6.11.7-rc1 review

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

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

From: Dan Williams <[email protected]>

commit 101c268bd2f37e965a5468353e62d154db38838e upstream.

In support of investigating an initialization failure report [1], cxl_test was updated to register mock memory-devices after the mock root-port/bus device had been registered. That led to cxl_test crashing with a use-after-free bug with the following signature:

cxl_port_attach_region: cxl region3: cxl_host_bridge.0:port3 decoder3.0 add: mem0:decoder7.0 @ 0 next: cxl_switch_uport.0 nr_eps: 1 nr_targets: 1
cxl_port_attach_region: cxl region3: cxl_host_bridge.0:port3 decoder3.0 add: mem4:decoder14.0 @ 1 next: cxl_switch_uport.0 nr_eps: 2 nr_targets: 1
cxl_port_setup_targets: cxl region3: cxl_switch_uport.0:port6 target[0] = cxl_switch_dport.0 for mem0:decoder7.0 @ 0
1) cxl_port_setup_targets: cxl region3: cxl_switch_uport.0:port6 target[1] = cxl_switch_dport.4 for mem4:decoder14.0 @ 1 [..]
cxld_unregister: cxl decoder14.0:
cxl_region_decode_reset: cxl_region region3:
mock_decoder_reset: cxl_port port3: decoder3.0 reset
2) mock_decoder_reset: cxl_port port3: decoder3.0: out of order reset, expected decoder3.1
cxl_endpoint_decoder_release: cxl decoder14.0:
[..]
cxld_unregister: cxl decoder7.0:
3) cxl_region_decode_reset: cxl_region region3:

    Oops: general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6bc3: 0000 [#1] PREEMPT SMP PTI
    [..]
    RIP: 0010:to_cxl_port+0x8/0x60 [cxl_core]
    [..]
    Call Trace:
     <TASK>
     cxl_region_decode_reset+0x69/0x190 [cxl_core]
     cxl_region_detach+0xe8/0x210 [cxl_core]
     cxl_decoder_kill_region+0x27/0x40 [cxl_core]
     cxld_unregister+0x5d/0x60 [cxl_core]

At 1) a region has been established with 2 endpoint decoders (7.0 and 14.0). Those endpoints share a common switch-decoder in the topology (3.0). At teardown, 2), decoder14.0 is the first to be removed and hits the "out of order reset case" in the switch decoder. The effect though is that region3 cleanup is aborted leaving it in-tact and referencing decoder14.0. At 3) the second attempt to teardown region3 trips over the stale decoder14.0 object which has long since been deleted.

The fix here is to recognize that the CXL specification places no mandate on in-order shutdown of switch-decoders, the driver enforces in-order allocation, and hardware enforces in-order commit. So, rather than fail and leave objects dangling, always remove them.

In support of making cxl_region_decode_reset() always succeed, cxl_region_invalidate_memregion() failures are turned into warnings. Crashing the kernel is ok there since system integrity is at risk if caches cannot be managed around physical address mutation events like CXL region destruction.

A new device_for_each_child_reverse_from() is added to cleanup port->commit_end after all dependent decoders have been disabled. In other words if decoders are allocated 0->1->2 and disabled 1->2->0 then port->commit_end only decrements from 2 after 2 has been disabled, and it decrements all the way to zero since 1 was disabled previously.

---
 drivers/base/core.c          |   35 ++++++++++++++++++++++++++++++
 drivers/cxl/core/hdm.c       |   50 ++++++++++++++++++++++++++++++++++++-------
 drivers/cxl/core/region.c    |   48 +++++++++++------------------------------
 drivers/cxl/cxl.h            |    3 +-
 include/linux/device.h       |    3 ++
 tools/testing/cxl/test/cxl.c |   14 ++++--------
 6 files changed, 100 insertions(+), 53 deletions(-)

@@ -4042,6 +4042,41 @@ int device_for_each_child_reverse(struct
 EXPORT_SYMBOL_GPL(device_for_each_child_reverse);
 
 /**
+ * device_for_each_child_reverse_from - device child iterator in reversed order.
+ * @parent: parent struct device.
+ * @from: optional starting point in child list
+ * @fn: function to be called for each device.
+ * @data: data for the callback.
+ *
+ * Iterate over @parent's child devices, starting at @from, and call @fn
+ * for each, passing it @data. This helper is identical to
+ * device_for_each_child_reverse() when @from is NULL.
+ *
+ * @fn is checked each iteration. If it returns anything other than 0,
+ * iteration stop and that value is returned to the caller of
+ * device_for_each_child_reverse_from();
+ */
+int device_for_each_child_reverse_from(struct device *parent,
+				       struct device *from, const void *data,
+				       int (*fn)(struct device *, const void *))
+{
+	struct klist_iter i;
+	struct device *child;
+	int error = 0;
+
+	if (!parent->p)
+		return 0;
+
+	klist_iter_init_node(&parent->p->klist_children, &i,
+			     (from ? &from->p->knode_parent : NULL));
+	while ((child = prev_device(&i)) && !error)
+		error = fn(child, data);
+	klist_iter_exit(&i);
+	return error;
+}
+EXPORT_SYMBOL_GPL(device_for_each_child_reverse_from);
+
+/**
  * device_find_child - device iterator for locating a particular device.
  * @parent: parent struct device
  * @match: Callback function to check device

@@ -359,7 +359,7 @@ struct cxl_decoder {
 	struct cxl_region *region;
 	unsigned long flags;
 	int (*commit)(struct cxl_decoder *cxld);
-	int (*reset)(struct cxl_decoder *cxld);
+	void (*reset)(struct cxl_decoder *cxld);
 };
 
 /*

@@ -730,6 +730,7 @@ static inline bool is_cxl_root(struct cx
 int cxl_num_decoders_committed(struct cxl_port *port);
 bool is_cxl_port(const struct device *dev);
 struct cxl_port *to_cxl_port(const struct device *dev);
+void cxl_port_commit_reap(struct cxl_decoder *cxld);
 struct pci_bus;
 int devm_cxl_register_pci_bus(struct device *host, struct device *uport_dev,
 			      struct pci_bus *bus);

@@ -1073,6 +1073,9 @@ int device_for_each_child(struct device
 			  int (*fn)(struct device *dev, void *data));
 int device_for_each_child_reverse(struct device *dev, void *data,
 				  int (*fn)(struct device *dev, void *data));
+int device_for_each_child_reverse_from(struct device *parent,
+				       struct device *from, const void *data,
+				       int (*fn)(struct device *, const void *));
 struct device *device_find_child(struct device *dev, void *data,
 				 int (*match)(struct device *dev, void *data));
 struct device *device_find_child_by_name(struct device *parent,

@@ -693,26 +693,22 @@ static int mock_decoder_commit(struct cx
 	return 0;
 }
 
-static int mock_decoder_reset(struct cxl_decoder *cxld)
+static void mock_decoder_reset(struct cxl_decoder *cxld)
 {
 	struct cxl_port *port = to_cxl_port(cxld->dev.parent);
 	int id = cxld->id;
 
 	if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)
-		return 0;
+		return;
 
 	dev_dbg(&port->dev, "%s reset\n", dev_name(&cxld->dev));
-	if (port->commit_end != id) {
+	if (port->commit_end == id)
+		cxl_port_commit_reap(cxld);
+	else
 		dev_dbg(&port->dev,
 			"%s: out of order reset, expected decoder%d.%d\n",
 			dev_name(&cxld->dev), port->id, port->commit_end);
-		return -EBUSY;
-	}
-
-	port->commit_end--;
 	cxld->flags &= ~CXL_DECODER_F_ENABLE;
-
-	return 0;
 }
 
 static void default_mock_decoder(struct cxl_decoder *cxld)

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

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

From: Dan Williams <[email protected]>

commit 6575b268157f37929948a8d1f3bafb3d7c055bc1 upstream.

When the CXL subsystem is built-in the module init order is determined by Makefile order. That order violates expectations. The expectation is that cxl_acpi and cxl_mem can race to attach. If cxl_acpi wins the race, cxl_mem will find the enabled CXL root ports it needs. If cxl_acpi loses the race it will retrigger cxl_mem to attach via cxl_bus_rescan(). That flow only works if cxl_acpi can assume ports are enabled immediately upon cxl_acpi_probe() return. That in turn can only happen in the CONFIG_CXL_ACPI=y case if the cxl_port driver is registered before cxl_acpi_probe() runs.

Fix up the order to prevent initialization failures. Ensure that cxl_port is built-in when cxl_acpi is also built-in, arrange for Makefile order to resolve the subsys_initcall() order of cxl_port and cxl_acpi, and arrange for Makefile order to resolve the device_initcall() (module_init()) order of the remaining objects.

As for what contributed to this not being found earlier, the CXL regression environment, cxl_test, builds all CXL functionality as a module to allow to symbol mocking and other dynamic reload tests. As a result there is no regression coverage for the built-in case.

---
 drivers/cxl/Kconfig  |    1 +
 drivers/cxl/Makefile |   20 ++++++++++++++------
 drivers/cxl/port.c   |   17 ++++++++++++++++-
 3 files changed, 31 insertions(+), 7 deletions(-)

@@ -60,6 +60,7 @@ config CXL_ACPI
 	default CXL_BUS
 	select ACPI_TABLE_LIB
 	select ACPI_HMAT
+	select CXL_PORT
 	help
 	  Enable support for host managed device memory (HDM) resources
 	  published by a platform's ACPI CXL memory layout description.  See

@@ -1,13 +1,21 @@
 # SPDX-License-Identifier: GPL-2.0
+
+# Order is important here for the built-in case:
+# - 'core' first for fundamental init
+# - 'port' before platform root drivers like 'acpi' so that CXL-root ports
+#   are immediately enabled
+# - 'mem' and 'pmem' before endpoint drivers so that memdevs are
+#   immediately enabled
+# - 'pci' last, also mirrors the hardware enumeration hierarchy
 obj-y += core/
-obj-$(CONFIG_CXL_PCI) += cxl_pci.o
-obj-$(CONFIG_CXL_MEM) += cxl_mem.o
+obj-$(CONFIG_CXL_PORT) += cxl_port.o
 obj-$(CONFIG_CXL_ACPI) += cxl_acpi.o
 obj-$(CONFIG_CXL_PMEM) += cxl_pmem.o
-obj-$(CONFIG_CXL_PORT) += cxl_port.o
+obj-$(CONFIG_CXL_MEM) += cxl_mem.o
+obj-$(CONFIG_CXL_PCI) += cxl_pci.o
 
-cxl_mem-y := mem.o
-cxl_pci-y := pci.o
+cxl_port-y := port.o
 cxl_acpi-y := acpi.o
 cxl_pmem-y := pmem.o security.o
-cxl_port-y := port.o
+cxl_mem-y := mem.o
+cxl_pci-y := pci.o

@@ -208,7 +208,22 @@ static struct cxl_driver cxl_port_driver
 	},
 };
 
-module_cxl_driver(cxl_port_driver);
+static int __init cxl_port_init(void)
+{
+	return cxl_driver_register(&cxl_port_driver);
+}
+/*
+ * Be ready to immediately enable ports emitted by the platform CXL root
+ * (e.g. cxl_acpi) when CONFIG_CXL_PORT=y.
+ */
+subsys_initcall(cxl_port_init);
+
+static void __exit cxl_port_exit(void)
+{
+	cxl_driver_unregister(&cxl_port_driver);
+}
+module_exit(cxl_port_exit);
+
 MODULE_DESCRIPTION("CXL: Port enumeration and services");
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS(CXL);

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

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

From: Ben Chuang <[email protected]>

commit 8c68b5656e55e9324875881f1000eb4ee3603a87 upstream.

On sdhci_gl9767_set_clock(), the vendor header space(VHS) is read-only after calling gl9767_disable_ssc_pll() and gl9767_set_ssc_pll_205mhz(). So the low power negotiation mode cannot be enabled again. Introduce gl9767_set_low_power_negotiation() function to fix it.

The explanation process is as below.

static void sdhci_gl9767_set_clock()

{
	...
        gl9767_vhs_write();
        ...
	value |= PCIE_GLI_9767_CFG_LOW_PWR_OFF;
        pci_write_config_dword(pdev, PCIE_GLI_9767_CFG, value); <--- (a)

        gl9767_disable_ssc_pll(); <--- (b)
        sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL);

        if (clock == 0)
                return;  <-- (I)

	...
        if (clock == 200000000 && ios->timing == MMC_TIMING_UHS_SDR104) {
		...
                gl9767_set_ssc_pll_205mhz(); <--- (c)
        }
	...
	value &= ~PCIE_GLI_9767_CFG_LOW_PWR_OFF;
        pci_write_config_dword(pdev, PCIE_GLI_9767_CFG, value); <-- (II)
        gl9767_vhs_read();
}

(a) disable low power negotiation mode. When return on (I), the low power mode is disabled. After (b) and (c), VHS is read-only, the low power mode cannot be enabled on (II).

Message-ID: <[email protected]>

---
 drivers/mmc/host/sdhci-pci-gli.c |   35 +++++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 14 deletions(-)

@@ -892,28 +892,40 @@ static void gl9767_disable_ssc_pll(struc
 	gl9767_vhs_read(pdev);
 }
 
+static void gl9767_set_low_power_negotiation(struct pci_dev *pdev, bool enable)
+{
+	u32 value;
+
+	gl9767_vhs_write(pdev);
+
+	pci_read_config_dword(pdev, PCIE_GLI_9767_CFG, &value);
+	if (enable)
+		value &= ~PCIE_GLI_9767_CFG_LOW_PWR_OFF;
+	else
+		value |= PCIE_GLI_9767_CFG_LOW_PWR_OFF;
+	pci_write_config_dword(pdev, PCIE_GLI_9767_CFG, value);
+
+	gl9767_vhs_read(pdev);
+}
+
 static void sdhci_gl9767_set_clock(struct sdhci_host *host, unsigned int clock)
 {
 	struct sdhci_pci_slot *slot = sdhci_priv(host);
 	struct mmc_ios *ios = &host->mmc->ios;
 	struct pci_dev *pdev;
-	u32 value;
 	u16 clk;
 
 	pdev = slot->chip->pdev;
 	host->mmc->actual_clock = 0;
 
-	gl9767_vhs_write(pdev);
-
-	pci_read_config_dword(pdev, PCIE_GLI_9767_CFG, &value);
-	value |= PCIE_GLI_9767_CFG_LOW_PWR_OFF;
-	pci_write_config_dword(pdev, PCIE_GLI_9767_CFG, value);
-
+	gl9767_set_low_power_negotiation(pdev, false);
 	gl9767_disable_ssc_pll(pdev);
 	sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL);
 
-	if (clock == 0)
+	if (clock == 0) {
+		gl9767_set_low_power_negotiation(pdev, true);
 		return;
+	}
 
 	clk = sdhci_calc_clk(host, clock, &host->mmc->actual_clock);
 	if (clock == 200000000 && ios->timing == MMC_TIMING_UHS_SDR104) {

@@ -922,12 +934,7 @@ static void sdhci_gl9767_set_clock(struc
 	}
 
 	sdhci_enable_clk(host, clk);
-
-	pci_read_config_dword(pdev, PCIE_GLI_9767_CFG, &value);
-	value &= ~PCIE_GLI_9767_CFG_LOW_PWR_OFF;
-	pci_write_config_dword(pdev, PCIE_GLI_9767_CFG, value);
-
-	gl9767_vhs_read(pdev);
+	gl9767_set_low_power_negotiation(pdev, true);
 }
 
 static void gli_set_9767(struct sdhci_host *host)

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

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

From: Ben Chuang <[email protected]>

commit c4dedaaeb3f78d3718e9c1b1e4d972a6b99073cd upstream.

When starting the SD Express process, the low power negotiation mode will be disabled, so we need to re-enable it after switching back to SD mode.

