Re: Linux 5.2.6

From: Greg KH
Date: Sun Aug 04 2019 - 06:14:29 EST


diff --git a/Makefile b/Makefile
index 78bd926c8439..3cd40f1a8f75 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 5
PATCHLEVEL = 2
-SUBLEVEL = 5
+SUBLEVEL = 6
EXTRAVERSION =
NAME = Bobtail Squid

diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig
index b9a37057b77a..cee24c308337 100644
--- a/arch/sh/boards/Kconfig
+++ b/arch/sh/boards/Kconfig
@@ -8,27 +8,19 @@ config SH_ALPHA_BOARD
bool

config SH_DEVICE_TREE
- bool "Board Described by Device Tree"
+ bool
select OF
select OF_EARLY_FLATTREE
select TIMER_OF
select COMMON_CLK
select GENERIC_CALIBRATE_DELAY
- help
- Select Board Described by Device Tree to build a kernel that
- does not hard-code any board-specific knowledge but instead uses
- a device tree blob provided by the boot-loader. You must enable
- drivers for any hardware you want to use separately. At this
- time, only boards based on the open-hardware J-Core processors
- have sufficient driver coverage to use this option; do not
- select it if you are using original SuperH hardware.

config SH_JCORE_SOC
bool "J-Core SoC"
- depends on SH_DEVICE_TREE && (CPU_SH2 || CPU_J2)
+ select SH_DEVICE_TREE
select CLKSRC_JCORE_PIT
select JCORE_AIC
- default y if CPU_J2
+ depends on CPU_J2
help
Select this option to include drivers core components of the
J-Core SoC, including interrupt controllers and timers.
diff --git a/drivers/bluetooth/hci_ath.c b/drivers/bluetooth/hci_ath.c
index a55be205b91a..dbfe34664633 100644
--- a/drivers/bluetooth/hci_ath.c
+++ b/drivers/bluetooth/hci_ath.c
@@ -98,6 +98,9 @@ static int ath_open(struct hci_uart *hu)

BT_DBG("hu %p", hu);

+ if (!hci_uart_has_flow_control(hu))
+ return -EOPNOTSUPP;
+
ath = kzalloc(sizeof(*ath), GFP_KERNEL);
if (!ath)
return -ENOMEM;
diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c
index 8905ad2edde7..ae2624fce913 100644
--- a/drivers/bluetooth/hci_bcm.c
+++ b/drivers/bluetooth/hci_bcm.c
@@ -406,6 +406,9 @@ static int bcm_open(struct hci_uart *hu)

bt_dev_dbg(hu->hdev, "hu %p", hu);

+ if (!hci_uart_has_flow_control(hu))
+ return -EOPNOTSUPP;
+
bcm = kzalloc(sizeof(*bcm), GFP_KERNEL);
if (!bcm)
return -ENOMEM;
diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c
index 207bae5e0d46..31f25153087d 100644
--- a/drivers/bluetooth/hci_intel.c
+++ b/drivers/bluetooth/hci_intel.c
@@ -391,6 +391,9 @@ static int intel_open(struct hci_uart *hu)

BT_DBG("hu %p", hu);

+ if (!hci_uart_has_flow_control(hu))
+ return -EOPNOTSUPP;
+
intel = kzalloc(sizeof(*intel), GFP_KERNEL);
if (!intel)
return -ENOMEM;
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index c84f985f348d..c953f14656b5 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -284,6 +284,19 @@ static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
return 0;
}

+/* Check the underlying device or tty has flow control support */
+bool hci_uart_has_flow_control(struct hci_uart *hu)
+{
+ /* serdev nodes check if the needed operations are present */
+ if (hu->serdev)
+ return true;
+
+ if (hu->tty->driver->ops->tiocmget && hu->tty->driver->ops->tiocmset)
+ return true;
+
+ return false;
+}
+
/* Flow control or un-flow control the device */
void hci_uart_set_flow_control(struct hci_uart *hu, bool enable)
{
diff --git a/drivers/bluetooth/hci_mrvl.c b/drivers/bluetooth/hci_mrvl.c
index 50212ac629e3..49dcf198ffd8 100644
--- a/drivers/bluetooth/hci_mrvl.c
+++ b/drivers/bluetooth/hci_mrvl.c
@@ -52,6 +52,9 @@ static int mrvl_open(struct hci_uart *hu)

BT_DBG("hu %p", hu);

+ if (!hci_uart_has_flow_control(hu))
+ return -EOPNOTSUPP;
+
mrvl = kzalloc(sizeof(*mrvl), GFP_KERNEL);
if (!mrvl)
return -ENOMEM;
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 9d273cdde563..f41fb2c02e4f 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -458,6 +458,9 @@ static int qca_open(struct hci_uart *hu)

BT_DBG("hu %p qca_open", hu);

+ if (!hci_uart_has_flow_control(hu))
+ return -EOPNOTSUPP;
+
qca = kzalloc(sizeof(struct qca_data), GFP_KERNEL);
if (!qca)
return -ENOMEM;
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index d8cf005e3c5d..22c278b13ab9 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -103,6 +103,7 @@ int hci_uart_tx_wakeup(struct hci_uart *hu);
int hci_uart_init_ready(struct hci_uart *hu);
void hci_uart_init_work(struct work_struct *work);
void hci_uart_set_baudrate(struct hci_uart *hu, unsigned int speed);
+bool hci_uart_has_flow_control(struct hci_uart *hu);
void hci_uart_set_flow_control(struct hci_uart *hu, bool enable);
void hci_uart_set_speeds(struct hci_uart *hu, unsigned int init_speed,
unsigned int oper_speed);
diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c
index 4c99739b937e..0e224232f746 100644
--- a/drivers/isdn/hardware/mISDN/hfcsusb.c
+++ b/drivers/isdn/hardware/mISDN/hfcsusb.c
@@ -1955,6 +1955,9 @@ hfcsusb_probe(struct usb_interface *intf, const struct usb_device_id *id)

