Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:

 1) Fix regression in multi-SKB responses to RTM_GETADDR, from Arthur
    Gautier.

 2) Fix ipv6 frag parsing in openvswitch, from Yi-Hung Wei.

 3) Unbounded recursion in ipv4 and ipv6 GUE tunnels, from Stefano
    Brivio.

 4) Use after free in hns driver, from Yonglong Liu.

 5) icmp6_send() needs to handle the case of NULL skb, from Eric
    Dumazet.

 6) Missing rcu read lock in __inet6_bind() when operating on mapped
    addresses, from David Ahern.

 7) Memory leak in tipc-nl_compat_publ_dump(), from Gustavo A. R. Silva.

 8) Fix PHY vs r8169 module loading ordering issues, from Heiner
    Kallweit.

 9) Fix bridge vlan memory leak, from Ido Schimmel.

10) Dev refcount leak in AF_PACKET, from Jason Gunthorpe.

11) Infoleak in ipv6_local_error(), flow label isn't completely
    initialized. From Eric Dumazet.

12) Handle mv88e6390 errata, from Andrew Lunn.

13) Making vhost/vsock CID hashing consistent, from Zha Bin.

14) Fix lack of UMH cleanup when it unexpectedly exits, from Taehee Yoo.

15) Bridge forwarding must clear skb->tstamp, from Paolo Abeni.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
  bnxt_en: Fix context memory allocation.
  bnxt_en: Fix ring checking logic on 57500 chips.
  mISDN: hfcsusb: Use struct_size() in kzalloc()
  net: clear skb->tstamp in bridge forwarding path
  net: bpfilter: disallow to remove bpfilter module while being used
  net: bpfilter: restart bpfilter_umh when error occurred
  net: bpfilter: use cleanup callback to release umh_info
  umh: add exit routine for UMH process
  isdn: i4l: isdn_tty: Fix some concurrency double-free bugs
  vhost/vsock: fix vhost vsock cid hashing inconsistent
  net: stmmac: Prevent RX starvation in stmmac_napi_poll()
  net: stmmac: Fix the logic of checking if RX Watchdog must be enabled
  net: stmmac: Check if CBS is supported before configuring
  net: stmmac: dwxgmac2: Only clear interrupts that are active
  net: stmmac: Fix PCI module removal leak
  tools/bpf: fix bpftool map dump with bitfields
  tools/bpf: test btf bitfield with >=256 struct member offset
  bpf: fix bpffs bitfield pretty print
  net: ethernet: mediatek: fix warning in phy_start_aneg
  tcp: change txhash on SYN-data timeout
  ...

2 files changed, 79 insertions, 44 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 4b4351141b94..d89a3da89e5a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -57,12 +57,12 @@ static void mlx4_free_icm_pages(struct mlx4_dev *dev, struct mlx4_icm_chunk *chu
 	int i;
 
 	if (chunk->nsg > 0)
-		pci_unmap_sg(dev->persist->pdev, chunk->mem, chunk->npages,
-			     PCI_DMA_BIDIRECTIONAL);
+		dma_unmap_sg(&dev->persist->pdev->dev, chunk->sg, chunk->npages,
+			     DMA_BIDIRECTIONAL);
 
 	for (i = 0; i < chunk->npages; ++i)
-		__free_pages(sg_page(&chunk->mem[i]),
-			     get_order(chunk->mem[i].length));
+		__free_pages(sg_page(&chunk->sg[i]),
+			     get_order(chunk->sg[i].length));
 }
 
 static void mlx4_free_icm_coherent(struct mlx4_dev *dev, struct mlx4_icm_chunk *chunk)
@@ -71,9 +71,9 @@ static void mlx4_free_icm_coherent(struct mlx4_dev *dev, struct mlx4_icm_chunk *
 
 	for (i = 0; i < chunk->npages; ++i)
 		dma_free_coherent(&dev->persist->pdev->dev,
-				  chunk->mem[i].length,
-				  lowmem_page_address(sg_page(&chunk->mem[i])),
-				  sg_dma_address(&chunk->mem[i]));
+				  chunk->buf[i].size,
+				  chunk->buf[i].addr,
+				  chunk->buf[i].dma_addr);
 }
 
 void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm, int coherent)
@@ -111,22 +111,21 @@ static int mlx4_alloc_icm_pages(struct scatterlist *mem, int order,
 	return 0;
 }
 
