summaryrefslogtreecommitdiff
path: root/fs/ocfs2/cluster
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ocfs2/cluster')
-rw-r--r--fs/ocfs2/cluster/heartbeat.c134
-rw-r--r--fs/ocfs2/cluster/masklog.h2
-rw-r--r--fs/ocfs2/cluster/netdebug.c40
-rw-r--r--fs/ocfs2/cluster/quorum.c34
-rw-r--r--fs/ocfs2/cluster/tcp.c69
5 files changed, 151 insertions, 128 deletions
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 60b97c92e2b2..724350925aff 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -3,6 +3,7 @@
* Copyright (C) 2004, 2005 Oracle. All rights reserved.
*/
+#include "linux/kstrtox.h"
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/jiffies.h>
@@ -213,7 +214,7 @@ struct o2hb_region {
unsigned int hr_num_pages;
struct page **hr_slot_data;
- struct block_device *hr_bdev;
+ struct file *hr_bdev_file;
struct o2hb_disk_slot *hr_slots;
/* live node map of this region */
@@ -261,6 +262,11 @@ struct o2hb_region {
int hr_last_hb_status;
};
+static inline struct block_device *reg_bdev(struct o2hb_region *reg)
+{
+ return reg->hr_bdev_file ? file_bdev(reg->hr_bdev_file) : NULL;
+}
+
struct o2hb_bio_wait_ctxt {
atomic_t wc_num_reqs;
struct completion wc_io_complete;
@@ -286,7 +292,7 @@ static void o2hb_write_timeout(struct work_struct *work)
hr_write_timeout_work.work);
mlog(ML_ERROR, "Heartbeat write timeout to device %pg after %u "
- "milliseconds\n", reg->hr_bdev,
+ "milliseconds\n", reg_bdev(reg),
jiffies_to_msecs(jiffies - reg->hr_last_timeout_start));
if (o2hb_global_heartbeat_active()) {
@@ -383,7 +389,7 @@ static void o2hb_nego_timeout(struct work_struct *work)
if (!test_bit(master_node, reg->hr_nego_node_bitmap)) {
printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg).\n",
o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000,
- config_item_name(&reg->hr_item), reg->hr_bdev);
+ config_item_name(&reg->hr_item), reg_bdev(reg));
set_bit(master_node, reg->hr_nego_node_bitmap);
}
if (!bitmap_equal(reg->hr_nego_node_bitmap, live_node_bitmap,
@@ -398,7 +404,8 @@ static void o2hb_nego_timeout(struct work_struct *work)
}
printk(KERN_NOTICE "o2hb: all nodes hb write hung, maybe region %s (%pg) is down.\n",
- config_item_name(&reg->hr_item), reg->hr_bdev);
+ config_item_name(&reg->hr_item),
+ reg_bdev(reg));
/* approve negotiate timeout request. */
o2hb_arm_timeout(reg);
@@ -419,7 +426,7 @@ static void o2hb_nego_timeout(struct work_struct *work)
/* negotiate timeout with master node. */
printk(KERN_NOTICE "o2hb: node %d hb write hung for %ds on region %s (%pg), negotiate timeout with node %d.\n",
o2nm_this_node(), O2HB_NEGO_TIMEOUT_MS/1000, config_item_name(&reg->hr_item),
- reg->hr_bdev, master_node);
+ reg_bdev(reg), master_node);
ret = o2hb_send_nego_msg(reg->hr_key, O2HB_NEGO_TIMEOUT_MSG,
master_node);
if (ret)
@@ -436,7 +443,8 @@ static int o2hb_nego_timeout_handler(struct o2net_msg *msg, u32 len, void *data,
nego_msg = (struct o2hb_nego_msg *)msg->buf;
printk(KERN_NOTICE "o2hb: receive negotiate timeout message from node %d on region %s (%pg).\n",
- nego_msg->node_num, config_item_name(&reg->hr_item), reg->hr_bdev);
+ nego_msg->node_num, config_item_name(&reg->hr_item),
+ reg_bdev(reg));
if (nego_msg->node_num < O2NM_MAX_NODES)
set_bit(nego_msg->node_num, reg->hr_nego_node_bitmap);
else
@@ -451,7 +459,7 @@ static int o2hb_nego_approve_handler(struct o2net_msg *msg, u32 len, void *data,
