1 files changed, 77 insertions, 260 deletions

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index e73d8ed34235..10912988c8f5 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -7,20 +7,12 @@
  */
 
 #include <linux/blk-integrity.h>
-#include <linux/mempool.h>
-#include <linux/export.h>
-#include <linux/bio.h>
-#include <linux/workqueue.h>
-#include <linux/slab.h>
 #include "blk.h"
 
-static struct kmem_cache *bip_slab;
-static struct workqueue_struct *kintegrityd_wq;
-
-void blk_flush_integrity(void)
-{
-	flush_workqueue(kintegrityd_wq);
-}
+struct bio_integrity_alloc {
+	struct bio_integrity_payload	bip;
+	struct bio_vec			bvecs[];
+};
 
 /**
  * bio_integrity_free - Free bio integrity payload
@@ -30,21 +22,23 @@ void blk_flush_integrity(void)
  */
 void bio_integrity_free(struct bio *bio)
 {
-	struct bio_integrity_payload *bip = bio_integrity(bio);
-	struct bio_set *bs = bio->bi_pool;
-
-	if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
-		if (bip->bip_vec)
-			bvec_free(&bs->bvec_integrity_pool, bip->bip_vec,
-				  bip->bip_max_vcnt);
-		mempool_free(bip, &bs->bio_integrity_pool);
-	} else {
-		kfree(bip);
-	}
+	kfree(bio_integrity(bio));
 	bio->bi_integrity = NULL;
 	bio->bi_opf &= ~REQ_INTEGRITY;
 }
 
+void bio_integrity_init(struct bio *bio, struct bio_integrity_payload *bip,
+		struct bio_vec *bvecs, unsigned int nr_vecs)
+{
+	memset(bip, 0, sizeof(*bip));
+	bip->bip_max_vcnt = nr_vecs;
+	if (nr_vecs)
+		bip->bip_vec = bvecs;
+
+	bio->bi_integrity = bip;
+	bio->bi_opf |= REQ_INTEGRITY;
+}
+
 /**
  * bio_integrity_alloc - Allocate integrity payload and attach it to bio
  * @bio:	bio to attach integrity metadata to
@@ -59,61 +53,25 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 						  gfp_t gfp_mask,
 						  unsigned int nr_vecs)
 {
-	struct bio_integrity_payload *bip;
-	struct bio_set *bs = bio->bi_pool;
-	unsigned inline_vecs;
+	struct bio_integrity_alloc *bia;
 
 	if (WARN_ON_ONCE(bio_has_crypt_ctx(bio)))
 		return ERR_PTR(-EOPNOTSUPP);
 
-	if (!bs || !mempool_initialized(&bs->bio_integrity_pool)) {
-		bip = kmalloc(struct_size(bip, bip_inline_vecs, nr_vecs), gfp_mask);
-		inline_vecs = nr_vecs;
-	} else {
-		bip = mempool_alloc(&bs->bio_integrity_pool, gfp_mask);
-		inline_vecs = BIO_INLINE_VECS;
-	}
-
-	if (unlikely(!bip))
+	bia = kmalloc(struct_size(bia, bvecs, nr_vecs), gfp_mask);
+	if (unlikely(!bia))
 		return ERR_PTR(-ENOMEM);
-
-	memset(bip, 0, sizeof(*bip));
-
-	/* always report as many vecs as asked explicitly, not inline vecs */
-	bip->bip_max_vcnt = nr_vecs;
-	if (nr_vecs > inline_vecs) {
-		bip->bip_vec = bvec_alloc(&bs->bvec_integrity_pool,
-					  &bip->bip_max_vcnt, gfp_mask);
-		if (!bip->bip_vec)
-			goto err;
-	} else if (nr_vecs) {
-		bip->bip_vec = bip->bip_inline_vecs;
-	}
-
-	bip->bip_bio = bio;
-	bio->bi_integrity = bip;
-	bio->bi_opf |= REQ_INTEGRITY;
-
-	return bip;
-err:
-	if (bs && mempool_initialized(&bs->bio_integrity_pool))
-		mempool_free(bip, &bs->bio_integrity_pool);
-	else
-		kfree(bip);
-	return ERR_PTR(-ENOMEM);
+	bio_integrity_init(bio, &bia->bip, bia->bvecs, nr_vecs);
+	return &bia->bip;
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
 
-static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs,
-				     bool dirty)
+static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs)
 {
 	int i;
 
