[PATCH AUTOSEL 4.20 022/105] soc/fsl/qe: fix err handling of ucc_of_parse_tdm

[PATCH AUTOSEL 4.20 022/105] soc/fsl/qe: fix err handling of ucc_of_parse_tdm

[Sasha Levin]

From: Wen Yang <wen.yang99@zte.com.cn>

[ Upstream commit 8d68100ab4ad92560a16a68b72e068613ac4d573 ]

Currently there are some issues with the ucc_of_parse_tdm function:
1, a possible null pointer dereference in ucc_of_parse_tdm,
detected by the semantic patch deref_null.cocci,
with the following warning:
drivers/soc/fsl/qe/qe_tdm.c:177:21-24: ERROR: pdev is NULL but dereferenced.
2, dev gets modified, so in any case that devm_iounmap() will fail
even when the new pdev is valid, because the iomap was done with a
 different pdev.
3, there is no driver bind with the "fsl,t1040-qe-si" or
"fsl,t1040-qe-siram" device. So allocating resources using devm_*()
with these devices won't provide a cleanup path for these resources
when the caller fails.

This patch fixes them.

Suggested-by: Li Yang <leoyang.li@nxp.com>
Suggested-by: Christophe LEROY <christophe.leroy@c-s.fr>
Signed-off-by: Wen Yang <wen.yang99@zte.com.cn>
Reviewed-by: Peng Hao <peng.hao2@zte.com.cn>
CC: Julia Lawall <julia.lawall@lip6.fr>
CC: Zhao Qiang <qiang.zhao@nxp.com>
CC: David S. Miller <davem@davemloft.net>
CC: netdev@vger.kernel.org
CC: linuxppc-dev@lists.ozlabs.org
CC: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/wan/fsl_ucc_hdlc.c | 62 +++++++++++++++++++++++++++++++++-
 drivers/soc/fsl/qe/qe_tdm.c    | 55 ------------------------------
 2 files changed, 61 insertions(+), 56 deletions(-)

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index 4d6409605207..af13d8cf94ad 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -1049,6 +1049,54 @@ static const struct net_device_ops uhdlc_ops = {
 	.ndo_tx_timeout	= uhdlc_tx_timeout,
 };
 
+static int hdlc_map_iomem(char *name, int init_flag, void __iomem **ptr)
+{
+	struct device_node *np;
+	struct platform_device *pdev;
+	struct resource *res;
+	static int siram_init_flag;
+	int ret = 0;
+
+	np = of_find_compatible_node(NULL, NULL, name);
+	if (!np)
+		return -EINVAL;
+
+	pdev = of_find_device_by_node(np);
+	if (!pdev) {
+		pr_err("%pOFn: failed to lookup pdev\n", np);
+		of_node_put(np);
+		return -EINVAL;
+	}
+
+	of_node_put(np);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		ret = -EINVAL;
+		goto error_put_device;
+	}
+	*ptr = ioremap(res->start, resource_size(res));
+	if (!*ptr) {
+		ret = -ENOMEM;
+		goto error_put_device;
+	}
+
+	/* We've remapped the addresses, and we don't need the device any
+	 * more, so we should release it.
+	 */
+	put_device(&pdev->dev);
+
+	if (init_flag && siram_init_flag == 0) {
+		memset_io(*ptr, 0, resource_size(res));
+		siram_init_flag = 1;
+	}
+	return  0;
+
+error_put_device:
+	put_device(&pdev->dev);
+
+	return ret;
+}
+
 static int ucc_hdlc_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
@@ -1143,6 +1191,15 @@ static int ucc_hdlc_probe(struct platform_device *pdev)
 		ret = ucc_of_parse_tdm(np, utdm, ut_info);
 		if (ret)
 			goto free_utdm;
+
+		ret = hdlc_map_iomem("fsl,t1040-qe-si", 0,
+				     (void __iomem **)&utdm->si_regs);
+		if (ret)
+			goto free_utdm;
+		ret = hdlc_map_iomem("fsl,t1040-qe-siram", 1,
+				     (void __iomem **)&utdm->siram);
+		if (ret)
+			goto unmap_si_regs;
 	}
 
 	if (of_property_read_u16(np, "fsl,hmask", &uhdlc_priv->hmask))
@@ -1151,7 +1208,7 @@ static int ucc_hdlc_probe(struct platform_device *pdev)
 	ret = uhdlc_init(uhdlc_priv);
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to init uhdlc\n");
-		goto free_utdm;
+		goto undo_uhdlc_init;
 	}
 
 	dev = alloc_hdlcdev(uhdlc_priv);
@@ -1181,6 +1238,9 @@ static int ucc_hdlc_probe(struct platform_device *pdev)
 free_dev:
 	free_netdev(dev);
 undo_uhdlc_init:
+	iounmap(utdm->siram);
+unmap_si_regs:
+	iounmap(utdm->si_regs);
 free_utdm:
 	if (uhdlc_priv->tsa)
 		kfree(utdm);
diff --git a/drivers/soc/fsl/qe/qe_tdm.c b/drivers/soc/fsl/qe/qe_tdm.c
index f78c34647ca2..76480df195a8 100644
--- a/drivers/soc/fsl/qe/qe_tdm.c
+++ b/drivers/soc/fsl/qe/qe_tdm.c
@@ -44,10 +44,6 @@ int ucc_of_parse_tdm(struct device_node *np, struct ucc_tdm *utdm,
 	const char *sprop;
 	int ret = 0;
 	u32 val;
-	struct resource *res;
-	struct device_node *np2;
-	static int siram_init_flag;
-	struct platform_device *pdev;
 
 	sprop = of_get_property(np, "fsl,rx-sync-clock", NULL);
 	if (sprop) {
@@ -124,57 +120,6 @@ int ucc_of_parse_tdm(struct device_node *np, struct ucc_tdm *utdm,
 	utdm->siram_entry_id = val;
 
 	set_si_param(utdm, ut_info);
-
-	np2 = of_find_compatible_node(NULL, NULL, "fsl,t1040-qe-si");
-	if (!np2)
-		return -EINVAL;
-
-	pdev = of_find_device_by_node(np2);
-	if (!pdev) {
-		pr_err("%pOFn: failed to lookup pdev\n", np2);
-		of_node_put(np2);
-		return -EINVAL;
-	}
-
-	of_node_put(np2);
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	utdm->si_regs = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(utdm->si_regs)) {
-		ret = PTR_ERR(utdm->si_regs);
-		goto err_miss_siram_property;
-	}
-
-	np2 = of_find_compatible_node(NULL, NULL, "fsl,t1040-qe-siram");
-	if (!np2) {
-		ret = -EINVAL;
-		goto err_miss_siram_property;
-	}
-
-	pdev = of_find_device_by_node(np2);
-	if (!pdev) {
-		ret = -EINVAL;
-		pr_err("%pOFn: failed to lookup pdev\n", np2);
-		of_node_put(np2);
-		goto err_miss_siram_property;
-	}
-
-	of_node_put(np2);
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	utdm->siram = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(utdm->siram)) {
-		ret = PTR_ERR(utdm->siram);
-		goto err_miss_siram_property;
-	}
-
-	if (siram_init_flag == 0) {
-		memset_io(utdm->siram, 0,  resource_size(res));
-		siram_init_flag = 1;
-	}
-
-	return ret;
-
-err_miss_siram_property:
-	devm_iounmap(&pdev->dev, utdm->si_regs);
 	return ret;
 }
 EXPORT_SYMBOL(ucc_of_parse_tdm);
-- 
2.19.1

[PATCH AUTOSEL 4.20 032/105] net/mlx4: Get rid of page operation after dma_alloc_coherent

[Sasha Levin]

From: Stephen Warren <swarren@nvidia.com>

[ Upstream commit f65e192af35058e5c82da9e90871b472d24912bc ]

This patch solves a crash at the time of mlx4 driver unload or system
shutdown. The crash occurs because dma_alloc_coherent() returns one
value in mlx4_alloc_icm_coherent(), but a different value is passed to
dma_free_coherent() in mlx4_free_icm_coherent(). In turn this is because
when allocated, that pointer is passed to sg_set_buf() to record it,
then when freed it is re-calculated by calling
lowmem_page_address(sg_page()) which returns a different value. Solve
this by recording the value that dma_alloc_coherent() returns, and
passing this to dma_free_coherent().

This patch is roughly equivalent to commit 378efe798ecf ("RDMA/hns: Get
rid of page operation after dma_alloc_coherent").

Based-on-code-from: Christoph Hellwig <hch@lst.de>
Signed-off-by: Stephen Warren <swarren@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/icm.c | 92 ++++++++++++++----------
 drivers/net/ethernet/mellanox/mlx4/icm.h | 22 +++++-
 2 files changed, 75 insertions(+), 39 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 4b4351141b94..76b84d08a058 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_unmap_sg(dev->persist->pdev, chunk->sg, chunk->npages,
 			     PCI_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);
 
@@ -205,7 +204,7 @@ 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->nsg = pci_map_sg(dev->persist->pdev, chunk->sg,
 						chunk->npages,
 						PCI_DMA_BIDIRECTIONAL);
 
@@ -220,7 +219,7 @@ 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->nsg = pci_map_sg(dev->persist->pdev, chunk->sg,
 					chunk->npages,
 					PCI_DMA_BIDIRECTIONAL);
 
@@ -320,7 +319,7 @@ 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 +335,49 @@ 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);
-- 
2.19.1

[PATCH AUTOSEL 4.20 034/105] xprtrdma: Double free in rpcrdma_sendctxs_create()

[Sasha Levin]

From: Dan Carpenter <dan.carpenter@oracle.com>

[ Upstream commit 6e17f58c486d9554341f70aa5b63b8fbed07b3fa ]

The clean up is handled by the caller, rpcrdma_buffer_create(), so this
call to rpcrdma_sendctxs_destroy() leads to a double free.

