#include <linux/iova.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/bitops.h>
#include <linux/cpu.h>
#define IOVA_ANCHOR ~0UL
#define IOVA_RANGE_CACHE_MAX_SIZE 6 /* log of max cached IOVA range size (in pages) */
static bool iova_rcache_insert(struct iova_domain *iovad,
unsigned long pfn,
unsigned long size);
static unsigned long iova_rcache_get(struct iova_domain *iovad,
unsigned long size,
unsigned long limit_pfn);
static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
static void free_iova_rcaches(struct iova_domain *iovad);
unsigned long iova_rcache_range(void)
{
return PAGE_SIZE << (IOVA_RANGE_CACHE_MAX_SIZE - 1);
}
static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
{
struct iova_domain *iovad;
iovad = hlist_entry_safe(node, struct iova_domain, cpuhp_dead);
free_cpu_cached_iovas(cpu, iovad);
return 0;
}
static void free_global_cached_iovas(struct iova_domain *iovad);
static struct iova *to_iova(struct rb_node *node)
{
return rb_entry(node, struct iova, node);
}
void
init_iova_domain(struct iova_domain *iovad, unsigned long granule,
unsigned long start_pfn)
{
BUG_ON((granule > PAGE_SIZE) || !is_power_of_2(granule));
spin_lock_init(&iovad->iova_rbtree_lock);
iovad->rbroot = RB_ROOT;
iovad->cached_node = &iovad->anchor.node;
iovad->cached32_node = &iovad->anchor.node;
iovad->granule = granule;
iovad->start_pfn = start_pfn;
iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad));
iovad->max32_alloc_size = iovad->dma_32bit_pfn;
iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR;
rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node);
rb_insert_color(&iovad->anchor.node, &iovad->rbroot);
}
EXPORT_SYMBOL_GPL(init_iova_domain);
static struct rb_node *
__get_cached_rbnode(struct iova_domain *iovad, unsigned long limit_pfn)
{
if (limit_pfn <= iovad->dma_32bit_pfn)
return iovad->cached32_node;
return iovad->cached_node;
}
static void
__cached_rbnode_insert_update(struct iova_domain *iovad, struct iova *new)
{
if (new->pfn_hi < iovad->dma_32bit_pfn)
iovad->cached32_node = &new->node;
else
iovad->cached_node = &new->node;
}
static void
__cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
{
struct iova *cached_iova;
cached_iova = to_iova(iovad->cached32_node);
if (free == cached_iova ||
(free->pfn_hi < iovad->dma_32bit_pfn &&
free->pfn_lo >= cached_iova->pfn_lo))
iovad->cached32_node = rb_next(&free->node);
if (free->pfn_lo < iovad->dma_32bit_pfn)
iovad->max32_alloc_size = iovad->dma_32bit_pfn;
cached_iova = to_iova(iovad->cached_node);
if (free->pfn_lo >= cached_iova->pfn_lo)
iovad->cached_node = rb_next(&free->node);
}
static struct rb_node *iova_find_limit(struct iova_domain *iovad, unsigned long limit_pfn)
{
struct rb_node *node, *next;
if (limit_pfn > iovad->dma_32bit_pfn)
return &iovad->anchor.node;
node = iovad->rbroot.rb_node;
while (to_iova(node)->pfn_hi < limit_pfn)
node = node->rb_right;
search_left:
while (node->rb_left && to_iova(node->rb_left)->pfn_lo >= limit_pfn)
node = node->rb_left;
if (!node->rb_left)
return node;
next = node->rb_left;
while (next->rb_right) {
next = next->rb_right;
if (to_iova(next)->pfn_lo >= limit_pfn) {
node = next;
goto search_left;
}
}
return node;
}
static void
iova_insert_rbtree(struct rb_root *root, struct iova *iova,
struct rb_node *start)
{
struct rb_node **new, *parent = NULL;
new = (start) ? &start : &(root->rb_node);
while (*new) {
struct iova *this = to_iova(*new);
parent = *new;
if (iova->pfn_lo < this->pfn_lo)
new = &((*new)->rb_left);
else if (iova->pfn_lo > this->pfn_lo)
new = &((*new)->rb_right);
else {
WARN_ON(1);
return;
}
}
rb_link_node(&iova->node, parent, new);
