4.18.19-stable review

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

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

From: Javier Martinez Canillas <[email protected]>

[ Upstream commit 0d6d0d62d9505a9816716aa484ebd0b04c795063 ]

For TPM 1.2 chips the system setup utility allows to set the TPM device in one of the following states:

* Active: Security chip is functional
* Inactive: Security chip is visible, but is not functional
* Disabled: Security chip is hidden and is not functional

When choosing the "Inactive" state, the TPM 1.2 device is enumerated and registered, but sending TPM commands fail with either TPM_DEACTIVATED or TPM_DISABLED depending if the firmware deactivated or disabled the TPM.

Since these TPM 1.2 error codes don't have special treatment, inactivating the TPM leads to a very noisy kernel log buffer that shows messages like the following:

tpm_tis 00:05: 1.2 TPM (device-id 0x0, rev-id 78)
tpm tpm0: A TPM error (6) occurred attempting to read a pcr value tpm tpm0: TPM is disabled/deactivated (0x6)
tpm tpm0: A TPM error (6) occurred attempting get random tpm tpm0: A TPM error (6) occurred attempting to read a pcr value
ima: No TPM chip found, activating TPM-bypass! (rc=6) tpm tpm0: A TPM error (6) occurred attempting get random tpm tpm0: A TPM error (6) occurred attempting get random tpm tpm0: A TPM error (6) occurred attempting get random tpm tpm0: A TPM error (6) occurred attempting get random

Let's just suppress error log messages for the TPM_{DEACTIVATED,DISABLED} return codes, since this is expected when the TPM 1.2 is set to Inactive.

In that case the kernel log is cleaner and less confusing for users, i.e:

tpm_tis 00:05: 1.2 TPM (device-id 0x0, rev-id 78) tpm tpm0: TPM is disabled/deactivated (0x6)
ima: No TPM chip found, activating TPM-bypass! (rc=6)

---
 drivers/char/tpm/tpm-interface.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -664,7 +664,8 @@ ssize_t tpm_transmit_cmd(struct tpm_chip
 		return len;
 
 	err = be32_to_cpu(header->return_code);
-	if (err != 0 && desc)
+	if (err != 0 && err != TPM_ERR_DISABLED && err != TPM_ERR_DEACTIVATED
+	    && desc)
 		dev_err(&chip->dev, "A TPM error (%d) occurred %s\n", err,
 			desc);
 	if (err)

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

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

From: Jaegeuk Kim <[email protected]>

[ Upstream commit fb7d70db305a1446864227abf711b756568f8242 ]

When running fault injection test, I hit somewhat wrong behavior in f2fs_gc -> gc_data_segment():

0. fault injection generated some PageError'ed pages

1. gc_data_segment
-> f2fs_get_read_data_page(REQ_RAHEAD)

2. move_data_page
-> f2fs_get_lock_data_page()
-> f2f_get_read_data_page()
-> f2fs_submit_page_read()

    -> submit_bio(READ)

-> return EIO due to PageError
-> fail to move data

---
 fs/f2fs/data.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -80,7 +80,8 @@ static void __read_end_io(struct bio *bi
 		/* PG_error was set if any post_read step failed */
 		if (bio->bi_status || PageError(page)) {
 			ClearPageUptodate(page);
-			SetPageError(page);
+			/* will re-read again later */
+			ClearPageError(page);
 		} else {
 			SetPageUptodate(page);
 		}

@@ -584,6 +585,7 @@ static int f2fs_submit_page_read(struct
 		bio_put(bio);
 		return -EFAULT;
 	}
+	ClearPageError(page);
 	__submit_bio(F2FS_I_SB(inode), bio, DATA);
 	return 0;
 }

@@ -1528,6 +1530,7 @@ submit_and_realloc:
 		if (bio_add_page(bio, page, blocksize, 0) < blocksize)
 			goto submit_and_realloc;
 
+		ClearPageError(page);
 		last_block_in_bio = block_nr;
 		goto next_page;
 set_error_page:

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

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

From: Dexuan Cui <[email protected]>

[ Upstream commit 25355252607ca288f329ee033f387764883393f6 ]

A cpumask structure on the stack can cause a warning with CONFIG_NR_CPUS=8192 (e.g. Ubuntu 16.04 and 18.04 use this):

drivers/hv//channel_mgmt.c: In function ‘init_vp_index’:
drivers/hv//channel_mgmt.c:702:1: warning: the frame size of 1032 bytes
is larger than 1024 bytes [-Wframe-larger-than=]

Nowadays it looks most distros enable CONFIG_CPUMASK_OFFSTACK=y, and hence we can work around the warning by using cpumask_var_t.

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

@@ -606,16 +606,18 @@ static void init_vp_index(struct vmbus_c
 	bool perf_chn = vmbus_devs[dev_type].perf_device;
 	struct vmbus_channel *primary = channel->primary_channel;
 	int next_node;
-	struct cpumask available_mask;
+	cpumask_var_t available_mask;
 	struct cpumask *alloced_mask;
 
 	if ((vmbus_proto_version == VERSION_WS2008) ||
-	    (vmbus_proto_version == VERSION_WIN7) || (!perf_chn)) {
+	    (vmbus_proto_version == VERSION_WIN7) || (!perf_chn) ||
+	    !alloc_cpumask_var(&available_mask, GFP_KERNEL)) {
 		/*
 		 * Prior to win8, all channel interrupts are
 		 * delivered on cpu 0.
 		 * Also if the channel is not a performance critical
 		 * channel, bind it to cpu 0.
+		 * In case alloc_cpumask_var() fails, bind it to cpu 0.
 		 */
 		channel->numa_node = 0;
 		channel->target_cpu = 0;

@@ -653,7 +655,7 @@ static void init_vp_index(struct vmbus_c
 		cpumask_clear(alloced_mask);
 	}
 
-	cpumask_xor(&available_mask, alloced_mask,
+	cpumask_xor(available_mask, alloced_mask,
 		    cpumask_of_node(primary->numa_node));
 
 	cur_cpu = -1;

@@ -671,10 +673,10 @@ static void init_vp_index(struct vmbus_c
 	}
 
 	while (true) {
-		cur_cpu = cpumask_next(cur_cpu, &available_mask);
+		cur_cpu = cpumask_next(cur_cpu, available_mask);
 		if (cur_cpu >= nr_cpu_ids) {
 			cur_cpu = -1;
-			cpumask_copy(&available_mask,
+			cpumask_copy(available_mask,
 				     cpumask_of_node(primary->numa_node));
 			continue;
 		}

@@ -704,6 +706,8 @@ static void init_vp_index(struct vmbus_c
 
 	channel->target_cpu = cur_cpu;
 	channel->target_vp = hv_cpu_number_to_vp_number(cur_cpu);
+
+	free_cpumask_var(available_mask);
 }
 
 static void vmbus_wait_for_unload(void)

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

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

From: Jorgen Hansen <[email protected]>

[ Upstream commit 11924ba5e671d6caef1516923e2bd8c72929a3fe ]

When adding a VMCI resource, the check for an existing entry would ignore that the new entry could be a wildcard. This could result in multiple resource entries that would match a given handle. One disastrous outcome of this is that the refcounting used to ensure that delayed callbacks for VMCI datagrams have run before the datagram is destroyed can be wrong, since the refcount could be increased on the duplicate entry. This in turn leads to a use after free bug. This issue was discovered by Hangbin Liu using KASAN and syzkaller.

---
 drivers/misc/vmw_vmci/vmci_driver.c   |    2 +-
 drivers/misc/vmw_vmci/vmci_resource.c |    3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

@@ -113,5 +113,5 @@ module_exit(vmci_drv_exit);
 
 MODULE_AUTHOR("VMware, Inc.");
 MODULE_DESCRIPTION("VMware Virtual Machine Communication Interface.");
-MODULE_VERSION("1.1.5.0-k");
+MODULE_VERSION("1.1.6.0-k");
 MODULE_LICENSE("GPL v2");

@@ -57,7 +57,8 @@ static struct vmci_resource *vmci_resour
 
 		if (r->type == type &&
 		    rid == handle.resource &&
-		    (cid == handle.context || cid == VMCI_INVALID_ID)) {
+		    (cid == handle.context || cid == VMCI_INVALID_ID ||
+		     handle.context == VMCI_INVALID_ID)) {
 			resource = r;
 			break;
 		}

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

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

From: Mika Westerberg <[email protected]>

[ Upstream commit 6299cf9ec3985cac70bede8a855b5087b81a6640 ]

We enable power management automatically for bridges where pci_bridge_d3_possible() returns true. However, these bridges may have ACPI methods such as _DSW that need to be called before D3 entry. For example in Lenovo Thinkpad X1 Carbon 6th _DSW method is used to prepare D3cold for the PCIe root port hosting Thunderbolt chain. Because wake is not enabled _DSW method is never called and the port does not enter D3cold properly consuming more power than necessary.

Users can work this around by writing "enabled" to "wakeup" sysfs file under the device in question but that is not something an ordinary user is expected to do.

Since we already automatically enable power management for PCIe ports with ->bridge_d3 set extend that to enable wake for them as well, assuming the port has any ACPI wakeup related objects implemented in the namespace (adev->wakeup.flags.valid is true). This ensures the necessary ACPI methods get called at appropriate times and allows the root port in Thinkpad X1 Carbon 6th to go into D3cold.

---
 drivers/pci/pci-acpi.c |   16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

@@ -779,19 +779,33 @@ static void pci_acpi_setup(struct device
 		return;
 
 	device_set_wakeup_capable(dev, true);
+	/*
+	 * For bridges that can do D3 we enable wake automatically (as
+	 * we do for the power management itself in that case). The
+	 * reason is that the bridge may have additional methods such as
+	 * _DSW that need to be called.
+	 */
+	if (pci_dev->bridge_d3)
+		device_wakeup_enable(dev);
+
 	acpi_pci_wakeup(pci_dev, false);
 }
 
 static void pci_acpi_cleanup(struct device *dev)
 {
 	struct acpi_device *adev = ACPI_COMPANION(dev);
+	struct pci_dev *pci_dev = to_pci_dev(dev);
 
 	if (!adev)
 		return;
 
 	pci_acpi_remove_pm_notifier(adev);
-	if (adev->wakeup.flags.valid)
+	if (adev->wakeup.flags.valid) {
+		if (pci_dev->bridge_d3)
+			device_wakeup_disable(dev);
+
 		device_set_wakeup_capable(dev, false);
+	}
 }
 
 static bool pci_acpi_bus_match(struct device *dev)

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

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

From: Chuck Lever <[email protected]>

[ Upstream commit ef739b2175dde9c05594f768cb78149f1ce2ac36 ]

On a fresh connection, an RPC/RDMA client is supposed to send only one RPC Call until it gets a credit grant in the first RPC Reply from the server [RFC 8166, Section 3.3.3].

There is a bug in the Linux client's credit accounting mechanism introduced by commit e7ce710a8802 ("xprtrdma: Avoid deadlock when credit window is reset"). On connect, it simply dumps all pending RPC Calls onto the new connection.

Servers have been tolerant of this bad behavior. Currently no server implementation ever changes its credit grant over reconnects, and servers always repost enough Receives before connections are fully established.

To correct this issue, ensure that the client resets both the credit grant _and_ the congestion window when handling a reconnect.

---
 net/sunrpc/xprtrdma/svc_rdma_backchannel.c |    1 +
 net/sunrpc/xprtrdma/transport.c            |    6 ++++++
 2 files changed, 7 insertions(+)

@@ -248,6 +248,7 @@ static void
 xprt_rdma_bc_close(struct rpc_xprt *xprt)
 {
 	dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);
+	xprt->cwnd = RPC_CWNDSHIFT;
 }
 
 static void

@@ -468,6 +468,12 @@ xprt_rdma_close(struct rpc_xprt *xprt)
 		xprt->reestablish_timeout = 0;
 	xprt_disconnect_done(xprt);
 	rpcrdma_ep_disconnect(ep, ia);
+
+	/* Prepare @xprt for the next connection by reinitializing
+	 * its credit grant to one (see RFC 8166, Section 3.3.3).
+	 */
+	r_xprt->rx_buf.rb_credits = 1;
+	xprt->cwnd = RPC_CWNDSHIFT;
 }
 
 /**

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

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

From: Lina Iyer <[email protected]>

[ Upstream commit 7bae48b22c8d38c5cd50f52b6e15d134e2bb3935 ]

The PDC irqchp can convert a falling edge or level low interrupt to a rising edge or level high interrupt at the GIC. We just need to setup the GIC correctly. Set up the interrupt type for the IRQ_TYPE_EDGE_BOTH as IRQ_TYPE_EDGE_RISING at the GIC.

---
 drivers/irqchip/qcom-pdc.c |    1 +
 1 file changed, 1 insertion(+)

@@ -124,6 +124,7 @@ static int qcom_pdc_gic_set_type(struct
 		break;
 	case IRQ_TYPE_EDGE_BOTH:
 		pdc_type = PDC_EDGE_DUAL;
+		type = IRQ_TYPE_EDGE_RISING;
 		break;
 	case IRQ_TYPE_LEVEL_HIGH:
 		pdc_type = PDC_LEVEL_HIGH;

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

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

From: Fabrice Gasnier <[email protected]>

[ Upstream commit 41ee1ea21052583eaf5487dfa0d0c907c9667548 ]

There's a race with root hub resume, when using external vbus supply. Root hub gets resumed, but runtime pm autosuspend runs as external vbus supply isn't enabled. So, host never exit from power down properly. Initialize vbus external supply before, rater that after hub resume.

vbus supply")

---
 drivers/usb/dwc2/hcd.c |   10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

@@ -4394,6 +4394,7 @@ static int _dwc2_hcd_start(struct usb_hc
 	struct dwc2_hsotg *hsotg = dwc2_hcd_to_hsotg(hcd);
 	struct usb_bus *bus = hcd_to_bus(hcd);
 	unsigned long flags;
+	int ret;
 
 	dev_dbg(hsotg->dev, "DWC OTG HCD START\n");
 

@@ -4409,6 +4410,13 @@ static int _dwc2_hcd_start(struct usb_hc
 
 	dwc2_hcd_reinit(hsotg);
 
+	/* enable external vbus supply before resuming root hub */
+	spin_unlock_irqrestore(&hsotg->lock, flags);
+	ret = dwc2_vbus_supply_init(hsotg);
+	if (ret)
+		return ret;
+	spin_lock_irqsave(&hsotg->lock, flags);
+
 	/* Initialize and connect root hub if one is not already attached */
 	if (bus->root_hub) {
 		dev_dbg(hsotg->dev, "DWC OTG HCD Has Root Hub\n");

@@ -4418,7 +4426,7 @@ static int _dwc2_hcd_start(struct usb_hc
 
 	spin_unlock_irqrestore(&hsotg->lock, flags);
 
-	return dwc2_vbus_supply_init(hsotg);
+	return 0;
 }
 
 /*

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

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

From: Alexandre Belloni <[email protected]>

[ Upstream commit bb80e4fa57eb75ebd64ae9be4155da6d12c1a997 ]

The at91sam9rl PMC is not quite the same as the at91sam9g45 one and now has its own compatible string. Add support for that.

