#define pr_fmt(fmt) "software IO TLB: " fmt
#include <linux/cache.h>
#include <linux/cc_platform.h>
#include <linux/ctype.h>
#include <linux/debugfs.h>
#include <linux/dma-direct.h>
#include <linux/dma-map-ops.h>
#include <linux/export.h>
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/io.h>
#include <linux/iommu-helper.h>
#include <linux/init.h>
#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/pfn.h>
#include <linux/rculist.h>
#include <linux/scatterlist.h>
#include <linux/set_memory.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/swiotlb.h>
#include <linux/types.h>
#ifdef CONFIG_DMA_RESTRICTED_POOL
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/of_reserved_mem.h>
#include <linux/slab.h>
#endif
#define CREATE_TRACE_POINTS
#include <trace/events/swiotlb.h>
#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
struct io_tlb_slot {
phys_addr_t orig_addr;
size_t alloc_size;
unsigned int list;
};
static bool swiotlb_force_bounce;
static bool swiotlb_force_disable;
#ifdef CONFIG_SWIOTLB_DYNAMIC
static void swiotlb_dyn_alloc(struct work_struct *work);
static struct io_tlb_mem io_tlb_default_mem = {
.lock = __SPIN_LOCK_UNLOCKED(io_tlb_default_mem.lock),
.pools = LIST_HEAD_INIT(io_tlb_default_mem.pools),
.dyn_alloc = __WORK_INITIALIZER(io_tlb_default_mem.dyn_alloc,
swiotlb_dyn_alloc),
};
#else /* !CONFIG_SWIOTLB_DYNAMIC */
static struct io_tlb_mem io_tlb_default_mem;
#endif /* CONFIG_SWIOTLB_DYNAMIC */
static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT;
static unsigned long default_nareas;
struct io_tlb_area {
unsigned long used;
unsigned int index;
spinlock_t lock;
};
static bool round_up_default_nslabs(void)
{
if (!default_nareas)
return false;
if (default_nslabs < IO_TLB_SEGSIZE * default_nareas)
default_nslabs = IO_TLB_SEGSIZE * default_nareas;
else if (is_power_of_2(default_nslabs))
return false;
default_nslabs = roundup_pow_of_two(default_nslabs);
return true;
}
static void swiotlb_adjust_nareas(unsigned int nareas)
{
if (!nareas)
nareas = 1;
else if (!is_power_of_2(nareas))
nareas = roundup_pow_of_two(nareas);
default_nareas = nareas;
pr_info("area num %d.\n", nareas);
if (round_up_default_nslabs())
pr_info("SWIOTLB bounce buffer size roundup to %luMB",
(default_nslabs << IO_TLB_SHIFT) >> 20);
}
static unsigned int limit_nareas(unsigned int nareas, unsigned long nslots)
{
if (nslots < nareas * IO_TLB_SEGSIZE)
return nslots / IO_TLB_SEGSIZE;
return nareas;
}
static int __init
setup_io_tlb_npages(char *str)
{
if (isdigit(*str)) {
default_nslabs =
ALIGN(simple_strtoul(str, &str, 0), IO_TLB_SEGSIZE);
}
if (*str == ',')
++str;
if (isdigit(*str))
swiotlb_adjust_nareas(simple_strtoul(str, &str, 0));
if (*str == ',')
++str;
if (!strcmp(str, "force"))
swiotlb_force_bounce = true;
else if (!strcmp(str, "noforce"))
swiotlb_force_disable = true;
return 0;
}
early_param("swiotlb", setup_io_tlb_npages);
unsigned long swiotlb_size_or_default(void)
{
return default_nslabs << IO_TLB_SHIFT;
}
void __init swiotlb_adjust_size(unsigned long size)
{
if (default_nslabs != IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT)
return;
size = ALIGN(size, IO_TLB_SIZE);
default_nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
if (round_up_default_nslabs())
size = default_nslabs << IO_TLB_SHIFT;
pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20);
}
void swiotlb_print_info(void)
{
struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
if (!mem->nslabs) {
pr_warn("No low mem\n");
return;
}
pr_info("mapped [mem %pa-%pa] (%luMB)\n", &mem->start, &mem->end,
(mem->nslabs << IO_TLB_SHIFT) >> 20);
}
static inline unsigned long io_tlb_offset(unsigned long val)
{
return val & (IO_TLB_SEGSIZE - 1);
}
static inline unsigned long nr_slots(u64 val)
{
return DIV_ROUND_UP(val, IO_TLB_SIZE);
}
void __init swiotlb_update_mem_attributes(void)
{
struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
unsigned long bytes;
if (!mem->nslabs || mem->late_alloc)
return;
bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT);
