6.10.13-rc1 review

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

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

From: Hannes Reinecke <[email protected]>

[ Upstream commit 63bcf9014e95a7d279d10d8e2caa5d88db2b1855 ]

NVME_NSHEAD_DISK_LIVE is a flag for struct nvme_ns_head, not nvme_ns. The current code has a typo causing NVME_NSHEAD_DISK_LIVE never to be cleared once device_add_disk_fails, causing the system never to create the 'generic' character device. Even several rescan attempts will change the situation and the system has to be rebooted to fix the issue.

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

index 03a6868f4dbc1..a47d35102b7ce 100644
@@ -587,7 +587,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 		rc = device_add_disk(&head->subsys->dev, head->disk,
 				     nvme_ns_attr_groups);
 		if (rc) {
-			clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags);
+			clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags);
 			return;
 		}
 		nvme_add_ns_head_cdev(head);

2.43.0

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

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

From: Guillaume Stols <[email protected]>

[ Upstream commit 8dc4594b54dbaaba40dc8884ad3d42083de39434 ]

gpiod_set_array_value was misused here: the implementation relied on the assumption that an unsigned long was required for each gpio, while the function expects a bit array stored in "as much unsigned long as needed for storing one bit per GPIO", i.e it is using a bit field.

This leaded to incorrect parameter passed to gpiod_set_array_value, that would set 1 value instead of 3.
It also prevents to select the software mode correctly for the AD7606B.

---
 drivers/iio/adc/ad7606.c     | 4 ++--
 drivers/iio/adc/ad7606_spi.c | 5 +++--
 2 files changed, 5 insertions(+), 4 deletions(-)

index 1c08c0921ee71..8c66b1e364014 100644
@@ -215,9 +215,9 @@ static int ad7606_write_os_hw(struct iio_dev *indio_dev, int val)
 	struct ad7606_state *st = iio_priv(indio_dev);
 	DECLARE_BITMAP(values, 3);
 
-	values[0] = val;
+	values[0] = val & GENMASK(2, 0);
 
-	gpiod_set_array_value(ARRAY_SIZE(values), st->gpio_os->desc,
+	gpiod_set_array_value(st->gpio_os->ndescs, st->gpio_os->desc,
 			      st->gpio_os->info, values);
 
 	/* AD7616 requires a reset to update value */

index 263a778bcf253..287a0591533b6 100644
@@ -249,8 +249,9 @@ static int ad7616_sw_mode_config(struct iio_dev *indio_dev)
 static int ad7606B_sw_mode_config(struct iio_dev *indio_dev)
 {
 	struct ad7606_state *st = iio_priv(indio_dev);
-	unsigned long os[3] = {1};
+	DECLARE_BITMAP(os, 3);
 
+	bitmap_fill(os, 3);
 	/*
 	 * Software mode is enabled when all three oversampling
 	 * pins are set to high. If oversampling gpios are defined

@@ -258,7 +259,7 @@ static int ad7606B_sw_mode_config(struct iio_dev *indio_dev)
 	 * otherwise, they must be hardwired to VDD
 	 */
 	if (st->gpio_os) {
-		gpiod_set_array_value(ARRAY_SIZE(os),
+		gpiod_set_array_value(st->gpio_os->ndescs,
 				      st->gpio_os->desc, st->gpio_os->info, os);
 	}
 	/* OS of 128 and 256 are available only in software mode */

2.43.0

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

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

From: Guillaume Stols <[email protected]>

[ Upstream commit 059fe4f8bbdf5cad212e1aeeb3e8968c80b9ff3b ]

The binding's documentation specifies that "As the line is active low, it should be marked GPIO_ACTIVE_LOW". However, in the driver, it was handled the opposite way. This commit sets the driver's behaviour in sync with the documentation

---
 drivers/iio/adc/ad7606.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 8c66b1e364014..4d755ffc3f414 100644
@@ -422,7 +422,7 @@ static int ad7606_request_gpios(struct ad7606_state *st)
 		return PTR_ERR(st->gpio_range);
 
 	st->gpio_standby = devm_gpiod_get_optional(dev, "standby",
-						   GPIOD_OUT_HIGH);
+						   GPIOD_OUT_LOW);
 	if (IS_ERR(st->gpio_standby))
 		return PTR_ERR(st->gpio_standby);
 

@@ -665,7 +665,7 @@ static int ad7606_suspend(struct device *dev)
 
 	if (st->gpio_standby) {
 		gpiod_set_value(st->gpio_range, 1);
-		gpiod_set_value(st->gpio_standby, 0);
+		gpiod_set_value(st->gpio_standby, 1);
 	}
 
 	return 0;

2.43.0

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

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

From: Zijun Hu <[email protected]>

[ Upstream commit 6d8249ac29bc23260dfa9747eb398ce76012d73c ]

For class-device, device_rename() failure maybe cause unexpected link name within its class folder as explained below:

/sys/class/.../old_name -> /sys/devices/.../old_name device_rename(..., new_name) and failed /sys/class/.../new_name -> /sys/devices/.../old_name

Fixed by undoing renaming link if renaming kobject failed.

---
 drivers/base/core.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

index b5399262198a6..6c1a944c00d9b 100644
@@ -4515,9 +4515,11 @@ EXPORT_SYMBOL_GPL(device_destroy);
  */
 int device_rename(struct device *dev, const char *new_name)
 {
+	struct subsys_private *sp = NULL;
 	struct kobject *kobj = &dev->kobj;
 	char *old_device_name = NULL;
 	int error;
+	bool is_link_renamed = false;
 
 	dev = get_device(dev);
 	if (!dev)

@@ -4532,7 +4534,7 @@ int device_rename(struct device *dev, const char *new_name)
 	}
 
 	if (dev->class) {
-		struct subsys_private *sp = class_to_subsys(dev->class);
+		sp = class_to_subsys(dev->class);
 
 		if (!sp) {
 			error = -EINVAL;

@@ -4541,16 +4543,19 @@ int device_rename(struct device *dev, const char *new_name)
 
 		error = sysfs_rename_link_ns(&sp->subsys.kobj, kobj, old_device_name,
 					     new_name, kobject_namespace(kobj));
-		subsys_put(sp);
 		if (error)
 			goto out;
+
+		is_link_renamed = true;
 	}
 
 	error = kobject_rename(kobj, new_name);
-	if (error)
-		goto out;
-
 out:
+	if (error && is_link_renamed)
+		sysfs_rename_link_ns(&sp->subsys.kobj, kobj, new_name,
+				     old_device_name, kobject_namespace(kobj));
+	subsys_put(sp);
+
 	put_device(dev);
 
 	kfree(old_device_name);

2.43.0

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

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

From: Antoniu Miclaus <[email protected]>

[ Upstream commit 7d34b4ad8cd2867b130b5b8d7d76d0d6092bd019 ]

Fix description of the filter_mode_available attribute by pointing to the correct name of the attribute that can be written with valid values.

---
 Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818 | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 31dbb390573ff..c431f0a13cf50 100644
@@ -3,7 +3,7 @@ KernelVersion:
 Contact:	[email protected]
 Description:
 		Reading this returns the valid values that can be written to the
-		on_altvoltage0_mode attribute:
+		filter_mode attribute:
 
 		- auto -> Adjust bandpass filter to track changes in input clock rate.
 		- manual -> disable/unregister the clock rate notifier / input clock tracking.

2.43.0

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

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

From: Vasileios Amoiridis <[email protected]>

[ Upstream commit 77641e5a477d428335cd094b88ac54e09ccb70f4 ]

Add mutexes in the {read/write}_raw() functions of the device to guard the read/write of data from/to the device. This is necessary because for any operation other than temperature, multiple reads need to take place from the device. Even though regmap has a locking by itself, it won't protect us from multiple applications trying to read at the same time temperature and pressure since the pressure reading includes an internal temperature reading and there is nothing to ensure that this temperature+pressure reading will happen sequentially without any other operation interfering in the meantime.

---
 drivers/iio/chemical/bme680_core.c | 7 +++++++
 1 file changed, 7 insertions(+)

index 500f56834b01f..a6bf689833dad 100644
@@ -10,6 +10,7 @@
  */
 #include <linux/acpi.h>
 #include <linux/bitfield.h>
+#include <linux/cleanup.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/module.h>

@@ -52,6 +53,7 @@ struct bme680_calib {
 struct bme680_data {
 	struct regmap *regmap;
 	struct bme680_calib bme680;
+	struct mutex lock; /* Protect multiple serial R/W ops to device. */
 	u8 oversampling_temp;
 	u8 oversampling_press;
 	u8 oversampling_humid;

@@ -827,6 +829,8 @@ static int bme680_read_raw(struct iio_dev *indio_dev,
 {
 	struct bme680_data *data = iio_priv(indio_dev);
 
+	guard(mutex)(&data->lock);
+
 	switch (mask) {
 	case IIO_CHAN_INFO_PROCESSED:
 		switch (chan->type) {

@@ -871,6 +875,8 @@ static int bme680_write_raw(struct iio_dev *indio_dev,
 {
 	struct bme680_data *data = iio_priv(indio_dev);
 
+	guard(mutex)(&data->lock);
+
 	if (val2 != 0)
 		return -EINVAL;
 

@@ -967,6 +973,7 @@ int bme680_core_probe(struct device *dev, struct regmap *regmap,
 		name = bme680_match_acpi_device(dev);
 
 	data = iio_priv(indio_dev);
+	mutex_init(&data->lock);
 	dev_set_drvdata(dev, indio_dev);
 	data->regmap = regmap;
 	indio_dev->name = name;

2.43.0

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

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

From: Krzysztof Kozlowski <[email protected]>

[ Upstream commit da6e3160df230692bbd48a6d52318035f19595e2 ]

All compatibles in this binding without prefixes were deprecated, so adding a new deprecated one after some time is not allowed, because it defies the core logic of deprecating things.

Drop the AK09916 vendorless compatible.

---
 drivers/iio/magnetometer/ak8975.c | 1 -
 1 file changed, 1 deletion(-)

index dd466c5fa6214..ccbebe5b66cde 100644
@@ -1081,7 +1081,6 @@ static const struct of_device_id ak8975_of_match[] = {
 	{ .compatible = "asahi-kasei,ak09912", .data = &ak_def_array[AK09912] },
 	{ .compatible = "ak09912", .data = &ak_def_array[AK09912] },
 	{ .compatible = "asahi-kasei,ak09916", .data = &ak_def_array[AK09916] },
-	{ .compatible = "ak09916", .data = &ak_def_array[AK09916] },
 	{}
 };
 MODULE_DEVICE_TABLE(of, ak8975_of_match);

2.43.0

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

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

From: Krzysztof Kozlowski <[email protected]>

[ Upstream commit c7668ac67bc21aebdd8e2d7f839bfffba31b7713 ]

All compatibles in this binding without prefixes were deprecated, so adding a new deprecated one after some time is not allowed, because it defies the core logic of deprecating things.

Drop the AK09916 vendorless compatible.

---
 .../devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml | 1 -
 1 file changed, 1 deletion(-)

index 9790f75fc669e..fe5145d3b73cf 100644
@@ -23,7 +23,6 @@ properties:
           - ak8963
           - ak09911
           - ak09912
-          - ak09916
         deprecated: true
 
   reg:

2.43.0

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

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

From: Jinjie Ruan <[email protected]>

[ Upstream commit 18ec12c97b39ff6aa15beb8d2b25d15cd44b87d8 ]

Inject fault while probing of-fpga-region, if kasprintf() fails in module_add_driver(), the second sysfs_remove_link() in exit path will cause null-ptr-deref as below because kernfs_name_hash() will call strlen() with NULL driver_name.

Fix it by releasing resources based on the exit path sequence.

	 KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
	 Mem abort info:
	   ESR = 0x0000000096000005
	   EC = 0x25: DABT (current EL), IL = 32 bits
	   SET = 0, FnV = 0
	   EA = 0, S1PTW = 0
	   FSC = 0x05: level 1 translation fault
	 Data abort info:
	   ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000
	   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
	   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
	 [dfffffc000000000] address between user and kernel address ranges
	 Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP
	 Dumping ftrace buffer:
	    (ftrace buffer empty)
	 Modules linked in: of_fpga_region(+) fpga_region fpga_bridge cfg80211 rfkill 8021q garp mrp stp llc ipv6 [last unloaded: of_fpga_region]
	 CPU: 2 UID: 0 PID: 2036 Comm: modprobe Not tainted 6.11.0-rc2-g6a0e38264012 #295
	 Hardware name: linux,dummy-virt (DT)
	 pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
	 pc : strlen+0x24/0xb0
	 lr : kernfs_name_hash+0x1c/0xc4
	 sp : ffffffc081f97380
	 x29: ffffffc081f97380 x28: ffffffc081f97b90 x27: ffffff80c821c2a0
	 x26: ffffffedac0be418 x25: 0000000000000000 x24: ffffff80c09d2000
	 x23: 0000000000000000 x22: 0000000000000000 x21: 0000000000000000
	 x20: 0000000000000000 x19: 0000000000000000 x18: 0000000000001840
	 x17: 0000000000000000 x16: 0000000000000000 x15: 1ffffff8103f2e42
	 x14: 00000000f1f1f1f1 x13: 0000000000000004 x12: ffffffb01812d61d
	 x11: 1ffffff01812d61c x10: ffffffb01812d61c x9 : dfffffc000000000
	 x8 : 0000004fe7ed29e4 x7 : ffffff80c096b0e7 x6 : 0000000000000001
	 x5 : ffffff80c096b0e0 x4 : 1ffffffdb990efa2 x3 : 0000000000000000
	 x2 : 0000000000000000 x1 : dfffffc000000000 x0 : 0000000000000000
	 Call trace:
	  strlen+0x24/0xb0
	  kernfs_name_hash+0x1c/0xc4
	  kernfs_find_ns+0x118/0x2e8
	  kernfs_remove_by_name_ns+0x80/0x100
	  sysfs_remove_link+0x74/0xa8
	  module_add_driver+0x278/0x394
	  bus_add_driver+0x1f0/0x43c
	  driver_register+0xf4/0x3c0
	  __platform_driver_register+0x60/0x88
	  of_fpga_region_init+0x20/0x1000 [of_fpga_region]
	  do_one_initcall+0x110/0x788
	  do_init_module+0x1dc/0x5c8
	  load_module+0x3c38/0x4cac
	  init_module_from_file+0xd4/0x128
	  idempotent_init_module+0x2cc/0x528
	  __arm64_sys_finit_module+0xac/0x100
	  invoke_syscall+0x6c/0x258
	  el0_svc_common.constprop.0+0x160/0x22c
	  do_el0_svc+0x44/0x5c
	  el0_svc+0x48/0xb8
	  el0t_64_sync_handler+0x13c/0x158
	  el0t_64_sync+0x190/0x194
	 Code: f2fbffe1 a90157f4 12000802 aa0003f5 (38e16861)
	 ---[ end trace 0000000000000000 ]---
	 Kernel panic - not syncing: Oops: Fatal exception

---
 drivers/base/module.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

index b0b79b9c189d4..0d5c5da367f72 100644
@@ -66,27 +66,31 @@ int module_add_driver(struct module *mod, struct device_driver *drv)
 	driver_name = make_driver_name(drv);
 	if (!driver_name) {
 		ret = -ENOMEM;
-		goto out;
+		goto out_remove_kobj;
 	}
 
 	module_create_drivers_dir(mk);
 	if (!mk->drivers_dir) {
 		ret = -EINVAL;
-		goto out;
+		goto out_free_driver_name;
 	}
 
 	ret = sysfs_create_link(mk->drivers_dir, &drv->p->kobj, driver_name);
 	if (ret)
-		goto out;
+		goto out_remove_drivers_dir;
 
 	kfree(driver_name);
 
 	return 0;
-out:
-	sysfs_remove_link(&drv->p->kobj, "module");
+
+out_remove_drivers_dir:
 	sysfs_remove_link(mk->drivers_dir, driver_name);
+
+out_free_driver_name:
 	kfree(driver_name);
 
+out_remove_kobj:
+	sysfs_remove_link(&drv->p->kobj, "module");
 	return ret;
 }
 

2.43.0

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

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

From: Markus Schneider-Pargmann <[email protected]>

[ Upstream commit 35e648a16018b747897be2ccc3ce95ff23237bb5 ]

If devm_request_irq fails, the code does not cleanup many things that were setup before. Instead of directly returning ret we should jump to err.

---
 drivers/tty/serial/8250/8250_omap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index afef1dd4ddf49..fca5f25d693a7 100644
@@ -1581,7 +1581,7 @@ static int omap8250_probe(struct platform_device *pdev)
 	ret = devm_request_irq(&pdev->dev, up.port.irq, omap8250_irq, 0,
 			       dev_name(&pdev->dev), priv);
 	if (ret < 0)
-		return ret;
+		goto err;
 
 	priv->wakeirq = irq_of_parse_and_map(np, 1);
 

2.43.0

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

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

From: Jie Gan <[email protected]>

[ Upstream commit 14f5fa9b5fcbe2b3d5098893aba6ad62254d2ef6 ]

The coresight_disable_source_sysfs function should verify the mode of the coresight device before disabling the source.

However, the mode for the TPDM device is always set to CS_MODE_DISABLED, resulting in the check consistently failing. As a result, TPDM cannot be properly disabled.

Configure CS_MODE_SYSFS/CS_MODE_PERF during the enablement. Configure CS_MODE_DISABLED during the disablement.

---
 drivers/hwtracing/coresight/coresight-tpdm.c | 6 ++++++
 1 file changed, 6 insertions(+)

index 0726f8842552c..5c5a4b3fe6871 100644
@@ -449,6 +449,11 @@ static int tpdm_enable(struct coresight_device *csdev, struct perf_event *event,
 		return -EBUSY;
 	}
 
+	if (!coresight_take_mode(csdev, mode)) {
+		spin_unlock(&drvdata->spinlock);
+		return -EBUSY;
+	}
+
 	__tpdm_enable(drvdata);
 	drvdata->enable = true;
 	spin_unlock(&drvdata->spinlock);

@@ -506,6 +511,7 @@ static void tpdm_disable(struct coresight_device *csdev,
 	}
 
 	__tpdm_disable(drvdata);
+	coresight_set_mode(csdev, CS_MODE_DISABLED);
 	drvdata->enable = false;
 	spin_unlock(&drvdata->spinlock);
 

2.43.0

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

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

From: Jie Gan <[email protected]>

[ Upstream commit e6b64cda393efd84709ab3df2e42d36d36d7553e ]

The coresight_disable_source_sysfs function should verify the mode of the coresight device before disabling the source. However, the mode for the dummy source device is always set to CS_MODE_DISABLED, resulting in the check consistently failing. As a result, dummy source cannot be properly disabled.

Configure CS_MODE_SYSFS/CS_MODE_PERF during the enablement. Configure CS_MODE_DISABLED during the disablement.

---
 drivers/hwtracing/coresight/coresight-dummy.c | 4 ++++
 1 file changed, 4 insertions(+)

index ac70c0b491beb..dab389a5507c1 100644
@@ -23,6 +23,9 @@ DEFINE_CORESIGHT_DEVLIST(sink_devs, "dummy_sink");
 static int dummy_source_enable(struct coresight_device *csdev,
 			       struct perf_event *event, enum cs_mode mode)
 {
+	if (!coresight_take_mode(csdev, mode))
+		return -EBUSY;
+
 	dev_dbg(csdev->dev.parent, "Dummy source enabled\n");
 
 	return 0;

@@ -31,6 +34,7 @@ static int dummy_source_enable(struct coresight_device *csdev,
 static void dummy_source_disable(struct coresight_device *csdev,
 				 struct perf_event *event)
 {
+	coresight_set_mode(csdev, CS_MODE_DISABLED);
 	dev_dbg(csdev->dev.parent, "Dummy source disabled\n");
 }
 

2.43.0

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

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

From: Suzuki K Poulose <[email protected]>

[ Upstream commit c58dc5a1f886f2fcc1133746d0cbaa1fe7fd44ff ]

Running perf with cs_etm on Juno triggers the following kmemleak warning !