-	for (i = 0; i < nr_vecs; i++) {
-		if (dirty && !PageCompound(bv[i].bv_page))
-			set_page_dirty_lock(bv[i].bv_page);
+	for (i = 0; i < nr_vecs; i++)
 		unpin_user_page(bv[i].bv_page);
-	}
 }
 
 static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
@@ -129,7 +87,7 @@ static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
 	ret = copy_to_iter(bvec_virt(bounce_bvec), bytes, &orig_iter);
 	WARN_ON_ONCE(ret != bytes);
 
-	bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs, true);
+	bio_integrity_unpin_bvec(orig_bvecs, orig_nr_vecs);
 }
 
 /**
@@ -149,8 +107,7 @@ void bio_integrity_unmap_user(struct bio *bio)
 		return;
 	}
 
-	bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt,
-			bio_data_dir(bio) == READ);
+	bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt);
 }
 
 /**
@@ -170,10 +127,8 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 
 	if (bip->bip_vcnt > 0) {
 		struct bio_vec *bv = &bip->bip_vec[bip->bip_vcnt - 1];
-		bool same_page = false;
 
-		if (bvec_try_merge_hw_page(q, bv, page, len, offset,
-					   &same_page)) {
+		if (bvec_try_merge_hw_page(q, bv, page, len, offset)) {
 			bip->bip_iter.bi_size += len;
 			return len;
 		}
@@ -199,10 +154,9 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 EXPORT_SYMBOL(bio_integrity_add_page);
 
 static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
-				   int nr_vecs, unsigned int len,
-				   unsigned int direction)
+				   int nr_vecs, unsigned int len)
 {
-	bool write = direction == ITER_SOURCE;
+	bool write = op_is_write(bio_op(bio));
 	struct bio_integrity_payload *bip;
 	struct iov_iter iter;
 	void *buf;
@@ -213,7 +167,7 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
 		return -ENOMEM;
 
 	if (write) {
-		iov_iter_bvec(&iter, direction, bvec, nr_vecs, len);
+		iov_iter_bvec(&iter, ITER_SOURCE, bvec, nr_vecs, len);
 		if (!copy_from_iter_full(buf, len, &iter)) {
 			ret = -EFAULT;
 			goto free_buf;
@@ -236,7 +190,7 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
 	}
 
 	if (write)
-		bio_integrity_unpin_bvec(bvec, nr_vecs, false);
+		bio_integrity_unpin_bvec(bvec, nr_vecs);
 	else
 		memcpy(&bip->bip_vec[1], bvec, nr_vecs * sizeof(*bvec));
 
@@ -302,16 +256,15 @@ static unsigned int bvec_from_pages(struct bio_vec *bvec, struct page **pages,
 	return nr_bvecs;
 }
 
-int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes)
+int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	unsigned int align = blk_lim_dma_alignment_and_pad(&q->limits);
 	struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages;
 	struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec;
-	unsigned int direction, nr_bvecs;
-	struct iov_iter iter;
+	size_t offset, bytes = iter->count;
+	unsigned int nr_bvecs;
 	int ret, nr_vecs;
-	size_t offset;
 	bool copy;
 
 	if (bio_integrity(bio))
@@ -319,13 +272,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes)
 	if (bytes >> SECTOR_SHIFT > queue_max_hw_sectors(q))
 		return -E2BIG;
 
-	if (bio_data_dir(bio) == READ)
-		direction = ITER_DEST;
-	else
-		direction = ITER_SOURCE;
-
-	iov_iter_ubuf(&iter, direction, ubuf, bytes);
-	nr_vecs = iov_iter_npages(&iter, BIO_MAX_VECS + 1);
+	nr_vecs = iov_iter_npages(iter, BIO_MAX_VECS + 1);
 	if (nr_vecs > BIO_MAX_VECS)
 		return -E2BIG;
 	if (nr_vecs > UIO_FASTIOV) {
@@ -335,8 +282,8 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes)
 		pages = NULL;
 	}
 
-	copy = !iov_iter_is_aligned(&iter, align, align);
-	ret = iov_iter_extract_pages(&iter, &pages, bytes, nr_vecs, 0, &offset);
+	copy = !iov_iter_is_aligned(iter, align, align);
+	ret = iov_iter_extract_pages(iter, &pages, bytes, nr_vecs, 0, &offset);
 	if (unlikely(ret < 0))
 		goto free_bvec;
 
