* Copyright (C) 1997-1999 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
*/
-#include <linux/config.h>
+#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/string.h>
#include <linux/initrd.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
+#include <linux/poison.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/kprobes.h>
#include <linux/cache.h>
#include <linux/sort.h>
+#include <linux/percpu.h>
#include <asm/head.h>
#include <asm/system.h>
#include <asm/sections.h>
#include <asm/tsb.h>
#include <asm/hypervisor.h>
+#include <asm/prom.h>
+#include <asm/sstate.h>
+#include <asm/mdesc.h>
-extern void device_scan(void);
+#define MAX_PHYS_ADDRESS (1UL << 42UL)
+#define KPTE_BITMAP_CHUNK_SZ (256UL * 1024UL * 1024UL)
+#define KPTE_BITMAP_BYTES \
+ ((MAX_PHYS_ADDRESS / KPTE_BITMAP_CHUNK_SZ) / 8)
+
+unsigned long kern_linear_pte_xor[2] __read_mostly;
+
+/* A bitmap, one bit for every 256MB of physical memory. If the bit
+ * is clear, we should use a 4MB page (via kern_linear_pte_xor[0]) else
+ * if set we should use a 256MB page (via kern_linear_pte_xor[1]).
+ */
+unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];
+
+#ifndef CONFIG_DEBUG_PAGEALLOC
+/* A special kernel TSB for 4MB and 256MB linear mappings.
+ * Space is allocated for this right after the trap table
+ * in arch/sparc64/kernel/head.S
+ */
+extern struct tsb swapper_4m_tsb[KERNEL_TSB4M_NENTRIES];
+#endif
#define MAX_BANKS 32
prom_halt();
}
- *num_ents = ents;
-
/* Sanitize what we got from the firmware, by page aligning
* everything.
*/
size = 0UL;
base = new_base;
}
+ if (size == 0UL) {
+ /* If it is empty, simply get rid of it.
+ * This simplifies the logic of the other
+ * functions that process these arrays.
+ */
+ memmove(®s[i], ®s[i + 1],
+ (ents - i - 1) * sizeof(regs[0]));
+ i--;
+ ents--;
+ continue;
+ }
regs[i].phys_addr = base;
regs[i].reg_size = size;
}
+
+ *num_ents = ents;
+
sort(regs, ents, sizeof(struct linux_prom64_registers),
cmp_p64, NULL);
}
unsigned long *sparc64_valid_addr_bitmap __read_mostly;
-/* Ugly, but necessary... -DaveM */
-unsigned long phys_base __read_mostly;
+/* Kernel physical address base and size in bytes. */
unsigned long kern_base __read_mostly;
unsigned long kern_size __read_mostly;
-unsigned long pfn_base __read_mostly;
-
-/* get_new_mmu_context() uses "cache + 1". */
-DEFINE_SPINLOCK(ctx_alloc_lock);
-unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
-#define CTX_BMAP_SLOTS (1UL << (CTX_NR_BITS - 6))
-unsigned long mmu_context_bmap[CTX_BMAP_SLOTS];
-
-/* References to special section boundaries */
-extern char _start[], _end[];
/* Initial ramdisk setup */
extern unsigned long sparc_ramdisk_image64;
int bigkernel = 0;
-kmem_cache_t *pgtable_cache __read_mostly;
-
-static void zero_ctor(void *addr, kmem_cache_t *cache, unsigned long flags)
-{
- clear_page(addr);
-}
-
-void pgtable_cache_init(void)
-{
- pgtable_cache = kmem_cache_create("pgtable_cache",
- PAGE_SIZE, PAGE_SIZE,
- SLAB_HWCACHE_ALIGN |
- SLAB_MUST_HWCACHE_ALIGN,
- zero_ctor,
- NULL);
- if (!pgtable_cache) {
- prom_printf("pgtable_cache_init(): Could not create!\n");
- prom_halt();
- }
-}
-
#ifdef CONFIG_DEBUG_DCFLUSH
atomic_t dcpage_flushes = ATOMIC_INIT(0);
#ifdef CONFIG_SMP
#endif
#endif
-__inline__ void flush_dcache_page_impl(struct page *page)
+inline void flush_dcache_page_impl(struct page *page)
{
+ BUG_ON(tlb_type == hypervisor);
#ifdef CONFIG_DEBUG_DCFLUSH
atomic_inc(&dcpage_flushes);
#endif
}
#define PG_dcache_dirty PG_arch_1
-#define PG_dcache_cpu_shift 24
-#define PG_dcache_cpu_mask (256 - 1)
-
-#if NR_CPUS > 256
-#error D-cache dirty tracking and thread_info->cpu need fixing for > 256 cpus
-#endif
+#define PG_dcache_cpu_shift 32UL
+#define PG_dcache_cpu_mask \
+ ((1UL<<ilog2(roundup_pow_of_two(NR_CPUS)))-1UL)
#define dcache_dirty_cpu(page) \
(((page)->flags >> PG_dcache_cpu_shift) & PG_dcache_cpu_mask)
{
unsigned long tsb_addr = (unsigned long) ent;
- if (tlb_type == cheetah_plus)
+ if (tlb_type == cheetah_plus || tlb_type == hypervisor)
tsb_addr = __pa(tsb_addr);
__tsb_insert(tsb_addr, tag, pte);
}
+unsigned long _PAGE_ALL_SZ_BITS __read_mostly;
+unsigned long _PAGE_SZBITS __read_mostly;
+
void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t pte)
{
struct mm_struct *mm;
- struct page *page;
- unsigned long pfn;
- unsigned long pg_flags;
-
- pfn = pte_pfn(pte);
- if (pfn_valid(pfn) &&
- (page = pfn_to_page(pfn), page_mapping(page)) &&
- ((pg_flags = page->flags) & (1UL << PG_dcache_dirty))) {
- int cpu = ((pg_flags >> PG_dcache_cpu_shift) &
- PG_dcache_cpu_mask);
- int this_cpu = get_cpu();
-
- /* This is just to optimize away some function calls
- * in the SMP case.
- */
- if (cpu == this_cpu)
- flush_dcache_page_impl(page);
- else
- smp_flush_dcache_page_impl(page, cpu);
+ struct tsb *tsb;
+ unsigned long tag, flags;
+ unsigned long tsb_index, tsb_hash_shift;
+
+ if (tlb_type != hypervisor) {
+ unsigned long pfn = pte_pfn(pte);
+ unsigned long pg_flags;
+ struct page *page;
+
+ if (pfn_valid(pfn) &&
+ (page = pfn_to_page(pfn), page_mapping(page)) &&
+ ((pg_flags = page->flags) & (1UL << PG_dcache_dirty))) {
+ int cpu = ((pg_flags >> PG_dcache_cpu_shift) &
+ PG_dcache_cpu_mask);
+ int this_cpu = get_cpu();
+
+ /* This is just to optimize away some function calls
+ * in the SMP case.
