6.1.159-rc1 review

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

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

From: Michal Hocko <[email protected]>

[ Upstream commit 9a5b183941b52f84c0f9e5f27ce44e99318c9e0f ]

28307d938fb2 ("percpu: make pcpu_alloc() aware of current gfp context") has fixed a reclaim recursion for scoped GFP_NOFS context. It has done that by avoiding taking pcpu_alloc_mutex. This is a correct solution as the worker context with full GFP_KERNEL allocation/reclaim power and which is using the same lock cannot block the NOFS pcpu_alloc caller.

On the other hand this is a very conservative approach that could lead to failures because pcpu_alloc lockless implementation is quite limited.

We have a bug report about premature failures when scsi array of 193 devices is scanned. Sometimes (not consistently) the scanning aborts because the iscsid daemon fails to create the queue for a random scsi device during the scan. iscsid itself is running with PR_SET_IO_FLUSHER set so all allocations from this process context are GFP_NOIO. This in turn makes any pcpu_alloc lockless (without pcpu_alloc_mutex) which leads to pre-mature failures.

It has turned out that iscsid has worked around this by dropping PR_SET_IO_FLUSHER (https://github.com/open-iscsi/open-iscsi/pull/382) when scanning host. But we can do better in this case on the kernel side and use pcpu_alloc_mutex for NOIO resp. NOFS constrained allocation scopes too. We just need the WQ worker to never trigger IO/FS reclaim. Achieve that by enforcing scoped GFP_NOIO for the whole execution of pcpu_balance_workfn (this will imply NOFS constrain as well). This will remove the dependency chain and preserve the full allocation power of the pcpu_alloc call.

While at it make is_atomic really test for blockable allocations.

---
 mm/percpu.c |    8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

@@ -1737,7 +1737,7 @@ static void __percpu *pcpu_alloc(size_t
 	gfp = current_gfp_context(gfp);
 	/* whitelisted flags that can be passed to the backing allocators */
 	pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
-	is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
+	is_atomic = !gfpflags_allow_blocking(gfp);
 	do_warn = !(gfp & __GFP_NOWARN);
 
 	/*

@@ -2237,7 +2237,12 @@ static void pcpu_balance_workfn(struct w
 	 * to grow other chunks.  This then gives pcpu_reclaim_populated() time
 	 * to move fully free chunks to the active list to be freed if
 	 * appropriate.
+	 *
+	 * Enforce GFP_NOIO allocations because we have pcpu_alloc users
+	 * constrained to GFP_NOIO/NOFS contexts and they could form lock
+	 * dependency through pcpu_alloc_mutex
 	 */
+	unsigned int flags = memalloc_noio_save();
 	mutex_lock(&pcpu_alloc_mutex);
 	spin_lock_irq(&pcpu_lock);
 

@@ -2248,6 +2253,7 @@ static void pcpu_balance_workfn(struct w
 
 	spin_unlock_irq(&pcpu_lock);
 	mutex_unlock(&pcpu_alloc_mutex);
+	memalloc_noio_restore(flags);
 }
 
 /**

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

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

From: Abdun Nihaal <[email protected]>

commit 3f978e3f1570155a1327ffa25f60968bc7b9398f upstream.

In hfcsusb_probe(), the memory allocated for ctrl_urb gets leaked when setup_instance() fails with an error code. Fix that by freeing the urb before freeing the hw structure. Also change the error paths to use the goto ladder style.

Compile tested only. Issue found using a prototype static analysis tool.

---
 drivers/isdn/hardware/mISDN/hfcsusb.c |   18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

@@ -1903,13 +1903,13 @@ out:
 	mISDN_freebchannel(&hw->bch[1]);
 	mISDN_freebchannel(&hw->bch[0]);
 	mISDN_freedchannel(&hw->dch);
-	kfree(hw);
 	return err;
 }
 
 static int
 hfcsusb_probe(struct usb_interface *intf, const struct usb_device_id *id)
 {
+	int err;
 	struct hfcsusb			*hw;
 	struct usb_device		*dev = interface_to_usbdev(intf);
 	struct usb_host_interface	*iface = intf->cur_altsetting;

@@ -2100,20 +2100,28 @@ hfcsusb_probe(struct usb_interface *intf
 	if (!hw->ctrl_urb) {
 		pr_warn("%s: No memory for control urb\n",
 			driver_info->vend_name);
-		kfree(hw);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto err_free_hw;
 	}
 
 	pr_info("%s: %s: detected \"%s\" (%s, if=%d alt=%d)\n",
 		hw->name, __func__, driver_info->vend_name,
 		conf_str[small_match], ifnum, alt_used);
 
-	if (setup_instance(hw, dev->dev.parent))
-		return -EIO;
+	if (setup_instance(hw, dev->dev.parent)) {
+		err = -EIO;
+		goto err_free_urb;
+	}
 
 	hw->intf = intf;
 	usb_set_intfdata(hw->intf, hw);
 	return 0;
+
+err_free_urb:
+	usb_free_urb(hw->ctrl_urb);
+err_free_hw:
+	kfree(hw);
+	return err;
 }
 
 /* function called when an active device is removed */

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

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

From: Arnd Bergmann <[email protected]>

commit 6e8d96909a23c8078ee965bd48bb31cbef2de943 upstream.

Unifying the asm-generic headers across 32-bit and 64-bit architectures based on the compiler provided macros was a good idea and appears to work with all user space, but it caused a regression when building old kernels on systems that have the new headers installed in /usr/include, as this combination trips an inconsistency in the kernel's own tools/include headers that are a mix of userspace and kernel-internal headers.

This affects kernel builds on arm64, riscv64 and loongarch64 systems that might end up using the "#define __BITS_PER_LONG 32" default from the old tools headers. Backporting the commit into stable kernels would address this, but it would still break building kernels without that backport, and waste time for developers trying to understand the problem.

arm64 build machines are rather common, and on riscv64 this can also happen in practice, but loongarch64 is probably new enough to not be used much for building old kernels, so only revert the bits for arm64 and riscv.

---
 arch/arm64/include/uapi/asm/bitsperlong.h       |   24 ++++++++++++++++++++++++
 arch/riscv/include/uapi/asm/bitsperlong.h       |   14 ++++++++++++++
 tools/arch/arm64/include/uapi/asm/bitsperlong.h |   24 ++++++++++++++++++++++++
 tools/arch/riscv/include/uapi/asm/bitsperlong.h |   14 ++++++++++++++
 4 files changed, 76 insertions(+)
 create mode 100644 arch/arm64/include/uapi/asm/bitsperlong.h
 create mode 100644 arch/riscv/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/arm64/include/uapi/asm/bitsperlong.h
 create mode 100644 tools/arch/riscv/include/uapi/asm/bitsperlong.h

@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_BITSPERLONG_H
+#define __ASM_BITSPERLONG_H
+
+#define __BITS_PER_LONG 64
+
+#include <asm-generic/bitsperlong.h>
+
+#endif	/* __ASM_BITSPERLONG_H */

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ */
+
+#ifndef _UAPI_ASM_RISCV_BITSPERLONG_H
+#define _UAPI_ASM_RISCV_BITSPERLONG_H
+
+#define __BITS_PER_LONG (__SIZEOF_POINTER__ * 8)
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* _UAPI_ASM_RISCV_BITSPERLONG_H */

@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_BITSPERLONG_H
+#define __ASM_BITSPERLONG_H
+
+#define __BITS_PER_LONG 64
+
+#include <asm-generic/bitsperlong.h>
+
+#endif	/* __ASM_BITSPERLONG_H */

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2015 Regents of the University of California
+ */
+
+#ifndef _UAPI_ASM_RISCV_BITSPERLONG_H
+#define _UAPI_ASM_RISCV_BITSPERLONG_H
+
+#define __BITS_PER_LONG (__SIZEOF_POINTER__ * 8)
+
+#include <asm-generic/bitsperlong.h>
+
+#endif /* _UAPI_ASM_RISCV_BITSPERLONG_H */

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

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

From: Maher Sanalla <[email protected]>

commit e3e01c1c15986f9531b854634eec8381e72cb605 upstream.

In the cited commit, shared buffer updates were added whenever port buffer gets updated.

However, in case the shared buffer update fails, exiting early from port_set_buffer() is performed without freeing previously-allocated memory.

Fix it by jumping to out label where memory is freed before returning with error.

---
 drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -325,11 +325,11 @@ static int port_set_buffer(struct mlx5e_
 	err = port_update_shared_buffer(priv->mdev, current_headroom_size,
 					new_headroom_size);
 	if (err)
-		return err;
+		goto out;
 
 	err = port_update_pool_cfg(priv->mdev, port_buffer);
 	if (err)
-		return err;
+		goto out;
 
 	err = mlx5e_port_set_pbmc(mdev, in);
 out:

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

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

From: Pedro Tammela <[email protected]>

commit fb07390463c95e6eef254044d6dde050bfb9807a upstream.

Smatch reports that 'ci' can be used uninitialized.
The current code ignores errno coming from tcf_idr_check_alloc, which will lead to the incorrect usage of 'ci'. Handle the errno as it should.

---
 net/sched/act_connmark.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -156,6 +156,9 @@ static int tcf_connmark_init(struct net
 		nparms->zone = parm->zone;
 
 		ret = 0;
+	} else {
+		err = ret;
+		goto out_free;
 	}
 
 	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);

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

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

From: Maher Sanalla <[email protected]>

commit 623efc4cbd6115db36716e31037cb6d1f3ce6754 upstream.

The shared buffer pools configuration which are stored in the SBCM register are updated when the user changes the prio2buffer mapping.

However, in case the user desired prio2buffer change is invalid, which can occur due to mapping a lossless priority to a not large enough buffer, the SBCM update should not be performed, as the user command is failed.

Thus, Perform the SBCM update only after xoff threshold calculation is performed and the user prio2buffer mapping is validated.

---
 drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -443,11 +443,11 @@ static int update_buffer_lossy(struct ml
 	}
 
 	if (changed) {
-		err = port_update_pool_cfg(mdev, port_buffer);
+		err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz);
 		if (err)
 			return err;
 
-		err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz);
+		err = port_update_pool_cfg(mdev, port_buffer);
 		if (err)
 			return err;
 

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

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

From: Armen Ratner <[email protected]>

commit 8b0587a885fdb34fd6090a3f8625cb7ac1444826 upstream.

When port buffer headroom changes, port_update_shared_buffer() recalculates the shared buffer size and splits it in a 3:1 ratio (lossy:lossless) - Currently, the calculation is:
lossless = shared / 4;
lossy = (shared / 4) * 3;

Meaning, the calculation dropped the remainder of shared % 4 due to integer division, unintentionally reducing the total shared buffer by up to three cells on each update. Over time, this could shrink the buffer below usable size.

Fix it by changing the calculation to:
lossless = shared / 4;
lossy = shared - lossless;

This retains all buffer cells while still approximating the intended 3:1 split, preventing capacity loss over time.

While at it, perform headroom calculations in units of cells rather than in bytes for more accurate calculations avoiding extra divisions.

---
 drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c |   18 ++++++---------
 1 file changed, 8 insertions(+), 10 deletions(-)

@@ -272,8 +272,8 @@ static int port_update_shared_buffer(str
 	/* Total shared buffer size is split in a ratio of 3:1 between
 	 * lossy and lossless pools respectively.
 	 */
-	lossy_epool_size = (shared_buffer_size / 4) * 3;
 	lossless_ipool_size = shared_buffer_size / 4;
+	lossy_epool_size    = shared_buffer_size - lossless_ipool_size;
 
 	mlx5e_port_set_sbpr(mdev, 0, MLX5_EGRESS_DIR, MLX5_LOSSY_POOL, 0,
 			    lossy_epool_size);

@@ -288,14 +288,12 @@ static int port_set_buffer(struct mlx5e_
 	u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int sz = MLX5_ST_SZ_BYTES(pbmc_reg);
-	u32 new_headroom_size = 0;
-	u32 current_headroom_size;
+	u32 current_headroom_cells = 0;
+	u32 new_headroom_cells = 0;
 	void *in;
 	int err;
 	int i;
 
-	current_headroom_size = port_buffer->headroom_size;
-
 	in = kzalloc(sz, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;

@@ -306,12 +304,14 @@ static int port_set_buffer(struct mlx5e_
 
 	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]);
+		current_headroom_cells += MLX5_GET(bufferx_reg, buffer, size);
+
 		u64 size = port_buffer->buffer[i].size;
 		u64 xoff = port_buffer->buffer[i].xoff;
 		u64 xon = port_buffer->buffer[i].xon;
 
-		new_headroom_size += size;
 		do_div(size, port_buff_cell_sz);
+		new_headroom_cells += size;
 		do_div(xoff, port_buff_cell_sz);
 		do_div(xon, port_buff_cell_sz);
 		MLX5_SET(bufferx_reg, buffer, size, size);

@@ -320,10 +320,8 @@ static int port_set_buffer(struct mlx5e_
 		MLX5_SET(bufferx_reg, buffer, xon_threshold, xon);
 	}
 
-	new_headroom_size /= port_buff_cell_sz;
-	current_headroom_size /= port_buff_cell_sz;
-	err = port_update_shared_buffer(priv->mdev, current_headroom_size,
-					new_headroom_size);
+	err = port_update_shared_buffer(priv->mdev, current_headroom_cells,
+					new_headroom_cells);
 	if (err)
 		goto out;
 

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

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

From: Yipeng Zou <[email protected]>

commit 20739af07383e6eb1ec59dcd70b72ebfa9ac362c upstream.

There is a race condition between timer_shutdown_sync() and timer expiration that can lead to hitting a WARN_ON in expire_timers().

The issue occurs when timer_shutdown_sync() clears the timer function to NULL while the timer is still running on another CPU. The race scenario looks like this:

CPU0 CPU1

					<SOFTIRQ>
					lock_timer_base()
					expire_timers()
					base->running_timer = timer;
					unlock_timer_base()
					[call_timer_fn enter]
					mod_timer()
					...

timer_shutdown_sync()
lock_timer_base()
// For now, will not detach the timer but only clear its function to NULL if (base->running_timer != timer)

	ret = detach_if_pending(timer, base, true);
if (shutdown)
	timer->function = NULL;
unlock_timer_base()
					[call_timer_fn exit]
					lock_timer_base()
					base->running_timer = NULL;
					unlock_timer_base()
					...
					// Now timer is pending while its function set to NULL.
					// next timer trigger
					<SOFTIRQ>
					expire_timers()
					WARN_ON_ONCE(!fn) // hit
					...
lock_timer_base()
// Now timer will detach
if (base->running_timer != timer)
	ret = detach_if_pending(timer, base, true);
if (shutdown)
	timer->function = NULL;

unlock_timer_base()

The problem is that timer_shutdown_sync() clears the timer function regardless of whether the timer is currently running. This can leave a pending timer with a NULL function pointer, which triggers the WARN_ON_ONCE(!fn) check in expire_timers().

