From 0aaf08de8426f823bd0e36797445222e6392e374 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 19 Jan 2023 19:22:22 -0500 Subject: __blockdev_direct_IO(): get rid of submit_io callback always NULL... Signed-off-by: Al Viro --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index c85916e9f7db..b07d13e546d3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2778,7 +2778,7 @@ enum { ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, - dio_iodone_t end_io, dio_submit_t submit_io, + dio_iodone_t end_io, int flags); static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, @@ -2787,7 +2787,7 @@ static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, get_block_t get_block) { return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, - get_block, NULL, NULL, DIO_LOCKING | DIO_SKIP_HOLES); + get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES); } #endif -- cgit v1.2.3-70-g09d2 From 4f704d9a8352f5c0a8fcdb6213b934630342bd44 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 14 Mar 2023 12:51:10 +0100 Subject: nfs: use vfs setgid helper We've aligned setgid behavior over multiple kernel releases. The details can be found in the following two merge messages: cf619f891971 ("Merge tag 'fs.ovl.setgid.v6.2') 426b4ca2d6a5 ("Merge tag 'fs.setgid.v6.0') Consistent setgid stripping behavior is now encapsulated in the setattr_should_drop_sgid() helper which is used by all filesystems that strip setgid bits outside of vfs proper. Switch nfs to rely on this helper as well. Without this patch the setgid stripping tests in xfstests will fail. Signed-off-by: Christian Brauner (Microsoft) Reviewed-by: Christoph Hellwig Message-Id: <20230313-fs-nfs-setgid-v2-1-9a59f436cfc0@kernel.org> Signed-off-by: Christian Brauner --- fs/attr.c | 1 + fs/internal.h | 2 -- fs/nfs/inode.c | 4 +--- include/linux/fs.h | 2 ++ 4 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/attr.c b/fs/attr.c index aca9ff7aed33..d60dc1edb526 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -47,6 +47,7 @@ int setattr_should_drop_sgid(struct mnt_idmap *idmap, return ATTR_KILL_SGID; return 0; } +EXPORT_SYMBOL(setattr_should_drop_sgid); /** * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to diff --git a/fs/internal.h b/fs/internal.h index dc4eb91a577a..ab36ed8fa41c 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -259,8 +259,6 @@ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *po /* * fs/attr.c */ -int setattr_should_drop_sgid(struct mnt_idmap *idmap, - const struct inode *inode); struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns); struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap); void mnt_idmap_put(struct mnt_idmap *idmap); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 222a28320e1c..97a76706fd54 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -717,9 +717,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, if ((attr->ia_valid & ATTR_KILL_SUID) != 0 && inode->i_mode & S_ISUID) inode->i_mode &= ~S_ISUID; - if ((attr->ia_valid & ATTR_KILL_SGID) != 0 && - (inode->i_mode & (S_ISGID | S_IXGRP)) == - (S_ISGID | S_IXGRP)) + if (setattr_should_drop_sgid(&nop_mnt_idmap, inode)) inode->i_mode &= ~S_ISGID; if ((attr->ia_valid & ATTR_MODE) != 0) { int mode = attr->ia_mode & S_IALLUGO; diff --git a/include/linux/fs.h b/include/linux/fs.h index c85916e9f7db..af95b64fc810 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2675,6 +2675,8 @@ extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *); extern int file_remove_privs(struct file *); +int setattr_should_drop_sgid(struct mnt_idmap *idmap, + const struct inode *inode); /* * This must be used for allocating filesystems specific inodes to set -- cgit v1.2.3-70-g09d2 From d8aeb44a9ae324c4b823689fabb30b6621d93c88 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 7 Mar 2023 09:40:28 -0700 Subject: fs: add FMODE_DIO_PARALLEL_WRITE flag Some filesystems support multiple threads writing to the same file with O_DIRECT without requiring exclusive access to it. io_uring can use this hint to avoid serializing dio writes to this inode, instead allowing them to run in parallel. XFS and ext4 both fall into this category, so set the flag for both of them. Reviewed-by: Darrick J. Wong Signed-off-by: Jens Axboe --- fs/ext4/file.c | 3 ++- fs/xfs/xfs_file.c | 3 ++- include/linux/fs.h | 3 +++ 3 