-static int mlx4_alloc_icm_coherent(struct device *dev, struct scatterlist *mem,
-				    int order, gfp_t gfp_mask)
+static int mlx4_alloc_icm_coherent(struct device *dev, struct mlx4_icm_buf *buf,
+				   int order, gfp_t gfp_mask)
 {
-	void *buf = dma_alloc_coherent(dev, PAGE_SIZE << order,
-				       &sg_dma_address(mem), gfp_mask);
-	if (!buf)
+	buf->addr = dma_alloc_coherent(dev, PAGE_SIZE << order,
+				       &buf->dma_addr, gfp_mask);
+	if (!buf->addr)
 		return -ENOMEM;
 
-	if (offset_in_page(buf)) {
-		dma_free_coherent(dev, PAGE_SIZE << order,
-				  buf, sg_dma_address(mem));
+	if (offset_in_page(buf->addr)) {
+		dma_free_coherent(dev, PAGE_SIZE << order, buf->addr,
+				  buf->dma_addr);
 		return -ENOMEM;
 	}
 
-	sg_set_buf(mem, buf, PAGE_SIZE << order);
-	sg_dma_len(mem) = PAGE_SIZE << order;
+	buf->size = PAGE_SIZE << order;
 	return 0;
 }
 
@@ -159,21 +158,21 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 
 	while (npages > 0) {
 		if (!chunk) {
-			chunk = kmalloc_node(sizeof(*chunk),
+			chunk = kzalloc_node(sizeof(*chunk),
 					     gfp_mask & ~(__GFP_HIGHMEM |
 							  __GFP_NOWARN),
 					     dev->numa_node);
 			if (!chunk) {
-				chunk = kmalloc(sizeof(*chunk),
+				chunk = kzalloc(sizeof(*chunk),
 						gfp_mask & ~(__GFP_HIGHMEM |
 							     __GFP_NOWARN));
 				if (!chunk)
 					goto fail;
 			}
+			chunk->coherent = coherent;
 
-			sg_init_table(chunk->mem, MLX4_ICM_CHUNK_LEN);
-			chunk->npages = 0;
-			chunk->nsg    = 0;
+			if (!coherent)
+				sg_init_table(chunk->sg, MLX4_ICM_CHUNK_LEN);
 			list_add_tail(&chunk->list, &icm->chunk_list);
 		}
 
@@ -186,10 +185,10 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 
 		if (coherent)
 			ret = mlx4_alloc_icm_coherent(&dev->persist->pdev->dev,
-						      &chunk->mem[chunk->npages],
-						      cur_order, mask);
+						&chunk->buf[chunk->npages],
+						cur_order, mask);
 		else
-			ret = mlx4_alloc_icm_pages(&chunk->mem[chunk->npages],
+			ret = mlx4_alloc_icm_pages(&chunk->sg[chunk->npages],
 						   cur_order, mask,
 						   dev->numa_node);
 
@@ -205,9 +204,9 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 		if (coherent)
 			++chunk->nsg;
 		else if (chunk->npages == MLX4_ICM_CHUNK_LEN) {
-			chunk->nsg = pci_map_sg(dev->persist->pdev, chunk->mem,
-						chunk->npages,
-						PCI_DMA_BIDIRECTIONAL);
+			chunk->nsg = dma_map_sg(&dev->persist->pdev->dev,
+						chunk->sg, chunk->npages,
+						DMA_BIDIRECTIONAL);
 
 			if (chunk->nsg <= 0)
 				goto fail;
@@ -220,9 +219,8 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 	}
 
 	if (!coherent && chunk) {
-		chunk->nsg = pci_map_sg(dev->persist->pdev, chunk->mem,
-					chunk->npages,
-					PCI_DMA_BIDIRECTIONAL);
+		chunk->nsg = dma_map_sg(&dev->persist->pdev->dev, chunk->sg,
+					chunk->npages, DMA_BIDIRECTIONAL);
 