set_memory_decrypted((unsigned long)mem->vaddr, bytes >> PAGE_SHIFT);
}
static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start,
unsigned long nslabs, bool late_alloc, unsigned int nareas)
{
void *vaddr = phys_to_virt(start);
unsigned long bytes = nslabs << IO_TLB_SHIFT, i;
mem->nslabs = nslabs;
mem->start = start;
mem->end = mem->start + bytes;
mem->late_alloc = late_alloc;
mem->nareas = nareas;
mem->area_nslabs = nslabs / mem->nareas;
for (i = 0; i < mem->nareas; i++) {
spin_lock_init(&mem->areas[i].lock);
mem->areas[i].index = 0;
mem->areas[i].used = 0;
}
for (i = 0; i < mem->nslabs; i++) {
mem->slots[i].list = IO_TLB_SEGSIZE - io_tlb_offset(i);
mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
mem->slots[i].alloc_size = 0;
}
memset(vaddr, 0, bytes);
mem->vaddr = vaddr;
return;
}
static void add_mem_pool(struct io_tlb_mem *mem, struct io_tlb_pool *pool)
{
#ifdef CONFIG_SWIOTLB_DYNAMIC
spin_lock(&mem->lock);
list_add_rcu(&pool->node, &mem->pools);
mem->nslabs += pool->nslabs;
spin_unlock(&mem->lock);
#else
mem->nslabs = pool->nslabs;
#endif
}
static void __init *swiotlb_memblock_alloc(unsigned long nslabs,
unsigned int flags,
int (*remap)(void *tlb, unsigned long nslabs))
{
size_t bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT);
void *tlb;
if (flags & SWIOTLB_ANY)
tlb = memblock_alloc(bytes, PAGE_SIZE);
else
tlb = memblock_alloc_low(bytes, PAGE_SIZE);
if (!tlb) {
pr_warn("%s: Failed to allocate %zu bytes tlb structure\n",
__func__, bytes);
return NULL;
}
if (remap && remap(tlb, nslabs) < 0) {
memblock_free(tlb, PAGE_ALIGN(bytes));
pr_warn("%s: Failed to remap %zu bytes\n", __func__, bytes);
return NULL;
}
return tlb;
}
void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags,
int (*remap)(void *tlb, unsigned long nslabs))
{
struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
unsigned long nslabs;
unsigned int nareas;
size_t alloc_size;
void *tlb;
if (!addressing_limit && !swiotlb_force_bounce)
return;
if (swiotlb_force_disable)
return;
io_tlb_default_mem.force_bounce =
swiotlb_force_bounce || (flags & SWIOTLB_FORCE);
#ifdef CONFIG_SWIOTLB_DYNAMIC
if (!remap)
io_tlb_default_mem.can_grow = true;
if (flags & SWIOTLB_ANY)
io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1);
else
io_tlb_default_mem.phys_limit = ARCH_LOW_ADDRESS_LIMIT;
#endif
if (!default_nareas)
swiotlb_adjust_nareas(num_possible_cpus());
nslabs = default_nslabs;
nareas = limit_nareas(default_nareas, nslabs);
while ((tlb = swiotlb_memblock_alloc(nslabs, flags, remap)) == NULL) {
if (nslabs <= IO_TLB_MIN_SLABS)
return;
nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
nareas = limit_nareas(nareas, nslabs);
}
if (default_nslabs != nslabs) {
pr_info("SWIOTLB bounce buffer size adjusted %lu -> %lu slabs",
default_nslabs, nslabs);
default_nslabs = nslabs;
}
alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs));
mem->slots = memblock_alloc(alloc_size, PAGE_SIZE);
if (!mem->slots) {
pr_warn("%s: Failed to allocate %zu bytes align=0x%lx\n",
__func__, alloc_size, PAGE_SIZE);
return;
}
mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area),
nareas), SMP_CACHE_BYTES);
if (!mem->areas) {
pr_warn("%s: Failed to allocate mem->areas.\n", __func__);
return;
}
swiotlb_init_io_tlb_pool(mem, __pa(tlb), nslabs, false, nareas);
add_mem_pool(&io_tlb_default_mem, mem);
if (flags & SWIOTLB_VERBOSE)
swiotlb_print_info();
}
void __init swiotlb_init(bool addressing_limit, unsigned int flags)
{
swiotlb_init_remap(addressing_limit, flags, NULL);
}
int swiotlb_init_late(size_t size, gfp_t gfp_mask,
int (*remap)(void *tlb, unsigned long nslabs))
{
struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE);
unsigned int nareas;
unsigned char *vstart = NULL;
unsigned int order, area_order;
bool retried = false;
int rc = 0;
if (io_tlb_default_mem.nslabs)
return 0;
if (swiotlb_force_disable)
return 0;
io_tlb_default_mem.force_bounce = swiotlb_force_bounce;
#ifdef CONFIG_SWIOTLB_DYNAMIC
if (!remap)
io_tlb_default_mem.can_grow = true;
if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp_mask & __GFP_DMA))
