summaryrefslogtreecommitdiff
path: root/kernel/fork.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/fork.c')
-rw-r--r--kernel/fork.c539
1 files changed, 296 insertions, 243 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index 2295fc69717f..be8aa5b98666 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -77,6 +77,7 @@
#include <linux/blkdev.h>
#include <linux/fs_struct.h>
#include <linux/magic.h>
+#include <linux/sched/mm.h>
#include <linux/perf_event.h>
#include <linux/posix-timers.h>
#include <linux/user-return-notifier.h>
@@ -282,8 +283,9 @@ static void free_thread_stack(struct task_struct *tsk)
void thread_stack_cache_init(void)
{
- thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
- THREAD_SIZE, 0, NULL);
+ thread_stack_cache = kmem_cache_create_usercopy("thread_stack",
+ THREAD_SIZE, THREAD_SIZE, 0, 0,
+ THREAD_SIZE, NULL);
BUG_ON(thread_stack_cache == NULL);
}
# endif
@@ -390,6 +392,246 @@ void free_task(struct task_struct *tsk)
}
EXPORT_SYMBOL(free_task);
+#ifdef CONFIG_MMU
+static __latent_entropy int dup_mmap(struct mm_struct *mm,
+ struct mm_struct *oldmm)
+{
+ struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
+ struct rb_node **rb_link, *rb_parent;
+ int retval;
+ unsigned long charge;
+ LIST_HEAD(uf);
+
+ uprobe_start_dup_mmap();
+ if (down_write_killable(&oldmm->mmap_sem)) {
+ retval = -EINTR;
+ goto fail_uprobe_end;
+ }
+ flush_cache_dup_mm(oldmm);
+ uprobe_dup_mmap(oldmm, mm);
+ /*
+ * Not linked in yet - no deadlock potential:
+ */
+ down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
+
+ /* No ordering required: file already has been exposed. */
+ RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+
+ mm->total_vm = oldmm->total_vm;
+ mm->data_vm = oldmm->data_vm;
+ mm->exec_vm = oldmm->exec_vm;
+ mm->stack_vm = oldmm->stack_vm;
+
+ rb_link = &mm->mm_rb.rb_node;
+ rb_parent = NULL;
+ pprev = &mm->mmap;
+ retval = ksm_fork(mm, oldmm);
+ if (retval)
+ goto out;
+ retval = khugepaged_fork(mm, oldmm);
+ if (retval)
+ goto out;
+
+ prev = NULL;
+ for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
+ struct file *file;
+
+ if (mpnt->vm_flags & VM_DONTCOPY) {
+ vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
+ continue;
+ }
+ charge = 0;
+ if (mpnt->vm_flags & VM_ACCOUNT) {
+ unsigned long len = vma_pages(mpnt);
+
+ if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
+ goto fail_nomem;
+ charge = len;
+ }
+ tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+ if (!tmp)
+ goto fail_nomem;
+ *tmp = *mpnt;
+ INIT_LIST_HEAD(&tmp->anon_vma_chain);
+ retval = vma_dup_policy(mpnt, tmp);
+ if (retval)
+ goto fail_nomem_policy;
+ tmp->vm_mm = mm;
+ retval = dup_userfaultfd(tmp, &uf);
+ if (retval)
+ goto fail_nomem_anon_vma_fork;
+ if (tmp->vm_flags & VM_WIPEONFORK) {
+ /* VM_WIPEONFORK gets a clean slate in the child. */
+ tmp->anon_vma = NULL;
+ if (anon_vma_prepare(tmp))
+ goto fail_nomem_anon_vma_fork;
+ } else if (anon_vma_fork(tmp, mpnt))
+ goto fail_nomem_anon_vma_fork;
+ tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
+ tmp->vm_next = tmp->vm_prev = NULL;
+ file = tmp->vm_file;
+ if (file) {
+ struct inode *inode = file_inode(file);
+ struct address_space *mapping = file->f_mapping;
+
+ get_file(file);
+ if (tmp->vm_flags & VM_DENYWRITE)
+ atomic_dec(&inode->i_writecount);
+ i_mmap_lock_write(mapping);
+ if (tmp->vm_flags & VM_SHARED)
+ atomic_inc(&mapping->i_mmap_writable);
+ flush_dcache_mmap_lock(mapping);
+ /* insert tmp into the share list, just after mpnt */
+ vma_interval_tree_insert_after(tmp, mpnt,
+ &mapping->i_mmap);
+ flush_dcache_mmap_unlock(mapping);
+ i_mmap_unlock_write(mapping);
+ }
+
+ /*
+ * Clear hugetlb-related page reserves for children. This only
+ * affects MAP_PRIVATE mappings. Faults generated by the child
+ * are not guaranteed to succeed, even if read-only
+ */
+ if (is_vm_hugetlb_page(tmp))
+ reset_vma_resv_huge_pages(tmp);
+
+ /*
+ * Link in the new vma and copy the page table entries.
