From a288eecce5253cc1565d400a52b9b476a157e040 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:37 +0200 Subject: ptrace: kill trivial tracehooks At this point, tracehooks aren't useful to mainline kernel and mostly just add an extra layer of obfuscation. Although they have comments, without actual in-kernel users, it is difficult to tell what are their assumptions and they're actually trying to achieve. To mainline kernel, they just aren't worth keeping around. This patch kills the following trivial tracehooks. * Ones testing whether task is ptraced. Replace with ->ptrace test. tracehook_expect_breakpoints() tracehook_consider_ignored_signal() tracehook_consider_fatal_signal() * ptrace_event() wrappers. Call directly. tracehook_report_exec() tracehook_report_exit() tracehook_report_vfork_done() * ptrace_release_task() wrapper. Call directly. tracehook_finish_release_task() * noop tracehook_prepare_release_task() tracehook_report_death() This doesn't introduce any behavior change. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Cc: Martin Schwidefsky Signed-off-by: Oleg Nesterov --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 0276c30401a0..d4f0dff9d617 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1527,7 +1527,7 @@ long do_fork(unsigned long clone_flags, freezer_do_not_count(); wait_for_completion(&vfork); freezer_count(); - tracehook_report_vfork_done(p, nr); + ptrace_event(PTRACE_EVENT_VFORK_DONE, nr); } } else { nr = PTR_ERR(p); -- cgit v1.2.3 From 4b9d33e6d83cc05a8005a8f9a8b9677fa0f53626 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 17 Jun 2011 16:50:38 +0200 Subject: ptrace: kill clone/exec tracehooks At this point, tracehooks aren't useful to mainline kernel and mostly just add an extra layer of obfuscation. Although they have comments, without actual in-kernel users, it is difficult to tell what are their assumptions and they're actually trying to achieve. To mainline kernel, they just aren't worth keeping around. This patch kills the following clone and exec related tracehooks. tracehook_prepare_clone() tracehook_finish_clone() tracehook_report_clone() tracehook_report_clone_complete() tracehook_unsafe_exec() The changes are mostly trivial - logic is moved to the caller and comments are merged and adjusted appropriately. The only exception is in check_unsafe_exec() where LSM_UNSAFE_PTRACE* are OR'd to bprm->unsafe instead of setting it, which produces the same result as the field is always zero on entry. It also tests p->ptrace instead of (p->ptrace & PT_PTRACED) for consistency, which also gives the same result. This doesn't introduce any behavior change. Signed-off-by: Tejun Heo Cc: Christoph Hellwig Signed-off-by: Oleg Nesterov --- kernel/fork.c | 41 ++++++++++++++++++++++++++++++++--------- 1 file changed, 32 insertions(+), 9 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index d4f0dff9d617..3c72a5b321a7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1340,7 +1340,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, } if (likely(p->pid)) { - tracehook_finish_clone(p, clone_flags, trace); + ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); if (thread_group_leader(p)) { if (is_child_reaper(pid)) @@ -1481,10 +1481,22 @@ long do_fork(unsigned long clone_flags, } /* - * When called from kernel_thread, don't do user tracing stuff. + * Determine whether and which event to report to ptracer. When + * called from kernel_thread or CLONE_UNTRACED is explicitly + * requested, no event is reported; otherwise, report if the event + * for the type of forking is enabled. */ - if (likely(user_mode(regs))) - trace = tracehook_prepare_clone(clone_flags); + if (likely(user_mode(regs)) && !(clone_flags & CLONE_UNTRACED)) { + if (clone_flags & CLONE_VFORK) + trace = PTRACE_EVENT_VFORK; + else if ((clone_flags & CSIGNAL) != SIGCHLD) + trace = PTRACE_EVENT_CLONE; + else + trace = PTRACE_EVENT_FORK; + + if (likely(!ptrace_event_enabled(current, trace))) + trace = 0; + } p = copy_process(clone_flags, stack_start, regs, stack_size, child_tidptr, NULL, trace); @@ -1508,20 +1520,31 @@ long do_fork(unsigned long clone_flags, } audit_finish_fork(p); - tracehook_report_clone(regs, clone_flags, nr, p); + + /* + * Child is ready but hasn't started running yet. Queue + * SIGSTOP if it's gonna be ptraced - it doesn't matter who + * attached/attaching to this task, the pending SIGSTOP is + * right in any case. + */ + if (unlikely(p->ptrace)) { + sigaddset(&p->pending.signal, SIGSTOP); + set_tsk_thread_flag(p, TIF_SIGPENDING); + } /* * We set PF_STARTING at creation in case tracing wants to * use this to distinguish a fully live task from one that - * hasn't gotten to tracehook_report_clone() yet. Now we - * clear it and set the child going. + * hasn't finished SIGSTOP raising yet. Now we clear it + * and set the child going. */ p->flags &= ~PF_STARTING; wake_up_new_task(p); - tracehook_report_clone_complete(trace, regs, - clone_flags, nr, p); + /* forking complete and child started to run, tell ptracer */ + if (unlikely(trace)) + ptrace_event(trace, nr); if (clone_flags & CLONE_VFORK) { freezer_do_not_count(); -- cgit v1.2.3 From 732375c6a5a4cc825b676c922d547aba96b8ce15 Mon Sep 17 00:00:00 2001 From: Dima Zavin Date: Thu, 7 Jul 2011 17:27:59 -0700 Subject: plist: Remove the need to supply locks to plist heads This was legacy code brought over from the RT tree and is no longer necessary. Signed-off-by: Dima Zavin Acked-by: Thomas Gleixner Cc: Daniel Walker Cc: Steven Rostedt Cc: Peter Zijlstra Cc: Andi Kleen Cc: Lai Jiangshan Link: http://lkml.kernel.org/r/1310084879-10351-2-git-send-email-dima@android.com Signed-off-by: Ingo Molnar --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 0276c30401a0..7517a53d50e3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1013,7 +1013,7 @@ static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES - plist_head_init_raw(&p->pi_waiters, &p->pi_lock); + plist_head_init(&p->pi_waiters); p->pi_blocked_on = NULL; #endif } -- cgit v1.2.3 From 4aede84b33d6beb401136a3deca0651ae07c5e99 Mon Sep 17 00:00:00 2001 From: Justin TerAvest Date: Tue, 12 Jul 2011 08:31:45 +0200 Subject: fixlet: Remove fs_excl from struct task. fs_excl is a poor man's priority inheritance for filesystems to hint to the block layer that an operation is important. It was never clearly specified, not widely adopted, and will not prevent starvation in many cases (like across cgroups). fs_excl was introduced with the time sliced CFQ IO scheduler, to indicate when a process held FS exclusive resources and thus needed a boost. It doesn't cover all file systems, and it was never fully complete. Lets kill it. Signed-off-by: Justin TerAvest Signed-off-by: Jens Axboe --- kernel/fork.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 0276c30401a0..30a0e8607223 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -291,7 +291,6 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) /* One for us, one for whoever does the "release_task()" (usually parent) */ atomic_set(&tsk->usage,2); - atomic_set(&tsk->fs_excl, 0); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif -- cgit v1.2.3 From dcace06cc29df927a74a6bc0e57b9bef87704377 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 8 Jul 2011 19:13:54 +0200 Subject: ptrace: mv send-SIGSTOP from do_fork() to ptrace_init_task() If the new child is traced, do_fork() adds the pending SIGSTOP. It assumes that either it is traced because of auto-attach or the tracer attached later, in both cases sigaddset/set_thread_flag is correct even if SIGSTOP is already pending. Now that we have PTRACE_SEIZE this is no longer right in the latter case. If the tracer does PTRACE_SEIZE after copy_process() makes the child visible the queued SIGSTOP is wrong. We could check PT_SEIZED bit and change ptrace_attach() to set both PT_PTRACED and PT_SEIZED bits simultaneously but see the next patch, we need to know whether this child was auto-attached or not anyway. So this patch simply moves this code to ptrace_init_task(), this way we can never race with ptrace_attach(). Signed-off-by: Oleg Nesterov Acked-by: Tejun Heo --- kernel/fork.c | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 3c72a5b321a7..4d4117e01504 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -37,7 +37,6 @@ #include #include #include -#include #include #include #include @@ -1521,17 +1520,6 @@ long do_fork(unsigned long clone_flags, audit_finish_fork(p); - /* - * Child is ready but hasn't started running yet. Queue - * SIGSTOP if it's gonna be ptraced - it doesn't matter who - * attached/attaching to this task, the pending SIGSTOP is - * right in any case. - */ - if (unlikely(p->ptrace)) { - sigaddset(&p->pending.signal, SIGSTOP); - set_tsk_thread_flag(p, TIF_SIGPENDING); - } - /* * We set PF_STARTING at creation in case tracing wants to * use this to distinguish a fully live task from one that -- cgit v1.2.3 From 6657719390cd05be45f4e3b501d8bb46889c0a19 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 28 Jun 2011 15:41:10 -0400 Subject: make sure that nsproxy_cache is initialized early enough Signed-off-by: Al Viro --- kernel/fork.