From 4714d1d32d97239fb5ae3e10521d3f133a899b66 Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Thu, 26 May 2011 16:25:18 -0700 Subject: cgroups: read-write lock CLONE_THREAD forking per threadgroup Adds functionality to read/write lock CLONE_THREAD fork()ing per-threadgroup Add an rwsem that lives in a threadgroup's signal_struct that's taken for reading in the fork path, under CONFIG_CGROUPS. If another part of the kernel later wants to use such a locking mechanism, the CONFIG_CGROUPS ifdefs should be changed to a higher-up flag that CGROUPS and the other system would both depend on. This is a pre-patch for cgroup-procs-write.patch. Signed-off-by: Ben Blum Cc: "Eric W. Biederman" Cc: Li Zefan Cc: Matt Helsley Reviewed-by: Paul Menage Cc: Oleg Nesterov Cc: David Rientjes Cc: Miao Xie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 8e7e135d0817..1fa9d940e301 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -957,6 +957,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) tty_audit_fork(sig); sched_autogroup_fork(sig); +#ifdef CONFIG_CGROUPS + init_rwsem(&sig->threadgroup_fork_lock); +#endif + sig->oom_adj = current->signal->oom_adj; sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; @@ -1138,6 +1142,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, monotonic_to_bootbased(&p->real_start_time); p->io_context = NULL; p->audit_context = NULL; + if (clone_flags & CLONE_THREAD) + threadgroup_fork_read_lock(current); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); @@ -1342,6 +1348,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, write_unlock_irq(&tasklist_lock); proc_fork_connector(p); cgroup_post_fork(p); + if (clone_flags & CLONE_THREAD) + threadgroup_fork_read_unlock(current); perf_event_fork(p); return p; @@ -1380,6 +1388,8 @@ bad_fork_cleanup_policy: mpol_put(p->mempolicy); bad_fork_cleanup_cgroup: #endif + if (clone_flags & CLONE_THREAD) + threadgroup_fork_read_unlock(current); cgroup_exit(p, cgroup_callbacks_done); delayacct_tsk_free(p); module_put(task_thread_info(p)->exec_domain->module); -- cgit From a77aea92010acf54ad785047234418d5d68772e2 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 26 May 2011 16:25:23 -0700 Subject: cgroup: remove the ns_cgroup The ns_cgroup is an annoying cgroup at the namespace / cgroup frontier and leads to some problems: * cgroup creation is out-of-control * cgroup name can conflict when pids are looping * it is not possible to have a single process handling a lot of namespaces without falling in a exponential creation time * we may want to create a namespace without creating a cgroup The ns_cgroup was replaced by a compatibility flag 'clone_children', where a newly created cgroup will copy the parent cgroup values. The userspace has to manually create a cgroup and add a task to the 'tasks' file. This patch removes the ns_cgroup as suggested in the following thread: https://lists.linux-foundation.org/pipermail/containers/2009-June/018616.html The 'cgroup_clone' function is removed because it is no longer used. This is a userspace-visible change. Commit 45531757b45c ("cgroup: notify ns_cgroup deprecated") (merged into 2.6.27) caused the kernel to emit a printk warning users that the feature is planned for removal. Since that time we have heard from XXX users who were affected by this. Signed-off-by: Daniel Lezcano Signed-off-by: Serge E. Hallyn Cc: Eric W. Biederman Cc: Jamal Hadi Salim Reviewed-by: Li Zefan Acked-by: Paul Menage Acked-by: Matt Helsley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 1fa9d940e301..1f84099ecce6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1229,12 +1229,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (clone_flags & CLONE_THREAD) p->tgid = current->tgid; - if (current->nsproxy != p->nsproxy) { - retval = ns_cgroup_clone(p, pid); - if (retval) - goto bad_fork_free_pid; - } - p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; /* * Clear TID on mm_release()? -- cgit From 3864601387cf4196371e3c1897fdffa5228296f9 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 26 May 2011 16:25:46 -0700 Subject: mm: extract exe_file handling from procfs Setup and cleanup of mm_struct->exe_file is currently done in fs/proc/. This was because exe_file was needed only for /proc//exe. Since we will need the exe_file functionality also for core dumps (so core name can contain full binary path), built this functionality always into the kernel. To achieve that move that out of proc FS to the kernel/ where in fact it should belong. By doing that we can make dup_mm_exe_file static. Also we can drop linux/proc_fs.h inclusion in fs/exec.c and kernel/fork.c. Signed-off-by: Jiri Slaby Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 51 insertions(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 1f84099ecce6..ca406d916713 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -59,7 +59,6 @@ #include #include #include -#include #include #include #include @@ -597,6 +596,57 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); +/* + * We added or removed a vma mapping the executable. The vmas are only mapped + * during exec and are not mapped with the mmap system call. + * Callers must hold down_write() on the mm's mmap_sem for these + */ +void added_exe_file_vma(struct mm_struct *mm) +{ + mm->num_exe_file_vmas++; +} + +void removed_exe_file_vma(struct mm_struct *mm) +{ + mm->num_exe_file_vmas--; + if ((mm->num_exe_file_vmas == 0) && mm->exe_file){ + fput(mm->exe_file); + mm->exe_file = NULL; + } + +} + +void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) +{ + if (new_exe_file) + get_file(new_exe_file); + if (mm->exe_file) + fput(mm->exe_file); + mm->exe_file = new_exe_file; + mm->num_exe_file_vmas = 0; +} + +struct file *get_mm_exe_file(struct mm_struct *mm) +{ + struct file *exe_file; + + /* We need mmap_sem to protect against races with removal of + * VM_EXECUTABLE vmas */ + down_read(&mm->mmap_sem); + exe_file = mm->exe_file; + if (exe_file) + get_file(exe_file); + up_read(&mm->mmap_sem); + return exe_file; +} + +static void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm) +{ + /* It's safe to write the exe_file pointer without exe_file_lock because + * this is called during fork when the task is not yet in /proc */ + newmm->exe_file = get_mm_exe_file(oldmm); +} + /** * get_task_mm - acquire a reference to the task's mm * -- cgit From 6345d24daf0c1fffe6642081d783cdf653ebaa5c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 29 May 2011 11:32:28 -0700 Subject: mm: Fix boot crash in mm_alloc() Thomas Gleixner reports that we now have a boot crash triggered by CONFIG_CPUMASK_OFFSTACK=y: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [] find_next_bit+0x55/0xb0 Call Trace: [] cpumask_any_but+0x2a/0x70 [] flush_tlb_mm+0x2b/0x80 [] pud_populate+0x35/0x50 [] pgd_alloc+0x9a/0xf0 [] mm_init+0xec/0x120 [] mm_alloc+0x53/0xd0 which was introduced by commit de03c72cfce5 ("mm: convert mm->cpu_vm_cpumask into cpumask_var_t"), and is due to wrong ordering of mm_init() vs mm_init_cpumask Thomas wrote a patch to just fix the ordering of initialization, but I hate the new double allocation in the fork path, so I ended up instead doing some more radical surgery to clean it all up. Reported-by: Thomas Gleixner Reported-by: Ingo Molnar Cc: KOSAKI Motohiro Cc: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 42 ++++++++++-------------------------------- 1 file changed, 10 insertions(+), 32 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index ca406d916713..0276c30401a0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -484,20 +484,6 @@ static void mm_init_aio(struct mm_struct *mm) #endif } -int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm) -{ -#ifdef CONFIG_CPUMASK_OFFSTACK - if (!alloc_cpumask_var(&mm->cpu_vm_mask_var, GFP_KERNEL)) - return -ENOMEM; - - if (oldmm) - cpumask_copy(mm_cpumask(mm), mm_cpumask(oldmm)); - else - memset(mm_cpumask(mm), 0, cpumask_size()); -#endif - return 0; -} - static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) { atomic_set(&mm->mm_users, 1); @@ -538,17 +524,8 @@ struct mm_struct * mm_alloc(void) return NULL; memset(mm, 0, sizeof(*mm)); - mm = mm_init(mm, current); - if (!mm) - return NULL; - - if (mm_init_cpumask(mm, NULL)) { - mm_free_pgd(mm); - free_mm(mm); - return NULL; - } - - return mm; + mm_init_cpumask(mm); + return mm_init(mm, current); } /* @@ -559,7 +536,6 @@ struct mm_struct * mm_alloc(void) void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); - free_cpumask_var(mm->cpu_vm_mask_var); mm_free_pgd(mm); destroy_context(mm); mmu_notifier_mm_destroy(mm); @@ -753,6 +729,7 @@ struct mm_struct *dup_mm(struct task_struct *tsk) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); + mm_init_cpumask(mm); /* Initializing for Swap token stuff */ mm->token_priority = 0; @@ -765,9 +742,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk) if (!mm_init(mm, tsk)) goto fail_nomem; - if (mm_init_cpumask(mm, oldmm)) - goto fail_nocpumask; - if (init_new_context(tsk, mm)) goto fail_nocontext; @@ -794,9 +768,6 @@ fail_nomem: return NULL; fail_nocontext: - free_cpumask_var(mm->cpu_vm_mask_var); - -fail_nocpumask: /* * If init_new_context() failed, we cannot use mmput() to free the mm * because it calls destroy_context() @@ -1591,6 +1562,13 @@ void __init proc_caches_init(void) fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + /* + * FIXME! The "sizeof(struct mm_struct)" currently includes the + * whole struct cpumask for the OFFSTACK case. We could change + * this to *only* allocate as much of it as required by the + * maximum number of CPU's we can ever have. The cpumask_allocation + * is at the end of the structure, exactly for that reason. + */ mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); -- cgit