/* get endpoint base */
idx = ((ep_addr & 0x7f) - 1) * 2;
+ if (idx > 15)
+ return -EIO;
+
if (ep_addr & 0x80)
idx++;
attr = ep->desc.bmAttributes;
diff --git a/drivers/media/radio/radio-raremono.c b/drivers/media/radio/radio-raremono.c
index 5e782b3c2fa9..bf1ee654df80 100644
--- a/drivers/media/radio/radio-raremono.c
+++ b/drivers/media/radio/radio-raremono.c
@@ -271,6 +271,14 @@ static int vidioc_g_frequency(struct file *file, void *priv,
return 0;
}

+static void raremono_device_release(struct v4l2_device *v4l2_dev)
+{
+ struct raremono_device *radio = to_raremono_dev(v4l2_dev);
+
+ kfree(radio->buffer);
+ kfree(radio);
+}
+
/* File system interface */
static const struct v4l2_file_operations usb_raremono_fops = {
.owner = THIS_MODULE,
@@ -295,12 +303,14 @@ static int usb_raremono_probe(struct usb_interface *intf,
struct raremono_device *radio;
int retval = 0;

- radio = devm_kzalloc(&intf->dev, sizeof(struct raremono_device), GFP_KERNEL);
- if (radio)
- radio->buffer = devm_kmalloc(&intf->dev, BUFFER_LENGTH, GFP_KERNEL);
-
- if (!radio || !radio->buffer)
+ radio = kzalloc(sizeof(*radio), GFP_KERNEL);
+ if (!radio)
+ return -ENOMEM;
+ radio->buffer = kmalloc(BUFFER_LENGTH, GFP_KERNEL);
+ if (!radio->buffer) {
+ kfree(radio);
return -ENOMEM;
+ }

radio->usbdev = interface_to_usbdev(intf);
radio->intf = intf;
@@ -324,7 +334,8 @@ static int usb_raremono_probe(struct usb_interface *intf,
if (retval != 3 ||
(get_unaligned_be16(&radio->buffer[1]) & 0xfff) == 0x0242) {
dev_info(&intf->dev, "this is not Thanko's Raremono.\n");
- return -ENODEV;
+ retval = -ENODEV;
+ goto free_mem;
}

dev_info(&intf->dev, "Thanko's Raremono connected: (%04X:%04X)\n",
@@ -333,7 +344,7 @@ static int usb_raremono_probe(struct usb_interface *intf,
retval = v4l2_device_register(&intf->dev, &radio->v4l2_dev);
if (retval < 0) {
dev_err(&intf->dev, "couldn't register v4l2_device\n");
- return retval;
+ goto free_mem;
}

mutex_init(&radio->lock);
@@ -345,6 +356,7 @@ static int usb_raremono_probe(struct usb_interface *intf,
radio->vdev.ioctl_ops = &usb_raremono_ioctl_ops;
radio->vdev.lock = &radio->lock;
radio->vdev.release = video_device_release_empty;
+ radio->v4l2_dev.release = raremono_device_release;

usb_set_intfdata(intf, &radio->v4l2_dev);

@@ -360,6 +372,10 @@ static int usb_raremono_probe(struct usb_interface *intf,
}
dev_err(&intf->dev, "could not register video device\n");
v4l2_device_unregister(&radio->v4l2_dev);
+
+free_mem:
+ kfree(radio->buffer);
+ kfree(radio);
return retval;
}

diff --git a/drivers/media/usb/au0828/au0828-core.c b/drivers/media/usb/au0828/au0828-core.c
index f746f6e2f686..a8a72d5fbd12 100644
--- a/drivers/media/usb/au0828/au0828-core.c
+++ b/drivers/media/usb/au0828/au0828-core.c
@@ -719,6 +719,12 @@ static int au0828_usb_probe(struct usb_interface *interface,
/* Setup */
au0828_card_setup(dev);

+ /*
+ * Store the pointer to the au0828_dev so it can be accessed in
+ * au0828_usb_disconnect
+ */
+ usb_set_intfdata(interface, dev);
+
/* Analog TV */
retval = au0828_analog_register(dev, interface);
if (retval) {
@@ -737,12 +743,6 @@ static int au0828_usb_probe(struct usb_interface *interface,
/* Remote controller */
au0828_rc_register(dev);

- /*
- * Store the pointer to the au0828_dev so it can be accessed in
- * au0828_usb_disconnect
- */
- usb_set_intfdata(interface, dev);
-
pr_info("Registered device AU0828 [%s]\n",
dev->board.name == NULL ? "Unset" : dev->board.name);

diff --git a/drivers/media/usb/cpia2/cpia2_usb.c b/drivers/media/usb/cpia2/cpia2_usb.c
index b2268981c963..17468f7d78ed 100644
--- a/drivers/media/usb/cpia2/cpia2_usb.c
+++ b/drivers/media/usb/cpia2/cpia2_usb.c
@@ -893,7 +893,6 @@ static void cpia2_usb_disconnect(struct usb_interface *intf)
cpia2_unregister_camera(cam);
v4l2_device_disconnect(&cam->v4l2_dev);
mutex_unlock(&cam->v4l2_lock);
- v4l2_device_put(&cam->v4l2_dev);

if(cam->buffers) {
DBG("Wakeup waiting processes\n");
@@ -902,6 +901,8 @@ static void cpia2_usb_disconnect(struct usb_interface *intf)
wake_up_interruptible(&cam->wq_stream);
}

