7.0.1-rc1 review

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

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

From: Junxi Qian <[email protected]>

commit 2b5dd4632966c39da6ba74dbc8689b309065e82c upstream.

In nfc_llcp_recv_hdlc() and nfc_llcp_recv_disc(), when the socket state is LLCP_CLOSED, the code correctly calls release_sock() and nfc_llcp_sock_put() but fails to return. Execution falls through to the remainder of the function, which calls release_sock() and nfc_llcp_sock_put() again. This results in a double release_sock() and a refcount underflow via double nfc_llcp_sock_put(), leading to a use-after-free.

Add the missing return statements after the LLCP_CLOSED branches in both functions to prevent the fall-through.

---
 net/nfc/llcp_core.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -1091,6 +1091,7 @@ static void nfc_llcp_recv_hdlc(struct nf
 	if (sk->sk_state == LLCP_CLOSED) {
 		release_sock(sk);
 		nfc_llcp_sock_put(llcp_sock);
+		return;
 	}
 
 	/* Pass the payload upstream */

@@ -1182,6 +1183,7 @@ static void nfc_llcp_recv_disc(struct nf
 	if (sk->sk_state == LLCP_CLOSED) {
 		release_sock(sk);
 		nfc_llcp_sock_put(llcp_sock);
+		return;
 	}
 
 	if (sk->sk_state == LLCP_CONNECTED) {

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

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

From: Greg Kroah-Hartman <[email protected]>

commit e597a809a2b97e927060ba182f58eb3e6101bc70 upstream.

platform_get_irq_byname() will return a negative value if an error happens, so it should be checked and not just passed directly into devm_request_threaded_irq() hoping all will be ok.

---
 drivers/gpu/drm/vc4/vc4_hdmi.c |   14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

@@ -2449,17 +2449,23 @@ static int vc4_hdmi_hotplug_init(struct
 	int ret;
 
 	if (vc4_hdmi->variant->external_irq_controller) {
-		unsigned int hpd_con = platform_get_irq_byname(pdev, "hpd-connected");
-		unsigned int hpd_rm = platform_get_irq_byname(pdev, "hpd-removed");
+		int hpd = platform_get_irq_byname(pdev, "hpd-connected");
 
-		ret = devm_request_threaded_irq(&pdev->dev, hpd_con,
+		if (hpd < 0)
+			return hpd;
+
+		ret = devm_request_threaded_irq(&pdev->dev, hpd,
 						NULL,
 						vc4_hdmi_hpd_irq_thread, IRQF_ONESHOT,
 						"vc4 hdmi hpd connected", vc4_hdmi);
 		if (ret)
 			return ret;
 
-		ret = devm_request_threaded_irq(&pdev->dev, hpd_rm,
+		hpd = platform_get_irq_byname(pdev, "hpd-removed");
+		if (hpd < 0)
+			return hpd;
+
+		ret = devm_request_threaded_irq(&pdev->dev, hpd,
 						NULL,
 						vc4_hdmi_hpd_irq_thread, IRQF_ONESHOT,
 						"vc4 hdmi hpd disconnected", vc4_hdmi);

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 8b0c25528cb64f71a73b5c0d49cbbcb68540a4ce upstream.

When auxiliary_device_add() fails, the error block calls auxiliary_device_uninit() but does not return. The uninit drops the last reference and synchronously runs bnge_aux_dev_release(), which sets bd->auxr_dev = NULL and frees the underlying object. The subsequent bd->auxr_dev->net = bd->netdev then dereferences NULL, which is not a good thing to have happen when trying to clean up from an error.

Add the missing return, as the auxiliary bus documentation states is a requirement (seems that LLM tools read documentation better than humans do...)

---
 drivers/net/ethernet/broadcom/bnge/bnge_auxr.c |    1 +
 1 file changed, 1 insertion(+)

@@ -194,6 +194,7 @@ void bnge_rdma_aux_device_add(struct bng
 		dev_warn(bd->dev, "Failed to add auxiliary device for ROCE\n");
 		auxiliary_device_uninit(aux_dev);
 		bd->flags &= ~BNGE_EN_ROCE;
+		return;
 	}
 
 	bd->auxr_dev->net = bd->netdev;

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 48bd344e1040b9f2eb512be73c13f5db83efc191 upstream.

A malicious USB device with the TASCAM US-144MKII device id can have a configuration containing bInterfaceNumber=1 but no interface 0. USB configuration descriptors are not required to assign interface numbers sequentially, so usb_ifnum_to_if(dev, 0) returns will NULL, which will then be dereferenced directly.

Fix this up by checking the return value properly.

---
 sound/usb/usx2y/us144mkii.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -420,7 +420,11 @@ static int tascam_probe(struct usb_inter
 
 	/* The device has two interfaces; we drive both from this driver. */
 	if (intf->cur_altsetting->desc.bInterfaceNumber == 1) {
-		tascam = usb_get_intfdata(usb_ifnum_to_if(dev, 0));
+		struct usb_interface *intf_zero = usb_ifnum_to_if(dev, 0);
+
+		if (!intf_zero)
+			return -ENODEV;
+		tascam = usb_get_intfdata(intf_zero);
 		if (tascam) {
 			usb_set_intfdata(intf, tascam);
 			tascam->iface1 = intf;

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 07704bbf36f57e4379e4cadf96410dab14621e3b upstream.

The status field in an EFW response is a 32-bit value supplied by the firewire device. efr_status_names[] has 17 entries so a status value outside that range goes off into the weeds when looking at the %s value.

Even worse, the status could return EFR_STATUS_INCOMPLETE which is 0x80000000, and is obviously not in that array of potential strings.

Fix this up by properly bounding the index against the array size and printing "unknown" if it's not recognized.

---
 sound/firewire/fireworks/fireworks_command.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -151,10 +151,13 @@ efw_transaction(struct snd_efw *efw, uns
 	    (be32_to_cpu(header->category) != category) ||
 	    (be32_to_cpu(header->command) != command) ||
 	    (be32_to_cpu(header->status) != EFR_STATUS_OK)) {
+		u32 st = be32_to_cpu(header->status);
+
 		dev_err(&efw->unit->device, "EFW command failed [%u/%u]: %s\n",
 			be32_to_cpu(header->category),
 			be32_to_cpu(header->command),
-			efr_status_names[be32_to_cpu(header->status)]);
+			st < ARRAY_SIZE(efr_status_names) ?
+				efr_status_names[st] : "unknown");
 		err = -EIO;
 		goto end;
 	}

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 8f98b81fe011e1879e6a7b1247e69e06a5e17af2 upstream.

Much like commit 19f953e74356 ("fbdev: fb_pm2fb: Avoid potential divide by zero error"), we also need to prevent that same crash from happening in the udlfb driver as it uses pixclock directly when dividing, which will crash.

---
 drivers/video/fbdev/tdfxfb.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -496,6 +496,9 @@ static int tdfxfb_check_var(struct fb_va
 		}
 	}
 
+	if (!var->pixclock)
+		return -EINVAL;
+
 	if (PICOS2KHZ(var->pixclock) > par->max_pixclock) {
 		DPRINTK("pixclock too high (%ldKHz)\n",
 			PICOS2KHZ(var->pixclock));

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 8f993d30b95dc9557a8a96ceca11abed674c8acb upstream.

The block_len read from the host-supplied NTB header is checked against ntb_max but has no lower bound. When block_len is smaller than opts->ndp_size, the bounds check of:

	ndp_index > (block_len - opts->ndp_size)

will underflow producing a huge unsigned value that ndp_index can never exceed, defeating the check entirely.

The same underflow occurs in the datagram index checks against block_len
- opts->dpe_size. With those checks neutered, a malicious USB host can choose ndp_index and datagram offsets that point past the actual transfer, and the skb_put_data() copies adjacent kernel memory into the network skb.

Fix this by rejecting block lengths that cannot hold at least the NTB header plus one NDP. This will make block_len - opts->ndp_size and block_len - opts->dpe_size both well-defined.

Commit 8d2b1a1ec9f5 ("CDC-NCM: avoid overflow in sanity checking") fixed a related class of issues on the host side of NCM.

---
 drivers/usb/gadget/function/f_ncm.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1210,8 +1210,8 @@ parse_ntb:
 
 	block_len = get_ncm(&tmp, opts->block_length);
 	/* (d)wBlockLength */
-	if (block_len > ntb_max) {
-		INFO(port->func.config->cdev, "OUT size exceeded\n");
+	if ((block_len < opts->nth_size + opts->ndp_size) || (block_len > ntb_max)) {
+		INFO(port->func.config->cdev, "Bad block length: %#X\n", block_len);
 		goto err;
 	}
 

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

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

From: Greg Kroah-Hartman <[email protected]>

commit c088d5dd2fffb4de1fb8e7f57751c8b82942180a upstream.

A broken/bored/mean USB host can overflow the skb_shared_info->frags[] array on a Linux gadget exposing a Phonet function by sending an unbounded sequence of full-page OUT transfers.

pn_rx_complete() finalizes the skb only when req->actual < req->length, where req->length is set to PAGE_SIZE by the gadget. If the host always sends exactly PAGE_SIZE bytes per transfer, fp->rx.skb will never be reset and each completion will add another fragment via skb_add_rx_frag(). Once nr_frags exceeds MAX_SKB_FRAGS (default 17), subsequent frag stores overwrite memory adjacent to the shinfo on the heap.

Drop the skb and account a length error when the frag limit is reached, matching the fix applied in t7xx by commit f0813bcd2d9d ("net: wwan:
t7xx: fix potential skb->frags overflow in RX path").

---
 drivers/usb/gadget/function/f_phonet.c |    9 +++++++++
 1 file changed, 9 insertions(+)

@@ -333,6 +333,15 @@ static void pn_rx_complete(struct usb_ep
 		if (unlikely(!skb))
 			break;
 
+		if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) {
+			/* Frame count from host exceeds frags[] capacity */
+			dev_kfree_skb_any(skb);
+			if (fp->rx.skb == skb)
+				fp->rx.skb = NULL;
+			dev->stats.rx_length_errors++;
+			break;
+		}
+
 		if (skb->len == 0) { /* First fragment */
 			skb->protocol = htons(ETH_P_PHONET);
 			skb_reset_mac_header(skb);

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

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

From: Greg Kroah-Hartman <[email protected]>

commit f880aac8a57ebd92abfa685d45424b2998ac1059 upstream.

The GET_STATUS and SET/CLEAR_FEATURE handlers extract the endpoint number from the host-supplied wIndex without any sort of validation. Fix this up by validating the number of endpoints actually match up with the number the device has before attempting to dereference a pointer based on this math.

This is just like what was done in commit ee0d382feb44 ("usb: gadget:
aspeed_udc: validate endpoint index for ast udc") for the aspeed driver.

---
 drivers/usb/gadget/udc/renesas_usb3.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

@@ -1669,6 +1669,10 @@ static bool usb3_std_req_get_status(stru
 		break;
 	case USB_RECIP_ENDPOINT:
 		num = le16_to_cpu(ctrl->wIndex) & USB_ENDPOINT_NUMBER_MASK;
+		if (num >= usb3->num_usb3_eps) {
+			stall = true;
+			break;
+		}
 		usb3_ep = usb3_get_ep(usb3, num);
 		if (usb3_ep->halt)
 			status |= 1 << USB_ENDPOINT_HALT;

@@ -1781,7 +1785,8 @@ static bool usb3_std_req_feature_endpoin
 	struct renesas_usb3_ep *usb3_ep;
 	struct renesas_usb3_request *usb3_req;
 
-	if (le16_to_cpu(ctrl->wValue) != USB_ENDPOINT_HALT)
+	if ((le16_to_cpu(ctrl->wValue) != USB_ENDPOINT_HALT) ||
+	    (num >= usb3->num_usb3_eps))
 		return true;	/* stall */
 
 	usb3_ep = usb3_get_ep(usb3, num);

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 3d8b9d06bd3ac4c6846f5498800b0f5f8062e53b upstream.

The bounds check uses (u8 *)ea + nlen + 1 + vlen as the end of the EA name and value, but ea_data sits at offset sizeof(struct smb2_file_full_ea_info) = 8 from ea, not at offset 0. The strncmp() later reads ea->ea_data[0..nlen-1] and the value bytes follow at ea_data[nlen+1..nlen+vlen], so the actual end is ea->ea_data + nlen + 1
+ vlen. Isn't pointer math fun?

The earlier check (u8 *)ea > end - sizeof(*ea) only guarantees the 8-byte header is in bounds, but since the last EA is placed within 8 bytes of the end of the response, the name and value bytes are read past the end of iov.

Fix this mess all up by using ea->ea_data as the base for the bounds check.

An "untrusted" server can use this to leak up to 8 bytes of kernel heap into the EA name comparison and influence which WSL xattr the data is interpreted as.

---
 fs/smb/client/smb2inode.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -128,7 +128,7 @@ static int check_wsl_eas(struct kvec *rs
 		nlen = ea->ea_name_length;
 		vlen = le16_to_cpu(ea->ea_value_length);
 		if (nlen != SMB2_WSL_XATTR_NAME_LEN ||
-		    (u8 *)ea + nlen + 1 + vlen > end)
+		    (u8 *)ea->ea_data + nlen + 1 + vlen > end)
 			return -EINVAL;
 
 		switch (vlen) {

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 3df690bba28edec865cf7190be10708ad0ddd67e upstream.

When a CREATE returns STATUS_STOPPED_ON_SYMLINK, smb2_check_message() returns success without any length validation, leaving the symlink parsers as the only defense against an untrusted server.

symlink_data() walks SMB 3.1.1 error contexts with the loop test "p < end", but reads p->ErrorId at offset 4 and p->ErrorDataLength at offset
0. When the server-controlled ErrorDataLength advances p to within 1-7 bytes of end, the next iteration will read past it. When the matching context is found, sym->SymLinkErrorTag is read at offset 4 from p->ErrorContextData with no check that the symlink header itself fits.

smb2_parse_symlink_response() then bounds-checks the substitute name using SMB2_SYMLINK_STRUCT_SIZE as the offset of PathBuffer from iov_base. That value is computed as sizeof(smb2_err_rsp) + sizeof(smb2_symlink_err_rsp), which is correct only when ErrorContextCount == 0.

With at least one error context the symlink data sits 8 bytes deeper, and each skipped non-matching context shifts it further by 8 + ALIGN(ErrorDataLength, 8). The check is too short, allowing the substitute name read to run past iov_len. The out-of-bound heap bytes are UTF-16-decoded into the symlink target and returned to userspace via readlink(2).

Fix this all up by making the loops test require the full context header to fit, rejecting sym if its header runs past end, and bound the substitute name against the actual position of sym->PathBuffer rather than a fixed offset.

Because sub_offs and sub_len are 16bits, the pointer math will not overflow here with the new greater-than.

---
 fs/smb/client/smb2file.c |   20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

@@ -27,10 +27,11 @@ static struct smb2_symlink_err_rsp *syml
 {
 	struct smb2_err_rsp *err = iov->iov_base;
 	struct smb2_symlink_err_rsp *sym = ERR_PTR(-EINVAL);
+	u8 *end = (u8 *)err + iov->iov_len;
 	u32 len;
 
 	if (err->ErrorContextCount) {
-		struct smb2_error_context_rsp *p, *end;
+		struct smb2_error_context_rsp *p;
 
 		len = (u32)err->ErrorContextCount * (offsetof(struct smb2_error_context_rsp,
 							      ErrorContextData) +

@@ -39,8 +40,7 @@ static struct smb2_symlink_err_rsp *syml
 			return ERR_PTR(-EINVAL);
 
 		p = (struct smb2_error_context_rsp *)err->ErrorData;
-		end = (struct smb2_error_context_rsp *)((u8 *)err + iov->iov_len);
-		do {
+		while ((u8 *)p + sizeof(*p) <= end) {
 			if (le32_to_cpu(p->ErrorId) == SMB2_ERROR_ID_DEFAULT) {
 				sym = (struct smb2_symlink_err_rsp *)p->ErrorContextData;
 				break;

@@ -50,14 +50,16 @@ static struct smb2_symlink_err_rsp *syml
 
 			len = ALIGN(le32_to_cpu(p->ErrorDataLength), 8);
 			p = (struct smb2_error_context_rsp *)(p->ErrorContextData + len);
-		} while (p < end);
+		}
 	} else if (le32_to_cpu(err->ByteCount) >= sizeof(*sym) &&
 		   iov->iov_len >= SMB2_SYMLINK_STRUCT_SIZE) {
 		sym = (struct smb2_symlink_err_rsp *)err->ErrorData;
 	}
 
-	if (!IS_ERR(sym) && (le32_to_cpu(sym->SymLinkErrorTag) != SYMLINK_ERROR_TAG ||
-			     le32_to_cpu(sym->ReparseTag) != IO_REPARSE_TAG_SYMLINK))
+	if (!IS_ERR(sym) &&
+	    ((u8 *)sym + sizeof(*sym) > end ||
+	     le32_to_cpu(sym->SymLinkErrorTag) != SYMLINK_ERROR_TAG ||
+	     le32_to_cpu(sym->ReparseTag) != IO_REPARSE_TAG_SYMLINK))
 		sym = ERR_PTR(-EINVAL);
 
 	return sym;

@@ -128,8 +130,10 @@ int smb2_parse_symlink_response(struct c
 	print_len = le16_to_cpu(sym->PrintNameLength);
 	print_offs = le16_to_cpu(sym->PrintNameOffset);
 
-	if (iov->iov_len < SMB2_SYMLINK_STRUCT_SIZE + sub_offs + sub_len ||
-	    iov->iov_len < SMB2_SYMLINK_STRUCT_SIZE + print_offs + print_len)
+	if ((char *)sym->PathBuffer + sub_offs + sub_len >
+		(char *)iov->iov_base + iov->iov_len ||
+	    (char *)sym->PathBuffer + print_offs + print_len >
+		(char *)iov->iov_base + iov->iov_len)
 		return -EINVAL;
 
 	return smb2_parse_native_symlink(path,

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

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

From: Borislav Petkov (AMD) <[email protected]>

commit e55d98e7756135f32150b9b8f75d580d0d4b2dd3 upstream.