:~# cat /sys/kernel/debug/kmemleak
 unreferenced object 0xffffff8806b6d720 (size 96):
 comm "perf", pid 562, jiffies 4297810960
 hex dump (first 32 bytes):
 38 d8 13 07 88 ff ff ff 00 d0 9e 85 c0 ff ff ff  8...............
 00 10 00 88 c0 ff ff ff 00 f0 ff f7 ff 00 00 00  ................
 backtrace (crc 1dbf6e00):
 [<ffffffc08107381c>] kmemleak_alloc+0xbc/0xd8
 [<ffffffc0802f9798>] kmalloc_trace_noprof+0x220/0x2e8
 [<ffffffc07bb71948>] tmc_alloc_sg_table+0x48/0x208 [coresight_tmc]
 [<ffffffc07bb71cbc>] tmc_etr_alloc_sg_buf+0xac/0x240 [coresight_tmc]
 [<ffffffc07bb72538>] tmc_alloc_etr_buf.constprop.0+0x1f0/0x260 [coresight_tmc]
 [<ffffffc07bb7280c>] alloc_etr_buf.constprop.0.isra.0+0x74/0xa8 [coresight_tmc]
 [<ffffffc07bb72950>] tmc_alloc_etr_buffer+0x110/0x260 [coresight_tmc]
 [<ffffffc07bb38afc>] etm_setup_aux+0x204/0x3b0 [coresight]
 [<ffffffc08025837c>] rb_alloc_aux+0x20c/0x318
 [<ffffffc08024dd84>] perf_mmap+0x2e4/0x7a0
 [<ffffffc0802cceb0>] mmap_region+0x3b0/0xa08
 [<ffffffc0802cd8a8>] do_mmap+0x3a0/0x500
 [<ffffffc080295328>] vm_mmap_pgoff+0x100/0x1d0
 [<ffffffc0802cadf8>] ksys_mmap_pgoff+0xb8/0x110
 [<ffffffc080020688>] __arm64_sys_mmap+0x38/0x58
 [<ffffffc080028fc0>] invoke_syscall.constprop.0+0x58/0x100

This due to the fact that we do not free the "sg_table" itself while freeing up the SG table and data pages. Fix this by freeing the sg_table in tmc_free_sg_table().

---
 drivers/hwtracing/coresight/coresight-tmc-etr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index e75428fa1592a..610ad51cda656 100644
@@ -261,6 +261,7 @@ void tmc_free_sg_table(struct tmc_sg_table *sg_table)
 {
 	tmc_free_table_pages(sg_table);
 	tmc_free_data_pages(sg_table);
+	kfree(sg_table);
 }
 EXPORT_SYMBOL_GPL(tmc_free_sg_table);
 

@@ -342,7 +343,6 @@ struct tmc_sg_table *tmc_alloc_sg_table(struct device *dev,
 		rc = tmc_alloc_table_pages(sg_table);
 	if (rc) {
 		tmc_free_sg_table(sg_table);
-		kfree(sg_table);
 		return ERR_PTR(rc);
 	}
 

2.43.0

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

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

From: Kees Cook <[email protected]>

[ Upstream commit c801ed86840ec38b2a9bcafeee3d7c9e14c743f3 ]

With the new __counted_by annotation, the "num_nodes" struct member must be set before accessing the "nodes" array. This initialization was done in other places where a new struct icc_onecell_data is allocated, but this case in icc_clk_register() was missed. Set "num_nodes" after allocation.

---
 drivers/interconnect/icc-clk.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

index d787f2ea36d97..a91df709cfb2f 100644
@@ -87,6 +87,7 @@ struct icc_provider *icc_clk_register(struct device *dev,
 	onecell = devm_kzalloc(dev, struct_size(onecell, nodes, 2 * num_clocks), GFP_KERNEL);
 	if (!onecell)
 		return ERR_PTR(-ENOMEM);
+	onecell->num_nodes = 2 * num_clocks;
 
 	qp = devm_kzalloc(dev, struct_size(qp, clocks, num_clocks), GFP_KERNEL);
 	if (!qp)

@@ -133,8 +134,6 @@ struct icc_provider *icc_clk_register(struct device *dev,
 		onecell->nodes[j++] = node;
 	}
 
-	onecell->num_nodes = j;
-
 	ret = icc_provider_register(provider);
 	if (ret)
 		goto err;

2.43.0

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

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

From: Dmitry Baryshkov <[email protected]>

[ Upstream commit d3681b30214eb5885092ce4586f07237dc3c522f ]

Enable the generic icc sync_state callback to ensure interconnect votes are actually taken into account, instead of being forced to the maximum value.

---
 drivers/interconnect/qcom/sm8350.c | 1 +
 1 file changed, 1 insertion(+)

index b321c3009acba..885a9d3f92e4d 100644
@@ -1965,6 +1965,7 @@ static struct platform_driver qnoc_driver = {
 	.driver = {
 		.name = "qnoc-sm8350",
 		.of_match_table = qnoc_of_match,
+		.sync_state = icc_sync_state,
 	},
 };
 module_platform_driver(qnoc_driver);

2.43.0

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

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

From: Yanfei Xu <[email protected]>

[ Upstream commit 55e268694e8b07026c88191f9b6949b6887d9ce3 ]

The function cxl_dvsec_rr_decode() retrieves and records DVSEC ranges into info->dvsec_range[], regardless of whether it is non-zero range, and the variable info->ranges indicates the number of non-zero ranges. However, in cxl_hdm_decode_init(), the validation for info->dvsec_range[] occurs in a for loop that iterates based on info->ranges. It may result in zero range to be validated but non-zero range not be validated, in turn, the number of allowed ranges is to be
0. Address it by only record non-zero ranges.

This fix is not urgent as it requires a configuration that zeroes out the first dvsec range while populating the second. This has not been observed, but it is theoretically possible. If this gets picked up for -stable, no harm done, but there is no urgency to backport.

---
 drivers/cxl/core/pci.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

index 8567dd11eaac7..205085ccf12c3 100644
@@ -390,10 +390,6 @@ int cxl_dvsec_rr_decode(struct device *dev, int d,
 
 		size |= temp & CXL_DVSEC_MEM_SIZE_LOW_MASK;
 		if (!size) {
-			info->dvsec_range[i] = (struct range) {
-				.start = 0,
-				.end = CXL_RESOURCE_NONE,
-			};
 			continue;
 		}
 

@@ -411,12 +407,10 @@ int cxl_dvsec_rr_decode(struct device *dev, int d,
 
 		base |= temp & CXL_DVSEC_MEM_BASE_LOW_MASK;
 
-		info->dvsec_range[i] = (struct range) {
+		info->dvsec_range[ranges++] = (struct range) {
 			.start = base,
 			.end = base + size - 1
 		};
-
-		ranges++;
 	}
 
 	info->ranges = ranges;

2.43.0

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

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

From: Dragos Tatulea <[email protected]>

[ Upstream commit dc12502905b7a3de9097ea6b98870470c2921e09 ]

Certain error paths from mlx5_vdpa_dev_add() can end up releasing mr resources which never got initialized in the first place.

This patch adds the missing check in mlx5_vdpa_destroy_mr_resources() to block releasing non-initialized mr resources.

Reference trace:

mlx5_core 0000:08:00.2: mlx5_vdpa_dev_add:3274:(pid 2700) warning: No mac address provisioned?

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 140216067 P4D 0
  Oops: 0000 [#1] PREEMPT SMP NOPTI
  CPU: 8 PID: 2700 Comm: vdpa Kdump: loaded Not tainted 5.14.0-496.el9.x86_64 #1
  Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
  RIP: 0010:vhost_iotlb_del_range+0xf/0xe0 [vhost_iotlb]
  Code: [...]
  RSP: 0018:ff1c823ac23077f0 EFLAGS: 00010246
  RAX: ffffffffc1a21a60 RBX: ffffffff899567a0 RCX: 0000000000000000
  RDX: ffffffffffffffff RSI: 0000000000000000 RDI: 0000000000000000
  RBP: ff1bda1f7c21e800 R08: 0000000000000000 R09: ff1c823ac2307670
  R10: ff1c823ac2307668 R11: ffffffff8a9e7b68 R12: 0000000000000000
  R13: 0000000000000000 R14: ff1bda1f43e341a0 R15: 00000000ffffffea
  FS:  00007f56eba7c740(0000) GS:ff1bda269f800000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000000 CR3: 0000000104d90001 CR4: 0000000000771ef0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  PKRU: 55555554
  Call Trace:

   ? show_trace_log_lvl+0x1c4/0x2df
   ? show_trace_log_lvl+0x1c4/0x2df
   ? mlx5_vdpa_free+0x3d/0x150 [mlx5_vdpa]
   ? __die_body.cold+0x8/0xd
   ? page_fault_oops+0x134/0x170
   ? __irq_work_queue_local+0x2b/0xc0
   ? irq_work_queue+0x2c/0x50
   ? exc_page_fault+0x62/0x150
   ? asm_exc_page_fault+0x22/0x30
   ? __pfx_mlx5_vdpa_free+0x10/0x10 [mlx5_vdpa]
   ? vhost_iotlb_del_range+0xf/0xe0 [vhost_iotlb]
   mlx5_vdpa_free+0x3d/0x150 [mlx5_vdpa]
   vdpa_release_dev+0x1e/0x50 [vdpa]
   device_release+0x31/0x90
   kobject_cleanup+0x37/0x130
   mlx5_vdpa_dev_add+0x2d2/0x7a0 [mlx5_vdpa]
   vdpa_nl_cmd_dev_add_set_doit+0x277/0x4c0 [vdpa]
   genl_family_rcv_msg_doit+0xd9/0x130
   genl_family_rcv_msg+0x14d/0x220
   ? __pfx_vdpa_nl_cmd_dev_add_set_doit+0x10/0x10 [vdpa]
   ? _copy_to_user+0x1a/0x30
   ? move_addr_to_user+0x4b/0xe0
   genl_rcv_msg+0x47/0xa0
   ? __import_iovec+0x46/0x150
   ? __pfx_genl_rcv_msg+0x10/0x10
   netlink_rcv_skb+0x54/0x100
   genl_rcv+0x24/0x40
   netlink_unicast+0x245/0x370
   netlink_sendmsg+0x206/0x440
   __sys_sendto+0x1dc/0x1f0
   ? do_read_fault+0x10c/0x1d0
   ? do_pte_missing+0x10d/0x190
   __x64_sys_sendto+0x20/0x30
   do_syscall_64+0x5c/0xf0
   ? __count_memcg_events+0x4f/0xb0
   ? mm_account_fault+0x6c/0x100
   ? handle_mm_fault+0x116/0x270
   ? do_user_addr_fault+0x1d6/0x6a0
   ? do_syscall_64+0x6b/0xf0
   ? clear_bhb_loop+0x25/0x80
   ? clear_bhb_loop+0x25/0x80
   ? clear_bhb_loop+0x25/0x80
   ? clear_bhb_loop+0x25/0x80
   ? clear_bhb_loop+0x25/0x80
   entry_SYSCALL_64_after_hwframe+0x78/0x80

Message-Id: <[email protected]>

---
 drivers/vdpa/mlx5/core/mr.c | 3 +++
 1 file changed, 3 insertions(+)

index 4758914ccf860..bf56f3d696253 100644
@@ -581,6 +581,9 @@ static void mlx5_vdpa_show_mr_leaks(struct mlx5_vdpa_dev *mvdev)
 
 void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev)
 {
+	if (!mvdev->res.valid)
+		return;
+
 	for (int i = 0; i < MLX5_VDPA_NUM_AS; i++)
 		mlx5_vdpa_update_mr(mvdev, NULL, i);
 

2.43.0

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

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

From: Jason Wang <[email protected]>

[ Upstream commit 02e9e9366fefe461719da5d173385b6685f70319 ]

We used to call irq_bypass_unregister_producer() in vhost_vdpa_setup_vq_irq() which is problematic as we don't know if the token pointer is still valid or not.

Actually, we use the eventfd_ctx as the token so the life cycle of the token should be bound to the VHOST_SET_VRING_CALL instead of vhost_vdpa_setup_vq_irq() which could be called by set_status().

Fixing this by setting up irq bypass producer's token when handling VHOST_SET_VRING_CALL and un-registering the producer before calling vhost_vring_ioctl() to prevent a possible use after free as eventfd could have been released in vhost_vring_ioctl(). And such registering and unregistering will only be done if DRIVER_OK is set.

Message-Id: <[email protected]>

---
 drivers/vhost/vdpa.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

index 6b9c12acf4381..b3d2a53f9bb77 100644
@@ -209,11 +209,9 @@ static void vhost_vdpa_setup_vq_irq(struct vhost_vdpa *v, u16 qid)
 	if (irq < 0)
 		return;
 
-	irq_bypass_unregister_producer(&vq->call_ctx.producer);
 	if (!vq->call_ctx.ctx)
 		return;
 
-	vq->call_ctx.producer.token = vq->call_ctx.ctx;
 	vq->call_ctx.producer.irq = irq;
 	ret = irq_bypass_register_producer(&vq->call_ctx.producer);
 	if (unlikely(ret))

@@ -709,6 +707,14 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 			vq->last_avail_idx = vq_state.split.avail_index;
 		}
 		break;
+	case VHOST_SET_VRING_CALL:
+		if (vq->call_ctx.ctx) {
+			if (ops->get_status(vdpa) &
+			    VIRTIO_CONFIG_S_DRIVER_OK)
+				vhost_vdpa_unsetup_vq_irq(v, idx);
+			vq->call_ctx.producer.token = NULL;
+		}
+		break;
 	}
 
 	r = vhost_vring_ioctl(&v->vdev, cmd, argp);

@@ -747,13 +753,16 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 			cb.callback = vhost_vdpa_virtqueue_cb;
 			cb.private = vq;
 			cb.trigger = vq->call_ctx.ctx;
+			vq->call_ctx.producer.token = vq->call_ctx.ctx;
+			if (ops->get_status(vdpa) &
+			    VIRTIO_CONFIG_S_DRIVER_OK)
+				vhost_vdpa_setup_vq_irq(v, idx);
 		} else {
 			cb.callback = NULL;
 			cb.private = NULL;
 			cb.trigger = NULL;
 		}
 		ops->set_vq_cb(vdpa, idx, &cb);
-		vhost_vdpa_setup_vq_irq(v, idx);
 		break;
 
 	case VHOST_SET_VRING_NUM:

@@ -1421,6 +1430,7 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)
 	for (i = 0; i < nvqs; i++) {
 		vqs[i] = &v->vqs[i];
 		vqs[i]->handle_kick = handle_vq_kick;
+		vqs[i]->call_ctx.ctx = NULL;
 	}
 	vhost_dev_init(dev, vqs, nvqs, 0, 0, 0, false,
 		       vhost_vdpa_process_iotlb_msg);

2.43.0

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

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

From: Dan Carpenter <[email protected]>

[ Upstream commit c7f06284a6427475e3df742215535ec3f6cd9662 ]

The psc->div[] array has psc->num_div elements. These values come from when we call clk_hw_register_div(). It's adc_divisors and ARRAY_SIZE(adc_divisors)) and so on. So this condition needs to be >= instead of > to prevent an out of bounds read.

---
 arch/arm/mach-ep93xx/clock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 85a496ddc6197..e9f72a529b508 100644
@@ -359,7 +359,7 @@ static unsigned long ep93xx_div_recalc_rate(struct clk_hw *hw,
 	u32 val = __raw_readl(psc->reg);
 	u8 index = (val & psc->mask) >> psc->shift;
 
-	if (index > psc->num_div)
+	if (index >= psc->num_div)
 		return 0;
 
 	return DIV_ROUND_UP_ULL(parent_rate, psc->div[index]);

2.43.0

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

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

From: Mikulas Patocka <[email protected]>

[ Upstream commit c8691cd0fc11197515ed148de0780d927bfca38b ]

This reverts commit fa247089de9936a46e290d4724cb5f0b845600f5.

The following sequence of commands causes a livelock - there will be workqueue process looping and consuming 100% CPU:

dmsetup create --notable test
truncate -s 1MiB testdata
losetup /dev/loop0 testdata
dmsetup load test --table '0 2048 linear /dev/loop0 0' dd if=/dev/zero of=/dev/dm-0 bs=16k count=1 conv=fdatasync

The livelock is caused by the commit fa247089de99. The commit claims that it fixes a race condition, however, it is unknown what the actual race condition is and what program is involved in the race condition.

When the inactive table is loaded, the nodes /dev/dm-0 and /sys/block/dm-0 are created. /dev/dm-0 has zero size at this point. When the device is suspended and resumed, the nodes /dev/mapper/test and /dev/disk/* are created.

If some program opens a block device before it is created by dmsetup or lvm, the program is buggy, so dm could just report an error as it used to do before.

---
 drivers/md/dm-rq.c |  4 +++-
 drivers/md/dm.c    | 11 ++++++++---
 2 files changed, 11 insertions(+), 4 deletions(-)

index f7e9a3632eb3d..499f8cc8a39fb 100644
@@ -496,8 +496,10 @@ static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 		map = dm_get_live_table(md, &srcu_idx);
 		if (unlikely(!map)) {
+			DMERR_LIMIT("%s: mapping table unavailable, erroring io",
+				    dm_device_name(md));
 			dm_put_live_table(md, srcu_idx);
-			return BLK_STS_RESOURCE;
+			return BLK_STS_IOERR;
 		}
 		ti = dm_table_find_target(map, 0);
 		dm_put_live_table(md, srcu_idx);

index 6e15ac4e0845c..a0b4afba8c608 100644
@@ -1880,10 +1880,15 @@ static void dm_submit_bio(struct bio *bio)
 	struct dm_table *map;
 
 	map = dm_get_live_table(md, &srcu_idx);
+	if (unlikely(!map)) {
+		DMERR_LIMIT("%s: mapping table unavailable, erroring io",
+			    dm_device_name(md));
+		bio_io_error(bio);
+		goto out;
+	}
 
-	/* If suspended, or map not yet available, queue this IO for later */
-	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) ||
-	    unlikely(!map)) {
+	/* If suspended, queue this IO for later */
+	if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
 		if (bio->bi_opf & REQ_NOWAIT)
 			bio_wouldblock_error(bio);
 		else if (bio->bi_opf & REQ_RAHEAD)

2.43.0

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

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

From: Sean Anderson <[email protected]>

[ Upstream commit ba0da2dc934ec5ac32bbeecbd0670da16ba03565 ]

As advised by Documentation/networking/napi.rst, masking IRQs after calling napi_schedule can be racy. Avoid this by only masking/scheduling if napi_schedule_prep returns true.

---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

index 88d7bc2ea7132..00b1a4cf7c4be 100644
@@ -1222,9 +1222,10 @@ static irqreturn_t axienet_tx_irq(int irq, void *_ndev)
 		u32 cr = lp->tx_dma_cr;
 
 		cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
-		axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
-
-		napi_schedule(&lp->napi_tx);
+		if (napi_schedule_prep(&lp->napi_tx)) {
+			axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
+			__napi_schedule(&lp->napi_tx);
+		}
 	}
 
 	return IRQ_HANDLED;

@@ -1266,9 +1267,10 @@ static irqreturn_t axienet_rx_irq(int irq, void *_ndev)
 		u32 cr = lp->rx_dma_cr;
 
 		cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
-		axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
-
-		napi_schedule(&lp->napi_rx);
+		if (napi_schedule_prep(&lp->napi_rx)) {
+			axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
+			__napi_schedule(&lp->napi_rx);
+		}
 	}
 
 	return IRQ_HANDLED;

2.43.0

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

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

From: Sean Anderson <[email protected]>

[ Upstream commit 5a6caa2cfabb559309b5ce29ee7c8e9ce1a9a9df ]

axienet_free_tx_chain returns the number of DMA descriptors it's handled. However, axienet_tx_poll treats the return as the number of packets. When scatter-gather SKBs are enabled, a single packet may use multiple DMA descriptors, which causes incorrect packet counts. Fix this by explicitly keepting track of the number of packets processed as separate from the DMA descriptors.

