4 files changed, 78 insertions, 41 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
index 9062a8434246..c308429dd9c7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
@@ -35,10 +35,10 @@ static inline unsigned int ipv6_clip_hash(struct clip_tbl *d, const u32 *key)
 }
 
 static unsigned int clip_addr_hash(struct clip_tbl *ctbl, const u32 *addr,
-                                   int addr_len)
+                                   u8 v6)
 {
-        return addr_len == 4 ? ipv4_clip_hash(ctbl, addr) :
-                                ipv6_clip_hash(ctbl, addr);
+        return v6 ? ipv6_clip_hash(ctbl, addr) :
+                        ipv4_clip_hash(ctbl, addr);
 }
 
 static int clip6_get_mbox(const struct net_device *dev,
@@ -78,23 +78,22 @@ int cxgb4_clip_get(const struct net_device *dev, const u32 *lip, u8 v6)
         struct clip_entry *ce, *cte;
         u32 *addr = (u32 *)lip;
         int hash;
-        int addr_len;
-        int ret = 0;
+        int ret = -1;
 
         if (!ctbl)
                 return 0;
 
-        if (v6)
-                addr_len = 16;
-        else
-                addr_len = 4;
-
-        hash = clip_addr_hash(ctbl, addr, addr_len);
+        hash = clip_addr_hash(ctbl, addr, v6);
 
         read_lock_bh(&ctbl->lock);
         list_for_each_entry(cte, &ctbl->hash_list[hash], list) {
-                if (addr_len == cte->addr_len &&
-                    memcmp(lip, cte->addr, cte->addr_len) == 0) {
+                if (cte->addr6.sin6_family == AF_INET6 && v6)
+                        ret = memcmp(lip, cte->addr6.sin6_addr.s6_addr,
+                                     sizeof(struct in6_addr));
+                else if (cte->addr.sin_family == AF_INET && !v6)
+                        ret = memcmp(lip, (char *)(&cte->addr.sin_addr),
+                                     sizeof(struct in_addr));
+                if (!ret) {
                         ce = cte;
                         read_unlock_bh(&ctbl->lock);
                         goto found;
@@ -111,15 +110,20 @@ int cxgb4_clip_get(const struct net_device *dev, const u32 *lip, u8 v6)
                 spin_lock_init(&ce->lock);
                 atomic_set(&ce->refcnt, 0);
                 atomic_dec(&ctbl->nfree);
-                ce->addr_len = addr_len;
-                memcpy(ce->addr, lip, addr_len);
                 list_add_tail(&ce->list, &ctbl->hash_list[hash]);
                 if (v6) {
+                        ce->addr6.sin6_family = AF_INET6;
+                        memcpy(ce->addr6.sin6_addr.s6_addr,
+                               lip, sizeof(struct in6_addr));
                         ret = clip6_get_mbox(dev, (const struct in6_addr *)lip);
                         if (ret) {
                                 write_unlock_bh(&ctbl->lock);
                                 return ret;
                         }
+                } else {
+                        ce->addr.sin_family = AF_INET;
+                        memcpy((char *)(&ce->addr.sin_addr), lip,
+                               sizeof(struct in_addr));
                 }
         } else {
                 write_unlock_bh(&ctbl->lock);
@@ -140,19 +144,19 @@ void cxgb4_clip_release(const struct net_device *dev, const u32 *lip, u8 v6)
         struct clip_entry *ce, *cte;
         u32 *addr = (u32 *)lip;
         int hash;
-        int addr_len;
-
-        if (v6)
-                addr_len = 16;
-        else
-                addr_len = 4;
+        int ret = -1;
 
-        hash = clip_addr_hash(ctbl, addr, addr_len);
+        hash = clip_addr_hash(ctbl, addr, v6);
 
         read_lock_bh(&ctbl->lock);
         list_for_each_entry(cte, &ctbl->hash_list[hash], list) {
-                if (addr_len == cte->addr_len &&
-                    memcmp(lip, cte->addr, cte->addr_len) == 0) {
+                if (cte->addr6.sin6_family == AF_INET6 && v6)
+                        ret = memcmp(lip, cte->addr6.sin6_addr.s6_addr,
+                                     sizeof(struct in6_addr));
+                else if (cte->addr.sin_family == AF_INET && !v6)
+                        ret = memcmp(lip, (char *)(&cte->addr.sin_addr),
+                                     sizeof(struct in_addr));
+                if (!ret) {
                         ce = cte;
                         read_unlock_bh(&ctbl->lock);
                         goto found;
@@ -249,10 +253,7 @@ int clip_tbl_show(struct seq_file *seq, void *v)
         for (i = 0 ; i < ctbl->clipt_size;  ++i) {
                 list_for_each_entry(ce, &ctbl->hash_list[i], list) {
                         ip[0] = '\0';
-                        if (ce->addr_len == 16)
-                                sprintf(ip, "%pI6c", ce->addr);
-                        else
-                                sprintf(ip, "%pI4c", ce->addr);
+                        sprintf(ip, "%pISc", &ce->addr);
                         seq_printf(seq, "%-25s   %u\n", ip,
                                    atomic_read(&ce->refcnt));
                 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h
index 2eaba0161cf8..35eb43c6bcbb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.h
@@ -14,8 +14,10 @@ struct clip_entry {
         spinlock_t lock;        /* Hold while modifying clip reference */
         atomic_t refcnt;
         struct list_head list;
-        u32 addr[4];
-        int addr_len;
+        union {
+                struct sockaddr_in addr;
+                struct sockaddr_in6 addr6;
+        };
 };
 
