Merge tag 'char-misc-3.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc

Pull char/misc driver fixes from Greg KH:
 "Here are a few driver fixes for char/misc drivers that resolve
  reported issues.

  All have been in linux-next successfully for a few days"

* tag 'char-misc-3.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
  Drivers: hv: vmbus: Negotiate version 3.0 when running on ws2012r2 hosts
  Tools: hv: Handle the case when the target file exists correctly
  vme_tsi148: Utilize to_pci_dev() macro
  vme_tsi148: Fix PCI address mapping assumption
  vme_tsi148: Fix typo in tsi148_slave_get()
  w1: avoid recursive device_add
  w1: fix netlink refcnt leak on error path
  misc: Grammar s/addition/additional/
  drivers: mcb: fix memory leak in chameleon_parse_cells() error path
  mei: ignore client writing state during cb completion
  mei: me: do not load the driver if the FW doesn't support MEI interface
  GenWQE: Increase driver version number
  GenWQE: Fix multithreading problems
  GenWQE: Ensure rc is not returning an uninitialized value
  GenWQE: Add wmb before DDCB is started
  GenWQE: Enable access to VPD flash area

18 files changed, 280 insertions, 158 deletions

diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index f2d7bf90c9fe..2e7801af466e 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -55,6 +55,9 @@ static __u32 vmbus_get_next_version(__u32 current_version)
 	case (VERSION_WIN8):
 		return VERSION_WIN7;
 
+	case (VERSION_WIN8_1):
+		return VERSION_WIN8;
+
 	case (VERSION_WS2008):
 	default:
 		return VERSION_INVAL;
@@ -77,7 +80,7 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
 	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
 	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
-	if (version == VERSION_WIN8)
+	if (version == VERSION_WIN8_1)
 		msg->target_vcpu = hv_context.vp_index[smp_processor_id()];
 
 	/*
diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c
index d1278b5f3028..004926955263 100644
--- a/drivers/mcb/mcb-parse.c
+++ b/drivers/mcb/mcb-parse.c
@@ -141,6 +141,7 @@ int chameleon_parse_cells(struct mcb_bus *bus, phys_addr_t mapbase,
 		default:
 			pr_err("Invalid chameleon descriptor type 0x%x\n",
 				dtype);
+			kfree(header);
 			return -EINVAL;
 		}
 		num_cells++;
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 1cb74085e410..8baff0effc7d 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -300,8 +300,8 @@ config SGI_GRU_DEBUG
 	depends on SGI_GRU
 	default n
 	---help---
-	This option enables addition debugging code for the SGI GRU driver. If
-	you are unsure, say N.
+	This option enables additional debugging code for the SGI GRU driver.
+	If you are unsure, say N.
 
 config APDS9802ALS
 	tristate "Medfield Avago APDS9802 ALS Sensor module"
diff --git a/drivers/misc/genwqe/card_base.h b/drivers/misc/genwqe/card_base.h
index 5e4dbd21f89a..0e608a288603 100644
--- a/drivers/misc/genwqe/card_base.h
+++ b/drivers/misc/genwqe/card_base.h
@@ -337,6 +337,44 @@ enum genwqe_requ_state {
 };
 
 /**
+ * struct genwqe_sgl - Scatter gather list describing user-space memory
+ * @sgl:            scatter gather list needs to be 128 byte aligned
+ * @sgl_dma_addr:   dma address of sgl
+ * @sgl_size:       size of area used for sgl
+ * @user_addr:      user-space address of memory area
+ * @user_size:      size of user-space memory area
+ * @page:           buffer for partial pages if needed
+ * @page_dma_addr:  dma address partial pages
+ */
+struct genwqe_sgl {
+	dma_addr_t sgl_dma_addr;
+	struct sg_entry *sgl;
+	size_t sgl_size;	/* size of sgl */
+
+	void __user *user_addr; /* user-space base-address */
+	size_t user_size;       /* size of memory area */
+
+	unsigned long nr_pages;
+	unsigned long fpage_offs;
+	size_t fpage_size;
+	size_t lpage_size;
+
+	void *fpage;
+	dma_addr_t fpage_dma_addr;
+
+	void *lpage;
+	dma_addr_t lpage_dma_addr;
+};
+
+int genwqe_alloc_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl,
+			  void __user *user_addr, size_t user_size);
+
+int genwqe_setup_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl,
+		     dma_addr_t *dma_list);
+
+int genwqe_free_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl);
+
+/**
  * struct ddcb_requ - Kernel internal representation of the DDCB request
  * @cmd:          User space representation of the DDCB execution request
  */
@@ -347,9 +385,7 @@ struct ddcb_requ {
 	struct ddcb_queue *queue;	  /* associated queue */
 
 	struct dma_mapping  dma_mappings[DDCB_FIXUPS];
-	struct sg_entry     *sgl[DDCB_FIXUPS];
-	dma_addr_t	    sgl_dma_addr[DDCB_FIXUPS];
-	size_t		    sgl_size[DDCB_FIXUPS];
+	struct genwqe_sgl sgls[DDCB_FIXUPS];
 