@@ -347,8 +294,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes)
 		copy = true;
 
 	if (copy)
-		ret = bio_integrity_copy_user(bio, bvec, nr_bvecs, bytes,
-					      direction);
+		ret = bio_integrity_copy_user(bio, bvec, nr_bvecs, bytes);
 	else
 		ret = bio_integrity_init_user(bio, bvec, nr_bvecs, bytes);
 	if (ret)
@@ -359,149 +305,60 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes)
 	return 0;
 
 release_pages:
-	bio_integrity_unpin_bvec(bvec, nr_bvecs, false);
+	bio_integrity_unpin_bvec(bvec, nr_bvecs);
 free_bvec:
 	if (bvec != stack_vec)
 		kfree(bvec);
 	return ret;
 }
 
-/**
- * bio_integrity_prep - Prepare bio for integrity I/O
- * @bio:	bio to prepare
- *
- * Description:  Checks if the bio already has an integrity payload attached.
- * If it does, the payload has been generated by another kernel subsystem,
- * and we just pass it through. Otherwise allocates integrity payload.
- * The bio must have data direction, target device and start sector set priot
- * to calling.  In the WRITE case, integrity metadata will be generated using
- * the block device's integrity function.  In the READ case, the buffer
- * will be prepared for DMA and a suitable end_io handler set up.
- */
-bool bio_integrity_prep(struct bio *bio)
+static void bio_uio_meta_to_bip(struct bio *bio, struct uio_meta *meta)
 {
-	struct bio_integrity_payload *bip;
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
-	unsigned int len;
-	void *buf;
-	gfp_t gfp = GFP_NOIO;
-
-	if (!bi)
-		return true;
-
-	if (!bio_sectors(bio))
-		return true;
-
-	/* Already protected? */
-	if (bio_integrity(bio))
-		return true;
-
-	switch (bio_op(bio)) {
-	case REQ_OP_READ:
-		if (bi->flags & BLK_INTEGRITY_NOVERIFY)
-			return true;
-		break;
-	case REQ_OP_WRITE:
-		if (bi->flags & BLK_INTEGRITY_NOGENERATE)
-			return true;
-
-		/*
-		 * Zero the memory allocated to not leak uninitialized kernel
-		 * memory to disk for non-integrity metadata where nothing else
-		 * initializes the memory.
-		 */
-		if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
-			gfp |= __GFP_ZERO;
-		break;
-	default:
-		return true;
-	}
-
-	/* Allocate kernel buffer for protection data */
-	len = bio_integrity_bytes(bi, bio_sectors(bio));
-	buf = kmalloc(len, gfp);
-	if (unlikely(buf == NULL)) {
-		goto err_end_io;
-	}
-
-	bip = bio_integrity_alloc(bio, GFP_NOIO, 1);
-	if (IS_ERR(bip)) {
-		kfree(buf);
-		goto err_end_io;
-	}
-
-	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
-	bip_set_seed(bip, bio->bi_iter.bi_sector);
-
-	if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
-		bip->bip_flags |= BIP_IP_CHECKSUM;
-
-	if (bio_integrity_add_page(bio, virt_to_page(buf), len,
-			offset_in_page(buf)) < len) {
-		printk(KERN_ERR "could not attach integrity payload\n");
-		goto err_end_io;
-	}
+	struct bio_integrity_payload *bip = bio_integrity(bio);
 
-	/* Auto-generate integrity metadata if this is a write */
-	if (bio_data_dir(bio) == WRITE)
-		blk_integrity_generate(bio);
-	else
-		bip->bio_iter = bio->bi_iter;
-	return true;
+	if (meta->flags & IO_INTEGRITY_CHK_GUARD)
+		bip->bip_flags |= BIP_CHECK_GUARD;
+	if (meta->flags & IO_INTEGRITY_CHK_APPTAG)
+		bip->bip_flags |= BIP_CHECK_APPTAG;
+	if (meta->flags & IO_INTEGRITY_CHK_REFTAG)
+		bip->bip_flags |= BIP_CHECK_REFTAG;
 
-err_end_io:
-	bio->bi_status = BLK_STS_RESOURCE;
-	bio_endio(bio);
-	return false;
+	bip->app_tag = meta->app_tag;
 }
-EXPORT_SYMBOL(bio_integrity_prep);
 
