Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a728fc4..a3c70e2 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/mm/vmalloc.c
*
@@ -18,6 +19,7 @@
#include <linux/interrupt.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/set_memory.h>
#include <linux/debugobjects.h>
#include <linux/kallsyms.h>
#include <linux/list.h>
@@ -31,6 +33,7 @@
#include <linux/compiler.h>
#include <linux/llist.h>
#include <linux/bitops.h>
+#include <linux/rbtree_augmented.h>
#include <linux/uaccess.h>
#include <asm/tlbflush.h>
@@ -323,22 +326,89 @@
/*** Global kva allocator ***/
-#define VM_LAZY_FREE 0x02
-#define VM_VM_AREA 0x04
+#define DEBUG_AUGMENT_PROPAGATE_CHECK 0
+#define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0
+
static DEFINE_SPINLOCK(vmap_area_lock);
/* Export for kexec only */
LIST_HEAD(vmap_area_list);
static LLIST_HEAD(vmap_purge_list);
static struct rb_root vmap_area_root = RB_ROOT;
+static bool vmap_initialized __read_mostly;
-/* 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;
+/*
+ * 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.
+ */
+static struct kmem_cache *vmap_area_cachep;
-static unsigned long vmap_area_pcpu_hole;
+/*
+ * 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.
+ */
+static struct 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);
+
+static __always_inline unsigned long
+va_size(struct vmap_area *va)
+{
+ return (va->va_end - va->va_start);
+}
+
+static __always_inline unsigned long
+get_subtree_max_size(struct rb_node *node)
+{
+ struct vmap_area *va;
+
+ va = rb_entry_safe(node, struct vmap_area, rb_node);
+ return va ? va->subtree_max_size : 0;
+}
+
+/*
+ * Gets called when remove the node and rotate.
+ */
+static __always_inline unsigned long
+compute_subtree_max_size(struct vmap_area *va)
+{
+ return max3(va_size(va),
+ get_subtree_max_size(va->rb_node.rb_left),
+ get_subtree_max_size(va->rb_node.rb_right));
+}
+
+RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb,
+ struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size)
+
+static void purge_vmap_area_lazy(void);
+static BLOCKING_NOTIFIER_HEAD(vmap_notify_list);
+static unsigned long lazy_max_pages(void);
+
+static atomic_long_t nr_vmalloc_pages;
+
+unsigned long vmalloc_nr_pages(void)
+{
+ return atomic_long_read(&nr_vmalloc_pages);
+}
static struct vmap_area *__find_vmap_area(unsigned long addr)
{
@@ -359,41 +429,618 @@
return NULL;
}
-static void __insert_vmap_area(struct vmap_area *va)
+/*
+ * This function returns back addresses of parent node
+ * and its left or right link for further processing.
+ */
+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 rb_node **p = &vmap_area_root.rb_node;
- struct rb_node *parent = NULL;
- struct rb_node *tmp;
+ struct vmap_area *tmp_va;
+ struct rb_node **link;
- 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();
+ if (root) {
+ link = &root->rb_node;
+ if (unlikely(!*link)) {
+ *parent = NULL;
+ return link;
+ }
+ } else {
+ link = &from;
}
- rb_link_node(&va->rb_node, parent, p);
- rb_insert_color(&va->rb_node, &vmap_area_root);
+ /*
+ * 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);
- /* 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);
+ /*
+ * During the traversal we also do some sanity check.
+ * Trigger the BUG() if there are sides(left/right)
+ * or full overlaps.
+ */
+ if (va->va_start < tmp_va->va_end &&
+ va->va_end <= tmp_va->va_start)
+ link = &(*link)->rb_left;
+ else if (va->va_end > tmp_va->va_start &&
+ va->va_start >= tmp_va->va_end)
+ link = &(*link)->rb_right;
+ else
+ BUG();
+ } while (*link);
+
+ *parent = &tmp_va->rb_node;
+ return link;
}
-static void purge_vmap_area_lazy(void);
+static __always_inline struct list_head *
+get_va_next_sibling(struct rb_node *parent, struct rb_node **link)
+{
+ struct list_head *list;
-static BLOCKING_NOTIFIER_HEAD(vmap_notify_list);
+ 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)
+{
+ /*
+ * 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 (root == &free_vmap_area_root) {
+ /*
+ * 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 of 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);
+}
+
+static __always_inline void
+unlink_va(struct vmap_area *va, struct rb_root *root)
+{
+ if (WARN_ON(RB_EMPTY_NODE(&va->rb_node)))
+ return;
+
+ if (root == &free_vmap_area_root)
+ rb_erase_augmented(&va->rb_node,
+ root, &free_vmap_area_rb_augment_cb);
+ else
+ rb_erase(&va->rb_node, root);
+
+ list_del(&va->list);
+ RB_CLEAR_NODE(&va->rb_node);
+}
+
+#if DEBUG_AUGMENT_PROPAGATE_CHECK
+static void
+augment_tree_propagate_check(struct rb_node *n)
+{
+ struct vmap_area *va;
+ struct rb_node *node;
+ unsigned long size;
+ bool found = false;
+
+ if (n == NULL)
+ return;
+
+ va = rb_entry(n, struct vmap_area, rb_node);
+ size = va->subtree_max_size;
+ node = n;
+
+ while (node) {
+ va = rb_entry(node, struct vmap_area, rb_node);
+
+ if (get_subtree_max_size(node->rb_left) == size) {
+ node = node->rb_left;
+ } else {
+ if (va_size(va) == size) {
+ found = true;
+ break;
+ }
+
+ node = node->rb_right;
+ }
+ }
+
+ if (!found) {
+ va = rb_entry(n, struct vmap_area, rb_node);
+ pr_emerg("tree is corrupted: %lu, %lu\n",
+ va_size(va), va->subtree_max_size);
+ }
+
+ augment_tree_propagate_check(n->rb_left);
+ augment_tree_propagate_check(n->rb_right);
+}
+#endif
+
+/*
+ * 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)
+{
+ struct rb_node *node = &va->rb_node;
+ unsigned long new_va_sub_max_size;
+
+ while (node) {
+ va = rb_entry(node, struct vmap_area, rb_node);
+ new_va_sub_max_size = compute_subtree_max_size(va);
+
+ /*
+ * If the newly calculated maximum available size of the
+ * subtree is equal to the current one, then it means that
+ * the tree is propagated correctly. So we have to stop at
+ * this point to save cycles.
