[PATCH AUTOSEL 4.19 01/27] iio: dummy: iio_simple_dummy: check the return value of kstrdup()

[PATCH AUTOSEL 4.19 01/27] iio: dummy: iio_simple_dummy: check the return value of kstrdup()

[Sasha Levin]

From: Xiaoke Wang <xkernel.wang@foxmail.com>

[ Upstream commit ba93642188a6fed754bf7447f638bc410e05a929 ]

kstrdup() is also a memory allocation-related function, it returns NULL
when some memory errors happen. So it is better to check the return
value of it so to catch the memory error in time. Besides, there should
have a kfree() to clear up the allocation if we get a failure later in
this function to prevent memory leak.

Signed-off-by: Xiaoke Wang <xkernel.wang@foxmail.com>
Link: https://lore.kernel.org/r/tencent_C920CFCC33B9CC1C63141FE1334A39FF8508@qq.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/iio/dummy/iio_simple_dummy.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/iio/dummy/iio_simple_dummy.c b/drivers/iio/dummy/iio_simple_dummy.c
index 62052479c349..f970b4388dda 100644
--- a/drivers/iio/dummy/iio_simple_dummy.c
+++ b/drivers/iio/dummy/iio_simple_dummy.c
@@ -571,10 +571,9 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 	struct iio_sw_device *swd;
 
 	swd = kzalloc(sizeof(*swd), GFP_KERNEL);
-	if (!swd) {
-		ret = -ENOMEM;
-		goto error_kzalloc;
-	}
+	if (!swd)
+		return ERR_PTR(-ENOMEM);
+
 	/*
 	 * Allocate an IIO device.
 	 *
@@ -586,7 +585,7 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 	indio_dev = iio_device_alloc(sizeof(*st));
 	if (!indio_dev) {
 		ret = -ENOMEM;
-		goto error_ret;
+		goto error_free_swd;
 	}
 
 	st = iio_priv(indio_dev);
@@ -617,6 +616,10 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 	 *    indio_dev->name = spi_get_device_id(spi)->name;
 	 */
 	indio_dev->name = kstrdup(name, GFP_KERNEL);
+	if (!indio_dev->name) {
+		ret = -ENOMEM;
+		goto error_free_device;
+	}
 
 	/* Provide description of available channels */
 	indio_dev->channels = iio_dummy_channels;
@@ -633,7 +636,7 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 
 	ret = iio_simple_dummy_events_register(indio_dev);
 	if (ret < 0)
-		goto error_free_device;
+		goto error_free_name;
 
 	ret = iio_simple_dummy_configure_buffer(indio_dev);
 	if (ret < 0)
@@ -650,11 +653,12 @@ static struct iio_sw_device *iio_dummy_probe(const char *name)
 	iio_simple_dummy_unconfigure_buffer(indio_dev);
 error_unregister_events:
 	iio_simple_dummy_events_unregister(indio_dev);
+error_free_name:
+	kfree(indio_dev->name);
 error_free_device:
 	iio_device_free(indio_dev);
-error_ret:
+error_free_swd:
 	kfree(swd);
-error_kzalloc:
 	return ERR_PTR(ret);
 }
 
-- 
2.35.1

[PATCH AUTOSEL 4.19 02/27] lkdtm/usercopy: Expand size of "out of frame" object

[Sasha Levin]

From: Kees Cook <keescook@chromium.org>

[ Upstream commit f387e86d3a74407bdd9c5815820ac9d060962840 ]

To be sufficiently out of range for the usercopy test to see the lifetime
mismatch, expand the size of the "bad" buffer, which will let it be
beyond current_stack_pointer regardless of stack growth direction.
Paired with the recent addition of stack depth checking under
CONFIG_HARDENED_USERCOPY=y, this will correctly start tripping again.

Reported-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Link: https://lore.kernel.org/lkml/762faf1b-0443-5ddf-4430-44a20cf2ec4d@collabora.com/
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/misc/lkdtm/usercopy.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/drivers/misc/lkdtm/usercopy.c b/drivers/misc/lkdtm/usercopy.c
index 9725aed305bb..b0e020372d11 100644
--- a/drivers/misc/lkdtm/usercopy.c
+++ b/drivers/misc/lkdtm/usercopy.c
@@ -30,12 +30,12 @@ static const unsigned char test_text[] = "This is a test.\n";
  */
 static noinline unsigned char *trick_compiler(unsigned char *stack)
 {
-	return stack + 0;
+	return stack + unconst;
 }
 
 static noinline unsigned char *do_usercopy_stack_callee(int value)
 {
-	unsigned char buf[32];
+	unsigned char buf[128];
 	int i;
 
 	/* Exercise stack to avoid everything living in registers. */
@@ -43,7 +43,12 @@ static noinline unsigned char *do_usercopy_stack_callee(int value)
 		buf[i] = value & 0xff;
 	}
 
-	return trick_compiler(buf);
+	/*
+	 * Put the target buffer in the middle of stack allocation
+	 * so that we don't step on future stack users regardless
+	 * of stack growth direction.
+	 */
+	return trick_compiler(&buf[(128/2)-32]);
 }
 
 static noinline void do_usercopy_stack(bool to_user, bool bad_frame)
@@ -66,6 +71,12 @@ static noinline void do_usercopy_stack(bool to_user, bool bad_frame)
 		bad_stack -= sizeof(unsigned long);
 	}
 
+#ifdef ARCH_HAS_CURRENT_STACK_POINTER
+	pr_info("stack     : %px\n", (void *)current_stack_pointer);
+#endif
+	pr_info("good_stack: %px-%px\n", good_stack, good_stack + sizeof(good_stack));
+	pr_info("bad_stack : %px-%px\n", bad_stack, bad_stack + sizeof(good_stack));
+
 	user_addr = vm_mmap(NULL, 0, PAGE_SIZE,
 			    PROT_READ | PROT_WRITE | PROT_EXEC,
 			    MAP_ANONYMOUS | MAP_PRIVATE, 0);
-- 
2.35.1

[PATCH AUTOSEL 4.19 03/27] tty: synclink_gt: Fix null-pointer-dereference in slgt_clean()

[Sasha Levin]

From: Zheyu Ma <zheyuma97@gmail.com>

[ Upstream commit 689ca31c542687709ba21ec2195c1fbce34fd029 ]

When the driver fails at alloc_hdlcdev(), and then we remove the driver
module, we will get the following splat:

[   25.065966] general protection fault, probably for non-canonical address 0xdffffc0000000182: 0000 [#1] PREEMPT SMP KASAN PTI
[   25.066914] KASAN: null-ptr-deref in range [0x0000000000000c10-0x0000000000000c17]
[   25.069262] RIP: 0010:detach_hdlc_protocol+0x2a/0x3e0
[   25.077709] Call Trace:
[   25.077924]  <TASK>
[   25.078108]  unregister_hdlc_device+0x16/0x30
[   25.078481]  slgt_cleanup+0x157/0x9f0 [synclink_gt]

Fix this by checking whether the 'info->netdev' is a null pointer first.

Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Zheyu Ma <zheyuma97@gmail.com>
Link: https://lore.kernel.org/r/20220410114814.3920474-1-zheyuma97@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/tty/synclink_gt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/tty/synclink_gt.c b/drivers/tty/synclink_gt.c
index afe34beec720..11c62fcd67f2 100644
--- a/drivers/tty/synclink_gt.c
+++ b/drivers/tty/synclink_gt.c
@@ -1753,6 +1753,8 @@ static int hdlcdev_init(struct slgt_info *info)
  */
 static void hdlcdev_exit(struct slgt_info *info)
 {
+	if (!info->netdev)
+		return;
 	unregister_hdlc_device(info->netdev);
 	free_netdev(info->netdev);
 	info->netdev = NULL;
-- 
2.35.1

[PATCH AUTOSEL 4.19 04/27] tty: Fix a possible resource leak in icom_probe

[Sasha Levin]

From: Huang Guobin <huangguobin4@huawei.com>

[ Upstream commit ee157a79e7c82b01ae4c25de0ac75899801f322c ]

When pci_read_config_dword failed, call pci_release_regions() and
pci_disable_device() to recycle the resource previously allocated.

Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Huang Guobin <huangguobin4@huawei.com>
Link: https://lore.kernel.org/r/20220331091005.3290753-1-huangguobin4@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/tty/serial/icom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/tty/serial/icom.c b/drivers/tty/serial/icom.c
index ad374f7c476d..cb950c78d66d 100644
--- a/drivers/tty/serial/icom.c
+++ b/drivers/tty/serial/icom.c
@@ -1501,7 +1501,7 @@ static int icom_probe(struct pci_dev *dev,
 	retval = pci_read_config_dword(dev, PCI_COMMAND, &command_reg);
 	if (retval) {
 		dev_err(&dev->dev, "PCI Config read FAILED\n");
-		return retval;
+		goto probe_exit0;
 	}
 
 	pci_write_config_dword(dev, PCI_COMMAND,
-- 
2.35.1

[PATCH AUTOSEL 4.19 05/27] drivers: staging: rtl8192u: Fix deadlock in ieee80211_beacons_stop()

[Sasha Levin]

From: Duoming Zhou <duoming@zju.edu.cn>

[ Upstream commit 806c7b53414934ba2a39449b31fd1a038e500273 ]

There is a deadlock in ieee80211_beacons_stop(), which is shown below:

   (Thread 1)              |      (Thread 2)
                           | ieee80211_send_beacon()
ieee80211_beacons_stop()   |  mod_timer()
 spin_lock_irqsave() //(1) |  (wait a time)
 ...                       | ieee80211_send_beacon_cb()
 del_timer_sync()          |  spin_lock_irqsave() //(2)
 (wait timer to stop)      |  ...

