4.4.122-stable review

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

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

From: Leon Romanovsky <[email protected]>

commit 6a21dfc0d0db7b7e0acedce67ca533a6eb19283c upstream.

Users of ucma are supposed to provide size of option level, in most paths it is supposed to be equal to u8 or u16, but it is not the case for the IB path record, where it can be multiple of struct ib_path_rec_data.

This patch takes simplest possible approach and prevents providing values more than possible to allocate.

---
 drivers/infiniband/core/ucma.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -1274,6 +1274,9 @@ static ssize_t ucma_set_option(struct uc
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
+	if (unlikely(cmd.optval > KMALLOC_MAX_SIZE))
+		return -EINVAL;
+
 	optval = memdup_user((void __user *) (unsigned long) cmd.optval,
 			     cmd.optlen);
 	if (IS_ERR(optval)) {

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

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

From: Lukas Wunner <[email protected]>

commit 27d4ee03078aba88c5e07dcc4917e8d01d046f38 upstream.

Introduce a helper to retrieve the current task's work struct if it is a workqueue worker.

This allows us to fix a long-standing deadlock in several DRM drivers wherein the ->runtime_suspend callback waits for a specific worker to finish and that worker in turn calls a function which waits for runtime suspend to finish. That function is invoked from multiple call sites and waiting for runtime suspend to finish is the correct thing to do except if it's executing in the context of the worker.

---
 include/linux/workqueue.h |    1 +
 kernel/workqueue.c        |   16 ++++++++++++++++
 2 files changed, 17 insertions(+)

@@ -451,6 +451,7 @@ extern bool cancel_delayed_work_sync(str
 
 extern void workqueue_set_max_active(struct workqueue_struct *wq,
 				     int max_active);
+extern struct work_struct *current_work(void);
 extern bool current_is_workqueue_rescuer(void);
 extern bool workqueue_congested(int cpu, struct workqueue_struct *wq);
 extern unsigned int work_busy(struct work_struct *work);

@@ -4048,6 +4048,22 @@ void workqueue_set_max_active(struct wor
 EXPORT_SYMBOL_GPL(workqueue_set_max_active);
 
 /**
+ * current_work - retrieve %current task's work struct
+ *
+ * Determine if %current task is a workqueue worker and what it's working on.
+ * Useful to find out the context that the %current task is running in.
+ *
+ * Return: work struct if %current task is a workqueue worker, %NULL otherwise.
+ */
+struct work_struct *current_work(void)
+{
+	struct worker *worker = current_wq_worker();
+
+	return worker ? worker->current_work : NULL;
+}
+EXPORT_SYMBOL(current_work);
+
+/**
  * current_is_workqueue_rescuer - is %current workqueue rescuer?
  *
  * Determine whether %current is a workqueue rescuer.  Can be used from

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

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

From: Lukas Wunner <[email protected]>

commit aa0aad57909eb321746325951d66af88a83bc956 upstream.

amdgpu's ->runtime_suspend hook calls drm_kms_helper_poll_disable(), which waits for the output poll worker to finish if it's running.

The output poll worker meanwhile calls pm_runtime_get_sync() in amdgpu's ->detect hooks, which waits for the ongoing suspend to finish, causing a deadlock.

Fix by not acquiring a runtime PM ref if the ->detect hooks are called in the output poll worker's context. This is safe because the poll worker is only enabled while runtime active and we know that ->runtime_suspend waits for it to finish.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c |   58 ++++++++++++++++---------
 1 file changed, 38 insertions(+), 20 deletions(-)

@@ -739,9 +739,11 @@ amdgpu_connector_lvds_detect(struct drm_
 	enum drm_connector_status ret = connector_status_disconnected;
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (encoder) {
 		struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);

@@ -760,8 +762,12 @@ amdgpu_connector_lvds_detect(struct drm_
 	/* check acpi lid status ??? */
 
 	amdgpu_connector_update_scratch_regs(connector, ret);
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
+
 	return ret;
 }
 

@@ -862,9 +868,11 @@ amdgpu_connector_vga_detect(struct drm_c
 	enum drm_connector_status ret = connector_status_disconnected;
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	encoder = amdgpu_connector_best_single_encoder(connector);
 	if (!encoder)

@@ -918,8 +926,10 @@ amdgpu_connector_vga_detect(struct drm_c
 	amdgpu_connector_update_scratch_regs(connector, ret);
 
 out:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }

@@ -981,9 +991,11 @@ amdgpu_connector_dvi_detect(struct drm_c
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) {
 		ret = connector->status;

@@ -1108,8 +1120,10 @@ out:
 	amdgpu_connector_update_scratch_regs(connector, ret);
 
 exit:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }

@@ -1351,9 +1365,11 @@ amdgpu_connector_dp_detect(struct drm_co
 	struct drm_encoder *encoder = amdgpu_connector_best_single_encoder(connector);
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (!force && amdgpu_connector_check_hpd_status_unchanged(connector)) {
 		ret = connector->status;

@@ -1421,8 +1437,10 @@ amdgpu_connector_dp_detect(struct drm_co
 
 	amdgpu_connector_update_scratch_regs(connector, ret);
 out:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }

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

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

From: Alex Deucher <[email protected]>

commit 0b58d90f89545e021d188c289fa142e5ff9e708b upstream.

Always set the graphics values to the max for the asic type. E.g., some 1 RB chips are actually 1 RB chips, others are actually harvested 2 RB chips.

---
 drivers/gpu/drm/radeon/cik.c |   31 ++-----------------------------
 1 file changed, 2 insertions(+), 29 deletions(-)

@@ -3599,35 +3599,8 @@ static void cik_gpu_init(struct radeon_d
 	case CHIP_KAVERI:
 		rdev->config.cik.max_shader_engines = 1;
 		rdev->config.cik.max_tile_pipes = 4;
-		if ((rdev->pdev->device == 0x1304) ||
-		    (rdev->pdev->device == 0x1305) ||
-		    (rdev->pdev->device == 0x130C) ||
-		    (rdev->pdev->device == 0x130F) ||
-		    (rdev->pdev->device == 0x1310) ||
-		    (rdev->pdev->device == 0x1311) ||
-		    (rdev->pdev->device == 0x131C)) {
-			rdev->config.cik.max_cu_per_sh = 8;
-			rdev->config.cik.max_backends_per_se = 2;
-		} else if ((rdev->pdev->device == 0x1309) ||
-			   (rdev->pdev->device == 0x130A) ||
-			   (rdev->pdev->device == 0x130D) ||
-			   (rdev->pdev->device == 0x1313) ||
-			   (rdev->pdev->device == 0x131D)) {
-			rdev->config.cik.max_cu_per_sh = 6;
-			rdev->config.cik.max_backends_per_se = 2;
-		} else if ((rdev->pdev->device == 0x1306) ||
-			   (rdev->pdev->device == 0x1307) ||
-			   (rdev->pdev->device == 0x130B) ||
-			   (rdev->pdev->device == 0x130E) ||
-			   (rdev->pdev->device == 0x1315) ||
-			   (rdev->pdev->device == 0x1318) ||
-			   (rdev->pdev->device == 0x131B)) {
-			rdev->config.cik.max_cu_per_sh = 4;
-			rdev->config.cik.max_backends_per_se = 1;
-		} else {
-			rdev->config.cik.max_cu_per_sh = 3;
-			rdev->config.cik.max_backends_per_se = 1;
-		}
+		rdev->config.cik.max_cu_per_sh = 8;
+		rdev->config.cik.max_backends_per_se = 2;
 		rdev->config.cik.max_sh_per_se = 1;
 		rdev->config.cik.max_texture_channel_caches = 4;
 		rdev->config.cik.max_gprs = 256;

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

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

From: Alex Deucher <[email protected]>

commit 545b0bcde7fbd3ee408fa842ea0731451dc4bd0a upstream.

Always set the graphics values to the max for the asic type. E.g., some 1 RB chips are actually 1 RB chips, others are actually harvested 2 RB chips.

---
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c |   30 ++----------------------------
 1 file changed, 2 insertions(+), 28 deletions(-)

@@ -2104,34 +2104,8 @@ static void gfx_v7_0_gpu_init(struct amd
 	case CHIP_KAVERI:
 		adev->gfx.config.max_shader_engines = 1;
 		adev->gfx.config.max_tile_pipes = 4;
-		if ((adev->pdev->device == 0x1304) ||
-		    (adev->pdev->device == 0x1305) ||
-		    (adev->pdev->device == 0x130C) ||
-		    (adev->pdev->device == 0x130F) ||
-		    (adev->pdev->device == 0x1310) ||
-		    (adev->pdev->device == 0x1311) ||
-		    (adev->pdev->device == 0x131C)) {
-			adev->gfx.config.max_cu_per_sh = 8;
-			adev->gfx.config.max_backends_per_se = 2;
-		} else if ((adev->pdev->device == 0x1309) ||
-			   (adev->pdev->device == 0x130A) ||
-			   (adev->pdev->device == 0x130D) ||
-			   (adev->pdev->device == 0x1313) ||
-			   (adev->pdev->device == 0x131D)) {
-			adev->gfx.config.max_cu_per_sh = 6;
-			adev->gfx.config.max_backends_per_se = 2;
-		} else if ((adev->pdev->device == 0x1306) ||
-			   (adev->pdev->device == 0x1307) ||
-			   (adev->pdev->device == 0x130B) ||
-			   (adev->pdev->device == 0x130E) ||
-			   (adev->pdev->device == 0x1315) ||
-			   (adev->pdev->device == 0x131B)) {
-			adev->gfx.config.max_cu_per_sh = 4;
-			adev->gfx.config.max_backends_per_se = 1;
-		} else {
-			adev->gfx.config.max_cu_per_sh = 3;
-			adev->gfx.config.max_backends_per_se = 1;
-		}
+		adev->gfx.config.max_cu_per_sh = 8;
+		adev->gfx.config.max_backends_per_se = 2;
 		adev->gfx.config.max_sh_per_se = 1;
 		adev->gfx.config.max_texture_channel_caches = 4;
 		adev->gfx.config.max_gprs = 256;

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

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

From: Justin Chen <[email protected]>

commit 06a3f0c9f2725f5d7c63c4203839373c9bd00c28 upstream.

Commit a3e6c1eff548 ("MIPS: IRQ: Fix disable_irq on CPU IRQs") fixes an issue where disable_irq did not actually disable the irq. The bug caused our IPIs to not be disabled, which actually is the correct behavior.

With the addition of commit a3e6c1eff548 ("MIPS: IRQ: Fix disable_irq on CPU IRQs"), the IPIs were getting disabled going into suspend, thus schedule_ipi() was not being called. This caused deadlocks where schedulable task were not being scheduled and other cpus were waiting for them to do something.

Add the IRQF_NO_SUSPEND flag so an irq_disable will not be called on the IPIs during suspend.

Patchwork: https://patchwork.linux-mips.org/patch/17385/

---
 arch/mips/kernel/smp-bmips.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -166,11 +166,11 @@ static void bmips_prepare_cpus(unsigned
 		return;
 	}
 
-	if (request_irq(IPI0_IRQ, bmips_ipi_interrupt, IRQF_PERCPU,
-			"smp_ipi0", NULL))
+	if (request_irq(IPI0_IRQ, bmips_ipi_interrupt,
+			IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi0", NULL))
 		panic("Can't request IPI0 interrupt");
-	if (request_irq(IPI1_IRQ, bmips_ipi_interrupt, IRQF_PERCPU,
-			"smp_ipi1", NULL))
+	if (request_irq(IPI1_IRQ, bmips_ipi_interrupt,
+			IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi1", NULL))
 		panic("Can't request IPI1 interrupt");
 }
 

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

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

From: Colin Ian King <[email protected]>

commit 902f4d067a50ccf645a58dd5fb1d113b6e0f9b5b upstream.

The allocation of host_data is not null checked, leading to a null pointer dereference if the allocation fails. Fix this by adding a null check and return with -ENOMEM.

Patchwork: https://patchwork.linux-mips.org/patch/18658/

---
 arch/mips/cavium-octeon/octeon-irq.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -2246,6 +2246,8 @@ static int __init octeon_irq_init_cib(st
 	}
 
 	host_data = kzalloc(sizeof(*host_data), GFP_KERNEL);
+	if (!host_data)
+		return -ENOMEM;
 	raw_spin_lock_init(&host_data->lock);
 
 	addr = of_get_address(ciu_node, 0, NULL, NULL);

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

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

From: Zhang Bo <[email protected]>

commit ea4f7bd2aca9f68470e9aac0fc9432fd180b1fe7 upstream.

If matrix_keypad_stop() is executing and the keypad interrupt is triggered, disable_row_irqs() may be called by both matrix_keypad_interrupt() and matrix_keypad_stop() at the same time, causing interrupts to be disabled twice and the keypad being "stuck" after resuming.

Take lock when setting keypad->stopped to ensure that ISR will not race with matrix_keypad_stop() disabling interrupts.

---
 drivers/input/keyboard/matrix_keypad.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -216,8 +216,10 @@ static void matrix_keypad_stop(struct in
 {
 	struct matrix_keypad *keypad = input_get_drvdata(dev);
 
+	spin_lock_irq(&keypad->lock);
 	keypad->stopped = true;
-	mb();
+	spin_unlock_irq(&keypad->lock);
+
 	flush_work(&keypad->work.work);
 	/*
 	 * matrix_keypad_scan() will leave IRQs enabled;

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

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

From: Ross Zwisler <[email protected]>

commit 1d037577c323e5090ce281e96bc313ab2eee5be2 upstream.

The following commit:

commit aa4d86163e4e ("block: loop: switch to VFS ITER_BVEC")

replaced __do_lo_send_write(), which used ITER_KVEC iterators, with lo_write_bvec() which uses ITER_BVEC iterators. In this change, though, the WRITE flag was lost:

- iov_iter_kvec(&from, ITER_KVEC | WRITE, &kvec, 1, len);
+ iov_iter_bvec(&i, ITER_BVEC, bvec, 1, bvec->bv_len);

This flag is necessary for the DAX case because we make decisions based on whether or not the iterator is a READ or a WRITE in dax_iomap_actor() and in dax_iomap_rw().

We end up going through this path in configurations where we combine a PMEM device with 4k sectors, a loopback device and DAX. The consequence of this missed flag is that what we intend as a write actually turns into a read in the DAX code, so no data is ever written.

The very simplest test case is to create a loopback device and try and write a small string to it, then hexdump a few bytes of the device to see if the write took. Without this patch you read back all zeros, with this you read back the string you wrote.

For XFS this causes us to fail or panic during the following xfstests:

	xfs/074 xfs/078 xfs/216 xfs/217 xfs/250

For ext4 we have a similar issue where writes never happen, but we don't currently have any xfstests that use loopback and show this issue.

Fix this by restoring the WRITE flag argument to iov_iter_bvec(). This causes the xfstests to all pass.

---
 drivers/block/loop.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -263,7 +263,7 @@ static int lo_write_bvec(struct file *fi
 	struct iov_iter i;
 	ssize_t bw;
 
-	iov_iter_bvec(&i, ITER_BVEC, bvec, 1, bvec->bv_len);
+	iov_iter_bvec(&i, ITER_BVEC | WRITE, bvec, 1, bvec->bv_len);
 
 	file_start_write(file);
 	bw = vfs_iter_write(file, &i, ppos);

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

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

From: James Hogan <[email protected]>

commit 55fe6da9efba102866e2fb5b40b04b6a4b26c19e upstream.

cmd_dt_S_dtb constructs the assembly source to incorporate a devicetree FDT (that is, the .dtb file) as binary data in the kernel image. This assembly source contains labels before and after the binary data. The label names incorporate the file name of the corresponding .dtb file. Hyphens are not legal characters in labels, so .dtb files built into the kernel with hyphens in the file name result in errors like the following:

bcm3368-netgear-cvg834g.dtb.S: Assembler messages:
bcm3368-netgear-cvg834g.dtb.S:5: Error: : no such section bcm3368-netgear-cvg834g.dtb.S:5: Error: junk at end of line, first unrecognized character is -' bcm3368-netgear-cvg834g.dtb.S:6: Error: unrecognized opcode __dtb_bcm3368-netgear-cvg834g_begin:' bcm3368-netgear-cvg834g.dtb.S:8: Error: unrecognized opcode __dtb_bcm3368-netgear-cvg834g_end:' bcm3368-netgear-cvg834g.dtb.S:9: Error: : no such section bcm3368-netgear-cvg834g.dtb.S:9: Error: junk at end of line, first unrecognized character is -'

Fix this by updating cmd_dt_S_dtb to transform all hyphens from the file name to underscores when constructing the labels.

