Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Ingo Molnar:
 "The changes in here are:

   - text_poke() fixes and an extensive set of executability lockdowns,
     to (hopefully) eliminate the last residual circumstances under
     which we are using W|X mappings even temporarily on x86 kernels.
     This required a broad range of surgery in text patching facilities,
     module loading, trampoline handling and other bits.

   - tweak page fault messages to be more informative and more
     structured.

   - remove DISCONTIGMEM support on x86-32 and make SPARSEMEM the
     default.

   - reduce KASLR granularity on 5-level paging kernels from 512 GB to
     1 GB.

   - misc other changes and updates"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  x86/mm: Initialize PGD cache during mm initialization
  x86/alternatives: Add comment about module removal races
  x86/kprobes: Use vmalloc special flag
  x86/ftrace: Use vmalloc special flag
  bpf: Use vmalloc special flag
  modules: Use vmalloc special flag
  mm/vmalloc: Add flag for freeing of special permsissions
  mm/hibernation: Make hibernation handle unmapped pages
  x86/mm/cpa: Add set_direct_map_*() functions
  x86/alternatives: Remove the return value of text_poke_*()
  x86/jump-label: Remove support for custom text poker
  x86/modules: Avoid breaking W^X while loading modules
  x86/kprobes: Set instruction page as executable
  x86/ftrace: Set trampoline pages as executable
  x86/kgdb: Avoid redundant comparison of patched code
  x86/alternatives: Use temporary mm for text poking
  x86/alternatives: Initialize temporary mm for patching
  fork: Provide a function for copying init_mm
  uprobes: Initialize uprobes earlier
  x86/mm: Save debug registers when loading a temporary mm
  ...

kernel/bpf/core.c

@@ -848,7 +848,6 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
 	if (fp->jited) {
 		struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
 
-		bpf_jit_binary_unlock_ro(hdr);
 		bpf_jit_binary_free(hdr);
 
 		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));

kernel/events/uprobes.c

@@ -2294,16 +2294,14 @@ static struct notifier_block uprobe_exception_nb = {
 	.priority		= INT_MAX-1,	/* notified after kprobes, kgdb */
 };
 
-static int __init init_uprobes(void)
+void __init uprobes_init(void)
 {
 	int i;
 
 	for (i = 0; i < UPROBES_HASH_SZ; i++)
 		mutex_init(&uprobes_mmap_mutex[i]);
 
-	if (percpu_init_rwsem(&dup_mmap_sem))
-		return -ENOMEM;
+	BUG_ON(percpu_init_rwsem(&dup_mmap_sem));
 
-	return register_die_notifier(&uprobe_exception_nb);
+	BUG_ON(register_die_notifier(&uprobe_exception_nb));
 }
-__initcall(init_uprobes);

kernel/fork.c

@@ -815,6 +815,7 @@ void __init fork_init(void)
 #endif
 
 	lockdep_init_task(&init_task);
+	uprobes_init();
 }
 
 int __weak arch_dup_task_struct(struct task_struct *dst,
@@ -1298,13 +1299,20 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 		complete_vfork_done(tsk);
 }
 
-/*
- * Allocate a new mm structure and copy contents from the
- * mm structure of the passed in task structure.
+/**
+ * dup_mm() - duplicates an existing mm structure
+ * @tsk: the task_struct with which the new mm will be associated.
+ * @oldmm: the mm to duplicate.
+ *
+ * Allocates a new mm structure and duplicates the provided @oldmm structure
+ * content into it.
+ *
+ * Return: the duplicated mm or NULL on failure.
  */
-static struct mm_struct *dup_mm(struct task_struct *tsk)
+static struct mm_struct *dup_mm(struct task_struct *tsk,
+				struct mm_struct *oldmm)
 {
-	struct mm_struct *mm, *oldmm = current->mm;
+	struct mm_struct *mm;
 	int err;
 
 	mm = allocate_mm();
@@ -1371,7 +1379,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 	}
 
 	retval = -ENOMEM;
-	mm = dup_mm(tsk);
+	mm = dup_mm(tsk, current->mm);
 	if (!mm)
 		goto fail_nomem;
 
