diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/async.c | 1 | ||||
-rw-r--r-- | kernel/audit.c | 19 | ||||
-rw-r--r-- | kernel/audit.h | 2 | ||||
-rw-r--r-- | kernel/auditsc.c | 6 | ||||
-rw-r--r-- | kernel/cred.c | 4 | ||||
-rw-r--r-- | kernel/debug/kdb/kdb_main.c | 4 | ||||
-rw-r--r-- | kernel/delayacct.c | 2 | ||||
-rw-r--r-- | kernel/events/uprobes.c | 13 | ||||
-rw-r--r-- | kernel/fork.c | 27 | ||||
-rw-r--r-- | kernel/futex.c | 65 | ||||
-rw-r--r-- | kernel/gcov/base.c | 7 | ||||
-rw-r--r-- | kernel/livepatch/core.c | 176 | ||||
-rw-r--r-- | kernel/memremap.c | 219 | ||||
-rw-r--r-- | kernel/module.c | 349 | ||||
-rw-r--r-- | kernel/panic.c | 3 | ||||
-rw-r--r-- | kernel/pid.c | 2 | ||||
-rw-r--r-- | kernel/printk/printk.c | 67 | ||||
-rw-r--r-- | kernel/resource.c | 11 | ||||
-rw-r--r-- | kernel/sched/idle.c | 1 | ||||
-rw-r--r-- | kernel/stop_machine.c | 4 | ||||
-rw-r--r-- | kernel/sysctl.c | 22 |
21 files changed, 593 insertions, 411 deletions
diff --git a/kernel/async.c b/kernel/async.c index 4c3773c0bf63..d2edd6efec56 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -326,3 +326,4 @@ bool current_is_async(void) return worker && worker->current_func == async_run_entry_fn; } +EXPORT_SYMBOL_GPL(current_is_async); diff --git a/kernel/audit.c b/kernel/audit.c index 5ffcbd354a52..3a3e5deeda8d 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -110,7 +110,6 @@ static u32 audit_backlog_limit = 64; #define AUDIT_BACKLOG_WAIT_TIME (60 * HZ) static u32 audit_backlog_wait_time_master = AUDIT_BACKLOG_WAIT_TIME; static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME; -static u32 audit_backlog_wait_overflow = 0; /* The identity of the user shutting down the audit system. */ kuid_t audit_sig_uid = INVALID_UID; @@ -509,8 +508,7 @@ static void flush_hold_queue(void) * if auditd just disappeared but we * dequeued an skb we need to drop ref */ - if (skb) - consume_skb(skb); + consume_skb(skb); } static int kauditd_thread(void *dummy) @@ -524,7 +522,8 @@ static int kauditd_thread(void *dummy) skb = skb_dequeue(&audit_skb_queue); if (skb) { - if (skb_queue_len(&audit_skb_queue) <= audit_backlog_limit) + if (!audit_backlog_limit || + (skb_queue_len(&audit_skb_queue) <= audit_backlog_limit)) wake_up(&audit_backlog_wait); if (audit_pid) kauditd_send_skb(skb); @@ -1232,9 +1231,7 @@ static void audit_buffer_free(struct audit_buffer *ab) if (!ab) return; - if (ab->skb) - kfree_skb(ab->skb); - + kfree_skb(ab->skb); spin_lock_irqsave(&audit_freelist_lock, flags); if (audit_freelist_count > AUDIT_MAXFREE) kfree(ab); @@ -1372,7 +1369,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, return NULL; if (gfp_mask & __GFP_DIRECT_RECLAIM) { - if (audit_pid && audit_pid == current->pid) + if (audit_pid && audit_pid == current->tgid) gfp_mask &= ~__GFP_DIRECT_RECLAIM; else reserve = 0; @@ -1395,12 +1392,12 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, skb_queue_len(&audit_skb_queue), audit_backlog_limit); audit_log_lost("backlog limit exceeded"); - audit_backlog_wait_time = audit_backlog_wait_overflow; + audit_backlog_wait_time = 0; wake_up(&audit_backlog_wait); return NULL; } - if (!reserve) + if (!reserve && !audit_backlog_wait_time) audit_backlog_wait_time = audit_backlog_wait_time_master; ab = audit_buffer_alloc(ctx, gfp_mask, type); @@ -1722,7 +1719,7 @@ static inline int audit_copy_fcaps(struct audit_names *name, /* Copy inode data into an audit_names. */ void audit_copy_inode(struct audit_names *name, const struct dentry *dentry, - const struct inode *inode) + struct inode *inode) { name->ino = inode->i_ino; name->dev = inode->i_sb->s_dev; diff --git a/kernel/audit.h b/kernel/audit.h index de6cbb7cf547..cbbe6bb6496e 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -207,7 +207,7 @@ extern u32 audit_ever_enabled; extern void audit_copy_inode(struct audit_names *name, const struct dentry *dentry, - const struct inode *inode); + struct inode *inode); extern void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap); extern void audit_log_name(struct audit_context *context, diff --git a/kernel/auditsc.c b/kernel/auditsc.c index b86cc04959de..195ffaee50b9 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1754,7 +1754,7 @@ void __audit_inode(struct filename *name, const struct dentry *dentry, unsigned int flags) { struct audit_context *context = current->audit_context; - const struct inode *inode = d_backing_inode(dentry); + struct inode *inode = d_backing_inode(dentry); struct audit_names *n; bool parent = flags & AUDIT_INODE_PARENT; @@ -1848,12 +1848,12 @@ void __audit_file(const struct file *file) * must be hooked prior, in order to capture the target inode during * unsuccessful attempts. */ -void __audit_inode_child(const struct inode *parent, +void __audit_inode_child(struct inode *parent, const struct dentry *dentry, const unsigned char type) { struct audit_context *context = current->audit_context; - const struct inode *inode = d_backing_inode(dentry); + struct inode *inode = d_backing_inode(dentry); const char *dname = dentry->d_name.name; struct audit_names *n, *found_parent = NULL, *found_child = NULL; diff --git a/kernel/cred.c b/kernel/cred.c index 71179a09c1d6..0c0cd8a62285 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -569,8 +569,8 @@ EXPORT_SYMBOL(revert_creds); void __init cred_init(void) { /* allocate a slab in which we can store credentials */ - cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), - 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); } /** diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 4121345498e0..2a20c0dfdafc 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2021,7 +2021,7 @@ static int kdb_lsmod(int argc, const char **argv) continue; kdb_printf("%-20s%8u 0x%p ", mod->name, - mod->core_size, (void *)mod); + mod->core_layout.size, (void *)mod); #ifdef CONFIG_MODULE_UNLOAD kdb_printf("%4d ", module_refcount(mod)); #endif @@ -2031,7 +2031,7 @@ static int kdb_lsmod(int argc, const char **argv) kdb_printf(" (Loading)"); else kdb_printf(" (Live)"); - kdb_printf(" 0x%p", mod->module_core); + kdb_printf(" 0x%p", mod->core_layout.base); #ifdef CONFIG_MODULE_UNLOAD { diff --git a/kernel/delayacct.c b/kernel/delayacct.c index ef90b04d783f..435c14a45118 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -34,7 +34,7 @@ __setup("nodelayacct", delayacct_setup_disable); void delayacct_init(void) { - delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC); + delayacct_cache = KMEM_CACHE(task_delay_info, SLAB_PANIC|SLAB_ACCOUNT); delayacct_tsk_init(&init_task); } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 7dad84913abf..0167679182c0 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -161,7 +161,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, const unsigned long mmun_end = addr + PAGE_SIZE; struct mem_cgroup *memcg; - err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg); + err = mem_cgroup_try_charge(kpage, vma->vm_mm, GFP_KERNEL, &memcg, + false); if (err) return err; @@ -175,12 +176,12 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, goto