Netdev List
 help / color / mirror / Atom feed
* [PATCH 06/11] vxge: add receive hardware timestamping
From: Jon Mason @ 2010-11-04 22:51 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Sivakumar Subramani, Sreenivasa Honnur, Ram Vepa
In-Reply-To: <1288911122-28669-1-git-send-email-jon.mason@exar.com>

Add support for enable/disabling hardware timestamping on receive
packets via ioctl call.  When enabled, the hardware timestamp replaces
the FCS in the payload.

Signed-off-by: Jon Mason <jon.mason@exar.com>
Signed-off-by: Ram Vepa <ram.vepa@exar.com>
---
 drivers/net/vxge/vxge-main.c |  133 ++++++++++++++++++++++++++++++++++++++++--
 drivers/net/vxge/vxge-main.h |    8 ++-
 2 files changed, 132 insertions(+), 9 deletions(-)

diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c
index 2c73ef7..13bf6ef 100644
--- a/drivers/net/vxge/vxge-main.c
+++ b/drivers/net/vxge/vxge-main.c
@@ -51,6 +51,7 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/firmware.h>
+#include <linux/net_tstamp.h>
 #include "vxge-main.h"
 #include "vxge-reg.h"
 
@@ -360,7 +361,7 @@ vxge_rx_1b_compl(struct __vxge_hw_ring *ringh, void *dtr,
 		 u8 t_code, void *userdata)
 {
 	struct vxge_ring *ring = (struct vxge_ring *)userdata;
-	struct  net_device *dev = ring->ndev;
+	struct net_device *dev = ring->ndev;
 	unsigned int dma_sizes;
 	void *first_dtr = NULL;
 	int dtr_cnt = 0;
@@ -504,6 +505,16 @@ vxge_rx_1b_compl(struct __vxge_hw_ring *ringh, void *dtr,
 		else
 			skb_checksum_none_assert(skb);
 
+
+		if (ring->rx_hwts) {
+			struct skb_shared_hwtstamps *skb_hwts;
+			u32 ns = *(u32 *)(skb->head + pkt_length);
+
+			skb_hwts = skb_hwtstamps(skb);
+			skb_hwts->hwtstamp = ns_to_ktime(ns);
+			skb_hwts->syststamp.tv64 = 0;
+		}
+
 		/* rth_hash_type and rth_it_hit are non-zero regardless of
 		 * whether rss is enabled.  Only the rth_value is zero/non-zero
 		 * if rss is disabled/enabled, so key off of that.
@@ -2026,6 +2037,7 @@ int vxge_open_vpaths(struct vxgedev *vdev)
 				vdev->config.fifo_indicate_max_pkts;
 			vpath->ring.rx_vector_no = 0;
 			vpath->ring.rx_csum = vdev->rx_csum;
+			vpath->ring.rx_hwts = vdev->rx_hwts;
 			vpath->is_open = 1;
 			vdev->vp_handles[i] = vpath->handle;
 			vpath->ring.gro_enable = vdev->config.gro_enable;
@@ -2960,6 +2972,101 @@ vxge_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *net_stats)
 	return net_stats;
 }
 
+static enum vxge_hw_status vxge_timestamp_config(struct vxgedev *vdev,
+						 int enable)
+{
+	enum vxge_hw_status status;
+	u64 val64;
+
+	/* Timestamp is passed to the driver via the FCS, therefore we
+	 * must disable the FCS stripping by the adapter.  Since this is
+	 * required for the driver to load (due to a hardware bug),
+	 * there is no need to do anything special here.
+	 */
+	if (enable)
+		val64 = VXGE_HW_XMAC_TIMESTAMP_EN |
+			VXGE_HW_XMAC_TIMESTAMP_USE_LINK_ID(0) |
+			VXGE_HW_XMAC_TIMESTAMP_INTERVAL(0);
+	else
+		val64 = 0;
+
+	status = vxge_hw_mgmt_reg_write(vdev->devh,
+					vxge_hw_mgmt_reg_type_mrpcim,
+					0,
+					offsetof(struct vxge_hw_mrpcim_reg,
+						 xmac_timestamp),
+					val64);
+	vxge_hw_device_flush_io(vdev->devh);
+	return status;
+}
+
+static int vxge_hwtstamp_ioctl(struct vxgedev *vdev, void __user *data)
+{
+	struct hwtstamp_config config;
+	enum vxge_hw_status status;
+	int i;
+
+	if (copy_from_user(&config, data, sizeof(config)))
+		return -EFAULT;
+
+	/* reserved for future extensions */
+	if (config.flags)
+		return -EINVAL;
+
+	/* Transmit HW Timestamp not supported */
+	switch (config.tx_type) {
+	case HWTSTAMP_TX_OFF:
+		break;
+	case HWTSTAMP_TX_ON:
+	default:
+		return -ERANGE;
+	}
+
+	switch (config.rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		status = vxge_timestamp_config(vdev, 0);
+		if (status != VXGE_HW_OK)
+			return -EFAULT;
+
+		vdev->rx_hwts = 0;
+		config.rx_filter = HWTSTAMP_FILTER_NONE;
+		break;
+
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+		status = vxge_timestamp_config(vdev, 1);
+		if (status != VXGE_HW_OK)
+			return -EFAULT;
+
+		vdev->rx_hwts = 1;
+		config.rx_filter = HWTSTAMP_FILTER_ALL;
+		break;
+
+	default:
+		 return -ERANGE;
+	}
+
+	for (i = 0; i < vdev->no_of_vpath; i++)
+		vdev->vpaths[i].ring.rx_hwts = vdev->rx_hwts;
+
+	if (copy_to_user(data, &config, sizeof(config)))
+		return -EFAULT;
+
+	return 0;
+}
+
 /**
  * vxge_ioctl
  * @dev: Device pointer.
@@ -2972,7 +3079,20 @@ vxge_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *net_stats)
  */
 static int vxge_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
-	return -EOPNOTSUPP;
+	struct vxgedev *vdev = netdev_priv(dev);
+	int ret;
+
+	switch (cmd) {
+	case SIOCSHWTSTAMP:
+		ret = vxge_hwtstamp_ioctl(vdev, rq->ifr_data);
+		if (ret)
+			return ret;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
 }
 
 /**
@@ -3169,6 +3289,7 @@ int __devinit vxge_device_register(struct __vxge_hw_device *hldev,
 	vdev->pdev = hldev->pdev;
 	memcpy(&vdev->config, config, sizeof(struct vxge_config));
 	vdev->rx_csum = 1;	/* Enable Rx CSUM by default. */
+	vdev->rx_hwts = 0;
 
 	SET_NETDEV_DEV(ndev, &vdev->pdev->dev);
 
@@ -4310,10 +4431,10 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre)
 	}
 
 	/* if FCS stripping is not disabled in MAC fail driver load */
-	if (vxge_hw_vpath_strip_fcs_check(hldev, vpath_mask) != VXGE_HW_OK) {
-		vxge_debug_init(VXGE_ERR,
-			"%s: FCS stripping is not disabled in MAC"
-			" failing driver load", VXGE_DRIVER_NAME);
+	status = vxge_hw_vpath_strip_fcs_check(hldev, vpath_mask);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR, "%s: FCS stripping is enabled in MAC"
+				" failing driver load", VXGE_DRIVER_NAME);
 		ret = -EINVAL;
 		goto _exit4;
 	}
diff --git a/drivers/net/vxge/vxge-main.h b/drivers/net/vxge/vxge-main.h
index 1e47319..947893e 100644
--- a/drivers/net/vxge/vxge-main.h
+++ b/drivers/net/vxge/vxge-main.h
@@ -248,8 +248,9 @@ struct vxge_ring {
 	 */
 	int driver_id;
 
-	 /* copy of the flag indicating whether rx_csum is to be used */
-	u32 rx_csum;
+	/* copy of the flag indicating whether rx_csum is to be used */
+	u32 rx_csum:1,
+	    rx_hwts:1;
 
 	int pkts_processed;
 	int budget;
@@ -327,7 +328,8 @@ struct vxgedev {
 	u16		all_multi_flg;
 
 	 /* A flag indicating whether rx_csum is to be used or not. */
-	u32	rx_csum;
+	u32	rx_csum:1,
+		rx_hwts:1;
 
 	struct vxge_msix_entry *vxge_entries;
 	struct msix_entry *entries;
-- 
1.7.0.4


^ permalink raw reply related

* [PATCH 05/11] vxge: add support for ethtool firmware flashing
From: Jon Mason @ 2010-11-04 22:51 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Sivakumar Subramani, Sreenivasa Honnur, Ram Vepa
In-Reply-To: <1288911122-28669-1-git-send-email-jon.mason@exar.com>

Add the ability in the vxge driver to flash firmware via ethtool.

Updated to include comments from Ben Hutchings.

Signed-off-by: Jon Mason <jon.mason@exar.com>
Signed-off-by: Ram Vepa <ram.vepa@exar.com>
---
 drivers/net/vxge/vxge-config.c  |  182 +++++++++++++++++++++++++++++++++++++
 drivers/net/vxge/vxge-config.h  |   71 ++++++++++++++-
 drivers/net/vxge/vxge-ethtool.c |   20 ++++
 drivers/net/vxge/vxge-main.c    |  190 +++++++++++++++++++++++++++++++++++----
 drivers/net/vxge/vxge-main.h    |    4 +
 drivers/net/vxge/vxge-reg.h     |   29 ++++++-
 drivers/net/vxge/vxge-version.h |   27 ++++++
 7 files changed, 502 insertions(+), 21 deletions(-)

diff --git a/drivers/net/vxge/vxge-config.c b/drivers/net/vxge/vxge-config.c
index e84d787..bc7cc16 100644
--- a/drivers/net/vxge/vxge-config.c
+++ b/drivers/net/vxge/vxge-config.c
@@ -169,6 +169,188 @@ out:
 	return status;
 }
 
+enum vxge_hw_status
+vxge_hw_upgrade_read_version(struct __vxge_hw_device *hldev, u32 *major,
+			     u32 *minor, u32 *build)
+{
+	u64 data0 = 0, data1 = 0, steer_ctrl = 0;
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status;
+
+	vpath = &hldev->virtual_paths[hldev->first_vp_id];
+
+	status = vxge_hw_vpath_fw_api(vpath,
+				      VXGE_HW_FW_UPGRADE_ACTION,
+				      VXGE_HW_FW_UPGRADE_MEMO,
+				      VXGE_HW_FW_UPGRADE_OFFSET_READ,
+				      &data0, &data1, &steer_ctrl);
+	if (status != VXGE_HW_OK)
+		return status;
+
+	*major = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MAJOR(data0);
+	*minor = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MINOR(data0);
+	*build = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_BUILD(data0);
+
+	return status;
+}
+
+enum vxge_hw_status vxge_hw_flash_fw(struct __vxge_hw_device *hldev)
+{
+	u64 data0 = 0, data1 = 0, steer_ctrl = 0;
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status;
+	u32 ret;
+
+	vpath = &hldev->virtual_paths[hldev->first_vp_id];
+
+	status = vxge_hw_vpath_fw_api(vpath,
+				      VXGE_HW_FW_UPGRADE_ACTION,
+				      VXGE_HW_FW_UPGRADE_MEMO,
+				      VXGE_HW_FW_UPGRADE_OFFSET_COMMIT,
+				      &data0, &data1, &steer_ctrl);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR, "%s: FW upgrade failed", __func__);
+		goto exit;
+	}
+
+	ret = VXGE_HW_RTS_ACCESS_STEER_CTRL_GET_ACTION(steer_ctrl) & 0x7F;
+	if (ret != 1) {
+		vxge_debug_init(VXGE_ERR, "%s: FW commit failed with error %d",
+				__func__, ret);
+		status = VXGE_HW_FAIL;
+	}
+
+exit:
+	return status;
+}
+
+enum vxge_hw_status
+vxge_update_fw_image(struct __vxge_hw_device *hldev, const u8 *fwdata, int size)
+{
+	u64 data0 = 0, data1 = 0, steer_ctrl = 0;
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status;
+	int ret_code, sec_code;
+
+	vpath = &hldev->virtual_paths[hldev->first_vp_id];
+
+	/* send upgrade start command */
+	status = vxge_hw_vpath_fw_api(vpath,
+				      VXGE_HW_FW_UPGRADE_ACTION,
+				      VXGE_HW_FW_UPGRADE_MEMO,
+				      VXGE_HW_FW_UPGRADE_OFFSET_START,
+				      &data0, &data1, &steer_ctrl);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR, " %s: Upgrade start cmd failed",
+				__func__);
+		return status;
+	}
+
+	/* Transfer fw image to adapter 16 bytes at a time */
+	for (; size > 0; size -= VXGE_HW_FW_UPGRADE_BLK_SIZE) {
+		steer_ctrl = 0;
+
+		/* The next 128bits of fwdata to be loaded onto the adapter */
+		data0 = *((u64 *)fwdata);
+		data1 = *((u64 *)fwdata + 1);
+
+		status = vxge_hw_vpath_fw_api(vpath,
+					      VXGE_HW_FW_UPGRADE_ACTION,
+					      VXGE_HW_FW_UPGRADE_MEMO,
+					      VXGE_HW_FW_UPGRADE_OFFSET_SEND,
+					      &data0, &data1, &steer_ctrl);
+		if (status != VXGE_HW_OK) {
+			vxge_debug_init(VXGE_ERR, "%s: Upgrade send failed",
+					__func__);
+			goto out;
+		}
+
+		ret_code = VXGE_HW_UPGRADE_GET_RET_ERR_CODE(data0);
+		switch (ret_code) {
+		case VXGE_HW_FW_UPGRADE_OK:
+			/* All OK, send next 16 bytes. */
+			break;
+		case VXGE_FW_UPGRADE_BYTES2SKIP:
+			/* skip bytes in the stream */
+			fwdata += (data0 >> 8) & 0xFFFFFFFF;
+			break;
+		case VXGE_HW_FW_UPGRADE_DONE:
+			goto out;
+		case VXGE_HW_FW_UPGRADE_ERR:
+			sec_code = VXGE_HW_UPGRADE_GET_SEC_ERR_CODE(data0);
+			switch (sec_code) {
+			case VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_1:
+			case VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_7:
+				printk(KERN_ERR
+				       "corrupted data from .ncf file\n");
+				break;
+			case VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_3:
+			case VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_4:
+			case VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_5:
+			case VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_6:
+			case VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_8:
+				printk(KERN_ERR "invalid .ncf file\n");
+				break;
+			case VXGE_HW_FW_UPGRADE_ERR_BUFFER_OVERFLOW:
+				printk(KERN_ERR "buffer overflow\n");
+				break;
+			case VXGE_HW_FW_UPGRADE_ERR_FAILED_TO_FLASH:
+				printk(KERN_ERR "failed to flash the image\n");
+				break;
+			case VXGE_HW_FW_UPGRADE_ERR_GENERIC_ERROR_UNKNOWN:
+				printk(KERN_ERR
+				       "generic error. Unknown error type\n");
+				break;
+			default:
+				printk(KERN_ERR "Unknown error of type %d\n",
+				       sec_code);
+				break;
+			}
+			status = VXGE_HW_FAIL;
+			goto out;
+		default:
+			printk(KERN_ERR "Unknown FW error: %d\n", ret_code);
+			status = VXGE_HW_FAIL;
+			goto out;
+		}
+		/* point to next 16 bytes */
+		fwdata += VXGE_HW_FW_UPGRADE_BLK_SIZE;
+	}
+out:
+	return status;
+}
+
+enum vxge_hw_status
+vxge_hw_vpath_eprom_img_ver_get(struct __vxge_hw_device *hldev,
+				struct eprom_image *img)
+{
+	u64 data0 = 0, data1 = 0, steer_ctrl = 0;
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status;
+	int i;
+
+	vpath = &hldev->virtual_paths[hldev->first_vp_id];
+
+	for (i = 0; i < VXGE_HW_MAX_ROM_IMAGES; i++) {
+		data0 = VXGE_HW_RTS_ACCESS_STEER_ROM_IMAGE_INDEX(i);
+		data1 = steer_ctrl = 0;
+
+		status = vxge_hw_vpath_fw_api(vpath,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO,
+			VXGE_HW_FW_API_GET_EPROM_REV,
+			0, &data0, &data1, &steer_ctrl);
+		if (status != VXGE_HW_OK)
+			break;
+
+		img[i].is_valid = VXGE_HW_GET_EPROM_IMAGE_VALID(data0);
+		img[i].index = VXGE_HW_GET_EPROM_IMAGE_INDEX(data0);
+		img[i].type = VXGE_HW_GET_EPROM_IMAGE_TYPE(data0);
+		img[i].version = VXGE_HW_GET_EPROM_IMAGE_REV(data0);
+	}
+
+	return status;
+}
+
 /*
  * __vxge_hw_channel_allocate - Allocate memory for channel
  * This function allocates required memory for the channel and various arrays
diff --git a/drivers/net/vxge/vxge-config.h b/drivers/net/vxge/vxge-config.h
index 2337665..3859d59 100644
--- a/drivers/net/vxge/vxge-config.h
+++ b/drivers/net/vxge/vxge-config.h
@@ -29,6 +29,15 @@
 #define VXGE_HW_MAX_MTU				9600
 #define VXGE_HW_DEFAULT_MTU			1500
 
+#define VXGE_HW_MAX_ROM_IMAGES			8
+
+struct eprom_image {
+	u8 is_valid:1;
+	u8 index;
+	u8 type;
+	u16 version;
+};
+
 #ifdef VXGE_DEBUG_ASSERT
 /**
  * vxge_assert
@@ -148,6 +157,47 @@ enum vxge_hw_device_link_state {
 };
 
 /**
+ * enum enum vxge_hw_fw_upgrade_code - FW upgrade return codes.
+ * @VXGE_HW_FW_UPGRADE_OK: All OK send next 16 bytes
+ * @VXGE_HW_FW_UPGRADE_DONE:  upload completed
+ * @VXGE_HW_FW_UPGRADE_ERR:  upload error
+ * @VXGE_FW_UPGRADE_BYTES2SKIP:  skip bytes in the stream
+ *
+ */
+enum vxge_hw_fw_upgrade_code {
+	VXGE_HW_FW_UPGRADE_OK		= 0,
+	VXGE_HW_FW_UPGRADE_DONE		= 1,
+	VXGE_HW_FW_UPGRADE_ERR		= 2,
+	VXGE_FW_UPGRADE_BYTES2SKIP	= 3
+};
+
+/**
+ * enum enum vxge_hw_fw_upgrade_err_code - FW upgrade error codes.
+ * @VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_1: corrupt data
+ * @VXGE_HW_FW_UPGRADE_ERR_BUFFER_OVERFLOW: buffer overflow
+ * @VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_3: invalid .ncf file
+ * @VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_4: invalid .ncf file
+ * @VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_5: invalid .ncf file
+ * @VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_6: invalid .ncf file
+ * @VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_7: corrupt data
+ * @VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_8: invalid .ncf file
+ * @VXGE_HW_FW_UPGRADE_ERR_GENERIC_ERROR_UNKNOWN: generic error unknown type
+ * @VXGE_HW_FW_UPGRADE_ERR_FAILED_TO_FLASH: failed to flash image check failed
+ */
+enum vxge_hw_fw_upgrade_err_code {
+	VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_1		= 1,
+	VXGE_HW_FW_UPGRADE_ERR_BUFFER_OVERFLOW		= 2,
+	VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_3		= 3,
+	VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_4		= 4,
+	VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_5		= 5,
+	VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_6		= 6,
+	VXGE_HW_FW_UPGRADE_ERR_CORRUPT_DATA_7		= 7,
+	VXGE_HW_FW_UPGRADE_ERR_INV_NCF_FILE_8		= 8,
+	VXGE_HW_FW_UPGRADE_ERR_GENERIC_ERROR_UNKNOWN	= 9,
+	VXGE_HW_FW_UPGRADE_ERR_FAILED_TO_FLASH		= 10
+};
+
+/**
  * struct vxge_hw_device_date - Date Format
  * @day: Day
  * @month: Month
@@ -454,7 +504,6 @@ struct vxge_hw_device_config {
  * See also: vxge_hw_driver_initialize().
  */
 struct vxge_hw_uld_cbs {
-
 	void (*link_up)(struct __vxge_hw_device *devh);
 	void (*link_down)(struct __vxge_hw_device *devh);
 	void (*crit_err)(struct __vxge_hw_device *devh,
@@ -721,6 +770,7 @@ struct __vxge_hw_device {
 	u32				debug_level;
 	u32				level_err;
 	u32				level_trace;
+	u16 eprom_versions[VXGE_HW_MAX_ROM_IMAGES];
 };
 
 #define VXGE_HW_INFO_LEN	64
@@ -2227,7 +2277,22 @@ __vxge_hw_device_is_privilaged(u32 host_type, u32 func_id);
 #define VXGE_HW_MIN_SUCCESSIVE_IDLE_COUNT 5
 #define VXGE_HW_MAX_POLLING_COUNT 100
 
-int vxge_hw_vpath_wait_receive_idle(struct __vxge_hw_device *hldev, u32 vp_id);
+void
+vxge_hw_device_wait_receive_idle(struct __vxge_hw_device *hldev);
+
+enum vxge_hw_status
+vxge_hw_upgrade_read_version(struct __vxge_hw_device *hldev, u32 *major,
+			     u32 *minor, u32 *build);
+
+enum vxge_hw_status vxge_hw_flash_fw(struct __vxge_hw_device *hldev);
 
-void  vxge_hw_device_wait_receive_idle(struct __vxge_hw_device *hldev);
+enum vxge_hw_status
+vxge_update_fw_image(struct __vxge_hw_device *hldev, const u8 *filebuf,
+		     int size);
+
+enum vxge_hw_status
+vxge_hw_vpath_eprom_img_ver_get(struct __vxge_hw_device *hldev,
+				struct eprom_image *eprom_image_data);
+
+int vxge_hw_vpath_wait_receive_idle(struct __vxge_hw_device *hldev, u32 vp_id);
 #endif
diff --git a/drivers/net/vxge/vxge-ethtool.c b/drivers/net/vxge/vxge-ethtool.c
index 6194fd9..76b126a 100644
--- a/drivers/net/vxge/vxge-ethtool.c
+++ b/drivers/net/vxge/vxge-ethtool.c
@@ -1153,6 +1153,25 @@ static int vxge_set_flags(struct net_device *dev, u32 data)
 	return 0;
 }
 
