[Drbd-dev] [PATCH 0/7] DRBD updates for the 3.19 merge window

[Drbd-dev] [PATCH 0/7] DRBD updates for the 3.19 merge window

[Philipp Reisner]

Hi Jens,

please take these patches for you for-3.19/drivers branch.
They where posted for review on 2014-10-29.

Some cleanups and 3 fixes. Two of them marked for stable:
0005-drbd-merge_bvec_fn-properly-remap-bvm-bi_bdev.patch and
0006-drbd-Fix-state-change-in-case-of-connection-timeout.patch
(marked for stable)

Thanks!


Andreas Gruenbacher (2):
  drbd: Minor cleanups
  drbd: Only use drbd_msg_put_info() in drbd_nl.c

Lars Ellenberg (2):
  drbd: fix resync throttling initialization
  drbd: merge_bvec_fn: properly remap bvm->bi_bdev

Philipp Reisner (3):
  drbd: fix race between role change and handshake
  drbd: Fix state change in case of connection timeout
  drbd: Remove an useless copy of kernel_setsockopt()

 drivers/block/drbd/drbd_actlog.c   |  3 +-
 drivers/block/drbd/drbd_int.h      | 39 +++++------------------
 drivers/block/drbd/drbd_main.c     | 23 ++++----------
 drivers/block/drbd/drbd_nl.c       | 64 +++++++++++++++++---------------------
 drivers/block/drbd/drbd_receiver.c |  2 +-
 drivers/block/drbd/drbd_req.c      |  3 +-
 drivers/block/drbd/drbd_state.c    | 42 ++++++++++++++++++++-----
 drivers/block/drbd/drbd_state.h    |  5 +++
 drivers/block/drbd/drbd_worker.c   |  5 ++-
 include/linux/drbd.h               |  2 +-
 10 files changed, 90 insertions(+), 98 deletions(-)

-- 
1.9.1

[PATCH 0/7] DRBD updates for the 3.19 merge window

[Philipp Reisner]

Hi Jens,

please take these patches for you for-3.19/drivers branch.
They where posted for review on 2014-10-29.

Some cleanups and 3 fixes. Two of them marked for stable:
0005-drbd-merge_bvec_fn-properly-remap-bvm-bi_bdev.patch and
0006-drbd-Fix-state-change-in-case-of-connection-timeout.patch
(marked for stable)

Thanks!


Andreas Gruenbacher (2):
  drbd: Minor cleanups
  drbd: Only use drbd_msg_put_info() in drbd_nl.c

Lars Ellenberg (2):
  drbd: fix resync throttling initialization
  drbd: merge_bvec_fn: properly remap bvm->bi_bdev

Philipp Reisner (3):
  drbd: fix race between role change and handshake
  drbd: Fix state change in case of connection timeout
  drbd: Remove an useless copy of kernel_setsockopt()

 drivers/block/drbd/drbd_actlog.c   |  3 +-
 drivers/block/drbd/drbd_int.h      | 39 +++++------------------
 drivers/block/drbd/drbd_main.c     | 23 ++++----------
 drivers/block/drbd/drbd_nl.c       | 64 +++++++++++++++++---------------------
 drivers/block/drbd/drbd_receiver.c |  2 +-
 drivers/block/drbd/drbd_req.c      |  3 +-
 drivers/block/drbd/drbd_state.c    | 42 ++++++++++++++++++++-----
 drivers/block/drbd/drbd_state.h    |  5 +++
 drivers/block/drbd/drbd_worker.c   |  5 ++-
 include/linux/drbd.h               |  2 +-
 10 files changed, 90 insertions(+), 98 deletions(-)

-- 
1.9.1

[Drbd-dev] [PATCH 1/7] drbd: Minor cleanups

[Philipp Reisner]

From: Andreas Gruenbacher <agruen@linbit.com>

 . Update comments
 . drbd_set_{in,out_of}_sync(): Remove unused parameters
 . Move common code into adm_del_resource()
 . Redefine ERR_MINOR_EXISTS -> ERR_MINOR_OR_VOLUME_EXISTS

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_actlog.c |  3 +-
 drivers/block/drbd/drbd_int.h    |  9 +++---
 drivers/block/drbd/drbd_main.c   |  6 ++--
 drivers/block/drbd/drbd_nl.c     | 60 +++++++++++++++++-----------------------
 include/linux/drbd.h             |  2 +-
 5 files changed, 35 insertions(+), 45 deletions(-)

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index a2dfa16..1318e32 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -827,8 +827,7 @@ static int update_sync_bits(struct drbd_device *device,
  *
  */
 int __drbd_change_sync(struct drbd_device *device, sector_t sector, int size,
-		enum update_sync_bits_mode mode,
-		const char *file, const unsigned int line)
+		enum update_sync_bits_mode mode)
 {
 	/* Is called from worker and receiver context _only_ */
 	unsigned long sbnr, ebnr, lbnr;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 9b22f8f..c14b718 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1662,14 +1662,13 @@ extern void drbd_advance_rs_marks(struct drbd_device *device, unsigned long stil
 
 enum update_sync_bits_mode { RECORD_RS_FAILED, SET_OUT_OF_SYNC, SET_IN_SYNC };
 extern int __drbd_change_sync(struct drbd_device *device, sector_t sector, int size,
-		enum update_sync_bits_mode mode,
-		const char *file, const unsigned int line);
+		enum update_sync_bits_mode mode);
 #define drbd_set_in_sync(device, sector, size) \
-	__drbd_change_sync(device, sector, size, SET_IN_SYNC, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, SET_IN_SYNC)
 #define drbd_set_out_of_sync(device, sector, size) \
-	__drbd_change_sync(device, sector, size, SET_OUT_OF_SYNC, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, SET_OUT_OF_SYNC)
 #define drbd_rs_failed_io(device, sector, size) \
-	__drbd_change_sync(device, sector, size, RECORD_RS_FAILED, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, RECORD_RS_FAILED)
 extern void drbd_al_shrink(struct drbd_device *device);
 extern int drbd_initialize_al(struct drbd_device *, void *);
 
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 973c185..cce25a5 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2731,7 +2731,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	device = minor_to_device(minor);
 	if (device)
-		return ERR_MINOR_EXISTS;
+		return ERR_MINOR_OR_VOLUME_EXISTS;
 
