6 @@ 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); @@ -908,7 +880,7 @@ static void cgroup_free_rcu(struct rcu_head *head) struct cgroup *cgrp = container_of(head, struct cgroup, rcu_head); INIT_WORK(&cgrp->destroy_work, cgroup_free_fn); - schedule_work(&cgrp->destroy_work); + queue_work(cgroup_destroy_wq, &cgrp->destroy_work); } static void cgroup_diput(struct dentry *dentry, struct inode *inode) @@ -932,11 +904,6 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) iput(inode); } -static int cgroup_delete(const struct dentry *d) -{ - return 1; -} - static void remove_dir(struct dentry *d) { struct dentry *parent = dget(d->d_parent); @@ -1523,7 +1490,7 @@ static int cgroup_get_rootdir(struct super_block *sb) { static const struct dentry_operations cgroup_dops = { .d_iput = cgroup_diput, - .d_delete = cgroup_delete, + .d_delete = always_delete_dentry, }; struct inode *inode = @@ -2463,7 +2430,7 @@ static const struct file_operations cgroup_seqfile_operations = { .read = seq_read, .write = cgroup_file_write, .llseek = seq_lseek, - .release = single_release, + .release = cgroup_file_release, }; static int cgroup_file_open(struct inode *inode, struct file *file) @@ -2524,6 +2491,8 @@ static int cgroup_file_release(struct inode *inode, struct file *file) ret = cft->release(inode, file); if (css->ss) css_put(css); + if (file->f_op == &cgroup_seqfile_operations) + single_release(inode, file); return ret; } @@ -4240,21 +4209,6 @@ 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); @@ -4306,7 +4260,7 @@ static void css_free_rcu_fn(struct rcu_head *rcu_head) * css_put(). dput() requires process context which we don't have. */ INIT_WORK(&css->destroy_work, css_free_work_fn); - schedule_work(&css->destroy_work); + queue_work(cgroup_destroy_wq, &css->destroy_work); } static void css_release(struct percpu_ref *ref) @@ -4323,7 +4277,6 @@ 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 +4408,6 @@ 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; - } } /* @@ -4603,7 +4550,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref) container_of(ref, struct cgroup_subsys_state, refcnt); INIT_WORK(&css->destroy_work, css_killed_work_fn); - schedule_work(&css->destroy_work); + queue_work(cgroup_destroy_wq, &css->destroy_work); } /** @@ -4925,12 +4872,6 @@ 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 +4937,6 @@ 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 +4963,7 @@ 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 +5034,6 @@ 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 */ @@ -5139,6 +5074,22 @@ out: return err; } +static int __init cgroup_wq_init(void) +{ + /* + * There isn't much point in executing destruction path in + * parallel. Good chunk is serialized with cgroup_mutex anyway. + * Use 1 for @max_active. + * + * We would prefer to do this in cgroup_init() above, but that + * is called before init_workqueues(): so leave this until after. + */ + cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); + BUG_ON(!cgroup_destroy_wq); + return 0; +} +core_initcall(cgroup_wq_init); + /* * proc_cgroup_show() * - Print task's cgroup paths into seq_file, one line for each hierarchy @@ -5518,181 +5469,6 @@ 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 63aa50d7ce1..deff2e69376 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -306,7 +306,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) __func__, cpu); goto out_release; } - smpboot_park_threads(cpu); /* * By now we've cleared cpu_active_mask, wait for all preempt-disabled @@ -315,12 +314,16 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) * * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might * not imply sync_sched(), so explicitly call both. + * + * Do sync before park smpboot threads to take care the rcu boost case. */ #ifdef CONFIG_PREEMPT synchronize_sched(); #endif synchronize_rcu(); + smpboot_park_threads(cpu); + /* * So now all preempt/rcu users must observe !cpu_active(). */ @@ -437,11 +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); @@ -452,27 +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/cpuset.c b/kernel/cpuset.c index 6bf981e13c4..4772034b4b1 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1033,8 +1033,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, need_loop = task_has_mempolicy(tsk) || !nodes_intersects(*newmems, tsk->mems_allowed); - if (need_loop) + if (need_loop) { + local_irq_disable(); write_seqcount_begin(&tsk->mems_allowed_seq); + } nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1); @@ -1042,8 +1044,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2); tsk->mems_allowed = *newmems; - if (need_loop) + if (need_loop) { write_seqcount_end(&tsk->mems_allowed_seq); + local_irq_enable(); + } task_unlock(tsk); } 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..72348dc192c 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) { @@ -5683,11 +5680,6 @@ static void swevent_hlist_put(struct perf_event *event) { int cpu; - if (event->cpu != -1) { - swevent_hlist_put_cpu(event, event->cpu); - return; - } - for_each_possible_cpu(cpu) swevent_hlist_put_cpu(event, cpu); } @@ -5721,9 +5713,6 @@ static int swevent_hlist_get(struct perf_event *event) int err; int cpu, failed_cpu; - if (event->cpu != -1) - return swevent_hlist_get_cpu(event, event->cpu); - get_online_cpus(); for_each_possible_cpu(cpu) { err = swevent_hlist_get_cpu(event, cpu); diff --git a/kernel/extable.c b/kernel/extable.c index 832cb28105b..763faf037ec 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -61,7 +61,7 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) static inline int init_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_sinittext && - addr <= (unsigned long)_einittext) + addr < (unsigned long)_einittext) return 1; return 0; } @@ -69,7 +69,7 @@ static inline int init_kernel_text(unsigned long addr) int core_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_stext && - addr <= (unsigned long)_etext) + addr < (unsigned long)_etext) return 1; if (system_state == SYSTEM_BOOTING && diff --git a/kernel/fork.c b/kernel/fork.c index f6d11fc67f7..728d5be9548 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -532,7 +532,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) mm->flags = (current->mm) ? (current->mm->flags & MMF_INIT_MASK) : default_dump_filter; mm->core_state = NULL; - mm->nr_ptes = 0; + atomic_long_set(&mm->nr_ptes, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); mm_init_aio(mm); @@ -560,7 +560,7 @@ static void check_mm(struct mm_struct *mm) "mm:%p idx:%d val:%ld\n", mm, i, x); } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS VM_BUG_ON(mm->pmd_huge_pte); #endif } @@ -814,7 +814,7 @@ struct mm_struct *dup_mm(struct task_struct *tsk) memcpy(mm, oldmm, sizeof(*mm)); mm_init_cpumask(mm); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; #endif if (!mm_init(mm, tsk)) 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..9328b80eaf1 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--; @@ -203,6 +207,14 @@ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, return ret; } +static atomic_t reset_hung_task = ATOMIC_INIT(0); + +void reset_hung_task_detector(void) +{ + atomic_set(&reset_hung_task, 1); +} +EXPORT_SYMBOL_GPL(reset_hung_task_detector); + /* * kthread which checks for tasks stuck in D state */ @@ -216,6 +228,9 @@ static int watchdog(void *dummy) while (schedule_timeout_interruptible(timeout_jiffies(timeout))) timeout = sysctl_hung_task_timeout_secs; + if (atomic_xchg(&reset_hung_task, 0)) + continue; + check_hung_uninterruptible_tasks(timeout); } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index a3bb14fbe5c..dc04c166c54 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -214,7 +214,7 @@ void irq_enable(struct irq_desc *desc) } /** - * irq_disable - Mark interupt disabled + * irq_disable - Mark interrupt disabled * @desc: irq descriptor which should be disabled * * If the chip does not implement the irq_disable callback, we 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/irq/manage.c b/kernel/irq/manage.c index 3e59f951d42..481a13c43b1 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -786,7 +786,7 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) } /* - * Interrupts explicitely requested as threaded interupts want to be + * Interrupts explicitly requested as threaded interrupts want to be * preemtible - many of them need to sleep and wait for slow busses to * complete. */ 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/kexec.c b/kernel/kexec.c index 2a74f307c5e..490afc03627 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -921,7 +921,7 @@ static int kimage_load_segment(struct kimage *image, * reinitialize them. * * - A machine specific part that includes the syscall number - * and the copies the image to it's final destination. And + * and then copies the image to it's final destination. And * jumps into the image at entry. * * kexec does not sync, or unmount filesystems so if you need 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/modsign_certificate.S b/kernel/modsign_certificate.S deleted file mode 100644 index 4a9a86d12c8..00000000000 --- a/kernel/modsign_certificate.S +++ /dev/null @@ -1,12 +0,0 @@ -#include <linux/export.h> - -#define GLOBAL(name) \ - .globl VMLINUX_SYMBOL(name); \ - VMLINUX_SYMBOL(name): - - .section ".init.data","aw" - -GLOBAL(modsign_certificate_list) - .incbin "signing_key.x509" - .incbin "extra_certificates" -GLOBAL(modsign_certificate_list_end) diff --git a/kernel/modsign_pubkey.c b/kernel/modsign_pubkey.c deleted file mode 100644 index 7cbd4507a7e..00000000000 --- a/kernel/modsign_pubkey.c +++ /dev/null @@ -1,104 +0,0 @@ -/* Public keys for module signature verification - * - * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - */ - -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/cred.h> -#include <linux/err.h> -#include <keys/asymmetric-type.h> -#include "module-internal.h" - -struct key *modsign_keyring; - -extern __initconst const u8 modsign_certificate_list[]; -extern __initconst const u8 modsign_certificate_list_end[]; - -/* - * We need to make sure ccache doesn't cache the .o file as it doesn't notice - * if modsign.pub changes. - */ -static __initconst const char annoy_ccache[] = __TIME__ "foo"; - -/* - * Load the compiled-in keys - */ -static __init int module_verify_init(void) -{ - pr_notice("Initialise module verification\n"); - - modsign_keyring = keyring_alloc(".module_sign", - KUIDT_INIT(0), KGIDT_INIT(0), - current_cred(), - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ), - KEY_ALLOC_NOT_IN_QUOTA, NULL); - if (IS_ERR(modsign_keyring)) - panic("Can't allocate module signing keyring\n"); - - return 0; -} - -/* - * Must be initialised before we try and load the keys into the keyring. - */ -device_initcall(module_verify_init); - -/* - * Load the compiled-in keys - */ -static __init int load_module_signing_keys(void) -{ - key_ref_t key; - const u8 *p, *end; - size_t plen; - - pr_notice("Loading module verification certificates\n"); - - end = modsign_certificate_list_end; - p = modsign_certificate_list; - while (p < end) { - /* Each cert begins with an ASN.1 SEQUENCE tag and must be more - * than 256 bytes in size. - */ - if (end - p < 4) - goto dodgy_cert; - if (p[0] != 0x30 && - p[1] != 0x82) - goto dodgy_cert; - plen = (p[2] << 8) | p[3]; - plen += 4; - if (plen > end - p) - goto dodgy_cert; - - key = key_create_or_update(make_key_ref(modsign_keyring, 1), - "asymmetric", - NULL, - p, - plen, - (KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW, - KEY_ALLOC_NOT_IN_QUOTA); - if (IS_ERR(key)) - pr_err("MODSIGN: Problem loading in-kernel X.509 certificate (%ld)\n", - PTR_ERR(key)); - else - pr_notice("MODSIGN: Loaded cert '%s'\n", - key_ref_to_ptr(key)->description); - p += plen; - } - - return 0; - -dodgy_cert: - pr_err("MODSIGN: Problem parsing in-kernel X.509 certificate list\n"); - return 0; -} -late_initcall(load_module_signing_keys); diff --git a/kernel/module-internal.h b/kernel/module-internal.h index 24f9247b7d0..915e123a430 100644 --- a/kernel/module-internal.h +++ b/kernel/module-internal.h @@ -9,6 +9,4 @@ * 2 of the Licence, or (at your option) any later version. */ -extern struct key *modsign_keyring; - extern int mod_verify_sig(const void *mod, unsigned long *_modlen); diff --git a/kernel/module.c b/kernel/module.c index dc582749fa1..f5a3b1e8ec5 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; @@ -644,8 +641,6 @@ static int module_unload_init(struct module *mod) /* Hold reference count during initialization. */ __this_cpu_write(mod->refptr->incs, 1); - /* Backwards compatibility macros put refcount during init. */ - mod->waiter = current; return 0; } @@ -679,7 +674,7 @@ 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; } @@ -771,16 +766,9 @@ static int __try_stop_module(void *_sref) static int try_stop_module(struct module *mod, int flags, int *forced) { - if (flags & O_NONBLOCK) { - struct stopref sref = { mod, flags, forced }; + struct stopref sref = { mod, flags, forced }; - return stop_machine(__try_stop_module, &sref, NULL); - } else { - /* We don't need to stop the machine for this. */ - mod->state = MODULE_STATE_GOING; - synchronize_sched(); - return 0; - } + return stop_machine(__try_stop_module, &sref, NULL); } unsigned long module_refcount(struct module *mod) @@ -813,21 +801,6 @@ EXPORT_SYMBOL(module_refcount); /* This exists whether we can unload or not */ static void free_module(struct module *mod); -static void wait_for_zero_refcount(struct module *mod) -{ - /* Since we might sleep for some time, release the mutex first */ - mutex_unlock(&module_mutex); - for (;;) { - pr_debug("Looking at refcount...\n"); - set_current_state(TASK_UNINTERRUPTIBLE); - if (module_refcount(mod) == 0) - break; - schedule(); - } - current->state = TASK_RUNNING; - mutex_lock(&module_mutex); -} - SYSCALL_DEFINE2(delete_module, const char __user *, name_user, unsigned int, flags) { @@ -842,6 +815,11 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, return -EFAULT; name[MODULE_NAME_LEN-1] = '\0'; + if (!(flags & O_NONBLOCK)) { + printk(KERN_WARNING + "waiting module removal not supported: please upgrade"); + } + if (mutex_lock_interruptible(&module_mutex) != 0) return -EINTR; @@ -859,8 +837,7 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, /* Doing init or already dying? */ if (mod->state != MODULE_STATE_LIVE) { - /* FIXME: if (force), slam module count and wake up - waiter --RR */ + /* FIXME: if (force), slam module count damn the torpedoes */ pr_debug("%s already dying\n", mod->name); ret = -EBUSY; goto out; @@ -876,18 +853,11 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, } } - /* Set this up before setting mod->state */ - mod->waiter = current; - /* Stop the machine so refcounts can't move and disable module. */ ret = try_stop_module(mod, flags, &forced); if (ret != 0) goto out; - /* Never wait if forced. */ - if (!forced && module_refcount(mod) != 0) - wait_for_zero_refcount(mod); - mutex_unlock(&module_mutex); /* Final destruction now no one is using it. */ if (mod->exit != NULL) @@ -1005,9 +975,6 @@ void module_put(struct module *module) __this_cpu_inc(module->refptr->decs); trace_module_put(module, _RET_IP_); - /* Maybe they're waiting for us to drop reference? */ - if (unlikely(!module_is_live(module))) - wake_up_process(module->waiter); preempt_enable(); } } @@ -1145,8 +1112,7 @@ 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 +1165,7 @@ 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 +1274,8 @@ 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 +1591,14 @@ 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 +1925,7 @@ 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 +1976,8 @@ 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 +2131,8 @@ 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 +2368,8 @@ 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 +2582,7 @@ 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 +2644,14 @@ 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 +2678,7 @@ 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 +2688,8 @@ 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 */ @@ -2738,7 +2698,7 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags) return 0; } -static void find_module_sections(struct module *mod, struct load_info *info) +static int find_module_sections(struct module *mod, struct load_info *info) { mod->kp = section_objs(info, "__param", sizeof(*mod->kp), &mod->num_kp); @@ -2768,6 +2728,18 @@ static void find_module_sections(struct module *mod, struct load_info *info) #ifdef CONFIG_CONSTRUCTORS mod->ctors = section_objs(info, ".ctors", sizeof(*mod->ctors), &mod->num_ctors); + if (!mod->ctors) + mod->ctors = section_objs(info, ".init_array", + sizeof(*mod->ctors), &mod->num_ctors); + else if (find_sec(info, ".init_array")) { + /* + * This shouldn't happen with same compiler and binutils + * building all parts of the module. + */ + printk(KERN_WARNING "%s: has both .ctors and .init_array.\n", + mod->name); + return -EINVAL; + } #endif #ifdef CONFIG_TRACEPOINTS @@ -2801,11 +2773,12 @@ 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); + + return 0; } static int move_module(struct module *mod, struct load_info *info) @@ -3078,11 +3051,10 @@ 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 +3177,8 @@ 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 +3213,9 @@ 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 @@ -3263,7 +3232,9 @@ static int load_module(struct load_info *info, const char __user *uargs, /* Now we've got everything in the final locations, we can * find optional sections. */ - find_module_sections(mod, info); + err = find_module_sections(mod, info); + if (err) + goto free_unload; err = check_module_license_and_versions(mod); if (err) diff --git a/kernel/module_signing.c b/kernel/module_signing.c index f2970bddc5e..be5b8fac4bd 100644 --- a/kernel/module_signing.c +++ b/kernel/module_signing.c @@ -14,6 +14,7 @@ #include <crypto/public_key.h> #include <crypto/hash.h> #include <keys/asymmetric-type.h> +#include <keys/system_keyring.h> #include "module-internal.h" /* @@ -28,7 +29,7 @@ */ struct module_signature { u8 algo; /* Public-key crypto algorithm [enum pkey_algo] */ - u8 hash; /* Digest algorithm [enum pkey_hash_algo] */ + u8 hash; /* Digest algorithm [enum hash_algo] */ u8 id_type; /* Key identifier type [enum pkey_id_type] */ u8 signer_len; /* Length of signer's name */ u8 key_id_len; /* Length of key identifier */ @@ -39,7 +40,7 @@ struct module_signature { /* * Digest the module contents. */ -static struct public_key_signature *mod_make_digest(enum pkey_hash_algo hash, +static struct public_key_signature *mod_make_digest(enum hash_algo hash, const void *mod, unsigned long modlen) { @@ -54,7 +55,7 @@ static struct public_key_signature *mod_make_digest(enum pkey_hash_algo hash, /* Allocate the hashing algorithm we're going to need and find out how * big the hash operational data will be. */ - tfm = crypto_alloc_shash(pkey_hash_algo[hash], 0, 0); + tfm = crypto_alloc_shash(hash_algo_name[hash], 0, 0); if (IS_ERR(tfm)) return (PTR_ERR(tfm) == -ENOENT) ? ERR_PTR(-ENOPKG) : ERR_CAST(tfm); @@ -157,7 +158,7 @@ static struct key *request_asymmetric_key(const char *signer, size_t signer_len, pr_debug("Look up: \"%s\"\n", id); - key = keyring_search(make_key_ref(modsign_keyring, 1), + key = keyring_search(make_key_ref(system_trusted_keyring, 1), &key_type_asymmetric, id); if (IS_ERR(key)) pr_warn("Request for unknown module key '%s' err %ld\n", @@ -217,7 +218,7 @@ int mod_verify_sig(const void *mod, unsigned long *_modlen) return -ENOPKG; if (ms.hash >= PKEY_HASH__LAST || - !pkey_hash_algo[ms.hash]) + !hash_algo_name[ms.hash]) return -ENOPKG; key = request_asymmetric_key(sig, ms.signer_len, diff --git a/kernel/padata.c b/kernel/padata.c index 07af2c95dcf..2abd25d79cc 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -46,6 +46,7 @@ static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) static int padata_cpu_hash(struct parallel_data *pd) { + unsigned int seq_nr; int cpu_index; /* @@ -53,10 +54,8 @@ static int padata_cpu_hash(struct parallel_data *pd) * seq_nr mod. number of cpus in use. */ - spin_lock(&pd->seq_lock); - cpu_index = pd->seq_nr % cpumask_weight(pd->cpumask.pcpu); - pd->seq_nr++; - spin_unlock(&pd->seq_lock); + seq_nr = atomic_inc_return(&pd->seq_nr); + cpu_index = seq_nr % cpumask_weight(pd->cpumask.pcpu); return padata_index_to_cpu(pd, cpu_index); } @@ -429,7 +428,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, padata_init_pqueues(pd); padata_init_squeues(pd); setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd); - pd->seq_nr = 0; + atomic_set(&pd->seq_nr, -1); atomic_set(&pd->reorder_objects, 0); atomic_set(&pd->refcnt, 0); pd->pinst = pinst; 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..b38109e204a 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -792,7 +792,8 @@ void free_basic_memory_bitmaps(void) { struct memory_bitmap *bm1, *bm2; - BUG_ON(!(forbidden_pages_map && free_pages_map)); + if (WARN_ON(!(forbidden_pages_map && free_pages_map))) + return; bm1 = forbidden_pages_map; bm2 = free_pages_map; @@ -1402,7 +1403,11 @@ 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..98d357584cd 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; @@ -70,6 +70,7 @@ static int snapshot_open(struct inode *inode, struct file *filp) data->swap = swsusp_resume_device ? swap_type_of(swsusp_resume_device, 0, NULL) : -1; data->mode = O_RDONLY; + data->free_bitmaps = false; error = pm_notifier_call_chain(PM_HIBERNATION_PREPARE); if (error) pm_notifier_call_chain(PM_POST_HIBERNATION); @@ -93,9 +94,9 @@ 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 +230,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, if (error) thaw_processes(); else - data->frozen = 1; + data->frozen = true; break; @@ -240,7 +241,7 @@ 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 +271,7 @@ 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 +335,7 @@ 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/tiny.c b/kernel/rcu/tiny.c index 0c9a934cfec..1254f312d02 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -181,7 +181,7 @@ EXPORT_SYMBOL_GPL(rcu_irq_enter); /* * Test whether RCU thinks that the current CPU is idle. */ -bool __rcu_is_watching(void) +bool notrace __rcu_is_watching(void) { return rcu_dynticks_nesting; } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 4c06ddfea7c..dd081987a8e 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -664,7 +664,7 @@ void rcu_nmi_exit(void) * rcu_is_watching(), the caller of __rcu_is_watching() must have at * least disabled preemption. */ -bool __rcu_is_watching(void) +bool notrace __rcu_is_watching(void) { return atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1; } @@ -675,7 +675,7 @@ bool __rcu_is_watching(void) * If the current CPU is in its idle loop and is neither in an interrupt * or NMI handler, return true. */ -bool rcu_is_watching(void) +bool notrace rcu_is_watching(void) { int ret; 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/sched/core.c b/kernel/sched/core.c index 1deccd78be9..e85cda20ab2 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2253,6 +2253,20 @@ unsigned long long task_sched_runtime(struct task_struct *p) struct rq *rq; u64 ns = 0; +#if defined(CONFIG_64BIT) && defined(CONFIG_SMP) + /* + * 64-bit doesn't need locks to atomically read a 64bit value. + * So we have a optimization chance when the task's delta_exec is 0. + * Reading ->on_cpu is racy, but this is ok. + * + * If we race with it leaving cpu, we'll take a lock. So we're correct. + * If we race with it