+static int vxge_fw_flash(struct net_device *dev, struct ethtool_flash *parms)
+{
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+
+	if (vdev->max_vpath_supported != VXGE_HW_MAX_VIRTUAL_PATHS) {
+		printk(KERN_INFO "Single Function Mode is required to flash the"
+		       " firmware\n");
+		return -EINVAL;
+	}
+
+	if (netif_running(dev)) {
+		printk(KERN_INFO "Interface %s must be down to flash the "
+		       "firmware\n", dev->name);
+		return -EBUSY;
+	}
+
+	return vxge_fw_upgrade(vdev, parms->data, 1);
+}
+
 static const struct ethtool_ops vxge_ethtool_ops = {
 	.get_settings		= vxge_ethtool_gset,
 	.set_settings		= vxge_ethtool_sset,
@@ -1175,6 +1194,7 @@ static const struct ethtool_ops vxge_ethtool_ops = {
 	.get_sset_count		= vxge_ethtool_get_sset_count,
 	.get_ethtool_stats	= vxge_get_ethtool_stats,
 	.set_flags		= vxge_set_flags,
+	.flash_device		= vxge_fw_flash,
 };
 
 void initialize_ethtool_ops(struct net_device *ndev)
diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c
index d977a63..2c73ef7 100644
--- a/drivers/net/vxge/vxge-main.c
+++ b/drivers/net/vxge/vxge-main.c
@@ -50,6 +50,7 @@
 #include <net/ip.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
+#include <linux/firmware.h>
 #include "vxge-main.h"
 #include "vxge-reg.h"
 
@@ -3237,6 +3238,7 @@ int __devinit vxge_device_register(struct __vxge_hw_device *hldev,
 		"%s: Ethernet device registered",
 		ndev->name);
 
+	hldev->ndev = ndev;
 	*vdev_out = vdev;
 
 	/* Resetting the Device stats */
@@ -3924,6 +3926,142 @@ static inline u32 vxge_get_num_vfs(u64 function_mode)
 	return num_functions;
 }
 
+int vxge_fw_upgrade(struct vxgedev *vdev, char *fw_name, int override)
+{
+	struct __vxge_hw_device *hldev = vdev->devh;
+	u32 maj, min, bld, cmaj, cmin, cbld;
+	enum vxge_hw_status status;
+	const struct firmware *fw;
+	int ret;
+
+	ret = request_firmware(&fw, fw_name, &vdev->pdev->dev);
+	if (ret) {
+		vxge_debug_init(VXGE_ERR, "%s: Firmware file '%s' not found",
+				VXGE_DRIVER_NAME, fw_name);
+		goto out;
+	}
+
+	/* Load the new firmware onto the adapter */
+	status = vxge_update_fw_image(hldev, fw->data, fw->size);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+				"%s: FW image download to adapter failed '%s'.",
+				VXGE_DRIVER_NAME, fw_name);
+		ret = -EIO;
+		goto out;
+	}
+
+	/* Read the version of the new firmware */
+	status = vxge_hw_upgrade_read_version(hldev, &maj, &min, &bld);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+				"%s: Upgrade read version failed '%s'.",
+				VXGE_DRIVER_NAME, fw_name);
+		ret = -EIO;
+		goto out;
+	}
+
+	cmaj = vdev->config.device_hw_info.fw_version.major;
+	cmin = vdev->config.device_hw_info.fw_version.minor;
+	cbld = vdev->config.device_hw_info.fw_version.build;
+	/* It's possible the version in /lib/firmware is not the latest version.
+	 * If so, we could get into a loop of trying to upgrade to the latest
+	 * and flashing the older version.
+	 */
+	if (VXGE_FW_VER(maj, min, bld) == VXGE_FW_VER(cmaj, cmin, cbld) &&
+	    !override) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	printk(KERN_NOTICE "Upgrade to firmware version %d.%d.%d commencing\n",
+	       maj, min, bld);
+
+	/* Flash the adapter with the new firmware */
+	status = vxge_hw_flash_fw(hldev);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR, "%s: Upgrade commit failed '%s'.",
+				VXGE_DRIVER_NAME, fw_name);
+		ret = -EIO;
+		goto out;
+	}
+
+	printk(KERN_NOTICE "Upgrade of firmware successful!  Adapter must be "
+	       "hard reset before using, thus requiring a system reboot or a "
+	       "hotplug event.\n");
+
+out:
+	return ret;
+}
+
+static int vxge_probe_fw_update(struct vxgedev *vdev)
+{
+	u32 maj, min, bld;
+	int ret, gpxe = 0;
+	char *fw_name;
+
+	maj = vdev->config.device_hw_info.fw_version.major;
+	min = vdev->config.device_hw_info.fw_version.minor;
+	bld = vdev->config.device_hw_info.fw_version.build;
+
+	if (VXGE_FW_VER(maj, min, bld) == VXGE_CERT_FW_VER)
+		return 0;
+
+	/* Ignore the build number when determining if the current firmware is
+	 * "too new" to load the driver
+	 */
+	if (VXGE_FW_VER(maj, min, 0) > VXGE_CERT_FW_VER) {
+		vxge_debug_init(VXGE_ERR, "%s: Firmware newer than last known "
+				"version, unable to load driver\n",
+				VXGE_DRIVER_NAME);
+		return -EINVAL;
+	}
+
+	/* Firmware 1.4.4 and older cannot be upgraded, and is too ancient to
+	 * work with this driver.
+	 */
+	if (VXGE_FW_VER(maj, min, bld) <= VXGE_FW_DEAD_VER) {
+		vxge_debug_init(VXGE_ERR, "%s: Firmware %d.%d.%d cannot be "
+				"upgraded\n", VXGE_DRIVER_NAME, maj, min, bld);
+		return -EINVAL;
+	}
+
+	/* If file not specified, determine gPXE or not */
+	if (VXGE_FW_VER(maj, min, bld) >= VXGE_EPROM_FW_VER) {
+		int i;
+		for (i = 0; i < VXGE_HW_MAX_ROM_IMAGES; i++)
+			if (vdev->devh->eprom_versions[i]) {
+				gpxe = 1;
+				break;
+			}
+	}
+	if (gpxe)
+		fw_name = "vxge/X3fw-pxe.ncf";
+	else
+		fw_name = "vxge/X3fw.ncf";
+
+	ret = vxge_fw_upgrade(vdev, fw_name, 0);
+	/* -EINVAL and -ENOENT are not fatal errors for flashing firmware on
+	 * probe, so ignore them
+	 */
+	if (ret != -EINVAL && ret != -ENOENT)
+		return -EIO;
+	else
+		ret = 0;
+
+	if (VXGE_FW_VER(VXGE_CERT_FW_VER_MAJOR, VXGE_CERT_FW_VER_MINOR, 0) >
+	    VXGE_FW_VER(maj, min, 0)) {
+		vxge_debug_init(VXGE_ERR, "%s: Firmware %d.%d.%d is too old to"
+				" be used with this driver.\n"
+				"Please get the latest version from "
+				"ftp://ftp.s2io.com/pub/X3100-Drivers/FIRMWARE",
+				VXGE_DRIVER_NAME, maj, min, bld);
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
 /**
  * vxge_probe
  * @pdev : structure containing the PCI related information of the device.
@@ -4082,16 +4220,6 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre)
 		goto _exit3;
 	}
 
-	if (ll_config->device_hw_info.fw_version.major !=
-		VXGE_DRIVER_FW_VERSION_MAJOR) {
-		vxge_debug_init(VXGE_ERR,
-			"%s: Incorrect firmware version."
-			"Please upgrade the firmware to version 1.x.x",
-			VXGE_DRIVER_NAME);
-		ret = -EINVAL;
-		goto _exit3;
-	}
-
 	vpath_mask = ll_config->device_hw_info.vpath_mask;
 	if (vpath_mask == 0) {
 		vxge_debug_ll_config(VXGE_TRACE,
@@ -4155,6 +4283,32 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre)
 			goto _exit3;
 	}
 
+	if (VXGE_FW_VER(ll_config->device_hw_info.fw_version.major,
+			ll_config->device_hw_info.fw_version.minor,
+			ll_config->device_hw_info.fw_version.build) >=
+	    VXGE_EPROM_FW_VER) {
+		struct eprom_image img[VXGE_HW_MAX_ROM_IMAGES];
+
+		status = vxge_hw_vpath_eprom_img_ver_get(hldev, img);
+		if (status != VXGE_HW_OK) {
+			vxge_debug_init(VXGE_ERR, "%s: Reading of EPROM failed",
+					VXGE_DRIVER_NAME);
+			/* This is a non-fatal error, continue */
+		}
+
+		for (i = 0; i < VXGE_HW_MAX_ROM_IMAGES; i++) {
+			hldev->eprom_versions[i] = img[i].version;
+			if (!img[i].is_valid)
+				break;
+			vxge_debug_init(VXGE_TRACE, "%s: EPROM %d, version "
+					"%d.%d.%d.%d\n", VXGE_DRIVER_NAME, i,
+					VXGE_EPROM_IMG_MAJOR(img[i].version),
+					VXGE_EPROM_IMG_MINOR(img[i].version),
+					VXGE_EPROM_IMG_FIX(img[i].version),
+					VXGE_EPROM_IMG_BUILD(img[i].version));
+		}
+	}
+
 	/* if FCS stripping is not disabled in MAC fail driver load */
 	if (vxge_hw_vpath_strip_fcs_check(hldev, vpath_mask) != VXGE_HW_OK) {
 		vxge_debug_init(VXGE_ERR,
@@ -4183,18 +4337,22 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre)
 	ll_config->tx_pause_enable = VXGE_PAUSE_CTRL_ENABLE;
 	ll_config->rx_pause_enable = VXGE_PAUSE_CTRL_ENABLE;
 
-	if (vxge_device_register(hldev, ll_config, high_dma, no_of_vpath,
-		&vdev)) {
+	ret = vxge_device_register(hldev, ll_config, high_dma, no_of_vpath,
+				   &vdev);
+	if (ret) {
 		ret = -EINVAL;
 		goto _exit4;
 	}
 
+	ret = vxge_probe_fw_update(vdev);
+	if (ret)
+		goto _exit5;
+
 	vxge_hw_device_debug_set(hldev, VXGE_TRACE, VXGE_COMPONENT_LL);
 	VXGE_COPY_DEBUG_INFO_TO_LL(vdev, vxge_hw_device_error_level_get(hldev),
 		vxge_hw_device_trace_level_get(hldev));
 
 	/* set private HW device info */
-	hldev->ndev = vdev->ndev;
 	vdev->mtu = VXGE_HW_DEFAULT_MTU;
 	vdev->bar0 = attr.bar0;
 	vdev->max_vpath_supported = max_vpath_supported;
@@ -4296,7 +4454,7 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre)
 				"%s: mac_addr_list : memory allocation failed",
 				vdev->ndev->name);
 			ret = -EPERM;
-			goto _exit5;
+			goto _exit6;
 		}
 		macaddr = (u8 *)&entry->macaddr;
 		memcpy(macaddr, vdev->ndev->dev_addr, ETH_ALEN);
@@ -4336,10 +4494,10 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre)
 	kfree(ll_config);
 	return 0;
 
-_exit5:
+_exit6:
 	for (i = 0; i < vdev->no_of_vpath; i++)
 		vxge_free_mac_add_list(&vdev->vpaths[i]);
-
+_exit5:
 	vxge_device_unregister(hldev);
 _exit4:
 	pci_disable_sriov(pdev);
diff --git a/drivers/net/vxge/vxge-main.h b/drivers/net/vxge/vxge-main.h
index 411732d..1e47319 100644
--- a/drivers/net/vxge/vxge-main.h
+++ b/drivers/net/vxge/vxge-main.h
@@ -451,7 +451,11 @@ enum vxge_hw_status vxge_restore_vpath_mac_addr(struct vxge_vpath *vpath);
 enum vxge_hw_status vxge_restore_vpath_vid_table(struct vxge_vpath *vpath);
 
 int do_vxge_close(struct net_device *dev, int do_io);
+
 extern void initialize_ethtool_ops(struct net_device *ndev);
+
+int vxge_fw_upgrade(struct vxgedev *vdev, char *fw_name, int override);
+
 /**
  * #define VXGE_DEBUG_INIT: debug for initialization functions
  * #define VXGE_DEBUG_TX	 : debug transmit related functions
diff --git a/drivers/net/vxge/vxge-reg.h b/drivers/net/vxge/vxge-reg.h
index 93fd752..0df52db 100644
--- a/drivers/net/vxge/vxge-reg.h
+++ b/drivers/net/vxge/vxge-reg.h
@@ -49,6 +49,30 @@
 #define VXGE_HW_TITAN_VPMGMT_REG_SPACES			17
 #define VXGE_HW_TITAN_VPATH_REG_SPACES			17
 
+#define VXGE_HW_FW_API_GET_EPROM_REV			31
+
+#define VXGE_EPROM_IMG_MAJOR(val)		(u32) vxge_bVALn(val, 48, 4)
+#define VXGE_EPROM_IMG_MINOR(val)		(u32) vxge_bVALn(val, 52, 4)
+#define VXGE_EPROM_IMG_FIX(val)			(u32) vxge_bVALn(val, 56, 4)
+#define VXGE_EPROM_IMG_BUILD(val)		(u32) vxge_bVALn(val, 60, 4)
+
+#define VXGE_HW_GET_EPROM_IMAGE_INDEX(val)		vxge_bVALn(val, 16, 8)
+#define VXGE_HW_GET_EPROM_IMAGE_VALID(val)		vxge_bVALn(val, 31, 1)
+#define VXGE_HW_GET_EPROM_IMAGE_TYPE(val)		vxge_bVALn(val, 40, 8)
+#define VXGE_HW_GET_EPROM_IMAGE_REV(val)		vxge_bVALn(val, 48, 16)
+#define VXGE_HW_RTS_ACCESS_STEER_ROM_IMAGE_INDEX(val)	vxge_vBIT(val, 16, 8)
+
+#define VXGE_HW_FW_UPGRADE_MEMO				13
+#define VXGE_HW_FW_UPGRADE_ACTION			16
+#define VXGE_HW_FW_UPGRADE_OFFSET_START			2
+#define VXGE_HW_FW_UPGRADE_OFFSET_SEND			3
+#define VXGE_HW_FW_UPGRADE_OFFSET_COMMIT		4
+#define VXGE_HW_FW_UPGRADE_OFFSET_READ			5
+
+#define VXGE_HW_FW_UPGRADE_BLK_SIZE			16
+#define VXGE_HW_UPGRADE_GET_RET_ERR_CODE(val)		(val & 0xff)
+#define VXGE_HW_UPGRADE_GET_SEC_ERR_CODE(val)		((val >> 8) & 0xff)
+
 #define VXGE_HW_ASIC_MODE_RESERVED				0
 #define VXGE_HW_ASIC_MODE_NO_IOV				1
 #define VXGE_HW_ASIC_MODE_SR_IOV				2
@@ -165,13 +189,13 @@
 #define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_ETYPE		2
 #define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_PN		3
 #define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_GEN_CFG	5
-#define	VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT	6
+#define	VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT		6
 #define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_JHASH_CFG	7
 #define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MASK		8
 #define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_KEY		9
 #define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_QOS		10
 #define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DS		11
-#define	VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT	12
+#define	VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT		12
 #define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO		13
 
 #define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_DA_MAC_ADDR(bits) \
@@ -437,6 +461,7 @@
 #define VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_BUILD(bits) \
 							vxge_bVALn(bits, 48, 16)
 #define VXGE_HW_RTS_ACCESS_STEER_DATA1_FLASH_VER_BUILD vxge_vBIT(val, 48, 16)
+#define VXGE_HW_RTS_ACCESS_STEER_CTRL_GET_ACTION(bits) vxge_bVALn(bits, 0, 8)
 
 #define	VXGE_HW_SRPCIM_TO_VPATH_ALARM_REG_GET_PPIF_SRPCIM_TO_VPATH_ALARM(bits)\
 							vxge_bVALn(bits, 0, 18)
diff --git a/drivers/net/vxge/vxge-version.h b/drivers/net/vxge/vxge-version.h
index 53fefe1..b4eced1 100644
--- a/drivers/net/vxge/vxge-version.h
+++ b/drivers/net/vxge/vxge-version.h
@@ -19,4 +19,31 @@
 #define VXGE_VERSION_FIX	"9"
 #define VXGE_VERSION_BUILD	"20840"
 #define VXGE_VERSION_FOR	"k"
+
+#define VXGE_FW_VER(maj, min, bld) (((maj) << 16) + ((min) << 8) + (bld))
+
+#define VXGE_DEAD_FW_VER_MAJOR	1
+#define VXGE_DEAD_FW_VER_MINOR	4
+#define VXGE_DEAD_FW_VER_BUILD	4
+
+#define VXGE_FW_DEAD_VER VXGE_FW_VER(VXGE_DEAD_FW_VER_MAJOR, \
+				     VXGE_DEAD_FW_VER_MINOR, \
+				     VXGE_DEAD_FW_VER_BUILD)
+
+#define VXGE_EPROM_FW_VER_MAJOR	1
+#define VXGE_EPROM_FW_VER_MINOR	6
+#define VXGE_EPROM_FW_VER_BUILD	1
+
+#define VXGE_EPROM_FW_VER VXGE_FW_VER(VXGE_EPROM_FW_VER_MAJOR, \
+				      VXGE_EPROM_FW_VER_MINOR, \
+				      VXGE_EPROM_FW_VER_BUILD)
+
+#define VXGE_CERT_FW_VER_MAJOR	1
+#define VXGE_CERT_FW_VER_MINOR	8
+#define VXGE_CERT_FW_VER_BUILD	1
+
+#define VXGE_CERT_FW_VER VXGE_FW_VER(VXGE_CERT_FW_VER_MAJOR, \
+				     VXGE_CERT_FW_VER_MINOR, \
+				     VXGE_CERT_FW_VER_BUILD)
+
 #endif
-- 
1.7.0.4


^ permalink raw reply related

* [PATCH 04/11] vxge: serialize access to steering control register
From: Jon Mason @ 2010-11-04 22:51 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Sivakumar Subramani, Sreenivasa Honnur, Ram Vepa
In-Reply-To: <1288911122-28669-1-git-send-email-jon.mason@exar.com>

It is possible for multiple callers to access the firmware interface for
the same vpath simultaneously, resulting in uncertain output.  Add locks
to serialize access.  Also, make functions only accessed locally static,
thus requiring some movement of code blocks.

Signed-off-by: Jon Mason <jon.mason@exar.com>
Signed-off-by: Ram Vepa <ram.vepa@exar.com>
---
 drivers/net/vxge/vxge-config.c |  787 +++++++++++++++++-----------------------
 drivers/net/vxge/vxge-config.h |   32 +--
 2 files changed, 325 insertions(+), 494 deletions(-)

diff --git a/drivers/net/vxge/vxge-config.c b/drivers/net/vxge/vxge-config.c
index dfc4d37..e84d787 100644
--- a/drivers/net/vxge/vxge-config.c
+++ b/drivers/net/vxge/vxge-config.c
@@ -19,6 +19,7 @@
 
 #include "vxge-traffic.h"
 #include "vxge-config.h"
+#include "vxge-main.h"
 
 static void
 vxge_hw_vpath_set_zero_rx_frm_len(struct vxge_hw_vpath_reg __iomem *vp_reg)
@@ -102,6 +103,72 @@ void vxge_hw_device_wait_receive_idle(struct __vxge_hw_device *hldev)
 	}
 }
 
+static enum vxge_hw_status
+vxge_hw_vpath_fw_api(struct __vxge_hw_virtualpath *vpath, u32 action,
+		     u32 fw_memo, u32 offset, u64 *data0, u64 *data1,
+		     u64 *steer_ctrl)
+{
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+	enum vxge_hw_status status;
+	u64 val64;
+	u32 retry = 0, max_retry = 100;
+
+	vp_reg = vpath->vp_reg;
+
+	if (vpath->vp_open) {
+		max_retry = 3;
+		spin_lock(&vpath->lock);
+	}
+
+	writeq(*data0, &vp_reg->rts_access_steer_data0);
+	writeq(*data1, &vp_reg->rts_access_steer_data1);
+	wmb();
+
+	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(action) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(fw_memo) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(offset) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
+		*steer_ctrl;
+
+	status = __vxge_hw_pio_mem_write64(val64,
+					   &vp_reg->rts_access_steer_ctrl,
+					   VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
+					   VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+
+	/* The __vxge_hw_device_register_poll can udelay for a significant
+	 * amount of time, blocking other proccess from the CPU.  If it delays
+	 * for ~5secs, a NMI error can occur.  A way around this is to give up
+	 * the processor via msleep, but this is not allowed is under lock.
+	 * So, only allow it to sleep for ~4secs if open.  Otherwise, delay for
+	 * 1sec and sleep for 10ms until the firmware operation has completed
+	 * or timed-out.
+	 */
+	while ((status != VXGE_HW_OK) && retry++ < max_retry) {
+		if (!vpath->vp_open)
+			msleep(20);
+		status = __vxge_hw_device_register_poll(
+					&vp_reg->rts_access_steer_ctrl,
+					VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
+					VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+	}
+
+	if (status != VXGE_HW_OK)
+		goto out;
+
+	val64 = readq(&vp_reg->rts_access_steer_ctrl);
+	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
+		*data0 = readq(&vp_reg->rts_access_steer_data0);
+		*data1 = readq(&vp_reg->rts_access_steer_data1);
+		*steer_ctrl = val64;
+	} else
+		status = VXGE_HW_FAIL;
+
+out:
+	if (vpath->vp_open)
+		spin_unlock(&vpath->lock);
+	return status;
+}
+
 /*
  * __vxge_hw_channel_allocate - Allocate memory for channel
  * This function allocates required memory for the channel and various arrays
@@ -477,10 +544,25 @@ __vxge_hw_device_is_privilaged(u32 host_type, u32 func_id)
 }
 
 /*
+ * __vxge_hw_vpath_func_id_get - Get the function id of the vpath.
+ * Returns the function number of the vpath.
+ */
+static u32
+__vxge_hw_vpath_func_id_get(struct vxge_hw_vpmgmt_reg __iomem *vpmgmt_reg)
+{
+	u64 val64;
+
+	val64 = readq(&vpmgmt_reg->vpath_to_func_map_cfg1);
+
+	return
+	 (u32)VXGE_HW_VPATH_TO_FUNC_MAP_CFG1_GET_VPATH_TO_FUNC_MAP_CFG1(val64);
+}
+
+/*
  * __vxge_hw_device_host_info_get
  * This routine returns the host type assignments
  */
-void __vxge_hw_device_host_info_get(struct __vxge_hw_device *hldev)
+static void __vxge_hw_device_host_info_get(struct __vxge_hw_device *hldev)
 {
 	u64 val64;
 	u32 i;
@@ -493,16 +575,18 @@ void __vxge_hw_device_host_info_get(struct __vxge_hw_device *hldev)
 	hldev->vpath_assignments = readq(&hldev->common_reg->vpath_assignments);
 
 	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
-
 		if (!(hldev->vpath_assignments & vxge_mBIT(i)))
 			continue;
 
 		hldev->func_id =
-			__vxge_hw_vpath_func_id_get(i, hldev->vpmgmt_reg[i]);
+			__vxge_hw_vpath_func_id_get(hldev->vpmgmt_reg[i]);
 
 		hldev->access_rights = __vxge_hw_device_access_rights_get(
 			hldev->host_type, hldev->func_id);
 