 	/* GFP_KERNEL, we are outside of all write-out paths */
 	device = kzalloc(sizeof(struct drbd_device), GFP_KERNEL);
@@ -2794,7 +2794,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	id = idr_alloc(&drbd_devices, device, minor, minor + 1, GFP_KERNEL);
 	if (id < 0) {
 		if (id == -ENOSPC) {
-			err = ERR_MINOR_EXISTS;
+			err = ERR_MINOR_OR_VOLUME_EXISTS;
 			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
 		}
 		goto out_no_minor_idr;
@@ -2804,7 +2804,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	id = idr_alloc(&resource->devices, device, vnr, vnr + 1, GFP_KERNEL);
 	if (id < 0) {
 		if (id == -ENOSPC) {
-			err = ERR_MINOR_EXISTS;
+			err = ERR_MINOR_OR_VOLUME_EXISTS;
 			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
 		}
 		goto out_idr_remove_minor;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 1cd47df..c145619 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2052,7 +2052,7 @@ check_net_options(struct drbd_connection *connection, struct net_conf *new_net_c
 	rv = _check_net_options(connection, rcu_dereference(connection->net_conf), new_net_conf);
 	rcu_read_unlock();
 
-	/* connection->volumes protected by genl_lock() here */
+	/* connection->peer_devices protected by genl_lock() here */
 	idr_for_each_entry(&connection->peer_devices, peer_device, i) {
 		struct drbd_device *device = peer_device->device;
 		if (!device->bitmap) {
@@ -3483,7 +3483,7 @@ int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info)
 	 * that first_peer_device(device)->connection and device->vnr match the request. */
 	if (adm_ctx.device) {
 		if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)
-			retcode = ERR_MINOR_EXISTS;
+			retcode = ERR_MINOR_OR_VOLUME_EXISTS;
 		/* else: still NO_ERROR */
 		goto out;
 	}
@@ -3530,6 +3530,27 @@ out:
 	return 0;
 }
 
+static int adm_del_resource(struct drbd_resource *resource)
+{
+	struct drbd_connection *connection;
+
+	for_each_connection(connection, resource) {
+		if (connection->cstate > C_STANDALONE)
+			return ERR_NET_CONFIGURED;
+	}
+	if (!idr_is_empty(&resource->devices))
+		return ERR_RES_IN_USE;
+
+	list_del_rcu(&resource->resources);
+	/* Make sure all threads have actually stopped: state handling only
+	 * does drbd_thread_stop_nowait(). */
+	list_for_each_entry(connection, &resource->connections, connections)
+		drbd_thread_stop(&connection->worker);
+	synchronize_rcu();
+	drbd_free_resource(resource);
+	return NO_ERROR;
+}
+
 int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
@@ -3575,14 +3596,6 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	/* If we reach this, all volumes (of this connection) are Secondary,
-	 * Disconnected, Diskless, aka Unconfigured. Make sure all threads have
-	 * actually stopped, state handling only does drbd_thread_stop_nowait(). */
-	for_each_connection(connection, resource)
-		drbd_thread_stop(&connection->worker);
-
-	/* Now, nothing can fail anymore */
-
 	/* delete volumes */
 	idr_for_each_entry(&resource->devices, device, i) {
 		retcode = adm_del_minor(device);
@@ -3593,10 +3606,7 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	list_del_rcu(&resource->resources);
-	synchronize_rcu();
-	drbd_free_resource(resource);
-	retcode = NO_ERROR;
+	retcode = adm_del_resource(resource);
 out:
 	mutex_unlock(&resource->adm_mutex);
 finish:
@@ -3608,7 +3618,6 @@ int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
 	struct drbd_resource *resource;
-	struct drbd_connection *connection;
 	enum drbd_ret_code retcode;
 
 	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE);
@@ -3616,27 +3625,10 @@ int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto finish;
-
 	resource = adm_ctx.resource;
-	mutex_lock(&resource->adm_mutex);
-	for_each_connection(connection, resource) {
-		if (connection->cstate > C_STANDALONE) {
-			retcode = ERR_NET_CONFIGURED;
-			goto out;
-		}
-	}
-	if (!idr_is_empty(&resource->devices)) {
-		retcode = ERR_RES_IN_USE;
-		goto out;
-	}
 
-	list_del_rcu(&resource->resources);
-	for_each_connection(connection, resource)
-		drbd_thread_stop(&connection->worker);
-	synchronize_rcu();
-	drbd_free_resource(resource);
-	retcode = NO_ERROR;
-out:
+	mutex_lock(&resource->adm_mutex);
+	retcode = adm_del_resource(resource);
 	mutex_unlock(&resource->adm_mutex);
 finish:
 	drbd_adm_finish(&adm_ctx, info, retcode);
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index debb70d..8723f2a 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -172,7 +172,7 @@ enum drbd_ret_code {
 	ERR_RES_NOT_KNOWN	= 158,
 	ERR_RES_IN_USE		= 159,
 	ERR_MINOR_CONFIGURED    = 160,
-	ERR_MINOR_EXISTS	= 161,
+	ERR_MINOR_OR_VOLUME_EXISTS = 161,
 	ERR_INVALID_REQUEST	= 162,
 	ERR_NEED_APV_100	= 163,
 	ERR_NEED_ALLOW_TWO_PRI  = 164,
-- 
1.9.1

[PATCH 1/7] drbd: Minor cleanups

[Philipp Reisner]

From: Andreas Gruenbacher <agruen@linbit.com>

 . Update comments
 . drbd_set_{in,out_of}_sync(): Remove unused parameters
 . Move common code into adm_del_resource()
 . Redefine ERR_MINOR_EXISTS -> ERR_MINOR_OR_VOLUME_EXISTS

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_actlog.c |  3 +-
 drivers/block/drbd/drbd_int.h    |  9 +++---
 drivers/block/drbd/drbd_main.c   |  6 ++--
 drivers/block/drbd/drbd_nl.c     | 60 +++++++++++++++++-----------------------
 include/linux/drbd.h             |  2 +-
 5 files changed, 35 insertions(+), 45 deletions(-)

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index a2dfa16..1318e32 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -827,8 +827,7 @@ static int update_sync_bits(struct drbd_device *device,
  *
  */
 int __drbd_change_sync(struct drbd_device *device, sector_t sector, int size,
-		enum update_sync_bits_mode mode,
-		const char *file, const unsigned int line)
+		enum update_sync_bits_mode mode)
 {
 	/* Is called from worker and receiver context _only_ */
 	unsigned long sbnr, ebnr, lbnr;
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 9b22f8f..c14b718 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1662,14 +1662,13 @@ extern void drbd_advance_rs_marks(struct drbd_device *device, unsigned long stil
 
 enum update_sync_bits_mode { RECORD_RS_FAILED, SET_OUT_OF_SYNC, SET_IN_SYNC };
 extern int __drbd_change_sync(struct drbd_device *device, sector_t sector, int size,
-		enum update_sync_bits_mode mode,
-		const char *file, const unsigned int line);
+		enum update_sync_bits_mode mode);
 #define drbd_set_in_sync(device, sector, size) \
-	__drbd_change_sync(device, sector, size, SET_IN_SYNC, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, SET_IN_SYNC)
 #define drbd_set_out_of_sync(device, sector, size) \
-	__drbd_change_sync(device, sector, size, SET_OUT_OF_SYNC, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, SET_OUT_OF_SYNC)
 #define drbd_rs_failed_io(device, sector, size) \
-	__drbd_change_sync(device, sector, size, RECORD_RS_FAILED, __FILE__, __LINE__)
+	__drbd_change_sync(device, sector, size, RECORD_RS_FAILED)
 extern void drbd_al_shrink(struct drbd_device *device);
 extern int drbd_initialize_al(struct drbd_device *, void *);
 
