diff options
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Kconfig.debug | 48 | ||||
-rw-r--r-- | lib/Makefile | 2 | ||||
-rw-r--r-- | lib/assoc_array.c | 2 | ||||
-rw-r--r-- | lib/cmdline.c | 14 | ||||
-rw-r--r-- | lib/cpumask.c | 4 | ||||
-rw-r--r-- | lib/decompress_unlz4.c | 1 | ||||
-rw-r--r-- | lib/dma-debug.c | 193 | ||||
-rw-r--r-- | lib/dynamic_debug.c | 15 | ||||
-rw-r--r-- | lib/kobject.c | 95 | ||||
-rw-r--r-- | lib/kstrtox.c | 1 | ||||
-rw-r--r-- | lib/parser.c | 62 | ||||
-rw-r--r-- | lib/percpu-refcount.c | 3 | ||||
-rw-r--r-- | lib/rbtree_test.c | 13 | ||||
-rw-r--r-- | lib/scatterlist.c | 3 | ||||
-rw-r--r-- | lib/show_mem.c | 6 | ||||
-rw-r--r-- | lib/swiotlb.c | 35 | ||||
-rw-r--r-- | lib/test_module.c | 33 | ||||
-rw-r--r-- | lib/test_user_copy.c | 110 | ||||
-rw-r--r-- | lib/vsprintf.c | 33 |
19 files changed, 548 insertions, 125 deletions
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index db25707..e0e2eeb 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -761,6 +761,15 @@ config PANIC_ON_OOPS_VALUE default 0 if !PANIC_ON_OOPS default 1 if PANIC_ON_OOPS +config PANIC_TIMEOUT + int "panic timeout" + default 0 + help + Set the timeout value (in seconds) until a reboot occurs when the + the kernel panics. If n = 0, then we wait forever. A timeout + value n > 0 will wait n seconds before rebooting, while a timeout + value n < 0 will reboot immediately. + config SCHED_DEBUG bool "Collect scheduler debugging info" depends on DEBUG_KERNEL && PROC_FS @@ -1575,8 +1584,43 @@ config DMA_API_DEBUG With this option you will be able to detect common bugs in device drivers like double-freeing of DMA mappings or freeing mappings that were never allocated. - This option causes a performance degredation. Use only if you want - to debug device drivers. If unsure, say N. + + This also attempts to catch cases where a page owned by DMA is + accessed by the cpu in a way that could cause data corruption. For + example, this enables cow_user_page() to check that the source page is + not undergoing DMA. + + This option causes a performance degradation. Use only if you want to + debug device drivers and dma interactions. + + If unsure, say N. + +config TEST_MODULE + tristate "Test module loading with 'hello world' module" + default n + depends on m + help + This builds the "test_module" module that emits "Hello, world" + on printk when loaded. It is designed to be used for basic + evaluation of the module loading subsystem (for example when + validating module verification). It lacks any extra dependencies, + and will not normally be loaded by the system unless explicitly + requested by name. + + If unsure, say N. + +config TEST_USER_COPY + tristate "Test user/kernel boundary protections" + default n + depends on m + help + This builds the "test_user_copy" module that runs sanity checks + on the copy_to/from_user infrastructure, making sure basic + user/kernel boundary testing is working. If it fails to load, + a regression has been detected in the user/kernel memory boundary + protections. + + If unsure, say N. source "samples/Kconfig" diff --git a/lib/Makefile b/lib/Makefile index d0f79c5..126b34f 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -31,6 +31,8 @@ obj-y += string_helpers.o obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o obj-y += kstrtox.o obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o +obj-$(CONFIG_TEST_MODULE) += test_module.o +obj-$(CONFIG_TEST_USER_COPY) += test_user_copy.o ifeq ($(CONFIG_DEBUG_KOBJECT),y) CFLAGS_kobject.o += -DDEBUG diff --git a/lib/assoc_array.c b/lib/assoc_array.c index 1b6a44f..c0b1007 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -157,7 +157,7 @@ enum assoc_array_walk_status { assoc_array_walk_tree_empty, assoc_array_walk_found_terminal_node, assoc_array_walk_found_wrong_shortcut, -} status; +}; struct assoc_array_walk_result { struct { diff --git a/lib/cmdline.c b/lib/cmdline.c index eb67911..d4932f7 100644 --- a/lib/cmdline.c +++ b/lib/cmdline.c @@ -49,13 +49,13 @@ static int get_range(char **str, int *pint) * 3 - hyphen found to denote a range */ -int get_option (char **str, int *pint) +int get_option(char **str, int *pint) { char *cur = *str; if (!cur || !