6.1.178-rc1 review

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

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

From: Samuel Page <[email protected]>

commit 2b66974a1b6134a4bbc3bfed181f7418f688eb54 upstream.

A broadcast PROTOCOL/STATE_MSG can carry a Gap ACK blocks record in its data area. tipc_get_gap_ack_blks() only verifies that the record's len field is self-consistent with its ugack_cnt/bgack_cnt counts (sz == struct_size(p, gacks, ugack_cnt + bgack_cnt)); it does not check that the record actually fits in the message data area, msg_data_sz().

The unicast caller tipc_link_proto_rcv() bounds it ("if (glen > dlen) break;"), but the broadcast caller tipc_bcast_sync_rcv() discards the returned size, so tipc_link_advance_transmq() copies the record off the receive skb with an attacker-controlled count:

	this_ga = kmemdup(ga, struct_size(ga, gacks, ga->bgack_cnt),
			  GFP_ATOMIC);

A TIPC neighbour that negotiated TIPC_GAP_ACK_BLOCK triggers it with one ordinary broadcast STATE_MSG (msg_bc_ack_invalid() clear), sized so its data area is short, carrying a Gap ACK record with len = 0x400, bgack_cnt = 0xff and ugack_cnt = 0. len then equals struct_size(p, gacks, 255), so the consistency check passes and ga is non-NULL; kmemdup() reads struct_size(ga, gacks, 255) = 1024 bytes out of the much smaller skb:

  BUG: KASAN: slab-out-of-bounds in kmemdup_noprof+0x48/0x60
  Read of size 1024 at addr ffff0000c7030d38 by task poc864/69
  Call trace:
   kmemdup_noprof+0x48/0x60
   tipc_link_advance_transmq+0x86c/0xb80
   tipc_link_bc_ack_rcv+0x19c/0x1e0
   tipc_bcast_sync_rcv+0x1c4/0x2c4
   tipc_rcv+0x85c/0x1340
   tipc_l2_rcv_msg+0xac/0x104
  The buggy address belongs to the object at ffff0000c7030d00
   which belongs to the cache skbuff_small_head of size 704
  The buggy address is located 56 bytes inside of
   allocated 704-byte region [ffff0000c7030d00, ffff0000c7030fc0)

The copied-out bytes are subsequently consumed as gap/ack values, but the read is already out of bounds at the kmemdup() regardless of how they are used.

The unicast STATE path drops such a message: "if (glen > dlen) break;" skips the rest of STATE_MSG handling and the skb is freed. Make the broadcast path drop it too. tipc_bcast_sync_rcv() now bounds the record against msg_data_sz() and, when it does not fit, reports it back through tipc_node_bc_sync_rcv() to tipc_rcv() so the skb is discarded rather than processed. ga is not cleared on this path: ga == NULL already means "legacy peer without Selective ACK", a distinct legitimate state.

---
 net/tipc/bcast.c |   22 ++++++++++++++--------
 net/tipc/bcast.h |    2 +-
 net/tipc/node.c  |   15 ++++++++++++---
 3 files changed, 27 insertions(+), 12 deletions(-)

@@ -497,12 +497,13 @@ void tipc_bcast_ack_rcv(struct net *net,
  */
 int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l,
 			struct tipc_msg *hdr,
-			struct sk_buff_head *retrq)
+			struct sk_buff_head *retrq, bool *valid)
 {
 	struct sk_buff_head *inputq = &tipc_bc_base(net)->inputq;
 	struct tipc_gap_ack_blks *ga;
 	struct sk_buff_head xmitq;
 	int rc = 0;
+	u16 glen;
 
 	__skb_queue_head_init(&xmitq);
 

@@ -510,13 +511,18 @@ int tipc_bcast_sync_rcv(struct net *net,
 	if (msg_type(hdr) != STATE_MSG) {
 		tipc_link_bc_init_rcv(l, hdr);
 	} else if (!msg_bc_ack_invalid(hdr)) {
-		tipc_get_gap_ack_blks(&ga, l, hdr, false);
-		if (!sysctl_tipc_bc_retruni)
-			retrq = &xmitq;
-		rc = tipc_link_bc_ack_rcv(l, msg_bcast_ack(hdr),
-					  msg_bc_gap(hdr), ga, &xmitq,
-					  retrq);
-		rc |= tipc_link_bc_sync_rcv(l, hdr, &xmitq);
+		glen = tipc_get_gap_ack_blks(&ga, l, hdr, false);
+		if (glen > msg_data_sz(hdr)) {
+			/* Malformed Gap ACK blocks; caller drops the msg */
+			*valid = false;
+		} else {
+			if (!sysctl_tipc_bc_retruni)
+				retrq = &xmitq;
+			rc = tipc_link_bc_ack_rcv(l, msg_bcast_ack(hdr),
+						  msg_bc_gap(hdr), ga, &xmitq,
+						  retrq);
+			rc |= tipc_link_bc_sync_rcv(l, hdr, &xmitq);
+		}
 	}
 	tipc_bcast_unlock(net);
 

@@ -97,7 +97,7 @@ void tipc_bcast_ack_rcv(struct net *net,
 			struct tipc_msg *hdr);
 int tipc_bcast_sync_rcv(struct net *net, struct tipc_link *l,
 			struct tipc_msg *hdr,
-			struct sk_buff_head *retrq);
+			struct sk_buff_head *retrq, bool *valid);
 int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg,
 			struct tipc_link *bcl);
 int tipc_nl_bc_link_set(struct net *net, struct nlattr *attrs[]);

@@ -1833,12 +1833,15 @@ static void tipc_node_mcast_rcv(struct t
 }
 
 static void tipc_node_bc_sync_rcv(struct tipc_node *n, struct tipc_msg *hdr,
-				  int bearer_id, struct sk_buff_head *xmitq)
+				  int bearer_id, struct sk_buff_head *xmitq,
+				  bool *valid)
 {
 	struct tipc_link *ucl;
 	int rc;
 
-	rc = tipc_bcast_sync_rcv(n->net, n->bc_entry.link, hdr, xmitq);
+	rc = tipc_bcast_sync_rcv(n->net, n->bc_entry.link, hdr, xmitq, valid);
+	if (!*valid)
+		return;
 
 	if (rc & TIPC_LINK_DOWN_EVT) {
 		tipc_node_reset_links(n);

@@ -2142,12 +2145,18 @@ rcv:
 
 	/* Ensure broadcast reception is in synch with peer's send state */
 	if (unlikely(usr == LINK_PROTOCOL)) {
+		bool valid = true;
+
 		if (unlikely(skb_linearize(skb))) {
 			tipc_node_put(n);
 			goto discard;
 		}
 		hdr = buf_msg(skb);
-		tipc_node_bc_sync_rcv(n, hdr, bearer_id, &xmitq);
+		tipc_node_bc_sync_rcv(n, hdr, bearer_id, &xmitq, &valid);
+		if (!valid) {
+			tipc_node_put(n);
+			goto discard;
+		}
 	} else if (unlikely(tipc_link_acked(n->bc_entry.link) != bc_ack)) {
 		tipc_bcast_ack_rcv(net, n->bc_entry.link, hdr);
 	}

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

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

From: Michael Tautschnig <[email protected]>

commit 9f32f38265014fac7f5dc9490fb01a638ce6e121 upstream.

The SLAVE-path helpers buffer_to_user() and buffer_from_user() copy 'count' bytes into/out of the fixed-size kern_buf (size_buf == PCI_BUF_SIZE == 0x20000, 128 KiB) using *ppos as the offset, without bounding *ppos + count against size_buf.

vme_user_write()/vme_user_read() only clamp count to the VME window size (image_size = vme_get_size(resource)), which VME_SET_SLAVE sets from the user-supplied slave.size -- validated against the VME address space (up to VME_A32_MAX = 4 GiB), not against PCI_BUF_SIZE. When the window exceeds 128 KiB, a write()/read() copies past the kern_buf allocation.

Clamp count against size_buf in both helpers, with an early return when *ppos is already at/after the buffer end. *ppos is >= 0 here (the caller rejects negative offsets), so size_buf - *ppos cannot wrap. This mirrors the existing clamp in the MASTER-path helpers resource_to_user() / resource_from_user(), and matches the read()/write() convention of a short transfer at end-of-buffer.

Found by static analysis (CodeQL taint tracking + CBMC bounded model checking) and confirmed dynamically under KASAN with the vme_fake bridge:

  BUG: KASAN: slab-out-of-bounds in _copy_from_user+0x2d/0x80
  Write of size 262144 at addr ffff888004100000 by task trigger/68
    _copy_from_user+0x2d/0x80
    vme_user_write+0x13e/0x240 [vme_user]
    vfs_write+0x1b8/0x7a0
    ksys_write+0xb8/0x150

---
 drivers/staging/vme_user/vme_user.c |   22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

@@ -153,6 +153,17 @@ static ssize_t buffer_to_user(unsigned i
 {
 	void *image_ptr;
 
+	/*
+	 * The slave window (image_size) can exceed the fixed kern_buf
+	 * (size_buf == PCI_BUF_SIZE), so bound the copy to kern_buf.
+	 * *ppos is >= 0 here (checked by the caller), so the
+	 * subtraction below cannot wrap.
+	 */
+	if (*ppos >= image[minor].size_buf)
+		return 0;
+	if (count > image[minor].size_buf - *ppos)
+		count = image[minor].size_buf - *ppos;
+
 	image_ptr = image[minor].kern_buf + *ppos;
 	if (copy_to_user(buf, image_ptr, (unsigned long)count))
 		return -EFAULT;

@@ -165,6 +176,17 @@ static ssize_t buffer_from_user(unsigned
 {
 	void *image_ptr;
 
+	/*
+	 * The slave window (image_size) can exceed the fixed kern_buf
+	 * (size_buf == PCI_BUF_SIZE), so bound the copy to kern_buf.
+	 * *ppos is >= 0 here (checked by the caller), so the
+	 * subtraction below cannot wrap.
+	 */
+	if (*ppos >= image[minor].size_buf)
+		return 0;
+	if (count > image[minor].size_buf - *ppos)
+		count = image[minor].size_buf - *ppos;
+
 	image_ptr = image[minor].kern_buf + *ppos;
 	if (copy_from_user(image_ptr, buf, (unsigned long)count))
 		return -EFAULT;

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

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

From: Shoichiro Miyamoto <[email protected]>

commit 53b7c271f06be4dd5cfc8c6ef552a8355c891a7f upstream.

smb2_check_message() has a long-standing quirk that accepts a response whose calculated length is one byte larger than the bytes actually received ("server can return one byte more due to implied bcc[0]"). This was introduced to accommodate servers that omit the trailing bcc[0] overlap byte when no data area is present.

However, the exemption is applied unconditionally, regardless of whether the command actually carries a data area (has_smb2_data_area[]). When a response with a data area is subject to the +1 exemption, the reported data can extend one byte beyond the bytes actually received, yet smb2_check_message() still accepts it. The subsequent decoder then reads past the end of the receive buffer. This is reachable during NEGOTIATE and SESSION_SETUP, before the session is established.

The resulting out-of-bounds reads are visible under KASAN when mounting against a non-conforming server; both the SPNEGO/negTokenInit and the NTLMSSP challenge decoders are affected:

  BUG: KASAN: slab-out-of-bounds in asn1_ber_decoder+0x16a7/0x1b00
  Read of size 1 at addr ffff8880084d67c0 by task mount.cifs/81
  CPU: 1 UID: 0 PID: 81 Comm: mount.cifs Not tainted 7.1.0-rc6 #1
  Call Trace:
   <TASK>
   dump_stack_lvl+0x4e/0x70
   print_report+0x157/0x4c9
   kasan_report+0xce/0x100
   asn1_ber_decoder+0x16a7/0x1b00
   decode_negTokenInit+0x19/0x30
   SMB2_negotiate+0x31d9/0x4c90
   cifs_negotiate_protocol+0x1f2/0x3f0
   cifs_get_smb_ses+0x93f/0x17e0
   cifs_mount_get_session+0x7f/0x3a0
   cifs_mount+0xb4/0xcf0
   cifs_smb3_do_mount+0x23a/0x1500
   smb3_get_tree+0x3b0/0x630
   vfs_get_tree+0x82/0x2d0
   fc_mount+0x10/0x1b0
   path_mount+0x50d/0x1de0
   __x64_sys_mount+0x20b/0x270
   do_syscall_64+0xee/0x590
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
   </TASK>
  Allocated by task 85:
   kmem_cache_alloc_noprof+0x106/0x380
   mempool_alloc_noprof+0x116/0x1e0
   cifs_small_buf_get+0x31/0x80
   allocate_buffers+0x10d/0x2b0
   cifs_demultiplex_thread+0x1d5/0x1d50
   kthread+0x2c6/0x390
   ret_from_fork+0x36e/0x5a0
   ret_from_fork_asm+0x1a/0x30
  The buggy address is located 0 bytes to the right of
   allocated 448-byte region [ffff8880084d6600, ffff8880084d67c0)
   which belongs to the cache cifs_small_rq of size 448

  BUG: KASAN: slab-out-of-bounds in kmemdup_noprof+0x36/0x50
  Read of size 329 at addr ffff88800726c678 by task mount.cifs/89
  CPU: 0 UID: 0 PID: 89 Comm: mount.cifs Tainted: G    B      7.1.0-rc6 #1
  Call Trace:
   <TASK>
   dump_stack_lvl+0x4e/0x70
   print_report+0x157/0x4c9
   kasan_report+0xce/0x100
   kasan_check_range+0x10f/0x1e0
   __asan_memcpy+0x23/0x60
   kmemdup_noprof+0x36/0x50
   decode_ntlmssp_challenge+0x457/0x680
   SMB2_sess_auth_rawntlmssp_negotiate+0x6f0/0xcb0
   SMB2_sess_setup+0x219/0x4f0
   cifs_setup_session+0x248/0xaf0
   cifs_get_smb_ses+0xf79/0x17e0
   cifs_mount_get_session+0x7f/0x3a0
   cifs_mount+0xb4/0xcf0
   cifs_smb3_do_mount+0x23a/0x1500
   smb3_get_tree+0x3b0/0x630
   vfs_get_tree+0x82/0x2d0
   fc_mount+0x10/0x1b0
   path_mount+0x50d/0x1de0
   __x64_sys_mount+0x20b/0x270
   do_syscall_64+0xee/0x590
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
   </TASK>
  Allocated by task 93:
   kmem_cache_alloc_noprof+0x106/0x380
   mempool_alloc_noprof+0x116/0x1e0
   cifs_small_buf_get+0x31/0x80
   allocate_buffers+0x10d/0x2b0
   cifs_demultiplex_thread+0x1d5/0x1d50
   kthread+0x2c6/0x390
   ret_from_fork+0x36e/0x5a0
   ret_from_fork_asm+0x1a/0x30
  The buggy address is located 120 bytes inside of
   allocated 448-byte region [ffff88800726c600, ffff88800726c7c0)
   which belongs to the cache cifs_small_rq of size 448

Restrict the +1 exemption to responses that have no data area, so that it still covers the bcc[0] omission it was meant for. When a data area is present, the +1 discrepancy instead means the reported data length overruns the received buffer, so the response must be rejected.

---
 fs/smb/client/smb2misc.c |   32 ++++++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 6 deletions(-)

@@ -18,6 +18,8 @@
 #include "nterr.h"
 #include "cached_dir.h"
 
+static unsigned int __smb2_calc_size(void *buf, bool *have_data);
+
 static int
 check_smb2_hdr(struct smb2_hdr *shdr, __u64 mid)
 {

@@ -143,6 +145,7 @@ smb2_check_message(char *buf, unsigned i
 	int command;
 	__u32 calc_len; /* calculated length */
 	__u64 mid;
+	bool have_data;
 
 	/* If server is a channel, select the primary channel */
 	pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;

@@ -226,7 +229,8 @@ smb2_check_message(char *buf, unsigned i
 		}
 	}
 
-	calc_len = smb2_calc_size(buf);
+	have_data = false;
+	calc_len = __smb2_calc_size(buf, &have_data);
 
 	/* For SMB2_IOCTL, OutputOffset and OutputLength are optional, so might
 	 * be 0, and not a real miscalculation */

@@ -245,8 +249,13 @@ smb2_check_message(char *buf, unsigned i
 		/* Windows 7 server returns 24 bytes more */
 		if (calc_len + 24 == len && command == SMB2_OPLOCK_BREAK_HE)
 			return 0;
-		/* server can return one byte more due to implied bcc[0] */
-		if (calc_len == len + 1)
+		/*
+		 * Server can return one byte more due to implied bcc[0].
+		 * Allow it only when there is no data area; if data_length > 0
+		 * the +1 gap indicates an overreported data length rather than
+		 * the bcc[0] omission.
+		 */
+		if (calc_len == len + 1 && !have_data)
 			return 0;
 
 		/*

@@ -407,14 +416,17 @@ smb2_get_data_area_len(int *off, int *le
 /*
  * Calculate the size of the SMB message based on the fixed header
  * portion, the number of word parameters and the data portion of the message.
+ * If have_data is non-NULL, it is set to true when a non-empty data area was
+ * found (data_length > 0), allowing callers to distinguish the implied bcc[0]
+ * case (no data area) from an overreported data length.
  */
-unsigned int
-smb2_calc_size(void *buf)
+static unsigned int
+__smb2_calc_size(void *buf, bool *have_data)
 {
 	struct smb2_pdu *pdu = buf;
 	struct smb2_hdr *shdr = &pdu->hdr;
 	int offset; /* the offset from the beginning of SMB to data area */
-	int data_length; /* the length of the variable length data area */
+	int data_length = 0; /* the length of the variable length data area */
 	/* Structure Size has already been checked to make sure it is 64 */
 	int len = le16_to_cpu(shdr->StructureSize);
 

@@ -447,9 +459,17 @@ smb2_calc_size(void *buf)
 	}
 calc_size_exit:
 	cifs_dbg(FYI, "SMB2 len %d\n", len);
+	if (have_data)
+		*have_data = (data_length > 0);
 	return len;
 }
 
+unsigned int
+smb2_calc_size(void *buf)
+{
+	return __smb2_calc_size(buf, NULL);
+}
+
 /* Note: caller must free return buffer */
 __le16 *
 cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)

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

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

From: Hao-Qun Huang <[email protected]>

commit e8422d89e8af41d87f0e9db564be8e2634f4c602 upstream.

fake_init() allocates a location monitor resource and links it into fake_bridge->lm_resources. The init error path frees this list, but fake_exit() only frees the slave and master resource lists. Loading and unloading the module therefore triggers a kmemleak warning:

unreferenced object 0xffff8b8b82aebe40 (size 64):

    comm "init", pid 1, jiffies 4294894572
    backtrace (crc c1e013ef):
      kmemleak_alloc+0x4e/0x90
      __kmalloc_cache_noprof+0x338/0x430
      0xffffffffc0602246
      do_one_initcall+0x4f/0x320
      do_init_module+0x68/0x270
      load_module+0x2a3b/0x2d90

Free the lm_resources list in fake_exit() as well, before fake_bridge is freed.

