4 files changed, 449 insertions, 0 deletions

diff --git a/fs/dlm/Makefile b/fs/dlm/Makefile
index d248e60951ba..ca1c9124c8ce 100644
--- a/fs/dlm/Makefile
+++ b/fs/dlm/Makefile
@@ -10,6 +10,7 @@ dlm-y :=			ast.o \
                                 midcomms.o \
                                 netlink.o \
                                 lowcomms.o \
+                                plock.o \
                                 rcom.o \
                                 recover.o \
                                 recoverd.o \
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index c70c8e58358f..caa1581e158f 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -582,6 +582,8 @@ static inline int dlm_no_directory(struct dlm_ls *ls)
 int dlm_netlink_init(void);
 void dlm_netlink_exit(void);
 void dlm_timeout_warn(struct dlm_lkb *lkb);
+int dlm_plock_init(void);
+void dlm_plock_exit(void);
 
 #ifdef CONFIG_DLM_DEBUG
 int dlm_register_debugfs(void);
diff --git a/fs/dlm/main.c b/fs/dlm/main.c
index 58487fb95a4c..b80e0aa3cfa5 100644
--- a/fs/dlm/main.c
+++ b/fs/dlm/main.c
@@ -46,10 +46,16 @@ static int __init init_dlm(void)
         if (error)
                 goto out_user;
 
+        error = dlm_plock_init();
+        if (error)
+                goto out_netlink;
+
         printk("DLM (built %s %s) installed\n", __DATE__, __TIME__);
 
         return 0;
 
+ out_netlink:
+        dlm_netlink_exit();
  out_user:
         dlm_user_exit();
  out_debug:
@@ -66,6 +72,7 @@ static int __init init_dlm(void)
 
 static void __exit exit_dlm(void)
 {
+        dlm_plock_exit();
         dlm_netlink_exit();
         dlm_user_exit();
         dlm_config_exit();
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
new file mode 100644
index 000000000000..d6d6e370f89c
--- /dev/null
+++ b/fs/dlm/plock.c
@@ -0,0 +1,439 @@
+/*
+ * Copyright (C) 2005-2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License version 2.
+ */
+
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/poll.h>
+#include <linux/dlm.h>
+#include <linux/dlm_plock.h>
+
+#include "dlm_internal.h"
+#include "lockspace.h"
+
+static spinlock_t ops_lock;
+static struct list_head send_list;
+static struct list_head recv_list;
+static wait_queue_head_t send_wq;
+static wait_queue_head_t recv_wq;
+
+struct plock_op {
+        struct list_head list;
+        int done;
+        struct dlm_plock_info info;
+};
+
+struct plock_xop {
+        struct plock_op xop;
+        void *callback;
+        void *fl;
+        void *file;
+        struct file_lock flc;
+};
+
+
+static inline void set_version(struct dlm_plock_info *info)
+{
+        info->version[0] = DLM_PLOCK_VERSION_MAJOR;
+        info->version[1] = DLM_PLOCK_VERSION_MINOR;
+        info->version[2] = DLM_PLOCK_VERSION_PATCH;
+}
+
+static int check_version(struct dlm_plock_info *info)
+{
+        if ((DLM_PLOCK_VERSION_MAJOR != info->version[0]) ||
+            (DLM_PLOCK_VERSION_MINOR < info->version[1])) {
+                log_print("plock device version mismatch: "
+                          "kernel (%u.%u.%u), user (%u.%u.%u)",
+                          DLM_PLOCK_VERSION_MAJOR,
+                          DLM_PLOCK_VERSION_MINOR,
+                          DLM_PLOCK_VERSION_PATCH,
+                          info->version[0],
+                          info->version[1],
+                          info->version[2]);
+                return -EINVAL;
+        }
+        return 0;
+}
+
+static void send_op(struct plock_op *op)
+{
+        set_version(&op->info);
+        INIT_LIST_HEAD(&op->list);
+        spin_lock(&ops_lock);
+        list_add_tail(&op->list, &send_list);
+        spin_unlock(&ops_lock);
+        wake_up(&send_wq);
+}
+
+int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
+                   int cmd, struct file_lock *fl)
