From c186afb4dbd0050a537b96c7fbee2dba3b57fc38 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 2 Feb 2014 21:16:54 -0500 Subject: switch ->is_partially_uptodate() to saner arguments Signed-off-by: Al Viro --- mm/filemap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 7a13f6ac5421..46e98019af6c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1148,7 +1148,7 @@ find_page: if (!page->mapping) goto page_not_up_to_date_locked; if (!mapping->a_ops->is_partially_uptodate(page, - desc, offset)) + offset, desc->count)) goto page_not_up_to_date_locked; unlock_page(page); } -- cgit From 9e8c2af96e0d2d5fe298dd796fb6bc16e888a48d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 2 Feb 2014 22:10:25 -0500 Subject: callers of iov_copy_from_user_atomic() don't need pagecache_disable() ... it does that itself (via kmap_atomic()) Signed-off-by: Al Viro --- fs/btrfs/file.c | 5 ----- fs/fuse/file.c | 2 -- mm/filemap.c | 3 --- 3 files changed, 10 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0165b8672f09..34e096201da1 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -425,13 +425,8 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages, struct page *page = prepared_pages[pg]; /* * Copy data from userspace to the current page - * - * Disable pagefault to avoid recursive lock since - * the pages are already locked */ - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, count); - pagefault_enable(); /* Flush processor's dcache for this page */ flush_dcache_page(page); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 77bcc303c3ae..a91d3b4d32f3 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1003,9 +1003,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req, if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); tmp = iov_iter_copy_from_user_atomic(page, ii, offset, bytes); - pagefault_enable(); flush_dcache_page(page); mark_page_accessed(page); diff --git a/mm/filemap.c b/mm/filemap.c index 46e98019af6c..bfb7a97d6d0f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1974,7 +1974,6 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, char *kaddr; size_t copied; - BUG_ON(!in_atomic()); kaddr = kmap_atomic(page); if (likely(i->nr_segs == 1)) { int left; @@ -2348,9 +2347,7 @@ again: if (mapping_writably_mapped(mapping)) flush_dcache_page(page); - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); - pagefault_enable(); flush_dcache_page(page); mark_page_accessed(page); -- cgit From 6e58e79db8a16222b31fc8da1ca2ac2dccfc4237 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 3 Feb 2014 17:07:03 -0500 Subject: introduce copy_page_to_iter, kill loop over iovec in generic_file_aio_read() generic_file_aio_read() was looping over the target iovec, with loop over (source) pages nested inside that. Just set an iov_iter up and pass *that* to do_generic_file_aio_read(). With copy_page_to_iter() doing all work of mapping and copying a page to iovec and advancing iov_iter. Switch shmem_file_aio_read() to the same and kill file_read_actor(), while we are at it. Signed-off-by: Al Viro --- include/linux/fs.h | 1 - include/linux/uio.h | 2 + mm/filemap.c | 202 ++++++++++++++++++++++++++++------------------------ mm/shmem.c | 77 +++++++------------- 4 files changed, 138 insertions(+), 144 deletions(-) (limited to 'mm/filemap.c') diff --git a/include/linux/fs.h b/include/linux/fs.h index 2261ac8f0534..2a5b1744f80a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2390,7 +2390,6 @@ extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr, unsigned long size, pgoff_t pgoff); -extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, diff --git a/include/linux/uio.h b/include/linux/uio.h index 347d70ce098e..199bcc34241b 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -67,6 +67,8 @@ size_t iov_iter_copy_from_user(struct page *page, void iov_iter_advance(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); +size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i); static inline void iov_iter_init(struct iov_iter *i, const struct iovec *iov, unsigned long nr_segs, diff --git a/mm/filemap.c b/mm/filemap.c index bfb7a97d6d0f..a16eb2c4f316 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1085,11 +1085,90 @@ static void shrink_readahead_size_eio(struct file *filp, ra->ra_pages /= 4; } +size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + size_t skip, copy, left, wanted; + const struct iovec *iov; + char __user *buf; + void *kaddr, *from; + + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + wanted = bytes; + iov = i->iov; + skip = i->iov_offset; + buf = iov->iov_base + skip; + copy = min(bytes, iov->iov_len - skip); + + if (!fault_in_pages_writeable(buf, copy)) { + kaddr = kmap_atomic(page); + from = kaddr + offset; + + /* first chunk, usually the only one */ + left = __copy_to_user_inatomic(buf, from, copy); + copy -= left; + skip += copy; + from += copy; + bytes -= copy; + + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_to_user_inatomic(buf, from, copy); + copy -= left; + skip = copy; + from += copy; + bytes -= copy; + } + if (likely(!bytes)) { + kunmap_atomic(kaddr); + goto done; + } + offset = from - kaddr; + buf += copy; + kunmap_atomic(kaddr); + copy = min(bytes, iov->iov_len - skip); + } + /* Too bad - revert to non-atomic kmap */ + kaddr = kmap(page); + from = kaddr + offset; + left = __copy_to_user(buf, from, copy); + copy -= left; + skip += copy; + from += copy; + bytes -= copy; + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_to_user(buf, from, copy); + copy -= left; + skip = copy; + from += copy; + bytes -= copy; + } + kunmap(page); +done: + i->count -= wanted - bytes; + i->nr_segs -= iov - i->iov; + i->iov = iov; + i->iov_offset = skip; + return wanted - bytes; +} +EXPORT_SYMBOL(copy_page_to_iter); + /** * do_generic_file_read - generic file read routine * @filp: the file to read * @ppos: current file position - * @desc: read_descriptor + * @iter: data destination + * @written: already copied * * This is a generic file read routine, and uses the * mapping->a_ops->readpage() function for the actual low-level stuff. @@ -1097,8 +1176,8 @@ static void shrink_readahead_size_eio(struct file *filp, * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. */ -static void do_generic_file_read(struct file *filp, loff_t *ppos, - read_descriptor_t *desc) +static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos, + struct iov_iter *iter, ssize_t written) { struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; @@ -1108,12 +1187,12 @@ static void do_generic_file_read(struct file *filp, loff_t *ppos, pgoff_t prev_index; unsigned long offset; /* offset into pagecache page */ unsigned int prev_offset; - int error; + int error = 0; index = *ppos >> PAGE_CACHE_SHIFT; prev_index = ra->prev_pos >> PAGE_CACHE_SHIFT; prev_offset = ra->prev_pos & (PAGE_CACHE_SIZE-1); - last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; + last_index = (*ppos + iter->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; offset = *ppos & ~PAGE_CACHE_MASK; for (;;) { @@ -1148,7 +1227,7 @@ find_page: if (!page->mapping) goto page_not_up_to_date_locked; if (!mapping->a_ops->is_partially_uptodate(page, - offset, desc->count)) + offset, iter->count)) goto page_not_up_to_date_locked; unlock_page(page); } @@ -1198,24 +1277,23 @@ page_ok: /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... - * - * The file_read_actor routine returns how many bytes were - * actually used.. - * NOTE! This may not be the same as how much of a user buffer - * we filled up (we may be padding etc), so we can only update - * "pos" here (the actor routine has to update the user buffer - * pointers and the remaining count). */ - ret = file_read_actor(desc, page, offset, nr); + + ret = copy_page_to_iter(page, offset, nr, iter); offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; prev_offset = offset; page_cache_release(page); - if (ret == nr && desc->count) - continue; - goto out; + written += ret; + if (!iov_iter_count(iter)) + goto out; + if (ret < nr) { + error = -EFAULT; + goto out; + } + continue; page_not_up_to_date: /* Get exclusive access to the page ... */ @@ -1250,6 +1328,7 @@ readpage: if (unlikely(error)) { if (error == AOP_TRUNCATED_PAGE) { page_cache_release(page); + error = 0; goto find_page; } goto readpage_error; @@ -1280,7 +1359,6 @@ readpage: readpage_error: /* UHHUH! A synchronous read error occurred. Report it */ - desc->error = error; page_cache_release(page); goto out; @@ -1291,16 +1369,17 @@ no_cached_page: */ page = page_cache_alloc_cold(mapping); if (!page) { - desc->error = -ENOMEM; + error = -ENOMEM; goto out; } error = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); if (error) { page_cache_release(page); - if (error == -EEXIST) + if (error == -EEXIST) { + error = 0; goto find_page; - desc->error = error; + } goto out; } goto readpage; @@ -1313,44 +1392,7 @@ out: *ppos = ((loff_t)index << PAGE_CACHE_SHIFT) + offset; file_accessed(filp); -} - -int file_read_actor(read_descriptor_t *desc, struct page *page, - unsigned long offset, unsigned long size) -{ - char *kaddr; - unsigned long left, count = desc->count; - - if (size > count) - size = count; - - /* - * Faults on the destination of a read are common, so do it before - * taking the kmap. - */ - if (!fault_in_pages_writeable(desc->arg.buf, size)) { - kaddr = kmap_atomic(page); - left = __copy_to_user_inatomic(desc->arg.buf, - kaddr + offset, size); - kunmap_atomic(kaddr); - if (left == 0) - goto success; - } - - /* Do it the slow way */ - kaddr = kmap(page); - left = __copy_to_user(desc->arg.buf, kaddr + offset, size); - kunmap(page); - - if (left) { - size -= left; - desc->error = -EFAULT; - } -success: - desc->count = count - size; - desc->written += size; - desc->arg.buf += size; - return size; + return written ? written : error; } /* @@ -1408,14 +1450,15 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, { struct file *filp = iocb->ki_filp; ssize_t retval; - unsigned long seg = 0; size_t count; loff_t *ppos = &iocb->ki_pos; + struct iov_iter i; count = 0; retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); if (retval) return retval; + iov_iter_init(&i, iov, nr_segs, count, 0); /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (filp->f_flags & O_DIRECT) { @@ -1437,6 +1480,11 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, if (retval > 0) { *ppos = pos + retval; count -= retval; + /* + * If we did a short DIO read we need to skip the + * section of the iov that we've already read data into. + */ + iov_iter_advance(&i, retval); } /* @@ -1453,39 +1501,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, } } - count = retval; - for (seg = 0; seg < nr_segs; seg++) { - read_descriptor_t desc; - loff_t offset = 0; - - /* - * If we did a short DIO read we need to skip the section of the - * iov that we've already read data into. - */ - if (count) { - if (count > iov[seg].iov_len) { - count -= iov[seg].iov_len; - continue; - } - offset = count; - count = 0; - } - - desc.written = 0; - desc.arg.buf = iov[seg].iov_base + offset; - desc.count = iov[seg].iov_len - offset; - if (desc.count == 0) - continue; - desc.error = 0; - do_generic_file_read(filp, ppos, &desc); - retval += desc.written; - if (desc.error) { - retval = retval ?: desc.error; - break; - } - if (desc.count > 0) - break; - } + retval = do_generic_file_read(filp, ppos, &i, retval); out: return retval; } diff --git a/mm/shmem.c b/mm/shmem.c index 9398e6cd48cb..17d3799d04bd 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1462,13 +1462,25 @@ shmem_write_end(struct file *file, struct address_space *mapping, return copied; } -static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc) +static ssize_t shmem_file_aio_read(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, loff_t pos) { - struct inode *inode = file_inode(filp); + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; pgoff_t index; unsigned long offset; enum sgp_type sgp = SGP_READ; + int error; + ssize_t retval; + size_t count; + loff_t *ppos = &iocb->ki_pos; + struct iov_iter iter; + + retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); + if (retval) + return retval; + iov_iter_init(&iter, iov, nr_segs, count, 0); /* * Might this read be for a stacking filesystem? Then when reading @@ -1496,10 +1508,10 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ break; } - desc->error = shmem_getpage(inode, index, &page, sgp, NULL); - if (desc->error) { - if (desc->error == -EINVAL) - desc->error = 0; + error = shmem_getpage(inode, index, &page, sgp, NULL); + if (error) { + if (error == -EINVAL) + error = 0; break; } if (page) @@ -1543,61 +1555,26 @@ static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_ /* * Ok, we have the page, and it's up-to-date, so * now we can copy it to user space... - * - * The actor routine returns how many bytes were actually used.. - * NOTE! This may not be the same as how much of a user buffer - * we filled up (we may be padding etc), so we can only update - * "pos" here (the actor routine has to update the user buffer - * pointers and the remaining count). */ - ret = file_read_actor(desc, page, offset, nr); + ret = copy_page_to_iter(page, offset, nr, &iter); + retval += ret; offset += ret; index += offset >> PAGE_CACHE_SHIFT; offset &= ~PAGE_CACHE_MASK; page_cache_release(page); - if (ret != nr || !desc->count) + if (!iov_iter_count(&iter)) break; - + if (ret < nr) { + error = -EFAULT; + break; + } cond_resched(); } *ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset; - file_accessed(filp); -} - -static ssize_t shmem_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; - - retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); - if (retval) - return retval; - - for (seg = 0; seg < nr_segs; seg++) { - read_descriptor_t desc; - - desc.written = 0; - desc.arg.buf = iov[seg].iov_base; - desc.count = iov[seg].iov_len; - if (desc.count == 0) - continue; - desc.error = 0; - do_shmem_file_read(filp, ppos, &desc); - retval += desc.written; - if (desc.error) { - retval = retval ?: desc.error; - break; - } - if (desc.count > 0) - break; - } - return retval; + file_accessed(file); + return retval ? retval : error; } static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, -- cgit From 4f18cd317a118c28482f97303600a2fe2ada6c79 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 5 Feb 2014 19:11:33 -0500 Subject: take iov_iter stuff to mm/iov_iter.c Signed-off-by: Al Viro --- mm/Makefile | 2 +- mm/filemap.c | 221 --------------------------------------------------------- mm/iov_iter.c | 224 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 225 insertions(+), 222 deletions(-) create mode 100644 mm/iov_iter.c (limited to 'mm/filemap.c') diff --git a/mm/Makefile b/mm/Makefile index 310c90a09264..178a43406b0c 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -17,7 +17,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o balloon_compaction.o \ - interval_tree.o list_lru.o $(mmu-y) + interval_tree.o list_lru.o iov_iter.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/filemap.c b/mm/filemap.c index a16eb2c4f316..c4730efa5d9e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1085,84 +1085,6 @@ static void shrink_readahead_size_eio(struct file *filp, ra->ra_pages /= 4; } -size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, - struct iov_iter *i) -{ - size_t skip, copy, left, wanted; - const struct iovec *iov; - char __user *buf; - void *kaddr, *from; - - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - wanted = bytes; - iov = i->iov; - skip = i->iov_offset; - buf = iov->iov_base + skip; - copy = min(bytes, iov->iov_len - skip); - - if (!fault_in_pages_writeable(buf, copy)) { - kaddr = kmap_atomic(page); - from = kaddr + offset; - - /* first chunk, usually the only one */ - left = __copy_to_user_inatomic(buf, from, copy); - copy -= left; - skip += copy; - from += copy; - bytes -= copy; - - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __copy_to_user_inatomic(buf, from, copy); - copy -= left; - skip = copy; - from += copy; - bytes -= copy; - } - if (likely(!bytes)) { - kunmap_atomic(kaddr); - goto done; - } - offset = from - kaddr; - buf += copy; - kunmap_atomic(kaddr); - copy = min(bytes, iov->iov_len - skip); - } - /* Too bad - revert to non-atomic kmap */ - kaddr = kmap(page); - from = kaddr + offset; - left = __copy_to_user(buf, from, copy); - copy -= left; - skip += copy; - from += copy; - bytes -= copy; - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __copy_to_user(buf, from, copy); - copy -= left; - skip = copy; - from += copy; - bytes -= copy; - } - kunmap(page); -done: - i->count -= wanted - bytes; - i->nr_segs -= iov - i->iov; - i->iov = iov; - i->iov_offset = skip; - return wanted - bytes; -} -EXPORT_SYMBOL(copy_page_to_iter); - /** * do_generic_file_read - generic file read routine * @filp: the file to read @@ -1957,149 +1879,6 @@ struct page *read_cache_page(struct address_space *mapping, } EXPORT_SYMBOL(read_cache_page); -static size_t __iovec_copy_from_user_inatomic(char *vaddr, - const struct iovec *iov, size_t base, size_t bytes) -{ - size_t copied = 0, left = 0; - - while (bytes) { - char __user *buf = iov->iov_base + base; - int copy = min(bytes, iov->iov_len - base); - - base = 0; - left = __copy_from_user_inatomic(vaddr, buf, copy); - copied += copy; - bytes -= copy; - vaddr += copy; - iov++; - - if (unlikely(left)) - break; - } - return copied - left; -} - -/* - * Copy as much as we can into the page and return the number of bytes which - * were successfully copied. If a fault is encountered then return the number of - * bytes which were copied. - */ -size_t iov_iter_copy_from_user_atomic(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr; - size_t copied; - - kaddr = kmap_atomic(page); - if (likely(i->nr_segs == 1)) { - int left; - char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); - copied = bytes - left; - } else { - copied = __iovec_copy_from_user_inatomic(kaddr + offset, - i->iov, i->iov_offset, bytes); - } - kunmap_atomic(kaddr); - - return copied; -} -EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); - -/* - * This has the same sideeffects and return value as - * iov_iter_copy_from_user_atomic(). - * The difference is that it attempts to resolve faults. - * Page must not be locked. - */ -size_t iov_iter_copy_from_user(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr; - size_t copied; - - kaddr = kmap(page); - if (likely(i->nr_segs == 1)) { - int left; - char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user(kaddr + offset, buf, bytes); - copied = bytes - left; - } else { - copied = __iovec_copy_from_user_inatomic(kaddr + offset, - i->iov, i->iov_offset, bytes); - } - kunmap(page); - return copied; -} -EXPORT_SYMBOL(iov_iter_copy_from_user); - -void iov_iter_advance(struct iov_iter *i, size_t bytes) -{ - BUG_ON(i->count < bytes); - - if (likely(i->nr_segs == 1)) { - i->iov_offset += bytes; - i->count -= bytes; - } else { - const struct iovec *iov = i->iov; - size_t base = i->iov_offset; - unsigned long nr_segs = i->nr_segs; - - /* - * The !iov->iov_len check ensures we skip over unlikely - * zero-length segments (without overruning the iovec). - */ - while (bytes || unlikely(i->count && !iov->iov_len)) { - int copy; - - copy = min(bytes, iov->iov_len - base); - BUG_ON(!i->count || i->count < copy); - i->count -= copy; - bytes -= copy; - base += copy; - if (iov->iov_len == base) { - iov++; - nr_segs--; - base = 0; - } - } - i->iov = iov; - i->iov_offset = base; - i->nr_segs = nr_segs; - } -} -EXPORT_SYMBOL(iov_iter_advance); - -/* - * Fault in the first iovec of the given iov_iter, to a maximum length - * of bytes. Returns 0 on success, or non-zero if the memory could not be - * accessed (ie. because it is an invalid address). - * - * writev-intensive code may want this to prefault several iovecs -- that - * would be possible (callers must not rely on the fact that _only_ the - * first iovec will be faulted with the current implementation). - */ -int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) -{ - char __user *buf = i->iov->iov_base + i->iov_offset; - bytes = min(bytes, i->iov->iov_len - i->iov_offset); - return fault_in_pages_readable(buf, bytes); -} -EXPORT_SYMBOL(iov_iter_fault_in_readable); - -/* - * Return the count of just the current iov_iter segment. - */ -size_t iov_iter_single_seg_count(const struct iov_iter *i) -{ - const struct iovec *iov = i->iov; - if (i->nr_segs == 1) - return i->count; - else - return min(i->count, iov->iov_len - i->iov_offset); -} -EXPORT_SYMBOL(iov_iter_single_seg_count); - /* * Performs necessary checks before doing a write * diff --git a/mm/iov_iter.c b/mm/iov_iter.c new file mode 100644 index 000000000000..10e46cd721de --- /dev/null +++ b/mm/iov_iter.c @@ -0,0 +1,224 @@ +#include +#include +#include + +size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, + struct iov_iter *i) +{ + size_t skip, copy, left, wanted; + const struct iovec *iov; + char __user *buf; + void *kaddr, *from; + + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + wanted = bytes; + iov = i->iov; + skip = i->iov_offset; + buf = iov->iov_base + skip; + copy = min(bytes, iov->iov_len - skip); + + if (!fault_in_pages_writeable(buf, copy)) { + kaddr = kmap_atomic(page); + from = kaddr + offset; + + /* first chunk, usually the only one */ + left = __copy_to_user_inatomic(buf, from, copy); + copy -= left; + skip += copy; + from += copy; + bytes -= copy; + + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_to_user_inatomic(buf, from, copy); + copy -= left; + skip = copy; + from += copy; + bytes -= copy; + } + if (likely(!bytes)) { + kunmap_atomic(kaddr); + goto done; + } + offset = from - kaddr; + buf += copy; + kunmap_atomic(kaddr); + copy = min(bytes, iov->iov_len - skip); + } + /* Too bad - revert to non-atomic kmap */ + kaddr = kmap(page); + from = kaddr + offset; + left = __copy_to_user(buf, from, copy); + copy -= left; + skip += copy; + from += copy; + bytes -= copy; + while (unlikely(!left && bytes)) { + iov++; + buf = iov->iov_base; + copy = min(bytes, iov->iov_len); + left = __copy_to_user(buf, from, copy); + copy -= left; + skip = copy; + from += copy; + bytes -= copy; + } + kunmap(page); +done: + i->count -= wanted - bytes; + i->nr_segs -= iov - i->iov; + i->iov = iov; + i->iov_offset = skip; + return wanted - bytes; +} +EXPORT_SYMBOL(copy_page_to_iter); + +static size_t __iovec_copy_from_user_inatomic(char *vaddr, + const struct iovec *iov, size_t base, size_t bytes) +{ + size_t copied = 0, left = 0; + + while (bytes) { + char __user *buf = iov->iov_base + base; + int copy = min(bytes, iov->iov_len - base); + + base = 0; + left = __copy_from_user_inatomic(vaddr, buf, copy); + copied += copy; + bytes -= copy; + vaddr += copy; + iov++; + + if (unlikely(left)) + break; + } + return copied - left; +} + +/* + * Copy as much as we can into the page and return the number of bytes which + * were successfully copied. If a fault is encountered then return the number of + * bytes which were copied. + */ +size_t iov_iter_copy_from_user_atomic(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes) +{ + char *kaddr; + size_t copied; + + kaddr = kmap_atomic(page); + if (likely(i->nr_segs == 1)) { + int left; + char __user *buf = i->iov->iov_base + i->iov_offset; + left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); + copied = bytes - left; + } else { + copied = __iovec_copy_from_user_inatomic(kaddr + offset, + i->iov, i->iov_offset, bytes); + } + kunmap_atomic(kaddr); + + return copied; +} +EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); + +/* + * This has the same sideeffects and return value as + * iov_iter_copy_from_user_atomic(). + * The difference is that it attempts to resolve faults. + * Page must not be locked. + */ +size_t iov_iter_copy_from_user(struct page *page, + struct iov_iter *i, unsigned long offset, size_t bytes) +{ + char *kaddr; + size_t copied; + + kaddr = kmap(page); + if (likely(i->nr_segs == 1)) { + int left; + char __user *buf = i->iov->iov_base + i->iov_offset; + left = __copy_from_user(kaddr + offset, buf, bytes); + copied = bytes - left; + } else { + copied = __iovec_copy_from_user_inatomic(kaddr + offset, + i->iov, i->iov_offset, bytes); + } + kunmap(page); + return copied; +} +EXPORT_SYMBOL(iov_iter_copy_from_user); + +void iov_iter_advance(struct iov_iter *i, size_t bytes) +{ + BUG_ON(i->count < bytes); + + if (likely(i->nr_segs == 1)) { + i->iov_offset += bytes; + i->count -= bytes; + } else { + const struct iovec *iov = i->iov; + size_t base = i->iov_offset; + unsigned long nr_segs = i->nr_segs; + + /* + * The !iov->iov_len check ensures we skip over unlikely + * zero-length segments (without overruning the iovec). + */ + while (bytes || unlikely(i->count && !iov->iov_len)) { + int copy; + + copy = min(bytes, iov->iov_len - base); + BUG_ON(!i->count || i->count < copy); + i->count -= copy; + bytes -= copy; + base += copy; + if (iov->iov_len == base) { + iov++; + nr_segs--; + base = 0; + } + } + i->iov = iov; + i->iov_offset = base; + i->nr_segs = nr_segs; + } +} +EXPORT_SYMBOL(iov_iter_advance); + +/* + * Fault in the first iovec of the given iov_iter, to a maximum length + * of bytes. Returns 0 on success, or non-zero if the memory could not be + * accessed (ie. because it is an invalid address). + * + * writev-intensive code may want this to prefault several iovecs -- that + * would be possible (callers must not rely on the fact that _only_ the + * first iovec will be faulted with the current implementation). + */ +int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) +{ + char __user *buf = i->iov->iov_base + i->iov_offset; + bytes = min(bytes, i->iov->iov_len - i->iov_offset); + return fault_in_pages_readable(buf, bytes); +} +EXPORT_SYMBOL(iov_iter_fault_in_readable); + +/* + * Return the count of just the current iov_iter segment. + */ +size_t iov_iter_single_seg_count(const struct iov_iter *i) +{ + const struct iovec *iov = i->iov; + if (i->nr_segs == 1) + return i->count; + else + return min(i->count, iov->iov_len - i->iov_offset); +} +EXPORT_SYMBOL(iov_iter_single_seg_count); -- cgit From 41fc56d573c35a212688b12b48af8c303f9bb6d2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 9 Feb 2014 12:58:52 -0500 Subject: kill the 4th argument of __generic_file_aio_write() It's always equal to &iocb->ki_pos, where iocb is the value of the 1st argument. Signed-off-by: Al Viro --- fs/block_dev.c | 2 +- fs/ext4/file.c | 2 +- fs/udf/file.c | 2 +- include/linux/fs.h | 3 +-- mm/filemap.c | 13 ++++++------- 5 files changed, 10 insertions(+), 12 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/block_dev.c b/fs/block_dev.c index 1e86823a9cbd..764bd3b8d2fa 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1518,7 +1518,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, BUG_ON(iocb->ki_pos != pos); blk_start_plug(&plug); - ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + ret = __generic_file_aio_write(iocb, iov, nr_segs); if (ret > 0) { ssize_t err; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 1a5073959f32..d564bcfb23c5 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -146,7 +146,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, overwrite = 1; } - ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + ret = __generic_file_aio_write(iocb, iov, nr_segs); mutex_unlock(&inode->i_mutex); if (ret > 0) { diff --git a/fs/udf/file.c b/fs/udf/file.c index 1037637957c7..d2c170f8b035 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -171,7 +171,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, } else up_write(&iinfo->i_data_sem); - retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + retval = __generic_file_aio_write(iocb, iov, nr_segs); mutex_unlock(&inode->i_mutex); if (retval > 0) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 2a5b1744f80a..e677d1e1189f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2392,8 +2392,7 @@ extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr, unsigned long size, pgoff_t pgoff); int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk); extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); -extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, - loff_t *); +extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, unsigned long *, loff_t, loff_t *, size_t, size_t); diff --git a/mm/filemap.c b/mm/filemap.c index c4730efa5d9e..ce2246dd90de 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2222,14 +2222,14 @@ EXPORT_SYMBOL(generic_file_buffered_write); * avoid syncing under i_mutex. */ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) + unsigned long nr_segs) { struct file *file = iocb->ki_filp; struct address_space * mapping = file->f_mapping; size_t ocount; /* original count */ size_t count; /* after file limit checks */ struct inode *inode = mapping->host; - loff_t pos; + loff_t pos = iocb->ki_pos; ssize_t written; ssize_t err; @@ -2239,7 +2239,6 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, return err; count = ocount; - pos = *ppos; /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; @@ -2266,7 +2265,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, ssize_t written_buffered; written = generic_file_direct_write(iocb, iov, &nr_segs, pos, - ppos, count, ocount); + &iocb->ki_pos, count, ocount); if (written < 0 || written == count) goto out; /* @@ -2276,7 +2275,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, pos += written; count -= written; written_buffered = generic_file_buffered_write(iocb, iov, - nr_segs, pos, ppos, count, + nr_segs, pos, &iocb->ki_pos, count, written); /* * If generic_file_buffered_write() retuned a synchronous error @@ -2310,7 +2309,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, } } else { written = generic_file_buffered_write(iocb, iov, nr_segs, - pos, ppos, count, written); + pos, &iocb->ki_pos, count, written); } out: current->backing_dev_info = NULL; @@ -2339,7 +2338,7 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); + ret = __generic_file_aio_write(iocb, iov, nr_segs); mutex_unlock(&inode->i_mutex); if (ret > 0) { -- cgit From fcacafd269adc88f41b68cb77a3f957a66563428 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 9 Feb 2014 13:37:49 -0500 Subject: kill the 5th argument of generic_file_buffered_write() same story - it's &iocb->ki_pos in all cases Signed-off-by: Al Viro --- fs/ceph/file.c | 3 +-- fs/ocfs2/file.c | 2 +- fs/xfs/xfs_file.c | 2 +- include/linux/fs.h | 2 +- mm/filemap.c | 9 ++++----- 5 files changed, 8 insertions(+), 10 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 09c7afe32e49..a798db5e5e39 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -978,8 +978,7 @@ retry_snap: * can not run at the same time */ written = generic_file_buffered_write(iocb, iov, nr_segs, - pos, &iocb->ki_pos, - count, 0); + pos, count, 0); mutex_unlock(&inode->i_mutex); } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 51632c40e896..89099cce14fe 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2383,7 +2383,7 @@ relock: } else { current->backing_dev_info = file->f_mapping->backing_dev_info; written = generic_file_buffered_write(iocb, iov, nr_segs, *ppos, - ppos, count, 0); + count, 0); current->backing_dev_info = NULL; } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 64b48eade91d..175ce58fbfa3 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -738,7 +738,7 @@ xfs_file_buffered_aio_write( write_retry: trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0); ret = generic_file_buffered_write(iocb, iovp, nr_segs, - pos, &iocb->ki_pos, count, 0); + pos, count, 0); /* * If we just got an ENOSPC, try to write back all dirty inodes to diff --git a/include/linux/fs.h b/include/linux/fs.h index e677d1e1189f..830e37420f5e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2397,7 +2397,7 @@ extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsi extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, unsigned long *, loff_t, loff_t *, size_t, size_t); extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, - unsigned long, loff_t, loff_t *, size_t, ssize_t); + unsigned long, loff_t, size_t, ssize_t); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); extern int generic_segment_checks(const struct iovec *iov, diff --git a/mm/filemap.c b/mm/filemap.c index ce2246dd90de..9d515a1a2372 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2183,7 +2183,7 @@ again: ssize_t generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos, loff_t *ppos, + unsigned long nr_segs, loff_t pos, size_t count, ssize_t written) { struct file *file = iocb->ki_filp; @@ -2195,7 +2195,7 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, if (likely(status >= 0)) { written += status; - *ppos = pos + status; + iocb->ki_pos = pos + status; } return written ? written : status; @@ -2275,8 +2275,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, pos += written; count -= written; written_buffered = generic_file_buffered_write(iocb, iov, - nr_segs, pos, &iocb->ki_pos, count, - written); + nr_segs, pos, count, written); /* * If generic_file_buffered_write() retuned a synchronous error * then we want to return the number of bytes which were @@ -2309,7 +2308,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, } } else { written = generic_file_buffered_write(iocb, iov, nr_segs, - pos, &iocb->ki_pos, count, written); + pos, count, written); } out: current->backing_dev_info = NULL; -- cgit From 5cb6c6c7eb1ed24744b41fad47d9a25b72207098 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Feb 2014 20:58:20 -0500 Subject: generic_file_direct_write(): get rid of ppos argument always equal to &iocb->ki_pos. Signed-off-by: Al Viro --- fs/btrfs/file.c | 2 +- fs/fuse/file.c | 3 +-- fs/ocfs2/file.c | 2 +- fs/xfs/xfs_file.c | 2 +- include/linux/fs.h | 2 +- mm/filemap.c | 6 +++--- 6 files changed, 8 insertions(+), 9 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f6032a2bfab9..8ed4b165abbd 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1640,7 +1640,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, loff_t endbyte; int err; - written = generic_file_direct_write(iocb, iov, &nr_segs, pos, &iocb->ki_pos, + written = generic_file_direct_write(iocb, iov, &nr_segs, pos, count, ocount); if (written < 0 || written == count) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index a91d3b4d32f3..fd06d1ebc2eb 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1143,8 +1143,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, goto out; if (file->f_flags & O_DIRECT) { - written = generic_file_direct_write(iocb, iov, &nr_segs, - pos, &iocb->ki_pos, + written = generic_file_direct_write(iocb, iov, &nr_segs, pos, count, ocount); if (written < 0 || written == count) goto out; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 89099cce14fe..77b8a742866f 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2375,7 +2375,7 @@ relock: if (direct_io) { written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos, - ppos, count, ocount); + count, ocount); if (written < 0) { ret = written; goto out_dio; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 175ce58fbfa3..e593554ce65e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -699,7 +699,7 @@ xfs_file_dio_aio_write( trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0); ret = generic_file_direct_write(iocb, iovp, - &nr_segs, pos, &iocb->ki_pos, count, ocount); + &nr_segs, pos, count, ocount); out: xfs_rw_iunlock(ip, iolock); diff --git a/include/linux/fs.h b/include/linux/fs.h index 830e37420f5e..9dfd7c7ff8e3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2395,7 +2395,7 @@ extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsig extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long); extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, - unsigned long *, loff_t, loff_t *, size_t, size_t); + unsigned long *, loff_t, size_t, size_t); extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, unsigned long, loff_t, size_t, ssize_t); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); diff --git a/mm/filemap.c b/mm/filemap.c index 9d515a1a2372..93e9cf576452 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1985,7 +1985,7 @@ EXPORT_SYMBOL(pagecache_write_end); ssize_t generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long *nr_segs, loff_t pos, loff_t *ppos, + unsigned long *nr_segs, loff_t pos, size_t count, size_t ocount) { struct file *file = iocb->ki_filp; @@ -2046,7 +2046,7 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, i_size_write(inode, pos); mark_inode_dirty(inode); } - *ppos = pos; + iocb->ki_pos = pos; } out: return written; @@ -2265,7 +2265,7 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, ssize_t written_buffered; written = generic_file_direct_write(iocb, iov, &nr_segs, pos, - &iocb->ki_pos, count, ocount); + count, ocount); if (written < 0 || written == count) goto out; /* -- cgit From 3b93f911d55cf8b3540f82fac4eeddfee7b5de0c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Feb 2014 21:34:08 -0500 Subject: export generic_perform_write(), start getting rid of generic_file_buffer_write() Signed-off-by: Al Viro --- include/linux/fs.h | 2 ++ mm/filemap.c | 37 +++++++++++++++++++++---------------- 2 files changed, 23 insertions(+), 16 deletions(-) (limited to 'mm/filemap.c') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9dfd7c7ff8e3..87be51aff9d7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -48,6 +48,7 @@ struct cred; struct swap_info_struct; struct seq_file; struct workqueue_struct; +struct iov_iter; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -2396,6 +2397,7 @@ extern ssize_t __generic_file_aio_write(struct kiocb *, const struct iovec *, un extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, unsigned long *, loff_t, size_t, size_t); +extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, unsigned long, loff_t, size_t, ssize_t); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); diff --git a/mm/filemap.c b/mm/filemap.c index 93e9cf576452..09bfc9b3bb51 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2092,7 +2092,7 @@ found: } EXPORT_SYMBOL(grab_cache_page_write_begin); -static ssize_t generic_perform_write(struct file *file, +ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { struct address_space *mapping = file->f_mapping; @@ -2180,6 +2180,7 @@ again: return written ? written : status; } +EXPORT_SYMBOL(generic_perform_write); ssize_t generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, @@ -2230,8 +2231,10 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, size_t count; /* after file limit checks */ struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; - ssize_t written; + ssize_t written = 0; ssize_t err; + ssize_t status; + struct iov_iter from; ocount = 0; err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); @@ -2242,8 +2245,6 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, /* 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, S_ISBLK(inode->i_mode)); if (err) goto out; @@ -2259,44 +2260,47 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err) goto out; + iov_iter_init(&from, iov, nr_segs, count, 0); + /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (unlikely(file->f_flags & O_DIRECT)) { loff_t endbyte; - ssize_t written_buffered; - written = generic_file_direct_write(iocb, iov, &nr_segs, pos, + written = generic_file_direct_write(iocb, iov, &from.nr_segs, pos, count, ocount); if (written < 0 || written == count) goto out; + iov_iter_advance(&from, written); + /* * direct-io write to a hole: fall through to buffered I/O * for completing the rest of the request. */ pos += written; count -= written; - written_buffered = generic_file_buffered_write(iocb, iov, - nr_segs, pos, count, written); + + status = generic_perform_write(file, &from, pos); /* - * If generic_file_buffered_write() retuned a synchronous error + * If generic_perform_write() returned 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; + if (unlikely(status < 0) && !written) { + err = status; goto out; } - + iocb->ki_pos = pos + status; /* * 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; + endbyte = pos + status - 1; err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte); if (err == 0) { - written = written_buffered; + written += status; invalidate_mapping_pages(mapping, pos >> PAGE_CACHE_SHIFT, endbyte >> PAGE_CACHE_SHIFT); @@ -2307,8 +2311,9 @@ ssize_t __generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, */ } } else { - written = generic_file_buffered_write(iocb, iov, nr_segs, - pos, count, written); + written = generic_perform_write(file, &from, pos); + if (likely(written >= 0)) + iocb->ki_pos = pos + written; } out: current->backing_dev_info = NULL; -- cgit From ccad2365668f12336dd497d9039e8584af836070 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 11 Feb 2014 22:36:48 -0500 Subject: kill generic_file_buffered_write() Signed-off-by: Al Viro --- include/linux/fs.h | 2 -- mm/filemap.c | 23 +---------------------- 2 files changed, 1 insertion(+), 24 deletions(-) (limited to 'mm/filemap.c') diff --git a/include/linux/fs.h b/include/linux/fs.h index 87be51aff9d7..c309b7a0da2d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2398,8 +2398,6 @@ extern ssize_t generic_file_aio_write(struct kiocb *, const struct iovec *, unsi extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *, unsigned long *, loff_t, size_t, size_t); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); -extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *, - unsigned long, loff_t, size_t, ssize_t); extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos); extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos); extern int generic_segment_checks(const struct iovec *iov, diff --git a/mm/filemap.c b/mm/filemap.c index 09bfc9b3bb51..1a455142784d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -76,7 +76,7 @@ * ->mmap_sem * ->lock_page (access_process_vm) * - * ->i_mutex (generic_file_buffered_write) + * ->i_mutex (generic_perform_write) * ->mmap_sem (fault_in_pages_readable->do_page_fault) * * bdi->wb.list_lock @@ -2182,27 +2182,6 @@ again: } EXPORT_SYMBOL(generic_perform_write); -ssize_t -generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos, - size_t count, ssize_t written) -{ - struct file *file = iocb->ki_filp; - ssize_t status; - struct iov_iter i; - - iov_iter_init(&i, iov, nr_segs, count, written); - status = generic_perform_write(file, &i, pos); - - if (likely(status >= 0)) { - written += status; - iocb->ki_pos = pos + status; - } - - return written ? written : status; -} -EXPORT_SYMBOL(generic_file_buffered_write); - /** * __generic_file_aio_write - write data to a file * @iocb: IO state structure (file, offset, etc.) -- cgit From d26914d11751b23ca2e8747725f2cae10c2f2c1b Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 3 Apr 2014 14:47:24 -0700 Subject: mm: optimize put_mems_allowed() usage Since put_mems_allowed() is strictly optional, its a seqcount retry, we don't need to evaluate the function if the allocation was in fact successful, saving a smp_rmb some loads and comparisons on some relative fast-paths. Since the naming, get/put_mems_allowed() does suggest a mandatory pairing, rename the interface, as suggested by Mel, to resemble the seqcount interface. This gives us: read_mems_allowed_begin() and read_mems_allowed_retry(), where it is important to note that the return value of the latter call is inverted from its previous incarnation. Signed-off-by: Peter Zijlstra Signed-off-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 27 ++++++++++++++------------- kernel/cpuset.c | 2 +- mm/filemap.c | 4 ++-- mm/hugetlb.c | 4 ++-- mm/mempolicy.c | 12 ++++++------ mm/page_alloc.c | 8 ++++---- mm/slab.c | 4 ++-- mm/slub.c | 16 +++++++--------- 8 files changed, 38 insertions(+), 39 deletions(-) (limited to 'mm/filemap.c') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 3fe661fe96d1..b19d3dc2e651 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -87,25 +87,26 @@ extern void rebuild_sched_domains(void); extern void cpuset_print_task_mems_allowed(struct task_struct *p); /* - * get_mems_allowed is required when making decisions involving mems_allowed - * such as during page allocation. mems_allowed can be updated in parallel - * and depending on the new value an operation can fail potentially causing - * process failure. A retry loop with get_mems_allowed and put_mems_allowed - * prevents these artificial failures. + * read_mems_allowed_begin is required when making decisions involving + * mems_allowed such as during page allocation. mems_allowed can be updated in + * parallel and depending on the new value an operation can fail potentially + * causing process failure. A retry loop with read_mems_allowed_begin and + * read_mems_allowed_retry prevents these artificial failures. */ -static inline unsigned int get_mems_allowed(void) +static inline unsigned int read_mems_allowed_begin(void) { return read_seqcount_begin(¤t->mems_allowed_seq); } /* - * If this returns false, the operation that took place after get_mems_allowed - * may have failed. It is up to the caller to retry the operation if + * If this returns true, the operation that took place after + * read_mems_allowed_begin may have failed artificially due to a concurrent + * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ -static inline bool put_mems_allowed(unsigned int seq) +static inline bool read_mems_allowed_retry(unsigned int seq) { - return !read_seqcount_retry(¤t->mems_allowed_seq, seq); + return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) @@ -225,14 +226,14 @@ static inline void set_mems_allowed(nodemask_t nodemask) { } -static inline unsigned int get_mems_allowed(void) +static inline unsigned int read_mems_allowed_begin(void) { return 0; } -static inline bool put_mems_allowed(unsigned int seq) +static inline bool read_mems_allowed_retry(unsigned int seq) { - return true; + return false; } #endif /* !CONFIG_CPUSETS */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index e6b1b66afe52..f6fc7475f1a1 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1022,7 +1022,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, task_lock(tsk); /* * Determine if a loop is necessary if another thread is doing - * get_mems_allowed(). If at least one node remains unchanged and + * read_mems_allowed_begin(). If at least one node remains unchanged and * tsk does not have a mempolicy, then an empty nodemask will not be * possible when mems_allowed is larger than a word. */ diff --git a/mm/filemap.c b/mm/filemap.c index 7a13f6ac5421..068cd2a63d32 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -520,10 +520,10 @@ struct page *__page_cache_alloc(gfp_t gfp) if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); page = alloc_pages_exact_node(n, gfp, 0); - } while (!put_mems_allowed(cpuset_mems_cookie) && !page); + } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); return page; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c01cb9fedb18..139b7462203b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -540,7 +540,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, goto err; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = huge_zonelist(vma, address, htlb_alloc_mask(h), &mpol, &nodemask); @@ -562,7 +562,7 @@ retry_cpuset: } mpol_cond_put(mpol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4755c8576942..e3ab02822799 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1899,7 +1899,7 @@ int node_random(const nodemask_t *maskp) * If the effective policy is 'BIND, returns a pointer to the mempolicy's * @nodemask for filtering the zonelist. * - * Must be protected by get_mems_allowed() + * Must be protected by read_mems_allowed_begin() */ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, @@ -2063,7 +2063,7 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, retry_cpuset: pol = get_vma_policy(current, vma, addr); - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); if (unlikely(pol->mode == MPOL_INTERLEAVE)) { unsigned nid; @@ -2071,7 +2071,7 @@ retry_cpuset: nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2081,7 +2081,7 @@ retry_cpuset: policy_nodemask(gfp, pol)); if (unlikely(mpol_needs_cond_ref(pol))) __mpol_put(pol); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; } @@ -2115,7 +2115,7 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) pol = &default_policy; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* * No reference counting needed for current->mempolicy @@ -2128,7 +2128,7 @@ retry_cpuset: policy_zonelist(gfp, pol, numa_node_id()), policy_nodemask(gfp, pol)); - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3bac76ae4b30..979378deccbf 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2739,7 +2739,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, return NULL; retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); /* The preferred zone is used for statistics later */ first_zones_zonelist(zonelist, high_zoneidx, @@ -2777,7 +2777,7 @@ out: * the mask is being updated. If a page allocation is about to fail, * check if the cpuset changed during allocation and if so, retry. */ - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; memcg_kmem_commit_charge(page, memcg, order); @@ -3045,9 +3045,9 @@ bool skip_free_areas_node(unsigned int flags, int nid) goto out; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); ret = !node_isset(nid, cpuset_current_mems_allowed); - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); out: return ret; } diff --git a/mm/slab.c b/mm/slab.c index b264214c77ea..9153c802e2fe 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3073,7 +3073,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); retry_cpuset: - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(slab_node(), flags); retry: @@ -3131,7 +3131,7 @@ retry: } } - if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj)) + if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return obj; } diff --git a/mm/slub.c b/mm/slub.c index 25f14ad8f817..7611f148ee81 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1684,7 +1684,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, return NULL; do { - cpuset_mems_cookie = get_mems_allowed(); + cpuset_mems_cookie = read_mems_allowed_begin(); zonelist = node_zonelist(slab_node(), flags); for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { struct kmem_cache_node *n; @@ -1696,19 +1696,17 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, object = get_partial_node(s, n, c, flags); if (object) { /* - * Return the object even if - * put_mems_allowed indicated that - * the cpuset mems_allowed was - * updated in parallel. It's a - * harmless race between the alloc - * and the cpuset update. + * Don't check read_mems_allowed_retry() + * here - if mems_allowed was updated in + * parallel, that was a harmless race + * between allocation and the cpuset + * update */ - put_mems_allowed(cpuset_mems_cookie); return object; } } } - } while (!put_mems_allowed(cpuset_mems_cookie)); + } while (read_mems_allowed_retry(cpuset_mems_cookie)); #endif return NULL; } -- cgit From e7b563bb2a6f4d974208da46200784b9c5b5a47e Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 3 Apr 2014 14:47:44 -0700 Subject: mm: filemap: move radix tree hole searching here The radix tree hole searching code is only used for page cache, for example the readahead code trying to get a a picture of the area surrounding a fault. It sufficed to rely on the radix tree definition of holes, which is "empty tree slot". But this is about to change, though, as shadow page descriptors will be stored in the page cache after the actual pages get evicted from memory. Move the functions over to mm/filemap.c and make them native page cache operations, where they can later be adapted to handle the new definition of "page cache hole". Signed-off-by: Johannes Weiner Reviewed-by: Rik van Riel Reviewed-by: Minchan Kim Acked-by: Mel Gorman Cc: Andrea Arcangeli Cc: Bob Liu Cc: Christoph Hellwig Cc: Dave Chinner Cc: Greg Thelen Cc: Hugh Dickins Cc: Jan Kara Cc: KOSAKI Motohiro Cc: Luigi Semenzato Cc: Metin Doslu Cc: Michel Lespinasse Cc: Ozgun Erdogan Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Ryan Mallon Cc: Tejun Heo Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/nfs/blocklayout/blocklayout.c | 2 +- include/linux/pagemap.h | 5 +++ include/linux/radix-tree.h | 4 --- lib/radix-tree.c | 75 --------------------------------------- mm/filemap.c | 76 ++++++++++++++++++++++++++++++++++++++++ mm/readahead.c | 4 +-- 6 files changed, 84 insertions(+), 82 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 56ff823ca82e..65d849bdf77a 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -1213,7 +1213,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE); if (end != NFS_I(inode)->npages) { rcu_read_lock(); - end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX); + end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); rcu_read_unlock(); } diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 1710d1b060ba..52d56872fe26 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -243,6 +243,11 @@ static inline struct page *page_cache_alloc_readahead(struct address_space *x) typedef int filler_t(void *, struct page *); +pgoff_t page_cache_next_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan); +pgoff_t page_cache_prev_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan); + extern struct page * find_get_page(struct address_space *mapping, pgoff_t index); extern struct page * find_lock_page(struct address_space *mapping, diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 1bf0a9c388d9..e8be53ecfc45 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -227,10 +227,6 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results, unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items); -unsigned long radix_tree_next_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan); -unsigned long radix_tree_prev_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); void radix_tree_init(void); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index d832117e7d94..7e30d2a7f346 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -946,81 +946,6 @@ next: } EXPORT_SYMBOL(radix_tree_range_tag_if_tagged); - -/** - * radix_tree_next_hole - find the next hole (not-present entry) - * @root: tree root - * @index: index key - * @max_scan: maximum range to search - * - * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the lowest - * indexed hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'return - index >= max_scan' - * will be true). In rare cases of index wrap-around, 0 will be returned. - * - * radix_tree_next_hole may be called under rcu_read_lock. However, like - * radix_tree_gang_lookup, this will not atomically search a snapshot of - * the tree at a single point in time. For example, if a hole is created - * at index 5, then subsequently a hole is created at index 10, - * radix_tree_next_hole covering both indexes may return 10 if called - * under rcu_read_lock. - */ -unsigned long radix_tree_next_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan) -{ - unsigned long i; - - for (i = 0; i < max_scan; i++) { - if (!radix_tree_lookup(root, index)) - break; - index++; - if (index == 0) - break; - } - - return index; -} -EXPORT_SYMBOL(radix_tree_next_hole); - -/** - * radix_tree_prev_hole - find the prev hole (not-present entry) - * @root: tree root - * @index: index key - * @max_scan: maximum range to search - * - * Search backwards in the range [max(index-max_scan+1, 0), index] - * for the first hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'index - return >= max_scan' - * will be true). In rare cases of wrap-around, ULONG_MAX will be returned. - * - * radix_tree_next_hole may be called under rcu_read_lock. However, like - * radix_tree_gang_lookup, this will not atomically search a snapshot of - * the tree at a single point in time. For example, if a hole is created - * at index 10, then subsequently a hole is created at index 5, - * radix_tree_prev_hole covering both indexes may return 5 if called under - * rcu_read_lock. - */ -unsigned long radix_tree_prev_hole(struct radix_tree_root *root, - unsigned long index, unsigned long max_scan) -{ - unsigned long i; - - for (i = 0; i < max_scan; i++) { - if (!radix_tree_lookup(root, index)) - break; - index--; - if (index == ULONG_MAX) - break; - } - - return index; -} -EXPORT_SYMBOL(radix_tree_prev_hole); - /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root diff --git a/mm/filemap.c b/mm/filemap.c index 068cd2a63d32..40115c6c0791 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -685,6 +685,82 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, } } +/** + * page_cache_next_hole - find the next hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the + * lowest indexed hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'return - index >= + * max_scan' will be true). In rare cases of index wrap-around, 0 will + * be returned. + * + * page_cache_next_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 5, then subsequently a hole is created at + * index 10, page_cache_next_hole covering both indexes may return 10 + * if called under rcu_read_lock. + */ +pgoff_t page_cache_next_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + if (!radix_tree_lookup(&mapping->page_tree, index)) + break; + index++; + if (index == 0) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_next_hole); + +/** + * page_cache_prev_hole - find the prev hole (not-present entry) + * @mapping: mapping + * @index: index + * @max_scan: maximum range to search + * + * Search backwards in the range [max(index-max_scan+1, 0), index] for + * the first hole. + * + * Returns: the index of the hole if found, otherwise returns an index + * outside of the set specified (in which case 'index - return >= + * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX + * will be returned. + * + * page_cache_prev_hole may be called under rcu_read_lock. However, + * like radix_tree_gang_lookup, this will not atomically search a + * snapshot of the tree at a single point in time. For example, if a + * hole is created at index 10, then subsequently a hole is created at + * index 5, page_cache_prev_hole covering both indexes may return 5 if + * called under rcu_read_lock. + */ +pgoff_t page_cache_prev_hole(struct address_space *mapping, + pgoff_t index, unsigned long max_scan) +{ + unsigned long i; + + for (i = 0; i < max_scan; i++) { + if (!radix_tree_lookup(&mapping->page_tree, index)) + break; + index--; + if (index == ULONG_MAX) + break; + } + + return index; +} +EXPORT_SYMBOL(page_cache_prev_hole); + /** * find_get_page - find and get a page reference * @mapping: the address_space to search diff --git a/mm/readahead.c b/mm/readahead.c index 0de2360d65f3..c62d85ace0cc 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -347,7 +347,7 @@ static pgoff_t count_history_pages(struct address_space *mapping, pgoff_t head; rcu_read_lock(); - head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max); + head = page_cache_prev_hole(mapping, offset - 1, max); rcu_read_unlock(); return offset - 1 - head; @@ -427,7 +427,7 @@ ondemand_readahead(struct address_space *mapping, pgoff_t start; rcu_read_lock(); - start = radix_tree_next_hole(&mapping->page_tree, offset+1,max); + start = page_cache_next_hole(mapping, offset + 1, max); rcu_read_unlock(); if (!start || start - offset > max) -- cgit From 0cd6144aadd2afd19d1aca880153530c52957604 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 3 Apr 2014 14:47:46 -0700 Subject: mm + fs: prepare for non-page entries in page cache radix trees shmem mappings already contain exceptional entries where swap slot information is remembered. To be able to store eviction information for regular page cache, prepare every site dealing with the radix trees directly to handle entries other than pages. The common lookup functions will filter out non-page entries and return NULL for page cache holes, just as before. But provide a raw version of the API which returns non-page entries as well, and switch shmem over to use it. Signed-off-by: Johannes Weiner Reviewed-by: Rik van Riel Reviewed-by: Minchan Kim Cc: Andrea Arcangeli Cc: Bob Liu Cc: Christoph Hellwig Cc: Dave Chinner Cc: Greg Thelen Cc: Hugh Dickins Cc: Jan Kara Cc: KOSAKI Motohiro Cc: Luigi Semenzato Cc: Mel Gorman Cc: Metin Doslu Cc: Michel Lespinasse Cc: Ozgun Erdogan Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Ryan Mallon Cc: Tejun Heo Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/btrfs/compression.c | 2 +- include/linux/mm.h | 8 ++ include/linux/pagemap.h | 15 ++-- include/linux/pagevec.h | 5 ++ include/linux/shmem_fs.h | 1 + mm/filemap.c | 202 +++++++++++++++++++++++++++++++++++++++++------ mm/mincore.c | 20 +++-- mm/readahead.c | 2 +- mm/shmem.c | 99 +++++------------------ mm/swap.c | 51 ++++++++++++ mm/truncate.c | 74 ++++++++++++++--- 11 files changed, 349 insertions(+), 130 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index b01fb6c527e3..d43c544d3b68 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -472,7 +472,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, pg_index); rcu_read_unlock(); - if (page) { + if (page && !radix_tree_exceptional_entry(page)) { misses++; if (misses > 4) break; diff --git a/include/linux/mm.h b/include/linux/mm.h index 2eec61fe75c9..b1331aff769c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1041,6 +1041,14 @@ extern void show_free_areas(unsigned int flags); extern bool skip_free_areas_node(unsigned int flags, int nid); int shmem_zero_setup(struct vm_area_struct *); +#ifdef CONFIG_SHMEM +bool shmem_mapping(struct address_space *mapping); +#else +static inline bool shmem_mapping(struct address_space *mapping) +{ + return false; +} +#endif extern int can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 52d56872fe26..493bfd85214e 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -248,12 +248,15 @@ pgoff_t page_cache_next_hole(struct address_space *mapping, pgoff_t page_cache_prev_hole(struct address_space *mapping, pgoff_t index, unsigned long max_scan); -extern struct page * find_get_page(struct address_space *mapping, - pgoff_t index); -extern struct page * find_lock_page(struct address_space *mapping, - pgoff_t index); -extern struct page * find_or_create_page(struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask); +struct page *find_get_entry(struct address_space *mapping, pgoff_t offset); +struct page *find_get_page(struct address_space *mapping, pgoff_t offset); +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset); +struct page *find_lock_page(struct address_space *mapping, pgoff_t offset); +struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, + gfp_t gfp_mask); +unsigned find_get_entries(struct address_space *mapping, pgoff_t start, + unsigned int nr_entries, struct page **entries, + pgoff_t *indices); unsigned find_get_pages(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index e4dbfab37729..b45d391b4540 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -22,6 +22,11 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_entries, + pgoff_t *indices); +void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_pages); unsigned pagevec_lookup_tag(struct pagevec *pvec, diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 9d55438bc4ad..4d1771c2d29f 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -51,6 +51,7 @@ extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern bool shmem_mapping(struct address_space *mapping); extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); diff --git a/mm/filemap.c b/mm/filemap.c index 40115c6c0791..efc63876477f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -446,6 +446,29 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); +static int page_cache_tree_insert(struct address_space *mapping, + struct page *page) +{ + void **slot; + int error; + + slot = radix_tree_lookup_slot(&mapping->page_tree, page->index); + if (slot) { + void *p; + + p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + if (!radix_tree_exceptional_entry(p)) + return -EEXIST; + radix_tree_replace_slot(slot, page); + mapping->nrpages++; + return 0; + } + error = radix_tree_insert(&mapping->page_tree, page->index, page); + if (!error) + mapping->nrpages++; + return error; +} + /** * add_to_page_cache_locked - add a locked page to the pagecache * @page: page to add @@ -480,11 +503,10 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, page->index = offset; spin_lock_irq(&mapping->tree_lock); - error = radix_tree_insert(&mapping->page_tree, offset, page); + error = page_cache_tree_insert(mapping, page); radix_tree_preload_end(); if (unlikely(error)) goto err_insert; - mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); spin_unlock_irq(&mapping->tree_lock); trace_mm_filemap_add_to_page_cache(page); @@ -712,7 +734,10 @@ pgoff_t page_cache_next_hole(struct address_space *mapping, unsigned long i; for (i = 0; i < max_scan; i++) { - if (!radix_tree_lookup(&mapping->page_tree, index)) + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) break; index++; if (index == 0) @@ -750,7 +775,10 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping, unsigned long i; for (i = 0; i < max_scan; i++) { - if (!radix_tree_lookup(&mapping->page_tree, index)) + struct page *page; + + page = radix_tree_lookup(&mapping->page_tree, index); + if (!page || radix_tree_exceptional_entry(page)) break; index--; if (index == ULONG_MAX) @@ -762,14 +790,19 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping, EXPORT_SYMBOL(page_cache_prev_hole); /** - * find_get_page - find and get a page reference + * find_get_entry - find and get a page cache entry * @mapping: the address_space to search - * @offset: the page index + * @offset: the page cache index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. * - * Is there a pagecache struct page at the given (mapping, offset) tuple? - * If yes, increment its refcount and return it; if no, return NULL. + * If the slot holds a shadow entry of a previously evicted page, it + * is returned. + * + * Otherwise, %NULL is returned. */ -struct page *find_get_page(struct address_space *mapping, pgoff_t offset) +struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) { void **pagep; struct page *page; @@ -810,24 +843,50 @@ out: return page; } -EXPORT_SYMBOL(find_get_page); +EXPORT_SYMBOL(find_get_entry); /** - * find_lock_page - locate, pin and lock a pagecache page + * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * - * Locates the desired pagecache page, locks it, increments its reference - * count and returns its address. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned with an increased refcount. * - * Returns zero if the page was not present. find_lock_page() may sleep. + * Otherwise, %NULL is returned. */ -struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) +struct page *find_get_page(struct address_space *mapping, pgoff_t offset) +{ + struct page *page = find_get_entry(mapping, offset); + + if (radix_tree_exceptional_entry(page)) + page = NULL; + return page; +} +EXPORT_SYMBOL(find_get_page); + +/** + * find_lock_entry - locate, pin and lock a page cache entry + * @mapping: the address_space to search + * @offset: the page cache index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the slot holds a shadow entry of a previously evicted page, it + * is returned. + * + * Otherwise, %NULL is returned. + * + * find_lock_entry() may sleep. + */ +struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset) { struct page *page; repeat: - page = find_get_page(mapping, offset); + page = find_get_entry(mapping, offset); if (page && !radix_tree_exception(page)) { lock_page(page); /* Has the page been truncated? */ @@ -840,6 +899,29 @@ repeat: } return page; } +EXPORT_SYMBOL(find_lock_entry); + +/** + * find_lock_page - locate, pin and lock a pagecache page + * @mapping: the address_space to search + * @offset: the page index + * + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * Otherwise, %NULL is returned. + * + * find_lock_page() may sleep. + */ +struct page *find_lock_page(struct address_space *mapping, pgoff_t offset) +{ + struct page *page = find_lock_entry(mapping, offset); + + if (radix_tree_exceptional_entry(page)) + page = NULL; + return page; +} EXPORT_SYMBOL(find_lock_page); /** @@ -848,16 +930,18 @@ EXPORT_SYMBOL(find_lock_page); * @index: the page's index into the mapping * @gfp_mask: page allocation mode * - * Locates a page in the pagecache. If the page is not present, a new page - * is allocated using @gfp_mask and is added to the pagecache and to the VM's - * LRU list. The returned page is locked and has its reference count - * incremented. + * Looks up the page cache slot at @mapping & @offset. If there is a + * page cache page, it is returned locked and with an increased + * refcount. + * + * If the page is not present, a new page is allocated using @gfp_mask + * and added to the page cache and the VM's LRU list. The page is + * returned locked and with an increased refcount. * - * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic - * allocation! + * On memory exhaustion, %NULL is returned. * - * find_or_create_page() returns the desired page's address, or zero on - * memory exhaustion. + * find_or_create_page() may sleep, even if @gfp_flags specifies an + * atomic allocation! */ struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask) @@ -889,6 +973,76 @@ repeat: } EXPORT_SYMBOL(find_or_create_page); +/** + * find_get_entries - gang pagecache lookup + * @mapping: The address_space to search + * @start: The starting page cache index + * @nr_entries: The maximum number of entries + * @entries: Where the resulting entries are placed + * @indices: The cache indices corresponding to the entries in @entries + * + * find_get_entries() will search for and return a group of up to + * @nr_entries entries in the mapping. The entries are placed at + * @entries. find_get_entries() takes a reference against any actual + * pages it returns. + * + * The search returns a group of mapping-contiguous page cache entries + * with ascending indexes. There may be holes in the indices due to + * not-present pages. + * + * Any shadow entries of evicted pages are included in the returned + * array. + * + * find_get_entries() returns the number of pages and shadow entries + * which were found. + */ +unsigned find_get_entries(struct address_space *mapping, + pgoff_t start, unsigned int nr_entries, + struct page **entries, pgoff_t *indices) +{ + void **slot; + unsigned int ret = 0; + struct radix_tree_iter iter; + + if (!nr_entries) + return 0; + + rcu_read_lock(); +restart: + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + struct page *page; +repeat: + page = radix_tree_deref_slot(slot); + if (unlikely(!page)) + continue; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + goto restart; + /* + * Otherwise, we must be storing a swap entry + * here as an exceptional entry: so return it + * without attempting to raise page count. + */ + goto export; + } + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *slot)) { + page_cache_release(page); + goto repeat; + } +export: + indices[ret] = iter.index; + entries[ret] = page; + if (++ret == nr_entries) + break; + } + rcu_read_unlock(); + return ret; +} + /** * find_get_pages - gang pagecache lookup * @mapping: The address_space to search diff --git a/mm/mincore.c b/mm/mincore.c index 101623378fbf..725c80961048 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) * any other file mapping (ie. marked !present and faulted in with * tmpfs's .fault). So swapped out tmpfs mappings are tested here. */ - page = find_get_page(mapping, pgoff); #ifdef CONFIG_SWAP - /* shmem/tmpfs may return swap: account for swapcache page too. */ - if (radix_tree_exceptional_entry(page)) { - swp_entry_t swap = radix_to_swp_entry(page); - page = find_get_page(swap_address_space(swap), swap.val); - } + if (shmem_mapping(mapping)) { + page = find_get_entry(mapping, pgoff); + /* + * shmem/tmpfs may return swap: account for swapcache + * page too. + */ + if (radix_tree_exceptional_entry(page)) { + swp_entry_t swp = radix_to_swp_entry(page); + page = find_get_page(swap_address_space(swp), swp.val); + } + } else + page = find_get_page(mapping, pgoff); +#else + page = find_get_page(mapping, pgoff); #endif if (page) { present = PageUptodate(page); diff --git a/mm/readahead.c b/mm/readahead.c index c62d85ace0cc..62c500a088a7 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -179,7 +179,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp, rcu_read_lock(); page = radix_tree_lookup(&mapping->page_tree, page_offset); rcu_read_unlock(); - if (page) + if (page && !radix_tree_exceptional_entry(page)) continue; page = page_cache_alloc_readahead(mapping); diff --git a/mm/shmem.c b/mm/shmem.c index e470997010cd..a3ba988ec946 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -328,56 +328,6 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) BUG_ON(error); } -/* - * Like find_get_pages, but collecting swap entries as well as pages. - */ -static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping, - pgoff_t start, unsigned int nr_pages, - struct page **pages, pgoff_t *indices) -{ - void **slot; - unsigned int ret = 0; - struct radix_tree_iter iter; - - if (!nr_pages) - return 0; - - rcu_read_lock(); -restart: - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { - struct page *page; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) - continue; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) - goto restart; - /* - * Otherwise, we must be storing a swap entry - * here as an exceptional entry: so return it - * without attempting to raise page count. - */ - goto export; - } - if (!page_cache_get_speculative(page)) - goto repeat; - - /* Has the page moved? */ - if (unlikely(page != *slot)) { - page_cache_release(page); - goto repeat; - } -export: - indices[ret] = iter.index; - pages[ret] = page; - if (++ret == nr_pages) - break; - } - rcu_read_unlock(); - return ret; -} - /* * Remove swap entry from radix tree, free the swap and its page cache. */ @@ -395,21 +345,6 @@ static int shmem_free_swap(struct address_space *mapping, return 0; } -/* - * Pagevec may contain swap entries, so shuffle up pages before releasing. - */ -static void shmem_deswap_pagevec(struct pagevec *pvec) -{ - int i, j; - - for (i = 0, j = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - if (!radix_tree_exceptional_entry(page)) - pvec->pages[j++] = page; - } - pvec->nr = j; -} - /* * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. */ @@ -428,12 +363,12 @@ void shmem_unlock_mapping(struct address_space *mapping) * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it * has finished, if it hits a row of PAGEVEC_SIZE swap entries. */ - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - PAGEVEC_SIZE, pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + PAGEVEC_SIZE, pvec.pages, indices); if (!pvec.nr) break; index = indices[pvec.nr - 1] + 1; - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); check_move_unevictable_pages(pvec.pages, pvec.nr); pagevec_release(&pvec); cond_resched(); @@ -465,9 +400,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, pagevec_init(&pvec, 0); index = start; while (index < end) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.nr = find_get_entries(mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + pvec.pages, indices); if (!pvec.nr) break; mem_cgroup_uncharge_start(); @@ -496,7 +431,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -534,9 +469,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index = start; for ( ; ; ) { cond_resched(); - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + + pvec.nr = find_get_entries(mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), - pvec.pages, indices); + pvec.pages, indices); if (!pvec.nr) { if (index == start || unfalloc) break; @@ -544,7 +480,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, continue; } if ((index == start || unfalloc) && indices[0] >= end) { - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); break; } @@ -573,7 +509,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } unlock_page(page); } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -1079,7 +1015,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, return -EFBIG; repeat: swap.val = 0; - page = find_lock_page(mapping, index); + page = find_lock_entry(mapping, index); if (radix_tree_exceptional_entry(page)) { swap = radix_to_swp_entry(page); page = NULL; @@ -1416,6 +1352,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode return inode; } +bool shmem_mapping(struct address_space *mapping) +{ + return mapping->backing_dev_info == &shmem_backing_dev_info; +} + #ifdef CONFIG_TMPFS static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; @@ -1728,7 +1669,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, pagevec_init(&pvec, 0); pvec.nr = 1; /* start small: we may be there already */ while (!done) { - pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + pvec.nr = find_get_entries(mapping, index, pvec.nr, pvec.pages, indices); if (!pvec.nr) { if (whence == SEEK_DATA) @@ -1755,7 +1696,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, break; } } - shmem_deswap_pagevec(&pvec); + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); pvec.nr = PAGEVEC_SIZE; cond_resched(); diff --git a/mm/swap.c b/mm/swap.c index 0092097b3f4c..c8048d71c642 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -947,6 +947,57 @@ void __pagevec_lru_add(struct pagevec *pvec) } EXPORT_SYMBOL(__pagevec_lru_add); +/** + * pagevec_lookup_entries - gang pagecache lookup + * @pvec: Where the resulting entries are placed + * @mapping: The address_space to search + * @start: The starting entry index + * @nr_entries: The maximum number of entries + * @indices: The cache indices corresponding to the entries in @pvec + * + * pagevec_lookup_entries() will search for and return a group of up + * to @nr_entries pages and shadow entries in the mapping. All + * entries are placed in @pvec. pagevec_lookup_entries() takes a + * reference against actual pages in @pvec. + * + * The search returns a group of mapping-contiguous entries with + * ascending indexes. There may be holes in the indices due to + * not-present entries. + * + * pagevec_lookup_entries() returns the number of entries which were + * found. + */ +unsigned pagevec_lookup_entries(struct pagevec *pvec, + struct address_space *mapping, + pgoff_t start, unsigned nr_pages, + pgoff_t *indices) +{ + pvec->nr = find_get_entries(mapping, start, nr_pages, + pvec->pages, indices); + return pagevec_count(pvec); +} + +/** + * pagevec_remove_exceptionals - pagevec exceptionals pruning + * @pvec: The pagevec to prune + * + * pagevec_lookup_entries() fills both pages and exceptional radix + * tree entries into the pagevec. This function prunes all + * exceptionals from @pvec without leaving holes, so that it can be + * passed on to page-only pagevec operations. + */ +void pagevec_remove_exceptionals(struct pagevec *pvec) +{ + int i, j; + + for (i = 0, j = 0; i < pagevec_count(pvec); i++) { + struct page *page = pvec->pages[i]; + if (!radix_tree_exceptional_entry(page)) + pvec->pages[j++] = page; + } + pvec->nr = j; +} + /** * pagevec_lookup - gang pagecache lookup * @pvec: Where the resulting pages are placed diff --git a/mm/truncate.c b/mm/truncate.c index 353b683afd6e..2e84fe59190b 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -22,6 +22,22 @@ #include #include "internal.h" +static void clear_exceptional_entry(struct address_space *mapping, + pgoff_t index, void *entry) +{ + /* Handled by shmem itself */ + if (shmem_mapping(mapping)) + return; + + spin_lock_irq(&mapping->tree_lock); + /* + * Regular page slots are stabilized by the page lock even + * without the tree itself locked. These unlocked entries + * need verification under the tree lock. + */ + radix_tree_delete_item(&mapping->page_tree, index, entry); + spin_unlock_irq(&mapping->tree_lock); +} /** * do_invalidatepage - invalidate part or all of a page @@ -208,6 +224,7 @@ void truncate_inode_pages_range(struct address_space *mapping, unsigned int partial_start; /* inclusive */ unsigned int partial_end; /* exclusive */ struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; @@ -238,17 +255,23 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_init(&pvec, 0); index = start; - while (index < end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE))) { + while (index < end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index >= end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -259,6 +282,7 @@ void truncate_inode_pages_range(struct address_space *mapping, truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -307,14 +331,16 @@ void truncate_inode_pages_range(struct address_space *mapping, index = start; for ( ; ; ) { cond_resched(); - if (!pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE))) { + if (!pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { if (index == start) break; index = start; continue; } - if (index == start && pvec.pages[0]->index >= end) { + if (index == start && indices[0] >= end) { + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); break; } @@ -323,16 +349,22 @@ void truncate_inode_pages_range(struct address_space *mapping, struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index >= end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + lock_page(page); WARN_ON(page->index != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; @@ -375,6 +407,7 @@ EXPORT_SYMBOL(truncate_inode_pages); unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index = start; unsigned long ret; @@ -390,17 +423,23 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, */ pagevec_init(&pvec, 0); - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + if (!trylock_page(page)) continue; WARN_ON(page->index != index); @@ -414,6 +453,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, deactivate_page(page); count += ret; } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); @@ -481,6 +521,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page) int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { + pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index; int i; @@ -491,17 +532,23 @@ int invalidate_inode_pages2_range(struct address_space *mapping, cleancache_invalidate_inode(mapping); pagevec_init(&pvec, 0); index = start; - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, + indices)) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ - index = page->index; + index = indices[i]; if (index > end) break; + if (radix_tree_exceptional_entry(page)) { + clear_exceptional_entry(mapping, index, page); + continue; + } + lock_page(page); WARN_ON(page->index != index); if (page->mapping != mapping) { @@ -539,6 +586,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, ret = ret2; unlock_page(page); } + pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); -- cgit From 91b0abe36a7b2b3b02d7500925a5f8455334f0e5 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 3 Apr 2014 14:47:49 -0700 Subject: mm + fs: store shadow entries in page cache Reclaim will be leaving shadow entries in the page cache radix tree upon evicting the real page. As those pages are found from the LRU, an iput() can lead to the inode being freed concurrently. At this point, reclaim must no longer install shadow pages because the inode freeing code needs to ensure the page tree is really empty. Add an address_space flag, AS_EXITING, that the inode freeing code sets under the tree lock before doing the final truncate. Reclaim will check for this flag before installing shadow pages. Signed-off-by: Johannes Weiner Reviewed-by: Rik van Riel Reviewed-by: Minchan Kim Cc: Andrea Arcangeli Cc: Bob Liu Cc: Christoph Hellwig Cc: Dave Chinner Cc: Greg Thelen Cc: Hugh Dickins Cc: Jan Kara Cc: KOSAKI Motohiro Cc: Luigi Semenzato Cc: Mel Gorman Cc: Metin Doslu Cc: Michel Lespinasse Cc: Ozgun Erdogan Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Ryan Mallon Cc: Tejun Heo Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/porting | 6 +-- drivers/staging/lustre/lustre/llite/llite_lib.c | 2 +- fs/9p/vfs_inode.c | 2 +- fs/affs/inode.c | 2 +- fs/afs/inode.c | 2 +- fs/bfs/inode.c | 2 +- fs/block_dev.c | 4 +- fs/btrfs/inode.c | 2 +- fs/cifs/cifsfs.c | 2 +- fs/coda/inode.c | 2 +- fs/ecryptfs/super.c | 2 +- fs/exofs/inode.c | 2 +- fs/ext2/inode.c | 2 +- fs/ext3/inode.c | 2 +- fs/ext4/inode.c | 4 +- fs/f2fs/inode.c | 2 +- fs/fat/inode.c | 2 +- fs/freevxfs/vxfs_inode.c | 2 +- fs/fuse/inode.c | 2 +- fs/gfs2/super.c | 2 +- fs/hfs/inode.c | 2 +- fs/hfsplus/super.c | 2 +- fs/hostfs/hostfs_kern.c | 2 +- fs/hpfs/inode.c | 2 +- fs/inode.c | 4 +- fs/jffs2/fs.c | 2 +- fs/jfs/inode.c | 4 +- fs/kernfs/inode.c | 2 +- fs/logfs/readwrite.c | 2 +- fs/minix/inode.c | 2 +- fs/ncpfs/inode.c | 2 +- fs/nfs/inode.c | 2 +- fs/nfs/nfs4super.c | 2 +- fs/nilfs2/inode.c | 6 +-- fs/ntfs/inode.c | 2 +- fs/ocfs2/inode.c | 4 +- fs/omfs/inode.c | 2 +- fs/proc/inode.c | 2 +- fs/reiserfs/inode.c | 2 +- fs/sysv/inode.c | 2 +- fs/ubifs/super.c | 2 +- fs/udf/inode.c | 4 +- fs/ufs/inode.c | 2 +- fs/xfs/xfs_super.c | 2 +- include/linux/fs.h | 1 + include/linux/mm.h | 1 + include/linux/pagemap.h | 13 +++++- mm/filemap.c | 33 ++++++++++++--- mm/truncate.c | 54 +++++++++++++++++++++++-- mm/vmscan.c | 2 +- 50 files changed, 147 insertions(+), 65 deletions(-) (limited to 'mm/filemap.c') diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index fe2b7ae6f962..0f3a1390bf00 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -295,9 +295,9 @@ in the beginning of ->setattr unconditionally. ->clear_inode() and ->delete_inode() are gone; ->evict_inode() should be used instead. It gets called whenever the inode is evicted, whether it has remaining links or not. Caller does *not* evict the pagecache or inode-associated -metadata buffers; getting rid of those is responsibility of method, as it had -been for ->delete_inode(). Caller makes sure async writeback cannot be running -for the inode while (or after) ->evict_inode() is called. +metadata buffers; the method has to use truncate_inode_pages_final() to get rid +of those. Caller makes sure async writeback cannot be running for the inode while +(or after) ->evict_inode() is called. ->drop_inode() returns int now; it's called on final iput() with inode->i_lock held and it returns true if filesystems wants the inode to be diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c index 26003d3c1be7..7c4fd97a7fa0 100644 --- a/drivers/staging/lustre/lustre/llite/llite_lib.c +++ b/drivers/staging/lustre/lustre/llite/llite_lib.c @@ -1877,7 +1877,7 @@ void ll_delete_inode(struct inode *inode) cl_sync_file_range(inode, 0, OBD_OBJECT_EOF, CL_FSYNC_DISCARD, 1); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); /* Workaround for LU-118 */ if (inode->i_data.nrpages) { diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index bb7991c7e5c7..53161ec058a7 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -451,7 +451,7 @@ void v9fs_evict_inode(struct inode *inode) { struct v9fs_inode *v9inode = V9FS_I(inode); - truncate_inode_pages(inode->i_mapping, 0); + truncate_inode_pages_final(inode->i_mapping); clear_inode(inode); filemap_fdatawrite(inode->i_mapping); diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 0e092d08680e..96df91e8c334 