entering cpu, unaccounted time is 0. This is + * indistinguishable from the read occurring a few cycles earlier. + */ + if (!p->on_cpu) + return p->se.sum_exec_runtime; +#endif + rq = task_rq_lock(p, &flags); ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); task_rq_unlock(rq, p, &flags); @@ -2646,6 +2660,7 @@ asmlinkage void __sched notrace preempt_schedule(void) } while (need_resched()); } EXPORT_SYMBOL(preempt_schedule); +#endif /* CONFIG_PREEMPT */ /* * this is the entry point to schedule() from kernel preemption @@ -2679,8 +2694,6 @@ asmlinkage void __sched preempt_schedule_irq(void) exception_exit(prev_state); } -#endif /* CONFIG_PREEMPT */ - int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, void *key) { @@ -4748,7 +4761,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) cpumask_clear_cpu(rq->cpu, old_rd->span); /* - * If we dont want to free the old_rt yet then + * If we dont want to free the old_rd yet then * set old_rd to NULL to skip the freeing later * in this function: */ @@ -4896,8 +4909,9 @@ static void update_top_cache_domain(int cpu) if (sd) { id = cpumask_first(sched_domain_span(sd)); size = cpumask_weight(sched_domain_span(sd)); - rcu_assign_pointer(per_cpu(sd_busy, cpu), sd->parent); + sd = sd->parent; /* sd_busy */ } + rcu_assign_pointer(per_cpu(sd_busy, cpu), sd); rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); per_cpu(sd_llc_size, cpu) = size; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index df77c605c7a..fd773ade1a3 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1000,7 +1000,7 @@ struct numa_stats { */ static void update_numa_stats(struct numa_stats *ns, int nid) { - int cpu; + int cpu, cpus = 0; memset(ns, 0, sizeof(*ns)); for_each_cpu(cpu, cpumask_of_node(nid)) { @@ -1009,8 +1009,21 @@ static void update_numa_stats(struct numa_stats *ns, int nid) ns->nr_running += rq->nr_running; ns->load += weighted_cpuload(cpu); ns->power += power_of(cpu); + + cpus++; } + /* + * If we raced with hotplug and there are no CPUs left in our mask + * the @ns structure is NULL'ed and task_numa_compare() will + * not find this node attractive. + * + * We'll either bail at !has_capacity, or we'll detect a huge imbalance + * and bail there. + */ + if (!cpus) + return; + ns->load = (ns->load * SCHED_POWER_SCALE) / ns->power; ns->capacity = DIV_ROUND_CLOSEST(ns->power, SCHED_POWER_SCALE); ns->has_capacity = (ns->nr_running < ns->capacity); @@ -1201,9 +1214,21 @@ static int task_numa_migrate(struct task_struct *p) */ rcu_read_lock(); sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu)); - env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2; + if (sd) + env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2; rcu_read_unlock(); + /* + * Cpusets can break the scheduler domain tree into smaller + * balance domains, some of which do not cross NUMA boundaries. + * Tasks that are "trapped" in such domains cannot be migrated + * elsewhere, so there is no point in (re)trying. + */ + if (unlikely(!sd)) { + p->numa_preferred_nid = cpu_to_node(task_cpu(p)); + return -EINVAL; + } + taskweight = task_weight(p, env.src_nid); groupweight = group_weight(p, env.src_nid); update_numa_stats(&env.src_stats, env.src_nid); @@ -2153,7 +2178,7 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa, long contrib; /* The fraction of a cpu used by this cfs_rq */ - contrib = div_u64(sa->runnable_avg_sum << NICE_0_SHIFT, + contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT, sa->runnable_avg_period + 1); contrib -= cfs_rq->tg_runnable_contrib; @@ -5354,10 +5379,31 @@ void update_group_power(struct sched_domain *sd, int cpu) */ for_each_cpu(cpu, sched_group_cpus(sdg)) { - struct sched_group *sg = cpu_rq(cpu)->sd->groups; + struct sched_group_power *sgp; + struct rq *rq = cpu_rq(cpu); + + /* + * build_sched_domains() -> init_sched_groups_power() + * gets here before we've attached the domains to the + * runqueues. + * + * Use power_of(), which is set irrespective of domains + * in update_cpu_power(). + * + * This avoids power/power_orig from being 0 and + * causing divide-by-zero issues on boot. + * + * Runtime updates will correct power_orig. + */ + if (unlikely(!rq->sd)) { + power_orig += power_of(cpu); + power += power_of(cpu); + continue; + } - power_orig += sg->sgp->power_orig; - power += sg->sgp->power; + sgp = rq->sd->groups->sgp; + power_orig += sgp->power_orig; + power += sgp->power; } } else { /* 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..bd9f9402883 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -15,9 +15,9 @@ #include "smpboot.h" -#ifdef CONFIG_USE_GENERIC_SMP_HELPERS enum { CSD_FLAG_LOCK = 0x01, + CSD_FLAG_WAIT = 0x02, }; struct call_function_data { @@ -124,7 +124,7 @@ 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: @@ -139,13 +139,15 @@ static void csd_unlock(struct call_single_data *csd) * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ -static -void generic_exec_single(int cpu, struct call_single_data *csd, int wait) +static void generic_exec_single(int cpu, struct call_single_data *csd, int wait) { struct call_single_queue *dst = &per_cpu(call_single_queue, cpu); 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 +342,7 @@ 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. @@ -459,7 +462,6 @@ int smp_call_function(smp_call_func_t func, void *info, int wait) return 0; } EXPORT_SYMBOL(smp_call_function); -#endif /* USE_GENERIC_SMP_HELPERS */ /* Setup configured maximum number of CPUs to activate */ unsigned int setup_max_cpus = NR_CPUS; diff --git a/kernel/softirq.c b/kernel/softirq.c index b2498835345..11025ccc06d 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -6,8 +6,6 @@ * Distribute under GPLv2. * * Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903) - * - * Remote softirq infrastructure is by Jens Axboe. */ #include <linux/export.h> @@ -627,146 +625,17 @@ void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer, } EXPORT_SYMBOL_GPL(tasklet_hrtimer_init); -/* - * Remote softirq bits - */ - -DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list); -EXPORT_PER_CPU_SYMBOL(softirq_work_list); - -static void __local_trigger(struct call_single_data *cp, int softirq) -{ - struct list_head *head = &__get_cpu_var(softirq_work_list[softirq]); - - list_add_tail(&cp->list, head); - - /* Trigger the softirq only if the list was previously empty. */ - if (head->next == &cp->list) - raise_softirq_irqoff(softirq); -} - -#ifdef CONFIG_USE_GENERIC_SMP_HELPERS -static void remote_softirq_receive(void *data) -{ - struct call_single_data *cp = data; - unsigned long flags; - int softirq; - - softirq = *(int *)cp->info; - local_irq_save(flags); - __local_trigger(cp, softirq); - local_irq_restore(flags); -} - -static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq) -{ - if (cpu_online(cpu)) { - cp->func = remote_softirq_receive; - cp->info = &softirq; - cp->flags = 0; - - __smp_call_function_single(cpu, cp, 0); - return 0; - } - return 1; -} -#else /* CONFIG_USE_GENERIC_SMP_HELPERS */ -static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq) -{ - return 1; -} -#endif - -/** - * __send_remote_softirq - try to schedule softirq work on a remote cpu - * @cp: private SMP call function data area - * @cpu: the remote cpu - * @this_cpu: the currently executing cpu - * @softirq: the softirq for the work - * - * Attempt to schedule softirq work on a remote cpu. If this cannot be - * done, the work is instead queued up on the local cpu. - * - * Interrupts must be disabled. - */ -void __send_remote_softirq(struct call_single_data *cp, int cpu, int this_cpu, int softirq) -{ - if (cpu == this_cpu || __try_remote_softirq(cp, cpu, softirq)) - __local_trigger(cp, softirq); -} -EXPORT_SYMBOL(__send_remote_softirq); - -/** - * send_remote_softirq - try to schedule softirq work on a remote cpu - * @cp: private SMP call function data area - * @cpu: the remote cpu - * @softirq: the softirq for the work - * - * Like __send_remote_softirq except that disabling interrupts and - * computing the current cpu is done for the caller. - */ -void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq) -{ - unsigned long flags; - int this_cpu; - - local_irq_save(flags); - this_cpu = smp_processor_id(); - __send_remote_softirq(cp, cpu, this_cpu, softirq); - local_irq_restore(flags); -} -EXPORT_SYMBOL(send_remote_softirq); - -static int remote_softirq_cpu_notify(struct notifier_block *self, - unsigned long action, void *hcpu) -{ - /* - * If a CPU goes away, splice its entries to the current CPU - * and trigger a run of the softirq - */ - if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) { - int cpu = (unsigned long) hcpu; - int i; - - local_irq_disable(); - for (i = 0; i < NR_SOFTIRQS; i++) { - struct list_head *head = &per_cpu(softirq_work_list[i], cpu); - struct list_head *local_head; - - if (list_empty(head)) - continue; - - local_head = &__get_cpu_var(softirq_work_list[i]); - list_splice_init(head, local_head); - raise_softirq_irqoff(i); - } - local_irq_enable(); - } - - return NOTIFY_OK; -} - -static struct notifier_block remote_softirq_cpu_notifier = { - .notifier_call = remote_softirq_cpu_notify, -}; - void __init softirq_init(void) { int cpu; for_each_possible_cpu(cpu) { - int i; - per_cpu(tasklet_vec, cpu).tail = &per_cpu(tasklet_vec, cpu).head; per_cpu(tasklet_hi_vec, cpu).tail = &per_cpu(tasklet_hi_vec, cpu).head; - for (i = 0; i < NR_SOFTIRQS; i++) - INIT_LIST_HEAD(&per_cpu(softirq_work_list[i], cpu)); } - register_hotcpu_notifier(&remote_softirq_cpu_notifier); - open_softirq(TASKLET_SOFTIRQ, tasklet_action); open_softirq(HI_SOFTIRQ, tasklet_hi_action); } 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/system_certificates.S b/kernel/system_certificates.S new file mode 100644 index 00000000000..4aef390671c --- /dev/null +++ b/kernel/system_certificates.S @@ -0,0 +1,10 @@ +#include <linux/export.h> +#include <linux/init.h> + + __INITRODATA + + .globl VMLINUX_SYMBOL(system_certificate_list) +VMLINUX_SYMBOL(system_certificate_list): + .incbin "kernel/x509_certificate_list" + .globl VMLINUX_SYMBOL(system_certificate_list_end) +VMLINUX_SYMBOL(system_certificate_list_end): diff --git a/kernel/system_keyring.c b/kernel/system_keyring.c new file mode 100644 index 00000000000..564dd93430a --- /dev/null +++ b/kernel/system_keyring.c @@ -0,0 +1,105 @@ +/* System trusted keyring for trusted public keys + * + * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/export.