unlock; get_page(kpage); - page_add_new_anon_rmap(kpage, vma, addr); - mem_cgroup_commit_charge(kpage, memcg, false); + page_add_new_anon_rmap(kpage, vma, addr, false); + mem_cgroup_commit_charge(kpage, memcg, false, false); lru_cache_add_active_or_unevictable(kpage, vma); if (!PageAnon(page)) { - dec_mm_counter(mm, MM_FILEPAGES); + dec_mm_counter(mm, mm_counter_file(page)); inc_mm_counter(mm, MM_ANONPAGES); } @@ -188,7 +189,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, ptep_clear_flush_notify(vma, addr, ptep); set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot)); - page_remove_rmap(page); + page_remove_rmap(page, false); if (!page_mapped(page)) try_to_free_swap(page); pte_unmap_unlock(ptep, ptl); @@ -199,7 +200,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, err = 0; unlock: - mem_cgroup_cancel_charge(kpage, memcg); + mem_cgroup_cancel_charge(kpage, memcg, false); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); unlock_page(page); return err; diff --git a/kernel/fork.c b/kernel/fork.c index 6774e6b2e96d..2e391c754ae7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -300,9 +300,9 @@ void __init fork_init(void) #define ARCH_MIN_TASKALIGN L1_CACHE_BYTES #endif /* create a slab on which task_structs can be allocated */ - task_struct_cachep = - kmem_cache_create("task_struct", arch_task_struct_size, - ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL); + task_struct_cachep = kmem_cache_create("task_struct", + arch_task_struct_size, ARCH_MIN_TASKALIGN, + SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, NULL); #endif /* do the arch specific task caches init */ @@ -414,7 +414,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm)); mm->total_vm = oldmm->total_vm; - mm->shared_vm = oldmm->shared_vm; + mm->data_vm = oldmm->data_vm; mm->exec_vm = oldmm->exec_vm; mm->stack_vm = oldmm->stack_vm; @@ -433,8 +433,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { - vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file, - -vma_pages(mpnt)); + vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt)); continue; } charge = 0; @@ -1848,16 +1847,19 @@ void __init proc_caches_init(void) sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_DESTROY_BY_RCU| - SLAB_NOTRACK, sighand_ctor); + SLAB_NOTRACK|SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); /* * FIXME! The "sizeof(struct mm_struct)" currently includes the * whole struct cpumask for the OFFSTACK case. We could change @@ -1867,8 +1869,9 @@ void __init proc_caches_init(void) */ mm_cachep = kmem_cache_create("mm_struct", sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL); - vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC); + SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, + NULL); + vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); mmap_init(); nsproxy_cache_init(); } diff --git a/kernel/futex.c b/kernel/futex.c index 8a310e240cda..c6f514573b28 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -469,7 +469,8 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) { unsigned long address = (unsigned long)uaddr; struct mm_struct *mm = current->mm; - struct page *page, *page_head; + struct page *page; + struct address_space *mapping; int err, ro = 0; /* @@ -519,46 +520,9 @@ again: else err = 0; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - page_head = page; - if (unlikely(PageTail(page))) { - put_page(page); - /* serialize against __split_huge_page_splitting() */ - local_irq_disable(); - if (likely(__get_user_pages_fast(address, 1, !ro, &page) == 1)) { - page_head = compound_head(page); - /* - * page_head is valid pointer but we must pin - * it before taking the PG_lock and/or - * PG_compound_lock. The moment we re-enable - * irqs __split_huge_page_splitting() can - * return and the head page can be freed from - * under us. We can't take the PG_lock and/or - * PG_compound_lock on a page that could be - * freed from under us. - */ - if (page != page_head) { - get_page(page_head); - put_page(page); - } - local_irq_enable(); - } else { - local_irq_enable(); - goto again; - } - } -#else - page_head = compound_head(page); - if (page != page_head) { - get_page(page_head); - put_page(page); - } -#endif - - lock_page(page_head); - + lock_page(page); /* - * If page_head->mapping is NULL, then it cannot be a PageAnon + * If page->mapping is NULL, then it cannot be a PageAnon * page; but it might be the ZERO_PAGE or in the gate area or * in a special mapping (all cases which we are happy to fail); * or it may have been a good file page when get_user_pages_fast @@ -570,12 +534,13 @@ again: * * The case we do have to guard against is when memory pressure made * shmem_writepage move it from filecache to swapcache beneath us: - * an unlikely race, but we do need to retry for page_head->mapping. + * an unlikely race, but we do need to retry for page->mapping. */ - if (!page_head->mapping) { - int shmem_swizzled = PageSwapCache(page_head); - unlock_page(page_head); - put_page(page_head); + mapping = compound_head(page)->mapping; + if (!mapping) { + int shmem_swizzled = PageSwapCache(page); + unlock_page(page); + put_page(page); if (shmem_swizzled) goto again; return -EFAULT; @@ -588,7 +553,7 @@ again: * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. */ - if (PageAnon(page_head)) { + if (PageAnon(page)) { /* * A RO anonymous page will never change and thus doesn't make * sense for futex operations. @@ -603,15 +568,15 @@ again: key->private.address = address; } else { key->both.offset |= FUT_OFF_INODE; /* inode-based key */ - key->shared.inode = page_head->mapping->host; + key->shared.inode = mapping->host; key->shared.pgoff = basepage_index(page); } get_futex_key_refs(key); /* implies MB (B) */ out: - unlock_page(page_head); - put_page(page_head); + unlock_page(page); + put_page(page); return err; } @@ -639,7 +604,7 @@ static int fault_in_user_writeable(u32 __user *uaddr) down_read(&mm->mmap_sem); ret = fixup_user_fault(current, mm, (unsigned long)uaddr, - FAULT_FLAG_WRITE); + FAULT_FLAG_WRITE, NULL); up_read(&mm->mmap_sem); return ret < 0 ? ret : 0; diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c index 7080ae1eb6c1..2f9df37940a0 100644 --- a/kernel/gcov/base.c +++ b/kernel/gcov/base.c @@ -123,11 +123,6 @@ void gcov_enable_events(void) } #ifdef CONFIG_MODULES -static inline int within(void *addr, void *start, unsigned long size) -{ - return ((addr >= start) && (addr < start + size)); -} - /* Update list and generate events when modules are unloaded. */ static int gcov_module_notifier(struct notifier_block *nb, unsigned long event, void *data) @@ -142,7 +137,7 @@ static int gcov_module_notifier(struct notifier_block *nb, unsigned long event, /* Remove entries located in module from linked list. */ while ((info = gcov_info_next(info))) { - if (within(info, mod->module_core, mod->core_size)) { + if (within_module((unsigned long)info, mod)) { gcov_info_unlink(prev, info); if (gcov_events_enabled) gcov_event(GCOV_REMOVE, info); diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index db545cbcdb89..bc2c85c064c1 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -28,6 +28,7 @@ #include <linux/list.h> #include <linux/kallsyms.h> #include <linux/livepatch.h> +#include <asm/cacheflush.h> /** * struct