Merge branch 'perf/urgent' into perf/core

Merge reason: Upcoming patch is dependent on a fix in perf/urgent.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

12 files changed, 199 insertions, 23 deletions

diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index f42e623030e..fa19f3fe05f 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -18,6 +18,9 @@
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 #include <asm-generic/cputime.h>
+#ifdef __KERNEL__
+static inline void setup_cputime_one_jiffy(void) { }
+#endif
 #else
 
 #include <linux/types.h>
@@ -49,6 +52,11 @@ typedef u64 cputime64_t;
 #ifdef __KERNEL__
 
 /*
+ * One jiffy in timebase units computed during initialization
+ */
+extern cputime_t cputime_one_jiffy;
+
+/*
  * Convert cputime <-> jiffies
  */
 extern u64 __cputime_jiffies_factor;
@@ -89,6 +97,11 @@ static inline cputime_t jiffies_to_cputime(const unsigned long jif)
 	return ct;
 }
 
+static inline void setup_cputime_one_jiffy(void)
+{
+	cputime_one_jiffy = jiffies_to_cputime(1);
+}
+
 static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
 {
 	cputime_t ct;
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 9dade15d1ab..6d94d27ed85 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -15,7 +15,16 @@ struct dev_archdata {
 
 	/* DMA operations on that device */
 	struct dma_map_ops	*dma_ops;
-	void			*dma_data;
+
+	/*
+	 * When an iommu is in use, dma_data is used as a ptr to the base of the
+	 * iommu_table.  Otherwise, it is a simple numerical offset.
+	 */
+	union {
+		dma_addr_t	dma_offset;
+		void		*iommu_table_base;
+	} dma_data;
+
 #ifdef CONFIG_SWIOTLB
 	dma_addr_t		max_direct_dma_addr;
 #endif
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index cb2ca41dd52..e281daebddc 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -26,7 +26,6 @@ extern void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 extern void dma_direct_free_coherent(struct device *dev, size_t size,
 				     void *vaddr, dma_addr_t dma_handle);
 
-extern unsigned long get_dma_direct_offset(struct device *dev);
 
 #ifdef CONFIG_NOT_COHERENT_CACHE
 /*
@@ -90,6 +89,28 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 	dev->archdata.dma_ops = ops;
 }
 
+/*
+ * get_dma_offset()
+ *
+ * Get the dma offset on configurations where the dma address can be determined
+ * from the physical address by looking at a simple offset.  Direct dma and
+ * swiotlb use this function, but it is typically not used by implementations
+ * with an iommu.
+ */
+static inline dma_addr_t get_dma_offset(struct device *dev)
+{
+	if (dev)
+		return dev->archdata.dma_data.dma_offset;
+
+	return PCI_DRAM_OFFSET;
+}
+
+static inline void set_dma_offset(struct device *dev, dma_addr_t off)
+{
+	if (dev)
+		dev->archdata.dma_data.dma_offset = off;
+}
+
 /* this will be removed soon */
 #define flush_write_buffers()
 
@@ -181,12 +202,12 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	return paddr + get_dma_direct_offset(dev);
+	return paddr + get_dma_offset(dev);
 }
 
