From 20d60f6364474a978ab2a2146fb4c2bd9b6bbe3f Mon Sep 17 00:00:00 2001
From: Maciej Grochowski <maciej.grochowski@pm.me>
Date: Tue, 14 Apr 2020 00:17:03 -0400
Subject: include/linux/dmaengine: Typos fixes in API documentation

Signed-off-by: Maciej Grochowski <maciej.grochowski@pm.me>
Link: https://lore.kernel.org/r/20200414041703.6661-1-maciek.grochowski@gmail.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/dmaengine.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 21065c04c4ac..31e58ec9f741 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -83,9 +83,9 @@ enum dma_transfer_direction {
 /**
  * Interleaved Transfer Request
  * ----------------------------
- * A chunk is collection of contiguous bytes to be transfered.
+ * A chunk is collection of contiguous bytes to be transferred.
  * The gap(in bytes) between two chunks is called inter-chunk-gap(ICG).
- * ICGs may or maynot change between chunks.
+ * ICGs may or may not change between chunks.
  * A FRAME is the smallest series of contiguous {chunk,icg} pairs,
  *  that when repeated an integral number of times, specifies the transfer.
  * A transfer template is specification of a Frame, the number of times
@@ -1069,7 +1069,7 @@ static inline int dmaengine_terminate_all(struct dma_chan *chan)
  * dmaengine_synchronize() needs to be called before it is safe to free
  * any memory that is accessed by previously submitted descriptors or before
  * freeing any resources accessed from within the completion callback of any
- * perviously submitted descriptors.
+ * previously submitted descriptors.
  *
  * This function can be called from atomic context as well as from within a
  * complete callback of a descriptor submitted on the same channel.
@@ -1091,7 +1091,7 @@ static inline int dmaengine_terminate_async(struct dma_chan *chan)
  *
  * Synchronizes to the DMA channel termination to the current context. When this
  * function returns it is guaranteed that all transfers for previously issued
- * descriptors have stopped and and it is safe to free the memory assoicated
+ * descriptors have stopped and it is safe to free the memory associated
  * with them. Furthermore it is guaranteed that all complete callback functions
  * for a previously submitted descriptor have finished running and it is safe to
  * free resources accessed from within the complete callbacks.
-- 
cgit v1.2.3-59-g8ed1b


From 2b07021a940ce1cdec736ec0cacad6af77717afc Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Thu, 16 Apr 2020 16:54:48 +0200
Subject: debugfs: remove return value of debugfs_create_u32()

No one checks the return value of debugfs_create_u32(), as it's not
needed, so make the return value void, so that no one tries to do so in
the future.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20200416145448.GA1380878@kroah.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/filesystems/debugfs.rst |  4 ++--
 fs/debugfs/file.c                     | 15 +++------------
 include/linux/debugfs.h               | 12 ++++--------
 3 files changed, 9 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/debugfs.rst b/Documentation/filesystems/debugfs.rst
index db9ea0854040..6c032db235a5 100644
--- a/Documentation/filesystems/debugfs.rst
+++ b/Documentation/filesystems/debugfs.rst
@@ -79,8 +79,8 @@ created with any of::
 			   struct dentry *parent, u8 *value);
     void debugfs_create_u16(const char *name, umode_t mode,
 			    struct dentry *parent, u16 *value);
-    struct dentry *debugfs_create_u32(const char *name, umode_t mode,
-				      struct dentry *parent, u32 *value);
+    void debugfs_create_u32(const char *name, umode_t mode,
+			    struct dentry *parent, u32 *value);
     void debugfs_create_u64(const char *name, umode_t mode,
 			    struct dentry *parent, u64 *value);
 
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 2d357680094c..ae49a55bda00 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -506,20 +506,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n");
  * This function creates a file in debugfs with the given name that
  * contains the value of the variable @value.  If the @mode variable is so
  * set, it can be read from, and written to.
- *
- * This function will return a pointer to a dentry if it succeeds.  This
- * pointer must be passed to the debugfs_remove() function when the file is
- * to be removed (no automatic cleanup happens if your module is unloaded,
- * you are responsible here.)  If an error occurs, ERR_PTR(-ERROR) will be
- * returned.
- *
- * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will
- * be returned.
  */
-struct dentry *debugfs_create_u32(const char *name, umode_t mode,
-				 struct dentry *parent, u32 *value)
+void debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent,
+			u32 *value)
 {
-	return debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u32,
+	debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u32,
 				   &fops_u32_ro, &fops_u32_wo);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_u32);
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index a274d95fa66e..63cb3606dea7 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -103,8 +103,8 @@ void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent,
 		       u8 *value);
 void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent,
 			u16 *value);
-struct dentry *debugfs_create_u32(const char *name, umode_t mode,
-				  struct dentry *parent, u32 *value);
+void debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent,
+			u32 *value);
 void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent,
 			u64 *value);
 struct dentry *debugfs_create_ulong(const char *name, umode_t mode,
@@ -250,12 +250,8 @@ static inline void debugfs_create_u8(const char *name, umode_t mode,
 static inline void debugfs_create_u16(const char *name, umode_t mode,
 				      struct dentry *parent, u16 *value) { }
 
-static inline struct dentry *debugfs_create_u32(const char *name, umode_t mode,
-						struct dentry *parent,
-						u32 *value)
-{
-	return ERR_PTR(-ENODEV);
-}
+static inline void debugfs_create_u32(const char *name, umode_t mode,
+				      struct dentry *parent, u32 *value) { }
 
 static inline void debugfs_create_u64(const char *name, umode_t mode,
 				      struct dentry *parent, u64 *value) { }
-- 
cgit v1.2.3-59-g8ed1b


From a07479147be03d2450376ebaff9ea1a0682f25d6 Mon Sep 17 00:00:00 2001
From: Lars Engebretsen <lars@engebretsen.ch>
Date: Wed, 15 Apr 2020 12:10:43 +0200
Subject: iio: core: remove extra semi-colon from devm_iio_device_register()
 macro

This change removes the semi-colon from the devm_iio_device_register()
macro which seems to have been added by accident.

Fixes: 63b19547cc3d9 ("iio: Use macro magic to avoid manual assign of driver_module")
Signed-off-by: Lars Engebretsen <lars@engebretsen.ch>
Cc: <Stable@vger.kernel.org>
Reviewed-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 include/linux/iio/iio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index eed58ed2f368..4e7848415c4f 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -600,7 +600,7 @@ void iio_device_unregister(struct iio_dev *indio_dev);
  * 0 on success, negative error number on failure.
  */
 #define devm_iio_device_register(dev, indio_dev) \
-	__devm_iio_device_register((dev), (indio_dev), THIS_MODULE);
+	__devm_iio_device_register((dev), (indio_dev), THIS_MODULE)
 int __devm_iio_device_register(struct device *dev, struct iio_dev *indio_dev,
 			       struct module *this_mod);
 void devm_iio_device_unregister(struct device *dev, struct iio_dev *indio_dev);
-- 
cgit v1.2.3-59-g8ed1b


From 0821009445a8261ac4d32a6df4b83938e007c765 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Mon, 13 Apr 2020 10:40:12 -0700
Subject: dmaengine: fix channel index enumeration

When the channel register code was changed to allow hotplug operations,
dynamic indexing wasn't taken into account. When channels are randomly
plugged and unplugged out of order, the serial indexing breaks. Convert
channel indexing to using IDA tracking in order to allow dynamic
assignment. The previous code does not cause any regression bug for
existing channel allocation besides idxd driver since the hotplug usage
case is only used by idxd at this point.

With this change, the chan->idr_ref is also not needed any longer. We can
have a device with no channels registered due to hot plug. The channel
device release code no longer should attempt to free the dma device id on
the last channel release.

