#include <linux/module.h>
#include <linux/mempool.h>
#include <linux/workqueue.h>
+#include <linux/blktrace_api.h>
+#include <scsi/sg.h> /* for struct sg_iovec */
#define BIO_POOL_SIZE 256
-static kmem_cache_t *bio_slab;
+static kmem_cache_t *bio_slab __read_mostly;
#define BIOVEC_NR_POOLS 6
* basically we just need to survive
*/
#define BIO_SPLIT_ENTRIES 8
-mempool_t *bio_split_pool;
+mempool_t *bio_split_pool __read_mostly;
struct biovec_slab {
int nr_vecs;
*/
#define BV(x) { .nr_vecs = x, .name = "biovec-"__stringify(x) }
-static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] = {
+static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
BV(1), BV(4), BV(16), BV(64), BV(128), BV(BIO_MAX_PAGES),
};
#undef BV
*/
static struct bio_set *fs_bio_set;
-static inline struct bio_vec *bvec_alloc_bs(unsigned int __nocast gfp_mask, int nr, unsigned long *idx, struct bio_set *bs)
+static inline struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct bio_set *bs)
{
struct bio_vec *bvl;
struct biovec_slab *bp;
return bvl;
}
-/*
- * default destructor for a bio allocated with bio_alloc_bioset()
- */
-static void bio_destructor(struct bio *bio)
+void bio_free(struct bio *bio, struct bio_set *bio_set)
{
const int pool_idx = BIO_POOL_IDX(bio);
- struct bio_set *bs = bio->bi_set;
BIO_BUG_ON(pool_idx >= BIOVEC_NR_POOLS);
- mempool_free(bio->bi_io_vec, bs->bvec_pools[pool_idx]);
- mempool_free(bio, bs->bio_pool);
+ mempool_free(bio->bi_io_vec, bio_set->bvec_pools[pool_idx]);
+ mempool_free(bio, bio_set->bio_pool);
+}
+
+/*
+ * default destructor for a bio allocated with bio_alloc_bioset()
+ */
+static void bio_fs_destructor(struct bio *bio)
+{
+ bio_free(bio, fs_bio_set);
}
-inline void bio_init(struct bio *bio)
+void bio_init(struct bio *bio)
{
bio->bi_next = NULL;
+ bio->bi_bdev = NULL;
bio->bi_flags = 1 << BIO_UPTODATE;
bio->bi_rw = 0;
bio->bi_vcnt = 0;
* allocate bio and iovecs from the memory pools specified by the
* bio_set structure.
**/
-struct bio *bio_alloc_bioset(unsigned int __nocast gfp_mask, int nr_iovecs, struct bio_set *bs)
+struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
{
struct bio *bio = mempool_alloc(bs->bio_pool, gfp_mask);
bio->bi_max_vecs = bvec_slabs[idx].nr_vecs;
}
bio->bi_io_vec = bvl;
- bio->bi_destructor = bio_destructor;
- bio->bi_set = bs;
}
out:
return bio;
}
-struct bio *bio_alloc(unsigned int __nocast gfp_mask, int nr_iovecs)
+struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs)
{
- return bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
+ struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
+
+ if (bio)
+ bio->bi_destructor = bio_fs_destructor;
+
+ return bio;
}
void zero_fill_bio(struct bio *bio)
* the actual data it points to. Reference count of returned
* bio will be one.
*/
-inline void __bio_clone(struct bio *bio, struct bio *bio_src)
+void __bio_clone(struct bio *bio, struct bio *bio_src)
{
request_queue_t *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));
+ memcpy(bio->bi_io_vec, bio_src->bi_io_vec,
+ bio_src->bi_max_vecs * sizeof(struct bio_vec));
bio->bi_sector = bio_src->bi_sector;
bio->bi_bdev = bio_src->bi_bdev;
bio->bi_flags |= 1 << BIO_CLONED;
bio->bi_rw = bio_src->bi_rw;
-
- /*
- * notes -- maybe just leave bi_idx alone. assume identical mapping
- * for the clone
- */
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);
}
*
* Like __bio_clone, only also allocates the returned bio
*/
-struct bio *bio_clone(struct bio *bio, unsigned int __nocast gfp_mask)
+struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
{
struct bio *b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, fs_bio_set);
- if (b)
+ if (b) {
+ b->bi_destructor = bio_fs_destructor;
__bio_clone(b, bio);
+ }
return b;
}
}
static int __bio_add_page(request_queue_t *q, struct bio *bio, struct page
- *page, unsigned int len, unsigned int offset)
+ *page, unsigned int len, unsigned int offset,
+ unsigned short max_sectors)
{
int retried_segments = 0;
struct bio_vec *bvec;
if (unlikely(bio_flagged(bio, BIO_CLONED)))
return 0;
- if (bio->bi_vcnt >= bio->bi_max_vecs)
+ if (((bio->bi_size + len) >> 9) > max_sectors)
return 0;
- if (((bio->bi_size + len) >> 9) > q->max_sectors)
+ /*
+ * For filesystems with a blocksize smaller than the pagesize
+ * we will often be called with the same page as last time and
+ * a consecutive offset. Optimize this special case.
