5.4.301-rc1 review

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

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

From: Thomas Fourier <[email protected]>

[ Upstream commit 1069a4fe637d0e3e4c163e3f8df9be306cc299b4 ]

The DMA map functions can fail and should be tested for errors. If the mapping fails, free blanking_ptr and set it to 0. As 0 is a valid DMA address, use blanking_ptr to test if the DMA address is set.

---
 drivers/media/pci/ivtv/ivtv-irq.c |    2 +-
 drivers/media/pci/ivtv/ivtv-yuv.c |    8 +++++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

@@ -351,7 +351,7 @@ void ivtv_dma_stream_dec_prepare(struct
 
 	/* Insert buffer block for YUV if needed */
 	if (s->type == IVTV_DEC_STREAM_TYPE_YUV && f->offset_y) {
-		if (yi->blanking_dmaptr) {
+		if (yi->blanking_ptr) {
 			s->sg_pending[idx].src = yi->blanking_dmaptr;
 			s->sg_pending[idx].dst = offset;
 			s->sg_pending[idx].size = 720 * 16;

@@ -125,7 +125,7 @@ static int ivtv_yuv_prep_user_dma(struct
 	ivtv_udma_fill_sg_array(dma, y_buffer_offset, uv_buffer_offset, y_size);
 
 	/* If we've offset the y plane, ensure top area is blanked */
-	if (f->offset_y && yi->blanking_dmaptr) {
+	if (f->offset_y && yi->blanking_ptr) {
 		dma->SGarray[dma->SG_length].size = cpu_to_le32(720*16);
 		dma->SGarray[dma->SG_length].src = cpu_to_le32(yi->blanking_dmaptr);
 		dma->SGarray[dma->SG_length].dst = cpu_to_le32(IVTV_DECODER_OFFSET + yuv_offset[frame]);

@@ -929,6 +929,12 @@ static void ivtv_yuv_init(struct ivtv *i
 		yi->blanking_dmaptr = dma_map_single(&itv->pdev->dev,
 						     yi->blanking_ptr,
 						     720 * 16, DMA_TO_DEVICE);
+		if (dma_mapping_error(&itv->pdev->dev, yi->blanking_dmaptr)) {
+			kfree(yi->blanking_ptr);
+			yi->blanking_ptr = NULL;
+			yi->blanking_dmaptr = 0;
+			IVTV_DEBUG_WARN("Failed to dma_map yuv blanking buffer\n");
+		}
 	} else {
 		yi->blanking_dmaptr = 0;
 		IVTV_DEBUG_WARN("Failed to allocate yuv blanking buffer\n");

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

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

From: Christophe JAILLET <[email protected]>

[ Upstream commit b49db89e9697ddfa7fbe7387e176072ee2feb2db ]

The wrappers in include/linux/pci-dma-compat.h should go away.

The patch has been generated with the coccinelle script below and has been hand modified to replace GFP_ with a correct flag.
It has been compile tested.

When memory is allocated in 'rio_probe1()' GFP_KERNEL can be used because it is a probe function and no lock is taken in the between.

@@
@@
- PCI_DMA_BIDIRECTIONAL
+ DMA_BIDIRECTIONAL

@@
@@
- PCI_DMA_TODEVICE
+ DMA_TO_DEVICE

@@
@@
- PCI_DMA_FROMDEVICE
+ DMA_FROM_DEVICE

@@
@@
- PCI_DMA_NONE
+ DMA_NONE

@@
expression e1, e2, e3;
@@
- pci_alloc_consistent(e1, e2, e3)
+ dma_alloc_coherent(&e1->dev, e2, e3, GFP_)

@@
expression e1, e2, e3;
@@
- pci_zalloc_consistent(e1, e2, e3)
+ dma_alloc_coherent(&e1->dev, e2, e3, GFP_)

@@
expression e1, e2, e3, e4;
@@
- pci_free_consistent(e1, e2, e3, e4)
+ dma_free_coherent(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
- pci_map_single(e1, e2, e3, e4)
+ dma_map_single(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
- pci_unmap_single(e1, e2, e3, e4)
+ dma_unmap_single(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4, e5;
@@
- pci_map_page(e1, e2, e3, e4, e5)
+ dma_map_page(&e1->dev, e2, e3, e4, e5)

@@
expression e1, e2, e3, e4;
@@
- pci_unmap_page(e1, e2, e3, e4)
+ dma_unmap_page(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
- pci_map_sg(e1, e2, e3, e4)
+ dma_map_sg(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
- pci_unmap_sg(e1, e2, e3, e4)
+ dma_unmap_sg(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_single_for_cpu(e1, e2, e3, e4)
+ dma_sync_single_for_cpu(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_single_for_device(e1, e2, e3, e4)
+ dma_sync_single_for_device(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_sg_for_cpu(e1, e2, e3, e4)
+ dma_sync_sg_for_cpu(&e1->dev, e2, e3, e4)

@@
expression e1, e2, e3, e4;
@@
- pci_dma_sync_sg_for_device(e1, e2, e3, e4)
+ dma_sync_sg_for_device(&e1->dev, e2, e3, e4)

@@
expression e1, e2;
@@
- pci_dma_mapping_error(e1, e2)
+ dma_mapping_error(&e1->dev, e2)

@@
expression e1, e2;
@@
- pci_set_dma_mask(e1, e2)
+ dma_set_mask(&e1->dev, e2)

@@
expression e1, e2;
@@
- pci_set_consistent_dma_mask(e1, e2)
+ dma_set_coherent_mask(&e1->dev, e2)

Stable-dep-of: 65946eac6d88 ("net: dlink: handle dma_map_single() failure properly")

---
 drivers/net/ethernet/dlink/dl2k.c | 80 ++++++++++++++++---------------
 1 file changed, 41 insertions(+), 39 deletions(-)

index b4a8d4f12087a..8597648156635 100644
@@ -233,13 +233,15 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata (pdev, dev);
 
-	ring_space = pci_alloc_consistent (pdev, TX_TOTAL_SIZE, &ring_dma);
+	ring_space = dma_alloc_coherent(&pdev->dev, TX_TOTAL_SIZE, &ring_dma,
+					GFP_KERNEL);
 	if (!ring_space)
 		goto err_out_iounmap;
 	np->tx_ring = ring_space;
 	np->tx_ring_dma = ring_dma;
 
-	ring_space = pci_alloc_consistent (pdev, RX_TOTAL_SIZE, &ring_dma);
+	ring_space = dma_alloc_coherent(&pdev->dev, RX_TOTAL_SIZE, &ring_dma,
+					GFP_KERNEL);
 	if (!ring_space)
 		goto err_out_unmap_tx;
 	np->rx_ring = ring_space;

@@ -290,9 +292,11 @@ rio_probe1 (struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 
 err_out_unmap_rx:
-	pci_free_consistent (pdev, RX_TOTAL_SIZE, np->rx_ring, np->rx_ring_dma);
+	dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, np->rx_ring,
+			  np->rx_ring_dma);
 err_out_unmap_tx:
-	pci_free_consistent (pdev, TX_TOTAL_SIZE, np->tx_ring, np->tx_ring_dma);
+	dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, np->tx_ring,
+			  np->tx_ring_dma);
 err_out_iounmap:
 #ifdef MEM_MAPPING
 	pci_iounmap(pdev, np->ioaddr);

@@ -446,8 +450,9 @@ static void free_list(struct net_device *dev)
 	for (i = 0; i < RX_RING_SIZE; i++) {
 		skb = np->rx_skbuff[i];
 		if (skb) {
-			pci_unmap_single(np->pdev, desc_to_dma(&np->rx_ring[i]),
-					 skb->len, PCI_DMA_FROMDEVICE);
+			dma_unmap_single(&np->pdev->dev,
+					 desc_to_dma(&np->rx_ring[i]),
+					 skb->len, DMA_FROM_DEVICE);
 			dev_kfree_skb(skb);
 			np->rx_skbuff[i] = NULL;
 		}

@@ -457,8 +462,9 @@ static void free_list(struct net_device *dev)
 	for (i = 0; i < TX_RING_SIZE; i++) {
 		skb = np->tx_skbuff[i];
 		if (skb) {
-			pci_unmap_single(np->pdev, desc_to_dma(&np->tx_ring[i]),
-					 skb->len, PCI_DMA_TODEVICE);
+			dma_unmap_single(&np->pdev->dev,
+					 desc_to_dma(&np->tx_ring[i]),
+					 skb->len, DMA_TO_DEVICE);
 			dev_kfree_skb(skb);
 			np->tx_skbuff[i] = NULL;
 		}

@@ -515,9 +521,8 @@ static int alloc_list(struct net_device *dev)
 						sizeof(struct netdev_desc));
 		/* Rubicon now supports 40 bits of addressing space. */
 		np->rx_ring[i].fraginfo =
-		    cpu_to_le64(pci_map_single(
-				  np->pdev, skb->data, np->rx_buf_sz,
-				  PCI_DMA_FROMDEVICE));
+		    cpu_to_le64(dma_map_single(&np->pdev->dev, skb->data,
+					       np->rx_buf_sz, DMA_FROM_DEVICE));
 		np->rx_ring[i].fraginfo |= cpu_to_le64((u64)np->rx_buf_sz << 48);
 	}
 

@@ -683,9 +688,8 @@ rio_timer (struct timer_list *t)
 				}
 				np->rx_skbuff[entry] = skb;
 				np->rx_ring[entry].fraginfo =
-				    cpu_to_le64 (pci_map_single
-					 (np->pdev, skb->data, np->rx_buf_sz,
-					  PCI_DMA_FROMDEVICE));
+				    cpu_to_le64 (dma_map_single(&np->pdev->dev, skb->data,
+								np->rx_buf_sz, DMA_FROM_DEVICE));
 			}
 			np->rx_ring[entry].fraginfo |=
 			    cpu_to_le64((u64)np->rx_buf_sz << 48);

@@ -739,9 +743,8 @@ start_xmit (struct sk_buff *skb, struct net_device *dev)
 		    ((u64)np->vlan << 32) |
 		    ((u64)skb->priority << 45);
 	}
-	txdesc->fraginfo = cpu_to_le64 (pci_map_single (np->pdev, skb->data,
-							skb->len,
-							PCI_DMA_TODEVICE));
+	txdesc->fraginfo = cpu_to_le64 (dma_map_single(&np->pdev->dev, skb->data,
+						       skb->len, DMA_TO_DEVICE));
 	txdesc->fraginfo |= cpu_to_le64((u64)skb->len << 48);
 
 	/* DL2K bug: DMA fails to get next descriptor ptr in 10Mbps mode

@@ -838,9 +841,9 @@ rio_free_tx (struct net_device *dev, int irq)
 		if (!(np->tx_ring[entry].status & cpu_to_le64(TFDDone)))
 			break;
 		skb = np->tx_skbuff[entry];
-		pci_unmap_single (np->pdev,
-				  desc_to_dma(&np->tx_ring[entry]),
-				  skb->len, PCI_DMA_TODEVICE);
+		dma_unmap_single(&np->pdev->dev,
+				 desc_to_dma(&np->tx_ring[entry]), skb->len,
+				 DMA_TO_DEVICE);
 		if (irq)
 			dev_consume_skb_irq(skb);
 		else

@@ -965,25 +968,25 @@ receive_packet (struct net_device *dev)
 
 			/* Small skbuffs for short packets */
 			if (pkt_len > copy_thresh) {
-				pci_unmap_single (np->pdev,
-						  desc_to_dma(desc),
-						  np->rx_buf_sz,
-						  PCI_DMA_FROMDEVICE);
+				dma_unmap_single(&np->pdev->dev,
+						 desc_to_dma(desc),
+						 np->rx_buf_sz,
+						 DMA_FROM_DEVICE);
 				skb_put (skb = np->rx_skbuff[entry], pkt_len);
 				np->rx_skbuff[entry] = NULL;
 			} else if ((skb = netdev_alloc_skb_ip_align(dev, pkt_len))) {
-				pci_dma_sync_single_for_cpu(np->pdev,
-							    desc_to_dma(desc),
-							    np->rx_buf_sz,
-							    PCI_DMA_FROMDEVICE);
+				dma_sync_single_for_cpu(&np->pdev->dev,
+							desc_to_dma(desc),
+							np->rx_buf_sz,
+							DMA_FROM_DEVICE);
 				skb_copy_to_linear_data (skb,
 						  np->rx_skbuff[entry]->data,
 						  pkt_len);
 				skb_put (skb, pkt_len);
-				pci_dma_sync_single_for_device(np->pdev,
-							       desc_to_dma(desc),
-							       np->rx_buf_sz,
-							       PCI_DMA_FROMDEVICE);
+				dma_sync_single_for_device(&np->pdev->dev,
+							   desc_to_dma(desc),
+							   np->rx_buf_sz,
+							   DMA_FROM_DEVICE);
 			}
 			skb->protocol = eth_type_trans (skb, dev);
 #if 0

@@ -1016,9 +1019,8 @@ receive_packet (struct net_device *dev)
 			}
 			np->rx_skbuff[entry] = skb;
 			np->rx_ring[entry].fraginfo =
-			    cpu_to_le64 (pci_map_single
-					 (np->pdev, skb->data, np->rx_buf_sz,
-					  PCI_DMA_FROMDEVICE));
+			    cpu_to_le64(dma_map_single(&np->pdev->dev, skb->data,
+						       np->rx_buf_sz, DMA_FROM_DEVICE));
 		}
 		np->rx_ring[entry].fraginfo |=
 		    cpu_to_le64((u64)np->rx_buf_sz << 48);

@@ -1818,10 +1820,10 @@ rio_remove1 (struct pci_dev *pdev)
 		struct netdev_private *np = netdev_priv(dev);
 
 		unregister_netdev (dev);
-		pci_free_consistent (pdev, RX_TOTAL_SIZE, np->rx_ring,
-				     np->rx_ring_dma);
-		pci_free_consistent (pdev, TX_TOTAL_SIZE, np->tx_ring,
-				     np->tx_ring_dma);
+		dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, np->rx_ring,
+				  np->rx_ring_dma);
+		dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, np->tx_ring,
+				  np->tx_ring_dma);
 #ifdef MEM_MAPPING
 		pci_iounmap(pdev, np->ioaddr);
 #endif

2.51.0

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

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

From: Yeounsu Moon <[email protected]>

[ Upstream commit 65946eac6d888d50ae527c4e5c237dbe5cc3a2f2 ]

There is no error handling for dma_map_single() failures.

Add error handling by checking dma_mapping_error() and freeing the skb using dev_kfree_skb() (process context) when it fails.

Tested-on: D-Link DGE-550T Rev-A3

---
 drivers/net/ethernet/dlink/dl2k.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

index 8597648156635..855328ae6ea57 100644
@@ -508,25 +508,34 @@ static int alloc_list(struct net_device *dev)
 	for (i = 0; i < RX_RING_SIZE; i++) {
 		/* Allocated fixed size of skbuff */
 		struct sk_buff *skb;
+		dma_addr_t addr;
 
 		skb = netdev_alloc_skb_ip_align(dev, np->rx_buf_sz);
 		np->rx_skbuff[i] = skb;
-		if (!skb) {
-			free_list(dev);
-			return -ENOMEM;
-		}
+		if (!skb)
+			goto err_free_list;
+
+		addr = dma_map_single(&np->pdev->dev, skb->data,
+				      np->rx_buf_sz, DMA_FROM_DEVICE);
+		if (dma_mapping_error(&np->pdev->dev, addr))
+			goto err_kfree_skb;
 
 		np->rx_ring[i].next_desc = cpu_to_le64(np->rx_ring_dma +
 						((i + 1) % RX_RING_SIZE) *
 						sizeof(struct netdev_desc));
 		/* Rubicon now supports 40 bits of addressing space. */
-		np->rx_ring[i].fraginfo =
-		    cpu_to_le64(dma_map_single(&np->pdev->dev, skb->data,
-					       np->rx_buf_sz, DMA_FROM_DEVICE));
+		np->rx_ring[i].fraginfo = cpu_to_le64(addr);
 		np->rx_ring[i].fraginfo |= cpu_to_le64((u64)np->rx_buf_sz << 48);
 	}
 
 	return 0;
+
+err_kfree_skb:
+	dev_kfree_skb(np->rx_skbuff[i]);
+	np->rx_skbuff[i] = NULL;
+err_free_list:
+	free_list(dev);
+	return -ENOMEM;
 }
 
 static void rio_hw_init(struct net_device *dev)

2.51.0

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

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

From: Dmitry Safonov <[email protected]>

[ Upstream commit 21f4d45eba0b2dcae5dbc9e5e0ad08735c993f16 ]

Similarly to ipv4 tunnel, ipv6 version updates dev->needed_headroom, too. While ipv4 tunnel headroom adjustment growth was limited in commit 5ae1e9922bbd ("net: ip_tunnel: prevent perpetual headroom growth"), ipv6 tunnel yet increases the headroom without any ceiling.

Reflect ipv4 tunnel headroom adjustment limit on ipv6 version.

Credits to Francesco Ruggeri, who was originally debugging this issue and wrote local Arista-specific patch and a reproducer.