+ */
+ *pprev = tmp;
+ pprev = &tmp->vm_next;
+ tmp->vm_prev = prev;
+ prev = tmp;
+
+ __vma_link_rb(mm, tmp, rb_link, rb_parent);
+ rb_link = &tmp->vm_rb.rb_right;
+ rb_parent = &tmp->vm_rb;
+
+ mm->map_count++;
+ if (!(tmp->vm_flags & VM_WIPEONFORK))
+ retval = copy_page_range(mm, oldmm, mpnt);
+
+ if (tmp->vm_ops && tmp->vm_ops->open)
+ tmp->vm_ops->open(tmp);
+
+ if (retval)
+ goto out;
+ }
+ /* a new mm has just been created */
+ arch_dup_mmap(oldmm, mm);
+ retval = 0;
+out:
+ up_write(&mm->mmap_sem);
+ flush_tlb_mm(oldmm);
+ up_write(&oldmm->mmap_sem);
+ dup_userfaultfd_complete(&uf);
+fail_uprobe_end:
+ uprobe_end_dup_mmap();
+ return retval;
+fail_nomem_anon_vma_fork:
+ mpol_put(vma_policy(tmp));
+fail_nomem_policy:
+ kmem_cache_free(vm_area_cachep, tmp);
+fail_nomem:
+ retval = -ENOMEM;
+ vm_unacct_memory(charge);
+ goto out;
+}
+
+static inline int mm_alloc_pgd(struct mm_struct *mm)
+{
+ mm->pgd = pgd_alloc(mm);
+ if (unlikely(!mm->pgd))
+ return -ENOMEM;
+ return 0;
+}
+
+static inline void mm_free_pgd(struct mm_struct *mm)
+{
+ pgd_free(mm, mm->pgd);
+}
+#else
+static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+ down_write(&oldmm->mmap_sem);
+ RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+ up_write(&oldmm->mmap_sem);
+ return 0;
+}
+#define mm_alloc_pgd(mm) (0)
+#define mm_free_pgd(mm)
+#endif /* CONFIG_MMU */
+
+static void check_mm(struct mm_struct *mm)
+{
+ int i;
+
+ for (i = 0; i < NR_MM_COUNTERS; i++) {
+ long x = atomic_long_read(&mm->rss_stat.count[i]);
+
+ if (unlikely(x))
+ printk(KERN_ALERT "BUG: Bad rss-counter state "
+ "mm:%p idx:%d val:%ld\n", mm, i, x);
+ }
+
+ if (mm_pgtables_bytes(mm))
+ pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n",
+ mm_pgtables_bytes(mm));
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
+ VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
+#endif
+}
+
+#define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL))
+#define free_mm(mm) (kmem_cache_free(mm_cachep, (mm)))
+
+/*
+ * Called when the last reference to the mm
+ * is dropped: either by a lazy thread or by
+ * mmput. Free the page directory and the mm.
+ */
+static void __mmdrop(struct mm_struct *mm)
+{
+ BUG_ON(mm == &init_mm);
+ mm_free_pgd(mm);
+ destroy_context(mm);
+ hmm_mm_destroy(mm);
+ mmu_notifier_mm_destroy(mm);
+ check_mm(mm);
+ put_user_ns(mm->user_ns);
+ free_mm(mm);
+}
+
+void mmdrop(struct mm_struct *mm)
+{
+ /*
+ * The implicit full barrier implied by atomic_dec_and_test() is
+ * required by the membarrier system call before returning to
+ * user-space, after storing to rq->curr.
