#include <linux/nodemask.h>
#include <linux/memblock.h>
#include <linux/fs.h>
+#include <linux/vmalloc.h>
+#include <asm/cp15.h>
#include <asm/cputype.h>
#include <asm/sections.h>
#include <asm/cachetype.h>
#include <asm/smp_plat.h>
#include <asm/tlb.h>
#include <asm/highmem.h>
+#include <asm/system_info.h>
+#include <asm/traps.h>
#include <asm/mach/arch.h>
#include <asm/mach/map.h>
#include "mm.h"
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
/*
* empty_zero_page is a special page that is used for
* zero-initialized data and COW.
struct cachepolicy {
const char policy[16];
unsigned int cr_mask;
- unsigned int pmd;
+ pmdval_t pmd;
pteval_t pte;
};
}
early_param("nowb", early_nowrite);
+#ifndef CONFIG_ARM_LPAE
static int __init early_ecc(char *p)
{
if (memcmp(p, "on", 2) == 0)
return 0;
}
early_param("ecc", early_ecc);
+#endif
static int __init noalign_setup(char *__unused)
{
.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN,
.domain = DOMAIN_KERNEL,
},
+#ifndef CONFIG_ARM_LPAE
[MT_MINICLEAN] = {
.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN | PMD_SECT_MINICACHE,
.domain = DOMAIN_KERNEL,
},
+#endif
[MT_LOW_VECTORS] = {
.prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
L_PTE_RDONLY,
.prot_l1 = PMD_TYPE_TABLE,
.domain = DOMAIN_KERNEL,
},
+ [MT_MEMORY_SO] = {
+ .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+ L_PTE_MT_UNCACHED,
+ .prot_l1 = PMD_TYPE_TABLE,
+ .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_S |
+ PMD_SECT_UNCACHED | PMD_SECT_XN,
+ .domain = DOMAIN_KERNEL,
+ },
};
const struct mem_type *get_mem_type(unsigned int type)
{
struct cachepolicy *cp;
unsigned int cr = get_cr();
- unsigned int user_pgprot, kern_pgprot, vecs_pgprot;
+ pteval_t user_pgprot, kern_pgprot, vecs_pgprot;
int cpu_arch = cpu_architecture();
int i;
* ARMv6 and above have extended page tables.
*/
if (cpu_arch >= CPU_ARCH_ARMv6 && (cr & CR_XP)) {
+#ifndef CONFIG_ARM_LPAE
/*
* Mark cache clean areas and XIP ROM read only
* from SVC mode and no access from userspace.
mem_types[MT_ROM].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
mem_types[MT_MINICLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE;
+#endif
if (is_smp()) {
/*
mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE;
}
+#ifdef CONFIG_ARM_LPAE
+ /*
+ * Do not generate access flag faults for the kernel mappings.
+ */
+ for (i = 0; i < ARRAY_SIZE(mem_types); i++) {
+ mem_types[i].prot_pte |= PTE_EXT_AF;
+ if (mem_types[i].prot_sect)
+ mem_types[i].prot_sect |= PMD_SECT_AF;
+ }
+ kern_pgprot |= PTE_EXT_AF;
+ vecs_pgprot |= PTE_EXT_AF;
+#endif
+
for (i = 0; i < 16; i++) {
unsigned long v = pgprot_val(protection_map[i]);
protection_map[i] = __pgprot(v | user_pgprot);
#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)) {
- pte_t *pte = early_alloc(2 * PTRS_PER_PTE * sizeof(pte_t));
+ pte_t *pte = early_alloc(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE);
__pmd_populate(pmd, __pa(pte), prot);
}
BUG_ON(pmd_bad(*pmd));
} while (pte++, addr += PAGE_SIZE, addr != end);
}
-static void __init alloc_init_section(pgd_t *pgd, unsigned long addr,
+static void __init alloc_init_section(pud_t *pud, unsigned long addr,
unsigned long end, phys_addr_t phys,
const struct mem_type *type)
{
- pmd_t *pmd = pmd_offset(pgd, addr);
+ pmd_t *pmd = pmd_offset(pud, addr);
/*
* Try a section mapping - end, addr and phys must all be aligned
if (((addr | end | phys) & ~SECTION_MASK) == 0) {
pmd_t *p = pmd;
+#ifndef CONFIG_ARM_LPAE
if (addr & SECTION_SIZE)
pmd++;
+#endif
do {
*pmd = __pmd(phys | type->prot_sect);
}
}
+static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
+ unsigned long end, unsigned long phys, const struct mem_type *type)
+{
+ pud_t *pud = pud_offset(pgd, addr);
+ unsigned long next;
+
+ do {
+ next = pud_addr_end(addr, end);
+ alloc_init_section(pud, addr, next, phys, type);
+ phys += next - addr;
+ } while (pud++, addr = next, addr != end);
+}
+
+#ifndef CONFIG_ARM_LPAE
static void __init create_36bit_mapping(struct map_desc *md,
const struct mem_type *type)
{
pgd_t *pgd;
addr = md->virtual;
- phys = (unsigned long)__pfn_to_phys(md->pfn);
