[net-next 0/5][pull request] Intel Wired LAN Driver Updates 2015-10-03

[net-next 0/5][pull request] Intel Wired LAN Driver Updates 2015-10-03

[Jeff Kirsher]

This series contains updates to i40e and i40evf, some of which are to
resolve more Red Hat bugzilla issues.

Jiang Liu updates the i40e and i40evf drivers to use numa_mem_id()
instead of numa_node_id() to get the nearest node with memory which
better supports memoryless nodes.

Anjali fixes an issue from Dan Carpenter <dan.carpenter@oracle.com>,
to resolve a memory leak in X722 RSS configuration path, where we should
free the memory allocated before exiting.

Shannon modifies the drivers to ensure we have the spinlocks before we
clear the ARQ and ASQ management registers.  In addition, we widen the
locked portion insert a sanity check to ensure we are working with safe
register values.

Mitch fixes an issue where under certain circumstances, we can get an
extra VF_RESOURCES message from the PF driver at runtime.  When this
occurs, we need to parse it because our VSI may have changed and that
will affect the relationship with the PF driver.  But this parsing also
blows away our current MAC address, so resolve the issue by restoring
the current MAC address from the netdev struct after we parse the
resource message.

The following are changes since commit e96f78ab2703f3b0d512f6b469bc685d2ef20475:
  tcp/dccp: add SLAB_DESTROY_BY_RCU flag for request sockets
and are available in the git repository at:
  git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue master

Anjali Singhai (1):
  i40e: Fix a memory leak in X722 rss config path

Jiang Liu (2):
  i40e: Use numa_mem_id() to better support memoryless node
  i40evf: Use numa_mem_id() to better support memoryless node

Mitch Williams (1):
  i40evf: don't blow away MAC address

Shannon Nelson (1):
  i40e/i40evf: grab the AQ spinlocks before clearing registers

 drivers/net/ethernet/intel/i40e/i40e_adminq.c      | 45 +++++++++++-----------
 drivers/net/ethernet/intel/i40e/i40e_main.c        |  4 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.c        |  2 +-
 drivers/net/ethernet/intel/i40evf/i40e_adminq.c    | 45 +++++++++++-----------
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c      |  2 +-
 .../net/ethernet/intel/i40evf/i40evf_virtchnl.c    |  2 +
 6 files changed, 53 insertions(+), 47 deletions(-)

-- 
2.4.3

[net-next 1/5] i40e: Use numa_mem_id() to better support memoryless node

[Jeff Kirsher]

From: Jiang Liu <jiang.liu@linux.intel.com>

Function i40e_clean_rx_irq() tries to reuse memory pages allocated
from the nearest node. To better support memoryless node, use
numa_mem_id() instead of numa_node_id() to get the nearest node with
memory.

This change should only affect performance.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 0d692dd..85e61b0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -1443,7 +1443,7 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 rx_packet_len, rx_header_len, rx_sph, rx_hbo;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
-	const int current_node = numa_node_id();
+	const int current_node = numa_mem_id();
 	struct i40e_vsi *vsi = rx_ring->vsi;
 	u16 i = rx_ring->next_to_clean;
 	union i40e_rx_desc *rx_desc;
-- 
2.4.3

[net-next 2/5] i40evf: Use numa_mem_id() to better support memoryless node

[Jeff Kirsher]

From: Jiang Liu <jiang.liu@linux.intel.com>

Function i40e_clean_rx_irq() tries to reuse memory pages allocated
from the nearest node. To better support memoryless node, use
numa_mem_id() instead of numa_node_id() to get the nearest node with
memory.

