Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "15 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  linux/kernel.h: fix overflow for DIV_ROUND_UP_ULL
  mm, swap: fix THP swap out
  fork,memcg: alloc_thread_stack_node needs to set tsk->stack
  MAINTAINERS: add CLANG/LLVM BUILD SUPPORT info
  mm/vmalloc.c: avoid bogus -Wmaybe-uninitialized warning
  mm/page_idle.c: fix oops because end_pfn is larger than max_pfn
  initramfs: fix populate_initrd_image() section mismatch
  mm/oom_kill.c: fix uninitialized oc->constraint
  mm: hugetlb: soft-offline: dissolve_free_huge_page() return zero on !PageHuge
  mm: soft-offline: return -EBUSY if set_hwpoison_free_buddy_page() fails
  signal: remove the wrong signal_pending() check in restore_user_sigmask()
  fs/binfmt_flat.c: make load_flat_shared_library() work
  mm/mempolicy.c: fix an incorrect rebind node in mpol_rebind_nodemask
  fs/proc/array.c: allow reporting eip/esp for all coredumping threads
  mm/dev_pfn: exclude MEMORY_DEVICE_PRIVATE while computing virtual address

MAINTAINERS

@@ -3942,6 +3942,14 @@ M:	Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
 S:	Maintained
 F:	.clang-format
 
+CLANG/LLVM BUILD SUPPORT
+L:	clang-built-linux@googlegroups.com
+W:	https://clangbuiltlinux.github.io/
+B:	https://github.com/ClangBuiltLinux/linux/issues
+C:	irc://chat.freenode.net/clangbuiltlinux
+S:	Supported
+K:	\b(?i:clang|llvm)\b
+
 CLEANCACHE API
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
 L:	linux-kernel@vger.kernel.org

fs/aio.c

@@ -2095,6 +2095,7 @@ SYSCALL_DEFINE6(io_pgetevents,
 	struct __aio_sigset	ksig = { NULL, };
 	sigset_t		ksigmask, sigsaved;
 	struct timespec64	ts;
+	bool interrupted;
 	int ret;
 
 	if (timeout && unlikely(get_timespec64(&ts, timeout)))
@@ -2108,8 +2109,10 @@ SYSCALL_DEFINE6(io_pgetevents,
 		return ret;
 
 	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
-	restore_user_sigmask(ksig.sigmask, &sigsaved);
-	if (signal_pending(current) && !ret)
+
+	interrupted = signal_pending(current);
+	restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted);
+	if (interrupted && !ret)
 		ret = -ERESTARTNOHAND;
 
 	return ret;
@@ -2128,6 +2131,7 @@ SYSCALL_DEFINE6(io_pgetevents_time32,
 	struct __aio_sigset	ksig = { NULL, };
 	sigset_t		ksigmask, sigsaved;
 	struct timespec64	ts;
+	bool interrupted;
 	int ret;
 
 	if (timeout && unlikely(get_old_timespec32(&ts, timeout)))
@@ -2142,8 +2146,10 @@ SYSCALL_DEFINE6(io_pgetevents_time32,
 		return ret;
 
 	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL);
-	restore_user_sigmask(ksig.sigmask, &sigsaved);
-	if (signal_pending(current) && !ret)
+
+	interrupted = signal_pending(current);
+	restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted);
+	if (interrupted && !ret)
 		ret = -ERESTARTNOHAND;
 
 	return ret;
@@ -2193,6 +2199,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents,
 	struct __compat_aio_sigset ksig = { NULL, };
 	sigset_t ksigmask, sigsaved;
 	struct timespec64 t;
+	bool interrupted;
 	int ret;
 
 	if (timeout && get_old_timespec32(&t, timeout))
@@ -2206,8 +2213,10 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents,
 		return ret;
 