Message-ID: <[email protected]>

---
 drivers/mmc/host/sdhci-pci-gli.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -1068,6 +1068,9 @@ static int gl9767_init_sd_express(struct
 		sdhci_writew(host, value, SDHCI_CLOCK_CONTROL);
 	}
 
+	pci_read_config_dword(pdev, PCIE_GLI_9767_CFG, &value);
+	value &= ~PCIE_GLI_9767_CFG_LOW_PWR_OFF;
+	pci_write_config_dword(pdev, PCIE_GLI_9767_CFG, value);
 	gl9767_vhs_read(pdev);
 
 	return 0;

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

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

From: Xinyu Zhang <[email protected]>

[ Upstream commit 2ff949441802a8d076d9013c7761f63e8ae5a9bd ]

blk_rq_map_user_bvec contains a check bytes + bv->bv_len > nr_iter which causes unnecessary failures in NVMe passthrough I/O, reproducible as follows:

- register a 2 page, page-aligned buffer against a ring
- use that buffer to do a 1 page io_uring NVMe passthrough read

The second (i = 1) iteration of the loop in blk_rq_map_user_bvec will then have nr_iter == 1 page, bytes == 1 page, bv->bv_len == 1 page, so the check bytes + bv->bv_len > nr_iter will succeed, causing the I/O to fail. This failure is unnecessary, as when the check succeeds, it means we've checked the entire buffer that will be used by the request - i.e. blk_rq_map_user_bvec should complete successfully. Therefore, terminate the loop early and return successfully when the check bytes + bv->bv_len

While we're at it, also remove the check that all segments in the bvec are single-page. While this seems to be true for all users of the function, it doesn't appear to be required anywhere downstream.

---
 block/blk-map.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

index 0e1167b239342..6ef2ec1f7d78b 100644
@@ -600,9 +600,7 @@ static int blk_rq_map_user_bvec(struct request *rq, const struct iov_iter *iter)
 		if (nsegs >= nr_segs || bytes > UINT_MAX - bv->bv_len)
 			goto put_bio;
 		if (bytes + bv->bv_len > nr_iter)
-			goto put_bio;
-		if (bv->bv_offset + bv->bv_len > PAGE_SIZE)
-			goto put_bio;
+			break;
 
 		nsegs++;
 		bytes += bv->bv_len;

2.43.0

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

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

From: Chen Ridong <[email protected]>

[ Upstream commit 117932eea99b729ee5d12783601a4f7f5fd58a23 ]

A hung_task problem shown below was found:

INFO: task kworker/0:0:8 blocked for more than 327 seconds.
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
Workqueue: events cgroup_bpf_release
Call Trace:
 <TASK>
 __schedule+0x5a2/0x2050
 ? find_held_lock+0x33/0x100
 ? wq_worker_sleeping+0x9e/0xe0
 schedule+0x9f/0x180
 schedule_preempt_disabled+0x25/0x50
 __mutex_lock+0x512/0x740
 ? cgroup_bpf_release+0x1e/0x4d0
 ? cgroup_bpf_release+0xcf/0x4d0
 ? process_scheduled_works+0x161/0x8a0
 ? cgroup_bpf_release+0x1e/0x4d0
 ? mutex_lock_nested+0x2b/0x40
 ? __pfx_delay_tsc+0x10/0x10
 mutex_lock_nested+0x2b/0x40
 cgroup_bpf_release+0xcf/0x4d0
 ? process_scheduled_works+0x161/0x8a0
 ? trace_event_raw_event_workqueue_execute_start+0x64/0xd0
 ? process_scheduled_works+0x161/0x8a0
 process_scheduled_works+0x23a/0x8a0
 worker_thread+0x231/0x5b0
 ? __pfx_worker_thread+0x10/0x10
 kthread+0x14d/0x1c0
 ? __pfx_kthread+0x10/0x10
 ret_from_fork+0x59/0x70
 ? __pfx_kthread+0x10/0x10
 ret_from_fork_asm+0x1b/0x30
 </TASK>

This issue can be reproduced by the following pressuse test:
1. A large number of cpuset cgroups are deleted.
2. Set cpu on and off repeatly.
3. Set watchdog_thresh repeatly.
The scripts can be obtained at LINK mentioned above the signature.

The reason for this issue is cgroup_mutex and cpu_hotplug_lock are acquired in different tasks, which may lead to deadlock.
It can lead to a deadlock through the following steps:
1. A large number of cpusets are deleted asynchronously, which puts a large number of cgroup_bpf_release works into system_wq. The max_active of system_wq is WQ_DFL_ACTIVE(256). Consequently, all active works are cgroup_bpf_release works, and many cgroup_bpf_release works will be put into inactive queue. As illustrated in the diagram, there are 256 (in the acvtive queue) + n (in the inactive queue) works.
2. Setting watchdog_thresh will hold cpu_hotplug_lock.read and put smp_call_on_cpu work into system_wq. However step 1 has already filled system_wq, 'sscs.work' is put into inactive queue. 'sscs.work' has to wait until the works that were put into the inacvtive queue earlier have executed (n cgroup_bpf_release), so it will be blocked for a while.
3. Cpu offline requires cpu_hotplug_lock.write, which is blocked by step 2.
4. Cpusets that were deleted at step 1 put cgroup_release works into cgroup_destroy_wq. They are competing to get cgroup_mutex all the time. When cgroup_metux is acqured by work at css_killed_work_fn, it will call cpuset_css_offline, which needs to acqure cpu_hotplug_lock.read. However, cpuset_css_offline will be blocked for step 3.
5. At this moment, there are 256 works in active queue that are cgroup_bpf_release, they are attempting to acquire cgroup_mutex, and as a result, all of them are blocked. Consequently, sscs.work can not be executed. Ultimately, this situation leads to four processes being blocked, forming a deadlock.

system_wq(step1) WatchDog(step2) cpu offline(step3) cgroup_destroy_wq(step4)
...
2000+ cgroups deleted asyn
256 actives + n inactives
__lockup_detector_reconfigure P(cpu_hotplug_lock.read) put sscs.work into system_wq
256 + n + 1(sscs.work)
sscs.work wait to be executed

				warting sscs.work finish
								percpu_down_write
								P(cpu_hotplug_lock.write)
								...blocking...
											css_killed_work_fn
											P(cgroup_mutex)
											cpuset_css_offline
											P(cpu_hotplug_lock.read)
											...blocking...

256 cgroup_bpf_release
mutex_lock(&cgroup_mutex);
..blocking...

To fix the problem, place cgroup_bpf_release works on a dedicated workqueue which can break the loop and solve the problem. System wqs are for misc things which shouldn't create a large number of concurrent work items. If something is going to generate >WQ_DFL_ACTIVE(256) concurrent work items, it should use its own dedicated workqueue.

---
 kernel/bpf/cgroup.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

index 8ba73042a2395..479a2ea5d9af6 100644
@@ -24,6 +24,23 @@
 DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_CGROUP_BPF_ATTACH_TYPE);
 EXPORT_SYMBOL(cgroup_bpf_enabled_key);
 
+/*
+ * cgroup bpf destruction makes heavy use of work items and there can be a lot
+ * of concurrent destructions.  Use a separate workqueue so that cgroup bpf
+ * destruction work items don't end up filling up max_active of system_wq
+ * which may lead to deadlock.
+ */
+static struct workqueue_struct *cgroup_bpf_destroy_wq;
+
+static int __init cgroup_bpf_wq_init(void)
+{
+	cgroup_bpf_destroy_wq = alloc_workqueue("cgroup_bpf_destroy", 0, 1);
+	if (!cgroup_bpf_destroy_wq)
+		panic("Failed to alloc workqueue for cgroup bpf destroy.\n");
+	return 0;
+}
+core_initcall(cgroup_bpf_wq_init);
+
 /* __always_inline is necessary to prevent indirect call through run_prog
  * function pointer.
  */

@@ -334,7 +351,7 @@ static void cgroup_bpf_release_fn(struct percpu_ref *ref)
 	struct cgroup *cgrp = container_of(ref, struct cgroup, bpf.refcnt);
 
 	INIT_WORK(&cgrp->bpf.release_work, cgroup_bpf_release);
-	queue_work(system_wq, &cgrp->bpf.release_work);
+	queue_work(cgroup_bpf_destroy_wq, &cgrp->bpf.release_work);
 }
 
 /* Get underlying bpf_prog of bpf_prog_list entry, regardless if it's through

2.43.0

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

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

From: Richard Zhu <[email protected]>

[ Upstream commit f89263b69731e0144d275fff777ee0dd92069200 ]

When enable initcall_debug together with higher debug level below. CONFIG_CONSOLE_LOGLEVEL_DEFAULT=9 CONFIG_CONSOLE_LOGLEVEL_QUIET=9 CONFIG_MESSAGE_LOGLEVEL_DEFAULT=7

The initialization of i.MX8MP PCIe PHY might be timeout failed randomly. To fix this issue, adjust the sequence of the resets refer to the power up sequence listed below.

i.MX8MP PCIe PHY power up sequence:

                          /---------------------------------------------
1.8v supply     ---------/
                    /---------------------------------------------------

0.8v supply ---/

---\ /--------------------------------------------------
X REFCLK Valid
Reference Clock ---/ \--------------------------------------------------

                             -------------------------------------------
                             |
i_init_restn    --------------
                                    ------------------------------------
                                    |
i_cmn_rstn      ---------------------
                                         -------------------------------
                                         |

o_pll_lock_done --------------------------

Logs:

imx6q-pcie 33800000.pcie: host bridge /soc@0/pcie@33800000 ranges:
imx6q-pcie 33800000.pcie:       IO 0x001ff80000..0x001ff8ffff -> 0x0000000000
imx6q-pcie 33800000.pcie:      MEM 0x0018000000..0x001fefffff -> 0x0018000000

probe of clk_imx8mp_audiomix.reset.0 returned 0 after 1052 usecs
probe of 30e20000.clock-controller returned 0 after 32971 usecs
phy phy-32f00000.pcie-phy.4: phy poweron failed --> -110
probe of 30e10000.dma-controller returned 0 after 10235 usecs
imx6q-pcie 33800000.pcie: waiting for PHY ready timeout!
dwhdmi-imx 32fd8000.hdmi: Detected HDMI TX controller v2.13a with HDCP (samsung_dw_hdmi_phy2) imx6q-pcie 33800000.pcie: probe with driver imx6q-pcie failed with error -110

v2 changes:
- Rebase to latest fixes branch of linux-phy git repo.
- Richard's environment have problem and can't sent out patch. So I help post this fix patch.

---
 drivers/phy/freescale/phy-fsl-imx8m-pcie.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

index 11fcb1867118c..e98361dcdeadf 100644
@@ -141,11 +141,6 @@ static int imx8_pcie_phy_power_on(struct phy *phy)
 			   IMX8MM_GPR_PCIE_REF_CLK_PLL);
 	usleep_range(100, 200);
 
-	/* Do the PHY common block reset */
-	regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14,
-			   IMX8MM_GPR_PCIE_CMN_RST,
-			   IMX8MM_GPR_PCIE_CMN_RST);
-
 	switch (imx8_phy->drvdata->variant) {
 	case IMX8MP:
 		reset_control_deassert(imx8_phy->perst);

@@ -156,6 +151,11 @@ static int imx8_pcie_phy_power_on(struct phy *phy)
 		break;
 	}
 
+	/* Do the PHY common block reset */
+	regmap_update_bits(imx8_phy->iomuxc_gpr, IOMUXC_GPR14,
+			   IMX8MM_GPR_PCIE_CMN_RST,
+			   IMX8MM_GPR_PCIE_CMN_RST);
+
 	/* Polling to check the phy is ready or not. */
 	ret = readl_poll_timeout(imx8_phy->base + IMX8MM_PCIE_PHY_CMN_REG075,
 				 val, val == ANA_PLL_DONE, 10, 20000);

2.43.0

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

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

From: Qu Wenruo <[email protected]>

[ Upstream commit 9ca0e58cb752b09816f56f7a3147a39773d5e831 ]

There are only two differences between the two functions:

- btrfs_orig_bbio_end_io() does extra error propagation This is mostly to allow tolerance for write errors.

- btrfs_orig_bbio_end_io() does extra pending_ios check This check can handle both the original bio, or the cloned one. (All accounting happens in the original one).

This makes btrfs_orig_bbio_end_io() a much safer call. In fact we already had a double freeing error due to usage of btrfs_bio_end_io() in the error path of btrfs_submit_chunk().

So just move the whole content of btrfs_orig_bbio_end_io() into btrfs_bio_end_io().

For normal paths this brings no change, because they are already calling btrfs_orig_bbio_end_io() in the first place.

For error paths (not only inside bio.c but also external callers), this change will introduce extra checks, especially for external callers, as they will error out without submitting the btrfs bio.

But considering it's already in the error path, such slower but much safer checks are still an overall win.

Stable-dep-of: d48e1dea3931 ("btrfs: fix error propagation of split bios")

---
 fs/btrfs/bio.c | 29 +++++++++++------------------
 1 file changed, 11 insertions(+), 18 deletions(-)

index b4e31ae17cd95..e93d376796a28 100644
@@ -120,12 +120,6 @@ static void __btrfs_bio_end_io(struct btrfs_bio *bbio)
 	}
 }
 
-void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
-{
-	bbio->bio.bi_status = status;
-	__btrfs_bio_end_io(bbio);
-}
-
 static void btrfs_orig_write_end_io(struct bio *bio);
 
 static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio,

@@ -147,8 +141,9 @@ static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio,
 	}
 }
 
-static void btrfs_orig_bbio_end_io(struct btrfs_bio *bbio)
+void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
 {
+	bbio->bio.bi_status = status;
 	if (bbio->bio.bi_pool == &btrfs_clone_bioset) {
 		struct btrfs_bio *orig_bbio = bbio->private;
 

@@ -179,7 +174,7 @@ static int prev_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
 static void btrfs_repair_done(struct btrfs_failed_bio *fbio)
 {
 	if (atomic_dec_and_test(&fbio->repair_count)) {
-		btrfs_orig_bbio_end_io(fbio->bbio);
+		btrfs_bio_end_io(fbio->bbio, fbio->bbio->bio.bi_status);
 		mempool_free(fbio, &btrfs_failed_bio_pool);
 	}
 }

@@ -326,7 +321,7 @@ static void btrfs_check_read_bio(struct btrfs_bio *bbio, struct btrfs_device *de
 	if (fbio)
 		btrfs_repair_done(fbio);
 	else
-		btrfs_orig_bbio_end_io(bbio);
+		btrfs_bio_end_io(bbio, bbio->bio.bi_status);
 }
 
 static void btrfs_log_dev_io_error(struct bio *bio, struct btrfs_device *dev)

@@ -360,7 +355,7 @@ static void btrfs_end_bio_work(struct work_struct *work)
 	if (is_data_bbio(bbio))
 		btrfs_check_read_bio(bbio, bbio->bio.bi_private);
 	else
-		btrfs_orig_bbio_end_io(bbio);
+		btrfs_bio_end_io(bbio, bbio->bio.bi_status);
 }
 
 static void btrfs_simple_end_io(struct bio *bio)

@@ -380,7 +375,7 @@ static void btrfs_simple_end_io(struct bio *bio)
 	} else {
 		if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status)
 			btrfs_record_physical_zoned(bbio);
-		btrfs_orig_bbio_end_io(bbio);
+		btrfs_bio_end_io(bbio, bbio->bio.bi_status);
 	}
 }
 

@@ -394,7 +389,7 @@ static void btrfs_raid56_end_io(struct bio *bio)
 	if (bio_op(bio) == REQ_OP_READ && is_data_bbio(bbio))
 		btrfs_check_read_bio(bbio, NULL);
 	else
-		btrfs_orig_bbio_end_io(bbio);
+		btrfs_bio_end_io(bbio, bbio->bio.bi_status);
 
 	btrfs_put_bioc(bioc);
 }

@@ -424,7 +419,7 @@ static void btrfs_orig_write_end_io(struct bio *bio)
 	if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status)
 		stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
 
-	btrfs_orig_bbio_end_io(bbio);
+	btrfs_bio_end_io(bbio, bbio->bio.bi_status);
 	btrfs_put_bioc(bioc);
 }
 

@@ -593,7 +588,7 @@ static void run_one_async_done(struct btrfs_work *work, bool do_free)
 
 	/* If an error occurred we just want to clean up the bio and move on. */
 	if (bio->bi_status) {
-		btrfs_orig_bbio_end_io(async->bbio);
+		btrfs_bio_end_io(async->bbio, async->bbio->bio.bi_status);
 		return;
 	}
 

@@ -765,11 +760,9 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
 		ASSERT(bbio->bio.bi_pool == &btrfs_clone_bioset);
 		ASSERT(remaining);
 
-		remaining->bio.bi_status = ret;
-		btrfs_orig_bbio_end_io(remaining);
+		btrfs_bio_end_io(remaining, ret);
 	}
-	bbio->bio.bi_status = ret;
-	btrfs_orig_bbio_end_io(bbio);
+	btrfs_bio_end_io(bbio, ret);
 	/* Do not submit another chunk */
 	return true;
 }

2.43.0

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

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

From: Naohiro Aota <[email protected]>

[ Upstream commit d48e1dea3931de64c26717adc2b89743c7ab6594 ]

The purpose of btrfs_bbio_propagate_error() shall be propagating an error of split bio to its original btrfs_bio, and tell the error to the upper layer. However, it's not working well on some cases.