klp_ops - structure for tracking registered ftrace ops structs @@ -135,13 +136,8 @@ struct klp_find_arg { const char *objname; const char *name; unsigned long addr; - /* - * If count == 0, the symbol was not found. If count == 1, a unique - * match was found and addr is set. If count > 1, there is - * unresolvable ambiguity among "count" number of symbols with the same - * name in the same object. - */ unsigned long count; + unsigned long pos; }; static int klp_find_callback(void *data, const char *name, @@ -158,37 +154,48 @@ static int klp_find_callback(void *data, const char *name, if (args->objname && strcmp(args->objname, mod->name)) return 0; - /* - * args->addr might be overwritten if another match is found - * but klp_find_object_symbol() handles this and only returns the - * addr if count == 1. - */ args->addr = addr; args->count++; + /* + * Finish the search when the symbol is found for the desired position + * or the position is not defined for a non-unique symbol. + */ + if ((args->pos && (args->count == args->pos)) || + (!args->pos && (args->count > 1))) + return 1; + return 0; } static int klp_find_object_symbol(const char *objname, const char *name, - unsigned long *addr) + unsigned long sympos, unsigned long *addr) { struct klp_find_arg args = { .objname = objname, .name = name, .addr = 0, - .count = 0 + .count = 0, + .pos = sympos, }; mutex_lock(&module_mutex); kallsyms_on_each_symbol(klp_find_callback, &args); mutex_unlock(&module_mutex); - if (args.count == 0) + /* + * Ensure an address was found. If sympos is 0, ensure symbol is unique; + * otherwise ensure the symbol position count matches sympos. + */ + if (args.addr == 0) pr_err("symbol '%s' not found in symbol table\n", name); - else if (args.count > 1) + else if (args.count > 1 && sympos == 0) { pr_err("unresolvable ambiguity (%lu matches) on symbol '%s' in object '%s'\n", args.count, name, objname); - else { + } else if (sympos != args.count && sympos > 0) { + pr_err("symbol position %lu for symbol '%s' in object '%s' not found\n", + sympos, name, objname ? objname : "vmlinux"); + } else { *addr = args.addr; return 0; } @@ -197,66 +204,6 @@ static int klp_find_object_symbol(const char *objname, const char *name, return -EINVAL; } -struct klp_verify_args { - const char *name; - const unsigned long addr; -}; - -static int klp_verify_callback(void *data, const char *name, - struct module *mod, unsigned long addr) -{ - struct klp_verify_args *args = data; - - if (!mod && - !strcmp(args->name, name) && - args->addr == addr) - return 1; - - return 0; -} - -static int klp_verify_vmlinux_symbol(const char *name, unsigned long addr) -{ - struct klp_verify_args args = { - .name = name, - .addr = addr, - }; - int ret; - - mutex_lock(&module_mutex); - ret = kallsyms_on_each_symbol(klp_verify_callback, &args); - mutex_unlock(&module_mutex); - - if (!ret) { - pr_err("symbol '%s' not found at specified address 0x%016lx, kernel mismatch?\n", - name, addr); - return -EINVAL; - } - - return 0; -} - -static int klp_find_verify_func_addr(struct klp_object *obj, - struct klp_func *func) -{ - int ret; - -#if defined(CONFIG_RANDOMIZE_BASE) - /* If KASLR has been enabled, adjust old_addr accordingly */ - if (kaslr_enabled() && func->old_addr) - func->old_addr += kaslr_offset(); -#endif - - if (!func->old_addr || klp_is_module(obj)) - ret = klp_find_object_symbol(obj->name, func->old_name, - &func->old_addr); - else - ret = klp_verify_vmlinux_symbol(func->old_name, - func->old_addr); - - return ret; -} - /* * external symbols are located outside the parent object (where the parent * object is either vmlinux or the kmod being patched). @@ -276,14 +223,18 @@ static int klp_find_external_symbol(struct module *pmod, const char *name, } preempt_enable(); - /* otherwise check if it's in another .o within the patch module */ - return klp_find_object_symbol(pmod->name, name, addr); + /* + * Check if it's in another .o within the patch module. This also + * checks that the external symbol is unique. + */ + return klp_find_object_symbol(pmod->name, name, 0, addr); } static int klp_write_object_relocations(struct module *pmod, struct klp_object *obj) { - int ret; + int ret = 0; + unsigned long val; struct klp_reloc *reloc; if (WARN_ON(!klp_is_object_loaded(obj))) @@ -292,41 +243,38 @@ static int klp_write_object_relocations(struct module *pmod, if (WARN_ON(!obj->relocs)) return -EINVAL; + module_disable_ro(pmod); + for (reloc = obj->relocs; reloc->name; reloc++) { - if (!klp_is_module(obj)) { - -#if defined(CONFIG_RANDOMIZE_BASE) - /* If KASLR has been enabled, adjust old value accordingly */ - if (kaslr_enabled()) - reloc->val += kaslr_offset(); -#endif - ret = klp_verify_vmlinux_symbol(reloc->name, - reloc->val); - if (ret) - return ret; - } else { - /* module, reloc->val needs to be discovered */ - if (reloc->external) - ret = klp_find_external_symbol(pmod, - reloc->name, - &reloc->val); - else - ret = klp_find_object_symbol(obj->mod->name, - reloc->name, - &reloc->val); - if (ret) - return ret; - } + /* discover the address of the referenced symbol */ + if (reloc->external) { + if (reloc->sympos > 0) { + pr_err("non-zero sympos for external reloc symbol '%s' is not supported\n", + reloc->name); + ret = -EINVAL; + goto out; + } + ret = klp_find_external_symbol(pmod, reloc->name, &val); + } else + ret = klp_find_object_symbol(obj->name, + reloc->name, + reloc->sympos, + &val); + if (ret) + goto out; + ret = klp_write_module_reloc(pmod, reloc->type, reloc->loc, - reloc->val + reloc->addend); + val + reloc->addend); if (ret) { pr_err("relocation failed for symbol '%s' at 0x%016lx (%d)\n", - reloc->name, reloc->val, ret); - return ret; + reloc->name, val, ret); + goto out; } } - return 0; +out: + module_enable_ro(pmod); + return ret; } static void notrace klp_ftrace_handler(unsigned long ip, @@ -593,7 +541,7 @@ EXPORT_SYMBOL_GPL(klp_enable_patch); * /sys/kernel/livepatch/<patch> * /sys/kernel/livepatch/<patch>/enabled * /sys/kernel/livepatch/<patch>/<object> - * /sys/kernel/livepatch/<patch>/<object>/<func> + * /sys/kernel/livepatch/<patch>/<object>/<function,sympos> */ static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, @@ -738,8 +686,14 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func) INIT_LIST_HEAD(&func->stack_node); func->state = KLP_DISABLED; + /* The format for the sysfs directory is <function,sympos> where sympos + * is the nth occurrence of this symbol in kallsyms for the patched + * object. If the user selects 0 for old_sympos, then 1 will be used + * since a unique symbol will be the first occurrence. + */ return kobject_init_and_add(&func->kobj, &klp_ktype_func, - &obj->kobj, "%s", func->old_name); + &obj->kobj, "%s,%lu", func->old_name, + func->old_sympos ? func->old_sympos : 1); } /* parts of the initialization that is done only when the object is loaded */ @@ -756,7 +710,9 @@ static int klp_init_object_loaded(struct klp_patch *patch, } klp_for_each_func(obj, func) { - ret = klp_find_verify_func_addr(obj, func); + ret = klp_find_object_symbol(obj->name, func->old_name, + func->old_sympos, + &func->old_addr); if (ret) return ret; } diff --git