diff options
Diffstat (limited to 'arch/sparc')
| -rw-r--r-- | arch/sparc/mm/Makefile | 6 | ||||
| -rw-r--r-- | arch/sparc/mm/fault_64.c | 440 | ||||
| -rw-r--r-- | arch/sparc/mm/generic_64.c | 163 | ||||
| -rw-r--r-- | arch/sparc/mm/hugetlbpage.c | 357 | ||||
| -rw-r--r-- | arch/sparc/mm/init_64.c | 2360 | ||||
| -rw-r--r-- | arch/sparc/mm/init_64.h | 49 | ||||
| -rw-r--r-- | arch/sparc/mm/tlb.c | 97 | ||||
| -rw-r--r-- | arch/sparc/mm/tsb.c | 496 | ||||
| -rw-r--r-- | arch/sparc/mm/ultra.S | 767 |
9 files changed, 4734 insertions, 1 deletions
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile index 3ad1b1f9953e..681abe0a4594 100644 --- a/arch/sparc/mm/Makefile +++ b/arch/sparc/mm/Makefile @@ -4,13 +4,17 @@ asflags-y := -ansi ccflags-y := -Werror -obj-y := fault_$(BITS).o +obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o +obj-y += fault_$(BITS).o obj-y += init_$(BITS).o obj-$(CONFIG_SPARC32) += loadmmu.o obj-y += generic_$(BITS).o obj-$(CONFIG_SPARC32) += extable.o btfixup.o srmmu.o iommu.o io-unit.o obj-$(CONFIG_SPARC32) += hypersparc.o viking.o tsunami.o swift.o +# Only used by sparc64 +obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o + # Only used by sparc32 obj-$(CONFIG_HIGHMEM) += highmem.o diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c new file mode 100644 index 000000000000..a9e474bf6385 --- /dev/null +++ b/arch/sparc/mm/fault_64.c @@ -0,0 +1,440 @@ +/* + * arch/sparc64/mm/fault.c: Page fault handlers for the 64-bit Sparc. + * + * Copyright (C) 1996, 2008 David S. Miller (davem@davemloft.net) + * Copyright (C) 1997, 1999 Jakub Jelinek (jj@ultra.linux.cz) + */ + +#include <asm/head.h> + +#include <linux/string.h> +#include <linux/types.h> +#include <linux/sched.h> +#include <linux/ptrace.h> +#include <linux/mman.h> +#include <linux/signal.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/kprobes.h> +#include <linux/kdebug.h> + +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/openprom.h> +#include <asm/oplib.h> +#include <asm/uaccess.h> +#include <asm/asi.h> +#include <asm/lsu.h> +#include <asm/sections.h> +#include <asm/mmu_context.h> + +#ifdef CONFIG_KPROBES +static inline int notify_page_fault(struct pt_regs *regs) +{ + int ret = 0; + + /* kprobe_running() needs smp_processor_id() */ + if (!user_mode(regs)) { + preempt_disable(); + if (kprobe_running() && kprobe_fault_handler(regs, 0)) + ret = 1; + preempt_enable(); + } + return ret; +} +#else +static inline int notify_page_fault(struct pt_regs *regs) +{ + return 0; +} +#endif + +static void __kprobes unhandled_fault(unsigned long address, + struct task_struct *tsk, + struct pt_regs *regs) +{ + if ((unsigned long) address < PAGE_SIZE) { + printk(KERN_ALERT "Unable to handle kernel NULL " + "pointer dereference\n"); + } else { + printk(KERN_ALERT "Unable to handle kernel paging request " + "at virtual address %016lx\n", (unsigned long)address); + } + printk(KERN_ALERT "tsk->{mm,active_mm}->context = %016lx\n", + (tsk->mm ? + CTX_HWBITS(tsk->mm->context) : + CTX_HWBITS(tsk->active_mm->context))); + printk(KERN_ALERT "tsk->{mm,active_mm}->pgd = %016lx\n", + (tsk->mm ? (unsigned long) tsk->mm->pgd : + (unsigned long) tsk->active_mm->pgd)); + die_if_kernel("Oops", regs); +} + +static void bad_kernel_pc(struct pt_regs *regs, unsigned long vaddr) +{ + printk(KERN_CRIT "OOPS: Bogus kernel PC [%016lx] in fault handler\n", + regs->tpc); + printk(KERN_CRIT "OOPS: RPC [%016lx]\n", regs->u_regs[15]); + printk("OOPS: RPC <%pS>\n", (void *) regs->u_regs[15]); + printk(KERN_CRIT "OOPS: Fault was to vaddr[%lx]\n", vaddr); + dump_stack(); + unhandled_fault(regs->tpc, current, regs); +} + +/* + * We now make sure that mmap_sem is held in all paths that call + * this. Additionally, to prevent kswapd from ripping ptes from + * under us, raise interrupts around the time that we look at the + * pte, kswapd will have to wait to get his smp ipi response from + * us. vmtruncate likewise. This saves us having to get pte lock. + */ +static unsigned int get_user_insn(unsigned long tpc) +{ + pgd_t *pgdp = pgd_offset(current->mm, tpc); + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep, pte; + unsigned long pa; + u32 insn = 0; + unsigned long pstate; + + if (pgd_none(*pgdp)) + goto outret; + pudp = pud_offset(pgdp, tpc); + if (pud_none(*pudp)) + goto outret; + pmdp = pmd_offset(pudp, tpc); + if (pmd_none(*pmdp)) + goto outret; + + /* This disables preemption for us as well. */ + __asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate)); + __asm__ __volatile__("wrpr %0, %1, %%pstate" + : : "r" (pstate), "i" (PSTATE_IE)); + ptep = pte_offset_map(pmdp, tpc); + pte = *ptep; + if (!pte_present(pte)) + goto out; + + pa = (pte_pfn(pte) << PAGE_SHIFT); + pa += (tpc & ~PAGE_MASK); + + /* Use phys bypass so we don't pollute dtlb/dcache. */ + __asm__ __volatile__("lduwa [%1] %2, %0" + : "=r" (insn) + : "r" (pa), "i" (ASI_PHYS_USE_EC)); + +out: + pte_unmap(ptep); + __asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate)); +outret: + return insn; +} + +extern unsigned long compute_effective_address(struct pt_regs *, unsigned int, unsigned int); + +static void do_fault_siginfo(int code, int sig, struct pt_regs *regs, + unsigned int insn, int fault_code) +{ + siginfo_t info; + + info.si_code = code; + info.si_signo = sig; + info.si_errno = 0; + if (fault_code & FAULT_CODE_ITLB) + info.si_addr = (void __user *) regs->tpc; + else + info.si_addr = (void __user *) + compute_effective_address(regs, insn, 0); + info.si_trapno = 0; + force_sig_info(sig, &info, current); +} + +extern int handle_ldf_stq(u32, struct pt_regs *); +extern int handle_ld_nf(u32, struct pt_regs *); + +static unsigned int get_fault_insn(struct pt_regs *regs, unsigned int insn) +{ + if (!insn) { + if (!regs->tpc || (regs->tpc & 0x3)) + return 0; + if (regs->tstate & TSTATE_PRIV) { + insn = *(unsigned int *) regs->tpc; + } else { + insn = get_user_insn(regs->tpc); + } + } + return insn; +} + +static void do_kernel_fault(struct pt_regs *regs, int si_code, int fault_code, + unsigned int insn, unsigned long address) +{ + unsigned char asi = ASI_P; + + if ((!insn) && (regs->tstate & TSTATE_PRIV)) + goto cannot_handle; + + /* If user insn could be read (thus insn is zero), that + * is fine. We will just gun down the process with a signal + * in that case. + */ + + if (!(fault_code & (FAULT_CODE_WRITE|FAULT_CODE_ITLB)) && + (insn & 0xc0800000) == 0xc0800000) { + if (insn & 0x2000) + asi = (regs->tstate >> 24); + else + asi = (insn >> 5); + if ((asi & 0xf2) == 0x82) { + if (insn & 0x1000000) { + handle_ldf_stq(insn, regs); + } else { + /* This was a non-faulting load. Just clear the + * destination register(s) and continue with the next + * instruction. -jj + */ + handle_ld_nf(insn, regs); + } + return; + } + } + + /* Is this in ex_table? */ + if (regs->tstate & TSTATE_PRIV) { + const struct exception_table_entry *entry; + + entry = search_exception_tables(regs->tpc); + if (entry) { + regs->tpc = entry->fixup; + regs->tnpc = regs->tpc + 4; + return; + } + } else { + /* The si_code was set to make clear whether + * this was a SEGV_MAPERR or SEGV_ACCERR fault. + */ + do_fault_siginfo(si_code, SIGSEGV, regs, insn, fault_code); + return; + } + +cannot_handle: + unhandled_fault (address, current, regs); +} + +asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned int insn = 0; + int si_code, fault_code, fault; + unsigned long address, mm_rss; + + fault_code = get_thread_fault_code(); + + if (notify_page_fault(regs)) + return; + + si_code = SEGV_MAPERR; + address = current_thread_info()->fault_address; + + if ((fault_code & FAULT_CODE_ITLB) && + (fault_code & FAULT_CODE_DTLB)) + BUG(); + + if (regs->tstate & TSTATE_PRIV) { + unsigned long tpc = regs->tpc; + + /* Sanity check the PC. */ + if ((tpc >= KERNBASE && tpc < (unsigned long) __init_end) || + (tpc >= MODULES_VADDR && tpc < MODULES_END)) { + /* Valid, no problems... */ + } else { + bad_kernel_pc(regs, address); + return; + } + } + + /* + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ + if (in_atomic() || !mm) + goto intr_or_no_mm; + + if (test_thread_flag(TIF_32BIT)) { + if (!