/* * linux/mm/vmalloc.c * * Copyright (C) 1993 Linus Torvalds * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian , May 2000 * Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002 * Numa awareness, Christoph Lameter, SGI, June 2005 */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include "internal.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) { pte_t *pte; pte = pte_offset_kernel(pmd, addr); do { pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); } while (pte++, addr += PAGE_SIZE, addr != end); } static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end) { pmd_t *pmd; unsigned long next; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); if (pmd_clear_huge(pmd)) continue; if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next); } while (pmd++, addr = next, addr != end); } static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end) { pud_t *pud; unsigned long next; pud = pud_offset(pgd, addr); do { next = pud_addr_end(addr, end); if (pud_clear_huge(pud)) continue; if (pud_none_or_clear_bad(pud)) continue; vunmap_pmd_range(pud, addr, next); } while (pud++, addr = next, addr != end); } static void vunmap_page_range(unsigned long addr, unsigned long end) { pgd_t *pgd; unsigned long next; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; vunmap_pud_range(pgd, addr, next); } while (pgd++, addr = next, addr != end); } static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr) { pte_t *pte; /* * nr is a running index into the array which helps higher level * callers keep track of where we're up to. */ pte = pte_alloc_kernel(pmd, addr); if (!pte) return -ENOMEM; do { struct page *page = pages[*nr]; if (WARN_ON(!pte_none(*pte))) return -EBUSY; if (WARN_ON(!page)) return -ENOMEM; set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); return 0; } static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr) { pmd_t *pmd; unsigned long next; pmd = pmd_alloc(&init_mm, pud, addr); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); if (vmap_pte_range(pmd, addr, next, prot, pages, nr)) return -ENOMEM; } while (pmd++, addr = next, addr != end); return 0; } static int vmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr) { pud_t *pud; unsigned long next; pud = pud_alloc(&init_mm, pgd, addr); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); if (vmap_pmd_range(pud, addr, next, prot, pages, nr)) return -ENOMEM; } while (pud++, addr = next, addr != end); return 0; } /* * Set up page tables in kva (addr, end). The ptes shall have prot "prot", and * will have pfns corresponding to the "pages" array. * * Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N] */ static int vmap_page_range_noflush(unsigned long start, unsigned long end, pgprot_t prot, struct page **pages) { pgd_t *pgd; unsigned long next; unsigned long addr = start; int err = 0; int nr = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); err = vmap_pud_range(pgd, addr, next, prot, pages, &nr); if (err) return err; } while (pgd++, addr = next, addr != end); 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; } int is_vmalloc_or_module_addr(const void *x) { /* * ARM, x86-64 and sparc64 put modules in a special place, * and fall back on vmalloc() if that fails. Others * just put it in the vmalloc space. */ #if defined(CONFIG_MODULES) && defined(MODULES_VADDR) unsigned long addr = (unsigned long)x; if (addr >= MODULES_VADDR && addr < MODULES_END) return 1; #endif return is_vmalloc_addr(x); } /* * Walk a vmap address to the struct page it maps. */ struct page *vmalloc_to_page(const void *vmalloc_addr) { unsigned long addr = (unsigned long) vmalloc_addr; struct page *page = NULL; pgd_t *pgd = pgd_offset_k(addr); /* * XXX we might need to change this if we add VIRTUAL_BUG_ON for * architectures that do not vmalloc module space */ VIRTUAL_BUG_ON(!is_vmalloc_or_module_addr(vmalloc_addr)); if (!pgd_none(*pgd)) { pud_t *pud = pud_offset(pgd, addr); if (!pud_none(*pud)) { pmd_t *pmd = pmd_offset(pud, addr); if (!pmd_none(*pmd)) { pte_t *ptep, pte; ptep = pte_offset_map(pmd, addr); pte = *ptep; if (pte_present(pte)) page = pte_page(pte); pte_unmap(ptep); } } } return page; } EXPORT_SYMBOL(vmalloc_to_page); /* * Map a vmalloc()-space virtual address to the physical page frame number. */ unsigned long vmalloc_to_pfn(const void *vmalloc_addr) { return page_to_pfn(vmalloc_to_page(vmalloc_addr)); } EXPORT_SYMBOL(vmalloc_to_pfn); /*** Global kva allocator ***/ #define VM_LAZY_FREE 0x01 #define VM_LAZY_FREEING 0x02 #define VM_VM_AREA 0x04 static DEFINE_SPINLOCK(vmap_area_lock); /* 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 */ static struct rb_node *free_vmap_cache; static unsigned long cached_hole_size; static unsigned long cached_vstart; static unsigned long cached_align; static unsigned long vmap_area_pcpu_hole; static struct vmap_area *__find_vmap_area(unsigned long addr) { struct rb_node *n = vmap_area_root.rb_node; while (n) { struct vmap_area *va; va = rb_entry(n, struct vmap_area, rb_node); if (addr < va->va_start) n = n->rb_left; else if (addr >= va->va_end) n = n->rb_right; else return va; } return NULL; } static void __insert_vmap_area(struct vmap_area *va) { struct rb_node **p = &vmap_area_root.rb_node; struct rb_node *parent = NULL; struct rb_node *tmp; while (*p) { struct vmap_area *tmp_va; parent = *p; tmp_va = rb_entry(parent, struct vmap_area, rb_node); if (va->va_start < tmp_va->va_end) p = &(*p)->rb_left; else if (va->va_end > tmp_va->va_start) p = &(*p)->rb_right; else BUG(); } rb_link_node(&va->rb_node, parent, p); rb_insert_color(&va->rb_node, &vmap_area_root); /* address-sort this list */ tmp = rb_prev(&va->rb_node); if (tmp) { struct vmap_area *prev; prev = rb_entry(tmp, struct vmap_area, rb_node); list_add_rcu(&va->list, &prev->list); } else list_add_rcu(&va->list, &vmap_area_list); } static void purge_vmap_area_lazy(void); /* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. */ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask) { struct vmap_area *va; struct rb_node *n; unsigned long addr; int purged = 0; struct vmap_area *first; BUG_ON(!size); BUG_ON(offset_in_page(size)); BUG_ON(!is_power_of_2(align)); va = kmalloc_node(sizeof(struct vmap_area), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); /* * Only scan the relevant parts containing pointers to other objects * to avoid false negatives. */ kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK); retry: spin_lock(&vmap_area_lock); /* * Invalidate cache if we have more permissive parameters. * cached_hole_size notes the largest hole noticed _below_ * the vmap_area cached in free_vmap_cache: if size fits * into that hole, we want to scan from vstart to reuse * the hole instead of allocating above free_vmap_cache. * Note that __free_vmap_area may update free_vmap_cache * without updating cached_hole_size or cached_align. */ if (!free_vmap_cache || size < cached_hole_size || vstart < cached_vstart || align < cached_align) { nocache: cached_hole_size = 0; free_vmap_cache = NULL; } /* record if we encounter less permissive parameters */ cached_vstart = vstart; cached_align = align; /* find starting point for our search */ if (free_vmap_cache) { first = rb_entry(free_vmap_cache, struct vmap_area, rb_node); addr = ALIGN(first->va_end, align); if (addr < vstart) goto nocache; if (addr + size < addr) goto overflow; } else { addr = ALIGN(vstart, align); if (addr + size < addr) goto overflow; n = vmap_area_root.rb_node; first = NULL; while (n) { struct vmap_area *tmp; tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_end >= addr) { first = tmp; if (tmp->va_start <= addr) break; n = n->rb_left; } else n = n->rb_right; } if (!first) goto found; } /* from the starting point, walk areas until a suitable hole is found */ while (addr + size > first->va_start && addr + size <= vend) { if (addr + cached_hole_size < first->va_start) cached_hole_size = first->va_start - addr; addr = ALIGN(first->va_end, align); if (addr + size < addr) goto overflow; if (list_is_last(&first->list, &vmap_area_list)) goto found; first = list_entry(first->list.next, struct vmap_area, list); } found: if (addr + size > vend) goto overflow; va->va_start = addr; va->va_end = addr + size; va->flags = 0; __insert_vmap_area(va); free_vmap_cache = &va->rb_node; spin_unlock(&vmap_area_lock); BUG_ON(va->va_start & (align-1)); BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); return va; overflow: spin_unlock(&vmap_area_lock); if (!purged) { purge_vmap_area_lazy(); purged = 1; goto retry; } if (printk_ratelimit()) pr_warn("vmap allocation for size %lu failed: " "use vmalloc= to increase size.\n", size); kfree(va); return ERR_PTR(-EBUSY); } static void __free_vmap_area(struct vmap_area *va) { BUG_ON(RB_EMPTY_NODE(&va->rb_node)); if (free_vmap_cache) { if (va->va_end < cached_vstart) { free_vmap_cache = NULL; } else { struct vmap_area *cache; cache = rb_entry(free_vmap_cache, struct vmap_area, rb_node); if (va->va_start <= cache->va_start) { free_vmap_cache = rb_prev(&va->rb_node); /* * We don't try to update cached_hole_size or * cached_align, but it won't go very wrong. */ } } } rb_erase(&va->rb_node, &vmap_area_root); RB_CLEAR_NODE(&va->rb_node); list_del_rcu(&va->list); /* * Track the highest possible candidate for pcpu area * allocation. Areas outside of 
/*
 *   linux/mm/fremap.c
 * 
 * Explicit pagetable population and nonlinear (random) mappings support.
 *
 * started by Ingo Molnar, Copyright (C) 2002, 2003
 */
#include <linux/backing-dev.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/file.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swapops.h>
#include <linux/rmap.h>
#include <linux/module.h>
#include <linux/syscalls.h>