rb_insert_color(&iova->node, root);
}
static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
unsigned long size, unsigned long limit_pfn,
struct iova *new, bool size_aligned)
{
struct rb_node *curr, *prev;
struct iova *curr_iova;
unsigned long flags;
unsigned long new_pfn, retry_pfn;
unsigned long align_mask = ~0UL;
unsigned long high_pfn = limit_pfn, low_pfn = iovad->start_pfn;
if (size_aligned)
align_mask <<= fls_long(size - 1);
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
if (limit_pfn <= iovad->dma_32bit_pfn &&
size >= iovad->max32_alloc_size)
goto iova32_full;
curr = __get_cached_rbnode(iovad, limit_pfn);
curr_iova = to_iova(curr);
retry_pfn = curr_iova->pfn_hi;
retry:
do {
high_pfn = min(high_pfn, curr_iova->pfn_lo);
new_pfn = (high_pfn - size) & align_mask;
prev = curr;
curr = rb_prev(curr);
curr_iova = to_iova(curr);
} while (curr && new_pfn <= curr_iova->pfn_hi && new_pfn >= low_pfn);
if (high_pfn < size || new_pfn < low_pfn) {
if (low_pfn == iovad->start_pfn && retry_pfn < limit_pfn) {
high_pfn = limit_pfn;
low_pfn = retry_pfn + 1;
curr = iova_find_limit(iovad, limit_pfn);
curr_iova = to_iova(curr);
goto retry;
}
iovad->max32_alloc_size = size;
goto iova32_full;
}
new->pfn_lo = new_pfn;
new->pfn_hi = new->pfn_lo + size - 1;
iova_insert_rbtree(&iovad->rbroot, new, prev);
__cached_rbnode_insert_update(iovad, new);
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
return 0;
iova32_full:
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
return -ENOMEM;
}
static struct kmem_cache *iova_cache;
static unsigned int iova_cache_users;
static DEFINE_MUTEX(iova_cache_mutex);
static struct iova *alloc_iova_mem(void)
{
return kmem_cache_zalloc(iova_cache, GFP_ATOMIC | __GFP_NOWARN);
}
static void free_iova_mem(struct iova *iova)
{
if (iova->pfn_lo != IOVA_ANCHOR)
kmem_cache_free(iova_cache, iova);
}
int iova_cache_get(void)
{
mutex_lock(&iova_cache_mutex);
if (!iova_cache_users) {
int ret;
ret = cpuhp_setup_state_multi(CPUHP_IOMMU_IOVA_DEAD, "iommu/iova:dead", NULL,
iova_cpuhp_dead);
if (ret) {
mutex_unlock(&iova_cache_mutex);
pr_err("Couldn't register cpuhp handler\n");
return ret;
}
iova_cache = kmem_cache_create(
"iommu_iova", sizeof(struct iova), 0,
SLAB_HWCACHE_ALIGN, NULL);
if (!iova_cache) {
cpuhp_remove_multi_state(CPUHP_IOMMU_IOVA_DEAD);
mutex_unlock(&iova_cache_mutex);
pr_err("Couldn't create iova cache\n");
return -ENOMEM;
}
}
iova_cache_users++;
mutex_unlock(&iova_cache_mutex);
return 0;
}
EXPORT_SYMBOL_GPL(iova_cache_get);
void iova_cache_put(void)
{
mutex_lock(&iova_cache_mutex);
if (WARN_ON(!iova_cache_users)) {
mutex_unlock(&iova_cache_mutex);
return;
}
iova_cache_users--;
if (!iova_cache_users) {
cpuhp_remove_multi_state(CPUHP_IOMMU_IOVA_DEAD);
kmem_cache_destroy(iova_cache);
}
mutex_unlock(&iova_cache_mutex);
}
EXPORT_SYMBOL_GPL(iova_cache_put);
struct iova *
alloc_iova(struct iova_domain *iovad, unsigned long size,
unsigned long limit_pfn,
bool size_aligned)
{
struct iova *new_iova;
int ret;
new_iova = alloc_iova_mem();
if (!new_iova)
return NULL;
ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn + 1,
new_iova, size_aligned);
if (ret) {
free_iova_mem(new_iova);
return NULL;
}
return new_iova;
}
EXPORT_SYMBOL_GPL(alloc_iova);
static struct iova *
private_find_iova(struct iova_domain *iovad, unsigned long pfn)
{
struct rb_node *node = iovad->rbroot.rb_node;
assert_spin_locked(&iovad->iova_rbtree_lock);
while (node) {
struct iova *iova = to_iova(node);
if (pfn < iova->pfn_lo)
node = node->rb_left;
else if (pfn > iova->pfn_hi)
node = node->rb_right;
else
return iova;
}
return NULL;
}
