Skip to contentSkip to conversation

6.1.176-rc1 review

PATCH In review Greg Kroah-Hartman 19 participants 561 messages Jun 16 – Jul 2 Page 2 of 5

Subsystems (4)
lore
Share & tools
lore
author maintainer
#135 lore raw

PATCH 125/522 ipv6: validate extension header length before copying to cmsg

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Qi Tang <[email protected]>

commit dd433671fef381fdaf7b530c631e6b782d66e224 upstream.

ip6_datagram_recv_specific_ctl() builds IPV6_{HOPOPTS,DSTOPTS,RTHDR} cmsgs (and their IPV6_2292* legacy counterparts) by trusting the on-wire hdrlen byte (ptr[1]) when computing the put_cmsg() length. The length was validated only at parse time (ipv6_parse_hopopts(), etc.). An nftables payload-write expression can rewrite hdrlen after parsing and before the skb reaches recvmsg; the write itself is in-bounds but put_cmsg() then reads up to ((hdrlen+1) << 3) = 2040 bytes from an 8-byte header. nftables is reachable from an unprivileged user namespace, so this is an unprivileged slab-out-of-bounds read:

  BUG: KASAN: slab-out-of-bounds in put_cmsg+0x3ac/0x540
   put_cmsg+0x3ac/0x540
   udpv6_recvmsg+0xca0/0x1250
   sock_recvmsg+0xdf/0x190
   ____sys_recvmsg+0x1b1/0x620

Add ipv6_get_exthdr_len() which validates that at least two bytes are accessible before reading the hdrlen field, then checks the computed length against skb_tail_pointer(skb), returning 0 on failure. Extension headers are kept in the linear skb area by pskb_may_pull() during input, so skb_tail_pointer() is the correct bound.

Use ipv6_get_exthdr_len() at all non-AH call sites: the five standalone cmsg blocks (HbH, 2292HbH, 2292DSTOPTS x2, 2292RTHDR) and the three standard cases in the extension-header walk loop (DSTOPTS, ROUTING, default). AH retains an inline bounds check because its length formula differs ((ptr[1]+2)<<2).

The walk loop also gets a pre-read bounds check at the top to validate ptr before any case accesses ptr[0] or ptr[1].

When the walk loop detects a corrupted header, return from the function instead of continuing to process later socket options.

---
 net/ipv6/datagram.c |   54 ++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 46 insertions(+), 8 deletions(-)
net/ipv6/datagram.c +46 -8
@@ -616,6 +616,18 @@ void ip6_datagram_recv_common_ctl(struct
 	}
 }
 
+static u16 ipv6_get_exthdr_len(const struct sk_buff *skb, const u8 *ptr)
+{
+	u16 len;
+
+	if (ptr + 2 > skb_tail_pointer(skb))
+		return 0;
+
+	len = (ptr[1] + 1) << 3;
+
+	return (len <= skb_tail_pointer(skb) - ptr) ? len : 0;
+}
+
 void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 				    struct sk_buff *skb)
 {
@@ -642,7 +654,10 @@ void ip6_datagram_recv_specific_ctl(stru
 	/* HbH is allowed only once */
 	if (np->rxopt.bits.hopopts && (opt->flags & IP6SKB_HOPBYHOP)) {
 		u8 *ptr = nh + sizeof(struct ipv6hdr);
-		put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr);
+		u16 len = ipv6_get_exthdr_len(skb, ptr);
+
+		if (len)
+			put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, len, ptr);
 	}
 
 	if (opt->lastopt &&
@@ -663,26 +678,37 @@ void ip6_datagram_recv_specific_ctl(stru
 			unsigned int len;
 			u8 *ptr = nh + off;
 
+			if (ptr + 2 > skb_tail_pointer(skb))
+				return;
+
 			switch (nexthdr) {
 			case IPPROTO_DSTOPTS:
 				nexthdr = ptr[0];
-				len = (ptr[1] + 1) << 3;
+				len = ipv6_get_exthdr_len(skb, ptr);
+				if (!len)
+					return;
 				if (np->rxopt.bits.dstopts)
 					put_cmsg(msg, SOL_IPV6, IPV6_DSTOPTS, len, ptr);
 				break;
 			case IPPROTO_ROUTING:
 				nexthdr = ptr[0];
-				len = (ptr[1] + 1) << 3;
+				len = ipv6_get_exthdr_len(skb, ptr);
+				if (!len)
+					return;
 				if (np->rxopt.bits.srcrt)
 					put_cmsg(msg, SOL_IPV6, IPV6_RTHDR, len, ptr);
 				break;
 			case IPPROTO_AH:
 				nexthdr = ptr[0];
 				len = (ptr[1] + 2) << 2;
+				if (ptr + len > skb_tail_pointer(skb))
+					return;
 				break;
 			default:
 				nexthdr = ptr[0];
-				len = (ptr[1] + 1) << 3;
+				len = ipv6_get_exthdr_len(skb, ptr);
+				if (!len)
+					return;
 				break;
 			}
 
@@ -704,19 +730,31 @@ void ip6_datagram_recv_specific_ctl(stru
 	}
 	if (np->rxopt.bits.ohopopts && (opt->flags & IP6SKB_HOPBYHOP)) {
 		u8 *ptr = nh + sizeof(struct ipv6hdr);
-		put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr);
+		u16 len = ipv6_get_exthdr_len(skb, ptr);
+
+		if (len)
+			put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, len, ptr);
 	}
 	if (np->rxopt.bits.odstopts && opt->dst0) {
 		u8 *ptr = nh + opt->dst0;
-		put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr);
+		u16 len = ipv6_get_exthdr_len(skb, ptr);
+
+		if (len)
+			put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, len, ptr);
 	}
 	if (np->rxopt.bits.osrcrt && opt->srcrt) {
 		struct ipv6_rt_hdr *rthdr = (struct ipv6_rt_hdr *)(nh + opt->srcrt);
-		put_cmsg(msg, SOL_IPV6, IPV6_2292RTHDR, (rthdr->hdrlen+1) << 3, rthdr);
+		u16 len = ipv6_get_exthdr_len(skb, (u8 *)rthdr);
+
+		if (len)
+			put_cmsg(msg, SOL_IPV6, IPV6_2292RTHDR, len, rthdr);
 	}
 	if (np->rxopt.bits.odstopts && opt->dst1) {
 		u8 *ptr = nh + opt->dst1;
-		put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr);
+		u16 len = ipv6_get_exthdr_len(skb, ptr);
+
+		if (len)
+			put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, len, ptr);
 	}
 	if (np->rxopt.bits.rxorigdstaddr) {
 		struct sockaddr_in6 sin6;
author maintainer
#136 lore raw

PATCH 126/522 xfrm: input: hold netns during deferred transport reinjection

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Zhengchuan Liang <[email protected]>

commit c16f74dc1d75d0e2e7670076d5375deda110ebeb upstream.

Transport-mode reinjection stores a struct net pointer in skb->cb and uses it later from xfrm_trans_reinject(). That pointer must stay valid until the deferred callback runs.

Take a netns reference when queueing deferred reinjection work and drop it after the callback completes. Use maybe_get_net() so the queueing path does not revive a namespace that is already being torn down.

This keeps the existing workqueue design and fixes the netns lifetime handling in one place for all users of xfrm_trans_queue_net().

Fixes 7b3801927e52 ("xfrm: introduce xfrm_trans_queue_net")
Assisted-by Codex:gpt-5.4
---
 net/xfrm/xfrm_input.c |   16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)
net/xfrm/xfrm_input.c +12 -4
@@ -759,9 +759,12 @@ static void xfrm_trans_reinject(struct w
 	spin_unlock_bh(&trans->queue_lock);
 
 	local_bh_disable();
-	while ((skb = __skb_dequeue(&queue)))
-		XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net,
-					       NULL, skb);
+	while ((skb = __skb_dequeue(&queue))) {
+		struct net *net = XFRM_TRANS_SKB_CB(skb)->net;
+
+		XFRM_TRANS_SKB_CB(skb)->finish(net, NULL, skb);
+		put_net(net);
+	}
 	local_bh_enable();
 }
 
@@ -770,6 +773,7 @@ int xfrm_trans_queue_net(struct net *net
 				       struct sk_buff *))
 {
 	struct xfrm_trans_tasklet *trans;
+	struct net *hold_net;
 
 	trans = this_cpu_ptr(&xfrm_trans_tasklet);
 
@@ -778,8 +782,12 @@ int xfrm_trans_queue_net(struct net *net
 
 	BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb));
 
+	hold_net = maybe_get_net(net);
+	if (!hold_net)
+		return -ENODEV;
+
 	XFRM_TRANS_SKB_CB(skb)->finish = finish;
-	XFRM_TRANS_SKB_CB(skb)->net = net;
+	XFRM_TRANS_SKB_CB(skb)->net = hold_net;
 	spin_lock_bh(&trans->queue_lock);
 	__skb_queue_tail(&trans->queue, skb);
 	spin_unlock_bh(&trans->queue_lock);
author maintainer
#137 lore raw

PATCH 127/522 ip6: vti: Use ip6_tnl.net in vti6_changelink().

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Kuniyuki Iwashima <[email protected]>

commit 11b326fb0a374f4654f9be22d0f0f7abd9f7d3fe upstream.

ip netns add ns1
ip netns add ns2
ip -n ns1 link add vti6_test type vti6 remote ::1 local ::2 key 7 ip -n ns1 link set vti6_test netns ns2
ip -n ns2 link set vti6_test type vti6 remote ::3 local ::4 key 9 ip netns del ns2
ip netns del ns1

[  132.495484] ------------[ cut here ]------------
[  132.497609] kernel BUG at net/core/dev.c:12376!

Commit 61220ab34948 ("vti6: Enable namespace changing") dropped NETIF_F_NETNS_LOCAL from vti6 devices. A vti6 tunnel can then move through IFLA_NET_NS_FD. After the move dev_net(dev) points at the new netns while t->net stays at the creation netns.

vti6_changelink() and vti6_update() still use dev_net(dev) and dev_net(t->dev). They unlink from one per netns hash and relink into another. The creation netns is left with a stale entry. cleanup_net() of that netns later walks freed memory.

Reachable from an unprivileged user namespace (unshare --user --map-root-user --net). Cross tenant scope on container hosts.

---
 net/ipv6/ip6_vti.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)
net/ipv6/ip6_vti.c +7 -5
@@ -728,10 +728,11 @@ vti6_tnl_change(struct ip6_tnl *t, const
 static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p,
 		       bool keep_mtu)
 {
-	struct net *net = dev_net(t->dev);
-	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+	struct net *net = t->net;
+	struct vti6_net *ip6n;
 	int err;
 
+	ip6n = net_generic(net, vti6_net_id);
 	vti6_tnl_unlink(ip6n, t);
 	synchronize_net();
 	err = vti6_tnl_change(t, p, keep_mtu);
@@ -1045,11 +1046,12 @@ static int vti6_changelink(struct net_de
 			   struct nlattr *data[],
 			   struct netlink_ext_ack *extack)
 {
-	struct ip6_tnl *t;
+	struct ip6_tnl *t = netdev_priv(dev);
+	struct net *net = t->net;
 	struct __ip6_tnl_parm p;
-	struct net *net = dev_net(dev);
-	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+	struct vti6_net *ip6n;
 
+	ip6n = net_generic(net, vti6_net_id);
 	if (dev == ip6n->fb_tnl_dev)
 		return -EINVAL;
 
author maintainer
#138 lore raw

PATCH 128/522 HID: wacom: Fix OOB write in wacom_hid_set_device_mode()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Lee Jones <[email protected]>

commit c0a8899e02ddebd51e2589835182c239c2e224ae upstream.

wacom_hid_set_device_mode() currently assumes that the HID_DG_INPUTMODE usage is always located in the first field (field[0]) of the feature report. However, a device can specify HID_DG_INPUTMODE in a different field.

If HID_DG_INPUTMODE is in a field other than the first one and the first field has a report_count smaller than the usage_index of HID_DG_INPUTMODE, this leads to an out-of-bounds write to r->field[0]->value.

Fix this by storing the field index of HID_DG_INPUTMODE in 'struct hid_data' during feature mapping. In wacom_hid_set_device_mode(), use this stored field index to access the correct field and add bounds checks to ensure both the field index and the value index are within valid ranges before writing.

Fixes 5ae6e89f7409 ("HID: wacom: implement the finger part of the HID generic handling")
---
 drivers/hid/wacom_sys.c |   13 ++++++++++---
 drivers/hid/wacom_wac.h |    1 +
 2 files changed, 11 insertions(+), 3 deletions(-)
drivers/hid/wacom_sys.c +10 -3
@@ -341,6 +341,7 @@ static void wacom_feature_mapping(struct
 
 		hid_data->inputmode = field->report->id;
 		hid_data->inputmode_index = usage->usage_index;
+		hid_data->inputmode_field_index = field->index;
 		break;
 
 	case HID_UP_DIGITIZER:
@@ -556,9 +557,14 @@ static int wacom_hid_set_device_mode(str
 
 	re = &(hdev->report_enum[HID_FEATURE_REPORT]);
 	r = re->report_id_hash[hid_data->inputmode];
-	if (r) {
-		r->field[0]->value[hid_data->inputmode_index] = 2;
-		hid_hw_request(hdev, r, HID_REQ_SET_REPORT);
+	if (r && hid_data->inputmode_field_index >= 0 &&
+	    hid_data->inputmode_field_index < r->maxfield) {
+		struct hid_field *field = r->field[hid_data->inputmode_field_index];
+
+		if (field && hid_data->inputmode_index < field->report_count) {
+			field->value[hid_data->inputmode_index] = 2;
+			hid_hw_request(hdev, r, HID_REQ_SET_REPORT);
+		}
 	}
 	return 0;
 }
@@ -2813,6 +2819,7 @@ static int wacom_probe(struct hid_device
 		return error;
 
 	wacom_wac->hid_data.inputmode = -1;
+	wacom_wac->hid_data.inputmode_field_index = -1;
 	wacom_wac->mode_report = -1;
 
 	if (hid_is_usb(hdev)) {
drivers/hid/wacom_wac.h +1 -0
@@ -297,6 +297,7 @@ struct wacom_shared {
 struct hid_data {
 	__s16 inputmode;	/* InputMode HID feature, -1 if non-existent */
 	__s16 inputmode_index;	/* InputMode HID feature index in the report */
+	__s16 inputmode_field_index; /* InputMode HID feature field index in the report */
 	bool sense_state;
 	bool inrange_state;
 	bool invert_state;
author maintainer
#139 lore raw

PATCH 129/522 iommu, debugobjects: avoid gcc-16.1 section mismatch warnings

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Arnd Bergmann <[email protected]>

commit 4c9ad387aa2d6785299722e54224d34764edaeb3 upstream.

gcc-16 has gained some more advanced inter-procedual optimization techniques that enable it to inline the dummy_tlb_add_page() and dummy_tlb_flush() function pointers into a specialized version of __arm_v7s_unmap:

WARNING: modpost: vmlinux: section mismatch in reference: __arm_v7s_unmap+0x2cc (section: .text) -> dummy_tlb_add_page (section: .init.text)
ERROR: modpost: Section mismatches detected.

Quoted 1 line

From what I can tell, the transformation is correct, as this is only

called when __arm_v7s_unmap() is called from arm_v7s_do_selftests(), which is also __init. Since __arm_v7s_unmap() however is not __init, gcc cannot inline the inner function calls directly.

In debug_objects_selftest(), the same thing happens. Both the caller and the leaf function are __init, but the IPA pulls it into a non-init one:

WARNING: modpost: vmlinux: section mismatch in reference: lookup_object_or_alloc+0x7c (section: .text.lookup_object_or_alloc) -> is_static_object (section: .init.text)

Marking the affected functions as not "__init" would reliably avoid this issue but is not a good solution because it removes an otherwise correct annotation. I tried marking the functions as 'noinline', but that ended up not covering all the affected configurations.

With some more experimenting, I found that marking these functions as __attribute__((noipa)) is both logical and reliable.

In order to keep the syntax readable, add a custom macro for this in include/linux/compiler_attributes.h next to other related macros and use it to annotate both files.

---
 drivers/iommu/io-pgtable-arm-v7s.c  |   18 ++++++++++++------
 include/linux/compiler_attributes.h |   11 +++++++++++
 lib/debugobjects.c                  |    2 +-
 3 files changed, 24 insertions(+), 7 deletions(-)
drivers/iommu/io-pgtable-arm-v7s.c +12 -6
@@ -909,21 +909,27 @@ struct io_pgtable_init_fns io_pgtable_ar
 
 static struct io_pgtable_cfg *cfg_cookie __initdata;
 
-static void __init dummy_tlb_flush_all(void *cookie)
+/*
+ * __noipa prevents gcc from turning indirect iommu_flush_ops calls
+ * into direct calls from a specialized __arm_v7s_unmap() that triggers
+ * a build time section mismatch assertion.
+ */
+static __noipa void __init dummy_tlb_flush_all(void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 }
 
-static void __init dummy_tlb_flush(unsigned long iova, size_t size,
-				   size_t granule, void *cookie)
+static __noipa void __init dummy_tlb_flush(unsigned long iova, size_t size,
+					   size_t granule, void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
 }
 
-static void __init dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
-				      unsigned long iova, size_t granule,
-				      void *cookie)
+static __noipa void __init dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
+					      unsigned long iova,
+					      size_t granule,
+					      void *cookie)
 {
 	dummy_tlb_flush(iova, granule, granule, cookie);
 }
include/linux/compiler_attributes.h +11 -0
@@ -385,6 +385,17 @@
 #endif
 
 /*
+ * Optional: not supported by clang
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Attributes.html#index-noipa
+ */
+#if __has_attribute(noipa)
+# define __noipa __attribute__((noipa))
+#else
+# define __noipa
+#endif
+
+/*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute
  */
lib/debugobjects.c +1 -1
@@ -1065,7 +1065,7 @@ struct self_test {
 
 static __initconst const struct debug_obj_descr descr_type_test;
 
-static bool __init is_static_object(void *addr)
+static __noipa bool __init is_static_object(void *addr)
 {
 	struct self_test *obj = addr;
 
author maintainer
#140 lore raw

PATCH 130/522 nfc: hci: fix out-of-bounds read in HCP header parsing

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Ashutosh Desai <[email protected]>

commit f040e590c035bfd9553fe79ee9585caf1b14d67b upstream.

Both nfc_hci_recv_from_llc() and nci_hci_data_received_cb() read packet->header from skb->data at function entry without first checking that the buffer holds at least one byte. A malicious NFC peer can send a 0-byte HCP frame that passes through the SHDLC layer and reaches these functions, causing an out-of-bounds heap read of packet->header. The same 0-byte frame, if queued as a non-final fragment, also causes the reassembly loop to underflow msg_len to UINT_MAX, triggering skb_over_panic() when the reassembled skb is written.

Fix this by adding a pskb_may_pull() check at the entry of each function before packet->header is first accessed. The existing pskb_may_pull() checks before the reassembled hcp_skb is cast to struct hcp_packet remain in place to guard the 2-byte HCP message header.

Fixes 8b8d2e08bf0d ("NFC: HCI support")
Fixes 11f54f228643 ("NFC: nci: Add HCI over NCI protocol support")
---
 net/nfc/hci/core.c |   10 ++++++++++
 net/nfc/nci/hci.c  |   10 ++++++++++
 2 files changed, 20 insertions(+)
net/nfc/hci/core.c +10 -0
@@ -861,6 +861,11 @@ static void nfc_hci_recv_from_llc(struct
 	struct sk_buff *frag_skb;
 	int msg_len;
 
+	if (!pskb_may_pull(skb, NFC_HCI_HCP_PACKET_HEADER_LEN)) {
+		kfree_skb(skb);
+		return;
+	}
+
 	packet = (struct hcp_packet *)skb->data;
 	if ((packet->header & ~NFC_HCI_FRAGMENT) == 0) {
 		skb_queue_tail(&hdev->rx_hcp_frags, skb);
@@ -904,6 +909,11 @@ static void nfc_hci_recv_from_llc(struct
 	 * unblock waiting cmd context. Otherwise, enqueue to dispatch
 	 * in separate context where handler can also execute command.
 	 */
+	if (!pskb_may_pull(hcp_skb, NFC_HCI_HCP_HEADER_LEN)) {
+		kfree_skb(hcp_skb);
+		return;
+	}
+
 	packet = (struct hcp_packet *)hcp_skb->data;
 	type = HCP_MSG_GET_TYPE(packet->message.header);
 	if (type == NFC_HCI_HCP_RESPONSE) {
net/nfc/nci/hci.c +10 -0
@@ -437,6 +437,11 @@ void nci_hci_data_received_cb(void *cont
 		return;
 	}
 
+	if (!pskb_may_pull(skb, NCI_HCI_HCP_PACKET_HEADER_LEN)) {
+		kfree_skb(skb);
+		return;
+	}
+
 	packet = (struct nci_hcp_packet *)skb->data;
 	if ((packet->header & ~NCI_HCI_FRAGMENT) == 0) {
 		skb_queue_tail(&ndev->hci_dev->rx_hcp_frags, skb);
@@ -480,6 +485,11 @@ void nci_hci_data_received_cb(void *cont
 	 * unblock waiting cmd context. Otherwise, enqueue to dispatch
 	 * in separate context where handler can also execute command.
 	 */
+	if (!pskb_may_pull(hcp_skb, NCI_HCI_HCP_HEADER_LEN)) {
+		kfree_skb(hcp_skb);
+		return;
+	}
+
 	packet = (struct nci_hcp_packet *)hcp_skb->data;
 	type = NCI_HCP_MSG_GET_TYPE(packet->message.header);
 	if (type == NCI_HCI_HCP_RESPONSE) {
author maintainer
#141 lore raw

PATCH 131/522 xfrm: route MIGRATE notifications to callers netns

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Maoyi Xie <[email protected]>

commit 7e2a4f7ca0952820731ef7bdadfc9a9e9d3571b4 upstream.

xfrm_send_migrate() in net/xfrm/xfrm_user.c and pfkey_send_migrate() in net/key/af_key.c both hardcode &init_net for the multicast that announces a successful XFRM_MSG_MIGRATE / SADB_X_MIGRATE.

XFRM_MSG_MIGRATE arrives on a per-netns NETLINK_XFRM socket, and the rest of the xfrm/af_key netlink path was made netns-aware in 2008. The other 14 multicast paths in xfrm_user.c route their event using xs_net(x), xp_net(xp) or sock_net(skb->sk); only the migrate path was missed.

Two consequences of the init_net hardcoding:

1. The notification (selector, old/new endpoint addresses, and the km_address) is delivered to listeners on init_net's XFRMNLGRP_MIGRATE / pfkey BROADCAST_ALL groups rather than on the issuing netns. An IKE daemon running in init_net therefore receives migration notifications originating from any other netns on the host.

2. An IKE daemon running inside a non-init netns and subscribed to its own XFRMNLGRP_MIGRATE / pfkey groups never receives the notification of its own migration. IKEv2 MOBIKE / address-update handling inside a netns is silently broken.

Thread struct net through km_migrate() and the xfrm_mgr.migrate function pointer, drop the &init_net override in xfrm_send_migrate() and pfkey_send_migrate(), and pass the caller's net (already in scope in xfrm_migrate() via sock_net(skb->sk)) all the way down. struct xfrm_mgr is in-tree only and not exported as a stable API, so the function-pointer signature change is internal.

pfkey_broadcast() is already netns-aware via net_generic(net, pfkey_net_id) since the pernet conversion. The five other pfkey_broadcast() callers in af_key.c already pass xs_net(x), sock_net(sk) or a per-netns net, so this only removes the &init_net outlier.

Fixes 5c79de6e79cd ("[XFRM]: User interface for handling XFRM_MSG_MIGRATE")
Cc [email protected] # v5.15+
---
 include/net/xfrm.h     |    3 ++-
 net/key/af_key.c       |    6 +++---
 net/xfrm/xfrm_policy.c |    2 +-
 net/xfrm/xfrm_state.c  |    4 ++--
 net/xfrm/xfrm_user.c   |    5 ++---
 5 files changed, 10 insertions(+), 10 deletions(-)
include/net/xfrm.h +2 -1
@@ -590,6 +590,7 @@ struct xfrm_mgr {
 					   const struct xfrm_migrate *m,
 					   int num_bundles,
 					   const struct xfrm_kmaddress *k,
+					   struct net *net,
 					   const struct xfrm_encap_tmpl *encap);
 	bool			(*is_alive)(const struct km_event *c);
 };
@@ -1692,7 +1693,7 @@ int xfrm_sk_policy_insert(struct sock *s
 #ifdef CONFIG_XFRM_MIGRATE
 int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	       const struct xfrm_migrate *m, int num_bundles,
-	       const struct xfrm_kmaddress *k,
+	       const struct xfrm_kmaddress *k, struct net *net,
 	       const struct xfrm_encap_tmpl *encap);
 struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net,
 						u32 if_id);
net/key/af_key.c +3 -3
@@ -3548,7 +3548,7 @@ static int set_ipsecrequest(struct sk_bu
 #ifdef CONFIG_NET_KEY_MIGRATE
 static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			      const struct xfrm_migrate *m, int num_bundles,
-			      const struct xfrm_kmaddress *k,
+			      const struct xfrm_kmaddress *k, struct net *net,
 			      const struct xfrm_encap_tmpl *encap)
 {
 	int i;
@@ -3653,7 +3653,7 @@ static int pfkey_send_migrate(const stru
 	}
 
 	/* broadcast migrate message to sockets */
-	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net);
+	pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, net);
 
 	return 0;
 
@@ -3664,7 +3664,7 @@ err:
 #else
 static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			      const struct xfrm_migrate *m, int num_bundles,
-			      const struct xfrm_kmaddress *k,
+			      const struct xfrm_kmaddress *k, struct net *net,
 			      const struct xfrm_encap_tmpl *encap)
 {
 	return -ENOPROTOOPT;
net/xfrm/xfrm_policy.c +1 -1
@@ -4492,7 +4492,7 @@ int xfrm_migrate(const struct xfrm_selec
 	}
 
 	/* Stage 5 - announce */
-	km_migrate(sel, dir, type, m, num_migrate, k, encap);
+	km_migrate(sel, dir, type, m, num_migrate, k, net, encap);
 
 	xfrm_pol_put(pol);
 
net/xfrm/xfrm_state.c +2 -2
@@ -2300,7 +2300,7 @@ EXPORT_SYMBOL(km_policy_expired);
 #ifdef CONFIG_XFRM_MIGRATE
 int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 	       const struct xfrm_migrate *m, int num_migrate,
-	       const struct xfrm_kmaddress *k,
+	       const struct xfrm_kmaddress *k, struct net *net,
 	       const struct xfrm_encap_tmpl *encap)
 {
 	int err = -EINVAL;
@@ -2311,7 +2311,7 @@ int km_migrate(const struct xfrm_selecto
 	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
 		if (km->migrate) {
 			ret = km->migrate(sel, dir, type, m, num_migrate, k,
-					  encap);
+					  net, encap);
 			if (!ret)
 				err = ret;
 		}
net/xfrm/xfrm_user.c +2 -3
@@ -2908,10 +2908,9 @@ out_cancel:
 
 static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			     const struct xfrm_migrate *m, int num_migrate,
-			     const struct xfrm_kmaddress *k,
+			     const struct xfrm_kmaddress *k, struct net *net,
 			     const struct xfrm_encap_tmpl *encap)
 {
-	struct net *net = &init_net;
 	struct sk_buff *skb;
 	int err;
 
@@ -2929,7 +2928,7 @@ static int xfrm_send_migrate(const struc
 #else
 static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 			     const struct xfrm_migrate *m, int num_migrate,
-			     const struct xfrm_kmaddress *k,
+			     const struct xfrm_kmaddress *k, struct net *net,
 			     const struct xfrm_encap_tmpl *encap)
 {
 	return -ENOPROTOOPT;
author maintainer
#142 lore raw

PATCH 132/522 xfrm: ah: use skb_to_full_sk in async output callbacks

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Bommarito <[email protected]>

commit 79d8be262377f7112cfa3088dfc4142d5a2533f3 upstream.

When AH output is offloaded to an asynchronous crypto provider (hardware accelerators such as AMD CCP, or a forced-async software shim used for testing), the digest completion fires ah_output_done() / ah6_output_done() on a workqueue. The egress skb at that point may have been originated by a TCP listener sending a SYN-ACK, which sets skb->sk to a request_sock via skb_set_owner_edemux(); it may also have been originated by an inet_timewait_sock retransmit. Neither is a full struct sock, and passing the raw skb->sk to xfrm_output_resume() then forwards a non-full socket through the rest of the xfrm output chain.

xfrm_output_resume() and its downstream consumers expect a full sk where they dereference at all. The natural egress path through ah_output_done() does not crash today because the consumers that read past sock_common are either gated by sk_fullsock() or short-circuit on flags that are clear on a fresh request_sock; an exhaustive walk of the 50 most plausible consumers under sch_fq, dev_queue_xmit, netfilter, tc-egress and cgroup-egress BPF found no current unguarded deref. The bug is still a real type confusion that future consumer changes could turn into a memory-corruption primitive.

This is the same bug class fixed for ESP in commit 1620c88887b1 ("xfrm: Fix the usage of skb->sk"). Apply the analogous fix to
AH: convert skb->sk to a full socket pointer (or NULL) via skb_to_full_sk() before handing it to xfrm_output_resume().

The same async AH callbacks were touched recently for an independent ESN-related ICV layout bug in commit ec54093e6a8f ("xfrm: ah: account for ESN high bits in async callbacks"); the sk type-confusion addressed here is orthogonal. This patch is part of an ongoing audit of the AH callback paths; an ah_output ihl-validation hardening series is also currently under review on netdev.

Reproduced under UML + KASAN + lockdep with a forced-async hmac(sha1) shim that registers at priority 9999 and wraps the sync in-tree hmac-sha1-lib. With the shim loaded, ah_output_done runs on every SYN-ACK egress through a transport-mode AH SA and skb->sk arrives as a request_sock (TCP_NEW_SYN_RECV); after this patch, xfrm_output_resume() receives the listener (the result of sk_to_full_sk()) and consumer derefs land on full-sock fields as intended.

Fixes 9ab1265d5231 ("xfrm: Use actual socket sk instead of skb socket for xfrm_output_resume")
Assisted-by Claude:claude-opus-4-7
---
 net/ipv4/ah4.c |    2 +-
 net/ipv6/ah6.c |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
net/ipv4/ah4.c +1 -1
@@ -141,7 +141,7 @@ static void ah_output_done(struct crypto
 	}
 
 	kfree(AH_SKB_CB(skb)->tmp);
-	xfrm_output_resume(skb->sk, skb, err);
+	xfrm_output_resume(skb_to_full_sk(skb), skb, err);
 }
 
 static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
net/ipv6/ah6.c +1 -1
@@ -335,7 +335,7 @@ static void ah6_output_done(struct crypt
 	ah6_restore_hdrs(top_iph, iph_ext, extlen);
 
 	kfree(AH_SKB_CB(skb)->tmp);
-	xfrm_output_resume(skb->sk, skb, err);
+	xfrm_output_resume(skb_to_full_sk(skb), skb, err);
 }
 
 static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
author maintainer
#143 lore raw

PATCH 133/522 netfilter: conntrack: tcp: do not force CLOSE on invalid-seq RST without direction check

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Hamza Mahfooz <[email protected]>

commit bed6e04be8e6b9133d8b16d5a42d0e0ce674fa9a upstream.

An unintended behavior in the TCP conntrack state machine allows a connection to be forced into the CLOSE state using an RST packet with an invalid sequence number.

Specifically, after a SYN packet is observed, an RST with an invalid SEQ can transition the conntrack entry to TCP_CONNTRACK_CLOSE, regardless of whether the RST corresponds to the expected reply direction. The relevant code path assumes the RST is a response to an outgoing SYN, but does not validate packet direction or ensure that a matching SYN was actually sent in the opposite direction.

As a result, a crafted packet sequence consisting of a SYN followed by an invalid-sequence RST can prematurely terminate an active NAT entry. This makes connection teardown easier than intended.

So, tighten the state transition logic to ensure that RST-triggered CLOSE transitions only occur when the RST is a valid response to a previously observed SYN in the correct direction.

Fixes 9fb9cbb1082d ("[NETFILTER]: Add nf_conntrack subsystem.")
---
 net/netfilter/nf_conntrack_proto_tcp.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
net/netfilter/nf_conntrack_proto_tcp.c +2 -1
@@ -1222,7 +1222,8 @@ int nf_conntrack_tcp_packet(struct nf_co
 			new_state = old_state;
 		}
 		if (((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
-			 && ct->proto.tcp.last_index == TCP_SYN_SET)
+			 && ct->proto.tcp.last_index == TCP_SYN_SET
+			 && ct->proto.tcp.last_dir != dir)
 			|| (!test_bit(IPS_ASSURED_BIT, &ct->status)
 			    && ct->proto.tcp.last_index == TCP_ACK_SET))
 		    && ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
author maintainer
#144 lore raw

PATCH 134/522 ASoC: qcom: q6asm-dai: close stream only when running

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Srinivas Kandagatla <[email protected]>

commit 048c540ee76ded666bda74f9dae1ca3254e0633c upstream.

q6asm_dai_close() and q6asm_dai_compr_free() currently issue CMD_CLOSE whenever prtd->state is non-zero.

After prepare() closes an existing stream, the state is updated to Q6ASM_STREAM_STOPPED. Since this state is also non-zero, the close and free paths can send CMD_CLOSE again for a stream that has already been closed.

Restrict CMD_CLOSE to the Q6ASM_STREAM_RUNNING state so the command is sent only when the ASM stream is still active.

---
 sound/soc/qcom/qdsp6/q6asm-dai.c |   14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
sound/soc/qcom/qdsp6/q6asm-dai.c +7 -7
@@ -456,12 +456,12 @@ static int q6asm_dai_close(struct snd_so
 	struct q6asm_dai_rtd *prtd = runtime->private_data;
 
 	if (prtd->audio_client) {
-		if (prtd->state)
+		if (prtd->state == Q6ASM_STREAM_RUNNING) {
 			q6asm_cmd(prtd->audio_client, prtd->stream_id,
 				  CMD_CLOSE);
-
-		q6asm_unmap_memory_regions(substream->stream,
+			q6asm_unmap_memory_regions(substream->stream,
 					   prtd->audio_client);
+		}
 		q6asm_audio_client_free(prtd->audio_client);
 		prtd->audio_client = NULL;
 	}
@@ -678,7 +678,7 @@ static int q6asm_dai_compr_free(struct s
 	struct snd_soc_pcm_runtime *rtd = stream->private_data;
 
 	if (prtd->audio_client) {
-		if (prtd->state) {
+		if (prtd->state == Q6ASM_STREAM_RUNNING) {
 			q6asm_cmd(prtd->audio_client, prtd->stream_id,
 				  CMD_CLOSE);
 			if (prtd->next_track_stream_id) {
@@ -686,11 +686,11 @@ static int q6asm_dai_compr_free(struct s
 					  prtd->next_track_stream_id,
 					  CMD_CLOSE);
 			}
-		}
 
-		snd_dma_free_pages(&prtd->dma_buffer);
-		q6asm_unmap_memory_regions(stream->direction,
+			q6asm_unmap_memory_regions(stream->direction,
 					   prtd->audio_client);
+		}
+		snd_dma_free_pages(&prtd->dma_buffer);
 		q6asm_audio_client_free(prtd->audio_client);
 		prtd->audio_client = NULL;
 	}
author maintainer
#145 lore raw

PATCH 135/522 ASoC: qcom: q6asm-dai: do not set stream state in event and trigger callbacks

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Srinivas Kandagatla <[email protected]>

commit cee3e63e7106c3c81b2053371fdf14240bfba2fc upstream.

The q6asm-dai stream state is used by prepare() to decide whether an existing stream setup needs to be closed before opening/configuring a new one. Updating the state from trigger or asynchronous DSP callbacks can make that state stale or incorrect relative to the actual setup lifetime.

In particular, setting Q6ASM_STREAM_STOPPED on STOP or EOS completion can make prepare() believe there is no active setup to close, which can result in opening/configuring the same stream more than once.

Keep stream state updates tied to prepare(), where the stream is actually closed and reopened, and stop changing it from trigger and EOS callbacks.

---
 sound/soc/qcom/qdsp6/q6asm-dai.c |    5 -----
 1 file changed, 5 deletions(-)
sound/soc/qcom/qdsp6/q6asm-dai.c +0 -5
@@ -191,7 +191,6 @@ static void event_handler(uint32_t opcod
 				   prtd->pcm_count, 0, 0, 0);
 		break;
 	case ASM_CLIENT_EVENT_CMD_EOS_DONE:
-		prtd->state = Q6ASM_STREAM_STOPPED;
 		break;
 	case ASM_CLIENT_EVENT_DATA_WRITE_DONE: {
 		prtd->pcm_irq_pos += prtd->pcm_count;
@@ -338,7 +337,6 @@ static int q6asm_dai_trigger(struct snd_
 				       0, 0, 0);
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
-		prtd->state = Q6ASM_STREAM_STOPPED;
 		ret = q6asm_cmd_nowait(prtd->audio_client, prtd->stream_id,
 				       CMD_EOS);
 		break;
@@ -554,8 +552,6 @@ static void compress_event_handler(uint3
 			snd_compr_drain_notify(prtd->cstream);
 			prtd->notify_on_drain = false;
 
-		} else {
-			prtd->state = Q6ASM_STREAM_STOPPED;
 		}
 		spin_unlock_irqrestore(&prtd->lock, flags);
 		break;
@@ -1018,7 +1014,6 @@ static int q6asm_dai_compr_trigger(struc
 				       0, 0, 0);
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
-		prtd->state = Q6ASM_STREAM_STOPPED;
 		ret = q6asm_cmd_nowait(prtd->audio_client, prtd->stream_id,
 				       CMD_EOS);
 		break;
author maintainer
#146 lore raw

PATCH 136/522 xfrm: esp: restore combined single-frag length gate

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Jingguo Tan <[email protected]>

commit dfa0d7b0ff1eb6b2c416b8fdb9b4f2cefba57a40 upstream.

The ESP out-of-place fast path appends the trailer in esp_output_head() before esp_output_tail() allocates the destination page frag. The head-side gate currently checks skb->data_len and tailen separately, but the tail code allocates a single destination frag from the combined post-trailer skb->data_len.

Reject the page-frag fast path when the combined aligned length exceeds a page. Otherwise skb_page_frag_refill() may fall back to a single page while the destination sg still spans the combined skb->data_len.

Restore this combined-length page gate for both IPv4 and IPv6.

Fixes 5bd8baab087d ("esp: limit skb_page_frag_refill use to a single page")
---
 net/ipv4/esp4.c |    4 ++--
 net/ipv6/esp6.c |    4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)
net/ipv4/esp4.c +2 -2
@@ -419,8 +419,8 @@ int esp_output_head(struct xfrm_state *x
 			return err;
 	}
 
-	if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
-	    ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
+	if (ALIGN(skb->data_len + tailen, L1_CACHE_BYTES) >
+	    PAGE_SIZE)
 		goto cow;
 
 	if (!skb_cloned(skb)) {
net/ipv6/esp6.c +2 -2
@@ -454,8 +454,8 @@ int esp6_output_head(struct xfrm_state *
 			return err;
 	}
 
-	if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
-	    ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
+	if (ALIGN(skb->data_len + tailen, L1_CACHE_BYTES) >
+	    PAGE_SIZE)
 		goto cow;
 
 	if (!skb_cloned(skb)) {
author maintainer
#147 lore raw

PATCH 137/522 Input: atmel_mxt_ts - fix boundary check in mxt_prepare_cfg_mem

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Dmitry Torokhov <[email protected]>

commit baa0210fb6a9dc3882509a9411b6d284d88fe30e upstream.

When a configuration file provides an object size that is larger than the driver's known mxt_obj_size(object), the driver intends to discard the extra bytes.

The loop iterates using for (i = 0; i < size; i++). Inside the loop, the condition to skip processing extra bytes is:

if (i > mxt_obj_size(object))
continue;

Since i is a 0-based index, the valid indices for the object are 0 through mxt_obj_size(object) - 1.

When i == mxt_obj_size(object), the condition evaluates to false, and the code processes the byte instead of discarding it.

This causes the code to calculate byte_offset = reg + i - cfg->start_ofs and writes the byte there, overwriting exactly one byte of the adjacent instance or object.

Update the boundary check to skip extra bytes correctly by using >=.

Fixes 50a77c658b80 ("Input: atmel_mxt_ts - download device config using firmware loader")
Assisted-by Gemini:gemini-3.1-pro
---
 drivers/input/touchscreen/atmel_mxt_ts.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/input/touchscreen/atmel_mxt_ts.c +1 -1
@@ -1443,7 +1443,7 @@ static int mxt_prepare_cfg_mem(struct mx
 			}
 			cfg->raw_pos += offset;
 
-			if (i > mxt_obj_size(object))
+			if (i >= mxt_obj_size(object))
 				continue;
 
 			byte_offset = reg + i - cfg->start_ofs;
author maintainer
#148 lore raw

PATCH 138/522 Input: synaptics - add LEN2058 to SMBus passlist for ThinkPad E490

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Nicolás Bazaes <[email protected]>

commit 16ca52bc209fa4bf9239cd9e5643e95533476b58 upstream.

The Lenovo ThinkPad E490 (PNP ID: LEN2058) has a Synaptics TM3471-020 touchpad that supports SMBus/RMI4 mode but is not listed in smbus_pnp_ids[]. Without this entry, RMI4 over SMBus is not enabled by default, and the touchpad falls back to PS/2 mode.

Adding LEN2058 to the passlist enables automatic RMI4 detection without requiring the psmouse.synaptics_intertouch parameter, and matches the behavior of similar ThinkPad models already in the list (E480/LEN2054, E580/LEN2055).

Tested on ThinkPad E490 with kernel 7.0.5-zen1 and Arch Linux. RMI4 over SMBus is confirmed working without any kernel parameters.

---
 drivers/input/mouse/synaptics.c |    1 +
 1 file changed, 1 insertion(+)
drivers/input/mouse/synaptics.c +1 -0
@@ -189,6 +189,7 @@ static const char * const smbus_pnp_ids[
 	"LEN2044", /* L470  */
 	"LEN2054", /* E480 */
 	"LEN2055", /* E580 */
+	"LEN2058", /* E490 */
 	"LEN2068", /* T14 Gen 1 */
 	"SYN1221", /* TUXEDO InfinityBook Pro 14 v5 */
 	"SYN3003", /* HP EliteBook 850 G1 */
author maintainer
#149 lore raw

PATCH 139/522 comedi: comedi_test: fix check for valid scan_begin_src in waveform_ai_cmdtest()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Ian Abbott <[email protected]>

commit 542f5248cb481073203e0dadab5bcbd28aeae308 upstream.

Commit 783ddaebd397 ("staging: comedi: comedi_test: support scan_begin_src == TRIG_FOLLOW") neglected to add a test that scan_begin_src has only one bit set. The allowed values are TRIG_FOLLOW and TRIG_TIMER, but the code incorrectly also allows TRIG_FOLLOW | TRIG_TIMER. Add a call to comedi_check_trigger_is_unique() to check that only one trigger source bit is set.

Fixes 783ddaebd397 ("staging: comedi: comedi_test: support scan_begin_src == TRIG_FOLLOW")
Cc stable <[email protected]>
---
 drivers/comedi/drivers/comedi_test.c |    1 +
 1 file changed, 1 insertion(+)
drivers/comedi/drivers/comedi_test.c +1 -0
@@ -271,6 +271,7 @@ static int waveform_ai_cmdtest(struct co
 	/* Step 2a : make sure trigger sources are unique */
 
 	err |= comedi_check_trigger_is_unique(cmd->convert_src);
+	err |= comedi_check_trigger_is_unique(cmd->scan_begin_src);
 	err |= comedi_check_trigger_is_unique(cmd->stop_src);
 
 	/* Step 2b : and mutually compatible */
author maintainer
#150 lore raw

PATCH 140/522 comedi: comedi_test: Fix limiting of convert_arg in waveform_ai_cmdtest()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Ian Abbott <[email protected]>

commit 8a3bee801d420be8a7a0bae4a26547b353b8fe22 upstream.

The function checks and possibly modifies the description of an asynchronous command to be run on the analog input subdevice of a comedi device attached to the "comedi_test" driver, returning 0 if no modifications were required, or a positive value that indicates which step of the checking process it failed on. Step 4 fixes up various argument values for various trigger sources.

There are two bugs in the fixing up of the convert_arg value to keep the scan_begin_arg value within the range of unsigned int when scan_begin_src and convert_src both have the value TRIG_TIMER, which indicates that the corresponding _arg values hold a time period in nanoseconds. The code also uses scan_end_arg which hold the number of "conversions" within each "scan". The goal is to end up with the scan period being less than or equal to the convert period multiplied by the number of conversions per scan. It intends to do that by clamping the convert_arg value to a maximum value of UINT_MAX / scan_end_arg rounded down to a multiple of 1000 (NSEC_PER_USEC).

(The rounding from nanoseconds to microseconds is because the driver is modelling a device that uses a 1 MHz clock for timing. This is partly because that is a more typical timing base for real hardware devices driven by comedi, and partly because the driver used to use struct timeval internally.)

The first bug is that the code checks if scan_begin_arg == TRIG_TIMER when it should be checking if scan_begin_src == TRIG_TIMER. The bugged check will always fail because if scan_begin_src == TRIG_TIMER, then scan_begin_arg will be at least 1000 (NSEC_PER_USEC), otherwise scan_begin_src == TRIG_FOLLOW and scan_begin_arg will be 0. (N.B TRIG_TIMER is defined as 0x10.) The second bug is that is rounding the maximum value down to a multiple of 1000000000 (NSEC_PER_SEC) instead of 1000 (NSEC_PER_USEC), however this bug is not reached due to the first bug. This patch fixes both bugs.

Fixes 783ddaebd397 ("staging: comedi: comedi_test: support scan_begin_src == TRIG_FOLLOW")
Fixes 5afdcad2f818 ("staging: comedi: comedi_test: limit maximum convert_arg")
Cc stable <[email protected]>
---
 drivers/comedi/drivers/comedi_test.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/comedi/drivers/comedi_test.c +2 -2
@@ -322,10 +322,10 @@ static int waveform_ai_cmdtest(struct co
 		arg = min(arg,
 			  rounddown(UINT_MAX, (unsigned int)NSEC_PER_USEC));
 		arg = NSEC_PER_USEC * DIV_ROUND_CLOSEST(arg, NSEC_PER_USEC);
-		if (cmd->scan_begin_arg == TRIG_TIMER) {
+		if (cmd->scan_begin_src == TRIG_TIMER) {
 			/* limit convert_arg to keep scan_begin_arg in range */
 			limit = UINT_MAX / cmd->scan_end_arg;
-			limit = rounddown(limit, (unsigned int)NSEC_PER_SEC);
+			limit = rounddown(limit, (unsigned int)NSEC_PER_USEC);
 			arg = min(arg, limit);
 		}
 		err |= comedi_check_trigger_arg_is(&cmd->convert_arg, arg);
author maintainer
#151 lore raw

PATCH 141/522 counter: Fix refcount leak in counter_alloc() error path

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Guangshuo Li <[email protected]>

commit d9eeb0ea0d2de658663bfaa9c26eccdd8fd64440 upstream.

After device_initialize(), the lifetime of the embedded struct device is expected to be managed through the device core reference counting.

In counter_alloc(), if dev_set_name() fails after device_initialize(), the error path removes the chrdev, frees the ID, and frees the backing allocation directly instead of releasing the device reference with put_device(). This bypasses the normal device lifetime rules and may leave the reference count of the embedded struct device unbalanced, resulting in a refcount leak.

The issue was identified by a static analysis tool I developed and confirmed by manual review.

Fix this by using put_device() in the dev_set_name() failure path and let counter_device_release() handle the final cleanup.

---
 drivers/counter/counter-core.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/counter/counter-core.c +2 -1
@@ -123,7 +123,8 @@ struct counter_device *counter_alloc(siz
 
 err_dev_set_name:
 
-	counter_chrdev_remove(counter);
+	put_device(dev);
+	return NULL;
 err_chrdev_add:
 
 	ida_free(&counter_ida, dev->id);
author maintainer
#152 lore raw

PATCH 142/522 tty: serial: pch_uart: add check for dma_alloc_coherent()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Zhaoyang Yu <[email protected]>

commit 6fe472c1bbbe238e91141f7cabc1226e96a60d43 upstream.

Add a check for dma_alloc_coherent() failure to prevent a potential NULL pointer dereference in dma_handle_rx(). Properly release DMA channels and the PCI device reference using a goto ladder if the allocation fails.

---
 drivers/tty/serial/pch_uart.c |   19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)
drivers/tty/serial/pch_uart.c +13 -6
@@ -694,8 +694,7 @@ static void pch_request_dma(struct uart_
 	if (!chan) {
 		dev_err(priv->port.dev, "%s:dma_request_channel FAILS(Tx)\n",
 			__func__);
-		pci_dev_put(dma_dev);
-		return;
+		goto err_pci_get;
 	}
 	priv->chan_tx = chan;
 
@@ -709,18 +708,26 @@ static void pch_request_dma(struct uart_
 	if (!chan) {
 		dev_err(priv->port.dev, "%s:dma_request_channel FAILS(Rx)\n",
 			__func__);
-		dma_release_channel(priv->chan_tx);
-		priv->chan_tx = NULL;
-		pci_dev_put(dma_dev);
-		return;
+		goto err_req_tx;
 	}
 
 	/* Get Consistent memory for DMA */
 	priv->rx_buf_virt = dma_alloc_coherent(port->dev, port->fifosize,
 				    &priv->rx_buf_dma, GFP_KERNEL);
+	if (!priv->rx_buf_virt)
+		goto err_req_rx;
 	priv->chan_rx = chan;
 
 	pci_dev_put(dma_dev);
+	return;
+
+err_req_rx:
+	dma_release_channel(chan);
+err_req_tx:
+	dma_release_channel(priv->chan_tx);
+	priv->chan_tx = NULL;
+err_pci_get:
+	pci_dev_put(dma_dev);
 }
 
 static void pch_dma_rx_complete(void *arg)
author maintainer
#153 lore raw

PATCH 143/522 usb: chipidea: core: convert ci_role_switch to local variable

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Xu Yang <[email protected]>

commit 8f6aa392653e52a45858cff5c063df550028836b upstream.