---
 drivers/staging/vme_user/vme_fake.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -1253,6 +1253,7 @@ static void __exit fake_exit(void)
 {
 	struct list_head *pos = NULL;
 	struct list_head *tmplist;
+	struct vme_lm_resource *lm;
 	struct vme_master_resource *master_image;
 	struct vme_slave_resource *slave_image;
 	int i;

@@ -1283,6 +1284,13 @@ static void __exit fake_exit(void)
 
 	fake_crcsr_exit(fake_bridge);
 	/* resources are stored in link list */
+	list_for_each_safe(pos, tmplist, &fake_bridge->lm_resources) {
+		lm = list_entry(pos, struct vme_lm_resource, list);
+		list_del(pos);
+		kfree(lm);
+	}
+
+	/* resources are stored in link list */
 	list_for_each_safe(pos, tmplist, &fake_bridge->slave_resources) {
 		slave_image = list_entry(pos, struct vme_slave_resource, list);
 		list_del(pos);

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

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

From: Hao-Qun Huang <[email protected]>

commit 151edde741f8bc7f2931c5f44ab376d32b0c8beb upstream.

tsi148_probe() allocates a location monitor resource and links it into tsi148_bridge->lm_resources. The probe error path frees this list, but tsi148_remove() only frees the dma, slave and master resource lists, so the location monitor resource is leaked on device unbind or module unload.

Free the lm_resources list in tsi148_remove() as well, before tsi148_bridge is freed.

---
 drivers/staging/vme_user/vme_tsi148.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -2548,6 +2548,7 @@ static void tsi148_remove(struct pci_dev
 {
 	struct list_head *pos = NULL;
 	struct list_head *tmplist;
+	struct vme_lm_resource *lm;
 	struct vme_master_resource *master_image;
 	struct vme_slave_resource *slave_image;
 	struct vme_dma_resource *dma_ctrlr;

@@ -2606,6 +2607,13 @@ static void tsi148_remove(struct pci_dev
 	tsi148_crcsr_exit(tsi148_bridge, pdev);
 
 	/* resources are stored in link list */
+	list_for_each_safe(pos, tmplist, &tsi148_bridge->lm_resources) {
+		lm = list_entry(pos, struct vme_lm_resource, list);
+		list_del(pos);
+		kfree(lm);
+	}
+
+	/* resources are stored in link list */
 	list_for_each_safe(pos, tmplist, &tsi148_bridge->dma_resources) {
 		dma_ctrlr = list_entry(pos, struct vme_dma_resource, list);
 		list_del(pos);

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

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

From: Ricardo Ribalda <[email protected]>

commit c32fe4c4918c9aa49f61359e3b42619c4d8686de upstream.

If the driver's stripe information is invalid it can result in an integer underflow. Add a range check to avoid this kind of error.

This patch fixes the following smatch error:
drivers/staging/media/ipu3/ipu3-css-params.c:1792 imgu_css_cfg_acc_stripe() warn: 'acc->stripe.bds_out_stripes[0]->width - 2 * f' 4294967168 can't fit into 65535 'acc->stripe.bds_out_stripes[1]->offset'

---
 drivers/staging/media/ipu3/ipu3-css-params.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

@@ -1770,6 +1770,8 @@ static int imgu_css_cfg_acc_stripe(struc
 		acc->stripe.bds_out_stripes[0].width =
 			ALIGN(css_pipe->rect[IPU3_CSS_RECT_BDS].width, f);
 	} else {
+		u32 offset;
+
 		/* Image processing is divided into two stripes */
 		acc->stripe.bds_out_stripes[0].width =
 			acc->stripe.bds_out_stripes[1].width =

@@ -1788,8 +1790,10 @@ static int imgu_css_cfg_acc_stripe(struc
 			acc->stripe.bds_out_stripes[1].width += f;
 		}
 		/* Overlap between stripes is IPU3_UAPI_ISP_VEC_ELEMS * 4 */
-		acc->stripe.bds_out_stripes[1].offset =
-			acc->stripe.bds_out_stripes[0].width - 2 * f;
+		offset = acc->stripe.bds_out_stripes[0].width - 2 * f;
+		if (offset > 65535)
+			return -EINVAL;
+		acc->stripe.bds_out_stripes[1].offset = offset;
 	}
 
 	acc->stripe.effective_stripes[0].height =

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

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

From: Arnd Bergmann <[email protected]>

commit f4d51e55dd47ef467fbe37d8575e20eee41b092d upstream.

The load_primary_binaries() function is overly complex and has som large variables on the stack, which can cause warnings depending on CONFIG_FRAME_WARN setting:

drivers/staging/media/atomisp/pci/sh_css.c: In function 'load_primary_binaries':
drivers/staging/media/atomisp/pci/sh_css.c:5260:1: error: the frame size of 1560 bytes is larger than 1536 bytes [-Werror=frame-larger-than=]

Half of the stack usage is for the prim_descr[] array, but only one member of the array is used at any given time.

Reduce the stack usage by turning the array into a single structure.

---
 drivers/staging/media/atomisp/pci/sh_css.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -5464,7 +5464,6 @@ static int load_primary_binaries(
 	struct ia_css_capture_settings *mycs;
 	unsigned int i;
 	bool need_extra_yuv_scaler = false;
-	struct ia_css_binary_descr prim_descr[MAX_NUM_PRIMARY_STAGES];
 
 	IA_CSS_ENTER_PRIVATE("");
 	assert(pipe);

@@ -5637,15 +5636,16 @@ static int load_primary_binaries(
 
 	/* Primary */
 	for (i = 0; i < mycs->num_primary_stage; i++) {
+		struct ia_css_binary_descr prim_descr;
 		struct ia_css_frame_info *local_vf_info = NULL;
 
 		if (pipe->enable_viewfinder[IA_CSS_PIPE_OUTPUT_STAGE_0] &&
 		    (i == mycs->num_primary_stage - 1))
 			local_vf_info = &vf_info;
-		ia_css_pipe_get_primary_binarydesc(pipe, &prim_descr[i],
+		ia_css_pipe_get_primary_binarydesc(pipe, &prim_descr,
 						   &prim_in_info, &prim_out_info,
 						   local_vf_info, i);
-		err = ia_css_binary_find(&prim_descr[i], &mycs->primary_binary[i]);
+		err = ia_css_binary_find(&prim_descr, &mycs->primary_binary[i]);
 		if (err) {
 			IA_CSS_LEAVE_ERR_PRIVATE(err);
 			return err;

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

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

From: Alexandru Hossu <[email protected]>

commit a1fc19d61f661d47204f095b593de507884849f7 upstream.

OnAuth() has two bugs in the shared-key authentication path.

When the Privacy bit is set, rtw_wep_decrypt() is called without verifying that the frame is long enough to contain a valid WEP IV and ICV. Inside rtw_wep_decrypt(), length is computed as:

length = len - WLAN_HDR_A3_LEN - iv_len

and then passed as (length - 4) to crc32_le(). If len is less than WLAN_HDR_A3_LEN + iv_len + icv_len (32 bytes), length - 4 is negative and, after the implicit cast to size_t, causes crc32_le() to read far beyond the frame buffer. Add a minimum length check before accessing the IV field and calling the decryption path.

When processing a seq=3 response, rtw_get_ie() stores the Challenge Text IE length in ie_len, but the subsequent memcmp() always reads 128 bytes regardless of ie_len. IEEE 802.11 mandates a challenge text of exactly 128 bytes; reject any IE whose length field differs, matching the check already applied to OnAuthClient().

---
 drivers/staging/rtl8723bs/core/rtw_mlme_ext.c |    8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

@@ -697,6 +697,9 @@ unsigned int OnAuth(struct adapter *pada
 	if ((pmlmeinfo->state&0x03) != WIFI_FW_AP_STATE)
 		return _FAIL;
 
+	if (len < WLAN_HDR_A3_LEN)
+		return _FAIL;
+
 	sa = GetAddr2Ptr(pframe);
 
 	auth_mode = psecuritypriv->dot11AuthAlgrthm;

@@ -708,6 +711,9 @@ unsigned int OnAuth(struct adapter *pada
 		prxattrib->hdrlen = WLAN_HDR_A3_LEN;
 		prxattrib->encrypt = _WEP40_;
 
+		if (len < WLAN_HDR_A3_LEN + 8)
+			return _FAIL;
+
 		iv = pframe+prxattrib->hdrlen;
 		prxattrib->key_index = ((iv[3]>>6)&0x3);
 

@@ -812,7 +818,7 @@ unsigned int OnAuth(struct adapter *pada
 			p = rtw_get_ie(pframe + WLAN_HDR_A3_LEN + 4 + _AUTH_IE_OFFSET_, WLAN_EID_CHALLENGE, (int *)&ie_len,
 					len - WLAN_HDR_A3_LEN - _AUTH_IE_OFFSET_ - 4);
 
-			if (!p || ie_len <= 0) {
+			if (!p || ie_len != 128) {
 				status = WLAN_STATUS_CHALLENGE_FAIL;
 				goto auth_fail;
 			}

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

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

From: Alexandru Hossu <[email protected]>

commit f9654207e92283e0acac5d64fe5f8835383b5a23 upstream.

The IE parsing loop in OnAssocRsp() advances by (pIE->length + 2) each iteration but only guards on i < pkt_len. When a malicious AP sends an AssocResponse whose last IE has only one byte remaining in the frame (the element_id byte lands at pkt_len-1), the loop reads pIE->length from pframe[pkt_len], which is one byte past the allocated receive buffer.

Additionally, even when the header bytes are in bounds, pIE->length itself can extend the data window beyond pkt_len, silently passing a truncated IE to the handler functions.

Add two guards at the top of the loop body:
1. Break if fewer than sizeof(*pIE) bytes remain (can't read header).
2. Break if the IE's declared data extends past pkt_len.

---
 drivers/staging/rtl8723bs/core/rtw_mlme_ext.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -1427,7 +1427,11 @@ unsigned int OnAssocRsp(struct adapter *
 	/* to handle HT, WMM, rate adaptive, update MAC reg */
 	/* for not to handle the synchronous IO in the tasklet */
 	for (i = (6 + WLAN_HDR_A3_LEN); i < pkt_len;) {
+		if (i + sizeof(*pIE) > pkt_len)
+			break;
 		pIE = (struct ndis_80211_var_ie *)(pframe + i);
+		if (i + sizeof(*pIE) + pIE->length > pkt_len)
+			break;
 
 		switch (pIE->element_id) {
 		case WLAN_EID_VENDOR_SPECIFIC:

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

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

From: Alexandru Hossu <[email protected]>

commit ed51de4a86e173c3b0ef78e039c2e49e08b11f16 upstream.

The IE parsing loop in update_beacon_info() advances by (pIE->length + 2) each iteration but only guards on i < len. When a malicious AP sends a Beacon whose last IE has only one byte remaining in the frame (the element_id byte lands at len-1), the loop reads pIE->length from one byte past the allocated receive buffer.

Additionally, even when the header bytes are in bounds, pIE->length itself can extend the data window beyond len, passing a truncated IE to the handler functions.

Add two guards at the top of the loop body:
1. Break if fewer than sizeof(*pIE) bytes remain (can't read header).
2. Break if the IE's declared data extends past len.

Also replace i += (pIE->length + 2) with i += sizeof(*pIE) + pIE->length for consistency with the sizeof(*pIE) guards added above.

---
 drivers/staging/rtl8723bs/core/rtw_wlan_util.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -1336,7 +1336,11 @@ void update_beacon_info(struct adapter *
 	len = pkt_len - (_BEACON_IE_OFFSET_ + WLAN_HDR_A3_LEN);
 
 	for (i = 0; i < len;) {
+		if (i + sizeof(*pIE) > len)
+			break;
 		pIE = (struct ndis_80211_var_ie *)(pframe + (_BEACON_IE_OFFSET_ + WLAN_HDR_A3_LEN) + i);
+		if (i + sizeof(*pIE) + pIE->length > len)
+			break;
 
 		switch (pIE->element_id) {
 		case WLAN_EID_VENDOR_SPECIFIC:

@@ -1361,7 +1365,7 @@ void update_beacon_info(struct adapter *
 			break;
 		}
 
-		i += (pIE->length + 2);
+		i += sizeof(*pIE) + pIE->length;
 	}
 }
 

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

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

From: Alexandru Hossu <[email protected]>

commit ef61d628dfad38fead1fd2e08979ae9126d011d5 upstream.

Two IE parsing loops are missing the header bounds checks before they dereference pIE->length:

- issue_assocreq() walks pmlmeinfo->network.ies to build the association request. If the stored IE data ends with only an element_id byte and no length byte, pIE->length is read one byte past the end of the buffer.

- join_cmd_hdl() walks pnetwork->ies during station join and has the same problem under the same conditions.

Both buffers are filled from AP beacon and probe-response frames, so a malicious AP that sends a truncated final IE can trigger the issue.

Apply the two-guard pattern established in update_beacon_info():
1. Break if fewer than sizeof(*pIE) bytes remain.
2. Break if the IE's declared data extends past the buffer end.

---
 drivers/staging/rtl8723bs/core/rtw_mlme_ext.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -2968,7 +2968,11 @@ void issue_assocreq(struct adapter *pada
 
 	/* vendor specific IE, such as WPA, WMM, WPS */
 	for (i = sizeof(struct ndis_802_11_fix_ie); i < pmlmeinfo->network.ie_length;) {
+		if (i + sizeof(*pIE) > pmlmeinfo->network.ie_length)
+			break;
 		pIE = (struct ndis_80211_var_ie *)(pmlmeinfo->network.ies + i);
+		if (i + sizeof(*pIE) + pIE->length > pmlmeinfo->network.ie_length)
+			break;
 
 		switch (pIE->element_id) {
 		case WLAN_EID_VENDOR_SPECIFIC:

@@ -5373,7 +5377,11 @@ u8 join_cmd_hdl(struct adapter *padapter
 
 	/* sizeof(struct ndis_802_11_fix_ie) */
 	for (i = _FIXED_IE_LENGTH_; i < pnetwork->ie_length;) {
+		if (i + sizeof(*pIE) > pnetwork->ie_length)
+			break;
 		pIE = (struct ndis_80211_var_ie *)(pnetwork->ies + i);
+		if (i + sizeof(*pIE) + pIE->length > pnetwork->ie_length)
+			break;
 
 		switch (pIE->element_id) {
 		case WLAN_EID_VENDOR_SPECIFIC:/* Get WMM IE. */

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

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

From: Alexandru Hossu <[email protected]>

commit 3bf39f711ff27c64be8680a8938bcc5001982e81 upstream.

The loop in is_ap_in_tkip() iterates over IEs without verifying that enough bytes remain before dereferencing the IE header or its payload:

- pIE->element_id and pIE->length are read without checking that i + sizeof(*pIE) <= ie_length, so a truncated IE at the end of the buffer causes an OOB read.

- For WLAN_EID_VENDOR_SPECIFIC the code compares pIE->data + 12, which requires pIE->length >= 16. For WLAN_EID_RSN it compares pIE->data + 8, requiring pIE->length >= 12. Neither requirement is checked.

Add the missing IE header and payload bounds checks and guard each data access with an explicit pIE->length minimum, matching the pattern established in update_beacon_info().

---
 drivers/staging/rtl8723bs/core/rtw_wlan_util.c |   14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

@@ -1381,15 +1381,23 @@ unsigned int is_ap_in_tkip(struct adapte
 		for (i = sizeof(struct ndis_802_11_fix_ie); i < pmlmeinfo->network.ie_length;) {
 			pIE = (struct ndis_80211_var_ie *)(pmlmeinfo->network.ies + i);
 
+			if (i + sizeof(*pIE) > pmlmeinfo->network.ie_length)
+				break;
+			if (i + sizeof(*pIE) + pIE->length > pmlmeinfo->network.ie_length)
+				break;
+
 			switch (pIE->element_id) {
 			case WLAN_EID_VENDOR_SPECIFIC:
-				if ((!memcmp(pIE->data, RTW_WPA_OUI, 4)) && (!memcmp((pIE->data + 12), WPA_TKIP_CIPHER, 4)))
+				if (pIE->length >= 16 &&
+				    !memcmp(pIE->data, RTW_WPA_OUI, 4) &&
+				    !memcmp((pIE->data + 12), WPA_TKIP_CIPHER, 4))
 					return true;
 
 				break;
 
 			case WLAN_EID_RSN:
-				if (!memcmp((pIE->data + 8), RSN_TKIP_CIPHER, 4))
+				if (pIE->length >= 12 &&
+				    !memcmp((pIE->data + 8), RSN_TKIP_CIPHER, 4))
 					return true;
 				break;
 

@@ -1397,7 +1405,7 @@ unsigned int is_ap_in_tkip(struct adapte
 				break;
 			}
 
-			i += (pIE->length + 2);
+			i += sizeof(*pIE) + pIE->length;
 		}
 
 		return false;

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

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

From: Alexandru Hossu <[email protected]>

commit f8001e1a516ba3b495728c65b61f799cbfad6bd0 upstream.