Fix this by only clearing the timer function when actually detaching the timer. If the timer is running, leave the function pointer intact, which is safe because the timer will be properly detached when it finishes running.

---
 kernel/time/timer.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

@@ -1413,10 +1413,11 @@ static int __try_to_del_timer_sync(struc
 
 	base = lock_timer_base(timer, &flags);
 
-	if (base->running_timer != timer)
+	if (base->running_timer != timer) {
 		ret = detach_if_pending(timer, base, true);
-	if (shutdown)
-		timer->function = NULL;
+		if (shutdown)
+			timer->function = NULL;
+	}
 
 	raw_spin_unlock_irqrestore(&base->lock, flags);
 

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

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

From: Zhang Heng <[email protected]>

commit beab067dbcff642243291fd528355d64c41dc3b2 upstream.

Based on available evidence, the USB ID 4c4a:4155 used by multiple devices has been attributed to Jieli. The commit 1a8953f4f774 ("HID: Add IGNORE quirk for SMARTLINKTECHNOLOGY") affected touchscreen functionality. Added checks for manufacturer and serial number to maintain microphone compatibility, enabling both devices to function properly.

---
 drivers/hid/hid-ids.h    |    4 ++--
 drivers/hid/hid-quirks.c |   13 ++++++++++++-
 2 files changed, 14 insertions(+), 3 deletions(-)

@@ -1460,7 +1460,7 @@
 #define USB_VENDOR_ID_SIGNOTEC			0x2133
 #define USB_DEVICE_ID_SIGNOTEC_VIEWSONIC_PD1011	0x0018
 
-#define USB_VENDOR_ID_SMARTLINKTECHNOLOGY              0x4c4a
-#define USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155         0x4155
+#define USB_VENDOR_ID_JIELI_SDK_DEFAULT		0x4c4a
+#define USB_DEVICE_ID_JIELI_SDK_4155		0x4155
 
 #endif

@@ -888,7 +888,6 @@ static const struct hid_device_id hid_ig
 #endif
 	{ HID_USB_DEVICE(USB_VENDOR_ID_YEALINK, USB_DEVICE_ID_YEALINK_P1K_P4K_B2K) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_HP_5MP_CAMERA_5473) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_SMARTLINKTECHNOLOGY, USB_DEVICE_ID_SMARTLINKTECHNOLOGY_4155) },
 	{ }
 };
 

@@ -1045,6 +1044,18 @@ bool hid_ignore(struct hid_device *hdev)
 					     strlen(elan_acpi_id[i].id)))
 					return true;
 		break;
+	case USB_VENDOR_ID_JIELI_SDK_DEFAULT:
+		/*
+		 * Multiple USB devices with identical IDs (mic & touchscreen).
+		 * The touch screen requires hid core processing, but the
+		 * microphone does not. They can be distinguished by manufacturer
+		 * and serial number.
+		 */
+		if (hdev->product == USB_DEVICE_ID_JIELI_SDK_4155 &&
+		    strncmp(hdev->name, "SmartlinkTechnology", 19) == 0 &&
+		    strncmp(hdev->uniq, "20201111000001", 14) == 0)
+			return true;
+		break;
 	}
 
 	if (hdev->type == HID_TYPE_USBMOUSE &&

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

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

From: Niravkumar L Rabara <[email protected]>

commit 5c56bf214af85ca042bf97f8584aab2151035840 upstream.

The DMA device pointer dma_dev was being dereferenced before ensuring that cdns_ctrl->dmac is properly initialized.

Move the assignment of dma_dev after successfully acquiring the DMA channel to ensure the pointer is valid before use.

---
 drivers/mtd/nand/raw/cadence-nand-controller.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -2830,7 +2830,7 @@ cadence_nand_irq_cleanup(int irqnum, str
 static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 {
 	dma_cap_mask_t mask;
-	struct dma_device *dma_dev = cdns_ctrl->dmac->device;
+	struct dma_device *dma_dev;
 	int ret;
 
 	cdns_ctrl->cdma_desc = dma_alloc_coherent(cdns_ctrl->dev,

@@ -2874,6 +2874,7 @@ static int cadence_nand_init(struct cdns
 		}
 	}
 
+	dma_dev = cdns_ctrl->dmac->device;
 	cdns_ctrl->io.iova_dma = dma_map_resource(dma_dev->dev, cdns_ctrl->io.dma,
 						  cdns_ctrl->io.size,
 						  DMA_BIDIRECTIONAL, 0);

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

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

From: Dan Carpenter <[email protected]>

commit e4185bed738da755b191aa3f2e16e8b48450e1b8 upstream.

The "req.start" and "req.len" variables are u64 values that come from the user at the start of the function. We mask away the high 32 bits of "req.len" so that's capped at U32_MAX but the "req.start" variable can go up to U64_MAX which means that the addition can still integer overflow.

Use check_add_overflow() to fix this bug.

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

@@ -599,6 +599,7 @@ mtdchar_write_ioctl(struct mtd_info *mtd
 	uint8_t *datbuf = NULL, *oobbuf = NULL;
 	size_t datbuf_len, oobbuf_len;
 	int ret = 0;
+	u64 end;
 
 	if (copy_from_user(&req, argp, sizeof(req)))
 		return -EFAULT;

@@ -618,7 +619,7 @@ mtdchar_write_ioctl(struct mtd_info *mtd
 	req.len &= 0xffffffff;
 	req.ooblen &= 0xffffffff;
 
-	if (req.start + req.len > mtd->size)
+	if (check_add_overflow(req.start, req.len, &end) || end > mtd->size)
 		return -EINVAL;
 
 	datbuf_len = min_t(size_t, req.len, mtd->erasesize);

@@ -698,6 +699,7 @@ mtdchar_read_ioctl(struct mtd_info *mtd,
 	size_t datbuf_len, oobbuf_len;
 	size_t orig_len, orig_ooblen;
 	int ret = 0;
+	u64 end;
 
 	if (copy_from_user(&req, argp, sizeof(req)))
 		return -EFAULT;

@@ -724,7 +726,7 @@ mtdchar_read_ioctl(struct mtd_info *mtd,
 	req.len &= 0xffffffff;
 	req.ooblen &= 0xffffffff;
 
-	if (req.start + req.len > mtd->size) {
+	if (check_add_overflow(req.start, req.len, &end) || end > mtd->size) {
 		ret = -EINVAL;
 		goto out;
 	}

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

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

From: Yongpeng Yang <[email protected]>

commit f2c1f631630e01821fe4c3fdf6077bc7a8284f82 upstream.

sb_min_blocksize() may return 0. Check its return value to avoid accessing the filesystem super block when sb->s_blocksize is 0.

---
 fs/exfat/super.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -425,7 +425,10 @@ static int exfat_read_boot_sector(struct
 	struct exfat_sb_info *sbi = EXFAT_SB(sb);
 
 	/* set block size to read super block */
-	sb_min_blocksize(sb, 512);
+	if (!sb_min_blocksize(sb, 512)) {
+		exfat_err(sb, "unable to set blocksize");
+		return -EINVAL;
+	}
 
 	/* read boot sector */
 	sbi->boot_bh = sb_bread(sb, 0);

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

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

From: Jiayuan Chen <[email protected]>

commit fbade4bd08ba52cbc74a71c4e86e736f059f99f7 upstream.

The sockmap feature allows bpf syscall from userspace, or based on bpf sockops, replacing the sk_prot of sockets during protocol stack processing with sockmap's custom read/write interfaces.
'''
tcp_rcv_state_process()
subflow_syn_recv_sock()

    tcp_init_transfer(BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB)
      bpf_skops_established       <== sockops
        bpf_sock_map_update(sk)   <== call bpf helper
          tcp_bpf_update_proto()  <== update sk_prot

'''
Consider two scenarios:

1. When the server has MPTCP enabled and the client also requests MPTCP, the sk passed to the BPF program is a subflow sk. Since subflows only handle partial data, replacing their sk_prot is meaningless and will cause traffic disruption.

2. When the server has MPTCP enabled but the client sends a TCP SYN without MPTCP, subflow_syn_recv_sock() performs a fallback on the subflow, replacing the subflow sk's sk_prot with the native sk_prot. '''
subflow_ulp_fallback()
subflow_drop_ctx()
mptcp_subflow_ops_undo_override()
'''
Subsequently, accept::mptcp_stream_accept::mptcp_fallback_tcp_ops() converts the subflow to plain TCP.

For the first case, we should prevent it from being combined with sockmap by setting sk_prot->psock_update_sk_prot to NULL, which will be blocked by sockmap's own flow.

For the second case, since subflow_syn_recv_sock() has already restored sk_prot to native tcp_prot/tcpv6_prot, no further action is needed.

---
 net/mptcp/subflow.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -1997,6 +1997,10 @@ void __init mptcp_subflow_init(void)
 	tcp_prot_override = tcp_prot;
 	tcp_prot_override.release_cb = tcp_release_cb_override;
 	tcp_prot_override.diag_destroy = tcp_abort_override;
+#ifdef CONFIG_BPF_SYSCALL
+	/* Disable sockmap processing for subflows */
+	tcp_prot_override.psock_update_sk_prot = NULL;
+#endif
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	/* In struct mptcp_subflow_request_sock, we assume the TCP request sock

@@ -2033,6 +2037,10 @@ void __init mptcp_subflow_init(void)
 	tcpv6_prot_override = tcpv6_prot;
 	tcpv6_prot_override.release_cb = tcp_release_cb_override;
 	tcpv6_prot_override.diag_destroy = tcp_abort_override;
+#ifdef CONFIG_BPF_SYSCALL
+	/* Disable sockmap processing for subflows */
+	tcpv6_prot_override.psock_update_sk_prot = NULL;
+#endif
 #endif
 
 	mptcp_diag_subflow_init(&subflow_ulp_ops);

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

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

From: Yihang Li <[email protected]>

commit b32cc17d607e8ae7af037303fe101368cb4dc44c upstream.

Call scsi_device_put() in ata_scsi_dev_rescan() if the device or its queue are not running.

---
 drivers/ata/libata-scsi.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -4683,8 +4683,10 @@ void ata_scsi_dev_rescan(struct work_str
 			spin_unlock_irqrestore(ap->lock, flags);
 			if (do_resume) {
 				ret = scsi_resume_device(sdev);
-				if (ret == -EWOULDBLOCK)
+				if (ret == -EWOULDBLOCK) {
+					scsi_device_put(sdev);
 					goto unlock_scan;
+				}
 				dev->flags &= ~ATA_DFLAG_RESUMING;
 			}
 			ret = scsi_rescan_device(sdev);

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

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

From: Andrey Vatoropin <[email protected]>

commit 7d277a7a58578dd62fd546ddaef459ec24ccae36 upstream.

be_insert_vlan_in_pkt() is called with the wrb_params argument being NULL at be_send_pkt_to_bmc() call site.  This may lead to dereferencing a NULL pointer when processing a workaround for specific packet, as commit bc0c3405abbb ("be2net: fix a Tx stall bug caused by a specific ipv6 packet") states.

The correct way would be to pass the wrb_params from be_xmit().

---
 drivers/net/ethernet/emulex/benet/be_main.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

@@ -1297,7 +1297,8 @@ static void be_xmit_flush(struct be_adap
 		(adapter->bmc_filt_mask & BMC_FILT_MULTICAST)
 
 static bool be_send_pkt_to_bmc(struct be_adapter *adapter,
-			       struct sk_buff **skb)
+			       struct sk_buff **skb,
+			       struct be_wrb_params *wrb_params)
 {
 	struct ethhdr *eh = (struct ethhdr *)(*skb)->data;
 	bool os2bmc = false;

@@ -1361,7 +1362,7 @@ done:
 	 * to BMC, asic expects the vlan to be inline in the packet.
 	 */
 	if (os2bmc)
-		*skb = be_insert_vlan_in_pkt(adapter, *skb, NULL);
+		*skb = be_insert_vlan_in_pkt(adapter, *skb, wrb_params);
 
 	return os2bmc;
 }

@@ -1388,7 +1389,7 @@ static netdev_tx_t be_xmit(struct sk_buf
 	/* if os2bmc is enabled and if the pkt is destined to bmc,
 	 * enqueue the pkt a 2nd time with mgmt bit set.
 	 */
-	if (be_send_pkt_to_bmc(adapter, &skb)) {
+	if (be_send_pkt_to_bmc(adapter, &skb, &wrb_params)) {
 		BE_WRB_F_SET(wrb_params.features, OS2BMC, 1);
 		wrb_cnt = be_xmit_enqueue(adapter, txo, skb, &wrb_params);
 		if (unlikely(!wrb_cnt))

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

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

From: Oleksij Rempel <[email protected]>

commit 3ceb6ac2116ecda1c5d779bb73271479e70fccb4 upstream.

Correct RGMII delay application logic in lan937x_set_tune_adj().

The function was missing data16 &= ~PORT_TUNE_ADJ before setting the new delay value. This caused the new value to be bitwise-OR'd with the existing PORT_TUNE_ADJ field instead of replacing it.

For example, when setting the RGMII 2 TX delay on port 4, the intended TUNE_ADJUST value of 0 (RGMII_2_TX_DELAY_2NS) was incorrectly OR'd with the default 0x1B (from register value 0xDA3), leaving the delay at the wrong setting.

This patch adds the missing mask to clear the field, ensuring the correct delay value is written. Physical measurements on the RGMII TX lines confirm the fix, showing the delay changing from ~1ns (before change) to ~2ns.

While testing on i.MX 8MP showed this was within the platform's timing tolerance, it did not match the intended hardware-characterized value.

---
 drivers/net/dsa/microchip/lan937x_main.c |    1 +
 1 file changed, 1 insertion(+)

@@ -328,6 +328,7 @@ static void lan937x_set_tune_adj(struct
 	ksz_pread16(dev, port, reg, &data16);
 
 	/* Update tune Adjust */
+	data16 &= ~PORT_TUNE_ADJ;
 	data16 |= FIELD_PREP(PORT_TUNE_ADJ, val);
 	ksz_pwrite16(dev, port, reg, data16);
 

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

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

From: Tzung-Bi Shih <[email protected]>

commit e08969c4d65ac31297fcb4d31d4808c789152f68 upstream.

