Merge branch 'bnx2x-fix-page-allocation-failure'

Jason Baron says:

====================
bnx2x: page allocation failure

While configuring ~500 multicast addrs, we ran into high order
page allocation failures. They don't need to be high order, and
thus I'm proposing to split them into at most PAGE_SIZE allocations.

Below is a sample failure.

[1201902.617882] bnx2x: [bnx2x_set_mc_list:12374(eth0)]Failed to create multicast MACs list: -12
[1207325.695021] kworker/1:0: page allocation failure: order:2, mode:0xc020
[1207325.702059] CPU: 1 PID: 15805 Comm: kworker/1:0 Tainted: G        W
[1207325.712940] Hardware name: SYNNEX CORPORATION 1x8-X4i SSD 10GE/S5512LE, BIOS V8.810 05/16/2013
[1207325.722284] Workqueue: events bnx2x_sp_rtnl_task [bnx2x]
[1207325.728206]  0000000000000000 ffff88012d873a78 ffffffff8267f7c7 000000000000c020
[1207325.736754]  0000000000000000 ffff88012d873b08 ffffffff8212f8e0 fffffffc00000003
[1207325.745301]  ffff88041ffecd80 ffff880400000030 0000000000000002 0000c0206800da13
[1207325.753846] Call Trace:
[1207325.756789]  [<ffffffff8267f7c7>] dump_stack+0x4d/0x63
[1207325.762426]  [<ffffffff8212f8e0>] warn_alloc_failed+0xe0/0x130
[1207325.768756]  [<ffffffff8213c898>] ? wakeup_kswapd+0x48/0x140
[1207325.774914]  [<ffffffff82132afc>] __alloc_pages_nodemask+0x2bc/0x970
[1207325.781761]  [<ffffffff82173691>] alloc_pages_current+0x91/0x100
[1207325.788260]  [<ffffffff8212fa1e>] alloc_kmem_pages+0xe/0x10
[1207325.794329]  [<ffffffff8214c9c8>] kmalloc_order+0x18/0x50
[1207325.800227]  [<ffffffff8214ca26>] kmalloc_order_trace+0x26/0xb0
[1207325.806642]  [<ffffffff82451c68>] ? _xfer_secondary_pool+0xa8/0x1a0
[1207325.813404]  [<ffffffff8217cfda>] __kmalloc+0x19a/0x1b0
[1207325.819142]  [<ffffffffa02fe975>] bnx2x_set_rx_mode_inner+0x3d5/0x590 [bnx2x]
[1207325.827000]  [<ffffffffa02ff52d>] bnx2x_sp_rtnl_task+0x28d/0x760 [bnx2x]
[1207325.834197]  [<ffffffff820695d4>] process_one_work+0x134/0x3c0
[1207325.840522]  [<ffffffff82069981>] worker_thread+0x121/0x460
[1207325.846585]  [<ffffffff82069860>] ? process_one_work+0x3c0/0x3c0
[1207325.853089]  [<ffffffff8206f039>] kthread+0xc9/0xe0
[1207325.858459]  [<ffffffff82070000>] ? notify_die+0x10/0x40
[1207325.864263]  [<ffffffff8206ef70>] ? kthread_create_on_node+0x180/0x180
[1207325.871288]  [<ffffffff826852d2>] ret_from_fork+0x42/0x70
[1207325.877183]  [<ffffffff8206ef70>] ? kthread_create_on_node+0x180/0x180

v2:
 -make use of list_next_entry()
 -only use PAGE_SIZE allocations
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c

@@ -12563,43 +12563,64 @@ static int bnx2x_close(struct net_device *dev)
 	return 0;
 }
 