Fixes: ae72950abf99 ("xprtrdma: Add data structure to manage RDMA Send arguments")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/xprtrdma/verbs.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index b9bc7f9f6bb9..4ffa6db804bb 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -913,17 +913,13 @@ static int rpcrdma_sendctxs_create(struct rpcrdma_xprt *r_xprt)
 	for (i = 0; i <= buf->rb_sc_last; i++) {
 		sc = rpcrdma_sendctx_create(&r_xprt->rx_ia);
 		if (!sc)
-			goto out_destroy;
+			return -ENOMEM;
 
 		sc->sc_xprt = r_xprt;
 		buf->rb_sc_ctxs[i] = sc;
 	}
 
 	return 0;
-
-out_destroy:
-	rpcrdma_sendctxs_destroy(buf);
-	return -ENOMEM;
 }
 
 /* The sendctx queue is not guaranteed to have a size that is a
-- 
2.19.1

[PATCH AUTOSEL 4.20 035/105] mlxsw: spectrum_acl: Add cleanup after C-TCAM update error condition

[Sasha Levin]

From: Nir Dotan <nird@mellanox.com>

[ Upstream commit ff0db43cd6c530ff944773ccf48ece55d32d0c22 ]

When writing to C-TCAM, mlxsw driver uses cregion->ops->entry_insert().
In case of C-TCAM HW insertion error, the opposite action should take
place.
Add error handling case in which the C-TCAM region entry is removed, by
calling cregion->ops->entry_remove().

Fixes: a0a777b9409f ("mlxsw: spectrum_acl: Start using A-TCAM")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c   | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index e3c6fe8b1d40..1dcf152b2813 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -75,7 +75,15 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	act_set = mlxsw_afa_block_first_set(rulei->act_block);
 	mlxsw_reg_ptce2_flex_action_set_memcpy_to(ptce2_pl, act_set);
 
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+	if (err)
+		goto err_ptce2_write;
+
+	return 0;
+
+err_ptce2_write:
+	cregion->ops->entry_remove(cregion, centry);
+	return err;
 }
 
 static void
-- 
2.19.1

[PATCH AUTOSEL 4.20 036/105] mlxsw: spectrum: Add VXLAN dependency for spectrum

[Sasha Levin]

From: Ido Schimmel <idosch@mellanox.com>

[ Upstream commit 143a8e038ac599ca73c6354c8af6a8fdeee9fa7d ]

When VXLAN is a loadable module, MLXSW_SPECTRUM must not be built-in:

drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c:2547: undefined
reference to `vxlan_fdb_find_uc'

Add Kconfig dependency to enforce usable configurations.

Fixes: 1231e04f5bba ("mlxsw: spectrum_switchdev: Add support for VxLAN encapsulation")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: kbuild test robot <lkp@intel.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index 8a291eb36c64..7338c9bac4e6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -78,6 +78,7 @@ config MLXSW_SPECTRUM
 	depends on IPV6 || IPV6=n
 	depends on NET_IPGRE || NET_IPGRE=n
 	depends on IPV6_GRE || IPV6_GRE=n
+	depends on VXLAN || VXLAN=n
 	select GENERIC_ALLOCATOR
 	select PARMAN
 	select MLXFW
-- 
2.19.1

[PATCH AUTOSEL 4.20 037/105] selftests: forwarding: Add a test for VLAN deletion

[Sasha Levin]

From: Ido Schimmel <idosch@mellanox.com>

[ Upstream commit 4fabf3bf93a194c7fa5288da3e0af37e4b943cf3 ]

Add a VLAN on a bridge port, delete it and make sure the PVID VLAN is
not affected.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../selftests/net/forwarding/bridge_vlan_aware.sh | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
index d8313d0438b7..04c6431b2bd8 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding"
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion"
 NUM_NETIFS=4
 CHECK_TC="yes"
 source lib.sh
@@ -96,6 +96,19 @@ flooding()
 	flood_test $swp2 $h1 $h2
 }
 
+vlan_deletion()
+{
+	# Test that the deletion of a VLAN on a bridge port does not affect
+	# the PVID VLAN
+	log_info "Add and delete a VLAN on bridge port $swp1"
+
+	bridge vlan add vid 10 dev $swp1
+	bridge vlan del vid 10 dev $swp1
+
+	ping_ipv4
+	ping_ipv6
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
2.19.1

[PATCH AUTOSEL 4.20 038/105] netfilter: nf_tables: fix leaking object reference count

[Sasha Levin]

From: Taehee Yoo <ap420073@gmail.com>

[ Upstream commit b91d9036883793122cf6575ca4dfbfbdd201a83d ]

There is no code that decreases the reference count of stateful objects
in error path of the nft_add_set_elem(). this causes a leak of reference
count of stateful objects.

Test commands:
   $nft add table ip filter
   $nft add counter ip filter c1
   $nft add map ip filter m1 { type ipv4_addr : counter \;}
   $nft add element ip filter m1 { 1 : c1 }
   $nft add element ip filter m1 { 1 : c1 }
   $nft delete element ip filter m1 { 1 }
   $nft delete counter ip filter c1

Result:
   Error: Could not process rule: Device or resource busy
   delete counter ip filter c1
   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^

At the second 'nft add element ip filter m1 { 1 : c1 }', the reference
count of the 'c1' is increased then it tries to insert into the 'm1'. but
the 'm1' already has same element so it returns -EEXIST.
But it doesn't decrease the reference count of the 'c1' in the error path.
Due to a leak of the reference count of the 'c1', the 'c1' can't be
removed by 'nft delete counter ip filter c1'.

Fixes: 8aeff920dcc9 ("netfilter: nf_tables: add stateful object reference to set elements")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nf_tables_api.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 6e548d7c9f67..aba6ec4a14ce 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4474,6 +4474,8 @@ err6:
 err5:
 	kfree(trans);
 err4:
+	if (obj)
+		obj->use--;
 	kfree(elem.priv);
 err3:
 	if (nla[NFTA_SET_ELEM_DATA] != NULL)
-- 
2.19.1

[PATCH AUTOSEL 4.20 043/105] netfilter: nft_flow_offload: Fix reverse route lookup

[Sasha Levin]

From: wenxu <wenxu@ucloud.cn>

[ Upstream commit a799aea0988ea0d1b1f263e996fdad2f6133c680 ]

Using the following example:

	client 1.1.1.7 ---> 2.2.2.7 which dnat to 10.0.0.7 server

The first reply packet (ie. syn+ack) uses an incorrect destination
address for the reverse route lookup since it uses:

	daddr = ct->tuplehash[!dir].tuple.dst.u3.ip;

which is 2.2.2.7 in the scenario that is described above, while this
should be:

	daddr = ct->tuplehash[dir].tuple.src.u3.ip;

that is 10.0.0.7.

Signed-off-by: wenxu <wenxu@ucloud.cn>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nft_flow_offload.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 974525eb92df..ccdb8f5ababb 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -29,10 +29,10 @@ static int nft_flow_route(const struct nft_pktinfo *pkt,
 	memset(&fl, 0, sizeof(fl));
 	switch (nft_pf(pkt)) {
 	case NFPROTO_IPV4:
-		fl.u.ip4.daddr = ct->tuplehash[!dir].tuple.dst.u3.ip;
+		fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip;
 		break;
 	case NFPROTO_IPV6:
-		fl.u.ip6.daddr = ct->tuplehash[!dir].tuple.dst.u3.in6;
+		fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6;
 		break;
 	}
 
-- 
2.19.1

[PATCH AUTOSEL 4.20 044/105] bpf: correctly set initial window on active Fast Open sender

[Sasha Levin]

From: Yuchung Cheng <ycheng@google.com>

[ Upstream commit 31aa6503a15ba00182ea6dbbf51afb63bf9e851d ]

The existing BPF TCP initial congestion window (TCP_BPF_IW) does not
to work on (active) Fast Open sender. This is because it changes the
(initial) window only if data_segs_out is zero -- but data_segs_out
is also incremented on SYN-data.  This patch fixes the issue by
proerly accounting for SYN-data additionally.

Fixes: fc7478103c84 ("bpf: Adds support for setting initial cwnd")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/filter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index eb0007f30142..fa9452406f21 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4019,7 +4019,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 			/* Only some options are supported */
 			switch (optname) {
 			case TCP_BPF_IW:
-				if (val <= 0 || tp->data_segs_out > 0)
+				if (val <= 0 || tp->data_segs_out > tp->syn_data)
 					ret = -EINVAL;
 				else
 					tp->snd_cwnd = val;
-- 
2.19.1

[PATCH AUTOSEL 4.20 046/105] selftests: bpf: install files tcp_(server|client)*.py

[Sasha Levin]

From: Anders Roxell <anders.roxell@linaro.org>

[ Upstream commit f98937c6bb73ae11717a15aec85c187d33ca5d34 ]

When test_tcpbpf_user runs it complains that it can't find files
tcp_server.py and tcp_client.py.

Rework so that tcp_server.py and tcp_client.py gets installed, added them
to the variable TEST_PROGS_EXTENDED.

Fixes: d6d4f60c3a09 ("bpf: add selftest for tcpbpf")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/Makefile | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index ecd79b7fb107..74ece4f9fcce 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -53,7 +53,9 @@ TEST_PROGS := test_kmod.sh \
 	test_flow_dissector.sh \
 	test_xdp_vlan.sh
 
-TEST_PROGS_EXTENDED := with_addr.sh
+TEST_PROGS_EXTENDED := with_addr.sh \
+	tcp_client.py \
+	tcp_server.py
 
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \
-- 
2.19.1

[PATCH AUTOSEL 4.20 047/105] bpf: fix panic in stack_map_get_build_id() on i386 and arm32

[Sasha Levin]

From: Song Liu <songliubraving@fb.com>

[ Upstream commit beaf3d1901f4ea46fbd5c9d857227d99751de469 ]

As Naresh reported, test_stacktrace_build_id() causes panic on i386 and
arm32 systems. This is caused by page_address() returns NULL in certain
cases.