This change should only affect performance.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
index aaee89f..0e1a4d6 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c
@@ -917,7 +917,7 @@ static int i40e_clean_rx_irq_ps(struct i40e_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	u16 rx_packet_len, rx_header_len, rx_sph, rx_hbo;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
-	const int current_node = numa_node_id();
+	const int current_node = numa_mem_id();
 	struct i40e_vsi *vsi = rx_ring->vsi;
 	u16 i = rx_ring->next_to_clean;
 	union i40e_rx_desc *rx_desc;
-- 
2.4.3

[net-next 3/5] i40e: Fix a memory leak in X722 rss config path

[Jeff Kirsher]

From: Anjali Singhai <anjali.singhai@intel.com>

In any case free the memory allocated before exiting.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 4345fc5..5646ee8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7625,7 +7625,7 @@ static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed)
 			 "Cannot set RSS key, err %s aq_err %s\n",
 			 i40e_stat_str(&pf->hw, ret),
 			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
-		return ret;
+		goto config_rss_aq_out;
 	}
 
 	if (vsi->type == I40E_VSI_MAIN)
@@ -7639,6 +7639,8 @@ static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed)
 			 i40e_stat_str(&pf->hw, ret),
 			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 
+config_rss_aq_out:
+	kfree(rss_lut);
 	return ret;
 }
 
-- 
2.4.3

[net-next 4/5] i40e/i40evf: grab the AQ spinlocks before clearing registers

[Jeff Kirsher]

From: Shannon Nelson <shannon.nelson@intel.com>

Make sure we have the spinlocks before we clear the ARQ and ASQ management
registers.  Also, widen the locked portion and make a sanity check earlier
in the send function to be sure we're working with safe register values.

Change-ID: I34b56044b33461ed780f3d2de8d62826cdf933f9
Signed-off-by: Shannon Nelson <shannon.nelson@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_adminq.c   | 45 +++++++++++++------------
 drivers/net/ethernet/intel/i40evf/i40e_adminq.c | 45 +++++++++++++------------
 2 files changed, 46 insertions(+), 44 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index e59ffb2..34a64e0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -482,8 +482,12 @@ static i40e_status i40e_shutdown_asq(struct i40e_hw *hw)
 {
 	i40e_status ret_code = 0;
 
-	if (hw->aq.asq.count == 0)
-		return I40E_ERR_NOT_READY;
+	mutex_lock(&hw->aq.asq_mutex);
+
+	if (hw->aq.asq.count == 0) {
+		ret_code = I40E_ERR_NOT_READY;
+		goto shutdown_asq_out;
+	}
 
 	/* Stop firmware AdminQ processing */
 	wr32(hw, hw->aq.asq.head, 0);
@@ -492,16 +496,13 @@ static i40e_status i40e_shutdown_asq(struct i40e_hw *hw)
 	wr32(hw, hw->aq.asq.bal, 0);
 	wr32(hw, hw->aq.asq.bah, 0);
 
-	/* make sure lock is available */
-	mutex_lock(&hw->aq.asq_mutex);
-
 	hw->aq.asq.count = 0; /* to indicate uninitialized queue */
 
 	/* free ring buffers */
 	i40e_free_asq_bufs(hw);
 
+shutdown_asq_out:
 	mutex_unlock(&hw->aq.asq_mutex);
-
 	return ret_code;
 }
 
@@ -515,8 +516,12 @@ static i40e_status i40e_shutdown_arq(struct i40e_hw *hw)
 {
 	i40e_status ret_code = 0;
 
-	if (hw->aq.arq.count == 0)
-		return I40E_ERR_NOT_READY;
+	mutex_lock(&hw->aq.arq_mutex);
+
+	if (hw->aq.arq.count == 0) {
+		ret_code = I40E_ERR_NOT_READY;
+		goto shutdown_arq_out;
+	}
 
 	/* Stop firmware AdminQ processing */
 	wr32(hw, hw->aq.arq.head, 0);
@@ -525,16 +530,13 @@ static i40e_status i40e_shutdown_arq(struct i40e_hw *hw)
 	wr32(hw, hw->aq.arq.bal, 0);
 	wr32(hw, hw->aq.arq.bah, 0);
 
-	/* make sure lock is available */
-	mutex_lock(&hw->aq.arq_mutex);
-
 	hw->aq.arq.count = 0; /* to indicate uninitialized queue */
 
 	/* free ring buffers */
 	i40e_free_arq_bufs(hw);
 
+shutdown_arq_out:
 	mutex_unlock(&hw->aq.arq_mutex);
-
 	return ret_code;
 }
 
@@ -745,19 +747,21 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw,
 	u16  retval = 0;
 	u32  val = 0;
 