+struct bnx2x_mcast_list_elem_group
+{
+	struct list_head mcast_group_link;
+	struct bnx2x_mcast_list_elem mcast_elems[];
+};
+
+#define MCAST_ELEMS_PER_PG \
+	((PAGE_SIZE - sizeof(struct bnx2x_mcast_list_elem_group)) / \
+	sizeof(struct bnx2x_mcast_list_elem))
+
+static void bnx2x_free_mcast_macs_list(struct list_head *mcast_group_list)
+{
+	struct bnx2x_mcast_list_elem_group *current_mcast_group;
+
+	while (!list_empty(mcast_group_list)) {
+		current_mcast_group = list_first_entry(mcast_group_list,
+				      struct bnx2x_mcast_list_elem_group,
+				      mcast_group_link);
+		list_del(&current_mcast_group->mcast_group_link);
+		free_page((unsigned long)current_mcast_group);
+	}
+}
+
 static int bnx2x_init_mcast_macs_list(struct bnx2x *bp,
-				      struct bnx2x_mcast_ramrod_params *p)
+				      struct bnx2x_mcast_ramrod_params *p,
+				      struct list_head *mcast_group_list)
 {
-	int mc_count = netdev_mc_count(bp->dev);
-	struct bnx2x_mcast_list_elem *mc_mac =
-		kcalloc(mc_count, sizeof(*mc_mac), GFP_ATOMIC);
+	struct bnx2x_mcast_list_elem *mc_mac;
 	struct netdev_hw_addr *ha;
+	struct bnx2x_mcast_list_elem_group *current_mcast_group = NULL;
+	int mc_count = netdev_mc_count(bp->dev);
+	int offset = 0;
 
-	if (!mc_mac) {
+	INIT_LIST_HEAD(&p->mcast_list);
+	netdev_for_each_mc_addr(ha, bp->dev) {
+		if (!offset) {
+			current_mcast_group =
+				(struct bnx2x_mcast_list_elem_group *)
+				__get_free_page(GFP_ATOMIC);
+			if (!current_mcast_group) {
+				bnx2x_free_mcast_macs_list(mcast_group_list);
 				BNX2X_ERR("Failed to allocate mc MAC list\n");
 				return -ENOMEM;
 			}
-
-	INIT_LIST_HEAD(&p->mcast_list);
-
-	netdev_for_each_mc_addr(ha, bp->dev) {
+			list_add(&current_mcast_group->mcast_group_link,
+				 mcast_group_list);
+		}
+		mc_mac = &current_mcast_group->mcast_elems[offset];
 		mc_mac->mac = bnx2x_mc_addr(ha);
 		list_add_tail(&mc_mac->link, &p->mcast_list);
-		mc_mac++;
+		offset++;
+		if (offset == MCAST_ELEMS_PER_PG)
+			offset = 0;
 	}
-
 	p->mcast_list_len = mc_count;
-
 	return 0;
 }
 
-static void bnx2x_free_mcast_macs_list(
-	struct bnx2x_mcast_ramrod_params *p)
-{
-	struct bnx2x_mcast_list_elem *mc_mac =
-		list_first_entry(&p->mcast_list, struct bnx2x_mcast_list_elem,
-				 link);
-
-	WARN_ON(!mc_mac);
-	kfree(mc_mac);
-}
-
 /**
  * bnx2x_set_uc_list - configure a new unicast MACs list.
  *
@@ -12647,6 +12668,7 @@ static int bnx2x_set_uc_list(struct bnx2x *bp)
 
 static int bnx2x_set_mc_list_e1x(struct bnx2x *bp)
 {
+	LIST_HEAD(mcast_group_list);
 	struct net_device *dev = bp->dev;
 	struct bnx2x_mcast_ramrod_params rparam = {NULL};
 	int rc = 0;
@@ -12662,7 +12684,7 @@ static int bnx2x_set_mc_list_e1x(struct bnx2x *bp)
 
 	/* then, configure a new MACs list */
 	if (netdev_mc_count(dev)) {
-		rc = bnx2x_init_mcast_macs_list(bp, &rparam);
+		rc = bnx2x_init_mcast_macs_list(bp, &rparam, &mcast_group_list);
 		if (rc)
 			return rc;
 