Zen1's hardware divider can leave, under certain circumstances, partial results from previous operations. Those results can be leaked by another, attacker thread.

Fix that with a chicken bit.

---
 arch/x86/include/asm/msr-index.h |    3 +++
 arch/x86/kernel/cpu/amd.c        |    3 +++
 2 files changed, 6 insertions(+)

@@ -674,6 +674,9 @@
 #define MSR_AMD64_DC_CFG		0xc0011022
 #define MSR_AMD64_TW_CFG		0xc0011023
 
+#define MSR_AMD64_FP_CFG		0xc0011028
+#define MSR_AMD64_FP_CFG_ZEN1_DENORM_FIX_BIT	9
+
 #define MSR_AMD64_DE_CFG		0xc0011029
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT	 1
 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE	BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT)

@@ -943,6 +943,9 @@ static void init_amd_zen1(struct cpuinfo
 		msr_clear_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
 		clear_cpu_cap(c, X86_FEATURE_IRPERF);
 	}
+
+	pr_notice_once("AMD Zen1 FPDSS bug detected, enabling mitigation.\n");
+	msr_set_bit(MSR_AMD64_FP_CFG, MSR_AMD64_FP_CFG_ZEN1_DENORM_FIX_BIT);
 }
 
 static const struct x86_cpu_id amd_zenbleed_microcode[] = {

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 66751841212c2cc196577453c37f7774ff363f02 upstream.

smb2_get_ea() reads ea_req->EaNameLength from the client request and passes it directly to strncmp() as the comparison length without verifying that the length of the name really is the size of the input buffer received.

Fix this up by properly checking the size of the name based on the value received and the overall size of the request, to prevent a later strncmp() call to use the length as a "trusted" size of the buffer. Without this check, uninitialized heap values might be slowly leaked to the client.

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

@@ -4716,6 +4716,11 @@ static int smb2_get_ea(struct ksmbd_work
 
 		ea_req = (struct smb2_ea_info_req *)((char *)req +
 						     le16_to_cpu(req->InputBufferOffset));
+
+		if (le32_to_cpu(req->InputBufferLength) <
+		    offsetof(struct smb2_ea_info_req, name) +
+		    ea_req->EaNameLength)
+			return -EINVAL;
 	} else {
 		/* need to send all EAs, if no specific EA is requested*/
 		if (le32_to_cpu(req->Flags) & SL_RETURN_SINGLE_ENTRY)

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 53370cf9090777774e07fd9a8ebce67c6cc333ab upstream.

parse_dacl() compares each ACE SID against sid_unix_NFS_mode and on match reads sid.sub_auth[2] as the file mode. If sid_unix_NFS_mode is the prefix S-1-5-88-3 with num_subauth = 2 then compare_sids() compares only min(num_subauth, 2) sub-authorities so a client SID with num_subauth = 2 and sub_auth = {88, 3} will match.

If num_subauth = 2 and the ACE is placed at the very end of the security descriptor, sub_auth[2] will be 4 bytes past end_of_acl. The out-of-band bytes will then be masked to the low 9 bits and applied as the file's POSIX mode, probably not something that is good to have happen.

Fix this up by forcing the SID to actually carry a third sub-authority before reading it at all.

---
 fs/smb/server/smbacl.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -451,7 +451,8 @@ static void parse_dacl(struct mnt_idmap
 		ppace[i]->access_req =
 			smb_map_generic_desired_access(ppace[i]->access_req);
 
-		if (!(compare_sids(&ppace[i]->sid, &sid_unix_NFS_mode))) {
+		if (ppace[i]->sid.num_subauth >= 3 &&
+		    !(compare_sids(&ppace[i]->sid, &sid_unix_NFS_mode))) {
 			fattr->cf_mode =
 				le32_to_cpu(ppace[i]->sid.sub_auth[2]);
 			break;

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

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

From: Greg Kroah-Hartman <[email protected]>

commit ad0057fb91218914d6c98268718ceb9d59b388e1 upstream.

The kernel ASN.1 BER decoder calls action callbacks incrementally as it walks the input. When ksmbd_decode_negTokenInit() reaches the mechToken
[2] OCTET STRING element, ksmbd_neg_token_alloc() allocates conn->mechToken immediately via kmemdup_nul(). If a later element in the same blob is malformed, then the decoder will return nonzero after the allocation is already live. This could happen if mechListMIC [3] overrunse the enclosing SEQUENCE.

decode_negotiation_token() then sets conn->use_spnego = false because both the negTokenInit and negTokenTarg grammars failed. The cleanup at the bottom of smb2_sess_setup() is gated on use_spnego:

	if (conn->use_spnego && conn->mechToken) {
		kfree(conn->mechToken);
		conn->mechToken = NULL;
	}

so the kfree is skipped, causing the mechToken to never be freed.

This codepath is reachable pre-authentication, so untrusted clients can cause slow memory leaks on a server without even being properly authenticated.

Fix this up by not checking check for use_spnego, as it's not required, so the memory will always be properly freed. At the same time, always free the memory in ksmbd_conn_free() incase some other failure path forgot to free it.

---
 fs/smb/server/connection.c |    1 +
 fs/smb/server/smb2pdu.c    |    2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

@@ -96,6 +96,7 @@ void ksmbd_conn_free(struct ksmbd_conn *
 	xa_destroy(&conn->sessions);
 	kvfree(conn->request_buf);
 	kfree(conn->preauth_info);
+	kfree(conn->mechToken);
 	if (atomic_dec_and_test(&conn->refcnt)) {
 		conn->transport->ops->free_transport(conn->transport);
 		kfree(conn);

@@ -1915,7 +1915,7 @@ out_err:
 	else if (rc)
 		rsp->hdr.Status = STATUS_LOGON_FAILURE;
 
-	if (conn->use_spnego && conn->mechToken) {
+	if (conn->mechToken) {
 		kfree(conn->mechToken);
 		conn->mechToken = NULL;
 	}

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

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

From: Stefan Metzmacher <[email protected]>

commit 27b7c3e916218b5eb2ee350211140e961bfc49be upstream.

smbd_send_batch_flush() already calls smbd_free_send_io(), so we should not call it again after smbd_post_send() moved it to the batch list.

---
 fs/smb/client/smbdirect.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -1551,17 +1551,25 @@ static int smbd_post_send_iter(struct sm
 
 	rc = smbd_post_send(sc, batch, request);
 	if (!rc) {
+		/*
+		 * From here request is moved to batch
+		 * and we should not free it explicitly.
+		 */
+
 		if (batch != &_batch)
 			return 0;
 
 		rc = smbd_send_batch_flush(sc, batch, true);
 		if (!rc)
 			return 0;
+
+		goto err_flush;
 	}
 
 err_dma:
 	smbd_free_send_io(request);
 
+err_flush:
 err_alloc:
 	atomic_inc(&sc->send_io.credits.count);
 	wake_up(&sc->send_io.credits.wait_queue);

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

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

From: Stefan Metzmacher <[email protected]>

commit 84ff995ae826aa6bbcc6c7b9ea569ff67c021d72 upstream.

smb_direct_flush_send_list() already calls smb_direct_free_sendmsg(), so we should not call it again after post_sendmsg()
moved it to the batch list.

---
 fs/smb/server/transport_rdma.c |    8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

@@ -1588,15 +1588,21 @@ static int smb_direct_post_send_data(str
 	if (ret)
 		goto err;
 
+	/*
+	 * From here msg is moved to send_ctx
+	 * and we should not free it explicitly.
+	 */
+
 	if (send_ctx == &_send_ctx) {
 		ret = smb_direct_flush_send_list(sc, send_ctx, true);
 		if (ret)
-			goto err;
+			goto flush_failed;
 	}
 
 	return 0;
 err:
 	smb_direct_free_sendmsg(sc, msg);
+flush_failed:
 header_failed:
 	atomic_inc(&sc->send_io.credits.count);
 credit_failed:

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

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

From: Nathan Rebello <[email protected]>

commit 2ab833a16a825373aad2ba7d54b572b277e95b71 upstream.

When a USB/IP client receives a RET_SUBMIT response, usbip_pack_ret_submit() unconditionally overwrites urb->number_of_packets from the network PDU. This value is subsequently used as the loop bound in usbip_recv_iso() and usbip_pad_iso() to iterate over urb->iso_frame_desc[], a flexible array whose size was fixed at URB allocation time based on the *original* number_of_packets from the CMD_SUBMIT.

A malicious USB/IP server can set number_of_packets in the response to a value larger than what was originally submitted, causing a heap out-of-bounds write when usbip_recv_iso() writes to urb->iso_frame_desc[i] beyond the allocated region.

KASAN confirmed this with kernel 7.0.0-rc5:

  BUG: KASAN: slab-out-of-bounds in usbip_recv_iso+0x46a/0x640
  Write of size 4 at addr ffff888106351d40 by task vhci_rx/69

The buggy address is located 0 bytes to the right of
allocated 320-byte region [ffff888106351c00, ffff888106351d40)

The server side (stub_rx.c) and gadget side (vudc_rx.c) already validate number_of_packets in the CMD_SUBMIT path since commits c6688ef9f297 ("usbip: fix stub_rx: harden CMD_SUBMIT path to handle malicious input") and b78d830f0049 ("usbip: fix vudc_rx: harden CMD_SUBMIT path to handle malicious input"). The server side validates against USBIP_MAX_ISO_PACKETS because no URB exists yet at that point. On the client side we have the original URB, so we can use the tighter
bound: the response must not exceed the original number_of_packets.

This mirrors the existing validation of actual_length against transfer_buffer_length in usbip_recv_xbuff(), which checks the response value against the original allocation size.

Kelvin Mbogo's series ("usb: usbip: fix integer overflow in usbip_recv_iso()", v2) hardens the receive-side functions themselves; this patch complements that work by catching the bad value at its source -- in usbip_pack_ret_submit() before the overwrite -- and using the tighter per-URB allocation bound rather than the global USBIP_MAX_ISO_PACKETS limit.

Fix this by checking rpdu->number_of_packets against urb->number_of_packets in usbip_pack_ret_submit() before the overwrite. On violation, clamp to zero so that usbip_recv_iso() and usbip_pad_iso() safely return early.

---
 drivers/usb/usbip/usbip_common.c |   12 ++++++++++++
 1 file changed, 12 insertions(+)

@@ -470,6 +470,18 @@ static void usbip_pack_ret_submit(struct
 		urb->status		= rpdu->status;
 		urb->actual_length	= rpdu->actual_length;
 		urb->start_frame	= rpdu->start_frame;
+		/*
+		 * The number_of_packets field determines the length of
+		 * iso_frame_desc[], which is a flexible array allocated
+		 * at URB creation time. A response must never claim more
+		 * packets than originally submitted; doing so would cause
+		 * an out-of-bounds write in usbip_recv_iso() and
+		 * usbip_pad_iso(). Clamp to zero on violation so both
+		 * functions safely return early.
+		 */
+		if (rpdu->number_of_packets < 0 ||
+		    rpdu->number_of_packets > urb->number_of_packets)
+			rpdu->number_of_packets = 0;
 		urb->number_of_packets = rpdu->number_of_packets;
 		urb->error_count	= rpdu->error_count;
 	}

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

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

From: Alexey Charkov <[email protected]>

commit 6b9db53197094f38a18797495df2e3c758ec51dc upstream.

FUSB302 fails to probe with -EINVAL if its interrupt line is connected via an I2C GPIO expander, such as TI TCA6416.

Switch the interrupt handler to a threaded one, which also works behind such GPIO expanders.

---
 drivers/usb/typec/tcpm/fusb302.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

@@ -1755,8 +1755,9 @@ static int fusb302_probe(struct i2c_clie
 		goto destroy_workqueue;
 	}
 
-	ret = request_irq(chip->gpio_int_n_irq, fusb302_irq_intn,
-			  IRQF_TRIGGER_LOW, "fsc_interrupt_int_n", chip);
+	ret = request_threaded_irq(chip->gpio_int_n_irq, NULL, fusb302_irq_intn,
+				   IRQF_ONESHOT | IRQF_TRIGGER_LOW,
+				   "fsc_interrupt_int_n", chip);
 	if (ret < 0) {
 		dev_err(dev, "cannot request IRQ for GPIO Int_N, ret=%d", ret);
 		goto tcpm_unregister_port;

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

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

From: Daniel Brát <[email protected]>

commit 609865ab3d5d803556f628e221ecd3d06aed9f30 upstream.

Expands range of matched bcdDevice values for the VL817 quirk entry. This is based on experience with Axagon EE35-GTR rev1 3.5" HDD enclosure, which reports its bcdDevice as 0x0843, but presumably other vendors using this IC in their products may set it to any other value.

---
 drivers/usb/storage/unusual_devs.h |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

@@ -2350,10 +2350,11 @@ UNUSUAL_DEV(  0x2027, 0xa001, 0x0000, 0x
 		US_FL_SCM_MULT_TARG ),
 
 /*
- * Reported by DocMAX <[email protected]>
- * and Thomas Weißschuh <[email protected]>
+ * Reported by DocMAX <[email protected]>,
+ * Thomas Weißschuh <[email protected]>
+ * and Daniel Brát <[email protected]>
  */
-UNUSUAL_DEV( 0x2109, 0x0715, 0x9999, 0x9999,
+UNUSUAL_DEV( 0x2109, 0x0715, 0x0000, 0x9999,
 		"VIA Labs, Inc.",
 		"VL817 SATA Bridge",
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,

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

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

From: Dave Carey <[email protected]>

commit f58752ebcb35e156c85cd1a82d6579c7af3b9023 upstream.

The Lenovo Yoga Book 9 14IAH10 (83KJ) has a composite USB device (17EF:6161) that controls both touchscreens via a CDC ACM interface. Interface 0 is a standard CDC ACM control interface, but interface 1 (the data interface) incorrectly declares vendor-specific class (0xFF) instead of USB_CLASS_CDC_DATA. cdc-acm rejects the device at probe with -EINVAL, leaving interface 0 unbound and EP 0x82 never polled.

With no consumer polling EP 0x82, the firmware's watchdog fires every ~20 seconds and resets the USB bus, producing a continuous disconnect/ reconnect loop that prevents the touchscreens from ever initialising.

Add two new quirk flags:

VENDOR_CLASS_DATA_IFACE: Bypasses the bInterfaceClass check in acm_probe() that would otherwise reject the vendor-class data interface with -EINVAL.

ALWAYS_POLL_CTRL: Submits the notification URB at probe() rather than waiting for a TTY open. This keeps EP 0x82 polled at all times, permanently suppressing the firmware watchdog. The URB is resubmitted after port_shutdown() and on system resume. SET_CONTROL_LINE_STATE (DTR|RTS) is sent at probe and after port_shutdown() to complete firmware handshake.

Note: the firmware performs exactly 4 USB connect/disconnect cycles (~19 s each) on every cold boot before stabilising. This is a fixed firmware property; touch is available ~75-80 s after power-on.