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/cred.h> +#include <linux/err.h> +#include <keys/asymmetric-type.h> +#include <keys/system_keyring.h> +#include "module-internal.h" + +struct key *system_trusted_keyring; +EXPORT_SYMBOL_GPL(system_trusted_keyring); + +extern __initconst const u8 system_certificate_list[]; +extern __initconst const u8 system_certificate_list_end[]; + +/* + * Load the compiled-in keys + */ +static __init int system_trusted_keyring_init(void) +{ + pr_notice("Initialise system trusted keyring\n"); + + system_trusted_keyring = + keyring_alloc(".system_keyring", + KUIDT_INIT(0), KGIDT_INIT(0), current_cred(), + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ | KEY_USR_SEARCH), + KEY_ALLOC_NOT_IN_QUOTA, NULL); + if (IS_ERR(system_trusted_keyring)) + panic("Can't allocate system trusted keyring\n"); + + set_bit(KEY_FLAG_TRUSTED_ONLY, &system_trusted_keyring->flags); + return 0; +} + +/* + * Must be initialised before we try and load the keys into the keyring. + */ +device_initcall(system_trusted_keyring_init); + +/* + * Load the compiled-in list of X.509 certificates. + */ +static __init int load_system_certificate_list(void) +{ + key_ref_t key; + const u8 *p, *end; + size_t plen; + + pr_notice("Loading compiled-in X.509 certificates\n"); + + end = system_certificate_list_end; + p = system_certificate_list; + while (p < end) { + /* Each cert begins with an ASN.1 SEQUENCE tag and must be more + * than 256 bytes in size. + */ + if (end - p < 4) + goto dodgy_cert; + if (p[0] != 0x30 && + p[1] != 0x82) + goto dodgy_cert; + plen = (p[2] << 8) | p[3]; + plen += 4; + if (plen > end - p) + goto dodgy_cert; + + key = key_create_or_update(make_key_ref(system_trusted_keyring, 1), + "asymmetric", + NULL, + p, + plen, + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ), + KEY_ALLOC_NOT_IN_QUOTA | + KEY_ALLOC_TRUSTED); + if (IS_ERR(key)) { + pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", + PTR_ERR(key)); + } else { + pr_notice("Loaded X.509 cert '%s'\n", + key_ref_to_ptr(key)->description); + key_ref_put(key); + } + p += plen; + } + + return 0; + +dodgy_cert: + pr_err("Problem parsing in-kernel X.509 certificate list\n"); + return 0; +} +late_initcall(load_system_certificate_list); diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 145bb4d3bd4..13d2f7cd65d 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); @@ -667,17 +673,18 @@ err: nlmsg_free(rep_skb); } -static struct genl_ops taskstats_ops = { - .cmd = TASKSTATS_CMD_GET, - .doit = taskstats_user_cmd, - .policy = taskstats_cmd_get_policy, - .flags = GENL_ADMIN_PERM, -}; - -static struct genl_ops cgroupstats_ops = { - .cmd = CGROUPSTATS_CMD_GET, - .doit = cgroupstats_user_cmd, - .policy = cgroupstats_cmd_get_policy, +static const struct genl_ops taskstats_ops[] = { + { + .cmd = TASKSTATS_CMD_GET, + .doit = taskstats_user_cmd, + .policy = taskstats_cmd_get_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = CGROUPSTATS_CMD_GET, + .doit = cgroupstats_user_cmd, + .policy = cgroupstats_cmd_get_policy, + }, }; /* Needed early in initialization */ @@ -696,26 +703,13 @@ static int __init taskstats_init(void) { int rc; - rc = genl_register_family(&family); + rc = genl_register_family_with_ops(&family, taskstats_ops); if (rc) return rc; - rc = genl_register_ops(&family, &taskstats_ops); - if (rc < 0) - goto err; - - rc = genl_register_ops(&family, &cgroupstats_ops); - if (rc < 0) - goto err_cgroup_ops; - family_registered = 1; pr_info("registered taskstats version %d\n", TASKSTATS_GENL_VERSION); return 0; -err_cgroup_ops: - genl_unregister_ops(&family, &taskstats_ops); -err: - genl_unregister_family(&family); - return rc; } /* 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; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 03cf44ac54d..0e9f9eaade2 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -367,9 +367,6 @@ static int remove_ftrace_list_ops(struct ftrace_ops **list, static int __register_ftrace_function(struct ftrace_ops *ops) { - if (unlikely(ftrace_disabled)) - return -ENODEV; - if (FTRACE_WARN_ON(ops == &global_ops)) return -EINVAL; @@ -428,9 +425,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops) { int ret; - if (ftrace_disabled) - return -ENODEV; - if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED))) return -EBUSY; @@ -2088,10 +2082,15 @@ static void ftrace_startup_enable(int command) static int ftrace_startup(struct ftrace_ops *ops, int command) { bool hash_enable = true; + int ret; if (unlikely(ftrace_disabled)) return -ENODEV; + ret = __register_ftrace_function(ops); + if (ret) + return ret; + ftrace_start_up++; command |= FTRACE_UPDATE_CALLS; @@ -2113,12 +2112,17 @@ static int ftrace_startup(struct ftrace_ops *ops, int command) return 0; } -static void ftrace_shutdown(struct ftrace_ops *ops, int command) +static int ftrace_shutdown(struct ftrace_ops *ops, int command) { bool hash_disable = true; + int ret; if (unlikely(ftrace_disabled)) - return; + return -ENODEV; + + ret = __unregister_ftrace_function(ops); + if (ret) + return ret; ftrace_start_up--; /* @@ -2153,9 +2157,10 @@ static void ftrace_shutdown(struct ftrace_ops *ops, int command) } if (!command || !ftrace_enabled) - return; + return 0; ftrace_run_update_code(command); + return 0; } static void ftrace_startup_sysctl(void) @@ -3060,16 +3065,13 @@ static void __enable_ftrace_function_probe(void) if (i == FTRACE_FUNC_HASHSIZE) return; - ret = __register_ftrace_function(&trace_probe_ops); - if (!ret) - ret = ftrace_startup(&trace_probe_ops, 0); + ret = ftrace_startup(&trace_probe_ops, 0); ftrace_probe_registered = 1; } static void __disable_ftrace_function_probe(void) { - int ret; int i; if (!ftrace_probe_registered) @@ -3082,9 +3084,7 @@ static void __disable_ftrace_function_probe(void) } /* no more funcs left */ - ret = __unregister_ftrace_function(&trace_probe_ops); - if (!ret) - ftrace_shutdown(&trace_probe_ops, 0); + ftrace_shutdown(&trace_probe_ops, 0); ftrace_probe_registered = 0; } @@ -3307,7 +3307,11 @@ void unregister_ftrace_function_probe_all(char *glob) static LIST_HEAD(ftrace_commands); static DEFINE_MUTEX(ftrace_cmd_mutex); -int register_ftrace_command(struct ftrace_func_command *cmd) +/* + * Currently we only register ftrace commands from __init, so mark this + * __init too. + */ +__init int register_ftrace_command(struct ftrace_func_command *cmd) { struct ftrace_func_command *p; int ret = 0; @@ -3326,7 +3330,11 @@ int register_ftrace_command(struct ftrace_func_command *cmd) return ret; } -int unregister_ftrace_command(struct ftrace_func_command *cmd) +/* + * Currently we only unregister ftrace commands from __init, so mark + * this __init too. + */ +__init int unregister_ftrace_command(struct ftrace_func_command *cmd) { struct ftrace_func_command *p, *n; int ret = -ENODEV; @@ -3641,7 +3649,7 @@ __setup("ftrace_filter=", set_ftrace_filter); #ifdef CONFIG_FUNCTION_GRAPH_TRACER static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; -static int ftrace_set_func(unsigned long *array, int *idx, char *buffer); +static int ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer); static int __init set_graph_function(char *str) { @@ -3659,7 +3667,7 @@ static void __init set_ftrace_early_graph(char *buf) func = strsep(&buf, ","); /* we allow only one expression at a time */ ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count, - func); + FTRACE_GRAPH_MAX_FUNCS, func); if (ret) printk(KERN_DEBUG "ftrace: function %s not " "traceable\n", func); @@ -3776,15 +3784,25 @@ static const struct file_operations ftrace_notrace_fops = { static DEFINE_MUTEX(graph_lock); int ftrace_graph_count; -int ftrace_graph_filter_enabled; +int ftrace_graph_notrace_count; unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly; +unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS] __read_mostly; + +struct ftrace_graph_data { + unsigned long *table; + size_t size; + int *count; + const struct seq_operations *seq_ops; +}; static void * __g_next(struct seq_file *m, loff_t *pos) { - if (*pos >= ftrace_graph_count) + struct ftrace_graph_data *fgd = m->private; + + if (*pos >= *fgd->count) return NULL; - return &ftrace_graph_funcs[*pos]; + return &fgd->table[*pos]; } static void * @@ -3796,10 +3814,12 @@ g_next(struct seq_file *m, void *v, loff_t *pos) static void *g_start(struct seq_file *m, loff_t *pos) { + struct ftrace_graph_data *fgd = m->private; + mutex_lock(&graph_lock); /* Nothing, tell g_show to print all functions are enabled */ - if (!ftrace_graph_filter_enabled && !*pos) + if (!*fgd->count && !*pos) return (void *)1; return __g_next(m, pos); @@ -3835,38 +3855,88 @@ static const struct seq_operations ftrace_graph_seq_ops = { }; static int -ftrace_graph_open(struct inode *inode, struct file *file) +__ftrace_graph_open(struct inode *inode, struct file *file, + struct ftrace_graph_data *fgd) { int ret = 0; - if (unlikely(ftrace_disabled)) - return -ENODEV; - mutex_lock(&graph_lock); if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { - ftrace_graph_filter_enabled = 0; - ftrace_graph_count = 0; - memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs)); + *fgd->count = 0; + memset(fgd->table, 0, fgd->size * sizeof(*fgd->table)); } mutex_unlock(&graph_lock); - if (file->f_mode & FMODE_READ) - ret = seq_open(file, &ftrace_graph_seq_ops); + if (file->f_mode & FMODE_READ) { + ret = seq_open(file, fgd->seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = fgd; + } + } else + file->private_data = fgd; return ret; } static int +ftrace_graph_open(struct inode *inode, struct file *file) +{ + struct ftrace_graph_data *fgd; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + fgd = kmalloc(sizeof(*fgd), GFP_KERNEL); + if (fgd == NULL) + return -ENOMEM; + + fgd->table = ftrace_graph_funcs; + fgd->size = FTRACE_GRAPH_MAX_FUNCS; + fgd->count = &ftrace_graph_count; + fgd->seq_ops = &ftrace_graph_seq_ops; + + return __ftrace_graph_open(inode, file, fgd); +} + +static int +ftrace_graph_notrace_open(struct inode *inode, struct file *file) +{ + struct ftrace_graph_data *fgd; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + fgd = kmalloc(sizeof(*fgd), GFP_KERNEL); + if (fgd == NULL) + return -ENOMEM; + + fgd->table = ftrace_graph_notrace_funcs; + fgd->size = FTRACE_GRAPH_MAX_FUNCS; + fgd->count = &ftrace_graph_notrace_count; + fgd->seq_ops = &ftrace_graph_seq_ops; + + return __ftrace_graph_open(inode, file, fgd); +} + +static int ftrace_graph_release(struct inode *inode, struct file *file) { - if (file->f_mode & FMODE_READ) + if (file->f_mode & FMODE_READ) { + struct seq_file *m = file->private_data; + + kfree(m->private); seq_release(inode, file); + } else { + kfree(file->private_data); + } + return 0; } static int -ftrace_set_func(unsigned long *array, int *idx, char *buffer) +ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer) { struct dyn_ftrace *rec; struct ftrace_page *pg; @@ -3879,7 +3949,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) /* decode regex */ type = filter_parse_regex(buffer, strlen(buffer), &search, ¬); - if (!not && *idx >= FTRACE_GRAPH_MAX_FUNCS) + if (!not && *idx >= size) return -EBUSY; search_len = strlen(search); @@ -3907,7 +3977,7 @@ ftrace_set_func(unsigned long *array, int *idx, char *buffer) fail = 0; if (!exists) { array[(*idx)++] = rec->ip; - if (*idx >= FTRACE_GRAPH_MAX_FUNCS) + if (*idx >= size) goto out; } } else { @@ -3925,8 +3995,6 @@ out: if (fail) return -EINVAL; - ftrace_graph_filter_enabled = !!(*idx); - return 0; } @@ -3935,36 +4003,33 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_parser parser; - ssize_t read, ret; + ssize_t read, ret = 0; + struct ftrace_graph_data *fgd = file->private_data; if (!cnt) return 0; - mutex_lock(&graph_lock); - - if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) { - ret = -ENOMEM; - goto out_unlock; - } + if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) + return -ENOMEM; read = trace_get_user(&parser, ubuf, cnt, ppos); if (read >= 0 && trace_parser_loaded((&parser))) { parser.buffer[parser.idx] = 0; + mutex_lock(&graph_lock); + /* we allow only one expression at a time */ - ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count, - parser.buffer); - if (ret) - goto out_free; + ret = ftrace_set_func(fgd->table, fgd->count, fgd->size, + parser.buffer); + + mutex_unlock(&graph_lock); } - ret = read; + if (!ret) + ret = read; -out_free: trace_parser_put(&parser); -out_unlock: - mutex_unlock(&graph_lock); return ret; } @@ -3976,6 +4041,14 @@ static const struct file_operations ftrace_graph_fops = { .llseek = ftrace_filter_lseek, .release = ftrace_graph_release, }; + +static const struct file_operations ftrace_graph_notrace_fops = { + .open = ftrace_graph_notrace_open, + .read = seq_read, + .write = ftrace_graph_write, + .llseek = ftrace_filter_lseek, + .release = ftrace_graph_release, +}; #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) @@ -3997,6 +4070,9 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer) trace_create_file("set_graph_function", 0444, d_tracer, NULL, &ftrace_graph_fops); + trace_create_file("set_graph_notrace", 0444, d_tracer, + NULL, + &ftrace_graph_notrace_fops); #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ return 0; @@ -4290,12 +4366,15 @@ core_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; } static inline void ftrace_startup_enable(int command) { } /* Keep as macros so we do not need to define the commands */ -# define ftrace_startup(ops, command) \ - ({ \ - (ops)->flags |= FTRACE_OPS_FL_ENABLED; \ - 0; \ +# define ftrace_startup(ops, command) \ + ({ \ + int ___ret = __register_ftrace_function(ops); \ + if (!