Budget does not affect the number of Tx completions we can process for NAPI, so we use the ring size as the limit instead of budget. As we no longer return the number of descriptors processed to axienet_tx_poll, we now update tx_bd_ci in axienet_free_tx_chain.

---
 .../net/ethernet/xilinx/xilinx_axienet_main.c | 23 +++++++++++--------
 1 file changed, 14 insertions(+), 9 deletions(-)

index 00b1a4cf7c4be..f1d928644b824 100644
@@ -674,15 +674,15 @@ static int axienet_device_reset(struct net_device *ndev)
  *
  * Would either be called after a successful transmit operation, or after
  * there was an error when setting up the chain.
- * Returns the number of descriptors handled.
+ * Returns the number of packets handled.
  */
 static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
 				 int nr_bds, bool force, u32 *sizep, int budget)
 {
 	struct axidma_bd *cur_p;
 	unsigned int status;
+	int i, packets = 0;
 	dma_addr_t phys;
-	int i;
 
 	for (i = 0; i < nr_bds; i++) {
 		cur_p = &lp->tx_bd_v[(first_bd + i) % lp->tx_bd_num];

@@ -701,8 +701,10 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
 				 (cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
 				 DMA_TO_DEVICE);
 
-		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK))
+		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
 			napi_consume_skb(cur_p->skb, budget);
+			packets++;
+		}
 
 		cur_p->app0 = 0;
 		cur_p->app1 = 0;

@@ -718,7 +720,13 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
 			*sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
 	}
 
-	return i;
+	if (!force) {
+		lp->tx_bd_ci += i;
+		if (lp->tx_bd_ci >= lp->tx_bd_num)
+			lp->tx_bd_ci %= lp->tx_bd_num;
+	}
+
+	return packets;
 }
 
 /**

@@ -891,13 +899,10 @@ static int axienet_tx_poll(struct napi_struct *napi, int budget)
 	u32 size = 0;
 	int packets;
 
-	packets = axienet_free_tx_chain(lp, lp->tx_bd_ci, budget, false, &size, budget);
+	packets = axienet_free_tx_chain(lp, lp->tx_bd_ci, lp->tx_bd_num, false,
+					&size, budget);
 
 	if (packets) {
-		lp->tx_bd_ci += packets;
-		if (lp->tx_bd_ci >= lp->tx_bd_num)
-			lp->tx_bd_ci %= lp->tx_bd_num;
-
 		u64_stats_update_begin(&lp->tx_stat_sync);
 		u64_stats_add(&lp->tx_packets, packets);
 		u64_stats_add(&lp->tx_bytes, size);

2.43.0

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

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

From: Eric Dumazet <[email protected]>

[ Upstream commit 9c778fe48d20ef362047e3376dee56d77f8500d4 ]

syzbot reported that nf_reject_ip6_tcphdr_put() was possibly sending garbage on the four reserved tcp bits (th->res1)

Use skb_put_zero() to clear the whole TCP header,
as done in nf_reject_ip_tcphdr_put()

BUG: KMSAN: uninit-value in nf_reject_ip6_tcphdr_put+0x688/0x6c0 net/ipv6/netfilter/nf_reject_ipv6.c:255
  nf_reject_ip6_tcphdr_put+0x688/0x6c0 net/ipv6/netfilter/nf_reject_ipv6.c:255
  nf_send_reset6+0xd84/0x15b0 net/ipv6/netfilter/nf_reject_ipv6.c:344
  nft_reject_inet_eval+0x3c1/0x880 net/netfilter/nft_reject_inet.c:48
  expr_call_ops_eval net/netfilter/nf_tables_core.c:240 [inline]
  nft_do_chain+0x438/0x22a0 net/netfilter/nf_tables_core.c:288
  nft_do_chain_inet+0x41a/0x4f0 net/netfilter/nft_chain_filter.c:161
  nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline]
  nf_hook_slow+0xf4/0x400 net/netfilter/core.c:626
  nf_hook include/linux/netfilter.h:269 [inline]
  NF_HOOK include/linux/netfilter.h:312 [inline]
  ipv6_rcv+0x29b/0x390 net/ipv6/ip6_input.c:310
  __netif_receive_skb_one_core net/core/dev.c:5661 [inline]
  __netif_receive_skb+0x1da/0xa00 net/core/dev.c:5775
  process_backlog+0x4ad/0xa50 net/core/dev.c:6108
  __napi_poll+0xe7/0x980 net/core/dev.c:6772
  napi_poll net/core/dev.c:6841 [inline]
  net_rx_action+0xa5a/0x19b0 net/core/dev.c:6963
  handle_softirqs+0x1ce/0x800 kernel/softirq.c:554
  __do_softirq+0x14/0x1a kernel/softirq.c:588
  do_softirq+0x9a/0x100 kernel/softirq.c:455
  __local_bh_enable_ip+0x9f/0xb0 kernel/softirq.c:382
  local_bh_enable include/linux/bottom_half.h:33 [inline]
  rcu_read_unlock_bh include/linux/rcupdate.h:908 [inline]
  __dev_queue_xmit+0x2692/0x5610 net/core/dev.c:4450
  dev_queue_xmit include/linux/netdevice.h:3105 [inline]
  neigh_resolve_output+0x9ca/0xae0 net/core/neighbour.c:1565
  neigh_output include/net/neighbour.h:542 [inline]
  ip6_finish_output2+0x2347/0x2ba0 net/ipv6/ip6_output.c:141
  __ip6_finish_output net/ipv6/ip6_output.c:215 [inline]
  ip6_finish_output+0xbb8/0x14b0 net/ipv6/ip6_output.c:226
  NF_HOOK_COND include/linux/netfilter.h:303 [inline]
  ip6_output+0x356/0x620 net/ipv6/ip6_output.c:247
  dst_output include/net/dst.h:450 [inline]
  NF_HOOK include/linux/netfilter.h:314 [inline]
  ip6_xmit+0x1ba6/0x25d0 net/ipv6/ip6_output.c:366
  inet6_csk_xmit+0x442/0x530 net/ipv6/inet6_connection_sock.c:135
  __tcp_transmit_skb+0x3b07/0x4880 net/ipv4/tcp_output.c:1466
  tcp_transmit_skb net/ipv4/tcp_output.c:1484 [inline]
  tcp_connect+0x35b6/0x7130 net/ipv4/tcp_output.c:4143
  tcp_v6_connect+0x1bcc/0x1e40 net/ipv6/tcp_ipv6.c:333
  __inet_stream_connect+0x2ef/0x1730 net/ipv4/af_inet.c:679
  inet_stream_connect+0x6a/0xd0 net/ipv4/af_inet.c:750
  __sys_connect_file net/socket.c:2061 [inline]
  __sys_connect+0x606/0x690 net/socket.c:2078
  __do_sys_connect net/socket.c:2088 [inline]
  __se_sys_connect net/socket.c:2085 [inline]
  __x64_sys_connect+0x91/0xe0 net/socket.c:2085
  x64_sys_call+0x27a5/0x3ba0 arch/x86/include/generated/asm/syscalls_64.h:43
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xcd/0x1e0 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Uninit was stored to memory at:

  nf_reject_ip6_tcphdr_put+0x60c/0x6c0 net/ipv6/netfilter/nf_reject_ipv6.c:249
  nf_send_reset6+0xd84/0x15b0 net/ipv6/netfilter/nf_reject_ipv6.c:344
  nft_reject_inet_eval+0x3c1/0x880 net/netfilter/nft_reject_inet.c:48
  expr_call_ops_eval net/netfilter/nf_tables_core.c:240 [inline]
  nft_do_chain+0x438/0x22a0 net/netfilter/nf_tables_core.c:288
  nft_do_chain_inet+0x41a/0x4f0 net/netfilter/nft_chain_filter.c:161
  nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline]
  nf_hook_slow+0xf4/0x400 net/netfilter/core.c:626
  nf_hook include/linux/netfilter.h:269 [inline]
  NF_HOOK include/linux/netfilter.h:312 [inline]
  ipv6_rcv+0x29b/0x390 net/ipv6/ip6_input.c:310
  __netif_receive_skb_one_core net/core/dev.c:5661 [inline]
  __netif_receive_skb+0x1da/0xa00 net/core/dev.c:5775
  process_backlog+0x4ad/0xa50 net/core/dev.c:6108
  __napi_poll+0xe7/0x980 net/core/dev.c:6772
  napi_poll net/core/dev.c:6841 [inline]
  net_rx_action+0xa5a/0x19b0 net/core/dev.c:6963
  handle_softirqs+0x1ce/0x800 kernel/softirq.c:554
  __do_softirq+0x14/0x1a kernel/softirq.c:588

Uninit was stored to memory at:

  nf_reject_ip6_tcphdr_put+0x2ca/0x6c0 net/ipv6/netfilter/nf_reject_ipv6.c:231
  nf_send_reset6+0xd84/0x15b0 net/ipv6/netfilter/nf_reject_ipv6.c:344
  nft_reject_inet_eval+0x3c1/0x880 net/netfilter/nft_reject_inet.c:48
  expr_call_ops_eval net/netfilter/nf_tables_core.c:240 [inline]
  nft_do_chain+0x438/0x22a0 net/netfilter/nf_tables_core.c:288
  nft_do_chain_inet+0x41a/0x4f0 net/netfilter/nft_chain_filter.c:161
  nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline]
  nf_hook_slow+0xf4/0x400 net/netfilter/core.c:626
  nf_hook include/linux/netfilter.h:269 [inline]
  NF_HOOK include/linux/netfilter.h:312 [inline]
  ipv6_rcv+0x29b/0x390 net/ipv6/ip6_input.c:310
  __netif_receive_skb_one_core net/core/dev.c:5661 [inline]
  __netif_receive_skb+0x1da/0xa00 net/core/dev.c:5775
  process_backlog+0x4ad/0xa50 net/core/dev.c:6108
  __napi_poll+0xe7/0x980 net/core/dev.c:6772
  napi_poll net/core/dev.c:6841 [inline]
  net_rx_action+0xa5a/0x19b0 net/core/dev.c:6963
  handle_softirqs+0x1ce/0x800 kernel/softirq.c:554
  __do_softirq+0x14/0x1a kernel/softirq.c:588

Uninit was created at:

  slab_post_alloc_hook mm/slub.c:3998 [inline]
  slab_alloc_node mm/slub.c:4041 [inline]
  kmem_cache_alloc_node_noprof+0x6bf/0xb80 mm/slub.c:4084
  kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:583
  __alloc_skb+0x363/0x7b0 net/core/skbuff.c:674
  alloc_skb include/linux/skbuff.h:1320 [inline]
  nf_send_reset6+0x98d/0x15b0 net/ipv6/netfilter/nf_reject_ipv6.c:327
  nft_reject_inet_eval+0x3c1/0x880 net/netfilter/nft_reject_inet.c:48
  expr_call_ops_eval net/netfilter/nf_tables_core.c:240 [inline]
  nft_do_chain+0x438/0x22a0 net/netfilter/nf_tables_core.c:288
  nft_do_chain_inet+0x41a/0x4f0 net/netfilter/nft_chain_filter.c:161
  nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline]
  nf_hook_slow+0xf4/0x400 net/netfilter/core.c:626
  nf_hook include/linux/netfilter.h:269 [inline]
  NF_HOOK include/linux/netfilter.h:312 [inline]
  ipv6_rcv+0x29b/0x390 net/ipv6/ip6_input.c:310
  __netif_receive_skb_one_core net/core/dev.c:5661 [inline]
  __netif_receive_skb+0x1da/0xa00 net/core/dev.c:5775
  process_backlog+0x4ad/0xa50 net/core/dev.c:6108
  __napi_poll+0xe7/0x980 net/core/dev.c:6772
  napi_poll net/core/dev.c:6841 [inline]
  net_rx_action+0xa5a/0x19b0 net/core/dev.c:6963
  handle_softirqs+0x1ce/0x800 kernel/softirq.c:554
  __do_softirq+0x14/0x1a kernel/softirq.c:588

---
 net/ipv6/netfilter/nf_reject_ipv6.c | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

index dedee264b8f6c..b9457473c176d 100644
@@ -223,33 +223,23 @@ void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb,
 			      const struct tcphdr *oth, unsigned int otcplen)
 {
 	struct tcphdr *tcph;
-	int needs_ack;
 
 	skb_reset_transport_header(nskb);
-	tcph = skb_put(nskb, sizeof(struct tcphdr));
+	tcph = skb_put_zero(nskb, sizeof(struct tcphdr));
 	/* Truncate to length (no data) */
 	tcph->doff = sizeof(struct tcphdr)/4;
 	tcph->source = oth->dest;
 	tcph->dest = oth->source;
 
 	if (oth->ack) {
-		needs_ack = 0;
 		tcph->seq = oth->ack_seq;
-		tcph->ack_seq = 0;
 	} else {
-		needs_ack = 1;
 		tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
 				      otcplen - (oth->doff<<2));
-		tcph->seq = 0;
+		tcph->ack = 1;
 	}
 
-	/* Reset flags */
-	((u_int8_t *)tcph)[13] = 0;
 	tcph->rst = 1;
-	tcph->ack = needs_ack;
-	tcph->window = 0;
-	tcph->urg_ptr = 0;
-	tcph->check = 0;
 
 	/* Adjust TCP checksum */
 	tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,

2.43.0

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

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

From: Kaixin Wang <[email protected]>

[ Upstream commit b5109b60ee4fcb2f2bb24f589575e10cc5283ad4 ]

In the ether3_probe function, a timer is initialized with a callback function ether3_ledoff, bound to &prev(dev)->timer. Once the timer is started, there is a risk of a race condition if the module or device is removed, triggering the ether3_remove function to perform cleanup. The sequence of operations that may lead to a UAF bug is as follows:

CPU0 CPU1

                      |  ether3_ledoff
ether3_remove         |
  free_netdev(dev);   |
  put_devic           |
  kfree(dev);         |
 |  ether3_outw(priv(dev)->regs.config2 |= CFG2_CTRLO, REG_CONFIG2);
                      | // use dev

Fix it by ensuring that the timer is canceled before proceeding with the cleanup in ether3_remove.

---
 drivers/net/ethernet/seeq/ether3.c | 2 ++
 1 file changed, 2 insertions(+)

index c672f92d65e97..9319a2675e7b6 100644
@@ -847,9 +847,11 @@ static void ether3_remove(struct expansion_card *ec)
 {
 	struct net_device *dev = ecard_get_drvdata(ec);
 
+	ether3_outw(priv(dev)->regs.config2 |= CFG2_CTRLO, REG_CONFIG2);
 	ecard_set_drvdata(ec, NULL);
 
 	unregister_netdev(dev);
+	del_timer_sync(&priv(dev)->timer);
 	free_netdev(dev);
 	ecard_release_resources(ec);
 }

2.43.0

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

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

From: Thomas Weißschuh <[email protected]>

[ Upstream commit 93c21077bb9ba08807c459982d440dbbee4c7af3 ]

The rpl sr tunnel code contains calls to dst_cache_*() which are only present when the dst cache is built.
Select DST_CACHE to build the dst cache, similar to other kconfig options in the same file.
Compiling the rpl sr tunnel without DST_CACHE will lead to linker errors.

---
 net/ipv6/Kconfig | 1 +
 1 file changed, 1 insertion(+)

index 08d4b7132d4c4..1c9c686d9522f 100644
@@ -323,6 +323,7 @@ config IPV6_RPL_LWTUNNEL
 	bool "IPv6: RPL Source Routing Header support"
 	depends on IPV6
 	select LWTUNNEL
+	select DST_CACHE
 	help
 	  Support for RFC6554 RPL Source Routing Header using the lightweight
 	  tunnels mechanism.

2.43.0

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

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

From: Josh Hunt <[email protected]>

[ Upstream commit c8770db2d54437a5f49417ae7b46f7de23d14db6 ]

We have some machines running stock Ubuntu 20.04.6 which is their 5.4.0-174-generic kernel that are running ceph and recently hit a null ptr dereference in tcp_rearm_rto(). Initially hitting it from the TLP path, but then later we also saw it getting hit from the RACK case as well. Here are examples of the oops messages we saw in each of those cases:

Jul 26 15:05:02 rx [11061395.780353] BUG: kernel NULL pointer dereference, address: 0000000000000020
Jul 26 15:05:02 rx [11061395.787572] #PF: supervisor read access in kernel mode
Jul 26 15:05:02 rx [11061395.792971] #PF: error_code(0x0000) - not-present page
Jul 26 15:05:02 rx [11061395.798362] PGD 0 P4D 0
Jul 26 15:05:02 rx [11061395.801164] Oops: 0000 [#1] SMP NOPTI
Jul 26 15:05:02 rx [11061395.805091] CPU: 0 PID: 9180 Comm: msgr-worker-1 Tainted: G W 5.4.0-174-generic #193-Ubuntu
Jul 26 15:05:02 rx [11061395.814996] Hardware name: Supermicro SMC 2x26 os-gen8 64C NVME-Y 256G/H12SSW-NTR, BIOS 2.5.V1.2U.NVMe.UEFI 05/09/2023
Jul 26 15:05:02 rx [11061395.825952] RIP: 0010:tcp_rearm_rto+0xe4/0x160
Jul 26 15:05:02 rx [11061395.830656] Code: 87 ca 04 00 00 00 5b 41 5c 41 5d 5d c3 c3 49 8b bc 24 40 06 00 00 eb 8d 48 bb cf f7 53 e3 a5 9b c4 20 4c 89 ef e8 0c fe 0e 00 <48> 8b 78 20 48 c1 ef 03 48 89 f8 41 8b bc 24 80 04 00 00 48 f7 e3
Jul 26 15:05:02 rx [11061395.849665] RSP: 0018:ffffb75d40003e08 EFLAGS: 00010246
Jul 26 15:05:02 rx [11061395.855149] RAX: 0000000000000000 RBX: 20c49ba5e353f7cf RCX: 0000000000000000
Jul 26 15:05:02 rx [11061395.862542] RDX: 0000000062177c30 RSI: 000000000000231c RDI: ffff9874ad283a60
Jul 26 15:05:02 rx [11061395.869933] RBP: ffffb75d40003e20 R08: 0000000000000000 R09: ffff987605e20aa8
Jul 26 15:05:02 rx [11061395.877318] R10: ffffb75d40003f00 R11: ffffb75d4460f740 R12: ffff9874ad283900
Jul 26 15:05:02 rx [11061395.884710] R13: ffff9874ad283a60 R14: ffff9874ad283980 R15: ffff9874ad283d30
Jul 26 15:05:02 rx [11061395.892095] FS: 00007f1ef4a2e700(0000) GS:ffff987605e00000(0000) knlGS:0000000000000000
Jul 26 15:05:02 rx [11061395.900438] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Jul 26 15:05:02 rx [11061395.906435] CR2: 0000000000000020 CR3: 0000003e450ba003 CR4: 0000000000760ef0
Jul 26 15:05:02 rx [11061395.913822] PKRU: 55555554
Jul 26 15:05:02 rx [11061395.916786] Call Trace:
Jul 26 15:05:02 rx [11061395.919488]
Jul 26 15:05:02 rx [11061395.921765] ? show_regs.cold+0x1a/0x1f
Jul 26 15:05:02 rx [11061395.925859] ? __die+0x90/0xd9
Jul 26 15:05:02 rx [11061395.929169] ? no_context+0x196/0x380
Jul 26 15:05:02 rx [11061395.933088] ? ip6_protocol_deliver_rcu+0x4e0/0x4e0
Jul 26 15:05:02 rx [11061395.938216] ? ip6_sublist_rcv_finish+0x3d/0x50
Jul 26 15:05:02 rx [11061395.943000] ? __bad_area_nosemaphore+0x50/0x1a0
Jul 26 15:05:02 rx [11061395.947873] ? bad_area_nosemaphore+0x16/0x20
Jul 26 15:05:02 rx [11061395.952486] ? do_user_addr_fault+0x267/0x450
Jul 26 15:05:02 rx [11061395.957104] ? ipv6_list_rcv+0x112/0x140
Jul 26 15:05:02 rx [11061395.961279] ? __do_page_fault+0x58/0x90
Jul 26 15:05:02 rx [11061395.965458] ? do_page_fault+0x2c/0xe0
Jul 26 15:05:02 rx [11061395.969465] ? page_fault+0x34/0x40
Jul 26 15:05:02 rx [11061395.973217] ? tcp_rearm_rto+0xe4/0x160
Jul 26 15:05:02 rx [11061395.977313] ? tcp_rearm_rto+0xe4/0x160
Jul 26 15:05:02 rx [11061395.981408] tcp_send_loss_probe+0x10b/0x220
Jul 26 15:05:02 rx [11061395.985937] tcp_write_timer_handler+0x1b4/0x240
Jul 26 15:05:02 rx [11061395.990809] tcp_write_timer+0x9e/0xe0
Jul 26 15:05:02 rx [11061395.994814] ? tcp_write_timer_handler+0x240/0x240
Jul 26 15:05:02 rx [11061395.999866] call_timer_fn+0x32/0x130
Jul 26 15:05:02 rx [11061396.003782] __run_timers.part.0+0x180/0x280
Jul 26 15:05:02 rx [11061396.008309] ? recalibrate_cpu_khz+0x10/0x10
Jul 26 15:05:02 rx [11061396.012841] ? native_x2apic_icr_write+0x30/0x30
Jul 26 15:05:02 rx [11061396.017718] ? lapic_next_event+0x21/0x30
Jul 26 15:05:02 rx [11061396.021984] ? clockevents_program_event+0x8f/0xe0
Jul 26 15:05:02 rx [11061396.027035] run_timer_softirq+0x2a/0x50
Jul 26 15:05:02 rx [11061396.031212] __do_softirq+0xd1/0x2c1
Jul 26 15:05:02 rx [11061396.035044] do_softirq_own_stack+0x2a/0x40
Jul 26 15:05:02 rx [11061396.039480]
Jul 26 15:05:02 rx [11061396.041840] do_softirq.part.0+0x46/0x50
Jul 26 15:05:02 rx [11061396.046022] __local_bh_enable_ip+0x50/0x60
Jul 26 15:05:02 rx [11061396.050460] _raw_spin_unlock_bh+0x1e/0x20
Jul 26 15:05:02 rx [11061396.054817] nf_conntrack_tcp_packet+0x29e/0xbe0 [nf_conntrack]
Jul 26 15:05:02 rx [11061396.060994] ? get_l4proto+0xe7/0x190 [nf_conntrack]
Jul 26 15:05:02 rx [11061396.066220] nf_conntrack_in+0xe9/0x670 [nf_conntrack]
Jul 26 15:05:02 rx [11061396.071618] ipv6_conntrack_local+0x14/0x20 [nf_conntrack]
Jul 26 15:05:02 rx [11061396.077356] nf_hook_slow+0x45/0xb0
Jul 26 15:05:02 rx [11061396.081098] ip6_xmit+0x3f0/0x5d0
Jul 26 15:05:02 rx [11061396.084670] ? ipv6_anycast_cleanup+0x50/0x50
Jul 26 15:05:02 rx [11061396.089282] ? __sk_dst_check+0x38/0x70
Jul 26 15:05:02 rx [11061396.093381] ? inet6_csk_route_socket+0x13b/0x200
Jul 26 15:05:02 rx [11061396.098346] inet6_csk_xmit+0xa7/0xf0
Jul 26 15:05:02 rx [11061396.102263] __tcp_transmit_skb+0x550/0xb30
Jul 26 15:05:02 rx [11061396.106701] tcp_write_xmit+0x3c6/0xc20
Jul 26 15:05:02 rx [11061396.110792] ? __alloc_skb+0x98/0x1d0
Jul 26 15:05:02 rx [11061396.114708] __tcp_push_pending_frames+0x37/0x100
Jul 26 15:05:02 rx [11061396.119667] tcp_push+0xfd/0x100
Jul 26 15:05:02 rx [11061396.123150] tcp_sendmsg_locked+0xc70/0xdd0
Jul 26 15:05:02 rx [11061396.127588] tcp_sendmsg+0x2d/0x50
Jul 26 15:05:02 rx [11061396.131245] inet6_sendmsg+0x43/0x70
Jul 26 15:05:02 rx [11061396.135075] __sock_sendmsg+0x48/0x70
Jul 26 15:05:02 rx [11061396.138994] ____sys_sendmsg+0x212/0x280
Jul 26 15:05:02 rx [11061396.143172] ___sys_sendmsg+0x88/0xd0
Jul 26 15:05:02 rx [11061396.147098] ? __seccomp_filter+0x7e/0x6b0
Jul 26 15:05:02 rx [11061396.151446] ? __switch_to+0x39c/0x460
Jul 26 15:05:02 rx [11061396.155453] ? __switch_to_asm+0x42/0x80
Jul 26 15:05:02 rx [11061396.159636] ? __switch_to_asm+0x5a/0x80
Jul 26 15:05:02 rx [11061396.163816] __sys_sendmsg+0x5c/0xa0
Jul 26 15:05:02 rx [11061396.167647] __x64_sys_sendmsg+0x1f/0x30
Jul 26 15:05:02 rx [11061396.171832] do_syscall_64+0x57/0x190
Jul 26 15:05:02 rx [11061396.175748] entry_SYSCALL_64_after_hwframe+0x5c/0xc1
Jul 26 15:05:02 rx [11061396.181055] RIP: 0033:0x7f1ef692618d
Jul 26 15:05:02 rx [11061396.184893] Code: 28 89 54 24 1c 48 89 74 24 10 89 7c 24 08 e8 ca ee ff ff 8b 54 24 1c 48 8b 74 24 10 41 89 c0 8b 7c 24 08 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 2f 44 89 c7 48 89 44 24 08 e8 fe ee ff ff 48
Jul 26 15:05:02 rx [11061396.203889] RSP: 002b:00007f1ef4a26aa0 EFLAGS: 00000293 ORIG_RAX: 000000000000002e
Jul 26 15:05:02 rx [11061396.211708] RAX: ffffffffffffffda RBX: 000000000000084b RCX: 00007f1ef692618d
Jul 26 15:05:02 rx [11061396.219091] RDX: 0000000000004000 RSI: 00007f1ef4a26b10 RDI: 0000000000000275
Jul 26 15:05:02 rx [11061396.226475] RBP: 0000000000004000 R08: 0000000000000000 R09: 0000000000000020
Jul 26 15:05:02 rx [11061396.233859] R10: 0000000000000000 R11: 0000000000000293 R12: 000000000000084b
Jul 26 15:05:02 rx [11061396.241243] R13: 00007f1ef4a26b10 R14: 0000000000000275 R15: 000055592030f1e8
Jul 26 15:05:02 rx [11061396.248628] Modules linked in: vrf bridge stp llc vxlan ip6_udp_tunnel udp_tunnel nls_iso8859_1 amd64_edac_mod edac_mce_amd kvm_amd kvm crct10dif_pclmul ghash_clmulni_intel aesni_intel crypto_simd cryptd glue_helper wmi_bmof ipmi_ssif input_leds joydev rndis_host cdc_ether usbnet mii ast drm_vram_helper ttm drm_kms_helper i2c_algo_bit fb_sys_fops syscopyarea sysfillrect sysimgblt ccp mac_hid ipmi_si ipmi_devintf ipmi_msghandler nft_ct sch_fq_codel nf_tables_set nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables nfnetlink ramoops reed_solomon efi_pstore drm ip_tables x_tables autofs4 raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid0 multipath linear mlx5_ib ib_uverbs ib_core raid1 mlx5_core hid_generic pci_hyperv_intf crc32_pclmul tls usbhid ahci mlxfw bnxt_en libahci hid nvme i2c_piix4 nvme_core wmi
Jul 26 15:05:02 rx [11061396.324334] CR2: 0000000000000020
Jul 26 15:05:02 rx [11061396.327944] ---[ end trace 68a2b679d1cfb4f1 ]---
Jul 26 15:05:02 rx [11061396.433435] RIP: 0010:tcp_rearm_rto+0xe4/0x160
Jul 26 15:05:02 rx [11061396.438137] Code: 87 ca 04 00 00 00 5b 41 5c 41 5d 5d c3 c3 49 8b bc 24 40 06 00 00 eb 8d 48 bb cf f7 53 e3 a5 9b c4 20 4c 89 ef e8 0c fe 0e 00 <48> 8b 78 20 48 c1 ef 03 48 89 f8 41 8b bc 24 80 04 00 00 48 f7 e3
Jul 26 15:05:02 rx [11061396.457144] RSP: 0018:ffffb75d40003e08 EFLAGS: 00010246
Jul 26 15:05:02 rx [11061396.462629] RAX: 0000000000000000 RBX: 20c49ba5e353f7cf RCX: 0000000000000000
Jul 26 15:05:02 rx [11061396.470012] RDX: 0000000062177c30 RSI: 000000000000231c RDI: ffff9874ad283a60
Jul 26 15:05:02 rx [11061396.477396] RBP: ffffb75d40003e20 R08: 0000000000000000 R09: ffff987605e20aa8
Jul 26 15:05:02 rx [11061396.484779] R10: ffffb75d40003f00 R11: ffffb75d4460f740 R12: ffff9874ad283900
Jul 26 15:05:02 rx [11061396.492164] R13: ffff9874ad283a60 R14: ffff9874ad283980 R15: ffff9874ad283d30
Jul 26 15:05:02 rx [11061396.499547] FS: 00007f1ef4a2e700(0000) GS:ffff987605e00000(0000) knlGS:0000000000000000
Jul 26 15:05:02 rx [11061396.507886] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Jul 26 15:05:02 rx [11061396.513884] CR2: 0000000000000020 CR3: 0000003e450ba003 CR4: 0000000000760ef0
Jul 26 15:05:02 rx [11061396.521267] PKRU: 55555554
Jul 26 15:05:02 rx [11061396.524230] Kernel panic - not syncing: Fatal exception in interrupt
Jul 26 15:05:02 rx [11061396.530885] Kernel Offset: 0x1b200000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
Jul 26 15:05:03 rx [11061396.660181] ---[ end Kernel panic - not syncing: Fatal
 exception in interrupt ]---

After we hit this we disabled TLP by setting tcp_early_retrans to 0 and then hit the crash in the RACK case:

Aug 7 07:26:16 rx [1006006.265582] BUG: kernel NULL pointer dereference, address: 0000000000000020
Aug 7 07:26:16 rx [1006006.272719] #PF: supervisor read access in kernel mode
Aug 7 07:26:16 rx [1006006.278030] #PF: error_code(0x0000) - not-present page
Aug 7 07:26:16 rx [1006006.283343] PGD 0 P4D 0
Aug 7 07:26:16 rx [1006006.286057] Oops: 0000 [#1] SMP NOPTI
Aug 7 07:26:16 rx [1006006.289896] CPU: 5 PID: 0 Comm: swapper/5 Tainted: G W 5.4.0-174-generic #193-Ubuntu
Aug 7 07:26:16 rx [1006006.299107] Hardware name: Supermicro SMC 2x26 os-gen8 64C NVME-Y 256G/H12SSW-NTR, BIOS 2.5.V1.2U.NVMe.UEFI 05/09/2023
Aug 7 07:26:16 rx [1006006.309970] RIP: 0010:tcp_rearm_rto+0xe4/0x160
Aug 7 07:26:16 rx [1006006.314584] Code: 87 ca 04 00 00 00 5b 41 5c 41 5d 5d c3 c3 49 8b bc 24 40 06 00 00 eb 8d 48 bb cf f7 53 e3 a5 9b c4 20 4c 89 ef e8 0c fe 0e 00 <48> 8b 78 20 48 c1 ef 03 48 89 f8 41 8b bc 24 80 04 00 00 48 f7 e3
Aug 7 07:26:16 rx [1006006.333499] RSP: 0018:ffffb42600a50960 EFLAGS: 00010246
Aug 7 07:26:16 rx [1006006.338895] RAX: 0000000000000000 RBX: 20c49ba5e353f7cf RCX: 0000000000000000
Aug 7 07:26:16 rx [1006006.346193] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff92d687ed8160
Aug 7 07:26:16 rx [1006006.353489] RBP: ffffb42600a50978 R08: 0000000000000000 R09: 00000000cd896dcc
Aug 7 07:26:16 rx [1006006.360786] R10: ffff92dc3404f400 R11: 0000000000000001 R12: ffff92d687ed8000
Aug 7 07:26:16 rx [1006006.368084] R13: ffff92d687ed8160 R14: 00000000cd896dcc R15: 00000000cd8fca81
Aug 7 07:26:16 rx [1006006.375381] FS: 0000000000000000(0000) GS:ffff93158ad40000(0000) knlGS:0000000000000000
Aug 7 07:26:16 rx [1006006.383632] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Aug 7 07:26:16 rx [1006006.389544] CR2: 0000000000000020 CR3: 0000003e775ce006 CR4: 0000000000760ee0
Aug 7 07:26:16 rx [1006006.396839] PKRU: 55555554
Aug 7 07:26:16 rx [1006006.399717] Call Trace:
Aug 7 07:26:16 rx [1006006.402335]
Aug 7 07:26:16 rx [1006006.404525] ? show_regs.cold+0x1a/0x1f
Aug 7 07:26:16 rx [1006006.408532] ? __die+0x90/0xd9
Aug 7 07:26:16 rx [1006006.411760] ? no_context+0x196/0x380
Aug 7 07:26:16 rx [1006006.415599] ? __bad_area_nosemaphore+0x50/0x1a0
Aug 7 07:26:16 rx [1006006.420392] ? _raw_spin_lock+0x1e/0x30
Aug 7 07:26:16 rx [1006006.424401] ? bad_area_nosemaphore+0x16/0x20
Aug 7 07:26:16 rx [1006006.428927] ? do_user_addr_fault+0x267/0x450
Aug 7 07:26:16 rx [1006006.433450] ? __do_page_fault+0x58/0x90
Aug 7 07:26:16 rx [1006006.437542] ? do_page_fault+0x2c/0xe0
Aug 7 07:26:16 rx [1006006.441470] ? page_fault+0x34/0x40
Aug 7 07:26:16 rx [1006006.445134] ? tcp_rearm_rto+0xe4/0x160
Aug 7 07:26:16 rx [1006006.449145] tcp_ack+0xa32/0xb30
Aug 7 07:26:16 rx [1006006.452542] tcp_rcv_established+0x13c/0x670
Aug 7 07:26:16 rx [1006006.456981] ? sk_filter_trim_cap+0x48/0x220
Aug 7 07:26:16 rx [1006006.461419] tcp_v6_do_rcv+0xdb/0x450
Aug 7 07:26:16 rx [1006006.465257] tcp_v6_rcv+0xc2b/0xd10
Aug 7 07:26:16 rx [1006006.468918] ip6_protocol_deliver_rcu+0xd3/0x4e0
Aug 7 07:26:16 rx [1006006.473706] ip6_input_finish+0x15/0x20
Aug 7 07:26:16 rx [1006006.477710] ip6_input+0xa2/0xb0
Aug 7 07:26:16 rx [1006006.481109] ? ip6_protocol_deliver_rcu+0x4e0/0x4e0
Aug 7 07:26:16 rx [1006006.486151] ip6_sublist_rcv_finish+0x3d/0x50
Aug 7 07:26:16 rx [1006006.490679] ip6_sublist_rcv+0x1aa/0x250
Aug 7 07:26:16 rx [1006006.494779] ? ip6_rcv_finish_core.isra.0+0xa0/0xa0
Aug 7 07:26:16 rx [1006006.499828] ipv6_list_rcv+0x112/0x140
Aug 7 07:26:16 rx [1006006.503748] __netif_receive_skb_list_core+0x1a4/0x250
Aug 7 07:26:16 rx [1006006.509057] netif_receive_skb_list_internal+0x1a1/0x2b0
Aug 7 07:26:16 rx [1006006.514538] gro_normal_list.part.0+0x1e/0x40
Aug 7 07:26:16 rx [1006006.519068] napi_complete_done+0x91/0x130
Aug 7 07:26:16 rx [1006006.523352] mlx5e_napi_poll+0x18e/0x610 [mlx5_core]
Aug 7 07:26:16 rx [1006006.528481] net_rx_action+0x142/0x390
Aug 7 07:26:16 rx [1006006.532398] __do_softirq+0xd1/0x2c1
Aug 7 07:26:16 rx [1006006.536142] irq_exit+0xae/0xb0
Aug 7 07:26:16 rx [1006006.539452] do_IRQ+0x5a/0xf0
Aug 7 07:26:16 rx [1006006.542590] common_interrupt+0xf/0xf
Aug 7 07:26:16 rx [1006006.546421]
Aug 7 07:26:16 rx [1006006.548695] RIP: 0010:native_safe_halt+0xe/0x10
Aug 7 07:26:16 rx [1006006.553399] Code: 7b ff ff ff eb bd 90 90 90 90 90 90 e9 07 00 00 00 0f 00 2d 36 2c 50 00 f4 c3 66 90 e9 07 00 00 00 0f 00 2d 26 2c 50 00 fb f4 90 0f 1f 44 00 00 55 48 89 e5 41 55 41 54 53 e8 dd 5e 61 ff 65
Aug 7 07:26:16 rx [1006006.572309] RSP: 0018:ffffb42600177e70 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffc2
Aug 7 07:26:16 rx [1006006.580040] RAX: ffffffff8ed08b20 RBX: 0000000000000005 RCX: 0000000000000001
Aug 7 07:26:16 rx [1006006.587337] RDX: 00000000f48eeca2 RSI: 0000000000000082 RDI: 0000000000000082
Aug 7 07:26:16 rx [1006006.594635] RBP: ffffb42600177e90 R08: 0000000000000000 R09: 000000000000020f
Aug 7 07:26:16 rx [1006006.601931] R10: 0000000000100000 R11: 0000000000000000 R12: 0000000000000005
Aug 7 07:26:16 rx [1006006.609229] R13: ffff93157deb5f00 R14: 0000000000000000 R15: 0000000000000000
Aug 7 07:26:16 rx [1006006.616530] ? __cpuidle_text_start+0x8/0x8
Aug 7 07:26:16 rx [1006006.620886] ? default_idle+0x20/0x140
Aug 7 07:26:16 rx [1006006.624804] arch_cpu_idle+0x15/0x20
Aug 7 07:26:16 rx [1006006.628545] default_idle_call+0x23/0x30
Aug 7 07:26:16 rx [1006006.632640] do_idle+0x1fb/0x270
Aug 7 07:26:16 rx [1006006.636035] cpu_startup_entry+0x20/0x30
Aug 7 07:26:16 rx [1006006.640126] start_secondary+0x178/0x1d0
Aug 7 07:26:16 rx [1006006.644218] secondary_startup_64+0xa4/0xb0
Aug 7 07:26:17 rx [1006006.648568] Modules linked in: vrf bridge stp llc vxlan ip6_udp_tunnel udp_tunnel nls_iso8859_1 nft_ct amd64_edac_mod edac_mce_amd kvm_amd kvm crct10dif_pclmul ghash_clmulni_intel aesni_intel crypto_simd cryptd glue_helper wmi_bmof ipmi_ssif input_leds joydev rndis_host cdc_ether usbnet ast mii drm_vram_helper ttm drm_kms_helper i2c_algo_bit fb_sys_fops syscopyarea sysfillrect sysimgblt ccp mac_hid ipmi_si ipmi_devintf ipmi_msghandler sch_fq_codel nf_tables_set nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables nfnetlink ramoops reed_solomon efi_pstore drm ip_tables x_tables autofs4 raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx xor raid6_pq libcrc32c raid0 multipath linear mlx5_ib ib_uverbs ib_core raid1 hid_generic mlx5_core pci_hyperv_intf crc32_pclmul usbhid ahci tls mlxfw bnxt_en hid libahci nvme i2c_piix4 nvme_core wmi [last unloaded: cpuid] Aug 7 07:26:17 rx [1006006.726180] CR2: 0000000000000020
Aug 7 07:26:17 rx [1006006.729718] ---[ end trace e0e2e37e4e612984 ]---