struct o2hb_region *reg = data;
printk(KERN_NOTICE "o2hb: negotiate timeout approved by master node on region %s (%pg).\n",
- config_item_name(&reg->hr_item), reg->hr_bdev);
+ config_item_name(&reg->hr_item), reg_bdev(reg));
o2hb_arm_timeout(reg);
return 0;
}
@@ -515,7 +523,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
* GFP_KERNEL that the local node can get fenced. It would be
* nicest if we could pre-allocate these bios and avoid this
* all together. */
- bio = bio_alloc(reg->hr_bdev, 16, opf, GFP_ATOMIC);
+ bio = bio_alloc(reg_bdev(reg), 16, opf, GFP_ATOMIC);
if (!bio) {
mlog(ML_ERROR, "Could not alloc slots BIO!\n");
bio = ERR_PTR(-ENOMEM);
@@ -687,7 +695,7 @@ static int o2hb_check_own_slot(struct o2hb_region *reg)
errstr = ERRSTR3;
mlog(ML_ERROR, "%s (%pg): expected(%u:0x%llx, 0x%llx), "
- "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg->hr_bdev,
+ "ondisk(%u:0x%llx, 0x%llx)\n", errstr, reg_bdev(reg),
slot->ds_node_num, (unsigned long long)slot->ds_last_generation,
(unsigned long long)slot->ds_last_time, hb_block->hb_node,
(unsigned long long)le64_to_cpu(hb_block->hb_generation),
@@ -861,7 +869,7 @@ static void o2hb_set_quorum_device(struct o2hb_region *reg)
goto unlock;
printk(KERN_NOTICE "o2hb: Region %s (%pg) is now a quorum device\n",
- config_item_name(&reg->hr_item), reg->hr_bdev);
+ config_item_name(&reg->hr_item), reg_bdev(reg));
set_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
@@ -920,7 +928,7 @@ static int o2hb_check_slot(struct o2hb_region *reg,
* consider it a transient miss but don't populate any
* other values as they may be junk. */
mlog(ML_ERROR, "Node %d has written a bad crc to %pg\n",
- slot->ds_node_num, reg->hr_bdev);
+ slot->ds_node_num, reg_bdev(reg));
o2hb_dump_slot(hb_block);
slot->ds_equal_samples++;
@@ -1003,8 +1011,8 @@ fire_callbacks:
"of %u ms, but our count is %u ms.\n"
"Please double check your configuration values "
"for 'O2CB_HEARTBEAT_THRESHOLD'\n",
- slot->ds_node_num, reg->hr_bdev, slot_dead_ms,
- dead_ms);
+ slot->ds_node_num, reg_bdev(reg),
+ slot_dead_ms, dead_ms);
}
goto out;
}
@@ -1013,7 +1021,7 @@ fire_callbacks:
if (list_empty(&slot->ds_live_item))
goto out;
- /* live nodes only go dead after enough consequtive missed
+ /* live nodes only go dead after enough consecutive missed
* samples.. reset the missed counter whenever we see
* activity */
if (slot->ds_equal_samples >= o2hb_dead_threshold || gen_changed) {
@@ -1143,7 +1151,7 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
* can't be sure that the new block ever made it to
* disk */
mlog(ML_ERROR, "Write error %d on device \"%pg\"\n",
- write_wc.wc_error, reg->hr_bdev);
+ write_wc.wc_error, reg_bdev(reg));
ret = write_wc.wc_error;
goto bail;
}
@@ -1169,7 +1177,7 @@ bail:
printk(KERN_NOTICE "o2hb: Unable to stabilize "
"heartbeat on region %s (%pg)\n",
config_item_name(&reg->hr_item),
- reg->hr_bdev);
+ reg_bdev(reg));
atomic_set(&reg->hr_steady_iterations, 0);
reg->hr_aborted_start = 1;
wake_up(&o2hb_steady_queue);
@@ -1489,7 +1497,7 @@ static void o2hb_region_release(struct config_item *item)
struct page *page;
struct o2hb_region *reg = to_o2hb_region(item);
- mlog(ML_HEARTBEAT, "hb region release (%pg)\n", reg->hr_bdev);
+ mlog(ML_HEARTBEAT, "hb region release (%pg)\n", reg_bdev(reg));
kfree(reg->hr_tmp_block);
@@ -1502,8 +1510,8 @@ static void o2hb_region_release(struct config_item *item)