---
 drivers/usb/gadget/udc/atmel_usba_udc.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -2018,6 +2018,8 @@ static struct usba_ep * atmel_udc_of_ini
 	udc->errata = match->data;
 	udc->pmc = syscon_regmap_lookup_by_compatible("atmel,at91sam9g45-pmc");
 	if (IS_ERR(udc->pmc))
+		udc->pmc = syscon_regmap_lookup_by_compatible("atmel,at91sam9rl-pmc");
+	if (IS_ERR(udc->pmc))
 		udc->pmc = syscon_regmap_lookup_by_compatible("atmel,at91sam9x5-pmc");
 	if (udc->errata && IS_ERR(udc->pmc))
 		return ERR_CAST(udc->pmc);

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

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

From: Theodore Ts'o <[email protected]>

[ Upstream commit f18b2b83a727a3db208308057d2c7945f368e625 ]

If the starting block number of either the source or destination file exceeds the EOF, EXT4_IOC_MOVE_EXT should return EINVAL.

Also fixed the helper function mext_check_coverage() so that if the logical block is beyond EOF, make it return immediately, instead of looping until the block number wraps all the away around. This takes long enough that if there are multiple threads trying to do pound on an the same inode doing non-sensical things, it can end up triggering the kernel's soft lockup detector.

---
 fs/ext4/move_extent.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

@@ -518,9 +518,13 @@ mext_check_arguments(struct inode *orig_
 			orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
-	if (orig_eof < orig_start + *len - 1)
+	if (orig_eof <= orig_start)
+		*len = 0;
+	else if (orig_eof < orig_start + *len - 1)
 		*len = orig_eof - orig_start;
-	if (donor_eof < donor_start + *len - 1)
+	if (donor_eof <= donor_start)
+		*len = 0;
+	else if (donor_eof < donor_start + *len - 1)
 		*len = donor_eof - donor_start;
 	if (!*len) {
 		ext4_debug("ext4 move extent: len should not be 0 "

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

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

From: Shaohua Li <[email protected]>

[ Upstream commit d595567dc4f0c1d90685ec1e2e296e2cad2643ac ]

If we change the number of array's device after device is removed from array, then add the device back to array, we can see that device is added as active role instead of spare which we expected.

Please see the below link for details:
https://marc.info/?l=linux-raid&m=153736982015076&w=2

This is caused by that we prefer to use device's previous role which is recorded by saved_raid_disk, but we should respect the new number of conf->raid_disks since it could be changed after device is removed.

---
 drivers/md/md.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -1779,6 +1779,10 @@ static int super_1_validate(struct mddev
 			} else
 				set_bit(In_sync, &rdev->flags);
 			rdev->raid_disk = role;
+			if (role >= mddev->raid_disks) {
+				rdev->saved_raid_disk = -1;
+				rdev->raid_disk = -1;
+			}
 			break;
 		}
 		if (sb->devflags & WriteMostly1)

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

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

From: Bartosz Golaszewski <[email protected]>

[ Upstream commit fa72d847d68d7833b77a4bef944cf2c5baf56f49 ]

This function can fail so check its return value in nvmem_register() and act accordingly.

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

@@ -518,11 +518,17 @@ struct nvmem_device *nvmem_register(cons
 			goto err_device_del;
 	}
 
-	if (config->cells)
-		nvmem_add_cells(nvmem, config->cells, config->ncells);
+	if (config->cells) {
+		rval = nvmem_add_cells(nvmem, config->cells, config->ncells);
+		if (rval)
+			goto err_teardown_compat;
+	}
 
 	return nvmem;
 
+err_teardown_compat:
+	if (config->compat)
+		device_remove_bin_file(nvmem->base_dev, &nvmem->eeprom);
 err_device_del:
 	device_del(&nvmem->dev);
 err_put_device:

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

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

From: Anshuman Gupta <[email protected]>

[ Upstream commit 330e2d61cdd58363eb5e66b2e72f76fe3c5492e0 ]

When USB bus host controller root hub resumes from autosuspend, it immediately tries to enter auto-suspend, but there can be a scenario when root hub is resuming its usb2 ports, in that particular case USB host controller auto suspend fails since it is busy to resuming its usb2 ports.

This makes multiple failed cycles of auto-suspend until all usb2 ports of host controller root hub do not resume.

This patch uses USB core framework usb_hcd_start_port_resume, usb_hcd_end_port_resume API's in order to autoresume/autosuspend root hub properly.

---
 drivers/usb/host/xhci-hub.c  |    5 +++++
 drivers/usb/host/xhci-ring.c |    1 +
 2 files changed, 6 insertions(+)

@@ -900,6 +900,7 @@ static u32 xhci_get_port_status(struct u
 				set_bit(wIndex, &bus_state->resuming_ports);
 				bus_state->resume_done[wIndex] = timeout;
 				mod_timer(&hcd->rh_timer, timeout);
+				usb_hcd_start_port_resume(&hcd->self, wIndex);
 			}
 		/* Has resume been signalled for USB_RESUME_TIME yet? */
 		} else if (time_after_eq(jiffies,

@@ -940,6 +941,7 @@ static u32 xhci_get_port_status(struct u
 				clear_bit(wIndex, &bus_state->rexit_ports);
 			}
 
+			usb_hcd_end_port_resume(&hcd->self, wIndex);
 			bus_state->port_c_suspend |= 1 << wIndex;
 			bus_state->suspended_ports &= ~(1 << wIndex);
 		} else {

@@ -962,6 +964,7 @@ static u32 xhci_get_port_status(struct u
 	    (raw_port_status & PORT_PLS_MASK) != XDEV_RESUME) {
 		bus_state->resume_done[wIndex] = 0;
 		clear_bit(wIndex, &bus_state->resuming_ports);
+		usb_hcd_end_port_resume(&hcd->self, wIndex);
 	}
 
 

@@ -1337,6 +1340,7 @@ int xhci_hub_control(struct usb_hcd *hcd
 					goto error;
 
 				set_bit(wIndex, &bus_state->resuming_ports);
+				usb_hcd_start_port_resume(&hcd->self, wIndex);
 				xhci_set_link_state(xhci, ports[wIndex],
 						    XDEV_RESUME);
 				spin_unlock_irqrestore(&xhci->lock, flags);

@@ -1345,6 +1349,7 @@ int xhci_hub_control(struct usb_hcd *hcd
 				xhci_set_link_state(xhci, ports[wIndex],
 							XDEV_U0);
 				clear_bit(wIndex, &bus_state->resuming_ports);
+				usb_hcd_end_port_resume(&hcd->self, wIndex);
 			}
 			bus_state->port_c_suspend |= 1 << wIndex;
 

@@ -1602,6 +1602,7 @@ static void handle_port_status(struct xh
 			set_bit(HCD_FLAG_POLL_RH, &hcd->flags);
 			mod_timer(&hcd->rh_timer,
 				  bus_state->resume_done[hcd_portnum]);
+			usb_hcd_start_port_resume(&hcd->self, hcd_portnum);
 			bogus_port_status = true;
 		}
 	}

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

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

From: Chao Yu <[email protected]>

[ Upstream commit 5cd1f387a13b5188b4edb4c834310302a85a6ea2 ]

Testcase to reproduce this bug:
1. mkfs.f2fs -O extra_attr -O inode_crtime /dev/sdd
2. mount -t f2fs /dev/sdd /mnt/f2fs
3. touch /mnt/f2fs/file
4. xfs_io -f /mnt/f2fs/file -c "fsync"
5. godown /mnt/f2fs
6. umount /mnt/f2fs
7. mount -t f2fs /dev/sdd /mnt/f2fs
8. xfs_io -f /mnt/f2fs/file -c "statx -r"

stat.btime.tv_sec = 0
stat.btime.tv_nsec = 0

This patch fixes to recover inode creation time fields during mount.

---
 fs/f2fs/node.c |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -2379,6 +2379,13 @@ retry:
 			F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize),
 								i_projid))
 			dst->i_projid = src->i_projid;
+
+		if (f2fs_sb_has_inode_crtime(sbi->sb) &&
+			F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize),
+							i_crtime_nsec)) {
+			dst->i_crtime = src->i_crtime;
+			dst->i_crtime_nsec = src->i_crtime_nsec;
+		}
 	}
 
 	new_ni = old_ni;

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

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

From: Chao Yu <[email protected]>

[ Upstream commit 19c73a691ccf6fb2f12d4e9cf9830023966cec88 ]

Testcase to reproduce this bug:
1. mkfs.f2fs /dev/sdd
2. mount -t f2fs /dev/sdd /mnt/f2fs
3. touch /mnt/f2fs/file
4. sync
5. chattr +A /mnt/f2fs/file
6. xfs_io -f /mnt/f2fs/file -c "fsync"
7. godown /mnt/f2fs
8. umount /mnt/f2fs
9. mount -t f2fs /dev/sdd /mnt/f2fs
10. lsattr /mnt/f2fs/file

-----------------N- /mnt/f2fs/file

But actually, we expect the corrct result is:

-------A---------N- /mnt/f2fs/file

The reason is we didn't recover inode.i_flags field during mount, fix it.

---
 fs/f2fs/recovery.c |    1 +
 1 file changed, 1 insertion(+)

@@ -221,6 +221,7 @@ static void recover_inode(struct inode *
 	inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec);
 
 	F2FS_I(inode)->i_advise = raw->i_advise;
+	F2FS_I(inode)->i_flags = le32_to_cpu(raw->i_flags);
 
 	recover_inline_flags(inode, raw);
 

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

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

From: Tonghao Zhang <[email protected]>

[ Upstream commit 4c1ef72e9b71a19fb405ebfcd37c0a5e16fa44ca ]

It is a serious driver defect to enable MSI or MSI-X more than once. Doing so may panic the kernel as in the stack trace below:

  Call Trace:
    sysfs_add_one+0xa5/0xd0
    create_dir+0x7c/0xe0
    sysfs_create_subdir+0x1c/0x20
    internal_create_group+0x6d/0x290
    sysfs_create_groups+0x4a/0xa0
    populate_msi_sysfs+0x1cd/0x210
    pci_enable_msix+0x31c/0x3e0
    igbuio_pci_open+0x72/0x300 [igb_uio]
    uio_open+0xcc/0x120 [uio]
    chrdev_open+0xa1/0x1e0
    [...]
    do_sys_open+0xf3/0x1f0
    SyS_open+0x1e/0x20
    system_call_fastpath+0x16/0x1b
    ---[ end trace 11042e2848880209 ]---
    Kernel panic - not syncing: stack-protector: Kernel stack is corrupted in: ffffffffa056b4fa

We want to keep the WARN_ON() and stack trace so the driver can be fixed, but we can avoid the kernel panic by returning an error. We may still get warnings like this:

  Call Trace:
    pci_enable_msix+0x3c9/0x3e0
    igbuio_pci_open+0x72/0x300 [igb_uio]
    uio_open+0xcc/0x120 [uio]
    chrdev_open+0xa1/0x1e0
    [...]
    do_sys_open+0xf3/0x1f0
    SyS_open+0x1e/0x20
    system_call_fastpath+0x16/0x1b
    ------------[ cut here ]------------
    WARNING: at fs/sysfs/dir.c:526 sysfs_add_one+0xa5/0xd0()
    sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:03.0/0000:01:00.1/msi_irqs'

---
 drivers/pci/msi.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

@@ -958,7 +958,6 @@ static int __pci_enable_msix(struct pci_
 			}
 		}
 	}
-	WARN_ON(!!dev->msix_enabled);
 
 	/* Check whether driver already requested for MSI irq */
 	if (dev->msi_enabled) {

@@ -1028,8 +1027,6 @@ static int __pci_enable_msi_range(struct
 	if (!pci_msi_supported(dev, minvec))
 		return -EINVAL;
 
-	WARN_ON(!!dev->msi_enabled);
-
 	/* Check whether driver already requested MSI-X irqs */
 	if (dev->msix_enabled) {
 		pci_info(dev, "can't enable MSI (MSI-X already enabled)\n");

@@ -1039,6 +1036,9 @@ static int __pci_enable_msi_range(struct
 	if (maxvec < minvec)
 		return -ERANGE;
 
+	if (WARN_ON_ONCE(dev->msi_enabled))
+		return -EINVAL;
+
 	nvec = pci_msi_vec_count(dev);
 	if (nvec < 0)
 		return nvec;

@@ -1087,6 +1087,9 @@ static int __pci_enable_msix_range(struc
 	if (maxvec < minvec)
 		return -ERANGE;
 
+	if (WARN_ON_ONCE(dev->msix_enabled))
+		return -EINVAL;
+
 	for (;;) {
 		if (affd) {
 			nvec = irq_calc_affinity_vectors(minvec, nvec, affd);

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

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

From: Suzuki K Poulose <[email protected]>

[ Upstream commit 987d1e8dcd370d96029a3d76a0031b043c4a69ae ]

If the ETB is already enabled in sysfs mode, the ETB reports success even if a perf mode is requested. Fix this by checking the requested mode.

---
 drivers/hwtracing/coresight/coresight-etb10.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -147,6 +147,10 @@ static int etb_enable(struct coresight_d
 	if (val == CS_MODE_PERF)
 		return -EBUSY;
 
+	/* Don't let perf disturb sysFS sessions */
+	if (val == CS_MODE_SYSFS && mode == CS_MODE_PERF)
+		return -EBUSY;
+
 	/* Nothing to do, the tracer is already enabled. */
 	if (val == CS_MODE_SYSFS)
 		goto out;

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

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

From: Vignesh R <[email protected]>

[ Upstream commit 726d75a6d243bf6730da3216f3592503f6f0f588 ]

Errata i870 is applicable in both EP and RC mode. Therefore rename function dra7xx_pcie_ep_unaligned_memaccess(), that implements errata workaround, to dra7xx_pcie_unaligned_memaccess() and call it for both RC and EP. Make sure driver probe does not fail in case the workaround is not applied for RC mode in order to maintain DT backward compatibility.

