1 files changed, 248 insertions, 160 deletions

diff --git a/fs/bio.c b/fs/bio.c
index 78562574cb52..77a55bcceedb 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -28,24 +28,9 @@
 #include <linux/blktrace_api.h>
 #include <scsi/sg.h>            /* for struct sg_iovec */
 
-#define BIO_POOL_SIZE 2
-
 static struct kmem_cache *bio_slab __read_mostly;
 
-#define BIOVEC_NR_POOLS 6
-
-/*
- * a small number of entries is fine, not going to be performance critical.
- * basically we just need to survive
- */
-#define BIO_SPLIT_ENTRIES 2
-mempool_t *bio_split_pool __read_mostly;
-
-struct biovec_slab {
-        int nr_vecs;
-        char *name; 
-        struct kmem_cache *slab;
-};
+static mempool_t *bio_split_pool __read_mostly;
 
 /*
  * if you change this list, also change bvec_alloc or things will
@@ -60,49 +45,61 @@ static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
 #undef BV
 
 /*
- * bio_set is used to allow other portions of the IO system to
- * allocate their own private memory pools for bio and iovec structures.
- * These memory pools in turn all allocate from the bio_slab
- * and the bvec_slabs[].
- */
-struct bio_set {
-        mempool_t *bio_pool;
-        mempool_t *bvec_pools[BIOVEC_NR_POOLS];
-};
-
-/*
  * fs_bio_set is the bio_set containing bio and iovec memory pools used by
  * IO code that does not need private memory pools.
  */
-static struct bio_set *fs_bio_set;
+struct bio_set *fs_bio_set;
+
+unsigned int bvec_nr_vecs(unsigned short idx)
+{
+        return bvec_slabs[idx].nr_vecs;
+}
 
-static inline struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct bio_set *bs)
+struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct bio_set *bs)
 {
         struct bio_vec *bvl;
 
         /*
-         * see comment near bvec_array define!
+         * If 'bs' is given, lookup the pool and do the mempool alloc.
+         * If not, this is a bio_kmalloc() allocation and just do a
+         * kzalloc() for the exact number of vecs right away.
          */
-        switch (nr) {
-                case   1        : *idx = 0; break;
-                case   2 ...   4: *idx = 1; break;
-                case   5 ...  16: *idx = 2; break;
-                case  17 ...  64: *idx = 3; break;
-                case  65 ... 128: *idx = 4; break;
-                case 129 ... BIO_MAX_PAGES: *idx = 5; break;
+        if (bs) {
+                /*
+                 * see comment near bvec_array define!
+                 */
+                switch (nr) {
+                case 1:
+                        *idx = 0;
+                        break;
+                case 2 ... 4:
+                        *idx = 1;
+                        break;
+                case 5 ... 16:
+                        *idx = 2;
+                        break;
+                case 17 ... 64:
+                        *idx = 3;
+                        break;
+                case 65 ... 128:
+                        *idx = 4;
+                        break;
+                case 129 ... BIO_MAX_PAGES:
+                        *idx = 5;
+                        break;
                 default:
                         return NULL;
-        }
-        /*
-         * idx now points to the pool we want to allocate from
-         */
-
-        bvl = mempool_alloc(bs->bvec_pools[*idx], gfp_mask);
-        if (bvl) {
-                struct biovec_slab *bp = bvec_slabs + *idx;
+                }
 
-                memset(bvl, 0, bp->nr_vecs * sizeof(struct bio_vec));
-        }
+                /*
+                 * idx now points to the pool we want to allocate from
+                 */
+                bvl = mempool_alloc(bs->bvec_pools[*idx], gfp_mask);
+                if (bvl)
+                        memset(bvl, 0,
+                                bvec_nr_vecs(*idx) * sizeof(struct bio_vec));
+        } else
+                bvl = kzalloc(nr * sizeof(struct bio_vec), gfp_mask);
 
         return bvl;
 }
@@ -117,6 +114,9 @@ void bio_free(struct bio *bio, struct bio_set *bio_set)
                 mempool_free(bio->bi_io_vec, bio_set->bvec_pools[pool_idx]);
         }
 