We hold ieee->beacon_lock in position (1) of thread 1 and use
del_timer_sync() to wait timer to stop, but timer handler
also need ieee->beacon_lock in position (2) of thread 2.
As a result, ieee80211_beacons_stop() will block forever.

This patch extracts del_timer_sync() from the protection of
spin_lock_irqsave(), which could let timer handler to obtain
the needed lock.

Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Link: https://lore.kernel.org/r/20220417135407.109536-1-duoming@zju.edu.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/staging/rtl8192u/ieee80211/ieee80211_softmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_softmac.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_softmac.c
index 212cc9ccbb96..426966a29d31 100644
--- a/drivers/staging/rtl8192u/ieee80211/ieee80211_softmac.c
+++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_softmac.c
@@ -529,9 +529,9 @@ static void ieee80211_beacons_stop(struct ieee80211_device *ieee)
 	spin_lock_irqsave(&ieee->beacon_lock, flags);
 
 	ieee->beacon_txing = 0;
-	del_timer_sync(&ieee->beacon_timer);
 
 	spin_unlock_irqrestore(&ieee->beacon_lock, flags);
+	del_timer_sync(&ieee->beacon_timer);
 }
 
 void ieee80211_stop_send_beacons(struct ieee80211_device *ieee)
-- 
2.35.1

[PATCH AUTOSEL 4.19 06/27] drivers: staging: rtl8192e: Fix deadlock in rtllib_beacons_stop()

[Sasha Levin]

From: Duoming Zhou <duoming@zju.edu.cn>

[ Upstream commit 9b6bdbd9337de3917945847bde262a34a87a6303 ]

There is a deadlock in rtllib_beacons_stop(), which is shown
below:

   (Thread 1)              |      (Thread 2)
                           | rtllib_send_beacon()
rtllib_beacons_stop()      |  mod_timer()
 spin_lock_irqsave() //(1) |  (wait a time)
 ...                       | rtllib_send_beacon_cb()
 del_timer_sync()          |  spin_lock_irqsave() //(2)
 (wait timer to stop)      |  ...

We hold ieee->beacon_lock in position (1) of thread 1 and
use del_timer_sync() to wait timer to stop, but timer handler
also need ieee->beacon_lock in position (2) of thread 2.
As a result, rtllib_beacons_stop() will block forever.

This patch extracts del_timer_sync() from the protection of
spin_lock_irqsave(), which could let timer handler to obtain
the needed lock.

Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Link: https://lore.kernel.org/r/20220417141641.124388-1-duoming@zju.edu.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/staging/rtl8192e/rtllib_softmac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c
index 919231fec09c..5f1dd4e2d12e 100644
--- a/drivers/staging/rtl8192e/rtllib_softmac.c
+++ b/drivers/staging/rtl8192e/rtllib_softmac.c
@@ -654,9 +654,9 @@ static void rtllib_beacons_stop(struct rtllib_device *ieee)
 	spin_lock_irqsave(&ieee->beacon_lock, flags);
 
 	ieee->beacon_txing = 0;
-	del_timer_sync(&ieee->beacon_timer);
 
 	spin_unlock_irqrestore(&ieee->beacon_lock, flags);
+	del_timer_sync(&ieee->beacon_timer);
 
 }
 
-- 
2.35.1

[PATCH AUTOSEL 4.19 07/27] USB: host: isp116x: check return value after calling platform_get_resource()

[Sasha Levin]

From: Zhen Ni <nizhen@uniontech.com>

[ Upstream commit 134a3408c2d3f7e23eb0e4556e0a2d9f36c2614e ]

It will cause null-ptr-deref if platform_get_resource() returns NULL,
we need check the return value.

Signed-off-by: Zhen Ni <nizhen@uniontech.com>
Link: https://lore.kernel.org/r/20220302033716.31272-1-nizhen@uniontech.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/usb/host/isp116x-hcd.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/isp116x-hcd.c b/drivers/usb/host/isp116x-hcd.c
index 74da136d322a..361327012c78 100644
--- a/drivers/usb/host/isp116x-hcd.c
+++ b/drivers/usb/host/isp116x-hcd.c
@@ -1541,10 +1541,12 @@ static int isp116x_remove(struct platform_device *pdev)
 
 	iounmap(isp116x->data_reg);
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	release_mem_region(res->start, 2);
+	if (res)
+		release_mem_region(res->start, 2);
 	iounmap(isp116x->addr_reg);
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(res->start, 2);
+	if (res)
+		release_mem_region(res->start, 2);
 
 	usb_put_hcd(hcd);
 	return 0;
-- 
2.35.1

[PATCH AUTOSEL 4.19 08/27] drivers: tty: serial: Fix deadlock in sa1100_set_termios()

[Sasha Levin]

From: Duoming Zhou <duoming@zju.edu.cn>

[ Upstream commit 62b2caef400c1738b6d22f636c628d9f85cd4c4c ]

There is a deadlock in sa1100_set_termios(), which is shown
below:

   (Thread 1)              |      (Thread 2)
                           | sa1100_enable_ms()
sa1100_set_termios()       |  mod_timer()
 spin_lock_irqsave() //(1) |  (wait a time)
 ...                       | sa1100_timeout()
 del_timer_sync()          |  spin_lock_irqsave() //(2)
 (wait timer to stop)      |  ...

We hold sport->port.lock in position (1) of thread 1 and
use del_timer_sync() to wait timer to stop, but timer handler
also need sport->port.lock in position (2) of thread 2. As a result,
sa1100_set_termios() will block forever.

This patch moves del_timer_sync() before spin_lock_irqsave()
in order to prevent the deadlock.

Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Link: https://lore.kernel.org/r/20220417111626.7802-1-duoming@zju.edu.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/tty/serial/sa1100.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/sa1100.c b/drivers/tty/serial/sa1100.c
index a399772be3fc..8a65fb1ce568 100644
--- a/drivers/tty/serial/sa1100.c
+++ b/drivers/tty/serial/sa1100.c
@@ -439,6 +439,8 @@ sa1100_set_termios(struct uart_port *port, struct ktermios *termios,
 	baud = uart_get_baud_rate(port, termios, old, 0, port->uartclk/16); 
 	quot = uart_get_divisor(port, baud);
 
+	del_timer_sync(&sport->timer);
+
 	spin_lock_irqsave(&sport->port.lock, flags);
 
 	sport->port.read_status_mask &= UTSR0_TO_SM(UTSR0_TFS);
@@ -469,8 +471,6 @@ sa1100_set_termios(struct uart_port *port, struct ktermios *termios,
 				UTSR1_TO_SM(UTSR1_ROR);
 	}
 
-	del_timer_sync(&sport->timer);
-
 	/*
 	 * Update the per-port timeout.
 	 */
-- 
2.35.1

[PATCH AUTOSEL 4.19 09/27] drivers: usb: host: Fix deadlock in oxu_bus_suspend()

[Sasha Levin]

From: Duoming Zhou <duoming@zju.edu.cn>

[ Upstream commit 4d378f2ae58138d4c55684e1d274e7dd94aa6524 ]

There is a deadlock in oxu_bus_suspend(), which is shown below:

   (Thread 1)              |      (Thread 2)
                           | timer_action()
oxu_bus_suspend()          |  mod_timer()
 spin_lock_irq() //(1)     |  (wait a time)
 ...                       | oxu_watchdog()
 del_timer_sync()          |  spin_lock_irq() //(2)
 (wait timer to stop)      |  ...

We hold oxu->lock in position (1) of thread 1, and use
del_timer_sync() to wait timer to stop, but timer handler
also need oxu->lock in position (2) of thread 2. As a result,
oxu_bus_suspend() will block forever.

This patch extracts del_timer_sync() from the protection of
spin_lock_irq(), which could let timer handler to obtain
the needed lock.