 	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
-	restore_user_sigmask(ksig.sigmask, &sigsaved);
-	if (signal_pending(current) && !ret)
+
+	interrupted = signal_pending(current);
+	restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted);
+	if (interrupted && !ret)
 		ret = -ERESTARTNOHAND;
 
 	return ret;
@@ -2226,6 +2235,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64,
 	struct __compat_aio_sigset ksig = { NULL, };
 	sigset_t ksigmask, sigsaved;
 	struct timespec64 t;
+	bool interrupted;
 	int ret;
 
 	if (timeout && get_timespec64(&t, timeout))
@@ -2239,8 +2249,10 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64,
 		return ret;
 
 	ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL);
-	restore_user_sigmask(ksig.sigmask, &sigsaved);
-	if (signal_pending(current) && !ret)
+
+	interrupted = signal_pending(current);
+	restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted);
+	if (interrupted && !ret)
 		ret = -ERESTARTNOHAND;
 
 	return ret;

fs/binfmt_flat.c

@@ -856,9 +856,14 @@ static int load_flat_file(struct linux_binprm *bprm,
 
 static int load_flat_shared_library(int id, struct lib_info *libs)
 {
+	/*
+	 * This is a fake bprm struct; only the members "buf", "file" and
+	 * "filename" are actually used.
+	 */
 	struct linux_binprm bprm;
 	int res;
 	char buf[16];
+	loff_t pos = 0;
 
 	memset(&bprm, 0, sizeof(bprm));
 
@@ -872,25 +877,11 @@ static int load_flat_shared_library(int id, struct lib_info *libs)
 	if (IS_ERR(bprm.file))
 		return res;
 
-	bprm.cred = prepare_exec_creds();
-	res = -ENOMEM;
-	if (!bprm.cred)
-		goto out;
-
-	/* We don't really care about recalculating credentials at this point
-	 * as we're past the point of no return and are dealing with shared
-	 * libraries.
-	 */
-	bprm.called_set_creds = 1;
+	res = kernel_read(bprm.file, bprm.buf, BINPRM_BUF_SIZE, &pos);
 
-	res = prepare_binprm(&bprm);
-
-	if (!res)
+	if (res >= 0)
 		res = load_flat_file(&bprm, libs, id, NULL);
 
-	abort_creds(bprm.cred);
-
-out:
 	allow_write_access(bprm.file);
 	fput(bprm.file);
 

fs/eventpoll.c

@@ -2325,7 +2325,7 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events,
 
 	error = do_epoll_wait(epfd, events, maxevents, timeout);
 
-	restore_user_sigmask(sigmask, &sigsaved);
+	restore_user_sigmask(sigmask, &sigsaved, error == -EINTR);
 
 	return error;
 }
@@ -2350,7 +2350,7 @@ COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd,
 
 	err = do_epoll_wait(epfd, events, maxevents, timeout);
 
-	restore_user_sigmask(sigmask, &sigsaved);
+	restore_user_sigmask(sigmask, &sigsaved, err == -EINTR);
 
 	return err;
 }

fs/io_uring.c

@@ -2200,11 +2200,12 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 	}
 
 	ret = wait_event_interruptible(ctx->wait, io_cqring_events(ring) >= min_events);
-	if (ret == -ERESTARTSYS)
-		ret = -EINTR;
 
 	if (sig)
-		restore_user_sigmask(sig, &sigsaved);
+		restore_user_sigmask(sig, &sigsaved, ret == -ERESTARTSYS);
+
+	if (ret == -ERESTARTSYS)
+		ret = -EINTR;
 
 	return READ_ONCE(ring->r.head) == READ_ONCE(ring->r.tail) ? ret : 0;
 }

fs/proc/array.c

@@ -462,7 +462,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 		 * a program is not able to use ptrace(2) in that case. It is
 		 * safe because the task has stopped executing permanently.
 		 */
-		if (permitted && (task->flags & PF_DUMPCORE)) {
+		if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE))) {
 			if (try_get_task_stack(task)) {
 				eip = KSTK_EIP(task);
 				esp = KSTK_ESP(task);

fs/select.c

@@ -758,10 +758,9 @@ static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp,
 		return ret;
 
 	ret = core_sys_select(n, inp, outp, exp, to);
+	restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND);
 	ret = poll_select_copy_remaining(&end_time, tsp, type, ret);
 