If cros_ec_keyb_register_matrix() isn't called (due to buttons_switches_only) in cros_ec_keyb_probe(), ckdev->idev remains NULL. An invalid memory access is observed in cros_ec_keyb_process() when receiving an EC_MKBP_EVENT_KEY_MATRIX event in cros_ec_keyb_work() in such case.

  Unable to handle kernel read from unreadable memory at virtual address 0000000000000028
  ...
  x3 : 0000000000000000 x2 : 0000000000000000
  x1 : 0000000000000000 x0 : 0000000000000000
  Call trace:
  input_event
  cros_ec_keyb_work
  blocking_notifier_call_chain
  ec_irq_thread

It's still unknown about why the kernel receives such malformed event, in any cases, the kernel shouldn't access ckdev->idev and friends if the driver doesn't intend to initialize them.

---
 drivers/input/keyboard/cros_ec_keyb.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -248,6 +248,12 @@ static int cros_ec_keyb_work(struct noti
 	case EC_MKBP_EVENT_KEY_MATRIX:
 		pm_wakeup_event(ckdev->dev, 0);
 
+		if (!ckdev->idev) {
+			dev_warn_once(ckdev->dev,
+				      "Unexpected key matrix event\n");
+			return NOTIFY_OK;
+		}
+
 		if (ckdev->ec->event_size != ckdev->cols) {
 			dev_err(ckdev->dev,
 				"Discarded incomplete key matrix event.\n");

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

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

From: Dan Carpenter <[email protected]>

commit d83f1512758f4ef6fc5e83219fe7eeeb6b428ea4 upstream.

This is supposed to be "priv" but we accidentally pass "&priv" which is an address in the stack and so it will lead to memory corruption when the imx_sc_key_action() function is called. Remove the &.

---
 drivers/input/keyboard/imx_sc_key.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -158,7 +158,7 @@ static int imx_sc_key_probe(struct platf
 		return error;
 	}
 
-	error = devm_add_action_or_reset(&pdev->dev, imx_sc_key_action, &priv);
+	error = devm_add_action_or_reset(&pdev->dev, imx_sc_key_action, priv);
 	if (error)
 		return error;
 

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

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

From: Seungjin Bae <[email protected]>

commit 69aeb507312306f73495598a055293fa749d454e upstream.

In the pegasus_notetaker driver, the pegasus_probe() function allocates the URB transfer buffer using the wMaxPacketSize value from the endpoint descriptor. An attacker can use a malicious USB descriptor to force the allocation of a very small buffer.

Subsequently, if the device sends an interrupt packet with a specific pattern (e.g., where the first byte is 0x80 or 0x42),
the pegasus_parse_packet() function parses the packet without checking the allocated buffer size. This leads to an out-of-bounds memory access.

---
 drivers/input/tablet/pegasus_notetaker.c |    9 +++++++++
 1 file changed, 9 insertions(+)

@@ -63,6 +63,9 @@
 #define BUTTON_PRESSED			0xb5
 #define COMMAND_VERSION			0xa9
 
+/* 1 Status + 1 Color + 2 X + 2 Y = 6 bytes */
+#define NOTETAKER_PACKET_SIZE		6
+
 /* in xy data packet */
 #define BATTERY_NO_REPORT		0x40
 #define BATTERY_LOW			0x41

@@ -303,6 +306,12 @@ static int pegasus_probe(struct usb_inte
 	}
 
 	pegasus->data_len = usb_maxpacket(dev, pipe);
+	if (pegasus->data_len < NOTETAKER_PACKET_SIZE) {
+		dev_err(&intf->dev, "packet size is too small (%d)\n",
+			pegasus->data_len);
+		error = -EINVAL;
+		goto err_free_mem;
+	}
 
 	pegasus->data = usb_alloc_coherent(dev, pegasus->data_len, GFP_KERNEL,
 					   &pegasus->data_dma);

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

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

From: Ewan D. Milne <[email protected]>

commit 0a2c5495b6d1ecb0fa18ef6631450f391a888256 upstream.

nvme_fc_delete_assocation() waits for pending I/O to complete before returning, and an error can cause ->ioerr_work to be queued after cancel_work_sync() had been called. Move the call to cancel_work_sync() to be after nvme_fc_delete_association() to ensure ->ioerr_work is not running when the nvme_fc_ctrl object is freed. Otherwise the following can occur:

[ 1135.911754] list_del corruption, ff2d24c8093f31f8->next is NULL
[ 1135.917705] ------------[ cut here ]------------
[ 1135.922336] kernel BUG at lib/list_debug.c:52!
[ 1135.926784] Oops: invalid opcode: 0000 [#1] SMP NOPTI
[ 1135.931851] CPU: 48 UID: 0 PID: 726 Comm: kworker/u449:23 Kdump: loaded Not tainted 6.12.0 #1 PREEMPT(voluntary)
[ 1135.943490] Hardware name: Dell Inc. PowerEdge R660/0HGTK9, BIOS 2.5.4 01/16/2025
[ 1135.950969] Workqueue:  0x0 (nvme-wq)
[ 1135.954673] RIP: 0010:__list_del_entry_valid_or_report.cold+0xf/0x6f
[ 1135.961041] Code: c7 c7 98 68 72 94 e8 26 45 fe ff 0f 0b 48 c7 c7 70 68 72 94 e8 18 45 fe ff 0f 0b 48 89 fe 48 c7 c7 80 69 72 94 e8 07 45 fe ff <0f> 0b 48 89 d1 48 c7 c7 a0 6a 72 94 48 89 c2 e8 f3 44 fe ff 0f 0b
[ 1135.979788] RSP: 0018:ff579b19482d3e50 EFLAGS: 00010046
[ 1135.985015] RAX: 0000000000000033 RBX: ff2d24c8093f31f0 RCX: 0000000000000000
[ 1135.992148] RDX: 0000000000000000 RSI: ff2d24d6bfa1d0c0 RDI: ff2d24d6bfa1d0c0
[ 1135.999278] RBP: ff2d24c8093f31f8 R08: 0000000000000000 R09: ffffffff951e2b08
[ 1136.006413] R10: ffffffff95122ac8 R11: 0000000000000003 R12: ff2d24c78697c100
[ 1136.013546] R13: fffffffffffffff8 R14: 0000000000000000 R15: ff2d24c78697c0c0
[ 1136.020677] FS:  0000000000000000(0000) GS:ff2d24d6bfa00000(0000) knlGS:0000000000000000
[ 1136.028765] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1136.034510] CR2: 00007fd207f90b80 CR3: 000000163ea22003 CR4: 0000000000f73ef0
[ 1136.041641] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1136.048776] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400
[ 1136.055910] PKRU: 55555554
[ 1136.058623] Call Trace:
[ 1136.061074]  <TASK>
[ 1136.063179]  ? show_trace_log_lvl+0x1b0/0x2f0
[ 1136.067540]  ? show_trace_log_lvl+0x1b0/0x2f0
[ 1136.071898]  ? move_linked_works+0x4a/0xa0
[ 1136.075998]  ? __list_del_entry_valid_or_report.cold+0xf/0x6f
[ 1136.081744]  ? __die_body.cold+0x8/0x12
[ 1136.085584]  ? die+0x2e/0x50
[ 1136.088469]  ? do_trap+0xca/0x110
[ 1136.091789]  ? do_error_trap+0x65/0x80
[ 1136.095543]  ? __list_del_entry_valid_or_report.cold+0xf/0x6f
[ 1136.101289]  ? exc_invalid_op+0x50/0x70
[ 1136.105127]  ? __list_del_entry_valid_or_report.cold+0xf/0x6f
[ 1136.110874]  ? asm_exc_invalid_op+0x1a/0x20
[ 1136.115059]  ? __list_del_entry_valid_or_report.cold+0xf/0x6f
[ 1136.120806]  move_linked_works+0x4a/0xa0
[ 1136.124733]  worker_thread+0x216/0x3a0
[ 1136.128485]  ? __pfx_worker_thread+0x10/0x10
[ 1136.132758]  kthread+0xfa/0x240
[ 1136.135904]  ? __pfx_kthread+0x10/0x10
[ 1136.139657]  ret_from_fork+0x31/0x50
[ 1136.143236]  ? __pfx_kthread+0x10/0x10
[ 1136.146988]  ret_from_fork_asm+0x1a/0x30
[ 1136.150915]  </TASK>

---
 drivers/nvme/host/fc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -3262,7 +3262,6 @@ nvme_fc_delete_ctrl(struct nvme_ctrl *nc
 {
 	struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
 
-	cancel_work_sync(&ctrl->ioerr_work);
 	cancel_delayed_work_sync(&ctrl->connect_work);
 	/*
 	 * kill the association on the link side.  this will block

@@ -3333,6 +3332,7 @@ nvme_fc_reset_ctrl_work(struct work_stru
 
 	/* will block will waiting for io to terminate */
 	nvme_fc_delete_association(ctrl);
+	cancel_work_sync(&ctrl->ioerr_work);
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
 		dev_err(ctrl->ctrl.device,

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

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

From: Bart Van Assche <[email protected]>

commit 90449f2d1e1f020835cba5417234636937dd657e upstream.

sg_finish_rem_req() calls blk_rq_unmap_user(). The latter function may sleep. Hence, call sg_finish_rem_req() with interrupts enabled instead of disabled.

---
 drivers/scsi/sg.c |   10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

@@ -2204,9 +2204,17 @@ sg_remove_sfp_usercontext(struct work_st
 	write_lock_irqsave(&sfp->rq_list_lock, iflags);
 	while (!list_empty(&sfp->rq_list)) {
 		srp = list_first_entry(&sfp->rq_list, Sg_request, entry);
-		sg_finish_rem_req(srp);
 		list_del(&srp->entry);
+		write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
+
+		sg_finish_rem_req(srp);
+		/*
+		 * sg_rq_end_io() uses srp->parentfp. Hence, only clear
+		 * srp->parentfp after blk_mq_free_request() has been called.
+		 */
 		srp->parentfp = NULL;
+
+		write_lock_irqsave(&sfp->rq_list_lock, iflags);
 	}
 	write_unlock_irqrestore(&sfp->rq_list_lock, iflags);
 

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

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

From: Hamza Mahfooz <[email protected]>

commit e6965188f84a7883e6a0d3448e86b0cf29b24dfc upstream.

If the allocation of tl_hba->sh fails in tcm_loop_driver_probe() and we attempt to dereference it in tcm_loop_tpg_address_show() we will get a segfault, see below for an example. So, check tl_hba->sh before dereferencing it.

Unable to allocate struct scsi_host

  BUG: kernel NULL pointer dereference, address: 0000000000000194
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: 0000 [#1] PREEMPT SMP NOPTI
  CPU: 1 PID: 8356 Comm: tokio-runtime-w Not tainted 6.6.104.2-4.azl3 #1
  Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 09/28/2024
  RIP: 0010:tcm_loop_tpg_address_show+0x2e/0x50 [tcm_loop]
...
  Call Trace:
   <TASK>
   configfs_read_iter+0x12d/0x1d0 [configfs]
   vfs_read+0x1b5/0x300
   ksys_read+0x6f/0xf0

...

---
 drivers/target/loopback/tcm_loop.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -934,6 +934,9 @@ static ssize_t tcm_loop_tpg_address_show
 			struct tcm_loop_tpg, tl_se_tpg);
 	struct tcm_loop_hba *tl_hba = tl_tpg->tl_hba;
 
+	if (!tl_hba->sh)
+		return -ENODEV;
+
 	return snprintf(page, PAGE_SIZE, "%d:0:%d\n",
 			tl_hba->sh->host_no, tl_tpg->tl_tpgt);
 }

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

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

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

commit ebd729fef31620e0bf74cbf8a4c7fda73a2a4e7e upstream.

Fix a regression that has caused accesses to the PCI MMIO window to complete unclaimed in non-EVA configurations with the SOC-it family of system controllers, preventing PCI devices from working that use MMIO.

In the non-EVA case PHYS_OFFSET is set to 0, meaning that PCI_BAR0 is set with an empty mask (and PCI_HEAD4 matches addresses starting from 0 accordingly). Consequently all addresses are matched for incoming DMA accesses from PCI. This seems to confuse the system controller's logic and outgoing bus cycles targeting the PCI MMIO window seem not to make it to the intended devices.

This happens as well when a wider mask is used with PCI_BAR0, such as 0x80000000 or 0xe0000000, that makes addresses match that overlap with the PCI MMIO window, which starts at 0x10000000 in our configuration.

Set the mask in PCI_BAR0 to 0xf0000000 for non-EVA then, covering the non-EVA maximum 256 MiB of RAM, which is what YAMON does and which used to work correctly up to the offending commit. Set PCI_P2SCMSKL to match PCI_BAR0 as required by the system controller's specification, and match PCI_P2SCMAPL to PCI_HEAD4 for identity mapping.

Verified with:

Core board type/revision =      0x0d (Core74K) / 0x01
System controller/revision =    MIPS SOC-it 101 OCP / 1.3   SDR-FW-4:1
Processor Company ID/options =  0x01 (MIPS Technologies, Inc.) / 0x1c
Processor ID/revision =         0x97 (MIPS 74Kf) / 0x4c

for non-EVA and with:

Core board type/revision =      0x0c (CoreFPGA-5) / 0x00
System controller/revision =    MIPS ROC-it2 / 0.0   FW-1:1 (CLK_unknown) GIC
Processor Company ID/options =  0x01 (MIPS Technologies, Inc.) / 0x00
Processor ID/revision =         0xa0 (MIPS interAptiv UP) / 0x20

for EVA/non-EVA, fixing:

defxx 0000:00:12.0: assign IRQ: got 10
defxx: v1.12 2021/03/10 Lawrence V. Stefani and others 0000:00:12.0: Could not read adapter factory MAC address!

vs:

defxx 0000:00:12.0: assign IRQ: got 10
defxx: v1.12 2021/03/10 Lawrence V. Stefani and others
0000:00:12.0: DEFPA at MMIO addr = 0x10142000, IRQ = 10, Hardware addr = 00-00-f8-xx-xx-xx 0000:00:12.0: registered as fddi0

for non-EVA and causing no change for EVA.

