Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:

 - most of the rest of MM (memcg, hugetlb, vmscan, proc, compaction,
   mempolicy, oom-kill, hugetlbfs, migration, thp, cma, util,
   memory-hotplug, cleanups, uaccess, migration, gup, pagemap),

 - various other subsystems (alpha, misc, sparse, bitmap, lib, bitops,
   checkpatch, autofs, minix, nilfs, ufs, fat, signals, kmod, coredump,
   exec, kdump, rapidio, panic, kcov, kgdb, ipc).

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (164 commits)
  mm/gup: remove task_struct pointer for all gup code
  mm: clean up the last pieces of page fault accountings
  mm/xtensa: use general page fault accounting
  mm/x86: use general page fault accounting
  mm/sparc64: use general page fault accounting
  mm/sparc32: use general page fault accounting
  mm/sh: use general page fault accounting
  mm/s390: use general page fault accounting
  mm/riscv: use general page fault accounting
  mm/powerpc: use general page fault accounting
  mm/parisc: use general page fault accounting
  mm/openrisc: use general page fault accounting
  mm/nios2: use general page fault accounting
  mm/nds32: use general page fault accounting
  mm/mips: use general page fault accounting
  mm/microblaze: use general page fault accounting
  mm/m68k: use general page fault accounting
  mm/ia64: use general page fault accounting
  mm/hexagon: use general page fault accounting
  mm/csky: use general page fault accounting
  ...

kernel/Makefile

@@ -36,7 +36,7 @@ KCOV_INSTRUMENT_stacktrace.o := n
 KCOV_INSTRUMENT_kcov.o := n
 KASAN_SANITIZE_kcov.o := n
 KCSAN_SANITIZE_kcov.o := n
-CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
+CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack) -fno-stack-protector
 
 # cond_syscall is currently not LTO compatible
 CFLAGS_sys_ni.o = $(DISABLE_LTO)

kernel/crash_core.c

@@ -11,6 +11,8 @@
 #include <asm/page.h>
 #include <asm/sections.h>
 
+#include <crypto/sha.h>
+
 /* vmcoreinfo stuff */
 unsigned char *vmcoreinfo_data;
 size_t vmcoreinfo_size;
@@ -376,6 +378,53 @@ phys_addr_t __weak paddr_vmcoreinfo_note(void)
 }
 EXPORT_SYMBOL(paddr_vmcoreinfo_note);
 
+#define NOTES_SIZE (&__stop_notes - &__start_notes)
+#define BUILD_ID_MAX SHA1_DIGEST_SIZE
+#define NT_GNU_BUILD_ID 3
+
+struct elf_note_section {
+	struct elf_note	n_hdr;
+	u8 n_data[];
+};
+
+/*
+ * Add build ID from .notes section as generated by the GNU ld(1)
+ * or LLVM lld(1) --build-id option.
+ */
+static void add_build_id_vmcoreinfo(void)
+{
+	char build_id[BUILD_ID_MAX * 2 + 1];
+	int n_remain = NOTES_SIZE;
+
+	while (n_remain >= sizeof(struct elf_note)) {
+		const struct elf_note_section *note_sec =
+			&__start_notes + NOTES_SIZE - n_remain;
+		const u32 n_namesz = note_sec->n_hdr.n_namesz;
+
+		if (note_sec->n_hdr.n_type == NT_GNU_BUILD_ID &&
+		    n_namesz != 0 &&
+		    !strcmp((char *)&note_sec->n_data[0], "GNU")) {
+			if (note_sec->n_hdr.n_descsz <= BUILD_ID_MAX) {
+				const u32 n_descsz = note_sec->n_hdr.n_descsz;
+				const u8 *s = &note_sec->n_data[n_namesz];
+
+				s = PTR_ALIGN(s, 4);
+				bin2hex(build_id, s, n_descsz);
+				build_id[2 * n_descsz] = '\0';
+				VMCOREINFO_BUILD_ID(build_id);
+				return;
+			}
+			pr_warn("Build ID is too large to include in vmcoreinfo: %u > %u\n",
+				note_sec->n_hdr.n_descsz,
+				BUILD_ID_MAX);
+			return;
+		}
+		n_remain -= sizeof(struct elf_note) +
+			ALIGN(note_sec->n_hdr.n_namesz, 4) +
+			ALIGN(note_sec->n_hdr.n_descsz, 4);
+	}
+}
+
 static int __init crash_save_vmcoreinfo_init(void)
 {
 	vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
@@ -394,6 +443,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	}
 
 	VMCOREINFO_OSRELEASE(init_uts_ns.name.release);
+	add_build_id_vmcoreinfo();
 	VMCOREINFO_PAGESIZE(PAGE_SIZE);
 
 	VMCOREINFO_SYMBOL(init_uts_ns);

kernel/events/callchain.c

@@ -217,10 +217,9 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 			if (add_mark)
 				perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
 