+ v4l2_device_put(&cam->v4l2_dev);
+
LOG("CPiA2 camera disconnected.\n");
}

diff --git a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
index 70b5cb08d65b..bbf361ce0bd0 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-hdw.c
@@ -1670,7 +1670,7 @@ static int pvr2_decoder_enable(struct pvr2_hdw *hdw,int enablefl)
}
if (!hdw->flag_decoder_missed) {
pvr2_trace(PVR2_TRACE_ERROR_LEGS,
- "WARNING: No decoder present");
+ "***WARNING*** No decoder present");
hdw->flag_decoder_missed = !0;
trace_stbit("flag_decoder_missed",
hdw->flag_decoder_missed);
@@ -2356,7 +2356,7 @@ struct pvr2_hdw *pvr2_hdw_create(struct usb_interface *intf,
if (hdw_desc->flag_is_experimental) {
pvr2_trace(PVR2_TRACE_INFO, "**********");
pvr2_trace(PVR2_TRACE_INFO,
- "WARNING: Support for this device (%s) is experimental.",
+ "***WARNING*** Support for this device (%s) is experimental.",
hdw_desc->description);
pvr2_trace(PVR2_TRACE_INFO,
"Important functionality might not be entirely working.");
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c b/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
index 68e323f8d9cf..275394bafe7d 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-i2c-core.c
@@ -333,11 +333,11 @@ static int i2c_hack_cx25840(struct pvr2_hdw *hdw,

if ((ret != 0) || (*rdata == 0x04) || (*rdata == 0x0a)) {
pvr2_trace(PVR2_TRACE_ERROR_LEGS,
- "WARNING: Detected a wedged cx25840 chip; the device will not work.");
+ "***WARNING*** Detected a wedged cx25840 chip; the device will not work.");
pvr2_trace(PVR2_TRACE_ERROR_LEGS,
- "WARNING: Try power cycling the pvrusb2 device.");
+ "***WARNING*** Try power cycling the pvrusb2 device.");
pvr2_trace(PVR2_TRACE_ERROR_LEGS,
- "WARNING: Disabling further access to the device to prevent other foul-ups.");
+ "***WARNING*** Disabling further access to the device to prevent other foul-ups.");
// This blocks all further communication with the part.
hdw->i2c_func[0x44] = NULL;
pvr2_hdw_render_useless(hdw);
diff --git a/drivers/media/usb/pvrusb2/pvrusb2-std.c b/drivers/media/usb/pvrusb2/pvrusb2-std.c
index 447279b4a545..e7ab41401577 100644
--- a/drivers/media/usb/pvrusb2/pvrusb2-std.c
+++ b/drivers/media/usb/pvrusb2/pvrusb2-std.c
@@ -343,7 +343,7 @@ struct v4l2_standard *pvr2_std_create_enum(unsigned int *countptr,
bcnt = pvr2_std_id_to_str(buf,sizeof(buf),fmsk);
pvr2_trace(
PVR2_TRACE_ERROR_LEGS,
- "WARNING: Failed to classify the following standard(s): %.*s",
+ "***WARNING*** Failed to classify the following standard(s): %.*s",
bcnt,buf);
}

diff --git a/drivers/net/wireless/ath/ath10k/usb.c b/drivers/net/wireless/ath/ath10k/usb.c
index 970cf69ac35f..a3ecf7d77949 100644
--- a/drivers/net/wireless/ath/ath10k/usb.c
+++ b/drivers/net/wireless/ath/ath10k/usb.c
@@ -1016,7 +1016,7 @@ static int ath10k_usb_probe(struct usb_interface *interface,
}

/* TODO: remove this once USB support is fully implemented */
- ath10k_warn(ar, "WARNING: ath10k USB support is incomplete, don't expect anything to work!\n");
+ ath10k_warn(ar, "Warning: ath10k USB support is incomplete, don't expect anything to work!\n");

return 0;

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 499acf07d61a..e942b3e84068 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -12,11 +12,6 @@ module_param(multipath, bool, 0444);
MODULE_PARM_DESC(multipath,
"turn on native support for multiple controllers per subsystem");

-inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
-{
- return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3));
-}
-
/*
* If multipathing is enabled we need to always use the subsystem instance
* number for numbering our devices to avoid conflicts between subsystems that
@@ -614,7 +609,8 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
{
int error;

- if (!nvme_ctrl_use_ana(ctrl))
+ /* check if multipath is enabled and we have the capability */
+ if (!multipath || !ctrl->subsys || !(ctrl->subsys->cmic & (1 << 3)))
return 0;

ctrl->anacap = id->anacap;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 55553d293a98..7391cd0a7739 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -472,7 +472,11 @@ extern const struct attribute_group *nvme_ns_id_attr_groups[];
extern const struct block_device_operations nvme_ns_head_ops;

#ifdef CONFIG_NVME_MULTIPATH
-bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl);
+static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+ return ctrl->ana_log_buf != NULL;
+}
+
void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
struct nvme_ctrl *ctrl, int *flags);
void nvme_failover_req(struct request *req);
diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c
index 3a546ec10d90..22a65ad4e46e 100644
--- a/drivers/pps/pps.c
+++ b/drivers/pps/pps.c
@@ -152,6 +152,14 @@ static long pps_cdev_ioctl(struct file *file,
pps->params.mode |= PPS_CANWAIT;
pps->params.api_version = PPS_API_VERS;

+ /*
+ * Clear unused fields of pps_kparams to avoid leaking
+ * uninitialized data of the PPS_SETPARAMS caller via
+ * PPS_GETPARAMS
+ */
+ pps->params.assert_off_tu.flags = 0;
+ pps->params.clear_off_tu.flags = 0;
+
spin_unlock_irq(&pps->lock);

break;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 0176241eaea7..7754d7679122 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1263,20 +1263,22 @@ static int send_cap_msg(struct cap_msg_args *arg)
}

/*
- * Queue cap releases when an inode is dropped from our cache. Since
- * inode is about to be destroyed, there is no need for i_ceph_lock.
+ * Queue cap releases when an inode is dropped from our cache.
*/
-void __ceph_remove_caps(struct inode *inode)
+void __ceph_remove_caps(struct ceph_inode_info *ci)
{
- struct ceph_inode_info *ci = ceph_inode(inode);
struct rb_node *p;

