5.4.171-rc1 review

From: Di Zhu <[email protected]>

commit 3116f59c12bd24c513194cd3acb3ec1f7d468954 upstream.

Using ifconfig command to delete the ipv6 address will cause the i40e network card driver to delete its internal mac_filter and i40e_service_task kernel thread will concurrently access the mac_filter. These two processes are not protected by lock
so causing the following use-after-free problems.

 print_address_description+0x70/0x360
 ? vprintk_func+0x5e/0xf0
 kasan_report+0x1b2/0x330
 i40e_sync_vsi_filters+0x4f0/0x1850 [i40e]
 i40e_sync_filters_subtask+0xe3/0x130 [i40e]
 i40e_service_task+0x195/0x24c0 [i40e]
 process_one_work+0x3f5/0x7d0
 worker_thread+0x61/0x6c0
 ? process_one_work+0x7d0/0x7d0
 kthread+0x1c3/0x1f0
 ? kthread_park+0xc0/0xc0
 ret_from_fork+0x35/0x40

Allocated by task 2279810:
 kasan_kmalloc+0xa0/0xd0
 kmem_cache_alloc_trace+0xf3/0x1e0
 i40e_add_filter+0x127/0x2b0 [i40e]
 i40e_add_mac_filter+0x156/0x190 [i40e]
 i40e_addr_sync+0x2d/0x40 [i40e]
 __hw_addr_sync_dev+0x154/0x210
 i40e_set_rx_mode+0x6d/0xf0 [i40e]
 __dev_set_rx_mode+0xfb/0x1f0
 __dev_mc_add+0x6c/0x90
 igmp6_group_added+0x214/0x230
 __ipv6_dev_mc_inc+0x338/0x4f0
 addrconf_join_solict.part.7+0xa2/0xd0
 addrconf_dad_work+0x500/0x980
 process_one_work+0x3f5/0x7d0
 worker_thread+0x61/0x6c0
 kthread+0x1c3/0x1f0
 ret_from_fork+0x35/0x40

Freed by task 2547073:
 __kasan_slab_free+0x130/0x180
 kfree+0x90/0x1b0
 __i40e_del_filter+0xa3/0xf0 [i40e]
 i40e_del_mac_filter+0xf3/0x130 [i40e]
 i40e_addr_unsync+0x85/0xa0 [i40e]
 __hw_addr_sync_dev+0x9d/0x210
 i40e_set_rx_mode+0x6d/0xf0 [i40e]
 __dev_set_rx_mode+0xfb/0x1f0
 __dev_mc_del+0x69/0x80
 igmp6_group_dropped+0x279/0x510
 __ipv6_dev_mc_dec+0x174/0x220
 addrconf_leave_solict.part.8+0xa2/0xd0
 __ipv6_ifa_notify+0x4cd/0x570
 ipv6_ifa_notify+0x58/0x80
 ipv6_del_addr+0x259/0x4a0
 inet6_addr_del+0x188/0x260
 addrconf_del_ifaddr+0xcc/0x130
 inet6_ioctl+0x152/0x190
 sock_do_ioctl+0xd8/0x2b0
 sock_ioctl+0x2e5/0x4c0
 do_vfs_ioctl+0x14e/0xa80
 ksys_ioctl+0x7c/0xa0
 __x64_sys_ioctl+0x42/0x50
 do_syscall_64+0x98/0x2c0
 entry_SYSCALL_64_after_hwframe+0x65/0xca

---
 drivers/net/ethernet/intel/i40e/i40e_main.c |   24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

@@ -107,6 +107,24 @@ MODULE_VERSION(DRV_VERSION);
 
 static struct workqueue_struct *i40e_wq;
 
+static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f,
+				  struct net_device *netdev, int delta)
+{
+	struct netdev_hw_addr *ha;
+
+	if (!f || !netdev)
+		return;
+
+	netdev_for_each_mc_addr(ha, netdev) {
+		if (ether_addr_equal(ha->addr, f->macaddr)) {
+			ha->refcount += delta;
+			if (ha->refcount <= 0)
+				ha->refcount = 1;
+			break;
+		}
+	}
+}
+
 /**
  * i40e_allocate_dma_mem_d - OS specific memory alloc for shared code
  * @hw:   pointer to the HW structure

@@ -2022,6 +2040,7 @@ static void i40e_undo_add_filter_entries
 	hlist_for_each_entry_safe(new, h, from, hlist) {
 		/* We can simply free the wrapper structure */
 		hlist_del(&new->hlist);
+		netdev_hw_addr_refcnt(new->f, vsi->netdev, -1);
 		kfree(new);
 	}
 }

@@ -2369,6 +2388,10 @@ int i40e_sync_vsi_filters(struct i40e_vs
 						       &tmp_add_list,
 						       &tmp_del_list,
 						       vlan_filters);
+
+		hlist_for_each_entry(new, &tmp_add_list, hlist)
+			netdev_hw_addr_refcnt(new->f, vsi->netdev, 1);
+
 		if (retval)
 			goto err_no_memory_locked;
 

@@ -2501,6 +2524,7 @@ int i40e_sync_vsi_filters(struct i40e_vs
 			if (new->f->state == I40E_FILTER_NEW)
 				new->f->state = new->state;
 			hlist_del(&new->hlist);
+			netdev_hw_addr_refcnt(new->f, vsi->netdev, -1);
 			kfree(new);
 		}
 		spin_unlock_bh(&vsi->mac_filter_hash_lock);

From: Naveen N. Rao <[email protected]>

commit 823e670f7ed616d0ce993075c8afe0217885f79d upstream.

With the new osnoise tracer, we are seeing the below splat:

    Kernel attempted to read user page (c7d880000) - exploit attempt? (uid: 0)
    BUG: Unable to handle kernel data access on read at 0xc7d880000
    Faulting instruction address: 0xc0000000002ffa10
    Oops: Kernel access of bad area, sig: 11 [#1]
    LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries
    ...
    NIP [c0000000002ffa10] __trace_array_vprintk.part.0+0x70/0x2f0
    LR [c0000000002ff9fc] __trace_array_vprintk.part.0+0x5c/0x2f0
    Call Trace:
    [c0000008bdd73b80] [c0000000001c49cc] put_prev_task_fair+0x3c/0x60 (unreliable)
    [c0000008bdd73be0] [c000000000301430] trace_array_printk_buf+0x70/0x90
    [c0000008bdd73c00] [c0000000003178b0] trace_sched_switch_callback+0x250/0x290
    [c0000008bdd73c90] [c000000000e70d60] __schedule+0x410/0x710
    [c0000008bdd73d40] [c000000000e710c0] schedule+0x60/0x130
    [c0000008bdd73d70] [c000000000030614] interrupt_exit_user_prepare_main+0x264/0x270
    [c0000008bdd73de0] [c000000000030a70] syscall_exit_prepare+0x150/0x180
    [c0000008bdd73e10] [c00000000000c174] system_call_vectored_common+0xf4/0x278

osnoise tracer on ppc64le is triggering osnoise_taint() for negative duration in get_int_safe_duration() called from trace_sched_switch_callback()->thread_exit().

The problem though is that the check for a valid trace_percpu_buffer is incorrect in get_trace_buf(). The check is being done after calculating the pointer for the current cpu, rather than on the main percpu pointer. Fix the check to be against trace_percpu_buffer.

---
 kernel/trace/trace.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -3017,7 +3017,7 @@ static char *get_trace_buf(void)
 {
 	struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer);
 
-	if (!buffer || buffer->nesting >= 4)
+	if (!trace_percpu_buffer || buffer->nesting >= 4)
 		return NULL;
 
 	buffer->nesting++;

From: Nathan Chancellor <[email protected]>

Upstream commit a02dcde595f7 ("Input: touchscreen - avoid bitwise vs logical OR warning") was applied as commit f6e9e7be9b80 ("Input:
touchscreen - avoid bitwise vs logical OR warning") in linux-5.4.y but it did not properly account for commit d9265e8a878a ("Input:
of_touchscreen - add support for touchscreen-min-x|y"), which means the warning mentioned in the commit message is not fully fixed:

drivers/input/touchscreen/of_touchscreen.c:78:17: warning: use of bitwise '|' with boolean operands [-Wbitwise-instead-of-logical]
data_present = touchscreen_get_prop_u32(dev, "touchscreen-min-x",
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/input/touchscreen/of_touchscreen.c:78:17: note: cast one or both operands to int to silence this warning drivers/input/touchscreen/of_touchscreen.c:92:17: warning: use of bitwise '|' with boolean operands [-Wbitwise-instead-of-logical]
data_present = touchscreen_get_prop_u32(dev, "touchscreen-min-y",
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/input/touchscreen/of_touchscreen.c:92:17: note: cast one or both operands to int to silence this warning 2 warnings generated.

It seems like the 4.19 backport was applied to the 5.4 tree, which did not have any conflicts so no issue was noticed at that point.

Fix up the backport to bring it more in line with the upstream version so that there is no warning.