* Case 1. Immediate (or quick) end_bio with an error

When btrfs sends btrfs_bio to mirrored devices, btrfs calls btrfs_bio_end_io() when all the mirroring bios are completed. If that btrfs_bio was split, it is from btrfs_clone_bioset and its end_io function is btrfs_orig_write_end_io. For this case, btrfs_bbio_propagate_error() accesses the orig_bbio's bio context to increase the error count.

That works well in most cases. However, if the end_io is called enough fast, orig_bbio's (remaining part after split) bio context may not be properly set at that time. Since the bio context is set when the orig_bbio (the last btrfs_bio) is sent to devices, that might be too late for earlier split btrfs_bio's completion. That will result in NULL pointer dereference.

That bug is easily reproducible by running btrfs/146 on zoned devices [1] and it shows the following trace.

[1] You need raid-stripe-tree feature as it create "-d raid0 -m raid1" FS.

  BUG: kernel NULL pointer dereference, address: 0000000000000020
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: Oops: 0000 [#1] PREEMPT SMP PTI
  CPU: 1 UID: 0 PID: 13 Comm: kworker/u32:1 Not tainted 6.11.0-rc7-BTRFS-ZNS+ #474
  Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  Workqueue: writeback wb_workfn (flush-btrfs-5)
  RIP: 0010:btrfs_bio_end_io+0xae/0xc0 [btrfs]
  BTRFS error (device dm-0): bdev /dev/mapper/error-test errs: wr 2, rd 0, flush 0, corrupt 0, gen 0
  RSP: 0018:ffffc9000006f248 EFLAGS: 00010246
  RAX: 0000000000000000 RBX: ffff888005a7f080 RCX: ffffc9000006f1dc
  RDX: 0000000000000000 RSI: 000000000000000a RDI: ffff888005a7f080
  RBP: ffff888011dfc540 R08: 0000000000000000 R09: 0000000000000001
  R10: ffffffff82e508e0 R11: 0000000000000005 R12: ffff88800ddfbe58
  R13: ffff888005a7f080 R14: ffff888005a7f158 R15: ffff888005a7f158
  FS:  0000000000000000(0000) GS:ffff88803ea80000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000000000000020 CR3: 0000000002e22006 CR4: 0000000000370ef0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   <TASK>
   ? __die_body.cold+0x19/0x26
   ? page_fault_oops+0x13e/0x2b0
   ? _printk+0x58/0x73
   ? do_user_addr_fault+0x5f/0x750
   ? exc_page_fault+0x76/0x240
   ? asm_exc_page_fault+0x22/0x30
   ? btrfs_bio_end_io+0xae/0xc0 [btrfs]
   ? btrfs_log_dev_io_error+0x7f/0x90 [btrfs]
   btrfs_orig_write_end_io+0x51/0x90 [btrfs]
   dm_submit_bio+0x5c2/0xa50 [dm_mod]
   ? find_held_lock+0x2b/0x80
   ? blk_try_enter_queue+0x90/0x1e0
   __submit_bio+0xe0/0x130
   ? ktime_get+0x10a/0x160
   ? lockdep_hardirqs_on+0x74/0x100
   submit_bio_noacct_nocheck+0x199/0x410
   btrfs_submit_bio+0x7d/0x150 [btrfs]
   btrfs_submit_chunk+0x1a1/0x6d0 [btrfs]
   ? lockdep_hardirqs_on+0x74/0x100
   ? __folio_start_writeback+0x10/0x2c0
   btrfs_submit_bbio+0x1c/0x40 [btrfs]
   submit_one_bio+0x44/0x60 [btrfs]
   submit_extent_folio+0x13f/0x330 [btrfs]
   ? btrfs_set_range_writeback+0xa3/0xd0 [btrfs]
   extent_writepage_io+0x18b/0x360 [btrfs]
   extent_write_locked_range+0x17c/0x340 [btrfs]
   ? __pfx_end_bbio_data_write+0x10/0x10 [btrfs]
   run_delalloc_cow+0x71/0xd0 [btrfs]
   btrfs_run_delalloc_range+0x176/0x500 [btrfs]
   ? find_lock_delalloc_range+0x119/0x260 [btrfs]
   writepage_delalloc+0x2ab/0x480 [btrfs]
   extent_write_cache_pages+0x236/0x7d0 [btrfs]
   btrfs_writepages+0x72/0x130 [btrfs]
   do_writepages+0xd4/0x240
   ? find_held_lock+0x2b/0x80
   ? wbc_attach_and_unlock_inode+0x12c/0x290
   ? wbc_attach_and_unlock_inode+0x12c/0x290
   __writeback_single_inode+0x5c/0x4c0
   ? do_raw_spin_unlock+0x49/0xb0
   writeback_sb_inodes+0x22c/0x560
   __writeback_inodes_wb+0x4c/0xe0
   wb_writeback+0x1d6/0x3f0
   wb_workfn+0x334/0x520
   process_one_work+0x1ee/0x570
   ? lock_is_held_type+0xc6/0x130
   worker_thread+0x1d1/0x3b0
   ? __pfx_worker_thread+0x10/0x10
   kthread+0xee/0x120
   ? __pfx_kthread+0x10/0x10
   ret_from_fork+0x30/0x50
   ? __pfx_kthread+0x10/0x10
   ret_from_fork_asm+0x1a/0x30
   </TASK>
  Modules linked in: dm_mod btrfs blake2b_generic xor raid6_pq rapl
  CR2: 0000000000000020

* Case 2. Earlier completion of orig_bbio for mirrored btrfs_bios

btrfs_bbio_propagate_error() assumes the end_io function for orig_bbio is called last among split bios. In that case, btrfs_orig_write_end_io() sets the bio->bi_status to BLK_STS_IOERR by seeing the bioc->error [2]. Otherwise, the increased orig_bio's bioc->error is not checked by anyone and return BLK_STS_OK to the upper layer.

[2] Actually, this is not true. Because we only increases orig_bioc->errors by max_errors, the condition "atomic_read(&bioc->error) > bioc->max_errors" is still not met if only one split btrfs_bio fails.

* Case 3. Later completion of orig_bbio for un-mirrored btrfs_bios

In contrast to the above case, btrfs_bbio_propagate_error() is not working well if un-mirrored orig_bbio is completed last. It sets orig_bbio->bio.bi_status to the btrfs_bio's error. But, that is easily over-written by orig_bbio's completion status. If the status is BLK_STS_OK, the upper layer would not know the failure.

* Solution

Considering the above cases, we can only save the error status in the orig_bbio (remaining part after split) itself as it is always available. Also, the saved error status should be propagated when all the split btrfs_bios are finished (i.e, bbio->pending_ios == 0).

This commit introduces "status" to btrfs_bbio and saves the first error of split bios to original btrfs_bio's "status" variable. When all the split bios are finished, the saved status is loaded into original btrfs_bio's status.

With this commit, btrfs/146 on zoned devices does not hit the NULL pointer dereference anymore.

---
 fs/btrfs/bio.c | 37 +++++++++++++------------------------
 fs/btrfs/bio.h |  3 +++
 2 files changed, 16 insertions(+), 24 deletions(-)

index e93d376796a28..31e437d94869d 100644
@@ -49,6 +49,7 @@ void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info,
 	bbio->end_io = end_io;
 	bbio->private = private;
 	atomic_set(&bbio->pending_ios, 1);
+	WRITE_ONCE(bbio->status, BLK_STS_OK);
 }
 
 /*

@@ -120,41 +121,29 @@ static void __btrfs_bio_end_io(struct btrfs_bio *bbio)
 	}
 }
 
-static void btrfs_orig_write_end_io(struct bio *bio);
-
-static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio,
-				       struct btrfs_bio *orig_bbio)
-{
-	/*
-	 * For writes we tolerate nr_mirrors - 1 write failures, so we can't
-	 * just blindly propagate a write failure here.  Instead increment the
-	 * error count in the original I/O context so that it is guaranteed to
-	 * be larger than the error tolerance.
-	 */
-	if (bbio->bio.bi_end_io == &btrfs_orig_write_end_io) {
-		struct btrfs_io_stripe *orig_stripe = orig_bbio->bio.bi_private;
-		struct btrfs_io_context *orig_bioc = orig_stripe->bioc;
-
-		atomic_add(orig_bioc->max_errors, &orig_bioc->error);
-	} else {
-		orig_bbio->bio.bi_status = bbio->bio.bi_status;
-	}
-}
-
 void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
 {
 	bbio->bio.bi_status = status;
 	if (bbio->bio.bi_pool == &btrfs_clone_bioset) {
 		struct btrfs_bio *orig_bbio = bbio->private;
 
-		if (bbio->bio.bi_status)
-			btrfs_bbio_propagate_error(bbio, orig_bbio);
 		btrfs_cleanup_bio(bbio);
 		bbio = orig_bbio;
 	}
 
-	if (atomic_dec_and_test(&bbio->pending_ios))
+	/*
+	 * At this point, bbio always points to the original btrfs_bio. Save
+	 * the first error in it.
+	 */
+	if (status != BLK_STS_OK)
+		cmpxchg(&bbio->status, BLK_STS_OK, status);
+
+	if (atomic_dec_and_test(&bbio->pending_ios)) {
+		/* Load split bio's error which might be set above. */
+		if (status == BLK_STS_OK)
+			bbio->bio.bi_status = READ_ONCE(bbio->status);
 		__btrfs_bio_end_io(bbio);
+	}
 }
 
 static int next_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)

index d9dd5276093df..043f94562166b 100644
@@ -79,6 +79,9 @@ struct btrfs_bio {
 	/* File system that this I/O operates on. */
 	struct btrfs_fs_info *fs_info;
 
+	/* Save the first error status of split bio. */
+	blk_status_t status;
+
 	/*
 	 * This member must come last, bio_alloc_bioset will allocate enough
 	 * bytes for entire btrfs_bio but relies on bio being last.

2.43.0

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

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

From: Frank Li <[email protected]>

[ Upstream commit 25f00a13dccf8e45441265768de46c8bf58e08f6 ]

Add check for the return value of spi_get_csgpiod() to avoid passing a NULL pointer to gpiod_direction_output(), preventing a crash when GPIO chip select is not used.

Fix below crash:

[    4.251960] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
[    4.260762] Mem abort info:
[    4.263556]   ESR = 0x0000000096000004
[    4.267308]   EC = 0x25: DABT (current EL), IL = 32 bits
[    4.272624]   SET = 0, FnV = 0
[    4.275681]   EA = 0, S1PTW = 0
[    4.278822]   FSC = 0x04: level 0 translation fault
[    4.283704] Data abort info:
[    4.286583]   ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[    4.292074]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[    4.297130]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[    4.302445] [0000000000000000] user address but active_mm is swapper
[    4.308805] Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP
[    4.315072] Modules linked in:
[    4.318124] CPU: 2 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.12.0-rc4-next-20241023-00008-ga20ec42c5fc1 #359
[    4.328130] Hardware name: LS1046A QDS Board (DT)
[    4.332832] pstate: 40000005 (nZcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[    4.339794] pc : gpiod_direction_output+0x34/0x5c
[    4.344505] lr : gpiod_direction_output+0x18/0x5c
[    4.349208] sp : ffff80008003b8f0
[    4.352517] x29: ffff80008003b8f0 x28: 0000000000000000 x27: ffffc96bcc7e9068
[    4.359659] x26: ffffc96bcc6e00b0 x25: ffffc96bcc598398 x24: ffff447400132810
[    4.366800] x23: 0000000000000000 x22: 0000000011e1a300 x21: 0000000000020002
[    4.373940] x20: 0000000000000000 x19: 0000000000000000 x18: ffffffffffffffff
[    4.381081] x17: ffff44740016e600 x16: 0000000500000003 x15: 0000000000000007
[    4.388221] x14: 0000000000989680 x13: 0000000000020000 x12: 000000000000001e
[    4.395362] x11: 0044b82fa09b5a53 x10: 0000000000000019 x9 : 0000000000000008
[    4.402502] x8 : 0000000000000002 x7 : 0000000000000007 x6 : 0000000000000000
[    4.409641] x5 : 0000000000000200 x4 : 0000000002000000 x3 : 0000000000000000
[    4.416781] x2 : 0000000000022202 x1 : 0000000000000000 x0 : 0000000000000000
[    4.423921] Call trace:
[    4.426362]  gpiod_direction_output+0x34/0x5c (P)
[    4.431067]  gpiod_direction_output+0x18/0x5c (L)
[    4.435771]  dspi_setup+0x220/0x334

---
 drivers/spi/spi-fsl-dspi.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index 191de1917f831..3fa990fb59c78 100644
@@ -1003,6 +1003,7 @@ static int dspi_setup(struct spi_device *spi)
 	u32 cs_sck_delay = 0, sck_cs_delay = 0;
 	struct fsl_dspi_platform_data *pdata;
 	unsigned char pasc = 0, asc = 0;
+	struct gpio_desc *gpio_cs;
 	struct chip_data *chip;
 	unsigned long clkrate;
 	bool cs = true;

@@ -1077,7 +1078,10 @@ static int dspi_setup(struct spi_device *spi)
 			chip->ctar_val |= SPI_CTAR_LSBFE;
 	}
 
-	gpiod_direction_output(spi_get_csgpiod(spi, 0), false);
+	gpio_cs = spi_get_csgpiod(spi, 0);
+	if (gpio_cs)
+		gpiod_direction_output(gpio_cs, false);
+
 	dspi_deassert_cs(spi, &cs);
 
 	spi_set_ctldata(spi, chip);

2.43.0

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

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

From: Alexandre Ghiti <[email protected]>

[ Upstream commit bf40167d54d55d4b54d0103713d86a8638fb9290 ]

The compiler is smart enough to insert a call to memset() in riscv_vdso_get_cpus(), which generates a dynamic relocation.

So prevent this by using -fno-builtin option.

---
 arch/riscv/kernel/vdso/Makefile | 1 +
 1 file changed, 1 insertion(+)

index f7ef8ad9b550d..54a7fec25d5f8 100644
@@ -18,6 +18,7 @@ obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
 
 ccflags-y := -fno-stack-protector
 ccflags-y += -DDISABLE_BRANCH_PROFILING
+ccflags-y += -fno-builtin
 
 ifneq ($(c-gettimeofday-y),)
   CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)

2.43.0

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

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

From: Dmitry Torokhov <[email protected]>

[ Upstream commit bffdf9d7e51a7be8eeaac2ccf9e54a5fde01ff65 ]

The driver neglects to free the instance of I2C regmap constructed at the beginning of the edt_ft5x06_ts_probe() method when probe fails. Additionally edt_ft5x06_ts_remove() is freeing the regmap too early, before the rest of the device resources that are managed by devm are released.

Fix this by installing a custom devm action that will ensure that the regmap is released at the right time during normal teardown as well as in case of probe failure.

Note that devm_regmap_init_i2c() could not be used because the driver may replace the original regmap with a regmap specific for M06 devices in the middle of the probe, and using devm_regmap_init_i2c() would result in releasing the M06 regmap too early.