This patch fixes this error by using kmap_atomic/kunmap_atomic instead
of page_address.

Fixes: 615755a77b24 (" bpf: extend stackmap to save binary_build_id+offset instead of address")
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/stackmap.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 90daf285de03..d9e2483669d0 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -260,7 +260,7 @@ static int stack_map_get_build_id(struct vm_area_struct *vma,
 		return -EFAULT;	/* page not mapped */
 
 	ret = -EINVAL;
-	page_addr = page_address(page);
+	page_addr = kmap_atomic(page);
 	ehdr = (Elf32_Ehdr *)page_addr;
 
 	/* compare magic x7f "ELF" */
@@ -276,6 +276,7 @@ static int stack_map_get_build_id(struct vm_area_struct *vma,
 	else if (ehdr->e_ident[EI_CLASS] == ELFCLASS64)
 		ret = stack_map_get_build_id_64(page_addr, build_id);
 out:
+	kunmap_atomic(page_addr);
 	put_page(page);
 	return ret;
 }
-- 
2.19.1

[PATCH AUTOSEL 4.20 049/105] netfilter: nft_flow_offload: fix interaction with vrf slave device

[Sasha Levin]

From: wenxu <wenxu@ucloud.cn>

[ Upstream commit 10f4e765879e514e1ce7f52ed26603047af196e2 ]

In the forward chain, the iif is changed from slave device to master vrf
device. Thus, flow offload does not find a match on the lower slave
device.

This patch uses the cached route, ie. dst->dev, to update the iif and
oif fields in the flow entry.

After this patch, the following example works fine:

 # ip addr add dev eth0 1.1.1.1/24
 # ip addr add dev eth1 10.0.0.1/24
 # ip link add user1 type vrf table 1
 # ip l set user1 up
 # ip l set dev eth0 master user1
 # ip l set dev eth1 master user1

 # nft add table firewall
 # nft add flowtable f fb1 { hook ingress priority 0 \; devices = { eth0, eth1 } \; }
 # nft add chain f ftb-all {type filter hook forward priority 0 \; policy accept \; }
 # nft add rule f ftb-all ct zone 1 ip protocol tcp flow offload @fb1
 # nft add rule f ftb-all ct zone 1 ip protocol udp flow offload @fb1

Signed-off-by: wenxu <wenxu@ucloud.cn>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/netfilter/nf_flow_table.h | 1 -
 net/netfilter/nf_flow_table_core.c    | 5 +++--
 net/netfilter/nft_flow_offload.c      | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 77e2761d4f2f..ff4eb9869e5b 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -84,7 +84,6 @@ struct flow_offload {
 struct nf_flow_route {
 	struct {
 		struct dst_entry	*dst;
-		int			ifindex;
 	} tuple[FLOW_OFFLOAD_DIR_MAX];
 };
 
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index b7a4816add76..cc91b4d6aa22 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -28,6 +28,7 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
 {
 	struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple;
 	struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple;
+	struct dst_entry *other_dst = route->tuple[!dir].dst;
 	struct dst_entry *dst = route->tuple[dir].dst;
 
 	ft->dir = dir;
@@ -50,8 +51,8 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct,
 	ft->src_port = ctt->src.u.tcp.port;
 	ft->dst_port = ctt->dst.u.tcp.port;
 
-	ft->iifidx = route->tuple[dir].ifindex;
-	ft->oifidx = route->tuple[!dir].ifindex;
+	ft->iifidx = other_dst->dev->ifindex;
+	ft->oifidx = dst->dev->ifindex;
 	ft->dst_cache = dst;
 }
 
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index ccdb8f5ababb..188c6bbf4e16 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -30,9 +30,11 @@ static int nft_flow_route(const struct nft_pktinfo *pkt,
 	switch (nft_pf(pkt)) {
 	case NFPROTO_IPV4:
 		fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip;
+		fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex;
 		break;
 	case NFPROTO_IPV6:
 		fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6;
+		fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex;
 		break;
 	}
 
@@ -41,9 +43,7 @@ static int nft_flow_route(const struct nft_pktinfo *pkt,
 		return -ENOENT;
 
 	route->tuple[dir].dst		= this_dst;
-	route->tuple[dir].ifindex	= nft_in(pkt)->ifindex;
 	route->tuple[!dir].dst		= other_dst;
-	route->tuple[!dir].ifindex	= nft_out(pkt)->ifindex;
 
 	return 0;
 }
-- 
2.19.1

[PATCH AUTOSEL 4.20 053/105] net: stmmac: Fix PCI module removal leak

[Sasha Levin]

From: Jose Abreu <jose.abreu@synopsys.com>

[ Upstream commit 6dea7e1881fd86b80da64e476ac398008daed857 ]

Since commit b7d0f08e9129, the enable / disable of PCI device is not
managed which will result in IO regions not being automatically unmapped.
As regions continue mapped it is currently not possible to remove and
then probe again the PCI module of stmmac.

Fix this by manually unmapping regions on remove callback.

Changes from v1:
- Fix build error

Cc: Joao Pinto <jpinto@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Fixes: b7d0f08e9129 ("net: stmmac: Fix WoL for PCI-based setups")
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index c54a50dbd5ac..d819e8eaba12 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -299,7 +299,17 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
  */
 static void stmmac_pci_remove(struct pci_dev *pdev)
 {
+	int i;
+
 	stmmac_dvr_remove(&pdev->dev);
+
+	for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
+		if (pci_resource_len(pdev, i) == 0)
+			continue;
+		pcim_iounmap_regions(pdev, BIT(i));
+		break;
+	}
+
 	pci_disable_device(pdev);
 }
 
-- 
2.19.1

[PATCH AUTOSEL 4.20 054/105] net: stmmac: dwxgmac2: Only clear interrupts that are active

[Sasha Levin]

From: Jose Abreu <jose.abreu@synopsys.com>

[ Upstream commit fcc509eb10ff4794641e6ad3082118287a750d0a ]

In DMA interrupt handler we were clearing all interrupts status, even
the ones that were not active. Fix this and only clear the active
interrupts.

Cc: Joao Pinto <jpinto@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 6c5092e7771c..c5e25580a43f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -263,6 +263,7 @@ static int dwxgmac2_dma_interrupt(void __iomem *ioaddr,
 				  struct stmmac_extra_stats *x, u32 chan)
 {
 	u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan));
+	u32 intr_en = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
 	int ret = 0;
 
 	/* ABNORMAL interrupts */
@@ -282,8 +283,7 @@ static int dwxgmac2_dma_interrupt(void __iomem *ioaddr,
 		x->normal_irq_n++;
 
 		if (likely(intr_status & XGMAC_RI)) {
-			u32 value = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
-			if (likely(value & XGMAC_RIE)) {
+			if (likely(intr_en & XGMAC_RIE)) {
 				x->rx_normal_irq_n++;
 				ret |= handle_rx;
 			}
@@ -295,7 +295,7 @@ static int dwxgmac2_dma_interrupt(void __iomem *ioaddr,
 	}
 
 	/* Clear interrupts */
-	writel(~0x0, ioaddr + XGMAC_DMA_CH_STATUS(chan));
+	writel(intr_en & intr_status, ioaddr + XGMAC_DMA_CH_STATUS(chan));
 
 	return ret;
 }
-- 
2.19.1

[PATCH AUTOSEL 4.20 055/105] net: stmmac: Check if CBS is supported before configuring

[Sasha Levin]

From: Jose Abreu <jose.abreu@synopsys.com>

[ Upstream commit 0650d4017f4d2eee67230a02285a7ae5204240c2 ]

Check if CBS is currently supported before trying to configure it in HW.

Cc: Joao Pinto <jpinto@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 531294f4978b..58ea18af9813 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -301,6 +301,8 @@ static int tc_setup_cbs(struct stmmac_priv *priv,
 	/* Queue 0 is not AVB capable */
 	if (queue <= 0 || queue >= tx_queues_count)
 		return -EINVAL;
+	if (!priv->dma_cap.av)
+		return -EOPNOTSUPP;
 	if (priv->speed != SPEED_100 && priv->speed != SPEED_1000)
 		return -EOPNOTSUPP;
 
-- 
2.19.1

[PATCH AUTOSEL 4.20 056/105] net: stmmac: Fix the logic of checking if RX Watchdog must be enabled

[Sasha Levin]

From: Jose Abreu <jose.abreu@synopsys.com>

[ Upstream commit 3b5094665e273c4a2a99f7f5f16977c0f1e19095 ]

RX Watchdog can be disabled by platform definitions but currently we are
initializing the descriptors before checking if Watchdog must be
disabled or not.

Fix this by checking earlier if user wants Watchdog disabled or not.

Cc: Joao Pinto <jpinto@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 24 +++++++++----------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c4a35e932f05..fe9240e15aea 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4194,6 +4194,18 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 			return ret;
 	}
 
+	/* Rx Watchdog is available in the COREs newer than the 3.40.
+	 * In some case, for example on bugged HW this feature
+	 * has to be disable and this can be done by passing the
+	 * riwt_off field from the platform.
+	 */
+	if (((priv->synopsys_id >= DWMAC_CORE_3_50) ||
+	    (priv->plat->has_xgmac)) && (!priv->plat->riwt_off)) {
+		priv->use_riwt = 1;
+		dev_info(priv->device,
+			 "Enable RX Mitigation via HW Watchdog Timer\n");
+	}
+
 	return 0;
 }
 
@@ -4326,18 +4338,6 @@ int stmmac_dvr_probe(struct device *device,
 	if (flow_ctrl)
 		priv->flow_ctrl = FLOW_AUTO;	/* RX/TX pause on */
 
-	/* Rx Watchdog is available in the COREs newer than the 3.40.
-	 * In some case, for example on bugged HW this feature
-	 * has to be disable and this can be done by passing the
-	 * riwt_off field from the platform.
-	 */
-	if (((priv->synopsys_id >= DWMAC_CORE_3_50) ||
-	    (priv->plat->has_xgmac)) && (!priv->plat->riwt_off)) {
-		priv->use_riwt = 1;
-		dev_info(priv->device,
-			 "Enable RX Mitigation via HW Watchdog Timer\n");
-	}
-
 	/* Setup channels NAPI */
 	maxq = max(priv->plat->rx_queues_to_use, priv->plat->tx_queues_to_use);
 
-- 
2.19.1

[PATCH AUTOSEL 4.20 057/105] net: stmmac: Prevent RX starvation in stmmac_napi_poll()

[Sasha Levin]

From: Jose Abreu <jose.abreu@synopsys.com>

[ Upstream commit fa0be0a43f101888ac677dba31b590963eafeaa1 ]

Currently, TX is given a budget which is consumed by stmmac_tx_clean()
and stmmac_rx() is given the remaining non-consumed budget.