Signed-off-by: Duoming Zhou <duoming@zju.edu.cn>
Link: https://lore.kernel.org/r/20220417120305.64577-1-duoming@zju.edu.cn
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/usb/host/oxu210hp-hcd.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c
index 10d97261b433..48533eb707e6 100644
--- a/drivers/usb/host/oxu210hp-hcd.c
+++ b/drivers/usb/host/oxu210hp-hcd.c
@@ -3476,8 +3476,10 @@ static int oxu_bus_suspend(struct usb_hcd *hcd)
 		}
 	}
 
+	spin_unlock_irq(&oxu->lock);
 	/* turn off now-idle HC */
 	del_timer_sync(&oxu->watchdog);
+	spin_lock_irq(&oxu->lock);
 	ehci_halt(oxu);
 	hcd->state = HC_STATE_SUSPENDED;
 
-- 
2.35.1

[PATCH AUTOSEL 4.19 10/27] USB: hcd-pci: Fully suspend across freeze/thaw cycle

[Sasha Levin]

From: Evan Green <evgreen@chromium.org>

[ Upstream commit 63acaa8e9c65dc34dc249440216f8e977f5d2748 ]

The documentation for the freeze() method says that it "should quiesce
the device so that it doesn't generate IRQs or DMA". The unspoken
consequence of not doing this is that MSIs aimed at non-boot CPUs may
get fully lost if they're sent during the period where the target CPU is
offline.

The current callbacks for USB HCD do not fully quiesce interrupts,
specifically on XHCI. Change to use the full suspend/resume flow for
freeze/thaw to ensure interrupts are fully quiesced. This fixes issues
where USB devices fail to thaw during hibernation because XHCI misses
its interrupt and cannot recover.

Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Evan Green <evgreen@chromium.org>
Link: https://lore.kernel.org/r/20220421103751.v3.2.I8226c7fdae88329ef70957b96a39b346c69a914e@changeid
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/usb/core/hcd-pci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c
index 7537681355f6..fed331d786e2 100644
--- a/drivers/usb/core/hcd-pci.c
+++ b/drivers/usb/core/hcd-pci.c
@@ -605,10 +605,10 @@ const struct dev_pm_ops usb_hcd_pci_pm_ops = {
 	.suspend_noirq	= hcd_pci_suspend_noirq,
 	.resume_noirq	= hcd_pci_resume_noirq,
 	.resume		= hcd_pci_resume,
-	.freeze		= check_root_hub_suspended,
+	.freeze		= hcd_pci_suspend,
 	.freeze_noirq	= check_root_hub_suspended,
 	.thaw_noirq	= NULL,
-	.thaw		= NULL,
+	.thaw		= hcd_pci_resume,
 	.poweroff	= hcd_pci_suspend,
 	.poweroff_noirq	= hcd_pci_suspend_noirq,
 	.restore_noirq	= hcd_pci_resume_noirq,
-- 
2.35.1

[PATCH AUTOSEL 4.19 11/27] usb: dwc2: gadget: don't reset gadget's driver->bus

[Sasha Levin]

From: Marek Szyprowski <m.szyprowski@samsung.com>

[ Upstream commit 3120aac6d0ecd9accf56894aeac0e265f74d3d5a ]

UDC driver should not touch gadget's driver internals, especially it
should not reset driver->bus. This wasn't harmful so far, but since
commit fc274c1e9973 ("USB: gadget: Add a new bus for gadgets") gadget
subsystem got it's own bus and messing with ->bus triggers the
following NULL pointer dereference:

dwc2 12480000.hsotg: bound driver g_ether
8<--- cut here ---
Unable to handle kernel NULL pointer dereference at virtual address 00000000
[00000000] *pgd=00000000
Internal error: Oops: 5 [#1] SMP ARM
Modules linked in: ...
CPU: 0 PID: 620 Comm: modprobe Not tainted 5.18.0-rc5-next-20220504 #11862
Hardware name: Samsung Exynos (Flattened Device Tree)
PC is at module_add_driver+0x44/0xe8
LR is at sysfs_do_create_link_sd+0x84/0xe0
...
Process modprobe (pid: 620, stack limit = 0x(ptrval))
...
 module_add_driver from bus_add_driver+0xf4/0x1e4
 bus_add_driver from driver_register+0x78/0x10c
 driver_register from usb_gadget_register_driver_owner+0x40/0xb4
 usb_gadget_register_driver_owner from do_one_initcall+0x44/0x1e0
 do_one_initcall from do_init_module+0x44/0x1c8
 do_init_module from load_module+0x19b8/0x1b9c
 load_module from sys_finit_module+0xdc/0xfc
 sys_finit_module from ret_fast_syscall+0x0/0x54
Exception stack(0xf1771fa8 to 0xf1771ff0)
...
dwc2 12480000.hsotg: new device is high-speed
---[ end trace 0000000000000000 ]---

Fix this by removing driver->bus entry reset.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20220505104618.22729-1-m.szyprowski@samsung.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/usb/dwc2/gadget.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index 1e46005929e4..85d25f7e9c27 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -4326,7 +4326,6 @@ static int dwc2_hsotg_udc_start(struct usb_gadget *gadget,
 
 	WARN_ON(hsotg->driver);
 
-	driver->driver.bus = NULL;
 	hsotg->driver = driver;
 	hsotg->gadget.dev.of_node = hsotg->dev->of_node;
 	hsotg->gadget.speed = USB_SPEED_UNKNOWN;
-- 
2.35.1

[PATCH AUTOSEL 4.19 12/27] misc: rtsx: set NULL intfdata when probe fails

[Sasha Levin]

From: Shuah Khan <skhan@linuxfoundation.org>

[ Upstream commit f861d36e021e1ac4a0a2a1f6411d623809975d63 ]

rtsx_usb_probe() doesn't call usb_set_intfdata() to null out the
interface pointer when probe fails. This leaves a stale pointer.
Noticed the missing usb_set_intfdata() while debugging an unrelated
invalid DMA mapping problem.

Fix it with a call to usb_set_intfdata(..., NULL).

Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/20220429210913.46804-1-skhan@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/misc/cardreader/rtsx_usb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/misc/cardreader/rtsx_usb.c b/drivers/misc/cardreader/rtsx_usb.c
index b97903ff1a72..869c176d48cc 100644
--- a/drivers/misc/cardreader/rtsx_usb.c
+++ b/drivers/misc/cardreader/rtsx_usb.c
@@ -678,6 +678,7 @@ static int rtsx_usb_probe(struct usb_interface *intf,
 	return 0;
 
 out_init_fail:
+	usb_set_intfdata(ucr->pusb_intf, NULL);
 	usb_free_coherent(ucr->pusb_dev, IOBUF_SIZE, ucr->iobuf,
 			ucr->iobuf_dma);
 	return ret;
-- 
2.35.1

[PATCH AUTOSEL 4.19 13/27] extcon: Modify extcon device to be created after driver data is set

[Sasha Levin]

From: bumwoo lee <bw365.lee@samsung.com>

[ Upstream commit 5dcc2afe716d69f5112ce035cb14f007461ff189 ]

Currently, someone can invoke the sysfs such as state_show()
intermittently before dev_set_drvdata() is done.
And it can be a cause of kernel Oops because of edev is Null at that time.
So modified the driver registration to after setting drviver data.

- Oops's backtrace.

Backtrace:
[<c067865c>] (state_show) from [<c05222e8>] (dev_attr_show)
[<c05222c0>] (dev_attr_show) from [<c02c66e0>] (sysfs_kf_seq_show)
[<c02c6648>] (sysfs_kf_seq_show) from [<c02c496c>] (kernfs_seq_show)
[<c02c4938>] (kernfs_seq_show) from [<c025e2a0>] (seq_read)
[<c025e11c>] (seq_read) from [<c02c50a0>] (kernfs_fop_read)
[<c02c5064>] (kernfs_fop_read) from [<c0231cac>] (__vfs_read)
[<c0231c5c>] (__vfs_read) from [<c0231ee0>] (vfs_read)
[<c0231e34>] (vfs_read) from [<c0232464>] (ksys_read)
[<c02323f0>] (ksys_read) from [<c02324fc>] (sys_read)
[<c02324e4>] (sys_read) from [<c00091d0>] (__sys_trace_return)

Signed-off-by: bumwoo lee <bw365.lee@samsung.com>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/extcon/extcon.c | 29 +++++++++++++++++------------
 1 file changed, 17 insertions(+), 12 deletions(-)

diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index e70f21ae85ff..4c70136c7aa3 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -1245,19 +1245,14 @@ int extcon_dev_register(struct extcon_dev *edev)
 		edev->dev.type = &edev->extcon_dev_type;
 	}
 
-	ret = device_register(&edev->dev);
-	if (ret) {
-		put_device(&edev->dev);
-		goto err_dev;
-	}
-
 	spin_lock_init(&edev->lock);
-	edev->nh = devm_kcalloc(&edev->dev, edev->max_supported,
-				sizeof(*edev->nh), GFP_KERNEL);
-	if (!edev->nh) {
-		ret = -ENOMEM;
-		device_unregister(&edev->dev);
-		goto err_dev;
+	if (edev->max_supported) {
+		edev->nh = kcalloc(edev->max_supported, sizeof(*edev->nh),
+				GFP_KERNEL);
+		if (!edev->nh) {
+			ret = -ENOMEM;
+			goto err_alloc_nh;
+		}
 	}
 
 	for (index = 0; index < edev->max_supported; index++)
@@ -1268,6 +1263,12 @@ int extcon_dev_register(struct extcon_dev *edev)
 	dev_set_drvdata(&edev->dev, edev);
 	edev->state = 0;
 
