Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Smooth Cong Wang's bug fix into 'net-next'.  Basically put
the bulk of the tcf_block_put() logic from 'net' into
tcf_block_put_ext(), but after the offload unbind.

Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/ABI/testing/sysfs-devices-power

@@ -211,9 +211,7 @@ Description:
 		device, after it has been suspended at run time, from a resume
 		request to the moment the device will be ready to process I/O,
 		in microseconds.  If it is equal to 0, however, this means that
-		the PM QoS resume latency may be arbitrary and the special value
-		"n/a" means that user space cannot accept any resume latency at
-		all for the given device.
+		the PM QoS resume latency may be arbitrary.
 
 		Not all drivers support this attribute.  If it isn't supported,
 		it is not present.

MAINTAINERS

@@ -6678,7 +6678,7 @@ F:	include/net/ieee802154_netdev.h
 F:	Documentation/networking/ieee802154.txt
 
 IFE PROTOCOL
-M:	Yotam Gigi <yotamg@mellanox.com>
+M:	Yotam Gigi <yotam.gi@gmail.com>
 M:	Jamal Hadi Salim <jhs@mojatatu.com>
 F:	net/ife
 F:	include/net/ife.h
@@ -8751,7 +8751,7 @@ Q:	http://patchwork.ozlabs.org/project/netdev/list/
 F:	drivers/net/ethernet/mellanox/mlxsw/
 
 MELLANOX FIRMWARE FLASH LIBRARY (mlxfw)
-M:	Yotam Gigi <yotamg@mellanox.com>
+M:	mlxsw@mellanox.com
 L:	netdev@vger.kernel.org
 S:	Supported
 W:	http://www.mellanox.com
@@ -10899,7 +10899,7 @@ S:	Maintained
 F:	drivers/block/ps3vram.c
 
 PSAMPLE PACKET SAMPLING SUPPORT:
-M:	Yotam Gigi <yotamg@mellanox.com>
+M:	Yotam Gigi <yotam.gi@gmail.com>
 S:	Maintained
 F:	net/psample
 F:	include/net/psample.h

arch/x86/crypto/chacha20-avx2-x86_64.S

@@ -45,7 +45,7 @@ ENTRY(chacha20_8block_xor_avx2)
 
 	vzeroupper
 	# 4 * 32 byte stack, 32-byte aligned
-	mov		%rsp, %r8
+	lea		8(%rsp),%r10
 	and		$~31, %rsp
 	sub		$0x80, %rsp
 
@@ -443,6 +443,6 @@ ENTRY(chacha20_8block_xor_avx2)
 	vmovdqu		%ymm15,0x01e0(%rsi)
 
 	vzeroupper
-	mov		%r8,%rsp
+	lea		-8(%r10),%rsp
 	ret
 ENDPROC(chacha20_8block_xor_avx2)

arch/x86/crypto/chacha20-ssse3-x86_64.S

@@ -160,7 +160,7 @@ ENTRY(chacha20_4block_xor_ssse3)
 	# done with the slightly better performing SSSE3 byte shuffling,
 	# 7/12-bit word rotation uses traditional shift+OR.
 
-	mov		%rsp,%r11
+	lea		8(%rsp),%r10
 	sub		$0x80,%rsp
 	and		$~63,%rsp
 
@@ -625,6 +625,6 @@ ENTRY(chacha20_4block_xor_ssse3)
 	pxor		%xmm1,%xmm15
 	movdqu		%xmm15,0xf0(%rsi)
 
-	mov		%r11,%rsp
+	lea		-8(%r10),%rsp
 	ret
 ENDPROC(chacha20_4block_xor_ssse3)

arch/x86/mm/fault.c

@@ -1440,7 +1440,17 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.  Since we never set FAULT_FLAG_RETRY_NOWAIT, if
 	 * we get VM_FAULT_RETRY back, the mmap_sem has been unlocked.
+	 *
+	 * Note that handle_userfault() may also release and reacquire mmap_sem
+	 * (and not return with VM_FAULT_RETRY), when returning to userland to
+	 * repeat the page fault later with a VM_FAULT_NOPAGE retval
+	 * (potentially after handling any pending signal during the return to
+	 * userland). The return to userland is identified whenever
+	 * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
+	 * Thus we have to be careful about not touching vma after handling the
+	 * fault, so we read the pkey beforehand.
 	 */
+	pkey = vma_pkey(vma);
 	fault = handle_mm_fault(vma, address, flags);
 	major |= fault & VM_FAULT_MAJOR;
 