#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>

static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long addr, pte_t *ptep)
{
	pte_t pte = *ptep;

	if (pte_present(pte)) {
		struct page *page;

		flush_cache_page(vma, addr, pte_pfn(pte));
		pte = ptep_clear_flush(vma, addr, ptep);
		page = vm_normal_page(vma, addr, pte);
		if (page) {
			if (pte_dirty(pte))
				set_page_dirty(page);
			page_remove_rmap(page, vma);
			page_cache_release(page);
			update_hiwater_rss(mm);
			dec_mm_counter(mm, file_rss);
		}
	} else {
		if (!pte_file(pte))
			free_swap_and_cache(pte_to_swp_entry(pte));
		pte_clear_not_present_full(mm, addr, ptep, 0);
	}
}

/*
 * Install a file pte to a given virtual memory address, release any
 * previously existing mapping.
 */
static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
		unsigned long addr, unsigned long pgoff, pgprot_t prot)
{
	int err = -ENOMEM;
	pte_t *pte;
	spinlock_t *ptl;

	pte = get_locked_pte(mm, addr, &ptl);
	if (!pte)
		goto out;

	if (!pte_none(*pte))
		zap_pte(mm, vma, addr, pte);

	set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff));
	/*
	 * We don't need to run update_mmu_cache() here because the "file pte"
	 * being installed by install_file_pte() is not a real pte - it's a
	 * non-present entry (like a swap entry), noting what file offset should
	 * be mapped there when there's a fault (in a non-linear vma where
	 * that's not obvious).
	 */
	pte_unmap_unlock(pte, ptl);
	err = 0;
out:
	return err;
}

static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma,
			unsigned long addr, unsigned long size, pgoff_t pgoff)
{
	int err;

	do {
		err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot);
		if (err)
			return err;

		size -= PAGE_SIZE;
		addr += PAGE_SIZE;
		pgoff++;
	} while (size);

        return 0;