(*cur)) return 0; - *pint = simple_strtol (cur, str, 0); + *pint = simple_strtol(cur, str, 0); if (cur == *str) return 0; if (**str == ',') { @@ -67,6 +67,7 @@ int get_option (char **str, int *pint) return 1; } +EXPORT_SYMBOL(get_option); /** * get_options - Parse a string into a list of integers @@ -84,13 +85,13 @@ int get_option (char **str, int *pint) * the parse to end (typically a null terminator, if @str is * completely parseable). */ - + char *get_options(const char *str, int nints, int *ints) { int res, i = 1; while (i < nints) { - res = get_option ((char **)&str, ints + i); + res = get_option((char **)&str, ints + i); if (res == 0) break; if (res == 3) { @@ -112,6 +113,7 @@ char *get_options(const char *str, int nints, int *ints) ints[0] = i - 1; return (char *)str; } +EXPORT_SYMBOL(get_options); /** * memparse - parse a string with mem suffixes into a number @@ -152,8 +154,4 @@ unsigned long long memparse(const char *ptr, char **retptr) return ret; } - - EXPORT_SYMBOL(memparse); -EXPORT_SYMBOL(get_option); -EXPORT_SYMBOL(get_options); diff --git a/lib/cpumask.c b/lib/cpumask.c index d327b87..b810b75 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -140,7 +140,7 @@ EXPORT_SYMBOL(zalloc_cpumask_var); */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { - *mask = alloc_bootmem(cpumask_size()); + *mask = memblock_virt_alloc(cpumask_size(), 0); } /** @@ -161,6 +161,6 @@ EXPORT_SYMBOL(free_cpumask_var); */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { - free_bootmem(__pa(mask), cpumask_size()); + memblock_free_early(__pa(mask), cpumask_size()); } #endif diff --git a/lib/decompress_unlz4.c b/lib/decompress_unlz4.c index 3e67cfad1..7d1e83c 100644 --- a/lib/decompress_unlz4.c +++ b/lib/decompress_unlz4.c @@ -141,6 +141,7 @@ STATIC inline int INIT unlz4(u8 *input, int in_len, goto exit_2; } + ret = -1; if (flush && flush(outp, dest_len) != dest_len) goto exit_2; if (output) diff --git a/lib/dma-debug.c b/lib/dma-debug.c index d87a17a..c380838 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -53,11 +53,26 @@ enum map_err_types { #define DMA_DEBUG_STACKTRACE_ENTRIES 5 +/** + * struct dma_debug_entry - track a dma_map* or dma_alloc_coherent mapping + * @list: node on pre-allocated free_entries list + * @dev: 'dev' argument to dma_map_{page|single|sg} or dma_alloc_coherent + * @type: single, page, sg, coherent + * @pfn: page frame of the start address + * @offset: offset of mapping relative to pfn + * @size: length of the mapping + * @direction: enum dma_data_direction + * @sg_call_ents: 'nents' from dma_map_sg + * @sg_mapped_ents: 'mapped_ents' from dma_map_sg + * @map_err_type: track whether dma_mapping_error() was checked + * @stacktrace: support backtraces when a violation is detected + */ struct dma_debug_entry { struct list_head list; struct device *dev; int type; - phys_addr_t paddr; + unsigned long pfn; + size_t offset; u64 dev_addr; u64 size; int direction; @@ -372,6 +387,11 @@ static void hash_bucket_del(struct dma_debug_entry *entry) list_del(&entry->list); } +static unsigned long long phys_addr(struct dma_debug_entry *entry) +{ + return page_to_phys(pfn_to_page(entry->pfn)) + entry->offset; +} + /* * Dump mapping entries for debugging purposes */ @@ -389,9 +409,9 @@ void debug_dma_dump_mappings(struct device *dev) list_for_each_entry(entry, &bucket->list, list) { if (!dev || dev == entry->dev) { dev_info(entry->dev, - "%s idx %d P=%Lx D=%Lx L=%Lx %s %s\n", + "%s idx %d P=%Lx N=%lx D=%Lx L=%Lx %s %s\n", type2name[entry->type], idx, - (unsigned long long)entry->paddr, + phys_addr(entry), entry->pfn, entry->dev_addr, entry->size, dir2name[entry->direction], maperr2str[entry->map_err_type]); @@ -404,6 +424,133 @@ void debug_dma_dump_mappings(struct device *dev) EXPORT_SYMBOL(debug_dma_dump_mappings); /* + * For each page mapped (initial page in the case of + * dma_alloc_coherent/dma_map_{single|page}, or each page in a + * scatterlist) insert into this tree using the pfn as the key. At + * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry. If + * the pfn already exists at insertion time add a tag as a reference + * count for the overlapping mappings. For now, the overlap tracking + * just ensures that 'unmaps' balance 'maps' before marking the pfn + * idle, but we should also be flagging overlaps as an API violation. + * + * Memory usage is mostly constrained by the maximum number of available + * dma-debug entries in that we need a free dma_debug_entry before + * inserting into the tree. In the case of dma_map_{single|page} and + * dma_alloc_coherent there is only one dma_debug_entry