Fixes: e81274cd6b52 ("dmaengine: add support to dynamic register/unregister of channels")

Reported-by: Yixin Zhang <yixin.zhang@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Tested-by: Yixin Zhang <yixin.zhang@intel.com>
Link: https://lore.kernel.org/r/158679961260.7674.8485924270472851852.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dmaengine.c   | 60 ++++++++++++++++++++---------------------------
 include/linux/dmaengine.h |  4 ++--
 2 files changed, 28 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 4830ba658ce1..d31076d9ef25 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -232,10 +232,6 @@ static void chan_dev_release(struct device *dev)
 	struct dma_chan_dev *chan_dev;
 
 	chan_dev = container_of(dev, typeof(*chan_dev), device);
-	if (atomic_dec_and_test(chan_dev->idr_ref)) {
-		ida_free(&dma_ida, chan_dev->dev_id);
-		kfree(chan_dev->idr_ref);
-	}
 	kfree(chan_dev);
 }
 
@@ -1043,27 +1039,9 @@ static int get_dma_id(struct dma_device *device)
 }
 
 static int __dma_async_device_channel_register(struct dma_device *device,
-					       struct dma_chan *chan,
-					       int chan_id)
+					       struct dma_chan *chan)
 {
 	int rc = 0;
-	int chancnt = device->chancnt;
-	atomic_t *idr_ref;
-	struct dma_chan *tchan;
-
-	tchan = list_first_entry_or_null(&device->channels,
-					 struct dma_chan, device_node);
-	if (!tchan)
-		return -ENODEV;
-
-	if (tchan->dev) {
-		idr_ref = tchan->dev->idr_ref;
-	} else {
-		idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL);
-		if (!idr_ref)
-			return -ENOMEM;
-		atomic_set(idr_ref, 0);
-	}
 
 	chan->local = alloc_percpu(typeof(*chan->local));
 	if (!chan->local)
@@ -1079,29 +1057,36 @@ static int __dma_async_device_channel_register(struct dma_device *device,
 	 * When the chan_id is a negative value, we are dynamically adding
 	 * the channel. Otherwise we are static enumerating.
 	 */
-	chan->chan_id = chan_id < 0 ? chancnt : chan_id;
+	mutex_lock(&device->chan_mutex);
+	chan->chan_id = ida_alloc(&device->chan_ida, GFP_KERNEL);
+	mutex_unlock(&device->chan_mutex);
+	if (chan->chan_id < 0) {
+		pr_err("%s: unable to alloc ida for chan: %d\n",
+		       __func__, chan->chan_id);
+		goto err_out;
+	}
+
 	chan->dev->device.class = &dma_devclass;
 	chan->dev->device.parent = device->dev;
 	chan->dev->chan = chan;
-	chan->dev->idr_ref = idr_ref;
 	chan->dev->dev_id = device->dev_id;
-	atomic_inc(idr_ref);
 	dev_set_name(&chan->dev->device, "dma%dchan%d",
 		     device->dev_id, chan->chan_id);
-
 	rc = device_register(&chan->dev->device);
 	if (rc)
-		goto err_out;
+		goto err_out_ida;
 	chan->client_count = 0;
-	device->chancnt = chan->chan_id + 1;
+	device->chancnt++;
 
 	return 0;
 
+ err_out_ida:
+	mutex_lock(&device->chan_mutex);
+	ida_free(&device->chan_ida, chan->chan_id);
+	mutex_unlock(&device->chan_mutex);
  err_out:
 	free_percpu(chan->local);
 	kfree(chan->dev);
-	if (atomic_dec_return(idr_ref) == 0)
-		kfree(idr_ref);
 	return rc;
 }
 
@@ -1110,7 +1095,7 @@ int dma_async_device_channel_register(struct dma_device *device,
 {
 	int rc;
 
-	rc = __dma_async_device_channel_register(device, chan, -1);
+	rc = __dma_async_device_channel_register(device, chan);
 	if (rc < 0)
 		return rc;
 
@@ -1130,6 +1115,9 @@ static void __dma_async_device_channel_unregister(struct dma_device *device,
 	device->chancnt--;
 	chan->dev->chan = NULL;
 	mutex_unlock(&dma_list_mutex);
+	mutex_lock(&device->chan_mutex);
+	ida_free(&device->chan_ida, chan->chan_id);
+	mutex_unlock(&device->chan_mutex);
 	device_unregister(&chan->dev->device);
 	free_percpu(chan->local);
 }
@@ -1152,7 +1140,7 @@ EXPORT_SYMBOL_GPL(dma_async_device_channel_unregister);
  */
 int dma_async_device_register(struct dma_device *device)
 {
-	int rc, i = 0;
+	int rc;
 	struct dma_chan* chan;
 
 	if (!device)
@@ -1257,9 +1245,12 @@ int dma_async_device_register(struct dma_device *device)
 	if (rc != 0)
 		return rc;
 
+	mutex_init(&device->chan_mutex);
+	ida_init(&device->chan_ida);
+
 	/* represent channels in sysfs. Probably want devs too */
 	list_for_each_entry(chan, &device->channels, device_node) {
-		rc = __dma_async_device_channel_register(device, chan, i++);
+		rc = __dma_async_device_channel_register(device, chan);
 		if (rc < 0)
 			goto err_out;
 	}
@@ -1334,6 +1325,7 @@ void dma_async_device_unregister(struct dma_device *device)
 	 */
 	dma_cap_set(DMA_PRIVATE, device->cap_mask);
 	dma_channel_rebalance();
+	ida_free(&dma_ida, device->dev_id);
 	dma_device_put(device);
 	mutex_unlock(&dma_list_mutex);
 }
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 31e58ec9f741..e1c03339918f 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -341,13 +341,11 @@ struct dma_chan {
  * @chan: driver channel device
  * @device: sysfs device
  * @dev_id: parent dma_device dev_id
- * @idr_ref: reference count to gate release of dma_device dev_id
  */
 struct dma_chan_dev {
 	struct dma_chan *chan;
 	struct device device;
 	int dev_id;
-	atomic_t *idr_ref;
 };
 
 /**
@@ -835,6 +833,8 @@ struct dma_device {
 	int dev_id;
 	struct device *dev;
 	struct module *owner;
+	struct ida chan_ida;
+	struct mutex chan_mutex;	/* to protect chan_ida */
 
 	u32 src_addr_widths;
 	u32 dst_addr_widths;
-- 
cgit v1.2.3-59-g8ed1b


From a78d163978567adc2733465289293dad479d842a Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 24 Apr 2020 17:08:30 +0200
Subject: vsock/virtio: fix multiple packet delivery to monitoring devices

In virtio_transport.c, if the virtqueue is full, the transmitting
packet is queued up and it will be sent in the next iteration.
This causes the same packet to be delivered multiple times to
monitoring devices.

We want to continue to deliver packets to monitoring devices before
it is put in the virtqueue, to avoid that replies can appear in the
packet capture before the transmitted packet.

This patch fixes the issue, adding a new flag (tap_delivered) in
struct virtio_vsock_pkt, to check if the packet is already delivered
to monitoring devices.

