unsigned long totalpages = totalram_pages + total_swap_pages;
unsigned long points = 0;
- read_lock(&tasklist_lock);
- if (pid_alive(task))
- points = oom_badness(task, NULL, NULL, totalpages) *
- 1000 / totalpages;
- read_unlock(&tasklist_lock);
+ points = oom_badness(task, NULL, NULL, totalpages) *
+ 1000 / totalpages;
seq_printf(m, "%lu\n", points);
return 0;
char buffer[PROC_NUMBUF];
int oom_adj = OOM_ADJUST_MIN;
size_t len;
- unsigned long flags;
if (!task)
return -ESRCH;
- if (lock_task_sighand(task, &flags)) {
- if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
- oom_adj = OOM_ADJUST_MAX;
- else
- oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
- OOM_SCORE_ADJ_MAX;
- unlock_task_sighand(task, &flags);
- }
+ if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
+ oom_adj = OOM_ADJUST_MAX;
+ else
+ oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
+ OOM_SCORE_ADJ_MAX;
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
+static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
+{
+ static DEFINE_MUTEX(oom_adj_mutex);
+ struct mm_struct *mm = NULL;
+ struct task_struct *task;
+ int err = 0;
+
+ task = get_proc_task(file_inode(file));
+ if (!task)
+ return -ESRCH;
+
+ mutex_lock(&oom_adj_mutex);
+ if (legacy) {
+ if (oom_adj < task->signal->oom_score_adj &&
+ !capable(CAP_SYS_RESOURCE)) {
+ err = -EACCES;
+ goto err_unlock;
+ }
+ /*
+ * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
+ * /proc/pid/oom_score_adj instead.
+ */
+ pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
+ current->comm, task_pid_nr(current), task_pid_nr(task),
+ task_pid_nr(task));
+ } else {
+ if ((short)oom_adj < task->signal->oom_score_adj_min &&
+ !capable(CAP_SYS_RESOURCE)) {
+ err = -EACCES;
+ goto err_unlock;
+ }
+ }
+
+ /*
+ * Make sure we will check other processes sharing the mm if this is
+ * not vfrok which wants its own oom_score_adj.
+ * pin the mm so it doesn't go away and get reused after task_unlock
+ */
+ if (!task->vfork_done) {
+ struct task_struct *p = find_lock_task_mm(task);
+
+ if (p) {
+ if (atomic_read(&p->mm->mm_users) > 1) {
+ mm = p->mm;
+ atomic_inc(&mm->mm_count);
+ }
+ task_unlock(p);
+ }
+ }
+
+ task->signal->oom_score_adj = oom_adj;
+ if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
+ task->signal->oom_score_adj_min = (short)oom_adj;
+ trace_oom_score_adj_update(task);
+
+ if (mm) {
+ struct task_struct *p;
+
+ rcu_read_lock();
+ for_each_process(p) {
+ if (same_thread_group(task, p))
+ continue;
+
+ /* do not touch kernel threads or the global init */
+ if (p->flags & PF_KTHREAD || is_global_init(p))
+ continue;
+
+ task_lock(p);
+ if (!p->vfork_done && process_shares_mm(p, mm)) {
+ pr_info("updating oom_score_adj for %d (%s) from %d to %d because it shares mm with %d (%s). Report if this is unexpected.\n",
+ task_pid_nr(p), p->comm,
+ p->signal->oom_score_adj, oom_adj,
+ task_pid_nr(task), task->comm);
+ p->signal->oom_score_adj = oom_adj;
+ if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
+ p->signal->oom_score_adj_min = (short)oom_adj;
+ }
+ task_unlock(p);
+ }
+ rcu_read_unlock();
+ mmdrop(mm);
+ }
+err_unlock:
+ mutex_unlock(&oom_adj_mutex);
+ put_task_struct(task);
+ return err;
+}
+
/*
* /proc/pid/oom_adj exists solely for backwards compatibility with previous
* kernels. The effective policy is defined by oom_score_adj, which has a
static ssize_t oom_adj_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
- struct task_struct *task;
char buffer[PROC_NUMBUF];
int oom_adj;
- unsigned long flags;
int err;
memset(buffer, 0, sizeof(buffer));
goto out;
}
- task = get_proc_task(file_inode(file));
- if (!task) {
- err = -ESRCH;
- goto out;
- }
-
- task_lock(task);
- if (!task->mm) {
- err = -EINVAL;
- goto err_task_lock;
- }
-
- if (!lock_task_sighand(task, &flags)) {
- err = -ESRCH;
- goto err_task_lock;
- }
-
/*
* Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
* value is always attainable.
else
oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
- if (oom_adj < task->signal->oom_score_adj &&
- !capable(CAP_SYS_RESOURCE)) {
- err = -EACCES;
- goto err_sighand;
- }
-
- /*
- * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
- * /proc/pid/oom_score_adj instead.
