// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 1993 Linus Torvalds * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000 * Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002 * Numa awareness, Christoph Lameter, SGI, June 2005 * Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019
*/
p4d = p4d_offset(pgd, addr); do {
next = p4d_addr_end(addr, end);
p4d_clear_huge(p4d); if (p4d_bad(*p4d))
*mask |= PGTBL_P4D_MODIFIED;
if (p4d_none_or_clear_bad(p4d)) continue;
vunmap_pud_range(p4d, addr, next, mask);
} while (p4d++, addr = next, addr != end);
}
/* * vunmap_range_noflush is similar to vunmap_range, but does not * flush caches or TLBs. * * The caller is responsible for calling flush_cache_vmap() before calling * this function, and flush_tlb_kernel_range after it has returned * successfully (and before the addresses are expected to cause a page fault * or be re-mapped for something else, if TLB flushes are being delayed or * coalesced). * * This is an internal function only. Do not use outside mm/.
*/ void __vunmap_range_noflush(unsignedlong start, unsignedlong end)
{ unsignedlong next;
pgd_t *pgd; unsignedlong addr = start;
pgtbl_mod_mask mask = 0;
BUG_ON(addr >= end);
pgd = pgd_offset_k(addr); do {
next = pgd_addr_end(addr, end); if (pgd_bad(*pgd))
mask |= PGTBL_PGD_MODIFIED; if (pgd_none_or_clear_bad(pgd)) continue;
vunmap_p4d_range(pgd, addr, next, &mask);
} while (pgd++, addr = next, addr != end);
if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
arch_sync_kernel_mappings(start, end);
}
/** * vunmap_range - unmap kernel virtual addresses * @addr: start of the VM area to unmap * @end: end of the VM area to unmap (non-inclusive) * * Clears any present PTEs in the virtual address range, flushes TLBs and * caches. Any subsequent access to the address before it has been re-mapped * is a kernel bug.
*/ void vunmap_range(unsignedlong addr, unsignedlong end)
{
flush_cache_vunmap(addr, end);
vunmap_range_noflush(addr, end);
flush_tlb_kernel_range(addr, end);
}
BUG_ON(addr >= end);
pgd = pgd_offset_k(addr); do {
next = pgd_addr_end(addr, end); if (pgd_bad(*pgd))
mask |= PGTBL_PGD_MODIFIED;
err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) break;
} while (pgd++, addr = next, addr != end);
if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
arch_sync_kernel_mappings(start, end);
return err;
}
/* * vmap_pages_range_noflush is similar to vmap_pages_range, but does not * flush caches. * * The caller is responsible for calling flush_cache_vmap() after this * function returns successfully and before the addresses are accessed. * * This is an internal function only. Do not use outside mm/.
*/ int __vmap_pages_range_noflush(unsignedlong addr, unsignedlong end,
pgprot_t prot, struct page **pages, unsignedint page_shift)
{ unsignedint i, nr = (end - addr) >> PAGE_SHIFT;
/** * vmap_pages_range - map pages to a kernel virtual address * @addr: start of the VM area to map * @end: end of the VM area to map (non-inclusive) * @prot: page protection flags to use * @pages: pages to map (always PAGE_SIZE pages) * @page_shift: maximum shift that the pages may be mapped with, @pages must * be aligned and contiguous up to at least this shift. * * RETURNS: * 0 on success, -errno on failure.
*/ int vmap_pages_range(unsignedlong addr, unsignedlong end,
pgprot_t prot, struct page **pages, unsignedint page_shift)
{ int err;
int is_vmalloc_or_module_addr(constvoid *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.
*/ #ifdefined(CONFIG_EXECMEM) && defined(MODULES_VADDR) unsignedlong addr = (unsignedlong)kasan_reset_tag(x); if (addr >= MODULES_VADDR && addr < MODULES_END) return 1; #endif return is_vmalloc_addr(x);
}
EXPORT_SYMBOL_GPL(is_vmalloc_or_module_addr);
/* * Walk a vmap address to the struct page it maps. Huge vmap mappings will * return the tail page that corresponds to the base page address, which * matches small vmap mappings.
*/ struct page *vmalloc_to_page(constvoid *vmalloc_addr)
{ unsignedlong addr = (unsignedlong) vmalloc_addr; struct page *page = NULL;
pgd_t *pgd = pgd_offset_k(addr);
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
/* * 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)) return NULL; if (WARN_ON_ONCE(pgd_leaf(*pgd))) return NULL; /* XXX: no allowance for huge pgd */ if (WARN_ON_ONCE(pgd_bad(*pgd))) return NULL;
p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) return NULL; if (p4d_leaf(*p4d)) return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(p4d_bad(*p4d))) return NULL;
pud = pud_offset(p4d, addr); if (pud_none(*pud)) return NULL; if (pud_leaf(*pud)) return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pud_bad(*pud))) return NULL;
pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) return NULL; if (pmd_leaf(*pmd)) return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); if (WARN_ON_ONCE(pmd_bad(*pmd))) return NULL;
/* * This kmem_cache is used for vmap_area objects. Instead of * allocating from slab we reuse an object from this cache to * make things faster. Especially in "no edge" splitting of * free block.
*/ staticstruct kmem_cache *vmap_area_cachep;
/* * This linked list is used in pair with free_vmap_area_root. * It gives O(1) access to prev/next to perform fast coalescing.
*/ static LIST_HEAD(free_vmap_area_list);
/* * This augment red-black tree represents the free vmap space. * All vmap_area objects in this tree are sorted by va->va_start * address. It is used for allocation and merging when a vmap * object is released. * * Each vmap_area node contains a maximum available free block * of its sub-tree, right or left. Therefore it is possible to * find a lowest match of free area.
*/ staticstruct rb_root free_vmap_area_root = RB_ROOT;
/* * Preload a CPU with one object for "no edge" split case. The * aim is to get rid of allocations from the atomic context, thus * to use more permissive allocation masks.
*/ static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node);
/* * This structure defines a single, solid model where a list and * rb-tree are part of one entity protected by the lock. Nodes are * sorted in ascending order, thus for O(1) access to left/right * neighbors a list is used as well as for sequential traversal.
*/ struct rb_list { struct rb_root root; struct list_head head;
spinlock_t lock;
};
/* * A fast size storage contains VAs up to 1M size. A pool consists * of linked between each other ready to go VAs of certain sizes. * An index in the pool-array corresponds to number of pages + 1.
*/ #define MAX_VA_SIZE_PAGES 256
/* * An effective vmap-node logic. Users make use of nodes instead * of a global heap. It allows to balance an access and mitigate * contention.
*/ staticstruct vmap_node { /* Simple size segregated storage. */ struct vmap_pool pool[MAX_VA_SIZE_PAGES];
spinlock_t pool_lock; bool skip_populate;
/* Bookkeeping data of this node. */ struct rb_list busy; struct rb_list lazy;
/* * Initial setup consists of one single node, i.e. a balancing * is fully disabled. Later on, after vmap is initialized these * parameters are updated based on a system capacity.
*/ staticstruct vmap_node *vmap_nodes = &single; static __read_mostly unsignedint nr_vmap_nodes = 1; static __read_mostly unsignedint vmap_zone_size = 1;
/* A simple iterator over all vmap-nodes. */ #define for_each_vmap_node(vn) \ for ((vn) = &vmap_nodes[0]; \
(vn) < &vmap_nodes[nr_vmap_nodes]; (vn)++)
WARN_ONCE(1, "An address 0x%p is out-of-bounds.\n", node); return 0;
}
/* * We use the value 0 to represent "no node", that is why * an encoded value will be the node-id incremented by 1. * It is always greater then 0. A valid node_id which can * be encoded is [0:nr_vmap_nodes - 1]. If a passed node_id * is not valid 0 is returned.
*/ staticunsignedint
encode_vn_id(unsignedint node_id)
{ /* Can store U8_MAX [0:254] nodes. */ if (node_id < nr_vmap_nodes) return (node_id + 1) << BITS_PER_BYTE;
/* Warn and no node encoded. */
WARN_ONCE(1, "Encode wrong node id (%u)\n", node_id); return 0;
}
/* * Returns an encoded node-id, the valid range is within * [0:nr_vmap_nodes-1] values. Otherwise nr_vmap_nodes is * returned if extracted data is wrong.
*/ staticunsignedint
decode_vn_id(unsignedint val)
{ unsignedint node_id = (val >> BITS_PER_BYTE) - 1;
/* Can store U8_MAX [0:254] nodes. */ if (node_id < nr_vmap_nodes) return node_id;
/* If it was _not_ zero, warn. */
WARN_ONCE(node_id != UINT_MAX, "Decode wrong node id (%d)\n", node_id);
return nr_vmap_nodes;
}
staticbool
is_vn_id_valid(unsignedint node_id)
{ if (node_id < nr_vmap_nodes) returntrue;
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;
}
/* * Returns a node where a first VA, that satisfies addr < va_end, resides. * If success, a node is locked. A user is responsible to unlock it when a * VA is no longer needed to be accessed. * * Returns NULL if nothing found.
