X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=mm%2Ffilemap.c;h=c3659a01e3a4ec58ed9022c75fde17e1af9f99c4;hb=refs%2Fheads%2Fvserver;hp=44da3d47699485004994c6af302c7406d606c569;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git diff --git a/mm/filemap.c b/mm/filemap.c index 44da3d476..c3659a01e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -9,11 +9,11 @@ * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ -#include #include #include #include #include +#include #include #include #include @@ -29,13 +29,15 @@ #include #include #include +#include #include "filemap.h" +#include "internal.h" + /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include /* for generic_osync_inode */ -#include #include static ssize_t @@ -73,8 +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) @@ -117,7 +119,7 @@ void __remove_from_page_cache(struct page *page) radix_tree_delete(&mapping->page_tree, page->index); page->mapping = NULL; mapping->nrpages--; - pagecache_acct(-1); + __dec_zone_page_state(page, NR_FILE_PAGES); } void remove_from_page_cache(struct page *page) @@ -168,27 +170,29 @@ static int sync_page(void *word) } /** - * filemap_fdatawrite_range - start writeback against all of a mapping's - * dirty pages that lie within the byte offsets + * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @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 * + * Start writeback against all of a mapping's dirty pages that lie + * within the byte offsets inclusive. + * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as - * opposed to a regular memory * cleansing writeback. The difference between + * opposed to a regular memory cleansing writeback. The difference between * 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)) @@ -201,7 +205,7 @@ 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) @@ -210,13 +214,16 @@ 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); } -/* +/** + * filemap_flush - mostly a non-blocking flush + * @mapping: target address_space + * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. */ @@ -226,11 +233,16 @@ int filemap_flush(struct address_space *mapping) } EXPORT_SYMBOL(filemap_flush); -/* +/** + * wait_on_page_writeback_range - wait for writeback to complete + * @mapping: target address_space + * @start: beginning page index + * @end: ending page index + * * 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; @@ -273,7 +285,13 @@ static int wait_on_page_writeback_range(struct address_space *mapping, return ret; } -/* +/** + * sync_page_range - write and wait on all pages in the passed range + * @inode: target inode + * @mapping: target address_space + * @pos: beginning offset in pages to write + * @count: number of bytes to write + * * Write and wait upon all the pages in the passed range. This is a "data * integrity" operation. It waits upon in-flight writeout before starting and * waiting upon new writeout. If there was an IO error, return it. @@ -302,7 +320,13 @@ int sync_page_range(struct inode *inode, struct address_space *mapping, } EXPORT_SYMBOL(sync_page_range); -/* +/** + * sync_page_range_nolock + * @inode: target inode + * @mapping: target address_space + * @pos: beginning offset in pages to write + * @count: number of bytes to write + * * 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. @@ -326,10 +350,11 @@ int sync_page_range_nolock(struct inode *inode, struct address_space *mapping, EXPORT_SYMBOL(sync_page_range_nolock); /** - * filemap_fdatawait - walk the list of under-writeback pages of the given - * address space and wait for all of them. - * + * filemap_fdatawait - wait for all under-writeback pages to complete * @mapping: address space structure to wait for + * + * Walk the list of under-writeback pages of the given address space + * and wait for all of them. */ int filemap_fdatawait(struct address_space *mapping) { @@ -365,6 +390,17 @@ int filemap_write_and_wait(struct address_space *mapping) } EXPORT_SYMBOL(filemap_write_and_wait); +/** + * filemap_write_and_wait_range - write out & wait on a file range + * @mapping: the address_space for the pages + * @lstart: offset in bytes where the range starts + * @lend: offset in bytes where the range ends (inclusive) + * + * 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) { @@ -385,8 +421,14 @@ int filemap_write_and_wait_range(struct address_space *mapping, return err; } -/* - * This function is used to add newly allocated pagecache pages: +/** + * add_to_page_cache - add newly allocated pagecache pages + * @page: page to add + * @mapping: the page's address_space + * @offset: page index + * @gfp_mask: page allocation mode + * + * This function is used to add newly allocated pagecache