(regs->tstate & TSTATE_PRIV)) + regs->tpc &= 0xffffffff; + address &= 0xffffffff; + } + + if (!down_read_trylock(&mm->mmap_sem)) { + if ((regs->tstate & TSTATE_PRIV) && + !search_exception_tables(regs->tpc)) { + insn = get_fault_insn(regs, insn); + goto handle_kernel_fault; + } + down_read(&mm->mmap_sem); + } + + vma = find_vma(mm, address); + if (!vma) + goto bad_area; + + /* Pure DTLB misses do not tell us whether the fault causing + * load/store/atomic was a write or not, it only says that there + * was no match. So in such a case we (carefully) read the + * instruction to try and figure this out. It's an optimization + * so it's ok if we can't do this. + * + * Special hack, window spill/fill knows the exact fault type. + */ + if (((fault_code & + (FAULT_CODE_DTLB | FAULT_CODE_WRITE | FAULT_CODE_WINFIXUP)) == FAULT_CODE_DTLB) && + (vma->vm_flags & VM_WRITE) != 0) { + insn = get_fault_insn(regs, 0); + if (!insn) + goto continue_fault; + /* All loads, stores and atomics have bits 30 and 31 both set + * in the instruction. Bit 21 is set in all stores, but we + * have to avoid prefetches which also have bit 21 set. + */ + if ((insn & 0xc0200000) == 0xc0200000 && + (insn & 0x01780000) != 0x01680000) { + /* Don't bother updating thread struct value, + * because update_mmu_cache only cares which tlb + * the access came from. + */ + fault_code |= FAULT_CODE_WRITE; + } + } +continue_fault: + + if (vma->vm_start <= address) + goto good_area; + if (!(vma->vm_flags & VM_GROWSDOWN)) + goto bad_area; + if (!(fault_code & FAULT_CODE_WRITE)) { + /* Non-faulting loads shouldn't expand stack. */ + insn = get_fault_insn(regs, insn); + if ((insn & 0xc0800000) == 0xc0800000) { + unsigned char asi; + + if (insn & 0x2000) + asi = (regs->tstate >> 24); + else + asi = (insn >> 5); + if ((asi & 0xf2) == 0x82) + goto bad_area; + } + } + if (expand_stack(vma, address)) + goto bad_area; + /* + * Ok, we have a good vm_area for this memory access, so + * we can handle it.. + */ +good_area: + si_code = SEGV_ACCERR; + + /* If we took a ITLB miss on a non-executable page, catch + * that here. + */ + if ((fault_code & FAULT_CODE_ITLB) && !(vma->vm_flags & VM_EXEC)) { + BUG_ON(address != regs->tpc); + BUG_ON(regs->tstate & TSTATE_PRIV); + goto bad_area; + } + + if (fault_code & FAULT_CODE_WRITE) { + if (!(vma->vm_flags & VM_WRITE)) + goto bad_area; + + /* Spitfire has an icache which does not snoop + * processor stores. Later processors do... + */ + if (tlb_type == spitfire && + (vma->vm_flags & VM_EXEC) != 0 && + vma->vm_file != NULL) + set_thread_fault_code(fault_code | + FAULT_CODE_BLKCOMMIT); + } else { + /* Allow reads even for write-only mappings */ + if (!(vma->vm_flags & (VM_READ | VM_EXEC))) + goto bad_area; + } + + fault = handle_mm_fault(mm, vma, address, (fault_code & FAULT_CODE_WRITE)); + if (unlikely(fault & VM_FAULT_ERROR)) { + if (fault & VM_FAULT_OOM) + goto out_of_memory; + else if (fault & VM_FAULT_SIGBUS) + goto do_sigbus; + BUG(); + } + if (fault & VM_FAULT_MAJOR) + current->maj_flt++; + else + current->min_flt++; + + up_read(&mm->mmap_sem); + + mm_rss = get_mm_rss(mm); +#ifdef CONFIG_HUGETLB_PAGE + mm_rss -= (mm->context.huge_pte_count * (HPAGE_SIZE / PAGE_SIZE)); +#endif + if (unlikely(mm_rss > + mm->context.tsb_block[MM_TSB_BASE].tsb_rss_limit)) + tsb_grow(mm, MM_TSB_BASE, mm_rss); +#ifdef CONFIG_HUGETLB_PAGE + mm_rss = mm->context.huge_pte_count; + if (unlikely(mm_rss > + mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit)) + tsb_grow(mm, MM_TSB_HUGE, mm_rss); +#endif + return; + + /* + * Something tried to access memory that isn't in our memory map.. + * Fix it, but check if it's kernel or user first.. + */ +bad_area: + insn = get_fault_insn(regs, insn); + up_read(&mm->mmap_sem); + +handle_kernel_fault: + do_kernel_fault(regs, si_code, fault_code, insn, address); + return; + +/* + * We ran out of memory, or some other thing happened to us that made + * us unable to handle the page fault gracefully. + */ +out_of_memory: + insn = get_fault_insn(regs, insn); + up_read(&mm->mmap_sem); + printk("VM: killing process %s\n", current->comm); + if (!(regs->tstate & TSTATE_PRIV)) + do_group_exit(SIGKILL); + goto handle_kernel_fault; + +intr_or_no_mm: + insn = get_fault_insn(regs, 0); + goto handle_kernel_fault; + +do_sigbus: + insn = get_fault_insn(regs, insn); + up_read(&mm->mmap_sem); + + /* + * Send a sigbus, regardless of whether we were in kernel + * or user mode. + */ + do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, insn, fault_code); + + /* Kernel mode? Handle exceptions or die */ + if (regs->tstate & TSTATE_PRIV) + goto handle_kernel_fault; +} diff --git a/arch/sparc/mm/generic_64.c b/arch/sparc/mm/generic_64.c new file mode 100644 index 000000000000..f362c2037013 --- /dev/null +++ b/arch/sparc/mm/generic_64.c @@ -0,0 +1,163 @@ +/* + * generic.c: Generic Sparc mm routines that are not dependent upon + * MMU type but are Sparc specific. + * + * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) + */ + +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/swap.h> +#include <linux/pagemap.h> + +#include <asm/pgalloc.h> +#include <asm/pgtable.h> +#include <asm/page.h> +#include <asm/tlbflush.h> + +/* Remap IO memory, the same way as remap_pfn_range(), but use + * the obio memory space. + * + * They use a pgprot that sets PAGE_IO and does not check the + * mem_map table as this is independent of normal memory. + */ +static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, + unsigned long address, + unsigned long size, + unsigned long offset, pgprot_t prot, + int space) +{ + unsigned long end; + + /* clear hack bit that was used as a write_combine side-effect flag */ + offset &= ~0x1UL; + address &= ~PMD_MASK; + end = address + size; + if (end > PMD_SIZE) + end = PMD_SIZE; + do { + pte_t entry; + unsigned long curend = address + PAGE_SIZE; + + entry = mk_pte_io(offset, prot, space, PAGE_SIZE); + if (!(address & 0xffff)) { + if (PAGE_SIZE < (4 * 1024 * 1024) && + !(address & 0x3fffff) && + !(offset & 0x3ffffe) && + end >= address + 0x400000) { + entry = mk_pte_io(offset, prot, space, + 4 * 1024 * 1024); + curend = address + 0x400000; + offset += 0x400000; + } else if (PAGE_SIZE < (512 * 1024) && + !(address & 0x7ffff) && + !(offset & 0x7fffe) && + end >= address + 0x80000) { + entry = mk_pte_io(offset, prot, space, + 512 * 1024 * 1024); + curend = address + 0x80000; + offset += 0x80000; + } else if (PAGE_SIZE < (64 * 1024) && + !(offset & 0xfffe) && + end >= address + 0x10000) { + entry = mk_pte_io(offset, prot, space, + 64 * 1024); + curend = address + 0x10000; + offset += 0x10000; + } else + offset += PAGE_SIZE; + } else + offset += PAGE_SIZE; + + if (pte_write(entry)) + entry = pte_mkdirty(entry); + do { + BUG_ON(!pte_none(*pte)); + set_pte_at(mm, address, pte, entry); + address += PAGE_SIZE; + pte_val(entry) += PAGE_SIZE; + pte++; + } while (address < curend); + } while (address < end); +} + +static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size, + unsigned long offset, pgprot_t prot, int space) +{ + unsigned long end; + + address &= ~PGDIR_MASK; + end = address + size; + if (end > PGDIR_SIZE) + end = PGDIR_SIZE; + offset -= address; + do { + pte_t * pte = pte_alloc_map(mm, pmd, address); + if (!pte) + return -ENOMEM; + io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space); + pte_unmap(pte); + address = (address + PMD_SIZE) & PMD_MASK; + pmd++; + } while (address < end); + return 0; +} + +static inline int io_remap_pud_range(struct mm_struct *mm, pud_t * pud, unsigned long address, unsigned long size, + unsigned long offset, pgprot_t prot, int space) +{ + unsigned long end; + + address &= ~PUD_MASK; + end = address + size; + if (end > PUD_SIZE) + end = PUD_SIZE; + offset -= address; + do { + pmd_t *pmd = pmd_alloc(mm, pud, address); + if (!pud) + return -ENOMEM; + io_remap_pmd_range(mm, pmd, address, end - address, address + offset, prot, space); + address = (address + PUD_SIZE) & PUD_MASK; + pud++; + } while (address < end); + return 0; +} + +int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + int error = 0; + pgd_t * dir; + unsigned long beg = from; + unsigned long end = from + size; + struct mm_struct *mm = vma->vm_mm; + int space = GET_IOSPACE(pfn); + unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT; + unsigned long phys_base; + + phys_base = offset | (((unsigned long) space) << 32UL); + + /* See comment in mm/memory.c remap_pfn_range */ + vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; + vma->vm_pgoff = phys_base >> PAGE_SHIFT; + + offset -= from; + dir = pgd_offset(mm, from); + flush_cache_range(vma, beg, end); + + while (from < end) { + pud_t *pud = pud_alloc(mm, dir, from); + error = -ENOMEM; + if (!pud) + break; + error = io_remap_pud_range(mm, pud, from, end - from, offset + from, prot, space); + if (error) + break; + from = (from + PGDIR_SIZE) & PGDIR_MASK; + dir++; + } + + flush_tlb_range(vma, beg, end); + return error; +} diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c new file mode 100644 index 000000000000..f27d10369e0c --- /dev/null +++ b/arch/sparc/mm/hugetlbpage.c @@ -0,0 +1,357 @@ +/* + * SPARC64 Huge TLB page support. + * + * Copyright (C) 2002, 2003, 2006 David S. Miller (davem@davemloft.net) + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/hugetlb.h> +#include <linux/pagemap.h> +#include <linux/slab.h> +#include <linux/sysctl.h> + +#include <asm/mman.h> +#include <asm/pgalloc.h> +#include <asm/tlb.h> +#include <asm/tlbflush.h> +#include <asm/cacheflush.h> +#include <asm/mmu_context.h> + +/* Slightly simplified from the non-hugepage variant because by + * definition we don't have to worry about any page coloring stuff + */ +#define VA_EXCLUDE_START (0x0000080000000000UL - (1UL << 32UL)) +#define VA_EXCLUDE_END (0xfffff80000000000UL + (1UL << 32UL)) + +static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp, + unsigned long addr, + unsigned long len, + unsigned long pgoff, + unsigned long flags) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct * vma; + unsigned long task_size = TASK_SIZE; + unsigned long start_addr; + + if (test_thread_flag(TIF_32BIT)) + task_size = STACK_TOP32; + if (unlikely(len >= VA_EXCLUDE_START)) + return -ENOMEM; + + if (len > mm->cached_hole_size) { + start_addr = addr = mm->free_area_cache; + } else { + start_addr = addr = TASK_UNMAPPED_BASE; + mm->cached_hole_size = 0; + } + + task_size -= len; + +full_search: + addr = ALIGN(addr, HPAGE_SIZE); + + for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { + /* At this point: (!vma || addr < vma->vm_end). */ + if (addr < VA_EXCLUDE_START && + (addr + len) >= VA_EXCLUDE_START) { + addr = VA_EXCLUDE_END; + vma = find_vma(mm, VA_EXCLUDE_END); + } + if (unlikely(task_size < addr)) { + if (start_addr != TASK_UNMAPPED_BASE) { + start_addr = addr = TASK_UNMAPPED_BASE; + mm->cached_hole_size = 0; + goto full_search; + } + return -ENOMEM; + } + if (likely(!vma || addr + len <= vma->vm_start)) { + /* + * Remember the place where we stopped the search: + */ + mm->free_area_cache = addr + len; + return addr; + } + if (addr + mm->cached_hole_size < vma->vm_start) + mm->cached_hole_size = vma->vm_start - addr; + + addr = ALIGN(vma->vm_end, HPAGE_SIZE); + } +} + +static unsigned long +hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, + const unsigned long len, + const unsigned long pgoff, + const unsigned long flags) +{ + struct vm_area_struct *vma; + struct mm_struct *mm = current->mm; + unsigned long addr = addr0; + + /* This should only ever run for 32-bit processes. */ + BUG_ON(!test_thread_flag(TIF_32BIT)); + + /* check if free_area_cache is useful for us */ + if (len <= mm->cached_hole_size) { + mm->cached_hole_size = 0; + mm->free_area_cache = mm->mmap_base; + } + + /* either no address requested or can't fit in requested address hole */ + addr = mm->free_area_cache & HPAGE_MASK; + + /* make sure it can fit in the remaining address space */ + if (likely(addr > len)) { + vma = find_vma(mm, addr-len); + if (!vma || addr <= vma->vm_start) { + /* remember the address as a hint for next time */ + return (mm->free_area_cache = addr-len); + } + } + + if (unlikely(mm->mmap_base < len)) + goto bottomup; + + addr = (mm->mmap_base-len) & HPAGE_MASK; + + do { + /* + * Lookup failure means no vma is above this address, + * else if new region fits below vma->vm_start, + * return with success: + */ + vma = find_vma(mm, addr); + if (likely(!vma || addr+len <= vma->vm_start)) { + /* remember the address as a hint for next time */ + return (mm->free_area_cache = addr); + } + + /* remember the largest hole we saw so far */ + if (addr + mm->cached_hole_size < vma->vm_start) + mm->cached_hole_size = vma->vm_start - addr; + + /* try just below the current vma->vm_start */ + addr = (vma->vm_start-len) & HPAGE_MASK; + } while (likely(len < vma->vm_start)); + +bottomup: + /* + * A failed mmap() very likely causes application failure, + * so fall back to the bottom-up function here. This scenario + * can happen with large stack limits and large mmap() + * allocations. + */ + mm->cached_hole_size = ~0UL; + mm->free_area_cache = TASK_UNMAPPED_BASE; + addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags); + /* + * Restore the topdown base: + */ + mm->free_area_cache = mm->mmap_base; + mm->cached_hole_size = ~0UL; + + return addr; +} + +unsigned long +hugetlb_get_unmapped_area(struct file *file, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long task_size = TASK_SIZE; + + if (test_thread_flag(TIF_32BIT)) + task_size = STACK_TOP32; + + if (len & ~HPAGE_MASK) + return -EINVAL; + if (len > task_size) + return -ENOMEM; + + if (flags & MAP_FIXED) { + if (prepare_hugepage_range(file, addr, len)) + return -EINVAL; + return addr; + } + + if (addr) { + addr = ALIGN(addr, HPAGE_SIZE); + vma = find_vma(mm, addr); + if (task_size - len >= addr && + (!vma || addr + len <= vma->vm_start)) + return addr; + } + if (mm->get_unmapped_area == arch_get_unmapped_area) + return hugetlb_get_unmapped_area_bottomup(file, addr, len, + pgoff, flags); + else + return hugetlb_get_unmapped_area_topdown(file, addr, len, + pgoff, flags); +} + +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte = NULL; + + /* We must align the address, because our caller will run + * set_huge_pte_at() on whatever we return, which writes out + * all of the sub-ptes for the hugepage range. So we have + * to give it the first such sub-pte. + */ + addr &= HPAGE_MASK; + + pgd = pgd_offset(mm, addr); + pud = pud_alloc(mm, pgd, addr); + if (pud) { + pmd = pmd_alloc(mm, pud, addr); + if (pmd) + pte = pte_alloc_map(mm, pmd, addr); + } + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte = NULL; + + addr &= HPAGE_MASK; + + pgd = pgd_offset(mm, addr); + if (!pgd_none(*pgd)) { + pud = pud_offset(pgd, addr); + if (!pud_none(*pud)) { + pmd = pmd_offset(pud, addr); + if (!pmd_none(*pmd)) + pte = pte_offset_map(pmd, addr); + } + } + return pte; +} + +int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +{ + return 0; +} + +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t entry) +{ + int i; + + if (!pte_present(*ptep) && pte_present(entry)) + mm->context.huge_pte_count++; + + addr &= HPAGE_MASK; + for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { + set_pte_at(mm, addr, ptep, entry); + ptep++; + addr += PAGE_SIZE; + pte_val(entry) += PAGE_SIZE; + } +} + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_t entry; + int i; + + entry = *ptep; + if (pte_present(entry)) + mm->context.huge_pte_count--; + + addr &= HPAGE_MASK; + + for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) { + pte_clear(mm, addr, ptep); + addr += PAGE_SIZE; + ptep++; + } + + return entry; +} + +struct page *follow_huge_addr(struct mm_struct *mm, + unsigned long address, int write) +{ + return ERR_PTR(-EINVAL); +} + +int pmd_huge(pmd_t pmd) +{ + return 0; +} + +int pud_huge(pud_t pud) +{ + return 0; +} + +struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, + pmd_t *pmd, int write) +{ + return NULL; +} + +static void context_reload(void *__data) +{ + struct mm_struct *mm = __data; + + if (mm == current->mm) + load_secondary_context(mm); +} + +void hugetlb_prefault_arch_hook(struct mm_struct *mm) +{ + struct tsb_config *tp = &mm->context.tsb_block[MM_TSB_HUGE]; + + if (likely(tp->tsb != NULL)) + return; + + tsb_grow(mm, MM_TSB_HUGE, 0); + tsb_context_switch(mm); + smp_tsb_sync(mm); + + /* On UltraSPARC-III+ and later, configure the second half of + * the Data-TLB for huge pages. + */ + if (tlb_type == cheetah_plus) { + unsigned long ctx; + + spin_lock(&ctx_alloc_lock); + ctx = mm->context.sparc64_ctx_val; + ctx &= ~CTX_PGSZ_MASK; + ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT; + ctx |= CTX_PGSZ_HUGE << CTX_PGSZ1_SHIFT; + + if (ctx != mm->context.sparc64_ctx_val) { + /* When changing the page size fields, we + * must perform a context flush so that no + * stale entries match. This flush must + * occur with the original context register + * settings. + */ + do_flush_tlb_mm(mm); + + /* Reload the context register of all processors + * also executing in this address space. + */ + mm->context.sparc64_ctx_val = ctx; + on_each_cpu(context_reload, mm, 0); + } + spin_unlock(&ctx_alloc_lock); + } +} diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c new file mode 100644 index 000000000000..6ea73da29312 --- /dev/null +++ b/arch/sparc/mm/init_64.c @@ -0,0 +1,2360 @@ +/* + * arch/sparc64/mm/init.c + * + * Copyright (C) 1996-1999 David S. Miller (davem@caip.rutgers.edu) + * Copyright (C) 1997-1999 Jakub Jelinek (jj@sunsite.mff.cuni.cz) + */ + +#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 <linux/lmb.h> +#include <linux/mmzone.