---
 include/net/ip_tunnels.h | 15 +++++++++++++++
 net/ipv4/ip_tunnel.c     | 14 --------------
 net/ipv6/ip6_tunnel.c    |  3 +--
 3 files changed, 16 insertions(+), 16 deletions(-)

index 3a04e2ccfb393..d2945ec5aba21 100644
@@ -454,6 +454,21 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
 					     gfp_t flags);
 
+static inline void ip_tunnel_adj_headroom(struct net_device *dev,
+					  unsigned int headroom)
+{
+	/* we must cap headroom to some upperlimit, else pskb_expand_head
+	 * will overflow header offsets in skb_headers_offset_update().
+	 */
+	const unsigned int max_allowed = 512;
+
+	if (headroom > max_allowed)
+		headroom = max_allowed;
+
+	if (headroom > READ_ONCE(dev->needed_headroom))
+		WRITE_ONCE(dev->needed_headroom, headroom);
+}
+
 int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask);
 
 static inline int iptunnel_pull_offloads(struct sk_buff *skb)

index 906c37c7f80d5..38cace81bfa2d 100644
@@ -560,20 +560,6 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	return 0;
 }
 
-static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom)
-{
-	/* we must cap headroom to some upperlimit, else pskb_expand_head
-	 * will overflow header offsets in skb_headers_offset_update().
-	 */
-	static const unsigned int max_allowed = 512;
-
-	if (headroom > max_allowed)
-		headroom = max_allowed;
-
-	if (headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, headroom);
-}
-
 void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		       u8 proto, int tunnel_hlen)
 {

index 5319093d9aa62..c79e6c032b300 100644
@@ -1201,8 +1201,7 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
 	 */
 	max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr)
 			+ dst->header_len + t->hlen;
-	if (max_headroom > READ_ONCE(dev->needed_headroom))
-		WRITE_ONCE(dev->needed_headroom, max_headroom);
+	ip_tunnel_adj_headroom(dev, max_headroom);
 
 	err = ip6_tnl_encap(skb, t, &proto, fl6);
 	if (err)

2.51.0

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

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

From: Raju Rangoju <[email protected]>

[ Upstream commit 2616222e423398bb374ffcb5d23dea4ba2c3e524 ]

During interface toggle operations (ifdown/ifup), the driver currently resets the local helper variable 'phy_link' to -1. This causes the link state machine to incorrectly interpret the state as a link change event, resulting in spurious "Link is down" messages being logged when the interface is brought back up.

Preserve the phy_link state across interface toggles to avoid treating the -1 sentinel value as a legitimate link state transition.

---
 drivers/net/ethernet/amd/xgbe/xgbe-drv.c  | 1 -
 drivers/net/ethernet/amd/xgbe/xgbe-mdio.c | 1 +
 2 files changed, 1 insertion(+), 1 deletion(-)

index de10e7e3a68d0..1fa7eb75d1a39 100644
@@ -1247,7 +1247,6 @@ static void xgbe_free_rx_data(struct xgbe_prv_data *pdata)
 
 static int xgbe_phy_reset(struct xgbe_prv_data *pdata)
 {
-	pdata->phy_link = -1;
 	pdata->phy_speed = SPEED_UNKNOWN;
 
 	return pdata->phy_if.phy_reset(pdata);

index 3819b23c927d5..6dd95e7d81e41 100644
@@ -1637,6 +1637,7 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata)
 		pdata->phy.duplex = DUPLEX_FULL;
 	}
 
+	pdata->phy_link = 0;
 	pdata->phy.link = 0;
 
 	pdata->phy.pause_autoneg = pdata->pause_autoneg;

2.51.0

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 295ce1eb36ae47dc862d6c8a1012618a25516208 ]

Neal reported that using neper tcp_stream with TCP_TX_DELAY set to 50ms would often lead to flows stuck in a small cwnd mode, regardless of the congestion control.

While tcp_stream sets TCP_TX_DELAY too late after the connect(), it highlighted two kernel bugs.

The following heuristic in tcp_tso_should_defer() seems wrong for large RTT:

delta = tp->tcp_clock_cache - head->tstamp;
/* If next ACK is likely to come too late (half srtt), do not defer */ if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0)

      goto send_now;

If next ACK is expected to come in more than 1 ms, we should not defer because we prefer a smooth ACK clocking.

While blamed commit was a step in the good direction, it was not generic enough.

Another patch fixing TCP_TX_DELAY for established flows will be proposed when net-next reopens.

---
 net/ipv4/tcp_output.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

index 4f203cbbc99b5..6492110e0c9b0 100644
@@ -1952,7 +1952,8 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 				 u32 max_segs)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	u32 send_win, cong_win, limit, in_flight;
+	u32 send_win, cong_win, limit, in_flight, threshold;
+	u64 srtt_in_ns, expected_ack, how_far_is_the_ack;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *head;
 	int win_divisor;

@@ -2014,9 +2015,19 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb,
 	head = tcp_rtx_queue_head(sk);
 	if (!head)
 		goto send_now;
-	delta = tp->tcp_clock_cache - head->tstamp;
-	/* If next ACK is likely to come too late (half srtt), do not defer */
-	if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0)
+
+	srtt_in_ns = (u64)(NSEC_PER_USEC >> 3) * tp->srtt_us;
+	/* When is the ACK expected ? */
+	expected_ack = head->tstamp + srtt_in_ns;
+	/* How far from now is the ACK expected ? */
+	how_far_is_the_ack = expected_ack - tp->tcp_clock_cache;
+
+	/* If next ACK is likely to come too late,
+	 * ie in more than min(1ms, half srtt), do not defer.
+	 */
+	threshold = min(srtt_in_ns >> 1, NSEC_PER_MSEC);
+
+	if ((s64)(how_far_is_the_ack - threshold) > 0)
 		goto send_now;
 
 	/* Ok, it looks like it is advisable to defer.

2.51.0

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

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

From: Alexey Simakov <[email protected]>

[ Upstream commit 0c3f2e62815a43628e748b1e4ad97a1c46cce703 ]

Some execution paths that jump to the fiber_setup_done label could leave the remote_adv and local_adv variables uninitialized and then use it.

Initialize this variables at the point of definition to avoid this.

---
 drivers/net/ethernet/broadcom/tg3.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

index 55aa877713339..3ea966d85ea38 100644
@@ -5827,7 +5827,7 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, bool force_reset)
 	u32 current_speed = SPEED_UNKNOWN;
 	u8 current_duplex = DUPLEX_UNKNOWN;
 	bool current_link_up = false;
-	u32 local_adv, remote_adv, sgsr;
+	u32 local_adv = 0, remote_adv = 0, sgsr;
 
 	if ((tg3_asic_rev(tp) == ASIC_REV_5719 ||
 	     tg3_asic_rev(tp) == ASIC_REV_5720) &&

@@ -5968,9 +5968,6 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, bool force_reset)
 		else
 			current_duplex = DUPLEX_HALF;
 
-		local_adv = 0;
-		remote_adv = 0;
-
 		if (bmcr & BMCR_ANENABLE) {
 			u32 common;
 

2.51.0

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

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

From: Sabrina Dubroca <[email protected]>

[ Upstream commit b6fe4c29bb51cf239ecf48eacf72b924565cb619 ]

When userspace wants to send a non-DATA record (via the TLS_SET_RECORD_TYPE cmsg), we need to send any pending data from a previous MSG_MORE send() as a separate DATA record. If that DATA record is encrypted asynchronously, tls_handle_open_record will return -EINPROGRESS. This is currently treated as an error by tls_process_cmsg, and it will skip setting record_type to the correct value, but the caller (tls_sw_sendmsg_locked) handles that return value correctly and proceeds with sending the new message with an incorrect record_type (DATA instead of whatever was requested in the cmsg).

Always set record_type before handling the open record. If tls_handle_open_record returns an error, record_type will be ignored. If it succeeds, whether with synchronous crypto (returning 0) or asynchronous (returning -EINPROGRESS), the caller will proceed correctly.

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

index cb51a2f46b11d..5bf809b090342 100644
@@ -181,12 +181,9 @@ int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg,
 			if (msg->msg_flags & MSG_MORE)
 				return -EINVAL;
 
-			rc = tls_handle_open_record(sk, msg->msg_flags);
-			if (rc)
-				return rc;
-
 			*record_type = *(unsigned char *)CMSG_DATA(cmsg);
-			rc = 0;
+
+			rc = tls_handle_open_record(sk, msg->msg_flags);
 			break;
 		default:
 			return -EINVAL;

2.51.0

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

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

From: Sabrina Dubroca <[email protected]>

[ Upstream commit 7f846c65ca11e63d2409868ff039081f80e42ae4 ]

With async crypto, we rely on tx_work to actually transmit records once encryption completes. But while send() is running, both the tx_lock and socket lock are held, so tx_work_handler cannot process the queue of encrypted records, and simply reschedules itself. During a large send(), this could last a long time, and use a lot of memory.

Transmit any pending encrypted records before restarting the main loop of tls_sw_sendmsg_locked.

---
 net/tls/tls_sw.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

index 8dabbbf521688..b175f0595a478 100644
@@ -1052,6 +1052,13 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 				else if (ret != -EAGAIN)
 					goto send_end;
 			}
+
+			/* Transmit if any encryptions have completed */
+			if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
+				cancel_delayed_work(&ctx->tx_work.work);
+				tls_tx_records(sk, msg->msg_flags);
+			}
+
 			continue;
 rollback_iter:
 			copied -= try_to_copy;

@@ -1106,6 +1113,12 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 					goto send_end;
 				}
 			}
+
+			/* Transmit if any encryptions have completed */
+			if (test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) {
+				cancel_delayed_work(&ctx->tx_work.work);
+				tls_tx_records(sk, msg->msg_flags);
+			}
 		}
 
 		continue;

2.51.0

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

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

From: Chen Yu <[email protected]>

[ Upstream commit d91cecc156620ec75d94c55369509c807c3d07e6 ]

After Commit 6e2df0581f56 ("sched: Fix pick_next_task() vs 'change' pattern race"), there is no need to expose newidle_balance() as it is only used within fair.c file. Change this function back to static again.

No functional change.

Stable-dep-of: 17e3e88ed0b6 ("sched/fair: Fix pelt lost idle time detection")

---
 kernel/sched/fair.c  | 6 ++++--
 kernel/sched/sched.h | 4 ----
 2 files changed, 4 insertions(+), 6 deletions(-)

index 2680216234ff2..db4a1da522e42 100644
@@ -3690,6 +3690,8 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
 	return cfs_rq->avg.load_avg;
 }
 
+static int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
+
 static inline unsigned long task_util(struct task_struct *p)
 {
 	return READ_ONCE(p->se.avg.util_avg);

@@ -3849,7 +3851,7 @@ attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags
 static inline void
 detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 
-static inline int idle_balance(struct rq *rq, struct rq_flags *rf)
+static inline int newidle_balance(struct rq *rq, struct rq_flags *rf)
 {
 	return 0;
 }

@@ -9898,7 +9900,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
-int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
+static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;

index b8a3db59e3267..46e6f4e905dd6 100644
@@ -1464,14 +1464,10 @@ static inline void unregister_sched_domain_sysctl(void)
 }
 #endif
 
-extern int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
-
 #else
 
 static inline void sched_ttwu_pending(void) { }
 
-static inline int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { return 0; }
-
 #endif /* CONFIG_SMP */
 
 #include "stats.h"

2.51.0

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

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

From: Barry Song <[email protected]>

[ Upstream commit 5b78f2dc315354c05300795064f587366a02c6ff ]

idle_balance() has been renamed to newidle_balance(). To differentiate with nohz_idle_balance, it seems refining the comment will be helpful for the readers of the code.

Stable-dep-of: 17e3e88ed0b6 ("sched/fair: Fix pelt lost idle time detection")

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

index db4a1da522e42..1d82b9cc9eb77 100644
@@ -9897,7 +9897,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
 /*
- * idle_balance is called by schedule() if this_cpu is about to become
+ * newidle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
 static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)

2.51.0

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

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

From: Ingo Molnar <[email protected]>

[ Upstream commit 7d058285cd77cc1411c91efd1b1673530bb1bee8 ]

Standardize scheduler load-balancing function names on the sched_balance_() prefix.

Stable-dep-of: 17e3e88ed0b6 ("sched/fair: Fix pelt lost idle time detection")

---
 kernel/sched/fair.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

index 1d82b9cc9eb77..62c0348ef556a 100644
@@ -3690,7 +3690,7 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
 	return cfs_rq->avg.load_avg;
 }
 
-static int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
+static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf);
 
 static inline unsigned long task_util(struct task_struct *p)
 {

@@ -3851,7 +3851,7 @@ attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags
 static inline void
 detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 
-static inline int newidle_balance(struct rq *rq, struct rq_flags *rf)
+static inline int sched_balance_newidle(struct rq *rq, struct rq_flags *rf)
 {
 	return 0;
 }

@@ -6690,7 +6690,7 @@ balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	if (rq->nr_running)
 		return 1;
 
-	return newidle_balance(rq, rf) != 0;
+	return sched_balance_newidle(rq, rf) != 0;
 }
 #endif /* CONFIG_SMP */
 

@@ -6981,10 +6981,10 @@ done: __maybe_unused;
 	if (!rf)
 		return NULL;
 
-	new_tasks = newidle_balance(rq, rf);
+	new_tasks = sched_balance_newidle(rq, rf);
 
 	/*
-	 * Because newidle_balance() releases (and re-acquires) rq->lock, it is
+	 * Because sched_balance_newidle() releases (and re-acquires) rq->lock, it is
 	 * possible for any higher priority task to appear. In that case we
 	 * must re-start the pick_next_entity() loop.
 	 */

@@ -9182,7 +9182,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 	ld_moved = 0;
 
 	/*
-	 * newidle_balance() disregards balance intervals, so we could
+	 * sched_balance_newidle() disregards balance intervals, so we could
 	 * repeatedly reach this code, which would lead to balance_interval
 	 * skyrocketting in a short amount of time. Skip the balance_interval
 	 * increase logic to avoid that.

@@ -9897,10 +9897,10 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
 /*
- * newidle_balance is called by schedule() if this_cpu is about to become
+ * sched_balance_newidle is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
-static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
+static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;

2.51.0

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

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

From: Vincent Guittot <[email protected]>

[ Upstream commit 17e3e88ed0b6318fde0d1c14df1a804711cab1b5 ]

The check for some lost idle pelt time should be always done when pick_next_task_fair() fails to pick a task and not only when we call it from the fair fast-path.

The case happens when the last running task on rq is a RT or DL task. When the latter goes to sleep and the /Sum of util_sum of the rq is at the max value, we don't account the lost of idle time whereas we should.

---
 kernel/sched/fair.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

index 62c0348ef556a..5e8f2167d8caa 100644
@@ -6978,21 +6978,21 @@ done: __maybe_unused;
 	return p;
 
 idle:
-	if (!rf)
-		return NULL;
-
-	new_tasks = sched_balance_newidle(rq, rf);
+	if (rf) {
+		new_tasks = sched_balance_newidle(rq, rf);
 
-	/*
-	 * Because sched_balance_newidle() releases (and re-acquires) rq->lock, it is
-	 * possible for any higher priority task to appear. In that case we
-	 * must re-start the pick_next_entity() loop.
-	 */
-	if (new_tasks < 0)
-		return RETRY_TASK;
+		/*
+		 * Because sched_balance_newidle() releases (and re-acquires)
+		 * rq->lock, it is possible for any higher priority task to
+		 * appear. In that case we must re-start the pick_next_entity()
+		 * loop.
+		 */
+		if (new_tasks < 0)
+			return RETRY_TASK;
 
-	if (new_tasks > 0)
-		goto again;
+		if (new_tasks > 0)
+			goto again;
+	}
 
 	/*
 	 * rq is about to be idle, check if we need to update the

2.51.0

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

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

From: Randy Dunlap <[email protected]>

[ Upstream commit d41f68dff783d181a8fd462e612bda0fbab7f735 ]

Fix spelling of CIP_NO_HEADER to prevent a kernel-doc warning.

Warning: amdtp-stream.h:57 Enum value 'CIP_NO_HEADER' not described in enum 'cip_flags'
Warning: amdtp-stream.h:57 Excess enum value '%CIP_NO_HEADERS' description in 'cip_flags'

---
 sound/firewire/amdtp-stream.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index bbbca964b9b46..f1933f7b9f1bf 100644
@@ -32,7 +32,7 @@
  *	allows 5 times as large as IEC 61883-6 defines.
  * @CIP_HEADER_WITHOUT_EOH: Only for in-stream. CIP Header doesn't include
  *	valid EOH.
- * @CIP_NO_HEADERS: a lack of headers in packets
+ * @CIP_NO_HEADER: a lack of headers in packets
  * @CIP_UNALIGHED_DBC: Only for in-stream. The value of dbc is not alighed to
  *	the value of current SYT_INTERVAL; e.g. initial value is not zero.
  */

2.51.0

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

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

From: Viacheslav Dubeyko <[email protected]>

commit 42520df65bf67189541a425f7d36b0b3e7bd7844 upstream.