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 0276c30401a0..31fa13e63b70 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1574,6 +1574,7 @@ void __init proc_caches_init(void) SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC); mmap_init(); + nsproxy_cache_init(); } /* -- cgit v1.2.3 From 778d3b0ff0654ad7092bf823fd32010066b12365 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 26 Jul 2011 16:08:30 -0700 Subject: cpusets: randomize node rotor used in cpuset_mem_spread_node() [ This patch has already been accepted as commit 0ac0c0d0f837 but later reverted (commit 35926ff5fba8) because it itroduced arch specific __node_random which was defined only for x86 code so it broke other archs. This is a followup without any arch specific code. Other than that there are no functional changes.] Some workloads that create a large number of small files tend to assign too many pages to node 0 (multi-node systems). Part of the reason is that the rotor (in cpuset_mem_spread_node()) used to assign nodes starts at node 0 for newly created tasks. This patch changes the rotor to be initialized to a random node number of the cpuset. [akpm@linux-foundation.org: fix layout] [Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration] [mhocko@suse.cz: Make it arch independent] [akpm@linux-foundation.org: fix CONFIG_NUMA=y, MAX_NUMNODES>1 build] Signed-off-by: Jack Steiner Signed-off-by: Lee Schermerhorn Signed-off-by: Michal Hocko Reviewed-by: KOSAKI Motohiro Cc: Christoph Lameter Cc: Pekka Enberg Cc: Paul Menage Cc: Jack Steiner Cc: Robin Holt Cc: David Rientjes Cc: Christoph Lameter Cc: David Rientjes Cc: Jack Steiner Cc: KOSAKI Motohiro Cc: Lee Schermerhorn Cc: Michal Hocko Cc: Paul Menage Cc: Pekka Enberg Cc: Robin Holt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 17bf7c8d6511..e33177edb3bf 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1173,6 +1173,10 @@ static struct task_struct *copy_process(unsigned long clone_flags, } mpol_fix_fork_child_flag(p); #endif +#ifdef CONFIG_CPUSETS + p->cpuset_mem_spread_rotor = NUMA_NO_NODE; + p->cpuset_slab_spread_rotor = NUMA_NO_NODE; +#endif #ifdef CONFIG_TRACE_IRQFLAGS p->irq_events = 0; #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW -- cgit v1.2.3 From fb0a685cb95a0267a96153af2f72486f27be5847 Mon Sep 17 00:00:00 2001 From: Daniel Rebelo de Oliveira Date: Tue, 26 Jul 2011 16:08:39 -0700 Subject: kernel/fork.c: fix a few coding style issues Signed-off-by: Daniel Rebelo de Oliveira Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 83 ++++++++++++++++++++++++++++++++++------------------------- 1 file changed, 48 insertions(+), 35 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index e33177edb3bf..e7ceaca89609 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -80,7 +80,7 @@ * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ -int nr_threads; /* The idle threads do not count.. */ +int nr_threads; /* The idle threads do not count.. */ int max_threads; /* tunable limit on nr_threads */ @@ -232,7 +232,7 @@ void __init fork_init(unsigned long mempages) /* * we need to allow at least 20 threads to boot a system */ - if(max_threads < 20) + if (max_threads < 20) max_threads = 20; init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; @@ -268,7 +268,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) return NULL; } - err = arch_dup_task_struct(tsk, orig); + err = arch_dup_task_struct(tsk, orig); if (err) goto out; @@ -288,8 +288,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) tsk->stack_canary = get_random_int(); #endif - /* One for us, one for whoever does the "release_task()" (usually parent) */ - atomic_set(&tsk->usage,2); + /* + * One for us, one for whoever does the "release_task()" (usually + * parent) + */ + atomic_set(&tsk->usage, 2); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif @@ -437,7 +440,7 @@ fail_nomem: goto out; } -static inline int mm_alloc_pgd(struct mm_struct * mm) +static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) @@ -445,7 +448,7 @@ static inline int mm_alloc_pgd(struct mm_struct * mm) return 0; } -static inline void mm_free_pgd(struct mm_struct * mm) +static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } @@ -482,7 +485,7 @@ static void mm_init_aio(struct mm_struct *mm) #endif } -static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) +static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) { atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); @@ -513,9 +516,9 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) /* * Allocate and initialize an mm_struct. */ -struct mm_struct * mm_alloc(void) +struct mm_struct *mm_alloc(void) { - struct mm_struct * mm; + struct mm_struct *mm; mm = allocate_mm(); if (!mm) @@ -583,7 +586,7 @@ void added_exe_file_vma(struct mm_struct *mm) void removed_exe_file_vma(struct mm_struct *mm) { mm->num_exe_file_vmas--; - if ((mm->num_exe_file_vmas == 0) && mm->exe_file){ + if ((mm->num_exe_file_vmas == 0) && mm->exe_file) { fput(mm->exe_file); mm->exe_file = NULL; } @@ -775,9 +778,9 @@ fail_nocontext: return NULL; } -static int copy_mm(unsigned long clone_flags, struct task_struct * tsk) +static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { - struct mm_struct * mm, *oldmm; + struct mm_struct *mm, *oldmm; int retval; tsk->min_flt = tsk->maj_flt = 0; @@ -844,7 +847,7 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) return 0; } -static int copy_files(unsigned long clone_flags, struct task_struct * tsk) +static int copy_files(unsigned long clone_flags, struct task_struct *tsk) { struct files_struct *oldf, *newf; int error = 0; @@ -1166,11 +1169,11 @@ static struct task_struct *copy_process(unsigned long clone_flags, cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); - if (IS_ERR(p->mempolicy)) { - retval = PTR_ERR(p->mempolicy); - p->mempolicy = NULL; - goto bad_fork_cleanup_cgroup; - } + if (IS_ERR(p->mempolicy)) { + retval = PTR_ERR(p->mempolicy); + p->mempolicy = NULL; + goto bad_fork_cleanup_cgroup; + } mpol_fix_fork_child_flag(p); #endif #ifdef CONFIG_CPUSETS @@ -1216,25 +1219,33 @@ static struct task_struct *copy_process(unsigned long clone_flags, retval = perf_event_init_task(p); if (retval) goto bad_fork_cleanup_policy; - - if ((retval = audit_alloc(p))) + retval = audit_alloc(p); + if (retval) goto bad_fork_cleanup_policy; /* copy all the process information */ - if ((retval = copy_semundo(clone_flags, p))) + retval = copy_semundo(clone_flags, p); + if (retval) goto bad_fork_cleanup_audit; - if ((retval = copy_files(clone_flags, p))) + retval = copy_files(clone_flags, p); + if (retval) goto bad_fork_cleanup_semundo; - if ((retval = copy_fs(clone_flags, p))) + retval = copy_fs(clone_flags, p); + if (retval) goto bad_fork_cleanup_files; - if ((retval = copy_sighand(clone_flags, p))) + retval = copy_sighand(clone_flags, p); + if (retval) goto bad_fork_cleanup_fs; - if ((retval = copy_signal(clone_flags, p))) + retval = copy_signal(clone_flags, p); + if (retval) goto bad_fork_cleanup_sighand; - if ((retval = copy_mm(clone_flags, p))) + retval = copy_mm(clone_flags, p); + if (retval) goto bad_fork_cleanup_signal; - if ((retval = copy_namespaces(clone_flags, p))) + retval = copy_namespaces(clone_flags, p); + if (retval) goto bad_fork_cleanup_mm; - if ((retval = copy_io(clone_flags, p))) + retval = copy_io(clone_flags, p); + if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(clone_flags, stack_start, stack_size, p, regs); if (retval) @@ -1256,7 +1267,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, /* * Clear TID on mm_release()? */ - p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL; + p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; #ifdef CONFIG_BLOCK p->plug = NULL; #endif @@ -1324,7 +1335,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, * it's process group. * A fatal signal pending means that current will exit, so the new * thread can't slip out of an OOM kill (or normal SIGKILL). - */ + */ recalc_sigpending(); if (signal_pending(current)) { spin_unlock(¤t->sighand->siglock); @@ -1685,12 +1696,14 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; - if ((err = unshare_fs(unshare_flags, &new_fs))) + err = unshare_fs(unshare_flags, &new_fs); + if (err) goto bad_unshare_out; - if ((err = unshare_fd(unshare_flags, &new_fd))) + err = unshare_fd(unshare_flags, &new_fd); + if (err) goto bad_unshare_cleanup_fs; - if ((err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, - new_fs))) + err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_fs); + if (err) goto bad_unshare_cleanup_fd; if (new_fs || new_fd || do_sysvsem || new_nsproxy) { -- cgit v1.2.3