From 048a0e8f5e1d94c01a5fc70f5b2f2fd2f4527326 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 26 Apr 2012 10:52:27 -0700 Subject: timer: Fix mod_timer_pinned() header comment The mod_timer_pinned() header comment states that it prevents timers from being migrated to a different CPU. This is not the case, instead, it ensures that the timer is posted to the current CPU, but does nothing to prevent CPU-hotplug operations from migrating the timer. This commit therefore brings the comment header into alignment with reality. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney Acked-by: Steven Rostedt --- kernel/timer.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/timer.c') diff --git a/kernel/timer.c b/kernel/timer.c index a297ffcf888e..837c552fe838 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -861,7 +861,13 @@ EXPORT_SYMBOL(mod_timer); * * mod_timer_pinned() is a way to update the expire field of an * active timer (if the timer is inactive it will be activated) - * and not allow the timer to be migrated to a different CPU. + * and to ensure that the timer is scheduled on the current CPU. + * + * Note that this does not prevent the timer from being migrated + * when the current CPU goes offline. If this is a problem for + * you, use CPU-hotplug notifiers to handle it correctly, for + * example, cancelling the timer when the corresponding CPU goes + * offline. * * mod_timer_pinned(timer, expires) is equivalent to: * -- cgit v1.2.3 From a29c33f4e506e1dae7e0985b6328046535becbf8 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 7 Feb 2012 18:51:01 -0800 Subject: userns: Convert setting and getting uid and gid system calls to use kuid and kgid Convert setregid, setgid, setreuid, setuid, setresuid, getresuid, setresgid, getresgid, setfsuid, setfsgid, getuid, geteuid, getgid, getegid, waitpid, waitid, wait4. Convert userspace uids and gids into kuids and kgids before being placed on struct cred. Convert struct cred kuids and kgids into userspace uids and gids when returning them. Signed-off-by: Eric W. Biederman --- kernel/exit.c | 6 +- kernel/sys.c | 216 +++++++++++++++++++++++++++++++++++++++------------------ kernel/timer.c | 8 +-- kernel/uid16.c | 34 +++++---- 4 files changed, 178 insertions(+), 86 deletions(-) (limited to 'kernel/timer.c') diff --git a/kernel/exit.c b/kernel/exit.c index d8bd3b425fa7..789e3c5777f7 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1214,7 +1214,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) unsigned long state; int retval, status, traced; pid_t pid = task_pid_vnr(p); - uid_t uid = __task_cred(p)->uid; + uid_t uid = from_kuid_munged(current_user_ns(), __task_cred(p)->uid); struct siginfo __user *infop; if (!likely(wo->wo_flags & WEXITED)) @@ -1427,7 +1427,7 @@ static int wait_task_stopped(struct wait_opts *wo, if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; - uid = task_uid(p); + uid = from_kuid_munged(current_user_ns(), __task_cred(p)->uid); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) @@ -1500,7 +1500,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; - uid = task_uid(p); + uid = from_kuid_munged(current_user_ns(), __task_cred(p)->uid); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); diff --git a/kernel/sys.c b/kernel/sys.c index 39962818c008..aff09f208eb3 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -555,9 +555,19 @@ void ctrl_alt_del(void) */ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kgid_t krgid, kegid; + + krgid = make_kgid(ns, rgid); + kegid = make_kgid(ns, egid); + + if ((rgid != (gid_t) -1) && !gid_valid(krgid)) + return -EINVAL; + if ((egid != (gid_t) -1) && !gid_valid(kegid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -566,25 +576,25 @@ SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) retval = -EPERM; if (rgid != (gid_t) -1) { - if (old->gid == rgid || - old->egid == rgid || + if (gid_eq(old->gid, krgid) || + gid_eq(old->egid, krgid) || nsown_capable(CAP_SETGID)) - new->gid = rgid; + new->gid = krgid; else goto error; } if (egid != (gid_t) -1) { - if (old->gid == egid || - old->egid == egid || - old->sgid == egid || + if (gid_eq(old->gid, kegid) || + gid_eq(old->egid, kegid) || + gid_eq(old->sgid, kegid) || nsown_capable(CAP_SETGID)) - new->egid = egid; + new->egid = kegid; else