From 9d77db3c730780c8ef5ccd4b66403ff5675cfe4e Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 13 May 2024 10:30:14 +0000
Subject: [PATCH] modify sin led gpio
---
kernel/fs/nfs/flexfilelayout/flexfilelayout.c | 658 +++++++++++++++++++++++++++++++++++-----------------------
1 files changed, 395 insertions(+), 263 deletions(-)
diff --git a/kernel/fs/nfs/flexfilelayout/flexfilelayout.c b/kernel/fs/nfs/flexfilelayout/flexfilelayout.c
index fee421d..e4f2820 100644
--- a/kernel/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/kernel/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Module for pnfs flexfile layout driver.
*
@@ -7,8 +8,10 @@
*/
#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
#include <linux/nfs_page.h>
#include <linux/module.h>
+#include <linux/sched/mm.h>
#include <linux/sunrpc/metrics.h>
@@ -27,9 +30,9 @@
#define FF_LAYOUT_POLL_RETRY_MAX (15*HZ)
#define FF_LAYOUTRETURN_MAXERR 20
+static unsigned short io_maxretrans;
-static struct group_info *ff_zero_group;
-
+static const struct pnfs_commit_ops ff_layout_commit_ops;
static void ff_layout_read_record_layoutstats_done(struct rpc_task *task,
struct nfs_pgio_header *hdr);
static int ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo,
@@ -46,9 +49,11 @@
ffl = kzalloc(sizeof(*ffl), gfp_flags);
if (ffl) {
+ pnfs_init_ds_commit_info(&ffl->commit_info);
INIT_LIST_HEAD(&ffl->error_list);
INIT_LIST_HEAD(&ffl->mirrors);
ffl->last_report_time = ktime_get();
+ ffl->commit_info.ops = &ff_layout_commit_ops;
return &ffl->generic_hdr;
} else
return NULL;
@@ -57,14 +62,14 @@
static void
ff_layout_free_layout_hdr(struct pnfs_layout_hdr *lo)
{
+ struct nfs4_flexfile_layout *ffl = FF_LAYOUT_FROM_HDR(lo);
struct nfs4_ff_layout_ds_err *err, *n;
- list_for_each_entry_safe(err, n, &FF_LAYOUT_FROM_HDR(lo)->error_list,
- list) {
+ list_for_each_entry_safe(err, n, &ffl->error_list, list) {
list_del(&err->list);
kfree(err);
}
- kfree(FF_LAYOUT_FROM_HDR(lo));
+ kfree_rcu(ffl, generic_hdr.plh_rcu);
}
static int decode_pnfs_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
@@ -226,16 +231,14 @@
static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
{
- struct rpc_cred *cred;
+ const struct cred *cred;
ff_layout_remove_mirror(mirror);
kfree(mirror->fh_versions);
cred = rcu_access_pointer(mirror->ro_cred);
- if (cred)
- put_rpccred(cred);
+ put_cred(cred);
cred = rcu_access_pointer(mirror->rw_cred);
- if (cred)
- put_rpccred(cred);
+ put_cred(cred);
nfs4_ff_layout_put_deviceid(mirror->mirror_ds);
kfree(mirror);
}
@@ -248,36 +251,10 @@
static void ff_layout_free_mirror_array(struct nfs4_ff_layout_segment *fls)
{
- int i;
+ u32 i;
- if (fls->mirror_array) {
- for (i = 0; i < fls->mirror_array_cnt; i++) {
- /* normally mirror_ds is freed in
- * .free_deviceid_node but we still do it here
- * for .alloc_lseg error path */
- ff_layout_put_mirror(fls->mirror_array[i]);
- }
- kfree(fls->mirror_array);
- fls->mirror_array = NULL;
- }
-}
-
-static int ff_layout_check_layout(struct nfs4_layoutget_res *lgr)
-{
- int ret = 0;
-
- dprintk("--> %s\n", __func__);
-
- /* FIXME: remove this check when layout segment support is added */
- if (lgr->range.offset != 0 ||
- lgr->range.length != NFS4_MAX_UINT64) {
- dprintk("%s Only whole file layouts supported. Use MDS i/o\n",
- __func__);
- ret = -EINVAL;
- }
-
- dprintk("--> %s returns %d\n", __func__, ret);
- return ret;
+ for (i = 0; i < fls->mirror_array_cnt; i++)
+ ff_layout_put_mirror(fls->mirror_array[i]);
}
static void _ff_layout_free_lseg(struct nfs4_ff_layout_segment *fls)
@@ -286,6 +263,23 @@
ff_layout_free_mirror_array(fls);
kfree(fls);
}
+}
+
+static bool
+ff_lseg_match_mirrors(struct pnfs_layout_segment *l1,
+ struct pnfs_layout_segment *l2)
+{
+ const struct nfs4_ff_layout_segment *fl1 = FF_LAYOUT_LSEG(l1);
+ const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l1);
+ u32 i;
+
+ if (fl1->mirror_array_cnt != fl2->mirror_array_cnt)
+ return false;
+ for (i = 0; i < fl1->mirror_array_cnt; i++) {
+ if (fl1->mirror_array[i] != fl2->mirror_array[i])
+ return false;
+ }
+ return true;
}
static bool
@@ -322,6 +316,8 @@
new_end = pnfs_calc_offset_end(new->pls_range.offset,
new->pls_range.length);
if (new_end < old->pls_range.offset)