When a system contains multiple USB controllers, the global ci_role_switch variable may be overwritten by subsequent driver initialization code.

This can cause issues in the following cases:
- The 2nd ci_hdrc_probe() sees ci_role_switch.fwnode as non-NULL even though the "usb-role-switch" property is not present for the controller.
- When the ci_hdrc device is unbound and bound again, ci_role_switch fwnode will not be reassigned, and the old value will be used instead.

Convert ci_role_switch to a local variable to fix these issues.

Fixes 05559f10ed79 ("usb: chipidea: add role switch class support")
Cc stable <[email protected]>
---
 drivers/usb/chipidea/core.c |   16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)
drivers/usb/chipidea/core.c +6 -10
@@ -661,12 +661,6 @@ static int ci_usb_role_switch_set(struct
 	return 0;
 }
 
-static struct usb_role_switch_desc ci_role_switch = {
-	.set = ci_usb_role_switch_set,
-	.get = ci_usb_role_switch_get,
-	.allow_userspace_control = true,
-};
-
 static int ci_get_platdata(struct device *dev,
 		struct ci_hdrc_platform_data *platdata)
 {
@@ -793,9 +787,6 @@ static int ci_get_platdata(struct device
 			cable->connected = false;
 	}
 
-	if (device_property_read_bool(dev, "usb-role-switch"))
-		ci_role_switch.fwnode = dev->fwnode;
-
 	platdata->pctl = devm_pinctrl_get(dev);
 	if (!IS_ERR(platdata->pctl)) {
 		struct pinctrl_state *p;
@@ -1016,6 +1007,7 @@ ATTRIBUTE_GROUPS(ci);
 
 static int ci_hdrc_probe(struct platform_device *pdev)
 {
+	struct usb_role_switch_desc ci_role_switch = {};
 	struct device	*dev = &pdev->dev;
 	struct ci_hdrc	*ci;
 	struct resource	*res;
@@ -1159,7 +1151,11 @@ static int ci_hdrc_probe(struct platform
 		}
 	}
 
-	if (ci_role_switch.fwnode) {
+	if (device_property_read_bool(dev, "usb-role-switch")) {
+		ci_role_switch.set = ci_usb_role_switch_set;
+		ci_role_switch.get = ci_usb_role_switch_get;
+		ci_role_switch.allow_userspace_control = true;
+		ci_role_switch.fwnode = dev_fwnode(dev);
 		ci_role_switch.driver_data = ci;
 		ci->role_switch = usb_role_switch_register(dev,
 					&ci_role_switch);
author maintainer
#154 lore raw

PATCH 144/522 usb: core: Fix up Interrupt IN endpoints with bogus wBytesPerInterval

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Michal Pecio <[email protected]>

commit 727d045d064b7c9a24db3bce9c0485a382cb768b upstream.

Tao Xue found that some common devices violate USB 3.x section 9.6.7 by reporting wBytesPerInterval lower than the size of packets they actually send. I confirmed that AX88179 may set it to 0 and RTL8153 CDC configuration sets it to 8 but sends both 8 and 16 byte packets:

S Ii:11:007:3 -115:128 16 <
C Ii:11:007:3 0:128 8 = a1000000 01000000
S Ii:11:007:3 -115:128 16 <
C Ii:11:007:3 0:128 16 = a12a0000 01000800 00000000 00000000

Most xHCI host controllers neglect interrupt bandwidth reservations and let such devices exceed theirs, some fail the URB with EOVERFLOW.

Assume that wBytesPerInterval lower than wMaxPacketSize is bogus and increase it to the worst case maximum on interrupt IN endpoints. This solves xHCI problems and appears to have no other effect. Interrupt transfers are not limited to one interval and drivers submit URBs of class defined size without looking at wBytesPerInterval. Any multi- interval transfer is considered terminated by a packet shorter than wMaxPacketSize regardless of wBytesPerInterval - see USB3 8.10.3.

Stay in spec on OUT endpoints and isochronous. No buggy devices are known and we don't want to risk sending more data than the device is prepared to handle or confusing isoc drivers regarding altsetting capacities guaranteed by the device itself. And don't complain when wMaxPacketSize <= wBytesPerInterval < wMaxPacketSize * (bMaxBurst+1) because enabling this seems to be the exact goal of the spec.

---
 drivers/usb/core/config.c |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)
drivers/usb/core/config.c +8 -1
@@ -165,7 +165,14 @@ static void usb_parse_ss_endpoint_compan
 			(desc->bMaxBurst + 1);
 	else
 		max_tx = 999999;
-	if (le16_to_cpu(desc->wBytesPerInterval) > max_tx) {
+	/*
+	 * wBytesPerInterval > max_tx is bogus, but USB3 spec doesn't forbid the opposite.
+	 * Experience shows that wBytesPerInterval < wMaxPacketSize on common interrupt IN
+	 * endpoints is usually bogus too, and recent HCs enforce interrupt BW limits.
+	 */
+	if (le16_to_cpu(desc->wBytesPerInterval) > max_tx ||
+	    (le16_to_cpu(desc->wBytesPerInterval) < usb_endpoint_maxp(&ep->desc) &&
+	     usb_endpoint_is_int_in(&ep->desc))) {
 		dev_notice(ddev, "%s endpoint with wBytesPerInterval of %d in "
 				"config %d interface %d altsetting %d ep %d: "
 				"setting to %d\n",
author maintainer
#155 lore raw

PATCH 145/522 USB: quirks: add NO_LPM for Lenovo ThinkPad USB-C Dock Gen2 hub controllers

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Stephen J. Fuhry <[email protected]>

commit 9ddb9c0deca48d2c2a22ebf4d2f35c925a520328 upstream.

The Lenovo ThinkPad USB-C Dock Gen2 (17ef:a391, 17ef:a392) hub controllers exhibit link instability when USB Link Power Management is enabled, similar to the dock's Ethernet adapter (17ef:a387) which already carries USB_QUIRK_NO_LPM.

When the dock reconnects after a transient disconnect, the hub controllers enter LPM states between re-enumeration retries, causing repeated disconnect/reconnect cycles lasting up to two minutes. Disabling LPM for these devices restores stable enumeration.

---
 drivers/usb/core/quirks.c |    4 ++++
 1 file changed, 4 insertions(+)
drivers/usb/core/quirks.c +4 -0
@@ -511,6 +511,10 @@ static const struct usb_device_id usb_qu
 	/* Lenovo ThinkPad USB-C Dock Gen2 Ethernet (RTL8153 GigE) */
 	{ USB_DEVICE(0x17ef, 0xa387), .driver_info = USB_QUIRK_NO_LPM },
 
+	/* Lenovo ThinkPad USB-C Dock Gen2 USB 3.1 and USB 2.0 hub controllers */
+	{ USB_DEVICE(0x17ef, 0xa391), .driver_info = USB_QUIRK_NO_LPM },
+	{ USB_DEVICE(0x17ef, 0xa392), .driver_info = USB_QUIRK_NO_LPM },
+
 	/* BUILDWIN Photo Frame */
 	{ USB_DEVICE(0x1908, 0x1315), .driver_info =
 			USB_QUIRK_HONOR_BNUMINTERFACES },
author maintainer
#156 lore raw

PATCH 146/522 usb: storage: Add quirks for PNY Elite Portable SSD

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Sam Burkels <[email protected]>

commit b53ebb811e00be50a779ce4e7aee604178b4a825 upstream.

The PNY Elite Portable SSD (USB ID 154b:f009) is a sibling of the already-quirked PNY Pro Elite SSDs (154b:f00b and 154b:f00d). Like its siblings, it uses a Phison-based USB-SATA bridge that exhibits firmware bugs when bound to the uas driver.

Without quirks, the device fails to complete READ CAPACITY commands when accessed over UAS on a SuperSpeed (USB 3) port. The device enumerates and reports as a SCSI direct-access device, but reports zero logical blocks and never finishes spin-up:

usb 2-3: new SuperSpeed USB device number 8 using xhci_hcd usb 2-3: New USB device found, idVendor=154b, idProduct=f009 usb 2-3: Product: PNY ELITE PSSD
usb 2-3: Manufacturer: PNY
scsi host0: uas
scsi 0:0:0:0: Direct-Access PNY PNY ELITE PSSD 0
sd 0:0:0:0: [sda] Spinning up disk...
[...10+ seconds of polling, no progress...]
sd 0:0:0:0: [sda] Read Capacity(16) failed: hostbyte=DID_ERROR sd 0:0:0:0: [sda] Read Capacity(10) failed: hostbyte=DID_ERROR sd 0:0:0:0: [sda] 0 512-byte logical blocks: (0 B/0 B)

Tested each individual quirk to find the minimum that fixes this:
- US_FL_NO_ATA_1X alone: device hangs on spin-up
- US_FL_NO_REPORT_OPCODES alone: works on USB 2.0, hangs on USB 3.0
- US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES: works on both

With both quirks the device enumerates correctly while still using the uas driver, and delivers full UAS throughput (~281 MB/s sequential read on a USB 3.0 Gen 1 port).

The existing PNY Pro Elite entries (f00b, f00d) only set NO_ATA_1X, but this device additionally chokes on REPORT OPCODES under SuperSpeed.

---
 drivers/usb/storage/unusual_uas.h |    7 +++++++
 1 file changed, 7 insertions(+)
drivers/usb/storage/unusual_uas.h +7 -0
@@ -132,6 +132,13 @@ UNUSUAL_DEV(0x152d, 0x0583, 0x0000, 0x99
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_REPORT_OPCODES),
 
+/* Reported-by: Sam Burkels <[email protected]> */
+UNUSUAL_DEV(0x154b, 0xf009, 0x0000, 0x9999,
+		"PNY",
+		"PNY ELITE PSSD",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES),
+
 /* Reported-by: Thinh Nguyen <[email protected]> */
 UNUSUAL_DEV(0x154b, 0xf00b, 0x0000, 0x9999,
 		"PNY",
author maintainer
#157 lore raw

PATCH 147/522 usbip: vudc: Fix use after free bug in vudc_remove due to race condition

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Bommarito <[email protected]>

commit d96209626a29ea64666be98c30b30ac82e5f1be6 upstream.

This patch follows up Zheng Wang's 2023 report of a use-after-free in vudc_remove(). The original thread stalled on Shuah Khan's request for runtime testing of the unplug/unbind path. This patch supplies that testing and keeps Zheng's original fix shape.

In vudc_probe(), v_init_timer() binds udc->tr_timer.timer to v_timer(). usbip_sockfd_store() starts the timer via v_start_timer()/v_kick_timer(). vudc_remove() can then free the containing struct vudc while the timer is still pending or executing.

KASAN confirms the race on an unpatched x86_64 QEMU guest with CONFIG_KASAN=y, CONFIG_USBIP_VUDC=y, CONFIG_USB_ZERO=y, and a tight loop that repeatedly writes a socket fd to usbip_sockfd, closes the socket pair, and unbinds/rebinds usbip-vudc.0:

  BUG: KASAN: slab-use-after-free in __run_timer_base.part.0+0x8ba/0x8e0
  Write of size 8 at addr ffff888001b80740 by task trigger_and_unb/239
  Allocated by task 239:
    vudc_probe+0x4d/0xaa0
  Freed by task 239:
    kfree+0x18f/0x520
    device_release_driver_internal+0x388/0x540
    unbind_store+0xd9/0x100

This lands in the timer core rather than v_timer() itself because the embedded timer_list is being walked after its containing struct vudc has already been freed. The underlying lifetime bug is the same one Zheng reported.

With v_stop_timer() called from vudc_remove() and the timer deleted synchronously, the same harness completed 5000 bind/unbind iterations with no KASAN report.

---
 drivers/usb/usbip/vudc_dev.c      |    1 +
 drivers/usb/usbip/vudc_transfer.c |    3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)
drivers/usb/usbip/vudc_dev.c +1 -0
@@ -633,6 +633,7 @@ int vudc_remove(struct platform_device *
 {
 	struct vudc *udc = platform_get_drvdata(pdev);
 
+	v_stop_timer(udc);
 	usb_del_gadget_udc(&udc->gadget);
 	cleanup_vudc_hw(udc);
 	kfree(udc);
drivers/usb/usbip/vudc_transfer.c +2 -1
@@ -490,7 +490,8 @@ void v_stop_timer(struct vudc *udc)
 {
 	struct transfer_timer *t = &udc->tr_timer;
 
-	/* timer itself will take care of stopping */
+	/* Delete the timer synchronously before teardown frees udc. */
 	dev_dbg(&udc->pdev->dev, "timer stop");
+	timer_delete_sync(&t->timer);
 	t->state = VUDC_TR_STOPPED;
 }
author maintainer
#158 lore raw

PATCH 148/522 usb: usbtmc: check URB actual_length for interrupt-IN notifications

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Heitor Alves de Siqueira <[email protected]>

commit 52f2ad3f7e5eb3b5908e1d685d4342519dc9cfcd upstream.

USBTMC devices can use an optional interrupt endpoint for notification messages. These typically contain two-byte headers indicating the payload format, but the driver does not check if these headers are present before accessing the data buffers. In cases where the URB actual_length is not enough to fit these headers, the driver will either cause an out-of-bounds read, or consume stale leftover data from a previous notification.

Fix by checking if actual_data contains enough bytes for the headers, otherwise resubmit URB to the interrupt endpoint.

---
 drivers/usb/class/usbtmc.c |    8 ++++++++
 1 file changed, 8 insertions(+)
drivers/usb/class/usbtmc.c +8 -0
@@ -2310,6 +2310,14 @@ static void usbtmc_interrupt(struct urb
 
 	switch (status) {
 	case 0: /* SUCCESS */
+		/* ensure at least two bytes of headers were transferred */
+		if (urb->actual_length < 2) {
+			dev_warn(dev,
+				"actual length %d not sufficient for interrupt headers\n",
+				urb->actual_length);
+			goto exit;
+		}
+
 		/* check for valid STB notification */
 		if (data->iin_buffer[0] > 0x81) {
 			data->bNotify1 = data->iin_buffer[0];
author maintainer
#159 lore raw

PATCH 149/522 usb: usbtmc: reject interrupt endpoints with small wMaxPacketSize

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Heitor Alves de Siqueira <[email protected]>

commit 121d2f682ba912b1427cddca7cf84840f41cc620 upstream.

The USB488 subclass specification requires interrupt wMaxPacketSize to be 0x02, unless the device sends vendor-specific notifications. Endpoints that advertise less than 2 bytes for wMaxPacketSize are unlikely to work with the current driver, as URBs will not have enough space for interrupt headers. Considering that any notification URBs will be ignored by the driver, reject these endpoints early during probe.

---
 drivers/usb/class/usbtmc.c |    6 ++++++
 1 file changed, 6 insertions(+)
drivers/usb/class/usbtmc.c +6 -0
@@ -2444,6 +2444,12 @@ static int usbtmc_probe(struct usb_inter
 		data->iin_ep = int_in->bEndpointAddress;
 		data->iin_wMaxPacketSize = usb_endpoint_maxp(int_in);
 		data->iin_interval = int_in->bInterval;
+		/* wMaxPacketSize should be 0x02 or more as per USB488 Table 22 */
+		if (iface_desc->desc.bInterfaceProtocol == 1 &&
+		    data->iin_wMaxPacketSize < 2) {
+			retcode = -EINVAL;
+			goto err_put;
+		}
 		dev_dbg(&intf->dev, "Found Int in endpoint at %u\n",
 				data->iin_ep);
 	}
author maintainer
#160 lore raw

PATCH 150/522 USB: serial: option: add MeiG SRM813Q

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Jan Volckaert <[email protected]>

commit 7d2b37d3e42d19071b62f4ddbee6e16e905efbf1 upstream.

Add support for the Qualcomm Technology Snapdragon X35-based MeiG SRM813Q module.

The module can be put in different modes via AT commands to enable/disable GPS functionality:

MODEM - PPP mode(2dee:4d63): AT+SER=1,1

If#= 0: RMNET
If#= 1: DIAG/ADB
If#= 2: MODEM
If#= 3: AT

P:  Vendor=2dee ProdID=4d63 Rev=05.15
S:  Manufacturer=MEIG
S:  Product=LTE-A Module
S:  SerialNumber=1bd51f0e
C:  #Ifs= 4 Cfg#= 1 Atr=80 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=03(Int.) MxPS=  10 Ivl=32ms

NMEA mode(2dee:4d64): AT+SER=51,1

If#= 0: RMNET
If#= 1: DIAG/ADB
If#= 2: NMEA
If#= 3: AT

P:  Vendor=2dee ProdID=4d64 Rev=05.15
S:  Manufacturer=MEIG
S:  Product=LTE-A Module
S:  SerialNumber=1bd51f0e
C:  #Ifs= 4 Cfg#= 1 Atr=80 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
---
 drivers/usb/serial/option.c |    6 ++++++
 1 file changed, 6 insertions(+)
drivers/usb/serial/option.c +6 -0
@@ -2450,6 +2450,12 @@ static const struct usb_device_id option
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d38, 0xff, 0xff, 0x30) },	/* MeiG Smart SRM825WN (Diag) */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d38, 0xff, 0xff, 0x40) },	/* MeiG Smart SRM825WN (AT) */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d38, 0xff, 0xff, 0x60) },	/* MeiG Smart SRM825WN (NMEA) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d63, 0xff, 0xff, 0x30) },	/* MeiG SRM813Q (Diag) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d63, 0xff, 0xff, 0x40) },	/* MeiG SRM813Q (AT) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d64, 0xff, 0xff, 0x30) },	/* MeiG SRM813Q (Diag) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d64, 0xff, 0xff, 0x40) },	/* MeiG SRM813Q (AT) */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d64, 0xff, 0xff, 0x60) },	/* MeiG SRM813Q (NMEA) */
+
 	{ USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) },			/* LongSung M5710 */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) },			/* GosunCn GM500 RNDIS */
 	{ USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) },			/* GosunCn GM500 MBIM */
author maintainer
#161 lore raw

PATCH 151/522 USB: serial: option: add missing RSVD(5) flag for Rolling RW135R-GL

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Wanquan Zhong <[email protected]>

commit 689f2facc689c8add11d7ff69fbbad17d65ee596 upstream.

The RW135R-GL entry added in commit 01e8d0f74222 ("USB: serial: option:
add support for Rolling Wireless RW135R-GL") was missing the .driver_info = RSVD(5) flag used by other Rolling Wireless MBIM laptop modules (e.g. RW135-GL and RW350-GL).

Without this flag, the option driver incorrectly binds to the reserved ADB interface (If#5) in multi-interface USB modes, causing AT/MBIM communication failures after mode switching. This matches the handling of other Rolling Wireless MBIM devices.

- VID:PID 33f8:1003, RW135R-GL for laptop debug M.2 cards (with MBIM interface for Linux/Chrome OS)

0x1003: mbim, diag, AT, pipe

Here are the outputs of usb-devices:

T:  Bus=03 Lev=01 Prnt=01 Port=04 Cnt=02 Dev#=  8 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=33f8 ProdID=1003 Rev= 5.15
S:  Manufacturer=Rolling Wireless S.a.r.l.
S:  Product=Rolling RW135R-GL Module
S:  SerialNumber=12345678
C:* #Ifs= 5 Cfg#= 1 Atr=a0 MxPwr=500mA
A:  FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00
I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim
E:  Ad=82(I) Atr=03(Int.) MxPS=  64 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

- VID:PID 33f8:1003, RW135R-GL for laptop debug M.2 cards (with MBIM interface for Linux/Chrome OS)

0x1003: mbim, diag, AT, ADB, pipe

Here are the outputs of usb-devices:

T:  Bus=03 Lev=01 Prnt=01 Port=04 Cnt=02 Dev#=  7 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=33f8 ProdID=1003 Rev= 5.15
S:  Manufacturer=Rolling Wireless S.a.r.l.
S:  Product=Rolling RW135R-GL Module
S:  SerialNumber=12345678
C:* #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=500mA
A:  FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00
I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim
E:  Ad=82(I) Atr=03(Int.) MxPS=  64 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

- VID:PID 33f8:1003, RW135R-GL for laptop debug M.2 cards (with MBIM interface for Linux/Chrome OS)

0x1003: mbim, pipe

Here are the outputs of usb-devices:

T:  Bus=03 Lev=01 Prnt=01 Port=04 Cnt=02 Dev#=  9 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=33f8 ProdID=1003 Rev= 5.15
S:  Manufacturer=Rolling Wireless S.a.r.l.
S:  Product=Rolling RW135R-GL Module
S:  SerialNumber=12345678
C:* #Ifs= 3 Cfg#= 1 Atr=a0 MxPwr=500mA
A:  FirstIf#= 0 IfCount= 2 Cls=02(comm.) Sub=0e Prot=00
I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=0e Prot=00 Driver=cdc_mbim
E:  Ad=82(I) Atr=03(Int.) MxPS=  64 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
Fixes 01e8d0f74222 ("USB: serial: option: add support for Rolling Wireless RW135R-GL")
---
 drivers/usb/serial/option.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/usb/serial/option.c +2 -1
@@ -2476,7 +2476,8 @@ static const struct usb_device_id option
 	{ USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x0302, 0xff) },			/* Rolling RW101R-GL (laptop MBIM) */
 	{ USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x0802, 0xff),			/* Rolling RW350-GL (laptop MBIM) */
 	  .driver_info = RSVD(5) },
-	{ USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x1003, 0xff) },			/* Rolling RW135R-GL (laptop MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(0x33f8, 0x1003, 0xff),			/* Rolling RW135R-GL (laptop MBIM) */
+	  .driver_info = RSVD(5) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0100, 0xff, 0xff, 0x30) },	/* NetPrisma LCUK54-WWD for Global */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0100, 0xff, 0x00, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x3731, 0x0100, 0xff, 0xff, 0x40) },
author maintainer
#162 lore raw

PATCH 152/522 USB: serial: belkin_sa: validate interrupt status length

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Zhang Cen <[email protected]>

commit 4ce058df2ee02cc2a0f0fd5cd64ce6f1482a0b65 upstream.

The Belkin interrupt callback treats interrupt data as a four-byte status report and reads LSR/MSR fields at offsets 2 and 3. The interrupt-in buffer length is derived from endpoint wMaxPacketSize, and short interrupt transfers may complete successfully with a smaller actual_length.

Check the completed interrupt packet length before parsing status fields so short interrupt endpoints and short successful packets are ignored instead of causing out-of-bounds or stale status-byte reads.

KASAN report as below:

BUG: KASAN: slab-out-of-bounds in belkin_sa_read_int_callback()
Read of size 1
Call trace:
  belkin_sa_read_int_callback() (drivers/usb/serial/belkin_sa.c:202)
  __usb_hcd_giveback_urb() (drivers/usb/core/hcd.c:1630)
  dummy_timer() (?:?)
Fixes 1da177e4c3f4 ("Linux-2.6.12-rc2")
Assisted-by Codex:gpt-5.5
---
 drivers/usb/serial/belkin_sa.c |    3 +++
 1 file changed, 3 insertions(+)
drivers/usb/serial/belkin_sa.c +3 -0
@@ -195,6 +195,9 @@ static void belkin_sa_read_int_callback(
 
 	usb_serial_debug_data(&port->dev, __func__, urb->actual_length, data);
 
+	if (urb->actual_length < BELKIN_SA_MSR_INDEX + 1)
+		goto exit;
+
 	/* Handle known interrupt data */
 	/* ignore data[0] and data[1] */
 
author maintainer
#163 lore raw

PATCH 153/522 USB: serial: cypress_m8: validate interrupt packet headers

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Zhang Cen <[email protected]>

commit 9f9bfc80c67f35a275820da7e83a35dface08281 upstream.

cypress_read_int_callback() parses the interrupt-in buffer according to the selected Cypress packet format. Format 1 has a two-byte status/count header and format 2 has a one-byte combined status/count header. The usb-serial core sizes the interrupt-in buffer from the endpoint descriptor's wMaxPacketSize, and successful interrupt transfers can complete short when URB_SHORT_NOT_OK is not set.

Check that the completed packet contains the selected header before reading it. Malformed short reports are ignored and the interrupt URB is resubmitted through the existing retry path, preventing out-of-bounds header-byte reads.

KASAN report as below:
KASAN slab-out-of-bounds in cypress_read_int_callback+0x240/0x7f0

Read of size 1
Call trace:
  cypress_read_int_callback() (drivers/usb/serial/cypress_m8.c:1009)
  __usb_hcd_giveback_urb()
  dummy_timer()
Fixes 3416eaa1f8f8 ("USB: cypress_m8: Packet format is separate from characteristic size")
Assisted-by Codex:gpt-5.5
Fixes 3416eaa1f8f8 ("USB: cypress_m8: Packet format is separate from characteristic size")
Cc [email protected] # 2.6.26
[ johan: use constants in header length sanity checks ]
---
 drivers/usb/serial/cypress_m8.c |   12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)
drivers/usb/serial/cypress_m8.c +11 -1
@@ -1020,8 +1020,8 @@ static void cypress_read_int_callback(st
 	char tty_flag = TTY_NORMAL;
 	int bytes = 0;
 	int result;
-	int i = 0;
 	int status = urb->status;
+	int i;
 
 	switch (status) {
 	case 0: /* success */
@@ -1059,22 +1059,32 @@ static void cypress_read_int_callback(st
 
 	spin_lock_irqsave(&priv->lock, flags);
 	result = urb->actual_length;
+	i = 0;
 	switch (priv->pkt_fmt) {
 	default:
 	case packet_format_1:
 		/* This is for the CY7C64013... */
+		if (result < 2)
+			break;
 		priv->current_status = data[0] & 0xF8;
 		bytes = data[1] + 2;
 		i = 2;
 		break;
 	case packet_format_2:
 		/* This is for the CY7C63743... */
+		if (result < 1)
+			break;
 		priv->current_status = data[0] & 0xF8;
 		bytes = (data[0] & 0x07) + 1;
 		i = 1;
 		break;
 	}
 	spin_unlock_irqrestore(&priv->lock, flags);
+	if (i == 0) {
+		dev_dbg(dev, "%s - short packet received: %d bytes\n",
+			__func__, result);
+		goto continue_read;
+	}
 	if (result < bytes) {
 		dev_dbg(dev,
 			"%s - wrong packet size - received %d bytes but packet said %d bytes\n",
author maintainer
#164 lore raw

PATCH 154/522 USB: serial: keyspan: fix missing indat transfer sanity check

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Johan Hovold <[email protected]>

commit ab8336a7e414f018430aa1af3a46944032f7ff96 upstream.

Add the missing sanity check on the size of usa49wg indat transfers to avoid parsing stale or uninitialised slab data.

Fixes 0ca1268e109a ("USB Serial Keyspan: add support for USA-49WG & USA-28XG")
Cc [email protected] # 2.6.23
---
 drivers/usb/serial/keyspan.c |    4 ++++
 1 file changed, 4 insertions(+)
drivers/usb/serial/keyspan.c +4 -0
@@ -1185,6 +1185,10 @@ static void usa49wg_indat_callback(struc
 	len = 0;
 
 	while (i < urb->actual_length) {
+		if (urb->actual_length - i < 3) {
+			dev_warn_ratelimited(&urb->dev->dev, "malformed indat packet\n");
+			break;
+		}
 
 		/* Check port number from message */
 		if (data[i] >= serial->num_ports) {
author maintainer
#165 lore raw

PATCH 155/522 USB: serial: mxuport: fix memory corruption with small endpoint

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Johan Hovold <[email protected]>

commit 4085f0dbb1ce2251c9a5938d693de6593f0ab2bd upstream.

Make sure that the bulk-out endpoint max packet size is at least eight bytes to avoid user-controlled slab corruption should a malicious device report a smaller size.

Fixes ee467a1f2066 ("USB: serial: add Moxa UPORT 12XX/14XX/16XX driver")
Cc Andrew Lunn <[email protected]>
---
 drivers/usb/serial/mxuport.c |    8 ++++++++
 1 file changed, 8 insertions(+)
drivers/usb/serial/mxuport.c +8 -0
@@ -962,6 +962,14 @@ static int mxuport_calc_num_ports(struct
 	 */
 	BUILD_BUG_ON(ARRAY_SIZE(epds->bulk_out) < 16);
 
+	/*
+	 * The bulk-out buffers must be large enough for the four-byte header
+	 * (and following data), but assume anything smaller than eight bytes
+	 * is broken.
+	 */
+	if (usb_endpoint_maxp(epds->bulk_out[0]) < 8)
+		return -EINVAL;
+
 	for (i = 1; i < num_ports; ++i)
 		epds->bulk_out[i] = epds->bulk_out[0];
 
author maintainer
#166 lore raw

PATCH 156/522 USB: serial: mct_u232: fix missing interrupt-in transfer sanity check

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Johan Hovold <[email protected]>

commit 245aba83e3c288e176ed037a1f6b618b09e92ed8 upstream.

Add the missing sanity check on the size of interrupt-in transfers to avoid parsing stale or uninitialised slab data (and leaking it to user space).

---
 drivers/usb/serial/mct_u232.c |    5 +++++
 1 file changed, 5 insertions(+)
drivers/usb/serial/mct_u232.c +5 -0
@@ -544,6 +544,11 @@ static void mct_u232_read_int_callback(s
 		goto exit;
 	}
 
+	if (urb->actual_length < 2) {
+		dev_warn_ratelimited(&port->dev, "short interrupt-in packet\n");
+		goto exit;
+	}
+
 	/*
 	 * The interrupt-in pipe signals exceptional conditions (modem line
 	 * signal changes and errors). data[0] holds MSR, data[1] holds LSR.
author maintainer
#167 lore raw

PATCH 157/522 usb: gadget: net2280: Fix double free in probe error path

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Guangshuo Li <[email protected]>

commit c8547c74988e0b5f4cbb1b895e2a57aae084f070 upstream.

usb_initialize_gadget() installs gadget_release() as the release callback for the embedded gadget device. The struct net2280 instance is therefore released through gadget_release() when the gadget device's last reference is dropped.

The probe error path calls net2280_remove(), which tears down the partially initialized device and drops the gadget reference with usb_put_gadget(). Calling kfree(dev) afterwards can free the same object again.

Drop the explicit kfree() and let the gadget device release callback handle the final free. This issue was found by a static analysis tool I am developing.

---
 drivers/usb/gadget/udc/net2280.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
drivers/usb/gadget/udc/net2280.c +1 -3
@@ -3790,10 +3790,8 @@ static int net2280_probe(struct pci_dev
 	return 0;
 
 done:
-	if (dev) {
+	if (dev)
 		net2280_remove(pdev);
-		kfree(dev);
-	}
 	return retval;
 }
 
author maintainer
#168 lore raw

PATCH 158/522 usb: gadget: dummy_hcd: Reject hub port requests for non-existent ports

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Seungjin Bae <[email protected]>

commit 7d9633528dd40e33964d2dc74a5abbf5c4d116ce upstream.

The dummy_hub_control() function handles USB hub class requests to the virtual root hub. The GetPortStatus case returns -EPIPE for requests with wIndex != 1, since the virtual root hub has only a single port. However, the ClearPortFeature and SetPortFeature cases lack the same check.

Fix this by extending the wIndex != 1 rejection to both cases, matching the existing behavior of GetPortStatus.

---
 drivers/usb/gadget/udc/dummy_hcd.c |    4 ++++
 1 file changed, 4 insertions(+)
drivers/usb/gadget/udc/dummy_hcd.c +4 -0
@@ -2133,6 +2133,8 @@ static int dummy_hub_control(
 	case ClearHubFeature:
 		break;
 	case ClearPortFeature:
+		if (wIndex != 1)
+			goto error;
 		switch (wValue) {
 		case USB_PORT_FEAT_SUSPEND:
 			if (hcd->speed == HCD_USB3) {
@@ -2247,6 +2249,8 @@ static int dummy_hub_control(
 		retval = -EPIPE;
 		break;
 	case SetPortFeature:
+		if (wIndex != 1)
+			goto error;
 		switch (wValue) {
 		case USB_PORT_FEAT_LINK_STATE:
 			if (hcd->speed != HCD_USB3) {
author maintainer
#169 lore raw

PATCH 159/522 usb: gadget: f_fs: copy only received bytes on short ep0 read

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Bommarito <[email protected]>

commit 4e036c10e7f4df5d951c69cc3697bc8e209c6d02 upstream.

ffs_ep0_read() allocates its control-OUT data buffer with kmalloc() (not kzalloc) at the Length value from the Setup packet, then copies that full len to userspace regardless of how many bytes were actually received:

    data = kmalloc(len, GFP_KERNEL);
    ...
    ret = __ffs_ep0_queue_wait(ffs, data, len);
    if ((ret > 0) && (copy_to_user(buf, data, len)))
            ret = -EFAULT;

__ffs_ep0_queue_wait() returns req->actual, which on a short control OUT transfer is strictly less than len. The copy_to_user() call still copies len bytes, so on a short OUT the last (len - ret) bytes of the kmalloc() buffer -- uninitialised slab residue -- are delivered to the FunctionFS daemon.

Short ep0 OUT completions are specified USB control-transfer behavior and are produced by in-tree UDCs:

* dwc2 continues on req->actual < req->length for ep0 DATA OUT (short-not-ok is the only ep0-OUT stall path).
* aspeed_udc ends ep0 OUT on rx_len < ep->ep.maxpacket.
* renesas_usbf logs "ep0 short packet" and completes the request.
* dwc3 stalls on short IN but not on short OUT.

A short ep0 OUT is therefore not evidence of a broken UDC; it is a normal condition f_fs has to cope with. The sibling gadgetfs implementation in drivers/usb/gadget/legacy/inode.c already does this correctly via min(len, dev->req->actual) before copy_to_user(). This patch brings f_fs.c to the same safe pattern rather than trimming at a defensive layer.

The bug is reached from the FunctionFS device node, which in real deployments is owned by the privileged gadget daemon (adbd, UMS, composite gadget services, etc.); it is not reachable from unprivileged userspace. Linux host stacks normally reject short-wLength control OUTs before they reach the gadget, so reproducing this required a build that bypasses that host-side check. With the bypass in place, a 1-byte payload on a 64-byte Setup produces 63 bytes of non-canary slab residue in the daemon's read buffer.

Fix by copying only ret (actually received) bytes to userspace.

Fixes ddf8abd25994 ("USB: f_fs: the FunctionFS driver")
Cc stable <[email protected]>
Assisted-by Claude:claude-opus-4-7
---
 drivers/usb/gadget/function/f_fs.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/usb/gadget/function/f_fs.c +1 -1
@@ -592,7 +592,7 @@ static ssize_t ffs_ep0_read(struct file
 
 		/* unlocks spinlock */
 		ret = __ffs_ep0_queue_wait(ffs, data, len);
-		if ((ret > 0) && (copy_to_user(buf, data, len)))
+		if ((ret > 0) && (copy_to_user(buf, data, ret)))
 			ret = -EFAULT;
 		goto done_mutex;
 
author maintainer
#170 lore raw

PATCH 160/522 thunderbolt: property: Reject u32 wrap in tb_property_entry_valid()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Bommarito <[email protected]>

commit 01deda0152066c6c955f0619114ea6afa070aaec upstream.

entry->value is u32 and entry->length is u16; the sum is performed in u32 and wraps. A malicious XDomain peer can pick
value = 0xffffff00, length = 0x100 so the sum 0x100000000 wraps to 0 and passes the > block_len check. tb_property_parse() then passes entry->value to parse_dwdata() as a dword offset into the property block, reading attacker-directed memory far past the allocation.

For TEXT-typed entries with the "deviceid" or "vendorid" keys this lands in xd->device_name / xd->vendor_name and is readable back via the per-XDomain device_name / vendor_name sysfs attributes; the leak is NUL-bounded (kstrdup() stops at the first zero byte) and untargeted (the attacker picks a delta, not an absolute address). DATA-typed entries are parsed into property->value.data but not generically surfaced to userspace.

Use check_add_overflow() so a wrapped sum is rejected.

Fixes cdae7c07e3e3 ("thunderbolt: Add support for XDomain properties")
Assisted-by Claude:claude-opus-4-6
Assisted-by Codex:gpt-5-4
---
 drivers/thunderbolt/property.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/thunderbolt/property.c +5 -1
@@ -8,6 +8,7 @@
  */
 
 #include <linux/err.h>
+#include <linux/overflow.h>
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/uuid.h>
@@ -52,13 +53,16 @@ static inline void format_dwdata(void *d
 static bool tb_property_entry_valid(const struct tb_property_entry *entry,
 				  size_t block_len)
 {
+	u32 end;
+
 	switch (entry->type) {
 	case TB_PROPERTY_TYPE_DIRECTORY:
 	case TB_PROPERTY_TYPE_DATA:
 	case TB_PROPERTY_TYPE_TEXT:
 		if (entry->length > block_len)
 			return false;
-		if (entry->value + entry->length > block_len)
+		if (check_add_overflow(entry->value, entry->length, &end) ||
+		    end > block_len)
 			return false;
 		break;
 
author maintainer
#171 lore raw

PATCH 161/522 thunderbolt: property: Reject dir_len < 4 to prevent size_t underflow

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Bommarito <[email protected]>

commit de21b59c29e31c5108ddc04210631bbfab81b997 upstream.

On the non-root path, __tb_property_parse_dir() takes dir_len from entry->length (u16 widened to size_t). Two distinct OOB conditions follow when entry->length < 4:

1. The non-root path begins with kmemdup(&block[dir_offset], sizeof(*dir->uuid), ...) which always reads 4 dwords from dir_offset. tb_property_entry_valid() only enforces dir_offset + entry->length <= block_len, so a crafted entry with dir_offset close to the end of the property block and entry->length in 0..3 passes that gate but lets the UUID copy run off the block (e.g. dir_offset = 497, dir_len = 3 in a 500-dword block reads block[497..501]).

2. After the kmemdup, content_len = dir_len - 4 underflows size_t to ~SIZE_MAX, nentries becomes SIZE_MAX / 4, and the entry walk runs OOB on each iteration until an entry fails validation or the kernel oopses on an unmapped page.

Reject dir_len < 4 on the non-root path *before* the UUID kmemdup, which closes both holes.

Also move INIT_LIST_HEAD(&dir->properties) up to immediately after the dir allocation so the new error-return path (and the existing uuid-alloc failure path) calling tb_property_free_dir() sees a walkable list rather than the zero-initialized NULL next/prev that list_for_each_entry_safe() would oops on.

Fixes cdae7c07e3e3 ("thunderbolt: Add support for XDomain properties")
Assisted-by Claude:claude-opus-4-6
Assisted-by Codex:gpt-5-4
---
 drivers/thunderbolt/property.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/thunderbolt/property.c +6 -2
@@ -174,10 +174,16 @@ static struct tb_property_dir *__tb_prop
 	if (!dir)
 		return NULL;
 
+	INIT_LIST_HEAD(&dir->properties);
+
 	if (is_root) {
 		content_offset = dir_offset + 2;
 		content_len = dir_len;
 	} else {
+		if (dir_len < 4) {
+			tb_property_free_dir(dir);
+			return NULL;
+		}
 		dir->uuid = kmemdup(&block[dir_offset], sizeof(*dir->uuid),
 				    GFP_KERNEL);
 		if (!dir->uuid) {
@@ -191,8 +197,6 @@ static struct tb_property_dir *__tb_prop
 	entries = (const struct tb_property_entry *)&block[content_offset];
 	nentries = content_len / (sizeof(*entries) / 4);
 
-	INIT_LIST_HEAD(&dir->properties);
-
 	for (i = 0; i < nentries; i++) {
 		struct tb_property *property;
 
author maintainer
#172 lore raw

PATCH 162/522 scsi: fcoe: Reject FIP descriptors with zero fip_dlen in CVL walker

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Bommarito <[email protected]>

commit 9eed1bd59937e6828b00d2f2dfef631d964f3636 upstream.

drivers/scsi/fcoe/fcoe_ctlr.c::fcoe_ctlr_recv_clr_vlink() advanced the descriptor cursor by an attacker-supplied fip_dlen without ever requiring dlen >= sizeof(struct fip_desc) in the default branch. The named descriptor cases (FIP_DT_MAC, FIP_DT_NAME, FIP_DT_VN_ID) checked their per-type minimum lengths, but a FIP_DT_NON_CRITICAL descriptor (fip_dtype >= 128, which the standard requires receivers to silently ignore) skipped that check entirely.

An unauthenticated L2 peer on the FCoE control VLAN could hang fcoe_ctlr_recv_work on an fcoe, qedf, or bnx2fc initiator indefinitely by emitting one FIP CVL frame whose single descriptor had fip_dtype == FIP_DT_NON_CRITICAL and fip_dlen == 0: the cursor advanced zero bytes per iteration and the loop condition rlen >= sizeof(*desc) stayed true forever, blocking every subsequent FIP frame on that controller.

Tighten the outer dlen guard to also reject dlen < sizeof(struct fip_desc), so a malformed descriptor whose length cannot even cover the descriptor header is rejected before the switch. This is the same lower-bound the named cases already apply and is the minimum scope that closes the loop.

Fixes 97c8389d54b9 ("[SCSI] fcoe, libfcoe: Add support for FIP. FCoE discovery and keep-alive.")
Assisted-by Claude:claude-opus-4-7
---
 drivers/scsi/fcoe/fcoe_ctlr.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/scsi/fcoe/fcoe_ctlr.c +1 -1
@@ -1386,7 +1386,7 @@ static void fcoe_ctlr_recv_clr_vlink(str
 
 	while (rlen >= sizeof(*desc)) {
 		dlen = desc->fip_dlen * FIP_BPW;
-		if (dlen > rlen)
+		if (dlen < sizeof(*desc) || dlen > rlen)
 			goto err;
 		/* Drop CVL if there are duplicate critical descriptors */
 		if ((desc->fip_dtype < 32) &&
author maintainer
#173 lore raw

PATCH 163/522 scsi: scsi_transport_fc: Widen FPIN pname walker counter to u32

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Bommarito <[email protected]>

commit a9a39233ec1fc9f97ea1340a4d09bb7ec2be5153 upstream.

An adjacent Fibre Channel fabric actor that can deliver an FPIN ELS frame to an lpfc or qla2xxx Linux initiator can trigger a non-return in the generic FC transport. This is not a local userspace or IP network path; the attacker must be able to inject fabric traffic, for example as a compromised switch or fabric controller, or as a same-zone N_Port on a fabric that permits source spoofing.

The Link-Integrity and Peer-Congestion FPIN walkers used a u8 loop counter against the 32-bit on-wire pname_count field, and did not bound pname_count by the descriptor body already validated by the TLV walker. A pname_count of 256 therefore wraps the counter and keeps the loop condition true indefinitely.

Factor the shared pname_list[] walk into one helper, widen the counter to u32, and clamp pname_count against the entries that fit in the descriptor body before iterating.

Fixes 3dcfe0de5a97 ("scsi: fc: Parse FPIN packets and update statistics")
Assisted-by Claude:claude-opus-4-7
---
 drivers/scsi/scsi_transport_fc.c |   77 ++++++++++++++++++++-------------------
 1 file changed, 41 insertions(+), 36 deletions(-)
drivers/scsi/scsi_transport_fc.c +41 -36
@@ -746,6 +746,37 @@ fc_cn_stats_update(u16 event_type, struc
 	}
 }
 
+static void
+fc_fpin_pname_stats_update(struct Scsi_Host *shost,
+			   struct fc_rport *attach_rport, u16 event_type,
+			   u32 desc_len, u32 fixed_len, u32 pname_count,
+			   __be64 *pname_list,
+			   void (*stats_update)(u16 event_type,
+						struct fc_fpin_stats *stats))
+{
+	u32 i;
+	struct fc_rport *rport;
+	u64 wwpn;
+
+	if (desc_len < fixed_len)
+		pname_count = 0;
+	else
+		pname_count = min(pname_count, (desc_len - fixed_len) /
+				   sizeof(pname_list[0]));
+
+	for (i = 0; i < pname_count; i++) {
+		wwpn = be64_to_cpu(pname_list[i]);
+		rport = fc_find_rport_by_wwpn(shost, wwpn);
+		if (rport &&
+		    (rport->roles & FC_PORT_ROLE_FCP_TARGET ||
+		     rport->roles & FC_PORT_ROLE_NVME_TARGET)) {
+			if (rport == attach_rport)
+				continue;
+			stats_update(event_type, &rport->fpin_stats);
+		}
+	}
+}
+
 /*
  * fc_fpin_li_stats_update - routine to update Link Integrity
  * event statistics.
@@ -756,13 +787,11 @@ fc_cn_stats_update(u16 event_type, struc
 static void
 fc_fpin_li_stats_update(struct Scsi_Host *shost, struct fc_tlv_desc *tlv)
 {
-	u8 i;
 	struct fc_rport *rport = NULL;
 	struct fc_rport *attach_rport = NULL;
 	struct fc_host_attrs *fc_host = shost_to_fc_host(shost);
 	struct fc_fn_li_desc *li_desc = (struct fc_fn_li_desc *)tlv;
 	u16 event_type = be16_to_cpu(li_desc->event_type);
-	u64 wwpn;
 
 	rport = fc_find_rport_by_wwpn(shost,
 				      be64_to_cpu(li_desc->attached_wwpn));
@@ -773,22 +802,11 @@ fc_fpin_li_stats_update(struct Scsi_Host
 		fc_li_stats_update(event_type, &attach_rport->fpin_stats);
 	}
 
-	if (be32_to_cpu(li_desc->pname_count) > 0) {
-		for (i = 0;
-		    i < be32_to_cpu(li_desc->pname_count);
-		    i++) {
-			wwpn = be64_to_cpu(li_desc->pname_list[i]);
-			rport = fc_find_rport_by_wwpn(shost, wwpn);
-			if (rport &&
-			    (rport->roles & FC_PORT_ROLE_FCP_TARGET ||
-			    rport->roles & FC_PORT_ROLE_NVME_TARGET)) {
-				if (rport == attach_rport)
-					continue;
-				fc_li_stats_update(event_type,
-						   &rport->fpin_stats);
-			}
-		}
-	}
+	fc_fpin_pname_stats_update(shost, attach_rport, event_type,
+				   be32_to_cpu(li_desc->desc_len),
+				   FC_TLV_DESC_LENGTH_FROM_SZ(*li_desc),
+				   be32_to_cpu(li_desc->pname_count),
+				   li_desc->pname_list, fc_li_stats_update);
 
 	if (fc_host->port_name == be64_to_cpu(li_desc->attached_wwpn))
 		fc_li_stats_update(event_type, &fc_host->fpin_stats);
@@ -836,13 +854,11 @@ static void
 fc_fpin_peer_congn_stats_update(struct Scsi_Host *shost,
 				struct fc_tlv_desc *tlv)
 {
-	u8 i;
 	struct fc_rport *rport = NULL;
 	struct fc_rport *attach_rport = NULL;
 	struct fc_fn_peer_congn_desc *pc_desc =
 	    (struct fc_fn_peer_congn_desc *)tlv;
 	u16 event_type = be16_to_cpu(pc_desc->event_type);
-	u64 wwpn;
 
 	rport = fc_find_rport_by_wwpn(shost,
 				      be64_to_cpu(pc_desc->attached_wwpn));
@@ -853,22 +869,11 @@ fc_fpin_peer_congn_stats_update(struct S
 		fc_cn_stats_update(event_type, &attach_rport->fpin_stats);
 	}
 
-	if (be32_to_cpu(pc_desc->pname_count) > 0) {
-		for (i = 0;
-		    i < be32_to_cpu(pc_desc->pname_count);
-		    i++) {
-			wwpn = be64_to_cpu(pc_desc->pname_list[i]);
-			rport = fc_find_rport_by_wwpn(shost, wwpn);
-			if (rport &&
-			    (rport->roles & FC_PORT_ROLE_FCP_TARGET ||
-			     rport->roles & FC_PORT_ROLE_NVME_TARGET)) {
-				if (rport == attach_rport)
-					continue;
-				fc_cn_stats_update(event_type,
-						   &rport->fpin_stats);
-			}
-		}
-	}
+	fc_fpin_pname_stats_update(shost, attach_rport, event_type,
+				   be32_to_cpu(pc_desc->desc_len),
+				   FC_TLV_DESC_LENGTH_FROM_SZ(*pc_desc),
+				   be32_to_cpu(pc_desc->pname_count),
+				   pc_desc->pname_list, fc_cn_stats_update);
 }
 
 /*
author maintainer
#174 lore raw

PATCH 164/522 scsi: target: iscsi: Bound iscsi_encode_text_output() appends to rsp_buf

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Bommarito <[email protected]>

commit bf33e01f88388c43e285492a63e539df6ffed64c upstream.

iscsi_encode_text_output() concatenates "key=value\0" records into login->rsp_buf, an 8192-byte kzalloc(MAX_KEY_VALUE_PAIRS) buffer allocated in iscsit_alloc_login_setup_buffer(). The three sprintf() call sites in this function (lines 1398, 1411, 1424 in v7.1-rc2) never check the remaining buffer capacity:

	*length += sprintf(output_buf, "%s=%s", er->key, er->value);
	*length += 1;
	output_buf = textbuf + *length;

The 8192-byte ceiling at iscsi_target_check_login_request() bounds the *input* Login PDU payload, but a single PDU can carry up to 2048 minimal four-byte "a=b\0" pairs, each unknown key expanding to a 16-byte "a=NotUnderstood\0" output record via iscsi_add_notunderstood_response(). 2048 * 16 = 32 KiB of output into an 8 KiB buffer, producing a ~24 KiB heap overrun in the kmalloc-8k slab.