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -259,7 +259,7 @@ affs_evict_inode(struct inode *inode) { unsigned long cache_page; pr_debug("AFFS: evict_inode(ino=%lu, nlink=%u)\n", inode->i_ino, inode->i_nlink); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index ce25d755b7aa..294671288449 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -422,7 +422,7 @@ void afs_evict_inode(struct inode *inode) ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); afs_give_up_callback(vnode); diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 8defc6b3f9a2..29aa5cf6639b 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -172,7 +172,7 @@ static void bfs_evict_inode(struct inode *inode) dprintf("ino=%08lx\n", ino); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); clear_inode(inode); diff --git a/fs/block_dev.c b/fs/block_dev.c index e4cba21a627e..ba0d2b05bb78 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -83,7 +83,7 @@ void kill_bdev(struct block_device *bdev) { struct address_space *mapping = bdev->bd_inode->i_mapping; - if (mapping->nrpages == 0) + if (mapping->nrpages == 0 && mapping->nrshadows == 0) return; invalidate_bh_lrus(); @@ -419,7 +419,7 @@ static void bdev_evict_inode(struct inode *inode) { struct block_device *bdev = &BDEV_I(inode)->bdev; struct list_head *p; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); /* is it needed here? */ clear_inode(inode); spin_lock(&bdev_lock); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d3d44486290b..49ec1398879f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4593,7 +4593,7 @@ static void evict_inode_truncate_pages(struct inode *inode) struct rb_node *node; ASSERT(inode->i_state & I_FREEING); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); write_lock(&map_tree->lock); while (!RB_EMPTY_ROOT(&map_tree->map)) { diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index e8ae8323c058..ab8ad2546c3e 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -286,7 +286,7 @@ cifs_destroy_inode(struct inode *inode) static void cifs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); cifs_fscache_release_inode_cookie(inode); } diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 506de34a4ef3..62618ec9356c 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -250,7 +250,7 @@ static void coda_put_super(struct super_block *sb) static void coda_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); coda_cache_clear_inode(inode); } diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index e879cf8ff0b1..afa1b81c3418 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -132,7 +132,7 @@ static int ecryptfs_statfs(struct dentry *dentry, struct kstatfs *buf) */ static void ecryptfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); iput(ecryptfs_inode_to_lower(inode)); } diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index ee4317faccb1..d1c244d67667 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1486,7 +1486,7 @@ void exofs_evict_inode(struct inode *inode) struct ore_io_state *ios; int ret; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); /* TODO: should do better here */ if (inode->i_nlink || is_bad_inode(inode)) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 94ed36849b71..b1d2a4675d42 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -78,7 +78,7 @@ void ext2_evict_inode(struct inode * inode) dquot_drop(inode); } - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (want_delete) { sb_start_intwrite(inode->i_sb); diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 384b6ebb655f..efce2bbfb5e5 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -228,7 +228,7 @@ void ext3_evict_inode (struct inode *inode) log_wait_commit(journal, commit_tid); filemap_write_and_wait(&inode->i_data); } - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); ext3_discard_reservation(inode); rsv = ei->i_block_alloc_info; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 24bfd7ff3049..175c3f933816 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -215,7 +215,7 @@ void ext4_evict_inode(struct inode *inode) jbd2_complete_transaction(journal, commit_tid); filemap_write_and_wait(&inode->i_data); } - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count)); goto no_delete; @@ -226,7 +226,7 @@ void ext4_evict_inode(struct inode *inode) if (ext4_should_order_data(inode)) ext4_begin_ordered_truncate(inode, 0); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); WARN_ON(atomic_read(&EXT4_I(inode)->i_ioend_count)); if (is_bad_inode(inode)) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 4d67ed736dca..28cea76d78c6 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -260,7 +260,7 @@ void f2fs_evict_inode(struct inode *inode) struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); trace_f2fs_evict_inode(inode); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (inode->i_ino == F2FS_NODE_INO(sbi) || inode->i_ino == F2FS_META_INO(sbi)) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 854b578f6695..c68d9f27135e 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -490,7 +490,7 @@ EXPORT_SYMBOL_GPL(fat_build_inode); static void fat_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; fat_truncate_blocks(inode, 0); diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index f47df72cef17..363e3ae25f6b 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -354,7 +354,7 @@ static void vxfs_i_callback(struct rcu_head *head) void vxfs_evict_inode(struct inode *ip) { - truncate_inode_pages(&ip->i_data, 0); + truncate_inode_pages_final(&ip->i_data); clear_inode(ip); call_rcu(&ip->i_rcu, vxfs_i_callback); } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d468643a68b2..9c761b611c54 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -123,7 +123,7 @@ static void fuse_destroy_inode(struct inode *inode) static void fuse_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (inode->i_sb->s_flags & MS_ACTIVE) { struct fuse_conn *fc = get_fuse_conn(inode); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 60f60f6181f3..24410cd9a82a 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1558,7 +1558,7 @@ out_unlock: fs_warn(sdp, "gfs2_evict_inode: %d\n", error); out: /* Case 3 starts here */ - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); gfs2_rs_delete(ip, NULL); gfs2_ordered_del_inode(ip); clear_inode(inode); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 380ab31b5e0f..9e2fecd62f62 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -547,7 +547,7 @@ out: void hfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (HFS_IS_RSRC(inode) && HFS_I(inode)->rsrc_inode) { HFS_I(HFS_I(inode)->rsrc_inode)->rsrc_inode = NULL; diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 80875aa640ef..a6abf87d79d0 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -161,7 +161,7 @@ static int hfsplus_write_inode(struct inode *inode, static void hfsplus_evict_inode(struct inode *inode) { hfs_dbg(INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (HFSPLUS_IS_RSRC(inode)) { HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index fe649d325b1f..9c470fde9878 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -230,7 +230,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb) static void hostfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (HOSTFS_I(inode)->fd != -1) { close_file(&HOSTFS_I(inode)->fd); diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 9edeeb0ea97e..50a427313835 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -304,7 +304,7 @@ void hpfs_write_if_changed(struct inode *inode) void hpfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (!inode->i_nlink) { hpfs_lock(inode->i_sb); diff --git a/fs/inode.c b/fs/inode.c index 4bcdad3c9361..e6905152c39f 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -503,6 +503,7 @@ void clear_inode(struct inode *inode) */ spin_lock_irq(&inode->i_data.tree_lock); BUG_ON(inode->i_data.nrpages); + BUG_ON(inode->i_data.nrshadows); spin_unlock_irq(&inode->i_data.tree_lock); BUG_ON(!list_empty(&inode->i_data.private_list)); BUG_ON(!(inode->i_state & I_FREEING)); @@ -548,8 +549,7 @@ static void evict(struct inode *inode) if (op->evict_inode) { op->evict_inode(inode); } else { - if (inode->i_data.nrpages) - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } if (S_ISBLK(inode->i_mode) && inode->i_bdev) diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index a69e426435dd..a012e16a8bb3 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -242,7 +242,7 @@ void jffs2_evict_inode (struct inode *inode) jffs2_dbg(1, "%s(): ino #%lu mode %o\n", __func__, inode->i_ino, inode->i_mode); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); jffs2_do_clear_inode(c, f); } diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index f4aab719add5..6f8fe72c2a7a 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -154,7 +154,7 @@ void jfs_evict_inode(struct inode *inode) dquot_initialize(inode); if (JFS_IP(inode)->fileset == FILESYSTEM_I) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (test_cflag(COMMIT_Freewmap, inode)) jfs_free_zero_link(inode); @@ -168,7 +168,7 @@ void jfs_evict_inode(struct inode *inode) dquot_free_inode(inode); } } else { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); } clear_inode(inode); dquot_drop(inode); diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index e55126f85bd2..abb0f1f53d93 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -355,7 +355,7 @@ void kernfs_evict_inode(struct inode *inode) { struct kernfs_node *kn = inode->i_private; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); kernfs_put(kn); } diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c index 9a59cbade2fb..48140315f627 100644 --- a/fs/logfs/readwrite.c +++ b/fs/logfs/readwrite.c @@ -2180,7 +2180,7 @@ void logfs_evict_inode(struct inode *inode) do_delete_inode(inode); } } - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); /* Cheaper version of write_inode. All changes are concealed in diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 0332109162a5..03aaeb1a694a 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -26,7 +26,7 @@ static int minix_remount (struct super_block * sb, int * flags, char * data); static void minix_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; minix_truncate(inode); diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 2cf2ebecb55f..ee59d35ff069 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -296,7 +296,7 @@ ncp_iget(struct super_block *sb, struct ncp_entry_info *info) static void ncp_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (S_ISDIR(inode->i_mode)) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 360114ae8b82..c4702baa22b8 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -128,7 +128,7 @@ EXPORT_SYMBOL_GPL(nfs_clear_inode); void nfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); nfs_clear_inode(inode); } diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 808f29574412..6f340f02f2ba 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -90,7 +90,7 @@ static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc) */ static void nfs4_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); pnfs_return_layout(inode); pnfs_destroy_layout(NFS_I(inode)); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 7e350c562e0e..b9c5726120e3 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -783,16 +783,14 @@ void nilfs_evict_inode(struct inode *inode) int ret; if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { - if (inode->i_data.nrpages) - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); nilfs_clear_inode(inode); return; } nilfs_transaction_begin(sb, &ti, 0); /* never fails */ - if (inode->i_data.nrpages) - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index ffb9b3675736..9d8153ebacfb 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2259,7 +2259,7 @@ void ntfs_evict_big_inode(struct inode *vi) { ntfs_inode *ni = NTFS_I(vi); - truncate_inode_pages(&vi->i_data, 0); + truncate_inode_pages_final(&vi->i_data); clear_inode(vi); #ifdef NTFS_RW diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index d437f3ba90b0..437de7f768c6 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -964,7 +964,7 @@ static void ocfs2_cleanup_delete_inode(struct inode *inode, (unsigned long long)OCFS2_I(inode)->ip_blkno, sync_data); if (sync_data) filemap_write_and_wait(inode->i_mapping); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); } static void ocfs2_delete_inode(struct inode *inode) @@ -1181,7 +1181,7 @@ void ocfs2_evict_inode(struct inode *inode) (OCFS2_I(inode)->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)) { ocfs2_delete_inode(inode); } else { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); } ocfs2_clear_inode(inode); } diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index d8b0afde2179..ec58c7659183 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -183,7 +183,7 @@ int omfs_sync_inode(struct inode *inode) */ static void omfs_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (inode->i_nlink) diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 124fc43c7090..8f20e3404fd2 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -35,7 +35,7 @@ static void proc_evict_inode(struct inode *inode) const struct proc_ns_operations *ns_ops; void *ns; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); /* Stop tracking associated processes */ diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index ad62bdbb451e..bc8b8009897d 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -35,7 +35,7 @@ void reiserfs_evict_inode(struct inode *inode) if (!inode->i_nlink && !is_bad_inode(inode)) dquot_initialize(inode); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (inode->i_nlink) goto no_delete; diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index c327d4ee1235..5625ca920f5e 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -295,7 +295,7 @@ int sysv_sync_inode(struct inode *inode) static void sysv_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (!inode->i_nlink) { inode->i_size = 0; sysv_truncate(inode); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 5ded8490c0c6..48f943f7f5d5 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -351,7 +351,7 @@ static void ubifs_evict_inode(struct inode *inode) dbg_gen("inode %lu, mode %#x", inode->i_ino, (int)inode->i_mode); ubifs_assert(!atomic_read(&inode->i_count)); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (inode->i_nlink) goto done; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 982ce05c87ed..5d643706212f 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -146,8 +146,8 @@ void udf_evict_inode(struct inode *inode) want_delete = 1; udf_setsize(inode, 0); udf_update_inode(inode, IS_SYNC(inode)); - } else - truncate_inode_pages(&inode->i_data, 0); + } + truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); clear_inode(inode); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index c8ca96086784..61e8a9b021dd 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -885,7 +885,7 @@ void ufs_evict_inode(struct inode * inode) if (!inode->i_nlink && !is_bad_inode(inode)) want_delete = 1; - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); if (want_delete) { loff_t old_i_size; /*UFS_I(inode)->i_dtime = CURRENT_TIME;*/ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index d971f4932b5d..0ef599218991 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -996,7 +996,7 @@ xfs_fs_evict_inode( trace_xfs_evict_inode(ip); - truncate_inode_pages(&inode->i_data, 0); + truncate_inode_pages_final(&inode->i_data); clear_inode(inode); XFS_STATS_INC(vn_rele); XFS_STATS_INC(vn_remove); diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e765d28841b..3ca9420f627e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -419,6 +419,7 @@ struct address_space { struct mutex i_mmap_mutex; /* protect tree, count, list */ /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ + unsigned long nrshadows; /* number of shadow entries */ pgoff_t writeback_index;/* writeback starts here */ const struct address_space_operations *a_ops; /* methods */ unsigned long flags; /* error bits/gfp mask */ diff --git a/include/linux/mm.h b/include/linux/mm.h index b1331aff769c..58d6ddba5db3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1834,6 +1834,7 @@ vm_unmapped_area(struct vm_unmapped_area_info *info) extern void truncate_inode_pages(struct address_space *, loff_t); extern void truncate_inode_pages_range(struct address_space *, loff_t lstart, loff_t lend); +extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern int filemap_fault(struct vm_area_struct *, struct vm_fault *); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 493bfd85214e..ff43253f568a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -25,6 +25,7 @@ enum mapping_flags { AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */ AS_UNEVICTABLE = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */ AS_BALLOON_MAP = __GFP_BITS_SHIFT + 4, /* balloon page special map */ + AS_EXITING = __GFP_BITS_SHIFT + 5, /* final truncate in progress */ }; static inline void mapping_set_error(struct address_space *mapping, int error) @@ -69,6 +70,16 @@ static inline int mapping_balloon(struct address_space *mapping) return mapping && test_bit(AS_BALLOON_MAP, &mapping->flags); } +static inline void mapping_set_exiting(struct address_space *mapping) +{ + set_bit(AS_EXITING, &mapping->flags); +} + +static inline int mapping_exiting(struct address_space *mapping) +{ + return test_bit(AS_EXITING, &mapping->flags); +} + static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return (__force gfp_t)mapping->flags & __GFP_BITS_MASK; @@ -547,7 +558,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void delete_from_page_cache(struct page *page); -extern void __delete_from_page_cache(struct page *page); +extern void __delete_from_page_cache(struct page *page, void *shadow); int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask); /* diff --git a/mm/filemap.c b/mm/filemap.c index efc63876477f..05c44aa44188 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -107,12 +107,33 @@ * ->tasklist_lock (memory_failure, collect_procs_ao) */ +static void page_cache_tree_delete(struct address_space *mapping, + struct page *page, void *shadow) +{ + if (shadow) { + void **slot; + + slot = radix_tree_lookup_slot(&mapping->page_tree, page->index); + radix_tree_replace_slot(slot, shadow); + mapping->nrshadows++; + /* + * Make sure the nrshadows update is committed before + * the nrpages update so that final truncate racing + * with reclaim does not see both counters 0 at the + * same time and miss a shadow entry. + */ + smp_wmb(); + } else + radix_tree_delete(&mapping->page_tree, page->index); + mapping->nrpages--; +} + /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the mapping's tree_lock. */ -void __delete_from_page_cache(struct page *page) +void __delete_from_page_cache(struct page *page, void *shadow) { struct address_space *mapping = page->mapping; @@ -127,10 +148,11 @@ void __delete_from_page_cache(struct page *page) else cleancache_invalidate_page(mapping, page); - radix_tree_delete(&mapping->page_tree, page->index); + page_cache_tree_delete(mapping, page, shadow); + page->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ - mapping->nrpages--; + __dec_zone_page_state(page, NR_FILE_PAGES); if (PageSwapBacked(page)) __dec_zone_page_state(page, NR_SHMEM); @@ -166,7 +188,7 @@ void delete_from_page_cache(struct page *page) freepage = mapping->a_ops->freepage; spin_lock_irq(&mapping->tree_lock); - __delete_from_page_cache(page); + __delete_from_page_cache(page, NULL); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); @@ -426,7 +448,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) new->index = offset; spin_lock_irq(&mapping->tree_lock); - __delete_from_page_cache(old); + __delete_from_page_cache(old, NULL); error = radix_tree_insert(&mapping->page_tree, offset, new); BUG_ON(error); mapping->nrpages++; @@ -460,6 +482,7 @@ static int page_cache_tree_insert(struct address_space *mapping, if (!radix_tree_exceptional_entry(p)) return -EEXIST; radix_tree_replace_slot(slot, page); + mapping->nrshadows--; mapping->nrpages++; return 0; } diff --git a/mm/truncate.c b/mm/truncate.c index 2e84fe59190b..0db9258319f0 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -35,7 +35,8 @@ static void clear_exceptional_entry(struct address_space *mapping, * without the tree itself locked. These unlocked entries * need verification under the tree lock. */ - radix_tree_delete_item(&mapping->page_tree, index, entry); + if (radix_tree_delete_item(&mapping->page_tree, index, entry) == entry) + mapping->nrshadows--; spin_unlock_irq(&mapping->tree_lock); } @@ -229,7 +230,7 @@ void truncate_inode_pages_range(struct address_space *mapping, int i; cleancache_invalidate_inode(mapping); - if (mapping->nrpages == 0) + if (mapping->nrpages == 0 && mapping->nrshadows == 0) return; /* Offsets within partial pages */ @@ -391,6 +392,53 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) } EXPORT_SYMBOL(truncate_inode_pages); +/** + * truncate_inode_pages_final - truncate *all* pages before inode dies + * @mapping: mapping to truncate + * + * Called under (and serialized by) inode->i_mutex. + * + * Filesystems have to use this in the .evict_inode path to inform the + * VM that this is the final truncate and the inode is going away. + */ +void truncate_inode_pages_final(struct address_space *mapping) +{ + unsigned long nrshadows; + unsigned long nrpages; + + /* + * Page reclaim can not participate in regular inode lifetime + * management (can't call iput()) and thus can race with the + * inode teardown. Tell it when the address space is exiting, + * so that it does not install eviction information after the + * final truncate has begun. + */ + mapping_set_exiting(mapping); + + /* + * When reclaim installs