1 files changed, 132 insertions, 60 deletions

diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 08a20e5bcf7f..afa16d7a8013 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -13,67 +13,49 @@
 #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;
@@ -82,7 +64,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 		}
 		fallthrough;
 	case IOMAP_HOLE:
-		if (seg->iomode == IOMODE_READ) {
+		if (iomode == IOMODE_READ) {
 			bex->es = PNFS_BLOCK_NONE_DATA;
 			break;
 		}
@@ -90,27 +72,107 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 	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
@@ -118,7 +180,6 @@ nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp,
 		struct iomap *iomaps, int nr_iomaps)
 {
 	struct timespec64 mtime = inode_get_mtime(inode);
-	loff_t new_size = lcp->lc_last_wr + 1;
 	struct iattr iattr = { .ia_valid = 0 };
 	int error;
 
@@ -128,9 +189,9 @@ nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp,
 	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,
@@ -173,16 +234,20 @@ nfsd4_block_proc_getdeviceinfo(struct super_block *sb,
 }
 
 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;
+
+	rqstp->rq_arg = lcp->lc_up_layout;
+	svcxdr_init_decode(rqstp);
 
-	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);
+	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);
 }
@@ -311,16 +376,20 @@ nfsd4_scsi_proc_getdeviceinfo(struct super_block *sb,
 	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);
 }
@@ -330,9 +399,12 @@ 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 = 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 = {