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux/fs.h') diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 0b8b4499e5ca..d101b3b0c7da 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -899,7 +899,8 @@ static int ext4_file_open(struct inode *inode, struct file *filp) return ret; } - filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC; + filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | + FMODE_DIO_PARALLEL_WRITE; return dquot_file_open(inode, filp); } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 705250f9f90a..863289aaa441 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1171,7 +1171,8 @@ xfs_file_open( { if (xfs_is_shutdown(XFS_M(inode->i_sb))) return -EIO; - file->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC; + file->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_BUF_WASYNC | + FMODE_DIO_PARALLEL_WRITE; return generic_file_open(inode, file); } diff --git a/include/linux/fs.h b/include/linux/fs.h index c85916e9f7db..475d88640d3d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -168,6 +168,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_NOREUSE ((__force fmode_t)0x800000) +/* File supports non-exclusive O_DIRECT writes from multiple threads */ +#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) -- cgit v1.2.3-70-g09d2 From f6c73a11133ef991284311387ca707b48bf53912 Mon Sep 17 00:00:00 2001 From: "Ritesh Harjani (IBM)" Date: Fri, 21 Apr 2023 08:52:42 -0700 Subject: fs.h: Add TRACE_IOCB_STRINGS for use in trace points Add TRACE_IOCB_STRINGS macro which can be used in the trace point patch to print different flag values with meaningful string output. Tested-by: Disha Goel Reviewed-by: Christoph Hellwig Signed-off-by: Ritesh Harjani (IBM) Reviewed-by: Darrick J. Wong [djwong: line up strings all prettylike] Signed-off-by: Darrick J. Wong --- include/linux/fs.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index c85916e9f7db..75d24fa082e5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -340,6 +340,20 @@ enum rw_hint { /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) +/* for use in trace events */ +#define TRACE_IOCB_STRINGS \ + { IOCB_HIPRI, "HIPRI" }, \ + { IOCB_DSYNC, "DSYNC" }, \ + { IOCB_SYNC, "SYNC" }, \ + { IOCB_NOWAIT, "NOWAIT" }, \ + { IOCB_APPEND, "APPEND" }, \ + { IOCB_EVENTFD, "EVENTFD"}, \ + { IOCB_DIRECT, "DIRECT" }, \ + { IOCB_WRITE, "WRITE" }, \ + { IOCB_WAITQ, "WAITQ" }, \ + { IOCB_NOIO, "NOIO" }, \ + { IOCB_ALLOC_CACHE, "ALLOC_CACHE" } + struct kiocb { struct file *ki_filp; loff_t ki_pos; -- cgit v1.2.3-70-g09d2 From f15afbd34d8fadbd375f1212e97837e32bc170cc Mon Sep 17 00:00:00 2001 From: Hao Ge Date: Mon, 24 Apr 2023 13:18:35 +0800 Subject: fs: fix undefined behavior in bit shift for SB_NOUSER Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. It was spotted by UBSAN. So let's just fix this by using the BIT() helper for all SB_* flags. Fixes: e462ec50cb5f ("VFS: Differentiate mount flags (MS_*) from internal superblock flags") Signed-off-by: Hao Ge Message-Id: <20230424051835.374204-1-gehao@kylinos.cn> [brauner@kernel.org: use BIT() for all SB_* flags] Signed-off-by: Christian Brauner --- include/linux/fs.h | 42 +++++++++++++++++++++--------------------- 1 file changed, 21 insertions(+), 21 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 21a981680856..133f0640fb24 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1076,29 +1076,29 @@ extern int send_sigurg(struct fown_struct *fown); * sb->s_flags. Note that these mirror the equivalent MS_* flags where * represented in both. */ -#define SB_RDONLY 1 /* Mount read-only */ -#define SB_NOSUID 2 /* Ignore suid and sgid bits */ -#define SB_NODEV 4 /* Disallow access to device special files */ -#define SB_NOEXEC 8 /* Disallow program execution */ -#define SB_SYNCHRONOUS 16 /* Writes are synced at once */ -#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */ -#define SB_DIRSYNC 128 /* Directory modifications are synchronous */ -#define SB_NOATIME 1024 /* Do not update access times. */ -#define SB_NODIRATIME 2048 /* Do not update directory access times */ -#define SB_SILENT 32768 -#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ -#define SB_INLINECRYPT (1<<17) /* Use blk-crypto for encrypted files */ -#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ -#define SB_I_VERSION (1<<23) /* Update inode