diff options
Diffstat (limited to 'kernel/dma/swiotlb.c')
| -rw-r--r-- | kernel/dma/swiotlb.c | 1197 |
1 files changed, 769 insertions, 428 deletions
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index c19379fabd20..339a990554e7 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -21,38 +21,36 @@ #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-noncoherent.h> -#include <linux/mm.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/scatterlist.h> +#include <linux/set_memory.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/swiotlb.h> -#include <linux/pfn.h> #include <linux/types.h> -#include <linux/ctype.h> -#include <linux/highmem.h> -#include <linux/gfp.h> -#include <linux/scatterlist.h> -#include <linux/mem_encrypt.h> -#include <linux/set_memory.h> -#ifdef CONFIG_DEBUG_FS -#include <linux/debugfs.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 -#include <asm/io.h> -#include <asm/dma.h> - -#include <linux/init.h> -#include <linux/memblock.h> -#include <linux/iommu-helper.h> - #define CREATE_TRACE_POINTS #include <trace/events/swiotlb.h> -#define OFFSET(val,align) ((unsigned long) \ - ( (val) & ( (align) - 1))) - #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT)) /* @@ -62,122 +60,183 @@ */ #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT) -enum swiotlb_force swiotlb_force; +#define INVALID_PHYS_ADDR (~(phys_addr_t)0) -/* - * Used to do a quick range check in swiotlb_tbl_unmap_single and - * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this - * API. - */ -phys_addr_t io_tlb_start, io_tlb_end; +struct io_tlb_slot { + phys_addr_t orig_addr; + size_t alloc_size; + unsigned int list; +}; -/* - * The number of IO TLB blocks (in groups of 64) between io_tlb_start and - * io_tlb_end. This is command line adjustable via setup_io_tlb_npages. - */ -static unsigned long io_tlb_nslabs; +static bool swiotlb_force_bounce; +static bool swiotlb_force_disable; -/* - * The number of used IO TLB block - */ -static unsigned long io_tlb_used; +struct io_tlb_mem io_tlb_default_mem; -/* - * This is a free list describing the number of free entries available from - * each index - */ -static unsigned int *io_tlb_list; -static unsigned int io_tlb_index; +phys_addr_t swiotlb_unencrypted_base; -/* - * Max segment that we can provide which (if pages are contingous) will - * not be bounced (unless SWIOTLB_FORCE is set). - */ -unsigned int max_segment; +static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT; +static unsigned long default_nareas; -/* - * We need to save away the original address corresponding to a mapped entry - * for the sync operations. +/** + * struct io_tlb_area - IO TLB memory area descriptor + * + * This is a single area with a single lock. + * + * @used: The number of used IO TLB block. + * @index: The slot index to start searching in this area for next round. + * @lock: The lock to protect the above data structures in the map and + * unmap calls. */ -#define INVALID_PHYS_ADDR (~(phys_addr_t)0) -static phys_addr_t *io_tlb_orig_addr; +struct io_tlb_area { + unsigned long used; + unsigned int index; + spinlock_t lock; +}; /* - * Protect the above data structures in the map and unmap calls + * Round up number of slabs to the next power of 2. The last area is going + * be smaller than the rest if default_nslabs is not power of two. + * The number of slot in an area should be a multiple of IO_TLB_SEGSIZE, + * otherwise a segment may span two or more areas. It conflicts with free + * contiguous slots tracking: free slots are treated contiguous no matter + * whether they cross an area boundary. + * + * Return true if default_nslabs is rounded up. */ -static DEFINE_SPINLOCK(io_tlb_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 int late_alloc; +static void swiotlb_adjust_nareas(unsigned int nareas) +{ + /* use a single area when non is specified */ + 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 int __init setup_io_tlb_npages(char *str) { if (isdigit(*str)) { - io_tlb_nslabs = simple_strtoul(str, &str, 0); /* avoid tail segment of size < IO_TLB_SEGSIZE */ - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + default_nslabs = + ALIGN(simple_strtoul(str, &str, 0), IO_TLB_SEGSIZE); } if (*str == ',') ++str; - if (!strcmp(str, "force")) { - swiotlb_force = SWIOTLB_FORCE; - } else if (!strcmp(str, "noforce")) { - swiotlb_force = SWIOTLB_NO_FORCE; - io_tlb_nslabs = 1; - } + 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); -static bool no_iotlb_memory; - -unsigned long swiotlb_nr_tbl(void) -{ - return unlikely(no_iotlb_memory) ? 