Merge tag 'dlm-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm

Pull dlm updates from David Teigland:
 "This set continues the ongoing rework of the low level communication
  layer in the dlm.

  The focus here is on improvements to connection handling, and
  reworking the receiving of messages"

* tag 'dlm-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm:
  fs: dlm: fix race in nodeid2con
  fs: dlm: rework receive handling
  fs: dlm: disallow buffer size below default
  fs: dlm: handle range check as callback
  fs: dlm: fix mark per nodeid setting
  fs: dlm: remove lock dependency warning
  fs: dlm: use free_con to free connection
  fs: dlm: handle possible othercon writequeues
  fs: dlm: move free writequeue into con free
  fs: dlm: fix configfs memory leak
  fs: dlm: fix dlm_local_addr memory leak
  fs: dlm: make connection hash lockless
  fs: dlm: synchronize dlm before shutdown

fs/dlm/Kconfig

@@ -4,6 +4,7 @@ menuconfig DLM
 	depends on INET
 	depends on SYSFS && CONFIGFS_FS && (IPV6 || IPV6=n)
 	select IP_SCTP
+	select SRCU
 	help
 	A general purpose distributed lock manager for kernel or userspace
 	applications.

fs/dlm/config.c

@@ -125,7 +125,7 @@ static ssize_t cluster_cluster_name_store(struct config_item *item,
 CONFIGFS_ATTR(cluster_, cluster_name);
 
 static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field,
-			   int *info_field, int check_zero,
+			   int *info_field, bool (*check_cb)(unsigned int x),
 			   const char *buf, size_t len)
 {
 	unsigned int x;
@@ -137,7 +137,7 @@ static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field,
 	if (rc)
 		return rc;
 
-	if (check_zero && !x)
+	if (check_cb && check_cb(x))
 		return -EINVAL;
 
 	*cl_field = x;
@@ -146,13 +146,13 @@ static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field,
 	return len;
 }
 
-#define CLUSTER_ATTR(name, check_zero)                                        \
+#define CLUSTER_ATTR(name, check_cb)                                          \
 static ssize_t cluster_##name##_store(struct config_item *item, \
 		const char *buf, size_t len) \
 {                                                                             \
 	struct dlm_cluster *cl = config_item_to_cluster(item);		      \
 	return cluster_set(cl, &cl->cl_##name, &dlm_config.ci_##name,         \
-			   check_zero, buf, len);                             \
+			   check_cb, buf, len);                               \
 }                                                                             \
 static ssize_t cluster_##name##_show(struct config_item *item, char *buf)     \
 {                                                                             \
@@ -161,20 +161,30 @@ static ssize_t cluster_##name##_show(struct config_item *item, char *buf)     \
 }                                                                             \
 CONFIGFS_ATTR(cluster_, name);
 
-CLUSTER_ATTR(tcp_port, 1);
-CLUSTER_ATTR(buffer_size, 1);
-CLUSTER_ATTR(rsbtbl_size, 1);
-CLUSTER_ATTR(recover_timer, 1);
-CLUSTER_ATTR(toss_secs, 1);
-CLUSTER_ATTR(scan_secs, 1);
-CLUSTER_ATTR(log_debug, 0);
-CLUSTER_ATTR(log_info, 0);
-CLUSTER_ATTR(protocol, 0);
-CLUSTER_ATTR(mark, 0);
-CLUSTER_ATTR(timewarn_cs, 1);
-CLUSTER_ATTR(waitwarn_us, 0);
-CLUSTER_ATTR(new_rsb_count, 0);
-CLUSTER_ATTR(recover_callbacks, 0);
+static bool dlm_check_zero(unsigned int x)
+{
+	return !x;
+}
+
+static bool dlm_check_buffer_size(unsigned int x)
+{
+	return (x < DEFAULT_BUFFER_SIZE);
+}
+
+CLUSTER_ATTR(tcp_port, dlm_check_zero);
+CLUSTER_ATTR(buffer_size, dlm_check_buffer_size);
+CLUSTER_ATTR(rsbtbl_size, dlm_check_zero);
+CLUSTER_ATTR(recover_timer, dlm_check_zero);
+CLUSTER_ATTR(toss_secs, dlm_check_zero);
+CLUSTER_ATTR(scan_secs, dlm_check_zero);
+CLUSTER_ATTR(log_debug, NULL);
+CLUSTER_ATTR(log_info, NULL);
+CLUSTER_ATTR(protocol, NULL);
+CLUSTER_ATTR(mark, NULL);
+CLUSTER_ATTR(timewarn_cs, dlm_check_zero);
+CLUSTER_ATTR(waitwarn_us, NULL);
+CLUSTER_ATTR(new_rsb_count, NULL);
+CLUSTER_ATTR(recover_callbacks, NULL);
 
