#include <linux/pfn.h>
#include <linux/kmemleak.h>
#include <linux/atomic.h>
+#include <linux/llist.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/shmparam.h>
+struct vfree_deferred {
+ struct llist_head list;
+ struct work_struct wq;
+};
+static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred);
+
+static void __vunmap(const void *, int);
+
+static void free_work(struct work_struct *w)
+{
+ struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq);
+ struct llist_node *llnode = llist_del_all(&p->list);
+ while (llnode) {
+ void *p = llnode;
+ llnode = llist_next(llnode);
+ __vunmap(p, 1);
+ }
+}
+
/*** Page table manipulation functions ***/
static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end)
#define VM_LAZY_FREEING 0x02
#define VM_VM_AREA 0x04
-struct vmap_area {
- unsigned long va_start;
- unsigned long va_end;
- unsigned long flags;
- struct rb_node rb_node; /* address sorted rbtree */
- struct list_head list; /* address sorted list */
- struct list_head purge_list; /* "lazy purge" list */
- struct vm_struct *vm;
- struct rcu_head rcu_head;
-};
-
static DEFINE_SPINLOCK(vmap_area_lock);
-static LIST_HEAD(vmap_area_list);
+/* Export for kexec only */
+LIST_HEAD(vmap_area_list);
static struct rb_root vmap_area_root = RB_ROOT;
/* The vmap cache globals are protected by vmap_area_lock */
rb_link_node(&va->rb_node, parent, p);
rb_insert_color(&va->rb_node, &vmap_area_root);
- /* address-sort this list so it is usable like the vmlist */
+ /* address-sort this list */
tmp = rb_prev(&va->rb_node);
if (tmp) {
struct vmap_area *prev;
}
EXPORT_SYMBOL(vm_map_ram);
+static struct vm_struct *vmlist __initdata;
/**
* vm_area_add_early - add vmap area early during boot
* @vm: vm_struct to add
for_each_possible_cpu(i) {
struct vmap_block_queue *vbq;
+ struct vfree_deferred *p;
vbq = &per_cpu(vmap_block_queue, i);
spin_lock_init(&vbq->lock);
INIT_LIST_HEAD(&vbq->free);
+ p = &per_cpu(vfree_deferred, i);
+ init_llist_head(&p->list);
+ INIT_WORK(&p->wq, free_work);
}
/* Import existing vmlist entries. */
}
EXPORT_SYMBOL_GPL(map_vm_area);
-/*** Old vmalloc interfaces ***/
-DEFINE_RWLOCK(vmlist_lock);
-struct vm_struct *vmlist;
-
static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
unsigned long flags, const void *caller)
{
+ spin_lock(&vmap_area_lock);
vm->flags = flags;
vm->addr = (void *)va->va_start;
vm->size = va->va_end - va->va_start;
vm->caller = caller;
va->vm = vm;
va->flags |= VM_VM_AREA;
+ spin_unlock(&vmap_area_lock);
}
-static void insert_vmalloc_vmlist(struct vm_struct *vm)
+static void clear_vm_unlist(struct vm_struct *vm)
{
- struct vm_struct *tmp, **p;
-
+ /*
+ * Before removing VM_UNLIST,
+ * we should make sure that vm has proper values.
+ * Pair with smp_rmb() in show_numa_info().
+ */
+ smp_wmb();
vm->flags &= ~VM_UNLIST;
- write_lock(&vmlist_lock);
- for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
- if (tmp->addr >= vm->addr)
- break;
- }
- vm->next = *p;
- *p = vm;
- write_unlock(&vmlist_lock);
}
static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
unsigned long flags, const void *caller)
{
setup_vmalloc_vm(vm, va, flags, caller);
- insert_vmalloc_vmlist(vm);
+ clear_vm_unlist(vm);
}
static struct vm_struct *__get_vm_area_node(unsigned long size,
/*
* When this function is called from __vmalloc_node_range,
- * we do not add vm_struct to vmlist here to avoid
- * accessing uninitialized members of vm_struct such as
- * pages and nr_pages fields. They will be set later.
- * To distinguish it from others, we use a VM_UNLIST flag.
+ * we add VM_UNLIST flag to avoid accessing uninitialized
+ * members of vm_struct such as pages and nr_pages fields.
+ * They will be set later.
*/
if (flags & VM_UNLIST)
setup_vmalloc_vm(area, va, flags, caller);
if (va && va->flags & VM_VM_AREA) {
struct vm_struct *vm = va->vm;
- if (!(vm->flags & VM_UNLIST)) {
- struct vm_struct *tmp, **p;
- /*
- * remove from list and disallow access to
- * this vm_struct before unmap. (address range
- * confliction is maintained by vmap.)