+ */
+ if (va->subtree_max_size == new_va_sub_max_size)
+ break;
+
+ va->subtree_max_size = new_va_sub_max_size;
+ node = rb_parent(&va->rb_node);
+ }
+
+#if DEBUG_AUGMENT_PROPAGATE_CHECK
+ augment_tree_propagate_check(free_vmap_area_root.rb_node);
+#endif
+}
+
+static void
+insert_vmap_area(struct vmap_area *va,
+ struct rb_root *root, struct list_head *head)
+{
+ struct rb_node **link;
+ struct rb_node *parent;
+
+ link = find_va_links(va, root, NULL, &parent);
+ link_va(va, root, parent, link, head);
+}
+
+static void
+insert_vmap_area_augment(struct vmap_area *va,
+ struct rb_node *from, struct rb_root *root,
+ struct list_head *head)
+{
+ struct rb_node **link;
+ struct rb_node *parent;
+
+ if (from)
+ link = find_va_links(va, NULL, from, &parent);
+ else
+ link = find_va_links(va, root, NULL, &parent);
+
+ link_va(va, root, parent, link, head);
+ augment_tree_propagate_from(va);
+}
+
+/*
+ * 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.
+ */
+static __always_inline void
+merge_or_add_vmap_area(struct vmap_area *va,
+ struct rb_root *root, struct list_head *head)
+{
+ 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);
+
+ /*
+ * 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;
+
+ /* Check and update the tree if needed. */
+ augment_tree_propagate_from(sibling);
+
+ /* Free vmap_area object. */
+ kmem_cache_free(vmap_area_cachep, va);
+
+ /* 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) {
+ sibling->va_end = va->va_end;
+
+ /* Check and update the tree if needed. */
+ augment_tree_propagate_from(sibling);
+
+ if (merged)
+ unlink_va(va, root);
+
+ /* Free vmap_area object. */
+ kmem_cache_free(vmap_area_cachep, va);
+ return;
+ }
+ }
+
+insert:
+ if (!merged) {
+ link_va(va, root, parent, link, head);
+ augment_tree_propagate_from(va);
+ }
+}
+
+static __always_inline bool
+is_within_this_va(struct vmap_area *va, unsigned long size,
+ unsigned long align, unsigned long vstart)
+{
+ unsigned long nva_start_addr;
+
+ if (va->va_start > vstart)
+ nva_start_addr = ALIGN(va->va_start, align);
+ else
+ nva_start_addr = ALIGN(vstart, align);
+
+ /* Can be overflowed due to big size or alignment. */
+ if (nva_start_addr + size < nva_start_addr ||
+ nva_start_addr < vstart)
+ return false;
+
+ 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.
+ */
+static __always_inline struct vmap_area *
+find_vmap_lowest_match(unsigned long size,
+ unsigned long align, unsigned long vstart)
+{
+ struct vmap_area *va;
+ struct rb_node *node;
+ unsigned long length;
+
+ /* Start from the root. */
+ node = free_vmap_area_root.rb_node;
+
+ /* Adjust the search size for alignment overhead. */
+ length = size + align - 1;
+
+ while (node) {
+ va = rb_entry(node, struct vmap_area, rb_node);
+
+ if (get_subtree_max_size(node->rb_left) >= length &&
+ vstart < va->va_start) {
+ node = node->rb_left;
+ } else {
+ if (is_within_this_va(va, size, align, vstart))
+ return va;
+
+ /*
+ * 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
+ * only once due to "vstart" restriction.
+ */
+ 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) {
+ node = node->rb_right;
+ break;
+ }
+ }
+ }
+ }
+
+ return NULL;
+}
+
+#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
+#include <linux/random.h>
+
+static struct vmap_area *
+find_vmap_lowest_linear_match(unsigned long size,
+ unsigned long align, unsigned long vstart)
+{
+ struct vmap_area *va;
+
+ list_for_each_entry(va, &free_vmap_area_list, list) {
+ if (!is_within_this_va(va, size, align, vstart))
+ continue;
+
+ return va;
+ }
+
+ return NULL;
+}
+
+static void
+find_vmap_lowest_match_check(unsigned long size)
+{
+ struct vmap_area *va_1, *va_2;
+ unsigned long vstart;
+ unsigned int rnd;
+
+ get_random_bytes(&rnd, sizeof(rnd));
+ vstart = VMALLOC_START + rnd;
+
+ va_1 = find_vmap_lowest_match(size, 1, vstart);
+ va_2 = find_vmap_lowest_linear_match(size, 1, vstart);
+
+ if (va_1 != va_2)
+ pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n",
+ va_1, va_2, vstart);
+}
+#endif
+
+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 */
+};
+
+static __always_inline enum fit_type
+classify_va_fit_type(struct vmap_area *va,
+ unsigned long nva_start_addr, unsigned long size)
+{
+ enum fit_type type;
+
+ /* Check if it is within VA. */
+ if (nva_start_addr < va->va_start ||
+ nva_start_addr + size > va->va_end)
+ return NOTHING_FIT;
+
+ /* Now classify. */
+ if (va->va_start == nva_start_addr) {
+ if (va->va_end == nva_start_addr + size)
+ type = FL_FIT_TYPE;
+ else
+ type = LE_FIT_TYPE;
+ } else if (va->va_end == nva_start_addr + size) {
+ type = RE_FIT_TYPE;
+ } else {
+ type = NE_FIT_TYPE;
+ }
+
+ return type;
+}
+
+static __always_inline int
+adjust_va_to_fit_type(struct vmap_area *va,
+ unsigned long nva_start_addr, unsigned long size,
+ enum fit_type type)
+{
+ struct vmap_area *lva = NULL;
+
+ if (type == FL_FIT_TYPE) {
+ /*
+ * No need to split VA, it fully fits.