The fix introduces a static iscsi_encode_text_record() helper that uses snprintf() with a per-call bounds check against the remaining buffer, and threads a u32 textbuf_size parameter through iscsi_encode_text_output(). Both call sites in iscsi_target_handle_csg_zero() (PHASE_SECURITY) and iscsi_target_handle_csg_one() (PHASE_OPERATIONAL) pass MAX_KEY_VALUE_PAIRS. On overflow the encoder logs the condition, calls iscsi_release_extra_responses() to drop queued records, and returns -1; both caller sites now emit ISCSI_STATUS_CLS_INITIATOR_ERR / ISCSI_LOGIN_STATUS_INIT_ERR via iscsit_tx_login_rsp() before returning, so the initiator sees an explicit failed-login response rather than a silent connection drop. (Prior to this patch only the PHASE_OPERATIONAL caller did that; the PHASE_SECURITY caller is converted to the same shape.)

Fixes e48354ce078c ("iscsi-target: Add iSCSI fabric support for target v4.1")
Assisted-by Claude:claude-opus-4-7
---
 drivers/target/iscsi/iscsi_target_nego.c       |    7 ++
 drivers/target/iscsi/iscsi_target_parameters.c |   62 +++++++++++++++++++------
 drivers/target/iscsi/iscsi_target_parameters.h |    2 
 3 files changed, 55 insertions(+), 16 deletions(-)
drivers/target/iscsi/iscsi_target_nego.c +6 -1
@@ -905,10 +905,14 @@ static int iscsi_target_handle_csg_zero(
 			SENDER_TARGET,
 			login->rsp_buf,
 			&login->rsp_length,
+			MAX_KEY_VALUE_PAIRS,
 			conn->param_list,
 			conn->tpg->tpg_attrib.login_keys_workaround);
-	if (ret < 0)
+	if (ret < 0) {
+		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_INITIATOR_ERR,
+				ISCSI_LOGIN_STATUS_INIT_ERR);
 		return -1;
+	}
 
 	if (!iscsi_check_negotiated_keys(conn->param_list)) {
 		bool auth_required = iscsi_conn_auth_required(conn);
@@ -992,6 +996,7 @@ static int iscsi_target_handle_csg_one(s
 			SENDER_TARGET,
 			login->rsp_buf,
 			&login->rsp_length,
+			MAX_KEY_VALUE_PAIRS,
 			conn->param_list,
 			conn->tpg->tpg_attrib.login_keys_workaround);
 	if (ret < 0) {
drivers/target/iscsi/iscsi_target_parameters.c +48 -14

101 lines not on this page · raw message

drivers/target/iscsi/iscsi_target_parameters.h +1 -1
@@ -46,7 +46,7 @@ extern struct iscsi_param *iscsi_find_pa
 extern int iscsi_extract_key_value(char *, char **, char **);
 extern int iscsi_update_param_value(struct iscsi_param *, char *);
 extern int iscsi_decode_text_input(u8, u8, char *, u32, struct iscsit_conn *);
-extern int iscsi_encode_text_output(u8, u8, char *, u32 *,
+extern int iscsi_encode_text_output(u8, u8, char *, u32 *, u32,
 			struct iscsi_param_list *, bool);
 extern int iscsi_check_negotiated_keys(struct iscsi_param_list *);
 extern void iscsi_set_connection_parameters(struct iscsi_conn_ops *,
author maintainer
#175 lore raw

PATCH 165/522 scsi: target: iscsi: Validate CHAP_R length before base64 decode

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Alexandru Hossu <[email protected]>

commit 85db7391310b1304d2dc8ae3b0b12105a9567147 upstream.

chap_server_compute_hash() allocates client_digest as kzalloc(chap->digest_size) and then, for BASE64-encoded responses, passes chap_r directly to chap_base64_decode() without checking whether the input length could produce more than digest_size bytes of output.

chap_base64_decode() writes to the destination unconditionally as long as there is input to consume. With MAX_RESPONSE_LENGTH set to 128 and the "0b" prefix stripped by extract_param(), up to 127 base64 characters can reach the decoder. 127 characters decode to 95 bytes. For SHA-256 (digest_size=32) this overflows client_digest by 63 bytes; for MD5 (digest_size=16) the overflow is 79 bytes.

The length check at line 344 fires after the write has already happened.

The HEX branch in the same switch statement already validates the length up front. Apply the same approach to the BASE64 branch: strip trailing base64 padding characters, then reject any input whose data length exceeds DIV_ROUND_UP(digest_size * 4, 3) before calling the decoder.

Stripping trailing '=' before the comparison handles both padded and unpadded encodings. chap_base64_decode() already returns early on '=', so the full original string is still passed to the decoder unchanged.

The mutual CHAP path decodes CHAP_C into initiatorchg_binhex, which is kzalloc(CHAP_CHALLENGE_STR_LEN). extract_param() caps initiatorchg at CHAP_CHALLENGE_STR_LEN characters, so at most CHAP_CHALLENGE_STR_LEN-1 base64 characters reach the decoder. The maximum decoded size, DIV_ROUND_UP((CHAP_CHALLENGE_STR_LEN-1) * 3, 4), is less than CHAP_CHALLENGE_STR_LEN, so no overflow is possible there. A comment is added at the call site to document this.

---
 drivers/target/iscsi/iscsi_target_auth.c |   19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)
drivers/target/iscsi/iscsi_target_auth.c +18 -1
@@ -339,13 +339,22 @@ static int chap_server_compute_hash(
 			goto out;
 		}
 		break;
-	case BASE64:
+	case BASE64: {
+		size_t r_len = strlen(chap_r);
+
+		while (r_len > 0 && chap_r[r_len - 1] == '=')
+			r_len--;
+		if (r_len > DIV_ROUND_UP(chap->digest_size * 4, 3)) {
+			pr_err("Malformed CHAP_R: base64 payload too long\n");
+			goto out;
+		}
 		if (chap_base64_decode(client_digest, chap_r, strlen(chap_r)) !=
 		    chap->digest_size) {
 			pr_err("Malformed CHAP_R: invalid BASE64\n");
 			goto out;
 		}
 		break;
+	}
 	default:
 		pr_err("Could not find CHAP_R\n");
 		goto out;
@@ -472,6 +481,14 @@ static int chap_server_compute_hash(
 		}
 		break;
 	case BASE64:
+		/*
+		 * No overflow check needed: initiatorchg_binhex is
+		 * CHAP_CHALLENGE_STR_LEN bytes and extract_param() caps
+		 * initiatorchg at CHAP_CHALLENGE_STR_LEN characters, so
+		 * the decoded output is at most DIV_ROUND_UP(
+		 * (CHAP_CHALLENGE_STR_LEN - 1) * 3, 4) bytes, which is
+		 * less than CHAP_CHALLENGE_STR_LEN.
+		 */
 		initiatorchg_len = chap_base64_decode(initiatorchg_binhex,
 						      initiatorchg,
 						      strlen(initiatorchg));
author maintainer
#176 lore raw

PATCH 166/522 drm/hyperv: validate resolution_count and fix WIN8 fallback

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Berkant Koc <[email protected]>

commit 13d33b9ef67066c77c84273fac5a1d3fde3533d1 upstream.

A SYNTHVID_RESOLUTION_RESPONSE with resolution_count > 64 walks past the supported_resolution[SYNTHVID_MAX_RESOLUTION_COUNT] array in the parse loop. Bound resolution_count against the array size, folded into the existing zero-check.

When the WIN10 resolution probe fails, the caller in hyperv_connect_vsp() left hv->screen_*_max / preferred_* unpopulated, which sets mode_config.max_width / max_height to 0 and makes drm_internal_framebuffer_create() reject every userspace framebuffer with -EINVAL. The pre-WIN10 branch had the same gap for preferred_width / preferred_height. Use a single post-probe fallback guarded by screen_width_max == 0 so both paths converge on the WIN8 defaults.

Assisted-by Claude:claude-opus-4-7 berkoc-pipeline
Fixes 76c56a5affeb ("drm/hyperv: Add DRM driver for hyperv synthetic video device")
---
 drivers/gpu/drm/hyperv/hyperv_drm_proto.c |   13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)
drivers/gpu/drm/hyperv/hyperv_drm_proto.c +10 -3
@@ -396,8 +396,11 @@ static int hyperv_get_supported_resoluti
 		return -ETIMEDOUT;
 	}
 
-	if (msg->resolution_resp.resolution_count == 0) {
-		drm_err(dev, "No supported resolutions\n");
+	if (msg->resolution_resp.resolution_count == 0 ||
+	    msg->resolution_resp.resolution_count >
+	    SYNTHVID_MAX_RESOLUTION_COUNT) {
+		drm_err(dev, "Invalid resolution count: %d\n",
+			msg->resolution_resp.resolution_count);
 		return -ENODEV;
 	}
 
@@ -513,9 +516,13 @@ int hyperv_connect_vsp(struct hv_device
 		ret = hyperv_get_supported_resolution(hdev);
 		if (ret)
 			drm_err(dev, "Failed to get supported resolution from host, use default\n");
-	} else {
+	}
+
+	if (!hv->screen_width_max) {
 		hv->screen_width_max = SYNTHVID_WIDTH_WIN8;
 		hv->screen_height_max = SYNTHVID_HEIGHT_WIN8;
+		hv->preferred_width = SYNTHVID_WIDTH_WIN8;
+		hv->preferred_height = SYNTHVID_HEIGHT_WIN8;
 	}
 
 	hv->mmio_megabytes = hdev->channel->offermsg.offer.mmio_megabytes;
author maintainer
#177 lore raw

PATCH 167/522 drm/hyperv: validate VMBus packet size in receive callback

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Berkant Koc <[email protected]>

commit 7f87763f47a3c22fb50265a00619ef10f2394b18 upstream.

hyperv_receive_sub() reads msg->vid_hdr.type and dispatches into one of four message-type branches without knowing how many bytes the host wrote into hv->recv_buf. The completion path then runs memcpy(hv->init_buf, msg, VMBUS_MAX_PACKET_SIZE), so the consumer that wakes on wait_for_completion_timeout() can read up to 16 KiB of residue from a prior message as if it were the response payload.

Pass bytes_recvd into hyperv_receive_sub() and reject any packet that does not cover the pipe + synthvid header. A single switch on msg->vid_hdr.type then computes the type-specific payload size: the three completion-driving types (SYNTHVID_VERSION_RESPONSE, SYNTHVID_RESOLUTION_RESPONSE, SYNTHVID_VRAM_LOCATION_ACK) fall through to a shared exit that requires that size before memcpy/complete, while SYNTHVID_FEATURE_CHANGE validates its own payload and returns before reading is_dirt_needed. Unknown types are dropped.

SYNTHVID_RESOLUTION_RESPONSE is variable length: the host fills resolution_count entries, not the full SYNTHVID_MAX_RESOLUTION_COUNT array. Validate the fixed prefix first so resolution_count can be read, bound it against the array, then require only the count-sized array, so the shorter responses the host actually sends are accepted.

Only run the sub-handler when vmbus_recvpacket() returned success. The memcpy length is bytes_recvd, which is bounded by VMBUS_MAX_PACKET_SIZE only on a successful receive; on -ENOBUFS vmbus_recvpacket() instead reports the required length, which can exceed hv->recv_buf, so copying bytes_recvd would read and write past the 16 KiB buffers. Gating on the success return keeps the copy bounded. The nonzero-return path is itself a malformed-message case and is now logged rather than silently skipped; channel recovery is not attempted.

Rejected packets are reported via drm_err_ratelimited() rather than silently dropped, matching the CoCo-hardened pattern in hv_kvp_onchannelcallback().

Fixes 76c56a5affeb ("drm/hyperv: Add DRM driver for hyperv synthetic video device")
Assisted-by Claude:claude-opus-4-7 berkoc-pipeline
---
 drivers/gpu/drm/hyperv/hyperv_drm_proto.c |  100 ++++++++++++++++++++++++++----
 1 file changed, 87 insertions(+), 13 deletions(-)
drivers/gpu/drm/hyperv/hyperv_drm_proto.c +87 -13
@@ -425,30 +425,92 @@ static int hyperv_get_supported_resoluti
 	return 0;
 }
 
-static void hyperv_receive_sub(struct hv_device *hdev)
+static void hyperv_receive_sub(struct hv_device *hdev, u32 bytes_recvd)
 {
 	struct hyperv_drm_device *hv = hv_get_drvdata(hdev);
 	struct synthvid_msg *msg;
+	size_t hdr_size;
+	size_t need;
 
 	if (!hv)
 		return;
 
-	msg = (struct synthvid_msg *)hv->recv_buf;
-
-	/* Complete the wait event */
-	if (msg->vid_hdr.type == SYNTHVID_VERSION_RESPONSE ||
-	    msg->vid_hdr.type == SYNTHVID_RESOLUTION_RESPONSE ||
-	    msg->vid_hdr.type == SYNTHVID_VRAM_LOCATION_ACK) {
-		memcpy(hv->init_buf, msg, VMBUS_MAX_PACKET_SIZE);
-		complete(&hv->wait);
+	hdr_size = sizeof(struct pipe_msg_hdr) +
+		   sizeof(struct synthvid_msg_hdr);
+	if (bytes_recvd < hdr_size) {
+		drm_err_ratelimited(&hv->dev,
+				    "synthvid packet too small for header: %u\n",
+				    bytes_recvd);
 		return;
 	}
 
-	if (msg->vid_hdr.type == SYNTHVID_FEATURE_CHANGE) {
+	msg = (struct synthvid_msg *)hv->recv_buf;
+	need = hdr_size;
+
+	switch (msg->vid_hdr.type) {
+	case SYNTHVID_VERSION_RESPONSE:
+		need += sizeof(struct synthvid_version_resp);
+		break;
+	case SYNTHVID_RESOLUTION_RESPONSE:
+		/*
+		 * The resolution response is variable length: the host
+		 * fills resolution_count entries, not the full
+		 * SYNTHVID_MAX_RESOLUTION_COUNT array. Require the fixed
+		 * prefix first so resolution_count can be read, then
+		 * demand exactly the count-sized array.
+		 */
+		need += offsetof(struct synthvid_supported_resolution_resp,
+				 supported_resolution);
+		if (bytes_recvd < need)
+			break;
+		if (msg->resolution_resp.resolution_count >
+		    SYNTHVID_MAX_RESOLUTION_COUNT) {
+			drm_err_ratelimited(&hv->dev,
+					    "synthvid resolution count too large: %u\n",
+					    msg->resolution_resp.resolution_count);
+			return;
+		}
+		need += msg->resolution_resp.resolution_count *
+			sizeof(struct hvd_screen_info);
+		break;
+	case SYNTHVID_VRAM_LOCATION_ACK:
+		need += sizeof(struct synthvid_vram_location_ack);
+		break;
+	case SYNTHVID_FEATURE_CHANGE:
+		/*
+		 * Not a completion-driving message: validate its own payload
+		 * and consume it here rather than falling through to the
+		 * memcpy/complete shared by the wait-event responses.
+		 */
+		if (bytes_recvd < need +
+		    sizeof(struct synthvid_feature_change)) {
+			drm_err_ratelimited(&hv->dev,
+					    "synthvid feature change packet too small: %u\n",
+					    bytes_recvd);
+			return;
+		}
 		hv->dirt_needed = msg->feature_chg.is_dirt_needed;
 		if (hv->dirt_needed)
 			hyperv_hide_hw_ptr(hv->hdev);
+		return;
+	default:
+		return;
+	}
+
+	/*
+	 * Shared completion path for the wait-event responses
+	 * (VERSION_RESPONSE, RESOLUTION_RESPONSE, VRAM_LOCATION_ACK):
+	 * require the type-specific payload before handing the buffer to
+	 * the waiter.
+	 */
+	if (bytes_recvd < need) {
+		drm_err_ratelimited(&hv->dev,
+				    "synthvid packet too small for type %u: %u < %zu\n",
+				    msg->vid_hdr.type, bytes_recvd, need);
+		return;
 	}
+	memcpy(hv->init_buf, msg, bytes_recvd);
+	complete(&hv->wait);
 }
 
 static void hyperv_receive(void *ctx)
@@ -469,9 +531,21 @@ static void hyperv_receive(void *ctx)
 		ret = vmbus_recvpacket(hdev->channel, recv_buf,
 				       VMBUS_MAX_PACKET_SIZE,
 				       &bytes_recvd, &req_id);
-		if (bytes_recvd > 0 &&
-		    recv_buf->pipe_hdr.type == PIPE_MSG_DATA)
-			hyperv_receive_sub(hdev);
+		if (ret) {
+			/*
+			 * A nonzero return (e.g. -ENOBUFS for an oversized
+			 * packet) is itself a malformed message: bytes_recvd
+			 * then reports the required length rather than a copied
+			 * payload, so it must not be forwarded to the
+			 * sub-handler. Channel recovery is not attempted.
+			 */
+			drm_err_ratelimited(&hv->dev,
+					    "vmbus_recvpacket failed: %d (need %u)\n",
+					    ret, bytes_recvd);
+		} else if (bytes_recvd > 0 &&
+			   recv_buf->pipe_hdr.type == PIPE_MSG_DATA) {
+			hyperv_receive_sub(hdev, bytes_recvd);
+		}
 	} while (bytes_recvd > 0 && ret == 0);
 }
 
author maintainer
#178 lore raw

PATCH 168/522 drm/i915: Fix potential UAF in TTM object purge

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Janusz Krzysztofik <[email protected]>

commit 5c4063c87a619e4df954c179d24628636f5db15f upstream.

TLDR: The bo->ttm object might be changed by calling ttm_bo_validate(),
move casting it to an i915_tt object later to actually get the right pointer.

A user reported hitting the following bug under heavy use on DG2:

[26620.095550] Oops: general protection fault, probably for non-canonical address 0xa56b6b6b6b6b6b8b: 0000 1 SMP NOPTI
[26620.095556] CPU: 2 UID: 0 PID: 631 Comm: Xorg Not tainted 6.18.8 #1 PREEMPT(lazy)
[26620.095558] Hardware name: ASRock B850M Steel Legend WiFi/B850M Steel Legend WiFi, BIOS 3.50 09/18/2025
[26620.095559] RIP: 0010:i915_ttm_purge+0x84/0x100 [i915]
[26620.095604] Code: 00 00 00 48 8d 54 24 10 48 89 e6 48 89 fb e8 83 aa ae ff 85 c0 75 6f 48 83 bb a8 01 00 00 00 74 2c 48 8b 45 78 48 85 c0 74 23 <48> 8b 78 20 48 c7 c2 ff ff ff ff 31 f6 e8 7a 73 e3 e0 48 8b 7d 78
[26620.095605] RSP: 0018:ffffc90005fd7430 EFLAGS: 00010282
[26620.095607] RAX: a56b6b6b6b6b6b6b RBX: ffff8881f46c3dc0 RCX: 0000000000000000
[26620.095608] RDX: 0000000000000000 RSI: 0000000000000246 RDI: 00000000ffffffff
[26620.095609] RBP: ffff888289610f00 R08: 0000000000000001 R09: ffff88823b022000
[26620.095609] R10: ffff888103029b28 R11: ffff8881fc7f3800 R12: ffff88810b6150d0
[26620.095609] R13: ffff888289610f00 R14: 0000000000000000 R15: ffff8881f46c3dc0
[26620.095610] FS: 00007f1004d86900(0000) GS:ffff88901c858000(0000) knlGS:0000000000000000
[26620.095611] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[26620.095611] CR2: 00007f0fdf489000 CR3: 000000035b0c1000 CR4: 0000000000750ef0
[26620.095612] PKRU: 55555554
[26620.095612] Call Trace:
[26620.095615] <TASK>
[26620.095615] i915_ttm_move+0x2b9/0x420 [i915]
[26620.095642] ? ttm_tt_init+0x65/0x80 [ttm]
[26620.095644] ? i915_ttm_tt_create+0xc6/0x150 [i915]
[26620.095667] ttm_bo_handle_move_mem+0xb6/0x160 [ttm]
[26620.095669] ttm_bo_evict+0x100/0x150 [ttm]
[26620.095671] ? preempt_count_add+0x64/0xa0
[26620.095673] ? _raw_spin_lock+0xe/0x30
[26620.095675] ? _raw_spin_unlock+0xd/0x30
[26620.095675] ? i915_gem_object_evictable+0xb7/0xd0 [i915]
[26620.095704] ttm_bo_evict_cb+0x6e/0xd0 [ttm]
[26620.095705] ttm_lru_walk_for_evict+0xa6/0x200 [ttm]
[26620.095708] ttm_bo_alloc_resource+0x185/0x4f0 [ttm]
[26620.095709] ? init_object+0x62/0xd0
[26620.095712] ttm_bo_validate+0x7a/0x180 [ttm]
[26620.095713] ? _raw_spin_unlock_irqrestore+0x16/0x30
[26620.095714] __i915_ttm_get_pages+0xb0/0x170 [i915]
[26620.095737] i915_ttm_get_pages+0x9f/0x150 [i915]
[26620.095759] ? i915_gem_do_execbuffer+0xedc/0x2b40 [i915]
[26620.095786] ? alloc_debug_processing+0xd0/0x100
[26620.095787] ? _raw_spin_unlock_irqrestore+0x16/0x30
[26620.095788] ? i915_vma_instance+0xa0/0x4e0 [i915]
[26620.095822] __i915_gem_object_get_pages+0x2f/0x40 [i915]
[26620.095848] i915_vma_pin_ww+0x706/0x980 [i915]
[26620.095875] ? i915_gem_do_execbuffer+0xedc/0x2b40 [i915]
[26620.095904] eb_validate_vmas+0x170/0xa00 [i915]
[26620.095930] i915_gem_do_execbuffer+0x1201/0x2b40 [i915]
[26620.095953] ? alloc_debug_processing+0xd0/0x100
[26620.095954] ? _raw_spin_unlock_irqrestore+0x16/0x30
[26620.095955] ? i915_gem_execbuffer2_ioctl+0xc9/0x240 [i915]
[26620.095977] ? __wake_up_sync_key+0x32/0x50
[26620.095979] ? i915_gem_execbuffer2_ioctl+0xc9/0x240 [i915]
[26620.096001] ? __slab_alloc.isra.0+0x67/0xc0
[26620.096003] i915_gem_execbuffer2_ioctl+0x11a/0x240 [i915]

Results from decode_stacktrace.sh pointed to dereference of a file pointer field of a i915 TTM page vector container associated with an object being purged on eviction. That path is taken when the object is marked as no longer needed.

Code analysis revealed a possibility of the i915 TTM page vector container being replaced with a new instance inside a function that purges content of the object, should it be still busy. That function is called, indirectly via a more general function that changes the object's placement and caching policy, before the problematic dereference, but still after a pointer to the container is captured, rendering the pointer no longer valid.

Fix the issue by capturing the pointer to the container only after its potential replacement.

v2: Move the container_of() inside the if block (Sebastian),
- a simplified version of the commit description that explains briefly why the change is necessary (Christian).

Fixes 7ae034590ceae ("drm/i915/ttm: add tt shmem backend")
Cc [email protected] # v5.17+
Cc Matthew Auld <[email protected]>
Cc Thomas Hellström <[email protected]>
Cc Sebastian Brzezinka <[email protected]>
Cc Christian König <[email protected]>
(cherry picked from commit 4462966a93eb185849b7f174f0d0de53476d00a4)
---
 drivers/gpu/drm/i915/gem/i915_gem_ttm.c |   28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)
drivers/gpu/drm/i915/gem/i915_gem_ttm.c +16 -12
@@ -422,8 +422,6 @@ void i915_ttm_free_cached_io_rsgt(struct
 int i915_ttm_purge(struct drm_i915_gem_object *obj)
 {
 	struct ttm_buffer_object *bo = i915_gem_to_ttm(obj);
-	struct i915_ttm_tt *i915_tt =
-		container_of(bo->ttm, typeof(*i915_tt), ttm);
 	struct ttm_operation_ctx ctx = {
 		.interruptible = true,
 		.no_wait_gpu = false,
@@ -438,16 +436,22 @@ int i915_ttm_purge(struct drm_i915_gem_o
 	if (ret)
 		return ret;
 
-	if (bo->ttm && i915_tt->filp) {
-		/*
-		 * The below fput(which eventually calls shmem_truncate) might
-		 * be delayed by worker, so when directly called to purge the
-		 * pages(like by the shrinker) we should try to be more
-		 * aggressive and release the pages immediately.
-		 */
-		shmem_truncate_range(file_inode(i915_tt->filp),
-				     0, (loff_t)-1);
-		fput(fetch_and_zero(&i915_tt->filp));
+	if (bo->ttm) {
+		struct i915_ttm_tt *i915_tt =
+			container_of(bo->ttm, typeof(*i915_tt), ttm);
+
+		if (i915_tt->filp) {
+			/*
+			 * The below fput(which eventually calls shmem_truncate)
+			 * might be delayed by worker, so when directly called
+			 * to purge the pages(like by the shrinker) we should
+			 * try to be more aggressive and release the pages
+			 * immediately.
+			 */
+			shmem_truncate_range(file_inode(i915_tt->filp),
+					     0, (loff_t)-1);
+			fput(fetch_and_zero(&i915_tt->filp));
+		}
 	}
 
 	obj->write_domain = 0;
author maintainer
#179 lore raw

PATCH 169/522 drm/amd/pm/si: Disregard vblank time when no displays are connected

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Timur Kristóf <[email protected]>

commit dd4f3ee535b3b0ac027f75dbf9dc5fc88733c765 upstream.

When no displays are connected, there is no vblank happening so the power management code shouldn't worry about it.

This fixes a regression that caused the memory clock to be stuck at maximum when there were no displays connected to a SI GPU.

Fixes 9003a0746864 ("drm/amd/pm: Treat zero vblank time as too short in si_dpm (v3)")
Fixes 9d73b107a61b ("drm/amd/pm: Use pm_display_cfg in legacy DPM (v2)")
(cherry picked from commit 6d87e0199f7b83735b56e422d59f170a201897a8)
---
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c |    4 ++++
 1 file changed, 4 insertions(+)
drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +4 -0
@@ -3062,6 +3062,10 @@ static bool si_dpm_vblank_too_short(void
 	/* we never hit the non-gddr5 limit so disable it */
 	u32 switch_limit = adev->gmc.vram_type == AMDGPU_VRAM_TYPE_GDDR5 ? 450 : 0;
 
+	/* Disregard vblank time when there are no displays connected */
+	if (!adev->pm.pm_display_cfg.num_display)
+		return false;
+
 	/* Consider zero vblank time too short and disable MCLK switching.
 	 * Note that the vblank time is set to maximum when no displays are attached,
 	 * so we'll still enable MCLK switching in that case.
author maintainer
#180 lore raw

PATCH 170/522 serial: altera_jtaguart: handle uart_add_one_port() failures

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Myeonghun Pak <[email protected]>

commit ea66be25f0e934f49d24cd0c5845d13cdba3520b upstream.

altera_jtaguart_probe() maps the register window before registering the UART port, but it ignores failures from uart_add_one_port(). If port registration fails, probe still returns success and the mapping remains live until a later remove path that is not part of probe failure cleanup.

Return the uart_add_one_port() error and unmap the register window on that failure path.

This issue was identified during our ongoing static-analysis research while reviewing kernel code.

Fixes 5bcd601049c6 ("serial: Add driver for the Altera JTAG UART")
Cc stable <[email protected]>
---
 drivers/tty/serial/altera_jtaguart.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/tty/serial/altera_jtaguart.c +6 -1
@@ -425,6 +425,7 @@ static int altera_jtaguart_probe(struct
 	struct resource *res_mem;
 	int i = pdev->id;
 	int irq;
+	int ret;
 
 	/* -1 emphasizes that the platform must have one port, no .N suffix */
 	if (i == -1)
@@ -464,7 +465,11 @@ static int altera_jtaguart_probe(struct
 	port->flags = UPF_BOOT_AUTOCONF;
 	port->dev = &pdev->dev;
 
-	uart_add_one_port(&altera_jtaguart_driver, port);
+	ret = uart_add_one_port(&altera_jtaguart_driver, port);
+	if (ret) {
+		iounmap(port->membase);
+		return ret;
+	}
 
 	return 0;
 }
author maintainer
#181 lore raw

PATCH 171/522 serial: sh-sci: fix memory region release in error path

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Hongling Zeng <[email protected]>

commit 92b1ea22454b08a39baef3a7290fb3ec50366616 upstream.

The sci_request_port() function uses request_mem_region() to reserve I/O memory, but in the error path when sci_remap_port() fails, it incorrectly calls release_resource() instead of release_mem_region().

This mismatch can cause resource accounting issues. Fix it by using the correct release function, consistent with sci_release_port().

---
 drivers/tty/serial/sh-sci.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/tty/serial/sh-sci.c +1 -1
@@ -2757,7 +2757,7 @@ static int sci_request_port(struct uart_
 
 	ret = sci_remap_port(port);
 	if (unlikely(ret != 0)) {
-		release_resource(res);
+		release_mem_region(port->mapbase, sport->reg_size);
 		return ret;
 	}
 
author maintainer
#182 lore raw

PATCH 172/522 serial: zs: Fix swapped RI/DSR modem line transition counting

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Maciej W. Rozycki <[email protected]>

commit d15cd40cb1858f75846eaafa9a6bca841b790a92 upstream.

Fix a thinko in the status interrupt handler that has caused counters for the RI and DSR modem line transitions to be used for the other line each.

Fixes 8b4a40809e53 ("zs: move to the serial subsystem")
Cc stable <[email protected]>
---
 drivers/tty/serial/zs.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/tty/serial/zs.c +2 -2
@@ -679,9 +679,9 @@ static void zs_status_handle(struct zs_p
 			uart_handle_dcd_change(uport,
 					       zport->mctrl & TIOCM_CAR);
 		if (delta & TIOCM_RNG)
-			uport->icount.dsr++;
-		if (delta & TIOCM_DSR)
 			uport->icount.rng++;
+		if (delta & TIOCM_DSR)
+			uport->icount.dsr++;
 
 		if (delta)
 			wake_up_interruptible(&uport->state->port.delta_msr_wait);
author maintainer
#183 lore raw

PATCH 173/522 serial: fsl_lpuart: fix rx buffer and DMA map leaks in start_rx_dma

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Shitalkumar Gandhi <[email protected]>

commit 9a9254c4a2a3ca2b3da16d173f3b0dd01f397ff6 upstream.

lpuart_start_rx_dma() allocates sport->rx_ring.buf with kzalloc() and then maps a scatterlist via dma_map_sg(). On three subsequent error paths the function returns directly without releasing those resources:

- when dma_map_sg() returns 0 (-EINVAL):

      ring->buf is leaked.
  - when dmaengine_slave_config() fails:
      ring->buf and the DMA mapping are leaked.
  - when dmaengine_prep_dma_cyclic() returns NULL:
      ring->buf and the DMA mapping are leaked.

The sole cleanup path, lpuart_dma_rx_free(), is only reached when lpuart_dma_rx_use is set, and the caller lpuart_rx_dma_startup() clears that flag on failure of lpuart_start_rx_dma(). So these resources are permanently leaked on every failure in this function. Repeated port open/close or termios changes under error conditions will slowly consume memory and leave stale streaming DMA mappings behind.

Fix it by introducing two error labels that unmap the scatterlist and free the ring buffer as appropriate. While here, replace the misleading -EFAULT (bad userspace pointer) returned when dmaengine_prep_dma_cyclic() fails with the more accurate -ENOMEM, matching how other dmaengine users in the tree treat this failure.

No functional change on the success path.

Fixes 5887ad43ee02 ("tty: serial: fsl_lpuart: Use cyclic DMA for Rx")
Cc stable <[email protected]>
---
 drivers/tty/serial/fsl_lpuart.c |   15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)
drivers/tty/serial/fsl_lpuart.c +12 -3
@@ -1298,7 +1298,8 @@ static inline int lpuart_start_rx_dma(st
 
 	if (!nent) {
 		dev_err(sport->port.dev, "DMA Rx mapping error\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_free_buf;
 	}
 
 	dma_rx_sconfig.src_addr = lpuart_dma_datareg_addr(sport);
@@ -1310,7 +1311,7 @@ static inline int lpuart_start_rx_dma(st
 	if (ret < 0) {
 		dev_err(sport->port.dev,
 				"DMA Rx slave config failed, err = %d\n", ret);
-		return ret;
+		goto err_unmap_sg;
 	}
 
 	sport->dma_rx_desc = dmaengine_prep_dma_cyclic(chan,
@@ -1321,7 +1322,8 @@ static inline int lpuart_start_rx_dma(st
 				 DMA_PREP_INTERRUPT);
 	if (!sport->dma_rx_desc) {
 		dev_err(sport->port.dev, "Cannot prepare cyclic DMA\n");
-		return -EFAULT;
+		ret = -ENOMEM;
+		goto err_unmap_sg;
 	}
 
 	sport->dma_rx_desc->callback = lpuart_dma_rx_complete;
@@ -1339,6 +1341,13 @@ static inline int lpuart_start_rx_dma(st
 	}
 
 	return 0;
+
+err_unmap_sg:
+	dma_unmap_sg(chan->device->dev, &sport->rx_sgl, 1, DMA_FROM_DEVICE);
+err_free_buf:
+	kfree(ring->buf);
+	ring->buf = NULL;
+	return ret;
 }
 
 static void lpuart_dma_rx_free(struct uart_port *port)
author maintainer
#184 lore raw

PATCH 174/522 drm/amdkfd: fix NULL pointer bug in svm_range_set_attr

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Eric Huang <[email protected]>

commit e984d61d92e702096058f0f828f4b2b8563b88ce upstream.

The process_info could be NULL if user doesn't call kfd_ioctl_acquire_vm before calling kfd_ioctl_svm.

(cherry picked from commit 83a26c812e0529eb040d31a76f73e33e637243d4)
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c |    3 +++
 1 file changed, 3 insertions(+)
drivers/gpu/drm/amd/amdkfd/kfd_svm.c +3 -0
@@ -3404,6 +3404,9 @@ svm_range_set_attr(struct kfd_process *p
 
 	svms = &p->svms;
 
+	if (!process_info)
+		return -EINVAL;
+
 	mutex_lock(&process_info->lock);
 
 	svm_range_list_lock_and_flush_work(svms, mm);
author maintainer
#185 lore raw

PATCH 175/522 drm/amdkfd: Check for pdd drm file first in CRIU restore path

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: David Francis <[email protected]>

commit 6842b6a4b72da9b2906ffc5ca9d846ace2c54c14 upstream.

CRIU restore ioctls are meant to be called by CRIU with no existing drm file. There's an error path
for if the drm file unexpectedly exists. It was positioned so it was missing a fput(drm_file).

Do that check earlier, as soon as we have the pdd.

(cherry picked from commit 2bab781dac78916c5cc8de76345a4102449267d7)
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +5 -5
@@ -2171,6 +2171,11 @@ static int criu_restore_devices(struct k
 			ret = -EINVAL;
 			goto exit;
 		}
+
+		if (pdd->drm_file) {
+			ret = -EINVAL;
+			goto exit;
+		}
 		pdd->user_gpu_id = device_buckets[i].user_gpu_id;
 
 		drm_file = fget(device_buckets[i].drm_fd);
@@ -2180,11 +2185,6 @@ static int criu_restore_devices(struct k
 			ret = -EINVAL;
 			goto exit;
 		}
-
-		if (pdd->drm_file) {
-			ret = -EINVAL;
-			goto exit;
-		}
 
 		/* create the vm using render nodes for kfd pdd */
 		if (kfd_process_device_init_vm(pdd, drm_file)) {
author maintainer
#186 lore raw

PATCH 176/522 serial: dz: Fix bootconsole message clobbering at chip reset

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Maciej W. Rozycki <[email protected]>

commit ca904f4b42355287bc5ce8b7550ebe909cda4c2c upstream.

In the DZ interface as implemented by the DC7085 gate array the serial transmitters are double buffered, meaning that at the time a transmitter is ready to accept the next character there is one in the transmit shift register still being sent to the line. Issuing a master clear at this time causes this character to be lost, so wait an extra amount of time sufficient for the transmit shift register to drain at 9600bps, which is the baud rate setting used by the firmware console.

Mind the specified 1.4us TRDY recovery time in the course and continue using iob() as the completion barrier, since the platforms involved use a write buffer that can delay and combine writes, and reorder them with respect to reads regardless of the MMIO locations accessed and we still lack a platform-independent handler for that.

When called from dz_serial_console_init() this is too early for fsleep() to work and even before lpj has been calculated and therefore the delay is actually not sufficient for the transmitter to drain and is merely a placeholder now. This will be addressed in a follow-up change.

---
 drivers/tty/serial/dz.c |   21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)
drivers/tty/serial/dz.c +21 -0
@@ -544,10 +544,31 @@ static int dz_encode_baud_rate(unsigned
 static void dz_reset(struct dz_port *dport)
 {
 	struct dz_mux *mux = dport->mux;
+	unsigned short tcr;
+	int loops = 10000;
 
 	if (mux->initialised)
 		return;
 
+	tcr = dz_in(dport, DZ_TCR);
+
+	/* Do not disturb any ongoing transmissions.  */
+	if (dz_in(dport, DZ_CSR) & DZ_MSE) {
+		unsigned short csr, mask;
+
+		mask = tcr;
+		while ((mask & DZ_LNENB) && loops--) {
+			csr = dz_in(dport, DZ_CSR);
+			if (!(csr & DZ_TRDY))
+				continue;
+			mask &= ~(1 << ((csr & DZ_TLINE) >> 8));
+			dz_out(dport, DZ_TCR, mask);
+			iob();
+			udelay(2);		/* 1.4us TRDY recovery.  */
+		}
+		udelay(1200);			/* Transmitter drain.  */
+	}
+
 	dz_out(dport, DZ_CSR, DZ_CLR);
 	while (dz_in(dport, DZ_CSR) & DZ_CLR);
 	iob();
author maintainer
#187 lore raw

PATCH 177/522 serial: zs: Fix bootconsole handover lockup

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Maciej W. Rozycki <[email protected]>

commit 6c05cf72e13314ce9b770b5951695dc5a2152920 upstream.

Calling zs_reset() in the course of setting up the serial device causes line parameters to be reset and the transmitter disabled. We've been lucky in that no message is usually produced to the kernel log between this call and the later call to uart_set_options() in the course of console setup done by zs_serial_console_init(), or the system would hang as the console output handler in the firmware tried to access a port the transmitter of which has been disabled and line parameters messed up.

This will change with the next change to the driver, so fix zs_reset() such that line parameters are set for 9600n8 console operation as with the system firmware and the transmitter re-enabled after reset. This also means zs_pm() serves no purpose anymore, so drop it.

Fixes 8b4a40809e53 ("zs: move to the serial subsystem")
Cc [email protected] # v2.6.23+
---
 drivers/tty/serial/zs.c |   29 ++++++++---------------------
 1 file changed, 8 insertions(+), 21 deletions(-)
drivers/tty/serial/zs.c +8 -21
@@ -105,18 +105,24 @@ struct zs_parms {
 
 static struct zs_scc zs_sccs[ZS_NUM_SCCS];
 
+/*
+ * Set parameters in WR5, WR12, WR13 such as not to interfere
+ * with the initial PROM-based console.  Otherwise any output
+ * produced before the console handover would cause the system
+ * firmware to hang (TxENAB) or produce rubbish (Tx8, B9600).
+ */
 static u8 zs_init_regs[ZS_NUM_REGS] __initdata = {
 	0,				/* write 0 */
 	PAR_SPEC,			/* write 1 */
 	0,				/* write 2 */
 	0,				/* write 3 */
 	X16CLK | SB1,			/* write 4 */
-	0,				/* write 5 */
+	Tx8 | TxENAB,			/* write 5 */
 	0, 0, 0,			/* write 6, 7, 8 */
 	MIE | DLC | NV,			/* write 9 */
 	NRZ,				/* write 10 */
 	TCBR | RCBR,			/* write 11 */
-	0, 0,				/* BRG time constant, write 12 + 13 */
+	0x16, 0x00,			/* BRG time constant, write 12 + 13 */
 	BRSRC | BRENABL,		/* write 14 */
 	0,				/* write 15 */
 };
@@ -955,23 +961,6 @@ static void zs_set_termios(struct uart_p
 	spin_unlock_irqrestore(&scc->zlock, flags);
 }
 
-/*
- * Hack alert!
- * Required solely so that the initial PROM-based console
- * works undisturbed in parallel with this one.
- */
-static void zs_pm(struct uart_port *uport, unsigned int state,
-		  unsigned int oldstate)
-{
-	struct zs_port *zport = to_zport(uport);
-
-	if (state < 3)
-		zport->regs[5] |= TxENAB;
-	else
-		zport->regs[5] &= ~TxENAB;
-	write_zsreg(zport, R5, zport->regs[5]);
-}
-
 
 static const char *zs_type(struct uart_port *uport)
 {
@@ -1054,7 +1043,6 @@ static const struct uart_ops zs_ops = {
 	.startup	= zs_startup,
 	.shutdown	= zs_shutdown,
 	.set_termios	= zs_set_termios,
-	.pm		= zs_pm,
 	.type		= zs_type,
 	.release_port	= zs_release_port,
 	.request_port	= zs_request_port,
@@ -1209,7 +1197,6 @@ static int __init zs_console_setup(struc
 		return ret;
 
 	zs_reset(zport);
-	zs_pm(uport, 0, -1);
 
 	if (options)
 		uart_parse_options(options, &baud, &parity, &bits, &flow);
author maintainer
#188 lore raw

PATCH 178/522 serial: zs: Switch to using channel reset

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Maciej W. Rozycki <[email protected]>

commit 8572955630f30948837088aa98bcbe0532d1ceac upstream.

Switch the driver to using the channel reset rather than hardware reset, simplifying handling by removing an interference between channels that causes the other channel to become uninitialised afterwards.

There is little difference between the two kinds of reset in terms of register settings that result, and we initialise the whole register set right away anyway. However this prevents a hang from happening should the console output handler in the firmware try to access the other port whose transmitter has been disabled and line parameters messed up.

For example this will happen if the keyboard port (port A) is chosen for the system console, unusually but not insanely for a headless system, as the port is wired to a standard DA-15 connector and an adapter can be easily made. Or with the next change in place this would happen for the regular console port (port B), since the keyboard port (port A) will be initialised first.

Just remove the unnecessary complication then, a channel reset is good enough. We still need the initialisation marker, now per channel rather than per SCC, as for the console port zs_reset() will be called twice:
once early on via zs_serial_console_init() for the console setup only, and then again via zs_config_port() as the port is associated with a TTY device.

Fixes 8b4a40809e53 ("zs: move to the serial subsystem")
Cc [email protected] # v2.6.23+
---
 drivers/tty/serial/zs.c |    7 ++++---
 drivers/tty/serial/zs.h |    2 +-
 2 files changed, 5 insertions(+), 4 deletions(-)
drivers/tty/serial/zs.c +4 -3
@@ -831,21 +831,22 @@ static void zs_shutdown(struct uart_port
 
 static void zs_reset(struct zs_port *zport)
 {
+	struct zs_port *zport_a = &zport->scc->zport[ZS_CHAN_A];
 	struct zs_scc *scc = zport->scc;
 	int irq;
 	unsigned long flags;
 
 	spin_lock_irqsave(&scc->zlock, flags);
 	irq = !irqs_disabled_flags(flags);
-	if (!scc->initialised) {
+	if (!zport->initialised) {
 		/* Reset the pointer first, just in case...  */
 		read_zsreg(zport, R0);
 		/* And let the current transmission finish.  */
 		zs_line_drain(zport, irq);
-		write_zsreg(zport, R9, FHWRES);
+		write_zsreg(zport, R9, zport == zport_a ? CHRA : CHRB);
 		udelay(10);
 		write_zsreg(zport, R9, 0);
-		scc->initialised = 1;
+		zport->initialised = 1;
 	}
 	load_zsregs(zport, zport->regs, irq);
 	spin_unlock_irqrestore(&scc->zlock, flags);
drivers/tty/serial/zs.h +1 -1
@@ -22,6 +22,7 @@
 struct zs_port {
 	struct zs_scc	*scc;			/* Containing SCC.  */
 	struct uart_port port;			/* Underlying UART.  */
+	int		initialised;		/* For the console port.  */
 
 	int		clk_mode;		/* May be 1, 16, 32, or 64.  */
 
@@ -41,7 +42,6 @@ struct zs_scc {
 	struct zs_port	zport[2];
 	spinlock_t	zlock;
 	atomic_t	irq_guard;
-	int		initialised;
 };
 
 #endif /* __KERNEL__ */
author maintainer
#189 lore raw

PATCH 179/522 HID: core: Add printk_ratelimited variants to hid_warn() etc

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Vicki Pfau <[email protected]>

[ Upstream commit 1d64624243af8329b4b219d8c39e28ea448f9929 ]

hid_warn_ratelimited() is needed. Add the others as part of the block.

---
 include/linux/hid.h | 11 +++++++++++
 1 file changed, 11 insertions(+)
include/linux/hid.h +11 -0
index 6c3dc24acefc2d..058ba486fdcf87 100644
@@ -1230,4 +1230,15 @@ do {									\
 #define hid_dbg_once(hid, fmt, ...)			\
 	dev_dbg_once(&(hid)->dev, fmt, ##__VA_ARGS__)
 
+#define hid_err_ratelimited(hid, fmt, ...)			\
+	dev_err_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
+#define hid_notice_ratelimited(hid, fmt, ...)			\
+	dev_notice_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
+#define hid_warn_ratelimited(hid, fmt, ...)			\
+	dev_warn_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
+#define hid_info_ratelimited(hid, fmt, ...)			\
+	dev_info_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
+#define hid_dbg_ratelimited(hid, fmt, ...)			\
+	dev_dbg_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
+
 #endif
Signature · 1 line
2.53.0
author maintainer
#190 lore raw

PATCH 180/522 HID: pass the buffer size to hid_report_raw_event

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Benjamin Tissoires <[email protected]>

[ Upstream commit 2c85c61d1332e1e16f020d76951baf167dcb6f7a ]

commit 0a3fe972a7cb ("HID: core: Mitigate potential OOB by removing bogus memset()") enforced the provided data to be at least the size of the declared buffer in the report descriptor to prevent a buffer overflow. However, we can try to be smarter by providing both the buffer size and the data size, meaning that hid_report_raw_event() can make better decision whether we should plaining reject the buffer (buffer overflow attempt) or if we can safely memset it to 0 and pass it to the rest of the stack.

