[PATCH v4 3/3] ARM: mm: use static_vm for managing static mapped areas

[Joonsoo Kim <iamjoonsoo.kim@lge.com>]

A static mapped area is ARM-specific, so it is better not to use
generic vmalloc data structure, that is, vmlist and vmlist_lock
for managing static mapped area. And it causes some needless overhead and
reducing this overhead is better idea.

Now, we have newly introduced static_vm infrastructure.
With it, we don't need to iterate all mapped areas. Instead, we just
iterate static mapped areas. It helps to reduce an overhead of finding
matched area. And architecture dependency on vmalloc layer is removed,
so it will help to maintainability for vmalloc layer.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>

diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index ceb34ae..7fe5b48 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -269,13 +269,14 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	const struct mem_type *type;
 	int err;
 	unsigned long addr;
- 	struct vm_struct * area;
+	struct vm_struct *area;
+	phys_addr_t paddr = __pfn_to_phys(pfn);
 
 #ifndef CONFIG_ARM_LPAE
 	/*
 	 * High mappings must be supersection aligned
 	 */
-	if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SUPERSECTION_MASK))
+	if (pfn >= 0x100000 && (paddr & ~SUPERSECTION_MASK))
 		return NULL;
 #endif
 
@@ -291,24 +292,17 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	/*
 	 * 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);
+	if (size && !((sizeof(phys_addr_t) == 4 && pfn >= 0x100000))) {
+		struct static_vm *svm;
+
+		svm = find_static_vm_paddr(paddr, size,
+				STATIC_VM_TYPE(STATIC_VM_MEM, mtype));
+		if (svm) {
+			addr = (unsigned long)svm->vm.addr;
+			addr += paddr - svm->vm.phys_addr;
+			return (void __iomem *) (offset + addr);
+		}
 	}
-	read_unlock(&vmlist_lock);
 
 	/*
 	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
@@ -320,21 +314,21 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
  	if (!area)
  		return NULL;
  	addr = (unsigned long)area->addr;
-	area->phys_addr = __pfn_to_phys(pfn);
+	area->phys_addr = paddr;
 
 #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 	if (DOMAIN_IO == 0 &&
 	    (((cpu_architecture() >= CPU_ARCH_ARMv6) && (get_cr() & CR_XP)) ||
 	       cpu_is_xsc3()) && pfn >= 0x100000 &&
-	       !((__pfn_to_phys(pfn) | size | addr) & ~SUPERSECTION_MASK)) {
+	       !((paddr | size | addr) & ~SUPERSECTION_MASK)) {
 		area->flags |= VM_ARM_SECTION_MAPPING;
 		err = remap_area_supersections(addr, pfn, size, type);
-	} else if (!((__pfn_to_phys(pfn) | size | addr) & ~PMD_MASK)) {
+	} else if (!((paddr | size | addr) & ~PMD_MASK)) {
 		area->flags |= VM_ARM_SECTION_MAPPING;
 		err = remap_area_sections(addr, pfn, size, type);
 	} else
 #endif
-		err = ioremap_page_range(addr, addr + size, __pfn_to_phys(pfn),
+		err = ioremap_page_range(addr, addr + size, paddr,
 					 __pgprot(type->prot_pte));
 
 	if (err) {
@@ -418,34 +412,21 @@ __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);
-	struct vm_struct *vm;
+	struct static_vm *svm;
+
+	svm = find_static_vm_vaddr(addr);
+	if (svm)
+		return;
 