@@ -12673,7 +12695,7 @@ static int bnx2x_set_mc_list_e1x(struct bnx2x *bp)
 			BNX2X_ERR("Failed to set a new multicast configuration: %d\n",
 				  rc);
 
-		bnx2x_free_mcast_macs_list(&rparam);
+		bnx2x_free_mcast_macs_list(&mcast_group_list);
 	}
 
 	return rc;
@@ -12681,6 +12703,7 @@ static int bnx2x_set_mc_list_e1x(struct bnx2x *bp)
 
 static int bnx2x_set_mc_list(struct bnx2x *bp)
 {
+	LIST_HEAD(mcast_group_list);
 	struct bnx2x_mcast_ramrod_params rparam = {NULL};
 	struct net_device *dev = bp->dev;
 	int rc = 0;
@@ -12692,7 +12715,7 @@ static int bnx2x_set_mc_list(struct bnx2x *bp)
 	rparam.mcast_obj = &bp->mcast_obj;
 
 	if (netdev_mc_count(dev)) {
-		rc = bnx2x_init_mcast_macs_list(bp, &rparam);
+		rc = bnx2x_init_mcast_macs_list(bp, &rparam, &mcast_group_list);
 		if (rc)
 			return rc;
 
@@ -12703,7 +12726,7 @@ static int bnx2x_set_mc_list(struct bnx2x *bp)
 			BNX2X_ERR("Failed to set a new multicast configuration: %d\n",
 				  rc);
 
-		bnx2x_free_mcast_macs_list(&rparam);
+		bnx2x_free_mcast_macs_list(&mcast_group_list);
 	} else {
 		/* If no mc addresses are required, flush the configuration */
 		rc = bnx2x_config_mcast(bp, &rparam, BNX2X_MCAST_CMD_DEL);

drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c

@@ -2606,8 +2606,23 @@ struct bnx2x_mcast_bin_elem {
 	int type; /* BNX2X_MCAST_CMD_SET_{ADD, DEL} */
 };
 
+union bnx2x_mcast_elem {
+	struct bnx2x_mcast_bin_elem bin_elem;
+	struct bnx2x_mcast_mac_elem mac_elem;
+};
+
+struct bnx2x_mcast_elem_group {
+	struct list_head mcast_group_link;
+	union bnx2x_mcast_elem mcast_elems[];
+};
+
+#define MCAST_MAC_ELEMS_PER_PG \
+	((PAGE_SIZE - sizeof(struct bnx2x_mcast_elem_group)) / \
+	sizeof(union bnx2x_mcast_elem))
+
 struct bnx2x_pending_mcast_cmd {
 	struct list_head link;
+	struct list_head group_head;
 	int type; /* BNX2X_MCAST_CMD_X */
 	union {
 		struct list_head macs_head;
@@ -2638,16 +2653,29 @@ static int bnx2x_mcast_wait(struct bnx2x *bp,
 	return 0;
 }
 
+static void bnx2x_free_groups(struct list_head *mcast_group_list)
+{
+	struct bnx2x_mcast_elem_group *current_mcast_group;
+
+	while (!list_empty(mcast_group_list)) {
+		current_mcast_group = list_first_entry(mcast_group_list,
+				      struct bnx2x_mcast_elem_group,
+				      mcast_group_link);
+		list_del(&current_mcast_group->mcast_group_link);
+		free_page((unsigned long)current_mcast_group);
+	}
+}
+
 static int bnx2x_mcast_enqueue_cmd(struct bnx2x *bp,
 				   struct bnx2x_mcast_obj *o,
 				   struct bnx2x_mcast_ramrod_params *p,
 				   enum bnx2x_mcast_cmd cmd)
 {
-	int total_sz;
 	struct bnx2x_pending_mcast_cmd *new_cmd;
-	struct bnx2x_mcast_mac_elem *cur_mac = NULL;
 	struct bnx2x_mcast_list_elem *pos;
-	int macs_list_len = 0, macs_list_len_size;
+	struct bnx2x_mcast_elem_group *elem_group;
+	struct bnx2x_mcast_mac_elem *mac_elem;
+	int total_elems = 0, macs_list_len = 0, offset = 0;
 