+ return false;
+ if (!ff_lseg_match_mirrors(new, old))
return false;
/* Mergeable: copy info from 'old' to 'new' */
@@ -400,21 +396,20 @@
goto out_err_free;
rc = -ENOMEM;
- fls = kzalloc(sizeof(*fls), gfp_flags);
+ fls = kzalloc(struct_size(fls, mirror_array, mirror_array_cnt),
+ gfp_flags);
if (!fls)
goto out_err_free;
fls->mirror_array_cnt = mirror_array_cnt;
fls->stripe_unit = stripe_unit;
- fls->mirror_array = kcalloc(fls->mirror_array_cnt,
- sizeof(fls->mirror_array[0]), gfp_flags);
- if (fls->mirror_array == NULL)
- goto out_err_free;
for (i = 0; i < fls->mirror_array_cnt; i++) {
struct nfs4_ff_layout_mirror *mirror;
- struct auth_cred acred = { .group_info = ff_zero_group };
- struct rpc_cred __rcu *cred;
+ struct cred *kcred;
+ const struct cred __rcu *cred;
+ kuid_t uid;
+ kgid_t gid;
u32 ds_count, fh_count, id;
int j;
@@ -482,21 +477,28 @@
if (rc)
goto out_err_free;
- acred.uid = make_kuid(&init_user_ns, id);
+ uid = make_kuid(&init_user_ns, id);
/* group */
rc = decode_name(&stream, &id);
if (rc)
goto out_err_free;
- acred.gid = make_kgid(&init_user_ns, id);
+ gid = make_kgid(&init_user_ns, id);
- /* find the cred for it */
- rcu_assign_pointer(cred, rpc_lookup_generic_cred(&acred, 0, gfp_flags));
- if (IS_ERR(cred)) {
- rc = PTR_ERR(cred);
- goto out_err_free;
+ if (gfp_flags & __GFP_FS)
+ kcred = prepare_kernel_cred(NULL);
+ else {
+ unsigned int nofs_flags = memalloc_nofs_save();
+ kcred = prepare_kernel_cred(NULL);
+ memalloc_nofs_restore(nofs_flags);
}
+ rc = -ENOMEM;
+ if (!kcred)
+ goto out_err_free;
+ kcred->fsuid = uid;
+ kcred->fsgid = gid;
+ cred = RCU_INITIALIZER(kcred);
if (lgr->range.iomode == IOMODE_READ)
rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
@@ -519,8 +521,8 @@
dprintk("%s: iomode %s uid %u gid %u\n", __func__,
lgr->range.iomode == IOMODE_READ ? "READ" : "RW",
- from_kuid(&init_user_ns, acred.uid),
- from_kgid(&init_user_ns, acred.gid));
+ from_kuid(&init_user_ns, uid),
+ from_kgid(&init_user_ns, gid));
}
p = xdr_inline_decode(&stream, 4);
@@ -536,9 +538,6 @@
out_sort_mirrors:
ff_layout_sort_mirrors(fls);
- rc = ff_layout_check_layout(lgr);
- if (rc)
- goto out_err_free;
ret = &fls->generic_hdr;
dprintk("<-- %s (success)\n", __func__);
out_free_page:
@@ -549,17 +548,6 @@
ret = ERR_PTR(rc);
dprintk("<-- %s (%d)\n", __func__, rc);
goto out_free_page;
-}
-
-static bool ff_layout_has_rw_segments(struct pnfs_layout_hdr *layout)
-{
- struct pnfs_layout_segment *lseg;
-
- list_for_each_entry(lseg, &layout->plh_segs, pls_list)
- if (lseg->pls_range.iomode == IOMODE_RW)
- return true;
-
- return false;
}
static void
@@ -576,21 +564,10 @@
ffl = FF_LAYOUT_FROM_HDR(lseg->pls_layout);
inode = ffl->generic_hdr.plh_inode;
spin_lock(&inode->i_lock);
- if (!ff_layout_has_rw_segments(lseg->pls_layout)) {
- ffl->commit_info.nbuckets = 0;
- kfree(ffl->commit_info.buckets);
- ffl->commit_info.buckets = NULL;
- }
+ pnfs_generic_ds_cinfo_release_lseg(&ffl->commit_info, lseg);
spin_unlock(&inode->i_lock);
}
_ff_layout_free_lseg(fls);
-}
-
-/* Return 1 until we have multiple lsegs support */
-static int
-ff_layout_get_lseg_count(struct nfs4_ff_layout_segment *fls)
-{
- return 1;
}
static void
@@ -737,74 +714,94 @@
spin_unlock(&mirror->lock);
}
-static int
-ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg,
- struct nfs_commit_info *cinfo,
- gfp_t gfp_flags)
+static void
+ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, u32 idx)
+{
+ struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
+
+ if (devid)
+ nfs4_mark_deviceid_unavailable(devid);
+}
+
+static void
+ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, u32 idx)
+{
+ struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
+
+ if (devid)
+ nfs4_mark_deviceid_available(devid);
+}
+
+static struct nfs4_pnfs_ds *
+ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg,
+ u32 start_idx, u32 *best_idx,
+ bool check_device)
{
struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
- struct pnfs_commit_bucket *buckets;
- int size;
+ struct nfs4_ff_layout_mirror *mirror;
+ struct nfs4_pnfs_ds *ds;
+ bool fail_return = false;
+ u32 idx;
- if (cinfo->ds->nbuckets != 0) {
- /* This assumes there is only one RW lseg per file.