+ */
+ if (unlikely(atomic_dec_and_test(&mm->mm_count)))
+ __mmdrop(mm);
+}
+EXPORT_SYMBOL_GPL(mmdrop);
+
+static void mmdrop_async_fn(struct work_struct *work)
+{
+ struct mm_struct *mm;
+
+ mm = container_of(work, struct mm_struct, async_put_work);
+ __mmdrop(mm);
+}
+
+static void mmdrop_async(struct mm_struct *mm)
+{
+ if (unlikely(atomic_dec_and_test(&mm->mm_count))) {
+ INIT_WORK(&mm->async_put_work, mmdrop_async_fn);
+ schedule_work(&mm->async_put_work);
+ }
+}
+
static inline void free_signal_struct(struct signal_struct *sig)
{
taskstats_tgid_free(sig);
@@ -457,6 +699,21 @@ static void set_max_threads(unsigned int max_threads_suggested)
int arch_task_struct_size __read_mostly;
#endif
+static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
+{
+ /* Fetch thread_struct whitelist for the architecture. */
+ arch_thread_struct_whitelist(offset, size);
+
+ /*
+ * Handle zero-sized whitelist or empty thread_struct, otherwise
+ * adjust offset to position of thread_struct in task_struct.
+ */
+ if (unlikely(*size == 0))
+ *offset = 0;
+ else
+ *offset += offsetof(struct task_struct, thread);
+}
+
void __init fork_init(void)
{
int i;
@@ -465,11 +722,14 @@ void __init fork_init(void)
#define ARCH_MIN_TASKALIGN 0
#endif
int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN);
+ unsigned long useroffset, usersize;
/* create a slab on which task_structs can be allocated */
- task_struct_cachep = kmem_cache_create("task_struct",
+ task_struct_whitelist(&useroffset, &usersize);
+ task_struct_cachep = kmem_cache_create_usercopy("task_struct",
arch_task_struct_size, align,
- SLAB_PANIC|SLAB_ACCOUNT, NULL);
+ SLAB_PANIC|SLAB_ACCOUNT,
+ useroffset, usersize, NULL);
#endif
/* do the arch specific task caches init */
@@ -594,181 +854,8 @@ free_tsk:
return NULL;
}
-#ifdef CONFIG_MMU
-static __latent_entropy int dup_mmap(struct mm_struct *mm,
- struct mm_struct *oldmm)
-{
- struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
- struct rb_node **rb_link, *rb_parent;
- int retval;
- unsigned long charge;
- LIST_HEAD(uf);
-
- uprobe_start_dup_mmap();
- if (down_write_killable(&oldmm->mmap_sem)) {
- retval = -EINTR;
- goto fail_uprobe_end;
- }
- flush_cache_dup_mm(oldmm);
- uprobe_dup_mmap(oldmm, mm);
- /*
- * Not linked in yet - no deadlock potential:
- */
- down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
-
- /* No ordering required: file already has been exposed. */
- RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
-
- mm->total_vm = oldmm->total_vm;
- mm->data_vm = oldmm->data_vm;
- mm->exec_vm = oldmm->exec_vm;
- mm->stack_vm = oldmm->stack_vm;
-
- rb_link = &mm->mm_rb.rb_node;
- rb_parent = NULL;
- pprev = &mm->mmap;
- retval = ksm_fork(mm, oldmm);
- if (retval)
- goto out;
- retval = khugepaged_fork(mm, oldmm);
- if (retval)
- goto out;
-
- prev = NULL;
- for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
- struct file *file;
-
- if (mpnt->vm_flags & VM_DONTCOPY) {
- vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
- continue;
- }
- charge = 0;
- if (mpnt->vm_flags & VM_ACCOUNT) {
- unsigned long len = vma_pages(mpnt);
-
- if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
- goto fail_nomem;
- charge = len;
- }
- tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
- if (!tmp)
- goto fail_nomem;
- *tmp = *mpnt;
- INIT_LIST_HEAD(&tmp->anon_vma_chain);
- retval = vma_dup_policy(mpnt, tmp);
- if (retval)
- goto fail_nomem_policy;
- tmp->vm_mm = mm;
- retval = dup_userfaultfd(tmp, &uf);
- if (retval)