Fixes 0a3fe972a7cb ("HID: core: Mitigate potential OOB by removing bogus memset()")

Stable-dep-of: 206342541fc8 ("HID: core: introduce hid_safe_input_report()")

[Lee: Backported to linux-6.12.y and beyond]
---
 drivers/hid/hid-core.c           | 33 +++++++++++++++++++++++---------
 drivers/hid/hid-gfrm.c           |  4 ++--
 drivers/hid/hid-logitech-hidpp.c |  2 +-
 drivers/hid/hid-multitouch.c     |  2 +-
 drivers/hid/hid-primax.c         |  2 +-
 drivers/hid/hid-vivaldi-common.c |  2 +-
 drivers/hid/wacom_sys.c          |  6 +++---
 drivers/staging/greybus/hid.c    |  2 +-
 include/linux/hid.h              |  4 ++--
 9 files changed, 36 insertions(+), 21 deletions(-)
drivers/hid/hid-core.c +24 -9
index 3f3de08969b55c..2be5823002a3a4 100644
@@ -1989,24 +1989,32 @@ int __hid_request(struct hid_device *hid, struct hid_report *report,
 }
 EXPORT_SYMBOL_GPL(__hid_request);
 
-int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size,
-			 int interrupt)
+int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data,
+			 size_t bufsize, u32 size, int interrupt)
 {
 	struct hid_report_enum *report_enum = hid->report_enum + type;
 	struct hid_report *report;
 	struct hid_driver *hdrv;
 	int max_buffer_size = HID_MAX_BUFFER_SIZE;
 	u32 rsize, csize = size;
+	size_t bsize = bufsize;
 	u8 *cdata = data;
 	int ret = 0;
 
 	report = hid_get_report(report_enum, data);
 	if (!report)
-		goto out;
+		return 0;
+
+	if (unlikely(bsize < csize)) {
+		hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %ld)\n",
+				     report->id, csize, bsize);
+		return -EINVAL;
+	}
 
 	if (report_enum->numbered) {
 		cdata++;
 		csize--;
+		bsize--;
 	}
 
 	rsize = hid_compute_report_size(report);
@@ -2019,9 +2027,15 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *
 	else if (rsize > max_buffer_size)
 		rsize = max_buffer_size;
 
+	if (bsize < rsize) {
+		hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %ld)\n",
+				     report->id, rsize, bsize);
+		return -EINVAL;
+	}
+
 	if (csize < rsize) {
 		dbg_hid("report %d is too short, (%d < %d)\n", report->id,
-				csize, rsize);
+			csize, rsize);
 		memset(cdata + csize, 0, rsize - csize);
 	}
 
@@ -2030,7 +2044,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *
 	if (hid->claimed & HID_CLAIMED_HIDRAW) {
 		ret = hidraw_report_event(hid, data, size);
 		if (ret)
-			goto out;
+			return ret;
 	}
 
 	if (hid->claimed != HID_CLAIMED_HIDRAW && report->maxfield) {
@@ -2042,7 +2056,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *
 
 	if (hid->claimed & HID_CLAIMED_INPUT)
 		hidinput_report_event(hid, report);
-out:
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(hid_report_raw_event);
@@ -2058,12 +2072,13 @@ EXPORT_SYMBOL_GPL(hid_report_raw_event);
  *
  * This is data entry for lower layers.
  */
-int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size,
-		     int interrupt)
+int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data,
+		     u32 size, int interrupt)
 {
 	struct hid_report_enum *report_enum;
 	struct hid_driver *hdrv;
 	struct hid_report *report;
+	size_t bufsize = size;
 	int ret = 0;
 
 	if (!hid)
@@ -2102,7 +2117,7 @@ int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data
 			goto unlock;
 	}
 
-	ret = hid_report_raw_event(hid, type, data, size, interrupt);
+	ret = hid_report_raw_event(hid, type, data, bufsize, size, interrupt);
 
 unlock:
 	up(&hid->driver_input_lock);
drivers/hid/hid-gfrm.c +2 -2
index 699186ff2349e9..d2a56bf92b416e 100644
@@ -66,7 +66,7 @@ static int gfrm_raw_event(struct hid_device *hdev, struct hid_report *report,
 	switch (data[1]) {
 	case GFRM100_SEARCH_KEY_DOWN:
 		ret = hid_report_raw_event(hdev, HID_INPUT_REPORT, search_key_dn,
-					   sizeof(search_key_dn), 1);
+					   sizeof(search_key_dn), sizeof(search_key_dn), 1);
 		break;
 
 	case GFRM100_SEARCH_KEY_AUDIO_DATA:
@@ -74,7 +74,7 @@ static int gfrm_raw_event(struct hid_device *hdev, struct hid_report *report,
 
 	case GFRM100_SEARCH_KEY_UP:
 		ret = hid_report_raw_event(hdev, HID_INPUT_REPORT, search_key_up,
-					   sizeof(search_key_up), 1);
+					   sizeof(search_key_up), sizeof(search_key_up), 1);
 		break;
 
 	default:
drivers/hid/hid-logitech-hidpp.c +1 -1
index c65b5f004bac57..89b0374bb9a851 100644
@@ -3451,7 +3451,7 @@ static int hidpp10_consumer_keys_raw_event(struct hidpp_device *hidpp,
 	memcpy(&consumer_report[1], &data[3], 4);
 	/* We are called from atomic context */
 	hid_report_raw_event(hidpp->hid_dev, HID_INPUT_REPORT,
-			     consumer_report, 5, 1);
+			     consumer_report, sizeof(consumer_report), 5, 1);
 
 	return 1;
 }
drivers/hid/hid-multitouch.c +1 -1
index 0039508943626d..6c04eed0a46464 100644
@@ -479,7 +479,7 @@ static void mt_get_feature(struct hid_device *hdev, struct hid_report *report)
 		}
 
 		ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, buf,
-					   size, 0);
+					   size, size, 0);
 		if (ret)
 			dev_warn(&hdev->dev, "failed to report feature\n");
 	}
drivers/hid/hid-primax.c +1 -1
index 1e6413d07cae21..16e2a811eda9f0 100644
@@ -44,7 +44,7 @@ static int px_raw_event(struct hid_device *hid, struct hid_report *report,
 			data[0] |= (1 << (data[idx] - 0xE0));
 			data[idx] = 0;
 		}
-		hid_report_raw_event(hid, HID_INPUT_REPORT, data, size, 0);
+		hid_report_raw_event(hid, HID_INPUT_REPORT, data, size, size, 0);
 		return 1;
 
 	default:	/* unknown report */
drivers/hid/hid-vivaldi-common.c +1 -1
index b0af2be948952c..7fb986615768f7 100644
@@ -85,7 +85,7 @@ void vivaldi_feature_mapping(struct hid_device *hdev,
 	}
 
 	ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, report_data,
-				   report_len, 0);
+				   report_len, report_len, 0);
 	if (ret) {
 		dev_warn(&hdev->dev, "failed to report feature %d\n",
 			 field->report->id);
drivers/hid/wacom_sys.c +3 -3
index 9106f16e42df23..9d2a54451b0b5f 100644
@@ -74,7 +74,7 @@ static void wacom_wac_queue_flush(struct hid_device *hdev,
 		int err;
 
 		size = kfifo_out(fifo, buf, sizeof(buf));
-		err = hid_report_raw_event(hdev, HID_INPUT_REPORT, buf, size, false);
+		err = hid_report_raw_event(hdev, HID_INPUT_REPORT, buf, size, size, false);
 		if (err) {
 			hid_warn(hdev, "%s: unable to flush event due to error %d\n",
 				 __func__, err);
@@ -319,7 +319,7 @@ static void wacom_feature_mapping(struct hid_device *hdev,
 					       data, n, WAC_CMD_RETRIES);
 			if (ret == n && features->type == HID_GENERIC) {
 				ret = hid_report_raw_event(hdev,
-					HID_FEATURE_REPORT, data, n, 0);
+					HID_FEATURE_REPORT, data, n, n, 0);
 			} else if (ret == 2 && features->type != HID_GENERIC) {
 				features->touch_max = data[1];
 			} else {
@@ -381,7 +381,7 @@ static void wacom_feature_mapping(struct hid_device *hdev,
 					data, n, WAC_CMD_RETRIES);
 		if (ret == n) {
 			ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT,
-						   data, n, 0);
+						   data, n, n, 0);
 		} else {
 			hid_warn(hdev, "%s: could not retrieve sensor offsets\n",
 				 __func__);
drivers/staging/greybus/hid.c +1 -1
index adb91286803a91..49b42c0ab078ec 100644
@@ -201,7 +201,7 @@ static void gb_hid_init_report(struct gb_hid *ghid, struct hid_report *report)
 	 * we just need to setup the input fields, so using
 	 * hid_report_raw_event is safe.
 	 */
-	hid_report_raw_event(ghid->hid, report->type, ghid->inbuf, size, 1);
+	hid_report_raw_event(ghid->hid, report->type, ghid->inbuf, ghid->bufsize, size, 1);
 }
 
 static void gb_hid_init_reports(struct gb_hid *ghid)
include/linux/hid.h +2 -2
index 058ba486fdcf87..c57fc6a918c030 100644
@@ -1188,8 +1188,8 @@ static inline u32 hid_report_len(struct hid_report *report)
 	return DIV_ROUND_UP(report->size, 8) + (report->id > 0);
 }
 
-int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size,
-			 int interrupt);
+int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *data,
+			 size_t bufsize, u32 size, int interrupt);
 
 /* HID quirks API */
 unsigned long hid_lookup_quirk(const struct hid_device *hdev);
Signature · 1 line
2.53.0
author maintainer
#191 lore raw

PATCH 181/522 HID: core: Fix size_t specifier in hid_report_raw_event()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Nathan Chancellor <[email protected]>

[ Upstream commit 4d3a2a466b8d68d852a1f3bbf11204b718428dc4 ]

When building for 32-bit platforms, for which 'size_t' is 'unsigned int', there are warnings around using the incorrect format specifier to print bsize in hid_report_raw_event():

drivers/hid/hid-core.c:2054:29: error: format specifies type 'long' but the argument has type 'size_t' (aka 'unsigned int') [-Werror,-Wformat]

   2053 |                 hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %ld)\n",
        |                                                                                         ~~~
        |                                                                                         %zu
   2054 |                                      report->id, csize, bsize);
        |                                                         ^~~~~
  drivers/hid/hid-core.c:2076:29: error: format specifies type 'long' but the argument has type 'size_t' (aka 'unsigned int') [-Werror,-Wformat]
   2075 |                 hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %ld)\n",
        |                                                                                          ~~~
        |                                                                                          %zu
   2076 |                                      report->id, rsize, bsize);
        |                                                         ^~~~~

Use the proper 'size_t' format specifier, '%zu', to clear up the warnings.

---
 drivers/hid/hid-core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/hid/hid-core.c +2 -2
index 2be5823002a3a4..2191205ce5b0bf 100644
@@ -2006,7 +2006,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *
 		return 0;
 
 	if (unlikely(bsize < csize)) {
-		hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %ld)\n",
+		hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %zu)\n",
 				     report->id, csize, bsize);
 		return -EINVAL;
 	}
@@ -2028,7 +2028,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 *
 		rsize = max_buffer_size;
 
 	if (bsize < rsize) {
-		hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %ld)\n",
+		hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %zu)\n",
 				     report->id, rsize, bsize);
 		return -EINVAL;
 	}
Signature · 1 line
2.53.0
author maintainer
#192 lore raw

PATCH 182/522 RDMA/rxe: Complete the rxe_cleanup_task backport

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Vladislav Nikolaev <[email protected]>

No upstream commit exists for this patch.

The issue was introduced with backporting upstream commit b2b1ddc45745 ("RDMA/rxe: Fix the error "trying to register non-static key in rxe_cleanup_task"") to the 6.1 stable tree as commit 3236221bb8e4 ("RDMA/rxe: Fix the error "trying to register non-static key in rxe_cleanup_task"").

The 6.1 backport guarded qp->req.task and qp->comp.task before calling rxe_cleanup_task(), but left qp->resp.task unguarded. It also kept the responder task cleanup before deleting the RC timers, while upstream had already moved it after the timer shutdown by commit 960ebe97e523 ("RDMA/rxe: Remove __rxe_do_task()").

In the 6.1 tree, rxe_qp_from_init() calls rxe_qp_init_req() before rxe_qp_init_resp(). Therefore, if rxe_qp_init_req() fails, cleanup can run before qp->resp.task has been initialized by rxe_init_task(), and the unconditional rxe_cleanup_task(&qp->resp.task) can still hit the same uninitialized task lock problem that upstream commit b2b1ddc45745 fixed.

Move responder task cleanup after deleting the RC timers, matching the upstream cleanup order, and guard it with qp->resp.task.func like the requester and completer tasks.

Fixes 3236221bb8e4 ("RDMA/rxe: Fix the error "trying to register non-static key in rxe_cleanup_task"")
---
 drivers/infiniband/sw/rxe/rxe_qp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/infiniband/sw/rxe/rxe_qp.c +3 -1
index 709c63e9773c5f..171c0f4dcbecfc 100644
@@ -781,13 +781,15 @@ static void rxe_qp_do_cleanup(struct work_struct *work)
 
 	qp->valid = 0;
 	qp->qp_timeout_jiffies = 0;
-	rxe_cleanup_task(&qp->resp.task);
 
 	if (qp_type(qp) == IB_QPT_RC) {
 		del_timer_sync(&qp->retrans_timer);
 		del_timer_sync(&qp->rnr_nak_timer);
 	}
 
+	if (qp->resp.task.func)
+		rxe_cleanup_task(&qp->resp.task);
+
 	if (qp->req.task.func)
 		rxe_cleanup_task(&qp->req.task);
 
Signature · 1 line
2.53.0
author maintainer
#193 lore raw

PATCH 183/522 USB: serial: digi_acceleport: fix memory corruption with small endpoints

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Johan Hovold <[email protected]>

commit cb3560e8eab1dfa1cac1ed52631adf8ec6ff2cd5 upstream.

Add the missing bulk-out buffer size sanity checks to avoid out-of-bounds memory accesses or slab corruption should a malicious device report smaller buffers than expected.

Fixes 1da177e4c3f4 ("Linux-2.6.12-rc2")
---
 drivers/usb/serial/digi_acceleport.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)
drivers/usb/serial/digi_acceleport.c +21 -2
index 45d688e9b93f68..eb23f7bb41e728 100644
@@ -1230,15 +1230,34 @@ static int digi_port_init(struct usb_serial_port *port, unsigned port_num)
 static int digi_startup(struct usb_serial *serial)
 {
 	struct digi_serial *serial_priv;
+	int oob_port_num;
 	int ret;
+	int i;
+
+	/*
+	 * The port bulk-out buffers must be large enough for header and
+	 * buffered data.
+	 */
+	for (i = 0; i < serial->type->num_ports; i++) {
+		if (serial->port[i]->bulk_out_size < DIGI_OUT_BUF_SIZE + 2)
+			return -EINVAL;
+	}
+
+	/*
+	 * The OOB port bulk-out buffer must be large enough for the two
+	 * commands in digi_set_modem_signals().
+	 */
+	oob_port_num = serial->type->num_ports;
+	if (serial->port[oob_port_num]->bulk_out_size < 8)
+		return -EINVAL;
 
 	serial_priv = kzalloc(sizeof(*serial_priv), GFP_KERNEL);
 	if (!serial_priv)
 		return -ENOMEM;
 
 	spin_lock_init(&serial_priv->ds_serial_lock);
-	serial_priv->ds_oob_port_num = serial->type->num_ports;
-	serial_priv->ds_oob_port = serial->port[serial_priv->ds_oob_port_num];
+	serial_priv->ds_oob_port_num = oob_port_num;
+	serial_priv->ds_oob_port = serial->port[oob_port_num];
 
 	ret = digi_port_init(serial_priv->ds_oob_port,
 						serial_priv->ds_oob_port_num);
Signature · 1 line
2.53.0
author maintainer
#194 lore raw

PATCH 184/522 xhci: tegra: Fix ghost USB device on dual-role port unplug

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Wei-Cheng Chen <[email protected]>

[ Upstream commit 5a4c828b8b29b47534814ade26d9aee09d5101fc ]

When a USB device is unplugged from the dual-role port, the device-mode path in tegra_xhci_id_work() explicitly clears both SS and HS port power via direct hub_control ClearPortFeature(POWER) calls. This preempts the xHCI controller's normal disconnect processing -- PORT_CSC is never generated, the USB core never sees the disconnect, and the device remains in its internal tree as a ghost visible in lsusb.

Add an otg_set_port_power flag to control whether the dual-role switch path performs explicit port power management. SoCs that need it (Tegra124 / Tegra210 / Tegra186) set the flag; later SoCs (Tegra194 and beyond) rely on the PHY mode change to handle disconnect naturally and skip all port power calls.

Within the port power path, otg_reset_sspi additionally gates the SSPI reset sequence on host-mode entry for SoCs that require it.

Flags set per SoC:

  Tegra124, Tegra186  -> otg_set_port_power
  Tegra210            -> otg_set_port_power, otg_reset_sspi
  Tegra194 and later  -> (none)

[ Backport to 6.1.y: keep the host-mode snapshot in the existing
tegra->lock section, retain pm_runtime_mark_last_busy() in the host port-power path, and omit the newer Tegra234 entry. ]

---
 drivers/usb/host/xhci-tegra.c | 78 ++++++++++++++++++++---------------
 1 file changed, 44 insertions(+), 34 deletions(-)
drivers/usb/host/xhci-tegra.c +44 -34
index 14a772feab7946..0f936aeb88d064 100644
@@ -210,6 +210,7 @@ struct tegra_xusb_soc {
 	bool has_ipfs;
 	bool lpm_support;
 	bool otg_reset_sspi;
+	bool otg_set_port_power;
 };
 
 struct tegra_xusb_context {
@@ -1211,14 +1212,17 @@ static void tegra_xhci_id_work(struct work_struct *work)
 	struct tegra_xusb_mbox_msg msg;
 	struct phy *phy = tegra_xusb_get_phy(tegra, "usb2",
 						    tegra->otg_usb2_port);
+	bool host_mode;
 	u32 status;
 	int ret;
 
-	dev_dbg(tegra->dev, "host mode %s\n", tegra->host_mode ? "on" : "off");
-
 	mutex_lock(&tegra->lock);
 
-	if (tegra->host_mode)
+	host_mode = tegra->host_mode;
+
+	dev_dbg(tegra->dev, "host mode %s\n", host_mode ? "on" : "off");
+
+	if (host_mode)
 		phy_set_mode_ext(phy, PHY_MODE_USB_OTG, USB_ROLE_HOST);
 	else
 		phy_set_mode_ext(phy, PHY_MODE_USB_OTG, USB_ROLE_NONE);
@@ -1229,42 +1233,44 @@ static void tegra_xhci_id_work(struct work_struct *work)
 								    tegra->otg_usb2_port);
 
 	pm_runtime_get_sync(tegra->dev);
-	if (tegra->host_mode) {
-		/* switch to host mode */
-		if (tegra->otg_usb3_port >= 0) {
-			if (tegra->soc->otg_reset_sspi) {
-				/* set PP=0 */
-				tegra_xhci_hc_driver.hub_control(
-					xhci->shared_hcd, GetPortStatus,
-					0, tegra->otg_usb3_port+1,
-					(char *) &status, sizeof(status));
-				if (status & USB_SS_PORT_STAT_POWER)
-					tegra_xhci_set_port_power(tegra, false,
-								  false);
-
-				/* reset OTG port SSPI */
-				msg.cmd = MBOX_CMD_RESET_SSPI;
-				msg.data = tegra->otg_usb3_port+1;
-
-				ret = tegra_xusb_mbox_send(tegra, &msg);
-				if (ret < 0) {
-					dev_info(tegra->dev,
-						"failed to RESET_SSPI %d\n",
-						ret);
+	if (tegra->soc->otg_set_port_power) {
+		if (host_mode) {
+			/* switch to host mode */
+			if (tegra->otg_usb3_port >= 0) {
+				if (tegra->soc->otg_reset_sspi) {
+					/* set PP=0 */
+					tegra_xhci_hc_driver.hub_control(
+						xhci->shared_hcd, GetPortStatus,
+						0, tegra->otg_usb3_port+1,
+						(char *) &status, sizeof(status));
+					if (status & USB_SS_PORT_STAT_POWER)
+						tegra_xhci_set_port_power(tegra, false,
+									  false);
+
+					/* reset OTG port SSPI */
+					msg.cmd = MBOX_CMD_RESET_SSPI;
+					msg.data = tegra->otg_usb3_port+1;
+
+					ret = tegra_xusb_mbox_send(tegra, &msg);
+					if (ret < 0) {
+						dev_info(tegra->dev,
+							"failed to RESET_SSPI %d\n",
+							ret);
+					}
 				}
-			}
 
-			tegra_xhci_set_port_power(tegra, false, true);
-		}
+				tegra_xhci_set_port_power(tegra, false, true);
+			}
 
-		tegra_xhci_set_port_power(tegra, true, true);
-		pm_runtime_mark_last_busy(tegra->dev);
+			tegra_xhci_set_port_power(tegra, true, true);
+			pm_runtime_mark_last_busy(tegra->dev);
 
-	} else {
-		if (tegra->otg_usb3_port >= 0)
-			tegra_xhci_set_port_power(tegra, false, false);
+		} else {
+			if (tegra->otg_usb3_port >= 0)
+				tegra_xhci_set_port_power(tegra, false, false);
 
-		tegra_xhci_set_port_power(tegra, true, false);
+			tegra_xhci_set_port_power(tegra, true, false);
+		}
 	}
 	pm_runtime_put_autosuspend(tegra->dev);
 }
@@ -2289,6 +2295,7 @@ static const struct tegra_xusb_soc tegra124_soc = {
 	.scale_ss_clock = true,
 	.has_ipfs = true,
 	.otg_reset_sspi = false,
+	.otg_set_port_power = true,
 	.mbox = {
 		.cmd = 0xe4,
 		.data_in = 0xe8,
@@ -2325,6 +2332,7 @@ static const struct tegra_xusb_soc tegra210_soc = {
 	.scale_ss_clock = false,
 	.has_ipfs = true,
 	.otg_reset_sspi = true,
+	.otg_set_port_power = true,
 	.mbox = {
 		.cmd = 0xe4,
 		.data_in = 0xe8,
@@ -2366,6 +2374,7 @@ static const struct tegra_xusb_soc tegra186_soc = {
 	.scale_ss_clock = false,
 	.has_ipfs = false,
 	.otg_reset_sspi = false,
+	.otg_set_port_power = true,
 	.mbox = {
 		.cmd = 0xe4,
 		.data_in = 0xe8,
@@ -2397,6 +2406,7 @@ static const struct tegra_xusb_soc tegra194_soc = {
 	.scale_ss_clock = false,
 	.has_ipfs = false,
 	.otg_reset_sspi = false,
+	.otg_set_port_power = false,
 	.mbox = {
 		.cmd = 0x68,
 		.data_in = 0x6c,
Signature · 1 line
2.53.0
author maintainer
#195 lore raw

PATCH 185/522 netfilter: nf_tables: restore set elements when delete set fails

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Pablo Neira Ayuso <[email protected]>

[ Upstream commit e79b47a8615d42c68aaeb68971593333667382ed ]

Quoted 1 line

From abort path, nft_mapelem_activate() needs to restore refcounters to

the original state. Currently, it uses the set->ops->walk() to iterate over these set elements. The existing set iterator skips inactive elements in the next generation, this does not work from the abort path to restore the original state since it has to skip active elements instead (not inactive ones).

This patch moves the check for inactive elements to the set iterator callback, then it reverses the logic for the .activate case which needs to skip active elements.

Toggle next generation bit for elements when delete set command is invoked and call nft_clear() from .activate (abort) path to restore the next generation bit.

The splat below shows an object in mappings memleak:

[43929.457523] ------------[ cut here ]------------
[43929.457532] WARNING: CPU: 0 PID: 1139 at include/net/netfilter/nf_tables.h:1237 nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables]
[...]
[43929.458014] RIP: 0010:nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables]
[43929.458076] Code: 83 f8 01 77 ab 49 8d 7c 24 08 e8 37 5e d0 de 49 8b 6c 24 08 48 8d 7d 50 e8 e9 5c d0 de 8b 45 50 8d 50 ff 89 55 50 85 c0 75 86 <0f> 0b eb 82 0f 0b eb b3 0f 1f 40 00 90 90 90 90 90 90 90 90 90 90
[43929.458081] RSP: 0018:ffff888140f9f4b0 EFLAGS: 00010246
[43929.458086] RAX: 0000000000000000 RBX: ffff8881434f5288 RCX: dffffc0000000000
[43929.458090] RDX: 00000000ffffffff RSI: ffffffffa26d28a7 RDI: ffff88810ecc9550
[43929.458093] RBP: ffff88810ecc9500 R08: 0000000000000001 R09: ffffed10281f3e8f
[43929.458096] R10: 0000000000000003 R11: ffff0000ffff0000 R12: ffff8881434f52a0
[43929.458100] R13: ffff888140f9f5f4 R14: ffff888151c7a800 R15: 0000000000000002
[43929.458103] FS:  00007f0c687c4740(0000) GS:ffff888390800000(0000) knlGS:0000000000000000
[43929.458107] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[43929.458111] CR2: 00007f58dbe5b008 CR3: 0000000123602005 CR4: 00000000001706f0
[43929.458114] Call Trace:
[43929.458118]  <TASK>
[43929.458121]  ? __warn+0x9f/0x1a0
[43929.458127]  ? nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables]
[43929.458188]  ? report_bug+0x1b1/0x1e0
[43929.458196]  ? handle_bug+0x3c/0x70
[43929.458200]  ? exc_invalid_op+0x17/0x40
[43929.458211]  ? nft_setelem_data_deactivate+0xd7/0xf0 [nf_tables]
[43929.458271]  ? nft_setelem_data_deactivate+0xe4/0xf0 [nf_tables]
[43929.458332]  nft_mapelem_deactivate+0x24/0x30 [nf_tables]
[43929.458392]  nft_rhash_walk+0xdd/0x180 [nf_tables]
[43929.458453]  ? __pfx_nft_rhash_walk+0x10/0x10 [nf_tables]
[43929.458512]  ? rb_insert_color+0x2e/0x280
[43929.458520]  nft_map_deactivate+0xdc/0x1e0 [nf_tables]
[43929.458582]  ? __pfx_nft_map_deactivate+0x10/0x10 [nf_tables]
[43929.458642]  ? __pfx_nft_mapelem_deactivate+0x10/0x10 [nf_tables]
[43929.458701]  ? __rcu_read_unlock+0x46/0x70
[43929.458709]  nft_delset+0xff/0x110 [nf_tables]
[43929.458769]  nft_flush_table+0x16f/0x460 [nf_tables]
[43929.458830]  nf_tables_deltable+0x501/0x580 [nf_tables]
Fixes 628bd3e49cba ("netfilter: nf_tables: drop map element references from preparation phase")
(cherry picked from commit e79b47a8615d42c68aaeb68971593333667382ed)

[Vegard: CVE-2024-27012; fixed conflicts due to missing commits
0e1ea651c9717ddcd8e0648d8468477a31867b0a ("netfilter: nf_tables: shrink memory consumption of set elements") and 9dad402b89e81a0516bad5e0ac009b7a0a80898f ("netfilter: nf_tables: expose opaque set element as struct nft_elem_priv") so we pass the correct types and values to nft_setelem_data_deactivate(), nft_setelem_validate(), nft_set_elem_ext(), etc.]

[acsjakub: clean cherry-pick of the commit 164936b2fc88
("netfilter: nf_tables: restore set elements when delete set fails") from 6.6.y. Plus, add "[ Upstream commit .." header to the message]

---
 net/netfilter/nf_tables_api.c  | 41 ++++++++++++++++++++++++++++++----
 net/netfilter/nft_set_bitmap.c |  4 +---
 net/netfilter/nft_set_hash.c   |  8 ++-----
 net/netfilter/nft_set_pipapo.c |  5 +----
 net/netfilter/nft_set_rbtree.c |  4 +---
 5 files changed, 42 insertions(+), 20 deletions(-)
net/netfilter/nf_tables_api.c +37 -4
index 0c422428263873..201e2cc0453992 100644
@@ -594,6 +594,12 @@ static int nft_mapelem_deactivate(const struct nft_ctx *ctx,
 				  const struct nft_set_iter *iter,
 				  struct nft_set_elem *elem)
 {
+	struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+
+	if (!nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
+	nft_set_elem_change_active(ctx->net, set, ext);
 	nft_setelem_data_deactivate(ctx->net, set, elem);
 
 	return 0;
@@ -619,6 +625,7 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx,
 			continue;
 
 		elem.priv = catchall->elem;
+		nft_set_elem_change_active(ctx->net, set, ext);
 		nft_setelem_data_deactivate(ctx->net, set, &elem);
 		break;
 	}
@@ -3593,6 +3600,9 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set,
 	const struct nft_data *data;
 	int err;
 
+	if (!nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
 	    *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
 		return 0;
@@ -3616,19 +3626,22 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set,
 
 int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set)
 {
-	u8 genmask = nft_genmask_next(ctx->net);
+	struct nft_set_iter dummy_iter = {
+		.genmask	= nft_genmask_next(ctx->net),
+	};
 	struct nft_set_elem_catchall *catchall;
 	struct nft_set_elem elem;
+
 	struct nft_set_ext *ext;
 	int ret = 0;
 
 	list_for_each_entry_rcu(catchall, &set->catchall_list, list) {
 		ext = nft_set_elem_ext(set, catchall->elem);
-		if (!nft_set_elem_active(ext, genmask))
+		if (!nft_set_elem_active(ext, dummy_iter.genmask))
 			continue;
 
 		elem.priv = catchall->elem;
-		ret = nft_setelem_validate(ctx, set, NULL, &elem);
+		ret = nft_setelem_validate(ctx, set, &dummy_iter, &elem);
 		if (ret < 0)
 			return ret;
 	}
@@ -5103,6 +5116,11 @@ static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx,
 					const struct nft_set_iter *iter,
 					struct nft_set_elem *elem)
 {
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+
+	if (!nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
 	return nft_setelem_data_validate(ctx, set, elem);
 }
 
@@ -5197,6 +5215,13 @@ static int nft_mapelem_activate(const struct nft_ctx *ctx,
 				const struct nft_set_iter *iter,
 				struct nft_set_elem *elem)
 {
+	struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+
+	/* called from abort path, reverse check to undo changes. */
+	if (nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
+	nft_clear(ctx->net, ext);
 	nft_setelem_data_activate(ctx->net, set, elem);
 
 	return 0;
@@ -5215,6 +5240,7 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx,
 		if (nft_set_elem_active(ext, genmask))
 			continue;
 
+		nft_clear(ctx->net, ext);
 		elem.priv = catchall->elem;
 		nft_setelem_data_activate(ctx->net, set, &elem);
 		break;
@@ -5488,6 +5514,9 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	struct nft_set_dump_args *args;
 
+	if (!nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
 	if (nft_set_elem_expired(ext) || nft_set_elem_is_dead(ext))
 		return 0;
 
@@ -6220,7 +6249,7 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set,
 	struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 
 	if (nft_setelem_is_catchall(set, elem)) {
-		nft_set_elem_change_active(net, set, ext);
+		nft_clear(net, ext);
 	} else {
 		set->ops->activate(net, set, elem);
 	}
@@ -6902,9 +6931,13 @@ static int nft_setelem_flush(const struct nft_ctx *ctx,
 			     const struct nft_set_iter *iter,
 			     struct nft_set_elem *elem)
 {
+	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	struct nft_trans *trans;
 	int err;
 
+	if (!nft_set_elem_active(ext, iter->genmask))
+		return 0;
+
 	trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM,
 				    sizeof(struct nft_trans_elem), GFP_ATOMIC);
 	if (!trans)
net/netfilter/nft_set_bitmap.c +1 -3
index 1e5e7a181e0bc2..cbf7f7825f1b88 100644
@@ -171,7 +171,7 @@ static void nft_bitmap_activate(const struct net *net,
 	nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off);
 	/* Enter 11 state. */
 	priv->bitmap[idx] |= (genmask << off);
-	nft_set_elem_change_active(net, set, &be->ext);
+	nft_clear(net, &be->ext);
 }
 
 static bool nft_bitmap_flush(const struct net *net,
@@ -223,8 +223,6 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx,
 	list_for_each_entry_rcu(be, &priv->list, head) {
 		if (iter->count < iter->skip)
 			goto cont;
-		if (!nft_set_elem_active(&be->ext, iter->genmask))
-			goto cont;
 
 		elem.priv = be;
 
net/netfilter/nft_set_hash.c +2 -6
index 9ea4a09903186d..5a74ee4b7dfb35 100644
@@ -196,7 +196,7 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set,
 {
 	struct nft_rhash_elem *he = elem->priv;
 
-	nft_set_elem_change_active(net, set, &he->ext);
+	nft_clear(net, &he->ext);
 }
 
 static bool nft_rhash_flush(const struct net *net,
@@ -285,8 +285,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set,
 
 		if (iter->count < iter->skip)
 			goto cont;
-		if (!nft_set_elem_active(&he->ext, iter->genmask))
-			goto cont;
 
 		elem.priv = he;
 
@@ -615,7 +613,7 @@ static void nft_hash_activate(const struct net *net, const struct nft_set *set,
 {
 	struct nft_hash_elem *he = elem->priv;
 
-	nft_set_elem_change_active(net, set, &he->ext);
+	nft_clear(net, &he->ext);
 }
 
 static bool nft_hash_flush(const struct net *net,
@@ -669,8 +667,6 @@ static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set,
 		hlist_for_each_entry_rcu(he, &priv->table[i], node) {
 			if (iter->count < iter->skip)
 				goto cont;
-			if (!nft_set_elem_active(&he->ext, iter->genmask))
-				goto cont;
 
 			elem.priv = he;
 
net/netfilter/nft_set_pipapo.c +1 -4
index cfd0d020f3382b..11473275c6e263 100644
@@ -1849,7 +1849,7 @@ static void nft_pipapo_activate(const struct net *net,
 {
 	struct nft_pipapo_elem *e = elem->priv;
 
-	nft_set_elem_change_active(net, set, &e->ext);
+	nft_clear(net, &e->ext);
 }
 
 /**
@@ -2151,9 +2151,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set,
 
 		e = f->mt[r].e;
 
-		if (!nft_set_elem_active(&e->ext, iter->genmask))
-			goto cont;
-
 		elem.priv = e;
 
 		iter->err = iter->fn(ctx, set, iter, &elem);
net/netfilter/nft_set_rbtree.c +1 -3
index 426becaad1b94f..23e4e656f7f0cb 100644
@@ -548,7 +548,7 @@ static void nft_rbtree_activate(const struct net *net,
 {
 	struct nft_rbtree_elem *rbe = elem->priv;
 
-	nft_set_elem_change_active(net, set, &rbe->ext);
+	nft_clear(net, &rbe->ext);
 }
 
 static bool nft_rbtree_flush(const struct net *net,
@@ -618,8 +618,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 		if (iter->count < iter->skip)
 			goto cont;
-		if (!nft_set_elem_active(&rbe->ext, iter->genmask))
-			goto cont;
 
 		elem.priv = rbe;
 
Signature · 1 line
2.53.0
author maintainer
#196 lore raw

PATCH 186/522 USB: serial: cypress_m8: fix memory corruption with small endpoint

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Johan Hovold <[email protected]>

commit e1a9d791fd66ab2431b9e6f6f835823809869047 upstream.

Make sure that the interrupt-out endpoint max packet size is at least eight bytes to avoid user-controlled slab corruption or NULL-pointer dereference should a malicious device report a smaller size.

Fixes 3416eaa1f8f8 ("USB: cypress_m8: Packet format is separate from characteristic size")
Cc [email protected] # 2.6.26
[ johan: adjust context for 6.18 ]
---
 drivers/usb/serial/cypress_m8.c | 8 ++++++++
 1 file changed, 8 insertions(+)
drivers/usb/serial/cypress_m8.c +8 -0
index 4c625e77da3a8f..f567617c8f2314 100644
@@ -448,6 +448,14 @@ static int cypress_generic_port_probe(struct usb_serial_port *port)
 		return -ENODEV;
 	}
 
+	/*
+	 * The buffer must be large enough for the one or two-byte header (and
+	 * following data), but assume anything smaller than eight bytes is
+	 * broken.
+	 */
+	if (port->interrupt_out_size < 8)
+		return -EINVAL;
+
 	priv = kzalloc(sizeof(struct cypress_private), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
Signature · 1 line
2.53.0
author maintainer
#197 lore raw

PATCH 187/522 serial: dz: Fix bootconsole handover lockup

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Maciej W. Rozycki <[email protected]>

commit 7f127b2208e5e2b817243cad41fe4211a6d5a7a3 upstream.

Calling dz_reset() in the course of setting up the serial device causes line parameters to be reset and the transmitter disabled. We've been lucky in that no message is usually produced to the kernel log between this call and the later call to uart_set_options() in the course of console setup done by dz_serial_console_init(), or the system would hang as the console output handler in the firmware tried to access a port the transmitter of which has been disabled and line parameters messed up.

This will change with the next change to the driver, so fix dz_reset() such that line parameters are set for 9600n8 console operation as with the system firmware and the transmitter re-enabled after reset. This also means dz_pm() serves no purpose anymore, so drop it.

---
 drivers/tty/serial/dz.c | 36 ++++++++++++------------------------
 1 file changed, 12 insertions(+), 24 deletions(-)
drivers/tty/serial/dz.c +12 -24
index a16738799418ca..d80bbd95a7f786 100644
@@ -573,6 +573,18 @@ static void dz_reset(struct dz_port *dport)
 	while (dz_in(dport, DZ_CSR) & DZ_CLR);
 	iob();
 
+	/*
+	 * Set parameters across all lines such as not to interfere
+	 * with the initial PROM-based console.  Otherwise any output
+	 * produced before the console handover would cause the system
+	 * firmware to produce rubbish.
+	 */
+	for (int line = 0; line < DZ_NB_PORT; line++)
+		dz_out(dport, DZ_LPR, DZ_B9600 | DZ_CS8 | line);
+
+	/* Re-enable transmission for the initial PROM-based console.  */
+	dz_out(dport, DZ_TCR, tcr);
+
 	/* Enable scanning.  */
 	dz_out(dport, DZ_CSR, DZ_MSE);
 
@@ -656,26 +668,6 @@ static void dz_set_termios(struct uart_port *uport, struct ktermios *termios,
 	spin_unlock_irqrestore(&dport->port.lock, flags);
 }
 
-/*
- * Hack alert!
- * Required solely so that the initial PROM-based console
- * works undisturbed in parallel with this one.
- */
-static void dz_pm(struct uart_port *uport, unsigned int state,
-		  unsigned int oldstate)
-{
-	struct dz_port *dport = to_dport(uport);
-	unsigned long flags;
-
-	spin_lock_irqsave(&dport->port.lock, flags);
-	if (state < 3)
-		dz_start_tx(&dport->port);
-	else
-		dz_stop_tx(&dport->port);
-	spin_unlock_irqrestore(&dport->port.lock, flags);
-}
-
-
 static const char *dz_type(struct uart_port *uport)
 {
 	return "DZ";
@@ -771,7 +763,6 @@ static const struct uart_ops dz_ops = {
 	.startup	= dz_startup,
 	.shutdown	= dz_shutdown,
 	.set_termios	= dz_set_termios,
-	.pm		= dz_pm,
 	.type		= dz_type,
 	.release_port	= dz_release_port,
 	.request_port	= dz_request_port,
@@ -896,10 +887,7 @@ static int __init dz_console_setup(struct console *co, char *options)
 	if (ret)
 		return ret;
 
-	spin_lock_init(&dport->port.lock);	/* For dz_pm().  */
-
 	dz_reset(dport);
-	dz_pm(uport, 0, -1);
 
 	if (options)
 		uart_parse_options(options, &baud, &parity, &bits, &flow);
Signature · 1 line
2.53.0
author maintainer
#198 lore raw

PATCH 188/522 bpf/bonding: reject vlan+srcmac xmit_hash_policy change when XDP is loaded

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Jiayuan Chen <[email protected]>

[ Upstream commit 479d589b40b836442bbdadc3fdb37f001bb67f26 ]

bond_option_mode_set() already rejects mode changes that would make a loaded XDP program incompatible via bond_xdp_check(). However, bond_option_xmit_hash_policy_set() has no such guard.

For 802.3ad and balance-xor modes, bond_xdp_check() returns false when xmit_hash_policy is vlan+srcmac, because the 802.1q payload is usually absent due to hardware offload. This means a user can:

1. Attach a native XDP program to a bond in 802.3ad/balance-xor mode with a compatible xmit_hash_policy (e.g. layer2+3).
2. Change xmit_hash_policy to vlan+srcmac while XDP remains loaded.

This leaves bond->xdp_prog set but bond_xdp_check() now returning false for the same device. When the bond is later destroyed, dev_xdp_uninstall() calls bond_xdp_set(dev, NULL, NULL) to remove the program, which hits the bond_xdp_check() guard and returns -EOPNOTSUPP, triggering:

WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL))

Fix this by rejecting xmit_hash_policy changes to vlan+srcmac when an XDP program is loaded on a bond in 802.3ad or balance-xor mode.

commit 39a0876d595b ("net, bonding: Disallow vlan+srcmac with XDP") introduced bond_xdp_check() which returns false for 802.3ad/balance-xor modes when xmit_hash_policy is vlan+srcmac. The check was wired into bond_xdp_set() to reject XDP attachment with an incompatible policy, but the symmetric path -- preventing xmit_hash_policy from being changed to an incompatible value after XDP is already loaded -- was left unguarded in bond_option_xmit_hash_policy_set().

Note:
commit 094ee6017ea0 ("bonding: check xdp prog when set bond mode") later added a similar guard to bond_option_mode_set(), but bond_option_xmit_hash_policy_set() remained unprotected.

---
 drivers/net/bonding/bond_main.c    | 9 +++++++--
 drivers/net/bonding/bond_options.c | 2 ++
 include/net/bonding.h              | 1 +
 3 files changed, 10 insertions(+), 2 deletions(-)
drivers/net/bonding/bond_main.c +7 -2
index 0e078252b52a98..f2e97f640467de 100644
@@ -322,7 +322,7 @@ bool bond_sk_check(struct bonding *bond)
 	}
 }
 
-bool bond_xdp_check(struct bonding *bond, int mode)
+bool __bond_xdp_check(int mode, int xmit_policy)
 {
 	switch (mode) {
 	case BOND_MODE_ROUNDROBIN:
@@ -333,7 +333,7 @@ bool bond_xdp_check(struct bonding *bond, int mode)
 		/* vlan+srcmac is not supported with XDP as in most cases the 802.1q
 		 * payload is not in the packet due to hardware offload.
 		 */
-		if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC)
+		if (xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC)
 			return true;
 		fallthrough;
 	default:
@@ -341,6 +341,11 @@ bool bond_xdp_check(struct bonding *bond, int mode)
 	}
 }
 
+bool bond_xdp_check(struct bonding *bond, int mode)
+{
+	return __bond_xdp_check(mode, bond->params.xmit_policy);
+}
+
 /*---------------------------------- VLAN -----------------------------------*/
 
 /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid,
drivers/net/bonding/bond_options.c +2 -0
index 40731d180bb505..3d15b340b5c939 100644
@@ -1590,6 +1590,8 @@ static int bond_option_fail_over_mac_set(struct bonding *bond,
 static int bond_option_xmit_hash_policy_set(struct bonding *bond,
 					    const struct bond_opt_value *newval)
 {
+	if (bond->xdp_prog && !__bond_xdp_check(BOND_MODE(bond), newval->value))
+		return -EOPNOTSUPP;
 	netdev_dbg(bond->dev, "Setting xmit hash policy to %s (%llu)\n",
 		   newval->string, newval->value);
 	bond->params.xmit_policy = newval->value;
include/net/bonding.h +1 -0
index 06a048d716b19f..f2dee8cefa1963 100644
@@ -704,6 +704,7 @@ void bond_debug_register(struct bonding *bond);
 void bond_debug_unregister(struct bonding *bond);
 void bond_debug_reregister(struct bonding *bond);
 const char *bond_mode_name(int mode);
+bool __bond_xdp_check(int mode, int xmit_policy);
 bool bond_xdp_check(struct bonding *bond, int mode);
 void bond_setup(struct net_device *bond_dev);
 unsigned int bond_get_num_tx_queues(void);
Signature · 1 line
2.53.0
author maintainer
#199 lore raw

PATCH 189/522 usb: core: Fix SuperSpeed root hub wMaxPacketSize

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Michal Pecio <[email protected]>

commit d1e280334b7f0a1df441e08bd1f6a1bcc36b3bbb upstream.

There is no good reason to have wBytesPerInterval < wMaxPacketSize - either one is too low or the other too high, and we may want to warn about such descriptors. Start with cleaning up our own root hubs.

USB 3.2 section 10.15.1 sets wMaxPacketSize and wBytesPerInterval of SuperSpeed hub status endpoints at 2 bytes, so reduce wMaxPacketSize from its former value of 4, which was derived from USB 2.0 spec and the kernel's USB_MAXCHILDREN limit. They don't apply because USB 3.2 10.15.2.1 specifies SuperSpeed hubs to have up to 15 ports.

---
 drivers/usb/core/hcd.c |    4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
drivers/usb/core/hcd.c +1 -3
@@ -353,9 +353,7 @@ static const u8 ss_rh_config_descriptor[
 	USB_DT_ENDPOINT, /* __u8 ep_bDescriptorType; Endpoint */
 	0x81,       /*  __u8  ep_bEndpointAddress; IN Endpoint 1 */
 	0x03,       /*  __u8  ep_bmAttributes; Interrupt */
-		    /* __le16 ep_wMaxPacketSize; 1 + (MAX_ROOT_PORTS / 8)
-		     * see hub.c:hub_configure() for details. */
-	(USB_MAXCHILDREN + 1 + 7) / 8, 0x00,
+	0x02, 0x00, /* __le16 ep_wMaxPacketSize; 2 bytes per USB3 10.15.1 */
 	0x0c,       /*  __u8  ep_bInterval; (256ms -- usb 2.0 spec) */
 
 	/* one SuperSpeed endpoint companion descriptor */
author maintainer
#200 lore raw

PATCH 190/522 bpf: Free reuseport cBPF prog after RCU grace period.

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit 18fc650ccd7fe3376eca89203668cfb8268f60df ]

Eulgyu Kim reported the splat below with a repro. [0]

The repro sets up a UDP reuseport group with a cBPF prog and replaces it with a new one while another thread is sending a UDP packet to the group.

The reuseport prog is freed by sk_reuseport_prog_free(). bpf_prog_put() is called for "e"BPF prog to destruct through multiple stages while cBPF prog is freed immediately by bpf_release_orig_filter() and bpf_prog_free().

If a reuseport prog is detached from the setsockopt() path (reuseport_attach_prog() or reuseport_detach_prog()), sk_reuseport_prog_free() is called without waiting for RCU readers to complete, resulting in various bugs.

Let's defer freeing the reuseport cBPF prog after one RCU grace period.

Note "e"BPF prog is safe as is unless the fast path starts to touch fields destroyed in bpf_prog_put_deferred() and __bpf_prog_put_noref().

[0]:

BUG: KASAN: vmalloc-out-of-bounds in reuseport_select_sock+0xedc/0x1220 net/core/sock_reuseport.c:596
Read of size 4 at addr ffffc9000051e004 by task slowme/10208
CPU: 6 UID: 1000 PID: 10208 Comm: slowme Not tainted 7.0.0-geb7ac95ff75e #32 PREEMPT(full)
Hardware name: QEMU Ubuntu 24.04 PC v2 (i440FX + PIIX, arch_caps fix, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
Call Trace:
 <IRQ>
 dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:378 [inline]
 print_report+0xca/0x240 mm/kasan/report.c:482
 kasan_report+0x118/0x150 mm/kasan/report.c:595
 reuseport_select_sock+0xedc/0x1220 net/core/sock_reuseport.c:596
 udp4_lib_lookup2+0x3bc/0x950 net/ipv4/udp.c:495
 __udp4_lib_lookup+0x768/0xe20 net/ipv4/udp.c:723
 __udp4_lib_lookup_skb+0x297/0x390 net/ipv4/udp.c:752
 __udp4_lib_rcv+0x1312/0x2620 net/ipv4/udp.c:2752
 ip_protocol_deliver_rcu+0x282/0x440 net/ipv4/ip_input.c:207
 ip_local_deliver_finish+0x3bb/0x6f0 net/ipv4/ip_input.c:241
 NF_HOOK+0x30c/0x3a0 include/linux/netfilter.h:318
 NF_HOOK+0x30c/0x3a0 include/linux/netfilter.h:318
 __netif_receive_skb_one_core net/core/dev.c:6181 [inline]
 __netif_receive_skb net/core/dev.c:6294 [inline]
 process_backlog+0xaa4/0x1960 net/core/dev.c:6645
 __napi_poll+0xae/0x340 net/core/dev.c:7709
 napi_poll net/core/dev.c:7772 [inline]
 net_rx_action+0x5d7/0xf50 net/core/dev.c:7929
 handle_softirqs+0x22b/0x870 kernel/softirq.c:622
 do_softirq+0x76/0xd0 kernel/softirq.c:523
 </IRQ>
 <TASK>
 __local_bh_enable_ip+0xf8/0x130 kernel/softirq.c:450
 local_bh_enable include/linux/bottom_half.h:33 [inline]
 rcu_read_unlock_bh include/linux/rcupdate.h:924 [inline]
 __dev_queue_xmit+0x1dd7/0x3710 net/core/dev.c:4890
 neigh_output include/net/neighbour.h:556 [inline]
 ip_finish_output2+0xca9/0x1070 net/ipv4/ip_output.c:237
 NF_HOOK_COND include/linux/netfilter.h:307 [inline]
 ip_output+0x29f/0x450 net/ipv4/ip_output.c:438
 ip_send_skb+0x45/0xc0 net/ipv4/ip_output.c:1508
 udp_send_skb+0xb04/0x1510 net/ipv4/udp.c:1195
 udp_sendmsg+0x1a71/0x2350 net/ipv4/udp.c:1485
 sock_sendmsg_nosec net/socket.c:727 [inline]
 __sock_sendmsg net/socket.c:742 [inline]
 __sys_sendto+0x554/0x680 net/socket.c:2206
 __do_sys_sendto net/socket.c:2213 [inline]
 __se_sys_sendto net/socket.c:2209 [inline]
 __x64_sys_sendto+0xde/0x100 net/socket.c:2209
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x160/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x415a2d
Code: b3 66 2e 0f 1f 84 00 00 00 00 00 66 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f6bc31e41e8 EFLAGS: 00000212 ORIG_RAX: 000000000000002c
RAX: ffffffffffffffda RBX: 00007f6bc31e4cdc RCX: 0000000000415a2d
RDX: 0000000000000001 RSI: 00007f6bc31e421f RDI: 0000000000000003
RBP: 00007f6bc31e4240 R08: 00007f6bc31e4220 R09: 0000000000000010
R10: 0000000000000000 R11: 0000000000000212 R12: 00007f6bc31e46c0
R13: ffffffffffffffb8 R14: 0000000000000000 R15: 00007ffc9b0d70b0
 </TASK>
---
 net/core/filter.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)
net/core/filter.c +12 -3
index 0ea9ede2c44724..3628ea596050f0 100644
@@ -1643,15 +1643,24 @@ int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 	return err;
 }
 
+static void sk_reuseport_prog_free_rcu(struct rcu_head *rcu)
+{
+	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
+	struct bpf_prog *prog = aux->prog;
+
+	bpf_release_orig_filter(prog);
+	bpf_prog_free(prog);
+}
+
 void sk_reuseport_prog_free(struct bpf_prog *prog)
 {
 	if (!prog)
 		return;
 
-	if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
-		bpf_prog_put(prog);
+	if (bpf_prog_was_classic(prog))
+		call_rcu(&prog->aux->rcu, sk_reuseport_prog_free_rcu);
 	else
-		bpf_prog_destroy(prog);
+		bpf_prog_put(prog);
 }
 
 struct bpf_scratchpad {
Signature · 1 line
2.53.0
author maintainer
#201 lore raw

PATCH 191/522 USB: serial: mct_u232: fix memory corruption with small endpoint

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Johan Hovold <[email protected]>

commit 915b36d701950503c4ea0f6e314b10868e59fce3 upstream.