- * To support multiple lseg per file, we need to
- * change struct pnfs_commit_bucket to allow dynamic
- * increasing nbuckets.
- */
- return 0;
+ /* mirrors are initially sorted by efficiency */
+ for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
+ if (idx+1 == fls->mirror_array_cnt)
+ fail_return = !check_device;
+
+ mirror = FF_LAYOUT_COMP(lseg, idx);
+ ds = nfs4_ff_layout_prepare_ds(lseg, mirror, fail_return);
+ if (!ds)
+ continue;
+
+ if (check_device &&
+ nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node))
+ continue;
+
+ *best_idx = idx;
+ return ds;
}
- size = ff_layout_get_lseg_count(fls) * FF_LAYOUT_MIRROR_COUNT(lseg);
+ return NULL;
+}
- buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket),
- gfp_flags);
- if (!buckets)
- return -ENOMEM;
- else {
- int i;
+static struct nfs4_pnfs_ds *
+ff_layout_choose_any_ds_for_read(struct pnfs_layout_segment *lseg,
+ u32 start_idx, u32 *best_idx)
+{
+ return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, false);
+}
- spin_lock(&cinfo->inode->i_lock);
- if (cinfo->ds->nbuckets != 0)
- kfree(buckets);
- else {
- cinfo->ds->buckets = buckets;
- cinfo->ds->nbuckets = size;
- for (i = 0; i < size; i++) {
- INIT_LIST_HEAD(&buckets[i].written);
- INIT_LIST_HEAD(&buckets[i].committing);
- /* mark direct verifier as unset */
- buckets[i].direct_verf.committed =
- NFS_INVALID_STABLE_HOW;
- }
- }
- spin_unlock(&cinfo->inode->i_lock);
- return 0;
- }
+static struct nfs4_pnfs_ds *
+ff_layout_choose_valid_ds_for_read(struct pnfs_layout_segment *lseg,
+ u32 start_idx, u32 *best_idx)
+{
+ return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, true);
}
static struct nfs4_pnfs_ds *
ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
- int start_idx,
- int *best_idx)
+ u32 start_idx, u32 *best_idx)
{
- struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
struct nfs4_pnfs_ds *ds;
- bool fail_return = false;
- int idx;
- /* mirrors are sorted by efficiency */
- for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
- if (idx+1 == fls->mirror_array_cnt)
- fail_return = true;
- ds = nfs4_ff_layout_prepare_ds(lseg, idx, fail_return);
- if (ds) {
- *best_idx = idx;
- return ds;
- }
- }
+ ds = ff_layout_choose_valid_ds_for_read(lseg, start_idx, best_idx);
+ if (ds)
+ return ds;
+ return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx);
+}
- return NULL;
+static struct nfs4_pnfs_ds *
+ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio,
+ u32 *best_idx)
+{
+ struct pnfs_layout_segment *lseg = pgio->pg_lseg;
+ struct nfs4_pnfs_ds *ds;
+
+ ds = ff_layout_choose_best_ds_for_read(lseg, pgio->pg_mirror_idx,
+ best_idx);
+ if (ds || !pgio->pg_mirror_idx)
+ return ds;
+ return ff_layout_choose_best_ds_for_read(lseg, 0, best_idx);
}
static void
@@ -814,9 +811,9 @@
{
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
- 0,
- NFS4_MAX_UINT64,
+ nfs_req_openctx(req),
+ req_offset(req),
+ req->wb_bytes,
IOMODE_READ,
strict_iomode,
GFP_KERNEL);
@@ -827,16 +824,24 @@
}
static void
+ff_layout_pg_check_layout(struct nfs_pageio_descriptor *pgio,
+ struct nfs_page *req)
+{
+ pnfs_generic_pg_check_layout(pgio);
+ pnfs_generic_pg_check_range(pgio, req);
+}
+
+static void
ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
struct nfs_pgio_mirror *pgm;
struct nfs4_ff_layout_mirror *mirror;
struct nfs4_pnfs_ds *ds;
- int ds_idx;
+ u32 ds_idx;
retry:
- pnfs_generic_pg_check_layout(pgio);
+ ff_layout_pg_check_layout(pgio, req);
/* Use full layout for now */
if (!pgio->pg_lseg) {
ff_layout_pg_get_read(pgio, req, false);
@@ -849,32 +854,35 @@
goto out_nolseg;
}
- ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx);
+ ds = ff_layout_get_ds_for_read(pgio, &ds_idx);
if (!ds) {
if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
- pnfs_put_lseg(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
+ pnfs_generic_pg_cleanup(pgio);
/* Sleep for 1 second before retrying */
ssleep(1);
goto retry;
}
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
-
- pgio->pg_mirror_idx = ds_idx;
-
- /* read always uses only one mirror - idx 0 for pgio layer */
pgm = &pgio->pg_mirrors[0];
pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
+ pgio->pg_mirror_idx = ds_idx;
+
+ if (NFS_SERVER(pgio->pg_inode)->flags &