kfree(reg->hr_slot_data);
}
- if (reg->hr_bdev)
- blkdev_put(reg->hr_bdev, FMODE_READ|FMODE_WRITE);
+ if (reg->hr_bdev_file)
+ fput(reg->hr_bdev_file);
kfree(reg->hr_slots);
@@ -1528,10 +1536,11 @@ static int o2hb_read_block_input(struct o2hb_region *reg,
{
unsigned long bytes;
char *p = (char *)page;
+ int ret;
- bytes = simple_strtoul(p, &p, 0);
- if (!p || (*p && (*p != '\n')))
- return -EINVAL;
+ ret = kstrtoul(p, 0, &bytes);
+ if (ret)
+ return ret;
/* Heartbeat and fs min / max block sizes are the same. */
if (bytes > 4096 || bytes < 512)
@@ -1562,7 +1571,7 @@ static ssize_t o2hb_region_block_bytes_store(struct config_item *item,
unsigned long block_bytes;
unsigned int block_bits;
- if (reg->hr_bdev)
+ if (reg->hr_bdev_file)
return -EINVAL;
status = o2hb_read_block_input(reg, page, &block_bytes,
@@ -1591,7 +1600,7 @@ static ssize_t o2hb_region_start_block_store(struct config_item *item,
char *p = (char *)page;
ssize_t ret;
- if (reg->hr_bdev)
+ if (reg->hr_bdev_file)
return -EINVAL;
ret = kstrtoull(p, 0, &tmp);
@@ -1615,13 +1624,14 @@ static ssize_t o2hb_region_blocks_store(struct config_item *item,
struct o2hb_region *reg = to_o2hb_region(item);
unsigned long tmp;
char *p = (char *)page;
+ int ret;
- if (reg->hr_bdev)
+ if (reg->hr_bdev_file)
return -EINVAL;
- tmp = simple_strtoul(p, &p, 0);
- if (!p || (*p && (*p != '\n')))
- return -EINVAL;
+ ret = kstrtoul(p, 0, &tmp);
+ if (ret)
+ return ret;
if (tmp > O2NM_MAX_NODES || tmp == 0)
return -ERANGE;
@@ -1635,8 +1645,8 @@ static ssize_t o2hb_region_dev_show(struct config_item *item, char *page)
{
unsigned int ret = 0;
- if (to_o2hb_region(item)->hr_bdev)
- ret = sprintf(page, "%pg\n", to_o2hb_region(item)->hr_bdev);
+ if (to_o2hb_region(item)->hr_bdev_file)
+ ret = sprintf(page, "%pg\n", reg_bdev(to_o2hb_region(item)));
return ret;
}
@@ -1745,7 +1755,10 @@ out:
return ret;
}
-/* this is acting as commit; we set up all of hr_bdev and hr_task or nothing */
+/*
+ * this is acting as commit; we set up all of hr_bdev_file and hr_task or
+ * nothing
+ */
static ssize_t o2hb_region_dev_store(struct config_item *item,
const char *page,
size_t count)
@@ -1755,45 +1768,44 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
long fd;
int sectsize;
char *p = (char *)page;
- struct fd f;
ssize_t ret = -EINVAL;
int live_threshold;
- if (reg->hr_bdev)
- goto out;
+ if (reg->hr_bdev_file)
+ return -EINVAL;
/* We can't heartbeat without having had our node number
* configured yet. */
if (o2nm_this_node() == O2NM_MAX_NODES)
- goto out;
+ return -EINVAL;
- fd = simple_strtol(p, &p, 0);
- if (!p || (*p && (*p != '\n')))
- goto out;
+ ret = kstrtol(p, 0, &fd);
+ if (ret < 0)
+ return -EINVAL;
if (fd < 0 || fd >= INT_MAX)
- goto out;
+ return -EINVAL;
- f = fdget(fd);
- if (f.file == NULL)
- goto out;
+ CLASS(fd, f)(fd);
+ if (fd_empty(f))
+ return -EINVAL;
if (reg->hr_blocks == 0 || reg->hr_start_block == 0 ||
reg->hr_block_bytes == 0)
- goto out2;
+ return -EINVAL;
- if (!S_ISBLK(f.file->f_mapping->host->i_mode))
- goto out2;
+ if (!S_ISBLK(fd_file(f)->f_mapping->host->i_mode))
+ return -EINVAL;
- reg->hr_bdev = blkdev_get_by_dev(f.file->f_mapping->host->i_rdev,
- FMODE_WRITE | FMODE_READ, NULL);
- if (IS_ERR(reg->hr_bdev)) {
- ret = PTR_ERR(reg->hr_bdev);
- reg->hr_bdev = NULL;
- goto out2;
+ reg->hr_bdev_file = bdev_file_open_by_dev(fd_file(f)->f_mapping->host->i_rdev,