The driver overrides the maximum transfer size for a specific device which only accepts 16 byte packets for its 32 byte bulk-out endpoint.

Make sure to never increase the maximum transfer size to prevent slab corruption should a malicious device report a smaller endpoint max packet size than expected.

Fixes 1da177e4c3f4 ("Linux-2.6.12-rc2")
---
 drivers/usb/serial/mct_u232.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)
drivers/usb/serial/mct_u232.c +11 -10
index 389bbab8182a41..3c1351bb7ca3d8 100644
@@ -379,6 +379,7 @@ static int mct_u232_port_probe(struct usb_serial_port *port)
 {
 	struct usb_serial *serial = port->serial;
 	struct mct_u232_private *priv;
+	u16 pid;
 
 	/* check first to simplify error handling */
 	if (!serial->port[1] || !serial->port[1]->interrupt_in_urb) {
@@ -386,6 +387,16 @@ static int mct_u232_port_probe(struct usb_serial_port *port)
 		return -ENODEV;
 	}
 
+	/*
+	 * Compensate for a hardware bug: although the Sitecom U232-P25
+	 * device reports a maximum output packet size of 32 bytes,
+	 * it seems to be able to accept only 16 bytes (and that's what
+	 * SniffUSB says too...)
+	 */
+	pid = le16_to_cpu(serial->dev->descriptor.idProduct);
+	if (pid == MCT_U232_SITECOM_PID)
+		port->bulk_out_size = min(16, port->bulk_out_size);
+
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
@@ -411,7 +422,6 @@ static void mct_u232_port_remove(struct usb_serial_port *port)
 
 static int  mct_u232_open(struct tty_struct *tty, struct usb_serial_port *port)
 {
-	struct usb_serial *serial = port->serial;
 	struct mct_u232_private *priv = usb_get_serial_port_data(port);
 	int retval = 0;
 	unsigned int control_state;
@@ -419,15 +429,6 @@ static int  mct_u232_open(struct tty_struct *tty, struct usb_serial_port *port)
 	unsigned char last_lcr;
 	unsigned char last_msr;
 
-	/* Compensate for a hardware bug: although the Sitecom U232-P25
-	 * device reports a maximum output packet size of 32 bytes,
-	 * it seems to be able to accept only 16 bytes (and that's what
-	 * SniffUSB says too...)
-	 */
-	if (le16_to_cpu(serial->dev->descriptor.idProduct)
-						== MCT_U232_SITECOM_PID)
-		port->bulk_out_size = 16;
-
 	/* Do a defined restart: the normal serial device seems to
 	 * always turn on DTR and RTS here, so do the same. I'm not
 	 * sure if this is really necessary. But it should not harm
Signature · 1 line
2.53.0
author maintainer
#202 lore raw

PATCH 192/522 dmaengine: idxd: Fix not releasing workqueue on .release()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Vinicius Costa Gomes <[email protected]>

[ Upstream commit 3d33de353b1ff9023d5ec73b9becf80ea87af695 ]

The workqueue associated with an DSA/IAA device is not released when the object is freed.

[ Remove destroy_workqueue(idxd->wq) from the function idxd_remove() to avoid the workqueue is released twice. ]

---
 drivers/dma/idxd/init.c  | 1 -
 drivers/dma/idxd/sysfs.c | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)
drivers/dma/idxd/init.c +0 -1
index 6059ffc08eace1..2880a0b0f5e67e 100644
@@ -813,7 +813,6 @@ static void idxd_remove(struct pci_dev *pdev)
 	if (device_user_pasid_enabled(idxd))
 		iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);
 	pci_disable_device(pdev);
-	destroy_workqueue(idxd->wq);
 	perfmon_pmu_remove(idxd);
 	put_device(idxd_confdev(idxd));
 }
drivers/dma/idxd/sysfs.c +1 -0
index 0689464c4816ab..ea222e1654ab94 100644
@@ -1663,6 +1663,7 @@ static void idxd_conf_device_release(struct device *dev)
 {
 	struct idxd_device *idxd = confdev_to_idxd(dev);
 
+	destroy_workqueue(idxd->wq);
 	kfree(idxd->groups);
 	bitmap_free(idxd->wq_enable_map);
 	kfree(idxd->wqs);
Signature · 1 line
2.53.0
author maintainer
#203 lore raw

PATCH 193/522 Disable -Wattribute-alias for clang-23 and newer

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Nathan Chancellor <[email protected]>

commit 175db11786bde9061db526bf1ac5107d915f5163 upstream.

Clang recently added support for -Wattribute-alias [1], which results in the same warnings that necessitated commit bee20031772a ("disable -Wattribute-alias warning for SYSCALL_DEFINEx()") for GCC.

kernel/time/itimer.c:325:1: error: alias and aliasee have different types 'long (unsigned int)' and 'long (typeof (__builtin_choose_expr((__builtin_types_compatible_p(typeof ((unsigned int)0), typeof (0LL)) || __builtin_types_compatible_p(typeof ((unsigned int)0), typeof (0ULL))), 0LL, 0L)))' (aka 'long (long)') [-Werror,-Wattribute-alias]
325 | SYSCALL_DEFINE1(alarm, unsigned int, seconds)
| ^
include/linux/syscalls.h:225:36: note: expanded from macro 'SYSCALL_DEFINE1'

    225 | #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
        |                                    ^
  include/linux/syscalls.h:236:2: note: expanded from macro 'SYSCALL_DEFINEx'
    236 |         __SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
        |         ^
  include/linux/syscalls.h:251:18: note: expanded from macro '__SYSCALL_DEFINEx'
    251 |                 __attribute__((alias(__stringify(__se_sys##name))));    \
        |                                ^
  kernel/time/itimer.c:325:1: note: aliasee is declared here
  include/linux/syscalls.h:225:36: note: expanded from macro 'SYSCALL_DEFINE1'
    225 | #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
        |                                    ^
  include/linux/syscalls.h:236:2: note: expanded from macro 'SYSCALL_DEFINEx'
    236 |         __SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
        |         ^
  include/linux/syscalls.h:255:18: note: expanded from macro '__SYSCALL_DEFINEx'
    255 |         asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))  \
        |                         ^
  <scratch space>:16:1: note: expanded from here
     16 | __se_sys_alarm
        | ^

Disable the warnings in the same way for clang-23 and newer. Disable the warning about unknown warning options to avoid breaking the build for versions of clang-23 that do not have -Wattribute-alias, such as ones deployed by vendors like Android or CI systems or when bisecting LLVM between llvmorg-23-init and release/23.x.

---
 include/linux/compat.h         | 4 ++++
 include/linux/compiler-clang.h | 6 ++++++
 include/linux/compiler_types.h | 4 ++++
 include/linux/syscalls.h       | 4 ++++
 4 files changed, 18 insertions(+)
include/linux/compat.h +4 -0
index 77e84d17521eb8..38f22c9ac9109b 100644
@@ -72,6 +72,10 @@
 	__diag_push();								\
 	__diag_ignore(GCC, 8, "-Wattribute-alias",				\
 		      "Type aliasing is used to sanitize syscall arguments");\
+	__diag_ignore(clang, 23, "-Wunknown-warning-option",			\
+		      "Avoid breaking versions without -Wattribute-alias");	\
+	__diag_ignore(clang, 23, "-Wattribute-alias",				\
+		      "Type aliasing is used to sanitize syscall arguments");	\
 	asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
 		__attribute__((alias(__stringify(__se_compat_sys##name))));	\
 	ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO);				\
include/linux/compiler-clang.h +6 -0
index f9de53fff3acc4..2fd5b596b36b5c 100644
@@ -144,5 +144,11 @@
 #define __diag_clang_11(s)
 #endif
 
+#if CONFIG_CLANG_VERSION >= 230000
+#define __diag_clang_23(s)	__diag(s)
+#else
+#define __diag_clang_23(s)
+#endif
+
 #define __diag_ignore_all(option, comment) \
 	__diag_clang(11, ignore, option)
include/linux/compiler_types.h +4 -0
index ef359a76b11f89..7c9883c499cfe1 100644
@@ -399,6 +399,10 @@ struct ftrace_likely_data {
 #define __diag_GCC(version, severity, string)
 #endif
 
+#ifndef __diag_clang
+#define __diag_clang(version, severity, string)
+#endif
+
 #define __diag_push()	__diag(push)
 #define __diag_pop()	__diag(pop)
 
include/linux/syscalls.h +4 -0
index dcce762b48facb..7ff6bc7da1f655 100644
@@ -240,6 +240,10 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
 	__diag_push();							\
 	__diag_ignore(GCC, 8, "-Wattribute-alias",			\
 		      "Type aliasing is used to sanitize syscall arguments");\
+	__diag_ignore(clang, 23, "-Wunknown-warning-option",		\
+		      "Avoid breaking versions without -Wattribute-alias");\
+	__diag_ignore(clang, 23, "-Wattribute-alias",			\
+		      "Type aliasing is used to sanitize syscall arguments");\
 	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
 		__attribute__((alias(__stringify(__se_sys##name))));	\
 	ALLOW_ERROR_INJECTION(sys##name, ERRNO);			\
Signature · 1 line
2.53.0
author maintainer
#204 lore raw

PATCH 194/522 i2c: dev: prevent integer overflow in I2C_TIMEOUT ioctl

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Mingyu Wang <[email protected]>

commit 617eb7c0961a8dfcfc811844a6396e406b2923ea upstream.

While fuzzing with Syzkaller, a persistent schedule_timeout: wrong timeout value warning was observed, accompanied by SMBus controller state machine corruption.

The I2C_TIMEOUT ioctl accepts a user-provided timeout in multiples of 10 ms. The user argument is checked against INT_MAX, but it is subsequently multiplied by 10 before being passed to msecs_to_jiffies().

A malicious user can pass a large value (e.g., 429496729) that passes the arg > INT_MAX check but overflows when multiplied by 10. This results in a truncated 32-bit unsigned value that bypasses the internal (int)m < 0 check in msecs_to_jiffies().

The truncated value is then assigned to client->adapter->timeout (a signed 32-bit int), which is reinterpreted as a negative number. When passed to wait_for_completion_timeout(), this negative value undergoes sign extension to a 64-bit unsigned long, triggering the schedule_timeout warning and causing premature returns. This leaves the SMBus state machine in an unrecoverable state, constituting a local Denial of Service (DoS).

Fix this by bounding the user argument to INT_MAX / 10.

[wsa: move the comment as well]
---
 drivers/i2c/i2c-dev.c |    9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)
drivers/i2c/i2c-dev.c +5 -4
@@ -476,12 +476,13 @@ static long i2cdev_ioctl(struct file *fi
 		client->adapter->retries = arg;
 		break;
 	case I2C_TIMEOUT:
-		if (arg > INT_MAX)
+		/*
+		 * For historical reasons, user-space sets the timeout value in
+		 * units of 10 ms.
+		 */
+		if (arg > INT_MAX / 10)
 			return -EINVAL;
 
-		/* For historical reasons, user-space sets the timeout
-		 * value in units of 10 ms.
-		 */
 		client->adapter->timeout = msecs_to_jiffies(arg * 10);
 		break;
 	default:
author maintainer
#205 lore raw

PATCH 195/522 ipv6: mcast: Fix use-after-free when processing MLD queries

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Ido Schimmel <[email protected]>

commit 791c91dc7a9dfb2457d5e29b8216a6484b9c4b40 upstream.

When processing an MLD query, a pointer to the multicast group address is retrieved when initially parsing the packet. This pointer is later dereferenced without being reloaded despite the fact that the skb header might have been reallocated following the pskb_may_pull() calls, leading to a use-after-free [1].

Fix by copying the multicast group address when the packet is initially parsed.

[1]

BUG: KASAN: slab-use-after-free in __mld_query_work (net/ipv6/mcast.c:1512)
Read of size 8 at addr ffff8881154b8e90 by task kworker/4:1/118

Workqueue: mld mld_query_work
Call Trace:
<TASK>
dump_stack_lvl (lib/dump_stack.c:94 lib/dump_stack.c:120)

print_address_description.constprop.0 (mm/kasan/report.c:378) print_report (mm/kasan/report.c:482)
kasan_report (mm/kasan/report.c:595)
__mld_query_work (net/ipv6/mcast.c:1512) mld_query_work (net/ipv6/mcast.c:1563) process_one_work (kernel/workqueue.c:3314) worker_thread (kernel/workqueue.c:3397 kernel/workqueue.c:3478) kthread (kernel/kthread.c:436)
ret_from_fork (arch/x86/kernel/process.c:158) ret_from_fork_asm (arch/x86/entry/entry_64.S:245)

</TASK>

[...]

Freed by task 118:
kasan_save_stack (mm/kasan/common.c:57)
kasan_save_track (mm/kasan/common.c:78)
kasan_save_free_info (mm/kasan/generic.c:584)
__kasan_slab_free (mm/kasan/common.c:253 mm/kasan/common.c:285)
kfree (./include/linux/kasan.h:235 mm/slub.c:2689 mm/slub.c:6251 mm/slub.c:6566)
pskb_expand_head (net/core/skbuff.c:2335)
__pskb_pull_tail (net/core/skbuff.c:2878 (discriminator 4))
__mld_query_work (net/ipv6/mcast.c:1495 (discriminator 1))

mld_query_work (net/ipv6/mcast.c:1563) process_one_work (kernel/workqueue.c:3314) worker_thread (kernel/workqueue.c:3397 kernel/workqueue.c:3478) kthread (kernel/kthread.c:436)
ret_from_fork (arch/x86/kernel/process.c:158) ret_from_fork_asm (arch/x86/entry/entry_64.S:245)

---
 net/ipv6/mcast.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
net/ipv6/mcast.c +4 -4
@@ -1392,9 +1392,9 @@ out:
 static void __mld_query_work(struct sk_buff *skb)
 {
 	struct mld2_query *mlh2 = NULL;
-	const struct in6_addr *group;
 	unsigned long max_delay;
 	struct inet6_dev *idev;
+	struct in6_addr group;
 	struct ifmcaddr6 *ma;
 	struct mld_msg *mld;
 	int group_type;
@@ -1426,8 +1426,8 @@ static void __mld_query_work(struct sk_b
 		goto kfree_skb;
 
 	mld = (struct mld_msg *)icmp6_hdr(skb);
-	group = &mld->mld_mca;
-	group_type = ipv6_addr_type(group);
+	group = mld->mld_mca;
+	group_type = ipv6_addr_type(&group);
 
 	if (group_type != IPV6_ADDR_ANY &&
 	    !(group_type&IPV6_ADDR_MULTICAST))
@@ -1477,7 +1477,7 @@ static void __mld_query_work(struct sk_b
 		}
 	} else {
 		for_each_mc_mclock(idev, ma) {
-			if (!ipv6_addr_equal(group, &ma->mca_addr))
+			if (!ipv6_addr_equal(&group, &ma->mca_addr))
 				continue;
 			if (ma->mca_flags & MAF_TIMER_RUNNING) {
 				/* gsquery <- gsquery && mark */
author maintainer
#206 lore raw

PATCH 196/522 net/smc: fix sleep-inside-lock in __smc_setsockopt() causing local DoS

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Nicolò Coccia <[email protected]>

commit a3fdd924d88c30b9f488636ce0e4696012cf5511 upstream.

A logic flaw in __smc_setsockopt() allows a local unprivileged user to cause a Denial of Service (DoS) by holding the socket lock indefinitely.

The function __smc_setsockopt() calls copy_from_sockptr() while holding lock_sock(sk). By passing a userfaultfd-monitored memory page (or FUSE-backed memory on systems where unprivileged userfaultfd is disabled) as the optval, an attacker can halt execution during the copy operation, keeping the lock held.

Combined with asynchronous tear-down operations like shutdown(), this exhausts the kernel wq (kworkers) and triggers the hung task watchdog.

[  240.123456] INFO: task kworker/u8:2 blocked for more than 120 seconds.
[  240.123489] Call Trace:
[  240.123501]  smc_shutdown+...
[  240.123512]  lock_sock_nested+...

This patch moves the user-space copy outside the lock_sock() critical section to prevent the issue.

Fixes a6a6fe27bab4 ("net/smc: Dynamic control handshake limitation by socket options")
---
 net/smc/af_smc.c |   17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)
net/smc/af_smc.c +8 -9
@@ -2947,18 +2947,17 @@ static int __smc_setsockopt(struct socke
 
 	smc = smc_sk(sk);
 
+	/* pre-fetch user data outside the lock */
+	if (optname == SMC_LIMIT_HS) {
+		if (optlen < sizeof(int))
+			return -EINVAL;
+		if (copy_from_sockptr(&val, optval, sizeof(int)))
+			return -EFAULT;
+	}
+
 	lock_sock(sk);
 	switch (optname) {
 	case SMC_LIMIT_HS:
-		if (optlen < sizeof(int)) {
-			rc = -EINVAL;
-			break;
-		}
-		if (copy_from_sockptr(&val, optval, sizeof(int))) {
-			rc = -EFAULT;
-			break;
-		}
-
 		smc->limit_smc_hs = !!val;
 		rc = 0;
 		break;
author maintainer
#207 lore raw

PATCH 197/522 tee: optee: prevent use-after-free when the client exits before the supplicant

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Amirreza Zarrabi <[email protected]>

[ Upstream commit 387a926ee166814611acecb960207fe2f3c4fd3e ]

Commit 70b0d6b0a199 ("tee: optee: Fix supplicant wait loop") made the client wait as killable so it can be interrupted during shutdown or after a supplicant crash. This changes the original lifetime expectations:
the client task can now terminate while the supplicant is still processing its request.

If the client exits first it removes the request from its queue and kfree()s it, while the request ID remains in supp->idr. A subsequent lookup on the supplicant path then dereferences freed memory, leading to a use-after-free.

Serialise access to the request with supp->mutex:

* Hold supp->mutex in optee_supp_recv() and optee_supp_send() while looking up and touching the request.
* Let optee_supp_thrd_req() notice that the client has terminated and signal optee_supp_send() accordingly.

With these changes the request cannot be freed while the supplicant still has a reference, eliminating the race.

Fixes 70b0d6b0a199 ("tee: optee: Fix supplicant wait loop")
---
 drivers/tee/optee/supp.c | 107 +++++++++++++++++++++++++++------------
 1 file changed, 74 insertions(+), 33 deletions(-)
drivers/tee/optee/supp.c +74 -33
index d0f397c9024201..2386bbd38ce78b 100644
@@ -10,7 +10,11 @@
 struct optee_supp_req {
 	struct list_head link;
 
+	int id;
+
 	bool in_queue;
+	bool processed;
+
 	u32 func;
 	u32 ret;
 	size_t num_params;
@@ -19,6 +23,9 @@ struct optee_supp_req {
 	struct completion c;
 };
 
+/* It is temporary request used for revoked pending request in supp->idr. */
+#define INVALID_REQ_PTR ((struct optee_supp_req *)ERR_PTR(-EBADF))
+
 void optee_supp_init(struct optee_supp *supp)
 {
 	memset(supp, 0, sizeof(*supp));
@@ -39,21 +46,23 @@ void optee_supp_release(struct optee_supp *supp)
 {
 	int id;
 	struct optee_supp_req *req;
-	struct optee_supp_req *req_tmp;
 
 	mutex_lock(&supp->mutex);
 
-	/* Abort all request retrieved by supplicant */
+	/* Abort all request */
 	idr_for_each_entry(&supp->idr, req, id) {
 		idr_remove(&supp->idr, id);
-		req->ret = TEEC_ERROR_COMMUNICATION;
-		complete(&req->c);
-	}
+		/* Skip if request was already marked invalid */
+		if (IS_ERR(req))
+			continue;
 
-	/* Abort all queued requests */
-	list_for_each_entry_safe(req, req_tmp, &supp->reqs, link) {
-		list_del(&req->link);
-		req->in_queue = false;
+		/* For queued requests where supplicant has not seen it */
+		if (req->in_queue) {
+			list_del(&req->link);
+			req->in_queue = false;
+		}
+
+		req->processed = true;
 		req->ret = TEEC_ERROR_COMMUNICATION;
 		complete(&req->c);
 	}
@@ -100,8 +109,16 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
 
 	/* Insert the request in the request list */
 	mutex_lock(&supp->mutex);
+	req->id = idr_alloc(&supp->idr, req, 1, 0, GFP_KERNEL);
+	if (req->id < 0) {
+		mutex_unlock(&supp->mutex);
+		kfree(req);
+		return TEEC_ERROR_OUT_OF_MEMORY;
+	}
+
 	list_add_tail(&req->link, &supp->reqs);
 	req->in_queue = true;
+	req->processed = false;
 	mutex_unlock(&supp->mutex);
 
 	/* Tell an eventual waiter there's a new request */
@@ -117,21 +134,43 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
 	if (wait_for_completion_killable(&req->c)) {
 		mutex_lock(&supp->mutex);
 		if (req->in_queue) {
+			/* Supplicant has not seen this request yet. */
+			idr_remove(&supp->idr, req->id);
 			list_del(&req->link);
 			req->in_queue = false;
+
+			ret = TEEC_ERROR_COMMUNICATION;
+		} else if (req->processed) {
+			/*
+			 * Supplicant has processed this request. Ignore the
+			 * kill signal for now and submit the result. req is not
+			 * in supp->reqs (removed by supp_pop_entry()) nor in
+			 * supp->idr (removed by supp_pop_req()).
+			 */
+			ret = req->ret;
+		} else {
+			/*
+			 * Supplicant is in the middle of processing this
+			 * request. Replace req with INVALID_REQ_PTR so that
+			 * the ID remains busy, causing optee_supp_send() to
+			 * fail on the next call to supp_pop_req() with this ID.
+			 */
+			idr_replace(&supp->idr, INVALID_REQ_PTR, req->id);
+			ret = TEEC_ERROR_COMMUNICATION;
 		}
+
 		mutex_unlock(&supp->mutex);
-		req->ret = TEEC_ERROR_COMMUNICATION;
+	} else {
+		ret = req->ret;
 	}
 
-	ret = req->ret;
 	kfree(req);
 
 	return ret;
 }
 
 static struct optee_supp_req  *supp_pop_entry(struct optee_supp *supp,
-					      int num_params, int *id)
+					      int num_params)
 {
 	struct optee_supp_req *req;
 
@@ -153,10 +192,6 @@ static struct optee_supp_req  *supp_pop_entry(struct optee_supp *supp,
 		return ERR_PTR(-EINVAL);
 	}
 
-	*id = idr_alloc(&supp->idr, req, 1, 0, GFP_KERNEL);
-	if (*id < 0)
-		return ERR_PTR(-ENOMEM);
-
 	list_del(&req->link);
 	req->in_queue = false;
 
@@ -214,7 +249,6 @@ int optee_supp_recv(struct tee_context *ctx, u32 *func, u32 *num_params,
 	struct optee *optee = tee_get_drvdata(teedev);
 	struct optee_supp *supp = &optee->supp;
 	struct optee_supp_req *req = NULL;
-	int id;
 	size_t num_meta;
 	int rc;
 
@@ -224,15 +258,11 @@ int optee_supp_recv(struct tee_context *ctx, u32 *func, u32 *num_params,
 
 	while (true) {
 		mutex_lock(&supp->mutex);
-		req = supp_pop_entry(supp, *num_params - num_meta, &id);
+		req = supp_pop_entry(supp, *num_params - num_meta);
+		if (req)
+			break; /* Keep mutex held. */
 		mutex_unlock(&supp->mutex);
 
-		if (req) {
-			if (IS_ERR(req))
-				return PTR_ERR(req);
-			break;
-		}
-
 		/*
 		 * If we didn't get a request we'll block in
 		 * wait_for_completion() to avoid needless spinning.
@@ -245,6 +275,13 @@ int optee_supp_recv(struct tee_context *ctx, u32 *func, u32 *num_params,
 			return -ERESTARTSYS;
 	}
 
+	/* supp->mutex held and req != NULL. */
+
+	if (IS_ERR(req)) {
+		mutex_unlock(&supp->mutex);
+		return PTR_ERR(req);
+	}
+
 	if (num_meta) {
 		/*
 		 * tee-supplicant support meta parameters -> requsts can be
@@ -252,13 +289,11 @@ int optee_supp_recv(struct tee_context *ctx, u32 *func, u32 *num_params,
 		 */
 		param->attr = TEE_IOCTL_PARAM_ATTR_TYPE_VALUE_INOUT |
 			      TEE_IOCTL_PARAM_ATTR_META;
-		param->u.value.a = id;
+		param->u.value.a = req->id;
 		param->u.value.b = 0;
 		param->u.value.c = 0;
 	} else {
-		mutex_lock(&supp->mutex);
-		supp->req_id = id;
-		mutex_unlock(&supp->mutex);
+		supp->req_id = req->id;
 	}
 
 	*func = req->func;
@@ -266,6 +301,7 @@ int optee_supp_recv(struct tee_context *ctx, u32 *func, u32 *num_params,
 	memcpy(param + num_meta, req->param,
 	       sizeof(struct tee_param) * req->num_params);
 
+	mutex_unlock(&supp->mutex);
 	return 0;
 }
 
@@ -297,12 +333,17 @@ static struct optee_supp_req *supp_pop_req(struct optee_supp *supp,
 	if (!req)
 		return ERR_PTR(-ENOENT);
 
+	/* optee_supp_thrd_req() already returned to optee. */
+	if (IS_ERR(req))
+		goto failed_req;
+
 	if ((num_params - nm) != req->num_params)
 		return ERR_PTR(-EINVAL);
 
+	*num_meta = nm;
+failed_req:
 	idr_remove(&supp->idr, id);
 	supp->req_id = -1;
-	*num_meta = nm;
 
 	return req;
 }
@@ -328,10 +369,9 @@ int optee_supp_send(struct tee_context *ctx, u32 ret, u32 num_params,
 
 	mutex_lock(&supp->mutex);
 	req = supp_pop_req(supp, num_params, param, &num_meta);
-	mutex_unlock(&supp->mutex);
-
 	if (IS_ERR(req)) {
-		/* Something is wrong, let supplicant restart. */
+		mutex_unlock(&supp->mutex);
+		/* Something is wrong, let supplicant handel it. */
 		return PTR_ERR(req);
 	}
 
@@ -355,9 +395,10 @@ int optee_supp_send(struct tee_context *ctx, u32 ret, u32 num_params,
 		}
 	}
 	req->ret = ret;
-
+	req->processed = true;
 	/* Let the requesting thread continue */
 	complete(&req->c);
+	mutex_unlock(&supp->mutex);
 
 	return 0;
 }
Signature · 1 line
2.53.0
author maintainer
#208 lore raw

PATCH 198/522 netfilter: xt_NFQUEUE: prefer raw_smp_processor_id

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Fernando Fernandez Mancera <[email protected]>

[ Upstream commit c6c5327dd18bec1e1bbf139b2cf5ae53608a9d30 ]

With PREEMPT_RCU this triggers a splat because smp_processor_id() can be preempted while inside a RCU critical section. If xt_NFQUEUE target is invoked via nft_compat_eval() path, we are inside a RCU critical section.

Just use the raw version instead.

Fixes 0ca743a55991 ("netfilter: nf_tables: add compatibility layer for x_tables")
---
 net/netfilter/xt_NFQUEUE.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/netfilter/xt_NFQUEUE.c +1 -1
index 466da23e36ff47..b32d153e3a1862 100644
@@ -91,7 +91,7 @@ nfqueue_tg_v3(struct sk_buff *skb, const struct xt_action_param *par)
 
 	if (info->queues_total > 1) {
 		if (info->flags & NFQ_FLAG_CPU_FANOUT) {
-			int cpu = smp_processor_id();
+			int cpu = raw_smp_processor_id();
 
 			queue = info->queuenum + cpu % info->queues_total;
 		} else {
Signature · 1 line
2.53.0
author maintainer
#209 lore raw

PATCH 199/522 ipvs: clear the svc scheduler ptr early on edit

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Julian Anastasov <[email protected]>

[ Upstream commit 193989cc6d80dd8e0460fb3992e69fa03bf0ff9b ]

ip_vs_edit_service() while unbinding the old scheduler clears the svc->scheduler ptr after the scheduler module initiates RCU callbacks. This can cause packets to use the old scheduler at the time when svc->sched_data is already freed after RCU grace period.

Fix it by clearing the ptr early in ip_vs_unbind_scheduler(), before the done_service method schedules any RCU callbacks.

Also, if the new scheduler fails to initialize when replacing the old scheduler, try to restore the old scheduler while still returning the error code.

---
 include/net/ip_vs.h              |  3 +--
 net/netfilter/ipvs/ip_vs_ctl.c   | 13 ++++++++-----
 net/netfilter/ipvs/ip_vs_sched.c | 14 +++++++-------
 3 files changed, 16 insertions(+), 14 deletions(-)
include/net/ip_vs.h +1 -2
index abc46f05762e6b..0b175ecd9562bd 100644
@@ -1407,8 +1407,7 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
 int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
 int ip_vs_bind_scheduler(struct ip_vs_service *svc,
 			 struct ip_vs_scheduler *scheduler);
-void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
-			    struct ip_vs_scheduler *sched);
+void ip_vs_unbind_scheduler(struct ip_vs_service *svc);
 struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
 void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
 struct ip_vs_conn *
net/netfilter/ipvs/ip_vs_ctl.c +8 -5
index 6cc50f05c46c15..15a083dd459737 100644
@@ -1415,7 +1415,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
 	if (ret_hooks >= 0)
 		ip_vs_unregister_hooks(ipvs, u->af);
 	if (svc != NULL) {
-		ip_vs_unbind_scheduler(svc, sched);
+		ip_vs_unbind_scheduler(svc);
 		ip_vs_service_free(svc);
 	}
 	ip_vs_scheduler_put(sched);
@@ -1477,9 +1477,8 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 	old_sched = rcu_dereference_protected(svc->scheduler, 1);
 	if (sched != old_sched) {
 		if (old_sched) {
-			ip_vs_unbind_scheduler(svc, old_sched);
-			RCU_INIT_POINTER(svc->scheduler, NULL);
-			/* Wait all svc->sched_data users */
+			ip_vs_unbind_scheduler(svc);
+			/* Wait all svc->scheduler/sched_data users */
 			synchronize_rcu();
 		}
 		/* Bind the new scheduler */
@@ -1487,6 +1486,10 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 			ret = ip_vs_bind_scheduler(svc, sched);
 			if (ret) {
 				ip_vs_scheduler_put(sched);
+				/* Try to restore the old_sched */
+				if (old_sched &&
+				    !ip_vs_bind_scheduler(svc, old_sched))
+					old_sched = NULL;
 				goto out;
 			}
 		}
@@ -1543,7 +1546,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
 
 	/* Unbind scheduler */
 	old_sched = rcu_dereference_protected(svc->scheduler, 1);
-	ip_vs_unbind_scheduler(svc, old_sched);
+	ip_vs_unbind_scheduler(svc);
 	ip_vs_scheduler_put(old_sched);
 
 	/* Unbind persistence engine, keep svc->pe */
net/netfilter/ipvs/ip_vs_sched.c +7 -7
index d4903723be7e90..49b2e5d2b2c837 100644
@@ -57,19 +57,19 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc,
 /*
  *  Unbind a service with its scheduler
  */
-void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
-			    struct ip_vs_scheduler *sched)
+void ip_vs_unbind_scheduler(struct ip_vs_service *svc)
 {
-	struct ip_vs_scheduler *cur_sched;
+	struct ip_vs_scheduler *sched;
 
-	cur_sched = rcu_dereference_protected(svc->scheduler, 1);
-	/* This check proves that old 'sched' was installed */
-	if (!cur_sched)
+	sched = rcu_dereference_protected(svc->scheduler, 1);
+	if (!sched)
 		return;
 
+	/* Reset the scheduler before initiating any RCU callbacks */
+	rcu_assign_pointer(svc->scheduler, NULL);
+	smp_wmb();	/* paired with smp_rmb() in ip_vs_schedule() */
 	if (sched->done_service)
 		sched->done_service(svc);
-	/* svc->scheduler can be set to NULL only by caller */
 }
 
 
Signature · 1 line
2.53.0
author maintainer
#210 lore raw

PATCH 200/522 netfilter: synproxy: add mutex to guard hook reference counting

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Fernando Fernandez Mancera <[email protected]>

[ Upstream commit 2fcba19caaeb2a33017459d3430f057967bb91b6 ]

As the synproxy infrastructure register netfilter hooks on-demand when a user adds the first iptables target or nftables expression, if done concurrently they can race each other.

Introduce a mutex to serialize the refcount control blocks access from both frontends. While a per namespace mutex might be more efficient, it is not needed for target/expression like SYNPROXY.

Fixes ad49d86e07a4 ("netfilter: nf_tables: Add synproxy support")
---
 net/netfilter/nf_synproxy_core.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)
net/netfilter/nf_synproxy_core.c +18 -6
index f5a52075691faa..500a90311ed505 100644
@@ -21,6 +21,8 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_synproxy.h>
 
+static DEFINE_MUTEX(synproxy_mutex);
+
 unsigned int synproxy_net_id;
 EXPORT_SYMBOL_GPL(synproxy_net_id);
 
@@ -768,26 +770,31 @@ static const struct nf_hook_ops ipv4_synproxy_ops[] = {
 
 int nf_synproxy_ipv4_init(struct synproxy_net *snet, struct net *net)
 {
-	int err;
+	int err = 0;
 
+	mutex_lock(&synproxy_mutex);
 	if (snet->hook_ref4 == 0) {
 		err = nf_register_net_hooks(net, ipv4_synproxy_ops,
 					    ARRAY_SIZE(ipv4_synproxy_ops));
 		if (err)
-			return err;
+			goto out;
 	}
 
 	snet->hook_ref4++;
-	return 0;
+out:
+	mutex_unlock(&synproxy_mutex);
+	return err;
 }
 EXPORT_SYMBOL_GPL(nf_synproxy_ipv4_init);
 
 void nf_synproxy_ipv4_fini(struct synproxy_net *snet, struct net *net)
 {
+	mutex_lock(&synproxy_mutex);
 	snet->hook_ref4--;
 	if (snet->hook_ref4 == 0)
 		nf_unregister_net_hooks(net, ipv4_synproxy_ops,
 					ARRAY_SIZE(ipv4_synproxy_ops));
+	mutex_unlock(&synproxy_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_synproxy_ipv4_fini);
 
@@ -1192,27 +1199,32 @@ static const struct nf_hook_ops ipv6_synproxy_ops[] = {
 int
 nf_synproxy_ipv6_init(struct synproxy_net *snet, struct net *net)
 {
-	int err;
+	int err = 0;
 
+	mutex_lock(&synproxy_mutex);
 	if (snet->hook_ref6 == 0) {
 		err = nf_register_net_hooks(net, ipv6_synproxy_ops,
 					    ARRAY_SIZE(ipv6_synproxy_ops));
 		if (err)
-			return err;
+			goto out;
 	}
 
 	snet->hook_ref6++;
-	return 0;
+out:
+	mutex_unlock(&synproxy_mutex);
+	return err;
 }
 EXPORT_SYMBOL_GPL(nf_synproxy_ipv6_init);
 
 void
 nf_synproxy_ipv6_fini(struct synproxy_net *snet, struct net *net)
 {
+	mutex_lock(&synproxy_mutex);
 	snet->hook_ref6--;
 	if (snet->hook_ref6 == 0)
 		nf_unregister_net_hooks(net, ipv6_synproxy_ops,
 					ARRAY_SIZE(ipv6_synproxy_ops));
+	mutex_unlock(&synproxy_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_synproxy_ipv6_fini);
 #endif /* CONFIG_IPV6 */
Signature · 1 line
2.53.0
author maintainer
#211 lore raw

PATCH 201/522 netfilter: conntrack_irc: fix possible out-of-bounds read

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Florian Westphal <[email protected]>

[ Upstream commit 66eba0ffce3b7e11449946b4cbbef8ea36112f56 ]

When parsing fails after we've matched the command string we should bail out instead of trying to match a different command.

This helper should be deprecated, given prevalence of TLS I doubt it has any relevance in 2026.

---
 net/netfilter/nf_conntrack_irc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
net/netfilter/nf_conntrack_irc.c +2 -2
index 5703846bea3b69..0f50ea92ced9df 100644
@@ -208,7 +208,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 			if (parse_dcc(data, data_limit, &dcc_ip,
 				       &dcc_port, &addr_beg_p, &addr_end_p)) {
 				pr_debug("unable to parse dcc command\n");
-				continue;
+				goto out;
 			}
 
 			pr_debug("DCC bound ip/port: %pI4:%u\n",
@@ -222,7 +222,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
 				net_warn_ratelimited("Forged DCC command from %pI4: %pI4:%u\n",
 						     &tuple->src.u3.ip,
 						     &dcc_ip, dcc_port);
-				continue;
+				goto out;
 			}
 
 			exp = nf_ct_expect_alloc(ct);
Signature · 1 line
2.53.0
author maintainer
#212 lore raw

PATCH 202/522 netfilter: bridge: make ebt_snat ARP rewrite writable

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Yiming Qian <[email protected]>

[ Upstream commit 67ba971ae02514d85818fe0c32549ab4bfa3bf49 ]

The ebtables SNAT target keeps the Ethernet source address rewrite behind skb_ensure_writable(skb, 0). This is intentional: at the bridge ebtables hooks the Ethernet header is addressed through skb_mac_header()/eth_hdr(), while skb->data points at the Ethernet payload. Asking skb_ensure_writable() for ETH_HLEN bytes would check the payload, not the Ethernet header, and would reintroduce the small packet regression fixed by commit 63137bc5882a.

However, the optional ARP sender hardware address rewrite is different. It writes through skb_store_bits() at an offset relative to skb->data:

        skb_store_bits(skb, sizeof(struct arphdr), info->mac, ETH_ALEN)

skb_header_pointer() only safely reads the ARP header; it does not make the later sender hardware address range writable. If that range is still held in a nonlinear skb fragment backed by a splice-imported file page, skb_store_bits() maps the frag page and copies the new MAC address directly into it.

Ensure the ARP SHA range is writable before reading the ARP header and before calling skb_store_bits().

Fixes 63137bc5882a ("netfilter: ebtables: Fixes dropping of small packets in bridge nat")
---
 net/bridge/netfilter/ebt_snat.c | 3 +++
 1 file changed, 3 insertions(+)
net/bridge/netfilter/ebt_snat.c +3 -0
index 7dfbcdfc30e5d2..c9e229af0366b8 100644
@@ -31,6 +31,9 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 		const struct arphdr *ap;
 		struct arphdr _ah;
 
+		if (skb_ensure_writable(skb, sizeof(_ah) + ETH_ALEN))
+			return EBT_DROP;
+
 		ap = skb_header_pointer(skb, 0, sizeof(_ah), &_ah);
 		if (ap == NULL)
 			return EBT_DROP;
Signature · 1 line
2.53.0
author maintainer
#213 lore raw

PATCH 203/522 dm cache policy smq: check allocation under invalidate lock

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Guangshuo Li <[email protected]>

[ Upstream commit d3f0a606b9f278ece8a0df626ded9c4044071235 ]

commit 2d1f7b65f5de ("dm cache policy smq: fix missing locks in invalidating cache blocks") added mq->lock around the destructive part of smq_invalidate_mapping(), but left the e->allocated check outside the critical section.

That leaves a check-then-act race. Two concurrent invalidators can both observe e->allocated as true before either of them takes mq->lock. The first invalidator that acquires the lock removes the entry from the queues and hash table and then calls free_entry(), which clears e->allocated and puts the entry back on the free list. The second invalidator can then acquire mq->lock and continue with the stale result of the unlocked check.

This can corrupt the SMQ queues or hash table by deleting an entry that is no longer on those structures. It can also hit the allocation check in free_entry() when the same entry is freed again.

Move the allocation check under mq->lock so the predicate and the destructive operations are serialized by the same lock.

Fixes 2d1f7b65f5de ("dm cache policy smq: fix missing locks in invalidating cache blocks")
---
 drivers/md/dm-cache-policy-smq.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)
drivers/md/dm-cache-policy-smq.c +8 -4
index d4c2bc5c0ef457..38fe5c31699bc1 100644
@@ -1588,18 +1588,22 @@ static int smq_invalidate_mapping(struct dm_cache_policy *p, dm_cblock_t cblock)
 	struct smq_policy *mq = to_smq_policy(p);
 	struct entry *e = get_entry(&mq->cache_alloc, from_cblock(cblock));
 	unsigned long flags;
-
-	if (!e->allocated)
-		return -ENODATA;
+	int r = 0;
 
 	spin_lock_irqsave(&mq->lock, flags);
+	if (!e->allocated) {
+		r = -ENODATA;
+		goto out;
+	}
 	// FIXME: what if this block has pending background work?
 	del_queue(mq, e);
 	h_remove(&mq->table, e);
 	free_entry(&mq->cache_alloc, e);
+
+out:
 	spin_unlock_irqrestore(&mq->lock, flags);
 
-	return 0;
+	return r;
 }
 
 static uint32_t smq_get_hint(struct dm_cache_policy *p, dm_cblock_t cblock)
Signature · 1 line
2.53.0
author maintainer
#214 lore raw

PATCH 204/522 net/sched: act_api: use RCU with deferred freeing for action lifecycle

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Jamal Hadi Salim <[email protected]>

[ Upstream commit 5057e1aca011e51ef51498c940ef96f3d3e8a305 ]

When NEWTFILTER and DELFILTER are run concurrently it is possible to create a race with an associated action.

Let's illustrate with CPU0 running NEWTFILTER and CPU1 running DELFILTER:

0: mutex_lock() <-- holds the idr lock
0: rcu_read_lock()
0: p = idr_find(idr, index) <-- action p is valid (RCU protects IDR) 0: mutex_unlock() <-- releases the idr lock
1: refcount_dec_and_mutex_lock() <-- refcnt 1->0, mutex held
1: idr_remove(idr, index) <-- Action removed from IDR
1: mutex_unlock() <-- mutex released allowing us to delete the action 1: tcf_action_cleanup(p); kfree(p) <-- Kfrees p immediately, no deferral 0: refcount_inc_not_zero(&p->tcfa_refcnt) <-- ouch, UAF p points to freed memory

This patch fixes the race condition between NEWTFILTER and DELFILTER by adding struct rcu_head to tc_action used in the deferral and introducing a call_rcu() in the delete path to defer the final kfree().

Note: this is a revert of commit d7fb60b9cafb ("net_sched: get rid of tcfa_rcu") but also modernization/simplification to directly use kfree_rcu().

Let's illustrate the new restored code path:

0: rcu_read_lock()
1: refcount_dec_and_mutex_lock() <-- refcnt 1->0, mutex held
1: idr_remove(idr, index)
1: mutex_unlock()
1: call_rcu(&p->tcfa_rcu, tcf_action_rcu_free) <-- defer kfree after grace period 0: p = idr_find(idr, index)
0: refcount_inc_not_zero(&p->tcfa_refcnt) <-- fails, refcnt already 0 1: rcu_read_unlock() <-- release so freeing can run after grace period

After CPU1 calls idr_remove(), the object is no longer reachable through the IDR. CPU0's subsequent idr_find() will return NULL, and even if it still held a stale pointer, the immediate kfree() is now deferred until after the RCU grace period, so no UAF can occur.

---
 include/net/act_api.h | 1 +
 net/sched/act_api.c   | 7 +------
 2 files changed, 2 insertions(+), 6 deletions(-)
include/net/act_api.h +1 -0
index 31e8d8f8bcd7eb..55e3b5ec1d92d8 100644
@@ -42,6 +42,7 @@ struct tc_action {
 	struct tc_cookie	__rcu *act_cookie;
 	struct tcf_chain	__rcu *goto_chain;
 	u32			tcfa_flags;
+	struct rcu_head         tcfa_rcu;
 	u8			hw_stats;
 	u8			used_hw_stats;
 	bool			used_hw_stats_valid;
net/sched/act_api.c +1 -6
index b75e22756c4b09..47f0d4c3dc487f 100644
@@ -111,11 +111,6 @@ struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action,
 }
 EXPORT_SYMBOL(tcf_action_set_ctrlact);
 
-/* XXX: For standalone actions, we don't need a RCU grace period either, because
- * actions are always connected to filters and filters are already destroyed in
- * RCU callbacks, so after a RCU grace period actions are already disconnected
- * from filters. Readers later can not find us.
- */
 static void free_tcf(struct tc_action *p)
 {
 	struct tcf_chain *chain = rcu_dereference_protected(p->goto_chain, 1);
@@ -128,7 +123,7 @@ static void free_tcf(struct tc_action *p)
 	if (chain)
 		tcf_chain_put_by_act(chain);
 
-	kfree(p);
+	kfree_rcu(p, tcfa_rcu);
 }
 
 static void offload_action_hw_count_set(struct tc_action *act,
Signature · 1 line
2.53.0
author maintainer
#215 lore raw

PATCH 205/522 6lowpan: fix off-by-one in multicast context address compression

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Yizhou Zhao <[email protected]>

[ Upstream commit 2a58899d11009bffc7b4b32a571858f381121837 ]

The second memcpy in lowpan_iphc_mcast_ctx_addr_compress() uses &data[1] as destination and &ipaddr->s6_addr[11] as source, but both should be offset by one: &data[2] and &ipaddr->s6_addr[12] respectively.

This off-by-one has two consequences:
1. data[1] is overwritten with s6_addr[11], corrupting the RIID field in the compressed multicast address
2. data[5] is never written, so uninitialized kernel stack memory is transmitted over the network via lowpan_push_hc_data(), leaking kernel stack contents

The correct inline data layout must match what the decompression function lowpan_uncompress_multicast_ctx_daddr() expects:
data[0..1] = s6_addr[1..2] (flags/scope + RIID) data[2..5] = s6_addr[12..15] (group ID)

Also zero-initialize the data array as a defensive measure against similar bugs in the future.

---
 net/6lowpan/iphc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
net/6lowpan/iphc.c +2 -2
index 52fad5dad9f715..d762c49e722fae 100644
@@ -1086,12 +1086,12 @@ static u8 lowpan_iphc_mcast_ctx_addr_compress(u8 **hc_ptr,
 					      const struct lowpan_iphc_ctx *ctx,
 					      const struct in6_addr *ipaddr)
 {
-	u8 data[6];
+	u8 data[6] = {};
 
 	/* flags/scope, reserved (RIID) */
 	memcpy(data, &ipaddr->s6_addr[1], 2);
 	/* group ID */
-	memcpy(&data[1], &ipaddr->s6_addr[11], 4);
+	memcpy(&data[2], &ipaddr->s6_addr[12], 4);
 	lowpan_push_hc_data(hc_ptr, data, 6);
 
 	return LOWPAN_IPHC_DAM_00;
Signature · 1 line
2.53.0
author maintainer
#216 lore raw

PATCH 206/522 drm/imx: Fix three kernel-doc warnings in dcss-scaler.c

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Yicong Hui <[email protected]>

[ Upstream commit ae0383e5a9a4b12d68c76c4769857def4665deff ]

Fix the following W=1 kerneldoc warnings by adding the missing parameter descriptions for @phase0_identity and @nn_interpolation in dcss_scaler_filter_design() and @phase0_identity in dcss_scaler_gaussian_filter()

Warning: drivers/gpu/drm/imx/dcss/dcss-scaler.c:173 function parameter 'phase0_identity' not described in 'dcss_scaler_gaussian_filter'
Warning: drivers/gpu/drm/imx/dcss/dcss-scaler.c:270 function parameter 'phase0_identity' not described in 'dcss_scaler_filter_design'
Warning: drivers/gpu/drm/imx/dcss/dcss-scaler.c:270 function parameter 'nn_interpolation' not described in 'dcss_scaler_filter_design'

Fixes 9021c317b770 ("drm/imx: Add initial support for DCSS on iMX8MQ")
---
 drivers/gpu/drm/imx/dcss/dcss-scaler.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/gpu/drm/imx/dcss/dcss-scaler.c +3 -0
index 47852b9dd5eaa2..d2a89a99bd71cf 100644
@@ -166,6 +166,7 @@ static int exp_approx_q(int x)
  * dcss_scaler_gaussian_filter() - Generate gaussian prototype filter.
  * @fc_q: fixed-point cutoff frequency normalized to range [0, 1]
  * @use_5_taps: indicates whether to use 5 taps or 7 taps
+ * @phase0_identity: whether to override phase 0 coefficients with identity filter
  * @coef: output filter coefficients
  */
 static void dcss_scaler_gaussian_filter(int fc_q, bool use_5_taps,
@@ -262,7 +263,9 @@ static void dcss_scaler_nearest_neighbor_filter(bool use_5_taps,
  * @src_length: length of input
  * @dst_length: length of output
  * @use_5_taps: 0 for 7 taps per phase, 1 for 5 taps
+ * @phase0_identity: whether to override phase 0 coefficients with identity filter
  * @coef: output coefficients
+ * @nn_interpolation: whether to use nearest neighbor instead of gaussian filter
  */
 static void dcss_scaler_filter_design(int src_length, int dst_length,
 				      bool use_5_taps, bool phase0_identity,
Signature · 1 line
2.53.0
author maintainer
#217 lore raw

PATCH 207/522 pcnet32: stop holding device spin lock during napi_complete_done

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Oscar Maes <[email protected]>

[ Upstream commit 73bf3cca7de6a73f53b6a52dc3b1c82ae5667a4d ]

napi_complete_done may call gro_flush_normal (though not currently, as GRO is unsupported at the moment), which may result in packet TX. This will eventually result in calling pcnet32_start_xmit - resulting in a deadlock while trying to re-acquire the already locked spin lock.

It is safe to split the spinlock block into two, because the hardware registers are still protected from concurrent access, and the two blocks perform unrelated operations that don't need to happen atomically.