As of v4.16-rc2, 1139 .dts files across ARM64, ARM, MIPS and PowerPC contain hyphens in their names, but the issue only currently manifests on Broadcom MIPS platforms, as that is the only place where such files are built into the kernel. For example when CONFIG_DT_NETGEAR_CVG834G=y, or on BMIPS kernels when the dtbs target is used (in the latter case it admittedly shouldn't really build all the dtb.o files, but thats a separate issue).

---
 scripts/Makefile.lib |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

@@ -270,11 +270,11 @@ cmd_dt_S_dtb=						\
 	echo '\#include <asm-generic/vmlinux.lds.h>'; 	\
 	echo '.section .dtb.init.rodata,"a"';		\
 	echo '.balign STRUCT_ALIGNMENT';		\
-	echo '.global __dtb_$(*F)_begin';		\
-	echo '__dtb_$(*F)_begin:';			\
+	echo '.global __dtb_$(subst -,_,$(*F))_begin';	\
+	echo '__dtb_$(subst -,_,$(*F))_begin:';		\
 	echo '.incbin "$<" ';				\
-	echo '__dtb_$(*F)_end:';			\
-	echo '.global __dtb_$(*F)_end';			\
+	echo '__dtb_$(subst -,_,$(*F))_end:';		\
+	echo '.global __dtb_$(subst -,_,$(*F))_end';	\
 	echo '.balign STRUCT_ALIGNMENT'; 		\
 ) > $@
 

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

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

From: Michael Lyle <[email protected]>

commit 86755b7a96faed57f910f9e6b8061e019ac1ec08 upstream.

This can happen e.g. during disk cloning.

This is an incomplete fix: it does not catch duplicate UUIDs earlier when things are still unattached. It does not unregister the device. Further changes to cope better with this are planned but conflict with Coly's ongoing improvements to handling device errors. In the meantime, one can manually stop the device after this has happened.

Attempts to attach a duplicate device result in:

[  136.372404] loop: module loaded
[  136.424461] bcache: register_bdev() registered backing device loop0
[  136.424464] bcache: bch_cached_dev_attach() Tried to attach loop0 but duplicate UUID already attached

My test procedure is:

dd if=/dev/sdb1 of=imgfile bs=1024 count=262144
losetup -f imgfile

---
 drivers/md/bcache/super.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

@@ -935,6 +935,7 @@ int bch_cached_dev_attach(struct cached_
 	uint32_t rtime = cpu_to_le32(get_seconds());
 	struct uuid_entry *u;
 	char buf[BDEVNAME_SIZE];
+	struct cached_dev *exist_dc, *t;
 
 	bdevname(dc->bdev, buf);
 

@@ -958,6 +959,16 @@ int bch_cached_dev_attach(struct cached_
 		return -EINVAL;
 	}
 
+	/* Check whether already attached */
+	list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) {
+		if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) {
+			pr_err("Tried to attach %s but duplicate UUID already attached",
+				buf);
+
+			return -EINVAL;
+		}
+	}
+
 	u = uuid_find(c, dc->sb.uuid);
 
 	if (u &&

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

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

From: Seunghun Han <[email protected]>

commit b3b7c4795ccab5be71f080774c45bbbcc75c2aaf upstream.

The check_interval file in

/sys/devices/system/machinecheck/machinecheck<cpu number>

directory is a global timer value for MCE polling. If it is changed by one CPU, mce_restart() broadcasts the event to other CPUs to delete and restart the MCE polling timer and __mcheck_cpu_init_timer() reinitializes the mce_timer variable.

If more than one CPU writes a specific value to the check_interval file concurrently, mce_timer is not protected from such concurrent accesses and all kinds of explosions happen. Since only root can write to those sysfs variables, the issue is not a big deal security-wise.

However, concurrent writes to these configuration variables is void of reason so the proper thing to do is to serialize the access with a mutex.

Boris:

- Make store_int_with_restart() use device_store_ulong() to filter out negative intervals
- Limit min interval to 1 second
- Correct locking
- Massage commit message

---
 arch/x86/kernel/cpu/mcheck/mce.c |   22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

--
To unsubscribe from this list: send the line "unsubscribe linux-edac" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

@@ -60,6 +60,9 @@ static DEFINE_MUTEX(mce_chrdev_read_mute
 	smp_load_acquire(&(p)); \
 })
 
+/* sysfs synchronization */
+static DEFINE_MUTEX(mce_sysfs_mutex);
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
 

@@ -2220,6 +2223,7 @@ static ssize_t set_ignore_ce(struct devi
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
+	mutex_lock(&mce_sysfs_mutex);
 	if (mca_cfg.ignore_ce ^ !!new) {
 		if (new) {
 			/* disable ce features */

@@ -2232,6 +2236,8 @@ static ssize_t set_ignore_ce(struct devi
 			on_each_cpu(mce_enable_ce, (void *)1, 1);
 		}
 	}
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return size;
 }
 

@@ -2244,6 +2250,7 @@ static ssize_t set_cmci_disabled(struct
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
+	mutex_lock(&mce_sysfs_mutex);
 	if (mca_cfg.cmci_disabled ^ !!new) {
 		if (new) {
 			/* disable cmci */

@@ -2255,6 +2262,8 @@ static ssize_t set_cmci_disabled(struct
 			on_each_cpu(mce_enable_ce, NULL, 1);
 		}
 	}
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return size;
 }
 

@@ -2262,8 +2271,19 @@ static ssize_t store_int_with_restart(st
 				      struct device_attribute *attr,
 				      const char *buf, size_t size)
 {
-	ssize_t ret = device_store_int(s, attr, buf, size);
+	unsigned long old_check_interval = check_interval;
+	ssize_t ret = device_store_ulong(s, attr, buf, size);
+
+	if (check_interval == old_check_interval)
+		return ret;
+
+	if (check_interval < 1)
+		check_interval = 1;
+
+	mutex_lock(&mce_sysfs_mutex);
 	mce_restart();
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return ret;
 }
 

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

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

From: Takashi Iwai <[email protected]>

commit d85739367c6d56e475c281945c68fdb05ca74b4c upstream.

This is a fix for a (sort of) fallout in the recent commit d15d662e89fc ("ALSA: seq: Fix racy pool initializations") for CVE-2018-1000004.
As the pool resize deletes the existing cells, it may lead to a race when another thread is writing concurrently, eventually resulting a UAF.

A simple workaround is not to allow the pool resizing when the pool is in use. It's an invalid behavior in anyway.

---
 sound/core/seq/seq_clientmgr.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -1924,6 +1924,9 @@ static int snd_seq_ioctl_set_client_pool
 	    (! snd_seq_write_pool_allocated(client) ||
 	     info.output_pool != client->pool->size)) {
 		if (snd_seq_write_pool_allocated(client)) {
+			/* is the pool in use? */
+			if (atomic_read(&client->pool->counter))
+				return -EBUSY;
 			/* remove all existing cells */
 			snd_seq_pool_mark_closing(client->pool);
 			snd_seq_queue_client_leave_cells(client->number);

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

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

From: Takashi Iwai <[email protected]>

commit 7bd80091567789f1c0cb70eb4737aac8bcd2b6b9 upstream.

This patch is an attempt for further hardening against races between the concurrent write and ioctls. The previous fix d15d662e89fc ("ALSA: seq: Fix racy pool initializations") covered the race of the pool initialization at writer and the pool resize ioctl by the client->ioctl_mutex (CVE-2018-1000004). However, basically this mutex should be applied more widely to the whole write operation for avoiding the unexpected pool operations by another thread.

The only change outside snd_seq_write() is the additional mutex argument to helper functions, so that we can unlock / relock the given mutex temporarily during schedule() call for blocking write.

---
 sound/core/seq/seq_clientmgr.c |   18 +++++++++++-------
 sound/core/seq/seq_fifo.c      |    2 +-
 sound/core/seq/seq_memory.c    |   14 ++++++++++----
 sound/core/seq/seq_memory.h    |    3 ++-
 4 files changed, 24 insertions(+), 13 deletions(-)

@@ -919,7 +919,8 @@ int snd_seq_dispatch_event(struct snd_se
 static int snd_seq_client_enqueue_event(struct snd_seq_client *client,
 					struct snd_seq_event *event,
 					struct file *file, int blocking,
-					int atomic, int hop)
+					int atomic, int hop,
+					struct mutex *mutexp)
 {
 	struct snd_seq_event_cell *cell;
 	int err;

@@ -957,7 +958,8 @@ static int snd_seq_client_enqueue_event(
 		return -ENXIO; /* queue is not allocated */
 
 	/* allocate an event cell */
-	err = snd_seq_event_dup(client->pool, event, &cell, !blocking || atomic, file);
+	err = snd_seq_event_dup(client->pool, event, &cell, !blocking || atomic,
+				file, mutexp);
 	if (err < 0)
 		return err;
 

@@ -1026,12 +1028,11 @@ static ssize_t snd_seq_write(struct file
 		return -ENXIO;
 
 	/* allocate the pool now if the pool is not allocated yet */ 
+	mutex_lock(&client->ioctl_mutex);
 	if (client->pool->size > 0 && !snd_seq_write_pool_allocated(client)) {
-		mutex_lock(&client->ioctl_mutex);
 		err = snd_seq_pool_init(client->pool);
-		mutex_unlock(&client->ioctl_mutex);
 		if (err < 0)
-			return -ENOMEM;
+			goto out;
 	}
 
 	/* only process whole events */

@@ -1082,7 +1083,7 @@ static ssize_t snd_seq_write(struct file
 		/* ok, enqueue it */
 		err = snd_seq_client_enqueue_event(client, &event, file,
 						   !(file->f_flags & O_NONBLOCK),
-						   0, 0);
+						   0, 0, &client->ioctl_mutex);
 		if (err < 0)
 			break;
 

@@ -1093,6 +1094,8 @@ static ssize_t snd_seq_write(struct file
 		written += len;
 	}
 
+ out:
+	mutex_unlock(&client->ioctl_mutex);
 	return written ? written : err;
 }
 

@@ -2350,7 +2353,8 @@ static int kernel_client_enqueue(int cli
 	if (! cptr->accept_output)
 		result = -EPERM;
 	else /* send it */
-		result = snd_seq_client_enqueue_event(cptr, ev, file, blocking, atomic, hop);
+		result = snd_seq_client_enqueue_event(cptr, ev, file, blocking,
+						      atomic, hop, NULL);
 
 	snd_seq_client_unlock(cptr);
 	return result;

@@ -123,7 +123,7 @@ int snd_seq_fifo_event_in(struct snd_seq
 		return -EINVAL;
 
 	snd_use_lock_use(&f->use_lock);
-	err = snd_seq_event_dup(f->pool, event, &cell, 1, NULL); /* always non-blocking */
+	err = snd_seq_event_dup(f->pool, event, &cell, 1, NULL, NULL); /* always non-blocking */
 	if (err < 0) {
 		if ((err == -ENOMEM) || (err == -EAGAIN))
 			atomic_inc(&f->overflow);

@@ -221,7 +221,8 @@ void snd_seq_cell_free(struct snd_seq_ev
  */
 static int snd_seq_cell_alloc(struct snd_seq_pool *pool,
 			      struct snd_seq_event_cell **cellp,
-			      int nonblock, struct file *file)
+			      int nonblock, struct file *file,
+			      struct mutex *mutexp)
 {
 	struct snd_seq_event_cell *cell;
 	unsigned long flags;

@@ -245,7 +246,11 @@ static int snd_seq_cell_alloc(struct snd
 		set_current_state(TASK_INTERRUPTIBLE);
 		add_wait_queue(&pool->output_sleep, &wait);
 		spin_unlock_irq(&pool->lock);
+		if (mutexp)
+			mutex_unlock(mutexp);
 		schedule();
+		if (mutexp)
+			mutex_lock(mutexp);
 		spin_lock_irq(&pool->lock);
 		remove_wait_queue(&pool->output_sleep, &wait);
 		/* interrupted? */

@@ -288,7 +293,7 @@ __error:
  */
 int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event,
 		      struct snd_seq_event_cell **cellp, int nonblock,
-		      struct file *file)
+		      struct file *file, struct mutex *mutexp)
 {
 	int ncells, err;
 	unsigned int extlen;

@@ -305,7 +310,7 @@ int snd_seq_event_dup(struct snd_seq_poo
 	if (ncells >= pool->total_elements)
 		return -ENOMEM;
 
-	err = snd_seq_cell_alloc(pool, &cell, nonblock, file);
+	err = snd_seq_cell_alloc(pool, &cell, nonblock, file, mutexp);
 	if (err < 0)
 		return err;
 

@@ -331,7 +336,8 @@ int snd_seq_event_dup(struct snd_seq_poo
 			int size = sizeof(struct snd_seq_event);
 			if (len < size)
 				size = len;
-			err = snd_seq_cell_alloc(pool, &tmp, nonblock, file);
+			err = snd_seq_cell_alloc(pool, &tmp, nonblock, file,
+						 mutexp);
 			if (err < 0)
 				goto __error;
 			if (cell->event.data.ext.ptr == NULL)

@@ -66,7 +66,8 @@ struct snd_seq_pool {
 void snd_seq_cell_free(struct snd_seq_event_cell *cell);
 
 int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event,
-		      struct snd_seq_event_cell **cellp, int nonblock, struct file *file);
+		      struct snd_seq_event_cell **cellp, int nonblock,
+		      struct file *file, struct mutex *mutexp);
 
 /* return number of unused (free) cells */
 static inline int snd_seq_unused_cells(struct snd_seq_pool *pool)

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

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

From: Dennis Wassenberg <[email protected]>

commit aea808172018ca01abf53db808323aed23281835 upstream.

This patch adds missing initialisation for HP 2013 UltraSlim Dock Line-In/Out PINs and activates keyboard mute/micmute leds for HP EliteBook 820 G3

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

@@ -849,6 +849,7 @@ static const struct snd_pci_quirk cxt506
 	SND_PCI_QUIRK(0x1025, 0x054c, "Acer Aspire 3830TG", CXT_FIXUP_ASPIRE_DMIC),
 	SND_PCI_QUIRK(0x1025, 0x054f, "Acer Aspire 4830T", CXT_FIXUP_ASPIRE_DMIC),
 	SND_PCI_QUIRK(0x103c, 0x8079, "HP EliteBook 840 G3", CXT_FIXUP_HP_DOCK),
+	SND_PCI_QUIRK(0x103c, 0x807C, "HP EliteBook 820 G3", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE),
 	SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),

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

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

From: Dennis Wassenberg <[email protected]>

commit 099fd6ca0ad25bc19c5ade2ea4b25b8fadaa11b3 upstream.

This patch adds missing initialisation for HP 2013 UltraSlim Dock Line-In/Out PINs and activates keyboard mute/micmute leds for HP ProBook 640 G2

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

@@ -850,6 +850,7 @@ static const struct snd_pci_quirk cxt506
 	SND_PCI_QUIRK(0x1025, 0x054f, "Acer Aspire 4830T", CXT_FIXUP_ASPIRE_DMIC),
 	SND_PCI_QUIRK(0x103c, 0x8079, "HP EliteBook 840 G3", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x807C, "HP EliteBook 820 G3", CXT_FIXUP_HP_DOCK),
+	SND_PCI_QUIRK(0x103c, 0x80FD, "HP ProBook 640 G2", CXT_FIXUP_HP_DOCK),
 	SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE),
 	SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
 	SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),

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

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

From: Dan Williams <[email protected]>

commit eb6174f6d1be16b19cfa43dac296bfed003ce1a6 upstream.

The nospec.h header expects the per-architecture header file <asm/barrier.h> to optionally define array_index_mask_nospec(). Include that dependency to prevent inadvertent fallback to the default array_index_mask_nospec() implementation.

The default implementation may not provide a full mitigation on architectures that perform data value speculation.

---
 include/linux/nospec.h |    1 +
 1 file changed, 1 insertion(+)

@@ -5,6 +5,7 @@
 
 #ifndef _LINUX_NOSPEC_H
 #define _LINUX_NOSPEC_H
+#include <asm/barrier.h>
 
 /**
  * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise

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

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

From: Florian Westphal <[email protected]>

commit a7f1884554b81bd68cd435d72f09a3527629ac43 upstream.

Since 4.4 we erronously use timestamp of the netlink skb (which is zero).