---
 arch/mips/mti-malta/malta-init.c |   20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

@@ -241,16 +241,22 @@ mips_pci_controller:
 #endif
 
 		/*
-		 * Setup the Malta max (2GB) memory for PCI DMA in host bridge
-		 * in transparent addressing mode.
+		 * Set up memory mapping in host bridge for PCI DMA masters,
+		 * in transparent addressing mode.  For EVA use the Malta
+		 * maximum of 2 GiB memory in the alias space at 0x80000000
+		 * as per PHYS_OFFSET.  Otherwise use 256 MiB of memory in
+		 * the regular space, avoiding mapping the PCI MMIO window
+		 * for DMA as it seems to confuse the system controller's
+		 * logic, causing PCI MMIO to stop working.
 		 */
-		mask = PHYS_OFFSET | PCI_BASE_ADDRESS_MEM_PREFETCH;
-		MSC_WRITE(MSC01_PCI_BAR0, mask);
-		MSC_WRITE(MSC01_PCI_HEAD4, mask);
+		mask = PHYS_OFFSET ? PHYS_OFFSET : 0xf0000000;
+		MSC_WRITE(MSC01_PCI_BAR0,
+			  mask | PCI_BASE_ADDRESS_MEM_PREFETCH);
+		MSC_WRITE(MSC01_PCI_HEAD4,
+			  PHYS_OFFSET | PCI_BASE_ADDRESS_MEM_PREFETCH);
 
-		mask &= MSC01_PCI_BAR0_SIZE_MSK;
 		MSC_WRITE(MSC01_PCI_P2SCMSKL, mask);
-		MSC_WRITE(MSC01_PCI_P2SCMAPL, mask);
+		MSC_WRITE(MSC01_PCI_P2SCMAPL, PHYS_OFFSET);
 
 		/* Don't handle target retries indefinitely.  */
 		if ((data & MSC01_PCI_CFG_MAXRTRY_MSK) ==

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

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

From: Huacai Chen <[email protected]>

commit a6b533adfc05ba15360631e019d3e18275080275 upstream.

If there is no valid cache info detected (may happen in virtual machine) for pci_dfl_cache_line_size, kernel shouldn't panic. Because in the PCI core it will be evaluated to (L1_CACHE_BYTES >> 2).

---
 arch/loongarch/pci/pci.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -51,11 +51,11 @@ static int __init pcibios_init(void)
 	 */
 	lsize = cpu_last_level_cache_line_size();
 
-	BUG_ON(!lsize);
+	if (lsize) {
+		pci_dfl_cache_line_size = lsize >> 2;
 
-	pci_dfl_cache_line_size = lsize >> 2;
-
-	pr_debug("PCI: pci_cache_line_size set to %d bytes\n", lsize);
+		pr_debug("PCI: pci_cache_line_size set to %d bytes\n", lsize);
+	}
 
 	return 0;
 }

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

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

From: Eric Dumazet <[email protected]>

commit 035bca3f017ee9dea3a5a756e77a6f7138cc6eea upstream.

syzbot reported use-after-free in mptcp_schedule_work() [1]

Issue here is that mptcp_schedule_work() schedules a work, then gets a refcount on sk->sk_refcnt if the work was scheduled. This refcount will be released by mptcp_worker().

[A] if (schedule_work(...)) {

[B]     sock_hold(sk);
        return true;
    }

Problem is that mptcp_worker() can run immediately and complete before [B]

We need instead :

    sock_hold(sk);
    if (schedule_work(...))
        return true;
    sock_put(sk);

[1]
refcount_t: addition on 0; use-after-free.

 WARNING: CPU: 1 PID: 29 at lib/refcount.c:25 refcount_warn_saturate+0xfa/0x1d0 lib/refcount.c:25
Call Trace:
 <TASK>
 __refcount_add include/linux/refcount.h:-1 [inline]
  __refcount_inc include/linux/refcount.h:366 [inline]
  refcount_inc include/linux/refcount.h:383 [inline]
  sock_hold include/net/sock.h:816 [inline]
  mptcp_schedule_work+0x164/0x1a0 net/mptcp/protocol.c:943
  mptcp_tout_timer+0x21/0xa0 net/mptcp/protocol.c:2316
  call_timer_fn+0x17e/0x5f0 kernel/time/timer.c:1747
  expire_timers kernel/time/timer.c:1798 [inline]
  __run_timers kernel/time/timer.c:2372 [inline]
  __run_timer_base+0x648/0x970 kernel/time/timer.c:2384
  run_timer_base kernel/time/timer.c:2393 [inline]
  run_timer_softirq+0xb7/0x180 kernel/time/timer.c:2403
  handle_softirqs+0x22f/0x710 kernel/softirq.c:622
  __do_softirq kernel/softirq.c:656 [inline]
  run_ktimerd+0xcf/0x190 kernel/softirq.c:1138
  smpboot_thread_fn+0x542/0xa60 kernel/smpboot.c:160
  kthread+0x711/0x8a0 kernel/kthread.c:463
  ret_from_fork+0x4bc/0x870 arch/x86/kernel/process.c:158
  ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245

---
 net/mptcp/protocol.c |   19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

@@ -966,14 +966,19 @@ static void mptcp_reset_rtx_timer(struct
 
 bool mptcp_schedule_work(struct sock *sk)
 {
-	if (inet_sk_state_load(sk) != TCP_CLOSE &&
-	    schedule_work(&mptcp_sk(sk)->work)) {
-		/* each subflow already holds a reference to the sk, and the
-		 * workqueue is invoked by a subflow, so sk can't go away here.
-		 */
-		sock_hold(sk);
+	if (inet_sk_state_load(sk) == TCP_CLOSE)
+		return false;
+
+	/* Get a reference on this socket, mptcp_worker() will release it.
+	 * As mptcp_worker() might complete before us, we can not avoid
+	 * a sock_hold()/sock_put() if schedule_work() returns false.
+	 */
+	sock_hold(sk);
+
+	if (schedule_work(&mptcp_sk(sk)->work))
 		return true;
-	}
+
+	sock_put(sk);
 	return false;
 }
 

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

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

From: Paolo Abeni <[email protected]>

commit 5e15395f6d9ec07395866c5511f4b4ac566c0c9b upstream.

mptcp_cleanup_rbuf() needs to know the last most recent, mptcp-level rcv_wnd sent, and such information is tracked into the msk->old_wspace field, updated at ack transmission time by mptcp_write_options().

Fallback socket do not add any mptcp options, such helper is never invoked, and msk->old_wspace value remain stale. That in turn makes ack generation at recvmsg() time quite random.

Address the issue ensuring mptcp_write_options() is invoked even for fallback sockets, and just update the needed info in such a case.

The issue went unnoticed for a long time, as mptcp currently overshots the fallback socket receive buffer autotune significantly. It is going to change in the near future.

---
 net/mptcp/options.c |   23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

@@ -834,8 +834,11 @@ bool mptcp_established_options(struct so
 
 	opts->suboptions = 0;
 
+	/* Force later mptcp_write_options(), but do not use any actual
+	 * option space.
+	 */
 	if (unlikely(__mptcp_check_fallback(msk) && !mptcp_check_infinite_map(skb)))
-		return false;
+		return true;
 
 	if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {
 		if (mptcp_established_options_fastclose(sk, &opt_size, remaining, opts) ||

@@ -1296,6 +1299,20 @@ update_wspace:
 	WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
 }
 
+static void mptcp_track_rwin(struct tcp_sock *tp)
+{
+	const struct sock *ssk = (const struct sock *)tp;
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk;
+
+	if (!ssk)
+		return;
+
+	subflow = mptcp_subflow_ctx(ssk);
+	msk = mptcp_sk(subflow->conn);
+	WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
+}
+
 __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
 {
 	struct csum_pseudo_header header;

@@ -1588,6 +1605,10 @@ mp_rst:
 				      opts->reset_transient,
 				      opts->reset_reason);
 		return;
+	} else if (unlikely(!opts->suboptions)) {
+		/* Fallback to TCP */
+		mptcp_track_rwin(tp);
+		return;
 	}
 
 	if (OPTION_MPTCP_PRIO & opts->suboptions) {

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

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

From: Paolo Abeni <[email protected]>

commit 17393fa7b7086664be519e7230cb6ed7ec7d9462 upstream.

I'm observing very frequent self-tests failures in case of fallback when running on a CONFIG_PREEMPT kernel.

The root cause is that subflow_sched_work_if_closed() closes any subflow as soon as it is half-closed and has no incoming data pending.

That works well for regular subflows - MPTCP needs bi-directional connectivity to operate on a given subflow - but for fallback socket is race prone.

When TCP peer closes the connection before the MPTCP one, subflow_sched_work_if_closed() will schedule the MPTCP worker to gracefully close the subflow, and shortly after will do another schedule to inject and process a dummy incoming DATA_FIN.

On CONFIG_PREEMPT kernel, the MPTCP worker can kick-in and close the fallback subflow before subflow_sched_work_if_closed() is able to create the dummy DATA_FIN, unexpectedly interrupting the transfer.

Address the issue explicitly avoiding closing fallback subflows on when the peer is only half-closed.

Note that, when the subflow is able to create the DATA_FIN before the worker invocation, the worker will change the msk state before trying to close the subflow and will skip the latter operation as the msk will not match anymore the precondition in __mptcp_close_subflow().

---
 net/mptcp/protocol.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -2598,7 +2598,8 @@ static void __mptcp_close_subflow(struct
 
 		if (ssk_state != TCP_CLOSE &&
 		    (ssk_state != TCP_CLOSE_WAIT ||
-		     inet_sk_state_load(sk) != TCP_ESTABLISHED))
+		     inet_sk_state_load(sk) != TCP_ESTABLISHED ||
+		     __mptcp_check_fallback(msk)))
 			continue;
 
 		/* 'subflow_data_ready' will re-sched once rx queue is empty */

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

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

From: Paolo Abeni <[email protected]>

commit 4f102d747cadd8f595f2b25882eed9bec1675fb1 upstream.

The rcv window is shared among all the subflows. Currently, MPTCP sync the TCP-level rcv window with the MPTCP one at tcp_transmit_skb() time.

The above means that incoming data may sporadically observe outdated TCP-level rcv window and being wrongly dropped by TCP.

Address the issue checking for the edge condition before queuing the data at TCP level, and eventually syncing the rcv window as needed.

Note that the issue is actually present from the very first MPTCP implementation, but backports older than the blamed commit below will range from impossible to useless.

Before:

  $ nstat -n; sleep 1; nstat -z TcpExtBeyondWindow
  TcpExtBeyondWindow              14                 0.0

After:

  $ nstat -n; sleep 1; nstat -z TcpExtBeyondWindow
  TcpExtBeyondWindow              0                  0.0

---
 net/mptcp/options.c  |   31 +++++++++++++++++++++++++++++++
 net/mptcp/protocol.h |    1 +
 2 files changed, 32 insertions(+)

@@ -1028,6 +1028,31 @@ u64 __mptcp_expand_seq(u64 old_seq, u64
 	return cur_seq;
 }
 
+static void rwin_update(struct mptcp_sock *msk, struct sock *ssk,
+			struct sk_buff *skb)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct tcp_sock *tp = tcp_sk(ssk);
+	u64 mptcp_rcv_wnd;
+
+	/* Avoid touching extra cachelines if TCP is going to accept this
+	 * skb without filling the TCP-level window even with a possibly
+	 * outdated mptcp-level rwin.
+	 */
+	if (!skb->len || skb->len < tcp_receive_window(tp))
+		return;
+
+	mptcp_rcv_wnd = atomic64_read(&msk->rcv_wnd_sent);
+	if (!after64(mptcp_rcv_wnd, subflow->rcv_wnd_sent))
+		return;
+
+	/* Some other subflow grew the mptcp-level rwin since rcv_wup,
+	 * resync.
+	 */
+	tp->rcv_wnd += mptcp_rcv_wnd - subflow->rcv_wnd_sent;
+	subflow->rcv_wnd_sent = mptcp_rcv_wnd;
+}
+
 static void ack_update_msk(struct mptcp_sock *msk,
 			   struct sock *ssk,
 			   struct mptcp_options_received *mp_opt)

@@ -1188,6 +1213,7 @@ bool mptcp_incoming_options(struct sock
 	 */
 	if (mp_opt.use_ack)
 		ack_update_msk(msk, sk, &mp_opt);
+	rwin_update(msk, sk, skb);
 
 	/* Zero-data-length packets are dropped by the caller and not
 	 * propagated to the MPTCP layer, so the skb extension does not

@@ -1274,6 +1300,10 @@ static void mptcp_set_rwin(struct tcp_so
 
 	if (rcv_wnd_new != rcv_wnd_old) {
 raise_win:
+		/* The msk-level rcv wnd is after the tcp level one,
+		 * sync the latter.
+		 */
+		rcv_wnd_new = rcv_wnd_old;
 		win = rcv_wnd_old - ack_seq;
 		tp->rcv_wnd = min_t(u64, win, U32_MAX);
 		new_win = tp->rcv_wnd;

@@ -1297,6 +1327,7 @@ raise_win:
 
 update_wspace:
 	WRITE_ONCE(msk->old_wspace, tp->rcv_wnd);
+	subflow->rcv_wnd_sent = rcv_wnd_new;
 }
 
 static void mptcp_track_rwin(struct tcp_sock *tp)

@@ -458,6 +458,7 @@ struct mptcp_subflow_context {
 	u64	remote_key;
 	u64	idsn;
 	u64	map_seq;
+	u64	rcv_wnd_sent;
 	u32	snd_isn;
 	u32	token;
 	u32	rel_write_seq;

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

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

From: Paolo Abeni <[email protected]>

commit 1bba3f219c5e8c29e63afa3c1fc24f875ebec119 upstream.

In case of DSS corruption, the MPTCP protocol tries to avoid the subflow reset if fallback is possible. Such corruptions happen in the receive path; to ensure fallback is possible the stack additionally needs to check for OoO data, otherwise the fallback will break the data stream.

---
 net/mptcp/protocol.c |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -911,6 +911,13 @@ static bool __mptcp_finish_join(struct m
 	if (sk->sk_state != TCP_ESTABLISHED)
 		return false;
 
+	/* The caller possibly is not holding the msk socket lock, but
+	 * in the fallback case only the current subflow is touching
+	 * the OoO queue.
+	 */
+	if (!RB_EMPTY_ROOT(&msk->out_of_order_queue))
+		return false;
+
 	spin_lock_bh(&msk->fallback_lock);
 	if (!msk->allow_subflows) {
 		spin_unlock_bh(&msk->fallback_lock);

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

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

From: Ma Ke <[email protected]>

commit 4c5376b4b143c4834ebd392aef2215847752b16a upstream.

driver_find_device() calls get_device() to increment the reference count once a matching device is found, but there is no put_device() to balance the reference count. To avoid reference count leakage, add put_device() to decrease the reference count.

Found by code review.