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 973c185..cce25a5 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2731,7 +2731,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	device = minor_to_device(minor);
 	if (device)
-		return ERR_MINOR_EXISTS;
+		return ERR_MINOR_OR_VOLUME_EXISTS;
 
 	/* GFP_KERNEL, we are outside of all write-out paths */
 	device = kzalloc(sizeof(struct drbd_device), GFP_KERNEL);
@@ -2794,7 +2794,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	id = idr_alloc(&drbd_devices, device, minor, minor + 1, GFP_KERNEL);
 	if (id < 0) {
 		if (id == -ENOSPC) {
-			err = ERR_MINOR_EXISTS;
+			err = ERR_MINOR_OR_VOLUME_EXISTS;
 			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
 		}
 		goto out_no_minor_idr;
@@ -2804,7 +2804,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	id = idr_alloc(&resource->devices, device, vnr, vnr + 1, GFP_KERNEL);
 	if (id < 0) {
 		if (id == -ENOSPC) {
-			err = ERR_MINOR_EXISTS;
+			err = ERR_MINOR_OR_VOLUME_EXISTS;
 			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
 		}
 		goto out_idr_remove_minor;
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 1cd47df..c145619 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2052,7 +2052,7 @@ check_net_options(struct drbd_connection *connection, struct net_conf *new_net_c
 	rv = _check_net_options(connection, rcu_dereference(connection->net_conf), new_net_conf);
 	rcu_read_unlock();
 
-	/* connection->volumes protected by genl_lock() here */
+	/* connection->peer_devices protected by genl_lock() here */
 	idr_for_each_entry(&connection->peer_devices, peer_device, i) {
 		struct drbd_device *device = peer_device->device;
 		if (!device->bitmap) {
@@ -3483,7 +3483,7 @@ int drbd_adm_new_minor(struct sk_buff *skb, struct genl_info *info)
 	 * that first_peer_device(device)->connection and device->vnr match the request. */
 	if (adm_ctx.device) {
 		if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)
-			retcode = ERR_MINOR_EXISTS;
+			retcode = ERR_MINOR_OR_VOLUME_EXISTS;
 		/* else: still NO_ERROR */
 		goto out;
 	}
@@ -3530,6 +3530,27 @@ out:
 	return 0;
 }
 
+static int adm_del_resource(struct drbd_resource *resource)
+{
+	struct drbd_connection *connection;
+
+	for_each_connection(connection, resource) {
+		if (connection->cstate > C_STANDALONE)
+			return ERR_NET_CONFIGURED;
+	}
+	if (!idr_is_empty(&resource->devices))
+		return ERR_RES_IN_USE;
+
+	list_del_rcu(&resource->resources);
+	/* Make sure all threads have actually stopped: state handling only
+	 * does drbd_thread_stop_nowait(). */
+	list_for_each_entry(connection, &resource->connections, connections)
+		drbd_thread_stop(&connection->worker);
+	synchronize_rcu();
+	drbd_free_resource(resource);
+	return NO_ERROR;
+}
+
 int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
@@ -3575,14 +3596,6 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	/* If we reach this, all volumes (of this connection) are Secondary,
-	 * Disconnected, Diskless, aka Unconfigured. Make sure all threads have
-	 * actually stopped, state handling only does drbd_thread_stop_nowait(). */
-	for_each_connection(connection, resource)
-		drbd_thread_stop(&connection->worker);
-
-	/* Now, nothing can fail anymore */
-
 	/* delete volumes */
 	idr_for_each_entry(&resource->devices, device, i) {
 		retcode = adm_del_minor(device);
@@ -3593,10 +3606,7 @@ int drbd_adm_down(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	list_del_rcu(&resource->resources);
-	synchronize_rcu();
-	drbd_free_resource(resource);
-	retcode = NO_ERROR;
+	retcode = adm_del_resource(resource);
 out:
 	mutex_unlock(&resource->adm_mutex);
 finish:
@@ -3608,7 +3618,6 @@ int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 {
 	struct drbd_config_context adm_ctx;
 	struct drbd_resource *resource;
-	struct drbd_connection *connection;
 	enum drbd_ret_code retcode;
 
 	retcode = drbd_adm_prepare(&adm_ctx, skb, info, DRBD_ADM_NEED_RESOURCE);
@@ -3616,27 +3625,10 @@ int drbd_adm_del_resource(struct sk_buff *skb, struct genl_info *info)
 		return retcode;
 	if (retcode != NO_ERROR)
 		goto finish;
-
 	resource = adm_ctx.resource;
-	mutex_lock(&resource->adm_mutex);
-	for_each_connection(connection, resource) {
-		if (connection->cstate > C_STANDALONE) {
-			retcode = ERR_NET_CONFIGURED;
-			goto out;
-		}
-	}
-	if (!idr_is_empty(&resource->devices)) {
-		retcode = ERR_RES_IN_USE;
-		goto out;
-	}
 
-	list_del_rcu(&resource->resources);
-	for_each_connection(connection, resource)
-		drbd_thread_stop(&connection->worker);
-	synchronize_rcu();
-	drbd_free_resource(resource);
-	retcode = NO_ERROR;
-out:
+	mutex_lock(&resource->adm_mutex);
+	retcode = adm_del_resource(resource);
 	mutex_unlock(&resource->adm_mutex);
 finish:
 	drbd_adm_finish(&adm_ctx, info, retcode);
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index debb70d..8723f2a 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -172,7 +172,7 @@ enum drbd_ret_code {
 	ERR_RES_NOT_KNOWN	= 158,
 	ERR_RES_IN_USE		= 159,
 	ERR_MINOR_CONFIGURED    = 160,
-	ERR_MINOR_EXISTS	= 161,
+	ERR_MINOR_OR_VOLUME_EXISTS = 161,
 	ERR_INVALID_REQUEST	= 162,
 	ERR_NEED_APV_100	= 163,
 	ERR_NEED_ALLOW_TWO_PRI  = 164,
-- 
1.9.1

[Drbd-dev] [PATCH 2/7] drbd: Only use drbd_msg_put_info() in drbd_nl.c

[Philipp Reisner]

