diff options
Diffstat (limited to 'kernel')
87 files changed, 4116 insertions, 3270 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 847a82bfe0e3..318789c728d3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -29,7 +29,6 @@ KCOV_INSTRUMENT_softirq.o := n KCSAN_SANITIZE_softirq.o = n # These are called from save_stack_trace() on slub debug path, # and produce insane amounts of uninteresting coverage. -KCOV_INSTRUMENT_module.o := n KCOV_INSTRUMENT_extable.o := n KCOV_INSTRUMENT_stacktrace.o := n # Don't self-instrument. @@ -53,6 +52,7 @@ obj-y += rcu/ obj-y += livepatch/ obj-y += dma/ obj-y += entry/ +obj-$(CONFIG_MODULES) += module/ obj-$(CONFIG_KCMP) += kcmp.o obj-$(CONFIG_FREEZER) += freezer.o @@ -66,9 +66,6 @@ ifneq ($(CONFIG_SMP),y) obj-y += up.o endif obj-$(CONFIG_UID16) += uid16.o -obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_MODULE_DECOMPRESS) += module_decompress.o -obj-$(CONFIG_MODULE_SIG) += module_signing.o obj-$(CONFIG_MODULE_SIG_FORMAT) += module_signature.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o diff --git a/kernel/acct.c b/kernel/acct.c index 3df53cf1dcd5..13706356ec54 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -70,11 +70,31 @@ * Turned into sysctl-controllable parameters. AV, 12/11/98 */ -int acct_parm[3] = {4, 2, 30}; +static int acct_parm[3] = {4, 2, 30}; #define RESUME (acct_parm[0]) /* >foo% free space - resume */ #define SUSPEND (acct_parm[1]) /* <foo% free space - suspend */ #define ACCT_TIMEOUT (acct_parm[2]) /* foo second timeout between checks */ +#ifdef CONFIG_SYSCTL +static struct ctl_table kern_acct_table[] = { + { + .procname = "acct", + .data = &acct_parm, + .maxlen = 3*sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static __init int kernel_acct_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_acct_table); + return 0; +} +late_initcall(kernel_acct_sysctls_init); +#endif /* CONFIG_SYSCTL */ + /* * External references and all of the globals. */ diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index 02348b48447c..6432a37ac1c9 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -100,7 +100,7 @@ struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pa audit_update_mark(audit_mark, dentry->d_inode); audit_mark->rule = krule; - ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, true); + ret = fsnotify_add_inode_mark(&audit_mark->mark, inode, 0); if (ret < 0) { fsnotify_put_mark(&audit_mark->mark); audit_mark = ERR_PTR(ret); @@ -181,7 +181,8 @@ static const struct fsnotify_ops audit_mark_fsnotify_ops = { static int __init audit_fsnotify_init(void) { - audit_fsnotify_group = fsnotify_alloc_group(&audit_mark_fsnotify_ops); + audit_fsnotify_group = fsnotify_alloc_group(&audit_mark_fsnotify_ops, + FSNOTIFY_GROUP_DUPS); if (IS_ERR(audit_fsnotify_group)) { audit_fsnotify_group = NULL; audit_panic("cannot create audit fsnotify group"); diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index e7315d487163..e867c17d3f84 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -351,7 +351,7 @@ static void untag_chunk(struct audit_chunk *chunk, struct fsnotify_mark *mark) struct audit_chunk *new; int size; - mutex_lock(&audit_tree_group->mark_mutex); + fsnotify_group_lock(audit_tree_group); /* * mark_mutex stabilizes chunk attached to the mark so we can check * whether it didn't change while we've dropped hash_lock. @@ -368,7 +368,7 @@ static void untag_chunk(struct audit_chunk *chunk, struct fsnotify_mark *mark) replace_mark_chunk(mark, NULL); spin_unlock(&hash_lock); fsnotify_detach_mark(mark); - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); audit_mark_put_chunk(chunk); fsnotify_free_mark(mark); return; @@ -385,12 +385,12 @@ static void untag_chunk(struct audit_chunk *chunk, struct fsnotify_mark *mark) */ replace_chunk(new, chunk); spin_unlock(&hash_lock); - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); audit_mark_put_chunk(chunk); return; out_mutex: - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); } /* Call with group->mark_mutex held, releases it */ @@ -400,19 +400,19 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree) struct audit_chunk *chunk = alloc_chunk(1); if (!chunk) { - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); return -ENOMEM; } mark = alloc_mark(); if (!mark) { - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); kfree(chunk); return -ENOMEM; } if (fsnotify_add_inode_mark_locked(mark, inode, 0)) { - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); fsnotify_put_mark(mark); kfree(chunk); return -ENOSPC; @@ -422,7 +422,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree) if (tree->goner) { spin_unlock(&hash_lock); fsnotify_detach_mark(mark); - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); fsnotify_free_mark(mark); fsnotify_put_mark(mark); kfree(chunk); @@ -444,7 +444,7 @@ static int create_chunk(struct inode *inode, struct audit_tree *tree) */ insert_hash(chunk); spin_unlock(&hash_lock); - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); /* * Drop our initial reference. When mark we point to is getting freed, * we get notification through ->freeing_mark callback and cleanup @@ -462,7 +462,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) struct audit_node *p; int n; - mutex_lock(&audit_tree_group->mark_mutex); + fsnotify_group_lock(audit_tree_group); mark = fsnotify_find_mark(&inode->i_fsnotify_marks, audit_tree_group); if (!mark) return create_chunk(inode, tree); @@ -478,7 +478,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) for (n = 0; n < old->count; n++) { if (old->owners[n].owner == tree) { spin_unlock(&hash_lock); - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); fsnotify_put_mark(mark); return 0; } @@ -487,7 +487,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) chunk = alloc_chunk(old->count + 1); if (!chunk) { - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); fsnotify_put_mark(mark); return -ENOMEM; } @@ -495,7 +495,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) spin_lock(&hash_lock); if (tree->goner) { spin_unlock(&hash_lock); - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); fsnotify_put_mark(mark); kfree(chunk); return 0; @@ -515,7 +515,7 @@ static int tag_chunk(struct inode *inode, struct audit_tree *tree) */ replace_chunk(chunk, old); spin_unlock(&hash_lock); - mutex_unlock(&audit_tree_group->mark_mutex); + fsnotify_group_unlock(audit_tree_group); fsnotify_put_mark(mark); /* pair to fsnotify_find_mark */ audit_mark_put_chunk(old); @@ -1044,12 +1044,12 @@ static void audit_tree_freeing_mark(struct fsnotify_mark *mark, { struct audit_chunk *chunk; - mutex_lock(&mark->group->mark_mutex); + fsnotify_group_lock(mark->group); spin_lock(&hash_lock); chunk = mark_chunk(mark); replace_mark_chunk(mark, NULL); spin_unlock(&hash_lock); - mutex_unlock(&mark->group->mark_mutex); + fsnotify_group_unlock(mark->group); if (chunk) { evict_chunk(chunk); audit_mark_put_chunk(chunk); @@ -1074,7 +1074,7 @@ static int __init audit_tree_init(void) audit_tree_mark_cachep = KMEM_CACHE(audit_tree_mark, SLAB_PANIC); - audit_tree_group = fsnotify_alloc_group(&audit_tree_ops); + audit_tree_group = fsnotify_alloc_group(&audit_tree_ops, 0); if (IS_ERR(audit_tree_group)) audit_panic("cannot initialize fsnotify group for rectree watches"); diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 713b256be944..4b0957aa2cd4 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -493,7 +493,7 @@ static const struct fsnotify_ops audit_watch_fsnotify_ops = { static int __init audit_watch_init(void) { - audit_watch_group = fsnotify_alloc_group(&audit_watch_fsnotify_ops); + audit_watch_group = fsnotify_alloc_group(&audit_watch_fsnotify_ops, 0); if (IS_ERR(audit_watch_group)) { audit_watch_group = NULL; audit_panic("cannot create audit fsnotify group"); diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h index 6b12f06ee18c..4ea227c9c1ad 100644 --- a/kernel/bpf/bpf_lru_list.h +++ b/kernel/bpf/bpf_lru_list.h @@ -4,6 +4,7 @@ #ifndef __BPF_LRU_LIST_H_ #define __BPF_LRU_LIST_H_ +#include <linux/cache.h> #include <linux/list.h> #include <linux/spinlock_types.h> diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 4d57c03714f4..71122e01623c 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -222,9 +222,6 @@ next: p = strstr(p+1, name); } - if (!ck_cmdline) - return NULL; - return ck_cmdline; } diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 6735ac36b718..67d3c48a1522 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -9,7 +9,6 @@ * Copyright (c) 2009 Wind River Systems, Inc. All Rights Reserved. */ -#include <linux/module.h> #include <linux/types.h> #include <linux/ctype.h> #include <linux/kernel.h> diff --git a/kernel/debug/kdb/kdb_keyboard.c b/kernel/debug/kdb/kdb_keyboard.c index f877a0a0d7cf..f87c750d3eb3 100644 --- a/kernel/debug/kdb/kdb_keyboard.c +++ b/kernel/debug/kdb/kdb_keyboard.c @@ -11,7 +11,6 @@ #include <linux/kdb.h> #include <linux/keyboard.h> #include <linux/ctype.h> -#include <linux/module.h> #include <linux/io.h> /* Keyboard Controller Registers on normal PCs. */ diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index ead4da947127..438b868cbfa9 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -26,7 +26,6 @@ #include <linux/utsname.h> #include <linux/vmalloc.h> #include <linux/atomic.h> -#include <linux/module.h> #include <linux/moduleparam.h> #include <linux/mm.h> #include <linux/init.h> @@ -2060,54 +2059,6 @@ static int kdb_ef(int argc, const char **argv) return 0; } -#if defined(CONFIG_MODULES) -/* - * kdb_lsmod - This function implements the 'lsmod' command. Lists - * currently loaded kernel modules. - * Mostly taken from userland lsmod. - */ -static int kdb_lsmod(int argc, const char **argv) -{ - struct module *mod; - - if (argc != 0) - return KDB_ARGCOUNT; - - kdb_printf("Module Size modstruct Used by\n"); - list_for_each_entry(mod, kdb_modules, list) { - if (mod->state == MODULE_STATE_UNFORMED) - continue; - - kdb_printf("%-20s%8u 0x%px ", mod->name, - mod->core_layout.size, (void *)mod); -#ifdef CONFIG_MODULE_UNLOAD - kdb_printf("%4d ", module_refcount(mod)); -#endif - if (mod->state == MODULE_STATE_GOING) - kdb_printf(" (Unloading)"); - else if (mod->state == MODULE_STATE_COMING) - kdb_printf(" (Loading)"); - else - kdb_printf(" (Live)"); - kdb_printf(" 0x%px", mod->core_layout.base); - -#ifdef CONFIG_MODULE_UNLOAD - { - struct module_use *use; - kdb_printf(" [ "); - list_for_each_entry(use, &mod->source_list, - source_list) - kdb_printf("%s ", use->target->name); - kdb_printf("]\n"); - } -#endif - } - - return 0; -} - -#endif /* CONFIG_MODULES */ - /* * kdb_env - This function implements the 'env' command. Display the * current environment variables. diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 0d2f9feea0a4..1f8c519a5f81 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -226,10 +226,6 @@ extern void kdb_kbd_cleanup_state(void); #define kdb_kbd_cleanup_state() #endif /* ! CONFIG_KDB_KEYBOARD */ -#ifdef CONFIG_MODULES -extern struct list_head *kdb_modules; -#endif /* CONFIG_MODULES */ - extern char kdb_prompt_str[]; #define KDB_WORD_SIZE ((int)sizeof(unsigned long)) diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 85cb51c4a17e..0a39497140bf 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -17,7 +17,6 @@ #include <linux/stddef.h> #include <linux/vmalloc.h> #include <linux/ptrace.h> -#include <linux/module.h> #include <linux/highmem.h> #include <linux/hardirq.h> #include <linux/delay.h> diff --git a/kernel/delayacct.c b/kernel/delayacct.c index c5e8cea9e05f..2c1e18f7c5cf 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -44,7 +44,7 @@ void delayacct_init(void) } #ifdef CONFIG_PROC_SYSCTL -int sysctl_delayacct(struct ctl_table *table, int write, void *buffer, +static int sysctl_delayacct(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int state = delayacct_on; @@ -63,6 +63,26 @@ int sysctl_delayacct(struct ctl_table *table, int write, void *buffer, set_delayacct(state); return err; } + +static struct ctl_table kern_delayacct_table[] = { + { + .procname = "task_delayacct", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_delayacct, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { } +}; + +static __init int kernel_delayacct_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_delayacct_table); + return 0; +} +late_initcall(kernel_delayacct_sysctls_init); #endif void __delayacct_tsk_init(struct task_struct *tsk) diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index f8ff598596b8..ac740630c79c 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -448,7 +448,7 @@ void debug_dma_dump_mappings(struct device *dev) * other hand, consumes a single dma_debug_entry, but inserts 'nents' * entries into the tree. */ -static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT); +static RADIX_TREE(dma_active_cacheline, GFP_ATOMIC); static DEFINE_SPINLOCK(radix_lock); #define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1) #define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT) diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 9743c6ccce1a..e978f36e6be8 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -79,7 +79,7 @@ static int dma_set_decrypted(struct device *dev, void *vaddr, size_t size) { if (!force_dma_unencrypted(dev)) return 0; - return set_memory_decrypted((unsigned long)vaddr, 1 << get_order(size)); + return set_memory_decrypted((unsigned long)vaddr, PFN_UP(size)); } static int dma_set_encrypted(struct device *dev, void *vaddr, size_t size) @@ -88,7 +88,7 @@ static int dma_set_encrypted(struct device *dev, void *vaddr, size_t size) if (!force_dma_unencrypted(dev)) return 0; - ret = set_memory_encrypted((unsigned long)vaddr, 1 << get_order(size)); + ret = set_memory_encrypted((unsigned long)vaddr, PFN_UP(size)); if (ret) pr_warn_ratelimited("leaking DMA memory that can't be re-encrypted\n"); return ret; @@ -115,7 +115,7 @@ static struct page *dma_direct_alloc_swiotlb(struct device *dev, size_t size) } static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, - gfp_t gfp) + gfp_t gfp, bool allow_highmem) { int node = dev_to_node(dev); struct page *page = NULL; @@ -129,9 +129,12 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size, gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, &phys_limit); page = dma_alloc_contiguous(dev, size, gfp); - if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) { - dma_free_contiguous(dev, page, size); - page = NULL; + if (page) { + if (!dma_coherent_ok(dev, page_to_phys(page), size) || + (!allow_highmem && PageHighMem(page))) { + dma_free_contiguous(dev, page, size); + page = NULL; + } } again: if (!page) @@ -189,7 +192,7 @@ static void *dma_direct_alloc_no_mapping(struct device *dev, size_t size, { struct page *page; - page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO); + page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO, true); if (!page) return NULL; @@ -262,7 +265,7 @@ void *dma_direct_alloc(struct device *dev, size_t size, return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp); /* we always manually zero the memory once we are done */ - page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO); + page = __dma_direct_alloc_pages(dev, size, gfp & ~__GFP_ZERO, true); if (!page) return NULL; @@ -370,19 +373,9 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size, if (force_dma_unencrypted(dev) && dma_direct_use_pool(dev, gfp)) return dma_direct_alloc_from_pool(dev, size, dma_handle, gfp); - page = __dma_direct_alloc_pages(dev, size, gfp); + page = __dma_direct_alloc_pages(dev, size, gfp, false); if (!page) return NULL; - if (PageHighMem(page)) { - /* - * Depending on the cma= arguments and per-arch setup - * dma_alloc_contiguous could return highmem pages. - * Without remapping there is no way to return them here, - * so log an error and fail. - */ - dev_info(dev, "Rejecting highmem page from CMA.\n"); - goto out_free_pages; - } ret = page_address(page); if (dma_set_decrypted(dev, ret, size)) diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index 8a6cd53dbe8c..a78c0ba70645 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -91,7 +91,7 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev, return swiotlb_map(dev, phys, size, dir, attrs); if (unlikely(!dma_capable(dev, dma_addr, size, true))) { - if (swiotlb_force != SWIOTLB_NO_FORCE) + if (is_swiotlb_active(dev)) return swiotlb_map(dev, phys, size, dir, attrs); dev_WARN_ONCE(dev, 1, diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 73a41cec9e38..dfa1de89dc94 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -62,18 +62,13 @@ #define INVALID_PHYS_ADDR (~(phys_addr_t)0) -enum swiotlb_force swiotlb_force; +static bool swiotlb_force_bounce; +static bool swiotlb_force_disable; struct io_tlb_mem io_tlb_default_mem; phys_addr_t swiotlb_unencrypted_base; -/* - * Max segment that we can provide which (if pages are contingous) will - * not be bounced (unless SWIOTLB_FORCE is set). - */ -static unsigned int max_segment; - static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT; static int __init @@ -87,9 +82,9 @@ setup_io_tlb_npages(char *str) if (*str == ',') ++str; if (!strcmp(str, "force")) - swiotlb_force = SWIOTLB_FORCE; + swiotlb_force_bounce = true; else if (!strcmp(str, "noforce")) - swiotlb_force = SWIOTLB_NO_FORCE; + swiotlb_force_disable = true; return 0; } @@ -97,18 +92,12 @@ early_param("swiotlb", setup_io_tlb_npages); unsigned int swiotlb_max_segment(void) { - return io_tlb_default_mem.nslabs ? max_segment : 0; + if (!io_tlb_default_mem.nslabs) + return 0; + return rounddown(io_tlb_default_mem.nslabs << IO_TLB_SHIFT, PAGE_SIZE); } EXPORT_SYMBOL_GPL(swiotlb_max_segment); -void swiotlb_set_max_segment(unsigned int val) -{ - if (swiotlb_force == SWIOTLB_FORCE) - max_segment = 1; - else - max_segment = rounddown(val, PAGE_SIZE); -} - unsigned long swiotlb_size_or_default(void) { return default_nslabs << IO_TLB_SHIFT; @@ -214,7 +203,7 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, mem->index = 0; mem->late_alloc = late_alloc; - if (swiotlb_force == SWIOTLB_FORCE) + if (swiotlb_force_bounce) mem->force_bounce = true; spin_lock_init(&mem->lock); @@ -236,17 +225,49 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, return; } -int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) +/* + * Statically reserve bounce buffer space and initialize bounce buffer data + * structures for the software IO TLB used to implement the DMA API. + */ +void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, + int (*remap)(void *tlb, unsigned long nslabs)) { struct io_tlb_mem *mem = &io_tlb_default_mem; + unsigned long nslabs = default_nslabs; size_t alloc_size; + size_t bytes; + void *tlb; - if (swiotlb_force == SWIOTLB_NO_FORCE) - return 0; + if (!addressing_limit && !swiotlb_force_bounce) + return; + if (swiotlb_force_disable) + return; - /* protect against double initialization */ - if (WARN_ON_ONCE(mem->nslabs)) - return -ENOMEM; + /* + * By default allocate the bounce buffer memory from low memory, but + * allow to pick a location everywhere for hypervisors with guest + * memory encryption. + */ +retry: + bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT); + if (flags & SWIOTLB_ANY) + tlb = memblock_alloc(bytes, PAGE_SIZE); + else + tlb = memblock_alloc_low(bytes, PAGE_SIZE); + if (!tlb) { + pr_warn("%s: failed to allocate tlb structure\n", __func__); + return; + } + + if (remap && remap(tlb, nslabs) < 0) { + memblock_free(tlb, PAGE_ALIGN(bytes)); + + nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); + if (nslabs < IO_TLB_MIN_SLABS) + panic("%s: Failed to remap %zu bytes\n", + __func__, bytes); + goto retry; + } alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs)); mem->slots = memblock_alloc(alloc_size, PAGE_SIZE); @@ -255,38 +276,15 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) __func__, alloc_size, PAGE_SIZE); swiotlb_init_io_tlb_mem(mem, __pa(tlb), nslabs, false); + mem->force_bounce = flags & SWIOTLB_FORCE; - if (verbose) + if (flags & SWIOTLB_VERBOSE) swiotlb_print_info(); - swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT); - return 0; } -/* - * Statically reserve bounce buffer space and initialize bounce buffer data - * structures for the software IO TLB used to implement the DMA API. - */ -void __init -swiotlb_init(int verbose) +void __init swiotlb_init(bool addressing_limit, unsigned int flags) { - size_t bytes = PAGE_ALIGN(default_nslabs << IO_TLB_SHIFT); - void *tlb; - - if (swiotlb_force == SWIOTLB_NO_FORCE) - return; - - /* Get IO TLB memory from the low pages */ - tlb = memblock_alloc_low(bytes, PAGE_SIZE); - if (!tlb) - goto fail; - if (swiotlb_init_with_tbl(tlb, default_nslabs, verbose)) - goto fail_free_mem; - return; - -fail_free_mem: - memblock_free(tlb, bytes); -fail: - pr_warn("Cannot allocate buffer"); + return swiotlb_init_remap(addressing_limit, flags, NULL); } /* @@ -294,72 +292,65 @@ fail: * initialize the swiotlb later using the slab allocator if needed. * This should be just like above, but with some error catching. */ -int -swiotlb_late_init_with_default_size(size_t default_size) +int swiotlb_init_late(size_t size, gfp_t gfp_mask, + int (*remap)(void *tlb, unsigned long nslabs)) { - unsigned long nslabs = - ALIGN(default_size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); - unsigned long bytes; + struct io_tlb_mem *mem = &io_tlb_default_mem; + unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); unsigned char *vstart = NULL; unsigned int order; + bool retried = false; int rc = 0; - if (swiotlb_force == SWIOTLB_NO_FORCE) + if (swiotlb_force_disable) return 0; - /* - * Get IO TLB memory from the low pages - */ +retry: order = get_order(nslabs << IO_TLB_SHIFT); nslabs = SLABS_PER_PAGE << order; - bytes = nslabs << IO_TLB_SHIFT; while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) { - vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, + vstart = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN, order); if (vstart) break; order--; + nslabs = SLABS_PER_PAGE << order; + retried = true; } if (!vstart) return -ENOMEM; - if (order != get_order(bytes)) { - pr_warn("only able to allocate %ld MB\n", - (PAGE_SIZE << order) >> 20); - nslabs = SLABS_PER_PAGE << order; - } - rc = swiotlb_late_init_with_tbl(vstart, nslabs); - if (rc) + if (remap) + rc = remap(vstart, nslabs); + if (rc) { free_pages((unsigned long)vstart, order); - return rc; -} - -int -swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) -{ - struct io_tlb_mem *mem = &io_tlb_default_mem; - unsigned long bytes = nslabs << IO_TLB_SHIFT; - - if (swiotlb_force == SWIOTLB_NO_FORCE) - return 0; + nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); + if (nslabs < IO_TLB_MIN_SLABS) + return rc; + retried = true; + goto retry; + } - /* protect against double initialization */ - if (WARN_ON_ONCE(mem->nslabs)) - return -ENOMEM; + if (retried) { + pr_warn("only able to allocate %ld MB\n", + (PAGE_SIZE << order) >> 20); + } mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(array_size(sizeof(*mem->slots), nslabs))); - if (!mem->slots) + if (!mem->slots) { + free_pages((unsigned long)vstart, order); return -ENOMEM; + } - set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT); - swiotlb_init_io_tlb_mem(mem, virt_to_phys(tlb), nslabs, true); + set_memory_decrypted((unsigned long)vstart, + (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT); + swiotlb_init_io_tlb_mem(mem, virt_to_phys(vstart), nslabs, true); swiotlb_print_info(); - swiotlb_set_max_segment(mem->nslabs << IO_TLB_SHIFT); return 0; } @@ -369,6 +360,9 @@ void __init swiotlb_exit(void) unsigned long tbl_vaddr; size_t tbl_size, slots_size; + if (swiotlb_force_bounce) + return; + if (!mem->nslabs) return; @@ -717,8 +711,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, phys_addr_t swiotlb_addr; dma_addr_t dma_addr; - trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size, - swiotlb_force); + trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size); swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir, attrs); @@ -743,7 +736,18 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, size_t swiotlb_max_mapping_size(struct device *dev) { - return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE; + int min_align_mask = dma_get_min_align_mask(dev); + int min_align = 0; + + /* + * swiotlb_find_slots() skips slots according to + * min align mask. This affects max mapping size. + * Take it into acount here. + */ + if (min_align_mask) + min_align = roundup(min_align_mask, IO_TLB_SIZE); + + return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE - min_align; } bool is_swiotlb_active(struct device *dev) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index a9bc3c98f76a..2eaa327f8158 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -180,7 +180,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, if (new_page) { get_page(new_page); - page_add_new_anon_rmap(new_page, vma, addr, false); + page_add_new_anon_rmap(new_page, vma, addr); lru_cache_add_inactive_or_unevictable(new_page, vma); } else /* no new page, just dec_mm_counter for old_page */ diff --git a/kernel/fork.c b/kernel/fork.c index 254ab63c1106..124829ed0163 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -612,9 +612,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, retval = ksm_fork(mm, oldmm); if (retval) goto out; - retval = khugepaged_fork(mm, oldmm); - if (retval) - goto out; + khugepaged_fork(mm, oldmm); prev = NULL; for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) { diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index c264cbeab71c..b5379c0e6d6d 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -3,6 +3,7 @@ #define _FUTEX_H #include <linux/futex.h> +#include <linux/rtmutex.h> #include <linux/sched/wake_q.h> #ifdef CONFIG_PREEMPT_RT diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 1966a749e0d9..0c78e64f747d 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -74,7 +74,7 @@ fi # of tree builds having stale headers in srctree. Just silence CPIO for now. for f in $dir_list; do find "$f" -name "*.h"; -done | cpio --quiet -pd $cpio_dir >/dev/null 2>&1 +done | cpio --quiet -pdu $cpio_dir >/dev/null 2>&1 # Remove comments except SDPX lines find $cpio_dir -type f -print0 | diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 02a65d554340..80bfea5dd5c4 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -73,7 +73,7 @@ static unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; * hung task is detected: */ unsigned int __read_mostly sysctl_hung_task_panic = - CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE; + IS_ENABLED(CONFIG_BOOTPARAM_HUNG_TASK_PANIC); static int hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr) diff --git a/kernel/kcov.c b/kernel/kcov.c index b3732b210593..e19c84b02452 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -204,8 +204,16 @@ void notrace __sanitizer_cov_trace_pc(void) /* The first 64-bit word is the number of subsequent PCs. */ pos = READ_ONCE(area[0]) + 1; if (likely(pos < t->kcov_size)) { - area[pos] = ip; + /* Previously we write pc before updating pos. However, some + * early interrupt code could bypass check_kcov_mode() check + * and invoke __sanitizer_cov_trace_pc(). If such interrupt is + * raised between writing pc and updating pos, the pc could be + * overitten by the recursive __sanitizer_cov_trace_pc(). + * Update pos before writing pc to avoid such interleaving. + */ WRITE_ONCE(area[0], pos); + barrier(); + area[pos] = ip; } } EXPORT_SYMBOL(__sanitizer_cov_trace_pc); @@ -236,11 +244,13 @@ static void notrace write_comp_data(u64 type, u64 arg1, u64 arg2, u64 ip) start_index = 1 + count * KCOV_WORDS_PER_CMP; end_pos = (start_index + KCOV_WORDS_PER_CMP) * sizeof(u64); if (likely(end_pos <= max_pos)) { + /* See comment in __sanitizer_cov_trace_pc(). */ + WRITE_ONCE(area[0], count + 1); + barrier(); area[start_index] = type; area[start_index + 1] = arg1; area[start_index + 2] = arg2; area[start_index + 3] = ip; - WRITE_ONCE(area[0], count + 1); } } diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index be4b54c2c615..4d34c78334ce 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -768,7 +768,6 @@ static struct page *kimage_alloc_page(struct kimage *image, kimage_free_pages(old_page); continue; } - addr = old_addr; page = old_page; break; } @@ -788,7 +787,6 @@ static int kimage_load_normal_segment(struct kimage *image, unsigned char __user *buf = NULL; unsigned char *kbuf = NULL; - result = 0; if (image->file_mode) kbuf = segment->kbuf; else @@ -936,6 +934,28 @@ int kimage_load_segment(struct kimage *image, struct kimage *kexec_image; struct kimage *kexec_crash_image; int kexec_load_disabled; +#ifdef CONFIG_SYSCTL +static struct ctl_table kexec_core_sysctls[] = { + { + .procname = "kexec_load_disabled", + .data = &kexec_load_disabled, + .maxlen = sizeof(int), + .mode = 0644, + /* only handle a transition from default "0" to "1" */ + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_ONE, + }, + { } +}; + +static int __init kexec_core_sysctl_init(void) +{ + register_sysctl_init("kernel", kexec_core_sysctls); + return 0; +} +late_initcall(kexec_core_sysctl_init); +#endif /* * No panic_cpu check version of crash_kexec(). This function is called diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 8347fc158d2b..145321a5e798 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -109,40 +109,6 @@ int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, #endif /* - * arch_kexec_apply_relocations_add - apply relocations of type RELA - * @pi: Purgatory to be relocated. - * @section: Section relocations applying to. - * @relsec: Section containing RELAs. - * @symtab: Corresponding symtab. - * - * Return: 0 on success, negative errno on error. - */ -int __weak -arch_kexec_apply_relocations_add(struct purgatory_info *pi, Elf_Shdr *section, - const Elf_Shdr *relsec, const Elf_Shdr *symtab) -{ - pr_err("RELA relocation unsupported.\n"); - return -ENOEXEC; -} - -/* - * arch_kexec_apply_relocations - apply relocations of type REL - * @pi: Purgatory to be relocated. - * @section: Section relocations applying to. - * @relsec: Section containing RELs. - * @symtab: Corresponding symtab. - * - * Return: 0 on success, negative errno on error. - */ -int __weak -arch_kexec_apply_relocations(struct purgatory_info *pi, Elf_Shdr *section, - const Elf_Shdr *relsec, const Elf_Shdr *symtab) -{ - pr_err("REL relocation unsupported.\n"); - return -ENOEXEC; -} - -/* * Free up memory used by kernel, initrd, and command line. This is temporary * memory allocation which is not needed any more after these buffers have * been loaded into separate segments and have been copied elsewhere. @@ -1260,7 +1226,7 @@ int crash_exclude_mem_range(struct crash_mem *mem, return 0; } -int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map, +int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, void **addr, unsigned long *sz) { Elf64_Ehdr *ehdr; @@ -1324,7 +1290,7 @@ int crash_prepare_elf64_headers(struct crash_mem *mem, int kernel_map, phdr++; /* Prepare PT_LOAD type program header for kernel text region */ - if (kernel_map) { + if (need_kernel_map) { phdr->p_type = PT_LOAD; phdr->p_flags = PF_R|PF_W|PF_X; phdr->p_vaddr = (unsigned long) _text; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index dd58c0be9ce2..f214f8c088ed 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1257,79 +1257,6 @@ void kprobe_busy_end(void) preempt_enable(); } -#if !defined(CONFIG_KRETPROBE_ON_RETHOOK) -static void free_rp_inst_rcu(struct rcu_head *head) -{ - struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu); - - if (refcount_dec_and_test(&ri->rph->ref)) - kfree(ri->rph); - kfree(ri); -} -NOKPROBE_SYMBOL(free_rp_inst_rcu); - -static void recycle_rp_inst(struct kretprobe_instance *ri) -{ - struct kretprobe *rp = get_kretprobe(ri); - - if (likely(rp)) - freelist_add(&ri->freelist, &rp->freelist); - else - call_rcu(&ri->rcu, free_rp_inst_rcu); -} -NOKPROBE_SYMBOL(recycle_rp_inst); - -/* - * This function is called from delayed_put_task_struct() when a task is - * dead and cleaned up to recycle any kretprobe instances associated with - * this task. These left over instances represent probed functions that - * have been called but will never return. - */ -void kprobe_flush_task(struct task_struct *tk) -{ - struct kretprobe_instance *ri; - struct llist_node *node; - - /* Early boot, not yet initialized. */ - if (unlikely(!kprobes_initialized)) - return; - - kprobe_busy_begin(); - - node = __llist_del_all(&tk->kretprobe_instances); - while (node) { - ri = container_of(node, struct kretprobe_instance, llist); - node = node->next; - - recycle_rp_inst(ri); - } - - kprobe_busy_end(); -} -NOKPROBE_SYMBOL(kprobe_flush_task); - -static inline void free_rp_inst(struct kretprobe *rp) -{ - struct kretprobe_instance *ri; - struct freelist_node *node; - int count = 0; - - node = rp->freelist.head; - while (node) { - ri = container_of(node, struct kretprobe_instance, freelist); - node = node->next; - - kfree(ri); - count++; - } - - if (refcount_sub_and_test(count, &rp->rph->ref)) { - kfree(rp->rph); - rp->rph = NULL; - } -} -#endif /* !CONFIG_KRETPROBE_ON_RETHOOK */ - /* Add the new probe to 'ap->list'. */ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { @@ -1928,6 +1855,77 @@ static struct notifier_block kprobe_exceptions_nb = { #ifdef CONFIG_KRETPROBES #if !defined(CONFIG_KRETPROBE_ON_RETHOOK) +static void free_rp_inst_rcu(struct rcu_head *head) +{ + struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu); + + if (refcount_dec_and_test(&ri->rph->ref)) + kfree(ri->rph); + kfree(ri); +} +NOKPROBE_SYMBOL(free_rp_inst_rcu); + +static void recycle_rp_inst(struct kretprobe_instance *ri) +{ + struct kretprobe *rp = get_kretprobe(ri); + + if (likely(rp)) + freelist_add(&ri->freelist, &rp->freelist); + else + call_rcu(&ri->rcu, free_rp_inst_rcu); +} +NOKPROBE_SYMBOL(recycle_rp_inst); + +/* + * This function is called from delayed_put_task_struct() when a task is + * dead and cleaned up to recycle any kretprobe instances associated with + * this task. These left over instances represent probed functions that + * have been called but will never return. + */ +void kprobe_flush_task(struct task_struct *tk) +{ + struct kretprobe_instance *ri; + struct llist_node *node; + + /* Early boot, not yet initialized. */ + if (unlikely(!kprobes_initialized)) + return; + + kprobe_busy_begin(); + + node = __llist_del_all(&tk->kretprobe_instances); + while (node) { + ri = container_of(node, struct kretprobe_instance, llist); + node = node->next; + + recycle_rp_inst(ri); + } + + kprobe_busy_end(); +} +NOKPROBE_SYMBOL(kprobe_flush_task); + +static inline void free_rp_inst(struct kretprobe *rp) +{ + struct kretprobe_instance *ri; + struct freelist_node *node; + int count = 0; + + node = rp->freelist.head; + while (node) { + ri = container_of(node, struct kretprobe_instance, freelist); + node = node->next; + + kfree(ri); + count++; + } + + if (refcount_sub_and_test(count, &rp->rph->ref)) { + kfree(rp->rph); + rp->rph = NULL; + } +} + /* This assumes the 'tsk' is the current task or the is not running. */ static kprobe_opcode_t *__kretprobe_find_ret_addr(struct task_struct *tsk, struct llist_node **cur) diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 166d7bf49666..76166df011a4 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -55,6 +55,7 @@ #include <linux/sched/stat.h> #include <linux/list.h> #include <linux/stacktrace.h> +#include <linux/sysctl.h> static DEFINE_RAW_SPINLOCK(latency_lock); @@ -63,6 +64,31 @@ static struct latency_record latency_record[MAXLR]; int latencytop_enabled; +#ifdef CONFIG_SYSCTL +static int sysctl_latencytop(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) +{ + int err; + + err = proc_dointvec(table, write, buffer, lenp, ppos); + if (latencytop_enabled) + force_schedstat_enabled(); + + return err; +} + +static struct ctl_table latencytop_sysctl[] = { + { + .procname = "latencytop", + .data = &latencytop_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sysctl_latencytop, + }, + {} +}; +#endif + void clear_tsk_latency_tracing(struct task_struct *p) { unsigned long flags; @@ -266,18 +292,9 @@ static const struct proc_ops lstats_proc_ops = { static int __init init_lstats_procfs(void) { proc_create("latency_stats", 0644, NULL, &lstats_proc_ops); +#ifdef CONFIG_SYSCTL + register_sysctl_init("kernel", latencytop_sysctl); +#endif return 0; } - -int sysctl_latencytop(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos) -{ - int err; - - err = proc_dointvec(table, write, buffer, lenp, ppos); - if (latencytop_enabled) - force_schedstat_enabled(); - - return err; -} device_initcall(init_lstats_procfs); diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c index c172bf92b576..4c4f5a776d80 100644 --- a/kernel/livepatch/patch.c +++ b/kernel/livepatch/patch.c @@ -118,7 +118,7 @@ static void notrace klp_ftrace_handler(unsigned long ip, if (func->nop) goto unlock; - klp_arch_set_pc(fregs, (unsigned long)func->new_func); + ftrace_instruction_pointer_set(fregs, (unsigned long)func->new_func); unlock: ftrace_test_recursion_unlock(bit); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index a6e671b8608d..81e87280513e 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -63,19 +63,50 @@ #include <trace/events/lock.h> #ifdef CONFIG_PROVE_LOCKING -int prove_locking = 1; +static int prove_locking = 1; module_param(prove_locking, int, 0644); #else #define prove_locking 0 #endif #ifdef CONFIG_LOCK_STAT -int lock_stat = 1; +static int lock_stat = 1; module_param(lock_stat, int, 0644); #else #define lock_stat 0 #endif +#ifdef CONFIG_SYSCTL +static struct ctl_table kern_lockdep_table[] = { +#ifdef CONFIG_PROVE_LOCKING + { + .procname = "prove_locking", + .data = &prove_locking, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif /* CONFIG_PROVE_LOCKING */ +#ifdef CONFIG_LOCK_STAT + { + .procname = "lock_stat", + .data = &lock_stat, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif /* CONFIG_LOCK_STAT */ + { } +}; + +static __init int kernel_lockdep_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_lockdep_table); + return 0; +} +late_initcall(kernel_lockdep_sysctls_init); +#endif /* CONFIG_SYSCTL */ + DEFINE_PER_CPU(unsigned int, lockdep_recursion); EXPORT_PER_CPU_SYMBOL_GPL(lockdep_recursion); diff --git a/kernel/module-internal.h b/kernel/module-internal.h deleted file mode 100644 index 8c381c99062f..000000000000 --- a/kernel/module-internal.h +++ /dev/null @@ -1,50 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* Module internals - * - * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/elf.h> -#include <asm/module.h> - -struct load_info { - const char *name; - /* pointer to module in temporary copy, freed at end of load_module() */ - struct module *mod; - Elf_Ehdr *hdr; - unsigned long len; - Elf_Shdr *sechdrs; - char *secstrings, *strtab; - unsigned long symoffs, stroffs, init_typeoffs, core_typeoffs; - struct _ddebug *debug; - unsigned int num_debug; - bool sig_ok; -#ifdef CONFIG_KALLSYMS - unsigned long mod_kallsyms_init_off; -#endif -#ifdef CONFIG_MODULE_DECOMPRESS - struct page **pages; - unsigned int max_pages; - unsigned int used_pages; -#endif - struct { - unsigned int sym, str, mod, vers, info, pcpu; - } index; -}; - -extern int mod_verify_sig(const void *mod, struct load_info *info); - -#ifdef CONFIG_MODULE_DECOMPRESS -int module_decompress(struct load_info *info, const void *buf, size_t size); -void module_decompress_cleanup(struct load_info *info); -#else -static inline int module_decompress(struct load_info *info, - const void *buf, size_t size) -{ - return -EOPNOTSUPP; -} -static inline void module_decompress_cleanup(struct load_info *info) -{ -} -#endif diff --git a/kernel/module/Makefile b/kernel/module/Makefile new file mode 100644 index 000000000000..948efea81e85 --- /dev/null +++ b/kernel/module/Makefile @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for linux kernel module support +# + +# These are called from save_stack_trace() on slub debug path, +# and produce insane amounts of uninteresting coverage. +KCOV_INSTRUMENT_module.o := n + +obj-y += main.o strict_rwx.o +obj-$(CONFIG_MODULE_DECOMPRESS) += decompress.o +obj-$(CONFIG_MODULE_SIG) += signing.o +obj-$(CONFIG_LIVEPATCH) += livepatch.o +obj-$(CONFIG_MODULES_TREE_LOOKUP) += tree_lookup.o +obj-$(CONFIG_DEBUG_KMEMLEAK) += debug_kmemleak.o +obj-$(CONFIG_KALLSYMS) += kallsyms.o +obj-$(CONFIG_PROC_FS) += procfs.o +obj-$(CONFIG_SYSFS) += sysfs.o +obj-$(CONFIG_KGDB_KDB) += kdb.o +obj-$(CONFIG_MODVERSIONS) += version.o +obj-$(CONFIG_MODULE_UNLOAD_TAINT_TRACKING) += tracking.o diff --git a/kernel/module/debug_kmemleak.c b/kernel/module/debug_kmemleak.c new file mode 100644 index 000000000000..12a569d361e8 --- /dev/null +++ b/kernel/module/debug_kmemleak.