void bio_free(struct bio *bio, struct bio_set *bio_set)
{
- const int pool_idx = BIO_POOL_IDX(bio);
+ if (bio->bi_io_vec) {
+ const int pool_idx = BIO_POOL_IDX(bio);
- BIO_BUG_ON(pool_idx >= BIOVEC_NR_POOLS);
+ BIO_BUG_ON(pool_idx >= BIOVEC_NR_POOLS);
+
+ mempool_free(bio->bi_io_vec, bio_set->bvec_pools[pool_idx]);
+ }
- mempool_free(bio->bi_io_vec, bio_set->bvec_pools[pool_idx]);
mempool_free(bio, bio_set->bio_pool);
}
void bio_init(struct bio *bio)
{
- bio->bi_next = NULL;
- bio->bi_bdev = NULL;
+ memset(bio, 0, sizeof(*bio));
bio->bi_flags = 1 << BIO_UPTODATE;
- bio->bi_rw = 0;
- bio->bi_vcnt = 0;
- bio->bi_idx = 0;
- bio->bi_phys_segments = 0;
- bio->bi_hw_segments = 0;
- bio->bi_hw_front_size = 0;
- bio->bi_hw_back_size = 0;
- bio->bi_size = 0;
- bio->bi_max_vecs = 0;
- bio->bi_end_io = NULL;
atomic_set(&bio->bi_cnt, 1);
- bio->bi_private = NULL;
}
/**
*/
void __bio_clone(struct bio *bio, struct bio *bio_src)
{
- struct request_queue *q = bdev_get_queue(bio_src->bi_bdev);
-
memcpy(bio->bi_io_vec, bio_src->bi_io_vec,
bio_src->bi_max_vecs * sizeof(struct bio_vec));
+ /*
+ * most users will be overriding ->bi_bdev with a new target,
+ * so we don't set nor calculate new physical/hw segment counts here
+ */
bio->bi_sector = bio_src->bi_sector;
bio->bi_bdev = bio_src->bi_bdev;
bio->bi_flags |= 1 << BIO_CLONED;
bio->bi_vcnt = bio_src->bi_vcnt;
bio->bi_size = bio_src->bi_size;
bio->bi_idx = bio_src->bi_idx;
- bio_phys_segments(q, bio);
- bio_hw_segments(q, bio);
}
/**
struct bio_map_data {
struct bio_vec *iovecs;
- void __user *userptr;
+ int nr_sgvecs;
+ struct sg_iovec *sgvecs;
};
-static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio)
+static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
+ struct sg_iovec *iov, int iov_count)
{
memcpy(bmd->iovecs, bio->bi_io_vec, sizeof(struct bio_vec) * bio->bi_vcnt);
+ memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
+ bmd->nr_sgvecs = iov_count;
bio->bi_private = bmd;
}
static void bio_free_map_data(struct bio_map_data *bmd)
{
kfree(bmd->iovecs);
+ kfree(bmd->sgvecs);
kfree(bmd);
}
-static struct bio_map_data *bio_alloc_map_data(int nr_segs)
+static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count)
{
struct bio_map_data *bmd = kmalloc(sizeof(*bmd), GFP_KERNEL);
return NULL;
bmd->iovecs = kmalloc(sizeof(struct bio_vec) * nr_segs, GFP_KERNEL);
- if (bmd->iovecs)
+ if (!bmd->iovecs) {
+ kfree(bmd);
+ return NULL;
+ }
+
+ bmd->sgvecs = kmalloc(sizeof(struct sg_iovec) * iov_count, GFP_KERNEL);
+ if (bmd->sgvecs)
return bmd;
+ kfree(bmd->iovecs);
kfree(bmd);
return NULL;
}
+static int __bio_copy_iov(struct bio *bio, struct sg_iovec *iov, int iov_count,
+ int uncopy)
+{
+ int ret = 0, i;
+ struct bio_vec *bvec;
+ int iov_idx = 0;
+ unsigned int iov_off = 0;
+ int read = bio_data_dir(bio) == READ;
+
+ __bio_for_each_segment(bvec, bio, i, 0) {
+ char *bv_addr = page_address(bvec->bv_page);
+ unsigned int bv_len = bvec->bv_len;
+
+ while (bv_len && iov_idx < iov_count) {
+ unsigned int bytes;
+ char *iov_addr;
+
+ bytes = min_t(unsigned int,
+ iov[iov_idx].iov_len - iov_off, bv_len);
+ iov_addr = iov[iov_idx].iov_base + iov_off;
+
+ if (!ret) {
+ if (!read && !uncopy)
+ ret = copy_from_user(bv_addr, iov_addr,
+ bytes);
+ if (read && uncopy)
+ ret = copy_to_user(iov_addr, bv_addr,
+ bytes);
+
+ if (ret)
+ ret = -EFAULT;
+ }
+
