1 files changed, 289 insertions, 81 deletions

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index fb95dbb21dd8..c9a16fba58b9 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -6,7 +6,7 @@
  * Written by: Martin K. Petersen <martin.petersen@oracle.com>
  */
 
-#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
 #include <linux/mempool.h>
 #include <linux/export.h>
 #include <linux/bio.h>
@@ -14,8 +14,6 @@
 #include <linux/slab.h>
 #include "blk.h"
 
-#define BIP_INLINE_VECS	4
-
 static struct kmem_cache *bip_slab;
 static struct workqueue_struct *kintegrityd_wq;
 
@@ -24,6 +22,19 @@ void blk_flush_integrity(void)
 	flush_workqueue(kintegrityd_wq);
 }
 
+static void __bio_integrity_free(struct bio_set *bs,
+				 struct bio_integrity_payload *bip)
+{
+	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);
+	}
+}
+
 /**
  * bio_integrity_alloc - Allocate integrity payload and attach it to bio
  * @bio:	bio to attach integrity metadata to
@@ -42,12 +53,15 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 	struct bio_set *bs = bio->bi_pool;
 	unsigned inline_vecs;
 
+	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 = BIP_INLINE_VECS;
+		inline_vecs = BIO_INLINE_VECS;
 	}
 
 	if (unlikely(!bip))
@@ -55,18 +69,15 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 
 	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) {
-		unsigned long idx = 0;
-
-		bip->bip_vec = bvec_alloc(gfp_mask, nr_vecs, &idx,
-					  &bs->bvec_integrity_pool);
+		bip->bip_vec = bvec_alloc(&bs->bvec_integrity_pool,
+					  &bip->bip_max_vcnt, gfp_mask);
 		if (!bip->bip_vec)
 			goto err;
-		bip->bip_max_vcnt = bvec_nr_vecs(idx);
-		bip->bip_slab = idx;
 	} else {
 		bip->bip_vec = bip->bip_inline_vecs;
-		bip->bip_max_vcnt = inline_vecs;
 	}
 
 	bip->bip_bio = bio;
@@ -75,11 +86,52 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 
 	return bip;
 err:
-	mempool_free(bip, &bs->bio_integrity_pool);
+	__bio_integrity_free(bs, bip);
 	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
 
+static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs,
+				     bool dirty)
+{
+	int i;
+
+	for (i = 0; i < nr_vecs; i++) {
+		if (dirty && !PageCompound(bv[i].bv_page))
+			set_page_dirty_lock(bv[i].bv_page);
+		unpin_user_page(bv[i].bv_page);
+	}
+}
+
+static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
+{
+	unsigned short nr_vecs = bip->bip_max_vcnt - 1;
+	struct bio_vec *copy = &bip->bip_vec[1];
+	size_t bytes = bip->bip_iter.bi_size;
+	struct iov_iter iter;
+	int ret;
+
+	iov_iter_bvec(&iter, ITER_DEST, copy, nr_vecs, bytes);
+	ret = copy_to_iter(bvec_virt(bip->bip_vec), bytes, &iter);
+	WARN_ON_ONCE(ret != bytes);
+
+	bio_integrity_unpin_bvec(copy, nr_vecs, true);
+}
+
+static void bio_integrity_unmap_user(struct bio_integrity_payload *bip)
+{
+	bool dirty = bio_data_dir(bip->bip_bio) == READ;
+
+	if (bip->bip_flags & BIP_COPY_USER) {
+		if (dirty)
+			bio_integrity_uncopy_user(bip);
+		kfree(bvec_virt(bip->bip_vec));
+		return;
+	}
+
+	bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt, dirty);
+}
+
 /**
  * bio_integrity_free - Free bio integrity payload
  * @bio:	bio containing bip to be freed
@@ -87,23 +139,17 @@ EXPORT_SYMBOL(bio_integrity_alloc);
  * Description: Used to free the integrity portion of a bio. Usually
  * called from bio_free().
  */
-static void bio_integrity_free(struct bio *bio)
+void bio_integrity_free(struct bio *bio)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	struct bio_set *bs = bio->bi_pool;
 
 	if (bip->bip_flags & BIP_BLOCK_INTEGRITY)
-		kfree(page_address(bip->bip_vec->bv_page) +
-		      bip->bip_vec->bv_offset);
-
-	if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
-		bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab);
-
-		mempool_free(bip, &bs->bio_integrity_pool);
-	} else {
-		kfree(bip);
-	}
+		kfree(bvec_virt(bip->bip_vec));
+	else if (bip->bip_flags & BIP_INTEGRITY_USER)
+		bio_integrity_unmap_user(bip);
 