---
 drivers/input/touchscreen/of_touchscreen.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -77,8 +77,8 @@ void touchscreen_parse_properties(struct
 	axis = multitouch ? ABS_MT_POSITION_X : ABS_X;
 	data_present = touchscreen_get_prop_u32(dev, "touchscreen-min-x",
 						input_abs_get_min(input, axis),
-						&minimum) |
-		       touchscreen_get_prop_u32(dev, "touchscreen-size-x",
+						&minimum);
+	data_present |= touchscreen_get_prop_u32(dev, "touchscreen-size-x",
 						input_abs_get_max(input,
 								  axis) + 1,
 						&maximum);

@@ -91,8 +91,8 @@ void touchscreen_parse_properties(struct
 	axis = multitouch ? ABS_MT_POSITION_Y : ABS_Y;
 	data_present = touchscreen_get_prop_u32(dev, "touchscreen-min-y",
 						input_abs_get_min(input, axis),
-						&minimum) |
-		       touchscreen_get_prop_u32(dev, "touchscreen-size-y",
+						&minimum);
+	data_present |= touchscreen_get_prop_u32(dev, "touchscreen-size-y",
 						input_abs_get_max(input,
 								  axis) + 1,
 						&maximum);

From: Shuah Khan <[email protected]>

commit dd40f44eabe1e122c6852fabb298aac05b083fce upstream.

Fix the following [-Wstringop-overread] by passing in the variable instead of the value.

test_vsyscall.c: In function ‘test_process_vm_readv’:
test_vsyscall.c:500:22: warning: ‘__builtin_memcmp_eq’ specified bound 4096 exceeds source size 0 [-Wstringop-overread]

  500 |                 if (!memcmp(buf, (const void *)0xffffffffff600000, 4096)) {
      |                      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

---
 tools/testing/selftests/x86/test_vsyscall.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -480,7 +480,7 @@ static int test_process_vm_readv(void)
 	}
 
 	if (vsyscall_map_r) {
-		if (!memcmp(buf, (const void *)0xffffffffff600000, 4096)) {
+		if (!memcmp(buf, remote.iov_base, sizeof(buf))) {
 			printf("[OK]\tIt worked and read correct data\n");
 		} else {
 			printf("[FAIL]\tIt worked but returned incorrect data\n");

From: Jiasheng Jiang <[email protected]>

commit 7694a7de22c53a312ea98960fcafc6ec62046531 upstream.

Because of the possible failure of the allocation, data might be NULL pointer and will cause the dereference of the NULL pointer later. Therefore, it might be better to check it and return -ENOMEM.

---
 drivers/infiniband/core/uverbs_uapi.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -450,6 +450,9 @@ static int uapi_finalize(struct uverbs_a
 	uapi->num_write_ex = max_write_ex + 1;
 	data = kmalloc_array(uapi->num_write + uapi->num_write_ex,
 			     sizeof(*uapi->write_methods), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
 	for (i = 0; i != uapi->num_write + uapi->num_write_ex; i++)
 		data[i] = &uapi->notsupp_method;
 	uapi->write_methods = data;

From: Mateusz Palczewski <[email protected]>

commit 40feded8a247f95957a0de9abd100085fb320a2f upstream.

When loading the i40e driver, it prints a message like: 'The driver for the device detected a newer version of the NVM image v1.x than expected v1.y. Please install the most recent version of the network driver.' This is misleading as the driver is working as expected.

Fix that by removing the second part of message and changing it from dev_info to dev_dbg.

---
 drivers/net/ethernet/intel/i40e/i40e_main.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -15036,8 +15036,8 @@ static int i40e_probe(struct pci_dev *pd
 
 	if (hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
 	    hw->aq.api_min_ver > I40E_FW_MINOR_VERSION(hw))
-		dev_info(&pdev->dev,
-			 "The driver for the device detected a newer version of the NVM image v%u.%u than expected v%u.%u. Please install the most recent version of the network driver.\n",
+		dev_dbg(&pdev->dev,
+			"The driver for the device detected a newer version of the NVM image v%u.%u than v%u.%u.\n",
 			 hw->aq.api_maj_ver,
 			 hw->aq.api_min_ver,
 			 I40E_FW_API_VERSION_MAJOR,

From: David Ahern <[email protected]>

commit 664b9c4b7392ce723b013201843264bf95481ce5 upstream.

Make sure RTA_FLOW is at least 4B before using.

---
 net/ipv4/fib_semantics.c |   17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

@@ -723,8 +723,13 @@ static int fib_get_nhs(struct fib_info *
 			}
 
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
-			if (nla)
+			if (nla) {
+				if (nla_len(nla) < sizeof(u32)) {
+					NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW");
+					return -EINVAL;
+				}
 				fib_cfg.fc_flow = nla_get_u32(nla);
+			}
 
 			fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
 			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);

@@ -955,8 +960,14 @@ int fib_nh_match(struct fib_config *cfg,
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
-			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
-				return 1;
+			if (nla) {
+				if (nla_len(nla) < sizeof(u32)) {
+					NL_SET_ERR_MSG(extack, "Invalid RTA_FLOW");
+					return -EINVAL;
+				}
+				if (nla_get_u32(nla) != nh->nh_tclassid)
+					return 1;
+			}
 #endif
 		}
 

From: David Ahern <[email protected]>

[ Upstream commit e30a845b0376eb51c9c94f56bbd53b2e08ba822f ]

ip6_route_multipath_del loop continues processing the multipath attribute even if delete of a nexthop path fails. For consistency, do the same if the gateway attribute is invalid.

---
 net/ipv6/route.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

index 53861f9c8ce0a..56f0783df5896 100644
@@ -5313,8 +5313,10 @@ static int ip6_route_multipath_del(struct fib6_config *cfg,
 			if (nla) {
 				err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
 							extack);
-				if (err)
-					return err;
+				if (err) {
+					last_err = err;
+					goto next_rtnh;
+				}
 
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}

@@ -5323,6 +5325,7 @@ static int ip6_route_multipath_del(struct fib6_config *cfg,
 		if (err)
 			last_err = err;
 
+next_rtnh:
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 

2.34.1

This is the start of the stable review cycle for the 5.4.171 release. There are 34 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, 12 Jan 2022 07:18:05 +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/v5.x/stable-review/patch-5.4.171-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-5.4.y
and the diffstat can be found below.

thanks,

greg k-h

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

Greg Kroah-Hartman <[email protected]>

    Linux 5.4.171-rc1

wolfgang huang <[email protected]>
mISDN: change function names to avoid conflicts

Zekun Shen <[email protected]>
atlantic: Fix buff_ring OOB in aq_ring_rx_clean

yangxingwu <[email protected]>
net: udp: fix alignment problem in udp4_seq_show()

William Zhao <[email protected]>
ip6_vti: initialize __ip6_tnl_parm struct in vti6_siocdevprivate

Lixiaokeng <[email protected]>
scsi: libiscsi: Fix UAF in iscsi_conn_get_param()/iscsi_conn_teardown()

Chunfeng Yun <[email protected]>
usb: mtu3: fix interval value for intr and isoc

David Ahern <[email protected]>
ipv6: Do cleanup if attribute validation fails in multipath route

David Ahern <[email protected]>
ipv6: Continue processing multipath route even if gateway attribute is invalid

Hangyu Hua <[email protected]>
phonet: refcount leak in pep_sock_accep

Thomas Toye <[email protected]>
rndis_host: support Hytera digital radios

Nathan Chancellor <[email protected]>
power: reset: ltc2952: Fix use of floating point literals

Linus Walleij <[email protected]>
power: supply: core: Break capacity loop

Darrick J. Wong <[email protected]>
xfs: map unwritten blocks in XFS_IOC_{ALLOC,FREE}SP just like fallocate

Christian Melki <[email protected]>
net: phy: micrel: set soft_reset callback to genphy_soft_reset for KSZ8081

Eric Dumazet <[email protected]>
sch_qfq: prevent shift-out-of-bounds in qfq_init_qdisc

Linus Lüssing <[email protected]>
batman-adv: mcast: don't send link-local multicast to mcast routers

David Ahern <[email protected]>
lwtunnel: Validate RTA_ENCAP_TYPE attribute length

David Ahern <[email protected]>
ipv6: Check attribute length for RTA_GATEWAY when deleting multipath route

David Ahern <[email protected]>
ipv6: Check attribute length for RTA_GATEWAY in multipath route

David Ahern <[email protected]>
ipv4: Check attribute length for RTA_FLOW in multipath route

David Ahern <[email protected]>
ipv4: Check attribute length for RTA_GATEWAY in multipath route

Jedrzej Jagielski <[email protected]>
i40e: Fix incorrect netdev's real number of RX/TX queues

Mateusz Palczewski <[email protected]>
i40e: Fix for displaying message regarding NVM version

Di Zhu <[email protected]>
i40e: fix use-after-free in i40e_sync_filters_subtask()

Tom Rix <[email protected]>
mac80211: initialize variable have_higher_than_11mbit

Jiasheng Jiang <[email protected]>
RDMA/uverbs: Check for null return of kmalloc_array

Leon Romanovsky <[email protected]>
RDMA/core: Don't infoleak GRH fields

Karen Sornek <[email protected]>
iavf: Fix limit of total number of queues to active queues of VF

Pavel Skripkin <[email protected]>
ieee802154: atusb: fix uninit value in atusb_set_extended_addr

Naveen N. Rao <[email protected]>
tracing: Tag trace_percpu_buffer as a percpu pointer

Naveen N. Rao <[email protected]>
tracing: Fix check for trace_percpu_buffer validity in get_trace_buf()

Shuah Khan <[email protected]>
selftests: x86: fix [-Wstringop-overread] warn in test_process_vm_readv()

Nathan Chancellor <[email protected]>

    Input: touchscreen - Fix backport of a02dcde595f7cbd240ccd64de96034ad91cffc40

Chao Yu <[email protected]>
f2fs: quota: fix potential deadlock

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

Diffstat:

 Makefile                                         |  4 +-
 drivers/infiniband/core/uverbs_marshall.c        |  2 +-
 drivers/infiniband/core/uverbs_uapi.c            |  3 ++
 drivers/input/touchscreen/of_touchscreen.c       |  8 ++--
 drivers/isdn/mISDN/core.c                        |  6 +--
 drivers/isdn/mISDN/core.h                        |  4 +-
 drivers/isdn/mISDN/layer1.c                      |  4 +-
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c |  8 ++++
 drivers/net/ethernet/intel/i40e/i40e_main.c      | 60 ++++++++++++++++++++----
 drivers/net/ethernet/intel/iavf/iavf_main.c      |  5 +-
 drivers/net/ieee802154/atusb.c                   | 10 ++--
 drivers/net/phy/micrel.c                         |  1 +
 drivers/net/usb/rndis_host.c                     |  5 ++
 drivers/power/reset/ltc2952-poweroff.c           |  4 +-
 drivers/power/supply/power_supply_core.c         |  4 ++
 drivers/scsi/libiscsi.c                          |  6 ++-
 drivers/usb/mtu3/mtu3_gadget.c                   |  4 +-
 fs/f2fs/checkpoint.c                             |  3 +-
 fs/xfs/xfs_ioctl.c                               |  3 +-
 kernel/trace/trace.c                             |  6 +--
 net/batman-adv/multicast.c                       | 15 ++++--
 net/batman-adv/multicast.h                       | 10 ++--
 net/batman-adv/soft-interface.c                  |  7 ++-
 net/core/lwtunnel.c                              |  4 ++
 net/ipv4/fib_semantics.c                         | 49 ++++++++++++++++---
 net/ipv4/udp.c                                   |  2 +-
 net/ipv6/ip6_vti.c                               |  2 +
 net/ipv6/route.c                                 | 32 ++++++++++++-
 net/mac80211/mlme.c                              |  2 +-
 net/phonet/pep.c                                 |  1 +
 net/sched/sch_qfq.c                              |  6 +--
 tools/testing/selftests/x86/test_vsyscall.c      |  2 +-
 32 files changed, 217 insertions(+), 65 deletions(-)

From: David Ahern <[email protected]>

[ Upstream commit 95bdba23b5b4aa75fe3e6c84335e638641c707bb ]

As Nicolas noted, if gateway validation fails walking the multipath attribute the code should jump to the cleanup to free previously allocated memory.

---
 net/ipv6/route.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

index 56f0783df5896..5ef6e27e026e9 100644
@@ -5146,12 +5146,10 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla) {
-				int ret;
-
-				ret = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
+				err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
 							extack);
-				if (ret)
-					return ret;
+				if (err)
+					goto cleanup;
 
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}

2.34.1

From: William Zhao <[email protected]>

[ Upstream commit c1833c3964d5bd8c163bd4e01736a38bc473cb8a ]

The "__ip6_tnl_parm" struct was left uninitialized causing an invalid load of random data when the "__ip6_tnl_parm" struct was used elsewhere. As an example, in the function "ip6_tnl_xmit_ctl()", it tries to access the "collect_md" member. With "__ip6_tnl_parm" being uninitialized and containing random data, the UBSAN detected that "collect_md" held a non-boolean value.

The UBSAN issue is as follows:
===============================================================

UBSAN: invalid-load in net/ipv6/ip6_tunnel.c:1025:14
load of value 30 is not a valid value for type '_Bool'
CPU: 1 PID: 228 Comm: kworker/1:3 Not tainted 5.16.0-rc4+ #8
Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
Workqueue: ipv6_addrconf addrconf_dad_work
Call Trace:
<TASK>
dump_stack_lvl+0x44/0x57
ubsan_epilogue+0x5/0x40
__ubsan_handle_load_invalid_value+0x66/0x70
? __cpuhp_setup_state+0x1d3/0x210
ip6_tnl_xmit_ctl.cold.52+0x2c/0x6f [ip6_tunnel]
vti6_tnl_xmit+0x79c/0x1e96 [ip6_vti]
? lock_is_held_type+0xd9/0x130
? vti6_rcv+0x100/0x100 [ip6_vti]
? lock_is_held_type+0xd9/0x130
? rcu_read_lock_bh_held+0xc0/0xc0
? lock_acquired+0x262/0xb10
dev_hard_start_xmit+0x1e6/0x820
__dev_queue_xmit+0x2079/0x3340
? mark_lock.part.52+0xf7/0x1050
? netdev_core_pick_tx+0x290/0x290
? kvm_clock_read+0x14/0x30
? kvm_sched_clock_read+0x5/0x10
? sched_clock_cpu+0x15/0x200
? find_held_lock+0x3a/0x1c0
? lock_release+0x42f/0xc90
? lock_downgrade+0x6b0/0x6b0
? mark_held_locks+0xb7/0x120
? neigh_connected_output+0x31f/0x470
? lockdep_hardirqs_on+0x79/0x100
? neigh_connected_output+0x31f/0x470
? ip6_finish_output2+0x9b0/0x1d90
? rcu_read_lock_bh_held+0x62/0xc0
? ip6_finish_output2+0x9b0/0x1d90
ip6_finish_output2+0x9b0/0x1d90
? ip6_append_data+0x330/0x330
? ip6_mtu+0x166/0x370
? __ip6_finish_output+0x1ad/0xfb0
? nf_hook_slow+0xa6/0x170
ip6_output+0x1fb/0x710
? nf_hook.constprop.32+0x317/0x430
? ip6_finish_output+0x180/0x180
? __ip6_finish_output+0xfb0/0xfb0
? lock_is_held_type+0xd9/0x130
ndisc_send_skb+0xb33/0x1590
? __sk_mem_raise_allocated+0x11cf/0x1560
? dst_output+0x4a0/0x4a0
? ndisc_send_rs+0x432/0x610
addrconf_dad_completed+0x30c/0xbb0
? addrconf_rs_timer+0x650/0x650
? addrconf_dad_work+0x73c/0x10e0
addrconf_dad_work+0x73c/0x10e0
? addrconf_dad_completed+0xbb0/0xbb0
? rcu_read_lock_sched_held+0xaf/0xe0
? rcu_read_lock_bh_held+0xc0/0xc0
process_one_work+0x97b/0x1740
? pwq_dec_nr_in_flight+0x270/0x270
worker_thread+0x87/0xbf0
? process_one_work+0x1740/0x1740
kthread+0x3ac/0x490
? set_kthread_struct+0x100/0x100
ret_from_fork+0x22/0x30
</TASK>
===============================================================

The solution is to initialize "__ip6_tnl_parm" struct to zeros in the "vti6_siocdevprivate()" function.

---
 net/ipv6/ip6_vti.c | 2 ++
 1 file changed, 2 insertions(+)

index 12ab6605d9617..8b44d3b53844e 100644
@@ -795,6 +795,8 @@ vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	struct net *net = dev_net(dev);
 	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
 
+	memset(&p1, 0, sizeof(p1));
+
 	switch (cmd) {
 	case SIOCGETTUNNEL:
 		if (dev == ip6n->fb_tnl_dev) {

2.34.1

From: Lixiaokeng <[email protected]>

[ Upstream commit 1b8d0300a3e9f216ae4901bab886db7299899ec6 ]

|- iscsi_if_destroy_conn            |-dev_attr_show
 |-iscsi_conn_teardown
  |-spin_lock_bh                     |-iscsi_sw_tcp_conn_get_param

  |-kfree(conn->persistent_address)   |-iscsi_conn_get_param
  |-kfree(conn->local_ipaddr)
                                       ==>|-read persistent_address
                                       ==>|-read local_ipaddr
  |-spin_unlock_bh

When iscsi_conn_teardown() and iscsi_conn_get_param() happen in parallel, a UAF may be triggered.

---
 drivers/scsi/libiscsi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index eeba6180711cd..f3cee64c6d12f 100644
@@ -2948,6 +2948,8 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn)
 {
 	struct iscsi_conn *conn = cls_conn->dd_data;
 	struct iscsi_session *session = conn->session;
+	char *tmp_persistent_address = conn->persistent_address;
+	char *tmp_local_ipaddr = conn->local_ipaddr;
 
 	del_timer_sync(&conn->transport_timer);
 

@@ -2969,8 +2971,6 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn)
 	spin_lock_bh(&session->frwd_lock);
 	free_pages((unsigned long) conn->data,
 		   get_order(ISCSI_DEF_MAX_RECV_SEG_LEN));
-	kfree(conn->persistent_address);
-	kfree(conn->local_ipaddr);
 	/* regular RX path uses back_lock */
 	spin_lock_bh(&session->back_lock);
 	kfifo_in(&session->cmdpool.queue, (void*)&conn->login_task,

@@ -2982,6 +2982,8 @@ void iscsi_conn_teardown(struct iscsi_cls_conn *cls_conn)
 	mutex_unlock(&session->eh_mutex);
 
 	iscsi_destroy_conn(cls_conn);
+	kfree(tmp_persistent_address);
+	kfree(tmp_local_ipaddr);
 }
 EXPORT_SYMBOL_GPL(iscsi_conn_teardown);
 

2.34.1

From: Zekun Shen <[email protected]>

[ Upstream commit 5f50153288452e10b6edd69ec9112c49442b054a ]

The function obtain the next buffer without boundary check. We should return with I/O error code.

The bug is found by fuzzing and the crash report is attached. It is an OOB bug although reported as use-after-free.

