1 files changed, 74 insertions, 38 deletions

diff --git a/drivers/net/cxgb4vf/t4vf_hw.c b/drivers/net/cxgb4vf/t4vf_hw.c
index e306c20dfaee..0f51c80475ce 100644
--- a/drivers/net/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/cxgb4vf/t4vf_hw.c
@@ -116,7 +116,7 @@ static void dump_mbox(struct adapter *adapter, const char *tag, u32 mbox_data)
 int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
 		      void *rpl, bool sleep_ok)
 {
-	static int delay[] = {
+	static const int delay[] = {
 		1, 1, 3, 5, 10, 10, 20, 50, 100
 	};
 
@@ -147,9 +147,20 @@ int t4vf_wr_mbox_core(struct adapter *adapter, const void *cmd, int size,
 	/*
 	 * Write the command array into the Mailbox Data register array and
 	 * transfer ownership of the mailbox to the firmware.
+	 *
+	 * For the VFs, the Mailbox Data "registers" are actually backed by
+	 * T4's "MA" interface rather than PL Registers (as is the case for
+	 * the PFs).  Because these are in different coherency domains, the
+	 * write to the VF's PL-register-backed Mailbox Control can race in
+	 * front of the writes to the MA-backed VF Mailbox Data "registers".
+	 * So we need to do a read-back on at least one byte of the VF Mailbox
+	 * Data registers before doing the write to the VF Mailbox Control
+	 * register.
 	 */
 	for (i = 0, p = cmd; i < size; i += 8)
 		t4_write_reg64(adapter, mbox_data + i, be64_to_cpu(*p++));
+	t4_read_reg(adapter, mbox_data);         /* flush write */
+
 	t4_write_reg(adapter, mbox_ctl,
 		     MBMSGVALID | MBOWNER(MBOX_OWNER_FW));
 	t4_read_reg(adapter, mbox_ctl);          /* flush write */
@@ -1014,48 +1025,72 @@ int t4vf_alloc_mac_filt(struct adapter *adapter, unsigned int viid, bool free,
 			unsigned int naddr, const u8 **addr, u16 *idx,
 			u64 *hash, bool sleep_ok)
 {
-	int i, ret;
+	int offset, ret = 0;
+	unsigned nfilters = 0;
+	unsigned int rem = naddr;
 	struct fw_vi_mac_cmd cmd, rpl;
-	struct fw_vi_mac_exact *p;
-	size_t len16;
 
-	if (naddr > ARRAY_SIZE(cmd.u.exact))
+	if (naddr > FW_CLS_TCAM_NUM_ENTRIES)
 		return -EINVAL;
-	len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd,
-				      u.exact[naddr]), 16);
 
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.op_to_viid = cpu_to_be32(FW_CMD_OP(FW_VI_MAC_CMD) |
-				     FW_CMD_REQUEST |
-				     FW_CMD_WRITE |
-				     (free ? FW_CMD_EXEC : 0) |
-				     FW_VI_MAC_CMD_VIID(viid));
-	cmd.freemacs_to_len16 = cpu_to_be32(FW_VI_MAC_CMD_FREEMACS(free) |
-					    FW_CMD_LEN16(len16));
+	for (offset = 0; offset < naddr; /**/) {
+		unsigned int fw_naddr = (rem < ARRAY_SIZE(cmd.u.exact)
+					 ? rem
+					 : ARRAY_SIZE(cmd.u.exact));
+		size_t len16 = DIV_ROUND_UP(offsetof(struct fw_vi_mac_cmd,
+						     u.exact[fw_naddr]), 16);
+		struct fw_vi_mac_exact *p;
+		int i;
 