The hfsplus_strcasecmp() logic can trigger the issue:

[  117.317703][ T9855] ==================================================================
[  117.318353][ T9855] BUG: KASAN: slab-out-of-bounds in hfsplus_strcasecmp+0x1bc/0x490
[  117.318991][ T9855] Read of size 2 at addr ffff88802160f40c by task repro/9855
[  117.319577][ T9855]
[  117.319773][ T9855] CPU: 0 UID: 0 PID: 9855 Comm: repro Not tainted 6.17.0-rc6 #33 PREEMPT(full)
[  117.319780][ T9855] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[  117.319783][ T9855] Call Trace:
[  117.319785][ T9855]  <TASK>
[  117.319788][ T9855]  dump_stack_lvl+0x1c1/0x2a0
[  117.319795][ T9855]  ? __virt_addr_valid+0x1c8/0x5c0
[  117.319803][ T9855]  ? __pfx_dump_stack_lvl+0x10/0x10
[  117.319808][ T9855]  ? rcu_is_watching+0x15/0xb0
[  117.319816][ T9855]  ? lock_release+0x4b/0x3e0
[  117.319821][ T9855]  ? __kasan_check_byte+0x12/0x40
[  117.319828][ T9855]  ? __virt_addr_valid+0x1c8/0x5c0
[  117.319835][ T9855]  ? __virt_addr_valid+0x4a5/0x5c0
[  117.319842][ T9855]  print_report+0x17e/0x7e0
[  117.319848][ T9855]  ? __virt_addr_valid+0x1c8/0x5c0
[  117.319855][ T9855]  ? __virt_addr_valid+0x4a5/0x5c0
[  117.319862][ T9855]  ? __phys_addr+0xd3/0x180
[  117.319869][ T9855]  ? hfsplus_strcasecmp+0x1bc/0x490
[  117.319876][ T9855]  kasan_report+0x147/0x180
[  117.319882][ T9855]  ? hfsplus_strcasecmp+0x1bc/0x490
[  117.319891][ T9855]  hfsplus_strcasecmp+0x1bc/0x490
[  117.319900][ T9855]  ? __pfx_hfsplus_cat_case_cmp_key+0x10/0x10
[  117.319906][ T9855]  hfs_find_rec_by_key+0xa9/0x1e0
[  117.319913][ T9855]  __hfsplus_brec_find+0x18e/0x470
[  117.319920][ T9855]  ? __pfx_hfsplus_bnode_find+0x10/0x10
[  117.319926][ T9855]  ? __pfx_hfs_find_rec_by_key+0x10/0x10
[  117.319933][ T9855]  ? __pfx___hfsplus_brec_find+0x10/0x10
[  117.319942][ T9855]  hfsplus_brec_find+0x28f/0x510
[  117.319949][ T9855]  ? __pfx_hfs_find_rec_by_key+0x10/0x10
[  117.319956][ T9855]  ? __pfx_hfsplus_brec_find+0x10/0x10
[  117.319963][ T9855]  ? __kmalloc_noprof+0x2a9/0x510
[  117.319969][ T9855]  ? hfsplus_find_init+0x8c/0x1d0
[  117.319976][ T9855]  hfsplus_brec_read+0x2b/0x120
[  117.319983][ T9855]  hfsplus_lookup+0x2aa/0x890
[  117.319990][ T9855]  ? __pfx_hfsplus_lookup+0x10/0x10
[  117.320003][ T9855]  ? d_alloc_parallel+0x2f0/0x15e0
[  117.320008][ T9855]  ? __lock_acquire+0xaec/0xd80
[  117.320013][ T9855]  ? __pfx_d_alloc_parallel+0x10/0x10
[  117.320019][ T9855]  ? __raw_spin_lock_init+0x45/0x100
[  117.320026][ T9855]  ? __init_waitqueue_head+0xa9/0x150
[  117.320034][ T9855]  __lookup_slow+0x297/0x3d0
[  117.320039][ T9855]  ? __pfx___lookup_slow+0x10/0x10
[  117.320045][ T9855]  ? down_read+0x1ad/0x2e0
[  117.320055][ T9855]  lookup_slow+0x53/0x70
[  117.320065][ T9855]  walk_component+0x2f0/0x430
[  117.320073][ T9855]  path_lookupat+0x169/0x440
[  117.320081][ T9855]  filename_lookup+0x212/0x590
[  117.320089][ T9855]  ? __pfx_filename_lookup+0x10/0x10
[  117.320098][ T9855]  ? strncpy_from_user+0x150/0x290
[  117.320105][ T9855]  ? getname_flags+0x1e5/0x540
[  117.320112][ T9855]  user_path_at+0x3a/0x60
[  117.320117][ T9855]  __x64_sys_umount+0xee/0x160
[  117.320123][ T9855]  ? __pfx___x64_sys_umount+0x10/0x10
[  117.320129][ T9855]  ? do_syscall_64+0xb7/0x3a0
[  117.320135][ T9855]  ? entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  117.320141][ T9855]  ? entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  117.320145][ T9855]  do_syscall_64+0xf3/0x3a0
[  117.320150][ T9855]  ? exc_page_fault+0x9f/0xf0
[  117.320154][ T9855]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  117.320158][ T9855] RIP: 0033:0x7f7dd7908b07
[  117.320163][ T9855] Code: 23 0d 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 31 f6 e9 09 00 00 00 66 0f 1f 84 00 00 08
[  117.320167][ T9855] RSP: 002b:00007ffd5ebd9698 EFLAGS: 00000202 ORIG_RAX: 00000000000000a6
[  117.320172][ T9855] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f7dd7908b07
[  117.320176][ T9855] RDX: 0000000000000009 RSI: 0000000000000009 RDI: 00007ffd5ebd9740
[  117.320179][ T9855] RBP: 00007ffd5ebda780 R08: 0000000000000005 R09: 00007ffd5ebd9530
[  117.320181][ T9855] R10: 00007f7dd799bfc0 R11: 0000000000000202 R12: 000055e2008b32d0
[  117.320184][ T9855] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
[  117.320189][ T9855]  </TASK>
[  117.320190][ T9855]
[  117.351311][ T9855] Allocated by task 9855:
[  117.351683][ T9855]  kasan_save_track+0x3e/0x80
[  117.352093][ T9855]  __kasan_kmalloc+0x8d/0xa0
[  117.352490][ T9855]  __kmalloc_noprof+0x288/0x510
[  117.352914][ T9855]  hfsplus_find_init+0x8c/0x1d0
[  117.353342][ T9855]  hfsplus_lookup+0x19c/0x890
[  117.353747][ T9855]  __lookup_slow+0x297/0x3d0
[  117.354148][ T9855]  lookup_slow+0x53/0x70
[  117.354514][ T9855]  walk_component+0x2f0/0x430
[  117.354921][ T9855]  path_lookupat+0x169/0x440
[  117.355325][ T9855]  filename_lookup+0x212/0x590
[  117.355740][ T9855]  user_path_at+0x3a/0x60
[  117.356115][ T9855]  __x64_sys_umount+0xee/0x160
[  117.356529][ T9855]  do_syscall_64+0xf3/0x3a0
[  117.356920][ T9855]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  117.357429][ T9855]
[  117.357636][ T9855] The buggy address belongs to the object at ffff88802160f000
[  117.357636][ T9855]  which belongs to the cache kmalloc-2k of size 2048
[  117.358827][ T9855] The buggy address is located 0 bytes to the right of
[  117.358827][ T9855]  allocated 1036-byte region [ffff88802160f000, ffff88802160f40c)
[  117.360061][ T9855]
[  117.360266][ T9855] The buggy address belongs to the physical page:
[  117.360813][ T9855] page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x21608
[  117.361562][ T9855] head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
[  117.362285][ T9855] flags: 0xfff00000000040(head|node=0|zone=1|lastcpupid=0x7ff)
[  117.362929][ T9855] page_type: f5(slab)
[  117.363282][ T9855] raw: 00fff00000000040 ffff88801a842f00 ffffea0000932000 dead000000000002
[  117.364015][ T9855] raw: 0000000000000000 0000000080080008 00000000f5000000 0000000000000000
[  117.364750][ T9855] head: 00fff00000000040 ffff88801a842f00 ffffea0000932000 dead000000000002
[  117.365491][ T9855] head: 0000000000000000 0000000080080008 00000000f5000000 0000000000000000
[  117.366232][ T9855] head: 00fff00000000003 ffffea0000858201 00000000ffffffff 00000000ffffffff
[  117.366968][ T9855] head: ffffffffffffffff 0000000000000000 00000000ffffffff 0000000000000008
[  117.367711][ T9855] page dumped because: kasan: bad access detected
[  117.368259][ T9855] page_owner tracks the page as allocated
[  117.368745][ T9855] page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN1
[  117.370541][ T9855]  post_alloc_hook+0x240/0x2a0
[  117.370954][ T9855]  get_page_from_freelist+0x2101/0x21e0
[  117.371435][ T9855]  __alloc_frozen_pages_noprof+0x274/0x380
[  117.371935][ T9855]  alloc_pages_mpol+0x241/0x4b0
[  117.372360][ T9855]  allocate_slab+0x8d/0x380
[  117.372752][ T9855]  ___slab_alloc+0xbe3/0x1400
[  117.373159][ T9855]  __kmalloc_cache_noprof+0x296/0x3d0
[  117.373621][ T9855]  nexthop_net_init+0x75/0x100
[  117.374038][ T9855]  ops_init+0x35c/0x5c0
[  117.374400][ T9855]  setup_net+0x10c/0x320
[  117.374768][ T9855]  copy_net_ns+0x31b/0x4d0
[  117.375156][ T9855]  create_new_namespaces+0x3f3/0x720
[  117.375613][ T9855]  unshare_nsproxy_namespaces+0x11c/0x170
[  117.376094][ T9855]  ksys_unshare+0x4ca/0x8d0
[  117.376477][ T9855]  __x64_sys_unshare+0x38/0x50
[  117.376879][ T9855]  do_syscall_64+0xf3/0x3a0
[  117.377265][ T9855] page last free pid 9110 tgid 9110 stack trace:
[  117.377795][ T9855]  __free_frozen_pages+0xbeb/0xd50
[  117.378229][ T9855]  __put_partials+0x152/0x1a0
[  117.378625][ T9855]  put_cpu_partial+0x17c/0x250
[  117.379026][ T9855]  __slab_free+0x2d4/0x3c0
[  117.379404][ T9855]  qlist_free_all+0x97/0x140
[  117.379790][ T9855]  kasan_quarantine_reduce+0x148/0x160
[  117.380250][ T9855]  __kasan_slab_alloc+0x22/0x80
[  117.380662][ T9855]  __kmalloc_noprof+0x232/0x510
[  117.381074][ T9855]  tomoyo_supervisor+0xc0a/0x1360
[  117.381498][ T9855]  tomoyo_env_perm+0x149/0x1e0
[  117.381903][ T9855]  tomoyo_find_next_domain+0x15ad/0x1b90
[  117.382378][ T9855]  tomoyo_bprm_check_security+0x11c/0x180
[  117.382859][ T9855]  security_bprm_check+0x89/0x280
[  117.383289][ T9855]  bprm_execve+0x8f1/0x14a0
[  117.383673][ T9855]  do_execveat_common+0x528/0x6b0
[  117.384103][ T9855]  __x64_sys_execve+0x94/0xb0
[  117.384500][ T9855]
[  117.384706][ T9855] Memory state around the buggy address:
[  117.385179][ T9855]  ffff88802160f300: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  117.385854][ T9855]  ffff88802160f380: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[  117.386534][ T9855] >ffff88802160f400: 00 04 fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  117.387204][ T9855]                       ^
[  117.387566][ T9855]  ffff88802160f480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  117.388243][ T9855]  ffff88802160f500: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  117.388918][ T9855] ==================================================================

The issue takes place if the length field of struct hfsplus_unistr is bigger than HFSPLUS_MAX_STRLEN. The patch simply checks the length of comparing strings. And if the strings' length is bigger than HFSPLUS_MAX_STRLEN, then it is corrected to this value.

v2
The string length correction has been added for hfsplus_strcmp().

---
 fs/hfsplus/unicode.c |   24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

@@ -40,6 +40,18 @@ int hfsplus_strcasecmp(const struct hfsp
 	p1 = s1->unicode;
 	p2 = s2->unicode;
 
+	if (len1 > HFSPLUS_MAX_STRLEN) {
+		len1 = HFSPLUS_MAX_STRLEN;
+		pr_err("invalid length %u has been corrected to %d\n",
+			be16_to_cpu(s1->length), len1);
+	}
+
+	if (len2 > HFSPLUS_MAX_STRLEN) {
+		len2 = HFSPLUS_MAX_STRLEN;
+		pr_err("invalid length %u has been corrected to %d\n",
+			be16_to_cpu(s2->length), len2);
+	}
+
 	while (1) {
 		c1 = c2 = 0;
 

@@ -74,6 +86,18 @@ int hfsplus_strcmp(const struct hfsplus_
 	p1 = s1->unicode;
 	p2 = s2->unicode;
 
+	if (len1 > HFSPLUS_MAX_STRLEN) {
+		len1 = HFSPLUS_MAX_STRLEN;
+		pr_err("invalid length %u has been corrected to %d\n",
+			be16_to_cpu(s1->length), len1);
+	}
+
+	if (len2 > HFSPLUS_MAX_STRLEN) {
+		len2 = HFSPLUS_MAX_STRLEN;
+		pr_err("invalid length %u has been corrected to %d\n",
+			be16_to_cpu(s2->length), len2);
+	}
+
 	for (len = min(len1, len2); len > 0; len--) {
 		c1 = be16_to_cpu(*p1);
 		c2 = be16_to_cpu(*p2);

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

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

From: Xichao Zhao <[email protected]>

[ Upstream commit 5e088248375d171b80c643051e77ade6b97bc386 ]

In the setup_arg_pages(), ret is declared as an unsigned long. The ret might take a negative value. Therefore, its type should be changed to int.

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

index 5dffc67745c80..5aa0d9ec7f21b 100644
@@ -701,7 +701,7 @@ int setup_arg_pages(struct linux_binprm *bprm,
 		    unsigned long stack_top,
 		    int executable_stack)
 {
-	unsigned long ret;
+	int ret;
 	unsigned long stack_shift;
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma = bprm->vma;

2.51.0

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

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

From: Viacheslav Dubeyko <[email protected]>

[ Upstream commit 18b07c44f245beb03588b00b212b38fce9af7cc9 ]

Currently, hfs_brec_remove() executes moving records towards the location of deleted record and it updates offsets of moved records. However, the hfs_brec_remove() logic ignores the "mess" of b-tree node's free space and it doesn't touch the offsets out of records number. Potentially, it could confuse fsck or driver logic or to be a reason of potential corruption cases.

This patch reworks the logic of hfs_brec_remove() by means of clearing freed space of b-tree node after the records moving. And it clear the last offset that keeping old location of free space because now the offset before this one is keeping the actual offset to the free space after the record deletion.

---
 fs/hfs/brec.c | 27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

index 896396554bcc1..b01db1fae147c 100644
@@ -179,6 +179,7 @@ int hfs_brec_remove(struct hfs_find_data *fd)
 	struct hfs_btree *tree;
 	struct hfs_bnode *node, *parent;
 	int end_off, rec_off, data_off, size;
+	int src, dst, len;
 
 	tree = fd->tree;
 	node = fd->bnode;

@@ -208,10 +209,14 @@ int hfs_brec_remove(struct hfs_find_data *fd)
 	}
 	hfs_bnode_write_u16(node, offsetof(struct hfs_bnode_desc, num_recs), node->num_recs);
 
-	if (rec_off == end_off)
-		goto skip;
 	size = fd->keylength + fd->entrylength;
 
+	if (rec_off == end_off) {
+		src = fd->keyoffset;
+		hfs_bnode_clear(node, src, size);
+		goto skip;
+	}
+
 	do {
 		data_off = hfs_bnode_read_u16(node, rec_off);
 		hfs_bnode_write_u16(node, rec_off + 2, data_off - size);

@@ -219,9 +224,23 @@ int hfs_brec_remove(struct hfs_find_data *fd)
 	} while (rec_off >= end_off);
 
 	/* fill hole */
-	hfs_bnode_move(node, fd->keyoffset, fd->keyoffset + size,
-		       data_off - fd->keyoffset - size);
+	dst = fd->keyoffset;
+	src = fd->keyoffset + size;
+	len = data_off - src;
+
+	hfs_bnode_move(node, dst, src, len);
+
+	src = dst + len;
+	len = data_off - src;
+
+	hfs_bnode_clear(node, src, len);
+
 skip:
+	/*
+	 * Remove the obsolete offset to free space.
+	 */
+	hfs_bnode_write_u16(node, end_off, 0);
+
 	hfs_bnode_dump(node);
 	if (!fd->record)
 		hfs_brec_update_parent(fd);

2.51.0

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

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

From: Viacheslav Dubeyko <[email protected]>

[ Upstream commit c62663a986acee7c4485c1fa9de5fc40194b6290 ]

Potenatially, __hfs_ext_read_extent() could operate by not initialized values of fd->key after hfs_brec_find() call:

static inline int __hfs_ext_read_extent(struct hfs_find_data *fd, struct hfs_extent *extent,

                                        u32 cnid, u32 block, u8 type)
{
        int res;

        hfs_ext_build_key(fd->search_key, cnid, block, type);
        fd->key->ext.FNum = 0;
        res = hfs_brec_find(fd);
        if (res && res != -ENOENT)
                return res;
        if (fd->key->ext.FNum != fd->search_key->ext.FNum ||
            fd->key->ext.FkType != fd->search_key->ext.FkType)
                return -ENOENT;
        if (fd->entrylength != sizeof(hfs_extent_rec))
                return -EIO;
        hfs_bnode_read(fd->bnode, extent, fd->entryoffset, sizeof(hfs_extent_rec));
        return 0;
}

This patch changes kmalloc() on kzalloc() in hfs_find_init() and intializes fd->record, fd->keyoffset, fd->keylength, fd->entryoffset, fd->entrylength for the case if hfs_brec_find() has been found nothing in the b-tree node.

