Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (49 commits)
  powerpc: Fix build bug with binutils < 2.18 and GCC < 4.2
  powerpc/eeh: Don't panic when EEH_MAX_FAILS is exceeded
  fbdev: Teaches offb about palette on radeon r5xx/r6xx
  powerpc/cell/edac: Log a syndrome code in case of correctable error
  powerpc/cell: Add DMA_ATTR_WEAK_ORDERING dma attribute and use in Cell IOMMU code
  powerpc: Indicate which oprofile counters to use while in compat mode
  powerpc/boot: Change spaces to tabs
  powerpc: Remove duplicate 6xx option in Kconfig
  powerpc: Use PPC_LONG and PPC_LONG_ALIGN in lib/string.S
  powerpc: Use PPC_LONG_ALIGN in uaccess.h
  powerpc: Add a #define for aligning to a long-sized boundary
  powerpc: Fix OF parsing of 64 bits PCI addresses
  powerpc: Use WARN_ON(1) instead of __WARN()
  powerpc: Fix support for latencytop
  powerpc/ps3: Update ps3_defconfig
  powerpc/ps3: Add a sub-match id to ps3_system_bus
  powerpc: Add a 6xx defconfig
  powerpc/dma: Use the struct dma_attrs in iommu code
  powerpc/cell: Add support for power button of future IBM cell blades
  powerpc/cell: Cleanup sysreset_hack for IBM cell blades
  ...

7 files changed, 130 insertions, 168 deletions

diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index f7f3c215d06f..b936a1dd0a50 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -355,6 +355,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.machine_check		= machine_check_generic,
+		.oprofile_cpu_type	= "ppc64/compat-power5+",
 		.platform		= "power5+",
 	},
 	{	/* Power6 */
@@ -386,6 +387,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.machine_check		= machine_check_generic,
+		.oprofile_cpu_type	= "ppc64/compat-power6",
 		.platform		= "power6",
 	},
 	{	/* 2.06-compliant processor, i.e. Power7 "architected" mode */
@@ -397,6 +399,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.machine_check		= machine_check_generic,
+		.oprofile_cpu_type	= "ppc64/compat-power7",
 		.platform		= "power7",
 	},
 	{	/* Power7 */
@@ -1629,6 +1632,23 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr)
 				t->cpu_setup = s->cpu_setup;
 				t->cpu_restore = s->cpu_restore;
 				t->platform = s->platform;
+				/*
+				 * If we have passed through this logic once
+				 * before and have pulled the default case
+				 * because the real PVR was not found inside
+				 * cpu_specs[], then we are possibly running in
+				 * compatibility mode. In that case, let the
+				 * oprofiler know which set of compatibility
+				 * counters to pull from by making sure the
+				 * oprofile_cpu_type string is set to that of
+				 * compatibility mode. If the oprofile_cpu_type
+				 * already has a value, then we are possibly
+				 * overriding a real PVR with a logical one, and,
+				 * in that case, keep the current value for
+				 * oprofile_cpu_type.
+				 */
+				if (t->oprofile_cpu_type == NULL)
+					t->oprofile_cpu_type = s->oprofile_cpu_type;
 			} else
 				*t = *s;
 			*PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index c4268500e856..3cb52fa0eda3 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -151,16 +151,11 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	/* Invalidate TLB0 */
 	li	r6,0x04
 	tlbivax 0,r6
-#ifdef CONFIG_SMP
-	tlbsync
-#endif
+	TLBSYNC
 	/* Invalidate TLB1 */
 	li	r6,0x0c
 	tlbivax 0,r6
-#ifdef CONFIG_SMP
-	tlbsync
-#endif
-	msync
+	TLBSYNC
 
 /* 3. Setup a temp mapping and jump to it */
 	andi.	r5, r3, 0x1	/* Find an entry not used and is non-zero */
@@ -238,10 +233,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	/* Invalidate TLB1 */
 	li	r9,0x0c
 	tlbivax 0,r9
-#ifdef CONFIG_SMP
-	tlbsync
-#endif
-	msync
+	TLBSYNC
 
 /* 6. Setup KERNELBASE mapping in TLB1[0] */
 	lis	r6,0x1000		/* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */
@@ -283,10 +275,7 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	/* Invalidate TLB1 */
 	li	r9,0x0c
 	tlbivax 0,r9
-#ifdef CONFIG_SMP
-	tlbsync
-#endif
-	msync
+	TLBSYNC
 
