From 01de85e057328ecbef36e108673b1e81059d54c1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 17 Oct 2006 19:50:36 +0200 Subject: [PATCH] Add lockless helpers for remove_suid() Right now users have to grab i_mutex before calling remove_suid(), in the unlikely event that a call to ->setattr() may be needed. Split up the function in two parts: - One to check if we need to remove suid - One to actually remove it The first we can call lockless. Signed-off-by: Jens Axboe --- mm/filemap.c | 30 ++++++++++++++++++++++-------- 1 file changed, 22 insertions(+), 8 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 3464b681f844..7c7addb9333c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1884,11 +1884,10 @@ repeat: * if suid or (sgid and xgrp) * remove privs */ -int remove_suid(struct dentry *dentry) +int should_remove_suid(struct dentry *dentry) { mode_t mode = dentry->d_inode->i_mode; int kill = 0; - int result = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) @@ -1901,13 +1900,28 @@ int remove_suid(struct dentry *dentry) if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) kill |= ATTR_KILL_SGID; - if (unlikely(kill && !capable(CAP_FSETID))) { - struct iattr newattrs; + if (unlikely(kill && !capable(CAP_FSETID))) + return kill; - newattrs.ia_valid = ATTR_FORCE | kill; - result = notify_change(dentry, &newattrs); - } - return result; + return 0; +} + +int __remove_suid(struct dentry *dentry, int kill) +{ + struct iattr newattrs; + + newattrs.ia_valid = ATTR_FORCE | kill; + return notify_change(dentry, &newattrs); +} + +int remove_suid(struct dentry *dentry) +{ + int kill = should_remove_suid(dentry); + + if (unlikely(kill)) + return __remove_suid(dentry, kill); + + return 0; } EXPORT_SYMBOL(remove_suid); -- cgit v1.2.3 From fb5527e68d495650a7658fec9a7246bf922db212 Mon Sep 17 00:00:00 2001 From: Jeff Moyer Date: Thu, 19 Oct 2006 23:28:13 -0700 Subject: [PATCH] direct-io: sync and invalidate file region when falling back to buffered write When direct-io falls back to buffered write, it will just leave the dirty data floating about in pagecache, pending regular writeback. But normal direct-io semantics are that IO is synchronous, and that it leaves no pagecache behind. So change the fallback-to-buffered-write code to sync the file region and to then strip away the pagecache, just as a regular direct-io write would do. Acked-by: Jeff Moyer Cc: Zach Brown Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 51 +++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 45 insertions(+), 6 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 3464b681f844..57faa8d12099 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2222,7 +2222,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t *ppos) { struct file *file = iocb->ki_filp; - const struct address_space * mapping = file->f_mapping; + struct address_space * mapping = file->f_mapping; size_t ocount; /* original count */ size_t count; /* after file limit checks */ struct inode *inode = mapping->host; @@ -2275,8 +2275,11 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (unlikely(file->f_flags & O_DIRECT)) { - written = generic_file_direct_write(iocb, iov, - &nr_segs, pos, ppos, count, ocount); + loff_t endbyte; + ssize_t written_buffered; + + written = generic_file_direct_write(iocb, iov, &nr_segs, pos, + ppos, count, ocount); if (written < 0 || written == count) goto out; /* @@ -2285,10 +2288,46 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, */ pos += written; count -= written; - } + written_buffered = generic_file_buffered_write(iocb, iov, + nr_segs, pos, ppos, count, + written); + /* + * If generic_file_buffered_write() retuned a synchronous error + * then we want to return the number of bytes which were + * direct-written, or the error code if that was zero. Note + * that this differs from normal direct-io semantics, which + * will return -EFOO even if some bytes were written. + */ + if (written_buffered < 0) { + err = written_buffered; + goto out; + } - written = generic_file_buffered_write(iocb, iov, nr_segs, - pos, ppos, count, written); + /* + * We need