+		hldev->virtual_paths[i].vp_open = VXGE_HW_VP_NOT_OPEN;
+		hldev->virtual_paths[i].vp_reg = hldev->vpath_reg[i];
+
 		hldev->first_vp_id = i;
 		break;
 	}
@@ -559,6 +643,192 @@ exit:
 	return status;
 }
 
+/*
+ * __vxge_hw_vpath_fw_ver_get - Get the fw version
+ * Returns FW Version
+ */
+static enum vxge_hw_status
+__vxge_hw_vpath_fw_ver_get(struct __vxge_hw_virtualpath *vpath,
+			   struct vxge_hw_device_hw_info *hw_info)
+{
+	struct vxge_hw_device_version *fw_version = &hw_info->fw_version;
+	struct vxge_hw_device_date *fw_date = &hw_info->fw_date;
+	struct vxge_hw_device_version *flash_version = &hw_info->flash_version;
+	struct vxge_hw_device_date *flash_date = &hw_info->flash_date;
+	u64 data0, data1 = 0, steer_ctrl = 0;
+	enum vxge_hw_status status;
+
+	status = vxge_hw_vpath_fw_api(vpath,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO,
+			0, &data0, &data1, &steer_ctrl);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	fw_date->day =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_DAY(data0);
+	fw_date->month =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MONTH(data0);
+	fw_date->year =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_YEAR(data0);
+
+	snprintf(fw_date->date, VXGE_HW_FW_STRLEN, "%2.2d/%2.2d/%4.4d",
+		 fw_date->month, fw_date->day, fw_date->year);
+
+	fw_version->major =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MAJOR(data0);
+	fw_version->minor =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MINOR(data0);
+	fw_version->build =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_BUILD(data0);
+
+	snprintf(fw_version->version, VXGE_HW_FW_STRLEN, "%d.%d.%d",
+		 fw_version->major, fw_version->minor, fw_version->build);
+
+	flash_date->day =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_DAY(data1);
+	flash_date->month =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MONTH(data1);
+	flash_date->year =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_YEAR(data1);
+
+	snprintf(flash_date->date, VXGE_HW_FW_STRLEN, "%2.2d/%2.2d/%4.4d",
+		 flash_date->month, flash_date->day, flash_date->year);
+
+	flash_version->major =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MAJOR(data1);
+	flash_version->minor =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MINOR(data1);
+	flash_version->build =
+	    (u32) VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_BUILD(data1);
+
+	snprintf(flash_version->version, VXGE_HW_FW_STRLEN, "%d.%d.%d",
+		 flash_version->major, flash_version->minor,
+		 flash_version->build);
+
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_card_info_get - Get the serial numbers,
+ * part number and product description.
+ */
+static enum vxge_hw_status
+__vxge_hw_vpath_card_info_get(struct __vxge_hw_virtualpath *vpath,
+			      struct vxge_hw_device_hw_info *hw_info)
+{
+	enum vxge_hw_status status;
+	u64 data0, data1 = 0, steer_ctrl = 0;
+	u8 *serial_number = hw_info->serial_number;
+	u8 *part_number = hw_info->part_number;
+	u8 *product_desc = hw_info->product_desc;
+	u32 i, j = 0;
+
+	data0 = VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_SERIAL_NUMBER;
+
+	status = vxge_hw_vpath_fw_api(vpath,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO,
+			0, &data0, &data1, &steer_ctrl);
+	if (status != VXGE_HW_OK)
+		return status;
+
+	((u64 *)serial_number)[0] = be64_to_cpu(data0);
+	((u64 *)serial_number)[1] = be64_to_cpu(data1);
+
+	data0 = VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_PART_NUMBER;
+	data1 = steer_ctrl = 0;
+
+	status = vxge_hw_vpath_fw_api(vpath,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO,
+			0, &data0, &data1, &steer_ctrl);
+	if (status != VXGE_HW_OK)
+		return status;
+
+	((u64 *)part_number)[0] = be64_to_cpu(data0);
+	((u64 *)part_number)[1] = be64_to_cpu(data1);
+
+	for (i = VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_0;
+	     i <= VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_3; i++) {
+		data0 = i;
+		data1 = steer_ctrl = 0;
+
+		status = vxge_hw_vpath_fw_api(vpath,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO,
+			0, &data0, &data1, &steer_ctrl);
+		if (status != VXGE_HW_OK)
+			return status;
+
+		((u64 *)product_desc)[j++] = be64_to_cpu(data0);
+		((u64 *)product_desc)[j++] = be64_to_cpu(data1);
+	}
+
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_pci_func_mode_get - Get the pci mode
+ * Returns pci function mode
+ */
+static u64
+__vxge_hw_vpath_pci_func_mode_get(struct __vxge_hw_virtualpath *vpath)
+{
+	u64 data0, data1 = 0, steer_ctrl = 0;
+	enum vxge_hw_status status;
+
+	data0 = VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_PCI_MODE;
+
+	status = vxge_hw_vpath_fw_api(vpath,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO,
+			0, &data0, &data1, &steer_ctrl);
+
+	return data0;
+}
+
+/*
+ * __vxge_hw_vpath_addr_get - Get the hw address entry for this vpath
+ *               from MAC address table.
+ */
+static enum vxge_hw_status
+__vxge_hw_vpath_addr_get(struct __vxge_hw_virtualpath *vpath,
+			 u8 *macaddr, u8 *macaddr_mask)
+{
+	u64 action = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_FIRST_ENTRY,
+	    data0 = 0, data1 = 0, steer_ctrl = 0;
+	enum vxge_hw_status status;
+	int i;
+
+	do {
+		status = vxge_hw_vpath_fw_api(vpath, action,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA,
+			0, &data0, &data1, &steer_ctrl);
+		if (status != VXGE_HW_OK)
+			goto exit;
+
+		data0 = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_DA_MAC_ADDR(data0);
+		data1 = VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_DA_MAC_ADDR_MASK(
+									data1);
+
+		for (i = ETH_ALEN; i > 0; i--) {
+			macaddr[i - 1] = (u8) (data0 & 0xFF);
+			data0 >>= 8;
+
+			macaddr_mask[i - 1] = (u8) (data1 & 0xFF);
+			data1 >>= 8;
+		}
+
+		action = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_NEXT_ENTRY;
+		data0 = 0, data1 = 0, steer_ctrl = 0;
+
+	} while (!is_valid_ether_addr(macaddr));
+exit:
+	return status;
+}
+
 /**
  * vxge_hw_device_hw_info_get - Get the hw information
  * Returns the vpath mask that has the bits set for each vpath allocated
@@ -574,9 +844,9 @@ vxge_hw_device_hw_info_get(void __iomem *bar0,
 	struct vxge_hw_toc_reg __iomem *toc;
 	struct vxge_hw_mrpcim_reg __iomem *mrpcim_reg;
 	struct vxge_hw_common_reg __iomem *common_reg;
-	struct vxge_hw_vpath_reg __iomem *vpath_reg;
 	struct vxge_hw_vpmgmt_reg __iomem *vpmgmt_reg;
 	enum vxge_hw_status status;
+	struct __vxge_hw_virtualpath vpath;
 
 	memset(hw_info, 0, sizeof(struct vxge_hw_device_hw_info));
 
@@ -611,7 +881,7 @@ vxge_hw_device_hw_info_get(void __iomem *bar0,
 		vpmgmt_reg = (struct vxge_hw_vpmgmt_reg __iomem *)
 				(bar0 + val64);
 
-		hw_info->func_id = __vxge_hw_vpath_func_id_get(i, vpmgmt_reg);
+		hw_info->func_id = __vxge_hw_vpath_func_id_get(vpmgmt_reg);
 		if (__vxge_hw_device_access_rights_get(hw_info->host_type,
 			hw_info->func_id) &
 			VXGE_HW_DEVICE_ACCESS_RIGHT_MRPCIM) {
@@ -627,16 +897,18 @@ vxge_hw_device_hw_info_get(void __iomem *bar0,
 
 		val64 = readq(&toc->toc_vpath_pointer[i]);
 
-		vpath_reg = (struct vxge_hw_vpath_reg __iomem *)(bar0 + val64);
+		vpath.vp_reg = (struct vxge_hw_vpath_reg __iomem *)
+			       (bar0 + val64);
+		vpath.vp_open = 0;
 
 		hw_info->function_mode =
-			__vxge_hw_vpath_pci_func_mode_get(i, vpath_reg);
+			__vxge_hw_vpath_pci_func_mode_get(&vpath);
 
-		status = __vxge_hw_vpath_fw_ver_get(i, vpath_reg, hw_info);
+		status = __vxge_hw_vpath_fw_ver_get(&vpath, hw_info);
 		if (status != VXGE_HW_OK)
 			goto exit;
 
-		status = __vxge_hw_vpath_card_info_get(i, vpath_reg, hw_info);
+		status = __vxge_hw_vpath_card_info_get(&vpath, hw_info);
 		if (status != VXGE_HW_OK)
 			goto exit;
 
@@ -644,14 +916,15 @@ vxge_hw_device_hw_info_get(void __iomem *bar0,
 	}
 
 	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
-
 		if (!((hw_info->vpath_mask) & vxge_mBIT(i)))
 			continue;
 
 		val64 = readq(&toc->toc_vpath_pointer[i]);
-		vpath_reg = (struct vxge_hw_vpath_reg __iomem *)(bar0 + val64);
+		vpath.vp_reg = (struct vxge_hw_vpath_reg __iomem *)
+			       (bar0 + val64);
+		vpath.vp_open = 0;
 
-		status =  __vxge_hw_vpath_addr_get(i, vpath_reg,
+		status =  __vxge_hw_vpath_addr_get(&vpath,
 				hw_info->mac_addrs[i],
 				hw_info->mac_addr_masks[i]);
 		if (status != VXGE_HW_OK)
@@ -723,7 +996,6 @@ vxge_hw_device_initialize(
 	nblocks++;
 
 	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
-
 		if (!(hldev->vpath_assignments & vxge_mBIT(i)))
 			continue;
 
@@ -748,7 +1020,6 @@ vxge_hw_device_initialize(
 	}
 
 	status = __vxge_hw_device_initialize(hldev);
-
 	if (status != VXGE_HW_OK) {
 		vxge_hw_device_terminate(hldev);
 		goto exit;
@@ -785,7 +1056,6 @@ vxge_hw_device_stats_get(struct __vxge_hw_device *hldev,
 	enum vxge_hw_status status = VXGE_HW_OK;
 
 	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
-
 		if (!(hldev->vpaths_deployed & vxge_mBIT(i)) ||
 			(hldev->virtual_paths[i].vp_open ==
 				VXGE_HW_VP_NOT_OPEN))
@@ -2618,297 +2888,6 @@ exit:
 	return status;
 }
 
-/*
- * __vxge_hw_vpath_func_id_get - Get the function id of the vpath.
- * Returns the function number of the vpath.
- */
-u32
-__vxge_hw_vpath_func_id_get(u32 vp_id,
-	struct vxge_hw_vpmgmt_reg __iomem *vpmgmt_reg)
-{
-	u64 val64;
-
-	val64 = readq(&vpmgmt_reg->vpath_to_func_map_cfg1);
-
-	return
-	 (u32)VXGE_HW_VPATH_TO_FUNC_MAP_CFG1_GET_VPATH_TO_FUNC_MAP_CFG1(val64);
-}
-
-/*
- * __vxge_hw_read_rts_ds - Program RTS steering critieria
- */
-static inline void
-__vxge_hw_read_rts_ds(struct vxge_hw_vpath_reg __iomem *vpath_reg,
-		      u64 dta_struct_sel)
-{
-	writeq(0, &vpath_reg->rts_access_steer_ctrl);
-	wmb();
-	writeq(dta_struct_sel, &vpath_reg->rts_access_steer_data0);
-	writeq(0, &vpath_reg->rts_access_steer_data1);
-	wmb();
-}
-
-
-/*
- * __vxge_hw_vpath_card_info_get - Get the serial numbers,
- * part number and product description.
- */
-enum vxge_hw_status
-__vxge_hw_vpath_card_info_get(
-	u32 vp_id,
-	struct vxge_hw_vpath_reg __iomem *vpath_reg,
-	struct vxge_hw_device_hw_info *hw_info)
-{
-	u32 i, j;
-	u64 val64;
-	u64 data1 = 0ULL;
-	u64 data2 = 0ULL;
-	enum vxge_hw_status status = VXGE_HW_OK;
-	u8 *serial_number = hw_info->serial_number;
-	u8 *part_number = hw_info->part_number;
-	u8 *product_desc = hw_info->product_desc;
-
-	__vxge_hw_read_rts_ds(vpath_reg,
-		VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_SERIAL_NUMBER);
-
-	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
-
-	status = __vxge_hw_pio_mem_write64(val64,
-				&vpath_reg->rts_access_steer_ctrl,
-				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
-				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
-
-	if (status != VXGE_HW_OK)
-		return status;
-
-	val64 = readq(&vpath_reg->rts_access_steer_ctrl);
-
-	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
-		data1 = readq(&vpath_reg->rts_access_steer_data0);
-		((u64 *)serial_number)[0] = be64_to_cpu(data1);
-
-		data2 = readq(&vpath_reg->rts_access_steer_data1);
-		((u64 *)serial_number)[1] = be64_to_cpu(data2);
-		status = VXGE_HW_OK;
-	} else
-		*serial_number = 0;
-
-	__vxge_hw_read_rts_ds(vpath_reg,
-			VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_PART_NUMBER);
-
-	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
-
-	status = __vxge_hw_pio_mem_write64(val64,
-				&vpath_reg->rts_access_steer_ctrl,
-				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
-				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
-
-	if (status != VXGE_HW_OK)
-		return status;
-
-	val64 = readq(&vpath_reg->rts_access_steer_ctrl);
-
-	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
-
-		data1 = readq(&vpath_reg->rts_access_steer_data0);
-		((u64 *)part_number)[0] = be64_to_cpu(data1);
-
-		data2 = readq(&vpath_reg->rts_access_steer_data1);
-		((u64 *)part_number)[1] = be64_to_cpu(data2);
-
-		status = VXGE_HW_OK;
-
-	} else
-		*part_number = 0;
-
-	j = 0;
-
-	for (i = VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_0;
-	     i <= VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_3; i++) {
-
-		__vxge_hw_read_rts_ds(vpath_reg, i);
-
-		val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) |
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
-
-		status = __vxge_hw_pio_mem_write64(val64,
-				&vpath_reg->rts_access_steer_ctrl,
-				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
-				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
-
-		if (status != VXGE_HW_OK)
-			return status;
-
-		val64 = readq(&vpath_reg->rts_access_steer_ctrl);
-
-		if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
-
-			data1 = readq(&vpath_reg->rts_access_steer_data0);
-			((u64 *)product_desc)[j++] = be64_to_cpu(data1);
-
-			data2 = readq(&vpath_reg->rts_access_steer_data1);
-			((u64 *)product_desc)[j++] = be64_to_cpu(data2);
-
-			status = VXGE_HW_OK;
-		} else
-			*product_desc = 0;
-	}
-
-	return status;
-}
-
-/*
- * __vxge_hw_vpath_fw_ver_get - Get the fw version
- * Returns FW Version
- */
-enum vxge_hw_status
-__vxge_hw_vpath_fw_ver_get(
-	u32 vp_id,
-	struct vxge_hw_vpath_reg __iomem *vpath_reg,
-	struct vxge_hw_device_hw_info *hw_info)
-{
-	u64 val64;
-	u64 data1 = 0ULL;
-	u64 data2 = 0ULL;
-	struct vxge_hw_device_version *fw_version = &hw_info->fw_version;
-	struct vxge_hw_device_date *fw_date = &hw_info->fw_date;
-	struct vxge_hw_device_version *flash_version = &hw_info->flash_version;
-	struct vxge_hw_device_date *flash_date = &hw_info->flash_date;
-	enum vxge_hw_status status = VXGE_HW_OK;
-
-	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_ENTRY) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
-
-	status = __vxge_hw_pio_mem_write64(val64,
-				&vpath_reg->rts_access_steer_ctrl,
-				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
-				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
-
-	if (status != VXGE_HW_OK)
-		goto exit;
-
-	val64 = readq(&vpath_reg->rts_access_steer_ctrl);
-
-	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
-
-		data1 = readq(&vpath_reg->rts_access_steer_data0);
-		data2 = readq(&vpath_reg->rts_access_steer_data1);
-
-		fw_date->day =
-			(u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_DAY(
-						data1);
-		fw_date->month =
-			(u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MONTH(
-						data1);
-		fw_date->year =
-			(u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_YEAR(
-						data1);
-
-		snprintf(fw_date->date, VXGE_HW_FW_STRLEN, "%2.2d/%2.2d/%4.4d",
-			fw_date->month, fw_date->day, fw_date->year);
-
-		fw_version->major =
-		    (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MAJOR(data1);
-		fw_version->minor =
-		    (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MINOR(data1);
-		fw_version->build =
-		    (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_BUILD(data1);
-
-		snprintf(fw_version->version, VXGE_HW_FW_STRLEN, "%d.%d.%d",
-		    fw_version->major, fw_version->minor, fw_version->build);
-
-		flash_date->day =
-		  (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_DAY(data2);
-		flash_date->month =
-		 (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MONTH(data2);
-		flash_date->year =
-		 (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_YEAR(data2);
-
-		snprintf(flash_date->date, VXGE_HW_FW_STRLEN,
-			"%2.2d/%2.2d/%4.4d",
-			flash_date->month, flash_date->day, flash_date->year);
-
-		flash_version->major =
-		 (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MAJOR(data2);
-		flash_version->minor =
-		 (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MINOR(data2);
-		flash_version->build =
-		 (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_BUILD(data2);
-
-		snprintf(flash_version->version, VXGE_HW_FW_STRLEN, "%d.%d.%d",
-			flash_version->major, flash_version->minor,
-			flash_version->build);
-
-		status = VXGE_HW_OK;
-
-	} else
-		status = VXGE_HW_FAIL;
-exit:
-	return status;
-}
-
-/*
- * __vxge_hw_vpath_pci_func_mode_get - Get the pci mode
- * Returns pci function mode
- */
-u64
-__vxge_hw_vpath_pci_func_mode_get(
-	u32  vp_id,
-	struct vxge_hw_vpath_reg __iomem *vpath_reg)
-{
-	u64 val64;
-	u64 data1 = 0ULL;
-	enum vxge_hw_status status = VXGE_HW_OK;
-
-	__vxge_hw_read_rts_ds(vpath_reg,
-		VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_PCI_MODE);
-
-	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
-
-	status = __vxge_hw_pio_mem_write64(val64,
-				&vpath_reg->rts_access_steer_ctrl,
-				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
-				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
-
-	if (status != VXGE_HW_OK)
-		goto exit;
-
-	val64 = readq(&vpath_reg->rts_access_steer_ctrl);
-
-	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
-		data1 = readq(&vpath_reg->rts_access_steer_data0);
-		status = VXGE_HW_OK;
-	} else {
-		data1 = 0;
-		status = VXGE_HW_FAIL;
-	}
-exit:
-	return data1;
-}
-
 /**
  * vxge_hw_device_flick_link_led - Flick (blink) link LED.
  * @hldev: HW device.
@@ -2917,37 +2896,24 @@ exit:
  * Flicker the link LED.
  */
 enum vxge_hw_status
-vxge_hw_device_flick_link_led(struct __vxge_hw_device *hldev,
-			       u64 on_off)
+vxge_hw_device_flick_link_led(struct __vxge_hw_device *hldev, u64 on_off)
 {
-	u64 val64;
-	enum vxge_hw_status status = VXGE_HW_OK;
-	struct vxge_hw_vpath_reg __iomem *vp_reg;
+	struct __vxge_hw_virtualpath *vpath;
+	u64 data0, data1 = 0, steer_ctrl = 0;
+	enum vxge_hw_status status;
 
 	if (hldev == NULL) {
 		status = VXGE_HW_ERR_INVALID_DEVICE;
 		goto exit;
 	}
 
-	vp_reg = hldev->vpath_reg[hldev->first_vp_id];
-
-	writeq(0, &vp_reg->rts_access_steer_ctrl);
-	wmb();
-	writeq(on_off, &vp_reg->rts_access_steer_data0);
-	writeq(0, &vp_reg->rts_access_steer_data1);
-	wmb();
-
-	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LED_CONTROL) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
-			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
+	vpath = &hldev->virtual_paths[hldev->first_vp_id];
 
-	status = __vxge_hw_pio_mem_write64(val64,
-				&vp_reg->rts_access_steer_ctrl,
-				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
-				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+	data0 = on_off;
+	status = vxge_hw_vpath_fw_api(vpath,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LED_CONTROL,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO,
+			0, &data0, &data1, &steer_ctrl);
 exit:
 	return status;
 }
@@ -2956,63 +2922,38 @@ exit:
  * __vxge_hw_vpath_rts_table_get - Get the entries from RTS access tables
  */
 enum vxge_hw_status
-__vxge_hw_vpath_rts_table_get(
-	struct __vxge_hw_vpath_handle *vp,
-	u32 action, u32 rts_table, u32 offset, u64 *data1, u64 *data2)
+__vxge_hw_vpath_rts_table_get(struct __vxge_hw_vpath_handle *vp,
+			      u32 action, u32 rts_table, u32 offset,
+			      u64 *data0, u64 *data1)
 {
-	u64 val64;
-	struct __vxge_hw_virtualpath *vpath;
-	struct vxge_hw_vpath_reg __iomem *vp_reg;
-
-	enum vxge_hw_status status = VXGE_HW_OK;
+	enum vxge_hw_status status;
+	u64 steer_ctrl = 0;
 
 	if (vp == NULL) {
 		status = VXGE_HW_ERR_INVALID_HANDLE;
 		goto exit;
 	}
 
-	vpath = vp->vpath;
-	vp_reg = vpath->vp_reg;
-
-	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(action) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(rts_table) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(offset);
-
 	if ((rts_table ==
-		VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT) ||
+	     VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT) ||
 	    (rts_table ==
-		VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT) ||
+	     VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT) ||
 	    (rts_table ==
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MASK) ||
+	     VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MASK) ||
 	    (rts_table ==
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_KEY)) {
-		val64 = val64 |	VXGE_HW_RTS_ACCESS_STEER_CTRL_TABLE_SEL;
+	     VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_KEY)) {
+		steer_ctrl = VXGE_HW_RTS_ACCESS_STEER_CTRL_TABLE_SEL;
 	}
 
