diff options
Diffstat (limited to 'lib')
| -rw-r--r-- | lib/Kconfig | 6 | ||||
| -rw-r--r-- | lib/Kconfig.debug | 2 | ||||
| -rw-r--r-- | lib/Makefile | 2 | ||||
| -rw-r--r-- | lib/assoc_array.c | 37 | ||||
| -rw-r--r-- | lib/chacha20.c | 71 | ||||
| -rw-r--r-- | lib/crc-ccitt.c | 58 | ||||
| -rw-r--r-- | lib/dma-direct.c | 156 | ||||
| -rw-r--r-- | lib/dma-noop.c | 68 | ||||
| -rw-r--r-- | lib/kobject.c | 2 | ||||
| -rw-r--r-- | lib/percpu-refcount.c | 8 | ||||
| -rw-r--r-- | lib/sbitmap.c | 2 | ||||
| -rw-r--r-- | lib/scatterlist.c | 127 | ||||
| -rw-r--r-- | lib/swiotlb.c | 205 | ||||
| -rw-r--r-- | lib/usercopy.c | 2 |
14 files changed, 527 insertions, 219 deletions
diff --git a/lib/Kconfig b/lib/Kconfig index c5e84fbcb30b..e96089499371 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -409,7 +409,11 @@ config HAS_DMA depends on !NO_DMA default y -config DMA_NOOP_OPS +config SGL_ALLOC + bool + default n + +config DMA_DIRECT_OPS bool depends on HAS_DMA && (!64BIT || ARCH_DMA_ADDR_T_64BIT) default n diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 890d4766cef3..64d7c19d3167 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1966,7 +1966,7 @@ config STRICT_DEVMEM bool "Filter access to /dev/mem" depends on MMU && DEVMEM depends on ARCH_HAS_DEVMEM_IS_ALLOWED - default y if TILE || PPC + default y if TILE || PPC || X86 || ARM64 ---help--- If this option is disabled, you allow userspace (root) access to all of memory, including kernel and userspace memory. Accidental diff --git a/lib/Makefile b/lib/Makefile index 75ec13778cd8..7adb066692b3 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -28,7 +28,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o -lib-$(CONFIG_DMA_NOOP_OPS) += dma-noop.o +lib-$(CONFIG_DMA_DIRECT_OPS) += dma-direct.o lib-$(CONFIG_DMA_VIRT_OPS) += dma-virt.o lib-y += kobject.o klist.o diff --git a/lib/assoc_array.c b/lib/assoc_array.c index b77d51da8c73..c6659cb37033 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -38,12 +38,10 @@ begin_node: if (assoc_array_ptr_is_shortcut(cursor)) { /* Descend through a shortcut */ shortcut = assoc_array_ptr_to_shortcut(cursor); - smp_read_barrier_depends(); - cursor = READ_ONCE(shortcut->next_node); + cursor = READ_ONCE(shortcut->next_node); /* Address dependency. */ } node = assoc_array_ptr_to_node(cursor); - smp_read_barrier_depends(); slot = 0; /* We perform two passes of each node. @@ -55,15 +53,12 @@ begin_node: */ has_meta = 0; for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = READ_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */ has_meta |= (unsigned long)ptr; if (ptr && assoc_array_ptr_is_leaf(ptr)) { - /* We need a barrier between the read of the pointer - * and dereferencing the pointer - but only if we are - * actually going to dereference it. + /* We need a barrier between the read of the pointer, + * which is supplied by the above READ_ONCE(). */ - smp_read_barrier_depends(); - /* Invoke the callback */ ret = iterator(assoc_array_ptr_to_leaf(ptr), iterator_data); @@ -86,10 +81,8 @@ begin_node: continue_node: node = assoc_array_ptr_to_node(cursor); - smp_read_barrier_depends(); - for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = READ_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */ if (assoc_array_ptr_is_meta(ptr)) { cursor = ptr; goto begin_node; @@ -98,16 +91,15 @@ continue_node: finished_node: /* Move up to the parent (may need to skip back over a shortcut) */ - parent = READ_ONCE(node->back_pointer); + parent = READ_ONCE(node->back_pointer); /* Address dependency. */ slot = node->parent_slot; if (parent == stop) return 0; if (assoc_array_ptr_is_shortcut(parent)) { shortcut = assoc_array_ptr_to_shortcut(parent); - smp_read_barrier_depends(); cursor = parent; - parent = READ_ONCE(shortcut->back_pointer); + parent = READ_ONCE(shortcut->back_pointer); /* Address dependency. */ slot = shortcut->parent_slot; if (parent == stop) return 0; @@ -147,7 +139,7 @@ int assoc_array_iterate(const struct assoc_array *array, void *iterator_data), void *iterator_data) { - struct assoc_array_ptr *root = READ_ONCE(array->root); + struct assoc_array_ptr *root = READ_ONCE(array->root); /* Address dependency. */ if (!root) return 0; @@ -194,7 +186,7 @@ assoc_array_walk(const struct assoc_array *array, pr_devel("-->%s()\n", __func__); - cursor = READ_ONCE(array->root); + cursor = READ_ONCE(array->root); /* Address dependency. */ if (!cursor) return assoc_array_walk_tree_empty; @@ -216,11 +208,9 @@ jumped: consider_node: node = assoc_array_ptr_to_node(cursor); - smp_read_barrier_depends(); - slot = segments >> (level & ASSOC_ARRAY_KEY_CHUNK_MASK); slot &= ASSOC_ARRAY_FAN_MASK; - ptr = READ_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */ pr_devel("consider slot %x [ix=%d type=%lu]\n", slot, level, (unsigned long)ptr & 3); @@ -254,7 +244,6 @@ consider_node: cursor = ptr; follow_shortcut: shortcut = assoc_array_ptr_to_shortcut(cursor); - smp_read_barrier_depends(); pr_devel("shortcut to %d\n", shortcut->skip_to_level); sc_level = level + ASSOC_ARRAY_LEVEL_STEP; BUG_ON(sc_level > shortcut->skip_to_level); @@ -294,7 +283,7 @@ follow_shortcut: } while (sc_level < shortcut->skip_to_level); /* The shortcut matches the leaf's index to this point. */ - cursor = READ_ONCE(shortcut->next_node); + cursor = READ_ONCE(shortcut->next_node); /* Address dependency. */ if (((level ^ sc_level) & ~ASSOC_ARRAY_KEY_CHUNK_MASK) != 0) { level = sc_level; goto jumped; @@ -331,20 +320,18 @@ void *assoc_array_find(const struct assoc_array *array, return NULL; node = result.terminal_node.node; - smp_read_barrier_depends(); /* If the target key is available to us, it's has to be pointed to by * the terminal node. */ for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) { - ptr = READ_ONCE(node->slots[slot]); + ptr = READ_ONCE(node->slots[slot]); /* Address dependency. */ if (ptr && assoc_array_ptr_is_leaf(ptr)) { /* We need a barrier between the read of the pointer * and dereferencing the pointer - but only if we are * actually going to dereference it. */ leaf = assoc_array_ptr_to_leaf(ptr); - smp_read_barrier_depends(); if (ops->compare_object(leaf, index_key)) return (void *)leaf; } diff --git a/lib/chacha20.c b/lib/chacha20.c index 250ceed9ec9a..c1cc50fb68c9 100644 --- a/lib/chacha20.c +++ b/lib/chacha20.c @@ -16,12 +16,7 @@ #include <asm/unaligned.h> #include <crypto/chacha20.h> -static inline u32 rotl32(u32 v, u8 n) -{ - return (v << n) | (v >> (sizeof(v) * 8 - n)); -} - -extern void chacha20_block(u32 *state, void *stream) +void chacha20_block(u32 *state, u32 *stream) { u32 x[16], *out = stream; int i; @@ -30,45 +25,45 @@ extern void chacha20_block(u32 *state, void *stream) x[i] = state[i]; for (i = 0; i < 20; i += 2) { - x[0] += x[4]; x[12] = rotl32(x[12] ^ x[0], 16); - x[1] += x[5]; x[13] = rotl32(x[13] ^ x[1], 16); - x[2] += x[6]; x[14] = rotl32(x[14] ^ x[2], 16); - x[3] += x[7]; x[15] = rotl32(x[15] ^ x[3], 16); + x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 16); + x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 16); + x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 16); + x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 16); - x[8] += x[12]; x[4] = rotl32(x[4] ^ x[8], 12); - x[9] += x[13]; x[5] = rotl32(x[5] ^ x[9], 12); - x[10] += x[14]; x[6] = rotl32(x[6] ^ x[10], 12); - x[11] += x[15]; x[7] = rotl32(x[7] ^ x[11], 12); + x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 12); + x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 12); + x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 12); + x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 12); - x[0] += x[4]; x[12] = rotl32(x[12] ^ x[0], 8); - x[1] += x[5]; x[13] = rotl32(x[13] ^ x[1], 8); - x[2] += x[6]; x[14] = rotl32(x[14] ^ x[2], 8); - x[3] += x[7]; x[15] = rotl32(x[15] ^ x[3], 8); + x[0] += x[4]; x[12] = rol32(x[12] ^ x[0], 8); + x[1] += x[5]; x[13] = rol32(x[13] ^ x[1], 8); + x[2] += x[6]; x[14] = rol32(x[14] ^ x[2], 8); + x[3] += x[7]; x[15] = rol32(x[15] ^ x[3], 8); - x[8] += x[12]; x[4] = rotl32(x[4] ^ x[8], 7); - x[9] += x[13]; x[5] = rotl32(x[5] ^ x[9], 7); - x[10] += x[14]; x[6] = rotl32(x[6] ^ x[10], 7); - x[11] += x[15]; x[7] = rotl32(x[7] ^ x[11], 7); + x[8] += x[12]; x[4] = rol32(x[4] ^ x[8], 7); + x[9] += x[13]; x[5] = rol32(x[5] ^ x[9], 7); + x[10] += x[14]; x[6] = rol32(x[6] ^ x[10], 7); + x[11] += x[15]; x[7] = rol32(x[7] ^ x[11], 7); - x[0] += x[5]; x[15] = rotl32(x[15] ^ x[0], 16); - x[1] += x[6]; x[12] = rotl32(x[12] ^ x[1], 16); - x[2] += x[7]; x[13] = rotl32(x[13] ^ x[2], 16); - x[3] += x[4]; x[14] = rotl32(x[14] ^ x[3], 