*/ staticstruct vmap_node *
find_vmap_area_exceed_addr_lock(unsignedlong addr, struct vmap_area **va)
{ unsignedlong va_start_lowest; struct vmap_node *vn;
if (*va) if (!va_start_lowest || (*va)->va_start < va_start_lowest)
va_start_lowest = (*va)->va_start;
spin_unlock(&vn->busy.lock);
}
/* * Check if found VA exists, it might have gone away. In this case we * repeat the search because a VA has been removed concurrently and we * need to proceed to the next one, which is a rare case.
*/ if (va_start_lowest) {
vn = addr_to_node(va_start_lowest);
/* * This function returns back addresses of parent node * and its left or right link for further processing. * * Otherwise NULL is returned. In that case all further * steps regarding inserting of conflicting overlap range * have to be declined and actually considered as a bug.
*/ static __always_inline struct rb_node **
find_va_links(struct vmap_area *va, struct rb_root *root, struct rb_node *from, struct rb_node **parent)
{ struct vmap_area *tmp_va; struct rb_node **link;
if (root) {
link = &root->rb_node; if (unlikely(!*link)) {
*parent = NULL; return link;
}
} else {
link = &from;
}
/* * Go to the bottom of the tree. When we hit the last point * we end up with parent rb_node and correct direction, i name * it link, where the new va->rb_node will be attached to.
*/ do {
tmp_va = rb_entry(*link, struct vmap_area, rb_node);
/* * During the traversal we also do some sanity check. * Trigger the BUG() if there are sides(left/right) * or full overlaps.
*/ if (va->va_end <= tmp_va->va_start)
link = &(*link)->rb_left; elseif (va->va_start >= tmp_va->va_end)
link = &(*link)->rb_right; else {
WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n",
va->va_start, va->va_end, tmp_va->va_start, tmp_va->va_end);
if (unlikely(!parent)) /* * The red-black tree where we try to find VA neighbors * before merging or inserting is empty, i.e. it means * there is no free vmap space. Normally it does not * happen but we handle this case anyway.
*/ return NULL;
list = &rb_entry(parent, struct vmap_area, rb_node)->list; return (&parent->rb_right == link ? list->next : list);
}
static __always_inline void
__link_va(struct vmap_area *va, struct rb_root *root, struct rb_node *parent, struct rb_node **link, struct list_head *head, bool augment)
{ /* * VA is still not in the list, but we can * identify its future previous list_head node.
*/ if (likely(parent)) {
head = &rb_entry(parent, struct vmap_area, rb_node)->list; if (&parent->rb_right != link)
head = head->prev;
}
/* Insert to the rb-tree */
rb_link_node(&va->rb_node, parent, link); if (augment) { /* * Some explanation here. Just perform simple insertion * to the tree. We do not set va->subtree_max_size to * its current size before calling rb_insert_augmented(). * It is because we populate the tree from the bottom * to parent levels when the node _is_ in the tree. * * Therefore we set subtree_max_size to zero after insertion, * to let __augment_tree_propagate_from() puts everything to * the correct order later on.
*/
rb_insert_augmented(&va->rb_node,
root, &free_vmap_area_rb_augment_cb);
va->subtree_max_size = 0;
} else {
rb_insert_color(&va->rb_node, root);
}
/* Address-sort this list */
list_add(&va->list, head);
}
/* * This function populates subtree_max_size from bottom to upper * levels starting from VA point. The propagation must be done * when VA size is modified by changing its va_start/va_end. Or * in case of newly inserting of VA to the tree. * * It means that __augment_tree_propagate_from() must be called: * - After VA has been inserted to the tree(free path); * - After VA has been shrunk(allocation path); * - After VA has been increased(merging path). * * Please note that, it does not mean that upper parent nodes * and their subtree_max_size are recalculated all the time up * to the root node. * * 4--8 * /\ * / \ * / \ * 2--2 8--8 * * For example if we modify the node 4, shrinking it to 2, then * no any modification is required. If we shrink the node 2 to 1 * its subtree_max_size is updated only, and set to 1. If we shrink * the node 8 to 6, then its subtree_max_size is set to 6 and parent * node becomes 4--6.
*/ static __always_inline void
augment_tree_propagate_from(struct vmap_area *va)
{ /* * Populate the tree from bottom towards the root until * the calculated maximum available size of checked node * is equal to its current one.
*/
free_vmap_area_rb_augment_cb_propagate(&va->rb_node, NULL);
/* * Merge de-allocated chunk of VA memory with previous * and next free blocks. If coalesce is not done a new * free area is inserted. If VA has been merged, it is * freed. * * Please note, it can return NULL in case of overlap * ranges, followed by WARN() report. Despite it is a * buggy behaviour, a system can be alive and keep * ongoing.
*/ static __always_inline struct vmap_area *
__merge_or_add_vmap_area(struct vmap_area *va, struct rb_root *root, struct list_head *head, bool augment)
{ struct vmap_area *sibling; struct list_head *next; struct rb_node **link; struct rb_node *parent; bool merged = false;
/* * Find a place in the tree where VA potentially will be * inserted, unless it is merged with its sibling/siblings.
*/
link = find_va_links(va, root, NULL, &parent); if (!link) return NULL;
/* * Get next node of VA to check if merging can be done.
*/
next = get_va_next_sibling(parent, link); if (unlikely(next == NULL)) goto insert;
/* * start end * | | * |<------VA------>|<-----Next----->| * | | * start end
*/ if (next != head) {
sibling = list_entry(next, struct vmap_area, list); if (sibling->va_start == va->va_end) {
sibling->va_start = va->va_start;
/* Point to the new merged area. */
va = sibling;
merged = true;
}
}
/* * start end * | | * |<-----Prev----->|<------VA------>| * | | * start end
*/ if (next->prev != head) {
sibling = list_entry(next->prev, struct vmap_area, list); if (sibling->va_end == va->va_start) { /* * If both neighbors are coalesced, it is important * to unlink the "next" node first, followed by merging * with "previous" one. Otherwise the tree might not be * fully populated if a sibling's augmented value is * "normalized" because of rotation operations.
*/ if (merged)
__unlink_va(va, root, augment);
/* Can be overflowed due to big size or alignment. */ if (nva_start_addr + size < nva_start_addr ||
nva_start_addr < vstart) returnfalse;
return (nva_start_addr + size <= va->va_end);
}
/* * Find the first free block(lowest start address) in the tree, * that will accomplish the request corresponding to passing * parameters. Please note, with an alignment bigger than PAGE_SIZE, * a search length is adjusted to account for worst case alignment * overhead.
*/ static __always_inline struct vmap_area *
find_vmap_lowest_match(struct rb_root *root, unsignedlong size, unsignedlong align, unsignedlong vstart, bool adjust_search_size)
{ struct vmap_area *va; struct rb_node *node; unsignedlong length;
/* Start from the root. */
node = root->rb_node;
/* Adjust the search size for alignment overhead. */
length = adjust_search_size ? size + align - 1 : size;
while (node) {
va = rb_entry(node, struct vmap_area, rb_node);
/* * Does not make sense to go deeper towards the right * sub-tree if it does not have a free block that is * equal or bigger to the requested search length.
*/ if (get_subtree_max_size(node->rb_right) >= length) {
node = node->rb_right; continue;
}
/* * OK. We roll back and find the first right sub-tree, * that will satisfy the search criteria. It can happen * due to "vstart" restriction or an alignment overhead * that is bigger then PAGE_SIZE.
*/ while ((node = rb_parent(node))) {
va = rb_entry(node, struct vmap_area, rb_node); if (is_within_this_va(va, size, align, vstart)) return va;
if (get_subtree_max_size(node->rb_right) >= length &&
vstart <= va->va_start) { /* * Shift the vstart forward. Please note, we update it with * parent's start address adding "1" because we do not want * to enter same sub-tree after it has already been checked * and no suitable free block found there.
*/
vstart = va->va_start + 1;
node = node->rb_right; break;
}
}
}
}
enum fit_type {
NOTHING_FIT = 0,
FL_FIT_TYPE = 1, /* full fit */
LE_FIT_TYPE = 2, /* left edge fit */
RE_FIT_TYPE = 3, /* right edge fit */
NE_FIT_TYPE = 4 /* no edge fit */
};
if (type == FL_FIT_TYPE) { /* * No need to split VA, it fully fits. * * | | * V NVA V * |---------------|
*/
unlink_va_augment(va, root);
kmem_cache_free(vmap_area_cachep, va);
} elseif (type == LE_FIT_TYPE) { /* * Split left edge of fit VA. * * | | * V NVA V R * |-------|-------|
*/
va->va_start += size;
} elseif (type == RE_FIT_TYPE) { /* * Split right edge of fit VA. * * | | * L V NVA V * |-------|-------|
*/
va->va_end = nva_start_addr;
} elseif (type == NE_FIT_TYPE) { /* * Split no edge of fit VA. * * | | * L V NVA V R * |---|-------|---|
*/
lva = __this_cpu_xchg(ne_fit_preload_node, NULL); if (unlikely(!lva)) { /* * For percpu allocator we do not do any pre-allocation * and leave it as it is. The reason is it most likely * never ends up with NE_FIT_TYPE splitting. In case of * percpu allocations offsets and sizes are aligned to * fixed align request, i.e. RE_FIT_TYPE and FL_FIT_TYPE * are its main fitting cases. * * There are a few exceptions though, as an example it is * a first allocation (early boot up) when we have "one" * big free space that has to be split. * * Also we can hit this path in case of regular "vmap" * allocations, if "this" current CPU was not preloaded. * See the comment in alloc_vmap_area() why. If so, then * GFP_NOWAIT is used instead to get an extra object for * split purpose. That is rare and most time does not * occur. * * What happens if an allocation gets failed. Basically, * an "overflow" path is triggered to purge lazily freed * areas to free some memory, then, the "retry" path is * triggered to repeat one more time. See more details * in alloc_vmap_area() function.
