Merge tag 'v5.5-rc4' into locking/kcsan, to resolve conflicts

Conflicts:
	init/main.c
	lib/Kconfig.debug

Signed-off-by: Ingo Molnar <mingo@kernel.org>

init/Kconfig

@@ -104,29 +104,9 @@ config COMPILE_TEST
 	  here. If you are a user/distributor, say N here to exclude useless
 	  drivers to be distributed.
 
-config HEADER_TEST
-	bool "Compile test headers that should be standalone compilable"
-	help
-	  Compile test headers listed in header-test-y target to ensure they are
-	  self-contained, i.e. compilable as standalone units.
-
-	  If you are a developer or tester and want to ensure the requested
-	  headers are self-contained, say Y here. Otherwise, choose N.
-
-config KERNEL_HEADER_TEST
-	bool "Compile test kernel headers"
-	depends on HEADER_TEST
-	help
-	  Headers in include/ are used to build external moduls.
-	  Compile test them to ensure they are self-contained, i.e.
-	  compilable as standalone units.
-
-	  If you are a developer or tester and want to ensure the headers
-	  in include/ are self-contained, say Y here. Otherwise, choose N.
-
 config UAPI_HEADER_TEST
 	bool "Compile test UAPI headers"
-	depends on HEADER_TEST && HEADERS_INSTALL && CC_CAN_LINK
+	depends on HEADERS_INSTALL && CC_CAN_LINK
 	help
 	  Compile test headers exported to user-space to ensure they are
 	  self-contained, i.e. compilable as standalone units.
@@ -166,13 +146,13 @@ config LOCALVERSION_AUTO
 	  which is done within the script "scripts/setlocalversion".)
 
 config BUILD_SALT
-       string "Build ID Salt"
-       default ""
-       help
-          The build ID is used to link binaries and their debug info. Setting
-          this option will use the value in the calculation of the build id.
-          This is mostly useful for distributions which want to ensure the
-          build is unique between builds. It's safe to leave the default.
+	string "Build ID Salt"
+	default ""
+	help
+	  The build ID is used to link binaries and their debug info. Setting
+	  this option will use the value in the calculation of the build id.
+	  This is mostly useful for distributions which want to ensure the
+	  build is unique between builds. It's safe to leave the default.
 
 config HAVE_KERNEL_GZIP
 	bool
@@ -785,6 +765,10 @@ config ARCH_SUPPORTS_NUMA_BALANCING
 config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	bool
 
+config CC_HAS_INT128
+	def_bool y
+	depends on !$(cc-option,-D__SIZEOF_INT128__=0)
+
 #
 # For architectures that know their GCC __int128 support is sound
 #
@@ -834,7 +818,7 @@ menuconfig CGROUPS
 if CGROUPS
 
 config PAGE_COUNTER
-       bool
+	bool
 
 config MEMCG
 	bool "Memory controller"
@@ -1327,9 +1311,9 @@ menuconfig EXPERT
 	select DEBUG_KERNEL
 	help
 	  This option allows certain base kernel options and settings
-          to be disabled or tweaked. This is for specialized
-          environments which can tolerate a "non-standard" kernel.
-          Only use this if you really know what you are doing.
+	  to be disabled or tweaked. This is for specialized
+	  environments which can tolerate a "non-standard" kernel.
+	  Only use this if you really know what you are doing.
 
 config UID16
 	bool "Enable 16-bit UID system calls" if EXPERT
@@ -1372,23 +1356,6 @@ config SYSFS_SYSCALL
 
 	  If unsure say Y here.
 
-config SYSCTL_SYSCALL
-	bool "Sysctl syscall support" if EXPERT
-	depends on PROC_SYSCTL
-	default n
-	select SYSCTL
-	---help---
-	  sys_sysctl uses binary paths that have been found challenging
-	  to properly maintain and use.  The interface in /proc/sys
-	  using paths with ascii names is now the primary path to this
-	  information.
-
-	  Almost nothing using the binary sysctl interface so if you are
-	  trying to save some space it is probably safe to disable this,
-	  making your kernel marginally smaller.
-
-	  If unsure say N here.
-
 config FHANDLE
 	bool "open by fhandle syscalls" if EXPERT
 	select EXPORTFS
@@ -1439,11 +1406,11 @@ config BUG
 	bool "BUG() support" if EXPERT
 	default y
 	help
-          Disabling this option eliminates support for BUG and WARN, reducing
-          the size of your kernel image and potentially quietly ignoring
-          numerous fatal conditions. You should only consider disabling this
-          option for embedded systems with no facilities for reporting errors.
-          Just say Y.
+	  Disabling this option eliminates support for BUG and WARN, reducing
+	  the size of your kernel image and potentially quietly ignoring
+	  numerous fatal conditions. You should only consider disabling this
+	  option for embedded systems with no facilities for reporting errors.
+	  Just say Y.
 