___ret) \ + (ops)->flags |= FTRACE_OPS_FL_ENABLED; \ + ___ret; \ }) -# define ftrace_shutdown(ops, command) do { } while (0) +# define ftrace_shutdown(ops, command) __unregister_ftrace_function(ops) + # define ftrace_startup_sysctl() do { } while (0) # define ftrace_shutdown_sysctl() do { } while (0) @@ -4320,12 +4399,21 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, */ preempt_disable_notrace(); trace_recursion_set(TRACE_CONTROL_BIT); + + /* + * Control funcs (perf) uses RCU. Only trace if + * RCU is currently active. + */ + if (!rcu_is_watching()) + goto out; + do_for_each_ftrace_op(op, ftrace_control_list) { if (!(op->flags & FTRACE_OPS_FL_STUB) && !ftrace_function_local_disabled(op) && ftrace_ops_test(op, ip, regs)) op->func(ip, parent_ip, op, regs); } while_for_each_ftrace_op(op); + out: trace_recursion_clear(TRACE_CONTROL_BIT); preempt_enable_notrace(); } @@ -4695,9 +4783,7 @@ int register_ftrace_function(struct ftrace_ops *ops) mutex_lock(&ftrace_lock); - ret = __register_ftrace_function(ops); - if (!ret) - ret = ftrace_startup(ops, 0); + ret = ftrace_startup(ops, 0); mutex_unlock(&ftrace_lock); @@ -4716,9 +4802,7 @@ int unregister_ftrace_function(struct ftrace_ops *ops) int ret; mutex_lock(&ftrace_lock); - ret = __unregister_ftrace_function(ops); - if (!ret) - ftrace_shutdown(ops, 0); + ret = ftrace_shutdown(ops, 0); mutex_unlock(&ftrace_lock); return ret; @@ -4912,6 +4996,13 @@ ftrace_suspend_notifier_call(struct notifier_block *bl, unsigned long state, return NOTIFY_DONE; } +/* Just a place holder for function graph */ +static struct ftrace_ops fgraph_ops __read_mostly = { + .func = ftrace_stub, + .flags = FTRACE_OPS_FL_STUB | FTRACE_OPS_FL_GLOBAL | + FTRACE_OPS_FL_RECURSION_SAFE, +}; + int register_ftrace_graph(trace_func_graph_ret_t retfunc, trace_func_graph_ent_t entryfunc) { @@ -4938,7 +5029,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc, ftrace_graph_return = retfunc; ftrace_graph_entry = entryfunc; - ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET); + ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET); out: mutex_unlock(&ftrace_lock); @@ -4955,7 +5046,7 @@ void unregister_ftrace_graph(void) ftrace_graph_active--; ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; ftrace_graph_entry = ftrace_graph_entry_stub; - ftrace_shutdown(&global_ops, FTRACE_STOP_FUNC_RET); + ftrace_shutdown(&fgraph_ops, FTRACE_STOP_FUNC_RET); unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d9fea7dfd5d..9d20cd9743e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -235,13 +235,33 @@ void trace_array_put(struct trace_array *this_tr) mutex_unlock(&trace_types_lock); } -int filter_current_check_discard(struct ring_buffer *buffer, - struct ftrace_event_call *call, void *rec, - struct ring_buffer_event *event) +int filter_check_discard(struct ftrace_event_file *file, void *rec, + struct ring_buffer *buffer, + struct ring_buffer_event *event) { - return filter_check_discard(call, rec, buffer, event); + if (unlikely(file->flags & FTRACE_EVENT_FL_FILTERED) && + !filter_match_preds(file->filter, rec)) { + ring_buffer_discard_commit(buffer, event); + return 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(filter_check_discard); + +int call_filter_check_discard(struct ftrace_event_call *call, void *rec, + struct ring_buffer *buffer, + struct ring_buffer_event *event) +{ + if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) && + !filter_match_preds(call->filter, rec)) { + ring_buffer_discard_commit(buffer, event); + return 1; + } + + return 0; } -EXPORT_SYMBOL_GPL(filter_current_check_discard); +EXPORT_SYMBOL_GPL(call_filter_check_discard); cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu) { @@ -843,9 +863,12 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, if (isspace(ch)) { parser->buffer[parser->idx] = 0; parser->cont = false; - } else { + } else if (parser->idx < parser->size - 1) { parser->cont = true; parser->buffer[parser->idx++] = ch; + } else { + ret = -EINVAL; + goto out; } *ppos += read; @@ -1261,21 +1284,6 @@ int is_tracing_stopped(void) } /** - * ftrace_off_permanent - disable all ftrace code permanently - * - * This should only be called when a serious anomally has - * been detected. This will turn off the function tracing, - * ring buffers, and other tracing utilites. It takes no - * locks and can be called from any context. - */ -void ftrace_off_permanent(void) -{ - tracing_disabled = 1; - ftrace_stop(); - tracing_off_permanent(); -} - -/** * tracing_start - quick start of the tracer * * If tracing is enabled but was stopped by tracing_stop, @@ -1631,7 +1639,7 @@ trace_function(struct trace_array *tr, entry->ip = ip; entry->parent_ip = parent_ip; - if (!filter_check_discard(call, entry, buffer, event)) + if (!call_filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); } @@ -1715,7 +1723,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, entry->size = trace.nr_entries; - if (!filter_check_discard(call, entry, buffer, event)) + if (!call_filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); out: @@ -1817,7 +1825,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) trace.entries = entry->caller; save_stack_trace_user(&trace); - if (!filter_check_discard(call, entry, buffer, event)) + if (!call_filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); out_drop_count: @@ -2009,7 +2017,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) entry->fmt = fmt; memcpy(entry->buf, tbuffer, sizeof(u32) * len); - if (!filter_check_discard(call, entry, buffer, event)) { + if (!call_filter_check_discard(call, entry, buffer, event)) { __buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); } @@ -2064,7 +2072,7 @@ __trace_array_vprintk(struct ring_buffer *buffer, memcpy(&entry->buf, tbuffer, len); entry->buf[len] = '\0'; - if (!filter_check_discard(call, entry, buffer, event)) { + if (!call_filter_check_discard(call, entry, buffer, event)) { __buffer_unlock_commit(buffer, event); ftrace_trace_stack(buffer, flags, 6, pc); } @@ -2761,7 +2769,7 @@ static void show_snapshot_main_help(struct seq_file *m) seq_printf(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n"); seq_printf(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n"); seq_printf(m, "# Takes a snapshot of the main buffer.\n"); - seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate)\n"); + seq_printf(m, "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate or free)\n"); seq_printf(m, "# (Doesn't have to be '2' works with any number that\n"); seq_printf(m, "# is not a '0' or '1')\n"); } @@ -2965,6 +2973,11 @@ int tracing_open_generic(struct inode *inode, struct file *filp) return 0; } +bool tracing_is_disabled(void) +{ + return (tracing_disabled) ? true: false; +} + /* * Open and update trace_array ref count. * Must have the current trace_array passed to it. @@ -5455,12 +5468,12 @@ static struct ftrace_func_command ftrace_snapshot_cmd = { .func = ftrace_trace_snapshot_callback, }; -static int register_snapshot_cmd(void) +static __init int register_snapshot_cmd(void) { return register_ftrace_command(&ftrace_snapshot_cmd); } #else -static inline int register_snapshot_cmd(void) { return 0; } +static inline __init int register_snapshot_cmd(void) { return 0; } #endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */ struct dentry *tracing_init_dentry_tr(struct trace_array *tr) @@ -6254,6 +6267,17 @@ void trace_init_global_iter(struct trace_iterator *iter) iter->trace = iter->tr->current_trace; iter->cpu_file = RING_BUFFER_ALL_CPUS; iter->trace_buffer = &global_trace.trace_buffer; + + if (iter->trace && iter->trace->open) + iter->trace->open(iter); + + /* Annotate start of buffers if we had overruns */ + if (ring_buffer_overruns(iter->trace_buffer->buffer)) + iter->iter_flags |= TRACE_FILE_ANNOTATE; + + /* Output in nanoseconds only if we are using a clock in nanoseconds. */ + if (trace_clocks[iter->tr->clock_id].in_ns) + iter->iter_flags |= TRACE_FILE_TIME_IN_NS; } void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 73d08aa25b5..ea189e027b8 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -193,8 +193,8 @@ struct trace_array { #ifdef CONFIG_FTRACE_SYSCALLS int sys_refcount_enter; int sys_refcount_exit; - DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls); - DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls); + struct ftrace_event_file __rcu *enter_syscall_files[NR_syscalls]; + struct ftrace_event_file __rcu *exit_syscall_files[NR_syscalls]; #endif int stop_count; int clock_id; @@ -515,6 +515,7 @@ void tracing_reset_online_cpus(struct trace_buffer *buf); void tracing_reset_current(int cpu); void tracing_reset_all_online_cpus(void); int tracing_open_generic(struct inode *inode, struct file *filp); +bool tracing_is_disabled(void); struct dentry *trace_create_file(const char *name, umode_t mode, struct dentry *parent, @@ -712,6 +713,8 @@ extern unsigned long trace_flags; #define TRACE_GRAPH_PRINT_PROC 0x8 #define TRACE_GRAPH_PRINT_DURATION 0x10 #define TRACE_GRAPH_PRINT_ABS_TIME 0x20 +#define TRACE_GRAPH_PRINT_FILL_SHIFT 28 +#define TRACE_GRAPH_PRINT_FILL_MASK (0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT) extern enum print_line_t print_graph_function_flags(struct trace_iterator *iter, u32 flags); @@ -731,15 +734,16 @@ extern void __trace_graph_return(struct trace_array *tr, #ifdef CONFIG_DYNAMIC_FTRACE /* TODO: make this variable */ #define FTRACE_GRAPH_MAX_FUNCS 32 -extern int ftrace_graph_filter_enabled; extern int ftrace_graph_count; extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS]; +extern int ftrace_graph_notrace_count; +extern unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS]; static inline int ftrace_graph_addr(unsigned long addr) { int i; - if (!ftrace_graph_filter_enabled) + if (!ftrace_graph_count) return 1; for (i = 0; i < ftrace_graph_count; i++) { @@ -759,11 +763,31 @@ static inline int ftrace_graph_addr(unsigned long addr) return 0; } + +static inline int ftrace_graph_notrace_addr(unsigned long addr) +{ + int i; + + if (!ftrace_graph_notrace_count) + return 0; + + for (i = 0; i < ftrace_graph_notrace_count; i++) { + if (addr == ftrace_graph_notrace_funcs[i]) + return 1; + } + + return 0; +} #else static inline int ftrace_graph_addr(unsigned long addr) { return 1; } + +static inline int ftrace_graph_notrace_addr(unsigned long addr) +{ + return 0; +} #endif /* CONFIG_DYNAMIC_FTRACE */ #else /* CONFIG_FUNCTION_GRAPH_TRACER */ static inline enum print_line_t @@ -987,9 +1011,9 @@ struct filter_pred { extern enum regex_type filter_parse_regex(char *buff, int len, char **search, int *not); -extern void print_event_filter(struct ftrace_event_call *call, +extern void print_event_filter(struct ftrace_event_file *file, struct trace_seq *s); -extern int apply_event_filter(struct ftrace_event_call *call, +extern int apply_event_filter(struct ftrace_event_file *file, char *filter_string); extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir, char *filter_string); @@ -1000,20 +1024,6 @@ extern int filter_assign_type(const char *type); struct ftrace_event_field * trace_find_event_field(struct ftrace_event_call *call, char *name); -static inline int -filter_check_discard(struct ftrace_event_call *call, void *rec, - struct ring_buffer *buffer, - struct ring_buffer_event *event) -{ - if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) && - !filter_match_preds(call->filter, rec)) { - ring_buffer_discard_commit(buffer, event); - return 1; - } - - return 