*/
lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); if (!lva) return -ENOMEM;
}
/* Check the "vend" restriction. */ if (nva_start_addr + size > vend) return -ERANGE;
/* Update the free vmap_area. */
ret = va_clip(root, head, va, nva_start_addr, size); if (WARN_ON_ONCE(ret)) return ret;
return nva_start_addr;
}
/* * Returns a start address of the newly allocated area, if success. * Otherwise an error value is returned that indicates failure.
*/ static __always_inline unsignedlong
__alloc_vmap_area(struct rb_root *root, struct list_head *head, unsignedlong size, unsignedlong align, unsignedlong vstart, unsignedlong vend)
{ bool adjust_search_size = true; unsignedlong nva_start_addr; struct vmap_area *va;
/* * Do not adjust when: * a) align <= PAGE_SIZE, because it does not make any sense. * All blocks(their start addresses) are at least PAGE_SIZE * aligned anyway; * b) a short range where a requested size corresponds to exactly * specified [vstart:vend] interval and an alignment > PAGE_SIZE. * With adjusted search length an allocation would not succeed.
*/ if (align <= PAGE_SIZE || (align > PAGE_SIZE && (vend - vstart) == size))
adjust_search_size = false;
va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size); if (unlikely(!va)) return -ENOENT;
#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK if (!IS_ERR_VALUE(nva_start_addr))
find_vmap_lowest_match_check(root, head, size, align); #endif
return nva_start_addr;
}
/* * Free a region of KVA allocated by alloc_vmap_area
*/ staticvoid free_vmap_area(struct vmap_area *va)
{ struct vmap_node *vn = addr_to_node(va->va_start);
/* * Remove from the busy tree/list.
*/
spin_lock(&vn->busy.lock);
unlink_va(va, &vn->busy.root);
spin_unlock(&vn->busy.lock);
/* * Insert/Merge it back to the free tree/list.
*/
spin_lock(&free_vmap_area_lock);
merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list);
spin_unlock(&free_vmap_area_lock);
}
/* * Preload this CPU with one extra vmap_area object. It is used * when fit type of free area is NE_FIT_TYPE. It guarantees that * a CPU that does an allocation is preloaded. * * We do it in non-atomic context, thus it allows us to use more * permissive allocation masks to be more stable under low memory * condition and high memory pressure.
*/ if (!this_cpu_read(ne_fit_preload_node))
va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node);
vp = size_to_va_pool(vn, size); if (!vp || list_empty(&vp->head)) return NULL;
spin_lock(&vn->pool_lock); if (!list_empty(&vp->head)) {
va = list_first_entry(&vp->head, struct vmap_area, list);
if (IS_ALIGNED(va->va_start, align)) { /* * Do some sanity check and emit a warning * if one of below checks detects an error.
*/
err |= (va_size(va) != size);
err |= (va->va_start < vstart);
err |= (va->va_end > vend);
if (!WARN_ON_ONCE(err)) {
list_del_init(&va->list);
WRITE_ONCE(vp->len, vp->len - 1);
} else {
va = NULL;
}
} else {
list_move_tail(&va->list, &vp->head);
va = NULL;
}
}
spin_unlock(&vn->pool_lock);
/* * Fallback to a global heap if not vmalloc or there * is only one node.
*/ if (vstart != VMALLOC_START || vend != VMALLOC_END ||
nr_vmap_nodes == 1) return NULL;
/* * Allocate a region of KVA of the specified size and alignment, within the * vstart and vend. If vm is passed in, the two will also be bound.
*/ staticstruct vmap_area *alloc_vmap_area(unsignedlong size, unsignedlong align, unsignedlong vstart, unsignedlong vend, int node, gfp_t gfp_mask, unsignedlong va_flags, struct vm_struct *vm)
{ struct vmap_node *vn; struct vmap_area *va; unsignedlong freed; unsignedlong addr; unsignedint vn_id; int purged = 0; int ret;
if (unlikely(!size || offset_in_page(size) || !is_power_of_2(align))) return ERR_PTR(-EINVAL);
if (unlikely(!vmap_initialized)) return ERR_PTR(-EBUSY);
/* Only reclaim behaviour flags are relevant. */
gfp_mask = gfp_mask & GFP_RECLAIM_MASK;
might_sleep();
/* * If a VA is obtained from a global heap(if it fails here) * it is anyway marked with this "vn_id" so it is returned * to this pool's node later. Such way gives a possibility * to populate pools based on users demand. * * On success a ready to go VA is returned.
*/
va = node_alloc(size, align, vstart, vend, &addr, &vn_id); if (!va) {
va = kmem_cache_alloc_node(vmap_area_cachep, gfp_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);
}
int register_vmap_purge_notifier(struct notifier_block *nb)
{ return blocking_notifier_chain_register(&vmap_notify_list, nb);
}
EXPORT_SYMBOL_GPL(register_vmap_purge_notifier);
int unregister_vmap_purge_notifier(struct notifier_block *nb)
{ return blocking_notifier_chain_unregister(&vmap_notify_list, nb);
}
EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier);
/* * lazy_max_pages is the maximum amount of virtual address space we gather up * before attempting to purge with a TLB flush. * * There is a tradeoff here: a larger number will cover more kernel page tables * and take slightly longer to purge, but it will linearly reduce the number of * global TLB flushes that must be performed. It would seem natural to scale * this number up linearly with the number of CPUs (because vmapping activity * could also scale linearly with the number of CPUs), however it is likely * that in practice, workloads might be constrained in other ways that mean * vmap activity will not scale linearly with CPUs. Also, I want to be * conservative and not introduce a big latency on huge systems, so go with * a less aggressive log scale. It will still be an improvement over the old * code, and it will be simple to change the scale factor if we find that it * becomes a problem on bigger systems.
*/ staticunsignedlong lazy_max_pages(void)
{ unsignedint log;
log = fls(num_online_cpus());
return log * (32UL * 1024 * 1024 / PAGE_SIZE);
}
/* * Serialize vmap purging. There is no actual critical section protected * by this lock, but we want to avoid concurrent calls for performance * reasons and to make the pcpu_get_vm_areas more deterministic.
*/ static DEFINE_MUTEX(vmap_purge_lock);
/* for per-CPU blocks */ staticvoid purge_fragmented_blocks_allcpus(void);
for (i = 0; i < MAX_VA_SIZE_PAGES; i++) {
LIST_HEAD(tmp_list);
if (list_empty(&vn->pool[i].head)) continue;
/* Detach the pool, so no-one can access it. */
spin_lock(&vn->pool_lock);
list_replace_init(&vn->pool[i].head, &tmp_list);
spin_unlock(&vn->pool_lock);
/* * Attach the pool back if it has been partly decayed. * Please note, it is supposed that nobody(other contexts) * can populate the pool therefore a simple list replace * operation takes place here.
*/ if (!list_empty(&tmp_list)) {
spin_lock(&vn->pool_lock);
list_replace_init(&tmp_list, &vn->pool[i].head);
WRITE_ONCE(vn->pool[i].len, pool_len);
spin_unlock(&vn->pool_lock);
}
}
end = max(end, list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end);
cpumask_set_cpu(node_to_id(vn), &purge_nodes);
}
nr_purge_nodes = cpumask_weight(&purge_nodes); if (nr_purge_nodes > 0) {
flush_tlb_kernel_range(start, end);
/* One extra worker is per a lazy_max_pages() full set minus one. */
nr_purge_helpers = atomic_long_read(&vmap_lazy_nr) / lazy_max_pages();
nr_purge_helpers = clamp(nr_purge_helpers, 1U, nr_purge_nodes) - 1;
/* * Free a vmap area, caller ensuring that the area has been unmapped, * unlinked and flush_cache_vunmap had been called for the correct * range previously.
*/ staticvoid free_vmap_area_noflush(struct vmap_area *va)
{ unsignedlong nr_lazy_max = lazy_max_pages(); unsignedlong va_start = va->va_start; unsignedint vn_id = decode_vn_id(va->flags); struct vmap_node *vn; unsignedlong nr_lazy;
/* * If it was request by a certain node we would like to * return it to that node, i.e. its pool for later reuse.