@@ -2186,6 +2194,11 @@ struct task_struct *fork_idle(int cpu)
 	return task;
 }
 
+struct mm_struct *copy_init_mm(void)
+{
+	return dup_mm(NULL, &init_mm);
+}
+
 /*
  *  Ok, this is the main fork-routine.
  *

kernel/module.c

@@ -98,6 +98,10 @@ DEFINE_MUTEX(module_mutex);
 EXPORT_SYMBOL_GPL(module_mutex);
 static LIST_HEAD(modules);
 
+/* Work queue for freeing init sections in success case */
+static struct work_struct init_free_wq;
+static struct llist_head init_free_list;
+
 #ifdef CONFIG_MODULES_TREE_LOOKUP
 
 /*
@@ -1949,9 +1953,16 @@ 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_text(&mod->core_layout, set_memory_x);
+
 	frob_rodata(&mod->core_layout, set_memory_ro);
+
 	frob_text(&mod->init_layout, set_memory_ro);
+	frob_text(&mod->init_layout, set_memory_x);
+
 	frob_rodata(&mod->init_layout, set_memory_ro);
 
 	if (after_init)
@@ -1967,15 +1978,6 @@ static void module_enable_nx(const struct module *mod)
 	frob_writable_data(&mod->init_layout, set_memory_nx);
 }
 
-static void module_disable_nx(const struct module *mod)
-{
-	frob_rodata(&mod->core_layout, set_memory_x);
-	frob_ro_after_init(&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 */
 void set_all_modules_text_rw(void)
 {
@@ -2019,23 +2021,8 @@ void set_all_modules_text_ro(void)
 	}
 	mutex_unlock(&module_mutex);
 }
-
-static void disable_ro_nx(const struct module_layout *layout)
-{
-	if (rodata_enabled) {
-		frob_text(layout, set_memory_rw);
-		frob_rodata(layout, set_memory_rw);
-		frob_ro_after_init(layout, set_memory_rw);
-	}
-	frob_rodata(layout, set_memory_x);
-	frob_ro_after_init(layout, set_memory_x);
-	frob_writable_data(layout, set_memory_x);
-}
-
 #else
-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
 
 #ifdef CONFIG_LIVEPATCH
@@ -2115,6 +2102,11 @@ static void free_module_elf(struct module *mod)
 
 void __weak module_memfree(void *module_region)
 {
+	/*
+	 * This memory may be RO, and freeing RO memory in an interrupt is not
+	 * supported by vmalloc.
+	 */
+	WARN_ON(in_interrupt());
 	vfree(module_region);
 }
 
@@ -2166,7 +2158,6 @@ static void free_module(struct module *mod)
 	mutex_unlock(&module_mutex);
 
 	/* This may be empty, but that's OK */
-	disable_ro_nx(&mod->init_layout);
 	module_arch_freeing_init(mod);
 	module_memfree(mod->init_layout.base);
 	kfree(mod->args);
@@ -2176,7 +2167,6 @@ static void free_module(struct module *mod)
 	lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size);
 
 	/* Finally, free the core (containing the module structure) */
-	disable_ro_nx(&mod->core_layout);
 	module_memfree(mod->core_layout.base);
 }
 
@@ -3415,17 +3405,34 @@ static void do_mod_ctors(struct module *mod)
 
 /* For freeing module_init on success, in case kallsyms traversing */
 struct mod_initfree {
-	struct rcu_head rcu;
+	struct llist_node node;
 	void *module_init;
 };
 
-static void do_free_init(struct rcu_head *head)
+static void do_free_init(struct work_struct *w)
 {
-	struct mod_initfree *m = container_of(head, struct mod_initfree, rcu);
-	module_memfree(m->module_init);
-	kfree(m);
+	struct llist_node *pos, *n, *list;
+	struct mod_initfree *initfree;
+
+	list = llist_del_all(&init_free_list);
+
+	synchronize_rcu();
+
+	llist_for_each_safe(pos, n, list) {
+		initfree = container_of(pos, struct mod_initfree, node);
+		module_memfree(initfree->module_init);
+		kfree(initfree);
+	}
 }
 