and one pfn to + * track per event. dma_map_sg(), on the other hand, + * consumes a single dma_debug_entry, but inserts 'nents' entries into + * the tree. + * + * At any time debug_dma_assert_idle() can be called to trigger a + * warning if the given page is in the active set. + */ +static RADIX_TREE(dma_active_pfn, GFP_NOWAIT); +static DEFINE_SPINLOCK(radix_lock); +#define ACTIVE_PFN_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1) + +static int active_pfn_read_overlap(unsigned long pfn) +{ + int overlap = 0, i; + + for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--) + if (radix_tree_tag_get(&dma_active_pfn, pfn, i)) + overlap |= 1 << i; + return overlap; +} + +static int active_pfn_set_overlap(unsigned long pfn, int overlap) +{ + int i; + + if (overlap > ACTIVE_PFN_MAX_OVERLAP || overlap < 0) + return 0; + + for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--) + if (overlap & 1 << i) + radix_tree_tag_set(&dma_active_pfn, pfn, i); + else + radix_tree_tag_clear(&dma_active_pfn, pfn, i); + + return overlap; +} + +static void active_pfn_inc_overlap(unsigned long pfn) +{ + int overlap = active_pfn_read_overlap(pfn); + + overlap = active_pfn_set_overlap(pfn, ++overlap); + + /* If we overflowed the overlap counter then we're potentially + * leaking dma-mappings. Otherwise, if maps and unmaps are + * balanced then this overflow may cause false negatives in + * debug_dma_assert_idle() as the pfn may be marked idle + * prematurely. + */ + WARN_ONCE(overlap == 0, + "DMA-API: exceeded %d overlapping mappings of pfn %lx\n", + ACTIVE_PFN_MAX_OVERLAP, pfn); +} + +static int active_pfn_dec_overlap(unsigned long pfn) +{ + int overlap = active_pfn_read_overlap(pfn); + + return active_pfn_set_overlap(pfn, --overlap); +} + +static int active_pfn_insert(struct dma_debug_entry *entry) +{ + unsigned long flags; + int rc; + + spin_lock_irqsave(&radix_lock, flags); + rc = radix_tree_insert(&dma_active_pfn, entry->pfn, entry); + if (rc == -EEXIST) + active_pfn_inc_overlap(entry->pfn); + spin_unlock_irqrestore(&radix_lock, flags); + + return rc; +} + +static void active_pfn_remove(struct dma_debug_entry *entry) +{ + unsigned long flags; + + spin_lock_irqsave(&radix_lock, flags); + if (active_pfn_dec_overlap(entry->pfn) == 0) + radix_tree_delete(&dma_active_pfn, entry->pfn); + spin_unlock_irqrestore(&radix_lock, flags); +} + +/** + * debug_dma_assert_idle() - assert that a page is not undergoing dma + * @page: page to lookup in the dma_active_pfn tree + * + * Place a call to this routine in cases where the cpu touching the page + * before the dma completes (page is dma_unmapped) will lead to data + * corruption. + */ +void debug_dma_assert_idle(struct page *page) +{ + unsigned long flags; + struct dma_debug_entry *entry; + + if (!page) + return; + + spin_lock_irqsave(&radix_lock, flags); + entry = radix_tree_lookup(&dma_active_pfn, page_to_pfn(page)); + spin_unlock_irqrestore(&radix_lock, flags); + + if (!entry) + return; + + err_printk(entry->dev, entry, + "DMA-API: cpu touching an active dma mapped page " + "[pfn=0x%lx]\n", entry->pfn); +} + +/* * Wrapper function for adding an entry to the hash. * This function takes care of locking itself. */ @@ -411,10 +558,21 @@ static void add_dma_entry(struct dma_debug_entry *entry) { struct hash_bucket *bucket; unsigned long flags; + int rc; bucket = get_hash_bucket(entry, &flags); hash_bucket_add(bucket, entry); put_hash_bucket(bucket, &flags); + + rc = active_pfn_insert(entry); + if (rc == -ENOMEM) { + pr_err("DMA-API: pfn tracking ENOMEM, dma-debug disabled\n"); + global_disable = true; + } + + /* TODO: report -EEXIST errors here as overlapping mappings are + * not supported by the DMA API + */ } static struct dma_debug_entry *__dma_entry_alloc(void) @@ -469,6 +627,8 @@ static void dma_entry_free(struct dma_debug_entry *entry) { unsigned long flags; + active_pfn_remove(entry); + /* * add to beginning of the list - this way the entries are * more likely cache hot when they are reallocated. @@ -895,15 +1055,15 @@ static void check_unmap(struct dma_debug_entry *ref) ref->dev_addr, ref->size, type2name[entry->type], type2name[ref->type]); } else if ((entry->type == dma_debug_coherent) && - (ref->paddr != entry->paddr)) { + (phys_addr(ref) != phys_addr(entry))) { err_printk(ref->dev, entry, "DMA-API: device driver frees " "DMA memory with different CPU address " "[device