16); + x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 16); + x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 16); + x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 16); + x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 16); - x[10] += x[15]; x[5] = rotl32(x[5] ^ x[10], 12); - x[11] += x[12]; x[6] = rotl32(x[6] ^ x[11], 12); - x[8] += x[13]; x[7] = rotl32(x[7] ^ x[8], 12); - x[9] += x[14]; x[4] = rotl32(x[4] ^ x[9], 12); + x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 12); + x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 12); + x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 12); + x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 12); - x[0] += x[5]; x[15] = rotl32(x[15] ^ x[0], 8); - x[1] += x[6]; x[12] = rotl32(x[12] ^ x[1], 8); - x[2] += x[7]; x[13] = rotl32(x[13] ^ x[2], 8); - x[3] += x[4]; x[14] = rotl32(x[14] ^ x[3], 8); + x[0] += x[5]; x[15] = rol32(x[15] ^ x[0], 8); + x[1] += x[6]; x[12] = rol32(x[12] ^ x[1], 8); + x[2] += x[7]; x[13] = rol32(x[13] ^ x[2], 8); + x[3] += x[4]; x[14] = rol32(x[14] ^ x[3], 8); - x[10] += x[15]; x[5] = rotl32(x[5] ^ x[10], 7); - x[11] += x[12]; x[6] = rotl32(x[6] ^ x[11], 7); - x[8] += x[13]; x[7] = rotl32(x[7] ^ x[8], 7); - x[9] += x[14]; x[4] = rotl32(x[4] ^ x[9], 7); + x[10] += x[15]; x[5] = rol32(x[5] ^ x[10], 7); + x[11] += x[12]; x[6] = rol32(x[6] ^ x[11], 7); + x[8] += x[13]; x[7] = rol32(x[7] ^ x[8], 7); + x[9] += x[14]; x[4] = rol32(x[4] ^ x[9], 7); } for (i = 0; i < ARRAY_SIZE(x); i++) diff --git a/lib/crc-ccitt.c b/lib/crc-ccitt.c index 7f6dd68d2d09..d873b34039ff 100644 --- a/lib/crc-ccitt.c +++ b/lib/crc-ccitt.c @@ -51,8 +51,49 @@ u16 const crc_ccitt_table[256] = { }; EXPORT_SYMBOL(crc_ccitt_table); +/* + * Similar table to calculate CRC16 variant known as CRC-CCITT-FALSE + * Reflected bits order, does not augment final value. + */ +u16 const crc_ccitt_false_table[256] = { + 0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50A5, 0x60C6, 0x70E7, + 0x8108, 0x9129, 0xA14A, 0xB16B, 0xC18C, 0xD1AD, 0xE1CE, 0xF1EF, + 0x1231, 0x0210, 0x3273, 0x2252, 0x52B5, 0x4294, 0x72F7, 0x62D6, + 0x9339, 0x8318, 0xB37B, 0xA35A, 0xD3BD, 0xC39C, 0xF3FF, 0xE3DE, + 0x2462, 0x3443, 0x0420, 0x1401, 0x64E6, 0x74C7, 0x44A4, 0x5485, + 0xA56A, 0xB54B, 0x8528, 0x9509, 0xE5EE, 0xF5CF, 0xC5AC, 0xD58D, + 0x3653, 0x2672, 0x1611, 0x0630, 0x76D7, 0x66F6, 0x5695, 0x46B4, + 0xB75B, 0xA77A, 0x9719, 0x8738, 0xF7DF, 0xE7FE, 0xD79D, 0xC7BC, + 0x48C4, 0x58E5, 0x6886, 0x78A7, 0x0840, 0x1861, 0x2802, 0x3823, + 0xC9CC, 0xD9ED, 0xE98E, 0xF9AF, 0x8948, 0x9969, 0xA90A, 0xB92B, + 0x5AF5, 0x4AD4, 0x7AB7, 0x6A96, 0x1A71, 0x0A50, 0x3A33, 0x2A12, + 0xDBFD, 0xCBDC, 0xFBBF, 0xEB9E, 0x9B79, 0x8B58, 0xBB3B, 0xAB1A, + 0x6CA6, 0x7C87, 0x4CE4, 0x5CC5, 0x2C22, 0x3C03, 0x0C60, 0x1C41, + 0xEDAE, 0xFD8F, 0xCDEC, 0xDDCD, 0xAD2A, 0xBD0B, 0x8D68, 0x9D49, + 0x7E97, 0x6EB6, 0x5ED5, 0x4EF4, 0x3E13, 0x2E32, 0x1E51, 0x0E70, + 0xFF9F, 0xEFBE, 0xDFDD, 0xCFFC, 0xBF1B, 0xAF3A, 0x9F59, 0x8F78, + 0x9188, 0x81A9, 0xB1CA, 0xA1EB, 0xD10C, 0xC12D, 0xF14E, 0xE16F, + 0x1080, 0x00A1, 0x30C2, 0x20E3, 0x5004, 0x4025, 0x7046, 0x6067, + 0x83B9, 0x9398, 0xA3FB, 0xB3DA, 0xC33D, 0xD31C, 0xE37F, 0xF35E, + 0x02B1, 0x1290, 0x22F3, 0x32D2, 0x4235, 0x5214, 0x6277, 0x7256, + 0xB5EA, 0xA5CB, 0x95A8, 0x8589, 0xF56E, 0xE54F, 0xD52C, 0xC50D, + 0x34E2, 0x24C3, 0x14A0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405, + 0xA7DB, 0xB7FA, 0x8799, 0x97B8, 0xE75F, 0xF77E, 0xC71D, 0xD73C, + 0x26D3, 0x36F2, 0x0691, 0x16B0, 0x6657, 0x7676, 0x4615, 0x5634, + 0xD94C, 0xC96D, 0xF90E, 0xE92F, 0x99C8, 0x89E9, 0xB98A, 0xA9AB, + 0x5844, 0x4865, 0x7806, 0x6827, 0x18C0, 0x08E1, 0x3882, 0x28A3, + 0xCB7D, 0xDB5C, 0xEB3F, 0xFB1E, 0x8BF9, 0x9BD8, 0xABBB, 0xBB9A, + 0x4A75, 0x5A54, 0x6A37, 0x7A16, 0x0AF1, 0x1AD0, 0x2AB3, 0x3A92, + 0xFD2E, 0xED0F, 0xDD6C, 0xCD4D, 0xBDAA, 0xAD8B, 0x9DE8, 0x8DC9, + 0x7C26, 0x6C07, 0x5C64, 0x4C45, 0x3CA2, 0x2C83, 0x1CE0, 0x0CC1, + 0xEF1F, 0xFF3E, 0xCF5D, 0xDF7C, 0xAF9B, 0xBFBA, 0x8FD9, 0x9FF8, + 0x6E17, 0x7E36, 0x4E55, 0x5E74, 0x2E93, 0x3EB2, 0x0ED1, 0x1EF0 +}; +EXPORT_SYMBOL(crc_ccitt_false_table); + /** - * crc_ccitt - recompute the CRC for the data buffer + * crc_ccitt - recompute the CRC (CRC-CCITT variant) for the data + * buffer * @crc: previous CRC value * @buffer: data pointer * @len: number