---
 drivers/pci/controller/dwc/pci-dra7xx.c |   11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

@@ -542,7 +542,7 @@ static const struct of_device_id of_dra7
 };
 
 /*
- * dra7xx_pcie_ep_unaligned_memaccess: workaround for AM572x/AM571x Errata i870
+ * dra7xx_pcie_unaligned_memaccess: workaround for AM572x/AM571x Errata i870
  * @dra7xx: the dra7xx device where the workaround should be applied
  *
  * Access to the PCIe slave port that are not 32-bit aligned will result

@@ -552,7 +552,7 @@ static const struct of_device_id of_dra7
  *
  * To avoid this issue set PCIE_SS1_AXI2OCP_LEGACY_MODE_ENABLE to 1.
  */
-static int dra7xx_pcie_ep_unaligned_memaccess(struct device *dev)
+static int dra7xx_pcie_unaligned_memaccess(struct device *dev)
 {
 	int ret;
 	struct device_node *np = dev->of_node;

@@ -704,6 +704,11 @@ static int __init dra7xx_pcie_probe(stru
 
 		dra7xx_pcie_writel(dra7xx, PCIECTRL_TI_CONF_DEVICE_TYPE,
 				   DEVICE_TYPE_RC);
+
+		ret = dra7xx_pcie_unaligned_memaccess(dev);
+		if (ret)
+			dev_err(dev, "WA for Errata i870 not applied\n");
+
 		ret = dra7xx_add_pcie_port(dra7xx, pdev);
 		if (ret < 0)
 			goto err_gpio;

@@ -717,7 +722,7 @@ static int __init dra7xx_pcie_probe(stru
 		dra7xx_pcie_writel(dra7xx, PCIECTRL_TI_CONF_DEVICE_TYPE,
 				   DEVICE_TYPE_EP);
 
-		ret = dra7xx_pcie_ep_unaligned_memaccess(dev);
+		ret = dra7xx_pcie_unaligned_memaccess(dev);
 		if (ret)
 			goto err_gpio;
 

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

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

From: "Horia Geantă" <[email protected]>

[ Upstream commit aae733a3f46f5ef338fbdde26e14cbb205a23de0 ]

Fix the following sparse endianness warnings:

drivers/crypto/caam/regs.h:95:1: sparse: incorrect type in return expression (different base types) @@ expected unsigned int @@ got restricted __le32unsigned int @@
drivers/crypto/caam/regs.h:95:1: expected unsigned int
drivers/crypto/caam/regs.h:95:1: got restricted __le32 [usertype] <noident>
drivers/crypto/caam/regs.h:95:1: sparse: incorrect type in return expression (different base types) @@ expected unsigned int @@ got restricted __be32unsigned int @@
drivers/crypto/caam/regs.h:95:1: expected unsigned int
drivers/crypto/caam/regs.h:95:1: got restricted __be32 [usertype] <noident>

drivers/crypto/caam/regs.h:92:1: sparse: cast to restricted __le32 drivers/crypto/caam/regs.h:92:1: sparse: cast to restricted __be32

---
 drivers/crypto/caam/regs.h |   28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

@@ -70,22 +70,22 @@
 extern bool caam_little_end;
 extern bool caam_imx;
 
-#define caam_to_cpu(len)				\
-static inline u##len caam##len ## _to_cpu(u##len val)	\
-{							\
-	if (caam_little_end)				\
-		return le##len ## _to_cpu(val);		\
-	else						\
-		return be##len ## _to_cpu(val);		\
+#define caam_to_cpu(len)						\
+static inline u##len caam##len ## _to_cpu(u##len val)			\
+{									\
+	if (caam_little_end)						\
+		return le##len ## _to_cpu((__force __le##len)val);	\
+	else								\
+		return be##len ## _to_cpu((__force __be##len)val);	\
 }
 
-#define cpu_to_caam(len)				\
-static inline u##len cpu_to_caam##len(u##len val)	\
-{							\
-	if (caam_little_end)				\
-		return cpu_to_le##len(val);		\
-	else						\
-		return cpu_to_be##len(val);		\
+#define cpu_to_caam(len)					\
+static inline u##len cpu_to_caam##len(u##len val)		\
+{								\
+	if (caam_little_end)					\
+		return (__force u##len)cpu_to_le##len(val);	\
+	else							\
+		return (__force u##len)cpu_to_be##len(val);	\
 }
 
 caam_to_cpu(16)

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

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

From: Loic Poulain <[email protected]>

[ Upstream commit 8b97d73c4d72a2abf58f8e49062a7ee1e5f1334e ]

The ChipIdea IRQ is disabled before scheduling the otg work and re-enabled on otg work completion. However if the job is already scheduled we have to undo the effect of disable_irq int order to balance the IRQ disable-depth value.

---
 drivers/usb/chipidea/otg.h |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -17,7 +17,8 @@ void ci_handle_vbus_change(struct ci_hdr
 static inline void ci_otg_queue_work(struct ci_hdrc *ci)
 {
 	disable_irq_nosync(ci->irq);
-	queue_work(ci->wq, &ci->work);
+	if (queue_work(ci->wq, &ci->work) == false)
+		enable_irq(ci->irq);
 }
 
 #endif /* __DRIVERS_USB_CHIPIDEA_OTG_H */

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

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

From: Casey Schaufler <[email protected]>

[ Upstream commit dcb569cf6ac99ca899b8109c128b6ae52477a015 ]

This fixes a pair of problems in the Smack ptrace checks related to checking capabilities. In both cases, as reported by Lukasz Pawelczyk, the raw capability calls are used rather than the Smack wrapper that check addition restrictions. In one case, as reported by Jann Horn, the wrong task is being checked for capabilities.

---
 security/smack/smack_lsm.c |   13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

@@ -420,6 +420,7 @@ static int smk_ptrace_rule_check(struct
 	struct smk_audit_info ad, *saip = NULL;
 	struct task_smack *tsp;
 	struct smack_known *tracer_known;
+	const struct cred *tracercred;
 
 	if ((mode & PTRACE_MODE_NOAUDIT) == 0) {
 		smk_ad_init(&ad, func, LSM_AUDIT_DATA_TASK);

@@ -428,7 +429,8 @@ static int smk_ptrace_rule_check(struct
 	}
 
 	rcu_read_lock();
-	tsp = __task_cred(tracer)->security;
+	tracercred = __task_cred(tracer);
+	tsp = tracercred->security;
 	tracer_known = smk_of_task(tsp);
 
 	if ((mode & PTRACE_MODE_ATTACH) &&

@@ -438,7 +440,7 @@ static int smk_ptrace_rule_check(struct
 			rc = 0;
 		else if (smack_ptrace_rule == SMACK_PTRACE_DRACONIAN)
 			rc = -EACCES;
-		else if (capable(CAP_SYS_PTRACE))
+		else if (smack_privileged_cred(CAP_SYS_PTRACE, tracercred))
 			rc = 0;
 		else
 			rc = -EACCES;

@@ -1840,6 +1842,7 @@ static int smack_file_send_sigiotask(str
 {
 	struct smack_known *skp;
 	struct smack_known *tkp = smk_of_task(tsk->cred->security);
+	const struct cred *tcred;
 	struct file *file;
 	int rc;
 	struct smk_audit_info ad;

@@ -1853,8 +1856,12 @@ static int smack_file_send_sigiotask(str
 	skp = file->f_security;
 	rc = smk_access(skp, tkp, MAY_DELIVER, NULL);
 	rc = smk_bu_note("sigiotask", skp, tkp, MAY_DELIVER, rc);
-	if (rc != 0 && has_capability(tsk, CAP_MAC_OVERRIDE))
+
+	rcu_read_lock();
+	tcred = __task_cred(tsk);
+	if (rc != 0 && smack_privileged_cred(CAP_MAC_OVERRIDE, tcred))
 		rc = 0;
+	rcu_read_unlock();
 
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_TASK);
 	smk_ad_setfield_u_tsk(&ad, tsk);

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

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

From: Waiman Long <[email protected]>

[ Upstream commit cfb03be6c7e8a1591285849c361d67b09f5149f7 ]

The following lockdep splat was observed:

[ 1222.241750] ======================================================
[ 1222.271301] WARNING: possible circular locking dependency detected
[ 1222.301060] 4.16.0-10.el8+5.x86_64+debug #1 Not tainted
[ 1222.326659] ------------------------------------------------------
[ 1222.356565] systemd-shutdow/1 is trying to acquire lock:
[ 1222.382660]  ((&ioat_chan->timer)){+.-.}, at: [<00000000f71e1a28>] del_timer_sync+0x5/0xf0
[ 1222.422928]
[ 1222.422928] but task is already holding lock:
[ 1222.451743]  (&(&ioat_chan->prep_lock)->rlock){+.-.}, at: [<000000008ea98b12>] ioat_shutdown+0x86/0x100 [ioatdma]
   :
[ 1223.524987] Chain exists of:
[ 1223.524987]   (&ioat_chan->timer) --> &(&ioat_chan->cleanup_lock)->rlock --> &(&ioat_chan->prep_lock)->rlock
[ 1223.524987]
[ 1223.594082]  Possible unsafe locking scenario:
[ 1223.594082]
[ 1223.622630]        CPU0                    CPU1
[ 1223.645080]        ----                    ----
[ 1223.667404]   lock(&(&ioat_chan->prep_lock)->rlock);
[ 1223.691535]                                lock(&(&ioat_chan->cleanup_lock)->rlock);
[ 1223.728657]                                lock(&(&ioat_chan->prep_lock)->rlock);
[ 1223.765122]   lock((&ioat_chan->timer));
[ 1223.784095]
[ 1223.784095]  *** DEADLOCK ***
[ 1223.784095]
[ 1223.813492] 4 locks held by systemd-shutdow/1:
[ 1223.834677]  #0:  (reboot_mutex){+.+.}, at: [<0000000056d33456>] SYSC_reboot+0x10f/0x300
[ 1223.873310]  #1:  (&dev->mutex){....}, at: [<00000000258dfdd7>] device_shutdown+0x1c8/0x660
[ 1223.913604]  #2:  (&dev->mutex){....}, at: [<0000000068331147>] device_shutdown+0x1d6/0x660
[ 1223.954000]  #3:  (&(&ioat_chan->prep_lock)->rlock){+.-.}, at: [<000000008ea98b12>] ioat_shutdown+0x86/0x100 [ioatdma]

In the ioat_shutdown() function:

	spin_lock_bh(&ioat_chan->prep_lock);
	set_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
	del_timer_sync(&ioat_chan->timer);
	spin_unlock_bh(&ioat_chan->prep_lock);

According to the synchronization rule for the del_timer_sync() function, the caller must not hold locks which would prevent completion of the timer's handler.

The timer structure has its own lock that manages its synchronization. Setting the IOAT_CHAN_DOWN bit should prevent other CPUs from trying to use that device anyway, there is probably no need to call del_timer_sync() while holding the prep_lock. So the del_timer_sync() call is now moved outside of the prep_lock critical section to prevent the circular lock dependency.

---
 drivers/dma/ioat/init.c |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

@@ -1205,8 +1205,15 @@ static void ioat_shutdown(struct pci_dev
 
 		spin_lock_bh(&ioat_chan->prep_lock);
 		set_bit(IOAT_CHAN_DOWN, &ioat_chan->state);
-		del_timer_sync(&ioat_chan->timer);
 		spin_unlock_bh(&ioat_chan->prep_lock);
+		/*
+		 * Synchronization rule for del_timer_sync():
+		 *  - The caller must not hold locks which would prevent
+		 *    completion of the timer's handler.
+		 * So prep_lock cannot be held before calling it.
+		 */
+		del_timer_sync(&ioat_chan->timer);
+
 		/* this should quiesce then reset */
 		ioat_reset_hw(ioat_chan);
 	}

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

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

From: Stephen Boyd <[email protected]>

[ Upstream commit 20edec388277b62ddfddb8b2b376a937a2cd6d1b ]

Both callers of coreboot_table_init() ioremap the pointer that comes in but they don't unmap the memory on failure. Both of them also fail probe immediately with the return value of coreboot_table_init(), leaking a mapping when it fails. The mapping isn't necessary at all after devices are populated either, so we can just drop the mapping here when we exit the function. Let's do that to simplify the code a bit and plug the leak.

---
 drivers/firmware/google/coreboot_table.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

@@ -110,7 +110,8 @@ int coreboot_table_init(struct device *d
 
 	if (strncmp(header.signature, "LBIO", sizeof(header.signature))) {
 		pr_warn("coreboot_table: coreboot table missing or corrupt!\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out;
 	}
 
 	ptr_entry = (void *)ptr_header + header.header_bytes;

@@ -137,7 +138,8 @@ int coreboot_table_init(struct device *d
 
 		ptr_entry += entry.size;
 	}
-
+out:
+	iounmap(ptr);
 	return ret;
 }
 EXPORT_SYMBOL(coreboot_table_init);

@@ -146,7 +148,6 @@ int coreboot_table_exit(void)
 {
 	if (ptr_header) {
 		bus_unregister(&coreboot_bus_type);
-		iounmap(ptr_header);
 		ptr_header = NULL;
 	}
 

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

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

From: Moni Shoua <[email protected]>

[ Upstream commit 99ed748e878a99c6c7b87bbec063eefd9e47cb42 ]

The transition is allowed from any state and the atrribute mask must be IB_QP_STATE.

---
 drivers/infiniband/hw/mlx5/qp.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -3264,7 +3264,9 @@ static bool modify_dci_qp_is_ok(enum ib_
 	int req = IB_QP_STATE;
 	int opt = 0;
 
-	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
+	if (new_state == IB_QPS_RESET) {
+		return is_valid_mask(attr_mask, req, opt);
+	} else if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
 		req |= IB_QP_PKEY_INDEX | IB_QP_PORT;
 		return is_valid_mask(attr_mask, req, opt);
 	} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_INIT) {

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

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

From: Alexandre Belloni <[email protected]>

[ Upstream commit ae61cf5b9913027c6953a79ed3894da4f47061bd ]

When both uio and the uio drivers are built in the kernel, it is possible for a driver to register devices before the uio class is registered.

This may result in a NULL pointer dereference later on in get_device_parent() when accessing the class glue_dirs spinlock.

The trace looks like that:

Unable to handle kernel NULL pointer dereference at virtual address 00000140
[...]
[<ffff0000089cc234>] _raw_spin_lock+0x14/0x48
[<ffff0000084f56bc>] device_add+0x154/0x6a0
[<ffff0000084f5e48>] device_create_groups_vargs+0x120/0x128
[<ffff0000084f5edc>] device_create+0x54/0x60
[<ffff0000086e72c0>] __uio_register_device+0x120/0x4a8
[<ffff000008528b7c>] jaguar2_pci_probe+0x2d4/0x558
[<ffff0000083fc18c>] local_pci_probe+0x3c/0xb8
[<ffff0000083fd81c>] pci_device_probe+0x11c/0x180
[<ffff0000084f88bc>] driver_probe_device+0x22c/0x2d8
[<ffff0000084f8a24>] __driver_attach+0xbc/0xc0
[<ffff0000084f69fc>] bus_for_each_dev+0x4c/0x98
[<ffff0000084f81b8>] driver_attach+0x20/0x28
[<ffff0000084f7d08>] bus_add_driver+0x1b8/0x228
[<ffff0000084f93c0>] driver_register+0x60/0xf8
[<ffff0000083fb918>] __pci_register_driver+0x40/0x48

Return EPROBE_DEFER in that case so the driver can register the device later.

---
 drivers/uio/uio.c |    9 +++++++++
 1 file changed, 9 insertions(+)

@@ -275,6 +275,8 @@ static struct class uio_class = {
 	.dev_groups = uio_groups,
 };
 
+bool uio_class_registered;
+
 /*
  * device functions
  */

@@ -877,6 +879,9 @@ static int init_uio_class(void)
 		printk(KERN_ERR "class_register failed for uio\n");
 		goto err_class_register;
 	}
+
+	uio_class_registered = true;
+
 	return 0;
 
 err_class_register:

@@ -887,6 +892,7 @@ exit:
 
 static void release_uio_class(void)
 {
+	uio_class_registered = false;
 	class_unregister(&uio_class);
 	uio_major_cleanup();
 }

@@ -913,6 +919,9 @@ int __uio_register_device(struct module
 	struct uio_device *idev;
 	int ret = 0;
 
+	if (!uio_class_registered)
+		return -EPROBE_DEFER;
+
 	if (!parent || !info || !info->name || !info->version)
 		return -EINVAL;
 

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

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

From: James Smart <[email protected]>

[ Upstream commit 0ef01a2d95fd62bb4f536e7ce4d5e8e74b97a244 ]

When running an mds diagnostic that passes frames with the switch, soft lockups are detected. The driver is in a CQE processing loop and has sufficient amount of traffic that it never exits the ring processing routine, thus the "lockup".