- */
- pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
- current->comm, task_pid_nr(current), task_pid_nr(task),
- task_pid_nr(task));
-
- task->signal->oom_score_adj = oom_adj;
- trace_oom_score_adj_update(task);
-err_sighand:
- unlock_task_sighand(task, &flags);
-err_task_lock:
- task_unlock(task);
- put_task_struct(task);
+ err = __set_oom_adj(file, oom_adj, true);
out:
return err < 0 ? err : count;
}
struct task_struct *task = get_proc_task(file_inode(file));
char buffer[PROC_NUMBUF];
short oom_score_adj = OOM_SCORE_ADJ_MIN;
- unsigned long flags;
size_t len;
if (!task)
return -ESRCH;
- if (lock_task_sighand(task, &flags)) {
- oom_score_adj = task->signal->oom_score_adj;
- unlock_task_sighand(task, &flags);
- }
+ oom_score_adj = task->signal->oom_score_adj;
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj);
return simple_read_from_buffer(buf, count, ppos, buffer, len);
static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
- struct task_struct *task;
char buffer[PROC_NUMBUF];
- unsigned long flags;
int oom_score_adj;
int err;
goto out;
}
- task = get_proc_task(file_inode(file));
- if (!task) {
- err = -ESRCH;
- goto out;
- }
-
- task_lock(task);
- if (!task->mm) {
- err = -EINVAL;
- goto err_task_lock;
- }
-
- if (!lock_task_sighand(task, &flags)) {
- err = -ESRCH;
- goto err_task_lock;
- }
-
- if ((short)oom_score_adj < task->signal->oom_score_adj_min &&
- !capable(CAP_SYS_RESOURCE)) {
- err = -EACCES;
- goto err_sighand;
- }
-
- task->signal->oom_score_adj = (short)oom_score_adj;
- if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
- task->signal->oom_score_adj_min = (short)oom_score_adj;
- trace_oom_score_adj_update(task);
-
-err_sighand:
- unlock_task_sighand(task, &flags);
-err_task_lock:
- task_unlock(task);
- put_task_struct(task);
+ err = __set_oom_adj(file, oom_score_adj, false);
out:
return err < 0 ? err : count;
}
static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
{
struct task_struct *task;
- struct mm_struct *mm;
struct file *exe_file;
task = get_proc_task(d_inode(dentry));
if (!task)
return -ENOENT;
- mm = get_task_mm(task);
+ exe_file = get_task_exe_file(task);
put_task_struct(task);
- if (!mm)
- return -ENOENT;
- exe_file = get_mm_exe_file(mm);
- mmput(mm);
if (exe_file) {
*exe_path = exe_file->f_path;
path_get(&exe_file->f_path);
child = d_hash_and_lookup(dir, &qname);
if (!child) {
- child = d_alloc(dir, &qname);
- if (!child)
- goto end_instantiate;
- if (instantiate(d_inode(dir), child, task, ptr) < 0) {
- dput(child);
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+ child = d_alloc_parallel(dir, &qname, &wq);
+ if (IS_ERR(child))
goto end_instantiate;
+ if (d_in_lookup(child)) {
+ int err = instantiate(d_inode(dir), child, task, ptr);
+ d_lookup_done(child);
+ if (err < 0) {
+ dput(child);
+ goto end_instantiate;
+ }
}
}
inode = d_inode(child);
static const struct file_operations proc_map_files_operations = {
.read = generic_read_dir,
- .iterate = proc_map_files_readdir,
- .llseek = default_llseek,
+ .iterate_shared = proc_map_files_readdir,
+ .llseek = generic_file_llseek,
};
#ifdef CONFIG_CHECKPOINT_RESTORE
static const struct file_operations proc_attr_dir_operations = {
.read = generic_read_dir,
- .iterate = proc_attr_dir_readdir,
- .llseek = default_llseek,
+ .iterate_shared = proc_attr_dir_readdir,
+ .llseek = generic_file_llseek,
};
static struct dentry *proc_attr_dir_lookup(struct inode *dir,
static const struct file_operations proc_tgid_base_operations = {
.read = generic_read_dir,
- .iterate = proc_tgid_base_readdir,
- .llseek = default_llseek,
+ .iterate_shared = proc_tgid_base_readdir,
+ .llseek = generic_file_llseek,
};
static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
return 0;
}
+/*
+ * proc_tid_comm_permission is a special permission function exclusively
+ * used for the node /proc/<pid>/task/<tid>/comm.