*/
vn = is_vn_id_valid(vn_id) ?
id_to_node(vn_id):addr_to_node(va->va_start);
/* After this point, we may free va at any time */ if (unlikely(nr_lazy > nr_lazy_max))
schedule_work(&drain_vmap_work);
}
/* * Free and unmap a vmap area
*/ staticvoid free_unmap_vmap_area(struct vmap_area *va)
{
flush_cache_vunmap(va->va_start, va->va_end);
vunmap_range_noflush(va->va_start, va->va_end); if (debug_pagealloc_enabled_static())
flush_tlb_kernel_range(va->va_start, va->va_end);
free_vmap_area_noflush(va);
}
struct vmap_area *find_vmap_area(unsignedlong addr)
{ struct vmap_node *vn; struct vmap_area *va; int i, j;
if (unlikely(!vmap_initialized)) return NULL;
/* * An addr_to_node_id(addr) converts an address to a node index * where a VA is located. If VA spans several zones and passed * addr is not the same as va->va_start, what is not common, we * may need to scan extra nodes. See an example: * * <----va----> * -|-----|-----|-----|-----|- * 1 2 0 1 * * VA resides in node 1 whereas it spans 1, 2 an 0. If passed * addr is within 2 or 0 nodes we should do extra work.
*/
i = j = addr_to_node_id(addr); do {
vn = &vmap_nodes[i];
spin_lock(&vn->busy.lock);
va = __find_vmap_area(addr, &vn->busy.root);
spin_unlock(&vn->busy.lock);
if (va) return va;
} while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j);
return NULL;
}
staticstruct vmap_area *find_unlink_vmap_area(unsignedlong addr)
{ struct vmap_node *vn; struct vmap_area *va; int i, j;
/* * Check the comment in the find_vmap_area() about the loop.
*/
i = j = addr_to_node_id(addr); do {
vn = &vmap_nodes[i];
spin_lock(&vn->busy.lock);
va = __find_vmap_area(addr, &vn->busy.root); if (va)
unlink_va(va, &vn->busy.root);
spin_unlock(&vn->busy.lock);
if (va) return va;
} while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j);
return NULL;
}
/*** Per cpu kva allocator ***/
/* * vmap space is limited especially on 32 bit architectures. Ensure there is * room for at least 16 percpu vmap blocks per CPU.
*/ /* * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able * to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess * instead (we just need a rough idea)
*/ #if BITS_PER_LONG == 32 #define VMALLOC_SPACE (128UL*1024*1024) #else #define VMALLOC_SPACE (128UL*1024*1024*1024) #endif
/* * Purge threshold to prevent overeager purging of fragmented blocks for * regular operations: Purge if vb->free is less than 1/4 of the capacity.
*/ #define VMAP_PURGE_THRESHOLD (VMAP_BBMAP_BITS / 4)
#define VMAP_RAM 0x1 /* indicates vm_map_ram area*/ #define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/ #define VMAP_FLAGS_MASK 0x3
/* * An xarray requires an extra memory dynamically to * be allocated. If it is an issue, we can use rb-tree * instead.
*/ struct xarray vmap_blocks;
};
/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);
/* * In order to fast access to any "vmap_block" associated with a * specific address, we use a hash. * * A per-cpu vmap_block_queue is used in both ways, to serialize * an access to free block chains among CPUs(alloc path) and it * also acts as a vmap_block hash(alloc/free paths). It means we * overload it, since we already have the per-cpu array which is * used as a hash table. When used as a hash a 'cpu' passed to * per_cpu() is not actually a CPU but rather a hash index. * * A hash function is addr_to_vb_xa() which hashes any address * to a specific index(in a hash) it belongs to. This then uses a * per_cpu() macro to access an array with generated index. * * An example: * * CPU_1 CPU_2 CPU_0 * | | | * V V V * 0 10 20 30 40 50 60 * |------|------|------|------|------|------|...<vmap address space> * CPU0 CPU1 CPU2 CPU0 CPU1 CPU2 * * - CPU_1 invokes vm_unmap_ram(6), 6 belongs to CPU0 zone, thus * it access: CPU0/INDEX0 -> vmap_blocks -> xa_lock; * * - CPU_2 invokes vm_unmap_ram(11), 11 belongs to CPU1 zone, thus * it access: CPU1/INDEX1 -> vmap_blocks -> xa_lock; * * - CPU_0 invokes vm_unmap_ram(20), 20 belongs to CPU2 zone, thus * it access: CPU2/INDEX2 -> vmap_blocks -> xa_lock. * * This technique almost always avoids lock contention on insert/remove, * however xarray spinlocks protect against any contention that remains.
*/ staticstruct xarray *
addr_to_vb_xa(unsignedlong addr)
{ int index = (addr / VMAP_BLOCK_SIZE) % nr_cpu_ids;
/* * Please note, nr_cpu_ids points on a highest set * possible bit, i.e. we never invoke cpumask_next() * if an index points on it which is nr_cpu_ids - 1.
*/ if (!cpu_possible(index))
index = cpumask_next(index, cpu_possible_mask);
/* * We should probably have a fallback mechanism to allocate virtual memory * out of partially filled vmap blocks. However vmap block sizing should be * fairly reasonable according to the vmalloc size, so it shouldn't be a * big problem.
*/
/** * new_vmap_block - allocates new vmap_block and occupies 2^order pages in this * block. Of course pages number can't exceed VMAP_BBMAP_BITS * @order: how many 2^order pages should be occupied in newly allocated block * @gfp_mask: flags for the page level allocator * * Return: virtual address in a newly allocated block or ERR_PTR(-errno)
*/ staticvoid *new_vmap_block(unsignedint order, gfp_t gfp_mask)
{ struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; struct xarray *xa; unsignedlong vb_idx; int node, err; void *vaddr;
va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE,
VMALLOC_START, VMALLOC_END,
node, gfp_mask,
VMAP_RAM|VMAP_BLOCK, NULL); if (IS_ERR(va)) {
kfree(vb); return ERR_CAST(va);
}
vaddr = vmap_block_vaddr(va->va_start, 0);
spin_lock_init(&vb->lock);
vb->va = va; /* At least something should be left free */
BUG_ON(VMAP_BBMAP_BITS <= (1UL << order));
bitmap_zero(vb->used_map, VMAP_BBMAP_BITS);
vb->free = VMAP_BBMAP_BITS - (1UL << order);
vb->dirty = 0;
vb->dirty_min = VMAP_BBMAP_BITS;
vb->dirty_max = 0;
bitmap_set(vb->used_map, 0, (1UL << order));
INIT_LIST_HEAD(&vb->free_list);
vb->cpu = raw_smp_processor_id();
xa = addr_to_vb_xa(va->va_start);
vb_idx = addr_to_vb_idx(va->va_start);
err = xa_insert(xa, vb_idx, vb, gfp_mask); if (err) {
kfree(vb);
free_vmap_area(va); return ERR_PTR(err);
} /* * list_add_tail_rcu could happened in another core * rather than vb->cpu due to task migration, which * is safe as list_add_tail_rcu will ensure the list's * integrity together with list_for_each_rcu from read * side.
*/
vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu);
spin_lock(&vbq->lock);
list_add_tail_rcu(&vb->free_list, &vbq->free);
spin_unlock(&vbq->lock);
/* * Try to purge a fragmented block first. If it's * not purgeable, check whether there is dirty * space to be flushed.
*/ if (!purge_fragmented_block(vb, &purge_list, false) &&
vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) { unsignedlong va_start = vb->va->va_start; unsignedlong s, e;
s = va_start + (vb->dirty_min << PAGE_SHIFT);
e = va_start + (vb->dirty_max << PAGE_SHIFT);
start = min(s, start);
end = max(e, end);
/* Prevent that this is flushed again */
vb->dirty_min = VMAP_BBMAP_BITS;
vb->dirty_max = 0;
if (!__purge_vmap_area_lazy(start, end, false) && flush)
flush_tlb_kernel_range(start, end);
mutex_unlock(&vmap_purge_lock);
}
/** * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer * * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily * to amortize TLB flushing overheads. What this means is that any page you * have now, may, in a former life, have been mapped into kernel virtual * address by the vmap layer and so there might be some CPUs with TLB entries * still referencing that page (additional to the regular 1:1 kernel mapping). * * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can * be sure that none of the pages we have control over will have any aliases * from the vmap layer.
