1 files changed, 119 insertions, 158 deletions

diff --git a/drivers/misc/sgi-xp/xpnet.c b/drivers/misc/sgi-xp/xpnet.c
index 822dc8e8d7f..71513b3af70 100644
--- a/drivers/misc/sgi-xp/xpnet.c
+++ b/drivers/misc/sgi-xp/xpnet.c
@@ -21,21 +21,8 @@
  */
 
 #include <linux/module.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/ioport.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
-#include <linux/delay.h>
-#include <linux/ethtool.h>
-#include <linux/mii.h>
-#include <linux/smp.h>
-#include <linux/string.h>
-#include <asm/sn/bte.h>
-#include <asm/sn/io.h>
-#include <asm/sn/sn_sal.h>
-#include <asm/atomic.h>
 #include "xp.h"
 
 /*
@@ -57,7 +44,7 @@ struct xpnet_message {
         u16 version;            /* Version for this message */
         u16 embedded_bytes;     /* #of bytes embedded in XPC message */
         u32 magic;              /* Special number indicating this is xpnet */
-        u64 buf_pa;             /* phys address of buffer to retrieve */
+        unsigned long buf_pa;   /* phys address of buffer to retrieve */
         u32 size;               /* #of bytes in buffer */
         u8 leadin_ignore;       /* #of bytes to ignore at the beginning */
         u8 tailout_ignore;      /* #of bytes to ignore at the end */
@@ -70,11 +57,10 @@ struct xpnet_message {
  *
  * XPC expects each message to exist in an individual cacheline.
  */
-#define XPNET_MSG_SIZE          (L1_CACHE_BYTES - XPC_MSG_PAYLOAD_OFFSET)
+#define XPNET_MSG_SIZE          XPC_MSG_PAYLOAD_MAX_SIZE
 #define XPNET_MSG_DATA_MAX      \
-                (XPNET_MSG_SIZE - (u64)(&((struct xpnet_message *)0)->data))
-#define XPNET_MSG_ALIGNED_SIZE  (L1_CACHE_ALIGN(XPNET_MSG_SIZE))
-#define XPNET_MSG_NENTRIES      (PAGE_SIZE / XPNET_MSG_ALIGNED_SIZE)
+                (XPNET_MSG_SIZE - offsetof(struct xpnet_message, data))
+#define XPNET_MSG_NENTRIES      (PAGE_SIZE / XPC_MSG_MAX_SIZE)
 
 #define XPNET_MAX_KTHREADS      (XPNET_MSG_NENTRIES + 1)
 #define XPNET_MAX_IDLE_KTHREADS (XPNET_MSG_NENTRIES + 1)
@@ -105,7 +91,6 @@ struct xpnet_message {
  * then be released.
  */
 struct xpnet_pending_msg {
-        struct list_head free_list;
         struct sk_buff *skb;
         atomic_t use_count;
 };
@@ -121,7 +106,7 @@ struct net_device *xpnet_device;
  * When we are notified of other partitions activating, we add them to
  * our bitmask of partitions to which we broadcast.
  */
-static u64 xpnet_broadcast_partitions;
+static unsigned long *xpnet_broadcast_partitions;
 /* protect above */
 static DEFINE_SPINLOCK(xpnet_broadcast_lock);
 
@@ -141,16 +126,13 @@ static DEFINE_SPINLOCK(xpnet_broadcast_lock);
 #define XPNET_DEF_MTU (0x8000UL)
 
 /*
- * The partition id is encapsulated in the MAC address.  The following
- * define locates the octet the partid is in.
+ * The partid is encapsulated in the MAC address beginning in the following
+ * octet and it consists of two octets.
  */
-#define XPNET_PARTID_OCTET      1
-#define XPNET_LICENSE_OCTET     2
+#define XPNET_PARTID_OCTET      2
+
+/* Define the XPNET debug device structures to be used with dev_dbg() et al */
 
-/*
- * Define the XPNET debug device structure that is to be used with dev_dbg(),
- * dev_err(), dev_warn(), and dev_info().
- */
 struct device_driver xpnet_dbg_name = {
         .name = "xpnet"
 };
@@ -169,7 +151,8 @@ static void
 xpnet_receive(short partid, int channel, struct xpnet_message *msg)
 {
         struct sk_buff *skb;
-        bte_result_t bret;
+        void *dst;
+        enum xp_retval ret;
         struct xpnet_dev_private *priv =
             (struct xpnet_dev_private *)xpnet_device->priv;
 