+ */
+ if (cpu == this_cpu)
+ flush_dcache_page_impl(page);
+ else
+ smp_flush_dcache_page_impl(page, cpu);
- clear_dcache_dirty_cpu(page, cpu);
+ clear_dcache_dirty_cpu(page, cpu);
- put_cpu();
+ put_cpu();
+ }
}
mm = vma->vm_mm;
- if ((pte_val(pte) & _PAGE_ALL_SZ_BITS) == _PAGE_SZBITS) {
- struct tsb *tsb;
- unsigned long tag;
-
- tsb = &mm->context.tsb[(address >> PAGE_SHIFT) &
- (mm->context.tsb_nentries - 1UL)];
- tag = (address >> 22UL) | CTX_HWBITS(mm->context) << 48UL;
- tsb_insert(tsb, tag, pte_val(pte));
+
+ tsb_index = MM_TSB_BASE;
+ tsb_hash_shift = PAGE_SHIFT;
+
+ spin_lock_irqsave(&mm->context.lock, flags);
+
+#ifdef CONFIG_HUGETLB_PAGE
+ if (mm->context.tsb_block[MM_TSB_HUGE].tsb != NULL) {
+ if ((tlb_type == hypervisor &&
+ (pte_val(pte) & _PAGE_SZALL_4V) == _PAGE_SZHUGE_4V) ||
+ (tlb_type != hypervisor &&
+ (pte_val(pte) & _PAGE_SZALL_4U) == _PAGE_SZHUGE_4U)) {
+ tsb_index = MM_TSB_HUGE;
+ tsb_hash_shift = HPAGE_SHIFT;
+ }
}
+#endif
+
+ tsb = mm->context.tsb_block[tsb_index].tsb;
+ tsb += ((address >> tsb_hash_shift) &
+ (mm->context.tsb_block[tsb_index].tsb_nentries - 1UL));
+ tag = (address >> 22UL);
+ tsb_insert(tsb, tag, pte_val(pte));
+
+ spin_unlock_irqrestore(&mm->context.lock, flags);
}
void flush_dcache_page(struct page *page)
struct address_space *mapping;
int this_cpu;
+ if (tlb_type == hypervisor)
+ return;
+
/* Do not bother with the expensive D-cache flush if it
* is merely the zero page. The 'bigcore' testcase in GDB
* causes this case to run millions of times.
if (tlb_type == spitfire) {
unsigned long kaddr;
- for (kaddr = start; kaddr < end; kaddr += PAGE_SIZE)
- __flush_icache_page(__get_phys(kaddr));
+ /* This code only runs on Spitfire cpus so this is
+ * why we can assume _PAGE_PADDR_4U.
+ */
+ for (kaddr = start; kaddr < end; kaddr += PAGE_SIZE) {
+ unsigned long paddr, mask = _PAGE_PADDR_4U;
+
+ if (kaddr >= PAGE_OFFSET)
+ paddr = kaddr & mask;
+ else {
+ pgd_t *pgdp = pgd_offset_k(kaddr);
+ pud_t *pudp = pud_offset(pgdp, kaddr);
+ pmd_t *pmdp = pmd_offset(pudp, kaddr);
+ pte_t *ptep = pte_offset_kernel(pmdp, kaddr);
+
+ paddr = pte_val(*ptep) & mask;
+ }
+ __flush_icache_page(paddr);
+ }
}
}
-unsigned long page_to_pfn(struct page *page)
-{
- return (unsigned long) ((page - mem_map) + pfn_base);
-}
-
-struct page *pfn_to_page(unsigned long pfn)
-{
- return (mem_map + (pfn - pfn_base));
-}
-
void show_mem(void)
{
- printk("Mem-info:\n");
+ unsigned long total = 0, reserved = 0;
+ unsigned long shared = 0, cached = 0;
+ pg_data_t *pgdat;
+
+ printk(KERN_INFO "Mem-info:\n");
show_free_areas();
- printk("Free swap: %6ldkB\n",
+ printk(KERN_INFO "Free swap: %6ldkB\n",
nr_swap_pages << (PAGE_SHIFT-10));
- printk("%ld pages of RAM\n", num_physpages);
- printk("%d free pages\n", nr_free_pages());
+ for_each_online_pgdat(pgdat) {
+ unsigned long i, flags;
+
+ pgdat_resize_lock(pgdat, &flags);
+ for (i = 0; i < pgdat->node_spanned_pages; i++) {
+ struct page *page = pgdat_page_nr(pgdat, i);
+ total++;
+ if (PageReserved(page))
+ reserved++;
+ else if (PageSwapCache(page))
+ cached++;
+ else if (page_count(page))
+ shared += page_count(page) - 1;
+ }
+ pgdat_resize_unlock(pgdat, &flags);
+ }
+
+ printk(KERN_INFO "%lu pages of RAM\n", total);
+ printk(KERN_INFO "%lu reserved pages\n", reserved);
+ printk(KERN_INFO "%lu pages shared\n", shared);
+ printk(KERN_INFO "%lu pages swap cached\n", cached);
+
+ printk(KERN_INFO "%lu pages dirty\n",
+ global_page_state(NR_FILE_DIRTY));
+ printk(KERN_INFO "%lu pages writeback\n",
+ global_page_state(NR_WRITEBACK));
+ printk(KERN_INFO "%lu pages mapped\n",
+ global_page_state(NR_FILE_MAPPED));
+ printk(KERN_INFO "%lu pages slab\n",
+ global_page_state(NR_SLAB_RECLAIMABLE) +
+ global_page_state(NR_SLAB_UNRECLAIMABLE));
+ printk(KERN_INFO "%lu pages pagetables\n",
+ global_page_state(NR_PAGETABLE));
}
void mmu_info(struct seq_file *m)
struct linux_prom_translation prom_trans[512] __read_mostly;
unsigned int prom_trans_ents __read_mostly;
-extern unsigned long prom_boot_page;
-extern void prom_remap(unsigned long physpage, unsigned long virtpage, int mmu_ihandle);
-extern int prom_get_mmu_ihandle(void);
-extern void register_prom_callbacks(void);
-
/* Exported for SMP bootup purposes. */
unsigned long kern_locked_tte_data;
-/*
- * Translate PROM's mapping we capture at boot time into physical address.
- * The second parameter is only set from prom_callback() invocations.
- */
-unsigned long prom_virt_to_phys(unsigned long promva, int *error)
-{
- int i;
-
- for (i = 0; i < prom_trans_ents; i++) {
- struct linux_prom_translation *p = &prom_trans[i];
-
- if (promva >= p->virt &&
- promva < (p->virt + p->size)) {
- unsigned long base = p->data & _PAGE_PADDR;
-
- if (error)
- *error = 0;
- return base + (promva & (8192 - 1));
- }
- }
- if (error)
- *error = 1;
- return 0UL;
-}
-
/* The obp translations are saved based on 8k pagesize, since obp can
* use a mixture of pagesizes. Misses to the LOW_OBP_ADDRESS ->
* HI_OBP_ADDRESS range are handled in ktlb.S.
unsigned long pte,
unsigned long mmu)
{
- register unsigned long func asm("%o5");
- register unsigned long arg0 asm("%o0");
- register unsigned long arg1 asm("%o1");
- register unsigned long arg2 asm("%o2");
- register unsigned long arg3 asm("%o3");
-
- func = HV_FAST_MMU_MAP_PERM_ADDR;
- arg0 = vaddr;
- arg1 = 0;
- arg2 = pte;
- arg3 = mmu;
- __asm__ __volatile__("ta 0x80"
- : "=&r" (func), "=&r" (arg0),
- "=&r" (arg1), "=&r" (arg2),
- "=&r" (arg3)
- : "0" (func), "1" (arg0), "2" (arg1),
- "3" (arg2), "4" (arg3));
+ unsigned long ret = sun4v_mmu_map_perm_addr(vaddr, 0, pte, mmu);
+
+ if (ret != 0) {
+ prom_printf("hypervisor_tlb_lock[%lx:%lx:%lx:%lx]: "
+ "errors with %lx\n", vaddr, 0, pte, mmu, ret);
+ prom_halt();
+ }
}
+static unsigned long kern_large_tte(unsigned long paddr);
+
static void __init remap_kernel(void)
{
unsigned long phys_page, tte_vaddr, tte_data;
tte_vaddr = (unsigned long) KERNBASE;
phys_page = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
- tte_data = (phys_page | (_PAGE_VALID | _PAGE_SZ4MB |
- _PAGE_CP | _PAGE_CV | _PAGE_P |
- _PAGE_L | _PAGE_W));
+ tte_data = kern_large_tte(phys_page);
kern_locked_tte_data = tte_data;
prom_printf("Remapping the kernel... ");
remap_kernel();
prom_printf("done.\n");
-
- prom_printf("Registering callbacks... ");
- register_prom_callbacks();
- prom_printf("done.\n");
}
void prom_world(int enter)
}
#endif /* DCACHE_ALIASING_POSSIBLE */
-/* If not locked, zap it. */
-void __flush_tlb_all(void)
-{
- unsigned long pstate;
- int i;
-
- __asm__ __volatile__("flushw\n\t"
- "rdpr %%pstate, %0\n\t"
- "wrpr %0, %1, %%pstate"
- : "=r" (pstate)
- : "i" (PSTATE_IE));
- if (tlb_type == spitfire) {
- for (i = 0; i < 64; i++) {
- /* Spitfire Errata #32 workaround */
- /* NOTE: Always runs on spitfire, so no
- * cheetah+ page size encodings.
