From: Alexander Aring <aahringo@redhat.com>
To: teigland@redhat.com
Cc: gfs2@lists.linux.dev, song@kernel.org, yukuai3@huawei.com,
linux-raid@vger.kernel.org, aahringo@redhat.com
Subject: [PATCH dlm/next 6/8] dlm: implement LSFL_SOFTIRQ_SAFE
Date: Mon, 3 Jun 2024 17:55:56 -0400 [thread overview]
Message-ID: <20240603215558.2722969-7-aahringo@redhat.com> (raw)
In-Reply-To: <20240603215558.2722969-1-aahringo@redhat.com>
This patch implements to allow to directly call ast and bast callbacks
in the context as soon they arrive. Currently every ast and bast callback
of a kernel lockspace callback is queued through a workqueue to provide
the dlm user a different context. However some users can't currently handle
the strongest context of ast/bast which is a softirq context but new users
should directly implement their dlm application to run in softirq context.
Another mentioned requirement that is more unlikely that a current DLM
runs into is a lock recursion if a lock if the same lock is held in the
callback and when the DLM API is called.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
---
fs/dlm/ast.c | 157 +++++++++++++++++++++++++++---------------
fs/dlm/ast.h | 11 ++-
fs/dlm/dlm_internal.h | 1 +
fs/dlm/lockspace.c | 3 +
fs/dlm/user.c | 38 +++++-----
5 files changed, 126 insertions(+), 84 deletions(-)
diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c
index 52ce27031314..742b30b61c19 100644
--- a/fs/dlm/ast.c
+++ b/fs/dlm/ast.c
@@ -18,35 +18,52 @@
#include "user.h"
#include "ast.h"
-static void dlm_callback_work(struct work_struct *work)
+static void dlm_run_callback(uint32_t ls_id, uint32_t lkb_id, int8_t mode,
+ uint32_t flags, uint8_t sb_flags, int sb_status,
+ struct dlm_lksb *lksb,
+ void (*astfn)(void *astparam),
+ void (*bastfn)(void *astparam, int mode),
+ void *astparam, const char *res_name,
+ size_t res_length)
{
- struct dlm_callback *cb = container_of(work, struct dlm_callback, work);
-
- if (cb->flags & DLM_CB_BAST) {
- trace_dlm_bast(cb->ls_id, cb->lkb_id, cb->mode, cb->res_name,
- cb->res_length);
- cb->bastfn(cb->astparam, cb->mode);
- } else if (cb->flags & DLM_CB_CAST) {
- trace_dlm_ast(cb->ls_id, cb->lkb_id, cb->sb_status,
- cb->sb_flags, cb->res_name, cb->res_length);
- cb->lkb_lksb->sb_status = cb->sb_status;
- cb->lkb_lksb->sb_flags = cb->sb_flags;
- cb->astfn(cb->astparam);
+ if (flags & DLM_CB_BAST) {
+ trace_dlm_bast(ls_id, lkb_id, mode, res_name, res_length);
+ bastfn(astparam, mode);
+ } else if (flags & DLM_CB_CAST) {
+ trace_dlm_ast(ls_id, lkb_id, sb_status, sb_flags, res_name,
+ res_length);
+ lksb->sb_status = sb_status;
+ lksb->sb_flags = sb_flags;
+ astfn(astparam);
}
+}
+static void dlm_do_callback(struct dlm_callback *cb)
+{
+ dlm_run_callback(cb->ls_id, cb->lkb_id, cb->mode, cb->flags,
+ cb->sb_flags, cb->sb_status, cb->lkb_lksb,
+ cb->astfn, cb->bastfn, cb->astparam,
+ cb->res_name, cb->res_length);
dlm_free_cb(cb);
}
-int dlm_queue_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
- int status, uint32_t sbflags,
- struct dlm_callback **cb)
+static void dlm_callback_work(struct work_struct *work)
+{
+ struct dlm_callback *cb = container_of(work, struct dlm_callback, work);