eviction entries, it increases + * nrshadows first, then decreases nrpages. Make sure we see + * this in the right order or we might miss an entry. + */ + nrpages = mapping->nrpages; + smp_rmb(); + nrshadows = mapping->nrshadows; + + if (nrpages || nrshadows) { + /* + * As truncation uses a lockless tree lookup, cycle + * the tree lock to make sure any ongoing tree + * modification that does not see AS_EXITING is + * completed before starting the final truncate. + */ + spin_lock_irq(&mapping->tree_lock); + spin_unlock_irq(&mapping->tree_lock); + + truncate_inode_pages(mapping, 0); + } +} +EXPORT_SYMBOL(truncate_inode_pages_final); + /** * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode * @mapping: the address_space which holds the pages to invalidate @@ -484,7 +532,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) goto failed; BUG_ON(page_has_private(page)); - __delete_from_page_cache(page); + __delete_from_page_cache(page, NULL); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); diff --git a/mm/vmscan.c b/mm/vmscan.c index c53d1a54964c..2a0bb8fdb259 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -572,7 +572,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) freepage = mapping->a_ops->freepage; - __delete_from_page_cache(page); + __delete_from_page_cache(page, NULL); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); -- cgit From a528910e12ec7ee203095eb1711468a66b9b60b0 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 3 Apr 2014 14:47:51 -0700 Subject: mm: thrash detection-based file cache sizing The VM maintains cached filesystem pages on two types of lists. One list holds the pages recently faulted into the cache, the other list holds pages that have been referenced repeatedly on that first list. The idea is to prefer reclaiming young pages over those that have shown to benefit from caching in the past. We call the recently usedbut ultimately was not significantly better than a FIFO policy and still thrashed cache based on eviction speed, rather than actual demand for cache. This patch solves one half of the problem by decoupling the ability to detect working set changes from the inactive list size. By maintaining a history of recently evicted file pages it can detect frequently used pages with an arbitrarily small inactive list size, and subsequently apply pressure on the active list based on actual demand for cache, not just overall eviction speed. Every zone maintains a counter that tracks inactive list aging speed. When a page is evicted, a snapshot of this counter is stored in the now-empty page cache radix tree slot. On refault, the minimum access distance of the page can be assessed, to evaluate whether the page should be part of the active list or not. This fixes the VM's blindness towards working set changes in excess of the inactive list. And it's the foundation to further improve the protection ability and reduce the minimum inactive list size of 50%. Signed-off-by: Johannes Weiner Reviewed-by: Rik van Riel Reviewed-by: Minchan Kim Reviewed-by: Bob Liu Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: Dave Chinner Cc: Greg Thelen Cc: Hugh Dickins Cc: Jan Kara Cc: KOSAKI Motohiro Cc: Luigi Semenzato Cc: Mel Gorman Cc: Metin Doslu Cc: Michel Lespinasse Cc: Ozgun Erdogan Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Ryan Mallon Cc: Tejun Heo Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 + include/linux/swap.h | 5 + mm/Makefile | 2 +- mm/filemap.c | 61 ++++++++---- mm/swap.c | 2 + mm/vmscan.c | 24 ++++- mm/vmstat.c | 2 + mm/workingset.c | 253 +++++++++++++++++++++++++++++++++++++++++++++++++ 8 files changed, 331 insertions(+), 23 deletions(-) create mode 100644 mm/workingset.c (limited to 'mm/filemap.c') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9b61b9bf81ac..f25db1d74a21 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -142,6 +142,8 @@ enum zone_stat_item { NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ #endif + WORKINGSET_REFAULT, + WORKINGSET_ACTIVATE, NR_ANON_TRANSPARENT_HUGEPAGES, NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; @@ -392,6 +394,9 @@ struct zone { spinlock_t lru_lock; struct lruvec lruvec; + /* Evictions & activations on the inactive file list */ + atomic_long_t inactive_age; + unsigned long pages_scanned; /* since last reclaim */ unsigned long flags; /* zone flags, see below */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 46ba0c6c219f..b83cf61403ed 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -260,6 +260,11 @@ struct swap_list_t { int next; /* swapfile to be used next */ }; +/* linux/mm/workingset.c */ +void *workingset_eviction(struct address_space *mapping, struct page *page); +bool workingset_refault(void *shadow); +void workingset_activation(struct page *page); + /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; diff --git a/mm/Makefile b/mm/Makefile index 310c90a09264..cdd741519ee0 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -17,7 +17,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o balloon_compaction.o \ - interval_tree.o list_lru.o $(mmu-y) + interval_tree.o list_lru.o workingset.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/filemap.c b/mm/filemap.c index 05c44aa44188..a603c4d7d3c9 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -469,7 +469,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) EXPORT_SYMBOL_GPL(replace_page_cache_page); static int page_cache_tree_insert(struct address_space *mapping, - struct page *page) + struct page *page, void **shadowp) { void **slot; int error; @@ -484,6 +484,8 @@ static int page_cache_tree_insert(struct address_space *mapping, radix_tree_replace_slot(slot, page); mapping->nrshadows--; mapping->nrpages++; + if (shadowp) + *shadowp = p; return 0; } error = radix_tree_insert(&mapping->page_tree, page->index, page); @@ -492,18 +494,10 @@ static int page_cache_tree_insert(struct address_space *mapping, return error; } -/** - * add_to_page_cache_locked - add a locked page to the pagecache - * @page: page to add - * @mapping: the page's address_space - * @offset: page index - * @gfp_mask: page allocation mode - * - * This function is used to add a page to the pagecache. It must be locked. - * This function does not add the page to the LRU. The caller must do that. - */ -int add_to_page_cache_locked(struct page *page, struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask) +static int __add_to_page_cache_locked(struct page *page, + struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask, + void **shadowp) { int error; @@ -526,7 +520,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, page->index = offset; spin_lock_irq(&mapping->tree_lock); - error = page_cache_tree_insert(mapping, page); + error = page_cache_tree_insert(mapping, page, shadowp); radix_tree_preload_end(); if (unlikely(error)) goto err_insert; @@ -542,16 +536,49 @@ err_insert: page_cache_release(page); return error; } + +/** + * add_to_page_cache_locked - add a locked page to the pagecache + * @page: page to add + * @mapping: the page's address_space + * @offset: page index + * @gfp_mask: page allocation mode + * + * This function is used to add a page to the pagecache. It must be locked. + * This function does not add the page to the LRU. The caller must do that. + */ +int add_to_page_cache_locked(struct page *page, struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask) +{ + return __add_to_page_cache_locked(page, mapping, offset, + gfp_mask, NULL); +} EXPORT_SYMBOL(add_to_page_cache_locked); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { + void *shadow = NULL; int ret; - ret = add_to_page_cache(page, mapping, offset, gfp_mask); - if (ret == 0) - lru_cache_add_file(page); + __set_page_locked(page); + ret = __add_to_page_cache_locked(page, mapping, offset, + gfp_mask, &shadow); + if (unlikely(ret)) + __clear_page_locked(page); + else { + /* + * The page might have been evicted from cache only + * recently, in which case it should be activated like + * any other repeatedly accessed page. + */ + if (shadow && workingset_refault(shadow)) { + SetPageActive(page); + workingset_activation(page); + } else + ClearPageActive(page); + lru_cache_add(page); + } return ret; } EXPORT_SYMBOL_GPL(add_to_page_cache_lru); diff --git a/mm/swap.c b/mm/swap.c index c8048d71c642..9ce43ba4498b 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -574,6 +574,8 @@ void mark_page_accessed(struct page *page) else __lru_cache_activate_page(page); ClearPageReferenced(page); + if (page_is_file_cache(page)) + workingset_activation(page); } else if (!PageReferenced(page)) { SetPageReferenced(page); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 2a0bb8fdb259..1f56a80a7c41 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -523,7 +523,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * Same as remove_mapping, but if the page is removed from the mapping, it * gets returned with a refcount of 0. */ -static int __remove_mapping(struct address_space *mapping, struct page *page) +static int __remove_mapping(struct address_space *mapping, struct page *page, + bool reclaimed) { BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); @@ -569,10 +570,23 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) swapcache_free(swap, page); } else { void (*freepage)(struct page *); + void *shadow = NULL; freepage = mapping->a_ops->freepage; - - __delete_from_page_cache(page, NULL); + /* + * Remember a shadow entry for reclaimed file cache in + * order to detect refaults, thus thrashing, later on. + * + * But don't store shadows in an address space that is + * already exiting. This is not just an optizimation, + * inode reclaim needs to empty out the radix tree or + * the nodes are lost. Don't plant shadows behind its + * back. + */ + if (reclaimed && page_is_file_cache(page) && + !mapping_exiting(mapping)) + shadow = workingset_eviction(mapping, page); + __delete_from_page_cache(page, shadow); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); @@ -595,7 +609,7 @@ cannot_free: */ int remove_mapping(struct address_space *mapping, struct page *page) { - if (__remove_mapping(mapping, page)) { + if (__remove_mapping(mapping, page, false)) { /* * Unfreezing the refcount with 1 rather than 2 effectively * drops the pagecache ref for us without requiring another @@ -1065,7 +1079,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, } } - if (!mapping || !__remove_mapping(mapping, page)) + if (!mapping || !__remove_mapping(mapping, page, true)) goto keep_locked; /* diff --git a/mm/vmstat.c b/mm/vmstat.c index def5dd2fbe61..843125a0e255 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -770,6 +770,8 @@ const char * const vmstat_text[] = { "numa_local", "numa_other", #endif + "workingset_refault", + "workingset_activate", "nr_anon_transparent_hugepages", "nr_free_cma", "nr_dirty_threshold", diff --git a/mm/workingset.c b/mm/workingset.c new file mode 100644 index 000000000000..8a6c7cff4923 --- /dev/null +++ b/mm/workingset.c @@ -0,0 +1,253 @@ +/* + * Workingset detection + * + * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Double CLOCK lists + * + * Per zone, two clock lists are maintained for file pages: the + * inactive and the active list. Freshly faulted pages start out at + * the head of the inactive list and page reclaim scans pages from the + * tail. Pages that are accessed multiple times on the inactive list + * are promoted to the active list, to protect them from reclaim, + * whereas active pages are demoted to the inactive list when the + * active list grows too big. + * + * fault ------------------------+ + * | + * +--------------+ | +-------------+ + * reclaim <- | inactive | <-+-- demotion | active | <--+ + * +--------------+ +-------------+ | + * | | + * +-------------- promotion ------------------+ + * + * + * Access frequency and refault distance + * + * A workload is thrashing when its pages are frequently used but they + * are evicted from the inactive list every time before another access + * would have promoted them to the active list. + * + * In cases where the average access distance between thrashing pages + * is bigger than the size of memory there is nothing that can be + * done - the thrashing set could never fit into memory under any + * circumstance. + * + * However, the average access distance could be bigger than the + * inactive list, yet smaller than the size of memory. In this case, + * the set could fit into memory if it weren't for the currently + * active pages - which may be used more, hopefully less frequently: + * + * +-memory available to cache-+ + * | | + * +-inactive------+-active----+ + * a b | c d e f g h i | J K L M N | + * +---------------+-----------+ + * + * It is prohibitively expensive to accurately track access frequency + * of pages. But a reasonable approximation can be made to measure + * thrashing on the inactive list, after which refaulting pages can be + * activated optimistically to compete with the existing active pages. + * + * Approximating inactive page access frequency - Observations: + * + * 1. When a page is accessed for the first time, it is added to the + * head of the inactive list, slides every existing inactive page + * towards the tail by one slot, and pushes the current tail page + * out of memory. + * + * 2. When a page is accessed for the second time, it is promoted to + * the active list, shrinking the inactive list by one slot. This + * also slides all inactive pages that were faulted into the cache + * more recently than the activated page towards the tail of the + * inactive list. + * + * Thus: + * + * 1. The sum of evictions and activations between any two points in + * time indicate the minimum number of inactive pages accessed in + * between. + * + * 2. Moving one inactive page N page slots towards the tail of the + * list requires at least N inactive page accesses. + * + * Combining these: + * + * 1. When a page is finally evicted from memory, the number of + * inactive pages accessed while the page was in cache is at least + * the number of page slots on the inactive list. + * + * 2. In addition, measuring the sum of evictions and activations (E) + * at the time of a page's eviction, and comparing it to another + * reading (R) at the time the page faults back into memory tells + * the minimum number of accesses while the page was not cached. + * This is called the refault distance. + * + * Because the first access of the page was the fault and the second + * access the refault, we combine the in-cache distance with the + * out-of-cache distance to get the complete minimum access distance + * of this page: + * + * NR_inactive + (R - E) + * + * And knowing the minimum access distance of a page, we can easily + * tell if the page would be able to stay in cache assuming all page + * slots in the cache were available: + * + * NR_inactive + (R - E) <= NR_inactive + NR_active + * + * which can be further simplified to + * + * (R - E) <= NR_active + * + * Put into words, the refault distance (out-of-cache) can be seen as + * a deficit in inactive list space (in-cache). If the inactive list + * had (R - E) more page slots, the page would not have been evicted + * in between accesses, but activated instead. And on a full system, + * the only thing eating into inactive list space is active pages. + * + * + * Activating refaulting pages + * + * All that is known about the active list is that the pages have been + * accessed more than once in the past. This means that at any given + * time there is actually a good chance that pages on the active list + * are no longer in active use. + * + * So when a refault distance of (R - E) is observed and there are at + * least (R - E) active pages, the refaulting page is activated + * optimistically in the hope that (R - E) active pages are actually + * used less frequently than the refaulting page - or even not used at + * all anymore. + * + * If this is wrong and demotion kicks in, the pages which are truly + * used more frequently will be reactivated while the less frequently + * used once will be evicted from memory. + * + * But if this is right, the stale pages will be pushed out of memory + * and the used pages get to stay in cache. + * + * + * Implementation + * + * For each zone's file LRU lists, a counter for inactive evictions + * and activations is maintained (zone->inactive_age). + * + * On eviction, a snapshot of this counter (along with some bits to + * identify the zone) is stored in the now empty page cache radix tree + * slot of the evicted page. This is called a shadow entry. + * + * On cache misses for which there are shadow entries, an eligible + * refault distance will immediately activate the refaulting page. + */ + +static void *pack_shadow(unsigned long eviction, struct zone *zone) +{ + eviction = (eviction << NODES_SHIFT) | zone_to_nid(zone); + eviction = (eviction << ZONES_SHIFT) | zone_idx(zone); + eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); + + return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); +} + +static void unpack_shadow(void *shadow, + struct zone **zone, + unsigned long *distance) +{ + unsigned long entry = (unsigned long)shadow; + unsigned long eviction; + unsigned long refault; + unsigned long mask; + int zid, nid; + + entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; + zid = entry & ((1UL << ZONES_SHIFT) - 1); + entry >>= ZONES_SHIFT; + nid = entry & ((1UL << NODES_SHIFT) - 1); + entry >>= NODES_SHIFT; + eviction = entry; + + *zone = NODE_DATA(nid)->node_zones + zid; + + refault = atomic_long_read(&(*zone)->inactive_age); + mask = ~0UL >> (NODES_SHIFT + ZONES_SHIFT + + RADIX_TREE_EXCEPTIONAL_SHIFT); + /* + * The unsigned subtraction here gives an accurate distance + * across inactive_age overflows in most cases. + * + * There is a special case: usually, shadow entries have a + * short lifetime and are either refaulted or reclaimed along + * with the inode before they get too old. But it is not + * impossible for the inactive_age to lap a shadow entry in + * the field, which can then can result in a false small + * refault distance, leading to a false activation should this + * old entry actually refault again. However, earlier kernels + * used to deactivate unconditionally with *every* reclaim + * invocation for the longest time, so the occasional + * inappropriate activation leading to pressure on the active + * list is not a problem. + */ + *distance = (refault - eviction) & mask; +} + +/** + * workingset_eviction - note the eviction of a page from memory + * @mapping: address space the page was backing + * @page: the page being evicted + * + * Returns a shadow entry to be stored in @mapping->page_tree in place + * of the evicted @page so that a later refault can be detected. + */ +void *workingset_eviction(struct address_space *mapping, struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long eviction; + + eviction = atomic_long_inc_return(&zone->inactive_age); + return pack_shadow(eviction, zone); +} + +/** + * workingset_refault - evaluate the refault of a previously evicted page + * @shadow: shadow entry of the evicted page + * + * Calculates and evaluates the refault distance of the previously + * evicted page in the context of the zone it was allocated in. + * + * Returns %true if the page should be activated, %false otherwise. + */ +bool workingset_refault(void *shadow) +{ + unsigned long refault_distance; + struct zone *zone; + + unpack_shadow(shadow, &zone, &refault_distance); + inc_zone_state(zone, WORKINGSET_REFAULT); + + if (refault_distance <= zone_page_state(zone, NR_ACTIVE_FILE)) { + inc_zone_state(zone, WORKINGSET_ACTIVATE); + return true; + } + return false; +} + +/** + * workingset_activation - note a page activation + * @page: page that is being activated + */ +void workingset_activation(struct page *page) +{ + atomic_long_inc(&page_zone(page)->inactive_age); +} -- cgit From 449dd6984d0e47643c04c807f609dd56d48d5bcc Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 3 Apr 2014 14:47:56 -0700 Subject: mm: keep page cache radix tree nodes in check Previously, page cache radix tree nodes were freed after reclaim emptied out their page pointers. But now reclaim stores shadow entries in their place, which are only reclaimed when the inodes themselves are reclaimed. This is problematic for bigger files that are still in use after they have a significant amount of their cache reclaimed, without any of those pages actually refaulting. The shadow entries will just sit there and waste memory. In the worst case, the shadow entries will accumulate until the machine runs out of memory. To get this under control, the VM will track radix tree nodes exclusively containing shadow entries on a per-NUMA node list. Per-NUMA rather than global because we expect the radix tree nodes themselves to be allocated node-locally and we want to reduce cross-node references of otherwise independent cache workloads. A simple shrinker will then reclaim these nodes on memory pressure. A few things need to be stored in the radix tree node to implement the shadow node LRU and allow tree deletions coming from the list: 1. There is no index available that would describe the reverse path from the node up to the tree root, which is needed to perform a deletion. To solve this, encode in each node its offset inside the parent. This can be stored in the unused upper bits of the same member that stores the node's height at no extra space cost. 2. The number of shadow entries needs to be counted in addition to the regular entries, to quickly detect when the node is ready to go to the shadow node LRU list. The current entry count is an unsigned int but the maximum number of entries is 64, so a shadow counter can easily be stored in the unused upper bits. 3. Tree modification needs tree lock and tree root, which are located in the