Cap the number of elements in the work processing routine to 64 elements. This ensures that the cpu will be given up and the handler reschedule to process additional items.

---
 drivers/scsi/lpfc/lpfc_sli.c |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -3790,6 +3790,7 @@ lpfc_sli_handle_slow_ring_event_s4(struc
 	struct hbq_dmabuf *dmabuf;
 	struct lpfc_cq_event *cq_event;
 	unsigned long iflag;
+	int count = 0;
 
 	spin_lock_irqsave(&phba->hbalock, iflag);
 	phba->hba_flag &= ~HBA_SP_QUEUE_EVT;

@@ -3811,16 +3812,22 @@ lpfc_sli_handle_slow_ring_event_s4(struc
 			if (irspiocbq)
 				lpfc_sli_sp_handle_rspiocb(phba, pring,
 							   irspiocbq);
+			count++;
 			break;
 		case CQE_CODE_RECEIVE:
 		case CQE_CODE_RECEIVE_V1:
 			dmabuf = container_of(cq_event, struct hbq_dmabuf,
 					      cq_event);
 			lpfc_sli4_handle_received_buffer(phba, dmabuf);
+			count++;
 			break;
 		default:
 			break;
 		}
+
+		/* Limit the number of events to 64 to avoid soft lockups */
+		if (count == 64)
+			break;
 	}
 }
 

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

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

From: James Smart <[email protected]>

[ Upstream commit ca7fb76e091f889cfda1287c07a9358f73832b39 ]

On io completion, the driver is taking an adapter wide lock and nulling the scsi command back pointer. The nulling of the back pointer is to signify the io was completed and the scsi_done() routine was called. However, the routine makes no check to see if the abort routine had done the same thing and possibly nulled the pointer. Thus it may doubly-complete the io.

Make the following mods:

- Check to make sure forward progress (call scsi_done()) only happens if the command pointer was non-null.

- As the taking of the lock, which is adapter wide, is very costly on a system under load, null the pointer using an xchg operation rather than under lock.

---
 drivers/scsi/lpfc/lpfc_scsi.c |   14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

@@ -4140,9 +4140,17 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba
 	}
 	lpfc_scsi_unprep_dma_buf(phba, lpfc_cmd);
 
-	spin_lock_irqsave(&phba->hbalock, flags);
-	lpfc_cmd->pCmd = NULL;
-	spin_unlock_irqrestore(&phba->hbalock, flags);
+	/* If pCmd was set to NULL from abort path, do not call scsi_done */
+	if (xchg(&lpfc_cmd->pCmd, NULL) == NULL) {
+		lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP,
+				 "0711 FCP cmd already NULL, sid: 0x%06x, "
+				 "did: 0x%06x, oxid: 0x%04x\n",
+				 vport->fc_myDID,
+				 (pnode) ? pnode->nlp_DID : 0,
+				 phba->sli_rev == LPFC_SLI_REV4 ?
+				 lpfc_cmd->cur_iocbq.sli4_xritag : 0xffff);
+		return;
+	}
 
 	/* The sdev is not guaranteed to be valid post scsi_done upcall. */
 	cmd->scsi_done(cmd);

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

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

From: Zhikang Zhang <[email protected]>

[ Upstream commit b430f7263673eab1dc40e662ae3441a9619d16b8 ]

In the call trace below, we might sleep in function dput().

So in order to avoid sleeping under spin_lock, we remove f2fs_mark_inode_dirty_sync from __try_update_largest_extent && __drop_largest_extent.

BUG: sleeping function called from invalid context at fs/dcache.c:796
Call trace:
	dump_backtrace+0x0/0x3f4
	show_stack+0x24/0x30
	dump_stack+0xe0/0x138
	___might_sleep+0x2a8/0x2c8
	__might_sleep+0x78/0x10c
	dput+0x7c/0x750
	block_dump___mark_inode_dirty+0x120/0x17c
	__mark_inode_dirty+0x344/0x11f0
	f2fs_mark_inode_dirty_sync+0x40/0x50
	__insert_extent_tree+0x2e0/0x2f4
	f2fs_update_extent_tree_range+0xcf4/0xde8
	f2fs_update_extent_cache+0x114/0x12c
	f2fs_update_data_blkaddr+0x40/0x50
	write_data_page+0x150/0x314
	do_write_data_page+0x648/0x2318
	__write_data_page+0xdb4/0x1640
	f2fs_write_cache_pages+0x768/0xafc
	__f2fs_write_data_pages+0x590/0x1218
	f2fs_write_data_pages+0x64/0x74
	do_writepages+0x74/0xe4
	__writeback_single_inode+0xdc/0x15f0
	writeback_sb_inodes+0x574/0xc98
	__writeback_inodes_wb+0x190/0x204
	wb_writeback+0x730/0xf14
	wb_check_old_data_flush+0x1bc/0x1c8
	wb_workfn+0x554/0xf74
	process_one_work+0x440/0x118c
	worker_thread+0xac/0x974
	kthread+0x1a0/0x1c8
	ret_from_fork+0x10/0x1c

---
 fs/f2fs/extent_cache.c |   51 ++++++++++++++++++++++++++++++-------------------
 fs/f2fs/f2fs.h         |    7 +++---
 2 files changed, 36 insertions(+), 22 deletions(-)

@@ -308,14 +308,13 @@ static unsigned int __free_extent_tree(s
 	return count - atomic_read(&et->node_cnt);
 }
 
-static void __drop_largest_extent(struct inode *inode,
+static void __drop_largest_extent(struct extent_tree *et,
 					pgoff_t fofs, unsigned int len)
 {
-	struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest;
-
-	if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) {
-		largest->len = 0;
-		f2fs_mark_inode_dirty_sync(inode, true);
+	if (fofs < et->largest.fofs + et->largest.len &&
+			fofs + len > et->largest.fofs) {
+		et->largest.len = 0;
+		et->largest_updated = true;
 	}
 }
 

@@ -416,12 +415,11 @@ out:
 	return ret;
 }
 
-static struct extent_node *__try_merge_extent_node(struct inode *inode,
+static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi,
 				struct extent_tree *et, struct extent_info *ei,
 				struct extent_node *prev_ex,
 				struct extent_node *next_ex)
 {
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_node *en = NULL;
 
 	if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) {

@@ -443,7 +441,7 @@ static struct extent_node *__try_merge_e
 	if (!en)
 		return NULL;
 
-	__try_update_largest_extent(inode, et, en);
+	__try_update_largest_extent(et, en);
 
 	spin_lock(&sbi->extent_lock);
 	if (!list_empty(&en->list)) {

@@ -454,12 +452,11 @@ static struct extent_node *__try_merge_e
 	return en;
 }
 
-static struct extent_node *__insert_extent_tree(struct inode *inode,
+static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi,
 				struct extent_tree *et, struct extent_info *ei,
 				struct rb_node **insert_p,
 				struct rb_node *insert_parent)
 {
-	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
 	struct extent_node *en = NULL;

@@ -476,7 +473,7 @@ do_insert:
 	if (!en)
 		return NULL;
 
-	__try_update_largest_extent(inode, et, en);
+	__try_update_largest_extent(et, en);
 
 	/* update in global extent list */
 	spin_lock(&sbi->extent_lock);

@@ -497,6 +494,7 @@ static void f2fs_update_extent_tree_rang
 	struct rb_node **insert_p = NULL, *insert_parent = NULL;
 	unsigned int end = fofs + len;
 	unsigned int pos = (unsigned int)fofs;
+	bool updated = false;
 
 	if (!et)
 		return;

@@ -517,7 +515,7 @@ static void f2fs_update_extent_tree_rang
 	 * drop largest extent before lookup, in case it's already
 	 * been shrunk from extent tree
 	 */
-	__drop_largest_extent(inode, fofs, len);
+	__drop_largest_extent(et, fofs, len);
 
 	/* 1. lookup first extent node in range [fofs, fofs + len - 1] */
 	en = (struct extent_node *)f2fs_lookup_rb_tree_ret(&et->root,

@@ -550,7 +548,7 @@ static void f2fs_update_extent_tree_rang
 				set_extent_info(&ei, end,
 						end - dei.fofs + dei.blk,
 						org_end - end);
-				en1 = __insert_extent_tree(inode, et, &ei,
+				en1 = __insert_extent_tree(sbi, et, &ei,
 							NULL, NULL);
 				next_en = en1;
 			} else {

@@ -570,7 +568,7 @@ static void f2fs_update_extent_tree_rang
 		}
 
 		if (parts)
-			__try_update_largest_extent(inode, et, en);
+			__try_update_largest_extent(et, en);
 		else
 			__release_extent_node(sbi, et, en);
 

@@ -590,15 +588,16 @@ static void f2fs_update_extent_tree_rang
 	if (blkaddr) {
 
 		set_extent_info(&ei, fofs, blkaddr, len);
-		if (!__try_merge_extent_node(inode, et, &ei, prev_en, next_en))
-			__insert_extent_tree(inode, et, &ei,
+		if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en))
+			__insert_extent_tree(sbi, et, &ei,
 						insert_p, insert_parent);
 
 		/* give up extent_cache, if split and small updates happen */
 		if (dei.len >= 1 &&
 				prev.len < F2FS_MIN_EXTENT_LEN &&
 				et->largest.len < F2FS_MIN_EXTENT_LEN) {
-			__drop_largest_extent(inode, 0, UINT_MAX);
+			et->largest.len = 0;
+			et->largest_updated = true;
 			set_inode_flag(inode, FI_NO_EXTENT);
 		}
 	}

@@ -606,7 +605,15 @@ static void f2fs_update_extent_tree_rang
 	if (is_inode_flag_set(inode, FI_NO_EXTENT))
 		__free_extent_tree(sbi, et);
 
+	if (et->largest_updated) {
+		et->largest_updated = false;
+		updated = true;
+	}
+
 	write_unlock(&et->lock);
+
+	if (updated)
+		f2fs_mark_inode_dirty_sync(inode, true);
 }
 
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)

@@ -705,6 +712,7 @@ void f2fs_drop_extent_tree(struct inode
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_tree *et = F2FS_I(inode)->extent_tree;
+	bool updated = false;
 
 	if (!f2fs_may_extent_tree(inode))
 		return;

@@ -713,8 +721,13 @@ void f2fs_drop_extent_tree(struct inode
 
 	write_lock(&et->lock);
 	__free_extent_tree(sbi, et);
-	__drop_largest_extent(inode, 0, UINT_MAX);
+	if (et->largest.len) {
+		et->largest.len = 0;
+		updated = true;
+	}
 	write_unlock(&et->lock);
+	if (updated)
+		f2fs_mark_inode_dirty_sync(inode, true);
 }
 
 void f2fs_destroy_extent_tree(struct inode *inode)

@@ -556,6 +556,7 @@ struct extent_tree {
 	struct list_head list;		/* to be used by sbi->zombie_list */
 	rwlock_t lock;			/* protect extent info rb-tree */
 	atomic_t node_cnt;		/* # of extent node in rb-tree*/
+	bool largest_updated;		/* largest extent updated */
 };
 
 /*

@@ -736,12 +737,12 @@ static inline bool __is_front_mergeable(
 }
 
 extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
-static inline void __try_update_largest_extent(struct inode *inode,
-			struct extent_tree *et, struct extent_node *en)
+static inline void __try_update_largest_extent(struct extent_tree *et,
+						struct extent_node *en)
 {
 	if (en->ei.len > et->largest.len) {
 		et->largest = en->ei;
-		f2fs_mark_inode_dirty_sync(inode, true);
+		et->largest_updated = true;
 	}
 }
 

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

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

From: Yunlei He <[email protected]>

[ Upstream commit cda9cc595f0bb6ffa51a4efc4b6533dfa4039b4c ]

Now, we depend on fsck to ensure quota file data is ok, so we scan whole partition if checkpoint without umount flag. It's same for quota off error case, which may make quota file data inconsistent.

generic/019 reports below error:

__quota_error: 1160 callbacks suppressed
Quota error (device zram1): write_blk: dquota write failed
Quota error (device zram1): qtree_write_dquot: Error -28 occurred while creating quota Quota error (device zram1): write_blk: dquota write failed
Quota error (device zram1): qtree_write_dquot: Error -28 occurred while creating quota Quota error (device zram1): write_blk: dquota write failed
Quota error (device zram1): qtree_write_dquot: Error -28 occurred while creating quota Quota error (device zram1): write_blk: dquota write failed
Quota error (device zram1): qtree_write_dquot: Error -28 occurred while creating quota Quota error (device zram1): write_blk: dquota write failed
Quota error (device zram1): qtree_write_dquot: Error -28 occurred while creating quota
VFS: Busy inodes after unmount of zram1. Self-destruct in 5 seconds. Have a nice day...

If we failed in below path due to fail to write dquot block, we will miss to release quota inode, fix it.

- f2fs_put_super
- f2fs_quota_off_umount
- f2fs_quota_off
- f2fs_quota_sync <-- failed
- dquot_quota_off <-- missed to call

---
 fs/f2fs/super.c |   19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

@@ -1820,7 +1820,9 @@ static int f2fs_quota_off(struct super_b
 	if (!inode || !igrab(inode))
 		return dquot_quota_off(sb, type);
 
-	f2fs_quota_sync(sb, type);
+	err = f2fs_quota_sync(sb, type);
+	if (err)
+		goto out_put;
 
 	err = dquot_quota_off(sb, type);
 	if (err || f2fs_sb_has_quota_ino(sb))

@@ -1839,9 +1841,20 @@ out_put:
 void f2fs_quota_off_umount(struct super_block *sb)
 {
 	int type;
+	int err;
 
-	for (type = 0; type < MAXQUOTAS; type++)
-		f2fs_quota_off(sb, type);
+	for (type = 0; type < MAXQUOTAS; type++) {
+		err = f2fs_quota_off(sb, type);
+		if (err) {
+			int ret = dquot_quota_off(sb, type);
+
+			f2fs_msg(sb, KERN_ERR,
+				"Fail to turn off disk quota "
+				"(type: %d, err: %d, ret:%d), Please "
+				"run fsck to fix it.", type, err, ret);
+			set_sbi_flag(F2FS_SB(sb), SBI_NEED_FSCK);
+		}
+	}
 }
 
 static int f2fs_get_projid(struct inode *inode, kprojid_t *projid)

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

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

From: "Eric W. Biederman" <[email protected]>

[ Upstream commit 3597dfe01d12f570bc739da67f857fd222a3ea66 ]

Instead of playing whack-a-mole and changing SEND_SIG_PRIV to SEND_SIG_FORCED throughout the kernel to ensure a pid namespace init gets signals sent by the kernel, stop allowing a pid namespace init to ignore SIGKILL or SIGSTOP sent by the kernel. A pid namespace init is only supposed to be able to ignore signals sent from itself and children with SIG_DFL.