+ *
+ * | |
+ * V NVA V
+ * |---------------|
+ */
+ unlink_va(va, &free_vmap_area_root);
+ kmem_cache_free(vmap_area_cachep, va);
+ } else if (type == LE_FIT_TYPE) {
+ /*
+ * Split left edge of fit VA.
+ *
+ * | |
+ * V NVA V R
+ * |-------|-------|
+ */
+ va->va_start += size;
+ } else if (type == RE_FIT_TYPE) {
+ /*
+ * Split right edge of fit VA.
+ *
+ * | |
+ * L V NVA V
+ * |-------|-------|
+ */
+ va->va_end = nva_start_addr;
+ } else if (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.
+ */
+ lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT);
+ if (!lva)
+ return -1;
+ }
+
+ /*
+ * Build the remainder.
+ */
+ lva->va_start = va->va_start;
+ lva->va_end = nva_start_addr;
+
+ /*
+ * Shrink this VA to remaining size.
+ */
+ va->va_start = nva_start_addr + size;
+ } else {
+ return -1;
+ }
+
+ if (type != FL_FIT_TYPE) {
+ augment_tree_propagate_from(va);
+
+ if (lva) /* type == NE_FIT_TYPE */
+ insert_vmap_area_augment(lva, &va->rb_node,
+ &free_vmap_area_root, &free_vmap_area_list);
+ }
+
+ return 0;
+}
+
+/*
+ * Returns a start address of the newly allocated area, if success.
+ * Otherwise a vend is returned that indicates failure.
+ */
+static __always_inline unsigned long
+__alloc_vmap_area(unsigned long size, unsigned long align,
+ unsigned long vstart, unsigned long vend)
+{
+ unsigned long nva_start_addr;
+ struct vmap_area *va;
+ enum fit_type type;
+ int ret;
+
+ va = find_vmap_lowest_match(size, align, vstart);
+ if (unlikely(!va))
+ return vend;
+
+ if (va->va_start > vstart)
+ nva_start_addr = ALIGN(va->va_start, align);
+ else
+ nva_start_addr = ALIGN(vstart, align);
+
+ /* Check the "vend" restriction. */
+ if (nva_start_addr + size > vend)
+ return vend;
+
+ /* Classify what we have found. */
+ type = classify_va_fit_type(va, nva_start_addr, size);
+ if (WARN_ON_ONCE(type == NOTHING_FIT))
+ return vend;
+
+ /* Update the free vmap_area. */
+ ret = adjust_va_to_fit_type(va, nva_start_addr, size, type);
+ if (ret)
+ return vend;
+
+#if DEBUG_AUGMENT_LOWEST_MATCH_CHECK
+ find_vmap_lowest_match_check(size);
+#endif
+
+ return nva_start_addr;
+}
/*
* Allocate a region of KVA of the specified size and alignment, within the
@@ -404,19 +1051,20 @@
unsigned long vstart, unsigned long vend,
int node, gfp_t gfp_mask)
{
- struct vmap_area *va;
- struct rb_node *n;
+ struct vmap_area *va, *pva;
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));
+ if (unlikely(!vmap_initialized))
+ return ERR_PTR(-EBUSY);
+
might_sleep();
- va = kmalloc_node(sizeof(struct vmap_area),
+ va = kmem_cache_alloc_node(vmap_area_cachep,
gfp_mask & GFP_RECLAIM_MASK, node);
if (unlikely(!va))
return ERR_PTR(-ENOMEM);
@@ -428,84 +1076,46 @@
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.
+ * Preload this CPU with one extra vmap_area object to ensure
+ * that we have it available when fit type of free area is
+ * NE_FIT_TYPE.
+ *
+ * The preload is done 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.
+ *
+ * Even if it fails we do not really care about that. Just proceed
+ * as it is. "overflow" path will refill the cache we allocate from.
*/
- 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;
+ preempt_disable();
+ if (!__this_cpu_read(ne_fit_preload_node)) {
+ preempt_enable();
+ pva = kmem_cache_alloc_node(vmap_area_cachep, GFP_KERNEL, node);
+ preempt_disable();
- /* 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 (__this_cpu_cmpxchg(ne_fit_preload_node, NULL, pva)) {
+ if (pva)
+ kmem_cache_free(vmap_area_cachep, pva);
}
-
- 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;
+ spin_lock(&vmap_area_lock);
+ preempt_enable();
- if (list_is_last(&first->list, &vmap_area_list))
- goto found;
-
- first = list_next_entry(first, list);
- }
-
-found:
- if (addr + size > vend)
+ /*
+ * If an allocation fails, the "vend" address is
+ * returned. Therefore trigger the overflow path.
+ */
+ addr = __alloc_vmap_area(size, align, vstart, vend);
+ if (unlikely(addr == 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;
+ va->vm = NULL;
+ insert_vmap_area(va, &vmap_area_root, &vmap_area_list);
+
spin_unlock(&vmap_area_lock);
BUG_ON(!IS_ALIGNED(va->va_start, align));
@@ -534,7 +1144,8 @@
if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit())
pr_warn("vmap allocation for size %lu failed: use vmalloc=<size> to increase size\n",
size);
- kfree(va);
+
+ kmem_cache_free(vmap_area_cachep, va);
return ERR_PTR(-EBUSY);
}
@@ -552,37 +1163,16 @@
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);
+ /*
+ * Remove from the busy tree/list.
