init.c

来自「linux 内核源代码」· C语言 代码 · 共 1,976 行 · 第 1/4 页

/*  $Id: init.c,v 1.209 2002/02/09 19:49:31 davem Exp $
 *  arch/sparc64/mm/init.c
 *
 *  Copyright (C) 1996-1999 David S. Miller ([e-mail])
 *  Copyright (C) 1997-1999 Jakub Jelinek ([e-mail])
 */
 
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/slab.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/page.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/oplib.h>
#include <asm/iommu.h>
#include <asm/io.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
#include <asm/dma.h>
#include <asm/starfire.h>
#include <asm/tlb.h>
#include <asm/spitfire.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>

#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

static struct linux_prom64_registers pavail[MAX_BANKS] __initdata;
static struct linux_prom64_registers pavail_rescan[MAX_BANKS] __initdata;
static int pavail_ents __initdata;
static int pavail_rescan_ents __initdata;

static int cmp_p64(const void *a, const void *b)
{
	const struct linux_prom64_registers *x = a, *y = b;

	if (x->phys_addr > y->phys_addr)
		return 1;
	if (x->phys_addr < y->phys_addr)
		return -1;
	return 0;
}

static void __init read_obp_memory(const char *property,
				   struct linux_prom64_registers *regs,
				   int *num_ents)
{
	int node = prom_finddevice("/memory");
	int prop_size = prom_getproplen(node, property);
	int ents, ret, i;

	ents = prop_size / sizeof(struct linux_prom64_registers);
	if (ents > MAX_BANKS) {
		prom_printf("The machine has more %s property entries than "
			    "this kernel can support (%d).\n",
			    property, MAX_BANKS);
		prom_halt();
	}

	ret = prom_getproperty(node, property, (char *) regs, prop_size);
	if (ret == -1) {
		prom_printf("Couldn't get %s property from /memory.\n");
		prom_halt();
	}

	/* Sanitize what we got from the firmware, by page aligning
	 * everything.
	 */
	for (i = 0; i < ents; i++) {
		unsigned long base, size;

		base = regs[i].phys_addr;
		size = regs[i].reg_size;

		size &= PAGE_MASK;
		if (base & ~PAGE_MASK) {
			unsigned long new_base = PAGE_ALIGN(base);

			size -= new_base - base;
			if ((long) size < 0L)
				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(&regs[i], &regs[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;

/* Kernel physical address base and size in bytes.  */
unsigned long kern_base __read_mostly;
unsigned long kern_size __read_mostly;

/* Initial ramdisk setup */
extern unsigned long sparc_ramdisk_image64;
extern unsigned int sparc_ramdisk_image;
extern unsigned int sparc_ramdisk_size;

struct page *mem_map_zero __read_mostly;

unsigned int sparc64_highest_unlocked_tlb_ent __read_mostly;

unsigned long sparc64_kern_pri_context __read_mostly;
unsigned long sparc64_kern_pri_nuc_bits __read_mostly;
unsigned long sparc64_kern_sec_context __read_mostly;

int bigkernel = 0;

#ifdef CONFIG_DEBUG_DCFLUSH
atomic_t dcpage_flushes = ATOMIC_INIT(0);
#ifdef CONFIG_SMP
atomic_t dcpage_flushes_xcall = ATOMIC_INIT(0);
#endif
#endif

inline void flush_dcache_page_impl(struct page *page)
{
	BUG_ON(tlb_type == hypervisor);
#ifdef CONFIG_DEBUG_DCFLUSH
	atomic_inc(&dcpage_flushes);
#endif

#ifdef DCACHE_ALIASING_POSSIBLE
	__flush_dcache_page(page_address(page),
			    ((tlb_type == spitfire) &&
			     page_mapping(page) != NULL));
#else
	if (page_mapping(page) != NULL &&
	    tlb_type == spitfire)
		__flush_icache_page(__pa(page_address(page)));
#endif
}

#define PG_dcache_dirty		PG_arch_1
#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)

static inline void set_dcache_dirty(struct page *page, int this_cpu)
{
	unsigned long mask = this_cpu;
	unsigned long non_cpu_bits;

	non_cpu_bits = ~(PG_dcache_cpu_mask << PG_dcache_cpu_shift);
	mask = (mask << PG_dcache_cpu_shift) | (1UL << PG_dcache_dirty);