- */
- __asm__ __volatile__("stxa %0, [%1] %2\n\t"
- "flush %%g6"
- : /* No outputs */
- : "r" (0),
- "r" (PRIMARY_CONTEXT), "i" (ASI_DMMU));
-
- if (!(spitfire_get_dtlb_data(i) & _PAGE_L)) {
- __asm__ __volatile__("stxa %%g0, [%0] %1\n\t"
- "membar #Sync"
- : /* no outputs */
- : "r" (TLB_TAG_ACCESS), "i" (ASI_DMMU));
- spitfire_put_dtlb_data(i, 0x0UL);
- }
-
- /* Spitfire Errata #32 workaround */
- /* NOTE: Always runs on spitfire, so no
- * cheetah+ page size encodings.
- */
- __asm__ __volatile__("stxa %0, [%1] %2\n\t"
- "flush %%g6"
- : /* No outputs */
- : "r" (0),
- "r" (PRIMARY_CONTEXT), "i" (ASI_DMMU));
-
- if (!(spitfire_get_itlb_data(i) & _PAGE_L)) {
- __asm__ __volatile__("stxa %%g0, [%0] %1\n\t"
- "membar #Sync"
- : /* no outputs */
- : "r" (TLB_TAG_ACCESS), "i" (ASI_IMMU));
- spitfire_put_itlb_data(i, 0x0UL);
- }
- }
- } else if (tlb_type == cheetah || tlb_type == cheetah_plus) {
- cheetah_flush_dtlb_all();
- cheetah_flush_itlb_all();
- }
- __asm__ __volatile__("wrpr %0, 0, %%pstate"
- : : "r" (pstate));
-}
+/* get_new_mmu_context() uses "cache + 1". */
+DEFINE_SPINLOCK(ctx_alloc_lock);
+unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
+#define MAX_CTX_NR (1UL << CTX_NR_BITS)
+#define CTX_BMAP_SLOTS BITS_TO_LONGS(MAX_CTX_NR)
+DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR);
/* Caller does TLB context flushing on local CPU if necessary.
* The caller also ensures that CTX_VALID(mm->context) is false.
* let the user have CTX 0 (nucleus) or we ever use a CTX
* version of zero (and thus NO_CONTEXT would not be caught
* by version mis-match tests in mmu_context.h).
+ *
+ * Always invoked with interrupts disabled.
*/
void get_new_mmu_context(struct mm_struct *mm)
{
unsigned long ctx, new_ctx;
unsigned long orig_pgsz_bits;
-
+ unsigned long flags;
+ int new_version;
- spin_lock(&ctx_alloc_lock);
+ spin_lock_irqsave(&ctx_alloc_lock, flags);
orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
+ new_version = 0;
if (new_ctx >= (1 << CTX_NR_BITS)) {
new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1);
if (new_ctx >= ctx) {
mmu_context_bmap[i + 2] = 0;
mmu_context_bmap[i + 3] = 0;
}
+ new_version = 1;
goto out;
}
}
out:
tlb_context_cache = new_ctx;
mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
- spin_unlock(&ctx_alloc_lock);
+ spin_unlock_irqrestore(&ctx_alloc_lock, flags);
+
+ if (unlikely(new_version))
+ smp_new_mmu_context_version();
}
-void sparc_ultra_dump_itlb(void)
+/* Find a free area for the bootmem map, avoiding the kernel image
+ * and the initial ramdisk.
+ */
+static unsigned long __init choose_bootmap_pfn(unsigned long start_pfn,
+ unsigned long end_pfn)
{
- int slot;
+ unsigned long avoid_start, avoid_end, bootmap_size;
+ int i;
- if (tlb_type == spitfire) {
- printk ("Contents of itlb: ");
- for (slot = 0; slot < 14; slot++) printk (" ");
- printk ("%2x:%016lx,%016lx\n",
- 0,
- spitfire_get_itlb_tag(0), spitfire_get_itlb_data(0));
- for (slot = 1; slot < 64; slot+=3) {
- printk ("%2x:%016lx,%016lx %2x:%016lx,%016lx %2x:%016lx,%016lx\n",
- slot,
- spitfire_get_itlb_tag(slot), spitfire_get_itlb_data(slot),
- slot+1,
- spitfire_get_itlb_tag(slot+1), spitfire_get_itlb_data(slot+1),
- slot+2,
- spitfire_get_itlb_tag(slot+2), spitfire_get_itlb_data(slot+2));
- }
- } else if (tlb_type == cheetah || tlb_type == cheetah_plus) {
- printk ("Contents of itlb0:\n");
- for (slot = 0; slot < 16; slot+=2) {
- printk ("%2x:%016lx,%016lx %2x:%016lx,%016lx\n",
- slot,
- cheetah_get_litlb_tag(slot), cheetah_get_litlb_data(slot),
- slot+1,
- cheetah_get_litlb_tag(slot+1), cheetah_get_litlb_data(slot+1));
- }
- printk ("Contents of itlb2:\n");
- for (slot = 0; slot < 128; slot+=2) {
- printk ("%2x:%016lx,%016lx %2x:%016lx,%016lx\n",
- slot,
- cheetah_get_itlb_tag(slot), cheetah_get_itlb_data(slot),
- slot+1,
- cheetah_get_itlb_tag(slot+1), cheetah_get_itlb_data(slot+1));
+ bootmap_size = bootmem_bootmap_pages(end_pfn - start_pfn);
+ bootmap_size <<= PAGE_SHIFT;
+
+ avoid_start = avoid_end = 0;
+#ifdef CONFIG_BLK_DEV_INITRD
+ avoid_start = initrd_start;
+ avoid_end = PAGE_ALIGN(initrd_end);
+#endif
+
+#ifdef CONFIG_DEBUG_BOOTMEM
+ prom_printf("choose_bootmap_pfn: kern[%lx:%lx] avoid[%lx:%lx]\n",
+ kern_base, PAGE_ALIGN(kern_base + kern_size),
+ avoid_start, avoid_end);
+#endif
+ for (i = 0; i < pavail_ents; i++) {
+ unsigned long start, end;
+
+ start = pavail[i].phys_addr;
+ end = start + pavail[i].reg_size;
+
+ while (start < end) {
+ if (start >= kern_base &&
+ start < PAGE_ALIGN(kern_base + kern_size)) {
+ start = PAGE_ALIGN(kern_base + kern_size);
+ continue;
+ }
+ if (start >= avoid_start && start < avoid_end) {
+ start = avoid_end;
+ continue;
+ }
+
+ if ((end - start) < bootmap_size)
+ break;
+
+ if (start < kern_base &&
+ (start + bootmap_size) > kern_base) {
+ start = PAGE_ALIGN(kern_base + kern_size);
+ continue;
+ }
+
+ if (start < avoid_start &&
+ (start + bootmap_size) > avoid_start) {
+ start = avoid_end;
+ continue;
+ }
+
+ /* OK, it doesn't overlap anything, use it. */
+#ifdef CONFIG_DEBUG_BOOTMEM
+ prom_printf("choose_bootmap_pfn: Using %lx [%lx]\n",
+ start >> PAGE_SHIFT, start);
+#endif
+ return start >> PAGE_SHIFT;
}
}
+
+ prom_printf("Cannot find free area for bootmap, aborting.\n");
+ prom_halt();
}
-void sparc_ultra_dump_dtlb(void)
+static void __init trim_pavail(unsigned long *cur_size_p,
+ unsigned long *end_of_phys_p)
{
- int slot;
+ unsigned long to_trim = *cur_size_p - cmdline_memory_size;
+ unsigned long avoid_start, avoid_end;
+ int i;
- if (tlb_type == spitfire) {
- printk ("Contents of dtlb: ");
- for (slot = 0; slot < 14; slot++) printk (" ");
- printk ("%2x:%016lx,%016lx\n", 0,
- spitfire_get_dtlb_tag(0), spitfire_get_dtlb_data(0));
- for (slot = 1; slot < 64; slot+=3) {
- printk ("%2x:%016lx,%016lx %2x:%016lx,%016lx %2x:%016lx,%016lx\n",
- slot,
- spitfire_get_dtlb_tag(slot), spitfire_get_dtlb_data(slot),
- slot+1,
- spitfire_get_dtlb_tag(slot+1), spitfire_get_dtlb_data(slot+1),
- slot+2,
- spitfire_get_dtlb_tag(slot+2), spitfire_get_dtlb_data(slot+2));
+ to_trim = PAGE_ALIGN(to_trim);
+
+ avoid_start = avoid_end = 0;
+#ifdef CONFIG_BLK_DEV_INITRD
+ avoid_start = initrd_start;
+ avoid_end = PAGE_ALIGN(initrd_end);
+#endif
+
+ /* Trim some pavail[] entries in order to satisfy the
+ * requested "mem=xxx" kernel command line specification.