0 : io_tlb_nslabs; -} -EXPORT_SYMBOL_GPL(swiotlb_nr_tbl); - unsigned int swiotlb_max_segment(void) { - return unlikely(no_iotlb_memory) ? 0 : max_segment; + if (!io_tlb_default_mem.nslabs) + return 0; + return rounddown(io_tlb_default_mem.nslabs << IO_TLB_SHIFT, PAGE_SIZE); } EXPORT_SYMBOL_GPL(swiotlb_max_segment); -void swiotlb_set_max_segment(unsigned int val) +unsigned long swiotlb_size_or_default(void) { - if (swiotlb_force == SWIOTLB_FORCE) - max_segment = 1; - else - max_segment = rounddown(val, PAGE_SIZE); + return default_nslabs << IO_TLB_SHIFT; } -/* default to 64MB */ -#define IO_TLB_DEFAULT_SIZE (64UL<<20) -unsigned long swiotlb_size_or_default(void) +void __init swiotlb_adjust_size(unsigned long size) { - unsigned long size; - - size = io_tlb_nslabs << IO_TLB_SHIFT; + /* + * If swiotlb parameter has not been specified, give a chance to + * architectures such as those supporting memory encryption to + * adjust/expand SWIOTLB size for their use. + */ + if (default_nslabs != IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT) + return; - return size ? size : (IO_TLB_DEFAULT_SIZE); + 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) { - unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT; + struct io_tlb_mem *mem = &io_tlb_default_mem; - if (no_iotlb_memory) { + if (!mem->nslabs) { pr_warn("No low mem\n"); return; } - pr_info("mapped [mem %#010llx-%#010llx] (%luMB)\n", - (unsigned long long)io_tlb_start, - (unsigned long long)io_tlb_end, - bytes >> 20); + 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); +} + +/* + * Remap swioltb memory in the unencrypted physical address space + * when swiotlb_unencrypted_base is set. (e.g. for Hyper-V AMD SEV-SNP + * Isolation VMs). + */ +#ifdef CONFIG_HAS_IOMEM +static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes) +{ + void *vaddr = NULL; + + if (swiotlb_unencrypted_base) { + phys_addr_t paddr = mem->start + swiotlb_unencrypted_base; + + vaddr = memremap(paddr, bytes, MEMREMAP_WB); + if (!vaddr) + pr_err("Failed to map the unencrypted memory %pa size %lx.\n", + &paddr, bytes); + } + + return vaddr; +} +#else +static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes) +{ + return NULL; +} +#endif + /* * Early SWIOTLB allocation may be too early to allow an architecture to * perform the desired operations. This function allows the architecture to @@ -186,87 +245,139 @@ void swiotlb_print_info(void) */ void __init swiotlb_update_mem_attributes(void) { + struct io_tlb_mem *mem = &io_tlb_default_mem; void *vaddr; unsigned long bytes; - if (no_iotlb_memory || late_alloc) + if (!mem->nslabs || mem->late_alloc) return; - - vaddr = phys_to_virt(io_tlb_start); - bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT); + vaddr = phys_to_virt(mem->start); + bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); - memset(vaddr, 0, bytes); + + mem->vaddr = swiotlb_mem_remap(mem, bytes); + if (!mem->vaddr) + mem->vaddr = vaddr; } -int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) +static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, + unsigned long nslabs, unsigned int flags, + bool late_alloc, unsigned int nareas) { - unsigned long i, bytes; - size_t alloc_size; - - bytes = nslabs << IO_TLB_SHIFT; + 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; + + mem->force_bounce = swiotlb_force_bounce || (flags & SWIOTLB_FORCE); + + for (i = 0; i < mem->nareas; i++) { + spin_lock_init(&mem->areas[i].lock); + mem->areas[i].index = 0; + mem->areas[i].used = 0; + } - io_tlb_nslabs = nslabs; - io_tlb_start = __pa(tlb); - io_tlb_end = io_tlb_start + bytes; + 