-	status = __vxge_hw_pio_mem_write64(val64,
-				&vp_reg->rts_access_steer_ctrl,
-				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
-				vpath->hldev->config.device_poll_millis);
-
+	status = vxge_hw_vpath_fw_api(vp->vpath, action, rts_table, offset,
+				      data0, data1, &steer_ctrl);
 	if (status != VXGE_HW_OK)
 		goto exit;
 
-	val64 = readq(&vp_reg->rts_access_steer_ctrl);
-
-	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
-
-		*data1 = readq(&vp_reg->rts_access_steer_data0);
-
-		if ((rts_table ==
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) ||
-		(rts_table ==
-		VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT)) {
-			*data2 = readq(&vp_reg->rts_access_steer_data1);
-		}
-		status = VXGE_HW_OK;
-	} else
-		status = VXGE_HW_FAIL;
+	if ((rts_table != VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) ||
+	    (rts_table !=
+	     VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT))
+		*data1 = 0;
 exit:
 	return status;
 }
@@ -3021,107 +2962,27 @@ exit:
  * __vxge_hw_vpath_rts_table_set - Set the entries of RTS access tables
  */
 enum vxge_hw_status
-__vxge_hw_vpath_rts_table_set(
-	struct __vxge_hw_vpath_handle *vp, u32 action, u32 rts_table,
-	u32 offset, u64 data1, u64 data2)
+__vxge_hw_vpath_rts_table_set(struct __vxge_hw_vpath_handle *vp, u32 action,
+			      u32 rts_table, u32 offset, u64 steer_data0,
+			      u64 steer_data1)
 {
-	u64 val64;
-	struct __vxge_hw_virtualpath *vpath;
-	enum vxge_hw_status status = VXGE_HW_OK;
-	struct vxge_hw_vpath_reg __iomem *vp_reg;
+	u64 data0, data1 = 0, steer_ctrl = 0;
+	enum vxge_hw_status status;
 
 	if (vp == NULL) {
 		status = VXGE_HW_ERR_INVALID_HANDLE;
 		goto exit;
 	}
 
-	vpath = vp->vpath;
-	vp_reg = vpath->vp_reg;
-
-	writeq(data1, &vp_reg->rts_access_steer_data0);
-	wmb();
+	data0 = steer_data0;
 
 	if ((rts_table == VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) ||
 	    (rts_table ==
-		VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT)) {
-		writeq(data2, &vp_reg->rts_access_steer_data1);
-		wmb();
-	}
-
-	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(action) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(rts_table) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(offset);
+	     VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT))
+		data1 = steer_data1;
 
-	status = __vxge_hw_pio_mem_write64(val64,
-				&vp_reg->rts_access_steer_ctrl,
-				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
-				vpath->hldev->config.device_poll_millis);
-
-	if (status != VXGE_HW_OK)
-		goto exit;
-
-	val64 = readq(&vp_reg->rts_access_steer_ctrl);
-
-	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS)
-		status = VXGE_HW_OK;
-	else
-		status = VXGE_HW_FAIL;
-exit:
-	return status;
-}
-
-/*
- * __vxge_hw_vpath_addr_get - Get the hw address entry for this vpath
- *               from MAC address table.
- */
-enum vxge_hw_status
-__vxge_hw_vpath_addr_get(
-	u32 vp_id, struct vxge_hw_vpath_reg __iomem *vpath_reg,
-	u8 (macaddr)[ETH_ALEN], u8 (macaddr_mask)[ETH_ALEN])
-{
-	u32 i;
-	u64 val64;
-	u64 data1 = 0ULL;
-	u64 data2 = 0ULL;
-	enum vxge_hw_status status = VXGE_HW_OK;
-
-	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_FIRST_ENTRY) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
-		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
-
-	status = __vxge_hw_pio_mem_write64(val64,
-				&vpath_reg->rts_access_steer_ctrl,
-				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
-				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
-
-	if (status != VXGE_HW_OK)
-		goto exit;
-
-	val64 = readq(&vpath_reg->rts_access_steer_ctrl);
-
-	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
-
-		data1 = readq(&vpath_reg->rts_access_steer_data0);
-		data2 = readq(&vpath_reg->rts_access_steer_data1);
-
-		data1 = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_DA_MAC_ADDR(data1);
-		data2 = VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_DA_MAC_ADDR_MASK(
-							data2);
-
-		for (i = ETH_ALEN; i > 0; i--) {
-			macaddr[i-1] = (u8)(data1 & 0xFF);
-			data1 >>= 8;
-
-			macaddr_mask[i-1] = (u8)(data2 & 0xFF);
-			data2 >>= 8;
-		}
-		status = VXGE_HW_OK;
-	} else
-		status = VXGE_HW_FAIL;
+	status = vxge_hw_vpath_fw_api(vp->vpath, action, rts_table, offset,
+				      &data0, &data1, &steer_ctrl);
 exit:
 	return status;
 }
@@ -4062,6 +3923,7 @@ __vxge_hw_vp_initialize(struct __vxge_hw_device *hldev, u32 vp_id,
 
 	vpath = &hldev->virtual_paths[vp_id];
 
+	spin_lock_init(&hldev->virtual_paths[vp_id].lock);
 	vpath->vp_id = vp_id;
 	vpath->vp_open = VXGE_HW_VP_OPEN;
 	vpath->hldev = hldev;
@@ -4072,14 +3934,12 @@ __vxge_hw_vp_initialize(struct __vxge_hw_device *hldev, u32 vp_id,
 	__vxge_hw_vpath_reset(hldev, vp_id);
 
 	status = __vxge_hw_vpath_reset_check(vpath);
-
 	if (status != VXGE_HW_OK) {
 		memset(vpath, 0, sizeof(struct __vxge_hw_virtualpath));
 		goto exit;
 	}
 
 	status = __vxge_hw_vpath_mgmt_read(hldev, vpath);
-
 	if (status != VXGE_HW_OK) {
 		memset(vpath, 0, sizeof(struct __vxge_hw_virtualpath));
 		goto exit;
@@ -4093,7 +3953,6 @@ __vxge_hw_vp_initialize(struct __vxge_hw_device *hldev, u32 vp_id,
 		hldev->tim_int_mask1, vp_id);
 
 	status = __vxge_hw_vpath_initialize(hldev, vp_id);
-
 	if (status != VXGE_HW_OK)
 		__vxge_hw_vp_terminate(hldev, vp_id);
 exit:
@@ -4359,7 +4218,9 @@ enum vxge_hw_status vxge_hw_vpath_close(struct __vxge_hw_vpath_handle *vp)
 
 	__vxge_hw_vp_terminate(devh, vp_id);
 
+	spin_lock(&vpath->lock);
 	vpath->vp_open = VXGE_HW_VP_NOT_OPEN;
+	spin_unlock(&vpath->lock);
 
 vpath_close_exit:
 	return status;
diff --git a/drivers/net/vxge/vxge-config.h b/drivers/net/vxge/vxge-config.h
index 285695a..2337665 100644
--- a/drivers/net/vxge/vxge-config.h
+++ b/drivers/net/vxge/vxge-config.h
@@ -172,11 +172,6 @@ struct vxge_hw_device_version {
 	char    version[VXGE_HW_FW_STRLEN];
 };
 
-u64
-__vxge_hw_vpath_pci_func_mode_get(
-	u32 vp_id,
-	struct vxge_hw_vpath_reg __iomem *vpath_reg);
-
 /**
  * struct vxge_hw_fifo_config - Configuration of fifo.
  * @enable: Is this fifo to be commissioned
@@ -646,6 +641,7 @@ struct __vxge_hw_virtualpath {
 	struct vxge_hw_vpath_stats_hw_info	*hw_stats;
 	struct vxge_hw_vpath_stats_hw_info	*hw_stats_sav;
 	struct vxge_hw_vpath_stats_sw_info	*sw_stats;
+	spinlock_t lock;
 };
 
 /*
@@ -1848,18 +1844,6 @@ enum vxge_hw_status __devinit vxge_hw_device_hw_info_get(
 	void __iomem *bar0,
 	struct vxge_hw_device_hw_info *hw_info);
 
-enum vxge_hw_status
-__vxge_hw_vpath_fw_ver_get(
-	u32	vp_id,
-	struct vxge_hw_vpath_reg __iomem *vpath_reg,
-	struct vxge_hw_device_hw_info *hw_info);
-
-enum vxge_hw_status
-__vxge_hw_vpath_card_info_get(
-	u32 vp_id,
-	struct vxge_hw_vpath_reg __iomem *vpath_reg,
-	struct vxge_hw_device_hw_info *hw_info);
-
 enum vxge_hw_status __devinit vxge_hw_device_config_default_get(
 	struct vxge_hw_device_config *device_config);
 
@@ -2181,9 +2165,6 @@ __vxge_hw_device_reg_addr_get(struct __vxge_hw_device *hldev);
 void
 __vxge_hw_device_id_get(struct __vxge_hw_device *hldev);
 
-void
-__vxge_hw_device_host_info_get(struct __vxge_hw_device *hldev);
-
 enum vxge_hw_status
 vxge_hw_device_flick_link_led(struct __vxge_hw_device *devh, u64 on_off);
 
@@ -2198,17 +2179,6 @@ __vxge_hw_vpath_pci_read(
 	u32			*val);
 
 enum vxge_hw_status
-__vxge_hw_vpath_addr_get(
-	u32 vp_id,
-	struct vxge_hw_vpath_reg __iomem *vpath_reg,
-	u8 (macaddr)[ETH_ALEN],
-	u8 (macaddr_mask)[ETH_ALEN]);
-
-u32
-__vxge_hw_vpath_func_id_get(
-	u32 vp_id, struct vxge_hw_vpmgmt_reg __iomem *vpmgmt_reg);
-
-enum vxge_hw_status
 __vxge_hw_vpath_reset_check(struct __vxge_hw_virtualpath *vpath);
 
 enum vxge_hw_status
-- 
1.7.0.4


^ permalink raw reply related

* [PATCH 03/11] vxge: cleanup debug printing and asserts
From: Jon Mason @ 2010-11-04 22:51 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Sivakumar Subramani, Sreenivasa Honnur, Ram Vepa
In-Reply-To: <1288911122-28669-1-git-send-email-jon.mason@exar.com>

Remove all of the unnecessary debug printk indirection and temporary
variables for vxge_debug_ll and vxge_assert.

Signed-off-by: Jon Mason <jon.mason@exar.com>
Signed-off-by: Ram Vepa <ram.vepa@exar.com>
---
 drivers/net/vxge/vxge-config.h |   43 +++++++++------------------------------
 drivers/net/vxge/vxge-main.h   |    2 -
 2 files changed, 10 insertions(+), 35 deletions(-)

diff --git a/drivers/net/vxge/vxge-config.h b/drivers/net/vxge/vxge-config.h
index eaa38e6..285695a 100644
--- a/drivers/net/vxge/vxge-config.h
+++ b/drivers/net/vxge/vxge-config.h
@@ -20,13 +20,6 @@
 #define VXGE_CACHE_LINE_SIZE 128
 #endif
 
-#define vxge_os_vaprintf(level, mask, fmt, ...) { \
-	char buff[255]; \
-		snprintf(buff, 255, fmt, __VA_ARGS__); \
-		printk(buff); \
-		printk("\n"); \
-}
-
 #ifndef VXGE_ALIGN
 #define VXGE_ALIGN(adrs, size) \
 	(((size) - (((u64)adrs) & ((size)-1))) & ((size)-1))
@@ -37,7 +30,6 @@
 #define VXGE_HW_DEFAULT_MTU			1500
 
 #ifdef VXGE_DEBUG_ASSERT
-
 /**
  * vxge_assert
  * @test: C-condition to check
@@ -48,16 +40,13 @@
  * compilation
  * time.
  */
-#define vxge_assert(test) { \
-	if (!(test)) \
-		vxge_os_bug("bad cond: "#test" at %s:%d\n", \
-				__FILE__, __LINE__); }
+#define vxge_assert(test) BUG_ON(!(test))
 #else
 #define vxge_assert(test)
 #endif /* end of VXGE_DEBUG_ASSERT */
 
 /**
- * enum enum vxge_debug_level
+ * enum vxge_debug_level
  * @VXGE_NONE: debug disabled
  * @VXGE_ERR: all errors going to be logged out
  * @VXGE_TRACE: all errors plus all kind of verbose tracing print outs
@@ -2224,8 +2213,9 @@ __vxge_hw_vpath_reset_check(struct __vxge_hw_virtualpath *vpath);
 
 enum vxge_hw_status
 vxge_hw_vpath_strip_fcs_check(struct __vxge_hw_device *hldev, u64 vpath_mask);
+
 /**
- * vxge_debug
+ * vxge_debug_ll
  * @level: level of debug verbosity.
  * @mask: mask for the debug
  * @buf: Circular buffer for tracing
@@ -2237,26 +2227,13 @@ vxge_hw_vpath_strip_fcs_check(struct __vxge_hw_device *hldev, u64 vpath_mask);
  * may be compiled out if DEBUG macro was never defined.
  * See also: enum vxge_debug_level{}.
  */
-
-#define vxge_trace_aux(level, mask, fmt, ...) \
-{\
-		vxge_os_vaprintf(level, mask, fmt, __VA_ARGS__);\
-}
-
-#define vxge_debug(module, level, mask, fmt, ...) { \
-if ((level >= VXGE_TRACE && ((module & VXGE_DEBUG_TRACE_MASK) == module)) || \
-	(level >= VXGE_ERR && ((module & VXGE_DEBUG_ERR_MASK) == module))) {\
-	if ((mask & VXGE_DEBUG_MASK) == mask)\
-		vxge_trace_aux(level, mask, fmt, __VA_ARGS__); \
-} \
-}
-
 #if (VXGE_COMPONENT_LL & VXGE_DEBUG_MODULE_MASK)
-#define vxge_debug_ll(level, mask, fmt, ...) \
-{\
-	vxge_debug(VXGE_COMPONENT_LL, level, mask, fmt, __VA_ARGS__);\
-}
-
+#define vxge_debug_ll(level, mask, fmt, ...) do {			       \
+	if ((level >= VXGE_ERR && VXGE_COMPONENT_LL & VXGE_DEBUG_ERR_MASK) ||  \
+	    (level >= VXGE_TRACE && VXGE_COMPONENT_LL & VXGE_DEBUG_TRACE_MASK))\
+		if ((mask & VXGE_DEBUG_MASK) == mask)			       \
+			printk(fmt "\n", __VA_ARGS__);			       \
+} while (0)
 #else
 #define vxge_debug_ll(level, mask, fmt, ...)
 #endif
diff --git a/drivers/net/vxge/vxge-main.h b/drivers/net/vxge/vxge-main.h
index 8641822..411732d 100644
--- a/drivers/net/vxge/vxge-main.h
+++ b/drivers/net/vxge/vxge-main.h
@@ -387,8 +387,6 @@ struct vxge_tx_priv {
 	static int p = val; \
 	module_param(p, int, 0)
 
-#define vxge_os_bug(fmt...)		{ printk(fmt); BUG(); }
-
 #define vxge_os_timer(timer, handle, arg, exp) do { \
 		init_timer(&timer); \
 		timer.function = handle; \
-- 
1.7.0.4


^ permalink raw reply related

* [PATCH 02/11] vxge: Wait for Rx to become idle before reseting or closing
From: Jon Mason @ 2010-11-04 22:51 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Sivakumar Subramani, Sreenivasa Honnur, Ram Vepa
In-Reply-To: <1288911122-28669-1-git-send-email-jon.mason@exar.com>

Wait for the receive traffic to become idle before attempting to close
or reset the adapter.  To enable the processing of packets while Receive
Idle, move the clearing of __VXGE_STATE_CARD_UP bit in vxge_close to
after it.  Also, modify the return value of the ISR when the adapter is
down to IRQ_HANDLED.  Otherwise there are unhandled interrupts for the
device.

Signed-off-by: Jon Mason <jon.mason@exar.com>
Signed-off-by: Ram Vepa <ram.vepa@exar.com>
---
 drivers/net/vxge/vxge-config.c |   86 ++++++++++++++++++++++++++++++++++++++-
 drivers/net/vxge/vxge-config.h |    7 +++
 drivers/net/vxge/vxge-main.c   |   16 ++++++--
 drivers/net/vxge/vxge-reg.h    |    1 +
 4 files changed, 103 insertions(+), 7 deletions(-)

diff --git a/drivers/net/vxge/vxge-config.c b/drivers/net/vxge/vxge-config.c
index 25f0938..dfc4d37 100644
--- a/drivers/net/vxge/vxge-config.c
+++ b/drivers/net/vxge/vxge-config.c
@@ -20,6 +20,88 @@
 #include "vxge-traffic.h"
 #include "vxge-config.h"
 
+static void
+vxge_hw_vpath_set_zero_rx_frm_len(struct vxge_hw_vpath_reg __iomem *vp_reg)
+{
+	u64 val64;
+
+	val64 = readq(&vp_reg->rxmac_vcfg0);
+	val64 &= ~VXGE_HW_RXMAC_VCFG0_RTS_MAX_FRM_LEN(0x3fff);
+	writeq(val64, &vp_reg->rxmac_vcfg0);
+	val64 = readq(&vp_reg->rxmac_vcfg0);
+
+	return;
+}
+
+/*
+ * vxge_hw_vpath_wait_receive_idle - Wait for Rx to become idle
+ */
+int vxge_hw_vpath_wait_receive_idle(struct __vxge_hw_device *hldev, u32 vp_id)
+{
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+	struct __vxge_hw_virtualpath *vpath;
+	u64 val64, rxd_count, rxd_spat;
+	int count = 0, total_count = 0;
+
+	vpath = &hldev->virtual_paths[vp_id];
+	vp_reg = vpath->vp_reg;
+
+	vxge_hw_vpath_set_zero_rx_frm_len(vp_reg);
+
+	/* Check that the ring controller for this vpath has enough free RxDs
+	 * to send frames to the host.  This is done by reading the
+	 * PRC_RXD_DOORBELL_VPn register and comparing the read value to the
+	 * RXD_SPAT value for the vpath.
+	 */
+	val64 = readq(&vp_reg->prc_cfg6);
+	rxd_spat = VXGE_HW_PRC_CFG6_GET_RXD_SPAT(val64) + 1;
+	/* Use a factor of 2 when comparing rxd_count against rxd_spat for some
+	 * leg room.
+	 */
+	rxd_spat *= 2;
+
+	do {
+		mdelay(1);
+
+		rxd_count = readq(&vp_reg->prc_rxd_doorbell);
+
+		/* Check that the ring controller for this vpath does
+		 * not have any frame in its pipeline.
+		 */
+		val64 = readq(&vp_reg->frm_in_progress_cnt);
+		if ((rxd_count <= rxd_spat) || (val64 > 0))
+			count = 0;
+		else
+			count++;
+		total_count++;
+	} while ((count < VXGE_HW_MIN_SUCCESSIVE_IDLE_COUNT) &&
+			(total_count < VXGE_HW_MAX_POLLING_COUNT));
+
+	if (total_count >= VXGE_HW_MAX_POLLING_COUNT)
+		printk(KERN_ALERT "%s: Still Receiving traffic. Abort wait\n",
+			__func__);
+
+	return total_count;
+}
+
+/* vxge_hw_device_wait_receive_idle - This function waits until all frames
+ * stored in the frame buffer for each vpath assigned to the given
+ * function (hldev) have been sent to the host.
+ */
+void vxge_hw_device_wait_receive_idle(struct __vxge_hw_device *hldev)
+{
+	int i, total_count = 0;
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+		if (!(hldev->vpaths_deployed & vxge_mBIT(i)))
+			continue;
+
+		total_count += vxge_hw_vpath_wait_receive_idle(hldev, i);
+		if (total_count >= VXGE_HW_MAX_POLLING_COUNT)
+			break;
+	}
+}
+
 /*
  * __vxge_hw_channel_allocate - Allocate memory for channel
  * This function allocates required memory for the channel and various arrays
@@ -217,7 +299,7 @@ __vxge_hw_device_register_poll(void __iomem *reg, u64 mask, u32 max_millis)
 	return ret;
 }
 
- /* __vxge_hw_device_vpath_reset_in_prog_check - Check if vpath reset
+/* __vxge_hw_device_vpath_reset_in_prog_check - Check if vpath reset
  * in progress
  * This routine checks the vpath reset in progress register is turned zero
  */
@@ -1006,7 +1088,6 @@ exit:
  * It can be used to set or reset Pause frame generation or reception
  * support of the NIC.
  */
-
 enum vxge_hw_status vxge_hw_device_setpause_data(struct __vxge_hw_device *hldev,
 						 u32 port, u32 tx, u32 rx)
 {
@@ -1250,7 +1331,6 @@ exit:
 /*
  * __vxge_hw_ring_create - Create a Ring
  * This function creates Ring and initializes it.
- *
  */
 enum vxge_hw_status
 __vxge_hw_ring_create(struct __vxge_hw_vpath_handle *vp,
diff --git a/drivers/net/vxge/vxge-config.h b/drivers/net/vxge/vxge-config.h
index 66c6773..eaa38e6 100644
--- a/drivers/net/vxge/vxge-config.h
+++ b/drivers/net/vxge/vxge-config.h
@@ -2276,4 +2276,11 @@ enum vxge_hw_status vxge_hw_vpath_rts_rth_set(
 
 enum vxge_hw_status
 __vxge_hw_device_is_privilaged(u32 host_type, u32 func_id);
+
+#define VXGE_HW_MIN_SUCCESSIVE_IDLE_COUNT 5
+#define VXGE_HW_MAX_POLLING_COUNT 100
+
+int vxge_hw_vpath_wait_receive_idle(struct __vxge_hw_device *hldev, u32 vp_id);
+
+void  vxge_hw_device_wait_receive_idle(struct __vxge_hw_device *hldev);
 #endif
diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c
index 8a59fe9..d977a63 100644
--- a/drivers/net/vxge/vxge-main.c
+++ b/drivers/net/vxge/vxge-main.c
@@ -1289,8 +1289,13 @@ void vxge_vpath_intr_enable(struct vxgedev *vdev, int vp_id)
 void vxge_vpath_intr_disable(struct vxgedev *vdev, int vp_id)
 {
 	struct vxge_vpath *vpath = &vdev->vpaths[vp_id];
+	struct __vxge_hw_device *hldev;
 	int msix_id;
 
+	hldev = (struct __vxge_hw_device *)pci_get_drvdata(vdev->pdev);
+
+	vxge_hw_vpath_wait_receive_idle(hldev, vpath->device_id);
+
 	vxge_hw_vpath_intr_disable(vpath->handle);
 
 	if (vdev->config.intr_type == INTA)
@@ -1420,6 +1425,7 @@ static int do_vxge_reset(struct vxgedev *vdev, int event)
 	}
 
 	if (event == VXGE_LL_FULL_RESET) {
+		vxge_hw_device_wait_receive_idle(vdev->devh);
 		vxge_hw_device_intr_disable(vdev->devh);
 
 		switch (vdev->cric_err_event) {
@@ -2068,7 +2074,7 @@ static irqreturn_t vxge_isr_napi(int irq, void *dev_id)
 		return IRQ_NONE;
 
 	if (unlikely(!is_vxge_card_up(vdev)))
-		return IRQ_NONE;
+		return IRQ_HANDLED;
 
 	status = vxge_hw_device_begin_irq(hldev, vdev->exec_mode,
 			&reason);
@@ -2775,7 +2781,6 @@ int do_vxge_close(struct net_device *dev, int do_io)
 	while (test_and_set_bit(__VXGE_STATE_RESET_CARD, &vdev->state))
 		msleep(50);
 
-	clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);
 	if (do_io) {
 		/* Put the vpath back in normal mode */
 		vpath_vector = vxge_mBIT(vdev->vpaths[0].device_id);
@@ -2819,6 +2824,11 @@ int do_vxge_close(struct net_device *dev, int do_io)
 
 	del_timer_sync(&vdev->vp_reset_timer);
 
+	if (do_io)
+		vxge_hw_device_wait_receive_idle(hldev);
+
+	clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);
+
 	/* Disable napi */
 	if (vdev->config.intr_type != MSI_X)
 		napi_disable(&vdev->napi);
@@ -2835,8 +2845,6 @@ int do_vxge_close(struct net_device *dev, int do_io)
 	if (do_io)
 		vxge_hw_device_intr_disable(vdev->devh);
 
-	mdelay(1000);
-
 	vxge_rem_isr(vdev);
 
 	vxge_napi_del_all(vdev);
diff --git a/drivers/net/vxge/vxge-reg.h b/drivers/net/vxge/vxge-reg.h
index 3dd5c96..93fd752 100644
--- a/drivers/net/vxge/vxge-reg.h
+++ b/drivers/net/vxge/vxge-reg.h
@@ -3998,6 +3998,7 @@ struct vxge_hw_vpath_reg {
 #define	VXGE_HW_PRC_CFG6_L4_CPC_TRSFR_CODE_EN	vxge_mBIT(9)
 #define VXGE_HW_PRC_CFG6_RXD_CRXDT(val) vxge_vBIT(val, 23, 9)
 #define VXGE_HW_PRC_CFG6_RXD_SPAT(val) vxge_vBIT(val, 36, 9)
+#define VXGE_HW_PRC_CFG6_GET_RXD_SPAT(val)	vxge_bVALn(val, 36, 9)
 /*0x00a78*/	u64	prc_cfg7;
 #define VXGE_HW_PRC_CFG7_SCATTER_MODE(val) vxge_vBIT(val, 6, 2)
 #define	VXGE_HW_PRC_CFG7_SMART_SCAT_EN	vxge_mBIT(11)
-- 
1.7.0.4


^ permalink raw reply related

* [PATCH 01/11] vxge: enable rxhash
From: Jon Mason @ 2010-11-04 22:51 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, Sivakumar Subramani, Sreenivasa Honnur, Ram Vepa

Enable RSS hashing and add ability to pass up the adapter calculated rx
hash up the network stack (if feature is available).  Add the ability to
enable/disable feature via ethtool, which requires that the adapter is
not running at the time.  Other miscellaneous cleanups and fixes
required to get RSS working.