+ * It bypasses generic permission checks in the case where a task of the same
+ * task group attempts to access the node.
+ * The rationale behind this is that glibc and bionic access this node for
+ * cross thread naming (pthread_set/getname_np(!self)). However, if
+ * PR_SET_DUMPABLE gets set to 0 this node among others becomes uid=0 gid=0,
+ * which locks out the cross thread naming implementation.
+ * This function makes sure that the node is always accessible for members of
+ * same thread group.
+ */
+static int proc_tid_comm_permission(struct inode *inode, int mask)
+{
+ bool is_same_tgroup;
+ struct task_struct *task;
+
+ task = get_proc_task(inode);
+ if (!task)
+ return -ESRCH;
+ is_same_tgroup = same_thread_group(current, task);
+ put_task_struct(task);
+
+ if (likely(is_same_tgroup && !(mask & MAY_EXEC))) {
+ /* This file (/proc/<pid>/task/<tid>/comm) can always be
+ * read or written by the members of the corresponding
+ * thread group.
+ */
+ return 0;
+ }
+
+ return generic_permission(inode, mask);
+}
+
+static const struct inode_operations proc_tid_comm_inode_operations = {
+ .permission = proc_tid_comm_permission,
+};
+
/*
* Tasks
*/
#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations),
#endif
- REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
+ NOD("comm", S_IFREG|S_IRUGO|S_IWUSR,
+ &proc_tid_comm_inode_operations,
+ &proc_pid_set_comm_operations, {}),
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
ONE("syscall", S_IRUSR, proc_pid_syscall),
#endif
static const struct file_operations proc_tid_base_operations = {
.read = generic_read_dir,
- .iterate = proc_tid_base_readdir,
- .llseek = default_llseek,
+ .iterate_shared = proc_tid_base_readdir,
+ .llseek = generic_file_llseek,
};
static const struct inode_operations proc_tid_base_inode_operations = {
static const struct file_operations proc_task_operations = {
.read = generic_read_dir,
- .iterate = proc_task_readdir,
- .llseek = default_llseek,
+ .iterate_shared = proc_task_readdir,
+ .llseek = generic_file_llseek,
};
#define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0))
#endif
+#ifndef page_to_virt
+#define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x)))
+#endif
+
/*
* To prevent common memory management code establishing
* a zero page mapping on a read fault.
* is set (which is also implied by
* VM_FAULT_ERROR).
*/
- /* for ->map_pages() only */
- pgoff_t max_pgoff; /* map pages for offset from pgoff till
- * max_pgoff inclusive */
- pte_t *pte; /* pte entry associated with ->pgoff */
+ void *entry; /* ->fault handler can alternatively
+ * return locked DAX entry. In that
+ * case handler should return
+ * VM_FAULT_DAX_LOCKED and fill in
+ * entry here.
+ */
+};
+
+/*
+ * Page fault context: passes though page fault handler instead of endless list
+ * of function arguments.
+ */
+struct fault_env {
+ struct vm_area_struct *vma; /* Target VMA */
+ unsigned long address; /* Faulting virtual address */
+ unsigned int flags; /* FAULT_FLAG_xxx flags */
+ pmd_t *pmd; /* Pointer to pmd entry matching
+ * the 'address'
+ */
+ pte_t *pte; /* Pointer to pte entry matching
+ * the 'address'. NULL if the page
+ * table hasn't been allocated.
+ */
+ spinlock_t *ptl; /* Page table lock.
+ * Protects pte page table if 'pte'
+ * is not NULL, otherwise pmd.