---
 kernel/signal.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -1009,7 +1009,7 @@ static int __send_signal(int sig, struct
 
 	result = TRACE_SIGNAL_IGNORED;
 	if (!prepare_signal(sig, t,
-			from_ancestor_ns || (info == SEND_SIG_FORCED)))
+			from_ancestor_ns || (info == SEND_SIG_PRIV) || (info == SEND_SIG_FORCED)))
 		goto ret;
 
 	pending = group ? &t->signal->shared_pending : &t->pending;

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

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

From: Alexandre Belloni <[email protected]>

[ Upstream commit 9612f8f503804d2fd2f63aa6ba1e58bba4612d96 ]

The IRQ work is added before the struct rtc is allocated and registered, but this struct is used in the IRQ handler. This may lead to a NULL pointer dereference.

Switch to devm_rtc_allocate_device/rtc_register_device to allocate the rtc before calling menelaus_add_irq_work.

Also, this solves a possible leak as the RTC is never released.

---
 drivers/mfd/menelaus.c |   13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

@@ -1094,6 +1094,7 @@ static void menelaus_rtc_alarm_work(stru
 static inline void menelaus_rtc_init(struct menelaus_chip *m)
 {
 	int	alarm = (m->client->irq > 0);
+	int	err;
 
 	/* assume 32KDETEN pin is pulled high */
 	if (!(menelaus_read_reg(MENELAUS_OSC_CTRL) & 0x80)) {

@@ -1101,6 +1102,12 @@ static inline void menelaus_rtc_init(str
 		return;
 	}
 
+	m->rtc = devm_rtc_allocate_device(&m->client->dev);
+	if (IS_ERR(m->rtc))
+		return;
+
+	m->rtc->ops = &menelaus_rtc_ops;
+
 	/* support RTC alarm; it can issue wakeups */
 	if (alarm) {
 		if (menelaus_add_irq_work(MENELAUS_RTCALM_IRQ,

@@ -1125,10 +1132,8 @@ static inline void menelaus_rtc_init(str
 		menelaus_write_reg(MENELAUS_RTC_CTRL, m->rtc_control);
 	}
 
-	m->rtc = rtc_device_register(DRIVER_NAME,
-			&m->client->dev,
-			&menelaus_rtc_ops, THIS_MODULE);
-	if (IS_ERR(m->rtc)) {
+	err = rtc_register_device(m->rtc);
+	if (err) {
 		if (alarm) {
 			menelaus_remove_irq_work(MENELAUS_RTCALM_IRQ);
 			device_init_wakeup(&m->client->dev, 0);

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

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

From: Paul Cercueil <[email protected]>

[ Upstream commit 54f919a04cf221bc1601d1193682d4379dacacbd ]

The driver calls clk_get() with the clock name set to NULL, which means that the driver could only work when probed from devicetree. From now on, we explicitly require the driver to be probed from devicetree.

---
 drivers/dma/dma-jz4780.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -761,6 +761,11 @@ static int jz4780_dma_probe(struct platf
 	struct resource *res;
 	int i, ret;
 
+	if (!dev->of_node) {
+		dev_err(dev, "This driver must be probed from devicetree\n");
+		return -EINVAL;
+	}
+
 	jzdma = devm_kzalloc(dev, sizeof(*jzdma), GFP_KERNEL);
 	if (!jzdma)
 		return -ENOMEM;

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

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

From: Vijay Immanuel <[email protected]>

[ Upstream commit b97db58557f4aa6d9903f8e1deea6b3d1ed0ba43 ]

Don't reset the resp opcode for a replayed read response. The resp opcode could be in the middle of a write or send sequence, when the duplicate read request was received.
An example sequence is as follows:
- Receive read request for 12KB PSN 20. Transmit read response first, middle and last with PSNs 20,21,22.
- Receive write first PSN 23.
At this point the resp psn is 24 and resp opcode is write first.
- The sender notices that PSN 20 is dropped and retransmits. Receive read request for 12KB PSN 20. Transmit read response first, middle and last with PSNs 20,21,22. The resp opcode is set to -1, the resp psn remains 24.
- Receive write first PSN 23. This is processed by duplicate_request(). The resp opcode remains -1 and resp psn remains 24.
- Receive write middle PSN 24. check_op_seq() reports a missing first error since the resp opcode is -1.

When sending an ack for a duplicate send or write request, use the psn of the previous ack sent. Do not use the psn of a read response for the ack.
An example sequence is as follows:
- Receive write PSN 30. Transmit ACK for PSN 30.
- Receive read request 4KB PSN 31. Transmit read response with PSN 31. The resp psn is now 32.
- The sender notices that PSN 30 is dropped and retransmits. Receive write PSN 30. duplicate_request() sends an ACK with PSN 31. That is incorrect since PSN 31 was a read request.

---
 drivers/infiniband/sw/rxe/rxe_resp.c  |    8 ++++++--
 drivers/infiniband/sw/rxe/rxe_verbs.h |    2 ++
 2 files changed, 8 insertions(+), 2 deletions(-)

@@ -682,6 +682,7 @@ static enum resp_states read_reply(struc
 		rxe_advance_resp_resource(qp);
 
 		res->type		= RXE_READ_MASK;
+		res->replay		= 0;
 
 		res->read.va		= qp->resp.va;
 		res->read.va_org	= qp->resp.va;

@@ -752,7 +753,8 @@ static enum resp_states read_reply(struc
 		state = RESPST_DONE;
 	} else {
 		qp->resp.res = NULL;
-		qp->resp.opcode = -1;
+		if (!res->replay)
+			qp->resp.opcode = -1;
 		if (psn_compare(res->cur_psn, qp->resp.psn) >= 0)
 			qp->resp.psn = res->cur_psn;
 		state = RESPST_CLEANUP;

@@ -814,6 +816,7 @@ static enum resp_states execute(struct r
 
 	/* next expected psn, read handles this separately */
 	qp->resp.psn = (pkt->psn + 1) & BTH_PSN_MASK;
+	qp->resp.ack_psn = qp->resp.psn;
 
 	qp->resp.opcode = pkt->opcode;
 	qp->resp.status = IB_WC_SUCCESS;

@@ -1060,7 +1063,7 @@ static enum resp_states duplicate_reques
 					  struct rxe_pkt_info *pkt)
 {
 	enum resp_states rc;
-	u32 prev_psn = (qp->resp.psn - 1) & BTH_PSN_MASK;
+	u32 prev_psn = (qp->resp.ack_psn - 1) & BTH_PSN_MASK;
 
 	if (pkt->mask & RXE_SEND_MASK ||
 	    pkt->mask & RXE_WRITE_MASK) {

@@ -1103,6 +1106,7 @@ static enum resp_states duplicate_reques
 			res->state = (pkt->psn == res->first_psn) ?
 					rdatm_res_state_new :
 					rdatm_res_state_replay;
+			res->replay = 1;
 
 			/* Reset the resource, except length. */
 			res->read.va_org = iova;

@@ -171,6 +171,7 @@ enum rdatm_res_state {
 
 struct resp_res {
 	int			type;
+	int			replay;
 	u32			first_psn;
 	u32			last_psn;
 	u32			cur_psn;

@@ -195,6 +196,7 @@ struct rxe_resp_info {
 	enum rxe_qp_state	state;
 	u32			msn;
 	u32			psn;
+	u32			ack_psn;
 	int			opcode;
 	int			drop_msg;
 	int			goto_error;

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

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

From: Takashi Iwai <[email protected]>

[ Upstream commit 78c9be61c3a5cd9e2439fd27a5ffad73a81958c7 ]

Introduce a new flag, uc_buffer, to indicate that the controller requires the non-cached pages for stream buffers, either as a chip-specific requirement or specified via snoop=0 option. This improves the code-readability.

Also, this patch fixes the incorrect behavior for C-Media chip where the stream buffers were never handled as non-cached due to the check of driver_type even if you pass snoop=0 option.

---
 sound/pci/hda/hda_controller.h |    1 +
 sound/pci/hda/hda_intel.c      |   11 ++++++++---
 2 files changed, 9 insertions(+), 3 deletions(-)

@@ -160,6 +160,7 @@ struct azx {
 	unsigned int msi:1;
 	unsigned int probing:1; /* codec probing phase */
 	unsigned int snoop:1;
+	unsigned int uc_buffer:1; /* non-cached pages for stream buffers */
 	unsigned int align_buffer_size:1;
 	unsigned int region_requested:1;
 	unsigned int disabled:1; /* disabled by vga_switcheroo */

@@ -410,7 +410,7 @@ static void __mark_pages_wc(struct azx *
 #ifdef CONFIG_SND_DMA_SGBUF
 	if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_SG) {
 		struct snd_sg_buf *sgbuf = dmab->private_data;
-		if (chip->driver_type == AZX_DRIVER_CMEDIA)
+		if (!chip->uc_buffer)
 			return; /* deal with only CORB/RIRB buffers */
 		if (on)
 			set_pages_array_wc(sgbuf->page_table, sgbuf->pages);

@@ -1636,6 +1636,7 @@ static void azx_check_snoop_available(st
 		dev_info(chip->card->dev, "Force to %s mode by module option\n",
 			 snoop ? "snoop" : "non-snoop");
 		chip->snoop = snoop;
+		chip->uc_buffer = !snoop;
 		return;
 	}
 

@@ -1656,8 +1657,12 @@ static void azx_check_snoop_available(st
 		snoop = false;
 
 	chip->snoop = snoop;
-	if (!snoop)
+	if (!snoop) {
 		dev_info(chip->card->dev, "Force to non-snoop mode\n");
+		/* C-Media requires non-cached pages only for CORB/RIRB */
+		if (chip->driver_type != AZX_DRIVER_CMEDIA)
+			chip->uc_buffer = true;
+	}
 }
 
 static void azx_probe_work(struct work_struct *work)

@@ -2096,7 +2101,7 @@ static void pcm_mmap_prepare(struct snd_
 #ifdef CONFIG_X86
 	struct azx_pcm *apcm = snd_pcm_substream_chip(substream);
 	struct azx *chip = apcm->chip;
-	if (!azx_snoop(chip) && chip->driver_type != AZX_DRIVER_CMEDIA)
+	if (chip->uc_buffer)
 		area->vm_page_prot = pgprot_writecombine(area->vm_page_prot);
 #endif
 }

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

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

From: Prarit Bhargava <[email protected]>

[ Upstream commit 8c22e2f695920ebd94f9a53bcf2a65eb36d4dba1 ]

The msr_pstate data is only 63 bits long and should be 64 bits.

Add in the missing bit from res1 for AMD Family 0x17.

Reference: https://www.amd.com/system/files/TechDocs/54945_PPR_Family_17h_Models_00h-0Fh.pdf, page 138.

---
 tools/power/cpupower/utils/helpers/amd.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -33,7 +33,7 @@ union msr_pstate {
 		unsigned vid:8;
 		unsigned iddval:8;
 		unsigned idddiv:2;
-		unsigned res1:30;
+		unsigned res1:31;
 		unsigned en:1;
 	} fam17h_bits;
 	unsigned long long val;

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

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

From: Jaegeuk Kim <[email protected]>

commit 164a63fa6b384e30ceb96ed80bc7dc3379bc0960 upstream.

This reverts commit 66110abc4c931f879d70e83e1281f891699364bf.

If we clear the cold data flag out of the writeback flow, we can miscount -1 by end_io, which incurs a deadlock caused by all I/Os being blocked during heavy GC.

Balancing F2FS Async:
- IO (CP: 1, Data: -1, Flush: ( 0 0 1), Discard: ( ...

GC thread: IRQ
- move_data_page()
- set_page_dirty()
- clear_cold_data()
- f2fs_write_end_io()
- type = WB_DATA_TYPE(page); here, we get wrong type
- dec_page_count(sbi, type);
- f2fs_wait_on_page_writeback()

---
 fs/f2fs/data.c |    4 ----
 1 file changed, 4 deletions(-)

@@ -2501,10 +2501,6 @@ static int f2fs_set_data_page_dirty(stru
 	if (!PageUptodate(page))
 		SetPageUptodate(page);
 
-	/* don't remain PG_checked flag which was set during GC */
-	if (is_cold_data(page))
-		clear_cold_data(page);
-
 	if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) {
 		if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
 			f2fs_register_inmem_page(inode, page);

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

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

From: Chao Yu <[email protected]>

commit ef2a007134b4eaa39264c885999f296577bc87d2 upstream.

Testcase to reproduce this bug:
1. mkfs.f2fs /dev/sdd
2. mount -t f2fs /dev/sdd /mnt/f2fs
3. touch /mnt/f2fs/file
4. sync
5. chattr +A /mnt/f2fs/file
6. xfs_io -f /mnt/f2fs/file -c "fsync"
7. godown /mnt/f2fs
8. umount /mnt/f2fs
9. mount -t f2fs /dev/sdd /mnt/f2fs
10. chattr -A /mnt/f2fs/file
11. xfs_io -f /mnt/f2fs/file -c "fsync"
12. umount /mnt/f2fs
13. mount -t f2fs /dev/sdd /mnt/f2fs
14. lsattr /mnt/f2fs/file

-----------------N- /mnt/f2fs/file

But actually, we expect the corrct result is:

-------A---------N- /mnt/f2fs/file

The reason is in step 9) we missed to recover cold bit flag in inode block, so later, in fsync, we will skip write inode block due to below condition check, result in lossing data in another SPOR.

f2fs_fsync_node_pages()

	if (!IS_DNODE(page) || !is_cold_node(page))
		continue;

Note that, I guess that some non-dir inode has already lost cold bit during POR, so in order to reenable recovery for those inode, let's try to recover cold bit in f2fs_iget() to save more fsynced data.

---
 fs/f2fs/inode.c |    6 ++++++
 fs/f2fs/node.c  |    2 +-
 2 files changed, 7 insertions(+), 1 deletion(-)

@@ -287,6 +287,12 @@ static int do_read_inode(struct inode *i
 	if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode))
 		__recover_inline_status(inode, node_page);
 
+	/* try to recover cold bit for non-dir inode */
+	if (!S_ISDIR(inode->i_mode) && !is_cold_node(node_page)) {
+		set_cold_node(node_page, false);
+		set_page_dirty(node_page);
+	}
+
 	/* get rdev by using inline_info */
 	__get_inode_rdev(inode, ri);
 

@@ -2356,7 +2356,7 @@ retry:
 	if (!PageUptodate(ipage))
 		SetPageUptodate(ipage);
 	fill_node_footer(ipage, ino, ino, 0, true);
-	set_cold_node(page, false);
+	set_cold_node(ipage, false);
 
 	src = F2FS_INODE(page);
 	dst = F2FS_INODE(ipage);

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

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

From: Chao Yu <[email protected]>

commit 4c58ed076875f36dae0f240da1e25e99e5d4afb8 upstream.

Below race can cause reversed reference on dirty count, fix it by relocating __submit_bio() and inc_page_count().

Thread A Thread B
- f2fs_inplace_write_data
- f2fs_submit_page_bio
- __submit_bio
- f2fs_write_end_io
- dec_page_count
- inc_page_count

---
 fs/f2fs/data.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -460,10 +460,10 @@ int f2fs_submit_page_bio(struct f2fs_io_
 
 	bio_set_op_attrs(bio, fio->op, fio->op_flags);
 
-	__submit_bio(fio->sbi, bio, fio->type);
-
 	if (!is_read_io(fio->op))
 		inc_page_count(fio->sbi, WB_DATA_TYPE(fio->page));
+
+	__submit_bio(fio->sbi, bio, fio->type);
 	return 0;
 }
 

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

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

From: Viresh Kumar <[email protected]>

commit 2fbb8670b4ff4454f1c0de510f788d737edc4b90 upstream.