HT_caps_handler() iterates pIE->length bytes and writes into HT_caps.u.HT_cap[], which is a fixed 26-byte array (sizeof struct HT_caps_element). Because pIE->length is a raw u8 from an over-the-air 802.11 AssocResponse frame and is never validated, a malicious AP can set it up to 255, causing up to 229 bytes of out-of-bounds writes into adjacent fields of struct mlme_ext_info.

Truncate the iteration count to the size of HT_caps.u.HT_cap using umin() so that data from a longer-than-expected IE is silently ignored rather than written out of bounds, preserving interoperability with APs that pad the element. An early return on oversized IEs was considered but rejected: it would bypass the pmlmeinfo->HT_caps_enable = 1 assignment that precedes the loop, silently disabling HT mode for APs that append extra bytes to the HT Capabilities IE.

---
 drivers/staging/rtl8723bs/core/rtw_wlan_util.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -979,7 +979,8 @@ void HT_caps_handler(struct adapter *pad
 
 	pmlmeinfo->HT_caps_enable = 1;
 
-	for (i = 0; i < (pIE->length); i++) {
+	for (i = 0; i < umin(pIE->length,
+			     sizeof(pmlmeinfo->HT_caps.u.HT_cap)); i++) {
 		if (i != 2) {
 			/* Commented by Albert 2010/07/12 */
 			/* Got the endian issue here. */

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

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

From: Dawei Feng <[email protected]>

commit 6d827ade51a24e18d81afb9f32756d339520a14c upstream.

When meson_allocate_chanlist() fails after a partial allocation, it already unwinds the allocated chanlist state through its local error path. meson_crypto_probe() then jump to error_flow and calls meson_free_chanlist() again, causing the same per-flow resources to be torn down twice. In the reproduced failure path, the second teardown re-entered crypto_engine_exit() on an already destroyed worker and KASAN reported a slab-use-after-free in kthread_destroy_worker().

Prevent double-free by handling partial allocation failures locally within meson_allocate_chanlist() and skipping the outer cleanup path.

The bug was first flagged by an experimental analysis tool we are developing for kernel memory-management bugs while analyzing v6.13-rc1. The tool is still under development and is not yet publicly available.

The bug was reproduced in a QEMU x86_64 guest booted with KASAN on v7.1, using the reproducer under tools/testing/meson_crypto_probe. The reproducer forces the second dma_alloc_attrs() call in the gxl-crypto probe path to return NULL, making meson_allocate_chanlist() fail after partial initialization. On the unpatched kernel this reliably triggered a slab-use-after-free. With this fix applied, the same reproducer no longer emits any KASAN report and the probe fails cleanly with -ENOMEM.

    ==================================================================
    BUG: KASAN: slab-use-after-free in kthread_destroy_worker+0xb2/0xd0
    Read of size 8 at addr ff1100010c057a68 by task insmod/265

    CPU: 1 UID: 0 PID: 265 Comm: insmod Tainted: G           O        7.1.0-rc2-00376-g810af9adc907-dirty #10 PREEMPT(lazy)
    Tainted: [O]=OOT_MODULE
    Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014
    Call Trace:
     <TASK>
     dump_stack_lvl+0x68/0xa0
     print_report+0xcb/0x5e0
     ? __virt_addr_valid+0x21d/0x3f0
     ? kthread_destroy_worker+0xb2/0xd0
     ? kthread_destroy_worker+0xb2/0xd0
     kasan_report+0xca/0x100
     ? kthread_destroy_worker+0xb2/0xd0
     kthread_destroy_worker+0xb2/0xd0
     meson_crypto_probe+0x4d0/0xc10 [amlogic_gxl_crypto]
     platform_probe+0x99/0x140
     really_probe+0x1c6/0x6a0
     ? __pfx___device_attach_driver+0x10/0x10
     __driver_probe_device+0x248/0x310
     ? acpi_driver_match_device+0xb0/0x100
     driver_probe_device+0x48/0x210
     ? __pfx___device_attach_driver+0x10/0x10
     __device_attach_driver+0x160/0x320
     bus_for_each_drv+0x104/0x190
     ? __pfx_bus_for_each_drv+0x10/0x10
     ? _raw_spin_unlock_irqrestore+0x2c/0x50
     __device_attach+0x19d/0x3b0
     ? __pfx___device_attach+0x10/0x10
     ? do_raw_spin_unlock+0x53/0x220
     device_initial_probe+0x78/0xa0
     bus_probe_device+0x5b/0x130
     device_add+0xcfd/0x1430
     ? __pfx_device_add+0x10/0x10
     ? insert_resource+0x34/0x50
     ? lock_release+0xc9/0x290
     platform_device_add+0x24e/0x590
     ? __pfx_meson_crypto_probe_repro_init+0x10/0x10 [meson_crypto_probe_repro]
     meson_crypto_probe_repro_init+0x330/0xff0 [meson_crypto_probe_repro]
     do_one_initcall+0xc0/0x450
     ? __pfx_do_one_initcall+0x10/0x10
     ? _raw_spin_unlock_irqrestore+0x2c/0x50
     ? __create_object+0x59/0x80
     ? kasan_unpoison+0x27/0x60
     do_init_module+0x27b/0x7d0
     ? __pfx_do_init_module+0x10/0x10
     ? kasan_quarantine_put+0x84/0x1d0
     ? kfree+0x32c/0x510
     ? load_module+0x561e/0x5ff0
     load_module+0x54fe/0x5ff0
     ? __pfx_load_module+0x10/0x10
     ? security_file_permission+0x20/0x40
     ? kernel_read_file+0x23d/0x6e0
     ? mmap_region+0x235/0x4a0
     ? __pfx_kernel_read_file+0x10/0x10
     ? __file_has_perm+0x2c0/0x3e0
     init_module_from_file+0x158/0x180
     ? __pfx_init_module_from_file+0x10/0x10
     ? __lock_acquire+0x45a/0x1ba0
     ? idempotent_init_module+0x315/0x610
     ? lock_release+0xc9/0x290
     ? lockdep_init_map_type+0x4b/0x220
     ? do_raw_spin_unlock+0x53/0x220
     idempotent_init_module+0x330/0x610
     ? __pfx_idempotent_init_module+0x10/0x10
     ? __pfx_cred_has_capability.isra.0+0x10/0x10
     ? ksys_mmap_pgoff+0x385/0x520
     __x64_sys_finit_module+0xbe/0x120
     do_syscall_64+0x115/0x690
     entry_SYSCALL_64_after_hwframe+0x77/0x7f
    RIP: 0033:0x7f7d6d31690d
    Code: 5b 41 5c c3 66 0f 1f 84 00 00 00 00 00 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 8b 0d f3 b4 0f 00 f7 d8 >
    RSP: 002b:00007fffc027ac68 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
    RAX: ffffffffffffffda RBX: 000055f7b81967c0 RCX: 00007f7d6d31690d
    RDX: 0000000000000000 RSI: 000055f79a0d6cd2 RDI: 0000000000000003
    RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
    R10: 0000000000000003 R11: 0000000000000246 R12: 000055f79a0d6cd2
    R13: 000055f7b8196790 R14: 000055f79a0d5888 R15: 000055f7b81968e0
     </TASK>

---
 drivers/crypto/amlogic/amlogic-gxl-core.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -272,8 +272,8 @@ static int meson_crypto_probe(struct pla
 	return 0;
 error_alg:
 	meson_unregister_algs(mc);
-error_flow:
 	meson_free_chanlist(mc, MAXFLOW - 1);
+error_flow:
 	clk_disable_unprepare(mc->busclk);
 	return err;
 }

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

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

From: Gil Portnoy <[email protected]>

commit 10f293a07f9e10e988b0ae44e2e99c631f5a68e0 upstream.

Commit f580d27e8928 ("ksmbd: fix use-after-free of a deferred file_lock on double SMB2_CANCEL") made smb2_cancel() skip a work whose state is KSMBD_WORK_CANCELLED, so its cancel_fn cannot be fired a second time. But KSMBD_WORK has three states (ACTIVE, CANCELLED, CLOSED), and the same freeing producer path is reached for CLOSED too:

SMB2_CLOSE on the locking handle -> set_close_state_blocked_works() sets the deferred work's state to KSMBD_WORK_CLOSED and wakes the smb2_lock() worker. The worker takes the non-ACTIVE early-exit, locks_free_lock()s the file_lock and, because the state is not KSMBD_WORK_CANCELLED, takes the STATUS_RANGE_NOT_LOCKED branch with "goto out2" -- which, like the cancelled branch, skips release_async_work(). The work stays on conn->async_requests with a live cancel_fn = smb2_remove_blocked_lock pointing at the freed file_lock.

A subsequent SMB2_CANCEL for the same AsyncId then passes the KSMBD_WORK_CANCELLED-only guard (its state is KSMBD_WORK_CLOSED), so smb2_cancel() fires cancel_fn again over the freed file_lock -- the same use-after-free fixed, via SMB2_CLOSE instead of a first SMB2_CANCEL:

  BUG: KASAN: slab-use-after-free in __locks_delete_block
    __locks_delete_block
    locks_delete_block
    ksmbd_vfs_posix_lock_unblock
    smb2_remove_blocked_lock
    smb2_cancel                 <- 2nd SMB2_CANCEL fires cancel_fn
    handle_ksmbd_work
  Allocated by ...: locks_alloc_lock <- smb2_lock
  Freed by ...:     locks_free_lock  <- smb2_lock (non-ACTIVE early-exit)
  ... cache file_lock_cache of size 192

Reproduced on mainline 7.1-rc7 (which already contains f580d27e8928) with KASAN by an authenticated SMB client; the double-SMB2_CANCEL control is silent on that kernel, so the splat is attributable to the CLOSE trigger.

Only an ACTIVE deferred work may have its cancel_fn fired: both terminal states (CANCELLED and CLOSED) reach the smb2_lock() early-exit that frees the file_lock and skips release_async_work(). Guard on KSMBD_WORK_ACTIVE so any non-active work is skipped.

---
 fs/smb/server/smb2pdu.c |   14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

@@ -6816,14 +6816,14 @@ int smb2_cancel(struct ksmbd_work *work)
 				continue;
 
 			/*
-			 * A cancelled deferred byte-range lock frees its
-			 * file_lock and takes the smb2_lock() early-exit that
-			 * skips release_async_work(), so the work stays on
-			 * conn->async_requests with a live cancel_fn pointing
-			 * at the freed file_lock.  Re-firing it on a second
-			 * SMB2_CANCEL is a use-after-free.
+			 * Only an ACTIVE deferred work may have its cancel_fn
+			 * fired.  A CANCELLED or CLOSED work already took the
+			 * smb2_lock() non-ACTIVE early-exit that frees the
+			 * file_lock and skips release_async_work(), so it is
+			 * still on conn->async_requests with a live cancel_fn
+			 * pointing at the freed file_lock.
 			 */
-			if (iter->state == KSMBD_WORK_CANCELLED)
+			if (iter->state != KSMBD_WORK_ACTIVE)
 				break;
 
 			ksmbd_debug(SMB,

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

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

From: Zijing Yin <[email protected]>

commit d129c3177d7b1138fd5066fcc63a698b3ba415b0 upstream.

pfkey_msg2xfrm_state() handles the IPComp (SADB_X_SATYPE_IPCOMP) case by allocating x->calg and copying only the algorithm name:

	x->calg = kmalloc_obj(*x->calg);
	if (!x->calg) {
		err = -ENOMEM;
		goto out;
	}
	strcpy(x->calg->alg_name, a->name);
	x->props.calgo = sa->sadb_sa_encrypt;

Unlike the authentication (x->aalg) and encryption (x->ealg) branches of the same function, the compression branch never initializes calg->alg_key_len. IPComp carries no key and the allocation only reserves sizeof(struct xfrm_algo) (i.e. no room for a key), so the field is left containing uninitialized slab data.

calg->alg_key_len is later used as a length by xfrm_algo_clone() when an IPComp state is cloned during XFRM_MSG_MIGRATE:

	xfrm_state_migrate()
	  xfrm_state_clone_and_setup()
	    x->calg = xfrm_algo_clone(orig->calg);
	      kmemdup(orig, xfrm_alg_len(orig));

where xfrm_alg_len() returns sizeof(*alg) + (alg_key_len + 7) / 8. With a non-zero garbage alg_key_len, kmemdup() reads past the end of the 68-byte calg object. Adding an IPComp SA via PF_KEY and then migrating it triggers (net-next, KASAN, init_on_alloc=0):

  BUG: KASAN: slab-out-of-bounds in kmemdup_noprof+0x44/0x60
  Read of size 4164 at addr ff11000025a74980 by task diag2/9287
  CPU: 3 UID: 0 PID: 9287 Comm: diag2 7.1.0-rc6-g903db046d557 #1
  Call Trace:
   <TASK>
   dump_stack_lvl+0x10e/0x1f0
   print_report+0xf7/0x600
   kasan_report+0xe4/0x120
   kasan_check_range+0x105/0x1b0
   __asan_memcpy+0x23/0x60
   kmemdup_noprof+0x44/0x60
   xfrm_state_migrate+0x70a/0x1da0
   xfrm_migrate+0x753/0x18a0
   xfrm_do_migrate+0xb47/0xf10
   xfrm_user_rcv_msg+0x411/0xb50
   netlink_rcv_skb+0x158/0x420
   xfrm_netlink_rcv+0x71/0x90
   netlink_unicast+0x584/0x850
   netlink_sendmsg+0x8b0/0xdc0
   ____sys_sendmsg+0x9f7/0xb90
   ___sys_sendmsg+0x134/0x1d0
   __sys_sendmsg+0x16d/0x220
   do_syscall_64+0x116/0x7d0
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
   </TASK>

  Allocated by task 9287:
   kasan_save_stack+0x33/0x60
   kasan_save_track+0x14/0x30
   __kasan_kmalloc+0xaa/0xb0
   pfkey_add+0x2652/0x2ea0
   pfkey_process+0x6d0/0x830
   pfkey_sendmsg+0x42c/0x850
   __sys_sendto+0x461/0x4b0
   __x64_sys_sendto+0xe0/0x1c0
   do_syscall_64+0x116/0x7d0
   entry_SYSCALL_64_after_hwframe+0x77/0x7f

  The buggy address belongs to the object at ff11000025a74980
   which belongs to the cache kmalloc-96 of size 96
  The buggy address is located 0 bytes inside of
   allocated 68-byte region [ff11000025a74980, ff11000025a749c4)

Depending on the uninitialized value the same field can instead request an oversized kmemdup() allocation and make the migration clone fail.

The XFRM netlink path is not affected: verify_one_alg() rejects an XFRMA_ALG_COMP attribute shorter than xfrm_alg_len(), so a calg added via XFRM_MSG_NEWSA is always self-consistent.

Initialize calg->alg_key_len to 0, matching the aalg/ealg branches.

---
 net/key/af_key.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1202,6 +1202,7 @@ static struct xfrm_state * pfkey_msg2xfr
 				goto out;
 			}
 			strcpy(x->calg->alg_name, a->name);
+			x->calg->alg_key_len = 0;
 			x->props.calgo = sa->sadb_sa_encrypt;
 		} else {
 			int keysize = 0;

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

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

From: Chi Wang <[email protected]>

commit c9a71daaecb2fb1d8c704545cc0b1c920b9bf5d7 upstream.

Multiple readers access audit_queue.qlen via skb_queue_len() without holding the queue lock or using READ_ONCE(), while kauditd writes to this field via the skb_dequeue() → __skb_unlink() path with WRITE_ONCE() protected by a spinlock. This constitutes data races.

All affected skb_queue_len(&audit_queue) call sites:
- kauditd_thread() wait_event_freezable() condition
- audit_receive_msg() AUDIT_GET handler (s.backlog assignment)
- audit_receive() backlog check
- audit_log_start() backlog check and pr_warn()

KCSAN reports the following conflicting access pattern (one example):
==================================================================

BUG: KCSAN: data-race in audit_log_start / skb_dequeue

write (marked) to 0xffffffff8512ee20 of 4 bytes by task 661 on cpu 57:

 skb_dequeue+0x70/0xf0
 kauditd_send_queue+0x71/0x220
 kauditd_thread+0x1cb/0x430
 kthread+0x1c2/0x210
 ret_from_fork+0x162/0x1a0
 ret_from_fork_asm+0x1a/0x30

read to 0xffffffff8512ee20 of 4 bytes by task 36586 on cpu 1:

 audit_log_start+0x2a0/0x6b0
 audit_core_dumps+0x64/0xa0
 do_coredump+0x14b/0x1260
 get_signal+0xeb2/0xf70
 arch_do_signal_or_restart+0x41/0x170
 exit_to_user_mode_loop+0xa2/0x1c0
 do_syscall_64+0x1a3/0x1c0
 entry_SYSCALL_64_after_hwframe+0x76/0xe0

value changed: 0x00000001 -> 0x00000000
==================================================================

Resolve the race by switching to lockless helper skb_queue_len_lockless(), which internally uses READ_ONCE() and properly pairs with the WRITE_ONCE() write accesses already present on the writer side.