of bytes in the buffer @@ -65,5 +106,20 @@ u16 crc_ccitt(u16 crc, u8 const *buffer, size_t len) } EXPORT_SYMBOL(crc_ccitt); +/** + * crc_ccitt_false - recompute the CRC (CRC-CCITT-FALSE variant) + * for the data buffer + * @crc: previous CRC value + * @buffer: data pointer + * @len: number of bytes in the buffer + */ +u16 crc_ccitt_false(u16 crc, u8 const *buffer, size_t len) +{ + while (len--) + crc = crc_ccitt_false_byte(crc, *buffer++); + return crc; +} +EXPORT_SYMBOL(crc_ccitt_false); + MODULE_DESCRIPTION("CRC-CCITT calculations"); MODULE_LICENSE("GPL"); diff --git a/lib/dma-direct.c b/lib/dma-direct.c new file mode 100644 index 000000000000..40b1f92f2214 --- /dev/null +++ b/lib/dma-direct.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DMA operations that map physical memory directly without using an IOMMU or + * flushing caches. + */ +#include <linux/export.h> +#include <linux/mm.h> +#include <linux/dma-direct.h> +#include <linux/scatterlist.h> +#include <linux/dma-contiguous.h> +#include <linux/pfn.h> + +#define DIRECT_MAPPING_ERROR 0 + +/* + * Most architectures use ZONE_DMA for the first 16 Megabytes, but + * some use it for entirely different regions: + */ +#ifndef ARCH_ZONE_DMA_BITS +#define ARCH_ZONE_DMA_BITS 24 +#endif + +static bool +check_addr(struct device *dev, dma_addr_t dma_addr, size_t size, + const char *caller) +{ + if (unlikely(dev && !dma_capable(dev, dma_addr, size))) { + if (*dev->dma_mask >= DMA_BIT_MASK(32)) { + dev_err(dev, + "%s: overflow %pad+%zu of device mask %llx\n", + caller, &dma_addr, size, *dev->dma_mask); + } + return false; + } + return true; +} + +static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) +{ + return phys_to_dma(dev, phys) + size - 1 <= dev->coherent_dma_mask; +} + +void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + int page_order = get_order(size); + struct page *page = NULL; + + /* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */ + if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) + gfp |= GFP_DMA; + if (dev->coherent_dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) + gfp |= GFP_DMA32; + +again: + /* CMA can be used only in the context which permits sleeping */ + if (gfpflags_allow_blocking(gfp)) { + page = dma_alloc_from_contiguous(dev, count, page_order, gfp); + if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + dma_release_from_contiguous(dev, page, count); + page = NULL; + } + } + if (!page) + page = alloc_pages_node(dev_to_node(dev), gfp, page_order); + + if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { + __free_pages(page, page_order); + page = NULL; + + if (dev->coherent_dma_mask < DMA_BIT_MASK(32) && + !(gfp & GFP_DMA)) { + gfp = (gfp & ~GFP_DMA32) | GFP_DMA; + goto again; + } + } + + if (!page) + return NULL; + + *dma_handle = phys_to_dma(dev, page_to_phys(page)); + memset(page_address(page), 0, size); + return page_address(page); +} + +void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t dma_addr, unsigned long attrs) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + + if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count)) + free_pages((unsigned long)cpu_addr, get_order(size)); +} + +static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + dma_addr_t dma_addr = phys_to_dma(dev, page_to_phys(page)) + offset; + + if (!check_addr(dev, dma_addr, size, __func__)) + return DIRECT_MAPPING_ERROR; + return dma_addr; +} + +static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + int i; + struct scatterlist *sg; + + for_each_sg(sgl, sg, nents, i) { + BUG_ON(!sg_page(sg)); + + sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg)); + if (!check_addr(dev, sg_dma_address(sg), sg->length, __func__)) + return 0; + sg_dma_len(sg) = sg->length; + } + + return nents; +} + +int dma_direct_supported(struct device *dev, u64 mask) +{ +#ifdef CONFIG_ZONE_DMA + if (mask < DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) + return 0; +#else + /* + * Because 32-bit DMA masks are so common we expect every architecture + * to be able to satisfy them - either by not supporting more physical + * memory, or by providing a ZONE_DMA32. If neither is the case, the + * architecture needs to use an IOMMU instead of the direct mapping. + */ + if (mask < DMA_BIT_MASK(32)) + return 0; +#endif + return 