+static int __init modules_wq_init(void)
+{
+	INIT_WORK(&init_free_wq, do_free_init);
+	init_llist_head(&init_free_list);
+	return 0;
+}
+module_init(modules_wq_init);
+
 /*
  * This is where the real work happens.
  *
@@ -3502,7 +3509,6 @@ static noinline int do_init_module(struct module *mod)
 #endif
 	module_enable_ro(mod, true);
 	mod_tree_remove_init(mod);
-	disable_ro_nx(&mod->init_layout);
 	module_arch_freeing_init(mod);
 	mod->init_layout.base = NULL;
 	mod->init_layout.size = 0;
@@ -3513,14 +3519,18 @@ static noinline int do_init_module(struct module *mod)
 	 * We want to free module_init, but be aware that kallsyms may be
 	 * walking this with preempt disabled.  In all the failure paths, we
 	 * call synchronize_rcu(), but we don't want to slow down the success
-	 * path, so use actual RCU here.
+	 * path. module_memfree() cannot be called in an interrupt, so do the
+	 * work and call synchronize_rcu() in a work queue.
+	 *
 	 * Note that module_alloc() on most architectures creates W+X page
 	 * mappings which won't be cleaned up until do_free_init() runs.  Any
 	 * code such as mark_rodata_ro() which depends on those mappings to
 	 * be cleaned up needs to sync with the queued work - ie
 	 * rcu_barrier()
 	 */
-	call_rcu(&freeinit->rcu, do_free_init);
+	if (llist_add(&freeinit->node, &init_free_list))
+		schedule_work(&init_free_wq);
+
 	mutex_unlock(&module_mutex);
 	wake_up_all(&module_wq);
 
@@ -3817,10 +3827,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	module_bug_cleanup(mod);
 	mutex_unlock(&module_mutex);
 
-	/* we can't deallocate the module until we clear memory protection */
-	module_disable_ro(mod);
-	module_disable_nx(mod);
-
  ddebug_cleanup:
 	ftrace_release_mod(mod);
 	dynamic_debug_remove(mod, info->debug);

kernel/power/snapshot.c

@@ -1342,8 +1342,9 @@ static inline void do_copy_page(long *dst, long *src)
  * safe_copy_page - Copy a page in a safe way.
  *
  * Check if the page we are going to copy is marked as present in the kernel
- * page tables (this always is the case if CONFIG_DEBUG_PAGEALLOC is not set
- * and in that case kernel_page_present() always returns 'true').
+ * page tables. This always is the case if CONFIG_DEBUG_PAGEALLOC or
+ * CONFIG_ARCH_HAS_SET_DIRECT_MAP is not set. In that case kernel_page_present()
+ * always returns 'true'.
  */
 static void safe_copy_page(void *dst, struct page *s_page)
 {

kernel/trace/bpf_trace.c

@@ -14,6 +14,8 @@
 #include <linux/syscalls.h>
 #include <linux/error-injection.h>
 
+#include <asm/tlb.h>
+
 #include "trace_probe.h"
 #include "trace.h"
 
@@ -163,6 +165,10 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 	 * access_ok() should prevent writing to non-user memory, but in
 	 * some situations (nommu, temporary switch, etc) access_ok() does
 	 * not provide enough validation, hence the check on KERNEL_DS.
+	 *
+	 * nmi_uaccess_okay() ensures the probe is not run in an interim
+	 * state, when the task or mm are switched. This is specifically
+	 * required to prevent the use of temporary mm.
 	 */
 
 	if (unlikely(in_interrupt() ||
@@ -170,6 +176,8 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 		return -EPERM;
 	if (unlikely(uaccess_kernel()))
 		return -EPERM;
+	if (unlikely(!nmi_uaccess_okay()))
+		return -EPERM;
 	if (!access_ok(unsafe_ptr, size))
 		return -EPERM;