+        if (bio_integrity(bio))
+                bio_integrity_free(bio, bio_set);
+
         mempool_free(bio, bio_set->bio_pool);
 }
 
@@ -128,10 +128,17 @@ static void bio_fs_destructor(struct bio *bio)
         bio_free(bio, fs_bio_set);
 }
 
+static void bio_kmalloc_destructor(struct bio *bio)
+{
+        kfree(bio->bi_io_vec);
+        kfree(bio);
+}
+
 void bio_init(struct bio *bio)
 {
         memset(bio, 0, sizeof(*bio));
         bio->bi_flags = 1 << BIO_UPTODATE;
+        bio->bi_comp_cpu = -1;
         atomic_set(&bio->bi_cnt, 1);
 }
 
@@ -139,19 +146,25 @@ void bio_init(struct bio *bio)
  * bio_alloc_bioset - allocate a bio for I/O
  * @gfp_mask:   the GFP_ mask given to the slab allocator
  * @nr_iovecs:  number of iovecs to pre-allocate
- * @bs:         the bio_set to allocate from
+ * @bs:         the bio_set to allocate from. If %NULL, just use kmalloc
  *
  * Description:
- *   bio_alloc_bioset will first try it's on mempool to satisfy the allocation.
+ *   bio_alloc_bioset will first try its own mempool to satisfy the allocation.
  *   If %__GFP_WAIT is set then we will block on the internal pool waiting
- *   for a &struct bio to become free.
+ *   for a &struct bio to become free. If a %NULL @bs is passed in, we will
+ *   fall back to just using @kmalloc to allocate the required memory.
  *
  *   allocate bio and iovecs from the memory pools specified by the
- *   bio_set structure.
+ *   bio_set structure, or @kmalloc if none given.
  **/
 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);
+        struct bio *bio;
+
+        if (bs)
+                bio = mempool_alloc(bs->bio_pool, gfp_mask);
+        else
+                bio = kmalloc(sizeof(*bio), gfp_mask);
 
         if (likely(bio)) {
                 struct bio_vec *bvl = NULL;
@@ -162,12 +175,15 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 
                         bvl = bvec_alloc_bs(gfp_mask, nr_iovecs, &idx, bs);
                         if (unlikely(!bvl)) {
-                                mempool_free(bio, bs->bio_pool);
+                                if (bs)
+                                        mempool_free(bio, bs->bio_pool);
+                                else
+                                        kfree(bio);
                                 bio = NULL;
                                 goto out;
                         }
                         bio->bi_flags |= idx << BIO_POOL_OFFSET;
-                        bio->bi_max_vecs = bvec_slabs[idx].nr_vecs;
+                        bio->bi_max_vecs = bvec_nr_vecs(idx);
                 }
                 bio->bi_io_vec = bvl;
         }
@@ -185,6 +201,23 @@ struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs)
         return bio;
 }
 
+/*
+ * Like bio_alloc(), but doesn't use a mempool backing. This means that
+ * it CAN fail, but while bio_alloc() can only be used for allocations
+ * that have a short (finite) life span, bio_kmalloc() should be used
+ * for more permanent bio allocations (like allocating some bio's for
+ * initalization or setup purposes).
+ */
+struct bio *bio_kmalloc(gfp_t gfp_mask, int nr_iovecs)
+{
+        struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
+
+        if (bio)
+                bio->bi_destructor = bio_kmalloc_destructor;
+
+        return bio;
+}
+
 void zero_fill_bio(struct bio *bio)
 {
         unsigned long flags;
@@ -229,14 +262,6 @@ inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
         return bio->bi_phys_segments;
 }
 