+ */
+ if (bio->bi_vcnt > 0) {
+ struct bio_vec *prev = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+ if (page == prev->bv_page &&
+ offset == prev->bv_offset + prev->bv_len) {
+ prev->bv_len += len;
+ if (q->merge_bvec_fn &&
+ q->merge_bvec_fn(q, bio, prev) < len) {
+ prev->bv_len -= len;
+ return 0;
+ }
+
+ goto done;
+ }
+ }
+
+ if (bio->bi_vcnt >= bio->bi_max_vecs)
return 0;
/*
bio->bi_vcnt++;
bio->bi_phys_segments++;
bio->bi_hw_segments++;
+ done:
bio->bi_size += len;
return len;
}
+/**
+ * bio_add_pc_page - attempt to add page to bio
+ * @q: the target queue
+ * @bio: destination bio
+ * @page: page to add
+ * @len: vec entry length
+ * @offset: vec entry offset
+ *
+ * Attempt to add a page to the bio_vec maplist. This can fail for a
+ * number of reasons, such as the bio being full or target block
+ * device limitations. The target block device must allow bio's
+ * smaller than PAGE_SIZE, so it is always possible to add a single
+ * page to an empty bio. This should only be used by REQ_PC bios.
+ */
+int bio_add_pc_page(request_queue_t *q, struct bio *bio, struct page *page,
+ unsigned int len, unsigned int offset)
+{
+ return __bio_add_page(q, bio, page, len, offset, q->max_hw_sectors);
+}
+
/**
* bio_add_page - attempt to add page to bio
* @bio: destination bio
int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
unsigned int offset)
{
- return __bio_add_page(bdev_get_queue(bio->bi_bdev), bio, page,
- len, offset);
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+ return __bio_add_page(q, bio, page, len, offset, q->max_sectors);
}
struct bio_map_data {
break;
}
- if (__bio_add_page(q, bio, page, bytes, 0) < bytes) {
+ if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes) {
ret = -EINVAL;
break;
}
return ERR_PTR(ret);
}
-static struct bio *__bio_map_user(request_queue_t *q, struct block_device *bdev,
- unsigned long uaddr, unsigned int len,
- int write_to_vm)
+static struct bio *__bio_map_user_iov(request_queue_t *q,
+ struct block_device *bdev,
+ 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;
- const int nr_pages = end - start;
- int ret, offset, i;
+ int i, j;
+ int nr_pages = 0;
struct page **pages;
struct bio *bio;
+ int cur_page = 0;
+ int ret, offset;
- /*
- * transfer and buffer must be aligned to at least hardsector
- * size for now, in the future we can relax this restriction
- */
- if ((uaddr & queue_dma_alignment(q)) || (len & queue_dma_alignment(q)))
+ for (i = 0; i < iov_count; i++) {
+ unsigned long uaddr = (unsigned long)iov[i].iov_base;
+ unsigned long len = iov[i].iov_len;
+ unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ unsigned long start = uaddr >> PAGE_SHIFT;
+
+ nr_pages += end - start;
+ /*
+ * transfer and buffer must be aligned to at least hardsector
+ * size for now, in the future we can relax this restriction
+ */
+ if ((uaddr & queue_dma_alignment(q)) || (len & queue_dma_alignment(q)))
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (!nr_pages)
return ERR_PTR(-EINVAL);
bio = bio_alloc(GFP_KERNEL, nr_pages);
return ERR_PTR(-ENOMEM);
ret = -ENOMEM;
- pages = kmalloc(nr_pages * sizeof(struct page *), GFP_KERNEL);
+ pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
if (!pages)
goto out;
- down_read(¤t->mm->mmap_sem);
- ret = get_user_pages(current, current->mm, uaddr, nr_pages,
- write_to_vm, 0, pages, NULL);
- up_read(¤t->mm->mmap_sem);
-
- if (ret < nr_pages)
- goto out;
-
- bio->bi_bdev = bdev;
-
- offset = uaddr & ~PAGE_MASK;
- for (i = 0; i < nr_pages; i++) {
- unsigned int bytes = PAGE_SIZE - offset;
-
- if (len <= 0)
- break;
+ for (i = 0; i < iov_count; i++) {
+ unsigned long uaddr = (unsigned long)iov[i].iov_base;
+ unsigned long len = iov[i].iov_len;
+ unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ unsigned long start = uaddr >> PAGE_SHIFT;
+ const int local_nr_pages = end - start;
+ const int page_limit = cur_page + local_nr_pages;
+
+ down_read(¤t->mm->mmap_sem);
+ ret = get_user_pages(current, current->mm, uaddr,
+ local_nr_pages,
+ write_to_vm, 0, &pages[cur_page], NULL);
+ up_read(¤t->mm->mmap_sem);
+
+ if (ret < local_nr_pages) {
+ ret = -EFAULT;
+ goto out_unmap;
+ }
- if (bytes > len)
- bytes = len;
+ offset = uaddr & ~PAGE_MASK;
+ for (j = cur_page; j < page_limit; j++) {
+ unsigned int bytes = PAGE_SIZE - offset;
+
+ if (len <= 0)
+ break;
+
+ if (bytes > len)
+ bytes = len;
+
+ /*
+ * sorry...
