diff options
Diffstat (limited to 'arch/arm/mm/mmu.c')
| -rw-r--r-- | arch/arm/mm/mmu.c | 663 |
1 files changed, 454 insertions, 209 deletions
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index ce328c7f5c9..6e3ba8d112a 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -22,18 +22,23 @@ #include <asm/cputype.h> #include <asm/sections.h> #include <asm/cachetype.h> +#include <asm/sections.h> #include <asm/setup.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/procinfo.h> +#include <asm/memory.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> #include <asm/mach/pci.h> +#include <asm/fixmap.h> #include "mm.h" +#include "tcm.h" /* * empty_zero_page is a special page that is used for @@ -57,6 +62,9 @@ static unsigned int cachepolicy __initdata = CPOLICY_WRITEBACK; static unsigned int ecc_mask __initdata = 0; pgprot_t pgprot_user; pgprot_t pgprot_kernel; +pgprot_t pgprot_hyp_device; +pgprot_t pgprot_s2; +pgprot_t pgprot_s2_device; EXPORT_SYMBOL(pgprot_user); EXPORT_SYMBOL(pgprot_kernel); @@ -66,59 +74,98 @@ struct cachepolicy { unsigned int cr_mask; pmdval_t pmd; pteval_t pte; + pteval_t pte_s2; }; +#ifdef CONFIG_ARM_LPAE +#define s2_policy(policy) policy +#else +#define s2_policy(policy) 0 +#endif + static struct cachepolicy cache_policies[] __initdata = { { .policy = "uncached", .cr_mask = CR_W|CR_C, .pmd = PMD_SECT_UNCACHED, .pte = L_PTE_MT_UNCACHED, + .pte_s2 = s2_policy(L_PTE_S2_MT_UNCACHED), }, { .policy = "buffered", .cr_mask = CR_C, .pmd = PMD_SECT_BUFFERED, .pte = L_PTE_MT_BUFFERABLE, + .pte_s2 = s2_policy(L_PTE_S2_MT_UNCACHED), }, { .policy = "writethrough", .cr_mask = 0, .pmd = PMD_SECT_WT, .pte = L_PTE_MT_WRITETHROUGH, + .pte_s2 = s2_policy(L_PTE_S2_MT_WRITETHROUGH), }, { .policy = "writeback", .cr_mask = 0, .pmd = PMD_SECT_WB, .pte = L_PTE_MT_WRITEBACK, + .pte_s2 = s2_policy(L_PTE_S2_MT_WRITEBACK), }, { .policy = "writealloc", .cr_mask = 0, .pmd = PMD_SECT_WBWA, .pte = L_PTE_MT_WRITEALLOC, + .pte_s2 = s2_policy(L_PTE_S2_MT_WRITEBACK), } }; +#ifdef CONFIG_CPU_CP15 +static unsigned long initial_pmd_value __initdata = 0; + /* - * These are useful for identifying cache coherency - * problems by allowing the cache or the cache and - * writebuffer to be turned off. (Note: the write - * buffer should not be on and the cache off). + * Initialise the cache_policy variable with the initial state specified + * via the "pmd" value. This is used to ensure that on ARMv6 and later, + * the C code sets the page tables up with the same policy as the head + * assembly code, which avoids an illegal state where the TLBs can get + * confused. See comments in early_cachepolicy() for more information. */ -static int __init early_cachepolicy(char *p) +void __init init_default_cache_policy(unsigned long pmd) { int i; + initial_pmd_value = pmd; + + pmd &= PMD_SECT_TEX(1) | PMD_SECT_BUFFERABLE | PMD_SECT_CACHEABLE; + + for (i = 0; i < ARRAY_SIZE(cache_policies); i++) + if (cache_policies[i].pmd == pmd) { + cachepolicy = i; + break; + } + + if (i == ARRAY_SIZE(cache_policies)) + pr_err("ERROR: could not find cache policy\n"); +} + +/* + * These are useful for identifying cache coherency problems by allowing + * the cache or the cache and writebuffer to be turned off. (Note: the + * write buffer should not be on and the cache off). + */ +static int __init early_cachepolicy(char *p) +{ + int i, selected = -1; + for (i = 0; i < ARRAY_SIZE(cache_policies); i++) { int len = strlen(cache_policies[i].policy); if (memcmp(p, cache_policies[i].policy, len) == 0) { - cachepolicy = i; - cr_alignment &= ~cache_policies[i].cr_mask; - cr_no_alignment &= ~cache_policies[i].cr_mask; + selected = i; break; } } - if (i == ARRAY_SIZE(cache_policies)) - printk(KERN_ERR "ERROR: unknown or unsupported cache policy\n"); + + if (selected == -1) + pr_err("ERROR: unknown or unsupported cache policy\n"); + /* * This restriction is partly to do with the way we boot; it is * unpredictable to have memory mapped using two different sets of @@ -126,12 +173,18 @@ static int __init early_cachepolicy(char *p) * change these attributes once the initial assembly has setup the * page tables. */ - if (cpu_architecture() >= CPU_ARCH_ARMv6) { - printk(KERN_WARNING "Only cachepolicy=writeback supported on ARMv6 and later\n"); - cachepolicy = CPOLICY_WRITEBACK; + if (cpu_architecture() >= CPU_ARCH_ARMv6 && selected != cachepolicy) { + pr_warn("Only cachepolicy=%s supported on ARMv6 and later\n", + cache_policies[cachepolicy].policy); + return 0; + } + + if (selected != cachepolicy) { + unsigned long cr = __clear_cr(cache_policies[selected].cr_mask); + cachepolicy = selected; + flush_cache_all(); + set_cr(cr); } - flush_cache_all(); - set_cr(cr_alignment); return 0; } early_param("cachepolicy", early_cachepolicy); @@ -166,42 +219,33 @@ static int __init early_ecc(char *p) early_param("ecc", early_ecc); #endif -static int __init noalign_setup(char *__unused) +#else /* ifdef CONFIG_CPU_CP15 */ + +static int __init early_cachepolicy(char *p) { - cr_alignment &= ~CR_A; - cr_no_alignment &= ~CR_A; - set_cr(cr_alignment); - return 1; + pr_warning("cachepolicy kernel parameter not supported without cp15\n"); } -__setup("noalign", noalign_setup); +early_param("cachepolicy", early_cachepolicy); -#ifndef CONFIG_SMP -void adjust_cr(unsigned long mask, unsigned long set) +static int __init noalign_setup(char *__unused) { - unsigned long flags; - - mask &= ~CR_A; - - set &= mask; - - local_irq_save(flags); - - cr_no_alignment = (cr_no_alignment & ~mask) | set; - cr_alignment = (cr_alignment & ~mask) | set; - - set_cr((get_cr() & ~mask) | set); - - local_irq_restore(flags); + pr_warning("noalign kernel parameter not supported without cp15\n"); } -#endif +__setup("noalign", noalign_setup); + +#endif /* ifdef CONFIG_CPU_CP15 / else */ #define PROT_PTE_DEVICE L_PTE_PRESENT|L_PTE_YOUNG|L_PTE_DIRTY|L_PTE_XN +#define PROT_PTE_S2_DEVICE PROT_PTE_DEVICE #define PROT_SECT_DEVICE PMD_TYPE_SECT|PMD_SECT_AP_WRITE static struct mem_type mem_types[] = { [MT_DEVICE] = { /* Strongly ordered / ARMv6 shared device */ .prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED | L_PTE_SHARED, + .prot_pte_s2 = s2_policy(PROT_PTE_S2_DEVICE) | + s2_policy(L_PTE_S2_MT_DEV_SHARED) | + L_PTE_SHARED, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PROT_SECT_DEVICE | PMD_SECT_S, .domain = DOMAIN_IO, @@ -252,36 +296,43 @@ static struct mem_type mem_types[] = { .prot_l1 = PMD_TYPE_TABLE, .domain = DOMAIN_USER, }, - [MT_MEMORY] = { + [MT_MEMORY_RWX] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, .domain = DOMAIN_KERNEL, }, + [MT_MEMORY_RW] = { + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_XN, + .prot_l1 = PMD_TYPE_TABLE, + .