+	__bio_integrity_free(bs, bip);
 	bio->bi_integrity = NULL;
 	bio->bi_opf &= ~REQ_INTEGRITY;
 }
@@ -120,30 +166,214 @@ static void bio_integrity_free(struct bio *bio)
 int bio_integrity_add_page(struct bio *bio, struct page *page,
 			   unsigned int len, unsigned int offset)
 {
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	struct bio_integrity_payload *bip = bio_integrity(bio);
-	struct bio_vec *iv;
 
-	if (bip->bip_vcnt >= bip->bip_max_vcnt) {
-		printk(KERN_ERR "%s: bip_vec full\n", __func__);
+	if (((bip->bip_iter.bi_size + len) >> SECTOR_SHIFT) >
+	    queue_max_hw_sectors(q))
 		return 0;
-	}
 
-	iv = bip->bip_vec + bip->bip_vcnt;
+	if (bip->bip_vcnt > 0) {
+		struct bio_vec *bv = &bip->bip_vec[bip->bip_vcnt - 1];
+		bool same_page = false;
 
-	if (bip->bip_vcnt &&
-	    bvec_gap_to_prev(bio->bi_disk->queue,
-			     &bip->bip_vec[bip->bip_vcnt - 1], offset))
-		return 0;
+		if (bvec_try_merge_hw_page(q, bv, page, len, offset,
+					   &same_page)) {
+			bip->bip_iter.bi_size += len;
+			return len;
+		}
+
+		if (bip->bip_vcnt >=
+		    min(bip->bip_max_vcnt, queue_max_integrity_segments(q)))
+			return 0;
 
-	iv->bv_page = page;
-	iv->bv_len = len;
-	iv->bv_offset = offset;
+		/*
+		 * If the queue doesn't support SG gaps and adding this segment
+		 * would create a gap, disallow it.
+		 */
+		if (bvec_gap_to_prev(&q->limits, bv, offset))
+			return 0;
+	}
+
+	bvec_set_page(&bip->bip_vec[bip->bip_vcnt], page, len, offset);
 	bip->bip_vcnt++;
+	bip->bip_iter.bi_size += len;
 
