5.4.300-rc1 review

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

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

From: Mathias Nyman <[email protected]>

commit 9bd9c8026341f75f25c53104eb7e656e357ca1a2 upstream.

Delayed work that prevents USB3 hubs from runtime-suspending too early needed to be flushed in hub_quiesce() to resolve issues detected on QC SC8280XP CRD board during suspend resume testing.

This flushing did however trigger new issues on Raspberry Pi 3B+, which doesn't have USB3 ports, and doesn't queue any post resume delayed work.

The flushed 'hub->init_work' item is used for several purposes, and is originally initialized with a 'NULL' work function. The work function is also changed on the fly, which may contribute to the issue.

Solve this by creating a dedicated delayed work item for post resume work, and flush that delayed work in hub_quiesce()

---
 drivers/usb/core/hub.c |   21 ++++++++-------------
 drivers/usb/core/hub.h |    1 +
 2 files changed, 9 insertions(+), 13 deletions(-)

@@ -1030,12 +1030,11 @@ int usb_remove_device(struct usb_device
 
 enum hub_activation_type {
 	HUB_INIT, HUB_INIT2, HUB_INIT3,		/* INITs must come first */
-	HUB_POST_RESET, HUB_RESUME, HUB_RESET_RESUME, HUB_POST_RESUME,
+	HUB_POST_RESET, HUB_RESUME, HUB_RESET_RESUME,
 };
 
 static void hub_init_func2(struct work_struct *ws);
 static void hub_init_func3(struct work_struct *ws);
-static void hub_post_resume(struct work_struct *ws);
 
 static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 {

@@ -1059,12 +1058,6 @@ static void hub_activate(struct usb_hub
 		goto init3;
 	}
 
-	if (type == HUB_POST_RESUME) {
-		usb_autopm_put_interface_async(to_usb_interface(hub->intfdev));
-		kref_put(&hub->kref, hub_release);
-		return;
-	}
-
 	kref_get(&hub->kref);
 
 	/* The superspeed hub except for root hub has to use Hub Depth

@@ -1318,8 +1311,8 @@ static void hub_activate(struct usb_hub
 		usb_autopm_get_interface_no_resume(
 			to_usb_interface(hub->intfdev));
 
-		INIT_DELAYED_WORK(&hub->init_work, hub_post_resume);
-		queue_delayed_work(system_power_efficient_wq, &hub->init_work,
+		queue_delayed_work(system_power_efficient_wq,
+				   &hub->post_resume_work,
 				   msecs_to_jiffies(USB_SS_PORT_U0_WAKE_TIME));
 		return;
 	}

@@ -1344,9 +1337,10 @@ static void hub_init_func3(struct work_s
 
 static void hub_post_resume(struct work_struct *ws)
 {
-	struct usb_hub *hub = container_of(ws, struct usb_hub, init_work.work);
+	struct usb_hub *hub = container_of(ws, struct usb_hub, post_resume_work.work);
 
-	hub_activate(hub, HUB_POST_RESUME);
+	usb_autopm_put_interface_async(to_usb_interface(hub->intfdev));
+	kref_put(&hub->kref, hub_release);
 }
 
 enum hub_quiescing_type {

@@ -1374,7 +1368,7 @@ static void hub_quiesce(struct usb_hub *
 
 	/* Stop hub_wq and related activity */
 	del_timer_sync(&hub->irq_urb_retry);
-	flush_delayed_work(&hub->init_work);
+	flush_delayed_work(&hub->post_resume_work);
 	usb_kill_urb(hub->urb);
 	if (hub->has_indicators)
 		cancel_delayed_work_sync(&hub->leds);

@@ -1921,6 +1915,7 @@ static int hub_probe(struct usb_interfac
 	hub->hdev = hdev;
 	INIT_DELAYED_WORK(&hub->leds, led_work);
 	INIT_DELAYED_WORK(&hub->init_work, NULL);
+	INIT_DELAYED_WORK(&hub->post_resume_work, hub_post_resume);
 	INIT_WORK(&hub->events, hub_event);
 	spin_lock_init(&hub->irq_urb_lock);
 	timer_setup(&hub->irq_urb_retry, hub_retry_irq_urb, 0);

@@ -69,6 +69,7 @@ struct usb_hub {
 	u8			indicator[USB_MAXCHILDREN];
 	struct delayed_work	leds;
 	struct delayed_work	init_work;
+	struct delayed_work	post_resume_work;
 	struct work_struct      events;
 	spinlock_t		irq_urb_lock;
 	struct timer_list	irq_urb_retry;

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

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

From: Wei Yang <[email protected]>

commit 394bfac1c7f7b701c2c93834c5761b9c9ceeebcf upstream.

Commit 8ee53820edfd ("thp: mmu_notifier_test_young") introduced mmu_notifier_test_young(), but we are passing the wrong address. In xxx_scan_pmd(), the actual iteration address is "_address" not "address". We seem to misuse the variable on the very beginning.

Change it to the right one.

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

@@ -1227,7 +1227,7 @@ static int khugepaged_scan_pmd(struct mm
 		}
 		if (pte_young(pteval) ||
 		    page_is_young(page) || PageReferenced(page) ||
-		    mmu_notifier_test_young(vma->vm_mm, address))
+		    mmu_notifier_test_young(vma->vm_mm, _address))
 			referenced++;
 	}
 	if (writable) {

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

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

From: Christophe Kerello <[email protected]>

[ Upstream commit 513c40e59d5a414ab763a9c84797534b5e8c208d ]

Avoid below overlapping mappings by using a contiguous non-cacheable buffer.

[    4.077708] DMA-API: stm32_fmc2_nfc 48810000.nand-controller: cacheline tracking EEXIST,
overlapping mappings aren't supported
[    4.089103] WARNING: CPU: 1 PID: 44 at kernel/dma/debug.c:568 add_dma_entry+0x23c/0x300
[    4.097071] Modules linked in:
[    4.100101] CPU: 1 PID: 44 Comm: kworker/u4:2 Not tainted 6.1.82 #1
[    4.106346] Hardware name: STMicroelectronics STM32MP257F VALID1 SNOR / MB1704 (LPDDR4 Power discrete) + MB1703 + MB1708 (SNOR MB1730) (DT)
[    4.118824] Workqueue: events_unbound deferred_probe_work_func
[    4.124674] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[    4.131624] pc : add_dma_entry+0x23c/0x300
[    4.135658] lr : add_dma_entry+0x23c/0x300
[    4.139792] sp : ffff800009dbb490
[    4.143016] x29: ffff800009dbb4a0 x28: 0000000004008022 x27: ffff8000098a6000
[    4.150174] x26: 0000000000000000 x25: ffff8000099e7000 x24: ffff8000099e7de8
[    4.157231] x23: 00000000ffffffff x22: 0000000000000000 x21: ffff8000098a6a20
[    4.164388] x20: ffff000080964180 x19: ffff800009819ba0 x18: 0000000000000006
[    4.171545] x17: 6361727420656e69 x16: 6c6568636163203a x15: 72656c6c6f72746e
[    4.178602] x14: 6f632d646e616e2e x13: ffff800009832f58 x12: 00000000000004ec
[    4.185759] x11: 00000000000001a4 x10: ffff80000988af58 x9 : ffff800009832f58
[    4.192916] x8 : 00000000ffffefff x7 : ffff80000988af58 x6 : 80000000fffff000
[    4.199972] x5 : 000000000000bff4 x4 : 0000000000000000 x3 : 0000000000000000
[    4.207128] x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff0000812d2c40
[    4.214185] Call trace:
[    4.216605]  add_dma_entry+0x23c/0x300
[    4.220338]  debug_dma_map_sg+0x198/0x350
[    4.224373]  __dma_map_sg_attrs+0xa0/0x110
[    4.228411]  dma_map_sg_attrs+0x10/0x2c
[    4.232247]  stm32_fmc2_nfc_xfer.isra.0+0x1c8/0x3fc
[    4.237088]  stm32_fmc2_nfc_seq_read_page+0xc8/0x174
[    4.242127]  nand_read_oob+0x1d4/0x8e0
[    4.245861]  mtd_read_oob_std+0x58/0x84
[    4.249596]  mtd_read_oob+0x90/0x150
[    4.253231]  mtd_read+0x68/0xac

---
 drivers/mtd/nand/raw/stm32_fmc2_nand.c |   27 +++++++++------------------
 1 file changed, 9 insertions(+), 18 deletions(-)

@@ -266,6 +266,7 @@ struct stm32_fmc2_nfc {
 	struct sg_table dma_data_sg;
 	struct sg_table dma_ecc_sg;
 	u8 *ecc_buf;
+	dma_addr_t dma_ecc_addr;
 	int dma_ecc_len;
 
 	struct completion complete;

@@ -942,24 +943,19 @@ static int stm32_fmc2_xfer(struct nand_c
 
 	if (!write_data && !raw) {
 		/* Configure DMA ECC status */
-		p = fmc2->ecc_buf;
 		for_each_sg(fmc2->dma_ecc_sg.sgl, sg, eccsteps, s) {
-			sg_set_buf(sg, p, fmc2->dma_ecc_len);
-			p += fmc2->dma_ecc_len;
+			sg_dma_address(sg) = fmc2->dma_ecc_addr +
+					     s * fmc2->dma_ecc_len;
+			sg_dma_len(sg) = fmc2->dma_ecc_len;
 		}
 
-		ret = dma_map_sg(fmc2->dev, fmc2->dma_ecc_sg.sgl,
-				 eccsteps, dma_data_dir);
-		if (ret < 0)
-			goto err_unmap_data;
-
 		desc_ecc = dmaengine_prep_slave_sg(fmc2->dma_ecc_ch,
 						   fmc2->dma_ecc_sg.sgl,
 						   eccsteps, dma_transfer_dir,
 						   DMA_PREP_INTERRUPT);
 		if (!desc_ecc) {
 			ret = -ENOMEM;
-			goto err_unmap_ecc;
+			goto err_unmap_data;
 		}
 
 		reinit_completion(&fmc2->dma_ecc_complete);

@@ -967,7 +963,7 @@ static int stm32_fmc2_xfer(struct nand_c
 		desc_ecc->callback_param = &fmc2->dma_ecc_complete;
 		ret = dma_submit_error(dmaengine_submit(desc_ecc));
 		if (ret)
-			goto err_unmap_ecc;
+			goto err_unmap_data;
 
 		dma_async_issue_pending(fmc2->dma_ecc_ch);
 	}

@@ -988,7 +984,7 @@ static int stm32_fmc2_xfer(struct nand_c
 		if (!write_data && !raw)
 			dmaengine_terminate_all(fmc2->dma_ecc_ch);
 		ret = -ETIMEDOUT;
-		goto err_unmap_ecc;
+		goto err_unmap_data;
 	}
 
 	/* Wait DMA data transfer completion */

@@ -1009,11 +1005,6 @@ static int stm32_fmc2_xfer(struct nand_c
 		}
 	}
 
-err_unmap_ecc:
-	if (!write_data && !raw)
-		dma_unmap_sg(fmc2->dev, fmc2->dma_ecc_sg.sgl,
-			     eccsteps, dma_data_dir);
-
 err_unmap_data:
 	dma_unmap_sg(fmc2->dev, fmc2->dma_data_sg.sgl, eccsteps, dma_data_dir);
 

@@ -1637,8 +1628,8 @@ static int stm32_fmc2_dma_setup(struct s
 		return ret;
 
 	/* Allocate a buffer to store ECC status registers */
-	fmc2->ecc_buf = devm_kzalloc(fmc2->dev, FMC2_MAX_ECC_BUF_LEN,
-				     GFP_KERNEL);
+	fmc2->ecc_buf = dmam_alloc_coherent(fmc2->dev, FMC2_MAX_ECC_BUF_LEN,
+					   &fmc2->dma_ecc_addr, GFP_KERNEL);
 	if (!fmc2->ecc_buf)
 		return -ENOMEM;
 

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

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

From: Alexander Dahl <[email protected]>

[ Upstream commit 1c60e027ffdebd36f4da766d9c9abbd1ea4dd8f9 ]

Looks like a copy'n'paste mistake introduced when initially adding the dynamic timings feature with commit f9ce2eddf176 ("mtd: nand: atmel: Add ->setup_data_interface() hooks"). The context around this and especially the code itself suggests 'read' is meant instead of write.

Stable-dep-of: fd779eac2d65 ("mtd: nand: raw: atmel: Respect tAR, tCLR in read setup timing")

---
 drivers/mtd/nand/raw/atmel/nand-controller.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1312,7 +1312,7 @@ static int atmel_smc_nand_prepare_smccon
 		return ret;
 
 	/*
-	 * The write cycle timing is directly matching tWC, but is also
+	 * The read cycle timing is directly matching tRC, but is also
 	 * dependent on the setup and hold timings we calculated earlier,
 	 * which gives:
 	 *

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

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

From: Alexander Sverdlin <[email protected]>

[ Upstream commit fd779eac2d659668be4d3dbdac0710afd5d6db12 ]

Having setup time 0 violates tAR, tCLR of some chips, for instance TOSHIBA TC58NVG2S3ETAI0 cannot be detected successfully (first ID byte being read duplicated, i.e. 98 98 dc 90 15 76 14 03 instead of 98 dc 90 15 76 ...).

Atmel Application Notes postulated 1 cycle NRD_SETUP without explanation [1], but it looks more appropriate to just calculate setup time properly.

[1] Link: https://ww1.microchip.com/downloads/aemDocuments/documents/MPU32/ApplicationNotes/ApplicationNotes/doc6255.pdf

---
 drivers/mtd/nand/raw/atmel/nand-controller.c |   16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

@@ -1312,13 +1312,23 @@ static int atmel_smc_nand_prepare_smccon
 		return ret;
 
 	/*
+	 * Read setup timing depends on the operation done on the NAND:
+	 *
+	 * NRD_SETUP = max(tAR, tCLR)
+	 */
+	timeps = max(conf->timings.sdr.tAR_min, conf->timings.sdr.tCLR_min);
+	ncycles = DIV_ROUND_UP(timeps, mckperiodps);
+	totalcycles += ncycles;
+	ret = atmel_smc_cs_conf_set_setup(smcconf, ATMEL_SMC_NRD_SHIFT, ncycles);
+	if (ret)
+		return ret;
+
+	/*
 	 * The read cycle timing is directly matching tRC, but is also
 	 * dependent on the setup and hold timings we calculated earlier,
 	 * which gives:
 	 *
-	 * NRD_CYCLE = max(tRC, NRD_PULSE + NRD_HOLD)
-	 *
-	 * NRD_SETUP is always 0.
+	 * NRD_CYCLE = max(tRC, NRD_SETUP + NRD_PULSE + NRD_HOLD)
 	 */
 	ncycles = DIV_ROUND_UP(conf->timings.sdr.tRC_min, mckperiodps);
 	ncycles = max(totalcycles, ncycles);

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

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

From: Fabian Vogt <[email protected]>

commit cfd956dcb101aa3d25bac321fae923323a47c607 upstream.

After hvc_write completes, call hvc_kick also in the case the output buffer has been drained, to ensure tty_wakeup gets called.

This fixes that functions which wait for a drained buffer got stuck occasionally.

---
 drivers/tty/hvc/hvc_console.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -543,10 +543,10 @@ static int hvc_write(struct tty_struct *
 	}
 
 	/*
-	 * Racy, but harmless, kick thread if there is still pending data.
+	 * Kick thread to flush if there's still pending data
+	 * or to wakeup the write queue.
 	 */
-	if (hp->n_outbuf)
-		hvc_kick();
+	hvc_kick();
 
 	return written;
 }

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

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

From: Fabio Porcedda <[email protected]>

commit cba70aff623b104085ab5613fedd21f6ea19095a upstream.

Add the following Telit Cinterion FN990A w/audio compositions:

0x1077: tty (diag) + adb + rmnet + audio + tty (AT/NMEA) + tty (AT) + tty (AT) + tty (AT)

T:  Bus=01 Lev=01 Prnt=01 Port=09 Cnt=01 Dev#=  8 Spd=480 MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1077 Rev=05.04
S:  Manufacturer=Telit Wireless Solutions
S:  Product=FN990
S:  SerialNumber=67e04c35
C:  #Ifs=10 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan
E:  Ad=0f(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 0 Cls=01(audio) Sub=01 Prot=20 Driver=snd-usb-audio
I:  If#= 4 Alt= 1 #EPs= 1 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
E:  Ad=03(O) Atr=0d(Isoc) MxPS=  68 Ivl=1ms
I:  If#= 5 Alt= 1 #EPs= 1 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
E:  Ad=84(I) Atr=0d(Isoc) MxPS=  68 Ivl=1ms
I:  If#= 6 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 7 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 8 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 9 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8c(I) Atr=03(Int.) MxPS=  10 Ivl=32ms

0x1078: tty (diag) + adb + MBIM + audio + tty (AT/NMEA) + tty (AT) + tty (AT) + tty (AT)

T:  Bus=01 Lev=01 Prnt=01 Port=09 Cnt=01 Dev#= 21 Spd=480 MxCh= 0
D:  Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1078 Rev=05.04
S:  Manufacturer=Telit Wireless Solutions
S:  Product=FN990
S:  SerialNumber=67e04c35
C:  #Ifs=11 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#=10 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8c(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 2 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=32ms
I:  If#= 3 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E:  Ad=0f(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 4 Alt= 0 #EPs= 0 Cls=01(audio) Sub=01 Prot=20 Driver=snd-usb-audio
I:  If#= 5 Alt= 0 #EPs= 0 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
I:  If#= 6 Alt= 1 #EPs= 1 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
E:  Ad=84(I) Atr=0d(Isoc) MxPS=  68 Ivl=1ms
I:  If#= 7 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 8 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 9 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms

0x1079: RNDIS + tty (diag) + adb + audio + tty (AT/NMEA) + tty (AT) + tty (AT) + tty (AT)

T:  Bus=01 Lev=01 Prnt=01 Port=09 Cnt=01 Dev#= 23 Spd=480 MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1079 Rev=05.04
S:  Manufacturer=Telit Wireless Solutions
S:  Product=FN990
S:  SerialNumber=67e04c35
C:  #Ifs=11 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=ef(misc ) Sub=04 Prot=01 Driver=rndis_host
E:  Ad=81(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=rndis_host
E:  Ad=0f(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#=10 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8c(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 4 Alt= 0 #EPs= 0 Cls=01(audio) Sub=01 Prot=20 Driver=snd-usb-audio
I:  If#= 5 Alt= 0 #EPs= 0 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
I:  If#= 6 Alt= 1 #EPs= 1 Cls=01(audio) Sub=02 Prot=20 Driver=snd-usb-audio
E:  Ad=84(I) Atr=0d(Isoc) MxPS=  68 Ivl=1ms
I:  If#= 7 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 8 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 9 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms

---
 drivers/usb/serial/option.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -1369,6 +1369,12 @@ static const struct usb_device_id option
 	  .driver_info = NCTRL(0) | RSVD(1) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff),	/* Telit FN990A (PCIe) */
 	  .driver_info = RSVD(0) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1077, 0xff),	/* Telit FN990A (rmnet + audio) */
+	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1078, 0xff),	/* Telit FN990A (MBIM + audio) */
+	  .driver_info = NCTRL(0) | RSVD(1) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1079, 0xff),	/* Telit FN990A (RNDIS + audio) */
+	  .driver_info = NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff),	/* Telit FE990A (rmnet) */
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff),	/* Telit FE990A (MBIM) */

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

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

From: Fabio Porcedda <[email protected]>

commit a5a261bea9bf8444300d1067b4a73bedee5b5227 upstream.