+
+ dlm_do_callback(cb);
+}
+
+bool dlm_may_skip_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
+ int status, uint32_t sbflags, int *copy_lvb)
{
struct dlm_rsb *rsb = lkb->lkb_resource;
- int rv = DLM_ENQUEUE_CALLBACK_SUCCESS;
struct dlm_ls *ls = rsb->res_ls;
- int copy_lvb = 0;
int prev_mode;
+ if (copy_lvb)
+ *copy_lvb = 0;
+
if (flags & DLM_CB_BAST) {
/* if cb is a bast, it should be skipped if the blocking mode is
* compatible with the last granted mode
@@ -56,7 +73,7 @@ int dlm_queue_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
log_debug(ls, "skip %x bast mode %d for cast mode %d",
lkb->lkb_id, mode,
lkb->lkb_last_cast_cb_mode);
- goto out;
+ return true;
}
}
@@ -74,7 +91,7 @@ int dlm_queue_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
(prev_mode > mode && prev_mode > DLM_LOCK_PR)) {
log_debug(ls, "skip %x add bast mode %d for bast mode %d",
lkb->lkb_id, mode, prev_mode);
- goto out;
+ return true;
}
}
@@ -85,8 +102,10 @@ int dlm_queue_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
prev_mode = lkb->lkb_last_cast_cb_mode;
if (!status && lkb->lkb_lksb->sb_lvbptr &&
- dlm_lvb_operations[prev_mode + 1][mode + 1])
- copy_lvb = 1;
+ dlm_lvb_operations[prev_mode + 1][mode + 1]) {
+ if (copy_lvb)
+ *copy_lvb = 1;
+ }
}
lkb->lkb_last_cast_cb_mode = mode;
@@ -96,11 +115,19 @@ int dlm_queue_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
lkb->lkb_last_cb_mode = mode;
lkb->lkb_last_cb_flags = flags;
+ return false;
+}
+
+int dlm_get_cb(struct dlm_lkb *lkb, uint32_t flags, int mode,
+ int status, uint32_t sbflags,
+ struct dlm_callback **cb)
+{
+ struct dlm_rsb *rsb = lkb->lkb_resource;
+ struct dlm_ls *ls = rsb->res_ls;
+
*cb = dlm_allocate_cb();
- if (!*cb) {
- rv = DLM_ENQUEUE_CALLBACK_FAILURE;
- goto out;
- }
+ if (WARN_ON_ONCE(!*cb))
+ return -ENOMEM;
/* for tracing */
(*cb)->lkb_id = lkb->lkb_id;
@@ -112,19 +139,34 @@ int dlm_queue_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
(*cb)->mode = mode;
(*cb)->sb_status = status;
(*cb)->sb_flags = (sbflags & 0x000000FF);
- (*cb)->copy_lvb = copy_lvb;
(*cb)->lkb_lksb = lkb->lkb_lksb;
- rv = DLM_ENQUEUE_CALLBACK_NEED_SCHED;
+ return 0;
+}
+
+static int dlm_get_queue_cb(struct dlm_lkb *lkb, uint32_t flags, int mode,
+ int status, uint32_t sbflags,
+ struct dlm_callback **cb)
+{
+ int rv;
-out:
- return rv;
+ rv = dlm_get_cb(lkb, flags, mode, status, sbflags, cb);
+ if (rv)
+ return rv;
+
+ (*cb)->astfn = lkb->lkb_astfn;
+ (*cb)->bastfn = lkb->lkb_bastfn;
+ (*cb)->astparam = lkb->lkb_astparam;
+ INIT_WORK(&(*cb)->work, dlm_callback_work);
+
+ return 0;
}
void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
- uint32_t sbflags)
+ uint32_t sbflags)
{
- struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+ struct dlm_rsb *rsb = lkb->lkb_resource;
+ struct dlm_ls *ls = rsb->res_ls;
struct dlm_callback *cb;
int rv;
@@ -133,35 +175,34 @@ void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
return;
}
- rv = dlm_queue_lkb_callback(lkb, flags, mode, status, sbflags,
- &cb);
- switch (rv) {
- case DLM_ENQUEUE_CALLBACK_NEED_SCHED:
- cb->astfn = lkb->lkb_astfn;