+ */
+ unlink_va(va, &vmap_area_root);
/*
- * Track the highest possible candidate for pcpu area
- * allocation. Areas outside of vmalloc area can be returned
- * here too, consider only end addresses which fall inside
- * vmalloc area proper.
+ * Merge VA with its neighbors, otherwise just add it.
*/
- if (va->va_end > VMALLOC_START && va->va_end <= VMALLOC_END)
- vmap_area_pcpu_hole = max(vmap_area_pcpu_hole, va->va_end);
-
- kfree_rcu(va, rcu_head);
+ merge_or_add_vmap_area(va,
+ &free_vmap_area_root, &free_vmap_area_list);
}
/*
@@ -628,7 +1218,7 @@
return log * (32UL * 1024 * 1024 / PAGE_SIZE);
}
-static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);
+static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0);
/*
* Serialize vmap purging. There is no actual criticial section protected
@@ -646,7 +1236,7 @@
*/
void set_iounmap_nonlazy(void)
{
- atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
+ atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1);
}
/*
@@ -654,34 +1244,53 @@
*/
static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
{
+ unsigned long resched_threshold;
struct llist_node *valist;
struct vmap_area *va;
struct vmap_area *n_va;
- bool do_free = false;
lockdep_assert_held(&vmap_purge_lock);
valist = llist_del_all(&vmap_purge_list);
+ if (unlikely(valist == NULL))
+ return false;
+
+ /*
+ * First make sure the mappings are removed from all page-tables
+ * before they are freed.
+ */
+ vmalloc_sync_all();
+
+ /*
+ * TODO: to calculate a flush range without looping.
+ * The list can be up to lazy_max_pages() elements.
+ */
llist_for_each_entry(va, valist, purge_list) {
if (va->va_start < start)
start = va->va_start;
if (va->va_end > end)
end = va->va_end;
- do_free = true;
}
- if (!do_free)
- return false;
-
flush_tlb_kernel_range(start, end);
+ resched_threshold = lazy_max_pages() << 1;
spin_lock(&vmap_area_lock);
llist_for_each_entry_safe(va, n_va, valist, purge_list) {
- int nr = (va->va_end - va->va_start) >> PAGE_SHIFT;
+ unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT;
- __free_vmap_area(va);
- atomic_sub(nr, &vmap_lazy_nr);
- cond_resched_lock(&vmap_area_lock);
+ /*
+ * Finally insert or merge lazily-freed area. It is
+ * detached and there is no need to "unlink" it from
+ * anything.
+ */
+ merge_or_add_vmap_area(va,
+ &free_vmap_area_root, &free_vmap_area_list);
+
+ atomic_long_sub(nr, &vmap_lazy_nr);
+
+ if (atomic_long_read(&vmap_lazy_nr) < resched_threshold)
+ cond_resched_lock(&vmap_area_lock);
}
spin_unlock(&vmap_area_lock);
return true;
@@ -717,10 +1326,14 @@
*/
static void free_vmap_area_noflush(struct vmap_area *va)
{
- int nr_lazy;
+ unsigned long nr_lazy;
- nr_lazy = atomic_add_return((va->va_end - va->va_start) >> PAGE_SHIFT,
- &vmap_lazy_nr);
+ spin_lock(&vmap_area_lock);
+ unlink_va(va, &vmap_area_root);
+ spin_unlock(&vmap_area_lock);
+
+ nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >>
+ PAGE_SHIFT, &vmap_lazy_nr);
/* After this point, we may free va at any time */
llist_add(&va->purge_list, &vmap_purge_list);
@@ -783,8 +1396,6 @@
#define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE)
-static bool vmap_initialized __read_mostly = false;
-
struct vmap_block_queue {
spinlock_t lock;
struct list_head free;
@@ -840,7 +1451,7 @@
* @order: how many 2^order pages should be occupied in newly allocated block
* @gfp_mask: flags for the page level allocator
*
- * Returns: virtual address in a newly allocated block or ERR_PTR(-errno)
+ * Return: virtual address in a newly allocated block or ERR_PTR(-errno)
*/
static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
{
@@ -1055,24 +1666,9 @@
spin_unlock(&vb->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)
+static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
{
- unsigned long start = ULONG_MAX, end = 0;
int cpu;
- int flush = 0;
if (unlikely(!vmap_initialized))
return;
@@ -1109,6 +1705,27 @@
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)
+{
+ unsigned long start = ULONG_MAX, end = 0;
+ int flush = 0;
+
+ _vm_unmap_aliases(start, end, flush);
+}
EXPORT_SYMBOL_GPL(vm_unmap_aliases);
/**
@@ -1187,6 +1804,7 @@
EXPORT_SYMBOL(vm_map_ram);
static struct vm_struct *vmlist __initdata;
+
/**
* vm_area_add_early - add vmap area early during boot
* @vm: vm_struct to add
@@ -1238,12 +1856,58 @@
vm_area_add_early(vm);
}
+static void vmap_init_free_space(void)
+{
+ unsigned long vmap_start = 1;
+ const unsigned long vmap_end = ULONG_MAX;
+ struct vmap_area *busy, *free;
+
+ /*
+ * B F B B B F
+ * -|-----|.....|-----|-----|-----|.....|-
+ * | The KVA space |
+ * |<--------------------------------->|
+ */
+ list_for_each_entry(busy, &vmap_area_list, list) {
+ if (busy->va_start - 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 = busy->va_start;
+
+ insert_vmap_area_augment(free, NULL,
+ &free_vmap_area_root,
+ &free_vmap_area_list);
+ }
+ }
+
+ vmap_start = busy->va_end;
+ }
+
+ if (vmap_end - 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 = vmap_end;
+
+ insert_vmap_area_augment(free, NULL,
+ &free_vmap_area_root,
+ &free_vmap_area_list);
+ }
+ }
+}
+
void __init vmalloc_init(void)
{
struct vmap_area *va;
struct vm_struct *tmp;
int i;
+ /*
+ * Create the cache for vmap_area objects.