+ (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
+ pgio->pg_maxretrans = io_maxretrans;
return;
out_nolseg:
if (pgio->pg_error < 0)
return;
out_mds:
- pnfs_put_lseg(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
+ trace_pnfs_mds_fallback_pg_init_read(pgio->pg_inode,
+ 0, NFS4_MAX_UINT64, IOMODE_READ,
+ NFS_I(pgio->pg_inode)->layout,
+ pgio->pg_lseg);
+ pgio->pg_maxretrans = 0;
nfs_pageio_reset_read_mds(pgio);
}
@@ -884,18 +892,16 @@
{
struct nfs4_ff_layout_mirror *mirror;
struct nfs_pgio_mirror *pgm;
- struct nfs_commit_info cinfo;
struct nfs4_pnfs_ds *ds;
- int i;
- int status;
+ u32 i;
retry:
- pnfs_generic_pg_check_layout(pgio);
+ ff_layout_pg_check_layout(pgio, req);
if (!pgio->pg_lseg) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
- 0,
- NFS4_MAX_UINT64,
+ nfs_req_openctx(req),
+ req_offset(req),
+ req->wb_bytes,
IOMODE_RW,
false,
GFP_NOFS);
@@ -909,39 +915,39 @@
if (pgio->pg_lseg == NULL)
goto out_mds;
- nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq);
- status = ff_layout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS);
- if (status < 0)
- goto out_mds;
-
/* Use a direct mapping of ds_idx to pgio mirror_idx */
if (pgio->pg_mirror_count != FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg))
goto out_eagain;
for (i = 0; i < pgio->pg_mirror_count; i++) {
- ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
+ mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
+ ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, mirror, true);
if (!ds) {
if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
- pnfs_put_lseg(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
+ pnfs_generic_pg_cleanup(pgio);
/* Sleep for 1 second before retrying */
ssleep(1);
goto retry;
}
pgm = &pgio->pg_mirrors[i];
- mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize;
}
+ if (NFS_SERVER(pgio->pg_inode)->flags &
+ (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR))
+ pgio->pg_maxretrans = io_maxretrans;
return;
out_eagain:
pnfs_generic_pg_cleanup(pgio);
pgio->pg_error = -EAGAIN;
return;
out_mds:
- pnfs_put_lseg(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
+ trace_pnfs_mds_fallback_pg_init_write(pgio->pg_inode,
+ 0, NFS4_MAX_UINT64, IOMODE_RW,
+ NFS_I(pgio->pg_inode)->layout,
+ pgio->pg_lseg);
+ pgio->pg_maxretrans = 0;
nfs_pageio_reset_write_mds(pgio);
pgio->pg_error = -EAGAIN;
}
@@ -952,9 +958,9 @@
{
if (!pgio->pg_lseg) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
- 0,
- NFS4_MAX_UINT64,
+ nfs_req_openctx(req),
+ req_offset(req),
+ req->wb_bytes,
IOMODE_RW,
false,
GFP_NOFS);
@@ -967,10 +973,29 @@
if (pgio->pg_lseg)
return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg);
+ trace_pnfs_mds_fallback_pg_get_mirror_count(pgio->pg_inode,
+ 0, NFS4_MAX_UINT64, IOMODE_RW,
+ NFS_I(pgio->pg_inode)->layout,
+ pgio->pg_lseg);
/* no lseg means that pnfs is not in use, so no mirroring here */
nfs_pageio_reset_write_mds(pgio);
out:
return 1;
+}
+
+static u32
+ff_layout_pg_set_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx)
+{
+ u32 old = desc->pg_mirror_idx;
+
+ desc->pg_mirror_idx = idx;
+ return old;
+}
+
+static struct nfs_pgio_mirror *
+ff_layout_pg_get_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx)
+{
+ return &desc->pg_mirrors[idx];
}
static const struct nfs_pageio_ops ff_layout_pg_read_ops = {
@@ -986,6 +1011,8 @@
.pg_doio = pnfs_generic_pg_writepages,
.pg_get_mirror_count = ff_layout_pg_get_mirror_count_write,
.pg_cleanup = pnfs_generic_pg_cleanup,
+ .pg_get_mirror = ff_layout_pg_get_mirror_write,
+ .pg_set_mirror = ff_layout_pg_set_mirror_write,
};
static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
@@ -1016,8 +1043,24 @@
hdr->args.count,
(unsigned long long)hdr->args.offset);
+ trace_pnfs_mds_fallback_write_done(hdr->inode,
+ hdr->args.offset, hdr->args.count,
+ IOMODE_RW, NFS_I(hdr->inode)->layout,
+ hdr->lseg);
task->tk_status = pnfs_write_done_resend_to_mds(hdr);
}
+}
+
+static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr)
+{
+ u32 idx = hdr->pgio_mirror_idx + 1;
+ u32 new_idx = 0;
+
+ if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx))
+ ff_layout_send_layouterror(hdr->lseg);
+ else
+ pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg);
+ pnfs_read_resend_pnfs(hdr, new_idx);
}
