X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Ffilemap.c;h=3342067ca436e33a8399664a35c7265986272427;hb=e0a42726794f71336ff4b26084d453dd597471ce;hp=4ef24a397684f7b9a51c70e94843f4cff35ed281;hpb=cc918c7ab7da017bfaf9661420bb5c462e057cfb;p=linux-2.6 diff --git a/mm/filemap.c b/mm/filemap.c index 4ef24a3976..3342067ca4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -28,7 +29,10 @@ #include #include #include +#include #include "filemap.h" +#include "internal.h" + /* * FIXME: remove all knowledge of the buffer layer from the core VM */ @@ -61,7 +65,7 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, * ->swap_lock (exclusive_swap_page, others) * ->mapping->tree_lock * - * ->i_sem + * ->i_mutex * ->i_mmap_lock (truncate->unmap_mapping_range) * * ->mmap_sem @@ -73,9 +77,9 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, * ->lock_page (access_process_vm) * * ->mmap_sem - * ->i_sem (msync) + * ->i_mutex (msync) * - * ->i_sem + * ->i_mutex * ->i_alloc_sem (various) * * ->inode_lock @@ -93,6 +97,7 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, * ->private_lock (try_to_unmap_one) * ->tree_lock (try_to_unmap_one) * ->zone.lru_lock (follow_page->mark_page_accessed) + * ->zone.lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) * ->tree_lock (page_remove_rmap->set_page_dirty) * ->inode_lock (page_remove_rmap->set_page_dirty) @@ -170,7 +175,7 @@ static int sync_page(void *word) * dirty pages that lie within the byte offsets * @mapping: address space structure to write * @start: offset in bytes where the range starts - * @end: offset in bytes where the range ends + * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as @@ -178,15 +183,15 @@ static int sync_page(void *word) * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. */ -static int __filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end, int sync_mode) +int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, + loff_t end, int sync_mode) { int ret; struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = mapping->nrpages * 2, - .start = start, - .end = end, + .range_start = start, + .range_end = end, }; if (!mapping_cap_writeback_dirty(mapping)) @@ -199,7 +204,7 @@ static int __filemap_fdatawrite_range(struct address_space *mapping, static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { - return __filemap_fdatawrite_range(mapping, 0, 0, sync_mode); + return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); } int filemap_fdatawrite(struct address_space *mapping) @@ -208,8 +213,8 @@ int filemap_fdatawrite(struct address_space *mapping) } EXPORT_SYMBOL(filemap_fdatawrite); -static int filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end) +static int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, + loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } @@ -228,7 +233,7 @@ EXPORT_SYMBOL(filemap_flush); * Wait for writeback to complete against pages indexed by start->end * inclusive */ -static int wait_on_page_writeback_range(struct address_space *mapping, +int wait_on_page_writeback_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { struct pagevec pvec; @@ -276,11 +281,11 @@ static int wait_on_page_writeback_range(struct address_space *mapping, * integrity" operation. It waits upon in-flight writeout before starting and * waiting upon new writeout. If there was an IO error, return it. * - * We need to re-take i_sem during the generic_osync_inode list walk because + * We need to re-take i_mutex during the generic_osync_inode list walk because * it is otherwise livelockable. */ int sync_page_range(struct inode *inode, struct address_space *mapping, - loff_t pos, size_t count) + loff_t pos, loff_t count) { pgoff_t start = pos >> PAGE_CACHE_SHIFT; pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT; @@ -290,9 +295,9 @@ int sync_page_range(struct inode *inode, struct address_space *mapping, return 0; ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1); if (ret == 0) { - down(&inode->i_sem); + mutex_lock(&inode->i_mutex); ret = generic_osync_inode(inode, mapping, OSYNC_METADATA); - up(&inode->i_sem); + mutex_unlock(&inode->i_mutex); } if (ret == 0) ret = wait_on_page_writeback_range(mapping, start, end); @@ -301,13 +306,12 @@ int sync_page_range(struct inode *inode, struct address_space *mapping, EXPORT_SYMBOL(sync_page_range); /* - * Note: Holding i_sem across sync_page_range_nolock is not a good idea + * Note: Holding i_mutex across sync_page_range_nolock is not a good idea * as it forces O_SYNC writers to different parts of the same file * to be serialised right until io completion. */ -static int sync_page_range_nolock(struct inode *inode, - struct address_space *mapping, - loff_t pos, size_t count) +int sync_page_range_nolock(struct inode *inode, struct address_space *mapping, + loff_t pos, loff_t count) { pgoff_t start = pos >> PAGE_CACHE_SHIFT; pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT; @@ -322,6 +326,7 @@ static int sync_page_range_nolock(struct inode *inode, ret = wait_on_page_writeback_range(mapping, start, end); return ret; } +EXPORT_SYMBOL(sync_page_range_nolock); /** * filemap_fdatawait - walk the list of under-writeback pages of the given @@ -343,30 +348,50 @@ EXPORT_SYMBOL(filemap_fdatawait); int filemap_write_and_wait(struct address_space *mapping) { - int retval = 0; + int err = 0; if (mapping->nrpages) { - retval = filemap_fdatawrite(mapping); - if (retval == 0) - retval = filemap_fdatawait(mapping); + err = filemap_fdatawrite(mapping); + /* + * Even if the above returned error, the pages may be + * written partially (e.g. -ENOSPC), so we wait for it. + * But the -EIO is special case, it may indicate the worst + * thing (e.g. bug) happened, so we avoid waiting for it. + */ + if (err != -EIO) { + int err2 = filemap_fdatawait(mapping); + if (!err) + err = err2; + } } - return retval; + return err; } +EXPORT_SYMBOL(filemap_write_and_wait); +/* + * Write out and wait upon file offsets lstart->lend, inclusive. + * + * Note that `lend' is inclusive (describes the last byte to be written) so + * that this function can be used to write to the very end-of-file (end = -1). + */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { - int retval = 0; + int err = 0; if (mapping->nrpages) { - retval = __filemap_fdatawrite_range(mapping, lstart, lend, - WB_SYNC_ALL); - if (retval == 0) - retval = wait_on_page_writeback_range(mapping, - lstart >> PAGE_CACHE_SHIFT, - lend >> PAGE_CACHE_SHIFT); + err = __filemap_fdatawrite_range(mapping, lstart, lend, + WB_SYNC_ALL); + /* See comment of filemap_write_and_wait() */ + if (err != -EIO) { + int err2 = wait_on_page_writeback_range(mapping, + lstart >> PAGE_CACHE_SHIFT, + lend >> PAGE_CACHE_SHIFT); + if (!err) + err = err2; + } } - return retval; + return err; } /* @@ -409,6 +434,28 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, return ret; } +#ifdef CONFIG_NUMA +struct page *page_cache_alloc(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), 0); + } + return alloc_pages(mapping_gfp_mask(x), 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); +#endif + /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of @@ -650,6 +697,38 @@ unsigned find_get_pages(struct address_space *mapping, pgoff_t start, return ret; } +/** + * find_get_pages_contig - gang contiguous pagecache lookup + * @mapping: The address_space to search + * @index: The starting page index + * @nr_pages: The maximum number of pages + * @pages: Where the resulting pages are placed + * + * find_get_pages_contig() works exactly like find_get_pages(), except + * that the returned number of pages are guaranteed to be contiguous. + * + * find_get_pages_contig() returns the number of pages which were found. + */ +unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, + unsigned int nr_pages, struct page **pages) +{ + unsigned int i; + unsigned int ret; + + read_lock_irq(&mapping->tree_lock); + ret = radix_tree_gang_lookup(&mapping->page_tree, + (void **)pages, index, nr_pages); + for (i = 0; i < ret; i++) { + if (pages[i]->mapping == NULL || pages[i]->index != index) + break; + + page_cache_get(pages[i]); + index++; + } + read_unlock_irq(&mapping->tree_lock); + return i; +} + /* * Like find_get_pages, except we only return pages which are tagged with * `tag'. We update *index to index the next page for the traversal. @@ -1878,7 +1957,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, /* * Sync the fs metadata but not the minor inode changes and * of course not the data as we did direct DMA for the IO. - * i_sem is held, which protects generic_osync_inode() from + * i_mutex is held, which protects generic_osync_inode() from * livelocking. */ if (written >= 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { @@ -2094,7 +2173,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, if (err) goto out; - inode_update_time(inode, 1); + file_update_time(file); /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (unlikely(file->f_flags & O_DIRECT)) { @@ -2181,10 +2260,10 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf, BUG_ON(iocb->ki_pos != pos); - down(&inode->i_sem); + mutex_lock(&inode->i_mutex); ret = __generic_file_aio_write_nolock(iocb, &local_iov, 1, &iocb->ki_pos); - up(&inode->i_sem); + mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { ssize_t err; @@ -2206,9 +2285,9 @@ ssize_t generic_file_write(struct file *file, const char __user *buf, struct iovec local_iov = { .iov_base = (void __user *)buf, .iov_len = count }; - down(&inode->i_sem); + mutex_lock(&inode->i_mutex); ret = __generic_file_write_nolock(file, &local_iov, 1, ppos); - up(&inode->i_sem); + mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { ssize_t err; @@ -2242,9 +2321,9 @@ ssize_t generic_file_writev(struct file *file, const struct iovec *iov, struct inode *inode = mapping->host; ssize_t ret; - down(&inode->i_sem); + mutex_lock(&inode->i_mutex); ret = __generic_file_write_nolock(file, iov, nr_segs, ppos); - up(&inode->i_sem); + mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { int err; @@ -2258,7 +2337,7 @@ ssize_t generic_file_writev(struct file *file, const struct iovec *iov, EXPORT_SYMBOL(generic_file_writev); /* - * Called under i_sem for writes to S_ISREG files. Returns -EIO if something + * Called under i_mutex for writes to S_ISREG files. Returns -EIO if something * went wrong during pagecache shootdown. */ static ssize_t