Signed-off-by: Jon Mason <jon.mason@exar.com>
Signed-off-by: Ram Vepa <ram.vepa@exar.com>
---
 drivers/net/vxge/vxge-config.c  |    2 +
 drivers/net/vxge/vxge-config.h  |   12 ++++----
 drivers/net/vxge/vxge-ethtool.c |   35 +++++++++++++++++++++++++
 drivers/net/vxge/vxge-main.c    |   54 ++++++++++++++++++++++++--------------
 drivers/net/vxge/vxge-main.h    |   18 ++++++------
 drivers/net/vxge/vxge-traffic.h |   28 --------------------
 6 files changed, 86 insertions(+), 63 deletions(-)

diff --git a/drivers/net/vxge/vxge-config.c b/drivers/net/vxge/vxge-config.c
index 0e6db59..25f0938 100644
--- a/drivers/net/vxge/vxge-config.c
+++ b/drivers/net/vxge/vxge-config.c
@@ -3067,6 +3067,8 @@ enum vxge_hw_status vxge_hw_vpath_rts_rth_set(
 		     VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_ENTRY,
 		     VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_GEN_CFG,
 			0, &data0, &data1);
+	if (status != VXGE_HW_OK)
+		goto exit;
 
 	data0 &= ~(VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_BUCKET_SIZE(0xf) |
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_ALG_SEL(0x3));
diff --git a/drivers/net/vxge/vxge-config.h b/drivers/net/vxge/vxge-config.h
index 1a94343..66c6773 100644
--- a/drivers/net/vxge/vxge-config.h
+++ b/drivers/net/vxge/vxge-config.h
@@ -1418,12 +1418,12 @@ enum vxge_hw_rth_algoritms {
  * See also: vxge_hw_vpath_rts_rth_set(), vxge_hw_vpath_rts_rth_get().
  */
 struct vxge_hw_rth_hash_types {
-	u8 hash_type_tcpipv4_en;
-	u8 hash_type_ipv4_en;
-	u8 hash_type_tcpipv6_en;
-	u8 hash_type_ipv6_en;
-	u8 hash_type_tcpipv6ex_en;
-	u8 hash_type_ipv6ex_en;
+	u8 hash_type_tcpipv4_en:1,
+	   hash_type_ipv4_en:1,
+	   hash_type_tcpipv6_en:1,
+	   hash_type_ipv6_en:1,
+	   hash_type_tcpipv6ex_en:1,
+	   hash_type_ipv6ex_en:1;
 };
 
 u32
diff --git a/drivers/net/vxge/vxge-ethtool.c b/drivers/net/vxge/vxge-ethtool.c
index 05679e3..6194fd9 100644
--- a/drivers/net/vxge/vxge-ethtool.c
+++ b/drivers/net/vxge/vxge-ethtool.c
@@ -1119,6 +1119,40 @@ static int vxge_ethtool_get_sset_count(struct net_device *dev, int sset)
 	}
 }
 
+static int vxge_set_flags(struct net_device *dev, u32 data)
+{
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+	enum vxge_hw_status status;
+
+	if (data & ~ETH_FLAG_RXHASH)
+		return -EOPNOTSUPP;
+
+	if (!!(data & ETH_FLAG_RXHASH) == vdev->devh->config.rth_en)
+		return 0;
+
+	if (netif_running(dev) || (vdev->config.rth_steering == NO_STEERING))
+		return -EINVAL;
+
+	vdev->devh->config.rth_en = !!(data & ETH_FLAG_RXHASH);
+
+	/* Enabling RTH requires some of the logic in vxge_device_register and a
+	 * vpath reset.  Due to these restrictions, only allow modification
+	 * while the interface is down.
+	 */
+	status = vxge_reset_all_vpaths(vdev);
+	if (status != VXGE_HW_OK) {
+		vdev->devh->config.rth_en = !vdev->devh->config.rth_en;
+		return -EFAULT;
+	}
+
+	if (vdev->devh->config.rth_en)
+		dev->features |= NETIF_F_RXHASH;
+	else
+		dev->features &= ~NETIF_F_RXHASH;
+
+	return 0;
+}
+
 static const struct ethtool_ops vxge_ethtool_ops = {
 	.get_settings		= vxge_ethtool_gset,
 	.set_settings		= vxge_ethtool_sset,
@@ -1140,6 +1174,7 @@ static const struct ethtool_ops vxge_ethtool_ops = {
 	.phys_id		= vxge_ethtool_idnic,
 	.get_sset_count		= vxge_ethtool_get_sset_count,
 	.get_ethtool_stats	= vxge_get_ethtool_stats,
+	.set_flags		= vxge_set_flags,
 };
 
 void initialize_ethtool_ops(struct net_device *ndev)
diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c
index a69542e..8a59fe9 100644
--- a/drivers/net/vxge/vxge-main.c
+++ b/drivers/net/vxge/vxge-main.c
@@ -503,6 +503,13 @@ vxge_rx_1b_compl(struct __vxge_hw_ring *ringh, void *dtr,
 		else
 			skb_checksum_none_assert(skb);
 
+		/* rth_hash_type and rth_it_hit are non-zero regardless of
+		 * whether rss is enabled.  Only the rth_value is zero/non-zero
+		 * if rss is disabled/enabled, so key off of that.
+		 */
+		if (ext_info.rth_value)
+			skb->rxhash = ext_info.rth_value;
+
 		vxge_rx_complete(ring, skb, ext_info.vlan,
 			pkt_length, &ext_info);
 
@@ -1679,15 +1686,6 @@ static enum vxge_hw_status vxge_rth_configure(struct vxgedev *vdev)
 		mtable[index] = index % vdev->no_of_vpath;
 	}
 
-	/* Fill RTH hash types */
-	hash_types.hash_type_tcpipv4_en   = vdev->config.rth_hash_type_tcpipv4;
-	hash_types.hash_type_ipv4_en      = vdev->config.rth_hash_type_ipv4;
-	hash_types.hash_type_tcpipv6_en   = vdev->config.rth_hash_type_tcpipv6;
-	hash_types.hash_type_ipv6_en      = vdev->config.rth_hash_type_ipv6;
-	hash_types.hash_type_tcpipv6ex_en =
-					vdev->config.rth_hash_type_tcpipv6ex;
-	hash_types.hash_type_ipv6ex_en    = vdev->config.rth_hash_type_ipv6ex;
-
 	/* set indirection table, bucket-to-vpath mapping */
 	status = vxge_hw_vpath_rts_rth_itable_set(vdev->vp_handles,
 						vdev->no_of_vpath,
@@ -1700,12 +1698,21 @@ static enum vxge_hw_status vxge_rth_configure(struct vxgedev *vdev)
 		return status;
 	}
 
+	/* Fill RTH hash types */
+	hash_types.hash_type_tcpipv4_en   = vdev->config.rth_hash_type_tcpipv4;
+	hash_types.hash_type_ipv4_en      = vdev->config.rth_hash_type_ipv4;
+	hash_types.hash_type_tcpipv6_en   = vdev->config.rth_hash_type_tcpipv6;
+	hash_types.hash_type_ipv6_en      = vdev->config.rth_hash_type_ipv6;
+	hash_types.hash_type_tcpipv6ex_en =
+					vdev->config.rth_hash_type_tcpipv6ex;
+	hash_types.hash_type_ipv6ex_en    = vdev->config.rth_hash_type_ipv6ex;
+
 	/*
-	* Because the itable_set() method uses the active_table field
-	* for the target virtual path the RTH config should be updated
-	* for all VPATHs. The h/w only uses the lowest numbered VPATH
-	* when steering frames.
-	*/
+	 * Because the itable_set() method uses the active_table field
+	 * for the target virtual path the RTH config should be updated
+	 * for all VPATHs. The h/w only uses the lowest numbered VPATH
+	 * when steering frames.
+	 */
 	 for (index = 0; index < vdev->no_of_vpath; index++) {
 		status = vxge_hw_vpath_rts_rth_set(
 				vdev->vpaths[index].handle,
@@ -2586,6 +2593,8 @@ vxge_open(struct net_device *dev)
 			goto out2;
 		}
 	}
+	printk(KERN_INFO "%s: Receive Hashing Offload %s\n", dev->name,
+	       hldev->config.rth_en ? "enabled" : "disabled");
 
 	for (i = 0; i < vdev->no_of_vpath; i++) {
 		vpath = &vdev->vpaths[i];
@@ -3166,6 +3175,11 @@ int __devinit vxge_device_register(struct __vxge_hw_device *hldev,
 
 	initialize_ethtool_ops(ndev);
 
+	if (vdev->config.rth_steering != NO_STEERING) {
+		ndev->features |= NETIF_F_RXHASH;
+		hldev->config.rth_en = VXGE_HW_RTH_ENABLE;
+	}
+
 	/* Allocate memory for vpath */
 	vdev->vpaths = kzalloc((sizeof(struct vxge_vpath)) *
 				no_of_vpath, GFP_KERNEL);
@@ -4151,12 +4165,12 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre)
 	ll_config->fifo_indicate_max_pkts = VXGE_FIFO_INDICATE_MAX_PKTS;
 	ll_config->addr_learn_en = addr_learn_en;
 	ll_config->rth_algorithm = RTH_ALG_JENKINS;
-	ll_config->rth_hash_type_tcpipv4 = VXGE_HW_RING_HASH_TYPE_TCP_IPV4;
-	ll_config->rth_hash_type_ipv4 = VXGE_HW_RING_HASH_TYPE_NONE;
-	ll_config->rth_hash_type_tcpipv6 = VXGE_HW_RING_HASH_TYPE_NONE;
-	ll_config->rth_hash_type_ipv6 = VXGE_HW_RING_HASH_TYPE_NONE;
-	ll_config->rth_hash_type_tcpipv6ex = VXGE_HW_RING_HASH_TYPE_NONE;
-	ll_config->rth_hash_type_ipv6ex = VXGE_HW_RING_HASH_TYPE_NONE;
+	ll_config->rth_hash_type_tcpipv4 = 1;
+	ll_config->rth_hash_type_ipv4 = 0;
+	ll_config->rth_hash_type_tcpipv6 = 0;
+	ll_config->rth_hash_type_ipv6 = 0;
+	ll_config->rth_hash_type_tcpipv6ex = 0;
+	ll_config->rth_hash_type_ipv6ex = 0;
 	ll_config->rth_bkt_sz = RTH_BUCKET_SIZE;
 	ll_config->tx_pause_enable = VXGE_PAUSE_CTRL_ENABLE;
 	ll_config->rx_pause_enable = VXGE_PAUSE_CTRL_ENABLE;
diff --git a/drivers/net/vxge/vxge-main.h b/drivers/net/vxge/vxge-main.h
index d4be07e..8641822 100644
--- a/drivers/net/vxge/vxge-main.h
+++ b/drivers/net/vxge/vxge-main.h
@@ -145,15 +145,15 @@ struct vxge_config {
 
 	int		addr_learn_en;
 
-	int		rth_steering;
-	int		rth_algorithm;
-	int		rth_hash_type_tcpipv4;
-	int		rth_hash_type_ipv4;
-	int		rth_hash_type_tcpipv6;
-	int		rth_hash_type_ipv6;
-	int		rth_hash_type_tcpipv6ex;
-	int		rth_hash_type_ipv6ex;
-	int		rth_bkt_sz;
+	u32		rth_steering:2,
+			rth_algorithm:2,
+			rth_hash_type_tcpipv4:1,
+			rth_hash_type_ipv4:1,
+			rth_hash_type_tcpipv6:1,
+			rth_hash_type_ipv6:1,
+			rth_hash_type_tcpipv6ex:1,
+			rth_hash_type_ipv6ex:1,
+			rth_bkt_sz:8;
 	int		rth_jhash_golden_ratio;
 	int		tx_steering_type;
 	int 	fifo_indicate_max_pkts;
diff --git a/drivers/net/vxge/vxge-traffic.h b/drivers/net/vxge/vxge-traffic.h
index 6fa07d1..20fda17 100644
--- a/drivers/net/vxge/vxge-traffic.h
+++ b/drivers/net/vxge/vxge-traffic.h
@@ -1912,34 +1912,6 @@ enum vxge_hw_ring_tcode {
 	VXGE_HW_RING_T_CODE_MULTI_ERR			= 0xF
 };
 
-/**
- * enum enum vxge_hw_ring_hash_type - RTH hash types
- * @VXGE_HW_RING_HASH_TYPE_NONE: No Hash
- * @VXGE_HW_RING_HASH_TYPE_TCP_IPV4: TCP IPv4
- * @VXGE_HW_RING_HASH_TYPE_UDP_IPV4: UDP IPv4
- * @VXGE_HW_RING_HASH_TYPE_IPV4: IPv4
- * @VXGE_HW_RING_HASH_TYPE_TCP_IPV6: TCP IPv6
- * @VXGE_HW_RING_HASH_TYPE_UDP_IPV6: UDP IPv6
- * @VXGE_HW_RING_HASH_TYPE_IPV6: IPv6
- * @VXGE_HW_RING_HASH_TYPE_TCP_IPV6_EX: TCP IPv6 extension
- * @VXGE_HW_RING_HASH_TYPE_UDP_IPV6_EX: UDP IPv6 extension
- * @VXGE_HW_RING_HASH_TYPE_IPV6_EX: IPv6 extension
- *
- * RTH hash types
- */
-enum vxge_hw_ring_hash_type {
-	VXGE_HW_RING_HASH_TYPE_NONE			= 0x0,
-	VXGE_HW_RING_HASH_TYPE_TCP_IPV4		= 0x1,
-	VXGE_HW_RING_HASH_TYPE_UDP_IPV4		= 0x2,
-	VXGE_HW_RING_HASH_TYPE_IPV4			= 0x3,
-	VXGE_HW_RING_HASH_TYPE_TCP_IPV6		= 0x4,
-	VXGE_HW_RING_HASH_TYPE_UDP_IPV6		= 0x5,
-	VXGE_HW_RING_HASH_TYPE_IPV6			= 0x6,
-	VXGE_HW_RING_HASH_TYPE_TCP_IPV6_EX	= 0x7,
-	VXGE_HW_RING_HASH_TYPE_UDP_IPV6_EX	= 0x8,
-	VXGE_HW_RING_HASH_TYPE_IPV6_EX		= 0x9
-};
-
 enum vxge_hw_status vxge_hw_ring_rxd_reserve(
 	struct __vxge_hw_ring *ring_handle,
 	void **rxdh);
-- 
1.7.0.4


^ permalink raw reply related

* [PATCH] mac80211: Remove redundant checks for NULL before calls to crypto_free_cipher()
From: Jesper Juhl @ 2010-11-04 21:59 UTC (permalink / raw)
  To: linux-kernel
  Cc: John W. Linville, Johannes Berg, David S. Miller, linux-wireless,
	netdev

Hello,

crypto_free_cipher() is a wrapper around crypto_free_tfm() which is a 
wrapper around crypto_destroy_tfm() and the latter can handle being passed 
a NULL pointer, so checking for NULL in the 
ieee80211_aes_key_free()/ieee80211_aes_cmac_key_free() wrappers around 
crypto_free_cipher() is pointless and just increase object code size 
needlesly and makes us execute extra test/branch instructions that we 
don't need.
Btw; don't we have to many wrappers around wrappers ad nauseam here?
Anyway, this patch removes the redundant conditionals.

Signed-off-by: Jesper Juhl <jj@chaosbits.net>
---
 aes_ccm.c  |    3 +--
 aes_cmac.c |    3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c
index d2b03e0..4bd6ef0 100644
--- a/net/mac80211/aes_ccm.c
+++ b/net/mac80211/aes_ccm.c
@@ -147,6 +147,5 @@ struct crypto_cipher *ieee80211_aes_key_setup_encrypt(const u8 key[])
 
 void ieee80211_aes_key_free(struct crypto_cipher *tfm)
 {
-	if (tfm)
-		crypto_free_cipher(tfm);
+	crypto_free_cipher(tfm);
 }
diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c
index b4d66cc..d502b26 100644
--- a/net/mac80211/aes_cmac.c
+++ b/net/mac80211/aes_cmac.c
@@ -128,6 +128,5 @@ struct crypto_cipher * ieee80211_aes_cmac_key_setup(const u8 key[])
 
 void ieee80211_aes_cmac_key_free(struct crypto_cipher *tfm)
 {
-	if (tfm)
-		crypto_free_cipher(tfm);
+	crypto_free_cipher(tfm);
 }



-- 
Jesper Juhl <jj@chaosbits.net>             http://www.chaosbits.net/
Plain text mails only, please      http://www.expita.com/nomime.html
Don't top-post  http://www.catb.org/~esr/jargon/html/T/top-post.html

^ permalink raw reply related

* [PATCH] classifier: report statistics for basic classifier
From: Stephen Hemminger @ 2010-11-04 21:47 UTC (permalink / raw)
  To: David Miller; +Cc: netdev

The basic classifier keeps statistics but does not report it to user space.
This showed up when using basic classifier (with police) as a default catch
all on ingress; no statistics were reported.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>

---
I consider this a bug and should go into net-2.6 but not stable.

 net/sched/cls_basic.c |    4 ++++
 1 file changed, 4 insertions(+)

--- a/net/sched/cls_basic.c	2010-11-04 16:06:19.984953193 -0400
+++ b/net/sched/cls_basic.c	2010-11-04 16:06:42.248953192 -0400
@@ -268,6 +268,10 @@ static int basic_dump(struct tcf_proto *
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
+
+	if (tcf_exts_dump_stats(skb, &f->exts, &basic_ext_map) < 0)
+		goto nla_put_failure;
+
 	return skb->len;
 
 nla_put_failure:

^ permalink raw reply

* Re: [RFC PATCH 1/1] vhost: TX used buffer guest signal accumulation
From: Shirley Ma @ 2010-11-04 21:37 UTC (permalink / raw)
  To: Michael S. Tsirkin; +Cc: David Miller, netdev, kvm, linux-kernel
In-Reply-To: <20101104093045.GA27506@redhat.com>

On Thu, 2010-11-04 at 11:30 +0200, Michael S. Tsirkin wrote:
> One thing to note is that deferred signalling needs to be
> benchmarked with old guests which don't orphan skbs on xmit
> (or disable orphaning in both networking stack and virtio-net).

Yes, we need run more test.

> 
> OK, so I guess I'll queue the __put_user etc patches for net-next, on
> top of this
> I think a patch which defers signalling would be nice to have,
> then we can figure out whether a separate heads array still has
> benefits
> for non zero copy case: if yes what they are, if no whether it should
> be
> used for zero copy only for both both non-zero copy and zero copy.
> 
> Makes sense? 

Agree.

Shirley

^ permalink raw reply

* Re: [PATCH 0/15] RFC: create drivers/net/legacy for ISA, EISA, MCA drivers
From: Paul Gortmaker @ 2010-11-04 21:20 UTC (permalink / raw)
  To: jeffrey.t.kirsher
  Cc: Joe Perches, davem@davemloft.net, netdev@vger.kernel.org
In-Reply-To: <1288396919.15283.23.camel@jtkirshe-MOBL1>

On 10-10-29 08:01 PM, Jeff Kirsher wrote:
> On Fri, 2010-10-29 at 15:08 -0700, Joe Perches wrote:
>> On Fri, 2010-10-29 at 17:26 -0400, Paul Gortmaker wrote:
>>> On 10-10-28 09:48 PM, Joe Perches wrote:
>>>> On Thu, 2010-10-28 at 21:19 -0400, Paul Gortmaker wrote:
>>>>> The drivers/net dir has a lot of files - originally there were
>>>>> no subdirs, but at least now subdirs are being used effectively.
>>>>> But the original drivers from 10+ years ago are still right
>>>>> there at the top.  This series creates a drivers/net/legacy dir.
>>>> I like this idea.
>>>> I suggest a bit of a further grouping by using a
>>>> drivers/net/ethernet directory and putting those
>>>> legacy drivers in a new subdirectory
>>>> drivers/net/ethernet/legacy.
>>> That is a substantially larger change, since you'd now be
>>> relocating nearly every remaining driver, i.e. all the
>>> relatively modern 100M and GigE drivers.
>>
> 
> I am not particularly a fan of making a "legacy" directory and moving
> old drivers into it.  Just because this is very subjective, if you say
> "drivers which are X years old and not used much" is vague and depending
> on who you ask would get varying results.  But if you were to were to
> define legacy as all ISA, EISA and MCA drivers (not based on their use)
> would be better.