-	val = rd32(hw, hw->aq.asq.head);
-	if (val >= hw->aq.num_asq_entries) {
+	mutex_lock(&hw->aq.asq_mutex);
+
+	if (hw->aq.asq.count == 0) {
 		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
-			   "AQTX: head overrun at %d\n", val);
+			   "AQTX: Admin queue not initialized.\n");
 		status = I40E_ERR_QUEUE_EMPTY;
-		goto asq_send_command_exit;
+		goto asq_send_command_error;
 	}
 
-	if (hw->aq.asq.count == 0) {
+	val = rd32(hw, hw->aq.asq.head);
+	if (val >= hw->aq.num_asq_entries) {
 		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
-			   "AQTX: Admin queue not initialized.\n");
+			   "AQTX: head overrun at %d\n", val);
 		status = I40E_ERR_QUEUE_EMPTY;
-		goto asq_send_command_exit;
+		goto asq_send_command_error;
 	}
 
 	details = I40E_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use);
@@ -782,8 +786,6 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw,
 	desc->flags &= ~cpu_to_le16(details->flags_dis);
 	desc->flags |= cpu_to_le16(details->flags_ena);
 
-	mutex_lock(&hw->aq.asq_mutex);
-
 	if (buff_size > hw->aq.asq_buf_size) {
 		i40e_debug(hw,
 			   I40E_DEBUG_AQ_MESSAGE,
@@ -907,7 +909,6 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw,
 
 asq_send_command_error:
 	mutex_unlock(&hw->aq.asq_mutex);
-asq_send_command_exit:
 	return status;
 }
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
index 5026773..c7f59e0 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
@@ -469,8 +469,12 @@ static i40e_status i40e_shutdown_asq(struct i40e_hw *hw)
 {
 	i40e_status ret_code = 0;
 
-	if (hw->aq.asq.count == 0)
-		return I40E_ERR_NOT_READY;
+	mutex_lock(&hw->aq.asq_mutex);
+
+	if (hw->aq.asq.count == 0) {
+		ret_code = I40E_ERR_NOT_READY;
+		goto shutdown_asq_out;
+	}
 
 	/* Stop firmware AdminQ processing */
 	wr32(hw, hw->aq.asq.head, 0);
@@ -479,16 +483,13 @@ static i40e_status i40e_shutdown_asq(struct i40e_hw *hw)
 	wr32(hw, hw->aq.asq.bal, 0);
 	wr32(hw, hw->aq.asq.bah, 0);
 
-	/* make sure lock is available */
-	mutex_lock(&hw->aq.asq_mutex);
-
 	hw->aq.asq.count = 0; /* to indicate uninitialized queue */
 
 	/* free ring buffers */
 	i40e_free_asq_bufs(hw);
 
+shutdown_asq_out:
 	mutex_unlock(&hw->aq.asq_mutex);
-
 	return ret_code;
 }
 
@@ -502,8 +503,12 @@ static i40e_status i40e_shutdown_arq(struct i40e_hw *hw)
 {
 	i40e_status ret_code = 0;
 
-	if (hw->aq.arq.count == 0)
-		return I40E_ERR_NOT_READY;
+	mutex_lock(&hw->aq.arq_mutex);
+
+	if (hw->aq.arq.count == 0) {
+		ret_code = I40E_ERR_NOT_READY;
+		goto shutdown_arq_out;
+	}
 
 	/* Stop firmware AdminQ processing */
 	wr32(hw, hw->aq.arq.head, 0);
@@ -512,16 +517,13 @@ static i40e_status i40e_shutdown_arq(struct i40e_hw *hw)
 	wr32(hw, hw->aq.arq.bal, 0);
 	wr32(hw, hw->aq.arq.bah, 0);
 
-	/* make sure lock is available */
-	mutex_lock(&hw->aq.arq_mutex);
-
 	hw->aq.arq.count = 0; /* to indicate uninitialized queue */
 
 	/* free ring buffers */
 	i40e_free_arq_bufs(hw);
 
+shutdown_arq_out:
 	mutex_unlock(&hw->aq.arq_mutex);
-
 	return ret_code;
 }
 
@@ -685,19 +687,21 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 	u16  retval = 0;
 	u32  val = 0;
 
