#include <linux/rbtree.h>
#include <linux/radix-tree.h>
#include <linux/rcupdate.h>
-#include <linux/bootmem.h>
+#include <linux/pfn.h>
+#include <linux/kmemleak.h>
#include <asm/atomic.h>
#include <asm/uaccess.h>
*
* Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N]
*/
-static int vmap_page_range(unsigned long start, unsigned long end,
- pgprot_t prot, struct page **pages)
+static int vmap_page_range_noflush(unsigned long start, unsigned long end,
+ pgprot_t prot, struct page **pages)
{
pgd_t *pgd;
unsigned long next;
if (err)
break;
} while (pgd++, addr = next, addr != end);
- flush_cache_vmap(start, end);
if (unlikely(err))
return err;
return nr;
}
+static int vmap_page_range(unsigned long start, unsigned long end,
+ pgprot_t prot, struct page **pages)
+{
+ int ret;
+
+ ret = vmap_page_range_noflush(start, end, prot, pages);
+ flush_cache_vmap(start, end);
+ return ret;
+}
+
static inline int is_vmalloc_or_module_addr(const void *x)
{
/*
static DEFINE_SPINLOCK(vmap_area_lock);
static struct rb_root vmap_area_root = RB_ROOT;
static LIST_HEAD(vmap_area_list);
+static unsigned long vmap_area_pcpu_hole;
static struct vmap_area *__find_vmap_area(unsigned long addr)
{
unsigned long addr;
int purged = 0;
+ BUG_ON(!size);
BUG_ON(size & ~PAGE_MASK);
va = kmalloc_node(sizeof(struct vmap_area),
addr = ALIGN(vstart, align);
spin_lock(&vmap_area_lock);
+ if (addr + size - 1 < addr)
+ goto overflow;
+
/* XXX: could have a last_hole cache */
n = vmap_area_root.rb_node;
if (n) {
while (addr + size > first->va_start && addr + size <= vend) {
addr = ALIGN(first->va_end + PAGE_SIZE, align);
+ if (addr + size - 1 < addr)
+ goto overflow;
n = rb_next(&first->rb_node);
if (n)
}
found:
if (addr + size > vend) {
+overflow:
spin_unlock(&vmap_area_lock);
if (!purged) {
purge_vmap_area_lazy();
printk(KERN_WARNING
"vmap allocation for size %lu failed: "
"use vmalloc=<size> to increase size.\n", size);
+ kfree(va);
return ERR_PTR(-EBUSY);
}
RB_CLEAR_NODE(&va->rb_node);
list_del_rcu(&va->list);
+ /*
+ * Track the highest possible candidate for pcpu area
+ * allocation. Areas outside of vmalloc area can be returned
+ * here too, consider only end addresses which fall inside
+ * vmalloc area proper.
+ */
+ if (va->va_end > VMALLOC_START && va->va_end <= VMALLOC_END)
+ vmap_area_pcpu_hole = max(vmap_area_pcpu_hole, va->va_end);
+
call_rcu(&va->rcu_head, rcu_free_va);
}
static DEFINE_SPINLOCK(purge_lock);
LIST_HEAD(valist);
struct vmap_area *va;
+ struct vmap_area *n_va;
int nr = 0;
/*
if (nr) {
spin_lock(&vmap_area_lock);
- list_for_each_entry(va, &valist, purge_list)
+ list_for_each_entry_safe(va, n_va, &valist, purge_list)
__free_vmap_area(va);
spin_unlock(&vmap_area_lock);
}
DECLARE_BITMAP(alloc_map, VMAP_BBMAP_BITS);
DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS);
union {
- struct {
- struct list_head free_list;
- struct list_head dirty_list;
- };
+ struct list_head free_list;
struct rcu_head rcu_head;
};
};
bitmap_zero(vb->alloc_map, VMAP_BBMAP_BITS);
bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS);
INIT_LIST_HEAD(&vb->free_list);
- INIT_LIST_HEAD(&vb->dirty_list);
vb_idx = addr_to_vb_idx(va->va_start);
spin_lock(&vmap_block_tree_lock);
struct vmap_block *tmp;
unsigned long vb_idx;
- spin_lock(&vb->vbq->lock);
- if (!list_empty(&vb->free_list))
- list_del(&vb->free_list);
- if (!list_empty(&vb->dirty_list))
- list_del(&vb->dirty_list);
- spin_unlock(&vb->vbq->lock);
+ BUG_ON(!list_empty(&vb->free_list));
vb_idx = addr_to_vb_idx(vb->va->va_start);
spin_lock(&vmap_block_tree_lock);
spin_lock(&vb->lock);
bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order);
- if (!vb->dirty) {
- spin_lock(&vb->vbq->lock);
- list_add(&vb->dirty_list, &vb->vbq->dirty);
- spin_unlock(&vb->vbq->lock);
- }
+
vb->dirty += 1UL << order;
if (vb->dirty == VMAP_BBMAP_BITS) {
BUG_ON(vb->free || !list_empty(&vb->free_list));
}
EXPORT_SYMBOL(vm_map_ram);
+/**
+ * vm_area_register_early - register vmap area early during boot
+ * @vm: vm_struct to register
+ * @align: requested alignment
+ *
+ * This function is used to register kernel vm area before
+ * vmalloc_init() is called. @vm->size and @vm->flags should contain
+ * proper values on entry and other fields should be zero. On return,
+ * vm->addr contains the allocated address.