---
 kernel/audit.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

@@ -910,7 +910,7 @@ main_queue:
 		 *       do the multicast send and rotate records from the
 		 *       main queue to the retry/hold queues */
 		wait_event_freezable(kauditd_wait,
-				     (skb_queue_len(&audit_queue) ? 1 : 0));
+				(skb_queue_len_lockless(&audit_queue) ? 1 : 0));
 	}
 
 	return 0;

@@ -1245,7 +1245,7 @@ static int audit_receive_msg(struct sk_b
 		s.rate_limit		   = audit_rate_limit;
 		s.backlog_limit		   = audit_backlog_limit;
 		s.lost			   = atomic_read(&audit_lost);
-		s.backlog		   = skb_queue_len(&audit_queue);
+		s.backlog		   = skb_queue_len_lockless(&audit_queue);
 		s.feature_bitmap	   = AUDIT_FEATURE_BITMAP_ALL;
 		s.backlog_wait_time	   = audit_backlog_wait_time;
 		s.backlog_wait_time_actual = atomic_read(&audit_backlog_wait_time_actual);

@@ -1586,7 +1586,7 @@ static void audit_receive(struct sk_buff
 
 	/* can't block with the ctrl lock, so penalize the sender now */
 	if (audit_backlog_limit &&
-	    (skb_queue_len(&audit_queue) > audit_backlog_limit)) {
+	    (skb_queue_len_lockless(&audit_queue) > audit_backlog_limit)) {
 		DECLARE_WAITQUEUE(wait, current);
 
 		/* wake kauditd to try and flush the queue */

@@ -1888,7 +1888,7 @@ struct audit_buffer *audit_log_start(str
 		long stime = audit_backlog_wait_time;
 
 		while (audit_backlog_limit &&
-		       (skb_queue_len(&audit_queue) > audit_backlog_limit)) {
+			(skb_queue_len_lockless(&audit_queue) > audit_backlog_limit)) {
 			/* wake kauditd to try and flush the queue */
 			wake_up_interruptible(&kauditd_wait);
 

@@ -1908,7 +1908,7 @@ struct audit_buffer *audit_log_start(str
 			} else {
 				if (audit_rate_check() && printk_ratelimit())
 					pr_warn("audit_backlog=%d > audit_backlog_limit=%d\n",
-						skb_queue_len(&audit_queue),
+						skb_queue_len_lockless(&audit_queue),
 						audit_backlog_limit);
 				audit_log_lost("backlog limit exceeded");
 				return NULL;

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

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

From: Thomas Gleixner <[email protected]>

commit b81dde13cc163450dcb402dcc915ef13ba241e01 upstream.

syzbot reported a puzzling splat:

   WARNING: kernel/time/hrtimer.c:443 at stub_timer+0xa/0x20

stub_timer() is installed as timer callback function in hrtimer_fixup_assert_init(), which is invoked when debug_object_assert_init() can't find a shadow object. In that case debug objects emits a warning about it before invoking the fixup.

Though the provided console log lacks this warning and instead has the following a few seconds before the splat:

ODEBUG: Out of memory. ODEBUG disabled

So the object was looked up in debug_object_assert_init() and the lookup failed due a concurrent out of memory situation which disabled debug objects and freed the shadow objects:

debug_object_assert_init()

        if (!debug_objects_enabled)
        	return;                         obj = alloc();
                				if (!obj) {
							// Out of memory
                                                	debug_objects_enabled = false;
                                                        free_objects();
        obj = lookup_or_alloc();

        // The lookup failed because the other side
        // removed the objects, so this returns
        // an error code as the object in question
        // is not statically initialized

	if (!IS_ERR_OR_NULL(obj))
        	return;
        if (!obj) {
        	debug_oom();
                return;
        }

        print(...)
           if (!debug_objects_enabled)
                return;

        fixup(...)

The debug object splat is skipped because debug_objects_enabled is false, but the fixup callback is invoked unconditionally, which makes the timer disfunctional.

This is only a problem in debug_object_assert_init() and debug_object_activate() as both have to handle statically initialized objects and therefore must handle the error pointer return case gracefully. All other places only handle the found/not found case and the NULL pointer return is a signal for OOM. Otherwise they get a valid shadow object.

Plug the hole by checking whether debug objects are still enabled before invoking the print and fixup function in those two places.

---
 lib/debugobjects.c |   17 +++++++++++++++++
 1 file changed, 17 insertions(+)

@@ -768,6 +768,14 @@ int debug_object_activate(void *addr, co
 	}
 
 	raw_spin_unlock_irqrestore(&db->lock, flags);
+
+	/*
+	 * lookup_object_or_alloc() might have raced with a concurrent
+	 * allocation failure which disabled debug objects.
+	 */
+	if (!debug_objects_enabled)
+		return 0;
+
 	debug_print_object(&o, "activate");
 
 	switch (o.state) {

@@ -945,6 +953,15 @@ void debug_object_assert_init(void *addr
 		return;
 	}
 
+	/*
+	 * lookup_object_or_alloc() might have raced with a concurrent
+	 * allocation failure which disabled debug objects. Don't run the fixup
+	 * as it might turn a valid object useless. See for example
+	 * hrtimer_fixup_assert_init().
+	 */
+	if (!debug_objects_enabled)
+		return;
+
 	/* Object is neither tracked nor static. It's not initialized. */
 	debug_print_object(&o, "assert_init");
 	debug_object_fixup(descr->fixup_assert_init, addr, ODEBUG_STATE_NOTAVAILABLE);

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

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

From: Yunpeng Tian <[email protected]>

commit 57382ec6ac63b63dce2789e835fded28b698ae79 upstream.

In the analysis pass of $LogFile journal replay, log_replay() copies LCNs from each action log record into an existing Dirty Page Table (DPT) entry without bounding the destination index. A crafted NTFS image with DPT entry lcns_follow=1 and an action log record with lcns_follow=2 produces a kernel slab out-of-bounds write at mount time:

  BUG: KASAN: slab-out-of-bounds in log_replay+0x654c/0xdb60
  Write of size 8 at addr ffff8880095e1040 by task mount

Two attacker-controlled fields can drive j+i past the allocated page_lcns[] array:

1. dp->lcns_follow (capacity) can be smaller than lrh->lcns_follow.
2. lrh->target_vcn may be smaller than dp->vcn, making the u64 subtraction wrap to a huge size_t.

Validate target VCN delta and per-record LCN count against the DPT entry capacity, bail via the existing out: cleanup label with -EINVAL.

This mirrors the bounds-check pattern added in commit b2bc7c44ed17 ("fs/ntfs3: Fix slab-out-of-bounds read in DeleteIndexEntryRoot") and commit 0ca0485e4b2e ("fs/ntfs3: validate rec->used in journal-replay file record check").

---
 fs/ntfs3/fslog.c |   20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

@@ -4546,11 +4546,21 @@ copy_lcns:
 		 * whole routine a loop, case Lcns do not fit below.
 		 */
 		t16 = le16_to_cpu(lrh->lcns_follow);
-		for (i = 0; i < t16; i++) {
-			size_t j = (size_t)(le64_to_cpu(lrh->target_vcn) -
-					    le64_to_cpu(dp->vcn));
-			dp->page_lcns[j + i] = lrh->page_lcns[i];
-		}
+                t32 = le32_to_cpu(dp->lcns_follow);
+                if (le64_to_cpu(lrh->target_vcn) < le64_to_cpu(dp->vcn)) {
+                        err = -EINVAL;
+                        goto out;
+                }
+
+                for (i = 0; i < t16; i++) {
+                        size_t j = (size_t)(le64_to_cpu(lrh->target_vcn) -
+                                            le64_to_cpu(dp->vcn));
+                        if (j >= t32 || i >= t32 - j) {
+                                err = -EINVAL;
+                                goto out;
+                        }
+                        dp->page_lcns[j + i] = lrh->page_lcns[i];
+                }
 
 		goto next_log_record_analyze;
 

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

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

From: Koichiro Den <[email protected]>

commit 4dcddc1c794d1c65eda68f1f8dd04a0fecc0870f upstream.

ntb_epf_vec_isr() calls pci_irq_vector() in hardirq context to derive the vector number. pci_irq_vector() calls msi_get_virq() that takes a mutex and can therefore trigger "scheduling while atomic" splats:

  BUG: scheduling while atomic: kworker/u33:0/55/0x00010001
  ...
  Call trace:
   ...
   schedule+0x38/0x110
   schedule_preempt_disabled+0x28/0x50
   __mutex_lock.constprop.0+0x848/0x908
   __mutex_lock_slowpath+0x18/0x30
   mutex_lock+0x4c/0x60
   msi_domain_get_virq+0xe8/0x138
   pci_irq_vector+0x2c/0x60
   ntb_epf_vec_isr+0x28/0x120 [ntb_hw_epf]
   __handle_irq_event_percpu+0x70/0x3a8
   handle_irq_event+0x48/0x100
   handle_edge_irq+0x100/0x1c8
   ...

Cache the Linux IRQ number for vector 0 when vectors are allocated and use it as a base in the ISR. Running the ISR in a threaded IRQ handler would also avoid the problem, but that would be unnecessary here.

---
 drivers/ntb/hw/epf/ntb_hw_epf.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -92,6 +92,7 @@ struct ntb_epf_dev {
 
 	int db_val;
 	u64 db_valid_mask;
+	int irq_base;
 };
 
 #define ntb_ndev(__ntb) container_of(__ntb, struct ntb_epf_dev, ntb)

@@ -318,7 +319,7 @@ static irqreturn_t ntb_epf_vec_isr(int i
 	struct ntb_epf_dev *ndev = dev;
 	int irq_no;
 
-	irq_no = irq - pci_irq_vector(ndev->ntb.pdev, 0);
+	irq_no = irq - ndev->irq_base;
 	ndev->db_val = irq_no + 1;
 
 	if (irq_no == 0)

@@ -350,6 +351,7 @@ static int ntb_epf_init_isr(struct ntb_e
 		argument &= ~MSIX_ENABLE;
 	}
 
+	ndev->irq_base = pci_irq_vector(pdev, 0);
 	for (i = 0; i < irq; i++) {
 		ret = request_irq(pci_irq_vector(pdev, i), ntb_epf_vec_isr,
 				  0, "ntb_epf", ndev);

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

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

From: Runyu Xiao <[email protected]>

commit 90f0109019e6817eb40a486671b7722d1544ae29 upstream.

sprd_eic_irq_unmask() enables the GPIO IRQ and then updates controller state through sprd_eic_update(), which takes sprd_eic->lock with spin_lock_irqsave(). The callback can be reached from irq_startup() while setting up a requested IRQ. That path is not sleepable, but on PREEMPT_RT a regular spinlock_t becomes a sleeping lock.

This issue was found by our static analysis tool and then manually reviewed against the current tree.

The grounded PoC kept the request_threaded_irq() -> __setup_irq() -> irq_startup() -> sprd_eic_irq_unmask() -> sprd_eic_update() carrier and used the original spin_lock_irqsave(&sprd_eic->lock) edge. Lockdep reported:

  BUG: sleeping function called from invalid context
  hardirqs last disabled at ... __setup_irq.constprop.0 ... [vuln_msv]
  sprd_rt_spin_lock_irqsave+0x1c/0x30 [vuln_msv]
  sprd_eic_update.constprop.0+0x48/0x90 [vuln_msv]
  sprd_eic_irq_unmask.constprop.0+0x35/0x50 [vuln_msv]
  __setup_irq.constprop.0+0xd/0x30 [vuln_msv]

Convert the Spreadtrum EIC controller lock to raw_spinlock_t. The locked section only serializes MMIO register updates and does not contain sleepable operations, so keeping it non-sleeping is appropriate for the irqchip callbacks.

---
 drivers/gpio/gpio-eic-sprd.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -94,7 +94,7 @@ struct sprd_eic {
 	struct irq_chip intc;
 	void __iomem *base[SPRD_EIC_MAX_BANK];
 	enum sprd_eic_type type;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	int irq;
 };
 

@@ -146,7 +146,7 @@ static void sprd_eic_update(struct gpio_
 	unsigned long flags;
 	u32 tmp;
 
-	spin_lock_irqsave(&sprd_eic->lock, flags);
+	raw_spin_lock_irqsave(&sprd_eic->lock, flags);
 	tmp = readl_relaxed(base + reg);
 
 	if (val)

@@ -155,7 +155,7 @@ static void sprd_eic_update(struct gpio_
 		tmp &= ~BIT(SPRD_EIC_BIT(offset));
 
 	writel_relaxed(tmp, base + reg);
-	spin_unlock_irqrestore(&sprd_eic->lock, flags);
+	raw_spin_unlock_irqrestore(&sprd_eic->lock, flags);
 }
 
 static int sprd_eic_read(struct gpio_chip *chip, unsigned int offset, u16 reg)

@@ -606,7 +606,7 @@ static int sprd_eic_probe(struct platfor
 	if (!sprd_eic)
 		return -ENOMEM;
 
-	spin_lock_init(&sprd_eic->lock);
+	raw_spin_lock_init(&sprd_eic->lock);
 	sprd_eic->type = pdata->type;
 
 	sprd_eic->irq = platform_get_irq(pdev, 0);

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

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

From: Runyu Xiao <[email protected]>

commit 29bef9934b2521f787bb15dd1985d4c0d12ae02a upstream.

commit 10dc95939817 ("io_uring/io-wq: check IO_WQ_BIT_EXIT inside work run loop") fixed the obvious case where io_worker_handle_work() took one exit-bit snapshot before draining pending work, but the fix stops one level too early.

io_worker_handle_work() now re-checks IO_WQ_BIT_EXIT in its outer work run loop, yet it still snapshots that bit once before processing a whole dependent linked-work chain. If io_wq_exit_start() sets IO_WQ_BIT_EXIT after the first linked item has started, the remaining linked items can still reuse stale do_kill = false, skip IO_WQ_WORK_CANCEL, and continue running after exit has begun.

Move the check further inside, so it covers linked items too. Note: this is a syzbot special as it loves setting up tons of slow linked work on weird devices like msr that take forever to read, and immediately close the ring. Exit then takes a long time.

---
 io_uring/io-wq.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -556,7 +556,6 @@ static void io_worker_handle_work(struct
 	struct io_wq *wq = wqe->wq;
 
 	do {
-		bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state);
 		struct io_wq_work *work;
 
 		/*

@@ -590,6 +589,7 @@ static void io_worker_handle_work(struct
 
 		/* handle a whole dependent link */
 		do {
+			bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state);
 			struct io_wq_work *next_hashed, *linked;
 			unsigned int hash = io_get_work_hash(work);
 

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

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

From: Yuyang Huang <[email protected]>

commit 7993211bde166471dffac074dc965489f86531f8 upstream.

When a device is destroyed under RTNL, ip_mc_destroy_dev() iterates through the multicast list and calls ip_ma_put() on each membership, scheduling them for RCU reclamation. However, they are not unlinked from the device's multicast hash table (mc_hash).

Since the device remains published in dev->ip_ptr until after ip_mc_destroy_dev() completes, concurrent RCU readers traversing mc_hash can still locate and access the multicast group after its refcount is decremented. If the RCU callback runs and frees the group while a reader is accessing it, a use-after-free occurs.

Fix this by unlinking the multicast group from mc_hash using ip_mc_hash_remove() before scheduling it for reclamation.

BUG: KASAN: slab-use-after-free in ip_check_mc_rcu+0x149/0x3f0
Read of size 4 at addr ffff888009bf1408 by task mausezahn/2276

Call Trace:
 <IRQ>
 dump_stack_lvl+0x67/0x90
 print_report+0x175/0x7c0
 kasan_report+0x147/0x180
 ip_check_mc_rcu+0x149/0x3f0
 udp_v4_early_demux+0x36d/0x12d0
 ip_rcv_finish_core+0xb8b/0x1390
 ip_rcv_finish+0x54/0x120
 NF_HOOK+0x213/0x2b0
 __netif_receive_skb+0x126/0x340
 process_backlog+0x4f2/0xf00
 __napi_poll+0x92/0x2c0
 net_rx_action+0x583/0xc60
 handle_softirqs+0x236/0x7f0
 do_softirq+0x57/0x80
 </IRQ>

Allocated by task 2239:
 kasan_save_track+0x3e/0x80
 __kasan_kmalloc+0x72/0x90
 ____ip_mc_inc_group+0x31a/0xa40
 __ip_mc_join_group+0x334/0x3f0
 do_ip_setsockopt+0x16fa/0x2010
 ip_setsockopt+0x3f/0x90
 do_sock_setsockopt+0x1ad/0x300

Freed by task 0:
 kasan_save_track+0x3e/0x80
 kasan_save_free_info+0x40/0x50
 __kasan_slab_free+0x3a/0x60
 __rcu_free_sheaf_prepare+0xd4/0x220
 rcu_free_sheaf+0x36/0x190
 rcu_core+0x8d9/0x12f0
 handle_softirqs+0x236/0x7f0

---
 net/ipv4/igmp.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1816,6 +1816,7 @@ void ip_mc_destroy_dev(struct in_device
 #endif
 
 	while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) {
+		ip_mc_hash_remove(in_dev, i);
 		in_dev->mc_list = i->next_rcu;
 		in_dev->mc_count--;
 		ip_mc_clear_src(i);

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

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

From: Wyatt Feng <[email protected]>

commit efb8763d7bbb40cff4cc55a6b62c3095a038149c upstream.

Reject invalid net.ipv4.tcp_reordering values before they reach TCP socket state. The sysctl is stored as an int but copied into the u32 tp->reordering field for new sockets, so negative writes wrap to large values.

With tcp_mtu_probing=2, the wrapped value can overflow the tcp_mtu_probe() size calculation and drive the MTU probing path into an out-of-bounds read. Route tcp_reordering writes through proc_dointvec_minmax() and require it to be at least 1. Also require tcp_max_reordering to be at least 1 so the configured maximum cannot become negative either.

When registering the table for a non-init network namespace, relocate extra2 pointers that refer into init_net.ipv4 so the tcp_reordering upper bound follows that namespace's tcp_max_reordering.