 	/* kernel/user shared content */
 	struct genwqe_ddcb_cmd cmd;	/* ddcb_no for this request */
@@ -453,22 +489,6 @@ int  genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m,
 int  genwqe_user_vunmap(struct genwqe_dev *cd, struct dma_mapping *m,
 			struct ddcb_requ *req);
 
-struct sg_entry *genwqe_alloc_sgl(struct genwqe_dev *cd, int num_pages,
-				 dma_addr_t *dma_addr, size_t *sgl_size);
-
-void genwqe_free_sgl(struct genwqe_dev *cd, struct sg_entry *sg_list,
-		    dma_addr_t dma_addr, size_t size);
-
-int genwqe_setup_sgl(struct genwqe_dev *cd,
-		    unsigned long offs,
-		    unsigned long size,
-		    struct sg_entry *sgl, /* genwqe sgl */
-		    dma_addr_t dma_addr, size_t sgl_size,
-		    dma_addr_t *dma_list, int page_offs, int num_pages);
-
-int genwqe_check_sgl(struct genwqe_dev *cd, struct sg_entry *sg_list,
-		     int size);
-
 static inline bool dma_mapping_used(struct dma_mapping *m)
 {
 	if (!m)
diff --git a/drivers/misc/genwqe/card_ddcb.c b/drivers/misc/genwqe/card_ddcb.c
index 6f1acc0ccf88..c8046db2d5a2 100644
--- a/drivers/misc/genwqe/card_ddcb.c
+++ b/drivers/misc/genwqe/card_ddcb.c
@@ -305,6 +305,8 @@ static int enqueue_ddcb(struct genwqe_dev *cd, struct ddcb_queue *queue,
 			break;
 
 		new = (old | DDCB_NEXT_BE32);
+
+		wmb();
 		icrc_hsi_shi = cmpxchg(&prev_ddcb->icrc_hsi_shi_32, old, new);
 
 		if (icrc_hsi_shi == old)
@@ -314,6 +316,8 @@ static int enqueue_ddcb(struct genwqe_dev *cd, struct ddcb_queue *queue,
 	/* Queue must be re-started by updating QUEUE_OFFSET */
 	ddcb_mark_tapped(pddcb);
 	num = (u64)ddcb_no << 8;
+
+	wmb();
 	__genwqe_writeq(cd, queue->IO_QUEUE_OFFSET, num); /* start queue */
 
 	return RET_DDCB_TAPPED;
@@ -1306,7 +1310,7 @@ static int queue_wake_up_all(struct genwqe_dev *cd)
  */
 int genwqe_finish_queue(struct genwqe_dev *cd)
 {
-	int i, rc, in_flight;
+	int i, rc = 0, in_flight;
 	int waitmax = genwqe_ddcb_software_timeout;
 	struct pci_dev *pci_dev = cd->pci_dev;
 	struct ddcb_queue *queue = &cd->queue;
diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c
index 2c2c9cc75231..1d2f163a1906 100644
--- a/drivers/misc/genwqe/card_dev.c
+++ b/drivers/misc/genwqe/card_dev.c
@@ -531,7 +531,9 @@ static int do_flash_update(struct genwqe_file *cfile,
 	case '1':
 		cmdopts = 0x1C;
 		break;		/* download/erase_first/part_1 */
-	case 'v':		/* cmdopts = 0x0c (VPD) */
+	case 'v':
+		cmdopts = 0x0C;
+		break;		/* download/erase_first/vpd */
 	default:
 		return -EINVAL;
 	}
@@ -665,6 +667,8 @@ static int do_flash_read(struct genwqe_file *cfile,
 		cmdopts = 0x1A;
 		break;		/* upload/part_1 */
 	case 'v':
+		cmdopts = 0x0A;
+		break;		/* upload/vpd */
 	default:
 		return -EINVAL;
 	}
@@ -836,15 +840,8 @@ static int ddcb_cmd_cleanup(struct genwqe_file *cfile, struct ddcb_requ *req)
 			__genwqe_del_mapping(cfile, dma_map);
 			genwqe_user_vunmap(cd, dma_map, req);
 		}
-		if (req->sgl[i] != NULL) {
-			genwqe_free_sgl(cd, req->sgl[i],
-				       req->sgl_dma_addr[i],
-				       req->sgl_size[i]);
-			req->sgl[i] = NULL;
-			req->sgl_dma_addr[i] = 0x0;
-			req->sgl_size[i] = 0;
-		}
-
+		if (req->sgls[i].sgl != NULL)
+			genwqe_free_sync_sgl(cd, &req->sgls[i]);
 	}
 	return 0;
 }
@@ -913,7 +910,7 @@ static int ddcb_cmd_fixups(struct genwqe_file *cfile, struct ddcb_requ *req)
 
 		case ATS_TYPE_SGL_RDWR:
 		case ATS_TYPE_SGL_RD: {
-			int page_offs, nr_pages, offs;
+			int page_offs;
 
 			u_addr = be64_to_cpu(*((__be64 *)
 					       &cmd->asiv[asiv_offs]));
@@ -951,27 +948,18 @@ static int ddcb_cmd_fixups(struct genwqe_file *cfile, struct ddcb_requ *req)
 				page_offs = 0;
 			}
 