I_version field */ -#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ +#define SB_RDONLY BIT(0) /* Mount read-only */ +#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ +#define SB_NODEV BIT(2) /* Disallow access to device special files */ +#define SB_NOEXEC BIT(3) /* Disallow program execution */ +#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ +#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ +#define SB_NOATIME BIT(10) /* Do not update access times. */ +#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ +#define SB_SILENT BIT(15) +#define SB_POSIXACL BIT(16) /* VFS does not apply the umask */ +#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ +#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ +#define SB_I_VERSION BIT(23) /* Update inode I_version field */ +#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ /* These sb flags are internal to the kernel */ -#define SB_SUBMOUNT (1<<26) -#define SB_FORCE (1<<27) -#define SB_NOSEC (1<<28) -#define SB_BORN (1<<29) -#define SB_ACTIVE (1<<30) -#define SB_NOUSER (1<<31) +#define SB_SUBMOUNT BIT(26) +#define SB_FORCE BIT(27) +#define SB_NOSEC BIT(28) +#define SB_BORN BIT(29) +#define SB_ACTIVE BIT(30) +#define SB_NOUSER BIT(31) /* These flags relate to encoding and casefolding */ #define SB_ENC_STRICT_MODE_FL (1 << 0) -- cgit v1.2.3-70-g09d2 From 9828ed3f695a138f7add89fa2a186ababceb8006 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 25 May 2023 09:32:25 -0700 Subject: module: error out early on concurrent load of the same module file It turns out that udev under certain circumstances will concurrently try to load the same modules over-and-over excessively. This isn't a kernel bug, but it ends up affecting the kernel, to the point that under certain circumstances we can fail to boot, because the kernel uses a lot of memory to read all the module data all at once. Note that it isn't a memory leak, it's just basically a thundering herd problem happening at bootup with a lot of CPUs, with the worst cases then being pretty bad. Admittedly the worst situations are somewhat contrived: lots and lots of CPUs, not a lot of memory, and KASAN enabled to make it all slower and as such (unintentionally) exacerbate the problem. Luis explains: [1] "My best assessment of the situation is that each CPU in udev ends up triggering a load of duplicate set of modules, not just one, but *a lot*. Not sure what heuristics udev uses to load a set of modules per CPU." Petr Pavlu chimes in: [2] "My understanding is that udev workers are forked. An initial kmod context is created by the main udevd process but no sharing happens after the fork. It means that the mentioned memory pool logic doesn't really kick in. Multiple parallel load requests come from multiple udev workers, for instance, each handling an udev event for one CPU device and making the exactly same requests as all others are doing at the same time. The optimization idea would be to recognize these duplicate requests at the udevd/kmod level and converge them" Note that module loading has tried to mitigate this issue before, see for example commit 064f4536d139 ("module: avoid allocation if module is already present and ready"), which has a few ASCII graphs on memory use due to this same issue. However, while that noticed that the module was already loaded, and exited with an error early before spending any more time on setting up the module, it didn't handle the case of multiple concurrent module loads all being active - but not complete - at the same time. Yes, one of them will eventually win the race and finalize its copy, and the others will then notice that the module already exists and error out, but while this all happens, we have tons of unnecessary concurrent work being done. Again, the real fix is for udev to not do that (maybe it should use threads instead of fork, and have actual shared data structures and not cause duplicate work). That real fix is apparently not trivial. But it turns out that the kernel already has a pretty good model for dealing with concurrent access to the same file: the i_writecount of the inode. In fact, the module loading already indirectly uses 'i_writecount' , because 'kernel_file_read()' will in fact do ret = deny_write_access(file); if (ret) return ret; ... allow_write_access(file); around the