---
 drivers/input/touchscreen/edt-ft5x06.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

index e70415f189a55..126b0ed85aa50 100644
@@ -1121,6 +1121,14 @@ static void edt_ft5x06_ts_set_regs(struct edt_ft5x06_ts_data *tsdata)
 	}
 }
 
+static void edt_ft5x06_exit_regmap(void *arg)
+{
+	struct edt_ft5x06_ts_data *data = arg;
+
+	if (!IS_ERR_OR_NULL(data->regmap))
+		regmap_exit(data->regmap);
+}
+
 static void edt_ft5x06_disable_regulators(void *arg)
 {
 	struct edt_ft5x06_ts_data *data = arg;

@@ -1154,6 +1162,16 @@ static int edt_ft5x06_ts_probe(struct i2c_client *client)
 		return PTR_ERR(tsdata->regmap);
 	}
 
+	/*
+	 * We are not using devm_regmap_init_i2c() and instead install a
+	 * custom action because we may replace regmap with M06-specific one
+	 * and we need to make sure that it will not be released too early.
+	 */
+	error = devm_add_action_or_reset(&client->dev, edt_ft5x06_exit_regmap,
+					 tsdata);
+	if (error)
+		return error;
+
 	chip_data = device_get_match_data(&client->dev);
 	if (!chip_data)
 		chip_data = (const struct edt_i2c_chip_data *)id->driver_data;

@@ -1347,7 +1365,6 @@ static void edt_ft5x06_ts_remove(struct i2c_client *client)
 	struct edt_ft5x06_ts_data *tsdata = i2c_get_clientdata(client);
 
 	edt_ft5x06_ts_teardown_debugfs(tsdata);
-	regmap_exit(tsdata->regmap);
 }
 
 static int edt_ft5x06_ts_suspend(struct device *dev)

2.43.0

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

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

From: Kailang Yang <[email protected]>

[ Upstream commit 78e7be018784934081afec77f96d49a2483f9188 ]

Dell want to limit internal Mic boost on all Dell platform.

---
 sound/pci/hda/patch_realtek.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

index 2583081c0a3a5..8d6f446d507c2 100644
@@ -7507,6 +7507,7 @@ enum {
 	ALC286_FIXUP_SONY_MIC_NO_PRESENCE,
 	ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT,
 	ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+	ALC269_FIXUP_DELL1_LIMIT_INT_MIC_BOOST,
 	ALC269_FIXUP_DELL2_MIC_NO_PRESENCE,
 	ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
 	ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,

@@ -7541,6 +7542,7 @@ enum {
 	ALC255_FIXUP_ACER_MIC_NO_PRESENCE,
 	ALC255_FIXUP_ASUS_MIC_NO_PRESENCE,
 	ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+	ALC255_FIXUP_DELL1_LIMIT_INT_MIC_BOOST,
 	ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
 	ALC255_FIXUP_HEADSET_MODE,
 	ALC255_FIXUP_HEADSET_MODE_NO_HP_MIC,

@@ -8102,6 +8104,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC269_FIXUP_HEADSET_MODE
 	},
+	[ALC269_FIXUP_DELL1_LIMIT_INT_MIC_BOOST] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_limit_int_mic_boost,
+		.chained = true,
+		.chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE
+	},
 	[ALC269_FIXUP_DELL2_MIC_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {

@@ -8382,6 +8390,12 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC255_FIXUP_HEADSET_MODE
 	},
+	[ALC255_FIXUP_DELL1_LIMIT_INT_MIC_BOOST] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc269_fixup_limit_int_mic_boost,
+		.chained = true,
+		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
+	},
 	[ALC255_FIXUP_DELL2_MIC_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {

@@ -11050,6 +11064,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC269_FIXUP_DELL2_MIC_NO_PRESENCE, .name = "dell-headset-dock"},
 	{.id = ALC269_FIXUP_DELL3_MIC_NO_PRESENCE, .name = "dell-headset3"},
 	{.id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, .name = "dell-headset4"},
+	{.id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET, .name = "dell-headset4-quiet"},
 	{.id = ALC283_FIXUP_CHROME_BOOK, .name = "alc283-dac-wcaps"},
 	{.id = ALC283_FIXUP_SENSE_COMBO_JACK, .name = "alc283-sense-combo"},
 	{.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"},

@@ -11604,16 +11619,16 @@ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = {
 	SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
 		{0x19, 0x40000000},
 		{0x1b, 0x40000000}),
-	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE_QUIET,
 		{0x19, 0x40000000},
 		{0x1b, 0x40000000}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x19, 0x40000000},
 		{0x1a, 0x40000000}),
-	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_LIMIT_INT_MIC_BOOST,
 		{0x19, 0x40000000},
 		{0x1a, 0x40000000}),
-	SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB,
+	SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC269_FIXUP_DELL1_LIMIT_INT_MIC_BOOST,
 		{0x19, 0x40000000},
 		{0x1a, 0x40000000}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC2XX_FIXUP_HEADSET_MIC,

2.43.0

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

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

From: Heinrich Schuchardt <[email protected]>

[ Upstream commit d41373a4b910961df5a5e3527d7bde6ad45ca438 ]

The IMAGE_DLLCHARACTERISTICS_NX_COMPAT informs the firmware that the EFI binary does not rely on pages that are both executable and writable.

The flag is used by some distro versions of GRUB to decide if the EFI binary may be executed.

As the Linux kernel neither has RWX sections nor needs RWX pages for relocation we should set the flag.

---
 arch/riscv/kernel/efi-header.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 515b2dfbca75b..c5f17c2710b58 100644
@@ -64,7 +64,7 @@ extra_header_fields:
 	.long	efi_header_end - _start			// SizeOfHeaders
 	.long	0					// CheckSum
 	.short	IMAGE_SUBSYSTEM_EFI_APPLICATION		// Subsystem
-	.short	0					// DllCharacteristics
+	.short	IMAGE_DLL_CHARACTERISTICS_NX_COMPAT	// DllCharacteristics
 	.quad	0					// SizeOfStackReserve
 	.quad	0					// SizeOfStackCommit
 	.quad	0					// SizeOfHeapReserve

2.43.0

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

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

From: Miquel Sabaté Solà <[email protected]>

[ Upstream commit 37233169a6ea912020c572f870075a63293b786a ]

When populating cache leaves we previously fetched the CPU device node at the very beginning. But when ACPI is enabled we go through a specific branch which returns early and does not call 'of_node_put' for the node that was acquired.

Since we are not using a CPU device node for the ACPI code anyways, we can simply move the initialization of it just passed the ACPI block, and we are guaranteed to have an 'of_node_put' call for the acquired node. This prevents a bad reference count of the CPU device node.

Moreover, the previous function did not check for errors when acquiring the device node, so a return -ENOENT has been added for that case.

---
 arch/riscv/kernel/cacheinfo.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

index d6c108c50cba9..d32dfdba083e1 100644
@@ -75,8 +75,7 @@ int populate_cache_leaves(unsigned int cpu)
 {
 	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
 	struct cacheinfo *this_leaf = this_cpu_ci->info_list;
-	struct device_node *np = of_cpu_device_node_get(cpu);
-	struct device_node *prev = NULL;
+	struct device_node *np, *prev;
 	int levels = 1, level = 1;
 
 	if (!acpi_disabled) {

@@ -100,6 +99,10 @@ int populate_cache_leaves(unsigned int cpu)
 		return 0;
 	}
 
+	np = of_cpu_device_node_get(cpu);
+	if (!np)
+		return -ENOENT;
+
 	if (of_property_read_bool(np, "cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
 	if (of_property_read_bool(np, "i-cache-size"))

2.43.0

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

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

From: WangYuli <[email protected]>

[ Upstream commit e0872ab72630dada3ae055bfa410bf463ff1d1e0 ]

'cpu' is an unsigned integer, so its conversion specifier should be %u, not %d.

---
 arch/riscv/kernel/cpu-hotplug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 28b58fc5ad199..a1e38ecfc8be2 100644
@@ -58,7 +58,7 @@ void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
 	if (cpu_ops->cpu_is_stopped)
 		ret = cpu_ops->cpu_is_stopped(cpu);
 	if (ret)
-		pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
+		pr_warn("CPU%u may not have stopped: %d\n", cpu, ret);
 }
 
 /*

2.43.0

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

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

From: Chunyan Zhang <[email protected]>

[ Upstream commit 46d4e5ac6f2f801f97bcd0ec82365969197dc9b1 ]

The macro is not used in the current version of kernel, it looks like can be removed to avoid a build warning:

../arch/riscv/kernel/asm-offsets.c: At top level:
../arch/riscv/kernel/asm-offsets.c:7: warning: macro "GENERATING_ASM_OFFSETS" is not used [-Wunused-macros]
7 | #define GENERATING_ASM_OFFSETS

---
 arch/riscv/kernel/asm-offsets.c | 2 --
 1 file changed, 2 deletions(-)

index b09ca5f944f77..cb09f0c4f62c7 100644
@@ -4,8 +4,6 @@
  * Copyright (C) 2017 SiFive
  */
 
-#define GENERATING_ASM_OFFSETS
-
 #include <linux/kbuild.h>
 #include <linux/mm.h>
 #include <linux/sched.h>

2.43.0

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

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

From: Chunyan Zhang <[email protected]>

[ Upstream commit 164f66de6bb6ef454893f193c898dc8f1da6d18b ]

The macro GET_RM defined twice in this file, one can be removed.

---
 arch/riscv/kernel/traps_misaligned.c | 2 --
 1 file changed, 2 deletions(-)

index d4fd8af7aaf5a..1b9867136b610 100644
@@ -136,8 +136,6 @@
 #define REG_PTR(insn, pos, regs)	\
 	(ulong *)((ulong)(regs) + REG_OFFSET(insn, pos))
 
-#define GET_RM(insn)			(((insn) >> 12) & 7)
-
 #define GET_RS1(insn, regs)		(*REG_PTR(insn, SH_RS1, regs))
 #define GET_RS2(insn, regs)		(*REG_PTR(insn, SH_RS2, regs))
 #define GET_RS1S(insn, regs)		(*REG_PTR(RVC_RS1S(insn), 0, regs))

2.43.0

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

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

From: Peter Wang <[email protected]>

[ Upstream commit cb7e509c4e0197f63717fee54fb41c4990ba8d3a ]

If ufshcd_rtc_work calls ufshcd_rpm_put_sync() and the pm's usage_count is 0, we will enter the runtime suspend callback. However, the runtime suspend callback will wait to flush ufshcd_rtc_work, causing a deadlock.

Replace ufshcd_rpm_put_sync() with ufshcd_rpm_put() to avoid the deadlock.

---
 drivers/ufs/core/ufshcd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 09408642a6efb..83567388a7b58 100644
@@ -8224,7 +8224,7 @@ static void ufshcd_update_rtc(struct ufs_hba *hba)
 
 	err = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR, QUERY_ATTR_IDN_SECONDS_PASSED,
 				0, 0, &val);
-	ufshcd_rpm_put_sync(hba);
+	ufshcd_rpm_put(hba);
 
 	if (err)
 		dev_err(hba->dev, "%s: Failed to update rtc %d\n", __func__, err);

2.43.0

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

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

From: Dan Williams <[email protected]>

[ Upstream commit 3d6ebf16438de5d712030fefbb4182b46373d677 ]

It turns out since its original introduction, pre-2.6.12, bus_rescan_devices() has skipped devices that might be in the process of attaching or detaching from their driver. For CXL this behavior is unwanted and expects that cxl_bus_rescan() is a probe barrier.

That behavior is simple enough to achieve with bus_for_each_dev() paired with call to device_attach(), and it is unclear why bus_rescan_devices() took the position of lockless consumption of dev->driver which is racy.

The "Fixes:" but no "Cc: stable" on this patch reflects that the issue is merely by inspection since the bug that triggered the discovery of this potential problem [1] is fixed by other means. However, a stable backport should do no harm.

---
 drivers/cxl/core/port.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

index 1d5007e3795a3..d3237346f6877 100644
@@ -2088,11 +2088,18 @@ static void cxl_bus_remove(struct device *dev)
 
 static struct workqueue_struct *cxl_bus_wq;
 
-static void cxl_bus_rescan_queue(struct work_struct *w)
+static int cxl_rescan_attach(struct device *dev, void *data)
 {
-	int rc = bus_rescan_devices(&cxl_bus_type);
+	int rc = device_attach(dev);
+
+	dev_vdbg(dev, "rescan: %s\n", rc ? "attach" : "detached");
 
-	pr_debug("CXL bus rescan result: %d\n", rc);
+	return 0;
+}
+
+static void cxl_bus_rescan_queue(struct work_struct *w)
+{
+	bus_for_each_dev(&cxl_bus_type, NULL, NULL, cxl_rescan_attach);
 }
 
 void cxl_bus_rescan(void)

2.43.0

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

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

From: Dan Williams <[email protected]>

[ Upstream commit 48f62d38a07d464a499fa834638afcfd2b68f852 ]

In order to ensure root CXL ports are enabled upon cxl_acpi_probe() when the 'cxl_port' driver is built as a module, arrange for the module to be pre-loaded or built-in.

The "Fixes:" but no "Cc: stable" on this patch reflects that the issue is merely by inspection since the bug that triggered the discovery of this potential problem [1] is fixed by other means. However, a stable backport should do no harm.

---
 drivers/cxl/acpi.c | 7 +++++++
 1 file changed, 7 insertions(+)

index 82b78e331d8ed..432b7cfd12a8e 100644
@@ -924,6 +924,13 @@ static void __exit cxl_acpi_exit(void)
 
 /* load before dax_hmem sees 'Soft Reserved' CXL ranges */
 subsys_initcall(cxl_acpi_init);
+
+/*
+ * Arrange for host-bridge ports to be active synchronous with
+ * cxl_acpi_probe() exit.
+ */
+MODULE_SOFTDEP("pre: cxl_port");
+
 module_exit(cxl_acpi_exit);
 MODULE_DESCRIPTION("CXL ACPI: Platform Support");
 MODULE_LICENSE("GPL v2");

2.43.0

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

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

From: Shawn Wang <[email protected]>

[ Upstream commit 9c70b2a33cd2aa6a5a59c5523ef053bd42265209 ]

When running stress-ng-vm-segv test, we found a null pointer dereference error in task_numa_work(). Here is the backtrace:

  [323676.066985] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020
  ......
  [323676.067108] CPU: 35 PID: 2694524 Comm: stress-ng-vm-se
  ......
  [323676.067113] pstate: 23401009 (nzCv daif +PAN -UAO +TCO +DIT +SSBS BTYPE=--)
  [323676.067115] pc : vma_migratable+0x1c/0xd0
  [323676.067122] lr : task_numa_work+0x1ec/0x4e0
  [323676.067127] sp : ffff8000ada73d20
  [323676.067128] x29: ffff8000ada73d20 x28: 0000000000000000 x27: 000000003e89f010
  [323676.067130] x26: 0000000000080000 x25: ffff800081b5c0d8 x24: ffff800081b27000
  [323676.067133] x23: 0000000000010000 x22: 0000000104d18cc0 x21: ffff0009f7158000
  [323676.067135] x20: 0000000000000000 x19: 0000000000000000 x18: ffff8000ada73db8
  [323676.067138] x17: 0001400000000000 x16: ffff800080df40b0 x15: 0000000000000035
  [323676.067140] x14: ffff8000ada73cc8 x13: 1fffe0017cc72001 x12: ffff8000ada73cc8
  [323676.067142] x11: ffff80008001160c x10: ffff000be639000c x9 : ffff8000800f4ba4
  [323676.067145] x8 : ffff000810375000 x7 : ffff8000ada73974 x6 : 0000000000000001
  [323676.067147] x5 : 0068000b33e26707 x4 : 0000000000000001 x3 : ffff0009f7158000
  [323676.067149] x2 : 0000000000000041 x1 : 0000000000004400 x0 : 0000000000000000
  [323676.067152] Call trace:
  [323676.067153]  vma_migratable+0x1c/0xd0
  [323676.067155]  task_numa_work+0x1ec/0x4e0
  [323676.067157]  task_work_run+0x78/0xd8
  [323676.067161]  do_notify_resume+0x1ec/0x290
  [323676.067163]  el0_svc+0x150/0x160
  [323676.067167]  el0t_64_sync_handler+0xf8/0x128
  [323676.067170]  el0t_64_sync+0x17c/0x180
  [323676.067173] Code: d2888001 910003fd f9000bf3 aa0003f3 (f9401000)
  [323676.067177] SMP: stopping secondary CPUs
  [323676.070184] Starting crashdump kernel...

stress-ng-vm-segv in stress-ng is used to stress test the SIGSEGV error handling function of the system, which tries to cause a SIGSEGV error on return from unmapping the whole address space of the child process.