0; -} - extern void trace_event_enable_cmd_record(bool enable); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index d594da0dc03..697fb9bac8f 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -78,7 +78,7 @@ probe_likely_condition(struct ftrace_branch_data *f, int val, int expect) entry->line = f->line; entry->correct = val == expect; - if (!filter_check_discard(call, entry, buffer, event)) + if (!call_filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); out: diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 78e27e3b52a..e854f420e03 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -24,6 +24,12 @@ static int total_ref_count; static int perf_trace_event_perm(struct ftrace_event_call *tp_event, struct perf_event *p_event) { + if (tp_event->perf_perm) { + int ret = tp_event->perf_perm(tp_event, p_event); + if (ret) + return ret; + } + /* The ftrace function trace is allowed only for root. */ if (ftrace_event_is_function(tp_event) && perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) @@ -173,7 +179,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event, int perf_trace_init(struct perf_event *p_event) { struct ftrace_event_call *tp_event; - int event_id = p_event->attr.config; + u64 event_id = p_event->attr.config; int ret = -EINVAL; mutex_lock(&event_mutex); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 368a4d50cc3..f919a2e21bf 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -989,7 +989,7 @@ static ssize_t event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call; + struct ftrace_event_file *file; struct trace_seq *s; int r = -ENODEV; @@ -1004,12 +1004,12 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt, trace_seq_init(s); mutex_lock(&event_mutex); - call = event_file_data(filp); - if (call) - print_event_filter(call, s); + file = event_file_data(filp); + if (file) + print_event_filter(file, s); mutex_unlock(&event_mutex); - if (call) + if (file) r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len); kfree(s); @@ -1021,7 +1021,7 @@ static ssize_t event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { - struct ftrace_event_call *call; + struct ftrace_event_file *file; char *buf; int err = -ENODEV; @@ -1039,9 +1039,9 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt, buf[cnt] = '\0'; mutex_lock(&event_mutex); - call = event_file_data(filp); - if (call) - err = apply_event_filter(call, buf); + file = event_file_data(filp); + if (file) + err = apply_event_filter(file, buf); mutex_unlock(&event_mutex); free_page((unsigned long) buf); @@ -1062,6 +1062,9 @@ static int subsystem_open(struct inode *inode, struct file *filp) struct trace_array *tr; int ret; + if (tracing_is_disabled()) + return -ENODEV; + /* Make sure the system still exists */ mutex_lock(&trace_types_lock); mutex_lock(&event_mutex); @@ -1108,6 +1111,9 @@ static int system_tr_open(struct inode *inode, struct file *filp) struct trace_array *tr = inode->i_private; int ret; + if (tracing_is_disabled()) + return -ENODEV; + if (trace_array_get(tr) < 0) return -ENODEV; @@ -1124,11 +1130,12 @@ static int system_tr_open(struct inode *inode, struct file *filp) if (ret < 0) { trace_array_put(tr); kfree(dir); + return ret; } filp->private_data = dir; - return ret; + return 0; } static int subsystem_release(struct inode *inode, struct file *file) @@ -1539,7 +1546,7 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file) return -1; } } - trace_create_file("filter", 0644, file->dir, call, + trace_create_file("filter", 0644, file->dir, file, &ftrace_event_filter_fops); trace_create_file("format", 0444, file->dir, call, @@ -1577,6 +1584,7 @@ static void event_remove(struct ftrace_event_call *call) if (file->event_call != call) continue; ftrace_event_enable_disable(file, 0); + destroy_preds(file); /* * The do_for_each_event_file() is * a double loop. After finding the call for this @@ -1700,7 +1708,7 @@ static void __trace_remove_event_call(struct ftrace_event_call *call) { event_remove(call); trace_destroy_fields(call); - destroy_preds(call); + destroy_call_preds(call); } static int probe_remove_event_call(struct ftrace_event_call *call) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 97daa8cf958..2468f56dc5d 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -637,10 +637,18 @@ static void append_filter_err(struct filter_parse_state *ps, free_page((unsigned long) buf); } +static inline struct event_filter *event_filter(struct ftrace_event_file *file) +{ + if (file->event_call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + return file->event_call->filter; + else + return file->filter; +} + /* caller must hold event_mutex */ -void print_event_filter(struct ftrace_event_call *call, struct trace_seq *s) +void print_event_filter(struct ftrace_event_file *file, struct trace_seq *s) { - struct event_filter *filter = call->filter; + struct event_filter *filter = event_filter(file); if (filter && filter->filter_string) trace_seq_printf(s, "%s\n", filter->filter_string); @@ -766,11 +774,21 @@ static void __free_preds(struct event_filter *filter) filter->n_preds = 0; } -static void filter_disable(struct ftrace_event_call *call) +static void call_filter_disable(struct ftrace_event_call *call) { call->flags &= ~TRACE_EVENT_FL_FILTERED; } +static void filter_disable(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + call_filter_disable(call); + else + file->flags &= ~FTRACE_EVENT_FL_FILTERED; +} + static void __free_filter(struct event_filter *filter) { if (!filter) @@ -781,16 +799,30 @@ static void __free_filter(struct event_filter *filter) kfree(filter); } +void destroy_call_preds(struct ftrace_event_call *call) +{ + __free_filter(call->filter); + call->filter = NULL; +} + +static void destroy_file_preds(struct ftrace_event_file *file) +{ + __free_filter(file->filter); + file->filter = NULL; +} + /* - * Called when destroying the ftrace_event_call. - * The call is being freed, so we do not need to worry about - * the call being currently used. This is for module code removing + * Called when destroying the ftrace_event_file. + * The file is being freed, so we do not need to worry about + * the file being currently used. This is for module code removing * the tracepoints from within it. */ -void destroy_preds(struct ftrace_event_call *call) +void destroy_preds(struct ftrace_event_file *file) { - __free_filter(call->filter); - call->filter = NULL; + if (file->event_call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + destroy_call_preds(file->event_call); + else + destroy_file_preds(file); } static struct event_filter *__alloc_filter(void) @@ -825,28 +857,56 @@ static int __alloc_preds(struct event_filter *filter, int n_preds) return 0; } -static void filter_free_subsystem_preds(struct event_subsystem *system) +static inline void __remove_filter(struct ftrace_event_file *file) { + struct ftrace_event_call *call = file->event_call; + + filter_disable(file); + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + remove_filter_string(call->filter); + else + remove_filter_string(file->filter); +} + +static void filter_free_subsystem_preds(struct event_subsystem *system, + struct trace_array *tr) +{ + struct ftrace_event_file *file; struct ftrace_event_call *call; - list_for_each_entry(call, &ftrace_events, list) { + list_for_each_entry(file, &tr->events, list) { + call = file->event_call; if (strcmp(call->class->system, system->name) != 0) continue; - filter_disable(call); - remove_filter_string(call->filter); + __remove_filter(file); } } -static void filter_free_subsystem_filters(struct event_subsystem *system) +static inline void __free_subsystem_filter(struct ftrace_event_file *file) { + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) { + __free_filter(call->filter); + call->filter = NULL; + } else { + __free_filter(file->filter); + file->filter = NULL; + } +} + +static void filter_free_subsystem_filters(struct event_subsystem *system, + struct trace_array *tr) +{ + struct ftrace_event_file *file; struct ftrace_event_call *call; - list_for_each_entry(call, &ftrace_events, list) { + list_for_each_entry(file, &tr->events, list) { + call = file->event_call; if (strcmp(call->class->system, system->name) != 0) continue; - __free_filter(call->filter); - call->filter = NULL; + __free_subsystem_filter(file); } } @@ -1617,15 +1677,85 @@ fail: return err; } +static inline void event_set_filtered_flag(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + call->flags |= TRACE_EVENT_FL_FILTERED; + else + file->flags |= FTRACE_EVENT_FL_FILTERED; +} + +static inline void event_set_filter(struct ftrace_event_file *file, + struct event_filter *filter) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + rcu_assign_pointer(call->filter, filter); + else + rcu_assign_pointer(file->filter, filter); +} + +static inline void event_clear_filter(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + RCU_INIT_POINTER(call->filter, NULL); + else + RCU_INIT_POINTER(file->filter, NULL); +} + +static inline void +event_set_no_set_filter_flag(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + call->flags |= TRACE_EVENT_FL_NO_SET_FILTER; + else + file->flags |= FTRACE_EVENT_FL_NO_SET_FILTER; +} + +static inline void +event_clear_no_set_filter_flag(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) + call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER; + else + file->flags &= ~FTRACE_EVENT_FL_NO_SET_FILTER; +} + +static inline bool +event_no_set_filter_flag(struct ftrace_event_file *file) +{ + struct ftrace_event_call *call = file->event_call; + + if (file->flags & FTRACE_EVENT_FL_NO_SET_FILTER) + return true; + + if ((call->flags & TRACE_EVENT_FL_USE_CALL_FILTER) && + (call->flags & TRACE_EVENT_FL_NO_SET_FILTER)) + return true; + + return false; +} + struct filter_list { struct list_head list; struct event_filter *filter; }; static int replace_system_preds(struct event_subsystem *system, + struct trace_array *tr, struct filter_parse_state *ps, char *filter_string) { + struct ftrace_event_file *file; struct ftrace_event_call *call; struct filter_list *filter_item; struct filter_list *tmp; @@ -1633,8 +1763,8 @@ static int replace_system_preds(struct event_subsystem *system, bool fail = true; int err; - list_for_each_entry(call, &ftrace_events, list) { - + list_for_each_entry(file, &tr->events, list) { + call = file->event_call; if (strcmp(call->class->system, system->name) != 0) continue; @@ -1644,18 +1774,20 @@ static int replace_system_preds(struct event_subsystem *system, */ err = replace_preds(call, NULL, ps, filter_string, true); if (err) - call->flags |= TRACE_EVENT_FL_NO_SET_FILTER; + event_set_no_set_filter_flag(file); else - call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER; + event_clear_no_set_filter_flag(file); } - list_for_each_entry(call, &ftrace_events, list) { + list_for_each_entry(file, &tr->events, list) { struct event_filter *filter; + call = file->event_call; + if (strcmp(call->class->system, system->name) != 0) continue; - if (call->flags & TRACE_EVENT_FL_NO_SET_FILTER) + if (event_no_set_filter_flag(file)) continue; filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL); @@ -1676,17 +1808,17 @@ static int replace_system_preds(struct event_subsystem *system, err = replace_preds(call, filter, ps, filter_string, false); if (err) { - filter_disable(call); + filter_disable(file); parse_error(ps, FILT_ERR_BAD_SUBSYS_FILTER, 0); append_filter_err(ps, filter); } else - call->flags |= TRACE_EVENT_FL_FILTERED; + event_set_filtered_flag(file); /* * Regardless of if this returned an error, we still * replace the filter for the call. */ - filter = call->filter; - rcu_assign_pointer(call->filter, filter_item->filter); + filter = event_filter(file); + event_set_filter(file, filter_item->filter); filter_item->filter = filter; fail = false; @@ -1816,6 +1948,7 @@ static int