+{
+        struct dlm_ls *ls;
+        struct plock_op *op;
+        struct plock_xop *xop;
+        int rv;
+
+        ls = dlm_find_lockspace_local(lockspace);
+        if (!ls)
+                return -EINVAL;
+
+        xop = kzalloc(sizeof(*xop), GFP_KERNEL);
+        if (!xop) {
+                rv = -ENOMEM;
+                goto out;
+        }
+
+        op = &xop->xop;
+        op->info.optype         = DLM_PLOCK_OP_LOCK;
+        op->info.pid            = fl->fl_pid;
+        op->info.ex             = (fl->fl_type == F_WRLCK);
+        op->info.wait           = IS_SETLKW(cmd);
+        op->info.fsid           = ls->ls_global_id;
+        op->info.number         = number;
+        op->info.start          = fl->fl_start;
+        op->info.end            = fl->fl_end;
+        if (fl->fl_lmops && fl->fl_lmops->fl_grant) {
+                /* fl_owner is lockd which doesn't distinguish
+                   processes on the nfs client */
+                op->info.owner  = (__u64) fl->fl_pid;
+                xop->callback   = fl->fl_lmops->fl_grant;
+                locks_init_lock(&xop->flc);
+                locks_copy_lock(&xop->flc, fl);
+                xop->fl         = fl;
+                xop->file       = file;
+        } else {
+                op->info.owner  = (__u64)(long) fl->fl_owner;
+                xop->callback   = NULL;
+        }
+
+        send_op(op);
+
+        if (xop->callback == NULL)
+                wait_event(recv_wq, (op->done != 0));
+        else {
+                rv = -EINPROGRESS;
+                goto out;
+        }
+
+        spin_lock(&ops_lock);
+        if (!list_empty(&op->list)) {
+                log_error(ls, "dlm_posix_lock: op on list %llx",
+                          (unsigned long long)number);
+                list_del(&op->list);
+        }
+        spin_unlock(&ops_lock);
+
+        rv = op->info.rv;
+
+        if (!rv) {
+                if (posix_lock_file_wait(file, fl) < 0)
+                        log_error(ls, "dlm_posix_lock: vfs lock error %llx",
+                                  (unsigned long long)number);
+        }
+
+        kfree(xop);
+out:
+        dlm_put_lockspace(ls);
+        return rv;
+}
+EXPORT_SYMBOL_GPL(dlm_posix_lock);
+
+/* Returns failure iff a succesful lock operation should be canceled */
+static int dlm_plock_callback(struct plock_op *op)
+{
+        struct file *file;
+        struct file_lock *fl;
+        struct file_lock *flc;
+        int (*notify)(void *, void *, int) = NULL;
+        struct plock_xop *xop = (struct plock_xop *)op;
+        int rv = 0;
+
+        spin_lock(&ops_lock);
+        if (!list_empty(&op->list)) {
+                log_print("dlm_plock_callback: op on list %llx",
+                          (unsigned long long)op->info.number);
+                list_del(&op->list);
+        }
+        spin_unlock(&ops_lock);
+
+        /* check if the following 2 are still valid or make a copy */
+        file = xop->file;
+        flc = &xop->flc;
+        fl = xop->fl;
+        notify = xop->callback;
+
+        if (op->info.rv) {
+                notify(flc, NULL, op->info.rv);
+                goto out;
+        }
+
+        /* got fs lock; bookkeep locally as well: */
+        flc->fl_flags &= ~FL_SLEEP;
+        if (posix_lock_file(file, flc, NULL)) {
+                /*
+                 * This can only happen in the case of kmalloc() failure.
+                 * The filesystem's own lock is the authoritative lock,
+                 * so a failure to get the lock locally is not a disaster.
+                 * As long as the fs cannot reliably cancel locks (especially
+                 * in a low-memory situation), we're better off ignoring
+                 * this failure than trying to recover.