Add the following Telit Cinterion LE910C4-WWX new compositions:

0x1034: tty (AT) + tty (AT) + rmnet

T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  8 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1034 Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x1036: tty (AT) + tty (AT)

T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 10 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1036 Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x1037: tty (diag) + tty (Telit custom) + tty (AT) + tty (AT) + rmnet

T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 15 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1037 Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=88(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x1038: tty (Telit custom) + tty (AT) + tty (AT) + rmnet

T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#=  9 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=1038 Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 4 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x103b: tty (diag) + tty (Telit custom) + tty (AT) + tty (AT)

T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 10 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=103b Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 4 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=84(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=86(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x103c: tty (Telit custom) + tty (AT) + tty (AT)

T:  Bus=01 Lev=01 Prnt=01 Port=00 Cnt=01 Dev#= 11 Spd=480 MxCh= 0
D:  Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=103c Rev=00.00
S:  Manufacturer=Telit
S:  Product=LE910C4-WWX
S:  SerialNumber=93f617e7
C:  #Ifs= 3 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=fe Prot=ff Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=03(Int.) MxPS=  64 Ivl=2ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

---
 drivers/usb/serial/option.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

@@ -1322,7 +1322,18 @@ static const struct usb_device_id option
 	 .driver_info = NCTRL(0) | RSVD(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1033, 0xff),	/* Telit LE910C1-EUX (ECM) */
 	 .driver_info = NCTRL(0) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1034, 0xff),	/* Telit LE910C4-WWX (rmnet) */
+	 .driver_info = RSVD(2) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1035, 0xff) }, /* Telit LE910C4-WWX (ECM) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1036, 0xff) },  /* Telit LE910C4-WWX */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1037, 0xff),	/* Telit LE910C4-WWX (rmnet) */
+	 .driver_info = NCTRL(0) | NCTRL(1) | RSVD(4) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1038, 0xff),	/* Telit LE910C4-WWX (rmnet) */
+	 .driver_info = NCTRL(0) | RSVD(3) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x103b, 0xff),	/* Telit LE910C4-WWX */
+	 .driver_info = NCTRL(0) | NCTRL(1) },
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x103c, 0xff),	/* Telit LE910C4-WWX */
+	 .driver_info = NCTRL(0) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0),
 	  .driver_info = RSVD(0) | RSVD(1) | NCTRL(2) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG1),

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

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

From: Stefan Wahren <[email protected]>

[ Upstream commit 03e79de4608bdd48ad6eec272e196124cefaf798 ]

The function of_phy_find_device may return NULL, so we need to take care before dereferencing phy_dev.

---
 drivers/net/ethernet/freescale/fec_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index f8a0966332805..7b2ab0cc562cc 100644
@@ -2018,7 +2018,8 @@ static void fec_enet_phy_reset_after_clk_enable(struct net_device *ndev)
 		 */
 		phy_dev = of_phy_find_device(fep->phy_node);
 		phy_reset_after_clk_enable(phy_dev);
-		put_device(&phy_dev->mdio.dev);
+		if (phy_dev)
+			put_device(&phy_dev->mdio.dev);
 	}
 }
 

2.51.0

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

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

From: Kohei Enju <[email protected]>

[ Upstream commit d709f178abca22a4d3642513df29afe4323a594b ]

The igb driver incorrectly skips the link test when the network interface is admin down (if_running == false), causing the test to always report PASS regardless of the actual physical link state.

This behavior is inconsistent with other drivers (e.g. i40e, ice, ixgbe, etc.) which correctly test the physical link state regardless of admin state.
Remove the if_running check to ensure link test always reflects the physical link state.

---
 drivers/net/ethernet/intel/igb/igb_ethtool.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

index de2c39436fe0a..8166fb619db45 100644
@@ -2070,11 +2070,8 @@ static void igb_diag_test(struct net_device *netdev,
 	} else {
 		dev_info(&adapter->pdev->dev, "online testing starting\n");
 
-		/* PHY is powered down when interface is down */
-		if (if_running && igb_link_test(adapter, &data[TEST_LINK]))
+		if (igb_link_test(adapter, &data[TEST_LINK]))
 			eth_test->flags |= ETH_TEST_FL_FAILED;
-		else
-			data[TEST_LINK] = 0;
 
 		/* Online tests aren't run; pass by default */
 		data[TEST_REG] = 0;

2.51.0

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

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

From: John Garry <[email protected]>

[ Upstream commit 1d3aec89286254487df7641c30f1b14ad1d127a5 ]

Add a function to allow the affinity of an interrupt be switched to managed, such that interrupts allocated for platform devices may be managed.

This new interface has certain limitations, and attempts to use it in the following circumstances will fail:
- For when the kernel is configured for generic IRQ reservation mode (in config GENERIC_IRQ_RESERVATION_MODE). The reason being that it could conflict with managed vs. non-managed interrupt accounting.
- The interrupt is already started, which should not be the case during init
- The interrupt is already configured as managed, which means double init

Stable-dep-of: 915470e1b44e ("i40e: fix IRQ freeing in i40e_vsi_request_irq_msix error path")

---
 include/linux/interrupt.h |  8 +++++
 kernel/irq/manage.c       | 70 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 78 insertions(+)

index 7b8bdc468492e..a601715279f50 100644
@@ -341,6 +341,8 @@ extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
 
 extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m);
+extern int irq_update_affinity_desc(unsigned int irq,
+				    struct irq_affinity_desc *affinity);
 
 extern int
 irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);

@@ -376,6 +378,12 @@ static inline int irq_set_affinity_hint(unsigned int irq,
 	return -EINVAL;
 }
 
+static inline int irq_update_affinity_desc(unsigned int irq,
+					   struct irq_affinity_desc *affinity)
+{
+	return -EINVAL;
+}
+
 static inline int
 irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 {

2.51.0

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

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

From: Kuniyuki Iwashima <[email protected]>

commit 0bb2f7a1ad1f11d861f58e5ee5051c8974ff9569 upstream.

When I ran the repro [0] and waited a few seconds, I observed two LOCKDEP splats: a warning immediately followed by a null-ptr-deref. [1]

Reproduction Steps:

1) Mount CIFS
2) Add an iptables rule to drop incoming FIN packets for CIFS
3) Unmount CIFS
4) Unload the CIFS module
5) Remove the iptables rule

At step 3), the CIFS module calls sock_release() for the underlying TCP socket, and it returns quickly. However, the socket remains in FIN_WAIT_1 because incoming FIN packets are dropped.

At this point, the module's refcnt is 0 while the socket is still alive, so the following rmmod command succeeds.

  # ss -tan
  State      Recv-Q Send-Q Local Address:Port  Peer Address:Port
  FIN-WAIT-1 0      477        10.0.2.15:51062   10.0.0.137:445

  # lsmod | grep cifs
  cifs                 1159168  0

This highlights a discrepancy between the lifetime of the CIFS module and the underlying TCP socket. Even after CIFS calls sock_release() and it returns, the TCP socket does not die immediately in order to close the connection gracefully.

While this is generally fine, it causes an issue with LOCKDEP because CIFS assigns a different lock class to the TCP socket's sk->sk_lock using sock_lock_init_class_and_name().

Once an incoming packet is processed for the socket or a timer fires, sk->sk_lock is acquired.

Then, LOCKDEP checks the lock context in check_wait_context(), where hlock_class() is called to retrieve the lock class. However, since the module has already been unloaded, hlock_class() logs a warning and returns NULL, triggering the null-ptr-deref.

If LOCKDEP is enabled, we must ensure that a module calling sock_lock_init_class_and_name() (CIFS, NFS, etc) cannot be unloaded while such a socket is still alive to prevent this issue.

Let's hold the module reference in sock_lock_init_class_and_name() and release it when the socket is freed in sk_prot_free().

Note that sock_lock_init() clears sk->sk_owner for svc_create_socket() that calls sock_lock_init_class_and_name() for a listening socket, which clones a socket by sk_clone_lock() without GFP_ZERO.

[0]:
CIFS_SERVER="10.0.0.137" CIFS_PATH="//${CIFS_SERVER}/Users/Administrator/Desktop/CIFS_TEST" DEV="enp0s3"
CRED="/root/WindowsCredential.txt"

MNT=$(mktemp -d /tmp/XXXXXX)
mount -t cifs ${CIFS_PATH} ${MNT} -o vers=3.0,credentials=${CRED},cache=none,echo_interval=1

iptables -A INPUT -s ${CIFS_SERVER} -j DROP

for i in $(seq 10);
do

    umount ${MNT}
    rmmod cifs
    sleep 1

done

rm -r ${MNT}

iptables -D INPUT -s ${CIFS_SERVER} -j DROP

[1]:
DEBUG_LOCKS_WARN_ON(1)

WARNING: CPU: 10 PID: 0 at kernel/locking/lockdep.c:234 hlock_class (kernel/locking/lockdep.c:234 kernel/locking/lockdep.c:223)
Modules linked in: cifs_arc4 nls_ucs2_utils cifs_md4 [last unloaded: cifs]
CPU: 10 UID: 0 PID: 0 Comm: swapper/10 Not tainted 6.14.0 #36
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
RIP: 0010:hlock_class (kernel/locking/lockdep.c:234 kernel/locking/lockdep.c:223)
...
Call Trace:
 <IRQ>
 __lock_acquire (kernel/locking/lockdep.c:4853 kernel/locking/lockdep.c:5178)
 lock_acquire (kernel/locking/lockdep.c:469 kernel/locking/lockdep.c:5853 kernel/locking/lockdep.c:5816)
 _raw_spin_lock_nested (kernel/locking/spinlock.c:379)
 tcp_v4_rcv (./include/linux/skbuff.h:1678 ./include/net/tcp.h:2547 net/ipv4/tcp_ipv4.c:2350)

...

BUG: kernel NULL pointer dereference, address: 00000000000000c4
 PF: supervisor read access in kernel mode
 PF: error_code(0x0000) - not-present page
PGD 0
Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 10 UID: 0 PID: 0 Comm: swapper/10 Tainted: G        W          6.14.0 #36
Tainted: [W]=WARN
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
RIP: 0010:__lock_acquire (kernel/locking/lockdep.c:4852 kernel/locking/lockdep.c:5178)
Code: 15 41 09 c7 41 8b 44 24 20 25 ff 1f 00 00 41 09 c7 8b 84 24 a0 00 00 00 45 89 7c 24 20 41 89 44 24 24 e8 e1 bc ff ff 4c 89 e7 <44> 0f b6 b8 c4 00 00 00 e8 d1 bc ff ff 0f b6 80 c5 00 00 00 88 44
RSP: 0018:ffa0000000468a10 EFLAGS: 00010046
RAX: 0000000000000000 RBX: ff1100010091cc38 RCX: 0000000000000027
RDX: ff1100081f09ca48 RSI: 0000000000000001 RDI: ff1100010091cc88
RBP: ff1100010091c200 R08: ff1100083fe6e228 R09: 00000000ffffbfff
R10: ff1100081eca0000 R11: ff1100083fe10dc0 R12: ff1100010091cc88
R13: 0000000000000001 R14: 0000000000000000 R15: 00000000000424b1
FS:  0000000000000000(0000) GS:ff1100081f080000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000000000c4 CR3: 0000000002c4a003 CR4: 0000000000771ef0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400
PKRU: 55555554
Call Trace:
 <IRQ>
 lock_acquire (kernel/locking/lockdep.c:469 kernel/locking/lockdep.c:5853 kernel/locking/lockdep.c:5816)
 _raw_spin_lock_nested (kernel/locking/spinlock.c:379)
 tcp_v4_rcv (./include/linux/skbuff.h:1678 ./include/net/tcp.h:2547 net/ipv4/tcp_ipv4.c:2350)
 ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205 (discriminator 1))
 ip_local_deliver_finish (./include/linux/rcupdate.h:878 net/ipv4/ip_input.c:234)
 ip_sublist_rcv_finish (net/ipv4/ip_input.c:576)
 ip_list_rcv_finish (net/ipv4/ip_input.c:628)
 ip_list_rcv (net/ipv4/ip_input.c:670)
 __netif_receive_skb_list_core (net/core/dev.c:5939 net/core/dev.c:5986)
 netif_receive_skb_list_internal (net/core/dev.c:6040 net/core/dev.c:6129)
 napi_complete_done (./include/linux/list.h:37 ./include/net/gro.h:519 ./include/net/gro.h:514 net/core/dev.c:6496)
 e1000_clean (drivers/net/ethernet/intel/e1000/e1000_main.c:3815)
 __napi_poll.constprop.0 (net/core/dev.c:7191)
 net_rx_action (net/core/dev.c:7262 net/core/dev.c:7382)
 handle_softirqs (kernel/softirq.c:561)
 __irq_exit_rcu (kernel/softirq.c:596 kernel/softirq.c:435 kernel/softirq.c:662)
 irq_exit_rcu (kernel/softirq.c:680)
 common_interrupt (arch/x86/kernel/irq.c:280 (discriminator 14))
  </IRQ>
 <TASK>
 asm_common_interrupt (./arch/x86/include/asm/idtentry.h:693)
RIP: 0010:default_idle (./arch/x86/include/asm/irqflags.h:37 ./arch/x86/include/asm/irqflags.h:92 arch/x86/kernel/process.c:744)
Code: 4c 01 c7 4c 29 c2 e9 72 ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa eb 07 0f 00 2d c3 2b 15 00 fb f4 <fa> c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 90 90 90 90 90
RSP: 0018:ffa00000000ffee8 EFLAGS: 00000202
RAX: 000000000000640b RBX: ff1100010091c200 RCX: 0000000000061aa4
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffff812f30c5
RBP: 000000000000000a R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000002 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
 ? do_idle (kernel/sched/idle.c:186 kernel/sched/idle.c:325)
 default_idle_call (./include/linux/cpuidle.h:143 kernel/sched/idle.c:118)
 do_idle (kernel/sched/idle.c:186 kernel/sched/idle.c:325)
 cpu_startup_entry (kernel/sched/idle.c:422 (discriminator 1))
 start_secondary (arch/x86/kernel/smpboot.c:315)
 common_startup_64 (arch/x86/kernel/head_64.S:421)
 </TASK>
Modules linked in: cifs_arc4 nls_ucs2_utils cifs_md4 [last unloaded: cifs]

CR2: 00000000000000c4

---
 include/net/sock.h |   40 ++++++++++++++++++++++++++++++++++++++--
 net/core/sock.c    |    5 +++++
 2 files changed, 43 insertions(+), 2 deletions(-)

@@ -321,6 +321,8 @@ struct bpf_sk_storage;
   *	@sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
   *	@sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
   *	@sk_txtime_unused: unused txtime flags
+  *	@sk_owner: reference to the real owner of the socket that calls
+  *		   sock_lock_init_class_and_name().
   */
 struct sock {
 	/*

@@ -515,6 +517,10 @@ struct sock {
 	struct bpf_sk_storage __rcu	*sk_bpf_storage;
 #endif
 	struct rcu_head		sk_rcu;
+
+#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES)
+	struct module		*sk_owner;
+#endif
 };
 
 enum sk_pacing {

@@ -1525,6 +1531,35 @@ static inline void sock_release_ownershi
 	}
 }
 
+#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES)
+static inline void sk_owner_set(struct sock *sk, struct module *owner)
+{
+	__module_get(owner);
+	sk->sk_owner = owner;
+}
+
+static inline void sk_owner_clear(struct sock *sk)
+{
+	sk->sk_owner = NULL;
+}
+
+static inline void sk_owner_put(struct sock *sk)
+{
+	module_put(sk->sk_owner);
+}
+#else
+static inline void sk_owner_set(struct sock *sk, struct module *owner)
+{
+}
+
+static inline void sk_owner_clear(struct sock *sk)
+{
+}
+
+static inline void sk_owner_put(struct sock *sk)
+{
+}
+#endif
 /*
  * Macro so as to not evaluate some arguments when
  * lockdep is not enabled.