static void remove_iova(struct iova_domain *iovad, struct iova *iova)
{
assert_spin_locked(&iovad->iova_rbtree_lock);
__cached_rbnode_delete_update(iovad, iova);
rb_erase(&iova->node, &iovad->rbroot);
}
struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
{
unsigned long flags;
struct iova *iova;
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
iova = private_find_iova(iovad, pfn);
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
return iova;
}
EXPORT_SYMBOL_GPL(find_iova);
void
__free_iova(struct iova_domain *iovad, struct iova *iova)
{
unsigned long flags;
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
remove_iova(iovad, iova);
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
free_iova_mem(iova);
}
EXPORT_SYMBOL_GPL(__free_iova);
void
free_iova(struct iova_domain *iovad, unsigned long pfn)
{
unsigned long flags;
struct iova *iova;
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
iova = private_find_iova(iovad, pfn);
if (!iova) {
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
return;
}
remove_iova(iovad, iova);
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
free_iova_mem(iova);
}
EXPORT_SYMBOL_GPL(free_iova);
unsigned long
alloc_iova_fast(struct iova_domain *iovad, unsigned long size,
unsigned long limit_pfn, bool flush_rcache)
{
unsigned long iova_pfn;
struct iova *new_iova;
if (size < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
size = roundup_pow_of_two(size);
iova_pfn = iova_rcache_get(iovad, size, limit_pfn + 1);
if (iova_pfn)
return iova_pfn;
retry:
new_iova = alloc_iova(iovad, size, limit_pfn, true);
if (!new_iova) {
unsigned int cpu;
if (!flush_rcache)
return 0;
flush_rcache = false;
for_each_online_cpu(cpu)
free_cpu_cached_iovas(cpu, iovad);
free_global_cached_iovas(iovad);
goto retry;
}
return new_iova->pfn_lo;
}
EXPORT_SYMBOL_GPL(alloc_iova_fast);
void
free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size)
{
if (iova_rcache_insert(iovad, pfn, size))
return;
free_iova(iovad, pfn);
}
EXPORT_SYMBOL_GPL(free_iova_fast);
static void iova_domain_free_rcaches(struct iova_domain *iovad)
{
cpuhp_state_remove_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
&iovad->cpuhp_dead);
free_iova_rcaches(iovad);
}
void put_iova_domain(struct iova_domain *iovad)
{
struct iova *iova, *tmp;
if (iovad->rcaches)
iova_domain_free_rcaches(iovad);
rbtree_postorder_for_each_entry_safe(iova, tmp, &iovad->rbroot, node)
free_iova_mem(iova);
}
EXPORT_SYMBOL_GPL(put_iova_domain);
static int
__is_range_overlap(struct rb_node *node,
unsigned long pfn_lo, unsigned long pfn_hi)
{
struct iova *iova = to_iova(node);
if ((pfn_lo <= iova->pfn_hi) && (pfn_hi >= iova->pfn_lo))
return 1;
return 0;
}
static inline struct iova *
alloc_and_init_iova(unsigned long pfn_lo, unsigned long pfn_hi)
{
struct iova *iova;
iova = alloc_iova_mem();
if (iova) {
iova->pfn_lo = pfn_lo;
iova->pfn_hi = pfn_hi;
}
return iova;
}
static struct iova *
__insert_new_range(struct iova_domain *iovad,
unsigned long pfn_lo, unsigned long pfn_hi)
{
struct iova *iova;
iova = alloc_and_init_iova(pfn_lo, pfn_hi);
if (iova)
iova_insert_rbtree(&iovad->rbroot, iova, NULL);
return iova;
}
static void
__adjust_overlap_range(struct iova *iova,
unsigned long *pfn_lo, unsigned long *pfn_hi)
{
if (*pfn_lo < iova->pfn_lo)
iova->pfn_lo = *pfn_lo;
if (*pfn_hi > iova->pfn_hi)
*pfn_lo = iova->pfn_hi + 1;
}
struct iova *
reserve_iova(struct iova_domain *iovad,
unsigned long pfn_lo, unsigned long pfn_hi)
{
struct rb_node *node;
unsigned long flags;
struct iova *iova;
unsigned int overlap = 0;
if (WARN_ON((pfn_hi | pfn_lo) > (ULLONG_MAX >> iova_shift(iovad))))
return NULL;