+	ret = device_register(&edev->dev);
+	if (ret) {
+		put_device(&edev->dev);
+		goto err_dev;
+	}
+
 	mutex_lock(&extcon_dev_list_lock);
 	list_add(&edev->entry, &extcon_dev_list);
 	mutex_unlock(&extcon_dev_list_lock);
@@ -1275,6 +1276,9 @@ int extcon_dev_register(struct extcon_dev *edev)
 	return 0;
 
 err_dev:
+	if (edev->max_supported)
+		kfree(edev->nh);
+err_alloc_nh:
 	if (edev->max_supported)
 		kfree(edev->extcon_dev_type.groups);
 err_alloc_groups:
@@ -1335,6 +1339,7 @@ void extcon_dev_unregister(struct extcon_dev *edev)
 	if (edev->max_supported) {
 		kfree(edev->extcon_dev_type.groups);
 		kfree(edev->cables);
+		kfree(edev->nh);
 	}
 
 	put_device(&edev->dev);
-- 
2.35.1

[PATCH AUTOSEL 4.19 14/27] clocksource/drivers/sp804: Avoid error on multiple instances

[Sasha Levin]

From: Andre Przywara <andre.przywara@arm.com>

[ Upstream commit a98399cbc1e05f7b977419f03905501d566cf54e ]

When a machine sports more than one SP804 timer instance, we only bring
up the first one, since multiple timers of the same kind are not useful
to Linux. As this is intentional behaviour, we should not return an
error message, as we do today:
===============
[    0.000800] Failed to initialize '/bus@8000000/motherboard-bus@8000000/iofpga-bus@300000000/timer@120000': -22
===============

Replace the -EINVAL return with a debug message and return 0 instead.

Also we do not reach the init function anymore if the DT node is
disabled (as this is now handled by OF_DECLARE), so remove the explicit
check for that case.

This fixes a long standing bogus error when booting ARM's fastmodels.

Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20220506162522.3675399-1-andre.przywara@arm.com
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/clocksource/timer-sp804.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/clocksource/timer-sp804.c b/drivers/clocksource/timer-sp804.c
index e01222ea888f..738c50e916f7 100644
--- a/drivers/clocksource/timer-sp804.c
+++ b/drivers/clocksource/timer-sp804.c
@@ -228,6 +228,11 @@ static int __init sp804_of_init(struct device_node *np)
 	struct clk *clk1, *clk2;
 	const char *name = of_get_property(np, "compatible", NULL);
 
+	if (initialized) {
+		pr_debug("%pOF: skipping further SP804 timer device\n", np);
+		return 0;
+	}
+
 	base = of_iomap(np, 0);
 	if (!base)
 		return -ENXIO;
@@ -236,11 +241,6 @@ static int __init sp804_of_init(struct device_node *np)
 	writel(0, base + TIMER_CTRL);
 	writel(0, base + TIMER_2_BASE + TIMER_CTRL);
 
-	if (initialized || !of_device_is_available(np)) {
-		ret = -EINVAL;
-		goto err;
-	}
-
 	clk1 = of_clk_get(np, 0);
 	if (IS_ERR(clk1))
 		clk1 = NULL;
-- 
2.35.1

[PATCH AUTOSEL 4.19 15/27] staging: rtl8712: fix uninit-value in r871xu_drv_init()

[Sasha Levin]

From: Wang Cheng <wanngchenng@gmail.com>

[ Upstream commit 0458e5428e5e959d201a40ffe71d762a79ecedc4 ]

When 'tmpU1b' returns from r8712_read8(padapter, EE_9346CR) is 0,
'mac[6]' will not be initialized.

BUG: KMSAN: uninit-value in r871xu_drv_init+0x2d54/0x3070 drivers/staging/rtl8712/usb_intf.c:541
 r871xu_drv_init+0x2d54/0x3070 drivers/staging/rtl8712/usb_intf.c:541
 usb_probe_interface+0xf19/0x1600 drivers/usb/core/driver.c:396
 really_probe+0x653/0x14b0 drivers/base/dd.c:596
 __driver_probe_device+0x3e9/0x530 drivers/base/dd.c:752
 driver_probe_device drivers/base/dd.c:782 [inline]
 __device_attach_driver+0x79f/0x1120 drivers/base/dd.c:899
 bus_for_each_drv+0x2d6/0x3f0 drivers/base/bus.c:427
 __device_attach+0x593/0x8e0 drivers/base/dd.c:970
 device_initial_probe+0x4a/0x60 drivers/base/dd.c:1017
 bus_probe_device+0x17b/0x3e0 drivers/base/bus.c:487
 device_add+0x1fff/0x26e0 drivers/base/core.c:3405
 usb_set_configuration+0x37e9/0x3ed0 drivers/usb/core/message.c:2170
 usb_generic_driver_probe+0x13c/0x300 drivers/usb/core/generic.c:238
 usb_probe_device+0x309/0x570 drivers/usb/core/driver.c:293
 really_probe+0x653/0x14b0 drivers/base/dd.c:596
 __driver_probe_device+0x3e9/0x530 drivers/base/dd.c:752
 driver_probe_device drivers/base/dd.c:782 [inline]
 __device_attach_driver+0x79f/0x1120 drivers/base/dd.c:899
 bus_for_each_drv+0x2d6/0x3f0 drivers/base/bus.c:427
 __device_attach+0x593/0x8e0 drivers/base/dd.c:970
 device_initial_probe+0x4a/0x60 drivers/base/dd.c:1017
 bus_probe_device+0x17b/0x3e0 drivers/base/bus.c:487
 device_add+0x1fff/0x26e0 drivers/base/core.c:3405
 usb_new_device+0x1b8e/0x2950 drivers/usb/core/hub.c:2566
 hub_port_connect drivers/usb/core/hub.c:5358 [inline]
 hub_port_connect_change drivers/usb/core/hub.c:5502 [inline]
 port_event drivers/usb/core/hub.c:5660 [inline]
 hub_event+0x58e3/0x89e0 drivers/usb/core/hub.c:5742
 process_one_work+0xdb6/0x1820 kernel/workqueue.c:2307
 worker_thread+0x10b3/0x21e0 kernel/workqueue.c:2454
 kthread+0x3c7/0x500 kernel/kthread.c:377
 ret_from_fork+0x1f/0x30

Local variable mac created at:
 r871xu_drv_init+0x1771/0x3070 drivers/staging/rtl8712/usb_intf.c:394
 usb_probe_interface+0xf19/0x1600 drivers/usb/core/driver.c:396

KMSAN: uninit-value in r871xu_drv_init
https://syzkaller.appspot.com/bug?id=3cd92b1d85428b128503bfa7a250294c9ae00bd8

Reported-by: <syzbot+6f5ecd144854c0d8580b@syzkaller.appspotmail.com>
Tested-by: <syzbot+6f5ecd144854c0d8580b@syzkaller.appspotmail.com>
Reviewed-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Wang Cheng <wanngchenng@gmail.com>
Link: https://lore.kernel.org/r/14c3886173dfa4597f0704547c414cfdbcd11d16.1652618244.git.wanngchenng@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/staging/rtl8712/usb_intf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/rtl8712/usb_intf.c b/drivers/staging/rtl8712/usb_intf.c
index 5e2cdc25401b..2b1ff63913af 100644
--- a/drivers/staging/rtl8712/usb_intf.c
+++ b/drivers/staging/rtl8712/usb_intf.c
@@ -569,13 +569,13 @@ static int r871xu_drv_init(struct usb_interface *pusb_intf,
 		} else {
 			AutoloadFail = false;
 		}
-		if (((mac[0] == 0xff) && (mac[1] == 0xff) &&
+		if ((!AutoloadFail) ||
+		    ((mac[0] == 0xff) && (mac[1] == 0xff) &&
 		     (mac[2] == 0xff) && (mac[3] == 0xff) &&
 		     (mac[4] == 0xff) && (mac[5] == 0xff)) ||
 		    ((mac[0] == 0x00) && (mac[1] == 0x00) &&
 		     (mac[2] == 0x00) && (mac[3] == 0x00) &&
-		     (mac[4] == 0x00) && (mac[5] == 0x00)) ||
-		     (!AutoloadFail)) {
+		     (mac[4] == 0x00) && (mac[5] == 0x00))) {
 			mac[0] = 0x00;
 			mac[1] = 0xe0;
 			mac[2] = 0x4c;
-- 
2.35.1

[PATCH AUTOSEL 4.19 16/27] serial: msm_serial: disable interrupts in __msm_console_write()

[Sasha Levin]

From: John Ogness <john.ogness@linutronix.de>

[ Upstream commit aabdbb1b7a5819e18c403334a31fb0cc2c06ad41 ]

__msm_console_write() assumes that interrupts are disabled, but
with threaded console printers it is possible that the write()
callback of the console is called with interrupts enabled.

Explicitly disable interrupts using local_irq_save() to preserve
the assumed context.

Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: John Ogness <john.ogness@linutronix.de>
Link: https://lore.kernel.org/r/20220506213324.470461-1-john.ogness@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/tty/serial/msm_serial.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c
index a40827956bd1..d248c43db36a 100644
--- a/drivers/tty/serial/msm_serial.c
+++ b/drivers/tty/serial/msm_serial.c
@@ -1579,6 +1579,7 @@ static inline struct uart_port *msm_get_port_from_line(unsigned int line)
 static void __msm_console_write(struct uart_port *port, const char *s,
 				unsigned int count, bool is_uartdm)
 {
+	unsigned long flags;
 	int i;
 	int num_newlines = 0;
 	bool replaced = false;
@@ -1596,6 +1597,8 @@ static void __msm_console_write(struct uart_port *port, const char *s,
 			num_newlines++;
 	count += num_newlines;
 
+	local_irq_save(flags);
+
 	if (port->sysrq)
 		locked = 0;
 	else if (oops_in_progress)
@@ -1641,6 +1644,8 @@ static void __msm_console_write(struct uart_port *port, const char *s,
 
 	if (locked)
 		spin_unlock(&port->lock);
+
+	local_irq_restore(flags);
 }
 
 static void msm_console_write(struct console *co, const char *s,
-- 
2.35.1

[PATCH AUTOSEL 4.19 17/27] kernfs: Separate kernfs_pr_cont_buf and rename_lock.

[Sasha Levin]

From: Hao Luo <haoluo@google.com>

[ Upstream commit 1a702dc88e150487c9c173a249b3d236498b9183 ]

Previously the protection of kernfs_pr_cont_buf was piggy backed by
rename_lock, which means that pr_cont() needs to be protected under
rename_lock. This can cause potential circular lock dependencies.

If there is an OOM, we have the following call hierarchy:

 -> cpuset_print_current_mems_allowed()
   -> pr_cont_cgroup_name()
     -> pr_cont_kernfs_name()

pr_cont_kernfs_name() will grab rename_lock and call printk. So we have
the following lock dependencies:

 kernfs_rename_lock -> console_sem

Sometimes, printk does a wakeup before releasing console_sem, which has
the dependence chain:

 console_sem -> p->pi_lock -> rq->lock

Now, imagine one wants to read cgroup_name under rq->lock, for example,
printing cgroup_name in a tracepoint in the scheduler code. They will
be holding rq->lock and take rename_lock:

 rq->lock -> kernfs_rename_lock

Now they will deadlock.

A prevention to this circular lock dependency is to separate the
protection of pr_cont_buf from rename_lock. In principle, rename_lock
is to protect the integrity of cgroup name when copying to buf. Once
pr_cont_buf has got its content, rename_lock can be dropped. So it's
safe to drop rename_lock after kernfs_name_locked (and
kernfs_path_from_node_locked) and rely on a dedicated pr_cont_lock
to protect pr_cont_buf.

Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Hao Luo <haoluo@google.com>
Link: https://lore.kernel.org/r/20220516190951.3144144-1-haoluo@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/kernfs/dir.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index a4a538abcaf9..99627d3438e5 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -20,7 +20,15 @@
 
 DEFINE_MUTEX(kernfs_mutex);
 static DEFINE_SPINLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
-static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by rename_lock */
+/*
+ * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to
+ * call pr_cont() while holding rename_lock. Because sometimes pr_cont()
+ * will perform wakeups when releasing console_sem. Holding rename_lock
+ * will introduce deadlock if the scheduler reads the kernfs_name in the
+ * wakeup path.
+ */
+static DEFINE_SPINLOCK(kernfs_pr_cont_lock);
+static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by pr_cont_lock */
 static DEFINE_SPINLOCK(kernfs_idr_lock);	/* root->ino_idr */
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
@@ -229,12 +237,12 @@ void pr_cont_kernfs_name(struct kernfs_node *kn)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	spin_lock_irqsave(&kernfs_pr_cont_lock, flags);
 
-	kernfs_name_locked(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
+	kernfs_name(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
 	pr_cont("%s", kernfs_pr_cont_buf);
 
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags);
 }
 
 /**
@@ -248,10 +256,10 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	unsigned long flags;
 	int sz;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	spin_lock_irqsave(&kernfs_pr_cont_lock, flags);
 
-	sz = kernfs_path_from_node_locked(kn, NULL, kernfs_pr_cont_buf,
-					  sizeof(kernfs_pr_cont_buf));
+	sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf,
+				   sizeof(kernfs_pr_cont_buf));
 	if (sz < 0) {
 		pr_cont("(error)");
 		goto out;
@@ -265,7 +273,7 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	pr_cont("%s", kernfs_pr_cont_buf);
 
 out:
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags);
 }
 
 /**
@@ -867,13 +875,12 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 
 	lockdep_assert_held(&kernfs_mutex);
 
-	/* grab kernfs_rename_lock to piggy back on kernfs_pr_cont_buf */
-	spin_lock_irq(&kernfs_rename_lock);
+	spin_lock_irq(&kernfs_pr_cont_lock);
 
 	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
 
 	if (len >= sizeof(kernfs_pr_cont_buf)) {
-		spin_unlock_irq(&kernfs_rename_lock);
+		spin_unlock_irq(&kernfs_pr_cont_lock);
 		return NULL;
 	}
 
@@ -885,7 +892,7 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 		parent = kernfs_find_ns(parent, name, ns);
 	}
 
-	spin_unlock_irq(&kernfs_rename_lock);
+	spin_unlock_irq(&kernfs_pr_cont_lock);
 
 	return parent;
 }
-- 
2.35.1

[PATCH AUTOSEL 4.19 18/27] md: don't unregister sync_thread with reconfig_mutex held

[Sasha Levin]

From: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>

[ Upstream commit 8b48ec23cc51a4e7c8dbaef5f34ebe67e1a80934 ]

Unregister sync_thread doesn't need to hold reconfig_mutex since it
doesn't reconfigure array.

And it could cause deadlock problem for raid5 as follows:

1. process A tried to reap sync thread with reconfig_mutex held after echo
   idle to sync_action.
2. raid5 sync thread was blocked if there were too many active stripes.
3. SB_CHANGE_PENDING was set (because of write IO comes from upper layer)
   which causes the number of active stripes can't be decreased.
4. SB_CHANGE_PENDING can't be cleared since md_check_recovery was not able
   to hold reconfig_mutex.

More details in the link:
https://lore.kernel.org/linux-raid/5ed54ffc-ce82-bf66-4eff-390cb23bc1ac@molgen.mpg.de/T/#t

And add one parameter to md_reap_sync_thread since it could be called by
dm-raid which doesn't hold reconfig_mutex.

Reported-and-tested-by: Donald Buczek <buczek@molgen.mpg.de>
Signed-off-by: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>
Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/md/dm-raid.c |  2 +-
 drivers/md/md.c      | 14 +++++++++-----
 drivers/md/md.h      |  2 +-
 3 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index b16332917220..0be03123d6a2 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3710,7 +3710,7 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 	if (!strcasecmp(argv[0], "idle") || !strcasecmp(argv[0], "frozen")) {
 		if (mddev->sync_thread) {
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_reap_sync_thread(mddev);
+			md_reap_sync_thread(mddev, false);
 		}
 	} else if (decipher_sync_action(mddev, mddev->recovery) != st_idle)
 		return -EBUSY;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 7e0477e883c7..da7954eff4d7 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4611,7 +4611,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 			flush_workqueue(md_misc_wq);
 			if (mddev->sync_thread) {
 				set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-				md_reap_sync_thread(mddev);
+				md_reap_sync_thread(mddev, true);
 			}
 			mddev_unlock(mddev);
 		}
@@ -5871,7 +5871,7 @@ static void __md_stop_writes(struct mddev *mddev)
 	flush_workqueue(md_misc_wq);
 	if (mddev->sync_thread) {
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-		md_reap_sync_thread(mddev);
+		md_reap_sync_thread(mddev, true);
 	}
 
 	del_timer_sync(&mddev->safemode_timer);
@@ -8893,7 +8893,7 @@ void md_check_recovery(struct mddev *mddev)
 			 * ->spare_active and clear saved_raid_disk
 			 */
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			md_reap_sync_thread(mddev);
+			md_reap_sync_thread(mddev, true);
 			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			clear_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags);
@@ -8928,7 +8928,7 @@ void md_check_recovery(struct mddev *mddev)
 			goto unlock;
 		}
 		if (mddev->sync_thread) {
-			md_reap_sync_thread(mddev);
+			md_reap_sync_thread(mddev, true);
 			goto unlock;
 		}
 		/* Set RUNNING before clearing NEEDED to avoid
@@ -9001,12 +9001,16 @@ void md_check_recovery(struct mddev *mddev)
 }
 EXPORT_SYMBOL(md_check_recovery);
 
-void md_reap_sync_thread(struct mddev *mddev)
+void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held)
 {
 	struct md_rdev *rdev;
 
+	if (reconfig_mutex_held)
+		mddev_unlock(mddev);
 	/* resync has finished, collect result */
 	md_unregister_thread(&mddev->sync_thread);
+	if (reconfig_mutex_held)
+		mddev_lock_nointr(mddev);
 	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
 	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
 	    mddev->degraded != mddev->raid_disks) {
diff --git a/drivers/md/md.h b/drivers/md/md.h
index cce62bbc2bcb..027b220dec14 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -674,7 +674,7 @@ extern struct md_thread *md_register_thread(
 extern void md_unregister_thread(struct md_thread **threadp);
 extern void md_wakeup_thread(struct md_thread *thread);
 extern void md_check_recovery(struct mddev *mddev);
-extern void md_reap_sync_thread(struct mddev *mddev);
+extern void md_reap_sync_thread(struct mddev *mddev, bool reconfig_mutex_held);
 extern int mddev_init_writes_pending(struct mddev *mddev);
 extern bool md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);
-- 
2.35.1

[PATCH AUTOSEL 4.19 19/27] md: protect md_unregister_thread from reentrancy

[Sasha Levin]

From: Guoqing Jiang <guoqing.jiang@cloud.ionos.com>

[ Upstream commit 1e267742283a4b5a8ca65755c44166be27e9aa0f ]

Generally, the md_unregister_thread is called with reconfig_mutex, but
raid_message in dm-raid doesn't hold reconfig_mutex to unregister thread,
so md_unregister_thread can be called simulitaneously from two call sites
in theory.