@@ -201,7 +184,7 @@ xpnet_receive(short partid, int channel, struct xpnet_message *msg)
 
         /*
          * The allocated skb has some reserved space.
-         * In order to use bte_copy, we need to get the
+         * In order to use xp_remote_memcpy(), we need to get the
          * skb->data pointer moved forward.
          */
         skb_reserve(skb, (L1_CACHE_BYTES - ((u64)skb->data &
@@ -226,26 +209,21 @@ xpnet_receive(short partid, int channel, struct xpnet_message *msg)
                 skb_copy_to_linear_data(skb, &msg->data,
                                         (size_t)msg->embedded_bytes);
         } else {
+                dst = (void *)((u64)skb->data & ~(L1_CACHE_BYTES - 1));
                 dev_dbg(xpnet, "transferring buffer to the skb->data area;\n\t"
-                        "bte_copy(0x%p, 0x%p, %hu)\n", (void *)msg->buf_pa,
-                        (void *)__pa((u64)skb->data & ~(L1_CACHE_BYTES - 1)),
-                        msg->size);
-
-                bret = bte_copy(msg->buf_pa,
-                                __pa((u64)skb->data & ~(L1_CACHE_BYTES - 1)),
-                                msg->size, (BTE_NOTIFY | BTE_WACQUIRE), NULL);
+                        "xp_remote_memcpy(0x%p, 0x%p, %hu)\n", dst,
+                                          (void *)msg->buf_pa, msg->size);
 
-                if (bret != BTE_SUCCESS) {
+                ret = xp_remote_memcpy(xp_pa(dst), msg->buf_pa, msg->size);
+                if (ret != xpSuccess) {
                         /*
-                         * >>> Need better way of cleaning skb.  Currently skb
-                         * >>> appears in_use and we can't just call
-                         * >>> dev_kfree_skb.
+                         * !!! Need better way of cleaning skb.  Currently skb
+                         * !!! appears in_use and we can't just call
+                         * !!! dev_kfree_skb.
                          */
-                        dev_err(xpnet, "bte_copy(0x%p, 0x%p, 0x%hx) returned "
-                                "error=0x%x\n", (void *)msg->buf_pa,
-                                (void *)__pa((u64)skb->data &
-                                             ~(L1_CACHE_BYTES - 1)),
-                                msg->size, bret);
+                        dev_err(xpnet, "xp_remote_memcpy(0x%p, 0x%p, 0x%hx) "
+                                "returned error=0x%x\n", dst,
+                                (void *)msg->buf_pa, msg->size, ret);
 
                         xpc_received(partid, channel, (void *)msg);
 
@@ -285,9 +263,7 @@ static void
 xpnet_connection_activity(enum xp_retval reason, short partid, int channel,
                           void *data, void *key)
 {
-        long bp;
-
-        DBUG_ON(partid <= 0 || partid >= XP_MAX_PARTITIONS);
+        DBUG_ON(partid < 0 || partid >= xp_max_npartitions);
         DBUG_ON(channel != XPC_NET_CHANNEL);
 
         switch (reason) {
@@ -299,31 +275,28 @@ xpnet_connection_activity(enum xp_retval reason, short partid, int channel,
 
         case xpConnected:       /* connection completed to a partition */
                 spin_lock_bh(&xpnet_broadcast_lock);
-                xpnet_broadcast_partitions |= 1UL << (partid - 1);
-                bp = xpnet_broadcast_partitions;
+                __set_bit(partid, xpnet_broadcast_partitions);
                 spin_unlock_bh(&xpnet_broadcast_lock);
 
                 netif_carrier_on(xpnet_device);
 
-                dev_dbg(xpnet, "%s connection created to partition %d; "
-                        "xpnet_broadcast_partitions=0x%lx\n",
-                        xpnet_device->name, partid, bp);
+                dev_dbg(xpnet, "%s connected to partition %d\n",
+                        xpnet_device->name, partid);
                 break;
 
         default:
                 spin_lock_bh(&xpnet_broadcast_lock);
-                xpnet_broadcast_partitions &= ~(1UL << (partid - 1));
-                bp = xpnet_broadcast_partitions;
+                __clear_bit(partid, xpnet_broadcast_partitions);
                 spin_unlock_bh(&xpnet_broadcast_lock);
 