static void ff_layout_reset_read(struct nfs_pgio_header *hdr)
@@ -1025,6 +1068,7 @@
struct rpc_task *task = &hdr->task;
pnfs_layoutcommit_inode(hdr->inode, false);
+ pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg);
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
dprintk("%s Reset task %5u for i/o through MDS "
@@ -1035,6 +1079,10 @@
hdr->args.count,
(unsigned long long)hdr->args.offset);
+ trace_pnfs_mds_fallback_read_done(hdr->inode,
+ hdr->args.offset, hdr->args.count,
+ IOMODE_READ, NFS_I(hdr->inode)->layout,
+ hdr->lseg);
task->tk_status = pnfs_read_done_resend_to_mds(hdr);
}
}
@@ -1043,7 +1091,7 @@
struct nfs4_state *state,
struct nfs_client *clp,
struct pnfs_layout_segment *lseg,
- int idx)
+ u32 idx)
{
struct pnfs_layout_hdr *lo = lseg->pls_layout;
struct inode *inode = lo->plh_inode;
@@ -1101,7 +1149,7 @@
nfs4_delete_deviceid(devid->ld, devid->nfs_client,
&devid->deviceid);
rpc_wake_up(&tbl->slot_tbl_waitq);
- /* fall through */
+ fallthrough;
default:
if (ff_layout_avoid_mds_available_ds(lseg))
return -NFS4ERR_RESET_TO_PNFS;
@@ -1117,7 +1165,7 @@
/* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
static int ff_layout_async_handle_error_v3(struct rpc_task *task,
struct pnfs_layout_segment *lseg,
- int idx)
+ u32 idx)
{
struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
@@ -1152,12 +1200,14 @@
struct nfs4_state *state,
struct nfs_client *clp,
struct pnfs_layout_segment *lseg,
- int idx)
+ u32 idx)
{
int vers = clp->cl_nfs_mod->rpc_vers->number;
- if (task->tk_status >= 0)
+ if (task->tk_status >= 0) {
+ ff_layout_mark_ds_reachable(lseg, idx);
return 0;
+ }
/* Handle the case of an invalid layout segment */
if (!pnfs_is_valid_lseg(lseg))
@@ -1177,10 +1227,11 @@
}
static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
- int idx, u64 offset, u64 length,
- u32 status, int opnum, int error)
+ u32 idx, u64 offset, u64 length,
+ u32 *op_status, int opnum, int error)
{
struct nfs4_ff_layout_mirror *mirror;
+ u32 status = *op_status;
int err;
if (status == 0) {
@@ -1189,6 +1240,7 @@
case -EPFNOSUPPORT:
case -EPROTONOSUPPORT:
case -EOPNOTSUPP:
+ case -EINVAL:
case -ECONNREFUSED:
case -ECONNRESET:
case -EHOSTDOWN:
@@ -1198,29 +1250,39 @@
case -ENOBUFS:
case -EPIPE:
case -EPERM:
- status = NFS4ERR_NXIO;
+ *op_status = status = NFS4ERR_NXIO;
break;
case -EACCES:
- status = NFS4ERR_ACCESS;
+ *op_status = status = NFS4ERR_ACCESS;
break;
default:
return;
}
}
- switch (status) {
- case NFS4ERR_DELAY:
- case NFS4ERR_GRACE:
- return;
- default:
- break;
- }
-
mirror = FF_LAYOUT_COMP(lseg, idx);
err = ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
mirror, offset, length, status, opnum,
GFP_NOIO);
- pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode, lseg);
+
+ switch (status) {
+ case NFS4ERR_DELAY:
+ case NFS4ERR_GRACE:
+ break;
+ case NFS4ERR_NXIO:
+ ff_layout_mark_ds_unreachable(lseg, idx);
+ /*
+ * Don't return the layout if this is a read and we still
+ * have layouts to try
+ */
+ if (opnum == OP_READ)
+ break;
+ fallthrough;
+ default:
+ pnfs_error_mark_layout_for_return(lseg->pls_layout->plh_inode,
+ lseg);
+ }
+
dprintk("%s: err %d op %d status %u\n", __func__, err, opnum, status);
}
@@ -1230,24 +1292,23 @@
{
int err;
- trace_nfs4_pnfs_read(hdr, task->tk_status);
- if (task->tk_status < 0)
+ if (task->tk_status < 0) {
ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx,
hdr->args.offset, hdr->args.count,
- hdr->res.op_status, OP_READ,
+ &hdr->res.op_status, OP_READ,
task->tk_status);
+ trace_ff_layout_read_error(hdr);
+ }
+
err = ff_layout_async_handle_error(task, hdr->args.context->state,
hdr->ds_clp, hdr->lseg,
hdr->pgio_mirror_idx);
+ trace_nfs4_pnfs_read(hdr, err);
clear_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags);
switch (err) {
case -NFS4ERR_RESET_TO_PNFS:
- if (ff_layout_choose_best_ds_for_read(hdr->lseg,
- hdr->pgio_mirror_idx + 1,
- &hdr->pgio_mirror_idx))
- goto out_eagain;
set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
return task->tk_status;
case -NFS4ERR_RESET_TO_MDS:
@@ -1291,15 +1352,6 @@
(unsigned long long) NFS_I(inode)->layout->plh_lwb);
}
-static bool
-ff_layout_device_unavailable(struct pnfs_layout_segment *lseg, int idx)
-{
- /* No mirroring for now */
- struct nfs4_deviceid_node *node = FF_LAYOUT_DEVID_NODE(lseg, idx);