create_filter(struct ftrace_event_call *call, * and always remembers @filter_str. */ static int create_system_filter(struct event_subsystem *system, + struct trace_array *tr, char *filter_str, struct event_filter **filterp) { struct event_filter *filter = NULL; @@ -1824,7 +1957,7 @@ static int create_system_filter(struct event_subsystem *system, err = create_filter_start(filter_str, true, &ps, &filter); if (!err) { - err = replace_system_preds(system, ps, filter_str); + err = replace_system_preds(system, tr, ps, filter_str); if (!err) { /* System filters just show a default message */ kfree(filter->filter_string); @@ -1840,20 +1973,25 @@ static int create_system_filter(struct event_subsystem *system, } /* caller must hold event_mutex */ -int apply_event_filter(struct ftrace_event_call *call, char *filter_string) +int apply_event_filter(struct ftrace_event_file *file, char *filter_string) { + struct ftrace_event_call *call = file->event_call; struct event_filter *filter; int err; if (!strcmp(strstrip(filter_string), "0")) { - filter_disable(call); - filter = call->filter; + filter_disable(file); + filter = event_filter(file); + if (!filter) return 0; - RCU_INIT_POINTER(call->filter, NULL); + + event_clear_filter(file); + /* Make sure the filter is not being used */ synchronize_sched(); __free_filter(filter); + return 0; } @@ -1866,14 +2004,15 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string) * string */ if (filter) { - struct event_filter *tmp = call->filter; + struct event_filter *tmp; + tmp = event_filter(file); if (!err) - call->flags |= TRACE_EVENT_FL_FILTERED; + event_set_filtered_flag(file); else - filter_disable(call); + filter_disable(file); - rcu_assign_pointer(call->filter, filter); + event_set_filter(file, filter); if (tmp) { /* Make sure the call is done with the filter */ @@ -1889,6 +2028,7 @@ int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir, char *filter_string) { struct event_subsystem *system = dir->subsystem; + struct trace_array *tr = dir->tr; struct event_filter *filter; int err = 0; @@ -1901,18 +2041,18 @@ int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir, } if (!strcmp(strstrip(filter_string), "0")) { - filter_free_subsystem_preds(system); + filter_free_subsystem_preds(system, tr); remove_filter_string(system->filter); filter = system->filter; system->filter = NULL; /* Ensure all filters are no longer used */ synchronize_sched(); - filter_free_subsystem_filters(system); + filter_free_subsystem_filters(system, tr); __free_filter(filter); goto out_unlock; } - err = create_system_filter(system, filter_string, &filter); + err = create_system_filter(system, tr, filter_string, &filter); if (filter) { /* * No event actually uses the system filter diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index d21a7467008..7c3e3e72e2b 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -180,7 +180,7 @@ struct ftrace_event_call __used event_##call = { \ .event.type = etype, \ .class = &event_class_ftrace_##call, \ .print_fmt = print, \ - .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \ + .flags = TRACE_EVENT_FL_IGNORE_ENABLE | TRACE_EVENT_FL_USE_CALL_FILTER, \ }; \ struct ftrace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index b5c09242683..0b99120d395 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -82,9 +82,9 @@ static struct trace_array *graph_array; * to fill in space into DURATION column. */ enum { - DURATION_FILL_FULL = -1, - DURATION_FILL_START = -2, - DURATION_FILL_END = -3, + FLAGS_FILL_FULL = 1 << TRACE_GRAPH_PRINT_FILL_SHIFT, + FLAGS_FILL_START = 2 << TRACE_GRAPH_PRINT_FILL_SHIFT, + FLAGS_FILL_END = 3 << TRACE_GRAPH_PRINT_FILL_SHIFT, }; static enum print_line_t @@ -114,16 +114,37 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, return -EBUSY; } + /* + * The curr_ret_stack is an index to ftrace return stack of + * current task. Its value should be in [0, FTRACE_RETFUNC_ + * DEPTH) when the function graph tracer is used. To support + * filtering out specific functions, it makes the index + * negative by subtracting huge value (FTRACE_NOTRACE_DEPTH) + * so when it sees a negative index the ftrace will ignore + * the record. And the index gets recovered when returning + * from the filtered function by adding the FTRACE_NOTRACE_ + * DEPTH and then it'll continue to record functions normally. + * + * The curr_ret_stack is initialized to -1 and get increased + * in this function. So it can be less than -1 only if it was + * filtered out via ftrace_graph_notrace_addr() which can be + * set from set_graph_notrace file in debugfs by user. + */ + if (current->curr_ret_stack < -1) + return -EBUSY; + calltime = trace_clock_local(); index = ++current->curr_ret_stack; + if (ftrace_graph_notrace_addr(func)) + current->curr_ret_stack -= FTRACE_NOTRACE_DEPTH; barrier(); current->ret_stack[index].ret = ret; current->ret_stack[index].func = func; current->ret_stack[index].calltime = calltime; current->ret_stack[index].subtime = 0; current->ret_stack[index].fp = frame_pointer; - *depth = index; + *depth = current->curr_ret_stack; return 0; } @@ -137,7 +158,17 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, index = current->curr_ret_stack; - if (unlikely(index < 0)) { + /* + * A negative index here means that it's just returned from a + * notrace'd function. Recover index to get an original + * return address. See ftrace_push_return_trace(). + * + * TODO: Need to check whether the stack gets corrupted. + */ + if (index < 0) + index += FTRACE_NOTRACE_DEPTH; + + if (unlikely(index < 0 || index >= FTRACE_RETFUNC_DEPTH)) { ftrace_graph_stop(); WARN_ON(1); /* Might as well panic, otherwise we have no where to go */ @@ -193,6 +224,15 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) trace.rettime = trace_clock_local(); barrier(); current->curr_ret_stack--; + /* + * The curr_ret_stack can be less than -1 only if it was + * filtered out and it's about to return from the function. + * Recover the index and continue to trace normal functions. + */ + if (current->curr_ret_stack < -1) { + current->curr_ret_stack += FTRACE_NOTRACE_DEPTH; + return ret; + } /* * The trace should run after decrementing the ret counter @@ -230,7 +270,7 @@ int __trace_graph_entry(struct trace_array *tr, return 0; entry = ring_buffer_event_data(event); entry->graph_ent = *trace; - if (!filter_current_check_discard(buffer, call, entry, event)) + if (!call_filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); return 1; @@ -259,10 +299,20 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) /* trace it when it is-nested-in or is a function enabled. */ if ((!(trace->depth || ftrace_graph_addr(trace->func)) || - ftrace_graph_ignore_irqs()) || + ftrace_graph_ignore_irqs()) || (trace->depth < 0) || (max_depth && trace->depth >= max_depth)) return 0; + /* + * Do not trace a function if it's filtered by set_graph_notrace. + * Make the index of ret stack negative to indicate that it should + * ignore further functions. But it needs its own ret stack entry + * to recover the original index in order to continue tracing after + * returning from the function. + */ + if (ftrace_graph_notrace_addr(trace->func)) + return 1; + local_irq_save(flags); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->trace_buffer.data, cpu); @@ -335,7 +385,7 @@ void __trace_graph_return(struct trace_array *tr, return; entry = ring_buffer_event_data(event); entry->ret = *trace; - if (!filter_current_check_discard(buffer, call, entry, event)) + if (!call_filter_check_discard(call, entry, buffer, event)) __buffer_unlock_commit(buffer, event); } @@ -652,7 +702,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr, } /* No overhead */ - ret = print_graph_duration(DURATION_FILL_START, s, flags); + ret = print_graph_duration(0, s, flags | FLAGS_FILL_START); if (ret != TRACE_TYPE_HANDLED) return ret; @@ -664,7 +714,7 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr, if (!ret) return TRACE_TYPE_PARTIAL_LINE; - ret = print_graph_duration(DURATION_FILL_END, s, flags); + ret = print_graph_duration(0, s, flags | FLAGS_FILL_END); if (ret != TRACE_TYPE_HANDLED) return ret; @@ -729,14 +779,14 @@ print_graph_duration(unsigned long long duration, struct trace_seq *s, return TRACE_TYPE_HANDLED; /* No real adata, just filling the column with spaces */ - switch (duration) { - case DURATION_FILL_FULL: + switch (flags & TRACE_GRAPH_PRINT_FILL_MASK) { + case FLAGS_FILL_FULL: ret = trace_seq_puts(s, " | "); return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; - case DURATION_FILL_START: + case FLAGS_FILL_START: ret = trace_seq_puts(s, " "); return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; - case DURATION_FILL_END: + case FLAGS_FILL_END: ret = trace_seq_puts(s, " |"); return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE; } @@ -852,7 +902,7 @@ print_graph_entry_nested(struct trace_iterator *iter, } /* No time */ - ret = print_graph_duration(DURATION_FILL_FULL, s, flags); + ret = print_graph_duration(0, s, flags | FLAGS_FILL_FULL); if (ret != TRACE_TYPE_HANDLED) return ret; @@ -1172,7 +1222,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent, return TRACE_TYPE_PARTIAL_LINE; /* No time */ - ret = print_graph_duration(DURATION_FILL_FULL, s, flags); + ret = print_graph_duration(0, s, flags | FLAGS_FILL_FULL); if (ret != TRACE_TYPE_HANDLED) return ret; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 243f6834d02..dae9541ada9 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -835,7 +835,7 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs, entry->ip = (unsigned long)tp->rp.kp.addr; store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); - if (!filter_current_check_discard(buffer, call, entry, event)) + if (!filter_check_discard(ftrace_file, entry, buffer, event)) trace_buffer_unlock_commit_regs(buffer, event, irq_flags, pc, regs); } @@ -884,7 +884,7 @@ __kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri, entry->ret_ip = (unsigned long)ri->ret_addr; store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize); - if (!filter_current_check_discard(buffer, call, entry, event)) + if (!filter_check_discard(ftrace_file, entry, buffer, event)) trace_buffer_unlock_commit_regs(buffer, event, irq_flags, pc, regs); } diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index b3dcfb2f0fe..0abd9b86347 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -323,7 +323,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->rw = *rw; - if (!filter_check_discard(call, entry, buffer, event)) + if (!call_filter_check_discard(call, entry, buffer, event)) trace_buffer_unlock_commit(buffer, event, 0, pc); } @@ -353,7 +353,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->map = *map; - if (!filter_check_discard(call, entry, buffer, event)) + if (!call_filter_check_discard(call, entry, buffer, event)) trace_buffer_unlock_commit(buffer, event, 0, pc); } diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 4e98e3b257a..3f34dc9b40f 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -45,7 +45,7 @@ tracing_sched_switch_trace(struct trace_array *tr, entry->next_state = next->state; entry->next_cpu = task_cpu(next); - if (!filter_check_discard(call, entry, buffer, event)) + if (!call_filter_check_discard(call, entry, buffer, event)) trace_buffer_unlock_commit(buffer, event, flags, pc); } @@ -101,7 +101,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry->next_state = wakee->state; entry->next_cpu = task_cpu(wakee); - if (!filter_check_discard(call, entry, buffer, event)) + if (!call_filter_check_discard(call, entry, buffer, event)) trace_buffer_unlock_commit(buffer, event, flags, pc); } diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 847f88a6194..7af67360b33 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -43,46 +43,15 @@ static DEFINE_MUTEX(all_stat_sessions_mutex); /* The