Merge branch 'vmalloc' of git://git.linaro.org/people/nico/linux into devel-stable

5 files changed, 113 insertions, 76 deletions

diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index fbdd12ea3a58..786adddf1a86 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -20,7 +20,6 @@
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
-#include <linux/sort.h>
 
 #include <asm/mach-types.h>
 #include <asm/prom.h>
@@ -134,30 +133,18 @@ void show_mem(unsigned int filter)
 }
 
 static void __init find_limits(unsigned long *min, unsigned long *max_low,
-	unsigned long *max_high)
+			       unsigned long *max_high)
 {
 	struct meminfo *mi = &meminfo;
 	int i;
 
-	*min = -1UL;
-	*max_low = *max_high = 0;
-
-	for_each_bank (i, mi) {
-		struct membank *bank = &mi->bank[i];
-		unsigned long start, end;
-
-		start = bank_pfn_start(bank);
-		end = bank_pfn_end(bank);
-
-		if (*min > start)
-			*min = start;
-		if (*max_high < end)
-			*max_high = end;
-		if (bank->highmem)
-			continue;
-		if (*max_low < end)
-			*max_low = end;
-	}
+	/* This assumes the meminfo array is properly sorted */
+	*min = bank_pfn_start(&mi->bank[0]);
+	for_each_bank (i, mi)
+		if (mi->bank[i].highmem)
+				break;
+	*max_low = bank_pfn_end(&mi->bank[i - 1]);
+	*max_high = bank_pfn_end(&mi->bank[mi->nr_banks - 1]);
 }
 
 static void __init arm_bootmem_init(unsigned long start_pfn,
@@ -319,19 +306,10 @@ static void arm_memory_present(void)
 }
 #endif
 
-static int __init meminfo_cmp(const void *_a, const void *_b)
-{
-	const struct membank *a = _a, *b = _b;
-	long cmp = bank_pfn_start(a) - bank_pfn_start(b);
-	return cmp < 0 ? -1 : cmp > 0 ? 1 : 0;
-}
-
 void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 {
 	int i;
 
-	sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
-
 	memblock_init();
 	for (i = 0; i < mi->nr_banks; i++)
 		memblock_add(mi->bank[i].start, mi->bank[i].size);
@@ -403,8 +381,6 @@ void __init bootmem_init(void)
 	 */
 	arm_bootmem_free(min, max_low, max_high);
 
-	high_memory = __va(((phys_addr_t)max_low << PAGE_SHIFT) - 1) + 1;
-
 	/*
 	 * This doesn't seem to be used by the Linux memory manager any
 	 * more, but is used by ll_rw_block.  If we can get rid of it, we
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index bdb248c4f55c..12c7ad215ce7 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -36,12 +36,6 @@
 #include <asm/mach/map.h>
 #include "mm.h"
 
-/*
- * Used by ioremap() and iounmap() code to mark (super)section-mapped
- * I/O regions in vm_struct->flags field.
- */
-#define VM_ARM_SECTION_MAPPING	0x80000000
-
 int ioremap_page(unsigned long virt, unsigned long phys,
 		 const struct mem_type *mtype)
 {
@@ -201,12 +195,6 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SUPERSECTION_MASK))
 		return NULL;
 
-	/*
-	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
-	 */
-	if (WARN_ON(pfn_valid(pfn)))
-		return NULL;
-
 	type = get_mem_type(mtype);
 	if (!type)
 		return NULL;
@@ -216,6 +204,34 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	 */
 	size = PAGE_ALIGN(offset + size);
 
