block: make bio auto-integrity deadlock safe

The current block layer automatic integrity protection allocates the
actual integrity buffer, which has three problems:

 - because it happens at the bottom of the I/O stack and doesn't use a
   mempool it can deadlock under load
 - because the data size in a bio is almost unbounded when using lage
   folios it can relatively easily exceed the maximum kmalloc size
 - even when it does not exceed the maximum kmalloc size, it could
   exceed the maximum segment size of the device

Fix this by limiting the I/O size so that we can allocate at least a
2MiB integrity buffer, i.e. 128MiB for 8 byte PI and 512 byte integrity
intervals, and create a mempool as a last resort for this maximum size,
mirroring the scheme used for bvecs.  As a nice upside none of this
can fail now, so we remove the error handling and open code the
trivial addition of the bip vec.

The new allocation helpers sit outside of bio-integrity-auto.c because
I plan to reuse them for file system based PI in the near future.

Fixes: 7ba1ba12eeef ("block: Block layer data integrity support")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Anuj Gupta <anuj20.g@samsung.com>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 48 insertions, 0 deletions

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index bed26f1ec869..09eeaf6e74b8 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -14,6 +14,45 @@ struct bio_integrity_alloc {
 	struct bio_vec			bvecs[];
 };
 
+static mempool_t integrity_buf_pool;
+
+void bio_integrity_alloc_buf(struct bio *bio, bool zero_buffer)
+{
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	unsigned int len = bio_integrity_bytes(bi, bio_sectors(bio));
+	gfp_t gfp = GFP_NOIO | (zero_buffer ? __GFP_ZERO : 0);
+	void *buf;
+
+	buf = kmalloc(len, (gfp & ~__GFP_DIRECT_RECLAIM) |
+			__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN);
+	if (unlikely(!buf)) {
+		struct page *page;
+
+		page = mempool_alloc(&integrity_buf_pool, GFP_NOFS);
+		if (zero_buffer)
+			memset(page_address(page), 0, len);
+		bvec_set_page(&bip->bip_vec[0], page, len, 0);
+		bip->bip_flags |= BIP_MEMPOOL;
+	} else {
+		bvec_set_page(&bip->bip_vec[0], virt_to_page(buf), len,
+				offset_in_page(buf));
+	}
+
+	bip->bip_vcnt = 1;
+	bip->bip_iter.bi_size = len;
+}
+
+void bio_integrity_free_buf(struct bio_integrity_payload *bip)
+{
+	struct bio_vec *bv = &bip->bip_vec[0];
+
+	if (bip->bip_flags & BIP_MEMPOOL)
+		mempool_free(bv->bv_page, &integrity_buf_pool);
+	else
+		kfree(bvec_virt(bv));
+}
+
 /**
  * bio_integrity_free - Free bio integrity payload
  * @bio:	bio containing bip to be freed
@@ -438,3 +477,12 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 
 	return 0;
 }
+
+static int __init bio_integrity_initfn(void)
+{
+	if (mempool_init_page_pool(&integrity_buf_pool, BIO_POOL_SIZE,
+			get_order(BLK_INTEGRITY_MAX_SIZE)))
+		panic("bio: can't create integrity buf pool\n");
+	return 0;
+}
+subsys_initcall(bio_integrity_initfn);