-/**
- * bio_integrity_verify_fn - Integrity I/O completion worker
- * @work:	Work struct stored in bio to be verified
- *
- * Description: This workqueue function is called to complete a READ
- * request.  The function verifies the transferred integrity metadata
- * and then calls the original bio end_io function.
- */
-static void bio_integrity_verify_fn(struct work_struct *work)
+int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta)
 {
-	struct bio_integrity_payload *bip =
-		container_of(work, struct bio_integrity_payload, bip_work);
-	struct bio *bio = bip->bip_bio;
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	unsigned int integrity_bytes;
+	int ret;
+	struct iov_iter it;
 
-	blk_integrity_verify(bio);
+	if (!bi)
+		return -EINVAL;
+	/*
+	 * original meta iterator can be bigger.
+	 * process integrity info corresponding to current data buffer only.
+	 */
+	it = meta->iter;
+	integrity_bytes = bio_integrity_bytes(bi, bio_sectors(bio));
+	if (it.count < integrity_bytes)
+		return -EINVAL;
 
-	kfree(bvec_virt(bip->bip_vec));
-	bio_integrity_free(bio);
-	bio_endio(bio);
-}
+	/* should fit into two bytes */
+	BUILD_BUG_ON(IO_INTEGRITY_VALID_FLAGS >= (1 << 16));
 
-/**
- * __bio_integrity_endio - Integrity I/O completion function
- * @bio:	Protected bio
- *
- * Description: Completion for integrity I/O
- *
- * Normally I/O completion is done in interrupt context.  However,
- * verifying I/O integrity is a time-consuming task which must be run
- * in process context.	This function postpones completion
- * accordingly.
- */
-bool __bio_integrity_endio(struct bio *bio)
-{
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
-	struct bio_integrity_payload *bip = bio_integrity(bio);
+	if (meta->flags && (meta->flags & ~IO_INTEGRITY_VALID_FLAGS))
+		return -EINVAL;
 
-	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && bi->csum_type) {
-		INIT_WORK(&bip->bip_work, bio_integrity_verify_fn);
-		queue_work(kintegrityd_wq, &bip->bip_work);
-		return false;
+	it.count = integrity_bytes;
+	ret = bio_integrity_map_user(bio, &it);
+	if (!ret) {
+		bio_uio_meta_to_bip(bio, meta);
+		bip_set_seed(bio_integrity(bio), meta->seed);
+		iov_iter_advance(&meta->iter, integrity_bytes);
+		meta->seed += bio_integrity_intervals(bi, bio_sectors(bio));
 	}
-
-	kfree(bvec_virt(bip->bip_vec));
-	bio_integrity_free(bio);
-	return true;
+	return ret;
 }
 
 /**
@@ -560,48 +417,8 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 
 	bip->bip_vec = bip_src->bip_vec;
 	bip->bip_iter = bip_src->bip_iter;
-	bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY;
+	bip->bip_flags = bip_src->bip_flags & BIP_CLONE_FLAGS;
+	bip->app_tag = bip_src->app_tag;
 
 	return 0;
 }
-
-int bioset_integrity_create(struct bio_set *bs, int pool_size)
-{
-	if (mempool_initialized(&bs->bio_integrity_pool))
-		return 0;
-
-	if (mempool_init_slab_pool(&bs->bio_integrity_pool,
-				   pool_size, bip_slab))
-		return -1;
-
-	if (biovec_init_pool(&bs->bvec_integrity_pool, pool_size)) {
-		mempool_exit(&bs->bio_integrity_pool);
-		return -1;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(bioset_integrity_create);
-
-void bioset_integrity_free(struct bio_set *bs)
-{
-	mempool_exit(&bs->bio_integrity_pool);
-	mempool_exit(&bs->bvec_integrity_pool);
-}
-
-void __init bio_integrity_init(void)
-{
-	/*
-	 * kintegrityd won't block much but may burn a lot of CPU cycles.
-	 * Make it highpri CPU intensive wq with max concurrency of 1.
-	 */
-	kintegrityd_wq = alloc_workqueue("kintegrityd", WQ_MEM_RECLAIM |
-					 WQ_HIGHPRI | WQ_CPU_INTENSIVE, 1);
-	if (!kintegrityd_wq)
-		panic("Failed to create kintegrityd\n");
-
-	bip_slab = kmem_cache_create("bio_integrity_payload",
-				     sizeof(struct bio_integrity_payload) +
-				     sizeof(struct bio_vec) * BIO_INLINE_VECS,
-				     0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
-}