io_tlb_default_mem.phys_limit = DMA_BIT_MASK(zone_dma_bits);
else if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp_mask & __GFP_DMA32))
io_tlb_default_mem.phys_limit = DMA_BIT_MASK(32);
else
io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1);
#endif
if (!default_nareas)
swiotlb_adjust_nareas(num_possible_cpus());
retry:
order = get_order(nslabs << IO_TLB_SHIFT);
nslabs = SLABS_PER_PAGE << order;
while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
vstart = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN,
order);
if (vstart)
break;
order--;
nslabs = SLABS_PER_PAGE << order;
retried = true;
}
if (!vstart)
return -ENOMEM;
if (remap)
rc = remap(vstart, nslabs);
if (rc) {
free_pages((unsigned long)vstart, order);
nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
if (nslabs < IO_TLB_MIN_SLABS)
return rc;
retried = true;
goto retry;
}
if (retried) {
pr_warn("only able to allocate %ld MB\n",
(PAGE_SIZE << order) >> 20);
}
nareas = limit_nareas(default_nareas, nslabs);
area_order = get_order(array_size(sizeof(*mem->areas), nareas));
mem->areas = (struct io_tlb_area *)
__get_free_pages(GFP_KERNEL | __GFP_ZERO, area_order);
if (!mem->areas)
goto error_area;
mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
get_order(array_size(sizeof(*mem->slots), nslabs)));
if (!mem->slots)
goto error_slots;
set_memory_decrypted((unsigned long)vstart,
(nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT);
swiotlb_init_io_tlb_pool(mem, virt_to_phys(vstart), nslabs, true,
nareas);
add_mem_pool(&io_tlb_default_mem, mem);
swiotlb_print_info();
return 0;
error_slots:
free_pages((unsigned long)mem->areas, area_order);
error_area:
free_pages((unsigned long)vstart, order);
return -ENOMEM;
}
void __init swiotlb_exit(void)
{
struct io_tlb_pool *mem = &io_tlb_default_mem.defpool;
unsigned long tbl_vaddr;
size_t tbl_size, slots_size;
unsigned int area_order;
if (swiotlb_force_bounce)
return;
if (!mem->nslabs)
return;
pr_info("tearing down default memory pool\n");
tbl_vaddr = (unsigned long)phys_to_virt(mem->start);
tbl_size = PAGE_ALIGN(mem->end - mem->start);
slots_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), mem->nslabs));
set_memory_encrypted(tbl_vaddr, tbl_size >> PAGE_SHIFT);
if (mem->late_alloc) {
area_order = get_order(array_size(sizeof(*mem->areas),
mem->nareas));
free_pages((unsigned long)mem->areas, area_order);
free_pages(tbl_vaddr, get_order(tbl_size));
free_pages((unsigned long)mem->slots, get_order(slots_size));
} else {
memblock_free_late(__pa(mem->areas),
array_size(sizeof(*mem->areas), mem->nareas));
memblock_free_late(mem->start, tbl_size);
memblock_free_late(__pa(mem->slots), slots_size);
}
memset(mem, 0, sizeof(*mem));
}
#ifdef CONFIG_SWIOTLB_DYNAMIC
static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes)
{
unsigned int order = get_order(bytes);
struct page *page;
void *vaddr;
page = alloc_pages(gfp, order);
if (!page)
return NULL;
vaddr = page_address(page);
if (set_memory_decrypted((unsigned long)vaddr, PFN_UP(bytes)))
goto error;
return page;
error:
__free_pages(page, order);
return NULL;
}
static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes,
u64 phys_limit, gfp_t gfp)
{
struct page *page;
if (!gfpflags_allow_blocking(gfp) && dev && force_dma_unencrypted(dev)) {
void *vaddr;
if (!IS_ENABLED(CONFIG_DMA_COHERENT_POOL))
return NULL;
return dma_alloc_from_pool(dev, bytes, &vaddr, gfp,
dma_coherent_ok);
}
gfp &= ~GFP_ZONEMASK;
if (phys_limit <= DMA_BIT_MASK(zone_dma_bits))
gfp |= __GFP_DMA;
else if (phys_limit <= DMA_BIT_MASK(32))
gfp |= __GFP_DMA32;
while ((page = alloc_dma_pages(gfp, bytes)) &&
page_to_phys(page) + bytes - 1 > phys_limit) {
__free_pages(page, get_order(bytes));
if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
phys_limit < DMA_BIT_MASK(64) &&
!(gfp & (__GFP_DMA32 | __GFP_DMA)))
gfp |= __GFP_DMA32;
else if (IS_ENABLED(CONFIG_ZONE_DMA) &&
!(gfp & __GFP_DMA))
gfp = (gfp & ~__GFP_DMA32) | __GFP_DMA;
else
return NULL;
}
return page;
}
static void swiotlb_free_tlb(void *vaddr, size_t bytes)
{