Normally this program will not cause kernel crashes. But before the munmap system call returns to user mode, a potential task_numa_work() for numa balancing could be added and executed. In this scenario, since the child process has no vma after munmap, the vma_next() in task_numa_work() will return a null pointer even if the vma iterator restarts from 0.

Recheck the vma pointer before dereferencing it in task_numa_work().

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

index 1d2cbdb162a67..425348b8d9eb3 100644
@@ -3289,7 +3289,7 @@ static void task_numa_work(struct callback_head *work)
 		vma = vma_next(&vmi);
 	}
 
-	do {
+	for (; vma; vma = vma_next(&vmi)) {
 		if (!vma_migratable(vma) || !vma_policy_mof(vma) ||
 			is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) {
 			trace_sched_skip_vma_numa(mm, vma, NUMAB_SKIP_UNSUITABLE);

@@ -3411,7 +3411,7 @@ static void task_numa_work(struct callback_head *work)
 		 */
 		if (vma_pids_forced)
 			break;
-	} for_each_vma(vmi, vma);
+	}
 
 	/*
 	 * If no VMAs are remaining and VMAs were skipped due to the PID

2.43.0

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

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

From: Benjamin Segall <[email protected]>

[ Upstream commit b5413156bad91dc2995a5c4eab1b05e56914638a ]

When cloning a new thread, its posix_cputimers are not inherited, and are cleared by posix_cputimers_init(). However, this does not clear the tick dependency it creates in tsk->tick_dep_mask, and the handler does not reach the code to clear the dependency if there were no timers to begin with.

Thus if a thread has a cputimer running before clone/fork, all descendants will prevent nohz_full unless they create a cputimer of their own.

Fix this by entirely clearing the tick_dep_mask in copy_process(). (There is currently no inherited state that needs a tick dependency)

Process-wide timers do not have this problem because fork does not copy signal_struct as a baseline, it creates one from scratch.

---
 include/linux/tick.h | 8 ++++++++
 kernel/fork.c        | 2 ++
 2 files changed, 10 insertions(+)

index 72744638c5b0f..99c9c5a7252aa 100644
@@ -251,12 +251,19 @@ static inline void tick_dep_set_task(struct task_struct *tsk,
 	if (tick_nohz_full_enabled())
 		tick_nohz_dep_set_task(tsk, bit);
 }
+
 static inline void tick_dep_clear_task(struct task_struct *tsk,
 				       enum tick_dep_bits bit)
 {
 	if (tick_nohz_full_enabled())
 		tick_nohz_dep_clear_task(tsk, bit);
 }
+
+static inline void tick_dep_init_task(struct task_struct *tsk)
+{
+	atomic_set(&tsk->tick_dep_mask, 0);
+}
+
 static inline void tick_dep_set_signal(struct task_struct *tsk,
 				       enum tick_dep_bits bit)
 {

@@ -290,6 +297,7 @@ static inline void tick_dep_set_task(struct task_struct *tsk,
 				     enum tick_dep_bits bit) { }
 static inline void tick_dep_clear_task(struct task_struct *tsk,
 				       enum tick_dep_bits bit) { }
+static inline void tick_dep_init_task(struct task_struct *tsk) { }
 static inline void tick_dep_set_signal(struct task_struct *tsk,
 				       enum tick_dep_bits bit) { }
 static inline void tick_dep_clear_signal(struct signal_struct *signal,

index 6b97fb2ac4af5..dbf3c5d81df3b 100644
@@ -104,6 +104,7 @@
 #include <linux/rseq.h>
 #include <uapi/linux/pidfd.h>
 #include <linux/pidfs.h>
+#include <linux/tick.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>

@@ -2290,6 +2291,7 @@ __latent_entropy struct task_struct *copy_process(
 	acct_clear_integrals(p);
 
 	posix_cputimers_init(&p->posix_cputimers);
+	tick_dep_init_task(p);
 
 	p->io_context = NULL;
 	audit_set_context(p, NULL);

2.43.0

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

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

From: Hugh Dickins <[email protected]>

[ Upstream commit c749d9b7ebbc5716af7a95f7768634b30d9446ec ]

generic/077 on x86_32 CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP=y with highmem, on huge=always tmpfs, issues a warning and then hangs (interruptibly):

WARNING: CPU: 5 PID: 3517 at mm/highmem.c:622 kunmap_local_indexed+0x62/0xc9
CPU: 5 UID: 0 PID: 3517 Comm: cp Not tainted 6.12.0-rc4 #2
...
copy_page_from_iter_atomic+0xa6/0x5ec
generic_perform_write+0xf6/0x1b4
shmem_file_write_iter+0x54/0x67

Fix copy_page_from_iter_atomic() by limiting it in that case (include/linux/skbuff.h skb_frag_must_loop() does similar).

But going forward, perhaps CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP is too surprising, has outlived its usefulness, and should just be removed?

---
 lib/iov_iter.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index 4a6a9f419bd7e..b892894228b03 100644
@@ -461,6 +461,8 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
 		size_t bytes, struct iov_iter *i)
 {
 	size_t n, copied = 0;
+	bool uses_kmap = IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) ||
+			 PageHighMem(page);
 
 	if (!page_copy_sane(page, offset, bytes))
 		return 0;

@@ -471,7 +473,7 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
 		char *p;
 
 		n = bytes - copied;
-		if (PageHighMem(page)) {
+		if (uses_kmap) {
 			page += offset / PAGE_SIZE;
 			offset %= PAGE_SIZE;
 			n = min_t(size_t, n, PAGE_SIZE - offset);

@@ -482,7 +484,7 @@ size_t copy_page_from_iter_atomic(struct page *page, size_t offset,
 		kunmap_atomic(p);
 		copied += n;
 		offset += n;
-	} while (PageHighMem(page) && copied != bytes && n > 0);
+	} while (uses_kmap && copied != bytes && n > 0);
 
 	return copied;
 }

2.43.0

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

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

From: Jarkko Sakkinen <[email protected]>

[ Upstream commit d658d59471ed80c4a8aaf082ccc3e83cdf5ae4c1 ]

Do not continue tpm2_sessions_init() further if the null key pair creation fails.

---
 drivers/char/tpm/tpm2-sessions.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

index 44f60730cff44..9551eeca6d691 100644
@@ -1347,14 +1347,21 @@ static int tpm2_create_null_primary(struct tpm_chip *chip)
  *
  * Derive and context save the null primary and allocate memory in the
  * struct tpm_chip for the authorizations.
+ *
+ * Return:
+ * * 0		- OK
+ * * -errno	- A system error
+ * * TPM_RC	- A TPM error
  */
 int tpm2_sessions_init(struct tpm_chip *chip)
 {
 	int rc;
 
 	rc = tpm2_create_null_primary(chip);
-	if (rc)
-		dev_err(&chip->dev, "TPM: security failed (NULL seed derivation): %d\n", rc);
+	if (rc) {
+		dev_err(&chip->dev, "null key creation failed with %d\n", rc);
+		return rc;
+	}
 
 	chip->auth = kmalloc(sizeof(*chip->auth), GFP_KERNEL);
 	if (!chip->auth)

2.43.0

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

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

From: Jarkko Sakkinen <[email protected]>

[ Upstream commit cc7d8594342a25693d40fe96f97e5c6c29ee609c ]

Do not continue on tpm2_create_primary() failure in tpm2_load_null().

---
 drivers/char/tpm/tpm2-sessions.c | 44 +++++++++++++++++---------------
 1 file changed, 24 insertions(+), 20 deletions(-)

index 9551eeca6d691..a194535619929 100644
@@ -915,33 +915,37 @@ static int tpm2_parse_start_auth_session(struct tpm2_auth *auth,
 
 static int tpm2_load_null(struct tpm_chip *chip, u32 *null_key)
 {
-	int rc;
 	unsigned int offset = 0; /* dummy offset for null seed context */
 	u8 name[SHA256_DIGEST_SIZE + 2];
+	u32 tmp_null_key;
+	int rc;
 
 	rc = tpm2_load_context(chip, chip->null_key_context, &offset,
-			       null_key);
-	if (rc != -EINVAL)
-		return rc;
+			       &tmp_null_key);
+	if (rc != -EINVAL) {
+		if (!rc)
+			*null_key = tmp_null_key;
+		goto err;
+	}
 
-	/* an integrity failure may mean the TPM has been reset */
-	dev_err(&chip->dev, "NULL key integrity failure!\n");
-	/* check the null name against what we know */
-	tpm2_create_primary(chip, TPM2_RH_NULL, NULL, name);
-	if (memcmp(name, chip->null_key_name, sizeof(name)) == 0)
-		/* name unchanged, assume transient integrity failure */
-		return rc;
-	/*
-	 * Fatal TPM failure: the NULL seed has actually changed, so
-	 * the TPM must have been illegally reset.  All in-kernel TPM
-	 * operations will fail because the NULL primary can't be
-	 * loaded to salt the sessions, but disable the TPM anyway so
-	 * userspace programmes can't be compromised by it.
-	 */
-	dev_err(&chip->dev, "NULL name has changed, disabling TPM due to interference\n");
+	/* Try to re-create null key, given the integrity failure: */
+	rc = tpm2_create_primary(chip, TPM2_RH_NULL, &tmp_null_key, name);
+	if (rc)
+		goto err;
+
+	/* Return null key if the name has not been changed: */
+	if (!memcmp(name, chip->null_key_name, sizeof(name))) {
+		*null_key = tmp_null_key;
+		return 0;
+	}
+
+	/* Deduce from the name change TPM interference: */
+	dev_err(&chip->dev, "null key integrity check failed\n");
+	tpm2_flush_context(chip, tmp_null_key);
 	chip->flags |= TPM_CHIP_FLAG_DISABLE;
 
-	return rc;
+err:
+	return rc ? -ENODEV : 0;
 }
 
 /**

2.43.0

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

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

From: Tvrtko Ursulin <[email protected]>

[ Upstream commit 4aa923a6e6406b43566ef6ac35a3d9a3197fa3e8 ]

KASAN reports that the GPU metrics table allocated in vangogh_tables_init() is not large enough for the memset done in smu_cmn_init_soft_gpu_metrics(). Condensed report follows:

[   33.861314] BUG: KASAN: slab-out-of-bounds in smu_cmn_init_soft_gpu_metrics+0x73/0x200 [amdgpu]
[   33.861799] Write of size 168 at addr ffff888129f59500 by task mangoapp/1067
...
[   33.861808] CPU: 6 UID: 1000 PID: 1067 Comm: mangoapp Tainted: G        W          6.12.0-rc4 #356 1a56f59a8b5182eeaf67eb7cb8b13594dd23b544
[   33.861816] Tainted: [W]=WARN
[   33.861818] Hardware name: Valve Galileo/Galileo, BIOS F7G0107 12/01/2023
[   33.861822] Call Trace:
[   33.861826]  <TASK>
[   33.861829]  dump_stack_lvl+0x66/0x90
[   33.861838]  print_report+0xce/0x620
[   33.861853]  kasan_report+0xda/0x110
[   33.862794]  kasan_check_range+0xfd/0x1a0
[   33.862799]  __asan_memset+0x23/0x40
[   33.862803]  smu_cmn_init_soft_gpu_metrics+0x73/0x200 [amdgpu 13b1bc364ec578808f676eba412c20eaab792779]
[   33.863306]  vangogh_get_gpu_metrics_v2_4+0x123/0xad0 [amdgpu 13b1bc364ec578808f676eba412c20eaab792779]
[   33.864257]  vangogh_common_get_gpu_metrics+0xb0c/0xbc0 [amdgpu 13b1bc364ec578808f676eba412c20eaab792779]
[   33.865682]  amdgpu_dpm_get_gpu_metrics+0xcc/0x110 [amdgpu 13b1bc364ec578808f676eba412c20eaab792779]
[   33.866160]  amdgpu_get_gpu_metrics+0x154/0x2d0 [amdgpu 13b1bc364ec578808f676eba412c20eaab792779]
[   33.867135]  dev_attr_show+0x43/0xc0
[   33.867147]  sysfs_kf_seq_show+0x1f1/0x3b0
[   33.867155]  seq_read_iter+0x3f8/0x1140
[   33.867173]  vfs_read+0x76c/0xc50
[   33.867198]  ksys_read+0xfb/0x1d0
[   33.867214]  do_syscall_64+0x90/0x160
...
[   33.867353] Allocated by task 378 on cpu 7 at 22.794876s:
[   33.867358]  kasan_save_stack+0x33/0x50
[   33.867364]  kasan_save_track+0x17/0x60
[   33.867367]  __kasan_kmalloc+0x87/0x90
[   33.867371]  vangogh_init_smc_tables+0x3f9/0x840 [amdgpu]
[   33.867835]  smu_sw_init+0xa32/0x1850 [amdgpu]
[   33.868299]  amdgpu_device_init+0x467b/0x8d90 [amdgpu]
[   33.868733]  amdgpu_driver_load_kms+0x19/0xf0 [amdgpu]
[   33.869167]  amdgpu_pci_probe+0x2d6/0xcd0 [amdgpu]
[   33.869608]  local_pci_probe+0xda/0x180
[   33.869614]  pci_device_probe+0x43f/0x6b0

Empirically we can confirm that the former allocates 152 bytes for the table, while the latter memsets the 168 large block.

Root cause appears that when GPU metrics tables for v2_4 parts were added it was not considered to enlarge the table to fit.

The fix in this patch is rather "brute force" and perhaps later should be done in a smarter way, by extracting and consolidating the part version to size logic to a common helper, instead of brute forcing the largest possible allocation. Nevertheless, for now this works and fixes the out of bounds write.

v2:
* Drop impossible v3_0 case. (Mario)

---
 drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

index 22737b11b1bfb..1fe020f1f4dbe 100644
@@ -242,7 +242,9 @@ static int vangogh_tables_init(struct smu_context *smu)
 		goto err0_out;
 	smu_table->metrics_time = 0;
 
-	smu_table->gpu_metrics_table_size = max(sizeof(struct gpu_metrics_v2_3), sizeof(struct gpu_metrics_v2_2));
+	smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_2);
+	smu_table->gpu_metrics_table_size = max(smu_table->gpu_metrics_table_size, sizeof(struct gpu_metrics_v2_3));
+	smu_table->gpu_metrics_table_size = max(smu_table->gpu_metrics_table_size, sizeof(struct gpu_metrics_v2_4));
 	smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL);
 	if (!smu_table->gpu_metrics_table)
 		goto err1_out;

2.43.0

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

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

From: Alex Deucher <[email protected]>

[ Upstream commit 935abb86a95def8c20dbb184ce30051db168e541 ]

The following 3 commits landed in parallel:
commit d7d2688bf4ea ("drm/amd/pm: update workload mask after the setting") commit 7a1613e47e65 ("drm/amdgpu/smu13: always apply the powersave optimization") commit 7c210ca5a2d7 ("drm/amdgpu: handle default profile on on devices without fullscreen 3D") While everything is set correctly, this caused the profile to be
reported incorrectly because both the powersave and fullscreen3d bits
were set in the mask and when the driver prints the profile, it looks
for the first bit set.

---
 drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index cb923e33fd6fc..d53e162dcd8de 100644
@@ -2485,7 +2485,7 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu,
 	DpmActivityMonitorCoeffInt_t *activity_monitor =
 		&(activity_monitor_external.DpmActivityMonitorCoeffInt);
 	int workload_type, ret = 0;
-	u32 workload_mask;
+	u32 workload_mask, selected_workload_mask;
 
 	smu->power_profile_mode = input[size];
 

@@ -2552,7 +2552,7 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu,
 	if (workload_type < 0)
 		return -EINVAL;
 
-	workload_mask = 1 << workload_type;
+	selected_workload_mask = workload_mask = 1 << workload_type;
 
 	/* Add optimizations for SMU13.0.0/10.  Reuse the power saving profile */
 	if ((amdgpu_ip_version(smu->adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 0) &&

@@ -2572,7 +2572,7 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu,
 					       workload_mask,
 					       NULL);
 	if (!ret)
-		smu->workload_mask = workload_mask;
+		smu->workload_mask = selected_workload_mask;
 
 	return ret;
 }

2.43.0

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

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

From: Jarkko Sakkinen <[email protected]>

[ Upstream commit df745e25098dcb2f706399c0d06dd8d1bab6b6ec ]

Move the allocation of chip->auth to tpm2_start_auth_session() so that this field can be used as flag to tell whether auth session is active or not.