+ *
+ * We must not trim off the kernel image area nor the
+ * initial ramdisk range (if any). Also, we must not trim
+ * any pavail[] entry down to zero in order to preserve
+ * the invariant that all pavail[] entries have a non-zero
+ * size which is assumed by all of the code in here.
+ */
+ for (i = 0; i < pavail_ents; i++) {
+ unsigned long start, end, kern_end;
+ unsigned long trim_low, trim_high, n;
+
+ kern_end = PAGE_ALIGN(kern_base + kern_size);
+
+ trim_low = start = pavail[i].phys_addr;
+ trim_high = end = start + pavail[i].reg_size;
+
+ if (kern_base >= start &&
+ kern_base < end) {
+ trim_low = kern_base;
+ if (kern_end >= end)
+ continue;
}
- } else if (tlb_type == cheetah || tlb_type == cheetah_plus) {
- printk ("Contents of dtlb0:\n");
- for (slot = 0; slot < 16; slot+=2) {
- printk ("%2x:%016lx,%016lx %2x:%016lx,%016lx\n",
- slot,
- cheetah_get_ldtlb_tag(slot), cheetah_get_ldtlb_data(slot),
- slot+1,
- cheetah_get_ldtlb_tag(slot+1), cheetah_get_ldtlb_data(slot+1));
+ if (kern_end >= start &&
+ kern_end < end) {
+ trim_high = kern_end;
}
- printk ("Contents of dtlb2:\n");
- for (slot = 0; slot < 512; slot+=2) {
- printk ("%2x:%016lx,%016lx %2x:%016lx,%016lx\n",
- slot,
- cheetah_get_dtlb_tag(slot, 2), cheetah_get_dtlb_data(slot, 2),
- slot+1,
- cheetah_get_dtlb_tag(slot+1, 2), cheetah_get_dtlb_data(slot+1, 2));
+ if (avoid_start &&
+ avoid_start >= start &&
+ avoid_start < end) {
+ if (trim_low > avoid_start)
+ trim_low = avoid_start;
+ if (avoid_end >= end)
+ continue;
}
- if (tlb_type == cheetah_plus) {
- printk ("Contents of dtlb3:\n");
- for (slot = 0; slot < 512; slot+=2) {
- printk ("%2x:%016lx,%016lx %2x:%016lx,%016lx\n",
- slot,
- cheetah_get_dtlb_tag(slot, 3), cheetah_get_dtlb_data(slot, 3),
- slot+1,
- cheetah_get_dtlb_tag(slot+1, 3), cheetah_get_dtlb_data(slot+1, 3));
+ if (avoid_end &&
+ avoid_end >= start &&
+ avoid_end < end) {
+ if (trim_high < avoid_end)
+ trim_high = avoid_end;
+ }
+
+ if (trim_high <= trim_low)
+ continue;
+
+ if (trim_low == start && trim_high == end) {
+ /* Whole chunk is available for trimming.
+ * Trim all except one page, in order to keep
+ * entry non-empty.
+ */
+ n = (end - start) - PAGE_SIZE;
+ if (n > to_trim)
+ n = to_trim;
+
+ if (n) {
+ pavail[i].phys_addr += n;
+ pavail[i].reg_size -= n;
+ to_trim -= n;
+ }
+ } else {
+ n = (trim_low - start);
+ if (n > to_trim)
+ n = to_trim;
+
+ if (n) {
+ pavail[i].phys_addr += n;
+ pavail[i].reg_size -= n;
+ to_trim -= n;
+ }
+ if (to_trim) {
+ n = end - trim_high;
+ if (n > to_trim)
+ n = to_trim;
+ if (n) {
+ pavail[i].reg_size -= n;
+ to_trim -= n;
+ }
}
}
+
+ if (!to_trim)
+ break;
}
-}
-extern unsigned long cmdline_memory_size;
+ /* Recalculate. */
+ *cur_size_p = 0UL;
+ for (i = 0; i < pavail_ents; i++) {
+ *end_of_phys_p = pavail[i].phys_addr +
+ pavail[i].reg_size;
+ *cur_size_p += pavail[i].reg_size;
+ }
+}
-unsigned long __init bootmem_init(unsigned long *pages_avail)
+/* About pages_avail, this is the value we will use to calculate
+ * the zholes_size[] argument given to free_area_init_node(). The
+ * page allocator uses this to calculate nr_kernel_pages,
+ * nr_all_pages and zone->present_pages. On NUMA it is used
+ * to calculate zone->min_unmapped_pages and zone->min_slab_pages.
+ *
+ * So this number should really be set to what the page allocator
+ * actually ends up with. This means:
+ * 1) It should include bootmem map pages, we'll release those.
+ * 2) It should not include the kernel image, except for the
+ * __init sections which we will also release.
+ * 3) It should include the initrd image, since we'll release
+ * that too.
+ */
+static unsigned long __init bootmem_init(unsigned long *pages_avail,
+ unsigned long phys_base)
{
- unsigned long bootmap_size, start_pfn, end_pfn;
+ unsigned long bootmap_size, end_pfn;
unsigned long end_of_phys_memory = 0UL;
unsigned long bootmap_pfn, bytes_avail, size;
int i;
end_of_phys_memory = pavail[i].phys_addr +
pavail[i].reg_size;
bytes_avail += pavail[i].reg_size;
- if (cmdline_memory_size) {
- if (bytes_avail > cmdline_memory_size) {
- unsigned long slack = bytes_avail - cmdline_memory_size;
-
- bytes_avail -= slack;
- end_of_phys_memory -= slack;
-
- pavail[i].reg_size -= slack;
- if ((long)pavail[i].reg_size <= 0L) {
- pavail[i].phys_addr = 0xdeadbeefUL;
- pavail[i].reg_size = 0UL;
- pavail_ents = i;
- } else {
- pavail[i+1].reg_size = 0Ul;
- pavail[i+1].phys_addr = 0xdeadbeefUL;
- pavail_ents = i + 1;
- }
- break;
- }
- }
}
- *pages_avail = bytes_avail >> PAGE_SHIFT;
-
- /* Start with page aligned address of last symbol in kernel
- * image. The kernel is hard mapped below PAGE_OFFSET in a
- * 4MB locked TLB translation.