+ bv_len -= bytes;
+ bv_addr += bytes;
+ iov_addr += bytes;
+ iov_off += bytes;
+
+ if (iov[iov_idx].iov_len == iov_off) {
+ iov_idx++;
+ iov_off = 0;
+ }
+ }
+
+ if (uncopy)
+ __free_page(bvec->bv_page);
+ }
+
+ return ret;
+}
+
/**
* bio_uncopy_user - finish previously mapped bio
* @bio: bio being terminated
int bio_uncopy_user(struct bio *bio)
{
struct bio_map_data *bmd = bio->bi_private;
- const int read = bio_data_dir(bio) == READ;
- struct bio_vec *bvec;
- int i, ret = 0;
-
- __bio_for_each_segment(bvec, bio, i, 0) {
- char *addr = page_address(bvec->bv_page);
- unsigned int len = bmd->iovecs[i].bv_len;
+ int ret;
- if (read && !ret && copy_to_user(bmd->userptr, addr, len))
- ret = -EFAULT;
+ ret = __bio_copy_iov(bio, bmd->sgvecs, bmd->nr_sgvecs, 1);
- __free_page(bvec->bv_page);
- bmd->userptr += len;
- }
bio_free_map_data(bmd);
bio_put(bio);
return ret;
}
/**
- * bio_copy_user - copy user data to bio
+ * bio_copy_user_iov - copy user data to bio
* @q: destination block queue
- * @uaddr: start of user address
- * @len: length in bytes
+ * @iov: the iovec.
+ * @iov_count: number of elements in the iovec
* @write_to_vm: bool indicating writing to pages or not
*
* Prepares and returns a bio for indirect user io, bouncing data
* to/from kernel pages as necessary. Must be paired with
* call bio_uncopy_user() on io completion.
*/
-struct bio *bio_copy_user(struct request_queue *q, unsigned long uaddr,
- unsigned int len, int write_to_vm)
+struct bio *bio_copy_user_iov(struct request_queue *q, struct sg_iovec *iov,
+ int iov_count, int write_to_vm)
{
- unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
- unsigned long start = uaddr >> PAGE_SHIFT;
struct bio_map_data *bmd;
struct bio_vec *bvec;
struct page *page;
struct bio *bio;
int i, ret;
+ int nr_pages = 0;
+ unsigned int len = 0;
+
+ for (i = 0; i < iov_count; i++) {
+ unsigned long uaddr;
+ unsigned long end;
+ unsigned long start;
+
+ uaddr = (unsigned long)iov[i].iov_base;
+ end = (uaddr + iov[i].iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ start = uaddr >> PAGE_SHIFT;
- bmd = bio_alloc_map_data(end - start);
+ nr_pages += end - start;
+ len += iov[i].iov_len;
+ }
+
+ bmd = bio_alloc_map_data(nr_pages, iov_count);
if (!bmd)
return ERR_PTR(-ENOMEM);
- bmd->userptr = (void __user *) uaddr;
-
ret = -ENOMEM;
- bio = bio_alloc(GFP_KERNEL, end - start);
+ bio = bio_alloc(GFP_KERNEL, nr_pages);
if (!bio)
goto out_bmd;
* success
*/
if (!write_to_vm) {
- char __user *p = (char __user *) uaddr;
-
- /*
- * for a write, copy in data to kernel pages
- */
- ret = -EFAULT;
- bio_for_each_segment(bvec, bio, i) {
- char *addr = page_address(bvec->bv_page);
-
- if (copy_from_user(addr, p, bvec->bv_len))
- goto cleanup;
- p += bvec->bv_len;
- }
+ ret = __bio_copy_iov(bio, iov, iov_count, 0);
+ if (ret)
+ goto cleanup;
}
- bio_set_map_data(bmd, bio);
+ bio_set_map_data(bmd, bio, iov, iov_count);
return bio;
cleanup:
bio_for_each_segment(bvec, bio, i)
return ERR_PTR(ret);
}
+/**
+ * bio_copy_user - copy user data to bio
+ * @q: destination block queue
+ * @uaddr: start of user address
+ * @len: length in bytes
+ * @write_to_vm: bool indicating writing to pages or not
+ *
+ * Prepares and returns a bio for indirect user io, bouncing data
+ * to/from kernel pages as necessary. Must be paired with
+ * call bio_uncopy_user() on io completion.
