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

Pull in 'net' to take in the bug fixes that didn't make it into
3.8-final.

Also, deal with the semantic conflict of the change made to
net/ipv6/xfrm6_policy.c   A missing rt6->n neighbour release
was added to 'net', but in 'net-next' we no longer cache the
neighbour entries in the ipv6 routes so that change is not
appropriate there.

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

18 files changed, 170 insertions, 90 deletions

diff --git a/drivers/gpu/drm/nouveau/core/core/falcon.c b/drivers/gpu/drm/nouveau/core/core/falcon.c
index 6b0843c3387..e05c1577758 100644
--- a/drivers/gpu/drm/nouveau/core/core/falcon.c
+++ b/drivers/gpu/drm/nouveau/core/core/falcon.c
@@ -73,8 +73,11 @@ _nouveau_falcon_init(struct nouveau_object *object)
 	nv_debug(falcon, "data limit: %d\n", falcon->data.limit);
 
 	/* wait for 'uc halted' to be signalled before continuing */
-	if (falcon->secret) {
-		nv_wait(falcon, 0x008, 0x00000010, 0x00000010);
+	if (falcon->secret && falcon->version < 4) {
+		if (!falcon->version)
+			nv_wait(falcon, 0x008, 0x00000010, 0x00000010);
+		else
+			nv_wait(falcon, 0x180, 0x80000000, 0);
 		nv_wo32(falcon, 0x004, 0x00000010);
 	}
 
diff --git a/drivers/gpu/drm/nouveau/core/core/subdev.c b/drivers/gpu/drm/nouveau/core/core/subdev.c
index f74c30aa33a..48f06378d3f 100644
--- a/drivers/gpu/drm/nouveau/core/core/subdev.c
+++ b/drivers/gpu/drm/nouveau/core/core/subdev.c
@@ -99,7 +99,7 @@ nouveau_subdev_create_(struct nouveau_object *parent,
 	if (ret)
 		return ret;
 
-	mutex_init(&subdev->mutex);
+	__mutex_init(&subdev->mutex, subname, &oclass->lock_class_key);
 	subdev->name = subname;
 
 	if (parent) {
diff --git a/drivers/gpu/drm/nouveau/core/include/core/object.h b/drivers/gpu/drm/nouveau/core/include/core/object.h
index 5982935ee23..106bb19fdd9 100644
--- a/drivers/gpu/drm/nouveau/core/include/core/object.h
+++ b/drivers/gpu/drm/nouveau/core/include/core/object.h
@@ -50,10 +50,13 @@ int  nouveau_object_fini(struct nouveau_object *, bool suspend);
 
 extern struct nouveau_ofuncs nouveau_object_ofuncs;
 
+/* Don't allocate dynamically, because lockdep needs lock_class_keys to be in
+ * ".data". */
 struct nouveau_oclass {
 	u32 handle;
-	struct nouveau_ofuncs *ofuncs;
-	struct nouveau_omthds *omthds;
+	struct nouveau_ofuncs * const ofuncs;
+	struct nouveau_omthds * const omthds;
+	struct lock_class_key lock_class_key;
 };
 
 #define nv_oclass(o)    nv_object(o)->oclass
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/base.c b/drivers/gpu/drm/nouveau/core/subdev/fb/base.c
index d6d16007ec1..d62045f454b 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/base.c
@@ -86,8 +86,8 @@ nouveau_fb_preinit(struct nouveau_fb *pfb)
 			return ret;
 	}
 
-	if (!nouveau_mm_initialised(&pfb->tags) && tags) {
-		ret = nouveau_mm_init(&pfb->tags, 0, ++tags, 1);
+	if (!nouveau_mm_initialised(&pfb->tags)) {
+		ret = nouveau_mm_init(&pfb->tags, 0, tags ? ++tags : 0, 1);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c b/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c
index 487cb8c6c20..eac236ed19b 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/fb/nv50.c
@@ -99,7 +99,7 @@ nv50_fb_vram_init(struct nouveau_fb *pfb)
 	struct nouveau_bios *bios = nouveau_bios(device);
 	const u32 rsvd_head = ( 256 * 1024) >> 12; /* vga memory */
 	const u32 rsvd_tail = (1024 * 1024) >> 12; /* vbios etc */
-	u32 size;
+	u32 size, tags = 0;
 	int ret;
 
 	pfb->ram.size = nv_rd32(pfb, 0x10020c);
@@ -140,10 +140,11 @@ nv50_fb_vram_init(struct nouveau_fb *pfb)
 			return ret;
 
 		pfb->ram.ranks = (nv_rd32(pfb, 0x100200) & 0x4) ? 2 : 1;
+		tags = nv_rd32(pfb, 0x100320);
 		break;
 	}
 