---
 drivers/net/ethernet/amd/pcnet32.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/amd/pcnet32.c +3 -1
index 72db9f9e7beeae..81cb83caf62a15 100644
@@ -1403,8 +1403,10 @@ static int pcnet32_poll(struct napi_struct *napi, int budget)
 		pcnet32_restart(dev, CSR0_START);
 		netif_wake_queue(dev);
 	}
+	spin_unlock_irqrestore(&lp->lock, flags);
 
 	if (work_done < budget && napi_complete_done(napi, work_done)) {
+		spin_lock_irqsave(&lp->lock, flags);
 		/* clear interrupt masks */
 		val = lp->a->read_csr(ioaddr, CSR3);
 		val &= 0x00ff;
@@ -1412,9 +1414,9 @@ static int pcnet32_poll(struct napi_struct *napi, int budget)
 
 		/* Set interrupt enable. */
 		lp->a->write_csr(ioaddr, CSR0, CSR0_INTEN);
+		spin_unlock_irqrestore(&lp->lock, flags);
 	}
 
-	spin_unlock_irqrestore(&lp->lock, flags);
 	return work_done;
 }
 
Signature · 1 line
2.53.0
author maintainer
#218 lore raw

PATCH 208/522 net: Annotate sk->sk_write_space() for UDP SOCKMAP.

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit b748765019fe9e9234660327090fc1a9665cdbdd ]

UDP TX skb->destructor() is sock_wfree(), and UDP holds lock_sock() only for UDP_CORK / MSG_MORE sendmsg().

Otherwise, sk->sk_write_space() may be read locklessly while SOCKMAP rewrites sk->sk_write_space().

Let's use WRITE_ONCE() and READ_ONCE() for sk->sk_write_space().

Note that the write side is annotated by commit 2ef2b20cf4e0 ("net: annotate data-races around sk->sk_{data_ready,write_space}").

---
 net/core/sock.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
net/core/sock.c +6 -2
index 6c178b47426669..62411c8870e855 100644
@@ -2433,8 +2433,12 @@ void sock_wfree(struct sk_buff *skb)
 	bool free;
 
 	if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) {
+		void (*sk_write_space)(struct sock *sk);
+
+		sk_write_space = READ_ONCE(sk->sk_write_space);
+
 		if (sock_flag(sk, SOCK_RCU_FREE) &&
-		    sk->sk_write_space == sock_def_write_space) {
+		    sk_write_space == sock_def_write_space) {
 			rcu_read_lock();
 			free = refcount_sub_and_test(len, &sk->sk_wmem_alloc);
 			sock_def_write_space_wfree(sk);
@@ -2449,7 +2453,7 @@ void sock_wfree(struct sk_buff *skb)
 		 * after sk_write_space() call
 		 */
 		WARN_ON(refcount_sub_and_test(len - 1, &sk->sk_wmem_alloc));
-		sk->sk_write_space(sk);
+		sk_write_space(sk);
 		len = 1;
 	}
 	/*
Signature · 1 line
2.53.0
#219 lore raw

Re: [PATCH 6.1 208/522] net: Annotate sk->sk_write_space() for UDP SOCKMAP.

Quoted 11 lines · Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit b748765019fe9e9234660327090fc1a9665cdbdd ]

UDP TX skb->destructor() is sock_wfree(), and UDP holds lock_sock() only for UDP_CORK / MSG_MORE sendmsg().

Quoted 7 lines

Otherwise, sk->sk_write_space() may be read locklessly while SOCKMAP rewrites sk->sk_write_space().

Let's use WRITE_ONCE() and READ_ONCE() for sk->sk_write_space().

Note that the write side is annotated by commit 2ef2b20cf4e0 ("net: annotate data-races around sk->sk_{data_ready,write_space}").

[...]

That other commit hasn't yet been backported to 6.1, so this is not a complete fix.

Ben.

Signature · 2 lines
Ben Hutchings
Who are all these weirdos? - David Bowie, on joining IRC
author maintainer
#220 lore raw

Re: [PATCH 6.1 208/522] net: Annotate sk->sk_write_space() for UDP SOCKMAP.

Quoted 15 lines · Ben Hutchings
Quoted 14 lines · Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit b748765019fe9e9234660327090fc1a9665cdbdd ]

UDP TX skb->destructor() is sock_wfree(), and UDP holds lock_sock() only for UDP_CORK / MSG_MORE sendmsg().

Otherwise, sk->sk_write_space() may be read locklessly while SOCKMAP rewrites sk->sk_write_space().

Quoted 8 lines
Quoted 4 lines

Let's use WRITE_ONCE() and READ_ONCE() for sk->sk_write_space().

Note that the write side is annotated by commit 2ef2b20cf4e0 ("net: annotate data-races around sk->sk_{data_ready,write_space}").

[...]

That other commit hasn't yet been backported to 6.1, so this is not a complete fix.

True, someone needs to provide that backport as well :)

thanks,

greg k-h

maintainer
#221 lore raw

Re: [PATCH 6.1 208/522] net: Annotate sk->sk_write_space() for UDP SOCKMAP.

Quoted 4 lines
Quoted 2 lines

That other commit hasn't yet been backported to 6.1, so this is not a complete fix.

True, someone needs to provide that backport as well :)

I looked at backporting the write-side annotation 2ef2b20cf4e0 ("net:
annotate data-races around sk->sk_{data_ready,write_space}") to 6.1, but a straight cherry-pick drags in four drop-counter/scalability infrastructure commits as Stable-dep-of (sk_drops_skbadd, sk_drop_counters, the raw-socket and NUMA softnet drop_counters work). That's far too much feature churn for what should be a small data-race annotation, so I'm not queuing it as-is.

I'll either prepare a minimal hand-crafted backport of just the WRITE_ONCE() annotation in net/core/skmsg.c (the part that pairs with the already-queued b748765019fe ("net: Annotate sk->sk_write_space() for UDP SOCKMAP.") READ_ONCE side), or we can leave the read-side annotation unpaired for now. Leaning towards the minimal hand-crafted version; will follow up.

Thanks,
Sasha

maintainer
#222 lore raw

Re: [PATCH 6.1 208/522] net: Annotate sk->sk_write_space() for UDP SOCKMAP.

Quoted 4 lines

I'll either prepare a minimal hand-crafted backport of just the WRITE_ONCE() annotation [...], or we can leave the read-side annotation unpaired for now. Leaning towards the minimal hand-crafted version; will follow up.

I've queued a backport of 2ef2b20cf4e0 ("net: annotate data-races around sk->sk_{data_ready,write_space}") for 6.1.

Signature · 2 lines
Thanks,
Sasha
author maintainer
#223 lore raw

PATCH 209/522 net: garp: fix unsigned integer underflow in garp_pdu_parse_attr

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Yizhou Zhao <[email protected]>

[ Upstream commit 16e408e607a94b646fb14a2a98422c6877ae4b3c ]

The receive-side GARP attribute parser computes dlen with reversed operands:

        dlen = sizeof(*ga) - ga->len;

ga->len is the on-wire attribute length and includes the GARP attribute header. For normal attributes with data, ga->len is larger than sizeof(*ga), so the subtraction underflows in unsigned arithmetic.

The resulting value is later passed to garp_attr_lookup(), whose length argument is u8. After truncation, the parsed data length usually no longer matches the length stored for locally registered attributes, so received Join/Leave events are ignored. This breaks the GARP receive path for common attributes, such as GVRP VLAN registration attributes.

Compute the data length as the attribute length minus the header length.

---
 net/802/garp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/802/garp.c +1 -1
index fc9eb02a912f81..f8037227e6dd66 100644
@@ -452,7 +452,7 @@ static int garp_pdu_parse_attr(struct garp_applicant *app, struct sk_buff *skb,
 	if (!pskb_may_pull(skb, ga->len))
 		return -1;
 	skb_pull(skb, ga->len);
-	dlen = sizeof(*ga) - ga->len;
+	dlen = ga->len - sizeof(*ga);
 
 	if (attrtype > app->app->maxattr)
 		return 0;
Signature · 1 line
2.53.0
author maintainer
#224 lore raw

PATCH 210/522 net: lan743x: permit VLAN-tagged packets up to configured MTU

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: David Thompson <[email protected]>

[ Upstream commit 8173d22b211f615015f7b35f48ab11a6dd78dc99 ]

VLAN-tagged interfaces on lan743x devices were previously unreachable via SSH and failed to respond to large ping packets (e.g. "ping -s 1469" given MTU=1500). In these scenarios, "ethtool -S" reports non-zero "RX Oversize Frame Errors". According to Microchip AN2948, the MAC_RX FSE (VLAN field size enforcement) bit determines whether frames with VLAN tags exceeding the base MTU plus tag length are discarded.

The driver must set the MAC_RX.FSE bit before setting MAC_RX.RXEN to allow VLAN-tagged frames up to the interface MTU, preventing them from being treated as oversized. As a result, both the base and VLAN-tagged interfaces can use the same MTU without receive errors.

---
 drivers/net/ethernet/microchip/lan743x_main.c | 32 +++++++++++++++++++
 drivers/net/ethernet/microchip/lan743x_main.h |  1 +
 2 files changed, 33 insertions(+)
drivers/net/ethernet/microchip/lan743x_main.c +32 -0
index 5dacc786db4559..c51d316ccdfb86 100644
@@ -1271,6 +1271,36 @@ static void lan743x_mac_set_address(struct lan743x_adapter *adapter,
 		   "MAC address set to %pM\n", addr);
 }
 
+static void lan743x_mac_rx_enable_fse(struct lan743x_adapter *adapter)
+{
+	u32 mac_rx;
+	bool rxen;
+
+	mac_rx = lan743x_csr_read(adapter, MAC_RX);
+	if (mac_rx & MAC_RX_FSE_)
+		return;
+
+	rxen = mac_rx & MAC_RX_RXEN_;
+	if (rxen) {
+		mac_rx &= ~MAC_RX_RXEN_;
+		lan743x_csr_write(adapter, MAC_RX, mac_rx);
+		lan743x_csr_wait_for_bit(adapter, MAC_RX, MAC_RX_RXD_,
+					 1, 1000, 20000, 100);
+	}
+
+	/* Per AN2948, hardware prevents modification of the FSE bit while the
+	 * MAC receiver is enabled (RXEN bit set). Use separate register write
+	 * to assert the FSE bit before enabling the RXEN bit in MAC_RX
+	 */
+	mac_rx |= MAC_RX_FSE_;
+	lan743x_csr_write(adapter, MAC_RX, mac_rx);
+
+	if (rxen) {
+		mac_rx |= MAC_RX_RXEN_;
+		lan743x_csr_write(adapter, MAC_RX, mac_rx);
+	}
+}
+
 static int lan743x_mac_init(struct lan743x_adapter *adapter)
 {
 	bool mac_address_valid = true;
@@ -1310,6 +1340,8 @@ static int lan743x_mac_init(struct lan743x_adapter *adapter)
 	lan743x_mac_set_address(adapter, adapter->mac_address);
 	eth_hw_addr_set(netdev, adapter->mac_address);
 
+	lan743x_mac_rx_enable_fse(adapter);
+
 	return 0;
 }
 
drivers/net/ethernet/microchip/lan743x_main.h +1 -0
index c0d209f36188a1..9f20c727a7e137 100644
@@ -180,6 +180,7 @@
 #define MAC_RX				(0x104)
 #define MAC_RX_MAX_SIZE_SHIFT_		(16)
 #define MAC_RX_MAX_SIZE_MASK_		(0x3FFF0000)
+#define MAC_RX_FSE_			BIT(2)
 #define MAC_RX_RXD_			BIT(1)
 #define MAC_RX_RXEN_			BIT(0)
 
Signature · 1 line
2.53.0
author maintainer
#225 lore raw

PATCH 211/522 net: fec: fix pinctrl default state restore order on resume

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Tapio Reijonen <[email protected]>

[ Upstream commit b455410146bf723c7ebcb49ecd5becc0d6611482 ]

In fec_resume(), fec_enet_clk_enable() is called before pinctrl_pm_select_default_state() in the non-WoL path, inverting the ordering used in fec_suspend() which correctly switches to the sleep pinctrl state before disabling clocks.

For PHYs with the PHY_RST_AFTER_CLK_EN flag (e.g. TI DP83848 or SMSC LAN87xx), fec_enet_clk_enable() triggers a hardware reset pulse via the phy-reset GPIO. With the GPIO pin still in sleep pinctrl state at that point, the GPIO write has no physical effect and the PHY never receives the required reset after clock enable, leading to unreliable link establishment after system resume.

Fix by restoring the default pinctrl state before enabling clocks, making resume the proper mirror of suspend. The call is made
unconditionally: fec_suspend() only switches to the sleep pinctrl state on the non-WoL path and leaves the pins in the default state when WoL is enabled, so on a WoL resume the device is already in the default state and pinctrl_pm_select_default_state() is a no-op.

---
 drivers/net/ethernet/freescale/fec_main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/net/ethernet/freescale/fec_main.c +1 -2
index e9c4945d0c2713..d1510af6aff1b5 100644
@@ -4322,6 +4322,7 @@ static int __maybe_unused fec_resume(struct device *dev)
 		if (fep->rpm_active)
 			pm_runtime_force_resume(dev);
 
+		pinctrl_pm_select_default_state(&fep->pdev->dev);
 		ret = fec_enet_clk_enable(ndev, true);
 		if (ret) {
 			rtnl_unlock();
@@ -4338,8 +4339,6 @@ static int __maybe_unused fec_resume(struct device *dev)
 			val &= ~(FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
 			writel(val, fep->hwp + FEC_ECNTRL);
 			fep->wol_flag &= ~FEC_WOL_FLAG_SLEEP_ON;
-		} else {
-			pinctrl_pm_select_default_state(&fep->pdev->dev);
 		}
 		fec_restart(ndev);
 		netif_tx_lock_bh(ndev);
Signature · 1 line
2.53.0
author maintainer
#226 lore raw

PATCH 212/522 Bluetooth: RFCOMM: hold listener socket in rfcomm_connect_ind()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Zhang Cen <[email protected]>

[ Upstream commit 43c441edacf953b39517a44f5e5e10a93618b226 ]

rfcomm_get_sock_by_channel() scans rfcomm_sk_list under the list lock, but returns the selected listener after dropping that lock without taking a reference. rfcomm_connect_ind() then locks the listener, queues a child socket on it, and may notify it after unlocking it.

The buggy scenario involves two paths, with each column showing the order within that path:

rfcomm_connect_ind(): listener close:
1. Find parent in 1. close() enters
rfcomm_get_sock_by_channel() rfcomm_sock_release().
2. Drop rfcomm_sk_list.lock 2. rfcomm_sock_shutdown()
without pinning parent. closes the listener.
3. Call lock_sock(parent) and 3. rfcomm_sock_kill()
bt_accept_enqueue(parent, unlinks and puts parent.
sk, true).
4. Read parent flags and may 4. parent can be freed.
call sk_state_change().

If close wins the race, parent can be freed before rfcomm_connect_ind() reaches lock_sock(), bt_accept_enqueue(), or the deferred-setup callback.

Take a reference on the listener before leaving rfcomm_sk_list.lock. After lock_sock() succeeds, recheck that it is still in BT_LISTEN before queueing a child, cache the deferred-setup bit while the parent is locked, and drop the reference after the last parent use.

KASAN reported a slab-use-after-free in lock_sock_nested() from rfcomm_connect_ind(), with the freeing stack going through rfcomm_sock_kill() and rfcomm_sock_release().

Fixes 1da177e4c3f4 ("Linux-2.6.12-rc2")
---
 net/bluetooth/rfcomm/sock.c | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)
net/bluetooth/rfcomm/sock.c +22 -4
index bc2b22c2b3aec7..d72cdcd2e2bb11 100644
@@ -122,7 +122,7 @@ static struct sock *__rfcomm_get_listen_sock_by_addr(u8 channel, bdaddr_t *src)
 }
 
 /* Find socket with channel and source bdaddr.
- * Returns closest match.
+ * Returns closest match with an extra reference held.
  */
 static struct sock *rfcomm_get_sock_by_channel(int state, u8 channel, bdaddr_t *src)
 {
@@ -136,15 +136,25 @@ static struct sock *rfcomm_get_sock_by_channel(int state, u8 channel, bdaddr_t *
 
 		if (rfcomm_pi(sk)->channel == channel) {
 			/* Exact match. */
-			if (!bacmp(&rfcomm_pi(sk)->src, src))
+			if (!bacmp(&rfcomm_pi(sk)->src, src)) {
+				sock_hold(sk);
 				break;
+			}
 
 			/* Closest match */
-			if (!bacmp(&rfcomm_pi(sk)->src, BDADDR_ANY))
+			if (!bacmp(&rfcomm_pi(sk)->src, BDADDR_ANY)) {
+				if (sk1)
+					sock_put(sk1);
+
 				sk1 = sk;
+				sock_hold(sk1);
+			}
 		}
 	}
 
+	if (sk && sk1)
+		sock_put(sk1);
+
 	read_unlock(&rfcomm_sk_list.lock);
 
 	return sk ? sk : sk1;
@@ -941,6 +951,7 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc *
 {
 	struct sock *sk, *parent;
 	bdaddr_t src, dst;
+	bool defer_setup = false;
 	int result = 0;
 
 	BT_DBG("session %p channel %d", s, channel);
@@ -954,6 +965,11 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc *
 
 	lock_sock(parent);
 
+	if (parent->sk_state != BT_LISTEN)
+		goto done;
+
+	defer_setup = test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags);
+
 	/* Check for backlog size */
 	if (sk_acceptq_is_full(parent)) {
 		BT_DBG("backlog full %d", parent->sk_ack_backlog);
@@ -981,9 +997,11 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc *
 done:
 	release_sock(parent);
 
-	if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags))
+	if (defer_setup)
 		parent->sk_state_change(parent);
 
+	sock_put(parent);
+
 	return result;
 }
 
Signature · 1 line
2.53.0
author maintainer
#227 lore raw

PATCH 213/522 Bluetooth: MGMT: validate advertising TLV before type checks

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Zhang Cen <[email protected]>

[ Upstream commit de23fb62259aa01d294f77238ae3b835eb674413 ]

tlv_data_is_valid() reads each advertising data field length from data[i], then inspects data[i + 1] for managed EIR types before checking that the current field still fits inside the supplied buffer.

A malformed field whose length byte is the last byte of the buffer can therefore make the parser read one byte past the advertising data.

KASAN reported the following when a malformed MGMT_OP_ADD_ADVERTISING request reached that path:

  BUG: KASAN: vmalloc-out-of-bounds in tlv_data_is_valid()
  Read of size 1
  Call trace:
    tlv_data_is_valid()
    add_advertising()
    hci_mgmt_cmd()
    hci_sock_sendmsg()

Move the existing element-length check before any type-octet inspection so each non-empty element is proven to contain its type byte before the parser looks at data[i + 1].

Fixes 2bb36870e8cb ("Bluetooth: Unify advertising instance flags check")
---
 net/bluetooth/mgmt.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
net/bluetooth/mgmt.c +6 -6
index dd7d12418e0738..cc058c77d2e252 100644
@@ -8602,6 +8602,12 @@ static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data,
 		if (!cur_len)
 			continue;
 
+		/* If the current field length would exceed the total data
+		 * length, then it's invalid.
+		 */
+		if (i + cur_len >= len)
+			return false;
+
 		if (data[i + 1] == EIR_FLAGS &&
 		    (!is_adv_data || flags_managed(adv_flags)))
 			return false;
@@ -8618,12 +8624,6 @@ static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data,
 		if (data[i + 1] == EIR_APPEARANCE &&
 		    appearance_managed(adv_flags))
 			return false;
-
-		/* If the current field length would exceed the total data
-		 * length, then it's invalid.
-		 */
-		if (i + cur_len >= len)
-			return false;
 	}
 
 	return true;
Signature · 1 line
2.53.0
author maintainer
#228 lore raw

PATCH 214/522 Bluetooth: RFCOMM: validate skb length in MCC handlers

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: SeungJu Cheon <[email protected]>

[ Upstream commit 23882b828c3c8c51d0c946446a396b10abb3b16b ]

The RFCOMM MCC handlers cast skb->data to protocol-specific structs without validating skb->len first. A malicious remote device can send truncated MCC frames and trigger out-of-bounds reads in these handlers.

Fix this by using skb_pull_data() to validate and access the required data before dereferencing it.

rfcomm_recv_rpn() requires special handling since ETSI TS 07.10 allows 1-byte RPN requests. Handle this by validating only the DLCI byte first, and validating the full struct only when len > 1.

---
 net/bluetooth/rfcomm/core.c | 67 +++++++++++++++++++++++++++----------
 1 file changed, 49 insertions(+), 18 deletions(-)
net/bluetooth/rfcomm/core.c +49 -18
index 4f54c7df3a94f8..374187def190da 100644
@@ -1427,10 +1427,15 @@ static int rfcomm_apply_pn(struct rfcomm_dlc *d, int cr, struct rfcomm_pn *pn)
 
 static int rfcomm_recv_pn(struct rfcomm_session *s, int cr, struct sk_buff *skb)
 {
-	struct rfcomm_pn *pn = (void *) skb->data;
+	struct rfcomm_pn *pn;
 	struct rfcomm_dlc *d;
-	u8 dlci = pn->dlci;
+	u8 dlci;
+
+	pn = skb_pull_data(skb, sizeof(*pn));
+	if (!pn)
+		return -EILSEQ;
 
+	dlci = pn->dlci;
 	BT_DBG("session %p state %ld dlci %d", s, s->state, dlci);
 
 	if (!dlci)
@@ -1479,8 +1484,8 @@ static int rfcomm_recv_pn(struct rfcomm_session *s, int cr, struct sk_buff *skb)
 
 static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_buff *skb)
 {
-	struct rfcomm_rpn *rpn = (void *) skb->data;
-	u8 dlci = __get_dlci(rpn->dlci);
+	struct rfcomm_rpn *rpn;
+	u8 dlci;
 
 	u8 bit_rate  = 0;
 	u8 data_bits = 0;
@@ -1491,15 +1496,16 @@ static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_
 	u8 xoff_char = 0;
 	u16 rpn_mask = RFCOMM_RPN_PM_ALL;
 
-	BT_DBG("dlci %d cr %d len 0x%x bitr 0x%x line 0x%x flow 0x%x xonc 0x%x xoffc 0x%x pm 0x%x",
-		dlci, cr, len, rpn->bit_rate, rpn->line_settings, rpn->flow_ctrl,
-		rpn->xon_char, rpn->xoff_char, rpn->param_mask);
+	if (len == 1) {
+		rpn = skb_pull_data(skb, 1);
+		if (!rpn)
+			return -EILSEQ;
 
-	if (!cr)
-		return 0;
+		dlci = __get_dlci(rpn->dlci);
+
+		if (!cr)
+			return 0;
 
-	if (len == 1) {
-		/* This is a request, return default (according to ETSI TS 07.10) settings */
 		bit_rate  = RFCOMM_RPN_BR_9600;
 		data_bits = RFCOMM_RPN_DATA_8;
 		stop_bits = RFCOMM_RPN_STOP_1;
@@ -1510,6 +1516,19 @@ static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_
 		goto rpn_out;
 	}
 
+	rpn = skb_pull_data(skb, sizeof(*rpn));
+	if (!rpn)
+		return -EILSEQ;
+
+	dlci = __get_dlci(rpn->dlci);
+
+	BT_DBG("dlci %d cr %d len 0x%x bitr 0x%x line 0x%x flow 0x%x xonc 0x%x xoffc 0x%x pm 0x%x",
+	       dlci, cr, len, rpn->bit_rate, rpn->line_settings, rpn->flow_ctrl,
+	       rpn->xon_char, rpn->xoff_char, rpn->param_mask);
+
+	if (!cr)
+		return 0;
+
 	/* Check for sane values, ignore/accept bit_rate, 8 bits, 1 stop bit,
 	 * no parity, no flow control lines, normal XON/XOFF chars */
 
@@ -1585,9 +1604,14 @@ static int rfcomm_recv_rpn(struct rfcomm_session *s, int cr, int len, struct sk_
 
 static int rfcomm_recv_rls(struct rfcomm_session *s, int cr, struct sk_buff *skb)
 {
-	struct rfcomm_rls *rls = (void *) skb->data;
-	u8 dlci = __get_dlci(rls->dlci);
+	struct rfcomm_rls *rls;
+	u8 dlci;
 
+	rls = skb_pull_data(skb, sizeof(*rls));
+	if (!rls)
+		return -EILSEQ;
+
+	dlci = __get_dlci(rls->dlci);
 	BT_DBG("dlci %d cr %d status 0x%x", dlci, cr, rls->status);
 
 	if (!cr)
@@ -1604,10 +1628,15 @@ static int rfcomm_recv_rls(struct rfcomm_session *s, int cr, struct sk_buff *skb
 
 static int rfcomm_recv_msc(struct rfcomm_session *s, int cr, struct sk_buff *skb)
 {
-	struct rfcomm_msc *msc = (void *) skb->data;
+	struct rfcomm_msc *msc;
 	struct rfcomm_dlc *d;
-	u8 dlci = __get_dlci(msc->dlci);
+	u8 dlci;
+
+	msc = skb_pull_data(skb, sizeof(*msc));
+	if (!msc)
+		return -EILSEQ;
 
+	dlci = __get_dlci(msc->dlci);
 	BT_DBG("dlci %d cr %d v24 0x%x", dlci, cr, msc->v24_sig);
 
 	d = rfcomm_dlc_get(s, dlci);
@@ -1640,17 +1669,19 @@ static int rfcomm_recv_msc(struct rfcomm_session *s, int cr, struct sk_buff *skb
 
 static int rfcomm_recv_mcc(struct rfcomm_session *s, struct sk_buff *skb)
 {
-	struct rfcomm_mcc *mcc = (void *) skb->data;
+	struct rfcomm_mcc *mcc;
 	u8 type, cr, len;
 
+	mcc = skb_pull_data(skb, sizeof(*mcc));
+	if (!mcc)
+		return -EILSEQ;
+
 	cr   = __test_cr(mcc->type);
 	type = __get_mcc_type(mcc->type);
 	len  = __get_mcc_len(mcc->len);
 
 	BT_DBG("%p type 0x%x cr %d", s, type, cr);
 
-	skb_pull(skb, 2);
-
 	switch (type) {
 	case RFCOMM_PN:
 		rfcomm_recv_pn(s, cr, skb);
Signature · 1 line
2.53.0
author maintainer
#229 lore raw

PATCH 215/522 Bluetooth: bnep: fix incorrect length parsing in bnep_rx_frame() extension handling

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Dudu Lu <[email protected]>

[ Upstream commit 72b8deccff17a7644e0367e1aaf1a36cfb014324 ]

In bnep_rx_frame(), the BNEP_FILTER_NET_TYPE_SET and BNEP_FILTER_MULTI_ADDR_SET extension header parsing has two bugs:

1) The 2-byte length field is read with *(u16 *)(skb->data + 1), which performs a native-endian read. The BNEP protocol specifies this field in big-endian (network byte order), and the same file correctly uses get_unaligned_be16() for the identical fields in bnep_ctrl_set_netfilter() and bnep_ctrl_set_mcfilter().

2) The length is multiplied by 2, but unlike BNEP_SETUP_CONN_REQ where the length byte counts UUID pairs (requiring * 2 for two UUIDs per entry), the filter extension length field already represents the total data size in bytes. This is confirmed by bnep_ctrl_set_netfilter() which reads the same field as a byte count and divides by 4 to get the number of filter entries.

The bogus * 2 means skb_pull advances twice as far as it should, either dropping valid data from the next header or causing the pull to fail entirely when the doubled length exceeds the remaining skb.

Fix by splitting the pull into two steps: first use skb_pull_data() to safely pull and validate the 3-byte fixed header (ctrl type + length), then pull the variable-length data using the properly decoded length.

Fixes bf8b9a9cb77b ("Bluetooth: bnep: Add support to extended headers of control frames")
---
 net/bluetooth/bnep/core.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)
net/bluetooth/bnep/core.c +10 -3
index e125afe573fcf2..9d804b08de88e0 100644
@@ -330,11 +330,18 @@ static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb)
 				goto badframe;
 			break;
 		case BNEP_FILTER_MULTI_ADDR_SET:
-		case BNEP_FILTER_NET_TYPE_SET:
-			/* Pull: ctrl type (1 b), len (2 b), data (len bytes) */
-			if (!skb_pull(skb, 3 + *(u16 *)(skb->data + 1) * 2))
+		case BNEP_FILTER_NET_TYPE_SET: {
+			u8 *hdr;
+
+			/* Pull ctrl type (1 b) + len (2 b) */
+			hdr = skb_pull_data(skb, 3);
+			if (!hdr)
+				goto badframe;
+			/* Pull data (len bytes); length is big-endian */
+			if (!skb_pull(skb, get_unaligned_be16(&hdr[1])))
 				goto badframe;
 			break;
+		}
 		default:
 			kfree_skb(skb);
 			return 0;
Signature · 1 line
2.53.0
author maintainer
#230 lore raw

PATCH 216/522 Bluetooth: bnep: reject short frames before parsing

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Zhang Cen <[email protected]>

[ Upstream commit 6770d3a8acdf9151769180cc3710346c4cfbe6f0 ]

A BNEP peer can send a short BNEP SDU. bnep_rx_frame() reads the packet type byte immediately and, for control packets, reads the control opcode and setup UUID-size byte before proving that those bytes are present. bnep_rx_control() also dereferences the control opcode without rejecting an empty control payload.

Use skb_pull_data() for the fixed fields in bnep_rx_frame() so a NULL return gates each dereference. Split the control handler so the frame path can pass an opcode that has already been pulled, and keep the byte-buffer wrapper for extension control payloads.

For BNEP_SETUP_CONN_REQ, name the UUID-size byte before pulling the setup payload. struct bnep_setup_conn_req carries destination and source service UUIDs after that byte, each uuid_size bytes, so the parser now documents that tuple explicitly instead of leaving the pull length as an opaque multiplication.

Validation reproduced this kernel report:
KASAN slab-out-of-bounds in bnep_rx_frame.isra.0+0x130c/0x1790

The buggy address belongs to the object at ffff88800c0f7908 which belongs
to the cache kmalloc-8 of size 8
The buggy address is located 0 bytes to the right of allocated 1-byte
region [ffff88800c0f7908, ffff88800c0f7909)
Read of size 1
Call trace:
  dump_stack_lvl+0xb3/0x140 (?:?)
  print_address_description+0x57/0x3a0 (?:?)
  bnep_rx_frame+0x130c/0x1790 (net/bluetooth/bnep/core.c:306)
  print_report+0xb9/0x2b0 (?:?)
  __virt_addr_valid+0x1ba/0x3a0 (?:?)
  srso_alias_return_thunk+0x5/0xfbef5 (?:?)
  kasan_addr_to_slab+0x21/0x60 (?:?)
  kasan_report+0xe0/0x110 (?:?)
  process_one_work+0xfce/0x17e0 (kernel/workqueue.c:3200)
  worker_thread+0x65c/0xe40 (?:?)
  __kthread_parkme+0x184/0x230 (?:?)
  kthread+0x35e/0x470 (?:?)
  _raw_spin_unlock_irq+0x28/0x50 (?:?)
  ret_from_fork+0x586/0x870 (?:?)
  __switch_to+0x74f/0xdc0 (?:?)
  ret_from_fork_asm+0x1a/0x30 (?:?)
Fixes 1da177e4c3f4 ("Linux-2.6.12-rc2")
Assisted-by Codex:gpt-5.5
---
 net/bluetooth/bnep/core.c | 57 ++++++++++++++++++++++++---------------
 1 file changed, 36 insertions(+), 21 deletions(-)
net/bluetooth/bnep/core.c +36 -21
index 9d804b08de88e0..45d0f84652fc60 100644
@@ -206,14 +206,11 @@ static int bnep_ctrl_set_mcfilter(struct bnep_session *s, u8 *data, int len)
 	return 0;
 }
 
-static int bnep_rx_control(struct bnep_session *s, void *data, int len)
+static int bnep_rx_control_cmd(struct bnep_session *s, u8 cmd, void *data,
+			       int len)
 {
-	u8  cmd = *(u8 *)data;
 	int err = 0;
 
-	data++;
-	len--;
-
 	switch (cmd) {
 	case BNEP_CMD_NOT_UNDERSTOOD:
 	case BNEP_SETUP_CONN_RSP:
@@ -254,6 +251,14 @@ static int bnep_rx_control(struct bnep_session *s, void *data, int len)
 	return err;
 }
 
+static int bnep_rx_control(struct bnep_session *s, void *data, int len)
+{
+	if (len < 1)
+		return -EILSEQ;
+
+	return bnep_rx_control_cmd(s, *(u8 *)data, data + 1, len - 1);
+}
+
 static int bnep_rx_extension(struct bnep_session *s, struct sk_buff *skb)
 {
 	struct bnep_ext_hdr *h;
@@ -299,19 +304,26 @@ static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb)
 {
 	struct net_device *dev = s->dev;
 	struct sk_buff *nskb;
+	u8 *data;
 	u8 type, ctrl_type;
 
 	dev->stats.rx_bytes += skb->len;
 
-	type = *(u8 *) skb->data;
-	skb_pull(skb, 1);
-	ctrl_type = *(u8 *)skb->data;
+	data = skb_pull_data(skb, sizeof(type));
+	if (!data)
+		goto badframe;
+	type = *data;
 
 	if ((type & BNEP_TYPE_MASK) >= sizeof(__bnep_rx_hlen))
 		goto badframe;
 
 	if ((type & BNEP_TYPE_MASK) == BNEP_CONTROL) {
-		if (bnep_rx_control(s, skb->data, skb->len) < 0) {
+		data = skb_pull_data(skb, sizeof(ctrl_type));
+		if (!data)
+			goto badframe;
+		ctrl_type = *data;
+
+		if (bnep_rx_control_cmd(s, ctrl_type, skb->data, skb->len) < 0) {
 			dev->stats.tx_errors++;
 			kfree_skb(skb);
 			return 0;
@@ -324,24 +336,27 @@ static int bnep_rx_frame(struct bnep_session *s, struct sk_buff *skb)
 
 		/* Verify and pull ctrl message since it's already processed */
 		switch (ctrl_type) {
-		case BNEP_SETUP_CONN_REQ:
-			/* Pull: ctrl type (1 b), len (1 b), data (len bytes) */
-			if (!skb_pull(skb, 2 + *(u8 *)(skb->data + 1) * 2))
+		case BNEP_SETUP_CONN_REQ: {
+			u8 uuid_size;
+
+			/* Pull uuid_size and the dst/src service UUIDs. */
+			data = skb_pull_data(skb, sizeof(uuid_size));
+			if (!data)
+				goto badframe;
+			uuid_size = *data;
+			if (!skb_pull(skb, uuid_size + uuid_size))
 				goto badframe;
 			break;
+		}
 		case BNEP_FILTER_MULTI_ADDR_SET:
-		case BNEP_FILTER_NET_TYPE_SET: {
-			u8 *hdr;
-
-			/* Pull ctrl type (1 b) + len (2 b) */
-			hdr = skb_pull_data(skb, 3);
-			if (!hdr)
+		case BNEP_FILTER_NET_TYPE_SET:
+			/* Pull: len (2 b), data (len bytes) */
+			data = skb_pull_data(skb, sizeof(u16));
+			if (!data)
 				goto badframe;
-			/* Pull data (len bytes); length is big-endian */
-			if (!skb_pull(skb, get_unaligned_be16(&hdr[1])))
+			if (!skb_pull(skb, get_unaligned_be16(data)))
 				goto badframe;
 			break;
-		}
 		default:
 			kfree_skb(skb);
 			return 0;
Signature · 1 line
2.53.0
author maintainer
#231 lore raw

PATCH 217/522 Bluetooth: fix memory leak in error path of hci_alloc_dev()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Bharath Reddy <[email protected]>

[ Upstream commit 37b3009bf5976e8ab77c8b9a9bc3bbd7ff49e37f ]

Early failures in Bluetooth HCI UART configuration leak SRCU percpu memory.

When device initialization fails before hci_register_dev() completes, the HCI_UNREGISTER flag is never set. As a result, when the device reference count reaches zero, bt_host_release() evaluates this flag as false and falls back to a direct kfree(hdev).

Because hci_release_dev() is bypassed, the SRCU struct initialized early in hci_alloc_dev() is never cleaned up, resulting in a leak of percpu memory.

Fix the leak by explicitly calling cleanup_srcu_struct() in the fallback (unregistered) branch of bt_host_release() before freeing the device.

Reported-by [email protected]
Fixes 1d6123102e9f ("Bluetooth: hci_core: Fix use-after-free in vhci_flush()")
---
 net/bluetooth/hci_sysfs.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
net/bluetooth/hci_sysfs.c +4 -2
index cc7d4a8ed8ce24..b1886e517a78bc 100644
@@ -81,10 +81,12 @@ static void bt_host_release(struct device *dev)
 {
 	struct hci_dev *hdev = to_hci_dev(dev);
 
-	if (hci_dev_test_flag(hdev, HCI_UNREGISTER))
+	if (hci_dev_test_flag(hdev, HCI_UNREGISTER)) {
 		hci_release_dev(hdev);
-	else
+	} else {
+		cleanup_srcu_struct(&hdev->srcu);
 		kfree(hdev);
+	}
 	module_put(THIS_MODULE);
 }
 
Signature · 1 line
2.53.0
author maintainer
#232 lore raw

PATCH 218/522 Bluetooth: MGMT: Fix backward compatibility with userspace

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Luiz Augusto von Dentz <[email protected]>

[ Upstream commit 149324fc762c2a7acef9c26790566f81f475e51f ]

bluetoothd has a bug with makes it send extra bytes as part of MGMT_OP_ADD_EXT_ADV_DATA which are now being checked to be the exact the expected length, relax this so only when the expected length is greater than the data length to cause an error since that would result in accessing invalid memory, otherwise just ignore the extra bytes.

Fixes d3f7d17960ed ("Bluetooth: MGMT: validate Add Extended Advertising Data length")
---
 net/bluetooth/mgmt.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
net/bluetooth/mgmt.c +3 -2
index cc058c77d2e252..cd494f5ebb4dba 100644
@@ -9079,8 +9079,9 @@ static int add_ext_adv_data(struct sock *sk, struct hci_dev *hdev, void *data,
 
 	BT_DBG("%s", hdev->name);
 
-	expected_len = struct_size(cp, data, cp->adv_data_len + cp->scan_rsp_len);
-	if (expected_len != data_len)
+	expected_len = struct_size(cp, data, cp->adv_data_len +
+				   cp->scan_rsp_len);
+	if (expected_len > data_len)
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_DATA,
 				       MGMT_STATUS_INVALID_PARAMS);
 
Signature · 1 line
2.53.0
author maintainer
#233 lore raw

PATCH 219/522 ipv4: restrict IPOPT_SSRR and IPOPT_LSRR options

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Eric Dumazet <[email protected]>

[ Upstream commit d3915a1f5a4bc0ac911032903c3c6ab8df9fcc7c ]

This patch restricts setting Loose Source and Record Route (LSRR) and Strict Source and Record Route (SSRR) IP options to users with CAP_NET_RAW capability.

This prevents unprivileged applications from forcing packets to route through attacker-controlled nodes to leak TCP ISN and possibly other protocol information.

While LSRR and SSRR are commonly filtered in many network environments, they may still be supported and forwarded along some network paths.

RFC 7126 (Recommendations on Filtering of IPv4 Packets Containing IPv4 Options) recommend to drop these options in 4.3 and 4.4.

---
 net/ipv4/ip_options.c | 4 ++++
 1 file changed, 4 insertions(+)
net/ipv4/ip_options.c +4 -0
index d898e1523a453e..7a60bbf4bee3aa 100644
@@ -530,6 +530,10 @@ int ip_options_get(struct net *net, struct ip_options_rcu **optp,
 		kfree(opt);
 		return -EINVAL;
 	}
+	if (opt->opt.srr && !ns_capable(net->user_ns, CAP_NET_RAW)) {
+		kfree(opt);
+		return -EPERM;
+	}
 	kfree(*optp);
 	*optp = opt;
 	return 0;
Signature · 1 line
2.53.0
author maintainer
#234 lore raw

PATCH 220/522 ptp: vclock: Switch from RCU to SRCU

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Kurt Kanzenbach <[email protected]>

[ Upstream commit 672bd0519e27c357c43b7f8c0d653fce3817d06e ]

The usage of PTP vClocks leads immediately to the following issues with ptp4l with LOCKDEP and DEBUG_ATOMIC_SLEEP enabled: "BUG: sleeping function called from invalid context".

ptp_convert_timestamp() acquires a mutex_t within a RCU read section. This is illegal, because acquiring a mutex_t can result in voluntary scheduling request which is not allowed within a RCU read section.

Replace the RCU usage with SRCU where sleeping is allowed.

---
 drivers/ptp/ptp_vclock.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)
drivers/ptp/ptp_vclock.c +9 -5
index dcf752c9e04506..eb57338a32414a 100644
@@ -19,6 +19,8 @@ static DEFINE_SPINLOCK(vclock_hash_lock);
 
 static DEFINE_READ_MOSTLY_HASHTABLE(vclock_hash, 8);
 
+DEFINE_STATIC_SRCU(vclock_srcu);
+
 static void ptp_vclock_hash_add(struct ptp_vclock *vclock)
 {
 	spin_lock(&vclock_hash_lock);
@@ -37,7 +39,7 @@ static void ptp_vclock_hash_del(struct ptp_vclock *vclock)
 
 	spin_unlock(&vclock_hash_lock);
 
-	synchronize_rcu();
+	synchronize_srcu(&vclock_srcu);
 }
 
 static int ptp_vclock_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
@@ -269,14 +271,16 @@ ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index)
 {
 	unsigned int hash = vclock_index % HASH_SIZE(vclock_hash);
 	struct ptp_vclock *vclock;
-	u64 ns;
 	u64 vclock_ns = 0;
+	int srcu_idx;
+	u64 ns;
 
 	ns = ktime_to_ns(*hwtstamp);
 
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&vclock_srcu);
 
-	hlist_for_each_entry_rcu(vclock, &vclock_hash[hash], vclock_hash_node) {
+	hlist_for_each_entry_srcu(vclock, &vclock_hash[hash], vclock_hash_node,
+				  srcu_read_lock_held(&vclock_srcu)) {
 		if (vclock->clock->index != vclock_index)
 			continue;
 
@@ -287,7 +291,7 @@ ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index)
 		break;
 	}
 
-	rcu_read_unlock();
+	srcu_read_unlock(&vclock_srcu, srcu_idx);
 
 	return ns_to_ktime(vclock_ns);
 }
Signature · 1 line
2.53.0
author maintainer
#235 lore raw

PATCH 221/522 octeontx2-af: npc: Fix CPT channel mask in npc_install_flow

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Nithin Dabilpuram <[email protected]>

[ Upstream commit 1d31eb27e570daa04f5373345f9ac98c95863be9 ]

Use the CPT-aware NIX channel mask in the npc_install_flow path so that when the host PF installs steering rules in kernel for a VF used from userspace (e.g. DPDK), MCAM entries see the same channel mask semantics as other RX paths.

Fixes 56bcef528bd8 ("octeontx2-af: Use npc_install_flow API for promisc and broadcast entries")
Cc Naveen Mamindlapalli <[email protected]>
---
 .../net/ethernet/marvell/octeontx2/af/rvu.h   |  1 +
 .../ethernet/marvell/octeontx2/af/rvu_npc.c   | 32 +++++++++----------
 .../marvell/octeontx2/af/rvu_npc_fs.c         |  2 +-
 3 files changed, 18 insertions(+), 17 deletions(-)
drivers/net/ethernet/marvell/octeontx2/af/rvu.h +1 -0
index fc0f3398a556bb..86ef67745ebdf7 100644
@@ -895,6 +895,7 @@ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int lf,
 			int slot);
 int rvu_cpt_ctx_flush(struct rvu *rvu, u16 pcifunc);
 int rvu_cpt_init(struct rvu *rvu);
+u32 rvu_get_cpt_chan_mask(struct rvu *rvu);
 
 #define NDC_AF_BANK_MASK       GENMASK_ULL(7, 0)
 #define NDC_AF_BANK_LINE_MASK  GENMASK_ULL(31, 16)
drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +16 -16
index 9b8a6046e6dff0..65ad7476e60983 100644
@@ -609,6 +609,19 @@ static u64 npc_get_mcam_action(struct rvu *rvu, struct npc_mcam *mcam,
 			  NPC_AF_MCAMEX_BANKX_ACTION(index, bank));
 }
 
+u32 rvu_get_cpt_chan_mask(struct rvu *rvu)
+{
+	/* For cn10k the upper two bits of the channel number are
+	 * cpt channel number. with masking out these bits in the
+	 * mcam entry, same entry used for NIX will allow packets
+	 * received from cpt for parsing.
+	 */
+	if (!is_rvu_otx2(rvu))
+		return NIX_CHAN_CPT_X2P_MASK;
+	else
+		return 0xFFFu;
+}
+
 void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 				 int nixlf, u64 chan, u8 *mac_addr)
 {
@@ -652,7 +665,7 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 	eth_broadcast_addr((u8 *)&req.mask.dmac);
 	req.features = BIT_ULL(NPC_DMAC);
 	req.channel = chan;
-	req.chan_mask = 0xFFFU;
+	req.chan_mask = rvu_get_cpt_chan_mask(rvu);
 	req.intf = pfvf->nix_rx_intf;
 	req.op = action.op;
 	req.hdr.pcifunc = 0; /* AF is requester */
@@ -722,11 +735,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 	 * mcam entry, same entry used for NIX will allow packets
 	 * received from cpt for parsing.
 	 */
-	if (!is_rvu_otx2(rvu)) {
-		req.chan_mask = NIX_CHAN_CPT_X2P_MASK;
-	} else {
-		req.chan_mask = 0xFFFU;
-	}
+	req.chan_mask = rvu_get_cpt_chan_mask(rvu);
 
 	if (chan_cnt > 1) {
 		if (!is_power_of_2(chan_cnt)) {
@@ -915,16 +924,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf,
 	ether_addr_copy(req.mask.dmac, mac_addr);
 	req.features = BIT_ULL(NPC_DMAC);
 
-	/* For cn10k the upper two bits of the channel number are
-	 * cpt channel number. with masking out these bits in the
-	 * mcam entry, same entry used for NIX will allow packets
-	 * received from cpt for parsing.
-	 */
-	if (!is_rvu_otx2(rvu))
-		req.chan_mask = NIX_CHAN_CPT_X2P_MASK;
-	else
-		req.chan_mask = 0xFFFU;
-
+	req.chan_mask = rvu_get_cpt_chan_mask(rvu);
 	req.channel = chan;
 	req.intf = pfvf->nix_rx_intf;
 	req.entry = index;
drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +1 -1
index 80d6aa3f14c11f..b79b28192a5764 100644
@@ -1320,7 +1320,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
 
 	/* ignore chan_mask in case pf func is not AF, revisit later */
 	if (!is_pffunc_af(req->hdr.pcifunc))
-		req->chan_mask = 0xFFF;
+		req->chan_mask = rvu_get_cpt_chan_mask(rvu);
 
 	err = npc_check_unsupported_flows(rvu, req->features, req->intf);
 	if (err)
Signature · 1 line
2.53.0
author maintainer
#236 lore raw

PATCH 222/522 vxlan: vnifilter: send notification on VNI add

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Andy Roulin <[email protected]>

[ Upstream commit aa6ca1c5c338907817374b59f7551fd855a88754 ]

When a new VNI is added to a vxlan device with vnifilter enabled, no RTM_NEWTUNNEL notification is sent to userspace. This means 'bridge monitor vni' never shows VNI add events, even though VNI delete events are reported correctly.

The bug is in vxlan_vni_add(), where the notification is guarded by 'if (changed)'. The 'changed' flag is set by vxlan_vni_update_group() only when the multicast group or remote IP is modified, but for a new VNI added without a group (e.g. in L3 VxLAN interface scenarios), the function returns early without setting changed=true. Since this is a new VNI, the notification should be sent unconditionally.

The notification is not guarded by the return value of vxlan_vni_update_group() because, at this point, the VNI has already been inserted into the hash table and list with no rollback on error. The VNI will be visible in 'bridge vni show' regardless, so userspace should be informed. This is consistent with vxlan_vni_del() which also notifies unconditionally.

The 'if (changed)' guard remains correct in vxlan_vni_update(), which handles the case where a VNI already exists and is being re-added -- there, we only want to notify if the group/remote actually changed.

Reproducer:

 # ip link add vxlan100 type vxlan dstport 4789 local 10.0.0.1 \
      nolearning external vnifilter
 # ip link set vxlan100 up
 # bridge monitor vni &
 # bridge vni add vni 1000 dev vxlan100    # no notification
 # bridge vni delete vni 1000 dev vxlan100 # notification received
Fixes f9c4bb0b245c ("vxlan: vni filtering support on collect metadata device")
---
 drivers/net/vxlan/vxlan_vnifilter.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/net/vxlan/vxlan_vnifilter.c +1 -2
index c6d4fae958ca80..ca866740a955d0 100644
@@ -769,8 +769,7 @@ static int vxlan_vni_add(struct vxlan_dev *vxlan,
 	err = vxlan_vni_update_group(vxlan, vninode, group, true, &changed,
 				     extack);
 
-	if (changed)
-		vxlan_vnifilter_notify(vxlan, vninode, RTM_NEWTUNNEL);
+	vxlan_vnifilter_notify(vxlan, vninode, RTM_NEWTUNNEL);
 
 	return err;
 }
Signature · 1 line
2.53.0
author maintainer
#237 lore raw

PATCH 223/522 vxlan: vnifilter: fix spurious notification on VNI update

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Andy Roulin <[email protected]>

[ Upstream commit 84683b5b60c7274e2c8f7f413d39d78d3db5540f ]

When a VNI is re-added with the same attributes (e.g. same group or no group), vxlan_vni_update() sends a spurious RTM_NEWTUNNEL notification even though nothing changed.

