diff options
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Kconfig | 43 | ||||
-rw-r--r-- | lib/Kconfig.debug | 19 | ||||
-rw-r--r-- | lib/Makefile | 3 | ||||
-rw-r--r-- | lib/dma-debug.c | 65 | ||||
-rw-r--r-- | lib/dma-direct.c | 32 | ||||
-rw-r--r-- | lib/dma-noncoherent.c | 102 | ||||
-rw-r--r-- | lib/errseq.c | 23 | ||||
-rw-r--r-- | lib/find_bit_benchmark.c | 7 | ||||
-rw-r--r-- | lib/iommu-common.c | 267 | ||||
-rw-r--r-- | lib/iommu-helper.c | 14 | ||||
-rw-r--r-- | lib/iov_iter.c | 4 | ||||
-rw-r--r-- | lib/kobject.c | 11 | ||||
-rw-r--r-- | lib/lockref.c | 28 | ||||
-rw-r--r-- | lib/radix-tree.c | 10 | ||||
-rw-r--r-- | lib/sbitmap.c | 113 | ||||
-rw-r--r-- | lib/sha256.c | 283 | ||||
-rw-r--r-- | lib/swiotlb.c | 19 | ||||
-rw-r--r-- | lib/test_bitmap.c | 21 | ||||
-rw-r--r-- | lib/textsearch.c | 40 | ||||
-rw-r--r-- | lib/vsprintf.c | 26 |
20 files changed, 710 insertions, 420 deletions
diff --git a/lib/Kconfig b/lib/Kconfig index 5fe577673b98..7a913937888b 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -429,15 +429,50 @@ config SGL_ALLOC bool default n +config NEED_SG_DMA_LENGTH + bool + +config NEED_DMA_MAP_STATE + bool + +config ARCH_DMA_ADDR_T_64BIT + def_bool 64BIT || PHYS_ADDR_T_64BIT + +config IOMMU_HELPER + bool + +config ARCH_HAS_SYNC_DMA_FOR_DEVICE + bool + +config ARCH_HAS_SYNC_DMA_FOR_CPU + bool + select NEED_DMA_MAP_STATE + config DMA_DIRECT_OPS bool - depends on HAS_DMA && (!64BIT || ARCH_DMA_ADDR_T_64BIT) - default n + depends on HAS_DMA + +config DMA_NONCOHERENT_OPS + bool + depends on HAS_DMA + select DMA_DIRECT_OPS + +config DMA_NONCOHERENT_MMAP + bool + depends on DMA_NONCOHERENT_OPS + +config DMA_NONCOHERENT_CACHE_SYNC + bool + depends on DMA_NONCOHERENT_OPS config DMA_VIRT_OPS bool - depends on HAS_DMA && (!64BIT || ARCH_DMA_ADDR_T_64BIT) - default n + depends on HAS_DMA + +config SWIOTLB + bool + select DMA_DIRECT_OPS + select NEED_DMA_MAP_STATE config CHECK_SIGNATURE bool diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c40c7b734cd1..76555479ae36 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1634,7 +1634,7 @@ config PROVIDE_OHCI1394_DMA_INIT config DMA_API_DEBUG bool "Enable debugging of DMA-API usage" - depends on HAVE_DMA_API_DEBUG + select NEED_DMA_MAP_STATE help Enable this option to debug the use of the DMA API by device drivers. With this option you will be able to detect common bugs in device @@ -1651,6 +1651,23 @@ config DMA_API_DEBUG If unsure, say N. +config DMA_API_DEBUG_SG + bool "Debug DMA scatter-gather usage" + default y + depends on DMA_API_DEBUG + help + Perform extra checking that callers of dma_map_sg() have respected the + appropriate segment length/boundary limits for the given device when + preparing DMA scatterlists. + + This is particularly likely to have been overlooked in cases where the + dma_map_sg() API is used for general bulk mapping of pages rather than + preparing literal scatter-gather descriptors, where there is a risk of + unexpected behaviour from DMA API implementations if the scatterlist + is technically out-of-spec. + + If unsure, say N. + menuconfig RUNTIME_TESTING_MENU bool "Runtime Testing" def_bool y diff --git a/lib/Makefile b/lib/Makefile index ce20696d5a92..9f18c8152281 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -30,6 +30,7 @@ lib-$(CONFIG_PRINTK) += dump_stack.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o lib-$(CONFIG_DMA_DIRECT_OPS) += dma-direct.o +lib-$(CONFIG_DMA_NONCOHERENT_OPS) += dma-noncoherent.o lib-$(CONFIG_DMA_VIRT_OPS) += dma-virt.o lib-y += kobject.o klist.o @@ -147,7 +148,7 @@ obj-$(CONFIG_AUDIT_GENERIC) += audit.o obj-$(CONFIG_AUDIT_COMPAT_GENERIC) += compat_audit.o obj-$(CONFIG_SWIOTLB) += swiotlb.o -obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o iommu-common.o +obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o diff --git a/lib/dma-debug.c b/lib/dma-debug.c index 7f5cdc1e6b29..c007d25bee09 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -41,6 +41,11 @@ #define HASH_FN_SHIFT 13 #define HASH_FN_MASK (HASH_SIZE - 1) +/* allow architectures to override this if absolutely required */ +#ifndef PREALLOC_DMA_DEBUG_ENTRIES +#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) +#endif + enum { dma_debug_single, dma_debug_page, @@ -127,7 +132,7 @@ static u32 min_free_entries; static u32 nr_total_entries; /* number of preallocated entries requested by kernel cmdline */ -static u32 req_entries; +static u32 nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES; /* debugfs dentry's for the stuff above */ static struct dentry *dma_debug_dent __read_mostly; @@ -439,7 +444,6 @@ void debug_dma_dump_mappings(struct device *dev) spin_unlock_irqrestore(&bucket->lock, flags); } } -EXPORT_SYMBOL(debug_dma_dump_mappings); /* * For each mapping (initial cacheline in the case of @@ -748,7 +752,6 @@ int dma_debug_resize_entries(u32 num_entries) return ret; } -EXPORT_SYMBOL(dma_debug_resize_entries); /* * DMA-API debugging init code @@ -1004,10 +1007,7 @@ void dma_debug_add_bus(struct bus_type *bus) bus_register_notifier(bus, nb); } -/* - * Let the architectures decide how many entries should be preallocated. - */ -void dma_debug_init(u32 num_entries) +static int dma_debug_init(void) { int i; @@ -1015,7 +1015,7 @@ void dma_debug_init(u32 num_entries) * called to set dma_debug_initialized */ if (global_disable) - return; + return 0; for (i = 0; i < HASH_SIZE; ++i) { INIT_LIST_HEAD(&dma_entry_hash[i].list); @@ -1026,17 +1026,14 @@ void dma_debug_init(u32 num_entries) pr_err("DMA-API: error creating debugfs entries - disabling\n"); global_disable = true; - return; + return 0; } - if (req_entries) - num_entries = req_entries; - - if (prealloc_memory(num_entries) != 0) { + if (prealloc_memory(nr_prealloc_entries) != 0) { pr_err("DMA-API: debugging out of memory error - disabled\n"); global_disable = true; - return; + return 0; } nr_total_entries = num_free_entries; @@ -1044,7 +1041,9 @@ void dma_debug_init(u32 num_entries) dma_debug_initialized = true; pr_info("DMA-API: debugging enabled by kernel config\n"); + return 0; } +core_initcall(dma_debug_init); static __init int dma_debug_cmdline(char *str) { @@ -1061,16 +1060,10 @@ static __init int dma_debug_cmdline(char *str) static __init int dma_debug_entries_cmdline(char *str) { - int res; - if (!str) return -EINVAL; - - res = get_option(&str, &req_entries); - - if (!res) - req_entries = 0; - + if (!get_option(&str, &nr_prealloc_entries)) + nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES; return 0; } @@ -1293,6 +1286,32 @@ out: put_hash_bucket(bucket, &flags); } +static void