address=0x%016llx] [size=%llu bytes] " "[cpu alloc address=0x%016llx] " "[cpu free address=0x%016llx]", ref->dev_addr, ref->size, - (unsigned long long)entry->paddr, - (unsigned long long)ref->paddr); + phys_addr(entry), + phys_addr(ref)); } if (ref->sg_call_ents && ref->type == dma_debug_sg && @@ -1052,7 +1212,8 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, entry->dev = dev; entry->type = dma_debug_page; - entry->paddr = page_to_phys(page) + offset; + entry->pfn = page_to_pfn(page); + entry->offset = offset, entry->dev_addr = dma_addr; entry->size = size; entry->direction = direction; @@ -1148,7 +1309,8 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, entry->type = dma_debug_sg; entry->dev = dev; - entry->paddr = sg_phys(s); + entry->pfn = page_to_pfn(sg_page(s)); + entry->offset = s->offset, entry->size = sg_dma_len(s); entry->dev_addr = sg_dma_address(s); entry->direction = direction; @@ -1198,7 +1360,8 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, struct dma_debug_entry ref = { .type = dma_debug_sg, .dev = dev, - .paddr = sg_phys(s), + .pfn = page_to_pfn(sg_page(s)), + .offset = s->offset, .dev_addr = sg_dma_address(s), .size = sg_dma_len(s), .direction = dir, @@ -1233,7 +1396,8 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size, entry->type = dma_debug_coherent; entry->dev = dev; - entry->paddr = virt_to_phys(virt); + entry->pfn = page_to_pfn(virt_to_page(virt)); + entry->offset = (size_t) virt & PAGE_MASK; entry->size = size; entry->dev_addr = dma_addr; entry->direction = DMA_BIDIRECTIONAL; @@ -1248,7 +1412,8 @@ void debug_dma_free_coherent(struct device *dev, size_t size, struct dma_debug_entry ref = { .type = dma_debug_coherent, .dev = dev, - .paddr = virt_to_phys(virt), + .pfn = page_to_pfn(virt_to_page(virt)), + .offset = (size_t) virt & PAGE_MASK, .dev_addr = addr, .size = size, .direction = DMA_BIDIRECTIONAL, @@ -1356,7 +1521,8 @@ void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, struct dma_debug_entry ref = { .type = dma_debug_sg, .dev = dev, - .paddr = sg_phys(s), + .pfn = page_to_pfn(sg_page(s)), + .offset = s->offset, .dev_addr = sg_dma_address(s), .size = sg_dma_len(s), .direction = direction, @@ -1388,7 +1554,8 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, struct dma_debug_entry ref = { .type = dma_debug_sg, .dev = dev, - .paddr = sg_phys(s), + .pfn = page_to_pfn(sg_page(s)), + .offset = s->offset, .dev_addr = sg_dma_address(s), .size = sg_dma_len(s), .direction = direction, diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index c37aeac..600ac57 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -8,6 +8,7 @@ * By Greg Banks <gnb@melbourne.sgi.com> * Copyright (c) 2008 Silicon Graphics Inc. All Rights Reserved. * Copyright (C) 2011 Bart Van Assche. All Rights Reserved. + * Copyright (C) 2013 Du, Changbin <changbin.du@gmail.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__ @@ -24,6 +25,7 @@ #include <linux/sysctl.h> #include <linux/ctype.h> #include <linux/string.h> +#include <linux/parser.h> #include <linux/string_helpers.h> #include <linux/uaccess.h> #include <linux/dynamic_debug.h> @@ -147,7 +149,8 @@ static int ddebug_change(const struct ddebug_query *query, list_for_each_entry(dt, &ddebug_tables, link) { /* match against the module name */ - if (query->module && strcmp(query->module, dt->mod_name)) + if (query->module && + !match_wildcard(query->module, dt->mod_name)) continue; for (i = 0; i < dt->num_ddebugs; i++) { @@ -155,14 +158,16 @@ static int ddebug_change(const struct ddebug_query *query, /* match against the source filename */ if (query->filename && - strcmp(query->filename, dp->filename) && - strcmp(query->filename, kbasename(dp->filename)) && - strcmp(query->filename, trim_prefix(dp->filename))) + !match_wildcard(query->filename, dp->filename) && + !match_wildcard(query->filename, + kbasename(dp->filename)) && + !match_wildcard(query->filename, + trim_prefix(dp->filename))) continue; /* match against the function */ if (query->function && - strcmp(query->function, dp->function)) + !match_wildcard(query->function, dp->function)) continue; /* match against the format */ diff --git a/lib/kobject.c b/lib/kobject.c index 5b4b888..b0b2666 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -13,11 +13,11 @@ */ #include <linux/kobject.h> -#include <linux/kobj_completion.h> #include <linux/string.h> #include <linux/export.h> #include <linux/stat.h> #include <linux/slab.h> +#include <linux/random.h> /** * kobject_namespace - return @kobj's namespace tag @@ -65,13 +65,17 @@ static int populate_dir(struct kobject *kobj) static int create_dir(struct kobject *kobj) { + const struct kobj_ns_type_operations *ops; int error; error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj)); - if (!error) { - error = populate_dir(kobj); - if (error) - sysfs_remove_dir(kobj); + if (error) + return error; + + error = populate_dir(kobj); + if (error) { + sysfs_remove_dir(kobj); + return error; } /* @@ -80,7 +84,20 @@ static int create_dir(struct kobject *kobj) */ sysfs_get(kobj->sd); - return error; + /* + * If @kobj has ns_ops, its children need to be filtered based on + * their namespace tags. Enable namespace support on @kobj->sd. + */ + ops = kobj_child_ns_ops(kobj); + if (ops) { + BUG_ON(ops->type <= KOBJ_NS_TYPE_NONE); + BUG_ON(ops->type >= KOBJ_NS_TYPES); + BUG_ON(!kobj_ns_type_registered(ops->type)); + + kernfs_enable_ns(kobj->sd); + } + + return 0; } static int get_kobj_path_length(struct kobject *kobj) @@ -247,8 +264,10 @@ int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, return 0; kobj->name = kvasprintf(GFP_KERNEL, fmt, vargs); - if (!kobj->name) + if (!kobj->name) { + kobj->name = old_name; return -ENOMEM; + } /* ewww... some of these buggers have '/' in the name ... */ while ((s = strchr(kobj->name, '/'))) @@ -346,7 +365,7 @@ static int kobject_add_varg(struct kobject *kobj, struct kobject *parent, * * If @parent is set, then the parent of the @kobj will be set to it. * If @parent is NULL, then the parent of the @kobj will be set to the - * kobject associted with the kset assigned to this kobject. If no kset + * kobject associated with the kset assigned to this kobject. If no kset * is assigned to the kobject, then the kobject will be located in the * root of the sysfs tree. * @@ -536,7 +555,7 @@ out: */ void kobject_del(struct kobject *kobj) { - struct sysfs_dirent *sd; + struct kernfs_node *sd; if (!kobj) return; @@ -625,10 +644,12 @@ static void kobject_release(struct kref *kref) { struct kobject *kobj = container_of(kref, struct kobject, kref); #ifdef CONFIG_DEBUG_KOBJECT_RELEASE - pr_info("kobject: '%s' (%p): %s, parent %p (delayed)\n", - kobject_name(kobj), kobj, __func__, kobj->parent); + unsigned long delay = HZ + HZ * (get_random_int() & 0x3); + pr_info("kobject: '%s' (%p): %s, parent %p (delayed %ld)\n", + kobject_name(kobj), kobj, __func__, kobj->parent, delay); INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup); - schedule_delayed_work(&kobj->release, HZ); + + schedule_delayed_work(&kobj->release, delay); #else kobject_cleanup(kobj); #endif @@ -760,55 +781,6 @@ const struct sysfs_ops kobj_sysfs_ops = { }; /** - * kobj_completion_init - initialize a kobj_completion object. - * @kc: kobj_completion - * @ktype: type of kobject to initialize - * - * kobj_completion structures can be embedded within structures with different - * lifetime rules. During the release of the enclosing object, we can - * wait on the release of the kobject so that we don't free it while it's - * still busy. - */ -void kobj_completion_init(struct kobj_completion *kc, struct kobj_type *ktype) -{ - init_completion(&kc->kc_unregister); - kobject_init(&kc->kc_kobj, ktype); -} -EXPORT_SYMBOL_GPL(kobj_completion_init); - -/** - * kobj_completion_release - release a kobj_completion object - * @kobj: kobject embedded in kobj_completion - * - * Used with kobject_release to notify waiters that the kobject has been - * released. - */ -void kobj_completion_release(struct kobject *kobj) -{ - struct kobj_completion *kc = kobj_to_kobj_completion(kobj); - complete(&kc->kc_unregister); -} -EXPORT_SYMBOL_GPL(kobj_completion_release); - -/** - * kobj_completion_del_and_wait - release the kobject and wait for it - * @kc: kobj_completion object to release - * - * Delete the kobject from sysfs and drop the reference count. Then wait - * until any other outstanding references are also dropped. This routine - * is only necessary once other references may have been taken on the - * kobject. Typically this happens when the kobject has been published - * to sysfs via kobject_add. - */ -void kobj_completion_del_and_wait(struct kobj_completion *kc) -{ - kobject_del(&kc->kc_kobj); - kobject_put(&kc->kc_kobj); - wait_for_completion(&kc->kc_unregister); -} -EXPORT_SYMBOL_GPL(kobj_completion_del_and_wait); - -/** * kset_register - initialize and add a kset. * @k: kset. */ @@ -835,6 +807,7 @@ void kset_unregister(struct kset *k) { if (!k) return; + kobject_del(&k->kobj); kobject_put(&k->kobj); } diff --git a/lib/kstrtox.c b/lib/kstrtox.c index f78ae0c..ec8da78 100644 --- a/lib/kstrtox.c +++ b/lib/kstrtox.c @@ -92,7 +92,6 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res) rv = _parse_integer(s, base, &_res); if (rv & KSTRTOX_OVERFLOW) return -ERANGE; - rv &= ~KSTRTOX_OVERFLOW; if (rv == 0) return -EINVAL; s += rv; diff --git a/lib/parser.c b/lib/parser.c index 807b2aa..b6d1163 100644 --- a/lib/parser.c +++ b/lib/parser.c @@ -113,6 +113,7 @@ int match_token(char *s, const match_table_t table, substring_t args[]) return p->token; } +EXPORT_SYMBOL(match_token); /** * match_number: scan a number in the given base from a substring_t @@ -163,6 +164,7 @@ int match_int(substring_t *s, int *result) { return match_number(s, result, 0); } +EXPORT_SYMBOL(match_int); /** * match_octal: - scan an octal representation of an integer from a substring_t @@ -177,6 +179,7 @@ int match_octal(substring_t *s, int *result) { return match_number(s, result, 8); } +EXPORT_SYMBOL(match_octal); /** * match_hex: - scan a hex representation of an integer from a substring_t @@ -191,6 +194,58 @@ int match_hex(substring_t *s, int *result) { return match_number(s, result, 16); } +EXPORT_SYMBOL(match_hex); + +/** + * match_wildcard: - parse if a string matches given wildcard pattern + * @pattern: wildcard pattern + * @str: the string to be parsed + * + * Description: Parse the string @str to check if matches wildcard + * pattern @pattern. The pattern may contain two type wildcardes: + * '*' - matches zero or more characters + * '?' - matches one character + * If it's matched, return true, else return false. + */ +bool match_wildcard(const char *pattern, const char *str) +{ + const char *s = str; + const char *p = pattern; + bool star = false; + + while (*s) { + switch (*p) { + case '?': + s++; + p++; + break; + case '*': + star = true; + str = s; + if (!*++p) + return true; + pattern = p; + break; + default: + if (*s == *p) { + s++; + p++; + } else { + if (!star) + return false; + str++; + s = str; + p = pattern; + } + break; + } + } + + if (*p == '*') + ++p; + return !*p; +} +EXPORT_SYMBOL(match_wildcard); /** * match_strlcpy: - Copy the characters from a substring_t to a sized buffer @@ -213,6 +268,7 @@ size_t match_strlcpy(char *dest, const substring_t *src, size_t size) } return ret; } +EXPORT_SYMBOL(match_strlcpy); /** * match_strdup: - allocate a new string with the contents of a substring_t @@ -230,10 +286,4 @@ char *match_strdup(const substring_t *s) match_strlcpy(p, s, sz); return p; } - -EXPORT_SYMBOL(match_token); -EXPORT_SYMBOL(match_int); -EXPORT_SYMBOL(match_octal); -EXPORT_SYMBOL(match_hex); -EXPORT_SYMBOL(match_strlcpy); EXPORT_SYMBOL(match_strdup); diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index 1a53d49..963b703 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -120,6 +120,9 @@ static void percpu_ref_kill_rcu(struct rcu_head *rcu) atomic_add((int) count - PCPU_COUNT_BIAS, &ref->count); + WARN_ONCE(atomic_read(&ref->count) <= 0, "percpu ref <= 0 (%i)", + atomic_read(&ref->count)); + /* @ref is viewed as dead on all CPUs, send out kill confirmation */ if (ref->confirm_kill) ref->confirm_kill(ref); diff --git a/lib/rbtree_test.c b/lib/rbtree_test.c index 31dd4cc..8b3c9dc 100644 --- a/lib/rbtree_test.c +++ b/lib/rbtree_test.c @@ -8,8 +8,8 @@ #define CHECK_LOOPS 100 struct test_node { - struct rb_node rb; u32 key; + struct rb_node rb; /* following fields used for testing augmented rbtree functionality */ u32 val; @@ -114,6 +114,16 @@ static int black_path_count(struct rb_node *rb) return count; } +static void check_postorder_foreach(int nr_nodes) +{ + struct test_node *cur, *n; + int count = 0; + rbtree_postorder_for_each_entry_safe(cur, n, &root, rb) + count++; + + WARN_ON_ONCE(count != nr_nodes); +} + static void check_postorder(int nr_nodes) { struct rb_node *rb; @@ -148,6 +158,7 @@ static void check(int nr_nodes) WARN_ON_ONCE(count < (1 << black_path_count(rb_last(&root))) - 1); check_postorder(nr_nodes); + check_postorder_foreach(nr_nodes); } static void check_augmented(int nr_nodes) diff --git a/lib/scatterlist.c b/lib/scatterlist.c index d16fa29..3a8e8e8 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -495,7 +495,7 @@ static