+ *
+ * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
+ */
+void __init vm_area_register_early(struct vm_struct *vm, size_t align)
+{
+ static size_t vm_init_off __initdata;
+ unsigned long addr;
+
+ addr = ALIGN(VMALLOC_START + vm_init_off, align);
+ vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START;
+
+ vm->addr = (void *)addr;
+
+ vm->next = vmlist;
+ vmlist = vm;
+}
+
void __init vmalloc_init(void)
{
struct vmap_area *va;
/* Import existing vmlist entries. */
for (tmp = vmlist; tmp; tmp = tmp->next) {
- va = alloc_bootmem(sizeof(struct vmap_area));
+ va = kzalloc(sizeof(struct vmap_area), GFP_NOWAIT);
va->flags = tmp->flags | VM_VM_AREA;
va->va_start = (unsigned long)tmp->addr;
va->va_end = va->va_start + tmp->size;
__insert_vmap_area(va);
}
+
+ vmap_area_pcpu_hole = VMALLOC_END;
+
vmap_initialized = true;
}
+/**
+ * map_kernel_range_noflush - map kernel VM area with the specified pages
+ * @addr: start of the VM area to map
+ * @size: size of the VM area to map
+ * @prot: page protection flags to use
+ * @pages: pages to map
+ *
+ * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size
+ * specify should have been allocated using get_vm_area() and its
+ * friends.
+ *
+ * NOTE:
+ * This function does NOT do any cache flushing. The caller is
+ * responsible for calling flush_cache_vmap() on to-be-mapped areas
+ * before calling this function.
+ *
+ * RETURNS:
+ * The number of pages mapped on success, -errno on failure.
+ */
+int map_kernel_range_noflush(unsigned long addr, unsigned long size,
+ pgprot_t prot, struct page **pages)
+{
+ return vmap_page_range_noflush(addr, addr + size, prot, pages);
+}
+
+/**
+ * unmap_kernel_range_noflush - unmap kernel VM area
+ * @addr: start of the VM area to unmap
+ * @size: size of the VM area to unmap
+ *
+ * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size
+ * specify should have been allocated using get_vm_area() and its
+ * friends.
+ *
+ * NOTE:
+ * This function does NOT do any cache flushing. The caller is
+ * responsible for calling flush_cache_vunmap() on to-be-mapped areas
+ * before calling this function and flush_tlb_kernel_range() after.
+ */
+void unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
+{
+ vunmap_page_range(addr, addr + size);
+}
+
+/**
+ * unmap_kernel_range - unmap kernel VM area and flush cache and TLB
+ * @addr: start of the VM area to unmap
+ * @size: size of the VM area to unmap
+ *
+ * Similar to unmap_kernel_range_noflush() but flushes vcache before
+ * the unmapping and tlb after.