+ */
+ pgtable_t prealloc_pte; /* Pre-allocated pte page table.
+ * vm_ops->map_pages() calls
+ * alloc_set_pte() from atomic context.
+ * do_fault_around() pre-allocates
+ * page table to avoid allocation from
+ * atomic context.
+ */
};
/*
int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
int (*pmd_fault)(struct vm_area_struct *, unsigned long address,
pmd_t *, unsigned int flags);
- void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf);
+ void (*map_pages)(struct fault_env *fe,
+ pgoff_t start_pgoff, pgoff_t end_pgoff);
/* notification that a previously read-only page is about to become
* writable, if an error is returned it will cause a SIGBUS */
* On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there
* is no special casing required.
*/
-static inline int is_vmalloc_addr(const void *x)
+static inline bool is_vmalloc_addr(const void *x)
{
#ifdef CONFIG_MMU
unsigned long addr = (unsigned long)x;
return addr >= VMALLOC_START && addr < VMALLOC_END;
#else
- return 0;
+ return false;
#endif
}
#ifdef CONFIG_MMU
static inline int compound_mapcount(struct page *page)
{
- if (!PageCompound(page))
- return 0;
+ VM_BUG_ON_PAGE(!PageCompound(page), page);
page = compound_head(page);
return atomic_read(compound_mapcount_ptr(page)) + 1;
}
void put_pages_list(struct list_head *pages);
void split_page(struct page *page, unsigned int order);
-int split_free_page(struct page *page);
/*
* Compound pages have a destructor function. Provide a
return pte;
}
-void do_set_pte(struct vm_area_struct *vma, unsigned long address,
- struct page *page, pte_t *pte, bool write, bool anon);
+int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg,
+ struct page *page);
#endif
/*
page = compound_head(page);
/*
* Getting a normal page or the head of a compound page
- * requires to already have an elevated page->_count.
+ * requires to already have an elevated page->_refcount.
*/
VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page);
page_ref_inc(page);
static inline void page_cpupid_reset_last(struct page *page)
{
- int cpupid = (1 << LAST_CPUPID_SHIFT) - 1;
-
- page->flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT);
- page->flags |= (cpupid & LAST_CPUPID_MASK) << LAST_CPUPID_PGSHIFT;
+ page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT;
}
#endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */
#else /* !CONFIG_NUMA_BALANCING */
return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
}
+static inline pg_data_t *page_pgdat(const struct page *page)
+{
+ return NODE_DATA(page_to_nid(page));
+}
+
#ifdef SECTION_IN_PAGE_FLAGS
static inline void set_page_section(struct page *page, unsigned long section)
{
{
return page->mem_cgroup;
}
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ return READ_ONCE(page->mem_cgroup);
+}
#else
static inline struct mem_cgroup *page_memcg(struct page *page)
{
return NULL;
}
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ return NULL;
+}
#endif
/*
static __always_inline void *lowmem_page_address(const struct page *page)
{
- return __va(PFN_PHYS(page_to_pfn(page)));
+ return page_to_virt(page);
}
#if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL)
return page->index;
}
-/*
- * Return true if this page is mapped into pagetables.
- * For compound page it returns true if any subpage of compound page is mapped.