+ BLK_OPEN_WRITE | BLK_OPEN_READ, NULL, NULL);
+ if (IS_ERR(reg->hr_bdev_file)) {
+ ret = PTR_ERR(reg->hr_bdev_file);
+ reg->hr_bdev_file = NULL;
+ return ret;
}
- sectsize = bdev_logical_block_size(reg->hr_bdev);
+ sectsize = bdev_logical_block_size(reg_bdev(reg));
if (sectsize != reg->hr_block_bytes) {
mlog(ML_ERROR,
"blocksize %u incorrect for device, expected %d",
@@ -1889,16 +1901,13 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
if (hb_task && o2hb_global_heartbeat_active())
printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%pg)\n",
- config_item_name(&reg->hr_item), reg->hr_bdev);
+ config_item_name(&reg->hr_item), reg_bdev(reg));
out3:
if (ret < 0) {
- blkdev_put(reg->hr_bdev, FMODE_READ | FMODE_WRITE);
- reg->hr_bdev = NULL;
+ fput(reg->hr_bdev_file);
+ reg->hr_bdev_file = NULL;
}
-out2:
- fdput(f);
-out:
return ret;
}
@@ -2084,7 +2093,7 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group,
printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%pg)\n",
((atomic_read(&reg->hr_steady_iterations) == 0) ?
"stopped" : "start aborted"), config_item_name(item),
- reg->hr_bdev);
+ reg_bdev(reg));
}
/*
@@ -2130,10 +2139,11 @@ static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *ite
{
unsigned long tmp;
char *p = (char *)page;
+ int ret;
- tmp = simple_strtoul(p, &p, 10);
- if (!p || (*p && (*p != '\n')))
- return -EINVAL;
+ ret = kstrtoul(p, 10, &tmp);
+ if (ret)
+ return ret;
/* this will validate ranges for us. */
o2hb_dead_threshold_set((unsigned int) tmp);
diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h
index b73fc42e46ff..630bd5a3dd0d 100644
--- a/fs/ocfs2/cluster/masklog.h
+++ b/fs/ocfs2/cluster/masklog.h
@@ -29,7 +29,7 @@
* just calling printk() so that this can eventually make its way through
* relayfs along with the debugging messages. Everything else gets KERN_DEBUG.
* The inline tests and macro dance give GCC the opportunity to quite cleverly
- * only emit the appropriage printk() when the caller passes in a constant
+ * only emit the appropriate printk() when the caller passes in a constant
* mask, as is almost always the case.
*
* All this bitmask nonsense is managed from the files under
diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
index 35c05c18de59..bc27301eab6d 100644
--- a/fs/ocfs2/cluster/netdebug.c
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -44,17 +44,17 @@ static LIST_HEAD(send_tracking);
void o2net_debug_add_nst(struct o2net_send_tracking *nst)
{
- spin_lock(&o2net_debug_lock);
+ spin_lock_bh(&o2net_debug_lock);
list_add(&nst->st_net_debug_item, &send_tracking);
- spin_unlock(&o2net_debug_lock);
+ spin_unlock_bh(&o2net_debug_lock);
}
void o2net_debug_del_nst(struct o2net_send_tracking *nst)
{
- spin_lock(&o2net_debug_lock);
+ spin_lock_bh(&o2net_debug_lock);
if (!list_empty(&nst->st_net_debug_item))
list_del_init(&nst->st_net_debug_item);
- spin_unlock(&o2net_debug_lock);
+ spin_unlock_bh(&o2net_debug_lock);
}
static struct o2net_send_tracking
@@ -84,9 +84,9 @@ static void *nst_seq_start(struct seq_file *seq, loff_t *pos)
{
struct o2net_send_tracking *nst, *dummy_nst = seq->private;
- spin_lock(&o2net_debug_lock);
+ spin_lock_bh(&o2net_debug_lock);
nst = next_nst(dummy_nst);
- spin_unlock(&o2net_debug_lock);
+ spin_unlock_bh(&o2net_debug_lock);
return nst;
}