*/ void vm_unmap_aliases(void)
{
_vm_unmap_aliases(ULONG_MAX, 0, 0);
}
EXPORT_SYMBOL_GPL(vm_unmap_aliases);
/** * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram * @mem: the pointer returned by vm_map_ram * @count: the count passed to that vm_map_ram call (cannot unmap partial)
*/ void vm_unmap_ram(constvoid *mem, unsignedint count)
{ unsignedlong size = (unsignedlong)count << PAGE_SHIFT; unsignedlong addr = (unsignedlong)kasan_reset_tag(mem); struct vmap_area *va;
/** * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space) * @pages: an array of pointers to the pages to be mapped * @count: number of pages * @node: prefer to allocate data structures on this node * * If you use this function for less than VMAP_MAX_ALLOC pages, it could be * faster than vmap so it's good. But if you mix long-life and short-life * objects with vm_map_ram(), it could consume lots of address space through * fragmentation (especially on a 32bit machine). You could see failures in * the end. Please use this function for short-lived objects. * * Returns: a pointer to the address that has been mapped, or %NULL on failure
*/ void *vm_map_ram(struct page **pages, unsignedint count, int node)
{ unsignedlong size = (unsignedlong)count << PAGE_SHIFT; unsignedlong addr; void *mem;
if (likely(count <= VMAP_MAX_ALLOC)) {
mem = vb_alloc(size, GFP_KERNEL); if (IS_ERR(mem)) return NULL;
addr = (unsignedlong)mem;
} else { struct vmap_area *va;
va = alloc_vmap_area(size, PAGE_SIZE,
VMALLOC_START, VMALLOC_END,
node, GFP_KERNEL, VMAP_RAM,
NULL); if (IS_ERR(va)) return NULL;
/* * Mark the pages as accessible, now that they are mapped. * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc().
*/
mem = kasan_unpoison_vmalloc(mem, size, KASAN_VMALLOC_PROT_NORMAL);
/** * vm_area_add_early - add vmap area early during boot * @vm: vm_struct to add * * This function is used to add fixed kernel vm area to vmlist before * vmalloc_init() is called. @vm->addr, @vm->size, and @vm->flags * should contain proper values and the other fields should be zero. * * DO NOT USE THIS FUNCTION UNLESS YOU KNOW WHAT YOU'RE DOING.
*/ void __init vm_area_add_early(struct vm_struct *vm)
{ struct vm_struct *tmp, **p;
/** * 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)
{ unsignedlong addr = ALIGN(VMALLOC_START, align); struct vm_struct *cur, **p;
BUG_ON(vmap_initialized);
for (p = &vmlist; (cur = *p) != NULL; p = &cur->next) { if ((unsignedlong)cur->addr - addr >= vm->size) break;
addr = ALIGN((unsignedlong)cur->addr + cur->size, align);
}
staticvoid clear_vm_uninitialized_flag(struct vm_struct *vm)
{ /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. * Pair with smp_rmb() in vread_iter() and vmalloc_info_show().
*/
smp_wmb();
vm->flags &= ~VM_UNINITIALIZED;
}
va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) {
kfree(area); return NULL;
}
/* * Mark pages for non-VM_ALLOC mappings as accessible. Do it now as a * best-effort approach, as they can be mapped outside of vmalloc code. * For VM_ALLOC mappings, the pages are marked as accessible after * getting mapped in __vmalloc_node_range(). * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc().
*/ if (!(flags & VM_ALLOC))
area->addr = kasan_unpoison_vmalloc(area->addr, requested_size,
KASAN_VMALLOC_PROT_NORMAL);
/** * get_vm_area - reserve a contiguous kernel virtual area * @size: size of the area * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC * * Search an area of @size in the kernel virtual mapping area, * and reserved it for out purposes. Returns the area descriptor * on success or %NULL on failure. * * Return: the area descriptor on success or %NULL on failure.
*/ struct vm_struct *get_vm_area(unsignedlong size, unsignedlong flags)
{ return __get_vm_area_node(size, 1, PAGE_SHIFT, flags,
VMALLOC_START, VMALLOC_END,
NUMA_NO_NODE, GFP_KERNEL,
__builtin_return_address(0));
}
/** * find_vm_area - find a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and return it. * It is up to the caller to do all required locking to keep the returned * pointer valid. * * Return: the area descriptor on success or %NULL on failure.
*/ struct vm_struct *find_vm_area(constvoid *addr)
{ struct vmap_area *va;
va = find_vmap_area((unsignedlong)addr); if (!va) return NULL;
return va->vm;
}
/** * remove_vm_area - find and remove a continuous kernel virtual area * @addr: base address * * Search for the kernel VM area starting at @addr, and remove it. * This function returns the found VM area, but using it is NOT safe * on SMP machines, except for its size or flags. * * Return: the area descriptor on success or %NULL on failure.
*/ struct vm_struct *remove_vm_area(constvoid *addr)
{ struct vmap_area *va; struct vm_struct *vm;
might_sleep();
if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n",
addr)) return NULL;
va = find_unlink_vmap_area((unsignedlong)addr); if (!va || !va->vm) return NULL;
vm = va->vm;
staticinlinevoid set_area_direct_map(conststruct vm_struct *area, int (*set_direct_map)(struct page *page))
{ int i;
/* HUGE_VMALLOC passes small pages to set_direct_map */ for (i = 0; i < area->nr_pages; i++) if (page_address(area->pages[i]))
set_direct_map(area->pages[i]);
}
/* * Flush the vm mapping and reset the direct map.
*/ staticvoid vm_reset_perms(struct vm_struct *area)
{ unsignedlong start = ULONG_MAX, end = 0; unsignedint page_order = vm_area_page_order(area); int flush_dmap = 0; int i;
/* * Find the start and end range of the direct mappings to make sure that * the vm_unmap_aliases() flush includes the direct map.
*/ for (i = 0; i < area->nr_pages; i += 1U << page_order) { unsignedlong addr = (unsignedlong)page_address(area->pages[i]);
/* * Set direct map to something invalid so that it won't be cached if * there are any accesses after the TLB flush, then flush the TLB and * reset the direct map permissions to the default.
*/
set_area_direct_map(area, set_direct_map_invalid_noflush);
_vm_unmap_aliases(start, end, flush_dmap);
set_area_direct_map(area, set_direct_map_default_noflush);
}
/** * vfree_atomic - release memory allocated by vmalloc() * @addr: memory base address * * This one is just like vfree() but can be called in any atomic context * except NMIs.
*/ void vfree_atomic(constvoid *addr)
{ struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred);
BUG_ON(in_nmi());
kmemleak_free(addr);
/* * Use raw_cpu_ptr() because this can be called from preemptible * context. Preemption is absolutely fine here, because the llist_add() * implementation is lockless, so it works even if we are adding to * another cpu's list. schedule_work() should be fine with this too.
*/ if (addr && llist_add((struct llist_node *)addr, &p->list))
schedule_work(&p->wq);
}
/** * vfree - Release memory allocated by vmalloc() * @addr: Memory base address * * Free the virtually continuous memory area starting at @addr, as obtained * from one of the vmalloc() family of APIs. This will usually also free the * physical memory underlying the virtual allocation, but that memory is * reference counted, so it will not be freed until the last user goes away. * * If @addr is NULL, no operation is performed. * * Context: * May sleep if called *not* from interrupt context. * Must not be called in NMI context (strictly speaking, it could be * if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling * conventions for vfree() arch-dependent would be a really bad idea).
*/ void vfree(constvoid *addr)
{ struct vm_struct *vm; int i;
if (unlikely(in_interrupt())) {
vfree_atomic(addr); return;
}
vm = remove_vm_area(addr); if (unlikely(!vm)) {
WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
addr); return;
}
if (unlikely(vm->flags & VM_FLUSH_RESET_PERMS))
vm_reset_perms(vm); /* All pages of vm should be charged to same memcg, so use first one. */ if (vm->nr_pages && !(vm->flags & VM_MAP_PUT_PAGES))
mod_memcg_page_state(vm->pages[0], MEMCG_VMALLOC, -vm->nr_pages); for (i = 0; i < vm->nr_pages; i++) { struct page *page = vm->pages[i];
BUG_ON(!page); /* * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations
*/
__free_page(page);
cond_resched();
} if (!(vm->flags & VM_MAP_PUT_PAGES))
atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages);
kvfree(vm->pages);
kfree(vm);
}
EXPORT_SYMBOL(vfree);
/** * vunmap - release virtual mapping obtained by vmap() * @addr: memory base address * * Free the virtually contiguous memory area starting at @addr, * which was created from the page array passed to vmap(). * * Must not be called in interrupt context.
*/ void vunmap(constvoid *addr)
{ struct vm_struct *vm;
BUG_ON(in_interrupt());
might_sleep();
if (!addr) return;
vm = remove_vm_area(addr); if (unlikely(!vm)) {
WARN(1, KERN_ERR "Trying to vunmap() nonexistent vm area (%p)\n",
addr); return;
}
kfree(vm);
}
EXPORT_SYMBOL(vunmap);
/** * vmap - map an array of pages into virtually contiguous space * @pages: array of page pointers * @count: number of pages to map * @flags: vm_area->flags * @prot: page protection for the mapping * * Maps @count pages from @pages into contiguous kernel virtual space. * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself * (which must be kmalloc or vmalloc memory) and one reference per pages in it * are transferred from the caller to vmap(), and will be freed / dropped when * vfree() is called on the return value. * * Return: the address of the area or %NULL on failure
*/ void *vmap(struct page **pages, unsignedint count, unsignedlong flags, pgprot_t prot)
{ struct vm_struct *area; unsignedlong addr; unsignedlong size; /* In bytes */
might_sleep();
if (WARN_ON_ONCE(flags & VM_FLUSH_RESET_PERMS)) return NULL;
/* * Your top guard is someone else's bottom guard. Not having a top * guard compromises someone else's mappings too.