-	return nv_rd32(pfb, 0x100320);
+	return tags;
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 69d7b1d0b9d..1699a9083a2 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -28,6 +28,7 @@
  */
 
 #include <core/engine.h>
+#include <linux/swiotlb.h>
 
 #include <subdev/fb.h>
 #include <subdev/vm.h>
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 8b090f1eb51..5e7aef23825 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -245,6 +245,8 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 	return 0;
 }
 
+static struct lock_class_key drm_client_lock_class_key;
+
 static int
 nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 {
@@ -256,6 +258,7 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 	ret = nouveau_cli_create(pdev, "DRM", sizeof(*drm), (void**)&drm);
 	if (ret)
 		return ret;
+	lockdep_set_class(&drm->client.mutex, &drm_client_lock_class_key);
 
 	dev->dev_private = drm;
 	drm->dev = dev;
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 7a445666e71..ee4cff534f1 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -2909,14 +2909,14 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				return -EINVAL;
 			}
 			if (tiled) {
-				dst_offset = ib[idx+1];
+				dst_offset = radeon_get_ib_value(p, idx+1);
 				dst_offset <<= 8;
 
 				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 				p->idx += count + 7;
 			} else {
-				dst_offset = ib[idx+1];
-				dst_offset |= ((u64)(ib[idx+2] & 0xff)) << 32;
+				dst_offset = radeon_get_ib_value(p, idx+1);
+				dst_offset |= ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32;
 
 				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 				ib[idx+2] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
@@ -2954,12 +2954,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 							DRM_ERROR("bad L2T, frame to fields DMA_PACKET_COPY\n");
 							return -EINVAL;
 						}
-						dst_offset = ib[idx+1];
+						dst_offset = radeon_get_ib_value(p, idx+1);
 						dst_offset <<= 8;
-						dst2_offset = ib[idx+2];
+						dst2_offset = radeon_get_ib_value(p, idx+2);
 						dst2_offset <<= 8;
-						src_offset = ib[idx+8];
-						src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
+						src_offset = radeon_get_ib_value(p, idx+8);
+						src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32;
 						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 							dev_warn(p->dev, "DMA L2T, frame to fields src buffer too small (%llu %lu)\n",
 								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
@@ -3014,12 +3014,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 							DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
 							return -EINVAL;
 						}
-						dst_offset = ib[idx+1];
+						dst_offset = radeon_get_ib_value(p, idx+1);
 						dst_offset <<= 8;
-						dst2_offset = ib[idx+2];
+						dst2_offset = radeon_get_ib_value(p, idx+2);
 						dst2_offset <<= 8;
-						src_offset = ib[idx+8];
-						src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
+						src_offset = radeon_get_ib_value(p, idx+8);
+						src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32;
 						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 							dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
 								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
@@ -3046,22 +3046,22 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 						/* detile bit */
 						if (idx_value & (1 << 31)) {
 							/* tiled src, linear dst */
-							src_offset = ib[idx+1];
+							src_offset = radeon_get_ib_value(p, idx+1);
 							src_offset <<= 8;
 							ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
 
-							dst_offset = ib[idx+7];
-							dst_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+							dst_offset = radeon_get_ib_value(p, idx+7);
+							dst_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
 							ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 							ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
 						} else {
 							/* linear src, tiled dst */
-							src_offset = ib[idx+7];
-							src_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+							src_offset = radeon_get_ib_value(p, idx+7);
+							src_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
 							ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
 							ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
 