[    4.804724] BUG: KASAN: use-after-free in aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.805661] Read of size 4 at addr ffff888034fe93a8 by task ksoftirqd/0/9
[    4.806505]
[    4.806703] CPU: 0 PID: 9 Comm: ksoftirqd/0 Tainted: G        W         5.6.0 #34
[    4.809030] Call Trace:
[    4.809343]  dump_stack+0x76/0xa0
[    4.809755]  print_address_description.constprop.0+0x16/0x200
[    4.810455]  ? aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.811234]  ? aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.813183]  __kasan_report.cold+0x37/0x7c
[    4.813715]  ? aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.814393]  kasan_report+0xe/0x20
[    4.814837]  aq_ring_rx_clean+0x1e88/0x2730 [atlantic]
[    4.815499]  ? hw_atl_b0_hw_ring_rx_receive+0x9a5/0xb90 [atlantic]
[    4.816290]  aq_vec_poll+0x179/0x5d0 [atlantic]
[    4.816870]  ? _GLOBAL__sub_I_65535_1_aq_pci_func_init+0x20/0x20 [atlantic]
[    4.817746]  ? __next_timer_interrupt+0xba/0xf0
[    4.818322]  net_rx_action+0x363/0xbd0
[    4.818803]  ? call_timer_fn+0x240/0x240
[    4.819302]  ? __switch_to_asm+0x40/0x70
[    4.819809]  ? napi_busy_loop+0x520/0x520
[    4.820324]  __do_softirq+0x18c/0x634
[    4.820797]  ? takeover_tasklets+0x5f0/0x5f0
[    4.821343]  run_ksoftirqd+0x15/0x20
[    4.821804]  smpboot_thread_fn+0x2f1/0x6b0
[    4.822331]  ? smpboot_unregister_percpu_thread+0x160/0x160
[    4.823041]  ? __kthread_parkme+0x80/0x100
[    4.823571]  ? smpboot_unregister_percpu_thread+0x160/0x160
[    4.824301]  kthread+0x2b5/0x3b0
[    4.824723]  ? kthread_create_on_node+0xd0/0xd0
[    4.825304]  ret_from_fork+0x35/0x40

---
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 8 ++++++++
 1 file changed, 8 insertions(+)

index 03821b46a8cb4..4c22f119ac62f 100644
@@ -305,6 +305,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 		if (!buff->is_eop) {
 			buff_ = buff;
 			do {
+				if (buff_->next >= self->size) {
+					err = -EIO;
+					goto err_exit;
+				}
 				next_ = buff_->next,
 				buff_ = &self->buff_ring[next_];
 				is_rsc_completed =

@@ -327,6 +331,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self,
 			if (buff->is_error || buff->is_cso_err) {
 				buff_ = buff;
 				do {
+					if (buff_->next >= self->size) {
+						err = -EIO;
+						goto err_exit;
+					}
 					next_ = buff_->next,
 					buff_ = &self->buff_ring[next_];
 

2.34.1

From: David Ahern <[email protected]>

commit 1ff15a710a862db1101b97810af14aedc835a86a upstream.

Make sure RTA_GATEWAY for IPv6 multipath route has enough bytes to hold an IPv6 address.

---
 net/ipv6/route.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -5307,7 +5307,11 @@ static int ip6_route_multipath_del(struc
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla) {
-				nla_memcpy(&r_cfg.fc_gateway, nla, 16);
+				err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
+							extack);
+				if (err)
+					return err;
+
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
 		}

From: Christian Melki <[email protected]>

commit 764d31cacfe48440745c4bbb55a62ac9471c9f19 upstream.

Following a similar reinstate for the KSZ9031.

Older kernels would use the genphy_soft_reset if the PHY did not implement a .soft_reset.

Bluntly removing that default may expose a lot of situations where various PHYs/board implementations won't recover on various changes. Like with this implementation during a 4.9.x to 5.4.x LTS transition. I think it's a good thing to remove unwanted soft resets but wonder if it did open a can of worms?

Atleast this fixes one iMX6 FEC/RMII/8081 combo.

---
 drivers/net/phy/micrel.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1096,6 +1096,7 @@ static struct phy_driver ksphy_driver[]
 	.probe		= kszphy_probe,
 	.config_init	= ksz8081_config_init,
 	.ack_interrupt	= kszphy_ack_interrupt,
+	.soft_reset	= genphy_soft_reset,
 	.config_intr	= kszphy_config_intr,
 	.get_sset_count = kszphy_get_sset_count,
 	.get_strings	= kszphy_get_strings,

From: Darrick J. Wong <[email protected]>

commit 983d8e60f50806f90534cc5373d0ce867e5aaf79 upstream.

The old ALLOCSP/FREESP ioctls in XFS can be used to preallocate space at the end of files, just like fallocate and RESVSP. Make the behavior consistent with the other ioctls.

---
 fs/xfs/xfs_ioctl.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -714,7 +714,8 @@ xfs_ioc_space(
 		flags |= XFS_PREALLOC_CLEAR;
 		if (bf->l_start > XFS_ISIZE(ip)) {
 			error = xfs_alloc_file_space(ip, XFS_ISIZE(ip),
-					bf->l_start - XFS_ISIZE(ip), 0);
+					bf->l_start - XFS_ISIZE(ip),
+					XFS_BMAPI_PREALLOC);
 			if (error)
 				goto out_unlock;
 		}

From: David Ahern <[email protected]>

commit 7a3429bace0e08d94c39245631ea6bc109dafa49 upstream.

syzbot reported uninit-value:
============================================================

  BUG: KMSAN: uninit-value in fib_get_nhs+0xac4/0x1f80
  net/ipv4/fib_semantics.c:708
   fib_get_nhs+0xac4/0x1f80 net/ipv4/fib_semantics.c:708
   fib_create_info+0x2411/0x4870 net/ipv4/fib_semantics.c:1453
   fib_table_insert+0x45c/0x3a10 net/ipv4/fib_trie.c:1224
   inet_rtm_newroute+0x289/0x420 net/ipv4/fib_frontend.c:886

Add helper to validate RTA_GATEWAY length before using the attribute.

---
 net/ipv4/fib_semantics.c |   29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

@@ -654,6 +654,19 @@ static int fib_count_nexthops(struct rtn
 	return nhs;
 }
 
+static int fib_gw_from_attr(__be32 *gw, struct nlattr *nla,
+			    struct netlink_ext_ack *extack)
+{
+	if (nla_len(nla) < sizeof(*gw)) {
+		NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_GATEWAY");
+		return -EINVAL;
+	}
+
+	*gw = nla_get_in_addr(nla);
+
+	return 0;
+}
+
 /* only called when fib_nh is integrated into fib_info */
 static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 		       int remaining, struct fib_config *cfg,

@@ -696,7 +709,11 @@ static int fib_get_nhs(struct fib_info *
 				return -EINVAL;
 			}
 			if (nla) {
-				fib_cfg.fc_gw4 = nla_get_in_addr(nla);
+				ret = fib_gw_from_attr(&fib_cfg.fc_gw4, nla,
+						       extack);
+				if (ret)
+					goto errout;
+
 				if (fib_cfg.fc_gw4)
 					fib_cfg.fc_gw_family = AF_INET;
 			} else if (nlav) {

@@ -894,6 +911,7 @@ int fib_nh_match(struct fib_config *cfg,
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
 			struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
+			int err;
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			nlav = nla_find(attrs, attrlen, RTA_VIA);

@@ -904,12 +922,17 @@ int fib_nh_match(struct fib_config *cfg,
 			}
 
 			if (nla) {
+				__be32 gw;
+
+				err = fib_gw_from_attr(&gw, nla, extack);
+				if (err)
+					return err;
+
 				if (nh->fib_nh_gw_family != AF_INET ||
-				    nla_get_in_addr(nla) != nh->fib_nh_gw4)
+				    gw != nh->fib_nh_gw4)
 					return 1;
 			} else if (nlav) {
 				struct fib_config cfg2;
-				int err;
 
 				err = fib_gw_from_via(&cfg2, nlav, extack);
 				if (err)

From: Linus Lüssing <[email protected]>

commit 938f2e0b57ffe8a6df71e1e177b2978b1b33fe5e upstream.

The addition of routable multicast TX handling introduced a bug/regression for packets with a link-local multicast destination:
These packets would be sent to all batman-adv nodes with a multicast router and to all batman-adv nodes with an old version without multicast router detection.

This even disregards the batman-adv multicast fanout setting, which can potentially lead to an unwanted, high number of unicast transmissions or even congestion.

Fixing this by avoiding to send link-local multicast packets to nodes in the multicast router list.