Then after previous commit which remove the protection of reconfig_mutex
for md_unregister_thread completely, the potential issue could be worse
than before.

Let's take pers_lock at the beginning of function to ensure reentrancy.

Reported-by: Donald Buczek <buczek@molgen.mpg.de>
Signed-off-by: Guoqing Jiang <guoqing.jiang@linux.dev>
Signed-off-by: Song Liu <song@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/md/md.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index da7954eff4d7..5439b6a71776 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -7618,17 +7618,22 @@ EXPORT_SYMBOL(md_register_thread);
 
 void md_unregister_thread(struct md_thread **threadp)
 {
-	struct md_thread *thread = *threadp;
-	if (!thread)
-		return;
-	pr_debug("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk));
-	/* Locking ensures that mddev_unlock does not wake_up a
+	struct md_thread *thread;
+
+	/*
+	 * Locking ensures that mddev_unlock does not wake_up a
 	 * non-existent thread
 	 */
 	spin_lock(&pers_lock);
+	thread = *threadp;
+	if (!thread) {
+		spin_unlock(&pers_lock);
+		return;
+	}
 	*threadp = NULL;
 	spin_unlock(&pers_lock);
 
+	pr_debug("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk));
 	kthread_stop(thread->tsk);
 	kfree(thread);
 }
-- 
2.35.1

[PATCH AUTOSEL 4.19 20/27] Revert "net: af_key: add check for pfkey_broadcast in function pfkey_process"

[Sasha Levin]

From: Michal Kubecek <mkubecek@suse.cz>

[ Upstream commit 9c90c9b3e50e16d03c7f87d63e9db373974781e0 ]

This reverts commit 4dc2a5a8f6754492180741facf2a8787f2c415d7.

A non-zero return value from pfkey_broadcast() does not necessarily mean
an error occurred as this function returns -ESRCH when no registered
listener received the message. In particular, a call with
BROADCAST_PROMISC_ONLY flag and null one_sk argument can never return
zero so that this commit in fact prevents processing any PF_KEY message.
One visible effect is that racoon daemon fails to find encryption
algorithms like aes and refuses to start.

Excluding -ESRCH return value would fix this but it's not obvious that
we really want to bail out here and most other callers of
pfkey_broadcast() also ignore the return value. Also, as pointed out by
Steffen Klassert, PF_KEY is kind of deprecated and newer userspace code
should use netlink instead so that we should only disturb the code for
really important fixes.

v2: add a comment explaining why is the return value ignored

Signed-off-by: Michal Kubecek <mkubecek@suse.cz>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/key/af_key.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/key/af_key.c b/net/key/af_key.c
index 1bbb6ec89ff3..af67e0d265c0 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2836,10 +2836,12 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb
 	void *ext_hdrs[SADB_EXT_MAX];
 	int err;
 
-	err = pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL,
-			      BROADCAST_PROMISC_ONLY, NULL, sock_net(sk));
-	if (err)
-		return err;
+	/* Non-zero return value of pfkey_broadcast() does not always signal
+	 * an error and even on an actual error we may still want to process
+	 * the message so rather ignore the return value.
+	 */
+	pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL,
+			BROADCAST_PROMISC_ONLY, NULL, sock_net(sk));
 
 	memset(ext_hdrs, 0, sizeof(ext_hdrs));
 	err = parse_exthdrs(skb, hdr, ext_hdrs);
-- 
2.35.1

[PATCH AUTOSEL 4.19 21/27] ceph: allow ceph.dir.rctime xattr to be updatable

[Sasha Levin]

From: Venky Shankar <vshankar@redhat.com>

[ Upstream commit d7a2dc523085f8b8c60548ceedc696934aefeb0e ]

`rctime' has been a pain point in cephfs due to its buggy
nature - inconsistent values reported and those sorts.
Fixing rctime is non-trivial needing an overall redesign
of the entire nested statistics infrastructure.

As a workaround, PR

     http://github.com/ceph/ceph/pull/37938

allows this extended attribute to be manually set. This allows
users to "fixup" inconsistent rctime values. While this sounds
messy, its probably the wisest approach allowing users/scripts
to workaround buggy rctime values.

The above PR enables Ceph MDS to allow manually setting
rctime extended attribute with the corresponding user-land
changes. We may as well allow the same to be done via kclient
for parity.

Signed-off-by: Venky Shankar <vshankar@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/ceph/xattr.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index a09ce27ab220..6fa9a784676b 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -273,6 +273,14 @@ static size_t ceph_vxattrcb_quota_max_files(struct ceph_inode_info *ci,
 	}
 #define XATTR_RSTAT_FIELD(_type, _name)			\
 	XATTR_NAME_CEPH(_type, _name, VXATTR_FLAG_RSTAT)
+#define XATTR_RSTAT_FIELD_UPDATABLE(_type, _name)			\
+	{								\
+		.name = CEPH_XATTR_NAME(_type, _name),			\
+		.name_size = sizeof (CEPH_XATTR_NAME(_type, _name)),	\
+		.getxattr_cb = ceph_vxattrcb_ ## _type ## _ ## _name,	\
+		.exists_cb = NULL,					\
+		.flags = VXATTR_FLAG_RSTAT,				\
+	}
 #define XATTR_LAYOUT_FIELD(_type, _name, _field)			\
 	{								\
 		.name = CEPH_XATTR_NAME2(_type, _name, _field),	\
@@ -310,7 +318,7 @@ static struct ceph_vxattr ceph_dir_vxattrs[] = {
 	XATTR_RSTAT_FIELD(dir, rfiles),
 	XATTR_RSTAT_FIELD(dir, rsubdirs),
 	XATTR_RSTAT_FIELD(dir, rbytes),
-	XATTR_RSTAT_FIELD(dir, rctime),
+	XATTR_RSTAT_FIELD_UPDATABLE(dir, rctime),
 	{
 		.name = "ceph.quota",
 		.name_size = sizeof("ceph.quota"),
-- 
2.35.1

[PATCH AUTOSEL 4.19 22/27] drm/radeon: fix a possible null pointer dereference

[Sasha Levin]

From: Gong Yuanjun <ruc_gongyuanjun@163.com>

[ Upstream commit a2b28708b645c5632dc93669ab06e97874c8244f ]

In radeon_fp_native_mode(), the return value of drm_mode_duplicate()
is assigned to mode, which will lead to a NULL pointer dereference
on failure of drm_mode_duplicate(). Add a check to avoid npd.

The failure status of drm_cvt_mode() on the other path is checked too.

Signed-off-by: Gong Yuanjun <ruc_gongyuanjun@163.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/radeon/radeon_connectors.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index b9927101e845..47240983f360 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -476,6 +476,8 @@ static struct drm_display_mode *radeon_fp_native_mode(struct drm_encoder *encode
 	    native_mode->vdisplay != 0 &&
 	    native_mode->clock != 0) {
 		mode = drm_mode_duplicate(dev, native_mode);
+		if (!mode)
+			return NULL;
 		mode->type = DRM_MODE_TYPE_PREFERRED | DRM_MODE_TYPE_DRIVER;
 		drm_mode_set_name(mode);
 
@@ -490,6 +492,8 @@ static struct drm_display_mode *radeon_fp_native_mode(struct drm_encoder *encode
 		 * simpler.
 		 */
 		mode = drm_cvt_mode(dev, native_mode->hdisplay, native_mode->vdisplay, 60, true, false, false);
+		if (!mode)
+			return NULL;
 		mode->type = DRM_MODE_TYPE_PREFERRED | DRM_MODE_TYPE_DRIVER;
 		DRM_DEBUG_KMS("Adding cvt approximation of native panel mode %s\n", mode->name);
 	}
-- 
2.35.1

[PATCH AUTOSEL 4.19 23/27] modpost: fix undefined behavior of is_arm_mapping_symbol()

[Sasha Levin]

From: Masahiro Yamada <masahiroy@kernel.org>

[ Upstream commit d6b732666a1bae0df3c3ae06925043bba34502b1 ]

The return value of is_arm_mapping_symbol() is unpredictable when "$"
is passed in.

strchr(3) says:
  The strchr() and strrchr() functions return a pointer to the matched
  character or NULL if the character is not found. The terminating null
  byte is considered part of the string, so that if c is specified as
  '\0', these functions return a pointer to the terminator.