+                 */
+                log_print("dlm_plock_callback: vfs lock error %llx file %p fl %p",
+                          (unsigned long long)op->info.number, file, fl);
+        }
+
+        rv = notify(flc, NULL, 0);
+        if (rv) {
+                /* XXX: We need to cancel the fs lock here: */
+                log_print("dlm_plock_callback: lock granted after lock request "
+                          "failed; dangling lock!\n");
+                goto out;
+        }
+
+out:
+        kfree(xop);
+        return rv;
+}
+
+int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
+                     struct file_lock *fl)
+{
+        struct dlm_ls *ls;
+        struct plock_op *op;
+        int rv;
+
+        ls = dlm_find_lockspace_local(lockspace);
+        if (!ls)
+                return -EINVAL;
+
+        op = kzalloc(sizeof(*op), GFP_KERNEL);
+        if (!op) {
+                rv = -ENOMEM;
+                goto out;
+        }
+
+        if (posix_lock_file_wait(file, fl) < 0)
+                log_error(ls, "dlm_posix_unlock: vfs unlock error %llx",
+                          (unsigned long long)number);
+
+        op->info.optype         = DLM_PLOCK_OP_UNLOCK;
+        op->info.pid            = fl->fl_pid;
+        op->info.fsid           = ls->ls_global_id;
+        op->info.number         = number;
+        op->info.start          = fl->fl_start;
+        op->info.end            = fl->fl_end;
+        if (fl->fl_lmops && fl->fl_lmops->fl_grant)
+                op->info.owner  = (__u64) fl->fl_pid;
+        else
+                op->info.owner  = (__u64)(long) fl->fl_owner;
+
+        send_op(op);
+        wait_event(recv_wq, (op->done != 0));
+
+        spin_lock(&ops_lock);
+        if (!list_empty(&op->list)) {
+                log_error(ls, "dlm_posix_unlock: op on list %llx",
+                          (unsigned long long)number);
+                list_del(&op->list);
+        }
+        spin_unlock(&ops_lock);
+
+        rv = op->info.rv;
+
+        if (rv == -ENOENT)
+                rv = 0;
+
+        kfree(op);
+out:
+        dlm_put_lockspace(ls);
+        return rv;
+}
+EXPORT_SYMBOL_GPL(dlm_posix_unlock);
+
+int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
+                  struct file_lock *fl)
+{
+        struct dlm_ls *ls;
+        struct plock_op *op;
+        int rv;
+
+        ls = dlm_find_lockspace_local(lockspace);
+        if (!ls)
+                return -EINVAL;
+
+        op = kzalloc(sizeof(*op), GFP_KERNEL);
+        if (!op) {
+                rv = -ENOMEM;
+                goto out;
+        }
+
+        op->info.optype         = DLM_PLOCK_OP_GET;
+        op->info.pid            = fl->fl_pid;
+        op->info.ex             = (fl->fl_type == F_WRLCK);
+        op->info.fsid           = ls->ls_global_id;
+        op->info.number         = number;
+        op->info.start          = fl->fl_start;
+        op->info.end            = fl->fl_end;
+        if (fl->fl_lmops && fl->fl_lmops->fl_grant)
+                op->info.owner  = (__u64) fl->fl_pid;
+        else
+                op->info.owner  = (__u64)(long) fl->fl_owner;
+
+        send_op(op);
+        wait_event(recv_wq, (op->done != 0));
+
+        spin_lock(&ops_lock);
+        if (!list_empty(&op->list)) {
+                log_error(ls, "dlm_posix_get: op on list %llx",
+                          (unsigned long long)number);
+                list_del(&op->list);
+        }
+        spin_unlock(&ops_lock);
+
+        /* info.rv from userspace is 1 for conflict, 0 for no-conflict,
+           -ENOENT if there are no locks on the file */
+
+        rv = op->info.rv;
+
+        fl->fl_type = F_UNLCK;
+        if (rv == -ENOENT)
+                rv = 0;
+        else if (rv > 0) {
+                fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