The OPP table was freed, but not the individual OPPs which is done from _dev_pm_opp_remove_table(). Fix it by calling _dev_pm_opp_remove_table() as well.

---
 drivers/opp/of.c |    1 +
 1 file changed, 1 insertion(+)

@@ -425,6 +425,7 @@ static int _of_add_opp_table_v2(struct d
 		dev_err(dev, "Not all nodes have performance state set (%d: %d)\n",
 			count, pstate_count);
 		ret = -ENOENT;
+		_dev_pm_opp_remove_table(opp_table, dev, false);
 		goto put_opp_table;
 	}
 

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

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

From: Viresh Kumar <[email protected]>

commit 672f33198bee21ee91e6af2cb8f67cfc8bc97ec1 upstream.

The cooling device properties, like "#cooling-cells" and "dynamic-power-coefficient", should either be present for all the CPUs of a cluster or none. If these are present only for a subset of CPUs of a cluster then things will start falling apart as soon as the CPUs are brought online in a different order. For example, this will happen because the operating system looks for such properties in the CPU node it is trying to bring up, so that it can register a cooling device.

Add such missing properties.

Fix other missing properties (clocks, OPP, clock latency) as well to make it all work.

---
 arch/arm/boot/dts/exynos3250.dtsi |   16 ++++++++++++++++
 arch/arm/boot/dts/exynos4210.dtsi |   13 +++++++++++++
 arch/arm/boot/dts/exynos4412.dtsi |    9 +++++++++
 arch/arm/boot/dts/exynos5250.dtsi |   23 +++++++++++++++++++++++
 4 files changed, 61 insertions(+)

@@ -78,6 +78,22 @@
 			compatible = "arm,cortex-a7";
 			reg = <1>;
 			clock-frequency = <1000000000>;
+			clocks = <&cmu CLK_ARM_CLK>;
+			clock-names = "cpu";
+			#cooling-cells = <2>;
+
+			operating-points = <
+				1000000 1150000
+				900000  1112500
+				800000  1075000
+				700000  1037500
+				600000  1000000
+				500000  962500
+				400000  925000
+				300000  887500
+				200000  850000
+				100000  850000
+			>;
 		};
 	};
 

@@ -55,6 +55,19 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0x901>;
+			clocks = <&clock CLK_ARM_CLK>;
+			clock-names = "cpu";
+			clock-latency = <160000>;
+
+			operating-points = <
+				1200000 1250000
+				1000000 1150000
+				800000	1075000
+				500000	975000
+				400000	975000
+				200000	950000
+			>;
+			#cooling-cells = <2>; /* min followed by max */
 		};
 	};
 

@@ -49,21 +49,30 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0xA01>;
+			clocks = <&clock CLK_ARM_CLK>;
+			clock-names = "cpu";
 			operating-points-v2 = <&cpu0_opp_table>;
+			#cooling-cells = <2>; /* min followed by max */
 		};
 
 		cpu@a02 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0xA02>;
+			clocks = <&clock CLK_ARM_CLK>;
+			clock-names = "cpu";
 			operating-points-v2 = <&cpu0_opp_table>;
+			#cooling-cells = <2>; /* min followed by max */
 		};
 
 		cpu@a03 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0xA03>;
+			clocks = <&clock CLK_ARM_CLK>;
+			clock-names = "cpu";
 			operating-points-v2 = <&cpu0_opp_table>;
+			#cooling-cells = <2>; /* min followed by max */
 		};
 	};
 

@@ -84,6 +84,29 @@
 			compatible = "arm,cortex-a15";
 			reg = <1>;
 			clock-frequency = <1700000000>;
+			clocks = <&clock CLK_ARM_CLK>;
+			clock-names = "cpu";
+			clock-latency = <140000>;
+
+			operating-points = <
+				1700000 1300000
+				1600000 1250000
+				1500000 1225000
+				1400000 1200000
+				1300000 1150000
+				1200000 1125000
+				1100000 1100000
+				1000000 1075000
+				 900000 1050000
+				 800000 1025000
+				 700000 1012500
+				 600000 1000000
+				 500000  975000
+				 400000  950000
+				 300000  937500
+				 200000  925000
+			>;
+			#cooling-cells = <2>; /* min followed by max */
 		};
 	};
 

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

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

From: Marek Szyprowski <[email protected]>

commit eb9e16d8573e243f8175647f851eb5085dbe97a4 upstream.

Convert Exynos5250 to OPP-v2 bindings. This is a preparation to add proper support for suspend operation point, which cannot be marked in opp-v1.

---
 arch/arm/boot/dts/exynos5250.dtsi |  130 +++++++++++++++++++++++++-------------
 1 file changed, 88 insertions(+), 42 deletions(-)

@@ -54,62 +54,108 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <0>;
-			clock-frequency = <1700000000>;
 			clocks = <&clock CLK_ARM_CLK>;
 			clock-names = "cpu";
-			clock-latency = <140000>;
-
-			operating-points = <
-				1700000 1300000
-				1600000 1250000
-				1500000 1225000
-				1400000 1200000
-				1300000 1150000
-				1200000 1125000
-				1100000 1100000
-				1000000 1075000
-				 900000 1050000
-				 800000 1025000
-				 700000 1012500
-				 600000 1000000
-				 500000  975000
-				 400000  950000
-				 300000  937500
-				 200000  925000
-			>;
+			operating-points-v2 = <&cpu0_opp_table>;
 			#cooling-cells = <2>; /* min followed by max */
 		};
 		cpu@1 {
 			device_type = "cpu";
 			compatible = "arm,cortex-a15";
 			reg = <1>;
-			clock-frequency = <1700000000>;
 			clocks = <&clock CLK_ARM_CLK>;
 			clock-names = "cpu";
-			clock-latency = <140000>;
-
-			operating-points = <
-				1700000 1300000
-				1600000 1250000
-				1500000 1225000
-				1400000 1200000
-				1300000 1150000
-				1200000 1125000
-				1100000 1100000
-				1000000 1075000
-				 900000 1050000
-				 800000 1025000
-				 700000 1012500
-				 600000 1000000
-				 500000  975000
-				 400000  950000
-				 300000  937500
-				 200000  925000
-			>;
+			operating-points-v2 = <&cpu0_opp_table>;
 			#cooling-cells = <2>; /* min followed by max */
 		};
 	};
 
+	cpu0_opp_table: opp_table0 {
+		compatible = "operating-points-v2";
+		opp-shared;
+
+		opp-200000000 {
+			opp-hz = /bits/ 64 <200000000>;
+			opp-microvolt = <925000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-300000000 {
+			opp-hz = /bits/ 64 <300000000>;
+			opp-microvolt = <937500>;
+			clock-latency-ns = <140000>;
+		};
+		opp-400000000 {
+			opp-hz = /bits/ 64 <400000000>;
+			opp-microvolt = <950000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-500000000 {
+			opp-hz = /bits/ 64 <500000000>;
+			opp-microvolt = <975000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-600000000 {
+			opp-hz = /bits/ 64 <600000000>;
+			opp-microvolt = <1000000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-700000000 {
+			opp-hz = /bits/ 64 <700000000>;
+			opp-microvolt = <1012500>;
+			clock-latency-ns = <140000>;
+		};
+		opp-800000000 {
+			opp-hz = /bits/ 64 <800000000>;
+			opp-microvolt = <1025000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-900000000 {
+			opp-hz = /bits/ 64 <900000000>;
+			opp-microvolt = <1050000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-1000000000 {
+			opp-hz = /bits/ 64 <1000000000>;
+			opp-microvolt = <1075000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-1100000000 {
+			opp-hz = /bits/ 64 <1100000000>;
+			opp-microvolt = <1100000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-1200000000 {
+			opp-hz = /bits/ 64 <1200000000>;
+			opp-microvolt = <1125000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-1300000000 {
+			opp-hz = /bits/ 64 <1300000000>;
+			opp-microvolt = <1150000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-1400000000 {
+			opp-hz = /bits/ 64 <1400000000>;
+			opp-microvolt = <1200000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-1500000000 {
+			opp-hz = /bits/ 64 <1500000000>;
+			opp-microvolt = <1225000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-1600000000 {
+			opp-hz = /bits/ 64 <1600000000>;
+			opp-microvolt = <1250000>;
+			clock-latency-ns = <140000>;
+		};
+		opp-1700000000 {
+			opp-hz = /bits/ 64 <1700000000>;
+			opp-microvolt = <1300000>;
+			clock-latency-ns = <140000>;
+		};
+	};
+
 	soc: soc {
 		sysram@2020000 {
 			compatible = "mmio-sram";

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

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

From: Marek Szyprowski <[email protected]>

commit 645b23da6f8b47f295fa87051335d41d139717a5 upstream.

1 GHz CPU OPP is the default boot value for the Exynos5250 SOC, so mark it as suspend OPP. This fixes suspend/resume on Samsung Exynos5250 Snow Chomebook, which was broken since switching to generic cpufreq-dt driver in v4.3.

---
 arch/arm/boot/dts/exynos5250.dtsi |    1 +
 1 file changed, 1 insertion(+)

@@ -118,6 +118,7 @@
 			opp-hz = /bits/ 64 <1000000000>;
 			opp-microvolt = <1075000>;
 			clock-latency-ns = <140000>;
+			opp-suspend;
 		};
 		opp-1100000000 {
 			opp-hz = /bits/ 64 <1100000000>;

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

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

From: Joe Jin <[email protected]>

commit 7250f422da0480d8512b756640f131b9b893ccda upstream.

xen_swiotlb_{alloc,free}_coherent() allocate/free memory based on the order of the pages and not size argument (bytes). This is inconsistent with range_straddles_page_boundary and memset which use the 'size' value, which may lead to not exchanging memory with Xen (range_straddles_page_boundary() returned true). And then the call to xen_swiotlb_free_coherent() would actually try to exchange the memory with Xen, leading to the kernel hitting an BUG (as the hypercall returned an error).

This patch fixes it by making the 'size' variable be of the same size as the amount of memory allocated.

---
 drivers/xen/swiotlb-xen.c |    6 ++++++
 1 file changed, 6 insertions(+)

@@ -303,6 +303,9 @@ xen_swiotlb_alloc_coherent(struct device
 	*/
 	flags &= ~(__GFP_DMA | __GFP_HIGHMEM);
 
+	/* Convert the size to actually allocated. */
+	size = 1UL << (order + XEN_PAGE_SHIFT);
+
 	/* On ARM this function returns an ioremap'ped virtual address for
 	 * which virt_to_phys doesn't return the corresponding physical
 	 * address. In fact on ARM virt_to_phys only works for kernel direct

@@ -351,6 +354,9 @@ xen_swiotlb_free_coherent(struct device
 	 * physical address */
 	phys = xen_bus_to_phys(dev_addr);
 
+	/* Convert the size to actually allocated. */
+	size = 1UL << (order + XEN_PAGE_SHIFT);
+
 	if (((dev_addr + size - 1 <= dma_mask)) ||
 	    range_straddles_page_boundary(phys, size))
 		xen_destroy_contiguous_region(phys, order);

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

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

From: Dr. Greg Wettstein <[email protected]>

commit e487a0f52301293152a6f8c4e217f2a11dd808e3 upstream.

Functionality of the xen-tpmfront driver was lost secondary to the introduction of xenbus multi-page support in commit ccc9d90a9a8b ("xenbus_client: Extend interface to support multi-page ring").

In this commit pointer to location of where the shared page address is stored was being passed to the xenbus_grant_ring() function rather then the address of the shared page itself. This resulted in a situation where the driver would attach to the vtpm-stubdom but any attempt to send a command to the stub domain would timeout.

A diagnostic finding for this regression is the following error message being generated when the xen-tpmfront driver probes for a device:

<3>vtpm vtpm-0: tpm_transmit: tpm_send: error -62

<3>vtpm vtpm-0: A TPM error (-62) occurred attempting to determine the timeouts

This fix is relevant to all kernels from 4.1 forward which is the release in which multi-page xenbus support was introduced.

Daniel De Graaf formulated the fix by code inspection after the regression point was located.

---
 drivers/char/tpm/xen-tpmfront.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -264,7 +264,7 @@ static int setup_ring(struct xenbus_devi
 		return -ENOMEM;
 	}
 
-	rv = xenbus_grant_ring(dev, &priv->shr, 1, &gref);
+	rv = xenbus_grant_ring(dev, priv->shr, 1, &gref);
 	if (rv < 0)
 		return rv;
 

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

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

From: Vasilis Liaskovitis <[email protected]>

commit f92898e7f32e3533bfd95be174044bc349d416ca upstream.

If a block device is hot-added when we are out of grants, gnttab_grant_foreign_access fails with -ENOSPC (log message "28 granting access to ring page") in this code path:

talk_to_blkback ->

	setup_blkring ->
		xenbus_grant_ring ->
			gnttab_grant_foreign_access

and the failing path in talk_to_blkback sets the driver_data to NULL:

destroy_blkring:

        blkif_free(info, 0);

        mutex_lock(&blkfront_mutex);
        free_info(info);
        mutex_unlock(&blkfront_mutex);

        dev_set_drvdata(&dev->dev, NULL);

This results in a NULL pointer BUG when blkfront_remove and blkif_free try to access the failing device's NULL struct blkfront_info.

---
 drivers/block/xen-blkfront.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -2475,6 +2475,9 @@ static int blkfront_remove(struct xenbus
 
 	dev_dbg(&xbdev->dev, "%s removed", xbdev->nodename);
 
+	if (!info)
+		return 0;
+
 	blkif_free(info, 0);
 
 	mutex_lock(&info->mutex);

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

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

From: Boris Ostrovsky <[email protected]>

commit 3aa6c19d2f38be9c6e9a8ad5fa8e3c9d29ee3c35 upstream.

Xend-based toolstacks don't have static-max entry in xenstore. The equivalent node for those toolstacks is memory_static_max.

---
 drivers/xen/xen-balloon.c |   13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

@@ -75,12 +75,15 @@ static void watch_target(struct xenbus_w
 
 	if (!watch_fired) {
 		watch_fired = true;
-		err = xenbus_scanf(XBT_NIL, "memory", "static-max", "%llu",
-				   &static_max);
-		if (err != 1)
-			static_max = new_target;
-		else
+
+		if ((xenbus_scanf(XBT_NIL, "memory", "static-max",
+				  "%llu", &static_max) == 1) ||
+		    (xenbus_scanf(XBT_NIL, "memory", "memory_static_max",
+				  "%llu", &static_max) == 1))
 			static_max >>= PAGE_SHIFT - 10;
+		else
+			static_max = new_target;
+
 		target_diff = (xen_pv_domain() || xen_initial_domain()) ? 0
 				: static_max - balloon_stats.target_pages;
 	}

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

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

From: Juergen Gross <[email protected]>

commit 2ac2a7d4d9ff4e01e36f9c3d116582f6f655ab47 upstream.