goto error; } if (rgid != (gid_t) -1 || - (egid != (gid_t) -1 && egid != old->gid)) + (egid != (gid_t) -1 && !gid_eq(kegid, old->gid))) new->sgid = new->egid; new->fsgid = new->egid; @@ -602,9 +612,15 @@ error: */ SYSCALL_DEFINE1(setgid, gid_t, gid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kgid_t kgid; + + kgid = make_kgid(ns, gid); + if (!gid_valid(kgid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -613,9 +629,9 @@ SYSCALL_DEFINE1(setgid, gid_t, gid) retval = -EPERM; if (nsown_capable(CAP_SETGID)) - new->gid = new->egid = new->sgid = new->fsgid = gid; - else if (gid == old->gid || gid == old->sgid) - new->egid = new->fsgid = gid; + new->gid = new->egid = new->sgid = new->fsgid = kgid; + else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid)) + new->egid = new->fsgid = kgid; else goto error; @@ -672,9 +688,19 @@ static int set_user(struct cred *new) */ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kuid_t kruid, keuid; + + kruid = make_kuid(ns, ruid); + keuid = make_kuid(ns, euid); + + if ((ruid != (uid_t) -1) && !uid_valid(kruid)) + return -EINVAL; + if ((euid != (uid_t) -1) && !uid_valid(keuid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -683,29 +709,29 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) retval = -EPERM; if (ruid != (uid_t) -1) { - new->uid = ruid; - if (old->uid != ruid && - old->euid != ruid && + new->uid = kruid; + if (!uid_eq(old->uid, kruid) && + !uid_eq(old->euid, kruid) && !nsown_capable(CAP_SETUID)) goto error; } if (euid != (uid_t) -1) { - new->euid = euid; - if (old->uid != euid && - old->euid != euid && - old->suid != euid && + new->euid = keuid; + if (!uid_eq(old->uid, keuid) && + !uid_eq(old->euid, keuid) && + !uid_eq(old->suid, keuid) && !nsown_capable(CAP_SETUID)) goto error; } - if (new->uid != old->uid) { + if (!uid_eq(new->uid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } if (ruid != (uid_t) -1 || - (euid != (uid_t) -1 && euid != old->uid)) + (euid != (uid_t) -1 && !uid_eq(keuid, old->uid))) new->suid = new->euid; new->fsuid = new->euid; @@ -733,9 +759,15 @@ error: */ SYSCALL_DEFINE1(setuid, uid_t, uid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kuid_t kuid; + + kuid = make_kuid(ns, uid); + if (!uid_valid(kuid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -744,17 +776,17 @@ SYSCALL_DEFINE1(setuid, uid_t, uid) retval = -EPERM; if (nsown_capable(CAP_SETUID)) { - new->suid = new->uid = uid; - if (uid != old->uid) { + new->suid = new->uid = kuid; + if (!uid_eq(kuid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } - } else if (uid != old->uid && uid != new->suid) { + } else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) { goto error; } - new->fsuid = new->euid = uid; + new->fsuid = new->euid = kuid; retval = security_task_fix_setuid(new, old, LSM_SETID_ID); if (retval < 0) @@ -774,9 +806,24 @@ error: */ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kuid_t kruid, keuid, ksuid; + + kruid = make_kuid(ns, ruid); + keuid = make_kuid(ns, euid); + ksuid = make_kuid(ns, suid); + + if ((ruid != (uid_t) -1) && !uid_valid(kruid)) + return -EINVAL; + + if ((euid != (uid_t) -1) && !uid_valid(keuid)) + return -EINVAL; + + if ((suid != (uid_t) -1) && !uid_valid(ksuid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -786,29 +833,29 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) retval = -EPERM; if (!nsown_capable(CAP_SETUID)) { - if (ruid != (uid_t) -1 && ruid != old->uid && - ruid != old->euid && ruid != old->suid) + if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && + !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid)) goto error; - if (euid != (uid_t) -1 && euid != old->uid && - euid != old->euid && euid != old->suid) + if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && + !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid)) goto error; - if (suid != (uid_t) -1 && suid != old->uid && - suid != old->euid && suid != old->suid) + if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && + !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid)) goto error; } if (ruid != (uid_t) -1) { - new->uid = ruid; - if (ruid != old->uid) { + new->uid = kruid; + if (!uid_eq(kruid, old->uid)) { retval = set_user(new); if (retval < 0) goto error; } } if (euid != (uid_t) -1) - new->euid = euid; + new->euid = keuid; if (suid != (uid_t) -1) - new->suid = suid; + new->suid = ksuid; new->fsuid = new->euid; retval = security_task_fix_setuid(new, old, LSM_SETID_RES); @@ -822,14 +869,19 @@ error: return retval; } -SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid) +SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp) { const struct cred *cred = current_cred(); int retval; + uid_t ruid, euid, suid; + + ruid = from_kuid_munged(cred->user_ns, cred->uid); + euid = from_kuid_munged(cred->user_ns, cred->euid); + suid = from_kuid_munged(cred->user_ns, cred->suid); - if (!(retval = put_user(cred->uid, ruid)) && - !(retval = put_user(cred->euid, euid))) - retval = put_user(cred->suid, suid); + if (!(retval = put_user(ruid, ruidp)) && + !(retval = put_user(euid, euidp))) + retval = put_user(suid, suidp); return retval; } @@ -839,9 +891,22 @@ SYSCALL_DEFINE3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __u */ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) { + struct user_namespace *ns = current_user_ns(); const struct cred *old; struct cred *new; int retval; + kgid_t krgid, kegid, ksgid; + + krgid = make_kgid(ns, rgid); + kegid = make_kgid(ns, egid); + ksgid = make_kgid(ns, sgid); + + if ((rgid != (gid_t) -1) && !gid_valid(krgid)) + return -EINVAL; + if ((egid != (gid_t) -1) && !gid_valid(kegid)) + return -EINVAL; + if ((sgid != (gid_t) -1) && !gid_valid(ksgid)) + return -EINVAL; new = prepare_creds(); if (!new) @@ -850,23 +915,23 @@ SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) retval = -EPERM; if (!nsown_capable(CAP_SETGID)) { - if (rgid != (gid_t) -1 && rgid != old->gid && - rgid != old->egid && rgid != old->sgid) + if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && + !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid)) goto error; - if (egid != (gid_t) -1 && egid != old->gid && - egid != old->egid && egid != old->sgid) + if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && + !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid)) goto error; - if (sgid != (gid_t) -1 && sgid != old->gid && - sgid != old->egid && sgid != old->sgid) + if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && + !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid)) goto error; } if (rgid != (gid_t) -1) - new->gid = rgid; + new->gid = krgid; if (egid != (gid_t) -1) - new->egid = egid; + new->egid = kegid; if (sgid != (gid_t) -1) - new->sgid = sgid; + new->sgid = ksgid; new->fsgid = new->egid; return commit_creds(new); @@ -876,14 +941,19 @@ error: return retval; } -SYSCALL_DEFINE3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid) +SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp) { const struct cred *cred = current_cred(); int retval; + gid_t rgid, egid, sgid; + + rgid = from_kgid_munged(cred->user_ns, cred->gid); + egid = from_kgid_munged(cred->user_ns, cred->egid); + sgid = from_kgid_munged(cred->user_ns, cred->sgid); - if (!(retval = put_user(cred->gid, rgid)) && - !(retval = put_user(cred->egid, egid))) - retval = put_user(cred->sgid, sgid); + if (!(retval = put_user(rgid, rgidp)) && + !(retval = put_user(egid, egidp))) + retval = put_user(sgid, sgidp); return retval; } @@ -900,18 +970,24 @@ SYSCALL_DEFINE1(setfsuid, uid_t, uid) const struct cred *old; struct cred *new; uid_t old_fsuid; + kuid_t kuid; + + old = current_cred(); + old_fsuid = from_kuid_munged(old->user_ns, old->fsuid); + + kuid = make_kuid(old->user_ns, uid); + if (!uid_valid(kuid)) + return old_fsuid; new = prepare_creds(); if (!new) - return current_fsuid(); - old = current_cred(); - old_fsuid = old->fsuid; + return old_fsuid; - if (uid == old->uid || uid == old->euid || - uid == old->suid || uid == old->fsuid || + if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) || + uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) || nsown_capable(CAP_SETUID)) { - if (uid != old_fsuid) { - new->fsuid = uid; + if (!uid_eq(kuid, old->fsuid)) { + new->fsuid = kuid; if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) goto change_okay; } @@ -933,18 +1009,24 @@ SYSCALL_DEFINE1(setfsgid, gid_t, gid) const struct cred *old; struct cred *new; gid_t old_fsgid; + kgid_t kgid; + + old = current_cred(); + old_fsgid = from_kgid_munged(old->user_ns, old->fsgid); + + kgid = make_kgid(old->user_ns, gid); + if (!gid_valid(kgid)) + return old_fsgid; new = prepare_creds(); if (!new) - return current_fsgid(); - old = current_cred(); - old_fsgid = old->fsgid; + return old_fsgid; - if (gid == old->gid || gid == old->egid || - gid == old->sgid || gid == old->fsgid || + if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) || + gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) || nsown_capable(CAP_SETGID)) { - if (gid != old_fsgid) { - new->fsgid = gid; + if (!gid_eq(kgid, old->fsgid)) { + new->fsgid = kgid; goto change_okay; } } @@ -1503,10 +1585,10 @@ static int check_prlimit_permission(struct task_struct *task) if (cred->user_ns == tcred->user_ns && (cred->uid == tcred->euid && cred->uid == tcred->suid && - cred->uid == tcred->uid && + cred->uid == tcred->uid && cred->gid == tcred->egid && cred->gid == tcred->sgid && - cred->gid == tcred->gid)) + cred->gid == tcred->gid)) return 0; if (ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) return 0; diff --git a/kernel/timer.c b/kernel/timer.c index a297ffcf888e..67316cb6a777 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1427,25 +1427,25 @@ SYSCALL_DEFINE0(getppid) SYSCALL_DEFINE0(getuid) { /* Only we change this so SMP safe */ - return current_uid(); + return from_kuid_munged(current_user_ns(), current_uid()); } SYSCALL_DEFINE0(geteuid) { /* Only we change this so SMP safe */ - return current_euid(); + return from_kuid_munged(current_user_ns(), current_euid()); } SYSCALL_DEFINE0(getgid) { /* Only we change this so SMP safe */ - return current_gid(); + return from_kgid_munged(current_user_ns(), current_gid()); } SYSCALL_DEFINE0(getegid) { /* Only we change this so SMP safe */ - return current_egid(); + return from_kgid_munged(current_user_ns(), current_egid()); } #endif diff --git a/kernel/uid16.c b/kernel/uid16.c index e530bc34c4cf..d7948eb10225 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -81,14 +81,19 @@ SYSCALL_DEFINE3(setresuid16, old_uid_t, ruid, old_uid_t, euid, old_uid_t, suid) return ret; } -SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruid, old_uid_t __user *, euid, old_uid_t __user *, suid) +SYSCALL_DEFINE3(getresuid16, old_uid_t __user *, ruidp, old_uid_t __user *, euidp, old_uid_t __user *, suidp) { const struct cred *cred = current_cred(); int retval; + old_uid_t ruid, euid, suid; - if (!(retval = put_user(high2lowuid(cred->uid), ruid)) && - !(retval = put_user(high2lowuid(cred->euid), euid))) - retval = put_user(high2lowuid(cred->suid), suid); + ruid = high2lowuid(from_kuid_munged(cred->user_ns, cred->uid)); + euid = high2lowuid(from_kuid_munged(cred->user_ns, cred->euid)); + suid = high2lowuid(from_kuid_munged(cred->user_ns, cred->suid)); + + if (!(retval = put_user(ruid, ruidp)) && + !(retval = put_user(euid, euidp))) + retval = put_user(suid, suidp); return retval; } @@ -103,14 +108,19 @@ SYSCALL_DEFINE3(setresgid16, old_gid_t, rgid, old_gid_t, egid, old_gid_t, sgid) } -SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgid, old_gid_t __user *, egid, old_gid_t __user *, sgid) +SYSCALL_DEFINE3(getresgid16, old_gid_t __user *, rgidp, old_gid_t __user *, egidp, old_gid_t __user *, sgidp) { const struct cred *cred = current_cred(); int retval; + old_gid_t rgid, egid, sgid; + + rgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->gid)); + egid = high2lowgid(from_kgid_munged(cred->user_ns, cred->egid)); + sgid = high2lowgid(from_kgid_munged(cred->user_ns, cred->sgid)); - if (!(retval = put_user(high2lowgid(cred->gid), rgid)) && - !(retval = put_user(high2lowgid(cred->egid), egid))) - retval = put_user(high2lowgid(cred->sgid), sgid); + if (!(retval = put_user(rgid, rgidp)) && + !