read of the file data. We do not allow concurrent writes to the file, and return -ETXTBUSY if the file was open for writing at the same time as the module data is loaded from it. And the solution to the reader concurrency problem is to simply extend this "no concurrent writers" logic to simply be "exclusive access". Note that "exclusive" in this context isn't really some absolute thing: it's only exclusion from writers and from other "special readers" that do this writer denial. So we simply introduce a variation of that "deny_write_access()" logic that not only denies write access, but also requires that this is the _only_ such access that denies write access. Which means that you can't start loading a module that is already being loaded as a module by somebody else, or you will get the same -ETXTBSY error that you would get if there were writers around. [ It also means that you can't try to load a currently executing executable as a module, for the same reason: executables do that same "deny_write_access()" thing, and that's obviously where the whole ETXTBSY logic traditionally came from. This is not a problem for kernel modules, since the set of normal executable files and kernel module files is entirely disjoint. ] This new function is called "exclusive_deny_write_access()", and the implementation is trivial, in that it's just an atomic decrement of i_writecount if it was 0 before. To use that new exclusivity check, all we then do is wrap the module loading with that exclusive_deny_write_access()() / allow_write_access() pair. The actual patch is a bit bigger than that, because we want to surround not just the "load file data" part, but the whole module setup, to get maximum exclusion. So this ends up splitting up "finit_module()" into a few helper functions to make it all very clear and legible. In Luis' test-case (bringing up 255 vcpu's in a virtual machine [3]), the "wasted vmalloc" space (ie module data read into a vmalloc'ed area in order to be loaded as a module, but then discarded because somebody else loaded the same module instead) dropped from 1.8GiB to 474kB. Yes, that's gigabytes to kilobytes. It doesn't drop completely to zero, because even with this change, you can still end up having completely serial pointless module loads, where one udev process has loaded a module fully (and thus the kernel has released that exclusive lock on the module file), and then another udev process tries to load the same module again. So while we cannot fully get rid of the fundamental bug in user space, we _can_ get rid of the excessive concurrent thundering herd effect. A couple of final side notes on this all: - This tweak only affects the "finit_module()" system call, which gives the kernel a file descriptor with the module data. You can also just feed the module data as raw data from user space with "init_module()" (note the lack of 'f' at the beginning), and obviously for that case we do _not_ have any "exclusive read" logic. So if you absolutely want to do things wrong in user space, and try to load the same module multiple times, and error out only later when the kernel ends up saying "you can't load the same module name twice", you can still do that. And in fact, some distros will do exactly that, because they will uncompress the kernel module data in user space before feeding it to the kernel (mainly because they haven't started using the new kernel side decompression yet). So this is not some absolute "you can't do concurrent loads of the same module". It's literally just a very simple heuristic that will catch it early in case you try to load the exact same module file at the same time, and in that case avoid a potentially nasty situation. - There is another user of "deny_write_access()": the verity code that enables fs-verity on a file (the FS_IOC_ENABLE_VERITY ioctl). If you use fs-verity and you care about verifying the kernel modules (which does make sense), you should do it *before* loading said kernel module. That may sound obvious, but now the implementation basically requires it. Because if you try to do it concurrently, the kernel may refuse to load the module file that is being set up by the fs-verity code. - This all will obviously mean that if you insist on loading the same module in parallel, only one module load will succeed, and the