check_sg_segment(struct device *dev, struct scatterlist *sg) +{ +#ifdef CONFIG_DMA_API_DEBUG_SG + unsigned int max_seg = dma_get_max_seg_size(dev); + u64 start, end, boundary = dma_get_seg_boundary(dev); + + /* + * Either the driver forgot to set dma_parms appropriately, or + * whoever generated the list forgot to check them. + */ + if (sg->length > max_seg) + err_printk(dev, NULL, "DMA-API: mapping sg segment longer than device claims to support [len=%u] [max=%u]\n", + sg->length, max_seg); + /* + * In some cases this could potentially be the DMA API + * implementation's fault, but it would usually imply that + * the scatterlist was built inappropriately to begin with. + */ + start = sg_dma_address(sg); + end = start + sg_dma_len(sg) - 1; + if ((start ^ end) & ~boundary) + err_printk(dev, NULL, "DMA-API: mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n", + start, end, boundary); +#endif +} + void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, int direction, dma_addr_t dma_addr, bool map_single) @@ -1423,6 +1442,8 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s)); } + check_sg_segment(dev, s); + add_dma_entry(entry); } } diff --git a/lib/dma-direct.c b/lib/dma-direct.c index c0bba30fef0a..8be8106270c2 100644 --- a/lib/dma-direct.c +++ b/lib/dma-direct.c @@ -34,6 +34,13 @@ 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) { + dev_err(dev, + "%s: call on device without dma_mask\n", + caller); + return false; + } + if (*dev->dma_mask >= DMA_BIT_MASK(32)) { dev_err(dev, "%s: overflow %pad+%zu of device mask %llx\n", @@ -84,7 +91,15 @@ again: __free_pages(page, page_order); page = NULL; - if (dev->coherent_dma_mask < DMA_BIT_MASK(32) && + if (IS_ENABLED(CONFIG_ZONE_DMA32) && + dev->coherent_dma_mask < DMA_BIT_MASK(64) && + !(gfp & (GFP_DMA32 | GFP_DMA))) { + gfp |= GFP_DMA32; + goto again; + } + + if (IS_ENABLED(CONFIG_ZONE_DMA) && + dev->coherent_dma_mask < DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) { gfp = (gfp & ~GFP_DMA32) | GFP_DMA; goto again; @@ -120,7 +135,7 @@ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, free_pages((unsigned long)cpu_addr, page_order); } -static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, +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) { @@ -131,8 +146,8 @@ static dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, 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 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; @@ -164,10 +179,16 @@ int dma_direct_supported(struct device *dev, u64 mask) if (mask < DMA_BIT_MASK(32)) return 0; #endif + /* + * Various PCI/PCIe bridges have broken support for > 32bit DMA even + * if the device itself might support it. + */ + if (dev->dma_32bit_limit && mask > DMA_BIT_MASK(32)) + return 0; return 1; } -static int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr) +int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr) { return dma_addr == DIRECT_MAPPING_ERROR; } @@ -179,6 +200,5 @@ const struct dma_map_ops dma_direct_ops = { .map_sg = dma_direct_map_sg, .dma_supported = dma_direct_supported, .mapping_error = dma_direct_mapping_error, - .is_phys = 1, }; EXPORT_SYMBOL(dma_direct_ops); diff --git a/lib/dma-noncoherent.c b/lib/dma-noncoherent.c new file mode 100644 index 000000000000..79e9a757387f --- /dev/null +++ b/lib/dma-noncoherent.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018 Christoph Hellwig. + * + * DMA operations that map physical memory directly without providing cache + * coherence. + */ +#include <linux/export.h> +#include <linux/mm.h> +#include <linux/dma-direct.h> +#include <linux/dma-noncoherent.h> +#include <linux/scatterlist.h> + +static void dma_noncoherent_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir); +} + +static void dma_noncoherent_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); +} + +static dma_addr_t dma_noncoherent_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 addr; + + addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); + if (!dma_mapping_error(dev, addr) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(dev, page_to_phys(page) + offset, + size, dir); + return addr; +} + +static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + nents = dma_direct_map_sg(dev, sgl, nents, dir, attrs); + if (nents > 0 && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_noncoherent_sync_sg_for_device(dev, sgl, nents, dir); + return nents; +} + +#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU +static void dma_noncoherent_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir); +} + +static void dma_noncoherent_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + for_each_sg(sgl, sg, nents, i) + arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); +} + +static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_noncoherent_sync_single_for_cpu(dev, addr, size, dir); +} + +static void dma_noncoherent_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_noncoherent_sync_sg_for_cpu(dev, sgl, nents, dir); +} +#endif + +const struct dma_map_ops dma_noncoherent_ops = { + .alloc = arch_dma_alloc, + .free = arch_dma_free, + .mmap = arch_dma_mmap, + .sync_single_for_device = dma_noncoherent_sync_single_for_device, + .sync_sg_for_device = dma_noncoherent_sync_sg_for_device, + .map_page = dma_noncoherent_map_page, + .map_sg = dma_noncoherent_map_sg, +#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU + .sync_single_for_cpu = dma_noncoherent_sync_single_for_cpu, + .sync_sg_for_cpu = dma_noncoherent_sync_sg_for_cpu, + .unmap_page = dma_noncoherent_unmap_page, + .unmap_sg = dma_noncoherent_unmap_sg, +#endif + .dma_supported = dma_direct_supported, + .mapping_error = dma_direct_mapping_error, + .cache_sync = arch_dma_cache_sync, +}; +EXPORT_SYMBOL(dma_noncoherent_ops); diff --git a/lib/errseq.c b/lib/errseq.c index df782418b333..81f9e33aa7e7 100644 --- a/lib/errseq.c +++ b/lib/errseq.c @@ -111,27 +111,22 @@ EXPORT_SYMBOL(errseq_set); * errseq_sample() - Grab current errseq_t value. * @eseq: Pointer to errseq_t to be sampled. * - * This function allows callers to sample an errseq_t value, marking it as - * "seen" if required. + * This function allows callers to initialise their errseq_t variable. + * If the error has been "seen", new callers will not see an old error. + * If there is an unseen error in @eseq, the caller of this function will + * see it the next time it checks for an error. * + * Context: Any context. * Return: The current errseq value. */ errseq_t errseq_sample(errseq_t *eseq) { errseq_t old = READ_ONCE(*eseq); - errseq_t new = old; - /* - * For the common case of no errors ever having been set, we can skip - * marking the SEEN bit. Once an error has been set, the value will - * never go back to zero. - */ - if (old != 0) { - new |= ERRSEQ_SEEN; - if (old != new) - cmpxchg(eseq, old, new); - } - return new; + /* If nobody has seen this error yet, then we can be the first. */ + if (!