---
 drivers/usb/class/cdc-acm.c |   53 ++++++++++++++++++++++++++++++++++++++------
 1 file changed, 46 insertions(+), 7 deletions(-)

@@ -114,6 +114,8 @@ static int acm_ctrl_msg(struct acm *acm,
 	int retval;
 
 	retval = usb_autopm_get_interface(acm->control);
+#define VENDOR_CLASS_DATA_IFACE		BIT(9)  /* data interface uses vendor-specific class */
+#define ALWAYS_POLL_CTRL		BIT(10) /* keep ctrl URB active even without an open TTY */
 	if (retval)
 		return retval;
 

@@ -710,12 +712,14 @@ static int acm_port_activate(struct tty_
 	set_bit(TTY_NO_WRITE_SPLIT, &tty->flags);
 	acm->control->needs_remote_wakeup = 1;
 
-	acm->ctrlurb->dev = acm->dev;
-	retval = usb_submit_urb(acm->ctrlurb, GFP_KERNEL);
-	if (retval) {
-		dev_err(&acm->control->dev,
-			"%s - usb_submit_urb(ctrl irq) failed\n", __func__);
-		goto error_submit_urb;
+	if (!(acm->quirks & ALWAYS_POLL_CTRL)) {
+		acm->ctrlurb->dev = acm->dev;
+		retval = usb_submit_urb(acm->ctrlurb, GFP_KERNEL);
+		if (retval) {
+			dev_err(&acm->control->dev,
+				"%s - usb_submit_urb(ctrl irq) failed\n", __func__);
+			goto error_submit_urb;
+		}
 	}
 
 	acm_tty_set_termios(tty, NULL);

@@ -788,6 +792,14 @@ static void acm_port_shutdown(struct tty
 
 	acm_unpoison_urbs(acm);
 
+	if (acm->quirks & ALWAYS_POLL_CTRL) {
+		acm->ctrlurb->dev = acm->dev;
+		if (usb_submit_urb(acm->ctrlurb, GFP_KERNEL))
+			dev_dbg(&acm->control->dev,
+				"ctrl polling restart failed after port close\n");
+		/* port_shutdown() cleared DTR/RTS; restore them */
+		acm_set_control(acm, USB_CDC_CTRL_DTR | USB_CDC_CTRL_RTS);
+	}
 }
 
 static void acm_tty_cleanup(struct tty_struct *tty)

@@ -1328,6 +1340,9 @@ skip_normal_probe:
 			dev_dbg(&intf->dev,
 				"Your device has switched interfaces.\n");
 			swap(control_interface, data_interface);
+		} else if (quirks & VENDOR_CLASS_DATA_IFACE) {
+			dev_dbg(&intf->dev,
+				"Vendor-specific data interface class, continuing.\n");
 		} else {
 			return -EINVAL;
 		}

@@ -1522,6 +1537,9 @@ skip_countries:
 	acm->line.bDataBits = 8;
 	acm_set_line(acm, &acm->line);
 
+	if (quirks & ALWAYS_POLL_CTRL)
+		acm_set_control(acm, USB_CDC_CTRL_DTR | USB_CDC_CTRL_RTS);
+
 	if (!acm->combined_interfaces) {
 		rv = usb_driver_claim_interface(&acm_driver, data_interface, acm);
 		if (rv)

@@ -1543,6 +1561,13 @@ skip_countries:
 
 	dev_info(&intf->dev, "ttyACM%d: USB ACM device\n", minor);
 
+	if (acm->quirks & ALWAYS_POLL_CTRL) {
+		acm->ctrlurb->dev = acm->dev;
+		if (usb_submit_urb(acm->ctrlurb, GFP_KERNEL))
+			dev_warn(&intf->dev,
+				 "failed to start persistent ctrl polling\n");
+	}
+
 	return 0;
 
 err_release_data_interface:

@@ -1669,7 +1694,7 @@ static int acm_resume(struct usb_interfa
 
 	acm_unpoison_urbs(acm);
 
-	if (tty_port_initialized(&acm->port)) {
+	if (tty_port_initialized(&acm->port) || (acm->quirks & ALWAYS_POLL_CTRL)) {
 		rv = usb_submit_urb(acm->ctrlurb, GFP_ATOMIC);
 
 		for (;;) {

@@ -2016,6 +2041,20 @@ static const struct usb_device_id acm_id
 	/* CH343 supports CAP_BRK, but doesn't advertise it */
 	{ USB_DEVICE(0x1a86, 0x55d3), .driver_info = MISSING_CAP_BRK, },
 
+	/*
+	 * Lenovo Yoga Book 9 14IAH10 (83KJ) — INGENIC 17EF:6161 touchscreen
+	 * composite device.  The CDC ACM control interface (0) uses a standard
+	 * Union descriptor, but the data interface (1) is declared as vendor-
+	 * specific class (0xff) with no CDC data descriptors, so cdc-acm would
+	 * normally reject it.  The firmware also requires continuous polling of
+	 * the notification endpoint (EP 0x82) to suppress a 20-second watchdog
+	 * reset; ALWAYS_POLL_CTRL keeps the ctrlurb active even when no TTY is
+	 * open.  Match only the control interface by class to avoid probing the
+	 * vendor-specific data interface.
+	 */
+	{ USB_DEVICE_INTERFACE_CLASS(0x17ef, 0x6161, USB_CLASS_COMM),
+	  .driver_info = VENDOR_CLASS_DATA_IFACE | ALWAYS_POLL_CTRL },
+
 	/* control interfaces without any protocol set */
 	{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
 		USB_CDC_PROTO_NONE) },

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

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

From: Michael Zimmermann <[email protected]>

commit 81ebd43cc0d6d106ce7b6ccbf7b5e40ca7f5503d upstream.

When calling unbind, then bind again, cdev_init reinitialized the cdev, even though there may still be references to it. That's the case when the /dev/hidg* device is still opened. This obviously unsafe behavior like oopes.

This fixes this by using cdev_alloc to put the cdev on the heap. That way, we can simply allocate a new one in hidg_bind.

---
 drivers/usb/gadget/function/f_hid.c |   15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

@@ -106,7 +106,7 @@ struct f_hidg {
 	struct list_head		report_list;
 
 	struct device			dev;
-	struct cdev			cdev;
+	struct cdev			*cdev;
 	struct usb_function		func;
 
 	struct usb_ep			*in_ep;

@@ -749,8 +749,9 @@ static int f_hidg_release(struct inode *
 
 static int f_hidg_open(struct inode *inode, struct file *fd)
 {
+	struct kobject *parent = inode->i_cdev->kobj.parent;
 	struct f_hidg *hidg =
-		container_of(inode->i_cdev, struct f_hidg, cdev);
+		container_of(parent, struct f_hidg, dev.kobj);
 
 	fd->private_data = hidg;
 

@@ -1276,8 +1277,12 @@ static int hidg_bind(struct usb_configur
 	}
 
 	/* create char device */
-	cdev_init(&hidg->cdev, &f_hidg_fops);
-	status = cdev_device_add(&hidg->cdev, &hidg->dev);
+	hidg->cdev = cdev_alloc();
+	if (!hidg->cdev)
+		goto fail_free_all;
+	hidg->cdev->ops = &f_hidg_fops;
+
+	status = cdev_device_add(hidg->cdev, &hidg->dev);
 	if (status)
 		goto fail_free_all;
 

@@ -1579,7 +1584,7 @@ static void hidg_unbind(struct usb_confi
 {
 	struct f_hidg *hidg = func_to_hidg(f);
 
-	cdev_device_del(&hidg->cdev, &hidg->dev);
+	cdev_device_del(hidg->cdev, &hidg->dev);
 	destroy_workqueue(hidg->workqueue);
 	usb_free_all_descriptors(f);
 }

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

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

From: Samuel Page <[email protected]>

commit a535a9217ca3f2fccedaafb2fddb4c48f27d36dc upstream.

raw_release() unregisters raw CAN receive filters via can_rx_unregister(), but receiver deletion is deferred with call_rcu(). This leaves a window where raw_rcv() may still be running in an RCU read-side critical section after raw_release() frees ro->uniq, leading to a use-after-free of the percpu uniq storage.

Move free_percpu(ro->uniq) out of raw_release() and into a raw-specific socket destructor. can_rx_unregister() takes an extra reference to the socket and only drops it from the RCU callback, so freeing uniq from sk_destruct ensures the percpu area is not released until the relevant callbacks have drained.

---
 net/can/raw.c |   11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

@@ -361,6 +361,14 @@ static int raw_notifier(struct notifier_
 	return NOTIFY_DONE;
 }
 
+static void raw_sock_destruct(struct sock *sk)
+{
+	struct raw_sock *ro = raw_sk(sk);
+
+	free_percpu(ro->uniq);
+	can_sock_destruct(sk);
+}
+
 static int raw_init(struct sock *sk)
 {
 	struct raw_sock *ro = raw_sk(sk);

@@ -387,6 +395,8 @@ static int raw_init(struct sock *sk)
 	if (unlikely(!ro->uniq))
 		return -ENOMEM;
 
+	sk->sk_destruct = raw_sock_destruct;
+
 	/* set notifier */
 	spin_lock(&raw_notifier_lock);
 	list_add_tail(&ro->notifier, &raw_notifier_list);

@@ -436,7 +446,6 @@ static int raw_release(struct socket *so
 	ro->bound = 0;
 	ro->dev = NULL;
 	ro->count = 0;
-	free_percpu(ro->uniq);
 
 	sock_orphan(sk);
 	sock->sk = NULL;

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

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

From: Xu Yang <[email protected]>

commit b84cc80610a8ce036deb987f056ce3196ead7f1e upstream.

When a port is disabled, an attached device will be disconnected. This causes a port-status-change event, which will race with hub autosuspend (if the disabled port was the only connected port on its hub), causing an immediate resume and a second autosuspend. Both of these can be avoided by adding a short delay after the call to usb_hub_set_port_power().

Below log shows what is happening:

$ echo 1 > usb1-port1/disable
[   37.958239] usb 1-1: USB disconnect, device number 2
[   37.964101] usb 1-1: unregistering device
[   37.970070] hub 1-0:1.0: hub_suspend
[   37.971305] hub 1-0:1.0: state 7 ports 1 chg 0000 evt 0002
[   37.974412] usb usb1: bus auto-suspend, wakeup 1
[   37.988175] usb usb1: suspend raced with wakeup event         <---
[   37.993947] usb usb1: usb auto-resume
[   37.998401] hub 1-0:1.0: hub_resume
[   38.105688] usb usb1-port1: status 0000, change 0000, 12 Mb/s
[   38.112399] hub 1-0:1.0: state 7 ports 1 chg 0000 evt 0000
[   38.118645] hub 1-0:1.0: hub_suspend
[   38.122963] usb usb1: bus auto-suspend, wakeup 1
[   38.200368] usb usb1: usb wakeup-resume
[   38.204982] usb usb1: usb auto-resume
[   38.209376] hub 1-0:1.0: hub_resume
[   38.213676] usb usb1-port1: status 0101 change 0001
[   38.321552] hub 1-0:1.0: state 7 ports 1 chg 0002 evt 0000
[   38.327978] usb usb1-port1: status 0101, change 0000, 12 Mb/s
[   38.457429] usb 1-1: new high-speed USB device number 3 using ci_hdrc

Then, port change bit will be fixed to the final state and usb_clear_port_feature() can correctly clear it after this period. This will also avoid usb runtime suspend routine to run because usb_autopm_put_interface() not run yet.

---
 drivers/usb/core/port.c |    1 +
 1 file changed, 1 insertion(+)

@@ -141,6 +141,7 @@ static ssize_t disable_store(struct devi
 		usb_disconnect(&port_dev->child);
 
 	rc = usb_hub_set_port_power(hdev, hub, port1, !disabled);
+	msleep(2 * hub_power_on_good_delay(hub));
 
 	if (disabled) {
 		usb_clear_port_feature(hdev, port1, USB_PORT_FEAT_C_CONNECTION);

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

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

From: Greg Kroah-Hartman <[email protected]>

commit c0128c7157d639a931353ea344fb44aad6d6e17a upstream.

The first byte of an i2c SMBUS message is the size, and it should be verified to ensure that it is in the range of 0..I2C_SMBUS_BLOCK_MAX before processing it.

This is the same logic that was added in commit a6e04f05ce0b ("i2c:
tegra: check msg length in SMBUS block read") to the i2c tegra driver.

---
 drivers/i2c/busses/i2c-s3c2410.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

@@ -503,8 +503,13 @@ static void i2c_s3c_irq_nextbyte(struct
 		i2c->msg->buf[i2c->msg_ptr++] = byte;
 
 		/* Add actual length to read for smbus block read */
-		if (i2c->msg->flags & I2C_M_RECV_LEN && i2c->msg->len == 1)
+		if (i2c->msg->flags & I2C_M_RECV_LEN && i2c->msg->len == 1) {
+			if (byte == 0 || byte > I2C_SMBUS_BLOCK_MAX) {
+				s3c24xx_i2c_stop(i2c, -EPROTO);
+				break;
+			}
 			i2c->msg->len += byte;
+		}
  prepare_read:
 		if (is_msglast(i2c)) {
 			/* last byte of buffer */

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

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

From: Lin YuChen <[email protected]>

commit 8c964b82a4e97ec7f25e17b803ee196009b38a57 upstream.

Initialize le_tmp64 to zero in rtw_BIP_verify() to prevent using uninitialized data.

Smatch warns that only 6 bytes are copied to this 8-byte (u64) variable, leaving the last two bytes uninitialized:

drivers/staging/rtl8723bs/core/rtw_security.c:1308 rtw_BIP_verify()
warn: not copying enough bytes for '&le_tmp64' (8 vs 6 bytes)

Initializing the variable at the start of the function fixes this warning and ensures predictable behavior.

---
 drivers/staging/rtl8723bs/core/rtw_security.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1291,7 +1291,7 @@ u32 rtw_BIP_verify(struct adapter *padap
 	u8 mic[16];
 	struct mlme_ext_priv *pmlmeext = &padapter->mlmeextpriv;
 	__le16 le_tmp;
-	__le64 le_tmp64;
+	__le64 le_tmp64 = 0;
 
 	ori_len = pattrib->pkt_len - WLAN_HDR_A3_LEN + BIP_AAD_SIZE;
 	BIP_AAD = kzalloc(ori_len, GFP_KERNEL);

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 1badfc4319224820d5d890f8eab6aa52e4e83339 upstream.

Commit ecfa6f34492c ("HID: Add HID_CLAIMED_INPUT guards in raw_event callbacks missing them") attempted to fix up the HID drivers that had missed the previous fix that was done in 2ff5baa9b527 ("HID: appleir:
Fix potential NULL dereference at raw event handle"), but the alps driver was missed.

Fix this up by properly checking in the hid-alps driver that it had been claimed correctly before attempting to process the raw event.

---
 drivers/hid/hid-alps.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -437,6 +437,9 @@ static int alps_raw_event(struct hid_dev
 	int ret = 0;
 	struct alps_dev *hdata = hid_get_drvdata(hdev);
 
+	if (!(hdev->claimed & HID_CLAIMED_INPUT) || !hdata->input)
+		return 0;
+
 	switch (hdev->product) {
 	case HID_PRODUCT_ID_T4_BTNLESS:
 		ret = t4_raw_event(hdata, data, size);

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 69c02ffde6ed4d535fa4e693a9e572729cad3d0d upstream.

s32ton() shifts by n-1 where n is the field's report_size, a value that comes directly from a HID device. The HID parser bounds report_size only to <= 256, so a broken HID device can supply a report descriptor with a wide field that triggers shift exponents up to 256 on a 32-bit type when an output report is built via hid_output_field() or hid_set_field().

Commit ec61b41918587 ("HID: core: fix shift-out-of-bounds in hid_report_raw_event") added the same n > 32 clamp to the function snto32(), but s32ton() was never given the same fix as I guess syzbot hadn't figured out how to fuzz a device the same way.

Fix this up by just clamping the max value of n, just like snto32() does.

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

@@ -71,6 +71,9 @@ static u32 s32ton(__s32 value, unsigned
 	if (!value || !n)
 		return 0;
 
+	if (n > 32)
+		n = 32;
+
 	a = value >> (n - 1);
 	if (a && a != -1)
 		return value < 0 ? 1 << (n - 1) : (1 << (n - 1)) - 1;

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 600dc40554dc5ad1e6f3af51f700228033f43ea7 upstream.

A malicious USB device claiming to be a CDC Phonet modem can overflow the skb_shared_info->frags[] array by sending an unbounded sequence of full-page bulk transfers.

Drop the skb and increment the length error when the frag limit is reached. This matches the same fix that commit f0813bcd2d9d ("net:
wwan: t7xx: fix potential skb->frags overflow in RX path") did for the t7xx driver.

---
 drivers/net/usb/cdc-phonet.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

@@ -157,11 +157,16 @@ static void rx_complete(struct urb *req)
 						PAGE_SIZE);
 				page = NULL;
 			}
-		} else {
+		} else if (skb_shinfo(skb)->nr_frags < MAX_SKB_FRAGS) {
 			skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 					page, 0, req->actual_length,
 					PAGE_SIZE);
 			page = NULL;
+		} else {
+			dev_kfree_skb_any(skb);
+			pnd->rx_skb = NULL;
+			skb = NULL;
+			dev->stats.rx_length_errors++;
 		}
 		if (req->actual_length < PAGE_SIZE)
 			pnd->rx_skb = NULL; /* Last fragment */

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

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

From: Greg Kroah-Hartman <[email protected]>

commit 46ce8be2ced389bccd84bcc04a12cf2f4d0c22d1 upstream.

The NFC-A anti-collision cascade in digital_in_recv_sdd_res() appends 3 or 4 bytes to target->nfcid1 on each round, but the number of cascade rounds is controlled entirely by the peer device. The peer sets the cascade tag in the SDD_RES (deciding 3 vs 4 bytes) and the cascade-incomplete bit in the SEL_RES (deciding whether another round follows).

ISO 14443-3 limits NFC-A to three cascade levels and target->nfcid1 is sized accordingly (NFC_NFCID1_MAXSIZE = 10), but nothing in the driver actually enforces this. This means a malicious peer can keep the cascade running, writing past the heap-allocated nfc_target with each round.

Fix this by rejecting the response when the accumulated UID would exceed the buffer.

Commit e329e71013c9 ("NFC: nci: Bounds check struct nfc_target arrays") fixed similar missing checks against the same field on the NCI path.

---
 net/nfc/digital_technology.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -424,6 +424,12 @@ static void digital_in_recv_sdd_res(stru
 		size = 4;
 	}
 
+	if (target->nfcid1_len + size > NFC_NFCID1_MAXSIZE) {
+		PROTOCOL_ERR("4.7.2.1");
+		rc = -EPROTO;
+		goto exit;
+	}
+
 	memcpy(target->nfcid1 + target->nfcid1_len, sdd_res->nfcid1 + offset,
 	       size);
 	target->nfcid1_len += size;

This is the start of the stable review cycle for the 7.0.1 release. There are 76 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Wed, 22 Apr 2026 15:38:50 +0000. Anything received after that time might be too late.