- */
- write_lock(&vmlist_lock);
- for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next)
- ;
- *p = tmp->next;
- write_unlock(&vmlist_lock);
- }
+ spin_lock(&vmap_area_lock);
+ va->vm = NULL;
+ va->flags &= ~VM_VM_AREA;
+ spin_unlock(&vmap_area_lock);
vmap_debug_free_range(va->va_start, va->va_end);
free_unmap_vmap_area(va);
kfree(area);
return;
}
-
+
/**
* vfree - release memory allocated by vmalloc()
* @addr: memory base address
* obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is
* NULL, no operation is performed.
*
- * Must not be called in interrupt context.
+ * Must not be called in NMI context (strictly speaking, only if we don't
+ * have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling
+ * conventions for vfree() arch-depenedent would be a really bad idea)
+ *
+ * NOTE: assumes that the object at *addr has a size >= sizeof(llist_node)
+ *
*/
void vfree(const void *addr)
{
- BUG_ON(in_interrupt());
+ BUG_ON(in_nmi());
kmemleak_free(addr);
- __vunmap(addr, 1);
+ if (!addr)
+ return;
+ if (unlikely(in_interrupt())) {
+ struct vfree_deferred *p = &__get_cpu_var(vfree_deferred);
+ llist_add((struct llist_node *)addr, &p->list);
+ schedule_work(&p->wq);
+ } else
+ __vunmap(addr, 1);
}
EXPORT_SYMBOL(vfree);
{
BUG_ON(in_interrupt());
might_sleep();
- __vunmap(addr, 0);
+ if (addr)
+ __vunmap(addr, 0);
}
EXPORT_SYMBOL(vunmap);
return NULL;
/*
- * In this function, newly allocated vm_struct is not added
- * to vmlist at __get_vm_area_node(). so, it is added here.
+ * In this function, newly allocated vm_struct has VM_UNLIST flag.
+ * It means that vm_struct is not fully initialized.
+ * Now, it is fully initialized, so remove this flag here.
*/
- insert_vmalloc_vmlist(area);
+ clear_vm_unlist(area);
/*
* A ref_count = 3 is needed because the vm_struct and vmap_area
long vread(char *buf, char *addr, unsigned long count)
{
- struct vm_struct *tmp;
+ struct vmap_area *va;
+ struct vm_struct *vm;
char *vaddr, *buf_start = buf;
unsigned long buflen = count;
unsigned long n;
if ((unsigned long) addr + count < count)
count = -(unsigned long) addr;
- read_lock(&vmlist_lock);
- for (tmp = vmlist; count && tmp; tmp = tmp->next) {
- vaddr = (char *) tmp->addr;
- if (addr >= vaddr + tmp->size - PAGE_SIZE)
+ spin_lock(&vmap_area_lock);
+ list_for_each_entry(va, &vmap_area_list, list) {
+ if (!count)
+ break;
+
+ if (!(va->flags & VM_VM_AREA))
+ continue;
+
+ vm = va->vm;
+ vaddr = (char *) vm->addr;
+ if (addr >= vaddr + vm->size - PAGE_SIZE)
continue;
while (addr < vaddr) {
if (count == 0)
addr++;
count--;
}
- n = vaddr + tmp->size - PAGE_SIZE - addr;
+ n = vaddr + vm->size - PAGE_SIZE - addr;
if (n > count)
n = count;
- if (!(tmp->flags & VM_IOREMAP))
+ if (!(vm->flags & VM_IOREMAP))
aligned_vread(buf, addr, n);
else /* IOREMAP area is treated as memory hole */
memset(buf, 0, n);
count -= n;
}
finished:
- read_unlock(&vmlist_lock);
+ spin_unlock(&vmap_area_lock);
if (buf == buf_start)
return 0;
long vwrite(char *buf, char *addr, unsigned long count)
{
- struct vm_struct *tmp;
+ struct vmap_area *va;
+ struct vm_struct *vm;
char *vaddr;
unsigned long n, buflen;
int copied = 0;
count = -(unsigned long) addr;
buflen = count;
- read_lock(&vmlist_lock);
- for (tmp = vmlist; count && tmp; tmp = tmp->next) {
- vaddr = (char *) tmp->addr;
- if (addr >= vaddr + tmp->size - PAGE_SIZE)
+ spin_lock(&vmap_area_lock);
+ list_for_each_entry(va, &vmap_area_list, list) {