+ */
void unmap_kernel_range(unsigned long addr, unsigned long size)
{
unsigned long end = addr + size;
+
+ flush_cache_vunmap(addr, end);
vunmap_page_range(addr, end);
flush_tlb_kernel_range(addr, end);
}
DEFINE_RWLOCK(vmlist_lock);
struct vm_struct *vmlist;
+static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
+ unsigned long flags, void *caller)
+{
+ struct vm_struct *tmp, **p;
+
+ vm->flags = flags;
+ vm->addr = (void *)va->va_start;
+ vm->size = va->va_end - va->va_start;
+ vm->caller = caller;
+ va->private = vm;
+ va->flags |= VM_VM_AREA;
+
+ 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 struct vm_struct *__get_vm_area_node(unsigned long size,
unsigned long flags, unsigned long start, unsigned long end,
int node, gfp_t gfp_mask, void *caller)
{
static struct vmap_area *va;
struct vm_struct *area;
- struct vm_struct *tmp, **p;
unsigned long align = 1;
BUG_ON(in_interrupt());
if (unlikely(!size))
return NULL;
- area = kmalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
+ area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
if (unlikely(!area))
return NULL;
return NULL;
}
- area->flags = flags;
- area->addr = (void *)va->va_start;
- area->size = size;
- area->pages = NULL;
- area->nr_pages = 0;
- area->phys_addr = 0;
- area->caller = caller;
- va->private = area;
- va->flags |= VM_VM_AREA;
-
- write_lock(&vmlist_lock);
- for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
- if (tmp->addr >= area->addr)
- break;
- }
- area->next = *p;
- *p = area;
- write_unlock(&vmlist_lock);
-
+ insert_vmalloc_vm(area, va, flags, caller);
return area;
}
void vfree(const void *addr)
{
BUG_ON(in_interrupt());
+
+ kmemleak_free(addr);
+
__vunmap(addr, 1);
}
EXPORT_SYMBOL(vfree);
void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
{
- return __vmalloc_area_node(area, gfp_mask, prot, -1,
- __builtin_return_address(0));
+ void *addr = __vmalloc_area_node(area, gfp_mask, prot, -1,
+ __builtin_return_address(0));
+
+ /*
+ * A ref_count = 3 is needed because the vm_struct and vmap_area
+ * structures allocated in the __get_vm_area_node() function contain
+ * references to the virtual address of the vmalloc'ed block.
+ */
+ kmemleak_alloc(addr, area->size - PAGE_SIZE, 3, gfp_mask);
+
+ return addr;
}
/**
int node, void *caller)
{
struct vm_struct *area;
+ void *addr;
+ unsigned long real_size = size;
size = PAGE_ALIGN(size);
if (!size || (size >> PAGE_SHIFT) > num_physpages)
if (!area)
return NULL;
- return __vmalloc_area_node(area, gfp_mask, prot, node, caller);
+ addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller);
+
+ /*
+ * A ref_count = 3 is needed because the vm_struct and vmap_area
+ * structures allocated in the __get_vm_area_node() function contain
+ * references to the virtual address of the vmalloc'ed block.
+ */
+ kmemleak_alloc(addr, real_size, 3, gfp_mask);
+
+ return addr;
}
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
}
EXPORT_SYMBOL_GPL(free_vm_area);
+static struct vmap_area *node_to_va(struct rb_node *n)
+{
+ return n ? rb_entry(n, struct vmap_area, rb_node) : NULL;
+}
+
+/**
+ * pvm_find_next_prev - find the next and prev vmap_area surrounding @end
+ * @end: target address
+ * @pnext: out arg for the next vmap_area
+ * @pprev: out arg for the previous vmap_area
+ *
+ * Returns: %true if either or both of next and prev are found,
+ * %false if no vmap_area exists
+ *
+ * Find vmap_areas end addresses of which enclose @end. ie. if not
+ * NULL, *pnext->va_end > @end and *pprev->va_end <= @end.
