// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007, 2008, 2009 Oracle Corporation
 * Written by: Martin K. Petersen <martin.petersen@oracle.com>
 *
 * Automatically generate and verify integrity data on PI capable devices if the
 * bio submitter didn't provide PI itself.  This ensures that kernel verifies
 * data integrity even if the file system (or other user of the block device) is
 * not aware of PI.
 */
#include <linux/blk-integrity.h>
#include <linux/t10-pi.h>
#include <linux/workqueue.h>
#include "blk.h"

struct bio_integrity_data {
	struct bio			*bio;
	struct bvec_iter		saved_bio_iter;
	struct work_struct		work;
	struct bio_integrity_payload	bip;
	struct bio_vec			bvec;
};

static struct kmem_cache *bid_slab;
static mempool_t bid_pool;
static struct workqueue_struct *kintegrityd_wq;

static void bio_integrity_finish(struct bio_integrity_data *bid)
{
	bid->bio->bi_integrity = NULL;
	bid->bio->bi_opf &= ~REQ_INTEGRITY;
	kfree(bvec_virt(bid->bip.bip_vec));
	mempool_free(bid, &bid_pool);
}

static void bio_integrity_verify_fn(struct work_struct *work)
{
	struct bio_integrity_data *bid =
		container_of(work, struct bio_integrity_data, work);
	struct bio *bio = bid->bio;

	blk_integrity_verify_iter(bio, &bid->saved_bio_iter);
	bio_integrity_finish(bid);
	bio_endio(bio);
}

#define BIP_CHECK_FLAGS (BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG)
static bool bip_should_check(struct bio_integrity_payload *bip)
{
	return bip->bip_flags & BIP_CHECK_FLAGS;
}

static bool bi_offload_capable(struct blk_integrity *bi)
{
	switch (bi->csum_type) {
	case BLK_INTEGRITY_CSUM_CRC64:
		return bi->metadata_size == sizeof(struct crc64_pi_tuple);
	case BLK_INTEGRITY_CSUM_CRC:
	case BLK_INTEGRITY_CSUM_IP:
		return bi->metadata_size == sizeof(struct t10_pi_tuple);
	default:
		pr_warn_once("%s: unknown integrity checksum type:%d\n",
			__func__, bi->csum_type);
		fallthrough;
	case BLK_INTEGRITY_CSUM_NONE:
		return false;
	}
}

/**
 * __bio_integrity_endio - Integrity I/O completion function
 * @bio:	Protected bio
 *
 * 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 bio_integrity_payload *bip = bio_integrity(bio);
	struct bio_integrity_data *bid =
		container_of(bip, struct bio_integrity_data, bip);

	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status &&
	    bip_should_check(bip)) {
		INIT_WORK(&bid->work, bio_integrity_verify_fn);
		queue_work(kintegrityd_wq, &bid->work);
		return false;
	}

	bio_integrity_finish(bid);
	return true;
}

/**
 * bio_integrity_prep - Prepare bio for integrity I/O
 * @bio:	bio to prepare
 *
 * 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 and for writes the integrity metadata
 * will be generated.  For reads, the completion handler will verify the
 * metadata.
 */
bool bio_integrity_prep(struct bio *bio)
{
	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
	struct bio_integrity_data *bid;
	bool set_flags = true;
	gfp_t gfp = GFP_NOIO;
	unsigned int len;
	void *buf;

	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) {
			if (bi_offload_capable(bi))
				return true;
			set_flags = false;
		}
		break;
	case REQ_OP_WRITE:
		/*
		 * Zero the memory allocated to not leak uninitialized kernel
		 * memory to disk for non-integrity metadata where nothing else
		 * initializes the memory.
		 */
		if (bi->flags & BLK_INTEGRITY_NOGENERATE) {
			if (bi_offload_capable(bi))
				return true;
			set_flags = false;
			gfp |= __GFP_ZERO;
		} else if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
			gfp |= __GFP_ZERO;
		break;
	default:
		return true;
	}

	if (WARN_ON_ONCE(bio_has_crypt_ctx(bio)))
		return true;

	/* Allocate kernel buffer for protection data */
	len = bio_integrity_bytes(bi, bio_sectors(bio));
	buf = kmalloc(len, gfp);
	if (!buf)
		goto err_end_io;
	bid = mempool_alloc(&bid_pool, GFP_NOIO);
	if (!bid)
		goto err_free_buf;
	bio_integrity_init(bio, &bid->bip, &bid->bvec, 1);

	bid->bio = bio;

	bid->bip.bip_flags |= BIP_BLOCK_INTEGRITY;
	bip_set_seed(&bid->bip, bio->bi_iter.bi_sector);

	if (set_flags) {
		if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
			bid->bip.bip_flags |= BIP_IP_CHECKSUM;
		if (bi->csum_type)
			bid->bip.bip_flags |= BIP_CHECK_GUARD;
		if (bi->flags & BLK_INTEGRITY_REF_TAG)
			bid->bip.bip_flags |= BIP_CHECK_REFTAG;
	}

	if (bio_integrity_add_page(bio, virt_to_page(buf), len,
			offset_in_page(buf)) < len)
		goto err_end_io;

	/* Auto-generate integrity metadata if this is a write */
	if (bio_data_dir(bio) == WRITE && bip_should_check(&bid->bip))
		blk_integrity_generate(bio);
	else
		bid->saved_bio_iter = bio->bi_iter;
	return true;

err_free_buf:
	kfree(buf);
err_end_io:
	bio->bi_status = BLK_STS_RESOURCE;
	bio_endio(bio);
	return false;
}
EXPORT_SYMBOL(bio_integrity_prep);

void blk_flush_integrity(void)
{
	flush_workqueue(kintegrityd_wq);
}

static int __init blk_integrity_auto_init(void)
{
	bid_slab = kmem_cache_create("bio_integrity_data",
			sizeof(struct bio_integrity_data), 0,
			SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);

	if (mempool_init_slab_pool(&bid_pool, BIO_POOL_SIZE, bid_slab))
		panic("bio: can't create integrity pool\n");

	/*
	 * 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");
	return 0;
}
subsys_initcall(blk_integrity_auto_init);