1 files changed, 185 insertions, 189 deletions

diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 9bbaa671c079..afa16d7a8013 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -4,135 +4,194 @@
  */
 #include <linux/exportfs.h>
 #include <linux/iomap.h>
-#include <linux/genhd.h>
 #include <linux/slab.h>
 #include <linux/pr.h>
 
 #include <linux/nfsd/debug.h>
-#include <scsi/scsi_proto.h>
-#include <scsi/scsi_common.h>
-#include <scsi/scsi_request.h>
 
 #include "blocklayoutxdr.h"
 #include "pnfs.h"
 #include "filecache.h"
+#include "vfs.h"
+#include "trace.h"
 
 #define NFSDDBG_FACILITY	NFSDDBG_PNFS
 
 
+/*
+ * Get an extent from the file system that starts at offset or below
+ * and may be shorter than the requested length.
+ */
 static __be32
-nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
-		struct nfsd4_layoutget *args)
+nfsd4_block_map_extent(struct inode *inode, const struct svc_fh *fhp,
+		u64 offset, u64 length, u32 iomode, u64 minlength,
+		struct pnfs_block_extent *bex)
 {
-	struct nfsd4_layout_seg *seg = &args->lg_seg;
 	struct super_block *sb = inode->i_sb;
-	u32 block_size = i_blocksize(inode);
-	struct pnfs_block_extent *bex;
 	struct iomap iomap;
 	u32 device_generation = 0;
 	int error;
 
-	if (seg->offset & (block_size - 1)) {
-		dprintk("pnfsd: I/O misaligned\n");
-		goto out_layoutunavailable;
-	}
-
-	/*
-	 * Some clients barf on non-zero block numbers for NONE or INVALID
-	 * layouts, so make sure to zero the whole structure.
-	 */
-	error = -ENOMEM;
-	bex = kzalloc(sizeof(*bex), GFP_KERNEL);
-	if (!bex)
-		goto out_error;
-	args->lg_content = bex;
-
-	error = sb->s_export_op->map_blocks(inode, seg->offset, seg->length,
-					    &iomap, seg->iomode != IOMODE_READ,
-					    &device_generation);
+	error = sb->s_export_op->map_blocks(inode, offset, length, &iomap,
+			iomode != IOMODE_READ, &device_generation);
 	if (error) {
 		if (error == -ENXIO)
-			goto out_layoutunavailable;
-		goto out_error;
-	}
-
-	if (iomap.length < args->lg_minlength) {
-		dprintk("pnfsd: extent smaller than minlength\n");
-		goto out_layoutunavailable;
+			return nfserr_layoutunavailable;
+		return nfserrno(error);
 	}
 
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
-		if (seg->iomode == IOMODE_READ)
+		if (iomode == IOMODE_READ)
 			bex->es = PNFS_BLOCK_READ_DATA;
 		else
 			bex->es = PNFS_BLOCK_READWRITE_DATA;
 		bex->soff = iomap.addr;
 		break;
 	case IOMAP_UNWRITTEN:
-		if (seg->iomode & IOMODE_RW) {
+		if (iomode & IOMODE_RW) {
 			/*
 			 * Crack monkey special case from section 2.3.1.
 			 */
-			if (args->lg_minlength == 0) {
+			if (minlength == 0) {
 				dprintk("pnfsd: no soup for you!\n");
-				goto out_layoutunavailable;
+				return nfserr_layoutunavailable;
 			}
 
 			bex->es = PNFS_BLOCK_INVALID_DATA;
 			bex->soff = iomap.addr;
 			break;
 		}
-		/*FALLTHRU*/
+		fallthrough;
 	case IOMAP_HOLE:
-		if (seg->iomode == IOMODE_READ) {
+		if (iomode == IOMODE_READ) {
 			bex->es = PNFS_BLOCK_NONE_DATA;
 			break;
 		}
-		/*FALLTHRU*/
+		fallthrough;
 	case IOMAP_DELALLOC:
 	default:
 		WARN(1, "pnfsd: filesystem returned %d extent\n", iomap.type);
-		goto out_layoutunavailable;
+		return nfserr_layoutunavailable;
 	}
 
 	error = nfsd4_set_deviceid(&bex->vol_id, fhp, device_generation);
 	if (error)
-		goto out_error;
+		return nfserrno(error);
+
 	bex->foff = iomap.offset;
 	bex->len = iomap.length;
+	return nfs_ok;
+}
 