-	restore_user_sigmask(sigmask, &sigsaved);
-
 	return ret;
 }
 
@@ -1106,8 +1105,7 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
 
 	ret = do_sys_poll(ufds, nfds, to);
 
-	restore_user_sigmask(sigmask, &sigsaved);
-
+	restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR);
 	/* We can restart this syscall, usually */
 	if (ret == -EINTR)
 		ret = -ERESTARTNOHAND;
@@ -1142,8 +1140,7 @@ SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds,
 
 	ret = do_sys_poll(ufds, nfds, to);
 
-	restore_user_sigmask(sigmask, &sigsaved);
-
+	restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR);
 	/* We can restart this syscall, usually */
 	if (ret == -EINTR)
 		ret = -ERESTARTNOHAND;
@@ -1350,10 +1347,9 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp,
 		return ret;
 
 	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND);
 	ret = poll_select_copy_remaining(&end_time, tsp, type, ret);
 
-	restore_user_sigmask(sigmask, &sigsaved);
-
 	return ret;
 }
 
@@ -1425,8 +1421,7 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds,
 
 	ret = do_sys_poll(ufds, nfds, to);
 
-	restore_user_sigmask(sigmask, &sigsaved);
-
+	restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR);
 	/* We can restart this syscall, usually */
 	if (ret == -EINTR)
 		ret = -ERESTARTNOHAND;
@@ -1461,8 +1456,7 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds,
 
 	ret = do_sys_poll(ufds, nfds, to);
 
-	restore_user_sigmask(sigmask, &sigsaved);
-
+	restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR);
 	/* We can restart this syscall, usually */
 	if (ret == -EINTR)
 		ret = -ERESTARTNOHAND;

include/linux/kernel.h

@@ -93,7 +93,8 @@
 #define DIV_ROUND_DOWN_ULL(ll, d) \
 	({ unsigned long long _tmp = (ll); do_div(_tmp, d); _tmp; })
 
-#define DIV_ROUND_UP_ULL(ll, d)		DIV_ROUND_DOWN_ULL((ll) + (d) - 1, (d))
+#define DIV_ROUND_UP_ULL(ll, d) \
+	DIV_ROUND_DOWN_ULL((unsigned long long)(ll) + (d) - 1, (d))
 
 #if BITS_PER_LONG == 32
 # define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP_ULL(ll, d)

include/linux/pfn_t.h

@@ -68,7 +68,7 @@ static inline phys_addr_t pfn_t_to_phys(pfn_t pfn)
 
 static inline void *pfn_t_to_virt(pfn_t pfn)
 {
-	if (pfn_t_has_page(pfn))
+	if (pfn_t_has_page(pfn) && !is_device_private_page(pfn_t_to_page(pfn)))
 		return __va(pfn_t_to_phys(pfn));
 	return NULL;
 }

include/linux/signal.h

@@ -276,7 +276,7 @@ extern int sigprocmask(int, sigset_t *, sigset_t *);
 extern int set_user_sigmask(const sigset_t __user *usigmask, sigset_t *set,
 	sigset_t *oldset, size_t sigsetsize);
 extern void restore_user_sigmask(const void __user *usigmask,
-				 sigset_t *sigsaved);
+				 sigset_t *sigsaved, bool interrupted);
 extern void set_current_blocked(sigset_t *);
 extern void __set_current_blocked(const sigset_t *);
 extern int show_unhandled_signals;

init/initramfs.c

@@ -617,7 +617,7 @@ static inline void clean_rootfs(void)
 #endif /* CONFIG_BLK_DEV_RAM */
 
 #ifdef CONFIG_BLK_DEV_RAM
-static void populate_initrd_image(char *err)
+static void __init populate_initrd_image(char *err)
 {
 	ssize_t written;
 	int fd;
@@ -637,7 +637,7 @@ static void populate_initrd_image(char *err)
 	ksys_close(fd);
 }
 #else
-static void populate_initrd_image(char *err)
+static void __init populate_initrd_image(char *err)
 {
 	printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err);
 }

kernel/fork.c

@@ -248,7 +248,11 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 	struct page *page = alloc_pages_node(node, THREADINFO_GFP,
 					     THREAD_SIZE_ORDER);
 