(retval = put_user(egid, egidp))) + retval = put_user(sgid, sgidp); return retval; } @@ -221,20 +231,20 @@ SYSCALL_DEFINE2(setgroups16, int, gidsetsize, old_gid_t __user *, grouplist) SYSCALL_DEFINE0(getuid16) { - return high2lowuid(current_uid()); + return high2lowuid(from_kuid_munged(current_user_ns(), current_uid())); } SYSCALL_DEFINE0(geteuid16) { - return high2lowuid(current_euid()); + return high2lowuid(from_kuid_munged(current_user_ns(), current_euid())); } SYSCALL_DEFINE0(getgid16) { - return high2lowgid(current_gid()); + return high2lowgid(from_kgid_munged(current_user_ns(), current_gid())); } SYSCALL_DEFINE0(getegid16) { - return high2lowgid(current_egid()); + return high2lowgid(from_kgid_munged(current_user_ns(), current_egid())); } -- cgit v1.2.3 From 4d82a1debbffec129cc387aafa8f40b7bbab3297 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 May 2012 08:06:19 -0700 Subject: lockdep: fix oops in processing workqueue Under memory load, on x86_64, with lockdep enabled, the workqueue's process_one_work() has been seen to oops in __lock_acquire(), barfing on a 0xffffffff00000000 pointer in the lockdep_map's class_cache[]. Because it's permissible to free a work_struct from its callout function, the map used is an onstack copy of the map given in the work_struct: and that copy is made without any locking. Surprisingly, gcc (4.5.1 in Hugh's case) uses "rep movsl" rather than "rep movsq" for that structure copy: which might race with a workqueue user's wait_on_work() doing lock_map_acquire() on the source of the copy, putting a pointer into the class_cache[], but only in time for the top half of that pointer to be copied to the destination map. Boom when process_one_work() subsequently does lock_map_acquire() on its onstack copy of the lockdep_map. Fix this, and a similar instance in call_timer_fn(), with a lockdep_copy_map() function which additionally NULLs the class_cache[]. Note: this oops was actually seen on 3.4-next, where flush_work() newly does the racing lock_map_acquire(); but Tejun points out that 3.4 and earlier are already vulnerable to the same through wait_on_work(). * Patch orginally from Peter. Hugh modified it a bit and wrote the description. Signed-off-by: Peter Zijlstra Reported-by: Hugh Dickins LKML-Reference: Signed-off-by: Tejun Heo --- include/linux/lockdep.h | 18 ++++++++++++++++++ kernel/timer.c | 4 +++- kernel/workqueue.c | 4 +++- 3 files changed, 24 insertions(+), 2 deletions(-) (limited to 'kernel/timer.c') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index d36619ead3ba..00e46376e28f 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -157,6 +157,24 @@ struct lockdep_map { #endif }; +static inline void lockdep_copy_map(struct lockdep_map *to, + struct lockdep_map *from) +{ + int i; + + *to = *from; + /* + * Since the class cache can be modified concurrently we could observe + * half pointers (64bit arch using 32bit copy insns). Therefore clear + * the caches and take the performance hit. + * + * XXX it doesn't work well with lockdep_set_class_and_subclass(), since + * that relies on cache abuse. + */ + for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++) + to->class_cache[i] = NULL; +} + /* * Every lock has a list of other locks that were taken after it. * We only grow the list, never remove from it: diff --git a/kernel/timer.c b/kernel/timer.c index a297ffcf888e..b12385244bb5 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1102,7 +1102,9 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(unsigned long), * warnings as well as problems when looking into * timer->lockdep_map, make a copy and use that here. */ - struct lockdep_map lockdep_map = timer->lockdep_map; + struct lockdep_map lockdep_map; + + lockdep_copy_map(&lockdep_map, &timer->lockdep_map); #endif /* * Couple the lock chain with the lock chain at diff --git a/kernel/workqueue.c b/kernel/workqueue.c index c36c86cf7900..9a3128dc67df 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1818,7 +1818,9 @@ __acquires(&gcwq->lock) * lock freed" warnings as well as problems when looking into * work->lockdep_map, make a copy and use that here. */ - struct lockdep_map lockdep_map = work->lockdep_map; + struct lockdep_map lockdep_map; + + lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif /* * A single work shouldn't be executed concurrently by -- cgit v1.2.3 From ec44bc7acc3687ba6ae8154b4b5a845b70279237 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 May 2012 22:08:57 +0000 Subject: timers: Create detach_if_pending() and use it Most callers of detach_timer() have the same pattern around them. Check whether the timer is pending and eventually updating base->next_timer. Create detach_if_pending() and replace the duplicated code. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Gilad Ben-Yossef Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/20120525214819.131246037@linutronix.de --- kernel/timer.c | 56 +++++++++++++++++++++++--------------------------------- 1 file changed, 23 insertions(+), 33 deletions(-) (limited to 'kernel/timer.c') diff --git a/kernel/timer.c b/kernel/timer.c index 6ec7e7e0db43..0f70deb20151 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -654,8 +654,7 @@ void init_timer_deferrable_key(struct timer_list *timer, } EXPORT_SYMBOL(init_timer_deferrable_key); -static inline void detach_timer(struct timer_list *timer, - int clear_pending) +static inline void detach_timer(struct timer_list *timer, bool clear_pending) { struct list_head *entry = &timer->entry; @@ -667,6 +666,19 @@ static inline void detach_timer(struct timer_list *timer, entry->prev = LIST_POISON2; } +static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, + bool clear_pending) +{ + if (!timer_pending(timer)) + return 0; + + detach_timer(timer, clear_pending); + if (timer->expires == base->next_timer && + !tbase_get_deferrable(timer->base)) + base->next_timer = base->timer_jiffies; + return 1; +} + /* * We are using hashed locking: holding per_cpu(tvec_bases).lock * means that all timers which are tied to this base via timer->base are @@ -712,16 +724,9 @@ __mod_timer(struct timer_list *timer, unsigned long expires, base = lock_timer_base(timer, &flags); - if (timer_pending(timer)) { - detach_timer(timer, 0); - if (timer->expires == base->next_timer && - !tbase_get_deferrable(timer->base)) - base->next_timer = base->timer_jiffies; - ret = 1; - } else { - if (pending_only) - goto out_unlock; - } + ret = detach_if_pending(timer, base, false); + if (!ret && pending_only) + goto out_unlock; debug_activate(timer, expires); @@ -959,13 +964,7 @@ int del_timer(struct timer_list *timer) timer_stats_timer_clear_start_info(timer); if (timer_pending(timer)) { base = lock_timer_base(timer, &flags); - if (timer_pending(timer)) { - detach_timer(timer, 1); - if (timer->expires == base->next_timer && - !tbase_get_deferrable(timer->base)) - base->next_timer = base->timer_jiffies; - ret = 1; - } + ret = detach_if_pending(timer, base, true); spin_unlock_irqrestore(&base->lock, flags); } @@ -990,19 +989,10 @@ int try_to_del_timer_sync(struct timer_list *timer) base = lock_timer_base(timer, &flags); - if (base->running_timer == timer) - goto out; - - timer_stats_timer_clear_start_info(timer); - ret = 0; - if (timer_pending(timer)) { - detach_timer(timer, 1); - if (timer->expires == base->next_timer && - !tbase_get_deferrable(timer->base)) - base->next_timer = base->timer_jiffies; - ret = 1; + if (base->running_timer != timer) { + timer_stats_timer_clear_start_info(timer); + ret = detach_if_pending(timer, base, true); } -out: spin_unlock_irqrestore(&base->lock, flags); return ret; @@ -1178,7 +1168,7 @@ static inline void __run_timers(struct tvec_base *base) timer_stats_account_timer(timer); base->running_timer = timer; - detach_timer(timer, 1); + detach_timer(timer, true); spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, data); @@ -1714,7 +1704,7 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea while (!list_empty(head)) { timer = list_first_entry(head, struct timer_list, entry); - detach_timer(timer, 0); + detach_timer(timer, false); timer_set_base(timer, new_base); if (time_before(timer->expires, new_base->next_timer) && !tbase_get_deferrable(timer->base)) -- cgit v1.2.3 From facbb4a7efbd658046bf615f03cd97a1504785d8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 May 2012 22:08:57 +0000 Subject: timers: Consolidate base->next_timer update Another bunch of mindlessly copied code. All callers of internal_add_timer() except the recascading code updates base->next_timer. Move this into internal_add_timer() and let the cascading code call __internal_add_timer(). Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Gilad Ben-Yossef Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/20120525214819.189946224@linutronix.de --- kernel/timer.