When str[1] is '\0', strchr("axtd", str[1]) is not NULL, and str[2] is
referenced (i.e. buffer overrun).

Test code
---------

  char str1[] = "abc";
  char str2[] = "ab";

  strcpy(str1, "$");
  strcpy(str2, "$");

  printf("test1: %d\n", is_arm_mapping_symbol(str1));
  printf("test2: %d\n", is_arm_mapping_symbol(str2));

Result
------

  test1: 0
  test2: 1

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 scripts/mod/modpost.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 7c693bd775c1..1c2f59245849 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1218,7 +1218,8 @@ static int secref_whitelist(const struct sectioncheck *mismatch,
 
 static inline int is_arm_mapping_symbol(const char *str)
 {
-	return str[0] == '$' && strchr("axtd", str[1])
+	return str[0] == '$' &&
+	       (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x')
 	       && (str[2] == '\0' || str[2] == '.');
 }
 
-- 
2.35.1

[PATCH AUTOSEL 4.19 24/27] nbd: call genl_unregister_family() first in nbd_cleanup()

[Sasha Levin]

From: Yu Kuai <yukuai3@huawei.com>

[ Upstream commit 06c4da89c24e7023ea448cadf8e9daf06a0aae6e ]

Otherwise there may be race between module removal and the handling of
netlink command, which can lead to the oops as shown below:

  BUG: kernel NULL pointer dereference, address: 0000000000000098
  Oops: 0002 [#1] SMP PTI
  CPU: 1 PID: 31299 Comm: nbd-client Tainted: G            E     5.14.0-rc4
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
  RIP: 0010:down_write+0x1a/0x50
  Call Trace:
   start_creating+0x89/0x130
   debugfs_create_dir+0x1b/0x130
   nbd_start_device+0x13d/0x390 [nbd]
   nbd_genl_connect+0x42f/0x748 [nbd]
   genl_family_rcv_msg_doit.isra.0+0xec/0x150
   genl_rcv_msg+0xe5/0x1e0
   netlink_rcv_skb+0x55/0x100
   genl_rcv+0x29/0x40
   netlink_unicast+0x1a8/0x250
   netlink_sendmsg+0x21b/0x430
   ____sys_sendmsg+0x2a4/0x2d0
   ___sys_sendmsg+0x81/0xc0
   __sys_sendmsg+0x62/0xb0
   __x64_sys_sendmsg+0x1f/0x30
   do_syscall_64+0x3b/0xc0
   entry_SYSCALL_64_after_hwframe+0x44/0xae
  Modules linked in: nbd(E-)

Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Link: https://lore.kernel.org/r/20220521073749.3146892-2-yukuai3@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/block/nbd.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 81b955670b12..29bed6397173 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -2337,6 +2337,12 @@ static void __exit nbd_cleanup(void)
 	struct nbd_device *nbd;
 	LIST_HEAD(del_list);
 
+	/*
+	 * Unregister netlink interface prior to waiting
+	 * for the completion of netlink commands.
+	 */
+	genl_unregister_family(&nbd_genl_family);
+
 	nbd_dbg_close();
 
 	mutex_lock(&nbd_index_mutex);
@@ -2352,7 +2358,6 @@ static void __exit nbd_cleanup(void)
 	}
 
 	idr_destroy(&nbd_index_idr);
-	genl_unregister_family(&nbd_genl_family);
 	unregister_blkdev(NBD_MAJOR, "nbd");
 }
 
-- 
2.35.1

[PATCH AUTOSEL 4.19 25/27] nbd: fix race between nbd_alloc_config() and module removal

[Sasha Levin]

From: Yu Kuai <yukuai3@huawei.com>

[ Upstream commit c55b2b983b0fa012942c3eb16384b2b722caa810 ]

When nbd module is being removing, nbd_alloc_config() may be
called concurrently by nbd_genl_connect(), although try_module_get()
will return false, but nbd_alloc_config() doesn't handle it.

The race may lead to the leak of nbd_config and its related
resources (e.g, recv_workq) and oops in nbd_read_stat() due
to the unload of nbd module as shown below:

  BUG: kernel NULL pointer dereference, address: 0000000000000040
  Oops: 0000 [#1] SMP PTI
  CPU: 5 PID: 13840 Comm: kworker/u17:33 Not tainted 5.14.0+ #1
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
  Workqueue: knbd16-recv recv_work [nbd]
  RIP: 0010:nbd_read_stat.cold+0x130/0x1a4 [nbd]
  Call Trace:
   recv_work+0x3b/0xb0 [nbd]
   process_one_work+0x1ed/0x390
   worker_thread+0x4a/0x3d0
   kthread+0x12a/0x150
   ret_from_fork+0x22/0x30

Fixing it by checking the return value of try_module_get()
in nbd_alloc_config(). As nbd_alloc_config() may return ERR_PTR(-ENODEV),
assign nbd->config only when nbd_alloc_config() succeeds to ensure
the value of nbd->config is binary (valid or NULL).

Also adding a debug message to check the reference counter
of nbd_config during module removal.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Link: https://lore.kernel.org/r/20220521073749.3146892-3-yukuai3@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/block/nbd.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 29bed6397173..f48553979b85 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1395,15 +1395,20 @@ static struct nbd_config *nbd_alloc_config(void)
 {
 	struct nbd_config *config;
 
+	if (!try_module_get(THIS_MODULE))
+		return ERR_PTR(-ENODEV);
+
 	config = kzalloc(sizeof(struct nbd_config), GFP_NOFS);
-	if (!config)
-		return NULL;
+	if (!config) {
+		module_put(THIS_MODULE);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	atomic_set(&config->recv_threads, 0);
 	init_waitqueue_head(&config->recv_wq);
 	init_waitqueue_head(&config->conn_wait);
 	config->blksize = NBD_DEF_BLKSIZE;
 	atomic_set(&config->live_connections, 0);
-	try_module_get(THIS_MODULE);
 	return config;
 }
 
@@ -1430,12 +1435,13 @@ static int nbd_open(struct block_device *bdev, fmode_t mode)
 			mutex_unlock(&nbd->config_lock);
 			goto out;
 		}
-		config = nbd->config = nbd_alloc_config();
-		if (!config) {
-			ret = -ENOMEM;
+		config = nbd_alloc_config();
+		if (IS_ERR(config)) {
+			ret = PTR_ERR(config);
 			mutex_unlock(&nbd->config_lock);
 			goto out;
 		}
+		nbd->config = config;
 		refcount_set(&nbd->config_refs, 1);
 		refcount_inc(&nbd->refs);
 		mutex_unlock(&nbd->config_lock);
@@ -1820,13 +1826,14 @@ static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
 		nbd_put(nbd);
 		return -EINVAL;
 	}
-	config = nbd->config = nbd_alloc_config();
-	if (!nbd->config) {
+	config = nbd_alloc_config();
+	if (IS_ERR(config)) {
 		mutex_unlock(&nbd->config_lock);
 		nbd_put(nbd);
 		printk(KERN_ERR "nbd: couldn't allocate config\n");
-		return -ENOMEM;
+		return PTR_ERR(config);
 	}
+	nbd->config = config;
 	refcount_set(&nbd->config_refs, 1);
 	set_bit(NBD_BOUND, &config->runtime_flags);
 
@@ -2352,6 +2359,9 @@ static void __exit nbd_cleanup(void)
 	while (!list_empty(&del_list)) {
 		nbd = list_first_entry(&del_list, struct nbd_device, list);
 		list_del_init(&nbd->list);
+		if (refcount_read(&nbd->config_refs))
+			printk(KERN_ERR "nbd: possibly leaking nbd_config (ref %d)\n",
+					refcount_read(&nbd->config_refs));
 		if (refcount_read(&nbd->refs) != 1)
 			printk(KERN_ERR "nbd: possibly leaking a device\n");
 		nbd_put(nbd);
-- 
2.35.1

[PATCH AUTOSEL 4.19 26/27] nbd: fix io hung while disconnecting device

[Sasha Levin]

From: Yu Kuai <yukuai3@huawei.com>

[ Upstream commit 09dadb5985023e27d4740ebd17e6fea4640110e5 ]

In our tests, "qemu-nbd" triggers a io hung:

INFO: task qemu-nbd:11445 blocked for more than 368 seconds.
      Not tainted 5.18.0-rc3-next-20220422-00003-g2176915513ca #884
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:qemu-nbd        state:D stack:    0 pid:11445 ppid:     1 flags:0x00000000
Call Trace:
 <TASK>
 __schedule+0x480/0x1050
 ? _raw_spin_lock_irqsave+0x3e/0xb0
 schedule+0x9c/0x1b0
 blk_mq_freeze_queue_wait+0x9d/0xf0
 ? ipi_rseq+0x70/0x70
 blk_mq_freeze_queue+0x2b/0x40
 nbd_add_socket+0x6b/0x270 [nbd]
 nbd_ioctl+0x383/0x510 [nbd]
 blkdev_ioctl+0x18e/0x3e0
 __x64_sys_ioctl+0xac/0x120
 do_syscall_64+0x35/0x80
 entry_SYSCALL_64_after_hwframe+0x44/0xae
RIP: 0033:0x7fd8ff706577
RSP: 002b:00007fd8fcdfebf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 0000000040000000 RCX: 00007fd8ff706577
RDX: 000000000000000d RSI: 000000000000ab00 RDI: 000000000000000f
RBP: 000000000000000f R08: 000000000000fbe8 R09: 000055fe497c62b0
R10: 00000002aff20000 R11: 0000000000000246 R12: 000000000000006d
R13: 0000000000000000 R14: 00007ffe82dc5e70 R15: 00007fd8fcdff9c0

"qemu-ndb -d" will call ioctl 'NBD_DISCONNECT' first, however, following
message was found:

block nbd0: Send disconnect failed -32

Which indicate that something is wrong with the server. Then,
"qemu-nbd -d" will call ioctl 'NBD_CLEAR_SOCK', however ioctl can't clear
requests after commit 2516ab1543fd("nbd: only clear the queue on device
teardown"). And in the meantime, request can't complete through timeout
because nbd_xmit_timeout() will always return 'BLK_EH_RESET_TIMER', which
means such request will never be completed in this situation.

Now that the flag 'NBD_CMD_INFLIGHT' can make sure requests won't
complete multiple times, switch back to call nbd_clear_sock() in
nbd_clear_sock_ioctl(), so that inflight requests can be cleared.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Link: https://lore.kernel.org/r/20220521073749.3146892-5-yukuai3@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/block/nbd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index f48553979b85..2ef7eec6461c 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1288,7 +1288,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b
 static void nbd_clear_sock_ioctl(struct nbd_device *nbd,
 				 struct block_device *bdev)
 {
-	sock_shutdown(nbd);
+	nbd_clear_sock(nbd);
 	__invalidate_device(bdev, true);
 	nbd_bdev_reset(bdev);
 	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
-- 
2.35.1

[PATCH AUTOSEL 4.19 27/27] nodemask: Fix return values to be unsigned

[Sasha Levin]

From: Kees Cook <keescook@chromium.org>

[ Upstream commit 0dfe54071d7c828a02917b595456bfde1afdddc9 ]

The nodemask routines had mixed return values that provided potentially
signed return values that could never happen. This was leading to the
compiler getting confusing about the range of possible return values
(it was thinking things could be negative where they could not be). Fix
all the nodemask routines that should be returning unsigned
(or bool) values. Silences:

 mm/swapfile.c: In function ‘setup_swap_info’:
 mm/swapfile.c:2291:47: error: array subscript -1 is below array bounds of ‘struct plist_node[]’ [-Werror=array-bounds]
  2291 |                                 p->avail_lists[i].prio = 1;
       |                                 ~~~~~~~~~~~~~~^~~
 In file included from mm/swapfile.c:16:
 ./include/linux/swap.h:292:27: note: while referencing ‘avail_lists’
   292 |         struct plist_node avail_lists[]; /*
       |                           ^~~~~~~~~~~

Reported-by: Christophe de Dinechin <dinechin@redhat.com>
Link: https://lore.kernel.org/lkml/20220414150855.2407137-3-dinechin@redhat.com/
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Yury Norov <yury.norov@gmail.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/linux/nodemask.h | 38 +++++++++++++++++++-------------------
 lib/nodemask.c           |  4 ++--
 2 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 5a30ad594ccc..52e78c66c396 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -42,11 +42,11 @@
  * void nodes_shift_right(dst, src, n)	Shift right
  * void nodes_shift_left(dst, src, n)	Shift left
  *
- * int first_node(mask)			Number lowest set bit, or MAX_NUMNODES
- * int next_node(node, mask)		Next node past 'node', or MAX_NUMNODES
- * int next_node_in(node, mask)		Next node past 'node', or wrap to first,
+ * unsigned int first_node(mask)	Number lowest set bit, or MAX_NUMNODES
+ * unsigend int next_node(node, mask)	Next node past 'node', or MAX_NUMNODES
+ * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first,
  *					or MAX_NUMNODES
- * int first_unset_node(mask)		First node not set in mask, or 
+ * unsigned int first_unset_node(mask)	First node not set in mask, or
  *					MAX_NUMNODES
  *
  * nodemask_t nodemask_of_node(node)	Return nodemask with bit 'node' set
@@ -153,7 +153,7 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
 
 #define node_test_and_set(node, nodemask) \
 			__node_test_and_set((node), &(nodemask))
-static inline int __node_test_and_set(int node, nodemask_t *addr)
+static inline bool __node_test_and_set(int node, nodemask_t *addr)
 {
 	return test_and_set_bit(node, addr->bits);
 }
@@ -200,7 +200,7 @@ static inline void __nodes_complement(nodemask_t *dstp,
 
 #define nodes_equal(src1, src2) \
 			__nodes_equal(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_equal(const nodemask_t *src1p,
+static inline bool __nodes_equal(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_equal(src1p->bits, src2p->bits, nbits);
@@ -208,7 +208,7 @@ static inline int __nodes_equal(const nodemask_t *src1p,
 
 #define nodes_intersects(src1, src2) \
 			__nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_intersects(const nodemask_t *src1p,
+static inline bool __nodes_intersects(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_intersects(src1p->bits, src2p->bits, nbits);
@@ -216,20 +216,20 @@ static inline int __nodes_intersects(const nodemask_t *src1p,
 
 #define nodes_subset(src1, src2) \
 			__nodes_subset(&(src1), &(src2), MAX_NUMNODES)
-static inline int __nodes_subset(const nodemask_t *src1p,
+static inline bool __nodes_subset(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_subset(src1p->bits, src2p->bits, nbits);
 }
 
 #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
-static inline int __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
+static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_empty(srcp->bits, nbits);
 }
 
 #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_full(const nodemask_t *srcp, unsigned int nbits)
+static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_full(srcp->bits, nbits);
 }
@@ -260,15 +260,15 @@ static inline void __nodes_shift_left(nodemask_t *dstp,
           > MAX_NUMNODES, then the silly min_ts could be dropped. */
 
 #define first_node(src) __first_node(&(src))
-static inline int __first_node(const nodemask_t *srcp)
+static inline unsigned int __first_node(const nodemask_t *srcp)
 {
-	return min_t(int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
+	return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
 }
 
 #define next_node(n, src) __next_node((n), &(src))
-static inline int __next_node(int n, const nodemask_t *srcp)
+static inline unsigned int __next_node(int n, const nodemask_t *srcp)
 {
-	return min_t(int,MAX_NUMNODES,find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
+	return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
 }
 
 /*
@@ -276,7 +276,7 @@ static inline int __next_node(int n, const nodemask_t *srcp)
  * the first node in src if needed.  Returns MAX_NUMNODES if src is empty.
  */
 #define next_node_in(n, src) __next_node_in((n), &(src))
-int __next_node_in(int node, const nodemask_t *srcp);
+unsigned int __next_node_in(int node, const nodemask_t *srcp);
 
 static inline void init_nodemask_of_node(nodemask_t *mask, int node)
 {
@@ -296,9 +296,9 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node)
 })
 
 #define first_unset_node(mask) __first_unset_node(&(mask))
-static inline int __first_unset_node(const nodemask_t *maskp)
+static inline unsigned int __first_unset_node(const nodemask_t *maskp)
 {
-	return min_t(int,MAX_NUMNODES,
+	return min_t(unsigned int, MAX_NUMNODES,
 			find_first_zero_bit(maskp->bits, MAX_NUMNODES));
 }
 
@@ -435,11 +435,11 @@ static inline int num_node_state(enum node_states state)
 
 #define first_online_node	first_node(node_states[N_ONLINE])
 #define first_memory_node	first_node(node_states[N_MEMORY])
-static inline int next_online_node(int nid)
+static inline unsigned int next_online_node(int nid)
 {
 	return next_node(nid, node_states[N_ONLINE]);
 }
-static inline int next_memory_node(int nid)
+static inline unsigned int next_memory_node(int nid)
 {
 	return next_node(nid, node_states[N_MEMORY]);
 }
diff --git a/lib/nodemask.c b/lib/nodemask.c
index 3aa454c54c0d..e22647f5181b 100644
--- a/lib/nodemask.c
+++ b/lib/nodemask.c
@@ -3,9 +3,9 @@
 #include <linux/module.h>
 #include <linux/random.h>
 
-int __next_node_in(int node, const nodemask_t *srcp)
+unsigned int __next_node_in(int node, const nodemask_t *srcp)
 {
-	int ret = __next_node(node, srcp);
+	unsigned int ret = __next_node(node, srcp);
 
 	if (ret == MAX_NUMNODES)
 		ret = __first_node(srcp);
-- 
2.35.1