-			offs = offset_in_page(u_addr);
-			nr_pages = DIV_ROUND_UP(offs + u_size, PAGE_SIZE);
-
 			/* create genwqe style scatter gather list */
-			req->sgl[i] = genwqe_alloc_sgl(cd, m->nr_pages,
-						      &req->sgl_dma_addr[i],
-						      &req->sgl_size[i]);
-			if (req->sgl[i] == NULL) {
-				rc = -ENOMEM;
+			rc = genwqe_alloc_sync_sgl(cd, &req->sgls[i],
+						   (void __user *)u_addr,
+						   u_size);
+			if (rc != 0)
 				goto err_out;
-			}
-			genwqe_setup_sgl(cd, offs, u_size,
-					req->sgl[i],
-					req->sgl_dma_addr[i],
-					req->sgl_size[i],
-					m->dma_list,
-					page_offs,
-					nr_pages);
+
+			genwqe_setup_sgl(cd, &req->sgls[i],
+					 &m->dma_list[page_offs]);
 
 			*((__be64 *)&cmd->asiv[asiv_offs]) =
-				cpu_to_be64(req->sgl_dma_addr[i]);
+				cpu_to_be64(req->sgls[i].sgl_dma_addr);
 
 			break;
 		}
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index 6b1a6ef9f1a8..d049d271699c 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -275,67 +275,107 @@ static int genwqe_sgl_size(int num_pages)
 	return roundup(len, PAGE_SIZE);
 }
 
-struct sg_entry *genwqe_alloc_sgl(struct genwqe_dev *cd, int num_pages,
-				  dma_addr_t *dma_addr, size_t *sgl_size)
+/**
+ * genwqe_alloc_sync_sgl() - Allocate memory for sgl and overlapping pages
+ *
+ * Allocates memory for sgl and overlapping pages. Pages which might
+ * overlap other user-space memory blocks are being cached for DMAs,
+ * such that we do not run into syncronization issues. Data is copied
+ * from user-space into the cached pages.
+ */
+int genwqe_alloc_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl,
+			  void __user *user_addr, size_t user_size)
 {
+	int rc;
 	struct pci_dev *pci_dev = cd->pci_dev;
-	struct sg_entry *sgl;
 
-	*sgl_size = genwqe_sgl_size(num_pages);
-	if (get_order(*sgl_size) > MAX_ORDER) {
+	sgl->fpage_offs = offset_in_page((unsigned long)user_addr);
+	sgl->fpage_size = min_t(size_t, PAGE_SIZE-sgl->fpage_offs, user_size);
+	sgl->nr_pages = DIV_ROUND_UP(sgl->fpage_offs + user_size, PAGE_SIZE);
+	sgl->lpage_size = (user_size - sgl->fpage_size) % PAGE_SIZE;
+
+	dev_dbg(&pci_dev->dev, "[%s] uaddr=%p usize=%8ld nr_pages=%ld "
+		"fpage_offs=%lx fpage_size=%ld lpage_size=%ld\n",
+		__func__, user_addr, user_size, sgl->nr_pages,
+		sgl->fpage_offs, sgl->fpage_size, sgl->lpage_size);
+
+	sgl->user_addr = user_addr;
+	sgl->user_size = user_size;
+	sgl->sgl_size = genwqe_sgl_size(sgl->nr_pages);
+
+	if (get_order(sgl->sgl_size) > MAX_ORDER) {
 		dev_err(&pci_dev->dev,
 			"[%s] err: too much memory requested!\n", __func__);
-		return NULL;
+		return -ENOMEM;
 	}
 
-	sgl = __genwqe_alloc_consistent(cd, *sgl_size, dma_addr);
-	if (sgl == NULL) {
+	sgl->sgl = __genwqe_alloc_consistent(cd, sgl->sgl_size,
+					     &sgl->sgl_dma_addr);
+	if (sgl->sgl == NULL) {
 		dev_err(&pci_dev->dev,
 			"[%s] err: no memory available!\n", __func__);
-		return NULL;
+		return -ENOMEM;
 	}
 