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) (limited to 'kernel/timer.c') diff --git a/kernel/timer.c b/kernel/timer.c index 0f70deb20151..7207690b5353 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -330,7 +330,8 @@ void set_timer_slack(struct timer_list *timer, int slack_hz) } EXPORT_SYMBOL_GPL(set_timer_slack); -static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) +static void +__internal_add_timer(struct tvec_base *base, struct timer_list *timer) { unsigned long expires = timer->expires; unsigned long idx = expires - base->timer_jiffies; @@ -372,6 +373,17 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) list_add_tail(&timer->entry, vec); } +static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) +{ + __internal_add_timer(base, timer); + /* + * Update base->next_timer if this is the earliest one. + */ + if (time_before(timer->expires, base->next_timer) && + !tbase_get_deferrable(timer->base)) + base->next_timer = timer->expires; +} + #ifdef CONFIG_TIMER_STATS void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr) { @@ -757,9 +769,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, } timer->expires = expires; - if (time_before(timer->expires, base->next_timer) && - !tbase_get_deferrable(timer->base)) - base->next_timer = timer->expires; internal_add_timer(base, timer); out_unlock: @@ -925,9 +934,6 @@ void add_timer_on(struct timer_list *timer, int cpu) spin_lock_irqsave(&base->lock, flags); timer_set_base(timer, base); debug_activate(timer, timer->expires); - if (time_before(timer->expires, base->next_timer) && - !tbase_get_deferrable(timer->base)) - base->next_timer = timer->expires; internal_add_timer(base, timer); /* * Check whether the other CPU is idle and needs to be @@ -1079,7 +1085,8 @@ static int cascade(struct tvec_base *base, struct tvec *tv, int index) */ list_for_each_entry_safe(timer, tmp, &tv_list, entry) { BUG_ON(tbase_get_base(timer->base) != base); - internal_add_timer(base, timer); + /* No accounting, while moving them */ + __internal_add_timer(base, timer); } return index; @@ -1706,9 +1713,6 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea timer = list_first_entry(head, struct timer_list, entry); detach_timer(timer, false); timer_set_base(timer, new_base); - if (time_before(timer->expires, new_base->next_timer) && - !tbase_get_deferrable(timer->base)) - new_base->next_timer = timer->expires; internal_add_timer(new_base, timer); } } -- cgit v1.2.3 From 99d5f3aac674fe081ffddd2dbb8946ccbc14c410 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 May 2012 22:08:58 +0000 Subject: timers: Add accounting of non deferrable timers The code in get_next_timer_interrupt() is suboptimal as it has to run through the cascade to find the next expiring timer. On a completely idle core we should only do that when there is an active timer enqueued and base->next_timer does not give us a fast answer. Add accounting of the active timers to the now consolidated attach/detach code. I deliberately avoided sanity checks because the code is fully symetric and any fiddling with timers w/o using the API functions will lead to cute explosions anyway. ulong is big enough even on 32bit and if we really run into the situation to have more than 1<<32 timers enqueued there, then we are definitely not in a state to go idle and run through that code. This allows us to fix another shortcoming of get_next_timer_interrupt(). Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Gilad Ben-Yossef Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/20120525214819.236377028@linutronix.de --- kernel/timer.c | 31 +++++++++++++++++++++++-------- 1 file changed, 23 insertions(+), 8 deletions(-) (limited to 'kernel/timer.c') diff --git a/kernel/timer.c b/kernel/timer.c index 7207690b5353..7fada698bd1a 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -77,6 +77,7 @@ struct tvec_base { struct timer_list *running_timer; unsigned long timer_jiffies; unsigned long next_timer; + unsigned long active_timers; struct tvec_root tv1; struct tvec tv2; struct tvec tv3; @@ -377,11 +378,13 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) { __internal_add_timer(base, timer); /* - * Update base->next_timer if this is the earliest one. + * Update base->active_timers and base->next_timer */ - if (time_before(timer->expires, base->next_timer) && - !tbase_get_deferrable(timer->base)) - base->next_timer = timer->expires; + if (!tbase_get_deferrable(timer->base)) { + if (time_before(timer->expires, base->next_timer)) + base->next_timer = timer->expires; + base->active_timers++; + } } #ifdef CONFIG_TIMER_STATS @@ -678,6 +681,14 @@ static inline void detach_timer(struct timer_list *timer, bool