-
- return ff_layout_test_devid_unavailable(node);
-}
-
static void ff_layout_read_record_layoutstats_start(struct rpc_task *task,
struct nfs_pgio_header *hdr)
{
@@ -1329,10 +1381,6 @@
if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
rpc_exit(task, -EIO);
return -EIO;
- }
- if (ff_layout_device_unavailable(hdr->lseg, hdr->pgio_mirror_idx)) {
- rpc_exit(task, -EHOSTDOWN);
- return -EAGAIN;
}
ff_layout_read_record_layoutstats_start(task, hdr);
@@ -1398,7 +1446,7 @@
ff_layout_read_record_layoutstats_done(&hdr->task, hdr);
if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags))
- pnfs_read_resend_pnfs(hdr);
+ ff_layout_resend_pnfs_read(hdr);
else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
ff_layout_reset_read(hdr);
pnfs_generic_rw_release(data);
@@ -1411,16 +1459,19 @@
loff_t end_offs = 0;
int err;
- trace_nfs4_pnfs_write(hdr, task->tk_status);
- if (task->tk_status < 0)
+ if (task->tk_status < 0) {
ff_layout_io_track_ds_error(hdr->lseg, hdr->pgio_mirror_idx,
hdr->args.offset, hdr->args.count,
- hdr->res.op_status, OP_WRITE,
+ &hdr->res.op_status, OP_WRITE,
task->tk_status);
+ trace_ff_layout_write_error(hdr);
+ }
+
err = ff_layout_async_handle_error(task, hdr->args.context->state,
hdr->ds_clp, hdr->lseg,
hdr->pgio_mirror_idx);
+ trace_nfs4_pnfs_write(hdr, err);
clear_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
clear_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags);
switch (err) {
@@ -1454,15 +1505,18 @@
{
int err;
- trace_nfs4_pnfs_commit_ds(data, task->tk_status);
- if (task->tk_status < 0)
+ if (task->tk_status < 0) {
ff_layout_io_track_ds_error(data->lseg, data->ds_commit_index,
data->args.offset, data->args.count,
- data->res.op_status, OP_COMMIT,
+ &data->res.op_status, OP_COMMIT,
task->tk_status);
+ trace_ff_layout_commit_error(data);
+ }
+
err = ff_layout_async_handle_error(task, NULL, data->ds_clp,
data->lseg, data->ds_commit_index);
+ trace_nfs4_pnfs_commit_ds(data, err);
switch (err) {
case -NFS4ERR_RESET_TO_PNFS:
pnfs_generic_prepare_to_resend_writes(data);
@@ -1509,11 +1563,6 @@
if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags))) {
rpc_exit(task, -EIO);
return -EIO;
- }
-
- if (ff_layout_device_unavailable(hdr->lseg, hdr->pgio_mirror_idx)) {
- rpc_exit(task, -EHOSTDOWN);
- return -EAGAIN;
}
ff_layout_write_record_layoutstats_start(task, hdr);
@@ -1571,9 +1620,10 @@
struct nfs_pgio_header *hdr = data;
ff_layout_write_record_layoutstats_done(&hdr->task, hdr);
- if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags))
+ if (test_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags)) {
+ ff_layout_send_layouterror(hdr->lseg);
ff_layout_reset_write(hdr, true);
- else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
+ } else if (test_bit(NFS_IOHDR_RESEND_MDS, &hdr->flags))
ff_layout_reset_write(hdr, false);
pnfs_generic_rw_release(data);
}
@@ -1701,7 +1751,8 @@
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
- struct rpc_cred *ds_cred;
+ struct nfs4_ff_layout_mirror *mirror;
+ const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
u32 idx = hdr->pgio_mirror_idx;
int vers;
@@ -1711,20 +1762,21 @@
__func__, hdr->inode->i_ino,
hdr->args.pgbase, (size_t)hdr->args.count, offset);
- ds = nfs4_ff_layout_prepare_ds(lseg, idx, false);
+ mirror = FF_LAYOUT_COMP(lseg, idx);
+ ds = nfs4_ff_layout_prepare_ds(lseg, mirror, false);
if (!ds)
goto out_failed;
- ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
+ ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
hdr->inode);
if (IS_ERR(ds_clnt))
goto out_failed;
- ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
+ ds_cred = ff_layout_get_ds_cred(mirror, &lseg->pls_range, hdr->cred);
if (!ds_cred)
goto out_failed;
- vers = nfs4_ff_layout_ds_version(lseg, idx);
+ vers = nfs4_ff_layout_ds_version(mirror);
dprintk("%s USE DS: %s cl_count %d vers %d\n", __func__,
ds->ds_remotestr, refcount_read(&ds->ds_clp->cl_count), vers);
@@ -1732,13 +1784,11 @@
hdr->pgio_done_cb = ff_layout_read_done_cb;
refcount_inc(&ds->ds_clp->cl_count);
hdr->ds_clp = ds->ds_clp;
- fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
+ fh = nfs4_ff_layout_select_ds_fh(mirror);
if (fh)
hdr->args.fh = fh;
- if (vers == 4 &&
- !nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
