summaryrefslogtreecommitdiff
path: root/kernel/fork.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/fork.c')
-rw-r--r--kernel/fork.c104
1 files changed, 53 insertions, 51 deletions
diff --git a/kernel/fork.c b/kernel/fork.c
index e45354cc7cac..c4ada32598bd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -189,33 +189,33 @@ static inline void free_task_struct(struct task_struct *tsk)
kmem_cache_free(task_struct_cachep, tsk);
}
-/*
- * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
- * kmemcache based allocator.
- */
-# if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)
-
-# ifdef CONFIG_VMAP_STACK
+#ifdef CONFIG_VMAP_STACK
/*
* vmalloc() is a bit slow, and calling vfree() enough times will force a TLB
* flush. Try to minimize the number of calls by caching stacks.
*/
#define NR_CACHED_STACKS 2
static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);
+/*
+ * Allocated stacks are cached and later reused by new threads, so memcg
+ * accounting is performed by the code assigning/releasing stacks to tasks.
+ * We need a zeroed memory without __GFP_ACCOUNT.
+ */
+#define GFP_VMAP_STACK (GFP_KERNEL | __GFP_ZERO)
struct vm_stack {
struct rcu_head rcu;
struct vm_struct *stack_vm_area;
};
-static bool try_release_thread_stack_to_cache(struct vm_struct *vm)
+static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area)
{
unsigned int i;
for (i = 0; i < NR_CACHED_STACKS; i++) {
struct vm_struct *tmp = NULL;
- if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm))
+ if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area))
return true;
}
return false;
@@ -224,11 +224,12 @@ static bool try_release_thread_stack_to_cache(struct vm_struct *vm)
static void thread_stack_free_rcu(struct rcu_head *rh)
{
struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu);
+ struct vm_struct *vm_area = vm_stack->stack_vm_area;
if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area))
return;
- vfree(vm_stack);
+ vfree(vm_area->addr);
}
static void thread_stack_delayed_free(struct task_struct *tsk)
@@ -241,32 +242,32 @@ static void thread_stack_delayed_free(struct task_struct *tsk)
static int free_vm_stack_cache(unsigned int cpu)
{
- struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu);
+ struct vm_struct **cached_vm_stack_areas = per_cpu_ptr(cached_stacks, cpu);
int i;
for (i = 0; i < NR_CACHED_STACKS; i++) {
- struct vm_struct *vm_stack = cached_vm_stacks[i];
+ struct vm_struct *vm_area = cached_vm_stack_areas[i];
- if (!vm_stack)
+ if (!vm_area)
continue;
- vfree(vm_stack->addr);
- cached_vm_stacks[i] = NULL;
+ vfree(vm_area->addr);
+ cached_vm_stack_areas[i] = NULL;
}
return 0;
}
-static int memcg_charge_kernel_stack(struct vm_struct *vm)
+static int memcg_charge_kernel_stack(struct vm_struct *vm_area)
{
int i;
int ret;
int nr_charged = 0;
- BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
+ BUG_ON(vm_area->nr_pages != THREAD_SIZE / PAGE_SIZE);
for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
- ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0);
+ ret = memcg_kmem_charge_page(vm_area->pages[i], GFP_KERNEL, 0);
if (ret)
goto err;
nr_charged++;
@@ -274,55 +275,47 @@ static int memcg_charge_kernel_stack(struct vm_struct *vm)
return 0;
err:
for (i = 0; i < nr_charged; i++)
- memcg_kmem_uncharge_page(vm->pages[i], 0);
+ memcg_kmem_uncharge_page(vm_area->pages[i], 0);
return ret;
}
static int alloc_thread_stack_node(struct task_struct *tsk, int node)
{
- struct vm_struct *vm;
+ struct vm_struct *vm_area;
void *stack;
int i;
for (i = 0; i < NR_CACHED_STACKS; i++) {
- struct vm_struct *s;
-
- s = this_cpu_xchg(cached_stacks[i], NULL);
-
- if (!s)
+ vm_area = this_cpu_xchg(cached_stacks[i], NULL);
+ if (!vm_area)
continue;
/* Reset stack metadata. */
- kasan_unpoison_range(s->addr, THREAD_SIZE);
+ kasan_unpoison_range(vm_area->addr, THREAD_SIZE);
- stack = kasan_reset_tag(s->addr);
+ stack = kasan_reset_tag(vm_area->addr);
/* Clear stale pointers from reused stack. */
memset(stack, 0, THREAD_SIZE);
- if (memcg_charge_kernel_stack(s)) {
- vfree(s->addr);
+ if (memcg_charge_kernel_stack(vm_area)) {
+ vfree(vm_area->addr);
return -ENOMEM;
}
- tsk->stack_vm_area = s;
+ tsk->stack_vm_area = vm_area;
tsk->stack = stack;
return 0;
}
- /*
- * Allocated stacks are cached and later reused by new threads,
- * so memcg accounting is performed manually on assigning/releasing
- * stacks to tasks. Drop __GFP_ACCOUNT.