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

	https://www.kernel.org/pub/linux/kernel/v7.x/stable-review/patch-7.0.1-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-7.0.y
and the diffstat can be found below.

thanks,

greg k-h

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

Greg Kroah-Hartman <[email protected]>

    Linux 7.0.1-rc1

Jianhui Zhou <[email protected]>
mm/userfaultfd: fix hugetlb fault mutex hash calculation

Jeongjun Park <[email protected]>
media: hackrf: fix to not free memory after the device is registered in hackrf_probe()

Abd-Alrhman Masalkhi <[email protected]>
media: vidtv: fix pass-by-value structs causing MSAN warnings

Deepanshu Kartikey <[email protected]>
nilfs2: fix NULL i_assoc_inode dereference in nilfs_mdt_save_to_shadow_map

Jeongjun Park <[email protected]>
media: as102: fix to not free memory after the device is registered in as102_usb_probe()

Shardul Bankar <[email protected]>
wireguard: device: use exit_rtnl callback instead of manual rtnl_lock in pre_exit

Mingzhe Zou <[email protected]>
bcache: fix cached_dev.sb_bio use-after-free and crash

Berk Cem Goksel <[email protected]>
ALSA: 6fire: fix use-after-free on disconnect

Sanman Pradhan <[email protected]>
hwmon: (powerz) Fix use-after-free on USB disconnect

Abhishek Kumar <[email protected]>

    media: em28xx: fix use-after-free in em28xx_v4l2_open()

Fan Wu <[email protected]>
media: mediatek: vcodec: fix use-after-free in encoder release path

Ruslan Valiyev <[email protected]>
media: vidtv: fix nfeeds state corruption on start_streaming failure

Breno Leitao <[email protected]>
mm: blk-cgroup: fix use-after-free in cgwb_release_workfn()

Ritesh Harjani (IBM) <[email protected]>
mm/kasan: fix double free for kasan pXds

Srinivas Kandagatla <[email protected]>
ASoC: qcom: q6apm: move component registration to unmanaged version

Sean Christopherson <[email protected]>
KVM: x86: Use scratch field in MMIO fragment to hold small write values

Linus Torvalds <[email protected]>
x86-64/arm64/powerpc: clean up and rename __copy_from_user_flushcache

Linus Torvalds <[email protected]>
x86: rename and clean up __copy_from_user_inatomic_nocache()

Linus Torvalds <[email protected]>
x86-64: rename misleadingly named '__copy_user_nocache()' function

Sasha Levin <[email protected]>
checkpatch: add support for Assisted-by tag

Matthew Wilcox (Oracle) <[email protected]>

    mm: call ->free_folio() directly in folio_unmap_invalidate()

Sean Christopherson <[email protected]>
KVM: SEV: Drop WARN on large size for KVM_MEMORY_ENCRYPT_REG_REGION

Sean Christopherson <[email protected]>
KVM: SEV: Lock all vCPUs when synchronzing VMSAs for SNP launch finish

Sean Christopherson <[email protected]>
KVM: SEV: Disallow LAUNCH_FINISH if vCPUs are actively being created

Sean Christopherson <[email protected]>

    KVM: SEV: Protect *all* of sev_mem_enc_register_region() with kvm->lock

Sean Christopherson <[email protected]>
KVM: SEV: Reject attempts to sync VMSA of an already-launched/encrypted vCPU

Sean Christopherson <[email protected]>
KVM: selftests: Remove duplicate LAUNCH_UPDATE_VMSA call in SEV-ES migrate test

Koichiro Den <[email protected]>
PCI: endpoint: pci-epf-vntb: Remove duplicate resource teardown

Koichiro Den <[email protected]>
PCI: endpoint: pci-epf-vntb: Stop cmd_handler work in epf_ntb_epc_cleanup

ZhengYuan Huang <[email protected]>
ocfs2: handle invalid dinode in ocfs2_group_extend

Tejas Bharambe <[email protected]>
ocfs2: fix use-after-free in ocfs2_fault() when VM_FAULT_RETRY

Joseph Qi <[email protected]>
ocfs2: fix possible deadlock between unlink and dio_end_io_write

Ruslan Valiyev <[email protected]>
media: vidtv: fix NULL pointer dereference in vidtv_channel_pmt_match_sections

Ryan Roberts <[email protected]>
arm64: mm: Handle invalid large leaf mappings correctly

Michał Winiarski <[email protected]>
vfio/xe: Reorganize the init to decouple migration from reset

Zhihao Cheng <[email protected]>
dcache: Limit the minimal number of bucket to two

Harin Lee <[email protected]>
ALSA: ctxfi: Limit PTP to a single page

SeongJae Park <[email protected]>
Docs/admin-guide/mm/damon/lru_sort: warn commit_inputs vs param updates race

SeongJae Park <[email protected]>
Docs/admin-guide/mm/damon/reclaim: warn commit_inputs vs param updates race

Fabio Porcedda <[email protected]>
USB: serial: option: add Telit Cinterion FN990A MBIM composition

Alistair Popple <[email protected]>
selftests/mm: hmm-tests: don't hardcode THP size to 2MB

Junrui Luo <[email protected]>
staging: sm750fb: fix division by zero in ps_to_hz()

Johan Hovold <[email protected]>
wifi: rtw88: fix device leak on probe failure

Tamir Duberstein <[email protected]>
scripts: generate_rust_analyzer.py: avoid FD leak

Benjamin Berg <[email protected]>
scripts/gdb/symbols: handle module path parameters

Greg Kroah-Hartman <[email protected]>
fbdev: udlfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO

Xu Yang <[email protected]>
usb: port: add delay after usb_hub_set_port_power()

Michael Zimmermann <[email protected]>
usb: gadget: f_hid: don't call cdev_init while cdev in use

Dave Carey <[email protected]>
USB: cdc-acm: Add quirks for Yoga Book 9 14IAH10 INGENIC touchscreen

Daniel Brát <[email protected]>
usb: storage: Expand range of matched versions for VL817 quirks entry

Alexey Charkov <[email protected]>
usb: typec: fusb302: Switch to threaded IRQ handler

Nathan Rebello <[email protected]>
usbip: validate number_of_packets in usbip_pack_ret_submit()

Stefan Metzmacher <[email protected]>
smb: server: avoid double-free in smb_direct_free_sendmsg after smb_direct_flush_send_list()

Stefan Metzmacher <[email protected]>
smb: client: avoid double-free in smbd_free_send_io() after smbd_send_batch_flush()

Greg Kroah-Hartman <[email protected]>
ksmbd: fix mechToken leak when SPNEGO decode fails after token alloc

Greg Kroah-Hartman <[email protected]>
ksmbd: require 3 sub-authorities before reading sub_auth[2]

Greg Kroah-Hartman <[email protected]>
ksmbd: validate EaNameLength in smb2_get_ea()

Greg Kroah-Hartman <[email protected]>
smb: client: fix OOB reads parsing symlink error response

Greg Kroah-Hartman <[email protected]>
smb: client: fix off-by-8 bounds check in check_wsl_eas()

Greg Kroah-Hartman <[email protected]>
usb: gadget: renesas_usb3: validate endpoint index in standard request handlers

Greg Kroah-Hartman <[email protected]>

    usb: gadget: f_phonet: fix skb frags[] overflow in pn_rx_complete()

Greg Kroah-Hartman <[email protected]>
usb: gadget: f_ncm: validate minimum block_len in ncm_unwrap_ntb()

Greg Kroah-Hartman <[email protected]>
fbdev: tdfxfb: avoid divide-by-zero on FBIOPUT_VSCREENINFO

Greg Kroah-Hartman <[email protected]>
ALSA: fireworks: bound device-supplied status before string array lookup

Greg Kroah-Hartman <[email protected]>
ALSA: usx2y: us144mkii: fix NULL deref on missing interface 0

Greg Kroah-Hartman <[email protected]>
bnge: return after auxiliary_device_uninit() in error path

Greg Kroah-Hartman <[email protected]>
drm/vc4: platform_get_irq_byname() returns an int

Greg Kroah-Hartman <[email protected]>
NFC: digital: Bounds check NFC-A cascade depth in SDD response handler

Greg Kroah-Hartman <[email protected]>

    net: usb: cdc-phonet: fix skb frags[] overflow in rx_complete()

Greg Kroah-Hartman <[email protected]>
HID: core: clamp report_size in s32ton() to avoid undefined shift

Greg Kroah-Hartman <[email protected]>
HID: alps: fix NULL pointer dereference in alps_raw_event()

Lin YuChen <[email protected]>
staging: rtl8723bs: initialize le_tmp64 in rtw_BIP_verify()

Greg Kroah-Hartman <[email protected]>
i2c: s3c24xx: check the size of the SMBUS message before using it

Samuel Page <[email protected]>

    can: raw: fix ro->uniq use-after-free in raw_rcv()

Borislav Petkov (AMD) <[email protected]>
x86/CPU: Fix FPDSS on Zen1

Junxi Qian <[email protected]>
nfc: llcp: add missing return after LLCP_CLOSED checks

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

Diffstat:

 Documentation/admin-guide/mm/damon/lru_sort.rst    |  4 ++
 Documentation/admin-guide/mm/damon/reclaim.rst     |  4 ++
 Makefile                                           |  4 +-
 arch/arm64/include/asm/pgtable-prot.h              |  2 +
 arch/arm64/include/asm/pgtable.h                   |  9 ++-
 arch/arm64/include/asm/uaccess.h                   |  2 +-
 arch/arm64/mm/mmu.c                                |  4 ++
 arch/arm64/mm/pageattr.c                           | 50 +++++++------
 arch/arm64/mm/trans_pgd.c                          | 42 ++---------
 arch/powerpc/include/asm/uaccess.h                 |  3 +-
 arch/powerpc/lib/pmem.c                            | 11 +--
 arch/x86/include/asm/msr-index.h                   |  3 +
 arch/x86/include/asm/uaccess.h                     |  2 +-
 arch/x86/include/asm/uaccess_32.h                  |  8 +--
 arch/x86/include/asm/uaccess_64.h                  | 16 +++--
 arch/x86/kernel/cpu/amd.c                          |  3 +
 arch/x86/kvm/svm/sev.c                             | 46 ++++++++----
 arch/x86/kvm/x86.c                                 | 14 +++-
 arch/x86/lib/copy_user_uncached_64.S               |  6 +-
 arch/x86/lib/usercopy_32.c                         |  9 +--
 arch/x86/lib/usercopy_64.c                         | 12 ++--
 drivers/gpu/drm/i915/i915_gem.c                    |  2 +-
 drivers/gpu/drm/qxl/qxl_ioctl.c                    |  2 +-
 drivers/gpu/drm/vc4/vc4_hdmi.c                     | 14 ++--
 drivers/hid/hid-alps.c                             |  3 +
 drivers/hid/hid-core.c                             |  3 +
 drivers/hwmon/powerz.c                             |  8 ++-
 drivers/i2c/busses/i2c-s3c2410.c                   |  7 +-
 drivers/infiniband/sw/rdmavt/qp.c                  |  8 +--
 drivers/md/bcache/super.c                          |  7 ++
 .../mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c   |  9 +++
 drivers/media/test-drivers/vidtv/vidtv_bridge.c    |  4 +-
 drivers/media/test-drivers/vidtv/vidtv_channel.c   |  4 ++
 drivers/media/test-drivers/vidtv/vidtv_mux.c       |  4 +-
 drivers/media/test-drivers/vidtv/vidtv_ts.c        | 48 ++++++-------
 drivers/media/test-drivers/vidtv/vidtv_ts.h        |  4 +-
 drivers/media/usb/as102/as102_usb_drv.c            |  2 +
 drivers/media/usb/em28xx/em28xx-video.c            | 14 ++--
 drivers/media/usb/hackrf/hackrf.c                  |  7 +-
 drivers/net/ethernet/broadcom/bnge/bnge_auxr.c     |  1 +
 drivers/net/usb/cdc-phonet.c                       |  7 +-
 drivers/net/wireguard/device.c                     |  8 +--
 drivers/net/wireless/realtek/rtw88/usb.c           |  3 +-
 drivers/ntb/ntb_transport.c                        |  7 +-
 drivers/pci/endpoint/functions/pci-epf-vntb.c      | 20 +-----
 drivers/staging/rtl8723bs/core/rtw_security.c      |  2 +-
 drivers/staging/sm750fb/sm750.c                    |  3 +
 drivers/usb/class/cdc-acm.c                        | 53 ++++++++++++--
 drivers/usb/core/port.c                            |  1 +
 drivers/usb/gadget/function/f_hid.c                | 15 ++--
 drivers/usb/gadget/function/f_ncm.c                |  4 +-
 drivers/usb/gadget/function/f_phonet.c             |  9 +++
 drivers/usb/gadget/udc/renesas_usb3.c              |  7 +-
 drivers/usb/serial/option.c                        |  2 +
 drivers/usb/storage/unusual_devs.h                 |  7 +-
 drivers/usb/typec/tcpm/fusb302.c                   |  5 +-
 drivers/usb/usbip/usbip_common.c                   | 12 ++++
 drivers/vfio/pci/xe/main.c                         | 43 ++++++-----
 drivers/video/fbdev/tdfxfb.c                       |  3 +
 drivers/video/fbdev/udlfb.c                        |  3 +
 fs/dcache.c                                        |  4 +-
 fs/nilfs2/dat.c                                    |  3 +
 fs/ocfs2/aops.c                                    |  3 +-
 fs/ocfs2/mmap.c                                    |  7 +-
 fs/ocfs2/ocfs2_trace.h                             | 10 ++-
 fs/ocfs2/resize.c                                  | 10 ++-
 fs/smb/client/smb2file.c                           | 20 +++---
 fs/smb/client/smb2inode.c                          |  2 +-
 fs/smb/client/smbdirect.c                          |  8 +++
 fs/smb/server/connection.c                         |  1 +
 fs/smb/server/smb2pdu.c                            |  7 +-
 fs/smb/server/smbacl.c                             |  3 +-
 fs/smb/server/transport_rdma.c                     |  8 ++-
 include/linux/hugetlb.h                            | 17 +++++
 include/linux/kvm_host.h                           | 10 ++-
 include/linux/uaccess.h                            | 11 ++-
 lib/iov_iter.c                                     |  4 +-
 mm/backing-dev.c                                   |  5 +-
 mm/filemap.c                                       |  3 +-
 mm/internal.h                                      |  1 -
 mm/kasan/init.c                                    |  8 +--
 mm/truncate.c                                      |  6 +-
 mm/userfaultfd.c                                   |  2 +-
 net/can/raw.c                                      | 11 ++-
 net/nfc/digital_technology.c                       |  6 ++
 net/nfc/llcp_core.c                                |  2 +
 scripts/checkpatch.pl                              | 10 +++
 scripts/gdb/linux/symbols.py                       |  2 +-
 scripts/generate_rust_analyzer.py                  |  3 +-
 sound/firewire/fireworks/fireworks_command.c       |  5 +-
 sound/pci/ctxfi/ctvmem.h                           |  2 +-
 sound/soc/qcom/qdsp6/q6apm.c                       | 14 +++-
 sound/usb/6fire/chip.c                             | 17 +++--
 sound/usb/usx2y/us144mkii.c                        |  6 +-
 tools/objtool/check.c                              |  2 +-
 .../testing/selftests/kvm/x86/sev_migrate_tests.c  |  2 -
 tools/testing/selftests/mm/hmm-tests.c             | 83 +++++-----------------
 97 files changed, 579 insertions(+), 358 deletions(-)

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

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

From: Benjamin Berg <[email protected]>

commit 8e4513303b8726e4434f718ab39749cbb4c142b1 upstream.

commit 581ee79a2547 ("scripts/gdb/symbols: make BPF debug info available to GDB") added support to make BPF debug information available to GDB. However, the argument handling loop was slightly broken, causing it to fail if further modules were passed. Fix it to append these passed modules to the instance variable after expansion.

---
 scripts/gdb/linux/symbols.py |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -298,7 +298,7 @@ are loaded as well."""
             if p == "-bpf":
                 monitor_bpf = True
             else:
-                p.append(os.path.abspath(os.path.expanduser(p)))
+                self.module_paths.append(os.path.abspath(os.path.expanduser(p)))
         self.module_paths.append(os.getcwd())
 
         if self.breakpoint is not None:

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

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

From: Zhihao Cheng <[email protected]>

commit f08fe8891c3eeb63b73f9f1f6d97aa629c821579 upstream.

There is an OOB read problem on dentry_hashtable when user sets 'dhash_entries=1':

  BUG: unable to handle page fault for address: ffff888b30b774b0
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  Oops: Oops: 0000 [#1] SMP PTI
  RIP: 0010:__d_lookup+0x56/0x120
   Call Trace:
    d_lookup.cold+0x16/0x5d
    lookup_dcache+0x27/0xf0
    lookup_one_qstr_excl+0x2a/0x180
    start_dirop+0x55/0xa0
    simple_start_creating+0x8d/0xa0
    debugfs_start_creating+0x8c/0x180
    debugfs_create_dir+0x1d/0x1c0
    pinctrl_init+0x6d/0x140
    do_one_initcall+0x6d/0x3d0
    kernel_init_freeable+0x39f/0x460
    kernel_init+0x2a/0x260

There will be only one bucket in dentry_hashtable when dhash_entries is set as one, and d_hash_shift is calculated as 32 by dcache_init(). Then, following process will access more than one buckets(which memory region is not allocated) in dentry_hashtable:
d_lookup
b = d_hash(hash)

    dentry_hashtable + ((u32)hashlen >> d_hash_shift)
    // The C standard defines the behavior of right shift amounts
    // exceeding the bit width of the operand as undefined. The
    // result of '(u32)hashlen >> d_hash_shift' becomes 'hashlen',
    // so 'b' will point to an unallocated memory region.
  hlist_bl_for_each_entry_rcu(b)
   hlist_bl_first_rcu(head)
    h->first  // read OOB!

Fix it by limiting the minimal number of dentry_hashtable bucket to two, so that 'd_hash_shift' won't exceeds the bit width of type u32.

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

@@ -3257,7 +3257,7 @@ static void __init dcache_init_early(voi
 					HASH_EARLY | HASH_ZERO,
 					&d_hash_shift,
 					NULL,
-					0,
+					2,
 					0);
 	d_hash_shift = 32 - d_hash_shift;
 

@@ -3289,7 +3289,7 @@ static void __init dcache_init(void)
 					HASH_ZERO,
 					&d_hash_shift,
 					NULL,
-					0,
+					2,
 					0);
 	d_hash_shift = 32 - d_hash_shift;
 

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

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

From: Michał Winiarski <[email protected]>

commit 1b81ed612e12ea9df8c5cb6f0ddd4419fd0b8ac8 upstream.