+ */
+ if (bio_add_pc_page(q, bio, pages[j], bytes, offset) <
+ bytes)
+ break;
+
+ len -= bytes;
+ offset = 0;
+ }
+ cur_page = j;
/*
- * sorry...
+ * release the pages we didn't map into the bio, if any
*/
- if (__bio_add_page(q, bio, pages[i], bytes, offset) < bytes)
- break;
-
- len -= bytes;
- offset = 0;
+ while (j < page_limit)
+ page_cache_release(pages[j++]);
}
- /*
- * release the pages we didn't map into the bio, if any
- */
- while (i < nr_pages)
- page_cache_release(pages[i++]);
-
kfree(pages);
/*
if (!write_to_vm)
bio->bi_rw |= (1 << BIO_RW);
+ bio->bi_bdev = bdev;
bio->bi_flags |= (1 << BIO_USER_MAPPED);
return bio;
-out:
+
+ out_unmap:
+ for (i = 0; i < nr_pages; i++) {
+ if(!pages[i])
+ break;
+ page_cache_release(pages[i]);
+ }
+ out:
kfree(pages);
bio_put(bio);
return ERR_PTR(ret);
*/
struct bio *bio_map_user(request_queue_t *q, struct block_device *bdev,
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_map_user_iov(q, bdev, &iov, 1, write_to_vm);
+}
+
+/**
+ * bio_map_user_iov - map user sg_iovec table into bio
+ * @q: the request_queue_t for the bio
+ * @bdev: destination block device
+ * @iov: the iovec.
+ * @iov_count: number of elements in the iovec
+ * @write_to_vm: bool indicating writing to pages or not
+ *
+ * Map the user space address into a bio suitable for io to a block
+ * device. Returns an error pointer in case of error.
+ */
+struct bio *bio_map_user_iov(request_queue_t *q, struct block_device *bdev,
+ struct sg_iovec *iov, int iov_count,
+ int write_to_vm)
{
struct bio *bio;
+ int len = 0, i;
- bio = __bio_map_user(q, bdev, uaddr, len, write_to_vm);
+ bio = __bio_map_user_iov(q, bdev, iov, iov_count, write_to_vm);
if (IS_ERR(bio))
return bio;
*/
bio_get(bio);
+ for (i = 0; i < iov_count; i++)
+ len += iov[i].iov_len;
+
if (bio->bi_size == len)
return bio;
bio_put(bio);
}
+static int bio_map_kern_endio(struct bio *bio, unsigned int bytes_done, int err)
+{
+ if (bio->bi_size)
+ return 1;
+
+ bio_put(bio);
+ return 0;
+}
+
+
+static struct bio *__bio_map_kern(request_queue_t *q, void *data,
+ unsigned int len, gfp_t gfp_mask)
+{
+ unsigned long kaddr = (unsigned long)data;
+ unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ unsigned long start = kaddr >> PAGE_SHIFT;
+ const int nr_pages = end - start;
+ int offset, i;
+ struct bio *bio;
+
+ bio = bio_alloc(gfp_mask, nr_pages);
+ if (!bio)
+ return ERR_PTR(-ENOMEM);
+
+ offset = offset_in_page(kaddr);
+ for (i = 0; i < nr_pages; i++) {
+ unsigned int bytes = PAGE_SIZE - offset;
+
+ if (len <= 0)
+ break;
+
+ if (bytes > len)
+ bytes = len;
+
+ if (bio_add_pc_page(q, bio, virt_to_page(data), bytes,
+ offset) < bytes)
+ break;
+
+ data += bytes;
+ len -= bytes;
+ offset = 0;
+ }
+
+ bio->bi_end_io = bio_map_kern_endio;
+ return bio;
+}
+
+/**
+ * bio_map_kern - map kernel address into bio
+ * @q: the request_queue_t for the bio
+ * @data: pointer to buffer to map
+ * @len: length in bytes
+ * @gfp_mask: allocation flags for bio allocation
+ *
+ * Map the kernel address into a bio suitable for io to a block
+ * device. Returns an error pointer in case of error.