-	return page ? page_address(page) : NULL;
+	if (likely(page)) {
+		tsk->stack = page_address(page);
+		return tsk->stack;
+	}
+	return NULL;
 #endif
 }
 

kernel/signal.c

@@ -2912,7 +2912,8 @@ EXPORT_SYMBOL(set_compat_user_sigmask);
  * This is useful for syscalls such as ppoll, pselect, io_pgetevents and
  * epoll_pwait where a new sigmask is passed in from userland for the syscalls.
  */
-void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved)
+void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved,
+				bool interrupted)
 {
 
 	if (!usigmask)
@@ -2922,7 +2923,7 @@ void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved)
 	 * Restoring sigmask here can lead to delivering signals that the above
 	 * syscalls are intended to block because of the sigmask passed in.
 	 */
-	if (signal_pending(current)) {
+	if (interrupted) {
 		current->saved_sigmask = *sigsaved;
 		set_restore_sigmask();
 		return;

mm/hugetlb.c

@@ -1510,16 +1510,29 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 
 /*
  * Dissolve a given free hugepage into free buddy pages. This function does
- * nothing for in-use (including surplus) hugepages. Returns -EBUSY if the
- * dissolution fails because a give page is not a free hugepage, or because
- * free hugepages are fully reserved.
+ * nothing for in-use hugepages and non-hugepages.
+ * This function returns values like below:
+ *
+ *  -EBUSY: failed to dissolved free hugepages or the hugepage is in-use
+ *          (allocated or reserved.)
+ *       0: successfully dissolved free hugepages or the page is not a
+ *          hugepage (considered as already dissolved)
  */
 int dissolve_free_huge_page(struct page *page)
 {
 	int rc = -EBUSY;
 
+	/* Not to disrupt normal path by vainly holding hugetlb_lock */
+	if (!PageHuge(page))
+		return 0;
+
 	spin_lock(&hugetlb_lock);
-	if (PageHuge(page) && !page_count(page)) {
+	if (!PageHuge(page)) {
+		rc = 0;
+		goto out;
+	}
+
+	if (!page_count(page)) {
 		struct page *head = compound_head(page);
 		struct hstate *h = page_hstate(head);
 		int nid = page_to_nid(head);
@@ -1564,12 +1577,10 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) {
 		page = pfn_to_page(pfn);
-		if (PageHuge(page) && !page_count(page)) {
 		rc = dissolve_free_huge_page(page);
 		if (rc)
 			break;
 	}
-	}
 
 	return rc;
 }

mm/memory-failure.c

@@ -1730,6 +1730,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
 		if (!ret) {
 			if (set_hwpoison_free_buddy_page(page))
 				num_poisoned_pages_inc();
+			else
+				ret = -EBUSY;
 		}
 	}
 	return ret;
@@ -1854,11 +1856,8 @@ static int soft_offline_in_use_page(struct page *page, int flags)
 
 static int soft_offline_free_page(struct page *page)
 {
-	int rc = 0;
-	struct page *head = compound_head(page);
+	int rc = dissolve_free_huge_page(page);
 
-	if (PageHuge(head))
-		rc = dissolve_free_huge_page(page);
 	if (!rc) {
 		if (set_hwpoison_free_buddy_page(page))
 			num_poisoned_pages_inc();

mm/mempolicy.c

@@ -306,7 +306,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
 	else {
 		nodes_remap(tmp, pol->v.nodes,pol->w.cpuset_mems_allowed,
 								*nodes);
-		pol->w.cpuset_mems_allowed = tmp;
+		pol->w.cpuset_mems_allowed = *nodes;
 	}
 
 	if (nodes_empty(tmp))