-	return sgl;
+	/* Only use buffering on incomplete pages */
+	if ((sgl->fpage_size != 0) && (sgl->fpage_size != PAGE_SIZE)) {
+		sgl->fpage = __genwqe_alloc_consistent(cd, PAGE_SIZE,
+						       &sgl->fpage_dma_addr);
+		if (sgl->fpage == NULL)
+			goto err_out;
+
+		/* Sync with user memory */
+		if (copy_from_user(sgl->fpage + sgl->fpage_offs,
+				   user_addr, sgl->fpage_size)) {
+			rc = -EFAULT;
+			goto err_out;
+		}
+	}
+	if (sgl->lpage_size != 0) {
+		sgl->lpage = __genwqe_alloc_consistent(cd, PAGE_SIZE,
+						       &sgl->lpage_dma_addr);
+		if (sgl->lpage == NULL)
+			goto err_out1;
+
+		/* Sync with user memory */
+		if (copy_from_user(sgl->lpage, user_addr + user_size -
+				   sgl->lpage_size, sgl->lpage_size)) {
+			rc = -EFAULT;
+			goto err_out1;
+		}
+	}
+	return 0;
+
+ err_out1:
+	__genwqe_free_consistent(cd, PAGE_SIZE, sgl->fpage,
+				 sgl->fpage_dma_addr);
+ err_out:
+	__genwqe_free_consistent(cd, sgl->sgl_size, sgl->sgl,
+				 sgl->sgl_dma_addr);
+	return -ENOMEM;
 }
 
-int genwqe_setup_sgl(struct genwqe_dev *cd,
-		     unsigned long offs,
-		     unsigned long size,
-		     struct sg_entry *sgl,
-		     dma_addr_t dma_addr, size_t sgl_size,
-		     dma_addr_t *dma_list, int page_offs, int num_pages)
+int genwqe_setup_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl,
+		     dma_addr_t *dma_list)
 {
 	int i = 0, j = 0, p;
 	unsigned long dma_offs, map_offs;
-	struct pci_dev *pci_dev = cd->pci_dev;
 	dma_addr_t prev_daddr = 0;
 	struct sg_entry *s, *last_s = NULL;
-
-	/* sanity checks */
-	if (offs > PAGE_SIZE) {
-		dev_err(&pci_dev->dev,
-			"[%s] too large start offs %08lx\n", __func__, offs);
-		return -EFAULT;
-	}
-	if (sgl_size < genwqe_sgl_size(num_pages)) {
-		dev_err(&pci_dev->dev,
-			"[%s] sgl_size too small %08lx for %d pages\n",
-			__func__, sgl_size, num_pages);
-		return -EFAULT;
-	}
+	size_t size = sgl->user_size;
 
 	dma_offs = 128;		/* next block if needed/dma_offset */
-	map_offs = offs;	/* offset in first page */
+	map_offs = sgl->fpage_offs; /* offset in first page */
 
-	s = &sgl[0];		/* first set of 8 entries */
+	s = &sgl->sgl[0];	/* first set of 8 entries */
 	p = 0;			/* page */
-	while (p < num_pages) {
+	while (p < sgl->nr_pages) {
 		dma_addr_t daddr;
 		unsigned int size_to_map;
 
 		/* always write the chaining entry, cleanup is done later */
 		j = 0;
-		s[j].target_addr = cpu_to_be64(dma_addr + dma_offs);
+		s[j].target_addr = cpu_to_be64(sgl->sgl_dma_addr + dma_offs);
 		s[j].len	 = cpu_to_be32(128);
 		s[j].flags	 = cpu_to_be32(SG_CHAINED);
 		j++;
@@ -343,7 +383,17 @@ int genwqe_setup_sgl(struct genwqe_dev *cd,
 		while (j < 8) {
 			/* DMA mapping for requested page, offs, size */
 			size_to_map = min(size, PAGE_SIZE - map_offs);
-			daddr = dma_list[page_offs + p] + map_offs;
+
+			if ((p == 0) && (sgl->fpage != NULL)) {
+				daddr = sgl->fpage_dma_addr + map_offs;
+
+			} else if ((p == sgl->nr_pages - 1) &&
+				   (sgl->lpage != NULL)) {
+				daddr = sgl->lpage_dma_addr;
+			} else {
+				daddr = dma_list[p] + map_offs;
+			}
+
 			size -= size_to_map;
 			map_offs = 0;
 
@@ -358,7 +408,7 @@ int genwqe_setup_sgl(struct genwqe_dev *cd,
 							  size_to_map);
 
 				p++; /* process next page */
-				if (p == num_pages)
+				if (p == sgl->nr_pages)
 					goto fixup;  /* nothing to do */
 
 				prev_daddr = daddr + size_to_map;
@@ -374,7 +424,7 @@ int genwqe_setup_sgl(struct genwqe_dev *cd,
 			j++;
 
 			p++;	/* process next page */
-			if (p == num_pages)
+			if (p == sgl->nr_pages)
 				goto fixup;  /* nothing to do */
 		}
 		dma_offs += 128;
@@ -395,10 +445,50 @@ int genwqe_setup_sgl(struct genwqe_dev *cd,
 	return 0;
 }
 