---
 drivers/gpu/drm/tegra/dc.c |    1 +
 1 file changed, 1 insertion(+)

@@ -3141,6 +3141,7 @@ static int tegra_dc_couple(struct tegra_
 		dc->client.parent = &parent->client;
 
 		dev_dbg(dc->dev, "coupled to %s\n", dev_name(companion));
+		put_device(companion);
 	}
 
 	return 0;

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

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

From: Yifan Zha <[email protected]>

commit 80d8a9ad1587b64c545d515ab6cb7ecb9908e1b3 upstream.

[Why]
Accoreding to CP updated to RS64 on gfx11,
WRITE_DATA with PREEMPTION_META_MEMORY(dst_sel=8) is illegal for CP FW. That packet is used for MCBP on F32 based system.
So it would lead to incorrect GRBM write and FW is not handling that extra case correctly.

[How]
With gfx11 rs64 enabled, skip emit de meta data.

---
 drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -5392,9 +5392,9 @@ static void gfx_v11_0_ring_emit_ib_gfx(s
 		if (flags & AMDGPU_IB_PREEMPTED)
 			control |= INDIRECT_BUFFER_PRE_RESUME(1);
 
-		if (vmid)
+		if (vmid && !ring->adev->gfx.rs64_enable)
 			gfx_v11_0_ring_emit_de_meta(ring,
-				    (!amdgpu_sriov_vf(ring->adev) && flags & AMDGPU_IB_PREEMPTED) ? true : false);
+				!amdgpu_sriov_vf(ring->adev) && (flags & AMDGPU_IB_PREEMPTED));
 	}
 
 	if (ring->is_mes_queue)

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

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

From: Jianbo Liu <[email protected]>

[ Upstream commit 61fafbee6cfed283c02a320896089f658fa67e56 ]

The GSO segmentation functions for ESP tunnel mode (xfrm4_tunnel_gso_segment and xfrm6_tunnel_gso_segment) were determining the inner packet's L2 protocol type by checking the static x->inner_mode.family field from the xfrm state.

This is unreliable. In tunnel mode, the state's actual inner family could be defined by x->inner_mode.family or by x->inner_mode_iaf.family. Checking only the former can lead to a mismatch with the actual packet being processed, causing GSO to create segments with the wrong L2 header type.

This patch fixes the bug by deriving the inner mode directly from the packet's inner protocol stored in XFRM_MODE_SKB_CB(skb)->protocol.

Instead of replicating the code, this patch modifies the xfrm_ip2inner_mode helper function. It now correctly returns &x->inner_mode if the selector family (x->sel.family) is already specified, thereby handling both specific and AF_UNSPEC cases appropriately.

With this change, ESP GSO can use xfrm_ip2inner_mode to get the correct inner mode. It doesn't affect existing callers, as the updated logic now mirrors the checks they were already performing externally.

---
 include/net/xfrm.h      | 3 ++-
 net/ipv4/esp4_offload.c | 6 ++++--
 net/ipv6/esp6_offload.c | 6 ++++--
 3 files changed, 10 insertions(+), 5 deletions(-)

index 64911162ab5f4..ac5db167370c9 100644
@@ -446,7 +446,8 @@ static inline int xfrm_af2proto(unsigned int family)
 
 static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto)
 {
-	if ((ipproto == IPPROTO_IPIP && x->props.family == AF_INET) ||
+	if ((x->sel.family != AF_UNSPEC) ||
+	    (ipproto == IPPROTO_IPIP && x->props.family == AF_INET) ||
 	    (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6))
 		return &x->inner_mode;
 	else

index ee848be59e65a..cbfc8b5b15bd2 100644
@@ -110,8 +110,10 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x,
 						struct sk_buff *skb,
 						netdev_features_t features)
 {
-	__be16 type = x->inner_mode.family == AF_INET6 ? htons(ETH_P_IPV6)
-						       : htons(ETH_P_IP);
+	const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x,
+					XFRM_MODE_SKB_CB(skb)->protocol);
+	__be16 type = inner_mode->family == AF_INET6 ? htons(ETH_P_IPV6)
+						     : htons(ETH_P_IP);
 
 	return skb_eth_gso_segment(skb, features, type);
 }

index fc6a5be732634..65d628e500059 100644
@@ -145,8 +145,10 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x,
 						struct sk_buff *skb,
 						netdev_features_t features)
 {
-	__be16 type = x->inner_mode.family == AF_INET ? htons(ETH_P_IP)
-						      : htons(ETH_P_IPV6);
+	const struct xfrm_mode *inner_mode = xfrm_ip2inner_mode(x,
+					XFRM_MODE_SKB_CB(skb)->protocol);
+	__be16 type = inner_mode->family == AF_INET ? htons(ETH_P_IP)
+						    : htons(ETH_P_IPV6);
 
 	return skb_eth_gso_segment(skb, features, type);
 }

2.51.0

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

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

From: Zilin Guan <[email protected]>

[ Upstream commit 407a06507c2358554958e8164dc97176feddcafc ]

The function mlxsw_sp_flower_stats() calls mlxsw_sp_acl_ruleset_get() to obtain a ruleset reference. If the subsequent call to mlxsw_sp_acl_rule_lookup() fails to find a rule, the function returns an error without releasing the ruleset reference, causing a memory leak.

Fix this by using a goto to the existing error handling label, which calls mlxsw_sp_acl_ruleset_put() to properly release the reference.

---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index e91fb205e0b4c..66e95918bdf6e 100644
@@ -719,8 +719,10 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 		return -EINVAL;
 
 	rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie);
-	if (!rule)
-		return -EINVAL;
+	if (!rule) {
+		err = -EINVAL;
+		goto err_rule_get_stats;
+	}
 
 	err = mlxsw_sp_acl_rule_get_stats(mlxsw_sp, rule, &packets, &bytes,
 					  &drops, &lastuse, &used_hw_stats);

2.51.0

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

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

From: Mikko Perttunen <[email protected]>

[ Upstream commit 8935002fc37fce1ad211d98a70f2fd42083c0594 ]

On Tegra234, engines that are programmed through Host1x channels can be attached to either the NISO0 or NISO1 SMMU. Because of that, when selecting a context device to use with an engine, we need to select one that is also attached to the same SMMU.

Add a parameter to host1x_memory_context_alloc to specify which device we are allocating a context for, and use it to pick an appropriate context device.

Stable-dep-of: 6cbab9f0da72 ("drm/tegra: Add call to put_pid()")

---
 drivers/gpu/drm/tegra/uapi.c | 2 +-
 drivers/gpu/host1x/context.c | 4 ++++
 include/linux/host1x.h       | 2 ++
 3 files changed, 7 insertions(+), 1 deletion(-)

index a98239cb0e29a..5adab6b229164 100644
@@ -116,7 +116,7 @@ int tegra_drm_ioctl_channel_open(struct drm_device *drm, void *data, struct drm_
 
 		if (supported)
 			context->memory_context = host1x_memory_context_alloc(
-				host, get_task_pid(current, PIDTYPE_TGID));
+				host, client->base.dev, get_task_pid(current, PIDTYPE_TGID));
 
 		if (IS_ERR(context->memory_context)) {
 			if (PTR_ERR(context->memory_context) != -EOPNOTSUPP) {

index 93c0c532fe5af..9c0db178fade9 100644
@@ -112,6 +112,7 @@ void host1x_memory_context_list_free(struct host1x_memory_context_list *cdl)
 }
 
 struct host1x_memory_context *host1x_memory_context_alloc(struct host1x *host1x,
+							  struct device *dev,
 							  struct pid *pid)
 {
 	struct host1x_memory_context_list *cdl = &host1x->context_list;

@@ -126,6 +127,9 @@ struct host1x_memory_context *host1x_memory_context_alloc(struct host1x *host1x,
 	for (i = 0; i < cdl->len; i++) {
 		struct host1x_memory_context *cd = &cdl->devs[i];
 
+		if (cd->dev.iommu->iommu_dev != dev->iommu->iommu_dev)
+			continue;
+
 		if (cd->owner == pid) {
 			refcount_inc(&cd->ref);
 			mutex_unlock(&cdl->lock);

index cb2100d9b0ffe..dc55d9d3b94f0 100644
@@ -469,11 +469,13 @@ struct host1x_memory_context {
 
 #ifdef CONFIG_IOMMU_API
 struct host1x_memory_context *host1x_memory_context_alloc(struct host1x *host1x,
+							  struct device *dev,
 							  struct pid *pid);
 void host1x_memory_context_get(struct host1x_memory_context *cd);
 void host1x_memory_context_put(struct host1x_memory_context *cd);
 #else
 static inline struct host1x_memory_context *host1x_memory_context_alloc(struct host1x *host1x,
+									struct device *dev,
 									struct pid *pid)
 {
 	return NULL;

2.51.0

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

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

From: Prateek Agarwal <[email protected]>

[ Upstream commit 6cbab9f0da72b4dc3c3f9161197aa3b9daa1fa3a ]

Add a call to put_pid() corresponding to get_task_pid(). host1x_memory_context_alloc() does not take ownership of the PID so we need to free it here to avoid leaking.

---
 drivers/gpu/drm/tegra/uapi.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

index 5adab6b229164..d0b6a1fa6efad 100644
@@ -114,9 +114,12 @@ int tegra_drm_ioctl_channel_open(struct drm_device *drm, void *data, struct drm_
 		if (err)
 			goto put_channel;
 
-		if (supported)
+		if (supported) {
+			struct pid *pid = get_task_pid(current, PIDTYPE_TGID);
 			context->memory_context = host1x_memory_context_alloc(
-				host, client->base.dev, get_task_pid(current, PIDTYPE_TGID));
+				host, client->base.dev, pid);
+			put_pid(pid);
+		}
 
 		if (IS_ERR(context->memory_context)) {
 			if (PTR_ERR(context->memory_context) != -EOPNOTSUPP) {

2.51.0

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

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

From: Pavel Zhigulin <[email protected]>

[ Upstream commit e6751b0b19a6baab219a62e1e302b8aa6b5a55b2 ]

The LED setup routine registered both led_sync_good and led_is_gm devices without checking the return values of led_classdev_register(). If either registration failed, the function continued silently, leaving the driver in a partially-initialized state and leaking a registered LED classdev.

Add proper error handling

---
 drivers/net/dsa/hirschmann/hellcreek_ptp.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

index b28baab6d56a1..763666480a8a8 100644
@@ -367,8 +367,18 @@ static int hellcreek_led_setup(struct hellcreek *hellcreek)
 		hellcreek_set_brightness(hellcreek, STATUS_OUT_IS_GM, 1);
 
 	/* Register both leds */
-	led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good);
-	led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm);
+	ret = led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good);
+	if (ret) {
+		dev_err(hellcreek->dev, "Failed to register sync_good LED\n");
+		goto out;
+	}
+
+	ret = led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm);
+	if (ret) {
+		dev_err(hellcreek->dev, "Failed to register is_gm LED\n");
+		led_classdev_unregister(&hellcreek->led_sync_good);
+		goto out;
+	}
 
 	ret = 0;
 

2.51.0

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

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

From: Pavel Zhigulin <[email protected]>

[ Upstream commit b0c959fec18f4595a6a6317ffc30615cfa37bf69 ]

The call to devlink_info_version_fixed_put() in mlxsw_linecard_devlink_info_get() did not check for errors, although it is checked everywhere in the code.

Add missed 'err' check to the mlxsw_linecard_devlink_info_get()

---
 drivers/net/ethernet/mellanox/mlxsw/core_linecards.c | 2 ++
 1 file changed, 2 insertions(+)

index 99196333d1324..525973da7abc9 100644
@@ -601,6 +601,8 @@ int mlxsw_linecard_devlink_info_get(struct mlxsw_linecard *linecard,
 		err = devlink_info_version_fixed_put(req,
 						     DEVLINK_INFO_VERSION_GENERIC_FW_PSID,
 						     info->psid);
+		if (err)
+			goto unlock;
 
 		sprintf(buf, "%u.%u.%u", info->fw_major, info->fw_minor,
 			info->fw_sub_minor);

2.51.0

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

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

From: Ilya Maximets <[email protected]>

[ Upstream commit dfe28c4167a9259fc0c372d9f9473e1ac95cff67 ]

The validation of the set(nsh(...)) action is completely wrong. It runs through the nsh_key_put_from_nlattr() function that is the same function that validates NSH keys for the flow match and the push_nsh() action. However, the set(nsh(...)) has a very different memory layout. Nested attributes in there are doubled in size in case of the masked set(). That makes proper validation impossible.

There is also confusion in the code between the 'masked' flag, that says that the nested attributes are doubled in size containing both the value and the mask, and the 'is_mask' that says that the value we're parsing is the mask. This is causing kernel crash on trying to write into mask part of the match with SW_FLOW_KEY_PUT() during validation, while validate_nsh() doesn't allocate any memory for it:

  BUG: kernel NULL pointer dereference, address: 0000000000000018
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 1c2383067 P4D 1c2383067 PUD 20b703067 PMD 0
  Oops: Oops: 0000 [#1] SMP NOPTI
  CPU: 8 UID: 0 Kdump: loaded Not tainted 6.17.0-rc4+ #107 PREEMPT(voluntary)
  RIP: 0010:nsh_key_put_from_nlattr+0x19d/0x610 [openvswitch]
  Call Trace:
   <TASK>
   validate_nsh+0x60/0x90 [openvswitch]
   validate_set.constprop.0+0x270/0x3c0 [openvswitch]
   __ovs_nla_copy_actions+0x477/0x860 [openvswitch]
   ovs_nla_copy_actions+0x8d/0x100 [openvswitch]
   ovs_packet_cmd_execute+0x1cc/0x310 [openvswitch]
   genl_family_rcv_msg_doit+0xdb/0x130
   genl_family_rcv_msg+0x14b/0x220
   genl_rcv_msg+0x47/0xa0
   netlink_rcv_skb+0x53/0x100
   genl_rcv+0x24/0x40
   netlink_unicast+0x280/0x3b0
   netlink_sendmsg+0x1f7/0x430
   ____sys_sendmsg+0x36b/0x3a0
   ___sys_sendmsg+0x87/0xd0
   __sys_sendmsg+0x6d/0xd0
   do_syscall_64+0x7b/0x2c0
   entry_SYSCALL_64_after_hwframe+0x76/0x7e

The third issue with this process is that while trying to convert the non-masked set into masked one, validate_set() copies and doubles the size of the OVS_KEY_ATTR_NSH as if it didn't have any nested attributes. It should be copying each nested attribute and doubling them in size independently. And the process must be properly reversed during the conversion back from masked to a non-masked variant during the flow dump.

In the end, the only two outcomes of trying to use this action are either validation failure or a kernel crash. And if somehow someone manages to install a flow with such an action, it will most definitely not do what it is supposed to, since all the keys and the masks are mixed up.

