From 5cf6a51e6062afe7cc507f32f1e5f7e6497ae844 Mon Sep 17 00:00:00 2001 From: Daniel Baluta Date: Fri, 20 Nov 2015 15:56:53 -0800 Subject: configfs: allow dynamic group creation This patchset introduces IIO software triggers, offers a way of configuring them via configfs and adds the IIO hrtimer based interrupt source to be used with software triggers. The architecture is now split in 3 parts, to remove all IIO trigger specific parts from IIO configfs core: (1) IIO configfs - creates the root of the IIO configfs subsys. (2) IIO software triggers - software trigger implementation, dynamically creating /config/iio/triggers group. (3) IIO hrtimer trigger - is the first interrupt source for software triggers (with syfs to follow). Each trigger type can implement its own set of attributes. Lockdep seems to be happy with the locking in configfs patch. This patch (of 5): We don't want to hardcode default groups at subsystem creation time. We export: * configfs_register_group * configfs_unregister_group to allow drivers to programatically create/destroy groups later, after module init time. This is needed for IIO configfs support. (akpm: the other 4 patches to be merged via the IIO tree) Signed-off-by: Daniel Baluta Suggested-by: Lars-Peter Clausen Reviewed-by: Christoph Hellwig Acked-by: Joel Becker Cc: Hartmut Knaack Cc: Octavian Purdila Cc: Paul Bolle Cc: Adriana Reus Cc: Cristina Opriceana Cc: Peter Meerwald Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/configfs/dir.c | 110 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 110 insertions(+) (limited to 'fs') diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index c81ce7f200a6..a7a1b218f308 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1636,6 +1636,116 @@ const struct file_operations configfs_dir_operations = { .iterate = configfs_readdir, }; +/** + * configfs_register_group - creates a parent-child relation between two groups + * @parent_group: parent group + * @group: child group + * + * link groups, creates dentry for the child and attaches it to the + * parent dentry. + * + * Return: 0 on success, negative errno code on error + */ +int configfs_register_group(struct config_group *parent_group, + struct config_group *group) +{ + struct configfs_subsystem *subsys = parent_group->cg_subsys; + struct dentry *parent; + int ret; + + mutex_lock(&subsys->su_mutex); + link_group(parent_group, group); + mutex_unlock(&subsys->su_mutex); + + parent = parent_group->cg_item.ci_dentry; + + mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT); + ret = create_default_group(parent_group, group); + if (!ret) { + spin_lock(&configfs_dirent_lock); + configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); + spin_unlock(&configfs_dirent_lock); + } + mutex_unlock(&d_inode(parent)->i_mutex); + return ret; +} +EXPORT_SYMBOL(configfs_register_group); + +/** + * configfs_unregister_group() - unregisters a child group from its parent + * @group: parent group to be unregistered + * + * Undoes configfs_register_group() + */ +void configfs_unregister_group(struct config_group *group) +{ + struct configfs_subsystem *subsys = group->cg_subsys; + struct dentry *dentry = group->cg_item.ci_dentry; + struct dentry *parent = group->cg_item.ci_parent->ci_dentry; + + mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT); + spin_lock(&configfs_dirent_lock); + configfs_detach_prep(dentry, NULL); + spin_unlock(&configfs_dirent_lock); + + configfs_detach_group(&group->cg_item); + d_inode(dentry)->i_flags |= S_DEAD; + dont_mount(dentry); + d_delete(dentry); + mutex_unlock(&d_inode(parent)->i_mutex); + + dput(dentry); + + mutex_lock(&subsys->su_mutex); + unlink_group(group); + mutex_unlock(&subsys->su_mutex); +} +EXPORT_SYMBOL(configfs_unregister_group); + +/** + * configfs_register_default_group() - allocates and registers a child group + * @parent_group: parent group + * @name: child group name + * @item_type: child item type description + * + * boilerplate to allocate and register a child group with its parent. We need + * kzalloc'ed memory because child's default_group is initially empty. + * + * Return: allocated config group or ERR_PTR() on error + */ +struct config_group * +configfs_register_default_group(struct config_group *parent_group, + const char *name, + struct config_item_type *item_type) +{ + int ret; + struct config_group *group; + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return ERR_PTR(-ENOMEM); + config_group_init_type_name(group, name, item_type); + + ret = configfs_register_group(parent_group, group); + if (ret) { + kfree(group); + return ERR_PTR(ret); + } + return group; +} +EXPORT_SYMBOL(configfs_register_default_group); + +/** + * configfs_unregister_default_group() - unregisters