@@ -1534,13 +1569,14 @@ static inline void sock_release_ownershi
  */
 #define sock_lock_init_class_and_name(sk, sname, skey, name, key)	\
 do {									\
+	sk_owner_set(sk, THIS_MODULE);					\
 	sk->sk_lock.owned = 0;						\
 	init_waitqueue_head(&sk->sk_lock.wq);				\
 	spin_lock_init(&(sk)->sk_lock.slock);				\
 	debug_check_no_locks_freed((void *)&(sk)->sk_lock,		\
-			sizeof((sk)->sk_lock));				\
+				   sizeof((sk)->sk_lock));		\
 	lockdep_set_class_and_name(&(sk)->sk_lock.slock,		\
-				(skey), (sname));				\
+				   (skey), (sname));			\
 	lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0);	\
 } while (0)
 

@@ -1567,6 +1567,8 @@ lenout:
  */
 static inline void sock_lock_init(struct sock *sk)
 {
+	sk_owner_clear(sk);
+
 	if (sk->sk_kern_sock)
 		sock_lock_init_class_and_name(
 			sk,

@@ -1652,6 +1654,9 @@ static void sk_prot_free(struct proto *p
 	cgroup_sk_free(&sk->sk_cgrp_data);
 	mem_cgroup_sk_free(sk);
 	security_sk_free(sk);
+
+	sk_owner_put(sk);
+
 	if (slab != NULL)
 		kmem_cache_free(slab, sk);
 	else

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

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

From: Thomas Gleixner <[email protected]>

[ Upstream commit 4d80d6ca5d77fde9880da8466e5b64f250e5bf82 ]

Perf modules abuse irq_set_affinity_hint() to set the affinity of system PMU interrupts just because irq_set_affinity() was not exported.

The fact that irq_set_affinity_hint() actually sets the affinity is a non-documented side effect and the name is clearly saying it's a hint.

To clean this up, export the real affinity setter.

Stable-dep-of: 915470e1b44e ("i40e: fix IRQ freeing in i40e_vsi_request_irq_msix error path")

---
 include/linux/interrupt.h | 35 ++---------------------------------
 kernel/irq/manage.c       | 33 ++++++++++++++++++++++++++++++++-
 2 files changed, 34 insertions(+), 34 deletions(-)

index a601715279f50..85a5d13a7dc9c 100644
@@ -303,39 +303,8 @@ struct irq_affinity_desc {
 
 extern cpumask_var_t irq_default_affinity;
 
-/* Internal implementation. Use the helpers below */
-extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask,
-			      bool force);
-
-/**
- * irq_set_affinity - Set the irq affinity of a given irq
- * @irq:	Interrupt to set affinity
- * @cpumask:	cpumask
- *
- * Fails if cpumask does not contain an online CPU
- */
-static inline int
-irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
-{
-	return __irq_set_affinity(irq, cpumask, false);
-}
-
-/**
- * irq_force_affinity - Force the irq affinity of a given irq
- * @irq:	Interrupt to set affinity
- * @cpumask:	cpumask
- *
- * Same as irq_set_affinity, but without checking the mask against
- * online cpus.
- *
- * Solely for low level cpu hotplug code, where we need to make per
- * cpu interrupts affine before the cpu becomes online.
- */
-static inline int
-irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
-{
-	return __irq_set_affinity(irq, cpumask, true);
-}
+extern int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask);
+extern int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask);
 
 extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);

index 44d77e834c229..05601bcd30118 100644
@@ -402,7 +402,8 @@ int irq_update_affinity_desc(unsigned int irq,
 	return ret;
 }
 
-int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
+static int __irq_set_affinity(unsigned int irq, const struct cpumask *mask,
+			      bool force)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;

@@ -417,6 +418,36 @@ int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
 	return ret;
 }
 
+/**
+ * irq_set_affinity - Set the irq affinity of a given irq
+ * @irq:	Interrupt to set affinity
+ * @cpumask:	cpumask
+ *
+ * Fails if cpumask does not contain an online CPU
+ */
+int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return __irq_set_affinity(irq, cpumask, false);
+}
+EXPORT_SYMBOL_GPL(irq_set_affinity);
+
+/**
+ * irq_force_affinity - Force the irq affinity of a given irq
+ * @irq:	Interrupt to set affinity
+ * @cpumask:	cpumask
+ *
+ * Same as irq_set_affinity, but without checking the mask against
+ * online cpus.
+ *
+ * Solely for low level cpu hotplug code, where we need to make per
+ * cpu interrupts affine before the cpu becomes online.
+ */
+int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return __irq_set_affinity(irq, cpumask, true);
+}
+EXPORT_SYMBOL_GPL(irq_force_affinity);
+
 int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 {
 	unsigned long flags;

2.51.0

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

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

From: Thomas Gleixner <[email protected]>

[ Upstream commit 65c7cdedeb3026fabcc967a7aae2f755ad4d0783 ]

The discussion about removing the side effect of irq_set_affinity_hint() of actually applying the cpumask (if not NULL) as affinity to the interrupt, unearthed a few unpleasantries:

1) The modular perf drivers rely on the current behaviour for the very wrong reasons.

2) While none of the other drivers prevents user space from changing the affinity, a cursorily inspection shows that there are at least expectations in some drivers.

#1 needs to be cleaned up anyway, so that's not a problem

#2 might result in subtle regressions especially when irqbalanced (which
nowadays ignores the affinity hint) is disabled.

Provide new interfaces:

irq_update_affinity_hint() - Only sets the affinity hint pointer irq_set_affinity_and_hint() - Set the pointer and apply the affinity to
the interrupt

Make irq_set_affinity_hint() a wrapper around irq_apply_affinity_hint() and document it to be phased out.

Stable-dep-of: 915470e1b44e ("i40e: fix IRQ freeing in i40e_vsi_request_irq_msix error path")

---
 include/linux/interrupt.h | 53 ++++++++++++++++++++++++++++++++++++++-
 kernel/irq/manage.c       |  8 +++---
 2 files changed, 56 insertions(+), 5 deletions(-)

index 85a5d13a7dc9c..7c06e33ad05ec 100644
@@ -309,7 +309,46 @@ extern int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask);
 extern int irq_can_set_affinity(unsigned int irq);
 extern int irq_select_affinity(unsigned int irq);
 
-extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m);
+extern int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m,
+				     bool setaffinity);
+
+/**
+ * irq_update_affinity_hint - Update the affinity hint
+ * @irq:	Interrupt to update
+ * @m:		cpumask pointer (NULL to clear the hint)
+ *
+ * Updates the affinity hint, but does not change the affinity of the interrupt.
+ */
+static inline int
+irq_update_affinity_hint(unsigned int irq, const struct cpumask *m)
+{
+	return __irq_apply_affinity_hint(irq, m, false);
+}
+
+/**
+ * irq_set_affinity_and_hint - Update the affinity hint and apply the provided
+ *			     cpumask to the interrupt
+ * @irq:	Interrupt to update
+ * @m:		cpumask pointer (NULL to clear the hint)
+ *
+ * Updates the affinity hint and if @m is not NULL it applies it as the
+ * affinity of that interrupt.
+ */
+static inline int
+irq_set_affinity_and_hint(unsigned int irq, const struct cpumask *m)
+{
+	return __irq_apply_affinity_hint(irq, m, true);
+}
+
+/*
+ * Deprecated. Use irq_update_affinity_hint() or irq_set_affinity_and_hint()
+ * instead.
+ */
+static inline int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
+{
+	return irq_set_affinity_and_hint(irq, m);
+}
+
 extern int irq_update_affinity_desc(unsigned int irq,
 				    struct irq_affinity_desc *affinity);
 

@@ -341,6 +380,18 @@ static inline int irq_can_set_affinity(unsigned int irq)
 
 static inline int irq_select_affinity(unsigned int irq)  { return 0; }
 
+static inline int irq_update_affinity_hint(unsigned int irq,
+					   const struct cpumask *m)
+{
+	return -EINVAL;
+}
+
+static inline int irq_set_affinity_and_hint(unsigned int irq,
+					    const struct cpumask *m)
+{
+	return -EINVAL;
+}
+
 static inline int irq_set_affinity_hint(unsigned int irq,
 					const struct cpumask *m)
 {

index 05601bcd30118..32513a2e26eb0 100644
@@ -448,7 +448,8 @@ int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
 }
 EXPORT_SYMBOL_GPL(irq_force_affinity);
 
-int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
+int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m,
+			      bool setaffinity)
 {
 	unsigned long flags;
 	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);

@@ -457,12 +458,11 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 		return -EINVAL;
 	desc->affinity_hint = m;
 	irq_put_desc_unlock(desc, flags);
-	/* set the initial affinity to prevent every interrupt being on CPU0 */
-	if (m)
+	if (m && setaffinity)
 		__irq_set_affinity(irq, m, false);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+EXPORT_SYMBOL_GPL(__irq_apply_affinity_hint);
 
 static void irq_affinity_notify(struct work_struct *work)
 {

2.51.0

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

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

From: Nitesh Narayan Lal <[email protected]>

[ Upstream commit d34c54d1739c2cdf2e4437b74e6da269147f4987 ]

The driver uses irq_set_affinity_hint() for two purposes:

- To set the affinity_hint which is consumed by the userspace for distributing the interrupts

- To apply an affinity that it provides for the i40e interrupts

The latter is done to ensure that all the interrupts are evenly spread across all available CPUs. However, since commit a0c9259dc4e1 ("irq/matrix:
Spread interrupts on allocation") the spreading of interrupts is dynamically performed at the time of allocation. Hence, there is no need for the drivers to enforce their own affinity for the spreading of interrupts.

Also, irq_set_affinity_hint() applying the provided cpumask as an affinity for the interrupt is an undocumented side effect. To remove this side effect irq_set_affinity_hint() has been marked as deprecated and new interfaces have been introduced. Hence, replace the irq_set_affinity_hint() with the new interface irq_update_affinity_hint() that only sets the pointer for the affinity_hint.

Stable-dep-of: 915470e1b44e ("i40e: fix IRQ freeing in i40e_vsi_request_irq_msix error path")

---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

index dfa06737ff05e..13d92c378957f 100644
@@ -3882,10 +3882,10 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 		 *
 		 * get_cpu_mask returns a static constant mask with
 		 * a permanent lifetime so it's ok to pass to
-		 * irq_set_affinity_hint without making a copy.
+		 * irq_update_affinity_hint without making a copy.
 		 */
 		cpu = cpumask_local_spread(q_vector->v_idx, -1);
-		irq_set_affinity_hint(irq_num, get_cpu_mask(cpu));
+		irq_update_affinity_hint(irq_num, get_cpu_mask(cpu));
 	}
 
 	vsi->irqs_ready = true;

@@ -3896,7 +3896,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 		vector--;
 		irq_num = pf->msix_entries[base + vector].vector;
 		irq_set_affinity_notifier(irq_num, NULL);
-		irq_set_affinity_hint(irq_num, NULL);
+		irq_update_affinity_hint(irq_num, NULL);
 		free_irq(irq_num, &vsi->q_vectors[vector]);
 	}
 	return err;

@@ -4714,7 +4714,7 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi)
 			/* clear the affinity notifier in the IRQ descriptor */
 			irq_set_affinity_notifier(irq_num, NULL);
 			/* remove our suggested affinity mask for this IRQ */
-			irq_set_affinity_hint(irq_num, NULL);
+			irq_update_affinity_hint(irq_num, NULL);
 			synchronize_irq(irq_num);
 			free_irq(irq_num, vsi->q_vectors[i]);
 

2.51.0

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

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

From: Michal Schmidt <[email protected]>

[ Upstream commit 915470e1b44e71d1dd07ee067276f003c3521ee3 ]

If request_irq() in i40e_vsi_request_irq_msix() fails in an iteration later than the first, the error path wants to free the IRQs requested so far. However, it uses the wrong dev_id argument for free_irq(), so it does not free the IRQs correctly and instead triggers the warning:

Trying to free already-free IRQ 173

 WARNING: CPU: 25 PID: 1091 at kernel/irq/manage.c:1829 __free_irq+0x192/0x2c0
 Modules linked in: i40e(+) [...]
 CPU: 25 UID: 0 PID: 1091 Comm: NetworkManager Not tainted 6.17.0-rc1+ #1 PREEMPT(lazy)
 Hardware name: [...]
 RIP: 0010:__free_irq+0x192/0x2c0
 [...]
 Call Trace:
  <TASK>
  free_irq+0x32/0x70
  i40e_vsi_request_irq_msix.cold+0x63/0x8b [i40e]
  i40e_vsi_request_irq+0x79/0x80 [i40e]
  i40e_vsi_open+0x21f/0x2f0 [i40e]
  i40e_open+0x63/0x130 [i40e]
  __dev_open+0xfc/0x210
  __dev_change_flags+0x1fc/0x240
  netif_change_flags+0x27/0x70
  do_setlink.isra.0+0x341/0xc70
  rtnl_newlink+0x468/0x860
  rtnetlink_rcv_msg+0x375/0x450
  netlink_rcv_skb+0x5c/0x110
  netlink_unicast+0x288/0x3c0
  netlink_sendmsg+0x20d/0x430
  ____sys_sendmsg+0x3a2/0x3d0
  ___sys_sendmsg+0x99/0xe0
  __sys_sendmsg+0x8a/0xf0
  do_syscall_64+0x82/0x2c0
  entry_SYSCALL_64_after_hwframe+0x76/0x7e
  [...]
  </TASK>
 ---[ end trace 0000000000000000 ]---

Use the same dev_id for free_irq() as for request_irq().

I tested this with inserting code to fail intentionally.

---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 13d92c378957f..e37e8a31b35d4 100644
@@ -3897,7 +3897,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 		irq_num = pf->msix_entries[base + vector].vector;
 		irq_set_affinity_notifier(irq_num, NULL);
 		irq_update_affinity_hint(irq_num, NULL);
-		free_irq(irq_num, &vsi->q_vectors[vector]);
+		free_irq(irq_num, vsi->q_vectors[vector]);
 	}
 	return err;
 }

2.51.0

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

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

From: Tetsuo Handa <[email protected]>

[ Upstream commit f214744c8a27c3c1da6b538c232da22cd027530e ]

Commit 25fe97cb7620 ("can: j1939: move j1939_priv_put() into sk_destruct callback") expects that a call to j1939_priv_put() can be unconditionally delayed until j1939_sk_sock_destruct() is called. But a refcount leak will happen when j1939_sk_bind() is called again after j1939_local_ecu_get()
from previous j1939_sk_bind() call returned an error. We need to call
j1939_priv_put() before j1939_sk_bind() returns an error.

---
 net/can/j1939/socket.c | 3 +++
 1 file changed, 3 insertions(+)

index 29f9a343b0dbf..f477add424bc9 100644
@@ -520,6 +520,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 	ret = j1939_local_ecu_get(priv, jsk->addr.src_name, jsk->addr.sa);
 	if (ret) {
 		j1939_netdev_stop(priv);
+		jsk->priv = NULL;
+		synchronize_rcu();
+		j1939_priv_put(priv);
 		goto out_release_sock;
 	}
 

2.51.0

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

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

From: Trond Myklebust <[email protected]>

[ Upstream commit 31f1a960ad1a14def94fa0b8c25d62b4c032813f ]

Don't clear the capabilities that are not going to get reset by the call to _nfs4_server_capabilities().

---
 fs/nfs/nfs4proc.c | 1 -
 1 file changed, 1 deletion(-)

index 5f8de86b27982..f511087d5e1c2 100644
@@ -3885,7 +3885,6 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle)
 	};
 	int err;
 
-	nfs_server_set_init_caps(server);
 	do {
 		err = nfs4_handle_exception(server,
 				_nfs4_server_capabilities(server, fhandle),

2.51.0

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

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

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit a3967baad4d533dc254c31e0d221e51c8d223d58 ]

syzbot reported the splat below. [0]

The repro does the following:

1. Load a sk_msg prog that calls bpf_msg_cork_bytes(msg, cork_bytes)
2. Attach the prog to a SOCKMAP
3. Add a socket to the SOCKMAP
4. Activate fault injection
5. Send data less than cork_bytes

At 5., the data is carried over to the next sendmsg() as it is smaller than the cork_bytes specified by bpf_msg_cork_bytes().

Then, tcp_bpf_send_verdict() tries to allocate psock->cork to hold the data, but this fails silently due to fault injection + __GFP_NOWARN.

If the allocation fails, we need to revert the sk->sk_forward_alloc change done by sk_msg_alloc().

Let's call sk_msg_free() when tcp_bpf_send_verdict fails to allocate psock->cork.

The "*copied" also needs to be updated such that a proper error can be returned to the caller, sendmsg. It fails to allocate psock->cork. Nothing has been corked so far, so this patch simply sets "*copied" to 0.