 	/* When adding MACs we'll need to store their values */
 	if (cmd == BNX2X_MCAST_CMD_ADD || cmd == BNX2X_MCAST_CMD_SET)
@@ -2657,50 +2685,61 @@ static int bnx2x_mcast_enqueue_cmd(struct bnx2x *bp,
 	if (!p->mcast_list_len)
 		return 0;
 
-	/* For a set command, we need to allocate sufficient memory for all
-	 * the bins, since we can't analyze at this point how much memory would
-	 * be required.
-	 */
-	macs_list_len_size = macs_list_len *
-			     sizeof(struct bnx2x_mcast_mac_elem);
-	if (cmd == BNX2X_MCAST_CMD_SET) {
-		int bin_size = BNX2X_MCAST_BINS_NUM *
-			       sizeof(struct bnx2x_mcast_bin_elem);
-
-		if (bin_size > macs_list_len_size)
-			macs_list_len_size = bin_size;
-	}
-	total_sz = sizeof(*new_cmd) + macs_list_len_size;
-
 	/* Add mcast is called under spin_lock, thus calling with GFP_ATOMIC */
-	new_cmd = kzalloc(total_sz, GFP_ATOMIC);
-
+	new_cmd = kzalloc(sizeof(*new_cmd), GFP_ATOMIC);
 	if (!new_cmd)
 		return -ENOMEM;
 
-	DP(BNX2X_MSG_SP, "About to enqueue a new %d command. macs_list_len=%d\n",
-	   cmd, macs_list_len);
-
 	INIT_LIST_HEAD(&new_cmd->data.macs_head);
-
+	INIT_LIST_HEAD(&new_cmd->group_head);
 	new_cmd->type = cmd;
 	new_cmd->done = false;
 
+	DP(BNX2X_MSG_SP, "About to enqueue a new %d command. macs_list_len=%d\n",
+	   cmd, macs_list_len);
+
 	switch (cmd) {
 	case BNX2X_MCAST_CMD_ADD:
 	case BNX2X_MCAST_CMD_SET:
-		cur_mac = (struct bnx2x_mcast_mac_elem *)
-			  ((u8 *)new_cmd + sizeof(*new_cmd));
-
-		/* Push the MACs of the current command into the pending command
-		 * MACs list: FIFO
+		/* For a set command, we need to allocate sufficient memory for
+		 * all the bins, since we can't analyze at this point how much
+		 * memory would be required.
 		 */
+		total_elems = macs_list_len;
+		if (cmd == BNX2X_MCAST_CMD_SET) {
+			if (total_elems < BNX2X_MCAST_BINS_NUM)
+				total_elems = BNX2X_MCAST_BINS_NUM;
+		}
+		while (total_elems > 0) {
+			elem_group = (struct bnx2x_mcast_elem_group *)
+				     __get_free_page(GFP_ATOMIC | __GFP_ZERO);
+			if (!elem_group) {
+				kfree(new_cmd);
+				bnx2x_free_groups(&new_cmd->group_head);
+				return -ENOMEM;
+			}
+			total_elems -= MCAST_MAC_ELEMS_PER_PG;
+			list_add_tail(&elem_group->mcast_group_link,
+				      &new_cmd->group_head);
+		}
+		elem_group = list_first_entry(&new_cmd->group_head,
+					      struct bnx2x_mcast_elem_group,
+					      mcast_group_link);
 		list_for_each_entry(pos, &p->mcast_list, link) {
-			memcpy(cur_mac->mac, pos->mac, ETH_ALEN);
-			list_add_tail(&cur_mac->link, &new_cmd->data.macs_head);
-			cur_mac++;
+			mac_elem = &elem_group->mcast_elems[offset].mac_elem;
+			memcpy(mac_elem->mac, pos->mac, ETH_ALEN);
+			/* Push the MACs of the current command into the pending
+			 * command MACs list: FIFO
+			 */
+			list_add_tail(&mac_elem->link,
+				      &new_cmd->data.macs_head);
+			offset++;
+			if (offset == MCAST_MAC_ELEMS_PER_PG) {
+				offset = 0;
+				elem_group = list_next_entry(elem_group,
+							     mcast_group_link);
+			}
 		}
-
 		break;
 