@@ -1467,7 +1477,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
 		return;
 	}
 
-	pkey = vma_pkey(vma);
 	up_read(&mm->mmap_sem);
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		mm_fault_error(regs, error_code, address, &pkey, fault);

drivers/base/cpu.c

@@ -377,8 +377,7 @@ int register_cpu(struct cpu *cpu, int num)
 
 	per_cpu(cpu_sys_devices, num) = &cpu->dev;
 	register_cpu_under_node(num, cpu_to_node(num));
-	dev_pm_qos_expose_latency_limit(&cpu->dev,
-					PM_QOS_RESUME_LATENCY_NO_CONSTRAINT);
+	dev_pm_qos_expose_latency_limit(&cpu->dev, 0);
 
 	return 0;
 }

drivers/base/power/domain_governor.c

@@ -14,20 +14,23 @@
 static int dev_update_qos_constraint(struct device *dev, void *data)
 {
 	s64 *constraint_ns_p = data;
-	s64 constraint_ns = -1;
+	s32 constraint_ns = -1;
 
 	if (dev->power.subsys_data && dev->power.subsys_data->domain_data)
 		constraint_ns = dev_gpd_data(dev)->td.effective_constraint_ns;
 
-	if (constraint_ns < 0)
+	if (constraint_ns < 0) {
 		constraint_ns = dev_pm_qos_read_value(dev);
-
-	if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+		constraint_ns *= NSEC_PER_USEC;
+	}
+	if (constraint_ns == 0)
 		return 0;
 
-	constraint_ns *= NSEC_PER_USEC;
-
-	if (constraint_ns < *constraint_ns_p || *constraint_ns_p < 0)
+	/*
+	 * constraint_ns cannot be negative here, because the device has been
+	 * suspended.
+	 */
+	if (constraint_ns < *constraint_ns_p || *constraint_ns_p == 0)
 		*constraint_ns_p = constraint_ns;
 
 	return 0;
@@ -60,14 +63,10 @@ static bool default_suspend_ok(struct device *dev)
 
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 
-	if (constraint_ns == 0)
+	if (constraint_ns < 0)
 		return false;
 
-	if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
-		constraint_ns = -1;
-	else
-		constraint_ns *= NSEC_PER_USEC;
-
+	constraint_ns *= NSEC_PER_USEC;
 	/*
 	 * We can walk the children without any additional locking, because
 	 * they all have been suspended at this point and their
@@ -77,19 +76,14 @@ static bool default_suspend_ok(struct device *dev)
 		device_for_each_child(dev, &constraint_ns,
 				      dev_update_qos_constraint);
 
-	if (constraint_ns < 0) {
-		/* The children have no constraints. */
-		td->effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
-		td->cached_suspend_ok = true;
-	} else {
-		constraint_ns -= td->suspend_latency_ns + td->resume_latency_ns;
-		if (constraint_ns > 0) {
-			td->effective_constraint_ns = constraint_ns;
-			td->cached_suspend_ok = true;
-		} else {
-			td->effective_constraint_ns = 0;
-		}
+	if (constraint_ns > 0) {
+		constraint_ns -= td->suspend_latency_ns +
+				td->resume_latency_ns;
+		if (constraint_ns == 0)
+			return false;
 	}
+	td->effective_constraint_ns = constraint_ns;
+	td->cached_suspend_ok = constraint_ns >= 0;
 
 	/*
 	 * The children have been suspended already, so we don't need to take
@@ -151,14 +145,13 @@ static bool __default_power_down_ok(struct dev_pm_domain *pd,
 		td = &to_gpd_data(pdd)->td;
 		constraint_ns = td->effective_constraint_ns;
 		/* default_suspend_ok() need not be called before us. */
-		if (constraint_ns < 0)
+		if (constraint_ns < 0) {
 			constraint_ns = dev_pm_qos_read_value(pdd->dev);
-
-		if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+			constraint_ns *= NSEC_PER_USEC;
+		}
+		if (constraint_ns == 0)
 			continue;
 