This is wrong and in case we are sending a large number of packets this
can starve RX because remaining budget will be low.

Let's give always the same budget for RX and TX clean.

While at it, check if we missed any interrupts while we were in NAPI
callback by looking at DMA interrupt status.

Cc: Joao Pinto <jpinto@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 27 ++++++++++---------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index fe9240e15aea..5d83d6a7694b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3525,27 +3525,28 @@ static int stmmac_napi_poll(struct napi_struct *napi, int budget)
 	struct stmmac_channel *ch =
 		container_of(napi, struct stmmac_channel, napi);
 	struct stmmac_priv *priv = ch->priv_data;
-	int work_done = 0, work_rem = budget;
+	int work_done, rx_done = 0, tx_done = 0;
 	u32 chan = ch->index;
 
 	priv->xstats.napi_poll++;
 
-	if (ch->has_tx) {
-		int done = stmmac_tx_clean(priv, work_rem, chan);
+	if (ch->has_tx)
+		tx_done = stmmac_tx_clean(priv, budget, chan);
+	if (ch->has_rx)
+		rx_done = stmmac_rx(priv, budget, chan);
 
-		work_done += done;
-		work_rem -= done;
-	}
-
-	if (ch->has_rx) {
-		int done = stmmac_rx(priv, work_rem, chan);
+	work_done = max(rx_done, tx_done);
+	work_done = min(work_done, budget);
 
-		work_done += done;
-		work_rem -= done;
-	}
+	if (work_done < budget && napi_complete_done(napi, work_done)) {
+		int stat;
 
-	if (work_done < budget && napi_complete_done(napi, work_done))
 		stmmac_enable_dma_irq(priv, priv->ioaddr, chan);
+		stat = stmmac_dma_interrupt_status(priv, priv->ioaddr,
+						   &priv->xstats, chan);
+		if (stat && napi_reschedule(napi))
+			stmmac_disable_dma_irq(priv, priv->ioaddr, chan);
+	}
 
 	return work_done;
 }
-- 
2.19.1

[PATCH AUTOSEL 4.20 058/105] isdn: i4l: isdn_tty: Fix some concurrency double-free bugs

[Sasha Levin]

From: Jia-Ju Bai <baijiaju1990@gmail.com>

[ Upstream commit 2ff33d6637393fe9348357285931811b76e1402f ]

The functions isdn_tty_tiocmset() and isdn_tty_set_termios() may be
concurrently executed.

isdn_tty_tiocmset
  isdn_tty_modem_hup
    line 719: kfree(info->dtmf_state);
    line 721: kfree(info->silence_state);
    line 723: kfree(info->adpcms);
    line 725: kfree(info->adpcmr);

isdn_tty_set_termios
  isdn_tty_modem_hup
    line 719: kfree(info->dtmf_state);
    line 721: kfree(info->silence_state);
    line 723: kfree(info->adpcms);
    line 725: kfree(info->adpcmr);

Thus, some concurrency double-free bugs may occur.

These possible bugs are found by a static tool written by myself and
my manual code review.

To fix these possible bugs, the mutex lock "modem_info_mutex" used in
isdn_tty_tiocmset() is added in isdn_tty_set_termios().

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/isdn/i4l/isdn_tty.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index 1b2239c1d569..dc1cded716c1 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -1437,15 +1437,19 @@ isdn_tty_set_termios(struct tty_struct *tty, struct ktermios *old_termios)
 {
 	modem_info *info = (modem_info *) tty->driver_data;
 
+	mutex_lock(&modem_info_mutex);
 	if (!old_termios)
 		isdn_tty_change_speed(info);
 	else {
 		if (tty->termios.c_cflag == old_termios->c_cflag &&
 		    tty->termios.c_ispeed == old_termios->c_ispeed &&
-		    tty->termios.c_ospeed == old_termios->c_ospeed)
+		    tty->termios.c_ospeed == old_termios->c_ospeed) {
+			mutex_unlock(&modem_info_mutex);
 			return;
+		}
 		isdn_tty_change_speed(info);
 	}
+	mutex_unlock(&modem_info_mutex);
 }
 
 /*
-- 
2.19.1

[PATCH AUTOSEL 4.20 065/105] netfilter: nft_flow_offload: fix checking method of conntrack helper

[Sasha Levin]

From: Henry Yen <henry.yen@mediatek.com>

[ Upstream commit 2314e879747e82896f51cce4488f6a00f3e1af7b ]

This patch uses nfct_help() to detect whether an established connection
needs conntrack helper instead of using test_bit(IPS_HELPER_BIT,
&ct->status).

The reason is that IPS_HELPER_BIT is only set when using explicit CT
target.

However, in the case that a device enables conntrack helper via command
"echo 1 > /proc/sys/net/netfilter/nf_conntrack_helper", the status of
IPS_HELPER_BIT will not present any change, and consequently it loses
the checking ability in the context.

Signed-off-by: Henry Yen <henry.yen@mediatek.com>
Reviewed-by: Ryder Lee <ryder.lee@mediatek.com>
Tested-by: John Crispin <john@phrozen.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nft_flow_offload.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 188c6bbf4e16..6e6b9adf7d38 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -12,6 +12,7 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <linux/netfilter/nf_conntrack_common.h>
 #include <net/netfilter/nf_flow_table.h>
+#include <net/netfilter/nf_conntrack_helper.h>
 
 struct nft_flow_offload {
 	struct nft_flowtable	*flowtable;
@@ -66,6 +67,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 {
 	struct nft_flow_offload *priv = nft_expr_priv(expr);
 	struct nf_flowtable *flowtable = &priv->flowtable->data;
+	const struct nf_conn_help *help;
 	enum ip_conntrack_info ctinfo;
 	struct nf_flow_route route;
 	struct flow_offload *flow;
@@ -88,7 +90,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 		goto out;
 	}
 
-	if (test_bit(IPS_HELPER_BIT, &ct->status))
+	help = nfct_help(ct);
+	if (help)
 		goto out;
 
 	if (ctinfo == IP_CT_NEW ||
-- 
2.19.1

[PATCH AUTOSEL 4.20 070/105] vhost: return EINVAL if iovecs size does not match the message size

[Sasha Levin]

From: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>

[ Upstream commit 74ad7419489ddade8044e3c9ab064ad656520306 ]

We've failed to copy and process vhost_iotlb_msg so let userspace at
least know about it. For instance before these patch the code below runs
without any error:

int main()
{
  struct vhost_msg msg;
  struct iovec iov;
  int fd;

  fd = open("/dev/vhost-net", O_RDWR);
  if (fd == -1) {
    perror("open");
    return 1;
  }

  iov.iov_base = &msg;
  iov.iov_len = sizeof(msg)-4;

  if (writev(fd, &iov,1) == -1) {
    perror("writev");
    return 1;
  }

  return 0;
}

Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/vhost/vhost.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index cf82e7266397..7a07b0e86644 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1035,8 +1035,10 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
 	int type, ret;
 
 	ret = copy_from_iter(&type, sizeof(type), from);
-	if (ret != sizeof(type))
+	if (ret != sizeof(type)) {
+		ret = -EINVAL;
 		goto done;
+	}
 
 	switch (type) {
 	case VHOST_IOTLB_MSG:
@@ -1055,8 +1057,10 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
 
 	iov_iter_advance(from, offset);
 	ret = copy_from_iter(&msg, sizeof(msg), from);
-	if (ret != sizeof(msg))
+	if (ret != sizeof(msg)) {
+		ret = -EINVAL;
 		goto done;
+	}
 	if (vhost_process_iotlb_msg(dev, &msg)) {
 		ret = -EFAULT;
 		goto done;
-- 
2.19.1

[PATCH AUTOSEL 4.20 071/105] vhost/scsi: Use copy_to_iter() to send control queue response

[Sasha Levin]

From: Bijan Mottahedeh <bijan.mottahedeh@oracle.com>

[ Upstream commit 8e5dadfe76cf2862ebf3e4f22adef29982df7766 ]

Uses copy_to_iter() instead of __copy_to_user() in order to ensure we
support arbitrary layouts and an input buffer split across iov entries.