Harden tcp_mtu_probe() itself by computing size_needed as u64. This keeps the send queue and window checks from being bypassed through signed integer overflow.

---
 net/ipv4/sysctl_net_ipv4.c |   10 ++++++++--
 net/ipv4/tcp_output.c      |    4 ++--
 2 files changed, 10 insertions(+), 4 deletions(-)

@@ -938,7 +938,9 @@ static struct ctl_table ipv4_net_table[]
 		.data		= &init_net.ipv4.sysctl_tcp_reordering,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= &init_net.ipv4.sysctl_tcp_max_reordering,
 	},
 	{
 		.procname	= "tcp_retries1",

@@ -1157,7 +1159,8 @@ static struct ctl_table ipv4_net_table[]
 		.data		= &init_net.ipv4.sysctl_tcp_max_reordering,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "tcp_dsack",

@@ -1423,6 +1426,9 @@ static __net_init int ipv4_sysctl_init_n
 				 */
 				table[i].mode &= ~0222;
 			}
+			if (table[i].extra2 >= (void *)&init_net.ipv4 &&
+			    table[i].extra2 < (void *)(&init_net.ipv4 + 1))
+				table[i].extra2 += (void *)net - (void *)&init_net;
 		}
 	}
 

@@ -2352,7 +2352,7 @@ static int tcp_mtu_probe(struct sock *sk
 	struct sk_buff *skb, *nskb, *next;
 	struct net *net = sock_net(sk);
 	int probe_size;
-	int size_needed;
+	u64 size_needed;
 	int copy, len;
 	int mss_now;
 	int interval;

@@ -2376,7 +2376,7 @@ static int tcp_mtu_probe(struct sock *sk
 	mss_now = tcp_current_mss(sk);
 	probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high +
 				    icsk->icsk_mtup.search_low) >> 1);
-	size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
+	size_needed = probe_size + (tp->reordering + 1) * (u64)tp->mss_cache;
 	interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low;
 	/* When misfortune happens, we are reprobing actively,
 	 * and then reprobe timer has expired. We stick with current

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

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

From: Andrei Kuchynski <[email protected]>

commit 8b2c1d41bc36c100b38ce5ee6def246c527eaf8a upstream.

If ec_device_probe() fails, cros_ec_class_release releases memory for the cros_ec_dev structure. However, because the drvdata was already set, sub-drivers like cros_ec_typec can still retrieve the stale pointer via the platform device. This leads to a use-after-free when cros_ec_typec attempts to access &typec->ec->ec->dev on a device that has already been released. Move dev_set_drvdata() to ensure that the pointer is only made available once all initialization steps have succeeded.

sysfs: cannot create duplicate filename '/class/chromeos/cros_ec'

 Call trace:
  sysfs_do_create_link_sd+0x94/0xdc
  sysfs_create_link+0x30/0x44
  device_add_class_symlinks+0x90/0x13c
  device_add+0xf0/0x50c
  ec_device_probe+0x150/0x4f0
  platform_probe+0xa0/0xe0
 ...
 BUG: KASAN: invalid-access in __memcpy+0x44/0x230
 Write at addr f5ffff809e2d33ac by task kworker/u32:5/125
 Pointer tag: [f5], memory tag: [fe]
 Tainted : [W]=WARN, [O]=OOT_MODULE
 Hardware name: Google Navi unprovisioned 0x7FFFFFFF/sku0 board/sku3
 Workqueue: events_unbound deferred_probe_work_func
 Call trace:
  __memcpy+0x44/0x230
  cros_ec_check_features+0x60/0xcc [cros_ec_proto]
  cros_typec_probe+0xe8/0x6e0 [cros_ec_typec]
  platform_probe+0xa0/0xe0

---
 drivers/mfd/cros_ec_dev.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -151,7 +151,6 @@ static int ec_device_probe(struct platfo
 	if (!ec)
 		return retval;
 
-	dev_set_drvdata(dev, ec);
 	ec->ec_dev = dev_get_drvdata(dev->parent);
 	ec->dev = dev;
 	ec->cmd_offset = ec_platform->cmd_offset;

@@ -193,6 +192,8 @@ static int ec_device_probe(struct platfo
 	if (retval)
 		goto failed;
 
+	dev_set_drvdata(dev, ec);
+
 	/* check whether this EC is a sensor hub. */
 	if (cros_ec_get_sensor_count(ec) > 0) {
 		retval = mfd_add_hotplug_devices(ec->dev,

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

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

From: Pratham Gupta <[email protected]>

commit a7f57320bbbc67e347bf5fff4b4a9bab980d5956 upstream.

Commit 02a3231b6d82 ("netfilter: nf_conntrack_expect: store netns and zone in expectation") introduced exp->net so RCU-only expectation paths no longer need to dereference exp->master for netns lookups.

Commit 3db5647984de ("netfilter: nf_conntrack_expect: skip expectations in other netns via proc") updated the proc path accordingly, but ctnetlink_exp_dump_table() still
compares against nf_ct_net(exp->master).

Use nf_ct_exp_net(exp) here as well so the netlink dump path matches the rest of the March 2026 expectation netns/RCU cleanup.

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

@@ -3152,7 +3152,7 @@ restart:
 			if (l3proto && exp->tuple.src.l3num != l3proto)
 				continue;
 
-			if (!net_eq(nf_ct_net(exp->master), net))
+			if (!net_eq(nf_ct_exp_net(exp), net))
 				continue;
 
 			if (cb->args[1]) {

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

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

From: Florian Westphal <[email protected]>

commit 084d23f818321390509e9738a0b08bbf46df6425 upstream.

We need to explicitly check the length, else we may pass non-null terminated string to request_module().

---
 net/bridge/netfilter/ebtables.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -402,6 +402,9 @@ ebt_check_match(struct ebt_entry_match *
 	    left - sizeof(struct ebt_entry_match) < m->match_size)
 		return -EINVAL;
 
+	if (strnlen(m->u.name, XT_EXTENSION_MAXNAMELEN) == XT_EXTENSION_MAXNAMELEN)
+		return -EINVAL;
+
 	match = xt_find_match(NFPROTO_BRIDGE, m->u.name, m->u.revision);
 	if (IS_ERR(match) || match->family != NFPROTO_BRIDGE) {
 		if (!IS_ERR(match))

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

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

From: Xiang Mei <[email protected]>

commit a622d2e9608c9dff47fc2e5759ac7aa3a836b45d upstream.

update_counters() and compat_update_counters() forward a user-supplied 32-byte table name to find_table_lock() without NUL-terminating it. On a lookup miss, find_inlist_lock() calls try_then_request_module(..., "%s%s", "ebtable_", name), and vsnprintf() reads past the name field and the stack object until it hits a zero byte.

  BUG: KASAN: stack-out-of-bounds in string (lib/vsprintf.c:648 lib/vsprintf.c:730)
  Read of size 1 at addr ffff8880119dfb20 by task exploit/147
  Call Trace:
  ...
   string (lib/vsprintf.c:648 lib/vsprintf.c:730)
   vsnprintf (lib/vsprintf.c:2945)
   __request_module (kernel/module/kmod.c:150)
   do_update_counters.isra.0 (net/bridge/netfilter/ebtables.c:371 net/bridge/netfilter/ebtables.c:380)
   update_counters (net/bridge/netfilter/ebtables.c:1440)
   do_ebt_set_ctl (net/bridge/netfilter/ebtables.c:2573)
   nf_setsockopt (net/netfilter/nf_sockopt.c:101)
   ip_setsockopt (net/ipv4/ip_sockglue.c:1424)
   raw_setsockopt (net/ipv4/raw.c:847)
   __sys_setsockopt (net/socket.c:2393)
  ...

compat_do_replace() shares the same unterminated name via compat_copy_ebt_replace_from_user(); terminate it there too so all find_table_lock() callers behave alike. The other callers already terminate the name after the copy.

---
 net/bridge/netfilter/ebtables.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -1433,6 +1433,8 @@ static int update_counters(struct net *n
 	if (copy_from_sockptr(&hlp, arg, sizeof(hlp)))
 		return -EFAULT;
 
+	hlp.name[sizeof(hlp.name) - 1] = '\0';
+
 	if (len != sizeof(hlp) + hlp.num_counters * sizeof(struct ebt_counter))
 		return -EINVAL;
 

@@ -2272,6 +2274,8 @@ static int compat_copy_ebt_replace_from_
 
 	memcpy(repl, &tmp, offsetof(struct ebt_replace, hook_entry));
 
+	repl->name[sizeof(repl->name) - 1] = '\0';
+
 	/* starting with hook_entry, 32 vs. 64 bit structures are different */
 	for (i = 0; i < NF_BR_NUMHOOKS; i++)
 		repl->hook_entry[i] = compat_ptr(tmp.hook_entry[i]);

@@ -2394,6 +2398,8 @@ static int compat_update_counters(struct
 	if (copy_from_sockptr(&hlp, arg, sizeof(hlp)))
 		return -EFAULT;
 
+	hlp.name[sizeof(hlp.name) - 1] = '\0';
+
 	/* try real handler in case userland supplied needed padding */
 	if (len != sizeof(hlp) + hlp.num_counters * sizeof(struct ebt_counter))
 		return update_counters(net, arg, len);

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

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

From: Sergey Senozhatsky <[email protected]>

commit a257407e2bbbb099ed427719a50563f67fa366d8 upstream.

Every once in a while we see a hung btmtksdio_flush() task:

 INFO: task kworker/u17:0:189 blocked for more than 122 seconds.
 __cancel_work_timer+0x3f4/0x460
 cancel_work_sync+0x1c/0x2c
 btmtksdio_flush+0x2c/0x40
 hci_dev_open_sync+0x10c4/0x2190
 [..]

It all boils down to incorrect time_is_before_jiffies() usage in btmtksdio_txrx_work(). The btmtksdio_txrx_work() loop is expected to be terminated if running for longer than 5*HZ. However the timeout check is twisted: time_is_before_jiffies(old_jiffies + 5*HZ) evaluates to true when old_jiffies + 5*HZ is in the past i.e. when a timeout has occurred. Using OR with time_is_before_jiffies(txrx_timeout) means that:
- before the 5-second timeout: the condition is int_status || false, so it loops as long as there are pending interrupts.
- after the 5-second timeout: the condition becomes int_status || true, which is always true.

When the loop becomes infinite btmtksdio_txrx_work() loop never terminates and never releases the SDIO host.

Fix loop termination condition to actually enforce a 5*HZ timeout.

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

@@ -605,7 +605,7 @@ static void btmtksdio_txrx_work(struct w
 			if (btmtksdio_rx_packet(bdev, rx_size) < 0)
 				bdev->hdev->stat.err_rx++;
 		}
-	} while (int_status || time_is_before_jiffies(txrx_timeout));
+	} while (int_status && time_is_after_jiffies(txrx_timeout));
 
 	/* Enable interrupt */
 	sdio_writel(bdev->func, C_INT_EN_SET, MTK_REG_CHLPCR, 0);

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

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

From: Yousef Alhouseen <[email protected]>

commit bb067a99a0356196c0b89a95721985485ebce5a5 upstream.

bnep_add_connection() reads the L2CAP connection without holding the channel lock, then passes its HCI device to register_netdev(). Controller teardown can clear and release that connection concurrently, leaving the network device registration path to dereference a freed parent device.

Take a reference to the L2CAP connection while holding the channel lock. Retain it until register_netdev() has taken the parent device reference.

---
 net/bluetooth/bnep/core.c |   27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

@@ -562,14 +562,18 @@ static int bnep_session(void *arg)
 	return 0;
 }
 
-static struct device *bnep_get_device(struct bnep_session *session)
+static struct l2cap_conn *bnep_get_conn(struct bnep_session *session)
 {
-	struct l2cap_conn *conn = l2cap_pi(session->sock->sk)->chan->conn;
+	struct l2cap_chan *chan = l2cap_pi(session->sock->sk)->chan;
+	struct l2cap_conn *conn;
 
-	if (!conn || !conn->hcon)
-		return NULL;
+	l2cap_chan_lock(chan);
+	conn = chan->conn;
+	if (conn)
+		l2cap_conn_get(conn);
+	l2cap_chan_unlock(chan);
 
-	return &conn->hcon->dev;
+	return conn;
 }
 
 static struct device_type bnep_type = {

@@ -581,6 +585,7 @@ int bnep_add_connection(struct bnep_conn
 	u32 valid_flags = BIT(BNEP_SETUP_RESPONSE);
 	struct net_device *dev;
 	struct bnep_session *s, *ss;
+	struct l2cap_conn *conn = NULL;
 	u8 dst[ETH_ALEN], src[ETH_ALEN];
 	int err;
 

@@ -640,10 +645,18 @@ int bnep_add_connection(struct bnep_conn
 	bnep_set_default_proto_filter(s);
 #endif
 
-	SET_NETDEV_DEV(dev, bnep_get_device(s));
+	conn = bnep_get_conn(s);
+	if (!conn) {
+		err = -ENOTCONN;
+		goto failed;
+	}
+
+	SET_NETDEV_DEV(dev, &conn->hcon->dev);
 	SET_NETDEV_DEVTYPE(dev, &bnep_type);
 
 	err = register_netdev(dev);
+	l2cap_conn_put(conn);
+	conn = NULL;
 	if (err)
 		goto failed;
 

@@ -665,6 +678,8 @@ int bnep_add_connection(struct bnep_conn
 	return 0;
 
 failed:
+	if (conn)
+		l2cap_conn_put(conn);
 	up_write(&bnep_session_sem);
 	free_netdev(dev);
 	return err;

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

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

From: Yousef Alhouseen <[email protected]>

commit 4bd0b274054f2679f28b70222b607bb0afc3ab9a upstream.

bt_accept_get() takes a temporary reference before dropping the accept queue lock. bt_accept_dequeue() currently drops that reference before bt_accept_unlink(), leaving only the queue reference.

bt_accept_unlink() drops the queue reference. The subsequent sock_hold() therefore accesses freed memory if it was the final reference, as observed by KASAN during listening L2CAP socket cleanup.

Retain the temporary queue-walk reference through unlink and hand it to the caller on success. Drop it explicitly on the closed and not-yet-connected paths.

---
 net/bluetooth/af_bluetooth.c |   17 +++--------------
 net/bluetooth/l2cap_sock.c   |    4 ++--
 2 files changed, 5 insertions(+), 16 deletions(-)

@@ -305,7 +305,7 @@ struct sock *bt_accept_dequeue(struct so
 
 restart:
 	for (sk = bt_accept_get(parent, NULL); sk; sk = next) {
-		/* Prevent early freeing of sk due to unlink and sock_kill */
+		/* The reference from bt_accept_get() keeps sk alive. */
 		lock_sock(sk);
 
 		/* Check sk has not already been unlinked via

@@ -321,13 +321,11 @@ restart:
 
 		next = bt_accept_get(parent, sk);
 
-		/* sk is safely in the parent list so reduce reference count */
-		sock_put(sk);
-
 		/* FIXME: Is this check still needed */
 		if (sk->sk_state == BT_CLOSED) {
 			bt_accept_unlink(sk);
 			release_sock(sk);
+			sock_put(sk);
 			continue;
 		}
 

@@ -337,16 +335,6 @@ restart:
 			if (newsock)
 				sock_graft(sk, newsock);
 
-			/* Hand the caller a reference taken while sk is
-			 * still locked.  bt_accept_unlink() just dropped
-			 * the accept-queue reference; without this hold a
-			 * concurrent teardown (e.g. l2cap_conn_del() ->
-			 * l2cap_sock_kill()) could free sk between
-			 * release_sock() and the caller using it.  Every
-			 * caller drops this with sock_put() when done.
-			 */
-			sock_hold(sk);
-
 			release_sock(sk);
 			if (next)
 				sock_put(next);

@@ -354,6 +342,7 @@ restart:
 		}
 
 		release_sock(sk);
+		sock_put(sk);
 	}
 
 	return NULL;

@@ -1465,8 +1465,8 @@ static void l2cap_sock_cleanup_listen(st
 
 	/* Close not yet accepted channels.
 	 *
-	 * bt_accept_dequeue() now returns sk with an extra reference held
-	 * (taken while sk was still locked) so a concurrent l2cap_conn_del()
+	 * bt_accept_dequeue() returns sk with its temporary queue-walk
+	 * reference held, so a concurrent l2cap_conn_del()
 	 * -> l2cap_sock_kill() cannot free sk under us.
 	 *
 	 * cleanup_listen() runs under the parent sk lock, so unlike

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

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

From: Muhammad Bilal <[email protected]>

commit 687617555cedfb74c9e3cb85d759b908dcb17856 upstream.

l2cap_get_conf_opt() derives the option length from the attacker-controlled opt->len field and immediately dereferences opt->val (as u8, get_unaligned_le16() or get_unaligned_le32(), or a raw pointer for the default case) before any caller has confirmed that opt->len bytes are present in the buffer. The callers (l2cap_parse_conf_req(), l2cap_parse_conf_rsp() and l2cap_conf_rfc_get()) only detect a malformed option afterwards, once the running length has gone negative, by which point the out-of-bounds read has already executed.

An existing post-hoc length check keeps the garbage value from being consumed, so this is not a data leak in the current control flow. It is still a validate-after-use ordering bug: up to 4 bytes are read past the end of the buffer before it is known to contain them, and it is fragile to future changes in the callers.

Fix it at the source. Pass the end of the buffer into l2cap_get_conf_opt() and refuse to touch opt->val unless the full option (header + value) fits. Each caller computes an end pointer once before the loop and checks the return value directly instead of inferring the error from a negative length.