 static struct configfs_attribute *cluster_attrs[] = {
 	[CLUSTER_ATTR_TCP_PORT] = &cluster_attr_tcp_port,
@@ -221,6 +231,7 @@ struct dlm_space {
 	struct list_head members;
 	struct mutex members_lock;
 	int members_count;
+	struct dlm_nodes *nds;
 };
 
 struct dlm_comms {
@@ -430,6 +441,7 @@ static struct config_group *make_space(struct config_group *g, const char *name)
 	INIT_LIST_HEAD(&sp->members);
 	mutex_init(&sp->members_lock);
 	sp->members_count = 0;
+	sp->nds = nds;
 	return &sp->group;
 
  fail:
@@ -451,6 +463,7 @@ static void drop_space(struct config_group *g, struct config_item *i)
 static void release_space(struct config_item *i)
 {
 	struct dlm_space *sp = config_item_to_space(i);
+	kfree(sp->nds);
 	kfree(sp);
 }
 
@@ -857,18 +870,22 @@ int dlm_comm_seq(int nodeid, uint32_t *seq)
 	return 0;
 }
 
-int dlm_comm_mark(int nodeid, unsigned int *mark)
+void dlm_comm_mark(int nodeid, unsigned int *mark)
 {
 	struct dlm_comm *cm;
 
 	cm = get_comm(nodeid);
-	if (!cm)
-		return -ENOENT;
+	if (!cm) {
+		*mark = dlm_config.ci_mark;
+		return;
+	}
 
+	if (cm->mark)
 		*mark = cm->mark;
-	put_comm(cm);
+	else
+		*mark = dlm_config.ci_mark;
 
-	return 0;
+	put_comm(cm);
 }
 
 int dlm_our_nodeid(void)
@@ -889,7 +906,6 @@ int dlm_our_addr(struct sockaddr_storage *addr, int num)
 
 /* Config file defaults */
 #define DEFAULT_TCP_PORT       21064
-#define DEFAULT_BUFFER_SIZE     4096
 #define DEFAULT_RSBTBL_SIZE     1024
 #define DEFAULT_RECOVER_TIMER      5
 #define DEFAULT_TOSS_SECS         10

fs/dlm/config.h

@@ -12,6 +12,8 @@
 #ifndef __CONFIG_DOT_H__
 #define __CONFIG_DOT_H__
 
+#define DEFAULT_BUFFER_SIZE     4096
+
 struct dlm_config_node {
 	int nodeid;
 	int weight;
@@ -46,7 +48,7 @@ void dlm_config_exit(void);
 int dlm_config_nodes(char *lsname, struct dlm_config_node **nodes_out,
 		     int *count_out);
 int dlm_comm_seq(int nodeid, uint32_t *seq);
-int dlm_comm_mark(int nodeid, unsigned int *mark);
+void dlm_comm_mark(int nodeid, unsigned int *mark);
 int dlm_our_nodeid(void);
 int dlm_our_addr(struct sockaddr_storage *addr, int num);
 

fs/dlm/midcomms.c

@@ -22,114 +22,84 @@
  * into packets and sends them to the comms layer.
  */
 
+#include <asm/unaligned.h>
+
 #include "dlm_internal.h"
 #include "lowcomms.h"
 #include "config.h"
 #include "lock.h"
 #include "midcomms.h"
 
-
-static void copy_from_cb(void *dst, const void *base, unsigned offset,
-			 unsigned len, unsigned limit)
-{
-	unsigned copy = len;
-
-	if ((copy + offset) > limit)
-		copy = limit - offset;
-	memcpy(dst, base + offset, copy);
-	len -= copy;
-	if (len)
-		memcpy(dst + copy, base, len);
-}
-
 /*
  * Called from the low-level comms layer to process a buffer of
  * commands.
- *
- * Only complete messages are processed here, any "spare" bytes from
- * the end of a buffer are saved and tacked onto the front of the next
- * message that comes in. I doubt this will happen very often but we
- * need to be able to cope with it and I don't want the task to be waiting
- * for packets to come in when there is useful work to be done.
  */
 