if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
dma_free_from_pool(NULL, vaddr, bytes))
return;
if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes)))
__free_pages(virt_to_page(vaddr), get_order(bytes));
}
static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev,
unsigned long minslabs, unsigned long nslabs,
unsigned int nareas, u64 phys_limit, gfp_t gfp)
{
struct io_tlb_pool *pool;
unsigned int slot_order;
struct page *tlb;
size_t pool_size;
size_t tlb_size;
if (nslabs > SLABS_PER_PAGE << MAX_ORDER) {
nslabs = SLABS_PER_PAGE << MAX_ORDER;
nareas = limit_nareas(nareas, nslabs);
}
pool_size = sizeof(*pool) + array_size(sizeof(*pool->areas), nareas);
pool = kzalloc(pool_size, gfp);
if (!pool)
goto error;
pool->areas = (void *)pool + sizeof(*pool);
tlb_size = nslabs << IO_TLB_SHIFT;
while (!(tlb = swiotlb_alloc_tlb(dev, tlb_size, phys_limit, gfp))) {
if (nslabs <= minslabs)
goto error_tlb;
nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE);
nareas = limit_nareas(nareas, nslabs);
tlb_size = nslabs << IO_TLB_SHIFT;
}
slot_order = get_order(array_size(sizeof(*pool->slots), nslabs));
pool->slots = (struct io_tlb_slot *)
__get_free_pages(gfp, slot_order);
if (!pool->slots)
goto error_slots;
swiotlb_init_io_tlb_pool(pool, page_to_phys(tlb), nslabs, true, nareas);
return pool;
error_slots:
swiotlb_free_tlb(page_address(tlb), tlb_size);
error_tlb:
kfree(pool);
error:
return NULL;
}
static void swiotlb_dyn_alloc(struct work_struct *work)
{
struct io_tlb_mem *mem =
container_of(work, struct io_tlb_mem, dyn_alloc);
struct io_tlb_pool *pool;
pool = swiotlb_alloc_pool(NULL, IO_TLB_MIN_SLABS, default_nslabs,
default_nareas, mem->phys_limit, GFP_KERNEL);
if (!pool) {
pr_warn_ratelimited("Failed to allocate new pool");
return;
}
add_mem_pool(mem, pool);
}
static void swiotlb_dyn_free(struct rcu_head *rcu)
{
struct io_tlb_pool *pool = container_of(rcu, struct io_tlb_pool, rcu);
size_t slots_size = array_size(sizeof(*pool->slots), pool->nslabs);
size_t tlb_size = pool->end - pool->start;
free_pages((unsigned long)pool->slots, get_order(slots_size));
swiotlb_free_tlb(pool->vaddr, tlb_size);
kfree(pool);
}
struct io_tlb_pool *swiotlb_find_pool(struct device *dev, phys_addr_t paddr)
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
struct io_tlb_pool *pool;
rcu_read_lock();
list_for_each_entry_rcu(pool, &mem->pools, node) {
if (paddr >= pool->start && paddr < pool->end)
goto out;
}
list_for_each_entry_rcu(pool, &dev->dma_io_tlb_pools, node) {
if (paddr >= pool->start && paddr < pool->end)
goto out;
}
pool = NULL;
out:
rcu_read_unlock();
return pool;
}
static void swiotlb_del_pool(struct device *dev, struct io_tlb_pool *pool)
{
unsigned long flags;
spin_lock_irqsave(&dev->dma_io_tlb_lock, flags);
list_del_rcu(&pool->node);
spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags);
call_rcu(&pool->rcu, swiotlb_dyn_free);
}
#endif /* CONFIG_SWIOTLB_DYNAMIC */
void swiotlb_dev_init(struct device *dev)
{
dev->dma_io_tlb_mem = &io_tlb_default_mem;
#ifdef CONFIG_SWIOTLB_DYNAMIC
INIT_LIST_HEAD(&dev->dma_io_tlb_pools);
spin_lock_init(&dev->dma_io_tlb_lock);
dev->dma_uses_io_tlb = false;
#endif
}
static unsigned int swiotlb_align_offset(struct device *dev, u64 addr)
{
return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1);
}
static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size,
enum dma_data_direction dir)
{
struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr);
int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT;
phys_addr_t orig_addr = mem->slots[index].orig_addr;
size_t alloc_size = mem->slots[index].alloc_size;
unsigned long pfn = PFN_DOWN(orig_addr);
unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start;
unsigned int tlb_offset, orig_addr_offset;
if (orig_addr == INVALID_PHYS_ADDR)
return;
tlb_offset = tlb_addr & (IO_TLB_SIZE - 1);
orig_addr_offset = swiotlb_align_offset(dev, orig_addr);
if (tlb_offset < orig_addr_offset) {
dev_WARN_ONCE(dev, 1,
"Access before mapping start detected. orig offset %u, requested offset %u.\n",