- goto fail_nomem_anon_vma_fork;
- if (tmp->vm_flags & VM_WIPEONFORK) {
- /* VM_WIPEONFORK gets a clean slate in the child. */
- tmp->anon_vma = NULL;
- if (anon_vma_prepare(tmp))
- goto fail_nomem_anon_vma_fork;
- } else if (anon_vma_fork(tmp, mpnt))
- goto fail_nomem_anon_vma_fork;
- tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
- tmp->vm_next = tmp->vm_prev = NULL;
- file = tmp->vm_file;
- if (file) {
- struct inode *inode = file_inode(file);
- struct address_space *mapping = file->f_mapping;
-
- get_file(file);
- if (tmp->vm_flags & VM_DENYWRITE)
- atomic_dec(&inode->i_writecount);
- i_mmap_lock_write(mapping);
- if (tmp->vm_flags & VM_SHARED)
- atomic_inc(&mapping->i_mmap_writable);
- flush_dcache_mmap_lock(mapping);
- /* insert tmp into the share list, just after mpnt */
- vma_interval_tree_insert_after(tmp, mpnt,
- &mapping->i_mmap);
- flush_dcache_mmap_unlock(mapping);
- i_mmap_unlock_write(mapping);
- }
-
- /*
- * Clear hugetlb-related page reserves for children. This only
- * affects MAP_PRIVATE mappings. Faults generated by the child
- * are not guaranteed to succeed, even if read-only
- */
- if (is_vm_hugetlb_page(tmp))
- reset_vma_resv_huge_pages(tmp);
-
- /*
- * Link in the new vma and copy the page table entries.
- */
- *pprev = tmp;
- pprev = &tmp->vm_next;
- tmp->vm_prev = prev;
- prev = tmp;
-
- __vma_link_rb(mm, tmp, rb_link, rb_parent);
- rb_link = &tmp->vm_rb.rb_right;
- rb_parent = &tmp->vm_rb;
-
- mm->map_count++;
- if (!(tmp->vm_flags & VM_WIPEONFORK))
- retval = copy_page_range(mm, oldmm, mpnt);
-
- if (tmp->vm_ops && tmp->vm_ops->open)
- tmp->vm_ops->open(tmp);
-
- if (retval)
- goto out;
- }
- /* a new mm has just been created */
- retval = arch_dup_mmap(oldmm, mm);
-out:
- up_write(&mm->mmap_sem);
- flush_tlb_mm(oldmm);
- up_write(&oldmm->mmap_sem);
- dup_userfaultfd_complete(&uf);
-fail_uprobe_end:
- uprobe_end_dup_mmap();
- return retval;
-fail_nomem_anon_vma_fork:
- mpol_put(vma_policy(tmp));
-fail_nomem_policy:
- kmem_cache_free(vm_area_cachep, tmp);
-fail_nomem:
- retval = -ENOMEM;
- vm_unacct_memory(charge);
- goto out;
-}
-
-static inline int mm_alloc_pgd(struct mm_struct *mm)
-{
- mm->pgd = pgd_alloc(mm);
- if (unlikely(!mm->pgd))
- return -ENOMEM;
- return 0;
-}
-
-static inline void mm_free_pgd(struct mm_struct *mm)
-{
- pgd_free(mm, mm->pgd);
-}
-#else
-static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
-{
- down_write(&oldmm->mmap_sem);
- RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
- up_write(&oldmm->mmap_sem);
- return 0;
-}
-#define mm_alloc_pgd(mm) (0)
-#define mm_free_pgd(mm)
-#endif /* CONFIG_MMU */
-
__cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock);
-#define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL))
-#define free_mm(mm) (kmem_cache_free(mm_cachep, (mm)))
-
static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT;
static int __init coredump_filter_setup(char *s)
@@ -858,27 +945,6 @@ fail_nopgd:
return NULL;
}
-static void check_mm(struct mm_struct *mm)
-{
- int i;
-
- for (i = 0; i < NR_MM_COUNTERS; i++) {
- long x = atomic_long_read(&mm->rss_stat.count[i]);
-
- if (unlikely(x))
- printk(KERN_ALERT "BUG: Bad rss-counter state "
- "mm:%p idx:%d val:%ld\n", mm, i, x);
- }
-
- if (mm_pgtables_bytes(mm))
- pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n",
- mm_pgtables_bytes(mm));
-
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
- VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
-#endif
-}
-
/*
* Allocate and initialize an mm_struct.