 static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
-	return daddr - get_dma_direct_offset(dev);
+	return daddr - get_dma_offset(dev);
 }
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
diff --git a/arch/powerpc/include/asm/fsldma.h b/arch/powerpc/include/asm/fsldma.h
new file mode 100644
index 00000000000..a67aeed17d4
--- /dev/null
+++ b/arch/powerpc/include/asm/fsldma.h
@@ -0,0 +1,136 @@
+/*
+ * Freescale MPC83XX / MPC85XX DMA Controller
+ *
+ * Copyright (c) 2009 Ira W. Snyder <iws@ovro.caltech.edu>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2. This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+#ifndef __ARCH_POWERPC_ASM_FSLDMA_H__
+#define __ARCH_POWERPC_ASM_FSLDMA_H__
+
+#include <linux/dmaengine.h>
+
+/*
+ * Definitions for the Freescale DMA controller's DMA_SLAVE implemention
+ *
+ * The Freescale DMA_SLAVE implementation was designed to handle many-to-many
+ * transfers. An example usage would be an accelerated copy between two
+ * scatterlists. Another example use would be an accelerated copy from
+ * multiple non-contiguous device buffers into a single scatterlist.
+ *
+ * A DMA_SLAVE transaction is defined by a struct fsl_dma_slave. This
+ * structure contains a list of hardware addresses that should be copied
+ * to/from the scatterlist passed into device_prep_slave_sg(). The structure
+ * also has some fields to enable hardware-specific features.
+ */
+
+/**
+ * struct fsl_dma_hw_addr
+ * @entry: linked list entry
+ * @address: the hardware address
+ * @length: length to transfer
+ *
+ * Holds a single physical hardware address / length pair for use
+ * with the DMAEngine DMA_SLAVE API.
+ */
+struct fsl_dma_hw_addr {
+	struct list_head entry;
+
+	dma_addr_t address;
+	size_t length;
+};
+
+/**
+ * struct fsl_dma_slave
+ * @addresses: a linked list of struct fsl_dma_hw_addr structures
+ * @request_count: value for DMA request count
+ * @src_loop_size: setup and enable constant source-address DMA transfers
+ * @dst_loop_size: setup and enable constant destination address DMA transfers
+ * @external_start: enable externally started DMA transfers
+ * @external_pause: enable externally paused DMA transfers
+ *
+ * Holds a list of address / length pairs for use with the DMAEngine
+ * DMA_SLAVE API implementation for the Freescale DMA controller.
+ */
+struct fsl_dma_slave {
+
+	/* List of hardware address/length pairs */
+	struct list_head addresses;
+
+	/* Support for extra controller features */
+	unsigned int request_count;
+	unsigned int src_loop_size;
+	unsigned int dst_loop_size;
+	bool external_start;
+	bool external_pause;
+};
+
+/**
+ * fsl_dma_slave_append - add an address/length pair to a struct fsl_dma_slave
+ * @slave: the &struct fsl_dma_slave to add to
+ * @address: the hardware address to add
+ * @length: the length of bytes to transfer from @address
+ *
+ * Add a hardware address/length pair to a struct fsl_dma_slave. Returns 0 on
+ * success, -ERRNO otherwise.
+ */
+static inline int fsl_dma_slave_append(struct fsl_dma_slave *slave,
+				       dma_addr_t address, size_t length)
+{
+	struct fsl_dma_hw_addr *addr;
+
+	addr = kzalloc(sizeof(*addr), GFP_ATOMIC);
+	if (!addr)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&addr->entry);
+	addr->address = address;
+	addr->length = length;
+
+	list_add_tail(&addr->entry, &slave->addresses);
+	return 0;
+}
+
+/**
+ * fsl_dma_slave_free - free a struct fsl_dma_slave
+ * @slave: the struct fsl_dma_slave to free
+ *
+ * Free a struct fsl_dma_slave and all associated address/length pairs
+ */
+static inline void fsl_dma_slave_free(struct fsl_dma_slave *slave)
+{
+	struct fsl_dma_hw_addr *addr, *tmp;
+
+	if (slave) {
+		list_for_each_entry_safe(addr, tmp, &slave->addresses, entry) {
+			list_del(&addr->entry);
+			kfree(addr);
+		}
+
+		kfree(slave);
+	}
+}
+
+/**
+ * fsl_dma_slave_alloc - allocate a struct fsl_dma_slave
+ * @gfp: the flags to pass to kmalloc when allocating this structure
+ *
+ * Allocate a struct fsl_dma_slave for use by the DMA_SLAVE API. Returns a new
+ * struct fsl_dma_slave on success, or NULL on failure.
+ */
+static inline struct fsl_dma_slave *fsl_dma_slave_alloc(gfp_t gfp)
+{
+	struct fsl_dma_slave *slave;
+
+	slave = kzalloc(sizeof(*slave), gfp);
+	if (!slave)
+		return NULL;
+
+	INIT_LIST_HEAD(&slave->addresses);
+	return slave;
+}
+
+#endif /* __ARCH_POWERPC_ASM_FSLDMA_H__ */
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 7464c0daddd..edfc9803ec9 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -70,6 +70,16 @@ struct iommu_table {
 
 struct scatterlist;
 
+static inline void set_iommu_table_base(struct device *dev, void *base)
+{
+	dev->archdata.dma_data.iommu_table_base = base;
+}
+
+static inline void *get_iommu_table_base(struct device *dev)
+{
+	return dev->archdata.dma_data.iommu_table_base;
+}
+
 /* Frees table for an individual device node */
 extern void iommu_free_table(struct iommu_table *tbl, const char *node_name);
 
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index 7b1c49811a2..d4a7f645c5d 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -25,6 +25,8 @@
 
 #define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
 #define MAP_NONBLOCK	0x10000		/* do not block on IO */
+#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
+#define MAP_HUGETLB	0x40000		/* create a huge page mapping */
 
 #ifdef __KERNEL__
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/pmc.h b/arch/powerpc/include/asm/pmc.h
index ccc68b50d05..5a9ede4962c 100644
--- a/arch/powerpc/include/asm/pmc.h
+++ b/arch/powerpc/include/asm/pmc.h
@@ -29,7 +29,7 @@ int reserve_pmc_hardware(perf_irq_t new_perf_irq);
 void release_pmc_hardware(void);
 void ppc_enable_pmcs(void);
 