The bug is that 'if (changed)' tests whether the pointer is non-NULL, not the bool value it points to. Since every caller passes a valid pointer, the condition is always true and the notification fires unconditionally.

Fix by dereferencing the pointer: 'if (*changed)'.

Reproducer:

 # ip link add vxlan100 type vxlan dstport 4789 local 10.0.0.1 \
      nolearning external vnifilter
 # ip link set vxlan100 up
 # bridge monitor vni &
 # bridge vni add vni 1000 dev vxlan100
 # bridge vni add vni 1000 dev vxlan100  # spurious notification
Fixes f9c4bb0b245c ("vxlan: vni filtering support on collect metadata device")
---
 drivers/net/vxlan/vxlan_vnifilter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/vxlan/vxlan_vnifilter.c +1 -1
index ca866740a955d0..abf96d60eb30d5 100644
@@ -671,7 +671,7 @@ static int vxlan_vni_update(struct vxlan_dev *vxlan,
 	if (ret)
 		return ret;
 
-	if (changed)
+	if (*changed)
 		vxlan_vnifilter_notify(vxlan, vninode, RTM_NEWTUNNEL);
 
 	return 0;
Signature · 1 line
2.53.0
author maintainer
#238 lore raw

PATCH 224/522 ieee802154: 6lowpan: only accept IPv6 packets in lowpan_xmit()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 3a5f3f7aff18bcc36a57839cf50cf0cc8de707f3 ]

The aoe driver (or similar) generates a non-IPv6 packet (e.g., ETH_P_AOE) and queues it for transmission via dev_queue_xmit() on a 6LoWPAN interface (configured by the user or test case).

Since the packet is not IPv6, the 6LoWPAN header_ops->create function (lowpan_header_create or header_create) returns early without initializing the lowpan_addr_info structure in the skb headroom.

In the transmit function (lowpan_xmit), the driver calls lowpan_header (or setup_header) which unconditionally copies and uses the lowpan_addr_info from the headroom, which contains uninitialized data.

Fix this by dropping non IPv6 packets.

A similar fix is needed in net/bluetooth/6lowpan.c bt_xmit().

---
 net/ieee802154/6lowpan/tx.c | 5 +++++
 1 file changed, 5 insertions(+)
net/ieee802154/6lowpan/tx.c +5 -0
index 0c07662b44c0ca..4df76ff50699ed 100644
@@ -255,6 +255,11 @@ netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev)
 
 	pr_debug("package xmit\n");
 
+	if (skb->protocol != htons(ETH_P_IPV6)) {
+		kfree_skb(skb);
+		return NET_XMIT_DROP;
+	}
+
 	WARN_ON_ONCE(skb->len > IPV6_MIN_MTU);
 
 	/* We must take a copy of the skb before we modify/replace the ipv6
Signature · 1 line
2.53.0
author maintainer
#239 lore raw

PATCH 225/522 net/802/mrp: fix vector attribute parsing in mrp_pdu_parse_vecattr

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Yizhou Zhao <[email protected]>

[ Upstream commit 7561c7fbc694308da73300f036719e63e42bf0b4 ]

In mrp_pdu_parse_vecattr(), vector attribute events are encoded three per byte and valen tracks the number of events left to process.

The parser decrements valen after processing the first and second events from each event byte, but not after processing the third one. When valen is exactly a multiple of three, the loop continues after the last valid event and consumes the next byte as a new event byte, applying a spurious event to the MRP applicant state.

Additionally, when valen is zero the parser unconditionally consumes attrlen bytes as FirstValue and advances the offset, even though per IEEE 802.1ak a VectorAttribute with only a LeaveAllEvent has valen of zero and no FirstValue or Vector fields. This corrupts the offset for subsequent PDU parsing.

Also, when valen exceeds three the loop crosses byte boundaries but the attribute value is not incremented between the last event of one byte and the first event of the next. This causes the first event of the next byte to use the same attribute value as the third event rather than the next consecutive value.

Decrement valen after processing the third event, skip FirstValue consumption when valen is zero, and increment the attribute value at the end of each loop iteration.

---
 net/802/mrp.c | 9 +++++++++
 1 file changed, 9 insertions(+)
net/802/mrp.c +9 -0
index 6c927d4b35f06e..dea0fd28cbed88 100644
@@ -702,6 +702,12 @@ static int mrp_pdu_parse_vecattr(struct mrp_applicant *app,
 	valen = be16_to_cpu(get_unaligned(&mrp_cb(skb)->vah->lenflags) &
 			    MRP_VECATTR_HDR_LEN_MASK);
 
+	/* If valen is 0, only a LeaveAllEvent is present; FirstValue and
+	 * Vector fields are absent per IEEE 802.1ak.
+	 */
+	if (valen == 0)
+		return 0;
+
 	/* The VectorAttribute structure in a PDU carries event information
 	 * about one or more attributes having consecutive values. Only the
 	 * value for the first attribute is contained in the structure. So
@@ -752,6 +758,9 @@ static int mrp_pdu_parse_vecattr(struct mrp_applicant *app,
 		vaevents %= __MRP_VECATTR_EVENT_MAX;
 		vaevent = vaevents;
 		mrp_pdu_parse_vecattr_event(app, skb, vaevent);
+		valen--;
+		mrp_attrvalue_inc(mrp_cb(skb)->attrvalue,
+				  mrp_cb(skb)->mh->attrlen);
 	}
 	return 0;
 }
Signature · 1 line
2.53.0
author maintainer
#240 lore raw

PATCH 226/522 sctp: purge outqueue on stale COOKIE-ECHO handling

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Xin Long <[email protected]>

[ Upstream commit e374b22e9b07b72a25909621464ff74096151bfb ]

sctp_stream_update() is only invoked when the association is moved into COOKIE_WAIT during association setup/reconfiguration. In this path, the outbound stream scheduler state (stream->out_curr) is expected to be clean, since no user data should have been transmitted yet unless the state machine has already partially progressed.

However, a corner case exists in sctp_sf_do_5_2_6_stale(): when a Stale Cookie ERROR is received, the association is rolled back from COOKIE_ECHOED to COOKIE_WAIT. In this scenario, user data may already have been queued and even bundled with the COOKIE-ECHO chunk.

During the rollback, sctp_stream_update() frees the old stream table and installs a new one, but it does not invalidate stream->out_curr. As a result, out_curr may still point to a freed sctp_stream_out entry from the previous stream state.

Later, SCTP scheduler dequeue paths (FCFS, RR, PRIO, etc.) rely on stream->out_curr->ext, which can lead to use-after-free once the old stream state has been released via sctp_stream_free().

This results in crashes such as (reported by Yuqi):

  BUG: KASAN: slab-use-after-free in sctp_sched_fcfs_dequeue+0x13a/0x140
  Read of size 8 at addr ff1100004d4d3208 by task mini_poc/9312
  CPU: 1 UID: 1001 PID: 9312 Comm: mini_poc Not tainted
     7.1.0-rc1-00305-gbd3a4795d574 #5 PREEMPT(full)
   sctp_sched_fcfs_dequeue+0x13a/0x140
   sctp_outq_flush+0x1603/0x33e0
   sctp_do_sm+0x31c9/0x5d30
   sctp_assoc_bh_rcv+0x392/0x6f0
   sctp_inq_push+0x1db/0x270
   sctp_rcv+0x138d/0x3c10

Fix this by fully purging the association outqueue when handling the Stale Cookie case. This ensures all pending transmit and retransmit state is dropped, and any scheduler cached pointers are invalidated, making it safe to rebuild stream state during COOKIE_WAIT restart.

Updating only stream->out_curr would be insufficient, since queued and retransmittable data would still reference the old stream state and trigger later use-after-free in dequeue paths.

---
 net/sctp/sm_statefuns.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)
net/sctp/sm_statefuns.c +1 -5
index 1685f73602d5e3..f5dc7822d220f2 100644
@@ -2599,11 +2599,7 @@ static enum sctp_disposition sctp_sf_do_5_2_6_stale(
 	 */
 	sctp_add_cmd_sf(commands, SCTP_CMD_DEL_NON_PRIMARY, SCTP_NULL());
 
-	/* If we've sent any data bundled with COOKIE-ECHO we will need to
-	 * resend
-	 */
-	sctp_add_cmd_sf(commands, SCTP_CMD_T1_RETRAN,
-			SCTP_TRANSPORT(asoc->peer.primary_path));
+	sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_OUTQUEUE, SCTP_NULL());
 
 	/* Cast away the const modifier, as we want to just
 	 * rerun it through as a sideffect.
Signature · 1 line
2.53.0
author maintainer
#241 lore raw

PATCH 227/522 ipmi: Fix rcu_read_unlock to srcu_read_unlock in handle_read_event_rsp

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Rui Qi <[email protected]>

Fix a bug where rcu_read_unlock() was used instead of srcu_read_unlock() in handle_read_event_rsp() when ipmi_alloc_recv_msg() fails.

This mismatch leads to an SRCU read-side critical section imbalance: the entry uses srcu_read_lock(&intf->users_srcu) but the error path incorrectly calls rcu_read_unlock(), which is a no-op for SRCU and leaves the SRCU lock held.

The offending code was restructured in mainline by commit 3be997d5a64a ("ipmi:msghandler: Remove srcu from the ipmi user structure"), which replaced the SRCU locking with a mutex in this function, effectively eliminating the mismatch. However, that commit is part of a larger SRCU removal series that is not suitable for stable backport. This minimal fix addresses the SRCU imbalance for 6.12 and earlier stable branches that still carry the original locking scheme.

Fixes e86ee2d44b44 ("ipmi: Rework locking and shutdown for hot remove")
---
 drivers/char/ipmi/ipmi_msghandler.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/char/ipmi/ipmi_msghandler.c +1 -1
index 8bc8da7f70bb8e..62d39ea9f00836 100644
@@ -4396,7 +4396,7 @@ static int handle_read_event_rsp(struct ipmi_smi *intf,
 
 		recv_msg = ipmi_alloc_recv_msg(user);
 		if (IS_ERR(recv_msg)) {
-			rcu_read_unlock();
+			srcu_read_unlock(&intf->users_srcu, index);
 			list_for_each_entry_safe(recv_msg, recv_msg2, &msgs,
 						 link) {
 				list_del(&recv_msg->link);
Signature · 1 line
2.53.0
author maintainer
#242 lore raw

PATCH 228/522 signal: clear JOBCTL_PENDING_MASK for caller in zap_other_threads()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Aleksandr Nogikh <[email protected]>

[ Upstream commit 90918794a4e2c3b440f8fcf3847765a8b1d81b25 ]

When a multi-threaded process receives a stop signal (e.g., SIGSTOP), do_signal_stop() sets JOBCTL_STOP_PENDING and JOBCTL_STOP_CONSUME on all threads and sets signal->group_stop_count to the number of threads. If one of the threads concurrently calls execve(), de_thread() invokes zap_other_threads() to kill all other threads. zap_other_threads() aborts the pending group stop by resetting signal->group_stop_count to 0 and clears the JOBCTL_PENDING_MASK for all other threads. However, it fails to clear the job control flags for the calling thread.

When execve() completes, the calling thread returns to user mode and checks for pending signals. Seeing the stale JOBCTL_STOP_PENDING flag, it calls do_signal_stop(), which invokes task_participate_group_stop(). Since JOBCTL_STOP_CONSUME is still set, it attempts to decrement the already-zero signal->group_stop_count, triggering a warning:

sig->group_stop_count == 0

WARNING: CPU: 1 PID: 6475 at kernel/signal.c:373
task_participate_group_stop+0x215/0x2d0
Call Trace:
 <TASK>
 do_signal_stop+0x3be/0x5c0 kernel/signal.c:2619
 get_signal+0xa8c/0x1330 kernel/signal.c:2884
 arch_do_signal_or_restart+0xbc/0x840 arch/x86/kernel/signal.c:337
 exit_to_user_mode_loop+0x8c/0x4d0 kernel/entry/common.c:98
 do_syscall_64+0x33e/0xf80 arch/x86/entry/syscall_64.c:100
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
 </TASK>

Fix this race condition by clearing the JOBCTL_PENDING_MASK for the calling thread in zap_other_threads(), ensuring it does not retain any stale job control state after the thread group is destroyed. This aligns with other functions that tear down a thread group and abort group stops, such as zap_process() and complete_signal(), which correctly clear these flags for all threads including the current one.

Fixes 39efa3ef3a37 ("signal: Use GROUP_STOP_PENDING to stop once for a single group stop")
Assisted-by Gemini:gemini-3.1-pro-preview Gemini:gemini-3-flash-preview syzbot
Reported-by [email protected]
---
 kernel/signal.c | 1 +
 1 file changed, 1 insertion(+)
kernel/signal.c +1 -0
index 723c84d162ddba..98dbe713829ec3 100644
@@ -1371,6 +1371,7 @@ int zap_other_threads(struct task_struct *p)
 	int count = 0;
 
 	p->signal->group_stop_count = 0;
+	task_clear_jobctl_pending(p, JOBCTL_PENDING_MASK);
 
 	while_each_thread(p, t) {
 		task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK);
Signature · 1 line
2.53.0
author maintainer
#243 lore raw

PATCH 229/522 time: Fix off-by-one in settimeofday() usec validation

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Naveen Kumar Chaudhary <[email protected]>

[ Upstream commit ce4abda5e12622f33450159e76c8f56d28d7f03d ]

The validation check uses '>' instead of '>=' when comparing tv_usec against USEC_PER_SEC, allowing the value 1000000 through. After conversion to nanoseconds (*= 1000), this produces tv_nsec == NSEC_PER_SEC, violating the timespec invariant that tv_nsec must be less than NSEC_PER_SEC.

Use '>=' to reject tv_usec values that are not in the valid range of 0 to 999999.

---
 kernel/time/time.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/time/time.c +1 -1
index 170f1f8a0046ce..0e0b54fb34905e 100644
@@ -207,7 +207,7 @@ SYSCALL_DEFINE2(settimeofday, struct __kernel_old_timeval __user *, tv,
 		    get_user(new_ts.tv_nsec, &tv->tv_usec))
 			return -EFAULT;
 
-		if (new_ts.tv_nsec > USEC_PER_SEC || new_ts.tv_nsec < 0)
+		if (new_ts.tv_nsec >= USEC_PER_SEC || new_ts.tv_nsec < 0)
 			return -EINVAL;
 
 		new_ts.tv_nsec *= NSEC_PER_USEC;
Signature · 1 line
2.53.0
author maintainer
#244 lore raw

PATCH 230/522 ALSA: PCM: Fix wait queue list corruption in snd_pcm_drain() on linked streams

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Ji'an Zhou <[email protected]>

[ Upstream commit 88fe2e3658726cb21ff2dcf9770bf672f9b9d31b ]

snd_pcm_drain() uses init_waitqueue_entry which does not clear entry.prev/next, and add_wait_queue with a conditional remove_wait_queue that is skipped when to_check is no longer in the group after concurrent UNLINK. The orphaned wait entry remains on the unlinked substream sleep queue. On the next drain iteration, add_wait_queue adds the entry to a new queue while still linked on the old one, corrupting both lists. A subsequent wake_up dereferences NULL at the func pointer (mapped from the spinlock at offset 0 of the misinterpreted wait_queue_head_t), causing a kernel panic.

Replace init_waitqueue_entry/add_wait_queue/conditional remove_wait_queue with init_wait_entry/prepare_to_wait/ finish_wait. init_wait_entry clears prev/next via INIT_LIST_HEAD on each iteration and sets autoremove_wake_function which auto-removes the entry on wake-up. finish_wait safely handles both the already-removed and still-queued cases.

Fixes 9b1dbd69ba6f ("ALSA: pcm: fix use-after-free on linked stream runtime in snd_pcm_drain")
---
 sound/core/pcm_native.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)
sound/core/pcm_native.c +3 -4
index 7be5f25612b954..2ed9abb911a7aa 100644
@@ -2178,9 +2178,8 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream,
 		drain_no_period_wakeup = to_check->no_period_wakeup;
 		drain_rate = to_check->rate;
 		drain_bufsz = to_check->buffer_size;
-		init_waitqueue_entry(&wait, current);
-		set_current_state(TASK_INTERRUPTIBLE);
-		add_wait_queue(&to_check->sleep, &wait);
+		init_wait_entry(&wait, 0);
+		prepare_to_wait(&to_check->sleep, &wait, TASK_INTERRUPTIBLE);
 		snd_pcm_stream_unlock_irq(substream);
 		if (drain_no_period_wakeup)
 			tout = MAX_SCHEDULE_TIMEOUT;
@@ -2198,7 +2197,7 @@ static int snd_pcm_drain(struct snd_pcm_substream *substream,
 		group = snd_pcm_stream_group_ref(substream);
 		snd_pcm_group_for_each_entry(s, substream) {
 			if (s->runtime == to_check) {
-				remove_wait_queue(&to_check->sleep, &wait);
+				finish_wait(&to_check->sleep, &wait);
 				break;
 			}
 		}
Signature · 1 line
2.53.0
author maintainer
#245 lore raw

PATCH 231/522 fs/ntfs3: Return error for inconsistent extended attributes

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Edward Lo <[email protected]>

[ Upstream commit c9db0ff04649aa0b45f497183c957fe260f229f6 ]

ntfs_read_ea is called when we want to read extended attributes. There are some sanity checks for the validity of the EAs. However, it fails to return a proper error code for the inconsistent attributes, which might lead to unpredicted memory accesses after return.

[  138.916927] BUG: KASAN: use-after-free in ntfs_set_ea+0x453/0xbf0
[  138.923876] Write of size 4 at addr ffff88800205cfac by task poc/199
[  138.931132]
[  138.933016] CPU: 0 PID: 199 Comm: poc Not tainted 6.2.0-rc1+ #4
[  138.938070] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
[  138.947327] Call Trace:
[  138.949557]  <TASK>
[  138.951539]  dump_stack_lvl+0x4d/0x67
[  138.956834]  print_report+0x16f/0x4a6
[  138.960798]  ? ntfs_set_ea+0x453/0xbf0
[  138.964437]  ? kasan_complete_mode_report_info+0x7d/0x200
[  138.969793]  ? ntfs_set_ea+0x453/0xbf0
[  138.973523]  kasan_report+0xb8/0x140
[  138.976740]  ? ntfs_set_ea+0x453/0xbf0
[  138.980578]  __asan_store4+0x76/0xa0
[  138.984669]  ntfs_set_ea+0x453/0xbf0
[  138.988115]  ? __pfx_ntfs_set_ea+0x10/0x10
[  138.993390]  ? kernel_text_address+0xd3/0xe0
[  138.998270]  ? __kernel_text_address+0x16/0x50
[  139.002121]  ? unwind_get_return_address+0x3e/0x60
[  139.005659]  ? __pfx_stack_trace_consume_entry+0x10/0x10
[  139.010177]  ? arch_stack_walk+0xa2/0x100
[  139.013657]  ? filter_irq_stacks+0x27/0x80
[  139.017018]  ntfs_setxattr+0x405/0x440
[  139.022151]  ? __pfx_ntfs_setxattr+0x10/0x10
[  139.026569]  ? kvmalloc_node+0x2d/0x120
[  139.030329]  ? kasan_save_stack+0x41/0x60
[  139.033883]  ? kasan_save_stack+0x2a/0x60
[  139.037338]  ? kasan_set_track+0x29/0x40
[  139.040163]  ? kasan_save_alloc_info+0x1f/0x30
[  139.043588]  ? __kasan_kmalloc+0x8b/0xa0
[  139.047255]  ? __kmalloc_node+0x68/0x150
[  139.051264]  ? kvmalloc_node+0x2d/0x120
[  139.055301]  ? vmemdup_user+0x2b/0xa0
[  139.058584]  __vfs_setxattr+0x121/0x170
[  139.062617]  ? __pfx___vfs_setxattr+0x10/0x10
[  139.066282]  __vfs_setxattr_noperm+0x97/0x300
[  139.070061]  __vfs_setxattr_locked+0x145/0x170
[  139.073580]  vfs_setxattr+0x137/0x2a0
[  139.076641]  ? __pfx_vfs_setxattr+0x10/0x10
[  139.080223]  ? __kasan_check_write+0x18/0x20
[  139.084234]  do_setxattr+0xce/0x150
[  139.087768]  setxattr+0x126/0x140
[  139.091250]  ? __pfx_setxattr+0x10/0x10
[  139.094948]  ? __virt_addr_valid+0xcb/0x140
[  139.097838]  ? __call_rcu_common.constprop.0+0x1c7/0x330
[  139.102688]  ? debug_smp_processor_id+0x1b/0x30
[  139.105985]  ? kasan_quarantine_put+0x5b/0x190
[  139.109980]  ? putname+0x84/0xa0
[  139.113886]  ? __kasan_slab_free+0x11e/0x1b0
[  139.117961]  ? putname+0x84/0xa0
[  139.121316]  ? preempt_count_sub+0x1c/0xd0
[  139.124427]  ? __mnt_want_write+0xae/0x100
[  139.127836]  ? mnt_want_write+0x8f/0x150
[  139.130954]  path_setxattr+0x164/0x180
[  139.133998]  ? __pfx_path_setxattr+0x10/0x10
[  139.137853]  ? __pfx_ksys_pwrite64+0x10/0x10
[  139.141299]  ? debug_smp_processor_id+0x1b/0x30
[  139.145714]  ? fpregs_assert_state_consistent+0x6b/0x80
[  139.150796]  __x64_sys_setxattr+0x71/0x90
[  139.155407]  do_syscall_64+0x3f/0x90
[  139.159035]  entry_SYSCALL_64_after_hwframe+0x72/0xdc
[  139.163843] RIP: 0033:0x7f108cae4469
[  139.166481] Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 088
[  139.183764] RSP: 002b:00007fff87588388 EFLAGS: 00000286 ORIG_RAX: 00000000000000bc
[  139.190657] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f108cae4469
[  139.196586] RDX: 00007fff875883b0 RSI: 00007fff875883d1 RDI: 00007fff875883b6
[  139.201716] RBP: 00007fff8758c530 R08: 0000000000000001 R09: 00007fff8758c618
[  139.207940] R10: 0000000000000006 R11: 0000000000000286 R12: 00000000004004c0
[  139.214007] R13: 00007fff8758c610 R14: 0000000000000000 R15: 0000000000000000
---
 fs/ntfs3/xattr.c | 1 +
 1 file changed, 1 insertion(+)
fs/ntfs3/xattr.c +1 -0
index 2e4eea854bda59..7dc650b0b832c2 100644
@@ -140,6 +140,7 @@ static int ntfs_read_ea(struct ntfs_inode *ni, struct EA_FULL **ea,
 
 	memset(Add2Ptr(ea_p, size), 0, add_bytes);
 
+	err = -EINVAL;
 	/* Check all attributes for consistency. */
 	for (off = 0; off < size; off += ea_size) {
 		const struct EA_FULL *ef = Add2Ptr(ea_p, off);
Signature · 1 line
2.53.0
author maintainer
#246 lore raw

PATCH 232/522 usb: gadget: f_ncm: Fix net_device lifecycle with device_move

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Kuen-Han Tsai <[email protected]>

[ Upstream commit ec35c1969650e7cb6c8a91020e568ed46e3551b0 ]

The network device outlived its parent gadget device during disconnection, resulting in dangling sysfs links and null pointer dereference problems.

A prior attempt to solve this by removing SET_NETDEV_DEV entirely [1] was reverted due to power management ordering concerns and a NO-CARRIER regression.

A subsequent attempt to defer net_device allocation to bind [2] broke 1:1 mapping between function instance and network device, making it impossible for configfs to report the resolved interface name. This results in a regression where the DHCP server fails on pmOS.

Use device_move to reparent the net_device between the gadget device and /sys/devices/virtual/ across bind/unbind cycles. This preserves the network interface across USB reconnection, allowing the DHCP server to retain their binding.

Introduce gether_attach_gadget()/gether_detach_gadget() helpers and use __free(detach_gadget) macro to undo attachment on bind failure. The bind_count ensures device_move executes only on the first bind.

[1] https://lore.kernel.org/lkml/[email protected]/
[2] https://lore.kernel.org/linux-usb/[email protected]/

Fixes 40d133d7f542 ("usb: gadget: f_ncm: convert to new function interface with backward compatibility")
Cc stable <[email protected]>
[ Use no_free_ptr() since retain_and_null_ptr() is unavailable in Linux 6.1. ]
---
 drivers/usb/gadget/function/f_ncm.c   | 35 ++++++++++++++++++---------
 drivers/usb/gadget/function/u_ether.c | 22 +++++++++++++++++
 drivers/usb/gadget/function/u_ether.h | 26 ++++++++++++++++++++
 drivers/usb/gadget/function/u_ncm.h   |  2 +-
 4 files changed, 73 insertions(+), 12 deletions(-)
drivers/usb/gadget/function/f_ncm.c +24 -11
index addd016ffbb3f7..5e240cafbe9ee8 100644
@@ -1440,6 +1440,7 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	struct f_ncm_opts	*ncm_opts;
 
 	struct usb_os_desc_table	*os_desc_table __free(kfree) = NULL;
+	struct net_device		*net __free(detach_gadget) = NULL;
 	struct usb_request		*request __free(free_usb_request) = NULL;
 
 	if (!can_support_ecm(cdev->gadget))
@@ -1453,16 +1454,18 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 			return -ENOMEM;
 	}
 
-	mutex_lock(&ncm_opts->lock);
-	gether_set_gadget(ncm_opts->net, cdev->gadget);
-	if (!ncm_opts->bound)
-		status = gether_register_netdev(ncm_opts->net);
-	mutex_unlock(&ncm_opts->lock);
-
-	if (status)
-		return status;
-
-	ncm_opts->bound = true;
+	scoped_guard(mutex, &ncm_opts->lock)
+		if (ncm_opts->bind_count == 0) {
+			if (!device_is_registered(&ncm_opts->net->dev)) {
+				gether_set_gadget(ncm_opts->net, cdev->gadget);
+				status = gether_register_netdev(ncm_opts->net);
+			} else
+				status = gether_attach_gadget(ncm_opts->net, cdev->gadget);
+
+			if (status)
+				return status;
+			net = ncm_opts->net;
+		}
 
 	ncm_string_defs[1].s = ncm->ethaddr;
 
@@ -1562,6 +1565,9 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
 	}
         ncm->notify_req = no_free_ptr(request);
 
+	ncm_opts->bind_count++;
+	no_free_ptr(net);
+
 	DBG(cdev, "CDC Network: %s speed IN/%s OUT/%s NOTIFY/%s\n",
 			gadget_is_superspeed(c->cdev->gadget) ? "super" :
 			gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full",
@@ -1610,7 +1616,7 @@ static void ncm_free_inst(struct usb_function_instance *f)
 	struct f_ncm_opts *opts;
 
 	opts = container_of(f, struct f_ncm_opts, func_inst);
-	if (opts->bound)
+	if (device_is_registered(&opts->net->dev))
 		gether_cleanup(netdev_priv(opts->net));
 	else
 		free_netdev(opts->net);
@@ -1672,9 +1678,12 @@ static void ncm_free(struct usb_function *f)
 static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
 {
 	struct f_ncm *ncm = func_to_ncm(f);
+	struct f_ncm_opts *ncm_opts;
 
 	DBG(c->cdev, "ncm unbind\n");
 
+	ncm_opts = container_of(f->fi, struct f_ncm_opts, func_inst);
+
 	hrtimer_cancel(&ncm->task_timer);
 
 	kfree(f->os_desc_table);
@@ -1690,6 +1699,10 @@ static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
 
 	kfree(ncm->notify_req->buf);
 	usb_ep_free_request(ncm->notify, ncm->notify_req);
+
+	ncm_opts->bind_count--;
+	if (ncm_opts->bind_count == 0)
+		gether_detach_gadget(ncm_opts->net);
 }
 
 static struct usb_function *ncm_alloc(struct usb_function_instance *fi)
drivers/usb/gadget/function/u_ether.c +22 -0
index e84178bffe7803..e972de236be5e2 100644
@@ -910,6 +910,28 @@ void gether_set_gadget(struct net_device *net, struct usb_gadget *g)
 }
 EXPORT_SYMBOL_GPL(gether_set_gadget);
 
+int gether_attach_gadget(struct net_device *net, struct usb_gadget *g)
+{
+	int ret;
+
+	ret = device_move(&net->dev, &g->dev, DPM_ORDER_DEV_AFTER_PARENT);
+	if (ret)
+		return ret;
+
+	gether_set_gadget(net, g);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gether_attach_gadget);
+
+void gether_detach_gadget(struct net_device *net)
+{
+	struct eth_dev *dev = netdev_priv(net);
+
+	device_move(&net->dev, NULL, DPM_ORDER_NONE);
+	dev->gadget = NULL;
+}
+EXPORT_SYMBOL_GPL(gether_detach_gadget);
+
 int gether_set_dev_addr(struct net_device *net, const char *dev_addr)
 {
 	struct eth_dev *dev;
drivers/usb/gadget/function/u_ether.h +26 -0
index 40144546d1b07f..3e12d60053c136 100644
@@ -149,6 +149,32 @@ static inline struct net_device *gether_setup_default(void)
  */
 void gether_set_gadget(struct net_device *net, struct usb_gadget *g);
 
+/**
+ * gether_attach_gadget - Reparent net_device to the gadget device.
+ * @net: The network device to reparent.
+ * @g: The target USB gadget device to parent to.
+ *
+ * This function moves the network device to be a child of the USB gadget
+ * device in the device hierarchy. This is typically done when the function
+ * is bound to a configuration.
+ *
+ * Returns 0 on success, or a negative error code on failure.
+ */
+int gether_attach_gadget(struct net_device *net, struct usb_gadget *g);
+
+/**
+ * gether_detach_gadget - Detach net_device from its gadget parent.
+ * @net: The network device to detach.
+ *
+ * This function moves the network device to be a child of the virtual
+ * devices parent, effectively detaching it from the USB gadget device
+ * hierarchy. This is typically done when the function is unbound
+ * from a configuration but the instance is not yet freed.
+ */
+void gether_detach_gadget(struct net_device *net);
+
+DEFINE_FREE(detach_gadget, struct net_device *, if (_T) gether_detach_gadget(_T))
+
 /**
  * gether_set_dev_addr - initialize an ethernet-over-usb link with eth address
  * @net: device representing this link
drivers/usb/gadget/function/u_ncm.h +1 -1
index 5408854d84072d..297e5087872f3f 100644
@@ -18,7 +18,7 @@
 struct f_ncm_opts {
 	struct usb_function_instance	func_inst;
 	struct net_device		*net;
-	bool				bound;
+	int				bind_count;
 
 	struct config_group		*ncm_interf_group;
 	struct usb_os_desc		ncm_os_desc;
Signature · 1 line
2.53.0
author maintainer
#247 lore raw

PATCH 233/522 usb: gadget: u_ether: Fix NULL pointer deref in eth_get_drvinfo

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Kuen-Han Tsai <[email protected]>

[ Upstream commit e002e92e88e12457373ed096b18716d97e7bbb20 ]

Commit ec35c1969650 ("usb: gadget: f_ncm: Fix net_device lifecycle with device_move") reparents the gadget device to /sys/devices/virtual during unbind, clearing the gadget pointer. If the userspace tool queries on the surviving interface during this detached window, this leads to a NULL pointer dereference.

Unable to handle kernel NULL pointer dereference
Call trace:
 eth_get_drvinfo+0x50/0x90
 ethtool_get_drvinfo+0x5c/0x1f0
 __dev_ethtool+0xaec/0x1fe0
 dev_ethtool+0x134/0x2e0
 dev_ioctl+0x338/0x560

Add a NULL check for dev->gadget in eth_get_drvinfo(). When detached, skip copying the fw_version and bus_info strings, which is natively handled by ethtool_get_drvinfo for empty strings.

---
 drivers/usb/gadget/function/u_ether.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/usb/gadget/function/u_ether.c +4 -2
index e972de236be5e2..83dfc5008b689e 100644
@@ -147,8 +147,10 @@ static void eth_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *p)
 
 	strscpy(p->driver, "g_ether", sizeof(p->driver));
 	strscpy(p->version, UETH__VERSION, sizeof(p->version));
-	strscpy(p->fw_version, dev->gadget->name, sizeof(p->fw_version));
-	strscpy(p->bus_info, dev_name(&dev->gadget->dev), sizeof(p->bus_info));
+	if (dev->gadget) {
+		strscpy(p->fw_version, dev->gadget->name, sizeof(p->fw_version));
+		strscpy(p->bus_info, dev_name(&dev->gadget->dev), sizeof(p->bus_info));
+	}
 }
 
 /* REVISIT can also support:
Signature · 1 line
2.53.0
author maintainer
#248 lore raw

PATCH 234/522 net: skbuff: fix missing zerocopy reference in pskb_carve helpers

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Minh Nguyen <[email protected]>

commit 98d0912e9f841e5529a5b89a972805f34cb1c69d upstream.

pskb_carve_inside_header() and pskb_carve_inside_nonlinear() both copy the old skb_shared_info header into a new buffer via memcpy(), which includes the destructor_arg pointer (uarg) for MSG_ZEROCOPY skbs. Neither function calls net_zcopy_get() for the new shinfo, creating an unaccounted holder: every skb_shared_info with destructor_arg set will call skb_zcopy_clear() once when freed, but the corresponding net_zcopy_get() was never called for the new copy. Repeated calls drive uarg->refcnt to zero prematurely, freeing ubuf_info_msgzc while TX skbs still hold live destructor_arg pointers.

KASAN reports use-after-free on a freed ubuf_info_msgzc:

  BUG: KASAN: slab-use-after-free in skb_release_data+0x77b/0x810
  Read of size 8 at addr ffff88801574d3e8 by task poc/220

  Call Trace:
   skb_release_data+0x77b/0x810
   kfree_skb_list_reason+0x13e/0x610
   skb_release_data+0x4cd/0x810
   sk_skb_reason_drop+0xf3/0x340
   skb_queue_purge_reason+0x282/0x440
   rds_tcp_inc_free+0x1e/0x30
   rds_recvmsg+0x354/0x1780
   __sys_recvmsg+0xdf/0x180

  Allocated by task 219:
   msg_zerocopy_realloc+0x157/0x7b0
   tcp_sendmsg_locked+0x2892/0x3ba0

  Freed by task 219:
   ip_recv_error+0x74a/0xb10
   tcp_recvmsg+0x475/0x530

The skb consuming the late access still referenced the same uarg via shinfo->destructor_arg copied by pskb_carve_inside_nonlinear() without a refcount bump. This has been verified to be reliably exploitable: a working proof-of-concept achieves full root privilege escalation from an unprivileged local user on a default kernel configuration.

The fix follows the pattern of pskb_expand_head() which has the same memcpy/cloned structure. For pskb_carve_inside_header(), net_zcopy_get() is placed after skb_orphan_frags() succeeds, so the orphan error path needs no cleanup. For pskb_carve_inside_nonlinear(), net_zcopy_get() is placed after all failure points and just before skb_release_data(), so no error path needs cleanup at all -- matching pskb_expand_head() more closely and avoiding the need for a balancing net_zcopy_put().

Fixes 6fa01ccd8830 ("skbuff: Add pskb_extract() helper function")
Assisted-by Claude:claude-sonnet-4-6

[Salvatore Bonaccorso: Backport for context changes, as 6.1.y has not 511a3eda2f8d ("net: dropreason: propagate drop_reason to skb_release_data()")].

---
 net/core/skbuff.c | 4 ++++
 1 file changed, 4 insertions(+)
net/core/skbuff.c +4 -0
index 41b2aaed7a14aa..f1f5b2b25f8522 100644
@@ -6247,6 +6247,8 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off,
 			kfree(data);
 			return -ENOMEM;
 		}
+		if (skb_zcopy(skb))
+			net_zcopy_get(skb_zcopy(skb));
 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
 			skb_frag_ref(skb, i);
 		if (skb_has_frag_list(skb))
@@ -6396,6 +6398,8 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off,
 		kfree(data);
 		return -ENOMEM;
 	}
+	if (skb_zcopy(skb))
+		net_zcopy_get(skb_zcopy(skb));
 	skb_release_data(skb);
 
 	skb->head = data;
Signature · 1 line
2.53.0
author maintainer
#249 lore raw

PATCH 235/522 tap: free page on error paths in tap_get_user_xdp()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Weiming Shi <[email protected]>

[ Upstream commit 3bcf7aec6a9d16438f2cec29f5d7c8d5b8edf9b2 ]

tap_get_user_xdp() rejects a frame shorter than ETH_HLEN with -EINVAL, and returns -ENOMEM when build_skb() fails. Both paths jump to the err label without freeing the page that vhost_net_build_xdp() allocated for the frame. tap_sendmsg() discards the per-buffer return value and always returns 0, so vhost_tx_batch() takes the success path and never frees the page; each rejected frame in a batch leaks one page-frag chunk.

Free the page on both error paths, before the skb is built. This is the tap counterpart of the same leak in tun_xdp_one().

Fixes 0efac27791ee ("tap: accept an array of XDP buffs through sendmsg()")
Fixes ed7f2afdd0e0 ("tap: add missing verification for short frame")
(cherry picked from commit 3bcf7aec6a9d16438f2cec29f5d7c8d5b8edf9b2)
---
 drivers/net/tap.c | 2 ++
 1 file changed, 2 insertions(+)
drivers/net/tap.c +2 -0
index f8e7b163810de6..15ab71f5288ac3 100644
@@ -1157,6 +1157,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 	int err, depth;
 
 	if (unlikely(xdp->data_end - xdp->data < ETH_HLEN)) {
+		put_page(virt_to_head_page(xdp->data));
 		err = -EINVAL;
 		goto err;
 	}
@@ -1166,6 +1167,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 
 	skb = build_skb(xdp->data_hard_start, buflen);
 	if (!skb) {
+		put_page(virt_to_head_page(xdp->data));
 		err = -ENOMEM;
 		goto err;
 	}
Signature · 1 line
2.53.0
author maintainer
#250 lore raw

PATCH 236/522 KVM: arm64: Remove VPIPT I-cache handling

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Marc Zyngier <[email protected]>

commit ced242ba9d7cb3571f6e0f165f643cb832d52148 upstream.

We have some special handling for VPIPT I-cache in critical parts of the cache and TLB maintenance. Remove it.

---
 arch/arm64/include/asm/kvm_mmu.h |  4 ++--
 arch/arm64/kvm/hyp/nvhe/tlb.c    | 35 --------------------------------
 arch/arm64/kvm/hyp/vhe/tlb.c     | 13 ------------
 3 files changed, 2 insertions(+), 50 deletions(-)
arch/arm64/include/asm/kvm_mmu.h +2 -2
index 7784081088e78f..1495fcddd98e58 100644
@@ -214,8 +214,8 @@ static inline void __invalidate_icache_guest_page(void *va, size_t size)
 	if (icache_is_aliasing()) {
 		/* any kind of VIPT cache */
 		icache_inval_all_pou();
-	} else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
-		/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
+	} else {
+		/* PIPT */
 		icache_inval_pou((unsigned long)va, (unsigned long)va + size);
 	}
 }
arch/arm64/kvm/hyp/nvhe/tlb.c +0 -35
index d296d617f58963..291789df24e3ee 100644
@@ -84,28 +84,6 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	dsb(ish);
 	isb();
 
-	/*
-	 * If the host is running at EL1 and we have a VPIPT I-cache,
-	 * then we must perform I-cache maintenance at EL2 in order for
-	 * it to have an effect on the guest. Since the guest cannot hit
-	 * I-cache lines allocated with a different VMID, we don't need
-	 * to worry about junk out of guest reset (we nuke the I-cache on
-	 * VMID rollover), but we do need to be careful when remapping
-	 * executable pages for the same guest. This can happen when KSM
-	 * takes a CoW fault on an executable page, copies the page into
-	 * a page that was previously mapped in the guest and then needs
-	 * to invalidate the guest view of the I-cache for that page
-	 * from EL1. To solve this, we invalidate the entire I-cache when
-	 * unmapping a page from a guest if we have a VPIPT I-cache but
-	 * the host is running at EL1. As above, we could do better if
-	 * we had the VA.
-	 *
-	 * The moral of this story is: if you have a VPIPT I-cache, then
-	 * you should be running with VHE enabled.
-	 */
-	if (icache_is_vpipt())
-		icache_inval_all_pou();
-
 	__tlb_switch_to_host(&cxt);
 }
 
@@ -144,18 +122,5 @@ void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);
-
-	/*
-	 * VIPT and PIPT caches are not affected by VMID, so no maintenance
-	 * is necessary across a VMID rollover.
-	 *
-	 * VPIPT caches constrain lookup and maintenance to the active VMID,
-	 * so we need to invalidate lines with a stale VMID to avoid an ABA
-	 * race after multiple rollovers.
-	 *
-	 */
-	if (icache_is_vpipt())
-		asm volatile("ic ialluis");
-
 	dsb(ish);
 }
arch/arm64/kvm/hyp/vhe/tlb.c +0 -13
index 24cef9b87f9e9c..fc3fcd29ccc306 100644
@@ -146,18 +146,5 @@ void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);
-
-	/*
-	 * VIPT and PIPT caches are not affected by VMID, so no maintenance
-	 * is necessary across a VMID rollover.
-	 *
-	 * VPIPT caches constrain lookup and maintenance to the active VMID,
-	 * so we need to invalidate lines with a stale VMID to avoid an ABA
-	 * race after multiple rollovers.
-	 *
-	 */
-	if (icache_is_vpipt())
-		asm volatile("ic ialluis");
-
 	dsb(ish);
 }
Signature · 1 line
2.53.0
author maintainer
#251 lore raw

PATCH 237/522 arm64: tlb: Allow XZR argument to TLBI ops

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Mark Rutland <[email protected]>

commit bfd9c931d19aa59fb8371d557774fa169b15db9a upstream.

The TLBI instruction accepts XZR as a register argument, and for TLBI operations with a register argument, there is no functional difference between using XZR or another GPR which contains zeroes. Operations without a register argument are encoded as if XZR were used.

Allow the __TLBI_1() macro to use XZR when a register argument is all zeroes.

Today this only results in a trivial code saving in __do_compat_cache_op()'s workaround for Neoverse-N1 erratum #1542419. In subsequent patches this pattern will be used more generally.

There should be no functional change as a result of this patch.

Cc Catalin Marinas <[email protected]>
Cc Marc Zyngier <[email protected]>
Cc Oliver Upton <[email protected]>
Cc Ryan Roberts <[email protected]>
Cc Will Deacon <[email protected]>
[Mark: Backport to v6.1.y]
---
 arch/arm64/include/asm/tlbflush.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
arch/arm64/include/asm/tlbflush.h +3 -3
index 412a3b9a3c25dc..2626a45849c241 100644
@@ -37,12 +37,12 @@
 			    : : )
 
 #define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
-			       "tlbi " #op ", %0\n"			       \
+			       "tlbi " #op ", %x0\n"			       \
 		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op ", %0",     \
+			       "dsb ish\n		tlbi " #op ", %x0",    \
 			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
 			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
-			    : : "r" (arg))
+			    : : "rZ" (arg))
 
 #define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
 
Signature · 1 line
2.53.0
author maintainer
#252 lore raw

PATCH 238/522 arm64: tlb: Optimize ARM64_WORKAROUND_REPEAT_TLBI

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Mark Rutland <[email protected]>

commit a8f78680ee6bf795086384e8aea159a52814f827 upstream.

The ARM64_WORKAROUND_REPEAT_TLBI workaround is used to mitigate several errata where broadcast TLBI;DSB sequences don't provide all the architecturally required synchronization. The workaround performs more work than necessary, and can have significant overhead. This patch optimizes the workaround, as explained below.

The workaround was originally added for Qualcomm Falkor erratum 1009 in commit:

d9ff80f83ecb ("arm64: Work around Falkor erratum 1009")

As noted in the message for that commit, the workaround is applied even in cases where it is not strictly necessary.

The workaround was later reused without changes for:

* Arm Cortex-A76 erratum #1286807
SDEN v33: https://developer.arm.com/documentation/SDEN-885749/33-0/

* Arm Cortex-A55 erratum #2441007
SDEN v16: https://developer.arm.com/documentation/SDEN-859338/1600/

* Arm Cortex-A510 erratum #2441009
SDEN v19: https://developer.arm.com/documentation/SDEN-1873351/1900/

The important details to note are as follows:

1. All relevant errata only affect the ordering and/or completion of memory accesses which have been translated by an invalidated TLB entry. The actual invalidation of TLB entries is unaffected.

2. The existing workaround is applied to both broadcast and local TLB invalidation, whereas for all relevant errata it is only necessary to apply a workaround for broadcast invalidation.

3. The existing workaround replaces every TLBI with a TLBI;DSB;TLBI sequence, whereas for all relevant errata it is only necessary to execute a single additional TLBI;DSB sequence after any number of TLBIs are completed by a DSB.

For example, for a sequence of batched TLBIs:

       TLBI <op1>[, <arg1>]
       TLBI <op2>[, <arg2>]
       TLBI <op3>[, <arg3>]
       DSB ISH

... the existing workaround will expand this to:

       TLBI <op1>[, <arg1>]
       DSB ISH                  // additional
       TLBI <op1>[, <arg1>]     // additional
       TLBI <op2>[, <arg2>]
       DSB ISH                  // additional
       TLBI <op2>[, <arg2>]     // additional
       TLBI <op3>[, <arg3>]
       DSB ISH                  // additional
       TLBI <op3>[, <arg3>]     // additional
       DSB ISH

... whereas it is sufficient to have:

       TLBI <op1>[, <arg1>]
       TLBI <op2>[, <arg2>]
       TLBI <op3>[, <arg3>]
       DSB ISH
       TLBI <opX>[, <argX>]     // additional
       DSB ISH                  // additional

Using a single additional TBLI and DSB at the end of the sequence can have significantly lower overhead as each DSB which completes a TLBI must synchronize with other PEs in the system, with potential performance effects both locally and system-wide.

4. The existing workaround repeats each specific TLBI operation, whereas for all relevant errata it is sufficient for the additional TLBI to use *any* operation which will be broadcast, regardless of which translation regime or stage of translation the operation applies to.

For example, for a single TLBI:

TLBI ALLE2IS
DSB ISH

... the existing workaround will expand this to:

TLBI ALLE2IS
DSB ISH
TLBI ALLE2IS // additional
DSB ISH // additional

... whereas it is sufficient to have:

TLBI ALLE2IS
DSB ISH
TLBI VALE1IS, XZR // additional
DSB ISH // additional

As the additional TLBI doesn't have to match a specific earlier TLBI, the additional TLBI can be implemented in separate code, with no memory of the earlier TLBIs. The additional TLBI can also use a cheaper TLBI operation.

5. The existing workaround is applied to both Stage-1 and Stage-2 TLB invalidation, whereas for all relevant errata it is only necessary to apply a workaround for Stage-1 invalidation.

Architecturally, TLBI operations which invalidate only Stage-2 information (e.g. IPAS2E1IS) are not required to invalidate TLB entries which combine information from Stage-1 and Stage-2 translation table entries, and consequently may not complete memory accesses translated by those combined entries. In these cases, completion of memory accesses is only guaranteed after subsequent invalidation of Stage-1 information (e.g. VMALLE1IS).

Taking the above points into account, this patch reworks the workaround logic to reduce overhead:

* New __tlbi_sync_s1ish() and __tlbi_sync_s1ish_hyp() functions are added and used in place of any dsb(ish) which is used to complete broadcast Stage-1 TLB maintenance. When the ARM64_WORKAROUND_REPEAT_TLBI workaround is enabled, these helpers will execute an additional TLBI;DSB sequence.

For consistency, it might make sense to add __tlbi_sync_*() helpers for local and stage 2 maintenance. For now I've left those with open-coded dsb() to keep the diff small.

* The duplication of TLBIs in __TLBI_0() and __TLBI_1() is removed. This is no longer needed as the necessary synchronization will happen in __tlbi_sync_s1ish() or __tlbi_sync_s1ish_hyp().

* The additional TLBI operation is chosen to have minimal impact:

- __tlbi_sync_s1ish() uses "TLBI VALE1IS, XZR". This is only used at EL1 or at EL2 with {E2H,TGE}=={1,1}, where it will target an unused entry for the reserved ASID in the kernel's own translation regime, and have no adverse affect.

- __tlbi_sync_s1ish_hyp() uses "TLBI VALE2IS, XZR". This is only used in hyp code, where it will target an unused entry in the hyp code's TTBR0 mapping, and should have no adverse effect.

* As __TLBI_0() and __TLBI_1() no longer replace each TLBI with a TLBI;DSB;TLBI sequence, batching TLBIs is worthwhile, and there's no need for arch_tlbbatch_should_defer() to consider ARM64_WORKAROUND_REPEAT_TLBI.