 		if (chunk->nsg <= 0)
 			goto fail;
@@ -320,7 +318,7 @@ void *mlx4_table_find(struct mlx4_icm_table *table, u32 obj,
 	u64 idx;
 	struct mlx4_icm_chunk *chunk;
 	struct mlx4_icm *icm;
-	struct page *page = NULL;
+	void *addr = NULL;
 
 	if (!table->lowmem)
 		return NULL;
@@ -336,28 +334,49 @@ void *mlx4_table_find(struct mlx4_icm_table *table, u32 obj,
 
 	list_for_each_entry(chunk, &icm->chunk_list, list) {
 		for (i = 0; i < chunk->npages; ++i) {
+			dma_addr_t dma_addr;
+			size_t len;
+
+			if (table->coherent) {
+				len = chunk->buf[i].size;
+				dma_addr = chunk->buf[i].dma_addr;
+				addr = chunk->buf[i].addr;
+			} else {
+				struct page *page;
+
+				len = sg_dma_len(&chunk->sg[i]);
+				dma_addr = sg_dma_address(&chunk->sg[i]);
+
+				/* XXX: we should never do this for highmem
+				 * allocation.  This function either needs
+				 * to be split, or the kernel virtual address
+				 * return needs to be made optional.
+				 */
+				page = sg_page(&chunk->sg[i]);
+				addr = lowmem_page_address(page);
+			}
+
 			if (dma_handle && dma_offset >= 0) {
-				if (sg_dma_len(&chunk->mem[i]) > dma_offset)
-					*dma_handle = sg_dma_address(&chunk->mem[i]) +
-						dma_offset;
-				dma_offset -= sg_dma_len(&chunk->mem[i]);
+				if (len > dma_offset)
+					*dma_handle = dma_addr + dma_offset;
+				dma_offset -= len;
 			}
+
 			/*
 			 * DMA mapping can merge pages but not split them,
 			 * so if we found the page, dma_handle has already
 			 * been assigned to.
 			 */
-			if (chunk->mem[i].length > offset) {
-				page = sg_page(&chunk->mem[i]);
+			if (len > offset)
 				goto out;
-			}
-			offset -= chunk->mem[i].length;
+			offset -= len;
 		}
 	}
 
+	addr = NULL;
 out:
 	mutex_unlock(&table->mutex);
-	return page ? lowmem_page_address(page) + offset : NULL;
+	return addr ? addr + offset : NULL;
 }
 
 int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.h b/drivers/net/ethernet/mellanox/mlx4/icm.h
index c9169a490557..d199874b1c07 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.h
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.h
@@ -47,11 +47,21 @@ enum {
 	MLX4_ICM_PAGE_SIZE	= 1 << MLX4_ICM_PAGE_SHIFT,
 };
 
+struct mlx4_icm_buf {
+	void			*addr;
+	size_t			size;
+	dma_addr_t		dma_addr;
+};
+
 struct mlx4_icm_chunk {
 	struct list_head	list;
 	int			npages;
 	int			nsg;
-	struct scatterlist	mem[MLX4_ICM_CHUNK_LEN];
+	bool			coherent;
+	union {
+		struct scatterlist	sg[MLX4_ICM_CHUNK_LEN];
+		struct mlx4_icm_buf	buf[MLX4_ICM_CHUNK_LEN];
+	};
 };
 
 struct mlx4_icm {
@@ -114,12 +124,18 @@ static inline void mlx4_icm_next(struct mlx4_icm_iter *iter)
 
 static inline dma_addr_t mlx4_icm_addr(struct mlx4_icm_iter *iter)
 {
-	return sg_dma_address(&iter->chunk->mem[iter->page_idx]);
+	if (iter->chunk->coherent)
+		return iter->chunk->buf[iter->page_idx].dma_addr;
+	else
+		return sg_dma_address(&iter->chunk->sg[iter->page_idx]);
 }
 
 static inline unsigned long mlx4_icm_size(struct mlx4_icm_iter *iter)
 {
-	return sg_dma_len(&iter->chunk->mem[iter->page_idx]);
+	if (iter->chunk->coherent)
+		return iter->chunk->buf[iter->page_idx].size;
+	else
+		return sg_dma_len(&iter->chunk->sg[iter->page_idx]);
 }
 
 int mlx4_MAP_ICM_AUX(struct mlx4_dev *dev, struct mlx4_icm *icm);