(old & ERRSEQ_SEEN)) + old = 0; + return old; } EXPORT_SYMBOL(errseq_sample); diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c index 5985a25e6cbc..5367ffa5c18f 100644 --- a/lib/find_bit_benchmark.c +++ b/lib/find_bit_benchmark.c @@ -132,7 +132,12 @@ static int __init find_bit_test(void) test_find_next_bit(bitmap, BITMAP_LEN); test_find_next_zero_bit(bitmap, BITMAP_LEN); test_find_last_bit(bitmap, BITMAP_LEN); - test_find_first_bit(bitmap, BITMAP_LEN); + + /* + * test_find_first_bit() may take some time, so + * traverse only part of bitmap to avoid soft lockup. + */ + test_find_first_bit(bitmap, BITMAP_LEN / 10); test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); pr_err("\nStart testing find_bit() with sparse bitmap\n"); diff --git a/lib/iommu-common.c b/lib/iommu-common.c deleted file mode 100644 index 55b00de106b5..000000000000 --- a/lib/iommu-common.c +++ /dev/null @@ -1,267 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * IOMMU mmap management and range allocation functions. - * Based almost entirely upon the powerpc iommu allocator. - */ - -#include <linux/export.h> -#include <linux/bitmap.h> -#include <linux/bug.h> -#include <linux/iommu-helper.h> -#include <linux/iommu-common.h> -#include <linux/dma-mapping.h> -#include <linux/hash.h> - -static unsigned long iommu_large_alloc = 15; - -static DEFINE_PER_CPU(unsigned int, iommu_hash_common); - -static inline bool need_flush(struct iommu_map_table *iommu) -{ - return ((iommu->flags & IOMMU_NEED_FLUSH) != 0); -} - -static inline void set_flush(struct iommu_map_table *iommu) -{ - iommu->flags |= IOMMU_NEED_FLUSH; -} - -static inline void clear_flush(struct iommu_map_table *iommu) -{ - iommu->flags &= ~IOMMU_NEED_FLUSH; -} - -static void setup_iommu_pool_hash(void) -{ - unsigned int i; - static bool do_once; - - if (do_once) - return; - do_once = true; - for_each_possible_cpu(i) - per_cpu(iommu_hash_common, i) = hash_32(i, IOMMU_POOL_HASHBITS); -} - -/* - * Initialize iommu_pool entries for the iommu_map_table. `num_entries' - * is the number of table entries. If `large_pool' is set to true, - * the top 1/4 of the table will be set aside for pool allocations - * of more than iommu_large_alloc pages. - */ -void iommu_tbl_pool_init(struct iommu_map_table *iommu, - unsigned long num_entries, - u32 table_shift, - void (*lazy_flush)(struct iommu_map_table *), - bool large_pool, u32 npools, - bool skip_span_boundary_check) -{ - unsigned int start, i; - struct iommu_pool *p = &(iommu->large_pool); - - setup_iommu_pool_hash(); - if (npools == 0) - iommu->nr_pools = IOMMU_NR_POOLS; - else - iommu->nr_pools = npools; - BUG_ON(npools > IOMMU_NR_POOLS); - - iommu->table_shift = table_shift; - iommu->lazy_flush = lazy_flush; - start = 0; - if (skip_span_boundary_check) - iommu->flags |= IOMMU_NO_SPAN_BOUND; - if (large_pool) - iommu->flags |= IOMMU_HAS_LARGE_POOL; - - if (!large_pool) - iommu->poolsize = num_entries/iommu->nr_pools; - else - iommu->poolsize = (num_entries * 3 / 4)/iommu->nr_pools; - for (i = 0; i < iommu->nr_pools; i++) { - spin_lock_init(&(iommu->pools[i].lock)); - iommu->pools[i].start = start; - iommu->pools[i].hint = start; - start += iommu->poolsize; /* start for next pool */ - iommu->pools[i].end = start - 1; - } - if (!large_pool) - return; - /* initialize large_pool */ - spin_lock_init(&(p->lock)); - p->start = start; - p->hint = p->start; - p->end = num_entries; -} -EXPORT_SYMBOL(iommu_tbl_pool_init); - -unsigned long iommu_tbl_range_alloc(struct device *dev, - struct iommu_map_table *iommu, - unsigned long npages, - unsigned long *handle, - unsigned long mask, - unsigned int align_order) -{ - unsigned int pool_hash = __this_cpu_read(iommu_hash_common); - unsigned long n, end, start, limit, boundary_size; - struct iommu_pool *pool; - int pass = 0; - unsigned int pool_nr; - unsigned int npools = iommu->nr_pools; - unsigned long flags; - bool large_pool = ((iommu->flags & IOMMU_HAS_LARGE_POOL) != 0); - bool largealloc = (large_pool && npages > iommu_large_alloc); - unsigned long shift; - unsigned long align_mask = 0; - - if (align_order > 0) - align_mask = ~0ul >> (BITS_PER_LONG - align_order); - - /* Sanity check */ - if (unlikely(npages == 0)) { - WARN_ON_ONCE(1); - return IOMMU_ERROR_CODE; - } - - if (largealloc) { - pool = &(iommu->large_pool); - pool_nr = 0; /* to keep compiler happy */ - } else { - /* pick out pool_nr */ - pool_nr = pool_hash & (npools - 1); - pool = &(iommu->pools[pool_nr]); - } - spin_lock_irqsave(&pool->lock, flags); - - again: - if (pass == 0 && handle && *handle && - (*handle >= pool->start) && (*handle < pool->end)) - start = *handle; - else - start = pool->hint; - - limit = pool->end; - - /* The case below can happen if we have a small segment appended - * to a large, or when the previous alloc was at the very end of - * the available space. If so, go back to the beginning. If a - * flush is needed, it will get done based on the return value - * from iommu_area_alloc() below. - */ - if (start >= limit) - start = pool->start; - shift = iommu->table_map_base >> iommu->table_shift; - if (limit + shift > mask) { - limit = mask - shift + 1; - /* If we're constrained on address range, first try - * at the masked hint to avoid O(n) search complexity, - * but on second pass, start at 0 in pool 0. - */ - if ((start & mask) >= limit || pass > 0) { - spin_unlock(&(pool->lock)); - pool = &(iommu->pools[0]); - spin_lock(&(pool->lock)); - start = pool->start; - } else { - start &= mask; - } - } - - if (dev) - boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1, - 1 << iommu->table_shift); - else - boundary_size = ALIGN(1ULL << 32, 1 << iommu->table_shift); - - boundary_size = boundary_size >> iommu->table_shift; - /* - * if the skip_span_boundary_check had been set during init, we set - * things up so that iommu_is_span_boundary() merely checks if the - * (index + npages) < num_tsb_entries - */ - if ((iommu->flags & IOMMU_NO_SPAN_BOUND) != 0) { - shift = 0; - boundary_size = iommu->poolsize * iommu->nr_pools; - } - n = iommu_area_alloc(iommu->map, limit, start, npages, shift, - boundary_size, align_mask); - if (n == -1) { - if (likely(pass == 0)) { - /* First failure, rescan from the beginning. */ - pool->hint = pool->start; - set_flush(iommu); - pass++; - goto