pages; * the page is new, so we can just run SetPageLocked() against it. * The other page state flags were set by rmqueue(). * @@ -406,14 +448,13 @@ int add_to_page_cache(struct page *page, struct address_space *mapping, page->mapping = mapping; page->index = offset; mapping->nrpages++; - pagecache_acct(1); + __inc_zone_page_state(page, NR_FILE_PAGES); } write_unlock_irq(&mapping->tree_lock); radix_tree_preload_end(); } return error; } - EXPORT_SYMBOL(add_to_page_cache); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, @@ -425,6 +466,24 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, return ret; } +#ifdef CONFIG_NUMA +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, gfp, 0); + } + return alloc_pages(gfp, 0); +} +EXPORT_SYMBOL(__page_cache_alloc); +#endif + +static int __sleep_on_page_lock(void *word) +{ + io_schedule(); + return 0; +} + /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of @@ -457,9 +516,20 @@ void fastcall wait_on_page_bit(struct page *page, int bit_nr) } EXPORT_SYMBOL(wait_on_page_bit); +void install_page_waitqueue_monitor(struct page *page, wait_queue_t *monitor) +{ + wait_queue_head_t *q = page_waitqueue(page); + unsigned long flags; + + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue(q, monitor); + spin_unlock_irqrestore(&q->lock, flags); +} + +EXPORT_SYMBOL_GPL(install_page_waitqueue_monitor); + /** - * unlock_page() - unlock a locked page - * + * unlock_page - unlock a locked page * @page: the page * * Unlocks the page and wakes up sleepers in ___wait_on_page_locked(). @@ -482,8 +552,9 @@ void fastcall unlock_page(struct page *page) } EXPORT_SYMBOL(unlock_page); -/* - * End writeback against a page. +/** + * end_page_writeback - end writeback against a page + * @page: the page */ void end_page_writeback(struct page *page) { @@ -496,10 +567,11 @@ void end_page_writeback(struct page *page) } EXPORT_SYMBOL(end_page_writeback); -/* - * Get a lock on the page, assuming we need to sleep to get it. +/** + * __lock_page - get a lock on the page, assuming we need to sleep to get it + * @page: the page to lock * - * Ugly: running sync_page() in state TASK_UNINTERRUPTIBLE is scary. If some + * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary. If some * random driver's requestfn sets TASK_RUNNING, we could busywait. However * chances are that on the second loop, the block layer's plug list is empty, * so sync_page() will then return in state TASK_UNINTERRUPTIBLE. @@ -514,8 +586,23 @@ void fastcall __lock_page(struct page *page) EXPORT_SYMBOL(__lock_page); /* - * a rather lightweight function, finding and getting a reference to a - * hashed page atomically. + * Variant of lock_page that does not require the caller to hold a reference + * on the page's mapping. + */ +void fastcall __lock_page_nosync(struct page *page) +{ + DEFINE_WAIT_BIT(wait, &page->flags, PG_locked); + __wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock, + TASK_UNINTERRUPTIBLE); +} + +/** + * find_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * Is there a pagecache struct page at the given (mapping, offset) tuple? + * If yes, increment its refcount and return it; if no, return NULL. */ struct page * find_get_page(struct address_space *mapping, unsigned long offset) { @@ -528,11 +615,14 @@ struct page * find_get_page(struct address_space *mapping, unsigned long offset) read_unlock_irq(&mapping->tree_lock); return page; } - EXPORT_SYMBOL(find_get_page); -/* - * Same as above, but trylock it instead of incrementing the count. +/** + * find_trylock_page - find and lock a page + * @mapping: the address_space to search + * @offset: the page index + * + * Same as find_get_page(), but trylock it instead of incrementing the count. */ struct page *find_trylock_page(struct address_space *mapping, unsigned long offset) { @@ -545,12 +635,10 @@ struct page *find_trylock_page(struct address_space *mapping, unsigned long offs read_unlock_irq(&mapping->tree_lock); return page; } - EXPORT_SYMBOL(find_trylock_page); /** * find_lock_page - locate, pin and lock a pagecache page - * * @mapping: the address_space to search * @offset: the page index * @@ -586,12 +674,10 @@ repeat: read_unlock_irq(&mapping->tree_lock); return page; } - EXPORT_SYMBOL(find_lock_page); /** * find_or_create_page - locate or add a pagecache page - * * @mapping: the page's address_space * @index: the page's index into the mapping * @gfp_mask: page allocation mode @@ -632,7 +718,6 @@ repeat: page_cache_release(cached_page); return page; } - EXPORT_SYMBOL(find_or_create_page); /** @@ -666,9 +751,48 @@ 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; +} + +/** + * find_get_pages_tag - find and return pages that match @tag + * @mapping: the address_space to search + * @index: the starting page index + * @tag: the tag index + * @nr_pages: the maximum number of pages + * @pages: where the resulting pages are placed + * * 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. + * @tag. We update @index to index the next page for the traversal. */ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, int tag, unsigned int nr_pages, struct page **pages) @@ -687,7 +811,11 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, return ret; } -/* +/** + * grab_cache_page_nowait - returns locked page at given index in given cache + * @mapping: target address_space + * @index: the page index + * * Same as grab_cache_page, but do not wait if the page is unavailable. * This is intended for speculative data generators, where the data can * be regenerated if the page couldn't be grabbed. This routine should @@ -700,7 +828,6 @@ 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)) @@ -708,27 +835,56 @@ 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; } return page; } - EXPORT_SYMBOL(grab_cache_page_nowait); /* + * CD/DVDs are error prone. When a medium error occurs, the driver may fail + * a _large_ part of the i/o request. Imagine the worst scenario: + * + * ---R__________________________________________B__________ + * ^ reading here ^ bad block(assume 4k) + * + * read(R) => miss => readahead(R...B) => media error => frustrating retries + * => failing the whole request => read(R) => read(R+1) => + * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => + * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => + * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... + * + * It is going insane. Fix it by quickly scaling down the readahead size. + */ +static void shrink_readahead_size_eio(struct file *filp, + struct file_ra_state *ra) +{ + if (!ra->ra_pages) + return; + + ra->ra_pages /= 4; +} + +/** + * do_generic_mapping_read - generic file read routine + * @mapping: address_space to be read + * @_ra: file's readahead state + * @filp: the file to read + * @ppos: current file position + * @desc: read_descriptor + * @actor: read method + * * This is a generic file read routine, and uses the - * mapping->a_ops->readpage() function for the actual low-level - * stuff. + * mapping->a_ops->readpage() function for the actual low-level stuff. * * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. * - * Note the struct file* is only passed for the use of readpage. It may be - * NULL. + * Note the struct file* is only passed for the use of readpage. + * It may be NULL. */ void do_generic_mapping_read(struct address_space *mapping, struct file_ra_state *_ra, @@ -744,6 +900,7 @@ void do_generic_mapping_read(struct address_space *mapping, unsigned long last_index; unsigned long next_index; unsigned long prev_index; + unsigned int prev_offset; loff_t isize; struct page *cached_page; int error; @@ -753,6 +910,7 @@ void do_generic_mapping_read(struct address_space *mapping, index = *ppos >> PAGE_CACHE_SHIFT; next_index = index; prev_index = ra.prev_page; + prev_offset = ra.offset; last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; offset = *ppos & ~PAGE_CACHE_MASK; @@ -800,10 +958,10 @@ page_ok: flush_dcache_page(page); /* - * When (part of) the same page is read multiple times - * in succession, only mark it as accessed the first time. + * When a sequential read accesses a page several times, + * only mark it as accessed the first time. */ - if (prev_index != index) + if (prev_index != index || offset != prev_offset) mark_page_accessed(page); prev_index = index; @@ -821,6 +979,7 @@ page_ok: offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; + prev_offset = ra.offset = offset; page_cache_release(page); if (ret == nr && desc->count) @@ -831,7 +990,7 @@ page_not_up_to_date: /* Get exclusive access to the page ... */ lock_page(page); - /* Did it get unhashed before we got the lock? */ + /* Did it get truncated before we got the lock? */ if (!page->mapping) { unlock_page(page); page_cache_release(page); @@ -869,6 +1028,7 @@ readpage: } unlock_page(page); error = -EIO; + shrink_readahead_size_eio(filp, &ra); goto readpage_error; } unlock_page(page); @@ -941,7 +1101,6 @@ out: if (filp) file_accessed(filp); } - EXPORT_SYMBOL(do_generic_mapping_read); int file_read_actor(read_descriptor_t *desc, struct page *page, @@ -982,18 +1141,25 @@ success: return size; } -/* +/** + * generic_file_aio_read - generic filesystem read routine + * @iocb: kernel I/O control block + * @iov: io vector request + * @nr_segs: number of segments in the iovec + * @pos: current file position + * * This is the "read()" routine for all filesystems * that can use the page cache