 	/* Establish the interrupt vector offsets */
 	SET_IVOR(0,  CriticalInput);
@@ -483,90 +472,16 @@ interrupt_base:
 
 	/* Data Storage Interrupt */
 	START_EXCEPTION(DataStorage)
-	mtspr	SPRN_SPRG0, r10		/* Save some working registers */
-	mtspr	SPRN_SPRG1, r11
-	mtspr	SPRN_SPRG4W, r12
-	mtspr	SPRN_SPRG5W, r13
-	mfcr	r11
-	mtspr	SPRN_SPRG7W, r11
-
-	/*
-	 * Check if it was a store fault, if not then bail
-	 * because a user tried to access a kernel or
-	 * read-protected page.  Otherwise, get the
-	 * offending address and handle it.
-	 */
-	mfspr	r10, SPRN_ESR
-	andis.	r10, r10, ESR_ST@h
-	beq	2f
-
-	mfspr	r10, SPRN_DEAR		/* Get faulting address */
-
-	/* If we are faulting a kernel address, we have to use the
-	 * kernel page tables.
-	 */
-	lis	r11, PAGE_OFFSET@h
-	cmplw	0, r10, r11
-	bge	2f
-
-	/* Get the PGD for the current thread */
-3:
-	mfspr	r11,SPRN_SPRG3
-	lwz	r11,PGDIR(r11)
-4:
-	FIND_PTE
-
-	/* Are _PAGE_USER & _PAGE_RW set & _PAGE_HWWRITE not? */
-	andi.	r13, r11, _PAGE_RW|_PAGE_USER|_PAGE_HWWRITE
-	cmpwi	0, r13, _PAGE_RW|_PAGE_USER
-	bne	2f			/* Bail if not */
-
-	/* Update 'changed'. */
-	ori	r11, r11, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE
-	stw	r11, PTE_FLAGS_OFFSET(r12) /* Update Linux page table */
-
-	/* MAS2 not updated as the entry does exist in the tlb, this
-	   fault taken to detect state transition (eg: COW -> DIRTY)
-	 */
-	andi.	r11, r11, _PAGE_HWEXEC
-	rlwimi	r11, r11, 31, 27, 27	/* SX <- _PAGE_HWEXEC */
-	ori	r11, r11, (MAS3_UW|MAS3_SW|MAS3_UR|MAS3_SR)@l /* set static perms */
-
-	/* update search PID in MAS6, AS = 0 */
-	mfspr	r12, SPRN_PID0
-	slwi	r12, r12, 16
-	mtspr	SPRN_MAS6, r12
-
-	/* find the TLB index that caused the fault.  It has to be here. */
-	tlbsx	0, r10
-
-	/* only update the perm bits, assume the RPN is fine */
-	mfspr	r12, SPRN_MAS3
-	rlwimi	r12, r11, 0, 20, 31
-	mtspr	SPRN_MAS3,r12
-	tlbwe
-
-	/* Done...restore registers and get out of here.  */
-	mfspr	r11, SPRN_SPRG7R
-	mtcr	r11
-	mfspr	r13, SPRN_SPRG5R
-	mfspr	r12, SPRN_SPRG4R
-	mfspr	r11, SPRN_SPRG1
-	mfspr	r10, SPRN_SPRG0
-	rfi			/* Force context change */
-
-2:
-	/*
-	 * The bailout.  Restore registers to pre-exception conditions
-	 * and call the heavyweights to help us out.
-	 */
-	mfspr	r11, SPRN_SPRG7R
-	mtcr	r11
-	mfspr	r13, SPRN_SPRG5R
-	mfspr	r12, SPRN_SPRG4R
-	mfspr	r11, SPRN_SPRG1
-	mfspr	r10, SPRN_SPRG0
-	b	data_access
+	NORMAL_EXCEPTION_PROLOG
+	mfspr	r5,SPRN_ESR		/* Grab the ESR, save it, pass arg3 */
+	stw	r5,_ESR(r11)
+	mfspr	r4,SPRN_DEAR		/* Grab the DEAR, save it, pass arg2 */
+	andis.	r10,r5,(ESR_ILK|ESR_DLK)@h
+	bne	1f
+	EXC_XFER_EE_LITE(0x0300, handle_page_fault)
+1:
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	EXC_XFER_EE_LITE(0x0300, CacheLockingException)
 