-inline int bio_hw_segments(struct request_queue *q, struct bio *bio)
-{
-        if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
-                blk_recount_segments(q, bio);
-
-        return bio->bi_hw_segments;
-}
-
 /**
  *      __bio_clone     -       clone a bio
  *      @bio: destination bio
@@ -275,9 +300,19 @@ 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) {
-                b->bi_destructor = bio_fs_destructor;
-                __bio_clone(b, bio);
+        if (!b)
+                return NULL;
+
+        b->bi_destructor = bio_fs_destructor;
+        __bio_clone(b, bio);
+
+        if (bio_integrity(bio)) {
+                int ret;
+
+                ret = bio_integrity_clone(b, bio, fs_bio_set);
+
+                if (ret < 0)
+                        return NULL;
         }
 
         return b;
@@ -333,10 +368,19 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
                 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;
+
+                        if (q->merge_bvec_fn) {
+                                struct bvec_merge_data bvm = {
+                                        .bi_bdev = bio->bi_bdev,
+                                        .bi_sector = bio->bi_sector,
+                                        .bi_size = bio->bi_size,
+                                        .bi_rw = bio->bi_rw,
+                                };
+
+                                if (q->merge_bvec_fn(q, &bvm, prev) < len) {
+                                        prev->bv_len -= len;
+                                        return 0;
+                                }
                         }
 
                         goto done;
@@ -352,8 +396,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
          */
 
         while (bio->bi_phys_segments >= q->max_phys_segments
-               || bio->bi_hw_segments >= q->max_hw_segments
-               || BIOVEC_VIRT_OVERSIZE(bio->bi_size)) {
+               || bio->bi_phys_segments >= q->max_hw_segments) {
 
                 if (retried_segments)
                         return 0;
@@ -377,11 +420,18 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
          * queue to get further control
          */
         if (q->merge_bvec_fn) {
+                struct bvec_merge_data bvm = {
+                        .bi_bdev = bio->bi_bdev,
+                        .bi_sector = bio->bi_sector,
+                        .bi_size = bio->bi_size,
+                        .bi_rw = bio->bi_rw,
+                };
+
                 /*
                  * merge_bvec_fn() returns number of bytes it can accept
                  * at this offset
                  */
-                if (q->merge_bvec_fn(q, bio, bvec) < len) {
+                if (q->merge_bvec_fn(q, &bvm, bvec) < len) {
                         bvec->bv_page = NULL;
                         bvec->bv_len = 0;
                         bvec->bv_offset = 0;
@@ -390,13 +440,11 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
         }
 
         /* If we may be able to merge these biovecs, force a recount */
-        if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec) ||
-            BIOVEC_VIRT_MERGEABLE(bvec-1, bvec)))
+        if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
                 bio->bi_flags &= ~(1 << BIO_SEG_VALID);
 
         bio->bi_vcnt++;
         bio->bi_phys_segments++;
-        bio->bi_hw_segments++;
  done:
         bio->bi_size += len;
         return len;
@@ -444,16 +492,19 @@ int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
 
 struct bio_map_data {
         struct bio_vec *iovecs;
-        int nr_sgvecs;
         struct sg_iovec *sgvecs;
+        int nr_sgvecs;
+        int is_our_pages;
 };
 
 static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
-                             struct sg_iovec *iov, int iov_count)
+                             struct sg_iovec *iov, int iov_count,
+                             int is_our_pages)
 {
         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;
+        bmd->is_our_pages = is_our_pages;
         bio->bi_private = bmd;
 }
 
@@ -464,20 +515,21 @@ static void bio_free_map_data(struct bio_map_data *bmd)
         kfree(bmd);
 }
 
-static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count)
+static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count,
+                                               gfp_t gfp_mask)
 {
-        struct bio_map_data *bmd = kmalloc(sizeof(*bmd), GFP_KERNEL);
+        struct bio_map_data *bmd = kmalloc(sizeof(*bmd), gfp_mask);
 
         if (!bmd)
                 return NULL;
 