From: Andreas Gruenbacher <agruen@linbit.com>

Avoid generic netlink calls in other parts of the code base.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h  |  1 -
 drivers/block/drbd/drbd_main.c | 17 +++--------------
 drivers/block/drbd/drbd_nl.c   |  2 +-
 3 files changed, 4 insertions(+), 16 deletions(-)

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index c14b718..d2a7589 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1454,7 +1454,6 @@ extern int is_valid_ar_handle(struct drbd_request *, sector_t);
 
 
 /* drbd_nl.c */
-extern int drbd_msg_put_info(struct sk_buff *skb, const char *info);
 extern void drbd_suspend_io(struct drbd_device *device);
 extern void drbd_resume_io(struct drbd_device *device);
 extern char *ppsize(char *buf, unsigned long long size);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index cce25a5..1fc8342 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2532,10 +2532,6 @@ int set_resource_options(struct drbd_resource *resource, struct res_opts *res_op
 
 	if (!zalloc_cpumask_var(&new_cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
-		/*
-		retcode = ERR_NOMEM;
-		drbd_msg_put_info("unable to allocate cpumask");
-		*/
 
 	/* silently ignore cpu mask on UP kernel */
 	if (nr_cpu_ids > 1 && res_opts->cpu_mask[0] != 0) {
@@ -2793,20 +2789,16 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	id = idr_alloc(&drbd_devices, device, minor, minor + 1, GFP_KERNEL);
 	if (id < 0) {
-		if (id == -ENOSPC) {
+		if (id == -ENOSPC)
 			err = ERR_MINOR_OR_VOLUME_EXISTS;
-			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
-		}
 		goto out_no_minor_idr;
 	}
 	kref_get(&device->kref);
 
 	id = idr_alloc(&resource->devices, device, vnr, vnr + 1, GFP_KERNEL);
 	if (id < 0) {
-		if (id == -ENOSPC) {
+		if (id == -ENOSPC)
 			err = ERR_MINOR_OR_VOLUME_EXISTS;
-			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
-		}
 		goto out_idr_remove_minor;
 	}
 	kref_get(&device->kref);
@@ -2825,10 +2817,8 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 		id = idr_alloc(&connection->peer_devices, peer_device, vnr, vnr + 1, GFP_KERNEL);
 		if (id < 0) {
-			if (id == -ENOSPC) {
+			if (id == -ENOSPC)
 				err = ERR_INVALID_REQUEST;
-				drbd_msg_put_info(adm_ctx->reply_skb, "requested volume exists already");
-			}
 			goto out_idr_remove_from_resource;
 		}
 		kref_get(&connection->kref);
@@ -2836,7 +2826,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	if (init_submitter(device)) {
 		err = ERR_NOMEM;
-		drbd_msg_put_info(adm_ctx->reply_skb, "unable to create submit workqueue");
 		goto out_idr_remove_vol;
 	}
 
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index c145619..4782d07 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -92,7 +92,7 @@ static void drbd_adm_send_reply(struct sk_buff *skb, struct genl_info *info)
 
 /* Used on a fresh "drbd_adm_prepare"d reply_skb, this cannot fail: The only
  * reason it could fail was no space in skb, and there are 4k available. */
-int drbd_msg_put_info(struct sk_buff *skb, const char *info)
+static int drbd_msg_put_info(struct sk_buff *skb, const char *info)
 {
 	struct nlattr *nla;
 	int err = -EMSGSIZE;
-- 
1.9.1

[PATCH 2/7] drbd: Only use drbd_msg_put_info() in drbd_nl.c

[Philipp Reisner]

From: Andreas Gruenbacher <agruen@linbit.com>

Avoid generic netlink calls in other parts of the code base.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h  |  1 -
 drivers/block/drbd/drbd_main.c | 17 +++--------------
 drivers/block/drbd/drbd_nl.c   |  2 +-
 3 files changed, 4 insertions(+), 16 deletions(-)

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index c14b718..d2a7589 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1454,7 +1454,6 @@ extern int is_valid_ar_handle(struct drbd_request *, sector_t);
 
 
 /* drbd_nl.c */
-extern int drbd_msg_put_info(struct sk_buff *skb, const char *info);
 extern void drbd_suspend_io(struct drbd_device *device);
 extern void drbd_resume_io(struct drbd_device *device);
 extern char *ppsize(char *buf, unsigned long long size);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index cce25a5..1fc8342 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2532,10 +2532,6 @@ int set_resource_options(struct drbd_resource *resource, struct res_opts *res_op
 
 	if (!zalloc_cpumask_var(&new_cpu_mask, GFP_KERNEL))
 		return -ENOMEM;
-		/*
-		retcode = ERR_NOMEM;
-		drbd_msg_put_info("unable to allocate cpumask");
-		*/
 
 	/* silently ignore cpu mask on UP kernel */
 	if (nr_cpu_ids > 1 && res_opts->cpu_mask[0] != 0) {
@@ -2793,20 +2789,16 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	id = idr_alloc(&drbd_devices, device, minor, minor + 1, GFP_KERNEL);
 	if (id < 0) {
-		if (id == -ENOSPC) {
+		if (id == -ENOSPC)
 			err = ERR_MINOR_OR_VOLUME_EXISTS;
-			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
-		}
 		goto out_no_minor_idr;
 	}
 	kref_get(&device->kref);
 
 	id = idr_alloc(&resource->devices, device, vnr, vnr + 1, GFP_KERNEL);
 	if (id < 0) {
-		if (id == -ENOSPC) {
+		if (id == -ENOSPC)
 			err = ERR_MINOR_OR_VOLUME_EXISTS;
-			drbd_msg_put_info(adm_ctx->reply_skb, "requested minor exists already");
-		}
 		goto out_idr_remove_minor;
 	}
 	kref_get(&device->kref);
@@ -2825,10 +2817,8 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 		id = idr_alloc(&connection->peer_devices, peer_device, vnr, vnr + 1, GFP_KERNEL);
 		if (id < 0) {
-			if (id == -ENOSPC) {
+			if (id == -ENOSPC)
 				err = ERR_INVALID_REQUEST;
-				drbd_msg_put_info(adm_ctx->reply_skb, "requested volume exists already");
-			}
 			goto out_idr_remove_from_resource;
 		}
 		kref_get(&connection->kref);
@@ -2836,7 +2826,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 
 	if (init_submitter(device)) {
 		err = ERR_NOMEM;
-		drbd_msg_put_info(adm_ctx->reply_skb, "unable to create submit workqueue");
 		goto out_idr_remove_vol;
 	}
 
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index c145619..4782d07 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -92,7 +92,7 @@ static void drbd_adm_send_reply(struct sk_buff *skb, struct genl_info *info)
 
 /* Used on a fresh "drbd_adm_prepare"d reply_skb, this cannot fail: The only
  * reason it could fail was no space in skb, and there are 4k available. */
-int drbd_msg_put_info(struct sk_buff *skb, const char *info)
+static int drbd_msg_put_info(struct sk_buff *skb, const char *info)
 {
 	struct nlattr *nla;
 	int err = -EMSGSIZE;
-- 
1.9.1

[Drbd-dev] [PATCH 3/7] drbd: fix race between role change and handshake

[Philipp Reisner]

Symptoms:
If DRBD was "cleanly shut down" (all in sync, both Secondary before
disconnect, identical data generation uuids), and then one side was
promoted *during* the next connection handshake, the role change
could confuse the handshake.