I think that being subjective can be an advantage.  There may
be some debate on whether X is legacy or not, but I see no harm
in that.  On the other hand, I see binding ourselves to concrete
inflexible rules as a disadvantage.

For example, look at the sister directory, drivers/serial -- the
venerable 8250 UART continues to support ISA-like mapped 0x3f8/0x2f8
PIO devices such as those on the ISA MultiIO/IDE cards first appearing
in 80286 computers.  But we probably don't want to shuffle that off to
a legacy dir, given that nearly every embedded CPU manufacturer has a
SoC 8250 UART implementation of their own, and it remains in high use.

> 
> But if a legacy directory was to be made, I like Joe's suggestion of
> drivers/net/ethernet/legacy.

If we extend that to being a rule, i.e. drivers/net/*/legacy
then we'd implicitly be advocating creation of things like:

	drivers/net/tokenring/legacy
	drivers/net/arcnet/legacy

Yes, I do imagine you aren't suggesting we do that.  :)

> 
>> Files to not need immediate renames.
>>
>> Renames could happen when the appropriate maintainer
>> wants to or gets coerced to conform to some new
>> file layout standard.
>>
>> I had submitted a related RFC patch:
>>
>> https://patchwork.kernel.org/patch/244641/
>>
>> and then had some off list discussions
>> with Jeff Kirsher from Intel.
>>
>> Perhaps Jeff will chime in.
>>
>>> Plus what do you
>>> do with the sb1000 - create drivers/cablemodem/legacy
>>> just for one file?
>>
>> I never looked at that particular driver before.
>> Maybe.  I don't have a strong opinion.  Leaving
>> it where it is might be OK.
>>
>>> Or the ethernet drivers already in
>>> existing subdirs, like arm and pcmcia -- do we move those?
>>
>> Maybe.  If there's no demand, there's no absolute need to
>> move it at all.  I think a reasonable goal is to have some
>> sensible and consistent file layout scheme though.
>>
>> There are arch specific directories under various drivers/...
>> so I don't see a need to move directories like drivers/net/arm
>> or drivers/s390.
> 
> I agree with Joe.

I don't think there is any disagreement here on this point.
Moving stuff that is already in an appropriate subdir was
never part of what I was proposing with drivers/legacy.

But if we create subdirs with concrete definitions, then
people will most likely be expecting all drivers that match
to be in that specific subdir.

> 
>>
>>> With this, I tried to aim for a significant gain (close to 1/3
>>> less files) within what I felt was a reasonable sized change
>>> set that had a chance of getting an overall OK from folks.
>>> Giant "flag-day" type mammoth changesets are a PITA for all.
>>
>> I believe there's no need for a flag-day.
>> File renames could happen gradually or not at all.
>>
>>
> 
> Again I agree with Joe.

Sure, renames can be async, and driven by the individual
maintainers of the files, but typically when conversion
like events are left open ended (timewise) they tend
to drag on for longer times than necessary.  At least in
my experience.  If I had sent the RFC with one patch that
amounted to a "mkdir", and no actual file moves, I wouldn't
have expected much other than a bagful of scorn in return. :)
Putting it to use and showing a real cleanup is where the
value became really apparent, I think.

In any case, I still think this is worthwhile, and in the
absence of an alternate proposal that gets a higher level
of universal agreement, I'm hoping we can still do this.
I've got a follow on commit ready that factors a lot of
the legacy related probe code out of Space.c too.

Regardless of which way it goes, thanks for the feedback.
Paul.

^ permalink raw reply

* Re: [PATCH] net: reset gso header when the copied skb is linearized
From: Flavio Leitner @ 2010-11-04 20:35 UTC (permalink / raw)
  To: David Miller; +Cc: netdev, herbert
In-Reply-To: <20101026.122801.52191238.davem@davemloft.net>

On Tue, Oct 26, 2010 at 12:28:01PM -0700, David Miller wrote:
> From: Flavio Leitner <fleitner@redhat.com>
> Date: Tue, 26 Oct 2010 17:25:11 -0200
> 
> > If I understand that correctly, the gso_segs is the number
> > of GSO segments which are divided in non-linear way. When the
> > copy is made using that function, the skb turns into a big
> > one segment inlined. So, the idea of segments is lost and
> > I'm not seeing how it is going to be divided again. 
> > Later the NIC drives does, for example:
> 
> GSO has nothing to do with linearity, although it just so happens
> to be that GSO packets tend to be non-linear due to the way
> TCP builds such frames.
> 
> The GSO segment count is the number of MSS sized frames are
> contained inside of a larger than MSS sized SKB.
> 
> That is it.  So the definition and meaning is independent of
> linearity.
> 
> Thus, if we linearize a larger than MSS sized frame, it should still
> have the same GSO attributes.

It makes sense, thanks for the explanation.
Please ignore the proposed patch.

thanks again,
-- 
Flavio

^ permalink raw reply

* Re: tap0 device stopped working in 2.6.36 (ok in 2.6.35)
From: Jim @ 2010-11-04 20:17 UTC (permalink / raw)
  To: Nolan Leake; +Cc: netdev
In-Reply-To: <1288825835.26640.517.camel@voxel>

On 11/04/2010 12:10 AM, Nolan Leake wrote:
> On Wed, 2010-10-27 at 18:09 +0200, Jim wrote:
>> Not exactly, VirtualBox calls it "bridged adapter", it 'bridges' the
>> guest machine to the tap0 interface on the host for so called host-only
>> networking.
>> See eg. http://forums.virtualbox.org/viewtopic.php?f=1&t=165
>>
>> And this sequence is now simply failing
>>   tunctl -t tap0 -u tuxuser
>>   ifconfig tap0 10.0.0.1 up
> 
> Jim,
> 
> Could you do me a favor and try this sequence:
>   tunctl -t tap0 -u tuxuser
>   <run virtualbox such that it attaches to tap0>
>   ifconfig tap0 10.0.0.1 up
> 
> Thanks,
>  - nolan
> 

Doesn't really work, virtualbox complaints loudly the tap0 device is
down, ignoring that after virtual machine is up-n-running, the
	ifconfig tap0 192.168.20.1 up
still gives  ADDRCONF(NETDEV_UP): tap0: link is not ready

Using wireshark I see guest machine is sending dhcp request but no
message is sent out from the host as before.


^ permalink raw reply

* netlink_carrier_on() race condition?
From: Eliad Peller @ 2010-11-04 19:43 UTC (permalink / raw)
  To: netdev

hi,

i might be missing something, but i think there is some race condition
in netlink_carrier_on():
when calling it, it clears the __LINK_STATE_NOCARRIER flag and
enqueues a work to do everything needed.
this cause a period, in which  __LINK_STATE_NOCARRIER is unset (which
implies IFF_LOWER_UP), but the default qdiscs are not attached yet
(since the work hasn't been executed yet).
userspace might get some netlink events (e.g. wireless wext) in which
the IFF_LOWER_UP flag is set, but the queues are not ready.

shouldn't we clear the flag only after all the work is done?

thanks,
Eliad.

^ permalink raw reply

* Re: [PATCH 2/2] inet_diag: Make sure we actually run the same bytecode we audited.
From: David Miller @ 2010-11-04 19:26 UTC (permalink / raw)
  To: tgraf; +Cc: nelhage, netdev
In-Reply-To: <20101104132802.GA2904@canuck.infradead.org>

From: Thomas Graf <tgraf@infradead.org>
Date: Thu, 4 Nov 2010 09:28:02 -0400

> On Wed, Nov 03, 2010 at 10:35:41PM -0400, Nelson Elhage wrote:
>> We were using nlmsg_find_attr() to look up the bytecode by attribute when
>> auditing, but then just using the first attribute when actually running
>> bytecode. So, if we received a message with two attribute elements, where only
>> the second had type INET_DIAG_REQ_BYTECODE, we would validate and run different
>> bytecode strings.
>> 
>> Fix this by consistently using nlmsg_find_attr everywhere.
>> 
>> Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
> 
> Both patches look good.
> 
> Signed-off-by: Thomas Graf <tgraf@infradead.org>

Applied.

^ permalink raw reply

* Re: [PATCH 1/2] netlink: Make nlmsg_find_attr take a const nlmsghdr*.
From: David Miller @ 2010-11-04 19:26 UTC (permalink / raw)
  To: nelhage; +Cc: netdev
In-Reply-To: <1288838141-17871-1-git-send-email-nelhage@ksplice.com>

From: Nelson Elhage <nelhage@ksplice.com>
Date: Wed,  3 Nov 2010 22:35:40 -0400

> This will let us use it on a nlmsghdr stored inside a netlink_callback.
> 
> Signed-off-by: Nelson Elhage <nelhage@ksplice.com>

Applied.

^ permalink raw reply

* Re: [PATCH 4/4] crypto: algif_skcipher - User-space interface for skcipher operations
From: David Miller @ 2010-11-04 19:23 UTC (permalink / raw)
  To: herbert; +Cc: linux-crypto, netdev, linux-kernel
In-Reply-To: <E1PE3jY-0000Ml-7B@gondolin.me.apana.org.au>

From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 04 Nov 2010 12:36:20 -0500

> crypto: algif_skcipher - User-space interface for skcipher operations
> 
> This patch adds the af_alg plugin for symmetric key ciphers,
> corresponding to the ablkcipher kernel operation type.
> 
> Keys can optionally be set through the setsockopt interface.
> 
> Once a sendmsg call occurs without MSG_MORE no further writes
> may be made to the socket until all previous data has been read.
> 
> IVs and and whether encryption/decryption is performed can be
> set through the setsockopt interface or as a control message
> to sendmsg.
> 
> The interface is completely synchronous, all operations are
> carried out in recvmsg(2) and will complete prior to the system
> call returning.
> 
> The splice(2) interface support reading the user-space data directly
> without copying (except that the Crypto API itself may copy the data
> if alignment is off).
> 
> The recvmsg(2) interface supports directly writing to user-space
> without additional copying, i.e., the kernel crypto interface will
> receive the user-space address as its output SG list.
> 
> Thakns to Miloslav Trmac for reviewing this and contributing
> fixes and improvements.
> 
> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

Acked-by: David S. Miller <davem@davemloft.net>

^ permalink raw reply

* Re: [PATCH 3/4] crypto: algif_hash - User-space interface for hash operations
From: David Miller @ 2010-11-04 19:23 UTC (permalink / raw)
  To: herbert; +Cc: linux-crypto, netdev, linux-kernel
In-Reply-To: <E1PE3jX-0000MX-UB@gondolin.me.apana.org.au>

From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 04 Nov 2010 12:36:19 -0500

> crypto: algif_hash - User-space interface for hash operations
> 
> This patch adds the af_alg plugin for hash, corresponding to
> the ahash kernel operation type.
> 
> Keys can optionally be set through the setsockopt interface.
> 
> Each sendmsg call will finalise the hash unless sent with a MSG_MORE
> flag.
> 
> Partial hash states can be cloned using accept(2).
> 
> The interface is completely synchronous, all operations will
> complete prior to the system call returning.
> 
> Both sendmsg(2) and splice(2) support reading the user-space
> data directly without copying (except that the Crypto API itself
> may copy the data if alignment is off).
> 
> For now only the splice(2) interface supports performing digest
> instead of init/update/final.  In future the sendmsg(2) interface
> will also be modified to use digest/finup where possible so that
> hardware that cannot return a partial hash state can still benefit
> from this interface.
> 
> Thakns to Miloslav Trmac for reviewing this and contributing
> fixes and improvements.
> 
> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

Acked-by: David S. Miller <davem@davemloft.net>

^ permalink raw reply

* Re: [PATCH 2/4] crypto: af_alg - User-space interface for Crypto API
From: David Miller @ 2010-11-04 19:23 UTC (permalink / raw)
  To: herbert; +Cc: linux-crypto, netdev, linux-kernel
In-Reply-To: <E1PE3jX-0000MM-MP@gondolin.me.apana.org.au>

From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 04 Nov 2010 12:36:19 -0500

> crypto: af_alg - User-space interface for Crypto API
> 
> This patch creates the backbone of the user-space interface for
> the Crypto API, through a new socket family AF_ALG.
> 
> Each session corresponds to one or more connections obtained from
> that socket.  The number depends on the number of inputs/outputs
> of that particular type of operation.  For most types there will
> be a s ingle connection/file descriptor that is used for both input
> and output.  AEAD is one of the few that require two inputs.
> 
> Each algorithm type will provide its own implementation that plugs
> into af_alg.  They're keyed using a string such as "skcipher" or
> "hash".
> 
> IOW this patch only contains the boring bits that is required
> to hold everything together.
> 
> Thakns to Miloslav Trmac for reviewing this and contributing
> fixes and improvements.
> 
> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

Acked-by: David S. Miller <davem@davemloft.net>

^ permalink raw reply

* Re: [PATCH 1/4] net - Add AF_ALG macros
From: David Miller @ 2010-11-04 19:22 UTC (permalink / raw)
  To: herbert; +Cc: linux-crypto, netdev, linux-kernel
In-Reply-To: <E1PE3jX-0000M8-FP@gondolin.me.apana.org.au>

From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 04 Nov 2010 12:36:19 -0500

> net - Add AF_ALG macros
> 
> This patch adds the socket family/level macros for the yet-to-be-born
> AF_ALG family.  The AF_ALG family provides the user-space interface
> for the kernel crypto API.
> 
> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

Acked-by: David S. Miller <davem@davemloft.net>

^ permalink raw reply

* Re: Freeing alive fib_info caused by ebc0ffae5
From: David Miller @ 2010-11-04 19:06 UTC (permalink / raw)
  To: michael; +Cc: eric.dumazet, netdev
In-Reply-To: <1288870526.30549.19.camel@concordia>

From: Michael Ellerman <michael@ellerman.id.au>
Date: Thu, 04 Nov 2010 22:35:26 +1100

> On Thu, 2010-11-04 at 12:21 +0100, Eric Dumazet wrote:
>> [PATCH] fib: fib_result_assign() should not change fib refcounts
>> 
>> After commit ebc0ffae5 (RCU conversion of fib_lookup()),
>> fib_result_assign()  should not change fib refcounts anymore.
>> 
>> Thanks to Michael who did the bisection and bug report.
 ...
> Perfect, that fixes it, thanks!

Applied, thanks everyone!

^ permalink raw reply

* Re: [RFC][net-next-2.6 PATCH 2/4] net: 8021Q consolidate header_ops routines
From: Jesse Gross @ 2010-11-04 18:26 UTC (permalink / raw)
  To: John Fastabend; +Cc: netdev@vger.kernel.org
In-Reply-To: <4CD2B883.30808@intel.com>

On Thu, Nov 4, 2010 at 6:43 AM, John Fastabend
<john.r.fastabend@intel.com> wrote:
> On 11/3/2010 5:47 PM, Jesse Gross wrote:
>> On Thu, Oct 21, 2010 at 3:10 PM, John Fastabend
>> <john.r.fastabend@intel.com> wrote:
>>> The only thing the 8021Q header ops routines are required
>>> for is the VLAN_FLAG_REORDER_HDR otherwise by the time
>>> the VLAN tag has been added the packet is already on
>>> its way down the stack. In this case using the Ethernet
>>> ops works OK.
>>>
>>> At present the VLAN_FLAG_REORDER_HDR flag does not work
>>> with vlan offloads. As I understand the flag the intent
>>> is to allow taps on the vlan device and possibly the
>>> QOS layer to see the vlan tag info.
>>>
>>> By inserting the tag in vlan_tci any taps or QOS policies
>>> should be able to retrieve the vlan info. This allows
>>> the flag to work the same in both the offload case and
>>> non-offloaded case. And allows us to use the underlying
>>> ethernet ops.
>>>
>>> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
>>
>> I noticed that you dropped this patch from your most recent series, so
>> I went back to take a look at it.  I realized that it probably works
>> inconsistently since header caching doesn't take into account
>> skb->vlan_tci, so whether you see the tag depends on the state of the
>> cache.
>>
>> It would be really good to have this type of code consolidation, both
>> for the sake of sanity and to eliminate the inconsistent behavior.  We
>> could do that by either not using header caching or making it work
>> with vlan offloading somehow.  However, I'm not sure that there's
>> really much point in that.  VLAN_FLAG_REORDER_HDR doesn't work with
>> cards that do vlan offloading, which is a pretty significant number of
>> them.  It similarly works inconsistently on the rx side.  So it's
>> broken most of the time and worse, the behavior changes depending on
>> the NIC (and now the ethtool setting).  Can we just eliminate it?
>
> Yes this is why I have dropped it for now. Also rebuild is broke as best I can tell. Although I doubt anyone would notice you would need to clear VLAN_FLAG_REORDER_HDR and be using one of the ARPHRD_{ROSE|AX25|NETROM}.
>
> The problem with caching the vlan header is the skb priority to vlan priority map. So we could cache the vid, sa, da, and protocols but I can not see anyway to cache the vlan priority. Also the cache would have to be flushed when the flag is toggled.

I agree, fixing this so that !VLAN_FLAG_REORDER_HDR works correctly in
all cases would be messy.

However, this has been broken for a long time and I don't know of
anyone complaining.  Since it is already a no-op in the accelerated
case, I would like to just drop the flag so we get consistent behavior
and less code.

^ permalink raw reply

* [PATCH 4/4] crypto: algif_skcipher - User-space interface for skcipher operations
From: Herbert Xu @ 2010-11-04 17:36 UTC (permalink / raw)
  To: Linux Crypto Mailing List, netdev, Linux Kernel Mailing List
In-Reply-To: <20101104173456.GA1321@gondor.apana.org.au>

crypto: algif_skcipher - User-space interface for skcipher operations

This patch adds the af_alg plugin for symmetric key ciphers,
corresponding to the ablkcipher kernel operation type.

Keys can optionally be set through the setsockopt interface.

Once a sendmsg call occurs without MSG_MORE no further writes
may be made to the socket until all previous data has been read.

IVs and and whether encryption/decryption is performed can be
set through the setsockopt interface or as a control message
to sendmsg.

The interface is completely synchronous, all operations are
carried out in recvmsg(2) and will complete prior to the system
call returning.

The splice(2) interface support reading the user-space data directly
without copying (except that the Crypto API itself may copy the data
if alignment is off).

The recvmsg(2) interface supports directly writing to user-space
without additional copying, i.e., the kernel crypto interface will
receive the user-space address as its output SG list.

Thakns to Miloslav Trmac for reviewing this and contributing
fixes and improvements.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---

 crypto/Kconfig          |    8 
 crypto/Makefile         |    1 
 crypto/algif_skcipher.c |  647 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 656 insertions(+)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 6db27d7..69437e2 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -852,6 +852,14 @@ config CRYPTO_USER_API_HASH
 	  This option enables the user-spaces interface for hash
 	  algorithms.
 
+config CRYPTO_USER_API_SKCIPHER
+	tristate "User-space interface for symmetric key cipher algorithms"
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_USER_API
+	help
+	  This option enables the user-spaces interface for symmetric
+	  key cipher algorithms.
+
 source "drivers/crypto/Kconfig"
 
 endif	# if CRYPTO
diff --git a/crypto/Makefile b/crypto/Makefile
index 14ab405..efc0f18 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -87,6 +87,7 @@ obj-$(CONFIG_CRYPTO_TEST) += tcrypt.o
 obj-$(CONFIG_CRYPTO_GHASH) += ghash-generic.o
 obj-$(CONFIG_CRYPTO_USER_API) += af_alg.o
 obj-$(CONFIG_CRYPTO_USER_API_HASH) += algif_hash.o
+obj-$(CONFIG_CRYPTO_USER_API_SKCIPHER) += algif_skcipher.o
 