+ */
+static bool pvm_find_next_prev(unsigned long end,
+ struct vmap_area **pnext,
+ struct vmap_area **pprev)
+{
+ struct rb_node *n = vmap_area_root.rb_node;
+ struct vmap_area *va = NULL;
+
+ while (n) {
+ va = rb_entry(n, struct vmap_area, rb_node);
+ if (end < va->va_end)
+ n = n->rb_left;
+ else if (end > va->va_end)
+ n = n->rb_right;
+ else
+ break;
+ }
+
+ if (!va)
+ return false;
+
+ if (va->va_end > end) {
+ *pnext = va;
+ *pprev = node_to_va(rb_prev(&(*pnext)->rb_node));
+ } else {
+ *pprev = va;
+ *pnext = node_to_va(rb_next(&(*pprev)->rb_node));
+ }
+ return true;
+}
+
+/**
+ * pvm_determine_end - find the highest aligned address between two vmap_areas
+ * @pnext: in/out arg for the next vmap_area
+ * @pprev: in/out arg for the previous vmap_area
+ * @align: alignment
+ *
+ * Returns: determined end address
+ *
+ * Find the highest aligned address between *@pnext and *@pprev below
+ * VMALLOC_END. *@pnext and *@pprev are adjusted so that the aligned
+ * down address is between the end addresses of the two vmap_areas.
+ *
+ * Please note that the address returned by this function may fall
+ * inside *@pnext vmap_area. The caller is responsible for checking
+ * that.
+ */
+static unsigned long pvm_determine_end(struct vmap_area **pnext,
+ struct vmap_area **pprev,
+ unsigned long align)
+{
+ const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
+ unsigned long addr;
+
+ if (*pnext)
+ addr = min((*pnext)->va_start & ~(align - 1), vmalloc_end);
+ else
+ addr = vmalloc_end;
+
+ while (*pprev && (*pprev)->va_end > addr) {
+ *pnext = *pprev;
+ *pprev = node_to_va(rb_prev(&(*pnext)->rb_node));
+ }
+
+ return addr;
+}
+
+/**
+ * pcpu_get_vm_areas - allocate vmalloc areas for percpu allocator
+ * @offsets: array containing offset of each area
+ * @sizes: array containing size of each area
+ * @nr_vms: the number of areas to allocate
+ * @align: alignment, all entries in @offsets and @sizes must be aligned to this
+ * @gfp_mask: allocation mask
+ *
+ * Returns: kmalloc'd vm_struct pointer array pointing to allocated
+ * vm_structs on success, %NULL on failure
+ *
+ * Percpu allocator wants to use congruent vm areas so that it can
+ * maintain the offsets among percpu areas. This function allocates
+ * congruent vmalloc areas for it. These areas tend to be scattered
+ * pretty far, distance between two areas easily going up to
+ * gigabytes. To avoid interacting with regular vmallocs, these areas
+ * are allocated from top.
+ *
+ * Despite its complicated look, this allocator is rather simple. It
+ * does everything top-down and scans areas from the end looking for
+ * matching slot. While scanning, if any of the areas overlaps with
+ * existing vmap_area, the base address is pulled down to fit the
+ * area. Scanning is repeated till all the areas fit and then all
+ * necessary data structres are inserted and the result is returned.
+ */
+struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
+ const size_t *sizes, int nr_vms,
+ size_t align, gfp_t gfp_mask)
+{
+ const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align);
+ const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
+ struct vmap_area **vas, *prev, *next;
+ struct vm_struct **vms;
+ int area, area2, last_area, term_area;
+ unsigned long base, start, end, last_end;
+ bool purged = false;
+
+ gfp_mask &= GFP_RECLAIM_MASK;
+
+ /* verify parameters and allocate data structures */
+ BUG_ON(align & ~PAGE_MASK || !is_power_of_2(align));
+ for (last_area = 0, area = 0; area < nr_vms; area++) {
+ start = offsets[area];
+ end = start + sizes[area];
+
+ /* is everything aligned properly? */
+ BUG_ON(!IS_ALIGNED(offsets[area], align));