-void genwqe_free_sgl(struct genwqe_dev *cd, struct sg_entry *sg_list,
-		    dma_addr_t dma_addr, size_t size)
+/**
+ * genwqe_free_sync_sgl() - Free memory for sgl and overlapping pages
+ *
+ * After the DMA transfer has been completed we free the memory for
+ * the sgl and the cached pages. Data is being transfered from cached
+ * pages into user-space buffers.
+ */
+int genwqe_free_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl)
 {
-	__genwqe_free_consistent(cd, size, sg_list, dma_addr);
+	int rc;
+	struct pci_dev *pci_dev = cd->pci_dev;
+
+	if (sgl->fpage) {
+		if (copy_to_user(sgl->user_addr, sgl->fpage + sgl->fpage_offs,
+				 sgl->fpage_size)) {
+			dev_err(&pci_dev->dev, "[%s] err: copying fpage!\n",
+				__func__);
+			rc = -EFAULT;
+		}
+		__genwqe_free_consistent(cd, PAGE_SIZE, sgl->fpage,
+					 sgl->fpage_dma_addr);
+		sgl->fpage = NULL;
+		sgl->fpage_dma_addr = 0;
+	}
+	if (sgl->lpage) {
+		if (copy_to_user(sgl->user_addr + sgl->user_size -
+				 sgl->lpage_size, sgl->lpage,
+				 sgl->lpage_size)) {
+			dev_err(&pci_dev->dev, "[%s] err: copying lpage!\n",
+				__func__);
+			rc = -EFAULT;
+		}
+		__genwqe_free_consistent(cd, PAGE_SIZE, sgl->lpage,
+					 sgl->lpage_dma_addr);
+		sgl->lpage = NULL;
+		sgl->lpage_dma_addr = 0;
+	}
+	__genwqe_free_consistent(cd, sgl->sgl_size, sgl->sgl,
+				 sgl->sgl_dma_addr);
+
+	sgl->sgl = NULL;
+	sgl->sgl_dma_addr = 0x0;
+	sgl->sgl_size = 0;
+	return rc;
 }
 
 /**
diff --git a/drivers/misc/genwqe/genwqe_driver.h b/drivers/misc/genwqe/genwqe_driver.h
index 46e916b36c70..cd5263163a6e 100644
--- a/drivers/misc/genwqe/genwqe_driver.h
+++ b/drivers/misc/genwqe/genwqe_driver.h
@@ -36,7 +36,7 @@
 #include <asm/byteorder.h>
 #include <linux/genwqe/genwqe_card.h>
 
-#define DRV_VERS_STRING		"2.0.0"
+#define DRV_VERS_STRING		"2.0.15"
 
 /*
  * Static minor number assignement, until we decide/implement
diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index 66f411a6e8ea..cabc04383685 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -115,6 +115,11 @@
 #define MEI_DEV_ID_LPT_HR     0x8CBA  /* Lynx Point H Refresh */
 
 #define MEI_DEV_ID_WPT_LP     0x9CBA  /* Wildcat Point LP */
+
+/* Host Firmware Status Registers in PCI Config Space */
+#define PCI_CFG_HFS_1         0x40
+#define PCI_CFG_HFS_2         0x48
+
 /*
  * MEI HW Section
  */
diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c
index 29b5af8efb71..4e3cba6da3f5 100644
--- a/drivers/misc/mei/interrupt.c
+++ b/drivers/misc/mei/interrupt.c
@@ -455,8 +455,7 @@ int mei_irq_write_handler(struct mei_device *dev, struct mei_cl_cb *cmpl_list)
 
 		cl->status = 0;
 		list_del(&cb->list);
-		if (MEI_WRITING == cl->writing_state &&
-		    cb->fop_type == MEI_FOP_WRITE &&
+		if (cb->fop_type == MEI_FOP_WRITE &&
 		    cl != &dev->iamthif_cl) {
 			cl_dbg(dev, cl, "MEI WRITE COMPLETE\n");
 			cl->writing_state = MEI_WRITE_COMPLETE;
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index b35594dbf52f..147413145c97 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -644,8 +644,7 @@ static unsigned int mei_poll(struct file *file, poll_table *wait)
 		goto out;
 	}
 