Prior to seeing the first crash and on other machines we also see the warning in tcp_send_loss_probe() where packets_out is non-zero, but both transmit and retrans queues are empty so we know the box is seeing some accounting issue in this area:

Jul 26 09:15:27 kernel: ------------[ cut here ]------------
Jul 26 09:15:27 kernel: invalid inflight: 2 state 1 cwnd 68 mss 8988
Jul 26 09:15:27 kernel: WARNING: CPU: 16 PID: 0 at net/ipv4/tcp_output.c:2605 tcp_send_loss_probe+0x214/0x220
Jul 26 09:15:27 kernel: Modules linked in: vrf bridge stp llc vxlan ip6_udp_tunnel udp_tunnel nls_iso8859_1 nft_ct amd64_edac_mod edac_mce_amd kvm_amd kvm crct10dif_pclmul ghash_clmulni_intel aesni_intel crypto_simd cryptd glue_helper wmi_bmof ipmi_ssif joydev input_leds rndis_host cdc_ether usbnet mii ast drm_vram_helper ttm drm_kms_he>
Jul 26 09:15:27 kernel: CPU: 16 PID: 0 Comm: swapper/16 Not tainted 5.4.0-174-generic #193-Ubuntu
Jul 26 09:15:27 kernel: Hardware name: Supermicro SMC 2x26 os-gen8 64C NVME-Y 256G/H12SSW-NTR, BIOS 2.5.V1.2U.NVMe.UEFI 05/09/2023
Jul 26 09:15:27 kernel: RIP: 0010:tcp_send_loss_probe+0x214/0x220
Jul 26 09:15:27 kernel: Code: 08 26 01 00 75 e2 41 0f b6 54 24 12 41 8b 8c 24 c0 06 00 00 45 89 f0 48 c7 c7 e0 b4 20 a7 c6 05 8d 08 26 01 01 e8 4a c0 0f 00 <0f> 0b eb ba 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41
Jul 26 09:15:27 kernel: RSP: 0018:ffffb7838088ce00 EFLAGS: 00010286
Jul 26 09:15:27 kernel: RAX: 0000000000000000 RBX: ffff9b84b5630430 RCX: 0000000000000006
Jul 26 09:15:27 kernel: RDX: 0000000000000007 RSI: 0000000000000096 RDI: ffff9b8e4621c8c0
Jul 26 09:15:27 kernel: RBP: ffffb7838088ce18 R08: 0000000000000927 R09: 0000000000000004
Jul 26 09:15:27 kernel: R10: 0000000000000000 R11: 0000000000000001 R12: ffff9b84b5630000
Jul 26 09:15:27 kernel: R13: 0000000000000000 R14: 000000000000231c R15: ffff9b84b5630430
Jul 26 09:15:27 kernel: FS: 0000000000000000(0000) GS:ffff9b8e46200000(0000) knlGS:0000000000000000
Jul 26 09:15:27 kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
Jul 26 09:15:27 kernel: CR2: 000056238cec2380 CR3: 0000003e49ede005 CR4: 0000000000760ee0
Jul 26 09:15:27 kernel: PKRU: 55555554
Jul 26 09:15:27 kernel: Call Trace:
Jul 26 09:15:27 kernel: <IRQ>
Jul 26 09:15:27 kernel: ? show_regs.cold+0x1a/0x1f
Jul 26 09:15:27 kernel: ? __warn+0x98/0xe0
Jul 26 09:15:27 kernel: ? tcp_send_loss_probe+0x214/0x220
Jul 26 09:15:27 kernel: ? report_bug+0xd1/0x100
Jul 26 09:15:27 kernel: ? do_error_trap+0x9b/0xc0
Jul 26 09:15:27 kernel: ? do_invalid_op+0x3c/0x50
Jul 26 09:15:27 kernel: ? tcp_send_loss_probe+0x214/0x220
Jul 26 09:15:27 kernel: ? invalid_op+0x1e/0x30
Jul 26 09:15:27 kernel: ? tcp_send_loss_probe+0x214/0x220
Jul 26 09:15:27 kernel: tcp_write_timer_handler+0x1b4/0x240
Jul 26 09:15:27 kernel: tcp_write_timer+0x9e/0xe0
Jul 26 09:15:27 kernel: ? tcp_write_timer_handler+0x240/0x240
Jul 26 09:15:27 kernel: call_timer_fn+0x32/0x130
Jul 26 09:15:27 kernel: __run_timers.part.0+0x180/0x280
Jul 26 09:15:27 kernel: ? timerqueue_add+0x9b/0xb0
Jul 26 09:15:27 kernel: ? enqueue_hrtimer+0x3d/0x90
Jul 26 09:15:27 kernel: ? do_error_trap+0x9b/0xc0
Jul 26 09:15:27 kernel: ? do_invalid_op+0x3c/0x50
Jul 26 09:15:27 kernel: ? tcp_send_loss_probe+0x214/0x220
Jul 26 09:15:27 kernel: ? invalid_op+0x1e/0x30
Jul 26 09:15:27 kernel: ? tcp_send_loss_probe+0x214/0x220
Jul 26 09:15:27 kernel: tcp_write_timer_handler+0x1b4/0x240
Jul 26 09:15:27 kernel: tcp_write_timer+0x9e/0xe0
Jul 26 09:15:27 kernel: ? tcp_write_timer_handler+0x240/0x240
Jul 26 09:15:27 kernel: call_timer_fn+0x32/0x130
Jul 26 09:15:27 kernel: __run_timers.part.0+0x180/0x280
Jul 26 09:15:27 kernel: ? timerqueue_add+0x9b/0xb0
Jul 26 09:15:27 kernel: ? enqueue_hrtimer+0x3d/0x90
Jul 26 09:15:27 kernel: ? recalibrate_cpu_khz+0x10/0x10
Jul 26 09:15:27 kernel: ? ktime_get+0x3e/0xa0
Jul 26 09:15:27 kernel: ? native_x2apic_icr_write+0x30/0x30
Jul 26 09:15:27 kernel: run_timer_softirq+0x2a/0x50
Jul 26 09:15:27 kernel: __do_softirq+0xd1/0x2c1
Jul 26 09:15:27 kernel: irq_exit+0xae/0xb0
Jul 26 09:15:27 kernel: smp_apic_timer_interrupt+0x7b/0x140
Jul 26 09:15:27 kernel: apic_timer_interrupt+0xf/0x20
Jul 26 09:15:27 kernel: </IRQ>
Jul 26 09:15:27 kernel: RIP: 0010:native_safe_halt+0xe/0x10
Jul 26 09:15:27 kernel: Code: 7b ff ff ff eb bd 90 90 90 90 90 90 e9 07 00 00 00 0f 00 2d 36 2c 50 00 f4 c3 66 90 e9 07 00 00 00 0f 00 2d 26 2c 50 00 fb f4 <c3> 90 0f 1f 44 00 00 55 48 89 e5 41 55 41 54 53 e8 dd 5e 61 ff 65
Jul 26 09:15:27 kernel: RSP: 0018:ffffb783801cfe70 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13
Jul 26 09:15:27 kernel: RAX: ffffffffa6908b20 RBX: 0000000000000010 RCX: 0000000000000001
Jul 26 09:15:27 kernel: RDX: 000000006fc0c97e RSI: 0000000000000082 RDI: 0000000000000082
Jul 26 09:15:27 kernel: RBP: ffffb783801cfe90 R08: 0000000000000000 R09: 0000000000000225
Jul 26 09:15:27 kernel: R10: 0000000000100000 R11: 0000000000000000 R12: 0000000000000010
Jul 26 09:15:27 kernel: R13: ffff9b8e390b0000 R14: 0000000000000000 R15: 0000000000000000
Jul 26 09:15:27 kernel: ? __cpuidle_text_start+0x8/0x8
Jul 26 09:15:27 kernel: ? default_idle+0x20/0x140
Jul 26 09:15:27 kernel: arch_cpu_idle+0x15/0x20
Jul 26 09:15:27 kernel: default_idle_call+0x23/0x30
Jul 26 09:15:27 kernel: do_idle+0x1fb/0x270
Jul 26 09:15:27 kernel: cpu_startup_entry+0x20/0x30
Jul 26 09:15:27 kernel: start_secondary+0x178/0x1d0
Jul 26 09:15:27 kernel: secondary_startup_64+0xa4/0xb0
Jul 26 09:15:27 kernel: ---[ end trace e7ac822987e33be1 ]---

The NULL ptr deref is coming from tcp_rto_delta_us() attempting to pull an skb off the head of the retransmit queue and then dereferencing that skb to get the skb_mstamp_ns value via tcp_skb_timestamp_us(skb).

The crash is the same one that was reported a # of years ago here:
https://lore.kernel.org/netdev/[email protected]/T/#t

and the kernel we're running has the fix which was added to resolve this issue.

Unfortunately we've been unsuccessful so far in reproducing this problem in the lab and do not have the luxury of pushing out a new kernel to try and test if newer kernels resolve this issue at the moment. I realize this is a report against both an Ubuntu kernel and also an older 5.4 kernel. I have reported this issue to Ubuntu here: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2077657
however I feel like since this issue has possibly cropped up again it makes sense to build in some protection in this path (even on the latest kernel versions) since the code in question just blindly assumes there's a valid skb without testing if it's NULL b/f it looks at the timestamp.

Given we have seen crashes in this path before and now this case it seems like we should protect ourselves for when packets_out accounting is incorrect. While we should fix that root cause we should also just make sure the skb is not NULL before dereferencing it. Also add a warn once here to capture some information if/when the problem case is hit again.

---
 include/net/tcp.h | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

index 45bbb54e42e85..ac647c952cf0c 100644
@@ -2437,9 +2437,26 @@ static inline s64 tcp_rto_delta_us(const struct sock *sk)
 {
 	const struct sk_buff *skb = tcp_rtx_queue_head(sk);
 	u32 rto = inet_csk(sk)->icsk_rto;
-	u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto);
 
-	return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp;
+	if (likely(skb)) {
+		u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto);
+
+		return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp;
+	} else {
+		WARN_ONCE(1,
+			"rtx queue emtpy: "
+			"out:%u sacked:%u lost:%u retrans:%u "
+			"tlp_high_seq:%u sk_state:%u ca_state:%u "
+			"advmss:%u mss_cache:%u pmtu:%u\n",
+			tcp_sk(sk)->packets_out, tcp_sk(sk)->sacked_out,
+			tcp_sk(sk)->lost_out, tcp_sk(sk)->retrans_out,
+			tcp_sk(sk)->tlp_high_seq, sk->sk_state,
+			inet_csk(sk)->icsk_ca_state,
+			tcp_sk(sk)->advmss, tcp_sk(sk)->mss_cache,
+			inet_csk(sk)->icsk_pmtu_cookie);
+		return jiffies_to_usecs(rto);
+	}
+
 }
 
 /*

2.43.0

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

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

From: Youssef Samir <[email protected]>

[ Upstream commit f011b313e8ebd5b7abd8521b5119aecef403de45 ]

When broadcasting data to multiple nodes via MHI, using skb_clone() causes all nodes to receive the same header data. This can result in packets being discarded by endpoints, leading to lost data.

This issue occurs when a socket is closed, and a QRTR_TYPE_DEL_CLIENT packet is broadcasted. All nodes receive the same destination node ID, causing the node connected to the client to discard the packet and remain unaware of the client's deletion.

Replace skb_clone() with pskb_copy(), to create a separate copy of the header for each sk_buff.

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

index 41ece61eb57ab..00c51cf693f3d 100644
@@ -884,7 +884,7 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 
 	mutex_lock(&qrtr_node_lock);
 	list_for_each_entry(node, &qrtr_all_nodes, item) {
-		skbn = skb_clone(skb, GFP_KERNEL);
+		skbn = pskb_copy(skb, GFP_KERNEL);
 		if (!skbn)
 			break;
 		skb_set_owner_w(skbn, skb->sk);

2.43.0

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

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

From: Paul Barker <[email protected]>

[ Upstream commit ec8234717db8589078d08b17efa528a235c61f4f ]

The RX frame size limit should not be based on the current MTU setting. Instead it should be based on the hardware capabilities.

While we're here, improve the description of the receive frame length setting as suggested by Niklas.

---
 drivers/net/ethernet/renesas/ravb_main.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

index 4d100283c30fb..067357b2495cd 100644
@@ -530,8 +530,16 @@ static void ravb_emac_init_gbeth(struct net_device *ndev)
 
 static void ravb_emac_init_rcar(struct net_device *ndev)
 {
-	/* Receive frame limit set register */
-	ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR);
+	struct ravb_private *priv = netdev_priv(ndev);
+
+	/* Set receive frame length
+	 *
+	 * The length set here describes the frame from the destination address
+	 * up to and including the CRC data. However only the frame data,
+	 * excluding the CRC, are transferred to memory. To allow for the
+	 * largest frames add the CRC length to the maximum Rx descriptor size.
+	 */
+	ravb_write(ndev, priv->info->rx_max_frame_size + ETH_FCS_LEN, RFLR);
 
 	/* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */
 	ravb_write(ndev, ECMR_ZPF | ECMR_DM |

2.43.0

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

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

From: Jiwon Kim <[email protected]>

[ Upstream commit 0cbfd45fbcf0cb26d85c981b91c62fe73cdee01c ]

syzbot reported a WARNING in bond_xdp_get_xmit_slave. To reproduce this[1], one bond device (bond1) has xdpdrv, which increases bpf_master_redirect_enabled_key. Another bond device (bond0) which is unsupported by XDP but its slave (veth3) has xdpgeneric that returns XDP_TX. This triggers WARN_ON_ONCE() from the xdp_master_redirect(). To reduce unnecessary warnings and improve log management, we need to delete the WARN_ON_ONCE() and add ratelimit to the netdev_err().

[1] Steps to reproduce:
# Needs tx_xdp with return XDP_TX;
ip l add veth0 type veth peer veth1
ip l add veth3 type veth peer veth4
ip l add bond0 type bond mode 6 # BOND_MODE_ALB, unsupported by XDP ip l add bond1 type bond # BOND_MODE_ROUNDROBIN by default ip l set veth0 master bond1
ip l set bond1 up
# Increases bpf_master_redirect_enabled_key
ip l set dev bond1 xdpdrv object tx_xdp.o section xdp_tx ip l set veth3 master bond0
ip l set bond0 up
ip l set veth4 up
# Triggers WARN_ON_ONCE() from the xdp_master_redirect() ip l set veth3 xdpgeneric object tx_xdp.o section xdp_tx

---
 drivers/net/bonding/bond_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index 60db34095a255..3c61f5fbe6b7f 100644
@@ -5536,9 +5536,9 @@ bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp)
 		break;
 
 	default:
-		/* Should never happen. Mode guarded by bond_xdp_check() */
-		netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond));
-		WARN_ON_ONCE(1);
+		if (net_ratelimit())
+			netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n",
+				   BOND_MODE(bond));
 		return NULL;
 	}
 

2.43.0

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

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

From: Wenbo Li <[email protected]>

[ Upstream commit c11a49d58ad229a1be1ebe08a2b68fedf83db6c8 ]

Currently, the virtio-net driver will perform a pre-dma-mapping for small or mergeable RX buffer. But for small packets, a mismatched address without VIRTNET_RX_PAD and xdp_headroom is used for unmapping.

That will result in unsynchronized buffers when SWIOTLB is enabled, for example, when running as a TDX guest.

This patch unifies the address passed to the virtio core as the address of the virtnet header and fixes the mismatched buffer address.

Changes from v2: unify the buf that passed to the virtio core in small and merge mode.
Changes from v1: Use ctx to get xdp_headroom.

---
 drivers/net/virtio_net.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

index 21bd0c127b05a..0b1630bb173a5 100644
@@ -1439,6 +1439,11 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	struct page *page = virt_to_head_page(buf);
 	struct sk_buff *skb;
 
+	/* We passed the address of virtnet header to virtio-core,
+	 * so truncate the padding.
+	 */
+	buf -= VIRTNET_RX_PAD + xdp_headroom;
+
 	len -= vi->hdr_len;
 	u64_stats_add(&stats->bytes, len);
 

@@ -2029,8 +2034,9 @@ static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
 	if (unlikely(!buf))
 		return -ENOMEM;
 
-	virtnet_rq_init_one_sg(rq, buf + VIRTNET_RX_PAD + xdp_headroom,
-			       vi->hdr_len + GOOD_PACKET_LEN);
+	buf += VIRTNET_RX_PAD + xdp_headroom;
+
+	virtnet_rq_init_one_sg(rq, buf, vi->hdr_len + GOOD_PACKET_LEN);
 
 	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
 	if (err < 0) {

2.43.0

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

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

From: Furong Xu <[email protected]>

[ Upstream commit b514c47ebf41a6536551ed28a05758036e6eca7c ]

Commit 5fabb01207a2 ("net: stmmac: Add initial XDP support") sets PP_FLAG_DMA_SYNC_DEV flag for page_pool unconditionally, page_pool_recycle_direct() will call page_pool_dma_sync_for_device() on every page even the page is not going to be reused by XDP program.

When XDP is not enabled, the page which holds the received buffer will be recycled once the buffer is copied into new SKB by skb_copy_to_linear_data(), then the MAC core will never reuse this page any longer. Always setting PP_FLAG_DMA_SYNC_DEV wastes CPU cycles on unnecessary calling of page_pool_dma_sync_for_device().

After this patch, up to 9% noticeable performance improvement was observed on certain platforms.

---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 33e2bd5a351ca..3b1bb6aa5b8c8 100644
@@ -2025,7 +2025,7 @@ static int __alloc_dma_rx_desc_resources(struct stmmac_priv *priv,
 	rx_q->queue_index = queue;
 	rx_q->priv_data = priv;
 
-	pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+	pp_params.flags = PP_FLAG_DMA_MAP | (xdp_prog ? PP_FLAG_DMA_SYNC_DEV : 0);
 	pp_params.pool_size = dma_conf->dma_rx_size;
 	num_pages = DIV_ROUND_UP(dma_conf->dma_buf_sz, PAGE_SIZE);
 	pp_params.order = ilog2(num_pages);

2.43.0

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

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

From: Phil Sutter <[email protected]>

[ Upstream commit 642c89c475419b4d0c0d90e29d9c1a0e4351f379 ]

Documentation of list_del_rcu() warns callers to not immediately free the deleted list item. While it seems not necessary to use the RCU-variant of list_del() here in the first place, doing so seems to require calling kfree_rcu() on the deleted item as well.

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

index d4b5f23930c9f..3c19928b359c3 100644
@@ -9137,7 +9137,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
 		flowtable->data.type->setup(&flowtable->data, hook->ops.dev,
 					    FLOW_BLOCK_UNBIND);
 		list_del_rcu(&hook->list);
-		kfree(hook);
+		kfree_rcu(hook, rcu);
 	}
 	kfree(flowtable->name);
 	module_put(flowtable->data.type->owner);

2.43.0

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

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

From: Simon Horman <[email protected]>

[ Upstream commit e1f1ee0e9ad8cbe660f5c104e791c5f1a7cf4c31 ]

Only provide ctnetlink_label_size when it is used, which is when CONFIG_NF_CONNTRACK_EVENTS is configured.