-							dst_offset = ib[idx+1];
+							dst_offset = radeon_get_ib_value(p, idx+1);
 							dst_offset <<= 8;
 							ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 						}
@@ -3098,12 +3098,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 							DRM_ERROR("bad L2T, broadcast DMA_PACKET_COPY\n");
 							return -EINVAL;
 						}
-						dst_offset = ib[idx+1];
+						dst_offset = radeon_get_ib_value(p, idx+1);
 						dst_offset <<= 8;
-						dst2_offset = ib[idx+2];
+						dst2_offset = radeon_get_ib_value(p, idx+2);
 						dst2_offset <<= 8;
-						src_offset = ib[idx+8];
-						src_offset |= ((u64)(ib[idx+9] & 0xff)) << 32;
+						src_offset = radeon_get_ib_value(p, idx+8);
+						src_offset |= ((u64)(radeon_get_ib_value(p, idx+9) & 0xff)) << 32;
 						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 							dev_warn(p->dev, "DMA L2T, broadcast src buffer too small (%llu %lu)\n",
 								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
@@ -3135,22 +3135,22 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 						/* detile bit */
 						if (idx_value & (1 << 31)) {
 							/* tiled src, linear dst */
-							src_offset = ib[idx+1];
+							src_offset = radeon_get_ib_value(p, idx+1);
 							src_offset <<= 8;
 							ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
 
-							dst_offset = ib[idx+7];
-							dst_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+							dst_offset = radeon_get_ib_value(p, idx+7);
+							dst_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
 							ib[idx+7] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 							ib[idx+8] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
 						} else {
 							/* linear src, tiled dst */
-							src_offset = ib[idx+7];
-							src_offset |= ((u64)(ib[idx+8] & 0xff)) << 32;
+							src_offset = radeon_get_ib_value(p, idx+7);
+							src_offset |= ((u64)(radeon_get_ib_value(p, idx+8) & 0xff)) << 32;
 							ib[idx+7] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
 							ib[idx+8] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
 
-							dst_offset = ib[idx+1];
+							dst_offset = radeon_get_ib_value(p, idx+1);
 							dst_offset <<= 8;
 							ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 						}
@@ -3176,10 +3176,10 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 					switch (misc) {
 					case 0:
 						/* L2L, byte */
-						src_offset = ib[idx+2];
-						src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
-						dst_offset = ib[idx+1];
-						dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
+						src_offset = radeon_get_ib_value(p, idx+2);
+						src_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
+						dst_offset = radeon_get_ib_value(p, idx+1);
+						dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32;
 						if ((src_offset + count) > radeon_bo_size(src_reloc->robj)) {
 							dev_warn(p->dev, "DMA L2L, byte src buffer too small (%llu %lu)\n",
 								 src_offset + count, radeon_bo_size(src_reloc->robj));
@@ -3216,12 +3216,12 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 							DRM_ERROR("bad L2L, dw, broadcast DMA_PACKET_COPY\n");
 							return -EINVAL;
 						}
-						dst_offset = ib[idx+1];
-						dst_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
-						dst2_offset = ib[idx+2];
-						dst2_offset |= ((u64)(ib[idx+5] & 0xff)) << 32;
-						src_offset = ib[idx+3];
-						src_offset |= ((u64)(ib[idx+6] & 0xff)) << 32;
+						dst_offset = radeon_get_ib_value(p, idx+1);
+						dst_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
+						dst2_offset = radeon_get_ib_value(p, idx+2);
+						dst2_offset |= ((u64)(radeon_get_ib_value(p, idx+5) & 0xff)) << 32;
+						src_offset = radeon_get_ib_value(p, idx+3);
+						src_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32;
 						if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 							dev_warn(p->dev, "DMA L2L, dw, broadcast src buffer too small (%llu %lu)\n",
 								 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
@@ -3251,10 +3251,10 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 					}
 				} else {
 					/* L2L, dw */
-					src_offset = ib[idx+2];
-					src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
-					dst_offset = ib[idx+1];
-					dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
+					src_offset = radeon_get_ib_value(p, idx+2);
+					src_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
+					dst_offset = radeon_get_ib_value(p, idx+1);
+					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32;
 					if ((src_offset + (count * 4)) > radeon_bo_size(src_reloc->robj)) {
 						dev_warn(p->dev, "DMA L2L, dw src buffer too small (%llu %lu)\n",
 							 src_offset + (count * 4), radeon_bo_size(src_reloc->robj));
@@ -3279,8 +3279,8 @@ int evergreen_dma_cs_parse(struct radeon_cs_parser *p)
 				DRM_ERROR("bad DMA_PACKET_CONSTANT_FILL\n");
 				return -EINVAL;
 			}
-			dst_offset = ib[idx+1];
-			dst_offset |= ((u64)(ib[idx+3] & 0x00ff0000)) << 16;
+			dst_offset = radeon_get_ib_value(p, idx+1);
+			dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0x00ff0000)) << 16;
 			if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
 				dev_warn(p->dev, "DMA constant fill buffer too small (%llu %lu)\n",
 					 dst_offset, radeon_bo_size(dst_reloc->robj));
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 69ec24ab8d6..9b2512bf1a4 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -2623,14 +2623,14 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p)
 				return -EINVAL;
 			}
 			if (tiled) {
-				dst_offset = ib[idx+1];
+				dst_offset = radeon_get_ib_value(p, idx+1);
 				dst_offset <<= 8;
 