clear_pending) entry->prev = LIST_POISON2; } +static inline void +detach_expired_timer(struct timer_list *timer, struct tvec_base *base) +{ + detach_timer(timer, true); + if (!tbase_get_deferrable(timer->base)) + timer->base->active_timers--; +} + static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, bool clear_pending) { @@ -685,9 +696,11 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, return 0; detach_timer(timer, clear_pending); - if (timer->expires == base->next_timer && - !tbase_get_deferrable(timer->base)) - base->next_timer = base->timer_jiffies; + if (!tbase_get_deferrable(timer->base)) { + timer->base->active_timers--; + if (timer->expires == base->next_timer) + base->next_timer = base->timer_jiffies; + } return 1; } @@ -1175,7 +1188,7 @@ static inline void __run_timers(struct tvec_base *base) timer_stats_account_timer(timer); base->running_timer = timer; - detach_timer(timer, true); + detach_expired_timer(timer, base); spin_unlock_irq(&base->lock); call_timer_fn(timer, fn, data); @@ -1701,6 +1714,7 @@ static int __cpuinit init_timers_cpu(int cpu) base->timer_jiffies = jiffies; base->next_timer = base->timer_jiffies; + base->active_timers = 0; return 0; } @@ -1711,6 +1725,7 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea while (!list_empty(head)) { timer = list_first_entry(head, struct timer_list, entry); + /* We ignore the accounting on the dying cpu */ detach_timer(timer, false); timer_set_base(timer, new_base); internal_add_timer(new_base, timer); -- cgit v1.2.3 From e40468a54882ef7411fb178dbf2e465ec2349af7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 May 2012 22:08:59 +0000 Subject: timers: Improve get_next_timer_interrupt() Gilad reported at http://lkml.kernel.org/r/1336056962-10465-2-git-send-email-gilad@benyossef.com "Current timer code fails to correctly return a value meaning that there is no future timer event, with the result that the timer keeps getting re-armed in HZ one shot mode even when we could turn it off, generating unneeded interrupts. What is happening is that when __next_timer_interrupt() wishes to return a value that signifies "there is no future timer event", it returns (base->timer_jiffies + NEXT_TIMER_MAX_DELTA). However, the code in tick_nohz_stop_sched_tick(), which called __next_timer_interrupt() via get_next_timer_interrupt(), compares the return value to (last_jiffies + NEXT_TIMER_MAX_DELTA) to see if the timer needs to be re-armed. base->timer_jiffies != last_jiffies and so tick_nohz_stop_sched_tick() interperts the return value as indication that there is a distant future event 12 days from now and programs the timer to fire next after KTIME_MAX nsecs instead of avoiding to arm it. This ends up causing a needless interrupt once every KTIME_MAX nsecs." Fix this by using the new active timer accounting. This avoids scans when no active timer is enqueued completely, so we don't have to rely on base->timer_next and base->timer_jiffies anymore. Reported-by: Gilad Ben-Yossef Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: Frederic Weisbecker Link: http://lkml.kernel.org/r/20120525214819.317535385@linutronix.de --- kernel/timer.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'kernel/timer.c') diff --git a/kernel/timer.c b/kernel/timer.c index 7fada698bd1a..a61c09374eba 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1326,18 +1326,21 @@ static unsigned long cmp_next_hrtimer_event(unsigned long now, unsigned long get_next_timer_interrupt(unsigned long now) { struct tvec_base *base = __this_cpu_read(tvec_bases); - unsigned long expires; + unsigned long expires = now + NEXT_TIMER_MAX_DELTA; /* * Pretend that there is no timer pending if the cpu is offline. * Possible pending timers will be migrated later to an active cpu. */ if (cpu_is_offline(smp_processor_id())) - return now + NEXT_TIMER_MAX_DELTA; + return expires; + spin_lock(&base->lock); - if (time_before_eq(base->next_timer, base->timer_jiffies)) - base->next_timer = __next_timer_interrupt(base); - expires = base->next_timer; + if (base->active_timers) { + if (time_before_eq(base->next_timer, base->timer_jiffies)) + base->next_timer = __next_timer_interrupt(base); + expires = base->next_timer; + } spin_unlock(&base->lock); if (time_before_eq(expires, now)) -- cgit v1.2.3