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Module kmemleak support + * + * Copyright (C) 2009 Catalin Marinas + */ + +#include <linux/module.h> +#include <linux/kmemleak.h> +#include "internal.h" + +void kmemleak_load_module(const struct module *mod, + const struct load_info *info) +{ + unsigned int i; + + /* only scan the sections containing data */ + kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL); + + for (i = 1; i < info->hdr->e_shnum; i++) { + /* Scan all writable sections that's not executable */ + if (!(info->sechdrs[i].sh_flags & SHF_ALLOC) || + !(info->sechdrs[i].sh_flags & SHF_WRITE) || + (info->sechdrs[i].sh_flags & SHF_EXECINSTR)) + continue; + + kmemleak_scan_area((void *)info->sechdrs[i].sh_addr, + info->sechdrs[i].sh_size, GFP_KERNEL); + } +} diff --git a/kernel/module_decompress.c b/kernel/module/decompress.c index ffef98a20320..2fc7081dd7c1 100644 --- a/kernel/module_decompress.c +++ b/kernel/module/decompress.c @@ -12,7 +12,7 @@ #include <linux/sysfs.h> #include <linux/vmalloc.h> -#include "module-internal.h" +#include "internal.h" static int module_extend_max_pages(struct load_info *info, unsigned int extent) { @@ -113,6 +113,7 @@ static ssize_t module_gzip_decompress(struct load_info *info, do { struct page *page = module_get_next_page(info); + if (!page) { retval = -ENOMEM; goto out_inflate_end; @@ -171,6 +172,7 @@ static ssize_t module_xz_decompress(struct load_info *info, do { struct page *page = module_get_next_page(info); + if (!page) { retval = -ENOMEM; goto out; @@ -256,6 +258,7 @@ static ssize_t compression_show(struct kobject *kobj, { return sysfs_emit(buf, "%s\n", __stringify(MODULE_COMPRESSION)); } + static struct kobj_attribute module_compression_attr = __ATTR_RO(compression); static int __init module_decompress_sysfs_init(void) diff --git a/kernel/module/internal.h b/kernel/module/internal.h new file mode 100644 index 000000000000..bc5507ab8450 --- /dev/null +++ b/kernel/module/internal.h @@ -0,0 +1,302 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Module internals + * + * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/elf.h> +#include <linux/compiler.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/rculist.h> +#include <linux/rcupdate.h> + +#ifndef ARCH_SHF_SMALL +#define ARCH_SHF_SMALL 0 +#endif + +/* If this is set, the section belongs in the init part of the module */ +#define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG - 1)) +/* Maximum number of characters written by module_flags() */ +#define MODULE_FLAGS_BUF_SIZE (TAINT_FLAGS_COUNT + 4) + +#ifndef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC +#define data_layout core_layout +#endif + +/* + * Modules' sections will be aligned on page boundaries + * to ensure complete separation of code and data, but + * only when CONFIG_STRICT_MODULE_RWX=y + */ +#ifdef CONFIG_STRICT_MODULE_RWX +# define strict_align(X) PAGE_ALIGN(X) +#else +# define strict_align(X) (X) +#endif + +extern struct mutex module_mutex; +extern struct list_head modules; + +extern struct module_attribute *modinfo_attrs[]; +extern size_t modinfo_attrs_count; + +/* Provided by the linker */ +extern const struct kernel_symbol __start___ksymtab[]; +extern const struct kernel_symbol __stop___ksymtab[]; +extern const struct kernel_symbol __start___ksymtab_gpl[]; +extern const struct kernel_symbol __stop___ksymtab_gpl[]; +extern const s32 __start___kcrctab[]; +extern const s32 __start___kcrctab_gpl[]; + +struct load_info { + const char *name; + /* pointer to module in temporary copy, freed at end of load_module() */ + struct module *mod; + Elf_Ehdr *hdr; + unsigned long len; + Elf_Shdr *sechdrs; + char *secstrings, *strtab; + unsigned long symoffs, stroffs, init_typeoffs, core_typeoffs; + struct _ddebug *debug; + unsigned int num_debug; + bool sig_ok; +#ifdef CONFIG_KALLSYMS + unsigned long mod_kallsyms_init_off; +#endif +#ifdef CONFIG_MODULE_DECOMPRESS + struct page **pages; + unsigned int max_pages; + unsigned int used_pages; +#endif + struct { + unsigned int sym, str, mod, vers, info, pcpu; + } index; +}; + +enum mod_license { + NOT_GPL_ONLY, + GPL_ONLY, +}; + +struct find_symbol_arg { + /* Input */ + const char *name; + bool gplok; + bool warn; + + /* Output */ + struct module *owner; + const s32 *crc; + const struct kernel_symbol *sym; + enum mod_license license; +}; + +int mod_verify_sig(const void *mod, struct load_info *info); +int try_to_force_load(struct module *mod, const char *reason); +bool find_symbol(struct find_symbol_arg *fsa); +struct module *find_module_all(const char *name, size_t len, bool even_unformed); +int cmp_name(const void *name, const void *sym); +long module_get_offset(struct module *mod, unsigned int *size, Elf_Shdr *sechdr, + unsigned int section); +char *module_flags(struct module *mod, char *buf); +size_t module_flags_taint(unsigned long taints, char *buf); + +static inline void module_assert_mutex_or_preempt(void) +{ +#ifdef CONFIG_LOCKDEP + if (unlikely(!debug_locks)) + return; + + WARN_ON_ONCE(!rcu_read_lock_sched_held() && + !lockdep_is_held(&module_mutex)); +#endif +} + +static inline unsigned long kernel_symbol_value(const struct kernel_symbol *sym) +{ +#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS + return (unsigned long)offset_to_ptr(&sym->value_offset); +#else + return sym->value; +#endif +} + +#ifdef CONFIG_LIVEPATCH +int copy_module_elf(struct module *mod, struct load_info *info); +void free_module_elf(struct module *mod); +#else /* !CONFIG_LIVEPATCH */ +static inline int copy_module_elf(struct module *mod, struct load_info *info) +{ + return 0; +} + +static inline void free_module_elf(struct module *mod) { } +#endif /* CONFIG_LIVEPATCH */ + +static inline bool set_livepatch_module(struct module *mod) +{ +#ifdef CONFIG_LIVEPATCH + mod->klp = true; + return true; +#else + return false; +#endif +} + +#ifdef CONFIG_MODULE_UNLOAD_TAINT_TRACKING +struct mod_unload_taint { + struct list_head list; + char name[MODULE_NAME_LEN]; + unsigned long taints; + u64 count; +}; + +int try_add_tainted_module(struct module *mod); +void print_unloaded_tainted_modules(void); +#else /* !CONFIG_MODULE_UNLOAD_TAINT_TRACKING */ +static inline int try_add_tainted_module(struct module *mod) +{ + return 0; +} + +static inline void print_unloaded_tainted_modules(void) +{ +} +#endif /* CONFIG_MODULE_UNLOAD_TAINT_TRACKING */ + +#ifdef CONFIG_MODULE_DECOMPRESS +int module_decompress(struct load_info *info, const void *buf, size_t size); +void module_decompress_cleanup(struct load_info *info); +#else +static inline int module_decompress(struct load_info *info, + const void *buf, size_t size) +{ + return -EOPNOTSUPP; +} + +static inline void module_decompress_cleanup(struct load_info *info) +{ +} +#endif + +struct mod_tree_root { +#ifdef CONFIG_MODULES_TREE_LOOKUP + struct latch_tree_root root; +#endif + unsigned long addr_min; + unsigned long addr_max; +}; + +extern struct mod_tree_root mod_tree; +extern struct mod_tree_root mod_data_tree; + +#ifdef CONFIG_MODULES_TREE_LOOKUP +void mod_tree_insert(struct module *mod); +void mod_tree_remove_init(struct module *mod); +void mod_tree_remove(struct module *mod); +struct module *mod_find(unsigned long addr, struct mod_tree_root *tree); +#else /* !CONFIG_MODULES_TREE_LOOKUP */ + +static inline void mod_tree_insert(struct module *mod) { } +static inline void mod_tree_remove_init(struct module *mod) { } +static inline void mod_tree_remove(struct module *mod) { } +static inline struct module *mod_find(unsigned long addr, struct mod_tree_root *tree) +{ + struct module *mod; + + list_for_each_entry_rcu(mod, &modules, list, + lockdep_is_held(&module_mutex)) { + if (within_module(addr, mod)) + return mod; + } + + return NULL; +} +#endif /* CONFIG_MODULES_TREE_LOOKUP */ + +void module_enable_ro(const struct module *mod, bool after_init); +void module_enable_nx(const struct module *mod); +void module_enable_x(const struct module *mod); +int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, + char *secstrings, struct module *mod); +bool module_check_misalignment(const struct module *mod); + +#ifdef CONFIG_MODULE_SIG +int module_sig_check(struct load_info *info, int flags); +#else /* !CONFIG_MODULE_SIG */ +static inline int module_sig_check(struct load_info *info, int flags) +{ + return 0; +} +#endif /* !CONFIG_MODULE_SIG */ + +#ifdef CONFIG_DEBUG_KMEMLEAK +void kmemleak_load_module(const struct module *mod, const struct load_info *info); +#else /* !CONFIG_DEBUG_KMEMLEAK */ +static inline void kmemleak_load_module(const struct module *mod, + const struct load_info *info) { } +#endif /* CONFIG_DEBUG_KMEMLEAK */ + +#ifdef CONFIG_KALLSYMS +void init_build_id(struct module *mod, const struct load_info *info); +void layout_symtab(struct module *mod, struct load_info *info); +void add_kallsyms(struct module *mod, const struct load_info *info); +unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name); + +static inline bool sect_empty(const Elf_Shdr *sect) +{ + return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0; +} +#else /* !CONFIG_KALLSYMS */ +static inline void init_build_id(struct module *mod, const struct load_info *info) { } +static inline void layout_symtab(struct module *mod, struct load_info *info) { } +static inline void add_kallsyms(struct module *mod, const struct load_info *info) { } +#endif /* CONFIG_KALLSYMS */ + +#ifdef CONFIG_SYSFS +int mod_sysfs_setup(struct module *mod, const struct load_info *info, + struct kernel_param *kparam, unsigned int num_params); +void mod_sysfs_teardown(struct module *mod); +void init_param_lock(struct module *mod); +#else /* !CONFIG_SYSFS */ +static inline int mod_sysfs_setup(struct module *mod, + const struct load_info *info, + struct kernel_param *kparam, + unsigned int num_params) +{ + return 0; +} + +static inline void mod_sysfs_teardown(struct module *mod) { } +static inline void init_param_lock(struct module *mod) { } +#endif /* CONFIG_SYSFS */ + +#ifdef CONFIG_MODVERSIONS +int check_version(const struct load_info *info, + const char *symname, struct module *mod, const s32 *crc); +void module_layout(struct module *mod, struct modversion_info *ver, struct kernel_param *kp, + struct kernel_symbol *ks, struct tracepoint * const *tp); +int check_modstruct_version(const struct load_info *info, struct module *mod); +int same_magic(const char *amagic, const char *bmagic, bool has_crcs); +#else /* !CONFIG_MODVERSIONS */ +static inline int check_version(const struct load_info *info, + const char *symname, + struct module *mod, + const s32 *crc) +{ + return 1; +} + +static inline int check_modstruct_version(const struct load_info *info, + struct module *mod) +{ + return 1; +} + +static inline int same_magic(const char *amagic, const char *bmagic, bool has_crcs) +{ + return strcmp(amagic, bmagic) == 0; +} +#endif /* CONFIG_MODVERSIONS */ diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c new file mode 100644 index 000000000000..3e11523bc6f6 --- /dev/null +++ b/kernel/module/kallsyms.c @@ -0,0 +1,512 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Module kallsyms support + * + * Copyright (C) 2010 Rusty Russell + */ + +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/buildid.h> +#include <linux/bsearch.h> +#include "internal.h" + +/* Lookup exported symbol in given range of kernel_symbols */ +static const struct kernel_symbol *lookup_exported_symbol(const char *name, + const struct kernel_symbol *start, + const struct kernel_symbol *stop) +{ + return bsearch(name, start, stop - start, + sizeof(struct kernel_symbol), cmp_name); +} + +static int is_exported(const char *name, unsigned long value, + const struct module *mod) +{ + const struct kernel_symbol *ks; + + if (!mod) + ks = lookup_exported_symbol(name, __start___ksymtab, __stop___ksymtab); + else + ks = lookup_exported_symbol(name, mod->syms, mod->syms + mod->num_syms); + + return ks && kernel_symbol_value(ks) == value; +} + +/* As per nm */ +static char elf_type(const Elf_Sym *sym, const struct load_info *info) +{ + const Elf_Shdr *sechdrs = info->sechdrs; + + if (ELF_ST_BIND(sym->st_info) == STB_WEAK) { + if (ELF_ST_TYPE(sym->st_info) == STT_OBJECT) + return 'v'; + else + return 'w'; + } + if (sym->st_shndx == SHN_UNDEF) + return 'U'; + if (sym->st_shndx == SHN_ABS || sym->st_shndx == info->index.pcpu) + return 'a'; + if (sym->st_shndx >= SHN_LORESERVE) + return '?'; + if (sechdrs[sym->st_shndx].sh_flags & SHF_EXECINSTR) + return 't'; + if (sechdrs[sym->st_shndx].sh_flags & SHF_ALLOC && + sechdrs[sym->st_shndx].sh_type != SHT_NOBITS) { + if (!(sechdrs[sym->st_shndx].sh_flags & SHF_WRITE)) + return 'r'; + else if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) + return 'g'; + else + return 'd'; + } + if (sechdrs[sym->st_shndx].sh_type == SHT_NOBITS) { + if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) + return 's'; + else + return 'b'; + } + if (strstarts(info->secstrings + sechdrs[sym->st_shndx].sh_name, + ".debug")) { + return 'n'; + } + return '?'; +} + +static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, + unsigned int shnum, unsigned int pcpundx) +{ + const Elf_Shdr *sec; + + if (src->st_shndx == SHN_UNDEF || + src->st_shndx >= shnum || + !src->st_name) + return false; + +#ifdef CONFIG_KALLSYMS_ALL + if (src->st_shndx == pcpundx) + return true; +#endif + + sec = sechdrs + src->st_shndx; + if (!(sec->sh_flags & SHF_ALLOC) +#ifndef CONFIG_KALLSYMS_ALL + || !(sec->sh_flags & SHF_EXECINSTR) +#endif + || (sec->sh_entsize & INIT_OFFSET_MASK)) + return false; + + return true; +} + +/* + * We only allocate and copy the strings needed by the parts of symtab + * we keep. This is simple, but has the effect of making multiple + * copies of duplicates. We could be more sophisticated, see + * linux-kernel thread starting with + * <73defb5e4bca04a6431392cc341112b1@localhost>. + */ +void layout_symtab(struct module *mod, struct load_info *info) +{ + Elf_Shdr *symsect = info->sechdrs + info->index.sym; + Elf_Shdr *strsect = info->sechdrs + info->index.str; + const Elf_Sym *src; + unsigned int i, nsrc, ndst, strtab_size = 0; + + /* Put symbol section at end of init part of module. */ + symsect->sh_flags |= SHF_ALLOC; + symsect->sh_entsize = module_get_offset(mod, &mod->init_layout.size, symsect, + info->index.sym) | INIT_OFFSET_MASK; + pr_debug("\t%s\n", info->secstrings + symsect->sh_name); + + src = (void *)info->hdr + symsect->sh_offset; + nsrc = symsect->sh_size / sizeof(*src); + + /* Compute total space required for the core symbols' strtab. */ + for (ndst = i = 0; i < nsrc; i++) { + if (i == 0 || is_livepatch_module(mod) || + is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum, + info->index.pcpu)) { + strtab_size += strlen(&info->strtab[src[i].st_name]) + 1; + ndst++; + } + } + + /* Append room for core symbols at end of core part. */ + info->symoffs = ALIGN(mod->data_layout.size, symsect->sh_addralign ?: 1); + info->stroffs = mod->data_layout.size = info->symoffs + ndst * sizeof(Elf_Sym); + mod->data_layout.size += strtab_size; + info->core_typeoffs = mod->data_layout.size; + mod->data_layout.size += ndst * sizeof(char); + mod->data_layout.size = strict_align(mod->data_layout.size); + + /* Put string table section at end of init part of module. */ + strsect->sh_flags |= SHF_ALLOC; + strsect->sh_entsize = module_get_offset(mod, &mod->init_layout.size, strsect, + info->index.str) | INIT_OFFSET_MASK; + pr_debug("\t%s\n", info->secstrings + strsect->sh_name); + + /* We'll tack temporary mod_kallsyms on the end. */ + mod->init_layout.size = ALIGN(mod->init_layout.size, + __alignof__(struct mod_kallsyms)); + info->mod_kallsyms_init_off = mod->init_layout.size; + mod->init_layout.size += sizeof(struct mod_kallsyms); + info->init_typeoffs = mod->init_layout.size; + mod->init_layout.size += nsrc * sizeof(char); + mod->init_layout.size = strict_align(mod->init_layout.size); +} + +/* + * We use the full symtab and strtab which layout_symtab arranged to + * be appended to the init section. Later we switch to the cut-down + * core-only ones. + */ +void add_kallsyms(struct module *mod, const struct load_info *info) +{ + unsigned int i, ndst; + const Elf_Sym *src; + Elf_Sym *dst; + char *s; + Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; + + /* Set up to point into init section. */ + mod->kallsyms = (void __rcu *)mod->init_layout.base + + info->mod_kallsyms_init_off; + + preempt_disable(); + /* The following is safe since this pointer cannot change */ + rcu_dereference_sched(mod->kallsyms)->symtab = (void *)symsec->sh_addr; + rcu_dereference_sched(mod->kallsyms)->num_symtab = symsec->sh_size / sizeof(Elf_Sym); + /* Make sure we get permanent strtab: don't use info->strtab. */ + rcu_dereference_sched(mod->kallsyms)->strtab = + (void *)info->sechdrs[info->index.str].sh_addr; + rcu_dereference_sched(mod->kallsyms)->typetab = mod->init_layout.base + info->init_typeoffs; + + /* + * Now populate the cut down core kallsyms for after init + * and set types up while we still have access to sections. + */ + mod->core_kallsyms.symtab = dst = mod->data_layout.base + info->symoffs; + mod->core_kallsyms.strtab = s = mod->data_layout.base + info->stroffs; + mod->core_kallsyms.typetab = mod->data_layout.base + info->core_typeoffs; + src = rcu_dereference_sched(mod->kallsyms)->symtab; + for (ndst = i = 0; i < rcu_dereference_sched(mod->kallsyms)->num_symtab; i++) { + rcu_dereference_sched(mod->kallsyms)->typetab[i] = elf_type(src + i, info); + if (i == 0 || is_livepatch_module(mod) || + is_core_symbol(src + i, info->sechdrs, info->hdr->e_shnum, + info->index.pcpu)) { + mod->core_kallsyms.typetab[ndst] = + rcu_dereference_sched(mod->kallsyms)->typetab[i]; + dst[ndst] = src[i]; + dst[ndst++].st_name = s - mod->core_kallsyms.strtab; + s += strscpy(s, + &rcu_dereference_sched(mod->kallsyms)->strtab[src[i].st_name], + KSYM_NAME_LEN) + 1; + } + } + preempt_enable(); + mod->core_kallsyms.num_symtab = ndst; +} + +#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) +void init_build_id(struct module *mod, const struct load_info *info) +{ + const Elf_Shdr *sechdr; + unsigned int i; + + for (i = 0; i < info->hdr->e_shnum; i++) { + sechdr = &info->sechdrs[i]; + if (!sect_empty(sechdr) && sechdr->sh_type == SHT_NOTE && + !build_id_parse_buf((void *)sechdr->sh_addr, mod->build_id, + sechdr->sh_size)) + break; + } +} +#else +void init_build_id(struct module *mod, const struct load_info *info) +{ +} +#endif + +/* + * This ignores the intensely annoying "mapping symbols" found + * in ARM ELF files: $a, $t and $d. + */ +static inline int is_arm_mapping_symbol(const char *str) +{ + if (str[0] == '.' && str[1] == 'L') + return true; + return str[0] == '$' && strchr("axtd", str[1]) && + (str[2] == '\0' || str[2] == '.'); +} + +static const char *kallsyms_symbol_name(struct mod_kallsyms *kallsyms, unsigned int symnum) +{ + return kallsyms->strtab + kallsyms->symtab[symnum].st_name; +} + +/* + * Given a module and address, find the corresponding symbol and return its name + * while providing its size and offset if needed. + */ +static const char *find_kallsyms_symbol(struct module *mod, + unsigned long addr, + unsigned long *size, + unsigned long *offset) +{ + unsigned int i, best = 0; + unsigned long nextval, bestval; + struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); + + /* At worse, next value is at end of module */ + if (within_module_init(addr, mod)) + nextval = (unsigned long)mod->init_layout.base + mod->init_layout.text_size; + else + nextval = (unsigned long)mod->core_layout.base + mod->core_layout.text_size; + + bestval = kallsyms_symbol_value(&kallsyms->symtab[best]); + + /* + * Scan for closest preceding symbol, and next symbol. (ELF + * starts real symbols at 1). + */ + for (i = 1; i < kallsyms->num_symtab; i++) { + const Elf_Sym *sym = &kallsyms->symtab[i]; + unsigned long thisval = kallsyms_symbol_value(sym); + + if (sym->st_shndx == SHN_UNDEF) + continue; + + /* + * We ignore unnamed symbols: they're uninformative + * and inserted at a whim. + */ + if (*kallsyms_symbol_name(kallsyms, i) == '\0' || + is_arm_mapping_symbol(kallsyms_symbol_name(kallsyms, i))) + continue; + + if (thisval <= addr && thisval > bestval) { + best = i; + bestval = thisval; + } + if (thisval > addr && thisval < nextval) + nextval = thisval; + } + + if (!best) + return NULL; + + if (size) + *size = nextval - bestval; + if (offset) + *offset = addr - bestval; + + return kallsyms_symbol_name(kallsyms, best); +} + +void * __weak dereference_module_function_descriptor(struct module *mod, + void *ptr) +{ + return ptr; +} + +/* + * For kallsyms to ask for address resolution. NULL means not found. Careful + * not to lock to avoid deadlock on oopses, simply disable preemption. + */ +const char *module_address_lookup(unsigned long addr, + unsigned long *size, + unsigned long *offset, + char **modname, + const unsigned char **modbuildid, + char *namebuf) +{ + const char *ret = NULL; + struct module *mod; + + preempt_disable(); + mod = __module_address(addr); + if (mod) { + if (modname) + *modname = mod->name; + if (modbuildid) { +#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) + *modbuildid = mod->build_id; +#else + *modbuildid = NULL; +#endif + } + + ret = find_kallsyms_symbol(mod, addr, size, offset); + } + /* Make a copy in here where it's safe */ + if (ret) { + strncpy(namebuf, ret, KSYM_NAME_LEN - 1); + ret = namebuf; + } + preempt_enable(); + + return ret; +} + +int lookup_module_symbol_name(unsigned long addr, char *symname) +{ + struct module *mod; + + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if (within_module(addr, mod)) { + const char *sym; + + sym = find_kallsyms_symbol(mod, addr, NULL, NULL); + if (!sym) + goto out; + + strscpy(symname, sym, KSYM_NAME_LEN); + preempt_enable(); + return 0; + } + } +out: + preempt_enable(); + return -ERANGE; +} + +int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, + unsigned long *offset, char *modname, char *name) +{ + struct module *mod; + + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if (within_module(addr, mod)) { + const char *sym; + + sym = find_kallsyms_symbol(mod, addr, size, offset); + if (!sym) + goto out; + if (modname) + strscpy(modname, mod->name, MODULE_NAME_LEN); + if (name) + strscpy(name, sym, KSYM_NAME_LEN); + preempt_enable(); + return 0; + } + } +out: + preempt_enable(); + return -ERANGE; +} + +int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, + char *name, char *module_name, int *exported) +{ + struct module *mod; + + preempt_disable(); + list_for_each_entry_rcu(mod, &modules, list) { + struct mod_kallsyms *kallsyms; + + if (mod->state == MODULE_STATE_UNFORMED) + continue; + kallsyms = rcu_dereference_sched(mod->kallsyms); + if (symnum < kallsyms->num_symtab) { + const Elf_Sym *sym = &kallsyms->symtab[symnum]; + + *value = kallsyms_symbol_value(sym); + *type = kallsyms->typetab[symnum]; + strscpy(name, kallsyms_symbol_name(kallsyms, symnum), KSYM_NAME_LEN); + strscpy(module_name, mod->name, MODULE_NAME_LEN); + *exported = is_exported(name, *value, mod); + preempt_enable(); + return 0; + } + symnum -= kallsyms->num_symtab; + } + preempt_enable(); + return -ERANGE; +} + +/* Given a module and name of symbol, find and return the symbol's value */ +unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name) +{ + unsigned int i; + struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); + + for (i = 0; i < kallsyms->num_symtab; i++) { + const Elf_Sym *sym = &kallsyms->symtab[i]; + + if (strcmp(name, kallsyms_symbol_name(kallsyms, i)) == 0 && + sym->st_shndx != SHN_UNDEF) + return kallsyms_symbol_value(sym); + } + return 0; +} + +/* Look for this name: can be of form module:name. */ +unsigned long module_kallsyms_lookup_name(const char *name) +{ + struct module *mod; + char *colon; + unsigned long ret = 0; + + /* Don't lock: we're in enough trouble already. */ + preempt_disable(); + if ((colon = strnchr(name, MODULE_NAME_LEN, ':')) != NULL) { + if ((mod = find_module_all(name, colon - name, false)) != NULL) + ret = find_kallsyms_symbol_value(mod, colon + 1); + } else { + list_for_each_entry_rcu(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + if ((ret = find_kallsyms_symbol_value(mod, name)) != 0) + break; + } + } + preempt_enable(); + return ret; +} + +#ifdef CONFIG_LIVEPATCH +int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, + struct module *, unsigned long), + void *data) +{ + struct module *mod; + unsigned int i; + int ret = 0; + + mutex_lock(&module_mutex); + list_for_each_entry(mod, &modules, list) { + struct mod_kallsyms *kallsyms; + + if (mod->state == MODULE_STATE_UNFORMED) + continue; + + /* Use rcu_dereference_sched() to remain compliant with the sparse tool */ + preempt_disable(); + kallsyms = rcu_dereference_sched(mod->kallsyms); + preempt_enable(); + + for (i = 0; i < kallsyms->num_symtab; i++) { + const Elf_Sym *sym = &kallsyms->symtab[i]; + + if (sym->st_shndx == SHN_UNDEF) + continue; + + ret = fn(data, kallsyms_symbol_name(kallsyms, i), + mod, kallsyms_symbol_value(sym)); + if (ret != 0) + goto out; + } + } +out: + mutex_unlock(&module_mutex); + return ret; +} +#endif /* CONFIG_LIVEPATCH */ diff --git a/kernel/module/kdb.c b/kernel/module/kdb.c new file mode 100644 index 000000000000..f4317f92e189 --- /dev/null +++ b/kernel/module/kdb.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Module kdb support + * + * Copyright (C) 2010 Jason Wessel + */ + +#include <linux/module.h> +#include <linux/kdb.h> +#include "internal.h" + +/* + * kdb_lsmod - This function implements the 'lsmod' command. Lists + * currently loaded kernel modules. + * Mostly taken from userland lsmod. + */ +int kdb_lsmod(int argc, const char **argv) +{ + struct module *mod; + + if (argc != 0) + return KDB_ARGCOUNT; + + kdb_printf("Module Size modstruct Used by\n"); + list_for_each_entry(mod, &modules, list) { + if (mod->state == MODULE_STATE_UNFORMED) + continue; + + kdb_printf("%-20s%8u", mod->name, mod->core_layout.size); +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + kdb_printf("/%8u", mod->data_layout.size); +#endif + kdb_printf(" 0x%px ", (void *)mod); +#ifdef CONFIG_MODULE_UNLOAD + kdb_printf("%4d ", module_refcount(mod)); +#endif + if (mod->state == MODULE_STATE_GOING) + kdb_printf(" (Unloading)"); + else if (mod->state == MODULE_STATE_COMING) + kdb_printf(" (Loading)"); + else + kdb_printf(" (Live)"); + kdb_printf(" 0x%px", mod->core_layout.base); +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + kdb_printf("/0x%px", mod->data_layout.base); +#endif + +#ifdef CONFIG_MODULE_UNLOAD + { + struct module_use *use; + + kdb_printf(" [ "); + list_for_each_entry(use, &mod->source_list, + source_list) + kdb_printf("%s ", use->target->name); + kdb_printf("]\n"); + } +#endif + } + + return 0; +} diff --git a/kernel/module/livepatch.c b/kernel/module/livepatch.c new file mode 100644 index 000000000000..486d4ff92719 --- /dev/null +++ b/kernel/module/livepatch.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Module livepatch support + * + * Copyright (C) 2016 Jessica Yu <jeyu@redhat.com> + */ + +#include <linux/module.h> +#include <linux/string.h> +#include <linux/slab.h> +#include "internal.h" + +/* + * Persist Elf information about a module. Copy the Elf header, + * section header table, section string table, and symtab section + * index from info to mod->klp_info. + */ +int copy_module_elf(struct module *mod, struct load_info *info) +{ + unsigned int size, symndx; + int ret; + + size = sizeof(*mod->klp_info); + mod->klp_info = kmalloc(size, GFP_KERNEL); + if (!mod->klp_info) + return -ENOMEM; + + /* Elf header */ + size = sizeof(mod->klp_info->hdr); + memcpy(&mod->klp_info->hdr, info->hdr, size); + + /* Elf section header table */ + size = sizeof(*info->sechdrs) * info->hdr->e_shnum; + mod->klp_info->sechdrs = kmemdup(info->sechdrs, size, GFP_KERNEL); + if (!mod->klp_info->sechdrs) { + ret = -ENOMEM; + goto free_info; + } + + /* Elf section name string table */ + size = info->sechdrs[info->hdr->e_shstrndx].sh_size; + mod->klp_info->secstrings = kmemdup(info->secstrings, size, GFP_KERNEL); + if (!mod->klp_info->secstrings) { + ret = -ENOMEM; + goto free_sechdrs; + } + + /* Elf symbol section index */ + symndx = info->index.sym; + mod->klp_info->symndx = symndx; + + /* + * For livepatch modules, core_kallsyms.symtab is a complete + * copy of the original symbol table. Adjust sh_addr to point + * to core_kallsyms.symtab since the copy of the symtab in module + * init memory is freed at the end of do_init_module(). + */ + mod->klp_info->sechdrs[symndx].sh_addr = (unsigned long)mod->core_kallsyms.symtab; + + return 0; + +free_sechdrs: + kfree(mod->klp_info->sechdrs); +free_info: + kfree(mod->klp_info); + return ret; +} + +void free_module_elf(struct module *mod) +{ + kfree(mod->klp_info->sechdrs); + kfree(mod->klp_info->secstrings); + kfree(mod->klp_info); +} diff --git a/kernel/module.c b/kernel/module/main.c index 6cea788fd965..fed58d30725d 100644 --- a/kernel/module.c +++ b/kernel/module/main.c @@ -14,16 +14,12 @@ #include <linux/init.h> #include <linux/kallsyms.h> #include <linux/buildid.h> -#include <linux/file.h> #include <linux/fs.h> -#include <linux/sysfs.