 	/* Instruction Storage Interrupt */
 	INSTRUCTION_STORAGE_EXCEPTION
@@ -645,15 +560,30 @@ interrupt_base:
 	lwz	r11,PGDIR(r11)
 
 4:
+	/* Mask of required permission bits. Note that while we
+	 * do copy ESR:ST to _PAGE_RW position as trying to write
+	 * to an RO page is pretty common, we don't do it with
+	 * _PAGE_DIRTY. We could do it, but it's a fairly rare
+	 * event so I'd rather take the overhead when it happens
+	 * rather than adding an instruction here. We should measure
+	 * whether the whole thing is worth it in the first place
+	 * as we could avoid loading SPRN_ESR completely in the first
+	 * place...
+	 *
+	 * TODO: Is it worth doing that mfspr & rlwimi in the first
+	 *       place or can we save a couple of instructions here ?
+	 */
+	mfspr	r12,SPRN_ESR
+	li	r13,_PAGE_PRESENT|_PAGE_ACCESSED
+	rlwimi	r13,r12,11,29,29
+
 	FIND_PTE
-	andi.	r13, r11, _PAGE_PRESENT	/* Is the page present? */
-	beq	2f			/* Bail if not present */
+	andc.	r13,r13,r11		/* Check permission */
+	bne	2f			/* Bail if permission mismach */
 
 #ifdef CONFIG_PTE_64BIT
 	lwz	r13, 0(r12)
 #endif
-	ori	r11, r11, _PAGE_ACCESSED
-	stw	r11, PTE_FLAGS_OFFSET(r12)
 
 	 /* Jump to common tlb load */
 	b	finish_tlb_load
@@ -667,7 +597,7 @@ interrupt_base:
 	mfspr	r12, SPRN_SPRG4R
 	mfspr	r11, SPRN_SPRG1
 	mfspr	r10, SPRN_SPRG0
-	b	data_access
+	b	DataStorage
 
 	/* Instruction TLB Error Interrupt */
 	/*
@@ -705,15 +635,16 @@ interrupt_base:
 	lwz	r11,PGDIR(r11)
 
 4:
+	/* Make up the required permissions */
+	li	r13,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_HWEXEC
+
 	FIND_PTE
-	andi.	r13, r11, _PAGE_PRESENT	/* Is the page present? */
-	beq	2f			/* Bail if not present */
+	andc.	r13,r13,r11		/* Check permission */
+	bne	2f			/* Bail if permission mismach */
 
 #ifdef CONFIG_PTE_64BIT
 	lwz	r13, 0(r12)
 #endif
-	ori	r11, r11, _PAGE_ACCESSED
-	stw	r11, PTE_FLAGS_OFFSET(r12)
 
 	/* Jump to common TLB load point */
 	b	finish_tlb_load
@@ -768,29 +699,13 @@ interrupt_base:
  * Local functions
  */
 
-	/*
-	 * Data TLB exceptions will bail out to this point
-	 * if they can't resolve the lightweight TLB fault.
-	 */
-data_access:
-	NORMAL_EXCEPTION_PROLOG
-	mfspr	r5,SPRN_ESR		/* Grab the ESR, save it, pass arg3 */
-	stw	r5,_ESR(r11)
-	mfspr	r4,SPRN_DEAR		/* Grab the DEAR, save it, pass arg2 */
-	andis.	r10,r5,(ESR_ILK|ESR_DLK)@h
-	bne	1f
-	EXC_XFER_EE_LITE(0x0300, handle_page_fault)
-1:
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	EXC_XFER_EE_LITE(0x0300, CacheLockingException)
-
 /*
-
  * Both the instruction and data TLB miss get to this
  * point to load the TLB.
  *	r10 - EA of fault
  *	r11 - TLB (info from Linux PTE)
- *	r12, r13 - available to use
+ *	r12 - available to use
+ *	r13 - upper bits of PTE (if PTE_64BIT) or available to use
  *	CR5 - results of addr >= PAGE_OFFSET
  *	MAS0, MAS1 - loaded with proper value when we get here
  *	MAS2, MAS3 - will need additional info from Linux PTE
@@ -812,20 +727,14 @@ finish_tlb_load:
 #endif
 	mtspr	SPRN_MAS2, r12
 