+ if (!count)
+ break;
+
+ if (!(va->flags & VM_VM_AREA))
+ continue;
+
+ vm = va->vm;
+ vaddr = (char *) vm->addr;
+ if (addr >= vaddr + vm->size - PAGE_SIZE)
continue;
while (addr < vaddr) {
if (count == 0)
addr++;
count--;
}
- n = vaddr + tmp->size - PAGE_SIZE - addr;
+ n = vaddr + vm->size - PAGE_SIZE - addr;
if (n > count)
n = count;
- if (!(tmp->flags & VM_IOREMAP)) {
+ if (!(vm->flags & VM_IOREMAP)) {
aligned_vwrite(buf, addr, n);
copied++;
}
count -= n;
}
finished:
- read_unlock(&vmlist_lock);
+ spin_unlock(&vmap_area_lock);
if (!copied)
return 0;
return buflen;
#ifdef CONFIG_PROC_FS
static void *s_start(struct seq_file *m, loff_t *pos)
- __acquires(&vmlist_lock)
+ __acquires(&vmap_area_lock)
{
loff_t n = *pos;
- struct vm_struct *v;
+ struct vmap_area *va;
- read_lock(&vmlist_lock);
- v = vmlist;
- while (n > 0 && v) {
+ spin_lock(&vmap_area_lock);
+ va = list_entry((&vmap_area_list)->next, typeof(*va), list);
+ while (n > 0 && &va->list != &vmap_area_list) {
n--;
- v = v->next;
+ va = list_entry(va->list.next, typeof(*va), list);
}
- if (!n)
- return v;
+ if (!n && &va->list != &vmap_area_list)
+ return va;
return NULL;
static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
- struct vm_struct *v = p;
+ struct vmap_area *va = p, *next;
++*pos;
- return v->next;
+ next = list_entry(va->list.next, typeof(*va), list);
+ if (&next->list != &vmap_area_list)
+ return next;
+
+ return NULL;
}
static void s_stop(struct seq_file *m, void *p)
- __releases(&vmlist_lock)
+ __releases(&vmap_area_lock)
{
- read_unlock(&vmlist_lock);
+ spin_unlock(&vmap_area_lock);
}
static void show_numa_info(struct seq_file *m, struct vm_struct *v)
if (!counters)
return;
+ /* Pair with smp_wmb() in clear_vm_unlist() */
+ smp_rmb();
+ if (v->flags & VM_UNLIST)
+ return;
+
memset(counters, 0, nr_node_ids * sizeof(unsigned int));
for (nr = 0; nr < v->nr_pages; nr++)
static int s_show(struct seq_file *m, void *p)
{
- struct vm_struct *v = p;
+ struct vmap_area *va = p;
+ struct vm_struct *v;
+
+ if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEING))
+ return 0;
+
+ if (!(va->flags & VM_VM_AREA)) {
+ seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
+ (void *)va->va_start, (void *)va->va_end,
+ va->va_end - va->va_start);
+ return 0;
+ }
+
+ v = va->vm;
seq_printf(m, "0x%pK-0x%pK %7ld",
v->addr, v->addr + v->size, v->size);
return 0;
}
module_init(proc_vmalloc_init);
+
+void get_vmalloc_info(struct vmalloc_info *vmi)
+{
+ struct vmap_area *va;
+ unsigned long free_area_size;
+ unsigned long prev_end;
+
+ vmi->used = 0;
+ vmi->largest_chunk = 0;
+
+ prev_end = VMALLOC_START;
+
+ spin_lock(&vmap_area_lock);
+
+ if (list_empty(&vmap_area_list)) {
+ vmi->largest_chunk = VMALLOC_TOTAL;
+ goto out;
+ }
+
+ list_for_each_entry(va, &vmap_area_list, list) {
+ unsigned long addr = va->va_start;
+
+ /*
+ * Some archs keep another range for modules in vmalloc space
+ */
+ if (addr < VMALLOC_START)
+ continue;
+ if (addr >= VMALLOC_END)
+ break;
+
+ if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEING))
+ continue;
+
+ vmi->used += (va->va_end - va->va_start);
+
+ free_area_size = addr - prev_end;
+ if (vmi->largest_chunk < free_area_size)
+ vmi->largest_chunk = free_area_size;
+
+ prev_end = va->va_end;
+ }
+
+ if (VMALLOC_END - prev_end > vmi->largest_chunk)
+ vmi->largest_chunk = VMALLOC_END - prev_end;
+
+out:
+ spin_unlock(&vmap_area_lock);
+}
#endif
projects / ~andy / linux / blobdiff