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/elf.h> -#include <linux/proc_fs.h> -#include <linux/security.h> #include <linux/seq_file.h> #include <linux/syscalls.h> #include <linux/fcntl.h> @@ -58,236 +54,69 @@ #include <linux/dynamic_debug.h> #include <linux/audit.h> #include <uapi/linux/module.h> -#include "module-internal.h" +#include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/module.h> -#ifndef ARCH_SHF_SMALL -#define ARCH_SHF_SMALL 0 -#endif - -/* - * Modules' sections will be aligned on page boundaries - * to ensure complete separation of code and data, but - * only when CONFIG_ARCH_HAS_STRICT_MODULE_RWX=y - */ -#ifdef CONFIG_ARCH_HAS_STRICT_MODULE_RWX -# define debug_align(X) ALIGN(X, PAGE_SIZE) -#else -# define debug_align(X) (X) -#endif - -/* If this is set, the section belongs in the init part of the module */ -#define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) - /* * Mutex protects: * 1) List of modules (also safely readable with preempt_disable), * 2) module_use links, - * 3) module_addr_min/module_addr_max. + * 3) mod_tree.addr_min/mod_tree.addr_max. * (delete and add uses RCU list operations). */ -static DEFINE_MUTEX(module_mutex); -static LIST_HEAD(modules); +DEFINE_MUTEX(module_mutex); +LIST_HEAD(modules); /* Work queue for freeing init sections in success case */ static void do_free_init(struct work_struct *w); static DECLARE_WORK(init_free_wq, do_free_init); static LLIST_HEAD(init_free_list); -#ifdef CONFIG_MODULES_TREE_LOOKUP - -/* - * Use a latched RB-tree for __module_address(); this allows us to use - * RCU-sched lookups of the address from any context. - * - * This is conditional on PERF_EVENTS || TRACING because those can really hit - * __module_address() hard by doing a lot of stack unwinding; potentially from - * NMI context. - */ - -static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n) -{ - struct module_layout *layout = container_of(n, struct module_layout, mtn.node); - - return (unsigned long)layout->base; -} - -static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n) -{ - struct module_layout *layout = container_of(n, struct module_layout, mtn.node); - - return (unsigned long)layout->size; -} - -static __always_inline bool -mod_tree_less(struct latch_tree_node *a, struct latch_tree_node *b) -{ - return __mod_tree_val(a) < __mod_tree_val(b); -} - -static __always_inline int -mod_tree_comp(void *key, struct latch_tree_node *n) -{ - unsigned long val = (unsigned long)key; - unsigned long start, end; - - start = __mod_tree_val(n); - if (val < start) - return -1; - - end = start + __mod_tree_size(n); - if (val >= end) - return 1; - - return 0; -} - -static const struct latch_tree_ops mod_tree_ops = { - .less = mod_tree_less, - .comp = mod_tree_comp, +struct mod_tree_root mod_tree __cacheline_aligned = { + .addr_min = -1UL, }; -static struct mod_tree_root { - struct latch_tree_root root; - unsigned long addr_min; - unsigned long addr_max; -} mod_tree __cacheline_aligned = { +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC +struct mod_tree_root mod_data_tree __cacheline_aligned = { .addr_min = -1UL, }; +#endif #define module_addr_min mod_tree.addr_min #define module_addr_max mod_tree.addr_max -static noinline void __mod_tree_insert(struct mod_tree_node *node) -{ - latch_tree_insert(&node->node, &mod_tree.root, &mod_tree_ops); -} - -static void __mod_tree_remove(struct mod_tree_node *node) -{ - latch_tree_erase(&node->node, &mod_tree.root, &mod_tree_ops); -} - -/* - * These modifications: insert, remove_init and remove; are serialized by the - * module_mutex. - */ -static void mod_tree_insert(struct module *mod) -{ - mod->core_layout.mtn.mod = mod; - mod->init_layout.mtn.mod = mod; - - __mod_tree_insert(&mod->core_layout.mtn); - if (mod->init_layout.size) - __mod_tree_insert(&mod->init_layout.mtn); -} - -static void mod_tree_remove_init(struct module *mod) -{ - if (mod->init_layout.size) - __mod_tree_remove(&mod->init_layout.mtn); -} - -static void mod_tree_remove(struct module *mod) -{ - __mod_tree_remove(&mod->core_layout.mtn); - mod_tree_remove_init(mod); -} - -static struct module *mod_find(unsigned long addr) -{ - struct latch_tree_node *ltn; - - ltn = latch_tree_find((void *)addr, &mod_tree.root, &mod_tree_ops); - if (!ltn) - return NULL; - - return container_of(ltn, struct mod_tree_node, node)->mod; -} - -#else /* MODULES_TREE_LOOKUP */ - -static unsigned long module_addr_min = -1UL, module_addr_max = 0; - -static void mod_tree_insert(struct module *mod) { } -static void mod_tree_remove_init(struct module *mod) { } -static void mod_tree_remove(struct module *mod) { } - -static struct module *mod_find(unsigned long addr) -{ - struct module *mod; - - list_for_each_entry_rcu(mod, &modules, list, - lockdep_is_held(&module_mutex)) { - if (within_module(addr, mod)) - return mod; - } - - return NULL; -} - -#endif /* MODULES_TREE_LOOKUP */ +struct symsearch { + const struct kernel_symbol *start, *stop; + const s32 *crcs; + enum mod_license license; +}; /* * Bounds of module text, for speeding up __module_address. * Protected by module_mutex. */ -static void __mod_update_bounds(void *base, unsigned int size) +static void __mod_update_bounds(void *base, unsigned int size, struct mod_tree_root *tree) { unsigned long min = (unsigned long)base; unsigned long max = min + size; - if (min < module_addr_min) - module_addr_min = min; - if (max > module_addr_max) - module_addr_max = max; + if (min < tree->addr_min) + tree->addr_min = min; + if (max > tree->addr_max) + tree->addr_max = max; } static void mod_update_bounds(struct module *mod) { - __mod_update_bounds(mod->core_layout.base, mod->core_layout.size); + __mod_update_bounds(mod->core_layout.base, mod->core_layout.size, &mod_tree); if (mod->init_layout.size) - __mod_update_bounds(mod->init_layout.base, mod->init_layout.size); -} - -#ifdef CONFIG_KGDB_KDB -struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */ -#endif /* CONFIG_KGDB_KDB */ - -static void module_assert_mutex_or_preempt(void) -{ -#ifdef CONFIG_LOCKDEP - if (unlikely(!debug_locks)) - return; - - WARN_ON_ONCE(!rcu_read_lock_sched_held() && - !lockdep_is_held(&module_mutex)); -#endif -} - -#ifdef CONFIG_MODULE_SIG -static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE); -module_param(sig_enforce, bool_enable_only, 0644); - -void set_module_sig_enforced(void) -{ - sig_enforce = true; -} -#else -#define sig_enforce false + __mod_update_bounds(mod->init_layout.base, mod->init_layout.size, &mod_tree); +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + __mod_update_bounds(mod->data_layout.base, mod->data_layout.size, &mod_data_tree); #endif - -/* - * Export sig_enforce kernel cmdline parameter to allow other subsystems rely - * on that instead of directly to CONFIG_MODULE_SIG_FORCE config. - */ -bool is_module_sig_enforced(void) -{ - return sig_enforce; } -EXPORT_SYMBOL(is_module_sig_enforced); /* Block module loading/unloading? */ int modules_disabled = 0; @@ -408,66 +237,12 @@ static __maybe_unused void *any_section_objs(const struct load_info *info, return (void *)info->sechdrs[sec].sh_addr; } -/* Provided by the linker */ -extern const struct kernel_symbol __start___ksymtab[]; -extern const struct kernel_symbol __stop___ksymtab[]; -extern const struct kernel_symbol __start___ksymtab_gpl[]; -extern const struct kernel_symbol __stop___ksymtab_gpl[]; -extern const s32 __start___kcrctab[]; -extern const s32 __start___kcrctab_gpl[]; - #ifndef CONFIG_MODVERSIONS #define symversion(base, idx) NULL #else #define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL) #endif -struct symsearch { - const struct kernel_symbol *start, *stop; - const s32 *crcs; - enum mod_license { - NOT_GPL_ONLY, - GPL_ONLY, - } license; -}; - -struct find_symbol_arg { - /* Input */ - const char *name; - bool gplok; - bool warn; - - /* Output */ - struct module *owner; - const s32 *crc; - const struct kernel_symbol *sym; - enum mod_license license; -}; - -static bool check_exported_symbol(const struct symsearch *syms, - struct module *owner, - unsigned int symnum, void *data) -{ - struct find_symbol_arg *fsa = data; - - if (!fsa->gplok && syms->license == GPL_ONLY) - return false; - fsa->owner = owner; - fsa->crc = symversion(syms->crcs, symnum); - fsa->sym = &syms->start[symnum]; - fsa->license = syms->license; - return true; -} - -static unsigned long kernel_symbol_value(const struct kernel_symbol *sym) -{ -#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS - return (unsigned long)offset_to_ptr(&sym->value_offset); -#else - return sym->value; -#endif -} - static const char *kernel_symbol_name(const struct kernel_symbol *sym) { #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS @@ -488,33 +263,38 @@ static const char *kernel_symbol_namespace(const struct kernel_symbol *sym) #endif } -static int cmp_name(const void *name, const void *sym) +int cmp_name(const void *name, const void *sym) { return strcmp(name, kernel_symbol_name(sym)); } static bool find_exported_symbol_in_section(const struct symsearch *syms, struct module *owner, - void *data) + struct find_symbol_arg *fsa) { - struct find_symbol_arg *fsa = data; struct kernel_symbol *sym; + if (!fsa->gplok && syms->license == GPL_ONLY) + return false; + sym = bsearch(fsa->name, syms->start, syms->stop - syms->start, sizeof(struct kernel_symbol), cmp_name); + if (!sym) + return false; - if (sym != NULL && check_exported_symbol(syms, owner, - sym - syms->start, data)) - return true; + fsa->owner = owner; + fsa->crc = symversion(syms->crcs, sym - syms->start); + fsa->sym = sym; + fsa->license = syms->license; - return false; + return true; } /* * Find an exported symbol and return it, along with, (optional) crc and * (optional) module which owns it. Needs preempt disabled or module_mutex. */ -static bool find_symbol(struct find_symbol_arg *fsa) +bool find_symbol(struct find_symbol_arg *fsa) { static const struct symsearch arr[] = { { __start___ksymtab, __stop___ksymtab, __start___kcrctab, @@ -558,8 +338,8 @@ static bool find_symbol(struct find_symbol_arg *fsa) * Search for module by name: must hold module_mutex (or preempt disabled * for read-only access). */ -static struct module *find_module_all(const char *name, size_t len, - bool even_unformed) +struct module *find_module_all(const char *name, size_t len, + bool even_unformed) { struct module *mod; @@ -985,31 +765,6 @@ out: return ret; } -static inline void print_unload_info(struct seq_file *m, struct module *mod) -{ - struct module_use *use; - int printed_something = 0; - - seq_printf(m, " %i ", module_refcount(mod)); - - /* - * Always include a trailing , so userspace can differentiate - * between this and the old multi-field proc format. - */ - list_for_each_entry(use, &mod->source_list, source_list) { - printed_something = 1; - seq_printf(m, "%s,", use->source->name); - } - - if (mod->init != NULL && mod->exit == NULL) { - printed_something = 1; - seq_puts(m, "[permanent],"); - } - - if (!printed_something) - seq_puts(m, "-"); -} - void __symbol_put(const char *symbol) { struct find_symbol_arg fsa = { @@ -1099,12 +854,6 @@ void module_put(struct module *module) EXPORT_SYMBOL(module_put); #else /* !CONFIG_MODULE_UNLOAD */ -static inline void print_unload_info(struct seq_file *m, struct module *mod) -{ - /* We don't know the usage count, or what modules are using. */ - seq_puts(m, " - -"); -} - static inline void module_unload_free(struct module *mod) { } @@ -1120,13 +869,13 @@ static inline int module_unload_init(struct module *mod) } #endif /* CONFIG_MODULE_UNLOAD */ -static size_t module_flags_taint(struct module *mod, char *buf) +size_t module_flags_taint(unsigned long taints, char *buf) { size_t l = 0; int i; for (i = 0; i < TAINT_FLAGS_COUNT; i++) { - if (taint_flags[i].module && test_bit(i, &mod->taints)) + if (taint_flags[i].module && test_bit(i, &taints)) buf[l++] = taint_flags[i].c_true; } @@ -1179,6 +928,17 @@ static ssize_t show_coresize(struct module_attribute *mattr, static struct module_attribute modinfo_coresize = __ATTR(coresize, 0444, show_coresize, NULL); +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC +static ssize_t show_datasize(struct module_attribute *mattr, + struct module_kobject *mk, char *buffer) +{ + return sprintf(buffer, "%u\n", mk->mod->data_layout.size); +} + +static struct module_attribute modinfo_datasize = + __ATTR(datasize, 0444, show_datasize, NULL); +#endif + static ssize_t show_initsize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { @@ -1193,7 +953,7 @@ static ssize_t show_taint(struct module_attribute *mattr, { size_t l; - l = module_flags_taint(mk->mod, buffer); + l = module_flags_taint(mk->mod->taints, buffer); buffer[l++] = '\n'; return l; } @@ -1201,12 +961,15 @@ static ssize_t show_taint(struct module_attribute *mattr, static struct module_attribute modinfo_taint = __ATTR(taint, 0444, show_taint, NULL); -static struct module_attribute *modinfo_attrs[] = { +struct module_attribute *modinfo_attrs[] = { &module_uevent, &modinfo_version, &modinfo_srcversion, &modinfo_initstate, &modinfo_coresize, +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + &modinfo_datasize, +#endif &modinfo_initsize, &modinfo_taint, #ifdef CONFIG_MODULE_UNLOAD @@ -1215,9 +978,11 @@ static struct module_attribute *modinfo_attrs[] = { NULL, }; +size_t modinfo_attrs_count = ARRAY_SIZE(modinfo_attrs); + static const char vermagic[] = VERMAGIC_STRING; -static int try_to_force_load(struct module *mod, const char *reason) +int try_to_force_load(struct module *mod, const char *reason) { #ifdef CONFIG_MODULE_FORCE_LOAD if (!test_taint(TAINT_FORCED_MODULE)) @@ -1229,115 +994,6 @@ static int try_to_force_load(struct module *mod, const char *reason) #endif } -#ifdef CONFIG_MODVERSIONS - -static u32 resolve_rel_crc(const s32 *crc) -{ - return *(u32 *)((void *)crc + *crc); -} - -static int check_version(const struct load_info *info, - const char *symname, - struct module *mod, - const s32 *crc) -{ - Elf_Shdr *sechdrs = info->sechdrs; - unsigned int versindex = info->index.vers; - unsigned int i, num_versions; - struct modversion_info *versions; - - /* Exporting module didn't supply crcs? OK, we're already tainted. */ - if (!crc) - return 1; - - /* No versions at all? modprobe --force does this. */ - if (versindex == 0) - return try_to_force_load(mod, symname) == 0; - - versions = (void *) sechdrs[versindex].sh_addr; - num_versions = sechdrs[versindex].sh_size - / sizeof(struct modversion_info); - - for (i = 0; i < num_versions; i++) { - u32 crcval; - - if (strcmp(versions[i].name, symname) != 0) - continue; - - if (IS_ENABLED(CONFIG_MODULE_REL_CRCS)) - crcval = resolve_rel_crc(crc); - else - crcval = *crc; - if (versions[i].crc == crcval) - return 1; - pr_debug("Found checksum %X vs module %lX\n", - crcval, versions[i].crc); - goto bad_version; - } - - /* Broken toolchain. Warn once, then let it go.. */ - pr_warn_once("%s: no symbol version for %s\n", info->name, symname); - return 1; - -bad_version: - pr_warn("%s: disagrees about version of symbol %s\n", - info->name, symname); - return 0; -} - -static inline int check_modstruct_version(const struct load_info *info, - struct module *mod) -{ - struct find_symbol_arg fsa = { - .name = "module_layout", - .gplok = true, - }; - - /* - * Since this should be found in kernel (which can't be removed), no - * locking is necessary -- use preempt_disable() to placate lockdep. - */ - preempt_disable(); - if (!find_symbol(&fsa)) { - preempt_enable(); - BUG(); - } - preempt_enable(); - return check_version(info, "module_layout", mod, fsa.crc); -} - -/* First part is kernel version, which we ignore if module has crcs. */ -static inline int same_magic(const char *amagic, const char *bmagic, - bool has_crcs) -{ - if (has_crcs) { - amagic += strcspn(amagic, " "); - bmagic += strcspn(bmagic, " "); - } - return strcmp(amagic, bmagic) == 0; -} -#else -static inline int check_version(const struct load_info *info, - const char *symname, - struct module *mod, - const s32 *crc) -{ - return 1; -} - -static inline int check_modstruct_version(const struct load_info *info, - struct module *mod) -{ - return 1; -} - -static inline int same_magic(const char *amagic, const char *bmagic, - bool has_crcs) -{ - return strcmp(amagic, bmagic) == 0; -} -#endif /* CONFIG_MODVERSIONS */ - static char *get_modinfo(const struct load_info *info, const char *tag); static char *get_next_modinfo(const struct load_info *info, const char *tag, char *prev); @@ -1372,20 +1028,20 @@ static int verify_namespace_is_imported(const struct load_info *info, return 0; } -static bool inherit_taint(struct module *mod, struct module *owner) +static bool inherit_taint(struct module *mod, struct module *owner, const char *name) { if (!owner || !test_bit(TAINT_PROPRIETARY_MODULE, &owner->taints)) return true; if (mod->using_gplonly_symbols) { - pr_err("%s: module using GPL-only symbols uses symbols from proprietary module %s.\n", - mod->name, owner->name); + pr_err("%s: module using GPL-only symbols uses symbols %s from proprietary module %s.\n", + mod->name, name, owner->name); return false; } if (!test_bit(TAINT_PROPRIETARY_MODULE, &mod->taints)) { - pr_warn("%s: module uses symbols from proprietary module %s, inheriting taint.\n", - mod->name, owner->name); + pr_warn("%s: module uses symbols %s from proprietary module %s, inheriting taint.\n", + mod->name, name, owner->name); set_bit(TAINT_PROPRIETARY_MODULE, &mod->taints); } return true; @@ -1417,7 +1073,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod, if (fsa.license == GPL_ONLY) mod->using_gplonly_symbols = true; - if (!inherit_taint(mod, fsa.owner)) { + if (!inherit_taint(mod, fsa.owner, name)) { fsa.sym = NULL; goto getname; } @@ -1465,674 +1121,6 @@ resolve_symbol_wait(struct module *mod, return ksym; } -#ifdef CONFIG_KALLSYMS -static inline bool sect_empty(const Elf_Shdr *sect) -{ - return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0; -} -#endif - -/* - * /sys/module/foo/sections stuff - * J. Corbet <corbet@lwn.net> - */ -#ifdef CONFIG_SYSFS - -#ifdef CONFIG_KALLSYMS -struct module_sect_attr { - struct bin_attribute battr; - unsigned long address; -}; - -struct module_sect_attrs { - struct attribute_group grp; - unsigned int nsections; - struct module_sect_attr attrs[]; -}; - -#define MODULE_SECT_READ_SIZE (3 /* "0x", "\n" */ + (BITS_PER_LONG / 4)) -static ssize_t module_sect_read(struct file *file, struct kobject *kobj, - struct bin_attribute *battr, - char *buf, loff_t pos, size_t count) -{ - struct module_sect_attr *sattr = - container_of(battr, struct module_sect_attr, battr); - char bounce[MODULE_SECT_READ_SIZE + 1]; - size_t wrote; - - if (pos != 0) - return -EINVAL; - - /* - * Since we're a binary read handler, we must account for the - * trailing NUL byte that sprintf will write: if "buf" is - * too small to hold the NUL, or the NUL is exactly the last - * byte, the read will look like it got truncated by one byte. - * Since there is no way to ask sprintf nicely to not write - * the NUL, we have to use a bounce buffer. - */ - wrote = scnprintf(bounce, sizeof(bounce), "0x%px\n", - kallsyms_show_value(file->f_cred) - ? (void *)sattr->address : NULL); - count = min(count, wrote); - memcpy(buf, bounce, count); - - return count; -} - -static void free_sect_attrs(struct module_sect_attrs *sect_attrs) -{ - unsigned int section; - - for (section = 0; section < sect_attrs->nsections; section++) - kfree(sect_attrs->attrs[section].battr.attr.name); - kfree(sect_attrs); -} - -static void add_sect_attrs(struct module *mod, const struct load_info *info) -{ - unsigned int nloaded = 0, i, size[2]; - struct module_sect_attrs *sect_attrs; - struct module_sect_attr *sattr; - struct bin_attribute **gattr; - - /* Count loaded sections and allocate structures */ - for (i = 0; i < info->hdr->e_shnum; i++) - if (!sect_empty(&info->sechdrs[i])) - nloaded++; - size[0] = ALIGN(struct_size(sect_attrs, attrs, nloaded), - sizeof(sect_attrs->grp.bin_attrs[0])); - size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]); - sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL); - if (sect_attrs == NULL) - return; - - /* Setup section attributes. */ - sect_attrs->grp.name = "sections"; - sect_attrs->grp.bin_attrs = (void *)sect_attrs + size[0]; - - sect_attrs->nsections = 0; - sattr = §_attrs->attrs[0]; - gattr = §_attrs->grp.bin_attrs[0]; - for (i = 0; i < info->hdr->e_shnum; i++) { - Elf_Shdr *sec = &info->sechdrs[i]; - if (sect_empty(sec)) - continue; - sysfs_bin_attr_init(&sattr->battr); - sattr->address = sec->sh_addr; - sattr->battr.attr.name = - kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL); - if (sattr->battr.attr.name == NULL) - goto out; - sect_attrs->nsections++; - sattr->battr.read = module_sect_read; - sattr->battr.size = MODULE_SECT_READ_SIZE; - sattr->battr.attr.mode = 0400; - *(gattr++) = &(sattr++)->battr; - } - *gattr = NULL; - - if (sysfs_create_group(&mod->mkobj.kobj, §_attrs->grp)) - goto out; - - mod->sect_attrs = sect_attrs; - return; - out: - free_sect_attrs(sect_attrs); -} - -static void remove_sect_attrs(struct module *mod) -{ - if (mod->sect_attrs) { - sysfs_remove_group(&mod->mkobj.kobj, - &mod->sect_attrs->grp); - /* - * We are positive that no one is using any sect attrs - * at this point. Deallocate immediately. - */ - free_sect_attrs(mod->sect_attrs); - mod->sect_attrs = NULL; - } -} - -/* - * /sys/module/foo/notes/.section.name gives contents of SHT_NOTE sections. - */ - -struct module_notes_attrs { - struct kobject *dir; - unsigned int notes; - struct bin_attribute attrs[]; -}; - -static ssize_t module_notes_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *bin_attr, - char *buf, loff_t pos, size_t count) -{ - /* - * The caller checked the pos and count against our size. - */ - memcpy(buf, bin_attr->private + pos, count); - return count; -} - -static void free_notes_attrs(struct module_notes_attrs *notes_attrs, - unsigned int i) -{ - if (notes_attrs->dir) { - while (i-- > 0) - sysfs_remove_bin_file(notes_attrs->dir, - ¬es_attrs->attrs[i]); - kobject_put(notes_attrs->dir); - } - kfree(notes_attrs); -} - -static void add_notes_attrs(struct module *mod, const struct load_info *info) -{ - unsigned int notes, loaded, i; - struct module_notes_attrs *notes_attrs; - struct bin_attribute *nattr; - - /* failed to create section attributes, so can't create notes */ - if (!mod->sect_attrs) - return; - - /* Count notes sections and allocate structures. */ - notes = 0; - for (i = 0; i < info->hdr->e_shnum; i++) - if (!sect_empty(&info->sechdrs[i]) && - (info->sechdrs[i].sh_type == SHT_NOTE)) - ++notes; - - if (notes == 0) - return; - - notes_attrs = kzalloc(struct_size(notes_attrs, attrs, notes), - GFP_KERNEL); - if (notes_attrs == NULL) - return; - - notes_attrs->notes = notes; - nattr = ¬es_attrs->attrs[0]; - for (loaded = i = 0; i < info->hdr->e_shnum; ++i) { - if (sect_empty(&info->sechdrs[i])) - continue; - if (info->sechdrs[i].sh_type == SHT_NOTE) { - sysfs_bin_attr_init(nattr); - nattr->attr.name = mod->sect_attrs->attrs[loaded].battr.attr.name; - nattr->attr.mode = S_IRUGO; - nattr->size = info->sechdrs[i].sh_size; - nattr->private = (void *) info->sechdrs[i].sh_addr; - nattr->read = module_notes_read; - ++nattr; - } - ++loaded; - } - - notes_attrs->dir = kobject_create_and_add("notes", &mod->mkobj.kobj); - if (!notes_attrs->dir) - goto out; - - for (i = 0; i < notes; ++i) - if (sysfs_create_bin_file(notes_attrs->dir, - ¬es_attrs->attrs[i])) - goto out; - - mod->notes_attrs = notes_attrs; - return; - - out: - free_notes_attrs(notes_attrs, i); -} - -static void remove_notes_attrs(struct module *mod) -{ - if (mod->notes_attrs) - free_notes_attrs(mod->notes_attrs, mod->notes_attrs->notes); -} - -#else - -static inline void add_sect_attrs(struct module *mod, - const struct load_info *info) -{ -} - -static inline void remove_sect_attrs(struct module *mod) -{ -} - -static inline void add_notes_attrs(struct module *mod, - const struct load_info *info) -{ -} - -static inline void remove_notes_attrs(struct module *mod) -{ -} -#endif /* CONFIG_KALLSYMS */ - -static void del_usage_links(struct module *mod) -{ -#ifdef CONFIG_MODULE_UNLOAD - struct module_use *use; - - mutex_lock(&module_mutex); - list_for_each_entry(use, &mod->target_list, target_list) - sysfs_remove_link(use->target->holders_dir, mod->name); - mutex_unlock(&module_mutex); -#endif -} - -static int add_usage_links(struct module *mod) -{ - int ret = 0; -#ifdef CONFIG_MODULE_UNLOAD - struct module_use *use; - - mutex_lock(&module_mutex); - list_for_each_entry(use, &mod->target_list, target_list) { - ret = sysfs_create_link(use->target->holders_dir, - &mod->mkobj.kobj, mod->name); - if (ret) - break; - } - mutex_unlock(&module_mutex); - if (ret) - del_usage_links(mod); -#endif - return ret; -} - -static void module_remove_modinfo_attrs(struct module *mod, int end); - -static int module_add_modinfo_attrs(struct module *mod) -{ - struct module_attribute *attr; - struct module_attribute *temp_attr; - int error = 0; - int i; - - mod->modinfo_attrs = kzalloc((sizeof(struct module_attribute) * - (ARRAY_SIZE(modinfo_attrs) + 1)), - GFP_KERNEL); - if (!mod->modinfo_attrs) - return -ENOMEM; - - temp_attr = mod->modinfo_attrs; - for (i = 0; (attr = modinfo_attrs[i]); i++) { - if (!attr->test || attr->test(mod)) { - memcpy(temp_attr, attr, sizeof(*temp_attr)); - sysfs_attr_init(&temp_attr->attr); - error = sysfs_create_file(&mod->mkobj.kobj, - &temp_attr->attr); - if (error) - goto error_out; - ++temp_attr; - } - } - - return 0; - -error_out: - if (i > 0) - module_remove_modinfo_attrs(mod, --i); - else - kfree(mod->modinfo_attrs); - return error; -} - -static void module_remove_modinfo_attrs(struct module *mod, int end) -{ - struct module_attribute *attr; - int i; - - for (i = 0; (attr = &mod->modinfo_attrs[i]); i++) { - if (end >= 0 && i > end) - break; - /* pick a field to test for end of list */ - if (!attr->attr.name) - break; - sysfs_remove_file(&mod->mkobj.kobj, &attr->attr); - if (attr->free) - attr->free(mod); - } - kfree(mod->modinfo_attrs); -} - -static void mod_kobject_put(struct module *mod) -{ - DECLARE_COMPLETION_ONSTACK(c); - mod->mkobj.kobj_completion = &c; - kobject_put(&mod->mkobj.kobj); - wait_for_completion(&c); -} - -static int mod_sysfs_init(struct module *mod) -{ - int err; - struct kobject *kobj; - - if (!module_sysfs_initialized) { - pr_err("%s: module sysfs not initialized\n", mod->name); - err = -EINVAL; - goto out; - } - - kobj = kset_find_obj(module_kset, mod->name); - if (kobj) { - pr_err("%s: module is already loaded\n", mod->name); - kobject_put(kobj); - err = -EINVAL; - goto out; - } - - mod->mkobj.mod = mod; - - memset(&mod->mkobj.kobj, 0, sizeof(mod->mkobj.kobj)); - mod->mkobj.kobj.kset = module_kset; - err = kobject_init_and_add(&mod->mkobj.kobj, &module_ktype, NULL, - "%s", mod->name); - if (err) - mod_kobject_put(mod); - -out: - return err; -} - -static int mod_sysfs_setup(struct module *mod, - const struct load_info *info, - struct kernel_param *kparam, - unsigned int num_params) -{ - int err; - - err = mod_sysfs_init(mod); - if (err) - goto out; - - mod->holders_dir = kobject_create_and_add("holders", &mod->mkobj.kobj); - if (!mod->holders_dir) { - err = -ENOMEM; - goto out_unreg; - } - - err = module_param_sysfs_setup(mod, kparam, num_params); - if (err) - goto out_unreg_holders; - - err = module_add_modinfo_attrs(mod); - if (err) - goto out_unreg_param; - - err = add_usage_links(mod); - if (err) - goto out_unreg_modinfo_attrs; - - add_sect_attrs(mod, info); - add_notes_attrs(mod, info); - - return 0; - -out_unreg_modinfo_attrs: - module_remove_modinfo_attrs(mod, -1); -out_unreg_param: - module_param_sysfs_remove(mod); -out_unreg_holders: - kobject_put(mod->holders_dir); -out_unreg: - mod_kobject_put(mod); -out: - return err; -} - -static void mod_sysfs_fini(struct module *mod) -{ - remove_notes_attrs(mod); - remove_sect_attrs(mod); - mod_kobject_put(mod); -} - -static void init_param_lock(struct module *mod) -{ - mutex_init(&mod->param_lock); -} -#else /* !CONFIG_SYSFS */ - -static int mod_sysfs_setup(struct module *mod, - const struct load_info *info, - struct kernel_param *kparam, - unsigned int num_params) -{ - return 0; -} - -static void mod_sysfs_fini(struct module *mod) -{ -} - -static void module_remove_modinfo_attrs(struct module *mod, int end) -{ -} - -static void del_usage_links(struct module *mod) -{ -} - -static void init_param_lock(struct module *mod) -{ -} -#endif /* CONFIG_SYSFS */ - -static void mod_sysfs_teardown(struct module *mod) -{ - del_usage_links(mod); - module_remove_modinfo_attrs(mod, -1); - module_param_sysfs_remove(mod); - kobject_put(mod->mkobj.drivers_dir); - kobject_put(mod->holders_dir); - mod_sysfs_fini(mod); -} - -/* - * LKM RO/NX protection: protect module's text/ro-data - * from modification and any data from execution. - * - * General layout of module is: - * [text] [read-only-data] [ro-after-init] [writable data] - * text_size -----^ ^ ^ ^ - * ro_size ------------------------| | | - * ro_after_init_size -----------------------------| | - * size -----------------------------------------------------------| - * - * These values are always page-aligned (as is base) - */ - -/* - * Since some arches are moving towards PAGE_KERNEL module allocations instead - * of PAGE_KERNEL_EXEC, keep frob_text() and module_enable_x() outside of the - * CONFIG_STRICT_MODULE_RWX block below because they are needed regardless of - * whether we are strict. - */ -#ifdef CONFIG_ARCH_HAS_STRICT_MODULE_RWX -static void frob_text(const struct module_layout *layout, - int (*set_memory)(unsigned long start, int num_pages)) -{ - BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); - BUG_ON((unsigned long)layout->text_size & (PAGE_SIZE-1)); - set_memory((unsigned long)layout->base, - layout->text_size >> PAGE_SHIFT); -} - -static void module_enable_x(const struct module *mod) -{ - frob_text(&mod->core_layout, set_memory_x); - frob_text(&mod->init_layout, set_memory_x); -} -#else /* !CONFIG_ARCH_HAS_STRICT_MODULE_RWX */ -static void module_enable_x(const struct module *mod) { } -#endif /* CONFIG_ARCH_HAS_STRICT_MODULE_RWX */ - -#ifdef CONFIG_STRICT_MODULE_RWX -static void frob_rodata(const struct module_layout *layout, - int (*set_memory)(unsigned long start, int num_pages)) -{ - BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); - BUG_ON((unsigned long)layout->text_size & (PAGE_SIZE-1)); - BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1)); - set_memory((unsigned long)layout->base + layout->text_size, - (layout->ro_size - layout->text_size) >> PAGE_SHIFT); -} - -static void frob_ro_after_init(const struct module_layout *layout, - int (*set_memory)(unsigned long start, int num_pages)) -{ - BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); - BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1)); - BUG_ON((unsigned long)layout->ro_after_init_size & (PAGE_SIZE-1)); - set_memory((unsigned long)layout->base + layout->ro_size, - (layout->ro_after_init_size - layout->ro_size) >> PAGE_SHIFT); -} - -static void frob_writable_data(const struct module_layout *layout, - int (*set_memory)(unsigned long start, int num_pages)) -{ - BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); - BUG_ON((unsigned long)layout->ro_after_init_size & (PAGE_SIZE-1)); - BUG_ON((unsigned long)layout->size & (PAGE_SIZE-1)); - set_memory((unsigned long)layout->base + layout->ro_after_init_size, - (layout->size - layout->ro_after_init_size) >> PAGE_SHIFT); -} - -static void module_enable_ro(const struct module *mod, bool after_init) -{ - if (!rodata_enabled) - return; - - set_vm_flush_reset_perms(mod->core_layout.base); - set_vm_flush_reset_perms(mod->init_layout.base); - frob_text(&mod->core_layout, set_memory_ro); - - frob_rodata(&mod->core_layout, set_memory_ro); - frob_text(&mod->init_layout, set_memory_ro); - frob_rodata(&mod->init_layout, set_memory_ro); - - if (after_init) - frob_ro_after_init(&mod->core_layout, set_memory_ro); -} - -static void module_enable_nx(const struct module *mod) -{ - frob_rodata(&mod->core_layout, set_memory_nx); - frob_ro_after_init(&mod->core_layout, set_memory_nx); - frob_writable_data(&mod->core_layout, set_memory_nx); - frob_rodata(&mod->init_layout, set_memory_nx); - frob_writable_data(&mod->init_layout, set_memory_nx); -} - -static int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, - char *secstrings, struct module *mod) -{ - const unsigned long shf_wx = SHF_WRITE|SHF_EXECINSTR; - int i; - - for (i = 0; i < hdr->e_shnum; i++) { - if ((sechdrs[i].sh_flags & shf_wx) == shf_wx) { - pr_err("%s: section %s (index %d) has invalid WRITE|EXEC flags\n", - mod->name, secstrings + sechdrs[i].sh_name, i); - return -ENOEXEC; - } - } - - return 0; -} - -#else /* !CONFIG_STRICT_MODULE_RWX */ -static void module_enable_nx(const struct module *mod) { } -static void module_enable_ro(const struct module *mod, bool after_init) {} -static int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, - char *secstrings, struct module *mod) -{ - return 0; -} -#endif /* CONFIG_STRICT_MODULE_RWX */ - -#ifdef CONFIG_LIVEPATCH -/* - * Persist Elf information about a module. Copy the Elf header, - * section header table, section string table, and symtab section - * index from info to mod->klp_info. - */ -static int copy_module_elf(struct module *mod, struct load_info *info) -{ - unsigned int size, symndx; - int ret; - - size = sizeof(*mod->klp_info); - mod->klp_info = kmalloc(size, GFP_KERNEL); - if (mod->klp_info == NULL) - return -ENOMEM; - - /* Elf header */ - size = sizeof(mod->klp_info->hdr); - memcpy(&mod->klp_info->hdr, info->hdr, size); - - /* Elf section header table */ - size = sizeof(*info->sechdrs) * info->hdr->e_shnum; - mod->klp_info->sechdrs = kmemdup(info->sechdrs, size, GFP_KERNEL); - if (mod->klp_info->sechdrs == NULL) { - ret = -ENOMEM; - goto free_info; - } - - /* Elf section name string table */ - size = info->sechdrs[info->hdr->e_shstrndx].sh_size; - mod->klp_info->secstrings = kmemdup(info->secstrings, size, GFP_KERNEL); - if (mod->klp_info->secstrings == NULL) { - ret = -ENOMEM; - goto free_sechdrs; - } - - /* Elf symbol section index */ - symndx = info->index.sym; - mod->klp_info->symndx = symndx; - - /* - * For livepatch modules, core_kallsyms.symtab is a complete - * copy of the original symbol table. Adjust sh_addr to point - * to core_kallsyms.symtab since the copy of the symtab in module - * init memory is freed at the end of do_init_module(). - */ - mod->klp_info->sechdrs[symndx].sh_addr = \ - (unsigned long) mod->core_kallsyms.symtab; - - return 0; - -free_sechdrs: - kfree(mod->klp_info->sechdrs); -free_info: - kfree(mod->klp_info); - return ret; -} - -static void free_module_elf(struct module *mod) -{ - kfree(mod->klp_info->sechdrs); - kfree(mod->klp_info->secstrings); - kfree(mod->klp_info); -} -#else /* !CONFIG_LIVEPATCH */ -static int copy_module_elf(struct module *mod, struct load_info *info) -{ - return 0; -} - -static void free_module_elf(struct module *mod) -{ -} -#endif /* CONFIG_LIVEPATCH */ - void __weak module_memfree(void *module_region) { /* @@ -2192,6 +1180,9 @@ static void free_module(struct module *mod) module_bug_cleanup(mod); /* Wait for RCU-sched synchronizing before releasing mod->list and buglist. */ synchronize_rcu(); + if (try_add_tainted_module(mod)) + pr_err("%s: adding tainted module to the unloaded tainted modules list failed.\n", + mod->name); mutex_unlock(&module_mutex); /* Clean up CFI for the module. */ @@ -2204,10 +1195,13 @@ static void free_module(struct module *mod) percpu_modfree(mod); /* Free lock-classes; relies on the preceding sync_rcu(). */ - lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); + lockdep_free_key_range(mod->data_layout.base, mod->data_layout.size); /* Finally, free the core (containing the module structure) */ module_memfree(mod->core_layout.base); +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + vfree(mod->data_layout.base); +#endif } void *__symbol_get(const char *symbol) @@ -2395,7 +1389,7 @@ unsigned int __weak arch_mod_section_prepend(struct module *mod, } /* Update size with this section: return offset. */ -static long get_offset(struct module *mod, unsigned int *size, +long module_get_offset(struct module *mod, unsigned int *size, Elf_Shdr *sechdr, unsigned int section) { long ret; @@ -2445,30 +1439,32 @@ static void layout_sections(struct module *mod, struct load_info *info) for (i = 0; i < info->hdr->e_shnum; ++i) { Elf_Shdr *s = &info->sechdrs[i]; const char *sname = info->secstrings + s->sh_name; + unsigned int *sizep; if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL || module_init_layout_section(sname)) continue; - s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i); + sizep = m ? &mod->data_layout.size : &mod->core_layout.size; + s->sh_entsize = module_get_offset(mod, sizep, s, i); pr_debug("\t%s\n", sname); } switch (m) { case 0: /* executable */ - mod->core_layout.size = debug_align(mod->core_layout.size); + mod->core_layout.size = strict_align(mod->core_layout.size); mod->core_layout.text_size = mod->core_layout.size; break; case 1: /* RO: text and ro-data */ - mod->core_layout.size = debug_align(mod->core_layout.size); - mod->core_layout.ro_size = mod->core_layout.size; + mod->data_layout.size = strict_align(mod->data_layout.size); + mod->data_layout.ro_size = mod->data_layout.size; break; case 2: /* RO after init */ - mod->core_layout.size = debug_align(mod->core_layout.size); - mod->core_layout.ro_after_init_size = mod->core_layout.size; + mod->data_layout.size = strict_align(mod->data_layout.size); + mod->data_layout.ro_after_init_size = mod->data_layout.size; break; case 4: /* whole core */ - mod->core_layout.size = debug_align(mod->core_layout.size); + mod->data_layout.size = strict_align(mod->data_layout.size); break; } } @@ -2484,17 +1480,17 @@ static void layout_sections(struct module *mod, struct load_info *info) || s->sh_entsize != ~0UL || !module_init_layout_section(sname)) continue; - s->sh_entsize = (get_offset(mod, &mod->init_layout.size, s, i) + s->sh_entsize = (module_get_offset(mod, &mod->init_layout.size, s, i) | INIT_OFFSET_MASK); pr_debug("\t%s\n", sname); } switch (m) { case 0: /* executable */ - mod->init_layout.size = debug_align(mod->init_layout.size); + mod->init_layout.size = strict_align(mod->init_layout.size); mod->init_layout.text_size = mod->init_layout.size; break; case 1: /* RO: text and ro-data */ - mod->init_layout.size = debug_align(mod->init_layout.size); + mod->init_layout.size = strict_align(mod->init_layout.size); mod->init_layout.ro_size = mod->init_layout.size; break; case 2: @@ -2505,7 +1501,7 @@ static void layout_sections(struct module *mod, struct load_info *info) mod->init_layout.ro_after_init_size = mod->init_layout.ro_size; break; case 4: /* whole init */ - mod->init_layout.size = debug_align(mod->init_layout.size); + mod->init_layout.size = strict_align(mod->init_layout.size); break; } } @@ -2597,228 +1593,6 @@ static void free_modinfo(struct module *mod) } } -#ifdef CONFIG_KALLSYMS - -/* Lookup exported symbol in given range of kernel_symbols */ -static const struct kernel_symbol *lookup_exported_symbol(const char *name, - const struct kernel_symbol *start, - const struct kernel_symbol *stop) -{ - return bsearch(name, start, stop - start, - sizeof(struct kernel_symbol), cmp_name); -} - -static int is_exported(const char *name, unsigned long value, - const struct module *mod) -{ - const struct kernel_symbol *ks; - if (!mod) - ks = lookup_exported_symbol(name, __start___ksymtab, __stop___ksymtab); - else - ks = lookup_exported_symbol(name, mod->syms, mod->syms + mod->num_syms); - - return ks != NULL && kernel_symbol_value(ks) == value; -} - -/* As per nm */ -static char elf_type(const Elf_Sym *sym, const struct load_info *info) -{ - const Elf_Shdr *sechdrs = info->sechdrs; - - if (ELF_ST_BIND(sym->st_info) == STB_WEAK) { - if (ELF_ST_TYPE(sym->st_info) == STT_OBJECT) - return 'v'; - else - return 'w'; - } - if (sym->st_shndx == SHN_UNDEF) - return 'U'; - if (sym->st_shndx == SHN_ABS || sym->st_shndx == info->index.pcpu) - return 'a'; - if (sym->st_shndx >= SHN_LORESERVE) - return '?'; - if (sechdrs[sym->st_shndx].sh_flags & SHF_EXECINSTR) - return 't'; - if (sechdrs[sym->st_shndx].sh_flags & SHF_ALLOC - && sechdrs[sym->st_shndx].sh_type != SHT_NOBITS) { - if (!