Attempting to issue reset on VF devices that don't support migration leads to the following:

  BUG: unable to handle page fault for address: 00000000000011f8
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: Oops: 0000 [#1] SMP NOPTI
  CPU: 2 UID: 0 PID: 7443 Comm: xe_sriov_flr Tainted: G S   U              7.0.0-rc1-lgci-xe-xe-4588-cec43d5c2696af219-nodebug+ #1 PREEMPT(lazy)
  Tainted: [S]=CPU_OUT_OF_SPEC, [U]=USER
  Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-P DDR4 RVP, BIOS RPLPFWI1.R00.4035.A00.2301200723 01/20/2023
  RIP: 0010:xe_sriov_vfio_wait_flr_done+0xc/0x80 [xe]
  Code: ff c3 cc cc cc cc 0f 1f 84 00 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 55 48 89 e5 41 54 53 <83> bf f8 11 00 00 02 75 61 41 89 f4 85 f6 74 52 48 8b 47 08 48 89
  RSP: 0018:ffffc9000f7c39b8 EFLAGS: 00010202
  RAX: ffffffffa04d8660 RBX: ffff88813e3e4000 RCX: 0000000000000000
  RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
  RBP: ffffc9000f7c39c8 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000000 R12: ffff888101a48800
  R13: ffff88813e3e4150 R14: ffff888130d0d008 R15: ffff88813e3e40d0
  FS:  00007877d3d0d940(0000) GS:ffff88890b6d3000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00000000000011f8 CR3: 000000015a762000 CR4: 0000000000f52ef0
  PKRU: 55555554
  Call Trace:
   <TASK>
   xe_vfio_pci_reset_done+0x49/0x120 [xe_vfio_pci]
   pci_dev_restore+0x3b/0x80
   pci_reset_function+0x109/0x140
   reset_store+0x5c/0xb0
   dev_attr_store+0x17/0x40
   sysfs_kf_write+0x72/0x90
   kernfs_fop_write_iter+0x161/0x1f0
   vfs_write+0x261/0x440
   ksys_write+0x69/0xf0
   __x64_sys_write+0x19/0x30
   x64_sys_call+0x259/0x26e0
   do_syscall_64+0xcb/0x1500
   ? __fput+0x1a2/0x2d0
   ? fput_close_sync+0x3d/0xa0
   ? __x64_sys_close+0x3e/0x90
   ? x64_sys_call+0x1b7c/0x26e0
   ? do_syscall_64+0x109/0x1500
   ? __task_pid_nr_ns+0x68/0x100
   ? __do_sys_getpid+0x1d/0x30
   ? x64_sys_call+0x10b5/0x26e0
   ? do_syscall_64+0x109/0x1500
   ? putname+0x41/0x90
   ? do_faccessat+0x1e8/0x300
   ? __x64_sys_access+0x1c/0x30
   ? x64_sys_call+0x1822/0x26e0
   ? do_syscall_64+0x109/0x1500
   ? tick_program_event+0x43/0xa0
   ? hrtimer_interrupt+0x126/0x260
   ? irqentry_exit+0xb2/0x710
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
  RIP: 0033:0x7877d5f1c5a4
  Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d a5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89
  RSP: 002b:00007fff48e5f908 EFLAGS: 00000202 ORIG_RAX: 0000000000000001
  RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007877d5f1c5a4
  RDX: 0000000000000001 RSI: 00007877d621b0c9 RDI: 0000000000000009
  RBP: 0000000000000001 R08: 00005fb49113b010 R09: 0000000000000007
  R10: 0000000000000000 R11: 0000000000000202 R12: 00007877d621b0c9
  R13: 0000000000000009 R14: 00007fff48e5fac0 R15: 00007fff48e5fac0
   </TASK>

This is caused by the fact that some of the xe_vfio_pci_core_device members needed for handling reset are only initialized as part of migration init.

Fix the problem by reorganizing the code to decouple VF init from migration init.

---
 drivers/vfio/pci/xe/main.c |   43 +++++++++++++++++++++++++------------------
 1 file changed, 25 insertions(+), 18 deletions(-)

@@ -454,39 +454,46 @@ static const struct vfio_migration_ops x
 static void xe_vfio_pci_migration_init(struct xe_vfio_pci_core_device *xe_vdev)
 {
 	struct vfio_device *core_vdev = &xe_vdev->core_device.vdev;
-	struct pci_dev *pdev = to_pci_dev(core_vdev->dev);
-	struct xe_device *xe = xe_sriov_vfio_get_pf(pdev);
 
-	if (!xe)
-		return;
-	if (!xe_sriov_vfio_migration_supported(xe))
+	if (!xe_sriov_vfio_migration_supported(xe_vdev->xe))
 		return;
 
-	mutex_init(&xe_vdev->state_mutex);
-	spin_lock_init(&xe_vdev->reset_lock);
-
-	/* PF internal control uses vfid index starting from 1 */
-	xe_vdev->vfid = pci_iov_vf_id(pdev) + 1;
-	xe_vdev->xe = xe;
-
 	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P;
 	core_vdev->mig_ops = &xe_vfio_pci_migration_ops;
 }
 
-static void xe_vfio_pci_migration_fini(struct xe_vfio_pci_core_device *xe_vdev)
+static int xe_vfio_pci_vf_init(struct xe_vfio_pci_core_device *xe_vdev)
 {
-	if (!xe_vdev->vfid)
-		return;
+	struct vfio_device *core_vdev = &xe_vdev->core_device.vdev;
+	struct pci_dev *pdev = to_pci_dev(core_vdev->dev);
+	struct xe_device *xe = xe_sriov_vfio_get_pf(pdev);
 
-	mutex_destroy(&xe_vdev->state_mutex);
+	if (!pdev->is_virtfn)
+		return 0;
+	if (!xe)
+		return -ENODEV;
+	xe_vdev->xe = xe;
+
+	/* PF internal control uses vfid index starting from 1 */
+	xe_vdev->vfid = pci_iov_vf_id(pdev) + 1;
+
+	xe_vfio_pci_migration_init(xe_vdev);
+
+	return 0;
 }
 
 static int xe_vfio_pci_init_dev(struct vfio_device *core_vdev)
 {
 	struct xe_vfio_pci_core_device *xe_vdev =
 		container_of(core_vdev, struct xe_vfio_pci_core_device, core_device.vdev);
+	int ret;
 
-	xe_vfio_pci_migration_init(xe_vdev);
+	mutex_init(&xe_vdev->state_mutex);
+	spin_lock_init(&xe_vdev->reset_lock);
+
+	ret = xe_vfio_pci_vf_init(xe_vdev);
+	if (ret)
+		return ret;
 
 	return vfio_pci_core_init_dev(core_vdev);
 }

@@ -496,7 +503,7 @@ static void xe_vfio_pci_release_dev(stru
 	struct xe_vfio_pci_core_device *xe_vdev =
 		container_of(core_vdev, struct xe_vfio_pci_core_device, core_device.vdev);
 
-	xe_vfio_pci_migration_fini(xe_vdev);
+	mutex_destroy(&xe_vdev->state_mutex);
 }
 
 static const struct vfio_device_ops xe_vfio_pci_ops = {

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

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

From: Ryan Roberts <[email protected]>

commit 15bfba1ad77fad8e45a37aae54b3c813b33fe27c upstream.

It has been possible for a long time to mark ptes in the linear map as invalid. This is done for secretmem, kfence, realm dma memory un/share, and others, by simply clearing the PTE_VALID bit. But until commit a166563e7ec37 ("arm64: mm: support large block mapping when rodata=full") large leaf mappings were never made invalid in this way.

It turns out various parts of the code base are not equipped to handle invalid large leaf mappings (in the way they are currently encoded) and I've observed a kernel panic while booting a realm guest on a BBML2_NOABORT system as a result:

[   15.432706] software IO TLB: Memory encryption is active and system is using DMA bounce buffers
[   15.476896] Unable to handle kernel paging request at virtual address ffff000019600000
[   15.513762] Mem abort info:
[   15.527245]   ESR = 0x0000000096000046
[   15.548553]   EC = 0x25: DABT (current EL), IL = 32 bits
[   15.572146]   SET = 0, FnV = 0
[   15.592141]   EA = 0, S1PTW = 0
[   15.612694]   FSC = 0x06: level 2 translation fault
[   15.640644] Data abort info:
[   15.661983]   ISV = 0, ISS = 0x00000046, ISS2 = 0x00000000
[   15.694875]   CM = 0, WnR = 1, TnD = 0, TagAccess = 0
[   15.723740]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[   15.755776] swapper pgtable: 4k pages, 48-bit VAs, pgdp=0000000081f3f000
[   15.800410] [ffff000019600000] pgd=0000000000000000, p4d=180000009ffff403, pud=180000009fffe403, pmd=00e8000199600704
[   15.855046] Internal error: Oops: 0000000096000046 [#1]  SMP
[   15.886394] Modules linked in:
[   15.900029] CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 7.0.0-rc4-dirty #4 PREEMPT
[   15.935258] Hardware name: linux,dummy-virt (DT)
[   15.955612] pstate: 21400005 (nzCv daif +PAN -UAO -TCO +DIT -SSBS BTYPE=--)
[   15.986009] pc : __pi_memcpy_generic+0x128/0x22c
[   16.006163] lr : swiotlb_bounce+0xf4/0x158
[   16.024145] sp : ffff80008000b8f0
[   16.038896] x29: ffff80008000b8f0 x28: 0000000000000000 x27: 0000000000000000
[   16.069953] x26: ffffb3976d261ba8 x25: 0000000000000000 x24: ffff000019600000
[   16.100876] x23: 0000000000000001 x22: ffff0000043430d0 x21: 0000000000007ff0
[   16.131946] x20: 0000000084570010 x19: 0000000000000000 x18: ffff00001ffe3fcc
[   16.163073] x17: 0000000000000000 x16: 00000000003fffff x15: 646e612065766974
[   16.194131] x14: 0000000000000000 x13: 0000000000000000 x12: 0000000000000000
[   16.225059] x11: 0000000000000000 x10: 0000000000000010 x9 : 0000000000000018
[   16.256113] x8 : 0000000000000018 x7 : 0000000000000000 x6 : 0000000000000000
[   16.287203] x5 : ffff000019607ff0 x4 : ffff000004578000 x3 : ffff000019600000
[   16.318145] x2 : 0000000000007ff0 x1 : ffff000004570010 x0 : ffff000019600000
[   16.349071] Call trace:
[   16.360143]  __pi_memcpy_generic+0x128/0x22c (P)
[   16.380310]  swiotlb_tbl_map_single+0x154/0x2b4
[   16.400282]  swiotlb_map+0x5c/0x228
[   16.415984]  dma_map_phys+0x244/0x2b8
[   16.432199]  dma_map_page_attrs+0x44/0x58
[   16.449782]  virtqueue_map_page_attrs+0x38/0x44
[   16.469596]  virtqueue_map_single_attrs+0xc0/0x130
[   16.490509]  virtnet_rq_alloc.isra.0+0xa4/0x1fc
[   16.510355]  try_fill_recv+0x2a4/0x584
[   16.526989]  virtnet_open+0xd4/0x238
[   16.542775]  __dev_open+0x110/0x24c
[   16.558280]  __dev_change_flags+0x194/0x20c
[   16.576879]  netif_change_flags+0x24/0x6c
[   16.594489]  dev_change_flags+0x48/0x7c
[   16.611462]  ip_auto_config+0x258/0x1114
[   16.628727]  do_one_initcall+0x80/0x1c8
[   16.645590]  kernel_init_freeable+0x208/0x2f0
[   16.664917]  kernel_init+0x24/0x1e0
[   16.680295]  ret_from_fork+0x10/0x20
[   16.696369] Code: 927cec03 cb0e0021 8b0e0042 a9411c26 (a900340c)
[   16.723106] ---[ end trace 0000000000000000 ]---
[   16.752866] Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
[   16.792556] Kernel Offset: 0x3396ea200000 from 0xffff800080000000
[   16.818966] PHYS_OFFSET: 0xfff1000080000000
[   16.837237] CPU features: 0x0000000,00060005,13e38581,957e772f
[   16.862904] Memory Limit: none
[   16.876526] ---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b ]---

This panic occurs because the swiotlb memory was previously shared to the host (__set_memory_enc_dec()), which involves transitioning the (large) leaf mappings to invalid, sharing to the host, then marking the mappings valid again. But pageattr_p[mu]d_entry() would only update the entry if it is a section mapping, since otherwise it concluded it must be a table entry so shouldn't be modified. But p[mu]d_sect() only returns true if the entry is valid. So the result was that the large leaf entry was made invalid in the first pass then ignored in the second pass. It remains invalid until the above code tries to access it and blows up.

The simple fix would be to update pageattr_pmd_entry() to use !pmd_table() instead of pmd_sect(). That would solve this problem.

But the ptdump code also suffers from a similar issue. It checks pmd_leaf() and doesn't call into the arch-specific note_page() machinery if it returns false. As a result of this, ptdump wasn't even able to show the invalid large leaf mappings; it looked like they were valid which made this super fun to debug. the ptdump code is core-mm and pmd_table() is arm64-specific so we can't use the same trick to solve that.

But we already support the concept of "present-invalid" for user space entries. And even better, pmd_leaf() will return true for a leaf mapping that is marked present-invalid. So let's just use that encoding for present-invalid kernel mappings too. Then we can use pmd_leaf() where we previously used pmd_sect() and everything is magically fixed.

Additionally, from inspection kernel_page_present() was broken in a similar way, so I'm also updating that to use pmd_leaf().

The transitional page tables component was also similarly broken; it creates a copy of the kernel page tables, making RO leaf mappings RW in the process. It also makes invalid (but-not-none) pte mappings valid. But it was not doing this for large leaf mappings. This could have resulted in crashes at kexec- or hibernate-time. This code is fixed to flip "present-invalid" mappings back to "present-valid" at all levels.

Finally, I have hardened split_pmd()/split_pud() so that if it is passed a "present-invalid" leaf, it will maintain that property in the split leaves, since I wasn't able to convince myself that it would only ever be called for "present-valid" leaves.

---
 arch/arm64/include/asm/pgtable-prot.h |    2 +
 arch/arm64/include/asm/pgtable.h      |    9 ++++--
 arch/arm64/mm/mmu.c                   |    4 ++
 arch/arm64/mm/pageattr.c              |   50 +++++++++++++++++++---------------
 arch/arm64/mm/trans_pgd.c             |   42 ++++------------------------
 5 files changed, 48 insertions(+), 59 deletions(-)

@@ -25,6 +25,8 @@
  */
 #define PTE_PRESENT_INVALID	(PTE_NG)		 /* only when !PTE_VALID */
 
+#define PTE_PRESENT_VALID_KERNEL (PTE_VALID | PTE_MAYBE_NG)
+
 #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
 #define PTE_UFFD_WP		(_AT(pteval_t, 1) << 58) /* uffd-wp tracking */
 #define PTE_SWP_UFFD_WP		(_AT(pteval_t, 1) << 3)	 /* only for swp ptes */

@@ -322,9 +322,11 @@ static inline pte_t pte_mknoncont(pte_t
 	return clear_pte_bit(pte, __pgprot(PTE_CONT));
 }
 
-static inline pte_t pte_mkvalid(pte_t pte)
+static inline pte_t pte_mkvalid_k(pte_t pte)
 {
-	return set_pte_bit(pte, __pgprot(PTE_VALID));
+	pte = clear_pte_bit(pte, __pgprot(PTE_PRESENT_INVALID));
+	pte = set_pte_bit(pte, __pgprot(PTE_PRESENT_VALID_KERNEL));
+	return pte;
 }
 
 static inline pte_t pte_mkinvalid(pte_t pte)

@@ -594,6 +596,7 @@ static inline int pmd_protnone(pmd_t pmd
 #define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mkvalid_k(pmd)	pte_pmd(pte_mkvalid_k(pmd_pte(pmd)))
 #define pmd_mkinvalid(pmd)	pte_pmd(pte_mkinvalid(pmd_pte(pmd)))
 #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
 #define pmd_uffd_wp(pmd)	pte_uffd_wp(pmd_pte(pmd))

@@ -635,6 +638,8 @@ static inline pmd_t pmd_mkspecial(pmd_t
 
 #define pud_young(pud)		pte_young(pud_pte(pud))
 #define pud_mkyoung(pud)	pte_pud(pte_mkyoung(pud_pte(pud)))
+#define pud_mkwrite_novma(pud)	pte_pud(pte_mkwrite_novma(pud_pte(pud)))
+#define pud_mkvalid_k(pud)	pte_pud(pte_mkvalid_k(pud_pte(pud)))
 #define pud_write(pud)		pte_write(pud_pte(pud))
 
 static inline pud_t pud_mkhuge(pud_t pud)

@@ -602,6 +602,8 @@ static int split_pmd(pmd_t *pmdp, pmd_t
 		tableprot |= PMD_TABLE_PXN;
 
 	prot = __pgprot((pgprot_val(prot) & ~PTE_TYPE_MASK) | PTE_TYPE_PAGE);
+	if (!pmd_valid(pmd))
+		prot = pte_pgprot(pte_mkinvalid(pfn_pte(0, prot)));
 	prot = __pgprot(pgprot_val(prot) & ~PTE_CONT);
 	if (to_cont)
 		prot = __pgprot(pgprot_val(prot) | PTE_CONT);

@@ -647,6 +649,8 @@ static int split_pud(pud_t *pudp, pud_t
 		tableprot |= PUD_TABLE_PXN;
 
 	prot = __pgprot((pgprot_val(prot) & ~PMD_TYPE_MASK) | PMD_TYPE_SECT);
+	if (!pud_valid(pud))
+		prot = pmd_pgprot(pmd_mkinvalid(pfn_pmd(0, prot)));
 	prot = __pgprot(pgprot_val(prot) & ~PTE_CONT);
 	if (to_cont)
 		prot = __pgprot(pgprot_val(prot) | PTE_CONT);

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

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

From: Ruslan Valiyev <[email protected]>

commit f8e1fc918a9fe67103bcda01d20d745f264d00a7 upstream.

syzbot reported a general protection fault in vidtv_psi_desc_assign [1].

vidtv_psi_pmt_stream_init() can return NULL on memory allocation failure, but vidtv_channel_pmt_match_sections() does not check for this. When tail is NULL, the subsequent call to vidtv_psi_desc_assign(&tail->descriptor, desc) dereferences a NULL pointer offset, causing a general protection fault.