---
 net/batman-adv/multicast.c      |   15 ++++++++++-----
 net/batman-adv/multicast.h      |   10 ++++++----
 net/batman-adv/soft-interface.c |    7 +++++--
 3 files changed, 21 insertions(+), 11 deletions(-)

@@ -1373,6 +1373,7 @@ batadv_mcast_forw_rtr_node_get(struct ba
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: The multicast packet to check
  * @orig: an originator to be set to forward the skb to
+ * @is_routable: stores whether the destination is routable
  *
  * Return: the forwarding mode as enum batadv_forw_mode and in case of
  * BATADV_FORW_SINGLE set the orig to the single originator the skb

@@ -1380,17 +1381,16 @@ batadv_mcast_forw_rtr_node_get(struct ba
  */
 enum batadv_forw_mode
 batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
-		       struct batadv_orig_node **orig)
+		       struct batadv_orig_node **orig, int *is_routable)
 {
 	int ret, tt_count, ip_count, unsnoop_count, total_count;
 	bool is_unsnoopable = false;
 	unsigned int mcast_fanout;
 	struct ethhdr *ethhdr;
-	int is_routable = 0;
 	int rtr_count = 0;
 
 	ret = batadv_mcast_forw_mode_check(bat_priv, skb, &is_unsnoopable,
-					   &is_routable);
+					   is_routable);
 	if (ret == -ENOMEM)
 		return BATADV_FORW_NONE;
 	else if (ret < 0)

@@ -1403,7 +1403,7 @@ batadv_mcast_forw_mode(struct batadv_pri
 	ip_count = batadv_mcast_forw_want_all_ip_count(bat_priv, ethhdr);
 	unsnoop_count = !is_unsnoopable ? 0 :
 			atomic_read(&bat_priv->mcast.num_want_all_unsnoopables);
-	rtr_count = batadv_mcast_forw_rtr_count(bat_priv, is_routable);
+	rtr_count = batadv_mcast_forw_rtr_count(bat_priv, *is_routable);
 
 	total_count = tt_count + ip_count + unsnoop_count + rtr_count;
 

@@ -1723,6 +1723,7 @@ batadv_mcast_forw_want_rtr(struct batadv
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: the multicast packet to transmit
  * @vid: the vlan identifier
+ * @is_routable: stores whether the destination is routable
  *
  * Sends copies of a frame with multicast destination to any node that signaled
  * interest in it, that is either via the translation table or the according

@@ -1735,7 +1736,7 @@ batadv_mcast_forw_want_rtr(struct batadv
  * is neither IPv4 nor IPv6. NET_XMIT_SUCCESS otherwise.
  */
 int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
-			   unsigned short vid)
+			   unsigned short vid, int is_routable)
 {
 	int ret;
 

@@ -1751,12 +1752,16 @@ int batadv_mcast_forw_send(struct batadv
 		return ret;
 	}
 
+	if (!is_routable)
+		goto skip_mc_router;
+
 	ret = batadv_mcast_forw_want_rtr(bat_priv, skb, vid);
 	if (ret != NET_XMIT_SUCCESS) {
 		kfree_skb(skb);
 		return ret;
 	}
 
+skip_mc_router:
 	consume_skb(skb);
 	return ret;
 }

@@ -44,7 +44,8 @@ enum batadv_forw_mode {
 
 enum batadv_forw_mode
 batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
-		       struct batadv_orig_node **mcast_single_orig);
+		       struct batadv_orig_node **mcast_single_orig,
+		       int *is_routable);
 
 int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv,
 				struct sk_buff *skb,

@@ -52,7 +53,7 @@ int batadv_mcast_forw_send_orig(struct b
 				struct batadv_orig_node *orig_node);
 
 int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
-			   unsigned short vid);
+			   unsigned short vid, int is_routable);
 
 void batadv_mcast_init(struct batadv_priv *bat_priv);
 

@@ -71,7 +72,8 @@ void batadv_mcast_purge_orig(struct bata
 
 static inline enum batadv_forw_mode
 batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
-		       struct batadv_orig_node **mcast_single_orig)
+		       struct batadv_orig_node **mcast_single_orig,
+		       int *is_routable)
 {
 	return BATADV_FORW_ALL;
 }

@@ -88,7 +90,7 @@ batadv_mcast_forw_send_orig(struct batad
 
 static inline int
 batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
-		       unsigned short vid)
+		       unsigned short vid, int is_routable)
 {
 	kfree_skb(skb);
 	return NET_XMIT_DROP;

@@ -200,6 +200,7 @@ static netdev_tx_t batadv_interface_tx(s
 	int gw_mode;
 	enum batadv_forw_mode forw_mode = BATADV_FORW_SINGLE;
 	struct batadv_orig_node *mcast_single_orig = NULL;
+	int mcast_is_routable = 0;
 	int network_offset = ETH_HLEN;
 	__be16 proto;
 

@@ -302,7 +303,8 @@ static netdev_tx_t batadv_interface_tx(s
 send:
 		if (do_bcast && !is_broadcast_ether_addr(ethhdr->h_dest)) {
 			forw_mode = batadv_mcast_forw_mode(bat_priv, skb,
-							   &mcast_single_orig);
+							   &mcast_single_orig,
+							   &mcast_is_routable);
 			if (forw_mode == BATADV_FORW_NONE)
 				goto dropped;
 

@@ -367,7 +369,8 @@ send:
 			ret = batadv_mcast_forw_send_orig(bat_priv, skb, vid,
 							  mcast_single_orig);
 		} else if (forw_mode == BATADV_FORW_SOME) {
-			ret = batadv_mcast_forw_send(bat_priv, skb, vid);
+			ret = batadv_mcast_forw_send(bat_priv, skb, vid,
+						     mcast_is_routable);
 		} else {
 			if (batadv_dat_snoop_outgoing_arp_request(bat_priv,
 								  skb))

From: Karen Sornek <[email protected]>

commit b712941c8085e638bb92456e866ed3de4404e3d5 upstream.

In the absence of this validation, if the user requests to configure queues more than the enabled queues, it results in sending the requested number of queues to the kernel stack (due to the asynchronous nature of VF response), in which case the stack might pick a queue to transmit that is not enabled and result in Tx hang. Fix this bug by limiting the total number of queues allocated for VF to active queues of VF.

---
 drivers/net/ethernet/intel/iavf/iavf_main.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -2604,8 +2604,11 @@ static int iavf_validate_ch_config(struc
 		total_max_rate += tx_rate;
 		num_qps += mqprio_qopt->qopt.count[i];
 	}
-	if (num_qps > IAVF_MAX_REQ_QUEUES)
+	if (num_qps > adapter->num_active_queues) {
+		dev_err(&adapter->pdev->dev,
+			"Cannot support requested number of queues\n");
 		return -EINVAL;
+	}
 
 	ret = iavf_validate_tx_bandwidth(adapter, total_max_rate);
 	return ret;

From: Chao Yu <[email protected]>

commit a5c0042200b28fff3bde6fa128ddeaef97990f8d upstream.

As Yi Zhuang reported in bugzilla:

https://bugzilla.kernel.org/show_bug.cgi?id=214299

There is potential deadlock during quota data flush as below:

Thread A: Thread B:
f2fs_dquot_acquire
down_read(&sbi->quota_sem)

				f2fs_write_checkpoint
				block_operations
				f2fs_look_all
				down_write(&sbi->cp_rwsem)

f2fs_quota_write
f2fs_write_begin
__do_map_lock
f2fs_lock_op
down_read(&sbi->cp_rwsem)

				__need_flush_qutoa
				down_write(&sbi->quota_sem)

This patch changes block_operations() to use trylock, if it fails, it means there is potential quota data updater, in this condition, let's flush quota data first and then trylock again to check dirty status of quota data.

The side effect is: in heavy race condition (e.g. multi quota data upaters vs quota data flusher), it may decrease the probability of synchronizing quota data successfully in checkpoint() due to limited retry time of quota flush.

---
 fs/f2fs/checkpoint.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -1144,7 +1144,8 @@ static bool __need_flush_quota(struct f2
 	if (!is_journalled_quota(sbi))
 		return false;
 
-	down_write(&sbi->quota_sem);
+	if (!down_write_trylock(&sbi->quota_sem))
+		return true;
 	if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) {
 		ret = false;
 	} else if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) {

From: Tom Rix <[email protected]>

commit 68a18ad71378a56858141c4449e02a30c829763e upstream.

Clang static analysis reports this warnings

mlme.c:5332:7: warning: Branch condition evaluates to a
garbage value

    have_higher_than_11mbit)
    ^~~~~~~~~~~~~~~~~~~~~~~

have_higher_than_11mbit is only set to true some of the time in ieee80211_get_rates() but is checked all of the time. So have_higher_than_11mbit needs to be initialized to false.

---
 net/mac80211/mlme.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -4953,7 +4953,7 @@ static int ieee80211_prep_connection(str
 	 */
 	if (new_sta) {
 		u32 rates = 0, basic_rates = 0;
-		bool have_higher_than_11mbit;
+		bool have_higher_than_11mbit = false;
 		int min_rate = INT_MAX, min_rate_index = -1;
 		const struct cfg80211_bss_ies *ies;
 		int shift = ieee80211_vif_get_shift(&sdata->vif);

From: Naveen N. Rao <[email protected]>

commit f28439db470cca8b6b082239314e9fd10bd39034 upstream.

Tag trace_percpu_buffer as a percpu pointer to resolve warnings
reported by sparse:
/linux/kernel/trace/trace.c:3218:46: warning: incorrect type in initializer (different address spaces)
/linux/kernel/trace/trace.c:3218:46: expected void const [noderef] __percpu *__vpp_verify
/linux/kernel/trace/trace.c:3218:46: got struct trace_buffer_struct *
/linux/kernel/trace/trace.c:3234:9: warning: incorrect type in initializer (different address spaces)
/linux/kernel/trace/trace.c:3234:9: expected void const [noderef] __percpu *__vpp_verify
/linux/kernel/trace/trace.c:3234:9: got int *

---
 kernel/trace/trace.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -3007,7 +3007,7 @@ struct trace_buffer_struct {
 	char buffer[4][TRACE_BUF_SIZE];
 };
 
-static struct trace_buffer_struct *trace_percpu_buffer;
+static struct trace_buffer_struct __percpu *trace_percpu_buffer;
 
 /*
  * Thise allows for lockless recording.  If we're nested too deeply, then

@@ -3036,7 +3036,7 @@ static void put_trace_buf(void)
 
 static int alloc_percpu_trace_buffer(void)
 {
-	struct trace_buffer_struct *buffers;
+	struct trace_buffer_struct __percpu *buffers;
 
 	buffers = alloc_percpu(struct trace_buffer_struct);
 	if (WARN(!buffers, "Could not allocate percpu trace_printk buffer"))

From: Leon Romanovsky <[email protected]>

commit b35a0f4dd544eaa6162b6d2f13a2557a121ae5fd upstream.