+ /* lock i_ceph_lock, because ceph_d_revalidate(..., LOOKUP_RCU)
+ * may call __ceph_caps_issued_mask() on a freeing inode. */
+ spin_lock(&ci->i_ceph_lock);
p = rb_first(&ci->i_caps);
while (p) {
struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node);
p = rb_next(p);
__ceph_remove_cap(cap, true);
}
+ spin_unlock(&ci->i_ceph_lock);
}

/*
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 5b7d4881a4f8..3c7a32779574 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -536,7 +536,7 @@ void ceph_evict_inode(struct inode *inode)

ceph_fscache_unregister_inode_cookie(ci);

- __ceph_remove_caps(inode);
+ __ceph_remove_caps(ci);

if (__ceph_has_any_quota(ci))
ceph_adjust_quota_realms_count(inode, false);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 048409fba1a8..edec39aa5ce2 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1000,7 +1000,7 @@ extern void ceph_add_cap(struct inode *inode,
unsigned cap, unsigned seq, u64 realmino, int flags,
struct ceph_cap **new_cap);
extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release);
-extern void __ceph_remove_caps(struct inode* inode);
+extern void __ceph_remove_caps(struct ceph_inode_info *ci);
extern void ceph_put_cap(struct ceph_mds_client *mdsc,
struct ceph_cap *cap);
extern int ceph_is_any_caps(struct inode *inode);
diff --git a/fs/exec.c b/fs/exec.c
index 89a500bb897a..39902cc9eb6f 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1828,7 +1828,7 @@ static int __do_execve_file(int fd, struct filename *filename,
membarrier_execve(current);
rseq_execve(current);
acct_update_integrals(current);
- task_numa_free(current);
+ task_numa_free(current, false);
free_bprm(bprm);
kfree(pathbuf);
if (filename)
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index d7e4f0848e28..4d90f5bf0b0a 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -406,10 +406,10 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
clp = nfs_match_client(cl_init);
if (clp) {
spin_unlock(&nn->nfs_client_lock);
- if (IS_ERR(clp))
- return clp;
if (new)
new->rpc_ops->free_client(new);
+ if (IS_ERR(clp))
+ return clp;
return nfs_found_client(cl_init, clp);
}
if (new) {
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 03517154fe0f..e781af70d10d 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -209,12 +209,53 @@ static int proc_root_link(struct dentry *dentry, struct path *path)
return result;
}

+/*
+ * If the user used setproctitle(), we just get the string from
+ * user space at arg_start, and limit it to a maximum of one page.
+ */
+static ssize_t get_mm_proctitle(struct mm_struct *mm, char __user *buf,
+ size_t count, unsigned long pos,
+ unsigned long arg_start)
+{
+ char *page;
+ int ret, got;
+
+ if (pos >= PAGE_SIZE)
+ return 0;
+
+ page = (char *)__get_free_page(GFP_KERNEL);
+ if (!page)
+ return -ENOMEM;
+
+ ret = 0;
+ got = access_remote_vm(mm, arg_start, page, PAGE_SIZE, FOLL_ANON);
+ if (got > 0) {
+ int len = strnlen(page, got);
+
+ /* Include the NUL character if it was found */
+ if (len < got)
+ len++;
+
+ if (len > pos) {
+ len -= pos;
+ if (len > count)
+ len = count;
+ len -= copy_to_user(buf, page+pos, len);
+ if (!len)
+ len = -EFAULT;
+ ret = len;
+ }
+ }
+ free_page((unsigned long)page);
+ return ret;
+}
+
static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf,
size_t count, loff_t *ppos)
{
unsigned long arg_start, arg_end, env_start, env_end;
unsigned long pos, len;
- char *page;
+ char *page, c;

/* Check if process spawned far enough to have cmdline. */
if (!mm->env_end)
@@ -231,28 +272,42 @@ static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf,
return 0;

/*
- * We have traditionally allowed the user to re-write
- * the argument strings and overflow the end result
- * into the environment section. But only do that if
- * the environment area is contiguous to the arguments.
+ * We allow setproctitle() to overwrite the argument
+ * strings, and overflow past the original end. But
+ * only when it overflows into the environment area.
*/
- if (env_start != arg_end || env_start >= env_end)
+ if (env_start != arg_end || env_end < env_start)
env_start = env_end = arg_end;
-
- /* .. and limit it to a maximum of one page of slop */
- if (env_end >= arg_end + PAGE_SIZE)
- env_end = arg_end + PAGE_SIZE - 1;
+ len = env_end - arg_start;

/* We're not going to care if "*ppos" has high bits set */
- pos = arg_start + *ppos;
-
- /* .. but we do check the result is in the proper range */
- if (pos < arg_start || pos >= env_end)
+ pos = *ppos;
+ if (pos >= len)
return 0;
+ if (count > len - pos)
+ count = len - pos;
+ if (!count)
+ return 0;
+
+ /*
+ * Magical special case: if the argv[] end byte is not
+ * zero, the user has overwritten it with setproctitle(3).
+ *
+ * Possible future enhancement: do this only once when
+ * pos is 0, and set a flag in the 'struct file'.
+ */
+ if (access_remote_vm(mm, arg_end-1, &c, 1, FOLL_ANON) == 1 && c)
+ return get_mm_proctitle(mm, buf, count, pos, arg_start);

- /* .. and we never go past env_end */
- if (env_end - pos < count)
- count = env_end - pos;
+ /*
+ * For the non-setproctitle() case we limit things strictly
+ * to the [arg_start, arg_end[ range.
+ */
+ pos += arg_start;
+ if (pos < arg_start || pos >= arg_end)
+ return 0;
+ if (count > arg_end - pos)
+ count = arg_end - pos;

page = (char *)__get_free_page(GFP_KERNEL);
if (!page)
@@ -262,48 +317,11 @@ static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf,
while (count) {
int got;
size_t size = min_t(size_t, PAGE_SIZE, count);
- long offset;