to ensure that the page cache pages are written to + * disk and invalidated to preserve the expected O_DIRECT + * semantics. + */ + endbyte = pos + written_buffered - written - 1; + err = do_sync_file_range(file, pos, endbyte, + SYNC_FILE_RANGE_WAIT_BEFORE| + SYNC_FILE_RANGE_WRITE| + SYNC_FILE_RANGE_WAIT_AFTER); + if (err == 0) { + written = written_buffered; + invalidate_mapping_pages(mapping, + pos >> PAGE_CACHE_SHIFT, + endbyte >> PAGE_CACHE_SHIFT); + } else { + /* + * We don't know how much we wrote, so just return + * the number of bytes which were direct-written + */ + } + } else { + written = generic_file_buffered_write(iocb, iov, nr_segs, + pos, ppos, count, written); + } out: current->backing_dev_info = NULL; return written ? written : err; -- cgit v1.2.3 From 82591e6ea234762eeaa8b2337fe060ed438c18dc Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Thu, 19 Oct 2006 23:29:10 -0700 Subject: [PATCH] mm: more commenting on lock ordering Clarify lockorder comments now that sys_msync dropps mmap_sem before calling do_fsync. Signed-off-by: Nick Piggin Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 4 ++-- mm/rmap.c | 36 +++++++++++++++--------------------- 2 files changed, 17 insertions(+), 23 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 57faa8d12099..8558732e85c1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -75,8 +75,8 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, * ->mmap_sem * ->lock_page (access_process_vm) * - * ->mmap_sem - * ->i_mutex (msync) + * ->i_mutex (generic_file_buffered_write) + * ->mmap_sem (fault_in_pages_readable->do_page_fault) * * ->i_mutex * ->i_alloc_sem (various) diff --git a/mm/rmap.c b/mm/rmap.c index a9136d8b7577..d8a842a586db 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -21,27 +21,21 @@ * Lock ordering in mm: * * inode->i_mutex (while writing or truncating, not reading or faulting) - * inode->i_alloc_sem - * - * When a page fault occurs in writing from user to file, down_read - * of mmap_sem nests within i_mutex; in sys_msync, i_mutex nests within - * down_read of mmap_sem; i_mutex and down_write of mmap_sem are never - * taken together; in truncation, i_mutex is taken outermost. - * - * mm->mmap_sem - * page->flags PG_locked (lock_page) - * mapping->i_mmap_lock - * anon_vma->lock - * mm->page_table_lock or pte_lock - * zone->lru_lock (in mark_page_accessed, isolate_lru_page) - * swap_lock (in swap_duplicate, swap_info_get) - * mmlist_lock (in mmput, drain_mmlist and others) - * mapping->private_lock (in __set_page_dirty_buffers) - * inode_lock (in set_page_dirty's __mark_inode_dirty) - * sb_lock (within inode_lock in fs/fs-writeback.c) - * mapping->tree_lock (widely used, in set_page_dirty, - * in arch-dependent flush_dcache_mmap_lock, - * within inode_lock in __sync_single_inode) + * inode->i_alloc_sem (vmtruncate_range) + * mm->mmap_sem + * page->flags PG_locked (lock_page) + * mapping->i_mmap_lock + * anon_vma->lock + * mm->page_table_lock or pte_lock + * zone->lru_lock (in mark_page_accessed, isolate_lru_page) + * swap_lock (in swap_duplicate, swap_info_get) + * mmlist_lock (in mmput, drain_mmlist and others) + * mapping->private_lock (in __set_page_dirty_buffers) + * inode_lock (in set_page_dirty's __mark_inode_dirty) + * sb_lock (within inode_lock in fs/fs-writeback.c) + * mapping->tree_lock (widely used, in set_page_dirty, + * in arch-dependent flush_dcache_mmap_lock, + * within inode_lock in __sync_single_inode) */ #include -- cgit v1.2.3 From 2ae88149a27cadf2840e0ab8155bef13be285c03 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Sat, 28 Oct 2006 10:38:23 -0700 Subject: [PATCH] mm: clean up pagecache allocation - Consolidate page_cache_alloc - Fix splice: only the pagecache pages and filesystem data need to use mapping_gfp_mask. - Fix grab_cache_page_nowait: same as splice, also honour NUMA placement. Signed-off-by: Nick Piggin Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/splice.c | 9 ++++----- include/linux/pagemap.h | 14 +++++++++----- mm/filemap.c | 24 ++++++------------------ 3 files changed, 19 insertions(+), 28 