- */
-static inline bool page_mapped(struct page *page)
-{
- int i;
- if (likely(!PageCompound(page)))
- return atomic_read(&page->_mapcount) >= 0;
- page = compound_head(page);
- if (atomic_read(compound_mapcount_ptr(page)) >= 0)
- return true;
- if (PageHuge(page))
- return false;
- for (i = 0; i < hpage_nr_pages(page); i++) {
- if (atomic_read(&page[i]._mapcount) >= 0)
- return true;
- }
- return false;
-}
+bool page_mapped(struct page *page);
+struct address_space *page_mapping(struct page *page);
/*
* Return true only if the page has been allocated with
#define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */
#define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */
#define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */
+#define VM_FAULT_DAX_LOCKED 0x1000 /* ->fault has locked DAX entry */
#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
int invalidate_inode_page(struct page *page);
#ifdef CONFIG_MMU
-extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
- unsigned long address, unsigned int flags);
+extern int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
+ unsigned int flags);
extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
unsigned long address, unsigned int fault_flags,
bool *unlocked);
#else
-static inline int handle_mm_fault(struct mm_struct *mm,
- struct vm_area_struct *vma, unsigned long address,
- unsigned int flags)
+static inline int handle_mm_fault(struct vm_area_struct *vma,
+ unsigned long address, unsigned int flags)
{
/* should never happen if there's no MMU */
BUG();
extern void adjust_managed_page_count(struct page *page, long count);
extern void mem_init_print_info(const char *str);
-extern void reserve_bootmem_region(unsigned long start, unsigned long end);
+extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end);
/* Free the reserved page into the buddy system, so it gets managed. */
static inline void __free_reserved_page(struct page *page)
extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
extern struct file *get_mm_exe_file(struct mm_struct *mm);
+ extern struct file *get_task_exe_file(struct task_struct *task);
extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages);
extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages);
#endif
/* These take the mm semaphore themselves */
-extern unsigned long vm_brk(unsigned long, unsigned long);
+extern int __must_check vm_brk(unsigned long, unsigned long);
extern int vm_munmap(unsigned long, size_t);
-extern unsigned long vm_mmap(struct file *, unsigned long,
+extern unsigned long __must_check vm_mmap(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
/* generic vm_area_ops exported for stackable file systems */
extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
-extern void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf);
+extern void filemap_map_pages(struct fault_env *fe,
+ pgoff_t start_pgoff, pgoff_t end_pgoff);
extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
/* mm/page-writeback.c */
}
#endif /* __HAVE_ARCH_GATE_AREA */
+extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm);
+
#ifdef CONFIG_SYSCTL
extern int sysctl_drop_caches;
int drop_caches_sysctl_handler(struct ctl_table *, int,
return false;
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ return false;
+
return test_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
}
#else
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
+ #include <linux/file.h>
#include <linux/kernel.h>
#include <linux/audit.h>
#include <linux/kthread.h>
inode_unlock(d_backing_inode(parent->dentry));
if (d_is_positive(d)) {
/* update watch filter fields */
- watch->dev = d_backing_inode(d)->i_sb->s_dev;
+ watch->dev = d->d_sb->s_dev;
watch->ino = d_backing_inode(d)->i_ino;
}
dput(d);
unsigned long ino;
dev_t dev;
- rcu_read_lock();
- exe_file = rcu_dereference(tsk->mm->exe_file);
+ exe_file = get_task_exe_file(tsk);
+ if (!exe_file)
+ return 0;
ino = exe_file->f_inode->i_ino;
dev = exe_file->f_inode->i_sb->s_dev;
- rcu_read_unlock();
+ fput(exe_file);
return audit_mark_compare(mark, ino, dev);
}
}
#endif
-void __weak arch_release_thread_info(struct thread_info *ti)
+void __weak arch_release_thread_stack(unsigned long *stack)
{
}
-#ifndef CONFIG_ARCH_THREAD_INFO_ALLOCATOR
+#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
/*
* Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
* kmemcache based allocator.
*/
# if THREAD_SIZE >= PAGE_SIZE
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