-                if (bp == 0)
+                if (bitmap_empty((unsigned long *)xpnet_broadcast_partitions,
+                                 xp_max_npartitions)) {
                         netif_carrier_off(xpnet_device);
+                }
 
-                dev_dbg(xpnet, "%s disconnected from partition %d; "
-                        "xpnet_broadcast_partitions=0x%lx\n",
-                        xpnet_device->name, partid, bp);
+                dev_dbg(xpnet, "%s disconnected from partition %d\n",
+                        xpnet_device->name, partid);
                 break;
-
         }
 }
 
@@ -334,8 +307,10 @@ xpnet_dev_open(struct net_device *dev)
 
         dev_dbg(xpnet, "calling xpc_connect(%d, 0x%p, NULL, %ld, %ld, %ld, "
                 "%ld)\n", XPC_NET_CHANNEL, xpnet_connection_activity,
-                XPNET_MSG_SIZE, XPNET_MSG_NENTRIES, XPNET_MAX_KTHREADS,
-                XPNET_MAX_IDLE_KTHREADS);
+                (unsigned long)XPNET_MSG_SIZE,
+                (unsigned long)XPNET_MSG_NENTRIES,
+                (unsigned long)XPNET_MAX_KTHREADS,
+                (unsigned long)XPNET_MAX_IDLE_KTHREADS);
 
         ret = xpc_connect(XPC_NET_CHANNEL, xpnet_connection_activity, NULL,
                           XPNET_MSG_SIZE, XPNET_MSG_NENTRIES,
@@ -426,35 +401,74 @@ xpnet_send_completed(enum xp_retval reason, short partid, int channel,
         }
 }
 
+static void
+xpnet_send(struct sk_buff *skb, struct xpnet_pending_msg *queued_msg,
+           u64 start_addr, u64 end_addr, u16 embedded_bytes, int dest_partid)
+{
+        u8 msg_buffer[XPNET_MSG_SIZE];
+        struct xpnet_message *msg = (struct xpnet_message *)&msg_buffer;
+        u16 msg_size = sizeof(struct xpnet_message);
+        enum xp_retval ret;
+
+        msg->embedded_bytes = embedded_bytes;
+        if (unlikely(embedded_bytes != 0)) {
+                msg->version = XPNET_VERSION_EMBED;
+                dev_dbg(xpnet, "calling memcpy(0x%p, 0x%p, 0x%lx)\n",
+                        &msg->data, skb->data, (size_t)embedded_bytes);
+                skb_copy_from_linear_data(skb, &msg->data,
+                                          (size_t)embedded_bytes);
+                msg_size += embedded_bytes - 1;
+        } else {
+                msg->version = XPNET_VERSION;
+        }
+        msg->magic = XPNET_MAGIC;
+        msg->size = end_addr - start_addr;
+        msg->leadin_ignore = (u64)skb->data - start_addr;
+        msg->tailout_ignore = end_addr - (u64)skb_tail_pointer(skb);
+        msg->buf_pa = xp_pa((void *)start_addr);
+
+        dev_dbg(xpnet, "sending XPC message to %d:%d\n"
+                KERN_DEBUG "msg->buf_pa=0x%lx, msg->size=%u, "
+                "msg->leadin_ignore=%u, msg->tailout_ignore=%u\n",
+                dest_partid, XPC_NET_CHANNEL, msg->buf_pa, msg->size,
+                msg->leadin_ignore, msg->tailout_ignore);
+
+        atomic_inc(&queued_msg->use_count);
+
+        ret = xpc_send_notify(dest_partid, XPC_NET_CHANNEL, XPC_NOWAIT, msg,
+                              msg_size, xpnet_send_completed, queued_msg);
+        if (unlikely(ret != xpSuccess))
+                atomic_dec(&queued_msg->use_count);
+}
+
 /*
  * Network layer has formatted a packet (skb) and is ready to place it
  * "on the wire".  Prepare and send an xpnet_message to all partitions
  * which have connected with us and are targets of this packet.
  *
  * MAC-NOTE:  For the XPNET driver, the MAC address contains the
- * destination partition_id.  If the destination partition id word
- * is 0xff, this packet is to broadcast to all partitions.
+ * destination partid.  If the destination partid octets are 0xffff,
+ * this packet is to be broadcast to all connected partitions.
  */
 static int
 xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
         struct xpnet_pending_msg *queued_msg;
-        enum xp_retval ret;
-        struct xpnet_message *msg;
         u64 start_addr, end_addr;
-        long dp;
-        u8 second_mac_octet;
         short dest_partid;
-        struct xpnet_dev_private *priv;
-        u16 embedded_bytes;
-
-        priv = (struct xpnet_dev_private *)dev->priv;
+        struct xpnet_dev_private *priv = (struct xpnet_dev_private *)dev->priv;
+        u16 embedded_bytes = 0;
 