+ BUG_ON(!IS_ALIGNED(sizes[area], align));
+
+ /* detect the area with the highest address */
+ if (start > offsets[last_area])
+ last_area = area;
+
+ for (area2 = 0; area2 < nr_vms; area2++) {
+ unsigned long start2 = offsets[area2];
+ unsigned long end2 = start2 + sizes[area2];
+
+ if (area2 == area)
+ continue;
+
+ BUG_ON(start2 >= start && start2 < end);
+ BUG_ON(end2 <= end && end2 > start);
+ }
+ }
+ last_end = offsets[last_area] + sizes[last_area];
+
+ if (vmalloc_end - vmalloc_start < last_end) {
+ WARN_ON(true);
+ return NULL;
+ }
+
+ vms = kzalloc(sizeof(vms[0]) * nr_vms, gfp_mask);
+ vas = kzalloc(sizeof(vas[0]) * nr_vms, gfp_mask);
+ if (!vas || !vms)
+ goto err_free;
+
+ for (area = 0; area < nr_vms; area++) {
+ vas[area] = kzalloc(sizeof(struct vmap_area), gfp_mask);
+ vms[area] = kzalloc(sizeof(struct vm_struct), gfp_mask);
+ if (!vas[area] || !vms[area])
+ goto err_free;
+ }
+retry:
+ spin_lock(&vmap_area_lock);
+
+ /* start scanning - we scan from the top, begin with the last area */
+ area = term_area = last_area;
+ start = offsets[area];
+ end = start + sizes[area];
+
+ if (!pvm_find_next_prev(vmap_area_pcpu_hole, &next, &prev)) {
+ base = vmalloc_end - last_end;
+ goto found;
+ }
+ base = pvm_determine_end(&next, &prev, align) - end;
+
+ while (true) {
+ BUG_ON(next && next->va_end <= base + end);
+ BUG_ON(prev && prev->va_end > base + end);
+
+ /*
+ * base might have underflowed, add last_end before
+ * comparing.
+ */
+ if (base + last_end < vmalloc_start + last_end) {
+ spin_unlock(&vmap_area_lock);
+ if (!purged) {
+ purge_vmap_area_lazy();
+ purged = true;
+ goto retry;
+ }
+ goto err_free;
+ }
+
+ /*
+ * If next overlaps, move base downwards so that it's
+ * right below next and then recheck.
+ */
+ if (next && next->va_start < base + end) {
+ base = pvm_determine_end(&next, &prev, align) - end;
+ term_area = area;
+ continue;
+ }
+
+ /*
+ * If prev overlaps, shift down next and prev and move
+ * base so that it's right below new next and then
+ * recheck.
+ */
+ if (prev && prev->va_end > base + start) {
+ next = prev;
+ prev = node_to_va(rb_prev(&next->rb_node));
+ base = pvm_determine_end(&next, &prev, align) - end;
+ term_area = area;
+ continue;
+ }
+
+ /*
+ * This area fits, move on to the previous one. If
+ * the previous one is the terminal one, we're done.
+ */
+ area = (area + nr_vms - 1) % nr_vms;
+ if (area == term_area)
+ break;
+ start = offsets[area];
+ end = start + sizes[area];
+ pvm_find_next_prev(base + end, &next, &prev);
+ }
+found:
+ /* we've found a fitting base, insert all va's */
+ for (area = 0; area < nr_vms; area++) {
+ struct vmap_area *va = vas[area];
+
+ va->va_start = base + offsets[area];
+ va->va_end = va->va_start + sizes[area];
+ __insert_vmap_area(va);
+ }
+
+ vmap_area_pcpu_hole = base + offsets[last_area];
+
+ spin_unlock(&vmap_area_lock);
+
+ /* insert all vm's */
+ for (area = 0; area < nr_vms; area++)
+ insert_vmalloc_vm(vms[area], vas[area], VM_ALLOC,
+ pcpu_get_vm_areas);
+
+ kfree(vas);
+ return vms;
+
+err_free:
+ for (area = 0; area < nr_vms; area++) {
+ if (vas)
+ kfree(vas[area]);
+ if (vms)
+ kfree(vms[area]);
+ }
+ kfree(vas);
+ kfree(vms);
+ return NULL;
+}
+
+/**
+ * pcpu_free_vm_areas - free vmalloc areas for percpu allocator
+ * @vms: vm_struct pointer array returned by pcpu_get_vm_areas()
+ * @nr_vms: the number of allocated areas
+ *
+ * Free vm_structs and the array allocated by pcpu_get_vm_areas().
+ */
+void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
+{
+ int i;
+
+ for (i = 0; i < nr_vms; i++)
+ free_vm_area(vms[i]);
+ kfree(vms);
+}
#ifdef CONFIG_PROC_FS
static void *s_start(struct seq_file *m, loff_t *pos)