@@ -95,13 +95,13 @@ static void *nst_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct o2net_send_tracking *nst, *dummy_nst = seq->private;
- spin_lock(&o2net_debug_lock);
+ spin_lock_bh(&o2net_debug_lock);
nst = next_nst(dummy_nst);
list_del_init(&dummy_nst->st_net_debug_item);
if (nst)
list_add(&dummy_nst->st_net_debug_item,
&nst->st_net_debug_item);
- spin_unlock(&o2net_debug_lock);
+ spin_unlock_bh(&o2net_debug_lock);
return nst; /* unused, just needs to be null when done */
}
@@ -112,7 +112,7 @@ static int nst_seq_show(struct seq_file *seq, void *v)
ktime_t now;
s64 sock, send, status;
- spin_lock(&o2net_debug_lock);
+ spin_lock_bh(&o2net_debug_lock);
nst = next_nst(dummy_nst);
if (!nst)
goto out;
@@ -145,7 +145,7 @@ static int nst_seq_show(struct seq_file *seq, void *v)
(long long)status);
out:
- spin_unlock(&o2net_debug_lock);
+ spin_unlock_bh(&o2net_debug_lock);
return 0;
}
@@ -191,16 +191,16 @@ static const struct file_operations nst_seq_fops = {
void o2net_debug_add_sc(struct o2net_sock_container *sc)
{
- spin_lock(&o2net_debug_lock);
+ spin_lock_bh(&o2net_debug_lock);
list_add(&sc->sc_net_debug_item, &sock_containers);
- spin_unlock(&o2net_debug_lock);
+ spin_unlock_bh(&o2net_debug_lock);
}
void o2net_debug_del_sc(struct o2net_sock_container *sc)
{
- spin_lock(&o2net_debug_lock);
+ spin_lock_bh(&o2net_debug_lock);
list_del_init(&sc->sc_net_debug_item);
- spin_unlock(&o2net_debug_lock);
+ spin_unlock_bh(&o2net_debug_lock);
}
struct o2net_sock_debug {
@@ -236,9 +236,9 @@ static void *sc_seq_start(struct seq_file *seq, loff_t *pos)
struct o2net_sock_debug *sd = seq->private;
struct o2net_sock_container *sc, *dummy_sc = sd->dbg_sock;
- spin_lock(&o2net_debug_lock);
+ spin_lock_bh(&o2net_debug_lock);
sc = next_sc(dummy_sc);
- spin_unlock(&o2net_debug_lock);
+ spin_unlock_bh(&o2net_debug_lock);
return sc;
}
@@ -248,12 +248,12 @@ static void *sc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
struct o2net_sock_debug *sd = seq->private;
struct o2net_sock_container *sc, *dummy_sc = sd->dbg_sock;
- spin_lock(&o2net_debug_lock);
+ spin_lock_bh(&o2net_debug_lock);
sc = next_sc(dummy_sc);
list_del_init(&dummy_sc->sc_net_debug_item);
if (sc)
list_add(&dummy_sc->sc_net_debug_item, &sc->sc_net_debug_item);
- spin_unlock(&o2net_debug_lock);
+ spin_unlock_bh(&o2net_debug_lock);
return sc; /* unused, just needs to be null when done */
}
@@ -349,7 +349,7 @@ static int sc_seq_show(struct seq_file *seq, void *v)
struct o2net_sock_debug *sd = seq->private;
struct o2net_sock_container *sc, *dummy_sc = sd->dbg_sock;
- spin_lock(&o2net_debug_lock);
+ spin_lock_bh(&o2net_debug_lock);
sc = next_sc(dummy_sc);
if (sc) {
@@ -359,7 +359,7 @@ static int sc_seq_show(struct seq_file *seq, void *v)
sc_show_sock_stats(seq, sc);
}
- spin_unlock(&o2net_debug_lock);
+ spin_unlock_bh(&o2net_debug_lock);
return 0;
}
diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c
index 189c111bc371..bfb8b456876c 100644
--- a/fs/ocfs2/cluster/quorum.c
+++ b/fs/ocfs2/cluster/quorum.c
@@ -23,7 +23,7 @@
* race between when we see a node start heartbeating and when we connect
* to it.
*
- * So nodes that are in this transtion put a hold on the quorum decision
+ * So nodes that are in this transition put a hold on the quorum decision
* with a counter. As they fall out of this transition they drop the count
* and if they're the last, they fire off the decision.