-	seg->offset = iomap.offset;
-	seg->length = iomap.length;
+static __be32
+nfsd4_block_proc_layoutget(struct svc_rqst *rqstp, struct inode *inode,
+		const struct svc_fh *fhp, struct nfsd4_layoutget *args)
+{
+	struct nfsd4_layout_seg *seg = &args->lg_seg;
+	struct pnfs_block_layout *bl;
+	struct pnfs_block_extent *first_bex, *last_bex;
+	u64 offset = seg->offset, length = seg->length;
+	u32 i, nr_extents_max, block_size = i_blocksize(inode);
+	__be32 nfserr;
 
-	dprintk("GET: 0x%llx:0x%llx %d\n", bex->foff, bex->len, bex->es);
-	return 0;
+	if (locks_in_grace(SVC_NET(rqstp)))
+		return nfserr_grace;
+
+	nfserr = nfserr_layoutunavailable;
+	if (seg->offset & (block_size - 1)) {
+		dprintk("pnfsd: I/O misaligned\n");
+		goto out_error;
+	}
+
+	/*
+	 * RFC 8881, section 3.3.17:
+	 *   The layout4 data type defines a layout for a file.
+	 *
+	 * RFC 8881, section 18.43.3:
+	 *   The loga_maxcount field specifies the maximum layout size
+	 *   (in bytes) that the client can handle. If the size of the
+	 *   layout structure exceeds the size specified by maxcount,
+	 *   the metadata server will return the NFS4ERR_TOOSMALL error.
+	 */
+	nfserr = nfserr_toosmall;
+	if (args->lg_maxcount < PNFS_BLOCK_LAYOUT4_SIZE +
+				PNFS_BLOCK_EXTENT_SIZE)
+		goto out_error;
+
+	/*
+	 * Limit the maximum layout size to avoid allocating
+	 * a large buffer on the server for each layout request.
+	 */
+	nr_extents_max = (min(args->lg_maxcount, PAGE_SIZE) -
+			  PNFS_BLOCK_LAYOUT4_SIZE) / PNFS_BLOCK_EXTENT_SIZE;
+
+	/*
+	 * Some clients barf on non-zero block numbers for NONE or INVALID
+	 * layouts, so make sure to zero the whole structure.
+	 */
+	nfserr = nfserrno(-ENOMEM);
+	bl = kzalloc(struct_size(bl, extents, nr_extents_max), GFP_KERNEL);
+	if (!bl)
+		goto out_error;
+	bl->nr_extents = nr_extents_max;
+	args->lg_content = bl;
+
+	for (i = 0; i < bl->nr_extents; i++) {
+		struct pnfs_block_extent *bex = bl->extents + i;
+		u64 bex_length;
+
+		nfserr = nfsd4_block_map_extent(inode, fhp, offset, length,
+				seg->iomode, args->lg_minlength, bex);
+		if (nfserr != nfs_ok)
+			goto out_error;
+
+		bex_length = bex->len - (offset - bex->foff);
+		if (bex_length >= length) {
+			bl->nr_extents = i + 1;
+			break;
+		}
+
+		offset = bex->foff + bex->len;
+		length -= bex_length;
+	}
+
+	first_bex = bl->extents;
+	last_bex = bl->extents + bl->nr_extents - 1;
+
+	nfserr = nfserr_layoutunavailable;
+	length = last_bex->foff + last_bex->len - seg->offset;
+	if (length < args->lg_minlength) {
+		dprintk("pnfsd: extent smaller than minlength\n");
+		goto out_error;
+	}
+
+	seg->offset = first_bex->foff;
+	seg->length = last_bex->foff - first_bex->foff + last_bex->len;
+	return nfs_ok;
 
 out_error:
 	seg->length = 0;
-	return nfserrno(error);
-out_layoutunavailable:
-	seg->length = 0;
-	return nfserr_layoutunavailable;
+	return nfserr;
 }
 