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, + .domain = DOMAIN_KERNEL, + }, [MT_ROM] = { .prot_sect = PMD_TYPE_SECT, .domain = DOMAIN_KERNEL, }, - [MT_MEMORY_NONCACHED] = { + [MT_MEMORY_RWX_NONCACHED] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_MT_BUFFERABLE, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE, .domain = DOMAIN_KERNEL, }, - [MT_MEMORY_DTCM] = { + [MT_MEMORY_RW_DTCM] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_XN, .prot_l1 = PMD_TYPE_TABLE, .prot_sect = PMD_TYPE_SECT | PMD_SECT_XN, .domain = DOMAIN_KERNEL, }, - [MT_MEMORY_ITCM] = { + [MT_MEMORY_RWX_ITCM] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY, .prot_l1 = PMD_TYPE_TABLE, .domain = DOMAIN_KERNEL, }, - [MT_MEMORY_SO] = { + [MT_MEMORY_RW_SO] = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_MT_UNCACHED | L_PTE_XN, .prot_l1 = PMD_TYPE_TABLE, @@ -290,7 +341,8 @@ static struct mem_type mem_types[] = { .domain = DOMAIN_KERNEL, }, [MT_MEMORY_DMA_READY] = { - .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY, + .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | + L_PTE_XN, .prot_l1 = PMD_TYPE_TABLE, .domain = DOMAIN_KERNEL, }, @@ -302,6 +354,44 @@ const struct mem_type *get_mem_type(unsigned int type) } EXPORT_SYMBOL(get_mem_type); +#define PTE_SET_FN(_name, pteop) \ +static int pte_set_##_name(pte_t *ptep, pgtable_t token, unsigned long addr, \ + void *data) \ +{ \ + pte_t pte = pteop(*ptep); \ +\ + set_pte_ext(ptep, pte, 0); \ + return 0; \ +} \ + +#define SET_MEMORY_FN(_name, callback) \ +int set_memory_##_name(unsigned long addr, int numpages) \ +{ \ + unsigned long start = addr; \ + unsigned long size = PAGE_SIZE*numpages; \ + unsigned end = start + size; \ +\ + if (start < MODULES_VADDR || start >= MODULES_END) \ + return -EINVAL;\ +\ + if (end < MODULES_VADDR || end >= MODULES_END) \ + return -EINVAL; \ +\ + apply_to_page_range(&init_mm, start, size, callback, NULL); \ + flush_tlb_kernel_range(start, end); \ + return 0;\ +} + +PTE_SET_FN(ro, pte_wrprotect) +PTE_SET_FN(rw, pte_mkwrite) +PTE_SET_FN(x, pte_mkexec) +PTE_SET_FN(nx, pte_mknexec) + +SET_MEMORY_FN(ro, pte_set_ro) +SET_MEMORY_FN(rw, pte_set_rw) +SET_MEMORY_FN(x, pte_set_x) +SET_MEMORY_FN(nx, pte_set_nx) + /* * Adjust the PMD section entries according to the CPU in use. */ @@ -310,6 +400,7 @@ static void __init build_mem_type_table(void) struct cachepolicy *cp; unsigned int cr = get_cr(); pteval_t user_pgprot, kern_pgprot, vecs_pgprot; + pteval_t hyp_device_pgprot, s2_pgprot, s2_device_pgprot; int cpu_arch = cpu_architecture(); int i; @@ -327,8 +418,17 @@ static void __init build_mem_type_table(void) cachepolicy = CPOLICY_WRITEBACK; ecc_mask = 0; } - if (is_smp()) - cachepolicy = CPOLICY_WRITEALLOC; + + if (is_smp()) { + if (cachepolicy != CPOLICY_WRITEALLOC) { + pr_warn("Forcing write-allocate cache policy for SMP\n"); + cachepolicy = CPOLICY_WRITEALLOC; + } + if (!(initial_pmd_value & PMD_SECT_S)) { + pr_warn("Forcing shared mappings for SMP\n"); + initial_pmd_value |= PMD_SECT_S; + } + } /* * Strip out features not present on earlier architectures. @@ -374,6 +474,9 @@ static void __init build_mem_type_table(void) mem_types[MT_DEVICE_NONSHARED].prot_sect |= PMD_SECT_XN; mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_XN; mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_XN; + + /* Also setup NX memory mapping */ + mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_XN; } if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) { /* @@ -421,6 +524,19 @@ static void __init build_mem_type_table(void) */ cp = &cache_policies[cachepolicy]; vecs_pgprot = kern_pgprot = user_pgprot = cp->pte; + s2_pgprot = cp->pte_s2; + hyp_device_pgprot = mem_types[MT_DEVICE].prot_pte; + s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2; + + /* + * We don't use domains on ARMv6 (since this causes problems with + * v6/v7 kernels), so we must use a separate memory type for user + * r/o, kernel r/w to map the vectors page. + */ +#ifndef CONFIG_ARM_LPAE + if (cpu_arch == CPU_ARCH_ARMv6) + vecs_pgprot |= L_PTE_MT_VECTORS; +#endif /* * ARMv6 and above have extended page tables. @@ -436,23 +552,27 @@ static void __init build_mem_type_table(void) mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_APX|PMD_SECT_AP_WRITE; #endif - if (is_smp()) { - /* - * Mark memory with the "shared" attribute - * for SMP systems - */ + /* + * If the initial page tables were created with the S bit + * set, then we need to do the same here for the same + * reasons given in early_cachepolicy(). + */ + if (initial_pmd_value & PMD_SECT_S) { user_pgprot |= L_PTE_SHARED; kern_pgprot |= L_PTE_SHARED; vecs_pgprot |= L_PTE_SHARED; + s2_pgprot |= L_PTE_SHARED; mem_types[MT_DEVICE_WC].prot_sect |= PMD_SECT_S; mem_types[MT_DEVICE_WC].prot_pte |= L_PTE_SHARED; mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S; mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED; - mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S; - mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_RWX].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_RWX].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_RW].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_RW].prot_pte |= L_PTE_SHARED; mem_types[MT_MEMORY_DMA_READY].prot_pte |= L_PTE_SHARED; - mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S; - mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED; + mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_S; + mem_types[MT_MEMORY_RWX_NONCACHED].prot_pte |= L_PTE_SHARED; } } @@ -463,15 +583,15 @@ static void __init build_mem_type_table(void) if (cpu_arch >= CPU_ARCH_ARMv6) { if (cpu_arch >= CPU_ARCH_ARMv7 && (cr & CR_TRE)) { /* Non-cacheable Normal is XCB = 001 */ - mem_types[MT_MEMORY_NONCACHED].prot_sect |= + mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_BUFFERED; } else { /* For both ARMv6 and non-TEX-remapping ARMv7 */ - mem_types[MT_MEMORY_NONCACHED].prot_sect |= + mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_TEX(1); } } else { - mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE; + mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= PMD_SECT_BUFFERABLE; } #ifdef CONFIG_ARM_LPAE @@ -498,13 +618,18 @@ static void __init build_mem_type_table(void) pgprot_user = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | user_pgprot); pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | kern_pgprot); + pgprot_s2 = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | s2_pgprot); + pgprot_s2_device = __pgprot(s2_device_pgprot); + pgprot_hyp_device = __pgprot(hyp_device_pgprot); mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask; mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask; - mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd; - mem_types[MT_MEMORY].prot_pte |= kern_pgprot; + mem_types[MT_MEMORY_RWX].prot_sect |= ecc_mask | cp->pmd; + mem_types[MT_MEMORY_RWX].prot_pte |= kern_pgprot; + mem_types[MT_MEMORY_RW].prot_sect |= ecc_mask | cp->pmd; + mem_types[MT_MEMORY_RW].prot_pte |= kern_pgprot; mem_types[MT_MEMORY_DMA_READY].prot_pte |= kern_pgprot; - mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask; + mem_types[MT_MEMORY_RWX_NONCACHED].prot_sect |= ecc_mask; mem_types[MT_ROM].prot_sect |= cp->pmd; switch (cp->pmd) { @@ -516,8 +641,8 @@ static void __init build_mem_type_table(void) mem_types[MT_CACHECLEAN].prot_sect |= PMD_SECT_WB; break; } - printk("Memory policy: ECC %sabled, Data cache %s\n", - ecc_mask ? "en" : "dis", cp->policy); + pr_info("Memory policy: %sData cache %s\n", + ecc_mask ? "ECC enabled, " : "", cp->policy); for (i = 0; i < ARRAY_SIZE(mem_types); i++) { struct mem_type *t = &mem_types[i]; @@ -576,50 +701,74 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr, } while (pte++, addr += PAGE_SIZE, addr != end); } -static void __init alloc_init_section(pud_t *pud, unsigned long addr, - unsigned long end, phys_addr_t phys, - const struct mem_type *type) +static void __init __map_init_section(pmd_t *pmd, unsigned long addr, + unsigned long end, phys_addr_t phys, + const struct mem_type *type) { - pmd_t *pmd = pmd_offset(pud, addr); + pmd_t *p = pmd; +#ifndef CONFIG_ARM_LPAE /* - * Try a section mapping - end, addr and phys must all be aligned - * to a section boundary. Note that PMDs refer to the individual - * L1 entries, whereas PGDs refer to a group of L1 entries making - * up one logical pointer to an L2 table. + * In classic MMU format, puds and pmds are folded in to + * the pgds. pmd_offset gives the PGD entry. PGDs refer to a + * group of L1 entries making up one logical pointer to + * an L2 table (2MB), where as PMDs refer to the individual + * L1 entries (1MB). Hence increment to get the correct + * offset for odd 1MB sections. + * (See arch/arm/include/asm/pgtable-2level.h) */ - if (type->prot_sect && ((addr | end | phys) & ~SECTION_MASK) == 0) { - pmd_t *p = pmd; - -#ifndef CONFIG_ARM_LPAE - if (addr & SECTION_SIZE) - pmd++; + if (addr & SECTION_SIZE) + pmd++; #endif + do { + *pmd = __pmd(phys | type->prot_sect); + phys += SECTION_SIZE; + } while (pmd++, addr += SECTION_SIZE, addr != end); - do { - *pmd = __pmd(phys | type->prot_sect); - phys += SECTION_SIZE; - } while (pmd++, addr += SECTION_SIZE, addr != end); + flush_pmd_entry(p); +} - flush_pmd_entry(p); - } else { +static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, + unsigned long end, phys_addr_t phys, + const struct mem_type *type) +{ + pmd_t *pmd = pmd_offset(pud, addr); + unsigned long next; + + do { /* - * No need to loop; pte's aren't interested in the - * individual L1 entries. + * With LPAE, we must loop over to map + * all the pmds for the given range. */ - alloc_init_pte(pmd, addr, end, __phys_to_pfn(phys), type); - } + next = pmd_addr_end(addr, end); + + /* + * Try a section mapping - addr, next and phys must all be + * aligned to a section boundary. + */ + if (type->prot_sect && + ((addr | next | phys) & ~SECTION_MASK) == 0) { + __map_init_section(pmd, addr, next, phys, type); + } else { + alloc_init_pte(pmd, addr, next, + __phys_to_pfn(phys), type); + } + + phys += next - addr; + + } while (pmd++, addr = next, addr != end); } static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr, - unsigned long end, unsigned long phys, const struct mem_type *type) + unsigned long end, phys_addr_t 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); + alloc_init_pmd(pud, addr, next, phys, type); phys += next - addr; } while (pud++, addr = next, addr != end); } @@ -757,21 +906,24 @@ 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 +931,16 @@ 