 				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 				p->idx += count + 5;
 			} else {
-				dst_offset = ib[idx+1];
-				dst_offset |= ((u64)(ib[idx+2] & 0xff)) << 32;
+				dst_offset = radeon_get_ib_value(p, idx+1);
+				dst_offset |= ((u64)(radeon_get_ib_value(p, idx+2) & 0xff)) << 32;
 
 				ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 				ib[idx+2] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
@@ -2658,32 +2658,32 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p)
 				/* detile bit */
 				if (idx_value & (1 << 31)) {
 					/* tiled src, linear dst */
-					src_offset = ib[idx+1];
+					src_offset = radeon_get_ib_value(p, idx+1);
 					src_offset <<= 8;
 					ib[idx+1] += (u32)(src_reloc->lobj.gpu_offset >> 8);
 
-					dst_offset = ib[idx+5];
-					dst_offset |= ((u64)(ib[idx+6] & 0xff)) << 32;
+					dst_offset = radeon_get_ib_value(p, idx+5);
+					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32;
 					ib[idx+5] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 					ib[idx+6] += upper_32_bits(dst_reloc->lobj.gpu_offset) & 0xff;
 				} else {
 					/* linear src, tiled dst */
-					src_offset = ib[idx+5];
-					src_offset |= ((u64)(ib[idx+6] & 0xff)) << 32;
+					src_offset = radeon_get_ib_value(p, idx+5);
+					src_offset |= ((u64)(radeon_get_ib_value(p, idx+6) & 0xff)) << 32;
 					ib[idx+5] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
 					ib[idx+6] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
 
-					dst_offset = ib[idx+1];
+					dst_offset = radeon_get_ib_value(p, idx+1);
 					dst_offset <<= 8;
 					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset >> 8);
 				}
 				p->idx += 7;
 			} else {
 				if (p->family >= CHIP_RV770) {
-					src_offset = ib[idx+2];
-					src_offset |= ((u64)(ib[idx+4] & 0xff)) << 32;
-					dst_offset = ib[idx+1];
-					dst_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
+					src_offset = radeon_get_ib_value(p, idx+2);
+					src_offset |= ((u64)(radeon_get_ib_value(p, idx+4) & 0xff)) << 32;
+					dst_offset = radeon_get_ib_value(p, idx+1);
+					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32;
 
 					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 					ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
@@ -2691,10 +2691,10 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p)
 					ib[idx+4] += upper_32_bits(src_reloc->lobj.gpu_offset) & 0xff;
 					p->idx += 5;
 				} else {
-					src_offset = ib[idx+2];
-					src_offset |= ((u64)(ib[idx+3] & 0xff)) << 32;
-					dst_offset = ib[idx+1];
-					dst_offset |= ((u64)(ib[idx+3] & 0xff0000)) << 16;
+					src_offset = radeon_get_ib_value(p, idx+2);
+					src_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff)) << 32;
+					dst_offset = radeon_get_ib_value(p, idx+1);
+					dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0xff0000)) << 16;
 