others will return with an error. That was true before too, but what is different is that the -ETXTBSY error can be returned *before* the success case of another process fully loading and instantiating the module. Again, that might sound obvious, and it is indeed the whole point of the whole change: we are much quicker to notice the whole "you're already in the process of loading this module". So it's very much intentional, but it does mean that if you just spray the kernel with "finit_module()", and expect that the module is immediately loaded afterwards without checking the return value, you are doing something horribly horribly wrong. I'd like to say that that would never happen, but the whole _reason_ for this commit is that udev is currently doing something horribly horribly wrong, so ... Link: https://lore.kernel.org/all/ZEGopJ8VAYnE7LQ2@bombadil.infradead.org/ [1] Link: https://lore.kernel.org/all/23bd0ce6-ef78-1cd8-1f21-0e706a00424a@suse.com/ [2] Link: https://lore.kernel.org/lkml/ZG%2Fa+nrt4%2FAAUi5z@bombadil.infradead.org/ [3] Cc: Greg Kroah-Hartman Cc: Lucas De Marchi Cc: Petr Pavlu Tested-by: Luis Chamberlain Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 ++++++ kernel/module/main.c | 58 ++++++++++++++++++++++++++++++++++++++-------------- 2 files changed, 49 insertions(+), 15 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 133f0640fb24..86b50271b4f7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2566,6 +2566,12 @@ static inline int deny_write_access(struct file *file) struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } +static inline int exclusive_deny_write_access(struct file *file) +{ + int old = 0; + struct inode *inode = file_inode(file); + return atomic_try_cmpxchg(&inode->i_writecount, &old, -1) ? 0 : -ETXTBSY; +} static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); diff --git a/kernel/module/main.c b/kernel/module/main.c index 044aa2c9e3cb..b4c7e925fdb0 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -3057,25 +3057,13 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, return load_module(&info, uargs, 0); } -SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) +static int file_init_module(struct file *file, const char __user * uargs, int flags) { struct load_info info = { }; void *buf = NULL; int len; - int err; - - err = may_init_module(); - if (err) - return err; - - pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS - |MODULE_INIT_IGNORE_VERMAGIC - |MODULE_INIT_COMPRESSED_FILE)) - return -EINVAL; - - len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL, + len = kernel_read_file(file, 0, &buf, INT_MAX, NULL, READING_MODULE); if (len < 0) { mod_stat_inc(&failed_kreads); @@ -3084,7 +3072,7 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) } if (flags & MODULE_INIT_COMPRESSED_FILE) { - err = module_decompress(&info, buf, len); + int err = module_decompress(&info, buf, len); vfree(buf); /* compressed data is no longer needed */ if (err) { mod_stat_inc(&failed_decompress); @@ -3099,6 +3087,46 @@ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) return load_module(&info, uargs, flags); } +/* + * kernel_read_file() will already deny write access, but module + * loading wants _exclusive_ access to the file, so we do that + * here, along with basic sanity checks. + */ +static int prepare_file_for_module_load(struct file *file) +{ + if (!file || !(file->f_mode & FMODE_READ)) + return -EBADF; + if (!S_ISREG(file_inode(file)->i_mode)) + return -EINVAL; + return exclusive_deny_write_access(file); +} + +SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) +{ + struct fd f; + int err; + + err = may_init_module(); + if (err) + return err; + + pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); + + if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS + |MODULE_INIT_IGNORE_VERMAGIC + |MODULE_INIT_COMPRESSED_FILE)) + return -EINVAL; + + f = fdget(fd); + err = prepare_file_for_module_load(f.file); + if (!err) { + err = file_init_module(f.file, uargs, flags); + allow_write_access(f.file); + } + fdput(f); + return err; +} + /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */ char *module_flags(struct module *mod, char *buf, bool show_state) { -- cgit v1.2.3-70-g09d2 From ac2263b588dffd3a1efd7ed0b156ea6c5aea200d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 29 May 2023 