- cb->bastfn = lkb->lkb_bastfn;
- cb->astparam = lkb->lkb_astparam;
- INIT_WORK(&cb->work, dlm_callback_work);
-
- spin_lock_bh(&ls->ls_cb_lock);
- if (test_bit(LSFL_CB_DELAY, &ls->ls_flags))
+ if (dlm_may_skip_callback(lkb, flags, mode, status, sbflags, NULL))
+ return;
+
+ spin_lock_bh(&ls->ls_cb_lock);
+ if (test_bit(LSFL_CB_DELAY, &ls->ls_flags)) {
+ rv = dlm_get_queue_cb(lkb, flags, mode, status, sbflags, &cb);
+ if (!rv)
list_add(&cb->list, &ls->ls_cb_delay);
- else
- queue_work(ls->ls_callback_wq, &cb->work);
- spin_unlock_bh(&ls->ls_cb_lock);
- break;
- case DLM_ENQUEUE_CALLBACK_SUCCESS:
- break;
- case DLM_ENQUEUE_CALLBACK_FAILURE:
- fallthrough;
- default:
- WARN_ON_ONCE(1);
- break;
+ } else {
+ if (test_bit(LSFL_SOFTIRQ, &ls->ls_flags)) {
+ dlm_run_callback(ls->ls_global_id, lkb->lkb_id, mode, flags,
+ sbflags, status, lkb->lkb_lksb,
+ lkb->lkb_astfn, lkb->lkb_bastfn,
+ lkb->lkb_astparam, rsb->res_name,
+ rsb->res_length);
+ } else {
+ rv = dlm_get_queue_cb(lkb, flags, mode, status, sbflags, &cb);
+ if (!rv)
+ queue_work(ls->ls_callback_wq, &cb->work);
+ }
}
+ spin_unlock_bh(&ls->ls_cb_lock);
}
int dlm_callback_start(struct dlm_ls *ls)
{
- if (!test_bit(LSFL_FS, &ls->ls_flags))
+ if (!test_bit(LSFL_FS, &ls->ls_flags) ||
+ test_bit(LSFL_SOFTIRQ, &ls->ls_flags))
return 0;
ls->ls_callback_wq = alloc_ordered_workqueue("dlm_callback",
@@ -207,7 +248,11 @@ void dlm_callback_resume(struct dlm_ls *ls)
spin_lock_bh(&ls->ls_cb_lock);
list_for_each_entry_safe(cb, safe, &ls->ls_cb_delay, list) {
list_del(&cb->list);
- queue_work(ls->ls_callback_wq, &cb->work);
+ if (test_bit(LSFL_SOFTIRQ, &ls->ls_flags))
+ dlm_do_callback(cb);
+ else
+ queue_work(ls->ls_callback_wq, &cb->work);
+
count++;
if (count == MAX_CB_QUEUE)
break;
diff --git a/fs/dlm/ast.h b/fs/dlm/ast.h
index 9093ff043bee..e2b86845d331 100644
--- a/fs/dlm/ast.h
+++ b/fs/dlm/ast.h
@@ -11,12 +11,11 @@
#ifndef __ASTD_DOT_H__
#define __ASTD_DOT_H__
-#define DLM_ENQUEUE_CALLBACK_NEED_SCHED 1
-#define DLM_ENQUEUE_CALLBACK_SUCCESS 0
-#define DLM_ENQUEUE_CALLBACK_FAILURE -1
-int dlm_queue_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
- int status, uint32_t sbflags,
- struct dlm_callback **cb);
+bool dlm_may_skip_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
+ int status, uint32_t sbflags, int *copy_lvb);
+int dlm_get_cb(struct dlm_lkb *lkb, uint32_t flags, int mode,
+ int status, uint32_t sbflags,
+ struct dlm_callback **cb);
void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
uint32_t sbflags);
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index 3b026d80aa2b..e299d8d4d971 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -727,6 +727,7 @@ struct dlm_ls {
#define LSFL_NODIR 10
#define LSFL_RECV_MSG_BLOCKED 11
#define LSFL_FS 12
+#define LSFL_SOFTIRQ 13
#define DLM_PROC_FLAGS_CLOSING 1
#define DLM_PROC_FLAGS_COMPAT 2
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 51f9516b710d..5b3a4c32ac99 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -407,6 +407,9 @@ static int new_lockspace(const char *name, const char *cluster,
ls->ls_ops_arg = ops_arg;
}
+ if (flags & DLM_LSFL_SOFTIRQ)
+ set_bit(LSFL_SOFTIRQ, &ls->ls_flags);