*/
@@ -894,24 +960,6 @@ struct mm_struct *mm_alloc(void)
return mm_init(mm, current, current_user_ns());
}
-/*
- * Called when the last reference to the mm
- * is dropped: either by a lazy thread or by
- * mmput. Free the page directory and the mm.
- */
-void __mmdrop(struct mm_struct *mm)
-{
- BUG_ON(mm == &init_mm);
- mm_free_pgd(mm);
- destroy_context(mm);
- hmm_mm_destroy(mm);
- mmu_notifier_mm_destroy(mm);
- check_mm(mm);
- put_user_ns(mm->user_ns);
- free_mm(mm);
-}
-EXPORT_SYMBOL_GPL(__mmdrop);
-
static inline void __mmput(struct mm_struct *mm)
{
VM_BUG_ON(atomic_read(&mm->mm_users));
@@ -1544,6 +1592,10 @@ static __latent_entropy struct task_struct *copy_process(
int retval;
struct task_struct *p;
+ /*
+ * Don't allow sharing the root directory with processes in a different
+ * namespace
+ */
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
@@ -2019,6 +2071,8 @@ long _do_fork(unsigned long clone_flags,
int __user *child_tidptr,
unsigned long tls)
{
+ struct completion vfork;
+ struct pid *pid;
struct task_struct *p;
int trace = 0;
long nr;
@@ -2044,43 +2098,40 @@ long _do_fork(unsigned long clone_flags,
p = copy_process(clone_flags, stack_start, stack_size,
child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
add_latent_entropy();
+
+ if (IS_ERR(p))
+ return PTR_ERR(p);
+
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
- if (!IS_ERR(p)) {
- struct completion vfork;
- struct pid *pid;
+ trace_sched_process_fork(current, p);
- trace_sched_process_fork(current, p);
+ pid = get_task_pid(p, PIDTYPE_PID);
+ nr = pid_vnr(pid);
- pid = get_task_pid(p, PIDTYPE_PID);
- nr = pid_vnr(pid);
+ if (clone_flags & CLONE_PARENT_SETTID)
+ put_user(nr, parent_tidptr);
- if (clone_flags & CLONE_PARENT_SETTID)
- put_user(nr, parent_tidptr);
-
- if (clone_flags & CLONE_VFORK) {
- p->vfork_done = &vfork;
- init_completion(&vfork);
- get_task_struct(p);
- }
+ if (clone_flags & CLONE_VFORK) {
+ p->vfork_done = &vfork;
+ init_completion(&vfork);
+ get_task_struct(p);
+ }
- wake_up_new_task(p);
+ wake_up_new_task(p);
- /* forking complete and child started to run, tell ptracer */
- if (unlikely(trace))
- ptrace_event_pid(trace, pid);
+ /* forking complete and child started to run, tell ptracer */
+ if (unlikely(trace))
+ ptrace_event_pid(trace, pid);
- if (clone_flags & CLONE_VFORK) {
- if (!wait_for_vfork_done(p, &vfork))
- ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
- }
-
- put_pid(pid);
- } else {
- nr = PTR_ERR(p);
+ if (clone_flags & CLONE_VFORK) {
+ if (!wait_for_vfork_done(p, &vfork))
+ ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
}
+
+ put_pid(pid);
return nr;
}
@@ -2224,9 +2275,11 @@ void __init proc_caches_init(void)
* 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",
+ mm_cachep = kmem_cache_create_usercopy("mm_struct",
sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
+ offsetof(struct mm_struct, saved_auxv),
+ sizeof_field(struct mm_struct, saved_auxv),
NULL);
vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT);
mmap_init();