summaryrefslogtreecommitdiff
path: root/fs/nfs/blocklayout
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfs/blocklayout')
-rw-r--r--fs/nfs/blocklayout/blocklayout.c4
-rw-r--r--fs/nfs/blocklayout/dev.c5
-rw-r--r--fs/nfs/blocklayout/extent_tree.c104
-rw-r--r--fs/nfs/blocklayout/rpc_pipefs.c53
4 files changed, 114 insertions, 52 deletions
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 47189476b553..5d6edafbed20 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -149,8 +149,8 @@ do_add_page_to_bio(struct bio *bio, int npg, enum req_op op, sector_t isect,
/* limit length to what the device mapping allows */
end = disk_addr + *len;
- if (end >= map->start + map->len)
- *len = map->start + map->len - disk_addr;
+ if (end >= map->disk_offset + map->len)
+ *len = map->disk_offset + map->len - disk_addr;
retry:
if (!bio) {
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index cab8809f0e0f..44306ac22353 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -257,10 +257,11 @@ static bool bl_map_stripe(struct pnfs_block_dev *dev, u64 offset,
struct pnfs_block_dev *child;
u64 chunk;
u32 chunk_idx;
+ u64 disk_chunk;
u64 disk_offset;
chunk = div_u64(offset, dev->chunk_size);
- div_u64_rem(chunk, dev->nr_children, &chunk_idx);
+ disk_chunk = div_u64_rem(chunk, dev->nr_children, &chunk_idx);
if (chunk_idx >= dev->nr_children) {
dprintk("%s: invalid chunk idx %d (%lld/%lld)\n",
@@ -273,7 +274,7 @@ static bool bl_map_stripe(struct pnfs_block_dev *dev, u64 offset,
offset = chunk * dev->chunk_size;
/* disk offset of the stripe */
- disk_offset = div_u64(offset, dev->nr_children);
+ disk_offset = disk_chunk * dev->chunk_size;
child = &dev->children[chunk_idx];
child->map(child, disk_offset, map);
diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c
index 8f7cff7a4293..315949a7e92d 100644
--- a/fs/nfs/blocklayout/extent_tree.c
+++ b/fs/nfs/blocklayout/extent_tree.c
@@ -6,6 +6,7 @@
#include <linux/vmalloc.h>
#include "blocklayout.h"
+#include "../nfs4trace.h"
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
@@ -520,10 +521,71 @@ static __be32 *encode_scsi_range(struct pnfs_block_extent *be, __be32 *p)
return xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT);
}
-static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
+/**
+ * ext_tree_try_encode_commit - try to encode all extents into the buffer
+ * @bl: pointer to the layout
+ * @p: pointer to the output buffer
+ * @buffer_size: size of the output buffer
+ * @count: output pointer to the number of encoded extents
+ * @lastbyte: output pointer to the last written byte
+ *
+ * Return values:
+ * %0: Success, all required extents encoded, outputs are valid
+ * %-ENOSPC: Buffer too small, nothing encoded, outputs are invalid
+ */
+static int
+ext_tree_try_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
size_t buffer_size, size_t *count, __u64 *lastbyte)
{
struct pnfs_block_extent *be;
+
+ spin_lock(&bl->bl_ext_lock);
+ for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) {
+ if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
+ be->be_tag != EXTENT_WRITTEN)
+ continue;
+
+ (*count)++;
+ if (ext_tree_layoutupdate_size(bl, *count) > buffer_size) {
+ spin_unlock(&bl->bl_ext_lock);
+ return -ENOSPC;
+ }
+ }
+ for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) {
+ if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
+ be->be_tag != EXTENT_WRITTEN)
+ continue;
+
+ if (bl->bl_scsi_layout)
+ p = encode_scsi_range(be, p);
+ else
+ p = encode_block_extent(be, p);
+ be->be_tag = EXTENT_COMMITTING;
+ }
+ *lastbyte = (bl->bl_lwb != 0) ? bl->bl_lwb - 1 : U64_MAX;
+ bl->bl_lwb = 0;
+ spin_unlock(&bl->bl_ext_lock);
+
+ return 0;
+}
+
+/**
+ * ext_tree_encode_commit - encode as much as possible extents into the buffer
+ * @bl: pointer to the layout
+ * @p: pointer to the output buffer
+ * @buffer_size: size of the output buffer
+ * @count: output pointer to the number of encoded extents
+ * @lastbyte: output pointer to the last written byte
+ *
+ * Return values:
+ * %0: Success, all required extents encoded, outputs are valid
+ * %-ENOSPC: Buffer too small, some extents are encoded, outputs are valid
+ */
+static int
+ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
+ size_t buffer_size, size_t *count, __u64 *lastbyte)
+{
+ struct pnfs_block_extent *be, *be_prev;
int ret = 0;
spin_lock(&bl->bl_ext_lock);
@@ -534,9 +596,9 @@ static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
(*count)++;
if (ext_tree_layoutupdate_size(bl, *count) > buffer_size) {
- /* keep counting.. */
+ (*count)--;
ret = -ENOSPC;
- continue;
+ break;
}
if (bl->bl_scsi_layout)
@@ -544,14 +606,30 @@ static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
else
p = encode_block_extent(be, p);
be->be_tag = EXTENT_COMMITTING;
+ be_prev = be;
+ }
+ if (!ret) {
+ *lastbyte = (bl->bl_lwb != 0) ? bl->bl_lwb - 1 : U64_MAX;
+ bl->bl_lwb = 0;
+ } else {
+ *lastbyte = be_prev->be_f_offset + be_prev->be_length;
+ *lastbyte <<= SECTOR_SHIFT;
+ *lastbyte -= 1;
}
- *lastbyte = bl->bl_lwb - 1;