 	case BNX2X_MCAST_CMD_DEL:
@@ -2978,7 +3017,8 @@ bnx2x_mcast_hdl_pending_set_e2_convert(struct bnx2x *bp,
 	u64 cur[BNX2X_MCAST_VEC_SZ], req[BNX2X_MCAST_VEC_SZ];
 	struct bnx2x_mcast_mac_elem *pmac_pos, *pmac_pos_n;
 	struct bnx2x_mcast_bin_elem *p_item;
-	int i, cnt = 0, mac_cnt = 0;
+	struct bnx2x_mcast_elem_group *elem_group;
+	int cnt = 0, mac_cnt = 0, offset = 0, i;
 
 	memset(req, 0, sizeof(u64) * BNX2X_MCAST_VEC_SZ);
 	memcpy(cur, o->registry.aprox_match.vec,
@@ -3001,9 +3041,10 @@ bnx2x_mcast_hdl_pending_set_e2_convert(struct bnx2x *bp,
 	 * a list that will be used to configure bins.
 	 */
 	cmd_pos->set_convert = true;
-	p_item = (struct bnx2x_mcast_bin_elem *)(cmd_pos + 1);
 	INIT_LIST_HEAD(&cmd_pos->data.macs_head);
-
+	elem_group = list_first_entry(&cmd_pos->group_head,
+				      struct bnx2x_mcast_elem_group,
+				      mcast_group_link);
 	for (i = 0; i < BNX2X_MCAST_BINS_NUM; i++) {
 		bool b_current = !!BIT_VEC64_TEST_BIT(cur, i);
 		bool b_required = !!BIT_VEC64_TEST_BIT(req, i);
@@ -3011,12 +3052,18 @@ bnx2x_mcast_hdl_pending_set_e2_convert(struct bnx2x *bp,
 		if (b_current == b_required)
 			continue;
 
+		p_item = &elem_group->mcast_elems[offset].bin_elem;
 		p_item->bin = i;
 		p_item->type = b_required ? BNX2X_MCAST_CMD_SET_ADD
 					  : BNX2X_MCAST_CMD_SET_DEL;
 		list_add_tail(&p_item->link , &cmd_pos->data.macs_head);
-		p_item++;
 		cnt++;
+		offset++;
+		if (offset == MCAST_MAC_ELEMS_PER_PG) {
+			offset = 0;
+			elem_group = list_next_entry(elem_group,
+						     mcast_group_link);
+		}
 	}
 
 	/* We now definitely know how many commands are hiding here.
@@ -3103,6 +3150,7 @@ static inline int bnx2x_mcast_handle_pending_cmds_e2(struct bnx2x *bp,
 		 */
 		if (cmd_pos->done) {
 			list_del(&cmd_pos->link);
+			bnx2x_free_groups(&cmd_pos->group_head);
 			kfree(cmd_pos);
 		}
 
@@ -3741,6 +3789,7 @@ static inline int bnx2x_mcast_handle_pending_cmds_e1(
 	}
 
 	list_del(&cmd_pos->link);
+	bnx2x_free_groups(&cmd_pos->group_head);
 	kfree(cmd_pos);
 
 	return cnt;