-	val = rd32(hw, hw->aq.asq.head);
-	if (val >= hw->aq.num_asq_entries) {
+	mutex_lock(&hw->aq.asq_mutex);
+
+	if (hw->aq.asq.count == 0) {
 		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
-			   "AQTX: head overrun at %d\n", val);
+			   "AQTX: Admin queue not initialized.\n");
 		status = I40E_ERR_QUEUE_EMPTY;
-		goto asq_send_command_exit;
+		goto asq_send_command_error;
 	}
 
-	if (hw->aq.asq.count == 0) {
+	val = rd32(hw, hw->aq.asq.head);
+	if (val >= hw->aq.num_asq_entries) {
 		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
-			   "AQTX: Admin queue not initialized.\n");
+			   "AQTX: head overrun at %d\n", val);
 		status = I40E_ERR_QUEUE_EMPTY;
-		goto asq_send_command_exit;
+		goto asq_send_command_error;
 	}
 
 	details = I40E_ADMINQ_DETAILS(hw->aq.asq, hw->aq.asq.next_to_use);
@@ -722,8 +726,6 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 	desc->flags &= ~cpu_to_le16(details->flags_dis);
 	desc->flags |= cpu_to_le16(details->flags_ena);
 
-	mutex_lock(&hw->aq.asq_mutex);
-
 	if (buff_size > hw->aq.asq_buf_size) {
 		i40e_debug(hw,
 			   I40E_DEBUG_AQ_MESSAGE,
@@ -848,7 +850,6 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 
 asq_send_command_error:
 	mutex_unlock(&hw->aq.asq_mutex);
-asq_send_command_exit:
 	return status;
 }
 
-- 
2.4.3

[net-next 5/5] i40evf: don't blow away MAC address

[Jeff Kirsher]

From: Mitch Williams <mitch.a.williams@intel.com>

Under certain circumstances, we can get an extra VF_RESOURCES message
from the PF driver at runtime. When this happens, we need to parse it
because our VSI may have changed out from underneath us, and that will
affect our relationship with the PF driver.

However, parsing the resources message also blows away our current MAC
address in the hardware struct, usually with all zeros. When this
happens, the next time the interface is opened, it will have no MAC
address and will a) not work and b) complain.

Fix this issue by restoring the current MAC address from the netdev
struct after we parse the resource message.

Change-ID: I6cd1b624fc20432f81dc901166c8de195b8e0e65
Signed-off-by: Mitch Williams <mitch.a.williams@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
index d4eb1a5..fbf2a1c 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c
@@ -756,6 +756,8 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter,
 			  sizeof(struct i40e_virtchnl_vsi_resource);
 		memcpy(adapter->vf_res, msg, min(msglen, len));
 		i40e_vf_parse_hw_config(&adapter->hw, adapter->vf_res);
+		/* restore current mac address */
+		ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr);
 		i40evf_process_config(adapter);
 		}
 		break;
-- 
2.4.3

Re: [net-next 0/5][pull request] Intel Wired LAN Driver Updates 2015-10-03

[David Miller]

From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Sat,  3 Oct 2015 19:54:38 -0700

> This series contains updates to i40e and i40evf, some of which are to
> resolve more Red Hat bugzilla issues.
> 
> Jiang Liu updates the i40e and i40evf drivers to use numa_mem_id()
> instead of numa_node_id() to get the nearest node with memory which
> better supports memoryless nodes.
> 
> Anjali fixes an issue from Dan Carpenter <dan.carpenter@oracle.com>,
> to resolve a memory leak in X722 RSS configuration path, where we should
> free the memory allocated before exiting.
> 
> Shannon modifies the drivers to ensure we have the spinlocks before we
> clear the ARQ and ASQ management registers.  In addition, we widen the
> locked portion insert a sanity check to ensure we are working with safe
> register values.
> 
> Mitch fixes an issue where under certain circumstances, we can get an
> extra VF_RESOURCES message from the PF driver at runtime.  When this
> occurs, we need to parse it because our VSI may have changed and that
> will affect the relationship with the PF driver.  But this parsing also
> blows away our current MAC address, so resolve the issue by restoring
> the current MAC address from the netdev struct after we parse the
> resource message.

Series applied, thanks Jeff.