Merge linux-block/for-4.3/core into md/for-linux

There were a few conflicts that are fairly easy to resolve.

Signed-off-by: NeilBrown <neilb@suse.com>

6 files changed, 135 insertions, 29 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index e2894b2..3e0b662 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1353,20 +1353,6 @@ config RCU_CPU_STALL_TIMEOUT
 	  RCU grace period persists, additional CPU stall warnings are
 	  printed at more widely spaced intervals.
 
-config RCU_CPU_STALL_INFO
-	bool "Print additional diagnostics on RCU CPU stall"
-	depends on (TREE_RCU || PREEMPT_RCU) && DEBUG_KERNEL
-	default y
-	help
-	  For each stalled CPU that is aware of the current RCU grace
-	  period, print out additional per-CPU diagnostic information
-	  regarding scheduling-clock ticks, idle state, and,
-	  for RCU_FAST_NO_HZ kernels, idle-entry state.
-
-	  Say N if you are unsure.
-
-	  Say Y if you want to enable such diagnostics.
-
 config RCU_TRACE
 	bool "Enable tracing for RCU"
 	depends on DEBUG_KERNEL
@@ -1379,7 +1365,7 @@ config RCU_TRACE
 	  Say N if you are unsure.
 
 config RCU_EQS_DEBUG
-	bool "Use this when adding any sort of NO_HZ support to your arch"
+	bool "Provide debugging asserts for adding NO_HZ support to an arch"
 	depends on DEBUG_KERNEL
 	help
 	  This option provides consistency checks in RCU's handling of
diff --git a/lib/iommu-common.c b/lib/iommu-common.c
index df30632..ff19f66 100644
--- a/lib/iommu-common.c
+++ b/lib/iommu-common.c
@@ -119,7 +119,7 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 	unsigned long align_mask = 0;
 
 	if (align_order > 0)
-		align_mask = 0xffffffffffffffffl >> (64 - align_order);
+		align_mask = ~0ul >> (BITS_PER_LONG - align_order);
 
 	/* Sanity check */
 	if (unlikely(npages == 0)) {
diff --git a/lib/klist.c b/lib/klist.c
index 89b485a..d74cf7a 100644
--- a/lib/klist.c
+++ b/lib/klist.c
@@ -324,6 +324,47 @@ static struct klist_node *to_klist_node(struct list_head *n)
 }
 
 /**
+ * klist_prev - Ante up prev node in list.
+ * @i: Iterator structure.
+ *
+ * First grab list lock. Decrement the reference count of the previous
+ * node, if there was one. Grab the prev node, increment its reference
+ * count, drop the lock, and return that prev node.
+ */
+struct klist_node *klist_prev(struct klist_iter *i)
+{
+	void (*put)(struct klist_node *) = i->i_klist->put;
+	struct klist_node *last = i->i_cur;
+	struct klist_node *prev;
+
+	spin_lock(&i->i_klist->k_lock);
+
+	if (last) {
+		prev = to_klist_node(last->n_node.prev);
+		if (!klist_dec_and_del(last))
+			put = NULL;
+	} else
+		prev = to_klist_node(i->i_klist->k_list.prev);
+
+	i->i_cur = NULL;
+	while (prev != to_klist_node(&i->i_klist->k_list)) {
+		if (likely(!knode_dead(prev))) {
+			kref_get(&prev->n_ref);
+			i->i_cur = prev;
+			break;
+		}
+		prev = to_klist_node(prev->n_node.prev);
+	}
+
+	spin_unlock(&i->i_klist->k_lock);
+
+	if (put && last)
+		put(last);
+	return i->i_cur;
+}
+EXPORT_SYMBOL_GPL(klist_prev);
+
+/**
  * klist_next - Ante up next node in list.
  * @i: Iterator structure.
  *
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
index bc0a1da..95c52a9 100644
--- a/lib/mpi/mpicoder.c
+++ b/lib/mpi/mpicoder.c
@@ -146,18 +146,25 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 	uint8_t *p;
 	mpi_limb_t alimb;
 	unsigned int n = mpi_get_size(a);
-	int i;
+	int i, lzeros = 0;
 