*/
@@ -60,7 +60,7 @@ static void o2quo_fence_self(void)
switch (o2nm_single_cluster->cl_fence_method) {
case O2NM_FENCE_PANIC:
panic("*** ocfs2 is very sorry to be fencing this system by "
- "panicing ***\n");
+ "panicking ***\n");
break;
default:
WARN_ON(o2nm_single_cluster->cl_fence_method >=
@@ -93,7 +93,7 @@ static void o2quo_make_decision(struct work_struct *work)
int lowest_hb, lowest_reachable = 0, fence = 0;
struct o2quo_state *qs = &o2quo_state;
- spin_lock(&qs->qs_lock);
+ spin_lock_bh(&qs->qs_lock);
lowest_hb = find_first_bit(qs->qs_hb_bm, O2NM_MAX_NODES);
if (lowest_hb != O2NM_MAX_NODES)
@@ -146,14 +146,14 @@ static void o2quo_make_decision(struct work_struct *work)
out:
if (fence) {
- spin_unlock(&qs->qs_lock);
+ spin_unlock_bh(&qs->qs_lock);
o2quo_fence_self();
} else {
mlog(ML_NOTICE, "not fencing this node, heartbeating: %d, "
"connected: %d, lowest: %d (%sreachable)\n",
qs->qs_heartbeating, qs->qs_connected, lowest_hb,
lowest_reachable ? "" : "un");
- spin_unlock(&qs->qs_lock);
+ spin_unlock_bh(&qs->qs_lock);
}
@@ -189,14 +189,14 @@ static void o2quo_clear_hold(struct o2quo_state *qs, u8 node)
}
/* as a node comes up we delay the quorum decision until we know the fate of
- * the connection. the hold will be droped in conn_up or hb_down. it might be
+ * the connection. the hold will be dropped in conn_up or hb_down. it might be
* perpetuated by con_err until hb_down. if we already have a conn, we might
* be dropping a hold that conn_up got. */
void o2quo_hb_up(u8 node)
{
struct o2quo_state *qs = &o2quo_state;
- spin_lock(&qs->qs_lock);
+ spin_lock_bh(&qs->qs_lock);
qs->qs_heartbeating++;
mlog_bug_on_msg(qs->qs_heartbeating == O2NM_MAX_NODES,
@@ -211,7 +211,7 @@ void o2quo_hb_up(u8 node)
else
o2quo_clear_hold(qs, node);
- spin_unlock(&qs->qs_lock);
+ spin_unlock_bh(&qs->qs_lock);
}
/* hb going down releases any holds we might have had due to this node from
@@ -220,7 +220,7 @@ void o2quo_hb_down(u8 node)
{
struct o2quo_state *qs = &o2quo_state;
- spin_lock(&qs->qs_lock);
+ spin_lock_bh(&qs->qs_lock);
qs->qs_heartbeating--;
mlog_bug_on_msg(qs->qs_heartbeating < 0,
@@ -233,7 +233,7 @@ void o2quo_hb_down(u8 node)
o2quo_clear_hold(qs, node);
- spin_unlock(&qs->qs_lock);
+ spin_unlock_bh(&qs->qs_lock);
}
/* this tells us that we've decided that the node is still heartbeating
@@ -245,18 +245,18 @@ void o2quo_hb_still_up(u8 node)
{
struct o2quo_state *qs = &o2quo_state;
- spin_lock(&qs->qs_lock);
+ spin_lock_bh(&qs->qs_lock);
mlog(0, "node %u\n", node);
qs->qs_pending = 1;
o2quo_clear_hold(qs, node);
- spin_unlock(&qs->qs_lock);
+ spin_unlock_bh(&qs->qs_lock);
}
/* This is analogous to hb_up. as a node's connection comes up we delay the
- * quorum decision until we see it heartbeating. the hold will be droped in
+ * quorum decision until we see it heartbeating. the hold will be dropped in
* hb_up or hb_down. it might be perpetuated by con_err until hb_down. if
* it's already heartbeating we might be dropping a hold that conn_up got.
* */
@@ -264,7 +264,7 @@ void o2quo_conn_up(u8 node)
{
struct o2quo_state *qs = &o2quo_state;
- spin_lock(&qs->qs_lock);
+ spin_lock_bh(&qs->qs_lock);
qs->qs_connected++;
mlog_bug_on_msg(qs->qs_connected == O2NM_MAX_NODES,
@@ -279,7 +279,7 @@ void o2quo_conn_up(u8 node)
else
o2quo_clear_hold(qs, node);
- spin_unlock(&qs->qs_lock);
+ spin_unlock_bh(&qs->qs_lock);
}
/* we've decided that we won't ever be connecting to the node again. if it's
@@ -290,7 +290,7 @@ void o2quo_conn_err(u8 node)
{
struct o2quo_state *qs = &o2quo_state;
- spin_lock(&qs->qs_lock);
+ spin_lock_bh(&qs->qs_lock);
if (test_bit(node, qs->qs_conn_bm)) {
qs->qs_connected--;
@@ -307,7 +307,7 @@ void o2quo_conn_err(u8 node)
mlog(0, "node %u, %d total\n", node, qs->qs_connected);
- spin_unlock(&qs->qs_lock);
+ spin_unlock_bh(&qs->qs_lock);
}
void o2quo_init(void)
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index a07b24d170f2..79b281e32f4c 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -5,13 +5,13 @@
*
* ----
*
- * Callers for this were originally written against a very simple synchronus
+ * Callers for this were originally written against a very simple synchronous
* API. This implementation reflects those simple callers. Some day I'm sure
* we'll need to move to a more robust posting/callback mechanism.