Bugzilla: https://bugzilla.netfilter.org/show_bug.cgi?id=1066

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

@@ -501,7 +501,7 @@ nfqnl_build_packet_message(struct net *n
 
 	if (entskb->tstamp.tv64) {
 		struct nfqnl_msg_packet_timestamp ts;
-		struct timespec64 kts = ktime_to_timespec64(skb->tstamp);
+		struct timespec64 kts = ktime_to_timespec64(entskb->tstamp);
 
 		ts.sec = cpu_to_be64(kts.tv_sec);
 		ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC);

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

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

From: Florian Westphal <[email protected]>

commit 57ebd808a97d7c5b1e1afb937c2db22beba3c1f8 upstream.

The rationale for removing the check is only correct for rulesets generated by ip(6)tables.

In iptables, a jump can only occur to a user-defined chain, i.e. because we size the stack based on number of user-defined chains we cannot exceed stack size.

However, the underlying binary format has no such restriction, and the validation step only ensures that the jump target is a valid rule start point.

IOW, its possible to build a rule blob that has no user-defined chains but does contain a jump.

If this happens, no jump stack gets allocated and crash occurs because no jumpstack was allocated.

---
 net/ipv4/netfilter/arp_tables.c |    4 ++++
 net/ipv4/netfilter/ip_tables.c  |    4 ++++
 net/ipv6/netfilter/ip6_tables.c |    4 ++++
 3 files changed, 12 insertions(+)

@@ -329,6 +329,10 @@ unsigned int arpt_do_table(struct sk_buf
 			}
 			if (table_base + v
 			    != arpt_next_entry(e)) {
+				if (unlikely(stackidx >= private->stacksize)) {
+					verdict = NF_DROP;
+					break;
+				}
 				jumpstack[stackidx++] = e;
 			}
 

@@ -408,6 +408,10 @@ ipt_do_table(struct sk_buff *skb,
 			}
 			if (table_base + v != ipt_next_entry(e) &&
 			    !(e->ip.flags & IPT_F_GOTO)) {
+				if (unlikely(stackidx >= private->stacksize)) {
+					verdict = NF_DROP;
+					break;
+				}
 				jumpstack[stackidx++] = e;
 				pr_debug("Pushed %p into pos %u\n",
 					 e, stackidx - 1);

@@ -425,6 +425,10 @@ ip6t_do_table(struct sk_buff *skb,
 			}
 			if (table_base + v != ip6t_next_entry(e) &&
 			    !(e->ipv6.flags & IP6T_F_GOTO)) {
+				if (unlikely(stackidx >= private->stacksize)) {
+					verdict = NF_DROP;
+					break;
+				}
 				jumpstack[stackidx++] = e;
 			}
 

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

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

From: Paolo Abeni <[email protected]>

commit db57ccf0f2f4624b4c4758379f8165277504fbd7 upstream.

syzbot reported a division by 0 bug in the netfilter nat code:

divide error: 0000 [#1] SMP KASAN
Dumping ftrace buffer:
(ftrace buffer empty)

Modules linked in:
CPU: 1 PID: 4168 Comm: syzkaller034710 Not tainted 4.16.0-rc1+ #309
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
RIP: 0010:nf_nat_l4proto_unique_tuple+0x291/0x530
net/netfilter/nf_nat_proto_common.c:88
RSP: 0018:ffff8801b2466778 EFLAGS: 00010246
RAX: 000000000000f153 RBX: ffff8801b2466dd8 RCX: ffff8801b2466c7c
RDX: 0000000000000000 RSI: ffff8801b2466c58 RDI: ffff8801db5293ac
RBP: ffff8801b24667d8 R08: ffff8801b8ba6dc0 R09: ffffffff88af5900
R10: ffff8801b24666f0 R11: 0000000000000000 R12: 000000002990f153
R13: 0000000000000001 R14: 0000000000000000 R15: ffff8801b2466c7c
FS:  00000000017e3880(0000) GS:ffff8801db500000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000208fdfe4 CR3: 00000001b5340002 CR4: 00000000001606e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
  dccp_unique_tuple+0x40/0x50 net/netfilter/nf_nat_proto_dccp.c:30
  get_unique_tuple+0xc28/0x1c10 net/netfilter/nf_nat_core.c:362
  nf_nat_setup_info+0x1c2/0xe00 net/netfilter/nf_nat_core.c:406
  nf_nat_redirect_ipv6+0x306/0x730 net/netfilter/nf_nat_redirect.c:124
  redirect_tg6+0x7f/0xb0 net/netfilter/xt_REDIRECT.c:34
  ip6t_do_table+0xc2a/0x1a30 net/ipv6/netfilter/ip6_tables.c:365
  ip6table_nat_do_chain+0x65/0x80 net/ipv6/netfilter/ip6table_nat.c:41
  nf_nat_ipv6_fn+0x594/0xa80 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c:302
  nf_nat_ipv6_local_fn+0x33/0x5d0
net/ipv6/netfilter/nf_nat_l3proto_ipv6.c:407
  ip6table_nat_local_fn+0x2c/0x40 net/ipv6/netfilter/ip6table_nat.c:69
  nf_hook_entry_hookfn include/linux/netfilter.h:120 [inline]
  nf_hook_slow+0xba/0x1a0 net/netfilter/core.c:483
  nf_hook include/linux/netfilter.h:243 [inline]
  NF_HOOK include/linux/netfilter.h:286 [inline]
  ip6_xmit+0x10ec/0x2260 net/ipv6/ip6_output.c:277
  inet6_csk_xmit+0x2fc/0x580 net/ipv6/inet6_connection_sock.c:139
  dccp_transmit_skb+0x9ac/0x10f0 net/dccp/output.c:142
  dccp_connect+0x369/0x670 net/dccp/output.c:564
  dccp_v6_connect+0xe17/0x1bf0 net/dccp/ipv6.c:946
  __inet_stream_connect+0x2d4/0xf00 net/ipv4/af_inet.c:620
  inet_stream_connect+0x58/0xa0 net/ipv4/af_inet.c:684
  SYSC_connect+0x213/0x4a0 net/socket.c:1639
  SyS_connect+0x24/0x30 net/socket.c:1620
  do_syscall_64+0x282/0x940 arch/x86/entry/common.c:287
  entry_SYSCALL_64_after_hwframe+0x26/0x9b
RIP: 0033:0x441c69
RSP: 002b:00007ffe50cc0be8 EFLAGS: 00000217 ORIG_RAX: 000000000000002a
RAX: ffffffffffffffda RBX: ffffffffffffffff RCX: 0000000000441c69
RDX: 000000000000001c RSI: 00000000208fdfe4 RDI: 0000000000000003
RBP: 00000000006cc018 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000538 R11: 0000000000000217 R12: 0000000000403590
R13: 0000000000403620 R14: 0000000000000000 R15: 0000000000000000
Code: 48 89 f0 83 e0 07 83 c0 01 38 d0 7c 08 84 d2 0f 85 46 02 00 00 48 8b
45 c8 44 0f b7 20 e8 88 97 04 fd 31 d2 41 0f b7 c4 4c 89 f9 <41> f7 f6 48
c1 e9 03 48 b8 00 00 00 00 00 fc ff df 0f b6 0c 01
RIP: nf_nat_l4proto_unique_tuple+0x291/0x530

net/netfilter/nf_nat_proto_common.c:88 RSP: ffff8801b2466778

The problem is that currently we don't have any check on the configured port range. A port range == -1 triggers the bug, while other negative values may require a very long time to complete the following loop.

This commit addresses the issue swapping the two ends on negative ranges. The check is performed in nf_nat_l4proto_unique_tuple() since the nft nat loads the port values from nft registers at runtime.

v1 -> v2: use the correct 'Fixes' tag
v2 -> v3: update commit message, drop unneeded READ_ONCE()

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

@@ -41,7 +41,7 @@ void nf_nat_l4proto_unique_tuple(const s
 				 const struct nf_conn *ct,
 				 u16 *rover)
 {
-	unsigned int range_size, min, i;
+	unsigned int range_size, min, max, i;
 	__be16 *portptr;
 	u_int16_t off;
 

@@ -71,7 +71,10 @@ void nf_nat_l4proto_unique_tuple(const s
 		}
 	} else {
 		min = ntohs(range->min_proto.all);
-		range_size = ntohs(range->max_proto.all) - min + 1;
+		max = ntohs(range->max_proto.all);
+		if (unlikely(max < min))
+			swap(max, min);
+		range_size = max - min + 1;
 	}
 
 	if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) {

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

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

From: Eric Dumazet <[email protected]>

commit cfc2c740533368b96e2be5e0a4e8c3cace7d9814 upstream.

We had one report from syzkaller [1]

First issue is that INIT_WORK() should be done before mod_timer() or we risk timer being fired too soon, even with a 1 second timer.

Second issue is that we need to reject too big info->timeout to avoid overflows in msecs_to_jiffies(info->timeout * 1000), or risk looping, if result after overflow is 0.

[1]

WARNING: CPU: 1 PID: 5129 at kernel/workqueue.c:1444 __queue_work+0xdf4/0x1230 kernel/workqueue.c:1444
Kernel panic - not syncing: panic_on_warn set ...

CPU: 1 PID: 5129 Comm: syzkaller159866 Not tainted 4.16.0-rc1+ #230
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:53
 panic+0x1e4/0x41c kernel/panic.c:183
 __warn+0x1dc/0x200 kernel/panic.c:547
 report_bug+0x211/0x2d0 lib/bug.c:184
 fixup_bug.part.11+0x37/0x80 arch/x86/kernel/traps.c:178
 fixup_bug arch/x86/kernel/traps.c:247 [inline]
 do_error_trap+0x2d7/0x3e0 arch/x86/kernel/traps.c:296
 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:315
 invalid_op+0x22/0x40 arch/x86/entry/entry_64.S:988
RIP: 0010:__queue_work+0xdf4/0x1230 kernel/workqueue.c:1444
RSP: 0018:ffff8801db507538 EFLAGS: 00010006
RAX: ffff8801aeb46080 RBX: ffff8801db530200 RCX: ffffffff81481404
RDX: 0000000000000100 RSI: ffffffff86b42640 RDI: 0000000000000082
RBP: ffff8801db507758 R08: 1ffff1003b6a0de5 R09: 000000000000000c
R10: ffff8801db5073f0 R11: 0000000000000020 R12: 1ffff1003b6a0eb6
R13: ffff8801b1067ae0 R14: 00000000000001f8 R15: dffffc0000000000
 queue_work_on+0x16a/0x1c0 kernel/workqueue.c:1488
 queue_work include/linux/workqueue.h:488 [inline]
 schedule_work include/linux/workqueue.h:546 [inline]
 idletimer_tg_expired+0x44/0x60 net/netfilter/xt_IDLETIMER.c:116
 call_timer_fn+0x228/0x820 kernel/time/timer.c:1326
 expire_timers kernel/time/timer.c:1363 [inline]
 __run_timers+0x7ee/0xb70 kernel/time/timer.c:1666
 run_timer_softirq+0x4c/0x70 kernel/time/timer.c:1692
 __do_softirq+0x2d7/0xb85 kernel/softirq.c:285
 invoke_softirq kernel/softirq.c:365 [inline]
 irq_exit+0x1cc/0x200 kernel/softirq.c:405
 exiting_irq arch/x86/include/asm/apic.h:541 [inline]
 smp_apic_timer_interrupt+0x16b/0x700 arch/x86/kernel/apic/apic.c:1052
 apic_timer_interrupt+0xa9/0xb0 arch/x86/entry/entry_64.S:829
 </IRQ>
RIP: 0010:arch_local_irq_restore arch/x86/include/asm/paravirt.h:777 [inline]
RIP: 0010:__raw_spin_unlock_irqrestore include/linux/spinlock_api_smp.h:160 [inline]
RIP: 0010:_raw_spin_unlock_irqrestore+0x5e/0xba kernel/locking/spinlock.c:184
RSP: 0018:ffff8801c20173c8 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff12
RAX: dffffc0000000000 RBX: 0000000000000282 RCX: 0000000000000006
RDX: 1ffffffff0d592cd RSI: 1ffff10035d68d23 RDI: 0000000000000282
RBP: ffff8801c20173d8 R08: 1ffff10038402e47 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff8820e5c8
R13: ffff8801b1067ad8 R14: ffff8801aea7c268 R15: ffff8801aea7c278
 __debug_object_init+0x235/0x1040 lib/debugobjects.c:378
 debug_object_init+0x17/0x20 lib/debugobjects.c:391
 __init_work+0x2b/0x60 kernel/workqueue.c:506
 idletimer_tg_create net/netfilter/xt_IDLETIMER.c:152 [inline]
 idletimer_tg_checkentry+0x691/0xb00 net/netfilter/xt_IDLETIMER.c:213
 xt_check_target+0x22c/0x7d0 net/netfilter/x_tables.c:850
 check_target net/ipv6/netfilter/ip6_tables.c:533 [inline]
 find_check_entry.isra.7+0x935/0xcf0 net/ipv6/netfilter/ip6_tables.c:575
 translate_table+0xf52/0x1690 net/ipv6/netfilter/ip6_tables.c:744
 do_replace net/ipv6/netfilter/ip6_tables.c:1160 [inline]
 do_ip6t_set_ctl+0x370/0x5f0 net/ipv6/netfilter/ip6_tables.c:1686
 nf_sockopt net/netfilter/nf_sockopt.c:106 [inline]
 nf_setsockopt+0x67/0xc0 net/netfilter/nf_sockopt.c:115
 ipv6_setsockopt+0x10b/0x130 net/ipv6/ipv6_sockglue.c:927
 udpv6_setsockopt+0x45/0x80 net/ipv6/udp.c:1422
 sock_common_setsockopt+0x95/0xd0 net/core/sock.c:2976
 SYSC_setsockopt net/socket.c:1850 [inline]
 SyS_setsockopt+0x189/0x360 net/socket.c:1829
 do_syscall_64+0x282/0x940 arch/x86/entry/common.c:287

---
 net/netfilter/xt_IDLETIMER.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

@@ -147,11 +147,11 @@ static int idletimer_tg_create(struct id
 		    (unsigned long) info->timer);
 	info->timer->refcnt = 1;
 
+	INIT_WORK(&info->timer->work, idletimer_tg_work);
+
 	mod_timer(&info->timer->timer,
 		  msecs_to_jiffies(info->timeout * 1000) + jiffies);
 
-	INIT_WORK(&info->timer->work, idletimer_tg_work);
-
 	return 0;
 
 out_free_attr:

@@ -192,7 +192,10 @@ static int idletimer_tg_checkentry(const
 		pr_debug("timeout value is zero\n");
 		return -EINVAL;
 	}
-
+	if (info->timeout >= INT_MAX / 1000) {
+		pr_debug("timeout value is too big\n");
+		return -EINVAL;
+	}
 	if (info->label[0] == '\0' ||
 	    strnlen(info->label,
 		    MAX_IDLETIMER_LABEL_SIZE) == MAX_IDLETIMER_LABEL_SIZE) {

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

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

From: Florian Westphal <[email protected]>

commit b71812168571fa55e44cdd0254471331b9c4c4c6 upstream.

We need to make sure the offsets are not out of range of the total size.
Also check that they are in ascending order.

The WARN_ON triggered by syzkaller (it sets panic_on_warn) is changed to also bail out, no point in continuing parsing.

Briefly tested with simple ruleset of
-A INPUT --limit 1/s' --log
plus jump to custom chains using 32bit ebtables binary.

---
 net/bridge/netfilter/ebtables.c |   13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

@@ -2021,7 +2021,9 @@ static int ebt_size_mwt(struct compat_eb
 		if (match_kern)
 			match_kern->match_size = ret;
 
-		WARN_ON(type == EBT_COMPAT_TARGET && size_left);
+		if (WARN_ON(type == EBT_COMPAT_TARGET && size_left))
+			return -EINVAL;
+
 		match32 = (struct compat_ebt_entry_mwt *) buf;
 	}
 

@@ -2078,6 +2080,15 @@ static int size_entry_mwt(struct ebt_ent
 	 *
 	 * offsets are relative to beginning of struct ebt_entry (i.e., 0).
 	 */
+	for (i = 0; i < 4 ; ++i) {
+		if (offsets[i] >= *total)
+			return -EINVAL;
+		if (i == 0)
+			continue;
+		if (offsets[i-1] > offsets[i])
+			return -EINVAL;
+	}
+
 	for (i = 0, j = 1 ; j < 4 ; j++, i++) {
 		struct compat_ebt_entry_mwt *match32;
 		unsigned int size;

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

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

From: Florian Westphal <[email protected]>

commit c4585a2823edf4d1326da44d1524ecbfda26bb37 upstream.

ebt_among is special, it has a dynamic match size and is exempt from the central size checks.