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
iova = to_iova(node);
__adjust_overlap_range(iova, &pfn_lo, &pfn_hi);
if ((pfn_lo >= iova->pfn_lo) &&
(pfn_hi <= iova->pfn_hi))
goto finish;
overlap = 1;
} else if (overlap)
break;
}
iova = __insert_new_range(iovad, pfn_lo, pfn_hi);
finish:
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
return iova;
}
EXPORT_SYMBOL_GPL(reserve_iova);
#define IOVA_MAG_SIZE 127
#define MAX_GLOBAL_MAGS 32 /* magazines per bin */
struct iova_magazine {
unsigned long size;
unsigned long pfns[IOVA_MAG_SIZE];
};
struct iova_cpu_rcache {
spinlock_t lock;
struct iova_magazine *loaded;
struct iova_magazine *prev;
};
struct iova_rcache {
spinlock_t lock;
unsigned long depot_size;
struct iova_magazine *depot[MAX_GLOBAL_MAGS];
struct iova_cpu_rcache __percpu *cpu_rcaches;
};
static struct iova_magazine *iova_magazine_alloc(gfp_t flags)
{
struct iova_magazine *mag;
mag = kmalloc(sizeof(*mag), flags);
if (mag)
mag->size = 0;
return mag;
}
static void iova_magazine_free(struct iova_magazine *mag)
{
kfree(mag);
}
static void
iova_magazine_free_pfns(struct iova_magazine *mag, struct iova_domain *iovad)
{
unsigned long flags;
int i;
spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
for (i = 0 ; i < mag->size; ++i) {
struct iova *iova = private_find_iova(iovad, mag->pfns[i]);
if (WARN_ON(!iova))
continue;
remove_iova(iovad, iova);
free_iova_mem(iova);
}
spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
mag->size = 0;
}
static bool iova_magazine_full(struct iova_magazine *mag)
{
return mag->size == IOVA_MAG_SIZE;
}
static bool iova_magazine_empty(struct iova_magazine *mag)
{
return mag->size == 0;
}
static unsigned long iova_magazine_pop(struct iova_magazine *mag,
unsigned long limit_pfn)
{
int i;
unsigned long pfn;
for (i = mag->size - 1; mag->pfns[i] > limit_pfn; i--)
if (i == 0)
return 0;
pfn = mag->pfns[i];
mag->pfns[i] = mag->pfns[--mag->size];
return pfn;
}
static void iova_magazine_push(struct iova_magazine *mag, unsigned long pfn)
{
mag->pfns[mag->size++] = pfn;
}
int iova_domain_init_rcaches(struct iova_domain *iovad)
{
unsigned int cpu;
int i, ret;
iovad->rcaches = kcalloc(IOVA_RANGE_CACHE_MAX_SIZE,
sizeof(struct iova_rcache),
GFP_KERNEL);
if (!iovad->rcaches)
return -ENOMEM;
for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
struct iova_cpu_rcache *cpu_rcache;
struct iova_rcache *rcache;
rcache = &iovad->rcaches[i];
spin_lock_init(&rcache->lock);
rcache->depot_size = 0;
rcache->cpu_rcaches = __alloc_percpu(sizeof(*cpu_rcache),
cache_line_size());
if (!rcache->cpu_rcaches) {
ret = -ENOMEM;
goto out_err;
}
for_each_possible_cpu(cpu) {
cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
spin_lock_init(&cpu_rcache->lock);
cpu_rcache->loaded = iova_magazine_alloc(GFP_KERNEL);
cpu_rcache->prev = iova_magazine_alloc(GFP_KERNEL);
if (!cpu_rcache->loaded || !cpu_rcache->prev) {
ret = -ENOMEM;
goto out_err;
}
}
}
ret = cpuhp_state_add_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
&iovad->cpuhp_dead);
if (ret)
goto out_err;
return 0;
out_err:
free_iova_rcaches(iovad);
return ret;
}
EXPORT_SYMBOL_GPL(iova_domain_init_rcaches);
static bool __iova_rcache_insert(struct iova_domain *iovad,
struct iova_rcache *rcache,
unsigned long iova_pfn)
{
struct iova_magazine *mag_to_free = NULL;
struct iova_cpu_rcache *cpu_rcache;
bool can_insert = false;
unsigned long flags;
cpu_rcache = raw_cpu_ptr(rcache->cpu_rcaches);
spin_lock_irqsave(&cpu_rcache->lock, flags);
if (!iova_magazine_full(cpu_rcache->loaded)) {
can_insert = true;
} else if (!iova_magazine_full(cpu_rcache->prev)) {
swap(cpu_rcache->prev, cpu_rcache->loaded);
can_insert = true;