---
 fs/hfs/bfind.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

index ef9498a6e88ac..6d37b4c759034 100644
@@ -18,7 +18,7 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd)
 
 	fd->tree = tree;
 	fd->bnode = NULL;
-	ptr = kmalloc(tree->max_key_len * 2 + 4, GFP_KERNEL);
+	ptr = kzalloc(tree->max_key_len * 2 + 4, GFP_KERNEL);
 	if (!ptr)
 		return -ENOMEM;
 	fd->search_key = ptr;

@@ -112,6 +112,12 @@ int hfs_brec_find(struct hfs_find_data *fd)
 	__be32 data;
 	int height, res;
 
+	fd->record = -1;
+	fd->keyoffset = -1;
+	fd->keylength = -1;
+	fd->entryoffset = -1;
+	fd->entrylength = -1;
+
 	tree = fd->tree;
 	if (fd->bnode)
 		hfs_bnode_put(fd->bnode);

2.51.0

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

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

From: Viacheslav Dubeyko <[email protected]>

[ Upstream commit 4840ceadef4290c56cc422f0fc697655f3cbf070 ]

The syzbot reported issue in __hfsplus_ext_cache_extent():

[   70.194323][ T9350] BUG: KMSAN: uninit-value in __hfsplus_ext_cache_extent+0x7d0/0x990
[   70.195022][ T9350]  __hfsplus_ext_cache_extent+0x7d0/0x990
[   70.195530][ T9350]  hfsplus_file_extend+0x74f/0x1cf0
[   70.195998][ T9350]  hfsplus_get_block+0xe16/0x17b0
[   70.196458][ T9350]  __block_write_begin_int+0x962/0x2ce0
[   70.196959][ T9350]  cont_write_begin+0x1000/0x1950
[   70.197416][ T9350]  hfsplus_write_begin+0x85/0x130
[   70.197873][ T9350]  generic_perform_write+0x3e8/0x1060
[   70.198374][ T9350]  __generic_file_write_iter+0x215/0x460
[   70.198892][ T9350]  generic_file_write_iter+0x109/0x5e0
[   70.199393][ T9350]  vfs_write+0xb0f/0x14e0
[   70.199771][ T9350]  ksys_write+0x23e/0x490
[   70.200149][ T9350]  __x64_sys_write+0x97/0xf0
[   70.200570][ T9350]  x64_sys_call+0x3015/0x3cf0
[   70.201065][ T9350]  do_syscall_64+0xd9/0x1d0
[   70.201506][ T9350]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[   70.202054][ T9350]
[   70.202279][ T9350] Uninit was created at:
[   70.202693][ T9350]  __kmalloc_noprof+0x621/0xf80
[   70.203149][ T9350]  hfsplus_find_init+0x8d/0x1d0
[   70.203602][ T9350]  hfsplus_file_extend+0x6ca/0x1cf0
[   70.204087][ T9350]  hfsplus_get_block+0xe16/0x17b0
[   70.204561][ T9350]  __block_write_begin_int+0x962/0x2ce0
[   70.205074][ T9350]  cont_write_begin+0x1000/0x1950
[   70.205547][ T9350]  hfsplus_write_begin+0x85/0x130
[   70.206017][ T9350]  generic_perform_write+0x3e8/0x1060
[   70.206519][ T9350]  __generic_file_write_iter+0x215/0x460
[   70.207042][ T9350]  generic_file_write_iter+0x109/0x5e0
[   70.207552][ T9350]  vfs_write+0xb0f/0x14e0
[   70.207961][ T9350]  ksys_write+0x23e/0x490
[   70.208375][ T9350]  __x64_sys_write+0x97/0xf0
[   70.208810][ T9350]  x64_sys_call+0x3015/0x3cf0
[   70.209255][ T9350]  do_syscall_64+0xd9/0x1d0
[   70.209680][ T9350]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[   70.210230][ T9350]
[   70.210454][ T9350] CPU: 2 UID: 0 PID: 9350 Comm: repro Not tainted 6.12.0-rc5 #5
[   70.211174][ T9350] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   70.212115][ T9350] =====================================================
[   70.212734][ T9350] Disabling lock debugging due to kernel taint
[   70.213284][ T9350] Kernel panic - not syncing: kmsan.panic set ...
[   70.213858][ T9350] CPU: 2 UID: 0 PID: 9350 Comm: repro Tainted: G    B              6.12.0-rc5 #5
[   70.214679][ T9350] Tainted: [B]=BAD_PAGE
[   70.215057][ T9350] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   70.215999][ T9350] Call Trace:
[   70.216309][ T9350]  <TASK>
[   70.216585][ T9350]  dump_stack_lvl+0x1fd/0x2b0
[   70.217025][ T9350]  dump_stack+0x1e/0x30
[   70.217421][ T9350]  panic+0x502/0xca0
[   70.217803][ T9350]  ? kmsan_get_metadata+0x13e/0x1c0

[   70.218294][ Message fromT sy9350]  kmsan_report+0x296/slogd@syzkaller 0x2aat Aug 18 22:11:058 ...
 kernel
:[   70.213284][ T9350] Kernel panic - not syncing: kmsan.panic [   70.220179][ T9350]  ? kmsan_get_metadata+0x13e/0x1c0
set ...
[   70.221254][ T9350]  ? __msan_warning+0x96/0x120
[   70.222066][ T9350]  ? __hfsplus_ext_cache_extent+0x7d0/0x990
[   70.223023][ T9350]  ? hfsplus_file_extend+0x74f/0x1cf0
[   70.224120][ T9350]  ? hfsplus_get_block+0xe16/0x17b0
[   70.224946][ T9350]  ? __block_write_begin_int+0x962/0x2ce0
[   70.225756][ T9350]  ? cont_write_begin+0x1000/0x1950
[   70.226337][ T9350]  ? hfsplus_write_begin+0x85/0x130
[   70.226852][ T9350]  ? generic_perform_write+0x3e8/0x1060
[   70.227405][ T9350]  ? __generic_file_write_iter+0x215/0x460
[   70.227979][ T9350]  ? generic_file_write_iter+0x109/0x5e0
[   70.228540][ T9350]  ? vfs_write+0xb0f/0x14e0
[   70.228997][ T9350]  ? ksys_write+0x23e/0x490
[   70.229458][ T9350]  ? __x64_sys_write+0x97/0xf0
[   70.229939][ T9350]  ? x64_sys_call+0x3015/0x3cf0
[   70.230432][ T9350]  ? do_syscall_64+0xd9/0x1d0
[   70.230941][ T9350]  ? entry_SYSCALL_64_after_hwframe+0x77/0x7f
[   70.231926][ T9350]  ? kmsan_get_metadata+0x13e/0x1c0
[   70.232738][ T9350]  ? kmsan_internal_set_shadow_origin+0x77/0x110
[   70.233711][ T9350]  ? kmsan_get_metadata+0x13e/0x1c0
[   70.234516][ T9350]  ? kmsan_get_shadow_origin_ptr+0x4a/0xb0
[   70.235398][ T9350]  ? __msan_metadata_ptr_for_load_4+0x24/0x40
[   70.236323][ T9350]  ? hfsplus_brec_find+0x218/0x9f0
[   70.237090][ T9350]  ? __pfx_hfs_find_rec_by_key+0x10/0x10
[   70.237938][ T9350]  ? __msan_instrument_asm_store+0xbf/0xf0
[   70.238827][ T9350]  ? __msan_metadata_ptr_for_store_4+0x27/0x40
[   70.239772][ T9350]  ? __hfsplus_ext_write_extent+0x536/0x620
[   70.240666][ T9350]  ? kmsan_get_metadata+0x13e/0x1c0
[   70.241175][ T9350]  __msan_warning+0x96/0x120
[   70.241645][ T9350]  __hfsplus_ext_cache_extent+0x7d0/0x990
[   70.242223][ T9350]  hfsplus_file_extend+0x74f/0x1cf0
[   70.242748][ T9350]  hfsplus_get_block+0xe16/0x17b0
[   70.243255][ T9350]  ? kmsan_internal_set_shadow_origin+0x77/0x110
[   70.243878][ T9350]  ? kmsan_get_metadata+0x13e/0x1c0
[   70.244400][ T9350]  ? kmsan_get_shadow_origin_ptr+0x4a/0xb0
[   70.244967][ T9350]  __block_write_begin_int+0x962/0x2ce0
[   70.245531][ T9350]  ? __pfx_hfsplus_get_block+0x10/0x10
[   70.246079][ T9350]  cont_write_begin+0x1000/0x1950
[   70.246598][ T9350]  hfsplus_write_begin+0x85/0x130
[   70.247105][ T9350]  ? __pfx_hfsplus_get_block+0x10/0x10
[   70.247650][ T9350]  ? __pfx_hfsplus_write_begin+0x10/0x10
[   70.248211][ T9350]  generic_perform_write+0x3e8/0x1060
[   70.248752][ T9350]  __generic_file_write_iter+0x215/0x460
[   70.249314][ T9350]  generic_file_write_iter+0x109/0x5e0
[   70.249856][ T9350]  ? kmsan_internal_set_shadow_origin+0x77/0x110
[   70.250487][ T9350]  vfs_write+0xb0f/0x14e0
[   70.250930][ T9350]  ? __pfx_generic_file_write_iter+0x10/0x10
[   70.251530][ T9350]  ksys_write+0x23e/0x490
[   70.251974][ T9350]  __x64_sys_write+0x97/0xf0
[   70.252450][ T9350]  x64_sys_call+0x3015/0x3cf0
[   70.252924][ T9350]  do_syscall_64+0xd9/0x1d0
[   70.253384][ T9350]  ? irqentry_exit+0x16/0x60
[   70.253844][ T9350]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[   70.254430][ T9350] RIP: 0033:0x7f7a92adffc9
[   70.254873][ T9350] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 48
[   70.256674][ T9350] RSP: 002b:00007fff0bca3188 EFLAGS: 00000202 ORIG_RAX: 0000000000000001
[   70.257485][ T9350] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f7a92adffc9
[   70.258246][ T9350] RDX: 000000000208e24b RSI: 0000000020000100 RDI: 0000000000000004
[   70.258998][ T9350] RBP: 00007fff0bca31a0 R08: 00007fff0bca31a0 R09: 00007fff0bca31a0
[   70.259769][ T9350] R10: 0000000000000000 R11: 0000000000000202 R12: 000055e0d75f8250
[   70.260520][ T9350] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
[   70.261286][ T9350]  </TASK>
[   70.262026][ T9350] Kernel Offset: disabled

(gdb) l *__hfsplus_ext_cache_extent+0x7d0
0xffffffff8318aef0 is in __hfsplus_ext_cache_extent (fs/hfsplus/extents.c:168).
163 fd->key->ext.cnid = 0;
164 res = hfs_brec_find(fd, hfs_find_rec_by_key);
165 if (res && res != -ENOENT)
166 return res;
167 if (fd->key->ext.cnid != fd->search_key->ext.cnid ||
168 fd->key->ext.fork_type != fd->search_key->ext.fork_type)
169 return -ENOENT;
170 if (fd->entrylength != sizeof(hfsplus_extent_rec))
171 return -EIO;
172 hfs_bnode_read(fd->bnode, extent, fd->entryoffset,

The __hfsplus_ext_cache_extent() calls __hfsplus_ext_read_extent():

res = __hfsplus_ext_read_extent(fd, hip->cached_extents, inode->i_ino,

				block, HFSPLUS_IS_RSRC(inode) ?
					HFSPLUS_TYPE_RSRC :
					HFSPLUS_TYPE_DATA);

And if inode->i_ino could be equal to zero or any non-available CNID, then hfs_brec_find() could not find the record in the tree. As a result, fd->key could be compared with fd->search_key. But hfsplus_find_init() uses kmalloc() for fd->key and fd->search_key allocation:

int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd) {
<skipped>

        ptr = kmalloc(tree->max_key_len * 2 + 4, GFP_KERNEL);
        if (!ptr)
                return -ENOMEM;
        fd->search_key = ptr;
        fd->key = ptr + tree->max_key_len + 2;

<skipped>
}

Finally, fd->key is still not initialized if hfs_brec_find() has found nothing.

This patch changes kmalloc() on kzalloc() in hfs_find_init() and intializes fd->record, fd->keyoffset, fd->keylength, fd->entryoffset, fd->entrylength for the case if hfs_brec_find() has been found nothing in the b-tree node.

---
 fs/hfsplus/bfind.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

index 901e83d65d202..26ebac4c60424 100644
@@ -18,7 +18,7 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd)
 
 	fd->tree = tree;
 	fd->bnode = NULL;
-	ptr = kmalloc(tree->max_key_len * 2 + 4, GFP_KERNEL);
+	ptr = kzalloc(tree->max_key_len * 2 + 4, GFP_KERNEL);
 	if (!ptr)
 		return -ENOMEM;
 	fd->search_key = ptr;

@@ -158,6 +158,12 @@ int hfs_brec_find(struct hfs_find_data *fd, search_strategy_t do_key_compare)
 	__be32 data;
 	int height, res;
 
+	fd->record = -1;
+	fd->keyoffset = -1;
+	fd->keylength = -1;
+	fd->entryoffset = -1;
+	fd->entrylength = -1;
+
 	tree = fd->tree;
 	if (fd->bnode)
 		hfs_bnode_put(fd->bnode);

2.51.0

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

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

From: Yang Chenzhi <[email protected]>

[ Upstream commit 738d5a51864ed8d7a68600b8c0c63fe6fe5c4f20 ]

hfsplus_bmap_alloc can trigger a crash if a
record offset or length is larger than node_size

[   15.264282] BUG: KASAN: slab-out-of-bounds in hfsplus_bmap_alloc+0x887/0x8b0
[   15.265192] Read of size 8 at addr ffff8881085ca188 by task test/183
[   15.265949]
[   15.266163] CPU: 0 UID: 0 PID: 183 Comm: test Not tainted 6.17.0-rc2-gc17b750b3ad9 #14 PREEMPT(voluntary)
[   15.266165] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   15.266167] Call Trace:
[   15.266168]  <TASK>
[   15.266169]  dump_stack_lvl+0x53/0x70
[   15.266173]  print_report+0xd0/0x660
[   15.266181]  kasan_report+0xce/0x100
[   15.266185]  hfsplus_bmap_alloc+0x887/0x8b0
[   15.266208]  hfs_btree_inc_height.isra.0+0xd5/0x7c0
[   15.266217]  hfsplus_brec_insert+0x870/0xb00
[   15.266222]  __hfsplus_ext_write_extent+0x428/0x570
[   15.266225]  __hfsplus_ext_cache_extent+0x5e/0x910
[   15.266227]  hfsplus_ext_read_extent+0x1b2/0x200
[   15.266233]  hfsplus_file_extend+0x5a7/0x1000
[   15.266237]  hfsplus_get_block+0x12b/0x8c0
[   15.266238]  __block_write_begin_int+0x36b/0x12c0
[   15.266251]  block_write_begin+0x77/0x110
[   15.266252]  cont_write_begin+0x428/0x720
[   15.266259]  hfsplus_write_begin+0x51/0x100
[   15.266262]  cont_write_begin+0x272/0x720
[   15.266270]  hfsplus_write_begin+0x51/0x100
[   15.266274]  generic_perform_write+0x321/0x750
[   15.266285]  generic_file_write_iter+0xc3/0x310
[   15.266289]  __kernel_write_iter+0x2fd/0x800
[   15.266296]  dump_user_range+0x2ea/0x910
[   15.266301]  elf_core_dump+0x2a94/0x2ed0
[   15.266320]  vfs_coredump+0x1d85/0x45e0
[   15.266349]  get_signal+0x12e3/0x1990
[   15.266357]  arch_do_signal_or_restart+0x89/0x580
[   15.266362]  irqentry_exit_to_user_mode+0xab/0x110
[   15.266364]  asm_exc_page_fault+0x26/0x30
[   15.266366] RIP: 0033:0x41bd35
[   15.266367] Code: bc d1 f3 0f 7f 27 f3 0f 7f 6f 10 f3 0f 7f 77 20 f3 0f 7f 7f 30 49 83 c0 0f 49 29 d0 48 8d 7c 17 31 e9 9f 0b 00 00 66 0f ef c0 <f3> 0f 6f 0e f3 0f 6f 56 10 66 0f 74 c1 66 0f d7 d0 49 83 f8f
[   15.266369] RSP: 002b:00007ffc9e62d078 EFLAGS: 00010283
[   15.266371] RAX: 00007ffc9e62d100 RBX: 0000000000000000 RCX: 0000000000000000
[   15.266372] RDX: 00000000000000e0 RSI: 0000000000000000 RDI: 00007ffc9e62d100
[   15.266373] RBP: 0000400000000040 R08: 00000000000000e0 R09: 0000000000000000
[   15.266374] R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
[   15.266375] R13: 0000000000000000 R14: 0000000000000000 R15: 0000400000000000
[   15.266376]  </TASK>

When calling hfsplus_bmap_alloc to allocate a free node, this function first retrieves the bitmap from header node and map node using node->page together with the offset and length from hfs_brec_lenoff

```
len = hfs_brec_lenoff(node, 2, &off16);
off = off16;

off += node->page_offset;
pagep = node->page + (off >> PAGE_SHIFT);
data = kmap_local_page(*pagep);
```

However, if the retrieved offset or length is invalid(i.e. exceeds node_size), the code may end up accessing pages outside the allocated range for this node.

This patch adds proper validation of both offset and length before use, preventing out-of-bounds page access. Move is_bnode_offset_valid and check_and_correct_requested_length to hfsplus_fs.h, as they may be required by other functions.

---
 fs/hfsplus/bnode.c      | 41 ----------------------------------------
 fs/hfsplus/btree.c      |  6 ++++++
 fs/hfsplus/hfsplus_fs.h | 42 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 48 insertions(+), 41 deletions(-)

index c9c38fddf505b..e566cea238279 100644
@@ -18,47 +18,6 @@
 #include "hfsplus_fs.h"
 #include "hfsplus_raw.h"
 
-static inline
-bool is_bnode_offset_valid(struct hfs_bnode *node, int off)
-{
-	bool is_valid = off < node->tree->node_size;
-
-	if (!is_valid) {
-		pr_err("requested invalid offset: "
-		       "NODE: id %u, type %#x, height %u, "
-		       "node_size %u, offset %d\n",
-		       node->this, node->type, node->height,
-		       node->tree->node_size, off);
-	}
-
-	return is_valid;
-}
-
-static inline
-int check_and_correct_requested_length(struct hfs_bnode *node, int off, int len)
-{
-	unsigned int node_size;
-
-	if (!is_bnode_offset_valid(node, off))
-		return 0;
-
-	node_size = node->tree->node_size;
-
-	if ((off + len) > node_size) {
-		int new_len = (int)node_size - off;
-
-		pr_err("requested length has been corrected: "
-		       "NODE: id %u, type %#x, height %u, "
-		       "node_size %u, offset %d, "
-		       "requested_len %d, corrected_len %d\n",
-		       node->this, node->type, node->height,
-		       node->tree->node_size, off, len, new_len);
-
-		return new_len;
-	}
-
-	return len;
-}
 
 /* Copy a specified range of bytes from the raw data of a node */
 void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len)

index 66774f4cb4fd5..2211907537fec 100644
@@ -392,6 +392,12 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
 	len = hfs_brec_lenoff(node, 2, &off16);
 	off = off16;
 
+	if (!is_bnode_offset_valid(node, off)) {
+		hfs_bnode_put(node);
+		return ERR_PTR(-EIO);
+	}
+	len = check_and_correct_requested_length(node, off, len);
+
 	off += node->page_offset;
 	pagep = node->page + (off >> PAGE_SHIFT);
 	data = kmap(*pagep);

2.51.0

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

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

From: Viacheslav Dubeyko <[email protected]>

[ Upstream commit 9b3d15a758910bb98ba8feb4109d99cc67450ee4 ]

The syzbot reported issue in hfsplus_delete_cat():