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/splice.c b/fs/splice.c index 49fb9f129938..8d705954d294 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -74,7 +74,7 @@ static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe, wait_on_page_writeback(page); if (PagePrivate(page)) - try_to_release_page(page, mapping_gfp_mask(mapping)); + try_to_release_page(page, GFP_KERNEL); /* * If we succeeded in removing the mapping, set LRU flag @@ -333,7 +333,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, break; error = add_to_page_cache_lru(page, mapping, index, - mapping_gfp_mask(mapping)); + GFP_KERNEL); if (unlikely(error)) { page_cache_release(page); if (error == -EEXIST) @@ -557,7 +557,6 @@ static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, { struct file *file = sd->file; struct address_space *mapping = file->f_mapping; - gfp_t gfp_mask = mapping_gfp_mask(mapping); unsigned int offset, this_len; struct page *page; pgoff_t index; @@ -591,7 +590,7 @@ static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, goto find_page; page = buf->page; - if (add_to_page_cache(page, mapping, index, gfp_mask)) { + if (add_to_page_cache(page, mapping, index, GFP_KERNEL)) { unlock_page(page); goto find_page; } @@ -613,7 +612,7 @@ find_page: * This will also lock the page */ ret = add_to_page_cache_lru(page, mapping, index, - gfp_mask); + GFP_KERNEL); if (unlikely(ret)) goto out; } diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 64f950925151..c3e255bf8594 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -52,19 +52,23 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) void release_pages(struct page **pages, int nr, int cold); #ifdef CONFIG_NUMA -extern struct page *page_cache_alloc(struct address_space *x); -extern struct page *page_cache_alloc_cold(struct address_space *x); +extern struct page *__page_cache_alloc(gfp_t gfp); #else +static inline struct page *__page_cache_alloc(gfp_t gfp) +{ + return alloc_pages(gfp, 0); +} +#endif + static inline struct page *page_cache_alloc(struct address_space *x) { - return alloc_pages(mapping_gfp_mask(x), 0); + return __page_cache_alloc(mapping_gfp_mask(x)); } static inline struct page *page_cache_alloc_cold(struct address_space *x) { - return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0); + return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD); } -#endif typedef int filler_t(void *, struct page *); diff --git a/mm/filemap.c b/mm/filemap.c index cb26e33fd0ff..7b84dc814347 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -467,25 +467,15 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, } #ifdef CONFIG_NUMA -struct page *page_cache_alloc(struct address_space *x) +struct page *__page_cache_alloc(gfp_t gfp) { if (cpuset_do_page_mem_spread()) { int n = cpuset_mem_spread_node(); - return alloc_pages_node(n, mapping_gfp_mask(x), 0); + return alloc_pages_node(n, gfp, 0); } - return alloc_pages(mapping_gfp_mask(x), 0); + return alloc_pages(gfp, 0); } -EXPORT_SYMBOL(page_cache_alloc); - -struct page *page_cache_alloc_cold(struct address_space *x) -{ - if (cpuset_do_page_mem_spread()) { - int n = cpuset_mem_spread_node(); - return alloc_pages_node(n, mapping_gfp_mask(x)|__GFP_COLD, 0); - } - return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0); -} -EXPORT_SYMBOL(page_cache_alloc_cold); +EXPORT_SYMBOL(__page_cache_alloc); #endif static int __sleep_on_page_lock(void *word) @@ -826,7 +816,6 @@ struct page * grab_cache_page_nowait(struct address_space *mapping, unsigned long index) { struct page *page = find_get_page(mapping, index); - gfp_t gfp_mask; if (page) { if (!TestSetPageLocked(page)) @@ -834,9 +823,8 @@ grab_cache_page_nowait(struct address_space *mapping, unsigned long index) page_cache_release(page); return NULL; } - gfp_mask = mapping_gfp_mask(mapping) & ~__GFP_FS; - page = alloc_pages(gfp_mask, 0); - if (page && add_to_page_cache_lru(page, mapping, index, gfp_mask)) { + page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS); + if (page && add_to_page_cache_lru(page, mapping, index, GFP_KERNEL)) { page_cache_release(page); page = NULL; } -- cgit v1.2.3