-	for (i = 0, p = cmd.u.exact; i < naddr; i++, p++) {
-		p->valid_to_idx =
-			cpu_to_be16(FW_VI_MAC_CMD_VALID |
-				    FW_VI_MAC_CMD_IDX(FW_VI_MAC_ADD_MAC));
-		memcpy(p->macaddr, addr[i], sizeof(p->macaddr));
-	}
+		memset(&cmd, 0, sizeof(cmd));
+		cmd.op_to_viid = cpu_to_be32(FW_CMD_OP(FW_VI_MAC_CMD) |
+					     FW_CMD_REQUEST |
+					     FW_CMD_WRITE |
+					     (free ? FW_CMD_EXEC : 0) |
+					     FW_VI_MAC_CMD_VIID(viid));
+		cmd.freemacs_to_len16 =
+			cpu_to_be32(FW_VI_MAC_CMD_FREEMACS(free) |
+				    FW_CMD_LEN16(len16));
+
+		for (i = 0, p = cmd.u.exact; i < fw_naddr; i++, p++) {
+			p->valid_to_idx = cpu_to_be16(
+				FW_VI_MAC_CMD_VALID |
+				FW_VI_MAC_CMD_IDX(FW_VI_MAC_ADD_MAC));
+			memcpy(p->macaddr, addr[offset+i], sizeof(p->macaddr));
+		}
+
+
+		ret = t4vf_wr_mbox_core(adapter, &cmd, sizeof(cmd), &rpl,
+					sleep_ok);
+		if (ret && ret != -ENOMEM)
+			break;
 
-	ret = t4vf_wr_mbox_core(adapter, &cmd, sizeof(cmd), &rpl, sleep_ok);
-	if (ret)
-		return ret;
-
-	for (i = 0, p = rpl.u.exact; i < naddr; i++, p++) {
-		u16 index = FW_VI_MAC_CMD_IDX_GET(be16_to_cpu(p->valid_to_idx));
-
-		if (idx)
-			idx[i] = (index >= FW_CLS_TCAM_NUM_ENTRIES
-				  ? 0xffff
-				  : index);
-		if (index < FW_CLS_TCAM_NUM_ENTRIES)
-			ret++;
-		else if (hash)
-			*hash |= (1 << hash_mac_addr(addr[i]));
+		for (i = 0, p = rpl.u.exact; i < fw_naddr; i++, p++) {
+			u16 index = FW_VI_MAC_CMD_IDX_GET(
+				be16_to_cpu(p->valid_to_idx));
+
+			if (idx)
+				idx[offset+i] =
+					(index >= FW_CLS_TCAM_NUM_ENTRIES
+					 ? 0xffff
+					 : index);
+			if (index < FW_CLS_TCAM_NUM_ENTRIES)
+				nfilters++;
+			else if (hash)
+				*hash |= (1ULL << hash_mac_addr(addr[offset+i]));
+		}
+
+		free = false;
+		offset += fw_naddr;
+		rem -= fw_naddr;
 	}
+
+	/*
+	 * If there were no errors or we merely ran out of room in our MAC
+	 * address arena, return the number of filters actually written.
+	 */
+	if (ret == 0 || ret == -ENOMEM)
+		ret = nfilters;
 	return ret;
 }
 
@@ -1276,7 +1311,7 @@ int t4vf_eth_eq_free(struct adapter *adapter, unsigned int eqid)
  */
 int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl)
 {
-	struct fw_cmd_hdr *cmd_hdr = (struct fw_cmd_hdr *)rpl;
+	const struct fw_cmd_hdr *cmd_hdr = (const struct fw_cmd_hdr *)rpl;
 	u8 opcode = FW_CMD_OP_GET(be32_to_cpu(cmd_hdr->hi));
 
 	switch (opcode) {
@@ -1284,7 +1319,8 @@ int t4vf_handle_fw_rpl(struct adapter *adapter, const __be64 *rpl)
 		/*
 		 * Link/module state change message.
 		 */
-		const struct fw_port_cmd *port_cmd = (void *)rpl;
+		const struct fw_port_cmd *port_cmd =
+			(const struct fw_port_cmd *)rpl;
 		u32 word;
 		int action, port_id, link_ok, speed, fc, pidx;