Fixes: 0d02dbd68c47b ("vhost/scsi: Respond to control queue operations")
Signed-off-by: Bijan Mottahedeh <bijan.mottahedeh@oracle.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/vhost/scsi.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 73a4adeab096..11bd8b6422eb 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1132,16 +1132,18 @@ vhost_scsi_send_tmf_reject(struct vhost_scsi *vs,
 			   struct vhost_virtqueue *vq,
 			   struct vhost_scsi_ctx *vc)
 {
-	struct virtio_scsi_ctrl_tmf_resp __user *resp;
 	struct virtio_scsi_ctrl_tmf_resp rsp;
+	struct iov_iter iov_iter;
 	int ret;
 
 	pr_debug("%s\n", __func__);
 	memset(&rsp, 0, sizeof(rsp));
 	rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED;
-	resp = vq->iov[vc->out].iov_base;
-	ret = __copy_to_user(resp, &rsp, sizeof(rsp));
-	if (!ret)
+
+	iov_iter_init(&iov_iter, READ, &vq->iov[vc->out], vc->in, sizeof(rsp));
+
+	ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
+	if (likely(ret == sizeof(rsp)))
 		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
 	else
 		pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n");
@@ -1152,16 +1154,18 @@ vhost_scsi_send_an_resp(struct vhost_scsi *vs,
 			struct vhost_virtqueue *vq,
 			struct vhost_scsi_ctx *vc)
 {
-	struct virtio_scsi_ctrl_an_resp __user *resp;
 	struct virtio_scsi_ctrl_an_resp rsp;
+	struct iov_iter iov_iter;
 	int ret;
 
 	pr_debug("%s\n", __func__);
 	memset(&rsp, 0, sizeof(rsp));	/* event_actual = 0 */
 	rsp.response = VIRTIO_SCSI_S_OK;
-	resp = vq->iov[vc->out].iov_base;
-	ret = __copy_to_user(resp, &rsp, sizeof(rsp));
-	if (!ret)
+
+	iov_iter_init(&iov_iter, READ, &vq->iov[vc->out], vc->in, sizeof(rsp));
+
+	ret = copy_to_iter(&rsp, sizeof(rsp), &iov_iter);
+	if (likely(ret == sizeof(rsp)))
 		vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0);
 	else
 		pr_err("Faulted on virtio_scsi_ctrl_an_resp\n");
-- 
2.19.1

[PATCH AUTOSEL 4.20 072/105] xsk: Check if a queue exists during umem setup

[Sasha Levin]

From: Krzysztof Kazimierczak <krzysztof.kazimierczak@intel.com>

[ Upstream commit cc5b5d3565048ae57d14e5674a5fb085b2ab0193 ]

In the xdp_umem_assign_dev() path, the xsk code does not
check if a queue for which umem is to be created exists.
It leads to a situation where umem is not assigned to any
Tx/Rx queue of a netdevice, without notifying the stack
about an error. This affects both XDP_SKB and XDP_DRV
modes - in case of XDP_DRV_ZC, queue index is checked by
the driver.

This patch fixes xsk code, so that in both XDP_SKB and
XDP_DRV mode of AF_XDP, an error is returned when requested
queue index exceedes an existing maximum.

Fixes: c9b47cc1fabca ("xsk: fix bug when trying to use both copy and zero-copy on one queue id")
Reported-by: Jakub Spizewski <jakub.spizewski@intel.com>
Signed-off-by: Krzysztof Kazimierczak <krzysztof.kazimierczak@intel.com>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/xdp/xdp_umem.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index a264cf2accd0..d4de871e7d4d 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -41,13 +41,20 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
  * not know if the device has more tx queues than rx, or the opposite.
  * This might also change during run time.
  */
-static void xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem,
-				u16 queue_id)
+static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem,
+			       u16 queue_id)
 {
+	if (queue_id >= max_t(unsigned int,
+			      dev->real_num_rx_queues,
+			      dev->real_num_tx_queues))
+		return -EINVAL;
+
 	if (queue_id < dev->real_num_rx_queues)
 		dev->_rx[queue_id].umem = umem;
 	if (queue_id < dev->real_num_tx_queues)
 		dev->_tx[queue_id].umem = umem;
+
+	return 0;
 }
 
 struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
@@ -88,7 +95,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 		goto out_rtnl_unlock;
 	}
 
-	xdp_reg_umem_at_qid(dev, umem, queue_id);
+	err = xdp_reg_umem_at_qid(dev, umem, queue_id);
+	if (err)
+		goto out_rtnl_unlock;
+
 	umem->dev = dev;
 	umem->queue_id = queue_id;
 	if (force_copy)
-- 
2.19.1

[PATCH AUTOSEL 4.20 073/105] selftests/bpf: install with_tunnels.sh for test_flow_dissector.sh

[Sasha Levin]

From: Stanislav Fomichev <sdf@google.com>

[ Upstream commit 1be72f29bfb98be27a95309f18b4ab5249967b59 ]

test_flow_dissector.sh depends on both with_addr.sh and with_tunnels.sh
However, we install only with_addr.sh.

Add with_tunnels.sh to TEST_PROGS_EXTENDED to make sure it gets
installed as well.

Tested with: make TARGETS=bpf install INSTALL_PATH=$PWD/x

Fixes: ef4ab8447aa26 ("selftests: bpf: install script with_addr.sh")
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 74ece4f9fcce..d5e992f7c7dd 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -54,6 +54,7 @@ TEST_PROGS := test_kmod.sh \
 	test_xdp_vlan.sh
 
 TEST_PROGS_EXTENDED := with_addr.sh \
+	with_tunnels.sh \
 	tcp_client.py \
 	tcp_server.py
 
-- 
2.19.1

[PATCH AUTOSEL 4.20 074/105] samples/bpf: workaround clang asm goto compilation errors

[Sasha Levin]

From: Yonghong Song <yhs@fb.com>

[ Upstream commit 6bf3bbe1f4d4cf405e3c2bf07bbdff56d3223ec8 ]

x86 compilation has required asm goto support since 4.17.
Since clang does not support asm goto, at 4.17,
Commit b1ae32dbab50 ("x86/cpufeature: Guard asm_volatile_goto usage
for BPF compilation") worked around the issue by permitting an
alternative implementation without asm goto for clang.

At 5.0, more asm goto usages appeared.
  [yhs@148 x86]$ egrep -r asm_volatile_goto
  include/asm/cpufeature.h:     asm_volatile_goto("1: jmp 6f\n"
  include/asm/jump_label.h:     asm_volatile_goto("1:"
  include/asm/jump_label.h:     asm_volatile_goto("1:"
  include/asm/rmwcc.h:  asm_volatile_goto (fullop "; j" #cc " %l[cc_label]"     \
  include/asm/uaccess.h:        asm_volatile_goto("\n"                          \
  include/asm/uaccess.h:        asm_volatile_goto("\n"                          \
  [yhs@148 x86]$

Compiling samples/bpf directories, most bpf programs failed
compilation with error messages like:
  In file included from /home/yhs/work/bpf-next/samples/bpf/xdp_sample_pkts_kern.c:2:
  In file included from /home/yhs/work/bpf-next/include/linux/ptrace.h:6:
  In file included from /home/yhs/work/bpf-next/include/linux/sched.h:15:
  In file included from /home/yhs/work/bpf-next/include/linux/sem.h:5:
  In file included from /home/yhs/work/bpf-next/include/uapi/linux/sem.h:5:
  In file included from /home/yhs/work/bpf-next/include/linux/ipc.h:9:
  In file included from /home/yhs/work/bpf-next/include/linux/refcount.h:72:
  /home/yhs/work/bpf-next/arch/x86/include/asm/refcount.h:70:9: error: 'asm goto' constructs are not supported yet
        return GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl",
               ^
  /home/yhs/work/bpf-next/arch/x86/include/asm/rmwcc.h:67:2: note: expanded from macro 'GEN_BINARY_SUFFIXED_RMWcc'
        __GEN_RMWcc(op " %[val], %[var]\n\t" suffix, var, cc,           \
        ^
  /home/yhs/work/bpf-next/arch/x86/include/asm/rmwcc.h:21:2: note: expanded from macro '__GEN_RMWcc'
        asm_volatile_goto (fullop "; j" #cc " %l[cc_label]"             \
        ^
  /home/yhs/work/bpf-next/include/linux/compiler_types.h:188:37: note: expanded from macro 'asm_volatile_goto'
  #define asm_volatile_goto(x...) asm goto(x)

Most implementation does not even provide an alternative
implementation. And it is also not practical to make changes
for each call site.

This patch workarounded the asm goto issue by redefining the macro like below:
  #define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")

If asm_volatile_goto is not used by bpf programs, which is typically the case, nothing bad
will happen. If asm_volatile_goto is used by bpf programs, which is incorrect, the compiler
will issue an error since "invalid use of asm_volatile_goto" is not valid assembly codes.

With this patch, all bpf programs under samples/bpf can pass compilation.

Note that bpf programs under tools/testing/selftests/bpf/ compiled fine as
they do not access kernel internal headers.

Fixes: e769742d3584 ("Revert "x86/jump-labels: Macrofy inline assembly code to work around GCC inlining bugs"")
Fixes: 18fe58229d80 ("x86, asm: change the GEN_*_RMWcc() macros to not quote the condition")
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 samples/bpf/Makefile              |  1 +
 samples/bpf/asm_goto_workaround.h | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)
 create mode 100644 samples/bpf/asm_goto_workaround.h

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index be0a961450bc..f5ce993c78e4 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -273,6 +273,7 @@ $(obj)/%.o: $(src)/%.c
 		-Wno-gnu-variable-sized-type-not-at-end \
 		-Wno-address-of-packed-member -Wno-tautological-compare \
 		-Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
+		-I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \
 		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf $(LLC_FLAGS) -filetype=obj -o $@
 ifeq ($(DWARF2BTF),y)
 	$(BTF_PAHOLE) -J $@
diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h
new file mode 100644
index 000000000000..5cd7c1d1a5d5
--- /dev/null
+++ b/samples/bpf/asm_goto_workaround.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Facebook */
+#ifndef __ASM_GOTO_WORKAROUND_H
+#define __ASM_GOTO_WORKAROUND_H
+
+/* this will bring in asm_volatile_goto macro definition
+ * if enabled by compiler and config options.
+ */
+#include <linux/types.h>
+
+#ifdef asm_volatile_goto
+#undef asm_volatile_goto
+#define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")
+#endif
+
+#endif
-- 
2.19.1

[PATCH AUTOSEL 4.20 075/105] SUNRPC: Ensure rq_bytes_sent is reset before request transmission

[Sasha Levin]

From: Trond Myklebust <trondmy@gmail.com>

[ Upstream commit e66721f0436396f779291a29616858b76bfd9415 ]