The Primary would get stuck in WFBitmapS, the Secondary would log
unexpected cstate (Connected) in receive_bitmap
and get stuck in WFBitmapT.

Fix:
The test in is_valid_soft_transition wrong. It works because
the not allowed actions (promote/attach) do not touch the
cstate. The previous condition failed to demand a cstate change
in one clause.

In order to avoid deadlocks give up the state_mutex while waiting
for the transient state to go away.

Conflicts:
	drbd/drbd_state.c
	drbd/drbd_state.h
	drbd/drbd_wrappers.h

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_nl.c    |  2 +-
 drivers/block/drbd/drbd_state.c | 41 ++++++++++++++++++++++++++++++++++-------
 drivers/block/drbd/drbd_state.h |  5 +++++
 3 files changed, 40 insertions(+), 8 deletions(-)

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 4782d07..74df8cf 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -588,7 +588,7 @@ drbd_set_role(struct drbd_device *const device, enum drbd_role new_role, int for
 	val.i  = 0; val.role  = new_role;
 
 	while (try++ < max_tries) {
-		rv = _drbd_request_state(device, mask, val, CS_WAIT_COMPLETE);
+		rv = _drbd_request_state_holding_state_mutex(device, mask, val, CS_WAIT_COMPLETE);
 
 		/* in case we first succeeded to outdate,
 		 * but now suddenly could establish a connection */
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 84b11f8..4529d92 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -215,6 +215,18 @@ static bool no_peer_wf_report_params(struct drbd_connection *connection)
 	return rv;
 }
 
+static void wake_up_all_devices(struct drbd_connection *connection)
+{
+	struct drbd_peer_device *peer_device;
+	int vnr;
+
+	rcu_read_lock();
+	idr_for_each_entry(&connection->peer_devices, peer_device, vnr)
+		wake_up(&peer_device->device->state_wait);
+	rcu_read_unlock();
+
+}
+
 
 /**
  * cl_wide_st_chg() - true if the state change is a cluster wide one
@@ -410,6 +422,22 @@ _drbd_request_state(struct drbd_device *device, union drbd_state mask,
 	return rv;
 }
 
+enum drbd_state_rv
+_drbd_request_state_holding_state_mutex(struct drbd_device *device, union drbd_state mask,
+		    union drbd_state val, enum chg_state_flags f)
+{
+	enum drbd_state_rv rv;
+
+	BUG_ON(f & CS_SERIALIZE);
+
+	wait_event_cmd(device->state_wait,
+		       (rv = drbd_req_state(device, mask, val, f)) != SS_IN_TRANSIENT_STATE,
+		       mutex_unlock(device->state_mutex),
+		       mutex_lock(device->state_mutex));
+
+	return rv;
+}
+
 static void print_st(struct drbd_device *device, const char *name, union drbd_state ns)
 {
 	drbd_err(device, " %s = { cs:%s ro:%s/%s ds:%s/%s %c%c%c%c%c%c }\n",
@@ -629,14 +657,11 @@ is_valid_soft_transition(union drbd_state os, union drbd_state ns, struct drbd_c
 	if (ns.conn == C_DISCONNECTING && os.conn == C_UNCONNECTED)
 		rv = SS_IN_TRANSIENT_STATE;
 
-	/* if (ns.conn == os.conn && ns.conn == C_WF_REPORT_PARAMS)
-	   rv = SS_IN_TRANSIENT_STATE; */
-
 	/* While establishing a connection only allow cstate to change.
-	   Delay/refuse role changes, detach attach etc... */
+	   Delay/refuse role changes, detach attach etc... (they do not touch cstate) */
 	if (test_bit(STATE_SENT, &connection->flags) &&
-	    !(os.conn == C_WF_REPORT_PARAMS ||
-	      (ns.conn == C_WF_REPORT_PARAMS && os.conn == C_WF_CONNECTION)))
+	    !((ns.conn == C_WF_REPORT_PARAMS && os.conn == C_WF_CONNECTION) ||
+	      (ns.conn >= C_CONNECTED && os.conn == C_WF_REPORT_PARAMS)))
 		rv = SS_IN_TRANSIENT_STATE;
 
 	if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && os.conn < C_CONNECTED)
@@ -1032,8 +1057,10 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 
 	/* Wake up role changes, that were delayed because of connection establishing */
 	if (os.conn == C_WF_REPORT_PARAMS && ns.conn != C_WF_REPORT_PARAMS &&
-	    no_peer_wf_report_params(connection))
+	    no_peer_wf_report_params(connection)) {
 		clear_bit(STATE_SENT, &connection->flags);
+		wake_up_all_devices(connection);
+	}
 
 	wake_up(&device->misc_wait);
 	wake_up(&device->state_wait);
diff --git a/drivers/block/drbd/drbd_state.h b/drivers/block/drbd/drbd_state.h
index cc41605..7f53c40 100644
--- a/drivers/block/drbd/drbd_state.h
+++ b/drivers/block/drbd/drbd_state.h
@@ -117,6 +117,11 @@ extern enum drbd_state_rv _drbd_request_state(struct drbd_device *,
 					      union drbd_state,
 					      union drbd_state,
 					      enum chg_state_flags);
+
+extern enum drbd_state_rv
+_drbd_request_state_holding_state_mutex(struct drbd_device *, union drbd_state,
+					union drbd_state, enum chg_state_flags);
+
 extern enum drbd_state_rv __drbd_set_state(struct drbd_device *, union drbd_state,
 					   enum chg_state_flags,
 					   struct completion *done);
-- 
1.9.1

[PATCH 3/7] drbd: fix race between role change and handshake

[Philipp Reisner]

Symptoms:
If DRBD was "cleanly shut down" (all in sync, both Secondary before
disconnect, identical data generation uuids), and then one side was
promoted *during* the next connection handshake, the role change
could confuse the handshake.

The Primary would get stuck in WFBitmapS, the Secondary would log
unexpected cstate (Connected) in receive_bitmap
and get stuck in WFBitmapT.

