#include <linux/notifier.h>
#include <linux/rbtree.h>
#include <linux/xarray.h>
+#include <linux/io.h>
#include <linux/rcupdate.h>
#include <linux/pfn.h>
#include <linux/kmemleak.h>
#include <linux/overflow.h>
#include <linux/pgtable.h>
#include <linux/uaccess.h>
+#include <linux/hugetlb.h>
#include <asm/tlbflush.h>
#include <asm/shmparam.h>
/*** Page table manipulation functions ***/
static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+ unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
pte_t *pte;
u64 pfn;
+ unsigned long size = PAGE_SIZE;
pfn = phys_addr >> PAGE_SHIFT;
pte = pte_alloc_kernel_track(pmd, addr, mask);
return -ENOMEM;
do {
BUG_ON(!pte_none(*pte));
+
+#ifdef CONFIG_HUGETLB_PAGE
+ size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift);
+ if (size != PAGE_SIZE) {
+ pte_t entry = pfn_pte(pfn, prot);
+
+ entry = pte_mkhuge(entry);
+ entry = arch_make_huge_pte(entry, ilog2(size), 0);
+ set_huge_pte_at(&init_mm, addr, pte, entry);
+ pfn += PFN_DOWN(size);
+ continue;
+ }
+#endif
set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
pfn++;
- } while (pte++, addr += PAGE_SIZE, addr != end);
+ } while (pte += PFN_DOWN(size), addr += size, addr != end);
*mask |= PGTBL_PTE_MODIFIED;
return 0;
}
continue;
}
- if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask))
+ if (vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask))
return -ENOMEM;
} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
return atomic_long_read(&nr_vmalloc_pages);
}
+static struct vmap_area *find_vmap_area_exceed_addr(unsigned long addr)
+{
+ struct vmap_area *va = NULL;
+ struct rb_node *n = vmap_area_root.rb_node;
+
+ while (n) {
+ struct vmap_area *tmp;
+
+ tmp = rb_entry(n, struct vmap_area, rb_node);
+ if (tmp->va_end > addr) {
+ va = tmp;
+ if (tmp->va_start <= addr)
+ break;
+
+ n = n->rb_left;
+ } else
+ n = n->rb_right;
+ }
+
+ return va;
+}
+
static struct vmap_area *__find_vmap_area(unsigned long addr)
{
struct rb_node *n = vmap_area_root.rb_node;
int node, gfp_t gfp_mask)
{
struct vmap_area *va;
+ unsigned long freed;
unsigned long addr;
int purged = 0;
int ret;
goto retry;
}
- if (gfpflags_allow_blocking(gfp_mask)) {
- unsigned long freed = 0;
- blocking_notifier_call_chain(&vmap_notify_list, 0, &freed);
- if (freed > 0) {
- purged = 0;
- goto retry;
- }
+ freed = 0;
+ blocking_notifier_call_chain(&vmap_notify_list, 0, &freed);
+
+ if (freed > 0) {
+ purged = 0;
+ goto retry;
}
if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit())
/* for per-CPU blocks */
static void purge_fragmented_blocks_allcpus(void);
+#ifdef CONFIG_X86_64
/*
* called before a call to iounmap() if the caller wants vm_area_struct's
* immediately freed.
{
atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1);
}
+#endif /* CONFIG_X86_64 */
/*
* Purges all lazily-freed vmap areas.
static inline unsigned int
vm_area_alloc_pages(gfp_t gfp, int nid,
- unsigned int order, unsigned long nr_pages, struct page **pages)
+ unsigned int order, unsigned int nr_pages, struct page **pages)
{
unsigned int nr_allocated = 0;
* to fails, fallback to a single page allocator that is
* more permissive.
*/
- if (!order)
- nr_allocated = alloc_pages_bulk_array_node(
- gfp, nid, nr_pages, pages);
- else
+ if (!order) {
+ while (nr_allocated < nr_pages) {
+ unsigned int nr, nr_pages_request;
+
+ /*
+ * A maximum allowed request is hard-coded and is 100
+ * pages per call. That is done in order to prevent a
+ * long preemption off scenario in the bulk-allocator
+ * so the range is [1:100].
+ */
+ nr_pages_request = min(100U, nr_pages - nr_allocated);
+
+ nr = alloc_pages_bulk_array_node(gfp, nid,
+ nr_pages_request, pages + nr_allocated);
+
+ nr_allocated += nr;
+ cond_resched();
+
+ /*
+ * If zero or pages were obtained partly,
+ * fallback to a single page allocator.
+ */
+ if (nr != nr_pages_request)
+ break;
+ }
+ } else
/*
* Compound pages required for remap_vmalloc_page if
* high-order pages.
for (i = 0; i < (1U << order); i++)
pages[nr_allocated + i] = page + i;
- if (gfpflags_allow_blocking(gfp))
- cond_resched();
-
+ cond_resched();
nr_allocated += 1U << order;
}
return NULL;
}
- if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP) &&
- arch_vmap_pmd_supported(prot)) {
+ if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) {
unsigned long size_per_node;
/*
size_per_node = size;
if (node == NUMA_NO_NODE)
size_per_node /= num_online_nodes();
- if (size_per_node >= PMD_SIZE) {
+ if (arch_vmap_pmd_supported(prot) && size_per_node >= PMD_SIZE)
shift = PMD_SHIFT;
- align = max(real_align, 1UL << shift);
- size = ALIGN(real_size, 1UL << shift);
- }
+ else
+ shift = arch_vmap_pte_supported_shift(size_per_node);
+
+ align = max(real_align, 1UL << shift);
+ size = ALIGN(real_size, 1UL << shift);
}
again:
count = -(unsigned long) addr;
spin_lock(&vmap_area_lock);
- va = __find_vmap_area((unsigned long)addr);
+ va = find_vmap_area_exceed_addr((unsigned long)addr);
if (!va)
goto finished;
+
+ /* no intersects with alive vmap_area */
+ if ((unsigned long)addr + count <= va->va_start)
+ goto finished;
+
list_for_each_entry_from(va, &vmap_area_list, list) {
if (!count)
break;