         dev_dbg(xpnet, ">skb->head=0x%p skb->data=0x%p skb->tail=0x%p "
                 "skb->end=0x%p skb->len=%d\n", (void *)skb->head,
                 (void *)skb->data, skb_tail_pointer(skb), skb_end_pointer(skb),
                 skb->len);
 
+        if (skb->data[0] == 0x33) {
+                dev_kfree_skb(skb);
+                return 0;       /* nothing needed to be done */
+        }
+
         /*
          * The xpnet_pending_msg tracks how many outstanding
          * xpc_send_notifies are relying on this skb.  When none
@@ -466,7 +480,6 @@ xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
                          "packet\n", sizeof(struct xpnet_pending_msg));
 
                 priv->stats.tx_errors++;
-
                 return -ENOMEM;
         }
 
@@ -475,7 +488,6 @@ xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
         end_addr = L1_CACHE_ALIGN((u64)skb_tail_pointer(skb));
 
         /* calculate how many bytes to embed in the XPC message */
-        embedded_bytes = 0;
         if (unlikely(skb->len <= XPNET_MSG_DATA_MAX)) {
                 /* skb->data does fit so embed */
                 embedded_bytes = skb->len;
@@ -491,82 +503,28 @@ xpnet_dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
         atomic_set(&queued_msg->use_count, 1);
         queued_msg->skb = skb;
 
-        second_mac_octet = skb->data[XPNET_PARTID_OCTET];
-        if (second_mac_octet == 0xff) {
+        if (skb->data[0] == 0xff) {
                 /* we are being asked to broadcast to all partitions */
-                dp = xpnet_broadcast_partitions;
-        } else if (second_mac_octet != 0) {
-                dp = xpnet_broadcast_partitions &
-                    (1UL << (second_mac_octet - 1));
-        } else {
-                /* 0 is an invalid partid.  Ignore */
-                dp = 0;
-        }
-        dev_dbg(xpnet, "destination Partitions mask (dp) = 0x%lx\n", dp);
-
-        /*
-         * If we wanted to allow promiscuous mode to work like an
-         * unswitched network, this would be a good point to OR in a
-         * mask of partitions which should be receiving all packets.
-         */
-
-        /*
-         * Main send loop.
-         */
-        for (dest_partid = 1; dp && dest_partid < XP_MAX_PARTITIONS;
-             dest_partid++) {
+                for_each_bit(dest_partid, xpnet_broadcast_partitions,
+                             xp_max_npartitions) {
 
-                if (!(dp & (1UL << (dest_partid - 1)))) {
-                        /* not destined for this partition */
-                        continue;
+                        xpnet_send(skb, queued_msg, start_addr, end_addr,
+                                   embedded_bytes, dest_partid);
                 }
+        } else {
+                dest_partid = (short)skb->data[XPNET_PARTID_OCTET + 1];
+                dest_partid |= (short)skb->data[XPNET_PARTID_OCTET + 0] << 8;
 