-        bmd->iovecs = kmalloc(sizeof(struct bio_vec) * nr_segs, GFP_KERNEL);
+        bmd->iovecs = kmalloc(sizeof(struct bio_vec) * nr_segs, gfp_mask);
         if (!bmd->iovecs) {
                 kfree(bmd);
                 return NULL;
         }
 
-        bmd->sgvecs = kmalloc(sizeof(struct sg_iovec) * iov_count, GFP_KERNEL);
+        bmd->sgvecs = kmalloc(sizeof(struct sg_iovec) * iov_count, gfp_mask);
         if (bmd->sgvecs)
                 return bmd;
 
@@ -486,8 +538,9 @@ static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count)
         return NULL;
 }
 
-static int __bio_copy_iov(struct bio *bio, struct sg_iovec *iov, int iov_count,
-                          int uncopy)
+static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
+                          struct sg_iovec *iov, int iov_count, int uncopy,
+                          int do_free_page)
 {
         int ret = 0, i;
         struct bio_vec *bvec;
@@ -497,7 +550,7 @@ static int __bio_copy_iov(struct bio *bio, struct sg_iovec *iov, int iov_count,
 
         __bio_for_each_segment(bvec, bio, i, 0) {
                 char *bv_addr = page_address(bvec->bv_page);
-                unsigned int bv_len = bvec->bv_len;
+                unsigned int bv_len = iovecs[i].bv_len;
 
                 while (bv_len && iov_idx < iov_count) {
                         unsigned int bytes;
@@ -530,7 +583,7 @@ static int __bio_copy_iov(struct bio *bio, struct sg_iovec *iov, int iov_count,
                         }
                 }
 
-                if (uncopy)
+                if (do_free_page)
                         __free_page(bvec->bv_page);
         }
 
@@ -547,10 +600,11 @@ static int __bio_copy_iov(struct bio *bio, struct sg_iovec *iov, int iov_count,
 int bio_uncopy_user(struct bio *bio)
 {
         struct bio_map_data *bmd = bio->bi_private;
-        int ret;
-
-        ret = __bio_copy_iov(bio, bmd->sgvecs, bmd->nr_sgvecs, 1);
+        int ret = 0;
 
+        if (!bio_flagged(bio, BIO_NULL_MAPPED))
+                ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
+                                     bmd->nr_sgvecs, 1, bmd->is_our_pages);
         bio_free_map_data(bmd);
         bio_put(bio);
         return ret;
@@ -559,16 +613,20 @@ int bio_uncopy_user(struct bio *bio)
 /**
  *      bio_copy_user_iov       -       copy user data to bio
  *      @q: destination block queue
+ *      @map_data: pointer to the rq_map_data holding pages (if necessary)
  *      @iov:   the iovec.
  *      @iov_count: number of elements in the iovec
  *      @write_to_vm: bool indicating writing to pages or not
+ *      @gfp_mask: memory allocation flags
  *
  *      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_iov(struct request_queue *q, struct sg_iovec *iov,
-                              int iov_count, int write_to_vm)
+struct bio *bio_copy_user_iov(struct request_queue *q,
+                              struct rq_map_data *map_data,
+                              struct sg_iovec *iov, int iov_count,
+                              int write_to_vm, gfp_t gfp_mask)
 {
         struct bio_map_data *bmd;
         struct bio_vec *bvec;
@@ -591,25 +649,38 @@ struct bio *bio_copy_user_iov(struct request_queue *q, struct sg_iovec *iov,
                 len += iov[i].iov_len;
         }
 
-        bmd = bio_alloc_map_data(nr_pages, iov_count);
+        bmd = bio_alloc_map_data(nr_pages, iov_count, gfp_mask);
         if (!bmd)
                 return ERR_PTR(-ENOMEM);
 
         ret = -ENOMEM;
-        bio = bio_alloc(GFP_KERNEL, nr_pages);
+        bio = bio_alloc(gfp_mask, nr_pages);
         if (!bio)
                 goto out_bmd;
 
         bio->bi_rw |= (!write_to_vm << BIO_RW);
 
         ret = 0;
+        i = 0;
         while (len) {
-                unsigned int bytes = PAGE_SIZE;
+                unsigned int bytes;
+
+                if (map_data)
+                        bytes = 1U << (PAGE_SHIFT + map_data->page_order);
+                else
+                        bytes = PAGE_SIZE;
 
                 if (bytes > len)
                         bytes = len;
 