Fixing all the issues is a complex task as it requires re-writing most of the validation code.

Given that and the fact that this functionality never worked since introduction, let's just remove it altogether. It's better to re-introduce it later with a proper implementation instead of trying to fix it in stable releases.

---
 net/openvswitch/actions.c      | 68 +---------------------------------
 net/openvswitch/flow_netlink.c | 64 ++++----------------------------
 net/openvswitch/flow_netlink.h |  2 -
 3 files changed, 9 insertions(+), 125 deletions(-)

index a87c25e06bafd..f7cc87e67d3c8 100644
@@ -595,69 +595,6 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	return 0;
 }
 
-static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key,
-		   const struct nlattr *a)
-{
-	struct nshhdr *nh;
-	size_t length;
-	int err;
-	u8 flags;
-	u8 ttl;
-	int i;
-
-	struct ovs_key_nsh key;
-	struct ovs_key_nsh mask;
-
-	err = nsh_key_from_nlattr(a, &key, &mask);
-	if (err)
-		return err;
-
-	/* Make sure the NSH base header is there */
-	if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN))
-		return -ENOMEM;
-
-	nh = nsh_hdr(skb);
-	length = nsh_hdr_len(nh);
-
-	/* Make sure the whole NSH header is there */
-	err = skb_ensure_writable(skb, skb_network_offset(skb) +
-				       length);
-	if (unlikely(err))
-		return err;
-
-	nh = nsh_hdr(skb);
-	skb_postpull_rcsum(skb, nh, length);
-	flags = nsh_get_flags(nh);
-	flags = OVS_MASKED(flags, key.base.flags, mask.base.flags);
-	flow_key->nsh.base.flags = flags;
-	ttl = nsh_get_ttl(nh);
-	ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl);
-	flow_key->nsh.base.ttl = ttl;
-	nsh_set_flags_and_ttl(nh, flags, ttl);
-	nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr,
-				  mask.base.path_hdr);
-	flow_key->nsh.base.path_hdr = nh->path_hdr;
-	switch (nh->mdtype) {
-	case NSH_M_TYPE1:
-		for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) {
-			nh->md1.context[i] =
-			    OVS_MASKED(nh->md1.context[i], key.context[i],
-				       mask.context[i]);
-		}
-		memcpy(flow_key->nsh.context, nh->md1.context,
-		       sizeof(nh->md1.context));
-		break;
-	case NSH_M_TYPE2:
-		memset(flow_key->nsh.context, 0,
-		       sizeof(flow_key->nsh.context));
-		break;
-	default:
-		return -EINVAL;
-	}
-	skb_postpush_rcsum(skb, nh, length);
-	return 0;
-}
-
 /* Must follow skb_ensure_writable() since that can move the skb data. */
 static void set_tp_port(struct sk_buff *skb, __be16 *port,
 			__be16 new_port, __sum16 *check)

@@ -1130,10 +1067,6 @@ static int execute_masked_set_action(struct sk_buff *skb,
 				   get_mask(a, struct ovs_key_ethernet *));
 		break;
 
-	case OVS_KEY_ATTR_NSH:
-		err = set_nsh(skb, flow_key, a);
-		break;
-
 	case OVS_KEY_ATTR_IPV4:
 		err = set_ipv4(skb, flow_key, nla_data(a),
 			       get_mask(a, struct ovs_key_ipv4 *));

@@ -1170,6 +1103,7 @@ static int execute_masked_set_action(struct sk_buff *skb,
 	case OVS_KEY_ATTR_CT_LABELS:
 	case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4:
 	case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6:
+	case OVS_KEY_ATTR_NSH:
 		err = -EINVAL;
 		break;
 	}

index fe7f77fc5f189..ff8cdecbe3465 100644
@@ -65,8 +65,6 @@ int ovs_nla_put_actions(const struct nlattr *attr,
 void ovs_nla_free_flow_actions(struct sw_flow_actions *);
 void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *);
 
-int nsh_key_from_nlattr(const struct nlattr *attr, struct ovs_key_nsh *nsh,
-			struct ovs_key_nsh *nsh_mask);
 int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh,
 			size_t size);
 

2.51.0

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

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

From: Shin'ichiro Kawasaki <[email protected]>

[ Upstream commit 6d87cd5335784351280f82c47cc8a657271929c3 ]

Blktests test cases nvme/014, 057 and 058 fail occasionally due to a lockdep WARN. As reported in the Closes tag URL, the WARN indicates that a deadlock can happen due to the dependency among disk->open_mutex, kblockd workqueue completion and partition_scan_work completion.

To avoid the lockdep WARN and the potential deadlock, cut the dependency by running the partition_scan_work not by kblockd workqueue but by nvme_wq.

---
 drivers/nvme/host/multipath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 43b89c7d585f0..a3e225bb4b88f 100644
@@ -577,7 +577,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 			return;
 		}
 		nvme_add_ns_head_cdev(head);
-		kblockd_schedule_work(&head->partition_scan_work);
+		queue_work(nvme_wq, &head->partition_scan_work);
 	}
 
 	mutex_lock(&head->lock);

2.51.0

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

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

From: Aleksei Nikiforov <[email protected]>

[ Upstream commit da02a1824884d6c84c5e5b5ac373b0c9e3288ec2 ]

The function 'mpc_rcvd_sweep_req(mpcginfo)' is called conditionally from function 'ctcmpc_unpack_skb'. It frees passed mpcginfo. After that a call to function 'kfree' in function 'ctcmpc_unpack_skb' frees it again.

Remove 'kfree' call in function 'mpc_rcvd_sweep_req(mpcginfo)'.

Bug detected by the clang static analyzer.

---
 drivers/s390/net/ctcm_mpc.c | 1 -
 1 file changed, 1 deletion(-)

index 8ac213a551418..55216d2fbea0b 100644
@@ -698,7 +698,6 @@ static void mpc_rcvd_sweep_req(struct mpcg_info *mpcginfo)
 
 	grp->sweep_req_pend_num--;
 	ctcmpc_send_sweep_resp(ch);
-	kfree(mpcginfo);
 	return;
 }
 

2.51.0

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

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

From: Haotian Zhang <[email protected]>

[ Upstream commit d8bb447efc5622577994287dc77c684fa8840b30 ]

isst_if_probe() uses pci_read_config_dword() that returns PCIBIOS_* codes. The return code is returned from the probe function as is but probe functions should return normal errnos. A proper implementation can be found in drivers/leds/leds-ss4200.c.

Convert PCIBIOS_* return codes using pcibios_err_to_errno() into normal errno before returning.

---
 drivers/platform/x86/intel/speed_select_if/isst_if_mmio.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index ff49025ec0856..bb38e5f021a80 100644
@@ -106,11 +106,11 @@ static int isst_if_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	ret = pci_read_config_dword(pdev, 0xD0, &mmio_base);
 	if (ret)
-		return ret;
+		return pcibios_err_to_errno(ret);
 
 	ret = pci_read_config_dword(pdev, 0xFC, &pcu_base);
 	if (ret)
-		return ret;
+		return pcibios_err_to_errno(ret);
 
 	pcu_base &= GENMASK(10, 0);
 	base_addr = (u64)mmio_base << 23 | (u64) pcu_base << 12;

2.51.0

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

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

From: Alejandro Colomar <[email protected]>

[ Upstream commit 3cd39bc3b11b8d34b7d7c961a35fdfd18b0ebf75 ]

Touching files so used for the kernel,
forces 'make' to recompile most of the kernel.

Having those definitions in more granular files
helps avoid recompiling so much of the kernel.

Stable-dep-of: 896f1a2493b5 ("net: qlogic/qede: fix potential out-of-bounds read in qede_tpa_cont() and qede_tpa_end()")

---
 include/linux/array_size.h | 13 +++++++++++++
 include/linux/kernel.h     |  7 +------
 include/linux/string.h     |  1 +
 3 files changed, 15 insertions(+), 6 deletions(-)
 create mode 100644 include/linux/array_size.h

new file mode 100644
index 0000000000000..06d7d83196ca3
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_ARRAY_SIZE_H
+#define _LINUX_ARRAY_SIZE_H
+
+#include <linux/compiler.h>
+
+/**
+ * ARRAY_SIZE - get the number of elements in array @arr
+ * @arr: array to be sized
+ */
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
+
+#endif  /* _LINUX_ARRAY_SIZE_H */

index fe6efb24d151a..50254bb6b7a98 100644
@@ -13,6 +13,7 @@
 
 #include <linux/stdarg.h>
 #include <linux/align.h>
+#include <linux/array_size.h>
 #include <linux/limits.h>
 #include <linux/linkage.h>
 #include <linux/stddef.h>

@@ -48,12 +49,6 @@
 #define READ			0
 #define WRITE			1
 
-/**
- * ARRAY_SIZE - get the number of elements in array @arr
- * @arr: array to be sized
- */
-#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
-
 #define PTR_IF(cond, ptr)	((cond) ? (ptr) : NULL)
 
 #define u64_to_user_ptr(x) (		\

index 422606e98cc42..e7ade5223d422 100644
@@ -2,6 +2,7 @@
 #ifndef _LINUX_STRING_H_
 #define _LINUX_STRING_H_
 
+#include <linux/array_size.h>
 #include <linux/compiler.h>	/* for inline */
 #include <linux/types.h>	/* for size_t */
 #include <linux/stddef.h>	/* for NULL */

2.51.0

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

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

From: Pavel Zhigulin <[email protected]>

[ Upstream commit 896f1a2493b59beb2b5ccdf990503dbb16cb2256 ]

The loops in 'qede_tpa_cont()' and 'qede_tpa_end()', iterate over 'cqe->len_list[]' using only a zero-length terminator as the stopping condition. If the terminator was missing or malformed, the loop could run past the end of the fixed-size array.

Add an explicit bound check using ARRAY_SIZE() in both loops to prevent a potential out-of-bounds access.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

---
 drivers/net/ethernet/qlogic/qede/qede_fp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

index cb1746bc0e0c5..273dae622c411 100644
@@ -4,6 +4,7 @@
  * Copyright (c) 2019-2020 Marvell International Ltd.
  */
 
+#include <linux/array_size.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/skbuff.h>

@@ -960,7 +961,7 @@ static inline void qede_tpa_cont(struct qede_dev *edev,
 {
 	int i;
 
-	for (i = 0; cqe->len_list[i]; i++)
+	for (i = 0; cqe->len_list[i] && i < ARRAY_SIZE(cqe->len_list); i++)
 		qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index,
 				   le16_to_cpu(cqe->len_list[i]));
 

@@ -985,7 +986,7 @@ static int qede_tpa_end(struct qede_dev *edev,
 		dma_unmap_page(rxq->dev, tpa_info->buffer.mapping,
 			       PAGE_SIZE, rxq->data_direction);
 
-	for (i = 0; cqe->len_list[i]; i++)
+	for (i = 0; cqe->len_list[i] && i < ARRAY_SIZE(cqe->len_list); i++)
 		qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index,
 				   le16_to_cpu(cqe->len_list[i]));
 	if (unlikely(i > 1))

2.51.0

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

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

From: Michal Luczaj <[email protected]>

[ Upstream commit 002541ef650b742a198e4be363881439bb9d86b4 ]

During connect(), acting on a signal/timeout by disconnecting an already established socket leads to several issues:

1. connect() invoking vsock_transport_cancel_pkt() -> virtio_transport_purge_skbs() may race with sendmsg() invoking virtio_transport_get_credit(). This results in a permanently elevated vvs->bytes_unsent. Which, in turn, confuses the SOCK_LINGER handling.

2. connect() resetting a connected socket's state may race with socket being placed in a sockmap. A disconnected socket remaining in a sockmap breaks sockmap's assumptions. And gives rise to WARNs.

3. connect() transitioning SS_CONNECTED -> SS_UNCONNECTED allows for a transport change/drop after TCP_ESTABLISHED. Which poses a problem for any simultaneous sendmsg() or connect() and may result in a use-after-free/null-ptr-deref.

Do not disconnect socket on signal/timeout. Keep the logic for unconnected
sockets: they don't linger, can't be placed in a sockmap, are rejected by sendmsg().

[1]: https://lore.kernel.org/netdev/[email protected]/
[2]: https://lore.kernel.org/netdev/[email protected]/
[3]: https://lore.kernel.org/netdev/[email protected]/

---
 net/vmw_vsock/af_vsock.c | 40 +++++++++++++++++++++++++++++++---------
 1 file changed, 31 insertions(+), 9 deletions(-)

index 6de321a6e43cf..95441466d90dd 100644
@@ -1502,18 +1502,40 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 		timeout = schedule_timeout(timeout);
 		lock_sock(sk);
 
-		if (signal_pending(current)) {
-			err = sock_intr_errno(timeout);
-			sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE;
-			sock->state = SS_UNCONNECTED;
-			vsock_transport_cancel_pkt(vsk);
-			vsock_remove_connected(vsk);
-			goto out_wait;
-		} else if ((sk->sk_state != TCP_ESTABLISHED) && (timeout == 0)) {
-			err = -ETIMEDOUT;
+		/* Connection established. Whatever happens to socket once we
+		 * release it, that's not connect()'s concern. No need to go
+		 * into signal and timeout handling. Call it a day.
+		 *
+		 * Note that allowing to "reset" an already established socket
+		 * here is racy and insecure.
+		 */
+		if (sk->sk_state == TCP_ESTABLISHED)
+			break;
+
+		/* If connection was _not_ established and a signal/timeout came
+		 * to be, we want the socket's state reset. User space may want
+		 * to retry.
+		 *
+		 * sk_state != TCP_ESTABLISHED implies that socket is not on
+		 * vsock_connected_table. We keep the binding and the transport
+		 * assigned.
+		 */
+		if (signal_pending(current) || timeout == 0) {
+			err = timeout == 0 ? -ETIMEDOUT : sock_intr_errno(timeout);
+
+			/* Listener might have already responded with
+			 * VIRTIO_VSOCK_OP_RESPONSE. Its handling expects our
+			 * sk_state == TCP_SYN_SENT, which hereby we break.
+			 * In such case VIRTIO_VSOCK_OP_RST will follow.
+			 */
 			sk->sk_state = TCP_CLOSE;
 			sock->state = SS_UNCONNECTED;
+
+			/* Try to cancel VIRTIO_VSOCK_OP_REQUEST skb sent out by
+			 * transport->connect().
+			 */
 			vsock_transport_cancel_pkt(vsk);
+
 			goto out_wait;
 		}
 

2.51.0

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

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

From: Rafał Miłecki <[email protected]>

[ Upstream commit a2a69add80411dd295c9088c1bcf925b1f4e53d7 ]

Some bus devices can be marked as disabled for specific SoCs or models. Those should not be registered to avoid probing them.