In vhost/vsock.c, we are splitting packets, so we must set
'tap_delivered' to false when we queue up the same virtio_vsock_pkt
to handle the remaining bytes.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/vsock.c                   | 6 ++++++
 include/linux/virtio_vsock.h            | 1 +
 net/vmw_vsock/virtio_transport_common.c | 4 ++++
 3 files changed, 11 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 4f50dcb89ac8..31a98c74f678 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -196,6 +196,12 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		 * to send it with the next available buffer.
 		 */
 		if (pkt->off < pkt->len) {
+			/* We are queueing the same virtio_vsock_pkt to handle
+			 * the remaining bytes, and we want to deliver it
+			 * to monitoring devices in the next iteration.
+			 */
+			pkt->tap_delivered = false;
+
 			spin_lock_bh(&vsock->send_pkt_list_lock);
 			list_add(&pkt->list, &vsock->send_pkt_list);
 			spin_unlock_bh(&vsock->send_pkt_list_lock);
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 71c81e0dc8f2..dc636b727179 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -48,6 +48,7 @@ struct virtio_vsock_pkt {
 	u32 len;
 	u32 off;
 	bool reply;
+	bool tap_delivered;
 };
 
 struct virtio_vsock_pkt_info {
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 709038a4783e..69efc891885f 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -157,7 +157,11 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque)
 
 void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt)
 {
+	if (pkt->tap_delivered)
+		return;
+
 	vsock_deliver_tap(virtio_transport_build_skb, pkt);
+	pkt->tap_delivered = true;
 }
 EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt);
 
-- 
cgit v1.2.3-59-g8ed1b


From 7c4310ff56422ea43418305d22bbc5fe19150ec4 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Fri, 3 Apr 2020 14:33:41 +1100
Subject: SUNRPC: defer slow parts of rpc_free_client() to a workqueue.

The rpciod workqueue is on the write-out path for freeing dirty memory,
so it is important that it never block waiting for memory to be
allocated - this can lead to a deadlock.

rpc_execute() - which is often called by an rpciod work item - calls
rcp_task_release_client() which can lead to rpc_free_client().

rpc_free_client() makes two calls which could potentially block wating
for memory allocation.

rpc_clnt_debugfs_unregister() calls into debugfs and will block while
any of the debugfs files are being accessed.  In particular it can block
while any of the 'open' methods are being called and all of these use
malloc for one thing or another.  So this can deadlock if the memory
allocation waits for NFS to complete some writes via rpciod.

rpc_clnt_remove_pipedir() can take the inode_lock() and while it isn't
obvious that memory allocations can happen while the lock it held, it is
safer to assume they might and to not let rpciod call
rpc_clnt_remove_pipedir().

So this patch moves these two calls (together with the final kfree() and
rpciod_down()) into a work-item to be run from the system work-queue.
rpciod can continue its important work, and the final stages of the free
can happen whenever they happen.

I have seen this deadlock on a 4.12 based kernel where debugfs used
synchronize_srcu() when removing objects.  synchronize_srcu() requires a
workqueue and there were no free workther threads and none could be
allocated.  While debugsfs no longer uses SRCU, I believe the deadlock
is still possible.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/clnt.h |  8 +++++++-
 net/sunrpc/clnt.c           | 21 +++++++++++++++++----
 2 files changed, 24 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index ca7e108248e2..7bd124e06b36 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -71,7 +71,13 @@ struct rpc_clnt {
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	struct dentry		*cl_debugfs;	/* debugfs directory */
 #endif
-	struct rpc_xprt_iter	cl_xpi;
+	/* cl_work is only needed after cl_xpi is no longer used,
+	 * and that are of similar size
+	 */
+	union {
+		struct rpc_xprt_iter	cl_xpi;
+		struct work_struct	cl_work;
+	};
 	const struct cred	*cl_cred;
 };
 
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 05404bb05607..8350d3a2e9a7 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -880,6 +880,20 @@ EXPORT_SYMBOL_GPL(rpc_shutdown_client);
 /*
  * Free an RPC client
  */
+static void rpc_free_client_work(struct work_struct *work)
+{
+	struct rpc_clnt *clnt = container_of(work, struct rpc_clnt, cl_work);
+
+	/* These might block on processes that might allocate memory,
+	 * so they cannot be called in rpciod, so they are handled separately
+	 * here.
+	 */
+	rpc_clnt_debugfs_unregister(clnt);
+	rpc_clnt_remove_pipedir(clnt);
+
+	kfree(clnt);
+	rpciod_down();
+}
 static struct rpc_clnt *
 rpc_free_client(struct rpc_clnt *clnt)
 {
@@ -890,17 +904,16 @@ rpc_free_client(struct rpc_clnt *clnt)
 			rcu_dereference(clnt->cl_xprt)->servername);
 	if (clnt->cl_parent != clnt)
 		parent = clnt->cl_parent;
-	rpc_clnt_debugfs_unregister(clnt);
-	rpc_clnt_remove_pipedir(clnt);
 	rpc_unregister_client(clnt);
 	rpc_free_iostats(clnt->cl_metrics);
 	clnt->cl_metrics = NULL;
 	xprt_put(rcu_dereference_raw(clnt->cl_xprt));
 	xprt_iter_destroy(&clnt->cl_xpi);
-	rpciod_down();
 	put_cred(clnt->cl_cred);
 	rpc_free_clid(clnt);
-	kfree(clnt);
+
+	INIT_WORK(&clnt->cl_work, rpc_free_client_work);
+	schedule_work(&clnt->cl_work);
 	return parent;
 }
 
-- 
cgit v1.2.3-59-g8ed1b


From dff58530c4ca8ce7ee5a74db431c6e35362cf682 Mon Sep 17 00:00:00 2001
From: Olga Kornievskaia <olga.kornievskaia@gmail.com>
Date: Fri, 24 Apr 2020 17:45:50 -0400
Subject: NFSv4.1: fix handling of backchannel binding in BIND_CONN_TO_SESSION

Currently, if the client sends BIND_CONN_TO_SESSION with
NFS4_CDFC4_FORE_OR_BOTH but only gets NFS4_CDFS4_FORE back it ignores
that it wasn't able to enable a backchannel.

To make sure, the client sends BIND_CONN_TO_SESSION as the first
operation on the connections (ie., no other session compounds haven't
been sent before), and if the client's request to bind the backchannel
is not satisfied, then reset the connection and retry.

Cc: stable@vger.kernel.org
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/nfs4proc.c           | 8 ++++++++
 include/linux/nfs_xdr.h     | 2 ++
 include/linux/sunrpc/clnt.h | 5 +++++
 3 files changed, 15 insertions(+)

(limited to 'include/linux')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 1c710a7834c2..a0c1e653a935 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7891,6 +7891,7 @@ static void
 nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 {
 	struct nfs41_bind_conn_to_session_args *args = task->tk_msg.rpc_argp;
+	struct nfs41_bind_conn_to_session_res *res = task->tk_msg.rpc_resp;
 	struct nfs_client *clp = args->client;
 
 	switch (task->tk_status) {
@@ -7899,6 +7900,12 @@ nfs4_bind_one_conn_to_session_done(struct rpc_task *task, void *calldata)
 		nfs4_schedule_session_recovery(clp->cl_session,
 				task->tk_status);
 	}
+	if (args->dir == NFS4_CDFC4_FORE_OR_BOTH &&
+			res->dir != NFS4_CDFS4_BOTH) {
+		rpc_task_close_connection(task);
+		if (args->retries++ < MAX_BIND_CONN_TO_SESSION_RETRIES)
+			rpc_restart_call(task);
+	}
 }
 
 static const struct rpc_call_ops nfs4_bind_one_conn_to_session_ops = {
@@ -7921,6 +7928,7 @@ int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
 	struct nfs41_bind_conn_to_session_args args = {
 		.client = clp,
 		.dir = NFS4_CDFC4_FORE_OR_BOTH,
+		.retries = 0,
 	};
 	struct nfs41_bind_conn_to_session_res res;
 	struct rpc_message msg = {
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 440230488025..e5f3e7d8d3d5 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1317,11 +1317,13 @@ struct nfs41_impl_id {
 	struct nfstime4			date;
 };
 
+#define MAX_BIND_CONN_TO_SESSION_RETRIES 3
 struct nfs41_bind_conn_to_session_args {
 	struct nfs_client		*client;
 	struct nfs4_sessionid		sessionid;
 	u32				dir;
 	bool				use_conn_in_rdma_mode;
+	int				retries;
 };
 
 struct nfs41_bind_conn_to_session_res {
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 7bd124e06b36..02e7a5863d28 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -242,4 +242,9 @@ static inline int rpc_reply_expected(struct rpc_task *task)
 		(task->tk_msg.rpc_proc->p_decode != NULL);
 }
 
+static inline void rpc_task_close_connection(struct rpc_task *task)
+{
+	if (task->tk_xprt)
+		xprt_force_disconnect(task->tk_xprt);
+}
 #endif /* _LINUX_SUNRPC_CLNT_H */
-- 
cgit v1.2.3-59-g8ed1b


From b31d1d2b1c3a8452f425b09ebd374ecd3ddd5179 Mon Sep 17 00:00:00 2001
From: Gwendal Grignou <gwendal@chromium.org>
Date: Mon, 27 Apr 2020 15:59:02 -0700
Subject: platform/chrome: cros_ec_sensorhub: Allocate sensorhub resource
 before claiming sensors

Allocate callbacks array before enumerating the sensors: The probe routine
for these sensors (for instance cros_ec_sensors_probe) can be called
within the sensorhub probe routine (cros_ec_sensors_probe())

Fixes: 145d59baff594 ("platform/chrome: cros_ec_sensorhub: Add FIFO support")
Signed-off-by: Gwendal Grignou <gwendal@chromium.org>
Reported-by: Douglas Anderson <dianders@chromium.org>
Tested-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
---
 drivers/platform/chrome/cros_ec_sensorhub.c      | 80 ++++++++++++++----------
 drivers/platform/chrome/cros_ec_sensorhub_ring.c | 73 +++++++++++++--------
 include/linux/platform_data/cros_ec_sensorhub.h  |  1 +
 3 files changed, 93 insertions(+), 61 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/platform/chrome/cros_ec_sensorhub.c b/drivers/platform/chrome/cros_ec_sensorhub.c
index b7f2c00db5e1..9c4af76a9956 100644
--- a/drivers/platform/chrome/cros_ec_sensorhub.c
+++ b/drivers/platform/chrome/cros_ec_sensorhub.c
@@ -52,28 +52,15 @@ static int cros_ec_sensorhub_register(struct device *dev,
 	int sensor_type[MOTIONSENSE_TYPE_MAX] = { 0 };
 	struct cros_ec_command *msg = sensorhub->msg;
 	struct cros_ec_dev *ec = sensorhub->ec;
-	int ret, i, sensor_num;
+	int ret, i;
 	char *name;
 
-	sensor_num = cros_ec_get_sensor_count(ec);
-	if (sensor_num < 0) {
-		dev_err(dev,
-			"Unable to retrieve sensor information (err:%d)\n",
-			sensor_num);
-		return sensor_num;
-	}
-
-	sensorhub->sensor_num = sensor_num;
-	if (sensor_num == 0) {
-		dev_err(dev, "Zero sensors reported.\n");
-		return -EINVAL;
-	}
 
 	msg->version = 1;
 	msg->insize = sizeof(struct ec_response_motion_sense);
 	msg->outsize = sizeof(struct ec_params_motion_sense);
 
-	for (i = 0; i < sensor_num; i++) {
+	for (i = 0; i < sensorhub->sensor_num; i++) {
 		sensorhub->params->cmd = MOTIONSENSE_CMD_INFO;
 		sensorhub->params->info.sensor_num = i;
 
@@ -140,8 +127,7 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev)
 	struct cros_ec_dev *ec = dev_get_drvdata(dev->parent);
 	struct cros_ec_sensorhub *data;
 	struct cros_ec_command *msg;
-	int ret;
-	int i;
+	int ret, i, sensor_num;
 
 	msg = devm_kzalloc(dev, sizeof(struct cros_ec_command) +
 			   max((u16)sizeof(struct ec_params_motion_sense),
@@ -166,10 +152,52 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev)
 	dev_set_drvdata(dev, data);
 
 	/* Check whether this EC is a sensor hub. */
-	if (cros_ec_check_features(data->ec, EC_FEATURE_MOTION_SENSE)) {
+	if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE)) {
+		sensor_num = cros_ec_get_sensor_count(ec);
+		if (sensor_num < 0) {
+			dev_err(dev,
+				"Unable to retrieve sensor information (err:%d)\n",
+				sensor_num);
+			return sensor_num;
+		}
+		if (sensor_num == 0) {
+			dev_err(dev, "Zero sensors reported.\n");
+			return -EINVAL;
+		}
+		data->sensor_num = sensor_num;
+
+		/*
+		 * Prepare the ring handler before enumering the
+		 * sensors.
+		 */
+		if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) {
+			ret = cros_ec_sensorhub_ring_allocate(data);
+			if (ret)
+				return ret;
+		}
+
+		/* Enumerate the sensors.*/
 		ret = cros_ec_sensorhub_register(dev, data);
 		if (ret)
 			return ret;
+
+		/*
+		 * When the EC does not have a FIFO, the sensors will query
+		 * their data themselves via sysfs or a software trigger.
+		 */
+		if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) {
+			ret = cros_ec_sensorhub_ring_add(data);
+			if (ret)
+				return ret;
+			/*
+			 * The msg and its data is not under the control of the
+			 * ring handler.
+			 */
+			return devm_add_action_or_reset(dev,
+					cros_ec_sensorhub_ring_remove,
+					data);
+		}
+
 	} else {
 		/*
 		 * If the device has sensors but does not claim to
@@ -184,22 +212,6 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev)
 		}
 	}
 
-	/*
-	 * If the EC does not have a FIFO, the sensors will query their data
-	 * themselves via sysfs or a software trigger.
-	 */
-	if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) {
-		ret = cros_ec_sensorhub_ring_add(data);
-		if (ret)
-			return ret;
-		/*
-		 * The msg and its data is not under the control of the ring
-		 * handler.
-		 */
-		return devm_add_action_or_reset(dev,
-						cros_ec_sensorhub_ring_remove,
-						data);
-	}
 
 	return 0;
 }
diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c
index c48e5b38a441..24e48d96ed76 100644
--- a/drivers/platform/chrome/cros_ec_sensorhub_ring.c
+++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c
@@ -957,17 +957,15 @@ static int cros_ec_sensorhub_event(struct notifier_block *nb,
 }
 
 /**
- * cros_ec_sensorhub_ring_add() - Add the FIFO functionality if the EC
- *				  supports it.
+ * cros_ec_sensorhub_ring_allocate() - Prepare the FIFO functionality if the EC
+ *				       supports it.
  *
  * @sensorhub : Sensor Hub object.
  *
  * Return: 0 on success.
  */
-int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub)
+int cros_ec_sensorhub_ring_allocate(struct cros_ec_sensorhub *sensorhub)
 {
-	struct cros_ec_dev *ec = sensorhub->ec;
-	int ret;
 	int fifo_info_length =
 		sizeof(struct ec_response_motion_sense_fifo_info) +
 		sizeof(u16) * sensorhub->sensor_num;
@@ -978,6 +976,49 @@ int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub)
 	if (!sensorhub->fifo_info)
 		return -ENOMEM;
 
+	/*
+	 * Allocate the callback area based on the number of sensors.
+	 * Add one for the sensor ring.
+	 */
+	sensorhub->push_data = devm_kcalloc(sensorhub->dev,
+			sensorhub->sensor_num,
+			sizeof(*sensorhub->push_data),
+			GFP_KERNEL);
+	if (!sensorhub->push_data)
+		return -ENOMEM;
+
+	sensorhub->tight_timestamps = cros_ec_check_features(
+			sensorhub->ec,
+			EC_FEATURE_MOTION_SENSE_TIGHT_TIMESTAMPS);
+
+	if (sensorhub->tight_timestamps) {
+		sensorhub->batch_state = devm_kcalloc(sensorhub->dev,
+				sensorhub->sensor_num,
+				sizeof(*sensorhub->batch_state),
+				GFP_KERNEL);
+		if (!sensorhub->batch_state)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * cros_ec_sensorhub_ring_add() - Add the FIFO functionality if the EC
+ *				  supports it.
+ *
+ * @sensorhub : Sensor Hub object.
+ *
+ * Return: 0 on success.
+ */
+int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub)
+{
+	struct cros_ec_dev *ec = sensorhub->ec;
+	int ret;
+	int fifo_info_length =
+		sizeof(struct ec_response_motion_sense_fifo_info) +
+		sizeof(u16) * sensorhub->sensor_num;
+
 	/* Retrieve FIFO information */
 	sensorhub->msg->version = 2;
 	sensorhub->params->cmd = MOTIONSENSE_CMD_FIFO_INFO;
@@ -998,31 +1039,9 @@ int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub)
 	if (!sensorhub->ring)
 		return -ENOMEM;
 
-	/*
-	 * Allocate the callback area based on the number of sensors.
-	 */
-	sensorhub->push_data = devm_kcalloc(
-			sensorhub->dev, sensorhub->sensor_num,
-			sizeof(*sensorhub->push_data),
-			GFP_KERNEL);
-	if (!sensorhub->push_data)
-		return -ENOMEM;
-
 	sensorhub->fifo_timestamp[CROS_EC_SENSOR_LAST_TS] =
 		cros_ec_get_time_ns();
 
-	sensorhub->tight_timestamps = cros_ec_check_features(
-			ec, EC_FEATURE_MOTION_SENSE_TIGHT_TIMESTAMPS);
-
-	if (sensorhub->tight_timestamps) {
-		sensorhub->batch_state = devm_kcalloc(sensorhub->dev,
-				sensorhub->sensor_num,
-				sizeof(*sensorhub->batch_state),
-				GFP_KERNEL);
-		if (!sensorhub->batch_state)
-			return -ENOMEM;
-	}
-
 	/* Register the notifier that will act as a top half interrupt. */
 	sensorhub->notifier.notifier_call = cros_ec_sensorhub_event;
 	ret = blocking_notifier_chain_register(&ec->ec_dev->event_notifier,
diff --git a/include/linux/platform_data/cros_ec_sensorhub.h b/include/linux/platform_data/cros_ec_sensorhub.h
index c588be843f61..0ecce6aa69d5 100644
--- a/include/linux/platform_data/cros_ec_sensorhub.h
+++ b/include/linux/platform_data/cros_ec_sensorhub.h
@@ -185,6 +185,7 @@ int cros_ec_sensorhub_register_push_data(struct cros_ec_sensorhub *sensorhub,
 void cros_ec_sensorhub_unregister_push_data(struct cros_ec_sensorhub *sensorhub,
 					    u8 sensor_num);
 
+int cros_ec_sensorhub_ring_allocate(struct cros_ec_sensorhub *sensorhub);
 int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub);
 void cros_ec_sensorhub_ring_remove(void *arg);
 int cros_ec_sensorhub_ring_fifo_enable(struct cros_ec_sensorhub *sensorhub,
-- 
cgit v1.2.3-59-g8ed1b


From 6f49c2515e2258f08f2b905c9772dbf729610415 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 7 Apr 2020 21:20:34 -0700
Subject: dma-buf: fix documentation build warnings

Fix documentation warnings in dma-buf.[hc]:

../drivers/dma-buf/dma-buf.c:678: warning: Function parameter or member 'importer_ops' not described in 'dma_buf_dynamic_attach'
../drivers/dma-buf/dma-buf.c:678: warning: Function parameter or member 'importer_priv' not described in 'dma_buf_dynamic_attach'
../include/linux/dma-buf.h:339: warning: Incorrect use of kernel-doc format:          * @move_notify

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: linux-media@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: linaro-mm-sig@lists.linaro.org
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/7bcbe6fe-0b4b-87da-d003-b68a26eb4cf0@infradead.org
---
 drivers/dma-buf/dma-buf.c | 4 ++--
 include/linux/dma-buf.h   | 3 +--
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index de155d41d274..07df88f2e305 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -656,8 +656,8 @@ EXPORT_SYMBOL_GPL(dma_buf_put);
  * calls attach() of dma_buf_ops to allow device-specific attach functionality
  * @dmabuf:		[in]	buffer to attach device to.
  * @dev:		[in]	device to be attached.
- * @importer_ops	[in]	importer operations for the attachment
- * @importer_priv	[in]	importer private pointer for the attachment
+ * @importer_ops:	[in]	importer operations for the attachment
+ * @importer_priv:	[in]	importer private pointer for the attachment
  *
  * Returns struct dma_buf_attachment pointer for this attachment. Attachments
  * must be cleaned up by calling dma_buf_detach().
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 1ade486fc2bb..57bcef6f988a 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -329,13 +329,12 @@ struct dma_buf {
 
 /**
  * struct dma_buf_attach_ops - importer operations for an attachment
- * @move_notify: [optional] notification that the DMA-buf is moving
  *
  * Attachment operations implemented by the importer.
  */
 struct dma_buf_attach_ops {
 	/**
-	 * @move_notify
+	 * @move_notify: [optional] notification that the DMA-buf is moving
 	 *
 	 * If this callback is provided the framework can avoid pinning the
 	 * backing store while mappings exists.
-- 
cgit v1.2.3-59-g8ed1b


From cfde141ea3faa30e362bbdb5c28001bbbdb0b8e0 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 30 Apr 2020 15:01:52 +0200
Subject: mptcp: move option parsing into mptcp_incoming_options()

The mptcp_options_received structure carries several per
packet flags (mp_capable, mp_join, etc.). Such fields must
be cleared on each packet, even on dropped ones or packet
not carrying any MPTCP options, but the current mptcp
code clears them only on TCP option reset.

On several races/corner cases we end-up with stray bits in
incoming options, leading to WARN_ON splats. e.g.:

[  171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713
[  171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531)
[  171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata
[  171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95
[  171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014
[  171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531)
[  171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c
[  171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282
[  171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000
[  171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e
[  171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955
[  171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca
[  171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020
[  171.228460] FS:  00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000
[  171.230065] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0
[  171.232586] Call Trace:
[  171.233109]  <IRQ>
[  171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691)
[  171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832)
[  171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1))
[  171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217)
[  171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822)
[  171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730)
[  171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009)
[  171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1))
[  171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232)
[  171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252)
[  171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539)
[  171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135)
[  171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640)
[  171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293)
[  171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083)
[  171.282358]  </IRQ>

We could address the issue clearing explicitly the relevant fields
in several places - tcp_parse_option, tcp_fast_parse_options,
possibly others.

Instead we move the MPTCP option parsing into the already existing
mptcp ingress hook, so that we need to clear the fields in a single
place.