-	if (MEI_WRITE_COMPLETE == cl->writing_state)
-		mask |= (POLLIN | POLLRDNORM);
+	mask |= (POLLIN | POLLRDNORM);
 
 out:
 	mutex_unlock(&dev->device_lock);
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 1c8fd3a3e135..95889e2e31ff 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -97,15 +97,31 @@ static bool mei_me_quirk_probe(struct pci_dev *pdev,
 				const struct pci_device_id *ent)
 {
 	u32 reg;
-	if (ent->device == MEI_DEV_ID_PBG_1) {
-		pci_read_config_dword(pdev, 0x48, &reg);
-		/* make sure that bit 9 is up and bit 10 is down */
-		if ((reg & 0x600) == 0x200) {
-			dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n");
-			return false;
-		}
+	/* Cougar Point || Patsburg */
+	if (ent->device == MEI_DEV_ID_CPT_1 ||
+	    ent->device == MEI_DEV_ID_PBG_1) {
+		pci_read_config_dword(pdev, PCI_CFG_HFS_2, &reg);
+		/* make sure that bit 9 (NM) is up and bit 10 (DM) is down */
+		if ((reg & 0x600) == 0x200)
+			goto no_mei;
 	}
+
+	/* Lynx Point */
+	if (ent->device == MEI_DEV_ID_LPT_H  ||
+	    ent->device == MEI_DEV_ID_LPT_W  ||
+	    ent->device == MEI_DEV_ID_LPT_HR) {
+		/* Read ME FW Status check for SPS Firmware */
+		pci_read_config_dword(pdev, PCI_CFG_HFS_1, &reg);
+		/* if bits [19:16] = 15, running SPS Firmware */
+		if ((reg & 0xf0000) == 0xf0000)
+			goto no_mei;
+	}
+
 	return true;
+
+no_mei:
+	dev_info(&pdev->dev, "Device doesn't have valid ME Interface\n");
+	return false;
 }
 /**
  * mei_probe - Device Initialization Routine
diff --git a/drivers/vme/bridges/vme_tsi148.c b/drivers/vme/bridges/vme_tsi148.c
index 06990c6a1a69..61e706c0e00c 100644
--- a/drivers/vme/bridges/vme_tsi148.c
+++ b/drivers/vme/bridges/vme_tsi148.c
@@ -320,7 +320,7 @@ static int tsi148_irq_init(struct vme_bridge *tsi148_bridge)
 	struct pci_dev *pdev;
 	struct tsi148_driver *bridge;
 
-	pdev = container_of(tsi148_bridge->parent, struct pci_dev, dev);
+	pdev = to_pci_dev(tsi148_bridge->parent);
 
 	bridge = tsi148_bridge->driver_priv;
 
@@ -433,9 +433,7 @@ static void tsi148_irq_set(struct vme_bridge *tsi148_bridge, int level,
 		iowrite32be(tmp, bridge->base + TSI148_LCSR_INTEO);
 
 		if (sync != 0) {
-			pdev = container_of(tsi148_bridge->parent,
-				struct pci_dev, dev);
-
+			pdev = to_pci_dev(tsi148_bridge->parent);
 			synchronize_irq(pdev->irq);
 		}
 	} else {
@@ -741,7 +739,7 @@ static int tsi148_slave_get(struct vme_slave_resource *image, int *enabled,
 	reg_join(vme_bound_high, vme_bound_low, &vme_bound);
 	reg_join(pci_offset_high, pci_offset_low, &pci_offset);
 
-	*pci_base = (dma_addr_t)vme_base + pci_offset;
+	*pci_base = (dma_addr_t)(*vme_base + pci_offset);
 
 	*enabled = 0;
 	*aspace = 0;
@@ -814,7 +812,7 @@ static int tsi148_alloc_resource(struct vme_master_resource *image,
 
 	tsi148_bridge = image->parent;
 
-	pdev = container_of(tsi148_bridge->parent, struct pci_dev, dev);
+	pdev = to_pci_dev(tsi148_bridge->parent);
 
 	existing_size = (unsigned long long)(image->bus_resource.end -
 		image->bus_resource.start);
@@ -910,11 +908,15 @@ static int tsi148_master_set(struct vme_master_resource *image, int enabled,
 	unsigned long long pci_bound, vme_offset, pci_base;
 	struct vme_bridge *tsi148_bridge;
 	struct tsi148_driver *bridge;
+	struct pci_bus_region region;
+	struct pci_dev *pdev;
 
 	tsi148_bridge = image->parent;
 
 	bridge = tsi148_bridge->driver_priv;
 
+	pdev = to_pci_dev(tsi148_bridge->parent);
+
 	/* Verify input data */
 	if (vme_base & 0xFFFF) {
 		dev_err(tsi148_bridge->parent, "Invalid VME Window "
@@ -949,7 +951,9 @@ static int tsi148_master_set(struct vme_master_resource *image, int enabled,
 		pci_bound = 0;
 		vme_offset = 0;
 	} else {
-		pci_base = (unsigned long long)image->bus_resource.start;
+		pcibios_resource_to_bus(pdev->bus, &region,
+					&image->bus_resource);
+		pci_base = region.start;
 
 		/*
 		 * Bound address is a valid address for the window, adjust
@@ -2232,7 +2236,7 @@ static void *tsi148_alloc_consistent(struct device *parent, size_t size,
 	struct pci_dev *pdev;
 
 	/* Find pci_dev container of dev */
-	pdev = container_of(parent, struct pci_dev, dev);
+	pdev = to_pci_dev(parent);
 
 	return pci_alloc_consistent(pdev, size, dma);
 }
@@ -2243,7 +2247,7 @@ static void tsi148_free_consistent(struct device *parent, size_t size,
 	struct pci_dev *pdev;
 