+ /* Determine the location of the initial ramdisk before trying
+ * to honor the "mem=xxx" command line argument. We must know
+ * where the kernel image and the ramdisk image are so that we
+ * do not trim those two areas from the physical memory map.
*/
- start_pfn = PAGE_ALIGN(kern_base + kern_size) >> PAGE_SHIFT;
-
- bootmap_pfn = start_pfn;
-
- end_pfn = end_of_phys_memory >> PAGE_SHIFT;
#ifdef CONFIG_BLK_DEV_INITRD
/* Now have to check initial ramdisk, so that bootmap does not overwrite it */
if (sparc_ramdisk_image || sparc_ramdisk_image64) {
unsigned long ramdisk_image = sparc_ramdisk_image ?
sparc_ramdisk_image : sparc_ramdisk_image64;
- if (ramdisk_image >= (unsigned long)_end - 2 * PAGE_SIZE)
- ramdisk_image -= KERNBASE;
+ ramdisk_image -= KERNBASE;
initrd_start = ramdisk_image + phys_base;
initrd_end = initrd_start + sparc_ramdisk_size;
if (initrd_end > end_of_phys_memory) {
"(0x%016lx > 0x%016lx)\ndisabling initrd\n",
initrd_end, end_of_phys_memory);
initrd_start = 0;
- }
- if (initrd_start) {
- if (initrd_start >= (start_pfn << PAGE_SHIFT) &&
- initrd_start < (start_pfn << PAGE_SHIFT) + 2 * PAGE_SIZE)
- bootmap_pfn = PAGE_ALIGN (initrd_end) >> PAGE_SHIFT;
+ initrd_end = 0;
}
}
#endif
+
+ if (cmdline_memory_size &&
+ bytes_avail > cmdline_memory_size)
+ trim_pavail(&bytes_avail,
+ &end_of_phys_memory);
+
+ *pages_avail = bytes_avail >> PAGE_SHIFT;
+
+ end_pfn = end_of_phys_memory >> PAGE_SHIFT;
+
/* Initialize the boot-time allocator. */
max_pfn = max_low_pfn = end_pfn;
- min_low_pfn = pfn_base;
+ min_low_pfn = (phys_base >> PAGE_SHIFT);
+
+ bootmap_pfn = choose_bootmap_pfn(min_low_pfn, end_pfn);
#ifdef CONFIG_DEBUG_BOOTMEM
prom_printf("init_bootmem(min[%lx], bootmap[%lx], max[%lx])\n",
min_low_pfn, bootmap_pfn, max_low_pfn);
#endif
- bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap_pfn, pfn_base, end_pfn);
+ bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap_pfn,
+ min_low_pfn, end_pfn);
/* Now register the available physical memory with the
* allocator.
if (initrd_start) {
size = initrd_end - initrd_start;
- /* Resert the initrd image area. */
+ /* Reserve the initrd image area. */
#ifdef CONFIG_DEBUG_BOOTMEM
prom_printf("reserve_bootmem(initrd): base[%llx] size[%lx]\n",
initrd_start, initrd_end);
#endif
reserve_bootmem(initrd_start, size);
- *pages_avail -= PAGE_ALIGN(size) >> PAGE_SHIFT;
initrd_start += PAGE_OFFSET;
initrd_end += PAGE_OFFSET;
reserve_bootmem(kern_base, kern_size);
*pages_avail -= PAGE_ALIGN(kern_size) >> PAGE_SHIFT;
+ /* Add back in the initmem pages. */
+ size = ((unsigned long)(__init_end) & PAGE_MASK) -
+ PAGE_ALIGN((unsigned long)__init_begin);
+ *pages_avail += size >> PAGE_SHIFT;
+
/* Reserve the bootmem map. We do not account for it
* in pages_avail because we will release that memory
* in free_all_bootmem.
(bootmap_pfn << PAGE_SHIFT), size);
#endif
reserve_bootmem((bootmap_pfn << PAGE_SHIFT), size);
- *pages_avail -= PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+ for (i = 0; i < pavail_ents; i++) {
+ unsigned long start_pfn, end_pfn;
+
+ start_pfn = pavail[i].phys_addr >> PAGE_SHIFT;
+ end_pfn = (start_pfn + (pavail[i].reg_size >> PAGE_SHIFT));
+#ifdef CONFIG_DEBUG_BOOTMEM
+ prom_printf("memory_present(0, %lx, %lx)\n",
+ start_pfn, end_pfn);
+#endif
+ memory_present(0, start_pfn, end_pfn);
+ }
+
+ sparse_init();
return end_pfn;
}
+static struct linux_prom64_registers pall[MAX_BANKS] __initdata;
+static int pall_ents __initdata;
+
#ifdef CONFIG_DEBUG_PAGEALLOC
static unsigned long kernel_map_range(unsigned long pstart, unsigned long pend, pgprot_t prot)
{
return alloc_bytes;
}
-static struct linux_prom64_registers pall[MAX_BANKS] __initdata;
-static int pall_ents __initdata;
-
extern unsigned int kvmap_linear_patch[1];
+#endif /* CONFIG_DEBUG_PAGEALLOC */
+
+static void __init mark_kpte_bitmap(unsigned long start, unsigned long end)
+{
+ const unsigned long shift_256MB = 28;
+ const unsigned long mask_256MB = ((1UL << shift_256MB) - 1UL);
+ const unsigned long size_256MB = (1UL << shift_256MB);
+
+ while (start < end) {
+ long remains;
+
+ remains = end - start;
+ if (remains < size_256MB)
+ break;
+
+ if (start & mask_256MB) {
+ start = (start + size_256MB) & ~mask_256MB;
+ continue;
+ }
+
+ while (remains >= size_256MB) {
+ unsigned long index = start >> shift_256MB;
+
+ __set_bit(index, kpte_linear_bitmap);
+
+ start += size_256MB;
+ remains -= size_256MB;
+ }
+ }
+}
static void __init kernel_physical_mapping_init(void)
{
- unsigned long i, mem_alloced = 0UL;
+ unsigned long i;
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ unsigned long mem_alloced = 0UL;
+#endif
read_obp_memory("reg", &pall[0], &pall_ents);
phys_start = pall[i].phys_addr;
phys_end = phys_start + pall[i].reg_size;
+
+ mark_kpte_bitmap(phys_start, phys_end);
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
mem_alloced += kernel_map_range(phys_start, phys_end,
PAGE_KERNEL);
+#endif
}
+#ifdef CONFIG_DEBUG_PAGEALLOC
printk("Allocated %ld bytes for kernel page tables.\n",
mem_alloced);
flushi(&kvmap_linear_patch[0]);
__flush_tlb_all();
+#endif
}
+#ifdef CONFIG_DEBUG_PAGEALLOC
void kernel_map_pages(struct page *page, int numpages, int enable)
{
unsigned long phys_start = page_to_pfn(page) << PAGE_SHIFT;
}
}
+/* Don't mark as init, we give this to the Hypervisor. */
+#ifndef CONFIG_DEBUG_PAGEALLOC
+#define NUM_KTSB_DESCR 2
+#else
+#define NUM_KTSB_DESCR 1
+#endif
+static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR];
+extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
+
+static void __init sun4v_ktsb_init(void)
+{
+ unsigned long ktsb_pa;
+
+ /* First KTSB for PAGE_SIZE mappings. */