Add a NULL check after vidtv_psi_pmt_stream_init(). On failure, clean up the already-allocated stream chain and return.

[1]

Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN PTI
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
RIP: 0010:vidtv_psi_desc_assign+0x24/0x90 drivers/media/test-drivers/vidtv/vidtv_psi.c:629
Call Trace:
 <TASK>
 vidtv_channel_pmt_match_sections drivers/media/test-drivers/vidtv/vidtv_channel.c:349 [inline]
 vidtv_channel_si_init+0x1445/0x1a50 drivers/media/test-drivers/vidtv/vidtv_channel.c:479
 vidtv_mux_init+0x526/0xbe0 drivers/media/test-drivers/vidtv/vidtv_mux.c:519
 vidtv_start_streaming drivers/media/test-drivers/vidtv/vidtv_bridge.c:194 [inline]
 vidtv_start_feed+0x33e/0x4d0 drivers/media/test-drivers/vidtv/vidtv_bridge.c:239

---
 drivers/media/test-drivers/vidtv/vidtv_channel.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -341,6 +341,10 @@ vidtv_channel_pmt_match_sections(struct
 					tail = vidtv_psi_pmt_stream_init(tail,
 									 s->type,
 									 e_pid);
+					if (!tail) {
+						vidtv_psi_pmt_stream_destroy(head);
+						return;
+					}
 
 					if (!head)
 						head = tail;

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

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

From: Joseph Qi <[email protected]>

commit b02da26a992db0c0e2559acbda0fc48d4a2fd337 upstream.

ocfs2_unlink takes orphan dir inode_lock first and then ip_alloc_sem, while in ocfs2_dio_end_io_write, it acquires these locks in reverse order. This creates an ABBA lock ordering violation on lock classes ocfs2_sysfile_lock_key[ORPHAN_DIR_SYSTEM_INODE] and ocfs2_file_ip_alloc_sem_key.

Lock Chain #0 (orphan dir inode_lock -> ip_alloc_sem):
ocfs2_unlink
ocfs2_prepare_orphan_dir
ocfs2_lookup_lock_orphan_dir
inode_lock(orphan_dir_inode) <- lock A
__ocfs2_prepare_orphan_dir
ocfs2_prepare_dir_for_insert
ocfs2_extend_dir
ocfs2_expand_inline_dir
down_write(&oi->ip_alloc_sem) <- Lock B

Lock Chain #1 (ip_alloc_sem -> orphan dir inode_lock):
ocfs2_dio_end_io_write
down_write(&oi->ip_alloc_sem) <- Lock B ocfs2_del_inode_from_orphan()
inode_lock(orphan_dir_inode) <- Lock A

Deadlock Scenario:
CPU0 (unlink) CPU1 (dio_end_io_write)
------ ------
inode_lock(orphan_dir_inode)
down_write(ip_alloc_sem)
down_write(ip_alloc_sem)
inode_lock(orphan_dir_inode)

Since ip_alloc_sem is to protect allocation changes, which is unrelated with operations in ocfs2_del_inode_from_orphan. So move ocfs2_del_inode_from_orphan out of ip_alloc_sem to fix the deadlock.

---
 fs/ocfs2/aops.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -2294,8 +2294,6 @@ static int ocfs2_dio_end_io_write(struct
 		goto out;
 	}
 
-	down_write(&oi->ip_alloc_sem);
-
 	/* Delete orphan before acquire i_rwsem. */
 	if (dwc->dw_orphaned) {
 		BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));

@@ -2308,6 +2306,7 @@ static int ocfs2_dio_end_io_write(struct
 			mlog_errno(ret);
 	}
 
+	down_write(&oi->ip_alloc_sem);
 	di = (struct ocfs2_dinode *)di_bh->b_data;
 
 	ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);

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

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

From: Tejas Bharambe <[email protected]>

commit 7de554cabf160e331e4442e2a9ad874ca9875921 upstream.

filemap_fault() may drop the mmap_lock before returning VM_FAULT_RETRY, as documented in mm/filemap.c:

"If our return value has VM_FAULT_RETRY set, it's because the mmap_lock may be dropped before doing I/O or by lock_folio_maybe_drop_mmap()."

When this happens, a concurrent munmap() can call remove_vma() and free the vm_area_struct via RCU. The saved 'vma' pointer in ocfs2_fault() then becomes a dangling pointer, and the subsequent trace_ocfs2_fault() call dereferences it -- a use-after-free.

Fix this by saving ip_blkno as a plain integer before calling filemap_fault(), and removing vma from the trace event. Since ip_blkno is copied by value before the lock can be dropped, it remains valid regardless of what happens to the vma or inode afterward.

---
 fs/ocfs2/mmap.c        |    7 +++----
 fs/ocfs2/ocfs2_trace.h |   10 ++++------
 2 files changed, 7 insertions(+), 10 deletions(-)

@@ -30,7 +30,8 @@
 
 static vm_fault_t ocfs2_fault(struct vm_fault *vmf)
 {
-	struct vm_area_struct *vma = vmf->vma;
+	unsigned long long ip_blkno =
+		OCFS2_I(file_inode(vmf->vma->vm_file))->ip_blkno;
 	sigset_t oldset;
 	vm_fault_t ret;
 

@@ -38,11 +39,9 @@ static vm_fault_t ocfs2_fault(struct vm_
 	ret = filemap_fault(vmf);
 	ocfs2_unblock_signals(&oldset);
 
-	trace_ocfs2_fault(OCFS2_I(vma->vm_file->f_mapping->host)->ip_blkno,
-			  vma, vmf->page, vmf->pgoff);
+	trace_ocfs2_fault(ip_blkno, vmf->page, vmf->pgoff);
 	return ret;
 }
-
 static vm_fault_t __ocfs2_page_mkwrite(struct file *file,
 			struct buffer_head *di_bh, struct folio *folio)
 {

@@ -1246,22 +1246,20 @@ TRACE_EVENT(ocfs2_write_end_inline,
 
 TRACE_EVENT(ocfs2_fault,
 	TP_PROTO(unsigned long long ino,
-		 void *area, void *page, unsigned long pgoff),
-	TP_ARGS(ino, area, page, pgoff),
+		 void *page, unsigned long pgoff),
+	TP_ARGS(ino, page, pgoff),
 	TP_STRUCT__entry(
 		__field(unsigned long long, ino)
-		__field(void *, area)
 		__field(void *, page)
 		__field(unsigned long, pgoff)
 	),
 	TP_fast_assign(
 		__entry->ino = ino;
-		__entry->area = area;
 		__entry->page = page;
 		__entry->pgoff = pgoff;
 	),
-	TP_printk("%llu %p %p %lu",
-		  __entry->ino, __entry->area, __entry->page, __entry->pgoff)
+	TP_printk("%llu %p %lu",
+		  __entry->ino, __entry->page, __entry->pgoff)
 );
 
 /* End of trace events for fs/ocfs2/mmap.c. */

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

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

From: ZhengYuan Huang <[email protected]>

commit 4a1c0ddc6e7bcf2e9db0eeaab9340dcfe97f448f upstream.

[BUG]
kernel BUG at fs/ocfs2/resize.c:308!

Oops: invalid opcode: 0000 [#1] SMP KASAN NOPTI
RIP: 0010:ocfs2_group_extend+0x10aa/0x1ae0 fs/ocfs2/resize.c:308
Code: 8b8520ff ffff83f8 860f8580 030000e8 5cc3c1fe
Call Trace:
 ...
 ocfs2_ioctl+0x175/0x6e0 fs/ocfs2/ioctl.c:869
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:597 [inline]
 __se_sys_ioctl fs/ioctl.c:583 [inline]
 __x64_sys_ioctl+0x197/0x1e0 fs/ioctl.c:583
 x64_sys_call+0x1144/0x26a0 arch/x86/include/generated/asm/syscalls_64.h:17
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x93/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x76/0x7e
 ...

[CAUSE]
ocfs2_group_extend() assumes that the global bitmap inode block returned from ocfs2_inode_lock() has already been validated and BUG_ONs when the signature is not a dinode. That assumption is too strong for crafted filesystems because the JBD2-managed buffer path can bypass structural validation and return an invalid dinode to the resize ioctl.

[FIX]
Validate the dinode explicitly in ocfs2_group_extend(). If the global bitmap buffer does not contain a valid dinode, report filesystem corruption with ocfs2_error() and fail the resize operation instead of crashing the kernel.

---
 fs/ocfs2/resize.c |   10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

@@ -303,9 +303,13 @@ int ocfs2_group_extend(struct inode * in
 
 	fe = (struct ocfs2_dinode *)main_bm_bh->b_data;
 
-	/* main_bm_bh is validated by inode read inside ocfs2_inode_lock(),
-	 * so any corruption is a code bug. */
-	BUG_ON(!OCFS2_IS_VALID_DINODE(fe));
+	/* JBD-managed buffers can bypass validation, so treat this as corruption. */
+	if (!OCFS2_IS_VALID_DINODE(fe)) {
+		ret = ocfs2_error(main_bm_inode->i_sb,
+				  "Invalid dinode #%llu\n",
+				  (unsigned long long)OCFS2_I(main_bm_inode)->ip_blkno);
+		goto out_unlock;
+	}
 
 	if (le16_to_cpu(fe->id2.i_chain.cl_cpg) !=
 		ocfs2_group_bitmap_size(osb->sb, 0,

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

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

From: Koichiro Den <[email protected]>

commit d799984233a50abd2667a7d17a9a710a3f10ebe2 upstream.

Disable the delayed work before clearing BAR mappings and doorbells to avoid running the handler after resources have been torn down.

  Unable to handle kernel paging request at virtual address ffff800083f46004
  [...]
  Internal error: Oops: 0000000096000007 [#1]  SMP
  [...]
  Call trace:
   epf_ntb_cmd_handler+0x54/0x200 [pci_epf_vntb] (P)
   process_one_work+0x154/0x3b0
   worker_thread+0x2c8/0x400
   kthread+0x148/0x210
   ret_from_fork+0x10/0x20

---
 drivers/pci/endpoint/functions/pci-epf-vntb.c |    1 +
 1 file changed, 1 insertion(+)

@@ -955,6 +955,7 @@ err_config_interrupt:
  */
 static void epf_ntb_epc_cleanup(struct epf_ntb *ntb)
 {
+	disable_delayed_work_sync(&ntb->cmd_handler);
 	epf_ntb_mw_bar_clear(ntb, ntb->num_mws);
 	epf_ntb_db_bar_clear(ntb);
 	epf_ntb_config_sspad_bar_clear(ntb);

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

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

From: Koichiro Den <[email protected]>

commit 0da63230d3ec1ec5fcc443a2314233e95bfece54 upstream.

epf_ntb_epc_destroy() duplicates the teardown that the caller is supposed to perform later. This leads to an oops when .allow_link fails or when .drop_link is performed. The following is an example oops of the former case:

  Unable to handle kernel paging request at virtual address dead000000000108
  [...]
  [dead000000000108] address between user and kernel address ranges
  Internal error: Oops: 0000000096000044 [#1]  SMP
  [...]
  Call trace:
   pci_epc_remove_epf+0x78/0xe0 (P)
   pci_primary_epc_epf_link+0x88/0xa8
   configfs_symlink+0x1f4/0x5a0
   vfs_symlink+0x134/0x1d8
   do_symlinkat+0x88/0x138
   __arm64_sys_symlinkat+0x74/0xe0
  [...]

Remove the helper, and drop pci_epc_put(). EPC device refcounting is tied to the configfs EPC group lifetime, and pci_epc_put() in the .drop_link path is sufficient.

---
 drivers/pci/endpoint/functions/pci-epf-vntb.c |   19 +------------------
 1 file changed, 1 insertion(+), 18 deletions(-)

@@ -764,19 +764,6 @@ static void epf_ntb_mw_bar_clear(struct
 }
 
 /**
- * epf_ntb_epc_destroy() - Cleanup NTB EPC interface
- * @ntb: NTB device that facilitates communication between HOST and VHOST
- *
- * Wrapper for epf_ntb_epc_destroy_interface() to cleanup all the NTB interfaces
- */
-static void epf_ntb_epc_destroy(struct epf_ntb *ntb)
-{
-	pci_epc_remove_epf(ntb->epf->epc, ntb->epf, 0);
-	pci_epc_put(ntb->epf->epc);
-}
-
-
-/**
  * epf_ntb_is_bar_used() - Check if a bar is used in the ntb configuration
  * @ntb: NTB device that facilitates communication between HOST and VHOST
  * @barno: Checked bar number

@@ -1526,7 +1513,7 @@ static int epf_ntb_bind(struct pci_epf *
 	ret = epf_ntb_init_epc_bar(ntb);
 	if (ret) {
 		dev_err(dev, "Failed to create NTB EPC\n");
-		goto err_bar_init;
+		return ret;
 	}
 
 	ret = epf_ntb_config_spad_bar_alloc(ntb);

@@ -1566,9 +1553,6 @@ err_epc_cleanup:
 err_bar_alloc:
 	epf_ntb_config_spad_bar_free(ntb);
 
-err_bar_init:
-	epf_ntb_epc_destroy(ntb);
-
 	return ret;
 }
 

@@ -1584,7 +1568,6 @@ static void epf_ntb_unbind(struct pci_ep
 
 	epf_ntb_epc_cleanup(ntb);
 	epf_ntb_config_spad_bar_free(ntb);
-	epf_ntb_epc_destroy(ntb);
 
 	pci_unregister_driver(&vntb_pci_driver);
 }

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

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

From: Sean Christopherson <[email protected]>

commit 25a642b6abc98bbbabbf2baef9fc498bbea6aee6 upstream.

Drop the explicit KVM_SEV_LAUNCH_UPDATE_VMSA call when creating an SEV-ES VM in the SEV migration test, as sev_vm_create() automatically updates the VMSA pages for SEV-ES guests. The only reason the duplicate call doesn't cause visible problems is because the test doesn't actually try to run the vCPUs. That will change when KVM adds a check to prevent userspace from re-launching a VMSA (which corrupts the VMSA page due to KVM writing encrypted private memory).

---
 tools/testing/selftests/kvm/x86/sev_migrate_tests.c |    2 --
 1 file changed, 2 deletions(-)

@@ -36,8 +36,6 @@ static struct kvm_vm *sev_vm_create(bool
 
 	sev_vm_launch(vm, es ? SEV_POLICY_ES : 0);
 
-	if (es)
-		vm_sev_ioctl(vm, KVM_SEV_LAUNCH_UPDATE_VMSA, NULL);
 	return vm;
 }
 

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

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

From: Tamir Duberstein <[email protected]>

commit 9b4744d8eda2824041064a5639ccbb079850914d upstream.

Use pathlib.Path.read_text() to avoid leaking file descriptors.

---
 scripts/generate_rust_analyzer.py |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -190,9 +190,10 @@ def generate_crates(srctree, objtree, sy
 
     def is_root_crate(build_file, target):
         try:
-            return f"{target}.o" in open(build_file).read()
+            contents = build_file.read_text()
         except FileNotFoundError:
             return False
+        return f"{target}.o" in contents
 
     # Then, the rest outside of `rust/`.
     #

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

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

From: Sean Christopherson <[email protected]>

commit 9b9f7962e3e879d12da2bf47e02a24ec51690e3d upstream.

Reject synchronizing vCPU state to its associated VMSA if the vCPU has already been launched, i.e. if the VMSA has already been encrypted. On a host with SNP enabled, accessing guest-private memory generates an RMP #PF and panics the host.

  BUG: unable to handle page fault for address: ff1276cbfdf36000
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x80000003) - RMP violation
  PGD 5a31801067 P4D 5a31802067 PUD 40ccfb5063 PMD 40e5954063 PTE 80000040fdf36163
  SEV-SNP: PFN 0x40fdf36, RMP entry: [0x6010fffffffff001 - 0x000000000000001f]
  Oops: Oops: 0003 [#1] SMP NOPTI
  CPU: 33 UID: 0 PID: 996180 Comm: qemu-system-x86 Tainted: G           OE
  Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
  Hardware name: Dell Inc. PowerEdge R7625/0H1TJT, BIOS 1.5.8 07/21/2023
  RIP: 0010:sev_es_sync_vmsa+0x54/0x4c0 [kvm_amd]
  Call Trace:
   <TASK>
   snp_launch_update_vmsa+0x19d/0x290 [kvm_amd]
   snp_launch_finish+0xb6/0x380 [kvm_amd]
   sev_mem_enc_ioctl+0x14e/0x720 [kvm_amd]
   kvm_arch_vm_ioctl+0x837/0xcf0 [kvm]
   kvm_vm_ioctl+0x3fd/0xcc0 [kvm]
   __x64_sys_ioctl+0xa3/0x100
   x64_sys_call+0xfe0/0x2350
   do_syscall_64+0x81/0x10f0
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
  RIP: 0033:0x7ffff673287d
   </TASK>

Note, the KVM flaw has been present since commit ad73109ae7ec ("KVM: SVM:
Provide support to launch and run an SEV-ES guest"), but has only been actively dangerous for the host since SNP support was added. With SEV-ES, KVM would "just" clobber guest state, which is totally fine from a host kernel perspective since userspace can clobber guest state any time before sev_launch_update_vmsa().