[   70.682285][ T9333] =====================================================
[   70.682943][ T9333] BUG: KMSAN: uninit-value in hfsplus_subfolders_dec+0x1d7/0x220
[   70.683640][ T9333]  hfsplus_subfolders_dec+0x1d7/0x220
[   70.684141][ T9333]  hfsplus_delete_cat+0x105d/0x12b0
[   70.684621][ T9333]  hfsplus_rmdir+0x13d/0x310
[   70.685048][ T9333]  vfs_rmdir+0x5ba/0x810
[   70.685447][ T9333]  do_rmdir+0x964/0xea0
[   70.685833][ T9333]  __x64_sys_rmdir+0x71/0xb0
[   70.686260][ T9333]  x64_sys_call+0xcd8/0x3cf0
[   70.686695][ T9333]  do_syscall_64+0xd9/0x1d0
[   70.687119][ T9333]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[   70.687646][ T9333]
[   70.687856][ T9333] Uninit was stored to memory at:
[   70.688311][ T9333]  hfsplus_subfolders_inc+0x1c2/0x1d0
[   70.688779][ T9333]  hfsplus_create_cat+0x148e/0x1800
[   70.689231][ T9333]  hfsplus_mknod+0x27f/0x600
[   70.689730][ T9333]  hfsplus_mkdir+0x5a/0x70
[   70.690146][ T9333]  vfs_mkdir+0x483/0x7a0
[   70.690545][ T9333]  do_mkdirat+0x3f2/0xd30
[   70.690944][ T9333]  __x64_sys_mkdir+0x9a/0xf0
[   70.691380][ T9333]  x64_sys_call+0x2f89/0x3cf0
[   70.691816][ T9333]  do_syscall_64+0xd9/0x1d0
[   70.692229][ T9333]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[   70.692773][ T9333]
[   70.692990][ T9333] Uninit was stored to memory at:
[   70.693469][ T9333]  hfsplus_subfolders_inc+0x1c2/0x1d0
[   70.693960][ T9333]  hfsplus_create_cat+0x148e/0x1800
[   70.694438][ T9333]  hfsplus_fill_super+0x21c1/0x2700
[   70.694911][ T9333]  mount_bdev+0x37b/0x530
[   70.695320][ T9333]  hfsplus_mount+0x4d/0x60
[   70.695729][ T9333]  legacy_get_tree+0x113/0x2c0
[   70.696167][ T9333]  vfs_get_tree+0xb3/0x5c0
[   70.696588][ T9333]  do_new_mount+0x73e/0x1630
[   70.697013][ T9333]  path_mount+0x6e3/0x1eb0
[   70.697425][ T9333]  __se_sys_mount+0x733/0x830
[   70.697857][ T9333]  __x64_sys_mount+0xe4/0x150
[   70.698269][ T9333]  x64_sys_call+0x2691/0x3cf0
[   70.698704][ T9333]  do_syscall_64+0xd9/0x1d0
[   70.699117][ T9333]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[   70.699730][ T9333]
[   70.699946][ T9333] Uninit was created at:
[   70.700378][ T9333]  __alloc_pages_noprof+0x714/0xe60
[   70.700843][ T9333]  alloc_pages_mpol_noprof+0x2a2/0x9b0
[   70.701331][ T9333]  alloc_pages_noprof+0xf8/0x1f0
[   70.701774][ T9333]  allocate_slab+0x30e/0x1390
[   70.702194][ T9333]  ___slab_alloc+0x1049/0x33a0
[   70.702635][ T9333]  kmem_cache_alloc_lru_noprof+0x5ce/0xb20
[   70.703153][ T9333]  hfsplus_alloc_inode+0x5a/0xd0
[   70.703598][ T9333]  alloc_inode+0x82/0x490
[   70.703984][ T9333]  iget_locked+0x22e/0x1320
[   70.704428][ T9333]  hfsplus_iget+0x5c/0xba0
[   70.704827][ T9333]  hfsplus_btree_open+0x135/0x1dd0
[   70.705291][ T9333]  hfsplus_fill_super+0x1132/0x2700
[   70.705776][ T9333]  mount_bdev+0x37b/0x530
[   70.706171][ T9333]  hfsplus_mount+0x4d/0x60
[   70.706579][ T9333]  legacy_get_tree+0x113/0x2c0
[   70.707019][ T9333]  vfs_get_tree+0xb3/0x5c0
[   70.707444][ T9333]  do_new_mount+0x73e/0x1630
[   70.707865][ T9333]  path_mount+0x6e3/0x1eb0
[   70.708270][ T9333]  __se_sys_mount+0x733/0x830
[   70.708711][ T9333]  __x64_sys_mount+0xe4/0x150
[   70.709158][ T9333]  x64_sys_call+0x2691/0x3cf0
[   70.709630][ T9333]  do_syscall_64+0xd9/0x1d0
[   70.710053][ T9333]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[   70.710611][ T9333]
[   70.710842][ T9333] CPU: 3 UID: 0 PID: 9333 Comm: repro Not tainted 6.12.0-rc6-dirty #17
[   70.711568][ T9333] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   70.712490][ T9333] =====================================================
[   70.713085][ T9333] Disabling lock debugging due to kernel taint
[   70.713618][ T9333] Kernel panic - not syncing: kmsan.panic set ...
[   70.714159][ T9333] CPU: 3 UID: 0 PID: 9333 Comm: repro Tainted: G    B              6.12.0-rc6-dirty #17
[   70.715007][ T9333] Tainted: [B]=BAD_PAGE
[   70.715365][ T9333] Hardware name: QEMU Ubuntu 24.04 PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
[   70.716311][ T9333] Call Trace:
[   70.716621][ T9333]  <TASK>
[   70.716899][ T9333]  dump_stack_lvl+0x1fd/0x2b0
[   70.717350][ T9333]  dump_stack+0x1e/0x30
[   70.717743][ T9333]  panic+0x502/0xca0
[   70.718116][ T9333]  ? kmsan_get_metadata+0x13e/0x1c0
[   70.718611][ T9333]  kmsan_report+0x296/0x2a0
[   70.719038][ T9333]  ? __msan_metadata_ptr_for_load_4+0x24/0x40
[   70.719859][ T9333]  ? __msan_warning+0x96/0x120
[   70.720345][ T9333]  ? hfsplus_subfolders_dec+0x1d7/0x220
[   70.720881][ T9333]  ? hfsplus_delete_cat+0x105d/0x12b0
[   70.721412][ T9333]  ? hfsplus_rmdir+0x13d/0x310
[   70.721880][ T9333]  ? vfs_rmdir+0x5ba/0x810
[   70.722458][ T9333]  ? do_rmdir+0x964/0xea0
[   70.722883][ T9333]  ? __x64_sys_rmdir+0x71/0xb0
[   70.723397][ T9333]  ? x64_sys_call+0xcd8/0x3cf0
[   70.723915][ T9333]  ? do_syscall_64+0xd9/0x1d0
[   70.724454][ T9333]  ? entry_SYSCALL_64_after_hwframe+0x77/0x7f
[   70.725110][ T9333]  ? vprintk_emit+0xd1f/0xe60
[   70.725616][ T9333]  ? vprintk_default+0x3f/0x50
[   70.726175][ T9333]  ? vprintk+0xce/0xd0
[   70.726628][ T9333]  ? _printk+0x17e/0x1b0
[   70.727129][ T9333]  ? __msan_metadata_ptr_for_load_4+0x24/0x40
[   70.727739][ T9333]  ? kmsan_get_metadata+0x13e/0x1c0
[   70.728324][ T9333]  __msan_warning+0x96/0x120
[   70.728854][ T9333]  hfsplus_subfolders_dec+0x1d7/0x220
[   70.729479][ T9333]  hfsplus_delete_cat+0x105d/0x12b0
[   70.729984][ T9333]  ? kmsan_get_shadow_origin_ptr+0x4a/0xb0
[   70.730646][ T9333]  ? __msan_metadata_ptr_for_load_4+0x24/0x40
[   70.731296][ T9333]  ? kmsan_get_metadata+0x13e/0x1c0
[   70.731863][ T9333]  hfsplus_rmdir+0x13d/0x310
[   70.732390][ T9333]  ? __pfx_hfsplus_rmdir+0x10/0x10
[   70.732919][ T9333]  vfs_rmdir+0x5ba/0x810
[   70.733416][ T9333]  ? kmsan_get_shadow_origin_ptr+0x4a/0xb0
[   70.734044][ T9333]  do_rmdir+0x964/0xea0
[   70.734537][ T9333]  __x64_sys_rmdir+0x71/0xb0
[   70.735032][ T9333]  x64_sys_call+0xcd8/0x3cf0
[   70.735579][ T9333]  do_syscall_64+0xd9/0x1d0
[   70.736092][ T9333]  ? irqentry_exit+0x16/0x60
[   70.736637][ T9333]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[   70.737269][ T9333] RIP: 0033:0x7fa9424eafc9
[   70.737775][ T9333] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 48
[   70.739844][ T9333] RSP: 002b:00007fff099cd8d8 EFLAGS: 00000202 ORIG_RAX: 0000000000000054
[   70.740760][ T9333] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fa9424eafc9
[   70.741642][ T9333] RDX: 006c6f72746e6f63 RSI: 000000000000000a RDI: 0000000020000100
[   70.742543][ T9333] RBP: 00007fff099cd8e0 R08: 00007fff099cd910 R09: 00007fff099cd910
[   70.743376][ T9333] R10: 0000000000000000 R11: 0000000000000202 R12: 0000565430642260
[   70.744247][ T9333] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
[   70.745082][ T9333]  </TASK>

The main reason of the issue that struct hfsplus_inode_info has not been properly initialized for the case of root folder. In the case of root folder, hfsplus_fill_super() calls the hfsplus_iget() that implements only partial initialization of struct hfsplus_inode_info and subfolders field is not initialized by hfsplus_iget() logic.

This patch implements complete initialization of struct hfsplus_inode_info in the hfsplus_iget() logic with the goal to prevent likewise issues for the case of root folder.

---
 fs/hfsplus/super.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

index 29a39afe26535..d744fde416804 100644
@@ -67,13 +67,26 @@ struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
 	if (!(inode->i_state & I_NEW))
 		return inode;
 
-	INIT_LIST_HEAD(&HFSPLUS_I(inode)->open_dir_list);
-	spin_lock_init(&HFSPLUS_I(inode)->open_dir_lock);
-	mutex_init(&HFSPLUS_I(inode)->extents_lock);
-	HFSPLUS_I(inode)->flags = 0;
+	atomic_set(&HFSPLUS_I(inode)->opencnt, 0);
+	HFSPLUS_I(inode)->first_blocks = 0;
+	HFSPLUS_I(inode)->clump_blocks = 0;
+	HFSPLUS_I(inode)->alloc_blocks = 0;
+	HFSPLUS_I(inode)->cached_start = U32_MAX;
+	HFSPLUS_I(inode)->cached_blocks = 0;
+	memset(HFSPLUS_I(inode)->first_extents, 0, sizeof(hfsplus_extent_rec));
+	memset(HFSPLUS_I(inode)->cached_extents, 0, sizeof(hfsplus_extent_rec));
 	HFSPLUS_I(inode)->extent_state = 0;
+	mutex_init(&HFSPLUS_I(inode)->extents_lock);
 	HFSPLUS_I(inode)->rsrc_inode = NULL;
-	atomic_set(&HFSPLUS_I(inode)->opencnt, 0);
+	HFSPLUS_I(inode)->create_date = 0;
+	HFSPLUS_I(inode)->linkid = 0;
+	HFSPLUS_I(inode)->flags = 0;
+	HFSPLUS_I(inode)->fs_blocks = 0;
+	HFSPLUS_I(inode)->userflags = 0;
+	HFSPLUS_I(inode)->subfolders = 0;
+	INIT_LIST_HEAD(&HFSPLUS_I(inode)->open_dir_list);
+	spin_lock_init(&HFSPLUS_I(inode)->open_dir_lock);
+	HFSPLUS_I(inode)->phys_size = 0;
 
 	if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID ||
 	    inode->i_ino == HFSPLUS_ROOT_CNID) {

2.51.0

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

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

From: Alexander Aring <[email protected]>

[ Upstream commit 6af515c9f3ccec3eb8a262ca86bef2c499d07951 ]

Force values over 3 are undefined, so don't treat them as 3.

---
 fs/dlm/lockspace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index c689359ca532b..9030e0e5927cb 100644
@@ -793,7 +793,7 @@ static int release_lockspace(struct dlm_ls *ls, int force)
 
 	dlm_device_deregister(ls);
 
-	if (force < 3 && dlm_user_daemon_available())
+	if (force != 3 && dlm_user_daemon_available())
 		do_uevent(ls, 0);
 
 	dlm_recoverd_stop(ls);

2.51.0

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

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

From: Viacheslav Dubeyko <[email protected]>

[ Upstream commit 2048ec5b98dbdfe0b929d2e42dc7a54c389c53dd ]

The syzbot reported issue in hfs_find_set_zero_bits():

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

BUG: KMSAN: uninit-value in hfs_find_set_zero_bits+0x74d/0xb60 fs/hfs/bitmap.c:45
 hfs_find_set_zero_bits+0x74d/0xb60 fs/hfs/bitmap.c:45
 hfs_vbm_search_free+0x13c/0x5b0 fs/hfs/bitmap.c:151
 hfs_extend_file+0x6a5/0x1b00 fs/hfs/extent.c:408
 hfs_get_block+0x435/0x1150 fs/hfs/extent.c:353
 __block_write_begin_int+0xa76/0x3030 fs/buffer.c:2151
 block_write_begin fs/buffer.c:2262 [inline]
 cont_write_begin+0x10e1/0x1bc0 fs/buffer.c:2601
 hfs_write_begin+0x85/0x130 fs/hfs/inode.c:52
 cont_expand_zero fs/buffer.c:2528 [inline]
 cont_write_begin+0x35a/0x1bc0 fs/buffer.c:2591
 hfs_write_begin+0x85/0x130 fs/hfs/inode.c:52
 hfs_file_truncate+0x1d6/0xe60 fs/hfs/extent.c:494
 hfs_inode_setattr+0x964/0xaa0 fs/hfs/inode.c:654
 notify_change+0x1993/0x1aa0 fs/attr.c:552
 do_truncate+0x28f/0x310 fs/open.c:68
 do_ftruncate+0x698/0x730 fs/open.c:195
 do_sys_ftruncate fs/open.c:210 [inline]
 __do_sys_ftruncate fs/open.c:215 [inline]
 __se_sys_ftruncate fs/open.c:213 [inline]
 __x64_sys_ftruncate+0x11b/0x250 fs/open.c:213
 x64_sys_call+0xfe3/0x3db0 arch/x86/include/generated/asm/syscalls_64.h:78
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xd9/0x210 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Uninit was created at:

 slab_post_alloc_hook mm/slub.c:4154 [inline]
 slab_alloc_node mm/slub.c:4197 [inline]
 __kmalloc_cache_noprof+0x7f7/0xed0 mm/slub.c:4354
 kmalloc_noprof include/linux/slab.h:905 [inline]
 hfs_mdb_get+0x1cc8/0x2a90 fs/hfs/mdb.c:175
 hfs_fill_super+0x3d0/0xb80 fs/hfs/super.c:337
 get_tree_bdev_flags+0x6e3/0x920 fs/super.c:1681
 get_tree_bdev+0x38/0x50 fs/super.c:1704
 hfs_get_tree+0x35/0x40 fs/hfs/super.c:388
 vfs_get_tree+0xb0/0x5c0 fs/super.c:1804
 do_new_mount+0x738/0x1610 fs/namespace.c:3902
 path_mount+0x6db/0x1e90 fs/namespace.c:4226
 do_mount fs/namespace.c:4239 [inline]
 __do_sys_mount fs/namespace.c:4450 [inline]
 __se_sys_mount+0x6eb/0x7d0 fs/namespace.c:4427
 __x64_sys_mount+0xe4/0x150 fs/namespace.c:4427
 x64_sys_call+0xfa7/0x3db0 arch/x86/include/generated/asm/syscalls_64.h:166
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0xd9/0x210 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

CPU: 1 UID: 0 PID: 12609 Comm: syz.1.2692 Not tainted 6.16.0-syzkaller #0 PREEMPT(none)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
=====================================================

The HFS_SB(sb)->bitmap buffer is allocated in hfs_mdb_get():

HFS_SB(sb)->bitmap = kmalloc(8192, GFP_KERNEL);

Finally, it can trigger the reported issue because kmalloc() doesn't clear the allocated memory. If allocated memory contains only zeros, then everything will work pretty fine.
But if the allocated memory contains the "garbage", then it can affect the bitmap operations and it triggers the reported issue.

This patch simply exchanges the kmalloc() on kzalloc() with the goal to guarantee the correctness of bitmap operations. Because, newly created allocation bitmap should have all available blocks free. Potentially, initialization bitmap's read operation could not fill the whole allocated memory and "garbage" in the not initialized memory will be the reason of volume coruptions and file system driver bugs.

---
 fs/hfs/mdb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 460281b1299eb..8036445672c5f 100644
@@ -166,7 +166,7 @@ int hfs_mdb_get(struct super_block *sb)
 		pr_warn("continuing without an alternate MDB\n");
 	}
 
-	HFS_SB(sb)->bitmap = kmalloc(8192, GFP_KERNEL);
+	HFS_SB(sb)->bitmap = kzalloc(8192, GFP_KERNEL);
 	if (!HFS_SB(sb)->bitmap)
 		goto out;
 

2.51.0

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

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

From: Yangtao Li <[email protected]>

[ Upstream commit 9282bc905f0949fab8cf86c0f620ca988761254c ]

If Catalog File contains corrupted record for the case of hidden directory's type, regard it as I/O error instead of Invalid argument.

---
 fs/hfsplus/super.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index d744fde416804..db68ed59b4b21 100644
@@ -539,7 +539,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	if (!hfs_brec_read(&fd, &entry, sizeof(entry))) {
 		hfs_find_exit(&fd);
 		if (entry.type != cpu_to_be16(HFSPLUS_FOLDER)) {
-			err = -EINVAL;
+			err = -EIO;
 			goto out_put_root;
 		}
 		inode = hfsplus_iget(sb, be32_to_cpu(entry.folder.id));

2.51.0

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

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

From: Geert Uytterhoeven <[email protected]>

[ Upstream commit 6d5674090543b89aac0c177d67e5fb32ddc53804 ]

The function signatures of the m68k-optimized implementations of the find_{first,next}_{,zero_}bit() helpers do not match the generic variants.