+ */
+ vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC);
+
for_each_possible_cpu(i) {
struct vmap_block_queue *vbq;
struct vfree_deferred *p;
@@ -1258,16 +1922,20 @@
/* Import existing vmlist entries. */
for (tmp = vmlist; tmp; tmp = tmp->next) {
- va = kzalloc(sizeof(struct vmap_area), GFP_NOWAIT);
- va->flags = VM_VM_AREA;
+ va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT);
+ if (WARN_ON_ONCE(!va))
+ continue;
+
va->va_start = (unsigned long)tmp->addr;
va->va_end = va->va_start + tmp->size;
va->vm = tmp;
- __insert_vmap_area(va);
+ insert_vmap_area(va, &vmap_area_root, &vmap_area_list);
}
- vmap_area_pcpu_hole = VMALLOC_END;
-
+ /*
+ * Now we can initialize a free vmap space.
+ */
+ vmap_init_free_space();
vmap_initialized = true;
}
@@ -1355,7 +2023,6 @@
vm->size = va->va_end - va->va_start;
vm->caller = caller;
va->vm = vm;
- va->flags |= VM_VM_AREA;
spin_unlock(&vmap_area_lock);
}
@@ -1421,13 +2088,15 @@
}
/**
- * get_vm_area - reserve a contiguous kernel virtual area
- * @size: size of the area
- * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC
+ * 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.
+ * 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(unsigned long size, unsigned long flags)
{
@@ -1444,31 +2113,35 @@
}
/**
- * find_vm_area - find a continuous kernel virtual area
- * @addr: base address
+ * 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.
+ * 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: pointer to the found area or %NULL on faulure
*/
struct vm_struct *find_vm_area(const void *addr)
{
struct vmap_area *va;
va = find_vmap_area((unsigned long)addr);
- if (va && va->flags & VM_VM_AREA)
- return va->vm;
+ if (!va)
+ return NULL;
- return NULL;
+ return va->vm;
}
/**
- * remove_vm_area - find and remove a continuous kernel virtual area
- * @addr: base address
+ * 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.
+ * 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: pointer to the found area or %NULL on faulure
*/
struct vm_struct *remove_vm_area(const void *addr)
{
@@ -1476,14 +2149,12 @@
might_sleep();
- va = find_vmap_area((unsigned long)addr);
- if (va && va->flags & VM_VM_AREA) {
+ spin_lock(&vmap_area_lock);
+ va = __find_vmap_area((unsigned long)addr);
+ if (va && va->vm) {
struct vm_struct *vm = va->vm;
- spin_lock(&vmap_area_lock);
va->vm = NULL;
- va->flags &= ~VM_VM_AREA;
- va->flags |= VM_LAZY_FREE;
spin_unlock(&vmap_area_lock);
kasan_free_shadow(vm);
@@ -1491,9 +2162,68 @@
return vm;
}
+
+ spin_unlock(&vmap_area_lock);
return NULL;
}
+static inline void set_area_direct_map(const struct vm_struct *area,
+ int (*set_direct_map)(struct page *page))
+{
+ int i;
+
+ for (i = 0; i < area->nr_pages; i++)
+ if (page_address(area->pages[i]))
+ set_direct_map(area->pages[i]);
+}
+
+/* Handle removing and resetting vm mappings related to the vm_struct. */
+static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
+{
+ unsigned long start = ULONG_MAX, end = 0;
+ int flush_reset = area->flags & VM_FLUSH_RESET_PERMS;
+ int flush_dmap = 0;
+ int i;
+
+ remove_vm_area(area->addr);
+
+ /* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */
+ if (!flush_reset)
+ return;
+
+ /*
+ * If not deallocating pages, just do the flush of the VM area and
+ * return.
+ */
+ if (!deallocate_pages) {
+ vm_unmap_aliases();
+ return;
+ }
+
+ /*
+ * If execution gets here, flush the vm mapping and reset the direct
+ * map. Find the start and end range of the direct mappings to make sure
+ * the vm_unmap_aliases() flush includes the direct map.
+ */
+ for (i = 0; i < area->nr_pages; i++) {
+ unsigned long addr = (unsigned long)page_address(area->pages[i]);
+ if (addr) {
+ start = min(addr, start);
+ end = max(addr + PAGE_SIZE, end);
+ flush_dmap = 1;
+ }
+ }
+
+ /*
+ * 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);
+}
+
static void __vunmap(const void *addr, int deallocate_pages)
{
struct vm_struct *area;
@@ -1505,7 +2235,7 @@
addr))
return;
- area = find_vmap_area((unsigned long)addr)->vm;
+ area = find_vm_area(addr);
if (unlikely(!area)) {
WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n",
addr);
@@ -1515,7 +2245,8 @@
debug_check_no_locks_freed(area->addr, get_vm_area_size(area));
debug_check_no_obj_freed(area->addr, get_vm_area_size(area));
- remove_vm_area(addr);
+ vm_remove_mappings(area, deallocate_pages);
+
if (deallocate_pages) {
int i;
@@ -1525,6 +2256,7 @@
BUG_ON(!page);
__free_pages(page, 0);
}
+ atomic_long_sub(area->nr_pages, &nr_vmalloc_pages);
kvfree(area->pages);
}
@@ -1548,11 +2280,11 @@
}
/**
- * vfree_atomic - release memory allocated by vmalloc()
- * @addr: memory base address
+ * 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.
+ * This one is just like vfree() but can be called in any atomic context
+ * except NMIs.