-int dlm_process_incoming_buffer(int nodeid, const void *base,
-				unsigned offset, unsigned len, unsigned limit)
+int dlm_process_incoming_buffer(int nodeid, unsigned char *buf, int len)
 {
-	union {
-		unsigned char __buf[DLM_INBUF_LEN];
-		/* this is to force proper alignment on some arches */
-		union dlm_packet p;
-	} __tmp;
-	union dlm_packet *p = &__tmp.p;
-	int ret = 0;
-	int err = 0;
+	const unsigned char *ptr = buf;
+	const struct dlm_header *hd;
 	uint16_t msglen;
-	uint32_t lockspace;
-
-	while (len > sizeof(struct dlm_header)) {
-
-		/* Copy just the header to check the total length.  The
-		   message may wrap around the end of the buffer back to the
-		   start, so we need to use a temp buffer and copy_from_cb. */
-
-		copy_from_cb(p, base, offset, sizeof(struct dlm_header),
-			     limit);
+	int ret = 0;
 
-		msglen = le16_to_cpu(p->header.h_length);
-		lockspace = p->header.h_lockspace;
+	while (len >= sizeof(struct dlm_header)) {
+		hd = (struct dlm_header *)ptr;
 
-		err = -EINVAL;
-		if (msglen < sizeof(struct dlm_header))
-			break;
-		if (p->header.h_cmd == DLM_MSG) {
-			if (msglen < sizeof(struct dlm_message))
-				break;
-		} else {
-			if (msglen < sizeof(struct dlm_rcom))
-				break;
-		}
-		err = -E2BIG;
-		if (msglen > dlm_config.ci_buffer_size) {
-			log_print("message size %d from %d too big, buf len %d",
-				  msglen, nodeid, len);
-			break;
+		/* no message should be more than this otherwise we
+		 * cannot deliver this message to upper layers
+		 */
+		msglen = get_unaligned_le16(&hd->h_length);
+		if (msglen > DEFAULT_BUFFER_SIZE) {
+			log_print("received invalid length header: %u, will abort message parsing",
+				  msglen);
+			return -EBADMSG;
 		}
-		err = 0;
-
-		/* If only part of the full message is contained in this
-		   buffer, then do nothing and wait for lowcomms to call
-		   us again later with more data.  We return 0 meaning
-		   we've consumed none of the input buffer. */
 
+		/* caller will take care that leftover
+		 * will be parsed next call with more data
+		 */
 		if (msglen > len)
 			break;
 
-		/* Allocate a larger temp buffer if the full message won't fit
-		   in the buffer on the stack (which should work for most
-		   ordinary messages). */
+		switch (hd->h_cmd) {
+		case DLM_MSG:
+			if (msglen < sizeof(struct dlm_message)) {
+				log_print("dlm msg too small: %u, will skip this message",
+					  msglen);
+				goto skip;
+			}
 
-		if (msglen > sizeof(__tmp) && p == &__tmp.p) {
-			p = kmalloc(dlm_config.ci_buffer_size, GFP_NOFS);
-			if (p == NULL)
-				return ret;
+			break;
+		case DLM_RCOM:
+			if (msglen < sizeof(struct dlm_rcom)) {
+				log_print("dlm rcom msg too small: %u, will skip this message",
+					  msglen);
+				goto skip;
 			}
 
-		copy_from_cb(p, base, offset, msglen, limit);
+			break;
+		default:
+			log_print("unsupported h_cmd received: %u, will skip this message",
+				  hd->h_cmd);
+			goto skip;
+		}
 
-		BUG_ON(lockspace != p->header.h_lockspace);
+		/* for aligned memory access, we just copy current message
+		 * to begin of the buffer which contains already parsed buffer
+		 * data and should provide align access for upper layers
+		 * because the start address of the buffer has a aligned
+		 * address. This memmove can be removed when the upperlayer
+		 * is capable of unaligned memory access.
+		 */
+		memmove(buf, ptr, msglen);
+		dlm_receive_buffer((union dlm_packet *)buf, nodeid);
 
+skip:
 		ret += msglen;
-		offset += msglen;
-		offset &= (limit - 1);
 		len -= msglen;
-
-		dlm_receive_buffer(p, nodeid);
+		ptr += msglen;
 	}
 
-	if (p != &__tmp.p)
-		kfree(p);
-
-	return err ? err : ret;
+	return ret;
 }
 

fs/dlm/midcomms.h

@@ -12,8 +12,7 @@
 #ifndef __MIDCOMMS_DOT_H__
 #define __MIDCOMMS_DOT_H__
 
-int dlm_process_incoming_buffer(int nodeid, const void *base, unsigned offset,
-				unsigned len, unsigned limit);
+int dlm_process_incoming_buffer(int nodeid, unsigned char *buf, int buflen);
 
 #endif				/* __MIDCOMMS_DOT_H__ */