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; + } /* - * Allocate and initialize the free list array. This array is used - * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE - * between io_tlb_start and io_tlb_end. + * If swiotlb_unencrypted_base is set, the bounce buffer memory will + * be remapped and cleared in swiotlb_update_mem_attributes. */ - alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(int)); - io_tlb_list = memblock_alloc(alloc_size, PAGE_SIZE); - if (!io_tlb_list) - panic("%s: Failed to allocate %zu bytes align=0x%lx\n", - __func__, alloc_size, PAGE_SIZE); - - alloc_size = PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)); - io_tlb_orig_addr = memblock_alloc(alloc_size, PAGE_SIZE); - if (!io_tlb_orig_addr) - panic("%s: Failed to allocate %zu bytes align=0x%lx\n", - __func__, alloc_size, PAGE_SIZE); - - for (i = 0; i < io_tlb_nslabs; i++) { - io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); - io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; - } - io_tlb_index = 0; - - if (verbose) - swiotlb_print_info(); + if (swiotlb_unencrypted_base) + return; - swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT); - return 0; + memset(vaddr, 0, bytes); + mem->vaddr = vaddr; + return; } /* * Statically reserve bounce buffer space and initialize bounce buffer data * structures for the software IO TLB used to implement the DMA API. */ -void __init -swiotlb_init(int verbose) +void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, + int (*remap)(void *tlb, unsigned long nslabs)) { - size_t default_size = IO_TLB_DEFAULT_SIZE; - unsigned char *vstart; - unsigned long bytes; + struct io_tlb_mem *mem = &io_tlb_default_mem; + unsigned long nslabs; + size_t alloc_size; + size_t bytes; + void *tlb; + + if (!addressing_limit && !swiotlb_force_bounce) + return; + if (swiotlb_force_disable) + return; + + /* + * default_nslabs maybe changed when adjust area number. + * So allocate bounce buffer after adjusting area number. + */ + if (!default_nareas) + swiotlb_adjust_nareas(num_possible_cpus()); - if (!io_tlb_nslabs) { - io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + nslabs = default_nslabs; + /* + * By default allocate the bounce buffer memory from low memory, but + * allow to pick a location everywhere for hypervisors with guest + * memory encryption. + */ +retry: + bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT); + 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 tlb structure\n", __func__); + return; + } + + if (remap && remap(tlb, nslabs) < 0) { + memblock_free(tlb, PAGE_ALIGN(bytes)); + + nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); + if (nslabs >= IO_TLB_MIN_SLABS) + goto retry; + + pr_warn("%s: Failed to remap %zu bytes\n", __func__, bytes); + return; } - bytes = io_tlb_nslabs << IO_TLB_SHIFT; + 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; + } - /* Get IO TLB memory from the low pages */ - vstart = memblock_alloc_low(PAGE_ALIGN(bytes), PAGE_SIZE); - if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) + mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area), + default_nareas), SMP_CACHE_BYTES); + if (!mem->areas) { + pr_warn("%s: Failed to allocate mem->areas.\n", __func__); return; + } + + swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, flags, false, + default_nareas); - if (io_tlb_start) - memblock_free_early(io_tlb_start, - PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); - pr_warn("Cannot allocate buffer"); - no_iotlb_memory = true; + if (flags & SWIOTLB_VERBOSE) + swiotlb_print_info(); +} + +void __init swiotlb_init(bool addressing_limit, unsigned int flags) +{ + swiotlb_init_remap(addressing_limit, flags, NULL); } /* @@ -274,148 +385,173 @@ swiotlb_init(int verbose) * initialize the swiotlb later using the slab allocator if needed. * This should be just like above, but with some error catching. */ -int -swiotlb_late_init_with_default_size(size_t default_size) +int swiotlb_init_late(size_t size, gfp_t gfp_mask, + int (*remap)(void *tlb, unsigned long nslabs)) { - unsigned long