-			fs = get_fs();
-			set_fs(USER_DS);
+			fs = force_uaccess_begin();
 			perf_callchain_user(&ctx, regs);
-			set_fs(fs);
+			force_uaccess_end(fs);
 		}
 	}
 

kernel/events/core.c

@@ -6453,10 +6453,9 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
 
 		/* Data. */
 		sp = perf_user_stack_pointer(regs);
-		fs = get_fs();
-		set_fs(USER_DS);
+		fs = force_uaccess_begin();
 		rem = __output_copy_user(handle, (void *) sp, dump_size);
-		set_fs(fs);
+		force_uaccess_end(fs);
 		dyn_size = dump_size - rem;
 
 		perf_output_skip(handle, rem);

kernel/events/uprobes.c

@@ -184,7 +184,7 @@ 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);
-		lru_cache_add_active_or_unevictable(new_page, vma);
+		lru_cache_add_inactive_or_unevictable(new_page, vma);
 	} else
 		/* no new page, just dec_mm_counter for old_page */
 		dec_mm_counter(mm, MM_ANONPAGES);
@@ -376,7 +376,7 @@ __update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d)
 	if (!vaddr || !d)
 		return -EINVAL;
 
-	ret = get_user_pages_remote(NULL, mm, vaddr, 1,
+	ret = get_user_pages_remote(mm, vaddr, 1,
 			FOLL_WRITE, &page, &vma, NULL);
 	if (unlikely(ret <= 0)) {
 		/*
@@ -477,7 +477,7 @@ retry:
 	if (is_register)
 		gup_flags |= FOLL_SPLIT_PMD;
 	/* Read the page with vaddr into memory */
-	ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags,
+	ret = get_user_pages_remote(mm, vaddr, 1, gup_flags,
 				    &old_page, &vma, NULL);
 	if (ret <= 0)
 		return ret;
@@ -2029,7 +2029,7 @@ static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr)
 	 * but we treat this as a 'remote' access since it is
 	 * essentially a kernel access to the memory.
 	 */
-	result = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &page,
+	result = get_user_pages_remote(mm, vaddr, 1, FOLL_FORCE, &page,
 			NULL, NULL);
 	if (result < 0)
 		return result;

kernel/exit.c

@@ -732,7 +732,7 @@ void __noreturn do_exit(long code)
 	 * mm_release()->clear_child_tid() from writing to a user-controlled
 	 * kernel address.
 	 */
-	set_fs(USER_DS);
+	force_uaccess_begin();
 
 	if (unlikely(in_atomic())) {
 		pr_info("note: %s[%d] exited with preempt_count %d\n",
@@ -1626,6 +1626,22 @@ long kernel_wait4(pid_t upid, int __user *stat_addr, int options,
 	return ret;
 }
 
+int kernel_wait(pid_t pid, int *stat)
+{
+	struct wait_opts wo = {
+		.wo_type	= PIDTYPE_PID,
+		.wo_pid		= find_get_pid(pid),
+		.wo_flags	= WEXITED,
+	};
+	int ret;
+
+	ret = do_wait(&wo);
+	if (ret > 0 && wo.wo_stat)
+		*stat = wo.wo_stat;
+	put_pid(wo.wo_pid);
+	return ret;
+}
+
 SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
 		int, options, struct rusage __user *, ru)
 {

kernel/futex.c

@@ -678,7 +678,7 @@ static int fault_in_user_writeable(u32 __user *uaddr)
 	int ret;
 
 	mmap_read_lock(mm);
-	ret = fixup_user_fault(current, mm, (unsigned long)uaddr,
+	ret = fixup_user_fault(mm, (unsigned long)uaddr,
 			       FAULT_FLAG_WRITE, NULL);
 	mmap_read_unlock(mm);
 

kernel/kcov.c

@@ -96,7 +96,7 @@ struct kcov_percpu_data {
 	int			saved_sequence;
 };
 
-DEFINE_PER_CPU(struct kcov_percpu_data, kcov_percpu_data);
+static DEFINE_PER_CPU(struct kcov_percpu_data, kcov_percpu_data);
 
 /* Must be called with kcov_remote_lock locked. */
 static struct kcov_remote *kcov_remote_find(u64 handle)
@@ -775,7 +775,7 @@ static inline bool kcov_mode_enabled(unsigned int mode)
 	return (mode & ~KCOV_IN_CTXSW) != KCOV_MODE_DISABLED;
 }
 
-void kcov_remote_softirq_start(struct task_struct *t)
+static void kcov_remote_softirq_start(struct task_struct *t)
 {
 	struct kcov_percpu_data *data = this_cpu_ptr(&kcov_percpu_data);
 	unsigned int mode;
@@ -792,7 +792,7 @@ void kcov_remote_softirq_start(struct task_struct *t)
 	}
 }
 