(sechdrs[sym->st_shndx].sh_flags & SHF_WRITE)) - return 'r'; - else if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) - return 'g'; - else - return 'd'; - } - if (sechdrs[sym->st_shndx].sh_type == SHT_NOBITS) { - if (sechdrs[sym->st_shndx].sh_flags & ARCH_SHF_SMALL) - return 's'; - else - return 'b'; - } - if (strstarts(info->secstrings + sechdrs[sym->st_shndx].sh_name, - ".debug")) { - return 'n'; - } - return '?'; -} - -static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, - unsigned int shnum, unsigned int pcpundx) -{ - const Elf_Shdr *sec; - - if (src->st_shndx == SHN_UNDEF - || src->st_shndx >= shnum - || !src->st_name) - return false; - -#ifdef CONFIG_KALLSYMS_ALL - if (src->st_shndx == pcpundx) - return true; -#endif - - sec = sechdrs + src->st_shndx; - if (!(sec->sh_flags & SHF_ALLOC) -#ifndef CONFIG_KALLSYMS_ALL - || !(sec->sh_flags & SHF_EXECINSTR) -#endif - || (sec->sh_entsize & INIT_OFFSET_MASK)) - return false; - - return true; -} - -/* - * We only allocate and copy the strings needed by the parts of symtab - * we keep. This is simple, but has the effect of making multiple - * copies of duplicates. We could be more sophisticated, see - * linux-kernel thread starting with - * <73defb5e4bca04a6431392cc341112b1@localhost>. - */ -static void layout_symtab(struct module *mod, struct load_info *info) -{ - Elf_Shdr *symsect = info->sechdrs + info->index.sym; - Elf_Shdr *strsect = info->sechdrs + info->index.str; - const Elf_Sym *src; - unsigned int i, nsrc, ndst, strtab_size = 0; - - /* Put symbol section at end of init part of module. */ - symsect->sh_flags |= SHF_ALLOC; - symsect->sh_entsize = get_offset(mod, &mod->init_layout.size, symsect, - info->index.sym) | INIT_OFFSET_MASK; - pr_debug("\t%s\n", info->secstrings + symsect->sh_name); - - src = (void *)info->hdr + symsect->sh_offset; - nsrc = symsect->sh_size / sizeof(*src); - - /* Compute total space required for the core symbols' strtab. */ - for (ndst = i = 0; i < nsrc; i++) { - if (i == 0 || is_livepatch_module(mod) || - is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum, - info->index.pcpu)) { - strtab_size += strlen(&info->strtab[src[i].st_name])+1; - ndst++; - } - } - - /* Append room for core symbols at end of core part. */ - info->symoffs = ALIGN(mod->core_layout.size, symsect->sh_addralign ?: 1); - info->stroffs = mod->core_layout.size = info->symoffs + ndst * sizeof(Elf_Sym); - mod->core_layout.size += strtab_size; - info->core_typeoffs = mod->core_layout.size; - mod->core_layout.size += ndst * sizeof(char); - mod->core_layout.size = debug_align(mod->core_layout.size); - - /* Put string table section at end of init part of module. */ - strsect->sh_flags |= SHF_ALLOC; - strsect->sh_entsize = get_offset(mod, &mod->init_layout.size, strsect, - info->index.str) | INIT_OFFSET_MASK; - pr_debug("\t%s\n", info->secstrings + strsect->sh_name); - - /* We'll tack temporary mod_kallsyms on the end. */ - mod->init_layout.size = ALIGN(mod->init_layout.size, - __alignof__(struct mod_kallsyms)); - info->mod_kallsyms_init_off = mod->init_layout.size; - mod->init_layout.size += sizeof(struct mod_kallsyms); - info->init_typeoffs = mod->init_layout.size; - mod->init_layout.size += nsrc * sizeof(char); - mod->init_layout.size = debug_align(mod->init_layout.size); -} - -/* - * We use the full symtab and strtab which layout_symtab arranged to - * be appended to the init section. Later we switch to the cut-down - * core-only ones. - */ -static void add_kallsyms(struct module *mod, const struct load_info *info) -{ - unsigned int i, ndst; - const Elf_Sym *src; - Elf_Sym *dst; - char *s; - Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; - - /* Set up to point into init section. */ - mod->kallsyms = mod->init_layout.base + info->mod_kallsyms_init_off; - - mod->kallsyms->symtab = (void *)symsec->sh_addr; - mod->kallsyms->num_symtab = symsec->sh_size / sizeof(Elf_Sym); - /* Make sure we get permanent strtab: don't use info->strtab. */ - mod->kallsyms->strtab = (void *)info->sechdrs[info->index.str].sh_addr; - mod->kallsyms->typetab = mod->init_layout.base + info->init_typeoffs; - - /* - * Now populate the cut down core kallsyms for after init - * and set types up while we still have access to sections. - */ - mod->core_kallsyms.symtab = dst = mod->core_layout.base + info->symoffs; - mod->core_kallsyms.strtab = s = mod->core_layout.base + info->stroffs; - mod->core_kallsyms.typetab = mod->core_layout.base + info->core_typeoffs; - src = mod->kallsyms->symtab; - for (ndst = i = 0; i < mod->kallsyms->num_symtab; i++) { - mod->kallsyms->typetab[i] = elf_type(src + i, info); - if (i == 0 || is_livepatch_module(mod) || - is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum, - info->index.pcpu)) { - mod->core_kallsyms.typetab[ndst] = - mod->kallsyms->typetab[i]; - dst[ndst] = src[i]; - dst[ndst++].st_name = s - mod->core_kallsyms.strtab; - s += strlcpy(s, &mod->kallsyms->strtab[src[i].st_name], - KSYM_NAME_LEN) + 1; - } - } - mod->core_kallsyms.num_symtab = ndst; -} -#else -static inline void layout_symtab(struct module *mod, struct load_info *info) -{ -} - -static void add_kallsyms(struct module *mod, const struct load_info *info) -{ -} -#endif /* CONFIG_KALLSYMS */ - -#if IS_ENABLED(CONFIG_KALLSYMS) && IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) -static void init_build_id(struct module *mod, const struct load_info *info) -{ - const Elf_Shdr *sechdr; - unsigned int i; - - for (i = 0; i < info->hdr->e_shnum; i++) { - sechdr = &info->sechdrs[i]; - if (!sect_empty(sechdr) && sechdr->sh_type == SHT_NOTE && - !build_id_parse_buf((void *)sechdr->sh_addr, mod->build_id, - sechdr->sh_size)) - break; - } -} -#else -static void init_build_id(struct module *mod, const struct load_info *info) -{ -} -#endif - static void dynamic_debug_setup(struct module *mod, struct _ddebug *debug, unsigned int num) { if (!debug) @@ -2849,97 +1623,6 @@ bool __weak module_exit_section(const char *name) return strstarts(name, ".exit"); } -#ifdef CONFIG_DEBUG_KMEMLEAK -static void kmemleak_load_module(const struct module *mod, - const struct load_info *info) -{ - unsigned int i; - - /* only scan the sections containing data */ - kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL); - - for (i = 1; i < info->hdr->e_shnum; i++) { - /* Scan all writable sections that's not executable */ - if (!(info->sechdrs[i].sh_flags & SHF_ALLOC) || - !(info->sechdrs[i].sh_flags & SHF_WRITE) || - (info->sechdrs[i].sh_flags & SHF_EXECINSTR)) - continue; - - kmemleak_scan_area((void *)info->sechdrs[i].sh_addr, - info->sechdrs[i].sh_size, GFP_KERNEL); - } -} -#else -static inline void kmemleak_load_module(const struct module *mod, - const struct load_info *info) -{ -} -#endif - -#ifdef CONFIG_MODULE_SIG -static int module_sig_check(struct load_info *info, int flags) -{ - int err = -ENODATA; - const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1; - const char *reason; - const void *mod = info->hdr; - bool mangled_module = flags & (MODULE_INIT_IGNORE_MODVERSIONS | - MODULE_INIT_IGNORE_VERMAGIC); - /* - * Do not allow mangled modules as a module with version information - * removed is no longer the module that was signed. - */ - if (!mangled_module && - info->len > markerlen && - memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) { - /* We truncate the module to discard the signature */ - info->len -= markerlen; - err = mod_verify_sig(mod, info); - if (!err) { - info->sig_ok = true; - return 0; - } - } - - /* - * We don't permit modules to be loaded into the trusted kernels - * without a valid signature on them, but if we're not enforcing, - * certain errors are non-fatal. - */ - switch (err) { - case -ENODATA: - reason = "unsigned module"; - break; - case -ENOPKG: - reason = "module with unsupported crypto"; - break; - case -ENOKEY: - reason = "module with unavailable key"; - break; - - default: - /* - * All other errors are fatal, including lack of memory, - * unparseable signatures, and signature check failures -- - * even if signatures aren't required. - */ - return err; - } - - if (is_module_sig_enforced()) { - pr_notice("Loading of %s is rejected\n", reason); - return -EKEYREJECTED; - } - - return security_locked_down(LOCKDOWN_MODULE_SIGNATURE); -} -#else /* !CONFIG_MODULE_SIG */ -static int module_sig_check(struct load_info *info, int flags) -{ - return 0; -} -#endif /* !CONFIG_MODULE_SIG */ - static int validate_section_offset(struct load_info *info, Elf_Shdr *shdr) { #if defined(CONFIG_64BIT) @@ -3033,6 +1716,10 @@ static int elf_validity_check(struct load_info *info) * strings in the section safe. */ info->secstrings = (void *)info->hdr + strhdr->sh_offset; + if (strhdr->sh_size == 0) { + pr_err("empty section name table\n"); + goto no_exec; + } if (info->secstrings[strhdr->sh_size - 1] != '\0') { pr_err("ELF Spec violation: section name table isn't null terminated\n"); goto no_exec; @@ -3107,30 +1794,23 @@ static int copy_chunked_from_user(void *dst, const void __user *usrc, unsigned l return 0; } -#ifdef CONFIG_LIVEPATCH static int check_modinfo_livepatch(struct module *mod, struct load_info *info) { - if (get_modinfo(info, "livepatch")) { - mod->klp = true; + if (!get_modinfo(info, "livepatch")) + /* Nothing more to do */ + return 0; + + if (set_livepatch_module(mod)) { add_taint_module(mod, TAINT_LIVEPATCH, LOCKDEP_STILL_OK); pr_notice_once("%s: tainting kernel with TAINT_LIVEPATCH\n", - mod->name); - } - - return 0; -} -#else /* !CONFIG_LIVEPATCH */ -static int check_modinfo_livepatch(struct module *mod, struct load_info *info) -{ - if (get_modinfo(info, "livepatch")) { - pr_err("%s: module is marked as livepatch module, but livepatch support is disabled", - mod->name); - return -ENOEXEC; + mod->name); + return 0; } - return 0; + pr_err("%s: module is marked as livepatch module, but livepatch support is disabled", + mod->name); + return -ENOEXEC; } -#endif /* CONFIG_LIVEPATCH */ static void check_modinfo_retpoline(struct module *mod, struct load_info *info) { @@ -3456,6 +2136,24 @@ static int move_module(struct module *mod, struct load_info *info) } else mod->init_layout.base = NULL; +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + /* Do the allocs. */ + ptr = vmalloc(mod->data_layout.size); + /* + * The pointer to this block is stored in the module structure + * which is inside the block. Just mark it as not being a + * leak. + */ + kmemleak_not_leak(ptr); + if (!ptr) { + module_memfree(mod->core_layout.base); + module_memfree(mod->init_layout.base); + return -ENOMEM; + } + + memset(ptr, 0, mod->data_layout.size); + mod->data_layout.base = ptr; +#endif /* Transfer each section which specifies SHF_ALLOC */ pr_debug("final section addresses:\n"); for (i = 0; i < info->hdr->e_shnum; i++) { @@ -3468,6 +2166,8 @@ static int move_module(struct module *mod, struct load_info *info) if (shdr->sh_entsize & INIT_OFFSET_MASK) dest = mod->init_layout.base + (shdr->sh_entsize & ~INIT_OFFSET_MASK); + else if (!(shdr->sh_flags & SHF_EXECINSTR)) + dest = mod->data_layout.base + shdr->sh_entsize; else dest = mod->core_layout.base + shdr->sh_entsize; @@ -3629,6 +2329,9 @@ static void module_deallocate(struct module *mod, struct load_info *info) module_arch_freeing_init(mod); module_memfree(mod->init_layout.base); module_memfree(mod->core_layout.base); +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + vfree(mod->data_layout.base); +#endif } int __weak module_finalize(const Elf_Ehdr *hdr, @@ -3879,6 +2582,9 @@ static int complete_formation(struct module *mod, struct load_info *info) /* This relies on module_mutex for list integrity. */ module_bug_finalize(info->hdr, info->sechdrs, mod); + if (module_check_misalignment(mod)) + goto out_misaligned; + module_enable_ro(mod, false); module_enable_nx(mod); module_enable_x(mod); @@ -3892,6 +2598,8 @@ static int complete_formation(struct module *mod, struct load_info *info) return 0; +out_misaligned: + err = -EINVAL; out: mutex_unlock(&module_mutex); return err; @@ -4158,7 +2866,7 @@ static int load_module(struct load_info *info, const char __user *uargs, mutex_unlock(&module_mutex); free_module: /* Free lock-classes; relies on the preceding sync_rcu() */ - lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); + lockdep_free_key_range(mod->data_layout.base, mod->data_layout.size); module_deallocate(mod, info); free_copy: @@ -4227,287 +2935,6 @@ static inline int within(unsigned long addr, void *start, unsigned long size) return ((void *)addr >= start && (void *)addr < start + size); } -#ifdef CONFIG_KALLSYMS -/* - * This ignores the intensely annoying "mapping symbols" found - * in ARM ELF files: $a, $t and $d. - */ -static inline int is_arm_mapping_symbol(const char *str) -{ - if (str[0] == '.' && str[1] == 'L') - return true; - return str[0] == '$' && strchr("axtd", str[1]) - && (str[2] == '\0' || str[2] == '.'); -} - -static const char *kallsyms_symbol_name(struct mod_kallsyms *kallsyms, unsigned int symnum) -{ - return kallsyms->strtab + kallsyms->symtab[symnum].st_name; -} - -/* - * Given a module and address, find the corresponding symbol and return its name - * while providing its size and offset if needed. - */ -static const char *find_kallsyms_symbol(struct module *mod, - unsigned long addr, - unsigned long *size, - unsigned long *offset) -{ - unsigned int i, best = 0; - unsigned long nextval, bestval; - struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); - - /* At worse, next value is at end of module */ - if (within_module_init(addr, mod)) - nextval = (unsigned long)mod->init_layout.base+mod->init_layout.text_size; - else - nextval = (unsigned long)mod->core_layout.base+mod->core_layout.text_size; - - bestval = kallsyms_symbol_value(&kallsyms->symtab[best]); - - /* - * Scan for closest preceding symbol, and next symbol. (ELF - * starts real symbols at 1). - */ - for (i = 1; i < kallsyms->num_symtab; i++) { - const Elf_Sym *sym = &kallsyms->symtab[i]; - unsigned long thisval = kallsyms_symbol_value(sym); - - if (sym->st_shndx == SHN_UNDEF) - continue; - - /* - * We ignore unnamed symbols: they're uninformative - * and inserted at a whim. - */ - if (*kallsyms_symbol_name(kallsyms, i) == '\0' - || is_arm_mapping_symbol(kallsyms_symbol_name(kallsyms, i))) - continue; - - if (thisval <= addr && thisval > bestval) { - best = i; - bestval = thisval; - } - if (thisval > addr && thisval < nextval) - nextval = thisval; - } - - if (!best) - return NULL; - - if (size) - *size = nextval - bestval; - if (offset) - *offset = addr - bestval; - - return kallsyms_symbol_name(kallsyms, best); -} - -void * __weak dereference_module_function_descriptor(struct module *mod, - void *ptr) -{ - return ptr; -} - -/* - * For kallsyms to ask for address resolution. NULL means not found. Careful - * not to lock to avoid deadlock on oopses, simply disable preemption. - */ -const char *module_address_lookup(unsigned long addr, - unsigned long *size, - unsigned long *offset, - char **modname, - const unsigned char **modbuildid, - char *namebuf) -{ - const char *ret = NULL; - struct module *mod; - - preempt_disable(); - mod = __module_address(addr); - if (mod) { - if (modname) - *modname = mod->name; - if (modbuildid) { -#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) - *modbuildid = mod->build_id; -#else - *modbuildid = NULL; -#endif - } - - ret = find_kallsyms_symbol(mod, addr, size, offset); - } - /* Make a copy in here where it's safe */ - if (ret) { - strncpy(namebuf, ret, KSYM_NAME_LEN - 1); - ret = namebuf; - } - preempt_enable(); - - return ret; -} - -int lookup_module_symbol_name(unsigned long addr, char *symname) -{ - struct module *mod; - - preempt_disable(); - list_for_each_entry_rcu(mod, &modules, list) { - if (mod->state == MODULE_STATE_UNFORMED) - continue; - if (within_module(addr, mod)) { - const char *sym; - - sym = find_kallsyms_symbol(mod, addr, NULL, NULL); - if (!sym) - goto out; - - strlcpy(symname, sym, KSYM_NAME_LEN); - preempt_enable(); - return 0; - } - } -out: - preempt_enable(); - return -ERANGE; -} - -int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, - unsigned long *offset, char *modname, char *name) -{ - struct module *mod; - - preempt_disable(); - list_for_each_entry_rcu(mod, &modules, list) { - if (mod->state == MODULE_STATE_UNFORMED) - continue; - if (within_module(addr, mod)) { - const char *sym; - - sym = find_kallsyms_symbol(mod, addr, size, offset); - if (!sym) - goto out; - if (modname) - strlcpy(modname, mod->name, MODULE_NAME_LEN); - if (name) - strlcpy(name, sym, KSYM_NAME_LEN); - preempt_enable(); - return 0; - } - } -out: - preempt_enable(); - return -ERANGE; -} - -int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, - char *name, char *module_name, int *exported) -{ - struct module *mod; - - preempt_disable(); - list_for_each_entry_rcu(mod, &modules, list) { - struct mod_kallsyms *kallsyms; - - if (mod->state == MODULE_STATE_UNFORMED) - continue; - kallsyms = rcu_dereference_sched(mod->kallsyms); - if (symnum < kallsyms->num_symtab) { - const Elf_Sym *sym = &kallsyms->symtab[symnum]; - - *value = kallsyms_symbol_value(sym); - *type = kallsyms->typetab[symnum]; - strlcpy(name, kallsyms_symbol_name(kallsyms, symnum), KSYM_NAME_LEN); - strlcpy(module_name, mod->name, MODULE_NAME_LEN); - *exported = is_exported(name, *value, mod); - preempt_enable(); - return 0; - } - symnum -= kallsyms->num_symtab; - } - preempt_enable(); - return -ERANGE; -} - -/* Given a module and name of symbol, find and return the symbol's value */ -static unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name) -{ - unsigned int i; - struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); - - for (i = 0; i < kallsyms->num_symtab; i++) { - const Elf_Sym *sym = &kallsyms->symtab[i]; - - if (strcmp(name, kallsyms_symbol_name(kallsyms, i)) == 0 && - sym->st_shndx != SHN_UNDEF) - return kallsyms_symbol_value(sym); - } - return 0; -} - -/* Look for this name: can be of form module:name. */ -unsigned long module_kallsyms_lookup_name(const char *name) -{ - struct module *mod; - char *colon; - unsigned long ret = 0; - - /* Don't lock: we're in enough trouble already. */ - preempt_disable(); - if ((colon = strnchr(name, MODULE_NAME_LEN, ':')) != NULL) { - if ((mod = find_module_all(name, colon - name, false)) != NULL) - ret = find_kallsyms_symbol_value(mod, colon+1); - } else { - list_for_each_entry_rcu(mod, &modules, list) { - if (mod->state == MODULE_STATE_UNFORMED) - continue; - if ((ret = find_kallsyms_symbol_value(mod, name)) != 0) - break; - } - } - preempt_enable(); - return ret; -} - -#ifdef CONFIG_LIVEPATCH -int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, - struct module *, unsigned long), - void *data) -{ - struct module *mod; - unsigned int i; - int ret = 0; - - mutex_lock(&module_mutex); - list_for_each_entry(mod, &modules, list) { - /* We hold module_mutex: no need for rcu_dereference_sched */ - struct mod_kallsyms *kallsyms = mod->kallsyms; - - if (mod->state == MODULE_STATE_UNFORMED) - continue; - for (i = 0; i < kallsyms->num_symtab; i++) { - const Elf_Sym *sym = &kallsyms->symtab[i]; - - if (sym->st_shndx == SHN_UNDEF) - continue; - - ret = fn(data, kallsyms_symbol_name(kallsyms, i), - mod, kallsyms_symbol_value(sym)); - if (ret != 0) - goto out; - - cond_resched(); - } - } -out: - mutex_unlock(&module_mutex); - return ret; -} -#endif /* CONFIG_LIVEPATCH */ -#endif /* CONFIG_KALLSYMS */ - static void cfi_init(struct module *mod) { #ifdef CONFIG_CFI_CLANG @@ -4531,22 +2958,19 @@ static void cfi_init(struct module *mod) mod->exit = *exit; #endif - cfi_module_add(mod, module_addr_min); + cfi_module_add(mod, mod_tree.addr_min); #endif } static void cfi_cleanup(struct module *mod) { #ifdef CONFIG_CFI_CLANG - cfi_module_remove(mod, module_addr_min); + cfi_module_remove(mod, mod_tree.addr_min); #endif } -/* Maximum number of characters written by module_flags() */ -#define MODULE_FLAGS_BUF_SIZE (TAINT_FLAGS_COUNT + 4) - /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */ -static char *module_flags(struct module *mod, char *buf) +char *module_flags(struct module *mod, char *buf) { int bx = 0; @@ -4555,7 +2979,7 @@ static char *module_flags(struct module *mod, char *buf) mod->state == MODULE_STATE_GOING || mod->state == MODULE_STATE_COMING) { buf[bx++] = '('; - bx += module_flags_taint(mod, buf + bx); + bx += module_flags_taint(mod->taints, buf + bx); /* Show a - for module-is-being-unloaded */ if (mod->state == MODULE_STATE_GOING) buf[bx++] = '-'; @@ -4569,103 +2993,6 @@ static char *module_flags(struct module *mod, char *buf) return buf; } -#ifdef CONFIG_PROC_FS -/* Called by the /proc file system to return a list of modules. */ -static void *m_start(struct seq_file *m, loff_t *pos) -{ - mutex_lock(&module_mutex); - return seq_list_start(&modules, *pos); -} - -static void *m_next(struct seq_file *m, void *p, loff_t *pos) -{ - return seq_list_next(p, &modules, pos); -} - -static void m_stop(struct seq_file *m, void *p) -{ - mutex_unlock(&module_mutex); -} - -static int m_show(struct seq_file *m, void *p) -{ - struct module *mod = list_entry(p, struct module, list); - char buf[MODULE_FLAGS_BUF_SIZE]; - void *value; - - /* We always ignore unformed modules. */ - if (mod->state == MODULE_STATE_UNFORMED) - return 0; - - seq_printf(m, "%s %u", - mod->name, mod->init_layout.size + mod->core_layout.size); - print_unload_info(m, mod); - - /* Informative for users. */ - seq_printf(m, " %s", - mod->state == MODULE_STATE_GOING ? "Unloading" : - mod->state == MODULE_STATE_COMING ? "Loading" : - "Live"); - /* Used by oprofile and other similar tools. */ - value = m->private ? NULL : mod->core_layout.base; - seq_printf(m, " 0x%px", value); - - /* Taints info */ - if (mod->taints) - seq_printf(m, " %s", module_flags(mod, buf)); - - seq_puts(m, "\n"); - return 0; -} - -/* - * Format: modulename size refcount deps address - * - * Where refcount is a number or -, and deps is a comma-separated list - * of depends or -. - */ -static const struct seq_operations modules_op = { - .start = m_start, - .next = m_next, - .stop = m_stop, - .show = m_show -}; - -/* - * This also sets the "private" pointer to non-NULL if the - * kernel pointers should be hidden (so you can just test - * "m->private" to see if you should keep the values private). - * - * We use the same logic as for /proc/kallsyms. - */ -static int modules_open(struct inode *inode, struct file *file) -{ - int err = seq_open(file, &modules_op); - - if (!err) { - struct seq_file *m = file->private_data; - m->private = kallsyms_show_value(file->f_cred) ? NULL : (void *)8ul; - } - - return err; -} - -static const struct proc_ops modules_proc_ops = { - .proc_flags = PROC_ENTRY_PERMANENT, - .proc_open = modules_open, - .proc_read = seq_read, - .proc_lseek = seq_lseek, - .proc_release = seq_release, -}; - -static int __init proc_modules_init(void) -{ - proc_create("modules", 0, NULL, &modules_proc_ops); - return 0; -} -module_init(proc_modules_init); -#endif - /* Given an address, look for it in the module exception tables. */ const struct exception_table_entry *search_module_extables(unsigned long addr) { @@ -4721,13 +3048,20 @@ bool is_module_address(unsigned long addr) struct module *__module_address(unsigned long addr) { struct module *mod; + struct mod_tree_root *tree; - if (addr < module_addr_min || addr > module_addr_max) + if (addr >= mod_tree.addr_min && addr <= mod_tree.addr_max) + tree = &mod_tree; +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + else if (addr >= mod_data_tree.addr_min && addr <= mod_data_tree.addr_max) + tree = &mod_data_tree; +#endif + else return NULL; module_assert_mutex_or_preempt(); - mod = mod_find(addr); + mod = mod_find(addr, tree); if (mod) { BUG_ON(!within_module(addr, mod)); if (mod->state == MODULE_STATE_UNFORMED) @@ -4788,23 +3122,10 @@ void print_modules(void) continue; pr_cont(" %s%s", mod->name, module_flags(mod, buf)); } + + print_unloaded_tainted_modules(); preempt_enable(); if (last_unloaded_module[0]) pr_cont(" [last unloaded: %s]", last_unloaded_module); pr_cont("\n"); } - -#ifdef CONFIG_MODVERSIONS -/* - * Generate the signature for all relevant module structures here. - * If these change, we don't want to try to parse the module. - */ -void module_layout(struct module *mod, - struct modversion_info *ver, - struct kernel_param *kp, - struct kernel_symbol *ks, - struct tracepoint * const *tp) -{ -} -EXPORT_SYMBOL(module_layout); -#endif diff --git a/kernel/module/procfs.c b/kernel/module/procfs.c new file mode 100644 index 000000000000..9a8f4f0f6329 --- /dev/null +++ b/kernel/module/procfs.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Module proc support + * + * Copyright (C) 2008 Alexey Dobriyan + */ + +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/mutex.h> +#include <linux/seq_file.h> +#include <linux/proc_fs.h> +#include "internal.h" + +#ifdef CONFIG_MODULE_UNLOAD +static inline void print_unload_info(struct seq_file *m, struct module *mod) +{ + struct module_use *use; + int printed_something = 0; + + seq_printf(m, " %i ", module_refcount(mod)); + + /* + * Always include a trailing , so userspace can differentiate + * between this and the old multi-field proc format. + */ + list_for_each_entry(use, &mod->source_list, source_list) { + printed_something = 1; + seq_printf(m, "%s,", use->source->name); + } + + if (mod->init && !mod->exit) { + printed_something = 1; + seq_puts(m, "[permanent],"); + } + + if (!printed_something) + seq_puts(m, "-"); +} +#else /* !CONFIG_MODULE_UNLOAD */ +static inline void print_unload_info(struct seq_file *m, struct module *mod) +{ + /* We don't know the usage count, or what modules are using. */ + seq_puts(m, " - -"); +} +#endif /* CONFIG_MODULE_UNLOAD */ + +/* Called by the /proc file system to return a list of modules. */ +static void *m_start(struct seq_file *m, loff_t *pos) +{ + mutex_lock(&module_mutex); + return seq_list_start(&modules, *pos); +} + +static void *m_next(struct seq_file *m, void *p, loff_t *pos) +{ + return seq_list_next(p, &modules, pos); +} + +static void m_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&module_mutex); +} + +static int m_show(struct seq_file *m, void *p) +{ + struct module *mod = list_entry(p, struct module, list); + char buf[MODULE_FLAGS_BUF_SIZE]; + void *value; + unsigned int size; + + /* We always ignore unformed modules. */ + if (mod->state == MODULE_STATE_UNFORMED) + return 0; + + size = mod->init_layout.size + mod->core_layout.size; +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + size += mod->data_layout.size; +#endif + seq_printf(m, "%s %u", mod->name, size); + print_unload_info(m, mod); + + /* Informative for users. */ + seq_printf(m, " %s", + mod->state == MODULE_STATE_GOING ? "Unloading" : + mod->state == MODULE_STATE_COMING ? "Loading" : + "Live"); + /* Used by oprofile and other similar tools. */ + value = m->private ? NULL : mod->core_layout.base; + seq_printf(m, " 0x%px", value); + + /* Taints info */ + if (mod->taints) + seq_printf(m, " %s", module_flags(mod, buf)); + + seq_puts(m, "\n"); + return 0; +} + +/* + * Format: modulename size refcount deps address + * + * Where refcount is a number or -, and deps is a comma-separated list + * of depends or -. + */ +static const struct seq_operations modules_op = { + .start = m_start, + .next = m_next, + .stop = m_stop, + .show = m_show +}; + +/* + * This also sets the "private" pointer to non-NULL if the + * kernel pointers should be hidden (so you can just test + * "m->private" to see if you should keep the values private). + * + * We use the same logic as for /proc/kallsyms. + */ +static int modules_open(struct inode *inode, struct file *file) +{ + int err = seq_open(file, &modules_op); + + if (!err) { + struct seq_file *m = file->private_data; + + m->private = kallsyms_show_value(file->f_cred) ? NULL : (void *)8ul; + } + + return err; +} + +static const struct proc_ops modules_proc_ops = { + .proc_flags = PROC_ENTRY_PERMANENT, + .proc_open = modules_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, +}; + +static int __init proc_modules_init(void) +{ + proc_create("modules", 0, NULL, &modules_proc_ops); + return 0; +} +module_init(proc_modules_init); diff --git a/kernel/module/signing.c b/kernel/module/signing.c new file mode 100644 index 000000000000..a2ff4242e623 --- /dev/null +++ b/kernel/module/signing.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Module signature checker + * + * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/module.h> +#include <linux/module_signature.h> +#include <linux/string.h> +#include <linux/verification.h> +#include <linux/security.h> +#include <crypto/public_key.h> +#include <uapi/linux/module.h> +#include "internal.h" + +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "module." + +static bool sig_enforce = IS_ENABLED(CONFIG_MODULE_SIG_FORCE); +module_param(sig_enforce, bool_enable_only, 0644); + +/* + * Export sig_enforce kernel cmdline parameter to allow other subsystems rely + * on that instead of directly to CONFIG_MODULE_SIG_FORCE config. + */ +bool is_module_sig_enforced(void) +{ + return sig_enforce; +} +EXPORT_SYMBOL(is_module_sig_enforced); + +void set_module_sig_enforced(void) +{ + sig_enforce = true; +} + +/* + * Verify the signature on a module. + */ +int mod_verify_sig(const void *mod, struct load_info *info) +{ + struct module_signature ms; + size_t sig_len, modlen = info->len; + int ret; + + pr_devel("==>%s(,%zu)\n", __func__, modlen); + + if (modlen <= sizeof(ms)) + return -EBADMSG; + + memcpy(&ms, mod + (modlen - sizeof(ms)), sizeof(ms)); + + ret = mod_check_sig(&ms, modlen, "module"); + if (ret) + return ret; + + sig_len = be32_to_cpu(ms.sig_len); + modlen -= sig_len + sizeof(ms); + info->len = modlen; + + return verify_pkcs7_signature(mod, modlen, mod + modlen, sig_len, + VERIFY_USE_SECONDARY_KEYRING, + VERIFYING_MODULE_SIGNATURE, + NULL, NULL); +} + +int module_sig_check(struct load_info *info, int flags) +{ + int err = -ENODATA; + const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1; + const char *reason; + const void *mod = info->hdr; + bool mangled_module = flags & (MODULE_INIT_IGNORE_MODVERSIONS | + MODULE_INIT_IGNORE_VERMAGIC); + /* + * Do not allow mangled modules as a module with version information + * removed is no longer the module that was signed. + */ + if (!mangled_module && + info->len > markerlen && + memcmp(mod + info->len - markerlen, MODULE_SIG_STRING, markerlen) == 0) { + /* We truncate the module to discard the signature */ + info->len -= markerlen; + err = mod_verify_sig(mod, info); + if (!err) { + info->sig_ok = true; + return 0; + } + } + + /* + * We don't permit modules to be loaded into the trusted kernels + * without a valid signature on them, but if we're not enforcing, + * certain errors are non-fatal. + */ + switch (err) { + case -ENODATA: + reason = "unsigned module"; + break; + case -ENOPKG: + reason = "module with unsupported crypto"; + break; + case -ENOKEY: + reason = "module with unavailable key"; + break; + + default: + /* + * All other errors are fatal, including lack of memory, + * unparseable signatures, and signature check failures -- + * even if signatures aren't required. + */ + return err; + } + + if (is_module_sig_enforced()) { + pr_notice("Loading of %s is rejected\n", reason); + return -EKEYREJECTED; + } + + return security_locked_down(LOCKDOWN_MODULE_SIGNATURE); +} diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c new file mode 100644 index 000000000000..14fbea66f12f --- /dev/null +++ b/kernel/module/strict_rwx.