Flagged by clang-18 W=1 builds as:

.../nf_conntrack_netlink.c:385:19: warning: unused function 'ctnetlink_label_size' [-Wunused-function]
385 | static inline int ctnetlink_label_size(const struct nf_conn *ct)

      |                   ^~~~~~~~~~~~~~~~~~~~

The condition on CONFIG_NF_CONNTRACK_LABELS being removed by this patch guards compilation of non-trivial implementations of ctnetlink_dump_labels() and ctnetlink_label_size().

However, this is not necessary as each of these functions will always return 0 if CONFIG_NF_CONNTRACK_LABELS is not defined as each function starts with the equivalent of:

	struct nf_conn_labels *labels = nf_ct_labels_find(ct);

	if (!labels)
		return 0;

And nf_ct_labels_find always returns NULL if CONFIG_NF_CONNTRACK_LABELS is not enabled. So I believe that the compiler optimises the code away in such cases anyway.

Found by inspection.
Compile tested only.

Originally splitted in two patches, Pablo Neira Ayuso collapsed them and added Fixes: tag.

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

index 4cbf71d0786b0..c55cf5bc36b2f 100644
@@ -382,7 +382,7 @@ static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct)
 #define ctnetlink_dump_secctx(a, b) (0)
 #endif
 
-#ifdef CONFIG_NF_CONNTRACK_LABELS
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
 static inline int ctnetlink_label_size(const struct nf_conn *ct)
 {
 	struct nf_conn_labels *labels = nf_ct_labels_find(ct);

@@ -391,6 +391,7 @@ static inline int ctnetlink_label_size(const struct nf_conn *ct)
 		return 0;
 	return nla_total_size(sizeof(labels->bits));
 }
+#endif
 
 static int
 ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct)

@@ -411,10 +412,6 @@ ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct)
 
 	return 0;
 }
-#else
-#define ctnetlink_dump_labels(a, b) (0)
-#define ctnetlink_label_size(a)	(0)
-#endif
 
 #define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple)
 

2.43.0

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

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

From: Pablo Neira Ayuso <[email protected]>

[ Upstream commit 4ffcf5ca81c3b83180473eb0d3c010a1a7c6c4de ]

Lockless iteration over hook list is possible from netlink dump path, use rcu variant to iterate over the hook list as is done with flowtable hooks.

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

index 3c19928b359c3..71df3e5cc46d9 100644
@@ -1795,7 +1795,7 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family,
 		if (!hook_list)
 			hook_list = &basechain->hook_list;
 
-		list_for_each_entry(hook, hook_list, list) {
+		list_for_each_entry_rcu(hook, hook_list, list) {
 			if (!first)
 				first = hook;
 

2.43.0

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

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

From: Pablo Neira Ayuso <[email protected]>

[ Upstream commit 69e687cea79fc99a17dfb0116c8644b9391b915e ]

Several ruleset objects are still not using GFP_KERNEL_ACCOUNT for memory accounting, update them. This includes:

- catchall elements
- compat match large info area
- log prefix
- meta secctx
- numgen counters
- pipapo set backend datastructure
- tunnel private objects

---
 net/netfilter/nf_tables_api.c  |  2 +-
 net/netfilter/nft_compat.c     |  6 +++---
 net/netfilter/nft_log.c        |  2 +-
 net/netfilter/nft_meta.c       |  2 +-
 net/netfilter/nft_numgen.c     |  2 +-
 net/netfilter/nft_set_pipapo.c | 13 +++++++------
 net/netfilter/nft_tunnel.c     |  5 +++--
 7 files changed, 17 insertions(+), 15 deletions(-)

index 71df3e5cc46d9..465cc43c75e30 100644
@@ -6631,7 +6631,7 @@ static int nft_setelem_catchall_insert(const struct net *net,
 		}
 	}
 
-	catchall = kmalloc(sizeof(*catchall), GFP_KERNEL);
+	catchall = kmalloc(sizeof(*catchall), GFP_KERNEL_ACCOUNT);
 	if (!catchall)
 		return -ENOMEM;
 

index d3d11dede5450..85450f6011426 100644
@@ -536,7 +536,7 @@ nft_match_large_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 	struct xt_match *m = expr->ops->data;
 	int ret;
 
-	priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL);
+	priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL_ACCOUNT);
 	if (!priv->info)
 		return -ENOMEM;
 

@@ -810,7 +810,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL);
+	ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL_ACCOUNT);
 	if (!ops) {
 		err = -ENOMEM;
 		goto err;

@@ -900,7 +900,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 		goto err;
 	}
 
-	ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL);
+	ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL_ACCOUNT);
 	if (!ops) {
 		err = -ENOMEM;
 		goto err;

index 5defe6e4fd982..e355881379957 100644
@@ -163,7 +163,7 @@ static int nft_log_init(const struct nft_ctx *ctx,
 
 	nla = tb[NFTA_LOG_PREFIX];
 	if (nla != NULL) {
-		priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
+		priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL_ACCOUNT);
 		if (priv->prefix == NULL)
 			return -ENOMEM;
 		nla_strscpy(priv->prefix, nla, nla_len(nla) + 1);

index 9139ce38ea7b9..f23faf565b687 100644
@@ -954,7 +954,7 @@ static int nft_secmark_obj_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_SECMARK_CTX] == NULL)
 		return -EINVAL;
 
-	priv->ctx = nla_strdup(tb[NFTA_SECMARK_CTX], GFP_KERNEL);
+	priv->ctx = nla_strdup(tb[NFTA_SECMARK_CTX], GFP_KERNEL_ACCOUNT);
 	if (!priv->ctx)
 		return -ENOMEM;
 

index 7d29db7c2ac0f..bd058babfc820 100644
@@ -66,7 +66,7 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx,
 	if (priv->offset + priv->modulus - 1 < priv->offset)
 		return -EOVERFLOW;
 
-	priv->counter = kmalloc(sizeof(*priv->counter), GFP_KERNEL);
+	priv->counter = kmalloc(sizeof(*priv->counter), GFP_KERNEL_ACCOUNT);
 	if (!priv->counter)
 		return -ENOMEM;
 

index eb4c4a4ac7ace..7be342b495f5f 100644
@@ -663,7 +663,7 @@ static int pipapo_realloc_mt(struct nft_pipapo_field *f,
 	    check_add_overflow(rules, extra, &rules_alloc))
 		return -EOVERFLOW;
 
-	new_mt = kvmalloc_array(rules_alloc, sizeof(*new_mt), GFP_KERNEL);
+	new_mt = kvmalloc_array(rules_alloc, sizeof(*new_mt), GFP_KERNEL_ACCOUNT);
 	if (!new_mt)
 		return -ENOMEM;
 

@@ -936,7 +936,7 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f)
 		return;
 	}
 
-	new_lt = kvzalloc(lt_size + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL);
+	new_lt = kvzalloc(lt_size + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL_ACCOUNT);
 	if (!new_lt)
 		return;
 

@@ -1212,7 +1212,7 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
 		scratch = kzalloc_node(struct_size(scratch, map,
 						   bsize_max * 2) +
 				       NFT_PIPAPO_ALIGN_HEADROOM,
-				       GFP_KERNEL, cpu_to_node(i));
+				       GFP_KERNEL_ACCOUNT, cpu_to_node(i));
 		if (!scratch) {
 			/* On failure, there's no need to undo previous
 			 * allocations: this means that some scratch maps have

@@ -1427,7 +1427,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 	struct nft_pipapo_match *new;
 	int i;
 
-	new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL);
+	new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL_ACCOUNT);
 	if (!new)
 		return NULL;
 

@@ -1457,7 +1457,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 		new_lt = kvzalloc(src->groups * NFT_PIPAPO_BUCKETS(src->bb) *
 				  src->bsize * sizeof(*dst->lt) +
 				  NFT_PIPAPO_ALIGN_HEADROOM,
-				  GFP_KERNEL);
+				  GFP_KERNEL_ACCOUNT);
 		if (!new_lt)
 			goto out_lt;
 

@@ -1470,7 +1470,8 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
 
 		if (src->rules > 0) {
 			dst->mt = kvmalloc_array(src->rules_alloc,
-						 sizeof(*src->mt), GFP_KERNEL);
+						 sizeof(*src->mt),
+						 GFP_KERNEL_ACCOUNT);
 			if (!dst->mt)
 				goto out_mt;
 

index 60a76e6e348e7..5c6ed68cc6e05 100644
@@ -509,13 +509,14 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx,
 			return err;
 	}
 
-	md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL, GFP_KERNEL);
+	md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL,
+				GFP_KERNEL_ACCOUNT);
 	if (!md)
 		return -ENOMEM;
 
 	memcpy(&md->u.tun_info, &info, sizeof(info));
 #ifdef CONFIG_DST_CACHE
-	err = dst_cache_init(&md->u.tun_info.dst_cache, GFP_KERNEL);
+	err = dst_cache_init(&md->u.tun_info.dst_cache, GFP_KERNEL_ACCOUNT);
 	if (err < 0) {
 		metadata_dst_free(md);
 		return err;

2.43.0

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

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

From: Phil Sutter <[email protected]>

[ Upstream commit fc786304ad9803e8bb86b8599bc64d1c1746c75f ]

If the client can't reach the server, the latter remains listening forever. Kill it after 5s of waiting.

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

index 4ceee9fb39495..d3edb16cd4b3f 100755
@@ -97,7 +97,7 @@ cleanup() {
 }
 
 server_listen() {
-	ip netns exec "$ns2" socat -u -4 TCP-LISTEN:8080,reuseaddr STDOUT > "${outfile}" &
+	ip netns exec "$ns2" timeout 5 socat -u -4 TCP-LISTEN:8080,reuseaddr STDOUT > "${outfile}" &
 	server_pid=$!
 	sleep 0.2
 }

2.43.0

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

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

From: Felix Moessbauer <[email protected]>

commit f011c9cf04c06f16b24f583d313d3c012e589e50 upstream.

The submit queue polling threads are userland threads that just never exit to the userland. When creating the thread with IORING_SETUP_SQ_AFF, the affinity of the poller thread is set to the cpu specified in sq_thread_cpu. However, this CPU can be outside of the cpuset defined by the cgroup cpuset controller. This violates the rules defined by the cpuset controller and is a potential issue for realtime applications.

In b7ed6d8ffd6 we fixed the default affinity of the poller thread, in case no explicit pinning is required by inheriting the one of the creating task. In case of explicit pinning, the check is more complicated, as also a cpu outside of the parent cpumask is allowed. We implemented this by using cpuset_cpus_allowed (that has support for cgroup cpusets) and testing if the requested cpu is in the set.

---
 io_uring/sqpoll.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/audit.h>
 #include <linux/security.h>
+#include <linux/cpuset.h>
 #include <linux/io_uring.h>
 
 #include <uapi/linux/io_uring.h>

@@ -460,10 +461,12 @@ __cold int io_sq_offload_create(struct i
 			return 0;
 
 		if (p->flags & IORING_SETUP_SQ_AFF) {
+			struct cpumask allowed_mask;
 			int cpu = p->sq_thread_cpu;
 
 			ret = -EINVAL;
-			if (cpu >= nr_cpu_ids || !cpu_online(cpu))
+			cpuset_cpus_allowed(current, &allowed_mask);
+			if (!cpumask_test_cpu(cpu, &allowed_mask))
 				goto err_sqpoll;
 			sqd->sq_cpu = cpu;
 		} else {

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

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

From: Jens Axboe <[email protected]>

commit c0a9d496e0fece67db777bd48550376cf2960c47 upstream.

Some file systems, ocfs2 in this case, will return -EOPNOTSUPP for an IOCB_NOWAIT read/write attempt. While this can be argued to be correct, the usual return value for something that requires blocking issue is -EAGAIN.

A refactoring io_uring commit dropped calling kiocb_done() for negative return values, which is otherwise where we already do that transformation. To ensure we catch it in both spots, check it in __io_read() itself as well.

---
 io_uring/rw.c |    8 ++++++++
 1 file changed, 8 insertions(+)

@@ -856,6 +856,14 @@ static int __io_read(struct io_kiocb *re
 
 	ret = io_iter_do_read(rw, &io->iter);
 
+	/*
+	 * Some file systems like to return -EOPNOTSUPP for an IOCB_NOWAIT
+	 * issue, even though they should be returning -EAGAIN. To be safe,
+	 * retry from blocking context for either.
+	 */
+	if (ret == -EOPNOTSUPP && force_nonblock)
+		ret = -EAGAIN;
+
 	if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
 		req->flags &= ~REQ_F_REISSUE;
 		/* If we can poll, just do that. */

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

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

From: Jens Axboe <[email protected]>

commit 04beb6e0e08c30c6f845f50afb7d7953603d7a6f upstream.

If some part of the kernel adds task_work that needs executing, in terms of signaling it'll generally use TWA_SIGNAL or TWA_RESUME. Those two directly translate to TIF_NOTIFY_SIGNAL or TIF_NOTIFY_RESUME, and can be used for a variety of use case outside of task_work.

However, io_cqring_wait_schedule() only tests explicitly for TIF_NOTIFY_SIGNAL. This means it can miss if task_work got added for the task, but used a different kind of signaling mechanism (or none at all). Normally this doesn't matter as any task_work will be run once the task exits to userspace, except if:

1) The ring is setup with DEFER_TASKRUN
2) The local work item may generate normal task_work

For condition 2, this can happen when closing a file and it's the final put of that file, for example. This can cause stalls where a task is waiting to make progress inside io_cqring_wait(), but there's nothing else that will wake it up. Hence change the "should we schedule or loop around" check to check for the presence of task_work explicitly, rather than just TIF_NOTIFY_SIGNAL as the mechanism. While in there, also change the ordering of what type of task_work first in terms of ordering, to both make it consistent with other task_work runs in io_uring, but also to better handle the case of defer task_work generating normal task_work, like in the above example.

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

@@ -2401,7 +2401,7 @@ static inline int io_cqring_wait_schedul
 		return 1;
 	if (unlikely(!llist_empty(&ctx->work_llist)))
 		return 1;
-	if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL)))
+	if (unlikely(task_work_pending(current)))
 		return 1;
 	if (unlikely(task_sigpending(current)))
 		return -EINTR;

@@ -2502,9 +2502,9 @@ static int io_cqring_wait(struct io_ring
 		 * If we got woken because of task_work being processed, run it
 		 * now rather than let the caller do another wait loop.
 		 */
-		io_run_task_work();
 		if (!llist_empty(&ctx->work_llist))
 			io_run_local_work(ctx, nr_wait);
+		io_run_task_work();
 
 		/*
 		 * Non-local task_work will be run on exit to userspace, but

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

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

From: yangyun <[email protected]>

commit 2f3d8ff457982f4055fe8f7bf19d3821ba22c376 upstream.

This may be a typo. The comment has said shared locks are not allowed when this bit is set. If using shared lock, the wait in fuse_file_cached_io_open may be forever.

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

index b8afeca12487..1b5cd46c8225 100644
@@ -1345,7 +1345,7 @@ static bool fuse_dio_wr_exclusive_lock(struct kiocb *iocb, struct iov_iter *from
 
 	/* shared locks are not allowed with parallel page cache IO */
 	if (test_bit(FUSE_I_CACHE_IO_MODE, &fi->state))
-		return false;
+		return true;
 
 	/* Parallel dio beyond EOF is not supported, at least for now. */
 	if (fuse_io_past_eof(iocb, from))

2.46.2

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

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

From: Jeongjun Park <[email protected]>

commit 8001070cfbec5cd4ea00b8b48ea51df91122f265 upstream.

I found a report from syzbot [1]

This report shows that the value can be changed, but in reality, the value of __folio_set_movable() cannot be changed because it holds the folio refcount.

Therefore, it is appropriate to add an annotate to make KCSAN ignore that data-race.

[1]

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

BUG: KCSAN: data-race in __filemap_remove_folio / migrate_pages_batch

write to 0xffffea0004b81dd8 of 8 bytes by task 6348 on cpu 0:

 page_cache_delete mm/filemap.c:153 [inline]
 __filemap_remove_folio+0x1ac/0x2c0 mm/filemap.c:233
 filemap_remove_folio+0x6b/0x1f0 mm/filemap.c:265
 truncate_inode_folio+0x42/0x50 mm/truncate.c:178
 shmem_undo_range+0x25b/0xa70 mm/shmem.c:1028
 shmem_truncate_range mm/shmem.c:1144 [inline]
 shmem_evict_inode+0x14d/0x530 mm/shmem.c:1272
 evict+0x2f0/0x580 fs/inode.c:731
 iput_final fs/inode.c:1883 [inline]
 iput+0x42a/0x5b0 fs/inode.c:1909
 dentry_unlink_inode+0x24f/0x260 fs/dcache.c:412
 __dentry_kill+0x18b/0x4c0 fs/dcache.c:615
 dput+0x5c/0xd0 fs/dcache.c:857
 __fput+0x3fb/0x6d0 fs/file_table.c:439
 ____fput+0x1c/0x30 fs/file_table.c:459
 task_work_run+0x13a/0x1a0 kernel/task_work.c:228
 resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:114 [inline]
 exit_to_user_mode_prepare include/linux/entry-common.h:328 [inline]
 __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline]
 syscall_exit_to_user_mode+0xbe/0x130 kernel/entry/common.c:218
 do_syscall_64+0xd6/0x1c0 arch/x86/entry/common.c:89
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

read to 0xffffea0004b81dd8 of 8 bytes by task 6342 on cpu 1:

 __folio_test_movable include/linux/page-flags.h:699 [inline]
 migrate_folio_unmap mm/migrate.c:1199 [inline]
 migrate_pages_batch+0x24c/0x1940 mm/migrate.c:1797
 migrate_pages_sync mm/migrate.c:1963 [inline]
 migrate_pages+0xff1/0x1820 mm/migrate.c:2072
 do_mbind mm/mempolicy.c:1390 [inline]
 kernel_mbind mm/mempolicy.c:1533 [inline]
 __do_sys_mbind mm/mempolicy.c:1607 [inline]
 __se_sys_mbind+0xf76/0x1160 mm/mempolicy.c:1603
 __x64_sys_mbind+0x78/0x90 mm/mempolicy.c:1603
 x64_sys_call+0x2b4d/0x2d60 arch/x86/include/generated/asm/syscalls_64.h:238
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xc9/0x1c0 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

value changed: 0xffff888127601078 -> 0x0000000000000000

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

@@ -1129,7 +1129,7 @@ static int migrate_folio_unmap(new_folio
 	int rc = -EAGAIN;
 	int old_page_state = 0;
 	struct anon_vma *anon_vma = NULL;
-	bool is_lru = !__folio_test_movable(src);
+	bool is_lru = data_race(!__folio_test_movable(src));
 	bool locked = false;
 	bool dst_locked = false;
 

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

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

From: Shu Han <[email protected]>

commit ea7e2d5e49c05e5db1922387b09ca74aa40f46e2 upstream.

The remap_file_pages syscall handler calls do_mmap() directly, which doesn't contain the LSM security check. And if the process has called personality(READ_IMPLIES_EXEC) before and remap_file_pages() is called for RW pages, this will actually result in remapping the pages to RWX, bypassing a W^X policy enforced by SELinux.

So we should check prot by security_mmap_file LSM hook in the remap_file_pages syscall handler before do_mmap() is called. Otherwise, it potentially permits an attacker to bypass a W^X policy enforced by SELinux.

The bypass is similar to CVE-2016-10044, which bypass the same thing via AIO and can be found in [1].

