Return-Path: Received: from int-mailstore01.merit.edu ([207.75.116.232]:53437 "EHLO int-mailstore01.merit.edu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755760Ab1FGR2i (ORCPT ); Tue, 7 Jun 2011 13:28:38 -0400 Date: Tue, 7 Jun 2011 13:28:36 -0400 From: Jim Rees To: Benny Halevy Cc: linux-nfs@vger.kernel.org, peter honeyman Subject: [PATCH 22/88] pnfsblock: xdr decode pnfs_block_layout4 Message-ID: <498fac41cf7e347d658ce3e2fd86fc751ef16c43.1307464382.git.rees@umich.edu> References: Content-Type: text/plain; charset=us-ascii In-Reply-To: Sender: linux-nfs-owner@vger.kernel.org List-ID: MIME-Version: 1.0 From: Fred Isaman XDR decodes the block layout payload sent in LAYOUTGET result, storing the result in an extent list. Signed-off-by: Fred Isaman [pnfsblock: fix bug getting pnfs_layout_type in translate_devid().] Signed-off-by: Tao Guo Signed-off-by: Benny Halevy --- fs/nfs/blocklayout/blocklayout.h | 2 + fs/nfs/blocklayout/blocklayoutdev.c | 165 ++++++++++++++++++++++++++++++++++- fs/nfs/blocklayout/extents.c | 12 +++ 3 files changed, 177 insertions(+), 2 deletions(-) diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h index bcf85be..f91939d 100644 --- a/fs/nfs/blocklayout/blocklayout.h +++ b/fs/nfs/blocklayout/blocklayout.h @@ -142,6 +142,7 @@ struct pnfs_block_layout { sector_t bl_blocksize; /* Server blocksize in sectors */ }; +#define BLK_ID(lo) ((struct block_mount_id *)(PNFS_MOUNTID(lo)->mountid)) #define BLK_LSEG2EXT(lseg) ((struct pnfs_block_layout *)lseg->layout->ld_data) #define BLK_LO2EXT(lo) ((struct pnfs_block_layout *)lo->ld_data) @@ -195,4 +196,5 @@ int nfs4_blk_flatten(struct pnfs_blk_volume *, int, struct pnfs_block_dev *); void free_block_dev(struct pnfs_block_dev *bdev); /* extents.c */ void put_extent(struct pnfs_block_extent *be); +struct pnfs_block_extent *alloc_extent(void); #endif /* FS_NFS_NFS4BLOCKLAYOUT_H */ diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c index 818cc1c..77190fd 100644 --- a/fs/nfs/blocklayout/blocklayoutdev.c +++ b/fs/nfs/blocklayout/blocklayoutdev.c @@ -554,11 +554,172 @@ nfs4_blk_decode_device(struct super_block *sb, return rv; } +/* Map deviceid returned by the server to constructed block_device */ +static struct block_device *translate_devid(struct pnfs_layout_type *lo, + struct pnfs_deviceid *id) +{ + struct block_device *rv = NULL; + struct block_mount_id *mid; + struct pnfs_block_dev *dev; + + dprintk("%s enter, lo=%p, id=%p\n", __func__, lo, id); + mid = BLK_ID(lo); + spin_lock(&mid->bm_lock); + list_for_each_entry(dev, &mid->bm_devlist, bm_node) { + if (memcmp(id->data, dev->bm_mdevid.data, + NFS4_PNFS_DEVICEID4_SIZE) == 0) { + rv = dev->bm_mdev; + goto out; + } + } + out: + spin_unlock(&mid->bm_lock); + dprintk("%s returning %p\n", __func__, rv); + return rv; +} + +/* Tracks info needed to ensure extents in layout obey constraints of spec */ +struct layout_verification { + u32 mode; /* R or RW */ + u64 start; /* Expected start of next non-COW extent */ + u64 inval; /* Start of INVAL coverage */ + u64 cowread; /* End of COW read coverage */ +}; + +/* Verify the extent meets the layout requirements of the pnfs-block draft, + * section 2.3.1. + */ +static int verify_extent(struct pnfs_block_extent *be, + struct layout_verification *lv) +{ + if (lv->mode == IOMODE_READ) { + if (be->be_state == PNFS_BLOCK_READWRITE_DATA || + be->be_state == PNFS_BLOCK_INVALID_DATA) + return -EIO; + if (be->be_f_offset != lv->start) + return -EIO; + lv->start += be->be_length; + return 0; + } + /* lv->mode == IOMODE_RW */ + if (be->be_state == PNFS_BLOCK_READWRITE_DATA) { + if (be->be_f_offset != lv->start) + return -EIO; + if (lv->cowread > lv->start) + return -EIO; + lv->start += be->be_length; + lv->inval = lv->start; + return 0; + } else if (be->be_state == PNFS_BLOCK_INVALID_DATA) { + if (be->be_f_offset != lv->start) + return -EIO; + lv->start += be->be_length; + return 0; + } else if (be->be_state == PNFS_BLOCK_READ_DATA) { + if (be->be_f_offset > lv->start) + return -EIO; + if (be->be_f_offset < lv->inval) + return -EIO; + if (be->be_f_offset < lv->cowread) + return -EIO; + /* It looks like you might want to min this with lv->start, + * but you really don't. + */ + lv->inval = lv->inval + be->be_length; + lv->cowread = be->be_f_offset + be->be_length; + return 0; + } else + return -EIO; +} + /* XDR decode pnfs_block_layout4 structure */ int nfs4_blk_process_layoutget(struct pnfs_layout_type *lo, struct nfs4_pnfs_layoutget_res *lgr) { - /* STUB */ - return -EIO; + struct pnfs_block_layout *bl = PNFS_LD_DATA(lo); + uint32_t *p = (uint32_t *)lgr->layout.buf; + uint32_t *end = (uint32_t *)((char *)lgr->layout.buf + lgr->layout.len); + int i, status = -EIO; + uint32_t count; + struct pnfs_block_extent *be = NULL; + uint64_t tmp; /* Used by READSECTOR */ + struct layout_verification lv = { + .mode = lgr->lseg.iomode, + .start = lgr->lseg.offset >> 9, + .inval = lgr->lseg.offset >> 9, + .cowread = lgr->lseg.offset >> 9, + }; + + LIST_HEAD(extents); + + BLK_READBUF(p, end, 4); + READ32(count); + + dprintk("%s enter, number of extents %i\n", __func__, count); + BLK_READBUF(p, end, (28 + NFS4_PNFS_DEVICEID4_SIZE) * count); + + /* Decode individual extents, putting them in temporary + * staging area until whole layout is decoded to make error + * recovery easier. + */ + for (i = 0; i < count; i++) { + be = alloc_extent(); + if (!be) { + status = -ENOMEM; + goto out_err; + } + READ_DEVID(&be->be_devid); + be->be_mdev = translate_devid(lo, &be->be_devid); + if (!be->be_mdev) + goto out_err; + /* The next three values are read in as bytes, + * but stored as 512-byte sector lengths + */ + READ_SECTOR(be->be_f_offset); + READ_SECTOR(be->be_length); + READ_SECTOR(be->be_v_offset); + READ32(be->be_state); + if (be->be_state == PNFS_BLOCK_INVALID_DATA) + be->be_inval = &bl->bl_inval; + if (verify_extent(be, &lv)) { + dprintk("%s verify failed\n", __func__); + goto out_err; + } + list_add_tail(&be->be_node, &extents); + } + if (p != end) { + dprintk("%s Undecoded cruft at end of opaque\n", __func__); + be = NULL; + goto out_err; + } + if (lgr->lseg.offset + lgr->lseg.length != lv.start << 9) { + dprintk("%s Final length mismatch\n", __func__); + be = NULL; + goto out_err; + } + if (lv.start < lv.cowread) { + dprintk("%s Final uncovered COW extent\n", __func__); + be = NULL; + goto out_err; + } + /* Extents decoded properly, now try to merge them in to + * existing layout extents. + */ + /* STUB - instead we just throw them away */ + status = 0; + goto out_err; + out: + dprintk("%s returns %i\n", __func__, status); + return status; + + out_err: + put_extent(be); + while (!list_empty(&extents)) { + be = list_first_entry(&extents, struct pnfs_block_extent, + be_node); + list_del(&be->be_node); + put_extent(be); + } + goto out; } diff --git a/fs/nfs/blocklayout/extents.c b/fs/nfs/blocklayout/extents.c index efdcc08..a952d39 100644 --- a/fs/nfs/blocklayout/extents.c +++ b/fs/nfs/blocklayout/extents.c @@ -53,3 +53,15 @@ put_extent(struct pnfs_block_extent *be) } } +struct pnfs_block_extent *alloc_extent(void) +{ + struct pnfs_block_extent *be; + + be = kmalloc(sizeof(struct pnfs_block_extent), GFP_KERNEL); + if (!be) + return NULL; + INIT_LIST_HEAD(&be->be_node); + kref_init(&be->be_refcnt); + be->be_inval = NULL; + return be; +} -- 1.7.4.1