directly. */ ssize_t -__generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *filp = iocb->ki_filp; ssize_t retval; unsigned long seg; size_t count; + loff_t *ppos = &iocb->ki_pos; count = 0; for (seg = 0; seg < nr_segs; seg++) { @@ -1017,7 +1183,7 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (filp->f_flags & O_DIRECT) { - loff_t pos = *ppos, size; + loff_t size; struct address_space *mapping; struct inode *inode; @@ -1030,13 +1196,13 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, if (pos < size) { retval = generic_file_direct_IO(READ, iocb, iov, pos, nr_segs); - if (retval > 0 && !is_sync_kiocb(iocb)) - retval = -EIOCBQUEUED; if (retval > 0) *ppos = pos + retval; } - file_accessed(filp); - goto out; + if (likely(retval != 0)) { + file_accessed(filp); + goto out; + } } retval = 0; @@ -1061,36 +1227,8 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, out: return retval; } - -EXPORT_SYMBOL(__generic_file_aio_read); - -ssize_t -generic_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos) -{ - struct iovec local_iov = { .iov_base = buf, .iov_len = count }; - - BUG_ON(iocb->ki_pos != pos); - return __generic_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos); -} - EXPORT_SYMBOL(generic_file_aio_read); -ssize_t -generic_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) -{ - struct iovec local_iov = { .iov_base = buf, .iov_len = count }; - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - ret = __generic_file_aio_read(&kiocb, &local_iov, 1, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} - -EXPORT_SYMBOL(generic_file_read); - int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size) { ssize_t written; @@ -1111,6 +1249,31 @@ int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long o return written; } +/* FIXME: It would be as simple as this, if we had a (void __user*) to write. + * We already have a kernel buffer, so it should be even simpler, right? ;) + * + * Yes, sorta. After duplicating the complete path of generic_file_write(), + * at least some special cases could be removed, so the copy is simpler than + * the original. But it remains a copy, so overall complexity increases. + */ +static ssize_t +generic_kernel_file_write(struct file *, const char *, size_t, loff_t *); + +ssize_t generic_file_sendpage(struct file *file, struct page *page, + int offset, size_t size, loff_t *ppos, int more) +{ + ssize_t ret; + char *kaddr; + + kaddr = kmap(page); + ret = generic_kernel_file_write(file, kaddr + offset, size, ppos); + kunmap(page); + + return ret; +} + +EXPORT_SYMBOL(generic_file_sendpage); + ssize_t generic_file_sendfile(struct file *in_file, loff_t *ppos, size_t count, read_actor_t actor, void *target) { @@ -1129,7 +1292,6 @@ ssize_t generic_file_sendfile(struct file *in_file, loff_t *ppos, return desc.written; return desc.error; } - EXPORT_SYMBOL(generic_file_sendfile); static ssize_t @@ -1165,11 +1327,15 @@ asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count) } #ifdef CONFIG_MMU -/* +static int FASTCALL(page_cache_read(struct file * file, unsigned long offset)); +/** + * page_cache_read - adds requested page to the page cache if not already there + * @file: file to read + * @offset: page index + * * This adds the requested page to the page cache if it isn't already there, * and schedules an I/O to read in its contents from disk. */ -static int FASTCALL(page_cache_read(struct file * file, unsigned long offset)); static int fastcall page_cache_read(struct file * file, unsigned long offset) { struct address_space *mapping = file->f_mapping; @@ -1196,7 +1362,12 @@ static int fastcall page_cache_read(struct file * file, unsigned long offset) #define MMAP_LOTSAMISS (100) -/* +/** + * filemap_nopage - read in file data for page fault handling + * @area: the applicable vm_area + * @address: target address to read in + * @type: returned with VM_FAULT_{MINOR,MAJOR} if not %NULL + * * filemap_nopage() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * @@ -1263,7 +1434,7 @@ retry_find: */ if (!did_readaround) { majmin = VM_FAULT_MAJOR; - inc_page_state(pgmajfault); + count_vm_event(PGMAJFAULT); } did_readaround = 1; ra_pages = max_sane_readahead(file->f_ra.ra_pages); @@ -1304,7 +1475,7 @@ outside_data_content: * accessible.. */ if (area->vm_mm == current->mm) - return NULL; + return NOPAGE_SIGBUS; /* Fall through to the non-read-ahead case */ no_cached_page: /* @@ -1312,7 +1483,6 @@ no_cached_page: * effect. */ error = page_cache_read(file, pgoff); - grab_swap_token(); /* * The page we want has now been added to the page cache. @@ -1329,12 +1499,12 @@ no_cached_page: */ if (error == -ENOMEM) return NOPAGE_OOM; - return NULL; + return NOPAGE_SIGBUS; page_not_uptodate: if (!did_readaround) { majmin = VM_FAULT_MAJOR; - inc_page_state(pgmajfault); + count_vm_event(PGMAJFAULT); } lock_page(page); @@ -1396,10 +1566,10 @@ page_not_uptodate: * Things didn't work out. Return zero to tell the * mm layer so, possibly freeing the page cache page first. */ + shrink_readahead_size_eio(file, ra); page_cache_release(page); - return NULL; + return NOPAGE_SIGBUS; } - EXPORT_SYMBOL(filemap_nopage); static struct page * filemap_getpage(struct file *file, unsigned long pgoff, @@ -1460,7 +1630,7 @@ no_cached_page: page_not_uptodate: lock_page(page); - /* Did it get unhashed while we waited for it? */ + /* Did it get truncated while we waited for it? */ if (!page->mapping) { unlock_page(page); goto err; @@ -1653,7 +1823,13 @@ repeat: return page; } -/* +/** + * read_cache_page - read into page cache, fill it if needed + * @mapping: the page's address_space + * @index: the page index + * @filler: function to perform the read + * @data: destination for read data + * * Read into the page cache. If a page already exists, * and PageUptodate() is not set, try to fill the page. */ @@ -1691,7 +1867,6 @@ retry: out: return page; } - EXPORT_SYMBOL(read_cache_page); /* @@ -1734,11 +1909,10 @@ 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)) @@ -1751,18 +1925,47 @@ 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; +} +EXPORT_SYMBOL(should_remove_suid); + +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); +static inline size_t +filemap_copy_from_kernel(struct page *page, unsigned long offset, + const char *buf, unsigned bytes) +{ + char *kaddr; + + kaddr = kmap(page); + memcpy(kaddr + offset, buf, bytes); + kunmap(page); + + return bytes; +} + size_t -__filemap_copy_from_user_iovec(char *vaddr, +__filemap_copy_from_user_iovec_inatomic(char *vaddr, const struct iovec *iov, size_t base, size_t bytes) { size_t copied = 0, left = 0; @@ -1772,18 +1975,14 @@ __filemap_copy_from_user_iovec(char *vaddr, int copy = min(bytes, iov->iov_len - base); base = 0; - left = __copy_from_user_inatomic(vaddr, buf, copy); + left = __copy_from_user_inatomic_nocache(vaddr, buf, copy); copied += copy; bytes -= copy; vaddr += copy; iov++; - if (unlikely(left)) { - /* zero the rest of the target like __copy_from_user */ - if (bytes) - memset(vaddr, 0, bytes); + if (unlikely(left)) break; - } } return copied - left; } @@ -1791,7 +1990,7 @@ __filemap_copy_from_user_iovec(char *vaddr, /* * Performs necessary checks before doing a write * - * Can adjust writing position aor amount of bytes to write. + * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ @@ -1852,6 +2051,7 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i if (unlikely(*pos + *count > inode->i_sb->s_maxbytes)) *count = inode->i_sb->s_maxbytes - *pos; } else { +#ifdef CONFIG_BLOCK loff_t isize; if (bdev_read_only(I_BDEV(inode))) return -EPERM; @@ -1863,6 +2063,9 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i if (*pos + *count > isize) *count = isize - *pos; +#else + return -EPERM; +#endif } return 0; } @@ -1895,15 +2098,14 @@ 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_mutex is held, which protects generic_osync_inode() from - * livelocking. + * livelocking. AIO O_DIRECT ops attempt to sync metadata here. */ - if (written >= 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { + if ((written >= 0 || written == -EIOCBQUEUED) && + ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { int err = generic_osync_inode(inode, mapping, OSYNC_METADATA); if (err < 0) written = err; } - if (written == count && !is_sync_kiocb(iocb)) - written = -EIOCBQUEUED; return written; } EXPORT_SYMBOL(generic_file_direct_write); @@ -1915,7 +2117,7 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; - struct address_space_operations *a_ops = mapping->a_ops; + const struct address_space_operations *a_ops = mapping->a_ops; struct inode *inode = mapping->host; long status = 0; struct page *page; @@ -1941,14 +2143,21 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, do { unsigned long index; unsigned long offset; - unsigned long maxlen; size_t copied; offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */ index = pos >> PAGE_CACHE_SHIFT; bytes = PAGE_CACHE_SIZE - offset; - if (bytes > count) - bytes = count; + + /* Limit the size of the copy to the caller's write size */ + bytes = min(bytes, count); + + /* + * Limit the size of the copy to that of the current segment, + * because fault_in_pages_readable() doesn't know how to walk + * segments. + */ + bytes = min(bytes, cur_iov->iov_len - iov_base); /* * Bring in the user page that we will copy from _first_. @@ -1956,10 +2165,7 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, * same page as we're