bool sg_miter_get_next_page(struct sg_mapping_iter *miter) * true if @miter contains the valid mapping. false if end of sg * list is reached. */ -static bool sg_miter_skip(struct sg_mapping_iter *miter, off_t offset) +bool sg_miter_skip(struct sg_mapping_iter *miter, off_t offset) { sg_miter_stop(miter); @@ -513,6 +513,7 @@ static bool sg_miter_skip(struct sg_mapping_iter *miter, off_t offset) return true; } +EXPORT_SYMBOL(sg_miter_skip); /** * sg_miter_next - proceed mapping iterator to the next mapping diff --git a/lib/show_mem.c b/lib/show_mem.c index 5847a49..0922579 100644 --- a/lib/show_mem.c +++ b/lib/show_mem.c @@ -17,9 +17,6 @@ void show_mem(unsigned int filter) printk("Mem-Info:\n"); show_free_areas(filter); - if (filter & SHOW_MEM_FILTER_PAGE_COUNT) - return; - for_each_online_pgdat(pgdat) { unsigned long flags; int zoneid; @@ -46,4 +43,7 @@ void show_mem(unsigned int filter) printk("%lu pages in pagetable cache\n", quicklist_total_size()); #endif +#ifdef CONFIG_MEMORY_FAILURE + printk("%lu pages hwpoisoned\n", atomic_long_read(&num_poisoned_pages)); +#endif } diff --git a/lib/swiotlb.c b/lib/swiotlb.c index e4399fa..615f3de 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -172,8 +172,9 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) /* * Get the overflow emergency buffer */ - v_overflow_buffer = alloc_bootmem_low_pages_nopanic( - PAGE_ALIGN(io_tlb_overflow)); + v_overflow_buffer = memblock_virt_alloc_nopanic( + PAGE_ALIGN(io_tlb_overflow), + PAGE_SIZE); if (!v_overflow_buffer) return -ENOMEM; @@ -184,11 +185,15 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE * between io_tlb_start and io_tlb_end. */ - io_tlb_list = alloc_bootmem_pages(PAGE_ALIGN(io_tlb_nslabs * sizeof(int))); + io_tlb_list = memblock_virt_alloc( + PAGE_ALIGN(io_tlb_nslabs * sizeof(int)), + PAGE_SIZE); for (i = 0; i < io_tlb_nslabs; i++) io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); io_tlb_index = 0; - io_tlb_orig_addr = alloc_bootmem_pages(PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); + io_tlb_orig_addr = memblock_virt_alloc( + PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)), + PAGE_SIZE); if (verbose) swiotlb_print_info(); @@ -215,13 +220,13 @@ swiotlb_init(int verbose) bytes = io_tlb_nslabs << IO_TLB_SHIFT; /* Get IO TLB memory from the low pages */ - vstart = alloc_bootmem_low_pages_nopanic(PAGE_ALIGN(bytes)); + vstart = memblock_virt_alloc_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE); if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) return; if (io_tlb_start) - free_bootmem(io_tlb_start, - PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + memblock_free_early(io_tlb_start, + PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); pr_warn("Cannot allocate SWIOTLB buffer"); no_iotlb_memory = true; } @@ -357,14 +362,14 @@ void __init swiotlb_free(void) free_pages((unsigned long)phys_to_virt(io_tlb_start), get_order(io_tlb_nslabs << IO_TLB_SHIFT)); } else { - free_bootmem_late(io_tlb_overflow_buffer, - PAGE_ALIGN(io_tlb_overflow)); - free_bootmem_late(__pa(io_tlb_orig_addr), - PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); - free_bootmem_late(__pa(io_tlb_list), - PAGE_ALIGN(io_tlb_nslabs * sizeof(int))); - free_bootmem_late(io_tlb_start, - PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + memblock_free_late(io_tlb_overflow_buffer, + PAGE_ALIGN(io_tlb_overflow)); + 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)); } io_tlb_nslabs = 0; } diff --git a/lib/test_module.c b/lib/test_module.c new file mode 100644 index 0000000..319b66f --- /dev/null +++ b/lib/test_module.c @@ -0,0 +1,33 @@ +/* + * This module emits "Hello, world" on printk when loaded. + * + * It is designed to be used for basic evaluation of the module loading + * subsystem (for example when validating module signing/verification). It + * lacks any extra dependencies, and will not normally be loaded by the + * system unless explicitly requested by name. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/printk.h> + +static int __init test_module_init(void) +{ + pr_warn("Hello, world\n"); + + return 0; +} + +module_init(test_module_init); + +static void __exit test_module_exit(void) +{ + pr_warn("Goodbye\n"); +} + +module_exit(test_module_exit); + +MODULE_AUTHOR("Kees Cook <keescook@chromium.org>"); +MODULE_LICENSE("GPL"); diff --git a/lib/test_user_copy.c b/lib/test_user_copy.c new file mode 100644 index 0000000..0ecef3e --- /dev/null +++ b/lib/test_user_copy.c @@ -0,0 +1,110 @@ +/* + * Kernel module for testing copy_to/from_user infrastructure. + * + * Copyright 2013 Google Inc. All Rights Reserved + * + * Authors: + * Kees Cook <keescook@chromium.org> + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/mman.