-	bge	5, 1f
-
-	/* is user addr */
-	andi.	r12, r11, (_PAGE_USER | _PAGE_HWWRITE | _PAGE_HWEXEC)
+	li	r10, (_PAGE_HWEXEC | _PAGE_PRESENT)
+	rlwimi	r10, r11, 31, 29, 29	/* extract _PAGE_DIRTY into SW */
+	and	r12, r11, r10
 	andi.	r10, r11, _PAGE_USER	/* Test for _PAGE_USER */
-	srwi	r10, r12, 1
-	or	r12, r12, r10	/* Copy user perms into supervisor */
-	iseleq	r12, 0, r12
-	b	2f
-
-	/* is kernel addr */
-1:	rlwinm	r12, r11, 31, 29, 29	/* Extract _PAGE_HWWRITE into SW */
-	ori	r12, r12, (MAS3_SX | MAS3_SR)
-
+	slwi	r10, r12, 1
+	or	r10, r10, r12
+	iseleq	r12, r12, r10
+	
 #ifdef CONFIG_PTE_64BIT
 2:	rlwimi	r12, r13, 24, 0, 7	/* grab RPN[32:39] */
 	rlwimi	r12, r11, 24, 8, 19	/* grab RPN[40:51] */
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 8c68ee9e5d1c..2385f68c1751 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -186,7 +186,8 @@ static unsigned long iommu_range_alloc(struct device *dev,
 static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 			      void *page, unsigned int npages,
 			      enum dma_data_direction direction,
-			      unsigned long mask, unsigned int align_order)
+			      unsigned long mask, unsigned int align_order,
+			      struct dma_attrs *attrs)
 {
 	unsigned long entry, flags;
 	dma_addr_t ret = DMA_ERROR_CODE;
@@ -205,7 +206,7 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 
 	/* Put the TCEs in the HW table */
 	ppc_md.tce_build(tbl, entry, npages, (unsigned long)page & IOMMU_PAGE_MASK,
-			 direction);
+			 direction, attrs);
 
 
 	/* Flush/invalidate TLB caches if necessary */
@@ -336,7 +337,8 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			    npages, entry, dma_addr);
 
 		/* Insert into HW table */
-		ppc_md.tce_build(tbl, entry, npages, vaddr & IOMMU_PAGE_MASK, direction);
+		ppc_md.tce_build(tbl, entry, npages, vaddr & IOMMU_PAGE_MASK,
+				 direction, attrs);
 
 		/* If we are in an open segment, try merging */
 		if (segstart != s) {
@@ -573,7 +575,8 @@ dma_addr_t iommu_map_single(struct device *dev, struct iommu_table *tbl,
 			align = PAGE_SHIFT - IOMMU_PAGE_SHIFT;
 
 		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction,
-					 mask >> IOMMU_PAGE_SHIFT, align);
+					 mask >> IOMMU_PAGE_SHIFT, align,
+					 attrs);
 		if (dma_handle == DMA_ERROR_CODE) {
 			if (printk_ratelimit())  {
 				printk(KERN_INFO "iommu_alloc failed, "
@@ -642,7 +645,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	nio_pages = size >> IOMMU_PAGE_SHIFT;
 	io_order = get_iommu_order(size);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
-			      mask >> IOMMU_PAGE_SHIFT, io_order);
+			      mask >> IOMMU_PAGE_SHIFT, io_order, NULL);
 	if (mapping == DMA_ERROR_CODE) {
 		free_pages((unsigned long)ret, order);
 		return NULL;
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 063cdd413049..224e9a11765c 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -598,6 +598,7 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose,
 			res->start = pci_addr;
 			break;
 		case 2:		/* PCI Memory space */
+		case 3:		/* PCI 64 bits Memory space */
 			printk(KERN_INFO
 			       " MEM 0x%016llx..0x%016llx -> 0x%016llx %s\n",
 			       cpu_addr, cpu_addr + size - 1, pci_addr,
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index 90eb3a3e383e..bc1fb27368af 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -128,12 +128,35 @@ static void of_bus_pci_count_cells(struct device_node *np,
 		*sizec = 2;
 }
 
+static unsigned int of_bus_pci_get_flags(const u32 *addr)
+{
+	unsigned int flags = 0;
+	u32 w = addr[0];
+
+	switch((w >> 24) & 0x03) {
+	case 0x01:
+		flags |= IORESOURCE_IO;
+		break;
+	case 0x02: /* 32 bits */
+	case 0x03: /* 64 bits */
+		flags |= IORESOURCE_MEM;
+		break;
+	}
+	if (w & 0x40000000)
+		flags |= IORESOURCE_PREFETCH;
+	return flags;
+}
+
 static u64 of_bus_pci_map(u32 *addr, const u32 *range, int na, int ns, int pna)
 {
 	u64 cp, s, da;
+	unsigned int af, rf;
+
+	af = of_bus_pci_get_flags(addr);
+	rf = of_bus_pci_get_flags(range);
 
 	/* Check address type match */
-	if ((addr[0] ^ range[0]) & 0x03000000)
+	if ((af ^ rf) & (IORESOURCE_MEM | IORESOURCE_IO))
 		return OF_BAD_ADDR;
 
 	/* Read address values, skipping high cell */
@@ -153,25 +176,6 @@ static int of_bus_pci_translate(u32 *addr, u64 offset, int na)
 	return of_bus_default_translate(addr + 1, offset, na - 1);
 }
 
-static unsigned int of_bus_pci_get_flags(const u32 *addr)
-{
-	unsigned int flags = 0;
-	u32 w = addr[0];
-
-	switch((w >> 24) & 0x03) {
-	case 0x01:
-		flags |= IORESOURCE_IO;
-		break;
-	case 0x02: /* 32 bits */
-	case 0x03: /* 64 bits */
-		flags |= IORESOURCE_MEM;
-		break;
-	}
-	if (w & 0x40000000)
-		flags |= IORESOURCE_PREFETCH;
-	return flags;
-}
-
 const u32 *of_get_pci_address(struct device_node *dev, int bar_no, u64 *size,
 			unsigned int *flags)
 {
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index 071bee3ec749..f2589645870a 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -59,6 +59,6 @@ EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
-	save_context_stack(trace, tsk->thread.regs->gpr[1], tsk, 0);
+	save_context_stack(trace, tsk->thread.ksp, tsk, 0);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 87a72c66ce27..a914411bced5 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -9,6 +9,25 @@
 
 ENTRY(_stext)
 
+PHDRS {
+	kernel PT_LOAD FLAGS(7); /* RWX */
+	notes PT_NOTE FLAGS(0);
+	dummy PT_NOTE FLAGS(0);
+
+	/* binutils < 2.18 has a bug that makes it misbehave when taking an
+	   ELF file with all segments at load address 0 as input.  This
+	   happens when running "strip" on vmlinux, because of the AT() magic
+	   in this linker script.  People using GCC >= 4.2 won't run into
+	   this problem, because the "build-id" support will put some data
+	   into the "notes" segment (at a non-zero load address).
+
+	   To work around this, we force some data into both the "dummy"
+	   segment and the kernel segment, so the dummy segment will get a
+	   non-zero load address.  It's not enough to always create the
+	   "notes" segment, since if nothing gets assigned to it, its load
+	   address will be zero.  */
+}
+
 #ifdef CONFIG_PPC64
 OUTPUT_ARCH(powerpc:common64)
 jiffies = jiffies_64;
@@ -50,7 +69,7 @@ SECTIONS
 		. = ALIGN(PAGE_SIZE);
 		_etext = .;
 		PROVIDE32 (etext = .);
-	}
+	} :kernel
 
 	/* Read-only data */
 	RODATA
@@ -62,7 +81,13 @@ SECTIONS
 		__stop___ex_table = .;
 	}
 
-	NOTES
+	NOTES :kernel :notes
+
+	/* The dummy segment contents for the bug workaround mentioned above
+	   near PHDRS.  */
+	.dummy : {
+		LONG(0xf177)
+	} :kernel :dummy
 
 /*
  * Init sections discarded at runtime
@@ -74,7 +99,7 @@ SECTIONS
 		_sinittext = .;
 		INIT_TEXT
 		_einittext = .;
-	}
+	} :kernel
 
 	/* .exit.text is discarded at runtime, not link time,
 	 * to deal with references from __bug_table