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Module strict rwx + * + * Copyright (C) 2015 Rusty Russell + */ + +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/vmalloc.h> +#include <linux/set_memory.h> +#include "internal.h" + +/* + * LKM RO/NX protection: protect module's text/ro-data + * from modification and any data from execution. + * + * General layout of module is: + * [text] [read-only-data] [ro-after-init] [writable data] + * text_size -----^ ^ ^ ^ + * ro_size ------------------------| | | + * ro_after_init_size -----------------------------| | + * size -----------------------------------------------------------| + * + * These values are always page-aligned (as is base) when + * CONFIG_STRICT_MODULE_RWX is set. + */ + +/* + * Since some arches are moving towards PAGE_KERNEL module allocations instead + * of PAGE_KERNEL_EXEC, keep frob_text() and module_enable_x() independent of + * CONFIG_STRICT_MODULE_RWX because they are needed regardless of whether we + * are strict. + */ +static void frob_text(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) +{ + set_memory((unsigned long)layout->base, + PAGE_ALIGN(layout->text_size) >> PAGE_SHIFT); +} + +static void frob_rodata(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) +{ + set_memory((unsigned long)layout->base + layout->text_size, + (layout->ro_size - layout->text_size) >> PAGE_SHIFT); +} + +static void frob_ro_after_init(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) +{ + set_memory((unsigned long)layout->base + layout->ro_size, + (layout->ro_after_init_size - layout->ro_size) >> PAGE_SHIFT); +} + +static void frob_writable_data(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) +{ + set_memory((unsigned long)layout->base + layout->ro_after_init_size, + (layout->size - layout->ro_after_init_size) >> PAGE_SHIFT); +} + +static bool layout_check_misalignment(const struct module_layout *layout) +{ + return WARN_ON(!PAGE_ALIGNED(layout->base)) || + WARN_ON(!PAGE_ALIGNED(layout->text_size)) || + WARN_ON(!PAGE_ALIGNED(layout->ro_size)) || + WARN_ON(!PAGE_ALIGNED(layout->ro_after_init_size)) || + WARN_ON(!PAGE_ALIGNED(layout->size)); +} + +bool module_check_misalignment(const struct module *mod) +{ + if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + return false; + + return layout_check_misalignment(&mod->core_layout) || + layout_check_misalignment(&mod->data_layout) || + layout_check_misalignment(&mod->init_layout); +} + +void module_enable_x(const struct module *mod) +{ + if (!PAGE_ALIGNED(mod->core_layout.base) || + !PAGE_ALIGNED(mod->init_layout.base)) + return; + + frob_text(&mod->core_layout, set_memory_x); + frob_text(&mod->init_layout, set_memory_x); +} + +void module_enable_ro(const struct module *mod, bool after_init) +{ + if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + return; +#ifdef CONFIG_STRICT_MODULE_RWX + if (!rodata_enabled) + return; +#endif + + set_vm_flush_reset_perms(mod->core_layout.base); + set_vm_flush_reset_perms(mod->init_layout.base); + frob_text(&mod->core_layout, set_memory_ro); + + frob_rodata(&mod->data_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_ro); + frob_rodata(&mod->init_layout, set_memory_ro); + + if (after_init) + frob_ro_after_init(&mod->data_layout, set_memory_ro); +} + +void module_enable_nx(const struct module *mod) +{ + if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + return; + + frob_rodata(&mod->data_layout, set_memory_nx); + frob_ro_after_init(&mod->data_layout, set_memory_nx); + frob_writable_data(&mod->data_layout, set_memory_nx); + frob_rodata(&mod->init_layout, set_memory_nx); + frob_writable_data(&mod->init_layout, set_memory_nx); +} + +int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, + char *secstrings, struct module *mod) +{ + const unsigned long shf_wx = SHF_WRITE | SHF_EXECINSTR; + int i; + + if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + return 0; + + for (i = 0; i < hdr->e_shnum; i++) { + if ((sechdrs[i].sh_flags & shf_wx) == shf_wx) { + pr_err("%s: section %s (index %d) has invalid WRITE|EXEC flags\n", + mod->name, secstrings + sechdrs[i].sh_name, i); + return -ENOEXEC; + } + } + + return 0; +} diff --git a/kernel/module/sysfs.c b/kernel/module/sysfs.c new file mode 100644 index 000000000000..ce68f821dcd1 --- /dev/null +++ b/kernel/module/sysfs.c @@ -0,0 +1,436 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Module sysfs support + * + * Copyright (C) 2008 Rusty Russell + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/fs.h> +#include <linux/sysfs.h> +#include <linux/slab.h> +#include <linux/kallsyms.h> +#include <linux/mutex.h> +#include "internal.h" + +/* + * /sys/module/foo/sections stuff + * J. Corbet <corbet@lwn.net> + */ +#ifdef CONFIG_KALLSYMS +struct module_sect_attr { + struct bin_attribute battr; + unsigned long address; +}; + +struct module_sect_attrs { + struct attribute_group grp; + unsigned int nsections; + struct module_sect_attr attrs[]; +}; + +#define MODULE_SECT_READ_SIZE (3 /* "0x", "\n" */ + (BITS_PER_LONG / 4)) +static ssize_t module_sect_read(struct file *file, struct kobject *kobj, + struct bin_attribute *battr, + char *buf, loff_t pos, size_t count) +{ + struct module_sect_attr *sattr = + container_of(battr, struct module_sect_attr, battr); + char bounce[MODULE_SECT_READ_SIZE + 1]; + size_t wrote; + + if (pos != 0) + return -EINVAL; + + /* + * Since we're a binary read handler, we must account for the + * trailing NUL byte that sprintf will write: if "buf" is + * too small to hold the NUL, or the NUL is exactly the last + * byte, the read will look like it got truncated by one byte. + * Since there is no way to ask sprintf nicely to not write + * the NUL, we have to use a bounce buffer. + */ + wrote = scnprintf(bounce, sizeof(bounce), "0x%px\n", + kallsyms_show_value(file->f_cred) + ? (void *)sattr->address : NULL); + count = min(count, wrote); + memcpy(buf, bounce, count); + + return count; +} + +static void free_sect_attrs(struct module_sect_attrs *sect_attrs) +{ + unsigned int section; + + for (section = 0; section < sect_attrs->nsections; section++) + kfree(sect_attrs->attrs[section].battr.attr.name); + kfree(sect_attrs); +} + +static void add_sect_attrs(struct module *mod, const struct load_info *info) +{ + unsigned int nloaded = 0, i, size[2]; + struct module_sect_attrs *sect_attrs; + struct module_sect_attr *sattr; + struct bin_attribute **gattr; + + /* Count loaded sections and allocate structures */ + for (i = 0; i < info->hdr->e_shnum; i++) + if (!sect_empty(&info->sechdrs[i])) + nloaded++; + size[0] = ALIGN(struct_size(sect_attrs, attrs, nloaded), + sizeof(sect_attrs->grp.bin_attrs[0])); + size[1] = (nloaded + 1) * sizeof(sect_attrs->grp.bin_attrs[0]); + sect_attrs = kzalloc(size[0] + size[1], GFP_KERNEL); + if (!sect_attrs) + return; + + /* Setup section attributes. */ + sect_attrs->grp.name = "sections"; + sect_attrs->grp.bin_attrs = (void *)sect_attrs + size[0]; + + sect_attrs->nsections = 0; + sattr = §_attrs->attrs[0]; + gattr = §_attrs->grp.bin_attrs[0]; + for (i = 0; i < info->hdr->e_shnum; i++) { + Elf_Shdr *sec = &info->sechdrs[i]; + + if (sect_empty(sec)) + continue; + sysfs_bin_attr_init(&sattr->battr); + sattr->address = sec->sh_addr; + sattr->battr.attr.name = + kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL); + if (!sattr->battr.attr.name) + goto out; + sect_attrs->nsections++; + sattr->battr.read = module_sect_read; + sattr->battr.size = MODULE_SECT_READ_SIZE; + sattr->battr.attr.mode = 0400; + *(gattr++) = &(sattr++)->battr; + } + *gattr = NULL; + + if (sysfs_create_group(&mod->mkobj.kobj, §_attrs->grp)) + goto out; + + mod->sect_attrs = sect_attrs; + return; +out: + free_sect_attrs(sect_attrs); +} + +static void remove_sect_attrs(struct module *mod) +{ + if (mod->sect_attrs) { + sysfs_remove_group(&mod->mkobj.kobj, + &mod->sect_attrs->grp); + /* + * We are positive that no one is using any sect attrs + * at this point. Deallocate immediately. + */ + free_sect_attrs(mod->sect_attrs); + mod->sect_attrs = NULL; + } +} + +/* + * /sys/module/foo/notes/.section.name gives contents of SHT_NOTE sections. + */ + +struct module_notes_attrs { + struct kobject *dir; + unsigned int notes; + struct bin_attribute attrs[]; +}; + +static ssize_t module_notes_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t pos, size_t count) +{ + /* + * The caller checked the pos and count against our size. + */ + memcpy(buf, bin_attr->private + pos, count); + return count; +} + +static void free_notes_attrs(struct module_notes_attrs *notes_attrs, + unsigned int i) +{ + if (notes_attrs->dir) { + while (i-- > 0) + sysfs_remove_bin_file(notes_attrs->dir, + ¬es_attrs->attrs[i]); + kobject_put(notes_attrs->dir); + } + kfree(notes_attrs); +} + +static void add_notes_attrs(struct module *mod, const struct load_info *info) +{ + unsigned int notes, loaded, i; + struct module_notes_attrs *notes_attrs; + struct bin_attribute *nattr; + + /* failed to create section attributes, so can't create notes */ + if (!mod->sect_attrs) + return; + + /* Count notes sections and allocate structures. */ + notes = 0; + for (i = 0; i < info->hdr->e_shnum; i++) + if (!sect_empty(&info->sechdrs[i]) && + info->sechdrs[i].sh_type == SHT_NOTE) + ++notes; + + if (notes == 0) + return; + + notes_attrs = kzalloc(struct_size(notes_attrs, attrs, notes), + GFP_KERNEL); + if (!notes_attrs) + return; + + notes_attrs->notes = notes; + nattr = ¬es_attrs->attrs[0]; + for (loaded = i = 0; i < info->hdr->e_shnum; ++i) { + if (sect_empty(&info->sechdrs[i])) + continue; + if (info->sechdrs[i].sh_type == SHT_NOTE) { + sysfs_bin_attr_init(nattr); + nattr->attr.name = mod->sect_attrs->attrs[loaded].battr.attr.name; + nattr->attr.mode = 0444; + nattr->size = info->sechdrs[i].sh_size; + nattr->private = (void *)info->sechdrs[i].sh_addr; + nattr->read = module_notes_read; + ++nattr; + } + ++loaded; + } + + notes_attrs->dir = kobject_create_and_add("notes", &mod->mkobj.kobj); + if (!notes_attrs->dir) + goto out; + + for (i = 0; i < notes; ++i) + if (sysfs_create_bin_file(notes_attrs->dir, + ¬es_attrs->attrs[i])) + goto out; + + mod->notes_attrs = notes_attrs; + return; + +out: + free_notes_attrs(notes_attrs, i); +} + +static void remove_notes_attrs(struct module *mod) +{ + if (mod->notes_attrs) + free_notes_attrs(mod->notes_attrs, mod->notes_attrs->notes); +} + +#else /* !CONFIG_KALLSYMS */ +static inline void add_sect_attrs(struct module *mod, const struct load_info *info) { } +static inline void remove_sect_attrs(struct module *mod) { } +static inline void add_notes_attrs(struct module *mod, const struct load_info *info) { } +static inline void remove_notes_attrs(struct module *mod) { } +#endif /* CONFIG_KALLSYMS */ + +static void del_usage_links(struct module *mod) +{ +#ifdef CONFIG_MODULE_UNLOAD + struct module_use *use; + + mutex_lock(&module_mutex); + list_for_each_entry(use, &mod->target_list, target_list) + sysfs_remove_link(use->target->holders_dir, mod->name); + mutex_unlock(&module_mutex); +#endif +} + +static int add_usage_links(struct module *mod) +{ + int ret = 0; +#ifdef CONFIG_MODULE_UNLOAD + struct module_use *use; + + mutex_lock(&module_mutex); + list_for_each_entry(use, &mod->target_list, target_list) { + ret = sysfs_create_link(use->target->holders_dir, + &mod->mkobj.kobj, mod->name); + if (ret) + break; + } + mutex_unlock(&module_mutex); + if (ret) + del_usage_links(mod); +#endif + return ret; +} + +static void module_remove_modinfo_attrs(struct module *mod, int end) +{ + struct module_attribute *attr; + int i; + + for (i = 0; (attr = &mod->modinfo_attrs[i]); i++) { + if (end >= 0 && i > end) + break; + /* pick a field to test for end of list */ + if (!attr->attr.name) + break; + sysfs_remove_file(&mod->mkobj.kobj, &attr->attr); + if (attr->free) + attr->free(mod); + } + kfree(mod->modinfo_attrs); +} + +static int module_add_modinfo_attrs(struct module *mod) +{ + struct module_attribute *attr; + struct module_attribute *temp_attr; + int error = 0; + int i; + + mod->modinfo_attrs = kzalloc((sizeof(struct module_attribute) * + (modinfo_attrs_count + 1)), + GFP_KERNEL); + if (!mod->modinfo_attrs) + return -ENOMEM; + + temp_attr = mod->modinfo_attrs; + for (i = 0; (attr = modinfo_attrs[i]); i++) { + if (!attr->test || attr->test(mod)) { + memcpy(temp_attr, attr, sizeof(*temp_attr)); + sysfs_attr_init(&temp_attr->attr); + error = sysfs_create_file(&mod->mkobj.kobj, + &temp_attr->attr); + if (error) + goto error_out; + ++temp_attr; + } + } + + return 0; + +error_out: + if (i > 0) + module_remove_modinfo_attrs(mod, --i); + else + kfree(mod->modinfo_attrs); + return error; +} + +static void mod_kobject_put(struct module *mod) +{ + DECLARE_COMPLETION_ONSTACK(c); + + mod->mkobj.kobj_completion = &c; + kobject_put(&mod->mkobj.kobj); + wait_for_completion(&c); +} + +static int mod_sysfs_init(struct module *mod) +{ + int err; + struct kobject *kobj; + + if (!module_sysfs_initialized) { + pr_err("%s: module sysfs not initialized\n", mod->name); + err = -EINVAL; + goto out; + } + + kobj = kset_find_obj(module_kset, mod->name); + if (kobj) { + pr_err("%s: module is already loaded\n", mod->name); + kobject_put(kobj); + err = -EINVAL; + goto out; + } + + mod->mkobj.mod = mod; + + memset(&mod->mkobj.kobj, 0, sizeof(mod->mkobj.kobj)); + mod->mkobj.kobj.kset = module_kset; + err = kobject_init_and_add(&mod->mkobj.kobj, &module_ktype, NULL, + "%s", mod->name); + if (err) + mod_kobject_put(mod); + +out: + return err; +} + +int mod_sysfs_setup(struct module *mod, + const struct load_info *info, + struct kernel_param *kparam, + unsigned int num_params) +{ + int err; + + err = mod_sysfs_init(mod); + if (err) + goto out; + + mod->holders_dir = kobject_create_and_add("holders", &mod->mkobj.kobj); + if (!mod->holders_dir) { + err = -ENOMEM; + goto out_unreg; + } + + err = module_param_sysfs_setup(mod, kparam, num_params); + if (err) + goto out_unreg_holders; + + err = module_add_modinfo_attrs(mod); + if (err) + goto out_unreg_param; + + err = add_usage_links(mod); + if (err) + goto out_unreg_modinfo_attrs; + + add_sect_attrs(mod, info); + add_notes_attrs(mod, info); + + return 0; + +out_unreg_modinfo_attrs: + module_remove_modinfo_attrs(mod, -1); +out_unreg_param: + module_param_sysfs_remove(mod); +out_unreg_holders: + kobject_put(mod->holders_dir); +out_unreg: + mod_kobject_put(mod); +out: + return err; +} + +static void mod_sysfs_fini(struct module *mod) +{ + remove_notes_attrs(mod); + remove_sect_attrs(mod); + mod_kobject_put(mod); +} + +void mod_sysfs_teardown(struct module *mod) +{ + del_usage_links(mod); + module_remove_modinfo_attrs(mod, -1); + module_param_sysfs_remove(mod); + kobject_put(mod->mkobj.drivers_dir); + kobject_put(mod->holders_dir); + mod_sysfs_fini(mod); +} + +void init_param_lock(struct module *mod) +{ + mutex_init(&mod->param_lock); +} diff --git a/kernel/module/tracking.c b/kernel/module/tracking.c new file mode 100644 index 000000000000..7f8133044d09 --- /dev/null +++ b/kernel/module/tracking.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Module taint unload tracking support + * + * Copyright (C) 2022 Aaron Tomlin + */ + +#include <linux/module.h> +#include <linux/string.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/list.h> +#include <linux/rculist.h> +#include "internal.h" + +static LIST_HEAD(unloaded_tainted_modules); + +int try_add_tainted_module(struct module *mod) +{ + struct mod_unload_taint *mod_taint; + + module_assert_mutex_or_preempt(); + + list_for_each_entry_rcu(mod_taint, &unloaded_tainted_modules, list, + lockdep_is_held(&module_mutex)) { + if (!strcmp(mod_taint->name, mod->name) && + mod_taint->taints & mod->taints) { + mod_taint->count++; + goto out; + } + } + + mod_taint = kmalloc(sizeof(*mod_taint), GFP_KERNEL); + if (unlikely(!mod_taint)) + return -ENOMEM; + strscpy(mod_taint->name, mod->name, MODULE_NAME_LEN); + mod_taint->taints = mod->taints; + list_add_rcu(&mod_taint->list, &unloaded_tainted_modules); + mod_taint->count = 1; +out: + return 0; +} + +void print_unloaded_tainted_modules(void) +{ + struct mod_unload_taint *mod_taint; + char buf[MODULE_FLAGS_BUF_SIZE]; + + if (!list_empty(&unloaded_tainted_modules)) { + printk(KERN_DEFAULT "Unloaded tainted modules:"); + list_for_each_entry_rcu(mod_taint, &unloaded_tainted_modules, + list) { + size_t l; + + l = module_flags_taint(mod_taint->taints, buf); + buf[l++] = '\0'; + pr_cont(" %s(%s):%llu", mod_taint->name, buf, + mod_taint->count); + } + } +} diff --git a/kernel/module/tree_lookup.c b/kernel/module/tree_lookup.c new file mode 100644 index 000000000000..8ec5cfd60496 --- /dev/null +++ b/kernel/module/tree_lookup.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Modules tree lookup + * + * Copyright (C) 2015 Peter Zijlstra + * Copyright (C) 2015 Rusty Russell + */ + +#include <linux/module.h> +#include <linux/rbtree_latch.h> +#include "internal.h" + +/* + * Use a latched RB-tree for __module_address(); this allows us to use + * RCU-sched lookups of the address from any context. + * + * This is conditional on PERF_EVENTS || TRACING because those can really hit + * __module_address() hard by doing a lot of stack unwinding; potentially from + * NMI context. + */ + +static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n) +{ + struct module_layout *layout = container_of(n, struct module_layout, mtn.node); + + return (unsigned long)layout->base; +} + +static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n) +{ + struct module_layout *layout = container_of(n, struct module_layout, mtn.node); + + return (unsigned long)layout->size; +} + +static __always_inline bool +mod_tree_less(struct latch_tree_node *a, struct latch_tree_node *b) +{ + return __mod_tree_val(a) < __mod_tree_val(b); +} + +static __always_inline int +mod_tree_comp(void *key, struct latch_tree_node *n) +{ + unsigned long val = (unsigned long)key; + unsigned long start, end; + + start = __mod_tree_val(n); + if (val < start) + return -1; + + end = start + __mod_tree_size(n); + if (val >= end) + return 1; + + return 0; +} + +static const struct latch_tree_ops mod_tree_ops = { + .less = mod_tree_less, + .comp = mod_tree_comp, +}; + +static noinline void __mod_tree_insert(struct mod_tree_node *node, struct mod_tree_root *tree) +{ + latch_tree_insert(&node->node, &tree->root, &mod_tree_ops); +} + +static void __mod_tree_remove(struct mod_tree_node *node, struct mod_tree_root *tree) +{ + latch_tree_erase(&node->node, &tree->root, &mod_tree_ops); +} + +/* + * These modifications: insert, remove_init and remove; are serialized by the + * module_mutex. + */ +void mod_tree_insert(struct module *mod) +{ + mod->core_layout.mtn.mod = mod; + mod->init_layout.mtn.mod = mod; + + __mod_tree_insert(&mod->core_layout.mtn, &mod_tree); + if (mod->init_layout.size) + __mod_tree_insert(&mod->init_layout.mtn, &mod_tree); + +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + mod->data_layout.mtn.mod = mod; + __mod_tree_insert(&mod->data_layout.mtn, &mod_data_tree); +#endif +} + +void mod_tree_remove_init(struct module *mod) +{ + if (mod->init_layout.size) + __mod_tree_remove(&mod->init_layout.mtn, &mod_tree); +} + +void mod_tree_remove(struct module *mod) +{ + __mod_tree_remove(&mod->core_layout.mtn, &mod_tree); + mod_tree_remove_init(mod); +#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC + __mod_tree_remove(&mod->data_layout.mtn, &mod_data_tree); +#endif +} + +struct module *mod_find(unsigned long addr, struct mod_tree_root *tree) +{ + struct latch_tree_node *ltn; + + ltn = latch_tree_find((void *)addr, &tree->root, &mod_tree_ops); + if (!ltn) + return NULL; + + return container_of(ltn, struct mod_tree_node, node)->mod; +} diff --git a/kernel/module/version.c b/kernel/module/version.c new file mode 100644 index 000000000000..53f43ac5a73e --- /dev/null +++ b/kernel/module/version.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Module version support + * + * Copyright (C) 2008 Rusty Russell + */ + +#include <linux/module.h> +#include <linux/string.h> +#include <linux/printk.h> +#include "internal.h" + +int check_version(const struct load_info *info, + const char *symname, + struct module *mod, + const s32 *crc) +{ + Elf_Shdr *sechdrs = info->sechdrs; + unsigned int versindex = info->index.vers; + unsigned int i, num_versions; + struct modversion_info *versions; + + /* Exporting module didn't supply crcs? OK, we're already tainted. */ + if (!crc) + return 1; + + /* No versions at all? modprobe --force does this. */ + if (versindex == 0) + return try_to_force_load(mod, symname) == 0; + + versions = (void *)sechdrs[versindex].sh_addr; + num_versions = sechdrs[versindex].sh_size + / sizeof(struct modversion_info); + + for (i = 0; i < num_versions; i++) { + u32 crcval; + + if (strcmp(versions[i].name, symname) != 0) + continue; + + crcval = *crc; + if (versions[i].crc == crcval) + return 1; + pr_debug("Found checksum %X vs module %lX\n", + crcval, versions[i].crc); + goto bad_version; + } + + /* Broken toolchain. Warn once, then let it go.. */ + pr_warn_once("%s: no symbol version for %s\n", info->name, symname); + return 1; + +bad_version: + pr_warn("%s: disagrees about version of symbol %s\n", info->name, symname); + return 0; +} + +int check_modstruct_version(const struct load_info *info, + struct module *mod) +{ + struct find_symbol_arg fsa = { + .name = "module_layout", + .gplok = true, + }; + + /* + * Since this should be found in kernel (which can't be removed), no + * locking is necessary -- use preempt_disable() to placate lockdep. + */ + preempt_disable(); + if (!find_symbol(&fsa)) { + preempt_enable(); + BUG(); + } + preempt_enable(); + return check_version(info, "module_layout", mod, fsa.crc); +} + +/* First part is kernel version, which we ignore if module has crcs. */ +int same_magic(const char *amagic, const char *bmagic, + bool has_crcs) +{ + if (has_crcs) { + amagic += strcspn(amagic, " "); + bmagic += strcspn(bmagic, " "); + } + return strcmp(amagic, bmagic) == 0; +} + +/* + * Generate the signature for all relevant module structures here. + * If these change, we don't want to try to parse the module. + */ +void module_layout(struct module *mod, + struct modversion_info *ver, + struct kernel_param *kp, + struct kernel_symbol *ks, + struct tracepoint * const *tp) +{ +} +EXPORT_SYMBOL(module_layout); diff --git a/kernel/module_signing.c b/kernel/module_signing.c deleted file mode 100644 index 8723ae70ea1f..000000000000 --- a/kernel/module_signing.c +++ /dev/null @@ -1,45 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Module signature checker - * - * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/module.h> -#include <linux/module_signature.h> -#include <linux/string.h> -#include <linux/verification.h> -#include <crypto/public_key.h> -#include "module-internal.h" - -/* - * Verify the signature on a module. - */ -int mod_verify_sig(const void *mod, struct load_info *info) -{ - struct module_signature ms; - size_t sig_len, modlen = info->len; - int ret; - - pr_devel("==>%s(,%zu)\n", __func__, modlen); - - if (modlen <= sizeof(ms)) - return -EBADMSG; - - memcpy(&ms, mod + (modlen - sizeof(ms)), sizeof(ms)); - - ret = mod_check_sig(&ms, modlen, "module"); - if (ret) - return ret; - - sig_len = be32_to_cpu(ms.sig_len); - modlen -= sig_len + sizeof(ms); - info->len = modlen; - - return verify_pkcs7_signature(mod, modlen, mod + modlen, sig_len, - VERIFY_USE_SECONDARY_KEYRING, - VERIFYING_MODULE_SIGNATURE, - NULL, NULL); -} diff --git a/kernel/notifier.c b/kernel/notifier.c index ba005ebf4730..0d5bd62c480e 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -20,7 +20,8 @@ BLOCKING_NOTIFIER_HEAD(reboot_notifier_list); */ static int notifier_chain_register(struct notifier_block **nl, - struct notifier_block *n) + struct notifier_block *n, + bool unique_priority) { while ((*nl) != NULL) { if (unlikely((*nl) == n)) { @@ -30,6 +31,8 @@ static int notifier_chain_register(struct notifier_block **nl, } if (n->priority > (*nl)->priority) break; + if (n->priority == (*nl)->priority && unique_priority) + return -EBUSY; nl = &((*nl)->next); } n->next = *nl; @@ -144,13 +147,36 @@ int atomic_notifier_chain_register(struct atomic_notifier_head *nh, int ret; spin_lock_irqsave(&nh->lock, flags); - ret = notifier_chain_register(&nh->head, n); + ret = notifier_chain_register(&nh->head, n, false); spin_unlock_irqrestore(&nh->lock, flags); return ret; } EXPORT_SYMBOL_GPL(atomic_notifier_chain_register); /** + * atomic_notifier_chain_register_unique_prio - Add notifier to an atomic notifier chain + * @nh: Pointer to head of the atomic notifier chain + * @n: New entry in notifier chain + * + * Adds a notifier to an atomic notifier chain if there is no other + * notifier registered using the same priority. + * + * Returns 0 on success, %-EEXIST or %-EBUSY on error. + */ +int atomic_notifier_chain_register_unique_prio(struct atomic_notifier_head *nh, + struct notifier_block *n) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&nh->lock, flags); + ret = notifier_chain_register(&nh->head, n, true); + spin_unlock_irqrestore(&nh->lock, flags); + return ret; +} +EXPORT_SYMBOL_GPL(atomic_notifier_chain_register_unique_prio); + +/** * atomic_notifier_chain_unregister - Remove notifier from an atomic notifier chain * @nh: Pointer to head of the atomic notifier chain * @n: Entry to remove from notifier chain @@ -204,23 +230,27 @@ int atomic_notifier_call_chain(struct atomic_notifier_head *nh, EXPORT_SYMBOL_GPL(atomic_notifier_call_chain); NOKPROBE_SYMBOL(atomic_notifier_call_chain); +/** + * atomic_notifier_call_chain_is_empty - Check whether notifier chain is empty + * @nh: Pointer to head of the atomic notifier chain + * + * Checks whether notifier chain is empty. + * + * Returns true is notifier chain is empty, false otherwise. + */ +bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh) +{ + return !rcu_access_pointer(nh->head); +} + /* * Blocking notifier chain routines. All access to the chain is * synchronized by an rwsem. */ -/** - * blocking_notifier_chain_register - Add notifier to a blocking notifier chain - * @nh: Pointer to head of the blocking notifier chain - * @n: New entry in notifier chain - * - * Adds a notifier to a blocking notifier chain. - * Must be called in process context. - * - * Returns 0 on success, %-EEXIST on error. - */ -int blocking_notifier_chain_register(struct blocking_notifier_head *nh, - struct notifier_block *n) +static int __blocking_notifier_chain_register(struct blocking_notifier_head *nh, + struct notifier_block *n, + bool unique_priority) { int ret; @@ -230,16 +260,49 @@ int blocking_notifier_chain_register(struct blocking_notifier_head *nh, * such times we must not call down_write(). */ if (unlikely(system_state == SYSTEM_BOOTING)) - return notifier_chain_register(&nh->head, n); + return notifier_chain_register(&nh->head, n, unique_priority); down_write(&nh->rwsem); - ret = notifier_chain_register(&nh->head, n); + ret = notifier_chain_register(&nh->head, n, unique_priority); up_write(&nh->rwsem); return ret; } + +/** + * blocking_notifier_chain_register - Add notifier to a blocking notifier chain + * @nh: Pointer to head of the blocking notifier chain + * @n: New entry in notifier chain + * + * Adds a notifier to a blocking notifier chain. + * Must be called in process context. + * + * Returns 0 on success, %-EEXIST on error. + */ +int blocking_notifier_chain_register(struct blocking_notifier_head *nh, + struct notifier_block *n) +{ + return __blocking_notifier_chain_register(nh, n, false); +} EXPORT_SYMBOL_GPL(blocking_notifier_chain_register); /** + * blocking_notifier_chain_register_unique_prio - Add notifier to a blocking notifier chain + * @nh: Pointer to head of the blocking notifier chain + * @n: New entry in notifier chain + * + * Adds a notifier to an blocking notifier chain if there is no other + * notifier registered using the same priority. + * + * Returns 0 on success, %-EEXIST or %-EBUSY on error. + */ +int blocking_notifier_chain_register_unique_prio(struct blocking_notifier_head *nh, + struct notifier_block *n) +{ + return __blocking_notifier_chain_register(nh, n, true); +} +EXPORT_SYMBOL_GPL(blocking_notifier_chain_register_unique_prio); + +/** * blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: Entry to remove from notifier chain @@ -341,7 +404,7 @@ EXPORT_SYMBOL_GPL(blocking_notifier_call_chain); int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *n) { - return notifier_chain_register(&nh->head, n); + return notifier_chain_register(&nh->head, n, false); } EXPORT_SYMBOL_GPL(raw_notifier_chain_register); @@ -420,10 +483,10 @@ int srcu_notifier_chain_register(struct srcu_notifier_head *nh, * such times we must not call mutex_lock(). */ if (unlikely(system_state == SYSTEM_BOOTING)) - return notifier_chain_register(&nh->head, n); + return notifier_chain_register(&nh->head, n, false); mutex_lock(&nh->mutex); - ret = notifier_chain_register(&nh->head, n); + ret = notifier_chain_register(&nh->head, n, false); mutex_unlock(&nh->mutex); return ret; } diff --git a/kernel/panic.c b/kernel/panic.c index 6737b2332275..a3c758dba15a 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -43,7 +43,9 @@ * Should we dump all CPUs backtraces in an oops event? * Defaults to 0, can be changed via sysctl. */ -unsigned int __read_mostly sysctl_oops_all_cpu_backtrace; +static unsigned int __read_mostly sysctl_oops_all_cpu_backtrace; +#else +#define sysctl_oops_all_cpu_backtrace 0 #endif /* CONFIG_SMP */ int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE; @@ -73,6 +75,28 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); +#if defined(CONFIG_SMP) && defined(CONFIG_SYSCTL) +static struct ctl_table kern_panic_table[] = { + { + .procname = "oops_all_cpu_backtrace", + .data = &sysctl_oops_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { } +}; + +static __init int kernel_panic_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_panic_table); + return 0; +} +late_initcall(kernel_panic_sysctls_init); +#endif + static long no_blink(int state) { return 0; diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index a46a3723bc66..f4f8cb0435b4 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -52,7 +52,7 @@ static struct kmem_cache *create_pid_cachep(unsigned int level) /* Name collision forces to do allocation under mutex. */ if (!*pkc) *pkc = kmem_cache_create(name, len, 0, - SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, 0); + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); mutex_unlock(&pid_caches_mutex); /* current can fail, but someone else can succeed. */ return READ_ONCE(*pkc); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 938d5c78b421..20a66bf9f465 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -83,7 +83,7 @@ bool hibernation_available(void) { return nohibernate == 0 && !security_locked_down(LOCKDOWN_HIBERNATION) && - !secretmem_active(); + !secretmem_active() && !cxl_mem_active(); } /** diff --git a/kernel/power/main.c b/kernel/power/main.c index 5242bf2ee469..e3694034b753 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -127,7 +127,9 @@ static ssize_t mem_sleep_show(struct kobject *kobj, struct kobj_attribute *attr, char *s = buf; suspend_state_t i; - for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) + for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) { + if (i >= PM_SUSPEND_MEM && cxl_mem_active()) + continue; if (mem_sleep_states[i]) { const char *label = mem_sleep_states[i]; @@ -136,6 +138,7 @@ static ssize_t mem_sleep_show(struct kobject *kobj, struct kobj_attribute *attr, else s += sprintf(s, "%s ", label); } + } /* Convert the last space to a newline if needed. */ if (s != buf) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 6fcdee7e87a5..827075944d28 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -236,7 +236,8 @@ EXPORT_SYMBOL_GPL(suspend_valid_only_mem); static bool sleep_state_supported(suspend_state_t state) { - return state == PM_SUSPEND_TO_IDLE || valid_state(state); + return state == PM_SUSPEND_TO_IDLE || + (valid_state(state) && !cxl_mem_active()); } static int platform_suspend_prepare(suspend_state_t state) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index a3e1035929b0..ea3dd55709e7 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3904,7 +3904,7 @@ static void wake_up_klogd_work_func(struct irq_work *irq_work) } if (pending & PRINTK_PENDING_WAKEUP) - wake_up_interruptible_all(&log_wait); + wake_up_interruptible(&log_wait); } static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = diff --git a/kernel/ptrace.c b/kernel/ptrace.c index ccc4b465775b..49c29baf9907 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -829,11 +829,7 @@ static long ptrace_get_rseq_configuration(struct task_struct *task, } #endif -#ifdef PTRACE_SINGLESTEP #define is_singlestep(request) ((request) == PTRACE_SINGLESTEP) -#else -#define is_singlestep(request) 0 -#endif #ifdef PTRACE_SINGLEBLOCK #define is_singleblock(request) ((request) == PTRACE_SINGLEBLOCK) @@ -1221,9 +1217,7 @@ int ptrace_request(struct task_struct *child, long request, } #endif -#ifdef PTRACE_SINGLESTEP case PTRACE_SINGLESTEP: -#endif #ifdef PTRACE_SINGLEBLOCK case PTRACE_SINGLEBLOCK: #endif diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 152492d52715..4916077119f3 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -23,6 +23,8 @@ #define RCU_SEQ_CTR_SHIFT 2 #define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) +extern int sysctl_sched_rt_runtime; + /* * Return the counter portion of a sequence number previously returned * by rcu_seq_snap() or rcu_seq_current(). diff --git a/kernel/reboot.c b/kernel/reboot.c index 4177645e74d6..a091145ee710 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -23,7 +23,7 @@ * this indicates whether you can reboot with ctrl-alt-del: the default is yes */ -int C_A_D = 1; +static int C_A_D = 1; struct pid *cad_pid; EXPORT_SYMBOL(cad_pid); @@ -48,12 +48,20 @@ int reboot_cpu; enum reboot_type reboot_type = BOOT_ACPI; int reboot_force; +struct sys_off_handler { + struct notifier_block nb; + int (*sys_off_cb)(struct sys_off_data *data); + void *cb_data; + enum sys_off_mode mode; + bool blocking; + void *list; +}; + /* - * If set, this is used for preparing the system to power off. + * Temporary stub that prevents linkage failure while we're in process + * of removing all uses of legacy pm_power_off() around the kernel. */ - -void (*pm_power_off_prepare)(void); -EXPORT_SYMBOL_GPL(pm_power_off_prepare); +void __weak (*pm_power_off)(void); /** * emergency_restart - reboot the system @@ -281,6 +289,316 @@ void kernel_halt(void) } EXPORT_SYMBOL_GPL(kernel_halt); +/* + * Notifier list for kernel code which wants to be called + * to prepare system for power off. + */ +static BLOCKING_NOTIFIER_HEAD(power_off_prep_handler_list); + +/* + * Notifier list for kernel code which wants to be called + * to power off system. + */ +static ATOMIC_NOTIFIER_HEAD(power_off_handler_list); + +static int sys_off_notify(struct notifier_block *nb, + unsigned long mode, void *cmd) +{ + struct sys_off_handler *handler; + struct sys_off_data data = {}; + + handler = container_of(nb, struct sys_off_handler, nb); + data.cb_data = handler->cb_data; + data.mode = mode; + data.cmd = cmd; + + return handler->sys_off_cb(&data); +} + +/** + * register_sys_off_handler - Register sys-off handler + * @mode: Sys-off mode + * @priority: Handler priority + * @callback: Callback function + * @cb_data: Callback argument + * + * Registers system power-off or restart handler that will be invoked + * at the step corresponding to the given sys-off mode. Handler's callback + * should return NOTIFY_DONE to permit execution of the next handler in + * the call chain or NOTIFY_STOP to break the chain (in error case for + * example). + * + * Multiple handlers can be registered at the default priority level. + * + * Only one handler can be registered at the non-default priority level, + * otherwise ERR_PTR(-EBUSY) is returned. + * + * Returns a new instance of struct sys_off_handler on success, or + * an ERR_PTR()-encoded error code otherwise. + */ +struct sys_off_handler * +register_sys_off_handler(enum sys_off_mode mode, + int priority, + int (*callback)(struct sys_off_data *data), + void *cb_data) +{ + struct sys_off_handler *handler; + int err; + + handler = kzalloc(sizeof(*handler), GFP_KERNEL); + if (!handler) + return ERR_PTR(-ENOMEM); + + switch (mode) { + case SYS_OFF_MODE_POWER_OFF_PREPARE: + handler->list = &power_off_prep_handler_list; + handler->blocking = true; + break; + + case SYS_OFF_MODE_POWER_OFF: + handler->list = &power_off_handler_list; + break; + + case SYS_OFF_MODE_RESTART: + handler->list = &restart_handler_list; + break; + + default: + kfree(handler); + return ERR_PTR(-EINVAL); + } + + handler->nb.notifier_call = sys_off_notify; + handler->nb.priority = priority; + handler->sys_off_cb = callback; + handler->cb_data = cb_data; + handler->mode = mode; + + if (handler->blocking) { + if (priority == SYS_OFF_PRIO_DEFAULT) + err = blocking_notifier_chain_register(handler->list, + &handler->nb); + else + err = blocking_notifier_chain_register_unique_prio(handler->list, + &handler->nb); + } else { + if (priority == SYS_OFF_PRIO_DEFAULT) + err = atomic_notifier_chain_register(handler->list, + &handler->nb); + else + err = atomic_notifier_chain_register_unique_prio(handler->list, + &handler->nb); + } + + if (err) { + kfree(handler); + return ERR_PTR(err); + } + + return handler; +} +EXPORT_SYMBOL_GPL(register_sys_off_handler); + +/** + * unregister_sys_off_handler - Unregister sys-off handler + * @handler: Sys-off handler + * + * Unregisters given sys-off handler. + */ +void unregister_sys_off_handler(struct sys_off_handler *handler) +{ + int err; + + if (!handler) + return; + + if (handler->blocking) + err = blocking_notifier_chain_unregister(handler->list, + &handler->nb); + else + err = atomic_notifier_chain_unregister(handler->list, + &handler->nb); + + /* sanity check, shall never happen */ + WARN_ON(err); + + kfree(handler); +} +EXPORT_SYMBOL_GPL(unregister_sys_off_handler); + +static void devm_unregister_sys_off_handler(void *data) +{ + struct sys_off_handler *handler = data; + + unregister_sys_off_handler(handler); +} + +/** + * devm_register_sys_off_handler - Register sys-off handler + * @dev: Device that registers handler + * @mode: Sys-off mode + * @priority: Handler priority + * @callback: Callback function + * @cb_data: Callback argument + * + * Registers resource-managed sys-off handler. + * + * Returns zero on success, or error code on failure. + */ +int devm_register_sys_off_handler(struct device *dev, + enum sys_off_mode mode, + int priority, + int (*callback)(struct sys_off_data *data), + void *cb_data) +{ + struct sys_off_handler *handler; + + handler = register_sys_off_handler(mode, priority, callback, cb_data); + if (IS_ERR(handler)) + return PTR_ERR(handler); + + return devm_add_action_or_reset(dev, devm_unregister_sys_off_handler, + handler); +} +EXPORT_SYMBOL_GPL(devm_register_sys_off_handler); + +/** + * devm_register_power_off_handler - Register power-off handler + * @dev: Device that registers callback + * @callback: Callback function + * @cb_data: Callback's argument + * + * Registers resource-managed sys-off handler with a default priority + * and using power-off mode. + * + * Returns zero on success, or error code on failure. + */ +int devm_register_power_off_handler(struct device *dev, + int (*callback)(struct sys_off_data *data), + void *cb_data) +{ + return devm_register_sys_off_handler(dev, + SYS_OFF_MODE_POWER_OFF, + SYS_OFF_PRIO_DEFAULT, + callback, cb_data); +} +EXPORT_SYMBOL_GPL(devm_register_power_off_handler); + +/** + * devm_register_restart_handler - Register restart handler + * @dev: Device that registers callback + * @callback: Callback function + * @cb_data: Callback's argument + * + * Registers resource-managed sys-off handler with a default priority + * and using restart mode. + * + * Returns zero on success, or error code on failure. + */ +int devm_register_restart_handler(struct device *dev, + int (*callback)(struct sys_off_data *data), + void *cb_data) +{ + return devm_register_sys_off_handler(dev, + SYS_OFF_MODE_RESTART, + SYS_OFF_PRIO_DEFAULT, + callback, cb_data); +} +EXPORT_SYMBOL_GPL(devm_register_restart_handler); + +static struct sys_off_handler *platform_power_off_handler; + +static int platform_power_off_notify(struct sys_off_data *data) +{ + void (*platform_power_power_off_cb)(void) = data->cb_data; + + platform_power_power_off_cb(); + + return NOTIFY_DONE; +} + +/** + * register_platform_power_off - Register platform-level power-off callback + * @power_off: Power-off callback + * + * Registers power-off callback that will be called as last step + * of the power-off sequence. This callback is expected to be invoked + * for the last resort. Only one platform power-off callback is allowed + * to be registered at a time. + * + * Returns zero on success, or error code on failure. + */ +int register_platform_power_off(void (*power_off)(void)) +{ + struct sys_off_handler *handler; + + handler = register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, + SYS_OFF_PRIO_PLATFORM, + platform_power_off_notify, + power_off); + if (IS_ERR(handler)) + return PTR_ERR(handler); + + platform_power_off_handler = handler; + + return 0; +} +EXPORT_SYMBOL_GPL(register_platform_power_off); + +/** + * unregister_platform_power_off - Unregister platform-level power-off callback + * @power_off: Power-off callback + * + * Unregisters previously registered platform power-off callback. + */ +void unregister_platform_power_off(void (*power_off)(void)) +{ + if (platform_power_off_handler && + platform_power_off_handler->cb_data == power_off) { + unregister_sys_off_handler(platform_power_off_handler); + platform_power_off_handler = NULL; + } +} +EXPORT_SYMBOL_GPL(unregister_platform_power_off); + +static int legacy_pm_power_off(struct sys_off_data *data) +{ + if (pm_power_off) + pm_power_off(); + + return NOTIFY_DONE; +} + +static void do_kernel_power_off_prepare(void) +{ + blocking_notifier_call_chain(&power_off_prep_handler_list, 