 	/* Find pci_dev container of dev */
-	pdev = container_of(parent, struct pci_dev, dev);
+	pdev = to_pci_dev(parent);
 
 	pci_free_consistent(pdev, size, vaddr, dma);
 }
diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c
index b96f61b15dc6..ff52618cafbe 100644
--- a/drivers/w1/w1.c
+++ b/drivers/w1/w1.c
@@ -614,27 +614,11 @@ end:
 	return err;
 }
 
-/*
- * Handle sysfs file creation and removal here, before userspace is told that
- * the device is added / removed from the system
- */
-static int w1_bus_notify(struct notifier_block *nb, unsigned long action,
-			 void *data)
+static int w1_family_notify(unsigned long action, struct w1_slave *sl)
 {
-	struct device *dev = data;
-	struct w1_slave *sl;
 	struct w1_family_ops *fops;
 	int err;
 
-	/*
-	 * Only care about slave devices at the moment.  Yes, we should use a
-	 * separate "type" for this, but for now, look at the release function
-	 * to know which type it is...
-	 */
-	if (dev->release != w1_slave_release)
-		return 0;
-
-	sl = dev_to_w1_slave(dev);
 	fops = sl->family->fops;
 
 	if (!fops)
@@ -673,10 +657,6 @@ static int w1_bus_notify(struct notifier_block *nb, unsigned long action,
 	return 0;
 }
 
-static struct notifier_block w1_bus_nb = {
-	.notifier_call = w1_bus_notify,
-};
-
 static int __w1_attach_slave_device(struct w1_slave *sl)
 {
 	int err;
@@ -698,6 +678,9 @@ static int __w1_attach_slave_device(struct w1_slave *sl)
 	dev_dbg(&sl->dev, "%s: registering %s as %p.\n", __func__,
 		dev_name(&sl->dev), sl);
 
+	/* suppress for w1_family_notify before sending KOBJ_ADD */
+	dev_set_uevent_suppress(&sl->dev, true);
+
 	err = device_register(&sl->dev);
 	if (err < 0) {
 		dev_err(&sl->dev,
@@ -705,7 +688,7 @@ static int __w1_attach_slave_device(struct w1_slave *sl)
 			dev_name(&sl->dev), err);
 		return err;
 	}
-
+	w1_family_notify(BUS_NOTIFY_ADD_DEVICE, sl);
 
 	dev_set_uevent_suppress(&sl->dev, false);
 	kobject_uevent(&sl->dev.kobj, KOBJ_ADD);
@@ -799,6 +782,7 @@ int w1_unref_slave(struct w1_slave *sl)
 		msg.type = W1_SLAVE_REMOVE;
 		w1_netlink_send(sl->master, &msg);
 
+		w1_family_notify(BUS_NOTIFY_DEL_DEVICE, sl);
 		device_unregister(&sl->dev);
 		#ifdef DEBUG
 		memset(sl, 0, sizeof(*sl));
@@ -1186,10 +1170,6 @@ static int __init w1_init(void)
 		goto err_out_exit_init;
 	}
 
-	retval = bus_register_notifier(&w1_bus_type, &w1_bus_nb);
-	if (retval)
-		goto err_out_bus_unregister;
-
 	retval = driver_register(&w1_master_driver);
 	if (retval) {
 		printk(KERN_ERR
diff --git a/drivers/w1/w1_netlink.c b/drivers/w1/w1_netlink.c
index 5234964fe001..a02704a59321 100644
--- a/drivers/w1/w1_netlink.c
+++ b/drivers/w1/w1_netlink.c
@@ -300,12 +300,6 @@ static int w1_process_command_root(struct cn_msg *msg,
 	struct w1_netlink_msg *w;
 	u32 *id;
 
-	if (mcmd->type != W1_LIST_MASTERS) {
-		printk(KERN_NOTICE "%s: msg: %x.%x, wrong type: %u, len: %u.\n",
-			__func__, msg->id.idx, msg->id.val, mcmd->type, mcmd->len);
-		return -EPROTO;
-	}
-
 	cn = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!cn)
 		return -ENOMEM;
@@ -441,6 +435,9 @@ static void w1_process_cb(struct w1_master *dev, struct w1_async_cmd *async_cmd)
 		w1_netlink_send_error(&node->block->msg, node->m, cmd,
 			node->block->portid, err);
 
+	/* ref taken in w1_search_slave or w1_search_master_id when building
+	 * the block
+	 */
 	if (sl)
 		w1_unref_slave(sl);
 	else
@@ -503,30 +500,42 @@ static void w1_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp)
 
 	msg_len = msg->len;
 	while (msg_len && !err) {
-		struct w1_reg_num id;
-		u16 mlen = m->len;
 
 		dev = NULL;
 		sl = NULL;
 