- */
stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN,
- THREADINFO_GFP & ~__GFP_ACCOUNT,
+ GFP_VMAP_STACK,
node, __builtin_return_address(0));
if (!stack)
return -ENOMEM;
- vm = find_vm_area(stack);
- if (memcg_charge_kernel_stack(vm)) {
+ vm_area = find_vm_area(stack);
+ if (memcg_charge_kernel_stack(vm_area)) {
vfree(stack);
return -ENOMEM;
}
@@ -331,7 +324,7 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node)
* free_thread_stack() can be called in interrupt context,
* so cache the vm_struct.
*/
- tsk->stack_vm_area = vm;
+ tsk->stack_vm_area = vm_area;
stack = kasan_reset_tag(stack);
tsk->stack = stack;
return 0;
@@ -346,7 +339,13 @@ static void free_thread_stack(struct task_struct *tsk)
tsk->stack_vm_area = NULL;
}
-# else /* !CONFIG_VMAP_STACK */
+#else /* !CONFIG_VMAP_STACK */
+
+/*
+ * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
+ * kmemcache based allocator.
+ */
+#if THREAD_SIZE >= PAGE_SIZE
static void thread_stack_free_rcu(struct rcu_head *rh)
{
@@ -378,8 +377,7 @@ static void free_thread_stack(struct task_struct *tsk)
tsk->stack = NULL;
}
-# endif /* CONFIG_VMAP_STACK */
-# else /* !(THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)) */
+#else /* !(THREAD_SIZE >= PAGE_SIZE) */
static struct kmem_cache *thread_stack_cache;
@@ -418,7 +416,8 @@ void thread_stack_cache_init(void)
BUG_ON(thread_stack_cache == NULL);
}
-# endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */
+#endif /* THREAD_SIZE >= PAGE_SIZE */
+#endif /* CONFIG_VMAP_STACK */
/* SLAB cache for signal_struct structures (tsk->signal) */
static struct kmem_cache *signal_cachep;
@@ -438,11 +437,11 @@ static struct kmem_cache *mm_cachep;
static void account_kernel_stack(struct task_struct *tsk, int account)
{
if (IS_ENABLED(CONFIG_VMAP_STACK)) {
- struct vm_struct *vm = task_stack_vm_area(tsk);
+ struct vm_struct *vm_area = task_stack_vm_area(tsk);
int i;
for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
- mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB,
+ mod_lruvec_page_state(vm_area->pages[i], NR_KERNEL_STACK_KB,
account * (PAGE_SIZE / 1024));
} else {
void *stack = task_stack_page(tsk);
@@ -458,12 +457,12 @@ void exit_task_stack_account(struct task_struct *tsk)
account_kernel_stack(tsk, -1);
if (IS_ENABLED(CONFIG_VMAP_STACK)) {
- struct vm_struct *vm;
+ struct vm_struct *vm_area;
int i;
- vm = task_stack_vm_area(tsk);
+ vm_area = task_stack_vm_area(tsk);
for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
- memcg_kmem_uncharge_page(vm->pages[i], 0);
+ memcg_kmem_uncharge_page(vm_area->pages[i], 0);
}
}
@@ -586,9 +585,12 @@ static void check_mm(struct mm_struct *mm)
for (i = 0; i < NR_MM_COUNTERS; i++) {
long x = percpu_counter_sum(&mm->rss_stat[i]);
- if (unlikely(x))
- pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n",
- mm, resident_page_types[i], x);
+ if (unlikely(x)) {
+ pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld Comm:%s Pid:%d\n",
+ mm, resident_page_types[i], x,
+ current->comm,
+ task_pid_nr(current));
+ }
}
if (mm_pgtables_bytes(mm))
generated by cgit v1.2.3 (git 2.46.0) at 2025-10-31 11:39:48 +0000