}

/**
 * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma
 * @start: start of the remapped virtual memory range
 * @size: size of the remapped virtual memory range
 * @prot: new protection bits of the range (see NOTE)
 * @pgoff: to-be-mapped page of the backing store file
 * @flags: 0 or MAP_NONBLOCKED - the later will cause no IO.
 *
 * sys_remap_file_pages remaps arbitrary pages of an existing VM_SHARED vma
 * (shared backing store file).
 *
 * This syscall works purely via pagetables, so it's the most efficient
 * way to map the same (large) file into a given virtual window. Unlike
 * mmap()/mremap() it does not create any new vmas. The new mappings are
 * also safe across swapout.
 *
 * NOTE: the @prot parameter right now is ignored (but must be zero),
 * and the vma's default protection is used. Arbitrary protections
 * might be implemented in the future.
 */
asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
	unsigned long prot, unsigned long pgoff, unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct address_space *mapping;
	unsigned long end = start + size;
	struct vm_area_struct *vma;
	int err = -EINVAL;
	int has_write_lock = 0;

	if (prot)
		return err;
	/*
	 * Sanitize the syscall parameters:
	 */
	start = start & PAGE_MASK;
	size = size & PAGE_MASK;

	/* Does the address range wrap, or is the span zero-sized? */
	if (start + size <= start)
		return err;

	/* Can we represent this offset inside this architecture's pte's? */
#if PTE_FILE_MAX_BITS < BITS_PER_LONG
	if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS))
		return err;
#endif

	/* We need down_write() to change vma->vm_flags. */
	down_read(&mm->mmap_sem);
 retry:
	vma = find_vma(mm, start);

	/*
	 * Make sure the vma is shared, that it supports prefaulting,
	 * and that the remapped range is valid and fully within
	 * the single existing vma.  vm_private_data is used as a
	 * swapout cursor in a VM_NONLINEAR vma.
	 */
	if (!vma || !(vma->vm_flags & VM_SHARED))
		goto out;

	if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR))
		goto out;

	if (!(vma->vm_flags & VM_CAN_NONLINEAR))
		goto out;

	if (end <= start || start < vma->vm_start || end > vma->vm_end)
		goto out;

	/* Must set VM_NONLINEAR before any pages are populated. */
	if (!(vma->vm_flags & VM_NONLINEAR)) {
		/* Don't need a nonlinear mapping, exit success */
		if (pgoff == linear_page_index(vma, start)) {
			err = 0;
			goto out;
		}

		if (!has_write_lock) {
			up_read(&mm->mmap_sem);
			down_write(&mm->mmap_sem);
			has_write_lock = 1;
			goto retry;
		}
		mapping = vma->vm_file->f_mapping;
		/*
		 * page_mkclean doesn't work on nonlinear vmas, so if
		 * dirty pages need to be accounted, emulate with linear
		 * vmas.
		 */
		if (mapping_cap_account_dirty(mapping)) {
			unsigned long addr;
			struct file *file = vma->vm_file;

			flags &= MAP_NONBLOCK;
			get_file(file);
			addr = mmap_region(file, start, size,
					flags, vma->vm_flags, pgoff, 1);
			fput(file);
			if (IS_ERR_VALUE(addr)) {
				err = addr;
			} else {
				BUG_ON(addr != start);
				err = 0;
			}
			goto out;
		}
		spin_lock(&mapping->i_mmap_lock);
		flush_dcache_mmap_lock(mapping);
		vma->vm_flags |= VM_NONLINEAR;
		vma_prio_tree_remove(vma, &mapping->i_mmap);
		vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
		flush_dcache_mmap_unlock(mapping);
		spin_unlock(&mapping->i_mmap_lock);
	}

	err = populate_range(mm, vma, start, size, pgoff);
	if (!err && !(flags & MAP_NONBLOCK)) {
		if (unlikely(has_write_lock)) {
			downgrade_write(&mm->mmap_sem);
			has_write_lock = 0;
		}
		make_pages_present(start, start+size);
	}