If dst->is_global field is not set, the GRH fields are not cleared and the following infoleak is reported.

=====================================================

BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:121 [inline]
BUG: KMSAN: kernel-infoleak in _copy_to_user+0x1c9/0x270 lib/usercopy.c:33
 instrument_copy_to_user include/linux/instrumented.h:121 [inline]
 _copy_to_user+0x1c9/0x270 lib/usercopy.c:33
 copy_to_user include/linux/uaccess.h:209 [inline]
 ucma_init_qp_attr+0x8c7/0xb10 drivers/infiniband/core/ucma.c:1242
 ucma_write+0x637/0x6c0 drivers/infiniband/core/ucma.c:1732
 vfs_write+0x8ce/0x2030 fs/read_write.c:588
 ksys_write+0x28b/0x510 fs/read_write.c:643
 __do_sys_write fs/read_write.c:655 [inline]
 __se_sys_write fs/read_write.c:652 [inline]
 __ia32_sys_write+0xdb/0x120 fs/read_write.c:652
 do_syscall_32_irqs_on arch/x86/entry/common.c:114 [inline]
 __do_fast_syscall_32+0x96/0xf0 arch/x86/entry/common.c:180
 do_fast_syscall_32+0x34/0x70 arch/x86/entry/common.c:205
 do_SYSENTER_32+0x1b/0x20 arch/x86/entry/common.c:248
 entry_SYSENTER_compat_after_hwframe+0x4d/0x5c

Local variable resp created at:

 ucma_init_qp_attr+0xa4/0xb10 drivers/infiniband/core/ucma.c:1214
 ucma_write+0x637/0x6c0 drivers/infiniband/core/ucma.c:1732

Bytes 40-59 of 144 are uninitialized
Memory access of size 144 starts at ffff888167523b00 Data copied to user address 0000000020000100

CPU: 1 PID: 25910 Comm: syz-executor.1 Not tainted 5.16.0-rc5-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
=====================================================

---
 drivers/infiniband/core/uverbs_marshall.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -66,7 +66,7 @@ void ib_copy_ah_attr_to_user(struct ib_d
 	struct rdma_ah_attr *src = ah_attr;
 	struct rdma_ah_attr conv_ah;
 
-	memset(&dst->grh.reserved, 0, sizeof(dst->grh.reserved));
+	memset(&dst->grh, 0, sizeof(dst->grh));
 
 	if ((ah_attr->type == RDMA_AH_ATTR_TYPE_OPA) &&
 	    (rdma_ah_get_dlid(ah_attr) > be16_to_cpu(IB_LID_PERMISSIVE)) &&

From: Nathan Chancellor <[email protected]>

commit 644106cdb89844be2496b21175b7c0c2e0fab381 upstream.

A new commit in LLVM causes an error on the use of 'long double' when '-mno-x87' is used, which the kernel does through an alias, '-mno-80387' (see the LLVM commit below for more details around why it does this).

drivers/power/reset/ltc2952-poweroff.c:162:28: error: expression requires 'long double' type support, but target 'x86_64-unknown-linux-gnu' does not support it

        data->wde_interval = 300L * 1E6L;
                                  ^
drivers/power/reset/ltc2952-poweroff.c:162:21: error: expression requires  'long double' type support, but target 'x86_64-unknown-linux-gnu' does not support it
        data->wde_interval = 300L * 1E6L;
                           ^
drivers/power/reset/ltc2952-poweroff.c:163:41: error: expression requires  'long double' type support, but target 'x86_64-unknown-linux-gnu' does not support it
        data->trigger_delay = ktime_set(2, 500L*1E6L);
                                               ^

3 errors generated.

This happens due to the use of a 'long double' literal. The 'E6' part of '1E6L' causes the literal to be a 'double' then the 'L' suffix promotes it to 'long double'.

There is no visible reason for floating point values in this driver, as the values are only assigned to integer types. Use NSEC_PER_MSEC, which is the same integer value as '1E6L', to avoid changing functionality but fix the error.

---
 drivers/power/reset/ltc2952-poweroff.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -160,8 +160,8 @@ static void ltc2952_poweroff_kill(void)
 
 static void ltc2952_poweroff_default(struct ltc2952_poweroff *data)
 {
-	data->wde_interval = 300L * 1E6L;
-	data->trigger_delay = ktime_set(2, 500L*1E6L);
+	data->wde_interval = 300L * NSEC_PER_MSEC;
+	data->trigger_delay = ktime_set(2, 500L * NSEC_PER_MSEC);
 
 	hrtimer_init(&data->timer_trigger, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	data->timer_trigger.function = ltc2952_poweroff_timer_trigger;

From: Thomas Toye <[email protected]>

commit 29262e1f773b4b6a43711120be564c57fca07cfb upstream.

Hytera makes a range of digital (DMR) radios. These radios can be programmed to a allow a computer to control them over Ethernet over USB, either using NCM or RNDIS.

This commit adds support for RNDIS for Hytera radios. I tested with a Hytera PD785 and a Hytera MD785G. When these radios are programmed to set up a Radio to PC Network using RNDIS, an USB interface will be added with class 2 (Communications), subclass 2 (Abstract Modem Control) and an interface protocol of 255 ("vendor specific" - lsusb even hints "MSFT RNDIS?").

This patch is similar to the solution of this StackOverflow user, but that only works for the Hytera MD785:
https://stackoverflow.com/a/53550858

To use the "Radio to PC Network" functionality of Hytera DMR radios, the radios need to be programmed correctly in CPS (Hytera's Customer Programming Software). "Forward to PC" should be checked in "Network" (under "General Setting" in "Conventional") and the "USB Network Communication Protocol" should be set to RNDIS.

---
 drivers/net/usb/rndis_host.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -609,6 +609,11 @@ static const struct usb_device_id	produc
 				      USB_CLASS_COMM, 2 /* ACM */, 0x0ff),
 	.driver_info = (unsigned long) &rndis_poll_status_info,
 }, {
+	/* Hytera Communications DMR radios' "Radio to PC Network" */
+	USB_VENDOR_AND_INTERFACE_INFO(0x238b,
+				      USB_CLASS_COMM, 2 /* ACM */, 0x0ff),
+	.driver_info = (unsigned long)&rndis_info,
+}, {
 	/* RNDIS is MSFT's un-official variant of CDC ACM */
 	USB_INTERFACE_INFO(USB_CLASS_COMM, 2 /* ACM */, 0x0ff),
 	.driver_info = (unsigned long) &rndis_info,

From: Pavel Skripkin <[email protected]>

commit 754e4382354f7908923a1949d8dc8d05f82f09cb upstream.

Alexander reported a use of uninitialized value in atusb_set_extended_addr(), that is caused by reading 0 bytes via usb_control_msg().

Fix it by validating if the number of bytes transferred is actually correct, since usb_control_msg() may read less bytes, than was requested by caller.

Fail log:

BUG: KASAN: uninit-cmp in ieee802154_is_valid_extended_unicast_addr include/linux/ieee802154.h:310 [inline]
BUG: KASAN: uninit-cmp in atusb_set_extended_addr drivers/net/ieee802154/atusb.c:1000 [inline]
BUG: KASAN: uninit-cmp in atusb_probe.cold+0x29f/0x14db drivers/net/ieee802154/atusb.c:1056
Uninit value used in comparison: 311daa649a2003bd stack handle: 000000009a2003bd
 ieee802154_is_valid_extended_unicast_addr include/linux/ieee802154.h:310 [inline]
 atusb_set_extended_addr drivers/net/ieee802154/atusb.c:1000 [inline]
 atusb_probe.cold+0x29f/0x14db drivers/net/ieee802154/atusb.c:1056
 usb_probe_interface+0x314/0x7f0 drivers/usb/core/driver.c:396

---
 drivers/net/ieee802154/atusb.c |   10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

@@ -93,7 +93,9 @@ static int atusb_control_msg(struct atus
 
 	ret = usb_control_msg(usb_dev, pipe, request, requesttype,
 			      value, index, data, size, timeout);
-	if (ret < 0) {
+	if (ret < size) {
+		ret = ret < 0 ? ret : -ENODATA;
+
 		atusb->err = ret;
 		dev_err(&usb_dev->dev,
 			"%s: req 0x%02x val 0x%x idx 0x%x, error %d\n",

@@ -861,9 +863,9 @@ static int atusb_get_and_show_build(stru
 	if (!build)
 		return -ENOMEM;
 
-	ret = atusb_control_msg(atusb, usb_rcvctrlpipe(usb_dev, 0),
-				ATUSB_BUILD, ATUSB_REQ_FROM_DEV, 0, 0,
-				build, ATUSB_BUILD_SIZE, 1000);
+	/* We cannot call atusb_control_msg() here, since this request may read various length data */
+	ret = usb_control_msg(atusb->usb_dev, usb_rcvctrlpipe(usb_dev, 0), ATUSB_BUILD,
+			      ATUSB_REQ_FROM_DEV, 0, 0, build, ATUSB_BUILD_SIZE, 1000);
 	if (ret >= 0) {
 		build[ret] = 0;
 		dev_info(&usb_dev->dev, "Firmware: build %s\n", build);

From: yangxingwu <[email protected]>

[ Upstream commit 6c25449e1a32c594d743df8e8258e8ef870b6a77 ]

$ cat /pro/net/udp

before:

sl local_address rem_address st tx_queue rx_queue tr tm->when
26050: 0100007F:0035 00000000:0000 07 00000000:00000000 00:00000000 26320: 0100007F:0143 00000000:0000 07 00000000:00000000 00:00000000 27135: 00000000:8472 00000000:0000 07 00000000:00000000 00:00000000

after:

sl local_address rem_address st tx_queue rx_queue tr tm->when
26050: 0100007F:0035 00000000:0000 07 00000000:00000000 00:00000000 26320: 0100007F:0143 00000000:0000 07 00000000:00000000 00:00000000 27135: 00000000:8472 00000000:0000 07 00000000:00000000 00:00000000

---
 net/ipv4/udp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index a0016f05c4f86..3cdf011a8dd8d 100644
@@ -2943,7 +2943,7 @@ int udp4_seq_show(struct seq_file *seq, void *v)
 {
 	seq_setwidth(seq, 127);
 	if (v == SEQ_START_TOKEN)
-		seq_puts(seq, "  sl  local_address rem_address   st tx_queue "
+		seq_puts(seq, "   sl  local_address rem_address   st tx_queue "
 			   "rx_queue tr tm->when retrnsmt   uid  timeout "
 			   "inode ref pointer drops");
 	else {

2.34.1

From: Chunfeng Yun <[email protected]>

[ Upstream commit e3d4621c22f90c33321ae6a6baab60cdb8e5a77c ]

Use the Interval value from isoc/intr endpoint descriptor, no need minus one. The original code doesn't cause transfer error for normal cases, but it may have side effect with respond time of ERDY or tPingTimeout.