*
* Transmit calls pass in kernel virtual addresses and block copying this into
* the socket's tx buffers via a usual blocking sendmsg. They'll block waiting
- * for a failed socket to timeout. TX callers can also pass in a poniter to an
+ * for a failed socket to timeout. TX callers can also pass in a pointer to an
* 'int' which gets filled with an errno off the wire in response to the
* message they send.
*
@@ -46,6 +46,7 @@
#include <linux/net.h>
#include <linux/export.h>
#include <net/tcp.h>
+#include <trace/events/sock.h>
#include <linux/uaccess.h>
@@ -100,7 +101,7 @@ static struct socket *o2net_listen_sock;
* o2net_wq. teardown detaches the callbacks before destroying the workqueue.
* quorum work is queued as sock containers are shutdown.. stop_listening
* tears down all the node's sock containers, preventing future shutdowns
- * and queued quroum work, before canceling delayed quorum work and
+ * and queued quorum work, before canceling delayed quorum work and
* destroying the work queue.
*/
static struct workqueue_struct *o2net_wq;
@@ -585,6 +586,8 @@ static void o2net_data_ready(struct sock *sk)
void (*ready)(struct sock *sk);
struct o2net_sock_container *sc;
+ trace_sk_data_ready(sk);
+
read_lock_bh(&sk->sk_callback_lock);
sc = sk->sk_user_data;
if (sc) {
@@ -721,7 +724,7 @@ static void o2net_shutdown_sc(struct work_struct *work)
if (o2net_unregister_callbacks(sc->sc_sock->sk, sc)) {
/* we shouldn't flush as we're in the thread, the
* races with pending sc work structs are harmless */
- del_timer_sync(&sc->sc_idle_timeout);
+ timer_delete_sync(&sc->sc_idle_timeout);
o2net_sc_cancel_delayed_work(sc, &sc->sc_keepalive_work);
sc_put(sc);
kernel_sock_shutdown(sc->sc_sock, SHUT_RDWR);
@@ -927,19 +930,22 @@ out:
}
static void o2net_sendpage(struct o2net_sock_container *sc,
- void *kmalloced_virt,
- size_t size)
+ void *virt, size_t size)
{
struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
+ struct msghdr msg = {};
+ struct bio_vec bv;
ssize_t ret;
+ bvec_set_virt(&bv, virt, size);
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, size);
+
while (1) {
+ msg.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES;
mutex_lock(&sc->sc_send_lock);
- ret = sc->sc_sock->ops->sendpage(sc->sc_sock,
- virt_to_page(kmalloced_virt),
- offset_in_page(kmalloced_virt),
- size, MSG_DONTWAIT);
+ ret = sock_sendmsg(sc->sc_sock, &msg);
mutex_unlock(&sc->sc_send_lock);
+
if (ret == size)
break;
if (ret == (ssize_t)-EAGAIN) {
@@ -1413,7 +1419,7 @@ out:
return ret;
}
-/* this work func is triggerd by data ready. it reads until it can read no
+/* this work func is triggered by data ready. it reads until it can read no
* more. it interprets 0, eof, as fatal. if data_ready hits while we're doing
* our work the work struct will be marked and we'll be called again. */
static void o2net_rx_until_empty(struct work_struct *work)
@@ -1477,12 +1483,13 @@ static void o2net_sc_send_keep_req(struct work_struct *work)
sc_put(sc);
}
-/* socket shutdown does a del_timer_sync against this as it tears down.
+/* socket shutdown does a timer_delete_sync against this as it tears down.