orig_addr_offset, tlb_offset);
return;
}
tlb_offset -= orig_addr_offset;
if (tlb_offset > alloc_size) {
dev_WARN_ONCE(dev, 1,
"Buffer overflow detected. Allocation size: %zu. Mapping size: %zu+%u.\n",
alloc_size, size, tlb_offset);
return;
}
orig_addr += tlb_offset;
alloc_size -= tlb_offset;
if (size > alloc_size) {
dev_WARN_ONCE(dev, 1,
"Buffer overflow detected. Allocation size: %zu. Mapping size: %zu.\n",
alloc_size, size);
size = alloc_size;
}
if (PageHighMem(pfn_to_page(pfn))) {
unsigned int offset = orig_addr & ~PAGE_MASK;
struct page *page;
unsigned int sz = 0;
unsigned long flags;
while (size) {
sz = min_t(size_t, PAGE_SIZE - offset, size);
local_irq_save(flags);
page = pfn_to_page(pfn);
if (dir == DMA_TO_DEVICE)
memcpy_from_page(vaddr, page, offset, sz);
else
memcpy_to_page(page, offset, vaddr, sz);
local_irq_restore(flags);
size -= sz;
pfn++;
vaddr += sz;
offset = 0;
}
} else if (dir == DMA_TO_DEVICE) {
memcpy(vaddr, phys_to_virt(orig_addr), size);
} else {
memcpy(phys_to_virt(orig_addr), vaddr, size);
}
}
static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx)
{
return start + (idx << IO_TLB_SHIFT);
}
static inline unsigned long get_max_slots(unsigned long boundary_mask)
{
return (boundary_mask >> IO_TLB_SHIFT) + 1;
}
static unsigned int wrap_area_index(struct io_tlb_pool *mem, unsigned int index)
{
if (index >= mem->area_nslabs)
return 0;
return index;
}
#ifdef CONFIG_DEBUG_FS
static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots)
{
unsigned long old_hiwater, new_used;
new_used = atomic_long_add_return(nslots, &mem->total_used);
old_hiwater = atomic_long_read(&mem->used_hiwater);
do {
if (new_used <= old_hiwater)
break;
} while (!atomic_long_try_cmpxchg(&mem->used_hiwater,
&old_hiwater, new_used));
}
static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
{
atomic_long_sub(nslots, &mem->total_used);
}
#else /* !CONFIG_DEBUG_FS */
static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots)
{
}
static void dec_used(struct io_tlb_mem *mem, unsigned int nslots)
{
}
#endif /* CONFIG_DEBUG_FS */
static int swiotlb_area_find_slots(struct device *dev, struct io_tlb_pool *pool,
int area_index, phys_addr_t orig_addr, size_t alloc_size,
unsigned int alloc_align_mask)
{
struct io_tlb_area *area = pool->areas + area_index;
unsigned long boundary_mask = dma_get_seg_boundary(dev);
dma_addr_t tbl_dma_addr =
phys_to_dma_unencrypted(dev, pool->start) & boundary_mask;
unsigned long max_slots = get_max_slots(boundary_mask);
unsigned int iotlb_align_mask =
dma_get_min_align_mask(dev) | alloc_align_mask;
unsigned int nslots = nr_slots(alloc_size), stride;
unsigned int offset = swiotlb_align_offset(dev, orig_addr);
unsigned int index, slots_checked, count = 0, i;
unsigned long flags;
unsigned int slot_base;
unsigned int slot_index;
BUG_ON(!nslots);
BUG_ON(area_index >= pool->nareas);
if (alloc_size >= PAGE_SIZE)
iotlb_align_mask |= ~PAGE_MASK;
iotlb_align_mask &= ~(IO_TLB_SIZE - 1);
stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1;
spin_lock_irqsave(&area->lock, flags);
if (unlikely(nslots > pool->area_nslabs - area->used))
goto not_found;
slot_base = area_index * pool->area_nslabs;
index = area->index;
for (slots_checked = 0; slots_checked < pool->area_nslabs; ) {
slot_index = slot_base + index;
if (orig_addr &&
(slot_addr(tbl_dma_addr, slot_index) &
iotlb_align_mask) != (orig_addr & iotlb_align_mask)) {
index = wrap_area_index(pool, index + 1);
slots_checked++;
continue;
}
if (!iommu_is_span_boundary(slot_index, nslots,
nr_slots(tbl_dma_addr),
max_slots)) {
if (pool->slots[slot_index].list >= nslots)
goto found;
}
index = wrap_area_index(pool, index + stride);
slots_checked += stride;
}
not_found:
spin_unlock_irqrestore(&area->lock, flags);
return -1;
found:
for (i = slot_index; i < slot_index + nslots; i++) {
pool->slots[i].list = 0;
pool->slots[i].alloc_size = alloc_size - (offset +
((i - slot_index) << IO_TLB_SHIFT));
}
for (i = slot_index - 1;
io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 &&
pool->slots[i].list; i--)