-		constraint_ns *= NSEC_PER_USEC;
-
 		/*
 		 * constraint_ns cannot be negative here, because the device has
 		 * been suspended.

drivers/base/power/qos.c

@@ -189,7 +189,7 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	plist_head_init(&c->list);
 	c->target_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
 	c->default_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
-	c->no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
+	c->no_constraint_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
 	c->type = PM_QOS_MIN;
 	c->notifiers = n;
 

drivers/base/power/runtime.c

@@ -253,7 +253,7 @@ static int rpm_check_suspend_allowed(struct device *dev)
 	    || (dev->power.request_pending
 			&& dev->power.request == RPM_REQ_RESUME))
 		retval = -EAGAIN;
-	else if (__dev_pm_qos_read_value(dev) == 0)
+	else if (__dev_pm_qos_read_value(dev) < 0)
 		retval = -EPERM;
 	else if (dev->power.runtime_status == RPM_SUSPENDED)
 		retval = 1;

drivers/base/power/sysfs.c

@@ -218,14 +218,7 @@ static ssize_t pm_qos_resume_latency_show(struct device *dev,
 					  struct device_attribute *attr,
 					  char *buf)
 {
-	s32 value = dev_pm_qos_requested_resume_latency(dev);
-
-	if (value == 0)
-		return sprintf(buf, "n/a\n");
-	else if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
-		value = 0;
-
-	return sprintf(buf, "%d\n", value);
+	return sprintf(buf, "%d\n", dev_pm_qos_requested_resume_latency(dev));
 }
 
 static ssize_t pm_qos_resume_latency_store(struct device *dev,
@@ -235,21 +228,11 @@ static ssize_t pm_qos_resume_latency_store(struct device *dev,
 	s32 value;
 	int ret;
 
-	if (!kstrtos32(buf, 0, &value)) {
-		/*
-		 * Prevent users from writing negative or "no constraint" values
-		 * directly.
-		 */
-		if (value < 0 || value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
-			return -EINVAL;
+	if (kstrtos32(buf, 0, &value))
+		return -EINVAL;
 
-		if (value == 0)
-			value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
-	} else if (!strcmp(buf, "n/a") || !strcmp(buf, "n/a\n")) {
-		value = 0;
-	} else {
+	if (value < 0)
 		return -EINVAL;
-	}
 
 	ret = dev_pm_qos_update_request(dev->power.qos->resume_latency_req,
 					value);

drivers/block/virtio_blk.c

@@ -593,10 +593,22 @@ static int virtblk_map_queues(struct blk_mq_tag_set *set)
 	return blk_mq_virtio_map_queues(set, vblk->vdev, 0);
 }
 
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+static void virtblk_initialize_rq(struct request *req)
+{
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+
+	scsi_req_init(&vbr->sreq);
+}
+#endif
+
 static const struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
 	.complete	= virtblk_request_done,
 	.init_request	= virtblk_init_request,
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+	.initialize_rq_fn = virtblk_initialize_rq,
+#endif
 	.map_queues	= virtblk_map_queues,
 };
 

drivers/cpuidle/governors/menu.c

@@ -298,8 +298,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		data->needs_update = 0;
 	}
 
-	if (resume_latency < latency_req &&
-	    resume_latency != PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+	/* resume_latency is 0 means no restriction */
+	if (resume_latency && resume_latency < latency_req)
 		latency_req = resume_latency;
 
 	/* Special case when user has set very strict latency requirement */

drivers/ide/ide-cd.c

@@ -1328,6 +1328,7 @@ static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
 	unsigned long blocks = blk_rq_sectors(rq) / (hard_sect >> 9);
 	struct scsi_request *req = scsi_req(rq);
 
+	scsi_req_init(req);
 	memset(req->cmd, 0, BLK_MAX_CDB);
 
 	if (rq_data_dir(rq) == READ)

drivers/infiniband/core/nldev.c

@@ -214,7 +214,9 @@ static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
 			  nldev_policy, extack);
-	if (err || !tb[RDMA_NLDEV_ATTR_PORT_INDEX])
+	if (err ||
+	    !tb[RDMA_NLDEV_ATTR_DEV_INDEX] ||
+	    !tb[RDMA_NLDEV_ATTR_PORT_INDEX])
 		return -EINVAL;
 