The PoC:

$ cat > test.c

int main(void) {
	size_t pagesz = sysconf(_SC_PAGE_SIZE);
	int mfd = syscall(SYS_memfd_create, "test", 0);
	const char *buf = mmap(NULL, 4 * pagesz, PROT_READ | PROT_WRITE,
		MAP_SHARED, mfd, 0);
	unsigned int old = syscall(SYS_personality, 0xffffffff);
	syscall(SYS_personality, READ_IMPLIES_EXEC | old);
	syscall(SYS_remap_file_pages, buf, pagesz, 0, 2, 0);
	syscall(SYS_personality, old);
	// show the RWX page exists even if W^X policy is enforced
	int fd = open("/proc/self/maps", O_RDONLY);
	unsigned char buf2[1024];
	while (1) {
		int ret = read(fd, buf2, 1024);
		if (ret <= 0) break;
		write(1, buf2, ret);
	}
	close(fd);
}

$ gcc test.c -o test
$ ./test | grep rwx
7f1836c34000-7f1836c35000 rwxs 00002000 00:01 2050 /memfd:test (deleted)

---
 mm/mmap.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -3127,8 +3127,12 @@ SYSCALL_DEFINE5(remap_file_pages, unsign
 		flags |= MAP_LOCKED;
 
 	file = get_file(vma->vm_file);
+	ret = security_mmap_file(vma->vm_file, prot, flags);
+	if (ret)
+		goto out_fput;
 	ret = do_mmap(vma->vm_file, start, size,
 			prot, flags, 0, pgoff, &populate, NULL);
+out_fput:
 	fput(file);
 out:
 	mmap_write_unlock(mm);

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

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

From: Fangzhi Zuo <[email protected]>

commit 4437936c6b696b98f3fe1d8679a2788c41b4df77 upstream.

Synaptics Cascaded Panamera topology needs to unconditionally acquire root aux for dsc decoding.

---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -251,7 +251,7 @@ static bool validate_dsc_caps_on_connect
 		aconnector->dsc_aux = &aconnector->mst_root->dm_dp_aux.aux;
 
 	/* synaptics cascaded MST hub case */
-	if (!aconnector->dsc_aux && is_synaptics_cascaded_panamera(aconnector->dc_link, port))
+	if (is_synaptics_cascaded_panamera(aconnector->dc_link, port))
 		aconnector->dsc_aux = port->mgr->aux;
 
 	if (!aconnector->dsc_aux)

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

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

From: Juergen Gross <[email protected]>

commit c4498ae316da5b5786ccd448fc555f3339b8e4ca upstream.

Move the checks for e820 memory map conflicts using the xen_chk_is_e820_usable() helper further up in order to prepare resolving some of the possible conflicts by doing some e820 map modifications, which must happen before evaluating the RAM layout.

---
 arch/x86/xen/setup.c |   44 ++++++++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 22 deletions(-)

@@ -855,6 +855,28 @@ char * __init xen_memory_setup(void)
 	/* Make sure the Xen-supplied memory map is well-ordered. */
 	e820__update_table(&xen_e820_table);
 
+	/*
+	 * Check whether the kernel itself conflicts with the target E820 map.
+	 * Failing now is better than running into weird problems later due
+	 * to relocating (and even reusing) pages with kernel text or data.
+	 */
+	xen_chk_is_e820_usable(__pa_symbol(_text),
+			       __pa_symbol(_end) - __pa_symbol(_text),
+			       "kernel");
+
+	/*
+	 * Check for a conflict of the xen_start_info memory with the target
+	 * E820 map.
+	 */
+	xen_chk_is_e820_usable(__pa(xen_start_info), sizeof(*xen_start_info),
+			       "xen_start_info");
+
+	/*
+	 * Check for a conflict of the hypervisor supplied page tables with
+	 * the target E820 map.
+	 */
+	xen_pt_check_e820();
+
 	max_pages = xen_get_max_pages();
 
 	/* How many extra pages do we need due to remapping? */

@@ -927,28 +949,6 @@ char * __init xen_memory_setup(void)
 
 	e820__update_table(e820_table);
 
-	/*
-	 * Check whether the kernel itself conflicts with the target E820 map.
-	 * Failing now is better than running into weird problems later due
-	 * to relocating (and even reusing) pages with kernel text or data.
-	 */
-	xen_chk_is_e820_usable(__pa_symbol(_text),
-			       __pa_symbol(_end) - __pa_symbol(_text),
-			       "kernel");
-
-	/*
-	 * Check for a conflict of the xen_start_info memory with the target
-	 * E820 map.
-	 */
-	xen_chk_is_e820_usable(__pa(xen_start_info), sizeof(*xen_start_info),
-			       "xen_start_info");
-
-	/*
-	 * Check for a conflict of the hypervisor supplied page tables with
-	 * the target E820 map.
-	 */
-	xen_pt_check_e820();
-
 	xen_reserve_xen_mfnlist();
 
 	/* Check for a conflict of the initrd with the target E820 map. */

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

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

From: Juergen Gross <[email protected]>

commit 9221222c717dbddac1e3c49906525475d87a3a44 upstream.

When running as a Xen PV dom0 the system needs to map ACPI data of the host using host physical addresses, while those addresses can conflict with the guest physical addresses of the loaded linux kernel. The same problem might apply in case a PV guest is configured to use the host memory map.

This conflict can be solved by mapping the ACPI data to a different guest physical address, but mapping the data via acpi_os_ioremap() must still be possible using the host physical address, as this address might be generated by AML when referencing some of the ACPI data.

When configured to support running as a Xen PV domain, have an implementation of acpi_os_ioremap() being aware of the possibility to need above mentioned translation of a host physical address to the guest physical address.

This modification requires to #include linux/acpi.h in some sources which need to include asm/acpi.h directly.

---
 arch/x86/include/asm/acpi.h        |    8 ++++++++
 arch/x86/kernel/acpi/boot.c        |   11 +++++++++++
 arch/x86/kernel/jailhouse.c        |    1 +
 arch/x86/kernel/mmconf-fam10h_64.c |    1 +
 arch/x86/kernel/smpboot.c          |    1 +
 arch/x86/kernel/x86_init.c         |    1 +
 arch/x86/xen/p2m.c                 |   35 +++++++++++++++++++++++++++++++++++
 arch/x86/xen/setup.c               |    2 +-
 8 files changed, 59 insertions(+), 1 deletion(-)

@@ -167,6 +167,14 @@ void acpi_generic_reduced_hw_init(void);
 void x86_default_set_root_pointer(u64 addr);
 u64 x86_default_get_root_pointer(void);
 
+#ifdef CONFIG_XEN_PV
+/* A Xen PV domain needs a special acpi_os_ioremap() handling. */
+extern void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys,
+					 acpi_size size);
+void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size);
+#define acpi_os_ioremap acpi_os_ioremap
+#endif
+
 #else /* !CONFIG_ACPI */
 
 #define acpi_lapic 0

@@ -1862,3 +1862,14 @@ u64 x86_default_get_root_pointer(void)
 {
 	return boot_params.acpi_rsdp_addr;
 }
+
+#ifdef CONFIG_XEN_PV
+void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
+{
+	return ioremap_cache(phys, size);
+}
+
+void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys, acpi_size size) =
+	x86_acpi_os_ioremap;
+EXPORT_SYMBOL_GPL(acpi_os_ioremap);
+#endif

@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/reboot.h>
 #include <linux/serial_8250.h>
+#include <linux/acpi.h>
 #include <asm/apic.h>
 #include <asm/io_apic.h>
 #include <asm/acpi.h>

@@ -9,6 +9,7 @@
 #include <linux/pci.h>
 #include <linux/dmi.h>
 #include <linux/range.h>
+#include <linux/acpi.h>
 
 #include <asm/pci-direct.h>
 #include <linux/sort.h>

@@ -60,6 +60,7 @@
 #include <linux/stackprotector.h>
 #include <linux/cpuhotplug.h>
 #include <linux/mc146818rtc.h>
+#include <linux/acpi.h>
 
 #include <asm/acpi.h>
 #include <asm/cacheinfo.h>

@@ -8,6 +8,7 @@
 #include <linux/ioport.h>
 #include <linux/export.h>
 #include <linux/pci.h>
+#include <linux/acpi.h>
 
 #include <asm/acpi.h>
 #include <asm/bios_ebda.h>

@@ -70,6 +70,7 @@
 #include <linux/memblock.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
+#include <linux/acpi.h>
 
 #include <asm/cache.h>
 #include <asm/setup.h>

@@ -835,6 +836,34 @@ void __init xen_do_remap_nonram(void)
 	pr_info("Remapped %u non-RAM page(s)\n", remapped);
 }
 
+#ifdef CONFIG_ACPI
+/*
+ * Xen variant of acpi_os_ioremap() taking potentially remapped non-RAM
+ * regions into account.
+ * Any attempt to map an area crossing a remap boundary will produce a
+ * WARN() splat.
+ * phys is related to remap->maddr on input and will be rebased to remap->paddr.
+ */
+static void __iomem *xen_acpi_os_ioremap(acpi_physical_address phys,
+					 acpi_size size)
+{
+	unsigned int i;
+	const struct nonram_remap *remap = xen_nonram_remap;
+
+	for (i = 0; i < nr_nonram_remap; i++) {
+		if (phys + size > remap->maddr &&
+		    phys < remap->maddr + remap->size) {
+			WARN_ON(phys < remap->maddr ||
+				phys + size > remap->maddr + remap->size);
+			phys += remap->paddr - remap->maddr;
+			break;
+		}
+	}
+
+	return x86_acpi_os_ioremap(phys, size);
+}
+#endif /* CONFIG_ACPI */
+
 /*
  * Add a new non-RAM remap entry.
  * In case of no free entry found, just crash the system.

@@ -849,6 +878,12 @@ void __init xen_add_remap_nonram(phys_ad
 		BUG();
 	}
 
+#ifdef CONFIG_ACPI
+	/* Switch to the Xen acpi_os_ioremap() variant. */
+	if (nr_nonram_remap == 0)
+		acpi_os_ioremap = xen_acpi_os_ioremap;
+#endif
+
 	xen_nonram_remap[nr_nonram_remap].maddr = maddr;
 	xen_nonram_remap[nr_nonram_remap].paddr = paddr;
 	xen_nonram_remap[nr_nonram_remap].size = size;

@@ -15,12 +15,12 @@
 #include <linux/cpuidle.h>
 #include <linux/cpufreq.h>
 #include <linux/memory_hotplug.h>
+#include <linux/acpi.h>
 
 #include <asm/elf.h>
 #include <asm/vdso.h>
 #include <asm/e820/api.h>
 #include <asm/setup.h>
-#include <asm/acpi.h>
 #include <asm/numa.h>
 #include <asm/idtentry.h>
 #include <asm/xen/hypervisor.h>

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

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

From: Jens Axboe <[email protected]>

commit a09c17240bdf2e9fa6d0591afa9448b59785f7d4 upstream.

A recent commit ensured that SQPOLL cannot be setup with a CPU that isn't in the current tasks cpuset, but it also dropped testing whether the CPU is valid in the first place. Without that, if a task passes in a CPU value that is too high, the following KASAN splat can get triggered:

BUG: KASAN: stack-out-of-bounds in io_sq_offload_create+0x858/0xaa4
Read of size 8 at addr ffff800089bc7b90 by task wq-aff.t/1391

CPU: 4 UID: 1000 PID: 1391 Comm: wq-aff.t Not tainted 6.11.0-rc7-00227-g371c468f4db6 #7080
Hardware name: linux,dummy-virt (DT)
Call trace:
 dump_backtrace.part.0+0xcc/0xe0
 show_stack+0x14/0x1c
 dump_stack_lvl+0x58/0x74
 print_report+0x16c/0x4c8
 kasan_report+0x9c/0xe4
 __asan_report_load8_noabort+0x1c/0x24
 io_sq_offload_create+0x858/0xaa4
 io_uring_setup+0x1394/0x17c4
 __arm64_sys_io_uring_setup+0x6c/0x180
 invoke_syscall+0x6c/0x260
 el0_svc_common.constprop.0+0x158/0x224
 do_el0_svc+0x3c/0x5c
 el0_svc+0x34/0x70
 el0t_64_sync_handler+0x118/0x124
 el0t_64_sync+0x168/0x16c

The buggy address belongs to stack of task wq-aff.t/1391
 and is located at offset 48 in frame:
 io_sq_offload_create+0x0/0xaa4

This frame has 1 object:
[32, 40) 'allowed_mask'

The buggy address belongs to the virtual mapping at
 [ffff800089bc0000, ffff800089bc9000) created by:
 kernel_clone+0x124/0x7e0

The buggy address belongs to the physical page:
page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff0000d740af80 pfn:0x11740a
memcg:ffff0000c2706f02
flags: 0xbffe00000000000(node=0|zone=2|lastcpupid=0x1fff)
raw: 0bffe00000000000 0000000000000000 dead000000000122 0000000000000000
raw: ffff0000d740af80 0000000000000000 00000001ffffffff ffff0000c2706f02
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff800089bc7a80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 ffff800089bc7b00: 00 00 00 00 00 00 00 00 00 00 00 00 f1 f1 f1 f1
>ffff800089bc7b80: 00 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00
                         ^
 ffff800089bc7c00: 00 00 00 00 00 00 00 00 00 00 00 00 f1 f1 f1 f1
 ffff800089bc7c80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 f3

---
 io_uring/sqpoll.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -465,6 +465,8 @@ __cold int io_sq_offload_create(struct i
 			int cpu = p->sq_thread_cpu;
 
 			ret = -EINVAL;
+			if (cpu >= nr_cpu_ids || !cpu_online(cpu))
+				goto err_sqpoll;
 			cpuset_cpus_allowed(current, &allowed_mask);
 			if (!cpumask_test_cpu(cpu, &allowed_mask))
 				goto err_sqpoll;

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

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

From: Felix Moessbauer <[email protected]>

commit 7f44beadcc11adb98220556d2ddbe9c97aa6d42d upstream.

Putting the cpumask on the stack is deprecated for a long time (since 2d3854a37e8), as these can be big. Given that, change the on-stack allocation of allowed_mask to be dynamically allocated.

---
 io_uring/sqpoll.c |   13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

@@ -461,15 +461,22 @@ __cold int io_sq_offload_create(struct i
 			return 0;
 
 		if (p->flags & IORING_SETUP_SQ_AFF) {
-			struct cpumask allowed_mask;
+			cpumask_var_t allowed_mask;
 			int cpu = p->sq_thread_cpu;
 
 			ret = -EINVAL;
 			if (cpu >= nr_cpu_ids || !cpu_online(cpu))
 				goto err_sqpoll;
-			cpuset_cpus_allowed(current, &allowed_mask);
-			if (!cpumask_test_cpu(cpu, &allowed_mask))
+			ret = -ENOMEM;
+			if (!alloc_cpumask_var(&allowed_mask, GFP_KERNEL))
 				goto err_sqpoll;
+			ret = -EINVAL;
+			cpuset_cpus_allowed(current, allowed_mask);
+			if (!cpumask_test_cpu(cpu, allowed_mask)) {
+				free_cpumask_var(allowed_mask);
+				goto err_sqpoll;
+			}
+			free_cpumask_var(allowed_mask);
 			sqd->sq_cpu = cpu;
 		} else {
 			sqd->sq_cpu = -1;

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

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

From: Eduard Zingerman <[email protected]>

commit d0a29cdb6ef95d8a175e09ab2d1334271f047e60 upstream.

Suppose log="foo bar buz" and msg->substr="bar".
In such case current match processing logic would update 'log' as
follows: log += strlen(msg->substr); -> log += 3 -> log=" bar". However, the intent behind the 'log' update is to make it point after the successful match, e.g. to make log=" buz" in the example above.

---
 tools/testing/selftests/bpf/test_loader.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -545,7 +545,7 @@ static void validate_msgs(char *log_buf,
 		if (msg->substr) {
 			match = strstr(log, msg->substr);
 			if (match)
-				log += strlen(msg->substr);
+				log = match + strlen(msg->substr);
 		} else {
 			err = regexec(&msg->regex, log, 1, reg_match, 0);
 			if (err == 0) {

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

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

From: Laurent Pinchart <[email protected]>

commit 76be4f5a784533c71afbbb1b8f2963ef9e2ee258 upstream.

Commit 3f1b0e1f2875 (".gitignore update") added *.orig and *.rej patterns to .gitignore in v2.6.23. The commit message didn't give a rationale. Later on, commit 1f5d3a6b6532 ("Remove *.rej pattern from .gitignore") removed the *.rej pattern in v2.6.26, on the rationale that *.rej files indicated something went really wrong and should not be ignored.

The *.rej files are now shown by git status, which helps located conflicts when applying patches and lowers the probability that they will go unnoticed. It is however still easy to overlook the *.orig files which slowly polute the source tree. That's not as big of a deal as not noticing a conflict, but it's still not nice.

Drop the *.orig pattern from .gitignore to avoid this and help keep the source tree clean.

[[email protected]:
I do not have a strong opinion about this. Perhaps some people may have a different opinion.

If you are someone who wants to ignore *.orig, it is likely you would want to do so across all projects. Then, $XDG_CONFIG_HOME/git/ignore would be more suitable for your needs. gitignore(5) suggests, "Patterns which a user wants Git to ignore in all situations generally go into a file specified by core.excludesFile in the user's ~/.gitconfig".

Please note that you cannot do the opposite; if *.orig is ignored by the project's .gitignore, you cannot override the decision because $XDG_CONFIG_HOME/git/ignore has a lower priority.

If *.orig is sitting on the fence, I'd leave it to the users. ]

---
 .gitignore |    1 -
 1 file changed, 1 deletion(-)

@@ -136,7 +136,6 @@ GTAGS
 # id-utils files
 ID
 
-*.orig
 *~
 \#*#
 

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

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

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

commit f68dea13405c94381d08f42dbf0416261622bdad upstream.

When `pcie_failed_link_retrain' has failed to retrain the link by hand it leaves the link speed restricted to 2.5GT/s, which will then affect any device that has been plugged in later on, which may not suffer from the problem that caused the speed restriction to have been attempted. Consequently such a downstream device will suffer from an unnecessary communication throughput limitation and therefore performance loss.

Remove the speed restriction then and revert the Link Control 2 register to its original state if link retraining with the speed restriction in place has failed. Retrain the link again afterwards so as to remove any residual state, waiting on LT rather than DLLLA to avoid an excessive delay and ignoring the result as this training is supposed to fail anyway.

---
 drivers/pci/quirks.c |   11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

@@ -66,7 +66,7 @@
  * apply this erratum workaround to any downstream ports as long as they
  * support Link Active reporting and have the Link Control 2 register.
  * Restrict the speed to 2.5GT/s then with the Target Link Speed field,
- * request a retrain and wait 200ms for the data link to go up.
+ * request a retrain and check the result.
  *
  * If this turns out successful and we know by the Vendor:Device ID it is
  * safe to do so, then lift the restriction, letting the devices negotiate

@@ -74,6 +74,10 @@
  * firmware may have already arranged and lift it with ports that already
  * report their data link being up.
  *
+ * Otherwise revert the speed to the original setting and request a retrain
+ * again to remove any residual state, ignoring the result as it's supposed
+ * to fail anyway.
+ *
  * Return TRUE if the link has been successfully retrained, otherwise FALSE.
  */
 bool pcie_failed_link_retrain(struct pci_dev *dev)

@@ -92,6 +96,8 @@ bool pcie_failed_link_retrain(struct pci
 	pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta);
 	if ((lnksta & (PCI_EXP_LNKSTA_LBMS | PCI_EXP_LNKSTA_DLLLA)) ==
 	    PCI_EXP_LNKSTA_LBMS) {
+		u16 oldlnkctl2 = lnkctl2;
+
 		pci_info(dev, "broken device, retraining non-functional downstream link at 2.5GT/s\n");
 
 		lnkctl2 &= ~PCI_EXP_LNKCTL2_TLS;

@@ -100,6 +106,9 @@ bool pcie_failed_link_retrain(struct pci
 
 		if (pcie_retrain_link(dev, false)) {
 			pci_info(dev, "retraining failed\n");
+			pcie_capability_write_word(dev, PCI_EXP_LNKCTL2,
+						   oldlnkctl2);
+			pcie_retrain_link(dev, true);
 			return false;
 		}
 

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

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

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

commit 8037ac08c2bbb3186f83a5a924f52d1048dbaec5 upstream.

The LBMS bit, where implemented, is set by hardware either in response to the completion of retraining caused by writing 1 to the Retrain Link bit or whenever hardware has changed the link speed or width in attempt to correct unreliable link operation. It is never cleared by hardware other than by software writing 1 to the bit position in the Link Status register and we never do such a write.