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/mdesc.h> +#include <asm/cpudata.h> +#include <asm/irq.h> + +#include "init_64.h" + +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 int pavail_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(®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; + +/* 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; +EXPORT_SYMBOL(mem_map_zero); + +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 num_kernel_image_mappings; + +#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" + "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" + "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 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 prom_trans[512] __read_mostly; +unsigned int prom_trans_ents __read_mostly; + +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; +} + +/* Read OBP translations property into 'prom_trans[]'. */ +static void __init read_obp_translations(void) +{ + int n, node, ents, first, last, i; + + node = prom_finddevice("/virtual-memory"); + n = prom_getproplen(node, "translations"); + if (unlikely(n == 0 || n == -1)) { + prom_printf("prom_mappings: Couldn't get size.\n"); + prom_halt(); + } + if (unlikely(n > sizeof(prom_trans))) { + prom_printf("prom_mappings: Size %Zd is too big.\n", n); + prom_halt(); + } + + if ((n = prom_getproperty(node, "translations", + (char *)&prom_trans[0], + sizeof(prom_trans))) == -1) { + prom_printf("prom_mappings: Couldn't get property.\n"); + prom_halt(); + } + + n = n / sizeof(struct linux_prom_translation); + + ents = n; + + sort(prom_trans, ents, sizeof(struct linux_prom_translation), + cmp_ptrans, NULL); + + /* Now kick out all the non-OBP entries. */ + for (i = 0; i < ents; i++) { + if (in_obp_range(prom_trans[i].virt)) + break; + } + first = i; + for (; i < ents; i++) { + if (!in_obp_range(prom_trans[i].virt)) + break; + } + last = i; + + for (i = 0; i < (last - first); i++) { + struct linux_prom_translation *src = &prom_trans[i + first]; + struct linux_prom_translation *dest = &prom_trans[i]; + + *dest = *src; + } + for (; i < ents; i++) { + struct linux_prom_translation *dest = &prom_trans[i]; + dest->virt = dest->size = dest->data = 0x0UL; + } + + prom_trans_ents = last - first; + + if (tlb_type == spitfire) { + /* Clear diag TTE bits. */ + for (i = 0; i < prom_trans_ents; i++) + prom_trans[i].data &= ~0x0003fe0000000000UL; + } +} + +static void __init hypervisor_tlb_lock(unsigned long vaddr, + unsigned long pte, + unsigned long mmu) +{ + 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; + int i, tlb_ent = sparc64_highest_locked_tlbent(); + + tte_vaddr = (unsigned long) KERNBASE; + phys_page = (prom_boot_mapping_phys_low >> 22UL) << 22UL; + tte_data = kern_large_tte(phys_page); + + kern_locked_tte_data = tte_data; + + /* Now lock us into the TLBs via Hypervisor or OBP. */ + if (tlb_type == hypervisor) { + for (i = 0; i < num_kernel_image_mappings; i++) { + hypervisor_tlb_lock(tte_vaddr, tte_data, HV_MMU_DMMU); + hypervisor_tlb_lock(tte_vaddr, tte_data, HV_MMU_IMMU); + tte_vaddr += 0x400000; + tte_data += 0x400000; + } + } else { + for (i = 0; i < num_kernel_image_mappings; i++) { + prom_dtlb_load(tlb_ent - i, tte_data, tte_vaddr); + prom_itlb_load(tlb_ent - i, tte_data, tte_vaddr); + tte_vaddr += 0x400000; + tte_data += 0x400000; + } + sparc64_highest_unlocked_tlb_ent = tlb_ent - i; + } + if (tlb_type == cheetah_plus) { + sparc64_kern_pri_context = (CTX_CHEETAH_PLUS_CTX0 | + CTX_CHEETAH_PLUS_NUC); + sparc64_kern_pri_nuc_bits = CTX_CHEETAH_PLUS_NUC; + sparc64_kern_sec_context = CTX_CHEETAH_PLUS_CTX0; + } +} + + +static void __init inherit_prom_mappings(void) +{ + /* Now fixup OBP's idea about where we really are mapped. */ + printk("Remapping the kernel... "); + remap_kernel(); + printk("done.\n"); +} + +void prom_world(int enter) +{ + if (!enter) + set_fs((mm_segment_t) { get_thread_current_ds() }); + + __asm__ __volatile__("flushw"); +} + +void __flush_dcache_range(unsigned long start, unsigned long end) +{ + unsigned long va; + + if (tlb_type == spitfire) { + int n = 0; + + for (va = start; va < end; va += 32) { + spitfire_put_dcache_tag(va & 0x3fe0, 0x0); + if (++n >= 512) + break; + } + } else if (tlb_type == cheetah || tlb_type == cheetah_plus) { + start = __pa(start); + end = __pa(end); + for (va = start; va < end; va += 32) + __asm__ __volatile__("stxa %%g0, [%0] %1\n\t" + "membar #Sync" + : /* no outputs */ + : "r" (va), + "i" (ASI_DCACHE_INVALIDATE)); + } +} + +/* 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. + * + * We must be careful about boundary cases so that we never + * 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_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) { + int i; + new_ctx = (tlb_context_cache & CTX_VERSION_MASK) + + CTX_FIRST_VERSION; + if (new_ctx == 1) + new_ctx = CTX_FIRST_VERSION; + + /* Don't call memset, for 16 entries that's just + * plain silly... + */ + mmu_context_bmap[0] = 3; + mmu_context_bmap[1] = 0; + mmu_context_bmap[2] = 0; + mmu_context_bmap[3] = 0; + for (i = 4; i < CTX_BMAP_SLOTS; i += 4) { + mmu_context_bmap[i + 0] = 0; + mmu_context_bmap[i + 1] = 0; + mmu_context_bmap[i + 2] = 0; + mmu_context_bmap[i + 3] = 0; + } + new_version = 1; + goto out; + } + } + mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63)); + new_ctx |= (tlb_context_cache & CTX_VERSION_MASK); +out: + tlb_context_cache = new_ctx; + mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits; + spin_unlock_irqrestore(&ctx_alloc_lock, flags); + + if (unlikely(new_version)) + smp_new_mmu_context_version(); +} + +static int numa_enabled = 1; +static int numa_debug; + +static int __init early_numa(char *p) +{ + if (!p) + return 0; + + if (strstr(p, "off")) + numa_enabled = 0; + + if (strstr(p, "debug")) + numa_debug = 1; + + return 0; +} +early_param("numa", early_numa); + +#define numadbg(f, a...) \ +do { if (numa_debug) \ + printk(KERN_INFO f, ## a); \ +} while (0) + +static void __init find_ramdisk(unsigned long phys_base) +{ +#ifdef CONFIG_BLK_DEV_INITRD + if (sparc_ramdisk_image || sparc_ramdisk_image64) { + unsigned long ramdisk_image; + + /* Older versions of the bootloader only supported a + * 32-bit physical address for the ramdisk image + * location, stored at sparc_ramdisk_image. Newer + * SILO versions set sparc_ramdisk_image to zero and + * provide a full 64-bit physical address at + * sparc_ramdisk_image64. + */ + ramdisk_image = sparc_ramdisk_image; + if (!ramdisk_image) + ramdisk_image = sparc_ramdisk_image64; + + /* Another bootloader quirk. The bootloader normalizes + * the physical address to KERNBASE, so we have to + * factor that back out and add in the lowest valid + * physical page address to get the true physical address. + */ + ramdisk_image -= KERNBASE; + ramdisk_image += phys_base; + + numadbg("Found ramdisk at physical address 0x%lx, size %u\n", + ramdisk_image, sparc_ramdisk_size); + + initrd_start = ramdisk_image; + initrd_end = ramdisk_image + sparc_ramdisk_size; + + lmb_reserve(initrd_start, sparc_ramdisk_size); + + initrd_start += PAGE_OFFSET; + initrd_end += PAGE_OFFSET; + } +#endif +} + +struct node_mem_mask { + unsigned long mask; + unsigned long val; + unsigned long bootmem_paddr; +}; +static struct node_mem_mask node_masks[MAX_NUMNODES]; +static int num_node_masks; + +int numa_cpu_lookup_table[NR_CPUS]; +cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES]; + +#ifdef CONFIG_NEED_MULTIPLE_NODES + +struct mdesc_mblock { + u64 base; + u64 size; + u64 offset; /* RA-to-PA */ +}; +static struct mdesc_mblock *mblocks; +static int num_mblocks; + +static unsigned long ra_to_pa(unsigned long addr) +{ + int i; + + for (i = 0; i < num_mblocks; i++) { + struct mdesc_mblock *m = &mblocks[i]; + + if (addr >= m->base && + addr < (m->base + m->size)) { + addr += m->offset; + break; + } + } + return addr; +} + +static int find_node(unsigned long addr) +{ + int i; + + addr = ra_to_pa(addr); + for (i = 0; i < num_node_masks; i++) { + struct node_mem_mask *p = &node_masks[i]; + + if ((addr & p->mask) == p->val) + return i; + } + return -1; +} + +static unsigned long nid_range(unsigned long start, unsigned long end, + int *nid) +{ + *nid = find_node(start); + start += PAGE_SIZE; + while (start < end) { + int n = find_node(start); + + if (n != *nid) + break; + start += PAGE_SIZE; + } + + if (start > end) + start = end; + + return start; +} +#else +static unsigned long nid_range(unsigned long start, unsigned long end, + int *nid) +{ + *nid = 0; + return end; +} +#endif + +/* This must be invoked after performing all of the necessary + * add_active_range() calls for 'nid'. We need to be able to get + * correct data from get_pfn_range_for_nid(). + */ +static void __init allocate_node_data(int nid) +{ + unsigned long paddr, num_pages, start_pfn, end_pfn; + struct pglist_data *p; + +#ifdef CONFIG_NEED_MULTIPLE_NODES + paddr = lmb_alloc_nid(sizeof(struct pglist_data), + SMP_CACHE_BYTES, nid, nid_range); + if (!paddr) { + prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid); + prom_halt(); + } + NODE_DATA(nid) = __va(paddr); + memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); + + NODE_DATA(nid)->bdata = &bootmem_node_data[nid]; +#endif + + p = NODE_DATA(nid); + + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + p->node_start_pfn = start_pfn; + p->node_spanned_pages = end_pfn - start_pfn; + + if (p->node_spanned_pages) { + num_pages = bootmem_bootmap_pages(p->node_spanned_pages); + + paddr = lmb_alloc_nid(num_pages << PAGE_SHIFT, PAGE_SIZE, nid, + nid_range); + if (!paddr) { + prom_printf("Cannot allocate bootmap for nid[%d]\n", + nid); + prom_halt(); + } + node_masks[nid].bootmem_paddr = paddr; + } +} + +static void init_node_masks_nonnuma(void) +{ + int i; + + numadbg("Initializing tables for non-numa.