When we resend a request, ensure that the 'rq_bytes_sent' is reset
to zero.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/clnt.c | 1 -
 net/sunrpc/xprt.c | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 24cbddc44c88..2189fbc4c570 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1738,7 +1738,6 @@ rpc_xdr_encode(struct rpc_task *task)
 	xdr_buf_init(&req->rq_rcv_buf,
 		     req->rq_rbuffer,
 		     req->rq_rcvsize);
-	req->rq_bytes_sent = 0;
 
 	p = rpc_encode_header(task);
 	if (p == NULL) {
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 943f08be7c38..f1ec2110efeb 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1151,6 +1151,7 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 	struct rpc_xprt *xprt = req->rq_xprt;
 
 	if (xprt_request_need_enqueue_transmit(task, req)) {
+		req->rq_bytes_sent = 0;
 		spin_lock(&xprt->queue_lock);
 		/*
 		 * Requests that carry congestion control credits are added
-- 
2.19.1

[PATCH AUTOSEL 4.20 076/105] SUNRPC: Ensure we respect the RPCSEC_GSS sequence number limit

[Sasha Levin]

From: Trond Myklebust <trondmy@gmail.com>

[ Upstream commit 97b78ae96ba76f4ca2d8f5afee6a2e567ccb8f45 ]

According to RFC2203, the RPCSEC_GSS sequence numbers are bounded to
an upper limit of MAXSEQ = 0x80000000. Ensure that we handle that
correctly.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/auth_gss/auth_gss.c | 12 +++++++++---
 net/sunrpc/clnt.c              | 19 ++++++++++++-------
 2 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index ba765473d1f0..efeee5586b2a 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1563,8 +1563,10 @@ gss_marshal(struct rpc_task *task, __be32 *p)
 	cred_len = p++;
 
 	spin_lock(&ctx->gc_seq_lock);
-	req->rq_seqno = ctx->gc_seq++;
+	req->rq_seqno = (ctx->gc_seq < MAXSEQ) ? ctx->gc_seq++ : MAXSEQ;
 	spin_unlock(&ctx->gc_seq_lock);
+	if (req->rq_seqno == MAXSEQ)
+		goto out_expired;
 
 	*p++ = htonl((u32) RPC_GSS_VERSION);
 	*p++ = htonl((u32) ctx->gc_proc);
@@ -1586,14 +1588,18 @@ gss_marshal(struct rpc_task *task, __be32 *p)
 	mic.data = (u8 *)(p + 1);
 	maj_stat = gss_get_mic(ctx->gc_gss_ctx, &verf_buf, &mic);
 	if (maj_stat == GSS_S_CONTEXT_EXPIRED) {
-		clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
+		goto out_expired;
 	} else if (maj_stat != 0) {
-		printk("gss_marshal: gss_get_mic FAILED (%d)\n", maj_stat);
+		pr_warn("gss_marshal: gss_get_mic FAILED (%d)\n", maj_stat);
+		task->tk_status = -EIO;
 		goto out_put_ctx;
 	}
 	p = xdr_encode_opaque(p, NULL, mic.len);
 	gss_put_ctx(ctx);
 	return p;
+out_expired:
+	clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
+	task->tk_status = -EKEYEXPIRED;
 out_put_ctx:
 	gss_put_ctx(ctx);
 	return NULL;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 2189fbc4c570..1ee04e0ec4bc 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1740,11 +1740,8 @@ rpc_xdr_encode(struct rpc_task *task)
 		     req->rq_rcvsize);
 
 	p = rpc_encode_header(task);
-	if (p == NULL) {
-		printk(KERN_INFO "RPC: couldn't encode RPC header, exit EIO\n");
-		rpc_exit(task, -EIO);
+	if (p == NULL)
 		return;
-	}
 
 	encode = task->tk_msg.rpc_proc->p_encode;
 	if (encode == NULL)
@@ -1769,10 +1766,17 @@ call_encode(struct rpc_task *task)
 	/* Did the encode result in an error condition? */
 	if (task->tk_status != 0) {
 		/* Was the error nonfatal? */
-		if (task->tk_status == -EAGAIN || task->tk_status == -ENOMEM)
+		switch (task->tk_status) {
+		case -EAGAIN:
+		case -ENOMEM:
 			rpc_delay(task, HZ >> 4);
-		else
+			break;
+		case -EKEYEXPIRED:
+			task->tk_action = call_refresh;
+			break;
+		default:
 			rpc_exit(task, task->tk_status);
+		}
 		return;
 	}
 
@@ -2334,7 +2338,8 @@ rpc_encode_header(struct rpc_task *task)
 	*p++ = htonl(clnt->cl_vers);	/* program version */
 	*p++ = htonl(task->tk_msg.rpc_proc->p_proc);	/* procedure */
 	p = rpcauth_marshcred(task, p);
-	req->rq_slen = xdr_adjust_iovec(&req->rq_svec[0], p);
+	if (p)
+		req->rq_slen = xdr_adjust_iovec(&req->rq_svec[0], p);
 	return p;
 }
 
-- 
2.19.1

[PATCH AUTOSEL 4.20 080/105] net: phy: micrel: set soft_reset callback to genphy_soft_reset for KSZ9031

[Sasha Levin]

From: Heiner Kallweit <hkallweit1@gmail.com>

[ Upstream commit 1d16073a326891c2a964e4cb95bc18fbcafb5f74 ]

So far genphy_soft_reset was used automatically if the PHY driver
didn't implement the soft_reset callback. This changed with the
mentioned commit and broke KSZ9031. To fix this configure the
KSZ9031 PHY driver to use genphy_soft_reset.

Fixes: 6e2d85ec0559 ("net: phy: Stop with excessive soft reset")
Reported-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Sekhar Nori <nsekhar@ti.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/phy/micrel.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 51611c7a23d1..22dfbd4c6aaf 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1076,6 +1076,7 @@ static struct phy_driver ksphy_driver[] = {
 	.driver_data	= &ksz9021_type,
 	.probe		= kszphy_probe,
 	.config_init	= ksz9031_config_init,
+	.soft_reset	= genphy_soft_reset,
 	.read_status	= ksz9031_read_status,
 	.ack_interrupt	= kszphy_ack_interrupt,
 	.config_intr	= kszphy_config_intr,
-- 
2.19.1

[PATCH AUTOSEL 4.20 089/105] bpf: don't assume build-id length is always 20 bytes

[Sasha Levin]

From: Stanislav Fomichev <sdf@google.com>

[ Upstream commit 0b698005a9d11c0e91141ec11a2c4918a129f703 ]

Build-id length is not fixed to 20, it can be (`man ld` /--build-id):
  * 128-bit (uuid)
  * 160-bit (sha1)
  * any length specified in ld --build-id=0xhexstring

To fix the issue of missing BPF_STACK_BUILD_ID_VALID for shorter build-ids,
assume that build-id is somewhere in the range of 1 .. 20.
Set the remaining bytes to zero.

v2:
* don't introduce new "len = min(BPF_BUILD_ID_SIZE, nhdr->n_descsz)",
  we already know that nhdr->n_descsz <= BPF_BUILD_ID_SIZE if we enter
  this 'if' condition

Fixes: 615755a77b24 ("bpf: extend stackmap to save binary_build_id+offset instead of address")
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/stackmap.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index d9e2483669d0..f9df545e92f6 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -180,11 +180,14 @@ static inline int stack_map_parse_build_id(void *page_addr,
 
 		if (nhdr->n_type == BPF_BUILD_ID &&
 		    nhdr->n_namesz == sizeof("GNU") &&
-		    nhdr->n_descsz == BPF_BUILD_ID_SIZE) {
+		    nhdr->n_descsz > 0 &&
+		    nhdr->n_descsz <= BPF_BUILD_ID_SIZE) {
 			memcpy(build_id,
 			       note_start + note_offs +
 			       ALIGN(sizeof("GNU"), 4) + sizeof(Elf32_Nhdr),
-			       BPF_BUILD_ID_SIZE);
+			       nhdr->n_descsz);
+			memset(build_id + nhdr->n_descsz, 0,
+			       BPF_BUILD_ID_SIZE - nhdr->n_descsz);
 			return 0;
 		}
 		new_offs = note_offs + sizeof(Elf32_Nhdr) +
-- 
2.19.1

[PATCH AUTOSEL 4.20 090/105] bpf: zero out build_id for BPF_STACK_BUILD_ID_IP

[Sasha Levin]

From: Stanislav Fomichev <sdf@google.com>

[ Upstream commit 4af396ae4836c4ecab61e975b8e61270c551894d ]

When returning BPF_STACK_BUILD_ID_IP from stack_map_get_build_id_offset,
make sure that build_id field is empty. Since we are using percpu
free list, there is a possibility that we might reuse some previous
bpf_stack_build_id with non-zero build_id.

Fixes: 615755a77b24 ("bpf: extend stackmap to save binary_build_id+offset instead of address")
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/stackmap.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index f9df545e92f6..d43b14535827 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -314,6 +314,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 		for (i = 0; i < trace_nr; i++) {
 			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
 			id_offs[i].ip = ips[i];
+			memset(id_offs[i].build_id, 0, BPF_BUILD_ID_SIZE);
 		}
 		return;
 	}
@@ -324,6 +325,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
 			/* per entry fall back to ips */
 			id_offs[i].status = BPF_STACK_BUILD_ID_IP;
 			id_offs[i].ip = ips[i];
+			memset(id_offs[i].build_id, 0, BPF_BUILD_ID_SIZE);
 			continue;
 		}
 		id_offs[i].offset = (vma->vm_pgoff << PAGE_SHIFT) + ips[i]
-- 
2.19.1

[PATCH AUTOSEL 4.20 091/105] selftests/bpf: retry tests that expect build-id

[Sasha Levin]

From: Stanislav Fomichev <sdf@google.com>

[ Upstream commit f67ad87ab3120e82845521b18a2b99273a340308 ]

While running test_progs in a loop I found out that I'm sometimes hitting
"Didn't find expected build ID from the map" error.