+ */
+struct bio *bio_copy_user(struct request_queue *q, unsigned long uaddr,
+ unsigned int len, int write_to_vm)
+{
+ struct sg_iovec iov;
+
+ iov.iov_base = (void __user *)uaddr;
+ iov.iov_len = len;
+
+ return bio_copy_user_iov(q, &iov, 1, write_to_vm);
+}
+
static struct bio *__bio_map_user_iov(struct request_queue *q,
struct block_device *bdev,
struct sg_iovec *iov, int iov_count,
bio_put(bio);
}
-static int bio_map_kern_endio(struct bio *bio, unsigned int bytes_done, int err)
+static void bio_map_kern_endio(struct bio *bio, int err)
{
- if (bio->bi_size)
- return 1;
-
bio_put(bio);
- return 0;
}
}
}
-void bio_release_pages(struct bio *bio)
+static void bio_release_pages(struct bio *bio)
{
struct bio_vec *bvec = bio->bi_io_vec;
int i;
/**
* bio_endio - end I/O on a bio
* @bio: bio
- * @bytes_done: number of bytes completed
* @error: error, if any
*
* Description:
- * bio_endio() will end I/O on @bytes_done number of bytes. This may be
- * just a partial part of the bio, or it may be the whole bio. bio_endio()
- * is the preferred way to end I/O on a bio, it takes care of decrementing
- * bi_size and clearing BIO_UPTODATE on error. @error is 0 on success, and
- * and one of the established -Exxxx (-EIO, for instance) error values in
- * case something went wrong. Noone should call bi_end_io() directly on
- * a bio unless they own it and thus know that it has an end_io function.
+ * bio_endio() will end I/O on the whole bio. bio_endio() is the
+ * preferred way to end I/O on a bio, it takes care of clearing
+ * BIO_UPTODATE on error. @error is 0 on success, and and one of the
+ * established -Exxxx (-EIO, for instance) error values in case
+ * something went wrong. Noone should call bi_end_io() directly on a
+ * bio unless they own it and thus know that it has an end_io
+ * function.
**/
-void bio_endio(struct bio *bio, unsigned int bytes_done, int error)
+void bio_endio(struct bio *bio, int error)
{
if (error)
clear_bit(BIO_UPTODATE, &bio->bi_flags);
-
- if (unlikely(bytes_done > bio->bi_size)) {
- printk("%s: want %u bytes done, only %u left\n", __FUNCTION__,
- bytes_done, bio->bi_size);
- bytes_done = bio->bi_size;
- }
-
- bio->bi_size -= bytes_done;
- bio->bi_sector += (bytes_done >> 9);
+ else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+ error = -EIO;
if (bio->bi_end_io)
- bio->bi_end_io(bio, bytes_done, error);
+ bio->bi_end_io(bio, error);
}
void bio_pair_release(struct bio_pair *bp)
if (atomic_dec_and_test(&bp->cnt)) {
struct bio *master = bp->bio1.bi_private;
- bio_endio(master, master->bi_size, bp->error);
+ bio_endio(master, bp->error);
mempool_free(bp, bp->bio2.bi_private);
}
}
-static int bio_pair_end_1(struct bio * bi, unsigned int done, int err)
+static void bio_pair_end_1(struct bio *bi, int err)
{
struct bio_pair *bp = container_of(bi, struct bio_pair, bio1);
if (err)
bp->error = err;
- if (bi->bi_size)
- return 1;
-
bio_pair_release(bp);
- return 0;
}
-static int bio_pair_end_2(struct bio * bi, unsigned int done, int err)
+static void bio_pair_end_2(struct bio *bi, int err)
{
struct bio_pair *bp = container_of(bi, struct bio_pair, bio2);
if (err)
bp->error = err;
- if (bi->bi_size)
- return 1;
-
bio_pair_release(bp);
- return 0;
}
/*
EXPORT_SYMBOL(bio_add_page);
EXPORT_SYMBOL(bio_add_pc_page);
EXPORT_SYMBOL(bio_get_nr_vecs);
+EXPORT_SYMBOL(bio_map_user);
+EXPORT_SYMBOL(bio_unmap_user);
EXPORT_SYMBOL(bio_map_kern);
EXPORT_SYMBOL(bio_pair_release);
EXPORT_SYMBOL(bio_split);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff