4.14.261-rc1 review

This is the start of the stable review cycle for the 4.14.261 release. There are 19 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Wed, 05 Jan 2022 14:20:40 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.14.261-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.14.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 4.14.261-rc1

Xin Long <[email protected]>
sctp: use call_rcu to free endpoint

Muchun Song <[email protected]>
net: fix use-after-free in tw_timer_handler

Leo L. Schwab <[email protected]>
Input: spaceball - fix parsing of movement data packets

Pavel Skripkin <[email protected]>
Input: appletouch - initialize work before device registration

Alexey Makhalov <[email protected]>
scsi: vmw_pvscsi: Set residual data length conditionally

Todd Kjos <[email protected]>
binder: fix async_free_space accounting for empty parcels

Vincent Pelletier <[email protected]>
usb: gadget: f_fs: Clear ffs_eventfd in ffs_data_clear.

Mathias Nyman <[email protected]>
xhci: Fresco FL1100 controller should not have BROKEN_MSI quirk set.

Dmitry V. Levin <[email protected]>
uapi: fix linux/nfc.h userspace compilation errors

Krzysztof Kozlowski <[email protected]>
nfc: uapi: use kernel size_t to fix user-space builds

Miaoqian Lin <[email protected]>
fsl/fman: Fix missing put_device() call in fman_port_probe

Wei Yongjun <[email protected]>
NFC: st21nfca: Fix memory leak in device probe and remove

Matthias-Christian Ott <[email protected]>
net: usb: pegasus: Do not drop long Ethernet frames

Dan Carpenter <[email protected]>
scsi: lpfc: Terminate string in lpfc_debugfs_nvmeio_trc_write()

Tom Rix <[email protected]>
selinux: initialize proto variable in selinux_ip_postroute_compat()

Heiko Carstens <[email protected]>
recordmcount.pl: fix typo in s390 mcount regex

Wang Qing <[email protected]>
platform/x86: apple-gmux: use resource_size() with res

Jens Wiklander <[email protected]>
tee: handle lookup of shm with reference count 0

Hans de Goede <[email protected]>
HID: asus: Add depends on USB_HID to HID_ASUS Kconfig option

-------------

Diffstat:

 Makefile                                        |   4 +-
 drivers/android/binder_alloc.c                  |   2 +-
 drivers/hid/Kconfig                             |   1 +
 drivers/input/joystick/spaceball.c              |  11 +-
 drivers/input/mouse/appletouch.c                |   4 +-
 drivers/net/ethernet/freescale/fman/fman_port.c |  12 +-
 drivers/net/usb/pegasus.c                       |   4 +-
 drivers/nfc/st21nfca/i2c.c                      |  29 +++--
 drivers/platform/x86/apple-gmux.c               |   2 +-
 drivers/scsi/lpfc/lpfc_debugfs.c                |   4 +-
 drivers/scsi/vmw_pvscsi.c                       |   7 +-
 drivers/tee/tee_private.h                       |   4 +-
 drivers/tee/tee_shm.c                           | 155 ++++++++++--------------
 drivers/usb/gadget/function/f_fs.c              |   9 +-
 drivers/usb/host/xhci-pci.c                     |   5 +-
 include/net/sctp/sctp.h                         |   6 +-
 include/net/sctp/structs.h                      |   3 +-
 include/uapi/linux/nfc.h                        |   6 +-
 net/ipv4/af_inet.c                              |  10 +-
 net/sctp/endpointola.c                          |  23 ++--
 net/sctp/sctp_diag.c                            |  12 +-
 net/sctp/socket.c                               |  23 ++--
 scripts/recordmcount.pl                         |   2 +-
 security/selinux/hooks.c                        |   2 +-
 24 files changed, 175 insertions(+), 165 deletions(-)

From: Hans de Goede <[email protected]>

commit c4f0126d487f3c68ab19ccb7c561e8fbf3ea2247 upstream.

Since commit 4bc43a421218 ("HID: asus: Add hid_is_using_ll_driver(usb_hid_driver) check") the hid-asus.c depends on the usb_hid_driver symbol. Add a depends on USB_HID to Kconfig to fix missing symbols errors in hid-asus when USB_HID is not enabled.

---
 drivers/hid/Kconfig |    1 +
 1 file changed, 1 insertion(+)

@@ -148,6 +148,7 @@ config HID_APPLEIR
 
 config HID_ASUS
 	tristate "Asus"
+	depends on USB_HID
 	depends on LEDS_CLASS
 	---help---
 	Support for Asus notebook built-in keyboard and touchpad via i2c, and

From: Jens Wiklander <[email protected]>

commit dfd0743f1d9ea76931510ed150334d571fbab49d upstream.

Since the tee subsystem does not keep a strong reference to its idle shared memory buffers, it races with other threads that try to destroy a shared memory through a close of its dma-buf fd or by unmapping the memory.

In tee_shm_get_from_id() when a lookup in teedev->idr has been successful, it is possible that the tee_shm is in the dma-buf teardown path, but that path is blocked by the teedev mutex. Since we don't have an API to tell if the tee_shm is in the dma-buf teardown path or not we must find another way of detecting this condition.

Fix this by doing the reference counting directly on the tee_shm using a new refcount_t refcount field. dma-buf is replaced by using anon_inode_getfd() instead, this separates the life-cycle of the underlying file from the tee_shm. tee_shm_put() is updated to hold the mutex when decreasing the refcount to 0 and then remove the tee_shm from teedev->idr before releasing the mutex. This means that the tee_shm can never be found unless it has a refcount larger than 0.

---
 drivers/tee/tee_private.h |    4 -
 drivers/tee/tee_shm.c     |  155 ++++++++++++++++++----------------------------
 2 files changed, 63 insertions(+), 96 deletions(-)

@@ -31,7 +31,7 @@ struct tee_device;
  * @paddr:	physical address of the shared memory
  * @kaddr:	virtual address of the shared memory
  * @size:	size of shared memory
- * @dmabuf:	dmabuf used to for exporting to user space
+ * @refcount:	reference counter
  * @flags:	defined by TEE_SHM_* in tee_drv.h
  * @id:		unique id of a shared memory object on this device
  */

@@ -42,7 +42,7 @@ struct tee_shm {
 	phys_addr_t paddr;
 	void *kaddr;
 	size_t size;
-	struct dma_buf *dmabuf;
+	refcount_t refcount;
 	u32 flags;
 	int id;
 };

From: Wang Qing <[email protected]>

[ Upstream commit eb66fb03a727cde0ab9b1a3858de55c26f3007da ]

This should be (res->end - res->start + 1) here actually, use resource_size() derectly.

---
 drivers/platform/x86/apple-gmux.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 7c4eb86c851ed..5463d740f3523 100644
@@ -628,7 +628,7 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id)
 	}
 
 	gmux_data->iostart = res->start;
-	gmux_data->iolen = res->end - res->start;
+	gmux_data->iolen = resource_size(res);
 
 	if (gmux_data->iolen < GMUX_MIN_IO_LEN) {
 		pr_err("gmux I/O region too small (%lu < %u)\n",

2.34.1

From: Heiko Carstens <[email protected]>

commit 4eb1782eaa9fa1c224ad1fa0d13a9f09c3ab2d80 upstream.

Commit 85bf17b28f97 ("recordmcount.pl: look for jgnop instruction as well as bcrl on s390") added a new alternative mnemonic for the existing brcl instruction. This is required for the combination old gcc version (pre 9.0) and binutils since version 2.37.
However at the same time this commit introduced a typo, replacing brcl with bcrl. As a result no mcount locations are detected anymore with old gcc versions (pre 9.0) and binutils before version 2.37.
Fix this by using the correct mnemonic again.

---
 scripts/recordmcount.pl |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -252,7 +252,7 @@ if ($arch eq "x86_64") {
 
 } elsif ($arch eq "s390" && $bits == 64) {
     if ($cc =~ /-DCC_USING_HOTPATCH/) {
-	$mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*(bcrl\\s*0,|jgnop\\s*)[0-9a-f]+ <([^\+]*)>\$";
+	$mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*(brcl\\s*0,|jgnop\\s*)[0-9a-f]+ <([^\+]*)>\$";
 	$mcount_adjust = 0;
     } else {
 	$mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_390_(PC|PLT)32DBL\\s+_mcount\\+0x2\$";

From: Tom Rix <[email protected]>

commit 732bc2ff080c447f8524f40c970c481f5da6eed3 upstream.

Clang static analysis reports this warning

hooks.c:5765:6: warning: 4th function call argument is an uninitialized

                value
        if (selinux_xfrm_postroute_last(sksec->sid, skb, &ad, proto))
            ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

selinux_parse_skb() can return ok without setting proto. The later call to selinux_xfrm_postroute_last() does an early check of proto and can return ok if the garbage proto value matches. So initialize proto.

---
 security/selinux/hooks.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -5321,7 +5321,7 @@ static unsigned int selinux_ip_postroute
 	struct common_audit_data ad;
 	struct lsm_network_audit net = {0,};
 	char *addrp;
-	u8 proto;
+	u8 proto = 0;
 
 	if (sk == NULL)
 		return NF_ACCEPT;

From: Dan Carpenter <[email protected]>

[ Upstream commit 9020be114a47bf7ff33e179b3bb0016b91a098e6 ]

The "mybuf" string comes from the user, so we need to ensure that it is NUL terminated.

---
 drivers/scsi/lpfc/lpfc_debugfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index c77ad2b78ce49..39a1c9e18c0ea 100644
@@ -2177,8 +2177,8 @@ lpfc_debugfs_nvmeio_trc_write(struct file *file, const char __user *buf,
 	char mybuf[64];
 	char *pbuf;
 
-	if (nbytes > 64)
-		nbytes = 64;
+	if (nbytes > 63)
+		nbytes = 63;
 
 	memset(mybuf, 0, sizeof(mybuf));
 

2.34.1

From: Matthias-Christian Ott <[email protected]>

[ Upstream commit ca506fca461b260ab32952b610c3d4aadc6c11fd ]

The D-Link DSB-650TX (2001:4002) is unable to receive Ethernet frames that are longer than 1518 octets, for example, Ethernet frames that contain 802.1Q VLAN tags.

The frames are sent to the pegasus driver via USB but the driver discards them because they have the Long_pkt field set to 1 in the received status report. The function read_bulk_callback of the pegasus driver treats such received "packets" (in the terminology of the hardware) as errors but the field simply does just indicate that the Ethernet frame (MAC destination to FCS) is longer than 1518 octets.

It seems that in the 1990s there was a distinction between "giant" (> 1518) and "runt" (< 64) frames and the hardware includes flags to indicate this distinction. It seems that the purpose of the distinction "giant" frames was to not allow infinitely long frames due to transmission errors and to allow hardware to have an upper limit of the frame size. However, the hardware already has such limit with its 2048 octet receive buffer and, therefore, Long_pkt is merely a convention and should not be treated as a receive error.

Actually, the hardware is even able to receive Ethernet frames with 2048 octets which exceeds the claimed limit frame size limit of the driver of 1536 octets (PEGASUS_MTU).

---
 drivers/net/usb/pegasus.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index d18a283a0ccff..408b996ff4dfb 100644
@@ -498,11 +498,11 @@ static void read_bulk_callback(struct urb *urb)
 		goto goon;
 
 	rx_status = buf[count - 2];
-	if (rx_status & 0x1e) {
+	if (rx_status & 0x1c) {
 		netif_dbg(pegasus, rx_err, net,
 			  "RX packet error %x\n", rx_status);
 		net->stats.rx_errors++;
-		if (rx_status & 0x06)	/* long or runt	*/
+		if (rx_status & 0x04)	/* runt	*/
 			net->stats.rx_length_errors++;
 		if (rx_status & 0x08)
 			net->stats.rx_crc_errors++;

2.34.1

From: Wei Yongjun <[email protected]>

[ Upstream commit 1b9dadba502234eea7244879b8d5d126bfaf9f0c ]

'phy->pending_skb' is alloced when device probe, but forgot to free in the error handling path and remove path, this cause memory leak as follows:

unreferenced object 0xffff88800bc06800 (size 512):
comm "8", pid 11775, jiffies 4295159829 (age 9.032s) hex dump (first 32 bytes):

    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<00000000d66c09ce>] __kmalloc_node_track_caller+0x1ed/0x450
    [<00000000c93382b3>] kmalloc_reserve+0x37/0xd0
    [<000000005fea522c>] __alloc_skb+0x124/0x380
    [<0000000019f29f9a>] st21nfca_hci_i2c_probe+0x170/0x8f2

Fix it by freeing 'pending_skb' in error and remove.

---
 drivers/nfc/st21nfca/i2c.c | 29 ++++++++++++++++++++---------
 1 file changed, 20 insertions(+), 9 deletions(-)

index cd1f7bfa75ebe..dc9dd66cf6735 100644
@@ -544,7 +544,8 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 	phy->gpiod_ena = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
 	if (IS_ERR(phy->gpiod_ena)) {
 		nfc_err(dev, "Unable to get ENABLE GPIO\n");
-		return PTR_ERR(phy->gpiod_ena);
+		r = PTR_ERR(phy->gpiod_ena);
+		goto out_free;
 	}
 
 	phy->se_status.is_ese_present =

@@ -555,7 +556,7 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 	r = st21nfca_hci_platform_init(phy);
 	if (r < 0) {
 		nfc_err(&client->dev, "Unable to reboot st21nfca\n");
-		return r;
+		goto out_free;
 	}
 
 	r = devm_request_threaded_irq(&client->dev, client->irq, NULL,

@@ -564,15 +565,23 @@ static int st21nfca_hci_i2c_probe(struct i2c_client *client,
 				ST21NFCA_HCI_DRIVER_NAME, phy);
 	if (r < 0) {
 		nfc_err(&client->dev, "Unable to register IRQ handler\n");
-		return r;
+		goto out_free;
 	}
 
-	return st21nfca_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
-					ST21NFCA_FRAME_HEADROOM,
-					ST21NFCA_FRAME_TAILROOM,
-					ST21NFCA_HCI_LLC_MAX_PAYLOAD,
-					&phy->hdev,
-					&phy->se_status);
+	r = st21nfca_hci_probe(phy, &i2c_phy_ops, LLC_SHDLC_NAME,
+			       ST21NFCA_FRAME_HEADROOM,
+			       ST21NFCA_FRAME_TAILROOM,
+			       ST21NFCA_HCI_LLC_MAX_PAYLOAD,
+			       &phy->hdev,
+			       &phy->se_status);
+	if (r)
+		goto out_free;
+
+	return 0;
+
+out_free:
+	kfree_skb(phy->pending_skb);
+	return r;
 }
 
 static int st21nfca_hci_i2c_remove(struct i2c_client *client)

@@ -585,6 +594,8 @@ static int st21nfca_hci_i2c_remove(struct i2c_client *client)
 
 	if (phy->powered)
 		st21nfca_hci_i2c_disable(phy);
+	if (phy->pending_skb)
+		kfree_skb(phy->pending_skb);
 
 	return 0;
 }

2.34.1

From: Miaoqian Lin <[email protected]>

[ Upstream commit bf2b09fedc17248b315f80fb249087b7d28a69a6 ]

The reference taken by 'of_find_device_by_node()' must be released when not needed anymore.
Add the corresponding 'put_device()' in the and error handling paths.

---
 drivers/net/ethernet/freescale/fman/fman_port.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

index ac3d791f52821..b7295f21aa580 100644
@@ -1779,7 +1779,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	fman = dev_get_drvdata(&fm_pdev->dev);
 	if (!fman) {
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 
 	err = of_property_read_u32(port_node, "cell-index", &val);

@@ -1787,7 +1787,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 		dev_err(port->dev, "%s: reading cell-index for %pOF failed\n",
 			__func__, port_node);
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 	port_id = (u8)val;
 	port->dts_params.id = port_id;

@@ -1821,7 +1821,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 	}  else {
 		dev_err(port->dev, "%s: Illegal port type\n", __func__);
 		err = -EINVAL;
-		goto return_err;
+		goto put_device;
 	}
 
 	port->dts_params.type = port_type;

@@ -1835,7 +1835,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 			dev_err(port->dev, "%s: incorrect qman-channel-id\n",
 				__func__);
 			err = -EINVAL;
-			goto return_err;
+			goto put_device;
 		}
 		port->dts_params.qman_channel_id = qman_channel_id;
 	}

@@ -1845,7 +1845,7 @@ static int fman_port_probe(struct platform_device *of_dev)
 		dev_err(port->dev, "%s: of_address_to_resource() failed\n",
 			__func__);
 		err = -ENOMEM;
-		goto return_err;
+		goto put_device;
 	}
 
 	port->dts_params.fman = fman;

@@ -1870,6 +1870,8 @@ static int fman_port_probe(struct platform_device *of_dev)
 
 	return 0;
 
+put_device:
+	put_device(&fm_pdev->dev);
 return_err:
 	of_node_put(port_node);
 free_port:

2.34.1

From: Krzysztof Kozlowski <[email protected]>

commit 79b69a83705e621b258ac6d8ae6d3bfdb4b930aa upstream.

Fix user-space builds if it includes /usr/include/linux/nfc.h before some of other headers:

/usr/include/linux/nfc.h:281:9: error: unknown type name ‘size_t’

    281 |         size_t service_name_len;
        |         ^~~~~~

---
 include/uapi/linux/nfc.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -276,7 +276,7 @@ struct sockaddr_nfc_llcp {
 	__u8 dsap; /* Destination SAP, if known */
 	__u8 ssap; /* Source SAP to be bound to */
 	char service_name[NFC_LLCP_MAX_SERVICE_NAME]; /* Service name URI */;
-	size_t service_name_len;
+	__kernel_size_t service_name_len;
 };
 
 /* NFC socket protocols */

From: Dmitry V. Levin <[email protected]>

commit 7175f02c4e5f5a9430113ab9ca0fd0ce98b28a51 upstream.

Replace sa_family_t with __kernel_sa_family_t to fix the following linux/nfc.h userspace compilation errors:

/usr/include/linux/nfc.h:266:2: error: unknown type name 'sa_family_t'
sa_family_t sa_family;
/usr/include/linux/nfc.h:274:2: error: unknown type name 'sa_family_t'
sa_family_t sa_family;

---
 include/uapi/linux/nfc.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -261,7 +261,7 @@ enum nfc_sdp_attr {
 #define NFC_SE_ENABLED  0x1
 
 struct sockaddr_nfc {
-	sa_family_t sa_family;
+	__kernel_sa_family_t sa_family;
 	__u32 dev_idx;
 	__u32 target_idx;
 	__u32 nfc_protocol;

@@ -269,7 +269,7 @@ struct sockaddr_nfc {
 
 #define NFC_LLCP_MAX_SERVICE_NAME 63
 struct sockaddr_nfc_llcp {
-	sa_family_t sa_family;
+	__kernel_sa_family_t sa_family;
 	__u32 dev_idx;
 	__u32 target_idx;
 	__u32 nfc_protocol;

From: Mathias Nyman <[email protected]>

commit e4844092581ceec22489b66c42edc88bc6079783 upstream.

The Fresco Logic FL1100 controller needs the TRUST_TX_LENGTH quirk like other Fresco controllers, but should not have the BROKEN_MSI quirks set.

BROKEN_MSI quirk causes issues in detecting usb drives connected to docks with this FL1100 controller.
The BROKEN_MSI flag was apparently accidentally set together with the TRUST_TX_LENGTH quirk

Original patch went to stable so this should go there as well.

---
 drivers/usb/host/xhci-pci.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -100,7 +100,6 @@ static void xhci_pci_quirks(struct devic
 	/* Look for vendor-specific quirks */
 	if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC &&
 			(pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_PDK ||
-			 pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1100 ||
 			 pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1400)) {
 		if (pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_PDK &&
 				pdev->revision == 0x0) {

@@ -135,6 +134,10 @@ static void xhci_pci_quirks(struct devic
 			pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1009)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 
+	if (pdev->vendor == PCI_VENDOR_ID_FRESCO_LOGIC &&
+			pdev->device == PCI_DEVICE_ID_FRESCO_LOGIC_FL1100)
+		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+
 	if (pdev->vendor == PCI_VENDOR_ID_NEC)
 		xhci->quirks |= XHCI_NEC_HOST;
 

From: Vincent Pelletier <[email protected]>

commit b1e0887379422975f237d43d8839b751a6bcf154 upstream.

ffs_data_clear is indirectly called from both ffs_fs_kill_sb and ffs_ep0_release, so it ends up being called twice when userland closes ep0 and then unmounts f_fs.
If userland provided an eventfd along with function's USB descriptors, it ends up calling eventfd_ctx_put as many times, causing a refcount underflow.
NULL-ify ffs_eventfd to prevent these extraneous eventfd_ctx_put calls.

Also, set epfiles to NULL right after de-allocating it, for readability.

For completeness, ffs_data_clear actually ends up being called thrice, the last call being before the whole ffs structure gets freed, so when this specific sequence happens there is a second underflow happening (but not being reported):

/sys/kernel/debug/tracing# modprobe usb_f_fs /sys/kernel/debug/tracing# echo ffs_data_clear > set_ftrace_filter /sys/kernel/debug/tracing# echo function > current_tracer /sys/kernel/debug/tracing# echo 1 > tracing_on
(setup gadget, run and kill function userland process, teardown gadget) /sys/kernel/debug/tracing# echo 0 > tracing_on /sys/kernel/debug/tracing# cat trace

 smartcard-openp-436     [000] .....  1946.208786: ffs_data_clear <-ffs_data_closed
 smartcard-openp-431     [000] .....  1946.279147: ffs_data_clear <-ffs_data_closed
 smartcard-openp-431     [000] .n...  1946.905512: ffs_data_clear <-ffs_data_put

Warning output corresponding to above trace:

[ 1946.284139] WARNING: CPU: 0 PID: 431 at lib/refcount.c:28 refcount_warn_saturate+0x110/0x15c
[ 1946.293094] refcount_t: underflow; use-after-free.
[ 1946.298164] Modules linked in: usb_f_ncm(E) u_ether(E) usb_f_fs(E) hci_uart(E) btqca(E) btrtl(E) btbcm(E) btintel(E) bluetooth(E) nls_ascii(E) nls_cp437(E) vfat(E) fat(E) bcm2835_v4l2(CE) bcm2835_mmal_vchiq(CE) videobuf2_vmalloc(E) videobuf2_memops(E) sha512_generic(E) videobuf2_v4l2(E) sha512_arm(E) videobuf2_common(E) videodev(E) cpufreq_dt(E) snd_bcm2835(CE) brcmfmac(E) mc(E) vc4(E) ctr(E) brcmutil(E) snd_soc_core(E) snd_pcm_dmaengine(E) drbg(E) snd_pcm(E) snd_timer(E) snd(E) soundcore(E) drm_kms_helper(E) cec(E) ansi_cprng(E) rc_core(E) syscopyarea(E) raspberrypi_cpufreq(E) sysfillrect(E) sysimgblt(E) cfg80211(E) max17040_battery(OE) raspberrypi_hwmon(E) fb_sys_fops(E) regmap_i2c(E) ecdh_generic(E) rfkill(E) ecc(E) bcm2835_rng(E) rng_core(E) vchiq(CE) leds_gpio(E) libcomposite(E) fuse(E) configfs(E) ip_tables(E) x_tables(E) autofs4(E) ext4(E) crc16(E) mbcache(E) jbd2(E) crc32c_generic(E) sdhci_iproc(E) sdhci_pltfm(E) sdhci(E)
[ 1946.399633] CPU: 0 PID: 431 Comm: smartcard-openp Tainted: G         C OE     5.15.0-1-rpi #1  Debian 5.15.3-1
[ 1946.417950] Hardware name: BCM2835
[ 1946.425442] Backtrace:
[ 1946.432048] [<c08d60a0>] (dump_backtrace) from [<c08d62ec>] (show_stack+0x20/0x24)
[ 1946.448226]  r7:00000009 r6:0000001c r5:c04a948c r4:c0a64e2c
[ 1946.458412] [<c08d62cc>] (show_stack) from [<c08d9ae0>] (dump_stack+0x28/0x30)
[ 1946.470380] [<c08d9ab8>] (dump_stack) from [<c0123500>] (__warn+0xe8/0x154)
[ 1946.482067]  r5:c04a948c r4:c0a71dc8
[ 1946.490184] [<c0123418>] (__warn) from [<c08d6948>] (warn_slowpath_fmt+0xa0/0xe4)
[ 1946.506758]  r7:00000009 r6:0000001c r5:c0a71dc8 r4:c0a71e04
[ 1946.517070] [<c08d68ac>] (warn_slowpath_fmt) from [<c04a948c>] (refcount_warn_saturate+0x110/0x15c)
[ 1946.535309]  r8:c0100224 r7:c0dfcb84 r6:ffffffff r5:c3b84c00 r4:c24a17c0
[ 1946.546708] [<c04a937c>] (refcount_warn_saturate) from [<c0380134>] (eventfd_ctx_put+0x48/0x74)
[ 1946.564476] [<c03800ec>] (eventfd_ctx_put) from [<bf5464e8>] (ffs_data_clear+0xd0/0x118 [usb_f_fs])
[ 1946.582664]  r5:c3b84c00 r4:c2695b00
[ 1946.590668] [<bf546418>] (ffs_data_clear [usb_f_fs]) from [<bf547cc0>] (ffs_data_closed+0x9c/0x150 [usb_f_fs])
[ 1946.609608]  r5:bf54d014 r4:c2695b00
[ 1946.617522] [<bf547c24>] (ffs_data_closed [usb_f_fs]) from [<bf547da0>] (ffs_fs_kill_sb+0x2c/0x30 [usb_f_fs])
[ 1946.636217]  r7:c0dfcb84 r6:c3a12260 r5:bf54d014 r4:c229f000
[ 1946.646273] [<bf547d74>] (ffs_fs_kill_sb [usb_f_fs]) from [<c0326d50>] (deactivate_locked_super+0x54/0x9c)
[ 1946.664893]  r5:bf54d014 r4:c229f000
[ 1946.672921] [<c0326cfc>] (deactivate_locked_super) from [<c0326df8>] (deactivate_super+0x60/0x64)
[ 1946.690722]  r5:c2a09000 r4:c229f000
[ 1946.698706] [<c0326d98>] (deactivate_super) from [<c0349a28>] (cleanup_mnt+0xe4/0x14c)
[ 1946.715553]  r5:c2a09000 r4:00000000
[ 1946.723528] [<c0349944>] (cleanup_mnt) from [<c0349b08>] (__cleanup_mnt+0x1c/0x20)
[ 1946.739922]  r7:c0dfcb84 r6:c3a12260 r5:c3a126fc r4:00000000
[ 1946.750088] [<c0349aec>] (__cleanup_mnt) from [<c0143d10>] (task_work_run+0x84/0xb8)
[ 1946.766602] [<c0143c8c>] (task_work_run) from [<c010bdc8>] (do_work_pending+0x470/0x56c)
[ 1946.783540]  r7:5ac3c35a r6:c0d0424c r5:c200bfb0 r4:c200a000
[ 1946.793614] [<c010b958>] (do_work_pending) from [<c01000c0>] (slow_work_pending+0xc/0x20)
[ 1946.810553] Exception stack(0xc200bfb0 to 0xc200bff8)
[ 1946.820129] bfa0:                                     00000000 00000000 000000aa b5e21430
[ 1946.837104] bfc0: bef867a0 00000001 bef86840 00000034 bef86838 bef86790 bef86794 bef867a0
[ 1946.854125] bfe0: 00000000 bef86798 b67b7a1c b6d626a4 60000010 b5a23760
[ 1946.865335]  r10:00000000 r9:c200a000 r8:c0100224 r7:00000034 r6:bef86840 r5:00000001
[ 1946.881914]  r4:bef867a0
[ 1946.888793] ---[ end trace 7387f2a9725b28d0 ]---

---
 drivers/usb/gadget/function/f_fs.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

@@ -1688,11 +1688,15 @@ static void ffs_data_clear(struct ffs_da
 
 	BUG_ON(ffs->gadget);
 
-	if (ffs->epfiles)
+	if (ffs->epfiles) {
 		ffs_epfiles_destroy(ffs->epfiles, ffs->eps_count);
+		ffs->epfiles = NULL;
+	}
 
-	if (ffs->ffs_eventfd)
+	if (ffs->ffs_eventfd) {
 		eventfd_ctx_put(ffs->ffs_eventfd);
+		ffs->ffs_eventfd = NULL;
+	}
 
 	kfree(ffs->raw_descs_data);
 	kfree(ffs->raw_strings);

@@ -1705,7 +1709,6 @@ static void ffs_data_reset(struct ffs_da
 
 	ffs_data_clear(ffs);
 
-	ffs->epfiles = NULL;
 	ffs->raw_descs_data = NULL;
 	ffs->raw_descs = NULL;
 	ffs->raw_strings = NULL;

From: Todd Kjos <[email protected]>

commit cfd0d84ba28c18b531648c9d4a35ecca89ad9901 upstream.

In 4.13, commit 74310e06be4d ("android: binder: Move buffer out of area shared with user space") fixed a kernel structure visibility issue. As part of that patch,
sizeof(void *) was used as the buffer size for 0-length data payloads so
the driver could detect abusive clients sending 0-length asynchronous transactions to a server by enforcing limits on async_free_size.

Unfortunately, on the "free" side, the accounting of async_free_space did not add the sizeof(void *) back. The result was that up to 8-bytes of async_free_space were leaked on every async transaction of 8-bytes or less. These small transactions are uncommon, so this accounting issue has gone undetected for several years.

The fix is to use "buffer_size" (the allocated buffer size) instead of "size" (the logical buffer size) when updating the async_free_space during the free operation. These are the same except for this corner case of asynchronous transactions with payloads < 8 bytes.

---
 drivers/android/binder_alloc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -619,7 +619,7 @@ static void binder_free_buf_locked(struc
 	BUG_ON(buffer->data > alloc->buffer + alloc->buffer_size);
 
 	if (buffer->async_transaction) {
-		alloc->free_async_space += size + sizeof(struct binder_buffer);
+		alloc->free_async_space += buffer_size + sizeof(struct binder_buffer);
 
 		binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC_ASYNC,
 			     "%d: binder_free_buf size %zd async free %zd\n",

From: Alexey Makhalov <[email protected]>

commit 142c779d05d1fef75134c3cb63f52ccbc96d9e1f upstream.

The PVSCSI implementation in the VMware hypervisor under specific configuration ("SCSI Bus Sharing" set to "Physical") returns zero dataLen in the completion descriptor for READ CAPACITY(16). As a result, the kernel can not detect proper disk geometry. This can be recognized by the kernel message:

  [ 0.776588] sd 1:0:0:0: [sdb] Sector size 0 reported, assuming 512.

The PVSCSI implementation in QEMU does not set dataLen at all, keeping it zeroed. This leads to a boot hang as was reported by Shmulik Ladkani.

It is likely that the controller returns the garbage at the end of the buffer. Residual length should be set by the driver in that case. The SCSI layer will erase corresponding data. See commit bdb2b8cab439 ("[SCSI] erase invalid data returned by device") for details.

Commit e662502b3a78 ("scsi: vmw_pvscsi: Set correct residual data length") introduced the issue by setting residual length unconditionally, causing the SCSI layer to erase the useful payload beyond dataLen when this value is returned as 0.

As a result, considering existing issues in implementations of PVSCSI controllers, we do not want to call scsi_set_resid() when dataLen ==
0. Calling scsi_set_resid() has no effect if dataLen equals buffer length.

---
 drivers/scsi/vmw_pvscsi.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

@@ -578,9 +578,12 @@ static void pvscsi_complete_request(stru
 			 * Commands like INQUIRY may transfer less data than
 			 * requested by the initiator via bufflen. Set residual
 			 * count to make upper layer aware of the actual amount
-			 * of data returned.
+			 * of data returned. There are cases when controller
+			 * returns zero dataLen with non zero data - do not set
+			 * residual count in that case.
 			 */
-			scsi_set_resid(cmd, scsi_bufflen(cmd) - e->dataLen);
+			if (e->dataLen && (e->dataLen < scsi_bufflen(cmd)))
+				scsi_set_resid(cmd, scsi_bufflen(cmd) - e->dataLen);
 			cmd->result = (DID_OK << 16);
 			break;
 

From: Pavel Skripkin <[email protected]>

commit 9f3ccdc3f6ef10084ceb3a47df0961bec6196fd0 upstream.

Syzbot has reported warning in __flush_work(). This warning is caused by work->func == NULL, which means missing work initialization.

This may happen, since input_dev->close() calls cancel_work_sync(&dev->work), but dev->work initalization happens _after_ input_register_device() call.

So this patch moves dev->work initialization before registering input device

---
 drivers/input/mouse/appletouch.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -929,6 +929,8 @@ static int atp_probe(struct usb_interfac
 	set_bit(BTN_TOOL_TRIPLETAP, input_dev->keybit);
 	set_bit(BTN_LEFT, input_dev->keybit);
 
+	INIT_WORK(&dev->work, atp_reinit);
+
 	error = input_register_device(dev->input);
 	if (error)
 		goto err_free_buffer;

@@ -936,8 +938,6 @@ static int atp_probe(struct usb_interfac
 	/* save our data pointer in this interface device */
 	usb_set_intfdata(iface, dev);
 
-	INIT_WORK(&dev->work, atp_reinit);
-
 	return 0;
 
  err_free_buffer:

From: Leo L. Schwab <[email protected]>

commit bc7ec91718c49d938849697cfad98fcd9877cc26 upstream.

The spaceball.c module was not properly parsing the movement reports coming from the device. The code read axis data as signed 16-bit little-endian values starting at offset 2.

In fact, axis data in Spaceball movement reports are signed 16-bit big-endian values starting at offset 3. This was determined first by visually inspecting the data packets, and later verified by consulting:
http://spacemice.org/pdf/SpaceBall_2003-3003_Protocol.pdf

If this ever worked properly, it was in the time before Git...

---
 drivers/input/joystick/spaceball.c |   11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

@@ -35,6 +35,7 @@
 #include <linux/module.h>
 #include <linux/input.h>
 #include <linux/serio.h>
+#include <asm/unaligned.h>
 
 #define DRIVER_DESC	"SpaceTec SpaceBall 2003/3003/4000 FLX driver"
 

@@ -91,9 +92,15 @@ static void spaceball_process_packet(str
 
 		case 'D':					/* Ball data */
 			if (spaceball->idx != 15) return;
-			for (i = 0; i < 6; i++)
+			/*
+			 * Skip first three bytes; read six axes worth of data.
+			 * Axis values are signed 16-bit big-endian.
+			 */
+			data += 3;
+			for (i = 0; i < ARRAY_SIZE(spaceball_axes); i++) {
 				input_report_abs(dev, spaceball_axes[i],
-					(__s16)((data[2 * i + 3] << 8) | data[2 * i + 2]));
+					(__s16)get_unaligned_be16(&data[i * 2]));
+			}
 			break;
 
 		case 'K':					/* Button data */

From: Muchun Song <[email protected]>

commit e22e45fc9e41bf9fcc1e92cfb78eb92786728ef0 upstream.

A real world panic issue was found as follow in Linux 5.4.

    BUG: unable to handle page fault for address: ffffde49a863de28
    PGD 7e6fe62067 P4D 7e6fe62067 PUD 7e6fe63067 PMD f51e064067 PTE 0
    RIP: 0010:tw_timer_handler+0x20/0x40
    Call Trace:
     <IRQ>
     call_timer_fn+0x2b/0x120
     run_timer_softirq+0x1ef/0x450
     __do_softirq+0x10d/0x2b8
     irq_exit+0xc7/0xd0
     smp_apic_timer_interrupt+0x68/0x120
     apic_timer_interrupt+0xf/0x20

This issue was also reported since 2017 in the thread [1], unfortunately, the issue was still can be reproduced after fixing DCCP.

The ipv4_mib_exit_net is called before tcp_sk_exit_batch when a net namespace is destroyed since tcp_sk_ops is registered befrore ipv4_mib_ops, which means tcp_sk_ops is in the front of ipv4_mib_ops in the list of pernet_list. There will be a use-after-free on net->mib.net_statistics in tw_timer_handler after ipv4_mib_exit_net if there are some inflight time-wait timers.

This bug is not introduced by commit f2bf415cfed7 ("mib: add net to NET_ADD_STATS_BH") since the net_statistics is a global variable instead of dynamic allocation and freeing. Actually, commit 61a7e26028b9 ("mib: put net statistics on struct net") introduces the bug since it put net statistics on struct net and free it when net namespace is destroyed.

Moving init_ipv4_mibs() to the front of tcp_init() to fix this bug and replace pr_crit() with panic() since continuing is meaningless when init_ipv4_mibs() fails.

[1] https://groups.google.com/g/syzkaller/c/p1tn-_Kc6l4/m/smuL_FMAAgAJ?pli=1

---
 net/ipv4/af_inet.c |   10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

@@ -1883,6 +1883,10 @@ static int __init inet_init(void)
 
 	ip_init();
 
+	/* Initialise per-cpu ipv4 mibs */
+	if (init_ipv4_mibs())
+		panic("%s: Cannot init ipv4 mibs\n", __func__);
+
 	/* Setup TCP slab cache for open requests. */
 	tcp_init();
 

@@ -1911,12 +1915,6 @@ static int __init inet_init(void)
 
 	if (init_inet_pernet_ops())
 		pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__);
-	/*
-	 *	Initialise per-cpu ipv4 mibs
-	 */
-
-	if (init_ipv4_mibs())
-		pr_crit("%s: Cannot init ipv4 mibs\n", __func__);
 
 	ipv4_proc_init();
 

From: Xin Long <[email protected]>

commit 5ec7d18d1813a5bead0b495045606c93873aecbb upstream.

This patch is to delay the endpoint free by calling call_rcu() to fix another use-after-free issue in sctp_sock_dump():

  BUG: KASAN: use-after-free in __lock_acquire+0x36d9/0x4c20
  Call Trace:
    __lock_acquire+0x36d9/0x4c20 kernel/locking/lockdep.c:3218
    lock_acquire+0x1ed/0x520 kernel/locking/lockdep.c:3844
    __raw_spin_lock_bh include/linux/spinlock_api_smp.h:135 [inline]
    _raw_spin_lock_bh+0x31/0x40 kernel/locking/spinlock.c:168
    spin_lock_bh include/linux/spinlock.h:334 [inline]
    __lock_sock+0x203/0x350 net/core/sock.c:2253
    lock_sock_nested+0xfe/0x120 net/core/sock.c:2774
    lock_sock include/net/sock.h:1492 [inline]
    sctp_sock_dump+0x122/0xb20 net/sctp/diag.c:324
    sctp_for_each_transport+0x2b5/0x370 net/sctp/socket.c:5091
    sctp_diag_dump+0x3ac/0x660 net/sctp/diag.c:527
    __inet_diag_dump+0xa8/0x140 net/ipv4/inet_diag.c:1049
    inet_diag_dump+0x9b/0x110 net/ipv4/inet_diag.c:1065
    netlink_dump+0x606/0x1080 net/netlink/af_netlink.c:2244
    __netlink_dump_start+0x59a/0x7c0 net/netlink/af_netlink.c:2352
    netlink_dump_start include/linux/netlink.h:216 [inline]
    inet_diag_handler_cmd+0x2ce/0x3f0 net/ipv4/inet_diag.c:1170
    __sock_diag_cmd net/core/sock_diag.c:232 [inline]
    sock_diag_rcv_msg+0x31d/0x410 net/core/sock_diag.c:263
    netlink_rcv_skb+0x172/0x440 net/netlink/af_netlink.c:2477
    sock_diag_rcv+0x2a/0x40 net/core/sock_diag.c:274

This issue occurs when asoc is peeled off and the old sk is freed after getting it by asoc->base.sk and before calling lock_sock(sk).

To prevent the sk free, as a holder of the sk, ep should be alive when calling lock_sock(). This patch uses call_rcu() and moves sock_put and ep free into sctp_endpoint_destroy_rcu(), so that it's safe to try to hold the ep under rcu_read_lock in sctp_transport_traverse_process().

If sctp_endpoint_hold() returns true, it means this ep is still alive and we have held it and can continue to dump it; If it returns false, it means this ep is dead and can be freed after rcu_read_unlock, and we should skip it.

In sctp_sock_dump(), after locking the sk, if this ep is different from tsp->asoc->ep, it means during this dumping, this asoc was peeled off before calling lock_sock(), and the sk should be skipped; If this ep is the same with tsp->asoc->ep, it means no peeloff happens on this asoc, and due to lock_sock, no peeloff will happen either until release_sock.

Note that delaying endpoint free won't delay the port release, as the port release happens in sctp_endpoint_destroy() before calling call_rcu(). Also, freeing endpoint by call_rcu() makes it safe to access the sk by asoc->base.sk in sctp_assocs_seq_show() and sctp_rcv().

Thanks Jones to bring this issue up.

v1->v2:
- improve the changelog.
- add kfree(ep) into sctp_endpoint_destroy_rcu(), as Jakub noticed.

---
 include/net/sctp/sctp.h    |    6 +++---
 include/net/sctp/structs.h |    3 ++-
 net/sctp/endpointola.c     |   23 +++++++++++++++--------
 net/sctp/sctp_diag.c       |   12 ++++++------
 net/sctp/socket.c          |   23 +++++++++++++++--------
 5 files changed, 41 insertions(+), 26 deletions(-)

@@ -118,6 +118,7 @@ extern struct percpu_counter sctp_socket
 int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *);
 struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *);
 
+typedef int (*sctp_callback_t)(struct sctp_endpoint *, struct sctp_transport *, void *);
 int sctp_transport_walk_start(struct rhashtable_iter *iter);
 void sctp_transport_walk_stop(struct rhashtable_iter *iter);
 struct sctp_transport *sctp_transport_get_next(struct net *net,

@@ -128,9 +129,8 @@ int sctp_transport_lookup_process(int (*
 				  struct net *net,
 				  const union sctp_addr *laddr,
 				  const union sctp_addr *paddr, void *p);
-int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
-			    int (*cb_done)(struct sctp_transport *, void *),
-			    struct net *net, int *pos, void *p);
+int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done,
+				    struct net *net, int *pos, void *p);
 int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), void *p);
 int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc,
 		       struct sctp_info *info);

@@ -1272,6 +1272,7 @@ struct sctp_endpoint {
 	      reconf_enable:1;
 
 	__u8  strreset_enable;
+	struct rcu_head rcu;
 };
 
 /* Recover the outter endpoint structure. */

@@ -1287,7 +1288,7 @@ static inline struct sctp_endpoint *sctp
 struct sctp_endpoint *sctp_endpoint_new(struct sock *, gfp_t);
 void sctp_endpoint_free(struct sctp_endpoint *);
 void sctp_endpoint_put(struct sctp_endpoint *);
-void sctp_endpoint_hold(struct sctp_endpoint *);
+int sctp_endpoint_hold(struct sctp_endpoint *ep);
 void sctp_endpoint_add_asoc(struct sctp_endpoint *, struct sctp_association *);
 struct sctp_association *sctp_endpoint_lookup_assoc(
 	const struct sctp_endpoint *ep,

@@ -242,6 +242,18 @@ void sctp_endpoint_free(struct sctp_endp
 }
 
 /* Final destructor for endpoint.  */
+static void sctp_endpoint_destroy_rcu(struct rcu_head *head)
+{
+	struct sctp_endpoint *ep = container_of(head, struct sctp_endpoint, rcu);
+	struct sock *sk = ep->base.sk;
+
+	sctp_sk(sk)->ep = NULL;
+	sock_put(sk);
+
+	kfree(ep);
+	SCTP_DBG_OBJCNT_DEC(ep);
+}
+
 static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
 {
 	struct sock *sk;

@@ -275,18 +287,13 @@ static void sctp_endpoint_destroy(struct
 	if (sctp_sk(sk)->bind_hash)
 		sctp_put_port(sk);
 
-	sctp_sk(sk)->ep = NULL;
-	/* Give up our hold on the sock */
-	sock_put(sk);
-
-	kfree(ep);
-	SCTP_DBG_OBJCNT_DEC(ep);
+	call_rcu(&ep->rcu, sctp_endpoint_destroy_rcu);
 }
 
 /* Hold a reference to an endpoint. */
-void sctp_endpoint_hold(struct sctp_endpoint *ep)
+int sctp_endpoint_hold(struct sctp_endpoint *ep)
 {
-	refcount_inc(&ep->base.refcnt);
+	return refcount_inc_not_zero(&ep->base.refcnt);
 }
 
 /* Release a reference to an endpoint and clean up if there are

@@ -276,9 +276,8 @@ out:
 	return err;
 }
 
-static int sctp_sock_dump(struct sctp_transport *tsp, void *p)
+static int sctp_sock_dump(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
 {
-	struct sctp_endpoint *ep = tsp->asoc->ep;
 	struct sctp_comm_param *commp = p;
 	struct sock *sk = ep->base.sk;
 	struct sk_buff *skb = commp->skb;

@@ -288,6 +287,8 @@ static int sctp_sock_dump(struct sctp_tr
 	int err = 0;
 
 	lock_sock(sk);
+	if (ep != tsp->asoc->ep)
+		goto release;
 	list_for_each_entry(assoc, &ep->asocs, asocs) {
 		if (cb->args[4] < cb->args[1])
 			goto next;

@@ -330,9 +331,8 @@ release:
 	return err;
 }
 
-static int sctp_sock_filter(struct sctp_transport *tsp, void *p)
+static int sctp_sock_filter(struct sctp_endpoint *ep, struct sctp_transport *tsp, void *p)
 {
-	struct sctp_endpoint *ep = tsp->asoc->ep;
 	struct sctp_comm_param *commp = p;
 	struct sock *sk = ep->base.sk;
 	const struct inet_diag_req_v2 *r = commp->r;

@@ -490,8 +490,8 @@ skip:
 	if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)))
 		goto done;
 
-	sctp_for_each_transport(sctp_sock_filter, sctp_sock_dump,
-				net, &pos, &commp);
+	sctp_transport_traverse_process(sctp_sock_filter, sctp_sock_dump,
+					net, &pos, &commp);
 	cb->args[2] = pos;
 
 done:

@@ -4738,11 +4738,12 @@ int sctp_transport_lookup_process(int (*
 }
 EXPORT_SYMBOL_GPL(sctp_transport_lookup_process);
 