+	/*
+	 * Try to reuse one of the static mapping whenever possible.
+	 */
+	read_lock(&vmlist_lock);
+	for (area = vmlist; area; area = area->next) {
+		if (!size || (sizeof(phys_addr_t) == 4 && pfn >= 0x100000))
+			break;
+		if (!(area->flags & VM_ARM_STATIC_MAPPING))
+			continue;
+		if ((area->flags & VM_ARM_MTYPE_MASK) != VM_ARM_MTYPE(mtype))
+			continue;
+		if (__phys_to_pfn(area->phys_addr) > pfn ||
+		    __pfn_to_phys(pfn) + size-1 > area->phys_addr + area->size-1)
+			continue;
+		/* we can drop the lock here as we know *area is static */
+		read_unlock(&vmlist_lock);
+		addr = (unsigned long)area->addr;
+		addr += __pfn_to_phys(pfn) - area->phys_addr;
+		return (void __iomem *) (offset + addr);
+	}
+	read_unlock(&vmlist_lock);
+
+	/*
+	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
+	 */
+	if (WARN_ON(pfn_valid(pfn)))
+		return NULL;
+
 	area = get_vm_area_caller(size, VM_IOREMAP, caller);
  	if (!area)
  		return NULL;
@@ -313,28 +329,34 @@ __arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached)
 void __iounmap(volatile void __iomem *io_addr)
 {
 	void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
-#ifndef CONFIG_SMP
-	struct vm_struct **p, *tmp;
+	struct vm_struct *vm;
 
-	/*
-	 * If this is a section based mapping we need to handle it
-	 * specially as the VM subsystem does not know how to handle
-	 * such a beast. We need the lock here b/c we need to clear
-	 * all the mappings before the area can be reclaimed
-	 * by someone else.
-	 */
-	write_lock(&vmlist_lock);
-	for (p = &vmlist ; (tmp = *p) ; p = &tmp->next) {
-		if ((tmp->flags & VM_IOREMAP) && (tmp->addr == addr)) {
-			if (tmp->flags & VM_ARM_SECTION_MAPPING) {
-				unmap_area_sections((unsigned long)tmp->addr,
-						    tmp->size);
-			}
+	read_lock(&vmlist_lock);
+	for (vm = vmlist; vm; vm = vm->next) {
+		if (vm->addr > addr)
+			break;
+		if (!(vm->flags & VM_IOREMAP))
+			continue;
+		/* If this is a static mapping we must leave it alone */
+		if ((vm->flags & VM_ARM_STATIC_MAPPING) &&
+		    (vm->addr <= addr) && (vm->addr + vm->size > addr)) {
+			read_unlock(&vmlist_lock);
+			return;
+		}
+#ifndef CONFIG_SMP
+		/*
+		 * If this is a section based mapping we need to handle it
+		 * specially as the VM subsystem does not know how to handle
+		 * such a beast.
+		 */
+		if ((vm->addr == addr) &&
+		    (vm->flags & VM_ARM_SECTION_MAPPING)) {
+			unmap_area_sections((unsigned long)vm->addr, vm->size);
 			break;
 		}
-	}
-	write_unlock(&vmlist_lock);
 #endif
+	}
+	read_unlock(&vmlist_lock);
 
 	vunmap(addr);
 }
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index ad7cce3bc431..70f6d3ea4834 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -21,6 +21,20 @@ const struct mem_type *get_mem_type(unsigned int type);
 
 extern void __flush_dcache_page(struct address_space *mapping, struct page *page);
 
+/*
+ * ARM specific vm_struct->flags bits.
+ */
+
+/* (super)section-mapped I/O regions used by ioremap()/iounmap() */
+#define VM_ARM_SECTION_MAPPING	0x80000000
+
+/* permanent static mappings from iotable_init() */
+#define VM_ARM_STATIC_MAPPING	0x40000000
+
+/* mapping type (attributes) for permanent static mappings */
+#define VM_ARM_MTYPE(mt)		((mt) << 20)
+#define VM_ARM_MTYPE_MASK	(0x1f << 20)
+
 #endif
 
 #ifdef CONFIG_ZONE_DMA
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index dc8c550e6cbd..27e366af67f9 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -15,6 +15,7 @@
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
 #include <linux/fs.h>
+#include <linux/vmalloc.h>
 
 #include <asm/cputype.h>
 #include <asm/sections.h>
@@ -529,13 +530,18 @@ EXPORT_SYMBOL(phys_mem_access_prot);
 
 #define vectors_base()	(vectors_high() ? 0xffff0000 : 0)
 
-static void __init *early_alloc(unsigned long sz)
+static void __init *early_alloc_aligned(unsigned long sz, unsigned long align)
 {
-	void *ptr = __va(memblock_alloc(sz, sz));
+	void *ptr = __va(memblock_alloc(sz, align));
 	memset(ptr, 0, sz);
 	return ptr;
 }
 