-void kcov_remote_softirq_stop(struct task_struct *t)
+static void kcov_remote_softirq_stop(struct task_struct *t)
 {
 	struct kcov_percpu_data *data = this_cpu_ptr(&kcov_percpu_data);
 

kernel/kmod.c

@@ -36,9 +36,8 @@
  *
  * If you need less than 50 threads would mean we're dealing with systems
  * smaller than 3200 pages. This assumes you are capable of having ~13M memory,
- * and this would only be an be an upper limit, after which the OOM killer
- * would take effect. Systems like these are very unlikely if modules are
- * enabled.
+ * and this would only be an upper limit, after which the OOM killer would take
+ * effect. Systems like these are very unlikely if modules are enabled.
  */
 #define MAX_KMOD_CONCURRENT 50
 static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT);

kernel/kthread.c

@@ -1258,8 +1258,7 @@ void kthread_use_mm(struct mm_struct *mm)
 	if (active_mm != mm)
 		mmdrop(active_mm);
 
-	to_kthread(tsk)->oldfs = get_fs();
-	set_fs(USER_DS);
+	to_kthread(tsk)->oldfs = force_uaccess_begin();
 }
 EXPORT_SYMBOL_GPL(kthread_use_mm);
 
@@ -1274,7 +1273,7 @@ void kthread_unuse_mm(struct mm_struct *mm)
 	WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD));
 	WARN_ON_ONCE(!tsk->mm);
 
-	set_fs(to_kthread(tsk)->oldfs);
+	force_uaccess_end(to_kthread(tsk)->oldfs);
 
 	task_lock(tsk);
 	sync_mm_rss(mm);

kernel/panic.c

@@ -505,7 +505,7 @@ static void do_oops_enter_exit(void)
  * Return true if the calling CPU is allowed to print oops-related info.
  * This is a bit racy..
  */
-int oops_may_print(void)
+bool oops_may_print(void)
 {
 	return pause_on_oops_flag == 0;
 }
@@ -551,7 +551,7 @@ static int init_oops_id(void)
 }
 late_initcall(init_oops_id);
 
-void print_oops_end_marker(void)
+static void print_oops_end_marker(void)
 {
 	init_oops_id();
 	pr_warn("---[ end trace %016llx ]---\n", (unsigned long long)oops_id);

kernel/stacktrace.c

@@ -233,10 +233,9 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
 	if (current->flags & PF_KTHREAD)
 		return 0;
 
-	fs = get_fs();
-	set_fs(USER_DS);
+	fs = force_uaccess_begin();
 	arch_stack_walk_user(consume_entry, &c, task_pt_regs(current));
-	set_fs(fs);
+	force_uaccess_end(fs);
 
 	return c.len;
 }

kernel/sysctl.c

@@ -2851,6 +2851,15 @@ static struct ctl_table vm_table[] = {
 		.mode		= 0200,
 		.proc_handler	= sysctl_compaction_handler,
 	},
+	{
+		.procname	= "compaction_proactiveness",
+		.data		= &sysctl_compaction_proactiveness,
+		.maxlen		= sizeof(sysctl_compaction_proactiveness),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &one_hundred,
+	},
 	{
 		.procname	= "extfrag_threshold",
 		.data		= &sysctl_extfrag_threshold,

kernel/umh.c

@@ -119,37 +119,16 @@ static void call_usermodehelper_exec_sync(struct subprocess_info *sub_info)
 {
 	pid_t pid;
 
-	/* If SIGCLD is ignored kernel_wait4 won't populate the status. */
+	/* If SIGCLD is ignored do_wait won't populate the status. */
 	kernel_sigaction(SIGCHLD, SIG_DFL);
 	pid = kernel_thread(call_usermodehelper_exec_async, sub_info, SIGCHLD);
-	if (pid < 0) {
+	if (pid < 0)
 		sub_info->retval = pid;
-	} else {
-		int ret = -ECHILD;
-		/*
-		 * Normally it is bogus to call wait4() from in-kernel because
-		 * wait4() wants to write the exit code to a userspace address.
-		 * But call_usermodehelper_exec_sync() always runs as kernel
-		 * thread (workqueue) and put_user() to a kernel address works
-		 * OK for kernel threads, due to their having an mm_segment_t
-		 * which spans the entire address space.
-		 *
-		 * Thus the __user pointer cast is valid here.
-		 */
-		kernel_wait4(pid, (int __user *)&ret, 0, NULL);
-
-		/*
-		 * If ret is 0, either call_usermodehelper_exec_async failed and
-		 * the real error code is already in sub_info->retval or
-		 * sub_info->retval is 0 anyway, so don't mess with it then.
-		 */
-		if (ret)
-			sub_info->retval = ret;
-	}
+	else
+		kernel_wait(pid, &sub_info->retval);
 
 	/* Restore default kernel sig handler */
 	kernel_sigaction(SIGCHLD, SIG_IGN);
-
 	umh_complete(sub_info);
 }