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
 #include <asm/lppaca.h>
 
 static inline void ppc_set_pmu_inuse(int inuse)
diff --git a/arch/powerpc/include/asm/pte-40x.h b/arch/powerpc/include/asm/pte-40x.h
index 6c3e1f4378d..ec0b0b0d1df 100644
--- a/arch/powerpc/include/asm/pte-40x.h
+++ b/arch/powerpc/include/asm/pte-40x.h
@@ -43,6 +43,7 @@
 #define	_PAGE_NO_CACHE	0x004	/* I: caching is inhibited */
 #define	_PAGE_WRITETHRU	0x008	/* W: caching is write-through */
 #define	_PAGE_USER	0x010	/* matches one of the zone permission bits */
+#define	_PAGE_SPECIAL	0x020	/* software: Special page */
 #define	_PAGE_RW	0x040	/* software: Writes permitted */
 #define	_PAGE_DIRTY	0x080	/* software: dirty page */
 #define _PAGE_HWWRITE	0x100	/* hardware: Dirty & RW, set in exception */
diff --git a/arch/powerpc/include/asm/pte-8xx.h b/arch/powerpc/include/asm/pte-8xx.h
index 94e979718dc..dd5ea95fe61 100644
--- a/arch/powerpc/include/asm/pte-8xx.h
+++ b/arch/powerpc/include/asm/pte-8xx.h
@@ -32,6 +32,7 @@
 #define _PAGE_FILE	0x0002	/* when !present: nonlinear file mapping */
 #define _PAGE_NO_CACHE	0x0002	/* I: cache inhibit */
 #define _PAGE_SHARED	0x0004	/* No ASID (context) compare */
+#define _PAGE_SPECIAL	0x0008	/* SW entry, forced to 0 by the TLB miss */
 
 /* These five software bits must be masked out when the entry is loaded
  * into the TLB.
diff --git a/arch/powerpc/include/asm/pte-common.h b/arch/powerpc/include/asm/pte-common.h
index c3b65076a26..f2b370180a0 100644
--- a/arch/powerpc/include/asm/pte-common.h
+++ b/arch/powerpc/include/asm/pte-common.h
@@ -25,9 +25,6 @@
 #ifndef _PAGE_WRITETHRU
 #define _PAGE_WRITETHRU	0
 #endif
-#ifndef _PAGE_SPECIAL
-#define _PAGE_SPECIAL	0
-#endif
 #ifndef _PAGE_4K_PFN
 #define _PAGE_4K_PFN		0
 #endif
@@ -179,7 +176,5 @@ extern unsigned long bad_call_to_PMD_PAGE_SIZE(void);
 #define HAVE_PAGE_AGP
 
 /* Advertise support for _PAGE_SPECIAL */
-#ifdef _PAGE_SPECIAL
 #define __HAVE_ARCH_PTE_SPECIAL
-#endif
 
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index c0d3b8af931..d9ea8d39c34 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -146,7 +146,7 @@ extern void smp_generic_take_timebase(void);
 extern struct smp_ops_t *smp_ops;
 
 extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 
 /* Definitions relative to the secondary CPU spin loop
  * and entry point. Not all of them exist on both 32 and
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 394edcbcce7..22f738d12ad 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -17,11 +17,6 @@ static inline int cpu_to_node(int cpu)
 
 #define parent_node(node)	(node)
 
-static inline cpumask_t node_to_cpumask(int node)
-{
-	return numa_cpumask_lookup_table[node];
-}
-
 #define cpumask_of_node(node) (&numa_cpumask_lookup_table[node])
 
 int of_node_to_nid(struct device_node *device);
@@ -36,11 +31,6 @@ static inline int pcibus_to_node(struct pci_bus *bus)
 }
 #endif
 
-#define pcibus_to_cpumask(bus)	(pcibus_to_node(bus) == -1 ? \
-					CPU_MASK_ALL : \
-					node_to_cpumask(pcibus_to_node(bus)) \
-				)
-
 #define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
 				 cpu_all_mask :				\
 				 cpumask_of_node(pcibus_to_node(bus)))
@@ -104,8 +94,6 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev,
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
 
-#define topology_thread_siblings(cpu)	(per_cpu(cpu_sibling_map, cpu))
-#define topology_core_siblings(cpu)	(per_cpu(cpu_core_map, cpu))
 #define topology_thread_cpumask(cpu)	(&per_cpu(cpu_sibling_map, cpu))
 #define topology_core_cpumask(cpu)	(&per_cpu(cpu_core_map, cpu))
 #define topology_core_id(cpu)		(cpu_to_core_id(cpu))