\n"); + + node_masks[0].mask = node_masks[0].val = 0; + num_node_masks = 1; + + for (i = 0; i < NR_CPUS; i++) + numa_cpu_lookup_table[i] = 0; + + numa_cpumask_lookup_table[0] = CPU_MASK_ALL; +} + +#ifdef CONFIG_NEED_MULTIPLE_NODES +struct pglist_data *node_data[MAX_NUMNODES]; + +EXPORT_SYMBOL(numa_cpu_lookup_table); +EXPORT_SYMBOL(numa_cpumask_lookup_table); +EXPORT_SYMBOL(node_data); + +struct mdesc_mlgroup { + u64 node; + u64 latency; + u64 match; + u64 mask; +}; +static struct mdesc_mlgroup *mlgroups; +static int num_mlgroups; + +static int scan_pio_for_cfg_handle(struct mdesc_handle *md, u64 pio, + u32 cfg_handle) +{ + u64 arc; + + mdesc_for_each_arc(arc, md, pio, MDESC_ARC_TYPE_FWD) { + u64 target = mdesc_arc_target(md, arc); + const u64 *val; + + val = mdesc_get_property(md, target, + "cfg-handle", NULL); + if (val && *val == cfg_handle) + return 0; + } + return -ENODEV; +} + +static int scan_arcs_for_cfg_handle(struct mdesc_handle *md, u64 grp, + u32 cfg_handle) +{ + u64 arc, candidate, best_latency = ~(u64)0; + + candidate = MDESC_NODE_NULL; + mdesc_for_each_arc(arc, md, grp, MDESC_ARC_TYPE_FWD) { + u64 target = mdesc_arc_target(md, arc); + const char *name = mdesc_node_name(md, target); + const u64 *val; + + if (strcmp(name, "pio-latency-group")) + continue; + + val = mdesc_get_property(md, target, "latency", NULL); + if (!val) + continue; + + if (*val < best_latency) { + candidate = target; + best_latency = *val; + } + } + + if (candidate == MDESC_NODE_NULL) + return -ENODEV; + + return scan_pio_for_cfg_handle(md, candidate, cfg_handle); +} + +int of_node_to_nid(struct device_node *dp) +{ + const struct linux_prom64_registers *regs; + struct mdesc_handle *md; + u32 cfg_handle; + int count, nid; + u64 grp; + + /* This is the right thing to do on currently supported + * SUN4U NUMA platforms as well, as the PCI controller does + * not sit behind any particular memory controller. + */ + if (!mlgroups) + return -1; + + regs = of_get_property(dp, "reg", NULL); + if (!regs) + return -1; + + cfg_handle = (regs->phys_addr >> 32UL) & 0x0fffffff; + + md = mdesc_grab(); + + count = 0; + nid = -1; + mdesc_for_each_node_by_name(md, grp, "group") { + if (!scan_arcs_for_cfg_handle(md, grp, cfg_handle)) { + nid = count; + break; + } + count++; + } + + mdesc_release(md); + + return nid; +} + +static void add_node_ranges(void) +{ + int i; + + for (i = 0; i < lmb.memory.cnt; i++) { + unsigned long size = lmb_size_bytes(&lmb.memory, i); + unsigned long start, end; + + start = lmb.memory.region[i].base; + end = start + size; + while (start < end) { + unsigned long this_end; + int nid; + + this_end = nid_range(start, end, &nid); + + numadbg("Adding active range nid[%d] " + "start[%lx] end[%lx]\n", + nid, start, this_end); + + add_active_range(nid, + start >> PAGE_SHIFT, + this_end >> PAGE_SHIFT); + + start = this_end; + } + } +} + +static int __init grab_mlgroups(struct mdesc_handle *md) +{ + unsigned long paddr; + int count = 0; + u64 node; + + mdesc_for_each_node_by_name(md, node, "memory-latency-group") + count++; + if (!count) + return -ENOENT; + + paddr = lmb_alloc(count * sizeof(struct mdesc_mlgroup), + SMP_CACHE_BYTES); + if (!paddr) + return -ENOMEM; + + mlgroups = __va(paddr); + num_mlgroups = count; + + count = 0; + mdesc_for_each_node_by_name(md, node, "memory-latency-group") { + struct mdesc_mlgroup *m = &mlgroups[count++]; + const u64 *val; + + m->node = node; + + val = mdesc_get_property(md, node, "latency", NULL); + m->latency = *val; + val = mdesc_get_property(md, node, "address-match", NULL); + m->match = *val; + val = mdesc_get_property(md, node, "address-mask", NULL); + m->mask = *val; + + numadbg("MLGROUP[%d]: node[%lx] latency[%lx] " + "match[%lx] mask[%lx]\n", + count - 1, m->node, m->latency, m->match, m->mask); + } + + return 0; +} + +static int __init grab_mblocks(struct mdesc_handle *md) +{ + unsigned long paddr; + int count = 0; + u64 node; + + mdesc_for_each_node_by_name(md, node, "mblock") + count++; + if (!count) + return -ENOENT; + + paddr = lmb_alloc(count * sizeof(struct mdesc_mblock), + SMP_CACHE_BYTES); + if (!paddr) + return -ENOMEM; + + mblocks = __va(paddr); + num_mblocks = count; + + count = 0; + mdesc_for_each_node_by_name(md, node, "mblock") { + struct mdesc_mblock *m = &mblocks[count++]; + const u64 *val; + + val = mdesc_get_property(md, node, "base", NULL); + m->base = *val; + val = mdesc_get_property(md, node, "size", NULL); + m->size = *val; + val = mdesc_get_property(md, node, + "address-congruence-offset", NULL); + m->offset = *val; + + numadbg("MBLOCK[%d]: base[%lx] size[%lx] offset[%lx]\n", + count - 1, m->base, m->size, m->offset); + } + + return 0; +} + +static void __init numa_parse_mdesc_group_cpus(struct mdesc_handle *md, + u64 grp, cpumask_t *mask) +{ + u64 arc; + + cpus_clear(*mask); + + mdesc_for_each_arc(arc, md, grp, MDESC_ARC_TYPE_BACK) { + u64 target = mdesc_arc_target(md, arc); + const char *name = mdesc_node_name(md, target); + const u64 *id; + + if (strcmp(name, "cpu")) + continue; + id = mdesc_get_property(md, target, "id", NULL); + if (*id < NR_CPUS) + cpu_set(*id, *mask); + } +} + +static struct mdesc_mlgroup * __init find_mlgroup(u64 node) +{ + int i; + + for (i = 0; i < num_mlgroups; i++) { + struct mdesc_mlgroup *m = &mlgroups[i]; + if (m->node == node) + return m; + } + return NULL; +} + +static int __init numa_attach_mlgroup(struct mdesc_handle *md, u64 grp, + int index) +{ + struct mdesc_mlgroup *candidate = NULL; + u64 arc, best_latency = ~(u64)0; + struct node_mem_mask *n; + + mdesc_for_each_arc(arc, md, grp, MDESC_ARC_TYPE_FWD) { + u64 target = mdesc_arc_target(md, arc); + struct mdesc_mlgroup *m = find_mlgroup(target); + if (!m) + continue; + if (m->latency < best_latency) { + candidate = m; + best_latency = m->latency; + } + } + if (!candidate) + return -ENOENT; + + if (num_node_masks != index) { + printk(KERN_ERR "Inconsistent NUMA state, " + "index[%d] != num_node_masks[%d]\n", + index, num_node_masks); + return -EINVAL; + } + + n = &node_masks[num_node_masks++]; + + n->mask = candidate->mask; + n->val = candidate->match; + + numadbg("NUMA NODE[%d]: mask[%lx] val[%lx] (latency[%lx])\n", + index, n->mask, n->val, candidate->latency); + + return 0; +} + +static int __init numa_parse_mdesc_group(struct mdesc_handle *md, u64 grp, + int index) +{ + cpumask_t mask; + int cpu; + + numa_parse_mdesc_group_cpus(md, grp, &mask); + + for_each_cpu_mask(cpu, mask) + numa_cpu_lookup_table[cpu] = index; + numa_cpumask_lookup_table[index] = mask; + + if (numa_debug) { + printk(KERN_INFO "NUMA GROUP[%d]: cpus [ ", index); + for_each_cpu_mask(cpu, mask) + printk("%d ", cpu); + printk("]\n"); + } + + return numa_attach_mlgroup(md, grp, index); +} + +static int __init numa_parse_mdesc(void) +{ + struct mdesc_handle *md = mdesc_grab(); + int i, err, count; + u64 node; + + node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups"); + if (node == MDESC_NODE_NULL) { + mdesc_release(md); + return -ENOENT; + } + + err = grab_mblocks(md); + if (err < 0) + goto out; + + err = grab_mlgroups(md); + if (err < 0) + goto out; + + count = 0; + mdesc_for_each_node_by_name(md, node, "group") { + err = numa_parse_mdesc_group(md, node, count); + if (err < 0) + break; + count++; + } + + add_node_ranges(); + + for (i = 0; i < num_node_masks; i++) { + allocate_node_data(i); + node_set_online(i); + } + + err = 0; +out: + mdesc_release(md); + return err; +} + +static int __init numa_parse_jbus(void) +{ + unsigned long cpu, index; + + /* NUMA node id is encoded in bits 36 and higher, and there is + * a 1-to-1 mapping from CPU ID to NUMA node ID. + */ + index = 0; + for_each_present_cpu(cpu) { + numa_cpu_lookup_table[cpu] = index; + numa_cpumask_lookup_table[index] = cpumask_of_cpu(cpu); + node_masks[index].mask = ~((1UL << 36UL) - 1UL); + node_masks[index].val = cpu << 36UL; + + index++; + } + num_node_masks = index; + + add_node_ranges(); + + for (index = 0; index < num_node_masks; index++) { + allocate_node_data(index); + node_set_online(index); + } + + return 0; +} + +static int __init numa_parse_sun4u(void) +{ + if (tlb_type == cheetah || tlb_type == cheetah_plus) { + unsigned long ver; + + __asm__ ("rdpr %%ver, %0" : "=r" (ver)); + if ((ver >> 32UL) == __JALAPENO_ID || + (ver >> 32UL) == __SERRANO_ID) + return numa_parse_jbus(); + } + return -1; +} + +static int __init bootmem_init_numa(void) +{ + int err = -1; + + numadbg("bootmem_init_numa()\n"); + + if (numa_enabled) { + if (tlb_type == hypervisor) + err = numa_parse_mdesc(); + else + err = numa_parse_sun4u(); + } + return err; +} + +#else + +static int bootmem_init_numa(void) +{ + return -1; +} + +#endif + +static void __init bootmem_init_nonnuma(void) +{ + unsigned long top_of_ram = lmb_end_of_DRAM(); + unsigned long total_ram = lmb_phys_mem_size(); + unsigned int i; + + numadbg("bootmem_init_nonnuma()\n"); + + printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n", + top_of_ram, total_ram); + printk(KERN_INFO "Memory hole size: %ldMB\n", + (top_of_ram - total_ram) >> 20); + + init_node_masks_nonnuma(); + + for (i = 0; i < lmb.memory.cnt; i++) { + unsigned long size = lmb_size_bytes(&lmb.memory, i); + unsigned long start_pfn, end_pfn; + + if (!size) + continue; + + start_pfn = lmb.memory.region[i].base >> PAGE_SHIFT; + end_pfn = start_pfn + lmb_size_pages(&lmb.memory, i); + add_active_range(0, start_pfn, end_pfn); + } + + allocate_node_data(0); + + node_set_online(0); +} + +static void __init reserve_range_in_node(int nid, unsigned long start, + unsigned long end) +{ + numadbg(" reserve_range_in_node(nid[%d],start[%lx],end[%lx]\n", + nid, start, end); + while (start < end) { + unsigned long this_end; + int n; + + this_end = nid_range(start, end, &n); + if (n == nid) { + numadbg(" MATCH reserving range [%lx:%lx]\n", + start, this_end); + reserve_bootmem_node(NODE_DATA(nid), start, + (this_end - start), BOOTMEM_DEFAULT); + } else + numadbg(" NO MATCH, advancing start to %lx\n", + this_end); + + start = this_end; + } +} + +static void __init trim_reserved_in_node(int nid) +{ + int i; + + numadbg(" trim_reserved_in_node(%d)\n", nid); + + for (i = 0; i < lmb.reserved.cnt; i++) { + unsigned long start = lmb.reserved.region[i].base; + unsigned long size = lmb_size_bytes(&lmb.reserved, i); + unsigned long end = start + size; + + reserve_range_in_node(nid, start, end); + } +} + +static void __init bootmem_init_one_node(int nid) +{ + struct pglist_data *p; + + numadbg("bootmem_init_one_node(%d)\n", nid); + + p = NODE_DATA(nid); + + if (p->node_spanned_pages) { + unsigned long paddr = node_masks[nid].bootmem_paddr; + unsigned long end_pfn; + + end_pfn = p->node_start_pfn + p->node_spanned_pages; + + numadbg(" init_bootmem_node(%d, %lx, %lx, %lx)\n", + nid, paddr >> PAGE_SHIFT, p->node_start_pfn, end_pfn); + + init_bootmem_node(p, paddr >> PAGE_SHIFT, + p->node_start_pfn, end_pfn); + + numadbg(" free_bootmem_with_active_regions(%d, %lx)\n", + nid, end_pfn); + free_bootmem_with_active_regions(nid, end_pfn); + + trim_reserved_in_node(nid); + + numadbg(" sparse_memory_present_with_active_regions(%d)\n", + nid); + sparse_memory_present_with_active_regions(nid); + } +} + +static unsigned long __init bootmem_init(unsigned long phys_base) +{ + unsigned long end_pfn; + int nid; + + end_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT; + max_pfn = max_low_pfn = end_pfn; + min_low_pfn = (phys_base >> PAGE_SHIFT); + + if (bootmem_init_numa() < 0) + bootmem_init_nonnuma(); + + /* XXX cpu notifier XXX */ + + for_each_online_node(nid) + bootmem_init_one_node(nid); + + 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 __ref kernel_map_range(unsigned long pstart, + unsigned long pend, pgprot_t prot) +{ + unsigned long vstart = PAGE_OFFSET + pstart; + unsigned long vend = PAGE_OFFSET + pend; + unsigned long alloc_bytes = 0UL; + + if ((vstart & ~PAGE_MASK) || (vend & ~PAGE_MASK)) { + prom_printf("kernel_map: Unaligned physmem[%lx:%lx]\n", + vstart, vend); + prom_halt(); + } + + while (vstart < vend) { + unsigned long this_end, paddr = __pa(vstart); + pgd_t *pgd = pgd_offset_k(vstart); + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pud = pud_offset(pgd, vstart); + if (pud_none(*pud)) { + pmd_t *new; + + new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + alloc_bytes += PAGE_SIZE; + pud_populate(&init_mm, pud, new); + } + + pmd = pmd_offset(pud, vstart); + if (!pmd_present(*pmd)) { + pte_t *new; + + new = __alloc_bootmem(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); + alloc_bytes += PAGE_SIZE; + pmd_populate_kernel(&init_mm, pmd, new); + } + + pte = pte_offset_kernel(pmd, vstart); + this_end = (vstart + PMD_SIZE) & PMD_MASK; + if (this_end > vend) + this_end = vend; + + while (vstart < this_end) { + pte_val(*pte) = (paddr | pgprot_val(prot)); + + vstart += PAGE_SIZE; + paddr += PAGE_SIZE; + pte++; + } + } + + return alloc_bytes; +} + +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 init_kpte_bitmap(void) +{ + unsigned long i; + + for (i = 0; i < pall_ents; i++) { + unsigned long phys_start, phys_end; + + phys_start = pall[i].phys_addr; + phys_end = phys_start + pall[i].reg_size; + + mark_kpte_bitmap(phys_start, phys_end); + } +} + +static void __init kernel_physical_mapping_init(void) +{ +#ifdef CONFIG_DEBUG_PAGEALLOC + unsigned long i, mem_alloced = 0UL; + + for (i = 0; i < pall_ents; i++) { + unsigned long phys_start, phys_end; + + phys_start = pall[i].phys_addr; + phys_end = phys_start + pall[i].reg_size; + + mem_alloced += kernel_map_range(phys_start, phys_end, + PAGE_KERNEL); + } + + printk("Allocated %ld bytes for kernel page tables.\n", + mem_alloced); + + kvmap_linear_patch[0] = 0x01000000; /* nop */ + 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; + unsigned long phys_end = phys_start + (numpages * PAGE_SIZE); + + kernel_map_range(phys_start, phys_end, + (enable ? PAGE_KERNEL : __pgprot(0))); + + flush_tsb_kernel_range(PAGE_OFFSET + phys_start, + PAGE_OFFSET + phys_end); + + /* we should perform an IPI and flush all tlbs, + * but that can deadlock->flush only current cpu. + */ + __flush_tlb_kernel_range(PAGE_OFFSET + phys_start, + PAGE_OFFSET + phys_end); +} +#endif + +unsigned long __init find_ecache_flush_span(unsigned long size) +{ + int i; + + for (i = 0; i < pavail_ents; i++) { + if (pavail[i].reg_size >= size) + return pavail[i].phys_addr; + } + + return ~0UL; +} + +static void __init tsb_phys_patch(void) +{ + struct tsb_ldquad_phys_patch_entry *pquad; + struct tsb_phys_patch_entry *p; + + pquad = &__tsb_ldquad_phys_patch; + while (pquad < &__tsb_ldquad_phys_patch_end) { + unsigned long addr = pquad->addr; + + if (tlb_type == hypervisor) + *(unsigned int *) addr = pquad->sun4v_insn; + else + *(unsigned int *) addr = pquad->sun4u_insn; + wmb(); + __asm__ __volatile__("flush %0" + : /* no outputs */ + : "r" (addr)); + + pquad++; + } + + p = &__tsb_phys_patch; + while (p < &__tsb_phys_patch_end) { + unsigned long addr = p->addr; + + *(unsigned int *) addr = p->insn; + wmb(); + __asm__ __volatile__("flush %0" + : /* no outputs */ + : "r" (addr)); + + p++; + } +} + +/* 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 */ + +static unsigned long last_valid_pfn; +pgd_t swapper_pg_dir[2048]; + +static void sun4u_pgprot_init(void); +static void sun4v_pgprot_init(void); + +/* Dummy function */ +void __init setup_per_cpu_areas(void) +{ +} + +void __init paging_init(void) +{ + unsigned long end_pfn, 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. + */ + + /* + * Page flags must not reach into upper 32 bits that are used + * for the cpu number + */ + BUILD_BUG_ON(NR_PAGEFLAGS > 32); + + /* + * The bit fields placed in the high range must not reach below + * the 32 bit boundary. Otherwise we cannot place the cpu field + * at the 32 bit boundary. + */ + BUILD_BUG_ON(SECTIONS_WIDTH + NODES_WIDTH + ZONES_WIDTH + + ilog2(roundup_pow_of_two(NR_CPUS)) > 32); + + BUILD_BUG_ON(NR_CPUS > 4096); + + kern_base = (prom_boot_mapping_phys_low >> 22UL) << 22UL; + kern_size = (unsigned