+ ktsb_pa = kern_base + ((unsigned long)&swapper_tsb[0] - KERNBASE);
+
+ switch (PAGE_SIZE) {
+ case 8 * 1024:
+ default:
+ ktsb_descr[0].pgsz_idx = HV_PGSZ_IDX_8K;
+ ktsb_descr[0].pgsz_mask = HV_PGSZ_MASK_8K;
+ break;
+
+ case 64 * 1024:
+ ktsb_descr[0].pgsz_idx = HV_PGSZ_IDX_64K;
+ ktsb_descr[0].pgsz_mask = HV_PGSZ_MASK_64K;
+ break;
+
+ case 512 * 1024:
+ ktsb_descr[0].pgsz_idx = HV_PGSZ_IDX_512K;
+ ktsb_descr[0].pgsz_mask = HV_PGSZ_MASK_512K;
+ break;
+
+ case 4 * 1024 * 1024:
+ ktsb_descr[0].pgsz_idx = HV_PGSZ_IDX_4MB;
+ ktsb_descr[0].pgsz_mask = HV_PGSZ_MASK_4MB;
+ break;
+ };
+
+ ktsb_descr[0].assoc = 1;
+ ktsb_descr[0].num_ttes = KERNEL_TSB_NENTRIES;
+ ktsb_descr[0].ctx_idx = 0;
+ ktsb_descr[0].tsb_base = ktsb_pa;
+ ktsb_descr[0].resv = 0;
+
+#ifndef CONFIG_DEBUG_PAGEALLOC
+ /* Second KTSB for 4MB/256MB mappings. */
+ ktsb_pa = (kern_base +
+ ((unsigned long)&swapper_4m_tsb[0] - KERNBASE));
+
+ ktsb_descr[1].pgsz_idx = HV_PGSZ_IDX_4MB;
+ ktsb_descr[1].pgsz_mask = (HV_PGSZ_MASK_4MB |
+ HV_PGSZ_MASK_256MB);
+ ktsb_descr[1].assoc = 1;
+ ktsb_descr[1].num_ttes = KERNEL_TSB4M_NENTRIES;
+ ktsb_descr[1].ctx_idx = 0;
+ ktsb_descr[1].tsb_base = ktsb_pa;
+ ktsb_descr[1].resv = 0;
+#endif
+}
+
+void __cpuinit sun4v_ktsb_register(void)
+{
+ unsigned long pa, ret;
+
+ pa = kern_base + ((unsigned long)&ktsb_descr[0] - KERNBASE);
+
+ ret = sun4v_mmu_tsb_ctx0(NUM_KTSB_DESCR, pa);
+ if (ret != 0) {
+ prom_printf("hypervisor_mmu_tsb_ctx0[%lx]: "
+ "errors with %lx\n", pa, ret);
+ prom_halt();
+ }
+}
+
/* paging_init() sets up the page tables */
extern void cheetah_ecache_flush_init(void);
extern void sun4v_patch_tlb_handlers(void);
+extern void cpu_probe(void);
+extern void central_probe(void);
+
static unsigned long last_valid_pfn;
pgd_t swapper_pg_dir[2048];
+static void sun4u_pgprot_init(void);
+static void sun4v_pgprot_init(void);
+
void __init paging_init(void)
{
- unsigned long end_pfn, pages_avail, shift;
+ unsigned long end_pfn, pages_avail, shift, phys_base;
unsigned long real_end, i;
+ /* These build time checkes make sure that the dcache_dirty_cpu()
+ * page->flags usage will work.
+ *
+ * When a page gets marked as dcache-dirty, we store the
+ * cpu number starting at bit 32 in the page->flags. Also,
+ * functions like clear_dcache_dirty_cpu use the cpu mask
+ * in 13-bit signed-immediate instruction fields.
+ */
+ BUILD_BUG_ON(FLAGS_RESERVED != 32);
+ BUILD_BUG_ON(SECTIONS_WIDTH + NODES_WIDTH + ZONES_WIDTH +
+ ilog2(roundup_pow_of_two(NR_CPUS)) > FLAGS_RESERVED);
+ BUILD_BUG_ON(NR_CPUS > 4096);
+
kern_base = (prom_boot_mapping_phys_low >> 22UL) << 22UL;
kern_size = (unsigned long)&_end - (unsigned long)KERNBASE;
+ sstate_booting();
+
+ /* Invalidate both kernel TSBs. */
+ memset(swapper_tsb, 0x40, sizeof(swapper_tsb));
+#ifndef CONFIG_DEBUG_PAGEALLOC
+ memset(swapper_4m_tsb, 0x40, sizeof(swapper_4m_tsb));
+#endif
+
+ if (tlb_type == hypervisor)
+ sun4v_pgprot_init();
+ else
+ sun4u_pgprot_init();
+
if (tlb_type == cheetah_plus ||
tlb_type == hypervisor)
tsb_phys_patch();
- if (tlb_type == hypervisor)
+ if (tlb_type == hypervisor) {
sun4v_patch_tlb_handlers();
+ sun4v_ktsb_init();
+ }
/* Find available physical memory... */
read_obp_memory("available", &pavail[0], &pavail_ents);
for (i = 0; i < pavail_ents; i++)
phys_base = min(phys_base, pavail[i].phys_addr);
- pfn_base = phys_base >> PAGE_SHIFT;
-
set_bit(0, mmu_context_bmap);
shift = kern_base + PAGE_OFFSET - ((unsigned long)KERNBASE);
__flush_tlb_all();
+ if (tlb_type == hypervisor)
+ sun4v_ktsb_register();
+
/* Setup bootmem... */
pages_avail = 0;
- last_valid_pfn = end_pfn = bootmem_init(&pages_avail);
+ last_valid_pfn = end_pfn = bootmem_init(&pages_avail, phys_base);
+
+ max_mapnr = last_valid_pfn;
-#ifdef CONFIG_DEBUG_PAGEALLOC
kernel_physical_mapping_init();
-#endif
+
+ real_setup_per_cpu_areas();
+
+ prom_build_devicetree();
+
+ if (tlb_type == hypervisor)
+ sun4v_mdesc_init();
{
unsigned long zones_size[MAX_NR_ZONES];
unsigned long zholes_size[MAX_NR_ZONES];
- unsigned long npages;
int znum;
for (znum = 0; znum < MAX_NR_ZONES; znum++)
zones_size[znum] = zholes_size[znum] = 0;
- npages = end_pfn - pfn_base;
- zones_size[ZONE_DMA] = npages;
- zholes_size[ZONE_DMA] = npages - pages_avail;
+ zones_size[ZONE_NORMAL] = end_pfn;
+ zholes_size[ZONE_NORMAL] = end_pfn - pages_avail;
free_area_init_node(0, &contig_page_data, zones_size,
- phys_base >> PAGE_SHIFT, zholes_size);
+ __pa(PAGE_OFFSET) >> PAGE_SHIFT,
+ zholes_size);
}
- device_scan();
+ prom_printf("Booting Linux...\n");
+
+ central_probe();
+ cpu_probe();
}
static void __init taint_real_pages(void)
while (old_start < old_end) {
int n;
- for (n = 0; pavail_rescan_ents; n++) {
+ for (n = 0; n < pavail_rescan_ents; n++) {
unsigned long new_start, new_end;
new_start = pavail_rescan[n].phys_addr;
}
}
+int __init page_in_phys_avail(unsigned long paddr)
+{
+ int i;
+
+ paddr &= PAGE_MASK;
+
+ for (i = 0; i < pavail_rescan_ents; i++) {
+ unsigned long start, end;
+
+ start = pavail_rescan[i].phys_addr;
+ end = start + pavail_rescan[i].reg_size;
+
+ if (paddr >= start && paddr < end)
+ return 1;
+ }
+ if (paddr >= kern_base && paddr < (kern_base + kern_size))
+ return 1;
+#ifdef CONFIG_BLK_DEV_INITRD
+ if (paddr >= __pa(initrd_start) &&
+ paddr < __pa(PAGE_ALIGN(initrd_end)))
+ return 1;
+#endif
+
+ return 0;
+}
+
void __init mem_init(void)
{
unsigned long codepages, datapages, initpages;
taint_real_pages();
- max_mapnr = last_valid_pfn - pfn_base;
high_memory = __va(last_valid_pfn << PAGE_SHIFT);
#ifdef CONFIG_DEBUG_BOOTMEM
prom_printf("mem_init: Calling free_all_bootmem().\n");
#endif
+
+ /* We subtract one to account for the mem_map_zero page
+ * allocated below.