Fix this by changing all non-pointer inputs and outputs to "unsigned long", and updating a few local variables.

---
 arch/m68k/include/asm/bitops.h | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

index 10133a968c8e1..d2a9aa0485175 100644
@@ -314,12 +314,12 @@ static inline int bfchg_mem_test_and_change_bit(int nr,
 #include <asm-generic/bitops/ffz.h>
 #else
 
-static inline int find_first_zero_bit(const unsigned long *vaddr,
-				      unsigned size)
+static inline unsigned long find_first_zero_bit(const unsigned long *vaddr,
+						unsigned long size)
 {
 	const unsigned long *p = vaddr;
-	int res = 32;
-	unsigned int words;
+	unsigned long res = 32;
+	unsigned long words;
 	unsigned long num;
 
 	if (!size)

@@ -340,8 +340,9 @@ static inline int find_first_zero_bit(const unsigned long *vaddr,
 }
 #define find_first_zero_bit find_first_zero_bit
 
-static inline int find_next_zero_bit(const unsigned long *vaddr, int size,
-				     int offset)
+static inline unsigned long find_next_zero_bit(const unsigned long *vaddr,
+					       unsigned long size,
+					       unsigned long offset)
 {
 	const unsigned long *p = vaddr + (offset >> 5);
 	int bit = offset & 31UL, res;

@@ -370,11 +371,12 @@ static inline int find_next_zero_bit(const unsigned long *vaddr, int size,
 }
 #define find_next_zero_bit find_next_zero_bit
 
-static inline int find_first_bit(const unsigned long *vaddr, unsigned size)
+static inline unsigned long find_first_bit(const unsigned long *vaddr,
+					   unsigned long size)
 {
 	const unsigned long *p = vaddr;
-	int res = 32;
-	unsigned int words;
+	unsigned long res = 32;
+	unsigned long words;
 	unsigned long num;
 
 	if (!size)

@@ -395,8 +397,9 @@ static inline int find_first_bit(const unsigned long *vaddr, unsigned size)
 }
 #define find_first_bit find_first_bit
 
-static inline int find_next_bit(const unsigned long *vaddr, int size,
-				int offset)
+static inline unsigned long find_next_bit(const unsigned long *vaddr,
+					  unsigned long size,
+					  unsigned long offset)
 {
 	const unsigned long *p = vaddr + (offset >> 5);
 	int bit = offset & 31UL, res;

2.51.0

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

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

From: Colin Ian King <[email protected]>

[ Upstream commit 7d3118016787b5c05da94b3bcdb96c9d6ff82c44 ]

The variable err is being initializeed with a value that is never read and it is being updated later with a new value. The initialization is redundant and can be removed.

Addresses-Coverity: ("Unused value")

Stable-dep-of: bf29555f5bdc ("rtnetlink: Allow deleting FDB entries in user namespace")

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

index 2b7ad5cf8fbfd..f1338734c2eee 100644
@@ -3823,8 +3823,8 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct ndmsg *ndm;
 	struct nlattr *tb[NDA_MAX+1];
 	struct net_device *dev;
-	int err = -EINVAL;
 	__u8 *addr;
+	int err;
 	u16 vid;
 
 	if (!netlink_capable(skb, CAP_NET_ADMIN))

2.51.0

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

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

From: Nikolay Aleksandrov <[email protected]>

[ Upstream commit 12dc5c2cb7b269c5a1c6d02844f40bfce942a7a6 ]

Add rtnl kind names instead of using raw values. We'll need to check for DEL kind later to validate bulk flag support.

Stable-dep-of: bf29555f5bdc ("rtnetlink: Allow deleting FDB entries in user namespace")

---
 include/net/rtnetlink.h | 7 +++++++
 net/core/rtnetlink.c    | 6 +++---
 2 files changed, 10 insertions(+), 3 deletions(-)

index 5c2a73bbfabee..74eff5259b361 100644
@@ -13,6 +13,13 @@ enum rtnl_link_flags {
 	RTNL_FLAG_DOIT_UNLOCKED = 1,
 };
 
+enum rtnl_kinds {
+	RTNL_KIND_NEW,
+	RTNL_KIND_DEL,
+	RTNL_KIND_GET,
+	RTNL_KIND_SET
+};
+
 void rtnl_register(int protocol, int msgtype,
 		   rtnl_doit_func, rtnl_dumpit_func, unsigned int flags);
 int rtnl_register_module(struct module *owner, int protocol, int msgtype,

index f1338734c2eee..2cdb07dd263bd 100644
@@ -5193,11 +5193,11 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 {
 	struct net *net = sock_net(skb->sk);
 	struct rtnl_link *link;
+	enum rtnl_kinds kind;
 	struct module *owner;
 	int err = -EOPNOTSUPP;
 	rtnl_doit_func doit;
 	unsigned int flags;
-	int kind;
 	int family;
 	int type;
 

@@ -5214,11 +5214,11 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family;
 	kind = type&3;
 
-	if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN))
+	if (kind != RTNL_KIND_GET && !netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
 	rcu_read_lock();
-	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
+	if (kind == RTNL_KIND_GET && (nlh->nlmsg_flags & NLM_F_DUMP)) {
 		struct sock *rtnl;
 		rtnl_dumpit_func dumpit;
 		u16 min_dump_alloc = 0;

2.51.0

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

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

From: Nikolay Aleksandrov <[email protected]>

[ Upstream commit 2e9ea3e30f696fd438319c07836422bb0bbb4608 ]

Add a helper which extracts the msg type's kind using the kind mask (0x3).

Stable-dep-of: bf29555f5bdc ("rtnetlink: Allow deleting FDB entries in user namespace")

---
 include/net/rtnetlink.h | 6 ++++++
 net/core/rtnetlink.c    | 2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

index 74eff5259b361..02b0636a4523d 100644
@@ -19,6 +19,12 @@ enum rtnl_kinds {
 	RTNL_KIND_GET,
 	RTNL_KIND_SET
 };
+#define RTNL_KIND_MASK 0x3
+
+static inline enum rtnl_kinds rtnl_msgtype_kind(int msgtype)
+{
+	return msgtype & RTNL_KIND_MASK;
+}
 
 void rtnl_register(int protocol, int msgtype,
 		   rtnl_doit_func, rtnl_dumpit_func, unsigned int flags);

index 2cdb07dd263bd..b41f31a09a7cd 100644
@@ -5212,7 +5212,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return 0;
 
 	family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family;
-	kind = type&3;
+	kind = rtnl_msgtype_kind(type);
 
 	if (kind != RTNL_KIND_GET && !netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;

2.51.0

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

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

From: Nikolay Aleksandrov <[email protected]>

[ Upstream commit 0569e31f1bc2f50613ba4c219f3ecc0d1174d841 ]

Use BIT to define flag values.

Stable-dep-of: bf29555f5bdc ("rtnetlink: Allow deleting FDB entries in user namespace")

---
 include/net/rtnetlink.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 02b0636a4523d..030fc7eef7401 100644
@@ -10,7 +10,7 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *,
 typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *);
 
 enum rtnl_link_flags {
-	RTNL_FLAG_DOIT_UNLOCKED = 1,
+	RTNL_FLAG_DOIT_UNLOCKED = BIT(0),
 };
 
 enum rtnl_kinds {

2.51.0

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

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

From: Nikolay Aleksandrov <[email protected]>

[ Upstream commit 545528d788556c724eeb5400757f828ef27782a8 ]

Add a new delete request modifier called NLM_F_BULK which, when supported, would cause the request to delete multiple objects. The flag is a convenient way to signal that a multiple delete operation is requested which can be gradually added to different delete requests. In order to make sure older kernels will error out if the operation is not supported instead of doing something unintended we have to break a required condition when implementing support for this flag, f.e. for neighbors we will omit the mandatory mac address attribute. Initially it will be used to add flush with filtering support for bridge fdbs, but it also opens the door to add similar support to others.

Stable-dep-of: bf29555f5bdc ("rtnetlink: Allow deleting FDB entries in user namespace")

---
 include/uapi/linux/netlink.h | 1 +
 1 file changed, 1 insertion(+)

index cf4e4836338f6..9ad4c47dea844 100644
@@ -72,6 +72,7 @@ struct nlmsghdr {
 
 /* Modifiers to DELETE request */
 #define NLM_F_NONREC	0x100	/* Do not delete recursively	*/
+#define NLM_F_BULK	0x200	/* Delete multiple objects	*/
 
 /* Flags for ACK message */
 #define NLM_F_CAPPED	0x100	/* request was capped */

2.51.0

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

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

From: Nikolay Aleksandrov <[email protected]>

[ Upstream commit a6cec0bcd34264be8887791594be793b3f12719f ]

Add a new rtnl flag (RTNL_FLAG_BULK_DEL_SUPPORTED) which is used to verify that the delete operation allows bulk object deletion. Also emit a warning if anyone tries to set it for non-delete kind.

Stable-dep-of: bf29555f5bdc ("rtnetlink: Allow deleting FDB entries in user namespace")

---
 include/net/rtnetlink.h | 3 ++-
 net/core/rtnetlink.c    | 8 ++++++++
 2 files changed, 10 insertions(+), 1 deletion(-)

index 030fc7eef7401..e893b1f21913e 100644
@@ -10,7 +10,8 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *,
 typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *);
 
 enum rtnl_link_flags {
-	RTNL_FLAG_DOIT_UNLOCKED = BIT(0),
+	RTNL_FLAG_DOIT_UNLOCKED		= BIT(0),
+	RTNL_FLAG_BULK_DEL_SUPPORTED	= BIT(1),
 };
 
 enum rtnl_kinds {

index b41f31a09a7cd..c4b33a2ecac26 100644
@@ -214,6 +214,8 @@ static int rtnl_register_internal(struct module *owner,
 	if (dumpit)
 		link->dumpit = dumpit;
 
+	WARN_ON(rtnl_msgtype_kind(msgtype) != RTNL_KIND_DEL &&
+		(flags & RTNL_FLAG_BULK_DEL_SUPPORTED));
 	link->flags |= flags;
 
 	/* publish protocol:msgtype */

@@ -5274,6 +5276,12 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	flags = link->flags;
+	if (kind == RTNL_KIND_DEL && (nlh->nlmsg_flags & NLM_F_BULK) &&
+	    !(flags & RTNL_FLAG_BULK_DEL_SUPPORTED)) {
+		NL_SET_ERR_MSG(extack, "Bulk delete is not supported");
+		goto err_unlock;
+	}
+
 	if (flags & RTNL_FLAG_DOIT_UNLOCKED) {
 		doit = link->doit;
 		rcu_read_unlock();

2.51.0

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

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

From: Nikolay Aleksandrov <[email protected]>

[ Upstream commit 1306d5362a591493a2d07f685ed2cc480dcda320 ]

Add a new netdev op called ndo_fdb_del_bulk, it will be later used for driver-specific bulk delete implementation dispatched from rtnetlink. The first user will be the bridge, we need it to signal to rtnetlink from the driver that we support bulk delete operation (NLM_F_BULK).

Stable-dep-of: bf29555f5bdc ("rtnetlink: Allow deleting FDB entries in user namespace")

---
 include/linux/netdevice.h | 9 +++++++++
 1 file changed, 9 insertions(+)

index f5c1058f565c8..037a48bc5690a 100644
@@ -1158,6 +1158,10 @@ struct tlsdev_ops;
  *		      struct net_device *dev,
  *		      const unsigned char *addr, u16 vid)
  *	Deletes the FDB entry from dev coresponding to addr.
+ * int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[],
+ *			   struct net_device *dev,
+ *			   u16 vid,
+ *			   struct netlink_ext_ack *extack);
  * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,
  *		       struct net_device *dev, struct net_device *filter_dev,
  *		       int *idx)

@@ -1396,6 +1400,11 @@ struct net_device_ops {
 					       struct net_device *dev,
 					       const unsigned char *addr,
 					       u16 vid);
+	int			(*ndo_fdb_del_bulk)(struct ndmsg *ndm,
+						    struct nlattr *tb[],
+						    struct net_device *dev,
+						    u16 vid,
+						    struct netlink_ext_ack *extack);
 	int			(*ndo_fdb_dump)(struct sk_buff *skb,
 						struct netlink_callback *cb,
 						struct net_device *dev,

2.51.0

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

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

From: Nikolay Aleksandrov <[email protected]>

[ Upstream commit 9e83425993f38bb89e0ea07849ba0039a748e85b ]

When NLM_F_BULK is specified in a fdb del message we need to handle it differently. First since this is a new call we can strictly validate the passed attributes, at first only ifindex and vlan are allowed as these will be the initially supported filter attributes, any other attribute is rejected. The mac address is no longer mandatory, but we use it to error out in older kernels because it cannot be specified with bulk request (the attribute is not allowed) and then we have to dispatch the call to ndo_fdb_del_bulk if the device supports it. The del bulk callback can do further validation of the attributes if necessary.

Stable-dep-of: bf29555f5bdc ("rtnetlink: Allow deleting FDB entries in user namespace")

---
 net/core/rtnetlink.c | 67 +++++++++++++++++++++++++++++++-------------
 1 file changed, 48 insertions(+), 19 deletions(-)

index c4b33a2ecac26..3d3743ef4f691 100644
@@ -3818,22 +3818,34 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm,
 }
 EXPORT_SYMBOL(ndo_dflt_fdb_del);
 
+static const struct nla_policy fdb_del_bulk_policy[NDA_MAX + 1] = {
+	[NDA_VLAN]	= { .type = NLA_U16 },
+	[NDA_IFINDEX]	= NLA_POLICY_MIN(NLA_S32, 1),
+};
+
 static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct netlink_ext_ack *extack)
 {
+	bool del_bulk = !!(nlh->nlmsg_flags & NLM_F_BULK);
 	struct net *net = sock_net(skb->sk);
+	const struct net_device_ops *ops;
 	struct ndmsg *ndm;
 	struct nlattr *tb[NDA_MAX+1];
 	struct net_device *dev;
-	__u8 *addr;
+	__u8 *addr = NULL;
 	int err;
 	u16 vid;
 
 	if (!netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX, NULL,
-				     extack);
+	if (!del_bulk) {
+		err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX,
+					     NULL, extack);
+	} else {
+		err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX,
+				  fdb_del_bulk_policy, extack);
+	}
 	if (err < 0)
 		return err;
 

@@ -3849,9 +3861,12 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -ENODEV;
 	}
 
-	if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
-		NL_SET_ERR_MSG(extack, "invalid address");
-		return -EINVAL;
+	if (!del_bulk) {
+		if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
+			NL_SET_ERR_MSG(extack, "invalid address");
+			return -EINVAL;
+		}
+		addr = nla_data(tb[NDA_LLADDR]);
 	}
 
 	if (dev->type != ARPHRD_ETHER) {

@@ -3859,8 +3874,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
-	addr = nla_data(tb[NDA_LLADDR]);
-
 	err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
 	if (err)
 		return err;

@@ -3871,10 +3884,16 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) &&
 	    netif_is_bridge_port(dev)) {
 		struct net_device *br_dev = netdev_master_upper_dev_get(dev);
-		const struct net_device_ops *ops = br_dev->netdev_ops;
 
-		if (ops->ndo_fdb_del)
-			err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid);
+		ops = br_dev->netdev_ops;
+		if (!del_bulk) {
+			if (ops->ndo_fdb_del)
+				err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid);
+		} else {
+			if (ops->ndo_fdb_del_bulk)
+				err = ops->ndo_fdb_del_bulk(ndm, tb, dev, vid,
+							    extack);
+		}
 
 		if (err)
 			goto out;

@@ -3884,15 +3903,24 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	/* Embedded bridge, macvlan, and any other device support */
 	if (ndm->ndm_flags & NTF_SELF) {
-		if (dev->netdev_ops->ndo_fdb_del)
-			err = dev->netdev_ops->ndo_fdb_del(ndm, tb, dev, addr,
-							   vid);
-		else
-			err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
+		ops = dev->netdev_ops;
+		if (!del_bulk) {
+			if (ops->ndo_fdb_del)
+				err = ops->ndo_fdb_del(ndm, tb, dev, addr, vid);
+			else
+				err = ndo_dflt_fdb_del(ndm, tb, dev, addr, vid);
+		} else {
+			/* in case err was cleared by NTF_MASTER call */
+			err = -EOPNOTSUPP;
+			if (ops->ndo_fdb_del_bulk)
+				err = ops->ndo_fdb_del_bulk(ndm, tb, dev, vid,
+							    extack);
+		}
 
 		if (!err) {
-			rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH,
-					ndm->ndm_state);
+			if (!del_bulk)
+				rtnl_fdb_notify(dev, addr, vid, RTM_DELNEIGH,
+						ndm->ndm_state);
 			ndm->ndm_flags &= ~NTF_SELF;
 		}
 	}

@@ -5407,7 +5435,8 @@ void __init rtnetlink_init(void)
 	rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, 0);
 
 	rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, 0);
-	rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, 0);
+	rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL,
+		      RTNL_FLAG_BULK_DEL_SUPPORTED);
 	rtnl_register(PF_BRIDGE, RTM_GETNEIGH, rtnl_fdb_get, rtnl_fdb_dump, 0);
 
 	rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, rtnl_bridge_getlink, 0);

2.51.0

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

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

From: Johannes Wiesböck <[email protected]>

[ Upstream commit bf29555f5bdc017bac22ca66fcb6c9f46ec8788f ]

Creating FDB entries is possible from a non-initial user namespace when having CAP_NET_ADMIN, yet, when deleting FDB entries, processes receive an EPERM because the capability is always checked against the initial user namespace. This restricts the FDB management from unprivileged containers.

Drop the netlink_capable check in rtnl_fdb_del as it was originally dropped in c5c351088ae7 and reintroduced in 1690be63a27b without intention.

This patch was tested using a container on GyroidOS, where it was possible to delete FDB entries from an unprivileged user namespace and private network namespace.