and frees a child group + * @group: the group to act on + */ +void configfs_unregister_default_group(struct config_group *group) +{ + configfs_unregister_group(group); + kfree(group); +} +EXPORT_SYMBOL(configfs_unregister_default_group); + int configfs_register_subsystem(struct configfs_subsystem *subsys) { int err; -- cgit v1.2.3 From 1491e30ed1a741009d1d38f9285f7a29e6c05c78 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 20 Nov 2015 15:56:56 -0800 Subject: ncpfs: don't allow negative timeouts This code causes a static checker warning because it's a user controlled variable where we cap the upper bound but not the lower bound. Let's return an -EINVAL for negative timeouts. [akpm@linux-foundation.org: remove unneeded `else'] Signed-off-by: Dan Carpenter Reviewed-by: Jan Kara Cc: Petr Vandrovec Cc: David Howells Cc: Jan Kara Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ncpfs/ioctl.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 79b113048eac..0a3f9b594602 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -525,6 +525,8 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg switch (rqdata.cmd) { case NCP_LOCK_EX: case NCP_LOCK_SH: + if (rqdata.timeout < 0) + return -EINVAL; if (rqdata.timeout == 0) rqdata.timeout = NCP_LOCK_DEFAULT_TIMEOUT; else if (rqdata.timeout > NCP_LOCK_MAX_TIMEOUT) -- cgit v1.2.3 From 1817889e3b2cc1db8abb595712095129ff9156c1 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 20 Nov 2015 15:57:13 -0800 Subject: mm/hugetlbfs: fix bugs in fallocate hole punch of areas with holes Hugh Dickins pointed out problems with the new hugetlbfs fallocate hole punch code. These problems are in the routine remove_inode_hugepages and mostly occur in the case where there are holes in the range of pages to be removed. These holes could be the result of a previous hole punch or simply sparse allocation. The current code could access pages outside the specified range. remove_inode_hugepages handles both hole punch and truncate operations. Page index handling was fixed/cleaned up so that the loop index always matches the page being processed. The code now only makes a single pass through the range of pages as it was determined page faults could not race with truncate. A cond_resched() was added after removing up to PAGEVEC_SIZE pages. Some totally unnecessary code in hugetlbfs_fallocate() that remained from early development was also removed. Tested with fallocate tests submitted here: http://librelist.com/browser//libhugetlbfs/2015/6/25/patch-tests-add-tests-for-fallocate-system-call/ And, some ftruncate tests under development Fixes: b5cec28d36f5 ("hugetlbfs: truncate_hugepages() takes a range of pages") Signed-off-by: Mike Kravetz Acked-by: Hugh Dickins Cc: Dave Hansen Cc: Naoya Horiguchi Cc: Davidlohr Bueso Cc: "Hillf Danton" Cc: [4.3] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 65 ++++++++++++++++++++++++++-------------------------- 1 file changed, 32 insertions(+), 33 deletions(-) (limited to 'fs') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 316adb968b65..de4bdfac0cec 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -332,12 +332,17 @@ static void remove_huge_page(struct page *page) * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserv - * maps and global counts. + * maps and global counts. Page faults can not race with truncation + * in this routine. hugetlb_no_page() prevents page faults in the + * truncated range. It checks i_size before allocation, and again after + * with the page table lock for the page held. The same lock must be + * acquired to unmap a page. * hole punch is indicated if end is not LLONG_MAX * In the hole punch case we scan the range and release found pages. * Only when releasing a page is the associated region/reserv map * deleted. The region/reserv map for ranges without associated - * pages are not modified. + * pages are not modified. Page faults can race with hole punch. + * This is indicated if we find a mapped page. * Note: If the passed end of range value is beyond the end of file, but * not LLONG_MAX this routine still performs a hole punch operation. */ @@ -361,46 +366,37 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, next = start; while (next < end) { /* - * Make sure to never grab more pages that we - * might possibly need. + * Don't grab more pages than the number left in the range. */ if (end - next < lookup_nr) lookup_nr = end - next; /* - * This pagevec_lookup() may return pages past 'end', - * so we must check for page->index > end. + * When no more pages are found, we are done. */ - if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) { - if (next == start) - break; - next = start; - continue; - } + if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) + break; for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; u32 hash; + /* + * The page (index) could be beyond end. This is + * only possible in the punch hole case as end is + * max page offset in the truncate case. + */ + next = page->index; + if (next >= end) + break; + hash = hugetlb_fault_mutex_hash(h, current->mm, &pseudo_vma, mapping, next, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); lock_page(page); - if (page->index >= end) { - unlock_page(page); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); - next = end; /* we are done */ - break; - } - - /* - * If page is mapped, it was faulted in after being - * unmapped. Do nothing in this race case. In the - * normal case page is not mapped. - */ - if (!page_mapped(page)) { + if (likely(!page_mapped(page))) { bool rsv_on_error = !PagePrivate(page); /* * We must free the huge page and remove @@ -421,17 +417,23 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, hugetlb_fix_reserve_counts( inode, rsv_on_error); } + } else { + /* + * If page is mapped, it was faulted in after + * being unmapped. It indicates a race between + * hole punch and page fault. Do nothing in + * this case. Getting here in a truncate + * operation is a bug. + */ + BUG_ON(truncate_op); } - if (page->index > next) - next = page->index; - - ++next; unlock_page(page); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); } + ++next; huge_pagevec_release(&pvec); + cond_resched(); } if (truncate_op) @@ -647,9 +649,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); inode->i_ctime = CURRENT_TIME; - spin_lock(&inode->i_lock); - inode->i_private = NULL; - spin_unlock(&inode->i_lock); out: mutex_unlock(&inode->i_mutex); return error; -- cgit v1.2.3 From 928a477102c4fc6739883415b66987207e3502f4 Mon Sep 17 00:00:00 2001 From: OGAWA Hirofumi Date: Fri, 20 Nov 2015 15:57:15 -0800 Subject: fat: fix fake_offset handling on error path For the root directory, . and .. are faked (using dir_emit_dots()) and ctx->pos is reset from 2 to 0. A corrupted root directory could cause fat_get_entry() to fail, but ->iterate() (fat_readdir()) reports progress to the VFS (with ctx->pos rewound to 0), so any following calls to ->iterate() continue to return the same entries again and again. The result is that userspace will never see the end of the directory, causing e.g. 'ls' to hang in a getdents() loop. [hirofumi@mail.parknet.co.jp: cleanup and make sure to correct fake_offset] Reported-by: Vegard Nossum Tested-by: Vegard Nossum Signed-off-by: Richard Weinberger Signed-off-by: OGAWA Hirofumi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/fat/dir.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 4afc4d9d2e41..8b2127ffb226 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -610,9 +610,9 @@ parse_record: int status = fat_parse_long(inode, &cpos, &bh, &de, &unicode, &nr_slots); if (status < 0) { - ctx->pos = cpos; + bh = NULL; ret = status; - goto out; + goto end_of_dir; } else if (status == PARSE_INVALID) goto record_end; else if (status == PARSE_NOT_LONGNAME) @@ -654,8 +654,9 @@ parse_record: fill_len = short_len; start_filldir: - if (!fake_offset) - ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry); + ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry); + if (fake_offset && ctx->pos < 2) + ctx->pos = 2; if (!memcmp(de->name, MSDOS_DOT, MSDOS_NAME)) { if (!dir_emit_dot(file, ctx)) @@ -681,14 +682,19 @@ record_end: fake_offset = 0; ctx->pos = cpos; goto get_new; + end_of_dir: - ctx->pos = cpos; + if (fake_offset && cpos < 2) + ctx->pos = 2; + else + ctx->pos = cpos; fill_failed: brelse(bh); if (unicode) __putname(unicode); out: mutex_unlock(&sbi->s_lock); + return ret; } -- cgit v1.2.3 From 8f1eb48758aacf6c1ffce18179295adbf3bd7640 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Fri, 20 Nov 2015 15:57:30 -0800 Subject: ocfs2: fix umask ignored issue New created file's mode is not masked with umask, and this makes umask not work for ocfs2 volume. Fixes: 702e5bc ("ocfs2: use generic posix ACL infrastructure") Signed-off-by: Junxiao Bi Cc: Gang He Cc: Mark Fasheh Cc: Joel Becker Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/namei.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 3b48ac25d8a7..a03f6f433075 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -372,6 +372,8 @@ static int ocfs2_mknod(struct inode *dir, mlog_errno(status); goto leave; } + /* update inode->i_mode after mask with "umask". */ + inode->i_mode = mode; handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, S_ISDIR(mode), -- cgit v1.2.3