- goto out_failed;
+ nfs4_ff_layout_select_ds_stateid(mirror, &hdr->args.stateid);
/*
* Note that if we ever decide to split across DSes,
@@ -1752,12 +1802,15 @@
vers == 3 ? &ff_layout_read_call_ops_v3 :
&ff_layout_read_call_ops_v4,
0, RPC_TASK_SOFTCONN);
- put_rpccred(ds_cred);
+ put_cred(ds_cred);
return PNFS_ATTEMPTED;
out_failed:
if (ff_layout_avoid_mds_available_ds(lseg))
return PNFS_TRY_AGAIN;
+ trace_pnfs_mds_fallback_read_pagelist(hdr->inode,
+ hdr->args.offset, hdr->args.count,
+ IOMODE_READ, NFS_I(hdr->inode)->layout, lseg);
return PNFS_NOT_ATTEMPTED;
}
@@ -1768,26 +1821,28 @@
struct pnfs_layout_segment *lseg = hdr->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
- struct rpc_cred *ds_cred;
+ struct nfs4_ff_layout_mirror *mirror;
+ const struct cred *ds_cred;
loff_t offset = hdr->args.offset;
int vers;
struct nfs_fh *fh;
- int idx = hdr->pgio_mirror_idx;
+ u32 idx = hdr->pgio_mirror_idx;
- ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
+ mirror = FF_LAYOUT_COMP(lseg, idx);
+ ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
if (!ds)
goto out_failed;
- ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
+ ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
hdr->inode);
if (IS_ERR(ds_clnt))
goto out_failed;
- ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
+ ds_cred = ff_layout_get_ds_cred(mirror, &lseg->pls_range, hdr->cred);
if (!ds_cred)
goto out_failed;
- vers = nfs4_ff_layout_ds_version(lseg, idx);
+ vers = nfs4_ff_layout_ds_version(mirror);
dprintk("%s ino %lu sync %d req %zu@%llu DS: %s cl_count %d vers %d\n",
__func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count,
@@ -1798,13 +1853,11 @@
refcount_inc(&ds->ds_clp->cl_count);
hdr->ds_clp = ds->ds_clp;
hdr->ds_commit_idx = idx;
- fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
+ fh = nfs4_ff_layout_select_ds_fh(mirror);
if (fh)
hdr->args.fh = fh;
- if (vers == 4 &&
- !nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid))
- goto out_failed;
+ nfs4_ff_layout_select_ds_stateid(mirror, &hdr->args.stateid);
/*
* Note that if we ever decide to split across DSes,
@@ -1817,12 +1870,15 @@
vers == 3 ? &ff_layout_write_call_ops_v3 :
&ff_layout_write_call_ops_v4,
sync, RPC_TASK_SOFTCONN);
- put_rpccred(ds_cred);
+ put_cred(ds_cred);
return PNFS_ATTEMPTED;
out_failed:
if (ff_layout_avoid_mds_available_ds(lseg))
return PNFS_TRY_AGAIN;
+ trace_pnfs_mds_fallback_write_pagelist(hdr->inode,
+ hdr->args.offset, hdr->args.count,
+ IOMODE_RW, NFS_I(hdr->inode)->layout, lseg);
return PNFS_NOT_ATTEMPTED;
}
@@ -1847,7 +1903,8 @@
struct pnfs_layout_segment *lseg = data->lseg;
struct nfs4_pnfs_ds *ds;
struct rpc_clnt *ds_clnt;
- struct rpc_cred *ds_cred;
+ struct nfs4_ff_layout_mirror *mirror;
+ const struct cred *ds_cred;
u32 idx;
int vers, ret;
struct nfs_fh *fh;
@@ -1857,20 +1914,21 @@
goto out_err;
idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
- ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
+ mirror = FF_LAYOUT_COMP(lseg, idx);
+ ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true);
if (!ds)
goto out_err;
- ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
+ ds_clnt = nfs4_ff_find_or_create_ds_client(mirror, ds->ds_clp,
data->inode);
if (IS_ERR(ds_clnt))
goto out_err;
- ds_cred = ff_layout_get_ds_cred(lseg, idx, data->cred);
+ ds_cred = ff_layout_get_ds_cred(mirror, &lseg->pls_range, data->cred);
if (!ds_cred)
goto out_err;
- vers = nfs4_ff_layout_ds_version(lseg, idx);
+ vers = nfs4_ff_layout_ds_version(mirror);
dprintk("%s ino %lu, how %d cl_count %d vers %d\n", __func__,
data->inode->i_ino, how, refcount_read(&ds->ds_clp->cl_count),
@@ -1887,7 +1945,7 @@
vers == 3 ? &ff_layout_commit_call_ops_v3 :
&ff_layout_commit_call_ops_v4,
how, RPC_TASK_SOFTCONN);
- put_rpccred(ds_cred);
+ put_cred(ds_cred);
return ret;
out_err:
pnfs_generic_prepare_to_resend_writes(data);
@@ -1912,6 +1970,33 @@
return NULL;
return &FF_LAYOUT_FROM_HDR(layout)->commit_info;
+}
+
+static void
+ff_layout_setup_ds_info(struct pnfs_ds_commit_info *fl_cinfo,
+ struct pnfs_layout_segment *lseg)
+{
+ struct nfs4_ff_layout_segment *flseg = FF_LAYOUT_LSEG(lseg);
+ struct inode *inode = lseg->pls_layout->plh_inode;
+ struct pnfs_commit_array *array, *new;
+
+ new = pnfs_alloc_commit_array(flseg->mirror_array_cnt, GFP_NOIO);