In the following situation a vcpu waiting for a lock might not be woken up from xen_poll_irq():

CPU 1: CPU 2: CPU 3:
takes a spinlock
tries to get lock
-> xen_qlock_wait()
frees the lock
-> xen_qlock_kick(cpu2)

                        -> xen_clear_irq_pending()

takes lock again

                                                  tries to get lock
                                                  -> *lock = _Q_SLOW_VAL
                        -> *lock == _Q_SLOW_VAL ?
                        -> xen_poll_irq()

frees the lock
-> xen_qlock_kick(cpu3)

And cpu 2 will sleep forever.

This can be avoided easily by modifying xen_qlock_wait() to call xen_poll_irq() only if the related irq was not pending and to call xen_clear_irq_pending() only if it was pending.

---
 arch/x86/xen/spinlock.c |   15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

@@ -45,17 +45,12 @@ static void xen_qlock_wait(u8 *byte, u8
 	if (irq == -1)
 		return;
 
-	/* clear pending */
-	xen_clear_irq_pending(irq);
-	barrier();
+	/* If irq pending already clear it and return. */
+	if (xen_test_irq_pending(irq)) {
+		xen_clear_irq_pending(irq);
+		return;
+	}
 
-	/*
-	 * We check the byte value after clearing pending IRQ to make sure
-	 * that we won't miss a wakeup event because of the clearing.
-	 *
-	 * The sync_clear_bit() call in xen_clear_irq_pending() is atomic.
-	 * So it is effectively a memory barrier for x86.
-	 */
 	if (READ_ONCE(*byte) != val)
 		return;
 

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

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

From: Juergen Gross <[email protected]>

commit a856531951dc8094359dfdac21d59cee5969c18e upstream.

xen_qlock_wait() isn't safe for nested calls due to interrupts. A call of xen_qlock_kick() might be ignored in case a deeper nesting level was active right before the call of xen_poll_irq():

CPU 1: CPU 2:
spin_lock(lock1)

                                         spin_lock(lock1)
                                         -> xen_qlock_wait()
                                            -> xen_clear_irq_pending()
                                            Interrupt happens
spin_unlock(lock1)
-> xen_qlock_kick(CPU 2)
spin_lock_irqsave(lock2)
                                         spin_lock_irqsave(lock2)
                                         -> xen_qlock_wait()
                                            -> xen_clear_irq_pending()
                                               clears kick for lock1
                                            -> xen_poll_irq()

spin_unlock_irq_restore(lock2)
-> xen_qlock_kick(CPU 2)
wakes up
spin_unlock_irq_restore(lock2) IRET
resumes in xen_qlock_wait() -> xen_poll_irq() never wakes up

The solution is to disable interrupts in xen_qlock_wait() and not to poll for the irq in case xen_qlock_wait() is called in nmi context.

---
 arch/x86/xen/spinlock.c |   24 ++++++++++--------------
 1 file changed, 10 insertions(+), 14 deletions(-)

@@ -39,29 +39,25 @@ static void xen_qlock_kick(int cpu)
  */
 static void xen_qlock_wait(u8 *byte, u8 val)
 {
+	unsigned long flags;
 	int irq = __this_cpu_read(lock_kicker_irq);
 
 	/* If kicker interrupts not initialized yet, just spin */
-	if (irq == -1)
+	if (irq == -1 || in_nmi())
 		return;
 
-	/* If irq pending already clear it and return. */
+	/* Guard against reentry. */
+	local_irq_save(flags);
+
+	/* If irq pending already clear it. */
 	if (xen_test_irq_pending(irq)) {
 		xen_clear_irq_pending(irq);
-		return;
+	} else if (READ_ONCE(*byte) == val) {
+		/* Block until irq becomes pending (or a spurious wakeup) */
+		xen_poll_irq(irq);
 	}
 
-	if (READ_ONCE(*byte) != val)
-		return;
-
-	/*
-	 * If an interrupt happens here, it will leave the wakeup irq
-	 * pending, which will cause xen_poll_irq() to return
-	 * immediately.
-	 */
-
-	/* Block until irq becomes pending (or perhaps a spurious wakeup) */
-	xen_poll_irq(irq);
+	local_irq_restore(flags);
 }
 
 static irqreturn_t dummy_handler(int irq, void *dev_id)

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

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

From: Roger Pau Monne <[email protected]>

commit 7deecbda3026f5e2a8cc095d7ef7261a920efcf2 upstream.

While booting on an AMD EPYC box the stack canary would detect stack overflows when using the current PVH early stack size (256). Switch to using the value defined by BOOT_STACK_SIZE, which prevents the stack overflow.

---
 arch/x86/xen/xen-pvh.S |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -181,7 +181,7 @@ canary:
 	.fill 48, 1, 0
 
 early_stack:
-	.fill 256, 1, 0
+	.fill BOOT_STACK_SIZE, 1, 0
 early_stack_end:
 
 	ELFNOTE(Xen, XEN_ELFNOTE_PHYS32_ENTRY,

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

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

From: Juergen Gross <[email protected]>

commit e6111161c0a02d58919d776eec94b313bb57911f upstream.

A Xen PVH guest has no associated qemu device model, so trying to unplug any emulated devices is making no sense at all.

Bail out early from xen_unplug_emulated_devices() when running as PVH guest. This will avoid issuing the boot message:

[    0.000000] Xen Platform PCI: unrecognised magic value

---
 arch/x86/xen/platform-pci-unplug.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -146,6 +146,10 @@ void xen_unplug_emulated_devices(void)
 {
 	int r;
 
+	/* PVH guests don't have emulated devices. */
+	if (xen_pvh_domain())
+		return;
+
 	/* user explicitly requested no unplug */
 	if (xen_emul_unplug & XEN_UNPLUG_NEVER)
 		return;

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

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

From: Lubomir Rintel <[email protected]>

commit 6528d88047801b80d2a5370ad46fb6eff2f509e0 upstream.

The USB core gets rightfully upset:

usb 1-1: BOGUS urb flags, 240 --> 200

  WARNING: CPU: 0 PID: 60 at drivers/usb/core/urb.c:503 usb_submit_urb+0x2f8/0x3ed
  Modules linked in:
  CPU: 0 PID: 60 Comm: kworker/0:3 Not tainted 4.19.0-rc6-00319-g5206d00a45c7 #39
  Hardware name: OLPC XO/XO, BIOS OLPC Ver 1.00.01 06/11/2014
  Workqueue: events request_firmware_work_func
  EIP: usb_submit_urb+0x2f8/0x3ed
  Code: 75 06 8b 8f 80 00 00 00 8d 47 78 89 4d e4 89 55 e8 e8 35 1c f6 ff 8b 55 e8 56 52 8b 4d e4 51 50 68 e3 ce c7 c0 e8 ed 18 c6 ff <0f> 0b 83 c4 14 80 7d ef 01 74 0a 80 7d ef 03 0f 85 b8 00 00 00 8b
  EAX: 00000025 EBX: ce7d4980 ECX: 00000000 EDX: 00000001
  ESI: 00000200 EDI: ce7d8800 EBP: ce7f5ea8 ESP: ce7f5e70
  DS: 007b ES: 007b FS: 0000 GS: 00e0 SS: 0068 EFLAGS: 00210292
  CR0: 80050033 CR2: 00000000 CR3: 00e80000 CR4: 00000090
  Call Trace:
   ? if_usb_fw_timeo+0x64/0x64
   __if_usb_submit_rx_urb+0x85/0xe6
   ? if_usb_fw_timeo+0x64/0x64
   if_usb_submit_rx_urb_fwload+0xd/0xf
   if_usb_prog_firmware+0xc0/0x3db
   ? _request_firmware+0x54/0x47b
   ? _request_firmware+0x89/0x47b
   ? if_usb_probe+0x412/0x412
   lbs_fw_loaded+0x55/0xa6
   ? debug_smp_processor_id+0x12/0x14
   helper_firmware_cb+0x3c/0x3f
   request_firmware_work_func+0x37/0x6f
   process_one_work+0x164/0x25a
   worker_thread+0x1c4/0x284
   kthread+0xec/0xf1
   ? cancel_delayed_work_sync+0xf/0xf
   ? kthread_create_on_node+0x1a/0x1a
   ret_from_fork+0x2e/0x38
  ---[ end trace 3ef1e3b2dd53852f ]---

---
 drivers/net/wireless/marvell/libertas/if_usb.c |    2 --
 1 file changed, 2 deletions(-)

@@ -456,8 +456,6 @@ static int __if_usb_submit_rx_urb(struct
 			  MRVDRV_ETH_RX_PACKET_BUFFER_SIZE, callbackfn,
 			  cardp);
 
-	cardp->rx_urb->transfer_flags |= URB_ZERO_PACKET;
-
 	lbs_deb_usb2(&cardp->udev->dev, "Pointer for rx_urb %p\n", cardp->rx_urb);
 	if ((ret = usb_submit_urb(cardp->rx_urb, GFP_ATOMIC))) {
 		lbs_deb_usbd(&cardp->udev->dev, "Submit Rx URB failed: %d\n", ret);

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

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

From: Shuah Khan (Samsung OSG) <[email protected]>

commit e28fd56ad5273be67d0fae5bedc7e1680e729952 upstream.

In rmmod path, usbip_vudc does platform_device_put() twice once from platform_device_unregister() and then from put_vudc_device().

The second put results in:

BUG kmalloc-2048 (Not tainted): Poison overwritten error or

BUG: KASAN: use-after-free in kobject_put+0x1e/0x230 if KASAN is

enabled.

[  169.042156] calling  init+0x0/0x1000 [usbip_vudc] @ 1697
[  169.042396] =============================================================================
[  169.043678] probe of usbip-vudc.0 returned 1 after 350 usecs
[  169.044508] BUG kmalloc-2048 (Not tainted): Poison overwritten
[  169.044509] -----------------------------------------------------------------------------
...
[  169.057849] INFO: Freed in device_release+0x2b/0x80 age=4223 cpu=3 pid=1693
[  169.057852] 	kobject_put+0x86/0x1b0
[  169.057853] 	0xffffffffc0c30a96
[  169.057855] 	__x64_sys_delete_module+0x157/0x240

Fix it to call platform_device_del() instead and let put_vudc_device() do the platform_device_put().

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

@@ -73,6 +73,10 @@ static int __init init(void)
 cleanup:
 	list_for_each_entry_safe(udc_dev, udc_dev2, &vudc_devices, dev_entry) {
 		list_del(&udc_dev->dev_entry);
+		/*
+		 * Just do platform_device_del() here, put_vudc_device()
+		 * calls the platform_device_put()
+		 */
 		platform_device_del(udc_dev->pdev);
 		put_vudc_device(udc_dev);
 	}

@@ -89,7 +93,11 @@ static void __exit cleanup(void)
 
 	list_for_each_entry_safe(udc_dev, udc_dev2, &vudc_devices, dev_entry) {
 		list_del(&udc_dev->dev_entry);
-		platform_device_unregister(udc_dev->pdev);
+		/*
+		 * Just do platform_device_del() here, put_vudc_device()
+		 * calls the platform_device_put()
+		 */
+		platform_device_del(udc_dev->pdev);
 		put_vudc_device(udc_dev);
 	}
 	platform_driver_unregister(&vudc_driver);

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

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

From: Adam Thomson <[email protected]>

commit 1b6af2f58c2b1522e0804b150ca95e50a9e80ea7 upstream.

Current code mistakenly checks against max current to determine order but this should be max voltage. This commit fixes the issue so order is correctly determined, thus avoiding failure based on a higher voltage PPS APDO having a lower maximum current output, which is actually valid.

---
 drivers/usb/typec/tcpm.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -1383,8 +1383,8 @@ static enum pdo_err tcpm_caps_err(struct
 				if (pdo_apdo_type(pdo[i]) != APDO_TYPE_PPS)
 					break;
 
-				if (pdo_pps_apdo_max_current(pdo[i]) <
-				    pdo_pps_apdo_max_current(pdo[i - 1]))
+				if (pdo_pps_apdo_max_voltage(pdo[i]) <
+				    pdo_pps_apdo_max_voltage(pdo[i - 1]))
 					return PDO_ERR_PPS_APDO_NOT_SORTED;
 				else if (pdo_pps_apdo_min_voltage(pdo[i]) ==
 					  pdo_pps_apdo_min_voltage(pdo[i - 1]) &&

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

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

From: Yoshihiro Shimoda <[email protected]>

commit afc92514a34c7414b28047b1205a6b709103c699 upstream.

If the "workaround_for_vbus" is true, the driver will not call usb_disconnect(). So, since the controller keeps some registers' value, the driver doesn't re-enumarate suitable speed after the b-device mode is disabled. To fix the issue, this patch adds usb_disconnect() calling in renesas_usb3_b_device_write() if workaround_for_vbus is true.

---
 drivers/usb/gadget/udc/renesas_usb3.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -2377,6 +2377,9 @@ static ssize_t renesas_usb3_b_device_wri
 	else
 		usb3->forced_b_device = false;
 
+	if (usb3->workaround_for_vbus)
+		usb3_disconnect(usb3);
+
 	/* Let this driver call usb3_connect() anyway */
 	usb3_check_id(usb3);
 

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

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

From: Felix Fietkau <[email protected]>

commit 5289976ad887deb07c76df7eecf553c264aeebed upstream.

If the first virtual interface is a station (or an AP with beacons temporarily disabled), the beacon of the second interface needs to occupy hardware beacon slot 0.
For some reason the beacon index was incorrectly masked with the virtual interface beacon mask, which prevents the secondary interface from sending beacons unless the first one also does.

---
 drivers/net/wireless/mediatek/mt76/mt76x2_mac.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -725,8 +725,7 @@ __mt76x2_mac_set_beacon(struct mt76x2_de
 	if (skb) {
 		ret = mt76_write_beacon(dev, beacon_addr, skb);
 		if (!ret)
-			dev->beacon_data_mask |= BIT(bcn_idx) &
-						 dev->beacon_mask;
+			dev->beacon_data_mask |= BIT(bcn_idx);
 	} else {
 		dev->beacon_data_mask &= ~BIT(bcn_idx);
 		for (i = 0; i < beacon_len; i += 4)

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

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

From: Luca Coelho <[email protected]>

commit 3d71c3f1f50cf309bd20659422af549bc784bfff upstream.

The rs_rate_from_ucode_rate() function may return -EINVAL if the rate is invalid, but none of the callsites check for the error, potentially making us access arrays with index IWL_RATE_INVALID, which is larger than the arrays, causing an out-of-bounds access. This will trigger KASAN warnings, such as the one reported in the bugzilla issue mentioned below.