---
 drivers/usb/mtu3/mtu3_gadget.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 253c8b71d3c49..061da9b82b967 100644
@@ -85,7 +85,7 @@ static int mtu3_ep_enable(struct mtu3_ep *mep)
 		if (usb_endpoint_xfer_int(desc) ||
 				usb_endpoint_xfer_isoc(desc)) {
 			interval = desc->bInterval;
-			interval = clamp_val(interval, 1, 16) - 1;
+			interval = clamp_val(interval, 1, 16);
 			if (usb_endpoint_xfer_isoc(desc) && comp_desc)
 				mult = comp_desc->bmAttributes;
 		}

@@ -97,7 +97,7 @@ static int mtu3_ep_enable(struct mtu3_ep *mep)
 		if (usb_endpoint_xfer_isoc(desc) ||
 				usb_endpoint_xfer_int(desc)) {
 			interval = desc->bInterval;
-			interval = clamp_val(interval, 1, 16) - 1;
+			interval = clamp_val(interval, 1, 16);
 			mult = usb_endpoint_maxp_mult(desc) - 1;
 		}
 		break;

2.34.1

From: wolfgang huang <[email protected]>

[ Upstream commit 8b5fdfc57cc2471179d1c51081424ded833c16c8 ]

As we build for mips, we meet following error. l1_init error with multiple definition. Some architecture devices usually marked with l1, l2, lxx as the start-up phase. so we change the mISDN function names, align with Isdnl2_xxx.

mips-linux-gnu-ld: drivers/isdn/mISDN/layer1.o: in function `l1_init':
(.text+0x890): multiple definition of `l1_init'; \
arch/mips/kernel/bmips_5xxx_init.o:(.text+0xf0): first defined here make[1]: *** [home/mips/kernel-build/linux/Makefile:1161: vmlinux] Error 1

---
 drivers/isdn/mISDN/core.c   | 6 +++---
 drivers/isdn/mISDN/core.h   | 4 ++--
 drivers/isdn/mISDN/layer1.c | 4 ++--
 3 files changed, 7 insertions(+), 7 deletions(-)

index 55891e4204460..a41b4b2645941 100644
@@ -381,7 +381,7 @@ mISDNInit(void)
 	err = mISDN_inittimer(&debug);
 	if (err)
 		goto error2;
-	err = l1_init(&debug);
+	err = Isdnl1_Init(&debug);
 	if (err)
 		goto error3;
 	err = Isdnl2_Init(&debug);

@@ -395,7 +395,7 @@ mISDNInit(void)
 error5:
 	Isdnl2_cleanup();
 error4:
-	l1_cleanup();
+	Isdnl1_cleanup();
 error3:
 	mISDN_timer_cleanup();
 error2:

@@ -408,7 +408,7 @@ static void mISDN_cleanup(void)
 {
 	misdn_sock_cleanup();
 	Isdnl2_cleanup();
-	l1_cleanup();
+	Isdnl1_cleanup();
 	mISDN_timer_cleanup();
 	class_unregister(&mISDN_class);
 

index 23b44d3033279..42599f49c189d 100644
@@ -60,8 +60,8 @@ struct Bprotocol	*get_Bprotocol4id(u_int);
 extern int	mISDN_inittimer(u_int *);
 extern void	mISDN_timer_cleanup(void);
 
-extern int	l1_init(u_int *);
-extern void	l1_cleanup(void);
+extern int	Isdnl1_Init(u_int *);
+extern void	Isdnl1_cleanup(void);
 extern int	Isdnl2_Init(u_int *);
 extern void	Isdnl2_cleanup(void);
 

index 98a3bc6c17009..7b31c25a550e3 100644
@@ -398,7 +398,7 @@ create_l1(struct dchannel *dch, dchannel_l1callback *dcb) {
 EXPORT_SYMBOL(create_l1);
 
 int
-l1_init(u_int *deb)
+Isdnl1_Init(u_int *deb)
 {
 	debug = deb;
 	l1fsm_s.state_count = L1S_STATE_COUNT;

@@ -409,7 +409,7 @@ l1_init(u_int *deb)
 }
 
 void
-l1_cleanup(void)
+Isdnl1_cleanup(void)
 {
 	mISDN_FsmFree(&l1fsm_s);
 }

2.34.1

From: David Ahern <[email protected]>

commit 4619bcf91399f00a40885100fb61d594d8454033 upstream.

Commit referenced in the Fixes tag used nla_memcpy for RTA_GATEWAY as does the current nla_get_in6_addr. nla_memcpy protects against accessing memory greater than what is in the attribute, but there is no check requiring the attribute to have an IPv6 address. Add it.

---
 net/ipv6/route.c |   21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

@@ -5092,6 +5092,19 @@ static void ip6_route_mpath_notify(struc
 		inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
 }
 
+static int fib6_gw_from_attr(struct in6_addr *gw, struct nlattr *nla,
+			     struct netlink_ext_ack *extack)
+{
+	if (nla_len(nla) < sizeof(*gw)) {
+		NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY");
+		return -EINVAL;
+	}
+
+	*gw = nla_get_in6_addr(nla);
+
+	return 0;
+}
+
 static int ip6_route_multipath_add(struct fib6_config *cfg,
 				   struct netlink_ext_ack *extack)
 {

@@ -5133,7 +5146,13 @@ static int ip6_route_multipath_add(struc
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
 			if (nla) {
-				r_cfg.fc_gateway = nla_get_in6_addr(nla);
+				int ret;
+
+				ret = fib6_gw_from_attr(&r_cfg.fc_gateway, nla,
+							extack);
+				if (ret)
+					return ret;
+
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
 			r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);

From: David Ahern <[email protected]>

commit 8bda81a4d400cf8a72e554012f0d8c45e07a3904 upstream.

lwtunnel_valid_encap_type_attr is used to validate encap attributes within a multipath route. Add length validation checking to the type.

lwtunnel_valid_encap_type_attr is called converting attributes to fib{6,}_config struct which means it is used before fib_get_nhs, ip6_route_multipath_add, and ip6_route_multipath_del - other locations that use rtnh_ok and then nla_get_u16 on RTA_ENCAP_TYPE attribute.

---
 net/core/lwtunnel.c      |    4 ++++
 net/ipv4/fib_semantics.c |    3 +++
 net/ipv6/route.c         |    4 ++++
 3 files changed, 11 insertions(+)

@@ -190,6 +190,10 @@ int lwtunnel_valid_encap_type_attr(struc
 			nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 
 			if (nla_entype) {
+				if (nla_len(nla_entype) < sizeof(u16)) {
+					NL_SET_ERR_MSG(extack, "Invalid RTA_ENCAP_TYPE");
+					return -EINVAL;
+				}
 				encap_type = nla_get_u16(nla_entype);
 
 				if (lwtunnel_valid_encap_type(encap_type,

@@ -732,6 +732,9 @@ static int fib_get_nhs(struct fib_info *
 			}
 
 			fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
+			/* RTA_ENCAP_TYPE length checked in
+			 * lwtunnel_valid_encap_type_attr
+			 */
 			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 			if (nla)
 				fib_cfg.fc_encap_type = nla_get_u16(nla);

@@ -5156,6 +5156,10 @@ static int ip6_route_multipath_add(struc
 				r_cfg.fc_flags |= RTF_GATEWAY;
 			}
 			r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
+
+			/* RTA_ENCAP_TYPE length checked in
+			 * lwtunnel_valid_encap_type_attr
+			 */
 			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
 			if (nla)
 				r_cfg.fc_encap_type = nla_get_u16(nla);

From: Linus Walleij <[email protected]>

commit 51c7b6a0398f54b9120795796a4cff4fc9634f7d upstream.

We should not go on looking for more capacity tables after we realize we have looked at the last one in power_supply_find_ocv2cap_table().

---
 drivers/power/supply/power_supply_core.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -742,6 +742,10 @@ power_supply_find_ocv2cap_table(struct p
 		return NULL;
 
 	for (i = 0; i < POWER_SUPPLY_OCV_TEMP_MAX; i++) {
+		/* Out of capacity tables */
+		if (!info->ocv_table[i])
+			break;
+
 		temp_diff = abs(info->ocv_temp[i] - temp);
 
 		if (temp_diff < best_temp_diff) {

From: Hangyu Hua <[email protected]>

commit bcd0f93353326954817a4f9fa55ec57fb38acbb0 upstream.

sock_hold(sk) is invoked in pep_sock_accept(), but __sock_put(sk) is not invoked in subsequent failure branches(pep_accept_conn() != 0).