 #
 # generic algorithms and the async_tx api
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
new file mode 100644
index 0000000..abc15b2
--- /dev/null
+++ b/crypto/algif_skcipher.c
@@ -0,0 +1,647 @@
+/*
+ * algif_skcipher: User-space interface for skcipher algorithms
+ *
+ * This file provides the user-space API for symmetric key ciphers.
+ *
+ * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/skcipher.h>
+#include <crypto/if_alg.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <net/sock.h>
+
+struct skcipher_sg_list {
+	struct list_head list;
+
+	int cur;
+
+	struct scatterlist sg[0];
+};
+
+struct skcipher_ctx {
+	struct list_head tsgl;
+	struct af_alg_sgl rsgl;
+
+	void *iv;
+
+	struct af_alg_completion completion;
+
+	unsigned used;
+
+	unsigned int len;
+	bool more;
+	bool merge;
+	bool enc;
+
+	struct ablkcipher_request req;
+};
+
+#define MAX_SGL_ENTS ((PAGE_SIZE - sizeof(struct skcipher_sg_list)) / \
+		      sizeof(struct scatterlist) - 1)
+
+static inline bool skcipher_writable(struct sock *sk)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct skcipher_ctx *ctx = ask->private;
+
+	return ctx->used + PAGE_SIZE <= max_t(int, sk->sk_sndbuf, PAGE_SIZE);
+}
+
+static int skcipher_alloc_sgl(struct sock *sk, int size)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct skcipher_ctx *ctx = ask->private;
+	struct skcipher_sg_list *sgl;
+	struct scatterlist *sg = NULL;
+
+	sgl = list_first_entry(&ctx->tsgl, struct skcipher_sg_list, list);
+	if (!list_empty(&ctx->tsgl))
+		sg = sgl->sg;
+
+	if (!sg || sgl->cur >= MAX_SGL_ENTS) {
+		sgl = sock_kmalloc(sk, sizeof(*sgl) +
+				       sizeof(sgl->sg[0]) * (MAX_SGL_ENTS + 1),
+				   GFP_KERNEL);
+		if (!sgl)
+			return -ENOMEM;
+
+		sg_init_table(sgl->sg, MAX_SGL_ENTS + 1);
+		sgl->cur = 0;
+
+		if (sg)
+			sg_chain(sg, MAX_SGL_ENTS + 1, sgl->sg);
+
+		list_add_tail(&sgl->list, &ctx->tsgl);
+	}
+
+	return 0;
+}
+
+static void skcipher_pull_sgl(struct sock *sk, int used)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct skcipher_ctx *ctx = ask->private;
+	struct skcipher_sg_list *sgl;
+	struct scatterlist *sg;
+	int i;
+
+	while (!list_empty(&ctx->tsgl)) {
+		sgl = list_first_entry(&ctx->tsgl, struct skcipher_sg_list,
+				       list);
+		sg = sgl->sg;
+
+		for (i = 0; i < sgl->cur; i++) {
+			int plen = min_t(int, used, sg[i].length);
+
+			if (!sg_page(sg + i))
+				continue;
+
+			if (!used)
+				return;
+
+			sg[i].length -= plen;
+			sg[i].offset += plen;
+
+			if (!sg[i].length) {
+				put_page(sg_page(sg + i));
+				sg_assign_page(sg + i, NULL);
+			}
+
+			used -= plen;
+			ctx->used -= plen;
+		}
+
+		list_del(&sgl->list);
+		sock_kfree_s(sk, sgl,
+			     sizeof(*sgl) + sizeof(sgl->sg[0]) *
+					    (MAX_SGL_ENTS + 1));
+	}
+
+	if (!ctx->used)
+		ctx->merge = 0;
+}
+
+static void skcipher_free_sgl(struct sock *sk)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct skcipher_ctx *ctx = ask->private;
+
+	skcipher_pull_sgl(sk, ctx->used);
+}
+
+static int skcipher_wait_for_wmem(struct sock *sk, unsigned flags)
+{
+	DEFINE_WAIT(wait);
+	int err = -ERESTARTSYS;
+
+	if (flags & MSG_DONTWAIT)
+		return -EAGAIN;
+
+	set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+
+	for (;;) {
+		if (signal_pending(current))
+			break;
+		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+		if (skcipher_writable(sk)) {
+			err = 0;
+			break;
+		}
+		schedule();
+	}
+	finish_wait(sk_sleep(sk), &wait);
+
+	return err;
+}
+
+static void skcipher_wmem_wakeup(struct sock *sk)
+{
+	struct socket_wq *wq;
+
+	if (!skcipher_writable(sk))
+		return;
+
+	rcu_read_lock();
+	wq = rcu_dereference(sk->sk_wq);
+	if (wq_has_sleeper(wq))
+		wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
+							   POLLRDNORM |
+							   POLLRDBAND);
+	sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+	rcu_read_unlock();
+}
+
+static int skcipher_wait_for_data(struct sock *sk, unsigned flags)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct skcipher_ctx *ctx = ask->private;
+	DEFINE_WAIT(wait);
+	int err = -ERESTARTSYS;
+
+	if (flags & MSG_DONTWAIT) {
+		return -EAGAIN;
+	}
+
+	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+
+	for (;;) {
+		if (signal_pending(current))
+			break;
+		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+		if (ctx->used) {
+			err = 0;
+			break;
+		}
+		schedule();
+	}
+	finish_wait(sk_sleep(sk), &wait);
+
+	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+
+	return err;
+}
+
+static void skcipher_data_wakeup(struct sock *sk)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct skcipher_ctx *ctx = ask->private;
+	struct socket_wq *wq;
+
+	if (!ctx->used);
+		return;
+
+	rcu_read_lock();
+	wq = rcu_dereference(sk->sk_wq);
+	if (wq_has_sleeper(wq))
+		wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
+							   POLLRDNORM |
+							   POLLRDBAND);
+	sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
+	rcu_read_unlock();
+}
+
+static int skcipher_sendmsg(struct kiocb *unused, struct socket *sock,
+			    struct msghdr *msg, size_t size)
+{
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	struct skcipher_ctx *ctx = ask->private;
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(&ctx->req);
+	unsigned ivsize = crypto_ablkcipher_ivsize(tfm);
+	struct skcipher_sg_list *sgl;
+	struct af_alg_control con = {};
+	long copied = 0;
+	bool enc = 0;
+	int limit;
+	int err;
+	int i;
+
+	if (msg->msg_controllen) {
+		err = af_alg_cmsg_send(msg, &con);
+		if (err)
+			return err;
+
+		switch (con.op) {
+		case ALG_OP_ENCRYPT:
+			enc = 1;
+			break;
+		case ALG_OP_DECRYPT:
+			enc = 0;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		if (con.iv && con.iv->ivlen != ivsize)
+			return -EINVAL;
+	}
+
+	err = -EINVAL;
+
+	lock_sock(sk);
+	if (!ctx->more && ctx->used)
+		goto unlock;
+
+	if (!ctx->used) {
+		ctx->enc = enc;
+		if (con.iv)
+			memcpy(ctx->iv, con.iv->iv, ivsize);
+	}
+
+	limit = max_t(int, sk->sk_sndbuf, PAGE_SIZE);
+	limit -= ctx->used;
+
+	while (size) {
+		struct scatterlist *sg;
+		unsigned long len = size;
+		int plen;
+
+		if (ctx->merge) {
+			sgl = list_entry(ctx->tsgl.prev,
+					 struct skcipher_sg_list, list);
+			sg = sgl->sg + sgl->cur - 1;
+			len = min_t(unsigned long, len, PAGE_SIZE - sg->length);
+
+			err = memcpy_fromiovec(page_address(sg_page(sg)) +
+					       sg->length, msg->msg_iov, len);
+			if (err)
+				goto unlock;
+
+			sg->length += len;
+			ctx->merge = sg->length & (PAGE_SIZE - 1);
+
+			size -= len;
+			copied += len;
+			continue;
+		}
+
+		if (limit < PAGE_SIZE) {
+			release_sock(sk);
+			err = skcipher_wait_for_wmem(sk, msg->msg_flags);
+			lock_sock(sk);
+			if (err)
+				goto unlock;
+
+			limit = max_t(int, sk->sk_sndbuf, PAGE_SIZE);
+			limit -= ctx->used;
+		}
+
+		len = min_t(unsigned long, len, limit);
+
+		err = skcipher_alloc_sgl(sk, len);
+		if (err)
+			goto unlock;
+
+		sgl = list_first_entry(&ctx->tsgl, struct skcipher_sg_list,
+				       list);
+		sg = sgl->sg;
+		do {
+			i = sgl->cur;
+			plen = min_t(int, len, PAGE_SIZE);
+
+			sg_assign_page(sg + i, alloc_page(GFP_KERNEL));
+			err = -ENOMEM;
+			if (!sg_page(sg + i))
+				goto unlock;
+
+			err = memcpy_fromiovec(page_address(sg_page(sg + i)),
+					       msg->msg_iov, plen);
+			if (err) {
+				__free_page(sg_page(sg + i));
+				sg_assign_page(sg + i, NULL);
+				goto unlock;
+			}
+
+			sg[i].length = plen;
+			len -= plen;
+			ctx->used += plen;
+			copied += plen;
+			size -= plen;
+			limit -= plen;
+			sgl->cur++;
+		} while (sg_page(sg + ++i));
+
+		ctx->merge = plen & (PAGE_SIZE - 1);
+		if (ctx->merge)
+			sgl->cur--;
+	}
+
+	err = 0;
+
+	ctx->more = msg->msg_flags & MSG_MORE;
+	if (!ctx->more && !list_empty(&ctx->tsgl)) {
+		sgl = list_entry(ctx->tsgl.prev, struct skcipher_sg_list, list);
+		sg_mark_end(sgl->sg + sgl->cur - 1);
+	}
+
+unlock:
+	skcipher_data_wakeup(sk);
+	release_sock(sk);
+
+	return copied ?: err;
+}
+
+static ssize_t skcipher_sendpage(struct socket *sock, struct page *page,
+				 int offset, size_t size, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	struct skcipher_ctx *ctx = ask->private;
+	struct skcipher_sg_list *sgl;
+	int err = -EINVAL;
+	int limit;
+
+	lock_sock(sk);
+	if (!ctx->more && ctx->used)
+		goto unlock;
+
+	if (!size)
+		goto done;
+
+	limit = max_t(int, sk->sk_sndbuf, PAGE_SIZE);
+	limit -= ctx->used;
+
+	if (limit < PAGE_SIZE) {
+		release_sock(sk);
+		err = skcipher_wait_for_wmem(sk, flags);
+		lock_sock(sk);
+		if (err)
+			goto unlock;
+
+		limit = max_t(int, sk->sk_sndbuf, PAGE_SIZE);
+		limit -= ctx->used;
+	}
+
+	err = skcipher_alloc_sgl(sk, 0);
+	if (err)
+		goto unlock;
+
+	ctx->merge = 0;
+	sgl = list_entry(ctx->tsgl.prev, struct skcipher_sg_list, list);
+
+	get_page(page);
+	sg_set_page(sgl->sg + sgl->cur, page, size, offset);
+	sgl->cur++;
+	ctx->used += size;
+
+done:
+	ctx->more = flags & MSG_MORE;
+	if (!ctx->more && !list_empty(&ctx->tsgl)) {
+		sgl = list_entry(ctx->tsgl.prev, struct skcipher_sg_list, list);
+		sg_mark_end(sgl->sg + sgl->cur - 1);
+	}
+
+unlock:
+	skcipher_data_wakeup(sk);
+	release_sock(sk);
+
+	return err ?: size;
+}
+
+static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock,
+			    struct msghdr *msg, size_t ignored, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	struct skcipher_ctx *ctx = ask->private;
+	unsigned bs = crypto_ablkcipher_blocksize(crypto_ablkcipher_reqtfm(
+		&ctx->req));
+	struct skcipher_sg_list *sgl;
+	struct scatterlist *sg;
+	unsigned long iovlen;
+	struct iovec *iov;
+	int err = -EAGAIN;
+	int used;
+	long copied = 0;
+
+	lock_sock(sk);
+	for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0;
+	     iovlen--, iov++) {
+		unsigned long seglen = iov->iov_len;
+		char __user *from = iov->iov_base;
+
+		sgl = list_first_entry(&ctx->tsgl, struct skcipher_sg_list,
+				       list);
+		sg = sgl->sg;
+		while (!sg->length)
+			sg++;
+
+		while (seglen) {
+			used = ctx->used;
+			if (!used) {
+				release_sock(sk);
+				err = skcipher_wait_for_data(sk, flags);
+				lock_sock(sk);
+				if (err)
+					goto unlock;
+			}
+
+			used = min_t(unsigned long, used, seglen);
+
+			if (ctx->more || used < ctx->used)
+				used -= used % bs;
+
+			err = -EINVAL;
+			if (!used)
+				goto unlock;
+
+			used = af_alg_make_sg(&ctx->rsgl, from, used, 1);
+			if (used < 0)
+				goto unlock;
+
+			ablkcipher_request_set_crypt(&ctx->req, sg,
+						     ctx->rsgl.sg, used,
+						     ctx->iv);
+
+			err = af_alg_wait_for_completion(
+				ctx->enc ?
+					crypto_ablkcipher_encrypt(&ctx->req) :
+					crypto_ablkcipher_decrypt(&ctx->req),
+				&ctx->completion);
+
+			af_alg_free_sg(&ctx->rsgl);
+
+			if (err)
+				goto unlock;
+
+			copied += used;
+			from += used;
+			seglen -= used;
+			skcipher_pull_sgl(sk, used);
+		}
+	}
+
+	err = 0;
+
+unlock:
+	skcipher_wmem_wakeup(sk);
+	release_sock(sk);
+
+	return copied ?: err;
+}
+
+
+static unsigned int skcipher_poll(struct file *file, struct socket *sock,
+				  poll_table *wait)
+{
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	struct skcipher_ctx *ctx = ask->private;
+	unsigned int mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
+
+	if (ctx->used)
+		mask |= POLLIN | POLLRDNORM;
+
+	if (skcipher_writable(sk))
+		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+
+	return mask;
+}
+
+static struct proto_ops algif_skcipher_ops = {
+	.family		=	PF_ALG,
+
+	.connect	=	sock_no_connect,
+	.socketpair	=	sock_no_socketpair,
+	.getname	=	sock_no_getname,
+	.ioctl		=	sock_no_ioctl,
+	.listen		=	sock_no_listen,
+	.shutdown	=	sock_no_shutdown,
+	.getsockopt	=	sock_no_getsockopt,
+	.mmap		=	sock_no_mmap,
+	.bind		=	sock_no_bind,
+	.accept		=	sock_no_accept,
+	.setsockopt	=	sock_no_setsockopt,
+
+	.release	=	af_alg_release,
+	.sendmsg	=	skcipher_sendmsg,
+	.sendpage	=	skcipher_sendpage,
+	.recvmsg	=	skcipher_recvmsg,
+	.poll		=	skcipher_poll,
+};
+
+static void *skcipher_bind(const char *name, u32 type, u32 mask)
+{
+	return crypto_alloc_ablkcipher(name, type, mask);
+}
+
+static void skcipher_release(void *private)
+{
+	crypto_free_ablkcipher(private);
+}
+
+static int skcipher_setkey(void *private, const u8 *key, unsigned int keylen)
+{
+	return crypto_ablkcipher_setkey(private, key, keylen);
+}
+
+static void skcipher_sock_destruct(struct sock *sk)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct skcipher_ctx *ctx = ask->private;
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(&ctx->req);
+
+	skcipher_free_sgl(sk);
+	sock_kfree_s(sk, ctx->iv, crypto_ablkcipher_blocksize(tfm));
+	sock_kfree_s(sk, ctx, ctx->len);
+	af_alg_release_parent(sk);
+}
+
+static int skcipher_accept_parent(void *private, struct sock *sk)
+{
+	struct skcipher_ctx *ctx;
+	struct alg_sock *ask = alg_sk(sk);
+	unsigned int len = sizeof(*ctx) + crypto_ablkcipher_reqsize(private);
+
+	ctx = sock_kmalloc(sk, len, GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->iv = sock_kmalloc(sk, crypto_ablkcipher_ivsize(private),
+			       GFP_KERNEL);
+	if (!ctx->iv) {
+		sock_kfree_s(sk, ctx, len);
+		return -ENOMEM;
+	}
+
+	memset(ctx->iv, 0, crypto_ablkcipher_ivsize(private));
+
+	INIT_LIST_HEAD(&ctx->tsgl);
+	ctx->len = len;
+	ctx->used = 0;
+	ctx->more = 0;
+	ctx->merge = 0;
+	ctx->enc = 0;
+	af_alg_init_completion(&ctx->completion);
+
+	ask->private = ctx;
+
+	ablkcipher_request_set_tfm(&ctx->req, private);
+	ablkcipher_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+					af_alg_complete, &ctx->completion);
+
+	sk->sk_destruct = skcipher_sock_destruct;
+
+	return 0;
+}
+
+static const struct af_alg_type algif_type_skcipher = {
+	.bind		=	skcipher_bind,
+	.release	=	skcipher_release,
+	.setkey		=	skcipher_setkey,
+	.accept		=	skcipher_accept_parent,
+	.ops		=	&algif_skcipher_ops,
+	.name		=	"skcipher",
+	.owner		=	THIS_MODULE
+};
+
+static int __init algif_skcipher_init(void)
+{
+	return af_alg_register_type(&algif_type_skcipher);
+}
+
+static void __exit algif_skcipher_exit(void)
+{
+	int err = af_alg_unregister_type(&algif_type_skcipher);
+	BUG_ON(err);
+}
+
+module_init(algif_skcipher_init);
+module_exit(algif_skcipher_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETPROTO(AF_ALG);

^ permalink raw reply related

* [PATCH 3/4] crypto: algif_hash - User-space interface for hash operations
From: Herbert Xu @ 2010-11-04 17:36 UTC (permalink / raw)
  To: Linux Crypto Mailing List, netdev, Linux Kernel Mailing List
In-Reply-To: <20101104173456.GA1321@gondor.apana.org.au>

crypto: algif_hash - User-space interface for hash operations

This patch adds the af_alg plugin for hash, corresponding to
the ahash kernel operation type.

Keys can optionally be set through the setsockopt interface.

Each sendmsg call will finalise the hash unless sent with a MSG_MORE
flag.

Partial hash states can be cloned using accept(2).

The interface is completely synchronous, all operations will
complete prior to the system call returning.

Both sendmsg(2) and splice(2) support reading the user-space
data directly without copying (except that the Crypto API itself
may copy the data if alignment is off).

For now only the splice(2) interface supports performing digest
instead of init/update/final.  In future the sendmsg(2) interface
will also be modified to use digest/finup where possible so that
hardware that cannot return a partial hash state can still benefit
from this interface.

Thakns to Miloslav Trmac for reviewing this and contributing
fixes and improvements.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---

 crypto/Kconfig      |    8 +
 crypto/Makefile     |    1 
 crypto/algif_hash.c |  321 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 330 insertions(+)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index 357e3ca..6db27d7 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -844,6 +844,14 @@ config CRYPTO_ANSI_CPRNG
 config CRYPTO_USER_API
 	tristate
 
+config CRYPTO_USER_API_HASH
+	tristate "User-space interface for hash algorithms"
+	select CRYPTO_HASH
+	select CRYPTO_USER_API
+	help
+	  This option enables the user-spaces interface for hash
+	  algorithms.
+
 source "drivers/crypto/Kconfig"
 
 endif	# if CRYPTO
diff --git a/crypto/Makefile b/crypto/Makefile
index 0b13197..14ab405 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -86,6 +86,7 @@ obj-$(CONFIG_CRYPTO_ANSI_CPRNG) += ansi_cprng.o
 obj-$(CONFIG_CRYPTO_TEST) += tcrypt.o
 obj-$(CONFIG_CRYPTO_GHASH) += ghash-generic.o
 obj-$(CONFIG_CRYPTO_USER_API) += af_alg.o
+obj-$(CONFIG_CRYPTO_USER_API_HASH) += algif_hash.o
 
 #
 # generic algorithms and the async_tx api
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
new file mode 100644
index 0000000..014ea43
--- /dev/null
+++ b/crypto/algif_hash.c
@@ -0,0 +1,321 @@
+/*
+ * algif_hash: User-space interface for hash algorithms
+ *
+ * This file provides the user-space API for hash algorithms.
+ *
+ * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <crypto/hash.h>
+#include <crypto/if_alg.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <net/sock.h>
+
+struct hash_ctx {
+	struct af_alg_sgl sgl;
+
+	u8 *result;
+
+	struct af_alg_completion completion;
+
+	unsigned int len;
+	int err;
+	bool more;
+
+	struct ahash_request req;
+};
+
+static int hash_sendmsg(struct kiocb *unused, struct socket *sock,
+			struct msghdr *msg, size_t ignored)
+{
+	int limit = ALG_MAX_PAGES * PAGE_SIZE;
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	struct hash_ctx *ctx = ask->private;
+	unsigned long iovlen;
+	struct iovec *iov;
+	long copied = 0;
+	int err;
+
+	if (limit > sk->sk_sndbuf)
+		limit = sk->sk_sndbuf;
+
+	lock_sock(sk);
+	if (!ctx->more) {
+		err = crypto_ahash_init(&ctx->req);
+		if (err)
+			goto unlock;
+	}
+
+	ctx->more = 0;
+
+	for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0;
+	     iovlen--, iov++) {
+		unsigned long seglen = iov->iov_len;
+		char __user *from = iov->iov_base;
+
+		while (seglen) {
+			int len = min_t(unsigned long, seglen, limit);
+			int newlen;
+
+			newlen = af_alg_make_sg(&ctx->sgl, from, len, 0);
+			if (newlen < 0)
+				goto unlock;
+
+			ahash_request_set_crypt(&ctx->req, ctx->sgl.sg, NULL,
+						newlen);
+
+			err = af_alg_wait_for_completion(
+				crypto_ahash_update(&ctx->req),
+				&ctx->completion);
+
+			af_alg_free_sg(&ctx->sgl);
+
+			if (err)
+				goto unlock;
+
+			seglen -= newlen;
+			from += newlen;
+			copied += newlen;
+		}
+	}
+
+	err = 0;
+
+	ctx->more = msg->msg_flags & MSG_MORE;
+	if (!ctx->more) {
+		ahash_request_set_crypt(&ctx->req, NULL, ctx->result, 0);
+		err = af_alg_wait_for_completion(crypto_ahash_final(&ctx->req),
+						 &ctx->completion);
+	}
+
+unlock:
+	release_sock(sk);
+
+	return err ?: copied;
+}
+
+static ssize_t hash_sendpage(struct socket *sock, struct page *page,
+			     int offset, size_t size, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	struct hash_ctx *ctx = ask->private;
+	int err;
+
+	lock_sock(sk);
+	sg_init_table(ctx->sgl.sg, 1);
+	sg_set_page(ctx->sgl.sg, page, size, offset);
+
+	ahash_request_set_crypt(&ctx->req, ctx->sgl.sg, ctx->result, size);
+
+	if (!(flags & MSG_MORE)) {
+		if (ctx->more)
+			err = crypto_ahash_finup(&ctx->req);
+		else
+			err = crypto_ahash_digest(&ctx->req);
+	} else {
+		if (!ctx->more) {
+			err = crypto_ahash_init(&ctx->req);
+			if (err)
+				goto unlock;
+		}
+
+		err = crypto_ahash_update(&ctx->req);
+	}
+
+	err = af_alg_wait_for_completion(err, &ctx->completion);
+	if (err)
+		goto unlock;
+
+	ctx->more = flags & MSG_MORE;
+
+unlock:
+	release_sock(sk);
+
+	return err ?: size;
+}
+
+static int hash_recvmsg(struct kiocb *unused, struct socket *sock,
+			struct msghdr *msg, size_t len, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	struct hash_ctx *ctx = ask->private;
+	unsigned ds = crypto_ahash_digestsize(crypto_ahash_reqtfm(&ctx->req));
+	int err;
+
+	if (len > ds)
+		len = ds;
+	else if (len < ds)
+		msg->msg_flags |= MSG_TRUNC;
+
+	lock_sock(sk);
+	if (ctx->more) {
+		ctx->more = 0;
+		ahash_request_set_crypt(&ctx->req, NULL, ctx->result, 0);
+		err = af_alg_wait_for_completion(crypto_ahash_final(&ctx->req),
+						 &ctx->completion);
+		if (err)
+			goto unlock;
+	}
+
+	err = memcpy_toiovec(msg->msg_iov, ctx->result, len);
+
+unlock:
+	release_sock(sk);
+
+	return err ?: len;
+}
+
+static int hash_accept(struct socket *sock, struct socket *newsock, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	struct hash_ctx *ctx = ask->private;
+	struct ahash_request *req = &ctx->req;
+	char state[crypto_ahash_statesize(crypto_ahash_reqtfm(req))];
+	struct sock *sk2;
+	struct alg_sock *ask2;
+	struct hash_ctx *ctx2;
+	int err;
+
+	err = crypto_ahash_export(req, state);
+	if (err)
+		return err;
+
+	err = af_alg_accept(ask->parent, newsock);
+	if (err)
+		return err;
+
+	sk2 = newsock->sk;
+	ask2 = alg_sk(sk2);
+	ctx2 = ask2->private;
+	ctx2->more = 1;
+
+	err = crypto_ahash_import(&ctx2->req, state);
+	if (err) {
+		sock_orphan(sk2);
+		sock_put(sk2);
+	}
+
+	return err;
+}
+
+static struct proto_ops algif_hash_ops = {
+	.family		=	PF_ALG,
+
+	.connect	=	sock_no_connect,
+	.socketpair	=	sock_no_socketpair,
+	.getname	=	sock_no_getname,
+	.ioctl		=	sock_no_ioctl,
+	.listen		=	sock_no_listen,
+	.shutdown	=	sock_no_shutdown,
+	.getsockopt	=	sock_no_getsockopt,
+	.mmap		=	sock_no_mmap,
+	.bind		=	sock_no_bind,
+	.setsockopt	=	sock_no_setsockopt,
+	.poll		=	sock_no_poll,
+
+	.release	=	af_alg_release,
+	.sendmsg	=	hash_sendmsg,
+	.sendpage	=	hash_sendpage,
+	.recvmsg	=	hash_recvmsg,
+	.accept		=	hash_accept,
+};
+
+static void *hash_bind(const char *name, u32 type, u32 mask)
+{
+	return crypto_alloc_ahash(name, type, mask);
+}
+
+static void hash_release(void *private)
+{
+	crypto_free_ahash(private);
+}
+
+static int hash_setkey(void *private, const u8 *key, unsigned int keylen)
+{
+	return crypto_ahash_setkey(private, key, keylen);
+}
+
+static void hash_sock_destruct(struct sock *sk)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	struct hash_ctx *ctx = ask->private;
+
+	sock_kfree_s(sk, ctx->result,
+		     crypto_ahash_digestsize(crypto_ahash_reqtfm(&ctx->req)));
+	sock_kfree_s(sk, ctx, ctx->len);
+	af_alg_release_parent(sk);
+}
+
+static int hash_accept_parent(void *private, struct sock *sk)
+{
+	struct hash_ctx *ctx;
+	struct alg_sock *ask = alg_sk(sk);
+	unsigned len = sizeof(*ctx) + crypto_ahash_reqsize(private);
+	unsigned ds = crypto_ahash_digestsize(private);
+
+	ctx = sock_kmalloc(sk, len, GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->result = sock_kmalloc(sk, ds, GFP_KERNEL);
+	if (!ctx->result) {
+		sock_kfree_s(sk, ctx, len);
+		return -ENOMEM;
+	}
+
+	memset(ctx->result, 0, ds);
+
+	ctx->len = len;
+	ctx->more = 0;
+	af_alg_init_completion(&ctx->completion);
+
+	ask->private = ctx;
+
+	ahash_request_set_tfm(&ctx->req, private);
+	ahash_request_set_callback(&ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				   af_alg_complete, &ctx->completion);
+
+	sk->sk_destruct = hash_sock_destruct;
+
+	return 0;
+}
+
+static const struct af_alg_type algif_type_hash = {
+	.bind		=	hash_bind,
+	.release	=	hash_release,
+	.setkey		=	hash_setkey,
+	.accept		=	hash_accept_parent,
+	.ops		=	&algif_hash_ops,
+	.name		=	"hash",
+	.owner		=	THIS_MODULE
+};
+
+static int __init algif_hash_init(void)
+{
+	return af_alg_register_type(&algif_type_hash);
+}
+
+static void __exit algif_hash_exit(void)
+{
+	int err = af_alg_unregister_type(&algif_type_hash);
+	BUG_ON(err);
+}
+
+module_init(algif_hash_init);
+module_exit(algif_hash_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETPROTO(AF_ALG);