---
 net/bluetooth/l2cap_core.c |   36 ++++++++++++++++++++++++++++--------
 1 file changed, 28 insertions(+), 8 deletions(-)

@@ -3188,13 +3188,24 @@ fail:
 	return NULL;
 }
 
-static inline int l2cap_get_conf_opt(void **ptr, int *type, int *olen,
-				     unsigned long *val)
+static inline int l2cap_get_conf_opt(void **ptr, void *end, int *type,
+				     int *olen, unsigned long *val)
 {
 	struct l2cap_conf_opt *opt = *ptr;
 	int len;
 
+	/* opt->len is attacker-controlled. Validate that the full option
+	 * (header + value) actually fits in the buffer before touching
+	 * opt->val, otherwise the switch below reads past the end of the
+	 * caller's buffer.
+	 */
+	if (end - *ptr < L2CAP_CONF_OPT_SIZE)
+		return -EINVAL;
+
 	len = L2CAP_CONF_OPT_SIZE + opt->len;
+	if (end - *ptr < len)
+		return -EINVAL;
+
 	*ptr += len;
 
 	*type = opt->type;

@@ -3600,6 +3611,7 @@ static int l2cap_parse_conf_req(struct l
 	void *ptr = rsp->data;
 	void *endptr = data + data_size;
 	void *req = chan->conf_req;
+	void *req_end = req + chan->conf_len;
 	int len = chan->conf_len;
 	int type, hint, olen;
 	unsigned long val;

@@ -3613,9 +3625,11 @@ static int l2cap_parse_conf_req(struct l
 	BT_DBG("chan %p", chan);
 
 	while (len >= L2CAP_CONF_OPT_SIZE) {
-		len -= l2cap_get_conf_opt(&req, &type, &olen, &val);
-		if (len < 0)
+		int ret = l2cap_get_conf_opt(&req, req_end, &type, &olen, &val);
+
+		if (ret < 0)
 			break;
+		len -= ret;
 
 		hint  = type & L2CAP_CONF_HINT;
 		type &= L2CAP_CONF_MASK;

@@ -3849,6 +3863,7 @@ static int l2cap_parse_conf_rsp(struct l
 	struct l2cap_conf_req *req = data;
 	void *ptr = req->data;
 	void *endptr = data + size;
+	void *rsp_end = rsp + len;
 	int type, olen;
 	unsigned long val;
 	struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC };

@@ -3857,9 +3872,11 @@ static int l2cap_parse_conf_rsp(struct l
 	BT_DBG("chan %p, rsp %p, len %d, req %p", chan, rsp, len, data);
 
 	while (len >= L2CAP_CONF_OPT_SIZE) {
-		len -= l2cap_get_conf_opt(&rsp, &type, &olen, &val);
-		if (len < 0)
+		int ret = l2cap_get_conf_opt(&rsp, rsp_end, &type, &olen, &val);
+
+		if (ret < 0)
 			break;
+		len -= ret;
 
 		switch (type) {
 		case L2CAP_CONF_MTU:

@@ -4112,6 +4129,7 @@ static void l2cap_conf_rfc_get(struct l2
 {
 	int type, olen;
 	unsigned long val;
+	void *rsp_end = rsp + len;
 	/* Use sane default values in case a misbehaving remote device
 	 * did not send an RFC or extended window size option.
 	 */

@@ -4130,9 +4148,11 @@ static void l2cap_conf_rfc_get(struct l2
 		return;
 
 	while (len >= L2CAP_CONF_OPT_SIZE) {
-		len -= l2cap_get_conf_opt(&rsp, &type, &olen, &val);
-		if (len < 0)
+		int ret = l2cap_get_conf_opt(&rsp, rsp_end, &type, &olen, &val);
+
+		if (ret < 0)
 			break;
+		len -= ret;
 
 		switch (type) {
 		case L2CAP_CONF_RFC:

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

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

From: Sebastian Andrzej Siewior <[email protected]>

commit 983512f3a87fd8dc4c94dfa6b596b6e57df5aad7 upstream.

skb_may_tx_timestamp() may acquire sock::sk_callback_lock. The lock must not be taken in IRQ context, only softirq is okay. A few drivers receive the timestamp via a dedicated interrupt and complete the TX timestamp from that handler. This will lead to a deadlock if the lock is already write-locked on the same CPU.

Taking the lock can be avoided. The socket (pointed by the skb) will remain valid until the skb is released. The ->sk_socket and ->file member will be set to NULL once the user closes the socket which may happen before the timestamp arrives.
If we happen to observe the pointer while the socket is closing but before the pointer is set to NULL then we may use it because both pointer (and the file's cred member) are RCU freed.

Drop the lock. Use READ_ONCE() to obtain the individual pointer. Add a matching WRITE_ONCE() where the pointer are cleared.

[ adapted sk_set_socket() in include/net/sock.h to fix the conflict from
not having commit 5d6b58c932ec ("net: lockless sock_i_ino()") and the additional previous changes required by it.
It comes down to just now having the lines of

    if (sock) {
            WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid);
            WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino);
    }

below the changed line. ]

---
 include/net/sock.h |  2 +-
 net/core/skbuff.c  | 23 ++++++++++++++++++-----
 net/socket.c       |  2 +-
 3 files changed, 20 insertions(+), 7 deletions(-)

index 1e7096e9bc4842..9fe621f9857401 100644
@@ -2181,7 +2181,7 @@ static inline int sk_rx_queue_get(const struct sock *sk)
 
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
-	sk->sk_socket = sock;
+	WRITE_ONCE(sk->sk_socket, sock);
 }
 
 static inline wait_queue_head_t *sk_sleep(struct sock *sk)

index f41dd20991c3df..6575a76a312e11 100644
@@ -4948,15 +4948,28 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
 
 static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
 {
-	bool ret;
+	struct socket *sock;
+	struct file *file;
+	bool ret = false;
 
 	if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly))
 		return true;
 
-	read_lock_bh(&sk->sk_callback_lock);
-	ret = sk->sk_socket && sk->sk_socket->file &&
-	      file_ns_capable(sk->sk_socket->file, &init_user_ns, CAP_NET_RAW);
-	read_unlock_bh(&sk->sk_callback_lock);
+	/* The sk pointer remains valid as long as the skb is. The sk_socket and
+	 * file pointer may become NULL if the socket is closed. Both structures
+	 * (including file->cred) are RCU freed which means they can be accessed
+	 * within a RCU read section.
+	 */
+	rcu_read_lock();
+	sock = READ_ONCE(sk->sk_socket);
+	if (!sock)
+		goto out;
+	file = READ_ONCE(sock->file);
+	if (!file)
+		goto out;
+	ret = file_ns_capable(file, &init_user_ns, CAP_NET_RAW);
+out:
+	rcu_read_unlock();
 	return ret;
 }
 

index f2b4cf9b09a322..8bf415a59e55c2 100644
@@ -666,7 +666,7 @@ static void __sock_release(struct socket *sock, struct inode *inode)
 		iput(SOCK_INODE(sock));
 		return;
 	}
-	sock->file = NULL;
+	WRITE_ONCE(sock->file, NULL);
 }
 
 /**

2.53.0

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

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

From: Gil Portnoy <[email protected]>

commit 388e4139db27a9e3612c9d356b826f5b1ff6a9e3 upstream.

The FSCTL_DUPLICATE_EXTENTS_TO_FILE arm of smb2_ioctl() overwrites the destination file's data via vfs_clone_file_range() with neither the share-level KSMBD_TREE_CONN_FLAG_WRITABLE check nor a per-handle fp->daccess check that the other write-bearing arms carry. A client can overwrite destination data on a read-only share, or from a handle opened with only FILE_WRITE_ATTRIBUTES (which still yields an FMODE_WRITE filp). FILE_WRITE_ATTRIBUTES-only destination handle overwrote the file's data via the clone. Add both checks, matching the FSCTL_SET_SPARSE permission fix; require FILE_WRITE_DATA since this writes data.

---
 fs/smb/server/smb2pdu.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

@@ -8033,6 +8033,17 @@ int smb2_ioctl(struct ksmbd_work *work)
 			goto dup_ext_out;
 		}
 
+		if (!test_tree_conn_flag(work->tcon,
+					 KSMBD_TREE_CONN_FLAG_WRITABLE)) {
+			ret = -EACCES;
+			goto dup_ext_out;
+		}
+
+		if (!(fp_out->daccess & FILE_WRITE_DATA_LE)) {
+			ret = -EACCES;
+			goto dup_ext_out;
+		}
+
 		src_off = le64_to_cpu(dup_ext->SourceFileOffset);
 		dst_off = le64_to_cpu(dup_ext->TargetFileOffset);
 		length = le64_to_cpu(dup_ext->ByteCount);

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

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

From: Gil Portnoy <[email protected]>

commit 3320ba068198adc144c89d6661b805acce01735b upstream.

FSCTL_SET_ZERO_DATA in smb2_ioctl() destroys file data via ksmbd_vfs_zero_data() -> vfs_fallocate(PUNCH_HOLE/ZERO_RANGE) after checking only the share-level KSMBD_TREE_CONN_FLAG_WRITABLE, with no per-handle access check. A handle opened with only FILE_WRITE_ATTRIBUTES still yields an FMODE_WRITE filp (FILE_WRITE_ATTRIBUTES is part of FILE_WRITE_DESIRE_ACCESS_LE, so smb2_create_open_flags() opens it O_WRONLY), so the vfs_fallocate FMODE_WRITE check does not stop it; only the missing fp->daccess gate would. Reproduced on mainline 7.1-rc7 with KASAN by an authenticated SMB client: a FILE_WRITE_ATTRIBUTES-only handle zeroed 4096 bytes of file data it had no FILE_WRITE_DATA right to (6/6; a FILE_READ_DATA-only handle was correctly denied).

This is the unfixed sibling of commit cc57232cae23 ("ksmbd: fix FSCTL permission bypass by adding a permission check for FSCTL_SET_SPARSE"). Because SET_ZERO_DATA writes data (not an attribute), require FILE_WRITE_DATA.

---
 fs/smb/server/smb2pdu.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -7958,6 +7958,12 @@ int smb2_ioctl(struct ksmbd_work *work)
 				goto out;
 			}
 
+			if (!(fp->daccess & FILE_WRITE_DATA_LE)) {
+				ksmbd_fd_put(work, fp);
+				ret = -EACCES;
+				goto out;
+			}
+
 			ret = ksmbd_vfs_zero_data(work, fp, off, len);
 			ksmbd_fd_put(work, fp);
 			if (ret < 0)

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

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

From: Namjae Jeon <[email protected]>

commit be6d26bf27499977c746abc163659915082348d8 upstream.

smb2_query_dir() stores a pointer to its stack-allocated private data in the ksmbd_file readdir_data. Concurrent QUERY_DIRECTORY requests using the same file handle can overwrite this pointer while an iterate_dir() callback is still using it, resulting in a stack use-after-free.

Add a per-file mutex and hold it while accessing the shared directory enumeration state. The lock covers scan restart, dot entry state, readdir_data setup and iteration, and response construction. This prevents another request from replacing readdir_data.private before the current request has finished using it and also serializes the shared file position.

---
 fs/smb/server/smb2pdu.c   |    4 ++++
 fs/smb/server/vfs_cache.c |    1 +
 fs/smb/server/vfs_cache.h |    2 ++
 3 files changed, 7 insertions(+)

@@ -4126,6 +4126,8 @@ int smb2_query_dir(struct ksmbd_work *wo
 		ksmbd_debug(SMB, "Search pattern is %s\n", srch_ptr);
 	}
 
+	mutex_lock(&dir_fp->readdir_lock);
+
 	if (srch_flag & SMB2_REOPEN || srch_flag & SMB2_RESTART_SCANS) {
 		ksmbd_debug(SMB, "Restart directory scan\n");
 		generic_file_llseek(dir_fp->filp, 0, SEEK_SET);

@@ -4230,6 +4232,7 @@ no_buf_len:
 			goto err_out;
 	}
 
+	mutex_unlock(&dir_fp->readdir_lock);
 	kfree(srch_ptr);
 	ksmbd_fd_put(work, dir_fp);
 	ksmbd_revert_fsids(work);

@@ -4237,6 +4240,7 @@ no_buf_len:
 
 err_out:
 	pr_err("error while processing smb2 query dir rc = %d\n", rc);
+	mutex_unlock(&dir_fp->readdir_lock);
 	kfree(srch_ptr);
 
 err_out2:

@@ -574,6 +574,7 @@ struct ksmbd_file *ksmbd_open_fd(struct
 	INIT_LIST_HEAD(&fp->node);
 	INIT_LIST_HEAD(&fp->lock_list);
 	spin_lock_init(&fp->f_lock);
+	mutex_init(&fp->readdir_lock);
 	atomic_set(&fp->refcount, 1);
 
 	fp->filp		= filp;

@@ -8,6 +8,7 @@
 
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/spinlock.h>
 #include <linux/idr.h>

@@ -103,6 +104,7 @@ struct ksmbd_file {
 
 	/* if ls is happening on directory, below is valid*/
 	struct ksmbd_readdir_data	readdir_data;
+	struct mutex			readdir_lock;
 	int				dot_dotdot[2];
 	unsigned int			f_state;
 	bool				reserve_lease_break;

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

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

From: Davide Ornaghi <[email protected]>

commit d20d1c8ba5765d1d12eefc0aee6385ab3f240e1e upstream.

When a blocking byte-range lock request is deferred in the FILE_LOCK_DEFERRED path, ksmbd registers the asynchronous work into the connection's async_requests list via setup_async_work(). The cancel callback smb2_remove_blocked_lock() holds a reference to the flock.

If the lock waiter is subsequently woken up but the work state is no longer KSMBD_WORK_ACTIVE (e.g., due to a concurrent cancellation), the cleanup path calls locks_free_lock(flock) without dequeuing the work from the async_requests list. Concurrently, smb2_cancel() walks the list under conn->request_lock and invokes the cancel callback, which then dereferences the already freed 'flock'. This leads to a slab-use-after-free inside __wake_up_common.

Fix this by restructuring the cleanup logic after the worker returns from ksmbd_vfs_posix_lock_wait(). Move list_del(&smb_lock->llist) and release_async_work(work) to the top of the cleanup block. This guarantees that the async work is completely dequeued and serialized under conn->request_lock before locks_free_lock(flock) is called, rendering the flock unreachable for any concurrent smb2_cancel().

---
 fs/smb/server/smb2pdu.c |   34 ++++++++++++++++------------------
 1 file changed, 16 insertions(+), 18 deletions(-)

@@ -7229,29 +7229,27 @@ skip:
 				list_del(&work->fp_entry);
 				spin_unlock(&fp->f_lock);
 
-				if (work->state != KSMBD_WORK_ACTIVE) {
-					list_del(&smb_lock->llist);
-					locks_free_lock(flock);
+				list_del(&smb_lock->llist);
+				release_async_work(work);
+
+				if (work->state == KSMBD_WORK_ACTIVE)
+					goto retry;
 
-					if (work->state == KSMBD_WORK_CANCELLED) {
-						rsp->hdr.Status =
-							STATUS_CANCELLED;
-						kfree(smb_lock);
-						smb2_send_interim_resp(work,
-								       STATUS_CANCELLED);
-						work->send_no_response = 1;
-						goto out;
-					}
+				locks_free_lock(flock);
 
-					rsp->hdr.Status =
-						STATUS_RANGE_NOT_LOCKED;
+				if (work->state == KSMBD_WORK_CANCELLED) {
+					rsp->hdr.Status = STATUS_CANCELLED;
 					kfree(smb_lock);
-					goto out2;
+					smb2_send_interim_resp(work,
+							STATUS_CANCELLED);
+					work->send_no_response = 1;
+					goto out;
 				}
 
-				list_del(&smb_lock->llist);
-				release_async_work(work);
-				goto retry;
+				rsp->hdr.Status =
+					STATUS_RANGE_NOT_LOCKED;
+				kfree(smb_lock);
+				goto out2;
 			} else if (!rc) {
 				list_add(&smb_lock->llist, &rollback_list);
 				spin_lock(&work->conn->llist_lock);

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

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

From: Namjae Jeon <[email protected]>

commit cedff600f1642aa982178503552f0d007bc829c8 upstream.

FSCTL_DUPLICATE_EXTENTS_TO_FILE passes the source file directly to vfs_clone_file_range() or vfs_copy_file_range() without checking the SMB access mask granted to the source handle. A handle opened with attribute access can consequently be used to copy file contents into an attacker-readable destination.

Require FILE_READ_DATA on the source handle before either VFS operation, matching other ksmbd data-copy paths.

---
 fs/smb/server/smb2pdu.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -8051,6 +8051,10 @@ int smb2_ioctl(struct ksmbd_work *work)
 			ret = -EACCES;
 			goto dup_ext_out;
 		}
+		if (!(fp_in->daccess & FILE_READ_DATA_LE)) {
+			ret = -EACCES;
+			goto dup_ext_out;
+		}
 
 		src_off = le64_to_cpu(dup_ext->SourceFileOffset);
 		dst_off = le64_to_cpu(dup_ext->TargetFileOffset);

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

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

From: Gil Portnoy <[email protected]>

commit 44df157a1183a7f746caa970c169255da5ac61f8 upstream.

commit cc57232cae23 ("ksmbd: fix FSCTL permission bypass by adding a permission check for FSCTL_SET_SPARSE") added a fp->daccess gate to fsctl_set_sparse and noted that "similar handle-level checks exist in other functions but are missing here." The SMB2 SET_INFO SECURITY arm is one of the missing ones, and the most security-relevant: smb2_set_info_sec() calls set_info_sec() with no per-handle access check.

set_info_sec() (fs/smb/server/smbacl.c) re-permissions the file: it rewrites owner/group/mode via notify_change(), rewrites the POSIX ACL via set_posix_acl(), and on KSMBD_SHARE_FLAG_ACL_XATTR shares removes and rewrites the Windows security descriptor via ksmbd_vfs_set_sd_xattr(). Every other persistent-mutation arm of the sibling handler smb2_set_info_file() checks fp->daccess first (FILE_WRITE_DATA / FILE_DELETE / FILE_WRITE_EA / FILE_WRITE_ATTRIBUTES); the SECURITY arm — which mutates the access control itself — is the only one with no gate.

