From c8f4c36f81623002165dce874fa60bb0c154b10e Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Fri, 23 Feb 2018 13:45:28 +0200 Subject: direct-io: Remove unused DIO_ASYNC_EXTEND flag This flag was added by 6039257378e4 ("direct-io: add flag to allow aio writes beyond i_size") to support XFS. However, with the rework of XFS' DIO's path to use iomap in acdda3aae146 ("xfs: use iomap_dio_rw") it became redundant. So let's remove it. Reviewed-by: Christoph Hellwig Signed-off-by: Nikolay Borisov Signed-off-by: Jens Axboe --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2a815560fda0..260c233e7375 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2977,9 +2977,6 @@ enum { /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, - /* filesystem can handle aio writes beyond i_size */ - DIO_ASYNC_EXTEND = 0x04, - /* inode/fs/bdev does not need truncate protection */ DIO_SKIP_DIO_COUNT = 0x08, }; -- cgit v1.2.3 From ce3077ee80d6ac1087c06441f4c63ce5f13ef12c Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Fri, 23 Feb 2018 13:45:29 +0200 Subject: direct-io: Remove unused DIO_SKIP_DIO_COUNT logic This flag was added by fe0f07d08ee3 ("direct-io: only inc/deci inode->i_dio_count for file systems") as means to optimise the atomic modificaiton of the variable for blockdevices. However with the advent of 542ff7bf18c6 ("block: new direct I/O implementation") it became unused. So let's remove it. Reviewed-by: Christoph Hellwig Signed-off-by: Nikolay Borisov Signed-off-by: Jens Axboe --- include/linux/fs.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 260c233e7375..9bee267209e5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2976,9 +2976,6 @@ enum { /* filesystem does not support filling holes */ DIO_SKIP_HOLES = 0x02, - - /* inode/fs/bdev does not need truncate protection */ - DIO_SKIP_DIO_COUNT = 0x08, }; void dio_end_io(struct bio *bio); -- cgit v1.2.3 From 1c94984396dc7bc40b4f6899674eaa41f29a4f6e Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 1 Mar 2018 00:19:21 +0100 Subject: vfs: make sure struct filename->iname is word-aligned I noticed that offsetof(struct filename, iname) is actually 28 on 64 bit platforms, so we always pass an unaligned pointer to strncpy_from_user. This is mostly a problem for those 64 bit platforms without HAVE_EFFICIENT_UNALIGNED_ACCESS, but even on x86_64, unaligned accesses carry a penalty. A user-space microbenchmark doing nothing but strncpy_from_user from the same (aligned) source string runs about 5% faster when the destination is aligned. That number increases to 20% when the string is long enough (~32 bytes) that we cross a cache line boundary - that's for example the case for about half the files a "git status" in a kernel tree ends up stat'ing. This won't make any real-life workloads 5%, or even 1%, faster, but path lookup is common enough that cutting even a few cycles should be worthwhile. So ensure we always pass an aligned destination pointer to strncpy_from_user. Instead of explicit padding, simply swap the refcnt and aname members, as suggested by Al Viro. Signed-off-by: Rasmus Villemoes Signed-off-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2a815560fda0..d7b2caadb292 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2380,8 +2380,8 @@ struct audit_names; struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ - struct audit_names *aname; int refcnt; + struct audit_names *aname; const char iname[]; }; -- cgit v1.2.3 From 08fdc8a0138afaf324296a342f32ad26ec465e43 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Tue, 3 Oct 2017 18:17:41 +0200 Subject: buffer.c: call thaw_super during emergency thaw There are 2 distinct freezing mechanisms - one operates on block devices and another one directly on super blocks. Both end up with the same result, but thaw of only one of these does not thaw the other. In particular fsfreeze --freeze uses the ioctl variant going to the super block. Since prior to this patch emergency thaw was not doing a relevant thaw, filesystems frozen with this method remained unaffected. The patch is a hack which adds blind unfreezing. In order to keep the super block write-locked the whole time the code is shuffled around and the newly introduced __iterate_supers is employed. Signed-off-by: Mateusz Guzik Signed-off-by: Al Viro --- include/linux/fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 339e73742e73..b864fcb3b5aa 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2428,6 +2428,7 @@ extern int sync_blockdev(struct block_device *bdev); extern void kill_bdev(struct block_device *); extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); +extern void emergency_thaw_bdev(struct super_block *sb); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); @@ -2453,6 +2454,11 @@ static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) return 0; } +static inline int emergency_thaw_bdev(struct super_block *sb) +{ + return 0; +} + static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) { } -- cgit v1.2.3 From 57b56ac6fecb05c3192586e4892572dd13d972de Mon Sep 17 00:00:00 2001 From: Mimi Zohar Date: Wed, 21 Feb 2018 11:33:37 -0500 Subject: ima: fail file signature verification on non-init mounted filesystems FUSE can be mounted by unprivileged users either today with fusermount installed with setuid, or soon with the upcoming patches to allow FUSE mounts in a non-init user namespace. This patch addresses the new unprivileged non-init mounted filesystems, which are untrusted, by failing the signature verification. This patch defines two new flags SB_I_IMA_UNVERIFIABLE_SIGNATURE and SB_I_UNTRUSTED_MOUNTER. Signed-off-by: Mimi Zohar Cc: Miklos Szeredi Cc: Seth Forshee Cc: Dongsu Park Cc: Alban Crequy Acked-by: Serge Hallyn Acked-by: "Eric W. Biederman" --- include/linux/fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index c6baf767619e..d9e60824c374 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1321,6 +1321,8 @@ extern int send_sigurg(struct fown_struct *fown); /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ +#define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 +#define SB_I_UNTRUSTED_MOUNTER 0x00000040 /* Possible states of 'frozen' field */ enum { -- cgit v1.2.3 From 0e11f6443f522f89509495b13ef1f3745640144d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 21 Feb 2018 07:54:49 -0800 Subject: fs: move I_DIRTY_INODE to fs.h And use it in a few more places rather than opencoding the values. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index d7b2caadb292..00da24bc0350 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2014,7 +2014,8 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) #define I_WB_SWITCH (1 << 13) #define I_OVL_INUSE (1 << 14) -#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) +#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) +#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) extern void __mark_inode_dirty(struct inode *, int); -- cgit v1.2.3 From f44c77630d26ca2c2a60b20c47dd9ce07c4361b3 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 7 Mar 2018 15:26:44 -0800 Subject: fs, dax: prepare for dax-specific address_space_operations In preparation for the dax implementation to start associating dax pages to inodes via page->mapping, we need to provide a 'struct address_space_operations' instance for dax. Define some generic VFS aops helpers for dax. These noop implementations are there in the dax case to prevent the VFS from falling back to operations with page-cache assumptions, dax_writeback_mapping_range() may not be referenced in the FS_DAX=n case. Cc: Jeff Moyer Cc: Ross Zwisler Suggested-by: Matthew Wilcox Suggested-by: Jan Kara Suggested-by: Christoph Hellwig Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara Suggested-by: Dave Chinner Signed-off-by: Dan Williams --- include/linux/fs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 79c413985305..44f7f7080faa 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3129,6 +3129,10 @@ extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern int noop_fsync(struct file *, loff_t, loff_t, int); +extern int noop_set_page_dirty(struct page *page); +extern void noop_invalidatepage(struct page *page, unsigned int offset, + unsigned int length); +extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, -- cgit v1.2.3 From a09acf4b43b90581bf53b0c03cc84ed693bf27e2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 9 Apr 2018 21:12:30 +0100 Subject: vfs: Remove the const from dir_context::actor Remove the const marking from the actor function pointer in the dir_context struct. The const prevents the structure from being used as part of a kmalloc'd object as it makes the compiler require that the actor member be set at object initialisation time (or not at all), incuring something like the following error if you try and set it later: fs/afs/dir.c:556:20: error: assignment of read-only member 'actor' Marking the member const like this adds very little in the way of sanity checking as the type checking system is likely to provide sufficient - and if not, the kernel is very likely to oops repeatably in this case. Fixes: ac6614b76478 ("[readdir] constify ->actor") Signed-off-by: David Howells Reviewed-by: Al Viro --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 1ee7f592e239..3a5c19d9f651 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1667,7 +1667,7 @@ typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { - const filldir_t actor; + filldir_t actor; loff_t pos; }; -- cgit v1.2.3 From b93b016313b3ba8003c3b8bb71f569af91f19fc7 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 10 Apr 2018 16:36:56 -0700 Subject: page cache: use xa_lock Remove the address_space ->tree_lock and use the xa_lock newly added to the radix_tree_root. Rename the address_space ->page_tree to ->i_pages, since we don't really care that it's a tree. [willy@infradead.org: fix nds32, fs/dax.c] Link: http://lkml.kernel.org/r/20180406145415.GB20605@bombadil.infradead.orgLink: http://lkml.kernel.org/r/20180313132639.17387-9-willy@infradead.org Signed-off-by: Matthew Wilcox Acked-by: Jeff Layton Cc: Darrick J. Wong Cc: Dave Chinner Cc: Ryusuke Konishi Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux/fs.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2aa02cad94d4..92efaf1f8977 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -390,12 +391,11 @@ int pagecache_write_end(struct file *, struct address_space *mapping, struct address_space { struct inode *host; /* owner: inode, block_device */ - struct radix_tree_root page_tree; /* radix tree of all pages */ - spinlock_t tree_lock; /* and lock protecting it */ + struct radix_tree_root i_pages; /* cached pages */ atomic_t i_mmap_writable;/* count VM_SHARED mappings */ struct rb_root_cached i_mmap; /* tree of private and shared mappings */ struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ - /* Protected by tree_lock together with the radix tree */ + /* Protected by the i_pages lock */ unsigned long nrpages; /* number of total pages */ /* number of shadow or DAX exceptional entries */ unsigned long nrexceptional; @@ -1989,7 +1989,7 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell - * wb stat updates to grab mapping->tree_lock. See + * wb stat updates to grab the i_pages lock. See * inode_switch_wb_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper -- cgit v1.2.3