*/
void vfree_atomic(const void *addr)
{
@@ -1565,19 +2297,29 @@
__vfree_deferred(addr);
}
+static void __vfree(const void *addr)
+{
+ if (unlikely(in_interrupt()))
+ __vfree_deferred(addr);
+ else
+ __vunmap(addr, 1);
+}
+
/**
- * vfree - release memory allocated by vmalloc()
- * @addr: memory base address
+ * vfree - release memory allocated by vmalloc()
+ * @addr: memory base address
*
- * Free the virtually continuous memory area starting at @addr, as
- * obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is
- * NULL, no operation is performed.
+ * Free the virtually continuous memory area starting at @addr, as
+ * obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is
+ * NULL, no operation is performed.
*
- * Must not be called in NMI context (strictly speaking, only if we don't
- * have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling
- * conventions for vfree() arch-depenedent would be a really bad idea)
+ * Must not be called in NMI context (strictly speaking, only if we don't
+ * have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling
+ * conventions for vfree() arch-depenedent would be a really bad idea)
*
- * NOTE: assumes that the object at @addr has a size >= sizeof(llist_node)
+ * May sleep if called *not* from interrupt context.
+ *
+ * NOTE: assumes that the object at @addr has a size >= sizeof(llist_node)
*/
void vfree(const void *addr)
{
@@ -1585,23 +2327,23 @@
kmemleak_free(addr);
+ might_sleep_if(!in_interrupt());
+
if (!addr)
return;
- if (unlikely(in_interrupt()))
- __vfree_deferred(addr);
- else
- __vunmap(addr, 1);
+
+ __vfree(addr);
}
EXPORT_SYMBOL(vfree);
/**
- * vunmap - release virtual mapping obtained by vmap()
- * @addr: memory base address
+ * 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().
+ * 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.
+ * Must not be called in interrupt context.
*/
void vunmap(const void *addr)
{
@@ -1613,24 +2355,26 @@
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
+ * 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.
+ * Maps @count pages from @pages into contiguous kernel virtual
+ * space.
+ *
+ * Return: the address of the area or %NULL on failure
*/
void *vmap(struct page **pages, unsigned int count,
- unsigned long flags, pgprot_t prot)
+ unsigned long flags, pgprot_t prot)
{
struct vm_struct *area;
unsigned long size; /* In bytes */
might_sleep();
- if (count > totalram_pages)
+ if (count > totalram_pages())
return NULL;
size = (unsigned long)count << PAGE_SHIFT;
@@ -1664,7 +2408,6 @@
nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
array_size = (nr_pages * sizeof(struct page *));
- area->nr_pages = nr_pages;
/* Please note that the recursion is strictly bounded. */
if (array_size > PAGE_SIZE) {
pages = __vmalloc_node(array_size, 1, nested_gfp|highmem_mask,
@@ -1672,13 +2415,16 @@
} else {
pages = kmalloc_node(array_size, nested_gfp, node);
}
- area->pages = pages;
- if (!area->pages) {
+
+ if (!pages) {
remove_vm_area(area->addr);
kfree(area);
return NULL;
}
+ area->pages = pages;
+ area->nr_pages = nr_pages;
+
for (i = 0; i < area->nr_pages; i++) {
struct page *page;
@@ -1690,12 +2436,14 @@
if (unlikely(!page)) {
/* Successfully allocated i pages, free them in __vunmap() */
area->nr_pages = i;
+ atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
goto fail;
}
area->pages[i] = page;
if (gfpflags_allow_blocking(gfp_mask|highmem_mask))
cond_resched();
}
+ atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
if (map_vm_area(area, prot, pages))
goto fail;
@@ -1705,25 +2453,27 @@
warn_alloc(gfp_mask, NULL,
"vmalloc: allocation failure, allocated %ld of %ld bytes",
(area->nr_pages*PAGE_SIZE), area->size);
- vfree(area->addr);
+ __vfree(area->addr);
return NULL;
}
/**
- * __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
+ * __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. Map them into contiguous
- * kernel virtual space, using a pagetable protection of @prot.
+ * Allocate enough pages to cover @size from the page level
+ * allocator with @gfp_mask flags. 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(unsigned long size, unsigned long align,
unsigned long start, unsigned long end, gfp_t gfp_mask,
@@ -1735,7 +2485,7 @@
unsigned long real_size = size;
size = PAGE_ALIGN(size);
- if (!size || (size >> PAGE_SHIFT) > totalram_pages)
+ if (!size || (size >> PAGE_SHIFT) > totalram_pages())
goto fail;
area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED |
@@ -1764,25 +2514,35 @@
return NULL;
}
+/*
+ * 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_range);
+#endif
+
/**
- * __vmalloc_node - allocate virtually contiguous memory
- * @size: allocation size
- * @align: desired alignment
- * @gfp_mask: flags for the page level allocator
- * @prot: protection mask for the allocated pages
- * @node: node to use for allocation or NUMA_NO_NODE
- * @caller: caller's return address
+ * __vmalloc_node - allocate virtually contiguous memory
+ * @size: allocation size
+ * @align: desired alignment
+ * @gfp_mask: flags for the page level allocator
+ * @prot: protection mask for the allocated pages
+ * @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, using a pagetable protection of @prot.
+ * Allocate enough pages to cover @size from the page level
+ * allocator with @gfp_mask flags. Map them into contiguous
+ * kernel virtual space, using a pagetable protection of @prot.
*
- * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL
- * and __GFP_NOFAIL are not supported
+ * 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.
+ * 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
*/
static void *__vmalloc_node(unsigned long size, unsigned long align,
gfp_t gfp_mask, pgprot_t prot,
@@ -1814,13 +2574,16 @@
}
/**
- * 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.
+ * vmalloc - allocate virtually contiguous memory
+ * @size: allocation size
*
- * For tight control over page level allocator and protection flags
- * use __vmalloc() instead.
+ * 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(unsigned long size)
{
@@ -1830,14 +2593,17 @@
EXPORT_SYMBOL(vmalloc);
/**
- * 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.
+ * vzalloc - allocate virtually contiguous memory with zero fill
+ * @size: allocation size
*
- * For tight control over page level allocator and protection flags
- * use __vmalloc() instead.