bytes, req_nslabs = io_tlb_nslabs; + struct io_tlb_mem *mem = &io_tlb_default_mem; + unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); unsigned char *vstart = NULL; - unsigned int order; + unsigned int order, area_order; + bool retried = false; int rc = 0; - if (!io_tlb_nslabs) { - io_tlb_nslabs = (default_size >> IO_TLB_SHIFT); - io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); - } + if (swiotlb_force_disable) + return 0; - /* - * Get IO TLB memory from the low pages - */ - order = get_order(io_tlb_nslabs << IO_TLB_SHIFT); - io_tlb_nslabs = SLABS_PER_PAGE << order; - bytes = io_tlb_nslabs << IO_TLB_SHIFT; +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_DMA | __GFP_NOWARN, + vstart = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN, order); if (vstart) break; order--; + nslabs = SLABS_PER_PAGE << order; + retried = true; } - if (!vstart) { - io_tlb_nslabs = req_nslabs; + 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 (order != get_order(bytes)) { + + if (retried) { pr_warn("only able to allocate %ld MB\n", (PAGE_SIZE << order) >> 20); - io_tlb_nslabs = SLABS_PER_PAGE << order; } - rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs); - if (rc) - free_pages((unsigned long)vstart, order); - return rc; -} + if (!default_nareas) + swiotlb_adjust_nareas(num_possible_cpus()); -static void swiotlb_cleanup(void) -{ - io_tlb_end = 0; - io_tlb_start = 0; - io_tlb_nslabs = 0; - max_segment = 0; -} + area_order = get_order(array_size(sizeof(*mem->areas), + default_nareas)); + mem->areas = (struct io_tlb_area *) + __get_free_pages(GFP_KERNEL | __GFP_ZERO, area_order); + if (!mem->areas) + goto error_area; -int -swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) -{ - unsigned long i, bytes; + mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(array_size(sizeof(*mem->slots), nslabs))); + if (!mem->slots) + goto error_slots; - bytes = nslabs << IO_TLB_SHIFT; - - io_tlb_nslabs = nslabs; - io_tlb_start = virt_to_phys(tlb); - io_tlb_end = io_tlb_start + bytes; - - set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT); - memset(tlb, 0, bytes); - - /* - * Allocate and initialize the free list array. This array is used - * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE - * between io_tlb_start and io_tlb_end. - */ - io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL, - get_order(io_tlb_nslabs * sizeof(int))); - if (!io_tlb_list) - goto cleanup3; - - io_tlb_orig_addr = (phys_addr_t *) - __get_free_pages(GFP_KERNEL, - get_order(io_tlb_nslabs * - sizeof(phys_addr_t))); - if (!io_tlb_orig_addr) - goto cleanup4; - - for (i = 0; i < io_tlb_nslabs; i++) { - io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); - io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; - } - io_tlb_index = 0; + set_memory_decrypted((unsigned long)vstart, + (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT); + swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, 0, true, + default_nareas); swiotlb_print_info(); - - late_alloc = 1; - - swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT); - return 0; -cleanup4: - free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs * - sizeof(int))); - io_tlb_list = NULL; -cleanup3: - swiotlb_cleanup(); +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) { - if (!io_tlb_orig_addr) + struct io_tlb_mem *mem = &io_tlb_default_mem; + unsigned long tbl_vaddr; + size_t tbl_size, slots_size; + unsigned int area_order; + + if (swiotlb_force_bounce) return; - if (late_alloc) { - free_pages((unsigned long)io_tlb_orig_addr, - get_order(io_tlb_nslabs * sizeof(phys_addr_t))); - free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs * - sizeof(int))); - free_pages((unsigned long)phys_to_virt(io_tlb_start), - get_order(io_tlb_nslabs << IO_TLB_SHIFT)); + 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(io_tlb_orig_addr), - PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); - memblock_free_late(__pa(io_tlb_list), - PAGE_ALIGN(io_tlb_nslabs * sizeof(int))); - memblock_free_late(io_tlb_start, - PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + 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); } - swiotlb_cleanup(); + + memset(mem, 0, sizeof(*mem)); +} + +/* + * Return the offset into a iotlb slot required to keep the device happy. + */ +static unsigned int swiotlb_align_offset(struct device *dev, u64 addr) +{ + return addr & dma_get_min_align_mask(dev) & (IO_TLB_SIZE - 1); } /* * Bounce: copy the swiotlb buffer from or back to the original dma location */ -static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir) +static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size, + enum dma_data_direction dir) { + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + 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 = phys_to_virt(tlb_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))) { - /* The buffer does not have a mapping. Map it in and copy */ unsigned int offset = orig_addr & ~PAGE_MASK; - char *buffer; + struct page *page; unsigned int sz = 0; unsigned long flags; @@ -423,12 +559,11 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, sz = min_t(size_t, PAGE_SIZE - offset, size); local_irq_save(flags); - buffer = kmap_atomic(pfn_to_page(pfn)); + page = pfn_to_page(pfn); if (dir == DMA_TO_DEVICE) - memcpy(vaddr, buffer + offset, sz); + memcpy_from_page(vaddr, page, offset, sz); else - memcpy(buffer + offset, vaddr, sz); - kunmap_atomic(buffer); + memcpy_to_page(page, offset, vaddr, sz); local_irq_restore(flags); size -= sz; @@ -443,82 +578,79 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr, } } -phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, - dma_addr_t tbl_dma_addr, - phys_addr_t orig_addr, - size_t mapping_size, - size_t alloc_size, - enum dma_data_direction dir, - unsigned long attrs) +static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx) { - unsigned long flags; - phys_addr_t tlb_addr; - unsigned int nslots, stride, index, wrap; - int i; - unsigned long mask; - unsigned long offset_slots; - unsigned long max_slots; - unsigned long tmp_io_tlb_used; - - if (no_iotlb_memory) - panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer"); - - if (mem_encrypt_active()) - pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n"); - - if (mapping_size > alloc_size) { - dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)", - mapping_size, alloc_size); - return (phys_addr_t)DMA_MAPPING_ERROR; - } - - mask = dma_get_seg_boundary(hwdev); - - tbl_dma_addr &= mask; + return start + (idx << IO_TLB_SHIFT); +} - offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; +/* + * Carefully handle integer overflow which can occur when boundary_mask == ~0UL. + */ +static inline unsigned long get_max_slots(unsigned long boundary_mask) +{ + if (boundary_mask == ~0UL) + return 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); + return nr_slots(boundary_mask + 1); +} - /* - * Carefully handle integer overflow which can occur when mask == ~0UL. - */ - max_slots = mask + 1 - ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT - : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT); +static unsigned int wrap_area_index(struct io_tlb_mem *mem, unsigned int index) +{ + if (index >= mem->area_nslabs) + return 0; + return index; +} - /* - * For mappings greater than or equal to a page, we limit the stride - * (and hence alignment) to a page size. - */ - nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; - if (alloc_size >= PAGE_SIZE) - stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT)); - else - stride = 1; +/* + * Find a suitable number of IO TLB entries size that will fit this request and + * allocate a buffer from that IO TLB pool. + */ +static int swiotlb_do_find_slots(struct device *dev, int area_index, + phys_addr_t orig_addr, size_t alloc_size, + unsigned int alloc_align_mask) +{ + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + struct io_tlb_area *area = mem->areas + area_index; + unsigned long boundary_mask = dma_get_seg_boundary(dev); + dma_addr_t tbl_dma_addr = + phys_to_dma_unencrypted(dev, mem->start) & boundary_mask; + unsigned long max_slots = get_max_slots(boundary_mask); + unsigned int iotlb_align_mask = + dma_get_min_align_mask(dev) & ~(IO_TLB_SIZE - 1); + unsigned int nslots = nr_slots(alloc_size), stride; + unsigned int index, wrap, count = 0, i; + unsigned int offset = swiotlb_align_offset(dev, orig_addr); + unsigned long flags; + unsigned int slot_base; + unsigned int slot_index; BUG_ON(!nslots); + BUG_ON(area_index >= mem->nareas); /* - * Find suitable number of IO TLB entries size that will fit this - * request and allocate a buffer from that IO TLB pool. + * For mappings with an alignment requirement don't bother looping to + * unaligned slots once we found an aligned one. For allocations of + * PAGE_SIZE or larger only look for page aligned allocations. */ - spin_lock_irqsave(&io_tlb_lock, flags); + stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1; + if (alloc_size >= PAGE_SIZE) + stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT)); + stride = max(stride, (alloc_align_mask >> IO_TLB_SHIFT) + 1); - if (unlikely(nslots > io_tlb_nslabs - io_tlb_used)) + spin_lock_irqsave(&area->lock, flags); + if (unlikely(nslots > mem->area_nslabs - area->used)) goto not_found; - index = ALIGN(io_tlb_index, stride); - if (index >= io_tlb_nslabs) - index = 0; - wrap = index; + slot_base = area_index * mem->area_nslabs; + index = wrap = wrap_area_index(mem, ALIGN(area->index, stride)); do { - while (iommu_is_span_boundary(index, nslots, offset_slots, - max_slots)) { - index += stride; - if (index >= io_tlb_nslabs) - index = 0; - if (index == wrap) - goto not_found; + 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(mem, index + 1); + continue; } /* @@ -526,74 +658,136 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, * contiguous buffers, we allocate the buffers from that slot * and mark the entries as '0' indicating unavailable. */ - if (io_tlb_list[index] >= nslots) { - int count = 0; - - for (i = index; i < (int) (index + nslots); i++) - io_tlb_list[i] = 0; - for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--) - io_tlb_list[i] = ++count; - tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT); - - /* - * Update the indices to avoid searching in the next - * round. - */ - io_tlb_index = ((index + nslots) < io_tlb_nslabs - ? (index + nslots) : 0); - - goto found; + if (!iommu_is_span_boundary(slot_index, nslots, + nr_slots(tbl_dma_addr), + max_slots)) { + if (mem->slots[slot_index].list >= nslots) + goto found; } - index += stride; - if (index >= io_tlb_nslabs) - index = 0; + index = wrap_area_index(mem, index + stride); } while (index != wrap); not_found: - tmp_io_tlb_used = io_tlb_used; + spin_unlock_irqrestore(&area->lock, flags); + return -1; - spin_unlock_irqrestore(&io_tlb_lock, flags); - if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) - dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n", - alloc_size, io_tlb_nslabs, tmp_io_tlb_used); - return (phys_addr_t)DMA_MAPPING_ERROR; found: - io_tlb_used += nslots; - spin_unlock_irqrestore(&io_tlb_lock, flags); + for (i = slot_index; i < slot_index + nslots; i++) { + mem->slots[i].list = 0; + mem->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 && + mem->slots[i].list; i--) + mem->slots[i].list = ++count; + + /* + * Update the indices to avoid searching in the next round. + */ + if (index + nslots < mem->area_nslabs) + area->index = index + nslots; + else + area->index = 0; + area->used += nslots; + spin_unlock_irqrestore(&area->lock, flags); + return slot_index; +} + +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_mem *mem = dev->dma_io_tlb_mem; + int start = raw_smp_processor_id() & (mem->nareas - 1); + int i = start, index; + + do { + index = swiotlb_do_find_slots(dev, i, orig_addr, alloc_size, + alloc_align_mask); + if (index >= 0) + return index; + if (++i >= mem->nareas) + i = 0; + } while (i != start); + + return -1; +} + +static unsigned long mem_used(struct io_tlb_mem *mem) +{ + int i; + unsigned long used = 0; + + for (i = 0; i < mem->nareas; i++) + used += mem->areas[i].used; + return used; +} + +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); + 