A client can therefore open a handle with FILE_WRITE_ATTRIBUTES only (no FILE_WRITE_DAC / FILE_WRITE_OWNER) and use SMB2_SET_INFO with InfoType SMB2_O_INFO_SECURITY to rewrite the file's DACL and owner, granting itself access the handle's daccess never carried. Unlike the FSCTL data arms this is a metadata/xattr operation, so there is no FMODE_WRITE VFS backstop — the missing fp->daccess check is the entire gate.

Setting a security descriptor is the WRITE_DAC / WRITE_OWNER operation, so require at least one of those on the handle before re-permissioning the file. -EACCES is mapped to STATUS_ACCESS_DENIED by smb2_set_info().

---
 fs/smb/server/smb2pdu.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -6117,6 +6117,9 @@ static int smb2_set_info_sec(struct ksmb
 
 	fp->saccess |= FILE_SHARE_DELETE_LE;
 
+	if (!(fp->daccess & (FILE_WRITE_DAC_LE | FILE_WRITE_OWNER_LE)))
+		return -EACCES;
+
 	return set_info_sec(fp->conn, fp->tcon, &fp->filp->f_path, pntsd,
 			buf_len, false, true);
 }

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

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

From: Namjae Jeon <[email protected]>

commit b383bcad3d2fe634b26efbce53e22bbb5753a520 upstream.

SMB2 SET_INFO handlers call path-based VFS helpers after checking the access mask granted to the SMB handle. Those helpers perform their owner, inode permission and LSM checks using the current ksmbd worker credentials.

Run the complete SET_INFO dispatch with the credentials captured when the handle was opened. This also removes the separate security information credential setup and keeps all SET_INFO classes under one credential scope.

Direct override_creds() is used because it can nest with the request credential overrides already used by rename and link helpers.

---
 fs/smb/server/smb2pdu.c |    8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

@@ -6132,6 +6132,7 @@ static int smb2_set_info_sec(struct ksmb
  */
 int smb2_set_info(struct ksmbd_work *work)
 {
+	const struct cred *saved_cred;
 	struct smb2_set_info_req *req;
 	struct smb2_set_info_rsp *rsp;
 	struct ksmbd_file *fp = NULL;

@@ -6173,6 +6174,7 @@ int smb2_set_info(struct ksmbd_work *wor
 		goto err_out;
 	}
 
+	saved_cred = override_creds(fp->filp->f_cred);
 	switch (req->InfoType) {
 	case SMB2_O_INFO_FILE:
 		ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n");

@@ -6180,19 +6182,15 @@ int smb2_set_info(struct ksmbd_work *wor
 		break;
 	case SMB2_O_INFO_SECURITY:
 		ksmbd_debug(SMB, "GOT SMB2_O_INFO_SECURITY\n");
-		if (ksmbd_override_fsids(work)) {
-			rc = -ENOMEM;
-			goto err_out;
-		}
 		rc = smb2_set_info_sec(fp,
 				       le32_to_cpu(req->AdditionalInformation),
 				       (char *)req + le16_to_cpu(req->BufferOffset),
 				       le32_to_cpu(req->BufferLength));
-		ksmbd_revert_fsids(work);
 		break;
 	default:
 		rc = -EOPNOTSUPP;
 	}
+	revert_creds(saved_cred);
 
 	if (rc < 0)
 		goto err_out;

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

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

From: Gil Portnoy <[email protected]>

commit 13f3942f2bf45856bb751faed2f0c4618f41ca20 upstream.

The FILE_LINK_INFORMATION arm of smb2_set_info_file() calls smb2_create_link() with no per-handle fp->daccess check. On the ReplaceIfExists path smb2_create_link() unlinks an existing file at the target name (ksmbd_vfs_remove_file) and creates a hardlink (ksmbd_vfs_link); neither helper checks daccess. A handle opened with FILE_READ_DATA only (no FILE_DELETE, no FILE_WRITE_DATA) can therefore delete an arbitrary file in the share and plant a hardlink over its name.

The sibling delete/move arms in the same switch already gate:
FILE_RENAME_INFORMATION and FILE_DISPOSITION_INFORMATION both require FILE_DELETE_LE; FILE_FULL_EA_INFORMATION requires FILE_WRITE_EA_LE. Gate the link arm the same way as its closest analogue (rename), since it mutates the namespace and, on replace, deletes an existing entry.

This is a sibling of commit cc57232cae23 ("ksmbd: fix FSCTL permission bypass by adding a permission check for FSCTL_SET_SPARSE").

---
 fs/smb/server/smb2pdu.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -6060,6 +6060,11 @@ static int smb2_set_info_file(struct ksm
 	}
 	case FILE_LINK_INFORMATION:
 	{
+		if (!(fp->daccess & FILE_DELETE_LE)) {
+			pr_err("no right to delete : 0x%x\n", fp->daccess);
+			return -EACCES;
+		}
+
 		if (buf_len < sizeof(struct smb2_file_link_info))
 			return -EINVAL;
 

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

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

From: Haoxiang Li <[email protected]>

commit 1c6267a1d5cf4c73b656f8181b310cbbb3e4767b upstream.

receive_encrypted_standard() allocates next_buffer before checking whether the number of compound PDUs already reached MAX_COMPOUND. If the limit check fails, the function returns immediately and the newly allocated next_buffer is not assigned to server->smallbuf/server->bigbuf, making it leaked.

Move the MAX_COMPOUND check before allocating next_buffer.

---
 fs/smb/client/smb2ops.c |   10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

@@ -5189,6 +5189,12 @@ receive_encrypted_standard(struct TCP_Se
 one_more:
 	shdr = (struct smb2_hdr *)buf;
 	next_cmd = le32_to_cpu(shdr->NextCommand);
+
+	if (*num_mids >= MAX_COMPOUND) {
+		cifs_server_dbg(VFS, "too many PDUs in compound\n");
+		return -1;
+	}
+
 	if (next_cmd) {
 		if (WARN_ON_ONCE(next_cmd > pdu_length))
 			return -1;

@@ -5212,10 +5218,6 @@ one_more:
 		mid_entry->resp_buf_size = server->pdu_size;
 	}
 
-	if (*num_mids >= MAX_COMPOUND) {
-		cifs_server_dbg(VFS, "too many PDUs in compound\n");
-		return -1;
-	}
 	bufs[*num_mids] = buf;
 	mids[(*num_mids)++] = mid_entry;
 

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

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

From: Zihan Xi <[email protected]>

commit b86467cd2691192ad4809a5a6e922fc24b8e9839 upstream.

The server controls create-context DataOffset, so the POSIX context data pointer may be misaligned on strict-alignment architectures. Use get_unaligned_le32() when reading nlink, reparse_tag, and mode.

---
 fs/smb/client/smb2pdu.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -2130,9 +2130,9 @@ parse_posix_ctxt(struct create_context *
 
 	memset(posix, 0, sizeof(*posix));
 
-	posix->nlink = le32_to_cpu(*(__le32 *)(beg + 0));
-	posix->reparse_tag = le32_to_cpu(*(__le32 *)(beg + 4));
-	posix->mode = le32_to_cpu(*(__le32 *)(beg + 8));
+	posix->nlink = get_unaligned_le32(beg);
+	posix->reparse_tag = get_unaligned_le32(beg + 4);
+	posix->mode = get_unaligned_le32(beg + 8);
 
 	sid = beg + 12;
 	sid_len = posix_info_sid_size(sid, end);

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

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

From: Zihan Xi <[email protected]>

commit 7ad2bcf2441430bb2e918fb3ef9a90d775a6e422 upstream.

posix_info_sid_size() reads sid[1] to obtain the subauthority count, but its existing boundary check still accepts buffers with only one remaining byte. Require two bytes before reading sid[1] so all client paths that reuse the helper reject truncated POSIX SIDs safely.

---
 fs/smb/client/smb2pdu.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -4857,7 +4857,7 @@ int posix_info_sid_size(const void *beg,
 	size_t subauth;
 	int total;
 
-	if (beg + 1 > end)
+	if (beg + 2 > end)
 		return -1;
 
 	subauth = *(u8 *)(beg+1);

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

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

From: Norbert Manthey <[email protected]>

commit e3d9c7160d483fc8f9e225aafad8ecbbc43f3151 upstream.

When modefromsid is active, parse_dacl() applies the server-provided sub_auth[2] value from the NFS mode SID to cf_mode without masking to 07777. Apply the correct masking, same as in the read path.

---
 fs/smb/client/cifsacl.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -887,7 +887,7 @@ static void parse_dacl(struct cifs_acl *
 				 */
 				fattr->cf_mode &= ~07777;
 				fattr->cf_mode |=
-					le32_to_cpu(ppace[i]->sid.sub_auth[2]);
+					le32_to_cpu(ppace[i]->sid.sub_auth[2]) & 07777;
 				break;
 			} else {
 				if (compare_sids(&(ppace[i]->sid), pownersid) == 0) {

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

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

From: Guangshuo Li <[email protected]>

commit 896df22ee57648b0c505bd76ddbc6b2341834696 upstream.

firmware_upload_register()
-> fw_create_instance()

     -> device_initialize()

After fw_create_instance() succeeds, the lifetime of the embedded struct device is expected to be managed through the device core reference counting, since fw_create_instance() has already called device_initialize().

In firmware_upload_register(), if alloc_lookup_fw_priv() fails after fw_create_instance() succeeds, the code reaches free_fw_sysfs and frees fw_sysfs directly instead of releasing the device reference with put_device(). This 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(fw_dev) in the failure path and letting fw_dev_release() handle the final cleanup, instead of freeing the instance directly from the error path.

---
 drivers/base/firmware_loader/sysfs_upload.c |    8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

@@ -340,7 +340,6 @@ firmware_upload_register(struct module *
 		goto free_fw_upload_priv;
 	}
 	fw_upload->priv = fw_sysfs;
-	fw_sysfs->fw_upload_priv = fw_upload_priv;
 	fw_dev = &fw_sysfs->dev;
 
 	ret = alloc_lookup_fw_priv(name, &fw_cache, &fw_priv,  NULL, 0, 0,

@@ -348,10 +347,12 @@ firmware_upload_register(struct module *
 	if (ret != 0) {
 		if (ret > 0)
 			ret = -EINVAL;
-		goto free_fw_sysfs;
+		put_device(fw_dev);
+		goto free_fw_upload_priv;
 	}
 	fw_priv->is_paged_buf = true;
 	fw_sysfs->fw_priv = fw_priv;
+	fw_sysfs->fw_upload_priv = fw_upload_priv;
 
 	ret = device_add(fw_dev);
 	if (ret) {

@@ -362,9 +363,6 @@ firmware_upload_register(struct module *
 
 	return fw_upload;
 
-free_fw_sysfs:
-	kfree(fw_sysfs);
-
 free_fw_upload_priv:
 	kfree(fw_upload_priv);
 

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

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

From: Fushuai Wang <[email protected]>

commit bcbdaa1086c25a8a5d48e04e1b82fdfb0682b681 upstream.

When a CPU goes offline with HWP disabled, intel_pstate_set_min_pstate() sets the MSR_IA32_PERF_CTL to minimum frequency to prevent SMT siblings from being restricted. However, the policy->cur value was not updated, leaving it at the previous value.

When the CPU comes back online, governor->limits() checks if target_freq equals policy->cur and skips the frequency adjustment if they match. Since policy->cur still holds the previous value, the governor does not call cpufreq_driver->target to update MSR_IA32_PERF_CTL.

Fix this by synchronizing policy->cur with the hardware state when setting minimum pstate during CPU offline.

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

@@ -2631,10 +2631,12 @@ static int intel_cpufreq_cpu_offline(str
 	 * from getting to lower performance levels, so force the minimum
 	 * performance on CPU offline to prevent that from happening.
 	 */
-	if (hwp_active)
+	if (hwp_active) {
 		intel_pstate_hwp_offline(cpu);
-	else
+	} else {
 		intel_pstate_set_min_pstate(cpu);
+		policy->cur = cpu->pstate.min_freq;
+	}
 
 	intel_pstate_exit_perf_limits(policy);
 

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

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

From: Steven Rostedt <[email protected]>

commit dd29c017aed628076e915fe4cdfb5392fd4c5cab upstream.

RT migration is done aggressively. When a CPU schedules out a high priority RT task for a lower priority task, it will look to see if there's any RT tasks that are waiting to run on another CPU that is of higher priority than the task this CPU is about to run. If it finds one, it will pull that task over to the CPU and allow it to run there instead.

Normally, this pulling is done by looking at the RT overloaded mask (rto) which contains all the CPUs in the scheduler domain with RT tasks that are waiting to run due to a higher priority RT task currently running on their CPU. The CPU that is about to schedule a lower priority task will grab the rq lock of the overloaded CPU and move the RT task from that CPU's runqueue to the local one and schedule the higher priority RT task.

This caused issues when a lot of CPUs would schedule a lower priority task at the same time. They would all try to grab the same runqueue lock of the CPU with the overloaded RT tasks. Only the first CPU that got in will get that task. All the others would wait until they got the runqueue lock and see there's nothing to pull and do nothing. On systems with lots of CPUs, this caused a large latency (up to 500us) which is beyond what PREEMPT_RT is to allow.

The solution to that was to create an RT_PUSH_IPI logic. When any CPU wanted to pull a task, instead of grabbing the runqueue lock of the overloaded CPU, it would start by sending an IPI to the overloaded CPU, and that IPI handler would have the CPU with the waiting RT task do a push instead. Then that handler would send an IPI to the next CPU with overloaded RT tasks, and so on. Note, after the first CPU starts this process, if another CPU wanted to do a pull, it would see that the process has already begun and would only increment a counter to have the IPIs continue again.

The RT_PUSH_IPI solved the latency problem with PREEMPT_RT but could cause a new issue with non PREEMPT_RT. Namely, softirqs run in a threaded context on PREEMPT_RT but they can run in an interrupt context in non-RT.

If an IPI lands on a CPU that has just woken up multiple RT tasks and the current CPU is running a non RT or a low priority RT task, instead of doing a push, it would simply do a schedule on that CPU. But if a softirq was also executing on this CPU, the schedule would need to wait until the softirq finished. Until then, the CPU would still be considered overloaded as there are RT tasks still waiting to run on it.

A live lock occurred on a workload that was doing heavy networking traffic on a large machine where the softirqs would run 500us out of 750us. And it would also be waking up RT tasks, causing the RT pull logic to be constantly executed.

When a softirq triggered on a CPU with RT tasks queued but not running yet, and the other CPUs would see this CPU as being overloaded, they would send an IPI over to it. The CPU would notice that the waiting RT tasks are of higher priority than the currently running task and simply schedule that CPU instead. But because the softirq was executing, before it could schedule, it would receive another IPI to do the same. The amount of IPIs would slow down the currently running softirq so much that before it could return back to task context, it would execute another softirq never allowing the CPU to schedule. This live locked that CPU.

As RT_PUSH_IPI was created to help PREEMPT_RT, make it default off if PREEMPT_RT is not enabled.

---
 kernel/sched/features.h |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -79,8 +79,16 @@ SCHED_FEAT(WARN_DOUBLE_CLOCK, false)
  * rq lock and possibly create a large contention, sending an
  * IPI to that CPU and let that CPU push the RT task to where
  * it should go may be a better scenario.
+ *
+ * This is best for PREEMPT_RT, but for non-RT it can cause issues
+ * when preemption is disabled for long periods of time. Have
+ * it only default enabled for PREEMPT_RT.
  */
+# ifdef CONFIG_PREEMPT_RT
 SCHED_FEAT(RT_PUSH_IPI, true)
+# else
+SCHED_FEAT(RT_PUSH_IPI, false)
+# endif
 #endif
 
 SCHED_FEAT(RT_RUNTIME_SHARE, false)

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

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

From: Tianxiang Chen <[email protected]>

commit a9029dd55696c651ee46912afa2a166fa456bb3e upstream.

During system reboot, cpufreq_suspend() is called via the kernel_restart() -> device_shutdown() path. Unlike the normal system suspend path, the reboot path does not call freeze_processes(), so userspace processes and kernel threads remain active.

This allows CPU hotplug operations to run concurrently with cpufreq_suspend(). The original code has no synchronization with CPU hotplug, leading to a race condition where governor_data can be freed by the hotplug path while cpufreq_suspend() is still accessing it, resulting in a null pointer dereference:

  Unable to handle kernel NULL pointer dereference
  Call Trace:
   do_kernel_fault+0x28/0x3c
   cpufreq_suspend+0xdc/0x160
   device_shutdown+0x18/0x200
   kernel_restart+0x40/0x80
   arm64_sys_reboot+0x1b0/0x200

Fix this by adding cpus_read_lock()/cpus_read_unlock() to cpufreq_suspend() to block CPU hotplug operations while suspend is in progress.

---
 drivers/cpufreq/cpufreq.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -1918,6 +1918,7 @@ void cpufreq_suspend(void)
 	if (!cpufreq_driver)
 		return;
 
+	cpus_read_lock();
 	if (!has_target() && !cpufreq_driver->suspend)
 		goto suspend;
 

@@ -1937,6 +1938,7 @@ void cpufreq_suspend(void)
 
 suspend:
 	cpufreq_suspended = true;
+	cpus_read_unlock();
 }
 
 /**

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

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

From: Yuho Choi <[email protected]>

commit 266d3dd8b757b48a576e90f018b51f7b7563cc32 upstream.

pcc_cpufreq_do_osc() calls acpi_evaluate_object() twice for the two-phase _OSC negotiation. Between the two calls it freed output.pointer but left output.length unchanged. Since acpi_evaluate_object() treats a non-zero length with a non-NULL pointer as an existing buffer to write into, the second call wrote into freed memory (use-after-free). The subsequent kfree(output.pointer) at out_free then freed the same pointer a second time (double free).