-		memcpy(&id, m->id.id, sizeof(id));
-#if 0
-		printk("%s: %02x.%012llx.%02x: type=%02x, len=%u.\n",
-				__func__, id.family, (unsigned long long)id.id, id.crc, m->type, m->len);
-#endif
 		if (m->len + sizeof(struct w1_netlink_msg) > msg_len) {
 			err = -E2BIG;
 			break;
 		}
 
+		/* execute on this thread, no need to process later */
+		if (m->type == W1_LIST_MASTERS) {
+			err = w1_process_command_root(msg, m, nsp->portid);
+			goto out_cont;
+		}
+
+		/* All following message types require additional data,
+		 * check here before references are taken.
+		 */
+		if (!m->len) {
+			err = -EPROTO;
+			goto out_cont;
+		}
+
+		/* both search calls take reference counts */
 		if (m->type == W1_MASTER_CMD) {
 			dev = w1_search_master_id(m->id.mst.id);
 		} else if (m->type == W1_SLAVE_CMD) {
-			sl = w1_search_slave(&id);
+			sl = w1_search_slave((struct w1_reg_num *)m->id.id);
 			if (sl)
 				dev = sl->master;
 		} else {
-			err = w1_process_command_root(msg, m, nsp->portid);
+			printk(KERN_NOTICE
+				"%s: msg: %x.%x, wrong type: %u, len: %u.\n",
+				__func__, msg->id.idx, msg->id.val,
+				m->type, m->len);
+			err = -EPROTO;
 			goto out_cont;
 		}
 
@@ -536,8 +545,6 @@ static void w1_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp)
 		}
 
 		err = 0;
-		if (!mlen)
-			goto out_cont;
 
 		atomic_inc(&block->refcnt);
 		node->async.cb = w1_process_cb;
@@ -557,7 +564,8 @@ out_cont:
 		if (err)
 			w1_netlink_send_error(msg, m, NULL, nsp->portid, err);
 		msg_len -= sizeof(struct w1_netlink_msg) + m->len;
-		m = (struct w1_netlink_msg *)(((u8 *)m) + sizeof(struct w1_netlink_msg) + m->len);
+		m = (struct w1_netlink_msg *)(((u8 *)m) +
+			sizeof(struct w1_netlink_msg) + m->len);
 
 		/*
 		 * Let's allow requests for nonexisting devices.
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index ab7359fde987..2d7b4f139c32 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -147,15 +147,17 @@ hv_get_ringbuffer_availbytes(struct hv_ring_buffer_info *rbi,
  * 0 . 13 (Windows Server 2008)
  * 1 . 1  (Windows 7)
  * 2 . 4  (Windows 8)
+ * 3 . 0  (Windows 8 R2)
  */
 
 #define VERSION_WS2008  ((0 << 16) | (13))
 #define VERSION_WIN7    ((1 << 16) | (1))
 #define VERSION_WIN8    ((2 << 16) | (4))
+#define VERSION_WIN8_1    ((3 << 16) | (0))
 
 #define VERSION_INVAL -1
 
-#define VERSION_CURRENT VERSION_WIN8
+#define VERSION_CURRENT VERSION_WIN8_1
 
 /* Make maximum size of pipe payload of 16K */
 #define MAX_PIPE_DATA_PAYLOAD		(sizeof(u8) * 16384)
diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h
index 9beb7c991638..78e4a86030dd 100644
--- a/include/uapi/linux/hyperv.h
+++ b/include/uapi/linux/hyperv.h
@@ -305,6 +305,7 @@ enum hv_kvp_exchg_pool {
 #define HV_ERROR_DEVICE_NOT_CONNECTED	0x8007048F
 #define HV_INVALIDARG			0x80070057
 #define HV_GUID_NOTFOUND		0x80041002
+#define HV_ERROR_ALREADY_EXISTS		0x80070050
 
 #define ADDR_FAMILY_NONE	0x00
 #define ADDR_FAMILY_IPV4	0x01
diff --git a/tools/hv/hv_fcopy_daemon.c b/tools/hv/hv_fcopy_daemon.c
index 4ecc4fd0bc1b..fba1c75aa484 100644
--- a/tools/hv/hv_fcopy_daemon.c
+++ b/tools/hv/hv_fcopy_daemon.c
@@ -82,8 +82,10 @@ static int hv_start_fcopy(struct hv_start_fcopy *smsg)
 
 	if (!access(target_fname, F_OK)) {
 		syslog(LOG_INFO, "File: %s exists", target_fname);
-		if (!smsg->copy_flags & OVER_WRITE)
+		if (!(smsg->copy_flags & OVER_WRITE)) {
+			error = HV_ERROR_ALREADY_EXISTS;
 			goto done;
+		}
 	}
 
 	target_fd = open(target_fname, O_RDWR | O_CREAT | O_CLOEXEC, 0744);