Instead of flushing and reloading the auth session for every transaction separately, keep the session open unless /dev/tpm0 is used.

---
 drivers/char/tpm/tpm-chip.c       | 10 +++++++
 drivers/char/tpm/tpm-dev-common.c |  3 +++
 drivers/char/tpm/tpm-interface.c  |  6 +++--
 drivers/char/tpm/tpm2-sessions.c  | 45 ++++++++++++++++++-------------
 4 files changed, 44 insertions(+), 20 deletions(-)

index 854546000c92b..1ff99a7091bbb 100644
@@ -674,6 +674,16 @@ EXPORT_SYMBOL_GPL(tpm_chip_register);
  */
 void tpm_chip_unregister(struct tpm_chip *chip)
 {
+#ifdef CONFIG_TCG_TPM2_HMAC
+	int rc;
+
+	rc = tpm_try_get_ops(chip);
+	if (!rc) {
+		tpm2_end_auth_session(chip);
+		tpm_put_ops(chip);
+	}
+#endif
+
 	tpm_del_legacy_sysfs(chip);
 	if (tpm_is_hwrng_enabled(chip))
 		hwrng_unregister(&chip->hwrng);

index c3fbbf4d3db79..48ff87444f851 100644
@@ -27,6 +27,9 @@ static ssize_t tpm_dev_transmit(struct tpm_chip *chip, struct tpm_space *space,
 	struct tpm_header *header = (void *)buf;
 	ssize_t ret, len;
 
+	if (chip->flags & TPM_CHIP_FLAG_TPM2)
+		tpm2_end_auth_session(chip);
+
 	ret = tpm2_prepare_space(chip, space, buf, bufsiz);
 	/* If the command is not implemented by the TPM, synthesize a
 	 * response with a TPM2_RC_COMMAND_CODE return for user-space.

index 5da134f12c9a4..8134f002b121f 100644
@@ -379,10 +379,12 @@ int tpm_pm_suspend(struct device *dev)
 
 	rc = tpm_try_get_ops(chip);
 	if (!rc) {
-		if (chip->flags & TPM_CHIP_FLAG_TPM2)
+		if (chip->flags & TPM_CHIP_FLAG_TPM2) {
+			tpm2_end_auth_session(chip);
 			tpm2_shutdown(chip, TPM2_SU_STATE);
-		else
+		} else {
 			rc = tpm1_pm_suspend(chip, tpm_suspend_pcr);
+		}
 
 		tpm_put_ops(chip);
 	}

2.43.0

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

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

From: Matthieu Baerts (NGI0) <[email protected]>

[ Upstream commit 3deb12c788c385e17142ce6ec50f769852fcec65 ]

Enabling CONFIG_PROVE_RCU_LIST with its dependence CONFIG_RCU_EXPERT creates this splat when an MPTCP socket is created:

=============================
WARNING: suspicious RCU usage
6.12.0-rc2+ #11 Not tainted
-----------------------------
net/mptcp/sched.c:44 RCU-list traversed in non-reader section!!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
no locks held by mptcp_connect/176.

  stack backtrace:
  CPU: 0 UID: 0 PID: 176 Comm: mptcp_connect Not tainted 6.12.0-rc2+ #11
  Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  Call Trace:
   <TASK>
   dump_stack_lvl (lib/dump_stack.c:123)
   lockdep_rcu_suspicious (kernel/locking/lockdep.c:6822)
   mptcp_sched_find (net/mptcp/sched.c:44 (discriminator 7))
   mptcp_init_sock (net/mptcp/protocol.c:2867 (discriminator 1))
   ? sock_init_data_uid (arch/x86/include/asm/atomic.h:28)
   inet_create.part.0.constprop.0 (net/ipv4/af_inet.c:386)
   ? __sock_create (include/linux/rcupdate.h:347 (discriminator 1))
   __sock_create (net/socket.c:1576)
   __sys_socket (net/socket.c:1671)
   ? __pfx___sys_socket (net/socket.c:1712)
   ? do_user_addr_fault (arch/x86/mm/fault.c:1419 (discriminator 1))
   __x64_sys_socket (net/socket.c:1728)
   do_syscall_64 (arch/x86/entry/common.c:52 (discriminator 1))
   entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)

That's because when the socket is initialised, rcu_read_lock() is not used despite the explicit comment written above the declaration of mptcp_sched_find() in sched.c. Adding the missing lock/unlock avoids the warning.

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

index d4b3bc46cdaaf..ec87b36f0d451 100644
@@ -2864,8 +2864,10 @@ static int mptcp_init_sock(struct sock *sk)
 	if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net))
 		return -ENOMEM;
 
+	rcu_read_lock();
 	ret = mptcp_init_sched(mptcp_sk(sk),
 			       mptcp_sched_find(mptcp_get_scheduler(net)));
+	rcu_read_unlock();
 	if (ret)
 		return ret;
 

2.43.0

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

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

From: Alexander Usyskin <[email protected]>

[ Upstream commit 4adf613e01bf99e1739f6ff3e162ad5b7d578d1a ]

Read buffer is allocated according to max message size, reported by the firmware and may reach 64K in systems with pxp client. Contiguous 64k allocation may fail under memory pressure. Read buffer is used as in-driver message storage and not required to be contiguous.
Use kvmalloc to allow kernel to allocate non-contiguous memory.

---
 drivers/misc/mei/client.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 9d090fa07516f..be011cef12e5d 100644
@@ -321,7 +321,7 @@ void mei_io_cb_free(struct mei_cl_cb *cb)
 		return;
 
 	list_del(&cb->list);
-	kfree(cb->buf.data);
+	kvfree(cb->buf.data);
 	kfree(cb->ext_hdr);
 	kfree(cb);
 }

@@ -497,7 +497,7 @@ struct mei_cl_cb *mei_cl_alloc_cb(struct mei_cl *cl, size_t length,
 	if (length == 0)
 		return cb;
 
-	cb->buf.data = kmalloc(roundup(length, MEI_SLOT_SIZE), GFP_KERNEL);
+	cb->buf.data = kvmalloc(roundup(length, MEI_SLOT_SIZE), GFP_KERNEL);
 	if (!cb->buf.data) {
 		mei_io_cb_free(cb);
 		return NULL;

2.43.0

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

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

From: Lorenzo Stoakes <[email protected]>

[ Upstream commit 985da552a98e27096444508ce5d853244019111f ]

There is no reason to invoke these hooks early against an mm that is in an incomplete state.

The change in commit d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()") makes this more pertinent as we may be in a state where entries in the maple tree are not yet consistent.

Their placement early in dup_mmap() only appears to have been meaningful for early error checking, and since functionally it'd require a very small allocation to fail (in practice 'too small to fail') that'd only occur in the most dire circumstances, meaning the fork would fail or be OOM'd in any case.

Since both khugepaged and KSM tracking are there to provide optimisations to memory performance rather than critical functionality, it doesn't really matter all that much if, under such dire memory pressure, we fail to register an mm with these.

As a result, we follow the example of commit d2081b2bf819 ("mm:
khugepaged: make khugepaged_enter() void function") and make ksm_fork() a void function also.

We only expose the mm to these functions once we are done with them and only if no error occurred in the fork operation.

---
 include/linux/ksm.h | 10 ++++------
 kernel/fork.c       |  7 ++-----
 2 files changed, 6 insertions(+), 11 deletions(-)

index 11690dacd9868..ec9c05044d4fe 100644
@@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm)
 	return atomic_long_read(&mm->ksm_zero_pages);
 }
 
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
+	/* Adding mm to ksm is best effort on fork. */
 	if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
-		return __ksm_enter(mm);
-
-	return 0;
+		__ksm_enter(mm);
 }
 
 static inline int ksm_execve(struct mm_struct *mm)

@@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_struct *mm)
 	return 0;
 }
 
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	return 0;
 }
 
 static inline int ksm_execve(struct mm_struct *mm)

index 6423ce60b8f97..dc08a23747338 100644
@@ -653,11 +653,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	mm->exec_vm = oldmm->exec_vm;
 	mm->stack_vm = oldmm->stack_vm;
 
-	retval = ksm_fork(mm, oldmm);
-	if (retval)
-		goto out;
-	khugepaged_fork(mm, oldmm);
-
 	/* Use __mt_dup() to efficiently build an identical maple tree. */
 	retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL);
 	if (unlikely(retval))

@@ -760,6 +755,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	vma_iter_free(&vmi);
 	if (!retval) {
 		mt_set_in_rcu(vmi.mas.tree);
+		ksm_fork(mm, oldmm);
+		khugepaged_fork(mm, oldmm);
 	} else if (mpnt) {
 		/*
 		 * The entire maple tree has already been duplicated. If the

2.43.0

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

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

From: Matt Fleming <[email protected]>

[ Upstream commit 281dd25c1a018261a04d1b8bf41a0674000bfe38 ]

Under memory pressure it's possible for GFP_ATOMIC order-0 allocations to fail even though free pages are available in the highatomic reserves. GFP_ATOMIC allocations cannot trigger unreserve_highatomic_pageblock() since it's only run from reclaim.

Given that such allocations will pass the watermarks in __zone_watermark_unusable_free(), it makes sense to fallback to highatomic reserves the same way that ALLOC_OOM can.

This fixes order-0 page allocation failures observed on Cloudflare's fleet when handling network packets:

kswapd1: page allocation failure: order:0, mode:0x820(GFP_ATOMIC), nodemask=(null),cpuset=/,mems_allowed=0-7

  CPU: 10 PID: 696 Comm: kswapd1 Kdump: loaded Tainted: G           O 6.6.43-CUSTOM #1
  Hardware name: MACHINE
  Call Trace:
   <IRQ>
   dump_stack_lvl+0x3c/0x50
   warn_alloc+0x13a/0x1c0
   __alloc_pages_slowpath.constprop.0+0xc9d/0xd10
   __alloc_pages+0x327/0x340
   __napi_alloc_skb+0x16d/0x1f0
   bnxt_rx_page_skb+0x96/0x1b0 [bnxt_en]
   bnxt_rx_pkt+0x201/0x15e0 [bnxt_en]
   __bnxt_poll_work+0x156/0x2b0 [bnxt_en]
   bnxt_poll+0xd9/0x1c0 [bnxt_en]
   __napi_poll+0x2b/0x1b0
   bpf_trampoline_6442524138+0x7d/0x1000
   __napi_poll+0x5/0x1b0
   net_rx_action+0x342/0x740
   handle_softirqs+0xcf/0x2b0
   irq_exit_rcu+0x6c/0x90
   sysvec_apic_timer_interrupt+0x72/0x90
   </IRQ>

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

index 91ace8ca97e21..ec459522c2934 100644
@@ -2874,12 +2874,12 @@ struct page *rmqueue_buddy(struct zone *preferred_zone, struct zone *zone,
 			page = __rmqueue(zone, order, migratetype, alloc_flags);
 
 			/*
-			 * If the allocation fails, allow OOM handling access
-			 * to HIGHATOMIC reserves as failing now is worse than
-			 * failing a high-order atomic allocation in the
-			 * future.
+			 * If the allocation fails, allow OOM handling and
+			 * order-0 (atomic) allocs access to HIGHATOMIC
+			 * reserves as failing now is worse than failing a
+			 * high-order atomic allocation in the future.
 			 */
-			if (!page && (alloc_flags & ALLOC_OOM))
+			if (!page && (alloc_flags & (ALLOC_OOM|ALLOC_NON_BLOCK)))
 				page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
 
 			if (!page) {

2.43.0

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

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

From: Gatlin Newhouse <[email protected]>

[ Upstream commit 7424fc6b86c8980a87169e005f5cd4438d18efe6 ]

Currently ARM64 extracts which specific sanitizer has caused a trap via encoded data in the trap instruction. Clang on x86 currently encodes the same data in the UD1 instruction but x86 handle_bug() and is_valid_bugaddr() currently only look at UD2.

Bring x86 to parity with ARM64, similar to commit 25b84002afb9 ("arm64:
Support Clang UBSAN trap codes for better reporting"). See the llvm links for information about the code generation.

Enable the reporting of UBSAN sanitizer details on x86 compiled with clang when CONFIG_UBSAN_TRAP=y by analysing UD1 and retrieving the type immediate which is encoded by the compiler after the UD1.

[ tglx: Simplified it by moving the printk() into handle_bug() ]

Stable-dep-of: 1db272864ff2 ("x86/traps: move kmsan check after instrumentation_begin")

---
 arch/x86/include/asm/bug.h | 12 ++++++++
 arch/x86/kernel/traps.c    | 59 ++++++++++++++++++++++++++++++++++----
 include/linux/ubsan.h      |  5 ++++
 lib/Kconfig.ubsan          |  4 +--
 4 files changed, 73 insertions(+), 7 deletions(-)

index a3ec87d198ac8..806649c7f23dc 100644
@@ -13,6 +13,18 @@
 #define INSN_UD2	0x0b0f
 #define LEN_UD2		2
 
+/*
+ * In clang we have UD1s reporting UBSAN failures on X86, 64 and 32bit.
+ */
+#define INSN_ASOP		0x67
+#define OPCODE_ESCAPE		0x0f
+#define SECOND_BYTE_OPCODE_UD1	0xb9
+#define SECOND_BYTE_OPCODE_UD2	0x0b
+
+#define BUG_NONE		0xffff
+#define BUG_UD1			0xfffe
+#define BUG_UD2			0xfffd
+
 #ifdef CONFIG_GENERIC_BUG
 
 #ifdef CONFIG_X86_32

index bff7445498ded..d8219cbe09ff8 100644
@@ -4,6 +4,11 @@
 
 #ifdef CONFIG_UBSAN_TRAP
 const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type);
+#else
+static inline const char *report_ubsan_failure(struct pt_regs *regs, u32 check_type)
+{
+	return NULL;
+}
 #endif
 
 #endif

index bdda600f8dfbe..1d4aa7a83b3a5 100644
@@ -29,8 +29,8 @@ config UBSAN_TRAP
 
 	  Also note that selecting Y will cause your kernel to Oops
 	  with an "illegal instruction" error with no further details
-	  when a UBSAN violation occurs. (Except on arm64, which will
-	  report which Sanitizer failed.) This may make it hard to
+	  when a UBSAN violation occurs. (Except on arm64 and x86, which
+	  will report which Sanitizer failed.) This may make it hard to
 	  determine whether an Oops was caused by UBSAN or to figure
 	  out the details of a UBSAN violation. It makes the kernel log
 	  output less useful for bug reports.

2.43.0

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

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

From: Sabyrzhan Tasbolatov <[email protected]>

[ Upstream commit 1db272864ff250b5e607283eaec819e1186c8e26 ]

During x86_64 kernel build with CONFIG_KMSAN, the objtool warns following:

  AR      built-in.a
  AR      vmlinux.a
  LD      vmlinux.o

vmlinux.o: warning: objtool: handle_bug+0x4: call to
kmsan_unpoison_entry_regs() leaves .noinstr.text section
OBJCOPY modules.builtin.modinfo
GEN modules.builtin
MODPOST Module.symvers
CC .vmlinux.export.o

Moving kmsan_unpoison_entry_regs() _after_ instrumentation_begin() fixes the warning.

There is decode_bug(regs->ip, &imm) is left before KMSAN unpoisoining, but it has the return condition and if we include it after instrumentation_begin() it results the warning "return with instrumentation enabled", hence, I'm concerned that regs will not be KMSAN unpoisoned if ud_type == BUG_NONE is true.