-                page = alloc_page(q->bounce_gfp | GFP_KERNEL);
+                if (map_data) {
+                        if (i == map_data->nr_entries) {
+                                ret = -ENOMEM;
+                                break;
+                        }
+                        page = map_data->pages[i++];
+                } else
+                        page = alloc_page(q->bounce_gfp | gfp_mask);
                 if (!page) {
                         ret = -ENOMEM;
                         break;
@@ -628,16 +699,17 @@ struct bio *bio_copy_user_iov(struct request_queue *q, struct sg_iovec *iov,
          * success
          */
         if (!write_to_vm) {
-                ret = __bio_copy_iov(bio, iov, iov_count, 0);
+                ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 0);
                 if (ret)
                         goto cleanup;
         }
 
-        bio_set_map_data(bmd, bio, iov, iov_count);
+        bio_set_map_data(bmd, bio, iov, iov_count, map_data ? 0 : 1);
         return bio;
 cleanup:
-        bio_for_each_segment(bvec, bio, i)
-                __free_page(bvec->bv_page);
+        if (!map_data)
+                bio_for_each_segment(bvec, bio, i)
+                        __free_page(bvec->bv_page);
 
         bio_put(bio);
 out_bmd:
@@ -648,29 +720,32 @@ out_bmd:
 /**
  *      bio_copy_user   -       copy user data to bio
  *      @q: destination block queue
+ *      @map_data: pointer to the rq_map_data holding pages (if necessary)
  *      @uaddr: start of user address
  *      @len: length in bytes
  *      @write_to_vm: bool indicating writing to pages or not
+ *      @gfp_mask: memory allocation flags
  *
  *      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(struct request_queue *q, struct rq_map_data *map_data,
+                          unsigned long uaddr, unsigned int len,
+                          int write_to_vm, gfp_t gfp_mask)
 {
         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);
+        return bio_copy_user_iov(q, map_data, &iov, 1, write_to_vm, gfp_mask);
 }
 
 static struct bio *__bio_map_user_iov(struct request_queue *q,
                                       struct block_device *bdev,
                                       struct sg_iovec *iov, int iov_count,
-                                      int write_to_vm)
+                                      int write_to_vm, gfp_t gfp_mask)
 {
         int i, j;
         int nr_pages = 0;
@@ -696,12 +771,12 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
         if (!nr_pages)
                 return ERR_PTR(-EINVAL);
 
-        bio = bio_alloc(GFP_KERNEL, nr_pages);
+        bio = bio_alloc(gfp_mask, nr_pages);
         if (!bio)
                 return ERR_PTR(-ENOMEM);
 
         ret = -ENOMEM;
-        pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
+        pages = kcalloc(nr_pages, sizeof(struct page *), gfp_mask);
         if (!pages)
                 goto out;
 
@@ -713,12 +788,8 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
                 const int local_nr_pages = end - start;
                 const int page_limit = cur_page + local_nr_pages;
                 
-                down_read(&current->mm->mmap_sem);
-                ret = get_user_pages(current, current->mm, uaddr,
-                                     local_nr_pages,
-                                     write_to_vm, 0, &pages[cur_page], NULL);
-                up_read(&current->mm->mmap_sem);
-
+                ret = get_user_pages_fast(uaddr, local_nr_pages,
+                                write_to_vm, &pages[cur_page]);
                 if (ret < local_nr_pages) {
                         ret = -EFAULT;
                         goto out_unmap;
@@ -784,19 +855,21 @@ static struct bio *__bio_map_user_iov(struct request_queue *q,
  *      @uaddr: start of user address
  *      @len: length in bytes
  *      @write_to_vm: bool indicating writing to pages or not
+ *      @gfp_mask: memory allocation flags
  *
  *      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(struct request_queue *q, struct block_device *bdev,
-                         unsigned long uaddr, unsigned int len, int write_to_vm)
+                         unsigned long uaddr, unsigned int len, int write_to_vm,
+                         gfp_t gfp_mask)
 {
         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);
+        return bio_map_user_iov(q, bdev, &iov, 1, write_to_vm, gfp_mask);
 }
 