Therefore it must check that the size of the match structure provided from userspace is sane by making sure em->match_size is at least the minimum size of the expected structure.

The module has such a check, but its only done after accessing a structure that might be out of bounds.

tested with: ebtables -A INPUT ... \
--among-dst fe:fe:fe:fe:fe:fe
--among-dst fe:fe:fe:fe:fe:fe --among-src fe:fe:fe:fe:ff:f,fe:fe:fe:fe:fe:fb,fe:fe:fe:fe:fc:fd,fe:fe:fe:fe:fe:fd,fe:fe:fe:fe:fe:fe --among-src fe:fe:fe:fe:ff:f,fe:fe:fe:fe:fe:fa,fe:fe:fe:fe:fe:fd,fe:fe:fe:fe:fe:fe,fe:fe:fe:fe:fe:fe

---
 net/bridge/netfilter/ebt_among.c |   21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

@@ -172,18 +172,35 @@ ebt_among_mt(const struct sk_buff *skb,
 	return true;
 }
 
+static bool poolsize_invalid(const struct ebt_mac_wormhash *w)
+{
+	return w && w->poolsize >= (INT_MAX / sizeof(struct ebt_mac_wormhash_tuple));
+}
+
 static int ebt_among_mt_check(const struct xt_mtchk_param *par)
 {
 	const struct ebt_among_info *info = par->matchinfo;
 	const struct ebt_entry_match *em =
 		container_of(par->matchinfo, const struct ebt_entry_match, data);
-	int expected_length = sizeof(struct ebt_among_info);
+	unsigned int expected_length = sizeof(struct ebt_among_info);
 	const struct ebt_mac_wormhash *wh_dst, *wh_src;
 	int err;
 
+	if (expected_length > em->match_size)
+		return -EINVAL;
+
 	wh_dst = ebt_among_wh_dst(info);
-	wh_src = ebt_among_wh_src(info);
+	if (poolsize_invalid(wh_dst))
+		return -EINVAL;
+
 	expected_length += ebt_mac_wormhash_size(wh_dst);
+	if (expected_length > em->match_size)
+		return -EINVAL;
+
+	wh_src = ebt_among_wh_src(info);
+	if (poolsize_invalid(wh_src))
+		return -EINVAL;
+
 	expected_length += ebt_mac_wormhash_size(wh_src);
 
 	if (em->match_size != EBT_ALIGN(expected_length)) {

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

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

From: Florian Westphal <[email protected]>

commit b078556aecd791b0e5cb3a59f4c3a14273b52121 upstream.

l4proto->manip_pkt() can cause reallocation of skb head so pointer to the ipv6 header must be reloaded.

---
 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -99,6 +99,10 @@ static bool nf_nat_ipv6_manip_pkt(struct
 	    !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff,
 				target, maniptype))
 		return false;
+
+	/* must reload, offset might have changed */
+	ipv6h = (void *)skb->data + iphdroff;
+
 manip_addr:
 	if (maniptype == NF_NAT_MANIP_SRC)
 		ipv6h->saddr = target->src.u3.in6;

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

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

From: Florian Westphal <[email protected]>

commit 29e09229d9f26129a39462fae0ddabc4d9533989 upstream.

inet_sk(skb->sk) is illegal in case skb is attached to request socket.

Reported by: Daniel J Blueman <[email protected]>

---
 net/ipv4/netfilter.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

@@ -23,7 +23,8 @@ int ip_route_me_harder(struct net *net,
 	struct rtable *rt;
 	struct flowi4 fl4 = {};
 	__be32 saddr = iph->saddr;
-	__u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
+	const struct sock *sk = skb_to_full_sk(skb);
+	__u8 flags = sk ? inet_sk_flowi_flags(sk) : 0;
 	unsigned int hh_len;
 
 	if (addr_type == RTN_UNSPEC)

@@ -39,7 +40,7 @@ int ip_route_me_harder(struct net *net,
 	fl4.daddr = iph->daddr;
 	fl4.saddr = saddr;
 	fl4.flowi4_tos = RT_TOS(iph->tos);
-	fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
+	fl4.flowi4_oif = sk ? sk->sk_bound_dev_if : 0;
 	fl4.flowi4_mark = skb->mark;
 	fl4.flowi4_flags = flags;
 	rt = ip_route_output_key(net, &fl4);

@@ -58,7 +59,7 @@ int ip_route_me_harder(struct net *net,
 	    xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
 		struct dst_entry *dst = skb_dst(skb);
 		skb_dst_set(skb, NULL);
-		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
+		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), sk, 0);
 		if (IS_ERR(dst))
 			return PTR_ERR(dst);
 		skb_dst_set(skb, dst);

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

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

From: Florian Westphal <[email protected]>

commit f28e15bacedd444608e25421c72eb2cf4527c9ca upstream.

Keeps some noise away from a followup patch.

---
 include/linux/netfilter/x_tables.h |   27 +--------------------------
 net/ipv4/netfilter/arp_tables.c    |    5 +----
 net/ipv4/netfilter/ip_tables.c     |    5 +----
 net/ipv6/netfilter/ip6_tables.c    |    5 +----
 net/netfilter/x_tables.c           |   30 ++++++++++++++++++++++++++++++
 5 files changed, 34 insertions(+), 38 deletions(-)

@@ -369,32 +369,7 @@ static inline unsigned long ifname_compa
 }
 
 
-/* On SMP, ip(6)t_entry->counters.pcnt holds address of the
- * real (percpu) counter.  On !SMP, its just the packet count,
- * so nothing needs to be done there.
- *
- * xt_percpu_counter_alloc returns the address of the percpu
- * counter, or 0 on !SMP. We force an alignment of 16 bytes
- * so that bytes/packets share a common cache line.
- *
- * Hence caller must use IS_ERR_VALUE to check for error, this
- * allows us to return 0 for single core systems without forcing
- * callers to deal with SMP vs. NONSMP issues.
- */
-static inline unsigned long xt_percpu_counter_alloc(void)
-{
-	if (nr_cpu_ids > 1) {
-		void __percpu *res = __alloc_percpu(sizeof(struct xt_counters),
-						    sizeof(struct xt_counters));
-
-		if (res == NULL)
-			return -ENOMEM;
-
-		return (__force unsigned long) res;
-	}
-
-	return 0;
-}
+bool xt_percpu_counter_alloc(struct xt_counters *counters);
 void xt_percpu_counter_free(struct xt_counters *cnt);
 
 static inline struct xt_counters *

@@ -515,13 +515,10 @@ find_check_entry(struct arpt_entry *e, c
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;
-	unsigned long pcnt;
 	int ret;
 
-	pcnt = xt_percpu_counter_alloc();
-	if (IS_ERR_VALUE(pcnt))
+	if (!xt_percpu_counter_alloc(&e->counters))
 		return -ENOMEM;
-	e->counters.pcnt = pcnt;
 
 	t = arpt_get_target(e);
 	target = xt_request_find_target(NFPROTO_ARP, t->u.user.name,

@@ -657,12 +657,9 @@ find_check_entry(struct ipt_entry *e, st
 	unsigned int j;
 	struct xt_mtchk_param mtpar;
 	struct xt_entry_match *ematch;
-	unsigned long pcnt;
 
-	pcnt = xt_percpu_counter_alloc();
-	if (IS_ERR_VALUE(pcnt))
+	if (!xt_percpu_counter_alloc(&e->counters))
 		return -ENOMEM;
-	e->counters.pcnt = pcnt;
 
 	j = 0;
 	mtpar.net	= net;

@@ -670,12 +670,9 @@ find_check_entry(struct ip6t_entry *e, s
 	unsigned int j;
 	struct xt_mtchk_param mtpar;
 	struct xt_entry_match *ematch;
-	unsigned long pcnt;
 
-	pcnt = xt_percpu_counter_alloc();
-	if (IS_ERR_VALUE(pcnt))
+	if (!xt_percpu_counter_alloc(&e->counters))
 		return -ENOMEM;
-	e->counters.pcnt = pcnt;
 
 	j = 0;
 	mtpar.net	= net;

@@ -1592,6 +1592,36 @@ void xt_proto_fini(struct net *net, u_in
 }
 EXPORT_SYMBOL_GPL(xt_proto_fini);
 
+/**
+ * xt_percpu_counter_alloc - allocate x_tables rule counter
+ *
+ * @counter: pointer to counter struct inside the ip(6)/arpt_entry struct
+ *
+ * On SMP, the packet counter [ ip(6)t_entry->counters.pcnt ] will then
+ * contain the address of the real (percpu) counter.
+ *
+ * Rule evaluation needs to use xt_get_this_cpu_counter() helper
+ * to fetch the real percpu counter.
+ *
+ * returns false on error.
+ */
+bool xt_percpu_counter_alloc(struct xt_counters *counter)
+{
+	void __percpu *res;
+
+	if (nr_cpu_ids <= 1)
+		return true;
+
+	res = __alloc_percpu(sizeof(struct xt_counters),
+			     sizeof(struct xt_counters));
+	if (!res)
+		return false;
+
+	counter->pcnt = (__force unsigned long)res;
+	return true;
+}
+EXPORT_SYMBOL_GPL(xt_percpu_counter_alloc);
+
 void xt_percpu_counter_free(struct xt_counters *counters)
 {
 	unsigned long pcnt = counters->pcnt;

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

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

From: Florian Westphal <[email protected]>

commit ae0ac0ed6fcf5af3be0f63eb935f483f44a402d2 upstream.

instead of allocating each xt_counter individually, allocate 4k chunks and then use these for counter allocation requests.

This should speed up rule evaluation by increasing data locality, also speeds up ruleset loading because we reduce calls to the percpu allocator.

As Eric points out we can't use PAGE_SIZE, page_allocator would fail on arches with 64k page size.

---
 include/linux/netfilter/x_tables.h |    7 ++++++-
 net/ipv4/netfilter/arp_tables.c    |    9 ++++++---
 net/ipv4/netfilter/ip_tables.c     |    9 ++++++---
 net/ipv6/netfilter/ip6_tables.c    |    9 ++++++---
 net/netfilter/x_tables.c           |   34 +++++++++++++++++++++++++---------
 5 files changed, 49 insertions(+), 19 deletions(-)

@@ -368,8 +368,13 @@ static inline unsigned long ifname_compa
 	return ret;
 }
 
+struct xt_percpu_counter_alloc_state {
+	unsigned int off;
+	const char __percpu *mem;
+};
 
-bool xt_percpu_counter_alloc(struct xt_counters *counters);
+bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state,
+			     struct xt_counters *counter);
 void xt_percpu_counter_free(struct xt_counters *cnt);
 
 static inline struct xt_counters *

@@ -511,13 +511,14 @@ static inline int check_target(struct ar
 }
 
 static inline int
-find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
+find_check_entry(struct arpt_entry *e, const char *name, unsigned int size,
+		 struct xt_percpu_counter_alloc_state *alloc_state)
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;
 	int ret;
 
-	if (!xt_percpu_counter_alloc(&e->counters))
+	if (!xt_percpu_counter_alloc(alloc_state, &e->counters))
 		return -ENOMEM;
 
 	t = arpt_get_target(e);

@@ -634,6 +635,7 @@ static inline void cleanup_entry(struct
 static int translate_table(struct xt_table_info *newinfo, void *entry0,
 			   const struct arpt_replace *repl)
 {
+	struct xt_percpu_counter_alloc_state alloc_state = { 0 };
 	struct arpt_entry *iter;
 	unsigned int *offsets;
 	unsigned int i;

@@ -707,7 +709,8 @@ static int translate_table(struct xt_tab
 	/* Finally, each sanity check must pass */
 	i = 0;
 	xt_entry_foreach(iter, entry0, newinfo->size) {
-		ret = find_check_entry(iter, repl->name, repl->size);
+		ret = find_check_entry(iter, repl->name, repl->size,
+				       &alloc_state);
 		if (ret != 0)
 			break;
 		++i;

@@ -649,7 +649,8 @@ static int check_target(struct ipt_entry
 
 static int
 find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
-		 unsigned int size)
+		 unsigned int size,
+		 struct xt_percpu_counter_alloc_state *alloc_state)
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;

@@ -658,7 +659,7 @@ find_check_entry(struct ipt_entry *e, st
 	struct xt_mtchk_param mtpar;
 	struct xt_entry_match *ematch;
 
-	if (!xt_percpu_counter_alloc(&e->counters))
+	if (!xt_percpu_counter_alloc(alloc_state, &e->counters))
 		return -ENOMEM;
 
 	j = 0;

@@ -803,6 +804,7 @@ static int
 translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 		const struct ipt_replace *repl)
 {
+	struct xt_percpu_counter_alloc_state alloc_state = { 0 };
 	struct ipt_entry *iter;
 	unsigned int *offsets;
 	unsigned int i;

@@ -872,7 +874,8 @@ translate_table(struct net *net, struct
 	/* Finally, each sanity check must pass */
 	i = 0;
 	xt_entry_foreach(iter, entry0, newinfo->size) {
-		ret = find_check_entry(iter, net, repl->name, repl->size);
+		ret = find_check_entry(iter, net, repl->name, repl->size,
+				       &alloc_state);
 		if (ret != 0)
 			break;
 		++i;

@@ -662,7 +662,8 @@ static int check_target(struct ip6t_entr
 
 static int
 find_check_entry(struct ip6t_entry *e, struct net *net, const char *name,
-		 unsigned int size)
+		 unsigned int size,
+		 struct xt_percpu_counter_alloc_state *alloc_state)
 {
 	struct xt_entry_target *t;
 	struct xt_target *target;

@@ -671,7 +672,7 @@ find_check_entry(struct ip6t_entry *e, s
 	struct xt_mtchk_param mtpar;
 	struct xt_entry_match *ematch;
 
-	if (!xt_percpu_counter_alloc(&e->counters))
+	if (!xt_percpu_counter_alloc(alloc_state, &e->counters))
 		return -ENOMEM;
 
 	j = 0;

@@ -814,6 +815,7 @@ static int
 translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
 		const struct ip6t_replace *repl)
 {
+	struct xt_percpu_counter_alloc_state alloc_state = { 0 };
 	struct ip6t_entry *iter;
 	unsigned int *offsets;
 	unsigned int i;

@@ -883,7 +885,8 @@ translate_table(struct net *net, struct
 	/* Finally, each sanity check must pass */
 	i = 0;
 	xt_entry_foreach(iter, entry0, newinfo->size) {
-		ret = find_check_entry(iter, net, repl->name, repl->size);
+		ret = find_check_entry(iter, net, repl->name, repl->size,
+				       &alloc_state);
 		if (ret != 0)
 			break;
 		++i;

@@ -38,6 +38,8 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Harald Welte <[email protected]>");
 MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module");
 
+#define XT_PCPU_BLOCK_SIZE 4096
+
 struct compat_delta {
 	unsigned int offset; /* offset in kernel */
 	int delta; /* delta in 32bit user land */

@@ -1595,6 +1597,7 @@ EXPORT_SYMBOL_GPL(xt_proto_fini);
 /**
  * xt_percpu_counter_alloc - allocate x_tables rule counter
  *
+ * @state: pointer to xt_percpu allocation state
  * @counter: pointer to counter struct inside the ip(6)/arpt_entry struct
  *
  * On SMP, the packet counter [ ip(6)t_entry->counters.pcnt ] will then

@@ -1603,21 +1606,34 @@ EXPORT_SYMBOL_GPL(xt_proto_fini);
  * Rule evaluation needs to use xt_get_this_cpu_counter() helper
  * to fetch the real percpu counter.
  *
+ * To speed up allocation and improve data locality, a 4kb block is
+ * allocated.
+ *
+ * xt_percpu_counter_alloc_state contains the base address of the
+ * allocated page and the current sub-offset.
+ *
  * returns false on error.
  */
-bool xt_percpu_counter_alloc(struct xt_counters *counter)
+bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state,
+			     struct xt_counters *counter)
 {
-	void __percpu *res;
+	BUILD_BUG_ON(XT_PCPU_BLOCK_SIZE < (sizeof(*counter) * 2));
 
 	if (nr_cpu_ids <= 1)
 		return true;
 
-	res = __alloc_percpu(sizeof(struct xt_counters),
-			     sizeof(struct xt_counters));
-	if (!res)
-		return false;
-
-	counter->pcnt = (__force unsigned long)res;
+	if (!state->mem) {
+		state->mem = __alloc_percpu(XT_PCPU_BLOCK_SIZE,
+					    XT_PCPU_BLOCK_SIZE);
+		if (!state->mem)
+			return false;
+	}
+	counter->pcnt = (__force unsigned long)(state->mem + state->off);
+	state->off += sizeof(*counter);
+	if (state->off > (XT_PCPU_BLOCK_SIZE - sizeof(*counter))) {
+		state->mem = NULL;
+		state->off = 0;
+	}
 	return true;
 }
 EXPORT_SYMBOL_GPL(xt_percpu_counter_alloc);

@@ -1626,7 +1642,7 @@ void xt_percpu_counter_free(struct xt_co
 {
 	unsigned long pcnt = counters->pcnt;
 
-	if (nr_cpu_ids > 1)
+	if (nr_cpu_ids > 1 && (pcnt & (XT_PCPU_BLOCK_SIZE - 1)) == 0)
 		free_percpu((void __percpu *)pcnt);
 }
 EXPORT_SYMBOL_GPL(xt_percpu_counter_free);

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

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

From: Tahsin Erdogan <[email protected]>

commit ec00022030da5761518476096626338bd67df57a upstream.

