From 8902dd526020748ccf16f753befc287b534fdefd Mon Sep 17 00:00:00 2001 From: "Paulo Alcantara (SUSE)" Date: Tue, 1 Oct 2019 14:10:27 -0300 Subject: init: Support mounting root file systems over SMB Add a new virtual device named /dev/cifs (0xfe) to tell the kernel to mount the root file system over the network by using SMB protocol. cifs_root_data() will be responsible to retrieve the parsed information of the new command-line option (cifsroot=) and then call do_mount_root() with the appropriate mount options for cifs.ko. Signed-off-by: Paulo Alcantara (SUSE) Signed-off-by: David S. Miller --- init/do_mounts.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) (limited to 'init') diff --git a/init/do_mounts.c b/init/do_mounts.c index 9634ecf3743d..af9cda887a23 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -212,6 +212,7 @@ static int match_dev_by_label(struct device *dev, const void *data) * a colon. * 9) PARTLABEL= 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; @@ -501,6 +505,42 @@ 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 +582,15 @@ 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 */ -- cgit v1.2.3 From 899ee4afe5eb262236717188ccdaa0192c00dc5a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sat, 28 Sep 2019 11:02:26 +0300 Subject: arm64: use generic free_initrd_mem() arm64 calls memblock_free() for the initrd area in its implementation of free_initrd_mem(), but this call has no actual effect that late in the boot process. By the time initrd is freed, all the reserved memory is managed by the page allocator and the memblock.reserved is unused, so the only purpose of the memblock_free() call is to keep track of initrd memory for debugging and accounting. Without the memblock_free() call the only difference between arm64 and the generic versions of free_initrd_mem() is the memory poisoning. Move memblock_free() call to the generic code, enable it there for the architectures that define ARCH_KEEP_MEMBLOCK and use the generic implementation of free_initrd_mem() on arm64. Tested-by: Anshuman Khandual #arm64 Reviewed-by: Anshuman Khandual Acked-by: Will Deacon Signed-off-by: Mike Rapoport Signed-off-by: Catalin Marinas --- init/initramfs.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'init') diff --git a/init/initramfs.c b/init/initramfs.c index c47dad0884f7..8ec1be4d7d51 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -10,6 +10,7 @@ #include #include #include +#include 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"); } -- cgit v1.2.3 From 561fb04a6a2257716738dac2ed812f377c2634c2 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 24 Oct 2019 07:25:42 -0600 Subject: io_uring: replace workqueue usage with io-wq Drop various work-arounds we have for workqueues: - We no longer need the async_list for tracking sequential IO. - We don't have to maintain our own mm tracking/setting. - We don't need a separate workqueue for buffered writes. This didn't even work that well to begin with, as it was suboptimal for multiple buffered writers on multiple files. - We can properly cancel pending interruptible work. This fixes deadlocks with particularly socket IO, where we cannot cancel them when the io_uring is closed. Hence the ring will wait forever for these requests to complete, which may never happen. This is different from disk IO where we know requests will complete in a finite amount of time. - Due to being able to cancel work interruptible work that is already running, we can implement file table support for work. We need that for supporting system calls that add to a process file table. - It gets us one step closer to adding async support for any system call. Signed-off-by: Jens Axboe --- init/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index b4daad2bac23..4d8d145c41d2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1548,6 +1548,7 @@ 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 -- cgit v1.2.3 From fcbb8461fd2376ba3782b5b8bd440c929b8e4980 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Thu, 7 Nov 2019 16:14:40 +0900 Subject: kbuild: remove header compile test There are both positive and negative options about this feature. At first, I thought it was a good idea, but actually Linus stated a negative opinion (https://lkml.org/lkml/2019/9/29/227). I admit it is ugly and annoying. The baseline I'd like to keep is the compile-test of uapi headers. (Otherwise, kernel developers have no way to ensure the correctness of the exported headers.) I will maintain a small build rule in usr/include/Makefile. Remove the other header test functionality. Signed-off-by: Masahiro Yamada --- init/Kconfig | 22 +--------------------- 1 file changed, 1 insertion(+), 21 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index b4daad2bac23..8d1667fc4415 100644 --- a/init/Kconfig +++ b/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. -- cgit v1.2.3 From c12d3362a74bf0cd9e1d488918d40607b62a3104 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 8 Nov 2019 13:22:27 +0100 Subject: int128: move __uint128_t compiler test to Kconfig In order to use 128-bit integer arithmetic in C code, the architecture needs to have declared support for it by setting ARCH_SUPPORTS_INT128, and it requires a version of the toolchain that supports this at build time. This is why all existing tests for ARCH_SUPPORTS_INT128 also test whether __SIZEOF_INT128__ is defined, since this is only the case for compilers that can support 128-bit integers. Let's fold this additional test into the Kconfig declaration of ARCH_SUPPORTS_INT128 so that we can also use the symbol in Makefiles, e.g., to decide whether a certain object needs to be included in the first place. Cc: Masahiro Yamada Signed-off-by: Ard Biesheuvel Signed-off-by: Herbert Xu --- init/Kconfig | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index b4daad2bac23..020526f681c0 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -785,6 +785,10 @@ 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 # -- cgit v1.2.3 From 61a47c1ad3a4dc6882f01ebdc88138ac62d0df03 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 1 Oct 2019 13:01:19 -0500 Subject: sysctl: Remove the sysctl system call This system call has been deprecated almost since it was introduced, and in a survey of the linux distributions I can no longer find any of them that enable CONFIG_SYSCTL_SYSCALL. The only indication that I can find that anyone might care is that a few of the defconfigs in the kernel enable CONFIG_SYSCTL_SYSCALL. However this appears in only 31 of 414 defconfigs in the kernel, so I suspect this symbols presence is simply because it is harmless to include rather than because it is necessary. As there appear to be no users of the sysctl system call, remove the code. As this removes one of the few uses of the internal kernel mount of proc I hope this allows for even more simplifications of the proc filesystem. Cc: Alex Smith Cc: Anders Berg Cc: Apelete Seketeli Cc: Arnd Bergmann Cc: Chee Nouk Phoon Cc: Chris Zankel Cc: Christian Ruppert Cc: Greg Ungerer Cc: Harvey Hunt Cc: Helge Deller Cc: Hongliang Tao Cc: Hua Yan Cc: Huacai Chen Cc: John Crispin Cc: Jonas Jensen Cc: Josh Boyer Cc: Jun Nie Cc: Kevin Hilman Cc: Kevin Wells Cc: Kumar Gala Cc: Lars-Peter Clausen Cc: Ley Foon Tan Cc: Linus Walleij Cc: Markos Chandras Cc: Max Filippov Cc: Noam Camus Cc: Olof Johansson Cc: Paul Burton Cc: Paul Mundt Cc: Phil Edworthy Cc: Pierrick Hascoet Cc: Ralf Baechle Cc: Roland Stigge Cc: Santosh Shilimkar Cc: Scott Telford Cc: Stephen Boyd Cc: Steven J. Hill Cc: Tanmay Inamdar Cc: Vineet Gupta Cc: Wolfram Sang Acked-by: Andi Kleen Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- init/Kconfig | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index b4daad2bac23..a408116c7719 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1372,23 +1372,6 @@ 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 -- cgit v1.2.3 From e8cf4e9ca056cb5dcec3fdf3125c6645fc9b594d Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Wed, 4 Dec 2019 16:52:28 -0800 Subject: init/Kconfig: fix indentation Adjust indentation from spaces to tab (+optional two spaces) as in coding style with command like: $ sed -e 's/^ / /' -i */Kconfig Link: http://lkml.kernel.org/r/1574306670-30234-1-git-send-email-krzk@kernel.org Signed-off-by: Krzysztof Kozlowski Cc: Jiri Kosina Cc: Masahiro Yamada Cc: Greg Kroah-Hartman Cc: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 76 ++++++++++++++++++++++++++++++------------------------------ 1 file changed, 38 insertions(+), 38 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index d7163fcf233b..a34064a031a5 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -146,13 +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 @@ -818,7 +818,7 @@ menuconfig CGROUPS if CGROUPS config PAGE_COUNTER - bool + bool config MEMCG bool "Memory controller" @@ -1311,9 +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 @@ -1406,11 +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 @@ -1426,8 +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 @@ -1545,29 +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 @@ -1710,12 +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 -- cgit v1.2.3 From 5e787dbf659fe77d56215be74044f85e01b3920f Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 23 Oct 2018 22:10:35 +0200 Subject: devtmpfs: use do_mount() instead of ksys_mount() In devtmpfs, do_mount() can be called directly instead of complex wrapping by ksys_mount(): - the first and third arguments are const strings in the kernel, and do not need to be copied over from userspace; - the fifth argument is NULL, and therefore no page needs to be copied over from userspace; - the second and fourth argument are passed through anyway. Signed-off-by: Dominik Brodowski --- init/do_mounts.