 config ELF_CORE
 	depends on COREDUMP
@@ -1459,8 +1426,8 @@ config PCSPKR_PLATFORM
 	select I8253_LOCK
 	default y
 	help
-          This option allows to disable the internal PC-Speaker
-          support, saving some memory.
+	  This option allows to disable the internal PC-Speaker
+	  support, saving some memory.
 
 config BASE_FULL
 	default y
@@ -1548,6 +1515,7 @@ config AIO
 config IO_URING
 	bool "Enable IO uring support" if EXPERT
 	select ANON_INODES
+	select IO_WQ
 	default y
 	help
 	  This option enables support for the io_uring interface, enabling
@@ -1577,29 +1545,29 @@ config MEMBARRIER
 	  If unsure, say Y.
 
 config KALLSYMS
-	 bool "Load all symbols for debugging/ksymoops" if EXPERT
-	 default y
-	 help
-	   Say Y here to let the kernel print out symbolic crash information and
-	   symbolic stack backtraces. This increases the size of the kernel
-	   somewhat, as all symbols have to be loaded into the kernel image.
+	bool "Load all symbols for debugging/ksymoops" if EXPERT
+	default y
+	help
+	  Say Y here to let the kernel print out symbolic crash information and
+	  symbolic stack backtraces. This increases the size of the kernel
+	  somewhat, as all symbols have to be loaded into the kernel image.
 
 config KALLSYMS_ALL
 	bool "Include all symbols in kallsyms"
 	depends on DEBUG_KERNEL && KALLSYMS
 	help
-	   Normally kallsyms only contains the symbols of functions for nicer
-	   OOPS messages and backtraces (i.e., symbols from the text and inittext
-	   sections). This is sufficient for most cases. And only in very rare
-	   cases (e.g., when a debugger is used) all symbols are required (e.g.,
-	   names of variables from the data sections, etc).
+	  Normally kallsyms only contains the symbols of functions for nicer
+	  OOPS messages and backtraces (i.e., symbols from the text and inittext
+	  sections). This is sufficient for most cases. And only in very rare
+	  cases (e.g., when a debugger is used) all symbols are required (e.g.,
+	  names of variables from the data sections, etc).
 
-	   This option makes sure that all symbols are loaded into the kernel
-	   image (i.e., symbols from all sections) in cost of increased kernel
-	   size (depending on the kernel configuration, it may be 300KiB or
-	   something like this).
+	  This option makes sure that all symbols are loaded into the kernel
+	  image (i.e., symbols from all sections) in cost of increased kernel
+	  size (depending on the kernel configuration, it may be 300KiB or
+	  something like this).
 
-	   Say N unless you really need all symbols.
+	  Say N unless you really need all symbols.
 
 config KALLSYMS_ABSOLUTE_PERCPU
 	bool
@@ -1742,12 +1710,12 @@ config DEBUG_PERF_USE_VMALLOC
 	depends on PERF_EVENTS && DEBUG_KERNEL && !PPC
 	select PERF_USE_VMALLOC
 	help
-	 Use vmalloc memory to back perf mmap() buffers.
+	  Use vmalloc memory to back perf mmap() buffers.
 
-	 Mostly useful for debugging the vmalloc code on platforms
-	 that don't require it.
+	  Mostly useful for debugging the vmalloc code on platforms
+	  that don't require it.
 