Fix:
The test in is_valid_soft_transition wrong. It works because
the not allowed actions (promote/attach) do not touch the
cstate. The previous condition failed to demand a cstate change
in one clause.

In order to avoid deadlocks give up the state_mutex while waiting
for the transient state to go away.

Conflicts:
	drbd/drbd_state.c
	drbd/drbd_state.h
	drbd/drbd_wrappers.h

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_nl.c    |  2 +-
 drivers/block/drbd/drbd_state.c | 41 ++++++++++++++++++++++++++++++++++-------
 drivers/block/drbd/drbd_state.h |  5 +++++
 3 files changed, 40 insertions(+), 8 deletions(-)

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 4782d07..74df8cf 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -588,7 +588,7 @@ drbd_set_role(struct drbd_device *const device, enum drbd_role new_role, int for
 	val.i  = 0; val.role  = new_role;
 
 	while (try++ < max_tries) {
-		rv = _drbd_request_state(device, mask, val, CS_WAIT_COMPLETE);
+		rv = _drbd_request_state_holding_state_mutex(device, mask, val, CS_WAIT_COMPLETE);
 
 		/* in case we first succeeded to outdate,
 		 * but now suddenly could establish a connection */
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 84b11f8..4529d92 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -215,6 +215,18 @@ static bool no_peer_wf_report_params(struct drbd_connection *connection)
 	return rv;
 }
 
+static void wake_up_all_devices(struct drbd_connection *connection)
+{
+	struct drbd_peer_device *peer_device;
+	int vnr;
+
+	rcu_read_lock();
+	idr_for_each_entry(&connection->peer_devices, peer_device, vnr)
+		wake_up(&peer_device->device->state_wait);
+	rcu_read_unlock();
+
+}
+
 
 /**
  * cl_wide_st_chg() - true if the state change is a cluster wide one
@@ -410,6 +422,22 @@ _drbd_request_state(struct drbd_device *device, union drbd_state mask,
 	return rv;
 }
 
+enum drbd_state_rv
+_drbd_request_state_holding_state_mutex(struct drbd_device *device, union drbd_state mask,
+		    union drbd_state val, enum chg_state_flags f)
+{
+	enum drbd_state_rv rv;
+
+	BUG_ON(f & CS_SERIALIZE);
+
+	wait_event_cmd(device->state_wait,
+		       (rv = drbd_req_state(device, mask, val, f)) != SS_IN_TRANSIENT_STATE,
+		       mutex_unlock(device->state_mutex),
+		       mutex_lock(device->state_mutex));
+
+	return rv;
+}
+
 static void print_st(struct drbd_device *device, const char *name, union drbd_state ns)
 {
 	drbd_err(device, " %s = { cs:%s ro:%s/%s ds:%s/%s %c%c%c%c%c%c }\n",
@@ -629,14 +657,11 @@ is_valid_soft_transition(union drbd_state os, union drbd_state ns, struct drbd_c
 	if (ns.conn == C_DISCONNECTING && os.conn == C_UNCONNECTED)
 		rv = SS_IN_TRANSIENT_STATE;
 
-	/* if (ns.conn == os.conn && ns.conn == C_WF_REPORT_PARAMS)
-	   rv = SS_IN_TRANSIENT_STATE; */
-
 	/* While establishing a connection only allow cstate to change.
-	   Delay/refuse role changes, detach attach etc... */
+	   Delay/refuse role changes, detach attach etc... (they do not touch cstate) */
 	if (test_bit(STATE_SENT, &connection->flags) &&
-	    !(os.conn == C_WF_REPORT_PARAMS ||
-	      (ns.conn == C_WF_REPORT_PARAMS && os.conn == C_WF_CONNECTION)))
+	    !((ns.conn == C_WF_REPORT_PARAMS && os.conn == C_WF_CONNECTION) ||
+	      (ns.conn >= C_CONNECTED && os.conn == C_WF_REPORT_PARAMS)))
 		rv = SS_IN_TRANSIENT_STATE;
 
 	if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && os.conn < C_CONNECTED)
@@ -1032,8 +1057,10 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 
 	/* Wake up role changes, that were delayed because of connection establishing */
 	if (os.conn == C_WF_REPORT_PARAMS && ns.conn != C_WF_REPORT_PARAMS &&
-	    no_peer_wf_report_params(connection))
+	    no_peer_wf_report_params(connection)) {
 		clear_bit(STATE_SENT, &connection->flags);
+		wake_up_all_devices(connection);
+	}
 
 	wake_up(&device->misc_wait);
 	wake_up(&device->state_wait);
diff --git a/drivers/block/drbd/drbd_state.h b/drivers/block/drbd/drbd_state.h
index cc41605..7f53c40 100644
--- a/drivers/block/drbd/drbd_state.h
+++ b/drivers/block/drbd/drbd_state.h
@@ -117,6 +117,11 @@ extern enum drbd_state_rv _drbd_request_state(struct drbd_device *,
 					      union drbd_state,
 					      union drbd_state,
 					      enum chg_state_flags);
+
+extern enum drbd_state_rv
+_drbd_request_state_holding_state_mutex(struct drbd_device *, union drbd_state,
+					union drbd_state, enum chg_state_flags);
+
 extern enum drbd_state_rv __drbd_set_state(struct drbd_device *, union drbd_state,
 					   enum chg_state_flags,
 					   struct completion *done);
-- 
1.9.1

[Drbd-dev] [PATCH 4/7] drbd: fix resync throttling initialization

[Philipp Reisner]

From: Lars Ellenberg <lars.ellenberg@linbit.com>

If for some reason DRBD resync was the only activity on a backend
device, drbd_rs_c_min_rate_throttle() would mistakenly decide that it is
still initialization time, and keep throttling the resync.

This patch explicitly initializes ->rs_last_events to the current
backend event counters, and drops the rs_last_events == 0 from the
throttle condition.