writing to, without it being marked * up-to-date. */ - maxlen = cur_iov->iov_len - iov_base; - if (maxlen > bytes) - maxlen = bytes; - fault_in_pages_readable(buf, maxlen); + fault_in_pages_readable(buf, bytes); page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec); if (!page) { @@ -1967,6 +2173,12 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, break; } + if (unlikely(bytes == 0)) { + status = 0; + copied = 0; + goto zero_length_segment; + } + status = a_ops->prepare_write(file, page, offset, offset+bytes); if (unlikely(status)) { loff_t isize = i_size_read(inode); @@ -1996,7 +2208,8 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, page_cache_release(page); continue; } - if (likely(copied > 0)) { +zero_length_segment: + if (likely(copied >= 0)) { if (!status) status = copied; @@ -2056,6 +2269,261 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, } EXPORT_SYMBOL(generic_file_buffered_write); +/* + * This writes the data from the source page to the specified page offset in + * the nominated file + * - the source page does not need to have any association with the file or the + * page offset + */ +int +generic_file_buffered_write_one_kernel_page(struct address_space *mapping, + pgoff_t index, + struct page *src) +{ + const struct address_space_operations *a_ops = mapping->a_ops; + struct pagevec lru_pvec; + struct page *page, *cached_page = NULL; + long status = 0; + + pagevec_init(&lru_pvec, 0); + +#if 0 + if (mapping->tree_lock.magic != RWLOCK_MAGIC) + printk("RWLOCK magic incorrect: %x != %x\n", + mapping->tree_lock.magic, RWLOCK_MAGIC); +#endif + + page = __grab_cache_page(mapping, index, &cached_page, &lru_pvec); + if (!page) { + BUG_ON(cached_page); + return -ENOMEM; + } + + status = a_ops->prepare_write(NULL, page, 0, PAGE_CACHE_SIZE); + if (unlikely(status)) { + loff_t isize = i_size_read(mapping->host); + + if (status != AOP_TRUNCATED_PAGE) + unlock_page(page); + page_cache_release(page); + if (status == AOP_TRUNCATED_PAGE) + goto sync; + + /* prepare_write() may have instantiated a few blocks outside + * i_size. Trim these off again. + */ + if ((1ULL << (index + 1)) > isize) + vmtruncate(mapping->host, isize); + goto sync; + } + + copy_highpage(page, src); + flush_dcache_page(page); + + status = a_ops->commit_write(NULL, page, 0, PAGE_CACHE_SIZE); + if (status == AOP_TRUNCATED_PAGE) { + page_cache_release(page); + goto sync; + } + + if (status > 0) + status = 0; + + unlock_page(page); + mark_page_accessed(page); + page_cache_release(page); + if (status < 0) + return status; + + balance_dirty_pages_ratelimited(mapping); + cond_resched(); + +sync: + if (cached_page) + page_cache_release(cached_page); + + /* the caller must handle O_SYNC themselves, but we handle S_SYNC and + * MS_SYNCHRONOUS here */ + if (unlikely(IS_SYNC(mapping->host)) && !a_ops->writepage) + status = generic_osync_inode(mapping->host, mapping, + OSYNC_METADATA | OSYNC_DATA); + + /* the caller must handle O_DIRECT for themselves */ + + pagevec_lru_add(&lru_pvec); + return status; +} +EXPORT_SYMBOL(generic_file_buffered_write_one_kernel_page); + +static inline void +filemap_set_next_kvec(const struct kvec **iovp, size_t *basep, size_t bytes) +{ + const struct kvec *iov = *iovp; + size_t base = *basep; + + while (bytes) { + int copy = min(bytes, iov->iov_len - base); + + bytes -= copy; + base += copy; + if (iov->iov_len == base) { + iov++; + base = 0; + } + } + *iovp = iov; + *basep = base; +} + +/* + * TODO: + * This largely tries to copy generic_file_aio_write_nolock(), although it + * doesn't have to be nearly as generic. A real cleanup should either + * merge this into generic_file_aio_write_nolock() as well or keep it special + * and remove as much code as possible. + */ +static ssize_t +generic_kernel_file_aio_write_nolock(struct kiocb *iocb, const struct kvec*iov, + unsigned long nr_segs, loff_t *ppos) +{ + struct file *file = iocb->ki_filp; + struct address_space * mapping = file->f_mapping; + const struct address_space_operations *a_ops = mapping->a_ops; + size_t ocount; /* original count */ + size_t count; /* after file limit checks */ + struct inode *inode = mapping->host; + long status = 0; + loff_t pos; + struct page *page; + struct page *cached_page = NULL; + const int isblk = S_ISBLK(inode->i_mode); + ssize_t written; + ssize_t err; + size_t bytes; + struct pagevec lru_pvec; + const struct kvec *cur_iov = iov; /* current kvec */ + size_t iov_base = 0; /* offset in the current kvec */ + unsigned long seg; + char *buf; + + ocount = 0; + for (seg = 0; seg < nr_segs; seg++) { + const struct kvec *iv = &iov[seg]; + + /* + * If any segment has a negative length, or the cumulative + * length ever wraps negative