- /*
- * Are we already starting past the official end?
- * We always include the last byte that is *supposed*
- * to be NUL
- */
- offset = (pos >= arg_end) ? pos - arg_end + 1 : 0;
-
- got = access_remote_vm(mm, pos - offset, page, size + offset, FOLL_ANON);
- if (got <= offset)
+ got = access_remote_vm(mm, pos, page, size, FOLL_ANON);
+ if (got <= 0)
break;
- got -= offset;
-
- /* Don't walk past a NUL character once you hit arg_end */
- if (pos + got >= arg_end) {
- int n = 0;
-
- /*
- * If we started before 'arg_end' but ended up
- * at or after it, we start the NUL character
- * check at arg_end-1 (where we expect the normal
- * EOF to be).
- *
- * NOTE! This is smaller than 'got', because
- * pos + got >= arg_end
- */
- if (pos < arg_end)
- n = arg_end - pos - 1;
-
- /* Cut off at first NUL after 'n' */
- got = n + strnlen(page+n, offset+got-n);
- if (got < offset)
- break;
- got -= offset;
-
- /* Include the NUL if it existed */
- if (got < size)
- got++;
- }
-
- got -= copy_to_user(buf, page+offset, got);
+ got -= copy_to_user(buf, page, got);
if (unlikely(!got)) {
if (!len)
len = -EFAULT;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 11837410690f..1157f6e245af 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1026,7 +1026,15 @@ struct task_struct {
u64 last_sum_exec_runtime;
struct callback_head numa_work;

- struct numa_group *numa_group;
+ /*
+ * This pointer is only modified for current in syscall and
+ * pagefault context (and for tasks being destroyed), so it can be read
+ * from any of the following contexts:
+ * - RCU read-side critical section
+ * - current->numa_group from everywhere
+ * - task's runqueue locked, task not running
+ */
+ struct numa_group __rcu *numa_group;

/*
* numa_faults is an array split into four regions:
diff --git a/include/linux/sched/numa_balancing.h b/include/linux/sched/numa_balancing.h
index e7dd04a84ba8..3988762efe15 100644
--- a/include/linux/sched/numa_balancing.h
+++ b/include/linux/sched/numa_balancing.h
@@ -19,7 +19,7 @@
extern void task_numa_fault(int last_node, int node, int pages, int flags);
extern pid_t task_numa_group_id(struct task_struct *p);
extern void set_numabalancing_state(bool enabled);
-extern void task_numa_free(struct task_struct *p);
+extern void task_numa_free(struct task_struct *p, bool final);
extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page,
int src_nid, int dst_cpu);
#else
@@ -34,7 +34,7 @@ static inline pid_t task_numa_group_id(struct task_struct *p)
static inline void set_numabalancing_state(bool enabled)
{
}
-static inline void task_numa_free(struct task_struct *p)
+static inline void task_numa_free(struct task_struct *p, bool final)
{
}
static inline bool should_numa_migrate_memory(struct task_struct *p,
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index cad09858a5f2..546ebee39e2a 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -1928,8 +1928,8 @@ static int btf_array_resolve(struct btf_verifier_env *env,
/* Check array->index_type */
index_type_id = array->index_type;
index_type = btf_type_by_id(btf, index_type_id);
- if (btf_type_is_resolve_source_only(index_type) ||
- btf_type_nosize_or_null(index_type)) {
+ if (btf_type_nosize_or_null(index_type) ||
+ btf_type_is_resolve_source_only(index_type)) {
btf_verifier_log_type(env, v->t, "Invalid index");
return -EINVAL;
}
@@ -1948,8 +1948,8 @@ static int btf_array_resolve(struct btf_verifier_env *env,
/* Check array->type */
elem_type_id = array->type;
elem_type = btf_type_by_id(btf, elem_type_id);
- if (btf_type_is_resolve_source_only(elem_type) ||
- btf_type_nosize_or_null(elem_type)) {
+ if (btf_type_nosize_or_null(elem_type) ||
+ btf_type_is_resolve_source_only(elem_type)) {
btf_verifier_log_type(env, v->t,
"Invalid elem");
return -EINVAL;
@@ -2170,8 +2170,8 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
const struct btf_type *member_type = btf_type_by_id(env->btf,
member_type_id);

- if (btf_type_is_resolve_source_only(member_type) ||
- btf_type_nosize_or_null(member_type)) {
+ if (btf_type_nosize_or_null(member_type) ||
+ btf_type_is_resolve_source_only(member_type)) {
btf_verifier_log_member(env, v->t, member,
"Invalid member");
return -EINVAL;
diff --git a/kernel/fork.c b/kernel/fork.c
index fe83343da24b..d3f006ed2f9d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -727,7 +727,7 @@ void __put_task_struct(struct task_struct *tsk)
WARN_ON(tsk == current);

cgroup_free(tsk);
- task_numa_free(tsk);
+ task_numa_free(tsk, true);
security_task_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f35930f5e528..9ecf1e4c624b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1067,6 +1067,21 @@ struct numa_group {
unsigned long faults[0];
};

+/*
+ * For functions that can be called in multiple contexts that permit reading
+ * ->numa_group (see struct task_struct for locking rules).
+ */
+static struct numa_group *deref_task_numa_group(struct task_struct *p)
+{
+ return rcu_dereference_check(p->numa_group, p == current ||
+ (lockdep_is_held(&task_rq(p)->lock) && !READ_ONCE(p->on_cpu)));
+}
+
+static struct numa_group *deref_curr_numa_group(struct task_struct *p)
+{
+ return rcu_dereference_protected(p->numa_group, p == current);
+}
+
static inline unsigned long group_faults_priv(struct numa_group *ng);
static inline unsigned long group_faults_shared(struct numa_group *ng);