---
 arch/x86/kernel/traps.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

index 415881607c5df..29ec49209ae01 100644
@@ -261,12 +261,6 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	int ud_type;
 	u32 imm;
 
-	/*
-	 * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug()
-	 * is a rare case that uses @regs without passing them to
-	 * irqentry_enter().
-	 */
-	kmsan_unpoison_entry_regs(regs);
 	ud_type = decode_bug(regs->ip, &imm);
 	if (ud_type == BUG_NONE)
 		return handled;

@@ -275,6 +269,12 @@ static noinstr bool handle_bug(struct pt_regs *regs)
 	 * All lies, just get the WARN/BUG out.
 	 */
 	instrumentation_begin();
+	/*
+	 * Normally @regs are unpoisoned by irqentry_enter(), but handle_bug()
+	 * is a rare case that uses @regs without passing them to
+	 * irqentry_enter().
+	 */
+	kmsan_unpoison_entry_regs(regs);
 	/*
 	 * Since we're emulating a CALL with exceptions, restore the interrupt
 	 * state to what it was at the exception site.

2.43.0

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

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

From: Edward Adam Davis <[email protected]>

[ Upstream commit bc0a2f3a73fcdac651fca64df39306d1e5ebe3b0 ]

Syzbot reported a kernel BUG in ocfs2_truncate_inline. There are two reasons for this: first, the parameter value passed is greater than ocfs2_max_inline_data_with_xattr, second, the start and end parameters of ocfs2_truncate_inline are "unsigned int".

So, we need to add a sanity check for byte_start and byte_len right before ocfs2_truncate_inline() in ocfs2_remove_inode_range(), if they are greater than ocfs2_max_inline_data_with_xattr return -EINVAL.

---
 fs/ocfs2/file.c | 8 ++++++++
 1 file changed, 8 insertions(+)

index ccc57038a9779..02d2beb7ddb95 100644
@@ -1783,6 +1783,14 @@ int ocfs2_remove_inode_range(struct inode *inode,
 		return 0;
 
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		int id_count = ocfs2_max_inline_data_with_xattr(inode->i_sb, di);
+
+		if (byte_start > id_count || byte_start + byte_len > id_count) {
+			ret = -EINVAL;
+			mlog_errno(ret);
+			goto out;
+		}
+
 		ret = ocfs2_truncate_inline(inode, di_bh, byte_start,
 					    byte_start + byte_len, 0);
 		if (ret) {

2.43.0

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

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

From: Gregory Price <[email protected]>

[ Upstream commit b125a0def25a082ae944c9615208bf359abdb61c ]

walk_system_ram_res_rev() erroneously discards resource flags when passing the information to the callback.

This causes systems with IORESOURCE_SYSRAM_DRIVER_MANAGED memory to have these resources selected during kexec to store kexec buffers if that memory happens to be at placed above normal system ram.

This leads to undefined behavior after reboot. If the kexec buffer is never touched, nothing happens. If the kexec buffer is touched, it could lead to a crash (like below) or undefined behavior.

Tested on a system with CXL memory expanders with driver managed memory, TPM enabled, and CONFIG_IMA_KEXEC=y. Adding printk's showed the flags were being discarded and as a result the check for IORESOURCE_SYSRAM_DRIVER_MANAGED passes.

find_next_iomem_res: name(System RAM (kmem))

		     start(10000000000)
		     end(1034fffffff)
		     flags(83000200)

locate_mem_hole_top_down: start(10000000000) end(1034fffffff) flags(0)

[.] BUG: unable to handle page fault for address: ffff89834ffff000 [.] #PF: supervisor read access in kernel mode
[.] #PF: error_code(0x0000) - not-present page
[.] PGD c04c8bf067 P4D c04c8bf067 PUD c04c8be067 PMD 0
[.] Oops: 0000 [#1] SMP
[.] RIP: 0010:ima_restore_measurement_list+0x95/0x4b0
[.] RSP: 0018:ffffc900000d3a80 EFLAGS: 00010286
[.] RAX: 0000000000001000 RBX: 0000000000000000 RCX: ffff89834ffff000 [.] RDX: 0000000000000018 RSI: ffff89834ffff000 RDI: ffff89834ffff018 [.] RBP: ffffc900000d3ba0 R08: 0000000000000020 R09: ffff888132b8a900 [.] R10: 4000000000000000 R11: 000000003a616d69 R12: 0000000000000000 [.] R13: ffffffff8404ac28 R14: 0000000000000000 R15: ffff89834ffff000 [.] FS: 0000000000000000(0000) GS:ffff893d44640000(0000) knlGS:0000000000000000 [.] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[.] ata5: SATA link down (SStatus 0 SControl 300)
[.] CR2: ffff89834ffff000 CR3: 000001034d00f001 CR4: 0000000000770ef0 [.] PKRU: 55555554
[.] Call Trace:

[.]  <TASK>
[.]  ? __die+0x78/0xc0
[.]  ? page_fault_oops+0x2a8/0x3a0
[.]  ? exc_page_fault+0x84/0x130
[.]  ? asm_exc_page_fault+0x22/0x30
[.]  ? ima_restore_measurement_list+0x95/0x4b0
[.]  ? template_desc_init_fields+0x317/0x410
[.]  ? crypto_alloc_tfm_node+0x9c/0xc0
[.]  ? init_ima_lsm+0x30/0x30
[.]  ima_load_kexec_buffer+0x72/0xa0
[.]  ima_init+0x44/0xa0
[.]  __initstub__kmod_ima__373_1201_init_ima7+0x1e/0xb0
[.]  ? init_ima_lsm+0x30/0x30
[.]  do_one_initcall+0xad/0x200
[.]  ? idr_alloc_cyclic+0xaa/0x110
[.]  ? new_slab+0x12c/0x420
[.]  ? new_slab+0x12c/0x420
[.]  ? number+0x12a/0x430
[.]  ? sysvec_apic_timer_interrupt+0xa/0x80
[.]  ? asm_sysvec_apic_timer_interrupt+0x16/0x20
[.]  ? parse_args+0xd4/0x380
[.]  ? parse_args+0x14b/0x380
[.]  kernel_init_freeable+0x1c1/0x2b0
[.]  ? rest_init+0xb0/0xb0
[.]  kernel_init+0x16/0x1a0
[.]  ret_from_fork+0x2f/0x40
[.]  ? rest_init+0xb0/0xb0
[.]  ret_from_fork_asm+0x11/0x20
[.]  </TASK>

---
 kernel/resource.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

index 1681ab5012e12..4f3df25176caa 100644
@@ -460,9 +460,7 @@ int walk_system_ram_res_rev(u64 start, u64 end, void *arg,
 			rams_size += 16;
 		}
 
-		rams[i].start = res.start;
-		rams[i++].end = res.end;
-
+		rams[i++] = res;
 		start = res.end + 1;
 	}
 

2.43.0

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

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

From: Matt Johnston <[email protected]>

[ Upstream commit 01e215975fd80af81b5b79f009d49ddd35976c13 ]

daddr can be NULL if there is no neighbour table entry present, in that case the tx packet should be dropped.

saddr will usually be set by MCTP core, but check for NULL in case a packet is transmitted by a different protocol.

---
 drivers/net/mctp/mctp-i2c.c | 3 +++
 1 file changed, 3 insertions(+)

index 4dc057c121f5d..e70fb66879941 100644
@@ -588,6 +588,9 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev,
 	if (len > MCTP_I2C_MAXMTU)
 		return -EMSGSIZE;
 
+	if (!daddr || !saddr)
+		return -EINVAL;
+
 	lldst = *((u8 *)daddr);
 	llsrc = *((u8 *)saddr);
 

2.43.0

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

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

From: Zhihao Cheng <[email protected]>

[ Upstream commit aec8e6bf839101784f3ef037dcdb9432c3f32343 ]

Mounting btrfs from two images (which have the same one fsid and two different dev_uuids) in certain executing order may trigger an UAF for variable 'device->bdev_file' in __btrfs_free_extra_devids(). And following are the details:

1. Attach image_1 to loop0, attach image_2 to loop1, and scan btrfs devices by ioctl(BTRFS_IOC_SCAN_DEV):

/ btrfs_device_1 → loop0
fs_device
\ btrfs_device_2 → loop1
2. mount /dev/loop0 /mnt
btrfs_open_devices

    btrfs_device_1->bdev_file = btrfs_get_bdev_and_sb(loop0)
    btrfs_device_2->bdev_file = btrfs_get_bdev_and_sb(loop1)
   btrfs_fill_super
    open_ctree
     fail: btrfs_close_devices // -ENOMEM
	    btrfs_close_bdev(btrfs_device_1)
             fput(btrfs_device_1->bdev_file)
	      // btrfs_device_1->bdev_file is freed
	    btrfs_close_bdev(btrfs_device_2)
             fput(btrfs_device_2->bdev_file)

3. mount /dev/loop1 /mnt
btrfs_open_devices

    btrfs_get_bdev_and_sb(&bdev_file)
     // EIO, btrfs_device_1->bdev_file is not assigned,
     // which points to a freed memory area
    btrfs_device_2->bdev_file = btrfs_get_bdev_and_sb(loop1)
   btrfs_fill_super
    open_ctree
     btrfs_free_extra_devids
      if (btrfs_device_1->bdev_file)
       fput(btrfs_device_1->bdev_file) // UAF !

Fix it by setting 'device->bdev_file' as 'NULL' after closing the btrfs_device in btrfs_close_one_device().

---
 fs/btrfs/volumes.c | 1 +
 1 file changed, 1 insertion(+)

index fcedc43ef291a..0485143cd75e0 100644
@@ -1103,6 +1103,7 @@ static void btrfs_close_one_device(struct btrfs_device *device)
 	if (device->bdev) {
 		fs_devices->open_devices--;
 		device->bdev = NULL;
+		device->bdev_file = NULL;
 	}
 	clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
 	btrfs_destroy_dev_zone_info(device);

2.43.0

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

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

From: Andrzej Kacprowski <[email protected]>

[ Upstream commit 72f7e16eccddde99386a10eb2d08833e805917c6 ]

The NOC firewall interrupt means that the HW prevented unauthorized access to a protected resource, so there is no need to trigger device reset in such case.

To facilitate security testing add firewall_irq_counter debugfs file that tracks firewall interrupts.

---
 drivers/accel/ivpu/ivpu_debugfs.c | 9 +++++++++
 drivers/accel/ivpu/ivpu_hw.c      | 1 +
 drivers/accel/ivpu/ivpu_hw.h      | 1 +
 drivers/accel/ivpu/ivpu_hw_ip.c   | 5 ++++-
 4 files changed, 15 insertions(+), 1 deletion(-)

index 6f86f8df30db0..8d50981594d15 100644
@@ -108,6 +108,14 @@ static int reset_pending_show(struct seq_file *s, void *v)
 	return 0;
 }
 
+static int firewall_irq_counter_show(struct seq_file *s, void *v)
+{
+	struct ivpu_device *vdev = seq_to_ivpu(s);
+
+	seq_printf(s, "%d\n", atomic_read(&vdev->hw->firewall_irq_counter));
+	return 0;
+}
+
 static const struct drm_debugfs_info vdev_debugfs_list[] = {
 	{"bo_list", bo_list_show, 0},
 	{"fw_name", fw_name_show, 0},

@@ -116,6 +124,7 @@ static const struct drm_debugfs_info vdev_debugfs_list[] = {
 	{"last_bootmode", last_bootmode_show, 0},
 	{"reset_counter", reset_counter_show, 0},
 	{"reset_pending", reset_pending_show, 0},
+	{"firewall_irq_counter", firewall_irq_counter_show, 0},
 };
 
 static ssize_t

index 27f0fe4d54e00..e69c0613513f1 100644
@@ -249,6 +249,7 @@ int ivpu_hw_init(struct ivpu_device *vdev)
 	platform_init(vdev);
 	wa_init(vdev);
 	timeouts_init(vdev);
+	atomic_set(&vdev->hw->firewall_irq_counter, 0);
 
 	return 0;
 }

index 1c0c98e3afb88..a96a05b2acda9 100644
@@ -52,6 +52,7 @@ struct ivpu_hw_info {
 	int dma_bits;
 	ktime_t d0i3_entry_host_ts;
 	u64 d0i3_entry_vpu_ts;
+	atomic_t firewall_irq_counter;
 };
 
 int ivpu_hw_init(struct ivpu_device *vdev);

index dfd2f4a5b5268..60b33fc59d96e 100644
@@ -1062,7 +1062,10 @@ static void irq_wdt_mss_handler(struct ivpu_device *vdev)
 
 static void irq_noc_firewall_handler(struct ivpu_device *vdev)
 {
-	ivpu_pm_trigger_recovery(vdev, "NOC Firewall IRQ");
+	atomic_inc(&vdev->hw->firewall_irq_counter);
+
+	ivpu_dbg(vdev, IRQ, "NOC Firewall interrupt detected, counter %d\n",
+		 atomic_read(&vdev->hw->firewall_irq_counter));
 }
 
 /* Handler for IRQs from NPU core */

2.43.0

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

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

From: Christoph Hellwig <[email protected]>

[ Upstream commit dc60992ce76fbc2f71c2674f435ff6bde2108028 ]

When the main loop in xfs_filestream_pick_ag fails to find a suitable AG it tries to just pick the online AG. But the loop for that uses args->pag as loop iterator while the later code expects pag to be set. Fix this by reusing the max_pag case for this last resort, and also add a check for impossible case of no AG just to make sure that the uninitialized pag doesn't even escape in theory.

---
 fs/xfs/xfs_filestream.c | 23 ++++++++++++-----------
 fs/xfs/xfs_trace.h      | 15 +++++----------
 2 files changed, 17 insertions(+), 21 deletions(-)

index e3aaa05555978..88bd23ce74cde 100644
@@ -64,7 +64,7 @@ xfs_filestream_pick_ag(
 	struct xfs_perag	*pag;
 	struct xfs_perag	*max_pag = NULL;
 	xfs_extlen_t		minlen = *longest;
-	xfs_extlen_t		free = 0, minfree, maxfree = 0;
+	xfs_extlen_t		minfree, maxfree = 0;
 	xfs_agnumber_t		agno;
 	bool			first_pass = true;
 	int			err;

@@ -107,7 +107,6 @@ xfs_filestream_pick_ag(
 			     !(flags & XFS_PICK_USERDATA) ||
 			     (flags & XFS_PICK_LOWSPACE))) {
 				/* Break out, retaining the reference on the AG. */
-				free = pag->pagf_freeblks;
 				break;
 			}
 		}

@@ -150,23 +149,25 @@ xfs_filestream_pick_ag(
 		 * grab.
 		 */
 		if (!max_pag) {
-			for_each_perag_wrap(args->mp, 0, start_agno, args->pag)
+			for_each_perag_wrap(args->mp, 0, start_agno, pag) {
+				max_pag = pag;
 				break;
-			atomic_inc(&args->pag->pagf_fstrms);
-			*longest = 0;
-		} else {
-			pag = max_pag;
-			free = maxfree;
-			atomic_inc(&pag->pagf_fstrms);
+			}
+
+			/* Bail if there are no AGs at all to select from. */
+			if (!max_pag)
+				return -ENOSPC;
 		}
+
+		pag = max_pag;
+		atomic_inc(&pag->pagf_fstrms);
 	} else if (max_pag) {
 		xfs_perag_rele(max_pag);
 	}
 
-	trace_xfs_filestream_pick(pag, pino, free);
+	trace_xfs_filestream_pick(pag, pino);
 	args->pag = pag;
 	return 0;
-
 }
 
 static struct xfs_inode *

index 180ce697305a9..f681a195a7441 100644
@@ -691,8 +691,8 @@ DEFINE_FILESTREAM_EVENT(xfs_filestream_lookup);
 DEFINE_FILESTREAM_EVENT(xfs_filestream_scan);
 
 TRACE_EVENT(xfs_filestream_pick,
-	TP_PROTO(struct xfs_perag *pag, xfs_ino_t ino, xfs_extlen_t free),
-	TP_ARGS(pag, ino, free),
+	TP_PROTO(struct xfs_perag *pag, xfs_ino_t ino),
+	TP_ARGS(pag, ino),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_ino_t, ino)

@@ -703,14 +703,9 @@ TRACE_EVENT(xfs_filestream_pick,
 	TP_fast_assign(
 		__entry->dev = pag->pag_mount->m_super->s_dev;
 		__entry->ino = ino;
-		if (pag) {
-			__entry->agno = pag->pag_agno;
-			__entry->streams = atomic_read(&pag->pagf_fstrms);
-		} else {
-			__entry->agno = NULLAGNUMBER;
-			__entry->streams = 0;
-		}
-		__entry->free = free;
+		__entry->agno = pag->pag_agno;
+		__entry->streams = atomic_read(&pag->pagf_fstrms);
+		__entry->free = pag->pagf_freeblks;
 	),
 	TP_printk("dev %d:%d ino 0x%llx agno 0x%x streams %d free %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),

2.43.0

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

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

From: Christoffer Sandberg <[email protected]>

[ Upstream commit 0b04fbe886b4274c8e5855011233aaa69fec6e75 ]

Quirk is needed to enable headset microphone on missing pin 0x19.