pool->slots[i].list = ++count;
area->index = wrap_area_index(pool, index + nslots);
area->used += nslots;
spin_unlock_irqrestore(&area->lock, flags);
inc_used_and_hiwater(dev->dma_io_tlb_mem, nslots);
return slot_index;
}
static int swiotlb_pool_find_slots(struct device *dev, struct io_tlb_pool *pool,
phys_addr_t orig_addr, size_t alloc_size,
unsigned int alloc_align_mask)
{
int start = raw_smp_processor_id() & (pool->nareas - 1);
int i = start, index;
do {
index = swiotlb_area_find_slots(dev, pool, i, orig_addr,
alloc_size, alloc_align_mask);
if (index >= 0)
return index;
if (++i >= pool->nareas)
i = 0;
} while (i != start);
return -1;
}
#ifdef CONFIG_SWIOTLB_DYNAMIC
static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
size_t alloc_size, unsigned int alloc_align_mask,
struct io_tlb_pool **retpool)
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
struct io_tlb_pool *pool;
unsigned long nslabs;
unsigned long flags;
u64 phys_limit;
int index;
rcu_read_lock();
list_for_each_entry_rcu(pool, &mem->pools, node) {
index = swiotlb_pool_find_slots(dev, pool, orig_addr,
alloc_size, alloc_align_mask);
if (index >= 0) {
rcu_read_unlock();
goto found;
}
}
rcu_read_unlock();
if (!mem->can_grow)
return -1;
schedule_work(&mem->dyn_alloc);
nslabs = nr_slots(alloc_size);
phys_limit = min_not_zero(*dev->dma_mask, dev->bus_dma_limit);
pool = swiotlb_alloc_pool(dev, nslabs, nslabs, 1, phys_limit,
GFP_NOWAIT | __GFP_NOWARN);
if (!pool)
return -1;
index = swiotlb_pool_find_slots(dev, pool, orig_addr,
alloc_size, alloc_align_mask);
if (index < 0) {
swiotlb_dyn_free(&pool->rcu);
return -1;
}
pool->transient = true;
spin_lock_irqsave(&dev->dma_io_tlb_lock, flags);
list_add_rcu(&pool->node, &dev->dma_io_tlb_pools);
spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags);
found:
WRITE_ONCE(dev->dma_uses_io_tlb, true);
smp_mb();
*retpool = pool;
return index;
}
#else /* !CONFIG_SWIOTLB_DYNAMIC */
static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr,
size_t alloc_size, unsigned int alloc_align_mask,
struct io_tlb_pool **retpool)
{
*retpool = &dev->dma_io_tlb_mem->defpool;
return swiotlb_pool_find_slots(dev, *retpool,
orig_addr, alloc_size, alloc_align_mask);
}
#endif /* CONFIG_SWIOTLB_DYNAMIC */
#ifdef CONFIG_DEBUG_FS
static unsigned long mem_used(struct io_tlb_mem *mem)
{
return atomic_long_read(&mem->total_used);
}
#else /* !CONFIG_DEBUG_FS */
static unsigned long mem_pool_used(struct io_tlb_pool *pool)
{
int i;
unsigned long used = 0;
for (i = 0; i < pool->nareas; i++)
used += pool->areas[i].used;
return used;
}
static unsigned long mem_used(struct io_tlb_mem *mem)
{
#ifdef CONFIG_SWIOTLB_DYNAMIC
struct io_tlb_pool *pool;
unsigned long used = 0;
rcu_read_lock();
list_for_each_entry_rcu(pool, &mem->pools, node)
used += mem_pool_used(pool);
rcu_read_unlock();
return used;
#else
return mem_pool_used(&mem->defpool);
#endif
}
#endif /* CONFIG_DEBUG_FS */
phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr,
size_t mapping_size, size_t alloc_size,
unsigned int alloc_align_mask, enum dma_data_direction dir,
unsigned long attrs)
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
unsigned int offset = swiotlb_align_offset(dev, orig_addr);
struct io_tlb_pool *pool;
unsigned int i;
int index;
phys_addr_t tlb_addr;
if (!mem || !mem->nslabs) {
dev_warn_ratelimited(dev,
"Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
return (phys_addr_t)DMA_MAPPING_ERROR;
}
if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n");
if (mapping_size > alloc_size) {
dev_warn_once(dev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
mapping_size, alloc_size);
return (phys_addr_t)DMA_MAPPING_ERROR;
}
index = swiotlb_find_slots(dev, orig_addr,
alloc_size + offset, alloc_align_mask, &pool);
if (index == -1) {
if (!(attrs & DMA_ATTR_NO_WARN))
dev_warn_ratelimited(dev,
"swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
alloc_size, mem->nslabs, mem_used(mem));
return (phys_addr_t)DMA_MAPPING_ERROR;
}
for (i = 0; i < nr_slots(alloc_size + offset); i++)
pool->slots[index + i].orig_addr = slot_addr(orig_addr, i);