1; +} + +static int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr == DIRECT_MAPPING_ERROR; +} + +const struct dma_map_ops dma_direct_ops = { + .alloc = dma_direct_alloc, + .free = dma_direct_free, + .map_page = dma_direct_map_page, + .map_sg = dma_direct_map_sg, + .dma_supported = dma_direct_supported, + .mapping_error = dma_direct_mapping_error, +}; +EXPORT_SYMBOL(dma_direct_ops); diff --git a/lib/dma-noop.c b/lib/dma-noop.c deleted file mode 100644 index a10185b0c2d4..000000000000 --- a/lib/dma-noop.c +++ /dev/null @@ -1,68 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * lib/dma-noop.c - * - * DMA operations that map to physical addresses without flushing memory. - */ -#include <linux/export.h> -#include <linux/mm.h> -#include <linux/dma-mapping.h> -#include <linux/scatterlist.h> -#include <linux/pfn.h> - -static void *dma_noop_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, - unsigned long attrs) -{ - void *ret; - - ret = (void *)__get_free_pages(gfp, get_order(size)); - if (ret) - *dma_handle = virt_to_phys(ret) - PFN_PHYS(dev->dma_pfn_offset); - - return ret; -} - -static void dma_noop_free(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t dma_addr, - unsigned long attrs) -{ - free_pages((unsigned long)cpu_addr, get_order(size)); -} - -static dma_addr_t dma_noop_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - return page_to_phys(page) + offset - PFN_PHYS(dev->dma_pfn_offset); -} - -static int dma_noop_map_sg(struct device *dev, struct scatterlist *sgl, int nents, - enum dma_data_direction dir, - unsigned long attrs) -{ - int i; - struct scatterlist *sg; - - for_each_sg(sgl, sg, nents, i) { - dma_addr_t offset = PFN_PHYS(dev->dma_pfn_offset); - void *va; - - BUG_ON(!sg_page(sg)); - va = sg_virt(sg); - sg_dma_address(sg) = (dma_addr_t)virt_to_phys(va) - offset; - sg_dma_len(sg) = sg->length; - } - - return nents; -} - -const struct dma_map_ops dma_noop_ops = { - .alloc = dma_noop_alloc, - .free = dma_noop_free, - .map_page = dma_noop_map_page, - .map_sg = dma_noop_map_sg, -}; - -EXPORT_SYMBOL(dma_noop_ops); diff --git a/lib/kobject.c b/lib/kobject.c index 763d70a18941..06b849eee0ca 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -1039,6 +1039,7 @@ void *kobj_ns_grab_current(enum kobj_ns_type type) return ns; } +EXPORT_SYMBOL_GPL(kobj_ns_grab_current); const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk) { @@ -1074,3 +1075,4 @@ void kobj_ns_drop(enum kobj_ns_type type, void *ns) kobj_ns_ops_tbl[type]->drop_ns(ns); spin_unlock(&kobj_ns_type_lock); } +EXPORT_SYMBOL_GPL(kobj_ns_drop); diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index fe03c6d52761..30e7dd88148b 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -197,10 +197,10 @@ static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref) atomic_long_add(PERCPU_COUNT_BIAS, &ref->count); /* - * Restore per-cpu operation. smp_store_release() is paired with - * smp_read_barrier_depends() in __ref_is_percpu() and guarantees - * that the zeroing is visible to all percpu accesses which can see - * the following __PERCPU_REF_ATOMIC clearing. + * Restore per-cpu operation. smp_store_release() is paired + * with READ_ONCE() in __ref_is_percpu() and guarantees that the + * zeroing is visible to all percpu accesses which can see the + * following __PERCPU_REF_ATOMIC clearing. */ for_each_possible_cpu(cpu) *per_cpu_ptr(percpu_count, cpu) = 0; diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 80aa8d5463fa..42b5ca0acf93 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -462,7 +462,7 @@ static void sbq_wake_up(struct sbitmap_queue *sbq) */ atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wait_cnt + wake_batch); sbq_index_atomic_inc(&sbq->wake_index); - wake_up(&ws->wait); + wake_up_nr(&ws->wait, wake_batch); } } diff --git a/lib/scatterlist.c b/lib/scatterlist.c index 7c1c55f7daaa..53728d391d3a 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -474,6 +474,133 @@ int sg_alloc_table_from_pages(struct sg_table *sgt, struct page **pages, } EXPORT_SYMBOL(sg_alloc_table_from_pages); +#ifdef CONFIG_SGL_ALLOC + +/** + * sgl_alloc_order - allocate a scatterlist and its pages + * @length: Length in bytes of the scatterlist. Must be at least one + * @order: Second argument for alloc_pages() + * @chainable: Whether or