+ * 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(unsigned long size)
{
@@ -1852,34 +2618,30 @@
*
* 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(unsigned long size)
{
- struct vm_struct *area;
- void *ret;
-
- ret = __vmalloc_node(size, SHMLBA,
- GFP_KERNEL | __GFP_ZERO,
- PAGE_KERNEL, NUMA_NO_NODE,
- __builtin_return_address(0));
- if (ret) {
- area = find_vm_area(ret);
- area->flags |= VM_USERMAP;
- }
- return ret;
+ return __vmalloc_node_range(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);
/**
- * vmalloc_node - allocate memory on a specific node
- * @size: allocation size
- * @node: numa node
+ * 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.
+ * 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.
+ * 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(unsigned long size, int node)
{
@@ -1899,6 +2661,8 @@
*
* For tight control over page level allocator and protection flags
* use __vmalloc_node() instead.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
*/
void *vzalloc_node(unsigned long size, int node)
{
@@ -1908,21 +2672,23 @@
EXPORT_SYMBOL(vzalloc_node);
/**
- * vmalloc_exec - allocate virtually contiguous, executable memory
- * @size: allocation size
+ * vmalloc_exec - allocate virtually contiguous, executable memory
+ * @size: allocation size
*
- * Kernel-internal function to allocate enough pages to cover @size
- * the page level allocator and map them into contiguous and
- * executable kernel virtual space.
+ * Kernel-internal function to allocate enough pages to cover @size
+ * the page level allocator and map them into contiguous and
+ * executable kernel virtual space.
*
- * For tight control over page level allocator and protection flags
- * use __vmalloc() instead.
+ * 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_exec(unsigned long size)
{
- return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL_EXEC,
- NUMA_NO_NODE, __builtin_return_address(0));
+ return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
+ GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
+ NUMA_NO_NODE, __builtin_return_address(0));
}
#if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
@@ -1938,11 +2704,13 @@
#endif
/**
- * vmalloc_32 - allocate virtually contiguous memory (32bit addressable)
- * @size: allocation size
+ * 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.
+ * 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(unsigned long size)
{
@@ -1953,23 +2721,19 @@
/**
* vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
- * @size: allocation size
+ * @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(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;
+ return __vmalloc_node_range(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);
@@ -2055,31 +2819,29 @@
}
/**
- * vread() - read vmalloc area in a safe way.
- * @buf: buffer for reading data
- * @addr: vm address.
- * @count: number of bytes to be read.
+ * 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.
*
- * 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.
*
- * 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 /dev/kmem.
*
- * 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.
- *
+ * 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(char *buf, char *addr, unsigned long count)
{
struct vmap_area *va;
@@ -2097,7 +2859,7 @@
if (!count)
break;
- if (!(va->flags & VM_VM_AREA))
+ if (!va->vm)
continue;
vm = va->vm;
@@ -2136,31 +2898,29 @@
}
/**
- * vwrite() - write vmalloc area in a safe way.
- * @buf: buffer for source data
- * @addr: vm address.
- * @count: number of bytes to be read.
+ * 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.
*
- * 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.
*
- * 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 information, as /dev/kmem.
*
- * 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.
+ * 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 vwrite(char *buf, char *addr, unsigned long count)
{
struct vmap_area *va;
@@ -2179,7 +2939,7 @@
if (!count)
break;
- if (!(va->flags & VM_VM_AREA))
+ if (!va->vm)
continue;
vm = va->vm;
@@ -2212,20 +2972,20 @@
}
/**
- * 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
+ * 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
+ * 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.
+ * 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)
+ * 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)
@@ -2241,10 +3001,10 @@
if (!area)
return -EINVAL;
- if (!(area->flags & VM_USERMAP))
+ if (!(area->flags & (VM_USERMAP | VM_DMA_COHERENT)))
return -EINVAL;
- if (kaddr + size > area->addr + area->size)
+ if (kaddr + size > area->addr + get_vm_area_size(area))
return -EINVAL;
do {
@@ -2267,18 +3027,18 @@
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
+ * 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
+ * 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.
+ * 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)
+ * Similar to remap_pfn_range() (see mm/memory.c)
*/
int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
unsigned long pgoff)
@@ -2292,13 +3052,16 @@
/*
* Implement a stub for vmalloc_sync_all() if the architecture chose not to
* have one.
+ *
+ * The purpose of this function is to make sure the vmalloc area
+ * mappings are identical in all page-tables in the system.
*/
void __weak vmalloc_sync_all(void)
{
}
-static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
+static int f(pte_t *pte, unsigned long addr, void *data)
{
pte_t ***p = data;
@@ -2310,18 +3073,18 @@
}
/**
- * alloc_vm_area - allocate a range of kernel address space
- * @size: size of the area
- * @ptes: returns the PTEs for the address space
+ * 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
+ * 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.
+ * 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.
+ * 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)
{
@@ -2362,81 +3125,64 @@
}
/**
- * 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
+ * pvm_find_va_enclose_addr - find the vmap_area @addr belongs to
+ * @addr: target address
*
- * 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.
+ * 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.
*/
-static bool pvm_find_next_prev(unsigned long end,
- struct vmap_area **pnext,
- struct vmap_area **pprev)
+static struct vmap_area *
+pvm_find_va_enclose_addr(unsigned long addr)
{
- struct rb_node *n = vmap_area_root.rb_node;
- struct vmap_area *va = NULL;
+ struct vmap_area *va, *tmp;
+ struct rb_node *n;
+
+ n = free_vmap_area_root.rb_node;
+ 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)
+ 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
- break;
+ } else {
+ n = n->rb_left;
+ }
}
- 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;
+ return va;
}
/**
- * 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
+ * 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.
*
- * 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.
+ * Returns: determined end address within vmap_area
*/
-static unsigned long pvm_determine_end(struct vmap_area **pnext,
- struct vmap_area **pprev,
- unsigned long align)
+static unsigned long
+pvm_determine_end_from_reverse(struct vmap_area **va, unsigned long align)
{
- const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
+ 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));
+ if (likely(*va)) {
+ list_for_each_entry_from_reverse((*va),
+ &free_vmap_area_list, list) {
+ addr = min((*va)->va_end & ~(align - 1), vmalloc_end);
+ if ((*va)->va_start < addr)
+ return addr;
+ }
}
- return addr;
+ return 0;
}
/**
@@ -2456,12 +3202,12 @@
* 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 structures are inserted and the result is returned.
+ * 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(const unsigned long *offsets,
const size_t *sizes, int nr_vms,
@@ -2469,11 +3215,12 @@
{
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 vmap_area **vas, *va;
struct vm_struct **vms;
int area, area2, last_area, term_area;
- unsigned long base, start, end, last_end;
+ unsigned long base, start, size, end, last_end;
bool purged = false;
+ enum fit_type type;
/* verify parameters and allocate data structures */
BUG_ON(offset_in_page(align) || !is_power_of_2(align));
@@ -2509,7 +3256,7 @@
goto err_free2;
for (area = 0; area < nr_vms; area++) {
- vas[area] = kzalloc(sizeof(struct vmap_area), GFP_KERNEL);
+ 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;
@@ -2522,49 +3269,39 @@
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;
+ va = pvm_find_va_enclose_addr(vmalloc_end);
+ base = pvm_determine_end_from_reverse(&va, 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 (base + last_end < vmalloc_start + last_end)
+ goto overflow;
/*
- * If next overlaps, move base downwards so that it's
- * right below next and then recheck.
+ * Fitting base has not been found.
*/
- if (next && next->va_start < base + end) {
- base = pvm_determine_end(&next, &prev, align) - end;
+ if (va == NULL)
+ goto overflow;
+
+ /*
+ * If required width exeeds 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 prev overlaps, shift down next and prev and move
- * base so that it's right below new next and then
- * recheck.
+ * If this VA does not fit, move base downwards and 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;
+ 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;
}
@@ -2576,22 +3313,41 @@
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);
+ va = pvm_find_va_enclose_addr(base + end);
}
-found:
+
/* we've found a fitting base, insert all va's */
for (area = 0; area < nr_vms; area++) {
- struct vmap_area *va = vas[area];
+ int ret;
- va->va_start = base + offsets[area];
- va->va_end = va->va_start + sizes[area];
- __insert_vmap_area(va);
+ 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;
+
+ type = classify_va_fit_type(va, start, size);
+ if (WARN_ON_ONCE(type == NOTHING_FIT))
+ /* It is a BUG(), but trigger recovery instead. */
+ goto recovery;
+
+ ret = adjust_va_to_fit_type(va, start, size, type);
+ if (unlikely(ret))
+ goto recovery;
+
+ /* Allocated area. */
+ va = vas[area];
+ va->va_start = start;
+ va->va_end = start + size;
+
+ insert_vmap_area(va, &vmap_area_root, &vmap_area_list);
}
- vmap_area_pcpu_hole = base + offsets[last_area];
-
spin_unlock(&vmap_area_lock);
/* insert all vm's */
@@ -2602,9 +3358,38 @@
kfree(vas);
return vms;
+recovery:
+ /* Remove previously inserted areas. */
+ while (area--) {
+ __free_vmap_area(vas[area]);
+ vas[area] = NULL;
+ }
+
+overflow:
+ spin_unlock(&vmap_area_lock);
+ if (!purged) {
+ purge_vmap_area_lazy();
+ 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++) {
- kfree(vas[area]);
+ if (vas[area])
+ kmem_cache_free(vmap_area_cachep, vas[area]);
+
kfree(vms[area]);
}
err_free2:
@@ -2673,6 +3458,22 @@
}
}
+static void show_purge_info(struct seq_file *m)
+{
+ struct llist_node *head;
+ struct vmap_area *va;
+
+ head = READ_ONCE(vmap_purge_list.first);
+ if (head == NULL)
+ return;
+
+ llist_for_each_entry(va, head, purge_list) {
+ seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n",
+ (void *)va->va_start, (void *)va->va_end,
+ va->va_end - va->va_start);
+ }
+}
+
static int s_show(struct seq_file *m, void *p)
{
struct vmap_area *va;
@@ -2681,14 +3482,13 @@
va = list_entry(p, struct vmap_area, list);
/*
- * 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.
+ * s_show can encounter race with remove_vm_area, !vm on behalf
+ * of vmap area is being tear down or vm_map_ram allocation.
*/
- if (!(va->flags & VM_VM_AREA)) {
- seq_printf(m, "0x%pK-0x%pK %7ld %s\n",
+ if (!va->vm) {
+ seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
(void *)va->va_start, (void *)va->va_end,
- va->va_end - va->va_start,
- va->flags & VM_LAZY_FREE ? "unpurged vm_area" : "vm_map_ram");
+ va->va_end - va->va_start);
return 0;
}
@@ -2719,11 +3519,24 @@
if (v->flags & VM_USERMAP)
seq_puts(m, " user");
+ if (v->flags & VM_DMA_COHERENT)
+ seq_puts(m, " dma-coherent");
+
if (is_vmalloc_addr(v->pages))
seq_puts(m, " vpages");
show_numa_info(m, v);
seq_putc(m, '\n');
+
+ /*
+ * As a final step, dump "unpurged" areas. Note,
+ * that entire "/proc/vmallocinfo" output will not
+ * be address sorted, because the purge list is not
+ * sorted.
+ */
+ if (list_is_last(&va->list, &vmap_area_list))
+ show_purge_info(m);
+
return 0;
}
@@ -2747,4 +3560,3 @@
module_init(proc_vmalloc_init);
#endif
-