Merge tag 'v4.4.64' into linux-linaro-lsk-v4.4

 This is the 4.4.64 stable release

Author: Alex Shi

Makefile

@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 63
+SUBLEVEL = 64
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 

arch/arm/kvm/mmu.c

@@ -301,6 +301,14 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
 		next = kvm_pgd_addr_end(addr, end);
 		if (!pgd_none(*pgd))
 			unmap_puds(kvm, pgd, addr, next);
+		/*
+		 * If we are dealing with a large range in
+		 * stage2 table, release the kvm->mmu_lock
+		 * to prevent starvation and lockup detector
+		 * warnings.
+		 */
+		if (kvm && (next != end))
+			cond_resched_lock(&kvm->mmu_lock);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -745,6 +753,7 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
  */
 static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 {
+	assert_spin_locked(&kvm->mmu_lock);
 	unmap_range(kvm, kvm->arch.pgd, start, size);
 }
 
@@ -831,7 +840,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
 	if (kvm->arch.pgd == NULL)
 		return;
 
+	spin_lock(&kvm->mmu_lock);
 	unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
+	spin_unlock(&kvm->mmu_lock);
+
 	kvm_free_hwpgd(kvm_get_hwpgd(kvm));
 	if (KVM_PREALLOC_LEVEL > 0)
 		kfree(kvm->arch.pgd);

arch/powerpc/kernel/entry_64.S

@@ -716,7 +716,7 @@ resume_kernel:
 
 	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */
 
-	lwz	r3,GPR1(r1)
+	ld	r3,GPR1(r1)
 	subi	r3,r3,INT_FRAME_SIZE	/* dst: Allocate a trampoline exception frame */
 	mr	r4,r1			/* src:  current exception frame */
 	mr	r1,r3			/* Reroute the trampoline frame to r1 */
@@ -730,8 +730,8 @@ resume_kernel:
 	addi	r6,r6,8
 	bdnz	2b
 
-	/* Do real store operation to complete stwu */
-	lwz	r5,GPR1(r1)
+	/* Do real store operation to complete stdu */
+	ld	r5,GPR1(r1)
 	std	r8,0(r5)
 
 	/* Clear _TIF_EMULATE_STACK_STORE flag */

arch/s390/include/asm/pgtable.h

@@ -829,6 +829,8 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 {
 	pgste_t pgste;
 
+	if (pte_present(entry))
+		pte_val(entry) &= ~_PAGE_UNUSED;
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
 		pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;

arch/x86/include/asm/pmem.h

@@ -72,8 +72,8 @@ static inline void arch_wmb_pmem(void)
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)
- * instruction.  This function requires explicit ordering with an
- * arch_wmb_pmem() call.  This API is internal to the x86 PMEM implementation.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
  */
 static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
 {
@@ -87,15 +87,6 @@ static inline void __arch_wb_cache_pmem(void *vaddr, size_t size)
 		clwb(p);
 }
 
-/*
- * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
- * iterators, so for other types (bvec & kvec) we must do a cache write-back.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
-	return iter_is_iovec(i) == false;
-}
-
 /**
  * arch_copy_from_iter_pmem - copy data from an iterator to PMEM
  * @addr:	PMEM destination address
@@ -114,8 +105,36 @@ static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
 	/* TODO: skip the write-back by always using non-temporal stores */
 	len = copy_from_iter_nocache(vaddr, bytes, i);
 
-	if (__iter_needs_pmem_wb(i))
-		__arch_wb_cache_pmem(vaddr, bytes);
+	/*
+	 * In the iovec case on x86_64 copy_from_iter_nocache() uses
+	 * non-temporal stores for the bulk of the transfer, but we need
+	 * to manually flush if the transfer is unaligned. A cached
+	 * memory copy is used when destination or size is not naturally
+	 * aligned. That is:
+	 *   - Require 8-byte alignment when size is 8 bytes or larger.
+	 *   - Require 4-byte alignment when size is 4 bytes.
+	 *
+	 * In the non-iovec case the entire destination needs to be
+	 * flushed.
+	 */
+	if (iter_is_iovec(i)) {
+		unsigned long flushed, dest = (unsigned long) addr;
+
+		if (bytes < 8) {
+			if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+				__arch_wb_cache_pmem(addr, 1);
+		} else {
+			if (!IS_ALIGNED(dest, 8)) {
+				dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+				__arch_wb_cache_pmem(addr, 1);
+			}
+
+			flushed = dest - (unsigned long) addr;
+			if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+				__arch_wb_cache_pmem(addr + bytes - 1, 1);
+		}
+	} else
+		__arch_wb_cache_pmem(addr, bytes);
 
 	return len;
 }

arch/x86/kernel/cpu/mcheck/mce_amd.c

@@ -53,7 +53,7 @@ static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
 	"combined_unit",
-	"",
+	"decode_unit",
 	"northbridge",
 	"execution_unit",
 };

block/genhd.c

@@ -664,7 +664,6 @@ void del_gendisk(struct gendisk *disk)
 
 	kobject_put(disk->part0.holder_dir);
 	kobject_put(disk->slave_dir);
-	disk->driverfs_dev = NULL;
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);

drivers/acpi/power.c

@@ -200,6 +200,7 @@ static int acpi_power_get_list_state(struct list_head *list, int *state)
 		return -EINVAL;
 
 	/* The state of the list is 'on' IFF all resources are 'on'. */
+	cur_state = 0;
 	list_for_each_entry(entry, list, node) {
 		struct acpi_power_resource *resource = entry->resource;
 		acpi_handle handle = resource->device.handle;

drivers/hv/channel.c

@@ -73,7 +73,6 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	void *in, *out;
 	unsigned long flags;
 	int ret, err = 0;
-	unsigned long t;
 	struct page *page;
 
 	spin_lock_irqsave(&newchannel->lock, flags);
@@ -183,11 +182,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 		goto error1;
 	}
 
-	t = wait_for_completion_timeout(&open_info->waitevent, 5*HZ);
-	if (t == 0) {
-		err = -ETIMEDOUT;
-		goto error1;
-	}
+	wait_for_completion(&open_info->waitevent);
 
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_del(&open_info->msglistentry);
@@ -375,7 +370,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	struct vmbus_channel_gpadl_header *gpadlmsg;
 	struct vmbus_channel_gpadl_body *gpadl_body;
 	struct vmbus_channel_msginfo *msginfo = NULL;
-	struct vmbus_channel_msginfo *submsginfo;
+	struct vmbus_channel_msginfo *submsginfo, *tmp;
 	u32 msgcount;
 	struct list_head *curr;
 	u32 next_gpadl_handle;
@@ -437,6 +432,13 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	list_del(&msginfo->msglistentry);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
+	if (msgcount > 1) {
+		list_for_each_entry_safe(submsginfo, tmp, &msginfo->submsglist,
+			 msglistentry) {
+			kfree(submsginfo);
+		}
+	}
+
 	kfree(msginfo);
 	return ret;
 }

drivers/hv/connection.c

@@ -429,7 +429,7 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 	union hv_connection_id conn_id;
 	int ret = 0;
 	int retries = 0;
-	u32 msec = 1;
+	u32 usec = 1;
 
 	conn_id.asu32 = 0;
 	conn_id.u.id = VMBUS_MESSAGE_CONNECTION_ID;
@@ -462,9 +462,9 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 		}
 
 		retries++;
-		msleep(msec);
-		if (msec < 2048)
-			msec *= 2;
+		udelay(usec);
+		if (usec < 2048)
+			usec *= 2;
 	}
 	return ret;
 }