When an xattr block has a single reference, block is updated inplace and it is reinserted to the cache. Later, a cache lookup is performed to see whether an existing block has the same contents. This cache lookup will most of the time return the just inserted entry so deduplication is not achieved.

Running the following test script will produce two xattr blocks which can be observed in "File ACL: " line of debugfs output:

mke2fs -b 1024 -I 128 -F -O extent /dev/sdb 1G
mount /dev/sdb /mnt/sdb

touch /mnt/sdb/{x,y}

setfattr -n user.1 -v aaa /mnt/sdb/x
setfattr -n user.2 -v bbb /mnt/sdb/x

setfattr -n user.1 -v aaa /mnt/sdb/y
setfattr -n user.2 -v bbb /mnt/sdb/y

debugfs -R 'stat x' /dev/sdb | cat
debugfs -R 'stat y' /dev/sdb | cat

This patch defers the reinsertion to the cache so that we can locate other blocks with the same contents.

---
 fs/ext4/xattr.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -828,8 +828,6 @@ ext4_xattr_block_set(handle_t *handle, s
 				if (!IS_LAST_ENTRY(s->first))
 					ext4_xattr_rehash(header(s->base),
 							  s->here);
-				ext4_xattr_cache_insert(ext4_mb_cache,
-					bs->bh);
 			}
 			unlock_buffer(bs->bh);
 			if (error == -EFSCORRUPTED)

@@ -918,6 +916,7 @@ inserted:
 		} else if (bs->bh && s->base == bs->bh->b_data) {
 			/* We were modifying this block in-place. */
 			ea_bdebug(bs->bh, "keeping this block");
+			ext4_xattr_cache_insert(ext4_mb_cache, bs->bh);
 			new_bh = bs->bh;
 			get_bh(new_bh);
 		} else {

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

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

From: Clay McClure <[email protected]>

commit a51a0c8d213594bc094cb8e54aad0cb6d7f7b9a6 upstream.

Similar to commit 714fb87e8bc0 ("ubi: Fix race condition between ubi device creation and udev"), we should make the volume active before registering it.

---
 drivers/mtd/ubi/vmt.c |   15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

@@ -265,6 +265,12 @@ int ubi_create_volume(struct ubi_device
 			vol->last_eb_bytes = vol->usable_leb_size;
 	}
 
+	/* Make volume "available" before it becomes accessible via sysfs */
+	spin_lock(&ubi->volumes_lock);
+	ubi->volumes[vol_id] = vol;
+	ubi->vol_count += 1;
+	spin_unlock(&ubi->volumes_lock);
+
 	/* Register character device for the volume */
 	cdev_init(&vol->cdev, &ubi_vol_cdev_operations);
 	vol->cdev.owner = THIS_MODULE;

@@ -304,11 +310,6 @@ int ubi_create_volume(struct ubi_device
 	if (err)
 		goto out_sysfs;
 
-	spin_lock(&ubi->volumes_lock);
-	ubi->volumes[vol_id] = vol;
-	ubi->vol_count += 1;
-	spin_unlock(&ubi->volumes_lock);
-
 	ubi_volume_notify(ubi, vol, UBI_VOLUME_ADDED);
 	self_check_volumes(ubi);
 	return err;

@@ -328,6 +329,10 @@ out_sysfs:
 out_cdev:
 	cdev_del(&vol->cdev);
 out_mapping:
+	spin_lock(&ubi->volumes_lock);
+	ubi->volumes[vol_id] = NULL;
+	ubi->vol_count -= 1;
+	spin_unlock(&ubi->volumes_lock);
 	if (do_free)
 		kfree(vol->eba_tbl);
 out_acc:

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

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

From: Quinn Tran <[email protected]>

commit 063b36d6b0ad74c748d536f5cb47bac2f850a0fa upstream.

Current code manually allocate an fcport structure that is not properly initialize. Replace kzalloc with qla2x00_alloc_fcport, so that all fields are initialized. Also set set scan flag to port found

---
 drivers/scsi/qla2xxx/qla_target.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -5502,7 +5502,7 @@ static fc_port_t *qlt_get_port_database(
 	fc_port_t *fcport;
 	int rc;
 
-	fcport = kzalloc(sizeof(*fcport), GFP_KERNEL);
+	fcport = qla2x00_alloc_fcport(vha, GFP_KERNEL);
 	if (!fcport) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf06f,
 		    "qla_target(%d): Allocation of tmp FC port failed",

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

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

From: Trond Myklebust <[email protected]>

commit d9ee65539d3eabd9ade46cca1780e3309ad0f907 upstream.

The start offset needs to be of type loff_t.

Fixed: 5fadeb47dcc5c ("nfs: count DIO good bytes correctly with mirroring")

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

@@ -86,9 +86,9 @@ struct nfs_direct_req {
 	struct nfs_direct_mirror mirrors[NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX];
 	int			mirror_count;
 
+	loff_t			io_start;	/* Start offset for I/O */
 	ssize_t			count,		/* bytes actually processed */
 				bytes_left,	/* bytes left to be sent */
-				io_start,	/* start of IO */
 				error;		/* any reported error */
 	struct completion	completion;	/* wait for i/o completion */
 

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

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

From: Greg Kroah-Hartman <[email protected]>

This reverts commit c86bfc7b7b01c4b98c29a39bd60e61fa8e337ebf which was commit 74402055a2d3ec998a1ded599e86185a27d9bbf4 upstream.

The backport merged incorrectly, so I'm dropping it.

---
 arch/arm/boot/dts/logicpd-torpedo-som.dtsi |    8 --------
 1 file changed, 8 deletions(-)

@@ -90,8 +90,6 @@
 };
 
 &i2c1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&i2c1_pins>;
 	clock-frequency = <2600000>;
 
 	twl: twl@48 {

@@ -148,12 +146,6 @@
 			OMAP3630_CORE2_IOPAD(0x25da, PIN_INPUT_PULLUP | MUX_MODE2)   /* etk_ctl.sdmmc3_cmd */
 		>;
 	};
-	i2c1_pins: pinmux_i2c1_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0)        /* i2c1_scl.i2c1_scl */
-			OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0)        /* i2c1_sda.i2c1_sda */
-		>;
-	};
 };
 
 #include "twl4030.dtsi"

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

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

From: Josh Poimboeuf <[email protected]>

commit eda9cec4c9a12208a6f69fbe68f72a6311d50032 upstream.

There have been some cases where external tooling (e.g., kpatch-build) creates a corrupt relocation which targets the wrong address. This is a silent failure which can corrupt memory in unexpected places.

On x86, the bytes of data being overwritten by relocations are always initialized to zero beforehand. Use that knowledge to add sanity checks to detect such cases before they corrupt memory.

---
 arch/x86/kernel/module.c |   13 +++++++++++++
 1 file changed, 13 insertions(+)

@@ -170,19 +170,27 @@ int apply_relocate_add(Elf64_Shdr *sechd
 		case R_X86_64_NONE:
 			break;
 		case R_X86_64_64:
+			if (*(u64 *)loc != 0)
+				goto invalid_relocation;
 			*(u64 *)loc = val;
 			break;
 		case R_X86_64_32:
+			if (*(u32 *)loc != 0)
+				goto invalid_relocation;
 			*(u32 *)loc = val;
 			if (val != *(u32 *)loc)
 				goto overflow;
 			break;
 		case R_X86_64_32S:
+			if (*(s32 *)loc != 0)
+				goto invalid_relocation;
 			*(s32 *)loc = val;
 			if ((s64)val != *(s32 *)loc)
 				goto overflow;
 			break;
 		case R_X86_64_PC32:
+			if (*(u32 *)loc != 0)
+				goto invalid_relocation;
 			val -= (u64)loc;
 			*(u32 *)loc = val;
 #if 0

@@ -198,6 +206,11 @@ int apply_relocate_add(Elf64_Shdr *sechd
 	}
 	return 0;
 
+invalid_relocation:
+	pr_err("x86/modules: Skipping invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n",
+	       (int)ELF64_R_TYPE(rel[i].r_info), loc, val);
+	return -ENOEXEC;
+
 overflow:
 	pr_err("overflow in relocation type %d val %Lx\n",
 	       (int)ELF64_R_TYPE(rel[i].r_info), val);

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

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

From: H.J. Lu <[email protected]>

commit b21ebf2fb4cde1618915a97cc773e287ff49173e upstream.

On i386, there are 2 types of PLTs, PIC and non-PIC. PIE and shared objects must use PIC PLT. To use PIC PLT, you need to load _GLOBAL_OFFSET_TABLE_ into EBX first. There is no need for that on x86-64 since x86-64 uses PC-relative PLT.

On x86-64, for 32-bit PC-relative branches, we can generate PLT32 relocation, instead of PC32 relocation, which can also be used as a marker for 32-bit PC-relative branches. Linker can always reduce
PLT32 relocation to PC32 if function is defined locally. Local
functions should use PC32 relocation. As far as Linux kernel is concerned, R_X86_64_PLT32 can be treated the same as R_X86_64_PC32 since Linux kernel doesn't use PLT.

R_X86_64_PLT32 for 32-bit PC-relative branches has been enabled in binutils master branch which will become binutils 2.31.

[ hjl is working on having better documentation on this all, but a few
more notes from him:

"PLT32 relocation is used as marker for PC-relative branches. Because
of EBX, it looks odd to generate PLT32 relocation on i386 when EBX doesn't have GOT.

As for symbol resolution, PLT32 and PC32 relocations are almost interchangeable. But when linker sees PLT32 relocation against a protected symbol, it can resolved locally at link-time since it is used on a branch instruction. Linker can't do that for PC32 relocation"

but for the kernel use, the two are basically the same, and this commit gets things building and working with the current binutils
master - Linus ]

---
 arch/x86/kernel/machine_kexec_64.c |    1 +
 arch/x86/kernel/module.c           |    1 +
 arch/x86/tools/relocs.c            |    3 +++
 3 files changed, 5 insertions(+)

@@ -519,6 +519,7 @@ int arch_kexec_apply_relocations_add(con
 				goto overflow;
 			break;
 		case R_X86_64_PC32:
+		case R_X86_64_PLT32:
 			value -= (u64)address;
 			*(u32 *)location = value;
 			break;

@@ -189,6 +189,7 @@ int apply_relocate_add(Elf64_Shdr *sechd
 				goto overflow;
 			break;
 		case R_X86_64_PC32:
+		case R_X86_64_PLT32:
 			if (*(u32 *)loc != 0)
 				goto invalid_relocation;
 			val -= (u64)loc;

@@ -769,9 +769,12 @@ static int do_reloc64(struct section *se
 		break;
 
 	case R_X86_64_PC32:
+	case R_X86_64_PLT32:
 		/*
 		 * PC relative relocations don't need to be adjusted unless
 		 * referencing a percpu symbol.
+		 *
+		 * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32.
 		 */
 		if (is_percpu_sym(sym, symname))
 			add_reloc(&relocs32neg, offset);

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

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

From: Ulrich Hecht <[email protected]>

commit 7842055bfce4bf0170d0f61df8b2add8399697be upstream.

When the TTY buffers fill up to the configured maximum, a system lockup occurs:

[  598.820128] INFO: rcu_preempt detected stalls on CPUs/tasks:
[  598.825796]  0-...!: (1 GPs behind) idle=5a6/2/0 softirq=1974/1974 fqs=1
[  598.832577]  (detected by 3, t=62517 jiffies, g=296, c=295, q=126)
[  598.838755] Task dump for CPU 0:
[  598.841977] swapper/0       R  running task        0     0      0 0x00000022
[  598.849023] Call trace:
[  598.851476]  __switch_to+0x98/0xb0
[  598.854870]            (null)

This can be prevented by doing a dummy read of the RX data register.

This issue affects both HSCIF and SCIF ports. Reported for R-Car H3 ES2.0; reproduced and fixed on H3 ES1.1. Probably affects other R-Car platforms as well.

---
 drivers/tty/serial/sh-sci.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -847,6 +847,8 @@ static void sci_receive_chars(struct uar
 		/* Tell the rest of the system the news. New characters! */
 		tty_flip_buffer_push(tport);
 	} else {
+		/* TTY buffers full; read from RX reg to prevent lockup */
+		serial_port_in(port, SCxRDR);
 		serial_port_in(port, SCxSR); /* dummy read */
 		sci_clear_SCxSR(port, SCxSR_RDxF_CLEAR(port));
 	}

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

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

From: Jonas Danielsson <[email protected]>

commit fd63a8903a2c40425a9811c3371dd4d0f42c0ad3 upstream.

On our at91sam9260 based board the usart0 and usart1 ports report their versions (ATMEL_US_VERSION) as 0x10302. This version is not included in the current checks in the driver.

---
 drivers/tty/serial/atmel_serial.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1783,6 +1783,7 @@ static void atmel_get_ip_name(struct uar
 		switch (version) {
 		case 0x302:
 		case 0x10213:
+		case 0x10302:
 			dev_dbg(port->dev, "This version is usart\n");
 			atmel_port->is_usart = true;
 			break;

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

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

From: Oliver Neukum <[email protected]>

commit 9a513c905bb95bef79d96feb08621c1ec8d8c4bb upstream.

A typo broke the comparison.

---
 drivers/usb/storage/uas.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1052,7 +1052,7 @@ static int uas_post_reset(struct usb_int
 		return 0;
 
 	err = uas_configure_endpoints(devinfo);
-	if (err && err != ENODEV)
+	if (err && err != -ENODEV)
 		shost_printk(KERN_ERR, shost,
 			     "%s: alloc streams error %d after reset",
 			     __func__, err);

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

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

From: Frank Mori Hess <[email protected]>

commit a42ae5905140c324362fe5036ae1dbb16e4d359c upstream.

A rounding error was causing comedi_nsamples_left to return the wrong value when nsamples was not a multiple of the scan length.

---
 drivers/staging/comedi/drivers.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -484,8 +484,7 @@ unsigned int comedi_nsamples_left(struct
 	struct comedi_cmd *cmd = &async->cmd;
 
 	if (cmd->stop_src == TRIG_COUNT) {
-		unsigned int nscans = nsamples / cmd->scan_end_arg;
-		unsigned int scans_left = __comedi_nscans_left(s, nscans);
+		unsigned int scans_left = __comedi_nscans_left(s, cmd->stop_arg);
 		unsigned int scan_pos =
 		    comedi_bytes_to_samples(s, async->scan_progress);
 		unsigned long long samples_left = 0;

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

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

From: Joel Fernandes <[email protected]>

commit cb57469c9573f6018cd1302953dd45d6e05aba7b upstream.

ashmem_mutex create a chain of dependencies like so:

(1)
mmap syscall ->
mmap_sem -> (acquired)
ashmem_mmap
ashmem_mutex (try to acquire)
(block)

(2)
llseek syscall ->
ashmem_llseek ->
ashmem_mutex -> (acquired)
inode_lock ->
inode->i_rwsem (try to acquire)
(block)

(3)
getdents ->
iterate_dir ->
inode_lock ->
inode->i_rwsem (acquired)
copy_to_user ->
mmap_sem (try to acquire)

There is a lock ordering created between mmap_sem and inode->i_rwsem causing a lockdep splat [2] during a syzcaller test, this patch fixes the issue by unlocking the mutex earlier. Functionally that's Ok since we don't need to protect vfs_llseek.