06:40:33 -0400 Subject: Revert "module: error out early on concurrent load of the same module file" This reverts commit 9828ed3f695a138f7add89fa2a186ababceb8006. Sadly, it does seem to cause failures to load modules. Johan Hovold reports: "This change breaks module loading during boot on the Lenovo Thinkpad X13s (aarch64). Specifically it results in indefinite probe deferral of the display and USB (ethernet) which makes it a pain to debug. Typing in the dark to acquire some logs reveals that other modules are missing as well" Since this was applied late as a "let's try this", I'm reverting it asap, and we can try to figure out what goes wrong later. The excessive parallel module loading problem is annoying, but not noticeable in normal situations, and this was only meant as an optimistic workaround for a user-space bug. One possible solution may be to do the optimistic exclusive open first, and then use a lock to serialize loading if that fails. Reported-by: Johan Hovold Link: https://lore.kernel.org/lkml/ZHRpH-JXAxA6DnzR@hovoldconsulting.com/ Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 ------ kernel/module/main.c | 58 ++++++++++++++-------------------------------------- 2 files changed, 15 insertions(+), 49 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 86b50271b4f7..133f0640fb24 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2566,12 +2566,6 @@ static inline int deny_write_access(struct file *file) struct inode *inode = file_inode(file); return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY; } -static inline int exclusive_deny_write_access(struct file *file) -{ - int old = 0; - struct inode *inode = file_inode(file); - return atomic_try_cmpxchg(&inode->i_writecount, &old, -1) ? 0 : -ETXTBSY; -} static inline void put_write_access(struct inode * inode) { atomic_dec(&inode->i_writecount); diff --git a/kernel/module/main.c b/kernel/module/main.c index b4c7e925fdb0..044aa2c9e3cb 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -3057,13 +3057,25 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, return load_module(&info, uargs, 0); } -static int file_init_module(struct file *file, const char __user * uargs, int flags) +SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) { struct load_info info = { }; void *buf = NULL; int len; + int err; + + err = may_init_module(); + if (err) + return err; + + pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - len = kernel_read_file(file, 0, &buf, INT_MAX, NULL, + if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS + |MODULE_INIT_IGNORE_VERMAGIC + |MODULE_INIT_COMPRESSED_FILE)) + return -EINVAL; + + len = kernel_read_file_from_fd(fd, 0, &buf, INT_MAX, NULL, READING_MODULE); if (len < 0) { mod_stat_inc(&failed_kreads); @@ -3072,7 +3084,7 @@ static int file_init_module(struct file *file, const char __user * uargs, int fl } if (flags & MODULE_INIT_COMPRESSED_FILE) { - int err = module_decompress(&info, buf, len); + err = module_decompress(&info, buf, len); vfree(buf); /* compressed data is no longer needed */ if (err) { mod_stat_inc(&failed_decompress); @@ -3087,46 +3099,6 @@ static int file_init_module(struct file *file, const char __user * uargs, int fl return load_module(&info, uargs, flags); } -/* - * kernel_read_file() will already deny write access, but module - * loading wants _exclusive_ access to the file, so we do that - * here, along with basic sanity checks. - */ -static int prepare_file_for_module_load(struct file *file) -{ - if (!file || !(file->f_mode & FMODE_READ)) - return -EBADF; - if (!S_ISREG(file_inode(file)->i_mode)) - return -EINVAL; - return exclusive_deny_write_access(file); -} - -SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags) -{ - struct fd f; - int err; - - err = may_init_module(); - if (err) - return err; - - pr_debug("finit_module: fd=%d, uargs=%p, flags=%i\n", fd, uargs, flags); - - if (flags & ~(MODULE_INIT_IGNORE_MODVERSIONS - |MODULE_INIT_IGNORE_VERMAGIC - |MODULE_INIT_COMPRESSED_FILE)) - return -EINVAL; - - f = fdget(fd); - err = prepare_file_for_module_load(f.file); - if (!err) { - err = file_init_module(f.file, uargs, flags); - allow_write_access(f.file); - } - fdput(f); - return err; -} - /* Keep in sync with MODULE_FLAGS_BUF_SIZE !!! */ char *module_flags(struct module *mod, char *buf, bool show_state) { -- cgit v1.2.3-70-g09d2