Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6 into for-linus

5 files changed, 98 insertions, 29 deletions

diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 2b5a399f6fa..0f2d239d94c 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -94,6 +94,9 @@ unsigned long htab_hash_mask;
 int mmu_linear_psize = MMU_PAGE_4K;
 int mmu_virtual_psize = MMU_PAGE_4K;
 int mmu_vmalloc_psize = MMU_PAGE_4K;
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+int mmu_vmemmap_psize = MMU_PAGE_4K;
+#endif
 int mmu_io_psize = MMU_PAGE_4K;
 int mmu_kernel_ssize = MMU_SEGSIZE_256M;
 int mmu_highuser_ssize = MMU_SEGSIZE_256M;
@@ -387,11 +390,32 @@ static void __init htab_init_page_sizes(void)
 	}
 #endif /* CONFIG_PPC_64K_PAGES */
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	/* We try to use 16M pages for vmemmap if that is supported
+	 * and we have at least 1G of RAM at boot
+	 */
+	if (mmu_psize_defs[MMU_PAGE_16M].shift &&
+	    lmb_phys_mem_size() >= 0x40000000)
+		mmu_vmemmap_psize = MMU_PAGE_16M;
+	else if (mmu_psize_defs[MMU_PAGE_64K].shift)
+		mmu_vmemmap_psize = MMU_PAGE_64K;
+	else
+		mmu_vmemmap_psize = MMU_PAGE_4K;
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+
 	printk(KERN_DEBUG "Page orders: linear mapping = %d, "
-	       "virtual = %d, io = %d\n",
+	       "virtual = %d, io = %d"
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	       ", vmemmap = %d"
+#endif
+	       "\n",
 	       mmu_psize_defs[mmu_linear_psize].shift,
 	       mmu_psize_defs[mmu_virtual_psize].shift,
-	       mmu_psize_defs[mmu_io_psize].shift);
+	       mmu_psize_defs[mmu_io_psize].shift
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	       ,mmu_psize_defs[mmu_vmemmap_psize].shift
+#endif
+	       );
 
 #ifdef CONFIG_HUGETLB_PAGE
 	/* Init large page size. Currently, we pick 16M or 1M depending
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index c5ac532a016..6aa65375abf 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -19,6 +19,8 @@
  *
  */
 
+#undef DEBUG
+
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -208,12 +210,12 @@ int __meminit vmemmap_populated(unsigned long start, int page_size)
 }
 
 int __meminit vmemmap_populate(struct page *start_page,
-					unsigned long nr_pages, int node)
+			       unsigned long nr_pages, int node)
 {
 	unsigned long mode_rw;
 	unsigned long start = (unsigned long)start_page;
 	unsigned long end = (unsigned long)(start_page + nr_pages);
-	unsigned long page_size = 1 << mmu_psize_defs[mmu_linear_psize].shift;
+	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
 
 	mode_rw = _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX;
 
@@ -235,11 +237,11 @@ int __meminit vmemmap_populate(struct page *start_page,
 			start, p, __pa(p));
 
 		mapped = htab_bolt_mapping(start, start + page_size,
-					__pa(p), mode_rw, mmu_linear_psize,
+					__pa(p), mode_rw, mmu_vmemmap_psize,
 					mmu_kernel_ssize);
 		BUG_ON(mapped < 0);
 	}
 
 	return 0;
 }
-#endif
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index d9e37f365b5..f67e118116f 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -154,19 +154,35 @@ out:
 
 /*
  * walk_memory_resource() needs to make sure there is no holes in a given
- * memory range. On PPC64, since this range comes from /sysfs, the range
- * is guaranteed to be valid, non-overlapping and can not contain any
- * holes. By the time we get here (memory add or remove), /proc/device-tree
- * is updated and correct. Only reason we need to check against device-tree
- * would be if we allow user-land to specify a memory range through a
- * system call/ioctl etc. instead of doing offline/online through /sysfs.
+ * memory range.  PPC64 does not maintain the memory layout in /proc/iomem.
+ * Instead it maintains it in lmb.memory structures.  Walk through the
+ * memory regions, find holes and callback for contiguous regions.
  */
 int
 walk_memory_resource(unsigned long start_pfn, unsigned long nr_pages, void *arg,
 			int (*func)(unsigned long, unsigned long, void *))
 {
-	return  (*func)(start_pfn, nr_pages, arg);
+	struct lmb_property res;
+	unsigned long pfn, len;
+	u64 end;
+	int ret = -1;
+
+	res.base = (u64) start_pfn << PAGE_SHIFT;
+	res.size = (u64) nr_pages << PAGE_SHIFT;
+
+	end = res.base + res.size - 1;
+	while ((res.base < end) && (lmb_find(&res) >= 0)) {
+		pfn = (unsigned long)(res.base >> PAGE_SHIFT);
+		len = (unsigned long)(res.size >> PAGE_SHIFT);
+		ret = (*func)(pfn, len, arg);
+		if (ret)
+			break;
+		res.base += (res.size + 1);
+		res.size = (end - res.base + 1);
+	}
+	return ret;
 }
+EXPORT_SYMBOL_GPL(walk_memory_resource);
 