@@ -1110,10 +1125,12 @@ static unsigned int task_scan_start(struct task_struct *p)
{
unsigned long smin = task_scan_min(p);
unsigned long period = smin;
+ struct numa_group *ng;

/* Scale the maximum scan period with the amount of shared memory. */
- if (p->numa_group) {
- struct numa_group *ng = p->numa_group;
+ rcu_read_lock();
+ ng = rcu_dereference(p->numa_group);
+ if (ng) {
unsigned long shared = group_faults_shared(ng);
unsigned long private = group_faults_priv(ng);

@@ -1121,6 +1138,7 @@ static unsigned int task_scan_start(struct task_struct *p)
period *= shared + 1;
period /= private + shared + 1;
}
+ rcu_read_unlock();

return max(smin, period);
}
@@ -1129,13 +1147,14 @@ static unsigned int task_scan_max(struct task_struct *p)
{
unsigned long smin = task_scan_min(p);
unsigned long smax;
+ struct numa_group *ng;

/* Watch for min being lower than max due to floor calculations */
smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p);

/* Scale the maximum scan period with the amount of shared memory. */
- if (p->numa_group) {
- struct numa_group *ng = p->numa_group;
+ ng = deref_curr_numa_group(p);
+ if (ng) {
unsigned long shared = group_faults_shared(ng);
unsigned long private = group_faults_priv(ng);
unsigned long period = smax;
@@ -1167,7 +1186,7 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
p->numa_scan_period = sysctl_numa_balancing_scan_delay;
p->numa_work.next = &p->numa_work;
p->numa_faults = NULL;
- p->numa_group = NULL;
+ RCU_INIT_POINTER(p->numa_group, NULL);
p->last_task_numa_placement = 0;
p->last_sum_exec_runtime = 0;

@@ -1214,7 +1233,16 @@ static void account_numa_dequeue(struct rq *rq, struct task_struct *p)

pid_t task_numa_group_id(struct task_struct *p)
{
- return p->numa_group ? p->numa_group->gid : 0;
+ struct numa_group *ng;
+ pid_t gid = 0;
+
+ rcu_read_lock();
+ ng = rcu_dereference(p->numa_group);
+ if (ng)
+ gid = ng->gid;
+ rcu_read_unlock();
+
+ return gid;
}

/*
@@ -1239,11 +1267,13 @@ static inline unsigned long task_faults(struct task_struct *p, int nid)

static inline unsigned long group_faults(struct task_struct *p, int nid)
{
- if (!p->numa_group)
+ struct numa_group *ng = deref_task_numa_group(p);
+
+ if (!ng)
return 0;

- return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] +
- p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)];
+ return ng->faults[task_faults_idx(NUMA_MEM, nid, 0)] +
+ ng->faults[task_faults_idx(NUMA_MEM, nid, 1)];
}

static inline unsigned long group_faults_cpu(struct numa_group *group, int nid)
@@ -1381,12 +1411,13 @@ static inline unsigned long task_weight(struct task_struct *p, int nid,
static inline unsigned long group_weight(struct task_struct *p, int nid,
int dist)
{
+ struct numa_group *ng = deref_task_numa_group(p);
unsigned long faults, total_faults;

- if (!p->numa_group)
+ if (!ng)
return 0;

- total_faults = p->numa_group->total_faults;
+ total_faults = ng->total_faults;

if (!total_faults)
return 0;
@@ -1400,7 +1431,7 @@ static inline unsigned long group_weight(struct task_struct *p, int nid,
bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
int src_nid, int dst_cpu)
{
- struct numa_group *ng = p->numa_group;
+ struct numa_group *ng = deref_curr_numa_group(p);
int dst_nid = cpu_to_node(dst_cpu);
int last_cpupid, this_cpupid;

@@ -1583,13 +1614,14 @@ static bool load_too_imbalanced(long src_load, long dst_load,
static void task_numa_compare(struct task_numa_env *env,
long taskimp, long groupimp, bool maymove)
{
+ struct numa_group *cur_ng, *p_ng = deref_curr_numa_group(env->p);
struct rq *dst_rq = cpu_rq(env->dst_cpu);
+ long imp = p_ng ? groupimp : taskimp;
struct task_struct *cur;
long src_load, dst_load;
- long load;
- long imp = env->p->numa_group ? groupimp : taskimp;
- long moveimp = imp;
int dist = env->dist;
+ long moveimp = imp;
+ long load;

if (READ_ONCE(dst_rq->numa_migrate_on))
return;
@@ -1628,21 +1660,22 @@ static void task_numa_compare(struct task_numa_env *env,
* If dst and source tasks are in the same NUMA group, or not
* in any group then look only at task weights.
*/
- if (cur->numa_group == env->p->numa_group) {
+ cur_ng = rcu_dereference(cur->numa_group);
+ if (cur_ng == p_ng) {
imp = taskimp + task_weight(cur, env->src_nid, dist) -
task_weight(cur, env->dst_nid, dist);
/*
* Add some hysteresis to prevent swapping the
* tasks within a group over tiny differences.
*/
- if (cur->numa_group)
+ if (cur_ng)
imp -= imp / 16;
} else {
/*
* Compare the group weights. If a task is all by itself
* (not part of a group), use the task weight instead.
*/
- if (cur->numa_group && env->p->numa_group)
+ if (cur_ng && p_ng)
imp += group_weight(cur, env->src_nid, dist) -
group_weight(cur, env->dst_nid, dist);
else
@@ -1740,11 +1773,12 @@ static int task_numa_migrate(struct task_struct *p)
.best_imp = 0,
.best_cpu = -1,
};
+ unsigned long taskweight, groupweight;
struct sched_domain *sd;
+ long taskimp, groupimp;
+ struct numa_group *ng;
struct rq *best_rq;
- unsigned long taskweight, groupweight;
int nid, ret, dist;
- long taskimp, groupimp;