[1] https://patchwork.kernel.org/patch/10185031/
[2] https://lkml.org/lkml/2018/1/10/48

---
 drivers/staging/android/ashmem.c |   15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

@@ -330,24 +330,23 @@ static loff_t ashmem_llseek(struct file
 	mutex_lock(&ashmem_mutex);
 
 	if (asma->size == 0) {
-		ret = -EINVAL;
-		goto out;
+		mutex_unlock(&ashmem_mutex);
+		return -EINVAL;
 	}
 
 	if (!asma->file) {
-		ret = -EBADF;
-		goto out;
+		mutex_unlock(&ashmem_mutex);
+		return -EBADF;
 	}
 
+	mutex_unlock(&ashmem_mutex);
+
 	ret = vfs_llseek(asma->file, offset, origin);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	/** Copy f_pos from backing file, since f_ops->llseek() sets it */
 	file->f_pos = asma->file->f_pos;
-
-out:
-	mutex_unlock(&ashmem_mutex);
 	return ret;
 }
 

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

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

From: Teijo Kinnunen <[email protected]>

commit 5126a504b63d82785eaece3a9c30c660b313785a upstream.

This USB-SATA controller seems to be similar with JMicron bridge 152d:2566 already on the list. Adding it here fixes "Invalid field in cdb" errors.

---
 drivers/usb/storage/unusual_devs.h |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -2142,6 +2142,13 @@ UNUSUAL_DEV(  0x22b8, 0x3010, 0x0001, 0x
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_FIX_CAPACITY | US_FL_IGNORE_RESIDUE ),
 
+/* Reported by Teijo Kinnunen <[email protected]> */
+UNUSUAL_DEV(  0x152d, 0x2567, 0x0117, 0x0117,
+		"JMicron",
+		"USB to ATA/ATAPI Bridge",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_BROKEN_FUA ),
+
 /* Reported-by George Cherian <[email protected]> */
 UNUSUAL_DEV(0x152d, 0x9561, 0x0000, 0x9999,
 		"JMicron",

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

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

From: Julia Lawall <[email protected]>

commit 46c236dc7d1212d7417e6fb0317f91c44c719322 upstream.

The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@@
expression e1,e2;
statement S1,S2;
@@

+e1 = e2;
if (IS_ERR(

    e1

- = e2
)) S1 else S2
// </smpl>

---
 drivers/usb/mon/mon_text.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

@@ -386,7 +386,8 @@ static ssize_t mon_text_read_t(struct fi
 	struct mon_event_text *ep;
 	struct mon_text_ptr ptr;
 
-	if (IS_ERR(ep = mon_text_read_wait(rp, file)))
+	ep = mon_text_read_wait(rp, file);
+	if (IS_ERR(ep))
 		return PTR_ERR(ep);
 	mutex_lock(&rp->printf_lock);
 	ptr.cnt = 0;

@@ -413,7 +414,8 @@ static ssize_t mon_text_read_u(struct fi
 	struct mon_event_text *ep;
 	struct mon_text_ptr ptr;
 
-	if (IS_ERR(ep = mon_text_read_wait(rp, file)))
+	ep = mon_text_read_wait(rp, file);
+	if (IS_ERR(ep))
 		return PTR_ERR(ep);
 	mutex_lock(&rp->printf_lock);
 	ptr.cnt = 0;

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

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

From: Pete Zaitcev <[email protected]>

commit a5f596830e27e15f7a0ecd6be55e433d776986d8 upstream.

This change fixes buffer overflows and silent data corruption with the usbmon device driver text file read operations.

---
 drivers/usb/mon/mon_text.c |  124 +++++++++++++++++++++++++++------------------
 1 file changed, 77 insertions(+), 47 deletions(-)

@@ -82,6 +82,8 @@ struct mon_reader_text {
 
 	wait_queue_head_t wait;
 	int printf_size;
+	size_t printf_offset;
+	size_t printf_togo;
 	char *printf_buf;
 	struct mutex printf_lock;
 

@@ -373,75 +375,103 @@ err_alloc:
 	return rc;
 }
 
-/*
- * For simplicity, we read one record in one system call and throw out
- * what does not fit. This means that the following does not work:
- *   dd if=/dbg/usbmon/0t bs=10
- * Also, we do not allow seeks and do not bother advancing the offset.
- */
+static ssize_t mon_text_copy_to_user(struct mon_reader_text *rp,
+    char __user * const buf, const size_t nbytes)
+{
+	const size_t togo = min(nbytes, rp->printf_togo);
+
+	if (copy_to_user(buf, &rp->printf_buf[rp->printf_offset], togo))
+		return -EFAULT;
+	rp->printf_togo -= togo;
+	rp->printf_offset += togo;
+	return togo;
+}
+
+/* ppos is not advanced since the llseek operation is not permitted. */
 static ssize_t mon_text_read_t(struct file *file, char __user *buf,
-				size_t nbytes, loff_t *ppos)
+    size_t nbytes, loff_t *ppos)
 {
 	struct mon_reader_text *rp = file->private_data;
 	struct mon_event_text *ep;
 	struct mon_text_ptr ptr;
+	ssize_t ret;
 
-	ep = mon_text_read_wait(rp, file);
-	if (IS_ERR(ep))
-		return PTR_ERR(ep);
 	mutex_lock(&rp->printf_lock);
-	ptr.cnt = 0;
-	ptr.pbuf = rp->printf_buf;
-	ptr.limit = rp->printf_size;
-
-	mon_text_read_head_t(rp, &ptr, ep);
-	mon_text_read_statset(rp, &ptr, ep);
-	ptr.cnt += snprintf(ptr.pbuf + ptr.cnt, ptr.limit - ptr.cnt,
-	    " %d", ep->length);
-	mon_text_read_data(rp, &ptr, ep);
 
-	if (copy_to_user(buf, rp->printf_buf, ptr.cnt))
-		ptr.cnt = -EFAULT;
+	if (rp->printf_togo == 0) {
+
+		ep = mon_text_read_wait(rp, file);
+		if (IS_ERR(ep)) {
+			mutex_unlock(&rp->printf_lock);
+			return PTR_ERR(ep);
+		}
+		ptr.cnt = 0;
+		ptr.pbuf = rp->printf_buf;
+		ptr.limit = rp->printf_size;
+
+		mon_text_read_head_t(rp, &ptr, ep);
+		mon_text_read_statset(rp, &ptr, ep);
+		ptr.cnt += snprintf(ptr.pbuf + ptr.cnt, ptr.limit - ptr.cnt,
+		    " %d", ep->length);
+		mon_text_read_data(rp, &ptr, ep);
+
+		rp->printf_togo = ptr.cnt;
+		rp->printf_offset = 0;
+
+		kmem_cache_free(rp->e_slab, ep);
+	}
+
+	ret = mon_text_copy_to_user(rp, buf, nbytes);
 	mutex_unlock(&rp->printf_lock);
-	kmem_cache_free(rp->e_slab, ep);
-	return ptr.cnt;
+	return ret;
 }
 
+/* ppos is not advanced since the llseek operation is not permitted. */
 static ssize_t mon_text_read_u(struct file *file, char __user *buf,
-				size_t nbytes, loff_t *ppos)
+    size_t nbytes, loff_t *ppos)
 {
 	struct mon_reader_text *rp = file->private_data;
 	struct mon_event_text *ep;
 	struct mon_text_ptr ptr;
+	ssize_t ret;
 
-	ep = mon_text_read_wait(rp, file);
-	if (IS_ERR(ep))
-		return PTR_ERR(ep);
 	mutex_lock(&rp->printf_lock);
-	ptr.cnt = 0;
-	ptr.pbuf = rp->printf_buf;
-	ptr.limit = rp->printf_size;
 
-	mon_text_read_head_u(rp, &ptr, ep);
-	if (ep->type == 'E') {
-		mon_text_read_statset(rp, &ptr, ep);
-	} else if (ep->xfertype == USB_ENDPOINT_XFER_ISOC) {
-		mon_text_read_isostat(rp, &ptr, ep);
-		mon_text_read_isodesc(rp, &ptr, ep);
-	} else if (ep->xfertype == USB_ENDPOINT_XFER_INT) {
-		mon_text_read_intstat(rp, &ptr, ep);
-	} else {
-		mon_text_read_statset(rp, &ptr, ep);
+	if (rp->printf_togo == 0) {
+
+		ep = mon_text_read_wait(rp, file);
+		if (IS_ERR(ep)) {
+			mutex_unlock(&rp->printf_lock);
+			return PTR_ERR(ep);
+		}
+		ptr.cnt = 0;
+		ptr.pbuf = rp->printf_buf;
+		ptr.limit = rp->printf_size;
+
+		mon_text_read_head_u(rp, &ptr, ep);
+		if (ep->type == 'E') {
+			mon_text_read_statset(rp, &ptr, ep);
+		} else if (ep->xfertype == USB_ENDPOINT_XFER_ISOC) {
+			mon_text_read_isostat(rp, &ptr, ep);
+			mon_text_read_isodesc(rp, &ptr, ep);
+		} else if (ep->xfertype == USB_ENDPOINT_XFER_INT) {
+			mon_text_read_intstat(rp, &ptr, ep);
+		} else {
+			mon_text_read_statset(rp, &ptr, ep);
+		}
+		ptr.cnt += snprintf(ptr.pbuf + ptr.cnt, ptr.limit - ptr.cnt,
+		    " %d", ep->length);
+		mon_text_read_data(rp, &ptr, ep);
+
+		rp->printf_togo = ptr.cnt;
+		rp->printf_offset = 0;
+
+		kmem_cache_free(rp->e_slab, ep);
 	}
-	ptr.cnt += snprintf(ptr.pbuf + ptr.cnt, ptr.limit - ptr.cnt,
-	    " %d", ep->length);
-	mon_text_read_data(rp, &ptr, ep);
 
-	if (copy_to_user(buf, rp->printf_buf, ptr.cnt))
-		ptr.cnt = -EFAULT;
+	ret = mon_text_copy_to_user(rp, buf, nbytes);
 	mutex_unlock(&rp->printf_lock);
-	kmem_cache_free(rp->e_slab, ep);
-	return ptr.cnt;
+	return ret;
 }
 
 static struct mon_event_text *mon_text_read_wait(struct mon_reader_text *rp,

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

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

From: Xinyong <[email protected]>

commit 1a087f032111a88e826877449dfb93ceb22b78b9 upstream.

When I debug a kernel crash issue in funcitonfs, found ffs_data.ref overflowed, While functionfs is unmounting, ffs_data is put twice.

Commit 43938613c6fd ("drivers, usb: convert ffs_data.ref from atomic_t to refcount_t") can avoid refcount overflow, but that is risk some situations. So no need put ffs data in ffs_fs_kill_sb, already put in ffs_data_closed.

The issue can be reproduced in Mediatek mt6763 SoC, ffs for ADB device. KASAN enabled configuration reports use-after-free errro.

BUG: KASAN: use-after-free in refcount_dec_and_test+0x14/0xe0 at addr ffffffc0579386a0
Read of size 4 by task umount/4650
====================================================

BUG kmalloc-512 (Tainted: P W O ): kasan: bad access detected
-----------------------------------------------------------------------------

INFO: Allocated in ffs_fs_mount+0x194/0x844 age=22856 cpu=2 pid=566

    alloc_debug_processing+0x1ac/0x1e8
    ___slab_alloc.constprop.63+0x640/0x648
    __slab_alloc.isra.57.constprop.62+0x24/0x34
    kmem_cache_alloc_trace+0x1a8/0x2bc
    ffs_fs_mount+0x194/0x844
    mount_fs+0x6c/0x1d0
    vfs_kern_mount+0x50/0x1b4
    do_mount+0x258/0x1034
INFO: Freed in ffs_data_put+0x25c/0x320 age=0 cpu=3 pid=4650
    free_debug_processing+0x22c/0x434
    __slab_free+0x2d8/0x3a0
    kfree+0x254/0x264
    ffs_data_put+0x25c/0x320
    ffs_data_closed+0x124/0x15c
    ffs_fs_kill_sb+0xb8/0x110
    deactivate_locked_super+0x6c/0x98
    deactivate_super+0xb0/0xbc
INFO: Object 0xffffffc057938600 @offset=1536 fp=0x          (null)
......
Call trace:
[<ffffff900808cf5c>] dump_backtrace+0x0/0x250
[<ffffff900808d3a0>] show_stack+0x14/0x1c
[<ffffff90084a8c04>] dump_stack+0xa0/0xc8
[<ffffff900826c2b4>] print_trailer+0x158/0x260
[<ffffff900826d9d8>] object_err+0x3c/0x40
[<ffffff90082745f0>] kasan_report_error+0x2a8/0x754
[<ffffff9008274f84>] kasan_report+0x5c/0x60
[<ffffff9008273208>] __asan_load4+0x70/0x88
[<ffffff90084cd81c>] refcount_dec_and_test+0x14/0xe0
[<ffffff9008d98f9c>] ffs_data_put+0x80/0x320
[<ffffff9008d9d904>] ffs_fs_kill_sb+0xc8/0x110
[<ffffff90082852a0>] deactivate_locked_super+0x6c/0x98
[<ffffff900828537c>] deactivate_super+0xb0/0xbc
[<ffffff90082af0c0>] cleanup_mnt+0x64/0xec
[<ffffff90082af1b0>] __cleanup_mnt+0x10/0x18
[<ffffff90080d9e68>] task_work_run+0xcc/0x124
[<ffffff900808c8c0>] do_notify_resume+0x60/0x70
[<ffffff90080866e4>] work_pending+0x10/0x14

---
 drivers/usb/gadget/function/f_fs.c |    1 -
 1 file changed, 1 deletion(-)

@@ -1333,7 +1333,6 @@ ffs_fs_kill_sb(struct super_block *sb)
 	if (sb->s_fs_info) {
 		ffs_release_dev(sb->s_fs_info);
 		ffs_data_closed(sb->s_fs_info);
-		ffs_data_put(sb->s_fs_info);
 	}
 }
 

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

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

From: Nikola Ciprich <[email protected]>

commit 9f2068f35729948bde84d87a40d135015911345d upstream.

Add PCI ids for two variants of Brainboxes UC-260 quad port PCI serial cards.

---
 drivers/tty/serial/8250/8250_pci.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

@@ -5300,6 +5300,17 @@ static struct pci_device_id serial_pci_t
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,    /* 135a.0dc0 */
 		pbn_b2_4_115200 },
 	/*
+	 * BrainBoxes UC-260
+	 */
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0D21,
+		PCI_ANY_ID, PCI_ANY_ID,
+		PCI_CLASS_COMMUNICATION_MULTISERIAL << 8, 0xffff00,
+		pbn_b2_4_115200 },
+	{	PCI_VENDOR_ID_INTASHIELD, 0x0E34,
+		PCI_ANY_ID, PCI_ANY_ID,
+		 PCI_CLASS_COMMUNICATION_MULTISERIAL << 8, 0xffff00,
+		pbn_b2_4_115200 },
+	/*
 	 * Perle PCI-RAS cards
 	 */
 	{       PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030,

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

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

From: Greg Kroah-Hartman <[email protected]>

So here's a fix for this problem.

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

@@ -1369,7 +1369,7 @@ static struct sctp_chunk *_sctp_make_chu
 	struct sock *sk;
 	int chunklen;
 
-	chunklen = sizeof(*chunk_hdr) + paylen;
+	chunklen = WORD_ROUND(sizeof(*chunk_hdr) + paylen);
 	if (chunklen > SCTP_MAX_CHUNK_LEN)
 		goto nodata;
 

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

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

From: Leon Romanovsky <[email protected]>

commit a5880b84430316e3e1c1f5d23aa32ec6000cc717 upstream.

The QP state is limited and declared in enum ib_qp_state, but ucma user was able to supply any possible (u32) value.

---
 drivers/infiniband/core/ucma.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -1138,6 +1138,9 @@ static ssize_t ucma_init_qp_attr(struct
 	if (copy_from_user(&cmd, inbuf, sizeof(cmd)))
 		return -EFAULT;
 
+	if (cmd.qp_state > IB_QPS_ERR)
+		return -EINVAL;
+
 	ctx = ucma_get_ctx(file, cmd.id);
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);

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

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

From: Leon Romanovsky <[email protected]>

commit 28e9091e3119933c38933cb8fc48d5618eb784c8 upstream.