+ phys = __pfn_to_phys(md->pfn);
length = PAGE_ALIGN(md->length);
if (!(cpu_architecture() >= CPU_ARCH_ARMv6 || cpu_is_xsc3())) {
printk(KERN_ERR "MM: CPU does not support supersection "
"mapping for 0x%08llx at 0x%08lx\n",
- __pfn_to_phys((u64)md->pfn), addr);
+ (long long)__pfn_to_phys((u64)md->pfn), addr);
return;
}
if (type->domain) {
printk(KERN_ERR "MM: invalid domain in supersection "
"mapping for 0x%08llx at 0x%08lx\n",
- __pfn_to_phys((u64)md->pfn), addr);
+ (long long)__pfn_to_phys((u64)md->pfn), addr);
return;
}
if ((addr | length | __pfn_to_phys(md->pfn)) & ~SUPERSECTION_MASK) {
- printk(KERN_ERR "MM: cannot create mapping for "
- "0x%08llx at 0x%08lx invalid alignment\n",
- __pfn_to_phys((u64)md->pfn), addr);
+ printk(KERN_ERR "MM: cannot create mapping for 0x%08llx"
+ " at 0x%08lx invalid alignment\n",
+ (long long)__pfn_to_phys((u64)md->pfn), addr);
return;
}
pgd = pgd_offset_k(addr);
end = addr + length;
do {
- pmd_t *pmd = pmd_offset(pgd, addr);
+ pud_t *pud = pud_offset(pgd, addr);
+ pmd_t *pmd = pmd_offset(pud, addr);
int i;
for (i = 0; i < 16; i++)
pgd += SUPERSECTION_SIZE >> PGDIR_SHIFT;
} while (addr != end);
}
+#endif /* !CONFIG_ARM_LPAE */
/*
* Create the page directory entries and any necessary
*/
static void __init create_mapping(struct map_desc *md)
{
- unsigned long phys, addr, length, end;
+ unsigned long addr, length, end;
+ phys_addr_t phys;
const struct mem_type *type;
pgd_t *pgd;
if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) {
- printk(KERN_WARNING "BUG: not creating mapping for "
- "0x%08llx at 0x%08lx in user region\n",
- __pfn_to_phys((u64)md->pfn), md->virtual);
+ printk(KERN_WARNING "BUG: not creating mapping for 0x%08llx"
+ " at 0x%08lx in user region\n",
+ (long long)__pfn_to_phys((u64)md->pfn), md->virtual);
return;
}
if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
- md->virtual >= PAGE_OFFSET && md->virtual < VMALLOC_END) {
- printk(KERN_WARNING "BUG: mapping for 0x%08llx at 0x%08lx "
- "overlaps vmalloc space\n",
- __pfn_to_phys((u64)md->pfn), md->virtual);
+ md->virtual >= PAGE_OFFSET &&
+ (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) {
+ printk(KERN_WARNING "BUG: mapping for 0x%08llx"
+ " at 0x%08lx out of vmalloc space\n",
+ (long long)__pfn_to_phys((u64)md->pfn), md->virtual);
}
type = &mem_types[md->type];
+#ifndef CONFIG_ARM_LPAE
/*
* Catch 36-bit addresses
*/
create_36bit_mapping(md, type);
return;
}
+#endif
addr = md->virtual & PAGE_MASK;
- phys = (unsigned long)__pfn_to_phys(md->pfn);
+ phys = __pfn_to_phys(md->pfn);
length = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK));
if (type->prot_l1 == 0 && ((addr | phys | length) & ~SECTION_MASK)) {
- printk(KERN_WARNING "BUG: map for 0x%08lx at 0x%08lx can not "
+ printk(KERN_WARNING "BUG: map for 0x%08llx at 0x%08lx can not "
"be mapped using pages, ignoring.\n",
- __pfn_to_phys(md->pfn), addr);
+ (long long)__pfn_to_phys(md->pfn), addr);
return;
}
do {
unsigned long next = pgd_addr_end(addr, end);
- alloc_init_section(pgd, addr, next, phys, type);
+ alloc_init_pud(pgd, addr, next, phys, type);
phys += next - addr;
addr = next;
*/
void __init iotable_init(struct map_desc *io_desc, int nr)
{
- int i;
+ struct map_desc *md;
+ struct vm_struct *vm;
- for (i = 0; i < nr; i++)
- create_mapping(io_desc + i);
+ if (!nr)
+ return;
+
+ 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)
{
static phys_addr_t lowmem_limit __initdata = 0;
-static void __init sanity_check_meminfo(void)
+void __init sanity_check_meminfo(void)
{
int i, j, highmem = 0;
- lowmem_limit = __pa(vmalloc_min - 1) + 1;
- memblock_set_current_limit(lowmem_limit);
-
for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
struct membank *bank = &meminfo.bank[j];
*bank = meminfo.bank[i];
+ if (bank->start > ULONG_MAX)
+ highmem = 1;
+
#ifdef CONFIG_HIGHMEM
- if (__va(bank->start) > vmalloc_min ||
+ if (__va(bank->start) >= vmalloc_min ||
__va(bank->start) < (void *)PAGE_OFFSET)
highmem = 1;
* Split those memory banks which are partially overlapping
* the vmalloc area greatly simplifying things later.