tlb_addr = slot_addr(pool->start, index) + offset;
swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE);
return tlb_addr;
}
static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr)
{
struct io_tlb_pool *mem = swiotlb_find_pool(dev, tlb_addr);
unsigned long flags;
unsigned int offset = swiotlb_align_offset(dev, tlb_addr);
int index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT;
int nslots = nr_slots(mem->slots[index].alloc_size + offset);
int aindex = index / mem->area_nslabs;
struct io_tlb_area *area = &mem->areas[aindex];
int count, i;
BUG_ON(aindex >= mem->nareas);
spin_lock_irqsave(&area->lock, flags);
if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE))
count = mem->slots[index + nslots].list;
else
count = 0;
for (i = index + nslots - 1; i >= index; i--) {
mem->slots[i].list = ++count;
mem->slots[i].orig_addr = INVALID_PHYS_ADDR;
mem->slots[i].alloc_size = 0;
}
for (i = index - 1;
io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && mem->slots[i].list;
i--)
mem->slots[i].list = ++count;
area->used -= nslots;
spin_unlock_irqrestore(&area->lock, flags);
dec_used(dev->dma_io_tlb_mem, nslots);
}
#ifdef CONFIG_SWIOTLB_DYNAMIC
static bool swiotlb_del_transient(struct device *dev, phys_addr_t tlb_addr)
{
struct io_tlb_pool *pool;
pool = swiotlb_find_pool(dev, tlb_addr);
if (!pool->transient)
return false;
dec_used(dev->dma_io_tlb_mem, pool->nslabs);
swiotlb_del_pool(dev, pool);
return true;
}
#else /* !CONFIG_SWIOTLB_DYNAMIC */
static inline bool swiotlb_del_transient(struct device *dev,
phys_addr_t tlb_addr)
{
return false;
}
#endif /* CONFIG_SWIOTLB_DYNAMIC */
void swiotlb_tbl_unmap_single(struct device *dev, phys_addr_t tlb_addr,
size_t mapping_size, enum dma_data_direction dir,
unsigned long attrs)
{
if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_FROM_DEVICE);
if (swiotlb_del_transient(dev, tlb_addr))
return;
swiotlb_release_slots(dev, tlb_addr);
}
void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr,
size_t size, enum dma_data_direction dir)
{
if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE);
else
BUG_ON(dir != DMA_FROM_DEVICE);
}
void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr,
size_t size, enum dma_data_direction dir)
{
if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
swiotlb_bounce(dev, tlb_addr, size, DMA_FROM_DEVICE);
else
BUG_ON(dir != DMA_TO_DEVICE);
}
dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size,
enum dma_data_direction dir, unsigned long attrs)
{
phys_addr_t swiotlb_addr;
dma_addr_t dma_addr;
trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size);
swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir,
attrs);
if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR)
return DMA_MAPPING_ERROR;
dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr);
if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, dir,
attrs | DMA_ATTR_SKIP_CPU_SYNC);
dev_WARN_ONCE(dev, 1,
"swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
&dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
return DMA_MAPPING_ERROR;
}
if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
arch_sync_dma_for_device(swiotlb_addr, size, dir);
return dma_addr;
}
size_t swiotlb_max_mapping_size(struct device *dev)
{
int min_align_mask = dma_get_min_align_mask(dev);
int min_align = 0;
if (min_align_mask)
min_align = roundup(min_align_mask, IO_TLB_SIZE);
return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE - min_align;
}
bool is_swiotlb_allocated(void)
{
return io_tlb_default_mem.nslabs;
}
bool is_swiotlb_active(struct device *dev)
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
return mem && mem->nslabs;
}
phys_addr_t default_swiotlb_base(void)
{
#ifdef CONFIG_SWIOTLB_DYNAMIC
io_tlb_default_mem.can_grow = false;
#endif
return io_tlb_default_mem.defpool.start;
}
phys_addr_t default_swiotlb_limit(void)
{
#ifdef CONFIG_SWIOTLB_DYNAMIC
return io_tlb_default_mem.phys_limit;
#else
return io_tlb_default_mem.defpool.end - 1;
#endif
}
#ifdef CONFIG_DEBUG_FS