-int sctp_for_each_transport(int (*cb)(struct sctp_transport *, void *),
-			    int (*cb_done)(struct sctp_transport *, void *),
-			    struct net *net, int *pos, void *p) {
+int sctp_transport_traverse_process(sctp_callback_t cb, sctp_callback_t cb_done,
+				    struct net *net, int *pos, void *p)
+{
 	struct rhashtable_iter hti;
 	struct sctp_transport *tsp;
+	struct sctp_endpoint *ep;
 	int ret;
 
 again:

@@ -4752,26 +4753,32 @@ again:
 
 	tsp = sctp_transport_get_idx(net, &hti, *pos + 1);
 	for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) {
-		ret = cb(tsp, p);
-		if (ret)
-			break;
+		ep = tsp->asoc->ep;
+		if (sctp_endpoint_hold(ep)) { /* asoc can be peeled off */
+			ret = cb(ep, tsp, p);
+			if (ret)
+				break;
+			sctp_endpoint_put(ep);
+		}
 		(*pos)++;
 		sctp_transport_put(tsp);
 	}
 	sctp_transport_walk_stop(&hti);
 
 	if (ret) {
-		if (cb_done && !cb_done(tsp, p)) {
+		if (cb_done && !cb_done(ep, tsp, p)) {
 			(*pos)++;
+			sctp_endpoint_put(ep);
 			sctp_transport_put(tsp);
 			goto again;
 		}
+		sctp_endpoint_put(ep);
 		sctp_transport_put(tsp);
 	}
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(sctp_for_each_transport);
+EXPORT_SYMBOL_GPL(sctp_transport_traverse_process);
 
 /* 7.2.1 Association Status (SCTP_STATUS)
 

Build results:

	total: 168 pass: 168 fail: 0
Qemu test results:
	total: 421 pass: 421 fail: 0

Guenter

All tests passing for Tegra ...

Test results for stable-v4.14:

    8 builds:	8 pass, 0 fail
    16 boots:	16 pass, 0 fail
    32 tests:	32 pass, 0 fail

Linux version: 4.14.261-rc1-g1e980b44673d
Boards tested: tegra124-jetson-tk1, tegra20-ventana,

                tegra210-p2371-2180, tegra30-cardhu-a04

Jon

Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.

## Build
* kernel: 4.14.261-rc1
* git: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
* git branch: linux-4.14.y
* git commit: 1e980b44673d11c0bb0bed2afb54341e7541c083
* git describe: v4.14.260-20-g1e980b44673d
* test details:
https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-4.14.y/build/v4.14.260-20-g1e980b44673d

## Test Regressions (compared to v4.14.260)
No test regressions found.

## Metric Regressions (compared to v4.14.260)
No metric regressions found.

## Test Fixes (compared to v4.14.260)
No test fixes found.

## Metric Fixes (compared to v4.14.260)
No metric fixes found.

## Test result summary
total: 70912, pass: 57256, fail: 577, skip: 11331, xfail: 1748

## Build Summary
* arm: 254 total, 242 passed, 12 failed
* arm64: 32 total, 32 passed, 0 failed
* dragonboard-410c: 1 total, 1 passed, 0 failed
* hi6220-hikey: 1 total, 1 passed, 0 failed
* i386: 19 total, 19 passed, 0 failed
* juno-r2: 1 total, 1 passed, 0 failed
* mips: 22 total, 22 passed, 0 failed
* powerpc: 52 total, 0 passed, 52 failed
* sparc: 12 total, 12 passed, 0 failed
* x15: 1 total, 1 passed, 0 failed
* x86: 1 total, 1 passed, 0 failed
* x86_64: 31 total, 31 passed, 0 failed

## Test suites summary
* fwts
* igt-gpu-tools
* kselftest-android
* kselftest-arm64
* kselftest-arm64/arm64.btitest.bti_c_func
* kselftest-arm64/arm64.btitest.bti_j_func
* kselftest-arm64/arm64.btitest.bti_jc_func
* kselftest-arm64/arm64.btitest.bti_none_func
* kselftest-arm64/arm64.btitest.nohint_func
* kselftest-arm64/arm64.btitest.paciasp_func
* kselftest-arm64/arm64.nobtitest.bti_c_func
* kselftest-arm64/arm64.nobtitest.bti_j_func
* kselftest-arm64/arm64.nobtitest.bti_jc_func
* kselftest-arm64/arm64.nobtitest.bti_none_func
* kselftest-arm64/arm64.nobtitest.nohint_func
* kselftest-arm64/arm64.nobtitest.paciasp_func
* kselftest-bpf
* kselftest-breakpoints
* kselftest-capabilities
* kselftest-cgroup
* kselftest-clone3
* kselftest-core
* kselftest-cpu-hotplug
* kselftest-cpufreq
* kselftest-drivers
* kselftest-efivarfs
* kselftest-filesystems
* kselftest-firmware
* kselftest-fpu
* kselftest-futex
* kselftest-gpio
* kselftest-intel_pstate
* kselftest-ipc
* kselftest-ir
* kselftest-kcmp
* kselftest-kexec
* kselftest-kvm
* kselftest-lib
* kselftest-livepatch
* kselftest-membarrier
* kselftest-net
* kselftest-netfilter
* kselftest-nsfs
* kselftest-openat2
* kselftest-pid_namespace
* kselftest-pidfd
* kselftest-proc
* kselftest-pstore
* kselftest-ptrace
* kselftest-rseq
* kselftest-rtc
* kselftest-seccomp
* kselftest-sigaltstack
* kselftest-size
* kselftest-splice
* kselftest-static_keys
* kselftest-sync
* kselftest-sysctl
* kselftest-tc-testing
* kselftest-timens
* kselftest-timers
* kselftest-tmpfs
* kselftest-tpm2
* kselftest-user
* kselftest-vm
* kselftest-x86
* kselftest-zram
* kvm-unit-tests
* libhugetlbfs
* linux-log-parser
* ltp-cap_bounds-tests
* ltp-commands-tests
* ltp-containers-tests
* ltp-controllers-tests
* ltp-cpuhotplug-tests
* ltp-crypto-tests
* ltp-cve-tests
* ltp-dio-tests
* ltp-fcntl-locktests-tests
* ltp-filecaps-tests
* ltp-fs-tests
* ltp-fs_bind-tests
* ltp-fs_perms_simple-tests
* ltp-fsx-tests
* ltp-hugetlb-tests
* ltp-io-tests
* ltp-ipc-tests
* ltp-math-tests
* ltp-mm-tests
* ltp-nptl-tests
* ltp-open-posix-tests
* ltp-pty-tests
* ltp-sched-tests
* ltp-securebits-tests
* ltp-syscalls-tests
* ltp-tracing-tests
* network-basic-tests
* packetdrill
* perf
* rcutorture
* ssuite
* v4l2-compliance

--
Linaro LKFT
https://lkft.linaro.org

Compiled and booted on my test system. No dmesg regressions.

thanks,
-- Shuah