	/*
	 * We can't clear VM_NONLINEAR because we'd have to do
	 * it after ->populate completes, and that would prevent
	 * downgrading the lock.  (Locks can't be upgraded).
	 */

out:
	if (likely(!has_write_lock))
		up_read(&mm->mmap_sem);
	else
		up_write(&mm->mmap_sem);

	return err;
}
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-04-30 12:26:40 +0000
GFP_KERNEL #elif defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) #define GFP_VMALLOC32 GFP_DMA | GFP_KERNEL #else #define GFP_VMALLOC32 GFP_KERNEL #endif /** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) * @size: allocation size * * Allocate enough 32bit PA addressable pages to cover @size from the * page level allocator and map them into contiguous kernel virtual space. */ void *vmalloc_32(unsigned long size) { return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); } EXPORT_SYMBOL(vmalloc_32); /** * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory * @size: allocation size * * The resulting memory area is 32bit addressable and zeroed so it can be * mapped to userspace without leaking data. */ void *vmalloc_32_user(unsigned long size) { struct vm_struct *area; void *ret; ret = __vmalloc_node(size, 1, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); if (ret) { area = find_vm_area(ret); area->flags |= VM_USERMAP; } return ret; } EXPORT_SYMBOL(vmalloc_32_user); /* * small helper routine , copy contents to buf from addr. * If the page is not present, fill zero. */ static int aligned_vread(char *buf, char *addr, unsigned long count) { struct page *p; int copied = 0; while (count) { unsigned long offset, length; offset = offset_in_page(addr); length = PAGE_SIZE - offset; if (length > count) length = count; p = vmalloc_to_page(addr); /* * To do safe access to this _mapped_ area, we need * lock. But adding lock here means that we need to add * overhead of vmalloc()/vfree() calles for this _debug_ * interface, rarely used. Instead of that, we'll use * kmap() and get small overhead in this access function. */ if (p) { /* * we can expect USER0 is not used (see vread/vwrite's * function description) */ void *map = kmap_atomic(p); memcpy(buf, map + offset, length); kunmap_atomic(map); } else memset(buf, 0, length); addr += length; buf += length; copied += length; count -= length; } return copied; } static int aligned_vwrite(char *buf, char *addr, unsigned long count) { struct page *p; int copied = 0; while (count) { unsigned long offset, length; offset = offset_in_page(addr); length = PAGE_SIZE - offset; if (length > count) length = count; p = vmalloc_to_page(addr); /* * To do safe access to this _mapped_ area, we need * lock. But adding lock here means that we need to add * overhead of vmalloc()/vfree() calles for this _debug_ * interface, rarely used. Instead of that, we'll use * kmap() and get small overhead in this access function. */ if (p) { /* * we can expect USER0 is not used (see vread/vwrite's * function description) */ void *map = kmap_atomic(p); memcpy(map + offset, buf, length); kunmap_atomic(map); } addr += length; buf += length; copied += length; count -= length; } return copied; } /** * vread() - read vmalloc area in a safe way. * @buf: buffer for reading data * @addr: vm address. * @count: number of bytes to be read. * * Returns # of bytes which addr and buf should be increased. * (same number to @count). Returns 0 if [addr...addr+count) doesn't * includes any intersect with alive vmalloc area. * * This function checks that addr is a valid vmalloc'ed area, and * copy data from that area to a given buffer. If the given memory range * of [addr...addr+count) includes some valid address, data is copied to * proper area of @buf. If there are memory holes, they'll be zero-filled. * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without * any informaion, as /dev/kmem. * */ long vread(char *buf, char *addr, unsigned long count) { struct vmap_area *va; struct vm_struct *vm; char *vaddr, *buf_start = buf; unsigned long buflen = count; unsigned long n; /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; 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 + get_vm_area_size(vm)) continue; while (addr < vaddr) { if (count == 0) goto finished; *buf = '\0'; buf++; addr++; count--; } n = vaddr + get_vm_area_size(vm) - addr; if (n > count) n = count; if (!