mm/oom_kill.c

@@ -987,8 +987,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 /*
  * Determines whether the kernel must panic because of the panic_on_oom sysctl.
  */
-static void check_panic_on_oom(struct oom_control *oc,
-			       enum oom_constraint constraint)
+static void check_panic_on_oom(struct oom_control *oc)
 {
 	if (likely(!sysctl_panic_on_oom))
 		return;
@@ -998,7 +997,7 @@ static void check_panic_on_oom(struct oom_control *oc,
 		 * does not panic for cpuset, mempolicy, or memcg allocation
 		 * failures.
 		 */
-		if (constraint != CONSTRAINT_NONE)
+		if (oc->constraint != CONSTRAINT_NONE)
 			return;
 	}
 	/* Do not panic for oom kills triggered by sysrq */
@@ -1035,7 +1034,6 @@ EXPORT_SYMBOL_GPL(unregister_oom_notifier);
 bool out_of_memory(struct oom_control *oc)
 {
 	unsigned long freed = 0;
-	enum oom_constraint constraint = CONSTRAINT_NONE;
 
 	if (oom_killer_disabled)
 		return false;
@@ -1071,10 +1069,10 @@ bool out_of_memory(struct oom_control *oc)
 	 * Check if there were limitations on the allocation (only relevant for
 	 * NUMA and memcg) that may require different handling.
 	 */
-	constraint = constrained_alloc(oc);
-	if (constraint != CONSTRAINT_MEMORY_POLICY)
+	oc->constraint = constrained_alloc(oc);
+	if (oc->constraint != CONSTRAINT_MEMORY_POLICY)
 		oc->nodemask = NULL;
-	check_panic_on_oom(oc, constraint);
+	check_panic_on_oom(oc);
 
 	if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task &&
 	    current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) &&

mm/page_idle.c

@@ -136,7 +136,7 @@ static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj,
 
 	end_pfn = pfn + count * BITS_PER_BYTE;
 	if (end_pfn > max_pfn)
-		end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS);
+		end_pfn = max_pfn;
 
 	for (; pfn < end_pfn; pfn++) {
 		bit = pfn % BITMAP_CHUNK_BITS;
@@ -181,7 +181,7 @@ static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj,
 
 	end_pfn = pfn + count * BITS_PER_BYTE;
 	if (end_pfn > max_pfn)
-		end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS);
+		end_pfn = max_pfn;
 
 	for (; pfn < end_pfn; pfn++) {
 		bit = pfn % BITMAP_CHUNK_BITS;

mm/page_io.c

@@ -29,10 +29,9 @@
 static struct bio *get_swap_bio(gfp_t gfp_flags,
 				struct page *page, bio_end_io_t end_io)
 {
-	int i, nr = hpage_nr_pages(page);
 	struct bio *bio;
 
-	bio = bio_alloc(gfp_flags, nr);
+	bio = bio_alloc(gfp_flags, 1);
 	if (bio) {
 		struct block_device *bdev;
 
@@ -41,9 +40,7 @@ static struct bio *get_swap_bio(gfp_t gfp_flags,
 		bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
 		bio->bi_end_io = end_io;
 
-		for (i = 0; i < nr; i++)
-			bio_add_page(bio, page + i, PAGE_SIZE, 0);
-		VM_BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE * nr);
+		bio_add_page(bio, page, PAGE_SIZE * hpage_nr_pages(page), 0);
 	}
 	return bio;
 }

mm/vmalloc.c

@@ -913,7 +913,7 @@ adjust_va_to_fit_type(struct vmap_area *va,
 	unsigned long nva_start_addr, unsigned long size,
 	enum fit_type type)
 {
-	struct vmap_area *lva;
+	struct vmap_area *lva = NULL;
 
 	if (type == FL_FIT_TYPE) {
 		/*
@@ -972,7 +972,7 @@ adjust_va_to_fit_type(struct vmap_area *va,
 	if (type != FL_FIT_TYPE) {
 		augment_tree_propagate_from(va);
 
-		if (type == NE_FIT_TYPE)
+		if (lva)	/* type == NE_FIT_TYPE */
 			insert_vmap_area_augment(lva, &va->rb_node,
 				&free_vmap_area_root, &free_vmap_area_list);
 	}