---
 drivers/bcma/main.c | 6 ++++++
 1 file changed, 6 insertions(+)

index 44392b624b200..11fbae15a7884 100644
@@ -293,6 +293,8 @@ static int bcma_register_devices(struct bcma_bus *bus)
 	int err;
 
 	list_for_each_entry(core, &bus->cores, list) {
+		struct device_node *np;
+
 		/* We support that core ourselves */
 		switch (core->id.id) {
 		case BCMA_CORE_4706_CHIPCOMMON:

@@ -310,6 +312,10 @@ static int bcma_register_devices(struct bcma_bus *bus)
 		if (bcma_is_core_needed_early(core->id.id))
 			continue;
 
+		np = core->dev.of_node;
+		if (np && !of_device_is_available(np))
+			continue;
+
 		/* Only first GMAC core on BCM4706 is connected and working */
 		if (core->id.id == BCMA_CORE_4706_MAC_GBIT &&
 		    core->core_unit > 0)

2.51.0

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

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

From: Steve French <[email protected]>

[ Upstream commit f765fdfcd8b5bce92c6aa1a517ff549529ddf590 ]

Fix typo in description of enable_gcm_256 module parameter

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

index 32b008bc99a09..74e4beb351946 100644
@@ -128,7 +128,7 @@ module_param(enable_oplocks, bool, 0644);
 MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks. Default: y/Y/1");
 
 module_param(enable_gcm_256, bool, 0644);
-MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: y/Y/0");
+MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: y/Y/1");
 
 module_param(require_gcm_256, bool, 0644);
 MODULE_PARM_DESC(require_gcm_256, "Require strongest (256 bit) GCM encryption. Default: n/N/0");

2.51.0

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

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

From: Bart Van Assche <[email protected]>

[ Upstream commit a0b7780602b1b196f47e527fec82166a7e67c4d0 ]

Commit 995412e23bb2 ("blk-mq: Replace tags->lock with SRCU for tag iterators") introduced the following regression:

Call trace:
 __srcu_read_lock+0x30/0x80 (P)
 blk_mq_tagset_busy_iter+0x44/0x300
 scsi_host_busy+0x38/0x70
 ufshcd_print_host_state+0x34/0x1bc
 ufshcd_link_startup.constprop.0+0xe4/0x2e0
 ufshcd_init+0x944/0xf80
 ufshcd_pltfrm_init+0x504/0x820
 ufs_rockchip_probe+0x2c/0x88
 platform_probe+0x5c/0xa4
 really_probe+0xc0/0x38c
 __driver_probe_device+0x7c/0x150
 driver_probe_device+0x40/0x120
 __driver_attach+0xc8/0x1e0
 bus_for_each_dev+0x7c/0xdc
 driver_attach+0x24/0x30
 bus_add_driver+0x110/0x230
 driver_register+0x68/0x130
 __platform_driver_register+0x20/0x2c
 ufs_rockchip_pltform_init+0x1c/0x28
 do_one_initcall+0x60/0x1e0
 kernel_init_freeable+0x248/0x2c4
 kernel_init+0x20/0x140
 ret_from_fork+0x10/0x20

Fix this regression by making scsi_host_busy() check whether the SCSI host tag set has already been initialized. tag_set->ops is set by scsi_mq_setup_tags() just before blk_mq_alloc_tag_set() is called. This fix is based on the assumption that scsi_host_busy() and scsi_mq_setup_tags() calls are serialized. This is the case in the UFS driver.

---
 drivers/scsi/hosts.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

index c785493b105c0..28cf473fcf96d 100644
@@ -600,8 +600,9 @@ int scsi_host_busy(struct Scsi_Host *shost)
 {
 	int cnt = 0;
 
-	blk_mq_tagset_busy_iter(&shost->tag_set,
-				scsi_host_check_in_flight, &cnt);
+	if (shost->tag_set.ops)
+		blk_mq_tagset_busy_iter(&shost->tag_set,
+					scsi_host_check_in_flight, &cnt);
 	return cnt;
 }
 EXPORT_SYMBOL(scsi_host_busy);

2.51.0

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

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

From: Po-Hsu Lin <[email protected]>

[ Upstream commit 9311e9540a8b406d9f028aa87fb072a3819d4c82 ]

In bareudp.sh, this script uses /bin/sh and it will load another lib.sh BASH script at the very beginning.

But on some operating systems like Ubuntu, /bin/sh is actually pointed to DASH, thus it will try to run BASH commands with DASH and consequently leads to syntax issues:
# ./bareudp.sh: 4: ./lib.sh: Bad substitution
# ./bareudp.sh: 5: ./lib.sh: source: not found
# ./bareudp.sh: 24: ./lib.sh: Syntax error: "(" unexpected

Fix this by explicitly using BASH for bareudp.sh. This fixes test execution failures on systems where /bin/sh is not BASH.

---
 tools/testing/selftests/net/bareudp.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index f366cadbc5e86..ff4308b48e65d 100755
@@ -1,4 +1,4 @@
-#!/bin/sh
+#!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
 # Test various bareudp tunnel configurations.

2.51.0

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

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

From: Shahar Shitrit <[email protected]>

[ Upstream commit c15d5c62ab313c19121f10e25d4fec852bd1c40c ]

When a netdev issues a RX async resync request for a TLS connection, the TLS module handles it by logging record headers and attempting to match them to the tcp_sn provided by the device. If a match is found, the TLS module approves the tcp_sn for resynchronization.

While waiting for a device response, the TLS module also increments rcd_delta each time a new TLS record is received, tracking the distance from the original resync request.

However, if the device response is delayed or fails (e.g due to unstable connection and device getting out of tracking, hardware errors, resource exhaustion etc.), the TLS module keeps logging and incrementing, which can lead to a WARN() when rcd_delta exceeds the threshold.

To address this, introduce tls_offload_rx_resync_async_request_cancel() to explicitly cancel resync requests when a device response failure is detected. Call this helper also as a final safeguard when rcd_delta crosses its threshold, as reaching this point implies that earlier cancellation did not occur.

---
 include/net/tls.h    | 6 ++++++
 net/tls/tls_device.c | 4 +++-
 2 files changed, 9 insertions(+), 1 deletion(-)

index 899c863aba02c..037049def8a7f 100644
@@ -475,6 +475,12 @@ tls_offload_rx_resync_async_request_end(struct sock *sk, __be32 seq)
 		     ((u64)ntohl(seq) << 32) | RESYNC_REQ);
 }
 
+static inline void
+tls_offload_rx_resync_async_request_cancel(struct tls_offload_resync_async *resync_async)
+{
+	atomic64_set(&resync_async->req, 0);
+}
+
 static inline void
 tls_offload_rx_resync_set_type(struct sock *sk, enum tls_offload_sync_type type)
 {

index 1849827884735..c51377a159bec 100644
@@ -739,8 +739,10 @@ tls_device_rx_resync_async(struct tls_offload_resync_async *resync_async,
 		/* shouldn't get to wraparound:
 		 * too long in async stage, something bad happened
 		 */
-		if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX))
+		if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX)) {
+			tls_offload_rx_resync_async_request_cancel(resync_async);
 			return false;
+		}
 
 		/* asynchronous stage: log all headers seq such that
 		 * req_seq <= seq <= end_seq, and wait for real resync request

2.51.0

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

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

From: Jakub Horký <[email protected]>

[ Upstream commit 3927c4a1084c48ef97f11281a0a43ecb2cb4d6f1 ]

Fix bug where make menuconfig doesn't initialize the default locale, which causes ncurses menu borders to be displayed incorrectly (lqqqqk) in UTF-8 terminals that don't support VT100 ACS by default, such as PuTTY.

---
 scripts/kconfig/mconf.c | 3 +++
 1 file changed, 3 insertions(+)

index 9d3cf510562f8..0649ff35ec5c0 100644
@@ -12,6 +12,7 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <limits.h>
+#include <locale.h>
 #include <stdarg.h>
 #include <stdlib.h>
 #include <string.h>

@@ -1005,6 +1006,8 @@ int main(int ac, char **av)
 
 	signal(SIGINT, sig_handler);
 
+	setlocale(LC_ALL, "");
+
 	if (ac > 1 && strcmp(av[1], "-s") == 0) {
 		silent = 1;
 		/* Silence conf_read() until the real callback is set up */

2.51.0

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

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

From: Jakub Horký <[email protected]>

[ Upstream commit 43c2931a95e6b295bfe9e3b90dbe0f7596933e91 ]

Fix bug where make nconfig doesn't initialize the default locale, which causes ncurses menu borders to be displayed incorrectly (lqqqqk) in UTF-8 terminals that don't support VT100 ACS by default, such as PuTTY.

---
 scripts/kconfig/nconf.c | 3 +++
 1 file changed, 3 insertions(+)

index 16a2db59432a5..e9ae03d056b09 100644
@@ -7,6 +7,7 @@
 #ifndef _GNU_SOURCE
 #define _GNU_SOURCE
 #endif
+#include <locale.h>
 #include <string.h>
 #include <strings.h>
 #include <stdlib.h>

@@ -1476,6 +1477,8 @@ int main(int ac, char **av)
 	int lines, columns;
 	char *mode;
 
+	setlocale(LC_ALL, "");
+
 	if (ac > 1 && strcmp(av[1], "-s") == 0) {
 		/* Silence conf_read() until the real callback is set up */
 		conf_set_message_callback(NULL);

2.51.0

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

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

From: Lance Yang <[email protected]>

[ Upstream commit 6f86d0534fddfbd08687fa0f01479d4226bc3c3d ]

When a page fault occurs in a secret memory file created with memfd_secret(2), the kernel will allocate a new page for it, mark the underlying page as not-present in the direct map, and add it to the file mapping.

If two tasks cause a fault in the same page concurrently, both could end up allocating a page and removing the page from the direct map, but only one would succeed in adding the page to the file mapping. The task that failed undoes the effects of its attempt by (a) freeing the page again and (b) putting the page back into the direct map. However, by doing these two operations in this order, the page becomes available to the allocator again before it is placed back in the direct mapping.

If another task attempts to allocate the page between (a) and (b), and the kernel tries to access it via the direct map, it would result in a supervisor not-present page fault.

Fix the ordering to restore the direct map before the page is freed.

---
 mm/secretmem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 18954eae995fc..b570a6e25b6be 100644
@@ -82,13 +82,13 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf)
 		__SetPageUptodate(page);
 		err = add_to_page_cache_lru(page, mapping, offset, gfp);
 		if (unlikely(err)) {
-			put_page(page);
 			/*
 			 * If a split of large page was required, it
 			 * already happened when we marked the page invalid
 			 * which guarantees that this call won't fail
 			 */
 			set_direct_map_default_noflush(page);
+			put_page(page);
 			if (err == -EEXIST)
 				goto retry;
 

2.51.0

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

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

From: Isaac J. Manjarres <[email protected]>

[ Upstream commit 0d6c356dd6547adac2b06b461528e3573f52d953 ]

When emitting the order of the allocation for a hash table, alloc_large_system_hash() unconditionally subtracts PAGE_SHIFT from log base 2 of the allocation size. This is not correct if the allocation size is smaller than a page, and yields a negative value for the order as seen below:

TCP established hash table entries: 32 (order: -4, 256 bytes, linear) TCP bind hash table entries: 32 (order: -2, 1024 bytes, linear)

Use get_order() to compute the order when emitting the hash table information to correctly handle cases where the allocation size is smaller than a page:

TCP established hash table entries: 32 (order: 0, 256 bytes, linear) TCP bind hash table entries: 32 (order: 0, 1024 bytes, linear)

---
 mm/page_alloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 86066a2cf258a..d760b96604eca 100644
@@ -9225,7 +9225,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 		panic("Failed to allocate %s hash table\n", tablename);
 
 	pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n",
-		tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size,
+		tablename, 1UL << log2qty, get_order(size), size,
 		virt ? (huge ? "vmalloc hugepage" : "vmalloc") : "linear");
 
 	if (_hash_shift)

2.51.0

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

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

From: René Rebe <[email protected]>

[ Upstream commit d26e9f669cc0a6a85cf17180c09a6686db9f4002 ]

Since 8b3a087f7f65 ("ALSA: usb-audio: Unify virtual type units type to UAC3 values") usb-audio is using UAC3_CLOCK_SOURCE instead of bDescriptorSubtype, later refactored with e0ccdef9265 ("ALSA: usb-audio:
Clean up check_input_term()") into parse_term_uac2_clock_source().

This breaks the clock source selection for at least my 1397:0003 BEHRINGER International GmbH FCA610 Pro.

Fix by using UAC2_CLOCK_SOURCE in parse_term_uac2_clock_source().

---
 sound/usb/mixer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 9b34004e67131..1540e9f1c2e3f 100644
@@ -930,7 +930,7 @@ static int parse_term_uac2_clock_source(struct mixer_build *state,
 {
 	struct uac_clock_source_descriptor *d = p1;
 
-	term->type = UAC3_CLOCK_SOURCE << 16; /* virtual type */
+	term->type = UAC2_CLOCK_SOURCE << 16; /* virtual type */
 	term->id = id;
 	term->name = d->iClockSource;
 	return 0;

2.51.0

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

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

From: Nishanth Menon <[email protected]>

[ Upstream commit 90a88306eb874fe4bbdd860e6c9787f5bbc588b5 ]

Make knav_dma_open_channel consistently return NULL on error instead of ERR_PTR. Currently the header include/linux/soc/ti/knav_dma.h returns NULL when the driver is disabled, but the driver implementation does not even return NULL or ERR_PTR on failure, causing inconsistency in the users. This results in a crash in netcp_free_navigator_resources as followed (trimmed):

Unhandled fault: alignment exception (0x221) at 0xfffffff2 [fffffff2] *pgd=80000800207003, *pmd=82ffda003, *pte=00000000

Internal error: : 221 [#1] SMP ARM
Modules linked in:
CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.17.0-rc7 #1 NONE
Hardware name: Keystone
PC is at knav_dma_close_channel+0x30/0x19c
LR is at netcp_free_navigator_resources+0x2c/0x28c

[... TRIM...]