 static __be32
 nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp,
 		struct iomap *iomaps, int nr_iomaps)
 {
-	loff_t new_size = lcp->lc_last_wr + 1;
+	struct timespec64 mtime = inode_get_mtime(inode);
 	struct iattr iattr = { .ia_valid = 0 };
 	int error;
 
 	if (lcp->lc_mtime.tv_nsec == UTIME_NOW ||
-	    timespec64_compare(&lcp->lc_mtime, &inode->i_mtime) < 0)
+	    timespec64_compare(&lcp->lc_mtime, &mtime) < 0)
 		lcp->lc_mtime = current_time(inode);
 	iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME;
 	iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime;
 
-	if (new_size > i_size_read(inode)) {
+	if (lcp->lc_size_chg) {
 		iattr.ia_valid |= ATTR_SIZE;
-		iattr.ia_size = new_size;
+		iattr.ia_size = lcp->lc_newsize;
 	}
 
 	error = inode->i_sb->s_export_op->commit_blocks(inode, iomaps,
@@ -149,8 +208,7 @@ nfsd4_block_get_device_info_simple(struct super_block *sb,
 	struct pnfs_block_deviceaddr *dev;
 	struct pnfs_block_volume *b;
 
-	dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) +
-		      sizeof(struct pnfs_block_volume), GFP_KERNEL);
+	dev = kzalloc(struct_size(dev, volumes, 1), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
 	gdp->gd_device = dev;
@@ -170,22 +228,26 @@ nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {
-	if (sb->s_bdev != sb->s_bdev->bd_contains)
+	if (bdev_is_partition(sb->s_bdev))
 		return nfserr_inval;
 	return nfserrno(nfsd4_block_get_device_info_simple(sb, gdp));
 }
 
 static __be32
-nfsd4_block_proc_layoutcommit(struct inode *inode,
+nfsd4_block_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp,
 		struct nfsd4_layoutcommit *lcp)
 {
 	struct iomap *iomaps;
 	int nr_iomaps;
+	__be32 nfserr;
 
-	nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
-			lcp->lc_up_len, &iomaps, i_blocksize(inode));
-	if (nr_iomaps < 0)
-		return nfserrno(nr_iomaps);
+	rqstp->rq_arg = lcp->lc_up_layout;
+	svcxdr_init_decode(rqstp);
+
+	nfserr = nfsd4_block_decode_layoutupdate(&rqstp->rq_arg_stream,
+			&iomaps, &nr_iomaps, i_blocksize(inode));
+	if (nfserr != nfs_ok)
+		return nfserr;
 
 	return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps);
 }
@@ -211,109 +273,6 @@ const struct nfsd4_layout_ops bl_layout_ops = {
 #endif /* CONFIG_NFSD_BLOCKLAYOUT */
 