-	 Say N if unsure.
+	  Say N if unsure.
 
 endmenu
 

init/do_mounts.c

@@ -212,6 +212,7 @@ static int match_dev_by_label(struct device *dev, const void *data)
  *	   a colon.
  *	9) PARTLABEL=<name> with name being the GPT partition label.
  *	   MSDOS partitions do not support labels!
+ *	10) /dev/cifs represents Root_CIFS (0xfe)
  *
  *	If name doesn't have fall into the categories above, we return (0,0).
  *	block_class is used to check if something is a disk name. If the disk
@@ -268,6 +269,9 @@ dev_t name_to_dev_t(const char *name)
 	res = Root_NFS;
 	if (strcmp(name, "nfs") == 0)
 		goto done;
+	res = Root_CIFS;
+	if (strcmp(name, "cifs") == 0)
+		goto done;
 	res = Root_RAM0;
 	if (strcmp(name, "ram") == 0)
 		goto done;
@@ -383,12 +387,27 @@ static void __init get_fs_names(char *page)
 	*s = '\0';
 }
 
-static int __init do_mount_root(char *name, char *fs, int flags, void *data)
+static int __init do_mount_root(const char *name, const char *fs,
+				 const int flags, const void *data)
 {
 	struct super_block *s;
-	int err = ksys_mount(name, "/root", fs, flags, data);
-	if (err)
-		return err;
+	struct page *p = NULL;
+	char *data_page = NULL;
+	int ret;
+
+	if (data) {
+		/* do_mount() requires a full page as fifth argument */
+		p = alloc_page(GFP_KERNEL);
+		if (!p)
+			return -ENOMEM;
+		data_page = page_address(p);
+		/* zero-pad. do_mount() will make sure it's terminated */
+		strncpy(data_page, data, PAGE_SIZE);
+	}
+
+	ret = do_mount(name, "/root", fs, flags, data_page);
+	if (ret)
+		goto out;
 
 	ksys_chdir("/root");
 	s = current->fs->pwd.dentry->d_sb;
@@ -398,7 +417,11 @@ static int __init do_mount_root(char *name, char *fs, int flags, void *data)
 	       s->s_type->name,
 	       sb_rdonly(s) ? " readonly" : "",
 	       MAJOR(ROOT_DEV), MINOR(ROOT_DEV));
-	return 0;
+
+out:
+	if (p)
+		put_page(p);
+	return ret;
 }
 
 void __init mount_block_root(char *name, int flags)
@@ -501,6 +524,42 @@ static int __init mount_nfs_root(void)
 }
 #endif
 
+#ifdef CONFIG_CIFS_ROOT
+
+extern int cifs_root_data(char **dev, char **opts);
+
+#define CIFSROOT_TIMEOUT_MIN	5
+#define CIFSROOT_TIMEOUT_MAX	30
+#define CIFSROOT_RETRY_MAX	5
+
+static int __init mount_cifs_root(void)
+{
+	char *root_dev, *root_data;
+	unsigned int timeout;
+	int try, err;
+
+	err = cifs_root_data(&root_dev, &root_data);
+	if (err != 0)
+		return 0;
+
+	timeout = CIFSROOT_TIMEOUT_MIN;
+	for (try = 1; ; try++) {
+		err = do_mount_root(root_dev, "cifs", root_mountflags,
+				    root_data);
+		if (err == 0)
+			return 1;
+		if (try > CIFSROOT_RETRY_MAX)
+			break;
+
+		ssleep(timeout);
+		timeout <<= 1;
+		if (timeout > CIFSROOT_TIMEOUT_MAX)
+			timeout = CIFSROOT_TIMEOUT_MAX;
+	}
+	return 0;
+}
+#endif
+
 #if defined(CONFIG_BLK_DEV_RAM) || defined(CONFIG_BLK_DEV_FD)
 void __init change_floppy(char *fmt, ...)
 {
@@ -542,6 +601,15 @@ void __init mount_root(void)
 		ROOT_DEV = Root_FD0;
 	}
 #endif
+#ifdef CONFIG_CIFS_ROOT
+	if (ROOT_DEV == Root_CIFS) {
+		if (mount_cifs_root())
+			return;
+
+		printk(KERN_ERR "VFS: Unable to mount root fs via SMB, trying floppy.\n");
+		ROOT_DEV = Root_FD0;
+	}
+#endif
 #ifdef CONFIG_BLK_DEV_FD
 	if (MAJOR(ROOT_DEV) == FLOPPY_MAJOR) {
 		/* rd_doload is 2 for a dual initrd/ramload setup */
@@ -621,8 +689,8 @@ void __init prepare_namespace(void)
 