This allows us dropping an MPTCP hook from the TCP code and
removing the quite large mptcp_options_received from the tcp_sock
struct. On the flip side, the MPTCP sockets will traverse the
option space twice (in tcp_parse_option() and in
mptcp_incoming_options(). That looks acceptable: we already
do that for syn and 3rd ack packets, plain TCP socket will
benefit from it, and even MPTCP sockets will experience better
code locality, reducing the jumps between TCP and MPTCP code.

v1 -> v2:
 - rebased on current '-net' tree

Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h  | 51 ----------------------------------------
 include/net/mptcp.h  |  2 --
 net/ipv4/tcp_input.c |  4 ----
 net/mptcp/options.c  | 66 +++++++++++++++++++++++++++++-----------------------
 net/mptcp/protocol.c |  6 ++---
 net/mptcp/protocol.h | 43 ++++++++++++++++++++++++++++++++--
 net/mptcp/subflow.c  | 65 +++++++++++++++++++++++++++------------------------
 7 files changed, 115 insertions(+), 122 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 421c99c12291..4f8159e90ce1 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -78,47 +78,6 @@ struct tcp_sack_block {
 #define TCP_SACK_SEEN     (1 << 0)   /*1 = peer is SACK capable, */
 #define TCP_DSACK_SEEN    (1 << 2)   /*1 = DSACK was received from peer*/
 
-#if IS_ENABLED(CONFIG_MPTCP)
-struct mptcp_options_received {
-	u64	sndr_key;
-	u64	rcvr_key;
-	u64	data_ack;
-	u64	data_seq;
-	u32	subflow_seq;
-	u16	data_len;
-	u16	mp_capable : 1,
-		mp_join : 1,
-		dss : 1,
-		add_addr : 1,
-		rm_addr : 1,
-		family : 4,
-		echo : 1,
-		backup : 1;
-	u32	token;
-	u32	nonce;
-	u64	thmac;
-	u8	hmac[20];
-	u8	join_id;
-	u8	use_map:1,
-		dsn64:1,
-		data_fin:1,
-		use_ack:1,
-		ack64:1,
-		mpc_map:1,
-		__unused:2;
-	u8	addr_id;
-	u8	rm_id;
-	union {
-		struct in_addr	addr;
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-		struct in6_addr	addr6;
-#endif
-	};
-	u64	ahmac;
-	u16	port;
-};
-#endif
-
 struct tcp_options_received {
 /*	PAWS/RTTM data	*/
 	int	ts_recent_stamp;/* Time we stored ts_recent (for aging) */
@@ -136,9 +95,6 @@ struct tcp_options_received {
 	u8	num_sacks;	/* Number of SACK blocks		*/
 	u16	user_mss;	/* mss requested by user in ioctl	*/
 	u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
-#if IS_ENABLED(CONFIG_MPTCP)
-	struct mptcp_options_received	mptcp;
-#endif
 };
 
 static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
@@ -148,13 +104,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 #if IS_ENABLED(CONFIG_SMC)
 	rx_opt->smc_ok = 0;
 #endif
-#if IS_ENABLED(CONFIG_MPTCP)
-	rx_opt->mptcp.mp_capable = 0;
-	rx_opt->mptcp.mp_join = 0;
-	rx_opt->mptcp.add_addr = 0;
-	rx_opt->mptcp.rm_addr = 0;
-	rx_opt->mptcp.dss = 0;
-#endif
 }
 
 /* This is the max number of SACKS that we'll generate and process. It's safe
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 4ecfa7d5e0c7..3bce2019e4da 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -68,8 +68,6 @@ static inline bool rsk_is_mptcp(const struct request_sock *req)
 	return tcp_rsk(req)->is_mptcp;
 }
 
-void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
-			int opsize, struct tcp_options_received *opt_rx);
 bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
 		       unsigned int *size, struct mptcp_out_options *opts);
 bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 81425542da44..b996dc1069c5 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3926,10 +3926,6 @@ void tcp_parse_options(const struct net *net,
 				 */
 				break;
 #endif
-			case TCPOPT_MPTCP:
-				mptcp_parse_option(skb, ptr, opsize, opt_rx);
-				break;
-
 			case TCPOPT_FASTOPEN:
 				tcp_parse_fastopen_option(
 					opsize - TCPOLEN_FASTOPEN_BASE,
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 8fea686a5562..eadbd59586e4 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -16,10 +16,10 @@ static bool mptcp_cap_flag_sha256(u8 flags)
 	return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256;
 }
 
-void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
-			int opsize, struct tcp_options_received *opt_rx)
+static void mptcp_parse_option(const struct sk_buff *skb,
+			       const unsigned char *ptr, int opsize,
+			       struct mptcp_options_received *mp_opt)
 {
-	struct mptcp_options_received *mp_opt = &opt_rx->mptcp;
 	u8 subtype = *ptr >> 4;
 	int expected_opsize;
 	u8 version;
@@ -283,12 +283,20 @@ void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr,
 }
 
 void mptcp_get_options(const struct sk_buff *skb,
-		       struct tcp_options_received *opt_rx)
+		       struct mptcp_options_received *mp_opt)
 {
-	const unsigned char *ptr;
 	const struct tcphdr *th = tcp_hdr(skb);
-	int length = (th->doff * 4) - sizeof(struct tcphdr);
+	const unsigned char *ptr;
+	int length;
 
+	/* initialize option status */
+	mp_opt->mp_capable = 0;
+	mp_opt->mp_join = 0;
+	mp_opt->add_addr = 0;
+	mp_opt->rm_addr = 0;
+	mp_opt->dss = 0;
+
+	length = (th->doff * 4) - sizeof(struct tcphdr);
 	ptr = (const unsigned char *)(th + 1);
 
 	while (length > 0) {
@@ -308,7 +316,7 @@ void mptcp_get_options(const struct sk_buff *skb,
 			if (opsize > length)
 				return;	/* don't parse partial options */
 			if (opcode == TCPOPT_MPTCP)
-				mptcp_parse_option(skb, ptr, opsize, opt_rx);
+				mptcp_parse_option(skb, ptr, opsize, mp_opt);
 			ptr += opsize - 2;
 			length -= opsize;
 		}
@@ -797,41 +805,41 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-	struct mptcp_options_received *mp_opt;
+	struct mptcp_options_received mp_opt;
 	struct mptcp_ext *mpext;
 
-	mp_opt = &opt_rx->mptcp;
-	if (!check_fully_established(msk, sk, subflow, skb, mp_opt))
+	mptcp_get_options(skb, &mp_opt);
+	if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
 		return;
 
-	if (mp_opt->add_addr && add_addr_hmac_valid(msk, mp_opt)) {
+	if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) {
 		struct mptcp_addr_info addr;
 
-		addr.port = htons(mp_opt->port);
-		addr.id = mp_opt->addr_id;
-		if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) {
+		addr.port = htons(mp_opt.port);
+		addr.id = mp_opt.addr_id;
+		if (mp_opt.family == MPTCP_ADDR_IPVERSION_4) {
 			addr.family = AF_INET;
-			addr.addr = mp_opt->addr;
+			addr.addr = mp_opt.addr;
 		}
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-		else if (mp_opt->family == MPTCP_ADDR_IPVERSION_6) {
+		else if (mp_opt.family == MPTCP_ADDR_IPVERSION_6) {
 			addr.family = AF_INET6;
-			addr.addr6 = mp_opt->addr6;
+			addr.addr6 = mp_opt.addr6;
 		}
 #endif
-		if (!mp_opt->echo)
+		if (!mp_opt.echo)
 			mptcp_pm_add_addr_received(msk, &addr);
-		mp_opt->add_addr = 0;
+		mp_opt.add_addr = 0;
 	}
 
-	if (!mp_opt->dss)
+	if (!mp_opt.dss)
 		return;
 
 	/* we can't wait for recvmsg() to update the ack_seq, otherwise
 	 * monodirectional flows will stuck
 	 */
-	if (mp_opt->use_ack)
-		update_una(msk, mp_opt);
+	if (mp_opt.use_ack)
+		update_una(msk, &mp_opt);
 
 	mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
 	if (!mpext)
@@ -839,8 +847,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 
 	memset(mpext, 0, sizeof(*mpext));
 