^ permalink raw reply related

* [PATCH 2/4] crypto: af_alg - User-space interface for Crypto API
From: Herbert Xu @ 2010-11-04 17:36 UTC (permalink / raw)
  To: Linux Crypto Mailing List, netdev, Linux Kernel Mailing List
In-Reply-To: <20101104173456.GA1321@gondor.apana.org.au>

crypto: af_alg - User-space interface for Crypto API

This patch creates the backbone of the user-space interface for
the Crypto API, through a new socket family AF_ALG.

Each session corresponds to one or more connections obtained from
that socket.  The number depends on the number of inputs/outputs
of that particular type of operation.  For most types there will
be a s ingle connection/file descriptor that is used for both input
and output.  AEAD is one of the few that require two inputs.

Each algorithm type will provide its own implementation that plugs
into af_alg.  They're keyed using a string such as "skcipher" or
"hash".

IOW this patch only contains the boring bits that is required
to hold everything together.

Thakns to Miloslav Trmac for reviewing this and contributing
fixes and improvements.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---

 crypto/Kconfig          |    3 
 crypto/Makefile         |    1 
 crypto/af_alg.c         |  460 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/crypto/if_alg.h |   92 +++++++++
 include/linux/if_alg.h  |   40 ++++
 5 files changed, 596 insertions(+)

diff --git a/crypto/Kconfig b/crypto/Kconfig
index e4bac29..357e3ca 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -841,6 +841,9 @@ config CRYPTO_ANSI_CPRNG
 	  ANSI X9.31 A.2.4. Note that this option must be enabled if
 	  CRYPTO_FIPS is selected
 
+config CRYPTO_USER_API
+	tristate
+
 source "drivers/crypto/Kconfig"
 
 endif	# if CRYPTO
diff --git a/crypto/Makefile b/crypto/Makefile
index 423b7de..0b13197 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -85,6 +85,7 @@ obj-$(CONFIG_CRYPTO_RNG2) += krng.o
 obj-$(CONFIG_CRYPTO_ANSI_CPRNG) += ansi_cprng.o
 obj-$(CONFIG_CRYPTO_TEST) += tcrypt.o
 obj-$(CONFIG_CRYPTO_GHASH) += ghash-generic.o
+obj-$(CONFIG_CRYPTO_USER_API) += af_alg.o
 
 #
 # generic algorithms and the async_tx api
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
new file mode 100644
index 0000000..92cd9b1
--- /dev/null
+++ b/crypto/af_alg.c
@@ -0,0 +1,460 @@
+/*
+ * af_alg: User-space algorithm interface
+ *
+ * This file provides the user-space API for algorithms.
+ *
+ * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#include <asm/atomic.h>
+#include <crypto/if_alg.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/rwsem.h>
+
+struct alg_type_list {
+	const struct af_alg_type *type;
+	struct list_head list;
+};
+
+static atomic_t alg_memory_allocated;
+
+static struct proto alg_proto = {
+	.name			= "ALG",
+	.owner			= THIS_MODULE,
+	.memory_allocated	= &alg_memory_allocated,
+	.obj_size		= sizeof(struct alg_sock),
+};
+
+static LIST_HEAD(alg_types);
+static DECLARE_RWSEM(alg_types_sem);
+
+static const struct af_alg_type *alg_get_type(const char *name)
+{
+	const struct af_alg_type *type = ERR_PTR(-ENOENT);
+	struct alg_type_list *node;
+
+	down_read(&alg_types_sem);
+	list_for_each_entry(node, &alg_types, list) {
+		if (strcmp(node->type->name, name))
+			continue;
+
+		if (try_module_get(node->type->owner))
+			type = node->type;
+		break;
+	}
+	up_read(&alg_types_sem);
+
+	return type;
+}
+
+int af_alg_register_type(const struct af_alg_type *type)
+{
+	struct alg_type_list *node;
+	int err = -EEXIST;
+
+	down_write(&alg_types_sem);
+	list_for_each_entry(node, &alg_types, list) {
+		if (!strcmp(node->type->name, type->name))
+			goto unlock;
+	}
+
+	node = kmalloc(sizeof(*node), GFP_KERNEL);
+	err = -ENOMEM;
+	if (!node)
+		goto unlock;
+
+	type->ops->owner = THIS_MODULE;
+	node->type = type;
+	list_add(&node->list, &alg_types);
+	err = 0;
+
+unlock:
+	up_write(&alg_types_sem);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(af_alg_register_type);
+
+int af_alg_unregister_type(const struct af_alg_type *type)
+{
+	struct alg_type_list *node;
+	int err = -ENOENT;
+
+	down_write(&alg_types_sem);
+	list_for_each_entry(node, &alg_types, list) {
+		if (strcmp(node->type->name, type->name))
+			continue;
+
+		list_del(&node->list);
+		kfree(node);
+		err = 0;
+		break;
+	}
+	up_write(&alg_types_sem);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(af_alg_unregister_type);
+
+static void alg_do_release(const struct af_alg_type *type, void *private)
+{
+	if (!type)
+		return;
+
+	type->release(private);
+	module_put(type->owner);
+}
+
+int af_alg_release(struct socket *sock)
+{
+	if (sock->sk)
+		sock_put(sock->sk);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(af_alg_release);
+
+static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
+{
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	struct sockaddr_alg *sa = (void *)uaddr;
+	const struct af_alg_type *type;
+	void *private;
+
+	if (sock->state == SS_CONNECTED)
+		return -EINVAL;
+
+	if (addr_len != sizeof(*sa))
+		return -EINVAL;
+
+	sa->salg_type[sizeof(sa->salg_type) - 1] = 0;
+	sa->salg_name[sizeof(sa->salg_name) - 1] = 0;
+
+	type = alg_get_type(sa->salg_type);
+	if (IS_ERR(type) && PTR_ERR(type) == -ENOENT) {
+		request_module("algif-%s", sa->salg_type);
+		type = alg_get_type(sa->salg_type);
+	}
+
+	if (IS_ERR(type))
+		return PTR_ERR(type);
+
+	private = type->bind(sa->salg_name, sa->salg_feat, sa->salg_mask);
+	if (IS_ERR(private)) {
+		module_put(type->owner);
+		return PTR_ERR(private);
+	}
+
+	lock_sock(sk);
+
+	swap(ask->type, type);
+	swap(ask->private, private);
+
+	release_sock(sk);
+
+	alg_do_release(type, private);
+
+	return 0;
+}
+
+static int alg_setkey(struct sock *sk, char __user *ukey,
+		      unsigned int keylen)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	const struct af_alg_type *type = ask->type;
+	u8 *key;
+	int err;
+
+	key = sock_kmalloc(sk, keylen, GFP_KERNEL);
+	if (!key)
+		return -ENOMEM;
+
+	if (copy_from_user(key, ukey, keylen))
+		return -EFAULT;
+
+	err = type->setkey(ask->private, key, keylen);
+
+	sock_kfree_s(sk, key, keylen);
+
+	return err;
+}
+
+static int alg_setsockopt(struct socket *sock, int level, int optname,
+			  char __user *optval, unsigned int optlen)
+{
+	struct sock *sk = sock->sk;
+	struct alg_sock *ask = alg_sk(sk);
+	const struct af_alg_type *type = ask->type;
+
+	if (level != SOL_ALG || !type)
+		return -ENOPROTOOPT;
+
+	switch (optname) {
+	case ALG_SET_KEY:
+		if (sock->state == SS_CONNECTED)
+			return -ENOPROTOOPT;
+		if (!type->setkey)
+			return -ENOPROTOOPT;
+
+		return alg_setkey(sk, optval, optlen);
+	}
+
+	return -ENOPROTOOPT;
+}
+
+int af_alg_accept(struct sock *sk, struct socket *newsock)
+{
+	struct alg_sock *ask = alg_sk(sk);
+	const struct af_alg_type *type = ask->type;
+	struct sock *sk2;
+	int err;
+
+	if (!type)
+		return -EINVAL;
+
+	sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto);
+	if (!sk2)
+		return -ENOMEM;
+
+	sock_init_data(newsock, sk2);
+
+	err = type->accept(ask->private, sk2);
+	if (err) {
+		sk_free(sk2);
+		return err;
+	}
+
+	sk2->sk_family = PF_ALG;
+
+	sock_hold(sk);
+	alg_sk(sk2)->parent = sk;
+	alg_sk(sk2)->type = type;
+
+	newsock->ops = type->ops;
+	newsock->state = SS_CONNECTED;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(af_alg_accept);
+
+static int alg_accept(struct socket *sock, struct socket *newsock, int flags)
+{
+	return af_alg_accept(sock->sk, newsock);
+}
+
+static const struct proto_ops alg_proto_ops = {
+	.family		=	PF_ALG,
+	.owner		=	THIS_MODULE,
+
+	.connect	=	sock_no_connect,
+	.socketpair	=	sock_no_socketpair,
+	.getname	=	sock_no_getname,
+	.ioctl		=	sock_no_ioctl,
+	.listen		=	sock_no_listen,
+	.shutdown	=	sock_no_shutdown,
+	.getsockopt	=	sock_no_getsockopt,
+	.mmap		=	sock_no_mmap,
+	.sendpage	=	sock_no_sendpage,
+	.sendmsg	=	sock_no_sendmsg,
+	.recvmsg	=	sock_no_recvmsg,
+	.poll		=	sock_no_poll,
+
+	.bind		=	alg_bind,
+	.release	=	af_alg_release,
+	.setsockopt	=	alg_setsockopt,
+	.accept		=	alg_accept,
+};
+
+static void alg_sock_destruct(struct sock *sk)
+{
+	struct alg_sock *ask = alg_sk(sk);
+
+	alg_do_release(ask->type, ask->private);
+}
+
+static int alg_create(struct net *net, struct socket *sock, int protocol,
+		      int kern)
+{
+	struct sock *sk;
+	int err;
+
+	if (sock->type != SOCK_SEQPACKET)
+		return -ESOCKTNOSUPPORT;
+	if (protocol != 0)
+		return -EPROTONOSUPPORT;
+
+	err = -ENOMEM;
+	sk = sk_alloc(net, PF_ALG, GFP_KERNEL, &alg_proto);
+	if (!sk)
+		goto out;
+
+	sock->ops = &alg_proto_ops;
+	sock_init_data(sock, sk);
+
+	sk->sk_family = PF_ALG;
+	sk->sk_destruct = alg_sock_destruct;
+
+	return 0;
+out:
+	return err;
+}
+
+static const struct net_proto_family alg_family = {
+	.family	=	PF_ALG,
+	.create	=	alg_create,
+	.owner	=	THIS_MODULE,
+};
+
+int af_alg_make_sg(struct af_alg_sgl *sgl, void __user *addr, int len,
+		   int write)
+{
+	unsigned long from = (unsigned long)addr;
+	unsigned long npages;
+	unsigned off;
+	int err;
+	int i;
+
+	err = -EFAULT;
+	if (!access_ok(write ? VERIFY_READ : VERIFY_WRITE, addr, len))
+		goto out;
+
+	off = from & ~PAGE_MASK;
+	npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	err = get_user_pages_fast(from, npages, write, sgl->pages);
+	if (err < 0)
+		goto out;
+
+	npages = err;
+	err = -EINVAL;
+	if (WARN_ON(npages == 0))
+		goto out;
+
+	err = 0;
+
+	sg_init_table(sgl->sg, npages);
+
+	for (i = 0; i < npages; i++) {
+		int plen = min_t(int, len, PAGE_SIZE - off);
+
+		sg_set_page(sgl->sg + i, sgl->pages[i], plen, off);
+
+		off = 0;
+		len -= plen;
+		err += plen;
+	}
+
+out:
+	return err;
+}
+EXPORT_SYMBOL_GPL(af_alg_make_sg);
+
+void af_alg_free_sg(struct af_alg_sgl *sgl)
+{
+	int i;
+
+	i = 0;
+	do {
+		put_page(sgl->pages[i]);
+	} while (!sg_is_last(sgl->sg + (i++)));
+}
+EXPORT_SYMBOL_GPL(af_alg_free_sg);
+
+int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con)
+{
+	struct cmsghdr *cmsg;
+
+	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) {
+		if (!CMSG_OK(msg, cmsg))
+			return -EINVAL;
+		if (cmsg->cmsg_level != SOL_ALG)
+			continue;
+
+		switch(cmsg->cmsg_type) {
+		case ALG_SET_IV:
+			if (cmsg->cmsg_len < sizeof(*con->iv))
+				return -EINVAL;
+			con->iv = (void *)CMSG_DATA(cmsg);
+			if (cmsg->cmsg_len < con->iv->ivlen +
+					     sizeof(con->iv->ivlen))
+				return -EINVAL;
+			break;
+
+		case ALG_SET_OP:
+			if (cmsg->cmsg_len < sizeof(u32))
+				return -EINVAL;
+			con->op = *(u32 *)CMSG_DATA(cmsg);
+			break;
+
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(af_alg_cmsg_send);
+
+int af_alg_wait_for_completion(int err, struct af_alg_completion *completion)
+{
+	switch (err) {
+	case -EINPROGRESS:
+	case -EBUSY:
+		wait_for_completion(&completion->completion);
+		INIT_COMPLETION(completion->completion);
+		err = completion->err;
+		break;
+	};
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(af_alg_wait_for_completion);
+
+void af_alg_complete(struct crypto_async_request *req, int err)
+{
+	struct af_alg_completion *completion = req->data;
+
+	completion->err = err;
+	complete(&completion->completion);
+}
+EXPORT_SYMBOL_GPL(af_alg_complete);
+
+static int __init af_alg_init(void)
+{
+	int err = proto_register(&alg_proto, 0);
+
+	if (err)
+		goto out;
+
+	err = sock_register(&alg_family);
+	if (err != 0)
+		goto out_unregister_proto;
+
+out:
+	return err;
+
+out_unregister_proto:
+	proto_unregister(&alg_proto);
+	goto out;
+}
+
+static void __exit af_alg_exit(void)
+{
+	sock_unregister(PF_ALG);
+	proto_unregister(&alg_proto);
+}
+
+module_init(af_alg_init);
+module_exit(af_alg_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETPROTO(AF_ALG);
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
new file mode 100644
index 0000000..c5813c8
--- /dev/null
+++ b/include/crypto/if_alg.h
@@ -0,0 +1,92 @@
+/*
+ * if_alg: User-space algorithm interface
+ *
+ * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _CRYPTO_IF_ALG_H
+#define _CRYPTO_IF_ALG_H
+
+#include <linux/compiler.h>
+#include <linux/completion.h>
+#include <linux/if_alg.h>
+#include <linux/types.h>
+#include <net/sock.h>
+
+#define ALG_MAX_PAGES			16
+
+struct crypto_async_request;
+
+struct alg_sock {
+	/* struct sock must be the first member of struct alg_sock */
+	struct sock sk;
+
+	struct sock *parent;
+
+	const struct af_alg_type *type;
+	void *private;
+};
+
+struct af_alg_completion {
+	struct completion completion;
+	int err;
+};
+
+struct af_alg_control {
+	struct af_alg_iv *iv;
+	int op;
+};
+
+struct af_alg_type {
+	void *(*bind)(const char *name, u32 type, u32 mask);
+	void (*release)(void *private);
+	int (*setkey)(void *private, const u8 *key, unsigned int keylen);
+	int (*accept)(void *private, struct sock *sk);
+
+	struct proto_ops *ops;
+	struct module *owner;
+	char name[14];
+};
+
+struct af_alg_sgl {
+	struct scatterlist sg[ALG_MAX_PAGES];
+	struct page *pages[ALG_MAX_PAGES];
+};
+
+int af_alg_register_type(const struct af_alg_type *type);
+int af_alg_unregister_type(const struct af_alg_type *type);
+
+int af_alg_release(struct socket *sock);
+int af_alg_accept(struct sock *sk, struct socket *newsock);
+
+int af_alg_make_sg(struct af_alg_sgl *sgl, void __user *addr, int len,
+		   int write);
+void af_alg_free_sg(struct af_alg_sgl *sgl);
+
+int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con);
+
+int af_alg_wait_for_completion(int err, struct af_alg_completion *completion);
+void af_alg_complete(struct crypto_async_request *req, int err);
+
+static inline struct alg_sock *alg_sk(struct sock *sk)
+{
+	return (struct alg_sock *)sk;
+}
+
+static inline void af_alg_release_parent(struct sock *sk)
+{
+	sock_put(alg_sk(sk)->parent);
+}
+
+static inline void af_alg_init_completion(struct af_alg_completion *completion)
+{
+	init_completion(&completion->completion);
+}
+
+#endif	/* _CRYPTO_IF_ALG_H */
diff --git a/include/linux/if_alg.h b/include/linux/if_alg.h
new file mode 100644
index 0000000..0f9acce
--- /dev/null
+++ b/include/linux/if_alg.h
@@ -0,0 +1,40 @@
+/*
+ * if_alg: User-space algorithm interface
+ *
+ * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _LINUX_IF_ALG_H
+#define _LINUX_IF_ALG_H
+
+#include <linux/types.h>
+
+struct sockaddr_alg {
+	__u16	salg_family;
+	__u8	salg_type[14];
+	__u32	salg_feat;
+	__u32	salg_mask;
+	__u8	salg_name[64];
+};
+
+struct af_alg_iv {
+	__u32	ivlen;
+	__u8	iv[0];
+};
+
+/* Socket options */
+#define ALG_SET_KEY			1
+#define ALG_SET_IV			2
+#define ALG_SET_OP			3
+
+/* Operations */
+#define ALG_OP_DECRYPT			0
+#define ALG_OP_ENCRYPT			1
+
+#endif	/* _LINUX_IF_ALG_H */

^ permalink raw reply related

* [PATCH 1/4] net - Add AF_ALG macros
From: Herbert Xu @ 2010-11-04 17:36 UTC (permalink / raw)
  To: Linux Crypto Mailing List, netdev, Linux Kernel Mailing List
In-Reply-To: <20101104173456.GA1321@gondor.apana.org.au>

net - Add AF_ALG macros

This patch adds the socket family/level macros for the yet-to-be-born
AF_ALG family.  The AF_ALG family provides the user-space interface
for the kernel crypto API.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---

 include/linux/socket.h |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/linux/socket.h b/include/linux/socket.h
index 5146b50..ebc081b 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -193,7 +193,8 @@ struct ucred {
 #define AF_PHONET	35	/* Phonet sockets		*/
 #define AF_IEEE802154	36	/* IEEE802154 sockets		*/
 #define AF_CAIF		37	/* CAIF sockets			*/
-#define AF_MAX		38	/* For now.. */
+#define AF_ALG		38	/* Algorithm sockets		*/
+#define AF_MAX		39	/* For now.. */
 
 /* Protocol families, same as address families. */
 #define PF_UNSPEC	AF_UNSPEC
@@ -234,6 +235,7 @@ struct ucred {
 #define PF_PHONET	AF_PHONET
 #define PF_IEEE802154	AF_IEEE802154
 #define PF_CAIF		AF_CAIF
+#define PF_ALG		AF_ALG
 #define PF_MAX		AF_MAX
 
 /* Maximum queue length specifiable by listen.  */
@@ -307,6 +309,7 @@ struct ucred {
 #define SOL_RDS		276
 #define SOL_IUCV	277
 #define SOL_CAIF	278
+#define SOL_ALG		279
 
 /* IPX options */
 #define IPX_TYPE	1

^ permalink raw reply related


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox