1 files changed, 63 insertions, 180 deletions

diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index d39f3219358b..b9b79ccfabf8 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -3,9 +3,10 @@
  * Copyright (c) 2011-2014, Intel Corporation.
  * Copyright (c) 2017-2021 Christoph Hellwig.
  */
+#include <linux/blk-integrity.h>
 #include <linux/ptrace.h>	/* for force_successful_syscall_return */
 #include <linux/nvme_ioctl.h>
-#include <linux/io_uring.h>
+#include <linux/io_uring/cmd.h>
 #include "nvme.h"
 
 enum {
@@ -18,15 +19,12 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 {
 	u32 effects;
 
-	if (capable(CAP_SYS_ADMIN))
-		return true;
-
 	/*
 	 * Do not allow unprivileged passthrough on partitions, as that allows an
 	 * escape from the containment of the partition.
 	 */
 	if (flags & NVME_IOCTL_PARTITION)
-		return false;
+		goto admin;
 
 	/*
 	 * Do not allow unprivileged processes to send vendor specific or fabrics
@@ -34,7 +32,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 	 */
 	if (c->common.opcode >= nvme_cmd_vendor_start ||
 	    c->common.opcode == nvme_fabrics_command)
-		return false;
+		goto admin;
 
 	/*
 	 * Do not allow unprivileged passthrough of admin commands except
@@ -53,7 +51,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 				return true;
 			}
 		}
-		return false;
+		goto admin;
 	}
 
 	/*
@@ -63,7 +61,7 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 	 */
 	effects = nvme_command_effects(ns->ctrl, ns, c->common.opcode);
 	if (!(effects & NVME_CMD_EFFECTS_CSUPP))
-		return false;
+		goto admin;
 
 	/*
 	 * Don't allow passthrough for command that have intrusive (or unknown)
@@ -72,16 +70,20 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 	if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
 			NVME_CMD_EFFECTS_UUID_SEL |
 			NVME_CMD_EFFECTS_SCOPE_MASK))
-		return false;
+		goto admin;
 
 	/*
 	 * Only allow I/O commands that transfer data to the controller or that
 	 * change the logical block contents if the file descriptor is open for
 	 * writing.
 	 */
-	if (nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC))
-		return open_for_write;
+	if ((nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC)) &&
+	    !open_for_write)
+		goto admin;
+
 	return true;
+admin:
+	return capable(CAP_SYS_ADMIN);
 }
 
 /*
@@ -96,55 +98,6 @@ static void __user *nvme_to_user_ptr(uintptr_t ptrval)
 	return (void __user *)ptrval;
 }
 
-static void *nvme_add_user_metadata(struct request *req, void __user *ubuf,
-		unsigned len, u32 seed)
-{
-	struct bio_integrity_payload *bip;
-	int ret = -ENOMEM;
-	void *buf;
-	struct bio *bio = req->bio;
-
-	buf = kmalloc(len, GFP_KERNEL);
-	if (!buf)
-		goto out;
-
-	ret = -EFAULT;
-	if ((req_op(req) == REQ_OP_DRV_OUT) && copy_from_user(buf, ubuf, len))
-		goto out_free_meta;
-
-	bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
-	if (IS_ERR(bip)) {
-		ret = PTR_ERR(bip);
-		goto out_free_meta;
-	}
-
-	bip->bip_iter.bi_size = len;
-	bip->bip_iter.bi_sector = seed;
-	ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
-			offset_in_page(buf));
-	if (ret != len) {
-		ret = -ENOMEM;
-		goto out_free_meta;
-	}
-
-	req->cmd_flags |= REQ_INTEGRITY;
-	return buf;
-out_free_meta:
-	kfree(buf);
-out:
-	return ERR_PTR(ret);
-}
-
-static int nvme_finish_user_metadata(struct request *req, void __user *ubuf,
-		void *meta, unsigned len, int ret)
-{
-	if (!ret && req_op(req) == REQ_OP_DRV_IN &&
-	    copy_to_user(ubuf, meta, len))
-		ret = -EFAULT;
-	kfree(meta);
-	return ret;
-}
-
 static struct request *nvme_alloc_user_request(struct request_queue *q,
 		struct nvme_command *cmd, blk_opf_t rq_flags,
 		blk_mq_req_flags_t blk_flags)
@@ -161,16 +114,19 @@ static struct request *nvme_alloc_user_request(struct request_queue *q,
 
 static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
-		u32 meta_seed, void **metap, struct io_uring_cmd *ioucmd,
-		unsigned int flags)
+		u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags)
 {
 	struct request_queue *q = req->q;
 	struct nvme_ns *ns = q->queuedata;
 	struct block_device *bdev = ns ? ns->disk->part0 : NULL;
+	bool supports_metadata = bdev && blk_get_integrity(bdev->bd_disk);
+	bool has_metadata = meta_buffer && meta_len;
 	struct bio *bio = NULL;
-	void *meta = NULL;
 	int ret;
 
+	if (has_metadata && !supports_metadata)
+		return -EINVAL;
+
 	if (ioucmd && (ioucmd->flags & IORING_URING_CMD_FIXED)) {
 		struct iov_iter iter;
 
@@ -190,18 +146,16 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 
 	if (ret)
 		goto out;
+
 	bio = req->bio;
 	if (bdev)
 		bio_set_dev(bio, bdev);
 
-	if (bdev && meta_buffer && meta_len) {
-		meta = nvme_add_user_metadata(req, meta_buffer, meta_len,
-				meta_seed);
-		if (IS_ERR(meta)) {
-			ret = PTR_ERR(meta);
+	if (has_metadata) {
+		ret = blk_rq_integrity_map_user(req, meta_buffer, meta_len,
+						meta_seed);
+		if (ret)
 			goto out_unmap;
-		}
-		*metap = meta;
 	}
 
 	return ret;
@@ -222,7 +176,6 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	struct nvme_ns *ns = q->queuedata;
 	struct nvme_ctrl *ctrl;
 	struct request *req;
-	void *meta = NULL;
 	struct bio *bio;
 	u32 effects;
 	int ret;
@@ -234,7 +187,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	req->timeout = timeout;
 	if (ubuffer && bufflen) {
 		ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer,
-				meta_len, meta_seed, &meta, NULL, flags);
+				meta_len, meta_seed, NULL, flags);
 		if (ret)
 			return ret;
 	}
@@ -246,9 +199,6 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	ret = nvme_execute_rq(req, false);
 	if (result)
 		*result = le64_to_cpu(nvme_req(req)->result.u64);
-	if (meta)
-		ret = nvme_finish_user_metadata(req, meta_buffer, meta,
-						meta_len, ret);
 	if (bio)
 		blk_rq_unmap_user(bio);
 	blk_mq_free_request(req);
@@ -280,10 +230,10 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 		return -EINVAL;
 	}
 
-	length = (io.nblocks + 1) << ns->lba_shift;
+	length = (io.nblocks + 1) << ns->head->lba_shift;
 
 	if ((io.control & NVME_RW_PRINFO_PRACT) &&
-	    ns->ms == sizeof(struct t10_pi_tuple)) {
+	    (ns->head->ms == ns->head->pi_size)) {
 		/*
 		 * Protection information is stripped/inserted by the
 		 * controller.
@@ -293,11 +243,11 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 		meta_len = 0;
 		metadata = NULL;
 	} else {
-		meta_len = (io.nblocks + 1) * ns->ms;
+		meta_len = (io.nblocks + 1) * ns->head->ms;
 		metadata = nvme_to_user_ptr(io.metadata);
 	}
 