-	if (mp_opt->use_map) {
-		if (mp_opt->mpc_map) {
+	if (mp_opt.use_map) {
+		if (mp_opt.mpc_map) {
 			/* this is an MP_CAPABLE carrying MPTCP data
 			 * we know this map the first chunk of data
 			 */
@@ -851,12 +859,12 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 			mpext->dsn64 = 1;
 			mpext->mpc_map = 1;
 		} else {
-			mpext->data_seq = mp_opt->data_seq;
-			mpext->subflow_seq = mp_opt->subflow_seq;
-			mpext->dsn64 = mp_opt->dsn64;
-			mpext->data_fin = mp_opt->data_fin;
+			mpext->data_seq = mp_opt.data_seq;
+			mpext->subflow_seq = mp_opt.subflow_seq;
+			mpext->dsn64 = mp_opt.dsn64;
+			mpext->data_fin = mp_opt.data_fin;
 		}
-		mpext->data_len = mp_opt->data_len;
+		mpext->data_len = mp_opt.data_len;
 		mpext->use_map = 1;
 	}
 }
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6e0188f5d3f3..e1f23016ed3f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1334,7 +1334,7 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
 #endif
 
 struct sock *mptcp_sk_clone(const struct sock *sk,
-			    const struct tcp_options_received *opt_rx,
+			    const struct mptcp_options_received *mp_opt,
 			    struct request_sock *req)
 {
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
@@ -1373,9 +1373,9 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 
 	msk->write_seq = subflow_req->idsn + 1;
 	atomic64_set(&msk->snd_una, msk->write_seq);
-	if (opt_rx->mptcp.mp_capable) {
+	if (mp_opt->mp_capable) {
 		msk->can_ack = true;
-		msk->remote_key = opt_rx->mptcp.sndr_key;
+		msk->remote_key = mp_opt->sndr_key;
 		mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);
 		ack_seq++;
 		msk->ack_seq = ack_seq;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a2b3048037d0..e4ca6320ce76 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -91,6 +91,45 @@
 #define MPTCP_WORK_RTX		2
 #define MPTCP_WORK_EOF		3
 
+struct mptcp_options_received {
+	u64	sndr_key;
+	u64	rcvr_key;
+	u64	data_ack;
+	u64	data_seq;
+	u32	subflow_seq;
+	u16	data_len;
+	u16	mp_capable : 1,
+		mp_join : 1,
+		dss : 1,
+		add_addr : 1,
+		rm_addr : 1,
+		family : 4,
+		echo : 1,
+		backup : 1;
+	u32	token;
+	u32	nonce;
+	u64	thmac;
+	u8	hmac[20];
+	u8	join_id;
+	u8	use_map:1,
+		dsn64:1,
+		data_fin:1,
+		use_ack:1,
+		ack64:1,
+		mpc_map:1,
+		__unused:2;
+	u8	addr_id;
+	u8	rm_id;
+	union {
+		struct in_addr	addr;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+		struct in6_addr	addr6;
+#endif
+	};
+	u64	ahmac;
+	u16	port;
+};
+
 static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field)
 {
 	return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) |
@@ -331,10 +370,10 @@ int mptcp_proto_v6_init(void);
 #endif
 
 struct sock *mptcp_sk_clone(const struct sock *sk,
-			    const struct tcp_options_received *opt_rx,
+			    const struct mptcp_options_received *mp_opt,
 			    struct request_sock *req);
 void mptcp_get_options(const struct sk_buff *skb,
-		       struct tcp_options_received *opt_rx);
+		       struct mptcp_options_received *mp_opt);
 
 void mptcp_finish_connect(struct sock *sk);
 void mptcp_data_ready(struct sock *sk, struct sock *ssk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 84f6408594c9..bad998529767 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -124,12 +124,11 @@ static void subflow_init_req(struct request_sock *req,
 {
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
-	struct tcp_options_received rx_opt;
+	struct mptcp_options_received mp_opt;
 
 	pr_debug("subflow_req=%p, listener=%p", subflow_req, listener);
 
-	memset(&rx_opt.mptcp, 0, sizeof(rx_opt.mptcp));
-	mptcp_get_options(skb, &rx_opt);
+	mptcp_get_options(skb, &mp_opt);
 
 	subflow_req->mp_capable = 0;
 	subflow_req->mp_join = 0;
@@ -142,16 +141,16 @@ static void subflow_init_req(struct request_sock *req,
 		return;
 #endif
 
-	if (rx_opt.mptcp.mp_capable) {
+	if (mp_opt.mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
 
-		if (rx_opt.mptcp.mp_join)
+		if (mp_opt.mp_join)
 			return;
-	} else if (rx_opt.mptcp.mp_join) {
+	} else if (mp_opt.mp_join) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
 	}
 
-	if (rx_opt.mptcp.mp_capable && listener->request_mptcp) {
+	if (mp_opt.mp_capable && listener->request_mptcp) {
 		int err;
 
 		err = mptcp_token_new_request(req);
@@ -159,13 +158,13 @@ static void subflow_init_req(struct request_sock *req,
 			subflow_req->mp_capable = 1;
 
 		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
-	} else if (rx_opt.mptcp.mp_join && listener->request_mptcp) {
+	} else if (mp_opt.mp_join && listener->request_mptcp) {
 		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
 		subflow_req->mp_join = 1;
-		subflow_req->backup = rx_opt.mptcp.backup;
-		subflow_req->remote_id = rx_opt.mptcp.join_id;
-		subflow_req->token = rx_opt.mptcp.token;
-		subflow_req->remote_nonce = rx_opt.mptcp.nonce;
+		subflow_req->backup = mp_opt.backup;
+		subflow_req->remote_id = mp_opt.join_id;
+		subflow_req->token = mp_opt.token;
+		subflow_req->remote_nonce = mp_opt.nonce;
 		pr_debug("token=%u, remote_nonce=%u", subflow_req->token,
 			 subflow_req->remote_nonce);
 		if (!subflow_token_join_request(req, skb)) {
@@ -221,6 +220,7 @@ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow)
 static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_options_received mp_opt;
 	struct sock *parent = subflow->conn;
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -237,16 +237,17 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 
 	subflow->conn_finished = 1;
 
-	if (subflow->request_mptcp && tp->rx_opt.mptcp.mp_capable) {
+	mptcp_get_options(skb, &mp_opt);
+	if (subflow->request_mptcp && mp_opt.mp_capable) {
 		subflow->mp_capable = 1;
 		subflow->can_ack = 1;
-		subflow->remote_key = tp->rx_opt.mptcp.sndr_key;
+		subflow->remote_key = mp_opt.sndr_key;
 		pr_debug("subflow=%p, remote_key=%llu", subflow,
 			 subflow->remote_key);
-	} else if (subflow->request_join && tp->rx_opt.mptcp.mp_join) {
+	} else if (subflow->request_join && mp_opt.mp_join) {
 		subflow->mp_join = 1;
-		subflow->thmac = tp->rx_opt.mptcp.thmac;
-		subflow->remote_nonce = tp->rx_opt.mptcp.nonce;
+		subflow->thmac = mp_opt.thmac;
+		subflow->remote_nonce = mp_opt.nonce;
 		pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow,
 			 subflow->thmac, subflow->remote_nonce);
 	} else if (subflow->request_mptcp) {
@@ -343,7 +344,7 @@ drop:
 