(vm->flags & VM_IOREMAP)) aligned_vread(buf, addr, n); else /* IOREMAP area is treated as memory hole */ memset(buf, 0, n); buf += n; addr += n; count -= n; } finished: spin_unlock(&vmap_area_lock); if (buf == buf_start) return 0; /* zero-fill memory holes */ if (buf != buf_start + buflen) memset(buf, 0, buflen - (buf - buf_start)); return buflen; } /** * vwrite() - write vmalloc area in a safe way. * @buf: buffer for source data * @addr: vm address. * @count: number of bytes to be read. * * Returns # of bytes which addr and buf should be incresed. * (same number to @count). * If [addr...addr+count) doesn't includes any intersect with valid * vmalloc area, returns 0. * * This function checks that addr is a valid vmalloc'ed area, and * copy data from a buffer to the given addr. If specified range of * [addr...addr+count) includes some valid address, data is copied from * proper area of @buf. If there are memory holes, no copy to hole. * IOREMAP area is treated as memory hole and no copy is done. * * If [addr...addr+count) doesn't includes any intersects with alive * vm_struct area, returns 0. @buf should be kernel's buffer. * * Note: In usual ops, vwrite() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without * any informaion, as /dev/kmem. */ long vwrite(char *buf, char *addr, unsigned long count) { struct vmap_area *va; struct vm_struct *vm; char *vaddr; unsigned long n, buflen; int copied = 0; /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; buflen = count; 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 + get_vm_area_size(vm)) continue; while (addr < vaddr) { if (count == 0) goto finished; buf++; addr++; count--; } n = vaddr + get_vm_area_size(vm) - addr; if (n > count) n = count; if (!(vm->flags & VM_IOREMAP)) { aligned_vwrite(buf, addr, n); copied++; } buf += n; addr += n; count -= n; } finished: spin_unlock(&vmap_area_lock); if (!copied) return 0; return buflen; } /** * remap_vmalloc_range_partial - map vmalloc pages to userspace * @vma: vma to cover * @uaddr: target user address to start at * @kaddr: virtual address of vmalloc kernel memory * @size: size of map area * * Returns: 0 for success, -Exxx on failure * * This function checks that @kaddr is a valid vmalloc'ed area, * and that it is big enough to cover the range starting at * @uaddr in @vma. Will return failure if that criteria isn't * met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, unsigned long size) { struct vm_struct *area; size = PAGE_ALIGN(size); if (!PAGE_ALIGNED(uaddr) || !PAGE_ALIGNED(kaddr)) return -EINVAL; area = find_vm_area(kaddr); if (!area) return -EINVAL; if (!(area->flags & VM_USERMAP)) return -EINVAL; if (kaddr + size > area->addr + area->size) return -EINVAL; do { struct page *page = vmalloc_to_page(kaddr); int ret; ret = vm_insert_page(vma, uaddr, page); if (ret) return ret; uaddr += PAGE_SIZE; kaddr += PAGE_SIZE; size -= PAGE_SIZE; } while (size > 0); vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; return 0; } EXPORT_SYMBOL(remap_vmalloc_range_partial); /** * remap_vmalloc_range - map vmalloc pages to userspace * @vma: vma to cover (map full range of vma) * @addr: vmalloc memory * @pgoff: number of pages into addr before first page to map * * Returns: 0 for success, -Exxx on failure * * This function checks that addr is a valid vmalloc'ed area, and * that it is big enough to cover the vma. Will return failure if * that criteria isn't met. * * Similar to remap_pfn_range() (see mm/memory.c) */ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff) { return remap_vmalloc_range_partial(vma, vma->vm_start, addr + (pgoff << PAGE_SHIFT), vma->vm_end - vma->vm_start); } EXPORT_SYMBOL(remap_vmalloc_range); /* * Implement a stub for vmalloc_sync_all() if the architecture chose not to * have one. */ void __weak vmalloc_sync_all(void) { } static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data) { pte_t ***p = data; if (p) { *(*p) = pte; (*p)++; } return 0; } /** * alloc_vm_area - allocate a range of kernel address space * @size: size of the area * @ptes: returns the PTEs for the address space * * Returns: NULL on failure, vm_struct on success * * This function reserves a range of kernel address space, and * allocates pagetables to map