 					ib[idx+1] += (u32)(dst_reloc->lobj.gpu_offset & 0xfffffffc);
 					ib[idx+2] += (u32)(src_reloc->lobj.gpu_offset & 0xfffffffc);
@@ -2724,8 +2724,8 @@ int r600_dma_cs_parse(struct radeon_cs_parser *p)
 				DRM_ERROR("bad DMA_PACKET_WRITE\n");
 				return -EINVAL;
 			}
-			dst_offset = ib[idx+1];
-			dst_offset |= ((u64)(ib[idx+3] & 0x00ff0000)) << 16;
+			dst_offset = radeon_get_ib_value(p, idx+1);
+			dst_offset |= ((u64)(radeon_get_ib_value(p, idx+3) & 0x00ff0000)) << 16;
 			if ((dst_offset + (count * 4)) > radeon_bo_size(dst_reloc->robj)) {
 				dev_warn(p->dev, "DMA constant fill buffer too small (%llu %lu)\n",
 					 dst_offset + (count * 4), radeon_bo_size(dst_reloc->robj));
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 1d8ff2f850b..93f760e27a9 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -38,6 +38,7 @@
 #include <drm/radeon_drm.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/swiotlb.h>
 #include "radeon_reg.h"
 #include "radeon.h"
 
diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c
index 358cd7ee905..7cd74e29cbc 100644
--- a/drivers/input/joystick/analog.c
+++ b/drivers/input/joystick/analog.c
@@ -162,7 +162,7 @@ static unsigned int get_time_pit(void)
 #define GET_TIME(x)	do { x = get_cycles(); } while (0)
 #define DELTA(x,y)	((y)-(x))
 #define TIME_NAME	"PCC"
-#elif defined(CONFIG_MN10300)
+#elif defined(CONFIG_MN10300) || defined(CONFIG_TILE)
 #define GET_TIME(x)	do { x = get_cycles(); } while (0)
 #define DELTA(x, y)	((x) - (y))
 #define TIME_NAME	"TSC"
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 571b5145c07..8f333151743 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -21,7 +21,7 @@
 
 #include "atl1c.h"
 
-#define ATL1C_DRV_VERSION "1.0.1.0-NAPI"
+#define ATL1C_DRV_VERSION "1.0.1.1-NAPI"
 char atl1c_driver_name[] = "atl1c";
 char atl1c_driver_version[] = ATL1C_DRV_VERSION;
 
@@ -1649,6 +1649,7 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter)
 	u16 num_alloc = 0;
 	u16 rfd_next_to_use, next_next;
 	struct atl1c_rx_free_desc *rfd_desc;
+	dma_addr_t mapping;
 
 	next_next = rfd_next_to_use = rfd_ring->next_to_use;
 	if (++next_next == rfd_ring->count)
@@ -1675,9 +1676,18 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter)
 		ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY);
 		buffer_info->skb = skb;
 		buffer_info->length = adapter->rx_buffer_len;
-		buffer_info->dma = pci_map_single(pdev, vir_addr,
+		mapping = pci_map_single(pdev, vir_addr,
 						buffer_info->length,
 						PCI_DMA_FROMDEVICE);
+		if (unlikely(pci_dma_mapping_error(pdev, mapping))) {
+			dev_kfree_skb(skb);
+			buffer_info->skb = NULL;
+			buffer_info->length = 0;
+			ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_FREE);
+			netif_warn(adapter, rx_err, adapter->netdev, "RX pci_map_single failed");
+			break;
+		}
+		buffer_info->dma = mapping;
 		ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_SINGLE,
 			ATL1C_PCIMAP_FROMDEVICE);
 		rfd_desc->buffer_addr = cpu_to_le64(buffer_info->dma);
@@ -2012,7 +2022,29 @@ check_sum:
 	return 0;
 }
 