 /* validate hmac received in third ACK */
 static bool subflow_hmac_valid(const struct request_sock *req,
-			       const struct tcp_options_received *rx_opt)
+			       const struct mptcp_options_received *mp_opt)
 {
 	const struct mptcp_subflow_request_sock *subflow_req;
 	u8 hmac[MPTCPOPT_HMAC_LEN];
@@ -360,7 +361,7 @@ static bool subflow_hmac_valid(const struct request_sock *req,
 			      subflow_req->local_nonce, hmac);
 
 	ret = true;
-	if (crypto_memneq(hmac, rx_opt->mptcp.hmac, sizeof(hmac)))
+	if (crypto_memneq(hmac, mp_opt->hmac, sizeof(hmac)))
 		ret = false;
 
 	sock_put((struct sock *)msk);
@@ -416,7 +417,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 {
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk);
 	struct mptcp_subflow_request_sock *subflow_req;
-	struct tcp_options_received opt_rx;
+	struct mptcp_options_received mp_opt;
 	bool fallback_is_fatal = false;
 	struct sock *new_msk = NULL;
 	bool fallback = false;
@@ -424,7 +425,10 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 
 	pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
 
-	opt_rx.mptcp.mp_capable = 0;
+	/* we need later a valid 'mp_capable' value even when options are not
+	 * parsed
+	 */
+	mp_opt.mp_capable = 0;
 	if (tcp_rsk(req)->is_mptcp == 0)
 		goto create_child;
 
@@ -439,22 +443,21 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			goto create_msk;
 		}
 
-		mptcp_get_options(skb, &opt_rx);
-		if (!opt_rx.mptcp.mp_capable) {
+		mptcp_get_options(skb, &mp_opt);
+		if (!mp_opt.mp_capable) {
 			fallback = true;
 			goto create_child;
 		}
 
 create_msk:
-		new_msk = mptcp_sk_clone(listener->conn, &opt_rx, req);
+		new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req);
 		if (!new_msk)
 			fallback = true;
 	} else if (subflow_req->mp_join) {
 		fallback_is_fatal = true;
-		opt_rx.mptcp.mp_join = 0;
-		mptcp_get_options(skb, &opt_rx);
-		if (!opt_rx.mptcp.mp_join ||
-		    !subflow_hmac_valid(req, &opt_rx)) {
+		mptcp_get_options(skb, &mp_opt);
+		if (!mp_opt.mp_join ||
+		    !subflow_hmac_valid(req, &mp_opt)) {
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
 			return NULL;
 		}
@@ -494,9 +497,9 @@ create_child:
 			/* with OoO packets we can reach here without ingress
 			 * mpc option
 			 */
-			ctx->remote_key = opt_rx.mptcp.sndr_key;
-			ctx->fully_established = opt_rx.mptcp.mp_capable;
-			ctx->can_ack = opt_rx.mptcp.mp_capable;
+			ctx->remote_key = mp_opt.sndr_key;
+			ctx->fully_established = mp_opt.mp_capable;
+			ctx->can_ack = mp_opt.mp_capable;
 		} else if (ctx->mp_join) {
 			struct mptcp_sock *owner;
 
-- 
cgit v1.2.3-59-g8ed1b


From 9d82973e032e246ff5663c9805fbb5407ae932e3 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Mon, 4 May 2020 09:16:37 -0700
Subject: gcc-10 warnings: fix low-hanging fruit

Due to a bug-report that was compiler-dependent, I updated one of my
machines to gcc-10.  That shows a lot of new warnings.  Happily they
seem to be mostly the valid kind, but it's going to cause a round of
churn for getting rid of them..

This is the really low-hanging fruit of removing a couple of zero-sized
arrays in some core code.  We have had a round of these patches before,
and we'll have many more coming, and there is nothing special about
these except that they were particularly trivial, and triggered more
warnings than most.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/fs.h  | 2 +-
 include/linux/tty.h | 2 +-
 scripts/kallsyms.c  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4f6f59b4f22a..45cc10cdf6dd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -983,7 +983,7 @@ struct file_handle {
 	__u32 handle_bytes;
 	int handle_type;
 	/* file identifier */
-	unsigned char f_handle[0];
+	unsigned char f_handle[];
 };
 
 static inline struct file *get_file(struct file *f)
diff --git a/include/linux/tty.h b/include/linux/tty.h
index bd5fe0e907e8..a99e9b8e4e31 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -66,7 +66,7 @@ struct tty_buffer {
 	int read;
 	int flags;
 	/* Data points here */
-	unsigned long data[0];
+	unsigned long data[];
 };
 
 /* Values for .flags field of tty_buffer */
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 3e8dea6e0a95..6dc3078649fa 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -34,7 +34,7 @@ struct sym_entry {
 	unsigned int len;
 	unsigned int start_pos;
 	unsigned int percpu_absolute;
-	unsigned char sym[0];
+	unsigned char sym[];
 };
 
 struct addr_range {
-- 
cgit v1.2.3-59-g8ed1b


From 9274124f023b5c56dc4326637d4f787968b03607 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 4 May 2020 12:48:54 -0400
Subject: net: stricter validation of untrusted gso packets

Syzkaller again found a path to a kernel crash through bad gso input:
a packet with transport header extending beyond skb_headlen(skb).

Tighten validation at kernel entry:

- Verify that the transport header lies within the linear section.

    To avoid pulling linux/tcp.h, verify just sizeof tcphdr.
    tcp_gso_segment will call pskb_may_pull (th->doff * 4) before use.

- Match the gso_type against the ip_proto found by the flow dissector.

Fixes: bfd5f4a3d605 ("packet: Add GSO/csum offload support.")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/virtio_net.h | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 0d1fe9297ac6..6f6ade63b04c 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -3,6 +3,8 @@
 #define _LINUX_VIRTIO_NET_H
 
 #include <linux/if_vlan.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/udp.h>
 #include <uapi/linux/virtio_net.h>
 
 static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,
@@ -28,17 +30,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 					bool little_endian)
 {
 	unsigned int gso_type = 0;
+	unsigned int thlen = 0;
+	unsigned int ip_proto;
 
 	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
 		case VIRTIO_NET_HDR_GSO_TCPV4:
 			gso_type = SKB_GSO_TCPV4;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			gso_type = SKB_GSO_TCPV6;
+			ip_proto = IPPROTO_TCP;
+			thlen = sizeof(struct tcphdr);
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
 			gso_type = SKB_GSO_UDP;
+			ip_proto = IPPROTO_UDP;
+			thlen = sizeof(struct udphdr);
 			break;
 		default:
 			return -EINVAL;
@@ -57,16 +67,22 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
+
+		if (skb_transport_offset(skb) + thlen > skb_headlen(skb))
+			return -EINVAL;
 	} else {
 		/* gso packets without NEEDS_CSUM do not set transport_offset.
 		 * probe and drop if does not match one of the above types.
 		 */
 		if (gso_type && skb->network_header) {
+			struct flow_keys_basic keys;
+
 			if (!skb->protocol)
 				virtio_net_hdr_set_proto(skb, hdr);
 retry:
-			skb_probe_transport_header(skb);
-			if (!skb_transport_header_was_set(skb)) {
+			if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
+							      NULL, 0, 0, 0,
+							      0)) {
 				/* UFO does not specify ipv4 or 6: try both */
 				if (gso_type & SKB_GSO_UDP &&
 				    skb->protocol == htons(ETH_P_IP)) {
@@ -75,6 +91,12 @@ retry:
 				}
 				return -EINVAL;
 			}
+
+			if (keys.control.thoff + thlen > skb_headlen(skb) ||
+			    keys.basic.ip_proto != ip_proto)
+				return -EINVAL;
+
+			skb_set_transport_header(skb, keys.control.thoff);
 		}
 	}
 
-- 
cgit v1.2.3-59-g8ed1b