} else {
struct iova_magazine *new_mag = iova_magazine_alloc(GFP_ATOMIC);
if (new_mag) {
spin_lock(&rcache->lock);
if (rcache->depot_size < MAX_GLOBAL_MAGS) {
rcache->depot[rcache->depot_size++] =
cpu_rcache->loaded;
} else {
mag_to_free = cpu_rcache->loaded;
}
spin_unlock(&rcache->lock);
cpu_rcache->loaded = new_mag;
can_insert = true;
}
}
if (can_insert)
iova_magazine_push(cpu_rcache->loaded, iova_pfn);
spin_unlock_irqrestore(&cpu_rcache->lock, flags);
if (mag_to_free) {
iova_magazine_free_pfns(mag_to_free, iovad);
iova_magazine_free(mag_to_free);
}
return can_insert;
}
static bool iova_rcache_insert(struct iova_domain *iovad, unsigned long pfn,
unsigned long size)
{
unsigned int log_size = order_base_2(size);
if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
return false;
return __iova_rcache_insert(iovad, &iovad->rcaches[log_size], pfn);
}
static unsigned long __iova_rcache_get(struct iova_rcache *rcache,
unsigned long limit_pfn)
{
struct iova_cpu_rcache *cpu_rcache;
unsigned long iova_pfn = 0;
bool has_pfn = false;
unsigned long flags;
cpu_rcache = raw_cpu_ptr(rcache->cpu_rcaches);
spin_lock_irqsave(&cpu_rcache->lock, flags);
if (!iova_magazine_empty(cpu_rcache->loaded)) {
has_pfn = true;
} else if (!iova_magazine_empty(cpu_rcache->prev)) {
swap(cpu_rcache->prev, cpu_rcache->loaded);
has_pfn = true;
} else {
spin_lock(&rcache->lock);
if (rcache->depot_size > 0) {
iova_magazine_free(cpu_rcache->loaded);
cpu_rcache->loaded = rcache->depot[--rcache->depot_size];
has_pfn = true;
}
spin_unlock(&rcache->lock);
}
if (has_pfn)
iova_pfn = iova_magazine_pop(cpu_rcache->loaded, limit_pfn);
spin_unlock_irqrestore(&cpu_rcache->lock, flags);
return iova_pfn;
}
static unsigned long iova_rcache_get(struct iova_domain *iovad,
unsigned long size,
unsigned long limit_pfn)
{
unsigned int log_size = order_base_2(size);
if (log_size >= IOVA_RANGE_CACHE_MAX_SIZE)
return 0;
return __iova_rcache_get(&iovad->rcaches[log_size], limit_pfn - size);
}
static void free_iova_rcaches(struct iova_domain *iovad)
{
struct iova_rcache *rcache;
struct iova_cpu_rcache *cpu_rcache;
unsigned int cpu;
int i, j;
for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
rcache = &iovad->rcaches[i];
if (!rcache->cpu_rcaches)
break;
for_each_possible_cpu(cpu) {
cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
iova_magazine_free(cpu_rcache->loaded);
iova_magazine_free(cpu_rcache->prev);
}
free_percpu(rcache->cpu_rcaches);
for (j = 0; j < rcache->depot_size; ++j)
iova_magazine_free(rcache->depot[j]);
}
kfree(iovad->rcaches);
iovad->rcaches = NULL;
}
static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
{
struct iova_cpu_rcache *cpu_rcache;
struct iova_rcache *rcache;
unsigned long flags;
int i;
for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
rcache = &iovad->rcaches[i];
cpu_rcache = per_cpu_ptr(rcache->cpu_rcaches, cpu);
spin_lock_irqsave(&cpu_rcache->lock, flags);
iova_magazine_free_pfns(cpu_rcache->loaded, iovad);
iova_magazine_free_pfns(cpu_rcache->prev, iovad);
spin_unlock_irqrestore(&cpu_rcache->lock, flags);
}
}
static void free_global_cached_iovas(struct iova_domain *iovad)
{
struct iova_rcache *rcache;
unsigned long flags;
int i, j;
for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
rcache = &iovad->rcaches[i];
spin_lock_irqsave(&rcache->lock, flags);
for (j = 0; j < rcache->depot_size; ++j) {
iova_magazine_free_pfns(rcache->depot[j], iovad);
iova_magazine_free(rcache->depot[j]);
}
rcache->depot_size = 0;
spin_unlock_irqrestore(&rcache->lock, flags);
}
}
MODULE_AUTHOR("Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>");
MODULE_LICENSE("GPL"