+static void __init *early_alloc(unsigned long sz)
+{
+	return early_alloc_aligned(sz, sz);
+}
+
 static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr, unsigned long prot)
 {
 	if (pmd_none(*pmd)) {
@@ -685,9 +691,10 @@ static void __init create_mapping(struct map_desc *md)
 	}
 
 	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
-	    md->virtual >= PAGE_OFFSET && md->virtual < VMALLOC_END) {
+	    md->virtual >= PAGE_OFFSET &&
+	    (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) {
 		printk(KERN_WARNING "BUG: mapping for 0x%08llx"
-		       " at 0x%08lx overlaps vmalloc space\n",
+		       " at 0x%08lx out of vmalloc space\n",
 		       (long long)__pfn_to_phys((u64)md->pfn), md->virtual);
 	}
 
@@ -729,18 +736,33 @@ static void __init create_mapping(struct map_desc *md)
  */
 void __init iotable_init(struct map_desc *io_desc, int nr)
 {
-	int i;
+	struct map_desc *md;
+	struct vm_struct *vm;
+
+	if (!nr)
+		return;
 
-	for (i = 0; i < nr; i++)
-		create_mapping(io_desc + i);
+	vm = early_alloc_aligned(sizeof(*vm) * nr, __alignof__(*vm));
+
+	for (md = io_desc; nr; md++, nr--) {
+		create_mapping(md);
+		vm->addr = (void *)(md->virtual & PAGE_MASK);
+		vm->size = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK));
+		vm->phys_addr = __pfn_to_phys(md->pfn); 
+		vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING; 
+		vm->flags |= VM_ARM_MTYPE(md->type);
+		vm->caller = iotable_init;
+		vm_area_add_early(vm++);
+	}
 }
 
-static void * __initdata vmalloc_min = (void *)(VMALLOC_END - SZ_128M);
+static void * __initdata vmalloc_min =
+	(void *)(VMALLOC_END - (240 << 20) - VMALLOC_OFFSET);
 
 /*
  * vmalloc=size forces the vmalloc area to be exactly 'size'
  * bytes. This can be used to increase (or decrease) the vmalloc
- * area - the default is 128m.
+ * area - the default is 240m.
  */
 static int __init early_vmalloc(char *arg)
 {
@@ -860,6 +882,7 @@ void __init sanity_check_meminfo(void)
 	}
 #endif
 	meminfo.nr_banks = j;
+	high_memory = __va(lowmem_limit - 1) + 1;
 	memblock_set_current_limit(lowmem_limit);
 }
 
@@ -890,10 +913,10 @@ static inline void prepare_page_table(void)
 
 	/*
 	 * Clear out all the kernel space mappings, except for the first
-	 * memory bank, up to the end of the vmalloc region.
+	 * memory bank, up to the vmalloc region.
 	 */
 	for (addr = __phys_to_virt(end);
-	     addr < VMALLOC_END; addr += PMD_SIZE)
+	     addr < VMALLOC_START; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 }
 
@@ -920,8 +943,8 @@ void __init arm_mm_memblock_reserve(void)
 }
 
 /*
- * Set up device the mappings.  Since we clear out the page tables for all
- * mappings above VMALLOC_END, we will remove any debug device mappings.
+ * Set up the device mappings.  Since we clear out the page tables for all
+ * mappings above VMALLOC_START, we will remove any debug device mappings.
  * This means you have to be careful how you debug this function, or any
  * called function.  This means you can't use any function or debugging
  * method which may touch any device, otherwise the kernel _will_ crash.
@@ -936,7 +959,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 */
 	vectors_page = early_alloc(PAGE_SIZE);
 
-	for (addr = VMALLOC_END; addr; addr += PMD_SIZE)
+	for (addr = VMALLOC_START; addr; addr += PMD_SIZE)
 		pmd_clear(pmd_off_k(addr));
 
 	/*
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 88417514b2c6..4fc6794cca4b 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -29,6 +29,8 @@ void __init arm_mm_memblock_reserve(void)
 
 void __init sanity_check_meminfo(void)
 {
+	phys_addr_t end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]);
+	high_memory = __va(end - 1) + 1;
 }
 
 /*