 #ifdef CONFIG_NFSD_SCSILAYOUT
-static int nfsd4_scsi_identify_device(struct block_device *bdev,
-		struct pnfs_block_volume *b)
-{
-	struct request_queue *q = bdev->bd_disk->queue;
-	struct request *rq;
-	struct scsi_request *req;
-	/*
-	 * The allocation length (passed in bytes 3 and 4 of the INQUIRY
-	 * command descriptor block) specifies the number of bytes that have
-	 * been allocated for the data-in buffer.
-	 * 252 is the highest one-byte value that is a multiple of 4.
-	 * 65532 is the highest two-byte value that is a multiple of 4.
-	 */
-	size_t bufflen = 252, maxlen = 65532, len, id_len;
-	u8 *buf, *d, type, assoc;
-	int retries = 1, error;
-
-	if (WARN_ON_ONCE(!blk_queue_scsi_passthrough(q)))
-		return -EINVAL;
-
-again:
-	buf = kzalloc(bufflen, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	rq = blk_get_request(q, REQ_OP_SCSI_IN, 0);
-	if (IS_ERR(rq)) {
-		error = -ENOMEM;
-		goto out_free_buf;
-	}
-	req = scsi_req(rq);
-
-	error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL);
-	if (error)
-		goto out_put_request;
-
-	req->cmd[0] = INQUIRY;
-	req->cmd[1] = 1;
-	req->cmd[2] = 0x83;
-	req->cmd[3] = bufflen >> 8;
-	req->cmd[4] = bufflen & 0xff;
-	req->cmd_len = COMMAND_SIZE(INQUIRY);
-
-	blk_execute_rq(rq->q, NULL, rq, 1);
-	if (req->result) {
-		pr_err("pNFS: INQUIRY 0x83 failed with: %x\n",
-			req->result);
-		error = -EIO;
-		goto out_put_request;
-	}
-
-	len = (buf[2] << 8) + buf[3] + 4;
-	if (len > bufflen) {
-		if (len <= maxlen && retries--) {
-			blk_put_request(rq);
-			kfree(buf);
-			bufflen = len;
-			goto again;
-		}
-		pr_err("pNFS: INQUIRY 0x83 response invalid (len = %zd)\n",
-			len);
-		goto out_put_request;
-	}
-
-	d = buf + 4;
-	for (d = buf + 4; d < buf + len; d += id_len + 4) {
-		id_len = d[3];
-		type = d[1] & 0xf;
-		assoc = (d[1] >> 4) & 0x3;
-
-		/*
-		 * We only care about a EUI-64 and NAA designator types
-		 * with LU association.
-		 */
-		if (assoc != 0x00)
-			continue;
-		if (type != 0x02 && type != 0x03)
-			continue;
-		if (id_len != 8 && id_len != 12 && id_len != 16)
-			continue;
-
-		b->scsi.code_set = PS_CODE_SET_BINARY;
-		b->scsi.designator_type = type == 0x02 ?
-			PS_DESIGNATOR_EUI64 : PS_DESIGNATOR_NAA;
-		b->scsi.designator_len = id_len;
-		memcpy(b->scsi.designator, d + 4, id_len);
-
-		/*
-		 * If we found a 8 or 12 byte descriptor continue on to
-		 * see if a 16 byte one is available.  If we find a
-		 * 16 byte descriptor we're done.
-		 */
-		if (id_len == 16)
-			break;
-	}
-
-out_put_request:
-	blk_put_request(rq);
-out_free_buf:
-	kfree(buf);
-	return error;
-}
-
 #define NFSD_MDS_PR_KEY		0x0100000000000000ULL
 
 /*
@@ -325,6 +284,31 @@ static u64 nfsd4_scsi_pr_key(struct nfs4_client *clp)
 	return ((u64)clp->cl_clientid.cl_boot << 32) | clp->cl_clientid.cl_id;
 }
 
+static const u8 designator_types[] = {
+	PS_DESIGNATOR_EUI64,
+	PS_DESIGNATOR_NAA,
+};
+
+static int
+nfsd4_block_get_unique_id(struct gendisk *disk, struct pnfs_block_volume *b)
+{
+	int ret, i;
+
+	for (i = 0; i < ARRAY_SIZE(designator_types); i++) {
+		u8 type = designator_types[i];
+
+		ret = disk->fops->get_unique_id(disk, b->scsi.designator, type);
+		if (ret > 0) {
+			b->scsi.code_set = PS_CODE_SET_BINARY;
+			b->scsi.designator_type = type;
+			b->scsi.designator_len = ret;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
 static int
 nfsd4_block_get_device_info_scsi(struct super_block *sb,
 		struct nfs4_client *clp,
@@ -333,10 +317,9 @@ nfsd4_block_get_device_info_scsi(struct super_block *sb,
 	struct pnfs_block_deviceaddr *dev;
 	struct pnfs_block_volume *b;
 	const struct pr_ops *ops;
-	int error;
+	int ret;
 
-	dev = kzalloc(sizeof(struct pnfs_block_deviceaddr) +
-		      sizeof(struct pnfs_block_volume), GFP_KERNEL);
+	dev = kzalloc(struct_size(dev, volumes, 1), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
 	gdp->gd_device = dev;
@@ -347,33 +330,39 @@ nfsd4_block_get_device_info_scsi(struct super_block *sb,
 	b->type = PNFS_BLOCK_VOLUME_SCSI;
 	b->scsi.pr_key = nfsd4_scsi_pr_key(clp);
 