not to allocate an extra element in the scatterlist + * for scatterlist chaining purposes + * @gfp: Memory allocation flags + * @nent_p: [out] Number of entries in the scatterlist that have pages + * + * Returns: A pointer to an initialized scatterlist or %NULL upon failure. + */ +struct scatterlist *sgl_alloc_order(unsigned long long length, + unsigned int order, bool chainable, + gfp_t gfp, unsigned int *nent_p) +{ + struct scatterlist *sgl, *sg; + struct page *page; + unsigned int nent, nalloc; + u32 elem_len; + + nent = round_up(length, PAGE_SIZE << order) >> (PAGE_SHIFT + order); + /* Check for integer overflow */ + if (length > (nent << (PAGE_SHIFT + order))) + return NULL; + nalloc = nent; + if (chainable) { + /* Check for integer overflow */ + if (nalloc + 1 < nalloc) + return NULL; + nalloc++; + } + sgl = kmalloc_array(nalloc, sizeof(struct scatterlist), + (gfp & ~GFP_DMA) | __GFP_ZERO); + if (!sgl) + return NULL; + + sg_init_table(sgl, nalloc); + sg = sgl; + while (length) { + elem_len = min_t(u64, length, PAGE_SIZE << order); + page = alloc_pages(gfp, order); + if (!page) { + sgl_free(sgl); + return NULL; + } + + sg_set_page(sg, page, elem_len, 0); + length -= elem_len; + sg = sg_next(sg); + } + WARN_ONCE(length, "length = %lld\n", length); + if (nent_p) + *nent_p = nent; + return sgl; +} +EXPORT_SYMBOL(sgl_alloc_order); + +/** + * sgl_alloc - allocate a scatterlist and its pages + * @length: Length in bytes of the scatterlist + * @gfp: Memory allocation flags + * @nent_p: [out] Number of entries in the scatterlist + * + * Returns: A pointer to an initialized scatterlist or %NULL upon failure. + */ +struct scatterlist *sgl_alloc(unsigned long long length, gfp_t gfp, + unsigned int *nent_p) +{ + return sgl_alloc_order(length, 0, false, gfp, nent_p); +} +EXPORT_SYMBOL(sgl_alloc); + +/** + * sgl_free_n_order - free a scatterlist and its pages + * @sgl: Scatterlist with one or more elements + * @nents: Maximum number of elements to free + * @order: Second argument for __free_pages() + * + * Notes: + * - If several scatterlists have been chained and each chain element is + * freed separately then it's essential to set nents correctly to avoid that a + * page would get freed twice. + * - All pages in a chained scatterlist can be freed at once by setting @nents + * to a high number. + */ +void sgl_free_n_order(struct scatterlist *sgl, int nents, int order) +{ + struct scatterlist *sg; + struct page *page; + int i; + + for_each_sg(sgl, sg, nents, i) { + if (!sg) + break; + page = sg_page(sg); + if (page) + __free_pages(page, order); + } + kfree(sgl); +} +EXPORT_SYMBOL(sgl_free_n_order); + +/** + * sgl_free_order - free a scatterlist and its pages + * @sgl: Scatterlist with one or more elements + * @order: Second argument for __free_pages() + */ +void sgl_free_order(struct scatterlist *sgl, int order) +{ + sgl_free_n_order(sgl, INT_MAX, order); +} +EXPORT_SYMBOL(sgl_free_order); + +/** + * sgl_free - free a scatterlist and its pages + * @sgl: Scatterlist with one or more elements + */ +void sgl_free(struct scatterlist *sgl) +{ + sgl_free_order(sgl, 0); +} +EXPORT_SYMBOL(sgl_free); + +#endif /* CONFIG_SGL_ALLOC */ + void __sg_page_iter_start(struct sg_page_iter *piter, struct scatterlist *sglist, unsigned int nents, unsigned long pgoffset) diff --git a/lib/swiotlb.c b/lib/swiotlb.c index cea19aaf303c..c43ec2271469 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -18,7 +18,7 @@ */ #include <linux/cache.h> -#include <linux/dma-mapping.h> +#include <linux/dma-direct.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/spinlock.h> @@ -417,7 +417,7 @@ cleanup2: return -ENOMEM; } -void __init swiotlb_free(void) +void __init swiotlb_exit(void) { if (!io_tlb_orig_addr) return; @@ -586,7 +586,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, not_found: spin_unlock_irqrestore(&io_tlb_lock, flags); - if (printk_ratelimit()) + if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes)\n", size); return SWIOTLB_MAP_ERROR; found: @@ -605,7 +605,6 @@ found: return tlb_addr; } -EXPORT_SYMBOL_GPL(swiotlb_tbl_map_single); /* * Allocates bounce buffer and returns its kernel virtual address. @@ -675,7 +674,6 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, } spin_unlock_irqrestore(&io_tlb_lock, flags); } -EXPORT_SYMBOL_GPL(swiotlb_tbl_unmap_single); void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir, @@ -707,92 +705,107 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, BUG(); } } -EXPORT_SYMBOL_GPL(swiotlb_tbl_sync_single); + +static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr, + size_t size) +{ + u64 mask = DMA_BIT_MASK(32); + + if (dev && dev->coherent_dma_mask) + mask = dev->coherent_dma_mask; + return addr + size - 1 <= mask; +} + +static void * +swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle, + unsigned long attrs) +{ + phys_addr_t phys_addr; + + if (swiotlb_force == SWIOTLB_NO_FORCE) + goto out_warn; + + phys_addr = swiotlb_tbl_map_single(dev, + swiotlb_phys_to_dma(dev, io_tlb_start), + 0, size, DMA_FROM_DEVICE, 0); + if (phys_addr == SWIOTLB_MAP_ERROR) + goto out_warn; + + *dma_handle = swiotlb_phys_to_dma(dev, phys_addr); + if (dma_coherent_ok(dev, *dma_handle, size)) + goto out_unmap; + + memset(phys_to_virt(phys_addr), 0, size); + return phys_to_virt(phys_addr); + +out_unmap: + dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n", + (unsigned long long)(dev ? dev->coherent_dma_mask : 0), + (unsigned long long)*dma_handle); + + /* + * DMA_TO_DEVICE to avoid memcpy in unmap_single. + * DMA_ATTR_SKIP_CPU_SYNC is optional. + */ + swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); +out_warn: + if ((attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) { + dev_warn(dev, + "swiotlb: coherent allocation failed, size=%zu\n", + size); + dump_stack(); + } + return NULL; +} void * swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags) { - dma_addr_t dev_addr; - void *ret; int order = get_order(size); - u64 dma_mask = DMA_BIT_MASK(32); - - if (hwdev && hwdev->coherent_dma_mask) - dma_mask = hwdev->coherent_dma_mask; + unsigned long attrs = (flags & __GFP_NOWARN) ? DMA_ATTR_NO_WARN : 0; + void *ret; ret = (void *)__get_free_pages(flags, order); if (ret) { - dev_addr = swiotlb_virt_to_bus(hwdev, ret); - if (dev_addr + size - 1 > dma_mask) { - /* - * The allocated memory isn't reachable by the device. - */ - free_pages((unsigned long) ret, order); - ret = NULL; + *dma_handle = swiotlb_virt_to_bus(hwdev, ret); + if (dma_coherent_ok(hwdev, *dma_handle, size)) { + memset(ret, 0, size); + return ret; } + free_pages((unsigned long)ret, order); } - if (!ret) { - /* - * We are either out of memory or the device can't DMA to - * GFP_DMA memory; fall back on map_single(), which - * will grab memory from the lowest available address range. - */ - phys_addr_t paddr = map_single(hwdev, 0, size, - DMA_FROM_DEVICE, 0); - if (paddr == SWIOTLB_MAP_ERROR) - goto err_warn; - ret = phys_to_virt(paddr); - dev_addr = swiotlb_phys_to_dma(hwdev, paddr); - - /* Confirm address can be DMA'd by device */ - if (dev_addr + size - 1 > dma_mask) { - printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n", - (unsigned long long)dma_mask, - (unsigned long long)dev_addr); - - /* - * DMA_TO_DEVICE to avoid memcpy in unmap_single. - * The DMA_ATTR_SKIP_CPU_SYNC is optional. - */ - swiotlb_tbl_unmap_single(hwdev, paddr, - size, DMA_TO_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - goto err_warn; - } - } + return swiotlb_alloc_buffer(hwdev, size, dma_handle, attrs); +} +EXPORT_SYMBOL(swiotlb_alloc_coherent); - *dma_handle = dev_addr; - memset(ret, 0, size); +static bool swiotlb_free_buffer(struct device *dev, size_t size, + dma_addr_t dma_addr) +{ + phys_addr_t phys_addr = dma_to_phys(dev, dma_addr); - return ret; + WARN_ON_ONCE(irqs_disabled()); -err_warn: - pr_warn("swiotlb: coherent allocation failed for device %s size=%zu\n", - dev_name(hwdev), size); - dump_stack(); + if (!is_swiotlb_buffer(phys_addr)) + return false; - return NULL; + /* + * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single. + * DMA_ATTR_SKIP_CPU_SYNC is optional. + */ + swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + return true; } -EXPORT_SYMBOL(swiotlb_alloc_coherent); void swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dev_addr) { - phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); - - WARN_ON(irqs_disabled()); - if (!is_swiotlb_buffer(paddr)) + if (!swiotlb_free_buffer(hwdev, size, dev_addr)) free_pages((unsigned long)vaddr, get_order(size)); - else - /* - * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single. - * DMA_ATTR_SKIP_CPU_SYNC