When building defconfig with GCC 15.1.0, compared to v6.19-rc1, this patch saves ~1KiB of text, makes the vmlinux ~42KiB smaller, and makes the resulting Image 64KiB smaller:

| [mark@lakrids:~/src/linux]% size vmlinux-*
|    text    data     bss     dec     hex filename
| 21179831        19660919         708216 41548966        279fca6 vmlinux-after
| 21181075        19660903         708216 41550194        27a0172 vmlinux-before
| [mark@lakrids:~/src/linux]% ls -l vmlinux-*
| -rwxr-xr-x 1 mark mark 157771472 Feb  4 12:05 vmlinux-after
| -rwxr-xr-x 1 mark mark 157815432 Feb  4 12:05 vmlinux-before
| [mark@lakrids:~/src/linux]% ls -l Image-*
| -rw-r--r-- 1 mark mark 41007616 Feb  4 12:05 Image-after
| -rw-r--r-- 1 mark mark 41073152 Feb  4 12:05 Image-before
Cc Catalin Marinas <[email protected]>
Cc Marc Zyngier <[email protected]>
Cc Oliver Upton <[email protected]>
Cc Ryan Roberts <[email protected]>
Cc Will Deacon <[email protected]>
[Mark: Backport to v6.1.y]
---
 arch/arm64/include/asm/tlbflush.h | 48 ++++++++++++++++++++++---------
 arch/arm64/kernel/sys_compat.c    |  2 +-
 arch/arm64/kvm/hyp/nvhe/tlb.c     |  6 ++--
 arch/arm64/kvm/hyp/pgtable.c      |  2 +-
 arch/arm64/kvm/hyp/vhe/tlb.c      |  6 ++--
 5 files changed, 42 insertions(+), 22 deletions(-)
arch/arm64/include/asm/tlbflush.h +34 -14
index 2626a45849c241..289c3948d5b08a 100644
@@ -30,18 +30,10 @@
  */
 #define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE			       \
 			       "tlbi " #op "\n"				       \
-		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op,	       \
-			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
-			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
 			    : : )
 
 #define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE			       \
 			       "tlbi " #op ", %x0\n"			       \
-		   ALTERNATIVE("nop\n			nop",		       \
-			       "dsb ish\n		tlbi " #op ", %x0",    \
-			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
-			       CONFIG_ARM64_WORKAROUND_REPEAT_TLBI)	       \
 			    : : "rZ" (arg))
 
 #define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
@@ -158,6 +150,34 @@ static inline unsigned long get_trans_granule(void)
 #define __TLBI_RANGE_NUM(pages, scale)	\
 	((((pages) >> (5 * (scale) + 1)) & TLBI_RANGE_MASK) - 1)
 
+#define __repeat_tlbi_sync(op, arg...)						\
+do {										\
+	if (!alternative_has_feature_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))	\
+		break;								\
+	__tlbi(op, ##arg);							\
+	dsb(ish);								\
+} while (0)
+
+/*
+ * Complete broadcast TLB maintenance issued by the host which invalidates
+ * stage 1 information in the host's own translation regime.
+ */
+static inline void __tlbi_sync_s1ish(void)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale1is, 0);
+}
+
+/*
+ * Complete broadcast TLB maintenance issued by hyp code which invalidates
+ * stage 1 translation information in any translation regime.
+ */
+static inline void __tlbi_sync_s1ish_hyp(void)
+{
+	dsb(ish);
+	__repeat_tlbi_sync(vale2is, 0);
+}
+
 /*
  *	TLB Invalidation
  *	================
@@ -239,7 +259,7 @@ static inline void flush_tlb_all(void)
 {
 	dsb(ishst);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 
@@ -251,7 +271,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	asid = __TLBI_VADDR(0, ASID(mm));
 	__tlbi(aside1is, asid);
 	__tlbi_user(aside1is, asid);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 static inline void flush_tlb_page_nosync(struct vm_area_struct *vma,
@@ -269,7 +289,7 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 				  unsigned long uaddr)
 {
 	flush_tlb_page_nosync(vma, uaddr);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 /*
@@ -357,7 +377,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 		}
 		scale++;
 	}
-	dsb(ish);
+	__tlbi_sync_s1ish();
 }
 
 static inline void flush_tlb_range(struct vm_area_struct *vma,
@@ -386,7 +406,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 	dsb(ishst);
 	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
 		__tlbi(vaale1is, addr);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 
@@ -400,7 +420,7 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
 
 	dsb(ishst);
 	__tlbi(vaae1is, addr);
-	dsb(ish);
+	__tlbi_sync_s1ish();
 	isb();
 }
 #endif
arch/arm64/kernel/sys_compat.c +1 -1
index df14336c3a29cf..2bc2ac91d79e39 100644
@@ -37,7 +37,7 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 			 * We pick the reserved-ASID to minimise the impact.
 			 */
 			__tlbi(aside1is, __TLBI_VADDR(0, 0));
-			dsb(ish);
+			__tlbi_sync_s1ish();
 		}
 
 		ret = caches_clean_inval_user_pou(start, start + chunk);
arch/arm64/kvm/hyp/nvhe/tlb.c +3 -3
index 291789df24e3ee..76973e3b48a076 100644
@@ -81,7 +81,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	 */
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	__tlb_switch_to_host(&cxt);
@@ -97,7 +97,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	__tlb_switch_to_host(&cxt);
@@ -122,5 +122,5 @@ void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 }
arch/arm64/kvm/hyp/pgtable.c +1 -1
index f0167dc7438f8a..d2838de92b4796 100644
@@ -486,7 +486,7 @@ static int hyp_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
 		data->unmapped += granule;
 	}
 
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 	mm_ops->put_page(ptep);
 
arch/arm64/kvm/hyp/vhe/tlb.c +3 -3
index fc3fcd29ccc306..59aa22b48e9538 100644
@@ -105,7 +105,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	 */
 	dsb(ish);
 	__tlbi(vmalle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	__tlb_switch_to_host(&cxt);
@@ -121,7 +121,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 	isb();
 
 	__tlb_switch_to_host(&cxt);
@@ -146,5 +146,5 @@ void __kvm_flush_vm_context(void)
 {
 	dsb(ishst);
 	__tlbi(alle1is);
-	dsb(ish);
+	__tlbi_sync_s1ish_hyp();
 }
Signature · 1 line
2.53.0
author maintainer
#253 lore raw

PATCH 239/522 iomap: dont revert iov_iter on partially completed buffered writes

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Brian Foster <[email protected]>

Gregg reports that the iomap retry behavior for nonblocking (nowait) append writes is broken. The problem occurs when an append write is first submitted in non-blocking mode (i.e. via io_uring), partially completes before hitting -EAGAIN, and then is resubmitted from blocking context.

The specific problem is that at least one iteration of the loop in iomap_write_iter() completes in non-blocking context and thus has bumped i_size. The next iteration hits -EAGAIN, reverts the iov_iter and returns. io_uring retries the entire append write from blocking context, but since i_size has already been increased, the data that was partially written on the first attempt is rewritten at the new i_size. This is essentially an intra-write data corruption since the data written to the file does not reflect the write from userspace.

This problem is already fixed on master as of commit 1a1a3b574b97 ("iomap: advance the iter directly on buffered writes"). That commit was primarily intended to clean up iomap iter state tracking, but it also happened to remove the iov_iter revert and thus accidentally fix this problem as well. Without the revert, iomap will commit partial progress internally and loop once more before it more than likely hits -EAGAIN and returns partial progress consistent with the inode updates. This means the blocking retry from io_uring will pick up where the first attempt left off at the current i_size and perform the remainder of the write correctly.

Fixes 18e419f6e80a ("iomap: Return -EAGAIN from iomap_write_iter()")
---
 fs/iomap/buffered-io.c | 4 ----
 1 file changed, 4 deletions(-)
fs/iomap/buffered-io.c +0 -4
index c3408ba636632a..243cb2ec76ed2e 100644
@@ -821,10 +821,6 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		length -= status;
 	} while (iov_iter_count(i) && length);
 
-	if (status == -EAGAIN) {
-		iov_iter_revert(i, written);
-		return -EAGAIN;
-	}
 	return written ? written : status;
 }
 
Signature · 1 line
2.53.0
author maintainer
#254 lore raw

PATCH 240/522 xfrm: policy: fix use-after-free on inexact bin in xfrm_policy_bysel_ctx()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Sanghyun Park <[email protected]>

[ Upstream commit 7f2d76c9c03257c0782afef9d95321fa04096f60 ]

Fix the race by pruning the bin while still holding xfrm_policy_lock, before dropping it. Use __xfrm_policy_inexact_prune_bin() directly since the lock is already held. The wrapper xfrm_policy_inexact_prune_bin() becomes unused and is removed.

Race:

CPU0 (XFRM_MSG_DELPOLICY) CPU1 (XFRM_MSG_NEWSPDINFO)
========================== ==========================
xfrm_policy_bysel_ctx():

    spin_lock_bh(xfrm_policy_lock)
    bin = xfrm_policy_inexact_lookup()
    __xfrm_policy_unlink(pol)
    spin_unlock_bh(xfrm_policy_lock)
    xfrm_policy_kill(ret)
    // wide window, lock not held
                                       xfrm_hash_rebuild():
                                         spin_lock_bh(xfrm_policy_lock)
                                         __xfrm_policy_inexact_flush():
                                           kfree_rcu(bin)  // bin freed
                                         spin_unlock_bh(xfrm_policy_lock)
    xfrm_policy_inexact_prune_bin(bin)
    // UAF: bin is freed
Fixes 6be3b0db6db8 ("xfrm: policy: add inexact policy search tree infrastructure")
---
 net/xfrm/xfrm_policy.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)
net/xfrm/xfrm_policy.c +2 -11
index cebbb47f701f47..aeb994f96192cd 100644
@@ -1124,15 +1124,6 @@ static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool
 	}
 }
 
-static void xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b)
-{
-	struct net *net = read_pnet(&b->k.net);
-
-	spin_lock_bh(&net->xfrm.xfrm_policy_lock);
-	__xfrm_policy_inexact_prune_bin(b, false);
-	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
-}
-
 static void __xfrm_policy_inexact_flush(struct net *net)
 {
 	struct xfrm_pol_inexact_bin *bin, *t;
@@ -1723,12 +1714,12 @@ xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id,
 		}
 		ret = pol;
 	}
+	if (bin && delete)
+		__xfrm_policy_inexact_prune_bin(bin, false);
 	spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
 
 	if (ret && delete)
 		xfrm_policy_kill(ret);
-	if (bin && delete)
-		xfrm_policy_inexact_prune_bin(bin);
 	return ret;
 }
 EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
Signature · 1 line
2.53.0
author maintainer
#255 lore raw

PATCH 241/522 netlabel: validate unlabeled address and mask attribute lengths

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Chenguang Zhao <[email protected]>

[ Upstream commit 9772589b57e44aedc240211c5c3f7a684a034d3a ]

netlbl_unlabel_addrinfo_get() used the address attribute length to determine whether the attribute data could be read as an IPv4 or IPv6 address, but did not independently validate the corresponding mask attribute length. A crafted Generic Netlink request could therefore provide a valid IPv4/IPv6 address attribute with a shorter mask attribute, which would later be read as a full struct in_addr or struct in6_addr.

NLA_BINARY policy lengths are maximum lengths by default, so use NLA_POLICY_EXACT_LEN() for the unlabeled IPv4/IPv6 address and mask attributes. This rejects short attributes during policy validation and also exposes the exact length requirements through policy introspection.

Fixes 8cc44579d1bd ("NetLabel: Introduce static network labels for unlabeled connections")
---
 net/netlabel/netlabel_unlabeled.c | 30 ++++++++++--------------------
 1 file changed, 10 insertions(+), 20 deletions(-)
net/netlabel/netlabel_unlabeled.c +10 -20
index 9996883bf2b78d..6007cb000da678 100644
@@ -114,14 +114,14 @@ static struct genl_family netlbl_unlabel_gnl_family;
 /* NetLabel Netlink attribute policy */
 static const struct nla_policy netlbl_unlabel_genl_policy[NLBL_UNLABEL_A_MAX + 1] = {
 	[NLBL_UNLABEL_A_ACPTFLG] = { .type = NLA_U8 },
-	[NLBL_UNLABEL_A_IPV6ADDR] = { .type = NLA_BINARY,
-				      .len = sizeof(struct in6_addr) },
-	[NLBL_UNLABEL_A_IPV6MASK] = { .type = NLA_BINARY,
-				      .len = sizeof(struct in6_addr) },
-	[NLBL_UNLABEL_A_IPV4ADDR] = { .type = NLA_BINARY,
-				      .len = sizeof(struct in_addr) },
-	[NLBL_UNLABEL_A_IPV4MASK] = { .type = NLA_BINARY,
-				      .len = sizeof(struct in_addr) },
+	[NLBL_UNLABEL_A_IPV6ADDR] =
+		NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
+	[NLBL_UNLABEL_A_IPV6MASK] =
+		NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
+	[NLBL_UNLABEL_A_IPV4ADDR] =
+		NLA_POLICY_EXACT_LEN(sizeof(struct in_addr)),
+	[NLBL_UNLABEL_A_IPV4MASK] =
+		NLA_POLICY_EXACT_LEN(sizeof(struct in_addr)),
 	[NLBL_UNLABEL_A_IFACE] = { .type = NLA_NUL_STRING,
 				   .len = IFNAMSIZ - 1 },
 	[NLBL_UNLABEL_A_SECCTX] = { .type = NLA_BINARY }
@@ -764,24 +764,14 @@ static int netlbl_unlabel_addrinfo_get(struct genl_info *info,
 				       void **mask,
 				       u32 *len)
 {
-	u32 addr_len;
-
 	if (info->attrs[NLBL_UNLABEL_A_IPV4ADDR] &&
 	    info->attrs[NLBL_UNLABEL_A_IPV4MASK]) {
-		addr_len = nla_len(info->attrs[NLBL_UNLABEL_A_IPV4ADDR]);
-		if (addr_len != sizeof(struct in_addr) &&
-		    addr_len != nla_len(info->attrs[NLBL_UNLABEL_A_IPV4MASK]))
-			return -EINVAL;
-		*len = addr_len;
+		*len = sizeof(struct in_addr);
 		*addr = nla_data(info->attrs[NLBL_UNLABEL_A_IPV4ADDR]);
 		*mask = nla_data(info->attrs[NLBL_UNLABEL_A_IPV4MASK]);
 		return 0;
 	} else if (info->attrs[NLBL_UNLABEL_A_IPV6ADDR]) {
-		addr_len = nla_len(info->attrs[NLBL_UNLABEL_A_IPV6ADDR]);
-		if (addr_len != sizeof(struct in6_addr) &&
-		    addr_len != nla_len(info->attrs[NLBL_UNLABEL_A_IPV6MASK]))
-			return -EINVAL;
-		*len = addr_len;
+		*len = sizeof(struct in6_addr);
 		*addr = nla_data(info->attrs[NLBL_UNLABEL_A_IPV6ADDR]);
 		*mask = nla_data(info->attrs[NLBL_UNLABEL_A_IPV6MASK]);
 		return 0;
Signature · 1 line
2.53.0
author maintainer
#256 lore raw

PATCH 242/522 ASoC: wm_adsp: Fix NULL dereference when removing firmware controls

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Richard Fitzgerald <[email protected]>

[ Upstream commit 7d3fb78b550301e43fdc60312aed733069694426 ]

In wm_adsp_control_remove() check that the priv pointer is not NULL before attempting to cleanup what it points to.

When cs_dsp creates a control it calls wm_adsp_control_add_cb() so that wm_adsp can create its own private control data. There are two cases where private data is not created:

1. The control is a SYSTEM control, so an ALSA control is not created.

2. The codec driver has registered a control_add() callback that hides the control, so wm_adsp_control_add() is not called.

When cs_dsp_remove destroys its control list it calls wm_adsp_control_remove() for each control. But wm_adsp_control_remove() was attempting to cleanup the private data pointed to by cs_ctl->priv without checking the pointer for NULL.

Fixes 0700bc2fb94c ("ASoC: wm_adsp: Separate generic cs_dsp_coeff_ctl handling")
---
 sound/soc/codecs/wm_adsp.c | 3 +++
 1 file changed, 3 insertions(+)
sound/soc/codecs/wm_adsp.c +3 -0
index 47a4c363227ccd..bc9798ea5a25e2 100644
@@ -666,6 +666,9 @@ static void wm_adsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl)
 {
 	struct wm_coeff_ctl *ctl = cs_ctl->priv;
 
+	if (!ctl)
+		return;
+
 	cancel_work_sync(&ctl->work);
 
 	kfree(ctl->name);
Signature · 1 line
2.53.0
author maintainer
#257 lore raw

PATCH 243/522 tcp: restrict SO_ATTACH_FILTER to priv users

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 5d39580f68e6ddeedd15e587282207489dfb3da2 ]

This patch restricts the use of SO_ATTACH_FILTER (cBPF) on TCP sockets to users with CAP_NET_ADMIN capability.

This blocks potential side-channel attack where an unprivileged application attaches a filter to leak TCP sequence/acknowledgment numbers.

Fixes 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc Willem de Bruijn <[email protected]>
Cc Alexei Starovoitov <[email protected]>
Cc Daniel Borkmann <[email protected]>
Cc Andrii Nakryiko <[email protected]>
Cc Martin KaFai Lau <[email protected]>
Cc Eduard Zingerman <[email protected]>
Cc Kumar Kartikeya Dwivedi <[email protected]>
Cc Song Liu <[email protected]>
Cc Yonghong Song <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc John Fastabend <[email protected]>
Cc Stanislav Fomichev <[email protected]>
---
 net/core/sock.c | 5 +++++
 1 file changed, 5 insertions(+)
net/core/sock.c +5 -0
index 62411c8870e855..5f79f0b78321c8 100644
@@ -1294,6 +1294,11 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 	case SO_ATTACH_FILTER: {
 		struct sock_fprog fprog;
 
+		if (sk_is_tcp(sk) &&
+		    !sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+			ret = -EPERM;
+			break;
+		}
 		ret = copy_bpf_fprog_from_user(&fprog, optval, optlen);
 		if (!ret)
 			ret = sk_attach_filter(&fprog, sk);
Signature · 1 line
2.53.0
author maintainer
#258 lore raw

PATCH 244/522 net/mlx4: avoid GCC 10 __bad_copy_from() false positive

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Yao Sang <[email protected]>

[ Upstream commit 2365343f4aad3e1b1e7a2e87e98cf66d5e590589 ]

mlx4_init_user_cqes() fills a scratch buffer with the CQE initialization pattern and then copies from that buffer to userspace.

In the single-copy path, the copy length is array_size(entries, cqe_size), but the scratch buffer is allocated with PAGE_SIZE. GCC 10 does not carry the branch invariant strongly enough through the object size checks and falsely triggers __bad_copy_from().

Size the scratch buffer to the actual copy length for the active path, keep array_size() for the single-copy case, and retain a WARN_ON_ONCE() guard for the PAGE_SIZE invariant before allocating the buffer.

Fixes f69bf5dee7ef ("net/mlx4: Use array_size() helper in copy_to_user()")
---
 drivers/net/ethernet/mellanox/mlx4/cq.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)
drivers/net/ethernet/mellanox/mlx4/cq.c +8 -1
index 4d4f9cf9facb87..fb83d8af8dcb9c 100644
@@ -290,6 +290,7 @@ static void mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn)
 static int mlx4_init_user_cqes(void *buf, int entries, int cqe_size)
 {
 	int entries_per_copy = PAGE_SIZE / cqe_size;
+	size_t copy_bytes;
 	void *init_ents;
 	int err = 0;
 	int i;
@@ -314,8 +315,14 @@ static int mlx4_init_user_cqes(void *buf, int entries, int cqe_size)
 			buf += PAGE_SIZE;
 		}
 	} else {
+		copy_bytes = array_size(entries, cqe_size);
+		if (WARN_ON_ONCE(copy_bytes > PAGE_SIZE)) {
+			err = -EINVAL;
+			goto out;
+		}
+
 		err = copy_to_user((void __user *)buf, init_ents,
-				   array_size(entries, cqe_size)) ?
+				   copy_bytes) ?
 			-EFAULT : 0;
 	}
 
Signature · 1 line
2.53.0
author maintainer
#259 lore raw

PATCH 245/522 net: qrtr: fix refcount saturation and potential UAF in qrtr_port_remove

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Mingyu Wang <[email protected]>

[ Upstream commit a2171131ecda1ed61a594a1eb715e75fdad0fef5 ]

In qrtr_port_remove(), the socket reference count is decremented via __sock_put() before the port is removed from the qrtr_ports XArray and before the RCU grace period elapses.

This breaks the fundamental RCU update paradigm. It exposes a race window where a concurrent RCU reader (such as qrtr_reset_ports() or qrtr_port_lookup()) can obtain a pointer to the socket from the XArray, and attempt to call sock_hold() on a socket whose reference count has already dropped to zero.

This exact race condition was hit during syzkaller fuzzing, leading to the following refcount saturation warning and a potential Use-After-Free:

refcount_t: saturated; leaking memory.

  WARNING: CPU: 3 PID: 1273 at lib/refcount.c:22 refcount_warn_saturate+0xae/0x1d0
  Modules linked in: qrtr(+) bochs drm_shmem_helper ...
  Call Trace:
   <TASK>
   qrtr_reset_ports net/qrtr/af_qrtr.c:768 [inline] [qrtr]
   __qrtr_bind.isra.0+0x48b/0x570 net/qrtr/af_qrtr.c:805 [qrtr]
   qrtr_bind+0x17d/0x210 net/qrtr/af_qrtr.c:901 [qrtr]
   kernel_bind+0xe4/0x120 net/socket.c:3592
   qrtr_ns_init+0x1a6/0x380 net/qrtr/ns.c:715 [qrtr]
   qrtr_proto_init+0x3b/0xff0 net/qrtr/af_qrtr.c:169 [qrtr]
   do_one_initcall+0xf5/0x5e0 init/main.c:1283
   ...
   </TASK>

Fix this by deferring the reference count decrement until after the xa_erase() and the synchronize_rcu() complete.

(Note: The v1 of this patch incorrectly replaced __sock_put() with sock_put(). As Simon Horman pointed out, the callers of qrtr_port_remove() still hold a reference to the socket, so freeing the socket memory here would lead to a subsequent UAF in the caller. Thus, the __sock_put() is kept, but only repositioned to close the RCU race.)

---
 net/qrtr/af_qrtr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
net/qrtr/af_qrtr.c +2 -2
index 3831eb25e240ae..8cedf26d78ee02 100644
@@ -702,13 +702,13 @@ static void qrtr_port_remove(struct qrtr_sock *ipc)
 	if (port == QRTR_PORT_CTRL)
 		port = 0;
 
-	__sock_put(&ipc->sk);
-
 	xa_erase(&qrtr_ports, port);
 
 	/* Ensure that if qrtr_port_lookup() did enter the RCU read section we
 	 * wait for it to up increment the refcount */
 	synchronize_rcu();
+
+	__sock_put(&ipc->sk);
 }
 
 /* Assign port number to socket.
Signature · 1 line
2.53.0
author maintainer
#260 lore raw

PATCH 246/522 ipv6: sit: reload inner IPv6 header after GSO offloads

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Kyle Zeng <[email protected]>

[ Upstream commit f0e42f0c4337b1f220de1ddd63f47197c7dee4de ]

ipip6_tunnel_xmit() caches the inner IPv6 header pointer at function entry and continues using it after iptunnel_handle_offloads().

For GSO skbs, iptunnel_handle_offloads() calls skb_header_unclone(). When the skb header is cloned, skb_header_unclone() can call pskb_expand_head(), which may move the skb head. The pskb_expand_head() contract requires pointers into the skb header to be reloaded after the call.

If the later skb_realloc_headroom() branch is not taken, SIT uses the stale iph6 pointer to read the inner hop limit and DS field. That can read from a freed skb head after the old head's remaining clone is released.

Reload iph6 after the offload helper succeeds and before subsequent reads from the inner IPv6 header. Keep the existing reload after skb_realloc_headroom(), since that branch can also replace the skb.

Fixes 14909664e4e1 ("sit: Setup and TX path for sit/UDP foo-over-udp encapsulation")
Reported-by [email protected]
---
 net/ipv6/sit.c | 1 +
 1 file changed, 1 insertion(+)
net/ipv6/sit.c +1 -0
index eb4c8e2a2b12e0..aa88a41034d920 100644
@@ -965,6 +965,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		ip_rt_put(rt);
 		goto tx_error;
 	}
+	iph6 = ipv6_hdr(skb);
 
 	if (df) {
 		mtu = dst_mtu(&rt->dst) - t_hlen;
Signature · 1 line
2.53.0
author maintainer
#261 lore raw

PATCH 247/522 net: openvswitch: fix possible kfree_skb of ERR_PTR

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Adrian Moreno <[email protected]>

[ Upstream commit ee30dd2909d8b98619f4341c70ec8dc8e155ab02 ]

After the patch in the "Fixes" tag, the allocation of the "reply" skb can happen either before or after locking the ovs_mutex.

However, error cleanups still follow the classical reversed order, assuming "reply" is allocated before locking: it is freed after unlocking.

If "reply" allocation happens after locking the mutex and it fails, "reply" is left with an ERR_PTR, and execution jumps to the correspondent cleanup stage which will try to free an invalid pointer.

Fix this by setting the pointer to NULL after having saved its error value.

Fixes 893f139b9a6c ("openvswitch: Minimize ovs_flow_cmd_new|set critical sections.")
---
 net/openvswitch/datapath.c | 1 +
 1 file changed, 1 insertion(+)
net/openvswitch/datapath.c +1 -0
index c751d6b36febd1..0c0d89470145a1 100644
@@ -1263,6 +1263,7 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
 
 		if (IS_ERR(reply)) {
 			error = PTR_ERR(reply);
+			reply = NULL;
 			goto err_unlock_ovs;
 		}
 	}
Signature · 1 line
2.53.0
author maintainer
#262 lore raw

PATCH 248/522 r8152: reduce the control transfer of rtl8152_get_version()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Hayes Wang <[email protected]>

[ Upstream commit 02767440e1dda9861a11ca1dbe0f19a760b1d5c2 ]

Reduce the control transfer by moving calling rtl8152_get_version() in rtl8152_probe(). This could prevent from calling rtl8152_get_version() for unnecessary situations. For example, after setting config #2 for the device, there are two interfaces and rtl8152_probe() may be called twice. However, we don't need to call rtl8152_get_version() for this situation.

Stable-dep-of: 19440600e729 ("r8152: handle the return value of usb_reset_device()")

---
 drivers/net/usb/r8152.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)
drivers/net/usb/r8152.c +5 -4
index 98e30291b0500b..f730f6a797e767 100644
@@ -9640,20 +9640,21 @@ static int rtl8152_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
-	u8 version = rtl8152_get_version(intf);
 	struct r8152 *tp;
 	struct net_device *netdev;
+	u8 version;
 	int ret;
 
-	if (version == RTL_VER_UNKNOWN)
-		return -ENODEV;
-
 	if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC)
 		return -ENODEV;
 
 	if (!rtl_check_vendor_ok(intf))
 		return -ENODEV;
 
+	version = rtl8152_get_version(intf);
+	if (version == RTL_VER_UNKNOWN)
+		return -ENODEV;
+
 	usb_reset_device(udev);
 	netdev = alloc_etherdev(sizeof(struct r8152));
 	if (!netdev) {
Signature · 1 line
2.53.0
author maintainer
#263 lore raw

PATCH 249/522 r8152: Block future register access if register access fails

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Douglas Anderson <[email protected]>

[ Upstream commit d9962b0d42029bcb40fe3c38bce06d1870fa4df4 ]

Even though the functions to read/write registers can fail, most of the places in the r8152 driver that read/write register values don't check error codes. The lack of error code checking is problematic in at least two ways.

The first problem is that the r8152 driver often uses code patterns similar to this:
x = read_register()
x = x | SOME_BIT;
write_register(x);

...with the above pattern, if the read_register() fails and returns garbage then we'll end up trying to write modified garbage back to the Realtek adapter. If the write_register() succeeds that's bad. Note that as of commit f53a7ad18959 ("r8152: Set memory to all 0xFFs on failed reg reads") the "garbage" returned by read_register() will at least be consistent garbage, but it is still garbage.

It turns out that this problem is very serious. Writing garbage to some of the hardware registers on the Ethernet adapter can put the adapter in such a bad state that it needs to be power cycled (fully unplugged and plugged in again) before it can enumerate again.

The second problem is that the r8152 driver generally has functions that are long sequences of register writes. Assuming everything will be OK if a random register write fails in the middle isn't a great assumption.

One might wonder if the above two problems are real. You could ask if we would really have a successful write after a failed read. It turns out that the answer appears to be "yes, this can happen". In fact, we've seen at least two distinct failure modes where this happens.

On a sc7180-trogdor Chromebook if you drop into kdb for a while and then resume, you can see:
1. We get a "Tx timeout"
2. The "Tx timeout" queues up a USB reset.
3. In rtl8152_pre_reset() we try to reinit the hardware.
4. The first several (2-9) register accesses fail with a timeout, then things recover.

The above test case was actually fixed by the patch ("r8152: Increase USB control msg timeout to 5000ms as per spec") but at least shows that we really can see successful calls after failed ones.

On a different (AMD) based Chromebook with a particular adapter, we found that during reboot tests we'd also sometimes get a transitory failure. In this case we saw -EPIPE being returned sometimes. Retrying worked, but retrying is not always safe for all register accesses since reading/writing some registers might have side effects (like registers that clear on read).

Let's fully lock out all register access if a register access fails. When we do this, we'll try to queue up a USB reset and try to unlock register access after the reset. This is slightly tricker than it sounds since the r8152 driver has an optimized reset sequence that only works reliably after probe happens. In order to handle this, we avoid the optimized reset if probe didn't finish. Instead, we simply retry the probe routine in this case.

When locking out access, we'll use the existing infrastructure that the driver was using when it detected we were unplugged. This keeps us from getting stuck in delay loops in some parts of the driver.

Stable-dep-of: 19440600e729 ("r8152: handle the return value of usb_reset_device()")

---
 drivers/net/usb/r8152.c | 207 ++++++++++++++++++++++++++++++++++------
 1 file changed, 176 insertions(+), 31 deletions(-)
drivers/net/usb/r8152.c +176 -31
index f730f6a797e767..e8a69d3d418379 100644
@@ -772,6 +772,9 @@ enum rtl8152_flags {
 	SCHEDULE_TASKLET,
 	GREEN_ETHERNET,
 	RX_EPROTO,
+	IN_PRE_RESET,
+	PROBED_WITH_NO_ERRORS,
+	PROBE_SHOULD_RETRY,
 };
 
 #define DEVICE_ID_LENOVO_USB_C_TRAVEL_HUB		0x721e
@@ -952,6 +955,8 @@ struct r8152 {
 	u8 version;
 	u8 duplex;
 	u8 autoneg;
+
+	unsigned int reg_access_reset_count;
 };
 
 /**
@@ -1199,6 +1204,96 @@ static unsigned int agg_buf_sz = 16384;
 
 #define RTL_LIMITED_TSO_SIZE	(size_to_mtu(agg_buf_sz) - sizeof(struct tx_desc))
 
+/* If register access fails then we block access and issue a reset. If this
+ * happens too many times in a row without a successful access then we stop
+ * trying to reset and just leave access blocked.
+ */
+#define REGISTER_ACCESS_MAX_RESETS	3
+
+static void rtl_set_inaccessible(struct r8152 *tp)
+{
+	set_bit(RTL8152_INACCESSIBLE, &tp->flags);
+	smp_mb__after_atomic();
+}
+
+static void rtl_set_accessible(struct r8152 *tp)
+{
+	clear_bit(RTL8152_INACCESSIBLE, &tp->flags);
+	smp_mb__after_atomic();
+}
+
+static
+int r8152_control_msg(struct r8152 *tp, unsigned int pipe, __u8 request,
+		      __u8 requesttype, __u16 value, __u16 index, void *data,
+		      __u16 size, const char *msg_tag)
+{
+	struct usb_device *udev = tp->udev;
+	int ret;
+
+	if (test_bit(RTL8152_INACCESSIBLE, &tp->flags))
+		return -ENODEV;
+
+	ret = usb_control_msg(udev, pipe, request, requesttype,
+			      value, index, data, size,
+			      USB_CTRL_GET_TIMEOUT);
+
+	/* No need to issue a reset to report an error if the USB device got
+	 * unplugged; just return immediately.
+	 */
+	if (ret == -ENODEV)
+		return ret;
+
+	/* If the write was successful then we're done */
+	if (ret >= 0) {
+		tp->reg_access_reset_count = 0;
+		return ret;
+	}
+
+	dev_err(&udev->dev,
+		"Failed to %s %d bytes at %#06x/%#06x (%d)\n",
+		msg_tag, size, value, index, ret);
+
+	/* Block all future register access until we reset. Much of the code
+	 * in the driver doesn't check for errors. Notably, many parts of the
+	 * driver do a read/modify/write of a register value without
+	 * confirming that the read succeeded. Writing back modified garbage
+	 * like this can fully wedge the adapter, requiring a power cycle.
+	 */
+	rtl_set_inaccessible(tp);
+
+	/* If probe hasn't yet finished, then we'll request a retry of the
+	 * whole probe routine if we get any control transfer errors. We
+	 * never have to clear this bit since we free/reallocate the whole "tp"
+	 * structure if we retry probe.
+	 */
+	if (!test_bit(PROBED_WITH_NO_ERRORS, &tp->flags)) {
+		set_bit(PROBE_SHOULD_RETRY, &tp->flags);
+		return ret;
+	}
+
+	/* Failing to access registers in pre-reset is not surprising since we
+	 * wouldn't be resetting if things were behaving normally. The register
+	 * access we do in pre-reset isn't truly mandatory--we're just reusing
+	 * the disable() function and trying to be nice by powering the
+	 * adapter down before resetting it. Thus, if we're in pre-reset,
+	 * we'll return right away and not try to queue up yet another reset.
+	 * We know the post-reset is already coming.
+	 */
+	if (test_bit(IN_PRE_RESET, &tp->flags))
+		return ret;
+
+	if (tp->reg_access_reset_count < REGISTER_ACCESS_MAX_RESETS) {
+		usb_queue_reset_device(tp->intf);
+		tp->reg_access_reset_count++;
+	} else if (tp->reg_access_reset_count == REGISTER_ACCESS_MAX_RESETS) {
+		dev_err(&udev->dev,
+			"Tried to reset %d times; giving up.\n",
+			REGISTER_ACCESS_MAX_RESETS);
+	}
+
+	return ret;
+}
+
 static
 int get_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data)
 {
@@ -1209,9 +1304,10 @@ int get_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data)
 	if (!tmp)
 		return -ENOMEM;
 
-	ret = usb_control_msg(tp->udev, tp->pipe_ctrl_in,
-			      RTL8152_REQ_GET_REGS, RTL8152_REQT_READ,
-			      value, index, tmp, size, USB_CTRL_GET_TIMEOUT);
+	ret = r8152_control_msg(tp, tp->pipe_ctrl_in,
+				RTL8152_REQ_GET_REGS, RTL8152_REQT_READ,
+				value, index, tmp, size, "read");
+
 	if (ret < 0)
 		memset(data, 0xff, size);
 	else
@@ -1232,9 +1328,9 @@ int set_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data)
 	if (!tmp)
 		return -ENOMEM;
 
-	ret = usb_control_msg(tp->udev, tp->pipe_ctrl_out,
-			      RTL8152_REQ_SET_REGS, RTL8152_REQT_WRITE,
-			      value, index, tmp, size, USB_CTRL_SET_TIMEOUT);
+	ret = r8152_control_msg(tp, tp->pipe_ctrl_out,
+				RTL8152_REQ_SET_REGS, RTL8152_REQT_WRITE,
+				value, index, tmp, size, "write");
 
 	kfree(tmp);
 
@@ -1243,10 +1339,8 @@ int set_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data)
 
 static void rtl_set_unplug(struct r8152 *tp)
 {
-	if (tp->udev->state == USB_STATE_NOTATTACHED) {
-		set_bit(RTL8152_INACCESSIBLE, &tp->flags);
-		smp_mb__after_atomic();
-	}
+	if (tp->udev->state == USB_STATE_NOTATTACHED)
+		rtl_set_inaccessible(tp);
 }
 
 static int generic_ocp_read(struct r8152 *tp, u16 index, u16 size,
@@ -8295,7 +8389,7 @@ static int rtl8152_pre_reset(struct usb_interface *intf)
 	struct r8152 *tp = usb_get_intfdata(intf);
 	struct net_device *netdev;
 
-	if (!tp)
+	if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags))
 		return 0;
 
 	netdev = tp->netdev;
@@ -8310,7 +8404,9 @@ static int rtl8152_pre_reset(struct usb_interface *intf)
 	napi_disable(&tp->napi);
 	if (netif_carrier_ok(netdev)) {
 		mutex_lock(&tp->control);
+		set_bit(IN_PRE_RESET, &tp->flags);
 		tp->rtl_ops.disable(tp);
+		clear_bit(IN_PRE_RESET, &tp->flags);
 		mutex_unlock(&tp->control);
 	}
 
@@ -8323,9 +8419,11 @@ static int rtl8152_post_reset(struct usb_interface *intf)
 	struct net_device *netdev;
 	struct sockaddr sa;
 
-	if (!tp)
+	if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags))
 		return 0;
 
+	rtl_set_accessible(tp);
+
 	/* reset the MAC address in case of policy change */
 	if (determine_ethernet_addr(tp, &sa) >= 0) {
 		rtnl_lock();
@@ -9527,17 +9625,29 @@ static u8 __rtl_get_hw_ver(struct usb_device *udev)
 	__le32 *tmp;
 	u8 version;
 	int ret;
+	int i;
 
 	tmp = kmalloc(sizeof(*tmp), GFP_KERNEL);
 	if (!tmp)
 		return 0;
 
-	ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
-			      RTL8152_REQ_GET_REGS, RTL8152_REQT_READ,
-			      PLA_TCR0, MCU_TYPE_PLA, tmp, sizeof(*tmp),
-			      USB_CTRL_GET_TIMEOUT);
-	if (ret > 0)
-		ocp_data = (__le32_to_cpu(*tmp) >> 16) & VERSION_MASK;
+	/* Retry up to 3 times in case there is a transitory error. We do this
+	 * since retrying a read of the version is always safe and this
+	 * function doesn't take advantage of r8152_control_msg().
+	 */
+	for (i = 0; i < 3; i++) {
+		ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0),
+				      RTL8152_REQ_GET_REGS, RTL8152_REQT_READ,
+				      PLA_TCR0, MCU_TYPE_PLA, tmp, sizeof(*tmp),
+				      USB_CTRL_GET_TIMEOUT);
+		if (ret > 0) {
+			ocp_data = (__le32_to_cpu(*tmp) >> 16) & VERSION_MASK;
+			break;
+		}
+	}
+
+	if (i != 0 && ret > 0)
+		dev_warn(&udev->dev, "Needed %d retries to read version\n", i);
 
 	kfree(tmp);
 
@@ -9636,25 +9746,14 @@ static bool rtl8152_supports_lenovo_macpassthru(struct usb_device *udev)
 	return 0;
 }
 
-static int rtl8152_probe(struct usb_interface *intf,
-			 const struct usb_device_id *id)
+static int rtl8152_probe_once(struct usb_interface *intf,
+			      const struct usb_device_id *id, u8 version)
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
 	struct r8152 *tp;
 	struct net_device *netdev;
-	u8 version;
 	int ret;
 
-	if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC)
-		return -ENODEV;
-
-	if (!rtl_check_vendor_ok(intf))
-		return -ENODEV;
-
-	version = rtl8152_get_version(intf);
-	if (version == RTL_VER_UNKNOWN)
-		return -ENODEV;
-
 	usb_reset_device(udev);
 	netdev = alloc_etherdev(sizeof(struct r8152));
 	if (!netdev) {
@@ -9818,10 +9917,20 @@ static int rtl8152_probe(struct usb_interface *intf,
 	else
 		device_set_wakeup_enable(&udev->dev, false);
 
+	/* If we saw a control transfer error while probing then we may
+	 * want to try probe() again. Consider this an error.
+	 */
+	if (test_bit(PROBE_SHOULD_RETRY, &tp->flags))
+		goto out2;
+
+	set_bit(PROBED_WITH_NO_ERRORS, &tp->flags);
 	netif_info(tp, probe, netdev, "%s\n", DRIVER_VERSION);
 
 	return 0;
 
+out2:
+	unregister_netdev(netdev);
+
 out1:
 	tasklet_kill(&tp->tx_tl);
 	cancel_delayed_work_sync(&tp->hw_phy_work);
@@ -9830,10 +9939,46 @@ static int rtl8152_probe(struct usb_interface *intf,
 	rtl8152_release_firmware(tp);
 	usb_set_intfdata(intf, NULL);
 out:
+	if (test_bit(PROBE_SHOULD_RETRY, &tp->flags))
+		ret = -EAGAIN;
+
 	free_netdev(netdev);
 	return ret;
 }
 
+#define RTL8152_PROBE_TRIES	3
+
+static int rtl8152_probe(struct usb_interface *intf,
+			 const struct usb_device_id *id)
+{
+	u8 version;
+	int ret;
+	int i;
+
+	if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC)
+		return -ENODEV;
+
+	if (!rtl_check_vendor_ok(intf))
+		return -ENODEV;
+
+	version = rtl8152_get_version(intf);
+	if (version == RTL_VER_UNKNOWN)
+		return -ENODEV;
+
+	for (i = 0; i < RTL8152_PROBE_TRIES; i++) {
+		ret = rtl8152_probe_once(intf, id, version);
+		if (ret != -EAGAIN)
+			break;
+	}
+	if (ret == -EAGAIN) {
+		dev_err(&intf->dev,
+			"r8152 failed probe after %d tries; giving up\n", i);
+		return -ENODEV;
+	}
+
+	return ret;
+}
+
 static void rtl8152_disconnect(struct usb_interface *intf)
 {
 	struct r8152 *tp = usb_get_intfdata(intf);
Signature · 1 line
2.53.0
#264 lore raw

Re: [PATCH 6.1 249/522] r8152: Block future register access if register access fails

Quoted 7 lines · Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Douglas Anderson <[email protected]>

[ Upstream commit d9962b0d42029bcb40fe3c38bce06d1870fa4df4 ]

[...]

This needs a further fix on top: commit e62adaeecdc6 "r8152: Hold the rtnl_lock for all of reset".

Ben.

Signature · 2 lines
Ben Hutchings
Who are all these weirdos? - David Bowie, on joining IRC
author maintainer
#265 lore raw

Re: [PATCH 6.1 249/522] r8152: Block future register access if register access fails

Quoted 5 lines · Ben Hutchings
Quoted 4 lines · Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

Quoted 7 lines
Quoted 3 lines

From: Douglas Anderson <[email protected]>

[ Upstream commit d9962b0d42029bcb40fe3c38bce06d1870fa4df4 ]

[...]

This needs a further fix on top: commit e62adaeecdc6 "r8152: Hold the rtnl_lock for all of reset".

Already queued up in this tree.

thanks,

greg k-h

author maintainer
#266 lore raw

PATCH 250/522 r8152: handle the return value of usb_reset_device()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Chih Kai Hsu <[email protected]>

[ Upstream commit 19440600e729d4f74a42591a872099cf25c7d28a ]

If usb_reset_device() returns a negative error code, stop the process of probing.

---
 drivers/net/usb/r8152.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/net/usb/r8152.c +6 -1
index e8a69d3d418379..c0f7a15e406fee 100644
@@ -9754,7 +9754,12 @@ static int rtl8152_probe_once(struct usb_interface *intf,
 	struct net_device *netdev;
 	int ret;
 
-	usb_reset_device(udev);
+	ret = usb_reset_device(udev);
+	if (ret < 0) {
+		dev_err(&intf->dev, "USB reset failed, errno=%d\n", ret);
+		return ret;
+	}
+
 	netdev = alloc_etherdev(sizeof(struct r8152));
 	if (!netdev) {
 		dev_err(&intf->dev, "Out of memory\n");
Signature · 1 line
2.53.0
author maintainer
#267 lore raw

PATCH 251/522 sctp: fix uninit-value in __sctp_rcv_asconf_lookup()

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Bommarito <[email protected]>

[ Upstream commit f8373d7090b745728de66308deeecc67e8d319ce ]

__sctp_rcv_asconf_lookup() in net/sctp/input.c only checks that the ASCONF chunk can hold the ADDIP header and a parameter header, then calls af->from_addr_param(), which reads the full address (16 bytes for IPv6) trusting the parameter's declared length.

An unauthenticated peer can send a truncated trailing ASCONF chunk that declares an IPv6 address parameter but stops after the 4-byte parameter header; reached from the no-association lookup path, from_addr_param() then reads uninitialized bytes past the parameter.

Impact: an unauthenticated SCTP peer makes the receive path read up to 16 bytes of uninitialized memory past a truncated ASCONF address parameter.

The sibling __sctp_rcv_init_lookup() bounds parameters with sctp_walk_params(); this path open-codes the fetch and omits the bound. Verify the whole address parameter lies within the chunk before from_addr_param() reads it, the same class of fix as commit 51e5ad549c43 ("net: sctp: fix KMSAN uninit-value in sctp_inq_pop").

Fixes df2185771439 ("[SCTP]: Update association lookup to look at ASCONF chunks as well")
---
 net/sctp/input.c | 8 ++++++++
 1 file changed, 8 insertions(+)
net/sctp/input.c +8 -0
index 182898cb754a52..70530cbe57d0a7 100644
@@ -1197,6 +1197,14 @@ static struct sctp_association *__sctp_rcv_asconf_lookup(
 	/* Skip over the ADDIP header and find the Address parameter */
 	param = (union sctp_addr_param *)(asconf + 1);
 
+	/* The whole address parameter must lie within the chunk before
+	 * af->from_addr_param() reads the variable-length address; otherwise a
+	 * truncated trailing ASCONF chunk lets it read uninitialized bytes past
+	 * the parameter.
+	 */
+	if (sizeof(*asconf) + ntohs(param->p.length) > ntohs(ch->length))
+		return NULL;
+
 	af = sctp_get_af_specific(param_type2af(param->p.type));
 	if (unlikely(!af))
 		return NULL;
Signature · 1 line
2.53.0
author maintainer
#268 lore raw

PATCH 252/522 net: guard timestamp cmsgs to real error queue skbs

In reply to Greg Kroah-Hartman

6.1-stable review patch. If anyone has any objections, please let me know.

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

From: Kyle Zeng <[email protected]>

[ Upstream commit 1ee90b77b727df903033db873c75caac5c27ec98 ]

skb_is_err_queue() treats PACKET_OUTGOING as the sole marker for an skb from sk_error_queue. That assumption is not true for AF_PACKET sockets:
outgoing packet taps are also delivered to packet sockets with skb->pkt_type == PACKET_OUTGOING, but their skb->cb is owned by AF_PACKET instead of struct sock_exterr_skb.

If such an skb is received with timestamping enabled, the generic timestamp cmsg path can read AF_PACKET control-buffer state as sock_exterr_skb::opt_stats. With SO_RXQ_OVFL enabled, the packet drop counter overlaps opt_stats. An odd drop count makes the path emit SCM_TIMESTAMPING_OPT_STATS with skb->len and skb->data. For non-linear skbs this copies past the linear head and can trigger hardened usercopy or disclose adjacent heap contents.

Keep skb_is_err_queue() local to net/socket.c, but make it verify that the PACKET_OUTGOING marker is paired with the sock_rmem_free destructor installed by sock_queue_err_skb(). AF_PACKET receive skbs use normal receive ownership and no longer pass as error-queue skbs, while legitimate sk_error_queue entries keep the PACKET_OUTGOING marker and sock_rmem_free ownership.

---
 include/net/sock.h |  1 +
 net/core/skbuff.c  |  6 +++---
 net/socket.c       | 11 ++++++-----
 3 files changed, 10 insertions(+), 8 deletions(-)
include/net/sock.h +1 -0
index 2d34dd5941e795..1e7096e9bc4842 100644
@@ -1945,6 +1945,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
 			     gfp_t priority);
 void skb_orphan_partial(struct sk_buff *skb);
 void sock_rfree(struct sk_buff *skb);
+void sock_rmem_free(struct sk_buff *skb);
 void sock_efree(struct sk_buff *skb);
 #ifdef CONFIG_INET
 void sock_edemux(struct sk_buff *skb);
net/core/skbuff.c +3 -3
index f1f5b2b25f8522..f41dd20991c3df 100644
@@ -4810,7 +4810,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer)
 }
 EXPORT_SYMBOL_GPL(skb_cow_data);
 
-static void sock_rmem_free(struct sk_buff *skb)
+void sock_rmem_free(struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
 
@@ -4819,8 +4819,8 @@ static void sock_rmem_free(struct sk_buff *skb)
 
 static void skb_set_err_queue(struct sk_buff *skb)
 {
-	/* pkt_type of skbs received on local sockets is never PACKET_OUTGOING.
-	 * So, it is safe to (mis)use it to mark skbs on the error queue.
+	/* The error-queue test in skb_is_err_queue() matches this marker
+	 * with the sock_rmem_free destructor installed by sock_queue_err_skb().
 	 */
 	skb->pkt_type = PACKET_OUTGOING;
 	BUILD_BUG_ON(PACKET_OUTGOING == 0);
net/socket.c +6 -5
index 701389e2f22b3a..f2b4cf9b09a322 100644
@@ -807,12 +807,13 @@ EXPORT_SYMBOL(kernel_sendmsg_locked);
 
 static bool skb_is_err_queue(const struct sk_buff *skb)
 {
-	/* pkt_type of skbs enqueued on the error queue are set to
-	 * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do
-	 * in recvmsg, since skbs received on a local socket will never
-	 * have a pkt_type of PACKET_OUTGOING.
+	/* Error-queue skbs are marked as PACKET_OUTGOING in
+	 * skb_set_err_queue() and use the destructor installed by
+	 * sock_queue_err_skb(). PACKET_OUTGOING alone is not unique:
+	 * AF_PACKET outgoing taps use the same pkt_type.
 	 */
-	return skb->pkt_type == PACKET_OUTGOING;
+	return skb->pkt_type == PACKET_OUTGOING &&
+	       skb->destructor == sock_rmem_free;
 }
 
 /* On transmit, software and hardware timestamps are returned independently.
Signature · 1 line
2.53.0