+                fl->fl_pid = op->info.pid;
+                fl->fl_start = op->info.start;
+                fl->fl_end = op->info.end;
+                rv = 0;
+        }
+
+        kfree(op);
+out:
+        dlm_put_lockspace(ls);
+        return rv;
+}
+EXPORT_SYMBOL_GPL(dlm_posix_get);
+
+/* a read copies out one plock request from the send list */
+static ssize_t dev_read(struct file *file, char __user *u, size_t count,
+                        loff_t *ppos)
+{
+        struct dlm_plock_info info;
+        struct plock_op *op = NULL;
+
+        if (count < sizeof(info))
+                return -EINVAL;
+
+        spin_lock(&ops_lock);
+        if (!list_empty(&send_list)) {
+                op = list_entry(send_list.next, struct plock_op, list);
+                list_move(&op->list, &recv_list);
+                memcpy(&info, &op->info, sizeof(info));
+        }
+        spin_unlock(&ops_lock);
+
+        if (!op)
+                return -EAGAIN;
+
+        if (copy_to_user(u, &info, sizeof(info)))
+                return -EFAULT;
+        return sizeof(info);
+}
+
+/* a write copies in one plock result that should match a plock_op
+   on the recv list */
+static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
+                         loff_t *ppos)
+{
+        struct dlm_plock_info info;
+        struct plock_op *op;
+        int found = 0;
+
+        if (count != sizeof(info))
+                return -EINVAL;
+
+        if (copy_from_user(&info, u, sizeof(info)))
+                return -EFAULT;
+
+        if (check_version(&info))
+                return -EINVAL;
+
+        spin_lock(&ops_lock);
+        list_for_each_entry(op, &recv_list, list) {
+                if (op->info.fsid == info.fsid && op->info.number == info.number &&
+                    op->info.owner == info.owner) {
+                        list_del_init(&op->list);
+                        found = 1;
+                        op->done = 1;
+                        memcpy(&op->info, &info, sizeof(info));
+                        break;
+                }
+        }
+        spin_unlock(&ops_lock);
+
+        if (found) {
+                struct plock_xop *xop;
+                xop = (struct plock_xop *)op;
+                if (xop->callback)
+                        count = dlm_plock_callback(op);
+                else
+                        wake_up(&recv_wq);
+        } else
+                log_print("dev_write no op %x %llx", info.fsid,
+                          (unsigned long long)info.number);
+        return count;
+}
+
+static unsigned int dev_poll(struct file *file, poll_table *wait)
+{
+        unsigned int mask = 0;
+
+        poll_wait(file, &send_wq, wait);
+
+        spin_lock(&ops_lock);
+        if (!list_empty(&send_list))
+                mask = POLLIN | POLLRDNORM;
+        spin_unlock(&ops_lock);
+
+        return mask;
+}
+
+static const struct file_operations dev_fops = {
+        .read    = dev_read,
+        .write   = dev_write,
+        .poll    = dev_poll,
+        .owner   = THIS_MODULE
+};
+
+static struct miscdevice plock_dev_misc = {
+        .minor = MISC_DYNAMIC_MINOR,
+        .name = DLM_PLOCK_MISC_NAME,
+        .fops = &dev_fops
+};
+
+int dlm_plock_init(void)
+{
+        int rv;
+
+        spin_lock_init(&ops_lock);
+        INIT_LIST_HEAD(&send_list);
+        INIT_LIST_HEAD(&recv_list);
+        init_waitqueue_head(&send_wq);
+        init_waitqueue_head(&recv_wq);
+
+        rv = misc_register(&plock_dev_misc);
+        if (rv)
+                log_print("dlm_plock_init: misc_register failed %d", rv);
+        return rv;
+}
+
+void dlm_plock_exit(void)
+{
+        if (misc_deregister(&plock_dev_misc) < 0)
+                log_print("dlm_plock_exit: misc_deregister failed");
+}
+