-	if (ns->features & NVME_NS_EXT_LBAS) {
+	if (ns->head->features & NVME_NS_EXT_LBAS) {
 		length += meta_len;
 		meta_len = 0;
 	} else if (meta_len) {
@@ -314,8 +264,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	c.rw.control = cpu_to_le16(io.control);
 	c.rw.dsmgmt = cpu_to_le32(io.dsmgmt);
 	c.rw.reftag = cpu_to_le32(io.reftag);
-	c.rw.apptag = cpu_to_le16(io.apptag);
-	c.rw.appmask = cpu_to_le16(io.appmask);
+	c.rw.lbat = cpu_to_le16(io.apptag);
+	c.rw.lbatm = cpu_to_le16(io.appmask);
 
 	return nvme_submit_user_cmd(ns->queue, &c, io.addr, length, metadata,
 			meta_len, lower_32_bits(io.slba), NULL, 0, 0);
@@ -443,19 +393,10 @@ struct nvme_uring_data {
  * Expect build errors if this grows larger than that.
  */
 struct nvme_uring_cmd_pdu {
-	union {
-		struct bio *bio;
-		struct request *req;
-	};
-	u32 meta_len;
-	u32 nvme_status;
-	union {
-		struct {
-			void *meta; /* kernel-resident buffer */
-			void __user *meta_buffer;
-		};
-		u64 result;
-	} u;
+	struct request *req;
+	struct bio *bio;
+	u64 result;
+	int status;
 };
 
 static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
@@ -464,31 +405,6 @@ static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
 	return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu;
 }
 
-static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd,
-				    unsigned issue_flags)
-{
-	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
-	struct request *req = pdu->req;
-	int status;
-	u64 result;
-
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
-		status = -EINTR;
-	else
-		status = nvme_req(req)->status;
-
-	result = le64_to_cpu(nvme_req(req)->result.u64);
-
-	if (pdu->meta_len)
-		status = nvme_finish_user_metadata(req, pdu->u.meta_buffer,
-					pdu->u.meta, pdu->meta_len, status);
-	if (req->bio)
-		blk_rq_unmap_user(req->bio);
-	blk_mq_free_request(req);
-
-	io_uring_cmd_done(ioucmd, status, result, issue_flags);
-}
-
 static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
 			       unsigned issue_flags)
 {
@@ -496,8 +412,7 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
 
 	if (pdu->bio)
 		blk_rq_unmap_user(pdu->bio);
-
-	io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result, issue_flags);
+	io_uring_cmd_done(ioucmd, pdu->status, pdu->result, issue_flags);
 }
 
 static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
@@ -506,20 +421,24 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	struct io_uring_cmd *ioucmd = req->end_io_data;
 	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
 
-	req->bio = pdu->bio;
 	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
-		pdu->nvme_status = -EINTR;
+		pdu->status = -EINTR;
 	else
-		pdu->nvme_status = nvme_req(req)->status;
-	pdu->u.result = le64_to_cpu(nvme_req(req)->result.u64);
+		pdu->status = nvme_req(req)->status;
+	pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*
-	 * For iopoll, complete it directly.
+	 * For iopoll, complete it directly. Note that using the uring_cmd
+	 * helper for this is safe only because we check blk_rq_is_poll().
+	 * As that returns false if we're NOT on a polled queue, then it's
+	 * safe to use the polled completion helper.
+	 *
 	 * Otherwise, move the completion to task work.
 	 */
 	if (blk_rq_is_poll(req)) {
-		WRITE_ONCE(ioucmd->cookie, NULL);
-		nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED);
+		if (pdu->bio)
+			blk_rq_unmap_user(pdu->bio);
+		io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
 	} else {
 		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
 	}
@@ -527,29 +446,6 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	return RQ_END_IO_FREE;
 }
 