0, NULL); +} + +/** + * do_kernel_power_off - Execute kernel power-off handler call chain + * + * Expected to be called as last step of the power-off sequence. + * + * Powers off the system immediately if a power-off handler function has + * been registered. Otherwise does nothing. + */ +void do_kernel_power_off(void) +{ + atomic_notifier_call_chain(&power_off_handler_list, 0, NULL); +} + +/** + * kernel_can_power_off - check whether system can be powered off + * + * Returns true if power-off handler is registered and system can be + * powered off, false otherwise. + */ +bool kernel_can_power_off(void) +{ + return !atomic_notifier_call_chain_is_empty(&power_off_handler_list); +} +EXPORT_SYMBOL_GPL(kernel_can_power_off); + /** * kernel_power_off - power_off the system * @@ -289,8 +607,7 @@ EXPORT_SYMBOL_GPL(kernel_halt); void kernel_power_off(void) { kernel_shutdown_prepare(SYSTEM_POWER_OFF); - if (pm_power_off_prepare) - pm_power_off_prepare(); + do_kernel_power_off_prepare(); migrate_to_reboot_cpu(); syscore_shutdown(); pr_emerg("Power down\n"); @@ -313,6 +630,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg) { struct pid_namespace *pid_ns = task_active_pid_ns(current); + struct sys_off_handler *sys_off = NULL; char buffer[256]; int ret = 0; @@ -337,10 +655,25 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, if (ret) return ret; + /* + * Register sys-off handlers for legacy PM callback. This allows + * legacy PM callbacks temporary co-exist with the new sys-off API. + * + * TODO: Remove legacy handlers once all legacy PM users will be + * switched to the sys-off based APIs. + */ + if (pm_power_off) { + sys_off = register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, + SYS_OFF_PRIO_DEFAULT, + legacy_pm_power_off, NULL); + if (IS_ERR(sys_off)) + return PTR_ERR(sys_off); + } + /* Instead of trying to make the power_off code look like * halt when pm_power_off is not set do it the easy way. */ - if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off) + if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !kernel_can_power_off()) cmd = LINUX_REBOOT_CMD_HALT; mutex_lock(&system_transition_mutex); @@ -394,6 +727,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd, break; } mutex_unlock(&system_transition_mutex); + unregister_sys_off_handler(sys_off); return ret; } @@ -417,7 +751,8 @@ void ctrl_alt_del(void) kill_cad_pid(SIGINT, 1); } -char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff"; +#define POWEROFF_CMD_PATH_LEN 256 +static char poweroff_cmd[POWEROFF_CMD_PATH_LEN] = "/sbin/poweroff"; static const char reboot_cmd[] = "/sbin/reboot"; static int run_cmd(const char *cmd) @@ -879,6 +1214,33 @@ static struct attribute *reboot_attrs[] = { NULL, }; +#ifdef CONFIG_SYSCTL +static struct ctl_table kern_reboot_table[] = { + { + .procname = "poweroff_cmd", + .data = &poweroff_cmd, + .maxlen = POWEROFF_CMD_PATH_LEN, + .mode = 0644, + .proc_handler = proc_dostring, + }, + { + .procname = "ctrl-alt-del", + .data = &C_A_D, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static void __init kernel_reboot_sysctls_init(void) +{ + register_sysctl_init("kernel", kern_reboot_table); +} +#else +#define kernel_reboot_sysctls_init() do { } while (0) +#endif /* CONFIG_SYSCTL */ + static const struct attribute_group reboot_attr_group = { .attrs = reboot_attrs, }; @@ -898,6 +1260,8 @@ static int __init reboot_ksysfs_init(void) return ret; } + kernel_reboot_sysctls_init(); + return 0; } late_initcall(reboot_ksysfs_init); diff --git a/kernel/relay.c b/kernel/relay.c index d1a67fbb819d..6a611e779e95 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -440,7 +440,7 @@ int relay_prepare_cpu(unsigned int cpu) mutex_lock(&relay_channels_mutex); list_for_each_entry(chan, &relay_channels, list) { - if ((buf = *per_cpu_ptr(chan->buf, cpu))) + if (*per_cpu_ptr(chan->buf, cpu)) continue; buf = relay_open_buf(chan, cpu); if (!buf) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a247f8d9d417..696c6490bd5b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -148,12 +148,6 @@ const_debug unsigned int sysctl_sched_nr_migrate = 8; const_debug unsigned int sysctl_sched_nr_migrate = 32; #endif -/* - * period over which we measure -rt task CPU usage in us. - * default: 1s - */ -unsigned int sysctl_sched_rt_period = 1000000; - __read_mostly int scheduler_running; #ifdef CONFIG_SCHED_CORE @@ -448,13 +442,6 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { } #endif /* CONFIG_SCHED_CORE */ /* - * part of the period that we allow rt tasks to run in us. - * default: 0.95s - */ -int sysctl_sched_rt_runtime = 950000; - - -/* * Serialization rules: * * Lock order: @@ -1322,10 +1309,10 @@ static void set_load_weight(struct task_struct *p, bool update_load) static DEFINE_MUTEX(uclamp_mutex); /* Max allowed minimum utilization */ -unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; +static unsigned int __maybe_unused sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; /* Max allowed maximum utilization */ -unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; +static unsigned int __maybe_unused sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; /* * By default RT tasks run at the maximum performance point/capacity of the @@ -1342,7 +1329,7 @@ unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; * This knob will not override the system default sched_util_clamp_min defined * above. */ -unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE; +static unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE; /* All clamps are required to be less or equal than these values */ static struct uclamp_se uclamp_default[UCLAMP_CNT]; @@ -1472,33 +1459,6 @@ static void uclamp_update_util_min_rt_default(struct task_struct *p) task_rq_unlock(rq, p, &rf); } -static void uclamp_sync_util_min_rt_default(void) -{ - struct task_struct *g, *p; - - /* - * copy_process() sysctl_uclamp - * uclamp_min_rt = X; - * write_lock(&tasklist_lock) read_lock(&tasklist_lock) - * // link thread smp_mb__after_spinlock() - * write_unlock(&tasklist_lock) read_unlock(&tasklist_lock); - * sched_post_fork() for_each_process_thread() - * __uclamp_sync_rt() __uclamp_sync_rt() - * - * Ensures that either sched_post_fork() will observe the new - * uclamp_min_rt or for_each_process_thread() will observe the new - * task. - */ - read_lock(&tasklist_lock); - smp_mb__after_spinlock(); - read_unlock(&tasklist_lock); - - rcu_read_lock(); - for_each_process_thread(g, p) - uclamp_update_util_min_rt_default(p); - rcu_read_unlock(); -} - static inline struct uclamp_se uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id) { @@ -1778,6 +1738,11 @@ uclamp_update_active_tasks(struct cgroup_subsys_state *css) } static void cpu_util_update_eff(struct cgroup_subsys_state *css); +#endif + +#ifdef CONFIG_SYSCTL +#ifdef CONFIG_UCLAMP_TASK +#ifdef CONFIG_UCLAMP_TASK_GROUP static void uclamp_update_root_tg(void) { struct task_group *tg = &root_task_group; @@ -1795,7 +1760,34 @@ static void uclamp_update_root_tg(void) static void uclamp_update_root_tg(void) { } #endif -int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, +static void uclamp_sync_util_min_rt_default(void) +{ + struct task_struct *g, *p; + + /* + * copy_process() sysctl_uclamp + * uclamp_min_rt = X; + * write_lock(&tasklist_lock) read_lock(&tasklist_lock) + * // link thread smp_mb__after_spinlock() + * write_unlock(&tasklist_lock) read_unlock(&tasklist_lock); + * sched_post_fork() for_each_process_thread() + * __uclamp_sync_rt() __uclamp_sync_rt() + * + * Ensures that either sched_post_fork() will observe the new + * uclamp_min_rt or for_each_process_thread() will observe the new + * task. + */ + read_lock(&tasklist_lock); + smp_mb__after_spinlock(); + read_unlock(&tasklist_lock); + + rcu_read_lock(); + for_each_process_thread(g, p) + uclamp_update_util_min_rt_default(p); + rcu_read_unlock(); +} + +static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { bool update_root_tg = false; @@ -1859,6 +1851,8 @@ done: return result; } +#endif +#endif static int uclamp_validate(struct task_struct *p, const struct sched_attr *attr) @@ -4433,7 +4427,7 @@ out: __setup("schedstats=", setup_schedstats); #ifdef CONFIG_PROC_SYSCTL -int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, +static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; @@ -4455,6 +4449,52 @@ int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, #endif /* CONFIG_PROC_SYSCTL */ #endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_core_sysctls[] = { +#ifdef CONFIG_SCHEDSTATS + { + .procname = "sched_schedstats", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_schedstats, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_UCLAMP_TASK + { + .procname = "sched_util_clamp_min", + .data = &sysctl_sched_uclamp_util_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, + { + .procname = "sched_util_clamp_max", + .data = &sysctl_sched_uclamp_util_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, + { + .procname = "sched_util_clamp_min_rt_default", + .data = &sysctl_sched_uclamp_util_min_rt_default, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, +#endif /* CONFIG_UCLAMP_TASK */ + {} +}; +static int __init sched_core_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_core_sysctls); + return 0; +} +late_initcall(sched_core_sysctl_init); +#endif /* CONFIG_SYSCTL */ + /* * fork()/clone()-time setup: */ diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 936817ae142f..b5152961b743 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -16,6 +16,40 @@ * Fabio Checconi <fchecconi@gmail.com> */ +/* + * Default limits for DL period; on the top end we guard against small util + * tasks still getting ridiculously long effective runtimes, on the bottom end we + * guard against timer DoS. + */ +static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */ +static unsigned int sysctl_sched_dl_period_min = 100; /* 100 us */ +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_dl_sysctls[] = { + { + .procname = "sched_deadline_period_max_us", + .data = &sysctl_sched_dl_period_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sched_deadline_period_min_us", + .data = &sysctl_sched_dl_period_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; + +static int __init sched_dl_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_dl_sysctls); + return 0; +} +late_initcall(sched_dl_sysctl_init); +#endif + static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se) { return container_of(dl_se, struct task_struct, dl); @@ -2873,14 +2907,6 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr) } /* - * Default limits for DL period; on the top end we guard against small util - * tasks still getting ridiculously long effective runtimes, on the bottom end we - * guard against timer DoS. - */ -unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */ -unsigned int sysctl_sched_dl_period_min = 100; /* 100 us */ - -/* * This function validates the new parameters of a -deadline task. * We ask for the deadline not being zero, and greater or equal * than the runtime, as well as the period of being zero or diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 906b2c7c48d1..8c5b74f66bd3 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -174,7 +174,37 @@ int __weak arch_asym_cpu_priority(int cpu) * * (default: 5 msec, units: microseconds) */ -unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +static unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +#endif + +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_fair_sysctls[] = { + { + .procname = "sched_child_runs_first", + .data = &sysctl_sched_child_runs_first, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_CFS_BANDWIDTH + { + .procname = "sched_cfs_bandwidth_slice_us", + .data = &sysctl_sched_cfs_bandwidth_slice, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + }, +#endif + {} +}; + +static int __init sched_fair_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_fair_sysctls); + return 0; +} +late_initcall(sched_fair_sysctl_init); #endif static inline void update_load_add(struct load_weight *lw, unsigned long inc) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 7891c0f0e1ff..8c9ed9664840 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -5,7 +5,6 @@ */ int sched_rr_timeslice = RR_TIMESLICE; -int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; /* More than 4 hours if BW_SHIFT equals 20. */ static const u64 max_rt_runtime = MAX_BW; @@ -13,6 +12,57 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); struct rt_bandwidth def_rt_bandwidth; +/* + * period over which we measure -rt task CPU usage in us. + * default: 1s + */ +unsigned int sysctl_sched_rt_period = 1000000; + +/* + * part of the period that we allow rt tasks to run in us. + * default: 0.95s + */ +int sysctl_sched_rt_runtime = 950000; + +#ifdef CONFIG_SYSCTL +static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; +static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +static int sched_rr_handler(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); +static struct ctl_table sched_rt_sysctls[] = { + { + .procname = "sched_rt_period_us", + .data = &sysctl_sched_rt_period, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_rt_handler, + }, + { + .procname = "sched_rt_runtime_us", + .data = &sysctl_sched_rt_runtime, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sched_rt_handler, + }, + { + .procname = "sched_rr_timeslice_ms", + .data = &sysctl_sched_rr_timeslice, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sched_rr_handler, + }, + {} +}; + +static int __init sched_rt_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_rt_sysctls); + return 0; +} +late_initcall(sched_rt_sysctl_init); +#endif + static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer) { struct rt_bandwidth *rt_b = @@ -2862,6 +2912,7 @@ long sched_group_rt_period(struct task_group *tg) return rt_period_us; } +#ifdef CONFIG_SYSCTL static int sched_rt_global_constraints(void) { int ret = 0; @@ -2872,6 +2923,7 @@ static int sched_rt_global_constraints(void) return ret; } +#endif /* CONFIG_SYSCTL */ int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) { @@ -2883,6 +2935,8 @@ int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) } #else /* !CONFIG_RT_GROUP_SCHED */ + +#ifdef CONFIG_SYSCTL static int sched_rt_global_constraints(void) { unsigned long flags; @@ -2900,8 +2954,10 @@ static int sched_rt_global_constraints(void) return 0; } +#endif /* CONFIG_SYSCTL */ #endif /* CONFIG_RT_GROUP_SCHED */ +#ifdef CONFIG_SYSCTL static int sched_rt_global_validate(void) { if (sysctl_sched_rt_period <= 0) @@ -2926,7 +2982,7 @@ static void sched_rt_do_global(void) raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); } -int sched_rt_handler(struct ctl_table *table, int write, void *buffer, +static int sched_rt_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_period, old_runtime; @@ -2965,7 +3021,7 @@ undo: return ret; } -int sched_rr_handler(struct ctl_table *table, int write, void *buffer, +static int sched_rr_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -2986,6 +3042,7 @@ int sched_rr_handler(struct ctl_table *table, int write, void *buffer, return ret; } +#endif /* CONFIG_SYSCTL */ #ifdef CONFIG_SCHED_DEBUG void print_rt_stats(struct seq_file *m, int cpu) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 2ce18584dca3..01259611beb9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -108,10 +108,17 @@ extern __read_mostly int scheduler_running; extern unsigned long calc_load_update; extern atomic_long_t calc_load_tasks; +extern unsigned int sysctl_sched_child_runs_first; + extern void calc_global_load_tick(struct rq *this_rq); extern long calc_load_fold_active(struct rq *this_rq, long adjust); extern void call_trace_sched_update_nr_running(struct rq *rq, int count); + +extern unsigned int sysctl_sched_rt_period; +extern int sysctl_sched_rt_runtime; +extern int sched_rr_timeslice; + /* * Helpers for converting nanosecond timing to jiffy resolution */ diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 810750e62118..05b6c2ad90b9 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -206,7 +206,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) DEFINE_STATIC_KEY_FALSE(sched_energy_present); -unsigned int sysctl_sched_energy_aware = 1; +static unsigned int sysctl_sched_energy_aware = 1; DEFINE_MUTEX(sched_energy_mutex); bool sched_energy_update; @@ -220,7 +220,7 @@ void rebuild_sched_domains_energy(void) } #ifdef CONFIG_PROC_SYSCTL -int sched_energy_aware_handler(struct ctl_table *table, int write, +static int sched_energy_aware_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, state; @@ -237,6 +237,27 @@ int sched_energy_aware_handler(struct ctl_table *table, int write, return ret; } + +static struct ctl_table sched_energy_aware_sysctls[] = { + { + .procname = "sched_energy_aware", + .data = &sysctl_sched_energy_aware, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sched_energy_aware_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static int __init sched_energy_aware_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_energy_aware_sysctls); + return 0; +} + +late_initcall(sched_energy_aware_sysctl_init); #endif static void free_pd(struct perf_domain *pd) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 82bcf5e3009f..e52b6e372c60 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -61,12 +61,9 @@ #include <linux/capability.h> #include <linux/binfmts.h> #include <linux/sched/sysctl.h> -#include <linux/kexec.h> #include <linux/mount.h> #include <linux/userfaultfd_k.h> -#include <linux/latencytop.h> #include <linux/pid.h> -#include <linux/delayacct.h> #include "../lib/kstrtox.h" @@ -81,15 +78,9 @@ #ifdef CONFIG_SPARC #include <asm/setup.h> #endif -#ifdef CONFIG_BSD_PROCESS_ACCT -#include <linux/acct.h> -#endif #ifdef CONFIG_RT_MUTEXES #include <linux/rtmutex.h> #endif -#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT) -#include <linux/lockdep.h> -#endif #if defined(CONFIG_SYSCTL) @@ -99,8 +90,6 @@ static const int six_hundred_forty_kb = 640 * 1024; #endif -/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ -static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; static const int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; @@ -1598,35 +1587,6 @@ int proc_do_static_key(struct ctl_table *table, int write, } static struct ctl_table kern_table[] = { - { - .procname = "sched_child_runs_first", - .data = &sysctl_sched_child_runs_first, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#ifdef CONFIG_SCHEDSTATS - { - .procname = "sched_schedstats", - .data = NULL, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_schedstats, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SCHEDSTATS */ -#ifdef CONFIG_TASK_DELAY_ACCT - { - .procname = "task_delayacct", - .data = NULL, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_delayacct, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_TASK_DELAY_ACCT */ #ifdef CONFIG_NUMA_BALANCING { .procname = "numa_balancing", @@ -1639,103 +1599,6 @@ static struct ctl_table kern_table[] = { }, #endif /* CONFIG_NUMA_BALANCING */ { - .procname = "sched_rt_period_us", - .data = &sysctl_sched_rt_period, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sched_rt_handler, - }, - { - .procname = "sched_rt_runtime_us", - .data = &sysctl_sched_rt_runtime, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = sched_rt_handler, - }, - { - .procname = "sched_deadline_period_max_us", - .data = &sysctl_sched_dl_period_max, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "sched_deadline_period_min_us", - .data = &sysctl_sched_dl_period_min, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "sched_rr_timeslice_ms", - .data = &sysctl_sched_rr_timeslice, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = sched_rr_handler, - }, -#ifdef CONFIG_UCLAMP_TASK - { - .procname = "sched_util_clamp_min", - .data = &sysctl_sched_uclamp_util_min, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_sched_uclamp_handler, - }, - { - .procname = "sched_util_clamp_max", - .data = &sysctl_sched_uclamp_util_max, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_sched_uclamp_handler, - }, - { - .procname = "sched_util_clamp_min_rt_default", - .data = &sysctl_sched_uclamp_util_min_rt_default, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sysctl_sched_uclamp_handler, - }, -#endif -#ifdef CONFIG_CFS_BANDWIDTH - { - .procname = "sched_cfs_bandwidth_slice_us", - .data = &sysctl_sched_cfs_bandwidth_slice, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - }, -#endif -#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) - { - .procname = "sched_energy_aware", - .data = &sysctl_sched_energy_aware, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sched_energy_aware_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif -#ifdef CONFIG_PROVE_LOCKING - { - .procname = "prove_locking", - .data = &prove_locking, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_LOCK_STAT - { - .procname = "lock_stat", - .data = &lock_stat, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif - { .procname = "panic", .data = &panic_timeout, .maxlen = sizeof(int), @@ -1759,24 +1622,6 @@ static struct ctl_table kern_table[] = { .extra2 = SYSCTL_ONE, }, #endif -#ifdef CONFIG_LATENCYTOP - { - .procname = "latencytop", - .data = &latencytop_enabled, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = sysctl_latencytop, - }, -#endif -#ifdef CONFIG_BLK_DEV_INITRD - { - .procname = "real-root-dev", - .data = &real_root_dev, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif { .procname = "print-fatal-signals", .data = &print_fatal_signals, @@ -1834,22 +1679,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif - { - .procname = "ctrl-alt-del", - .data = &C_A_D, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#ifdef CONFIG_FUNCTION_TRACER - { - .procname = "ftrace_enabled", - .data = &ftrace_enabled, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = ftrace_enable_sysctl, - }, -#endif #ifdef CONFIG_STACK_TRACER { .procname = "stack_tracer_enabled", @@ -1882,18 +1711,6 @@ static struct ctl_table kern_table[] = { .proc_handler = tracepoint_printk_sysctl, }, #endif -#ifdef CONFIG_KEXEC_CORE - { - .procname = "kexec_load_disabled", - .data = &kexec_load_disabled, - .maxlen = sizeof(int), - .mode = 0644, - /* only handle a transition from default "0" to "1" */ - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - .extra2 = SYSCTL_ONE, - }, -#endif #ifdef CONFIG_MODULES { .procname = "modprobe", @@ -1922,15 +1739,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dostring, }, #endif -#ifdef CONFIG_BSD_PROCESS_ACCT - { - .procname = "acct", - .data = &acct_parm, - .maxlen = 3*sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif #ifdef CONFIG_MAGIC_SYSRQ { .procname = "sysrq", @@ -1988,17 +1796,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_SMP - { - .procname = "oops_all_cpu_backtrace", - .data = &sysctl_oops_all_cpu_backtrace, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SMP */ { .procname = "pid_max", .data = &pid_max, @@ -2147,13 +1944,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif - { - .procname = "poweroff_cmd", - .data = &poweroff_cmd, - .maxlen = POWEROFF_CMD_PATH_LEN, - .mode = 0644, - .proc_handler = proc_dostring, - }, #ifdef CONFIG_KEYS { .procname = "keys", @@ -2263,29 +2053,6 @@ static struct ctl_table vm_table[] = { .extra2 = SYSCTL_TWO, }, { - .procname = "panic_on_oom", - .data = &sysctl_panic_on_oom, - .maxlen = sizeof(sysctl_panic_on_oom), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_TWO, - }, - { - .procname = "oom_kill_allocating_task", - .data = &sysctl_oom_kill_allocating_task, - .maxlen = sizeof(sysctl_oom_kill_allocating_task), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "oom_dump_tasks", - .data = &sysctl_oom_dump_tasks, - .maxlen = sizeof(sysctl_oom_dump_tasks), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { .procname = "overcommit_ratio", .data = &sysctl_overcommit_ratio, .maxlen = sizeof(sysctl_overcommit_ratio), @@ -2308,55 +2075,6 @@ static struct ctl_table vm_table[] = { .extra1 = SYSCTL_ZERO, }, { - .procname = "dirty_background_ratio", - .data = &dirty_background_ratio, - .maxlen = sizeof(dirty_background_ratio), - .mode = 0644, - .proc_handler = dirty_background_ratio_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE_HUNDRED, - }, - { - .procname = "dirty_background_bytes", - .data = &dirty_background_bytes, - .maxlen = sizeof(dirty_background_bytes), - .mode = 0644, - .proc_handler = dirty_background_bytes_handler, - .extra1 = SYSCTL_LONG_ONE, - }, - { - .procname = "dirty_ratio", - .data = &vm_dirty_ratio, - .maxlen = sizeof(vm_dirty_ratio), - .mode = 0644, - .proc_handler = dirty_ratio_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE_HUNDRED, - }, - { - .procname = "dirty_bytes", - .data = &vm_dirty_bytes, - .maxlen = sizeof(vm_dirty_bytes), - .mode = 0644, - .proc_handler = dirty_bytes_handler, - .extra1 = (void *)&dirty_bytes_min, - }, - { - .procname = "dirty_writeback_centisecs", - .data = &dirty_writeback_interval, - .maxlen = sizeof(dirty_writeback_interval), - .mode = 0644, - .proc_handler = dirty_writeback_centisecs_handler, - }, - { - .procname = "dirty_expire_centisecs", - .data = &dirty_expire_interval, - .maxlen = sizeof(dirty_expire_interval), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, - { .procname = "dirtytime_expire_seconds", .data = &dirtytime_expire_interval, .maxlen = sizeof(dirtytime_expire_interval), @@ -2528,13 +2246,6 @@ static struct ctl_table vm_table[] = { }, #endif { - .procname = "laptop_mode", - .data = &laptop_mode, - .maxlen = sizeof(laptop_mode), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { .procname = "vfs_cache_pressure", .data = &sysctl_vfs_cache_pressure, .maxlen = sizeof(sysctl_vfs_cache_pressure), @@ -2631,17 +2342,6 @@ static struct ctl_table vm_table[] = { .extra1 = SYSCTL_ZERO, }, #endif -#ifdef CONFIG_HIGHMEM - { - .procname = "highmem_is_dirtyable", - .data = &vm_highmem_is_dirtyable, - .maxlen = sizeof(vm_highmem_is_dirtyable), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif #ifdef CONFIG_MEMORY_FAILURE { .procname = "memory_failure_early_kill", diff --git a/kernel/taskstats.c b/kernel/taskstats.c index bcac5a9043aa..f7e246336218 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/taskstats_kern.h> #include <linux/tsacct_kern.h> +#include <linux/acct.h> #include <linux/delayacct.h> #include <linux/cpumask.h> #include <linux/percpu.h> @@ -153,6 +154,23 @@ static void send_cpu_listeners(struct sk_buff *skb, up_write(&listeners->sem); } +static void exe_add_tsk(struct taskstats *stats, struct task_struct *tsk) +{ + /* No idea if I'm allowed to access that here, now. */ + struct file *exe_file = get_task_exe_file(tsk); + + if (exe_file) { + /* Following cp_new_stat64() in stat.c . */ + stats->ac_exe_dev = + huge_encode_dev(exe_file->f_inode->i_sb->s_dev); + stats->ac_exe_inode = exe_file->f_inode->i_ino; + fput(exe_file); + } else { + stats->ac_exe_dev = 0; + stats->ac_exe_inode = 0; + } +} + static void fill_stats(struct user_namespace *user_ns, struct pid_namespace *pid_ns, struct task_struct *tsk, struct taskstats *stats) @@ -175,6 +193,9 @@ static void fill_stats(struct user_namespace *user_ns, /* fill in extended acct fields */ xacct_add_tsk(stats, tsk); + + /* add executable info */ + exe_add_tsk(stats, tsk); } static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) @@ -620,6 +641,8 @@ void taskstats_exit(struct task_struct *tsk, int group_dead) goto err; fill_stats(&init_user_ns, &init_pid_ns, tsk, stats); + if (group_dead) + stats->ac_flag |= AGROUP; /* * Doesn't matter if tsk is the leader or the last group member leaving @@ -665,6 +688,7 @@ static struct genl_family family __ro_after_init = { .module = THIS_MODULE, .ops = taskstats_ops, .n_ops = ARRAY_SIZE(taskstats_ops), + .netnsok = true, }; /* Needed early in initialization */ diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index d77cd8032213..0d261774d6f3 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -31,6 +31,10 @@ ifdef CONFIG_GCOV_PROFILE_FTRACE GCOV_PROFILE := y endif +# Functions in this file could be invoked from early interrupt +# code and produce random code coverage. +KCOV_INSTRUMENT_trace_preemptirq.o := n + CFLAGS_bpf_trace.o := -I$(src) CFLAGS_trace_benchmark.o := -I$(src) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 674add0aafb3..e750fe141a60 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -45,6 +45,8 @@ #include "trace_output.h" #include "trace_stat.h" +#define FTRACE_INVALID_FUNCTION "__ftrace_invalid_address__" + #define FTRACE_WARN_ON(cond) \ ({ \ int ___r = cond; \ @@ -86,7 +88,7 @@ struct ftrace_ops ftrace_list_end __read_mostly = { /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; -static int last_ftrace_enabled; +static int __maybe_unused last_ftrace_enabled; /* Current function tracing op */ struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end; @@ -119,7 +121,7 @@ struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; struct ftrace_ops global_ops; -/* Defined by vmlinux.lds.h see the commment above arch_ftrace_ops_list_func for details */ +/* Defined by vmlinux.lds.h see the comment above arch_ftrace_ops_list_func for details */ void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); @@ -952,7 +954,6 @@ static struct tracer_stat function_stats __initdata = { static __init void ftrace_profile_tracefs(struct dentry *d_tracer) { struct ftrace_profile_stat *stat; - struct dentry *entry; char *name; int ret; int cpu; @@ -983,11 +984,9 @@ static __init void ftrace_profile_tracefs(struct dentry *d_tracer) } } - entry = tracefs_create_file("function_profile_enabled", - TRACE_MODE_WRITE, d_tracer, NULL, - &ftrace_profile_fops); - if (!entry) - pr_warn("Could not create tracefs 'function_profile_enabled' entry\n"); + trace_create_file("function_profile_enabled", + TRACE_MODE_WRITE, d_tracer, NULL, + &ftrace_profile_fops); } #else /* CONFIG_FUNCTION_PROFILER */ @@ -2707,18 +2706,16 @@ ftrace_nop_initialize(struct module *mod, struct dyn_ftrace *rec) * archs can override this function if they must do something * before the modifying code is performed. */ -int __weak ftrace_arch_code_modify_prepare(void) +void __weak ftrace_arch_code_modify_prepare(void) { - return 0; } /* * archs can override this function if they must do something * after the modifying code is performed. */ -int __weak ftrace_arch_code_modify_post_process(void) +void __weak ftrace_arch_code_modify_post_process(void) { - return 0; } void ftrace_modify_all_code(int command) @@ -2804,12 +2801,7 @@ void __weak arch_ftrace_update_code(int command) static void ftrace_run_update_code(int command) { - int ret; - - ret = ftrace_arch_code_modify_prepare(); - FTRACE_WARN_ON(ret); - if (ret) - return; + ftrace_arch_code_modify_prepare(); /* * By default we use stop_machine() to modify the code. @@ -2819,8 +2811,7 @@ static void ftrace_run_update_code(int command) */ arch_ftrace_update_code(command); - ret = ftrace_arch_code_modify_post_process(); - FTRACE_WARN_ON(ret); + ftrace_arch_code_modify_post_process(); } static void ftrace_run_modify_code(struct ftrace_ops *ops, int command, @@ -3065,40 +3056,6 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) return 0; } -static void ftrace_startup_sysctl(void) -{ - int command; - - if (unlikely(ftrace_disabled)) - return; - - /* Force update next time */ - saved_ftrace_func = NULL; - /* ftrace_start_up is true if we want ftrace running */ - if (ftrace_start_up) { - command = FTRACE_UPDATE_CALLS; - if (ftrace_graph_active) - command |= FTRACE_START_FUNC_RET; - ftrace_startup_enable(command); - } -} - -static void ftrace_shutdown_sysctl(void) -{ - int command; - - if (unlikely(ftrace_disabled)) - return; - - /* ftrace_start_up is true if ftrace is running */ - if (ftrace_start_up) { - command = FTRACE_DISABLE_CALLS; - if (ftrace_graph_active) - command |= FTRACE_STOP_FUNC_RET; - ftrace_run_update_code(command); - } -} - static u64 ftrace_update_time; unsigned long ftrace_update_tot_cnt; unsigned long ftrace_number_of_pages; @@ -3665,6 +3622,105 @@ static void add_trampoline_func(struct seq_file *m, struct ftrace_ops *ops, seq_printf(m, " ->%pS", ptr); } +#ifdef FTRACE_MCOUNT_MAX_OFFSET +/* + * Weak functions can still have an mcount/fentry that is saved in + * the __mcount_loc section. These can be detected by having a + * symbol offset of greater than FTRACE_MCOUNT_MAX_OFFSET, as the + * symbol found by kallsyms is not the function that the mcount/fentry + * is part of. The offset is much greater in these cases. + * + * Test the record to make sure that the ip points to a valid kallsyms + * and if not, mark it disabled. + */ +static int test_for_valid_rec(struct dyn_ftrace *rec) +{ + char str[KSYM_SYMBOL_LEN]; + unsigned long offset; + const char *ret; + + ret = kallsyms_lookup(rec->ip, NULL, &offset, NULL, str); + + /* Weak functions can cause invalid addresses */ + if (!ret || offset > FTRACE_MCOUNT_MAX_OFFSET) { + rec->flags |= FTRACE_FL_DISABLED; + return 0; + } + return 1; +} + +static struct workqueue_struct *ftrace_check_wq __initdata; +static struct work_struct ftrace_check_work __initdata; + +/* + * Scan all the mcount/fentry entries to make sure they are valid. + */ +static __init void ftrace_check_work_func(struct work_struct *work) +{ + struct ftrace_page *pg; + struct dyn_ftrace *rec; + + mutex_lock(&ftrace_lock); + do_for_each_ftrace_rec(pg, rec) { + test_for_valid_rec(rec); + } while_for_each_ftrace_rec(); + mutex_unlock(&ftrace_lock); +} + +static int __init ftrace_check_for_weak_functions(void) +{ + INIT_WORK(&ftrace_check_work, ftrace_check_work_func); + + ftrace_check_wq = alloc_workqueue("ftrace_check_wq", WQ_UNBOUND, 0); + + queue_work(ftrace_check_wq, &ftrace_check_work); + return 0; +} + +static int __init ftrace_check_sync(void) +{ + /* Make sure the ftrace_check updates are finished */ + if (ftrace_check_wq) + destroy_workqueue(ftrace_check_wq); + return 0; +} + +late_initcall_sync(ftrace_check_sync); +subsys_initcall(ftrace_check_for_weak_functions); + +static int print_rec(struct seq_file *m, unsigned long ip) +{ + unsigned long offset; + char str[KSYM_SYMBOL_LEN]; + char *modname; + const char *ret; + + ret = kallsyms_lookup(ip, NULL, &offset, &modname, str); + /* Weak functions can cause invalid addresses */ + if (!ret || offset > FTRACE_MCOUNT_MAX_OFFSET) { + snprintf(str, KSYM_SYMBOL_LEN, "%s_%ld", + FTRACE_INVALID_FUNCTION, offset); + ret = NULL; + } + + seq_puts(m, str); + if (modname) + seq_printf(m, " [%s]", modname); + return ret == NULL ? -1 : 0; +} +#else +static inline int test_for_valid_rec(struct dyn_ftrace *rec) +{ + return 1; +} + +static inline int print_rec(struct seq_file *m, unsigned long ip) +{ + seq_printf(m, "%ps", (void *)ip); + return 0; +} +#endif + static int t_show(struct seq_file *m, void *v) { struct ftrace_iterator *iter = m->private; @@ -3689,7 +3745,13 @@ static int t_show(struct seq_file *m, void *v) if (!rec) return 0; - seq_printf(m, "%ps", (void *)rec->ip); + if (print_rec(m, rec->ip)) { + /* This should only happen when a rec is disabled */ + WARN_ON_ONCE(!(rec->flags & FTRACE_FL_DISABLED)); + seq_putc(m, '\n'); + return 0; + } + if (iter->flags & FTRACE_ITER_ENABLED) { struct ftrace_ops *ops; @@ -4007,6 +4069,24 @@ add_rec_by_index(struct ftrace_hash *hash, struct ftrace_glob *func_g, return 0; } +#ifdef FTRACE_MCOUNT_MAX_OFFSET +static int lookup_ip(unsigned long ip, char **modname, char *str) +{ + unsigned long offset; + + kallsyms_lookup(ip, NULL, &offset, modname, str); + if (offset > FTRACE_MCOUNT_MAX_OFFSET) + return -1; + return 0; +} +#else +static int lookup_ip(unsigned long ip, char **modname, char *str) +{ + kallsyms_lookup(ip, NULL, NULL, modname, str); + return 0; +} +#endif + static int ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g, struct ftrace_glob *mod_g, int exclude_mod) @@ -4014,7 +4094,12 @@ ftrace_match_record(struct dyn_ftrace *rec, struct ftrace_glob *func_g, char str[KSYM_SYMBOL_LEN]; char *modname; - kallsyms_lookup(rec->ip, NULL, NULL, &modname, str); + if (lookup_ip(rec->ip, &modname, str)) { + /* This should only happen when a rec is disabled */ + WARN_ON_ONCE(system_state == SYSTEM_RUNNING && + !