a/kernel/memremap.c b/kernel/memremap.c index 7658d32c5c78..e517a16cb426 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -10,8 +10,11 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. */ +#include <linux/radix-tree.h> +#include <linux/memremap.h> #include <linux/device.h> #include <linux/types.h> +#include <linux/pfn_t.h> #include <linux/io.h> #include <linux/mm.h> #include <linux/memory_hotplug.h> @@ -147,24 +150,127 @@ void devm_memunmap(struct device *dev, void *addr) } EXPORT_SYMBOL(devm_memunmap); +pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags) +{ + return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags); +} +EXPORT_SYMBOL(phys_to_pfn_t); + #ifdef CONFIG_ZONE_DEVICE +static DEFINE_MUTEX(pgmap_lock); +static RADIX_TREE(pgmap_radix, GFP_KERNEL); +#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) +#define SECTION_SIZE (1UL << PA_SECTION_SHIFT) + struct page_map { struct resource res; + struct percpu_ref *ref; + struct dev_pagemap pgmap; + struct vmem_altmap altmap; }; -static void devm_memremap_pages_release(struct device *dev, void *res) +void get_zone_device_page(struct page *page) +{ + percpu_ref_get(page->pgmap->ref); +} +EXPORT_SYMBOL(get_zone_device_page); + +void put_zone_device_page(struct page *page) +{ + put_dev_pagemap(page->pgmap); +} +EXPORT_SYMBOL(put_zone_device_page); + +static void pgmap_radix_release(struct resource *res) +{ + resource_size_t key; + + mutex_lock(&pgmap_lock); + for (key = res->start; key <= res->end; key += SECTION_SIZE) + radix_tree_delete(&pgmap_radix, key >> PA_SECTION_SHIFT); + mutex_unlock(&pgmap_lock); +} + +static unsigned long pfn_first(struct page_map *page_map) +{ + struct dev_pagemap *pgmap = &page_map->pgmap; + const struct resource *res = &page_map->res; + struct vmem_altmap *altmap = pgmap->altmap; + unsigned long pfn; + + pfn = res->start >> PAGE_SHIFT; + if (altmap) + pfn += vmem_altmap_offset(altmap); + return pfn; +} + +static unsigned long pfn_end(struct page_map *page_map) +{ + const struct resource *res = &page_map->res; + + return (res->start + resource_size(res)) >> PAGE_SHIFT; +} + +#define for_each_device_pfn(pfn, map) \ + for (pfn = pfn_first(map); pfn < pfn_end(map); pfn++) + +static void devm_memremap_pages_release(struct device *dev, void *data) { - struct page_map *page_map = res; + struct page_map *page_map = data; + struct resource *res = &page_map->res; + resource_size_t align_start, align_size; + struct dev_pagemap *pgmap = &page_map->pgmap; + + if (percpu_ref_tryget_live(pgmap->ref)) { + dev_WARN(dev, "%s: page mapping is still live!\n", __func__); + percpu_ref_put(pgmap->ref); + } + + pgmap_radix_release(res); /* pages are dead and unused, undo the arch mapping */ - arch_remove_memory(page_map->res.start, resource_size(&page_map->res)); + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(resource_size(res), SECTION_SIZE); + arch_remove_memory(align_start, align_size); + dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc, + "%s: failed to free all reserved pages\n", __func__); +} + +/* assumes rcu_read_lock() held at entry */ +struct dev_pagemap *find_dev_pagemap(resource_size_t phys) +{ + struct page_map *page_map; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + page_map = radix_tree_lookup(&pgmap_radix, phys >> PA_SECTION_SHIFT); + return page_map ? &page_map->pgmap : NULL; } -void *devm_memremap_pages(struct device *dev, struct resource *res) +/** + * devm_memremap_pages - remap and provide memmap backing for the given resource + * @dev: hosting device for @res + * @res: "host memory" address range + * @ref: a live per-cpu reference count + * @altmap: optional descriptor for allocating the memmap from @res + * + * Notes: + * 1/ @ref must be 'live' on entry and 'dead' before devm_memunmap_pages() time + * (or devm release event). + * + * 2/ @res is expected to be a host memory range that could feasibly be + * treated as a "System RAM" range, i.e. not a device mmio range, but + * this is not enforced. + */ +void *devm_memremap_pages(struct device *dev, struct resource *res, + struct percpu_ref *ref, struct vmem_altmap *altmap) { int is_ram = region_intersects(res->start, resource_size(res), "System RAM"); + resource_size_t key, align_start, align_size; + struct dev_pagemap *pgmap; struct page_map *page_map; + unsigned long pfn; int error, nid; if (is_ram == REGION_MIXED) { @@ -176,25 +282,120 @@ void *devm_memremap_pages(struct device *dev, struct resource *res) if (is_ram == REGION_INTERSECTS) return __va(res->start); + if (altmap && !IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) { + dev_err(dev, "%s: altmap requires CONFIG_SPARSEMEM_VMEMMAP=y\n", + __func__); + return ERR_PTR(-ENXIO); + } + + if (!ref) + return ERR_PTR(-EINVAL); + page_map = devres_alloc_node(devm_memremap_pages_release, sizeof(*page_map), GFP_KERNEL, dev_to_node(dev)); if (!page_map) return ERR_PTR(-ENOMEM); + pgmap = &page_map->pgmap; memcpy(&page_map->res, res, sizeof(*res)); + pgmap->dev = dev; + if (altmap) { + memcpy(&page_map->altmap, altmap, sizeof(*altmap)); + pgmap->altmap = &page_map->altmap; + } + pgmap->ref = ref; + pgmap->res = &page_map->res; + + mutex_lock(&pgmap_lock); + error = 0; + for (key = res->start; key <= res->end; key += SECTION_SIZE) { + struct dev_pagemap *dup; + + rcu_read_lock(); + dup = find_dev_pagemap(key); + rcu_read_unlock(); + if (dup) { + dev_err(dev, "%s: %pr collides with mapping for %s\n", + __func__, res, dev_name(dup->dev)); + error = -EBUSY; + break; + } + error = radix_tree_insert(&pgmap_radix, key >> PA_SECTION_SHIFT, + page_map); + if (error) { + dev_err(dev, "%s: failed: %d\n", __func__, error); + break; + } + } + mutex_unlock(&pgmap_lock); + if (error) + goto err_radix; + nid = dev_to_node(dev); if (nid < 0) nid = numa_mem_id(); - error = arch_add_memory(nid, res->start, resource_size(res), true); - if (error) { - devres_free(page_map); - return ERR_PTR(error); - } + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(resource_size(res), SECTION_SIZE); + error = arch_add_memory(nid, align_start, align_size, true); + if (error) + goto err_add_memory; + for_each_device_pfn(pfn, page_map) { + struct page *page = pfn_to_page(pfn); + + /* ZONE_DEVICE pages must never appear on a slab lru */ + list_force_poison(&page->lru); + page->pgmap = pgmap; + } devres_add(dev, page_map); return __va(res->start); + + err_add_memory: + err_radix: + pgmap_radix_release(res); + devres_free(page_map); + return ERR_PTR(error); } EXPORT_SYMBOL(devm_memremap_pages); + +unsigned long vmem_altmap_offset(struct vmem_altmap *altmap) +{ + /* number of pfns from base where pfn_to_page() is valid */ + return altmap->reserve + altmap->free; +} + +void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) +{ + altmap->alloc -= nr_pfns; +} + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start) +{ + /* + * 'memmap_start' is the virtual address for the first "struct + * page" in this range of the vmemmap array. In the case of + * CONFIG_SPARSE_VMEMMAP a page_to_pfn conversion is simple + * pointer arithmetic, so we can perform this to_vmem_altmap() + * conversion without concern for the initialization state of + * the struct page fields. + */ + struct page *page = (struct page *) memmap_start; + struct dev_pagemap *pgmap; + + /* + * Uncoditionally retrieve a dev_pagemap associated with the + * given physical address, this is only for use in the + * arch_{add|remove}_memory() for setting up and tearing down + * the memmap. + */ + rcu_read_lock(); + pgmap = find_dev_pagemap(__pfn_to_phys(page_to_pfn(page))); + rcu_read_unlock(); + + return pgmap ? pgmap->altmap : NULL; +} +#endif /* CONFIG_SPARSEMEM_VMEMMAP */ #endif /* CONFIG_ZONE_DEVICE */ diff --git a/kernel/module.c b/kernel/module.c index 38c7bd5583ff..8358f4697c0c 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -80,15 +80,6 @@ # define debug_align(X) (X) #endif -/* - * Given BASE and SIZE this macro calculates the number of pages the - * memory regions occupies - */ -#define MOD_NUMBER_OF_PAGES(BASE, SIZE) (((SIZE) > 0) ? \ - (PFN_DOWN((unsigned long)(BASE) + (SIZE) - 1) - \ - PFN_DOWN((unsigned long)BASE) + 1) \ - : (0UL)) - /* If this is set, the section belongs in the init part of the module */ #define INIT_OFFSET_MASK (1UL << (BITS_PER_LONG-1)) @@ -108,13 +99,6 @@ static LIST_HEAD(modules); * Use a latched RB-tree for __module_address(); this allows us to use * RCU-sched lookups of the address from any context. * - * Because modules have two address ranges: init and core, we need two - * latch_tree_nodes entries. Therefore we need the back-pointer from - * mod_tree_node. - * - * Because init ranges are short lived we mark them unlikely and have placed - * them outside the critical cacheline in struct module. - * * 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. @@ -122,24 +106,16 @@ static LIST_HEAD(modules); static __always_inline unsigned long __mod_tree_val(struct latch_tree_node *n) { - struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node); - struct module *mod = mtn->mod; + struct module_layout *layout = container_of(n, struct module_layout, mtn.node); - if (unlikely(mtn == &mod->mtn_init)) - return (unsigned long)mod->module_init; - - return (unsigned long)mod->module_core; + return (unsigned long)layout->base; } static __always_inline unsigned long __mod_tree_size(struct latch_tree_node *n) { - struct mod_tree_node *mtn = container_of(n, struct mod_tree_node, node); - struct module *mod = mtn->mod; - - if (unlikely(mtn == &mod->mtn_init)) - return (unsigned long)mod->init_size; + struct module_layout *layout = container_of(n, struct module_layout, mtn.node); - return (unsigned long)mod->core_size; + return (unsigned long)layout->size; } static __always_inline bool @@ -197,23 +173,23 @@ static void __mod_tree_remove(struct mod_tree_node *node) */ static void mod_tree_insert(struct module *mod) { - mod->mtn_core.mod = mod; - mod->mtn_init.mod = mod; + mod->core_layout.mtn.mod = mod; + mod->init_layout.mtn.mod = mod; - __mod_tree_insert(&mod->mtn_core); - if (mod->init_size) - __mod_tree_insert(&mod->mtn_init); + __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_size) - __mod_tree_remove(&mod->mtn_init); + if (mod->init_layout.size) + __mod_tree_remove(&mod->init_layout.mtn); } static void mod_tree_remove(struct module *mod) { - __mod_tree_remove(&mod->mtn_core); + __mod_tree_remove(&mod->core_layout.mtn); mod_tree_remove_init(mod); } @@ -267,9 +243,9 @@ static void __mod_update_bounds(void *base, unsigned int size) static void mod_update_bounds(struct module *mod) { - __mod_update_bounds(mod->module_core, mod->core_size); - if (mod->init_size) - __mod_update_bounds(mod->module_init, mod->init_size); + __mod_update_bounds(mod->core_layout.base, mod->core_layout.size); + if (mod->init_layout.size) + __mod_update_bounds(mod->init_layout.base, mod->init_layout.size); } #ifdef CONFIG_KGDB_KDB @@ -1214,7 +1190,7 @@ struct module_attribute module_uevent = static ssize_t show_coresize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", mk->mod->core_size); + return sprintf(buffer, "%u\n", mk->mod->core_layout.size); } static struct module_attribute modinfo_coresize = @@ -1223,7 +1199,7 @@ static struct module_attribute modinfo_coresize = static ssize_t show_initsize(struct module_attribute *mattr, struct module_kobject *mk, char *buffer) { - return sprintf(buffer, "%u\n", mk->mod->init_size); + return sprintf(buffer, "%u\n", mk->mod->init_layout.size); } static struct module_attribute modinfo_initsize = @@ -1873,64 +1849,75 @@ static void mod_sysfs_teardown(struct module *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] [writable data] + * text_size -----^ ^ ^ + * ro_size ------------------------| | + * size -------------------------------------------| + * + * These values are always page-aligned (as is base) */ -void set_page_attributes(void *start, void *end, int (*set)(unsigned long start, int num_pages)) +static void frob_text(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) { - unsigned long begin_pfn = PFN_DOWN((unsigned long)start); - unsigned long end_pfn = PFN_DOWN((unsigned long)end); + 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); +} - if (end_pfn > begin_pfn) - set(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn); +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 set_section_ro_nx(void *base, - unsigned long text_size, - unsigned long ro_size, - unsigned long total_size) +static void frob_writable_data(const struct module_layout *layout, + int (*set_memory)(unsigned long start, int num_pages)) { - /* begin and end PFNs of the current subsection */ - unsigned long begin_pfn; - unsigned long end_pfn; + BUG_ON((unsigned long)layout->base & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->ro_size & (PAGE_SIZE-1)); + BUG_ON((unsigned long)layout->size & (PAGE_SIZE-1)); + set_memory((unsigned long)layout->base + layout->ro_size, + (layout->size - layout->ro_size) >> PAGE_SHIFT); +} - /* - * Set RO for module text and RO-data: - * - Always protect first page. - * - Do not protect last partial page. - */ - if (ro_size > 0) - set_page_attributes(base, base + ro_size, set_memory_ro); +/* livepatching wants to disable read-only so it can frob module. */ +void module_disable_ro(const struct module *mod) +{ + frob_text(&mod->core_layout, set_memory_rw); + frob_rodata(&mod->core_layout, set_memory_rw); + frob_text(&mod->init_layout, set_memory_rw); + frob_rodata(&mod->init_layout, set_memory_rw); +} - /* - * Set NX permissions for module data: - * - Do not protect first partial page. - * - Always protect last page. - */ - if (total_size > text_size) { - begin_pfn = PFN_UP((unsigned long)base + text_size); - end_pfn = PFN_UP((unsigned long)base + total_size); - if (end_pfn > begin_pfn) - set_memory_nx(begin_pfn << PAGE_SHIFT, end_pfn - begin_pfn); - } +void module_enable_ro(const struct module *mod) +{ + 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); } -static void unset_module_core_ro_nx(struct module *mod) +static void module_enable_nx(const struct module *mod) { - set_page_attributes(mod->module_core + mod->core_text_size, - mod->module_core + mod->core_size, - set_memory_x); - set_page_attributes(mod->module_core, - mod->module_core + mod->core_ro_size, - set_memory_rw); + frob_rodata(&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 