- struct page *page = alloc_kmem_pages_node(node, THREADINFO_GFP,
- THREAD_SIZE_ORDER);
-
- if (page)
- memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
- 1 << THREAD_SIZE_ORDER);
+ struct page *page = alloc_pages_node(node, THREADINFO_GFP,
+ THREAD_SIZE_ORDER);
return page ? page_address(page) : NULL;
}
-static inline void free_thread_info(struct thread_info *ti)
+static inline void free_thread_stack(unsigned long *stack)
{
- struct page *page = virt_to_page(ti);
-
- memcg_kmem_update_page_stat(page, MEMCG_KERNEL_STACK,
- -(1 << THREAD_SIZE_ORDER));
- __free_kmem_pages(page, THREAD_SIZE_ORDER);
+ __free_pages(virt_to_page(stack), THREAD_SIZE_ORDER);
}
# else
-static struct kmem_cache *thread_info_cache;
+static struct kmem_cache *thread_stack_cache;
-static struct thread_info *alloc_thread_info_node(struct task_struct *tsk,
+static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
- return kmem_cache_alloc_node(thread_info_cache, THREADINFO_GFP, node);
+ return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
}
-static void free_thread_info(struct thread_info *ti)
+static void free_thread_stack(unsigned long *stack)
{
- kmem_cache_free(thread_info_cache, ti);
+ kmem_cache_free(thread_stack_cache, stack);
}
-void thread_info_cache_init(void)
+void thread_stack_cache_init(void)
{
- thread_info_cache = kmem_cache_create("thread_info", THREAD_SIZE,
+ thread_stack_cache = kmem_cache_create("thread_stack", THREAD_SIZE,
THREAD_SIZE, 0, NULL);
- BUG_ON(thread_info_cache == NULL);
+ BUG_ON(thread_stack_cache == NULL);
}
# endif
#endif
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
-static void account_kernel_stack(struct thread_info *ti, int account)
+static void account_kernel_stack(unsigned long *stack, int account)
{
- struct zone *zone = page_zone(virt_to_page(ti));
+ /* All stack pages are in the same zone and belong to the same memcg. */
+ struct page *first_page = virt_to_page(stack);
+
+ mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
+ THREAD_SIZE / 1024 * account);
- mod_zone_page_state(zone, NR_KERNEL_STACK, account);
+ memcg_kmem_update_page_stat(
+ first_page, MEMCG_KERNEL_STACK_KB,
+ account * (THREAD_SIZE / 1024));
}
void free_task(struct task_struct *tsk)
{
account_kernel_stack(tsk->stack, -1);
- arch_release_thread_info(tsk->stack);
- free_thread_info(tsk->stack);
+ arch_release_thread_stack(tsk->stack);
+ free_thread_stack(tsk->stack);
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
put_seccomp_filter(tsk);
*stackend = STACK_END_MAGIC; /* for overflow detection */
}
-static struct task_struct *dup_task_struct(struct task_struct *orig)
+static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
{
struct task_struct *tsk;
- struct thread_info *ti;
- int node = tsk_fork_get_node(orig);
+ unsigned long *stack;
int err;
+ if (node == NUMA_NO_NODE)
+ node = tsk_fork_get_node(orig);
tsk = alloc_task_struct_node(node);
if (!tsk)
return NULL;
- ti = alloc_thread_info_node(tsk, node);
- if (!ti)
+ stack = alloc_thread_stack_node(tsk, node);
+ if (!stack)
goto free_tsk;
err = arch_dup_task_struct(tsk, orig);
if (err)
- goto free_ti;
+ goto free_stack;
- tsk->stack = ti;
+ tsk->stack = stack;
#ifdef CONFIG_SECCOMP
/*
* We must handle setting up seccomp filters once we're under
tsk->task_frag.page = NULL;
tsk->wake_q.next = NULL;
- account_kernel_stack(ti, 1);
+ account_kernel_stack(stack, 1);
kcov_task_init(tsk);
return tsk;
-free_ti:
- free_thread_info(ti);
+free_stack:
+ free_thread_stack(stack);
free_tsk:
free_task_struct(tsk);
return NULL;
unsigned long charge;
uprobe_start_dup_mmap();
- down_write(&oldmm->mmap_sem);
+ if (down_write_killable(&oldmm->mmap_sem)) {
+ retval = -EINTR;
+ goto fail_uprobe_end;
+ }
flush_cache_dup_mm(oldmm);
uprobe_dup_mmap(oldmm, mm);
/*
up_write(&mm->mmap_sem);
flush_tlb_mm(oldmm);
up_write(&oldmm->mmap_sem);
+fail_uprobe_end:
uprobe_end_dup_mmap();
return retval;
fail_nomem_anon_vma_fork:
}
EXPORT_SYMBOL_GPL(__mmdrop);
+static inline void __mmput(struct mm_struct *mm)
+{
+ VM_BUG_ON(atomic_read(&mm->mm_users));
+
+ uprobe_clear_state(mm);
+ exit_aio(mm);
+ ksm_exit(mm);
+ khugepaged_exit(mm); /* must run before exit_mmap */
+ exit_mmap(mm);
+ set_mm_exe_file(mm, NULL);
+ if (!list_empty(&mm->mmlist)) {
+ spin_lock(&mmlist_lock);
+ list_del(&mm->mmlist);
+ spin_unlock(&mmlist_lock);
+ }
+ if (mm->binfmt)
+ module_put(mm->binfmt->module);
+ mmdrop(mm);
+}
+
/*
* Decrement the use count and release all resources for an mm.