again; - } else if (!largealloc && pass <= iommu->nr_pools) { - spin_unlock(&(pool->lock)); - pool_nr = (pool_nr + 1) & (iommu->nr_pools - 1); - pool = &(iommu->pools[pool_nr]); - spin_lock(&(pool->lock)); - pool->hint = pool->start; - set_flush(iommu); - pass++; - goto again; - } else { - /* give up */ - n = IOMMU_ERROR_CODE; - goto bail; - } - } - if (iommu->lazy_flush && - (n < pool->hint || need_flush(iommu))) { - clear_flush(iommu); - iommu->lazy_flush(iommu); - } - - end = n + npages; - pool->hint = end; - - /* Update handle for SG allocations */ - if (handle) - *handle = end; -bail: - spin_unlock_irqrestore(&(pool->lock), flags); - - return n; -} -EXPORT_SYMBOL(iommu_tbl_range_alloc); - -static struct iommu_pool *get_pool(struct iommu_map_table *tbl, - unsigned long entry) -{ - struct iommu_pool *p; - unsigned long largepool_start = tbl->large_pool.start; - bool large_pool = ((tbl->flags & IOMMU_HAS_LARGE_POOL) != 0); - - /* The large pool is the last pool at the top of the table */ - if (large_pool && entry >= largepool_start) { - p = &tbl->large_pool; - } else { - unsigned int pool_nr = entry / tbl->poolsize; - - BUG_ON(pool_nr >= tbl->nr_pools); - p = &tbl->pools[pool_nr]; - } - return p; -} - -/* Caller supplies the index of the entry into the iommu map table - * itself when the mapping from dma_addr to the entry is not the - * default addr->entry mapping below. - */ -void iommu_tbl_range_free(struct iommu_map_table *iommu, u64 dma_addr, - unsigned long npages, unsigned long entry) -{ - struct iommu_pool *pool; - unsigned long flags; - unsigned long shift = iommu->table_shift; - - if (entry == IOMMU_ERROR_CODE) /* use default addr->entry mapping */ - entry = (dma_addr - iommu->table_map_base) >> shift; - pool = get_pool(iommu, entry); - - spin_lock_irqsave(&(pool->lock), flags); - bitmap_clear(iommu->map, entry, npages); - spin_unlock_irqrestore(&(pool->lock), flags); -} -EXPORT_SYMBOL(iommu_tbl_range_free); diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c index 23633c0fda4a..92a9f243c0e2 100644 --- a/lib/iommu-helper.c +++ b/lib/iommu-helper.c @@ -3,19 +3,8 @@ * IOMMU helper functions for the free area management */ -#include <linux/export.h> #include <linux/bitmap.h> -#include <linux/bug.h> - -int iommu_is_span_boundary(unsigned int index, unsigned int nr, - unsigned long shift, - unsigned long boundary_size) -{ - BUG_ON(!is_power_of_2(boundary_size)); - - shift = (shift + index) & (boundary_size - 1); - return shift + nr > boundary_size; -} +#include <linux/iommu-helper.h> unsigned long iommu_area_alloc(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, @@ -38,4 +27,3 @@ again: } return -1; } -EXPORT_SYMBOL(iommu_area_alloc); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 970212670b6a..fdae394172fa 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1012,7 +1012,7 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i) } EXPORT_SYMBOL(iov_iter_gap_alignment); -static inline size_t __pipe_get_pages(struct iov_iter *i, +static inline ssize_t __pipe_get_pages(struct iov_iter *i, size_t maxsize, struct page **pages, int idx, @@ -1102,7 +1102,7 @@ static ssize_t pipe_get_pages_alloc(struct iov_iter *i, size_t *start) { struct page **p; - size_t n; + ssize_t n; int idx; int npages; diff --git a/lib/kobject.c b/lib/kobject.c index e1d1f290bf35..18989b5b3b56 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -233,13 +233,12 @@ static int kobject_add_internal(struct kobject *kobj) /* be noisy on error issues */ if (error == -EEXIST) - WARN(1, - "%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n", - __func__, kobject_name(kobj)); + pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n", + __func__, kobject_name(kobj)); else - WARN(1, "%s failed for %s (error: %d parent: %s)\n", - __func__, kobject_name(kobj), error, - parent ? kobject_name(parent) : "'none'"); + pr_err("%s failed for %s (error: %d parent: %s)\n", + __func__, kobject_name(kobj), error, + parent ? kobject_name(parent) : "'none'"); } else kobj->state_in_sysfs = 1; diff --git a/lib/lockref.c b/lib/lockref.c index 47169ed7e964..3d468b53d4c9 100644 --- a/lib/lockref.c +++ b/lib/lockref.c @@ -81,6 +81,34 @@ int lockref_get_not_zero(struct lockref *lockref) EXPORT_SYMBOL(lockref_get_not_zero); /** + * lockref_put_not_zero - Decrements count unless count <= 1 before decrement + * @lockref: pointer to lockref structure + * Return: 1 if count updated successfully or 0 if count would become zero + */ +int lockref_put_not_zero(struct lockref *lockref) +{ + int retval; + + CMPXCHG_LOOP( + new.count--; + if (old.count <= 1) + return 0; + , + return 1; + ); + + spin_lock(&lockref->lock); + retval = 0; + if (lockref->count > 1) { + lockref->count--; + retval = 1; + } + spin_unlock(&lockref->lock); + return retval; +} +EXPORT_SYMBOL(lockref_put_not_zero); + +/** * lockref_get_or_lock - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero diff --git a/lib/radix-tree.c b/lib/radix-tree.c index da9e10c827df..a9e41aed6de4 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1612,11 +1612,9 @@ static void set_iter_tags(struct radix_tree_iter *iter, static void __rcu **skip_siblings(struct radix_tree_node **nodep, void __rcu **slot, struct radix_tree_iter *iter) { - void *sib = node_to_entry(slot - 1); - while (iter->index < iter->next_index) { *nodep = rcu_dereference_raw(*slot); - if (*nodep && *nodep != sib) + if (*nodep && !is_sibling_entry(iter->node, *nodep)) return slot; slot++; iter->index = __radix_tree_iter_add(iter, 1); @@ -1631,7 +1629,7 @@ void __rcu **__radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; - struct radix_tree_node *node = rcu_dereference_raw(*slot); + struct radix_tree_node *node; slot = skip_siblings(&node, slot, iter); @@ -2036,10 +2034,12 @@ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; - void __rcu **slot; + void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); + if (!slot) + return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; diff --git a/lib/sbitmap.c b/lib/sbitmap.c index e6a9c06ec70c..6fdc6267f4a8 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -270,18 +270,33 @@ void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m) } EXPORT_SYMBOL_GPL(sbitmap_bitmap_show); -static unsigned int sbq_calc_wake_batch(unsigned int depth) +static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq, + unsigned int depth) { unsigned int wake_batch; + unsigned int shallow_depth; /* * For each batch, we wake up one queue. We need to make sure that our - * batch size is small enough that the full depth of the bitmap is - * enough