---
 net/core/rtnetlink.c | 3 ---
 1 file changed, 3 deletions(-)

index 3d3743ef4f691..342b92afd1219 100644
@@ -3836,9 +3836,6 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err;
 	u16 vid;
 
-	if (!netlink_capable(skb, CAP_NET_ADMIN))
-		return -EPERM;
-
 	if (!del_bulk) {
 		err = nlmsg_parse_deprecated(nlh, sizeof(*ndm), tb, NDA_MAX,
 					     NULL, extack);

2.51.0

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

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

From: Wei Fang <[email protected]>

[ Upstream commit e59bc32df2e989f034623a580e30a2a72af33b3f ]

The ENETC RX ring uses the page halves flipping mechanism, each page is split into two halves for the RX ring to use. And ENETC_RXB_TRUESIZE is defined to 2048 to indicate the size of half a page. However, the page size is configurable, for ARM64 platform, PAGE_SIZE is default to 4K, but it could be configured to 16K or 64K.

When PAGE_SIZE is set to 16K or 64K, ENETC_RXB_TRUESIZE is not correct, and the RX ring will always use the first half of the page. This is not consistent with the description in the relevant kernel doc and commit messages.

This issue is invisible in most cases, but if users want to increase PAGE_SIZE to receive a Jumbo frame with a single buffer for some use cases, it will not work as expected, because the buffer size of each RX BD is fixed to 2048 bytes.

Based on the above two points, we expect to correct ENETC_RXB_TRUESIZE to (PAGE_SIZE >> 1), as described in the comment.

---
 drivers/net/ethernet/freescale/enetc/enetc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index b8801a2b6a025..6203d117d0d2c 100644
@@ -27,7 +27,7 @@ struct enetc_tx_swbd {
 };
 
 #define ENETC_RX_MAXFRM_SIZE	ENETC_MAC_MAXFRM_SIZE
-#define ENETC_RXB_TRUESIZE	2048 /* PAGE_SIZE >> 1 */
+#define ENETC_RXB_TRUESIZE	(PAGE_SIZE >> 1)
 #define ENETC_RXB_PAD		NET_SKB_PAD /* add extra space if needed */
 #define ENETC_RXB_DMA_SIZE	\
 	(SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - ENETC_RXB_PAD)

2.51.0

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

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

From: Huang Ying <[email protected]>

[ Upstream commit 143937ca51cc6ae2fccc61a1cb916abb24cd34f5 ]

Current pte_mkwrite_novma() makes PTE dirty unconditionally. This may mark some pages that are never written dirty wrongly. For example, do_swap_page() may map the exclusive pages with writable and clean PTEs if the VMA is writable and the page fault is for read access. However, current pte_mkwrite_novma() implementation always dirties the PTE. This may cause unnecessary disk writing if the pages are never written before being reclaimed.

So, change pte_mkwrite_novma() to clear the PTE_RDONLY bit only if the PTE_DIRTY bit is set to make it possible to make the PTE writable and clean.

The current behavior was introduced in commit 73e86cb03cf2 ("arm64:
Move PTE_RDONLY bit handling out of set_pte_at()"). Before that, pte_mkwrite() only sets the PTE_WRITE bit, while set_pte_at() only clears the PTE_RDONLY bit if both the PTE_WRITE and the PTE_DIRTY bits are set.

To test the performance impact of the patch, on an arm64 server machine, run 16 redis-server processes on socket 1 and 16 memtier_benchmark processes on socket 0 with mostly get transactions (that is, redis-server will mostly read memory only). The memory footprint of redis-server is larger than the available memory, so swap out/in will be triggered. Test results show that the patch can avoid most swapping out because the pages are mostly clean. And the benchmark throughput improves ~23.9% in the test.

---
 arch/arm64/include/asm/pgtable.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 709badd4475f5..a05d782dcf5e9 100644
@@ -145,7 +145,8 @@ static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot)
 static inline pte_t pte_mkwrite(pte_t pte)
 {
 	pte = set_pte_bit(pte, __pgprot(PTE_WRITE));
-	pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+	if (pte_sw_dirty(pte))
+		pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
 	return pte;
 }
 

2.51.0

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

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

From: Alexey Simakov <[email protected]>

[ Upstream commit 441f0647f7673e0e64d4910ef61a5fb8f16bfb82 ]

chunk->skb pointer is dereferenced in the if-block where it's supposed to be NULL only.

chunk->skb can only be NULL if chunk->head_skb is not. Check for frag_list instead and do it just before replacing chunk->skb. We're sure that otherwise chunk->skb is non-NULL because of outer if() condition.

---
 net/sctp/inqueue.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

index 7182c5a450fb5..6a434d441dc70 100644
@@ -163,13 +163,14 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue)
 				chunk->head_skb = chunk->skb;
 
 			/* skbs with "cover letter" */
-			if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len)
+			if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) {
+				if (WARN_ON(!skb_shinfo(chunk->skb)->frag_list)) {
+					__SCTP_INC_STATS(dev_net(chunk->skb->dev),
+							 SCTP_MIB_IN_PKT_DISCARDS);
+					sctp_chunk_free(chunk);
+					goto next_chunk;
+				}
 				chunk->skb = skb_shinfo(chunk->skb)->frag_list;
-
-			if (WARN_ON(!chunk->skb)) {
-				__SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS);
-				sctp_chunk_free(chunk);
-				goto next_chunk;
 			}
 		}
 

2.51.0

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

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

From: Tonghao Zhang <[email protected]>

commit 10843e1492e474c02b91314963161731fa92af91 upstream.

If the send_peer_notif counter and the peer event notify are not synchronized. It may cause problems such as the loss or dup of peer notify event.

Before this patch:
- If should_notify_peers is true and the lock for send_peer_notif-- fails, peer event may be sent again in next mii_monitor loop, because should_notify_peers is still true.
- If should_notify_peers is true and the lock for send_peer_notif-- succeeded, but the lock for peer event fails, the peer event will be lost.

This patch locks the RTNL for send_peer_notif, events, and commit simultaneously.

---
 drivers/net/bonding/bond_main.c |   40 ++++++++++++++++++----------------------
 1 file changed, 18 insertions(+), 22 deletions(-)

@@ -2331,7 +2331,7 @@ static void bond_mii_monitor(struct work
 {
 	struct bonding *bond = container_of(work, struct bonding,
 					    mii_work.work);
-	bool should_notify_peers = false;
+	bool should_notify_peers;
 	bool commit;
 	unsigned long delay;
 	struct slave *slave;

@@ -2343,30 +2343,33 @@ static void bond_mii_monitor(struct work
 		goto re_arm;
 
 	rcu_read_lock();
+
 	should_notify_peers = bond_should_notify_peers(bond);
 	commit = !!bond_miimon_inspect(bond);
-	if (bond->send_peer_notif) {
-		rcu_read_unlock();
-		if (rtnl_trylock()) {
-			bond->send_peer_notif--;
-			rtnl_unlock();
-		}
-	} else {
-		rcu_read_unlock();
-	}
 
-	if (commit) {
+	rcu_read_unlock();
+
+	if (commit || bond->send_peer_notif) {
 		/* Race avoidance with bond_close cancel of workqueue */
 		if (!rtnl_trylock()) {
 			delay = 1;
-			should_notify_peers = false;
 			goto re_arm;
 		}
 
-		bond_for_each_slave(bond, slave, iter) {
-			bond_commit_link_state(slave, BOND_SLAVE_NOTIFY_LATER);
+		if (commit) {
+			bond_for_each_slave(bond, slave, iter) {
+				bond_commit_link_state(slave,
+						       BOND_SLAVE_NOTIFY_LATER);
+			}
+			bond_miimon_commit(bond);
+		}
+
+		if (bond->send_peer_notif) {
+			bond->send_peer_notif--;
+			if (should_notify_peers)
+				call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
+							 bond->dev);
 		}
-		bond_miimon_commit(bond);
 
 		rtnl_unlock();	/* might sleep, hold no other locks */
 	}

@@ -2374,13 +2377,6 @@ static void bond_mii_monitor(struct work
 re_arm:
 	if (bond->params.miimon)
 		queue_delayed_work(bond->wq, &bond->mii_work, delay);
-
-	if (should_notify_peers) {
-		if (!rtnl_trylock())
-			return;
-		call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev);
-		rtnl_unlock();
-	}
 }
 
 static int bond_upper_dev_walk(struct net_device *upper, void *data)

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

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

From: Rafael J. Wysocki <[email protected]>

commit 10fad4012234a7dea621ae17c0c9486824f645a0 upstream.

It is reported that commit 85975daeaa4d ("cpuidle: menu: Avoid discarding useful information") led to a performance regression on Intel Jasper Lake systems because it reduced the time spent by CPUs in idle state C7 which is correlated to the maximum frequency the CPUs can get to because of an average running power limit [1].

Before that commit, get_typical_interval() would have returned UINT_MAX whenever it had been unable to make a high-confidence prediction which had led to selecting the deepest available idle state too often and both power and performance had been inadequate as a result of that on some systems. However, this had not been a problem on systems with relatively aggressive average running power limits, like the Jasper Lake systems in question, because on those systems it was compensated by the ability to run CPUs faster.

It was addressed by causing get_typical_interval() to return a number based on the recent idle duration information available to it even if it could not make a high-confidence prediction, but that clearly did not take the possible correlation between idle power and available CPU capacity into account.

For this reason, revert most of the changes made by commit 85975daeaa4d, except for one cosmetic cleanup, and add a comment explaining the rationale for returning UINT_MAX from get_typical_interval() when it is unable to make a high-confidence prediction.

---
 drivers/cpuidle/governors/menu.c |   21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

@@ -258,20 +258,17 @@ again:
 	 *
 	 * This can deal with workloads that have long pauses interspersed
 	 * with sporadic activity with a bunch of short pauses.
+	 *
+	 * However, if the number of remaining samples is too small to exclude
+	 * any more outliers, allow the deepest available idle state to be
+	 * selected because there are systems where the time spent by CPUs in
+	 * deep idle states is correlated to the maximum frequency the CPUs
+	 * can get to.  On those systems, shallow idle states should be avoided
+	 * unless there is a clear indication that the given CPU is most likley
+	 * going to be woken up shortly.
 	 */
-	if (divisor * 4 <= INTERVALS * 3) {
-		/*
-		 * If there are sufficiently many data points still under
-		 * consideration after the outliers have been eliminated,
-		 * returning without a prediction would be a mistake because it
-		 * is likely that the next interval will not exceed the current
-		 * maximum, so return the latter in that case.
-		 */
-		if (divisor >= INTERVALS / 2)
-			return max;
-
+	if (divisor * 4 <= INTERVALS * 3)
 		return UINT_MAX;
-	}
 
 	thresh = max - 1;
 	goto again;

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

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

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

commit bf5570590a981d0659d0808d2d4bcda21b27a2a5 upstream.

MIPS Malta platform code registers the PCI southbridge legacy port I/O PS/2 keyboard range as a standard resource marked as busy. It prevents the i8042 driver from registering as it fails to claim the resource in a call to i8042_platform_init(). Consequently PS/2 keyboard and mouse devices cannot be used with this platform.

Fix the issue by removing the busy marker from the standard reservation, making the driver register successfully:

serio: i8042 KBD port at 0x60,0x64 irq 1
serio: i8042 AUX port at 0x60,0x64 irq 12

and the resource show up as expected among the legacy devices:

00000000-00ffffff : MSC PCI I/O

    00000000-0000001f : dma1
    00000020-00000021 : pic1
    00000040-0000005f : timer
    00000060-0000006f : keyboard
      00000060-0000006f : i8042
    00000070-00000077 : rtc0
    00000080-0000008f : dma page reg
    000000a0-000000a1 : pic2
    000000c0-000000df : dma2
    [...]

If the i8042 driver has not been configured, then the standard resource will remain there preventing any conflicting dynamic assignment of this PCI port I/O address range.

---
 arch/mips/mti-malta/malta-setup.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -48,7 +48,7 @@ static struct resource standard_io_resou
 		.name = "keyboard",
 		.start = 0x60,
 		.end = 0x6f,
-		.flags = IORESOURCE_IO | IORESOURCE_BUSY
+		.flags = IORESOURCE_IO
 	},
 	{
 		.name = "dma page reg",

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

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

From: Deepanshu Kartikey <[email protected]>

commit 78a63493f8e352296dbc7cb7b3f4973105e8679e upstream.

The extent map cache can become stale when extents are moved or defragmented, causing subsequent operations to see outdated extent flags. This triggers a BUG_ON in ocfs2_refcount_cal_cow_clusters().

The problem occurs when:
1. copy_file_range() creates a reflinked extent with OCFS2_EXT_REFCOUNTED
2. ioctl(FITRIM) triggers ocfs2_move_extents()
3. __ocfs2_move_extents_range() reads and caches the extent (flags=0x2)
4. ocfs2_move_extent()/ocfs2_defrag_extent() calls __ocfs2_move_extent() which clears OCFS2_EXT_REFCOUNTED flag on disk (flags=0x0)
5. The extent map cache is not invalidated after the move
6. Later write() operations read stale cached flags (0x2) but disk has updated flags (0x0), causing a mismatch
7. BUG_ON(!(rec->e_flags & OCFS2_EXT_REFCOUNTED)) triggers

Fix by clearing the extent map cache after each extent move/defrag operation in __ocfs2_move_extents_range(). This ensures subsequent operations read fresh extent data from disk.

---
 fs/ocfs2/move_extents.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -870,6 +870,11 @@ static int __ocfs2_move_extents_range(st
 			mlog_errno(ret);
 			goto out;
 		}
+		/*
+		 * Invalidate extent cache after moving/defragging to prevent
+		 * stale cached data with outdated extent flags.
+		 */
+		ocfs2_extent_map_trunc(inode, cpos);
 
 		context->clusters_moved += alloc_size;
 next:

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

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

From: Michal Pecio <[email protected]>

commit 75cea9860aa6b2350d90a8d78fed114d27c7eca2 upstream.

TX frames aren't padded and unknown memory is sent into the ether.

Theoretically, it isn't even guaranteed that the extra memory exists and can be sent out, which could cause further problems. In practice, I found that plenty of tailroom exists in the skb itself (in my test with ping at least) and skb_padto() easily succeeds, so use it here.

In the event of -ENOMEM drop the frame like other drivers do.

The use of one more padding byte instead of a USB zero-length packet is retained to avoid regression. I have a dodgy Etron xHCI controller which doesn't seem to support sending ZLPs at all.

---
 drivers/net/usb/rtl8150.c |   11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

@@ -705,9 +705,16 @@ static netdev_tx_t rtl8150_start_xmit(st
 	rtl8150_t *dev = netdev_priv(netdev);
 	int count, res;
 
+	/* pad the frame and ensure terminating USB packet, datasheet 9.2.3 */
+	count = max(skb->len, ETH_ZLEN);
+	if (count % 64 == 0)
+		count++;
+	if (skb_padto(skb, count)) {
+		netdev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
+
 	netif_stop_queue(netdev);
-	count = (skb->len < 60) ? 60 : skb->len;
-	count = (count & 0x3f) ? count : count + 1;
 	dev->tx_skb = skb;
 	usb_fill_bulk_urb(dev->tx_urb, dev->udev, usb_sndbulkpipe(dev->udev, 2),
 		      skb->data, count, write_bulk_callback, dev);

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

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

From: Lad Prabhakar <[email protected]>

commit 706136c5723626fcde8dd8f598a4dcd251e24927 upstream.

Add a final dma_wmb() barrier before triggering the transmit request (TCCR_TSRQ) to ensure all descriptor and buffer writes are visible to the DMA engine.

According to the hardware manual, a read-back operation is required before writing to the doorbell register to guarantee completion of previous writes. Instead of performing a dummy read, a dma_wmb() is used to both enforce the same ordering semantics on the CPU side and also to ensure completion of writes.

---
 drivers/net/ethernet/renesas/ravb_main.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -1602,6 +1602,14 @@ static netdev_tx_t ravb_start_xmit(struc
 	} else {
 		desc->die_dt = DT_FSINGLE;
 	}
+
+	/* Before ringing the doorbell we need to make sure that the latest
+	 * writes have been committed to memory, otherwise it could delay
+	 * things until the doorbell is rang again.
+	 * This is in replacement of the read operation mentioned in the HW
+	 * manuals.
+	 */
+	dma_wmb();
 	ravb_modify(ndev, TCCR, TCCR_TSRQ0 << q, TCCR_TSRQ0 << q);
 
 	priv->cur_tx[q] += num_tx_desc;

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

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

From: Renjun Wang <[email protected]>

commit 71c07570b918f000de5d0f7f1bf17a2887e303b5 upstream.

Add support for UNISOC (Spreadtrum) UIS7720 (A7720) module.

T:  Bus=05 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  5 Spd=480 MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1782 ProdID=4064 Rev=04.04
S:  Manufacturer=Unisoc-phone
S:  Product=Unisoc-phone
S:  SerialNumber=0123456789ABCDEF
C:  #Ifs= 9 Cfg#= 1 Atr=c0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=e0(wlcon) Sub=01 Prot=03 Driver=rndis_host
E:  Ad=82(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=rndis_host
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 7 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 8 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=08(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0&1: RNDIS, 2: LOG, 3: DIAG, 4&5: AT Ports, 6&7: AT2 Ports, 8: ADB

---
 drivers/usb/serial/option.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -617,6 +617,7 @@ static void option_instat_callback(struc
 #define UNISOC_VENDOR_ID			0x1782
 /* TOZED LT70-C based on UNISOC SL8563 uses UNISOC's vendor ID */
 #define TOZED_PRODUCT_LT70C			0x4055
+#define UNISOC_PRODUCT_UIS7720			0x4064
 /* Luat Air72*U series based on UNISOC UIS8910 uses UNISOC's vendor ID */
 #define LUAT_PRODUCT_AIR720U			0x4e00
 

@@ -2466,6 +2467,7 @@ static const struct usb_device_id option
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x30) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9291, 0xff, 0xff, 0x40) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, UNISOC_PRODUCT_UIS7720, 0xff, 0, 0) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff),			/* TCL IK512 MBIM */
 	  .driver_info = NCTRL(1) },

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

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

From: Reinhard Speyerer <[email protected]>

commit 89205c60c0fc96b73567a2e9fe27ee3f59d01193 upstream.

Add support for Quectel RG255C devices to complement commit 5c964c8a97c1 ("net: usb: qmi_wwan: add Quectel RG255C").
The composition is DM / NMEA / AT / QMI.