*/
- if (__va(bank->start) < vmalloc_min &&
+ if (!highmem && __va(bank->start) < vmalloc_min &&
bank->size > vmalloc_min - __va(bank->start)) {
if (meminfo.nr_banks >= NR_BANKS) {
printk(KERN_CRIT "NR_BANKS too low, "
bank->highmem = highmem;
/*
+ * Highmem banks not allowed with !CONFIG_HIGHMEM.
+ */
+ if (highmem) {
+ printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx "
+ "(!CONFIG_HIGHMEM).\n",
+ (unsigned long long)bank->start,
+ (unsigned long long)bank->start + bank->size - 1);
+ continue;
+ }
+
+ /*
* Check whether this memory bank would entirely overlap
* the vmalloc area.
*/
if (__va(bank->start) >= vmalloc_min ||
__va(bank->start) < (void *)PAGE_OFFSET) {
- printk(KERN_NOTICE "Ignoring RAM at %.8lx-%.8lx "
+ printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx "
"(vmalloc region overlap).\n",
- bank->start, bank->start + bank->size - 1);
+ (unsigned long long)bank->start,
+ (unsigned long long)bank->start + bank->size - 1);
continue;
}
if (__va(bank->start + bank->size) > vmalloc_min ||
__va(bank->start + bank->size) < __va(bank->start)) {
unsigned long newsize = vmalloc_min - __va(bank->start);
- printk(KERN_NOTICE "Truncating RAM at %.8lx-%.8lx "
- "to -%.8lx (vmalloc region overlap).\n",
- bank->start, bank->start + bank->size - 1,
- bank->start + newsize - 1);
+ printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx "
+ "to -%.8llx (vmalloc region overlap).\n",
+ (unsigned long long)bank->start,
+ (unsigned long long)bank->start + bank->size - 1,
+ (unsigned long long)bank->start + newsize - 1);
bank->size = newsize;
}
#endif
+ if (!bank->highmem && bank->start + bank->size > lowmem_limit)
+ lowmem_limit = bank->start + bank->size;
+
j++;
}
#ifdef CONFIG_HIGHMEM
* rather difficult.
*/
reason = "with VIPT aliasing cache";
- } else if (is_smp() && tlb_ops_need_broadcast()) {
- /*
- * kmap_high needs to occasionally flush TLB entries,
- * however, if the TLB entries need to be broadcast
- * we may deadlock:
- * kmap_high(irqs off)->flush_all_zero_pkmaps->
- * flush_tlb_kernel_range->smp_call_function_many
- * (must not be called with irqs off)
- */
- reason = "without hardware TLB ops broadcasting";
}
if (reason) {
printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n",
}
#endif
meminfo.nr_banks = j;
+ high_memory = __va(lowmem_limit - 1) + 1;
+ memblock_set_current_limit(lowmem_limit);
}
static inline void prepare_page_table(void)
/*
* Clear out all the mappings below the kernel image.
*/
- for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE)
+ for (addr = 0; addr < MODULES_VADDR; addr += PMD_SIZE)
pmd_clear(pmd_off_k(addr));
#ifdef CONFIG_XIP_KERNEL
/* The XIP kernel is mapped in the module area -- skip over it */
- addr = ((unsigned long)_etext + PGDIR_SIZE - 1) & PGDIR_MASK;
+ addr = ((unsigned long)_etext + PMD_SIZE - 1) & PMD_MASK;
#endif
- for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE)
+ for ( ; addr < PAGE_OFFSET; addr += PMD_SIZE)
pmd_clear(pmd_off_k(addr));
/*
/*
* 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 += PGDIR_SIZE)
+ addr < VMALLOC_START; addr += PMD_SIZE)
pmd_clear(pmd_off_k(addr));
}
+#ifdef CONFIG_ARM_LPAE
+/* the first page is reserved for pgd */
+#define SWAPPER_PG_DIR_SIZE (PAGE_SIZE + \
+ PTRS_PER_PGD * PTRS_PER_PMD * sizeof(pmd_t))
+#else
+#define SWAPPER_PG_DIR_SIZE (PTRS_PER_PGD * sizeof(pgd_t))
+#endif
+
/*
* Reserve the special regions of memory
*/
* Reserve the page tables. These are already in use,
* and can only be in node 0.
*/
- memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t));
+ memblock_reserve(__pa(swapper_pg_dir), SWAPPER_PG_DIR_SIZE);
#ifdef CONFIG_SA1111
/*
}
/*
- * 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.
*/
vectors = early_alloc(PAGE_SIZE);
- for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
+ early_trap_init(vectors);
+
+ for (addr = VMALLOC_START; addr; addr += PMD_SIZE)
pmd_clear(pmd_off_k(addr));
/*
{
void *zero_page;
+ memblock_set_current_limit(lowmem_limit);
+
build_mem_type_table();
- sanity_check_meminfo();
prepare_page_table();
map_lowmem();
devicemaps_init(mdesc);