+ */
totalram_pages = num_physpages = free_all_bootmem() - 1;
/*
initpages = (((unsigned long) __init_end) - ((unsigned long) __init_begin));
initpages = PAGE_ALIGN(initpages) >> PAGE_SHIFT;
- printk("Memory: %uk available (%ldk kernel code, %ldk data, %ldk init) [%016lx,%016lx]\n",
+ printk("Memory: %luk available (%ldk kernel code, %ldk data, %ldk init) [%016lx,%016lx]\n",
nr_free_pages() << (PAGE_SHIFT-10),
codepages << (PAGE_SHIFT-10),
datapages << (PAGE_SHIFT-10),
page = (addr +
((unsigned long) __va(kern_base)) -
((unsigned long) KERNBASE));
- memset((void *)addr, 0xcc, PAGE_SIZE);
+ memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
p = virt_to_page(page);
ClearPageReserved(p);
- set_page_count(p, 1);
+ init_page_count(p);
__free_page(p);
num_physpages++;
totalram_pages++;
struct page *p = virt_to_page(start);
ClearPageReserved(p);
- set_page_count(p, 1);
+ init_page_count(p);
__free_page(p);
num_physpages++;
totalram_pages++;
}
}
#endif
+
+#define _PAGE_CACHE_4U (_PAGE_CP_4U | _PAGE_CV_4U)
+#define _PAGE_CACHE_4V (_PAGE_CP_4V | _PAGE_CV_4V)
+#define __DIRTY_BITS_4U (_PAGE_MODIFIED_4U | _PAGE_WRITE_4U | _PAGE_W_4U)
+#define __DIRTY_BITS_4V (_PAGE_MODIFIED_4V | _PAGE_WRITE_4V | _PAGE_W_4V)
+#define __ACCESS_BITS_4U (_PAGE_ACCESSED_4U | _PAGE_READ_4U | _PAGE_R)
+#define __ACCESS_BITS_4V (_PAGE_ACCESSED_4V | _PAGE_READ_4V | _PAGE_R)
+
+pgprot_t PAGE_KERNEL __read_mostly;
+EXPORT_SYMBOL(PAGE_KERNEL);
+
+pgprot_t PAGE_KERNEL_LOCKED __read_mostly;
+pgprot_t PAGE_COPY __read_mostly;
+
+pgprot_t PAGE_SHARED __read_mostly;
+EXPORT_SYMBOL(PAGE_SHARED);
+
+pgprot_t PAGE_EXEC __read_mostly;
+unsigned long pg_iobits __read_mostly;
+
+unsigned long _PAGE_IE __read_mostly;
+EXPORT_SYMBOL(_PAGE_IE);
+
+unsigned long _PAGE_E __read_mostly;
+EXPORT_SYMBOL(_PAGE_E);
+
+unsigned long _PAGE_CACHE __read_mostly;
+EXPORT_SYMBOL(_PAGE_CACHE);
+
+static void prot_init_common(unsigned long page_none,
+ unsigned long page_shared,
+ unsigned long page_copy,
+ unsigned long page_readonly,
+ unsigned long page_exec_bit)
+{
+ PAGE_COPY = __pgprot(page_copy);
+ PAGE_SHARED = __pgprot(page_shared);
+
+ protection_map[0x0] = __pgprot(page_none);
+ protection_map[0x1] = __pgprot(page_readonly & ~page_exec_bit);
+ protection_map[0x2] = __pgprot(page_copy & ~page_exec_bit);
+ protection_map[0x3] = __pgprot(page_copy & ~page_exec_bit);
+ protection_map[0x4] = __pgprot(page_readonly);
+ protection_map[0x5] = __pgprot(page_readonly);
+ protection_map[0x6] = __pgprot(page_copy);
+ protection_map[0x7] = __pgprot(page_copy);
+ protection_map[0x8] = __pgprot(page_none);
+ protection_map[0x9] = __pgprot(page_readonly & ~page_exec_bit);
+ protection_map[0xa] = __pgprot(page_shared & ~page_exec_bit);
+ protection_map[0xb] = __pgprot(page_shared & ~page_exec_bit);
+ protection_map[0xc] = __pgprot(page_readonly);
+ protection_map[0xd] = __pgprot(page_readonly);
+ protection_map[0xe] = __pgprot(page_shared);
+ protection_map[0xf] = __pgprot(page_shared);
+}
+
+static void __init sun4u_pgprot_init(void)
+{
+ unsigned long page_none, page_shared, page_copy, page_readonly;
+ unsigned long page_exec_bit;
+
+ PAGE_KERNEL = __pgprot (_PAGE_PRESENT_4U | _PAGE_VALID |
+ _PAGE_CACHE_4U | _PAGE_P_4U |
+ __ACCESS_BITS_4U | __DIRTY_BITS_4U |
+ _PAGE_EXEC_4U);
+ PAGE_KERNEL_LOCKED = __pgprot (_PAGE_PRESENT_4U | _PAGE_VALID |
+ _PAGE_CACHE_4U | _PAGE_P_4U |
+ __ACCESS_BITS_4U | __DIRTY_BITS_4U |
+ _PAGE_EXEC_4U | _PAGE_L_4U);
+ PAGE_EXEC = __pgprot(_PAGE_EXEC_4U);
+
+ _PAGE_IE = _PAGE_IE_4U;
+ _PAGE_E = _PAGE_E_4U;
+ _PAGE_CACHE = _PAGE_CACHE_4U;
+
+ pg_iobits = (_PAGE_VALID | _PAGE_PRESENT_4U | __DIRTY_BITS_4U |
+ __ACCESS_BITS_4U | _PAGE_E_4U);
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZBITS_4U) ^
+ 0xfffff80000000000;
+#else
+ kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4U) ^
+ 0xfffff80000000000;
+#endif
+ kern_linear_pte_xor[0] |= (_PAGE_CP_4U | _PAGE_CV_4U |
+ _PAGE_P_4U | _PAGE_W_4U);
+
+ /* XXX Should use 256MB on Panther. XXX */
+ kern_linear_pte_xor[1] = kern_linear_pte_xor[0];
+
+ _PAGE_SZBITS = _PAGE_SZBITS_4U;
+ _PAGE_ALL_SZ_BITS = (_PAGE_SZ4MB_4U | _PAGE_SZ512K_4U |
+ _PAGE_SZ64K_4U | _PAGE_SZ8K_4U |
+ _PAGE_SZ32MB_4U | _PAGE_SZ256MB_4U);
+
+
+ page_none = _PAGE_PRESENT_4U | _PAGE_ACCESSED_4U | _PAGE_CACHE_4U;
+ page_shared = (_PAGE_VALID | _PAGE_PRESENT_4U | _PAGE_CACHE_4U |
+ __ACCESS_BITS_4U | _PAGE_WRITE_4U | _PAGE_EXEC_4U);
+ page_copy = (_PAGE_VALID | _PAGE_PRESENT_4U | _PAGE_CACHE_4U |
+ __ACCESS_BITS_4U | _PAGE_EXEC_4U);
+ page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4U | _PAGE_CACHE_4U |
+ __ACCESS_BITS_4U | _PAGE_EXEC_4U);
+
+ page_exec_bit = _PAGE_EXEC_4U;
+
+ prot_init_common(page_none, page_shared, page_copy, page_readonly,
+ page_exec_bit);
+}
+
+static void __init sun4v_pgprot_init(void)
