Merge tag 'v4.4.93' into linux-linaro-lsk-v4.4

 This is the 4.4.93 stable release

Author: Alex Shi

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 92
+SUBLEVEL = 93
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 

arch/mips/math-emu/cp1emu.c

@@ -2360,7 +2360,6 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 					break;
 				default:
 					/* Reserved R6 ops */
-					pr_err("Reserved MIPS R6 CMP.condn.S operation\n");
 					return SIGILL;
 				}
 			}
@@ -2434,7 +2433,6 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 					break;
 				default:
 					/* Reserved R6 ops */
-					pr_err("Reserved MIPS R6 CMP.condn.D operation\n");
 					return SIGILL;
 				}
 			}

arch/x86/include/asm/alternative-asm.h

@@ -62,8 +62,10 @@
 #define new_len2		145f-144f
 
 /*
- * max without conditionals. Idea adapted from:
+ * gas compatible max based on the idea from:
  * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ *
+ * The additional "-" is needed because gas uses a "true" value of -1.
  */
 #define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
 

arch/x86/include/asm/alternative.h

@@ -102,12 +102,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	alt_end_marker ":\n"
 
 /*
- * max without conditionals. Idea adapted from:
+ * gas compatible max based on the idea from:
  * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
  *
- * The additional "-" is needed because gas works with s32s.
+ * The additional "-" is needed because gas uses a "true" value of -1.
  */
-#define alt_max_short(a, b)	"((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") - (" b ")))))"
+#define alt_max_short(a, b)	"((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))"
 
 /*
  * Pad the second replacement alternative with additional NOPs if it is

arch/x86/kvm/vmx.c

@@ -10369,7 +10369,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	 * (KVM doesn't change it)- no reason to call set_cr4_guest_host_mask();
 	 */
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
-	kvm_set_cr4(vcpu, vmcs12->host_cr4);
+	vmx_set_cr4(vcpu, vmcs12->host_cr4);
 
 	nested_ept_uninit_mmu_context(vcpu);
 

block/bio.c

@@ -1320,6 +1320,7 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 		offset = uaddr & ~PAGE_MASK;
 		for (j = cur_page; j < page_limit; j++) {
 			unsigned int bytes = PAGE_SIZE - offset;
+			unsigned short prev_bi_vcnt = bio->bi_vcnt;
 
 			if (len <= 0)
 				break;
@@ -1334,6 +1335,13 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 					    bytes)
 				break;
 
+			/*
+			 * check if vector was merged with previous
+			 * drop page reference if needed
+			 */
+			if (bio->bi_vcnt == prev_bi_vcnt)
+				put_page(pages[j]);
+
 			len -= bytes;
 			offset = 0;
 		}

crypto/shash.c

@@ -274,12 +274,14 @@ static int shash_async_finup(struct ahash_request *req)
 
 int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc)
 {
-	struct scatterlist *sg = req->src;
-	unsigned int offset = sg->offset;
 	unsigned int nbytes = req->nbytes;
+	struct scatterlist *sg;
+	unsigned int offset;
 	int err;
 
-	if (nbytes < min(sg->length, ((unsigned int)(PAGE_SIZE)) - offset)) {
+	if (nbytes &&
+	    (sg = req->src, offset = sg->offset,
+	     nbytes < min(sg->length, ((unsigned int)(PAGE_SIZE)) - offset))) {
 		void *data;
 
 		data = kmap_atomic(sg_page(sg));

drivers/dma/edma.c

@@ -1126,11 +1126,24 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
 	struct edma_desc *edesc;
 	struct device *dev = chan->device->dev;
 	struct edma_chan *echan = to_edma_chan(chan);
-	unsigned int width, pset_len;
+	unsigned int width, pset_len, array_size;
 
 	if (unlikely(!echan || !len))
 		return NULL;
 
+	/* Align the array size (acnt block) with the transfer properties */
+	switch (__ffs((src | dest | len))) {
+	case 0:
+		array_size = SZ_32K - 1;
+		break;
+	case 1:
+		array_size = SZ_32K - 2;
+		break;
+	default:
+		array_size = SZ_32K - 4;
+		break;
+	}
+
 	if (len < SZ_64K) {
 		/*
 		 * Transfer size less than 64K can be handled with one paRAM
@@ -1152,7 +1165,7 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
 		 * When the full_length is multibple of 32767 one slot can be
 		 * used to complete the transfer.
 		 */
-		width = SZ_32K - 1;
+		width = array_size;
 		pset_len = rounddown(len, width);
 		/* One slot is enough for lengths multiple of (SZ_32K -1) */
 		if (unlikely(pset_len == len))
@@ -1202,7 +1215,7 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
 		}
 		dest += pset_len;
 		src += pset_len;
-		pset_len = width = len % (SZ_32K - 1);
+		pset_len = width = len % array_size;
 
 		ret = edma_config_pset(chan, &edesc->pset[1], src, dest, 1,
 				       width, pset_len, DMA_MEM_TO_MEM);

drivers/hid/usbhid/hid-core.c

@@ -971,6 +971,8 @@ static int usbhid_parse(struct hid_device *hid)
 	unsigned int rsize = 0;
 	char *rdesc;
 	int ret, n;
+	int num_descriptors;
+	size_t offset = offsetof(struct hid_descriptor, desc);
 
 	quirks = usbhid_lookup_quirk(le16_to_cpu(dev->descriptor.idVendor),
 			le16_to_cpu(dev->descriptor.idProduct));
@@ -993,10 +995,18 @@ static int usbhid_parse(struct hid_device *hid)
 		return -ENODEV;
 	}
 
+	if (hdesc->bLength < sizeof(struct hid_descriptor)) {
+		dbg_hid("hid descriptor is too short\n");
+		return -EINVAL;
+	}
+
 	hid->version = le16_to_cpu(hdesc->bcdHID);
 	hid->country = hdesc->bCountryCode;
 
-	for (n = 0; n < hdesc->bNumDescriptors; n++)
+	num_descriptors = min_t(int, hdesc->bNumDescriptors,
+	       (hdesc->bLength - offset) / sizeof(struct hid_class_descriptor));
+
+	for (n = 0; n < num_descriptors; n++)
 		if (hdesc->desc[n].bDescriptorType == HID_DT_REPORT)
 			rsize = le16_to_cpu(hdesc->desc[n].wDescriptorLength);
 

drivers/iommu/amd_iommu.c

@@ -3096,6 +3096,7 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
 	mutex_unlock(&domain->api_lock);
 
 	domain_flush_tlb_pde(domain);
+	domain_flush_complete(domain);
 
 	return unmap_size;
 }