From ed8fd2186a4e4f3b98434093b56f9b793d48443e Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Sat, 9 Feb 2013 06:28:05 +0100 Subject: ARM: 7645/1: ioremap: introduce an infrastructure for static mapped area In current implementation, we used ARM-specific flag, that is, VM_ARM_STATIC_MAPPING, for distinguishing ARM specific static mapped area. The purpose of static mapped area is to re-use static mapped area when entire physical address range of the ioremap request can be covered by this area. This implementation causes needless overhead for some cases. For example, assume that there is only one static mapped area and vmlist has 300 areas. Every time we call ioremap, we check 300 areas for deciding whether it is matched or not. Moreover, even if there is no static mapped area and vmlist has 300 areas, every time we call ioremap, we check 300 areas in now. If we construct a extra list for static mapped area, we can eliminate above mentioned overhead. With a extra list, if there is one static mapped area, we just check only one area and proceed next operation quickly. In fact, it is not a critical problem, because ioremap is not frequently used. But reducing overhead is better idea. Another reason for doing this work is for removing architecture dependency on vmalloc layer. I think that vmlist and vmlist_lock is internal data structure for vmalloc layer. Some codes for debugging and stat inevitably use vmlist and vmlist_lock. But it is preferable that they are used as least as possible in outside of vmalloc.c Now, I introduce an ARM-specific infrastructure for static mapped area. In the following patch, we will use this and resolve above mentioned problem. Reviewed-by: Nicolas Pitre Tested-by: Santosh Shilimkar Signed-off-by: Joonsoo Kim Signed-off-by: Russell King --- arch/arm/mm/ioremap.c | 64 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) (limited to 'arch/arm/mm/ioremap.c') diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 88fd86cf3d9a..904c15e86063 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -39,6 +39,70 @@ #include #include "mm.h" + +LIST_HEAD(static_vmlist); + +static struct static_vm *find_static_vm_paddr(phys_addr_t paddr, + size_t size, unsigned int mtype) +{ + struct static_vm *svm; + struct vm_struct *vm; + + list_for_each_entry(svm, &static_vmlist, list) { + vm = &svm->vm; + if (!(vm->flags & VM_ARM_STATIC_MAPPING)) + continue; + if ((vm->flags & VM_ARM_MTYPE_MASK) != VM_ARM_MTYPE(mtype)) + continue; + + if (vm->phys_addr > paddr || + paddr + size - 1 > vm->phys_addr + vm->size - 1) + continue; + + return svm; + } + + return NULL; +} + +struct static_vm *find_static_vm_vaddr(void *vaddr) +{ + struct static_vm *svm; + struct vm_struct *vm; + + list_for_each_entry(svm, &static_vmlist, list) { + vm = &svm->vm; + + /* static_vmlist is ascending order */ + if (vm->addr > vaddr) + break; + + if (vm->addr <= vaddr && vm->addr + vm->size > vaddr) + return svm; + } + + return NULL; +} + +void __init add_static_vm_early(struct static_vm *svm) +{ + struct static_vm *curr_svm; + struct vm_struct *vm; + void *vaddr; + + vm = &svm->vm; + vm_area_add_early(vm); + vaddr = vm->addr; + + list_for_each_entry(curr_svm, &static_vmlist, list) { + vm = &curr_svm->vm; + + if (vm->addr > vaddr) + break; + } + list_add_tail(&svm->list, &curr_svm->list); +} + int ioremap_page(unsigned long virt, unsigned long phys, const struct mem_type *mtype) { -- cgit v1.2.3 From 101eeda38c0ab8a4f916176e325d9e036d981a24 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Sat, 9 Feb 2013 06:28:06 +0100 Subject: ARM: 7646/1: mm: use static_vm for managing static mapped areas 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. Reviewed-by: Nicolas Pitre Acked-by: Rob Herring Tested-by: Santosh Shilimkar Signed-off-by: Joonsoo Kim Signed-off-by: Russell King --- arch/arm/mm/ioremap.c | 71 +++++++++++++++++++++------------------------------ arch/arm/mm/mmu.c | 34 ++++++++++++------------ 2 files changed, 46 insertions(+), 59 deletions(-) (limited to 'arch/arm/mm/ioremap.c') diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 904c15e86063..04d9006eab1f 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -261,13 +261,14 @@ 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 @@ -283,24 +284,16 @@ 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, 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+ @@ -312,21 +305,21 @@ 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) { @@ -410,34 +403,28 @@ __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; + + /* If this is a static mapping, we must leave it alone */ + 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) + { + struct vm_struct *vm; + + vm = find_vm_area(addr); + /* * 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)) { + 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/mmu.c b/arch/arm/mm/mmu.c index 9f0610243bd6..a35b314d270d 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->caller = iotable_init; - vm_area_add_early(vm++); + add_static_vm_early(svm++); } } @@ -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->caller = caller; - vm_area_add_early(vm); + add_static_vm_early(svm); } #ifndef CONFIG_ARM_LPAE @@ -810,14 +816,13 @@ 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; + list_for_each_entry(svm, &static_vmlist, list) { + vm = &svm->vm; addr = (unsigned long)vm->addr; if (addr < next) continue; @@ -859,17 +864,12 @@ 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 -- cgit v1.2.3