 	return len;
 }
 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, u32 seed)
+{
+	bool write = direction == ITER_SOURCE;
+	struct bio_integrity_payload *bip;
+	struct iov_iter iter;
+	void *buf;
+	int ret;
+
+	buf = kmalloc(len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (write) {
+		iov_iter_bvec(&iter, direction, bvec, nr_vecs, len);
+		if (!copy_from_iter_full(buf, len, &iter)) {
+			ret = -EFAULT;
+			goto free_buf;
+		}
+
+		bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
+	} else {
+		memset(buf, 0, len);
+
+		/*
+		 * We need to preserve the original bvec and the number of vecs
+		 * in it for completion handling
+		 */
+		bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs + 1);
+	}
+
+	if (IS_ERR(bip)) {
+		ret = PTR_ERR(bip);
+		goto free_buf;
+	}
+
+	if (write)
+		bio_integrity_unpin_bvec(bvec, nr_vecs, false);
+	else
+		memcpy(&bip->bip_vec[1], bvec, nr_vecs * sizeof(*bvec));
+
+	ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
+				     offset_in_page(buf));
+	if (ret != len) {
+		ret = -ENOMEM;
+		goto free_bip;
+	}
+
+	bip->bip_flags |= BIP_INTEGRITY_USER | BIP_COPY_USER;
+	bip->bip_iter.bi_sector = seed;
+	return 0;
+free_bip:
+	bio_integrity_free(bio);
+free_buf:
+	kfree(buf);
+	return ret;
+}
+
+static int bio_integrity_init_user(struct bio *bio, struct bio_vec *bvec,
+				   int nr_vecs, unsigned int len, u32 seed)
+{
+	struct bio_integrity_payload *bip;
+
+	bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs);
+	if (IS_ERR(bip))
+		return PTR_ERR(bip);
+
+	memcpy(bip->bip_vec, bvec, nr_vecs * sizeof(*bvec));
+	bip->bip_flags |= BIP_INTEGRITY_USER;
+	bip->bip_iter.bi_sector = seed;
+	bip->bip_iter.bi_size = len;
+	return 0;
+}
+
+static unsigned int bvec_from_pages(struct bio_vec *bvec, struct page **pages,
+				    int nr_vecs, ssize_t bytes, ssize_t offset)
+{
+	unsigned int nr_bvecs = 0;
+	int i, j;
+
+	for (i = 0; i < nr_vecs; i = j) {
+		size_t size = min_t(size_t, bytes, PAGE_SIZE - offset);
+		struct folio *folio = page_folio(pages[i]);
+
+		bytes -= size;
+		for (j = i + 1; j < nr_vecs; j++) {
+			size_t next = min_t(size_t, PAGE_SIZE, bytes);
+
+			if (page_folio(pages[j]) != folio ||
+			    pages[j] != pages[j - 1] + 1)
+				break;
+			unpin_user_page(pages[j]);
+			size += next;
+			bytes -= next;
+		}
+
+		bvec_set_page(&bvec[nr_bvecs], pages[i], size, offset);
+		offset = 0;
+		nr_bvecs++;
+	}
+
+	return nr_bvecs;
+}
+
+int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes,
+			   u32 seed)
+{
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+	unsigned int align = q->dma_pad_mask | queue_dma_alignment(q);
+	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;
+	int ret, nr_vecs;
+	size_t offset;
+	bool copy;
+
+	if (bio_integrity(bio))
+		return -EINVAL;
+	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);
+	if (nr_vecs > BIO_MAX_VECS)
+		return -E2BIG;
+	if (nr_vecs > UIO_FASTIOV) {
+		bvec = kcalloc(nr_vecs, sizeof(*bvec), GFP_KERNEL);
+		if (!bvec)
+			return -ENOMEM;
+		pages = NULL;
+	}
+
+	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;
+
+	nr_bvecs = bvec_from_pages(bvec, pages, nr_vecs, bytes, offset);
+	if (pages != stack_pages)
+		kvfree(pages);
+	if (nr_bvecs > queue_max_integrity_segments(q))
+		copy = true;
+
+	if (copy)
+		ret = bio_integrity_copy_user(bio, bvec, nr_bvecs, bytes,
+					      direction, seed);
+	else
+		ret = bio_integrity_init_user(bio, bvec, nr_bvecs, bytes, seed);
+	if (ret)
+		goto release_pages;
+	if (bvec != stack_vec)
+		kfree(bvec);
+
+	return 0;
+
+release_pages:
+	bio_integrity_unpin_bvec(bvec, nr_bvecs, false);
+free_bvec:
+	if (bvec != stack_vec)
+		kfree(bvec);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(bio_integrity_map_user);
+
 /**
  * bio_integrity_process - Process integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
@@ -153,33 +383,30 @@ EXPORT_SYMBOL(bio_integrity_add_page);
 static blk_status_t bio_integrity_process(struct bio *bio,
 		struct bvec_iter *proc_iter, integrity_processing_fn *proc_fn)
 {
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_disk);
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	struct blk_integrity_iter iter;
 	struct bvec_iter bviter;
 	struct bio_vec bv;
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 	blk_status_t ret = BLK_STS_OK;
-	void *prot_buf = page_address(bip->bip_vec->bv_page) +
-		bip->bip_vec->bv_offset;
 
-	iter.disk_name = bio->bi_disk->disk_name;
+	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
 	iter.interval = 1 << bi->interval_exp;
+	iter.tuple_size = bi->tuple_size;
 	iter.seed = proc_iter->bi_sector;
-	iter.prot_buf = prot_buf;
+	iter.prot_buf = bvec_virt(bip->bip_vec);
 
 	__bio_for_each_segment(bv, bio, bviter, *proc_iter) {
-		void *kaddr = kmap_atomic(bv.bv_page);
+		void *kaddr = bvec_kmap_local(&bv);
 
-		iter.data_buf = kaddr + bv.bv_offset;
+		iter.data_buf = kaddr;
 		iter.data_size = bv.bv_len;
-
 		ret = proc_fn(&iter);
-		if (ret) {
-			kunmap_atomic(kaddr);
-			return ret;
-		}
+		kunmap_local(kaddr);
+
+		if (ret)
+			break;
 
-		kunmap_atomic(kaddr);
 	}
 	return ret;
 }
@@ -199,14 +426,11 @@ static blk_status_t bio_integrity_process(struct bio *bio,
 bool bio_integrity_prep(struct bio *bio)
 {
 	struct bio_integrity_payload *bip;
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_disk);
-	struct request_queue *q = bio->bi_disk->queue;
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	void *buf;
 	unsigned long start, end;
 	unsigned int len, nr_pages;
 	unsigned int bytes, offset, i;
-	unsigned int intervals;
-	blk_status_t status;
 
 	if (!bi)
 		return true;
@@ -230,12 +454,10 @@ bool bio_integrity_prep(struct bio *bio)
 		    !(bi->flags & BLK_INTEGRITY_GENERATE))
 			return true;
 	}
-	intervals = bio_integrity_intervals(bi, bio_sectors(bio));
 