+ if (new) {
+ spin_lock(&inode->i_lock);
+ array = pnfs_add_commit_array(fl_cinfo, new, lseg);
+ spin_unlock(&inode->i_lock);
+ if (array != new)
+ pnfs_free_commit_array(new);
+ }
+}
+
+static void
+ff_layout_release_ds_info(struct pnfs_ds_commit_info *fl_cinfo,
+ struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ pnfs_generic_ds_cinfo_destroy(fl_cinfo);
+ spin_unlock(&inode->i_lock);
}
static void
@@ -2034,7 +2119,7 @@
dprintk("%s: Begin\n", __func__);
- xdr_init_encode(&tmp_xdr, &tmp_buf, NULL);
+ xdr_init_encode(&tmp_xdr, &tmp_buf, NULL, NULL);
ff_layout_encode_ioerr(&tmp_xdr, args, ff_args);
ff_layout_encode_iostats_array(&tmp_xdr, args, ff_args);
@@ -2099,6 +2184,52 @@
out_nomem:
return -ENOMEM;
}
+
+#ifdef CONFIG_NFS_V4_2
+void
+ff_layout_send_layouterror(struct pnfs_layout_segment *lseg)
+{
+ struct pnfs_layout_hdr *lo = lseg->pls_layout;
+ struct nfs42_layout_error *errors;
+ LIST_HEAD(head);
+
+ if (!nfs_server_capable(lo->plh_inode, NFS_CAP_LAYOUTERROR))
+ return;
+ ff_layout_fetch_ds_ioerr(lo, &lseg->pls_range, &head, -1);
+ if (list_empty(&head))
+ return;
+
+ errors = kmalloc_array(NFS42_LAYOUTERROR_MAX,
+ sizeof(*errors), GFP_NOFS);
+ if (errors != NULL) {
+ const struct nfs4_ff_layout_ds_err *pos;
+ size_t n = 0;
+
+ list_for_each_entry(pos, &head, list) {
+ errors[n].offset = pos->offset;
+ errors[n].length = pos->length;
+ nfs4_stateid_copy(&errors[n].stateid, &pos->stateid);
+ errors[n].errors[0].dev_id = pos->deviceid;
+ errors[n].errors[0].status = pos->status;
+ errors[n].errors[0].opnum = pos->opnum;
+ n++;
+ if (!list_is_last(&pos->list, &head) &&
+ n < NFS42_LAYOUTERROR_MAX)
+ continue;
+ if (nfs42_proc_layouterror(lseg, errors, n) < 0)
+ break;
+ n = 0;
+ }
+ kfree(errors);
+ }
+ ff_layout_free_ds_ioerr(&head);
+}
+#else
+void
+ff_layout_send_layouterror(struct pnfs_layout_segment *lseg)
+{
+}
+#endif
static int
ff_layout_ntop4(const struct sockaddr *sap, char *buf, const size_t buflen)
@@ -2353,11 +2484,22 @@
return 0;
}
+static const struct pnfs_commit_ops ff_layout_commit_ops = {
+ .setup_ds_info = ff_layout_setup_ds_info,
+ .release_ds_info = ff_layout_release_ds_info,
+ .mark_request_commit = pnfs_layout_mark_request_commit,
+ .clear_request_commit = pnfs_generic_clear_request_commit,
+ .scan_commit_lists = pnfs_generic_scan_commit_lists,
+ .recover_commit_reqs = pnfs_generic_recover_commit_reqs,
+ .commit_pagelist = ff_layout_commit_pagelist,
+};
+
static struct pnfs_layoutdriver_type flexfilelayout_type = {
.id = LAYOUT_FLEX_FILES,
.name = "LAYOUT_FLEX_FILES",
.owner = THIS_MODULE,
.flags = PNFS_LAYOUTGET_ON_OPEN,
+ .max_layoutget_response = 4096, /* 1 page or so... */
.set_layoutdriver = ff_layout_set_layoutdriver,
.alloc_layout_hdr = ff_layout_alloc_layout_hdr,
.free_layout_hdr = ff_layout_free_layout_hdr,
@@ -2368,11 +2510,6 @@
.pg_write_ops = &ff_layout_pg_write_ops,
.get_ds_info = ff_layout_get_ds_info,
.free_deviceid_node = ff_layout_free_deviceid_node,
- .mark_request_commit = pnfs_layout_mark_request_commit,
- .clear_request_commit = pnfs_generic_clear_request_commit,
- .scan_commit_lists = pnfs_generic_scan_commit_lists,
- .recover_commit_reqs = pnfs_generic_recover_commit_reqs,
- .commit_pagelist = ff_layout_commit_pagelist,
.read_pagelist = ff_layout_read_pagelist,
.write_pagelist = ff_layout_write_pagelist,
.alloc_deviceid_node = ff_layout_alloc_deviceid_node,
@@ -2385,11 +2522,6 @@
{
printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Registering...\n",
__func__);
- if (!ff_zero_group) {
- ff_zero_group = groups_alloc(0);
- if (!ff_zero_group)
- return -ENOMEM;
- }
return pnfs_register_layoutdriver(&flexfilelayout_type);
}
@@ -2398,10 +2530,6 @@
printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Unregistering...\n",
__func__);
pnfs_unregister_layoutdriver(&flexfilelayout_type);
- if (ff_zero_group) {
- put_group_info(ff_zero_group);
- ff_zero_group = NULL;
- }
}
MODULE_ALIAS("nfs-layouttype4-4");
@@ -2411,3 +2539,7 @@
module_init(nfs4flexfilelayout_init);
module_exit(nfs4flexfilelayout_exit);
+
+module_param(io_maxretrans, ushort, 0644);
+MODULE_PARM_DESC(io_maxretrans, "The number of times the NFSv4.1 client "
+ "retries an I/O request before returning an error. ");
--
Gitblit v1.6.2