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c
index 906daeda59a..89497fb0428 100644
--- a/arch/powerpc/mm/slb.c
+++ b/arch/powerpc/mm/slb.c
@@ -28,9 +28,9 @@
 #include <asm/udbg.h>
 
 #ifdef DEBUG
-#define DBG(fmt...) udbg_printf(fmt)
+#define DBG(fmt...) printk(fmt)
 #else
-#define DBG(fmt...)
+#define DBG pr_debug
 #endif
 
 extern void slb_allocate_realmode(unsigned long ea);
@@ -44,13 +44,13 @@ static void slb_allocate(unsigned long ea)
 	slb_allocate_realmode(ea);
 }
 
+#define slb_esid_mask(ssize)	\
+	(((ssize) == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T)
+
 static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
 					 unsigned long slot)
 {
-	unsigned long mask;
-
-	mask = (ssize == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T;
-	return (ea & mask) | SLB_ESID_V | slot;
+	return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | slot;
 }
 
 #define slb_vsid_shift(ssize)	\
@@ -263,13 +263,19 @@ void slb_initialize(void)
 	extern unsigned int *slb_miss_kernel_load_linear;
 	extern unsigned int *slb_miss_kernel_load_io;
 	extern unsigned int *slb_compare_rr_to_size;
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	extern unsigned int *slb_miss_kernel_load_vmemmap;
+	unsigned long vmemmap_llp;
+#endif
 
 	/* Prepare our SLB miss handler based on our page size */
 	linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
 	io_llp = mmu_psize_defs[mmu_io_psize].sllp;
 	vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
 	get_paca()->vmalloc_sllp = SLB_VSID_KERNEL | vmalloc_llp;
-
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	vmemmap_llp = mmu_psize_defs[mmu_vmemmap_psize].sllp;
+#endif
 	if (!slb_encoding_inited) {
 		slb_encoding_inited = 1;
 		patch_slb_encoding(slb_miss_kernel_load_linear,
@@ -279,8 +285,14 @@ void slb_initialize(void)
 		patch_slb_encoding(slb_compare_rr_to_size,
 				   mmu_slb_size);
 
-		DBG("SLB: linear  LLP = %04x\n", linear_llp);
-		DBG("SLB: io      LLP = %04x\n", io_llp);
+		DBG("SLB: linear  LLP = %04lx\n", linear_llp);
+		DBG("SLB: io      LLP = %04lx\n", io_llp);
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+		patch_slb_encoding(slb_miss_kernel_load_vmemmap,
+				   SLB_VSID_KERNEL | vmemmap_llp);
+		DBG("SLB: vmemmap LLP = %04lx\n", vmemmap_llp);
+#endif
 	}
 
 	get_paca()->stab_rr = SLB_NUM_BOLTED;
@@ -301,11 +313,16 @@ void slb_initialize(void)
 
 	create_shadowed_slbe(VMALLOC_START, mmu_kernel_ssize, vflags, 1);
 
+	/* For the boot cpu, we're running on the stack in init_thread_union,
+	 * which is in the first segment of the linear mapping, and also
+	 * get_paca()->kstack hasn't been initialized yet.
+	 * For secondary cpus, we need to bolt the kernel stack entry now.
+	 */
 	slb_shadow_clear(2);
+	if (raw_smp_processor_id() != boot_cpuid &&
+	    (get_paca()->kstack & slb_esid_mask(mmu_kernel_ssize)) > PAGE_OFFSET)
+		create_shadowed_slbe(get_paca()->kstack,
+				     mmu_kernel_ssize, lflags, 2);
 
-	/* We don't bolt the stack for the time being - we're in boot,
-	 * so the stack is in the bolted segment.  By the time it goes
-	 * elsewhere, we'll call _switch() which will bolt in the new
-	 * one. */
 	asm volatile("isync":::"memory");
 }
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index 657f6b37e9d..bc44dc4b5c6 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -47,8 +47,7 @@ _GLOBAL(slb_allocate_realmode)
 	 * it to VSID 0, which is reserved as a bad VSID - one which
 	 * will never have any pages in it.  */
 
-	/* Check if hitting the linear mapping of the vmalloc/ioremap
-	 * kernel space
+	/* Check if hitting the linear mapping or some other kernel space
 	*/
 	bne	cr7,1f
 
@@ -62,7 +61,18 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT)
 	b	slb_finish_load_1T
 
-1:	/* vmalloc/ioremap mapping encoding bits, the "li" instructions below
+1:
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+	/* Check virtual memmap region. To be patches at kernel boot */
+	cmpldi	cr0,r9,0xf
+	bne	1f
+_GLOBAL(slb_miss_kernel_load_vmemmap)
+	li	r11,0
+	b	6f
+1:
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+
+	/* vmalloc/ioremap mapping encoding bits, the "li" instructions below
 	 * will be patched by the kernel at boot
 	 */
 BEGIN_FTR_SECTION