-static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req,
-						     blk_status_t err)
-{
-	struct io_uring_cmd *ioucmd = req->end_io_data;
-	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
-
-	req->bio = pdu->bio;
-	pdu->req = req;
-
-	/*
-	 * For iopoll, complete it directly.
-	 * Otherwise, move the completion to task work.
-	 */
-	if (blk_rq_is_poll(req)) {
-		WRITE_ONCE(ioucmd->cookie, NULL);
-		nvme_uring_task_meta_cb(ioucmd, IO_URING_F_UNLOCKED);
-	} else {
-		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_meta_cb);
-	}
-
-	return RQ_END_IO_NONE;
-}
-
 static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 		struct io_uring_cmd *ioucmd, unsigned int issue_flags, bool vec)
 {
@@ -561,7 +457,6 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	struct request *req;
 	blk_opf_t rq_flags = REQ_ALLOC_CACHE;
 	blk_mq_req_flags_t blk_flags = 0;
-	void *meta = NULL;
 	int ret;
 
 	c.common.opcode = READ_ONCE(cmd->opcode);
@@ -609,27 +504,16 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	if (d.addr && d.data_len) {
 		ret = nvme_map_user_request(req, d.addr,
 			d.data_len, nvme_to_user_ptr(d.metadata),
-			d.metadata_len, 0, &meta, ioucmd, vec);
+			d.metadata_len, 0, ioucmd, vec);
 		if (ret)
 			return ret;
 	}
 
-	if (blk_rq_is_poll(req)) {
-		ioucmd->flags |= IORING_URING_CMD_POLLED;
-		WRITE_ONCE(ioucmd->cookie, req);
-	}
-
 	/* to free bio on completion, as req->bio will be null at that time */
 	pdu->bio = req->bio;
-	pdu->meta_len = d.metadata_len;
+	pdu->req = req;
 	req->end_io_data = ioucmd;
-	if (pdu->meta_len) {
-		pdu->u.meta = meta;
-		pdu->u.meta_buffer = nvme_to_user_ptr(d.metadata);
-		req->end_io = nvme_uring_cmd_end_io_meta;
-	} else {
-		req->end_io = nvme_uring_cmd_end_io;
-	}
+	req->end_io = nvme_uring_cmd_end_io;
 	blk_execute_rq_nowait(req, false);
 	return -EIOCBQUEUED;
 }
@@ -780,16 +664,12 @@ int nvme_ns_chr_uring_cmd_iopoll(struct io_uring_cmd *ioucmd,
 				 struct io_comp_batch *iob,
 				 unsigned int poll_flags)
 {
-	struct request *req;
-	int ret = 0;
-
-	if (!(ioucmd->flags & IORING_URING_CMD_POLLED))
-		return 0;
+	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
+	struct request *req = pdu->req;
 
-	req = READ_ONCE(ioucmd->cookie);
 	if (req && blk_rq_is_poll(req))
-		ret = blk_rq_poll(req, iob, poll_flags);
-	return ret;
+		return blk_rq_poll(req, iob, poll_flags);
+	return 0;
 }
 #ifdef CONFIG_NVME_MULTIPATH
 static int nvme_ns_head_ctrl_ioctl(struct nvme_ns *ns, unsigned int cmd,
@@ -914,15 +794,15 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
 		bool open_for_write)
 {
 	struct nvme_ns *ns;
-	int ret;
+	int ret, srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
 	if (list_empty(&ctrl->namespaces)) {
 		ret = -ENOTTY;
 		goto out_unlock;
 	}
 
-	ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list);
+	ns = list_first_or_null_rcu(&ctrl->namespaces, struct nvme_ns, list);
 	if (ns != list_last_entry(&ctrl->namespaces, struct nvme_ns, list)) {
 		dev_warn(ctrl->device,
 			"NVME_IOCTL_IO_CMD not supported when multiple namespaces present!\n");
@@ -932,15 +812,18 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
 
 	dev_warn(ctrl->device,
 		"using deprecated NVME_IOCTL_IO_CMD ioctl on the char device!\n");
-	kref_get(&ns->kref);
-	up_read(&ctrl->namespaces_rwsem);
+	if (!nvme_get_ns(ns)) {
+		ret = -ENXIO;
+		goto out_unlock;
+	}
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 
 	ret = nvme_user_cmd(ctrl, ns, argp, 0, open_for_write);
 	nvme_put_ns(ns);
 	return ret;
 
 out_unlock:
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	return ret;
 }