---
 net/phonet/pep.c |    1 +
 1 file changed, 1 insertion(+)

@@ -868,6 +868,7 @@ static struct sock *pep_sock_accept(stru
 
 	err = pep_accept_conn(newsk, skb);
 	if (err) {
+		__sock_put(sk);
 		sock_put(newsk);
 		newsk = NULL;
 		goto drop;

From: Eric Dumazet <[email protected]>

commit 7d18a07897d07495ee140dd319b0e9265c0f68ba upstream.

tx_queue_len can be set to ~0U, we need to be more careful about overflows.

__fls(0) is undefined, as this report shows:

UBSAN: shift-out-of-bounds in net/sched/sch_qfq.c:1430:24
shift exponent 51770272 is too large for 32-bit type 'int'
CPU: 0 PID: 25574 Comm: syz-executor.0 Not tainted 5.16.0-rc7-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x201/0x2d8 lib/dump_stack.c:106
 ubsan_epilogue lib/ubsan.c:151 [inline]
 __ubsan_handle_shift_out_of_bounds+0x494/0x530 lib/ubsan.c:330
 qfq_init_qdisc+0x43f/0x450 net/sched/sch_qfq.c:1430
 qdisc_create+0x895/0x1430 net/sched/sch_api.c:1253
 tc_modify_qdisc+0x9d9/0x1e20 net/sched/sch_api.c:1660
 rtnetlink_rcv_msg+0x934/0xe60 net/core/rtnetlink.c:5571
 netlink_rcv_skb+0x200/0x470 net/netlink/af_netlink.c:2496
 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline]
 netlink_unicast+0x814/0x9f0 net/netlink/af_netlink.c:1345
 netlink_sendmsg+0xaea/0xe60 net/netlink/af_netlink.c:1921
 sock_sendmsg_nosec net/socket.c:704 [inline]
 sock_sendmsg net/socket.c:724 [inline]
 ____sys_sendmsg+0x5b9/0x910 net/socket.c:2409
 ___sys_sendmsg net/socket.c:2463 [inline]
 __sys_sendmsg+0x280/0x370 net/socket.c:2492
 do_syscall_x64 arch/x86/entry/common.c:50 [inline]
 do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80
 entry_SYSCALL_64_after_hwframe+0x44/0xae

---
 net/sched/sch_qfq.c |    6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

@@ -1421,10 +1421,8 @@ static int qfq_init_qdisc(struct Qdisc *
 	if (err < 0)
 		return err;
 
-	if (qdisc_dev(sch)->tx_queue_len + 1 > QFQ_MAX_AGG_CLASSES)
-		max_classes = QFQ_MAX_AGG_CLASSES;
-	else
-		max_classes = qdisc_dev(sch)->tx_queue_len + 1;
+	max_classes = min_t(u64, (u64)qdisc_dev(sch)->tx_queue_len + 1,
+			    QFQ_MAX_AGG_CLASSES);
 	/* max_cl_shift = floor(log_2(max_classes)) */
 	max_cl_shift = __fls(max_classes);
 	q->max_agg_classes = 1<<max_cl_shift;

From: Jedrzej Jagielski <[email protected]>

commit e738451d78b2f8a9635d66c6a87f304b4d965f7a upstream.

There was a wrong queues representation in sysfs during driver's reinitialization in case of online cpus number is less than combined queues. It was caused by stopped NetworkManager, which is responsible for calling vsi_open function during driver's initialization.
In specific situation (ex. 12 cpus online) there were 16 queues in /sys/class/net/<iface>/queues. In case of modifying queues with value higher, than number of online cpus, then it caused write errors and other errors.
Add updating of sysfs's queues representation during driver initialization.

---
 drivers/net/ethernet/intel/i40e/i40e_main.c |   32 +++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 7 deletions(-)

@@ -8327,6 +8327,27 @@ int i40e_open(struct net_device *netdev)
 }
 
 /**
+ * i40e_netif_set_realnum_tx_rx_queues - Update number of tx/rx queues
+ * @vsi: vsi structure
+ *
+ * This updates netdev's number of tx/rx queues
+ *
+ * Returns status of setting tx/rx queues
+ **/
+static int i40e_netif_set_realnum_tx_rx_queues(struct i40e_vsi *vsi)
+{
+	int ret;
+
+	ret = netif_set_real_num_rx_queues(vsi->netdev,
+					   vsi->num_queue_pairs);
+	if (ret)
+		return ret;
+
+	return netif_set_real_num_tx_queues(vsi->netdev,
+					    vsi->num_queue_pairs);
+}
+
+/**
  * i40e_vsi_open -
  * @vsi: the VSI to open
  *

@@ -8362,13 +8383,7 @@ int i40e_vsi_open(struct i40e_vsi *vsi)
 			goto err_setup_rx;
 
 		/* Notify the stack of the actual queue counts. */
-		err = netif_set_real_num_tx_queues(vsi->netdev,
-						   vsi->num_queue_pairs);
-		if (err)
-			goto err_set_queues;
-
-		err = netif_set_real_num_rx_queues(vsi->netdev,
-						   vsi->num_queue_pairs);
+		err = i40e_netif_set_realnum_tx_rx_queues(vsi);
 		if (err)
 			goto err_set_queues;
 

@@ -13792,6 +13807,9 @@ struct i40e_vsi *i40e_vsi_setup(struct i
 		ret = i40e_config_netdev(vsi);
 		if (ret)
 			goto err_netdev;
+		ret = i40e_netif_set_realnum_tx_rx_queues(vsi);
+		if (ret)
+			goto err_netdev;
 		ret = register_netdev(vsi->netdev);
 		if (ret)
 			goto err_netdev;

All tests passing for Tegra ...

Test results for stable-v5.4:

    10 builds:	10 pass, 0 fail
    26 boots:	26 pass, 0 fail
    59 tests:	59 pass, 0 fail

Linux version: 5.4.171-rc1-g681e37e4e026
Boards tested: tegra124-jetson-tk1, tegra186-p2771-0000,

                tegra194-p2972-0000, tegra20-ventana,
                tegra210-p2371-2180, tegra210-p3450-0000,
                tegra30-cardhu-a04

Jon

On ARCH_BRCMSTB using 32-bit and 64-bit ARM kernels:

Florian

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

thanks,
-- Shuah

Build results:

	total: 157 pass: 157 fail: 0
Qemu test results:
	total: 444 pass: 444 fail: 0

Guenter

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

## Build
* kernel: 5.4.171-rc1
* git: https://gitlab.com/Linaro/lkft/mirrors/stable/linux-stable-rc
* git branch: linux-5.4.y
* git commit: 681e37e4e026f3e38040daf69869b507a40b60c3
* git describe: v5.4.170-35-g681e37e4e026
* test details:
https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-5.4.y/build/v5.4.170-35-g681e37e4e026

## Test Regressions (compared to v5.4.169)
No test regressions found.

## Metric Regressions (compared to v5.4.169)
No metric regressions found.

## Test Fixes (compared to v5.4.169)
No test fixes found.

## Metric Fixes (compared to v5.4.169)
No metric fixes found.

## Test result summary
total: 88836, pass: 73926, fail: 769, skip: 12722, xfail: 1419

## Build Summary
* arc: 10 total, 10 passed, 0 failed
* arm: 258 total, 254 passed, 4 failed
* arm64: 36 total, 31 passed, 5 failed
* dragonboard-410c: 1 total, 1 passed, 0 failed
* hi6220-hikey: 1 total, 1 passed, 0 failed
* i386: 20 total, 20 passed, 0 failed
* juno-r2: 1 total, 1 passed, 0 failed
* mips: 34 total, 34 passed, 0 failed
* parisc: 12 total, 12 passed, 0 failed
* powerpc: 52 total, 48 passed, 4 failed
* riscv: 24 total, 24 passed, 0 failed
* s390: 12 total, 12 passed, 0 failed
* sh: 24 total, 24 passed, 0 failed
* sparc: 12 total, 12 passed, 0 failed
* x15: 1 total, 1 passed, 0 failed
* x86: 1 total, 1 passed, 0 failed
* x86_64: 36 total, 36 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-memfd
* kselftest-memory-hotplug
* kselftest-mincore
* kselftest-mount
* kselftest-mqueue
* 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
* libgpiod
* 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

Hi Greg,

Build test:
mips (gcc version 11.2.1 20220106): 65 configs -> no new failure arm (gcc version 11.2.1 20220106): 107 configs -> no new failure arm64 (gcc version 11.2.1 20220106): 2 configs -> no failure x86_64 (gcc version 11.2.1 20220106): 4 configs -> no failure

Boot test:
x86_64: Booted on my test laptop. No regression.
x86_64: Booted on qemu. No regression. [1]

[1]. https://openqa.qa.codethink.co.uk/tests/610

--
Regards
Sudip

Tested on arm64 and x86 for 5.4.171-rc1,

Kernel repo:
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
Branch: linux-5.4.y
Version: 5.4.171-rc1
Commit: 681e37e4e026f3e38040daf69869b507a40b60c3
Compiler: gcc version 7.3.0 (GCC)

arm64:
--------------------------------------------------------------------
Testcase Result Summary:
total: 9014
passed: 9014
failed: 0
timeout: 0
--------------------------------------------------------------------

x86:
--------------------------------------------------------------------
Testcase Result Summary:
total: 9014
passed: 9014
failed: 0
timeout: 0
--------------------------------------------------------------------