*/
{
might_sleep();
+ if (atomic_dec_and_test(&mm->mm_users))
+ __mmput(mm);
+}
+EXPORT_SYMBOL_GPL(mmput);
+
+#ifdef CONFIG_MMU
+static void mmput_async_fn(struct work_struct *work)
+{
+ struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
+ __mmput(mm);
+}
+
+void mmput_async(struct mm_struct *mm)
+{
if (atomic_dec_and_test(&mm->mm_users)) {
- uprobe_clear_state(mm);
- exit_aio(mm);
- ksm_exit(mm);
- khugepaged_exit(mm); /* must run before exit_mmap */
- exit_mmap(mm);
- set_mm_exe_file(mm, NULL);
- if (!list_empty(&mm->mmlist)) {
- spin_lock(&mmlist_lock);
- list_del(&mm->mmlist);
- spin_unlock(&mmlist_lock);
- }
- if (mm->binfmt)
- module_put(mm->binfmt->module);
- mmdrop(mm);
+ INIT_WORK(&mm->async_put_work, mmput_async_fn);
+ schedule_work(&mm->async_put_work);
}
}
-EXPORT_SYMBOL_GPL(mmput);
+#endif
/**
* set_mm_exe_file - change a reference to the mm's executable file
return exe_file;
}
EXPORT_SYMBOL(get_mm_exe_file);
+
+ /**
+ * get_task_exe_file - acquire a reference to the task's executable file
+ *
+ * Returns %NULL if task's mm (if any) has no associated executable file or
+ * this is a kernel thread with borrowed mm (see the comment above get_task_mm).
+ * User must release file via fput().
+ */
+ struct file *get_task_exe_file(struct task_struct *task)
+ {
+ struct file *exe_file = NULL;
+ struct mm_struct *mm;
+
+ task_lock(task);
+ mm = task->mm;
+ if (mm) {
+ if (!(task->flags & PF_KTHREAD))
+ exe_file = get_mm_exe_file(mm);
+ }
+ task_unlock(task);
+ return exe_file;
+ }
+ EXPORT_SYMBOL(get_task_exe_file);
/**
* get_task_mm - acquire a reference to the task's mm
int __user *child_tidptr,
struct pid *pid,
int trace,
- unsigned long tls)
+ unsigned long tls,
+ int node)
{
int retval;
struct task_struct *p;
goto fork_out;
retval = -ENOMEM;
- p = dup_task_struct(current);
+ p = dup_task_struct(current, node);
if (!p)
goto fork_out;
p->real_start_time = ktime_get_boot_ns();
p->io_context = NULL;
p->audit_context = NULL;
- threadgroup_change_begin(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
pid = alloc_pid(p->nsproxy->pid_ns_for_children);
if (IS_ERR(pid)) {
retval = PTR_ERR(pid);
- goto bad_fork_cleanup_io;
+ goto bad_fork_cleanup_thread;
}
}
* sigaltstack should be cleared when sharing the same VM
*/
if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
- p->sas_ss_sp = p->sas_ss_size = 0;
+ sas_ss_reset(p);
/*
* Syscall tracing and stepping should be turned off in the
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
+ threadgroup_change_begin(current);
/*
* Ensure that the cgroup subsystem policies allow the new process to be
* forked. It should be noted the the new process's css_set can be changed
bad_fork_cancel_cgroup:
cgroup_cancel_fork(p);
bad_fork_free_pid:
+ threadgroup_change_end(current);
if (pid != &init_struct_pid)
free_pid(pid);
+bad_fork_cleanup_thread:
+ exit_thread(p);
bad_fork_cleanup_io:
if (p->io_context)
exit_io_context(p);
mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
#endif
- threadgroup_change_end(current);
delayacct_tsk_free(p);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
struct task_struct *fork_idle(int cpu)
{
struct task_struct *task;
- task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0);
+ task = copy_process(CLONE_VM, 0, 0, NULL, &init_struct_pid, 0, 0,
+ cpu_to_node(cpu));
if (!IS_ERR(task)) {
init_idle_pids(task->pids);
init_idle(task, cpu);
}
p = copy_process(clone_flags, stack_start, stack_size,
- child_tidptr, NULL, trace, tls);
+ child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.