nvme: Add pr_ops read_reservation support

This patch adds support for the pr_ops read_reservation callout by
calling the NVMe Reservation Report helper. It then parses that info to
detect if there is a reservation and if there is then convert the
returned info to a pr_ops pr_held_reservation struct.

Signed-off-by: Mike Christie <michael.christie@oracle.com>
Link: https://lore.kernel.org/r/20230407200551.12660-14-michael.christie@oracle.com
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

1 files changed, 83 insertions, 0 deletions

diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
index 732c56b417c2..391b1465ebfd 100644
--- a/drivers/nvme/host/pr.c
+++ b/drivers/nvme/host/pr.c
@@ -29,6 +29,26 @@ static enum nvme_pr_type nvme_pr_type_from_blk(enum pr_type type)
 	return 0;
 }
 
+static enum pr_type block_pr_type_from_nvme(enum nvme_pr_type type)
+{
+	switch (type) {
+	case NVME_PR_WRITE_EXCLUSIVE:
+		return PR_WRITE_EXCLUSIVE;
+	case NVME_PR_EXCLUSIVE_ACCESS:
+		return PR_EXCLUSIVE_ACCESS;
+	case NVME_PR_WRITE_EXCLUSIVE_REG_ONLY:
+		return PR_WRITE_EXCLUSIVE_REG_ONLY;
+	case NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY:
+		return PR_EXCLUSIVE_ACCESS_REG_ONLY;
+	case NVME_PR_WRITE_EXCLUSIVE_ALL_REGS:
+		return PR_WRITE_EXCLUSIVE_ALL_REGS;
+	case NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS:
+		return PR_EXCLUSIVE_ACCESS_ALL_REGS;
+	}
+
+	return 0;
+}
+
 static int nvme_send_ns_head_pr_command(struct block_device *bdev,
 		struct nvme_command *c, void *data, unsigned int data_len)
 {
@@ -222,6 +242,68 @@ free_rse:
 	return ret;
 }
 
+static int nvme_pr_read_reservation(struct block_device *bdev,
+		struct pr_held_reservation *resv)
+{
+	struct nvme_reservation_status_ext tmp_rse, *rse;
+	int ret, i, num_regs;
+	u32 rse_len;
+	bool eds;
+
+get_num_regs:
+	/*
+	 * Get the number of registrations so we know how big to allocate
+	 * the response buffer.
+	 */
+	ret = nvme_pr_resv_report(bdev, &tmp_rse, sizeof(tmp_rse), &eds);
+	if (ret)
+		return ret;
+
+	num_regs = get_unaligned_le16(&tmp_rse.regctl);
+	if (!num_regs) {
+		resv->generation = le32_to_cpu(tmp_rse.gen);
+		return 0;
+	}
+
+	rse_len = struct_size(rse, regctl_eds, num_regs);
+	rse = kzalloc(rse_len, GFP_KERNEL);
+	if (!rse)
+		return -ENOMEM;
+
+	ret = nvme_pr_resv_report(bdev, rse, rse_len, &eds);
+	if (ret)
+		goto free_rse;
+
+	if (num_regs != get_unaligned_le16(&rse->regctl)) {
+		kfree(rse);
+		goto get_num_regs;
+	}
+
+	resv->generation = le32_to_cpu(rse->gen);
+	resv->type = block_pr_type_from_nvme(rse->rtype);
+
+	for (i = 0; i < num_regs; i++) {
+		if (eds) {
+			if (rse->regctl_eds[i].rcsts) {
+				resv->key = le64_to_cpu(rse->regctl_eds[i].rkey);
+				break;
+			}
+		} else {
+			struct nvme_reservation_status *rs;
+
+			rs = (struct nvme_reservation_status *)rse;
+			if (rs->regctl_ds[i].rcsts) {
+				resv->key = le64_to_cpu(rs->regctl_ds[i].rkey);
+				break;
+			}
+		}
+	}
+
+free_rse:
+	kfree(rse);
+	return ret;
+}
+
 const struct pr_ops nvme_pr_ops = {
 	.pr_register	= nvme_pr_register,
 	.pr_reserve	= nvme_pr_reserve,
@@ -229,4 +311,5 @@ const struct pr_ops nvme_pr_ops = {
 	.pr_preempt	= nvme_pr_preempt,
 	.pr_clear	= nvme_pr_clear,
 	.pr_read_keys	= nvme_pr_read_keys,
+	.pr_read_reservation = nvme_pr_read_reservation,
 };