(rec->flags & FTRACE_FL_DISABLED)); + return 0; + } if (mod_g) { int mod_matches = (modname) ? ftrace_match(modname, mod_g) : 0; @@ -4465,7 +4550,7 @@ int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper, * @ip: The instruction pointer address to remove the data from * * Returns the data if it is found, otherwise NULL. - * Note, if the data pointer is used as the data itself, (see + * Note, if the data pointer is used as the data itself, (see * ftrace_func_mapper_find_ip(), then the return value may be meaningless, * if the data pointer was set to zero. */ @@ -4560,8 +4645,8 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr, struct ftrace_probe_ops *probe_ops, void *data) { + struct ftrace_func_probe *probe = NULL, *iter; struct ftrace_func_entry *entry; - struct ftrace_func_probe *probe; struct ftrace_hash **orig_hash; struct ftrace_hash *old_hash; struct ftrace_hash *hash; @@ -4580,11 +4665,13 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr, mutex_lock(&ftrace_lock); /* Check if the probe_ops is already registered */ - list_for_each_entry(probe, &tr->func_probes, list) { - if (probe->probe_ops == probe_ops) + list_for_each_entry(iter, &tr->func_probes, list) { + if (iter->probe_ops == probe_ops) { + probe = iter; break; + } } - if (&probe->list == &tr->func_probes) { + if (!probe) { probe = kzalloc(sizeof(*probe), GFP_KERNEL); if (!probe) { mutex_unlock(&ftrace_lock); @@ -4702,9 +4789,9 @@ int unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, struct ftrace_probe_ops *probe_ops) { + struct ftrace_func_probe *probe = NULL, *iter; struct ftrace_ops_hash old_hash_ops; struct ftrace_func_entry *entry; - struct ftrace_func_probe *probe; struct ftrace_glob func_g; struct ftrace_hash **orig_hash; struct ftrace_hash *old_hash; @@ -4732,11 +4819,13 @@ unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr, mutex_lock(&ftrace_lock); /* Check if the probe_ops is already registered */ - list_for_each_entry(probe, &tr->func_probes, list) { - if (probe->probe_ops == probe_ops) + list_for_each_entry(iter, &tr->func_probes, list) { + if (iter->probe_ops == probe_ops) { + probe = iter; break; + } } - if (&probe->list == &tr->func_probes) + if (!probe) goto err_unlock_ftrace; ret = -EINVAL; @@ -5195,8 +5284,6 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) goto out_unlock; ret = ftrace_set_filter_ip(&direct_ops, ip, 0, 0); - if (ret) - remove_hash_entry(direct_functions, entry); if (!ret && !(direct_ops.flags & FTRACE_OPS_FL_ENABLED)) { ret = register_ftrace_function(&direct_ops); @@ -5205,6 +5292,7 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) } if (ret) { + remove_hash_entry(direct_functions, entry); kfree(entry); if (!direct->count) { list_del_rcu(&direct->next); @@ -6827,6 +6915,13 @@ void ftrace_module_enable(struct module *mod) !within_module_init(rec->ip, mod)) break; + /* Weak functions should still be ignored */ + if (!test_for_valid_rec(rec)) { + /* Clear all other flags. Should not be enabled anyway */ + rec->flags = FTRACE_FL_DISABLED; + continue; + } + cnt = 0; /* @@ -6863,11 +6958,16 @@ void ftrace_module_enable(struct module *mod) void ftrace_module_init(struct module *mod) { + int ret; + if (ftrace_disabled || !mod->num_ftrace_callsites) return; - ftrace_process_locs(mod, mod->ftrace_callsites, - mod->ftrace_callsites + mod->num_ftrace_callsites); + ret = ftrace_process_locs(mod, mod->ftrace_callsites, + mod->ftrace_callsites + mod->num_ftrace_callsites); + if (ret) + pr_warn("ftrace: failed to allocate entries for module '%s' functions\n", + mod->name); } static void save_ftrace_mod_rec(struct ftrace_mod_map *mod_map, @@ -7200,15 +7300,19 @@ void __init ftrace_init(void) pr_info("ftrace: allocating %ld entries in %ld pages\n", count, count / ENTRIES_PER_PAGE + 1); - last_ftrace_enabled = ftrace_enabled = 1; - ret = ftrace_process_locs(NULL, __start_mcount_loc, __stop_mcount_loc); + if (ret) { + pr_warn("ftrace: failed to allocate entries for functions\n"); + goto failed; + } pr_info("ftrace: allocated %ld pages with %ld groups\n", ftrace_number_of_pages, ftrace_number_of_groups); + last_ftrace_enabled = ftrace_enabled = 1; + set_ftrace_early_filters(); return; @@ -7267,9 +7371,6 @@ core_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; } static inline void ftrace_startup_all(int command) { } -# define ftrace_startup_sysctl() do { } while (0) -# define ftrace_shutdown_sysctl() do { } while (0) - static void ftrace_update_trampoline(struct ftrace_ops *ops) { } @@ -7909,62 +8010,6 @@ int unregister_ftrace_function(struct ftrace_ops *ops) } EXPORT_SYMBOL_GPL(unregister_ftrace_function); -static bool is_permanent_ops_registered(void) -{ - struct ftrace_ops *op; - - do_for_each_ftrace_op(op, ftrace_ops_list) { - if (op->flags & FTRACE_OPS_FL_PERMANENT) - return true; - } while_for_each_ftrace_op(op); - - return false; -} - -int -ftrace_enable_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = -ENODEV; - - mutex_lock(&ftrace_lock); - - if (unlikely(ftrace_disabled)) - goto out; - - ret = proc_dointvec(table, write, buffer, lenp, ppos); - - if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) - goto out; - - if (ftrace_enabled) { - - /* we are starting ftrace again */ - if (rcu_dereference_protected(ftrace_ops_list, - lockdep_is_held(&ftrace_lock)) != &ftrace_list_end) - update_ftrace_function(); - - ftrace_startup_sysctl(); - - } else { - if (is_permanent_ops_registered()) { - ftrace_enabled = true; - ret = -EBUSY; - goto out; - } - - /* stopping ftrace calls (just send to ftrace_stub) */ - ftrace_trace_function = ftrace_stub; - - ftrace_shutdown_sysctl(); - } - - last_ftrace_enabled = !!ftrace_enabled; - out: - mutex_unlock(&ftrace_lock); - return ret; -} - static int symbols_cmp(const void *a, const void *b) { const char **str_a = (const char **) a; @@ -8026,3 +8071,119 @@ int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *a return err; return args.found == args.cnt ? 0 : -ESRCH; } + +#ifdef CONFIG_SYSCTL + +#ifdef CONFIG_DYNAMIC_FTRACE +static void ftrace_startup_sysctl(void) +{ + int command; + + if (unlikely(ftrace_disabled)) + return; + + /* Force update next time */ + saved_ftrace_func = NULL; + /* ftrace_start_up is true if we want ftrace running */ + if (ftrace_start_up) { + command = FTRACE_UPDATE_CALLS; + if (ftrace_graph_active) + command |= FTRACE_START_FUNC_RET; + ftrace_startup_enable(command); + } +} + +static void ftrace_shutdown_sysctl(void) +{ + int command; + + if (unlikely(ftrace_disabled)) + return; + + /* ftrace_start_up is true if ftrace is running */ + if (ftrace_start_up) { + command = FTRACE_DISABLE_CALLS; + if (ftrace_graph_active) + command |= FTRACE_STOP_FUNC_RET; + ftrace_run_update_code(command); + } +} +#else +# define ftrace_startup_sysctl() do { } while (0) +# define ftrace_shutdown_sysctl() do { } while (0) +#endif /* CONFIG_DYNAMIC_FTRACE */ + +static bool is_permanent_ops_registered(void) +{ + struct ftrace_ops *op; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (op->flags & FTRACE_OPS_FL_PERMANENT) + return true; + } while_for_each_ftrace_op(op); + + return false; +} + +static int +ftrace_enable_sysctl(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = -ENODEV; + + mutex_lock(&ftrace_lock); + + if (unlikely(ftrace_disabled)) + goto out; + + ret = proc_dointvec(table, write, buffer, lenp, ppos); + + if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) + goto out; + + if (ftrace_enabled) { + + /* we are starting ftrace again */ + if (rcu_dereference_protected(ftrace_ops_list, + lockdep_is_held(&ftrace_lock)) != &ftrace_list_end) + update_ftrace_function(); + + ftrace_startup_sysctl(); + + } else { + if (is_permanent_ops_registered()) { + ftrace_enabled = true; + ret = -EBUSY; + goto out; + } + + /* stopping ftrace calls (just send to ftrace_stub) */ + ftrace_trace_function = ftrace_stub; + + ftrace_shutdown_sysctl(); + } + + last_ftrace_enabled = !!ftrace_enabled; + out: + mutex_unlock(&ftrace_lock); + return ret; +} + +static struct ctl_table ftrace_sysctls[] = { + { + .procname = "ftrace_enabled", + .data = &ftrace_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = ftrace_enable_sysctl, + }, + {} +}; + +static int __init ftrace_sysctl_init(void) +{ + register_sysctl_init("kernel", ftrace_sysctls); + return 0; +} +late_initcall(ftrace_sysctl_init); +#endif diff --git a/kernel/trace/pid_list.c b/kernel/trace/pid_list.c index a2ef1d18126a..95106d02b32d 100644 --- a/kernel/trace/pid_list.c +++ b/kernel/trace/pid_list.c @@ -118,9 +118,9 @@ static inline unsigned int pid_join(unsigned int upper1, /** * trace_pid_list_is_set - test if the pid is set in the list * @pid_list: The pid list to test - * @pid: The pid to to see if set in the list. + * @pid: The pid to see if set in the list. * - * Tests if @pid is is set in the @pid_list. This is usually called + * Tests if @pid is set in the @pid_list. This is usually called * from the scheduler when a task is scheduled. Its pid is checked * if it should be traced or not. * diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 05dfc7a12d3d..d59b6a328b7f 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -29,6 +29,14 @@ #include <asm/local.h> +/* + * The "absolute" timestamp in the buffer is only 59 bits. + * If a clock has the 5 MSBs set, it needs to be saved and + * reinserted. + */ +#define TS_MSB (0xf8ULL << 56) +#define ABS_TS_MASK (~TS_MSB) + static void update_pages_handler(struct work_struct *work); /* @@ -468,6 +476,7 @@ struct rb_time_struct { local_t cnt; local_t top; local_t bottom; + local_t msb; }; #else #include <asm/local64.h> @@ -569,7 +578,6 @@ struct ring_buffer_iter { * For the ring buffer, 64 bit required operations for the time is * the following: * - * - Only need 59 bits (uses 60 to make it even). * - Reads may fail if it interrupted a modification of the time stamp. * It will succeed if it did not interrupt another write even if * the read itself is interrupted by a write. @@ -594,6 +602,7 @@ struct ring_buffer_iter { */ #define RB_TIME_SHIFT 30 #define RB_TIME_VAL_MASK ((1 << RB_TIME_SHIFT) - 1) +#define RB_TIME_MSB_SHIFT 60 static inline int rb_time_cnt(unsigned long val) { @@ -613,7 +622,7 @@ static inline u64 rb_time_val(unsigned long top, unsigned long bottom) static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt) { - unsigned long top, bottom; + unsigned long top, bottom, msb; unsigned long c; /* @@ -625,6 +634,7 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt) c = local_read(&t->cnt); top = local_read(&t->top); bottom = local_read(&t->bottom); + msb = local_read(&t->msb); } while (c != local_read(&t->cnt)); *cnt = rb_time_cnt(top); @@ -633,7 +643,8 @@ static inline bool __rb_time_read(rb_time_t *t, u64 *ret, unsigned long *cnt) if (*cnt != rb_time_cnt(bottom)) return false; - *ret = rb_time_val(top, bottom); + /* The shift to msb will lose its cnt bits */ + *ret = rb_time_val(top, bottom) | ((u64)msb << RB_TIME_MSB_SHIFT); return true; } @@ -649,10 +660,12 @@ static inline unsigned long rb_time_val_cnt(unsigned long val, unsigned long cnt return (val & RB_TIME_VAL_MASK) | ((cnt & 3) << RB_TIME_SHIFT); } -static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom) +static inline void rb_time_split(u64 val, unsigned long *top, unsigned long *bottom, + unsigned long *msb) { *top = (unsigned long)((val >> RB_TIME_SHIFT) & RB_TIME_VAL_MASK); *bottom = (unsigned long)(val & RB_TIME_VAL_MASK); + *msb = (unsigned long)(val >> RB_TIME_MSB_SHIFT); } static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long cnt) @@ -663,15 +676,16 @@ static inline void rb_time_val_set(local_t *t, unsigned long val, unsigned long static void rb_time_set(rb_time_t *t, u64 val) { - unsigned long cnt, top, bottom; + unsigned long cnt, top, bottom, msb; - rb_time_split(val, &top, &bottom); + rb_time_split(val, &top, &bottom, &msb); /* Writes always succeed with a valid number even if it gets interrupted. */ do { cnt = local_inc_return(&t->cnt); rb_time_val_set(&t->top, top, cnt); rb_time_val_set(&t->bottom, bottom, cnt); + rb_time_val_set(&t->msb, val >> RB_TIME_MSB_SHIFT, cnt); } while (cnt != local_read(&t->cnt)); } @@ -686,8 +700,8 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set) static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) { - unsigned long cnt, top, bottom; - unsigned long cnt2, top2, bottom2; + unsigned long cnt, top, bottom, msb; + unsigned long cnt2, top2, bottom2, msb2; u64 val; /* The cmpxchg always fails if it interrupted an update */ @@ -703,16 +717,18 @@ static int rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set) cnt2 = cnt + 1; - rb_time_split(val, &top, &bottom); + rb_time_split(val, &top, &bottom, &msb); top = rb_time_val_cnt(top, cnt); bottom = rb_time_val_cnt(bottom, cnt); - rb_time_split(set, &top2, &bottom2); + rb_time_split(set, &top2, &bottom2, &msb2); top2 = rb_time_val_cnt(top2, cnt2); bottom2 = rb_time_val_cnt(bottom2, cnt2); if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2)) return false; + if (!rb_time_read_cmpxchg(&t->msb, msb, msb2)) + return false; if (!rb_time_read_cmpxchg(&t->top, top, top2)) return false; if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2)) @@ -783,6 +799,24 @@ static inline void verify_event(struct ring_buffer_per_cpu *cpu_buffer, } #endif +/* + * The absolute time stamp drops the 5 MSBs and some clocks may + * require them. The rb_fix_abs_ts() will take a previous full + * time stamp, and add the 5 MSB of that time stamp on to the + * saved absolute time stamp. Then they are compared in case of + * the unlikely event that the latest time stamp incremented + * the 5 MSB. + */ +static inline u64 rb_fix_abs_ts(u64 abs, u64 save_ts) +{ + if (save_ts & TS_MSB) { + abs |= save_ts & TS_MSB; + /* Check for overflow */ + if (unlikely(abs < save_ts)) + abs += 1ULL << 59; + } + return abs; +} static inline u64 rb_time_stamp(struct trace_buffer *buffer); @@ -811,8 +845,10 @@ u64 ring_buffer_event_time_stamp(struct trace_buffer *buffer, u64 ts; /* If the event includes an absolute time, then just use that */ - if (event->type_len == RINGBUF_TYPE_TIME_STAMP) - return rb_event_time_stamp(event); + if (event->type_len == RINGBUF_TYPE_TIME_STAMP) { + ts = rb_event_time_stamp(event); + return rb_fix_abs_ts(ts, cpu_buffer->tail_page->page->time_stamp); + } nest = local_read(&cpu_buffer->committing); verify_event(cpu_buffer, event); @@ -2754,8 +2790,15 @@ static void rb_add_timestamp(struct ring_buffer_per_cpu *cpu_buffer, (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE); if (unlikely(info->delta > (1ULL << 59))) { + /* + * Some timers can use more than 59 bits, and when a timestamp + * is added to the buffer, it will lose those bits. + */ + if (abs && (info->ts & TS_MSB)) { + info->delta &= ABS_TS_MASK; + /* did the clock go backwards */ - if (info->before == info->after && info->before > info->ts) { + } else if (info->before == info->after && info->before > info->ts) { /* not interrupted */ static int once; @@ -3304,7 +3347,7 @@ static void dump_buffer_page(struct buffer_data_page *bpage, case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); - ts = delta; + ts = rb_fix_abs_ts(delta, ts); pr_warn(" [%lld] absolute:%lld TIME STAMP\n", ts, delta); break; @@ -3380,7 +3423,7 @@ static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); - ts = delta; + ts = rb_fix_abs_ts(delta, ts); break; case RINGBUF_TYPE_PADDING: @@ -4367,6 +4410,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer, case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); + delta = rb_fix_abs_ts(delta, cpu_buffer->read_stamp); cpu_buffer->read_stamp = delta; return; @@ -4397,6 +4441,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter, case RINGBUF_TYPE_TIME_STAMP: delta = rb_event_time_stamp(event); + delta = rb_fix_abs_ts(delta, iter->read_stamp); iter->read_stamp = delta; return; @@ -4650,6 +4695,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts, case RINGBUF_TYPE_TIME_STAMP: if (ts) { *ts = rb_event_time_stamp(event); + *ts = rb_fix_abs_ts(*ts, reader->page->time_stamp); ring_buffer_normalize_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu, ts); } @@ -4741,6 +4787,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) case RINGBUF_TYPE_TIME_STAMP: if (ts) { *ts = rb_event_time_stamp(event); + *ts = rb_fix_abs_ts(*ts, iter->head_page->page->time_stamp); ring_buffer_normalize_time_stamp(cpu_buffer->buffer, cpu_buffer->cpu, ts); } @@ -6011,10 +6058,10 @@ static __init int test_ringbuffer(void) pr_info(" total events: %ld\n", total_lost + total_read); pr_info(" recorded len bytes: %ld\n", total_len); pr_info(" recorded size bytes: %ld\n", total_size); - if (total_lost) + if (total_lost) { pr_info(" With dropped events, record len and size may not match\n" " alloced and written from above\n"); - if (!total_lost) { + } else { if (RB_WARN_ON(buffer, total_len != total_alloc || total_size != total_written)) break; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 124f1897fd56..2c95992e2c71 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -721,13 +721,16 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, pos = 0; ret = trace_get_user(&parser, ubuf, cnt, &pos); - if (ret < 0 || !trace_parser_loaded(&parser)) + if (ret < 0) break; read += ret; ubuf += ret; cnt -= ret; + if (!trace_parser_loaded(&parser)) + break; + ret = -EINVAL; if (kstrtoul(parser.buffer, 0, &val)) break; @@ -753,7 +756,6 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, if (!nr_pids) { /* Cleared the list of pids */ trace_pid_list_free(pid_list); - read = ret; pid_list = NULL; } @@ -1174,7 +1176,7 @@ void tracing_snapshot_cond(struct trace_array *tr, void *cond_data) EXPORT_SYMBOL_GPL(tracing_snapshot_cond); /** - * tracing_snapshot_cond_data - get the user data associated with a snapshot + * tracing_cond_snapshot_data - get the user data associated with a snapshot * @tr: The tracing instance * * When the user enables a conditional snapshot using @@ -1542,6 +1544,7 @@ static struct { { ktime_get_mono_fast_ns, "mono", 1 }, { ktime_get_raw_fast_ns, "mono_raw", 1 }, { ktime_get_boot_fast_ns, "boot", 1 }, + { ktime_get_tai_fast_ns, "tai", 1 }, ARCH_TRACE_CLOCKS }; @@ -2835,7 +2838,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, } EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve); -static DEFINE_SPINLOCK(tracepoint_iter_lock); +static DEFINE_RAW_SPINLOCK(tracepoint_iter_lock); static DEFINE_MUTEX(tracepoint_printk_mutex); static void output_printk(struct trace_event_buffer *fbuffer) @@ -2863,14 +2866,14 @@ static void output_printk(struct trace_event_buffer *fbuffer) event = &fbuffer->trace_file->event_call->event; - spin_lock_irqsave(&tracepoint_iter_lock, flags); + raw_spin_lock_irqsave(&tracepoint_iter_lock, flags); trace_seq_init(&iter->seq); iter->ent = fbuffer->entry; event_call->event.funcs->trace(iter, 0, event); trace_seq_putc(&iter->seq, 0); printk("%s", iter->seq.buffer); - spin_unlock_irqrestore(&tracepoint_iter_lock, flags); + raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags); } int tracepoint_printk_sysctl(struct ctl_table *table, int write, @@ -4249,7 +4252,7 @@ static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file unsigned int flags) { bool tgid = flags & TRACE_ITER_RECORD_TGID; - const char *space = " "; + static const char space[] = " "; int prec = tgid ? 12 : 2; print_event_info(buf, m); @@ -4273,9 +4276,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) struct tracer *type = iter->trace; unsigned long entries; unsigned long total; - const char *name = "preemption"; - - name = type->name; + const char *name = type->name; get_total_entries(buf, &total, &entries); @@ -5469,7 +5470,7 @@ static const char readme_msg[] = " error_log\t- error log for failed commands (that support it)\n" " buffer_size_kb\t- view and modify size of per cpu buffer\n" " buffer_total_size_kb - view total size of all cpu buffers\n\n" - " trace_clock\t\t-change the clock used to order events\n" + " trace_clock\t\t- change the clock used to order events\n" " local: Per cpu clock but may not be synced across CPUs\n" " global: Synced across CPUs but slows tracing down.\n" " counter: Not a clock, but just an increment\n" @@ -5478,7 +5479,7 @@ static const char readme_msg[] = #ifdef CONFIG_X86_64 " x86-tsc: TSC cycle counter\n" #endif - "\n timestamp_mode\t-view the mode used to timestamp events\n" + "\n timestamp_mode\t- view the mode used to timestamp events\n" " delta: Delta difference against a buffer-wide timestamp\n" " absolute: Absolute (standalone) timestamp\n" "\n trace_marker\t\t- Writes into this file writes into the kernel buffer\n" @@ -6326,12 +6327,18 @@ static void tracing_set_nop(struct trace_array *tr) tr->current_trace = &nop_trace; } +static bool tracer_options_updated; + static void add_tracer_options(struct trace_array *tr, struct tracer *t) { /* Only enable if the directory has been created already. */ if (!tr->dir) return; + /* Only create trace option files after update_tracer_options finish */ + if (!tracer_options_updated) + return; + create_trace_option_files(tr, t); } @@ -6448,7 +6455,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, { struct trace_array *tr = filp->private_data; char buf[MAX_TRACER_SIZE+1]; - int i; + char *name; size_t ret; int err; @@ -6462,11 +6469,9 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf, buf[cnt] = 0; - /* strip ending whitespace. */ - for (i = cnt - 1; i > 0 && isspace(buf[i]); i--) - buf[i] = 0; + name = strim(buf); - err = tracing_set_tracer(tr, buf); + err = tracing_set_tracer(tr, name); if (err) return err; @@ -9170,6 +9175,7 @@ static void __update_tracer_options(struct trace_array *tr) static void update_tracer_options(struct trace_array *tr) { mutex_lock(&trace_types_lock); + tracer_options_updated = true; __update_tracer_options(tr); mutex_unlock(&trace_types_lock); } @@ -9602,6 +9608,7 @@ extern struct trace_eval_map *__stop_ftrace_eval_maps[]; static struct workqueue_struct *eval_map_wq __initdata; static struct work_struct eval_map_work __initdata; +static struct work_struct tracerfs_init_work __initdata; static void __init eval_map_work_func(struct work_struct *work) { @@ -9627,6 +9634,8 @@ static int __init trace_eval_init(void) return 0; } +subsys_initcall(trace_eval_init); + static int __init trace_eval_sync(void) { /* Make sure the eval map updates are finished */ @@ -9709,15 +9718,8 @@ static struct notifier_block trace_module_nb = { }; #endif /* CONFIG_MODULES */ -static __init int tracer_init_tracefs(void) +static __init void tracer_init_tracefs_work_func(struct work_struct *work) { - int ret; - - trace_access_lock_init(); - - ret = tracing_init_dentry(); - if (ret) - return 0; event_trace_init(); @@ -9739,8 +9741,6 @@ static __init int tracer_init_tracefs(void) trace_create_file("saved_tgids", TRACE_MODE_READ, NULL, NULL, &tracing_saved_tgids_fops); - trace_eval_init(); - trace_create_eval_file(NULL); #ifdef CONFIG_MODULES @@ -9755,6 +9755,24 @@ static __init int tracer_init_tracefs(void) create_trace_instances(NULL); update_tracer_options(&global_trace); +} + +static __init int tracer_init_tracefs(void) +{ + int ret; + + trace_access_lock_init(); + + ret = tracing_init_dentry(); + if (ret) + return 0; + + if (eval_map_wq) { + INIT_WORK(&tracerfs_init_work, tracer_init_tracefs_work_func); + queue_work(eval_map_wq, &tracerfs_init_work); + } else { + tracer_init_tracefs_work_func(NULL); + } return 0; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 07d990270e2a..ff816fb41e48 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1573,13 +1573,12 @@ struct enable_trigger_data { }; extern int event_enable_trigger_print(struct seq_file *m, - struct event_trigger_ops *ops, - struct event_trigger_data *data); -extern void event_enable_trigger_free(struct event_trigger_ops *ops, struct event_trigger_data *data); +extern void event_enable_trigger_free(struct event_trigger_data *data); extern int event_enable_trigger_parse(struct event_command *cmd_ops, struct trace_event_file *file, - char *glob, char *cmd, char *param); + char *glob, char *cmd, + char *param_and_filter); extern int event_enable_register_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file); @@ -1587,8 +1586,7 @@ extern void event_enable_unregister_trigger(char *glob, struct event_trigger_data *test, struct trace_event_file *file); extern void trigger_data_free(struct event_trigger_data *data); -extern int event_trigger_init(struct event_trigger_ops *ops, - struct event_trigger_data *data); +extern int event_trigger_init(struct event_trigger_data *data); extern int trace_event_trigger_enable_disable(struct trace_event_file *file, int trigger_enable); extern void update_cond_flag(struct trace_event_file *file); @@ -1629,10 +1627,11 @@ extern void event_trigger_reset_filter(struct event_command *cmd_ops, extern int event_trigger_register(struct event_command *cmd_ops, struct trace_event_file *file, char *glob, - char *cmd, - char *trigger, - struct event_trigger_data *trigger_data, - int *n_registered); + struct event_trigger_data *trigger_data); +extern void event_trigger_unregister(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, + struct event_trigger_data *trigger_data); /** * struct event_trigger_ops - callbacks for trace event triggers @@ -1686,12 +1685,9 @@ struct event_trigger_ops { struct trace_buffer *buffer, void *rec, struct ring_buffer_event *rbe); - int (*init)(struct event_trigger_ops *ops, - struct event_trigger_data *data); - void (*free)(struct event_trigger_ops *ops, - struct event_trigger_data *data); + int (*init)(struct event_trigger_data *data); + void (*free)(struct event_trigger_data *data); int (*print)(struct seq_file *m, - struct event_trigger_ops *ops, struct event_trigger_data *data); }; diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index 0580287d7a0d..778200dd8ede 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -300,7 +300,7 @@ trace_boot_hist_add_handlers(struct xbc_node *hnode, char **bufp, { struct xbc_node *node; const char *p, *handler; - int ret; + int ret = 0; handler = xbc_node_get_data(hnode); diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index e34e8182ee4b..076b447a1b88 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -255,19 +255,14 @@ static const struct file_operations dynamic_events_ops = { /* Make a tracefs interface for controlling dynamic events */ static __init int init_dynamic_event(void) { - struct dentry *entry; int ret; ret = tracing_init_dentry(); if (ret) return 0; - entry = tracefs_create_file("dynamic_events", TRACE_MODE_WRITE, NULL, - NULL, &dynamic_events_ops); - - /* Event list interface */ - if (!entry) - pr_warn("Could not create tracefs 'dynamic_events' entry\n"); + trace_create_file("dynamic_events", TRACE_MODE_WRITE, NULL, + NULL, &dynamic_events_ops); return 0; } diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 541aa13581b9..7d4478525c66 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -511,20 +511,17 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec) * functions are just stubs to fulfill what is needed to use the trigger * infrastructure. */ -static int eprobe_trigger_init(struct event_trigger_ops *ops, - struct event_trigger_data *data) +static int eprobe_trigger_init(struct event_trigger_data *data) { return 0; } -static void eprobe_trigger_free(struct event_trigger_ops *ops, - struct event_trigger_data *data) +static void eprobe_trigger_free(struct event_trigger_data *data) { } static int eprobe_trigger_print(struct seq_file *m, - struct event_trigger_ops *ops, struct event_trigger_data *data) { /* Do not print eprobe event triggers */ @@ -549,7 +546,8 @@ static struct event_trigger_ops eprobe_trigger_ops = { static int eprobe_trigger_cmd_parse(struct event_command *cmd_ops, struct trace_event_file *file, - char *glob, char *cmd, char *param) + char *glob, char *cmd, + char *param_and_filter) { return -1; } @@ -650,7 +648,7 @@ static struct trace_event_functions eprobe_funcs = { static int disable_eprobe(struct trace_eprobe *ep, struct trace_array *tr) { - struct event_trigger_data *trigger; + struct event_trigger_data *trigger = NULL, *iter; struct trace_event_file *file; struct eprobe_data *edata; @@ -658,14 +656,16 @@ static int disable_eprobe(struct trace_eprobe *ep, if (!file) return -ENOENT; - list_for_each_entry(trigger, &file->triggers, list) { - if (!(trigger->flags & EVENT_TRIGGER_FL_PROBE)) + list_for_each_entry(iter, &file->triggers, list) { + if (!(iter->flags & EVENT_TRIGGER_FL_PROBE)) continue; - edata = trigger->private_data; - if (edata->ep == ep) + edata = iter->private_data; + if (edata->ep == ep) { + trigger = iter; break; + } } - if (list_entry_is_head(trigger, &file->triggers, list)) + if (!trigger) return -ENODEV; list_del_rcu(&trigger->list); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f97de82d1342..181f08186d32 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -392,12 +392,6 @@ static void test_event_printk(struct trace_event_call *call) if (!(dereference_flags & (1ULL << arg))) goto next_arg; - /* Check for __get_sockaddr */; - if (str_has_prefix(fmt + i, "__get_sockaddr(")) { - dereference_flags &= ~(1ULL << arg); - goto next_arg; - } - /* Find the REC-> in the argument */ c = strchr(fmt + i, ','); r = strstr(fmt + i, "REC->"); @@ -413,7 +407,14 @@ static void test_event_printk(struct trace_event_call *call) a = strchr(fmt + i, '&'); if ((a && (a < r)) || test_field(r, call)) dereference_flags &= ~(1ULL << arg); + } else if ((r = strstr(fmt + i, "__get_dynamic_array(")) && + (!c || r < c)) { + dereference_flags &= ~(1ULL << arg); + } else if ((r = strstr(fmt + i, "__get_sockaddr(")) && + (!c || r < c)) { + dereference_flags &= ~(1ULL << arg); } + next_arg: i--; arg++; @@ -1723,9 +1724,9 @@ static LIST_HEAD(event_subsystems); static int subsystem_open(struct inode *inode, struct file *filp) { + struct trace_subsystem_dir *dir = NULL, *iter_dir; + struct trace_array *tr = NULL, *iter_tr; struct event_subsystem *system = NULL; - struct trace_subsystem_dir *dir = NULL; /* Initialize for gcc */ - struct trace_array *tr; int ret; if (tracing_is_disabled()) @@ -1734,10 +1735,12 @@ static int subsystem_open(struct inode *inode, struct file *filp) /* Make sure the system still exists */ mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); - list_for_each_entry(tr, &ftrace_trace_arrays, list) { - list_for_each_entry(dir, &tr->systems, list) { - if (dir == inode->i_private) { + list_for_each_entry(iter_tr, &ftrace_trace_arrays, list) { + list_for_each_entry(iter_dir, &iter_tr->systems, list) { + if (iter_dir == inode->i_private) { /* Don't open systems with no events */ + tr = iter_tr; + dir = iter_dir; if (dir->nr_events) { __get_system_dir(dir); system = dir->subsystem; @@ -1753,9 +1756,6 @@ static int subsystem_open(struct inode *inode, struct file *filp) if (!system) return -ENODEV; - /* Some versions of gcc think dir can be uninitialized here */ - WARN_ON(!dir); - /* Still need to increment the ref count of the system */ if (trace_array_get(tr) < 0) { put_system(dir); @@ -2280,8 +2280,8 @@ static struct dentry * event_subsystem_dir(struct trace_array *tr, const char *name, struct trace_event_file *file, struct dentry *parent) { + struct event_subsystem *system, *iter; struct trace_subsystem_dir *dir; - struct event_subsystem *system; struct dentry *entry; /* First see if we did not already create this dir */ @@ -2295,13 +2295,13 @@ event_subsystem_dir(struct trace_array *tr, const char *name, } /* Now see if the system itself exists. */ - list_for_each_entry(system, &event_subsystems, list) { - if (strcmp(system->name, name) == 0) + system = NULL; + list_for_each_entry(iter, &event_subsystems, list) { + if (strcmp(iter->name, name) == 0) { + system = iter; break; + } } - /* Reset system variable when not found */ - if (&system->list == &event_subsystems) - system = NULL; dir = kmalloc(sizeof(*dir), GFP_KERNEL); if (!dir) @@ -3546,12 +3546,10 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) struct dentry *d_events; struct dentry *entry; - entry = tracefs_create_file("set_event", TRACE_MODE_WRITE, parent, - tr, &ftrace_set_event_fops); - if (!entry) { - pr_warn("Could not create tracefs 'set_event' entry\n"); + entry = trace_create_file("set_event", TRACE_MODE_WRITE, parent, + tr, &ftrace_set_event_fops); + if (!entry) return -ENOMEM; - } d_events = tracefs_create_dir("events", parent); if (!d_events) { @@ -3566,16 +3564,12 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) /* There are not as crucial, just warn if they are not created */ - entry = tracefs_create_file("set_event_pid", TRACE_MODE_WRITE, parent, - tr, &ftrace_set_event_pid_fops); - if (!entry) - pr_warn("Could not create tracefs 'set_event_pid' entry\n"); + trace_create_file("set_event_pid", TRACE_MODE_WRITE, parent, + tr, &ftrace_set_event_pid_fops); - entry = tracefs_create_file("set_event_notrace_pid", - TRACE_MODE_WRITE, parent, tr, - &ftrace_set_event_notrace_pid_fops); - if (!entry) - pr_warn("Could not create tracefs 'set_event_notrace_pid' entry\n"); + trace_create_file("set_event_notrace_pid", + TRACE_MODE_WRITE, parent, tr, + &ftrace_set_event_notrace_pid_fops); /* ring buffer internal formats */ trace_create_file("header_page", TRACE_MODE_READ, d_events, @@ -3790,17 +3784,14 @@ static __init int event_trace_init_fields(void) __init int event_trace_init(void) { struct trace_array *tr; - struct dentry *entry; int ret; tr = top_trace_array(); if (!tr) return -ENODEV; - entry = tracefs_create_file("available_events", TRACE_MODE_READ, - NULL, tr, &ftrace_avail_fops); - if (!entry) - pr_warn("Could not create tracefs 'available_events' entry\n"); + trace_create_file("available_events", TRACE_MODE_READ, + NULL, tr, &ftrace_avail_fops); ret = early_event_add_tracer(NULL, tr); if (ret) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index b458a9afa2c0..4b1057ab9d96 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1816,7 +1816,7 @@ static void create_filter_finish(struct filter_parse_error *pe) * create_filter - create a filter for a trace_event_call * @tr: the trace array associated with these events * @call: trace_event_call to create a filter for - * @filter_str: filter string + * @filter_string: filter string * @set_str: remember @filter_str and enable detailed error in filter * @filterp: out param for created filter (always updated on return) * Must be a pointer that references a NULL pointer. diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 44db5ba9cabb..48e82e141d54 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2093,8 +2093,11 @@ static int init_var_ref(struct hist_field *ref_field, return err; free: kfree(ref_field->system); + ref_field->system = NULL; kfree(ref_field->event_name); + ref_field->event_name = NULL; kfree(ref_field->name); + ref_field->name = NULL; goto out; } @@ -2785,7 +2788,8 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data, static struct event_command trigger_hist_cmd; static int event_hist_trigger_parse(struct event_command *cmd_ops, struct trace_event_file *file, - char *glob, char *cmd, char *param); + char *glob, char *cmd, + char *param_and_filter); static bool compatible_keys(struct hist_trigger_data *target_hist_data, struct hist_trigger_data *hist_data, @@ -4161,7 +4165,7 @@ static int create_val_field(struct hist_trigger_data *hist_data, return __create_val_field(hist_data, val_idx, file, NULL, field_str, 0); } -static const char *no_comm = "(no comm)"; +static const char no_comm[] = "(no comm)"; static u64 hist_field_execname(struct hist_field *hist_field, struct tracing_map_elt *elt, @@ -5252,7 +5256,7 @@ static void hist_trigger_show(struct seq_file *m, seq_puts(m, "\n\n"); seq_puts(m, "# event histogram\n#\n# trigger info: "); - data->ops->print(m, data->ops, data); + data->ops->print(m, data); seq_puts(m, "#\n\n"); hist_data = data->private_data; @@ -5484,7 +5488,7 @@ static void hist_trigger_debug_show(struct seq_file *m, seq_puts(m, "\n\n"); seq_puts(m, "# event histogram\n#\n# trigger info: "); - data->ops->print(m, data->ops, data); + data->ops->print(m, data); seq_puts(m, "#\n\n"); hist_data = data->private_data; @@ -5621,7 +5625,6 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field) } static int event_hist_trigger_print(struct seq_file *m, - struct event_trigger_ops *ops, struct event_trigger_data *data) { struct hist_trigger_data *hist_data = data->private_data; @@ -5729,8 +5732,7 @@ static int event_hist_trigger_print(struct seq_file *m, return 0; } -static int event_hist_trigger_init(struct event_trigger_ops *ops, - struct event_trigger_data *data) +static int event_hist_trigger_init(struct event_trigger_data *data) { struct hist_trigger_data *hist_data = data->private_data; @@ -5758,8 +5760,7 @@ static void unregister_field_var_hists(struct hist_trigger_data *hist_data) } } -static void event_hist_trigger_free(struct event_trigger_ops *ops, - struct event_trigger_data *data) +static void event_hist_trigger_free(struct event_trigger_data *data) { struct hist_trigger_data *hist_data = data->private_data; @@ -5788,25 +5789,23 @@ static struct event_trigger_ops event_hist_trigger_ops = { .free = event_hist_trigger_free, }; -static int event_hist_trigger_named_init(struct event_trigger_ops *ops, - struct event_trigger_data *data) +static int event_hist_trigger_named_init(struct event_trigger_data *data) { data->ref++; save_named_trigger(data->named_data->name, data); - event_hist_trigger_init(ops, data->named_data); + event_hist_trigger_init(data->named_data); return 0; } -static void event_hist_trigger_named_free(struct event_trigger_ops *ops, - struct event_trigger_data *data) +static void event_hist_trigger_named_free(struct event_trigger_data *data) { if (WARN_ON_ONCE(data->ref <= 0)) return; - event_hist_trigger_free(ops, data->named_data); + event_hist_trigger_free(data->named_data); data->ref--; if (!data->ref) { @@ -5933,6 +5932,48 @@ static bool hist_trigger_match(struct event_trigger_data *data, return true; } +static bool existing_hist_update_only(char *glob, + struct event_trigger_data *data, + struct trace_event_file *file) +{ + struct hist_trigger_data *hist_data = data->private_data; + struct event_trigger_data *test, *named_data = NULL; + bool updated = false; + + if (!hist_data->attrs->pause && !hist_data->attrs->cont && + !hist_data->attrs->clear) + goto out; + + if (hist_data->attrs->name) { + named_data = find_named_trigger(hist_data->attrs->name); + if (named_data) { + if (!hist_trigger_match(data, named_data, named_data, + true)) + goto out; + } + } + + if (hist_data->attrs->name && !named_data) + goto out; + + list_for_each_entry(test, &file->triggers, list) { + if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { + if (!hist_trigger_match(data, test, named_data, false)) + continue; + if (hist_data->attrs->pause) + test->paused = true; + else if (hist_data->attrs->cont) + test->paused = false; + else if (hist_data->attrs->clear) + hist_clear(test); + updated = true; + goto out; + } + } + out: + return updated; +} + static int hist_register_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file) @@ -5961,19 +6002,11 @@ static int hist_register_trigger(char *glob, list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { - if (!hist_trigger_match(data, test, named_data, false)) - continue; - if (hist_data->attrs->pause) - test->paused = true; - else if (hist_data->attrs->cont) - test->paused = false; - else if (hist_data->attrs->clear) - hist_clear(test); - else { + if (hist_trigger_match(data, test, named_data, false)) { hist_err(tr, HIST_ERR_TRIGGER_EEXIST, 0); ret = -EEXIST; + goto out; } - goto out; } } new: @@ -5993,7 +6026,7 @@ static int hist_register_trigger(char *glob, } if (data->ops->init) { - ret = data->ops->init(data->ops, data); + ret = data->ops->init(data); if (ret < 0) goto out; } @@ -6012,8 +6045,6 @@ static int hist_register_trigger(char *glob, if (named_data) destroy_hist_data(hist_data); - - ret++; out: return ret; } @@ -6089,20 +6120,19 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_data *data, struct trace_event_file *file) { + struct event_trigger_data *test = NULL, *iter, *named_data = NULL; struct hist_trigger_data *hist_data = data->private_data; - struct event_trigger_data *test, *named_data = NULL; - bool unregistered = false; lockdep_assert_held(&event_mutex); if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry(test, &file->triggers, list) { - if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { - if (!hist_trigger_match(data, test, named_data, false)) + list_for_each_entry(iter, &file->triggers, list) { + if (iter->cmd_ops->trigger_type == ETT_EVENT_HIST) { + if (!hist_trigger_match(data, iter, named_data, false)) continue; - unregistered = true; + test = iter; list_del_rcu(&test->list); trace_event_trigger_enable_disable(file, 0); update_cond_flag(file); @@ -6110,11 +6140,11 @@ static void hist_unregister_trigger(char *glob, } } - if (unregistered && test->ops->free) - test->ops->free(test->ops, test); + if (test && test->ops->free) + test->ops->free(test); if (hist_data->enable_timestamps) { - if (!hist_data->remove || unregistered) + if (!hist_data->remove || test) tracing_set_filter_buffering(file->tr, false); } } @@ -6164,57 +6194,57 @@ static void hist_unreg_all(struct trace_event_file *file) if (hist_data->enable_timestamps) tracing_set_filter_buffering(file->tr, false); if (test->ops->free) - test->ops->free(test->ops, test); + test->ops->free(test); } } } static int event_hist_trigger_parse(struct event_command *cmd_ops, struct trace_event_file *file, - char *glob, char *cmd, char *param) + char *glob, char *cmd, + char *param_and_filter) { unsigned int hist_trigger_bits = TRACING_MAP_BITS_DEFAULT; struct event_trigger_data *trigger_data; struct hist_trigger_attrs *attrs; - struct event_trigger_ops *trigger_ops; struct hist_trigger_data *hist_data; + char *param, *filter, *p, *start; struct synth_event *se; const char *se_name; - bool remove = false; - char *trigger, *p, *start; + bool remove; int ret = 0; lockdep_assert_held(&event_mutex); - WARN_ON(!glob); + if (WARN_ON(!glob)) + return -EINVAL; - if (strlen(glob)) { + if (glob[0]) { hist_err_clear(); - last_cmd_set(file, param); + last_cmd_set(file, param_and_filter); } - if (!param) - return -EINVAL; + remove = event_trigger_check_remove(glob); - if (glob[0] == '!') - remove = true; + if (event_trigger_empty_param(param_and_filter)) + return -EINVAL; /* * separate the trigger from the filter (k:v [if filter]) * allowing for whitespace in the trigger */ - p = trigger = param; + p = param = param_and_filter; do { p = strstr(p, "if"); if (!p) break; - if (p == param) + if (p == param_and_filter) return -EINVAL; if (*(p - 1) != ' ' && *(p - 1) != '\t') { p++; continue; } - if (p >= param + strlen(param) - (sizeof("if") - 1) - 1) + if (p >= param_and_filter + strlen(param_and_filter) - (sizeof("if") - 1) - 1) return -EINVAL; if (*(p + sizeof("if") - 1) != ' ' && *(p + sizeof("if") - 1) != '\t') { p++; @@ -6224,24 +6254,24 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, } while (1); if (!p) - param = NULL; + filter = NULL; else { *(p - 1) = '\0'; - param = strstrip(p); - trigger = strstrip(trigger); + filter = strstrip(p); + param = strstrip(param); } /* * To simplify arithmetic expression parsing, replace occurrences of * '.sym-offset' modifier with '.symXoffset' */ - start = strstr(trigger, ".sym-offset"); + start = strstr(param, ".sym-offset"); while (start) { *(start + 4) = 'X'; start = strstr(start + 11, ".sym-offset"); } - attrs = parse_hist_trigger_attrs(file->tr, trigger); + attrs = parse_hist_trigger_attrs(file->tr, param); if (IS_ERR(attrs)) return PTR_ERR(attrs); @@ -6254,29 +6284,15 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, return PTR_ERR(hist_data); } - trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger); - - trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL); + trigger_data = event_trigger_alloc(cmd_ops, cmd, param, hist_data); if (!trigger_data) { ret = -ENOMEM; goto out_free; } - trigger_data->count = -1; - trigger_data->ops = trigger_ops; - trigger_data->cmd_ops = cmd_ops; - - INIT_LIST_HEAD(&trigger_data->list); - RCU_INIT_POINTER(trigger_data->filter, NULL); - - trigger_data->private_data = hist_data; - - /* if param is non-empty, it's supposed to be a filter */ - if (param && cmd_ops->set_filter) { - ret = cmd_ops->set_filter(param, trigger_data, file); - if (ret < 0) - goto out_free; - } + ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data); + if (ret < 0) + goto out_free; if (remove) { if (!have_hist_trigger_match(trigger_data, file)) @@ -6287,7 +6303,7 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, goto out_free; } - cmd_ops->unreg(glob+1, trigger_data, file); + event_trigger_unregister(cmd_ops, file, glob+1, trigger_data); se_name = trace_event_name(file->event_call); se = find_synth_event(se_name); if (se) @@ -6296,17 +6312,11 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, goto out_free; } - ret = cmd_ops->reg(glob, trigger_data, file); - /* - * The above returns on success the # of triggers registered, - * but if it didn't register any it returns zero. Consider no - * triggers registered a failure too. - */ - if (!ret) { - if (!(attrs->pause || attrs->cont || attrs->clear)) - ret = -ENOENT; + if (existing_hist_update_only(glob, trigger_data, file)) goto out_free; - } else if (ret < 0) + + ret = event_trigger_register(cmd_ops, file, glob, trigger_data); + if (ret < 0) goto out_free; if (get_named_trigger_data(trigger_data)) @@ -6331,18 +6341,15 @@ enable: se = find_synth_event(se_name); if (se) se->ref++; - /* Just return zero, not the number of registered triggers */ - ret = 0; out: if (ret == 0) hist_err_clear(); return ret; out_unreg: - cmd_ops->unreg(glob+1, trigger_data, file); + event_trigger_unregister(cmd_ops, file, glob+1, trigger_data); out_free: - if (cmd_ops->set_filter) - cmd_ops->set_filter(NULL, trigger_data, NULL); + event_trigger_reset_filter(cmd_ops, trigger_data); remove_hist_vars(hist_data); @@ -6463,7 +6470,7 @@ static void hist_enable_unreg_all(struct trace_event_file *file) update_cond_flag(file); trace_event_trigger_enable_disable(file, 0); if (test->ops->free) - test->ops->free(test->ops, test); + test->ops->free(test); } } } diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 7eb9d04f1c2e..cb866c3141af 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -188,7 +188,7 @@ static int trigger_show(struct seq_file *m, void *v) } data = list_entry(v, struct event_trigger_data, list); - data->ops->print(m, data->ops, data); + data->ops->print(m, data); return 0; } @@ -432,7 +432,6 @@ event_trigger_print(const char *name, struct seq_file *m, /** * event_trigger_init - Generic event_trigger_ops @init implementation - * @ops: The trigger ops associated with the trigger * @data: Trigger-specific data * * Common implementation of event trigger initialization. @@ -442,8 +441,7 @@ event_trigger_print(const char *name, struct seq_file *m, * * Return: 0 on success, errno otherwise */ -int event_trigger_init(struct event_trigger_ops *ops, - struct event_trigger_data *data) +int event_trigger_init(struct event_trigger_data *data) { data->ref++; return 0; @@ -451,7 +449,6 @@ int event_trigger_init(struct event_trigger_ops *ops, /** * event_trigger_free - Generic event_trigger_ops @free implementation - * @ops: The trigger ops associated with the trigger * @data: Trigger-specific data * * Common implementation of event trigger de-initialization. @@ -460,8 +457,7 @@ int event_trigger_init(struct event_trigger_ops *ops, * implementations. */ static void -event_trigger_free(struct event_trigger_ops *ops, - struct event_trigger_data *data) +event_trigger_free(struct event_trigger_data *data) { if (WARN_ON_ONCE(data->ref <= 0)) return; @@ -515,7 +511,7 @@ clear_event_triggers(struct trace_array *tr) trace_event_trigger_enable_disable(file, 0); list_del_rcu(&data->list); if (data->ops->free) - data->ops->free(data->ops, data); + data->ops->free(data); } } } @@ -581,19 +577,18 @@ static int register_trigger(char *glob, } if (data->ops->init) { - ret = data->ops->init(data->ops, data); + ret = data->ops->init(data); if (ret < 0) goto out; } list_add_rcu(&data->list, &file->triggers); - ret++; update_cond_flag(file); - if (trace_event_trigger_enable_disable(file, 1) < 0) { + ret = trace_event_trigger_enable_disable(file, 1); + if (ret < 0) { list_del_rcu(&data->list); update_cond_flag(file); - ret--; } out: return ret; @@ -614,14 +609,13 @@ static void unregister_trigger(char *glob, struct event_trigger_data *test, struct trace_event_file *file) { - struct event_trigger_data *data; - bool unregistered = false; + struct event_trigger_data *data = NULL, *iter; lockdep_assert_held(&event_mutex); - list_for_each_entry(data, &file->triggers, list) { - if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) { - unregistered = true; + list_for_each_entry(iter, &file->triggers, list) { + if (iter->cmd_ops->trigger_type == test->cmd_ops->trigger_type) { + data = iter; list_del_rcu(&data->list); trace_event_trigger_enable_disable(file, 0); update_cond_flag(file); @@ -629,8 +623,8 @@ static void unregister_trigger(char *glob, } } - if (unregistered && data->ops->free) - data->ops->free(data->ops, data); + if (data && data->ops->free) + data->ops->free(data); } /* @@ -744,15 +738,15 @@ bool event_trigger_empty_param(const char *param) /** * event_trigger_separate_filter - separate an event trigger from a filter - * @param: The param string containing trigger and possibly filter - * @trigger: outparam, will be filled with a pointer to the trigger + * @param_and_filter: String containing trigger and possibly filter + * @param: outparam, will be filled with a pointer to the trigger * @filter: outparam, will be filled with a pointer to the filter * @param_required: Specifies whether or not the param string is required * * Given a param string of the form '[trigger] [if filter]', this * function separates the filter from the trigger and returns the - * trigger in *trigger and the filter in *filter. Either the *trigger - * or the *filter may be set to NULL by this function - if not set to + * trigger in @param and the filter in @filter. Either the @param + * or the @filter may be set to NULL by this function - if not set to * NULL, they will contain strings corresponding to the trigger and * filter. * @@ -927,48 +921,37 @@ void event_trigger_reset_filter(struct event_command *cmd_ops, * @cmd_ops: The event_command operations for the trigger * @file: The event file for the trigger's event * @glob: The trigger command string, with optional remove(!) operator - * @cmd: The cmd string - * @param: The param string * @trigger_data: The trigger_data for the trigger - * @n_registered: optional outparam, the number of triggers registered * * Register an event trigger. The @cmd_ops are used to call the - * cmd_ops->reg() function which actually does the registration. The - * cmd_ops->reg() function returns the number of triggers registered, - * which is assigned to n_registered, if n_registered is non-NULL. + * cmd_ops->reg() function which actually does the registration. * * Return: 0 on success, errno otherwise */ int event_trigger_register(struct event_command *cmd_ops, struct trace_event_file *file, char *glob, - char *cmd, - char *param, - struct event_trigger_data *trigger_data, - int *n_registered) + struct event_trigger_data *trigger_data) { - int ret; - - if (n_registered) - *n_registered = 0; - - ret = cmd_ops->reg(glob, trigger_data, file); - /* - * The above returns on success the # of functions enabled, - * but if it didn't find any functions it returns zero. - * Consider no functions a failure too. - */ - if (!ret) { - cmd_ops->unreg(glob, trigger_data, file); - ret = -ENOENT; - } else if (ret > 0) { - if (n_registered) - *n_registered = ret; - /* Just return zero, not the number of enabled functions */ - ret = 0; - } + return cmd_ops->reg(glob, trigger_data, file); +} - return ret; +/** + * event_trigger_unregister - unregister an event trigger + * @cmd_ops: The event_command operations for the trigger + * @file: The event file for the trigger's event + * @glob: The trigger command string, with optional remove(!) operator + * @trigger_data: The trigger_data for the trigger + * + * Unregister an event trigger. The @cmd_ops are used to call the + * cmd_ops->unreg() function which actually does the unregistration. + */ +void event_trigger_unregister(struct event_command *cmd_ops, + struct trace_event_file *file, + char *glob, + struct event_trigger_data *trigger_data) +{ + cmd_ops->unreg(glob, trigger_data, file); } /* @@ -981,7 +964,7 @@ int event_trigger_register(struct event_command *cmd_ops, * @file: The trace_event_file associated with the event * @glob: The raw string used to register the trigger * @cmd: The cmd portion of the string used to register the trigger - * @param: The params portion of the string used to register the trigger + * @param_and_filter: The param and filter portion of the string used to register the trigger * * Common implementation for event command parsing and trigger * instantiation. @@ -994,94 +977,53 @@ int event_trigger_register(struct event_command *cmd_ops, static int event_trigger_parse(struct event_command *cmd_ops, struct trace_event_file *file, - char *glob, char *cmd, char *param) + char *glob, char *cmd, char *param_and_filter) { struct event_trigger_data *trigger_data; - struct event_trigger_ops *trigger_ops; - char *trigger = NULL; - char *number; + char *param, *filter; + bool remove; int ret; - /* separate the trigger from the filter (t:n [if filter]) */ - if (param && isdigit(param[0])) { - trigger = strsep(¶m, " \t"); - if (param) { - param = skip_spaces(param); - if (!*param) - param = NULL; - } - } + remove = event_trigger_check_remove(glob); - trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger); + ret = event_trigger_separate_filter(param_and_filter, ¶m, &filter, false); + if (ret) + return ret; ret = -ENOMEM; - trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL); + trigger_data = event_trigger_alloc(cmd_ops, cmd, param, file); if (!trigger_data) goto out; - trigger_data->count = -1; - trigger_data->ops = trigger_ops; - trigger_data->cmd_ops = cmd_ops; - trigger_data->private_data = file; - INIT_LIST_HEAD(&trigger_data->list); - INIT_LIST_HEAD(&trigger_data->named_list); - - if (glob[0] == '!') { - cmd_ops->unreg(glob+1, trigger_data, file); + if (remove) { + event_trigger_unregister(cmd_ops, file, glob+1, trigger_data); kfree(trigger_data); ret = 0; goto out; } - if (trigger) { - number = strsep(&trigger, ":"); - - ret = -EINVAL; - if (!strlen(number)) - goto out_free; - - /* - * We use the callback data field (which is a pointer) - * as our counter. - */ - ret = kstrtoul(number, 0, &trigger_data->count); - if (ret) - goto out_free; - } - - if (!param) /* if param is non-empty, it's supposed to be a filter */ - goto out_reg; - - if (!cmd_ops->set_filter) - goto out_reg; + ret = event_trigger_parse_num(param, trigger_data); + if (ret) + goto out_free; - ret = cmd_ops->set_filter(param, trigger_data, file); + ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data); if (ret < 0) goto out_free; - out_reg: /* Up the trigger_data count to make sure reg doesn't free it on failure */ - event_trigger_init(trigger_ops, trigger_data); - ret = cmd_ops->reg(glob, trigger_data, file); - /* - * The above returns on success the # of functions enabled, - * but if it didn't find any functions it returns zero. - * Consider no functions a failure too. - */ - if (!ret) { - cmd_ops->unreg(glob, trigger_data, file); - ret = -ENOENT; - } else if (ret > 0) - ret = 0; + event_trigger_init(trigger_data); + + ret = event_trigger_register(cmd_ops, file, glob, trigger_data); + if (ret) + goto out_free; /* Down the counter of trigger_data or free it if not used anymore */ - event_trigger_free(trigger_ops, trigger_data); + event_trigger_free(trigger_data); out: return ret; out_free: - if (cmd_ops->set_filter) - cmd_ops->set_filter(NULL, trigger_data, NULL); + event_trigger_reset_filter(cmd_ops, trigger_data); kfree(trigger_data); goto out; } @@ -1401,16 +1343,14 @@ traceoff_count_trigger(struct event_trigger_data *data, } static int -traceon_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, - struct event_trigger_data *data) +traceon_trigger_print(struct seq_file *m, struct event_trigger_data *data) { return event_trigger_print("traceon", m, (void *)data->count, data->filter_str); } static int -traceoff_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, - struct event_trigger_data *data) +traceoff_trigger_print(struct seq_file *m, struct event_trigger_data *data) { return event_trigger_print("traceoff", m, (void *)data->count, data->filter_str); @@ -1521,8 +1461,7 @@ register_snapshot_trigger(char *glob, } static int -snapshot_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, - struct event_trigger_data *data) +snapshot_trigger_print(struct seq_file *m, struct event_trigger_data *data) { return event_trigger_print("snapshot", m, (void *)data->count, data->filter_str); @@ -1617,8 +1556,7 @@ stacktrace_count_trigger(struct event_trigger_data *data, } static int -stacktrace_trigger_print(struct seq_file *m, struct event_trigger_ops *ops, - struct event_trigger_data *data) +stacktrace_trigger_print(struct seq_file *m, struct event_trigger_data *data) { return event_trigger_print("stacktrace", m, (void *)data->count, data->filter_str); @@ -1708,7 +1646,6 @@ event_enable_count_trigger(struct event_trigger_data *data, } int event_enable_trigger_print(struct seq_file *m, - struct event_trigger_ops *ops, struct event_trigger_data *data) { struct enable_trigger_data *enable_data = data->private_data; @@ -1733,8 +1670,7 @@ int event_enable_trigger_print(struct seq_file *m, return 0; } -void event_enable_trigger_free(struct event_trigger_ops *ops, - struct event_trigger_data *data) +void event_enable_trigger_free(struct event_trigger_data *data) { struct enable_trigger_data *enable_data = data->private_data; @@ -1781,39 +1717,33 @@ static struct event_trigger_ops event_disable_count_trigger_ops = { int event_enable_trigger_parse(struct event_command *cmd_ops, struct trace_event_file *file, - char *glob, char *cmd, char *param) + char *glob, char *cmd, char *param_and_filter) { struct trace_event_file *event_enable_file; struct enable_trigger_data *enable_data; struct event_trigger_data *trigger_data; - struct event_trigger_ops *trigger_ops; struct trace_array *tr = file->tr; + char *param, *filter; + bool enable, remove; const char *system; const char *event; bool hist = false; - char *trigger; - char *number; - bool enable; int ret; - if (!param) - return -EINVAL; + remove = event_trigger_check_remove(glob); - /* separate the trigger from the filter (s:e:n [if filter]) */ - trigger = strsep(¶m, " \t"); - if (!trigger) + if (event_trigger_empty_param(param_and_filter)) return -EINVAL; - if (param) { - param = skip_spaces(param); - if (!*param) - param = NULL; - } - system = strsep(&trigger, ":"); - if (!trigger) + ret = event_trigger_separate_filter(param_and_filter, ¶m, &filter, true); + if (ret) + return ret; + + system = strsep(¶m, ":"); + if (!param) return -EINVAL; - event = strsep(&trigger, ":"); + event = strsep(¶m, ":"); ret = -EINVAL; event_enable_file = find_event_file(tr, system, event); @@ -1829,32 +1759,24 @@ int event_enable_trigger_parse(struct event_command *cmd_ops, #else enable = strcmp(cmd, ENABLE_EVENT_STR) == 0; #endif - trigger_ops = cmd_ops->get_trigger_ops(cmd, trigger); - ret = -ENOMEM; - trigger_data = kzalloc(sizeof(*trigger_data), GFP_KERNEL); - if (!trigger_data) - goto out; enable_data = kzalloc(sizeof(*enable_data), GFP_KERNEL); - if (!enable_data) { - kfree(trigger_data); + if (!enable_data) goto out; - } - - trigger_data->count = -1; - trigger_data->ops = trigger_ops; - trigger_data->cmd_ops = cmd_ops; - INIT_LIST_HEAD(&trigger_data->list); - RCU_INIT_POINTER(trigger_data->filter, NULL); enable_data->hist = hist; enable_data->enable = enable; enable_data->file = event_enable_file; - trigger_data->private_data = enable_data; - if (glob[0] == '!') { - cmd_ops->unreg(glob+1, trigger_data, file); + trigger_data = event_trigger_alloc(cmd_ops, cmd, param, enable_data); + if (!trigger_data) { + kfree(enable_data); + goto out; + } + + if (remove) { + event_trigger_unregister(cmd_ops, file, glob+1, trigger_data); kfree(trigger_data); kfree(enable_data); ret = 0; @@ -1862,35 +1784,16 @@ int event_enable_trigger_parse(struct event_command *cmd_ops, } /* Up the trigger_data count to make sure nothing frees it on failure */ - event_trigger_init(trigger_ops, trigger_data); - - if (trigger) { - number = strsep(&trigger, ":"); - - ret = -EINVAL; - if (!strlen(number)) - goto out_free; - - /* - * We use the callback data field (which is a pointer) - * as our counter. - */ - ret = kstrtoul(number, 0, &trigger_data->count); - if (ret) - goto out_free; - } + event_trigger_init(trigger_data); - if (!param) /* if param is non-empty, it's supposed to be a filter */ - goto out_reg; - - if (!cmd_ops->set_filter) - goto out_reg; + ret = event_trigger_parse_num(param, trigger_data); + if (ret) + goto out_free; - ret = cmd_ops->set_filter(param, trigger_data, file); + ret = event_trigger_set_filter(cmd_ops, file, filter, trigger_data); if (ret < 0) goto out_free; - out_reg: /* Don't let event modules unload while probe registered */ ret = trace_event_try_get_ref(event_enable_file->event_call); if (!ret) { @@ -1901,32 +1804,23 @@ int event_enable_trigger_parse(struct event_command *cmd_ops, ret = trace_event_enable_disable(event_enable_file, 1, 1); if (ret < 0) goto out_put; - ret = cmd_ops->reg(glob, trigger_data, file); - /* - * The above returns on success the # of functions enabled, - * but if it didn't find any functions it returns zero. - * Consider no functions a failure too. - */ - if (!ret) { - ret = -ENOENT; - goto out_disable; - } else if (ret < 0) + + ret = event_trigger_register(cmd_ops, file, glob, trigger_data); + if (ret) goto out_disable; - /* Just return zero, not the number of enabled functions */ - ret = 0; - event_trigger_free(trigger_ops, trigger_data); + + event_trigger_free(trigger_data); out: return ret; - out_disable: trace_event_enable_disable(event_enable_file, 0, 1); out_put: trace_event_put_ref(event_enable_file->event_call); out_free: - if (cmd_ops->set_filter) - cmd_ops->set_filter(NULL, trigger_data, NULL); - event_trigger_free(trigger_ops, trigger_data); + event_trigger_reset_filter(cmd_ops, trigger_data); + event_trigger_free(trigger_data); kfree(enable_data); + goto out; } @@ -1953,19 +1847,18 @@ int event_enable_register_trigger(char *glob, } if (data->ops->init) { - ret = data->ops->init(data->ops, data); + ret = data->ops->init(data); if (ret < 0) goto out; } list_add_rcu(&data->list, &file->triggers); - ret++; update_cond_flag(file); - if (trace_event_trigger_enable_disable(file, 1) < 0) { + ret = trace_event_trigger_enable_disable(file, 1); + if (ret < 0) { list_del_rcu(&data->list); update_cond_flag(file); - ret--; } out: return ret; @@ -1976,19 +1869,18 @@ void event_enable_unregister_trigger(char *glob, struct trace_event_file *file) { struct enable_trigger_data *test_enable_data = test->private_data; + struct event_trigger_data *data = NULL, *iter; struct enable_trigger_data *enable_data; - struct event_trigger_data *data; - bool unregistered = false; lockdep_assert_held(&event_mutex); - list_for_each_entry(data, &file->triggers, list) { - enable_data = data->private_data; + list_for_each_entry(iter, &file->triggers, list) { + enable_data = iter->private_data; if (enable_data && - (data->cmd_ops->trigger_type == + (iter->cmd_ops->trigger_type == test->cmd_ops->trigger_type) && (enable_data->file == test_enable_data->file)) { - unregistered = true; + data = iter; list_del_rcu(&data->list); trace_event_trigger_enable_disable(file, 0); update_cond_flag(file); @@ -1996,8 +1888,8 @@ void event_enable_unregister_trigger(char *glob, } } - if (unregistered && data->ops->free) - data->ops->free(data->ops, data); + if (data && data->ops->free) + data->ops->free(data); } static struct event_trigger_ops * diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 47cebef78532..93507330462c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1907,25 +1907,18 @@ core_initcall(init_kprobe_trace_early); static __init int init_kprobe_trace(void) { int ret; - struct dentry *entry; ret = tracing_init_dentry(); if (ret) return 0; - entry = tracefs_create_file("kprobe_events", TRACE_MODE_WRITE, - NULL, NULL, &kprobe_events_ops); - /* Event list interface */ - if (!entry) - pr_warn("Could not create tracefs 'kprobe_events' entry\n"); + trace_create_file("kprobe_events", TRACE_MODE_WRITE, + NULL, NULL, &kprobe_events_ops); /* Profile interface */ - entry = tracefs_create_file("kprobe_profile", TRACE_MODE_READ, - NULL, NULL, &kprobe_profile_ops); - - if (!entry) - pr_warn("Could not create tracefs 'kprobe_profile' entry\n"); + trace_create_file("kprobe_profile", TRACE_MODE_READ, + NULL, NULL, &kprobe_profile_ops); setup_boot_kprobe_events(); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index afb92e2f0aea..313439920a8c 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1578,11 +1578,27 @@ static enum hrtimer_restart timerlat_irq(struct hrtimer *timer) trace_timerlat_sample(&s); - notify_new_max_latency(diff); + if (osnoise_data.stop_tracing) { + if (time_to_us(diff) >= osnoise_data.stop_tracing) { + + /* + * At this point, if stop_tracing is set and <= print_stack, + * print_stack is set and would be printed in the thread handler. + * + * Thus, print the stack trace as it is helpful to define the + * root cause of an IRQ latency. + */ + if (osnoise_data.stop_tracing <= osnoise_data.print_stack) { + timerlat_save_stack(0); + timerlat_dump_stack(time_to_us(diff)); + } - if (osnoise_data.stop_tracing) - if (time_to_us(diff) >= osnoise_data.stop_tracing) osnoise_stop_tracing(); + notify_new_max_latency(diff); + + return HRTIMER_NORESTART; + } + } wake_up_process(tlat->kthread); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 8aa493d25c73..67f47ea27921 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -692,7 +692,7 @@ static LIST_HEAD(ftrace_event_list); static int trace_search_list(struct list_head **list) { - struct trace_event *e; + struct trace_event *e = NULL, *iter; int next = __TRACE_LAST_TYPE; if (list_empty(&ftrace_event_list)) { @@ -704,9 +704,11 @@ static int trace_search_list(struct list_head **list) * We used up all possible max events, * lets see if somebody freed one. */ - list_for_each_entry(e, &ftrace_event_list, list) { - if (e->type != next) + list_for_each_entry(iter, &ftrace_event_list, list) { + if (iter->type != next) { + e = iter; break; + } next++; } @@ -714,7 +716,10 @@ static int trace_search_list(struct list_head **list) if (next > TRACE_EVENT_TYPE_MAX) return 0; - *list = &e->list; + if (e) + *list = &e->list; + else + *list = &ftrace_event_list; return next; } @@ -778,9 +783,8 @@ int register_trace_event(struct trace_event *event) list_add_tail(&event->list, list); - } else if (event->type > __TRACE_LAST_TYPE) { - printk(KERN_WARNING "Need to add type to trace.h\n"); - WARN_ON(1); + } else if (WARN(event->type > __TRACE_LAST_TYPE, + "Need to add type to trace.h")) { goto out; } else { /* Is this event already used */ @@ -1571,13 +1575,8 @@ __init static int init_events(void) for (i = 0; events[i]; i++) { event = events[i]; - ret = register_trace_event(event); - if (!ret) { - printk(KERN_WARNING "event %d failed to register\n", - event->type); - WARN_ON_ONCE(1); - } + WARN_ONCE(!ret, "event %d failed to register", event->type); } return 0; diff --git a/kernel/trace/trace_recursion_record.c b/kernel/trace/trace_recursion_record.c index 4d4b78c8ca25..a520b11afb0d 100644 --- a/kernel/trace/trace_recursion_record.c +++ b/kernel/trace/trace_recursion_record.c @@ -224,12 +224,9 @@ static const struct file_operations recursed_functions_fops = { __init static int create_recursed_functions(void) { - struct dentry *dentry; - dentry = trace_create_file("recursed_functions", TRACE_MODE_WRITE, - NULL, NULL, &recursed_functions_fops); - if (!dentry) - pr_warn("WARNING: Failed to create recursed_functions\n"); + trace_create_file("recursed_functions", TRACE_MODE_WRITE, + NULL, NULL, &recursed_functions_fops); return 0; } diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index abcadbe933bb..a2d301f58ced 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -895,6 +895,9 @@ trace_selftest_startup_function_graph(struct tracer *trace, ret = -1; goto out; } + + /* Enable tracing on all functions again */ + ftrace_set_global_filter(NULL, 0, 1); #endif /* Don't test dynamic tracing, the function tracer already did */ diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index f755bde42fd0..b69e207012c9 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -154,7 +154,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags, goto end; /* parameter types */ - if (tr->trace_flags & TRACE_ITER_VERBOSE) + if (tr && tr->trace_flags & TRACE_ITER_VERBOSE) trace_seq_printf(s, "%s ", entry->types[i]); /* parameter values */ @@ -296,9 +296,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) struct trace_event_file *trace_file; struct syscall_trace_enter *entry; struct syscall_metadata *sys_data; - struct ring_buffer_event *event; - struct trace_buffer *buffer; - unsigned int trace_ctx; + struct trace_event_buffer fbuffer; unsigned long args[6]; int syscall_nr; int size; @@ -321,20 +319,16 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; - trace_ctx = tracing_gen_ctx(); - - event = trace_event_buffer_lock_reserve(&buffer, trace_file, - sys_data->enter_event->event.type, size, trace_ctx); - if (!event) + entry = trace_event_buffer_reserve(&fbuffer, trace_file, size); + if (!entry) return; - entry = ring_buffer_event_data(event); + entry = ring_buffer_event_data(fbuffer.event); entry->nr = syscall_nr; syscall_get_arguments(current, regs, args); memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args); - event_trigger_unlock_commit(trace_file, buffer, event, entry, - trace_ctx); + trace_event_buffer_commit(&fbuffer); } static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) @@ -343,9 +337,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) struct trace_event_file *trace_file; struct syscall_trace_exit *entry; struct syscall_metadata *sys_data; - struct ring_buffer_event *event; - struct trace_buffer *buffer; - unsigned int trace_ctx; + struct trace_event_buffer fbuffer; int syscall_nr; syscall_nr = trace_get_syscall_nr(current, regs); @@ -364,20 +356,15 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) if (!sys_data) return; - trace_ctx = tracing_gen_ctx(); - - event = trace_event_buffer_lock_reserve(&buffer, trace_file, - sys_data->exit_event->event.type, sizeof(*entry), - trace_ctx); - if (!event) + entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry)); + if (!entry) return; - entry = ring_buffer_event_data(event); + entry = ring_buffer_event_data(fbuffer.event); entry->nr = syscall_nr; entry->ret = syscall_get_return_value(current, regs); - event_trigger_unlock_commit(trace_file, buffer, event, entry, - trace_ctx); + trace_event_buffer_commit(&fbuffer); } static int reg_event_syscall_enter(struct trace_event_file *file, diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 9628b5571846..9901708ce6b8 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -1045,7 +1045,8 @@ static void sort_secondary(struct tracing_map *map, /** * tracing_map_sort_entries - Sort the current set of tracing_map_elts in a map * @map: The tracing_map - * @sort_key: The sort key to use for sorting + * @sort_keys: The sort key to use for sorting + * @n_sort_keys: hitcount, always have at least one * @sort_entries: outval: pointer to allocated and sorted array of entries * * tracing_map_sort_entries() sorts the current set of entries in the diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 1d261fbe367b..4252f0645b9e 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -23,15 +23,20 @@ void bacct_add_tsk(struct user_namespace *user_ns, { const struct cred *tcred; u64 utime, stime, utimescaled, stimescaled; - u64 delta; + u64 now_ns, delta; time64_t btime; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); /* calculate task elapsed time in nsec */ - delta = ktime_get_ns() - tsk->start_time; + now_ns = ktime_get_ns(); + /* store whole group time first */ + delta = now_ns - tsk->group_leader->start_time; /* Convert to micro seconds */ do_div(delta, NSEC_PER_USEC); + stats->ac_tgetime = delta; + delta = now_ns - tsk->start_time; + do_div(delta, NSEC_PER_USEC); stats->ac_etime = delta; /* Convert to seconds for btime (note y2106 limit) */ btime = ktime_get_real_seconds() - div_u64(delta, USEC_PER_SEC); @@ -51,6 +56,7 @@ void bacct_add_tsk(struct user_namespace *user_ns, stats->ac_nice = task_nice(tsk); stats->ac_sched = tsk->policy; stats->ac_pid = task_pid_nr_ns(tsk, pid_ns); + stats->ac_tgid = task_tgid_nr_ns(tsk, pid_ns); rcu_read_lock(); tcred = __task_cred(tsk); stats->ac_uid = from_kuid_munged(user_ns, tcred->uid); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 40024e03d422..20a7a55e62b6 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -57,7 +57,7 @@ int __read_mostly sysctl_hardlockup_all_cpu_backtrace; * Should we panic when a soft-lockup or hard-lockup occurs: */ unsigned int __read_mostly hardlockup_panic = - CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; + IS_ENABLED(CONFIG_BOOTPARAM_HARDLOCKUP_PANIC); /* * We may not want to enable hard lockup detection by default in all cases, * for example when running the kernel as a guest on a hypervisor. In these @@ -168,7 +168,7 @@ static struct cpumask watchdog_allowed_mask __read_mostly; /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = - CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; + IS_ENABLED(CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC); static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; |