 /**
@@ -806,18 +879,19 @@ struct bio *bio_map_user(struct request_queue *q, struct block_device *bdev,
  *      @iov:   the iovec.
  *      @iov_count: number of elements in the iovec
  *      @write_to_vm: bool indicating writing to pages or not
+ *      @gfp_mask: memory allocation flags
  *
  *      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(struct request_queue *q, struct block_device *bdev,
                              struct sg_iovec *iov, int iov_count,
-                             int write_to_vm)
+                             int write_to_vm, gfp_t gfp_mask)
 {
         struct bio *bio;
 
-        bio = __bio_map_user_iov(q, bdev, iov, iov_count, write_to_vm);
-
+        bio = __bio_map_user_iov(q, bdev, iov, iov_count, write_to_vm,
+                                 gfp_mask);
         if (IS_ERR(bio))
                 return bio;
 
@@ -941,19 +1015,22 @@ static void bio_copy_kern_endio(struct bio *bio, int err)
 {
         struct bio_vec *bvec;
         const int read = bio_data_dir(bio) == READ;
-        char *p = bio->bi_private;
+        struct bio_map_data *bmd = bio->bi_private;
         int i;
+        char *p = bmd->sgvecs[0].iov_base;
 
         __bio_for_each_segment(bvec, bio, i, 0) {
                 char *addr = page_address(bvec->bv_page);
+                int len = bmd->iovecs[i].bv_len;
 
                 if (read && !err)
-                        memcpy(p, addr, bvec->bv_len);
+                        memcpy(p, addr, len);
 
                 __free_page(bvec->bv_page);
-                p += bvec->bv_len;
+                p += len;
         }
 
+        bio_free_map_data(bmd);
         bio_put(bio);
 }
 
@@ -971,38 +1048,13 @@ static void bio_copy_kern_endio(struct bio *bio, int err)
 struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
                           gfp_t gfp_mask, int reading)
 {
-        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;
         struct bio *bio;
         struct bio_vec *bvec;
-        int i, ret;
-
-        bio = bio_alloc(gfp_mask, nr_pages);
-        if (!bio)
-                return ERR_PTR(-ENOMEM);
-
-        while (len) {
-                struct page *page;
-                unsigned int bytes = PAGE_SIZE;
-
-                if (bytes > len)
-                        bytes = len;
-
-                page = alloc_page(q->bounce_gfp | gfp_mask);
-                if (!page) {
-                        ret = -ENOMEM;
-                        goto cleanup;
-                }
-
-                if (bio_add_pc_page(q, bio, page, bytes, 0) < bytes) {
-                        ret = -EINVAL;
-                        goto cleanup;
-                }
+        int i;
 
-                len -= bytes;
-        }
+        bio = bio_copy_user(q, NULL, (unsigned long)data, len, 1, gfp_mask);
+        if (IS_ERR(bio))
+                return bio;
 
         if (!reading) {
                 void *p = data;
@@ -1015,16 +1067,9 @@ struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
                 }
         }
 
-        bio->bi_private = data;
         bio->bi_end_io = bio_copy_kern_endio;
-        return bio;
-cleanup:
-        bio_for_each_segment(bvec, bio, i)
-                __free_page(bvec->bv_page);
-
-        bio_put(bio);
 