that range. No actual mappings * are created. * * If @ptes is non-NULL, pointers to the PTEs (in init_mm) * allocated for the VM area are returned. */ struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes) { struct vm_struct *area; area = get_vm_area_caller(size, VM_IOREMAP, __builtin_return_address(0)); if (area == NULL) return NULL; /* * This ensures that page tables are constructed for this region * of kernel virtual address space and mapped into init_mm. */ if (apply_to_page_range(&init_mm, (unsigned long)area->addr, size, f, ptes ? &ptes : NULL)) { free_vm_area(area); return NULL; } return area; } EXPORT_SYMBOL_GPL(alloc_vm_area); void free_vm_area(struct vm_struct *area) { struct vm_struct *ret; ret = remove_vm_area(area->addr); BUG_ON(ret != area); kfree(area); } EXPORT_SYMBOL_GPL(free_vm_area); #ifdef CONFIG_SMP 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 * * 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 with GFP_KERNEL. 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) { 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; /* verify parameters and allocate data structures */ BUG_ON(offset_in_page(align) || !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 = kcalloc(nr_vms, sizeof(vms[0]), GFP_KERNEL); vas = kcalloc(nr_vms, sizeof(vas[0]), GFP_KERNEL); if (!vas || !vms) goto err_free2; for (area = 0; area < nr_vms; area++) { vas[area] = kzalloc(sizeof(struct vmap_area), GFP_KERNEL); vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL); 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++) setup_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++) { kfree(vas[area]); kfree(vms[area]); } err_free2: 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); } #endif /* CONFIG_SMP */ #ifdef CONFIG_PROC_FS static void *s_start(struct seq_file *m, loff_t *pos) __acquires(&vmap_area_lock) { loff_t n = *pos; struct vmap_area *va; spin_lock(&vmap_area_lock); va = list_entry((&vmap_area_list)->next, typeof(*va), list); while (n > 0 && &va->list != &vmap_area_list) { n--; va = list_entry(va->list.next, typeof(*va), list); } 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 vmap_area *va = p, *next; ++*pos; 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(&vmap_area_lock) { spin_unlock(&vmap_area_lock); } static void show_numa_info(struct seq_file *m, struct vm_struct *v) { if (IS_ENABLED(CONFIG_NUMA)) { unsigned int nr, *counters = m->private; if (!counters) return; if (v->flags & VM_UNINITIALIZED) return; /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ smp_rmb(); memset(counters, 0, nr_node_ids * sizeof(unsigned int)); for (nr = 0; nr < v->nr_pages; nr++) counters[page_to_nid(v->pages[nr])]++; for_each_node_state(nr, N_HIGH_MEMORY) if (counters[nr]) seq_printf(m, " N%u=%u", nr, counters[nr]); } } static int s_show(struct seq_file *m, void *p) { struct vmap_area *va = p; struct vm_struct *v; /* * s_show can encounter race with remove_vm_area, !VM_VM_AREA on * behalf of vmap area is being tear down or vm_map_ram allocation. */ if (!(va->flags & VM_VM_AREA)) return 0; v = va->vm; seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); if (v->caller) seq_printf(m, " %pS", v->caller); if (v->nr_pages) seq_printf(m, " pages=%d", v->nr_pages); if (v->phys_addr) seq_printf(m, " phys=%llx", (unsigned long long)v->phys_addr); if (v->flags & VM_IOREMAP) seq_puts(m, " ioremap"); if (v->flags & VM_ALLOC) seq_puts(m, " vmalloc"); if (v->flags & VM_MAP) seq_puts(m, " vmap"); if (v->flags & VM_USERMAP) seq_puts(m, " user"); if (v->flags & VM_VPAGES) seq_puts(m, " vpages"); show_numa_info(m, v); seq_putc(m, '\n'); return 0; } static const struct seq_operations vmalloc_op = { .start = s_start, .next = s_next, .stop = s_stop, .show = s_show, }; static int vmalloc_open(struct inode *inode, struct file *file) { if (IS_ENABLED(CONFIG_NUMA)) return seq_open_private(file, &vmalloc_op, nr_node_ids * sizeof(unsigned int)); else return seq_open(file, &vmalloc_op); } static const struct file_operations proc_vmalloc_operations = { .open = vmalloc_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_private, }; static int __init proc_vmalloc_init(void) { proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations); return 0; } module_init(proc_vmalloc_init); #endif