The user can provide very large cqe_size which will cause to integer overflow as it can be seen in the following UBSAN warning:

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

UBSAN: Undefined behaviour in drivers/infiniband/hw/mlx5/cq.c:1192:53
signed integer overflow:
64870 * 65536 cannot be represented in type 'int'
CPU: 0 PID: 267 Comm: syzkaller605279 Not tainted 4.15.0+ #90 Hardware
name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
rel-1.7.5-0-ge51488c-20140602_164612-nilsson.home.kraxel.org 04/01/2014
Call Trace:
 dump_stack+0xde/0x164
 ? dma_virt_map_sg+0x22c/0x22c
 ubsan_epilogue+0xe/0x81
 handle_overflow+0x1f3/0x251
 ? __ubsan_handle_negate_overflow+0x19b/0x19b
 ? lock_acquire+0x440/0x440
 mlx5_ib_resize_cq+0x17e7/0x1e40
 ? cyc2ns_read_end+0x10/0x10
 ? native_read_msr_safe+0x6c/0x9b
 ? cyc2ns_read_end+0x10/0x10
 ? mlx5_ib_modify_cq+0x220/0x220
 ? sched_clock_cpu+0x18/0x200
 ? lookup_get_idr_uobject+0x200/0x200
 ? rdma_lookup_get_uobject+0x145/0x2f0
 ib_uverbs_resize_cq+0x207/0x3e0
 ? ib_uverbs_ex_create_cq+0x250/0x250
 ib_uverbs_write+0x7f9/0xef0
 ? cyc2ns_read_end+0x10/0x10
 ? print_irqtrace_events+0x280/0x280
 ? ib_uverbs_ex_create_cq+0x250/0x250
 ? uverbs_devnode+0x110/0x110
 ? sched_clock_cpu+0x18/0x200
 ? do_raw_spin_trylock+0x100/0x100
 ? __lru_cache_add+0x16e/0x290
 __vfs_write+0x10d/0x700
 ? uverbs_devnode+0x110/0x110
 ? kernel_read+0x170/0x170
 ? sched_clock_cpu+0x18/0x200
 ? security_file_permission+0x93/0x260
 vfs_write+0x1b0/0x550
 SyS_write+0xc7/0x1a0
 ? SyS_read+0x1a0/0x1a0
 ? trace_hardirqs_on_thunk+0x1a/0x1c
 entry_SYSCALL_64_fastpath+0x1e/0x8b
RIP: 0033:0x433549
RSP: 002b:00007ffe63bd1ea8 EFLAGS: 00000217
=======================================================================

---
 drivers/infiniband/hw/mlx5/cq.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

@@ -972,7 +972,12 @@ static int resize_user(struct mlx5_ib_de
 	if (ucmd.reserved0 || ucmd.reserved1)
 		return -EINVAL;
 
-	umem = ib_umem_get(context, ucmd.buf_addr, entries * ucmd.cqe_size,
+	/* check multiplication overflow */
+	if (ucmd.cqe_size && SIZE_MAX / ucmd.cqe_size <= entries - 1)
+		return -EINVAL;
+
+	umem = ib_umem_get(context, ucmd.buf_addr,
+			   (size_t)ucmd.cqe_size * entries,
 			   IB_ACCESS_LOCAL_WRITE, 1);
 	if (IS_ERR(umem)) {
 		err = PTR_ERR(umem);

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

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

From: [email protected] <[email protected]>

commit 1514839b366417934e2f1328edb50ed1e8a719f5 upstream.

This patch fixes NULL pointer crash due to active timer running for abort IOCB.

encountered a corrupted entry on the timer list.

#9 [ffff95e1f6f0fd40] page_fault at ffffffff914fe8f8

    [exception RIP: get_next_timer_interrupt+440]
    RIP: ffffffff90ea3088  RSP: ffff95e1f6f0fdf0  RFLAGS: 00010013
    RAX: ffff95e1f6451028  RBX: 000218e2389e5f40  RCX: 00000001232ad600
    RDX: 0000000000000001  RSI: ffff95e1f6f0fdf0  RDI: 0000000001232ad6
    RBP: ffff95e1f6f0fe40   R8: ffff95e1f6451188   R9: 0000000000000001
    R10: 0000000000000016  R11: 0000000000000016  R12: 00000001232ad5f6
    R13: ffff95e1f6450000  R14: ffff95e1f6f0fdf8  R15: ffff95e1f6f0fe10
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018

Looking at the assembly of get_next_timer_interrupt(), address came from %r8 (ffff95e1f6451188) which is pointing to list_head with single entry at ffff95e5ff621178.

 0xffffffff90ea307a <get_next_timer_interrupt+426>:      mov    (%r8),%rdx
 0xffffffff90ea307d <get_next_timer_interrupt+429>:      cmp    %r8,%rdx
 0xffffffff90ea3080 <get_next_timer_interrupt+432>:      je     0xffffffff90ea30a7 <get_next_timer_interrupt+471>
 0xffffffff90ea3082 <get_next_timer_interrupt+434>:      nopw   0x0(%rax,%rax,1)
 0xffffffff90ea3088 <get_next_timer_interrupt+440>:      testb  $0x1,0x18(%rdx)

crash> rd ffff95e1f6451188 10

 ffff95e1f6451188:  ffff95e5ff621178 ffff95e5ff621178   x.b.....x.b.....
 ffff95e1f6451198:  ffff95e1f6451198 ffff95e1f6451198   ..E.......E.....
 ffff95e1f64511a8:  ffff95e1f64511a8 ffff95e1f64511a8   ..E.......E.....
 ffff95e1f64511b8:  ffff95e77cf509a0 ffff95e77cf509a0   ...|.......|....
 ffff95e1f64511c8:  ffff95e1f64511c8 ffff95e1f64511c8   ..E.......E.....

crash> rd ffff95e5ff621178 10

 ffff95e5ff621178:  0000000000000001 ffff95e15936aa00   ..........6Y....
 ffff95e5ff621188:  0000000000000000 00000000ffffffff   ................
 ffff95e5ff621198:  00000000000000a0 0000000000000010   ................
 ffff95e5ff6211a8:  ffff95e5ff621198 000000000000000c   ..b.............
 ffff95e5ff6211b8:  00000f5800000000 ffff95e751f8d720   ....X... ..Q....

ffff95e5ff621178 belongs to freed mempool object at ffff95e5ff621080.

CACHE NAME OBJSIZE ALLOCATED TOTAL SLABS SSIZE
ffff95dc7fd74d00 mnt_cache 384 19785 24948 594 16k
SLAB MEMORY NODE TOTAL ALLOCATED FREE
ffffdc5dabfd8800 ffff95e5ff620000 1 42 29 13
FREE / [ALLOCATED]

    ffff95e5ff621080  (cpu 6 cache)

Examining the contents of that memory reveals a pointer to a constant string in the driver, "abort\0", which is set by qla24xx_async_abort_cmd().

crash> rd ffffffffc059277c 20

 ffffffffc059277c:  6e490074726f6261 0074707572726574   abort.Interrupt.
 ffffffffc059278c:  00676e696c6c6f50 6920726576697244   Polling.Driver i
 ffffffffc059279c:  646f6d207325206e 6974736554000a65   n %s mode..Testi
 ffffffffc05927ac:  636976656420676e 786c252074612065   ng device at %lx
 ffffffffc05927bc:  6b63656843000a2e 646f727020676e69   ...Checking prod
 ffffffffc05927cc:  6f20444920746375 0a2e706968632066   uct ID of chip..
 ffffffffc05927dc:  5120646e756f4600 204130303232414c   .Found QLA2200A
 ffffffffc05927ec:  43000a2e70696843 20676e696b636568   Chip...Checking
 ffffffffc05927fc:  65786f626c69616d 6c636e69000a2e73   mailboxes...incl
 ffffffffc059280c:  756e696c2f656475 616d2d616d642f78   ude/linux/dma-ma

crash> struct -ox srb_iocb

 struct srb_iocb {
           union {
               struct {...} logio;
               struct {...} els_logo;
               struct {...} tmf;
               struct {...} fxiocb;
               struct {...} abt;
               struct ct_arg ctarg;
               struct {...} mbx;
               struct {...} nack;
    [0x0 ] } u;
    [0xb8] struct timer_list timer;
    [0x108] void (*timeout)(void *);

}
SIZE: 0x110

crash> ! bc
ibase=16
obase=10
B8+40
F8

The object is a srb_t, and at offset 0xf8 within that structure (i.e. ffff95e5ff621080 + f8 -> ffff95e5ff621178) is a struct timer_list.

---
 drivers/scsi/qla2xxx/qla_init.c |    1 +
 1 file changed, 1 insertion(+)

@@ -365,6 +365,7 @@ qla24xx_abort_sp_done(void *data, void *
 	srb_t *sp = (srb_t *)ptr;
 	struct srb_iocb *abt = &sp->u.iocb_cmd;
 
+	del_timer(&sp->u.iocb_cmd.timer);
 	complete(&abt->u.abt.comp);
 }
 

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

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

From: Lukas Wunner <[email protected]>

commit 25c058ccaf2ebbc3e250ec1e199e161f91fe27d4 upstream.

Introduce a helper to determine if the current task is an output poll worker.

This allows us to fix a long-standing deadlock in several DRM drivers wherein the ->runtime_suspend callback waits for the output poll worker to finish and the worker in turn calls a ->detect callback which waits for runtime suspend to finish. The ->detect callback is invoked from multiple call sites and waiting for runtime suspend to finish is the correct thing to do except if it's executing in the context of the worker.

v2: Expand kerneldoc to specifically mention deadlock between
output poll worker and autosuspend worker as use case. (Lyude)

---
 drivers/gpu/drm/drm_probe_helper.c |   20 ++++++++++++++++++++
 include/drm/drm_crtc_helper.h      |    1 +
 2 files changed, 21 insertions(+)

@@ -412,6 +412,26 @@ out:
 }
 
 /**
+ * drm_kms_helper_is_poll_worker - is %current task an output poll worker?
+ *
+ * Determine if %current task is an output poll worker.  This can be used
+ * to select distinct code paths for output polling versus other contexts.
+ *
+ * One use case is to avoid a deadlock between the output poll worker and
+ * the autosuspend worker wherein the latter waits for polling to finish
+ * upon calling drm_kms_helper_poll_disable(), while the former waits for
+ * runtime suspend to finish upon calling pm_runtime_get_sync() in a
+ * connector ->detect hook.
+ */
+bool drm_kms_helper_is_poll_worker(void)
+{
+	struct work_struct *work = current_work();
+
+	return work && work->func == output_poll_execute;
+}
+EXPORT_SYMBOL(drm_kms_helper_is_poll_worker);
+
+/**
  * drm_kms_helper_poll_disable - disable output polling
  * @dev: drm_device
  *

@@ -241,5 +241,6 @@ extern void drm_kms_helper_hotplug_event
 extern void drm_kms_helper_poll_disable(struct drm_device *dev);
 extern void drm_kms_helper_poll_enable(struct drm_device *dev);
 extern void drm_kms_helper_poll_enable_locked(struct drm_device *dev);
+extern bool drm_kms_helper_is_poll_worker(void);
 
 #endif

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

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

From: Lukas Wunner <[email protected]>

commit d61a5c1063515e855bedb1b81e20e50b0ac3541e upstream.

nouveau's ->runtime_suspend hook calls drm_kms_helper_poll_disable(), which waits for the output poll worker to finish if it's running.

The output poll worker meanwhile calls pm_runtime_get_sync() in nouveau_connector_detect() which waits for the ongoing suspend to finish, causing a deadlock.

Fix by not acquiring a runtime PM ref if nouveau_connector_detect() is called in the output poll worker's context. This is safe because the poll worker is only enabled while runtime active and we know that ->runtime_suspend waits for it to finish.

Other contexts calling nouveau_connector_detect() do require a runtime PM ref, these comprise:

status_store() drm sysfs interface
->fill_modes drm callback
drm_fb_helper_probe_connector_modes()
drm_mode_getconnector()
nouveau_connector_hotplug()
nouveau_display_hpd_work()
nv17_tv_set_property()

Stack trace for posterity:

  INFO: task kworker/0:1:58 blocked for more than 120 seconds.
  Workqueue: events output_poll_execute [drm_kms_helper]
  Call Trace:
   schedule+0x28/0x80
   rpm_resume+0x107/0x6e0
   __pm_runtime_resume+0x47/0x70
   nouveau_connector_detect+0x7e/0x4a0 [nouveau]
   nouveau_connector_detect_lvds+0x132/0x180 [nouveau]
   drm_helper_probe_detect_ctx+0x85/0xd0 [drm_kms_helper]
   output_poll_execute+0x11e/0x1c0 [drm_kms_helper]
   process_one_work+0x184/0x380
   worker_thread+0x2e/0x390

  INFO: task kworker/0:2:252 blocked for more than 120 seconds.
  Workqueue: pm pm_runtime_work
  Call Trace:
   schedule+0x28/0x80
   schedule_timeout+0x1e3/0x370
   wait_for_completion+0x123/0x190
   flush_work+0x142/0x1c0
   nouveau_pmops_runtime_suspend+0x7e/0xd0 [nouveau]
   pci_pm_runtime_suspend+0x5c/0x180
   vga_switcheroo_runtime_suspend+0x1e/0xa0
   __rpm_callback+0xc1/0x200
   rpm_callback+0x1f/0x70
   rpm_suspend+0x13c/0x640
   pm_runtime_work+0x6e/0x90
   process_one_work+0x184/0x380
   worker_thread+0x2e/0x390

Bugzilla: https://bugs.archlinux.org/task/53497
Bugzilla: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=870523
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=70388#c33

---
 drivers/gpu/drm/nouveau/nouveau_connector.c |   18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

@@ -253,9 +253,15 @@ nouveau_connector_detect(struct drm_conn
 		nv_connector->edid = NULL;
 	}
 
-	ret = pm_runtime_get_sync(connector->dev->dev);
-	if (ret < 0 && ret != -EACCES)
-		return conn_status;
+	/* Outputs are only polled while runtime active, so acquiring a
+	 * runtime PM ref here is unnecessary (and would deadlock upon
+	 * runtime suspend because it waits for polling to finish).
+	 */
+	if (!drm_kms_helper_is_poll_worker()) {
+		ret = pm_runtime_get_sync(connector->dev->dev);
+		if (ret < 0 && ret != -EACCES)
+			return conn_status;
+	}
 
 	nv_encoder = nouveau_connector_ddc_detect(connector);
 	if (nv_encoder && (i2c = nv_encoder->i2c) != NULL) {

@@ -323,8 +329,10 @@ detect_analog:
 
  out:
 
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return conn_status;
 }

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

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

From: Lukas Wunner <[email protected]>

commit 15734feff2bdac24aa3266c437cffa42851990e3 upstream.

radeon's ->runtime_suspend hook calls drm_kms_helper_poll_disable(), which waits for the output poll worker to finish if it's running.

The output poll worker meanwhile calls pm_runtime_get_sync() in radeon's ->detect hooks, which waits for the ongoing suspend to finish, causing a deadlock.

Fix by not acquiring a runtime PM ref if the ->detect hooks are called in the output poll worker's context. This is safe because the poll worker is only enabled while runtime active and we know that ->runtime_suspend waits for it to finish.