* we can't start this timer until we've got to the point in sc buildup
* where shutdown is going to be involved */
static void o2net_idle_timer(struct timer_list *t)
{
- struct o2net_sock_container *sc = from_timer(sc, t, sc_idle_timeout);
+ struct o2net_sock_container *sc = timer_container_of(sc, t,
+ sc_idle_timeout);
struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
#ifdef CONFIG_DEBUG_FS
unsigned long msecs = ktime_to_ms(ktime_get()) -
@@ -1608,7 +1615,7 @@ static void o2net_start_connect(struct work_struct *work)
myaddr.sin_addr.s_addr = mynode->nd_ipv4_address;
myaddr.sin_port = htons(0); /* any port */
- ret = sock->ops->bind(sock, (struct sockaddr *)&myaddr,
+ ret = sock->ops->bind(sock, (struct sockaddr_unsized *)&myaddr,
sizeof(myaddr));
if (ret) {
mlog(ML_ERROR, "bind failed with %d at address %pI4\n",
@@ -1631,7 +1638,7 @@ static void o2net_start_connect(struct work_struct *work)
remoteaddr.sin_port = node->nd_ipv4_port;
ret = sc->sc_sock->ops->connect(sc->sc_sock,
- (struct sockaddr *)&remoteaddr,
+ (struct sockaddr_unsized *)&remoteaddr,
sizeof(remoteaddr),
O_NONBLOCK);
if (ret == -EINPROGRESS)
@@ -1778,6 +1785,9 @@ static int o2net_accept_one(struct socket *sock, int *more)
struct o2nm_node *node = NULL;
struct o2nm_node *local_node = NULL;
struct o2net_sock_container *sc = NULL;
+ struct proto_accept_arg arg = {
+ .flags = O_NONBLOCK,
+ };
struct o2net_node *nn;
unsigned int nofs_flag;
@@ -1796,7 +1806,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
new_sock->type = sock->type;
new_sock->ops = sock->ops;
- ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, false);
+ ret = sock->ops->accept(sock, new_sock, &arg);
if (ret < 0)
goto out;
@@ -1931,6 +1941,8 @@ static void o2net_listen_data_ready(struct sock *sk)
{
void (*ready)(struct sock *sk);
+ trace_sk_data_ready(sk);
+
read_lock_bh(&sk->sk_callback_lock);
ready = sk->sk_user_data;
if (ready == NULL) { /* check for teardown race */
@@ -1990,7 +2002,7 @@ static int o2net_open_listening_sock(__be32 addr, __be16 port)
INIT_WORK(&o2net_listen_work, o2net_accept_many);
sock->sk->sk_reuse = SK_CAN_REUSE;
- ret = sock->ops->bind(sock, (struct sockaddr *)&sin, sizeof(sin));
+ ret = sock->ops->bind(sock, (struct sockaddr_unsized *)&sin, sizeof(sin));
if (ret < 0) {
printk(KERN_ERR "o2net: Error %d while binding socket at "
"%pI4:%u\n", ret, &addr, ntohs(port));
@@ -2082,18 +2094,24 @@ void o2net_stop_listening(struct o2nm_node *node)
int o2net_init(void)
{
+ struct folio *folio;
+ void *p;
unsigned long i;
o2quo_init();
-
o2net_debugfs_init();
- o2net_hand = kzalloc(sizeof(struct o2net_handshake), GFP_KERNEL);
- o2net_keep_req = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
- o2net_keep_resp = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL);
- if (!o2net_hand || !o2net_keep_req || !o2net_keep_resp)
+ folio = folio_alloc(GFP_KERNEL | __GFP_ZERO, 0);
+ if (!folio)
goto out;
+ p = folio_address(folio);
+ o2net_hand = p;
+ p += sizeof(struct o2net_handshake);
+ o2net_keep_req = p;
+ p += sizeof(struct o2net_msg);
+ o2net_keep_resp = p;
+
o2net_hand->protocol_version = cpu_to_be64(O2NET_PROTOCOL_VERSION);
o2net_hand->connector_id = cpu_to_be64(1);
@@ -2119,9 +2137,6 @@ int o2net_init(void)
return 0;
out:
- kfree(o2net_hand);
- kfree(o2net_keep_req);
- kfree(o2net_keep_resp);
o2net_debugfs_exit();
o2quo_exit();
return -ENOMEM;
@@ -2130,8 +2145,6 @@ out:
void o2net_exit(void)
{
o2quo_exit();
- kfree(o2net_hand);
- kfree(o2net_keep_req);
- kfree(o2net_keep_resp);
o2net_debugfs_exit();
+ folio_put(virt_to_folio(o2net_hand));
}
generated by cgit (git 2.34.1) at 2025-12-25 09:59:33 +0000