address space, so store an address_space backpointer in the node. The parent pointer of the node is in a union with the 2-word rcu_head, so the backpointer comes at no extra cost as well. 4. The node needs to be linked to an LRU list, which requires a list head inside the node. This does increase the size of the node, but it does not change the number of objects that fit into a slab page. [akpm@linux-foundation.org: export the right function] Signed-off-by: Johannes Weiner Reviewed-by: Rik van Riel Reviewed-by: Minchan Kim Cc: Andrea Arcangeli Cc: Bob Liu Cc: Christoph Hellwig Cc: Dave Chinner Cc: Greg Thelen Cc: Hugh Dickins Cc: Jan Kara Cc: KOSAKI Motohiro Cc: Luigi Semenzato Cc: Mel Gorman Cc: Metin Doslu Cc: Michel Lespinasse Cc: Ozgun Erdogan Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Ryan Mallon Cc: Tejun Heo Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 8 ++- include/linux/mmzone.h | 1 + include/linux/radix-tree.h | 32 ++++++--- include/linux/swap.h | 31 +++++++++ lib/radix-tree.c | 36 ++++++---- mm/filemap.c | 90 ++++++++++++++++++++----- mm/list_lru.c | 16 ++++- mm/truncate.c | 26 +++++++- mm/vmstat.c | 1 + mm/workingset.c | 161 +++++++++++++++++++++++++++++++++++++++++++++ 10 files changed, 359 insertions(+), 43 deletions(-) (limited to 'mm/filemap.c') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 3ce541753c88..f3434533fbf8 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -13,6 +13,8 @@ /* list_lru_walk_cb has to always return one of those */ enum lru_status { LRU_REMOVED, /* item removed from list */ + LRU_REMOVED_RETRY, /* item removed, but lock has been + dropped and reacquired */ LRU_ROTATE, /* item referenced, give another pass */ LRU_SKIP, /* item cannot be locked, skip */ LRU_RETRY, /* item not freeable. May drop the lock @@ -32,7 +34,11 @@ struct list_lru { }; void list_lru_destroy(struct list_lru *lru); -int list_lru_init(struct list_lru *lru); +int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key); +static inline int list_lru_init(struct list_lru *lru) +{ + return list_lru_init_key(lru, NULL); +} /** * list_lru_add: add an element to the lru list's tail diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f25db1d74a21..fac5509c18f0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -144,6 +144,7 @@ enum zone_stat_item { #endif WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_NODERECLAIM, NR_ANON_TRANSPARENT_HUGEPAGES, NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 13636c40bc42..33170dbd9db4 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -72,21 +72,37 @@ static inline int radix_tree_is_indirect_ptr(void *ptr) #define RADIX_TREE_TAG_LONGS \ ((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG) +#define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) +#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ + RADIX_TREE_MAP_SHIFT)) + +/* Height component in node->path */ +#define RADIX_TREE_HEIGHT_SHIFT (RADIX_TREE_MAX_PATH + 1) +#define RADIX_TREE_HEIGHT_MASK ((1UL << RADIX_TREE_HEIGHT_SHIFT) - 1) + +/* Internally used bits of node->count */ +#define RADIX_TREE_COUNT_SHIFT (RADIX_TREE_MAP_SHIFT + 1) +#define RADIX_TREE_COUNT_MASK ((1UL << RADIX_TREE_COUNT_SHIFT) - 1) + struct radix_tree_node { - unsigned int height; /* Height from the bottom */ + unsigned int path; /* Offset in parent & height from the bottom */ unsigned int count; union { - struct radix_tree_node *parent; /* Used when ascending tree */ - struct rcu_head rcu_head; /* Used when freeing node */ + struct { + /* Used when ascending tree */ + struct radix_tree_node *parent; + /* For tree user */ + void *private_data; + }; + /* Used when freeing node */ + struct rcu_head rcu_head; }; + /* For tree user */ + struct list_head private_list; void __rcu *slots[RADIX_TREE_MAP_SIZE]; unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -#define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) -#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ - RADIX_TREE_MAP_SHIFT)) - /* root tags are stored in gfp_mask, shifted by __GFP_BITS_SHIFT */ struct radix_tree_root { unsigned int height; @@ -251,7 +267,7 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void ***slotp); void *radix_tree_lookup(struct radix_tree_root *, unsigned long); void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); -bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index, +bool __radix_tree_delete_node(struct radix_tree_root *root, struct radix_tree_node *node); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); diff --git a/include/linux/swap.h b/include/linux/swap.h index b83cf61403ed..350711560753 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -264,6 +264,37 @@ struct swap_list_t { void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); void workingset_activation(struct page *page); +extern struct list_lru workingset_shadow_nodes; + +static inline unsigned int workingset_node_pages(struct radix_tree_node *node) +{ + return node->count & RADIX_TREE_COUNT_MASK; +} + +static inline void workingset_node_pages_inc(struct radix_tree_node *node) +{ + node->count++; +} + +static inline void workingset_node_pages_dec(struct radix_tree_node *node) +{ + node->count--; +} + +static inline unsigned int workingset_node_shadows(struct radix_tree_node *node) +{ + return node->count >> RADIX_TREE_COUNT_SHIFT; +} + +static inline void workingset_node_shadows_inc(struct radix_tree_node *node) +{ + node->count += 1U << RADIX_TREE_COUNT_SHIFT; +} + +static inline void workingset_node_shadows_dec(struct radix_tree_node *node) +{ + node->count -= 1U << RADIX_TREE_COUNT_SHIFT; +} /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; diff --git a/lib/radix-tree.c b/lib/radix-tree.c index d60be40c111b..9599aa72d7a0 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -342,7 +342,8 @@ static int radix_tree_extend(struct radix_tree_root *root, unsigned long index) /* Increase the height. */ newheight = root->height+1; - node->height = newheight; + BUG_ON(newheight & ~RADIX_TREE_HEIGHT_MASK); + node->path = newheight; node->count = 1; node->parent = NULL; slot = root->rnode; @@ -400,11 +401,12 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index, /* Have to add a child node. */ if (!(slot = radix_tree_node_alloc(root))) return -ENOMEM; - slot->height = height; + slot->path = height; slot->parent = node; if (node) { rcu_assign_pointer(node->slots[offset], slot); node->count++; + slot->path |= offset << RADIX_TREE_HEIGHT_SHIFT; } else rcu_assign_pointer(root->rnode, ptr_to_indirect(slot)); } @@ -498,7 +500,7 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, } node = indirect_to_ptr(node); - height = node->height; + height = node->path & RADIX_TREE_HEIGHT_MASK; if (index > radix_tree_maxindex(height)) return NULL; @@ -704,7 +706,7 @@ int radix_tree_tag_get(struct radix_tree_root *root, return (index == 0); node = indirect_to_ptr(node); - height = node->height; + height = node->path & RADIX_TREE_HEIGHT_MASK; if (index > radix_tree_maxindex(height)) return 0; @@ -741,7 +743,7 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, { unsigned shift, tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *rnode, *node; - unsigned long index, offset; + unsigned long index, offset, height; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; @@ -772,7 +774,8 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, return NULL; restart: - shift = (rnode->height - 1) * RADIX_TREE_MAP_SHIFT; + height = rnode->path & RADIX_TREE_HEIGHT_MASK; + shift = (height - 1) * RADIX_TREE_MAP_SHIFT; offset = index >> shift; /* Index outside of the tree */ @@ -1142,7 +1145,7 @@ static unsigned long __locate(struct radix_tree_node *slot, void *item, unsigned int shift, height; unsigned long i; - height = slot->height; + height = slot->path & RADIX_TREE_HEIGHT_MASK; shift = (height-1) * RADIX_TREE_MAP_SHIFT; for ( ; height > 1; height--) { @@ -1205,7 +1208,8 @@ unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item) } node = indirect_to_ptr(node); - max_index = radix_tree_maxindex(node->height); + max_index = radix_tree_maxindex(node->path & + RADIX_TREE_HEIGHT_MASK); if (cur_index > max_index) { rcu_read_unlock(); break; @@ -1301,7 +1305,7 @@ static inline void radix_tree_shrink(struct radix_tree_root *root) * * Returns %true if @node was freed, %false otherwise. */ -bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index, +bool __radix_tree_delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; @@ -1320,9 +1324,10 @@ bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index, parent = node->parent; if (parent) { - index >>= RADIX_TREE_MAP_SHIFT; + unsigned int offset; - parent->slots[index & RADIX_TREE_MAP_MASK] = NULL; + offset = node->path >> RADIX_TREE_HEIGHT_SHIFT; + parent->slots[offset] = NULL; parent->count--; } else { root_tag_clear_all(root); @@ -1386,7 +1391,7 @@ void *radix_tree_delete_item(struct radix_tree_root *root, node->slots[offset] = NULL; node->count--; - __radix_tree_delete_node(root, index, node); + __radix_tree_delete_node(root, node); return entry; } @@ -1419,9 +1424,12 @@ int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag) EXPORT_SYMBOL(radix_tree_tagged); static void -radix_tree_node_ctor(void *node) +radix_tree_node_ctor(void *arg) { - memset(node, 0, sizeof(struct radix_tree_node)); + struct radix_tree_node *node = arg; + + memset(node, 0, sizeof(*node)); + INIT_LIST_HEAD(&node->private_list); } static __init unsigned long __maxindex(unsigned int height) diff --git a/mm/filemap.c b/mm/filemap.c index a603c4d7d3c9..d6df3bacb0fb 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -110,11 +110,17 @@ static void page_cache_tree_delete(struct address_space *mapping, struct page *page, void *shadow) { - if (shadow) { - void **slot; + struct radix_tree_node *node; + unsigned long index; + unsigned int offset; + unsigned int tag; + void **slot; - slot = radix_tree_lookup_slot(&mapping->page_tree, page->index); - radix_tree_replace_slot(slot, shadow); + VM_BUG_ON(!PageLocked(page)); + + __radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot); + + if (shadow) { mapping->nrshadows++; /* * Make sure the nrshadows update is committed before @@ -123,9 +129,45 @@ static void page_cache_tree_delete(struct address_space *mapping, * same time and miss a shadow entry. */ smp_wmb(); - } else - radix_tree_delete(&mapping->page_tree, page->index); + } mapping->nrpages--; + + if (!node) { + /* Clear direct pointer tags in root node */ + mapping->page_tree.gfp_mask &= __GFP_BITS_MASK; + radix_tree_replace_slot(slot, shadow); + return; + } + + /* Clear tree tags for the removed page */ + index = page->index; + offset = index & RADIX_TREE_MAP_MASK; + for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { + if (test_bit(offset, node->tags[tag])) + radix_tree_tag_clear(&mapping->page_tree, index, tag); + } + + /* Delete page, swap shadow entry */ + radix_tree_replace_slot(slot, shadow); + workingset_node_pages_dec(node); + if (shadow) + workingset_node_shadows_inc(node); + else + if (__radix_tree_delete_node(&mapping->page_tree, node)) + return; + + /* + * Track node that only contains shadow entries. + * + * Avoid acquiring the list_lru lock if already tracked. The + * list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!workingset_node_pages(node) && + list_empty(&node->private_list)) { + node->private_data = mapping; + list_lru_add(&workingset_shadow_nodes, &node->private_list); + } } /* @@ -471,27 +513,43 @@ EXPORT_SYMBOL_GPL(replace_page_cache_page); static int page_cache_tree_insert(struct address_space *mapping, struct page *page, void **shadowp) { + struct radix_tree_node *node; void **slot; int error; - slot = radix_tree_lookup_slot(&mapping->page_tree, page->index); - if (slot) { + error = __radix_tree_create(&mapping->page_tree, page->index, + &node, &slot); + if (error) + return error; + if (*slot) { void *p; p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); if (!radix_tree_exceptional_entry(p)) return -EEXIST; - radix_tree_replace_slot(slot, page); - mapping->nrshadows--; - mapping->nrpages++; if (shadowp) *shadowp = p; - return 0; + mapping->nrshadows--; + if (node) + workingset_node_shadows_dec(node); } - error = radix_tree_insert(&mapping->page_tree, page->index, page); - if (!error) - mapping->nrpages++; - return error; + radix_tree_replace_slot(slot, page); + mapping->nrpages++; + if (node) { + workingset_node_pages_inc(node); + /* + * Don't track node that contains actual pages. + * + * Avoid acquiring the list_lru lock if already + * untracked. The list_empty() test is safe as + * node->private_list is protected by + * mapping->tree_lock. + */ + if (!list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, + &node->private_list); + } + return 0; } static int __add_to_page_cache_locked(struct page *page, diff --git a/mm/list_lru.c b/mm/list_lru.c index 72f9decb0104..f1a0db194173 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -87,11 +87,20 @@ restart: ret = isolate(item, &nlru->lock, cb_arg); switch (ret) { + case LRU_REMOVED_RETRY: + assert_spin_locked(&nlru->lock); case LRU_REMOVED: if (--nlru->nr_items == 0) node_clear(nid, lru->active_nodes); WARN_ON_ONCE(nlru->nr_items < 0); isolated++; + /* + * If the lru lock has been dropped, our list + * traversal is now invalid and so we have to + * restart from scratch. + */ + if (ret == LRU_REMOVED_RETRY) + goto restart; break; case LRU_ROTATE: list_move_tail(item, &nlru->list); @@ -103,6 +112,7 @@ restart: * The lru lock has been dropped, our list traversal is * now invalid and so we have to restart from scratch. */ + assert_spin_locked(&nlru->lock); goto restart; default: BUG(); @@ -114,7 +124,7 @@ restart: } EXPORT_SYMBOL_GPL(list_lru_walk_node); -int list_lru_init(struct list_lru *lru) +int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key) { int i; size_t size = sizeof(*lru->node) * nr_node_ids; @@ -126,12 +136,14 @@ int list_lru_init(struct list_lru *lru) nodes_clear(lru->active_nodes); for (i = 0; i < nr_node_ids; i++) { spin_lock_init(&lru->node[i].lock); + if (key) + lockdep_set_class(&lru->node[i].lock, key); INIT_LIST_HEAD(&lru->node[i].list); lru->node[i].nr_items = 0; } return 0; } -EXPORT_SYMBOL_GPL(list_lru_init); +EXPORT_SYMBOL_GPL(list_lru_init_key); void list_lru_destroy(struct list_lru *lru) { diff --git a/mm/truncate.c b/mm/truncate.c index 0db9258319f0..e5cc39ab0751 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -25,6 +25,9 @@ static void clear_exceptional_entry(struct address_space *mapping, pgoff_t index, void *entry) { + struct radix_tree_node *node; + void **slot; + /* Handled by shmem itself */ if (shmem_mapping(mapping)) return; @@ -35,8 +38,27 @@ static void clear_exceptional_entry(struct address_space *mapping, * without the tree itself locked. These unlocked entries * need verification under the tree lock. */ - if (radix_tree_delete_item(&mapping->page_tree, index, entry) == entry) - mapping->nrshadows--; + if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot)) + goto unlock; + if (*slot != entry) + goto unlock; + radix_tree_replace_slot(slot, NULL); + mapping->nrshadows--; + if (!node) + goto unlock; + workingset_node_shadows_dec(node); + /* + * Don't track node without shadow entries. + * + * Avoid acquiring the list_lru lock if already untracked. + * The list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!workingset_node_shadows(node) && + !list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, &node->private_list); + __radix_tree_delete_node(&mapping->page_tree, node); +unlock: spin_unlock_irq(&mapping->tree_lock); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 843125a0e255..f3155d51acfd 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -772,6 +772,7 @@ const char * const vmstat_text[] = { #endif "workingset_refault", "workingset_activate", + "workingset_nodereclaim", "nr_anon_transparent_hugepages", "nr_free_cma", "nr_dirty_threshold", diff --git a/mm/workingset.c b/mm/workingset.c index 8a6c7cff4923..f7216fa7da27 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -251,3 +251,164 @@ void workingset_activation(struct page *page) { atomic_long_inc(&page_zone(page)->inactive_age); } + +/* + * Shadow entries reflect the share of the working set that does not + * fit into memory, so their number depends on the access pattern of + * the workload. In most cases, they will refault or get reclaimed + * along with the inode, but a (malicious) workload that streams + * through files with a total size several times that of available + * memory, while preventing the inodes from being reclaimed, can + * create excessive amounts of shadow nodes. To keep a lid on this, + * track shadow nodes and reclaim them when they grow way past the + * point where they would still be useful. + */ + +struct list_lru workingset_shadow_nodes; + +static unsigned long count_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long shadow_nodes; + unsigned long max_nodes; + unsigned long pages; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ + local_irq_disable(); + shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid); + local_irq_enable(); + + pages = node_present_pages(sc->nid); + /* + * Active cache pages are limited to 50% of memory, and shadow + * entries that represent a refault distance bigger than that + * do not have any effect. Limit the number of shadow nodes + * such that shadow entries do not exceed the number of active + * cache pages, assuming a worst-case node population density + * of 1/8th on average. + * + * On 64-bit with 7 radix_tree_nodes per page and 64 slots + * each, this will reclaim shadow entries when they consume + * ~2% of available memory: + * + * PAGE_SIZE / radix_tree_nodes / node_entries / PAGE_SIZE + */ + max_nodes = pages >> (1 + RADIX_TREE_MAP_SHIFT - 3); + + if (shadow_nodes <= max_nodes) + return 0; + + return shadow_nodes - max_nodes; +} + +static enum lru_status shadow_lru_isolate(struct list_head *item, + spinlock_t *lru_lock, + void *arg) +{ + struct address_space *mapping; + struct radix_tree_node *node; + unsigned int i; + int ret; + + /* + * Page cache insertions and deletions synchroneously maintain + * the shadow node LRU under the mapping->tree_lock and the + * lru_lock. Because the page cache tree is emptied before + * the inode can be destroyed, holding the lru_lock pins any + * address_space that has radix tree nodes on the LRU. + * + * We can then safely transition to the mapping->tree_lock to + * pin only the address_space of the particular node we want + * to reclaim, take the node off-LRU, and drop the lru_lock. + */ + + node = container_of(item, struct radix_tree_node, private_list); + mapping = node->private_data; + + /* Coming from the list, invert the lock order */ + if (!spin_trylock(&mapping->tree_lock)) { + spin_unlock(lru_lock); + ret = LRU_RETRY; + goto out; + } + + list_del_init(item); + spin_unlock(lru_lock); + + /* + * The nodes should only contain one or more shadow entries, + * no pages, so we expect to be able to remove them all and + * delete and free the empty node afterwards. + */ + + BUG_ON(!node->count); + BUG_ON(node->count & RADIX_TREE_COUNT_MASK); + + for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { + if (node->slots[i]) { + BUG_ON(!radix_tree_exceptional_entry(node->slots[i])); + node->slots[i] = NULL; + BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT)); + node->count -= 1U << RADIX_TREE_COUNT_SHIFT; + BUG_ON(!mapping->nrshadows); + mapping->nrshadows--; + } + } + BUG_ON(node->count); + inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM); + if (!