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> + +#define test(condition, msg) \ +({ \ + int cond = (condition); \ + if (cond) \ + pr_warn("%s\n", msg); \ + cond; \ +}) + +static int __init test_user_copy_init(void) +{ + int ret = 0; + char *kmem; + char __user *usermem; + char *bad_usermem; + unsigned long user_addr; + unsigned long value = 0x5A; + + kmem = kmalloc(PAGE_SIZE * 2, GFP_KERNEL); + if (!kmem) + return -ENOMEM; + + user_addr = vm_mmap(NULL, 0, PAGE_SIZE * 2, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_ANONYMOUS | MAP_PRIVATE, 0); + if (user_addr >= (unsigned long)(TASK_SIZE)) { + pr_warn("Failed to allocate user memory\n"); + kfree(kmem); + return -ENOMEM; + } + + usermem = (char __user *)user_addr; + bad_usermem = (char *)user_addr; + + /* Legitimate usage: none of these should fail. */ + ret |= test(copy_from_user(kmem, usermem, PAGE_SIZE), + "legitimate copy_from_user failed"); + ret |= test(copy_to_user(usermem, kmem, PAGE_SIZE), + "legitimate copy_to_user failed"); + ret |= test(get_user(value, (unsigned long __user *)usermem), + "legitimate get_user failed"); + ret |= test(put_user(value, (unsigned long __user *)usermem), + "legitimate put_user failed"); + + /* Invalid usage: none of these should succeed. */ + ret |= test(!copy_from_user(kmem, (char __user *)(kmem + PAGE_SIZE), + PAGE_SIZE), + "illegal all-kernel copy_from_user passed"); + ret |= test(!copy_from_user(bad_usermem, (char __user *)kmem, + PAGE_SIZE), + "illegal reversed copy_from_user passed"); + ret |= test(!copy_to_user((char __user *)kmem, kmem + PAGE_SIZE, + PAGE_SIZE), + "illegal all-kernel copy_to_user passed"); + ret |= test(!copy_to_user((char __user *)kmem, bad_usermem, + PAGE_SIZE), + "illegal reversed copy_to_user passed"); + ret |= test(!get_user(value, (unsigned long __user *)kmem), + "illegal get_user passed"); + ret |= test(!put_user(value, (unsigned long __user *)kmem), + "illegal put_user passed"); + + vm_munmap(user_addr, PAGE_SIZE * 2); + kfree(kmem); + + if (ret == 0) { + pr_info("tests passed.\n"); + return 0; + } + + return -EINVAL; +} + +module_init(test_user_copy_init); + +static void __exit test_user_copy_exit(void) +{ + pr_info("unloaded.\n"); +} + +module_exit(test_user_copy_exit); + +MODULE_AUTHOR("Kees Cook <keescook@chromium.org>"); +MODULE_LICENSE("GPL"); diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 10909c5..185b6d3 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1155,6 +1155,30 @@ char *netdev_feature_string(char *buf, char *end, const u8 *addr, return number(buf, end, *(const netdev_features_t *)addr, spec); } +static noinline_for_stack +char *address_val(char *buf, char *end, const void *addr, + struct printf_spec spec, const char *fmt) +{ + unsigned long long num; + + spec.flags |= SPECIAL | SMALL | ZEROPAD; + spec.base = 16; + + switch (fmt[1]) { + case 'd': + num = *(const dma_addr_t *)addr; + spec.field_width = sizeof(dma_addr_t) * 2 + 2; + break; + case 'p': + default: + num = *(const phys_addr_t *)addr; + spec.field_width = sizeof(phys_addr_t) * 2 + 2; + break; + } + + return number(buf, end, num, spec); +} + int kptr_restrict __read_mostly; /* @@ -1218,7 +1242,8 @@ int kptr_restrict __read_mostly; * N no separator * The maximum supported length is 64 bytes of the input. Consider * to use print_hex_dump() for the larger input. - * - 'a' For a phys_addr_t type and its derivative types (passed by reference) + * - 'a[pd]' For address types [p] phys_addr_t, [d] dma_addr_t and derivatives + * (default assumed to be phys_addr_t, passed by reference) * - 'd[234]' For a dentry name (optionally 2-4 last components) * - 'D[234]' Same as 'd' but for a struct file * @@ -1353,11 +1378,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, } break; case 'a': - spec.flags |= SPECIAL | SMALL | ZEROPAD; - spec.field_width = sizeof(phys_addr_t) * 2 + 2; - spec.base = 16; - return number(buf, end, - (unsigned long long) *((phys_addr_t *)ptr), spec); + return address_val(buf, end, ptr, spec, fmt); case 'd': return dentry_name(buf, end, ptr, spec, fmt); case 'D': |