[0]:

WARNING: net/ipv4/af_inet.c:156 at inet_sock_destruct+0x623/0x730 net/ipv4/af_inet.c:156, CPU#1: syz-executor/5983
Modules linked in:
CPU: 1 UID: 0 PID: 5983 Comm: syz-executor Not tainted syzkaller #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
RIP: 0010:inet_sock_destruct+0x623/0x730 net/ipv4/af_inet.c:156
Code: 0f 0b 90 e9 62 fe ff ff e8 7a db b5 f7 90 0f 0b 90 e9 95 fe ff ff e8 6c db b5 f7 90 0f 0b 90 e9 bb fe ff ff e8 5e db b5 f7 90 <0f> 0b 90 e9 e1 fe ff ff 89 f9 80 e1 07 80 c1 03 38 c1 0f 8c 9f fc
RSP: 0018:ffffc90000a08b48 EFLAGS: 00010246
RAX: ffffffff8a09d0b2 RBX: dffffc0000000000 RCX: ffff888024a23c80
RDX: 0000000000000100 RSI: 0000000000000fff RDI: 0000000000000000
RBP: 0000000000000fff R08: ffff88807e07c627 R09: 1ffff1100fc0f8c4
R10: dffffc0000000000 R11: ffffed100fc0f8c5 R12: ffff88807e07c380
R13: dffffc0000000000 R14: ffff88807e07c60c R15: 1ffff1100fc0f872
FS:  00005555604c4500(0000) GS:ffff888125af1000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005555604df5c8 CR3: 0000000032b06000 CR4: 00000000003526f0
Call Trace:
 <IRQ>
 __sk_destruct+0x86/0x660 net/core/sock.c:2339
 rcu_do_batch kernel/rcu/tree.c:2605 [inline]
 rcu_core+0xca8/0x1770 kernel/rcu/tree.c:2861
 handle_softirqs+0x286/0x870 kernel/softirq.c:579
 __do_softirq kernel/softirq.c:613 [inline]
 invoke_softirq kernel/softirq.c:453 [inline]
 __irq_exit_rcu+0xca/0x1f0 kernel/softirq.c:680
 irq_exit_rcu+0x9/0x30 kernel/softirq.c:696
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1052 [inline]
 sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1052
 </IRQ>

---
 net/ipv4/tcp_bpf.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index 8c1508a2e241a..df0b9edd4e87e 100644
@@ -336,8 +336,11 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 		if (!psock->cork) {
 			psock->cork = kzalloc(sizeof(*psock->cork),
 					      GFP_ATOMIC | __GFP_NOWARN);
-			if (!psock->cork)
+			if (!psock->cork) {
+				sk_msg_free(sk, msg);
+				*copied = 0;
 				return -ENOMEM;
+			}
 		}
 		memcpy(psock->cork, msg, sizeof(*msg));
 		return 0;

2.51.0

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

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

From: Salah Triki <[email protected]>

commit ff2a66d21fd2364ed9396d151115eec59612b200 upstream.

dma_free_coherent() must only be called if the corresponding dma_alloc_coherent() call has succeeded. Calling it when the allocation fails leads to undefined behavior.

Delete the wrong call.

[ bp: Massage commit message. ]

---
 drivers/edac/altera_edac.c |    1 -
 1 file changed, 1 deletion(-)

@@ -125,7 +125,6 @@ static ssize_t altr_sdr_mc_err_inject_wr
 
 	ptemp = dma_alloc_coherent(mci->pdev, 16, &dma_handle, GFP_KERNEL);
 	if (!ptemp) {
-		dma_free_coherent(mci->pdev, 16, ptemp, dma_handle);
 		edac_printk(KERN_ERR, EDAC_MC,
 			    "Inject: Buffer Allocation error\n");
 		return -ENOMEM;

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

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

From: Mark Tinguely <[email protected]>

commit 04100f775c2ea501927f508f17ad824ad1f23c8d upstream.

syzbot detected a OCFS2 hang due to a recursive semaphore on a FS_IOC_FIEMAP of the extent list on a specially crafted mmap file.

context_switch kernel/sched/core.c:5357 [inline]
   __schedule+0x1798/0x4cc0 kernel/sched/core.c:6961
   __schedule_loop kernel/sched/core.c:7043 [inline]
   schedule+0x165/0x360 kernel/sched/core.c:7058
   schedule_preempt_disabled+0x13/0x30 kernel/sched/core.c:7115
   rwsem_down_write_slowpath+0x872/0xfe0 kernel/locking/rwsem.c:1185
   __down_write_common kernel/locking/rwsem.c:1317 [inline]
   __down_write kernel/locking/rwsem.c:1326 [inline]
   down_write+0x1ab/0x1f0 kernel/locking/rwsem.c:1591
   ocfs2_page_mkwrite+0x2ff/0xc40 fs/ocfs2/mmap.c:142
   do_page_mkwrite+0x14d/0x310 mm/memory.c:3361
   wp_page_shared mm/memory.c:3762 [inline]
   do_wp_page+0x268d/0x5800 mm/memory.c:3981
   handle_pte_fault mm/memory.c:6068 [inline]
   __handle_mm_fault+0x1033/0x5440 mm/memory.c:6195
   handle_mm_fault+0x40a/0x8e0 mm/memory.c:6364
   do_user_addr_fault+0x764/0x1390 arch/x86/mm/fault.c:1387
   handle_page_fault arch/x86/mm/fault.c:1476 [inline]
   exc_page_fault+0x76/0xf0 arch/x86/mm/fault.c:1532
   asm_exc_page_fault+0x26/0x30 arch/x86/include/asm/idtentry.h:623
RIP: 0010:copy_user_generic arch/x86/include/asm/uaccess_64.h:126 [inline]
RIP: 0010:raw_copy_to_user arch/x86/include/asm/uaccess_64.h:147 [inline]
RIP: 0010:_inline_copy_to_user include/linux/uaccess.h:197 [inline]
RIP: 0010:_copy_to_user+0x85/0xb0 lib/usercopy.c:26
Code: e8 00 bc f7 fc 4d 39 fc 72 3d 4d 39 ec 77 38 e8 91 b9 f7 fc 4c 89

f7 89 de e8 47 25 5b fd 0f 01 cb 4c 89 ff 48 89 d9 4c 89 f6 <f3> a4 0f 1f 00 48 89 cb 0f 01 ca 48 89 d8 5b 41 5c 41 5d 41 5e 41
RSP: 0018:ffffc9000403f950 EFLAGS: 00050256
RAX: ffffffff84c7f101 RBX: 0000000000000038 RCX: 0000000000000038
RDX: 0000000000000000 RSI: ffffc9000403f9e0 RDI: 0000200000000060
RBP: ffffc9000403fa90 R08: ffffc9000403fa17 R09: 1ffff92000807f42
R10: dffffc0000000000 R11: fffff52000807f43 R12: 0000200000000098
R13: 00007ffffffff000 R14: ffffc9000403f9e0 R15: 0000200000000060

   copy_to_user include/linux/uaccess.h:225 [inline]
   fiemap_fill_next_extent+0x1c0/0x390 fs/ioctl.c:145
   ocfs2_fiemap+0x888/0xc90 fs/ocfs2/extent_map.c:806
   ioctl_fiemap fs/ioctl.c:220 [inline]
   do_vfs_ioctl+0x1173/0x1430 fs/ioctl.c:532
   __do_sys_ioctl fs/ioctl.c:596 [inline]
   __se_sys_ioctl+0x82/0x170 fs/ioctl.c:584
   do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
   do_syscall_64+0xfa/0x3b0 arch/x86/entry/syscall_64.c:94
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f5f13850fd9
RSP: 002b:00007ffe3b3518b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 0000200000000000 RCX: 00007f5f13850fd9
RDX: 0000200000000040 RSI: 00000000c020660b RDI: 0000000000000004
RBP: 6165627472616568 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffe3b3518f0
R13: 00007ffe3b351b18 R14: 431bde82d7b634db R15: 00007f5f1389a03b

ocfs2_fiemap() takes a read lock of the ip_alloc_sem semaphore (since v2.6.22-527-g7307de80510a) and calls fiemap_fill_next_extent() to read the extent list of this running mmap executable. The user supplied buffer to hold the fiemap information page faults calling ocfs2_page_mkwrite() which will take a write lock (since v2.6.27-38-g00dc417fa3e7) of the same semaphore. This recursive semaphore will hold filesystem locks and causes a hang of the fileystem.

The ip_alloc_sem protects the inode extent list and size. Release the read semphore before calling fiemap_fill_next_extent() in ocfs2_fiemap() and ocfs2_fiemap_inline(). This does an unnecessary semaphore lock/unlock on the last extent but simplifies the error path.

---
 fs/ocfs2/extent_map.c |   10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

@@ -698,6 +698,8 @@ out:
  * it not only handles the fiemap for inlined files, but also deals
  * with the fast symlink, cause they have no difference for extent
  * mapping per se.
+ *
+ * Must be called with ip_alloc_sem semaphore held.
  */
 static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh,
 			       struct fiemap_extent_info *fieinfo,

@@ -709,6 +711,7 @@ static int ocfs2_fiemap_inline(struct in
 	u64 phys;
 	u32 flags = FIEMAP_EXTENT_DATA_INLINE|FIEMAP_EXTENT_LAST;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+	lockdep_assert_held_read(&oi->ip_alloc_sem);
 
 	di = (struct ocfs2_dinode *)di_bh->b_data;
 	if (ocfs2_inode_is_fast_symlink(inode))

@@ -724,8 +727,11 @@ static int ocfs2_fiemap_inline(struct in
 			phys += offsetof(struct ocfs2_dinode,
 					 id2.i_data.id_data);
 
+		/* Release the ip_alloc_sem to prevent deadlock on page fault */
+		up_read(&OCFS2_I(inode)->ip_alloc_sem);
 		ret = fiemap_fill_next_extent(fieinfo, 0, phys, id_count,
 					      flags);
+		down_read(&OCFS2_I(inode)->ip_alloc_sem);
 		if (ret < 0)
 			return ret;
 	}

@@ -796,9 +802,11 @@ int ocfs2_fiemap(struct inode *inode, st
 		len_bytes = (u64)le16_to_cpu(rec.e_leaf_clusters) << osb->s_clustersize_bits;
 		phys_bytes = le64_to_cpu(rec.e_blkno) << osb->sb->s_blocksize_bits;
 		virt_bytes = (u64)le32_to_cpu(rec.e_cpos) << osb->s_clustersize_bits;
-
+		/* Release the ip_alloc_sem to prevent deadlock on page fault */
+		up_read(&OCFS2_I(inode)->ip_alloc_sem);
 		ret = fiemap_fill_next_extent(fieinfo, virt_bytes, phys_bytes,
 					      len_bytes, fe_flags);
+		down_read(&OCFS2_I(inode)->ip_alloc_sem);
 		if (ret)
 			break;
 

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

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

From: Christophe Kerello <[email protected]>

commit 811c0da4542df3c065f6cb843ced68780e27bb44 upstream.

In case OOB write is requested during a data write, ECC is currently lost. Avoid this issue by only writing in the free spare area. This issue has been seen with a YAFFS2 file system.

---
 drivers/mtd/nand/raw/stm32_fmc2_nand.c |   18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

@@ -1037,9 +1037,21 @@ static int stm32_fmc2_sequencer_write(st
 
 	/* Write oob */
 	if (oob_required) {
-		ret = nand_change_write_column_op(chip, mtd->writesize,
-						  chip->oob_poi, mtd->oobsize,
-						  false);
+		unsigned int offset_in_page = mtd->writesize;
+		const void *buf = chip->oob_poi;
+		unsigned int len = mtd->oobsize;
+
+		if (!raw) {
+			struct mtd_oob_region oob_free;
+
+			mtd_ooblayout_free(mtd, 0, &oob_free);
+			offset_in_page += oob_free.offset;
+			buf += oob_free.offset;
+			len = oob_free.length;
+		}
+
+		ret = nand_change_write_column_op(chip, offset_in_page,
+						  buf, len, false);
 		if (ret)
 			return ret;
 	}

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

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

From: Miklos Szeredi <[email protected]>

commit e5203209b3935041dac541bc5b37efb44220cc0b upstream.

Just like write(), copy_file_range() should check if the return value is less or equal to the requested number of bytes.

---
 fs/fuse/file.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -3365,6 +3365,9 @@ static ssize_t __fuse_copy_file_range(st
 		fc->no_copy_file_range = 1;
 		err = -EOPNOTSUPP;
 	}
+	if (!err && outarg.size > len)
+		err = -EIO;
+
 	if (err)
 		goto out;
 

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

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

From: Miklos Szeredi <[email protected]>

commit 1e08938c3694f707bb165535df352ac97a8c75c9 upstream.

The FUSE protocol uses struct fuse_write_out to convey the return value of copy_file_range, which is restricted to uint32_t. But the COPY_FILE_RANGE interface supports a 64-bit size copies.

Currently the number of bytes copied is silently truncated to 32-bit, which may result in poor performance or even failure to copy in case of truncation to zero.

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

@@ -3299,7 +3299,7 @@ static ssize_t __fuse_copy_file_range(st
 		.nodeid_out = ff_out->nodeid,
 		.fh_out = ff_out->fh,
 		.off_out = pos_out,
-		.len = len,
+		.len = min_t(size_t, len, UINT_MAX & PAGE_MASK),
 		.flags = flags
 	};
 	struct fuse_write_out outarg;

This is the start of the stable review cycle for the 5.4.300 release. There are 81 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Thu, 02 Oct 2025 14:37:59 +0000. Anything received after that time might be too late.

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

	https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.4.300-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.4.y
and the diffstat can be found below.

thanks,

greg k-h

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

Greg Kroah-Hartman <[email protected]>

    Linux 5.4.300-rc1

Jinjiang Tu <[email protected]>
mm/hugetlb: fix folio is still mapped when deleted

Lukasz Czapnik <[email protected]>
i40e: add mask to apply valid bits for itr_idx

Lukasz Czapnik <[email protected]>
i40e: fix validation of VF state in get resources

Lukasz Czapnik <[email protected]>
i40e: fix idx validation in config queues msg

Lukasz Czapnik <[email protected]>
i40e: add validation for ring_len param

Justin Bronder <[email protected]>
i40e: increase max descriptors for XL710

David Hildenbrand <[email protected]>
mm/migrate_device: don't add folio to be freed to LRU in migrate_device_finalize()

Thomas Zimmermann <[email protected]>
fbcon: Fix OOB access in font allocation

Samasth Norway Ananda <[email protected]>
fbcon: fix integer overflow in fbcon_do_set_font

Lukasz Czapnik <[email protected]>
i40e: add max boundary check for VF filters

Lukasz Czapnik <[email protected]>
i40e: fix input validation logic for action_meta

Lukasz Czapnik <[email protected]>
i40e: fix idx validation in i40e_validate_queue_map

Zabelin Nikita <[email protected]>
drm/gma500: Fix null dereference in hdmi teardown

Stéphane Grosjean <[email protected]>
can: peak_usb: fix shift-out-of-bounds issue

Vincent Mailhol <[email protected]>
can: mcba_usb: populate ndo_change_mtu() to prevent buffer overflow

Vincent Mailhol <[email protected]>
can: sun4i_can: populate ndo_change_mtu() to prevent buffer overflow

Vincent Mailhol <[email protected]>
can: hi311x: populate ndo_change_mtu() to prevent buffer overflow

Geert Uytterhoeven <[email protected]>
can: rcar_can: rcar_can_resume(): fix s2ram with PSCI

Or Har-Toov <[email protected]>
IB/mlx5: Fix obj_type mismatch for SRQ event subscriptions

Jiayi Li <[email protected]>

    usb: core: Add 0x prefix to quirks debug output

Takashi Iwai <[email protected]>
ALSA: usb-audio: Fix build with CONFIG_INPUT=n

Chen Ni <[email protected]>
ALSA: usb-audio: Convert comma to semicolon

Cristian Ciocaltea <[email protected]>
ALSA: usb-audio: Add mixer quirk for Sony DualSense PS5

Cristian Ciocaltea <[email protected]>
ALSA: usb-audio: Remove unneeded wmb() in mixer_quirks

Cristian Ciocaltea <[email protected]>
ALSA: usb-audio: Simplify NULL comparison in mixer_quirks

Cristian Ciocaltea <[email protected]>
ALSA: usb-audio: Avoid multiple assignments in mixer_quirks

Cristian Ciocaltea <[email protected]>
ALSA: usb-audio: Fix block comments in mixer_quirks

Maciej S. Szmigiero <[email protected]>
KVM: SVM: Sync TPR from LAPIC into VMCB::V_TPR even if AVIC is active

Hans de Goede <[email protected]>
net: rfkill: gpio: Fix crash due to dereferencering uninitialized pointer

Philipp Zabel <[email protected]>
net: rfkill: gpio: add DT support

Hugo Villeneuve <[email protected]>
serial: sc16is7xx: fix bug in flow control levels init

Alan Stern <[email protected]>
USB: gadget: dummy-hcd: Fix locking bug in RT-enabled kernels

Jakob Koschel <[email protected]>
usb: gadget: dummy_hcd: remove usage of list iterator past the loop body

Colin Ian King <[email protected]>
ASoC: SOF: Intel: hda-stream: Fix incorrect variable used in error message

Charles Keepax <[email protected]>
ASoC: wm8974: Correct PLL rate rounding

Charles Keepax <[email protected]>
ASoC: wm8940: Correct typo in control name

Håkon Bugge <[email protected]>
rds: ib: Increment i_fastreg_wrs before bailing out

Thomas Fourier <[email protected]>
mmc: mvsdio: Fix dma_unmap_sg() nents value

H. Nikolaus Schaller <[email protected]>
power: supply: bq27xxx: restrict no-battery detection to bq27000

H. Nikolaus Schaller <[email protected]>
power: supply: bq27xxx: fix error return in case of no bq27000 hdq battery

Nathan Chancellor <[email protected]>
nilfs2: fix CFI failure when accessing /sys/fs/nilfs2/features/*

Duoming Zhou <[email protected]>
cnic: Fix use-after-free bugs in cnic_delete_task

Alexey Nepomnyashih <[email protected]>
net: liquidio: fix overflow in octeon_init_instr_queue()

Tariq Toukan <[email protected]>
Revert "net/mlx5e: Update and set Xon/Xoff upon port speed set"

Kuniyuki Iwashima <[email protected]>

    tcp: Clear tcp_sk(sk)->fastopen_rsk in tcp_disconnect().