void unset_module_init_ro_nx(struct module *mod) +static void module_disable_nx(const struct module *mod) { - set_page_attributes(mod->module_init + mod->init_text_size, - mod->module_init + mod->init_size, - set_memory_x); - set_page_attributes(mod->module_init, - mod->module_init + mod->init_ro_size, - set_memory_rw); + frob_rodata(&mod->core_layout, set_memory_x); + frob_writable_data(&mod->core_layout, set_memory_x); + frob_rodata(&mod->init_layout, set_memory_x); + frob_writable_data(&mod->init_layout, set_memory_x); } /* Iterate through all modules and set each module's text as RW */ @@ -1942,16 +1929,9 @@ void set_all_modules_text_rw(void) list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; - if ((mod->module_core) && (mod->core_text_size)) { - set_page_attributes(mod->module_core, - mod->module_core + mod->core_text_size, - set_memory_rw); - } - if ((mod->module_init) && (mod->init_text_size)) { - set_page_attributes(mod->module_init, - mod->module_init + mod->init_text_size, - set_memory_rw); - } + + frob_text(&mod->core_layout, set_memory_rw); + frob_text(&mod->init_layout, set_memory_rw); } mutex_unlock(&module_mutex); } @@ -1965,23 +1945,25 @@ void set_all_modules_text_ro(void) list_for_each_entry_rcu(mod, &modules, list) { if (mod->state == MODULE_STATE_UNFORMED) continue; - if ((mod->module_core) && (mod->core_text_size)) { - set_page_attributes(mod->module_core, - mod->module_core + mod->core_text_size, - set_memory_ro); - } - if ((mod->module_init) && (mod->init_text_size)) { - set_page_attributes(mod->module_init, - mod->module_init + mod->init_text_size, - set_memory_ro); - } + + frob_text(&mod->core_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_ro); } mutex_unlock(&module_mutex); } + +static void disable_ro_nx(const struct module_layout *layout) +{ + frob_text(layout, set_memory_rw); + frob_rodata(layout, set_memory_rw); + frob_rodata(layout, set_memory_x); + frob_writable_data(layout, set_memory_x); +} + #else -static inline void set_section_ro_nx(void *base, unsigned long text_size, unsigned long ro_size, unsigned long total_size) { } -static void unset_module_core_ro_nx(struct module *mod) { } -static void unset_module_init_ro_nx(struct module *mod) { } +static void disable_ro_nx(const struct module_layout *layout) { } +static void module_enable_nx(const struct module *mod) { } +static void module_disable_nx(const struct module *mod) { } #endif void __weak module_memfree(void *module_region) @@ -2033,19 +2015,19 @@ static void free_module(struct module *mod) synchronize_sched(); mutex_unlock(&module_mutex); - /* This may be NULL, but that's OK */ - unset_module_init_ro_nx(mod); + /* This may be empty, but that's OK */ + disable_ro_nx(&mod->init_layout); module_arch_freeing_init(mod); - module_memfree(mod->module_init); + module_memfree(mod->init_layout.base); kfree(mod->args); percpu_modfree(mod); /* Free lock-classes; relies on the preceding sync_rcu(). */ - lockdep_free_key_range(mod->module_core, mod->core_size); + lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); /* Finally, free the core (containing the module structure) */ - unset_module_core_ro_nx(mod); - module_memfree(mod->module_core); + disable_ro_nx(&mod->core_layout); + module_memfree(mod->core_layout.base); #ifdef CONFIG_MPU update_protections(current->mm); @@ -2248,20 +2230,20 @@ static void layout_sections(struct module *mod, struct load_info *info) || s->sh_entsize != ~0UL || strstarts(sname, ".init")) continue; - s->sh_entsize = get_offset(mod, &mod->core_size, s, i); + s->sh_entsize = get_offset(mod, &mod->core_layout.size, s, i); pr_debug("\t%s\n", sname); } switch (m) { case 0: /* executable */ - mod->core_size = debug_align(mod->core_size); - mod->core_text_size = mod->core_size; + mod->core_layout.size = debug_align(mod->core_layout.size); + mod->core_layout.text_size = mod->core_layout.size; break; case 1: /* RO: text and ro-data */ - mod->core_size = debug_align(mod->core_size); - mod->core_ro_size = mod->core_size; + mod->core_layout.size = debug_align(mod->core_layout.size); + mod->core_layout.ro_size = mod->core_layout.size; break; case 3: /* whole core */ - mod->core_size = debug_align(mod->core_size); + mod->core_layout.size = debug_align(mod->core_layout.size); break; } } @@ -2277,21 +2259,21 @@ static void layout_sections(struct module *mod, struct load_info *info) || s->sh_entsize != ~0UL || !strstarts(sname, ".init")) continue; - s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) + s->sh_entsize = (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_size = debug_align(mod->init_size); - mod->init_text_size = mod->init_size; + mod->init_layout.size = debug_align(mod->init_layout.size); + mod->init_layout.text_size = mod->init_layout.size; break; case 1: /* RO: text and ro-data */ - mod->init_size = debug_align(mod->init_size); - mod->init_ro_size = mod->init_size; + mod->init_layout.size = debug_align(mod->init_layout.size); + mod->init_layout.ro_size = mod->init_layout.size; break; case 3: /* whole init */ - mod->init_size = debug_align(mod->init_size); + mod->init_layout.size = debug_align(mod->init_layout.size); break; } } @@ -2401,7 +2383,7 @@ static char elf_type(const Elf_Sym *sym, const struct load_info *info) } if (sym->st_shndx == SHN_UNDEF) return 'U'; - if (sym->st_shndx == SHN_ABS) + if (sym->st_shndx == SHN_ABS || sym->st_shndx == info->index.pcpu) return 'a'; if (sym->st_shndx >= SHN_LORESERVE) return '?'; @@ -2430,7 +2412,7 @@ static char elf_type(const Elf_Sym *sym, const struct load_info *info) } static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, - unsigned int shnum) + unsigned int shnum, unsigned int pcpundx) { const Elf_Shdr *sec; @@ -2439,6 +2421,11 @@ static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, || !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 @@ -2466,7 +2453,7 @@ static void layout_symtab(struct module *mod, struct load_info *info) /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; - symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect, + 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); @@ -2476,23 +2463,24 @@ static void layout_symtab(struct module *mod, struct load_info *info) /* Compute total space required for the core symbols' strtab. */ for (ndst = i = 0; i < nsrc; i++) { if (i == 0 || - is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) { + 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_size, symsect->sh_addralign ?: 1); - info->stroffs = mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym); - mod->core_size += strtab_size; - mod->core_size = debug_align(mod->core_size); + 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; + 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_size, strsect, + strsect->sh_entsize = get_offset(mod, &mod->init_layout.size, strsect, info->index.str) | INIT_OFFSET_MASK; - mod->init_size = debug_align(mod->init_size); + mod->init_layout.size = debug_align(mod->init_layout.size); pr_debug("\t%s\n", info->secstrings + strsect->sh_name); } @@ -2513,12 +2501,13 @@ static void add_kallsyms(struct module *mod, const struct load_info *info) for (i = 0; i < mod->num_symtab; i++) mod->symtab[i].st_info = elf_type(&mod->symtab[i], info); - mod->core_symtab = dst = mod->module_core + info->symoffs; - mod->core_strtab = s = mod->module_core + info->stroffs; + mod->core_symtab = dst = mod->core_layout.base + info->symoffs; + mod->core_strtab = s = mod->core_layout.base + info->stroffs; src = mod->symtab; for (ndst = i = 0; i < mod->num_symtab; i++) { if (i == 0 || - is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum)) { + is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum, + info->index.pcpu)) { dst[ndst] = src[i]; dst[ndst++].st_name = s - mod->core_strtab; s += strlcpy(s, &mod->strtab[src[i].st_name], @@ -2964,7 +2953,7 @@ static int move_module(struct module *mod, struct load_info *info) void *ptr; /* Do the allocs. */ - ptr = module_alloc(mod->core_size); + ptr = module_alloc(mod->core_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 @@ -2974,11 +2963,11 @@ static int move_module(struct module *mod, struct load_info *info) if (!ptr) return -ENOMEM; - memset(ptr, 0, mod->core_size); - mod->module_core = ptr; + memset(ptr, 0, mod->core_layout.size); + mod->core_layout.base = ptr; - if (mod->init_size) { - ptr = module_alloc(mod->init_size); + if (mod->init_layout.size) { + ptr = module_alloc(mod->init_layout.size); /* * The pointer to this block is stored in the module structure * which is inside the block. This block doesn't need to be @@ -2987,13 +2976,13 @@ static int move_module(struct module *mod, struct load_info *info) */ kmemleak_ignore(ptr); if (!ptr) { - module_memfree(mod->module_core); + module_memfree(mod->core_layout.base); return -ENOMEM; } - memset(ptr, 0, mod->init_size); - mod->module_init = ptr; + memset(ptr, 0, mod->init_layout.size); + mod->init_layout.base = ptr; } else - mod->module_init = NULL; + mod->init_layout.base = NULL; /* Transfer each section which specifies SHF_ALLOC */ pr_debug("final section addresses:\n"); @@ -3005,10 +2994,10 @@ static int move_module(struct module *mod, struct load_info *info) continue; if (shdr->sh_entsize & INIT_OFFSET_MASK) - dest = mod->module_init + dest = mod->init_layout.base + (shdr->sh_entsize & ~INIT_OFFSET_MASK); else - dest = mod->module_core + shdr->sh_entsize; + dest = mod->core_layout.base + shdr->sh_entsize; if (shdr->sh_type != SHT_NOBITS) memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); @@ -3070,12 +3059,12 @@ static void flush_module_icache(const struct module *mod) * Do it before processing of module parameters, so the module * can provide parameter accessor functions of its own. */ - if (mod->module_init) - flush_icache_range((unsigned long)mod->module_init, - (unsigned long)mod->module_init - + mod->init_size); - flush_icache_range((unsigned long)mod->module_core, - (unsigned long)mod->module_core + mod->core_size); + if (mod->init_layout.base) + flush_icache_range((unsigned long)mod->init_layout.base, + (unsigned long)mod->init_layout.base + + mod->init_layout.size); + flush_icache_range((unsigned long)mod->core_layout.base, + (unsigned long)mod->core_layout.base + mod->core_layout.size); set_fs(old_fs); } @@ -3133,8 +3122,8 @@ static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); module_arch_freeing_init(mod); - module_memfree(mod->module_init); - module_memfree(mod->module_core); + module_memfree(mod->init_layout.base); + module_memfree(mod->core_layout.base); } int __weak module_finalize(const Elf_Ehdr *hdr, @@ -3221,7 +3210,7 @@ static noinline int do_init_module(struct module *mod) ret = -ENOMEM; goto fail; } - freeinit->module_init = mod->module_init; + freeinit->module_init = mod->init_layout.base; /* * We want to find out whether @mod uses async during init. Clear @@ -3279,12 +3268,12 @@ static noinline int do_init_module(struct module *mod) mod->strtab = mod->core_strtab; #endif mod_tree_remove_init(mod); - unset_module_init_ro_nx(mod); + disable_ro_nx(&mod->init_layout); module_arch_freeing_init(mod); - mod->module_init = NULL; - mod->init_size = 0; - mod->init_ro_size = 0; - mod->init_text_size = 0; + mod->init_layout.base = NULL; + mod->init_layout.size = 0; + mod->init_layout.ro_size = 0; + mod->init_layout.text_size = 0; /* * We want to free module_init, but be aware that kallsyms may be * walking this with preempt disabled. In all the failure paths, we @@ -3373,17 +3362,9 @@ 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); - /* Set RO and NX regions for core */ - set_section_ro_nx(mod->module_core, - mod->core_text_size, - mod->core_ro_size, - mod->core_size); - - /* Set RO and NX regions for init */ - set_section_ro_nx(mod->module_init, - mod->init_text_size, - mod->init_ro_size, - mod->init_size); + /* Set RO and NX regions */ + module_enable_ro(mod); + module_enable_nx(mod); /* Mark state as coming so strong_try_module_get() ignores us, * but kallsyms etc. can see us. */ @@ -3548,8 +3529,8 @@ static int load_module(struct load_info *info, const char __user *uargs, MODULE_STATE_GOING, mod); /* we can't deallocate the module until we clear memory protection */ - unset_module_init_ro_nx(mod); - unset_module_core_ro_nx(mod); + module_disable_ro(mod); + module_disable_nx(mod); ddebug_cleanup: dynamic_debug_remove(info->debug); @@ -3578,7 +3559,7 @@ static int load_module(struct load_info *info, const char __user *uargs, */ ftrace_release_mod(mod); /* Free lock-classes; relies on the preceding sync_rcu() */ - lockdep_free_key_range(mod->module_core, mod->core_size); + lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size); module_deallocate(mod, info); free_copy: @@ -3656,9 +3637,9 @@ static const char *get_ksymbol(struct module *mod, /* At worse, next value is at end of module */ if (within_module_init(addr, mod)) - nextval = (unsigned long)mod->module_init+mod->init_text_size; + nextval = (unsigned long)mod->init_layout.base+mod->init_layout.text_size; else - nextval = (unsigned long)mod->module_core+mod->core_text_size; + nextval = (unsigned long)mod->core_layout.base+mod->core_layout.text_size; /* Scan for closest preceding symbol, and next symbol. (ELF starts real symbols at 1). */ @@ -3905,7 +3886,7 @@ static int m_show(struct seq_file *m, void *p) return 0; seq_printf(m, "%s %u", - mod->name, mod->init_size + mod->core_size); + mod->name, mod->init_layout.size + mod->core_layout.size); print_unload_info(m, mod); /* Informative for users. */ @@ -3914,7 +3895,7 @@ static int m_show(struct seq_file *m, void *p) mod->state == MODULE_STATE_COMING ? "Loading" : "Live"); /* Used by oprofile and other similar tools. */ - seq_printf(m, " 0x%pK", mod->module_core); + seq_printf(m, " 0x%pK", mod->core_layout.base); /* Taints info */ if (mod->taints) @@ -4057,8 +4038,8 @@ struct module *__module_text_address(unsigned long addr) struct module *mod = __module_address(addr); if (mod) { /* Make sure it's within the text section. */ - if (!within(addr, mod->module_init, mod->init_text_size) - && !within(addr, mod->module_core, mod->core_text_size)) + if (!within(addr, mod->init_layout.base, mod->init_layout.text_size) + && !within(addr, mod->core_layout.base, mod->core_layout.text_size)) mod = NULL; } return mod; diff --git a/kernel/panic.c b/kernel/panic.c index b333380c6bb2..d96469de72dc 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -180,8 +180,7 @@ void panic(const char *fmt, ...) * panic() is not being callled from OOPS. */ debug_locks_off(); - console_trylock(); - console_unlock(); + console_flush_on_panic(); if (!panic_blink) panic_blink = no_blink; diff --git a/kernel/pid.c b/kernel/pid.c index 78b3d9f80d44..f4ad91b746f1 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -604,5 +604,5 @@ void __init pidmap_init(void) atomic_dec(&init_pid_ns.pidmap[0].nr_free); init_pid_ns.pid_cachep = KMEM_CACHE(pid, - SLAB_HWCACHE_ALIGN | SLAB_PANIC); + SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 2ce8826f1053..e79439134978 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -48,6 +48,7 @@ #include <linux/uio.h> #include <asm/uaccess.h> +#include <asm-generic/sections.h> #define CREATE_TRACE_POINTS #include <trace/events/printk.h> @@ -1660,7 +1661,7 @@ asmlinkage int vprintk_emit(int facility, int level, const char *dict, size_t dictlen, const char *fmt, va_list args) { - static int recursion_bug; + static bool recursion_bug; static char textbuf[LOG_LINE_MAX]; char *text = textbuf; size_t text_len = 0; @@ -1696,7 +1697,7 @@ asmlinkage int vprintk_emit(int facility, int level, * it can be printed at the next appropriate moment: */ if (!oops_in_progress && !lockdep_recursing(current)) { - recursion_bug = 1; + recursion_bug = true; local_irq_restore(flags); return 0; } @@ -1711,7 +1712,7 @@ asmlinkage int vprintk_emit(int facility, int level, static const char recursion_msg[] = "BUG: recent printk recursion!"; - recursion_bug = 0; + recursion_bug = false; /* emit KERN_CRIT message */ printed_len += log_store(0, 2, LOG_PREFIX|LOG_NEWLINE, 0, NULL, 0, recursion_msg, @@ -2233,13 +2234,24 @@ void console_unlock(void) static u64 seen_seq; unsigned long flags; bool wake_klogd = false; - bool retry; + bool do_cond_resched, retry; if (console_suspended) { up_console_sem(); return; } + /* + * Console drivers are called under logbuf_lock, so + * @console_may_schedule should be cleared before; however, we may + * end up dumping a lot of lines, for example, if called from + * console registration path, and should invoke cond_resched() + * between lines if allowable. Not doing so can cause a very long + * scheduling stall on a slow console leading to RCU stall and + * softlockup warnings which exacerbate the issue with more + * messages practically incapacitating the system. + */ + do_cond_resched = console_may_schedule; console_may_schedule = 0; /* flush buffered message fragment immediately to console */ @@ -2311,6 +2323,9 @@ skip: call_console_drivers(level, ext_text, ext_len, text, len); start_critical_timings(); local_irq_restore(flags); + + if (do_cond_resched) + cond_resched(); } console_locked = 0; @@ -2378,6 +2393,25 @@ void console_unblank(void) console_unlock(); } +/** + * console_flush_on_panic - flush console content on panic + * + * Immediately output all pending messages no matter what. + */ +void console_flush_on_panic(void) +{ + /* + * If someone else is holding the console lock, trylock will fail + * and may_schedule may be set. Ignore and proceed to unlock so + * that messages are flushed out. As this can be called from any + * context and we don't want to get preempted while flushing, + * ensure may_schedule is cleared. + */ + console_trylock(); + console_may_schedule = 0; + console_unlock(); +} + /* * Return the console tty driver structure and its associated index */ @@ -2658,13 +2692,36 @@ int unregister_console(struct console *console) } EXPORT_SYMBOL(unregister_console); +/* + * Some boot consoles access data that is in the init section and which will + * be discarded after the initcalls have been run. To make sure that no code + * will access this data, unregister the boot consoles in a late initcall. + * + * If for some reason, such as deferred probe or the driver being a loadable + * module, the real console hasn't registered yet at this point, there will + * be a brief interval in which no messages are logged to the console, which + * makes it difficult to diagnose problems that occur during this time. + * + * To mitigate this problem somewhat, only unregister consoles whose memory + * intersects with the init section. Note that code exists elsewhere to get + * rid of the boot console as soon as the proper console shows up, so there + * won't be side-effects from postponing the removal. + */ static int __init printk_late_init(void) { struct console *con; for_each_console(con) { if (!keep_bootcon && con->flags & CON_BOOT) { - unregister_console(con); + /* + * Make sure to unregister boot consoles whose data + * resides in the init section before the init section + * is discarded. Boot consoles whose data will stick + * around will automatically be unregistered when the + * proper console replaces them. + */ + if (init_section_intersects(con, sizeof(*con))) + unregister_console(con); } } hotcpu_notifier(console_cpu_notify, 0); diff --git a/kernel/resource.c b/kernel/resource.c index f150dbbe6f62..09c0597840b0 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1498,8 +1498,15 @@ int iomem_is_exclusive(u64 addr) break; if (p->end < addr) continue; - if (p->flags & IORESOURCE_BUSY && - p->flags & IORESOURCE_EXCLUSIVE) { + /* + * A resource is exclusive if IORESOURCE_EXCLUSIVE is set + * or CONFIG_IO_STRICT_DEVMEM is enabled and the + * resource is busy. + */ + if ((p->flags & IORESOURCE_BUSY) == 0) + continue; + if (IS_ENABLED(CONFIG_IO_STRICT_DEVMEM) + || p->flags & IORESOURCE_EXCLUSIVE) { err = 1; break; } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 34852ee70d54..de0e786b2667 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -213,6 +213,7 @@ static void cpu_idle_loop(void) */ __current_set_polling(); + quiet_vmstat(); tick_nohz_idle_enter(); while (!need_resched()) { diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index edb6de4f5908..a467e6c28a3b 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -529,8 +529,6 @@ static int __init cpu_stop_init(void) } early_initcall(cpu_stop_init); -#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) - static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { struct multi_stop_data msdata = { @@ -628,5 +626,3 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, mutex_unlock(&stop_cpus_mutex); return ret ?: done.ret; } - -#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5faf89ac9ec0..c810f8afdb7f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1568,6 +1568,28 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS + { + .procname = "mmap_rnd_bits", + .data = &mmap_rnd_bits, + .maxlen = sizeof(mmap_rnd_bits), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&mmap_rnd_bits_min, + .extra2 = (void *)&mmap_rnd_bits_max, + }, +#endif +#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS + { + .procname = "mmap_rnd_compat_bits", + .data = &mmap_rnd_compat_bits, + .maxlen = sizeof(mmap_rnd_compat_bits), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = (void *)&mmap_rnd_compat_bits_min, + .extra2 = (void *)&mmap_rnd_compat_bits_max, + }, +#endif { } }; |