to wake up all of the queues. + * batch size is small enough that the full depth of the bitmap, + * potentially limited by a shallow depth, is enough to wake up all of + * the queues. + * + * Each full word of the bitmap has bits_per_word bits, and there might + * be a partial word. There are depth / bits_per_word full words and + * depth % bits_per_word bits left over. In bitwise arithmetic: + * + * bits_per_word = 1 << shift + * depth / bits_per_word = depth >> shift + * depth % bits_per_word = depth & ((1 << shift) - 1) + * + * Each word can be limited to sbq->min_shallow_depth bits. */ - wake_batch = SBQ_WAKE_BATCH; - if (wake_batch > depth / SBQ_WAIT_QUEUES) - wake_batch = max(1U, depth / SBQ_WAIT_QUEUES); + shallow_depth = min(1U << sbq->sb.shift, sbq->min_shallow_depth); + depth = ((depth >> sbq->sb.shift) * shallow_depth + + min(depth & ((1U << sbq->sb.shift) - 1), shallow_depth)); + wake_batch = clamp_t(unsigned int, depth / SBQ_WAIT_QUEUES, 1, + SBQ_WAKE_BATCH); return wake_batch; } @@ -307,7 +322,8 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, *per_cpu_ptr(sbq->alloc_hint, i) = prandom_u32() % depth; } - sbq->wake_batch = sbq_calc_wake_batch(depth); + sbq->min_shallow_depth = UINT_MAX; + sbq->wake_batch = sbq_calc_wake_batch(sbq, depth); atomic_set(&sbq->wake_index, 0); sbq->ws = kzalloc_node(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags, node); @@ -327,21 +343,28 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, } EXPORT_SYMBOL_GPL(sbitmap_queue_init_node); -void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth) +static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq, + unsigned int depth) { - unsigned int wake_batch = sbq_calc_wake_batch(depth); + unsigned int wake_batch = sbq_calc_wake_batch(sbq, depth); int i; if (sbq->wake_batch != wake_batch) { WRITE_ONCE(sbq->wake_batch, wake_batch); /* - * Pairs with the memory barrier in sbq_wake_up() to ensure that - * the batch size is updated before the wait counts. + * Pairs with the memory barrier in sbitmap_queue_wake_up() + * to ensure that the batch size is updated before the wait + * counts. */ smp_mb__before_atomic(); for (i = 0; i < SBQ_WAIT_QUEUES; i++) atomic_set(&sbq->ws[i].wait_cnt, 1); } +} + +void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth) +{ + sbitmap_queue_update_wake_batch(sbq, depth); sbitmap_resize(&sbq->sb, depth); } EXPORT_SYMBOL_GPL(sbitmap_queue_resize); @@ -380,6 +403,8 @@ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, unsigned int hint, depth; int nr; + WARN_ON_ONCE(shallow_depth < sbq->min_shallow_depth); + hint = this_cpu_read(*sbq->alloc_hint); depth = READ_ONCE(sbq->sb.depth); if (unlikely(hint >= depth)) { @@ -403,6 +428,14 @@ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, } EXPORT_SYMBOL_GPL(__sbitmap_queue_get_shallow); +void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq, + unsigned int min_shallow_depth) +{ + sbq->min_shallow_depth = min_shallow_depth; + sbitmap_queue_update_wake_batch(sbq, sbq->sb.depth); +} +EXPORT_SYMBOL_GPL(sbitmap_queue_min_shallow_depth); + static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) { int i, wake_index; @@ -425,52 +458,67 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq) return NULL; } -static void sbq_wake_up(struct sbitmap_queue *sbq) +static bool __sbq_wake_up(struct sbitmap_queue *sbq) { struct sbq_wait_state *ws; unsigned int wake_batch; int wait_cnt; - /* - * Pairs with the memory barrier in set_current_state() to ensure the - * proper ordering of clear_bit()/waitqueue_active() in the waker and - * test_and_set_bit_lock()/prepare_to_wait()/finish_wait() in the - * waiter. See the comment on waitqueue_active(). This is __after_atomic - * because we just did clear_bit_unlock() in the caller. - */ - smp_mb__after_atomic(); - ws = sbq_wake_ptr(sbq); if (!ws) - return; + return false; wait_cnt = atomic_dec_return(&ws->wait_cnt); if (wait_cnt <= 0) { + int ret; + wake_batch = READ_ONCE(sbq->wake_batch); + /* * Pairs with the memory barrier in sbitmap_queue_resize() to * ensure that we see the batch size update before the wait * count is reset. */ smp_mb__before_atomic(); + /* - * If there are concurrent callers to sbq_wake_up(), the last - * one to decrement the wait count below zero will bump it back - * up. If there is a concurrent resize, the count reset will - * either cause the cmpxchg to fail or overwrite after the - * cmpxchg. + * For concurrent callers of this, the one that failed the + * atomic_cmpxhcg() race should call this function again + * to wakeup a new batch on a different 'ws'. */ - atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wait_cnt + wake_batch); - sbq_index_atomic_inc(&sbq->wake_index); - wake_up_nr(&ws->wait, wake_batch); + ret = atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wake_batch); + if (ret == wait_cnt) { + sbq_index_atomic_inc(&sbq->wake_index); + wake_up_nr(&ws->wait, wake_batch); + return false; + } + + return true; } + + return false; +} + +void sbitmap_queue_wake_up(struct sbitmap_queue *sbq) +{ + while (__sbq_wake_up(sbq)) + ; } +EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up); void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, unsigned int cpu) { sbitmap_clear_bit_unlock(&sbq->sb, nr); - sbq_wake_up(sbq); + /* + * Pairs with the memory barrier in set_current_state() to ensure the + * proper ordering of clear_bit_unlock()/waitqueue_active() in the waker + * and test_and_set_bit_lock()/prepare_to_wait()/finish_wait() in the + * waiter. See the comment on waitqueue_active(). + */ + smp_mb__after_atomic(); + sbitmap_queue_wake_up(sbq); + if (likely(!sbq->round_robin && nr < sbq->sb.depth)) *per_cpu_ptr(sbq->alloc_hint, cpu) = nr; } @@ -482,7 +530,7 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq) /* * Pairs with the memory barrier in set_current_state() like in - * sbq_wake_up(). + * sbitmap_queue_wake_up(). */ smp_mb(); wake_index = atomic_read(&sbq->wake_index); @@ -528,5 +576,6 @@ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m) seq_puts(m, "}\n"); seq_printf(m, "round_robin=%d\n", sbq->round_robin); + seq_printf(m, "min_shallow_depth=%u\n", sbq->min_shallow_depth); } EXPORT_SYMBOL_GPL(sbitmap_queue_show); diff --git a/lib/sha256.c b/lib/sha256.c new file mode 100644 index 000000000000..4400c832e2aa --- /dev/null +++ b/lib/sha256.c @@ -0,0 +1,283 @@ +/* + * SHA-256, as specified in + * http://csrc.nist.gov/groups/STM/cavp/documents/shs/sha256-384-512.pdf + * + * SHA-256 code by Jean-Luc Cooke <jlcooke@certainkey.com>. + * + * Copyright (c) Jean-Luc Cooke <jlcooke@certainkey.com> + * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk> + * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> + * Copyright (c) 2014 Red Hat Inc. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +#include <linux/bitops.h> +#include <linux/sha256.h> +#include <linux/string.h> +#include <asm/byteorder.h> + +static inline u32 Ch(u32 x, u32 y, u32 z) +{ + return z ^ (x & (y ^ z)); +} + +static inline u32 Maj(u32 x, u32 y, u32 z) +{ + return (x & y) | (z & (x | y)); +} + +#define e0(x) (ror32(x, 2) ^ ror32(x, 13) ^ ror32(x, 22)) +#define e1(x) (ror32(x, 6) ^ ror32(x, 11) ^ ror32(x, 25)) +#define s0(x) (ror32(x, 7) ^ ror32(x, 18) ^ (x >> 3)) +#define s1(x) (ror32(x, 17) ^ ror32(x, 19) ^ (x >> 10)) + +static inline void LOAD_OP(int I, u32 *W, const u8 *input) +{ + W[I] = __be32_to_cpu(((__be32 *)(input))[I]); +} + +static inline void BLEND_OP(int I, u32 *W) +{ + W[I] = s1(W[I-2]) + W[I-7] + s0(W[I-15]) + W[I-16]; +} + +static void sha256_transform(u32 *state, const u8 *input) +{ + u32 a, b, c, d, e, f, g, h, t1, t2; + u32 W[64]; + int i; + + /* load the input */ + for (i = 0; i < 16; i++) + LOAD_OP(i, W, input); + + /* now blend */ + for (i = 16; i < 64; i++) + BLEND_OP(i, W); + + /* load the state into our registers */ + a = state[0]; b = state[1]; c = state[2]; d = state[3]; + e = state[4]; f = state[5]; g = state[6]; h = state[7]; + + /* now iterate */ + t1 = h + e1(e) + Ch(e, f, g) + 0x428a2f98 + W[0]; + t2 = e0(a) + Maj(a, b, c); d += t1; h = t1 + t2; + t1 = g + e1(d) + Ch(d, e, f) + 0x71374491 + W[1]; + t2 = e0(h) + Maj(h, a, b); c += t1; g = t1 + t2; + t1 = f + e1(c) + Ch(c, d, e) + 0xb5c0fbcf + W[2]; + t2 = e0(g) + Maj(g, h, a); b += t1; f = t1 + t2; + t1 = e + e1(b) + Ch(b, c, d) + 0xe9b5dba5 + W[3]; + t2 = e0(f) + Maj(f, g, h); a += t1; e = t1 + t2; + t1 = d + e1(a) + Ch(a, b, c) + 0x3956c25b + W[4]; + t2 = e0(e) + Maj(e, f, g); h += t1; d = t1 + t2; + t1 = c + e1(h) + Ch(h, a, b) + 0x59f111f1 + W[5]; + t2 = e0(d) + Maj(d, e, f); g += t1; c = t1 + t2; + t1 = b + e1(g) + Ch(g, h, a) + 0x923f82a4 + W[6]; + t2 = e0(c) + Maj(c, d, e); f += t1; b = t1 + t2; + t1 = a + e1(f) + Ch(f, g, h) + 0xab1c5ed5 + W[7]; + t2 = e0(b) + Maj(b, c, d); e += t1; a = t1 + t2; + + t1 = h + e1(e) + Ch(e, f, g) + 0xd807aa98 + W[8]; + t2 = e0(a) + Maj(a, b, c); d += t1; h = t1 + t2; + t1 = g + e1(d) + Ch(d, e, f) + 0x12835b01 + W[9]; + t2 = e0(h) + Maj(h, a, b); c += t1; g = t1 + t2; + t1 = f + e1(c) + Ch(c, d, e) + 0x243185be + W[10]; + t2 = e0(g) + Maj(g, h, a); b += t1; f = t1 + t2; + t1 = e + e1(b) + Ch(b, c, d) + 0x550c7dc3 + W[11]; + t2 = e0(f) + Maj(f, g, h); a += t1; e = t1 + t2; + t1 = d + e1(a) + Ch(a, b, c) + 0x72be5d74 + W[12]; + t2 = e0(e) + Maj(e, f, g); h += t1; d = t1 + t2; + t1 = c + e1(h) + Ch(h, a, b) + 0x80deb1fe + W[13]; + t2 = e0(d) + Maj(d, e, f); g += t1; c = t1 + t2; + t1 = b + e1(g) + Ch(g, h, a) + 0x9bdc06a7 + W[14]; + t2 = e0(c) + Maj(c, d, e); f += t1; b = t1 + t2; + t1 = a + e1(f) + Ch(f, g, h) + 0xc19bf174 + W[15]; + t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2; + + t1 = h + e1(e) + Ch(e, f, g) + 0xe49b69c1 + W[16]; + t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2; + t1 = g + e1(d) + Ch(d, e, f) + 0xefbe4786 + W[17]; + t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2; + t1 = f + e1(c) + Ch(c, d, e) + 0x0fc19dc6 + W[18]; + t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2; + t1 = e + e1(b) + Ch(b, c, d) + 0x240ca1cc + W[19]; + t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2; + t1 = d + e1(a) + Ch(a, b, c) + 0x2de92c6f + W[20]; + t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2; + t1 = c + e1(h) + Ch(h, a, b) + 0x4a7484aa + W[21]; + t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2; + t1 = b + e1(g) + Ch(g, h, a) + 0x5cb0a9dc + W[22]; + t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2; + t1 = a + e1(f) + Ch(f, g, h) + 0x76f988da + W[23]; + t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2; + + t1 = h + e1(e) + Ch(e, f, g) + 0x983e5152 + W[24]; + t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2; + t1 = g + e1(d) + Ch(d, e, f) + 0xa831c66d + W[25]; + t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2; + t1 = f + e1(c) + Ch(c, d, e) + 0xb00327c8 + W[26]; + t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2; + t1 = e + e1(b) + Ch(b, c, d) + 0xbf597fc7 + W[27]; + t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2; + t1 = d + e1(a) + Ch(a, b, c) + 0xc6e00bf3 + W[28]; + t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2; + t1 = c + e1(h) + Ch(h, a, b) + 0xd5a79147 + W[29]; + t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2; + t1 = b + e1(g) + Ch(g, h, a) + 0x06ca6351 + W[30]; + t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2; + t1 = a + e1(f) + Ch(f, g, h) + 0x14292967 + W[31]; + t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2; + + t1 = h + e1(e) + Ch(e, f, g) + 0x27b70a85 + W[32]; + t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2; + t1 = g + e1(d) + Ch(d, e, f) + 0x2e1b2138 + W[33]; + t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2; + t1 = f + e1(c) + Ch(c, d, e) + 0x4d2c6dfc + W[34]; + t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2; + t1 = e + e1(b) + Ch(b, c, d) + 0x53380d13 + W[35]; + t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2; + t1 = d + e1(a) + Ch(a, b, c) + 0x650a7354 + W[36]; + t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2; + t1 = c + e1(h) + Ch(h, a, b) + 0x766a0abb + W[37]; + t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2; + t1 = b + e1(g) + Ch(g, h, a) + 0x81c2c92e + W[38]; + t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2; + t1 = a + e1(f) + Ch(f, g, h) + 0x92722c85 + W[39]; + t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2; + + t1 = h + e1(e) + Ch(e, f, g) + 0xa2bfe8a1 + W[40]; + t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2; + t1 = g + e1(d) + Ch(d, e, f) + 0xa81a664b + W[41]; + t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2; + t1 = f + e1(c) + Ch(c, d, e) + 0xc24b8b70 + W[42]; + t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2; + t1 = e + e1(b) + Ch(b, c, d) + 0xc76c51a3 + W[43]; + t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2; + t1 = d + e1(a) + Ch(a, b, c) + 0xd192e819 + W[44]; + t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2; + t1 = c + e1(h) + Ch(h, a, b) + 0xd6990624 + W[45]; + t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2; + t1 = b + e1(g) + Ch(g, h, a) + 0xf40e3585 + W[46]; + t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2; + t1 = a + e1(f) + Ch(f, g, h) + 0x106aa070 + W[47]; + t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2; + + t1 = h + e1(e) + Ch(e, f, g) + 0x19a4c116 + W[48]; + t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2; + t1 = g + e1(d) + Ch(d, e, f) + 0x1e376c08 + W[49]; + t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2; + t1 = f + e1(c) + Ch(c, d, e) + 0x2748774c + W[50]; + t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2; + t1 = e + e1(b) + Ch(b, c, d) + 0x34b0bcb5 + W[51]; + t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2; + t1 = d + e1(a) + Ch(a, b, c) + 0x391c0cb3 + W[52]; + t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2; + t1 = c + e1(h) + Ch(h, a, b) + 0x4ed8aa4a + W[53]; + t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2; + t1 = b + e1(g) + Ch(g, h, a) + 0x5b9cca4f + W[54]; + t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2; + t1 = a + e1(f) + Ch(f, g, h) + 0x682e6ff3 + W[55]; + t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2; + + t1 = h + e1(e) + Ch(e, f, g) + 0x748f82ee + W[56]; + t2 = e0(a) + Maj(a, b, c); d += t1; h = t1+t2; + t1 = g + e1(d) + Ch(d, e, f) + 0x78a5636f + W[57]; + t2 = e0(h) + Maj(h, a, b); c += t1; g = t1+t2; + t1 = f + e1(c) + Ch(c, d, e) + 0x84c87814 + W[58]; + t2 = e0(g) + Maj(g, h, a); b += t1; f = t1+t2; + t1 = e + e1(b) + Ch(b, c, d) + 0x8cc70208 + W[59]; + t2 = e0(f) + Maj(f, g, h); a += t1; e = t1+t2; + t1 = d + e1(a) + Ch(a, b, c) + 0x90befffa + W[60]; + t2 = e0(e) + Maj(e, f, g); h += t1; d = t1+t2; + t1 = c + e1(h) + Ch(h, a, b) + 0xa4506ceb + W[61]; + t2 = e0(d) + Maj(d, e, f); g += t1; c = t1+t2; + t1 = b + e1(g) + Ch(g, h, a) + 0xbef9a3f7 + W[62]; + t2 = e0(c) + Maj(c, d, e); f += t1; b = t1+t2; + t1 = a + e1(f) + Ch(f, g, h) + 0xc67178f2 + W[63]; + t2 = e0(b) + Maj(b, c, d); e += t1; a = t1+t2; + + state[0] += a; state[1] += b; state[2] += c; state[3] += d; + state[4] += e; state[5] += f; state[6] += g; state[7] += h; + + /* clear any sensitive info... */ + a = b = c = d = e = f = g = h = t1 = t2 = 0; + memset(W, 0, 64 * sizeof(u32)); +} + +int sha256_init(struct sha256_state *sctx) +{ + sctx->state[0] = SHA256_H0; + sctx->state[1] = SHA256_H1; + sctx->state[2] = SHA256_H2; + sctx->state[3] = SHA256_H3; + sctx->state[4] = SHA256_H4; + sctx->state[5] = SHA256_H5; + sctx->state[6] = SHA256_H6; + sctx->state[7] = SHA256_H7; + sctx->count = 0; + + return 0; +} + +int sha256_update(struct sha256_state *sctx, const u8 *data, unsigned int len) +{ + unsigned int partial, done; + const u8 *src; + + partial = sctx->count & 0x3f; + sctx->count += len; + done = 0; + src = data; + + if ((partial + len) > 63) { + if (partial) { + done = -partial; + memcpy(sctx->buf + partial, data, done + 64); + src = sctx->buf; + } + + do { + sha256_transform(sctx->state, src); + done += 64; + src = data + done; + } while (done + 63 < len); + + partial = 0; + } + memcpy(sctx->buf + partial, src, len - done); + + return 0; +} + +int sha256_final(struct sha256_state *sctx, u8 *out) +{ + __be32 *dst = (__be32 *)out; + __be64 bits; + unsigned int index, pad_len; + int i; + static const u8 padding[64] = { 0x80, }; + + /* Save number of bits */ + bits = cpu_to_be64(sctx->count << 3); + + /* Pad out to 56 mod 64. */ + index = sctx->count & 0x3f; + pad_len = (index < 56) ? (56 - index) : ((64+56) - index); + sha256_update(sctx, padding, pad_len); + + /* Append length (before padding) */ + sha256_update(sctx, (const u8 *)&bits, sizeof(bits)); + + /* Store state in digest */ + for (i = 0; i < 8; i++) + dst[i] = cpu_to_be32(sctx->state[i]); + + /* Zeroize sensitive information. */ + memset(sctx, 0, sizeof(*sctx)); + + return 0; +} diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 47aeb04c1997..04b68d9dffac 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -593,9 +593,8 @@ found: } /* - * Allocates bounce buffer and returns its kernel virtual address. + * Allocates bounce buffer and returns its physical address. */ - static phys_addr_t map_single(struct device *hwdev, phys_addr_t phys, size_t size, enum dma_data_direction dir, unsigned long attrs) @@ -614,7 +613,7 @@ map_single(struct device *hwdev, phys_addr_t phys, size_t size, } /* - * dma_addr is the kernel virtual address of the bounce buffer to unmap. + * 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 size, enum dma_data_direction dir, @@ -692,7 +691,6 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, } } -#ifdef CONFIG_DMA_DIRECT_OPS static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr, size_t size) { @@ -714,12 +712,12 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle, phys_addr = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start), - 0, size, DMA_FROM_DEVICE, 0); + 0, size, DMA_FROM_DEVICE, attrs); if (phys_addr == SWIOTLB_MAP_ERROR) goto out_warn; *dma_handle = __phys_to_dma(dev, phys_addr); - if (dma_coherent_ok(dev, *dma_handle, size)) + if (!dma_coherent_ok(dev, *dma_handle, size)) goto out_unmap; memset(phys_to_virt(phys_addr), 0, size); @@ -727,7 +725,7 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle, 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)dev->coherent_dma_mask, (unsigned long long)*dma_handle); /* @@ -737,7 +735,7 @@ out_unmap: 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()) { + if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) { dev_warn(dev, "swiotlb: coherent allocation failed, size=%zu\n", size); @@ -764,7 +762,6 @@ static bool swiotlb_free_buffer(struct device *dev, size_t size, DMA_ATTR_SKIP_CPU_SYNC); return true; } -#endif static void swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir, @@ -1045,7 +1042,6 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask) return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask; } -#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) { @@ -1087,6 +1083,5 @@ const struct dma_map_ops swiotlb_dma_ops = { .unmap_sg = swiotlb_unmap_sg_attrs, .map_page = swiotlb_map_page, .unmap_page = swiotlb_unmap_page, - .dma_supported = swiotlb_dma_supported, + .dma_supported = dma_direct_supported, }; -#endif /* CONFIG_DMA_DIRECT_OPS */ diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index de16f7869fb1..6cd7d0740005 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -331,23 +331,32 @@ static void noinline __init test_mem_optimisations(void) unsigned int start, nbits; for (start = 0; start < 1024; start += 8) { - memset(bmap1, 0x5a, sizeof(bmap1)); - memset(bmap2, 0x5a, sizeof(bmap2)); for (nbits = 0; nbits < 1024 - start; nbits += 8) { + memset(bmap1, 0x5a, sizeof(bmap1)); + memset(bmap2, 0x5a, sizeof(bmap2)); + bitmap_set(bmap1, start, nbits); __bitmap_set(bmap2, start, nbits); - if (!bitmap_equal(bmap1, bmap2, 1024)) + if (!bitmap_equal(bmap1, bmap2, 1024)) { printk("set not equal %d %d\n", start, nbits); - if (!