long)&_end - (unsigned long)KERNBASE; + + /* 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) { + sun4v_patch_tlb_handlers(); + sun4v_ktsb_init(); + } + + lmb_init(); + + /* Find available physical memory... + * + * Read it twice in order to work around a bug in openfirmware. + * The call to grab this table itself can cause openfirmware to + * allocate memory, which in turn can take away some space from + * the list of available memory. Reading it twice makes sure + * we really do get the final value. + */ + read_obp_translations(); + read_obp_memory("reg", &pall[0], &pall_ents); + read_obp_memory("available", &pavail[0], &pavail_ents); + read_obp_memory("available", &pavail[0], &pavail_ents); + + phys_base = 0xffffffffffffffffUL; + for (i = 0; i < pavail_ents; i++) { + phys_base = min(phys_base, pavail[i].phys_addr); + lmb_add(pavail[i].phys_addr, pavail[i].reg_size); + } + + lmb_reserve(kern_base, kern_size); + + find_ramdisk(phys_base); + + lmb_enforce_memory_limit(cmdline_memory_size); + + lmb_analyze(); + lmb_dump_all(); + + set_bit(0, mmu_context_bmap); + + shift = kern_base + PAGE_OFFSET - ((unsigned long)KERNBASE); + + real_end = (unsigned long)_end; + num_kernel_image_mappings = DIV_ROUND_UP(real_end - KERNBASE, 1 << 22); + printk("Kernel: Using %d locked TLB entries for main kernel image.\n", + num_kernel_image_mappings); + + /* Set kernel pgd to upper alias so physical page computations + * work. + */ + init_mm.pgd += ((shift) / (sizeof(pgd_t))); + + memset(swapper_low_pmd_dir, 0, sizeof(swapper_low_pmd_dir)); + + /* Now can init the kernel/bad page tables. */ + pud_set(pud_offset(&swapper_pg_dir[0], 0), + swapper_low_pmd_dir + (shift / sizeof(pgd_t))); + + inherit_prom_mappings(); + + init_kpte_bitmap(); + + /* Ok, we can use our TLB miss and window trap handlers safely. */ + setup_tba(); + + __flush_tlb_all(); + + if (tlb_type == hypervisor) + sun4v_ktsb_register(); + + /* We must setup the per-cpu areas before we pull in the + * PROM and the MDESC. The code there fills in cpu and + * other information into per-cpu data structures. + */ + real_setup_per_cpu_areas(); + + prom_build_devicetree(); + + if (tlb_type == hypervisor) + sun4v_mdesc_init(); + + /* Once the OF device tree and MDESC have been setup, we know + * the list of possible cpus. Therefore we can allocate the + * IRQ stacks. + */ + for_each_possible_cpu(i) { + /* XXX Use node local allocations... XXX */ + softirq_stack[i] = __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + hardirq_stack[i] = __va(lmb_alloc(THREAD_SIZE, THREAD_SIZE)); + } + + /* Setup bootmem... */ + last_valid_pfn = end_pfn = bootmem_init(phys_base); + +#ifndef CONFIG_NEED_MULTIPLE_NODES + max_mapnr = last_valid_pfn; +#endif + kernel_physical_mapping_init(); + + { + unsigned long max_zone_pfns[MAX_NR_ZONES]; + + memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); + + max_zone_pfns[ZONE_NORMAL] = end_pfn; + + free_area_init_nodes(max_zone_pfns); + } + + printk("Booting Linux...\n"); +} + +int __init page_in_phys_avail(unsigned long paddr) +{ + int i; + + paddr &= PAGE_MASK; + + for (i = 0; i < pavail_ents; i++) { + unsigned long start, end; + + start = pavail[i].phys_addr; + end = start + pavail[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; +} + +static struct linux_prom64_registers pavail_rescan[MAX_BANKS] __initdata; +static int pavail_rescan_ents __initdata; + +/* Certain OBP calls, such as fetching "available" properties, can + * claim physical memory. So, along with initializing the valid + * address bitmap, what we do here is refetch the physical available + * memory list again, and make sure it provides at least as much + * memory as 'pavail' does. + */ +static void __init setup_valid_addr_bitmap_from_pavail(void) +{ + int i; + + read_obp_memory("available", &pavail_rescan[0], &pavail_rescan_ents); + + for (i = 0; i < pavail_ents; i++) { + unsigned long old_start, old_end; + + old_start = pavail[i].phys_addr; + old_end = old_start + pavail[i].reg_size; + while (old_start < old_end) { + int n; + + for (n = 0; n < pavail_rescan_ents; n++) { + unsigned long new_start, new_end; + + new_start = pavail_rescan[n].phys_addr; + new_end = new_start + + pavail_rescan[n].reg_size; + + if (new_start <= old_start && + new_end >= (old_start + PAGE_SIZE)) { + set_bit(old_start >> 22, + sparc64_valid_addr_bitmap); + goto do_next_page; + } + } + + prom_printf("mem_init: Lost memory in pavail\n"); + prom_printf("mem_init: OLD start[%lx] size[%lx]\n", + pavail[i].phys_addr, + pavail[i].reg_size); + prom_printf("mem_init: NEW start[%lx] size[%lx]\n", + pavail_rescan[i].phys_addr, + pavail_rescan[i].reg_size); + prom_printf("mem_init: Cannot continue, aborting.\n"); + prom_halt(); + + do_next_page: + old_start += PAGE_SIZE; + } + } +} + +void __init mem_init(void) +{ + unsigned long codepages, datapages, initpages; + unsigned long addr, last; + int i; + + i = last_valid_pfn >> ((22 - PAGE_SHIFT) + 6); + i += 1; + sparc64_valid_addr_bitmap = (unsigned long *) alloc_bootmem(i << 3); + if (sparc64_valid_addr_bitmap == NULL) { + prom_printf("mem_init: Cannot alloc valid_addr_bitmap.\n"); + prom_halt(); + } + memset(sparc64_valid_addr_bitmap, 0, i << 3); + + addr = PAGE_OFFSET + kern_base; + last = PAGE_ALIGN(kern_size) + addr; + while (addr < last) { + set_bit(__pa(addr) >> 22, sparc64_valid_addr_bitmap); + addr += PAGE_SIZE; + } + + setup_valid_addr_bitmap_from_pavail(); + + high_memory = __va(last_valid_pfn << PAGE_SHIFT); + +#ifdef CONFIG_NEED_MULTIPLE_NODES + for_each_online_node(i) { + if (NODE_DATA(i)->node_spanned_pages != 0) { + totalram_pages += + free_all_bootmem_node(NODE_DATA(i)); + } + } +#else + totalram_pages = free_all_bootmem(); +#endif + + /* We subtract one to account for the mem_map_zero page + * allocated below. + */ + totalram_pages -= 1; + num_physpages = totalram_pages; + + /* + * Set up the zero page, mark it reserved, so that page count + * is not manipulated when freeing the page from user ptes. + */ + mem_map_zero = alloc_pages(GFP_KERNEL|__GFP_ZERO, 0); + if (mem_map_zero == NULL) { + prom_printf("paging_init: Cannot alloc zero page.\n"); + prom_halt(); + } + SetPageReserved(mem_map_zero); + + codepages = (((unsigned long) _etext) - ((unsigned long) _start)); + codepages = PAGE_ALIGN(codepages) >> PAGE_SHIFT; + datapages = (((unsigned long) _edata) - ((unsigned long) _etext)); + datapages = PAGE_ALIGN(datapages) >> PAGE_SHIFT; + initpages = (((unsigned long) __init_end) - ((unsigned long) __init_begin)); + initpages = PAGE_ALIGN(initpages) >> PAGE_SHIFT; + + 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), + initpages << (PAGE_SHIFT-10), + PAGE_OFFSET, (last_valid_pfn << PAGE_SHIFT)); + + if (tlb_type == cheetah || tlb_type == cheetah_plus) + cheetah_ecache_flush_init(); +} + +void free_initmem(void) +{ + unsigned long addr, initend; + int do_free = 1; + + /* If the physical memory maps were trimmed by kernel command + * line options, don't even try freeing this initmem stuff up. + * The kernel image could have been in the trimmed out region + * and if so the freeing below will free invalid page structs. + */ + if (cmdline_memory_size) + do_free = 0; + + /* + * The init section is aligned to 8k in vmlinux.lds. Page align for >8k pagesizes. + */ + addr = PAGE_ALIGN((unsigned long)(__init_begin)); + initend = (unsigned long)(__init_end) & PAGE_MASK; + for (; addr < initend; addr += PAGE_SIZE) { + unsigned long page; + struct page *p; + + page = (addr + + ((unsigned long) __va(kern_base)) - + ((unsigned long) KERNBASE)); + memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE); + + if (do_free) { + p = virt_to_page(page); + + ClearPageReserved(p); + init_page_count(p); + __free_page(p); + num_physpages++; + totalram_pages++; + } + } +} + +#ifdef CONFIG_BLK_DEV_INITRD +void free_initrd_mem(unsigned long start, unsigned long end) +{ + if (start < end) + printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10); + for (; start < end; start += PAGE_SIZE) { + struct page *p = virt_to_page(start); + + ClearPageReserved(p); + 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); + +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); + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +unsigned long vmemmap_table[VMEMMAP_SIZE]; + +int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) +{ + unsigned long vstart = (unsigned long) start; + unsigned long vend = (unsigned long) (start + nr); + unsigned long phys_start = (vstart - VMEMMAP_BASE); + unsigned long phys_end = (vend - VMEMMAP_BASE); + unsigned long addr = phys_start & VMEMMAP_CHUNK_MASK; + unsigned long end = VMEMMAP_ALIGN(phys_end); + unsigned long pte_base; + + pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4U | + _PAGE_CP_4U | _PAGE_CV_4U | + _PAGE_P_4U | _PAGE_W_4U); + if (tlb_type == hypervisor) + pte_base = (_PAGE_VALID | _PAGE_SZ4MB_4V | + _PAGE_CP_4V | _PAGE_CV_4V | + _PAGE_P_4V | _PAGE_W_4V); + + for (; addr < end; addr += VMEMMAP_CHUNK) { + unsigned long *vmem_pp = + vmemmap_table + (addr >> VMEMMAP_CHUNK_SHIFT); + void *block; + + if (!