Stack trace for posterity:

  INFO: task kworker/0:3:31847 blocked for more than 120 seconds
  Workqueue: events output_poll_execute [drm_kms_helper]
  Call Trace:
   schedule+0x3c/0x90
   rpm_resume+0x1e2/0x690
   __pm_runtime_resume+0x3f/0x60
   radeon_lvds_detect+0x39/0xf0 [radeon]
   output_poll_execute+0xda/0x1e0 [drm_kms_helper]
   process_one_work+0x14b/0x440
   worker_thread+0x48/0x4a0

  INFO: task kworker/2:0:10493 blocked for more than 120 seconds.
  Workqueue: pm pm_runtime_work
  Call Trace:
   schedule+0x3c/0x90
   schedule_timeout+0x1b3/0x240
   wait_for_common+0xc2/0x180
   wait_for_completion+0x1d/0x20
   flush_work+0xfc/0x1a0
   __cancel_work_timer+0xa5/0x1d0
   cancel_delayed_work_sync+0x13/0x20
   drm_kms_helper_poll_disable+0x1f/0x30 [drm_kms_helper]
   radeon_pmops_runtime_suspend+0x3d/0xa0 [radeon]
   pci_pm_runtime_suspend+0x61/0x1a0
   vga_switcheroo_runtime_suspend+0x21/0x70
   __rpm_callback+0x32/0x70
   rpm_callback+0x24/0x80
   rpm_suspend+0x12b/0x640
   pm_runtime_work+0x6f/0xb0
   process_one_work+0x14b/0x440
   worker_thread+0x48/0x4a0

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94147

---
 drivers/gpu/drm/radeon/radeon_connectors.c |   74 +++++++++++++++++++----------
 1 file changed, 49 insertions(+), 25 deletions(-)

@@ -891,9 +891,11 @@ radeon_lvds_detect(struct drm_connector
 	enum drm_connector_status ret = connector_status_disconnected;
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (encoder) {
 		struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);

@@ -916,8 +918,12 @@ radeon_lvds_detect(struct drm_connector
 	/* check acpi lid status ??? */
 
 	radeon_connector_update_scratch_regs(connector, ret);
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
+
 	return ret;
 }
 

@@ -1020,9 +1026,11 @@ radeon_vga_detect(struct drm_connector *
 	enum drm_connector_status ret = connector_status_disconnected;
 	int r;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	encoder = radeon_best_single_encoder(connector);
 	if (!encoder)

@@ -1089,8 +1097,10 @@ radeon_vga_detect(struct drm_connector *
 	radeon_connector_update_scratch_regs(connector, ret);
 
 out:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }

@@ -1153,9 +1163,11 @@ radeon_tv_detect(struct drm_connector *c
 	if (!radeon_connector->dac_load_detect)
 		return ret;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	encoder = radeon_best_single_encoder(connector);
 	if (!encoder)

@@ -1167,8 +1179,12 @@ radeon_tv_detect(struct drm_connector *c
 	if (ret == connector_status_connected)
 		ret = radeon_connector_analog_encoder_conflict_solve(connector, encoder, ret, false);
 	radeon_connector_update_scratch_regs(connector, ret);
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
+
 	return ret;
 }
 

@@ -1230,9 +1246,11 @@ radeon_dvi_detect(struct drm_connector *
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (radeon_connector->detected_hpd_without_ddc) {
 		force = true;

@@ -1415,8 +1433,10 @@ out:
 	}
 
 exit:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }

@@ -1666,9 +1686,11 @@ radeon_dp_detect(struct drm_connector *c
 	if (radeon_dig_connector->is_mst)
 		return connector_status_disconnected;
 
-	r = pm_runtime_get_sync(connector->dev->dev);
-	if (r < 0)
-		return connector_status_disconnected;
+	if (!drm_kms_helper_is_poll_worker()) {
+		r = pm_runtime_get_sync(connector->dev->dev);
+		if (r < 0)
+			return connector_status_disconnected;
+	}
 
 	if (!force && radeon_check_hpd_status_unchanged(connector)) {
 		ret = connector->status;

@@ -1755,8 +1777,10 @@ radeon_dp_detect(struct drm_connector *c
 	}
 
 out:
-	pm_runtime_mark_last_busy(connector->dev->dev);
-	pm_runtime_put_autosuspend(connector->dev->dev);
+	if (!drm_kms_helper_is_poll_worker()) {
+		pm_runtime_mark_last_busy(connector->dev->dev);
+		pm_runtime_put_autosuspend(connector->dev->dev);
+	}
 
 	return ret;
 }

This is the start of the stable review cycle for the 4.4.122 release. There are 63 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 Sun Mar 18 15:22:41 UTC 2018. 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/v4.x/stable-review/patch-4.4.122-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-4.4.y
and the diffstat can be found below.

thanks,

greg k-h

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

Greg Kroah-Hartman <[email protected]>

    Linux 4.4.122-rc1

Greg Kroah-Hartman <[email protected]>
fixup: sctp: verify size of a new chunk in _sctp_make_chunk()

Nikola Ciprich <[email protected]>
serial: 8250_pci: Add Brainboxes UC-260 4 port serial device

Xinyong <[email protected]>
usb: gadget: f_fs: Fix use-after-free in ffs_fs_kill_sb()

Pete Zaitcev <[email protected]>
usb: usbmon: Read text within supplied buffer size

Julia Lawall <[email protected]>
USB: usbmon: remove assignment from IS_ERR argument

Danilo Krummrich <[email protected]>
usb: quirks: add control message delay for 1b1c:1b20

Teijo Kinnunen <[email protected]>
USB: storage: Add JMicron bridge 152d:2567 to unusual_devs.h

Joel Fernandes <[email protected]>
staging: android: ashmem: Fix lockdep issue during llseek

Frank Mori Hess <[email protected]>
staging: comedi: fix comedi_nsamples_left.

Oliver Neukum <[email protected]>
uas: fix comparison for error code

Jonas Danielsson <[email protected]>
tty/serial: atmel: add new version check for usart

Ulrich Hecht <[email protected]>
serial: sh-sci: prevent lockup on full TTY buffers

H.J. Lu <[email protected]>

    x86: Treat R_X86_64_PLT32 as R_X86_64_PC32

Josh Poimboeuf <[email protected]>
x86/module: Detect and skip invalid relocations

Greg Kroah-Hartman <[email protected]>
Revert "ARM: dts: LogicPD Torpedo: Fix I2C1 pinmux"

Trond Myklebust <[email protected]>
NFS: Fix an incorrect type in struct nfs_direct_req

Quinn Tran <[email protected]>
scsi: qla2xxx: Replace fcport alloc with qla2x00_alloc_fcport

Clay McClure <[email protected]>
ubi: Fix race condition between ubi volume creation and udev

Tahsin Erdogan <[email protected]>
ext4: inplace xattr block update fails to deduplicate blocks

Florian Westphal <[email protected]>
netfilter: x_tables: pack percpu counter allocations

Florian Westphal <[email protected]>
netfilter: x_tables: pass xt_counters struct to counter allocator

Florian Westphal <[email protected]>
netfilter: x_tables: pass xt_counters struct instead of packet counter

Florian Westphal <[email protected]>
netfilter: use skb_to_full_sk in ip_route_me_harder

Florian Westphal <[email protected]>
netfilter: ipv6: fix use-after-free Write in nf_nat_ipv6_manip_pkt

Florian Westphal <[email protected]>
netfilter: bridge: ebt_among: add missing match size checks

Florian Westphal <[email protected]>
netfilter: ebtables: CONFIG_COMPAT: don't trust userland offsets

Eric Dumazet <[email protected]>
netfilter: IDLETIMER: be syzkaller friendly

Paolo Abeni <[email protected]>
netfilter: nat: cope with negative port range

Paolo Abeni <[email protected]>
netfilter: x_tables: fix missing timer initialization in xt_LED

Florian Westphal <[email protected]>
netfilter: add back stackpointer size checks

Philipp Zabel <[email protected]>
tc358743: fix register i2c_rd/wr function fix

Dmitry Torokhov <[email protected]>
Input: tca8418_keypad - remove double read of key event register

Arnd Bergmann <[email protected]>
ARM: omap2: hide omap3_save_secure_ram on non-OMAP3 builds

Florian Westphal <[email protected]>
netfilter: nfnetlink_queue: fix timestamp attribute

Arnd Bergmann <[email protected]>
watchdog: hpwdt: fix unused variable warning

Jerry Hoemann <[email protected]>
watchdog: hpwdt: Check source of NMI

Jerry Hoemann <[email protected]>
watchdog: hpwdt: SMBIOS check

Dan Williams <[email protected]>
nospec: Include <asm/barrier.h> dependency

Dennis Wassenberg <[email protected]>
ALSA: hda: add dock and led support for HP ProBook 640 G2

Dennis Wassenberg <[email protected]>
ALSA: hda: add dock and led support for HP EliteBook 820 G3

Takashi Iwai <[email protected]>
ALSA: seq: More protection for concurrent write and ioctl races

Takashi Iwai <[email protected]>
ALSA: seq: Don't allow resizing pool in use

Takashi Iwai <[email protected]>
ALSA: hda/realtek - Fix dock line-out volume on Dell Precision 7520

Seunghun Han <[email protected]>
x86/MCE: Serialize sysfs changes

Michael Lyle <[email protected]>
bcache: don't attach backing with duplicate UUID

James Hogan <[email protected]>
kbuild: Handle builtin dtb file names containing hyphens

Ross Zwisler <[email protected]>
loop: Fix lost writes caused by missing flag

Zhang Bo <[email protected]>
Input: matrix_keypad - fix race when disabling interrupts

Colin Ian King <[email protected]>
MIPS: OCTEON: irq: Check for null return on kzalloc allocation

Colin Ian King <[email protected]>
MIPS: ath25: Check for kzalloc allocation failure

Justin Chen <[email protected]>
MIPS: BMIPS: Do not mask IPIs during suspend

Alex Deucher <[email protected]>
drm/amdgpu: fix KV harvesting

Alex Deucher <[email protected]>
drm/radeon: fix KV harvesting

Rex Zhu <[email protected]>
drm/amdgpu: Notify sbios device ready before send request

Lukas Wunner <[email protected]>
drm/amdgpu: Fix deadlock on runtime suspend

Lukas Wunner <[email protected]>
drm/radeon: Fix deadlock on runtime suspend

Lukas Wunner <[email protected]>
drm/nouveau: Fix deadlock on runtime suspend

Lukas Wunner <[email protected]>
drm: Allow determining if current task is output poll worker

Lukas Wunner <[email protected]>
workqueue: Allow retrieval of current task's work struct

[email protected] <[email protected]>
scsi: qla2xxx: Fix NULL pointer crash due to active timer for ABTS

Leon Romanovsky <[email protected]>
RDMA/mlx5: Fix integer overflow while resizing CQ

Leon Romanovsky <[email protected]>
RDMA/ucma: Check that user doesn't overflow QP state

Leon Romanovsky <[email protected]>
RDMA/ucma: Limit possible option size

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

Diffstat:

 Makefile                                       |   4 +-
 arch/arm/boot/dts/logicpd-torpedo-som.dtsi     |   8 --
 arch/arm/mach-omap2/omap-secure.c              |   2 +
 arch/mips/ath25/board.c                        |   2 +
 arch/mips/cavium-octeon/octeon-irq.c           |   2 +
 arch/mips/kernel/smp-bmips.c                   |   8 +-
 arch/x86/kernel/cpu/mcheck/mce.c               |  22 ++++-
 arch/x86/kernel/machine_kexec_64.c             |   1 +
 arch/x86/kernel/module.c                       |  14 +++
 arch/x86/tools/relocs.c                        |   3 +
 drivers/block/loop.c                           |   2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c       |   3 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c |  58 ++++++++----
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c          |  30 +-----
 drivers/gpu/drm/drm_probe_helper.c             |  20 ++++
 drivers/gpu/drm/nouveau/nouveau_connector.c    |  18 +++-
 drivers/gpu/drm/radeon/cik.c                   |  31 +------
 drivers/gpu/drm/radeon/radeon_connectors.c     |  74 ++++++++++-----
 drivers/infiniband/core/ucma.c                 |   6 ++
 drivers/infiniband/hw/mlx5/cq.c                |   7 +-
 drivers/input/keyboard/matrix_keypad.c         |   4 +-
 drivers/input/keyboard/tca8418_keypad.c        |   2 -
 drivers/md/bcache/super.c                      |  11 +++
 drivers/media/i2c/tc358743.c                   |   2 +-
 drivers/mtd/ubi/vmt.c                          |  15 ++-
 drivers/scsi/qla2xxx/qla_init.c                |   1 +
 drivers/scsi/qla2xxx/qla_target.c              |   2 +-
 drivers/staging/android/ashmem.c               |  15 ++-
 drivers/staging/comedi/drivers.c               |   3 +-
 drivers/tty/serial/8250/8250_pci.c             |  11 +++
 drivers/tty/serial/atmel_serial.c              |   1 +
 drivers/tty/serial/sh-sci.c                    |   2 +
 drivers/usb/core/message.c                     |   4 +
 drivers/usb/core/quirks.c                      |   3 +-
 drivers/usb/gadget/function/f_fs.c             |   1 -
 drivers/usb/mon/mon_text.c                     | 124 ++++++++++++++++---------
 drivers/usb/storage/uas.c                      |   2 +-
 drivers/usb/storage/unusual_devs.h             |   7 ++
 drivers/watchdog/hpwdt.c                       |  12 ++-
 fs/ext4/xattr.c                                |   3 +-
 fs/nfs/direct.c                                |   2 +-
 include/drm/drm_crtc_helper.h                  |   1 +
 include/linux/netfilter/x_tables.h             |  38 ++------
 include/linux/nospec.h                         |   1 +
 include/linux/usb/quirks.h                     |   3 +
 include/linux/workqueue.h                      |   1 +
 kernel/workqueue.c                             |  16 ++++
 net/bridge/netfilter/ebt_among.c               |  21 ++++-
 net/bridge/netfilter/ebtables.c                |  13 ++-
 net/ipv4/netfilter.c                           |   7 +-
 net/ipv4/netfilter/arp_tables.c                |  20 ++--
 net/ipv4/netfilter/ip_tables.c                 |  20 ++--
 net/ipv6/netfilter/ip6_tables.c                |  21 +++--
 net/ipv6/netfilter/nf_nat_l3proto_ipv6.c       |   4 +
 net/netfilter/nf_nat_proto_common.c            |   7 +-
 net/netfilter/nfnetlink_queue.c                |   2 +-
 net/netfilter/x_tables.c                       |  55 +++++++++++
 net/netfilter/xt_IDLETIMER.c                   |   9 +-
 net/netfilter/xt_LED.c                         |  12 +--
 net/sctp/sm_make_chunk.c                       |   2 +-
 scripts/Makefile.lib                           |   8 +-
 sound/core/seq/seq_clientmgr.c                 |  21 +++--
 sound/core/seq/seq_fifo.c                      |   2 +-
 sound/core/seq/seq_memory.c                    |  14 ++-
 sound/core/seq/seq_memory.h                    |   3 +-
 sound/pci/hda/patch_conexant.c                 |   2 +
 sound/pci/hda/patch_realtek.c                  |  16 ++++
 67 files changed, 572 insertions(+), 289 deletions(-)

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

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

From: Rex Zhu <[email protected]>

commit 1bced75f4ab04bec55aecb57d99435dc6d0ae5a0 upstream.

it is required if a platform supports PCIe root complex core voltage reduction. After receiving this notification, SBIOS can apply default PCIe root complex power policy.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -585,6 +585,9 @@ int amdgpu_acpi_pcie_performance_request
 	size_t size;
 	u32 retry = 3;
 
+	if (amdgpu_acpi_pcie_notify_device_ready(adev))
+		return -EINVAL;
+
 	/* Get the device handle */
 	handle = ACPI_HANDLE(&adev->pdev->dev);
 	if (!handle)

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

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

From: Takashi Iwai <[email protected]>

commit e312a869cd726c698a75caca0d9e5c22fd3f1534 upstream.

The dock line-out pin (NID 0x17 of ALC3254 codec) on Dell Precision 7520 may route to three different DACs, 0x02, 0x03 and 0x06. The first two DACS have the volume amp controls while the last one doesn't. And unfortunately, the auto-parser assigns this pin to DAC3, resulting in the non-working volume control for the line out.

Fix it by disabling the routing to DAC3 on the corresponding pin.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199029

---
 sound/pci/hda/patch_realtek.c |   16 ++++++++++++++++
 1 file changed, 16 insertions(+)

@@ -4722,6 +4722,16 @@ static void alc298_fixup_speaker_volume(
 	}
 }
 
+/* disable DAC3 (0x06) selection on NID 0x17 as it has no volume amp control */
+static void alc295_fixup_disable_dac3(struct hda_codec *codec,
+				      const struct hda_fixup *fix, int action)
+{
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		hda_nid_t conn[2] = { 0x02, 0x03 };
+		snd_hda_override_conn_list(codec, 0x17, 2, conn);
+	}
+}
+
 /* Hook to update amp GPIO4 for automute */
 static void alc280_hp_gpio4_automute_hook(struct hda_codec *codec,
 					  struct hda_jack_callback *jack)

@@ -4871,6 +4881,7 @@ enum {
 	ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY,
 	ALC255_FIXUP_DELL_SPK_NOISE,
 	ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
+	ALC295_FIXUP_DISABLE_DAC3,
 	ALC280_FIXUP_HP_HEADSET_MIC,
 	ALC221_FIXUP_HP_FRONT_MIC,
 	ALC292_FIXUP_TPT460,

@@ -5560,6 +5571,10 @@ static const struct hda_fixup alc269_fix
 		.chained = true,
 		.chain_id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE,
 	},
+	[ALC295_FIXUP_DISABLE_DAC3] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc295_fixup_disable_dac3,
+	},
 	[ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {

@@ -5617,6 +5632,7 @@ static const struct snd_pci_quirk alc269
 	SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME),
+	SND_PCI_QUIRK(0x1028, 0x07b0, "Dell Precision 7520", ALC295_FIXUP_DISABLE_DAC3),
 	SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
 	SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),

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

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