/*
* Pick the lowest SD_NUMA domain, as that would have the smallest
@@ -1790,7 +1824,8 @@ static int task_numa_migrate(struct task_struct *p)
* multiple NUMA nodes; in order to better consolidate the group,
* we need to check other locations.
*/
- if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) {
+ ng = deref_curr_numa_group(p);
+ if (env.best_cpu == -1 || (ng && ng->active_nodes > 1)) {
for_each_online_node(nid) {
if (nid == env.src_nid || nid == p->numa_preferred_nid)
continue;
@@ -1823,7 +1858,7 @@ static int task_numa_migrate(struct task_struct *p)
* A task that migrated to a second choice node will be better off
* trying for a better one later. Do not set the preferred node here.
*/
- if (p->numa_group) {
+ if (ng) {
if (env.best_cpu == -1)
nid = env.src_nid;
else
@@ -2118,6 +2153,7 @@ static void task_numa_placement(struct task_struct *p)
unsigned long total_faults;
u64 runtime, period;
spinlock_t *group_lock = NULL;
+ struct numa_group *ng;

/*
* The p->mm->numa_scan_seq field gets updated without
@@ -2135,8 +2171,9 @@ static void task_numa_placement(struct task_struct *p)
runtime = numa_get_avg_runtime(p, &period);

/* If the task is part of a group prevent parallel updates to group stats */
- if (p->numa_group) {
- group_lock = &p->numa_group->lock;
+ ng = deref_curr_numa_group(p);
+ if (ng) {
+ group_lock = &ng->lock;
spin_lock_irq(group_lock);
}

@@ -2177,7 +2214,7 @@ static void task_numa_placement(struct task_struct *p)
p->numa_faults[cpu_idx] += f_diff;
faults += p->numa_faults[mem_idx];
p->total_numa_faults += diff;
- if (p->numa_group) {
+ if (ng) {
/*
* safe because we can only change our own group
*
@@ -2185,14 +2222,14 @@ static void task_numa_placement(struct task_struct *p)
* nid and priv in a specific region because it
* is at the beginning of the numa_faults array.
*/
- p->numa_group->faults[mem_idx] += diff;
- p->numa_group->faults_cpu[mem_idx] += f_diff;
- p->numa_group->total_faults += diff;
- group_faults += p->numa_group->faults[mem_idx];
+ ng->faults[mem_idx] += diff;
+ ng->faults_cpu[mem_idx] += f_diff;
+ ng->total_faults += diff;
+ group_faults += ng->faults[mem_idx];
}
}

- if (!p->numa_group) {
+ if (!ng) {
if (faults > max_faults) {
max_faults = faults;
max_nid = nid;
@@ -2203,8 +2240,8 @@ static void task_numa_placement(struct task_struct *p)
}
}

- if (p->numa_group) {
- numa_group_count_active_nodes(p->numa_group);
+ if (ng) {
+ numa_group_count_active_nodes(ng);
spin_unlock_irq(group_lock);
max_nid = preferred_group_nid(p, max_nid);
}
@@ -2238,7 +2275,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
int cpu = cpupid_to_cpu(cpupid);
int i;

- if (unlikely(!p->numa_group)) {
+ if (unlikely(!deref_curr_numa_group(p))) {
unsigned int size = sizeof(struct numa_group) +
4*nr_node_ids*sizeof(unsigned long);

@@ -2274,7 +2311,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
if (!grp)
goto no_join;

- my_grp = p->numa_group;
+ my_grp = deref_curr_numa_group(p);
if (grp == my_grp)
goto no_join;

@@ -2336,13 +2373,24 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags,
return;
}

-void task_numa_free(struct task_struct *p)
+/*
+ * Get rid of NUMA staticstics associated with a task (either current or dead).
+ * If @final is set, the task is dead and has reached refcount zero, so we can
+ * safely free all relevant data structures. Otherwise, there might be
+ * concurrent reads from places like load balancing and procfs, and we should
+ * reset the data back to default state without freeing ->numa_faults.
+ */
+void task_numa_free(struct task_struct *p, bool final)
{
- struct numa_group *grp = p->numa_group;
- void *numa_faults = p->numa_faults;
+ /* safe: p either is current or is being freed by current */
+ struct numa_group *grp = rcu_dereference_raw(p->numa_group);
+ unsigned long *numa_faults = p->numa_faults;
unsigned long flags;
int i;

+ if (!numa_faults)
+ return;
+
if (grp) {
spin_lock_irqsave(&grp->lock, flags);
for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
@@ -2355,8 +2403,14 @@ void task_numa_free(struct task_struct *p)
put_numa_group(grp);
}

- p->numa_faults = NULL;
- kfree(numa_faults);
+ if (final) {
+ p->numa_faults = NULL;
+ kfree(numa_faults);
+ } else {
+ p->total_numa_faults = 0;
+ for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
+ numa_faults[i] = 0;
+ }
}

/*
@@ -2409,7 +2463,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
* actively using should be counted as local. This allows the
* scan rate to slow down when a workload has settled down.
*/
- ng = p->numa_group;
+ ng = deref_curr_numa_group(p);
if (!priv && !local && ng && ng->active_nodes > 1 &&
numa_is_active_node(cpu_node, ng) &&
numa_is_active_node(mem_node, ng))
@@ -10708,18 +10762,22 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m)
{
int node;
unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0;
+ struct numa_group *ng;