*/ if (WARN_ON_ONCE(flags & VM_NO_GUARD))
flags &= ~VM_NO_GUARD;
if (count > totalram_pages()) return NULL;
size = (unsignedlong)count << PAGE_SHIFT;
area = get_vm_area_caller(size, flags, __builtin_return_address(0)); if (!area) return NULL;
/** * vmap_pfn - map an array of PFNs into virtually contiguous space * @pfns: array of PFNs * @count: number of pages to map * @prot: page protection for the mapping * * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns * the start address of the mapping.
*/ void *vmap_pfn(unsignedlong *pfns, unsignedint count, pgprot_t prot)
{ struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) }; struct vm_struct *area;
area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP,
__builtin_return_address(0)); if (!area) return NULL; if (apply_to_page_range(&init_mm, (unsignedlong)area->addr,
count * PAGE_SIZE, vmap_pfn_apply, &data)) {
free_vm_area(area); return NULL;
}
/* * For order-0 pages we make use of bulk allocator, if * the page array is partly or not at all populated due * to fails, fallback to a single page allocator that is * more permissive.
*/ if (!order) { while (nr_allocated < nr_pages) { unsignedint 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);
/* memory allocation should consider mempolicy, we can't * wrongly use nearest node when nid == NUMA_NO_NODE, * otherwise memory may be allocated in only one node, * but mempolicy wants to alloc memory by interleaving.
*/ if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
nr = alloc_pages_bulk_mempolicy_noprof(gfp,
nr_pages_request,
pages + nr_allocated); else
nr = alloc_pages_bulk_node_noprof(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;
}
}
/* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { if (!(gfp & __GFP_NOFAIL) && fatal_signal_pending(current)) break;
/* * High-order allocations must be able to be treated as * independent small pages by callers (as they can with * small-page vmallocs). Some drivers do their own refcounting * on vmalloc_to_page() pages, some use page->mapping, * page->lru, etc.
*/ if (order)
split_page(page, order);
/* * Careful, we allocate and map page-order pages, but * tracking is done per PAGE_SIZE page so as to keep the * vm_struct APIs independent of the physical/mapped size.
*/ for (i = 0; i < (1U << order); i++)
pages[nr_allocated + i] = page + i;
/* * High-order nofail allocations are really expensive and * potentially dangerous (pre-mature OOM, disruptive reclaim * and compaction etc. * * Please note, the __vmalloc_node_range_noprof() falls-back * to order-0 pages if high-order attempt is unsuccessful.
*/
area->nr_pages = vm_area_alloc_pages((page_order ?
gfp_mask & ~__GFP_NOFAIL : gfp_mask) | __GFP_NOWARN,
node, page_order, nr_small_pages, area->pages);
atomic_long_add(area->nr_pages, &nr_vmalloc_pages); /* All pages of vm should be charged to same memcg, so use first one. */ if (gfp_mask & __GFP_ACCOUNT && area->nr_pages)
mod_memcg_page_state(area->pages[0], MEMCG_VMALLOC,
area->nr_pages);
/* * If not enough pages were obtained to accomplish an * allocation request, free them via vfree() if any.
*/ if (area->nr_pages != nr_small_pages) { /* * vm_area_alloc_pages() can fail due to insufficient memory but * also:- * * - a pending fatal signal * - insufficient huge page-order pages * * Since we always retry allocations at order-0 in the huge page * case a warning for either is spurious.
*/ if (!fatal_signal_pending(current) && page_order == 0)
warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, failed to allocate pages",
area->nr_pages * PAGE_SIZE); goto fail;
}
/* * page tables allocations ignore external gfp mask, enforce it * by the scope API
*/ if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
flags = memalloc_nofs_save(); elseif ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
flags = memalloc_noio_save();
do {
ret = vmap_pages_range(addr, addr + size, prot, area->pages,
page_shift); if (nofail && (ret < 0))
schedule_timeout_uninterruptible(1);
} while (nofail && (ret < 0));
/** * __vmalloc_node_range - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @start: vm area range start * @end: vm area range end * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages * @vm_flags: additional vm area flags (e.g. %VM_NO_GUARD) * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level * allocator with @gfp_mask flags. Please note that the full set of gfp * flags are not supported. GFP_KERNEL, GFP_NOFS and GFP_NOIO are all * supported. * Zone modifiers are not supported. From the reclaim modifiers * __GFP_DIRECT_RECLAIM is required (aka GFP_NOWAIT is not supported) * and only __GFP_NOFAIL is supported (i.e. __GFP_NORETRY and * __GFP_RETRY_MAYFAIL are not supported). * * __GFP_NOWARN can be used to suppress failures messages. * * Map them into contiguous kernel virtual space, using a pagetable * protection of @prot. * * Return: the address of the area or %NULL on failure
*/ void *__vmalloc_node_range_noprof(unsignedlong size, unsignedlong align, unsignedlong start, unsignedlong end, gfp_t gfp_mask,
pgprot_t prot, unsignedlong vm_flags, int node, constvoid *caller)
{ struct vm_struct *area; void *ret;
kasan_vmalloc_flags_t kasan_flags = KASAN_VMALLOC_NONE; unsignedlong original_align = align; unsignedint shift = PAGE_SHIFT;
if (WARN_ON_ONCE(!size)) return NULL;
if ((size >> PAGE_SHIFT) > totalram_pages()) {
warn_alloc(gfp_mask, NULL, "vmalloc error: size %lu, exceeds total pages",
size); return NULL;
}
if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { /* * Try huge pages. Only try for PAGE_KERNEL allocations, * others like modules don't yet expect huge pages in * their allocations due to apply_to_page_range not * supporting them.
*/
/* * Prepare arguments for __vmalloc_area_node() and * kasan_unpoison_vmalloc().
*/ if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) { if (kasan_hw_tags_enabled()) { /* * Modify protection bits to allow tagging. * This must be done before mapping.
*/
prot = arch_vmap_pgprot_tagged(prot);
/* * Skip page_alloc poisoning and zeroing for physical * pages backing VM_ALLOC mapping. Memory is instead * poisoned and zeroed by kasan_unpoison_vmalloc().
*/
gfp_mask |= __GFP_SKIP_KASAN | __GFP_SKIP_ZERO;
}
/* Take note that the mapping is PAGE_KERNEL. */
kasan_flags |= KASAN_VMALLOC_PROT_NORMAL;
}
/* Allocate physical pages and map them into vmalloc space. */
ret = __vmalloc_area_node(area, gfp_mask, prot, shift, node); if (!ret) goto fail;
/* * Mark the pages as accessible, now that they are mapped. * The condition for setting KASAN_VMALLOC_INIT should complement the * one in post_alloc_hook() with regards to the __GFP_SKIP_ZERO check * to make sure that memory is initialized under the same conditions. * Tag-based KASAN modes only assign tags to normal non-executable * allocations, see __kasan_unpoison_vmalloc().
*/
kasan_flags |= KASAN_VMALLOC_VM_ALLOC; if (!want_init_on_free() && want_init_on_alloc(gfp_mask) &&
(gfp_mask & __GFP_SKIP_ZERO))
kasan_flags |= KASAN_VMALLOC_INIT; /* KASAN_VMALLOC_PROT_NORMAL already set if required. */
area->addr = kasan_unpoison_vmalloc(area->addr, size, kasan_flags);
/* * In this function, newly allocated vm_struct has VM_UNINITIALIZED * flag. It means that vm_struct is not fully initialized. * Now, it is fully initialized, so remove this flag here.
*/
clear_vm_uninitialized_flag(area);
if (!(vm_flags & VM_DEFER_KMEMLEAK))
kmemleak_vmalloc(area, PAGE_ALIGN(size), gfp_mask);
/** * __vmalloc_node - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment * @gfp_mask: flags for the page level allocator * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * * Allocate enough pages to cover @size from the page level allocator with * @gfp_mask flags. Map them into contiguous kernel virtual space. * * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL * and __GFP_NOFAIL are not supported * * Any use of gfp flags outside of GFP_KERNEL should be consulted * with mm people. * * Return: pointer to the allocated memory or %NULL on error
*/ void *__vmalloc_node_noprof(unsignedlong size, unsignedlong align,
gfp_t gfp_mask, int node, constvoid *caller)
{ return __vmalloc_node_range_noprof(size, align, VMALLOC_START, VMALLOC_END,
gfp_mask, PAGE_KERNEL, 0, node, caller);
} /* * This is only for performance analysis of vmalloc and stress purpose. * It is required by vmalloc test module, therefore do not use it other * than that.