-static void atl1c_tx_map(struct atl1c_adapter *adapter,
+static void atl1c_tx_rollback(struct atl1c_adapter *adpt,
+			      struct atl1c_tpd_desc *first_tpd,
+			      enum atl1c_trans_queue type)
+{
+	struct atl1c_tpd_ring *tpd_ring = &adpt->tpd_ring[type];
+	struct atl1c_buffer *buffer_info;
+	struct atl1c_tpd_desc *tpd;
+	u16 first_index, index;
+
+	first_index = first_tpd - (struct atl1c_tpd_desc *)tpd_ring->desc;
+	index = first_index;
+	while (index != tpd_ring->next_to_use) {
+		tpd = ATL1C_TPD_DESC(tpd_ring, index);
+		buffer_info = &tpd_ring->buffer_info[index];
+		atl1c_clean_buffer(adpt->pdev, buffer_info, 0);
+		memset(tpd, 0, sizeof(struct atl1c_tpd_desc));
+		if (++index == tpd_ring->count)
+			index = 0;
+	}
+	tpd_ring->next_to_use = first_index;
+}
+
+static int atl1c_tx_map(struct atl1c_adapter *adapter,
 		      struct sk_buff *skb, struct atl1c_tpd_desc *tpd,
 			enum atl1c_trans_queue type)
 {
@@ -2037,7 +2069,10 @@ static void atl1c_tx_map(struct atl1c_adapter *adapter,
 		buffer_info->length = map_len;
 		buffer_info->dma = pci_map_single(adapter->pdev,
 					skb->data, hdr_len, PCI_DMA_TODEVICE);
-		ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY);
+		if (unlikely(pci_dma_mapping_error(adapter->pdev,
+						   buffer_info->dma)))
+			goto err_dma;
+
 		ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_SINGLE,
 			ATL1C_PCIMAP_TODEVICE);
 		mapped_len += map_len;
@@ -2059,6 +2094,10 @@ static void atl1c_tx_map(struct atl1c_adapter *adapter,
 		buffer_info->dma =
 			pci_map_single(adapter->pdev, skb->data + mapped_len,
 					buffer_info->length, PCI_DMA_TODEVICE);
+		if (unlikely(pci_dma_mapping_error(adapter->pdev,
+						   buffer_info->dma)))
+			goto err_dma;
+
 		ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY);
 		ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_SINGLE,
 			ATL1C_PCIMAP_TODEVICE);
@@ -2080,6 +2119,9 @@ static void atl1c_tx_map(struct atl1c_adapter *adapter,
 						    frag, 0,
 						    buffer_info->length,
 						    DMA_TO_DEVICE);
+		if (dma_mapping_error(&adapter->pdev->dev, buffer_info->dma))
+			goto err_dma;
+
 		ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_BUSY);
 		ATL1C_SET_PCIMAP_TYPE(buffer_info, ATL1C_PCIMAP_PAGE,
 			ATL1C_PCIMAP_TODEVICE);
@@ -2092,6 +2134,13 @@ static void atl1c_tx_map(struct atl1c_adapter *adapter,
 	/* The last buffer info contain the skb address,
 	   so it will be free after unmap */
 	buffer_info->skb = skb;
+
+	return 0;
+
+err_dma:
+	buffer_info->dma = 0;
+	buffer_info->length = 0;
+	return -1;
 }
 
 static void atl1c_tx_queue(struct atl1c_adapter *adapter, struct sk_buff *skb,
@@ -2154,10 +2203,18 @@ static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb,
 	if (skb_network_offset(skb) != ETH_HLEN)
 		tpd->word1 |= 1 << TPD_ETH_TYPE_SHIFT; /* Ethernet frame */
 
-	atl1c_tx_map(adapter, skb, tpd, type);
-	atl1c_tx_queue(adapter, skb, tpd, type);
+	if (atl1c_tx_map(adapter, skb, tpd, type) < 0) {
+		netif_info(adapter, tx_done, adapter->netdev,
+			   "tx-skb droppted due to dma error\n");
+		/* roll back tpd/buffer */
+		atl1c_tx_rollback(adapter, tpd, type);
+		spin_unlock_irqrestore(&adapter->tx_lock, flags);
+		dev_kfree_skb(skb);
+	} else {
+		atl1c_tx_queue(adapter, skb, tpd, type);
+		spin_unlock_irqrestore(&adapter->tx_lock, flags);
+	}
 
-	spin_unlock_irqrestore(&adapter->tx_lock, flags);
 	return NETDEV_TX_OK;
 }
 
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 352190b9ebe..79039439bfd 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -693,6 +693,11 @@ static int macb_poll(struct napi_struct *napi, int budget)
 		 * get notified when new packets arrive.
 		 */
 		macb_writel(bp, IER, MACB_RX_INT_FLAGS);
+
+		/* Packets received while interrupts were disabled */
+		status = macb_readl(bp, RSR);
+		if (unlikely(status))
+			napi_reschedule(napi);
 	}
 
