netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Stephen Warren <swarren@nvidia.com>,
	"David S . Miller" <davem@davemloft.net>,
	Sasha Levin <sashal@kernel.org>,
	netdev@vger.kernel.org, linux-rdma@vger.kernel.org
Subject: [PATCH AUTOSEL 4.19 27/83] net/mlx4: Get rid of page operation after dma_alloc_coherent
Date: Tue, 12 Feb 2019 21:36:05 -0500	[thread overview]
Message-ID: <20190213023701.20286-27-sashal@kernel.org> (raw)
In-Reply-To: <20190213023701.20286-1-sashal@kernel.org>

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 7262c6310650..288fca826a55 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


  parent reply	other threads:[~2019-02-13  2:55 UTC|newest]

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20190213023701.20286-1-sashal@kernel.org>
2019-02-13  2:35 ` [PATCH AUTOSEL 4.19 21/83] qed: Fix qed_chain_set_prod() for PBL chains with non power of 2 page count Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 22/83] qed: Fix qed_ll2_post_rx_buffer_notify_fw() by adding a write memory barrier Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 23/83] net: hns: Fix use after free identified by SLUB debug Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 24/83] bpf: Fix [::] -> [::1] rewrite in sys_sendmsg Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 25/83] selftests/bpf: Test [::] -> [::1] rewrite in sys_sendmsg in test_sock_addr Sasha Levin
2019-02-13  2:36 ` Sasha Levin [this message]
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 29/83] xprtrdma: Double free in rpcrdma_sendctxs_create() Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 30/83] mlxsw: spectrum_acl: Add cleanup after C-TCAM update error condition Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 31/83] selftests: forwarding: Add a test for VLAN deletion Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 32/83] netfilter: nf_tables: fix leaking object reference count Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 37/83] netfilter: nft_flow_offload: Fix reverse route lookup Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 38/83] bpf: correctly set initial window on active Fast Open sender Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 40/83] bpf: fix panic in stack_map_get_build_id() on i386 and arm32 Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 41/83] netfilter: nft_flow_offload: fix interaction with vrf slave device Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 45/83] net: stmmac: Fix PCI module removal leak Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 46/83] net: stmmac: dwxgmac2: Only clear interrupts that are active Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 47/83] net: stmmac: Check if CBS is supported before configuring Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 48/83] net: stmmac: Fix the logic of checking if RX Watchdog must be enabled Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 49/83] net: stmmac: Prevent RX starvation in stmmac_napi_poll() Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 50/83] isdn: i4l: isdn_tty: Fix some concurrency double-free bugs Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 56/83] netfilter: nft_flow_offload: fix checking method of conntrack helper Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 61/83] vhost: return EINVAL if iovecs size does not match the message size Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 70/83] bpf: don't assume build-id length is always 20 bytes Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 71/83] bpf: zero out build_id for BPF_STACK_BUILD_ID_IP Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 72/83] selftests/bpf: retry tests that expect build-id Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 73/83] atm: he: fix sign-extension overflow on large shift Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 76/83] bpf: bpf_setsockopt: reset sock dst on SO_MARK changes Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 77/83] dpaa_eth: NETIF_F_LLTX requires to do our own update of trans_start Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 78/83] mlxsw: pci: Return error on PCI reset timeout Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 79/83] net: bridge: Mark FDB entries that were added by user as such Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 80/83] mlxsw: spectrum_switchdev: Do not treat static FDB entries as sticky Sasha Levin
2019-02-13  2:36 ` [PATCH AUTOSEL 4.19 81/83] selftests: forwarding: Add a test case for externally learned FDB entries Sasha Levin
2019-02-13  2:37 ` [PATCH AUTOSEL 4.19 82/83] net/mlx5e: Fix wrong (zero) TX drop counter indication for representor Sasha Levin
2019-02-13  2:37 ` [PATCH AUTOSEL 4.19 83/83] isdn: avm: Fix string plus integer warning from Clang Sasha Levin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190213023701.20286-27-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=davem@davemloft.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=stable@vger.kernel.org \
    --cc=swarren@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).