T:  Bus=01 Lev=02 Prnt=99 Port=01 Cnt=02 Dev#=110 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=2c7c ProdID=0316 Rev= 5.15
S:  Manufacturer=Quectel
S:  Product=RG255C-GL
S:  SerialNumber=xxxxxxxx
C:* #Ifs= 4 Cfg#= 1 Atr=a0 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=00 Prot=00 Driver=option
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan
E:  Ad=86(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms

---
 drivers/usb/serial/option.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -273,6 +273,7 @@ static void option_instat_callback(struc
 #define QUECTEL_PRODUCT_EM05CN			0x0312
 #define QUECTEL_PRODUCT_EM05G_GR		0x0313
 #define QUECTEL_PRODUCT_EM05G_RS		0x0314
+#define QUECTEL_PRODUCT_RG255C			0x0316
 #define QUECTEL_PRODUCT_EM12			0x0512
 #define QUECTEL_PRODUCT_RM500Q			0x0800
 #define QUECTEL_PRODUCT_RM520N			0x0801

@@ -1271,6 +1272,9 @@ static const struct usb_device_id option
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RG650V, 0xff, 0xff, 0x30) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RG650V, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RG255C, 0xff, 0xff, 0x30) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RG255C, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RG255C, 0xff, 0xff, 0x40) },
 
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },

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

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

From: LI Qingwu <[email protected]>

commit 622865c73ae30f254abdf182f4b66cccbe3e0f10 upstream.

Add support for the Telit Cinterion FN920C04 module when operating in ECM (Ethernet Control Model) mode. The following USB product IDs are used by the module when AT#USBCFG is set to 3 or 7.

0x10A3: ECM + tty (NMEA) + tty (DUN) [+ tty (DIAG)]

T:  Bus=01 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=10a3 Rev= 5.15
S:  Manufacturer=Telit Cinterion
S:  Product=FN920
S:  SerialNumber=76e7cb38
C:* #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=06 Prot=00 Driver=cdc_ether
E:  Ad=82(I) Atr=03(Int.) MxPS=  16 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether
I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x10A8: ECM + tty (DUN) + tty (AUX) [+ tty (DIAG)]

T:  Bus=03 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=  3 Spd=480  MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=10a8 Rev= 5.15
S:  Manufacturer=Telit Cinterion
S:  Product=FN920
S:  SerialNumber=76e7cb38
C:* #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 1 Cls=02(comm.) Sub=06 Prot=00 Driver=cdc_ether
E:  Ad=82(I) Atr=03(Int.) MxPS=  16 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 0 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether
I:* If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:* If#= 4 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Adding these IDs allows the option driver to automatically create the corresponding /dev/ttyUSB* ports under ECM mode.

Tested with FN920C04 under ECM configuration (USBCFG=3 and 7).

---
 drivers/usb/serial/option.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -1403,10 +1403,14 @@ static const struct usb_device_id option
 	  .driver_info = RSVD(0) | NCTRL(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a2, 0xff),	/* Telit FN920C04 (MBIM) */
 	  .driver_info = NCTRL(4) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a3, 0xff),	/* Telit FN920C04 (ECM) */
+	  .driver_info = NCTRL(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a4, 0xff),	/* Telit FN20C04 (rmnet) */
 	  .driver_info = RSVD(0) | NCTRL(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a7, 0xff),	/* Telit FN920C04 (MBIM) */
 	  .driver_info = NCTRL(4) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a8, 0xff),	/* Telit FN920C04 (ECM) */
+	  .driver_info = NCTRL(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a9, 0xff),	/* Telit FN20C04 (rmnet) */
 	  .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10aa, 0xff),	/* Telit FN920C04 (MBIM) */

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

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

From: Tim Guttzeit <[email protected]>

commit dfc2cf4dcaa03601cd4ca0f7def88b2630fca6ab upstream.

The list of Huawei LTE modules needing the quirk fixing spurious wakeups was missing the IDs of the Huawei ME906S module, therefore suspend did not work.

---
 drivers/usb/core/quirks.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -462,6 +462,8 @@ static const struct usb_device_id usb_qu
 	/* Huawei 4G LTE module */
 	{ USB_DEVICE(0x12d1, 0x15bb), .driver_info =
 			USB_QUIRK_DISCONNECT_SUSPEND },
+	{ USB_DEVICE(0x12d1, 0x15c1), .driver_info =
+			USB_QUIRK_DISCONNECT_SUSPEND },
 	{ USB_DEVICE(0x12d1, 0x15c3), .driver_info =
 			USB_QUIRK_DISCONNECT_SUSPEND },
 

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

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

From: Mathias Nyman <[email protected]>

commit 2bbd38fcd29670e46c0fdb9cd0e90507a8a1bf6a upstream.

DbC is currently only enabled back if it's in configured state during suspend.

If system is suspended after DbC is enabled, but before the device is properly enumerated by the host, then DbC would not be enabled back in resume.

Always enable DbC back in resume if it's suspended in enabled, connected, or configured state

---
 drivers/usb/host/xhci-dbgcap.c |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

@@ -975,8 +975,15 @@ int xhci_dbc_suspend(struct xhci_hcd *xh
 	if (!dbc)
 		return 0;
 
-	if (dbc->state == DS_CONFIGURED)
+	switch (dbc->state) {
+	case DS_ENABLED:
+	case DS_CONNECTED:
+	case DS_CONFIGURED:
 		dbc->resume_required = 1;
+		break;
+	default:
+		break;
+	}
 
 	xhci_dbc_stop(xhci);
 

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

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

From: Alice Ryhl <[email protected]>

commit d90eeb8ecd227c204ab6c34a17b372bd950b7aa2 upstream.

There are no scenarios where a weak increment is invalid on binder_node. The only possible case where it could be invalid is if the kernel delivers BR_DECREFS to the process that owns the node, and then increments the weak refcount again, effectively "reviving" a dead node.

However, that is not possible: when the BR_DECREFS command is delivered, the kernel removes and frees the binder_node. The fact that you were able to call binder_inc_node_nilocked() implies that the node is not yet destroyed, which implies that BR_DECREFS has not been delivered to userspace, so incrementing the weak refcount is valid.

Note that it's currently possible to trigger this condition if the owner calls BINDER_THREAD_EXIT while node->has_weak_ref is true. This causes BC_INCREFS on binder_ref instances to fail when they should not.

---
 drivers/android/binder.c |   11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

@@ -1208,17 +1208,8 @@ static int binder_inc_node_nilocked(stru
 	} else {
 		if (!internal)
 			node->local_weak_refs++;
-		if (!node->has_weak_ref && list_empty(&node->work.entry)) {
-			if (target_list == NULL) {
-				pr_err("invalid inc weak node for %d\n",
-					node->debug_id);
-				return -EINVAL;
-			}
-			/*
-			 * See comment above
-			 */
+		if (!node->has_weak_ref && target_list && list_empty(&node->work.entry))
 			binder_enqueue_work_ilocked(&node->work, target_list);
-		}
 	}
 	return 0;
 }

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

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

From: Deepanshu Kartikey <[email protected]>

commit 87b318ba81dda2ee7b603f4f6c55e78ec3e95974 upstream.

The comedi_buf_munge() function performs a modulo operation async->munge_chan %= async->cmd.chanlist_len without first checking if chanlist_len is zero. If a user program submits a command with chanlist_len set to zero, this causes a divide-by-zero error when the device processes data in the interrupt handler path.

Add a check for zero chanlist_len at the beginning of the function, similar to the existing checks for !map and CMDF_RAWDATA flag. When chanlist_len is zero, update munge_count and return early, indicating the data was handled without munging.

This prevents potential kernel panics from malformed user commands.

---
 drivers/staging/comedi/comedi_buf.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -369,7 +369,7 @@ static unsigned int comedi_buf_munge(str
 	unsigned int count = 0;
 	const unsigned int num_sample_bytes = comedi_bytes_per_sample(s);
 
-	if (!s->munge || (async->cmd.flags & CMDF_RAWDATA)) {
+	if (!s->munge || (async->cmd.flags & CMDF_RAWDATA) || async->cmd.chanlist_len == 0) {
 		async->munge_count += num_bytes;
 		count = num_bytes;
 	} else {

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

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

From: Mark Rutland <[email protected]>

commit 3bbf004c4808e2c3241e5c1ad6cc102f38a03c39 upstream.

Add cputype definitions for Neoverse-V3AE. These will be used for errata detection in subsequent patches.

These values can be found in the Neoverse-V3AE TRM:

https://developer.arm.com/documentation/SDEN-2615521/9-0/

... in section A.6.1 ("MIDR_EL1, Main ID Register").

---
 arch/arm64/include/asm/cputype.h |    2 ++
 1 file changed, 2 insertions(+)

@@ -87,6 +87,7 @@
 #define ARM_CPU_PART_NEOVERSE_V2	0xD4F
 #define ARM_CPU_PART_CORTEX_A720	0xD81
 #define ARM_CPU_PART_CORTEX_X4		0xD82
+#define ARM_CPU_PART_NEOVERSE_V3AE	0xD83
 #define ARM_CPU_PART_NEOVERSE_V3	0xD84
 #define ARM_CPU_PART_CORTEX_X925	0xD85
 #define ARM_CPU_PART_CORTEX_A725	0xD87

@@ -139,6 +140,7 @@
 #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2)
 #define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720)
 #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4)
+#define MIDR_NEOVERSE_V3AE	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3AE)
 #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3)
 #define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925)
 #define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725)

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

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

From: Mark Rutland <[email protected]>

commit 0c33aa1804d101c11ba1992504f17a42233f0e11 upstream.

Neoverse-V3AE is also affected by erratum #3312417, as described in its Software Developer Errata Notice (SDEN) document:

Neoverse V3AE (MP172) SDEN v9.0, erratum 3312417
https://developer.arm.com/documentation/SDEN-2615521/9-0/

Enable the workaround for Neoverse-V3AE, and document this.

---
 Documentation/arm64/silicon-errata.rst |    2 ++
 arch/arm64/Kconfig                     |    1 +
 arch/arm64/kernel/cpu_errata.c         |    1 +
 3 files changed, 4 insertions(+)

@@ -134,6 +134,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-V3     | #3312417        | ARM64_ERRATUM_3194386       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-V3AE   | #3312417        | ARM64_ERRATUM_3194386       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+

@@ -617,6 +617,7 @@ config ARM64_ERRATUM_3194386
 	  * ARM Neoverse-V1 erratum 3324341
 	  * ARM Neoverse V2 erratum 3324336
 	  * ARM Neoverse-V3 erratum 3312417
+	  * ARM Neoverse-V3AE erratum 3312417
 
 	  On affected cores "MSR SSBS, #0" instructions may not affect
 	  subsequent speculative instructions, which may permit unexepected

@@ -863,6 +863,7 @@ static const struct midr_range erratum_s
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2),
 	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3),
+	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3AE),
 	{}
 };
 #endif

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

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

From: Krzysztof Kozlowski <[email protected]>

[ Upstream commit 90de1c75d8acd83e9a699b93153307a1e411ef3a ]

Align indentation with open parenthesis (or fix existing alignment).

Stable-dep-of: 6744085079e7 ("memory: samsung: exynos-srom: Fix of_iomap leak in exynos_srom_probe")

---
 drivers/memory/samsung/exynos-srom.c |   22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

@@ -47,9 +47,9 @@ struct exynos_srom {
 	struct exynos_srom_reg_dump *reg_offset;
 };
 
-static struct exynos_srom_reg_dump *exynos_srom_alloc_reg_dump(
-		const unsigned long *rdump,
-		unsigned long nr_rdump)
+static struct exynos_srom_reg_dump *
+exynos_srom_alloc_reg_dump(const unsigned long *rdump,
+			   unsigned long nr_rdump)
 {
 	struct exynos_srom_reg_dump *rd;
 	unsigned int i;

@@ -116,7 +116,7 @@ static int exynos_srom_probe(struct plat
 	}
 
 	srom = devm_kzalloc(&pdev->dev,
-			sizeof(struct exynos_srom), GFP_KERNEL);
+			    sizeof(struct exynos_srom), GFP_KERNEL);
 	if (!srom)
 		return -ENOMEM;
 

@@ -130,7 +130,7 @@ static int exynos_srom_probe(struct plat
 	platform_set_drvdata(pdev, srom);
 
 	srom->reg_offset = exynos_srom_alloc_reg_dump(exynos_srom_offsets,
-			ARRAY_SIZE(exynos_srom_offsets));
+						      ARRAY_SIZE(exynos_srom_offsets));
 	if (!srom->reg_offset) {
 		iounmap(srom->reg_base);
 		return -ENOMEM;

@@ -157,16 +157,16 @@ static int exynos_srom_probe(struct plat
 
 #ifdef CONFIG_PM_SLEEP
 static void exynos_srom_save(void __iomem *base,
-				    struct exynos_srom_reg_dump *rd,
-				    unsigned int num_regs)
+			     struct exynos_srom_reg_dump *rd,
+			     unsigned int num_regs)
 {
 	for (; num_regs > 0; --num_regs, ++rd)
 		rd->value = readl(base + rd->offset);
 }
 
 static void exynos_srom_restore(void __iomem *base,
-				      const struct exynos_srom_reg_dump *rd,
-				      unsigned int num_regs)
+				const struct exynos_srom_reg_dump *rd,
+				unsigned int num_regs)
 {
 	for (; num_regs > 0; --num_regs, ++rd)
 		writel(rd->value, base + rd->offset);

@@ -177,7 +177,7 @@ static int exynos_srom_suspend(struct de
 	struct exynos_srom *srom = dev_get_drvdata(dev);
 
 	exynos_srom_save(srom->reg_base, srom->reg_offset,
-				ARRAY_SIZE(exynos_srom_offsets));
+			 ARRAY_SIZE(exynos_srom_offsets));
 	return 0;
 }
 

@@ -186,7 +186,7 @@ static int exynos_srom_resume(struct dev
 	struct exynos_srom *srom = dev_get_drvdata(dev);
 
 	exynos_srom_restore(srom->reg_base, srom->reg_offset,
-				ARRAY_SIZE(exynos_srom_offsets));
+			    ARRAY_SIZE(exynos_srom_offsets));
 	return 0;
 }
 #endif

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

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

From: Zhen Ni <[email protected]>

[ Upstream commit 6744085079e785dae5f7a2239456135407c58b25 ]

The of_platform_populate() call at the end of the function has a possible failure path, causing a resource leak.

Replace of_iomap() with devm_platform_ioremap_resource() to ensure automatic cleanup of srom->reg_base.

This issue was detected by smatch static analysis:
drivers/memory/samsung/exynos-srom.c:155 exynos_srom_probe()warn:
'srom->reg_base' from of_iomap() not released on lines: 155.

---
 drivers/memory/samsung/exynos-srom.c |   10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

@@ -121,20 +121,18 @@ static int exynos_srom_probe(struct plat
 		return -ENOMEM;
 
 	srom->dev = dev;
-	srom->reg_base = of_iomap(np, 0);
-	if (!srom->reg_base) {
+	srom->reg_base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(srom->reg_base)) {
 		dev_err(&pdev->dev, "iomap of exynos srom controller failed\n");
-		return -ENOMEM;
+		return PTR_ERR(srom->reg_base);
 	}
 
 	platform_set_drvdata(pdev, srom);
 
 	srom->reg_offset = exynos_srom_alloc_reg_dump(exynos_srom_offsets,
 						      ARRAY_SIZE(exynos_srom_offsets));
-	if (!srom->reg_offset) {
-		iounmap(srom->reg_base);
+	if (!srom->reg_offset)
 		return -ENOMEM;
-	}
 
 	for_each_child_of_node(np, child) {
 		if (exynos_srom_configure_bank(srom, child)) {

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

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

From: Pratyush Yadav <[email protected]>

[ Upstream commit 29e0b471ccbd674d20d4bbddea1a51e7105212c5 ]

cqspi_indirect_read_execute() and cqspi_indirect_write_execute() first set the enable bit on APB region and then start reading/writing to the AHB region. On TI K3 SoCs these regions lie on different endpoints. This means that the order of the two operations is not guaranteed, and they might be reordered at the interconnect level.

It is possible for the AHB write to be executed before the APB write to enable the indirect controller, causing the transaction to be invalid and the write erroring out. Read back the APB region write before accessing the AHB region to make sure the write got flushed and the race condition is eliminated.

Message-ID: <[email protected]>

---
 drivers/mtd/spi-nor/cadence-quadspi.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -523,6 +523,7 @@ static int cqspi_indirect_read_execute(s
 	reinit_completion(&cqspi->transfer_complete);
 	writel(CQSPI_REG_INDIRECTRD_START_MASK,
 	       reg_base + CQSPI_REG_INDIRECTRD);
+	readl(reg_base + CQSPI_REG_INDIRECTRD); /* Flush posted write. */
 
 	while (remaining > 0) {
 		if (!wait_for_completion_timeout(&cqspi->transfer_complete,

@@ -633,6 +634,8 @@ static int cqspi_indirect_write_execute(
 	reinit_completion(&cqspi->transfer_complete);
 	writel(CQSPI_REG_INDIRECTWR_START_MASK,
 	       reg_base + CQSPI_REG_INDIRECTWR);
+	readl(reg_base + CQSPI_REG_INDIRECTWR); /* Flush posted write. */
+
 	/*
 	 * As per 66AK2G02 TRM SPRUHY8F section 11.15.5.3 Indirect Access
 	 * Controller programming sequence, couple of cycles of

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

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

From: Pratyush Yadav <[email protected]>

[ Upstream commit 1ad55767e77a853c98752ed1e33b68049a243bd7 ]

cqspi_read_setup() and cqspi_write_setup() program the address width as the last step in the setup. This is likely to be immediately followed by a DAC region read/write. On TI K3 SoCs the DAC region is on a different endpoint from the register region. This means that the order of the two operations is not guaranteed, and they might be reordered at the interconnect level. It is possible that the DAC read/write goes through before the address width update goes through. In this situation if the previous command used a different address width the OSPI command is sent with the wrong number of address bytes, resulting in an invalid command and undefined behavior.

Read back the size register to make sure the write gets flushed before accessing the DAC region.

Message-ID: <[email protected]>