Reported-by: Mikhail Sugakov <msugakov@amazon.de>

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_receiver.c | 2 +-
 drivers/block/drbd/drbd_state.c    | 1 -
 drivers/block/drbd/drbd_worker.c   | 5 ++++-
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 6960fb0..d169b4a 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2482,7 +2482,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device)
 			atomic_read(&device->rs_sect_ev);
 
 	if (atomic_read(&device->ap_actlog_cnt)
-	    || !device->rs_last_events || curr_events - device->rs_last_events > 64) {
+	    || curr_events - device->rs_last_events > 64) {
 		unsigned long rs_left;
 		int i;
 
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 4529d92..2d7dd26 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -1099,7 +1099,6 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 
 		set_ov_position(device, ns.conn);
 		device->rs_start = now;
-		device->rs_last_events = 0;
 		device->rs_last_sect_ev = 0;
 		device->ov_last_oos_size = 0;
 		device->ov_last_oos_start = 0;
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index d2d1f97..d0fae55 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1592,11 +1592,15 @@ void drbd_resync_after_changed(struct drbd_device *device)
 
 void drbd_rs_controller_reset(struct drbd_device *device)
 {
+	struct gendisk *disk = device->ldev->backing_bdev->bd_contains->bd_disk;
 	struct fifo_buffer *plan;
 
 	atomic_set(&device->rs_sect_in, 0);
 	atomic_set(&device->rs_sect_ev, 0);
 	device->rs_in_flight = 0;
+	device->rs_last_events =
+		(int)part_stat_read(&disk->part0, sectors[0]) +
+		(int)part_stat_read(&disk->part0, sectors[1]);
 
 	/* Updating the RCU protected object in place is necessary since
 	   this function gets called from atomic context.
@@ -1743,7 +1747,6 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 		device->rs_failed    = 0;
 		device->rs_paused    = 0;
 		device->rs_same_csum = 0;
-		device->rs_last_events = 0;
 		device->rs_last_sect_ev = 0;
 		device->rs_total     = tw;
 		device->rs_start     = now;
-- 
1.9.1

[PATCH 4/7] drbd: fix resync throttling initialization

[Philipp Reisner]

From: Lars Ellenberg <lars.ellenberg@linbit.com>

If for some reason DRBD resync was the only activity on a backend
device, drbd_rs_c_min_rate_throttle() would mistakenly decide that it is
still initialization time, and keep throttling the resync.

This patch explicitly initializes ->rs_last_events to the current
backend event counters, and drops the rs_last_events == 0 from the
throttle condition.

Reported-by: Mikhail Sugakov <msugakov@amazon.de>

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_receiver.c | 2 +-
 drivers/block/drbd/drbd_state.c    | 1 -
 drivers/block/drbd/drbd_worker.c   | 5 ++++-
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 6960fb0..d169b4a 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2482,7 +2482,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device)
 			atomic_read(&device->rs_sect_ev);
 
 	if (atomic_read(&device->ap_actlog_cnt)
-	    || !device->rs_last_events || curr_events - device->rs_last_events > 64) {
+	    || curr_events - device->rs_last_events > 64) {
 		unsigned long rs_left;
 		int i;
 
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 4529d92..2d7dd26 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -1099,7 +1099,6 @@ __drbd_set_state(struct drbd_device *device, union drbd_state ns,
 
 		set_ov_position(device, ns.conn);
 		device->rs_start = now;
-		device->rs_last_events = 0;
 		device->rs_last_sect_ev = 0;
 		device->ov_last_oos_size = 0;
 		device->ov_last_oos_start = 0;
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index d2d1f97..d0fae55 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1592,11 +1592,15 @@ void drbd_resync_after_changed(struct drbd_device *device)
 
 void drbd_rs_controller_reset(struct drbd_device *device)
 {
+	struct gendisk *disk = device->ldev->backing_bdev->bd_contains->bd_disk;
 	struct fifo_buffer *plan;
 
 	atomic_set(&device->rs_sect_in, 0);
 	atomic_set(&device->rs_sect_ev, 0);
 	device->rs_in_flight = 0;
+	device->rs_last_events =
+		(int)part_stat_read(&disk->part0, sectors[0]) +
+		(int)part_stat_read(&disk->part0, sectors[1]);
 
 	/* Updating the RCU protected object in place is necessary since
 	   this function gets called from atomic context.
@@ -1743,7 +1747,6 @@ void drbd_start_resync(struct drbd_device *device, enum drbd_conns side)
 		device->rs_failed    = 0;
 		device->rs_paused    = 0;
 		device->rs_same_csum = 0;
-		device->rs_last_events = 0;
 		device->rs_last_sect_ev = 0;
 		device->rs_total     = tw;
 		device->rs_start     = now;
-- 
1.9.1

[Drbd-dev] [PATCH 5/7] drbd: merge_bvec_fn: properly remap bvm->bi_bdev

[Philipp Reisner]

From: Lars Ellenberg <lars.ellenberg@linbit.com>

This was not noticed for many years. Affects operation if
md raid is used a backing device for DRBD.

CC: stable@kernel.org # v3.2+
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_req.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 5a01c53..90319b1 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1545,6 +1545,7 @@ int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct
 		struct request_queue * const b =
 			device->ldev->backing_bdev->bd_disk->queue;
 		if (b->merge_bvec_fn) {
+			bvm->bi_bdev = device->ldev->backing_bdev;
 			backing_limit = b->merge_bvec_fn(b, bvm, bvec);
 			limit = min(limit, backing_limit);
 		}
-- 
1.9.1

[PATCH 5/7] drbd: merge_bvec_fn: properly remap bvm->bi_bdev

[Philipp Reisner]

From: Lars Ellenberg <lars.ellenberg@linbit.com>

This was not noticed for many years. Affects operation if
md raid is used a backing device for DRBD.

CC: stable@kernel.org # v3.2+
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_req.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 5a01c53..90319b1 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1545,6 +1545,7 @@ int drbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct
 		struct request_queue * const b =
 			device->ldev->backing_bdev->bd_disk->queue;
 		if (b->merge_bvec_fn) {
+			bvm->bi_bdev = device->ldev->backing_bdev;
 			backing_limit = b->merge_bvec_fn(b, bvm, bvec);
 			limit = min(limit, backing_limit);
 		}
-- 
1.9.1

[Drbd-dev] [PATCH 6/7] drbd: Fix state change in case of connection timeout

[Philipp Reisner]

A connection timeout affects all volumes of a resource!
Under the following conditions:

 A resource with multiple volumes
  AND
 ko-count >=1
  AND
 a write request triggers the timeout (ko-count * timeout)

DRBD's internal state gets confused. That in turn may
lead to very miss leading follow up failures. E.g.
"BUG: scheduling while atomic"

CC: stable@kernel.org # v3.17
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_req.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 90319b1..3b797cd 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1629,7 +1629,7 @@ void request_timer_fn(unsigned long data)
 		 time_after(now, req_peer->pre_send_jif + ent) &&
 		!time_in_range(now, connection->last_reconnect_jif, connection->last_reconnect_jif + ent)) {
 		drbd_warn(device, "Remote failed to finish a request within ko-count * timeout\n");
-		_drbd_set_state(_NS(device, conn, C_TIMEOUT), CS_VERBOSE | CS_HARD, NULL);
+		_conn_request_state(connection, NS(conn, C_TIMEOUT), CS_VERBOSE | CS_HARD);
 	}
 	if (dt && oldest_submit_jif != now &&
 		 time_after(now, oldest_submit_jif + dt) &&
-- 
1.9.1