-	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;
-		}
 #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
-		/*
-		 * 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)) {
+	{
+		struct vm_struct *vm;
+
+		vm = find_vm_area(addr);
+		if (vm && (vm->flags & VM_ARM_SECTION_MAPPING))
 			unmap_area_sections((unsigned long)vm->addr, vm->size);
-			break;
-		}
-#endif
 	}
-	read_unlock(&vmlist_lock);
+#endif
 
 	vunmap(addr);
 }
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index fb45c79..24c1df4 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -54,16 +54,6 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
 /* (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
-
-/* empty mapping */
-#define VM_ARM_EMPTY_MAPPING	0x20000000
-
-/* mapping type (attributes) for permanent static mappings */
-#define VM_ARM_MTYPE(mt)		((mt) << 20)
-#define VM_ARM_MTYPE_MASK	(0x1f << 20)
-
 /* consistent regions used by dma_alloc_attrs() */
 #define VM_ARM_DMA_CONSISTENT	0x20000000
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index ce328c7..a7dc9a2 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -757,21 +757,24 @@ void __init iotable_init(struct map_desc *io_desc, int nr)
 {
 	struct map_desc *md;
 	struct vm_struct *vm;
+	struct static_vm *svm;
 
 	if (!nr)
 		return;
 
-	vm = early_alloc_aligned(sizeof(*vm) * nr, __alignof__(*vm));
+	svm = early_alloc_aligned(sizeof(*svm) * nr, __alignof__(*svm));
 
 	for (md = io_desc; nr; md++, nr--) {
 		create_mapping(md);
+
+		vm = &svm->vm;
 		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->flags = VM_IOREMAP;
 		vm->caller = iotable_init;
-		vm_area_add_early(vm++);
+		add_static_vm_early(svm++,
+			STATIC_VM_TYPE(STATIC_VM_MEM, md->type));
 	}
 }
 
@@ -779,13 +782,16 @@ void __init vm_reserve_area_early(unsigned long addr, unsigned long size,
 				  void *caller)
 {
 	struct vm_struct *vm;
+	struct static_vm *svm;
+
+	svm = early_alloc_aligned(sizeof(*svm), __alignof__(*svm));
 
-	vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm));
+	vm = &svm->vm;
 	vm->addr = (void *)addr;
 	vm->size = size;
-	vm->flags = VM_IOREMAP | VM_ARM_EMPTY_MAPPING;
+	vm->flags = VM_IOREMAP;
 	vm->caller = caller;
-	vm_area_add_early(vm);
+	add_static_vm_early(svm, STATIC_VM_TYPE(STATIC_VM_EMPTY, 0));
 }
 
 #ifndef CONFIG_ARM_LPAE
@@ -810,14 +816,20 @@ static void __init pmd_empty_section_gap(unsigned long addr)
 
 static void __init fill_pmd_gaps(void)
 {
+	struct static_vm *svm;
 	struct vm_struct *vm;
 	unsigned long addr, next = 0;
 	pmd_t *pmd;
 
-	/* we're still single threaded hence no lock needed here */
-	for (vm = vmlist; vm; vm = vm->next) {
-		if (!(vm->flags & (VM_ARM_STATIC_MAPPING | VM_ARM_EMPTY_MAPPING)))
-			continue;
+	/*
+	 * We should not take a lock here, because pmd_empty_section_gap()
+	 * invokes vm_reserve_area_early(), and then it call
+	 * add_static_vm_early() which try to take a lock.
+	 * We're still single thread, so traverse whole list without a lock
+	 * is safe for now. And inserting new entry is also safe.
+	 */
+	list_for_each_entry(svm, &static_vmlist, list) {
+		vm = &svm->vm;
 		addr = (unsigned long)vm->addr;
 		if (addr < next)
 			continue;
@@ -859,17 +871,12 @@ static void __init pci_reserve_io(void)
 {
 	struct vm_struct *vm;
 	unsigned long addr;
+	struct static_vm *svm;
 
-	/* we're still single threaded hence no lock needed here */
-	for (vm = vmlist; vm; vm = vm->next) {
-		if (!(vm->flags & VM_ARM_STATIC_MAPPING))
-			continue;
-		addr = (unsigned long)vm->addr;
-		addr &= ~(SZ_2M - 1);
-		if (addr == PCI_IO_VIRT_BASE)
-			return;
+	svm = find_static_vm_vaddr((void *)PCI_IO_VIRT_BASE);
+	if (svm)
+		return;
 
-	}
 	vm_reserve_area_early(PCI_IO_VIRT_BASE, SZ_2M, pci_reserve_io);
 }
 #else
-- 
1.7.9.5