---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

index 8d6f446d507c2..25d4c417d3c07 100644
@@ -10729,6 +10729,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x1404, "Clevo N150CU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x14a1, "Clevo L141MU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x2624, "Clevo L240TU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1558, 0x28c1, "Clevo V370VND", ALC2XX_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1558, 0x4018, "Clevo NV40M[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x4019, "Clevo NV40MZ", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1558, 0x4020, "Clevo NV40MB", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),

2.43.0

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

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

From: Christoffer Sandberg <[email protected]>

[ Upstream commit e49370d769e71456db3fbd982e95bab8c69f73e8 ]

Quirk is needed to enable headset microphone on missing pin 0x19.

---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

index 25d4c417d3c07..660fd984a9285 100644
@@ -10971,6 +10971,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP),
 	SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP),
 	SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1d05, 0x1409, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d17, 0x3288, "Haier Boyue G42", ALC269VC_FIXUP_ACER_VCOPPERBOX_PINS),
 	SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE),

2.43.0

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

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

From: Vitaliy Shevtsov <[email protected]>

[ Upstream commit d2f551b1f72b4c508ab9298419f6feadc3b5d791 ]

ctrl->dh_key might be used across multiple calls to nvmet_setup_dhgroup() for the same controller. So it's better to nullify it after release on error path in order to avoid double free later in nvmet_destroy_auth().

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

---
 drivers/nvme/target/auth.c | 1 +
 1 file changed, 1 insertion(+)

index 8bc3f431c77f6..8c41a47dfed17 100644
@@ -103,6 +103,7 @@ int nvmet_setup_dhgroup(struct nvmet_ctrl *ctrl, u8 dhgroup_id)
 			pr_debug("%s: ctrl %d failed to generate private key, err %d\n",
 				 __func__, ctrl->cntlid, ret);
 			kfree_sensitive(ctrl->dh_key);
+			ctrl->dh_key = NULL;
 			return ret;
 		}
 		ctrl->dh_keysize = crypto_kpp_maxsize(ctrl->dh_tfm);

2.43.0

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

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

From: Keith Busch <[email protected]>

[ Upstream commit 5eed4fb274cd6579f2fb4190b11c4c86c553cd06 ]

This was previously fixed with commit 1147dd0503564fa0e0348 ("nvme: fix error-handling for io_uring nvme-passthrough"), but the change was mistakenly undone in a later commit.

---
 drivers/nvme/host/ioctl.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

index 15c93ce07e263..2cb35c4528a93 100644
@@ -423,10 +423,13 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	struct io_uring_cmd *ioucmd = req->end_io_data;
 	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
 
-	if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+	if (nvme_req(req)->flags & NVME_REQ_CANCELLED) {
 		pdu->status = -EINTR;
-	else
+	} else {
 		pdu->status = nvme_req(req)->status;
+		if (!pdu->status)
+			pdu->status = blk_status_to_errno(err);
+	}
 	pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*

2.43.0

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

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

From: Andrey Konovalov <[email protected]>

[ Upstream commit 330d8df81f3673d6fb74550bbc9bb159d81b35f7 ]

Commit 1a2473f0cbc0 ("kasan: improve vmalloc tests") added the vmalloc_percpu KASAN test with the assumption that __alloc_percpu always uses vmalloc internally, which is tagged by KASAN.

However, __alloc_percpu might allocate memory from the first per-CPU chunk, which is not allocated via vmalloc(). As a result, the test might fail.

Remove the test until proper KASAN annotation for the per-CPU allocated are added; tracked in https://bugzilla.kernel.org/show_bug.cgi?id=215019.

---
 mm/kasan/kasan_test.c | 27 ---------------------------
 1 file changed, 27 deletions(-)

index 7b32be2a3cf0e..9efde47f80698 100644
@@ -1765,32 +1765,6 @@ static void vm_map_ram_tags(struct kunit *test)
 	free_pages((unsigned long)p_ptr, 1);
 }
 
-static void vmalloc_percpu(struct kunit *test)
-{
-	char __percpu *ptr;
-	int cpu;
-
-	/*
-	 * This test is specifically crafted for the software tag-based mode,
-	 * the only tag-based mode that poisons percpu mappings.
-	 */
-	KASAN_TEST_NEEDS_CONFIG_ON(test, CONFIG_KASAN_SW_TAGS);
-
-	ptr = __alloc_percpu(PAGE_SIZE, PAGE_SIZE);
-
-	for_each_possible_cpu(cpu) {
-		char *c_ptr = per_cpu_ptr(ptr, cpu);
-
-		KUNIT_EXPECT_GE(test, (u8)get_tag(c_ptr), (u8)KASAN_TAG_MIN);
-		KUNIT_EXPECT_LT(test, (u8)get_tag(c_ptr), (u8)KASAN_TAG_KERNEL);
-
-		/* Make sure that in-bounds accesses don't crash the kernel. */
-		*c_ptr = 0;
-	}
-
-	free_percpu(ptr);
-}
-
 /*
  * Check that the assigned pointer tag falls within the [KASAN_TAG_MIN,
  * KASAN_TAG_KERNEL) range (note: excluding the match-all tag) for tag-based

@@ -1967,7 +1941,6 @@ static struct kunit_case kasan_kunit_test_cases[] = {
 	KUNIT_CASE(vmalloc_oob),
 	KUNIT_CASE(vmap_tags),
 	KUNIT_CASE(vm_map_ram_tags),
-	KUNIT_CASE(vmalloc_percpu),
 	KUNIT_CASE(match_all_not_assigned),
 	KUNIT_CASE(match_all_ptr_tag),
 	KUNIT_CASE(match_all_mem_tag),

2.43.0

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

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

From: Jinjie Ruan <[email protected]>

[ Upstream commit caa714f86699bcfb01aa2d698db12d91af7d0d81 ]

As Maxime suggested, add a new helper drm_kunit_display_mode_from_cea_vic(), it can replace the direct call of drm_display_mode_from_cea_vic(), and it will help solving the mode memory leaks.

Stable-dep-of: 926163342a2e ("drm/connector: hdmi: Fix memory leak in drm_display_mode_from_cea_vic()")

---
 drivers/gpu/drm/tests/drm_kunit_helpers.c | 42 +++++++++++++++++++++++
 include/drm/drm_kunit_helpers.h           |  4 +++
 2 files changed, 46 insertions(+)

index aa62719dab0e4..04a6b8cc62ac6 100644
@@ -3,6 +3,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_drv.h>
+#include <drm/drm_edid.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_kunit_helpers.h>
 #include <drm/drm_managed.h>

@@ -311,6 +312,47 @@ drm_kunit_helper_create_crtc(struct kunit *test,
 }
 EXPORT_SYMBOL_GPL(drm_kunit_helper_create_crtc);
 
+static void kunit_action_drm_mode_destroy(void *ptr)
+{
+	struct drm_display_mode *mode = ptr;
+
+	drm_mode_destroy(NULL, mode);
+}
+
+/**
+ * drm_kunit_display_mode_from_cea_vic() - return a mode for CEA VIC
+					   for a KUnit test
+ * @test: The test context object
+ * @dev: DRM device
+ * @video_code: CEA VIC of the mode
+ *
+ * Creates a new mode matching the specified CEA VIC for a KUnit test.
+ *
+ * Resources will be cleaned up automatically.
+ *
+ * Returns: A new drm_display_mode on success or NULL on failure
+ */
+struct drm_display_mode *
+drm_kunit_display_mode_from_cea_vic(struct kunit *test, struct drm_device *dev,
+				    u8 video_code)
+{
+	struct drm_display_mode *mode;
+	int ret;
+
+	mode = drm_display_mode_from_cea_vic(dev, video_code);
+	if (!mode)
+		return NULL;
+
+	ret = kunit_add_action_or_reset(test,
+					kunit_action_drm_mode_destroy,
+					mode);
+	if (ret)
+		return NULL;
+
+	return mode;
+}
+EXPORT_SYMBOL_GPL(drm_kunit_display_mode_from_cea_vic);
+
 MODULE_AUTHOR("Maxime Ripard <[email protected]>");
 MODULE_DESCRIPTION("KUnit test suite helper functions");
 MODULE_LICENSE("GPL");

index e7cc17ee4934a..afdd46ef04f70 100644
@@ -120,4 +120,8 @@ drm_kunit_helper_create_crtc(struct kunit *test,
 			     const struct drm_crtc_funcs *funcs,
 			     const struct drm_crtc_helper_funcs *helper_funcs);
 
+struct drm_display_mode *
+drm_kunit_display_mode_from_cea_vic(struct kunit *test, struct drm_device *dev,
+				    u8 video_code);
+
 #endif // DRM_KUNIT_HELPERS_H_

2.43.0

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

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

From: Jinjie Ruan <[email protected]>

[ Upstream commit 926163342a2e7595d950e84c17c693b1272bd491 ]

modprobe drm_connector_test and then rmmod drm_connector_test, the following memory leak occurs.

The mode allocated in drm_mode_duplicate() called by drm_display_mode_from_cea_vic() is not freed, which cause the memory leak:

	unreferenced object 0xffffff80cb0ee400 (size 128):
	  comm "kunit_try_catch", pid 1948, jiffies 4294950339
	  hex dump (first 32 bytes):
	    14 44 02 00 80 07 d8 07 04 08 98 08 00 00 38 04  .D............8.
	    3c 04 41 04 65 04 00 00 05 00 00 00 00 00 00 00  <.A.e...........
	  backtrace (crc 90e9585c):
	    [<00000000ec42e3d7>] kmemleak_alloc+0x34/0x40
	    [<00000000d0ef055a>] __kmalloc_cache_noprof+0x26c/0x2f4
	    [<00000000c2062161>] drm_mode_duplicate+0x44/0x19c
	    [<00000000f96c74aa>] drm_display_mode_from_cea_vic+0x88/0x98
	    [<00000000d8f2c8b4>] 0xffffffdc982a4868
	    [<000000005d164dbc>] kunit_try_run_case+0x13c/0x3ac
	    [<000000006fb23398>] kunit_generic_run_threadfn_adapter+0x80/0xec
	    [<000000006ea56ca0>] kthread+0x2e8/0x374
	    [<000000000676063f>] ret_from_fork+0x10/0x20
	......

Free mode by using drm_kunit_display_mode_from_cea_vic() to fix it.

---
 drivers/gpu/drm/tests/drm_connector_test.c | 24 +++++++++++-----------
 1 file changed, 12 insertions(+), 12 deletions(-)

index 15e36a8db6858..6bba97d0be88e 100644
@@ -996,7 +996,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb(struct kunit *test)
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);

@@ -1017,7 +1017,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_10bpc(struct kunit *test)
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);

@@ -1038,7 +1038,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_10bpc_vic_1(struct kunit *t
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 1);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	rate = drm_hdmi_compute_mode_clock(mode, 10, HDMI_COLORSPACE_RGB);

@@ -1056,7 +1056,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_12bpc(struct kunit *test)
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);

@@ -1077,7 +1077,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_12bpc_vic_1(struct kunit *t
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 1);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	rate = drm_hdmi_compute_mode_clock(mode, 12, HDMI_COLORSPACE_RGB);

@@ -1095,7 +1095,7 @@ static void drm_test_drm_hdmi_compute_mode_clock_rgb_double(struct kunit *test)
 	unsigned long long rate;
 	struct drm_device *drm = &priv->drm;
 
-	mode = drm_display_mode_from_cea_vic(drm, 6);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 6);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_TRUE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);

@@ -1118,7 +1118,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv420_valid(struct kunit
 	unsigned long long rate;
 	unsigned int vic = *(unsigned int *)test->param_value;
 
-	mode = drm_display_mode_from_cea_vic(drm, vic);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, vic);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);

@@ -1155,7 +1155,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv420_10_bpc(struct kuni
 		drm_hdmi_compute_mode_clock_yuv420_vic_valid_tests[0];
 	unsigned long long rate;
 
-	mode = drm_display_mode_from_cea_vic(drm, vic);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, vic);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);

@@ -1180,7 +1180,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv420_12_bpc(struct kuni
 		drm_hdmi_compute_mode_clock_yuv420_vic_valid_tests[0];
 	unsigned long long rate;
 
-	mode = drm_display_mode_from_cea_vic(drm, vic);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, vic);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);

@@ -1203,7 +1203,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv422_8_bpc(struct kunit
 	struct drm_device *drm = &priv->drm;
 	unsigned long long rate;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);

@@ -1225,7 +1225,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv422_10_bpc(struct kuni
 	struct drm_device *drm = &priv->drm;
 	unsigned long long rate;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);

@@ -1247,7 +1247,7 @@ static void drm_test_connector_hdmi_compute_mode_clock_yuv422_12_bpc(struct kuni
 	struct drm_device *drm = &priv->drm;
 	unsigned long long rate;
 
-	mode = drm_display_mode_from_cea_vic(drm, 16);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 16);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	KUNIT_ASSERT_FALSE(test, mode->flags & DRM_MODE_FLAG_DBLCLK);

2.43.0

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

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

From: Jinjie Ruan <[email protected]>

[ Upstream commit add4163aca0d4a86e9fe4aa513865e4237db8aef ]

modprobe drm_hdmi_state_helper_test and then rmmod it, the following memory leak occurs.

The mode allocated in drm_mode_duplicate() called by drm_display_mode_from_cea_vic() is not freed, which cause the memory leak:

	unreferenced object 0xffffff80ccd18100 (size 128):
	  comm "kunit_try_catch", pid 1851, jiffies 4295059695
	  hex dump (first 32 bytes):
	    57 62 00 00 80 02 90 02 f0 02 20 03 00 00 e0 01  Wb........ .....
	    ea 01 ec 01 0d 02 00 00 0a 00 00 00 00 00 00 00  ................
	  backtrace (crc c2f1aa95):
	    [<000000000f10b11b>] kmemleak_alloc+0x34/0x40
	    [<000000001cd4cf73>] __kmalloc_cache_noprof+0x26c/0x2f4
	    [<00000000f1f3cffa>] drm_mode_duplicate+0x44/0x19c
	    [<000000008cbeef13>] drm_display_mode_from_cea_vic+0x88/0x98
	    [<0000000019daaacf>] 0xffffffedc11ae69c
	    [<000000000aad0f85>] kunit_try_run_case+0x13c/0x3ac
	    [<00000000a9210bac>] kunit_generic_run_threadfn_adapter+0x80/0xec
	    [<000000000a0b2e9e>] kthread+0x2e8/0x374
	    [<00000000bd668858>] ret_from_fork+0x10/0x20
	......

Free mode by using drm_kunit_display_mode_from_cea_vic() to fix it.

---
 drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

index 34ee95d41f296..294773342e710 100644
@@ -441,7 +441,7 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode_vic_1(struct kunit *test)
 	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
 
-	mode = drm_display_mode_from_cea_vic(drm, 1);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	drm = &priv->drm;

@@ -555,7 +555,7 @@ static void drm_test_check_broadcast_rgb_full_cea_mode_vic_1(struct kunit *test)
 	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
 
-	mode = drm_display_mode_from_cea_vic(drm, 1);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	drm = &priv->drm;

@@ -671,7 +671,7 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode_vic_1(struct kunit *te
 	ctx = drm_kunit_helper_acquire_ctx_alloc(test);
 	KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx);
 
-	mode = drm_display_mode_from_cea_vic(drm, 1);
+	mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1);
 	KUNIT_ASSERT_NOT_NULL(test, mode);
 
 	drm = &priv->drm;