*/ #ifdef CONFIG_TEST_VMALLOC_MODULE
EXPORT_SYMBOL_GPL(__vmalloc_node_noprof); #endif
/** * vmalloc - allocate virtually contiguous memory * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error
*/ void *vmalloc_noprof(unsignedlong size)
{ return __vmalloc_node_noprof(size, 1, GFP_KERNEL, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_noprof);
/** * vmalloc_huge_node - allocate virtually contiguous memory, allow huge pages * @size: allocation size * @gfp_mask: flags for the page level allocator * @node: node to use for allocation or NUMA_NO_NODE * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * If @size is greater than or equal to PMD_SIZE, allow using * huge pages for the memory * * Return: pointer to the allocated memory or %NULL on error
*/ void *vmalloc_huge_node_noprof(unsignedlong size, gfp_t gfp_mask, int node)
{ return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END,
gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP,
node, __builtin_return_address(0));
}
EXPORT_SYMBOL_GPL(vmalloc_huge_node_noprof);
/** * vzalloc - allocate virtually contiguous memory with zero fill * @size: allocation size * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error
*/ void *vzalloc_noprof(unsignedlong size)
{ return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vzalloc_noprof);
/** * vmalloc_user - allocate zeroed virtually contiguous memory for userspace * @size: allocation size * * The resulting memory area is zeroed so it can be mapped to userspace * without leaking data. * * Return: pointer to the allocated memory or %NULL on error
*/ void *vmalloc_user_noprof(unsignedlong size)
{ return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END,
GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL,
VM_USERMAP, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_user_noprof);
/** * vmalloc_node - allocate memory on a specific node * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * * For tight control over page level allocator and protection flags * use __vmalloc() instead. * * Return: pointer to the allocated memory or %NULL on error
*/ void *vmalloc_node_noprof(unsignedlong size, int node)
{ return __vmalloc_node_noprof(size, 1, GFP_KERNEL, node,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_node_noprof);
/** * vzalloc_node - allocate memory on a specific node with zero fill * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * * Return: pointer to the allocated memory or %NULL on error
*/ void *vzalloc_node_noprof(unsignedlong size, int node)
{ return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, node,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vzalloc_node_noprof);
/** * vrealloc - reallocate virtually contiguous memory; contents remain unchanged * @p: object to reallocate memory for * @size: the size to reallocate * @flags: the flags for the page level allocator * * If @p is %NULL, vrealloc() behaves exactly like vmalloc(). If @size is 0 and * @p is not a %NULL pointer, the object pointed to is freed. * * If __GFP_ZERO logic is requested, callers must ensure that, starting with the * initial memory allocation, every subsequent call to this API for the same * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that * __GFP_ZERO is not fully honored by this API. * * In any case, the contents of the object pointed to are preserved up to the * lesser of the new and old sizes. * * This function must not be called concurrently with itself or vfree() for the * same memory allocation. * * Return: pointer to the allocated memory; %NULL if @size is zero or in case of * failure
*/ void *vrealloc_noprof(constvoid *p, size_t size, gfp_t flags)
{ struct vm_struct *vm = NULL;
size_t alloced_size = 0;
size_t old_size = 0; void *n;
if (!size) {
vfree(p); return NULL;
}
if (p) {
vm = find_vm_area(p); if (unlikely(!vm)) {
WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p); return NULL;
}
alloced_size = get_vm_area_size(vm);
old_size = vm->requested_size; if (WARN(alloced_size < old_size, "vrealloc() has mismatched area vs requested sizes (%p)\n", p)) return NULL;
}
/* * TODO: Shrink the vm_area, i.e. unmap and free unused pages. What * would be a good heuristic for when to shrink the vm_area?
*/ if (size <= old_size) { /* Zero out "freed" memory, potentially for future realloc. */ if (want_init_on_free() || want_init_on_alloc(flags))
memset((void *)p + size, 0, old_size - size);
vm->requested_size = size;
kasan_poison_vmalloc(p + size, old_size - size); return (void *)p;
}
/* * We already have the bytes available in the allocation; use them.
*/ if (size <= alloced_size) {
kasan_unpoison_vmalloc(p + old_size, size - old_size,
KASAN_VMALLOC_PROT_NORMAL); /* * No need to zero memory here, as unused memory will have * already been zeroed at initial allocation time or during * realloc shrink time.
*/
vm->requested_size = size; return (void *)p;
}
/* TODO: Grow the vm_area, i.e. allocate and map additional pages. */
n = __vmalloc_noprof(size, flags); if (!n) return NULL;
if (p) {
memcpy(n, p, old_size);
vfree(p);
}
return n;
}
#ifdefined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) #define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #elifdefined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA) #define GFP_VMALLOC32 (GFP_DMA | GFP_KERNEL) #else /* * 64b systems should always have either DMA or DMA32 zones. For others * GFP_DMA32 should do the right thing and use the normal zone.
*/ #define GFP_VMALLOC32 (GFP_DMA32 | 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. * * Return: pointer to the allocated memory or %NULL on error
*/ void *vmalloc_32_noprof(unsignedlong size)
{ return __vmalloc_node_noprof(size, 1, GFP_VMALLOC32, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32_noprof);
/** * 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. * * Return: pointer to the allocated memory or %NULL on error
*/ void *vmalloc_32_user_noprof(unsignedlong size)
{ return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END,
GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
VM_USERMAP, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32_user_noprof);
/* * Atomically zero bytes in the iterator. * * Returns the number of zeroed bytes.
*/ static size_t zero_iter(struct iov_iter *iter, size_t count)
{
size_t remains = count;
/* * small helper routine, copy contents to iter from addr. * If the page is not present, fill zero. * * Returns the number of copied bytes.
*/ static size_t aligned_vread_iter(struct iov_iter *iter, constchar *addr, size_t count)
{
size_t remains = count; struct page *page;
offset = offset_in_page(addr);
length = PAGE_SIZE - offset; if (length > remains)
length = remains;
page = 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() calls for this _debug_ interface, rarely * used. Instead of that, we'll use an local mapping via * copy_page_to_iter_nofault() and accept a small overhead in * this access function.
*/ if (page)
copied = copy_page_to_iter_nofault(page, offset,
length, iter); else
copied = zero_iter(iter, length);
addr += copied;
remains -= copied;
if (copied != length) break;
}
return count - remains;
}
/* * Read from a vm_map_ram region of memory. * * Returns the number of copied bytes.
*/ static size_t vmap_ram_vread_iter(struct iov_iter *iter, constchar *addr,
size_t count, unsignedlong flags)
{ char *start; struct vmap_block *vb; struct xarray *xa; unsignedlong offset; unsignedint rs, re;
size_t remains, n;
/* * If it's area created by vm_map_ram() interface directly, but * not further subdividing and delegating management to vmap_block, * handle it here.
*/ if (!(flags & VMAP_BLOCK)) return aligned_vread_iter(iter, addr, count);
remains = count;
/* * Area is split into regions and tracked with vmap_block, read out * each region and zero fill the hole between regions.
*/
xa = addr_to_vb_xa((unsignedlong) addr);
vb = xa_load(xa, addr_to_vb_idx((unsignedlong)addr)); if (!vb) goto finished_zero;
spin_lock(&vb->lock); if (bitmap_empty(vb->used_map, VMAP_BBMAP_BITS)) {
spin_unlock(&vb->lock); goto finished_zero;
}
for_each_set_bitrange(rs, re, vb->used_map, VMAP_BBMAP_BITS) {
size_t copied;
/*it could start reading from the middle of used region*/
offset = offset_in_page(addr);
n = ((re - rs + 1) << PAGE_SHIFT) - offset; if (n > remains)
n = remains;
finished_zero: /* zero-fill the left dirty or free regions */ return count - remains + zero_iter(iter, remains);
finished: /* We couldn't copy/zero everything */
spin_unlock(&vb->lock); return count - remains;
}
/** * vread_iter() - read vmalloc area in a safe way to an iterator. * @iter: the iterator to which data should be written. * @addr: vm address. * @count: number of bytes to be read. * * 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 information, as /proc/kcore. * * Return: number of bytes for which addr and buf should be increased * (same number as @count) or %0 if [addr...addr+count) doesn't * include any intersection with valid vmalloc area
*/ long vread_iter(struct iov_iter *iter, constchar *addr, size_t count)
{ struct vmap_node *vn; struct vmap_area *va; struct vm_struct *vm; char *vaddr;
size_t n, size, flags, remains; unsignedlong next;
vn = find_vmap_area_exceed_addr_lock((unsignedlong) addr, &va); if (!vn) goto finished_zero;
/* no intersects with alive vmap_area */ if ((unsignedlong)addr + remains <= va->va_start) goto finished_zero;
do {
size_t copied;
if (remains == 0) goto finished;
vm = va->vm;
flags = va->flags & VMAP_FLAGS_MASK; /* * VMAP_BLOCK indicates a sub-type of vm_map_ram area, need * be set together with VMAP_RAM.