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/do_mounts.c b/init/do_mounts.c index af9cda887a23..43f6d098c880 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -670,7 +670,7 @@ void __init prepare_namespace(void) mount_root(); out: - devtmpfs_mount("dev"); + devtmpfs_mount(); ksys_mount(".", "/", NULL, MS_MOVE, NULL); ksys_chroot("."); } -- cgit v1.2.3 From d4440aac83d12f87df9bcc51e992b9c28c7f4fa5 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Wed, 27 Nov 2019 20:24:14 +0100 Subject: initrd: use do_mount() instead of ksys_mount() All three calls to ksys_mount() in initrd-related kernel code can be switched over to do_mount(): - the first and third arguments are const strings in the kernel, and do not need to be copied over from userspace; - the fifth argument is NULL, and therefore no page needs to be, copied over from userspace; - the second and fourth argument are passed through anyway. Signed-off-by: Dominik Brodowski --- init/do_mounts_initrd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'init') diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index a9c6cc56f505..3bf7b74153ab 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -54,7 +54,7 @@ static int init_linuxrc(struct subprocess_info *info, struct cred *new) ksys_dup(0); /* 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 +89,7 @@ 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 +103,7 @@ 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 { -- cgit v1.2.3 From cccaa5e33525fc07f4a2ce0518e50b9ddf435e47 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 23 Oct 2018 22:41:09 +0200 Subject: init: use do_mount() instead of ksys_mount() In prepare_namespace(), do_mount() can be used instead of ksys_mount() as the first and third argument are const strings in the kernel, the second and fourth argument are passed through anyway, and the fifth argument is NULL. In do_mount_root(), ksys_mount() is called with the first and third argument being already kernelspace strings, which do not need to be copied over from userspace to kernelspace (again). The second and fourth arguments are passed through to do_mount() anyway. The fifth argument, while already residing in kernelspace, needs to be put into a page of its own. Then, do_mount() can be used instead of ksys_mount(). Once this is done, there are no in-kernel users to ksys_mount() left, which can therefore be removed. Signed-off-by: Dominik Brodowski --- init/do_mounts.c | 28 ++++++++++++++++++++++------ 1 file changed, 22 insertions(+), 6 deletions(-) (limited to 'init') diff --git a/init/do_mounts.c b/init/do_mounts.c index 43f6d098c880..f55cbd9cb818 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -387,12 +387,25 @@ 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; + char *data_page; + struct page *p; + int ret; + + /* do_mount() requires a full page as fifth argument */ + p = alloc_page(GFP_KERNEL); + if (!p) + return -ENOMEM; + + data_page = page_address(p); + strncpy(data_page, data, PAGE_SIZE - 1); + + ret = do_mount(name, "/root", fs, flags, data_page); + if (ret) + goto out; ksys_chdir("/root"); s = current->fs->pwd.dentry->d_sb; @@ -402,7 +415,10 @@ 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: + put_page(p); + return ret; } void __init mount_block_root(char *name, int flags) @@ -671,7 +687,7 @@ void __init prepare_namespace(void) mount_root(); out: devtmpfs_mount(); - ksys_mount(".", "/", NULL, MS_MOVE, NULL); + do_mount(".", "/", NULL, MS_MOVE, NULL); ksys_chroot("."); } -- cgit v1.2.3 From b49a733d684e0096340b93e9dfd471f0e3ddc06d Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 23 Oct 2018 16:00:10 +0200 Subject: init: unify opening /dev/console as stdin/stdout/stderr Merge the two instances where /dev/console is opened as stdin/stdout/stderr. Signed-off-by: Dominik Brodowski --- init/do_mounts_initrd.c | 5 +---- init/main.c | 17 ++++++++++++----- 2 files changed, 13 insertions(+), 9 deletions(-) (limited to 'init') diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 3bf7b74153ab..dab8b1151b56 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -48,10 +48,7 @@ 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"); do_mount(".", "/", NULL, MS_MOVE, NULL); diff --git a/init/main.c b/init/main.c index 91f6ebb30ef0..2cd736059416 100644 --- a/init/main.c +++ b/init/main.c @@ -1155,6 +1155,17 @@ static int __ref kernel_init(void *unused) "See Linux Documentation/admin-guide/init.rst for guidance."); } +void console_on_rootfs(void) +{ + /* Open the /dev/console as stdin, 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"); + + /* create stdout/stderr */ + (void) ksys_dup(0); + (void) ksys_dup(0); +} + static noinline void __init kernel_init_freeable(void) { /* @@ -1190,12 +1201,8 @@ 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 -- cgit v1.2.3 From 8243186f0cc7c57cf9d6a110cd7315c44e3e0be8 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 23 Oct 2018 16:24:09 +0200 Subject: fs: remove ksys_dup() ksys_dup() is used only at one place in the kernel, namely to duplicate fd 0 of /dev/console to stdout and stderr. The same functionality can be achieved by using functions already available within the kernel namespace. Signed-off-by: Dominik Brodowski --- init/main.c | 26 ++++++++++++++++++++------ 1 file changed, 20 insertions(+), 6 deletions(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index 2cd736059416..ec3a1463ac69 100644 --- a/init/main.c +++ b/init/main.c @@ -93,6 +93,7 @@ #include #include #include +#include #include #include @@ -1157,13 +1158,26 @@ static int __ref kernel_init(void *unused) void console_on_rootfs(void) { - /* Open the /dev/console as stdin, 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"); + struct file *file; + unsigned int i; + + /* Open /dev/console in kernelspace, this should never fail */ + file = filp_open("/dev/console", O_RDWR, 0); + if (!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; - /* create stdout/stderr */ - (void) ksys_dup(0); - (void) ksys_dup(0); +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) -- cgit v1.2.3 From 7de7de7ca0ae0fc70515ee3154af33af75edae2c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 15 Dec 2019 19:50:23 -0800 Subject: Fix root mounting with no mount options MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The "trivial conversion" in commit cccaa5e33525 ("init: use do_mount() instead of ksys_mount()") was totally broken, since it didn't handle the case of a NULL mount data pointer. And while I had "tested" it (and presumably Dominik had too) that bug was hidden by me having options. Cc: Dominik Brodowski Cc: Arnd Bergmann Reported-by: Ondřej Jirman Reported-by: Guenter Roeck Reported-by: Naresh Kamboju Reported-and-tested-by: Borislav Petkov Tested-by: Chris Clayton Tested-by: Eric Biggers Tested-by: Geert Uytterhoeven Tested-by: Guido Günther Signed-off-by: Linus Torvalds --- init/do_mounts.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) (limited to 'init') diff --git a/init/do_mounts.c b/init/do_mounts.c index f55cbd9cb818..0ae9cc22f2ae 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -391,17 +391,19 @@ static int __init do_mount_root(const char *name, const char *fs, const int flags, const void *data) { struct super_block *s; - char *data_page; - struct page *p; + struct page *p = NULL; + char *data_page = NULL; int ret; - /* do_mount() requires a full page as fifth argument */ - p = alloc_page(GFP_KERNEL); - if (!p) - return -ENOMEM; - - data_page = page_address(p); - strncpy(data_page, data, PAGE_SIZE - 1); + 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) @@ -417,7 +419,8 @@ static int __init do_mount_root(const char *name, const char *fs, MAJOR(ROOT_DEV), MINOR(ROOT_DEV)); out: - put_page(p); + if (p) + put_page(p); return ret; } -- cgit v1.2.3 From 2d3145f8d2809592ef803a30c8a342b5a9e2de9a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 17 Dec 2019 13:10:11 -0800 Subject: early init: fix error handling when opening /dev/console The comment says "this should never fail", but it definitely can fail when you have odd initial boot filesystems, or kernel configurations. So get the error handling right: filp_open() returns an error pointer. Reported-by: Jesse Barnes Reported-by: youling 257 Fixes: 8243186f0cc7 ("fs: remove ksys_dup()") Cc: Dominik Brodowski Signed-off-by: Linus Torvalds --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index ec3a1463ac69..1ecfd43ed464 100644 --- a/init/main.c +++ b/init/main.c @@ -1163,7 +1163,7 @@ void console_on_rootfs(void) /* Open /dev/console in kernelspace, this should never fail */ file = filp_open("/dev/console", O_RDWR, 0); - if (!file) + if (IS_ERR(file)) goto err_out; /* create stdin/stdout/stderr, this should never fail */ -- cgit v1.2.3