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 +965,13 @@ 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; @@ -857,19 +1011,12 @@ static void __init fill_pmd_gaps(void) #if defined(CONFIG_PCI) && !defined(CONFIG_NEED_MACH_IO_H) 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 @@ -888,7 +1035,7 @@ void __init debug_ll_io_init(void) map.virtual &= PAGE_MASK; map.length = PAGE_SIZE; map.type = MT_DEVICE; - create_mapping(&map); + iotable_init(&map, 1); } #endif @@ -927,113 +1074,85 @@ phys_addr_t arm_lowmem_limit __initdata = 0; void __init sanity_check_meminfo(void) { - int i, j, highmem = 0; + phys_addr_t memblock_limit = 0; + int highmem = 0; + phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1; + struct memblock_region *reg; - for (i = 0, j = 0; i < meminfo.nr_banks; i++) { - struct membank *bank = &meminfo.bank[j]; - *bank = meminfo.bank[i]; + for_each_memblock(memory, reg) { + phys_addr_t block_start = reg->base; + phys_addr_t block_end = reg->base + reg->size; + phys_addr_t size_limit = reg->size; - if (bank->start > ULONG_MAX) + if (reg->base >= vmalloc_limit) highmem = 1; + else + size_limit = vmalloc_limit - reg->base; -#ifdef CONFIG_HIGHMEM - if (__va(bank->start) >= vmalloc_min || - __va(bank->start) < (void *)PAGE_OFFSET) - highmem = 1; - bank->highmem = highmem; + if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) { - /* - * Split those memory banks which are partially overlapping - * the vmalloc area greatly simplifying things later. - */ - 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, " - "ignoring high memory\n"); - } else { - memmove(bank + 1, bank, - (meminfo.nr_banks - i) * sizeof(*bank)); - meminfo.nr_banks++; - i++; - bank[1].size -= vmalloc_min - __va(bank->start); - bank[1].start = __pa(vmalloc_min - 1) + 1; - bank[1].highmem = highmem = 1; - j++; + if (highmem) { + pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n", + &block_start, &block_end); + memblock_remove(reg->base, reg->size); + continue; } - bank->size = vmalloc_min - __va(bank->start); - } -#else - 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 %.8llx-%.8llx " - "(vmalloc region overlap).\n", - (unsigned long long)bank->start, - (unsigned long long)bank->start + bank->size - 1); - continue; - } + if (reg->size > size_limit) { + phys_addr_t overlap_size = reg->size - size_limit; - /* - * Check whether this memory bank would partially overlap - * the vmalloc area. - */ - if (__va(bank->start + bank->size - 1) >= vmalloc_min || - __va(bank->start + bank->size - 1) <= __va(bank->start)) { - unsigned long newsize = vmalloc_min - __va(bank->start); - 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; + pr_notice("Truncating RAM at %pa-%pa to -%pa", + &block_start, &block_end, &vmalloc_limit); + memblock_remove(vmalloc_limit, overlap_size); + block_end = vmalloc_limit; + } } -#endif - if (!bank->highmem && bank->start + bank->size > arm_lowmem_limit) - arm_lowmem_limit = bank->start + bank->size; - j++; - } -#ifdef CONFIG_HIGHMEM - if (highmem) { - const char *reason = NULL; + if (!highmem) { + if (block_end > arm_lowmem_limit) { + if (reg->size > size_limit) + arm_lowmem_limit = vmalloc_limit; + else + arm_lowmem_limit = block_end; + } - if (cache_is_vipt_aliasing()) { /* - * Interactions between kmap and other mappings - * make highmem support with aliasing VIPT caches - * rather difficult. + * Find the first non-section-aligned page, and point + * memblock_limit at it. This