From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752857Ab2KVSau (ORCPT ); Thu, 22 Nov 2012 13:30:50 -0500 Received: from aserp1050.oracle.com ([141.146.126.70]:22356 "EHLO aserp1050.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752812Ab2KVSao (ORCPT ); Thu, 22 Nov 2012 13:30:44 -0500 From: Dave Kleikamp To: linux-fsdevel@vger.kernel.org Cc: linux-kernel@vger.kernel.org, Zach Brown , "Maxim V. Patlasov" , Dave Kleikamp Subject: [PATCH v4 06/31] iov_iter: add bvec support Date: Wed, 21 Nov 2012 16:40:46 -0600 Message-Id: <1353537671-26284-7-git-send-email-dave.kleikamp@oracle.com> X-Mailer: git-send-email 1.8.0 In-Reply-To: <1353537671-26284-1-git-send-email-dave.kleikamp@oracle.com> References: <1353537671-26284-1-git-send-email-dave.kleikamp@oracle.com> X-Source-IP: aserp1040.oracle.com [141.146.126.69] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Zach Brown This adds a set of iov_iter_ops calls which work with memory which is specified by an array of bio_vec structs instead of an array of iovec structs. The big difference is that the pages referenced by the bio_vec elements are pinned. They don't need to be faulted in and we can always use kmap_atomic() to map them one at a time. Signed-off-by: Dave Kleikamp Cc: Zach Brown --- include/linux/fs.h | 17 ++++++++ mm/iov-iter.c | 126 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 143 insertions(+) diff --git a/include/linux/fs.h b/include/linux/fs.h index 6cece28..0d7f42f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -342,6 +342,23 @@ static inline size_t iov_iter_single_seg_count(struct iov_iter *i) return i->ops->ii_single_seg_count(i); } +extern struct iov_iter_ops ii_bvec_ops; + +struct bio_vec; +static inline void iov_iter_init_bvec(struct iov_iter *i, + struct bio_vec *bvec, + unsigned long nr_segs, + size_t count, size_t written) +{ + i->ops = &ii_bvec_ops; + i->data = (unsigned long)bvec; + i->nr_segs = nr_segs; + i->iov_offset = 0; + i->count = count + written; + + iov_iter_advance(i, written); +} + extern struct iov_iter_ops ii_iovec_ops; static inline void iov_iter_init(struct iov_iter *i, diff --git a/mm/iov-iter.c b/mm/iov-iter.c index bae1553..c5d0a9e 100644 --- a/mm/iov-iter.c +++ b/mm/iov-iter.c @@ -5,6 +5,7 @@ #include #include #include +#include static size_t __iovec_copy_to_user(char *vaddr, const struct iovec *iov, size_t base, size_t bytes, int atomic) @@ -86,6 +87,131 @@ static size_t ii_iovec_copy_to_user(struct page *page, return copied; } +/* + * As an easily verifiable first pass, we implement all the methods that + * copy data to and from bvec pages with one function. We implement it + * all with kmap_atomic(). + */ +static size_t bvec_copy_tofrom_page(struct iov_iter *iter, struct page *page, + unsigned long page_offset, size_t bytes, + int topage) +{ + struct bio_vec *bvec = (struct bio_vec *)iter->data; + size_t bvec_offset = iter->iov_offset; + size_t remaining = bytes; + void *bvec_map; + void *page_map; + size_t copy; + + page_map = kmap_atomic(page); + + BUG_ON(bytes > iter->count); + while (remaining) { + BUG_ON(bvec->bv_len == 0); + BUG_ON(bvec_offset >= bvec->bv_len); + copy = min(remaining, bvec->bv_len - bvec_offset); + bvec_map = kmap_atomic(bvec->bv_page); + if (topage) + memcpy(page_map + page_offset, + bvec_map + bvec->bv_offset + bvec_offset, + copy); + else + memcpy(bvec_map + bvec->bv_offset + bvec_offset, + page_map + page_offset, + copy); + kunmap_atomic(bvec_map); + remaining -= copy; + bvec_offset += copy; + page_offset += copy; + if (bvec_offset == bvec->bv_len) { + bvec_offset = 0; + bvec++; + } + } + + kunmap_atomic(page_map); + + return bytes; +} + +static size_t ii_bvec_copy_to_user_atomic(struct page *page, struct iov_iter *i, + unsigned long offset, size_t bytes) +{ + return bvec_copy_tofrom_page(i, page, offset, bytes, 0); +} +static size_t ii_bvec_copy_to_user(struct page *page, struct iov_iter *i, + unsigned long offset, size_t bytes) +{ + return bvec_copy_tofrom_page(i, page, offset, bytes, 0); +} +static size_t ii_bvec_copy_from_user_atomic(struct page *page, + struct iov_iter *i, + unsigned long offset, size_t bytes) +{ + return bvec_copy_tofrom_page(i, page, offset, bytes, 1); +} +static size_t ii_bvec_copy_from_user(struct page *page, struct iov_iter *i, + unsigned long offset, size_t bytes) +{ + return bvec_copy_tofrom_page(i, page, offset, bytes, 1); +} + +/* + * bio_vecs have a stricter structure than iovecs that might have + * come from userspace. There are no zero length bio_vec elements. + */ +static void ii_bvec_advance(struct iov_iter *i, size_t bytes) +{ + struct bio_vec *bvec = (struct bio_vec *)i->data; + size_t offset = i->iov_offset; + size_t delta; + + BUG_ON(i->count < bytes); + while (bytes) { + BUG_ON(bvec->bv_len == 0); + BUG_ON(bvec->bv_len <= offset); + delta = min(bytes, bvec->bv_len - offset); + offset += delta; + i->count -= delta; + bytes -= delta; + if (offset == bvec->bv_len) { + bvec++; + offset = 0; + } + } + + i->data = (unsigned long)bvec; + i->iov_offset = offset; +} + +/* + * pages pointed to by bio_vecs are always pinned. + */ +static int ii_bvec_fault_in_readable(struct iov_iter *i, size_t bytes) +{ + return 0; +} + +static size_t ii_bvec_single_seg_count(struct iov_iter *i) +{ + const struct bio_vec *bvec = (struct bio_vec *)i->data; + if (i->nr_segs == 1) + return i->count; + else + return min(i->count, bvec->bv_len - i->iov_offset); +} + +struct iov_iter_ops ii_bvec_ops = { + .ii_copy_to_user_atomic = ii_bvec_copy_to_user_atomic, + .ii_copy_to_user = ii_bvec_copy_to_user, + .ii_copy_from_user_atomic = ii_bvec_copy_from_user_atomic, + .ii_copy_from_user = ii_bvec_copy_from_user, + .ii_advance = ii_bvec_advance, + .ii_fault_in_readable = ii_bvec_fault_in_readable, + .ii_single_seg_count = ii_bvec_single_seg_count, +}; +EXPORT_SYMBOL(ii_bvec_ops); + static size_t __iovec_copy_from_user(char *vaddr, const struct iovec *iov, size_t base, size_t bytes, int atomic) { -- 1.8.0