Reset output.pointer to NULL and output.length to ACPI_ALLOCATE_BUFFER after freeing the first result, so ACPICA allocates a fresh buffer for each phase independently.

---
 drivers/cpufreq/pcc-cpufreq.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -351,6 +351,8 @@ static int __init pcc_cpufreq_do_osc(acp
 	}
 
 	kfree(output.pointer);
+	output.pointer = NULL;
+	output.length = ACPI_ALLOCATE_BUFFER;
 	capabilities[0] = 0x0;
 	capabilities[1] = 0x1;
 

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

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

From: WenTao Liang <[email protected]>

commit 87bd2ad568e15b90d5f7d4bcd70342d05dad649c upstream.

In do_cpu_nanosleep(), posix_cpu_timer_create() takes a pid reference via get_pid() and stores it in timer.it.cpu.pid. If the subsequent posix_cpu_timer_set() call fails, the function returns immediately without calling posix_cpu_timer_del() to release the pid reference, causing a leak.

Fix it by calling posix_cpu_timer_del() before the unlock-and-return on the error path, consistent with the other exit paths in the same function.

---
 kernel/time/posix-cpu-timers.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1536,6 +1536,7 @@ static int do_cpu_nanosleep(const clocki
 		spin_lock_irq(&timer.it_lock);
 		error = posix_cpu_timer_set(&timer, flags, &it, NULL);
 		if (error) {
+			posix_cpu_timer_del(&timer);
 			spin_unlock_irq(&timer.it_lock);
 			return error;
 		}

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

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

From: Kartik Rajput <[email protected]>

commit ca57bf46e7a94f8c53d05c376df9fcfdcb482100 upstream.

Tegra SoCs support multiple watchdogs; currently only one (WDT0) is used. When multiple watchdogs are registered, tegra186_wdt_enable() overwrites the TKEIE(x) register, discarding any existing watchdog interrupt enable bits. As a result, enabling one watchdog inadvertently disables interrupts for the others.

Fix this by preserving the existing TKEIE(x) value and updating it using a read-modify-write sequence.

---
 drivers/clocksource/timer-tegra186.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -145,7 +145,8 @@ static void tegra186_wdt_enable(struct t
 	u32 value;
 
 	/* unmask hardware IRQ, this may have been lost across powergate */
-	value = TKEIE_WDT_MASK(wdt->index, 1);
+	value = readl(tegra->regs + TKEIE(wdt->tmr->hwirq));
+	value |= TKEIE_WDT_MASK(wdt->index, 1);
 	writel(value, tegra->regs + TKEIE(wdt->tmr->hwirq));
 
 	/* clear interrupt */

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

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

From: Lukas Wunner <[email protected]>

commit 3b626ba431c4501512ad07549310685e07fe4706 upstream.

x509_load_certificate_list() seeks to enforce that a certificate starts with 0x30 0x82 (ASN.1 SEQUENCE tag followed by a length of more than 256 and less than 65535 bytes).

But it only enforces that *either* of those two byte values are present, instead of checking for the *conjunction* of the two values. Fix it.

---
 crypto/asymmetric_keys/x509_loader.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -20,7 +20,7 @@ int x509_load_certificate_list(const u8
 		 */
 		if (end - p < 4)
 			goto dodgy_cert;
-		if (p[0] != 0x30 &&
+		if (p[0] != 0x30 ||
 		    p[1] != 0x82)
 			goto dodgy_cert;
 		plen = (p[2] << 8) | p[3];

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

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

From: Myeonghun Pak <[email protected]>

commit ec2612b8ad9e642596db011dd8b6568ef1edeaa1 upstream.

wacom_parse_and_register() starts HID hardware before registering inputs and initializing pad LEDs/remotes. Those later steps can fail, but their error paths currently release Wacom resources without stopping the HID hardware.

Route post-hid_hw_start() failures through hid_hw_stop() before releasing driver resources.

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

---
 drivers/hid/wacom_sys.c |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

@@ -2425,16 +2425,16 @@ static int wacom_parse_and_register(stru
 
 	error = wacom_register_inputs(wacom);
 	if (error)
-		goto fail;
+		goto fail_hw_stop;
 
 	if (wacom->wacom_wac.features.device_type & WACOM_DEVICETYPE_PAD) {
 		error = wacom_initialize_leds(wacom);
 		if (error)
-			goto fail;
+			goto fail_hw_stop;
 
 		error = wacom_initialize_remotes(wacom);
 		if (error)
-			goto fail;
+			goto fail_hw_stop;
 	}
 
 	if (!wireless) {

@@ -2448,14 +2448,14 @@ static int wacom_parse_and_register(stru
 		cancel_delayed_work_sync(&wacom->init_work);
 		_wacom_query_tablet_data(wacom);
 		error = -ENODEV;
-		goto fail_quirks;
+		goto fail_hw_stop;
 	}
 
 	if (features->device_type & WACOM_DEVICETYPE_WL_MONITOR) {
 		error = hid_hw_open(hdev);
 		if (error) {
 			hid_err(hdev, "hw open failed\n");
-			goto fail_quirks;
+			goto fail_hw_stop;
 		}
 	}
 

@@ -2464,7 +2464,7 @@ static int wacom_parse_and_register(stru
 
 	return 0;
 
-fail_quirks:
+fail_hw_stop:
 	hid_hw_stop(hdev);
 fail:
 	wacom_release_resources(wacom);

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

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

From: Manish Khadka <[email protected]>

commit 46c8beeccd8ab2c863827254a85ea877654a3534 upstream.

letsketch_driver does not provide a .remove callback, but letsketch_probe() arms a per-device timer:

    timer_setup(&data->inrange_timer, letsketch_inrange_timeout, 0);

The timer is re-armed from letsketch_raw_event() with a 100 ms timeout on every pen-in-range report, and its callback dereferences data->input_tablet to deliver a synthetic BTN_TOOL_PEN release.

letsketch_data is allocated with devm_kzalloc(), and its input_dev fields are devm-allocated via letsketch_setup_input_tablet(). On device unbind (USB unplug or rmmod), the HID core runs its default teardown and devm cleanup frees both letsketch_data and the input devices. Because no .remove callback exists, nothing drains the timer first: if raw_event armed it within ~100 ms of the unbind, the pending timer fires on freed memory. This is a UAF read of data and of data->input_tablet, followed by input_report_key() / input_sync() into the freed input_dev.

The same problem can occur on the probe error path: if hid_hw_start() enabled I/O on an always-poll-quirk device and then failed, raw_event may have armed the timer before devm releases data.

Fix by adding a .remove callback that calls hid_hw_stop() first. hid_hw_stop() synchronously kills the URBs that deliver raw_event(), so once it returns no path can re-arm the timer. timer_shutdown_sync() then drains any in-flight callback and permanently disables further mod_timer() calls. Apply the same timer_shutdown_sync() in the probe error path so the timer is guaranteed not to outlive data.

---
 drivers/hid/hid-letsketch.c |   36 +++++++++++++++++++++++++++++++++---
 1 file changed, 33 insertions(+), 3 deletions(-)

@@ -295,13 +295,42 @@ static int letsketch_probe(struct hid_de
 
 	ret = letsketch_setup_input_tablet(data);
 	if (ret)
-		return ret;
+		goto err_shutdown_timer;
 
 	ret = letsketch_setup_input_tablet_pad(data);
 	if (ret)
-		return ret;
+		goto err_shutdown_timer;
 
-	return hid_hw_start(hdev, HID_CONNECT_HIDRAW);
+	ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW);
+	if (ret)
+		goto err_shutdown_timer;
+
+	return 0;
+
+err_shutdown_timer:
+	/*
+	 * Drain any pending callback and permanently disable the timer
+	 * before devm releases data: if hid_hw_start() enabled I/O on an
+	 * always-poll-quirk device and then failed, raw_event may have
+	 * armed the timer already.
+	 */
+	timer_shutdown_sync(&data->inrange_timer);
+	return ret;
+}
+
+static void letsketch_remove(struct hid_device *hdev)
+{
+	struct letsketch_data *data = hid_get_drvdata(hdev);
+
+	/*
+	 * hid_hw_stop() synchronously kills the URBs that deliver
+	 * raw_event(), so once it returns no path can re-arm
+	 * inrange_timer.  timer_shutdown_sync() then drains any
+	 * in-flight callback and permanently disables further
+	 * mod_timer() calls before devm releases data.
+	 */
+	hid_hw_stop(hdev);
+	timer_shutdown_sync(&data->inrange_timer);
 }
 
 static const struct hid_device_id letsketch_devices[] = {

@@ -314,6 +343,7 @@ static struct hid_driver letsketch_drive
 	.name = "letsketch",
 	.id_table = letsketch_devices,
 	.probe = letsketch_probe,
+	.remove = letsketch_remove,
 	.raw_event = letsketch_raw_event,
 };
 module_hid_driver(letsketch_driver);

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

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

From: Maoyi Xie <[email protected]>

commit 7705b4140d188ce22656f6e541ae7ef834c7e11a upstream.

lg_g15_data is allocated with devm and holds a work item. The report handlers schedule that work straight from device input. lg_g15_event() and lg_g15_v2_event() do it on the backlight cycle key, and lg_g510_leds_event() does it too. The worker dereferences the lg_g15_data back through container_of.

The driver had no remove callback and never cancelled the work. So if a report scheduled the work and the keyboard was then unplugged, devres freed lg_g15_data while the work was still pending or running, and the worker touched freed memory. This is a use-after-free. It is reachable as a race on device unplug.

Add a remove callback that cancels the work before devres frees the state. g15->work is only initialized for the models that schedule it (G15, G15 v2, G510). The G13 and Z-10 leave it zeroed, so guard the cancel on g15->work.func to avoid cancelling a work that was never set up. The g15 NULL test mirrors the one already in lg_g15_raw_event().

---
 drivers/hid/hid-lg-g15.c |   16 ++++++++++++++++
 1 file changed, 16 insertions(+)

@@ -944,11 +944,27 @@ static const struct hid_device_id lg_g15
 };
 MODULE_DEVICE_TABLE(hid, lg_g15_devices);
 
+static void lg_g15_remove(struct hid_device *hdev)
+{
+	struct lg_g15_data *g15 = hid_get_drvdata(hdev);
+
+	/*
+	 * g15->work is only initialized for the models that schedule it
+	 * (G15, G15 v2, G510). The G13 and Z-10 leave it zeroed, so only
+	 * cancel it when it was set up.
+	 */
+	if (g15 && g15->work.func)
+		cancel_work_sync(&g15->work);
+
+	hid_hw_stop(hdev);
+}
+
 static struct hid_driver lg_g15_driver = {
 	.name			= "lg-g15",
 	.id_table		= lg_g15_devices,
 	.raw_event		= lg_g15_raw_event,
 	.probe			= lg_g15_probe,
+	.remove			= lg_g15_remove,
 };
 module_hid_driver(lg_g15_driver);
 

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

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

From: Srinivas Pandruvada <[email protected]>

commit f784fcea450617055d2d12eec5b2f6e0e38bf878 upstream.

sensor_hub_input_attr_get_raw_value() is limited to returning a single 32-bit value, which is insufficient for sensors that report data larger than 32 bits, such as a quaternion with four s16 elements.

Add sensor_hub_input_attr_read_values() that accepts a caller-provided buffer and accumulates incoming data until the buffer is full. The two paths are distinguished in sensor_hub_raw_event() by pending.max_raw_size being non-zero, preserving backward compatibility.

---
 drivers/hid/hid-sensor-hub.c   |   77 +++++++++++++++++++++++++++++++++++++----
 include/linux/hid-sensor-hub.h |   25 +++++++++++++
 2 files changed, 96 insertions(+), 6 deletions(-)

@@ -286,6 +286,54 @@ done_proc:
 }
 EXPORT_SYMBOL_GPL(sensor_hub_get_feature);
 
+int sensor_hub_input_attr_read_values(struct hid_sensor_hub_device *hsdev,
+				      u32 usage_id, u32 attr_usage_id,
+				      u32 report_id,
+				      enum sensor_hub_read_flags flag,
+				      u32 buffer_size, u8 *buffer)
+{
+	struct sensor_hub_data *data = hid_get_drvdata(hsdev->hdev);
+	struct hid_report *report;
+	unsigned long flags;
+	long cycles;
+	int ret;
+
+	report = sensor_hub_report(report_id, hsdev->hdev, HID_INPUT_REPORT);
+	if (!report)
+		return -EINVAL;
+
+	mutex_lock(hsdev->mutex_ptr);
+	if (flag == SENSOR_HUB_SYNC) {
+		memset(&hsdev->pending, 0, sizeof(hsdev->pending));
+		init_completion(&hsdev->pending.ready);
+		hsdev->pending.usage_id = usage_id;
+		hsdev->pending.attr_usage_id = attr_usage_id;
+		hsdev->pending.max_raw_size = buffer_size;
+		hsdev->pending.raw_data = buffer;
+
+		spin_lock_irqsave(&data->lock, flags);
+		hsdev->pending.status = true;
+		spin_unlock_irqrestore(&data->lock, flags);
+	}
+	mutex_lock(&data->mutex);
+	hid_hw_request(hsdev->hdev, report, HID_REQ_GET_REPORT);
+	mutex_unlock(&data->mutex);
+	ret = 0;
+	if (flag == SENSOR_HUB_SYNC) {
+		cycles = wait_for_completion_interruptible_timeout(&hsdev->pending.ready,
+								   HZ * 5);
+		if (cycles == 0)
+			ret = -ETIMEDOUT;
+		else if (cycles < 0)
+			ret = cycles;
+
+		hsdev->pending.status = false;
+	}
+	mutex_unlock(hsdev->mutex_ptr);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sensor_hub_input_attr_read_values);
 
 int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev,
 					u32 usage_id,

@@ -479,6 +527,8 @@ static int sensor_hub_raw_event(struct h
 	struct hid_collection *collection = NULL;
 	void *priv = NULL;
 	struct hid_sensor_hub_device *hsdev = NULL;
+	u32 copy_size;
+	u32 avail;
 
 	hid_dbg(hdev, "sensor_hub_raw_event report id:0x%x size:%d type:%d\n",
 			 report->id, size, report->type);

@@ -518,12 +568,27 @@ static int sensor_hub_raw_event(struct h
 					      hsdev->pending.attr_usage_id ==
 					      report->field[i]->logical)) {
 			hid_dbg(hdev, "data was pending ...\n");
-			hsdev->pending.raw_data = kmemdup(ptr, sz, GFP_ATOMIC);
-			if (hsdev->pending.raw_data)
-				hsdev->pending.raw_size = sz;
-			else
-				hsdev->pending.raw_size = 0;
-			complete(&hsdev->pending.ready);
+			if (hsdev->pending.max_raw_size) {
+				if (hsdev->pending.index < hsdev->pending.max_raw_size) {
+					avail = hsdev->pending.max_raw_size - hsdev->pending.index;
+					copy_size = clamp(sz, 0U, avail);
+
+					memcpy(hsdev->pending.raw_data + hsdev->pending.index,
+					       ptr, copy_size);
+					hsdev->pending.index += copy_size;
+					if (hsdev->pending.index >= hsdev->pending.max_raw_size) {
+						hsdev->pending.raw_size = hsdev->pending.index;
+						complete(&hsdev->pending.ready);
+					}
+				}
+			} else {
+				hsdev->pending.raw_data = kmemdup(ptr, sz, GFP_ATOMIC);
+				if (hsdev->pending.raw_data)
+					hsdev->pending.raw_size = sz;
+				else
+					hsdev->pending.raw_size = 0;
+				complete(&hsdev->pending.ready);
+			}
 		}
 		if (callback->capture_sample) {
 			if (report->field[i]->logical)

@@ -43,6 +43,8 @@ struct hid_sensor_hub_attribute_info {
  * @attr_usage_id:	Usage Id of a field, E.g. X-AXIS for a gyro.
  * @raw_size:		Response size for a read request.
  * @raw_data:		Place holder for received response.
+ * @index:		Current write index into raw_data for multi-byte reads.
+ * @max_raw_size:	Total buffer size for multi-byte reads; 0 for single-value reads.
  */
 struct sensor_hub_pending {
 	bool status;

@@ -51,6 +53,8 @@ struct sensor_hub_pending {
 	u32 attr_usage_id;
 	int raw_size;
 	u8  *raw_data;
+	u32 index;
+	u32 max_raw_size;
 };
 
 /**

@@ -183,6 +187,27 @@ int sensor_hub_input_attr_get_raw_value(
 );
 
 /**
+ * sensor_hub_input_attr_read_values() - Synchronous multi-byte read request
+ * @hsdev:		Hub device instance.
+ * @usage_id:		Attribute usage id of parent physical device as per spec
+ * @attr_usage_id:	Attribute usage id as per spec
+ * @report_id:		Report id to look for
+ * @flag:		Synchronous or asynchronous read
+ * @buffer_size:	Size of the buffer in bytes
+ * @buffer:		Buffer to store the read data
+ *
+ * Issues a synchronous or asynchronous read request for an input attribute,
+ * accumulating data into the provided buffer until it is full.
+ * Return: 0 on success, -ETIMEDOUT if the device did not respond, or a
+ * negative error code.
+ */
+int sensor_hub_input_attr_read_values(struct hid_sensor_hub_device *hsdev,
+				      u32 usage_id, u32 attr_usage_id,
+				      u32 report_id,
+				      enum sensor_hub_read_flags flag,
+				      u32 buffer_size, u8 *buffer);
+
+/**
 * sensor_hub_set_feature() - Feature set request
 * @hsdev:	Hub device instance.
 * @report_id:	Report id to look for