 	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);

drivers/mmc/host/renesas_sdhi_internal_dmac.c

@@ -146,11 +146,8 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host,
 	WARN_ON(host->sg_len > 1);
 
 	/* This DMAC cannot handle if buffer is not 8-bytes alignment */
-	if (!IS_ALIGNED(sg->offset, 8)) {
-		host->force_pio = true;
-		renesas_sdhi_internal_dmac_enable_dma(host, false);
-		return;
-	}
+	if (!IS_ALIGNED(sg->offset, 8))
+		goto force_pio;
 
 	if (data->flags & MMC_DATA_READ) {
 		dtran_mode |= DTRAN_MODE_CH_NUM_CH1;
@@ -163,8 +160,8 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host,
 	}
 
 	ret = dma_map_sg(&host->pdev->dev, sg, host->sg_len, dir);
-	if (ret < 0)
-		return;
+	if (ret == 0)
+		goto force_pio;
 
 	renesas_sdhi_internal_dmac_enable_dma(host, true);
 
@@ -176,6 +173,12 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host,
 					    dtran_mode);
 	renesas_sdhi_internal_dmac_dm_write(host, DM_DTRAN_ADDR,
 					    sg->dma_address);
+
+	return;
+
+force_pio:
+	host->force_pio = true;
+	renesas_sdhi_internal_dmac_enable_dma(host, false);
 }
 
 static void renesas_sdhi_internal_dmac_issue_tasklet_fn(unsigned long arg)

drivers/mmc/host/tmio_mmc_core.c

@@ -47,6 +47,7 @@
 #include <linux/mmc/sdio.h>
 #include <linux/scatterlist.h>
 #include <linux/spinlock.h>
+#include <linux/swiotlb.h>
 #include <linux/workqueue.h>
 
 #include "tmio_mmc.h"
@@ -1215,6 +1216,18 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	mmc->max_blk_count = pdata->max_blk_count ? :
 		(PAGE_SIZE / mmc->max_blk_size) * mmc->max_segs;
 	mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count;
+	/*
+	 * Since swiotlb has memory size limitation, this will calculate
+	 * the maximum size locally (because we don't have any APIs for it now)
+	 * and check the current max_req_size. And then, this will update
+	 * the max_req_size if needed as a workaround.
+	 */
+	if (swiotlb_max_segment()) {
+		unsigned int max_size = (1 << IO_TLB_SHIFT) * IO_TLB_SEGSIZE;
+
+		if (mmc->max_req_size > max_size)
+			mmc->max_req_size = max_size;
+	}
 	mmc->max_seg_size = mmc->max_req_size;
 
 	_host->native_hotplug = !(pdata->flags & TMIO_MMC_USE_GPIO_CD ||

drivers/net/ethernet/hisilicon/hns/hns_enet.c

@@ -2369,8 +2369,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 			priv->enet_ver = AE_VERSION_2;
 
 		ae_node = of_parse_phandle(dev->of_node, "ae-handle", 0);
-		if (IS_ERR_OR_NULL(ae_node)) {
-			ret = PTR_ERR(ae_node);
+		if (!ae_node) {
+			ret = -ENODEV;
 			dev_err(dev, "not find ae-handle\n");
 			goto out_read_prop_fail;
 		}

drivers/net/ethernet/mellanox/mlxsw/i2c.c

@@ -294,7 +294,7 @@ mlxsw_i2c_write(struct device *dev, size_t in_mbox_size, u8 *in_mbox, int num,
 		write_tran.len = MLXSW_I2C_ADDR_WIDTH + chunk_size;
 		mlxsw_i2c_set_slave_addr(tran_buf, off);
 		memcpy(&tran_buf[MLXSW_I2C_ADDR_BUF_SIZE], in_mbox +
-		       chunk_size * i, chunk_size);
+		       MLXSW_I2C_BLK_MAX * i, chunk_size);
 
 		j = 0;
 		end = jiffies + timeout;