Looking at stack_map_get_build_id_offset() it seems that it is racy (by
design) and can sometimes return BPF_STACK_BUILD_ID_IP (i.e. can't trylock
current->mm->mmap_sem).

Let's retry this test a single time.

Fixes: 13790d1cc72c ("bpf: add selftest for stackmap with build_id in NMI context")
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/test_progs.c | 30 ++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 2d3c04f45530..998b6cc77ed6 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -1136,7 +1136,9 @@ static void test_stacktrace_build_id(void)
 	int i, j;
 	struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
 	int build_id_matches = 0;
+	int retry = 1;
 
+retry:
 	err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
 	if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
 		goto out;
@@ -1249,6 +1251,19 @@ static void test_stacktrace_build_id(void)
 		previous_key = key;
 	} while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
 
+	/* stack_map_get_build_id_offset() is racy and sometimes can return
+	 * BPF_STACK_BUILD_ID_IP instead of BPF_STACK_BUILD_ID_VALID;
+	 * try it one more time.
+	 */
+	if (build_id_matches < 1 && retry--) {
+		ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
+		close(pmu_fd);
+		bpf_object__close(obj);
+		printf("%s:WARN:Didn't find expected build ID from the map, retrying\n",
+		       __func__);
+		goto retry;
+	}
+
 	if (CHECK(build_id_matches < 1, "build id match",
 		  "Didn't find expected build ID from the map\n"))
 		goto disable_pmu;
@@ -1289,7 +1304,9 @@ static void test_stacktrace_build_id_nmi(void)
 	int i, j;
 	struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
 	int build_id_matches = 0;
+	int retry = 1;
 
+retry:
 	err = bpf_prog_load(file, BPF_PROG_TYPE_PERF_EVENT, &obj, &prog_fd);
 	if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
 		return;
@@ -1384,6 +1401,19 @@ static void test_stacktrace_build_id_nmi(void)
 		previous_key = key;
 	} while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
 
+	/* stack_map_get_build_id_offset() is racy and sometimes can return
+	 * BPF_STACK_BUILD_ID_IP instead of BPF_STACK_BUILD_ID_VALID;
+	 * try it one more time.
+	 */
+	if (build_id_matches < 1 && retry--) {
+		ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
+		close(pmu_fd);
+		bpf_object__close(obj);
+		printf("%s:WARN:Didn't find expected build ID from the map, retrying\n",
+		       __func__);
+		goto retry;
+	}
+
 	if (CHECK(build_id_matches < 1, "build id match",
 		  "Didn't find expected build ID from the map\n"))
 		goto disable_pmu;
-- 
2.19.1

[PATCH AUTOSEL 4.20 092/105] atm: he: fix sign-extension overflow on large shift

[Sasha Levin]

From: Colin Ian King <colin.king@canonical.com>

[ Upstream commit cb12d72b27a6f41325ae23a11033cf5fedfa1b97 ]

Shifting the 1 by exp by an int can lead to sign-extension overlow when
exp is 31 since 1 is an signed int and sign-extending this result to an
unsigned long long will set the upper 32 bits.  Fix this by shifting an
unsigned long.

Detected by cppcheck:
(warning) Shifting signed 32-bit value by 31 bits is undefined behaviour

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/atm/he.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/atm/he.c b/drivers/atm/he.c
index 29f102dcfec4..329ce9072ee9 100644
--- a/drivers/atm/he.c
+++ b/drivers/atm/he.c
@@ -717,7 +717,7 @@ static int he_init_cs_block_rcm(struct he_dev *he_dev)
 			instead of '/ 512', use '>> 9' to prevent a call
 			to divdu3 on x86 platforms
 		*/
-		rate_cps = (unsigned long long) (1 << exp) * (man + 512) >> 9;
+		rate_cps = (unsigned long long) (1UL << exp) * (man + 512) >> 9;
 
 		if (rate_cps < 10)
 			rate_cps = 10;	/* 2.2.1 minimum payload rate is 10 cps */
-- 
2.19.1

[PATCH AUTOSEL 4.20 095/105] bpf: bpf_setsockopt: reset sock dst on SO_MARK changes

[Sasha Levin]

From: Peter Oskolkov <posk@google.com>

[ Upstream commit f4924f24da8c7ef64195096817f3cde324091d97 ]

In sock_setsockopt() (net/core/sock.h), when SO_MARK option is used
to change sk_mark, sk_dst_reset(sk) is called. The same should be
done in bpf_setsockopt().

Fixes: 8c4b4c7e9ff0 ("bpf: Add setsockopt helper function to bpf")
Reported-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/filter.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index fa9452406f21..e176b335ddc0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3948,7 +3948,10 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 			sk->sk_rcvlowat = val ? : 1;
 			break;
 		case SO_MARK:
-			sk->sk_mark = val;
+			if (sk->sk_mark != val) {
+				sk->sk_mark = val;
+				sk_dst_reset(sk);
+			}
 			break;
 		default:
 			ret = -EINVAL;
-- 
2.19.1

[PATCH AUTOSEL 4.20 096/105] bpf: fix SO_MAX_PACING_RATE to support TCP internal pacing

[Sasha Levin]

From: Yuchung Cheng <ycheng@google.com>

[ Upstream commit e224c390a6259c529f7b2a6bd215a087b3344f5c ]

If sch_fq packet scheduler is not used, TCP can fallback to
internal pacing, but this requires sk_pacing_status to
be properly set.

Fixes: 8c4b4c7e9ff0 ("bpf: Add setsockopt helper function to bpf")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Lawrence Brakmo <brakmo@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/filter.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index e176b335ddc0..16350f8c8815 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3935,6 +3935,10 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 			sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF);
 			break;
 		case SO_MAX_PACING_RATE: /* 32bit version */
+			if (val != ~0U)
+				cmpxchg(&sk->sk_pacing_status,
+					SK_PACING_NONE,
+					SK_PACING_NEEDED);
 			sk->sk_max_pacing_rate = (val == ~0U) ? ~0UL : val;
 			sk->sk_pacing_rate = min(sk->sk_pacing_rate,
 						 sk->sk_max_pacing_rate);
-- 
2.19.1

[PATCH AUTOSEL 4.20 097/105] dpaa_eth: NETIF_F_LLTX requires to do our own update of trans_start

[Sasha Levin]

From: Madalin Bucur <madalin.bucur@nxp.com>

[ Upstream commit c6ddfb9a963f0cac0f7365acfc87f3f3b33a3b69 ]

As txq_trans_update() only updates trans_start when the lock is held,
trans_start does not get updated if NETIF_F_LLTX is declared.

Signed-off-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 6e0f47f2c8a3..3e53be0fcd7e 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -2051,6 +2051,7 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 	bool nonlinear = skb_is_nonlinear(skb);
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa_percpu_priv *percpu_priv;
+	struct netdev_queue *txq;
 	struct dpaa_priv *priv;
 	struct qm_fd fd;
 	int offset = 0;
@@ -2100,6 +2101,11 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 	if (unlikely(err < 0))
 		goto skb_to_fd_failed;
 
+	txq = netdev_get_tx_queue(net_dev, queue_mapping);
+
+	/* LLTX requires to do our own update of trans_start */
+	txq->trans_start = jiffies;
+
 	if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
 		fd.cmd |= cpu_to_be32(FM_FD_CMD_UPD);
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-- 
2.19.1

[PATCH AUTOSEL 4.20 098/105] mlxsw: pci: Return error on PCI reset timeout

[Sasha Levin]

From: Nir Dotan <nird@mellanox.com>

[ Upstream commit 67c14cc9b35055264fc0efed00159a7de1819f1b ]

Return an appropriate error in the case when the driver timeouts on waiting
for firmware to go out of PCI reset.

Fixes: 233fa44bd67a ("mlxsw: pci: Implement reset done check")
Signed-off-by: Nir Dotan <nird@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/pci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index c7901a3f2a79..a903e97793f9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1367,10 +1367,10 @@ static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci,
 		u32 val = mlxsw_pci_read32(mlxsw_pci, FW_READY);
 
 		if ((val & MLXSW_PCI_FW_READY_MASK) == MLXSW_PCI_FW_READY_MAGIC)
-			break;
+			return 0;
 		cond_resched();
 	} while (time_before(jiffies, end));
-	return 0;
+	return -EBUSY;
 }
 
 static int mlxsw_pci_alloc_irq_vectors(struct mlxsw_pci *mlxsw_pci)
-- 
2.19.1

[PATCH AUTOSEL 4.20 099/105] net: bridge: Mark FDB entries that were added by user as such

[Sasha Levin]

From: Ido Schimmel <idosch@mellanox.com>

[ Upstream commit 710ae72877378e7cde611efd30fe90502a6e5b30 ]

Externally learned entries can be added by a user or by a switch driver
that is notifying the bridge driver about entries that were learned in
hardware.

In the first case, the entries are not marked with the 'added_by_user'
flag, which causes switch drivers to ignore them and not offload them.

The 'added_by_user' flag can be set on externally learned FDB entries
based on the 'swdev_notify' parameter in br_fdb_external_learn_add(),
which effectively means if the created / updated FDB entry was added by
a user or not.

Fixes: 816a3bed9549 ("switchdev: Add fdb.added_by_user to switchdev notifications")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Cc: Roopa Prabhu <roopa@cumulusnetworks.com>
Cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Cc: bridge@lists.linux-foundation.org
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/bridge/br_fdb.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index e56ba3912a90..8b8abf88befb 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -1102,6 +1102,8 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
 			err = -ENOMEM;
 			goto err_unlock;
 		}
+		if (swdev_notify)
+			fdb->added_by_user = 1;
 		fdb->added_by_external_learn = 1;
 		fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify);
 	} else {
@@ -1121,6 +1123,9 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
 			modified = true;
 		}
 
+		if (swdev_notify)
+			fdb->added_by_user = 1;
+
 		if (modified)
 			fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify);
 	}
-- 
2.19.1

[PATCH AUTOSEL 4.20 100/105] mlxsw: spectrum_switchdev: Do not treat static FDB entries as sticky

[Sasha Levin]

From: Ido Schimmel <idosch@mellanox.com>

[ Upstream commit 64254a2054611205798e6bde634639bc704573ac ]

The driver currently treats static FDB entries as both static and
sticky. This is incorrect and prevents such entries from being roamed to
a different port via learning.