---
 arch/x86/kvm/svm/sev.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -882,6 +882,9 @@ static int sev_es_sync_vmsa(struct vcpu_
 	u8 *d;
 	int i;
 
+	if (vcpu->arch.guest_state_protected)
+		return -EINVAL;
+
 	/* Check some debug related fields before encrypting the VMSA */
 	if (svm->vcpu.guest_debug || (svm->vmcb->save.dr7 & ~DR7_FIXED_1))
 		return -EINVAL;

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

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

From: Sean Christopherson <[email protected]>

commit b6408b6cec5df76a165575777800ef2aba12b109 upstream.

Take and hold kvm->lock for before checking sev_guest() in sev_mem_enc_register_region(), as sev_guest() isn't stable unless kvm->lock is held (or KVM can guarantee KVM_SEV_INIT{2} has completed and can't rollack state). If KVM_SEV_INIT{2} fails, KVM can end up trying to add to a not-yet-initialized sev->regions_list, e.g. triggering a #GP

  Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI
  KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
  CPU: 110 UID: 0 PID: 72717 Comm: syz.15.11462 Tainted: G     U  W  O        6.16.0-smp-DEV #1 NONE
  Tainted: [U]=USER, [W]=WARN, [O]=OOT_MODULE
  Hardware name: Google, Inc. Arcadia_IT_80/Arcadia_IT_80, BIOS 12.52.0-0 10/28/2024
  RIP: 0010:sev_mem_enc_register_region+0x3f0/0x4f0 ../include/linux/list.h:83
  Code: <41> 80 3c 04 00 74 08 4c 89 ff e8 f1 c7 a2 00 49 39 ed 0f 84 c6 00
  RSP: 0018:ffff88838647fbb8 EFLAGS: 00010256
  RAX: dffffc0000000000 RBX: 1ffff92015cf1e0b RCX: dffffc0000000000
  RDX: 0000000000000000 RSI: 0000000000001000 RDI: ffff888367870000
  RBP: ffffc900ae78f050 R08: ffffea000d9e0007 R09: 1ffffd4001b3c000
  R10: dffffc0000000000 R11: fffff94001b3c001 R12: 0000000000000000
  R13: ffff8982ab0bde00 R14: ffffc900ae78f058 R15: 0000000000000000
  FS:  00007f34e9dc66c0(0000) GS:ffff89ee64d33000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007fe180adef98 CR3: 000000047210e000 CR4: 0000000000350ef0
  Call Trace:
   <TASK>
   kvm_arch_vm_ioctl+0xa72/0x1240 ../arch/x86/kvm/x86.c:7371
   kvm_vm_ioctl+0x649/0x990 ../virt/kvm/kvm_main.c:5363
   __se_sys_ioctl+0x101/0x170 ../fs/ioctl.c:51
   do_syscall_x64 ../arch/x86/entry/syscall_64.c:63 [inline]
   do_syscall_64+0x6f/0x1f0 ../arch/x86/entry/syscall_64.c:94
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
  RIP: 0033:0x7f34e9f7e9a9
  Code: <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
  RSP: 002b:00007f34e9dc6038 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
  RAX: ffffffffffffffda RBX: 00007f34ea1a6080 RCX: 00007f34e9f7e9a9
  RDX: 0000200000000280 RSI: 000000008010aebb RDI: 0000000000000007
  RBP: 00007f34ea000d69 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
  R13: 0000000000000000 R14: 00007f34ea1a6080 R15: 00007ffce77197a8
   </TASK>

with a syzlang reproducer that looks like:

syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000040)={0x0, &(0x7f0000000180)=ANY=[], 0x70}) (async) syz_kvm_add_vcpu$x86(0x0, &(0x7f0000000080)={0x0, &(0x7f0000000180)=ANY=[@ANYBLOB="..."], 0x4f}) (async)
r0 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000200), 0x0, 0x0)
r1 = ioctl$KVM_CREATE_VM(r0, 0xae01, 0x0)
r2 = openat$kvm(0xffffffffffffff9c, &(0x7f0000000240), 0x0, 0x0)
r3 = ioctl$KVM_CREATE_VM(r2, 0xae01, 0x0)
ioctl$KVM_SET_CLOCK(r3, 0xc008aeba, &(0x7f0000000040)={0x1, 0x8, 0x0, 0x5625e9b0}) (async) ioctl$KVM_SET_PIT2(r3, 0x8010aebb, &(0x7f0000000280)={[...], 0x5}) (async)
ioctl$KVM_SET_PIT2(r1, 0x4070aea0, 0x0) (async)
r4 = ioctl$KVM_CREATE_VM(0xffffffffffffffff, 0xae01, 0x0)
openat$kvm(0xffffffffffffff9c, 0x0, 0x0, 0x0) (async)
ioctl$KVM_SET_USER_MEMORY_REGION(r4, 0x4020ae46, &(0x7f0000000400)={0x0, 0x0, 0x0, 0x2000, &(0x7f0000001000/0x2000)=nil}) (async) r5 = ioctl$KVM_CREATE_VCPU(r4, 0xae41, 0x2)
close(r0) (async)
openat$kvm(0xffffffffffffff9c, &(0x7f0000000000), 0x8000, 0x0) (async)
ioctl$KVM_SET_GUEST_DEBUG(r5, 0x4048ae9b, &(0x7f0000000300)={0x4376ea830d46549b, 0x0, [0x46, 0x0, 0x0, 0x0, 0x0, 0x1000]}) (async) ioctl$KVM_RUN(r5, 0xae80, 0x0)

Opportunistically use guard() to avoid having to define a new error label and goto usage.

---
 arch/x86/kvm/svm/sev.c |    6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

@@ -2704,6 +2704,8 @@ int sev_mem_enc_register_region(struct k
 	struct enc_region *region;
 	int ret = 0;
 
+	guard(mutex)(&kvm->lock);
+
 	if (!sev_guest(kvm))
 		return -ENOTTY;
 

@@ -2718,12 +2720,10 @@ int sev_mem_enc_register_region(struct k
 	if (!region)
 		return -ENOMEM;
 
-	mutex_lock(&kvm->lock);
 	region->pages = sev_pin_memory(kvm, range->addr, range->size, &region->npages,
 				       FOLL_WRITE | FOLL_LONGTERM);
 	if (IS_ERR(region->pages)) {
 		ret = PTR_ERR(region->pages);
-		mutex_unlock(&kvm->lock);
 		goto e_free;
 	}
 

@@ -2741,8 +2741,6 @@ int sev_mem_enc_register_region(struct k
 	region->size = range->size;
 
 	list_add_tail(&region->list, &sev->regions_list);
-	mutex_unlock(&kvm->lock);
-
 	return ret;
 
 e_free:

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

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

From: Sean Christopherson <[email protected]>

commit 624bf3440d7214b62c22d698a0a294323f331d5d upstream.

Reject LAUNCH_FINISH for SEV-ES and SNP VMs if KVM is actively creating one or more vCPUs, as KVM needs to process and encrypt each vCPU's VMSA. Letting userspace create vCPUs while LAUNCH_FINISH is in-progress is "fine", at least in the current code base, as kvm_for_each_vcpu() operates on online_vcpus, LAUNCH_FINISH (all SEV+ sub-ioctls) holds kvm->mutex, and fully onlining a vCPU in kvm_vm_ioctl_create_vcpu() is done under kvm->mutex. I.e. there's no difference between an in-progress vCPU and a vCPU that is created entirely after LAUNCH_FINISH.

However, given that concurrent LAUNCH_FINISH and vCPU creation can't possibly work (for any reasonable definition of "work"), since userspace can't guarantee whether a particular vCPU will be encrypted or not, disallow the combination as a hardening measure, to reduce the probability of introducing bugs in the future, and to avoid having to reason about the safety of future changes related to LAUNCH_FINISH.

---
 arch/x86/kvm/svm/sev.c   |   10 ++++++++--
 include/linux/kvm_host.h |    7 +++++++
 2 files changed, 15 insertions(+), 2 deletions(-)

@@ -1030,6 +1030,9 @@ static int sev_launch_update_vmsa(struct
 	if (!sev_es_guest(kvm))
 		return -ENOTTY;
 
+	if (kvm_is_vcpu_creation_in_progress(kvm))
+		return -EBUSY;
+
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		ret = mutex_lock_killable(&vcpu->mutex);
 		if (ret)

@@ -2050,8 +2053,8 @@ static int sev_check_source_vcpus(struct
 	struct kvm_vcpu *src_vcpu;
 	unsigned long i;
 
-	if (src->created_vcpus != atomic_read(&src->online_vcpus) ||
-	    dst->created_vcpus != atomic_read(&dst->online_vcpus))
+	if (kvm_is_vcpu_creation_in_progress(src) ||
+	    kvm_is_vcpu_creation_in_progress(dst))
 		return -EBUSY;
 
 	if (!sev_es_guest(src))

@@ -2450,6 +2453,9 @@ static int snp_launch_update_vmsa(struct
 	unsigned long i;
 	int ret;
 
+	if (kvm_is_vcpu_creation_in_progress(kvm))
+		return -EBUSY;
+
 	data.gctx_paddr = __psp_pa(sev->snp_context);
 	data.page_type = SNP_PAGE_TYPE_VMSA;
 

@@ -1029,6 +1029,13 @@ static inline struct kvm_vcpu *kvm_get_v
 	return NULL;
 }
 
+static inline bool kvm_is_vcpu_creation_in_progress(struct kvm *kvm)
+{
+	lockdep_assert_held(&kvm->lock);
+
+	return kvm->created_vcpus != atomic_read(&kvm->online_vcpus);
+}
+
 void kvm_destroy_vcpus(struct kvm *kvm);
 
 int kvm_trylock_all_vcpus(struct kvm *kvm);

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

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

From: Sean Christopherson <[email protected]>

commit cb923ee6a80f4e604e6242a4702b59251e61a380 upstream.

Lock all vCPUs when synchronizing and encrypting VMSAs for SNP guests, as allowing userspace to manipulate and/or run a vCPU while its state is being synchronized would at best corrupt vCPU state, and at worst crash the host kernel.

Opportunistically assert that vcpu->mutex is held when synchronizing its VMSA (the SEV-ES path already locks vCPUs).

---
 arch/x86/kvm/svm/sev.c |   16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

@@ -882,6 +882,8 @@ static int sev_es_sync_vmsa(struct vcpu_
 	u8 *d;
 	int i;
 
+	lockdep_assert_held(&vcpu->mutex);
+
 	if (vcpu->arch.guest_state_protected)
 		return -EINVAL;
 

@@ -2456,6 +2458,10 @@ static int snp_launch_update_vmsa(struct
 	if (kvm_is_vcpu_creation_in_progress(kvm))
 		return -EBUSY;
 
+	ret = kvm_lock_all_vcpus(kvm);
+	if (ret)
+		return ret;
+
 	data.gctx_paddr = __psp_pa(sev->snp_context);
 	data.page_type = SNP_PAGE_TYPE_VMSA;
 

@@ -2465,12 +2471,12 @@ static int snp_launch_update_vmsa(struct
 
 		ret = sev_es_sync_vmsa(svm);
 		if (ret)
-			return ret;
+			goto out;
 
 		/* Transition the VMSA page to a firmware state. */
 		ret = rmp_make_private(pfn, INITIAL_VMSA_GPA, PG_LEVEL_4K, sev->asid, true);
 		if (ret)
-			return ret;
+			goto out;
 
 		/* Issue the SNP command to encrypt the VMSA */
 		data.address = __sme_pa(svm->sev_es.vmsa);

@@ -2479,7 +2485,7 @@ static int snp_launch_update_vmsa(struct
 		if (ret) {
 			snp_page_reclaim(kvm, pfn);
 
-			return ret;
+			goto out;
 		}
 
 		svm->vcpu.arch.guest_state_protected = true;

@@ -2493,7 +2499,9 @@ static int snp_launch_update_vmsa(struct
 		svm_enable_lbrv(vcpu);
 	}
 
-	return 0;
+out:
+	kvm_unlock_all_vcpus(kvm);
+	return ret;
 }
 
 static int snp_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)

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

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

From: Sean Christopherson <[email protected]>

commit 8acffeef5ef720c35e513e322ab08e32683f32f2 upstream.

Drop the WARN in sev_pin_memory() on npages overflowing an int, as the WARN is comically trivially to trigger from userspace, e.g. by doing:

  struct kvm_enc_region range = {
          .addr = 0,
          .size = -1ul,
  };

  __vm_ioctl(vm, KVM_MEMORY_ENCRYPT_REG_REGION, &range);

Note, the checks in sev_mem_enc_register_region() that presumably exist to verify the incoming address+size are completely worthless, as both "addr" and "size" are u64s and SEV is 64-bit only, i.e. they _can't_ be greater than ULONG_MAX. That wart will be cleaned up in the near future.

	if (range->addr > ULONG_MAX || range->size > ULONG_MAX)
		return -EINVAL;

Opportunistically add a comment to explain why the code calculates the number of pages the "hard" way, e.g. instead of just shifting @ulen.

---
 arch/x86/kvm/svm/sev.c |   11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

@@ -690,10 +690,16 @@ static struct page **sev_pin_memory(stru
 	if (ulen == 0 || uaddr + ulen < uaddr)
 		return ERR_PTR(-EINVAL);
 
-	/* Calculate number of pages. */
+	/*
+	 * Calculate the number of pages that need to be pinned to cover the
+	 * entire range.  Note!  This isn't simply ulen >> PAGE_SHIFT, as KVM
+	 * doesn't require the incoming address+size to be page aligned!
+	 */
 	first = (uaddr & PAGE_MASK) >> PAGE_SHIFT;
 	last = ((uaddr + ulen - 1) & PAGE_MASK) >> PAGE_SHIFT;
 	npages = (last - first + 1);
+	if (npages > INT_MAX)
+		return ERR_PTR(-EINVAL);
 
 	locked = sev->pages_locked + npages;
 	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;

@@ -702,9 +708,6 @@ static struct page **sev_pin_memory(stru
 		return ERR_PTR(-ENOMEM);
 	}
 
-	if (WARN_ON_ONCE(npages > INT_MAX))
-		return ERR_PTR(-EINVAL);
-
 	/* Avoid using vmalloc for smaller buffers. */
 	size = npages * sizeof(struct page *);
 	if (size > PAGE_SIZE)

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

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

From: Matthew Wilcox (Oracle) <[email protected]>

commit 615d9bb2ccad42f9e21d837431e401db2e471195 upstream.

We can only call filemap_free_folio() if we have a reference to (or hold a lock on) the mapping. Otherwise, we've already removed the folio from the mapping so it no longer pins the mapping and the mapping can be removed, causing a use-after-free when accessing mapping->a_ops.

Follow the same pattern as __remove_mapping() and load the free_folio function pointer before dropping the lock on the mapping. That lets us make filemap_free_folio() static as this was the only caller outside filemap.c.

---
 mm/filemap.c  |    3 ++-
 mm/internal.h |    1 -
 mm/truncate.c |    6 +++++-
 3 files changed, 7 insertions(+), 3 deletions(-)

@@ -228,7 +228,8 @@ void __filemap_remove_folio(struct folio
 	page_cache_delete(mapping, folio, shadow);
 }
 
-void filemap_free_folio(struct address_space *mapping, struct folio *folio)
+static void filemap_free_folio(const struct address_space *mapping,
+		struct folio *folio)
 {
 	void (*free_folio)(struct folio *);
 

@@ -540,7 +540,6 @@ unsigned find_lock_entries(struct addres
 		pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
 unsigned find_get_entries(struct address_space *mapping, pgoff_t *start,
 		pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices);
-void filemap_free_folio(struct address_space *mapping, struct folio *folio);
 int truncate_inode_folio(struct address_space *mapping, struct folio *folio);
 bool truncate_inode_partial_folio(struct folio *folio, loff_t start,
 		loff_t end);

@@ -622,6 +622,7 @@ static int folio_launder(struct address_
 int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio,
 			   gfp_t gfp)
 {
+	void (*free_folio)(struct folio *);
 	int ret;
 
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);

@@ -648,9 +649,12 @@ int folio_unmap_invalidate(struct addres
 	xa_unlock_irq(&mapping->i_pages);
 	if (mapping_shrinkable(mapping))
 		inode_lru_list_add(mapping->host);
+	free_folio = mapping->a_ops->free_folio;
 	spin_unlock(&mapping->host->i_lock);
 
-	filemap_free_folio(mapping, folio);
+	if (free_folio)
+		free_folio(folio);
+	folio_put_refs(folio, folio_nr_pages(folio));
 	return 1;
 failed:
 	xa_unlock_irq(&mapping->i_pages);

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

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

From: Sasha Levin <[email protected]>

commit d1db4118489fffd2b2f612140b7acbb477880839 upstream.