-	if (buf_len < n || !buf)
+	if (buf_len < n || !buf || !nbytes)
 		return -EINVAL;
 
 	if (sign)
 		*sign = a->sign;
 
-	if (nbytes)
-		*nbytes = n;
+	p = (void *)&a->d[a->nlimbs] - 1;
+
+	for (i = a->nlimbs * sizeof(alimb) - 1; i >= 0; i--, p--) {
+		if (!*p)
+			lzeros++;
+		else
+			break;
+	}
 
 	p = buf;
+	*nbytes = n - lzeros;
 
 	for (i = a->nlimbs - 1; i >= 0; i--) {
 		alimb = a->d[i];
@@ -178,6 +185,19 @@ int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 #else
 #error please implement for this limb size.
 #endif
+
+		if (lzeros > 0) {
+			if (lzeros >= sizeof(alimb)) {
+				p -= sizeof(alimb);
+			} else {
+				mpi_limb_t *limb1 = (void *)p - sizeof(alimb);
+				mpi_limb_t *limb2 = (void *)p - sizeof(alimb)
+							+ lzeros;
+				*limb1 = *limb2;
+				p -= lzeros;
+			}
+			lzeros -= sizeof(alimb);
+		}
 	}
 	return 0;
 }
@@ -197,7 +217,7 @@ EXPORT_SYMBOL_GPL(mpi_read_buffer);
  */
 void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
 {
-	uint8_t *buf, *p;
+	uint8_t *buf;
 	unsigned int n;
 	int ret;
 
@@ -220,14 +240,6 @@ void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
 		kfree(buf);
 		return NULL;
 	}
-
-	/* this is sub-optimal but we need to do the shift operation
-	 * because the caller has to free the returned buffer */
-	for (p = buf; !*p && *nbytes; p++, --*nbytes)
-		;
-	if (p != buf)
-		memmove(buf, p, *nbytes);
-
 	return buf;
 }
 EXPORT_SYMBOL_GPL(mpi_get_buffer);
diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c
index bcce5f1..5f5d24d 100644
--- a/lib/pci_iomap.c
+++ b/lib/pci_iomap.c
@@ -52,6 +52,51 @@ void __iomem *pci_iomap_range(struct pci_dev *dev,
 EXPORT_SYMBOL(pci_iomap_range);
 
 /**
+ * pci_iomap_wc_range - create a virtual WC mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @offset: map memory at the given offset in BAR
+ * @maxlen: max length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way. When possible write combining
+ * is used.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR from offset to the end, pass %0 here.
+ * */
+void __iomem *pci_iomap_wc_range(struct pci_dev *dev,
+				 int bar,
+				 unsigned long offset,
+				 unsigned long maxlen)
+{
+	resource_size_t start = pci_resource_start(dev, bar);
+	resource_size_t len = pci_resource_len(dev, bar);
+	unsigned long flags = pci_resource_flags(dev, bar);
+
+
+	if (flags & IORESOURCE_IO)
+		return NULL;
+
+	if (len <= offset || !start)
+		return NULL;
+
+	len -= offset;
+	start += offset;
+	if (maxlen && len > maxlen)
+		len = maxlen;
+
+	if (flags & IORESOURCE_MEM)
+		return ioremap_wc(start, len);
+
+	/* What? */
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(pci_iomap_wc_range);
+
+/**
  * pci_iomap - create a virtual mapping cookie for a PCI BAR
  * @dev: PCI device that owns the BAR
  * @bar: BAR number
@@ -70,4 +115,25 @@ void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 	return pci_iomap_range(dev, bar, 0, maxlen);
 }
 EXPORT_SYMBOL(pci_iomap);
+
+/**
+ * pci_iomap_wc - create a virtual WC mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @maxlen: length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way. When possible write combining
+ * is used.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR without checking for its length first, pass %0 here.
+ * */
+void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+	return pci_iomap_wc_range(dev, bar, 0, maxlen);
+}
+EXPORT_SYMBOL_GPL(pci_iomap_wc);
 #endif /* CONFIG_PCI */
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index da39c60..95cd63b 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -17,6 +17,7 @@
  */
 
 #include <stdarg.h>
+#include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/module.h>	/* for KSYM_SYMBOL_LEN */
 #include <linux/types.h>