+ rcu_read_lock();
+ ng = rcu_dereference(p->numa_group);
for_each_online_node(node) {
if (p->numa_faults) {
tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)];
tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)];
}
- if (p->numa_group) {
- gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)],
- gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)];
+ if (ng) {
+ gsf = ng->faults[task_faults_idx(NUMA_MEM, node, 0)],
+ gpf = ng->faults[task_faults_idx(NUMA_MEM, node, 1)];
}
print_numa_stats(m, node, tsf, tpf, gsf, gpf);
}
+ rcu_read_unlock();
}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_SCHED_DEBUG */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 169112f8aa1e..ab47bf3ab66e 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -274,7 +274,8 @@ EXPORT_SYMBOL_GPL(vsock_insert_connected);
void vsock_remove_bound(struct vsock_sock *vsk)
{
spin_lock_bh(&vsock_table_lock);
- __vsock_remove_bound(vsk);
+ if (__vsock_in_bound_table(vsk))
+ __vsock_remove_bound(vsk);
spin_unlock_bh(&vsock_table_lock);
}
EXPORT_SYMBOL_GPL(vsock_remove_bound);
@@ -282,7 +283,8 @@ EXPORT_SYMBOL_GPL(vsock_remove_bound);
void vsock_remove_connected(struct vsock_sock *vsk)
{
spin_lock_bh(&vsock_table_lock);
- __vsock_remove_connected(vsk);
+ if (__vsock_in_connected_table(vsk))
+ __vsock_remove_connected(vsk);
spin_unlock_bh(&vsock_table_lock);
}
EXPORT_SYMBOL_GPL(vsock_remove_connected);
@@ -318,35 +320,10 @@ struct sock *vsock_find_connected_socket(struct sockaddr_vm *src,
}
EXPORT_SYMBOL_GPL(vsock_find_connected_socket);

-static bool vsock_in_bound_table(struct vsock_sock *vsk)
-{
- bool ret;
-
- spin_lock_bh(&vsock_table_lock);
- ret = __vsock_in_bound_table(vsk);
- spin_unlock_bh(&vsock_table_lock);
-
- return ret;
-}
-
-static bool vsock_in_connected_table(struct vsock_sock *vsk)
-{
- bool ret;
-
- spin_lock_bh(&vsock_table_lock);
- ret = __vsock_in_connected_table(vsk);
- spin_unlock_bh(&vsock_table_lock);
-
- return ret;
-}
-
void vsock_remove_sock(struct vsock_sock *vsk)
{
- if (vsock_in_bound_table(vsk))
- vsock_remove_bound(vsk);
-
- if (vsock_in_connected_table(vsk))
- vsock_remove_connected(vsk);
+ vsock_remove_bound(vsk);
+ vsock_remove_connected(vsk);
}
EXPORT_SYMBOL_GPL(vsock_remove_sock);

@@ -477,8 +454,7 @@ static void vsock_pending_work(struct work_struct *work)
* incoming packets can't find this socket, and to reduce the reference
* count.
*/
- if (vsock_in_connected_table(vsk))
- vsock_remove_connected(vsk);
+ vsock_remove_connected(vsk);

sk->sk_state = TCP_CLOSE;

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index b1694d5d15d3..82be7780bbe8 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1280,13 +1280,17 @@ static void xfrm_hash_rebuild(struct work_struct *work)

hlist_for_each_entry_safe(policy, n,
&net->xfrm.policy_inexact[dir],
- bydst_inexact_list)
+ bydst_inexact_list) {
+ hlist_del_rcu(&policy->bydst);
hlist_del_init(&policy->bydst_inexact_list);
+ }

hmask = net->xfrm.policy_bydst[dir].hmask;
odst = net->xfrm.policy_bydst[dir].table;
- for (i = hmask; i >= 0; i--)
- INIT_HLIST_HEAD(odst + i);
+ for (i = hmask; i >= 0; i--) {
+ hlist_for_each_entry_safe(policy, n, odst + i, bydst)
+ hlist_del_rcu(&policy->bydst);
+ }
if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
/* dir out => dst = remote, src = local */
net->xfrm.policy_bydst[dir].dbits4 = rbits4;
@@ -1315,8 +1319,6 @@ static void xfrm_hash_rebuild(struct work_struct *work)
chain = policy_hash_bysel(net, &policy->selector,
policy->family, dir);

- hlist_del_rcu(&policy->bydst);
-
if (!chain) {
void *p = xfrm_policy_inexact_insert(policy, dir, 0);

diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh
index 71d7fdc513c1..5445943bf07f 100755
--- a/tools/testing/selftests/net/xfrm_policy.sh
+++ b/tools/testing/selftests/net/xfrm_policy.sh
@@ -257,6 +257,29 @@ check_exceptions()
return $lret
}

+check_hthresh_repeat()
+{
+ local log=$1
+ i=0
+
+ for i in $(seq 1 10);do
+ ip -net ns1 xfrm policy update src e000:0001::0000 dst ff01::0014:0000:0001 dir in tmpl src :: dst :: proto esp mode tunnel priority 100 action allow || break
+ ip -net ns1 xfrm policy set hthresh6 0 28 || break
+
+ ip -net ns1 xfrm policy update src e000:0001::0000 dst ff01::01 dir in tmpl src :: dst :: proto esp mode tunnel priority 100 action allow || break
+ ip -net ns1 xfrm policy set hthresh6 0 28 || break
+ done
+
+ if [ $i -ne 10 ] ;then
+ echo "FAIL: $log" 1>&2
+ ret=1
+ return 1
+ fi
+
+ echo "PASS: $log"
+ return 0
+}
+
#check for needed privileges
if [ "$(id -u)" -ne 0 ];then
echo "SKIP: Need root privileges"
@@ -404,7 +427,9 @@ for n in ns3 ns4;do
ip -net $n xfrm policy set hthresh4 32 32 hthresh6 128 128
sleep $((RANDOM%5))
done
-check_exceptions "exceptions and block policies after hresh change to normal"
+check_exceptions "exceptions and block policies after htresh change to normal"
+
+check_hthresh_repeat "policies with repeated htresh change"

for i in 1 2 3 4;do ip netns del ns$i;done