Maciej Fijalkowski <[email protected]>
i40e: remove redundant memory barrier when cleaning Tx descs

Yeounsu Moon <[email protected]>
net: natsemi: fix rx_dropped double accounting on netif_rx() failure

Chen Ridong <[email protected]>
cgroup: split cgroup_destroy_wq into 3 workqueues

Geert Uytterhoeven <[email protected]>
pcmcia: omap_cf: Mark driver struct with __refdata to prevent section mismatch

Liao Yuanhong <[email protected]>
wifi: mac80211: fix incorrect type for ret

Takashi Sakamoto <[email protected]>
ALSA: firewire-motu: drop EPOLLOUT from poll return values as write is not supported

Miaohe Lin <[email protected]>
mm/memory-failure: fix VM_BUG_ON_PAGE(PagePoisoned(page)) when unpoison memory

Bjorn Andersson <[email protected]>
soc: qcom: mdt_loader: Deal with zero e_shentsize

Johan Hovold <[email protected]>
phy: ti-pipe3: fix device leak at unbind

Stephan Gerhold <[email protected]>
dmaengine: qcom: bam_dma: Fix DT error handling for num-channels/ees

Anders Roxell <[email protected]>
dmaengine: ti: edma: Fix memory allocation size for queue_priority_map

Tetsuo Handa <[email protected]>

    can: j1939: j1939_local_ecu_get(): undo increment when j1939_local_ecu_get() fails

Tetsuo Handa <[email protected]>

    can: j1939: j1939_sk_bind(): call j1939_priv_put() immediately when j1939_local_ecu_get() failed

Michal Schmidt <[email protected]>
i40e: fix IRQ freeing in i40e_vsi_request_irq_msix error path

Nitesh Narayan Lal <[email protected]>
i40e: Use irq_update_affinity_hint()

Thomas Gleixner <[email protected]>
genirq: Provide new interfaces for affinity hints

Thomas Gleixner <[email protected]>
genirq: Export affinity setter for modules

John Garry <[email protected]>
genirq/affinity: Add irq_update_affinity_desc()

Kohei Enju <[email protected]>
igb: fix link test skipping when interface is admin down

Stefan Wahren <[email protected]>
net: fec: Fix possible NPD in fec_enet_phy_reset_after_clk_enable()

Fabio Porcedda <[email protected]>
USB: serial: option: add Telit Cinterion LE910C4-WWX new compositions

Fabio Porcedda <[email protected]>
USB: serial: option: add Telit Cinterion FN990A w/audio compositions

Fabian Vogt <[email protected]>
tty: hvc_console: Call hvc_kick in hvc_write unconditionally

Alexander Sverdlin <[email protected]>
mtd: nand: raw: atmel: Respect tAR, tCLR in read setup timing

Alexander Dahl <[email protected]>
mtd: nand: raw: atmel: Fix comment in timings preparation

Christophe Kerello <[email protected]>
mtd: rawnand: stm32_fmc2: avoid overlapping mappings on ECC buffer

Wei Yang <[email protected]>
mm/khugepaged: fix the address passed to notifier on testing young

Miklos Szeredi <[email protected]>
fuse: prevent overflow in copy_file_range return value

Miklos Szeredi <[email protected]>
fuse: check if copy_file_range() returns larger than requested size

Christophe Kerello <[email protected]>
mtd: rawnand: stm32_fmc2: fix ECC overwrite

Mark Tinguely <[email protected]>
ocfs2: fix recursive semaphore deadlock in fiemap call

Salah Triki <[email protected]>
EDAC/altera: Delete an inappropriate dma_free_coherent() call

Kuniyuki Iwashima <[email protected]>

    tcp_bpf: Call sk_msg_free() when tcp_bpf_send_verdict() fails to allocate psock->cork.

Trond Myklebust <[email protected]>
NFSv4: Don't clear capabilities that won't be reset

Kuniyuki Iwashima <[email protected]>
net: Fix null-ptr-deref by sock_lock_init_class_and_name() and rmmod.

Mathias Nyman <[email protected]>
usb: hub: Fix flushing of delayed work used for post resume purposes

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

Diffstat:

 Makefile                                           |   4 +-
 arch/x86/kvm/svm.c                                 |   3 +-
 drivers/dma/qcom/bam_dma.c                         |   8 +-
 drivers/dma/ti/edma.c                              |   4 +-
 drivers/edac/altera_edac.c                         |   1 -
 drivers/gpu/drm/gma500/oaktrail_hdmi.c             |   2 +-
 drivers/infiniband/hw/mlx5/devx.c                  |   1 +
 drivers/mmc/host/mvsdio.c                          |   2 +-
 drivers/mtd/nand/raw/atmel/nand-controller.c       |  18 +-
 drivers/mtd/nand/raw/stm32_fmc2_nand.c             |  45 ++--
 drivers/net/can/rcar/rcar_can.c                    |   8 +-
 drivers/net/can/spi/hi311x.c                       |   1 +
 drivers/net/can/sun4i_can.c                        |   1 +
 drivers/net/can/usb/mcba_usb.c                     |   1 +
 drivers/net/can/usb/peak_usb/pcan_usb_core.c       |   2 +-
 drivers/net/ethernet/broadcom/cnic.c               |   3 +-
 .../net/ethernet/cavium/liquidio/request_manager.c |   2 +-
 drivers/net/ethernet/freescale/fec_main.c          |   3 +-
 drivers/net/ethernet/intel/i40e/i40e.h             |   1 +
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c     |  25 +-
 drivers/net/ethernet/intel/i40e/i40e_main.c        |  10 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.c        |   3 -
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c |  46 +++-
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h |   3 +-
 drivers/net/ethernet/intel/igb/igb_ethtool.c       |   5 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |   2 -
 drivers/net/ethernet/natsemi/ns83820.c             |  13 +-
 drivers/pcmcia/omap_cf.c                           |   8 +-
 drivers/phy/ti/phy-ti-pipe3.c                      |  13 +
 drivers/power/supply/bq27xxx_battery.c             |   4 +-
 drivers/soc/qcom/mdt_loader.c                      |  12 +-
 drivers/tty/hvc/hvc_console.c                      |   6 +-
 drivers/tty/serial/sc16is7xx.c                     |  13 +-
 drivers/usb/core/hub.c                             |  21 +-
 drivers/usb/core/hub.h                             |   1 +
 drivers/usb/core/quirks.c                          |   2 +-
 drivers/usb/gadget/udc/dummy_hcd.c                 |  25 +-
 drivers/usb/serial/option.c                        |  17 ++
 drivers/video/fbdev/core/fbcon.c                   |  13 +-
 fs/fuse/file.c                                     |   5 +-
 fs/hugetlbfs/inode.c                               |  14 +-
 fs/nfs/nfs4proc.c                                  |   1 -
 fs/nilfs2/sysfs.c                                  |   4 +-
 fs/nilfs2/sysfs.h                                  |   8 +-
 fs/ocfs2/extent_map.c                              |  10 +-
 include/linux/interrupt.h                          |  96 ++++---
 include/net/sock.h                                 |  40 ++-
 kernel/cgroup/cgroup.c                             |  43 +++-
 kernel/irq/manage.c                                | 111 +++++++-
 mm/khugepaged.c                                    |   2 +-
 mm/memory-failure.c                                |   7 +-
 mm/migrate.c                                       |  12 +-
 net/can/j1939/bus.c                                |   5 +-
 net/can/j1939/socket.c                             |   3 +
 net/core/sock.c                                    |   5 +
 net/ipv4/tcp.c                                     |   5 +
 net/ipv4/tcp_bpf.c                                 |   5 +-
 net/mac80211/driver-ops.h                          |   2 +-
 net/rds/ib_frmr.c                                  |  20 +-
 net/rfkill/rfkill-gpio.c                           |  22 +-
 sound/firewire/motu/motu-hwdep.c                   |   2 +-
 sound/soc/codecs/wm8940.c                          |   2 +-
 sound/soc/codecs/wm8974.c                          |   8 +-
 sound/soc/sof/intel/hda-stream.c                   |   2 +-
 sound/usb/mixer_quirks.c                           | 279 ++++++++++++++++++++-
 65 files changed, 829 insertions(+), 236 deletions(-)

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

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

From: Anders Roxell <[email protected]>

[ Upstream commit e63419dbf2ceb083c1651852209c7f048089ac0f ]

Fix a critical memory allocation bug in edma_setup_from_hw() where queue_priority_map was allocated with insufficient memory. The code declared queue_priority_map as s8 (*)[2] (pointer to array of 2 s8), but allocated memory using sizeof(s8) instead of the correct size.

This caused out-of-bounds memory writes when accessing:
queue_priority_map[i][0] = i; queue_priority_map[i][1] = i;

The bug manifested as kernel crashes with "Oops - undefined instruction" on ARM platforms (BeagleBoard-X15) during EDMA driver probe, as the memory corruption triggered kernel hardening features on Clang.

Change the allocation to use sizeof(*queue_priority_map) which automatically gets the correct size for the 2D array structure.

---
 drivers/dma/ti/edma.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 01089e5c565f3..7a0f188fb43c5 100644
@@ -2029,8 +2029,8 @@ static int edma_setup_from_hw(struct device *dev, struct edma_soc_info *pdata,
 	 * priority. So Q0 is the highest priority queue and the last queue has
 	 * the lowest priority.
 	 */
-	queue_priority_map = devm_kcalloc(dev, ecc->num_tc + 1, sizeof(s8),
-					  GFP_KERNEL);
+	queue_priority_map = devm_kcalloc(dev, ecc->num_tc + 1,
+					  sizeof(*queue_priority_map), GFP_KERNEL);
 	if (!queue_priority_map)
 		return -ENOMEM;
 

2.51.0

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

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

From: Yeounsu Moon <[email protected]>

[ Upstream commit 93ab4881a4e2b9657bdce4b8940073bfb4ed5eab ]

netif_rx() already increments rx_dropped core stat when it fails. The driver was also updating ndev->stats.rx_dropped in the same path. Since both are reported together via ip -s -s command, this resulted in drops being counted twice in user-visible stats.

Keep the driver update on if (unlikely(!skb)), but skip it after netif_rx() errors.

---
 drivers/net/ethernet/natsemi/ns83820.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

index 6af9a7eee1149..ded37141683a9 100644
@@ -818,7 +818,7 @@ static void rx_irq(struct net_device *ndev)
 	struct ns83820 *dev = PRIV(ndev);
 	struct rx_info *info = &dev->rx_info;
 	unsigned next_rx;
-	int rx_rc, len;
+	int len;
 	u32 cmdsts;
 	__le32 *desc;
 	unsigned long flags;

@@ -879,8 +879,10 @@ static void rx_irq(struct net_device *ndev)
 		if (likely(CMDSTS_OK & cmdsts)) {
 #endif
 			skb_put(skb, len);
-			if (unlikely(!skb))
+			if (unlikely(!skb)) {
+				ndev->stats.rx_dropped++;
 				goto netdev_mangle_me_harder_failed;
+			}
 			if (cmdsts & CMDSTS_DEST_MULTI)
 				ndev->stats.multicast++;
 			ndev->stats.rx_packets++;

@@ -899,15 +901,12 @@ static void rx_irq(struct net_device *ndev)
 				__vlan_hwaccel_put_tag(skb, htons(ETH_P_IPV6), tag);
 			}
 #endif
-			rx_rc = netif_rx(skb);
-			if (NET_RX_DROP == rx_rc) {
-netdev_mangle_me_harder_failed:
-				ndev->stats.rx_dropped++;
-			}
+			netif_rx(skb);
 		} else {
 			dev_kfree_skb_irq(skb);
 		}
 
+netdev_mangle_me_harder_failed:
 		nr++;
 		next_rx = info->next_rx;
 		desc = info->descs + (DESC_SIZE * next_rx);

2.51.0

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

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

From: Maciej Fijalkowski <[email protected]>

[ Upstream commit e37084a26070c546ae7961ee135bbfb15fbe13fd ]

i40e has a feature which writes to memory location last descriptor successfully sent. Memory barrier in i40e_clean_tx_irq() was used to avoid forward-reading descriptor fields in case DD bit was not set. Having mentioned feature in place implies that such situation will not happen as we know in advance how many descriptors HW has dealt with.

Besides, this barrier placement was wrong. Idea is to have this protection *after* reading DD bit from HW descriptor, not before. Digging through git history showed me that indeed barrier was before DD bit check, anyways the commit introducing i40e_get_head() should have wiped it out altogether.

Also, there was one commit doing s/read_barrier_depends/smp_rmb when get head feature was already in place, but it was only theoretical based on ixgbe experiences, which is different in these terms as that driver has to read DD bit from HW descriptor.

---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 ---
 1 file changed, 3 deletions(-)

index 6067c88668341..ff213cbe84ca8 100644
@@ -794,9 +794,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		if (!eop_desc)
 			break;
 
-		/* prevent any other reads prior to eop_desc */
-		smp_rmb();
-
 		i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
 		/* we have caught up to head, no work left to do */
 		if (tx_head == tx_desc)

2.51.0

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

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

From: Kuniyuki Iwashima <[email protected]>

[ Upstream commit 45c8a6cc2bcd780e634a6ba8e46bffbdf1fc5c01 ]

syzbot reported the splat below where a socket had tcp_sk(sk)->fastopen_rsk in the TCP_ESTABLISHED state. [0]

syzbot reused the server-side TCP Fast Open socket as a new client before the TFO socket completes 3WHS:

1. accept()
2. connect(AF_UNSPEC)
3. connect() to another destination

As of accept(), sk->sk_state is TCP_SYN_RECV, and tcp_disconnect() changes it to TCP_CLOSE and makes connect() possible, which restarts timers.

Since tcp_disconnect() forgot to clear tcp_sk(sk)->fastopen_rsk, the retransmit timer triggered the warning and the intended packet was not retransmitted.

Let's call reqsk_fastopen_remove() in tcp_disconnect().

[0]:

WARNING: CPU: 2 PID: 0 at net/ipv4/tcp_timer.c:542 tcp_retransmit_timer (net/ipv4/tcp_timer.c:542 (discriminator 7))
Modules linked in:
CPU: 2 UID: 0 PID: 0 Comm: swapper/2 Not tainted 6.17.0-rc5-g201825fb4278 #62 PREEMPT(voluntary)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
RIP: 0010:tcp_retransmit_timer (net/ipv4/tcp_timer.c:542 (discriminator 7))
Code: 41 55 41 54 55 53 48 8b af b8 08 00 00 48 89 fb 48 85 ed 0f 84 55 01 00 00 0f b6 47 12 3c 03 74 0c 0f b6 47 12 3c 04 74 04 90 <0f> 0b 90 48 8b 85 c0 00 00 00 48 89 ef 48 8b 40 30 e8 6a 4f 06 3e
RSP: 0018:ffffc900002f8d40 EFLAGS: 00010293
RAX: 0000000000000002 RBX: ffff888106911400 RCX: 0000000000000017
RDX: 0000000002517619 RSI: ffffffff83764080 RDI: ffff888106911400
RBP: ffff888106d5c000 R08: 0000000000000001 R09: ffffc900002f8de8
R10: 00000000000000c2 R11: ffffc900002f8ff8 R12: ffff888106911540
R13: ffff888106911480 R14: ffff888106911840 R15: ffffc900002f8de0
FS:  0000000000000000(0000) GS:ffff88907b768000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f8044d69d90 CR3: 0000000002c30003 CR4: 0000000000370ef0
Call Trace:
 <IRQ>
 tcp_write_timer (net/ipv4/tcp_timer.c:738)
 call_timer_fn (kernel/time/timer.c:1747)
 __run_timers (kernel/time/timer.c:1799 kernel/time/timer.c:2372)
 timer_expire_remote (kernel/time/timer.c:2385 kernel/time/timer.c:2376 kernel/time/timer.c:2135)
 tmigr_handle_remote_up (kernel/time/timer_migration.c:944 kernel/time/timer_migration.c:1035)
 __walk_groups.isra.0 (kernel/time/timer_migration.c:533 (discriminator 1))
 tmigr_handle_remote (kernel/time/timer_migration.c:1096)
 handle_softirqs (./arch/x86/include/asm/jump_label.h:36 ./include/trace/events/irq.h:142 kernel/softirq.c:580)
 irq_exit_rcu (kernel/softirq.c:614 kernel/softirq.c:453 kernel/softirq.c:680 kernel/softirq.c:696)
 sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1050 (discriminator 35) arch/x86/kernel/apic/apic.c:1050 (discriminator 35))
 </IRQ>

---
 net/ipv4/tcp.c | 5 +++++
 1 file changed, 5 insertions(+)

index 55754bf176d99..cc0efcb4a553c 100644
@@ -2593,6 +2593,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int old_state = sk->sk_state;
+	struct request_sock *req;
 	u32 seq;
 
 	/* Deny disconnect if other threads are blocked in sk_wait_event()

@@ -2711,6 +2712,10 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 
 	/* Clean up fastopen related fields */
+	req = rcu_dereference_protected(tp->fastopen_rsk,
+					lockdep_sock_is_held(sk));
+	if (req)
+		reqsk_fastopen_remove(sk, req, false);
 	tcp_free_fastopen_req(tp);
 	inet->defer_connect = 0;
 	tp->fastopen_client_fail = 0;

2.51.0

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

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

From: Tariq Toukan <[email protected]>

[ Upstream commit 3fbfe251cc9f6d391944282cdb9bcf0bd02e01f8 ]

This reverts commit d24341740fe48add8a227a753e68b6eedf4b385a. It causes errors when trying to configure QoS, as well as loss of L2 connectivity (on multi-host devices).