then return -EINVAL. + */ + ocount += iv->iov_len; + if (unlikely((ssize_t)(ocount|iv->iov_len) < 0)) + return -EINVAL; + } + + count = ocount; + pos = *ppos; + pagevec_init(&lru_pvec, 0); + + /* We can write back this queue in page reclaim */ + current->backing_dev_info = mapping->backing_dev_info; + written = 0; + + err = generic_write_checks(file, &pos, &count, isblk); + if (err) + goto out; + + + if (count == 0) + goto out; + + remove_suid(file->f_dentry); + file_update_time(file); + + /* There is no sane reason to use O_DIRECT */ + BUG_ON(file->f_flags & O_DIRECT); + + buf = iov->iov_base; + do { + unsigned long index; + unsigned long offset; + size_t copied; + + offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */ + index = pos >> PAGE_CACHE_SHIFT; + bytes = PAGE_CACHE_SIZE - offset; + if (bytes > count) + bytes = count; + + page = __grab_cache_page(mapping,index,&cached_page,&lru_pvec); + if (!page) { + status = -ENOMEM; + break; + } + + status = a_ops->prepare_write(file, page, offset, offset+bytes); + if (unlikely(status)) { + loff_t isize = i_size_read(inode); + /* + * prepare_write() may have instantiated a few blocks + * outside i_size. Trim these off again. + */ + unlock_page(page); + page_cache_release(page); + if (pos + bytes > isize) + vmtruncate(inode, isize); + break; + } + + BUG_ON(nr_segs != 1); + copied = filemap_copy_from_kernel(page, offset, buf, bytes); + + flush_dcache_page(page); + status = a_ops->commit_write(file, page, offset, offset+bytes); + if (likely(copied > 0)) { + if (!status) + status = copied; + + if (status >= 0) { + written += status; + count -= status; + pos += status; + buf += status; + if (unlikely(nr_segs > 1)) + filemap_set_next_kvec(&cur_iov, + &iov_base, status); + } + } + if (unlikely(copied != bytes)) + if (status >= 0) + status = -EFAULT; + unlock_page(page); + mark_page_accessed(page); + page_cache_release(page); + if (status < 0) + break; + balance_dirty_pages_ratelimited(mapping); + cond_resched(); + } while (count); + *ppos = pos; + + if (cached_page) + page_cache_release(cached_page); + + /* + * For now, when the user asks for O_SYNC, we'll actually give O_DSYNC + */ + if (status >= 0) { + if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) + status = generic_osync_inode(inode, mapping, + OSYNC_METADATA|OSYNC_DATA); + } + + err = written ? written : status; +out: + pagevec_lru_add(&lru_pvec); + current->backing_dev_info = 0; + return err; +} + static ssize_t __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t *ppos) @@ -2106,7 +2574,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; - err = remove_suid(file->f_dentry); + err = remove_suid(file->f_path.dentry); if (err) goto out; @@ -2114,8 +2582,11 @@ __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; /* @@ -2124,154 +2595,130 @@ __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; } -EXPORT_SYMBOL(generic_file_aio_write_nolock); - -ssize_t -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; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - loff_t pos = *ppos; - - ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, ppos); - - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; - - err = sync_page_range_nolock(inode, mapping, pos, ret); - if (err < 0) - ret = err; - } - return ret; -} static ssize_t -__generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +generic_kernel_file_write_nolock(struct file *file, const struct kvec *iov, + unsigned long nr_segs, loff_t *ppos) { struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, file); - ret = __generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); + ret = generic_kernel_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); if (ret == -EIOCBQUEUED) ret = wait_on_sync_kiocb(&kiocb); return ret; } -ssize_t -generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +static ssize_t generic_kernel_file_write(struct file *file, const char *buf, + size_t count, loff_t *ppos) { - struct kiocb kiocb; - ssize_t ret; + struct inode *inode = file->f_mapping->host; + ssize_t err; + struct kvec local_iov = { .iov_base = (char *) buf, + .iov_len = count }; - init_sync_kiocb(&kiocb, file); - ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; + mutex_lock(&inode->i_mutex); + err = generic_kernel_file_write_nolock(file, &local_iov, 1, ppos); + mutex_unlock(&inode->i_mutex); + + return err; } -EXPORT_SYMBOL(generic_file_write_nolock); -ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) + +ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; BUG_ON(iocb->ki_pos != pos); - mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write_nolock(iocb, &local_iov, 1, - &iocb->ki_pos); - mutex_unlock(&inode->i_mutex); + ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, + &iocb->ki_pos); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { ssize_t err; - err = sync_page_range(inode, mapping, pos, ret); + err = sync_page_range_nolock(inode, mapping, pos, ret); if (err < 0) ret = err; } return ret; } -EXPORT_SYMBOL(generic_file_aio_write); +EXPORT_SYMBOL(generic_file_aio_write_nolock); -ssize_t generic_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { + struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; - ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; - - mutex_lock(&inode->i_mutex); - ret = __generic_file_write_nolock(file, &local_iov, 1, ppos); - mutex_unlock(&inode->i_mutex); - - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - ssize_t err; - - err = sync_page_range(inode, mapping, *ppos - ret, ret); - if (err < 0) - ret = err; - } - return ret; -} -EXPORT_SYMBOL(generic_file_write); - -ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; ssize_t ret; - init_sync_kiocb(&kiocb, filp); - ret = __generic_file_aio_read(&kiocb, iov, nr_segs, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} -EXPORT_SYMBOL(generic_file_readv); - -ssize_t generic_file_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; + BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = __generic_file_write_nolock(file, iov, nr_segs, ppos); + ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, + &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; + ssize_t err; - err = sync_page_range(inode, mapping, *ppos - ret, ret); + err = sync_page_range(inode, mapping, pos, ret); if (err < 0) ret = err; } return ret; } -EXPORT_SYMBOL(generic_file_writev); +EXPORT_SYMBOL(generic_file_aio_write); /* * Called under i_mutex for writes to S_ISREG files. Returns -EIO if something @@ -2284,7 +2731,8 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; ssize_t retval; - size_t write_len = 0; + size_t write_len; + pgoff_t end = 0; /* silence gcc */ /* * If it's a write, unmap all mmappings of the file up-front. This @@ -2293,22 +2741,75 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, */ if (rw == WRITE) { write_len = iov_length(iov, nr_segs); + end = (offset + write_len - 1) >> PAGE_CACHE_SHIFT; if (mapping_mapped(mapping)) unmap_mapping_range(mapping, offset, write_len, 0); } retval = filemap_write_and_wait(mapping); - if (retval == 0) { - retval = mapping->a_ops->direct_IO(rw, iocb, iov, - offset, nr_segs); - if (rw == WRITE && mapping->nrpages) { - pgoff_t end = (offset + write_len - 1) - >> PAGE_CACHE_SHIFT; - int err = invalidate_inode_pages2_range(mapping, + if (retval) + goto out; + + /* + * After a write we want buffered reads to be sure to go to disk to get + * the new data. We invalidate clean cached page from the region we're + * about to write. We do this *before* the write so that we can return + * -EIO without clobbering -EIOCBQUEUED from ->direct_IO(). + */ + if (rw == WRITE && mapping->nrpages) { + retval = invalidate_inode_pages2_range(mapping, offset >> PAGE_CACHE_SHIFT, end); - if (err) - retval = err; - } + if (retval) + goto out; } + + retval = mapping->a_ops->direct_IO(rw, iocb, iov, offset, nr_segs); + if (retval) + goto out; + + /* + * Finally, try again to invalidate clean pages which might have been + * faulted in by get_user_pages() if the source of the write was an + * mmap()ed region of the file we're writing. That's a pretty crazy + * thing to do, so we don't support it 100%. If this invalidation + * fails and we have -EIOCBQUEUED we ignore the failure. + */ + if (rw == WRITE && mapping->nrpages) { + int err = invalidate_inode_pages2_range(mapping, + offset >> PAGE_CACHE_SHIFT, end); + if (err && retval >= 0) + retval = err; + } +out: return retval; } + +/** + * try_to_release_page() - release old fs-specific metadata on a page + * + * @page: the page which the kernel is trying to free + * @gfp_mask: memory allocation flags (and I/O mode) + * + * The address_space is to try to release any data against the page + * (presumably at page->private). If the release was successful, return `1'. + * Otherwise return zero. + * + * The @gfp_mask argument specifies whether I/O may be performed to release + * this page (__GFP_IO), and whether the call may block (__GFP_WAIT). + * + * NOTE: @gfp_mask may go away, and this function may become non-blocking. + */ +int try_to_release_page(struct page *page, gfp_t gfp_mask) +{ + struct address_space * const mapping = page->mapping; + + BUG_ON(!PageLocked(page)); + if (PageWriteback(page)) + return 0; + + if (mapping && mapping->a_ops->releasepage) + return mapping->a_ops->releasepage(page, gfp_mask); + return try_to_free_buffers(page); +} + +EXPORT_SYMBOL(try_to_release_page);