 struct clip_tbl {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index d6cda17efe6e..97842d03675b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -1103,7 +1103,7 @@ int t4_restart_aneg(struct adapter *adap, unsigned int mbox, unsigned int port);
 #define T4_MEMORY_WRITE 0
 #define T4_MEMORY_READ  1
 int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr, u32 len,
-                 __be32 *buf, int dir);
+                 void *buf, int dir);
 static inline int t4_memory_write(struct adapter *adap, int mtype, u32 addr,
                                   u32 len, __be32 *buf)
 {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 4d643b65265e..853c38997c82 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -449,7 +449,7 @@ int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, u64 *ecc)
  *      @mtype: memory type: MEM_EDC0, MEM_EDC1 or MEM_MC
  *      @addr: address within indicated memory type
  *      @len: amount of memory to transfer
- *      @buf: host memory buffer
+ *      @hbuf: host memory buffer
  *      @dir: direction of transfer T4_MEMORY_READ (1) or T4_MEMORY_WRITE (0)
  *
  *      Reads/writes an [almost] arbitrary memory region in the firmware: the
@@ -460,15 +460,17 @@ int t4_edc_read(struct adapter *adap, int idx, u32 addr, __be32 *data, u64 *ecc)
  *      caller's responsibility to perform appropriate byte order conversions.
  */
 int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr,
-                 u32 len, __be32 *buf, int dir)
+                 u32 len, void *hbuf, int dir)
 {
         u32 pos, offset, resid, memoffset;
         u32 edc_size, mc_size, win_pf, mem_reg, mem_aperture, mem_base;
+        u32 *buf;
 
         /* Argument sanity checks ...
          */
-        if (addr & 0x3)
+        if (addr & 0x3 || (uintptr_t)hbuf & 0x3)
                 return -EINVAL;
+        buf = (u32 *)hbuf;
 
         /* It's convenient to be able to handle lengths which aren't a
          * multiple of 32-bits because we often end up transferring files to
@@ -532,14 +534,45 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr,
 
         /* Transfer data to/from the adapter as long as there's an integral
          * number of 32-bit transfers to complete.
+         *
+         * A note on Endianness issues:
+         *
+         * The "register" reads and writes below from/to the PCI-E Memory
+         * Window invoke the standard adapter Big-Endian to PCI-E Link
+         * Little-Endian "swizzel."  As a result, if we have the following
+         * data in adapter memory:
+         *
+         *     Memory:  ... | b0 | b1 | b2 | b3 | ...
+         *     Address:      i+0  i+1  i+2  i+3
+         *
+         * Then a read of the adapter memory via the PCI-E Memory Window
+         * will yield:
+         *
+         *     x = readl(i)
+         *         31                  0
+         *         [ b3 | b2 | b1 | b0 ]
+         *
+         * If this value is stored into local memory on a Little-Endian system
+         * it will show up correctly in local memory as:
+         *
+         *     ( ..., b0, b1, b2, b3, ... )
+         *
+         * But on a Big-Endian system, the store will show up in memory
+         * incorrectly swizzled as:
+         *
+         *     ( ..., b3, b2, b1, b0, ... )
+         *
+         * So we need to account for this in the reads and writes to the
+         * PCI-E Memory Window below by undoing the register read/write
+         * swizzels.
          */
         while (len > 0) {
                 if (dir == T4_MEMORY_READ)
-                        *buf++ = (__force __be32) t4_read_reg(adap,
-                                                        mem_base + offset);
+                        *buf++ = le32_to_cpu((__force __le32)t4_read_reg(adap,
+                                                mem_base + offset));
                 else
                         t4_write_reg(adap, mem_base + offset,
-                                     (__force u32) *buf++);
+                                     (__force u32)cpu_to_le32(*buf++));
                 offset += sizeof(__be32);
                 len -= sizeof(__be32);
 
@@ -568,15 +601,16 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr,
          */
         if (resid) {
                 union {
-                        __be32 word;
+                        u32 word;
                         char byte[4];
                 } last;
                 unsigned char *bp;
                 int i;
 
                 if (dir == T4_MEMORY_READ) {
-                        last.word = (__force __be32) t4_read_reg(adap,
-                                                        mem_base + offset);
+                        last.word = le32_to_cpu(
+                                        (__force __le32)t4_read_reg(adap,
+                                                mem_base + offset));
                         for (bp = (unsigned char *)buf, i = resid; i < 4; i++)
                                 bp[i] = last.byte[i];
                 } else {
@@ -584,7 +618,7 @@ int t4_memory_rw(struct adapter *adap, int win, int mtype, u32 addr,
                         for (i = resid; i < 4; i++)
                                 last.byte[i] = 0;
                         t4_write_reg(adap, mem_base + offset,
-                                     (__force u32) last.word);
+                                     (__force u32)cpu_to_le32(last.word));
                 }
         }