---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 --
 1 file changed, 2 deletions(-)

index b8d0b68befcb9..41bd16cc9d0f6 100644
@@ -141,8 +141,6 @@ void mlx5e_update_carrier(struct mlx5e_priv *priv)
 	if (port_state == VPORT_STATE_UP) {
 		netdev_info(priv->netdev, "Link up\n");
 		netif_carrier_on(priv->netdev);
-		mlx5e_port_manual_buffer_config(priv, 0, priv->netdev->mtu,
-						NULL, NULL, NULL);
 	} else {
 		netdev_info(priv->netdev, "Link down\n");
 		netif_carrier_off(priv->netdev);

2.51.0

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

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

From: Alexey Nepomnyashih <[email protected]>

[ Upstream commit cca7b1cfd7b8a0eff2a3510c5e0f10efe8fa3758 ]

The expression (conf->instr_type == 64) << iq_no can overflow because iq_no may be as high as 64 (CN23XX_MAX_RINGS_PER_PF). Casting the operand to u64 ensures correct 64-bit arithmetic.

---
 drivers/net/ethernet/cavium/liquidio/request_manager.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 6dd65f9b347cb..b606cb1906644 100644
@@ -139,7 +139,7 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 	oct->io_qmask.iq |= BIT_ULL(iq_no);
 
 	/* Set the 32B/64B mode for each input queue */
-	oct->io_qmask.iq64B |= ((conf->instr_type == 64) << iq_no);
+	oct->io_qmask.iq64B |= ((u64)(conf->instr_type == 64) << iq_no);
 	iq->iqcmd_64B = (conf->instr_type == 64);
 
 	oct->fn_list.setup_iq_regs(oct, iq_no);

2.51.0

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

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

From: Duoming Zhou <[email protected]>

[ Upstream commit cfa7d9b1e3a8604afc84e9e51d789c29574fb216 ]

The original code uses cancel_delayed_work() in cnic_cm_stop_bnx2x_hw(), which does not guarantee that the delayed work item 'delete_task' has fully completed if it was already running. Additionally, the delayed work item is cyclic, the flush_workqueue() in cnic_cm_stop_bnx2x_hw() only blocks and waits for work items that were already queued to the workqueue prior to its invocation. Any work items submitted after flush_workqueue() is called are not included in the set of tasks that the flush operation awaits. This means that after the cyclic work items have finished executing, a delayed work item may still exist in the workqueue. This leads to use-after-free scenarios where the cnic_dev is deallocated by cnic_free_dev(), while delete_task remains active and attempt to dereference cnic_dev in cnic_delete_task().

A typical race condition is illustrated below:

CPU 0 (cleanup)              | CPU 1 (delayed work callback)
cnic_netdev_event()          |
  cnic_stop_hw()             | cnic_delete_task()
    cnic_cm_stop_bnx2x_hw()  | ...
      cancel_delayed_work()  | /* the queue_delayed_work()
      flush_workqueue()      |    executes after flush_workqueue()*/
                             | queue_delayed_work()
  cnic_free_dev(dev)//free   | cnic_delete_task() //new instance
                             |   dev = cp->dev; //use

Replace cancel_delayed_work() with cancel_delayed_work_sync() to ensure that the cyclic delayed work item is properly canceled and that any ongoing execution of the work item completes before the cnic_dev is deallocated. Furthermore, since cancel_delayed_work_sync() uses __flush_work(work, true) to synchronously wait for any currently executing instance of the work item to finish, the flush_workqueue() becomes redundant and should be removed.

This bug was identified through static analysis. To reproduce the issue and validate the fix, I simulated the cnic PCI device in QEMU and introduced intentional delays — such as inserting calls to ssleep() within the cnic_delete_task() function — to increase the likelihood of triggering the bug.

---
 drivers/net/ethernet/broadcom/cnic.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

index 155599dcee76d..3283f66e02b6e 100644
@@ -4224,8 +4224,7 @@ static void cnic_cm_stop_bnx2x_hw(struct cnic_dev *dev)
 
 	cnic_bnx2x_delete_wait(dev, 0);
 
-	cancel_delayed_work(&cp->delete_task);
-	flush_workqueue(cnic_wq);
+	cancel_delayed_work_sync(&cp->delete_task);
 
 	if (atomic_read(&cp->iscsi_conn) != 0)
 		netdev_warn(dev->netdev, "%d iSCSI connections not destroyed\n",

2.51.0

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

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

From: Nathan Chancellor <[email protected]>

commit 025e87f8ea2ae3a28bf1fe2b052bfa412c27ed4a upstream.

When accessing one of the files under /sys/fs/nilfs2/features when CONFIG_CFI_CLANG is enabled, there is a CFI violation:

CFI failure at kobj_attr_show+0x59/0x80 (target: nilfs_feature_revision_show+0x0/0x30; expected type: 0xfc392c4d)
...

  Call Trace:
   <TASK>
   sysfs_kf_seq_show+0x2a6/0x390
   ? __cfi_kobj_attr_show+0x10/0x10
   kernfs_seq_show+0x104/0x15b
   seq_read_iter+0x580/0xe2b
  ...

When the kobject of the kset for /sys/fs/nilfs2 is initialized, its ktype is set to kset_ktype, which has a ->sysfs_ops of kobj_sysfs_ops. When nilfs_feature_attr_group is added to that kobject via sysfs_create_group(), the kernfs_ops of each files is sysfs_file_kfops_rw, which will call sysfs_kf_seq_show() when ->seq_show() is called. sysfs_kf_seq_show() in turn calls kobj_attr_show() through ->sysfs_ops->show(). kobj_attr_show() casts the provided attribute out to a 'struct kobj_attribute' via container_of() and calls ->show(), resulting in the CFI violation since neither nilfs_feature_revision_show() nor nilfs_feature_README_show() match the prototype of ->show() in 'struct kobj_attribute'.

Resolve the CFI violation by adjusting the second parameter in nilfs_feature_{revision,README}_show() from 'struct attribute' to 'struct kobj_attribute' to match the expected prototype.

---
 fs/nilfs2/sysfs.c |    4 ++--
 fs/nilfs2/sysfs.h |    8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

@@ -1081,7 +1081,7 @@ void nilfs_sysfs_delete_device_group(str
  ************************************************************************/
 
 static ssize_t nilfs_feature_revision_show(struct kobject *kobj,
-					    struct attribute *attr, char *buf)
+					    struct kobj_attribute *attr, char *buf)
 {
 	return sysfs_emit(buf, "%d.%d\n",
 			NILFS_CURRENT_REV, NILFS_MINOR_REV);

@@ -1093,7 +1093,7 @@ static const char features_readme_str[]
 	"(1) revision\n\tshow current revision of NILFS file system driver.\n";
 
 static ssize_t nilfs_feature_README_show(struct kobject *kobj,
-					 struct attribute *attr,
+					 struct kobj_attribute *attr,
 					 char *buf)
 {
 	return sysfs_emit(buf, features_readme_str);

@@ -50,16 +50,16 @@ struct nilfs_sysfs_dev_subgroups {
 	struct completion sg_segments_kobj_unregister;
 };
 
-#define NILFS_COMMON_ATTR_STRUCT(name) \
+#define NILFS_KOBJ_ATTR_STRUCT(name) \
 struct nilfs_##name##_attr { \
 	struct attribute attr; \
-	ssize_t (*show)(struct kobject *, struct attribute *, \
+	ssize_t (*show)(struct kobject *, struct kobj_attribute *, \
 			char *); \
-	ssize_t (*store)(struct kobject *, struct attribute *, \
+	ssize_t (*store)(struct kobject *, struct kobj_attribute *, \
 			 const char *, size_t); \
 }
 
-NILFS_COMMON_ATTR_STRUCT(feature);
+NILFS_KOBJ_ATTR_STRUCT(feature);
 
 #define NILFS_DEV_ATTR_STRUCT(name) \
 struct nilfs_##name##_attr { \

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

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

From: H. Nikolaus Schaller <[email protected]>

commit 2c334d038466ac509468fbe06905a32d202117db upstream.

Since commit

commit f16d9fb6cf03 ("power: supply: bq27xxx: Retrieve again when busy")

the console log of some devices with hdq enabled but no bq27000 battery (like e.g. the Pandaboard) is flooded with messages like:

[   34.247833] power_supply bq27000-battery: driver failed to report 'status' property: -1

as soon as user-space is finding a /sys entry and trying to read the "status" property.

It turns out that the offending commit changes the logic to now return the value of cache.flags if it is <0. This is likely under the assumption that it is an error number. In normal errors from bq27xxx_read() this is indeed the case.

But there is special code to detect if no bq27000 is installed or accessible through hdq/1wire and wants to report this. In that case, the cache.flags are set historically by

	commit 3dd843e1c26a ("bq27000: report missing device better.")

to constant -1 which did make reading properties return -ENODEV. So everything appeared to be fine before the return value was passed upwards.

Now the -1 is returned as -EPERM instead of -ENODEV, triggering the error condition in power_supply_format_property() which then floods the console log.

So we change the detection of missing bq27000 battery to simply set

cache.flags = -ENODEV

instead of -1.

---
 drivers/power/supply/bq27xxx_battery.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1553,7 +1553,7 @@ static void bq27xxx_battery_update_unloc
 
 	cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag);
 	if ((cache.flags & 0xff) == 0xff)
-		cache.flags = -1; /* read error */
+		cache.flags = -ENODEV; /* read error */
 	if (cache.flags >= 0) {
 		cache.temperature = bq27xxx_battery_read_temperature(di);
 		if (has_ci_flag && (cache.flags & BQ27000_FLAG_CI)) {

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

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

From: H. Nikolaus Schaller <[email protected]>

commit 1e451977e1703b6db072719b37cd1b8e250b9cc9 upstream.

There are fuel gauges in the bq27xxx series (e.g. bq27z561) which may in some cases report 0xff as the value of BQ27XXX_REG_FLAGS that should not be interpreted as "no battery" like for a disconnected battery with some built in bq27000 chip.

So restrict the no-battery detection originally introduced by

    commit 3dd843e1c26a ("bq27000: report missing device better.")

to the bq27000.

There is no need to backport further because this was hidden before

commit f16d9fb6cf03 ("power: supply: bq27xxx: Retrieve again when busy")

---
 drivers/power/supply/bq27xxx_battery.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1552,8 +1552,8 @@ static void bq27xxx_battery_update_unloc
 	bool has_singe_flag = di->opts & BQ27XXX_O_ZERO;
 
 	cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag);
-	if ((cache.flags & 0xff) == 0xff)
-		cache.flags = -ENODEV; /* read error */
+	if (di->chip == BQ27000 && (cache.flags & 0xff) == 0xff)
+		cache.flags = -ENODEV; /* bq27000 hdq read error */
 	if (cache.flags >= 0) {
 		cache.temperature = bq27xxx_battery_read_temperature(di);
 		if (has_ci_flag && (cache.flags & BQ27000_FLAG_CI)) {

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

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

From: Thomas Fourier <[email protected]>

commit 8ab2f1c35669bff7d7ed1bb16bf5cc989b3e2e17 upstream.

The dma_unmap_sg() functions should be called with the same nents as the dma_map_sg(), not the value the map function returned.

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

@@ -292,7 +292,7 @@ static u32 mvsd_finish_data(struct mvsd_
 		host->pio_ptr = NULL;
 		host->pio_size = 0;
 	} else {
-		dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->sg_frags,
+		dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len,
 			     mmc_get_dma_dir(data));
 	}
 

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

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

From: Stephan Gerhold <[email protected]>

commit 5068b5254812433e841a40886e695633148d362d upstream.

When we don't have a clock specified in the device tree, we have no way to ensure the BAM is on. This is often the case for remotely-controlled or remotely-powered BAM instances. In this case, we need to read num-channels from the DT to have all the necessary information to complete probing.

However, at the moment invalid device trees without clock and without num-channels still continue probing, because the error handling is missing return statements. The driver will then later try to read the number of channels from the registers. This is unsafe, because it relies on boot firmware and lucky timing to succeed. Unfortunately, the lack of proper error handling here has been abused for several Qualcomm SoCs upstream, causing early boot crashes in several situations [1, 2].

Avoid these early crashes by erroring out when any of the required DT properties are missing. Note that this will break some of the existing DTs upstream (mainly BAM instances related to the crypto engine). However, clearly these DTs have never been tested properly, since the error in the kernel log was just ignored. It's safer to disable the crypto engine for these broken DTBs.

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

---
 drivers/dma/qcom/bam_dma.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

@@ -1266,13 +1266,17 @@ static int bam_dma_probe(struct platform
 	if (bdev->controlled_remotely) {
 		ret = of_property_read_u32(pdev->dev.of_node, "num-channels",
 					   &bdev->num_channels);
-		if (ret)
+		if (ret) {
 			dev_err(bdev->dev, "num-channels unspecified in dt\n");
+			return ret;
+		}
 
 		ret = of_property_read_u32(pdev->dev.of_node, "qcom,num-ees",
 					   &bdev->num_ees);
-		if (ret)
+		if (ret) {
 			dev_err(bdev->dev, "num-ees unspecified in dt\n");
+			return ret;
+		}
 	}
 
 	bdev->bamclk = devm_clk_get(bdev->dev, "bam_clk");

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

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

From: Håkon Bugge <[email protected]>

commit 4351ca3fcb3ffecf12631b4996bf085a2dad0db6 upstream.

We need to increment i_fastreg_wrs before we bail out from rds_ib_post_reg_frmr().

We have a fixed budget of how many FRWR operations that can be outstanding using the dedicated QP used for memory registrations and de-registrations. This budget is enforced by the atomic_t i_fastreg_wrs. If we bail out early in rds_ib_post_reg_frmr(), we will "leak" the possibility of posting an FRWR operation, and if that accumulates, no FRWR operation can be carried out.

---
 net/rds/ib_frmr.c |   20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

@@ -133,12 +133,15 @@ static int rds_ib_post_reg_frmr(struct r
 
 	ret = ib_map_mr_sg_zbva(frmr->mr, ibmr->sg, ibmr->sg_dma_len,
 				&off, PAGE_SIZE);
-	if (unlikely(ret != ibmr->sg_dma_len))
-		return ret < 0 ? ret : -EINVAL;
+	if (unlikely(ret != ibmr->sg_dma_len)) {
+		ret = ret < 0 ? ret : -EINVAL;
+		goto out_inc;
+	}
 
-	if (cmpxchg(&frmr->fr_state,
-		    FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE)
-		return -EBUSY;
+	if (cmpxchg(&frmr->fr_state, FRMR_IS_FREE, FRMR_IS_INUSE) != FRMR_IS_FREE) {
+		ret = -EBUSY;
+		goto out_inc;
+	}
 
 	atomic_inc(&ibmr->ic->i_fastreg_inuse_count);
 

@@ -166,11 +169,10 @@ static int rds_ib_post_reg_frmr(struct r
 		/* Failure here can be because of -ENOMEM as well */
 		rds_transition_frwr_state(ibmr, FRMR_IS_INUSE, FRMR_IS_STALE);
 
-		atomic_inc(&ibmr->ic->i_fastreg_wrs);
 		if (printk_ratelimit())
 			pr_warn("RDS/IB: %s returned error(%d)\n",
 				__func__, ret);
-		goto out;
+		goto out_inc;
 	}
 
 	/* Wait for the registration to complete in order to prevent an invalid

@@ -179,8 +181,10 @@ static int rds_ib_post_reg_frmr(struct r
 	 */
 	wait_event(frmr->fr_reg_done, !frmr->fr_reg);
 
-out:
+	return ret;
 
+out_inc:
+	atomic_inc(&ibmr->ic->i_fastreg_wrs);
 	return ret;
 }
 

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

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

From: Charles Keepax <[email protected]>

[ Upstream commit b4799520dcd6fe1e14495cecbbe9975d847cd482 ]

---
 sound/soc/codecs/wm8940.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index c194fbde8ad6e..a02554b8edf71 100644
@@ -218,7 +218,7 @@ static const struct snd_kcontrol_new wm8940_snd_controls[] = {
 	SOC_SINGLE_TLV("Digital Capture Volume", WM8940_ADCVOL,
 		       0, 255, 0, wm8940_adc_tlv),
 	SOC_ENUM("Mic Bias Level", wm8940_mic_bias_level_enum),
-	SOC_SINGLE_TLV("Capture Boost Volue", WM8940_ADCBOOST,
+	SOC_SINGLE_TLV("Capture Boost Volume", WM8940_ADCBOOST,
 		       8, 1, 0, wm8940_capture_boost_vol_tlv),
 	SOC_SINGLE_TLV("Speaker Playback Volume", WM8940_SPKVOL,
 		       0, 63, 0, wm8940_spk_vol_tlv),

2.51.0

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

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

From: Charles Keepax <[email protected]>

[ Upstream commit 9b17d3724df55ecc2bc67978822585f2b023be48 ]

Using a single value of 22500000 for both 48000Hz and 44100Hz audio will sometimes result in returning wrong dividers due to rounding. Update the code to use the actual value for both.

---
 sound/soc/codecs/wm8974.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

index dc4fe4f5239d6..f32527ed06fb5 100644
@@ -427,10 +427,14 @@ static int wm8974_update_clocks(struct snd_soc_dai *dai)
 	fs256 = 256 * priv->fs;
 
 	f = wm8974_get_mclkdiv(priv->mclk, fs256, &mclkdiv);
-
 	if (f != priv->mclk) {
 		/* The PLL performs best around 90MHz */
-		fpll = wm8974_get_mclkdiv(22500000, fs256, &mclkdiv);
+		if (fs256 % 8000)
+			f = 22579200;
+		else
+			f = 24576000;
+
+		fpll = wm8974_get_mclkdiv(f, fs256, &mclkdiv);
 	}
 
 	wm8974_set_dai_pll(dai, 0, 0, priv->mclk, fpll);

2.51.0

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

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

From: Colin Ian King <[email protected]>

[ Upstream commit 35fc531a59694f24a2456569cf7d1a9c6436841c ]

The dev_err message is reporting an error about capture streams however it is using the incorrect variable num_playback instead of num_capture. Fix this by using the correct variable num_capture.