We currently have two places, namely apply_bad_link_workaround() and pcie_failed_link_retrain() in drivers/pci/controller/dwc/pcie-tegra194.c and drivers/pci/quirks.c respectively where we check the state of the LBMS bit and neither is interested in the state of the bit resulting from the completion of retraining, both check for a link fault.

And in particular pcie_failed_link_retrain() causes issues consequently, by trying to retrain a link where there's no downstream device anymore and the state of 1 in the LBMS bit has been retained from when there was a device downstream that has since been removed.

Clear the LBMS bit then at the conclusion of pcie_retrain_link(), so that we have a single place that controls it and that our code can track link speed or width changes resulting from unreliable link operation.

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

@@ -4647,7 +4647,15 @@ int pcie_retrain_link(struct pci_dev *pd
 		pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_RL);
 	}
 
-	return pcie_wait_for_link_status(pdev, use_lt, !use_lt);
+	rc = pcie_wait_for_link_status(pdev, use_lt, !use_lt);
+
+	/*
+	 * Clear LBMS after a manual retrain so that the bit can be used
+	 * to track link speed or width changes made by hardware itself
+	 * in attempt to correct unreliable link operation.
+	 */
+	pcie_capability_write_word(pdev, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS);
+	return rc;
 }
 
 /**

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

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

From: Siddharth Vadapalli <[email protected]>

commit 03f84b3baba7836bdfc162c19288d5ce1aa92890 upstream.

Commit da87d35a6e51 ("PCI: dra7xx: Use threaded IRQ handler for "dra7xx-pcie-main" IRQ") switched from devm_request_irq() to devm_request_threaded_irq() for the "dra7xx-pcie-main" interrupt.

Since the primary handler was set to NULL, the "IRQF_ONESHOT" flag should have also been set. Fix this.

---
 drivers/pci/controller/dwc/pci-dra7xx.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -850,7 +850,8 @@ static int dra7xx_pcie_probe(struct plat
 	dra7xx->mode = mode;
 
 	ret = devm_request_threaded_irq(dev, irq, NULL, dra7xx_pcie_irq_handler,
-			       IRQF_SHARED, "dra7xx-pcie-main", dra7xx);
+					IRQF_SHARED | IRQF_ONESHOT,
+					"dra7xx-pcie-main", dra7xx);
 	if (ret) {
 		dev_err(dev, "failed to request irq\n");
 		goto err_gpio;

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

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

From: Frank Li <[email protected]>

commit 5b04d44d5c74e4d8aab1678496b84700b4b343fe upstream.

Fix missing call to phy_power_off() in the error path of imx6_pcie_host_init(). Remove unnecessary check for imx6_pcie->phy as the PHY API already handles NULL pointers.

---
 drivers/pci/controller/dwc/pci-imx6.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

@@ -958,7 +958,7 @@ static int imx6_pcie_host_init(struct dw
 		ret = phy_power_on(imx6_pcie->phy);
 		if (ret) {
 			dev_err(dev, "waiting for PHY ready timeout!\n");
-			goto err_phy_off;
+			goto err_phy_exit;
 		}
 	}
 

@@ -973,8 +973,9 @@ static int imx6_pcie_host_init(struct dw
 	return 0;
 
 err_phy_off:
-	if (imx6_pcie->phy)
-		phy_exit(imx6_pcie->phy);
+	phy_power_off(imx6_pcie->phy);
+err_phy_exit:
+	phy_exit(imx6_pcie->phy);
 err_clk_disable:
 	imx6_pcie_clk_disable(imx6_pcie);
 err_reg_disable:

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

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

From: Richard Zhu <[email protected]>

commit 5214ff221a14cadab1e2ee29499750fd5e884feb upstream.

Add IMX6_PCIE_FLAG_HAS_APP_RESET flag to IMX8MM_EP and IMX8MP_EP drvdata.

This flag was overlooked during code restructuring. It is crucial to release the app-reset from the System Reset Controller before initiating LTSSM to rectify the issue.

---
 drivers/pci/controller/dwc/pci-imx6.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

@@ -1579,7 +1579,8 @@ static const struct imx6_pcie_drvdata dr
 	},
 	[IMX8MM_EP] = {
 		.variant = IMX8MM_EP,
-		.flags = IMX6_PCIE_FLAG_HAS_PHYDRV,
+		.flags = IMX6_PCIE_FLAG_HAS_APP_RESET |
+			 IMX6_PCIE_FLAG_HAS_PHYDRV,
 		.mode = DW_PCIE_EP_TYPE,
 		.gpr = "fsl,imx8mm-iomuxc-gpr",
 		.clk_names = imx8mm_clks,

@@ -1590,7 +1591,8 @@ static const struct imx6_pcie_drvdata dr
 	},
 	[IMX8MP_EP] = {
 		.variant = IMX8MP_EP,
-		.flags = IMX6_PCIE_FLAG_HAS_PHYDRV,
+		.flags = IMX6_PCIE_FLAG_HAS_APP_RESET |
+			 IMX6_PCIE_FLAG_HAS_PHYDRV,
 		.mode = DW_PCIE_EP_TYPE,
 		.gpr = "fsl,imx8mp-iomuxc-gpr",
 		.clk_names = imx8mm_clks,

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

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

From: Richard Zhu <[email protected]>

commit 5cb3aa92c7cf182940ae575c3f450d3708af087c upstream.

Correct occasional MSI triggering failures in i.MX8MP PCIe EP by applying the correct hardware outbound alignment requirement.

The i.MX platform has a restriction about outbound address translation. The pci-epc-mem uses page_size to manage it. Set the correct page_size for i.MX platform to meet the hardware requirement, which is the same as inbound address alignment.

Thus, align it with epc_features::align.

---
 drivers/pci/controller/dwc/pci-imx6.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -1119,6 +1119,8 @@ static int imx6_add_pcie_ep(struct imx6_
 	if (imx6_check_flag(imx6_pcie, IMX6_PCIE_FLAG_SUPPORT_64BIT))
 		dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 
+	ep->page_size = imx6_pcie->drvdata->epc_features->align;
+
 	ret = dw_pcie_ep_init(ep);
 	if (ret) {
 		dev_err(dev, "failed to initialize endpoint\n");

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

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

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

commit 712e49c967064a3a7a5738c6f65ac540a3f6a1df upstream.

Only return successful completion status from pcie_failed_link_retrain() if retraining has actually been done, preventing excessive delays from being triggered at call sites in a hope that communication will finally be established with the downstream device where in fact nothing has been done about the link in question that would justify such a hope.

---
 drivers/pci/quirks.c |   12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

@@ -78,7 +78,8 @@
  * again to remove any residual state, ignoring the result as it's supposed
  * to fail anyway.
  *
- * Return TRUE if the link has been successfully retrained, otherwise FALSE.
+ * Return TRUE if the link has been successfully retrained.  Return FALSE
+ * if retraining was not needed or we attempted a retrain and it failed.
  */
 bool pcie_failed_link_retrain(struct pci_dev *dev)
 {

@@ -87,6 +88,7 @@ bool pcie_failed_link_retrain(struct pci
 		{}
 	};
 	u16 lnksta, lnkctl2;
+	bool ret = false;
 
 	if (!pci_is_pcie(dev) || !pcie_downstream_port(dev) ||
 	    !pcie_cap_has_lnkctl2(dev) || !dev->link_active_reporting)

@@ -104,7 +106,8 @@ bool pcie_failed_link_retrain(struct pci
 		lnkctl2 |= PCI_EXP_LNKCTL2_TLS_2_5GT;
 		pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
 
-		if (pcie_retrain_link(dev, false)) {
+		ret = pcie_retrain_link(dev, false) == 0;
+		if (!ret) {
 			pci_info(dev, "retraining failed\n");
 			pcie_capability_write_word(dev, PCI_EXP_LNKCTL2,
 						   oldlnkctl2);

@@ -126,13 +129,14 @@ bool pcie_failed_link_retrain(struct pci
 		lnkctl2 |= lnkcap & PCI_EXP_LNKCAP_SLS;
 		pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
 
-		if (pcie_retrain_link(dev, false)) {
+		ret = pcie_retrain_link(dev, false) == 0;
+		if (!ret) {
 			pci_info(dev, "retraining failed\n");
 			return false;
 		}
 	}
 
-	return true;
+	return ret;
 }
 
 static ktime_t fixup_debug_start(struct pci_dev *dev,

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

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

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

commit 59100eb248c0b15585affa546c7f6834b30eb5a4 upstream.

Given how the call place in pcie_wait_for_link_delay() got structured now, and that pcie_retrain_link() returns a potentially useful error code, convert pcie_failed_link_retrain() to return an error code rather than a boolean status, fixing handling at the call site mentioned. Update the other call site accordingly.

---
 drivers/pci/pci.c    |    2 +-
 drivers/pci/pci.h    |    6 +++---
 drivers/pci/quirks.c |   20 ++++++++++----------
 3 files changed, 14 insertions(+), 14 deletions(-)

@@ -1295,7 +1295,7 @@ static int pci_dev_wait(struct pci_dev *
 		if (delay > PCI_RESET_WAIT) {
 			if (retrain) {
 				retrain = false;
-				if (pcie_failed_link_retrain(bridge)) {
+				if (pcie_failed_link_retrain(bridge) == 0) {
 					delay = 1;
 					continue;
 				}

@@ -541,7 +541,7 @@ void pci_acs_init(struct pci_dev *dev);
 int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
 int pci_dev_specific_enable_acs(struct pci_dev *dev);
 int pci_dev_specific_disable_acs_redir(struct pci_dev *dev);
-bool pcie_failed_link_retrain(struct pci_dev *dev);
+int pcie_failed_link_retrain(struct pci_dev *dev);
 #else
 static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
 					       u16 acs_flags)

@@ -556,9 +556,9 @@ static inline int pci_dev_specific_disab
 {
 	return -ENOTTY;
 }
-static inline bool pcie_failed_link_retrain(struct pci_dev *dev)
+static inline int pcie_failed_link_retrain(struct pci_dev *dev)
 {
-	return false;
+	return -ENOTTY;
 }
 #endif
 

@@ -78,21 +78,21 @@
  * again to remove any residual state, ignoring the result as it's supposed
  * to fail anyway.
  *
- * Return TRUE if the link has been successfully retrained.  Return FALSE
+ * Return 0 if the link has been successfully retrained.  Return an error
  * if retraining was not needed or we attempted a retrain and it failed.
  */
-bool pcie_failed_link_retrain(struct pci_dev *dev)
+int pcie_failed_link_retrain(struct pci_dev *dev)
 {
 	static const struct pci_device_id ids[] = {
 		{ PCI_VDEVICE(ASMEDIA, 0x2824) }, /* ASMedia ASM2824 */
 		{}
 	};
 	u16 lnksta, lnkctl2;
-	bool ret = false;
+	int ret = -ENOTTY;
 
 	if (!pci_is_pcie(dev) || !pcie_downstream_port(dev) ||
 	    !pcie_cap_has_lnkctl2(dev) || !dev->link_active_reporting)
-		return false;
+		return ret;
 
 	pcie_capability_read_word(dev, PCI_EXP_LNKCTL2, &lnkctl2);
 	pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta);

@@ -106,13 +106,13 @@ bool pcie_failed_link_retrain(struct pci
 		lnkctl2 |= PCI_EXP_LNKCTL2_TLS_2_5GT;
 		pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
 
-		ret = pcie_retrain_link(dev, false) == 0;
-		if (!ret) {
+		ret = pcie_retrain_link(dev, false);
+		if (ret) {
 			pci_info(dev, "retraining failed\n");
 			pcie_capability_write_word(dev, PCI_EXP_LNKCTL2,
 						   oldlnkctl2);
 			pcie_retrain_link(dev, true);
-			return false;
+			return ret;
 		}
 
 		pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta);

@@ -129,10 +129,10 @@ bool pcie_failed_link_retrain(struct pci
 		lnkctl2 |= lnkcap & PCI_EXP_LNKCAP_SLS;
 		pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
 
-		ret = pcie_retrain_link(dev, false) == 0;
-		if (!ret) {
+		ret = pcie_retrain_link(dev, false);
+		if (ret) {
 			pci_info(dev, "retraining failed\n");
-			return false;
+			return ret;
 		}
 	}
 

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

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

From: Sean Anderson <[email protected]>

commit 0199d2f2bd8cd97b310f7ed82a067247d7456029 upstream.

MSGF_LEG_MASK is laid out with INTA in bit 0, INTB in bit 1, INTC in bit 2, and INTD in bit 3. Hardware IRQ numbers start at 0, and we register PCI_NUM_INTX IRQs. So to enable INTA (aka hwirq 0) we should set bit 0. Remove the subtraction of one.

This bug would cause INTx interrupts not to be delivered, as enabling INTB would actually enable INTA, and enabling INTA wouldn't enable anything at all. It is likely that this got overlooked for so long since most PCIe hardware uses MSIs. This fixes the following UBSAN error:

  UBSAN: shift-out-of-bounds in ../drivers/pci/controller/pcie-xilinx-nwl.c:389:11
  shift exponent 18446744073709551615 is too large for 32-bit type 'int'
  CPU: 1 PID: 61 Comm: kworker/u10:1 Not tainted 6.6.20+ #268
  Hardware name: xlnx,zynqmp (DT)
  Workqueue: events_unbound deferred_probe_work_func
  Call trace:
  dump_backtrace (arch/arm64/kernel/stacktrace.c:235)
  show_stack (arch/arm64/kernel/stacktrace.c:242)
  dump_stack_lvl (lib/dump_stack.c:107)
  dump_stack (lib/dump_stack.c:114)
  __ubsan_handle_shift_out_of_bounds (lib/ubsan.c:218 lib/ubsan.c:387)
  nwl_unmask_leg_irq (drivers/pci/controller/pcie-xilinx-nwl.c:389 (discriminator 1))
  irq_enable (kernel/irq/internals.h:234 kernel/irq/chip.c:170 kernel/irq/chip.c:439 kernel/irq/chip.c:432 kernel/irq/chip.c:345)
  __irq_startup (kernel/irq/internals.h:239 kernel/irq/chip.c:180 kernel/irq/chip.c:250)
  irq_startup (kernel/irq/chip.c:270)
  __setup_irq (kernel/irq/manage.c:1800)
  request_threaded_irq (kernel/irq/manage.c:2206)
  pcie_pme_probe (include/linux/interrupt.h:168 drivers/pci/pcie/pme.c:348)

---
 drivers/pci/controller/pcie-xilinx-nwl.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -371,7 +371,7 @@ static void nwl_mask_intx_irq(struct irq
 	u32 mask;
 	u32 val;
 
-	mask = 1 << (data->hwirq - 1);
+	mask = 1 << data->hwirq;
 	raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags);
 	val = nwl_bridge_readl(pcie, MSGF_LEG_MASK);
 	nwl_bridge_writel(pcie, (val & (~mask)), MSGF_LEG_MASK);

@@ -385,7 +385,7 @@ static void nwl_unmask_intx_irq(struct i
 	u32 mask;
 	u32 val;
 
-	mask = 1 << (data->hwirq - 1);
+	mask = 1 << data->hwirq;
 	raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags);
 	val = nwl_bridge_readl(pcie, MSGF_LEG_MASK);
 	nwl_bridge_writel(pcie, (val | mask), MSGF_LEG_MASK);

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

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

From: Siddharth Vadapalli <[email protected]>

commit 4d60f6d4b8fa4d7bad4aeb2b3ee5c10425bc60a4 upstream.

Commit d4c7d1a089d6 ("PCI: dwc: dra7xx: Push request_irq() call to the bottom of probe") moved the IRQ request for "dra7xx-pcie-main" towards the end of dra7xx_pcie_probe().

However, the error handling does not take into account the initialization performed by either dra7xx_add_pcie_port() or dra7xx_add_pcie_ep(), depending on the mode of operation.

Fix the error handling to address this.

---
 drivers/pci/controller/dwc/pci-dra7xx.c |    8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

@@ -854,11 +854,17 @@ static int dra7xx_pcie_probe(struct plat
 					"dra7xx-pcie-main", dra7xx);
 	if (ret) {
 		dev_err(dev, "failed to request irq\n");
-		goto err_gpio;
+		goto err_deinit;
 	}
 
 	return 0;
 
+err_deinit:
+	if (dra7xx->mode == DW_PCIE_RC_TYPE)
+		dw_pcie_host_deinit(&dra7xx->pci->pp);
+	else
+		dw_pcie_ep_deinit(&dra7xx->pci->ep);
+
 err_gpio:
 err_get_sync:
 	pm_runtime_put(dev);

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

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

From: Dmitry Baryshkov <[email protected]>

commit b17155133391d7f6dd18d3fb94a7d492fdec18fa upstream.

The rpm_requests device nodes have the compatible node. As such the rpmsg core uses OF modalias instead of a native rpmsg modalias. Thus if smd-rpm is built as a module, it doesn't get autoloaded for the device.

Revert the commit bcabe1e09135 ("soc: qcom: smd-rpm: Match rpmsg channel instead of compatible")

---
 drivers/soc/qcom/smd-rpm.c |   35 ++++++++++++++++++++++++++---------
 1 file changed, 26 insertions(+), 9 deletions(-)

@@ -196,9 +196,6 @@ static int qcom_smd_rpm_probe(struct rpm
 {
 	struct qcom_smd_rpm *rpm;
 
-	if (!rpdev->dev.of_node)
-		return -EINVAL;
-
 	rpm = devm_kzalloc(&rpdev->dev, sizeof(*rpm), GFP_KERNEL);
 	if (!rpm)
 		return -ENOMEM;

@@ -218,18 +215,38 @@ static void qcom_smd_rpm_remove(struct r
 	of_platform_depopulate(&rpdev->dev);
 }
 
-static const struct rpmsg_device_id qcom_smd_rpm_id_table[] = {
-	{ .name = "rpm_requests", },
-	{ /* sentinel */ }
+static const struct of_device_id qcom_smd_rpm_of_match[] = {
+	{ .compatible = "qcom,rpm-apq8084" },
+	{ .compatible = "qcom,rpm-ipq6018" },
+	{ .compatible = "qcom,rpm-ipq9574" },
+	{ .compatible = "qcom,rpm-msm8226" },
+	{ .compatible = "qcom,rpm-msm8909" },
+	{ .compatible = "qcom,rpm-msm8916" },
+	{ .compatible = "qcom,rpm-msm8936" },
+	{ .compatible = "qcom,rpm-msm8953" },
+	{ .compatible = "qcom,rpm-msm8974" },
+	{ .compatible = "qcom,rpm-msm8976" },
+	{ .compatible = "qcom,rpm-msm8994" },
+	{ .compatible = "qcom,rpm-msm8996" },
+	{ .compatible = "qcom,rpm-msm8998" },
+	{ .compatible = "qcom,rpm-sdm660" },
+	{ .compatible = "qcom,rpm-sm6115" },
+	{ .compatible = "qcom,rpm-sm6125" },
+	{ .compatible = "qcom,rpm-sm6375" },
+	{ .compatible = "qcom,rpm-qcm2290" },
+	{ .compatible = "qcom,rpm-qcs404" },
+	{}
 };
-MODULE_DEVICE_TABLE(rpmsg, qcom_smd_rpm_id_table);
+MODULE_DEVICE_TABLE(of, qcom_smd_rpm_of_match);
 
 static struct rpmsg_driver qcom_smd_rpm_driver = {
 	.probe = qcom_smd_rpm_probe,
 	.remove = qcom_smd_rpm_remove,
 	.callback = qcom_smd_rpm_callback,
-	.id_table = qcom_smd_rpm_id_table,
-	.drv.name = "qcom_smd_rpm",
+	.drv  = {
+		.name  = "qcom_smd_rpm",
+		.of_match_table = qcom_smd_rpm_of_match,
+	},
 };
 
 static int __init qcom_smd_rpm_init(void)