 	/* Allocate kernel buffer for protection data */
-	len = intervals * bi->tuple_size;
-	buf = kmalloc(len, GFP_NOIO | q->bounce_gfp);
-	status = BLK_STS_RESOURCE;
+	len = bio_integrity_bytes(bi, bio_sectors(bio));
+	buf = kmalloc(len, GFP_NOIO);
 	if (unlikely(buf == NULL)) {
 		printk(KERN_ERR "could not allocate integrity buffer\n");
 		goto err_end_io;
@@ -250,12 +472,10 @@ bool bio_integrity_prep(struct bio *bio)
 	if (IS_ERR(bip)) {
 		printk(KERN_ERR "could not allocate data integrity bioset\n");
 		kfree(buf);
-		status = BLK_STS_RESOURCE;
 		goto err_end_io;
 	}
 
 	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
-	bip->bip_iter.bi_size = len;
 	bip_set_seed(bip, bio->bi_iter.bi_sector);
 
 	if (bi->flags & BLK_INTEGRITY_IP_CHECKSUM)
@@ -263,29 +483,18 @@ bool bio_integrity_prep(struct bio *bio)
 
 	/* Map it */
 	offset = offset_in_page(buf);
-	for (i = 0 ; i < nr_pages ; i++) {
-		int ret;
+	for (i = 0; i < nr_pages && len > 0; i++) {
 		bytes = PAGE_SIZE - offset;
 
-		if (len <= 0)
-			break;
-
 		if (bytes > len)
 			bytes = len;
 
-		ret = bio_integrity_add_page(bio, virt_to_page(buf),
-					     bytes, offset);
-
-		if (ret == 0) {
+		if (bio_integrity_add_page(bio, virt_to_page(buf),
+					   bytes, offset) < bytes) {
 			printk(KERN_ERR "could not attach integrity payload\n");
-			kfree(buf);
-			status = BLK_STS_RESOURCE;
 			goto err_end_io;
 		}
 
-		if (ret < bytes)
-			break;
-
 		buf += bytes;
 		len -= bytes;
 		offset = 0;
@@ -301,10 +510,9 @@ bool bio_integrity_prep(struct bio *bio)
 	return true;
 
 err_end_io:
-	bio->bi_status = status;
+	bio->bi_status = BLK_STS_RESOURCE;
 	bio_endio(bio);
 	return false;
-
 }
 EXPORT_SYMBOL(bio_integrity_prep);
 
@@ -321,7 +529,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	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_disk);
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 
 	/*
 	 * At the moment verify is called bio's iterator was advanced
@@ -347,7 +555,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
  */
 bool __bio_integrity_endio(struct bio *bio)
 {
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_disk);
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 
 	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status &&
@@ -373,10 +581,10 @@ bool __bio_integrity_endio(struct bio *bio)
 void bio_integrity_advance(struct bio *bio, unsigned int bytes_done)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_disk);
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9);
 
-	bip->bip_iter.bi_sector += bytes_done >> 9;
+	bip->bip_iter.bi_sector += bio_integrity_intervals(bi, bytes_done >> 9);
 	bvec_iter_advance(bip->bip_vec, &bip->bip_iter, bytes);
 }
 
@@ -389,7 +597,7 @@ void bio_integrity_advance(struct bio *bio, unsigned int bytes_done)
 void bio_integrity_trim(struct bio *bio)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_disk);
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 
 	bip->bip_iter.bi_size = bio_integrity_bytes(bi, bio_sectors(bio));
 }
@@ -420,10 +628,10 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 
 	bip->bip_vcnt = bip_src->bip_vcnt;
 	bip->bip_iter = bip_src->bip_iter;
+	bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY;
 
 	return 0;
 }
-EXPORT_SYMBOL(bio_integrity_clone);
 
 int bioset_integrity_create(struct bio_set *bs, int pool_size)
 {
@@ -462,6 +670,6 @@ void __init bio_integrity_init(void)
 
 	bip_slab = kmem_cache_create("bio_integrity_payload",
 				     sizeof(struct bio_integrity_payload) +
-				     sizeof(struct bio_vec) * BIP_INLINE_VECS,
+				     sizeof(struct bio_vec) * BIO_INLINE_VECS,
 				     0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 }