+ */
+struct bio *bio_map_kern(request_queue_t *q, void *data, unsigned int len,
+ gfp_t gfp_mask)
+{
+ struct bio *bio;
+
+ bio = __bio_map_kern(q, data, len, gfp_mask);
+ if (IS_ERR(bio))
+ return bio;
+
+ if (bio->bi_size == len)
+ return bio;
+
+ /*
+ * Don't support partial mappings.
+ */
+ bio_put(bio);
+ return ERR_PTR(-EINVAL);
+}
+
/*
* bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
* for performing direct-IO in BIOs.
if (!bp)
return bp;
+ blk_add_trace_pdu_int(bdev_get_queue(bi->bi_bdev), BLK_TA_SPLIT, bi,
+ bi->bi_sector + first_sectors);
+
BUG_ON(bi->bi_vcnt != 1);
BUG_ON(bi->bi_idx != 0);
atomic_set(&bp->cnt, 3);
bp->bio1.bi_io_vec = &bp->bv1;
bp->bio2.bi_io_vec = &bp->bv2;
+ bp->bio1.bi_max_vecs = 1;
+ bp->bio2.bi_max_vecs = 1;
+
bp->bio1.bi_end_io = bio_pair_end_1;
bp->bio2.bi_end_io = bio_pair_end_2;
return bp;
}
-static void *bio_pair_alloc(unsigned int __nocast gfp_flags, void *data)
-{
- return kmalloc(sizeof(struct bio_pair), gfp_flags);
-}
-
-static void bio_pair_free(void *bp, void *data)
-{
- kfree(bp);
-}
-
/*
* create memory pools for biovec's in a bio_set.
if (i >= scale)
pool_entries >>= 1;
- *bvp = mempool_create(pool_entries, mempool_alloc_slab,
- mempool_free_slab, bp->slab);
+ *bvp = mempool_create_slab_pool(pool_entries, bp->slab);
if (!*bvp)
return -ENOMEM;
}
struct bio_set *bioset_create(int bio_pool_size, int bvec_pool_size, int scale)
{
- struct bio_set *bs = kmalloc(sizeof(*bs), GFP_KERNEL);
+ struct bio_set *bs = kzalloc(sizeof(*bs), GFP_KERNEL);
if (!bs)
return NULL;
- memset(bs, 0, sizeof(*bs));
- bs->bio_pool = mempool_create(bio_pool_size, mempool_alloc_slab,
- mempool_free_slab, bio_slab);
-
+ bs->bio_pool = mempool_create_slab_pool(bio_pool_size, bio_slab);
if (!bs->bio_pool)
goto bad;
scale = 4;
/*
- * scale number of entries
+ * Limit number of entries reserved -- mempools are only used when
+ * the system is completely unable to allocate memory, so we only
+ * need enough to make progress.
*/
- bvec_pool_entries = megabytes * 2;
- if (bvec_pool_entries > 256)
- bvec_pool_entries = 256;
+ bvec_pool_entries = 1 + scale;
fs_bio_set = bioset_create(BIO_POOL_SIZE, bvec_pool_entries, scale);
if (!fs_bio_set)
panic("bio: can't allocate bios\n");
- bio_split_pool = mempool_create(BIO_SPLIT_ENTRIES,
- bio_pair_alloc, bio_pair_free, NULL);
+ bio_split_pool = mempool_create_kmalloc_pool(BIO_SPLIT_ENTRIES,
+ sizeof(struct bio_pair));
if (!bio_split_pool)
panic("bio: can't create split pool\n");
EXPORT_SYMBOL(bio_alloc);
EXPORT_SYMBOL(bio_put);
+EXPORT_SYMBOL(bio_free);
EXPORT_SYMBOL(bio_endio);
EXPORT_SYMBOL(bio_init);
EXPORT_SYMBOL(__bio_clone);
EXPORT_SYMBOL(bio_phys_segments);
EXPORT_SYMBOL(bio_hw_segments);
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);
EXPORT_SYMBOL(bio_split_pool);
git://git.onelab.eu / linux-2.6.git / blobdiff