 	/* TODO: Handle errors */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d185a50870b..39c6c552463 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2254,7 +2254,7 @@ static int __init stmmac_cmdline_opt(char *str)
 		} else if (!strncmp(opt, "pause:", 6)) {
 			if (kstrtoint(opt + 6, 0, &pause))
 				goto err;
-		} else if (!strncmp(opt, "eee_timer:", 6)) {
+		} else if (!strncmp(opt, "eee_timer:", 10)) {
 			if (kstrtoint(opt + 10, 0, &eee_timer))
 				goto err;
 		}
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index d7115eca5ef..4a8c25a2229 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -576,9 +576,14 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 	if ((intf->num_altsetting == 2) &&
 	    !usb_set_interface(dev->udev,
 			       intf->cur_altsetting->desc.bInterfaceNumber,
-			       CDC_NCM_COMM_ALTSETTING_MBIM) &&
-	    cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
-		return -ENODEV;
+			       CDC_NCM_COMM_ALTSETTING_MBIM)) {
+		if (cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
+			return -ENODEV;
+		else
+			usb_set_interface(dev->udev,
+					  intf->cur_altsetting->desc.bInterfaceNumber,
+					  CDC_NCM_COMM_ALTSETTING_NCM);
+	}
 #endif
 
 	/* NCM data altsetting is always 1 */
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index fc1b8d78f4b..d9841416848 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -132,6 +132,7 @@ static void xenvif_up(struct xenvif *vif)
 static void xenvif_down(struct xenvif *vif)
 {
 	disable_irq(vif->irq);
+	del_timer_sync(&vif->credit_timeout);
 	xen_netbk_deschedule_xenvif(vif);
 	xen_netbk_remove_xenvif(vif);
 }
@@ -365,8 +366,6 @@ void xenvif_disconnect(struct xenvif *vif)
 	atomic_dec(&vif->refcnt);
 	wait_event(vif->waiting_to_free, atomic_read(&vif->refcnt) == 0);
 
-	del_timer_sync(&vif->credit_timeout);
-
 	if (vif->irq)
 		unbind_from_irqhandler(vif->irq, vif);
 
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 2b9520c46e9..cd49ba94963 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -911,13 +911,13 @@ static int netbk_count_requests(struct xenvif *vif,
 		if (frags >= work_to_do) {
 			netdev_err(vif->dev, "Need more frags\n");
 			netbk_fatal_tx_err(vif);
-			return -frags;
+			return -ENODATA;
 		}
 
 		if (unlikely(frags >= MAX_SKB_FRAGS)) {
 			netdev_err(vif->dev, "Too many frags\n");
 			netbk_fatal_tx_err(vif);
-			return -frags;
+			return -E2BIG;
 		}
 
 		memcpy(txp, RING_GET_REQUEST(&vif->tx, cons + frags),
@@ -925,7 +925,7 @@ static int netbk_count_requests(struct xenvif *vif,
 		if (txp->size > first->size) {
 			netdev_err(vif->dev, "Frag is bigger than frame.\n");
 			netbk_fatal_tx_err(vif);
-			return -frags;
+			return -EIO;
 		}
 
 		first->size -= txp->size;
@@ -935,7 +935,7 @@ static int netbk_count_requests(struct xenvif *vif,
 			netdev_err(vif->dev, "txp->offset: %x, size: %u\n",
 				 txp->offset, txp->size);
 			netbk_fatal_tx_err(vif);
-			return -frags;
+			return -EINVAL;
 		}
 	} while ((txp++)->flags & XEN_NETTXF_more_data);
 	return frags;
diff --git a/drivers/rtc/rtc-pl031.c b/drivers/rtc/rtc-pl031.c
index 10c1a3454e4..81c5077feff 100644
--- a/drivers/rtc/rtc-pl031.c
+++ b/drivers/rtc/rtc-pl031.c
@@ -350,7 +350,9 @@ static int pl031_probe(struct amba_device *adev, const struct amba_id *id)
 	/* Enable the clockwatch on ST Variants */
 	if (vendor->clockwatch)
 		data |= RTC_CR_CWEN;
-	writel(data | RTC_CR_EN, ldata->base + RTC_CR);
+	else
+		data |= RTC_CR_EN;
+	writel(data, ldata->base + RTC_CR);
 
 	/*
 	 * On ST PL031 variants, the RTC reset value does not provide correct