+{
+ unsigned long page_none, page_shared, page_copy, page_readonly;
+ unsigned long page_exec_bit;
+
+ PAGE_KERNEL = __pgprot (_PAGE_PRESENT_4V | _PAGE_VALID |
+ _PAGE_CACHE_4V | _PAGE_P_4V |
+ __ACCESS_BITS_4V | __DIRTY_BITS_4V |
+ _PAGE_EXEC_4V);
+ PAGE_KERNEL_LOCKED = PAGE_KERNEL;
+ PAGE_EXEC = __pgprot(_PAGE_EXEC_4V);
+
+ _PAGE_IE = _PAGE_IE_4V;
+ _PAGE_E = _PAGE_E_4V;
+ _PAGE_CACHE = _PAGE_CACHE_4V;
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZBITS_4V) ^
+ 0xfffff80000000000;
+#else
+ kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4V) ^
+ 0xfffff80000000000;
+#endif
+ kern_linear_pte_xor[0] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+ _PAGE_P_4V | _PAGE_W_4V);
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZBITS_4V) ^
+ 0xfffff80000000000;
+#else
+ kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZ256MB_4V) ^
+ 0xfffff80000000000;
+#endif
+ kern_linear_pte_xor[1] |= (_PAGE_CP_4V | _PAGE_CV_4V |
+ _PAGE_P_4V | _PAGE_W_4V);
+
+ pg_iobits = (_PAGE_VALID | _PAGE_PRESENT_4V | __DIRTY_BITS_4V |
+ __ACCESS_BITS_4V | _PAGE_E_4V);
+
+ _PAGE_SZBITS = _PAGE_SZBITS_4V;
+ _PAGE_ALL_SZ_BITS = (_PAGE_SZ16GB_4V | _PAGE_SZ2GB_4V |
+ _PAGE_SZ256MB_4V | _PAGE_SZ32MB_4V |
+ _PAGE_SZ4MB_4V | _PAGE_SZ512K_4V |
+ _PAGE_SZ64K_4V | _PAGE_SZ8K_4V);
+
+ page_none = _PAGE_PRESENT_4V | _PAGE_ACCESSED_4V | _PAGE_CACHE_4V;
+ page_shared = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ __ACCESS_BITS_4V | _PAGE_WRITE_4V | _PAGE_EXEC_4V);
+ page_copy = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ __ACCESS_BITS_4V | _PAGE_EXEC_4V);
+ page_readonly = (_PAGE_VALID | _PAGE_PRESENT_4V | _PAGE_CACHE_4V |
+ __ACCESS_BITS_4V | _PAGE_EXEC_4V);
+
+ page_exec_bit = _PAGE_EXEC_4V;
+
+ prot_init_common(page_none, page_shared, page_copy, page_readonly,
+ page_exec_bit);
+}
+
+unsigned long pte_sz_bits(unsigned long sz)
+{
+ if (tlb_type == hypervisor) {
+ switch (sz) {
+ case 8 * 1024:
+ default:
+ return _PAGE_SZ8K_4V;
+ case 64 * 1024:
+ return _PAGE_SZ64K_4V;
+ case 512 * 1024:
+ return _PAGE_SZ512K_4V;
+ case 4 * 1024 * 1024:
+ return _PAGE_SZ4MB_4V;
+ };
+ } else {
+ switch (sz) {
+ case 8 * 1024:
+ default:
+ return _PAGE_SZ8K_4U;
+ case 64 * 1024:
+ return _PAGE_SZ64K_4U;
+ case 512 * 1024:
+ return _PAGE_SZ512K_4U;
+ case 4 * 1024 * 1024:
+ return _PAGE_SZ4MB_4U;
+ };
+ }
+}
+
+pte_t mk_pte_io(unsigned long page, pgprot_t prot, int space, unsigned long page_size)
+{
+ pte_t pte;
+
+ pte_val(pte) = page | pgprot_val(pgprot_noncached(prot));
+ pte_val(pte) |= (((unsigned long)space) << 32);
+ pte_val(pte) |= pte_sz_bits(page_size);
+
+ return pte;
+}
+
+static unsigned long kern_large_tte(unsigned long paddr)
+{
+ unsigned long val;
+
+ val = (_PAGE_VALID | _PAGE_SZ4MB_4U |
+ _PAGE_CP_4U | _PAGE_CV_4U | _PAGE_P_4U |
+ _PAGE_EXEC_4U | _PAGE_L_4U | _PAGE_W_4U);
+ if (tlb_type == hypervisor)
+ val = (_PAGE_VALID | _PAGE_SZ4MB_4V |
+ _PAGE_CP_4V | _PAGE_CV_4V | _PAGE_P_4V |
+ _PAGE_EXEC_4V | _PAGE_W_4V);
+
+ return val | paddr;
+}
+
+/* If not locked, zap it. */
+void __flush_tlb_all(void)
+{
+ unsigned long pstate;
+ int i;
+
+ __asm__ __volatile__("flushw\n\t"
+ "rdpr %%pstate, %0\n\t"
+ "wrpr %0, %1, %%pstate"
+ : "=r" (pstate)
+ : "i" (PSTATE_IE));
+ if (tlb_type == spitfire) {
+ for (i = 0; i < 64; i++) {
+ /* Spitfire Errata #32 workaround */
+ /* NOTE: Always runs on spitfire, so no
+ * cheetah+ page size encodings.
+ */
+ __asm__ __volatile__("stxa %0, [%1] %2\n\t"
+ "flush %%g6"
+ : /* No outputs */
+ : "r" (0),
+ "r" (PRIMARY_CONTEXT), "i" (ASI_DMMU));
+
+ if (!(spitfire_get_dtlb_data(i) & _PAGE_L_4U)) {
+ __asm__ __volatile__("stxa %%g0, [%0] %1\n\t"
+ "membar #Sync"
+ : /* no outputs */
+ : "r" (TLB_TAG_ACCESS), "i" (ASI_DMMU));
+ spitfire_put_dtlb_data(i, 0x0UL);
+ }
+
+ /* Spitfire Errata #32 workaround */
+ /* NOTE: Always runs on spitfire, so no
+ * cheetah+ page size encodings.
+ */
+ __asm__ __volatile__("stxa %0, [%1] %2\n\t"
+ "flush %%g6"
+ : /* No outputs */
+ : "r" (0),
+ "r" (PRIMARY_CONTEXT), "i" (ASI_DMMU));
+
+ if (!(spitfire_get_itlb_data(i) & _PAGE_L_4U)) {
+ __asm__ __volatile__("stxa %%g0, [%0] %1\n\t"
+ "membar #Sync"
+ : /* no outputs */
+ : "r" (TLB_TAG_ACCESS), "i" (ASI_IMMU));
+ spitfire_put_itlb_data(i, 0x0UL);
+ }
+ }
+ } else if (tlb_type == cheetah || tlb_type == cheetah_plus) {
+ cheetah_flush_dtlb_all();
+ cheetah_flush_itlb_all();
+ }
+ __asm__ __volatile__("wrpr %0, 0, %%pstate"
+ : : "r" (pstate));
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+
+void online_page(struct page *page)
+{
+ ClearPageReserved(page);
+ init_page_count(page);
+ __free_page(page);
+ totalram_pages++;
+ num_physpages++;
+}
+
+int remove_memory(u64 start, u64 size)
+{
+ return -EINVAL;
+}
+
+#endif /* CONFIG_MEMORY_HOTPLUG */
Code Review / linux-2.6.git / blobdiff