root directory for all stat files */ static struct dentry *stat_dir; -/* - * Iterate through the rbtree using a post order traversal path - * to release the next node. - * It won't necessary release one at each iteration - * but it will at least advance closer to the next one - * to be released. - */ -static struct rb_node *release_next(struct tracer_stat *ts, - struct rb_node *node) +static void __reset_stat_session(struct stat_session *session) { - struct stat_node *snode; - struct rb_node *parent = rb_parent(node); - - if (node->rb_left) - return node->rb_left; - else if (node->rb_right) - return node->rb_right; - else { - if (!parent) - ; - else if (parent->rb_left == node) - parent->rb_left = NULL; - else - parent->rb_right = NULL; + struct stat_node *snode, *n; - snode = container_of(node, struct stat_node, node); - if (ts->stat_release) - ts->stat_release(snode->stat); + rbtree_postorder_for_each_entry_safe(snode, n, &session->stat_root, node) { + if (session->ts->stat_release) + session->ts->stat_release(snode->stat); kfree(snode); - - return parent; } -} - -static void __reset_stat_session(struct stat_session *session) -{ - struct rb_node *node = session->stat_root.rb_node; - - while (node) - node = release_next(session->ts, node); session->stat_root = RB_ROOT; } diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 559329d9bd2..e4b6d11bdf7 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -302,6 +302,7 @@ static int __init syscall_exit_define_fields(struct ftrace_event_call *call) static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) { struct trace_array *tr = data; + struct ftrace_event_file *ftrace_file; struct syscall_trace_enter *entry; struct syscall_metadata *sys_data; struct ring_buffer_event *event; @@ -314,7 +315,13 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) syscall_nr = trace_get_syscall_nr(current, regs); if (syscall_nr < 0) return; - if (!test_bit(syscall_nr, tr->enabled_enter_syscalls)) + + /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */ + ftrace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]); + if (!ftrace_file) + return; + + if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags)) return; sys_data = syscall_nr_to_meta(syscall_nr); @@ -336,8 +343,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) entry->nr = syscall_nr; syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args); - if (!filter_current_check_discard(buffer, sys_data->enter_event, - entry, event)) + if (!filter_check_discard(ftrace_file, entry, buffer, event)) trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc); } @@ -345,6 +351,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) { struct trace_array *tr = data; + struct ftrace_event_file *ftrace_file; struct syscall_trace_exit *entry; struct syscall_metadata *sys_data; struct ring_buffer_event *event; @@ -356,7 +363,13 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) syscall_nr = trace_get_syscall_nr(current, regs); if (syscall_nr < 0) return; - if (!test_bit(syscall_nr, tr->enabled_exit_syscalls)) + + /* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */ + ftrace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]); + if (!ftrace_file) + return; + + if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags)) return; sys_data = syscall_nr_to_meta(syscall_nr); @@ -377,8 +390,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) entry->nr = syscall_nr; entry->ret = syscall_get_return_value(current, regs); - if (!filter_current_check_discard(buffer, sys_data->exit_event, - entry, event)) + if (!filter_check_discard(ftrace_file, entry, buffer, event)) trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc); } @@ -397,7 +409,7 @@ static int reg_event_syscall_enter(struct ftrace_event_file *file, if (!tr->sys_refcount_enter) ret = register_trace_sys_enter(ftrace_syscall_enter, tr); if (!ret) { - set_bit(num, tr->enabled_enter_syscalls); + rcu_assign_pointer(tr->enter_syscall_files[num], file); tr->sys_refcount_enter++; } mutex_unlock(&syscall_trace_lock); @@ -415,10 +427,15 @@ static void unreg_event_syscall_enter(struct ftrace_event_file *file, return; mutex_lock(&syscall_trace_lock); tr->sys_refcount_enter--; - clear_bit(num, tr->enabled_enter_syscalls); + rcu_assign_pointer(tr->enter_syscall_files[num], NULL); if (!tr->sys_refcount_enter) unregister_trace_sys_enter(ftrace_syscall_enter, tr); mutex_unlock(&syscall_trace_lock); + /* + * Callers expect the event to be completely disabled on + * return, so wait for current handlers to finish. + */ + synchronize_sched(); } static int reg_event_syscall_exit(struct ftrace_event_file *file, @@ -435,7 +452,7 @@ static int reg_event_syscall_exit(struct ftrace_event_file *file, if (!tr->sys_refcount_exit) ret = register_trace_sys_exit(ftrace_syscall_exit, tr); if (!ret) { - set_bit(num, tr->enabled_exit_syscalls); + rcu_assign_pointer(tr->exit_syscall_files[num], file); tr->sys_refcount_exit++; } mutex_unlock(&syscall_trace_lock); @@ -453,10 +470,15 @@ static void unreg_event_syscall_exit(struct ftrace_event_file *file, return; mutex_lock(&syscall_trace_lock); tr->sys_refcount_exit--; - clear_bit(num, tr->enabled_exit_syscalls); + rcu_assign_pointer(tr->exit_syscall_files[num], NULL); if (!tr->sys_refcount_exit) unregister_trace_sys_exit(ftrace_syscall_exit, tr); mutex_unlock(&syscall_trace_lock); + /* + * Callers expect the event to be completely disabled on + * return, so wait for current handlers to finish. + */ + synchronize_sched(); } static int __init init_syscall_trace(struct ftrace_event_call *call) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 272261b5f94..b6dcc42ef7f 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -128,6 +128,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; init_trace_uprobe_filter(&tu->filter); + tu->call.flags |= TRACE_EVENT_FL_USE_CALL_FILTER; return tu; error: @@ -561,7 +562,7 @@ static void uprobe_trace_print(struct trace_uprobe *tu, for (i = 0; i < tu->nr_args; i++) call_fetch(&tu->args[i].fetch, regs, data + tu->args[i].offset); - if (!filter_current_check_discard(buffer, call, entry, event)) + if (!call_filter_check_discard(call, entry, buffer, event)) trace_buffer_unlock_commit(buffer, event, 0, 0); } diff --git a/kernel/up.c b/kernel/up.c index 630d72bf7e4..509403e3fbc 100644 --- a/kernel/up.c +++ b/kernel/up.c @@ -22,6 +22,17 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, } EXPORT_SYMBOL(smp_call_function_single); +void __smp_call_function_single(int cpu, struct call_single_data *csd, + int wait) +{ + unsigned long flags; + + local_irq_save(flags); + csd->func(csd->info); + local_irq_restore(flags); +} +EXPORT_SYMBOL(__smp_call_function_single); + int on_each_cpu(smp_call_func_t func, void *info, int wait) { unsigned long flags; diff --git a/kernel/user.c b/kernel/user.c index 5bbb91988e6..a3a0dbfda32 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -51,6 +51,10 @@ struct user_namespace init_user_ns = { .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .proc_inum = PROC_USER_INIT_INO, +#ifdef CONFIG_KEYS_KERBEROS_CACHE + .krb_cache_register_sem = + __RWSEM_INITIALIZER(init_user_ns.krb_cache_register_sem), +#endif }; EXPORT_SYMBOL_GPL(init_user_ns); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 13fb1134ba5..240fb62cf39 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -101,6 +101,9 @@ int create_user_ns(struct cred *new) set_cred_user_ns(new, ns); +#ifdef CONFIG_PERSISTENT_KEYRINGS + init_rwsem(&ns->persistent_keyring_register_sem); +#endif return 0; } @@ -130,6 +133,9 @@ void free_user_ns(struct user_namespace *ns) do { parent = ns->parent; +#ifdef CONFIG_PERSISTENT_KEYRINGS + key_put(ns->persistent_keyring_register); +#endif proc_free_inum(ns->proc_inum); kmem_cache_free(user_ns_cachep, ns); ns = parent; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 987293d03eb..c66912be990 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -305,6 +305,9 @@ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); /* I: attributes used when instantiating standard unbound pools on demand */ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; +/* I: attributes used when instantiating ordered pools on demand */ +static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; + struct workqueue_struct *system_wq __read_mostly; EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_highpri_wq __read_mostly; @@ -518,14 +521,21 @@ static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif -/* allocate ID and assign it to @pool */ +/** + * worker_pool_assign_id - allocate ID and assing it to @pool + * @pool: the pool pointer of interest + * + * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned + * successfully, -errno on failure. + */ static int worker_pool_assign_id(struct worker_pool *pool) { int ret; lockdep_assert_held(&wq_pool_mutex); - ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL); + ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, + GFP_KERNEL); if (ret >= 0) { pool->id = ret; return 0; @@ -1320,7 +1330,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, debug_work_activate(work); - /* if dying, only works from the same workqueue are allowed */ + /* if draining, only works from the same workqueue are allowed */ if (unlikely(wq->flags & __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq))) return; @@ -1736,16 +1746,17 @@ static struct worker *create_worker(struct worker_pool *pool) if (IS_ERR(worker->task)) goto fail; + set_user_nice(worker->task, pool->attrs->nice); + + /* prevent userland from meddling with cpumask of workqueue workers */ + worker->task->flags |= PF_NO_SETAFFINITY; + /* * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any * online CPUs. It'll be re-applied when any of the CPUs come up. */ - set_user_nice(worker->task, pool->attrs->nice); set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask); - /* prevent userland from meddling with cpumask of workqueue workers */ - worker->task->flags |= PF_NO_SETAFFINITY; - /* * The caller is responsible for ensuring %POOL_DISASSOCIATED * remains stable across this function. See the comments above the @@ -4106,7 +4117,7 @@ out_unlock: static int alloc_and_link_pwqs(struct workqueue_struct *wq) { bool highpri = wq->flags & WQ_HIGHPRI; - int cpu; + int cpu, ret; if (!(wq->flags & WQ_UNBOUND)) { wq->cpu_pwqs = alloc_percpu(struct pool_workqueue); @@ -4126,6 +4137,13 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) mutex_unlock(&wq->mutex); } return 0; + } else if (wq->flags & __WQ_ORDERED) { + ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); + /* there should only be single pwq for ordering guarantee */ + WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || + wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), + "ordering guarantee broken for workqueue %s\n", wq->name); + return ret; } else { return apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } @@ -5009,10 +5027,6 @@ static int __init init_workqueues(void) int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; int i, cpu; - /* make sure we have enough bits for OFFQ pool ID */ - BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT)) < - WORK_CPU_END * NR_STD_WORKER_POOLS); - WARN_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); @@ -5051,13 +5065,23 @@ static int __init init_workqueues(void) } } - /* create default unbound wq attrs */ + /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL))); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; + + /* + * An ordered wq should have only one pwq as ordering is + * guaranteed by max_active which is enforced by pwqs. + * Turn off NUMA so that dfl_pwq is used for all nodes. + */ + BUG_ON(!(attrs = alloc_workqueue_attrs(GFP_KERNEL))); + attrs->nice = std_nice[i]; + attrs->no_numa = true; + ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", 0, 0); |