This fixes https://bugzilla.kernel.org/show_bug.cgi?id=200659

---
 drivers/net/wireless/intel/iwlwifi/mvm/rs.c |   24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

@@ -1218,7 +1218,11 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm
 	    !(info->flags & IEEE80211_TX_STAT_AMPDU))
 		return;
 
-	rs_rate_from_ucode_rate(tx_resp_hwrate, info->band, &tx_resp_rate);
+	if (rs_rate_from_ucode_rate(tx_resp_hwrate, info->band,
+				    &tx_resp_rate)) {
+		WARN_ON_ONCE(1);
+		return;
+	}
 
 #ifdef CONFIG_MAC80211_DEBUGFS
 	/* Disable last tx check if we are debugging with fixed rate but

@@ -1269,7 +1273,10 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm
 	 */
 	table = &lq_sta->lq;
 	lq_hwrate = le32_to_cpu(table->rs_table[0]);
-	rs_rate_from_ucode_rate(lq_hwrate, info->band, &lq_rate);
+	if (rs_rate_from_ucode_rate(lq_hwrate, info->band, &lq_rate)) {
+		WARN_ON_ONCE(1);
+		return;
+	}
 
 	/* Here we actually compare this rate to the latest LQ command */
 	if (lq_color != LQ_FLAG_COLOR_GET(table->flags)) {

@@ -1371,8 +1378,12 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm
 		/* Collect data for each rate used during failed TX attempts */
 		for (i = 0; i <= retries; ++i) {
 			lq_hwrate = le32_to_cpu(table->rs_table[i]);
-			rs_rate_from_ucode_rate(lq_hwrate, info->band,
-						&lq_rate);
+			if (rs_rate_from_ucode_rate(lq_hwrate, info->band,
+						    &lq_rate)) {
+				WARN_ON_ONCE(1);
+				return;
+			}
+
 			/*
 			 * Only collect stats if retried rate is in the same RS
 			 * table as active/search.

@@ -3241,7 +3252,10 @@ static void rs_build_rates_table_from_fi
 	for (i = 0; i < num_rates; i++)
 		lq_cmd->rs_table[i] = ucode_rate_le32;
 
-	rs_rate_from_ucode_rate(ucode_rate, band, &rate);
+	if (rs_rate_from_ucode_rate(ucode_rate, band, &rate)) {
+		WARN_ON_ONCE(1);
+		return;
+	}
 
 	if (is_mimo(&rate))
 		lq_cmd->mimo_delim = num_rates - 1;

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

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

From: Stefan Nuernberger <[email protected]>

commit 076ed3da0c9b2f88d9157dbe7044a45641ae369e upstream.

commit 40413955ee26 ("Cipso: cipso_v4_optptr enter infinite loop") fixed a possible infinite loop in the IP option parsing of CIPSO. The fix assumes that ip_options_compile filtered out all zero length options and that no other one-byte options beside IPOPT_END and IPOPT_NOOP exist. While this assumption currently holds true, add explicit checks for zero length and invalid length options to be safe for the future. Even though ip_options_compile should have validated the options, the introduction of new one-byte options can still confuse this code without the additional checks.

---
 net/ipv4/cipso_ipv4.c |   11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

@@ -1512,7 +1512,7 @@ static int cipso_v4_parsetag_loc(const s
  *
  * Description:
  * Parse the packet's IP header looking for a CIPSO option.  Returns a pointer
- * to the start of the CIPSO option on success, NULL if one if not found.
+ * to the start of the CIPSO option on success, NULL if one is not found.
  *
  */
 unsigned char *cipso_v4_optptr(const struct sk_buff *skb)

@@ -1522,10 +1522,8 @@ unsigned char *cipso_v4_optptr(const str
 	int optlen;
 	int taglen;
 
-	for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) {
+	for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 1; ) {
 		switch (optptr[0]) {
-		case IPOPT_CIPSO:
-			return optptr;
 		case IPOPT_END:
 			return NULL;
 		case IPOPT_NOOP:

@@ -1534,6 +1532,11 @@ unsigned char *cipso_v4_optptr(const str
 		default:
 			taglen = optptr[1];
 		}
+		if (!taglen || taglen > optlen)
+			return NULL;
+		if (optptr[0] == IPOPT_CIPSO)
+			return optptr;
+
 		optlen -= taglen;
 		optptr += taglen;
 	}

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

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

From: Christian Lamparter <[email protected]>

commit 27d8d2d7a9b7eb05c4484b74b749eaee7b50b845 upstream.

There are two poly_store, but one should have been poly_show.

|adma.c:4382:16: error: conflicting types for 'poly_store'
| static ssize_t poly_store(struct device_driver *dev, const char *buf,
|                ^~~~~~~~~~
|adma.c:4363:16: note: previous definition of 'poly_store' was here
| static ssize_t poly_store(struct device_driver *dev, char *buf)
|                ^~~~~~~~~~

---
 drivers/dma/ppc4xx/adma.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -4360,7 +4360,7 @@ static ssize_t enable_store(struct devic
 }
 static DRIVER_ATTR_RW(enable);
 
-static ssize_t poly_store(struct device_driver *dev, char *buf)
+static ssize_t poly_show(struct device_driver *dev, char *buf)
 {
 	ssize_t size = 0;
 	u32 reg;

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

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

From: Alexander Duyck <[email protected]>

commit b6eae0f61db27748606cc00dafcfd1e2c032f0a5 upstream.

Unlike asynchronous initialization in the core we have not yet associated the device with the parent, and as such the device doesn't hold a reference to the parent.

In order to resolve that we should be holding a reference on the parent until the asynchronous initialization has completed.

---
 drivers/nvdimm/bus.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -488,6 +488,8 @@ static void nd_async_device_register(voi
 		put_device(dev);
 	}
 	put_device(dev);
+	if (dev->parent)
+		put_device(dev->parent);
 }
 
 static void nd_async_device_unregister(void *d, async_cookie_t cookie)

@@ -507,6 +509,8 @@ void __nd_device_register(struct device
 	if (!dev)
 		return;
 	dev->bus = &nvdimm_bus_type;
+	if (dev->parent)
+		get_device(dev->parent);
 	get_device(dev);
 	async_schedule_domain(nd_async_device_register, dev,
 			&nd_async_domain);

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

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

From: Dan Williams <[email protected]>

commit 5d394eee2c102453278d81d9a7cf94c80253486a upstream.

While experimenting with region driver loading the following backtrace was triggered:

INFO: trying to register non-static key.
the code is fine but needs lockdep annotation.
turning off the locking correctness validator.
[..]

 Call Trace:
  dump_stack+0x85/0xcb
  register_lock_class+0x571/0x580
  ? __lock_acquire+0x2ba/0x1310
  ? kernfs_seq_start+0x2a/0x80
  __lock_acquire+0xd4/0x1310
  ? dev_attr_show+0x1c/0x50
  ? __lock_acquire+0x2ba/0x1310
  ? kernfs_seq_start+0x2a/0x80
  ? lock_acquire+0x9e/0x1a0
  lock_acquire+0x9e/0x1a0
  ? dev_attr_show+0x1c/0x50
  badblocks_show+0x70/0x190
  ? dev_attr_show+0x1c/0x50
  dev_attr_show+0x1c/0x50

This results from a missing successful call to devm_init_badblocks() from nd_region_probe(). Block attempts to show badblocks while the region is not enabled.

---
 drivers/nvdimm/region_devs.c |   11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

@@ -545,10 +545,17 @@ static ssize_t region_badblocks_show(str
 		struct device_attribute *attr, char *buf)
 {
 	struct nd_region *nd_region = to_nd_region(dev);
+	ssize_t rc;
 
-	return badblocks_show(&nd_region->bb, buf, 0);
-}
+	device_lock(dev);
+	if (dev->driver)
+		rc = badblocks_show(&nd_region->bb, buf, 0);
+	else
+		rc = -ENXIO;
+	device_unlock(dev);
 
+	return rc;
+}
 static DEVICE_ATTR(badblocks, 0444, region_badblocks_show, NULL);
 
 static ssize_t resource_show(struct device *dev,

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

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

From: Dan Williams <[email protected]>

commit 91ed7ac444ef749603a95629a5ec483988c4f14b upstream.

The driver is only initializing bb_res in the devm_memremap_pages() paths, but the raw namespace case is passing an uninitialized bb_res to nvdimm_badblocks_populate().

---
 drivers/nvdimm/pmem.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -393,9 +393,11 @@ static int pmem_attach_disk(struct devic
 		addr = devm_memremap_pages(dev, &pmem->pgmap);
 		pmem->pfn_flags |= PFN_MAP;
 		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
-	} else
+	} else {
 		addr = devm_memremap(dev, pmem->phys_addr,
 				pmem->size, ARCH_MEMREMAP_PMEM);
+		memcpy(&bb_res, &nsio->res, sizeof(bb_res));
+	}
 
 	/*
 	 * At release time the queue must be frozen before

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

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

From: Takashi Iwai <[email protected]>

commit 9c80c5a8831471e0a3e139aad1b0d4c0fdc50b2f upstream.

skl_tplg_get_token() misses a break in the big switch() block for SKL_TKN_U8_CORE_ID entry.
Spotted nicely by -Wimplicit-fallthrough compiler option.

---
 sound/soc/intel/skylake/skl-topology.c |    1 +
 1 file changed, 1 insertion(+)

@@ -2458,6 +2458,7 @@ static int skl_tplg_get_token(struct dev
 
 	case SKL_TKN_U8_CORE_ID:
 		mconfig->core_id = tkn_elem->value;
+		break;
 
 	case SKL_TKN_U8_MOD_TYPE:
 		mconfig->m_type = tkn_elem->value;

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

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

From: Daniel Mack <[email protected]>

commit 747df19747bc9752cd40b9cce761e17a033aa5c2 upstream.

The ESD watchdog code in sta32x_watchdog() dereferences the pointer which is never assigned.

This is a regression from a1be4cead9b950 ("ASoC: sta32x: Convert to direct regmap API usage.") which went unnoticed since nobody seems to use that ESD workaround.

---
 sound/soc/codecs/sta32x.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -879,6 +879,9 @@ static int sta32x_probe(struct snd_soc_c
 	struct sta32x_priv *sta32x = snd_soc_component_get_drvdata(component);
 	struct sta32x_platform_data *pdata = sta32x->pdata;
 	int i, ret = 0, thermal = 0;
+
+	sta32x->component = component;
+
 	ret = regulator_bulk_enable(ARRAY_SIZE(sta32x->supplies),
 				    sta32x->supplies);
 	if (ret != 0) {

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

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

From: Artemy Kovalyov <[email protected]>

commit 013c2403bf32e48119aeb13126929f81352cc7ac upstream.

Schedule MR cache work only after bucket was initialized.

---
 drivers/infiniband/hw/mlx5/mr.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -691,7 +691,6 @@ int mlx5_mr_cache_init(struct mlx5_ib_de
 		init_completion(&ent->compl);
 		INIT_WORK(&ent->work, cache_work_func);
 		INIT_DELAYED_WORK(&ent->dwork, delayed_cache_work_func);
-		queue_work(cache->wq, &ent->work);
 
 		if (i > MR_CACHE_LAST_STD_ENTRY) {
 			mlx5_odp_init_mr_cache_entry(ent);

@@ -711,6 +710,7 @@ int mlx5_mr_cache_init(struct mlx5_ib_de
 			ent->limit = dev->mdev->profile->mr_cache[i].limit;
 		else
 			ent->limit = 0;
+		queue_work(cache->wq, &ent->work);
 	}
 
 	err = mlx5_mr_cache_debugfs_init(dev);

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

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

From: Jason Gunthorpe <[email protected]>

commit 9a59739bd01f77db6fbe2955a4fce165f0f43568 upstream.

This enum has become part of the uABI, as both RXE and the ib_uverbs_post_send() command expect userspace to supply values from this enum. So it should be properly placed in include/uapi/rdma.

In userspace this enum is called 'enum ibv_wr_opcode' as part of libibverbs.h. That enum defines different values for IB_WR_LOCAL_INV, IB_WR_SEND_WITH_INV, and IB_WR_LSO. These were introduced (incorrectly, it turns out) into libiberbs in 2015.

The kernel has changed its mind on the numbering for several of the IB_WC values over the years, but has remained stable on IB_WR_LOCAL_INV and below.

Based on this we can conclude that there is no real user space user of the values beyond IB_WR_ATOMIC_FETCH_AND_ADD, as they have never worked via rdma-core. This is confirmed by inspection, only rxe uses the kernel enum and implements the latter operations. rxe has clearly never worked with these attributes from userspace. Other drivers that support these opcodes implement the functionality without calling out to the kernel.

To make IB_WR_SEND_WITH_INV and related work for RXE in userspace we choose to renumber the IB_WR enum in the kernel to match the uABI that userspace has bee using since before Soft RoCE was merged. This is an overall simpler configuration for the whole software stack, and obviously can't break anything existing.

---
 include/rdma/ib_verbs.h           |   34 ++++++++++++++++++++--------------
 include/uapi/rdma/ib_user_verbs.h |   20 +++++++++++++++++++-
 2 files changed, 39 insertions(+), 15 deletions(-)

@@ -1296,21 +1296,27 @@ struct ib_qp_attr {
 };
 
 enum ib_wr_opcode {
-	IB_WR_RDMA_WRITE,
-	IB_WR_RDMA_WRITE_WITH_IMM,
-	IB_WR_SEND,
-	IB_WR_SEND_WITH_IMM,
-	IB_WR_RDMA_READ,
-	IB_WR_ATOMIC_CMP_AND_SWP,
-	IB_WR_ATOMIC_FETCH_AND_ADD,
-	IB_WR_LSO,
-	IB_WR_SEND_WITH_INV,
-	IB_WR_RDMA_READ_WITH_INV,
-	IB_WR_LOCAL_INV,
-	IB_WR_REG_MR,
-	IB_WR_MASKED_ATOMIC_CMP_AND_SWP,
-	IB_WR_MASKED_ATOMIC_FETCH_AND_ADD,
+	/* These are shared with userspace */
+	IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE,
+	IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM,
+	IB_WR_SEND = IB_UVERBS_WR_SEND,
+	IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM,
+	IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ,
+	IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP,
+	IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD,
+	IB_WR_LSO = IB_UVERBS_WR_TSO,
+	IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV,
+	IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV,
+	IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV,
+	IB_WR_MASKED_ATOMIC_CMP_AND_SWP =
+		IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP,
+	IB_WR_MASKED_ATOMIC_FETCH_AND_ADD =
+		IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD,
+
+	/* These are kernel only and can not be issued by userspace */
+	IB_WR_REG_MR = 0x20,
 	IB_WR_REG_SIG_MR,
+
 	/* reserve values for low level drivers' internal use.
 	 * These values will not be used at all in the ib core layer.
 	 */

@@ -762,10 +762,28 @@ struct ib_uverbs_sge {
 	__u32 lkey;
 };
 
+enum ib_uverbs_wr_opcode {
+	IB_UVERBS_WR_RDMA_WRITE = 0,
+	IB_UVERBS_WR_RDMA_WRITE_WITH_IMM = 1,
+	IB_UVERBS_WR_SEND = 2,
+	IB_UVERBS_WR_SEND_WITH_IMM = 3,
+	IB_UVERBS_WR_RDMA_READ = 4,
+	IB_UVERBS_WR_ATOMIC_CMP_AND_SWP = 5,
+	IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD = 6,
+	IB_UVERBS_WR_LOCAL_INV = 7,
+	IB_UVERBS_WR_BIND_MW = 8,
+	IB_UVERBS_WR_SEND_WITH_INV = 9,
+	IB_UVERBS_WR_TSO = 10,
+	IB_UVERBS_WR_RDMA_READ_WITH_INV = 11,
+	IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP = 12,
+	IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD = 13,
+	/* Review enum ib_wr_opcode before modifying this */
+};
+
 struct ib_uverbs_send_wr {
 	__aligned_u64 wr_id;
 	__u32 num_sge;
-	__u32 opcode;
+	__u32 opcode;		/* see enum ib_uverbs_wr_opcode */
 	__u32 send_flags;
 	union {
 		__be32 imm_data;