---
 sound/soc/sof/intel/hda-stream.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 0c11fceb28a7a..d3edc40c7f473 100644
@@ -655,7 +655,7 @@ int hda_dsp_stream_init(struct snd_sof_dev *sdev)
 
 	if (num_capture >= SOF_HDA_CAPTURE_STREAMS) {
 		dev_err(sdev->dev, "error: too many capture streams %d\n",
-			num_playback);
+			num_capture);
 		return -EINVAL;
 	}
 

2.51.0

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

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

From: Jakob Koschel <[email protected]>

[ Upstream commit 7975f080d3557725160a878b1a64339043ba3d91 ]

To move the list iterator variable into the list_for_each_entry_*() macro in the future it should be avoided to use the list iterator variable after the loop body.

To *never* use the list iterator variable after the loop it was concluded to use a separate iterator variable [1].

Stable-dep-of: 8d63c83d8eb9 ("USB: gadget: dummy-hcd: Fix locking bug in RT-enabled kernels")

---
 drivers/usb/gadget/udc/dummy_hcd.c |   17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

@@ -748,7 +748,7 @@ static int dummy_dequeue(struct usb_ep *
 	struct dummy		*dum;
 	int			retval = -EINVAL;
 	unsigned long		flags;
-	struct dummy_request	*req = NULL;
+	struct dummy_request	*req = NULL, *iter;
 
 	if (!_ep || !_req)
 		return retval;

@@ -760,13 +760,14 @@ static int dummy_dequeue(struct usb_ep *
 
 	local_irq_save(flags);
 	spin_lock(&dum->lock);
-	list_for_each_entry(req, &ep->queue, queue) {
-		if (&req->req == _req) {
-			list_del_init(&req->queue);
-			_req->status = -ECONNRESET;
-			retval = 0;
-			break;
-		}
+	list_for_each_entry(iter, &ep->queue, queue) {
+		if (&iter->req != _req)
+			continue;
+		list_del_init(&iter->queue);
+		_req->status = -ECONNRESET;
+		req = iter;
+		retval = 0;
+		break;
 	}
 	spin_unlock(&dum->lock);
 

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

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

From: Alan Stern <[email protected]>

[ Upstream commit 8d63c83d8eb922f6c316320f50c82fa88d099bea ]

Yunseong Kim and the syzbot fuzzer both reported a problem in RT-enabled kernels caused by the way dummy-hcd mixes interrupt management and spin-locking. The pattern was:

	local_irq_save(flags);
	spin_lock(&dum->lock);
	...
	spin_unlock(&dum->lock);
	...		// calls usb_gadget_giveback_request()
	local_irq_restore(flags);

The code was written this way because usb_gadget_giveback_request() needs to be called with interrupts disabled and the private lock not held.

While this pattern works fine in non-RT kernels, it's not good when RT is enabled. RT kernels handle spinlocks much like mutexes; in particular, spin_lock() may sleep. But sleeping is not allowed while local interrupts are disabled.

To fix the problem, rewrite the code to conform to the pattern used elsewhere in dummy-hcd and other UDC drivers:

	spin_lock_irqsave(&dum->lock, flags);
	...
	spin_unlock(&dum->lock);
	usb_gadget_giveback_request(...);
	spin_lock(&dum->lock);
	...
	spin_unlock_irqrestore(&dum->lock, flags);

This approach satisfies the RT requirements.

---
 drivers/usb/gadget/udc/dummy_hcd.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -758,8 +758,7 @@ static int dummy_dequeue(struct usb_ep *
 	if (!dum->driver)
 		return -ESHUTDOWN;
 
-	local_irq_save(flags);
-	spin_lock(&dum->lock);
+	spin_lock_irqsave(&dum->lock, flags);
 	list_for_each_entry(iter, &ep->queue, queue) {
 		if (&iter->req != _req)
 			continue;

@@ -769,15 +768,16 @@ static int dummy_dequeue(struct usb_ep *
 		retval = 0;
 		break;
 	}
-	spin_unlock(&dum->lock);
 
 	if (retval == 0) {
 		dev_dbg(udc_dev(dum),
 				"dequeued req %p from %s, len %d buf %p\n",
 				req, _ep->name, _req->length, _req->buf);
+		spin_unlock(&dum->lock);
 		usb_gadget_giveback_request(_ep, _req);
+		spin_lock(&dum->lock);
 	}
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&dum->lock, flags);
 	return retval;
 }
 

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

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

From: Hugo Villeneuve <[email protected]>

[ Upstream commit 535fd4c98452c87537a40610abba45daf5761ec6 ]

When trying to set MCR[2], XON1 is incorrectly accessed instead. And when writing to the TCR register to configure flow control levels, we are incorrectly writing to the MSR register. The default value of $00 is then used for TCR, which means that selectable trigger levels in FCR are used in place of TCR.

TCR/TLR access requires EFR[4] (enable enhanced functions) and MCR[2] to be set. EFR[4] is already set in probe().

MCR access requires LCR[7] to be zero.

Since LCR is set to $BF when trying to set MCR[2], XON1 is incorrectly accessed instead because MCR shares the same address space as XON1.

Since MCR[2] is unmodified and still zero, when writing to TCR we are in fact writing to MSR because TCR/TLR registers share the same address space as MSR/SPR.

Fix by first removing useless reconfiguration of EFR[4] (enable enhanced functions), as it is already enabled in sc16is7xx_probe() since commit 43c51bb573aa ("sc16is7xx: make sure device is in suspend once probed"). Now LCR is $00, which means that MCR access is enabled.

Also remove regcache_cache_bypass() calls since we no longer access the enhanced registers set, and TCR is already declared as volatile (in fact by declaring MSR as volatile, which shares the same address).

Finally disable access to TCR/TLR registers after modifying them by clearing MCR[2].

Note: the comment about "... and internal clock div" is wrong and can be
ignored/removed as access to internal clock div registers (DLL/DLH) is permitted only when LCR[7] is logic 1, not when enhanced features is enabled. And DLL/DLH access is not needed in sc16is7xx_startup().

---
 drivers/tty/serial/sc16is7xx.c |   13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

@@ -1032,16 +1032,6 @@ static int sc16is7xx_startup(struct uart
 	sc16is7xx_port_write(port, SC16IS7XX_FCR_REG,
 			     SC16IS7XX_FCR_FIFO_BIT);
 
-	/* Enable EFR */
-	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
-			     SC16IS7XX_LCR_CONF_MODE_B);
-
-	regcache_cache_bypass(s->regmap, true);
-
-	/* Enable write access to enhanced features and internal clock div */
-	sc16is7xx_port_write(port, SC16IS7XX_EFR_REG,
-			     SC16IS7XX_EFR_ENABLE_BIT);
-
 	/* Enable TCR/TLR */
 	sc16is7xx_port_update(port, SC16IS7XX_MCR_REG,
 			      SC16IS7XX_MCR_TCRTLR_BIT,

@@ -1053,7 +1043,8 @@ static int sc16is7xx_startup(struct uart
 			     SC16IS7XX_TCR_RX_RESUME(24) |
 			     SC16IS7XX_TCR_RX_HALT(48));
 
-	regcache_cache_bypass(s->regmap, false);
+	/* Disable TCR/TLR access */
+	sc16is7xx_port_update(port, SC16IS7XX_MCR_REG, SC16IS7XX_MCR_TCRTLR_BIT, 0);
 
 	/* Now, initialize the UART */
 	sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_WORD_LEN_8);

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

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

From: Philipp Zabel <[email protected]>

[ Upstream commit d64c732dfc9edcd57feb693c23162117737e426b ]

Allow probing rfkill-gpio via device tree. This hooks up the already existing support that was started in commit 262c91ee5e52 ("net:
rfkill: gpio: prepare for DT and ACPI support") via the "rfkill-gpio" compatible, with the "name" and "type" properties renamed to "label" and "radio-type", respectively, in the device tree case.

Stable-dep-of: b6f56a44e4c1 ("net: rfkill: gpio: Fix crash due to dereferencering uninitialized pointer")

---
 net/rfkill/rfkill-gpio.c |   20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

@@ -79,6 +79,8 @@ static int rfkill_gpio_probe(struct plat
 {
 	struct rfkill_gpio_data *rfkill;
 	struct gpio_desc *gpio;
+	const char *name_property;
+	const char *type_property;
 	const char *type_name;
 	int ret;
 

@@ -86,8 +88,15 @@ static int rfkill_gpio_probe(struct plat
 	if (!rfkill)
 		return -ENOMEM;
 
-	device_property_read_string(&pdev->dev, "name", &rfkill->name);
-	device_property_read_string(&pdev->dev, "type", &type_name);
+	if (dev_of_node(&pdev->dev)) {
+		name_property = "label";
+		type_property = "radio-type";
+	} else {
+		name_property = "name";
+		type_property = "type";
+	}
+	device_property_read_string(&pdev->dev, name_property, &rfkill->name);
+	device_property_read_string(&pdev->dev, type_property, &type_name);
 
 	if (!rfkill->name)
 		rfkill->name = dev_name(&pdev->dev);

@@ -169,12 +178,19 @@ static const struct acpi_device_id rfkil
 MODULE_DEVICE_TABLE(acpi, rfkill_acpi_match);
 #endif
 
+static const struct of_device_id rfkill_of_match[] __maybe_unused = {
+	{ .compatible = "rfkill-gpio", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, rfkill_of_match);
+
 static struct platform_driver rfkill_gpio_driver = {
 	.probe = rfkill_gpio_probe,
 	.remove = rfkill_gpio_remove,
 	.driver = {
 		.name = "rfkill_gpio",
 		.acpi_match_table = ACPI_PTR(rfkill_acpi_match),
+		.of_match_table = of_match_ptr(rfkill_of_match),
 	},
 };
 

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

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

From: Hans de Goede <[email protected]>

[ Upstream commit b6f56a44e4c1014b08859dcf04ed246500e310e5 ]

Since commit 7d5e9737efda ("net: rfkill: gpio: get the name and type from device property") rfkill_find_type() gets called with the possibly uninitialized "const char *type_name;" local variable.

On x86 systems when rfkill-gpio binds to a "BCM4752" or "LNV4752" acpi_device, the rfkill->type is set based on the ACPI acpi_device_id:

        rfkill->type = (unsigned)id->driver_data;

and there is no "type" property so device_property_read_string() will fail and leave type_name uninitialized, leading to a potential crash.

rfkill_find_type() does accept a NULL pointer, fix the potential crash by initializing type_name to NULL.

Note likely sofar this has not been caught because:

1. Not many x86 machines actually have a "BCM4752"/"LNV4752" acpi_device
2. The stack happened to contain NULL where type_name is stored

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

@@ -78,10 +78,10 @@ static int rfkill_gpio_acpi_probe(struct
 static int rfkill_gpio_probe(struct platform_device *pdev)
 {
 	struct rfkill_gpio_data *rfkill;
-	struct gpio_desc *gpio;
+	const char *type_name = NULL;
 	const char *name_property;
 	const char *type_property;
-	const char *type_name;
+	struct gpio_desc *gpio;
 	int ret;
 
 	rfkill = devm_kzalloc(&pdev->dev, sizeof(*rfkill), GFP_KERNEL);

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

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

From: "Maciej S. Szmigiero" <[email protected]>

[ Upstream commit d02e48830e3fce9701265f6c5a58d9bdaf906a76 ]

Commit 3bbf3565f48c ("svm: Do not intercept CR8 when enable AVIC") inhibited pre-VMRUN sync of TPR from LAPIC into VMCB::V_TPR in sync_lapic_to_cr8() when AVIC is active.

AVIC does automatically sync between these two fields, however it does so only on explicit guest writes to one of these fields, not on a bare VMRUN.

This meant that when AVIC is enabled host changes to TPR in the LAPIC state might not get automatically copied into the V_TPR field of VMCB.

This is especially true when it is the userspace setting LAPIC state via KVM_SET_LAPIC ioctl() since userspace does not have access to the guest VMCB.

Practice shows that it is the V_TPR that is actually used by the AVIC to decide whether to issue pending interrupts to the CPU (not TPR in TASKPRI), so any leftover value in V_TPR will cause serious interrupt delivery issues in the guest when AVIC is enabled.

Fix this issue by doing pre-VMRUN TPR sync from LAPIC into VMCB::V_TPR even when AVIC is enabled.

---
 arch/x86/kvm/svm.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -5580,8 +5580,7 @@ static inline void sync_lapic_to_cr8(str
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 cr8;
 
-	if (svm_nested_virtualize_tpr(vcpu) ||
-	    kvm_vcpu_apicv_active(vcpu))
+	if (svm_nested_virtualize_tpr(vcpu))
 		return;
 
 	cr8 = kvm_get_cr8(vcpu);

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

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

From: Johan Hovold <[email protected]>

commit e19bcea99749ce8e8f1d359f68ae03210694ad56 upstream.

Make sure to drop the reference to the control device taken by of_find_device_by_node() during probe when the driver is unbound.

---
 drivers/phy/ti/phy-ti-pipe3.c |   13 +++++++++++++
 1 file changed, 13 insertions(+)

@@ -667,12 +667,20 @@ static int ti_pipe3_get_clk(struct ti_pi
 	return 0;
 }
 
+static void ti_pipe3_put_device(void *_dev)
+{
+	struct device *dev = _dev;
+
+	put_device(dev);
+}
+
 static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy)
 {
 	struct device *dev = phy->dev;
 	struct device_node *node = dev->of_node;
 	struct device_node *control_node;
 	struct platform_device *control_pdev;
+	int ret;
 
 	phy->phy_power_syscon = syscon_regmap_lookup_by_phandle(node,
 							"syscon-phy-power");

@@ -703,6 +711,11 @@ static int ti_pipe3_get_sysctrl(struct t
 		}
 
 		phy->control_dev = &control_pdev->dev;
+
+		ret = devm_add_action_or_reset(dev, ti_pipe3_put_device,
+					       phy->control_dev);
+		if (ret)
+			return ret;
 	}
 
 	if (phy->mode == PIPE3_MODE_PCIE) {

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

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

From: Cristian Ciocaltea <[email protected]>

[ Upstream commit 231225d8a20f8668b4fd6601d54a2fac0e0ab7a5 ]

Address a couple of comment formatting issues indicated by checkpatch.pl:

WARNING: Block comments use a trailing */ on a separate line

---
 sound/usb/mixer_quirks.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

index bc065ec997f39..96397a4fdf873 100644
@@ -75,7 +75,8 @@ static int snd_create_std_mono_ctl_offset(struct usb_mixer_interface *mixer,
 	cval->idx_off = idx_off;
 
 	/* get_min_max() is called only for integer volumes later,
-	 * so provide a short-cut for booleans */
+	 * so provide a short-cut for booleans
+	 */
 	cval->min = 0;
 	cval->max = 1;
 	cval->res = 0;

@@ -2502,7 +2503,8 @@ static void snd_dragonfly_quirk_db_scale(struct usb_mixer_interface *mixer,
 					 struct snd_kcontrol *kctl)
 {
 	/* Approximation using 10 ranges based on output measurement on hw v1.2.
-	 * This seems close to the cubic mapping e.g. alsamixer uses. */
+	 * This seems close to the cubic mapping e.g. alsamixer uses.
+	 */
 	static const DECLARE_TLV_DB_RANGE(scale,
 		 0,  1, TLV_DB_MINMAX_ITEM(-5300, -4970),
 		 2,  5, TLV_DB_MINMAX_ITEM(-4710, -4160),

2.51.0

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

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

From: Cristian Ciocaltea <[email protected]>

[ Upstream commit 03ddd3bdb94df3edb1f2408b57cfb00b3d92a208 ]

Handle report from checkpatch.pl:

CHECK: multiple assignments should be avoided

---
 sound/usb/mixer_quirks.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

index 96397a4fdf873..22f483fee5f8c 100644
@@ -1592,7 +1592,8 @@ static int snd_microii_spdif_default_put(struct snd_kcontrol *kcontrol,
 	unsigned int pval, pval_old;
 	int err;
 
-	pval = pval_old = kcontrol->private_value;
+	pval = kcontrol->private_value;
+	pval_old = pval;
 	pval &= 0xfffff0f0;
 	pval |= (ucontrol->value.iec958.status[1] & 0x0f) << 8;
 	pval |= (ucontrol->value.iec958.status[0] & 0x0f);

2.51.0

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

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

From: Cristian Ciocaltea <[email protected]>

[ Upstream commit f2d6d660e8fd5f4467e80743f82119201e67fa9c ]

Handle report from checkpatch.pl:

CHECK: Comparison to NULL could be written "t->name"

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

index 22f483fee5f8c..f318b80d646d5 100644
@@ -125,7 +125,7 @@ static int snd_create_std_mono_table(struct usb_mixer_interface *mixer,
 {
 	int err;
 
-	while (t->name != NULL) {
+	while (t->name) {
 		err = snd_create_std_mono_ctl(mixer, t->unitid, t->control,
 				t->cmask, t->val_type, t->name, t->tlv_callback);
 		if (err < 0)

2.51.0

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

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

From: Cristian Ciocaltea <[email protected]>

[ Upstream commit 9cea7425595697802e8d55a322a251999554b8b1 ]

Adding a memory barrier before wake_up() in snd_usb_soundblaster_remote_complete() is supposed to ensure the write to mixer->rc_code is visible in wait_event_interruptible() from snd_usb_sbrc_hwdep_read().