*/
WARN_ON(flags == VMAP_BLOCK);
if (!vm && !flags) goto next_va;
if (vm && (vm->flags & VM_UNINITIALIZED)) goto next_va;
/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
smp_rmb();
n = vaddr + size - addr; if (n > remains)
n = remains;
if (flags & VMAP_RAM)
copied = vmap_ram_vread_iter(iter, addr, n, flags); elseif (!(vm && (vm->flags & (VM_IOREMAP | VM_SPARSE))))
copied = aligned_vread_iter(iter, addr, n); else/* IOREMAP | SPARSE area is treated as memory hole */
copied = zero_iter(iter, n);
addr += copied;
remains -= copied;
if (copied != n) goto finished;
next_va:
next = va->va_end;
spin_unlock(&vn->busy.lock);
} while ((vn = find_vmap_area_exceed_addr_lock(next, &va)));
finished_zero: if (vn)
spin_unlock(&vn->busy.lock);
/* zero-fill memory holes */ return count - remains + zero_iter(iter, remains);
finished: /* Nothing remains, or We couldn't copy/zero everything. */ if (vn)
spin_unlock(&vn->busy.lock);
return count - remains;
}
/** * 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 * @pgoff: offset from @kaddr to start at * @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, unsignedlong uaddr, void *kaddr, unsignedlong pgoff, unsignedlong size)
{ struct vm_struct *area; unsignedlong off; unsignedlong end_index;
if (check_shl_overflow(pgoff, PAGE_SHIFT, &off)) return -EINVAL;
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 | VM_DMA_COHERENT))) return -EINVAL;
/** * 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, unsignedlong pgoff)
{ return remap_vmalloc_range_partial(vma, vma->vm_start,
addr, pgoff,
vma->vm_end - vma->vm_start);
}
EXPORT_SYMBOL(remap_vmalloc_range);
/** * pvm_find_va_enclose_addr - find the vmap_area @addr belongs to * @addr: target address * * Returns: vmap_area if it is found. If there is no such area * the first highest(reverse order) vmap_area is returned * i.e. va->va_start < addr && va->va_end < addr or NULL * if there are no any areas before @addr.
*/ staticstruct vmap_area *
pvm_find_va_enclose_addr(unsignedlong addr)
{ struct vmap_area *va, *tmp; struct rb_node *n;
n = free_vmap_area_root.rb_node;
va = NULL;
while (n) {
tmp = rb_entry(n, struct vmap_area, rb_node); if (tmp->va_start <= addr) {
va = tmp; if (tmp->va_end >= addr) break;
n = n->rb_right;
} else {
n = n->rb_left;
}
}
return va;
}
/** * pvm_determine_end_from_reverse - find the highest aligned address * of free block below VMALLOC_END * @va: * in - the VA we start the search(reverse order); * out - the VA with the highest aligned end address. * @align: alignment for required highest address * * Returns: determined end address within vmap_area
*/ staticunsignedlong
pvm_determine_end_from_reverse(struct vmap_area **va, unsignedlong align)
{ unsignedlong vmalloc_end = VMALLOC_END & ~(align - 1); unsignedlong 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 free blocks from the end looking * for matching base. While scanning, if any of the areas do not fit the * base address is pulled down to fit the area. Scanning is repeated till * all the areas fit and then all necessary data structures are inserted * and the result is returned.
*/ struct vm_struct **pcpu_get_vm_areas(constunsignedlong *offsets, const size_t *sizes, int nr_vms,
size_t align)
{ constunsignedlong vmalloc_start = ALIGN(VMALLOC_START, align); constunsignedlong vmalloc_end = VMALLOC_END & ~(align - 1); struct vmap_area **vas, *va; struct vm_struct **vms; int area, area2, last_area, term_area; unsignedlong base, start, size, end, last_end, orig_start, orig_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;
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] = kmem_cache_zalloc(vmap_area_cachep, GFP_KERNEL);
vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL); if (!vas[area] || !vms[area]) goto err_free;
}
retry:
spin_lock(&free_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];
va = pvm_find_va_enclose_addr(vmalloc_end);
base = pvm_determine_end_from_reverse(&va, align) - end;
while (true) { /* * base might have underflowed, add last_end before * comparing.
*/ if (base + last_end < vmalloc_start + last_end) goto overflow;
/* * Fitting base has not been found.
*/ if (va == NULL) goto overflow;
/* * If required width exceeds current VA block, move * base downwards and then recheck.
*/ if (base + end > va->va_end) {
base = pvm_determine_end_from_reverse(&va, align) - end;
term_area = area; continue;
}
/* * If this VA does not fit, move base downwards and recheck.
*/ if (base + start < va->va_start) {
va = node_to_va(rb_prev(&va->rb_node));
base = pvm_determine_end_from_reverse(&va, 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];
va = pvm_find_va_enclose_addr(base + end);
}
/* we've found a fitting base, insert all va's */ for (area = 0; area < nr_vms; area++) { int ret;
start = base + offsets[area];
size = sizes[area];
va = pvm_find_va_enclose_addr(start); if (WARN_ON_ONCE(va == NULL)) /* It is a BUG(), but trigger recovery instead. */ goto recovery;
ret = va_clip(&free_vmap_area_root,
&free_vmap_area_list, va, start, size); if (WARN_ON_ONCE(unlikely(ret))) /* It is a BUG(), but trigger recovery instead. */ goto recovery;
/* populate the kasan shadow space */ for (area = 0; area < nr_vms; area++) { if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area], GFP_KERNEL)) goto err_free_shadow;
}
/* insert all vm's */ for (area = 0; area < nr_vms; area++) { struct vmap_node *vn = addr_to_node(vas[area]->va_start);
/* * Mark allocated areas as accessible. Do it now as a best-effort * approach, as they can be mapped outside of vmalloc code. * With hardware tag-based KASAN, marking is skipped for * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc().
*/ for (area = 0; area < nr_vms; area++)
vms[area]->addr = kasan_unpoison_vmalloc(vms[area]->addr,
vms[area]->size, KASAN_VMALLOC_PROT_NORMAL);
kfree(vas); return vms;
recovery: /* * Remove previously allocated areas. There is no * need in removing these areas from the busy tree, * because they are inserted only on the final step * and when pcpu_get_vm_areas() is success.
*/ while (area--) {
orig_start = vas[area]->va_start;
orig_end = vas[area]->va_end;
va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
&free_vmap_area_list); if (va)
kasan_release_vmalloc(orig_start, orig_end,
va->va_start, va->va_end,
KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH);
vas[area] = NULL;
}
overflow:
spin_unlock(&free_vmap_area_lock); if (!purged) {
reclaim_and_purge_vmap_areas();
purged = true;
/* Before "retry", check if we recover. */ for (area = 0; area < nr_vms; area++) { if (vas[area]) continue;
vas[area] = kmem_cache_zalloc(
vmap_area_cachep, GFP_KERNEL); if (!vas[area]) goto err_free;
}
goto retry;
}
err_free: for (area = 0; area < nr_vms; area++) { if (vas[area])
kmem_cache_free(vmap_area_cachep, vas[area]);
err_free_shadow:
spin_lock(&free_vmap_area_lock); /* * We release all the vmalloc shadows, even the ones for regions that * hadn't been successfully added. This relies on kasan_release_vmalloc * being able to tolerate this case.
*/ for (area = 0; area < nr_vms; area++) {
orig_start = vas[area]->va_start;
orig_end = vas[area]->va_end;
va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
&free_vmap_area_list); if (va)
kasan_release_vmalloc(orig_start, orig_end,
va->va_start, va->va_end,
KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH);
vas[area] = NULL;
kfree(vms[area]);
}
spin_unlock(&free_vmap_area_lock);
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 */
pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n",
nr_pages, addr, caller);
returntrue;
} #endif
#ifdef CONFIG_PROC_FS
/* * Print number of pages allocated on each memory node. * * This function can only be called if CONFIG_NUMA is enabled * and VM_UNINITIALIZED bit in v->flags is disabled.
*/ staticvoid show_numa_info(struct seq_file *m, struct vm_struct *v, unsignedint *counters)
{ unsignedint nr; unsignedint step = 1U << vm_area_page_order(v);
/* * B F B B B F * -|-----|.....|-----|-----|-----|.....|- * | The KVA space | * |<--------------------------------->|
*/ for (busy = vmlist; busy; busy = busy->next) { if ((unsignedlong) busy->addr - vmap_start > 0) {
free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); if (!WARN_ON_ONCE(!free)) {
free->va_start = vmap_start;
free->va_end = (unsignedlong) busy->addr;
staticvoid vmap_init_nodes(void)
{ struct vmap_node *vn; int i;
#if BITS_PER_LONG == 64 /* * A high threshold of max nodes is fixed and bound to 128, * thus a scale factor is 1 for systems where number of cores * are less or equal to specified threshold. * * As for NUMA-aware notes. For bigger systems, for example * NUMA with multi-sockets, where we can end-up with thousands * of cores in total, a "sub-numa-clustering" should be added. * * In this case a NUMA domain is considered as a single entity * with dedicated sub-nodes in it which describe one group or * set of cores. Therefore a per-domain purging is supposed to * be added as well as a per-domain balancing.
*/ int n = clamp_t(unsignedint, num_possible_cpus(), 1, 128);
if (n > 1) {
vn = kmalloc_array(n, sizeof(*vn), GFP_NOWAIT | __GFP_NOWARN); if (vn) { /* Node partition is 16 pages. */
vmap_zone_size = (1 << 4) * PAGE_SIZE;
nr_vmap_nodes = n;
vmap_nodes = vn;
} else {
pr_err("Failed to allocate an array. Disable a node layer\n");
}
} #endif
¤ Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.0.85Bemerkung:
(vorverarbeitet am 2026-04-25)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.