Call trace:
 knav_dma_close_channel from netcp_free_navigator_resources+0x2c/0x28c
 netcp_free_navigator_resources from netcp_ndo_open+0x430/0x46c
 netcp_ndo_open from __dev_open+0x114/0x29c
 __dev_open from __dev_change_flags+0x190/0x208
 __dev_change_flags from netif_change_flags+0x1c/0x58
 netif_change_flags from dev_change_flags+0x38/0xa0
 dev_change_flags from ip_auto_config+0x2c4/0x11f0
 ip_auto_config from do_one_initcall+0x58/0x200
 do_one_initcall from kernel_init_freeable+0x1cc/0x238
 kernel_init_freeable from kernel_init+0x1c/0x12c
 kernel_init from ret_from_fork+0x14/0x38

[... TRIM...]

Standardize the error handling by making the function return NULL on all error conditions. The API is used in just the netcp_core.c so the impact is limited.

Note, this change, in effect reverts commit 5b6cb43b4d62 ("net:
ethernet: ti: netcp_core: return error while dma channel open issue"), but provides a less error prone implementation.

---
 drivers/net/ethernet/ti/netcp_core.c | 10 +++++-----
 drivers/soc/ti/knav_dma.c            | 14 +++++++-------
 2 files changed, 12 insertions(+), 12 deletions(-)

index 9eb9eaff4dc90..6c0c9b795c8fe 100644
@@ -1338,10 +1338,10 @@ int netcp_txpipe_open(struct netcp_tx_pipe *tx_pipe)
 
 	tx_pipe->dma_channel = knav_dma_open_channel(dev,
 				tx_pipe->dma_chan_name, &config);
-	if (IS_ERR(tx_pipe->dma_channel)) {
+	if (!tx_pipe->dma_channel) {
 		dev_err(dev, "failed opening tx chan(%s)\n",
 			tx_pipe->dma_chan_name);
-		ret = PTR_ERR(tx_pipe->dma_channel);
+		ret = -EINVAL;
 		goto err;
 	}
 

@@ -1359,7 +1359,7 @@ int netcp_txpipe_open(struct netcp_tx_pipe *tx_pipe)
 	return 0;
 
 err:
-	if (!IS_ERR_OR_NULL(tx_pipe->dma_channel))
+	if (tx_pipe->dma_channel)
 		knav_dma_close_channel(tx_pipe->dma_channel);
 	tx_pipe->dma_channel = NULL;
 	return ret;

@@ -1678,10 +1678,10 @@ static int netcp_setup_navigator_resources(struct net_device *ndev)
 
 	netcp->rx_channel = knav_dma_open_channel(netcp->netcp_device->device,
 					netcp->dma_chan_name, &config);
-	if (IS_ERR(netcp->rx_channel)) {
+	if (!netcp->rx_channel) {
 		dev_err(netcp->ndev_dev, "failed opening rx chan(%s\n",
 			netcp->dma_chan_name);
-		ret = PTR_ERR(netcp->rx_channel);
+		ret = -EINVAL;
 		goto fail;
 	}
 

index 84afebd355bef..10014ffca829a 100644
@@ -402,7 +402,7 @@ static int of_channel_match_helper(struct device_node *np, const char *name,
  * @name:	slave channel name
  * @config:	dma configuration parameters
  *
- * Returns pointer to appropriate DMA channel on success or error.
+ * Return: Pointer to appropriate DMA channel on success or NULL on error.
  */
 void *knav_dma_open_channel(struct device *dev, const char *name,
 					struct knav_dma_cfg *config)

@@ -414,13 +414,13 @@ void *knav_dma_open_channel(struct device *dev, const char *name,
 
 	if (!kdev) {
 		pr_err("keystone-navigator-dma driver not registered\n");
-		return (void *)-EINVAL;
+		return NULL;
 	}
 
 	chan_num = of_channel_match_helper(dev->of_node, name, &instance);
 	if (chan_num < 0) {
 		dev_err(kdev->dev, "No DMA instance with name %s\n", name);
-		return (void *)-EINVAL;
+		return NULL;
 	}
 
 	dev_dbg(kdev->dev, "initializing %s channel %d from DMA %s\n",

@@ -431,7 +431,7 @@ void *knav_dma_open_channel(struct device *dev, const char *name,
 	if (config->direction != DMA_MEM_TO_DEV &&
 	    config->direction != DMA_DEV_TO_MEM) {
 		dev_err(kdev->dev, "bad direction\n");
-		return (void *)-EINVAL;
+		return NULL;
 	}
 
 	/* Look for correct dma instance */

@@ -443,7 +443,7 @@ void *knav_dma_open_channel(struct device *dev, const char *name,
 	}
 	if (!dma) {
 		dev_err(kdev->dev, "No DMA instance with name %s\n", instance);
-		return (void *)-EINVAL;
+		return NULL;
 	}
 
 	/* Look for correct dma channel from dma instance */

@@ -463,14 +463,14 @@ void *knav_dma_open_channel(struct device *dev, const char *name,
 	if (!chan) {
 		dev_err(kdev->dev, "channel %d is not in DMA %s\n",
 				chan_num, instance);
-		return (void *)-EINVAL;
+		return NULL;
 	}
 
 	if (atomic_read(&chan->ref_count) >= 1) {
 		if (!check_config(chan, config)) {
 			dev_err(kdev->dev, "channel %d config miss-match\n",
 				chan_num);
-			return (void *)-EINVAL;
+			return NULL;
 		}
 	}
 

2.51.0

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

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

From: Zhang Chujun <[email protected]>

[ Upstream commit 53afec2c8fb2a562222948cb1c2aac48598578c9 ]

The help message incorrectly listed '-t' as the short option for --threads, but the actual getopt_long configuration uses '-e'. This mismatch can confuse users and lead to incorrect command-line usage. This patch updates the usage string to correctly show:

	"-e, --threads NRTHR"

to match the implementation.

Note: checkpatch.pl reports a false-positive spelling warning on 'Run', which is intentional.

---
 tools/tracing/latency/latency-collector.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index f7ed8084e16ad..ec95b94f80e1f 100644
@@ -1725,7 +1725,7 @@ static void show_usage(void)
 "-n, --notrace\t\tIf latency is detected, do not print out the content of\n"
 "\t\t\tthe trace file to standard output\n\n"
 
-"-t, --threads NRTHR\tRun NRTHR threads for printing. Default is %d.\n\n"
+"-e, --threads NRTHR\tRun NRTHR threads for printing. Default is %d.\n\n"
 
 "-r, --random\t\tArbitrarily sleep a certain amount of time, default\n"
 "\t\t\t%ld ms, before reading the trace file. The\n"

2.51.0

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

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

From: Long Li <[email protected]>

commit d062463edf1770427dc2d637df4088df4835aa47 upstream.

Hyper-V may offer a non latency sensitive device with subchannels without monitor bit enabled. The decision is entirely on the Hyper-V host not configurable within guest.

When a device has subchannels, also signal events for the subchannel if its monitor bit is disabled.

This patch also removes the memory barrier when monitor bit is enabled as it is not necessary. The memory barrier is only needed between setting up interrupt mask and calling vmbus_set_event() when monitor bit is disabled.

---
 drivers/uio/uio_hv_generic.c |   21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

@@ -80,9 +80,15 @@ hv_uio_irqcontrol(struct uio_info *info,
 {
 	struct hv_uio_private_data *pdata = info->priv;
 	struct hv_device *dev = pdata->device;
+	struct vmbus_channel *primary, *sc;
 
-	dev->channel->inbound.ring_buffer->interrupt_mask = !irq_state;
-	virt_mb();
+	primary = dev->channel;
+	primary->inbound.ring_buffer->interrupt_mask = !irq_state;
+
+	mutex_lock(&vmbus_connection.channel_mutex);
+	list_for_each_entry(sc, &primary->sc_list, sc_list)
+		sc->inbound.ring_buffer->interrupt_mask = !irq_state;
+	mutex_unlock(&vmbus_connection.channel_mutex);
 
 	return 0;
 }

@@ -93,11 +99,18 @@ hv_uio_irqcontrol(struct uio_info *info,
 static void hv_uio_channel_cb(void *context)
 {
 	struct vmbus_channel *chan = context;
-	struct hv_device *hv_dev = chan->device_obj;
-	struct hv_uio_private_data *pdata = hv_get_drvdata(hv_dev);
+	struct hv_device *hv_dev;
+	struct hv_uio_private_data *pdata;
 
 	virt_mb();
 
+	/*
+	 * The callback may come from a subchannel, in which case look
+	 * for the hv device in the primary channel
+	 */
+	hv_dev = chan->primary_channel ?
+		 chan->primary_channel->device_obj : chan->device_obj;
+	pdata = hv_get_drvdata(hv_dev);
 	uio_event_notify(&pdata->info);
 }
 

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

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

From: Kiryl Shutsemau <[email protected]>

commit fa04f5b60fda62c98a53a60de3a1e763f11feb41 upstream.

Accesses within VMA, but beyond i_size rounded up to PAGE_SIZE are supposed to generate SIGBUS.

This behavior might not be respected on truncation.

During truncation, the kernel splits a large folio in order to reclaim memory. As a side effect, it unmaps the folio and destroys PMD mappings of the folio. The folio will be refaulted as PTEs and SIGBUS semantics are preserved.

However, if the split fails, PMD mappings are preserved and the user will not receive SIGBUS on any accesses within the PMD.

Unmap the folio on split failure. It will lead to refault as PTEs and preserve SIGBUS semantics.

Make an exception for shmem/tmpfs that for long time intentionally mapped with PMDs across i_size.

---
 mm/truncate.c |   27 ++++++++++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

@@ -196,6 +196,31 @@ int truncate_inode_folio(struct address_
 	return 0;
 }
 
+static int try_folio_split_or_unmap(struct folio *folio)
+{
+	enum ttu_flags ttu_flags =
+		TTU_SYNC |
+		TTU_SPLIT_HUGE_PMD |
+		TTU_IGNORE_MLOCK;
+	int ret;
+
+	ret = split_folio(folio);
+
+	/*
+	 * If the split fails, unmap the folio, so it will be refaulted
+	 * with PTEs to respect SIGBUS semantics.
+	 *
+	 * Make an exception for shmem/tmpfs that for long time
+	 * intentionally mapped with PMDs across i_size.
+	 */
+	if (ret && !shmem_mapping(folio->mapping)) {
+		try_to_unmap(folio, ttu_flags);
+		WARN_ON(folio_mapped(folio));
+	}
+
+	return ret;
+}
+
 /*
  * Handle partial folios.  The folio may be entirely within the
  * range if a split has raced with us.  If not, we zero the part of the

@@ -239,7 +264,7 @@ bool truncate_inode_partial_folio(struct
 		folio_invalidate(folio, offset, length);
 	if (!folio_test_large(folio))
 		return true;
-	if (split_folio(folio) == 0)
+	if (try_folio_split_or_unmap(folio) == 0)
 		return true;
 	if (folio_test_dirty(folio))
 		return false;

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

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

From: Martin Kaiser <[email protected]>

commit 91a54090026f84ceffaa12ac53c99b9f162946f6 upstream.

maple_tree tracepoints contain pointers to function names. Such a pointer is saved when a tracepoint logs an event. There's no guarantee that it's still valid when the event is parsed later and the pointer is dereferenced.

The kernel warns about these unsafe pointers.

	event 'ma_read' has unsafe pointer field 'fn'
	WARNING: kernel/trace/trace.c:3779 at ignore_event+0x1da/0x1e4

Mark the function names as tracepoint_string() to fix the events.

One case that doesn't work without my patch would be trace-cmd record to save the binary ringbuffer and trace-cmd report to parse it in userspace. The address of __func__ can't be dereferenced from userspace but tracepoint_string will add an entry to /sys/kernel/tracing/printk_formats

---
 lib/maple_tree.c |   30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

@@ -62,6 +62,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/maple_tree.h>
 
+#define TP_FCT tracepoint_string(__func__)
+
 #define MA_ROOT_PARENT 1
 
 /*

@@ -3165,7 +3167,7 @@ static inline int mas_rebalance(struct m
 	MA_STATE(l_mas, mas->tree, mas->index, mas->last);
 	MA_STATE(r_mas, mas->tree, mas->index, mas->last);
 
-	trace_ma_op(__func__, mas);
+	trace_ma_op(TP_FCT, mas);
 
 	/*
 	 * Rebalancing occurs if a node is insufficient.  Data is rebalanced

@@ -3542,7 +3544,7 @@ static int mas_split(struct ma_state *ma
 	MA_STATE(prev_r_mas, mas->tree, mas->index, mas->last);
 	MA_TOPIARY(mat, mas->tree);
 
-	trace_ma_op(__func__, mas);
+	trace_ma_op(TP_FCT, mas);
 	mas->depth = mas_mt_height(mas);
 	/* Allocation failures will happen early. */
 	mas_node_count(mas, 1 + mas->depth * 2);

@@ -3786,7 +3788,7 @@ static bool mas_is_span_wr(struct ma_wr_
 			return false;
 	}
 
-	trace_ma_write(__func__, wr_mas->mas, piv, entry);
+	trace_ma_write(TP_FCT, wr_mas->mas, piv, entry);
 
 	return true;
 }

@@ -4035,7 +4037,7 @@ static inline int mas_wr_spanning_store(
 	 * of data may happen.
 	 */
 	mas = wr_mas->mas;
-	trace_ma_op(__func__, mas);
+	trace_ma_op(TP_FCT, mas);
 
 	if (unlikely(!mas->index && mas->last == ULONG_MAX))
 		return mas_new_root(mas, wr_mas->entry);

@@ -4221,7 +4223,7 @@ done:
 	} else {
 		memcpy(wr_mas->node, newnode, sizeof(struct maple_node));
 	}
-	trace_ma_write(__func__, mas, 0, wr_mas->entry);
+	trace_ma_write(TP_FCT, mas, 0, wr_mas->entry);
 	mas_update_gap(mas);
 	return true;
 }

@@ -4276,7 +4278,7 @@ static inline bool mas_wr_slot_store(str
 	mas->offset++; /* Keep mas accurate. */
 
 done:
-	trace_ma_write(__func__, mas, 0, wr_mas->entry);
+	trace_ma_write(TP_FCT, mas, 0, wr_mas->entry);
 	mas_update_gap(mas);
 	return true;
 }

@@ -4377,7 +4379,7 @@ static void mas_wr_bnode(struct ma_wr_st
 {
 	struct maple_big_node b_node;
 
-	trace_ma_write(__func__, wr_mas->mas, 0, wr_mas->entry);
+	trace_ma_write(TP_FCT, wr_mas->mas, 0, wr_mas->entry);
 	memset(&b_node, 0, sizeof(struct maple_big_node));
 	mas_store_b_node(wr_mas, &b_node, wr_mas->offset_end);
 	mas_commit_b_node(wr_mas, &b_node, wr_mas->node_end);