__bitmap_equal(bmap1, bmap2, 1024)) + failed_tests++; + } + if (!__bitmap_equal(bmap1, bmap2, 1024)) { printk("set not __equal %d %d\n", start, nbits); + failed_tests++; + } bitmap_clear(bmap1, start, nbits); __bitmap_clear(bmap2, start, nbits); - if (!bitmap_equal(bmap1, bmap2, 1024)) + if (!bitmap_equal(bmap1, bmap2, 1024)) { printk("clear not equal %d %d\n", start, nbits); - if (!__bitmap_equal(bmap1, bmap2, 1024)) + failed_tests++; + } + if (!__bitmap_equal(bmap1, bmap2, 1024)) { printk("clear not __equal %d %d\n", start, nbits); + failed_tests++; + } } } } diff --git a/lib/textsearch.c b/lib/textsearch.c index 0b79908dfe89..5939549c0e7b 100644 --- a/lib/textsearch.c +++ b/lib/textsearch.c @@ -10,7 +10,10 @@ * Pablo Neira Ayuso <pablo@netfilter.org> * * ========================================================================== - * + */ + +/** + * DOC: ts_intro * INTRODUCTION * * The textsearch infrastructure provides text searching facilities for @@ -19,7 +22,9 @@ * * ARCHITECTURE * - * User + * .. code-block:: none + * + * User * +----------------+ * | finish()|<--------------(6)-----------------+ * |get_next_block()|<--------------(5)---------------+ | @@ -33,21 +38,21 @@ * | (3)|----->| find()/next() |-----------+ | * | (7)|----->| destroy() |----------------------+ * +----------------+ +---------------+ - * - * (1) User configures a search by calling _prepare() specifying the - * search parameters such as the pattern and algorithm name. + * + * (1) User configures a search by calling textsearch_prepare() specifying + * the search parameters such as the pattern and algorithm name. * (2) Core requests the algorithm to allocate and initialize a search * configuration according to the specified parameters. - * (3) User starts the search(es) by calling _find() or _next() to - * fetch subsequent occurrences. A state variable is provided - * to the algorithm to store persistent variables. + * (3) User starts the search(es) by calling textsearch_find() or + * textsearch_next() to fetch subsequent occurrences. A state variable + * is provided to the algorithm to store persistent variables. * (4) Core eventually resets the search offset and forwards the find() * request to the algorithm. * (5) Algorithm calls get_next_block() provided by the user continuously * to fetch the data to be searched in block by block. * (6) Algorithm invokes finish() after the last call to get_next_block * to clean up any leftovers from get_next_block. (Optional) - * (7) User destroys the configuration by calling _destroy(). + * (7) User destroys the configuration by calling textsearch_destroy(). * (8) Core notifies the algorithm to destroy algorithm specific * allocations. (Optional) * @@ -62,9 +67,10 @@ * amount of times and even in parallel as long as a separate struct * ts_state variable is provided to every instance. * - * The actual search is performed by either calling textsearch_find_- - * continuous() for linear data or by providing an own get_next_block() - * implementation and calling textsearch_find(). Both functions return + * The actual search is performed by either calling + * textsearch_find_continuous() for linear data or by providing + * an own get_next_block() implementation and + * calling textsearch_find(). Both functions return * the position of the first occurrence of the pattern or UINT_MAX if * no match was found. Subsequent occurrences can be found by calling * textsearch_next() regardless of the linearity of the data. @@ -72,7 +78,7 @@ * Once you're done using a configuration it must be given back via * textsearch_destroy. * - * EXAMPLE + * EXAMPLE:: * * int pos; * struct ts_config *conf; @@ -87,13 +93,13 @@ * goto errout; * } * - * pos = textsearch_find_continuous(conf, &state, example, strlen(example)); + * pos = textsearch_find_continuous(conf, \&state, example, strlen(example)); * if (pos != UINT_MAX) - * panic("Oh my god, dancing chickens at %d\n", pos); + * panic("Oh my god, dancing chickens at \%d\n", pos); * * textsearch_destroy(conf); - * ========================================================================== */ +/* ========================================================================== */ #include <linux/module.h> #include <linux/types.h> @@ -225,7 +231,7 @@ static unsigned int get_linear_data(unsigned int consumed, const u8 **dst, * * Returns the position of first occurrence of the pattern or * %UINT_MAX if no occurrence was found. - */ + */ unsigned int textsearch_find_continuous(struct ts_config *conf, struct ts_state *state, const void *data, unsigned int len) diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 30c0cb8cc9bc..23920c5ff728 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1669,19 +1669,22 @@ char *pointer_string(char *buf, char *end, const void *ptr, return number(buf, end, (unsigned long int)ptr, spec); } -static bool have_filled_random_ptr_key __read_mostly; +static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key); static siphash_key_t ptr_key __read_mostly; -static void fill_random_ptr_key(struct random_ready_callback *unused) +static void enable_ptr_key_workfn(struct work_struct *work) { get_random_bytes(&ptr_key, sizeof(ptr_key)); - /* - * have_filled_random_ptr_key==true is dependent on get_random_bytes(). - * ptr_to_id() needs to see have_filled_random_ptr_key==true - * after get_random_bytes() returns. - */ - smp_mb(); - WRITE_ONCE(have_filled_random_ptr_key, true); + /* Needs to run from preemptible context */ + static_branch_disable(¬_filled_random_ptr_key); +} + +static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn); + +static void fill_random_ptr_key(struct random_ready_callback *unused) +{ + /* This may be in an interrupt handler. */ + queue_work(system_unbound_wq, &enable_ptr_key_work); } static struct random_ready_callback random_ready = { @@ -1695,7 +1698,8 @@ static int __init initialize_ptr_random(void) if (!ret) { return 0; } else if (ret == -EALREADY) { - fill_random_ptr_key(&random_ready); + /* This is in preemptible context */ + enable_ptr_key_workfn(&enable_ptr_key_work); return 0; } @@ -1709,7 +1713,7 @@ static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec) unsigned long hashval; const int default_width = 2 * sizeof(ptr); - if (unlikely(!have_filled_random_ptr_key)) { + if (static_branch_unlikely(¬_filled_random_ptr_key)) { spec.field_width = default_width; /* string length must be less than default_width */ return string(buf, end, "(ptrval)", spec); |