static int io_tlb_used_get(void *data, u64 *val)
{
struct io_tlb_mem *mem = data;
*val = mem_used(mem);
return 0;
}
static int io_tlb_hiwater_get(void *data, u64 *val)
{
struct io_tlb_mem *mem = data;
*val = atomic_long_read(&mem->used_hiwater);
return 0;
}
static int io_tlb_hiwater_set(void *data, u64 val)
{
struct io_tlb_mem *mem = data;
if (val != 0)
return -EINVAL;
atomic_long_set(&mem->used_hiwater, val);
return 0;
}
DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_used, io_tlb_used_get, NULL, "%llu\n");
DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get,
io_tlb_hiwater_set, "%llu\n");
static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
const char *dirname)
{
atomic_long_set(&mem->total_used, 0);
atomic_long_set(&mem->used_hiwater, 0);
mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs);
if (!mem->nslabs)
return;
debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs);
debugfs_create_file("io_tlb_used", 0400, mem->debugfs, mem,
&fops_io_tlb_used);
debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem,
&fops_io_tlb_hiwater);
}
static int __init swiotlb_create_default_debugfs(void)
{
swiotlb_create_debugfs_files(&io_tlb_default_mem, "swiotlb");
return 0;
}
late_initcall(swiotlb_create_default_debugfs);
#else /* !CONFIG_DEBUG_FS */
static inline void swiotlb_create_debugfs_files(struct io_tlb_mem *mem,
const char *dirname)
{
}
#endif /* CONFIG_DEBUG_FS */
#ifdef CONFIG_DMA_RESTRICTED_POOL
struct page *swiotlb_alloc(struct device *dev, size_t size)
{
struct io_tlb_mem *mem = dev->dma_io_tlb_mem;
struct io_tlb_pool *pool;
phys_addr_t tlb_addr;
int index;
if (!mem)
return NULL;
index = swiotlb_find_slots(dev, 0, size, 0, &pool);
if (index == -1)
return NULL;
tlb_addr = slot_addr(pool->start, index);
return pfn_to_page(PFN_DOWN(tlb_addr));
}
bool swiotlb_free(struct device *dev, struct page *page, size_t size)
{
phys_addr_t tlb_addr = page_to_phys(page);
if (!is_swiotlb_buffer(dev, tlb_addr))
return false;
swiotlb_release_slots(dev, tlb_addr);
return true;
}
static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
struct device *dev)
{
struct io_tlb_mem *mem = rmem->priv;
unsigned long nslabs = rmem->size >> IO_TLB_SHIFT;
unsigned int nareas = 1;
if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) {
dev_err(dev, "Restricted DMA pool must be accessible within the linear mapping.");
return -EINVAL;
}
if (!mem) {
struct io_tlb_pool *pool;
mem = kzalloc(sizeof(*mem), GFP_KERNEL);
if (!mem)
return -ENOMEM;
pool = &mem->defpool;
pool->slots = kcalloc(nslabs, sizeof(*pool->slots), GFP_KERNEL);
if (!pool->slots) {
kfree(mem);
return -ENOMEM;
}
pool->areas = kcalloc(nareas, sizeof(*pool->areas),
GFP_KERNEL);
if (!pool->areas) {
kfree(pool->slots);
kfree(mem);
return -ENOMEM;
}
set_memory_decrypted((unsigned long)phys_to_virt(rmem->base),
rmem->size >> PAGE_SHIFT);
swiotlb_init_io_tlb_pool(pool, rmem->base, nslabs,
false, nareas);
mem->force_bounce = true;
mem->for_alloc = true;
#ifdef CONFIG_SWIOTLB_DYNAMIC
spin_lock_init(&mem->lock);
#endif
add_mem_pool(mem, pool);
rmem->priv = mem;
swiotlb_create_debugfs_files(mem, rmem->name);
}
dev->dma_io_tlb_mem = mem;
return 0;
}
static void rmem_swiotlb_device_release(struct reserved_mem *rmem,
struct device *dev)
{
dev->dma_io_tlb_mem = &io_tlb_default_mem;
}
static const struct reserved_mem_ops rmem_swiotlb_ops = {
.device_init = rmem_swiotlb_device_init,
.device_release = rmem_swiotlb_device_release,
};
static int __init rmem_swiotlb_setup(struct reserved_mem *rmem)
{
unsigned long node = rmem->fdt_node;
if (of_get_flat_dt_prop(node, "reusable", NULL) ||
of_get_flat_dt_prop(node, "linux,cma-default", NULL) ||
of_get_flat_dt_prop(node, "linux,dma-default", NULL) ||
of_get_flat_dt_prop(node, "no-map", NULL))
return -EINVAL;
rmem->ops = &rmem_swiotlb_ops;
pr_info("Reserved memory: created restricted DMA pool at %pa, size %ld MiB\n",
&rmem->base, (unsigned long)rmem->size / SZ_1M);
return 0;
}
RESERVEDMEM_OF_DECLARE(dma, "restricted-dma-pool", rmem_swiotlb_setup);
#endif /* CONFIG_DMA_RESTRICTED_POOL */