However, this is not really necessary, since wake_up() is just a wrapper over __wake_up() which already executes a full memory barrier before accessing the state of the task to be waken up.

Drop the redundant call to wmb() and implicitly fix the checkpatch complaint:

WARNING: memory barrier without comment

---
 sound/usb/mixer_quirks.c | 1 -
 1 file changed, 1 deletion(-)

index f318b80d646d5..03d49d4c5141d 100644
@@ -207,7 +207,6 @@ static void snd_usb_soundblaster_remote_complete(struct urb *urb)
 	if (code == rc->mute_code)
 		snd_usb_mixer_notify_id(mixer, rc->mute_mixer_id);
 	mixer->rc_code = code;
-	wmb();
 	wake_up(&mixer->rc_waitq);
 }
 

2.51.0

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

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

From: Bjorn Andersson <[email protected]>

commit 25daf9af0ac1bf12490b723b5efaf8dcc85980bc upstream.

Firmware that doesn't provide section headers leave both e_shentsize and e_shnum 0, which obvious isn't compatible with the newly introduced stricter checks.

Make the section-related checks conditional on either of these values being non-zero.

---
 drivers/soc/qcom/mdt_loader.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

@@ -39,12 +39,14 @@ static bool mdt_header_valid(const struc
 	if (phend > fw->size)
 		return false;
 
-	if (ehdr->e_shentsize != sizeof(struct elf32_shdr))
-		return false;
+	if (ehdr->e_shentsize || ehdr->e_shnum) {
+		if (ehdr->e_shentsize != sizeof(struct elf32_shdr))
+			return false;
 
-	shend = size_add(size_mul(sizeof(struct elf32_shdr), ehdr->e_shnum), ehdr->e_shoff);
-	if (shend > fw->size)
-		return false;
+		shend = size_add(size_mul(sizeof(struct elf32_shdr), ehdr->e_shnum), ehdr->e_shoff);
+		if (shend > fw->size)
+			return false;
+	}
 
 	return true;
 }

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

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

From: Miaohe Lin <[email protected]>

[ Upstream commit d613f53c83ec47089c4e25859d5e8e0359f6f8da ]

When I did memory failure tests, below panic occurs:

page dumped because: VM_BUG_ON_PAGE(PagePoisoned(page))
kernel BUG at include/linux/page-flags.h:616!
Oops: invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
CPU: 3 PID: 720 Comm: bash Not tainted 6.10.0-rc1-00195-g148743902568 #40
RIP: 0010:unpoison_memory+0x2f3/0x590
RSP: 0018:ffffa57fc8787d60 EFLAGS: 00000246
RAX: 0000000000000037 RBX: 0000000000000009 RCX: ffff9be25fcdc9c8
RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff9be25fcdc9c0
RBP: 0000000000300000 R08: ffffffffb4956f88 R09: 0000000000009ffb
R10: 0000000000000284 R11: ffffffffb4926fa0 R12: ffffe6b00c000000
R13: ffff9bdb453dfd00 R14: 0000000000000000 R15: fffffffffffffffe
FS:  00007f08f04e4740(0000) GS:ffff9be25fcc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000564787a30410 CR3: 000000010d4e2000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 unpoison_memory+0x2f3/0x590
 simple_attr_write_xsigned.constprop.0.isra.0+0xb3/0x110
 debugfs_attr_write+0x42/0x60
 full_proxy_write+0x5b/0x80
 vfs_write+0xd5/0x540
 ksys_write+0x64/0xe0
 do_syscall_64+0xb9/0x1d0
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f08f0314887
RSP: 002b:00007ffece710078 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000009 RCX: 00007f08f0314887
RDX: 0000000000000009 RSI: 0000564787a30410 RDI: 0000000000000001
RBP: 0000564787a30410 R08: 000000000000fefe R09: 000000007fffffff
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000009
R13: 00007f08f041b780 R14: 00007f08f0417600 R15: 00007f08f0416a00
 </TASK>
Modules linked in: hwpoison_inject
---[ end trace 0000000000000000 ]---
RIP: 0010:unpoison_memory+0x2f3/0x590
RSP: 0018:ffffa57fc8787d60 EFLAGS: 00000246
RAX: 0000000000000037 RBX: 0000000000000009 RCX: ffff9be25fcdc9c8
RDX: 0000000000000000 RSI: 0000000000000027 RDI: ffff9be25fcdc9c0
RBP: 0000000000300000 R08: ffffffffb4956f88 R09: 0000000000009ffb
R10: 0000000000000284 R11: ffffffffb4926fa0 R12: ffffe6b00c000000
R13: ffff9bdb453dfd00 R14: 0000000000000000 R15: fffffffffffffffe
FS:  00007f08f04e4740(0000) GS:ffff9be25fcc0000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000564787a30410 CR3: 000000010d4e2000 CR4: 00000000000006f0
Kernel panic - not syncing: Fatal exception
Kernel Offset: 0x31c00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff)
---[ end Kernel panic - not syncing: Fatal exception ]---

The root cause is that unpoison_memory() tries to check the PG_HWPoison flags of an uninitialized page. So VM_BUG_ON_PAGE(PagePoisoned(page)) is triggered. This can be reproduced by below steps:

1.Offline memory block:

echo offline > /sys/devices/system/memory/memory12/state

2.Get offlined memory pfn:

page-types -b n -rlN

3.Write pfn to unpoison-pfn

echo <pfn> > /sys/kernel/debug/hwpoison/unpoison-pfn

This scenario can be identified by pfn_to_online_page() returning NULL. And ZONE_DEVICE pages are never expected, so we can simply fail if pfn_to_online_page() == NULL to fix the bug.

---
 mm/memory-failure.c |    7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

@@ -1543,10 +1543,9 @@ int unpoison_memory(unsigned long pfn)
 	static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
 					DEFAULT_RATELIMIT_BURST);
 
-	if (!pfn_valid(pfn))
-		return -ENXIO;
-
-	p = pfn_to_page(pfn);
+	p = pfn_to_online_page(pfn);
+	if (!p)
+		return -EIO;
 	page = compound_head(p);
 
 	if (!PageHWPoison(p)) {

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

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

From: Takashi Sakamoto <[email protected]>

[ Upstream commit aea3493246c474bc917d124d6fb627663ab6bef0 ]

The ALSA HwDep character device of the firewire-motu driver incorrectly returns EPOLLOUT in poll(2), even though the driver implements no operation for write(2). This misleads userspace applications to believe write() is allowed, potentially resulting in unnecessarily wakeups.

This issue dates back to the driver's initial code added by a commit 71c3797779d3 ("ALSA: firewire-motu: add hwdep interface"), and persisted when POLLOUT was updated to EPOLLOUT by a commit a9a08845e9ac ('vfs: do bulk POLL* -> EPOLL* replacement("").').

This commit fixes the bug.

---
 sound/firewire/motu/motu-hwdep.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index 0764a477052a2..5e1254f106bf8 100644
@@ -73,7 +73,7 @@ static __poll_t hwdep_poll(struct snd_hwdep *hwdep, struct file *file,
 		events = 0;
 	spin_unlock_irq(&motu->lock);
 
-	return events | EPOLLOUT;
+	return events;
 }
 
 static int hwdep_get_info(struct snd_motu *motu, void __user *arg)

2.51.0

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

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

From: Liao Yuanhong <[email protected]>

[ Upstream commit a33b375ab5b3a9897a0ab76be8258d9f6b748628 ]

The variable ret is declared as a u32 type, but it is assigned a value of -EOPNOTSUPP. Since unsigned types cannot correctly represent negative values, the type of ret should be changed to int.

---
 net/mac80211/driver-ops.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index f4c7e0af896b1..ce902f8a08942 100644
@@ -1237,7 +1237,7 @@ drv_get_ftm_responder_stats(struct ieee80211_local *local,
 			    struct ieee80211_sub_if_data *sdata,
 			    struct cfg80211_ftm_responder_stats *ftm_stats)
 {
-	u32 ret = -EOPNOTSUPP;
+	int ret = -EOPNOTSUPP;
 
 	if (local->ops->get_ftm_responder_stats)
 		ret = local->ops->get_ftm_responder_stats(&local->hw,

2.51.0

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

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

From: Geert Uytterhoeven <[email protected]>

[ Upstream commit d1dfcdd30140c031ae091868fb5bed084132bca1 ]

As described in the added code comment, a reference to .exit.text is ok for drivers registered via platform_driver_probe(). Make this explicit to prevent the following section mismatch warning

    WARNING: modpost: drivers/pcmcia/omap_cf: section mismatch in reference: omap_cf_driver+0x4 (section: .data) -> omap_cf_remove (section: .exit.text)

that triggers on an omap1_defconfig + CONFIG_OMAP_CF=m build.

---
 drivers/pcmcia/omap_cf.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

index 0a04eb04f3a28..2e7559b7f103e 100644
@@ -327,7 +327,13 @@ static int __exit omap_cf_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct platform_driver omap_cf_driver = {
+/*
+ * omap_cf_remove() lives in .exit.text. For drivers registered via
+ * platform_driver_probe() this is ok because they cannot get unbound at
+ * runtime. So mark the driver struct with __refdata to prevent modpost
+ * triggering a section mismatch warning.
+ */
+static struct platform_driver omap_cf_driver __refdata = {
 	.driver = {
 		.name	= (char *) driver_name,
 	},

2.51.0

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

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

From: Chen Ridong <[email protected]>

[ Upstream commit 79f919a89c9d06816dbdbbd168fa41d27411a7f9 ]

A hung task can occur during [1] LTP cgroup testing when repeatedly mounting/unmounting perf_event and net_prio controllers with systemd.unified_cgroup_hierarchy=1. The hang manifests in cgroup_lock_and_drain_offline() during root destruction.

Related case:
cgroup_fj_function_perf_event cgroup_fj_function.sh perf_event cgroup_fj_function_net_prio cgroup_fj_function.sh net_prio

Call Trace:
	cgroup_lock_and_drain_offline+0x14c/0x1e8
	cgroup_destroy_root+0x3c/0x2c0
	css_free_rwork_fn+0x248/0x338
	process_one_work+0x16c/0x3b8
	worker_thread+0x22c/0x3b0
	kthread+0xec/0x100
	ret_from_fork+0x10/0x20

Root Cause:

CPU0                            CPU1
mount perf_event                umount net_prio
cgroup1_get_tree                cgroup_kill_sb
rebind_subsystems               // root destruction enqueues
				// cgroup_destroy_wq
// kill all perf_event css
                                // one perf_event css A is dying
                                // css A offline enqueues cgroup_destroy_wq
                                // root destruction will be executed first
                                css_free_rwork_fn
                                cgroup_destroy_root
                                cgroup_lock_and_drain_offline
                                // some perf descendants are dying
                                // cgroup_destroy_wq max_active = 1
                                // waiting for css A to die

Problem scenario:
1. CPU0 mounts perf_event (rebind_subsystems)
2. CPU1 unmounts net_prio (cgroup_kill_sb), queuing root destruction work
3. A dying perf_event CSS gets queued for offline after root destruction
4. Root destruction waits for offline completion, but offline work is blocked behind root destruction in cgroup_destroy_wq (max_active=1)

Solution:
Split cgroup_destroy_wq into three dedicated workqueues:
cgroup_offline_wq – Handles CSS offline operations cgroup_release_wq – Manages resource release cgroup_free_wq – Performs final memory deallocation

This separation eliminates blocking in the CSS free path while waiting for offline operations to complete.

[1] https://github.com/linux-test-project/ltp/blob/master/runtest/controllers

---
 kernel/cgroup/cgroup.c | 43 +++++++++++++++++++++++++++++++++++-------
 1 file changed, 36 insertions(+), 7 deletions(-)

index 801022a8899b5..b761d70eccbf4 100644
@@ -114,8 +114,31 @@ DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem);
  * of concurrent destructions.  Use a separate workqueue so that cgroup
  * destruction work items don't end up filling up max_active of system_wq
  * which may lead to deadlock.
+ *
+ * A cgroup destruction should enqueue work sequentially to:
+ * cgroup_offline_wq: use for css offline work
+ * cgroup_release_wq: use for css release work
+ * cgroup_free_wq: use for free work
+ *
+ * Rationale for using separate workqueues:
+ * The cgroup root free work may depend on completion of other css offline
+ * operations. If all tasks were enqueued to a single workqueue, this could
+ * create a deadlock scenario where:
+ * - Free work waits for other css offline work to complete.
+ * - But other css offline work is queued after free work in the same queue.
+ *
+ * Example deadlock scenario with single workqueue (cgroup_destroy_wq):
+ * 1. umount net_prio
+ * 2. net_prio root destruction enqueues work to cgroup_destroy_wq (CPUx)
+ * 3. perf_event CSS A offline enqueues work to same cgroup_destroy_wq (CPUx)
+ * 4. net_prio cgroup_destroy_root->cgroup_lock_and_drain_offline.
+ * 5. net_prio root destruction blocks waiting for perf_event CSS A offline,
+ *    which can never complete as it's behind in the same queue and
+ *    workqueue's max_active is 1.
  */
-static struct workqueue_struct *cgroup_destroy_wq;
+static struct workqueue_struct *cgroup_offline_wq;
+static struct workqueue_struct *cgroup_release_wq;
+static struct workqueue_struct *cgroup_free_wq;
 
 /* generate an array of cgroup subsystem pointers */
 #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,

@@ -5233,7 +5256,7 @@ static void css_release_work_fn(struct work_struct *work)
 	mutex_unlock(&cgroup_mutex);
 
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
-	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
+	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);
 }
 
 static void css_release(struct percpu_ref *ref)

@@ -5242,7 +5265,7 @@ static void css_release(struct percpu_ref *ref)
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
 	INIT_WORK(&css->destroy_work, css_release_work_fn);
-	queue_work(cgroup_destroy_wq, &css->destroy_work);
+	queue_work(cgroup_release_wq, &css->destroy_work);
 }
 
 static void init_and_link_css(struct cgroup_subsys_state *css,

@@ -5373,7 +5396,7 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 err_free_css:
 	list_del_rcu(&css->rstat_css_node);
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
-	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
+	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);
 	return ERR_PTR(err);
 }
 

@@ -5626,7 +5649,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 
 	if (atomic_dec_and_test(&css->online_cnt)) {
 		INIT_WORK(&css->destroy_work, css_killed_work_fn);
-		queue_work(cgroup_destroy_wq, &css->destroy_work);
+		queue_work(cgroup_offline_wq, &css->destroy_work);
 	}
 }
 

@@ -6002,8 +6025,14 @@ static int __init cgroup_wq_init(void)
 	 * We would prefer to do this in cgroup_init() above, but that
 	 * is called before init_workqueues(): so leave this until after.
 	 */
-	cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
-	BUG_ON(!cgroup_destroy_wq);
+	cgroup_offline_wq = alloc_workqueue("cgroup_offline", 0, 1);
+	BUG_ON(!cgroup_offline_wq);
+
+	cgroup_release_wq = alloc_workqueue("cgroup_release", 0, 1);
+	BUG_ON(!cgroup_release_wq);
+
+	cgroup_free_wq = alloc_workqueue("cgroup_free", 0, 1);
+	BUG_ON(!cgroup_free_wq);
 	return 0;
 }
 core_initcall(cgroup_wq_init);

2.51.0

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

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

From: Tetsuo Handa <[email protected]>

[ Upstream commit 06e02da29f6f1a45fc07bd60c7eaf172dc21e334 ]

Since j1939_sk_bind() and j1939_sk_release() call j1939_local_ecu_put() when J1939_SOCK_BOUND was already set, but the error handling path for j1939_sk_bind() will not set J1939_SOCK_BOUND when j1939_local_ecu_get() fails, j1939_local_ecu_get() needs to undo priv->ents[sa].nusers++ when j1939_local_ecu_get() returns an error.

---
 net/can/j1939/bus.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

index 4866879016021..e0b966c2517cf 100644
@@ -290,8 +290,11 @@ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa)
 	if (!ecu)
 		ecu = j1939_ecu_create_locked(priv, name);
 	err = PTR_ERR_OR_ZERO(ecu);
-	if (err)
+	if (err) {
+		if (j1939_address_is_unicast(sa))
+			priv->ents[sa].nusers--;
 		goto done;
+	}
 
 	ecu->nusers++;
 	/* TODO: do we care if ecu->addr != sa? */

2.51.0

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

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

From: Chen Ni <[email protected]>

[ Upstream commit 9ca30a1b007d5fefb5752428f852a2d8d7219c1c ]

Replace comma between expressions with semicolons.

Using a ',' in place of a ';' can have unintended side effects. Although that is not the case here, it is seems best to use ';' unless ',' is intended.

Found by inspection.
No functional change intended.
Compile tested only.

---
 sound/usb/mixer_quirks.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

index cea1c970359c1..833f894a692c7 100644
@@ -757,9 +757,9 @@ static int snd_dualsense_jack_create(struct usb_mixer_interface *mixer,
 
 	mei->ih.event = snd_dualsense_ih_event;
 	mei->ih.match = snd_dualsense_ih_match;
-	mei->ih.connect = snd_dualsense_ih_connect,
-	mei->ih.disconnect = snd_dualsense_ih_disconnect,
-	mei->ih.start = snd_dualsense_ih_start,
+	mei->ih.connect = snd_dualsense_ih_connect;
+	mei->ih.disconnect = snd_dualsense_ih_disconnect;
+	mei->ih.start = snd_dualsense_ih_start;
 	mei->ih.name = name;
 	mei->ih.id_table = mei->id_table;