-                /* remove this partition from the destinations mask */
-                dp &= ~(1UL << (dest_partid - 1));
-
-                /* found a partition to send to */
-
-                ret = xpc_allocate(dest_partid, XPC_NET_CHANNEL,
-                                   XPC_NOWAIT, (void **)&msg);
-                if (unlikely(ret != xpSuccess))
-                        continue;
-
-                msg->embedded_bytes = embedded_bytes;
-                if (unlikely(embedded_bytes != 0)) {
-                        msg->version = XPNET_VERSION_EMBED;
-                        dev_dbg(xpnet, "calling memcpy(0x%p, 0x%p, 0x%lx)\n",
-                                &msg->data, skb->data, (size_t)embedded_bytes);
-                        skb_copy_from_linear_data(skb, &msg->data,
-                                                  (size_t)embedded_bytes);
-                } else {
-                        msg->version = XPNET_VERSION;
-                }
-                msg->magic = XPNET_MAGIC;
-                msg->size = end_addr - start_addr;
-                msg->leadin_ignore = (u64)skb->data - start_addr;
-                msg->tailout_ignore = end_addr - (u64)skb_tail_pointer(skb);
-                msg->buf_pa = __pa(start_addr);
-
-                dev_dbg(xpnet, "sending XPC message to %d:%d\n"
-                        KERN_DEBUG "msg->buf_pa=0x%lx, msg->size=%u, "
-                        "msg->leadin_ignore=%u, msg->tailout_ignore=%u\n",
-                        dest_partid, XPC_NET_CHANNEL, msg->buf_pa, msg->size,
-                        msg->leadin_ignore, msg->tailout_ignore);
-
-                atomic_inc(&queued_msg->use_count);
-
-                ret = xpc_send_notify(dest_partid, XPC_NET_CHANNEL, msg,
-                                      xpnet_send_completed, queued_msg);
-                if (unlikely(ret != xpSuccess)) {
-                        atomic_dec(&queued_msg->use_count);
-                        continue;
+                if (dest_partid >= 0 &&
+                    dest_partid < xp_max_npartitions &&
+                    test_bit(dest_partid, xpnet_broadcast_partitions) != 0) {
+
+                        xpnet_send(skb, queued_msg, start_addr, end_addr,
+                                   embedded_bytes, dest_partid);
                 }
         }
 
         if (atomic_dec_return(&queued_msg->use_count) == 0) {
-                dev_dbg(xpnet, "no partitions to receive packet destined for "
-                        "%d\n", dest_partid);
-
                 dev_kfree_skb(skb);
                 kfree(queued_msg);
         }
@@ -594,23 +552,28 @@ xpnet_dev_tx_timeout(struct net_device *dev)
 static int __init
 xpnet_init(void)
 {
-        int i;
-        u32 license_num;
-        int result = -ENOMEM;
+        int result;
 
-        if (!ia64_platform_is("sn2"))
+        if (!is_shub() && !is_uv())
                 return -ENODEV;
 
         dev_info(xpnet, "registering network device %s\n", XPNET_DEVICE_NAME);
 
+        xpnet_broadcast_partitions = kzalloc(BITS_TO_LONGS(xp_max_npartitions) *
+                                             sizeof(long), GFP_KERNEL);
+        if (xpnet_broadcast_partitions == NULL)
+                return -ENOMEM;
+
         /*
          * use ether_setup() to init the majority of our device
          * structure and then override the necessary pieces.
          */
         xpnet_device = alloc_netdev(sizeof(struct xpnet_dev_private),
                                     XPNET_DEVICE_NAME, ether_setup);
-        if (xpnet_device == NULL)
+        if (xpnet_device == NULL) {
+                kfree(xpnet_broadcast_partitions);
                 return -ENOMEM;
+        }
 
         netif_carrier_off(xpnet_device);
 
@@ -628,14 +591,10 @@ xpnet_init(void)
          * MAC addresses.  We chose the first octet of the MAC to be unlikely
          * to collide with any vendor's officially issued MAC.
          */
-        xpnet_device->dev_addr[0] = 0xfe;
-        xpnet_device->dev_addr[XPNET_PARTID_OCTET] = sn_partition_id;
-        license_num = sn_partition_serial_number_val();
-        for (i = 3; i >= 0; i--) {
-                xpnet_device->dev_addr[XPNET_LICENSE_OCTET + i] =
-                    license_num & 0xff;
-                license_num = license_num >> 8;
-        }
+        xpnet_device->dev_addr[0] = 0x02;     /* locally administered, no OUI */
+
+        xpnet_device->dev_addr[XPNET_PARTID_OCTET + 1] = xp_partition_id;
+        xpnet_device->dev_addr[XPNET_PARTID_OCTET + 0] = (xp_partition_id >> 8);
 
         /*
          * ether_setup() sets this to a multicast device.  We are
@@ -651,8 +610,10 @@ xpnet_init(void)
         xpnet_device->features = NETIF_F_NO_CSUM;
 
         result = register_netdev(xpnet_device);
-        if (result != 0)
+        if (result != 0) {
                 free_netdev(xpnet_device);
+                kfree(xpnet_broadcast_partitions);
+        }
 
         return result;
 }
@@ -666,8 +627,8 @@ xpnet_exit(void)
                  xpnet_device[0].name);
 
         unregister_netdev(xpnet_device);
-
         free_netdev(xpnet_device);
+        kfree(xpnet_broadcast_partitions);
 }
 
 module_exit(xpnet_exit);