relies on rounding the + * limit down to be section-aligned, which happens at + * the end of this function. + * + * With this algorithm, the start or end of almost any + * bank can be non-section-aligned. The only exception + * is that the start of the bank 0 must be section- + * aligned, since otherwise memory would need to be + * allocated when mapping the start of bank 0, which + * occurs before any free memory is mapped. */ - reason = "with VIPT aliasing cache"; - } - if (reason) { - printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n", - reason); - while (j > 0 && meminfo.bank[j - 1].highmem) - j--; + if (!memblock_limit) { + if (!IS_ALIGNED(block_start, SECTION_SIZE)) + memblock_limit = block_start; + else if (!IS_ALIGNED(block_end, SECTION_SIZE)) + memblock_limit = arm_lowmem_limit; + } + } } -#endif - meminfo.nr_banks = j; + high_memory = __va(arm_lowmem_limit - 1) + 1; - memblock_set_current_limit(arm_lowmem_limit); + + /* + * Round the memblock limit down to a section size. This + * helps to ensure that we will allocate memory from the + * last full section, which should be mapped. + */ + if (memblock_limit) + memblock_limit = round_down(memblock_limit, SECTION_SIZE); + if (!memblock_limit) + memblock_limit = arm_lowmem_limit; + + memblock_set_current_limit(memblock_limit); } static inline void prepare_page_table(void) @@ -1105,7 +1224,7 @@ void __init arm_mm_memblock_reserve(void) * called function. This means you can't use any function or debugging * method which may touch any device, otherwise the kernel _will_ crash. */ -static void __init devicemaps_init(struct machine_desc *mdesc) +static void __init devicemaps_init(const struct machine_desc *mdesc) { struct map_desc map; unsigned long addr; @@ -1114,7 +1233,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc) /* * Allocate the vector page early. */ - vectors = early_alloc(PAGE_SIZE); + vectors = early_alloc(PAGE_SIZE * 2); early_trap_init(vectors); @@ -1159,20 +1278,34 @@ static void __init devicemaps_init(struct machine_desc *mdesc) map.pfn = __phys_to_pfn(virt_to_phys(vectors)); map.virtual = 0xffff0000; map.length = PAGE_SIZE; +#ifdef CONFIG_KUSER_HELPERS map.type = MT_HIGH_VECTORS; +#else + map.type = MT_LOW_VECTORS; +#endif create_mapping(&map); if (!vectors_high()) { map.virtual = 0; + map.length = PAGE_SIZE * 2; map.type = MT_LOW_VECTORS; create_mapping(&map); } + /* Now create a kernel read-only mapping */ + map.pfn += 1; + map.virtual = 0xffff0000 + PAGE_SIZE; + map.length = PAGE_SIZE; + map.type = MT_LOW_VECTORS; + create_mapping(&map); + /* * Ask the machine support to map in the statically mapped devices. */ if (mdesc->map_io) mdesc->map_io(); + else + debug_ll_io_init(); fill_pmd_gaps(); /* Reserve fixed i/o space in VMALLOC region */ @@ -1193,12 +1326,17 @@ static void __init kmap_init(void) #ifdef CONFIG_HIGHMEM pkmap_page_table = early_pte_alloc(pmd_off_k(PKMAP_BASE), PKMAP_BASE, _PAGE_KERNEL_TABLE); + + fixmap_page_table = early_pte_alloc(pmd_off_k(FIXADDR_START), + FIXADDR_START, _PAGE_KERNEL_TABLE); #endif } static void __init map_lowmem(void) { struct memblock_region *reg; + unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE); + unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE); /* Map all the lowmem memory banks. */ for_each_memblock(memory, reg) { @@ -1211,31 +1349,138 @@ static void __init map_lowmem(void) if (start >= end) break; - map.pfn = __phys_to_pfn(start); - map.virtual = __phys_to_virt(start); - map.length = end - start; - map.type = MT_MEMORY; + if (end < kernel_x_start || start >= kernel_x_end) { + map.pfn = __phys_to_pfn(start); + map.virtual = __phys_to_virt(start); + map.length = end - start; + map.type = MT_MEMORY_RWX; - create_mapping(&map); + create_mapping(&map); + } else { + /* This better cover the entire kernel */ + if (start < kernel_x_start) { + map.pfn = __phys_to_pfn(start); + map.virtual = __phys_to_virt(start); + map.length = kernel_x_start - start; + map.type = MT_MEMORY_RW; + + create_mapping(&map); + } + + map.pfn = __phys_to_pfn(kernel_x_start); + map.virtual = __phys_to_virt(kernel_x_start); + map.length = kernel_x_end - kernel_x_start; + map.type = MT_MEMORY_RWX; + + create_mapping(&map); + + if (kernel_x_end < end) { + map.pfn = __phys_to_pfn(kernel_x_end); + map.virtual = __phys_to_virt(kernel_x_end); + map.length = end - kernel_x_end; + map.type = MT_MEMORY_RW; + + create_mapping(&map); + } + } + } +} + +#ifdef CONFIG_ARM_LPAE +/* + * early_paging_init() recreates boot time page table setup, allowing machines + * to switch over to a high (>4G) address space on LPAE systems + */ +void __init early_paging_init(const struct machine_desc *mdesc, + struct proc_info_list *procinfo) +{ + pmdval_t pmdprot = procinfo->__cpu_mm_mmu_flags; + unsigned long map_start, map_end; + pgd_t *pgd0, *pgdk; + pud_t *pud0, *pudk, *pud_start; + pmd_t *pmd0, *pmdk; + phys_addr_t phys; + int i; + + if (!(mdesc->init_meminfo)) + return; + + /* remap kernel code and data */ + map_start = init_mm.start_code & PMD_MASK; + map_end = ALIGN(init_mm.brk, PMD_SIZE); + + /* get a handle on things... */ + pgd0 = pgd_offset_k(0); + pud_start = pud0 = pud_offset(pgd0, 0); + pmd0 = pmd_offset(pud0, 0); + + pgdk = pgd_offset_k(map_start); + pudk = pud_offset(pgdk, map_start); + pmdk = pmd_offset(pudk, map_start); + + mdesc->init_meminfo(); + + /* Run the patch stub to update the constants */ + fixup_pv_table(&__pv_table_begin, + (&__pv_table_end - &__pv_table_begin) << 2); + + /* + * Cache cleaning operations for self-modifying code + * We should clean the entries by MVA but running a + * for loop over every pv_table entry pointer would + * just complicate the code. + */ + flush_cache_louis(); + dsb(ishst); + isb(); + + /* remap level 1 table */ + for (i = 0; i < PTRS_PER_PGD; pud0++, i++) { + set_pud(pud0, + __pud(__pa(pmd0) | PMD_TYPE_TABLE | L_PGD_SWAPPER)); + pmd0 += PTRS_PER_PMD; } + + /* remap pmds for kernel mapping */ + phys = __pa(map_start); + do { + *pmdk++ = __pmd(phys | pmdprot); + phys += PMD_SIZE; + } while (phys < map_end); + + flush_cache_all(); + cpu_switch_mm(pgd0, &init_mm); + cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET); + local_flush_bp_all(); + local_flush_tlb_all(); } +#else + +void __init early_paging_init(const struct machine_desc *mdesc, + struct proc_info_list *procinfo) +{ + if (mdesc->init_meminfo) + mdesc->init_meminfo(); +} + +#endif + /* * paging_init() sets up the page tables, initialises the zone memory * maps, and sets up the zero page, bad page and bad page tables. */ -void __init paging_init(struct machine_desc *mdesc) +void __init paging_init(const struct machine_desc *mdesc) { void *zero_page; - memblock_set_current_limit(arm_lowmem_limit); - build_mem_type_table(); prepare_page_table(); map_lowmem(); dma_contiguous_remap(); devicemaps_init(mdesc); kmap_init(); + tcm_init(); top_pmd = pmd_off_k(0xffff0000); |