Fix this by configuring static entries with ageing disabled and roaming
enabled.

In net-next we can add proper support for the newly introduced 'sticky'
flag.

Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reported-by: Alexander Petrovskiy <alexpe@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_switchdev.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 69f556ddb934..9fc6b609834b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1244,7 +1244,7 @@ mlxsw_sp_bridge_port_fdb_flush(struct mlxsw_sp *mlxsw_sp,
 static enum mlxsw_reg_sfd_rec_policy mlxsw_sp_sfd_rec_policy(bool dynamic)
 {
 	return dynamic ? MLXSW_REG_SFD_REC_POLICY_DYNAMIC_ENTRY_INGRESS :
-			 MLXSW_REG_SFD_REC_POLICY_STATIC_ENTRY;
+			 MLXSW_REG_SFD_REC_POLICY_DYNAMIC_ENTRY_MLAG;
 }
 
 static enum mlxsw_reg_sfd_op mlxsw_sp_sfd_op(bool adding)
@@ -1301,7 +1301,7 @@ out:
 static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				     const char *mac, u16 fid, bool adding,
 				     enum mlxsw_reg_sfd_rec_action action,
-				     bool dynamic)
+				     enum mlxsw_reg_sfd_rec_policy policy)
 {
 	char *sfd_pl;
 	u8 num_rec;
@@ -1312,8 +1312,7 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		return -ENOMEM;
 
 	mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
-	mlxsw_reg_sfd_uc_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic),
-			      mac, fid, action, local_port);
+	mlxsw_reg_sfd_uc_pack(sfd_pl, 0, policy, mac, fid, action, local_port);
 	num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
 	if (err)
@@ -1332,7 +1331,8 @@ static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				   bool dynamic)
 {
 	return __mlxsw_sp_port_fdb_uc_op(mlxsw_sp, local_port, mac, fid, adding,
-					 MLXSW_REG_SFD_REC_ACTION_NOP, dynamic);
+					 MLXSW_REG_SFD_REC_ACTION_NOP,
+					 mlxsw_sp_sfd_rec_policy(dynamic));
 }
 
 int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
@@ -1340,7 +1340,7 @@ int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
 {
 	return __mlxsw_sp_port_fdb_uc_op(mlxsw_sp, 0, mac, fid, adding,
 					 MLXSW_REG_SFD_REC_ACTION_FORWARD_IP_ROUTER,
-					 false);
+					 MLXSW_REG_SFD_REC_POLICY_STATIC_ENTRY);
 }
 
 static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id,
-- 
2.19.1

[PATCH AUTOSEL 4.20 101/105] selftests: forwarding: Add a test case for externally learned FDB entries

[Sasha Levin]

From: Ido Schimmel <idosch@mellanox.com>

[ Upstream commit 479a2b761d61c04e2ae97325aa391a8a8c99c23e ]

Test that externally learned FDB entries can roam, but not age out.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/forwarding/bridge_vlan_aware.sh       | 34 ++++++++++++++++++-
 1 file changed, 33 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
index 04c6431b2bd8..b90dff8d3a94 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion"
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn"
 NUM_NETIFS=4
 CHECK_TC="yes"
 source lib.sh
@@ -109,6 +109,38 @@ vlan_deletion()
 	ping_ipv6
 }
 
+extern_learn()
+{
+	local mac=de:ad:be:ef:13:37
+	local ageing_time
+
+	# Test that externally learned FDB entries can roam, but not age out
+	RET=0
+
+	bridge fdb add de:ad:be:ef:13:37 dev $swp1 master extern_learn vlan 1
+
+	bridge fdb show brport $swp1 | grep -q de:ad:be:ef:13:37
+	check_err $? "Did not find FDB entry when should"
+
+	# Wait for 10 seconds after the ageing time to make sure the FDB entry
+	# was not aged out
+	ageing_time=$(bridge_ageing_time_get br0)
+	sleep $((ageing_time + 10))
+
+	bridge fdb show brport $swp1 | grep -q de:ad:be:ef:13:37
+	check_err $? "FDB entry was aged out when should not"
+
+	$MZ $h2 -c 1 -p 64 -a $mac -t ip -q
+
+	bridge fdb show brport $swp2 | grep -q de:ad:be:ef:13:37
+	check_err $? "FDB entry did not roam when should"
+
+	log_test "Externally learned FDB entry - ageing & roaming"
+
+	bridge fdb del de:ad:be:ef:13:37 dev $swp2 master vlan 1 &> /dev/null
+	bridge fdb del de:ad:be:ef:13:37 dev $swp1 master vlan 1 &> /dev/null
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
2.19.1

[PATCH AUTOSEL 4.20 103/105] net/mlx5e: Force CHECKSUM_UNNECESSARY for short ethernet frames

[Sasha Levin]

From: Cong Wang <xiyou.wangcong@gmail.com>

[ Upstream commit e8c8b53ccaff568fef4c13a6ccaf08bf241aa01a ]

When an ethernet frame is padded to meet the minimum ethernet frame
size, the padding octets are not covered by the hardware checksum.
Fortunately the padding octets are usually zero's, which don't affect
checksum. However, we have a switch which pads non-zero octets, this
causes kernel hardware checksum fault repeatedly.

Prior to:
commit '88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE ...")'
skb checksum was forced to be CHECKSUM_NONE when padding is detected.
After it, we need to keep skb->csum updated, like what we do for RXFCS.
However, fixing up CHECKSUM_COMPLETE requires to verify and parse IP
headers, it is not worthy the effort as the packets are so small that
CHECKSUM_COMPLETE can't save anything.

Fixes: 88078d98d1bb ("net: pskb_trim_rcsum() and CHECKSUM_COMPLETE are friends"),
Cc: Eric Dumazet <edumazet@google.com>
Cc: Tariq Toukan <tariqt@mellanox.com>
Cc: Nikola Ciprich <nikola.ciprich@linuxbox.cz>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 0b5ef6d4e815..7185f0dd58eb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -732,6 +732,8 @@ static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
 					    ((struct ipv6hdr *)ip_p)->nexthdr;
 }
 
+#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
+
 static inline void mlx5e_handle_csum(struct net_device *netdev,
 				     struct mlx5_cqe64 *cqe,
 				     struct mlx5e_rq *rq,
@@ -754,6 +756,17 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 	if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)))
 		goto csum_unnecessary;
 
+	/* CQE csum doesn't cover padding octets in short ethernet
+	 * frames. And the pad field is appended prior to calculating
+	 * and appending the FCS field.
+	 *
+	 * Detecting these padded frames requires to verify and parse
+	 * IP headers, so we simply force all those small frames to be
+	 * CHECKSUM_UNNECESSARY even if they are not padded.
+	 */
+	if (short_frame(skb->len))
+		goto csum_unnecessary;
+
 	if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) {
 		if (unlikely(get_ip_proto(skb, network_depth, proto) == IPPROTO_SCTP))
 			goto csum_unnecessary;
-- 
2.19.1

[PATCH AUTOSEL 4.20 104/105] net/mlx5e: Fix wrong (zero) TX drop counter indication for representor

[Sasha Levin]

From: Tariq Toukan <tariqt@mellanox.com>

[ Upstream commit 7fdc1adc52d3975740547a78c2df329bb207f15d ]

For representors, the TX dropped counter is not folded from the
per-ring counters. Fix it.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 820fe85100b0..4dccc84fdcf2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -143,6 +143,7 @@ static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
 
 			s->tx_packets		+= sq_stats->packets;
 			s->tx_bytes		+= sq_stats->bytes;
+			s->tx_queue_dropped	+= sq_stats->dropped;
 		}
 	}
 }
-- 
2.19.1

[PATCH AUTOSEL 4.20 105/105] isdn: avm: Fix string plus integer warning from Clang

[Sasha Levin]

From: Nathan Chancellor <natechancellor@gmail.com>

[ Upstream commit 7afa81c55fca0cad589722cb4bce698b4803b0e1 ]

A recent commit in Clang expanded the -Wstring-plus-int warning, showing
some odd behavior in this file.

drivers/isdn/hardware/avm/b1.c:426:30: warning: adding 'int' to a string does not append to the string [-Wstring-plus-int]
                cinfo->version[j] = "\0\0" + 1;
                                    ~~~~~~~^~~
drivers/isdn/hardware/avm/b1.c:426:30: note: use array indexing to silence this warning
                cinfo->version[j] = "\0\0" + 1;
                                           ^
                                    &      [  ]
1 warning generated.

This is equivalent to just "\0". Nick pointed out that it is smarter to
use "" instead of "\0" because "" is used elsewhere in the kernel and
can be deduplicated at the linking stage.

Link: https://github.com/ClangBuiltLinux/linux/issues/309
Suggested-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/isdn/hardware/avm/b1.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/isdn/hardware/avm/b1.c b/drivers/isdn/hardware/avm/b1.c
index 4ac378e48902..40ca1e8fa09f 100644
--- a/drivers/isdn/hardware/avm/b1.c
+++ b/drivers/isdn/hardware/avm/b1.c
@@ -423,7 +423,7 @@ void b1_parse_version(avmctrl_info *cinfo)
 	int i, j;
 
 	for (j = 0; j < AVM_MAXVERSION; j++)
-		cinfo->version[j] = "\0\0" + 1;
+		cinfo->version[j] = "";
 	for (i = 0, j = 0;
 	     j < AVM_MAXVERSION && i < cinfo->versionlen;
 	     j++, i += cinfo->versionbuf[i] + 1)
-- 
2.19.1