__radix_tree_delete_node(&mapping->page_tree, node)) + BUG(); + + spin_unlock(&mapping->tree_lock); + ret = LRU_REMOVED_RETRY; +out: + local_irq_enable(); + cond_resched(); + local_irq_disable(); + spin_lock(lru_lock); + return ret; +} + +static unsigned long scan_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long ret; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ + local_irq_disable(); + ret = list_lru_walk_node(&workingset_shadow_nodes, sc->nid, + shadow_lru_isolate, NULL, &sc->nr_to_scan); + local_irq_enable(); + return ret; +} + +static struct shrinker workingset_shadow_shrinker = { + .count_objects = count_shadow_nodes, + .scan_objects = scan_shadow_nodes, + .seeks = DEFAULT_SEEKS, + .flags = SHRINKER_NUMA_AWARE, +}; + +/* + * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe + * mapping->tree_lock. + */ +static struct lock_class_key shadow_nodes_key; + +static int __init workingset_init(void) +{ + int ret; + + ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key); + if (ret) + goto err; + ret = register_shrinker(&workingset_shadow_shrinker); + if (ret) + goto err_list_lru; + return 0; +err_list_lru: + list_lru_destroy(&workingset_shadow_nodes); +err: + return ret; +} +module_init(workingset_init); -- cgit From 67f9fd91f93c582b7de2ab9325b6e179db77e4d5 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Thu, 3 Apr 2014 14:48:18 -0700 Subject: mm: remove read_cache_page_async() This patch removes read_cache_page_async() which wasn't really needed anywhere and simplifies the code around it a bit. read_cache_page_async() is useful when we want to read a page into the cache without waiting for it to complete. This happens when the appropriate callback 'filler' doesn't complete its read operation and releases the page lock immediately, and instead queues a different completion routine to do that. This never actually happened anywhere in the code. read_cache_page_async() had 3 different callers: - read_cache_page() which is the sync version, it would just wait for the requested read to complete using wait_on_page_read(). - JFFS2 would call it from jffs2_gc_fetch_page(), but the filler function it supplied doesn't do any async reads, and would complete before the filler function returns - making it actually a sync read. - CRAMFS would call it using the read_mapping_page_async() wrapper, with a similar story to JFFS2 - the filler function doesn't do anything that reminds async reads and would always complete before the filler function returns. To sum it up, the code in mm/filemap.c never took advantage of having read_cache_page_async(). While there are filler callbacks that do async reads (such as the block one), we always called it with the read_cache_page(). This patch adds a mandatory wait for read to complete when adding a new page to the cache, and removes read_cache_page_async() and its wrappers. Signed-off-by: Sasha Levin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/cramfs/inode.c | 3 +-- fs/jffs2/fs.c | 2 +- include/linux/pagemap.h | 10 -------- mm/filemap.c | 64 ++++++++++++++++++------------------------------- 4 files changed, 25 insertions(+), 54 deletions(-) (limited to 'mm/filemap.c') diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 06610cf94d57..a1f801c14fbc 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -195,8 +195,7 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i struct page *page = NULL; if (blocknr + i < devsize) { - page = read_mapping_page_async(mapping, blocknr + i, - NULL); + page = read_mapping_page(mapping, blocknr + i, NULL); /* synchronous error? */ if (IS_ERR(page)) page = NULL; diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index a012e16a8bb3..f73991522672 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c, struct inode *inode = OFNI_EDONI_2SFFJ(f); struct page *pg; - pg = read_cache_page_async(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, + pg = read_cache_page(inode->i_mapping, offset >> PAGE_CACHE_SHIFT, (void *)jffs2_do_readpage_unlock, inode); if (IS_ERR(pg)) return (void *)pg; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ff43253f568a..45598f1e9aa3 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -289,8 +289,6 @@ static inline struct page *grab_cache_page(struct address_space *mapping, extern struct page * grab_cache_page_nowait(struct address_space *mapping, pgoff_t index); -extern struct page * read_cache_page_async(struct address_space *mapping, - pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, @@ -298,14 +296,6 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping, extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); -static inline struct page *read_mapping_page_async( - struct address_space *mapping, - pgoff_t index, void *data) -{ - filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return read_cache_page_async(mapping, index, filler, data); -} - static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, void *data) { diff --git a/mm/filemap.c b/mm/filemap.c index d6df3bacb0fb..21781f1fe52b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2133,6 +2133,18 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma) EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); +static struct page *wait_on_page_read(struct page *page) +{ + if (!IS_ERR(page)) { + wait_on_page_locked(page); + if (!PageUptodate(page)) { + page_cache_release(page); + page = ERR_PTR(-EIO); + } + } + return page; +} + static struct page *__read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), @@ -2159,6 +2171,8 @@ repeat: if (err < 0) { page_cache_release(page); page = ERR_PTR(err); + } else { + page = wait_on_page_read(page); } } return page; @@ -2195,6 +2209,10 @@ retry: if (err < 0) { page_cache_release(page); return ERR_PTR(err); + } else { + page = wait_on_page_read(page); + if (IS_ERR(page)) + return page; } out: mark_page_accessed(page); @@ -2202,40 +2220,25 @@ out: } /** - * read_cache_page_async - read into page cache, fill it if needed + * 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: first arg to filler(data, page) function, often left as NULL * - * Same as read_cache_page, but don't wait for page to become unlocked - * after submitting it to the filler. - * * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page but don't wait for it to become unlocked. + * not set, try to fill the page and wait for it to become unlocked. * * If the page does not get brought uptodate, return -EIO. */ -struct page *read_cache_page_async(struct address_space *mapping, +struct page *read_cache_page(struct address_space *mapping, pgoff_t index, int (*filler)(void *, struct page *), void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); } -EXPORT_SYMBOL(read_cache_page_async); - -static struct page *wait_on_page_read(struct page *page) -{ - if (!IS_ERR(page)) { - wait_on_page_locked(page); - if (!PageUptodate(page)) { - page_cache_release(page); - page = ERR_PTR(-EIO); - } - } - return page; -} +EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. @@ -2254,31 +2257,10 @@ struct page *read_cache_page_gfp(struct address_space *mapping, { filler_t *filler = (filler_t *)mapping->a_ops->readpage; - return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp)); + return do_read_cache_page(mapping, index, filler, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); -/** - * 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: first arg to filler(data, page) function, often left as NULL - * - * Read into the page cache. If a page already exists, and PageUptodate() is - * not set, try to fill the page then wait for it to become unlocked. - * - * If the page does not get brought uptodate, return -EIO. - */ -struct page *read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data) -{ - return wait_on_page_read(read_cache_page_async(mapping, index, filler, data)); -} -EXPORT_SYMBOL(read_cache_page); - static size_t __iovec_copy_from_user_inatomic(char *vaddr, const struct iovec *iov, size_t base, size_t bytes) { -- cgit From f1820361f83d556a7f0a9f629100f3825e594328 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Mon, 7 Apr 2014 15:37:19 -0700 Subject: mm: implement ->map_pages for page cache filemap_map_pages() is generic implementation of ->map_pages() for filesystems who uses page cache. It should be safe to use filemap_map_pages() for ->map_pages() if filesystem use filemap_fault() for ->fault(). Signed-off-by: Kirill A. Shutemov Acked-by: Linus Torvalds Cc: Mel Gorman Cc: Rik van Riel Cc: Andi Kleen Cc: Matthew Wilcox Cc: Dave Hansen Cc: Alexander Viro Cc: Dave Chinner Cc: Ning Qu Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/9p/vfs_file.c | 2 ++ fs/btrfs/file.c | 1 + fs/cifs/file.c | 1 + fs/ext4/file.c | 1 + fs/f2fs/file.c | 1 + fs/fuse/file.c | 1 + fs/gfs2/file.c | 1 + fs/nfs/file.c | 1 + fs/nilfs2/file.c | 1 + fs/ubifs/file.c | 1 + fs/xfs/xfs_file.c | 1 + include/linux/mm.h | 1 + mm/filemap.c | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ mm/nommu.c | 6 +++++ 14 files changed, 93 insertions(+) (limited to 'mm/filemap.c') diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index a16b0ff497ca..d8223209d4b1 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -832,6 +832,7 @@ static void v9fs_mmap_vm_close(struct vm_area_struct *vma) static const struct vm_operations_struct v9fs_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = v9fs_vm_page_mkwrite, .remap_pages = generic_file_remap_pages, }; @@ -839,6 +840,7 @@ static const struct vm_operations_struct v9fs_file_vm_ops = { static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { .close = v9fs_mmap_vm_close, .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = v9fs_vm_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index e1ffb1e22898..c660527af838 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2025,6 +2025,7 @@ out: static const struct vm_operations_struct btrfs_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = btrfs_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 834fce759d80..216d7e99f921 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3113,6 +3113,7 @@ cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) static struct vm_operations_struct cifs_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = cifs_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 6db7f7db7777..4e508fc83dcf 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -200,6 +200,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = ext4_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 0dfcef53a6ed..129a3bdb05ca 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -84,6 +84,7 @@ out: static const struct vm_operations_struct f2fs_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = f2fs_vm_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 65df7d8be4f5..48992cac714b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2117,6 +2117,7 @@ static int fuse_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) static const struct vm_operations_struct fuse_file_vm_ops = { .close = fuse_vma_close, .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = fuse_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 6c794085abac..80d67253623c 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -494,6 +494,7 @@ out: static const struct vm_operations_struct gfs2_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = gfs2_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 5bb790a69c71..284ca901fe16 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -617,6 +617,7 @@ out: static const struct vm_operations_struct nfs_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = nfs_vm_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 08fdb77852ac..f3a82fbcae02 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -134,6 +134,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) static const struct vm_operations_struct nilfs_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = nilfs_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 123c79b7261e..4f34dbae823d 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1538,6 +1538,7 @@ out_unlock: static const struct vm_operations_struct ubifs_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = ubifs_vm_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f7abff8c16ca..003c0051b62f 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1483,6 +1483,7 @@ const struct file_operations xfs_dir_file_operations = { static const struct vm_operations_struct xfs_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = xfs_vm_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/include/linux/mm.h b/include/linux/mm.h index f710d32291e8..9132faed1a41 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1847,6 +1847,7 @@ extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern int filemap_fault(struct vm_area_struct *, struct vm_fault *); +extern void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf); extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); /* mm/page-writeback.c */ diff --git a/mm/filemap.c b/mm/filemap.c index 21781f1fe52b..3f9b5fbb623f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -33,6 +33,7 @@ #include /* for BUG_ON(!in_atomic()) only */ #include #include +#include #include "internal.h" #define CREATE_TRACE_POINTS @@ -2064,6 +2065,78 @@ page_not_uptodate: } EXPORT_SYMBOL(filemap_fault); +void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct radix_tree_iter iter; + void **slot; + struct file *file = vma->vm_file; + struct address_space *mapping = file->f_mapping; + loff_t size; + struct page *page; + unsigned long address = (unsigned long) vmf->virtual_address; + unsigned long addr; + pte_t *pte; + + rcu_read_lock(); + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, vmf->pgoff) { + if (iter.index > vmf->max_pgoff) + break; +repeat: + page = radix_tree_deref_slot(slot); + if (unlikely(!page)) + goto next; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) + break; + else + goto next; + } + + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *slot)) { + page_cache_release(page); + goto repeat; + } + + if (!PageUptodate(page) || + PageReadahead(page) || + PageHWPoison(page)) + goto skip; + if (!trylock_page(page)) + goto skip; + + if (page->mapping != mapping || !PageUptodate(page)) + goto unlock; + + size = i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1; + if (page->index >= size >> PAGE_CACHE_SHIFT) + goto unlock; + + pte = vmf->pte + page->index - vmf->pgoff; + if (!pte_none(*pte)) + goto unlock; + + if (file->f_ra.mmap_miss > 0) + file->f_ra.mmap_miss--; + addr = address + (page->index - vmf->pgoff) * PAGE_SIZE; + do_set_pte(vma, addr, page, pte, false, false); + unlock_page(page); + goto next; +unlock: + unlock_page(page); +skip: + page_cache_release(page); +next: + if (iter.index == vmf->max_pgoff) + break; + } + rcu_read_unlock(); +} +EXPORT_SYMBOL(filemap_map_pages); + int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { struct page *page = vmf->page; @@ -2093,6 +2166,7 @@ EXPORT_SYMBOL(filemap_page_mkwrite); const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, + .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, .remap_pages = generic_file_remap_pages, }; diff --git a/mm/nommu.c b/mm/nommu.c index a554e5a451cd..e19482533ce3 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1985,6 +1985,12 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) } EXPORT_SYMBOL(filemap_fault); +void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + BUG(); +} +EXPORT_SYMBOL(filemap_map_pages); + int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, unsigned long size, pgoff_t pgoff) { -- cgit From 99e3e53f4e0fd807607bf381e14f6de8feedd383 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Mon, 7 Apr 2014 15:37:21 -0700 Subject: mm: cleanup size checks in filemap_fault() and filemap_map_pages() Minor cleanups: - 'size' variable is now in bytes, not pages; - use round_up(): it should be easier to read. Signed-off-by: Kirill A. Shutemov Cc: Linus Torvalds Cc: Mel Gorman Cc: Rik van Riel Cc: Andi Kleen Cc: Matthew Wilcox Cc: Dave Hansen Cc: Alexander Viro Cc: Dave Chinner Cc: Ning Qu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 3f9b5fbb623f..b952d99c827c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1953,11 +1953,11 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct inode *inode = mapping->host; pgoff_t offset = vmf->pgoff; struct page *page; - pgoff_t size; + loff_t size; int ret = 0; - size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (offset >= size) + size = round_up(i_size_read(inode), PAGE_CACHE_SIZE); + if (offset >= size >> PAGE_CACHE_SHIFT) return VM_FAULT_SIGBUS; /* @@ -2006,8 +2006,8 @@ retry_find: * Found the page and have a reference on it. * We must recheck i_size under page lock. */ - size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (unlikely(offset >= size)) { + size = round_up(i_size_read(inode), PAGE_CACHE_SIZE); + if (unlikely(offset >= size >> PAGE_CACHE_SHIFT)) { unlock_page(page); page_cache_release(page); return VM_FAULT_SIGBUS; @@ -2111,8 +2111,8 @@ repeat: if (page->mapping != mapping || !PageUptodate(page)) goto unlock; - size = i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1; - if (page->index >= size >> PAGE_CACHE_SHIFT) + size = round_up(i_size_read(mapping->host), PAGE_CACHE_SIZE); + if (page->index >= size >> PAGE_CACHE_SHIFT) goto unlock; pte = vmf->pte + page->index - vmf->pgoff; -- cgit From d715ae08f2ff87508a081c4df78061bf4f7211d6 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Mon, 7 Apr 2014 15:37:46 -0700 Subject: memcg: rename high level charging functions mem_cgroup_newpage_charge is used only for charging anonymous memory so it is better to rename it to mem_cgroup_charge_anon. mem_cgroup_cache_charge is used for file backed memory so rename it to mem_cgroup_charge_file. Signed-off-by: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/memcg_test.txt | 4 ++-- include/linux/memcontrol.h | 8 ++++---- mm/filemap.c | 2 +- mm/huge_memory.c | 8 ++++---- mm/memcontrol.c | 4 ++-- mm/memory.c | 6 +++--- mm/shmem.c | 6 +++--- 7 files changed, 19 insertions(+), 19 deletions(-) (limited to 'mm/filemap.c') diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt index ce94a83a7d9a..80ac454704b8 100644 --- a/Documentation/cgroups/memcg_test.txt +++ b/Documentation/cgroups/memcg_test.txt @@ -24,7 +24,7 @@ Please note that implementation details can be changed. a page/swp_entry may be charged (usage += PAGE_SIZE) at - mem_cgroup_newpage_charge() + mem_cgroup_charge_anon() Called at new page fault and Copy-On-Write. mem_cgroup_try_charge_swapin() @@ -32,7 +32,7 @@ Please note that implementation details can be changed. Followed by charge-commit-cancel protocol. (With swap accounting) At commit, a charge recorded in swap_cgroup is removed. - mem_cgroup_cache_charge() + mem_cgroup_charge_file() Called at add_to_page_cache() mem_cgroup_cache_charge_swapin() diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 134636f835f7..96f3fc87ab96 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -65,7 +65,7 @@ struct mem_cgroup_reclaim_cookie { * (Of course, if memcg does memory allocation in future, GFP_KERNEL is sane.) */ -extern int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm, +extern int mem_cgroup_charge_anon(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); /* for swap handling */ extern int mem_cgroup_try_charge_swapin(struct mm_struct *mm, @@ -74,7 +74,7 @@ extern void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg); extern void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg); -extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, +extern int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); @@ -233,13 +233,13 @@ void mem_cgroup_print_bad_page(struct page *page); #else /* CONFIG_MEMCG */ struct mem_cgroup; -static inline int mem_cgroup_newpage_charge(struct page *page, +static inline int mem_cgroup_charge_anon(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { return 0; } -static inline int mem_cgroup_cache_charge(struct page *page, +static inline int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { return 0; diff --git a/mm/filemap.c b/mm/filemap.c index b952d99c827c..27ebc0c9571b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -563,7 +563,7 @@ static int __add_to_page_cache_locked(struct page *page, VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapBacked(page), page); - error = mem_cgroup_cache_charge(page, current->mm, + error = mem_cgroup_charge_file(page, current->mm, gfp_mask & GFP_RECLAIM_MASK); if (error) return error; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index a2f4981418fc..64635f5278ff 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -827,7 +827,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } - if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { + if (unlikely(mem_cgroup_charge_anon(page, mm, GFP_KERNEL))) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -968,7 +968,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, __GFP_OTHER_NODE, vma, address, page_to_nid(page)); if (unlikely(!pages[i] || - mem_cgroup_newpage_charge(pages[i], mm, + mem_cgroup_charge_anon(pages[i], mm, GFP_KERNEL))) { if (pages[i]) put_page(pages[i]); @@ -1101,7 +1101,7 @@ alloc: goto out; } - if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { + if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))) { put_page(new_page); if (page) { split_huge_page(page); @@ -2359,7 +2359,7 @@ static void collapse_huge_page(struct mm_struct *mm, if (!new_page) return; - if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) + if (unlikely(mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL))) return; /* diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 038b037f8d67..e33b1d09eb1f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3818,7 +3818,7 @@ out: return ret; } -int mem_cgroup_newpage_charge(struct page *page, +int mem_cgroup_charge_anon(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { unsigned int nr_pages = 1; @@ -3954,7 +3954,7 @@ void mem_cgroup_commit_charge_swapin(struct page *page, MEM_CGROUP_CHARGE_TYPE_ANON); } -int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, +int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE; diff --git a/mm/memory.c b/mm/memory.c index 1b88da5c08b3..854e4027719f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2828,7 +2828,7 @@ gotten: } __SetPageUptodate(new_page); - if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) + if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) goto oom_free_new; mmun_start = address & PAGE_MASK; @@ -3281,7 +3281,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, */ __SetPageUptodate(page); - if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) + if (mem_cgroup_charge_anon(page, mm, GFP_KERNEL)) goto oom_free_page; entry = mk_pte(page, vma->vm_page_prot); @@ -3537,7 +3537,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (!new_page) return VM_FAULT_OOM; - if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL)) { + if (mem_cgroup_charge_anon(new_page, mm, GFP_KERNEL)) { page_cache_release(new_page); return VM_FAULT_OOM; } diff --git a/mm/shmem.c b/mm/shmem.c index 70709347a1e2..70273f8df586 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -683,7 +683,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page) * the shmem_swaplist_mutex which might hold up shmem_writepage(). * Charged back to the user (not to caller) when swap account is used. */ - error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); + error = mem_cgroup_charge_file(page, current->mm, GFP_KERNEL); if (error) goto out; /* No radix_tree_preload: swap entry keeps a place for page in tree */ @@ -1080,7 +1080,7 @@ repeat: goto failed; } - error = mem_cgroup_cache_charge(page, current->mm, + error = mem_cgroup_charge_file(page, current->mm, gfp & GFP_RECLAIM_MASK); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, @@ -1134,7 +1134,7 @@ repeat: SetPageSwapBacked(page); __set_page_locked(page); - error = mem_cgroup_cache_charge(page, current->mm, + error = mem_cgroup_charge_file(page, current->mm, gfp & GFP_RECLAIM_MASK); if (error) goto decused; -- cgit