+
/* ls_exflags are forced to match among nodes, and we don't
* need to require all nodes to have some flags set
*/
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index f6635a5314f4..5cb3896be826 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -182,7 +182,7 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
struct dlm_user_args *ua;
struct dlm_user_proc *proc;
struct dlm_callback *cb;
- int rv;
+ int rv, copy_lvb;
if (test_bit(DLM_DFL_ORPHAN_BIT, &lkb->lkb_dflags) ||
test_bit(DLM_IFL_DEAD_BIT, &lkb->lkb_iflags))
@@ -213,28 +213,22 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
spin_lock_bh(&proc->asts_spin);
- rv = dlm_queue_lkb_callback(lkb, flags, mode, status, sbflags, &cb);
- switch (rv) {
- case DLM_ENQUEUE_CALLBACK_NEED_SCHED:
- cb->ua = *ua;
- cb->lkb_lksb = &cb->ua.lksb;
- if (cb->copy_lvb) {
- memcpy(cb->lvbptr, ua->lksb.sb_lvbptr,
- DLM_USER_LVB_LEN);
- cb->lkb_lksb->sb_lvbptr = cb->lvbptr;
+ if (!dlm_may_skip_callback(lkb, flags, mode, status, sbflags,
+ ©_lvb)) {
+ rv = dlm_get_cb(lkb, flags, mode, status, sbflags, &cb);
+ if (!rv) {
+ cb->copy_lvb = copy_lvb;
+ cb->ua = *ua;
+ cb->lkb_lksb = &cb->ua.lksb;
+ if (copy_lvb) {
+ memcpy(cb->lvbptr, ua->lksb.sb_lvbptr,
+ DLM_USER_LVB_LEN);
+ cb->lkb_lksb->sb_lvbptr = cb->lvbptr;
+ }
+
+ list_add_tail(&cb->list, &proc->asts);
+ wake_up_interruptible(&proc->wait);
}
-
- list_add_tail(&cb->list, &proc->asts);
- wake_up_interruptible(&proc->wait);
- break;
- case DLM_ENQUEUE_CALLBACK_SUCCESS:
- break;
- case DLM_ENQUEUE_CALLBACK_FAILURE:
- fallthrough;
- default:
- spin_unlock_bh(&proc->asts_spin);
- WARN_ON_ONCE(1);
- goto out;
}
spin_unlock_bh(&proc->asts_spin);
--
2.43.0
next prev parent reply other threads:[~2024-06-03 21:56 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-03 21:55 [PATCH dlm/next 0/8] dlm: md: introduce DLM_LSFL_SOFTIRQ_SAFE Alexander Aring
2024-06-03 21:55 ` [PATCH dlm/next 1/8] dlm: using rcu to avoid rsb lookup again Alexander Aring
2024-06-03 21:55 ` [PATCH dlm/next 2/8] dlm: remove struct field with the same meaning Alexander Aring
2024-06-10 14:17 ` Alexander Aring
2024-06-03 21:55 ` [PATCH dlm/next 3/8] dlm: use is_master() on checks if we are the master Alexander Aring
2024-06-03 21:55 ` [PATCH dlm/next 4/8] dlm: use LSFL_FS to check if it's a kernel lockspace Alexander Aring
2024-06-03 21:55 ` [PATCH dlm/next 5/8] dlm: introduce DLM_LSFL_SOFTIRQ_SAFE Alexander Aring
2024-06-03 21:55 ` Alexander Aring [this message]
2024-06-03 21:55 ` [PATCH dlm/next 7/8] dlm: convert ls_cb_lock to rwlock Alexander Aring
2024-06-03 21:55 ` [PATCH dlm/next 8/8] md-cluster: use DLM_LSFL_SOFTIRQ for dlm_new_lockspace() Alexander Aring
2024-06-05 18:54 ` Alexander Aring
2024-06-06 2:48 ` Heming Zhao
2024-06-06 14:33 ` Alexander Aring
2024-06-06 22:55 ` Heming Zhao
2024-06-08 4:21 ` Song Liu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240603215558.2722969-7-aahringo@redhat.com \
--to=aahringo@redhat.com \
--cc=gfs2@lists.linux.dev \
--cc=linux-raid@vger.kernel.org \
--cc=song@kernel.org \
--cc=teigland@redhat.com \
--cc=yukuai3@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).