The Assisted-by tag was introduced in Documentation/process/coding-assistants.rst for attributing AI tool contributions to kernel patches. However, checkpatch.pl did not recognize this tag, causing two issues:

WARNING: Non-standard signature: Assisted-by:
ERROR: Unrecognized email address: 'AGENT_NAME:MODEL_VERSION'

Fix this by:
1. Adding Assisted-by to the recognized $signature_tags list
2. Skipping email validation for Assisted-by lines since they use the AGENT_NAME:MODEL_VERSION format instead of an email address
3. Warning when the Assisted-by value doesn't match the expected format

---
 scripts/checkpatch.pl |   10 ++++++++++
 1 file changed, 10 insertions(+)

@@ -641,6 +641,7 @@ our $signature_tags = qr{(?xi:
 	Reviewed-by:|
 	Reported-by:|
 	Suggested-by:|
+	Assisted-by:|
 	To:|
 	Cc:
 )};

@@ -3105,6 +3106,15 @@ sub process {
 				}
 			}
 
+			# Assisted-by uses AGENT_NAME:MODEL_VERSION format, not email
+			if ($sign_off =~ /^Assisted-by:/i) {
+				if ($email !~ /^\S+:\S+/) {
+					WARN("BAD_SIGN_OFF",
+					     "Assisted-by expects 'AGENT_NAME:MODEL_VERSION [TOOL1] [TOOL2]' format\n" . $herecurr);
+				}
+				next;
+			}
+
 			my ($email_name, $name_comment, $email_address, $comment) = parse_email($email);
 			my $suggested_email = format_email(($email_name, $name_comment, $email_address, $comment));
 			if ($suggested_email eq "") {

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

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

From: Linus Torvalds <[email protected]>

commit d187a86de793f84766ea40b9ade7ac60aabbb4fe upstream.

This function was a masterclass in bad naming, for various historical reasons.

It claimed to be a non-cached user copy. It is literally _neither_ of those things. It's a specialty memory copy routine that uses non-temporal stores for the destination (but not the source), and that does exception handling for both source and destination accesses.

Also note that while it works for unaligned targets, any unaligned parts (whether at beginning or end) will not use non-temporal stores, since only words and quadwords can be non-temporal on x86.

The exception handling means that it _can_ be used for user space accesses, but not on its own - it needs all the normal "start user space access" logic around it.

But typically the user space access would be the source, not the non-temporal destination. That was the original intention of this, where the destination was some fragile persistent memory target that needed non-temporal stores in order to catch machine check exceptions synchronously and deal with them gracefully.

Thus that non-descriptive name: one use case was to copy from user space into a non-cached kernel buffer. However, the existing users are a mix of that intended use-case, and a couple of random drivers that just did this as a performance tweak.

Some of those random drivers then actively misused the user copying version (with STAC/CLAC and all) to do kernel copies without ever even caring about the exception handling, _just_ for the non-temporal destination.

Rename it as a first small step to actually make it halfway sane, and change the prototype to be more normal: it doesn't take a user pointer unless the caller has done the proper conversion, and the argument size is the full size_t (it still won't actually copy more than 4GB in one go, but there's also no reason to silently truncate the size argument in the caller).

Finally, use this now sanely named function in the NTB code, which mis-used a user copy version (with STAC/CLAC and all) of this interface despite it not actually being a user copy at all.

---
 arch/x86/include/asm/uaccess_64.h    |    5 +++--
 arch/x86/lib/copy_user_uncached_64.S |    6 +++---
 arch/x86/lib/usercopy_64.c           |    4 ++--
 drivers/infiniband/sw/rdmavt/qp.c    |    8 +++-----
 drivers/ntb/ntb_transport.c          |    7 ++++---
 tools/objtool/check.c                |    2 +-
 6 files changed, 16 insertions(+), 16 deletions(-)

@@ -147,7 +147,8 @@ raw_copy_to_user(void __user *dst, const
 	return copy_user_generic((__force void *)dst, src, size);
 }
 
-extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size);
+#define copy_to_nontemporal copy_to_nontemporal
+extern size_t copy_to_nontemporal(void *dst, const void *src, size_t size);
 extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size);
 
 static inline int

@@ -157,7 +158,7 @@ __copy_from_user_inatomic_nocache(void *
 	long ret;
 	kasan_check_write(dst, size);
 	stac();
-	ret = __copy_user_nocache(dst, src, size);
+	ret = copy_to_nontemporal(dst, (__force const void *)src, size);
 	clac();
 	return ret;
 }

@@ -27,7 +27,7 @@
  * Output:
  * rax uncopied bytes or 0 if successful.
  */
-SYM_FUNC_START(__copy_user_nocache)
+SYM_FUNC_START(copy_to_nontemporal)
 	ANNOTATE_NOENDBR
 	/* If destination is not 7-byte aligned, we'll have to align it */
 	testb $7,%dil

@@ -240,5 +240,5 @@ _ASM_EXTABLE_UA(95b, .Ldone)
 _ASM_EXTABLE_UA(52b, .Ldone0)
 _ASM_EXTABLE_UA(53b, .Ldone0)
 
-SYM_FUNC_END(__copy_user_nocache)
-EXPORT_SYMBOL(__copy_user_nocache)
+SYM_FUNC_END(copy_to_nontemporal)
+EXPORT_SYMBOL(copy_to_nontemporal)

@@ -49,11 +49,11 @@ long __copy_user_flushcache(void *dst, c
 	long rc;
 
 	stac();
-	rc = __copy_user_nocache(dst, src, size);
+	rc = copy_to_nontemporal(dst, (__force const void *)src, size);
 	clac();
 
 	/*
-	 * __copy_user_nocache() uses non-temporal stores for the bulk
+	 * copy_to_nontemporal() uses non-temporal stores for the bulk
 	 * of the transfer, but we need to manually flush if the
 	 * transfer is unaligned. A cached memory copy is used when
 	 * destination or size is not naturally aligned. That is:

@@ -92,12 +92,10 @@ static int rvt_wss_llc_size(void)
 static void cacheless_memcpy(void *dst, void *src, size_t n)
 {
 	/*
-	 * Use the only available X64 cacheless copy.  Add a __user cast
-	 * to quiet sparse.  The src agument is already in the kernel so
-	 * there are no security issues.  The extra fault recovery machinery
-	 * is not invoked.
+	 * Use the only available X64 cacheless copy.
+	 * The extra fault recovery machinery is not invoked.
 	 */
-	__copy_user_nocache(dst, (void __user *)src, n);
+	copy_to_nontemporal(dst, src, n);
 }
 
 void rvt_wss_exit(struct rvt_dev_info *rdi)

@@ -1779,12 +1779,13 @@ static void ntb_tx_copy_callback(void *d
 
 static void ntb_memcpy_tx_on_stack(struct ntb_queue_entry *entry, void __iomem *offset)
 {
-#ifdef ARCH_HAS_NOCACHE_UACCESS
+#ifdef copy_to_nontemporal
 	/*
 	 * Using non-temporal mov to improve performance on non-cached
-	 * writes, even though we aren't actually copying from user space.
+	 * writes. This only works if __iomem is strictly memory-like,
+	 * but that is the case on x86-64
 	 */
-	__copy_from_user_inatomic_nocache(offset, entry->buf, entry->len);
+	copy_to_nontemporal(offset, entry->buf, entry->len);
 #else
 	memcpy_toio(offset, entry->buf, entry->len);
 #endif

@@ -1301,7 +1301,7 @@ static const char *uaccess_safe_builtin[
 	"copy_mc_enhanced_fast_string",
 	"rep_stos_alternative",
 	"rep_movs_alternative",
-	"__copy_user_nocache",
+	"copy_to_nontemporal",
 	NULL
 };
 

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

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

From: Linus Torvalds <[email protected]>

commit 5de7bcaadf160c1716b20a263cf8f5b06f658959 upstream.

Similarly to the previous commit, this renames the somewhat confusingly named function. But in this case, it was at least less confusing: the __copy_from_user_inatomic_nocache is indeed copying from user memory, and it is indeed ok to be used in an atomic context, so it will not warn about it.

But the previous commit also removed the NTB mis-use of the __copy_from_user_inatomic_nocache() function, and as a result every call-site is now _actually_ doing a real user copy. That means that we can now do the proper user pointer verification too.

End result: add proper address checking, remove the double underscores, and change the "nocache" to "nontemporal" to more accurately describe what this x86-only function actually does. It might be worth noting that only the target is non-temporal: the actual user accesses are normal memory accesses.

Also worth noting is that non-x86 targets (and on older 32-bit x86 CPU's before XMM2 in the Pentium III) we end up just falling back on a regular user copy, so nothing can actually depend on the non-temporal semantics, but that has always been true.

---
 arch/x86/include/asm/uaccess.h    |    2 +-
 arch/x86/include/asm/uaccess_32.h |    8 +-------
 arch/x86/include/asm/uaccess_64.h |    3 ++-
 arch/x86/lib/usercopy_32.c        |    9 +++++----
 drivers/gpu/drm/i915/i915_gem.c   |    2 +-
 drivers/gpu/drm/qxl/qxl_ioctl.c   |    2 +-
 include/linux/uaccess.h           |   11 ++++++++---
 lib/iov_iter.c                    |    2 +-
 8 files changed, 20 insertions(+), 19 deletions(-)

@@ -507,7 +507,7 @@ extern struct movsl_mask {
 } ____cacheline_aligned_in_smp movsl_mask;
 #endif
 
-#define ARCH_HAS_NOCACHE_UACCESS 1
+#define ARCH_HAS_NONTEMPORAL_UACCESS 1
 
 /*
  * The "unsafe" user accesses aren't really "unsafe", but the naming

@@ -26,13 +26,7 @@ raw_copy_from_user(void *to, const void
 	return __copy_user_ll(to, (__force const void *)from, n);
 }
 
-static __always_inline unsigned long
-__copy_from_user_inatomic_nocache(void *to, const void __user *from,
-				  unsigned long n)
-{
-       return __copy_from_user_ll_nocache_nozero(to, from, n);
-}
-
+unsigned long __must_check copy_from_user_inatomic_nontemporal(void *, const void __user *, unsigned long n);
 unsigned long __must_check clear_user(void __user *mem, unsigned long len);
 unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
 

@@ -152,11 +152,12 @@ extern size_t copy_to_nontemporal(void *
 extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size);
 
 static inline int
-__copy_from_user_inatomic_nocache(void *dst, const void __user *src,
+copy_from_user_inatomic_nontemporal(void *dst, const void __user *src,
 				  unsigned size)
 {
 	long ret;
 	kasan_check_write(dst, size);
+	src = mask_user_address(src);
 	stac();
 	ret = copy_to_nontemporal(dst, (__force const void *)src, size);
 	clac();

@@ -322,10 +322,11 @@ unsigned long __copy_user_ll(void *to, c
 }
 EXPORT_SYMBOL(__copy_user_ll);
 
-unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
+unsigned long copy_from_user_inatomic_nontemporal(void *to, const void __user *from,
 					unsigned long n)
 {
-	__uaccess_begin_nospec();
+	if (!user_access_begin(from, n))
+		return n;
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && static_cpu_has(X86_FEATURE_XMM2))
 		n = __copy_user_intel_nocache(to, from, n);

@@ -334,7 +335,7 @@ unsigned long __copy_from_user_ll_nocach
 #else
 	__copy_user(to, from, n);
 #endif
-	__uaccess_end();
+	user_access_end();
 	return n;
 }
-EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
+EXPORT_SYMBOL(copy_from_user_inatomic_nontemporal);

@@ -520,7 +520,7 @@ ggtt_write(struct io_mapping *mapping,
 
 	/* We can use the cpu mem copy function because this is X86. */
 	vaddr = io_mapping_map_atomic_wc(mapping, base);
-	unwritten = __copy_from_user_inatomic_nocache((void __force *)vaddr + offset,
+	unwritten = copy_from_user_inatomic_nontemporal((void __force *)vaddr + offset,
 						      user_data, length);
 	io_mapping_unmap_atomic(vaddr);
 	if (unwritten) {

@@ -183,7 +183,7 @@ static int qxl_process_single_command(st
 
 	/* TODO copy slow path code from i915 */
 	fb_cmd = qxl_bo_kmap_atomic_page(qdev, cmd_bo, (release->release_offset & PAGE_MASK));
-	unwritten = __copy_from_user_inatomic_nocache
+	unwritten = copy_from_user_inatomic_nontemporal
 		(fb_cmd + sizeof(union qxl_release_info) + (release->release_offset & ~PAGE_MASK),
 		 u64_to_user_ptr(cmd->command), cmd->command_size);
 

@@ -331,16 +331,21 @@ static inline size_t probe_subpage_write
 
 #endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */
 
-#ifndef ARCH_HAS_NOCACHE_UACCESS
+#ifndef ARCH_HAS_NONTEMPORAL_UACCESS
 
 static inline __must_check unsigned long
-__copy_from_user_inatomic_nocache(void *to, const void __user *from,
+copy_from_user_inatomic_nontemporal(void *to, const void __user *from,
 				  unsigned long n)
 {
+	if (can_do_masked_user_access())
+		from = mask_user_address(from);
+	else
+		if (!access_ok(from, n))
+			return n;
 	return __copy_from_user_inatomic(to, from, n);
 }
 
-#endif		/* ARCH_HAS_NOCACHE_UACCESS */
+#endif		/* ARCH_HAS_NONTEMPORAL_UACCESS */
 
 extern __must_check int check_zeroed_user(const void __user *from, size_t size);
 

@@ -277,7 +277,7 @@ static __always_inline
 size_t copy_from_user_iter_nocache(void __user *iter_from, size_t progress,
 				   size_t len, void *to, void *priv2)
 {
-	return __copy_from_user_inatomic_nocache(to + progress, iter_from, len);
+	return copy_from_user_inatomic_nontemporal(to + progress, iter_from, len);
 }
 
 size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)

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

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

From: Linus Torvalds <[email protected]>

commit 809b997a5ce945ab470f70c187048fe4f5df20bf upstream.

This finishes the work on these odd functions that were only implemented by a handful of architectures.

The 'flushcache' function was only used from the iterator code, and let's make it do the same thing that the nontemporal version does:
remove the two underscores and add the user address checking.

Yes, yes, the user address checking is also done at iovec import time, but we have long since walked away from the old double-underscore thing where we try to avoid address checking overhead at access time, and these functions shouldn't be so special and old-fashioned.

The arm64 version already did the address check, in fact, so there it's just a matter of renaming it. For powerpc and x86-64 we now do the proper user access boilerplate.

---
 arch/arm64/include/asm/uaccess.h   |    2 +-
 arch/powerpc/include/asm/uaccess.h |    3 +--
 arch/powerpc/lib/pmem.c            |   11 ++++++-----
 arch/x86/include/asm/uaccess_64.h  |    8 ++++----
 arch/x86/lib/usercopy_64.c         |    8 ++++----
 lib/iov_iter.c                     |    2 +-
 6 files changed, 17 insertions(+), 17 deletions(-)

@@ -478,7 +478,7 @@ extern __must_check long strnlen_user(co
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 extern unsigned long __must_check __copy_user_flushcache(void *to, const void __user *from, unsigned long n);
 
-static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
+static inline size_t copy_from_user_flushcache(void *dst, const void __user *src, size_t size)
 {
 	kasan_check_write(dst, size);
 	return __copy_user_flushcache(dst, __uaccess_mask_ptr(src), size);

@@ -434,8 +434,7 @@ copy_mc_to_user(void __user *to, const v
 }
 #endif
 
-extern long __copy_from_user_flushcache(void *dst, const void __user *src,
-		unsigned size);
+extern size_t copy_from_user_flushcache(void *dst, const void __user *src, size_t size);
 
 static __must_check __always_inline bool __user_access_begin(const void __user *ptr, size_t len,
 							     unsigned long dir)

@@ -66,15 +66,16 @@ EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
 /*
  * CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE symbols
  */
-long __copy_from_user_flushcache(void *dest, const void __user *src,
-		unsigned size)
+size_t copy_from_user_flushcache(void *dest, const void __user *src,
+				 size_t size)
 {
-	unsigned long copied, start = (unsigned long) dest;
+	unsigned long not_copied, start = (unsigned long) dest;
 
-	copied = __copy_from_user(dest, src, size);
+	src = mask_user_address(src);
+	not_copied = __copy_from_user(dest, src, size);
 	clean_pmem_range(start, start + size);
 
-	return copied;
+	return not_copied;
 }
 
 void memcpy_flushcache(void *dest, const void *src, size_t size)

@@ -149,7 +149,7 @@ raw_copy_to_user(void __user *dst, const
 
 #define copy_to_nontemporal copy_to_nontemporal
 extern size_t copy_to_nontemporal(void *dst, const void *src, size_t size);
-extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size);
+extern size_t copy_user_flushcache(void *dst, const void __user *src, size_t size);
 
 static inline int
 copy_from_user_inatomic_nontemporal(void *dst, const void __user *src,

@@ -164,11 +164,11 @@ copy_from_user_inatomic_nontemporal(void
 	return ret;
 }
 
-static inline int
-__copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
+static inline size_t
+copy_from_user_flushcache(void *dst, const void __user *src, size_t size)
 {
 	kasan_check_write(dst, size);
-	return __copy_user_flushcache(dst, src, size);
+	return copy_user_flushcache(dst, src, size);
 }
 
 /*

@@ -43,14 +43,14 @@ void arch_wb_cache_pmem(void *addr, size
 }
 EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
 
-long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
+size_t copy_user_flushcache(void *dst, const void __user *src, size_t size)
 {
 	unsigned long flushed, dest = (unsigned long) dst;
-	long rc;
+	unsigned long rc;
 
-	stac();
+	src = masked_user_access_begin(src);
 	rc = copy_to_nontemporal(dst, (__force const void *)src, size);
-	clac();
+	user_access_end();
 
 	/*
 	 * copy_to_nontemporal() uses non-temporal stores for the bulk