	__asm__ __volatile__("1:\n\t"
			     "ldx	[%2], %%g7\n\t"
			     "and	%%g7, %1, %%g1\n\t"
			     "or	%%g1, %0, %%g1\n\t"
			     "casx	[%2], %%g7, %%g1\n\t"
			     "cmp	%%g7, %%g1\n\t"
			     "membar	#StoreLoad | #StoreStore\n\t"
			     "bne,pn	%%xcc, 1b\n\t"
			     " nop"
			     : /* no outputs */
			     : "r" (mask), "r" (non_cpu_bits), "r" (&page->flags)
			     : "g1", "g7");
}

static inline void clear_dcache_dirty_cpu(struct page *page, unsigned long cpu)
{
	unsigned long mask = (1UL << PG_dcache_dirty);

	__asm__ __volatile__("! test_and_clear_dcache_dirty\n"
			     "1:\n\t"
			     "ldx	[%2], %%g7\n\t"
			     "srlx	%%g7, %4, %%g1\n\t"
			     "and	%%g1, %3, %%g1\n\t"
			     "cmp	%%g1, %0\n\t"
			     "bne,pn	%%icc, 2f\n\t"
			     " andn	%%g7, %1, %%g1\n\t"
			     "casx	[%2], %%g7, %%g1\n\t"
			     "cmp	%%g7, %%g1\n\t"
			     "membar	#StoreLoad | #StoreStore\n\t"
			     "bne,pn	%%xcc, 1b\n\t"
			     " nop\n"
			     "2:"
			     : /* no outputs */
			     : "r" (cpu), "r" (mask), "r" (&page->flags),
			       "i" (PG_dcache_cpu_mask),
			       "i" (PG_dcache_cpu_shift)
			     : "g1", "g7");
}

static inline void tsb_insert(struct tsb *ent, unsigned long tag, unsigned long pte)
{
	unsigned long tsb_addr = (unsigned long) ent;

	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 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);

			put_cpu();
		}
	}

	mm = vma->vm_mm;

	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 (page == ZERO_PAGE(0))
		return;

	this_cpu = get_cpu();

	mapping = page_mapping(page);
	if (mapping && !mapping_mapped(mapping)) {
		int dirty = test_bit(PG_dcache_dirty, &page->flags);
		if (dirty) {
			int dirty_cpu = dcache_dirty_cpu(page);

			if (dirty_cpu == this_cpu)
				goto out;
			smp_flush_dcache_page_impl(page, dirty_cpu);
		}
		set_dcache_dirty(page, this_cpu);
	} else {
		/* We could delay the flush for the !page_mapping
		 * case too.  But that case is for exec env/arg
		 * pages and those are %99 certainly going to get
		 * faulted into the tlb (and thus flushed) anyways.
		 */
		flush_dcache_page_impl(page);
	}

out:
	put_cpu();
}

void __kprobes flush_icache_range(unsigned long start, unsigned long end)
{
	/* Cheetah and Hypervisor platform cpus have coherent I-cache. */
	if (tlb_type == spitfire) {
		unsigned long 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);
		}
	}
}

void show_mem(void)
{
	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(KERN_INFO "Free swap:       %6ldkB\n",
	       nr_swap_pages << (PAGE_SHIFT-10));
	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)
{
	if (tlb_type == cheetah)
		seq_printf(m, "MMU Type\t: Cheetah\n");
	else if (tlb_type == cheetah_plus)
		seq_printf(m, "MMU Type\t: Cheetah+\n");
	else if (tlb_type == spitfire)
		seq_printf(m, "MMU Type\t: Spitfire\n");
	else if (tlb_type == hypervisor)
		seq_printf(m, "MMU Type\t: Hypervisor (sun4v)\n");
	else
		seq_printf(m, "MMU Type\t: ???\n");

#ifdef CONFIG_DEBUG_DCFLUSH
	seq_printf(m, "DCPageFlushes\t: %d\n",
		   atomic_read(&dcpage_flushes));
#ifdef CONFIG_SMP
	seq_printf(m, "DCPageFlushesXC\t: %d\n",
		   atomic_read(&dcpage_flushes_xcall));
#endif /* CONFIG_SMP */
#endif /* CONFIG_DEBUG_DCFLUSH */
}

struct linux_prom_translation {
	unsigned long virt;
	unsigned long size;
	unsigned long data;
};

/* Exported for kernel TLB miss handling in ktlb.S */
struct linux_prom_translation prom_trans[512] __read_mostly;
unsigned int prom_trans_ents __read_mostly;

/* Exported for SMP bootup purposes. */
unsigned long kern_locked_tte_data;

/* 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.
 */
static inline int in_obp_range(unsigned long vaddr)
{
	return (vaddr >= LOW_OBP_ADDRESS &&
		vaddr < HI_OBP_ADDRESS);
}

static int cmp_ptrans(const void *a, const void *b)
{
	const struct linux_prom_translation *x = a, *y = b;

	if (x->virt > y->virt)
		return 1;
	if (x->virt < y->virt)
		return -1;
	return 0;
}