is optional. - */ - swiotlb_tbl_unmap_single(hwdev, paddr, size, DMA_TO_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); } EXPORT_SYMBOL(swiotlb_free_coherent); @@ -868,7 +881,6 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, return swiotlb_phys_to_dma(dev, io_tlb_overflow_buffer); } -EXPORT_SYMBOL_GPL(swiotlb_map_page); /* * Unmap a single streaming mode DMA translation. The dma_addr and size must @@ -909,7 +921,6 @@ void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, { unmap_single(hwdev, dev_addr, size, dir, attrs); } -EXPORT_SYMBOL_GPL(swiotlb_unmap_page); /* * Make physical memory consistent for a single streaming mode DMA translation @@ -947,7 +958,6 @@ swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, { swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU); } -EXPORT_SYMBOL(swiotlb_sync_single_for_cpu); void swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, @@ -955,7 +965,6 @@ swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, { swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE); } -EXPORT_SYMBOL(swiotlb_sync_single_for_device); /* * Map a set of buffers described by scatterlist in streaming mode for DMA. @@ -1007,7 +1016,6 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, } return nelems; } -EXPORT_SYMBOL(swiotlb_map_sg_attrs); /* * Unmap a set of streaming mode DMA translations. Again, cpu read rules @@ -1027,7 +1035,6 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs); } -EXPORT_SYMBOL(swiotlb_unmap_sg_attrs); /* * Make physical memory consistent for a set of streaming mode DMA translations @@ -1055,7 +1062,6 @@ swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, { swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU); } -EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu); void swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, @@ -1063,14 +1069,12 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, { swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE); } -EXPORT_SYMBOL(swiotlb_sync_sg_for_device); int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) { return (dma_addr == swiotlb_phys_to_dma(hwdev, io_tlb_overflow_buffer)); } -EXPORT_SYMBOL(swiotlb_dma_mapping_error); /* * Return whether the given device DMA address mask can be supported @@ -1083,4 +1087,49 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask) { return swiotlb_phys_to_dma(hwdev, io_tlb_end - 1) <= mask; } -EXPORT_SYMBOL(swiotlb_dma_supported); + +#ifdef CONFIG_DMA_DIRECT_OPS +void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, + gfp_t gfp, unsigned long attrs) +{ + void *vaddr; + + /* temporary workaround: */ + if (gfp & __GFP_NOWARN) + attrs |= DMA_ATTR_NO_WARN; + + /* + * Don't print a warning when the first allocation attempt fails. + * swiotlb_alloc_coherent() will print a warning when the DMA memory + * allocation ultimately failed. + */ + gfp |= __GFP_NOWARN; + + vaddr = dma_direct_alloc(dev, size, dma_handle, gfp, attrs); + if (!vaddr) + vaddr = swiotlb_alloc_buffer(dev, size, dma_handle, attrs); + return vaddr; +} + +void swiotlb_free(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_addr, unsigned long attrs) +{ + if (!swiotlb_free_buffer(dev, size, dma_addr)) + dma_direct_free(dev, size, vaddr, dma_addr, attrs); +} + +const struct dma_map_ops swiotlb_dma_ops = { + .mapping_error = swiotlb_dma_mapping_error, + .alloc = swiotlb_alloc, + .free = swiotlb_free, + .sync_single_for_cpu = swiotlb_sync_single_for_cpu, + .sync_single_for_device = swiotlb_sync_single_for_device, + .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, + .sync_sg_for_device = swiotlb_sync_sg_for_device, + .map_sg = swiotlb_map_sg_attrs, + .unmap_sg = swiotlb_unmap_sg_attrs, + .map_page = swiotlb_map_page, + .unmap_page = swiotlb_unmap_page, + .dma_supported = swiotlb_dma_supported, +}; +#endif /* CONFIG_DMA_DIRECT_OPS */ diff --git a/lib/usercopy.c b/lib/usercopy.c index 15e2e6fb060e..3744b2a8e591 100644 --- a/lib/usercopy.c +++ b/lib/usercopy.c @@ -20,7 +20,7 @@ EXPORT_SYMBOL(_copy_from_user); #endif #ifndef INLINE_COPY_TO_USER -unsigned long _copy_to_user(void *to, const void __user *from, unsigned long n) +unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (likely(access_ok(VERIFY_WRITE, to, n))) { |