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); + 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; + } /* * Save away the mapping from the original address to the DMA address. * This is needed when we sync the memory. Then we sync the buffer if * needed. */ - for (i = 0; i < nslots; i++) - io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT); - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE); - + for (i = 0; i < nr_slots(alloc_size + offset); i++) + mem->slots[index + i].orig_addr = slot_addr(orig_addr, i); + tlb_addr = slot_addr(mem->start, index) + offset; + /* + * When dir == DMA_FROM_DEVICE we could omit the copy from the orig + * to the tlb buffer, if we knew for sure the device will + * overwrite the entire current content. But we don't. Thus + * unconditional bounce may prevent leaking swiotlb content (i.e. + * kernel memory) to user-space. + */ + swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE); return tlb_addr; } -/* - * tlb_addr is the physical address of the bounce buffer to unmap. - */ -void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, - size_t mapping_size, size_t alloc_size, - enum dma_data_direction dir, unsigned long attrs) +static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr) { + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned long flags; - int i, count, nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; - int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; - phys_addr_t orig_addr = io_tlb_orig_addr[index]; - - /* - * First, sync the memory before unmapping the entry - */ - if (orig_addr != INVALID_PHYS_ADDR && - !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))) - swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_FROM_DEVICE); + 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; /* * Return the buffer to the free list by setting the corresponding @@ -601,59 +795,69 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, * While returning the entries to the free list, we merge the entries * with slots below and above the pool being returned. */ - spin_lock_irqsave(&io_tlb_lock, flags); - { - count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ? - io_tlb_list[index + nslots] : 0); - /* - * Step 1: return the slots to the free list, merging the - * slots with superceeding slots - */ - for (i = index + nslots - 1; i >= index; i--) { - io_tlb_list[i] = ++count; - io_tlb_orig_addr[i] = INVALID_PHYS_ADDR; - } - /* - * Step 2: merge the returned slots with the preceding slots, - * if available (non zero) - */ - for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--) - io_tlb_list[i] = ++count; + 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; - io_tlb_used -= nslots; + /* + * Step 1: return the slots to the free list, merging the slots with + * superceeding slots + */ + 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; } - spin_unlock_irqrestore(&io_tlb_lock, flags); + + /* + * Step 2: merge the returned slots with the preceding slots, if + * available (non zero) + */ + 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); } -void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir, - enum dma_sync_target target) +/* + * tlb_addr is the physical address of the bounce buffer to unmap. + */ +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) { - int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT; - phys_addr_t orig_addr = io_tlb_orig_addr[index]; + /* + * First, sync the memory before unmapping the entry + */ + 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 (orig_addr == INVALID_PHYS_ADDR) - return; - orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1); - - switch (target) { - case SYNC_FOR_CPU: - if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(orig_addr, tlb_addr, - size, DMA_FROM_DEVICE); - else - BUG_ON(dir != DMA_TO_DEVICE); - break; - case SYNC_FOR_DEVICE: - if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(orig_addr, tlb_addr, - size, DMA_TO_DEVICE); - else - BUG_ON(dir != DMA_FROM_DEVICE); - break; - default: - BUG(); - } + 