- bl->bl_lwb = 0;
spin_unlock(&bl->bl_ext_lock);
return ret;
}
+/**
+ * ext_tree_prepare_commit - encode extents that need to be committed
+ * @arg: layout commit data
+ *
+ * Return values:
+ * %0: Success, all required extents are encoded
+ * %-ENOSPC: Some extents are encoded, but not all, due to RPC size limit
+ * %-ENOMEM: Out of memory, extents not encoded
+ */
int
ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
{
@@ -560,20 +638,18 @@ ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
__be32 *start_p;
int ret;
- dprintk("%s enter\n", __func__);
-
arg->layoutupdate_page = alloc_page(GFP_NOFS);
if (!arg->layoutupdate_page)
return -ENOMEM;
start_p = page_address(arg->layoutupdate_page);
arg->layoutupdate_pages = &arg->layoutupdate_page;
-retry:
- ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count, &arg->lastbytewritten);
+ ret = ext_tree_try_encode_commit(bl, start_p + 1, buffer_size,
+ &count, &arg->lastbytewritten);
if (unlikely(ret)) {
ext_tree_free_commitdata(arg, buffer_size);
- buffer_size = ext_tree_layoutupdate_size(bl, count);
+ buffer_size = NFS_SERVER(arg->inode)->wsize;
count = 0;
arg->layoutupdate_pages =
@@ -588,7 +664,8 @@ retry:
return -ENOMEM;
}
- goto retry;
+ ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size,
+ &count, &arg->lastbytewritten);
}
*start_p = cpu_to_be32(count);
@@ -607,8 +684,9 @@ retry:
}
}
- dprintk("%s found %zu ranges\n", __func__, count);
- return 0;
+ trace_bl_ext_tree_prepare_commit(ret, count,
+ arg->lastbytewritten, !!ret);
+ return ret;
}
void
diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index d8d50a88de04..d526f5ba7887 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -141,24 +141,18 @@ static const struct rpc_pipe_ops bl_upcall_ops = {
.destroy_msg = bl_pipe_destroy_msg,
};
-static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
+static int nfs4blocklayout_register_sb(struct super_block *sb,
struct rpc_pipe *pipe)
{
- struct dentry *dir, *dentry;
+ struct dentry *dir;
+ int err;
dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
if (dir == NULL)
- return ERR_PTR(-ENOENT);
- dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
+ return -ENOENT;
+ err = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
dput(dir);
- return dentry;
-}
-
-static void nfs4blocklayout_unregister_sb(struct super_block *sb,
- struct rpc_pipe *pipe)
-{
- if (pipe->dentry)
- rpc_unlink(pipe->dentry);
+ return err;
}
static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
@@ -167,7 +161,6 @@ static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
struct super_block *sb = ptr;
struct net *net = sb->s_fs_info;
struct nfs_net *nn = net_generic(net, nfs_net_id);
- struct dentry *dentry;
int ret = 0;
if (!try_module_get(THIS_MODULE))
@@ -180,16 +173,10 @@ static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
switch (event) {
case RPC_PIPEFS_MOUNT:
- dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
- if (IS_ERR(dentry)) {
- ret = PTR_ERR(dentry);
- break;
- }
- nn->bl_device_pipe->dentry = dentry;
+ ret = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
break;
case RPC_PIPEFS_UMOUNT:
- if (nn->bl_device_pipe->dentry)
- nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe);
+ rpc_unlink(nn->bl_device_pipe);
break;
default:
ret = -ENOTSUPP;
@@ -203,18 +190,17 @@ static struct notifier_block nfs4blocklayout_block = {
.notifier_call = rpc_pipefs_event,
};
-static struct dentry *nfs4blocklayout_register_net(struct net *net,
- struct rpc_pipe *pipe)
+static int nfs4blocklayout_register_net(struct net *net, struct rpc_pipe *pipe)
{
struct super_block *pipefs_sb;
- struct dentry *dentry;
+ int ret;
pipefs_sb = rpc_get_sb_net(net);
if (!pipefs_sb)
- return NULL;
- dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe);
+ return 0;
+ ret = nfs4blocklayout_register_sb(pipefs_sb, pipe);
rpc_put_sb_net(net);
- return dentry;
+ return ret;
}
static void nfs4blocklayout_unregister_net(struct net *net,
@@ -224,7 +210,7 @@ static void nfs4blocklayout_unregister_net(struct net *net,
pipefs_sb = rpc_get_sb_net(net);
if (pipefs_sb) {
- nfs4blocklayout_unregister_sb(pipefs_sb, pipe);
+ rpc_unlink(pipe);
rpc_put_sb_net(net);
}
}
@@ -232,20 +218,17 @@ static void nfs4blocklayout_unregister_net(struct net *net,
static int nfs4blocklayout_net_init(struct net *net)
{
struct nfs_net *nn = net_generic(net, nfs_net_id);
- struct dentry *dentry;
+ int err;
mutex_init(&nn->bl_mutex);
init_waitqueue_head(&nn->bl_wq);
nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
if (IS_ERR(nn->bl_device_pipe))
return PTR_ERR(nn->bl_device_pipe);
- dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
- if (IS_ERR(dentry)) {
+ err = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
+ if (unlikely(err))
rpc_destroy_pipe_data(nn->bl_device_pipe);
- return PTR_ERR(dentry);
- }
- nn->bl_device_pipe->dentry = dentry;
- return 0;
+ return err;
}
static void nfs4blocklayout_net_exit(struct net *net)
generated by cgit (git 2.34.1) at 2025-08-10 03:40:19 +0000