[PATCH 6/7] drbd: Fix state change in case of connection timeout

[Philipp Reisner]

A connection timeout affects all volumes of a resource!
Under the following conditions:

 A resource with multiple volumes
  AND
 ko-count >=1
  AND
 a write request triggers the timeout (ko-count * timeout)

DRBD's internal state gets confused. That in turn may
lead to very miss leading follow up failures. E.g.
"BUG: scheduling while atomic"

CC: stable@kernel.org # v3.17
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_req.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 90319b1..3b797cd 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1629,7 +1629,7 @@ void request_timer_fn(unsigned long data)
 		 time_after(now, req_peer->pre_send_jif + ent) &&
 		!time_in_range(now, connection->last_reconnect_jif, connection->last_reconnect_jif + ent)) {
 		drbd_warn(device, "Remote failed to finish a request within ko-count * timeout\n");
-		_drbd_set_state(_NS(device, conn, C_TIMEOUT), CS_VERBOSE | CS_HARD, NULL);
+		_conn_request_state(connection, NS(conn, C_TIMEOUT), CS_VERBOSE | CS_HARD);
 	}
 	if (dt && oldest_submit_jif != now &&
 		 time_after(now, oldest_submit_jif + dt) &&
-- 
1.9.1

[Drbd-dev] [PATCH 7/7] drbd: Remove an useless copy of kernel_setsockopt()

[Philipp Reisner]

Old backward-compat cruft

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h | 29 ++++-------------------------
 1 file changed, 4 insertions(+), 25 deletions(-)

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index d2a7589..b905e98 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1557,52 +1557,31 @@ extern void drbd_set_recv_tcq(struct drbd_device *device, int tcq_enabled);
 extern void _drbd_clear_done_ee(struct drbd_device *device, struct list_head *to_be_freed);
 extern int drbd_connected(struct drbd_peer_device *);
 
-/* Yes, there is kernel_setsockopt, but only since 2.6.18.
- * So we have our own copy of it here. */
-static inline int drbd_setsockopt(struct socket *sock, int level, int optname,
-				  char *optval, int optlen)
-{
-	mm_segment_t oldfs = get_fs();
-	char __user *uoptval;
-	int err;
-
-	uoptval = (char __user __force *)optval;
-
-	set_fs(KERNEL_DS);
-	if (level == SOL_SOCKET)
-		err = sock_setsockopt(sock, level, optname, uoptval, optlen);
-	else
-		err = sock->ops->setsockopt(sock, level, optname, uoptval,
-					    optlen);
-	set_fs(oldfs);
-	return err;
-}
-
 static inline void drbd_tcp_cork(struct socket *sock)
 {
 	int val = 1;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_CORK,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_CORK,
 			(char*)&val, sizeof(val));
 }
 
 static inline void drbd_tcp_uncork(struct socket *sock)
 {
 	int val = 0;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_CORK,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_CORK,
 			(char*)&val, sizeof(val));
 }
 
 static inline void drbd_tcp_nodelay(struct socket *sock)
 {
 	int val = 1;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_NODELAY,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
 			(char*)&val, sizeof(val));
 }
 
 static inline void drbd_tcp_quickack(struct socket *sock)
 {
 	int val = 2;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_QUICKACK,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_QUICKACK,
 			(char*)&val, sizeof(val));
 }
 
-- 
1.9.1

[PATCH 7/7] drbd: Remove an useless copy of kernel_setsockopt()

[Philipp Reisner]

Old backward-compat cruft

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
---
 drivers/block/drbd/drbd_int.h | 29 ++++-------------------------
 1 file changed, 4 insertions(+), 25 deletions(-)

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index d2a7589..b905e98 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1557,52 +1557,31 @@ extern void drbd_set_recv_tcq(struct drbd_device *device, int tcq_enabled);
 extern void _drbd_clear_done_ee(struct drbd_device *device, struct list_head *to_be_freed);
 extern int drbd_connected(struct drbd_peer_device *);
 
-/* Yes, there is kernel_setsockopt, but only since 2.6.18.
- * So we have our own copy of it here. */
-static inline int drbd_setsockopt(struct socket *sock, int level, int optname,
-				  char *optval, int optlen)
-{
-	mm_segment_t oldfs = get_fs();
-	char __user *uoptval;
-	int err;
-
-	uoptval = (char __user __force *)optval;
-
-	set_fs(KERNEL_DS);
-	if (level == SOL_SOCKET)
-		err = sock_setsockopt(sock, level, optname, uoptval, optlen);
-	else
-		err = sock->ops->setsockopt(sock, level, optname, uoptval,
-					    optlen);
-	set_fs(oldfs);
-	return err;
-}
-
 static inline void drbd_tcp_cork(struct socket *sock)
 {
 	int val = 1;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_CORK,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_CORK,
 			(char*)&val, sizeof(val));
 }
 
 static inline void drbd_tcp_uncork(struct socket *sock)
 {
 	int val = 0;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_CORK,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_CORK,
 			(char*)&val, sizeof(val));
 }
 
 static inline void drbd_tcp_nodelay(struct socket *sock)
 {
 	int val = 1;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_NODELAY,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
 			(char*)&val, sizeof(val));
 }
 
 static inline void drbd_tcp_quickack(struct socket *sock)
 {
 	int val = 2;
-	(void) drbd_setsockopt(sock, SOL_TCP, TCP_QUICKACK,
+	(void) kernel_setsockopt(sock, SOL_TCP, TCP_QUICKACK,
 			(char*)&val, sizeof(val));
 }
 
-- 
1.9.1

Re: [Drbd-dev] [PATCH 0/7] DRBD updates for the 3.19 merge window

[Jens Axboe]

On 2014-11-10 09:21, Philipp Reisner wrote:
> Hi Jens,
>
> please take these patches for you for-3.19/drivers branch.
> They where posted for review on 2014-10-29.
>
> Some cleanups and 3 fixes. Two of them marked for stable:
> 0005-drbd-merge_bvec_fn-properly-remap-bvm-bi_bdev.patch and
> 0006-drbd-Fix-state-change-in-case-of-connection-timeout.patch
> (marked for stable)

Applied, thanks.

-- 
Jens Axboe

Re: [PATCH 0/7] DRBD updates for the 3.19 merge window

[Jens Axboe]

On 2014-11-10 09:21, Philipp Reisner wrote:
> Hi Jens,
>
> please take these patches for you for-3.19/drivers branch.
> They where posted for review on 2014-10-29.
>
> Some cleanups and 3 fixes. Two of them marked for stable:
> 0005-drbd-merge_bvec_fn-properly-remap-bvm-bi_bdev.patch and
> 0006-drbd-Fix-state-change-in-case-of-connection-timeout.patch
> (marked for stable)

Applied, thanks.

-- 
Jens Axboe