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); } /* @@ -666,19 +870,17 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, phys_addr_t swiotlb_addr; dma_addr_t dma_addr; - trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size, - swiotlb_force); + trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size); - swiotlb_addr = swiotlb_tbl_map_single(dev, - __phys_to_dma(dev, io_tlb_start), - paddr, size, size, dir, attrs); + 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; /* Ensure that the address returned is DMA'ble */ - dma_addr = __phys_to_dma(dev, swiotlb_addr); + 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, size, dir, + 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", @@ -693,30 +895,169 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, size_t swiotlb_max_mapping_size(struct device *dev) { - return ((size_t)1 << IO_TLB_SHIFT) * IO_TLB_SEGSIZE; -} + int min_align_mask = dma_get_min_align_mask(dev); + int min_align = 0; -bool is_swiotlb_active(void) -{ /* - * When SWIOTLB is initialized, even if io_tlb_start points to physical - * address zero, io_tlb_end surely doesn't. + * swiotlb_find_slots() skips slots according to + * min align mask. This affects max mapping size. + * Take it into acount here. */ - return io_tlb_end != 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_active(struct device *dev) +{ + struct io_tlb_mem *mem = dev->dma_io_tlb_mem; + + return mem && mem->nslabs; +} +EXPORT_SYMBOL_GPL(is_swiotlb_active); + +static int io_tlb_used_get(void *data, u64 *val) +{ + *val = mem_used(&io_tlb_default_mem); + return 0; +} +DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_used, io_tlb_used_get, NULL, "%llu\n"); + +static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, + const char *dirname) +{ + 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, NULL, + &fops_io_tlb_used); +} + +static int __init __maybe_unused swiotlb_create_default_debugfs(void) +{ + swiotlb_create_debugfs_files(&io_tlb_default_mem, "swiotlb"); + return 0; } #ifdef CONFIG_DEBUG_FS +late_initcall(swiotlb_create_default_debugfs); +#endif + +#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; + phys_addr_t tlb_addr; + int index; + + if (!mem) + return NULL; + + index = swiotlb_find_slots(dev, 0, size, 0); + if (index == -1) + return NULL; + + tlb_addr = slot_addr(mem->start, index); + + return pfn_to_page(PFN_DOWN(tlb_addr)); +} -static int __init swiotlb_create_debugfs(void) +bool swiotlb_free(struct device *dev, struct page *page, size_t size) { - struct dentry *root; + 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; + + /* Set Per-device io tlb area to one */ + unsigned int nareas = 1; + + /* + * Since multiple devices can share the same pool, the private data, + * io_tlb_mem struct, will be initialized by the first device attached + * to it. + */ + if (!mem) { + mem = kzalloc(sizeof(*mem), GFP_KERNEL); + if (!mem) + return -ENOMEM; + + mem->slots = kcalloc(nslabs, sizeof(*mem->slots), GFP_KERNEL); + if (!mem->slots) { + kfree(mem); + return -ENOMEM; + } + + mem->areas = kcalloc(nareas, sizeof(*mem->areas), + GFP_KERNEL); + if (!mem->areas) { + kfree(mem->slots); + kfree(mem); + return -ENOMEM; + } + + set_memory_decrypted((unsigned long)phys_to_virt(rmem->base), + rmem->size >> PAGE_SHIFT); + swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, SWIOTLB_FORCE, + false, nareas); + mem->for_alloc = true; + + rmem->priv = mem; + + swiotlb_create_debugfs_files(mem, rmem->name); + } + + dev->dma_io_tlb_mem = mem; - root = debugfs_create_dir("swiotlb", NULL); - debugfs_create_ulong("io_tlb_nslabs", 0400, root, &io_tlb_nslabs); - debugfs_create_ulong("io_tlb_used", 0400, root, &io_tlb_used); return 0; } -late_initcall(swiotlb_create_debugfs); +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, +}; -#endif +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; + + if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) { + pr_err("Restricted DMA pool must be accessible within the linear mapping."); + 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 */ |