-        return ERR_PTR(ret);
+        return bio;
 }
 
 /*
@@ -1211,9 +1256,9 @@ static void bio_pair_end_2(struct bio *bi, int err)
  * split a bio - only worry about a bio with a single page
  * in it's iovec
  */
-struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
+struct bio_pair *bio_split(struct bio *bi, int first_sectors)
 {
-        struct bio_pair *bp = mempool_alloc(pool, GFP_NOIO);
+        struct bio_pair *bp = mempool_alloc(bio_split_pool, GFP_NOIO);
 
         if (!bp)
                 return bp;
@@ -1247,11 +1292,50 @@ struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
         bp->bio2.bi_end_io = bio_pair_end_2;
 
         bp->bio1.bi_private = bi;
-        bp->bio2.bi_private = pool;
+        bp->bio2.bi_private = bio_split_pool;
+
+        if (bio_integrity(bi))
+                bio_integrity_split(bi, bp, first_sectors);
 
         return bp;
 }
 
+/**
+ *      bio_sector_offset - Find hardware sector offset in bio
+ *      @bio:           bio to inspect
+ *      @index:         bio_vec index
+ *      @offset:        offset in bv_page
+ *
+ *      Return the number of hardware sectors between beginning of bio
+ *      and an end point indicated by a bio_vec index and an offset
+ *      within that vector's page.
+ */
+sector_t bio_sector_offset(struct bio *bio, unsigned short index,
+                           unsigned int offset)
+{
+        unsigned int sector_sz = queue_hardsect_size(bio->bi_bdev->bd_disk->queue);
+        struct bio_vec *bv;
+        sector_t sectors;
+        int i;
+
+        sectors = 0;
+
+        if (index >= bio->bi_idx)
+                index = bio->bi_vcnt - 1;
+
+        __bio_for_each_segment(bv, bio, i, 0) {
+                if (i == index) {
+                        if (offset > bv->bv_offset)
+                                sectors += (offset - bv->bv_offset) / sector_sz;
+                        break;
+                }
+
+                sectors += bv->bv_len / sector_sz;
+        }
+
+        return sectors;
+}
+EXPORT_SYMBOL(bio_sector_offset);
 
 /*
  * create memory pools for biovec's in a bio_set.
@@ -1290,6 +1374,7 @@ void bioset_free(struct bio_set *bs)
         if (bs->bio_pool)
                 mempool_destroy(bs->bio_pool);
 
+        bioset_integrity_free(bs);
         biovec_free_pools(bs);
 
         kfree(bs);
@@ -1306,6 +1391,9 @@ struct bio_set *bioset_create(int bio_pool_size, int bvec_pool_size)
         if (!bs->bio_pool)
                 goto bad;
 
+        if (bioset_integrity_create(bs, bio_pool_size))
+                goto bad;
+
         if (!biovec_create_pools(bs, bvec_pool_size))
                 return bs;
 
@@ -1332,6 +1420,7 @@ static int __init init_bio(void)
 {
         bio_slab = KMEM_CACHE(bio, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
 
+        bio_integrity_init_slab();
         biovec_init_slabs();
 
         fs_bio_set = bioset_create(BIO_POOL_SIZE, 2);
@@ -1349,6 +1438,7 @@ static int __init init_bio(void)
 subsys_initcall(init_bio);
 
 EXPORT_SYMBOL(bio_alloc);
+EXPORT_SYMBOL(bio_kmalloc);
 EXPORT_SYMBOL(bio_put);
 EXPORT_SYMBOL(bio_free);
 EXPORT_SYMBOL(bio_endio);
@@ -1356,7 +1446,6 @@ EXPORT_SYMBOL(bio_init);
 EXPORT_SYMBOL(__bio_clone);
 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);
@@ -1366,7 +1455,6 @@ EXPORT_SYMBOL(bio_map_kern);
 EXPORT_SYMBOL(bio_copy_kern);
 EXPORT_SYMBOL(bio_pair_release);
 EXPORT_SYMBOL(bio_split);
-EXPORT_SYMBOL(bio_split_pool);
 EXPORT_SYMBOL(bio_copy_user);
 EXPORT_SYMBOL(bio_uncopy_user);
 EXPORT_SYMBOL(bioset_create);