-	error = nfsd4_scsi_identify_device(sb->s_bdev, b);
-	if (error)
-		return error;
+	ret = nfsd4_block_get_unique_id(sb->s_bdev->bd_disk, b);
+	if (ret < 0)
+		goto out_free_dev;
 
+	ret = -EINVAL;
 	ops = sb->s_bdev->bd_disk->fops->pr_ops;
 	if (!ops) {
 		pr_err("pNFS: device %s does not support PRs.\n",
 			sb->s_id);
-		return -EINVAL;
+		goto out_free_dev;
 	}
 
-	error = ops->pr_register(sb->s_bdev, 0, NFSD_MDS_PR_KEY, true);
-	if (error) {
+	ret = ops->pr_register(sb->s_bdev, 0, NFSD_MDS_PR_KEY, true);
+	if (ret) {
 		pr_err("pNFS: failed to register key for device %s.\n",
 			sb->s_id);
-		return -EINVAL;
+		goto out_free_dev;
 	}
 
-	error = ops->pr_reserve(sb->s_bdev, NFSD_MDS_PR_KEY,
+	ret = ops->pr_reserve(sb->s_bdev, NFSD_MDS_PR_KEY,
 			PR_EXCLUSIVE_ACCESS_REG_ONLY, 0);
-	if (error) {
+	if (ret) {
 		pr_err("pNFS: failed to reserve device %s.\n",
 			sb->s_id);
-		return -EINVAL;
+		goto out_free_dev;
 	}
 
 	return 0;
+
+out_free_dev:
+	kfree(dev);
+	gdp->gd_device = NULL;
+	return ret;
 }
 
 static __be32
@@ -382,33 +371,40 @@ nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
 		struct nfs4_client *clp,
 		struct nfsd4_getdeviceinfo *gdp)
 {
-	if (sb->s_bdev != sb->s_bdev->bd_contains)
+	if (bdev_is_partition(sb->s_bdev))
 		return nfserr_inval;
 	return nfserrno(nfsd4_block_get_device_info_scsi(sb, clp, gdp));
 }
 static __be32
-nfsd4_scsi_proc_layoutcommit(struct inode *inode,
+nfsd4_scsi_proc_layoutcommit(struct inode *inode, struct svc_rqst *rqstp,
 		struct nfsd4_layoutcommit *lcp)
 {
 	struct iomap *iomaps;
 	int nr_iomaps;
+	__be32 nfserr;
+
+	rqstp->rq_arg = lcp->lc_up_layout;
+	svcxdr_init_decode(rqstp);
 
-	nr_iomaps = nfsd4_scsi_decode_layoutupdate(lcp->lc_up_layout,
-			lcp->lc_up_len, &iomaps, i_blocksize(inode));
-	if (nr_iomaps < 0)
-		return nfserrno(nr_iomaps);
+	nfserr = nfsd4_scsi_decode_layoutupdate(&rqstp->rq_arg_stream,
+			&iomaps, &nr_iomaps, i_blocksize(inode));
+	if (nfserr != nfs_ok)
+		return nfserr;
 
 	return nfsd4_block_commit_blocks(inode, lcp, iomaps, nr_iomaps);
 }
 
 static void
-nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls)
+nfsd4_scsi_fence_client(struct nfs4_layout_stateid *ls, struct nfsd_file *file)
 {
 	struct nfs4_client *clp = ls->ls_stid.sc_client;
-	struct block_device *bdev = ls->ls_file->nf_file->f_path.mnt->mnt_sb->s_bdev;
+	struct block_device *bdev = file->nf_file->f_path.mnt->mnt_sb->s_bdev;
+	int status;
 
-	bdev->bd_disk->fops->pr_ops->pr_preempt(bdev, NFSD_MDS_PR_KEY,
-			nfsd4_scsi_pr_key(clp), 0, true);
+	status = bdev->bd_disk->fops->pr_ops->pr_preempt(bdev, NFSD_MDS_PR_KEY,
+			nfsd4_scsi_pr_key(clp),
+			PR_EXCLUSIVE_ACCESS_REG_ONLY, true);
+	trace_nfsd_pnfs_fence(clp, bdev->bd_disk->disk_name, status);
 }
 
 const struct nfsd4_layout_ops scsi_layout_ops = {