 	mount_root();
 out:
-	devtmpfs_mount("dev");
-	ksys_mount(".", "/", NULL, MS_MOVE, NULL);
+	devtmpfs_mount();
+	do_mount(".", "/", NULL, MS_MOVE, NULL);
 	ksys_chroot(".");
 }
 

init/do_mounts_initrd.c

@@ -48,13 +48,10 @@ early_param("initrd", early_initrd);
 static int init_linuxrc(struct subprocess_info *info, struct cred *new)
 {
 	ksys_unshare(CLONE_FS | CLONE_FILES);
-	/* stdin/stdout/stderr for /linuxrc */
-	ksys_open("/dev/console", O_RDWR, 0);
-	ksys_dup(0);
-	ksys_dup(0);
+	console_on_rootfs();
 	/* move initrd over / and chdir/chroot in initrd root */
 	ksys_chdir("/root");
-	ksys_mount(".", "/", NULL, MS_MOVE, NULL);
+	do_mount(".", "/", NULL, MS_MOVE, NULL);
 	ksys_chroot(".");
 	ksys_setsid();
 	return 0;
@@ -89,7 +86,7 @@ static void __init handle_initrd(void)
 	current->flags &= ~PF_FREEZER_SKIP;
 
 	/* move initrd to rootfs' /old */
-	ksys_mount("..", ".", NULL, MS_MOVE, NULL);
+	do_mount("..", ".", NULL, MS_MOVE, NULL);
 	/* switch root and cwd back to / of rootfs */
 	ksys_chroot("..");
 
@@ -103,7 +100,7 @@ static void __init handle_initrd(void)
 	mount_root();
 
 	printk(KERN_NOTICE "Trying to move old root to /initrd ... ");
-	error = ksys_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL);
+	error = do_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL);
 	if (!error)
 		printk("okay\n");
 	else {

init/initramfs.c

@@ -10,6 +10,7 @@
 #include <linux/syscalls.h>
 #include <linux/utime.h>
 #include <linux/file.h>
+#include <linux/memblock.h>
 
 static ssize_t __init xwrite(int fd, const char *p, size_t count)
 {
@@ -529,6 +530,13 @@ extern unsigned long __initramfs_size;
 
 void __weak free_initrd_mem(unsigned long start, unsigned long end)
 {
+#ifdef CONFIG_ARCH_KEEP_MEMBLOCK
+	unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE);
+	unsigned long aligned_end = ALIGN(end, PAGE_SIZE);
+
+	memblock_free(__pa(aligned_start), aligned_end - aligned_start);
+#endif
+
 	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
 			"initrd");
 }

init/main.c

@@ -93,6 +93,7 @@
 #include <linux/rodata_test.h>
 #include <linux/jump_label.h>
 #include <linux/mem_encrypt.h>
+#include <linux/file.h>
 #include <linux/kcsan.h>
 
 #include <asm/io.h>
@@ -1157,6 +1158,30 @@ static int __ref kernel_init(void *unused)
 	      "See Linux Documentation/admin-guide/init.rst for guidance.");
 }
 
+void console_on_rootfs(void)
+{
+	struct file *file;
+	unsigned int i;
+
+	/* Open /dev/console in kernelspace, this should never fail */
+	file = filp_open("/dev/console", O_RDWR, 0);
+	if (IS_ERR(file))
+		goto err_out;
+
+	/* create stdin/stdout/stderr, this should never fail */
+	for (i = 0; i < 3; i++) {
+		if (f_dupfd(i, file, 0) != i)
+			goto err_out;
+	}
+
+	return;
+
+err_out:
+	/* no panic -- this might not be fatal */
+	pr_err("Warning: unable to open an initial console.\n");
+	return;
+}
+
 static noinline void __init kernel_init_freeable(void)
 {
 	/*
@@ -1192,12 +1217,8 @@ static noinline void __init kernel_init_freeable(void)
 
 	do_basic_setup();
 
-	/* Open the /dev/console on the rootfs, this should never fail */
-	if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
-		pr_err("Warning: unable to open an initial console.\n");
+	console_on_rootfs();
 
-	(void) ksys_dup(0);
-	(void) ksys_dup(0);
 	/*
 	 * check if there is an early userspace init.  If yes, let it do all
 	 * the work