(*vmem_pp & _PAGE_VALID)) { + block = vmemmap_alloc_block(1UL << 22, node); + if (!block) + return -ENOMEM; + + *vmem_pp = pte_base | __pa(block); + + printk(KERN_INFO "[%p-%p] page_structs=%lu " + "node=%d entry=%lu/%lu\n", start, block, nr, + node, + addr >> VMEMMAP_CHUNK_SHIFT, + VMEMMAP_SIZE >> VMEMMAP_CHUNK_SHIFT); + } + } + return 0; +} +#endif /* CONFIG_SPARSEMEM_VMEMMAP */ + +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_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) ^ + 0xfffff80000000000UL; +#else + kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4U) ^ + 0xfffff80000000000UL; +#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_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) ^ + 0xfffff80000000000UL; +#else + kern_linear_pte_xor[0] = (_PAGE_VALID | _PAGE_SZ4MB_4V) ^ + 0xfffff80000000000UL; +#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) ^ + 0xfffff80000000000UL; +#else + kern_linear_pte_xor[1] = (_PAGE_VALID | _PAGE_SZ256MB_4V) ^ + 0xfffff80000000000UL; +#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 == hypervisor) { + sun4v_mmu_demap_all(); + } else 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)); +} diff --git a/arch/sparc/mm/init_64.h b/arch/sparc/mm/init_64.h new file mode 100644 index 000000000000..16063870a489 --- /dev/null +++ b/arch/sparc/mm/init_64.h @@ -0,0 +1,49 @@ +#ifndef _SPARC64_MM_INIT_H +#define _SPARC64_MM_INIT_H + +/* Most of the symbols in this file are defined in init.c and + * marked non-static so that assembler code can get at them. + */ + +#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) + +extern unsigned long kern_linear_pte_xor[2]; +extern unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)]; +extern unsigned int sparc64_highest_unlocked_tlb_ent; +extern unsigned long sparc64_kern_pri_context; +extern unsigned long sparc64_kern_pri_nuc_bits; +extern unsigned long sparc64_kern_sec_context; +extern void mmu_info(struct seq_file *m); + +struct linux_prom_translation { + unsigned long virt; + unsigned long size; + unsigned long data; +}; + +/* Exported for kernel TLB miss handling in ktlb.S */ +extern struct linux_prom_translation prom_trans[512]; +extern unsigned int prom_trans_ents; + +/* Exported for SMP bootup purposes. */ +extern unsigned long kern_locked_tte_data; + +extern void prom_world(int enter); + +extern void free_initmem(void); + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#define VMEMMAP_CHUNK_SHIFT 22 +#define VMEMMAP_CHUNK (1UL << VMEMMAP_CHUNK_SHIFT) +#define VMEMMAP_CHUNK_MASK ~(VMEMMAP_CHUNK - 1UL) +#define VMEMMAP_ALIGN(x) (((x)+VMEMMAP_CHUNK-1UL)&VMEMMAP_CHUNK_MASK) + +#define VMEMMAP_SIZE ((((1UL << MAX_PHYSADDR_BITS) >> PAGE_SHIFT) * \ + sizeof(struct page *)) >> VMEMMAP_CHUNK_SHIFT) +extern unsigned long vmemmap_table[VMEMMAP_SIZE]; +#endif + +#endif /* _SPARC64_MM_INIT_H */ diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c new file mode 100644 index 000000000000..d8f21e24a82f --- /dev/null +++ b/arch/sparc/mm/tlb.c @@ -0,0 +1,97 @@ +/* arch/sparc64/mm/tlb.c + * + * Copyright (C) 2004 David S. Miller <davem@redhat.com> + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/percpu.h> +#include <linux/mm.h> +#include <linux/swap.h> +#include <linux/preempt.h> + +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> +#include <asm/cacheflush.h> +#include <asm/mmu_context.h> +#include <asm/tlb.h> + +/* Heavily inspired by the ppc64 code. */ + +DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); + +void flush_tlb_pending(void) +{ + struct mmu_gather *mp = &get_cpu_var(mmu_gathers); + + if (mp->tlb_nr) { + flush_tsb_user(mp); + + if (CTX_VALID(mp->mm->context)) { +#ifdef CONFIG_SMP + smp_flush_tlb_pending(mp->mm, mp->tlb_nr, + &mp->vaddrs[0]); +#else + __flush_tlb_pending(CTX_HWBITS(mp->mm->context), + mp->tlb_nr, &mp->vaddrs[0]); +#endif + } + mp->tlb_nr = 0; + } + + put_cpu_var(mmu_gathers); +} + +void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr, pte_t *ptep, pte_t orig) +{ + struct mmu_gather *mp = &__get_cpu_var(mmu_gathers); + unsigned long nr; + + vaddr &= PAGE_MASK; + if (pte_exec(orig)) + vaddr |= 0x1UL; + + if (tlb_type != hypervisor && + pte_dirty(orig)) { + unsigned long paddr, pfn = pte_pfn(orig); + struct address_space *mapping; + struct page *page; + + if (!pfn_valid(pfn)) + goto no_cache_flush; + + page = pfn_to_page(pfn); + if (PageReserved(page)) + goto no_cache_flush; + + /* A real file page? */ + mapping = page_mapping(page); + if (!mapping) + goto no_cache_flush; + + paddr = (unsigned long) page_address(page); + if ((paddr ^ vaddr) & (1 << 13)) + flush_dcache_page_all(mm, page); + } + +no_cache_flush: + + if (mp->fullmm) + return; + + nr = mp->tlb_nr; + + if (unlikely(nr != 0 && mm != mp->mm)) { + flush_tlb_pending(); + nr = 0; + } + + if (nr == 0) + mp->mm = mm; + + mp->vaddrs[nr] = vaddr; + mp->tlb_nr = ++nr; + if (nr >= TLB_BATCH_NR) + flush_tlb_pending(); +} diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c new file mode 100644 index 000000000000..f0282fad632a --- /dev/null +++ b/arch/sparc/mm/tsb.c @@ -0,0 +1,496 @@ +/* arch/sparc64/mm/tsb.c + * + * Copyright (C) 2006, 2008 David S. Miller <davem@davemloft.net> + */ + +#include <linux/kernel.h> +#include <linux/preempt.h> +#include <asm/system.h> +#include <asm/page.h> +#include <asm/tlbflush.h> +#include <asm/tlb.h> +#include <asm/mmu_context.h> +#include <asm/pgtable.h> +#include <asm/tsb.h> +#include <asm/oplib.h> + +extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES]; + +static inline unsigned long tsb_hash(unsigned long vaddr, unsigned long hash_shift, unsigned long nentries) +{ + vaddr >>= hash_shift; + return vaddr & (nentries - 1); +} + +static inline int tag_compare(unsigned long tag, unsigned long vaddr) +{ + return (tag == (vaddr >> 22)); +} + +/* TSB flushes need only occur on the processor initiating the address + * space modification, not on each cpu the address space has run on. + * Only the TLB flush needs that treatment. + */ + +void flush_tsb_kernel_range(unsigned long start, unsigned long end) +{ + unsigned long v; + + for (v = start; v < end; v += PAGE_SIZE) { + unsigned long hash = tsb_hash(v, PAGE_SHIFT, + KERNEL_TSB_NENTRIES); + struct tsb *ent = &swapper_tsb[hash]; + + if (tag_compare(ent->tag, v)) + ent->tag = (1UL << TSB_TAG_INVALID_BIT); + } +} + +static void __flush_tsb_one(struct mmu_gather *mp, unsigned long hash_shift, unsigned long tsb, unsigned long nentries) +{ + unsigned long i; + + for (i = 0; i < mp->tlb_nr; i++) { + unsigned long v = mp->vaddrs[i]; + unsigned long tag, ent, hash; + + v &= ~0x1UL; + + hash = tsb_hash(v, hash_shift, nentries); + ent = tsb + (hash * sizeof(struct tsb)); + tag = (v >> 22UL); + + tsb_flush(ent, tag); + } +} + +void flush_tsb_user(struct mmu_gather *mp) +{ + struct mm_struct *mm = mp->mm; + unsigned long nentries, base, flags; + + spin_lock_irqsave(&mm->context.lock, flags); + + base = (unsigned long) mm->context.tsb_block[MM_TSB_BASE].tsb; + nentries = mm->context.tsb_block[MM_TSB_BASE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one(mp, PAGE_SHIFT, base, nentries); + +#ifdef CONFIG_HUGETLB_PAGE + if (mm->context.tsb_block[MM_TSB_HUGE].tsb) { + base = (unsigned long) mm->context.tsb_block[MM_TSB_HUGE].tsb; + nentries = mm->context.tsb_block[MM_TSB_HUGE].tsb_nentries; + if (tlb_type == cheetah_plus || tlb_type == hypervisor) + base = __pa(base); + __flush_tsb_one(mp, HPAGE_SHIFT, base, nentries); + } +#endif + spin_unlock_irqrestore(&mm->context.lock, flags); +} + +#if defined(CONFIG_SPARC64_PAGE_SIZE_8KB) +#define HV_PGSZ_IDX_BASE HV_PGSZ_IDX_8K +#define HV_PGSZ_MASK_BASE HV_PGSZ_MASK_8K +#elif defined(CONFIG_SPARC64_PAGE_SIZE_64KB) +#define HV_PGSZ_IDX_BASE HV_PGSZ_IDX_64K +#define HV_PGSZ_MASK_BASE HV_PGSZ_MASK_64K +#else +#error Broken base page size setting... +#endif + +#ifdef CONFIG_HUGETLB_PAGE +#if defined(CONFIG_HUGETLB_PAGE_SIZE_64K) +#define HV_PGSZ_IDX_HUGE HV_PGSZ_IDX_64K +#define HV_PGSZ_MASK_HUGE HV_PGSZ_MASK_64K +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_512K) +#define HV_PGSZ_IDX_HUGE HV_PGSZ_IDX_512K +#define HV_PGSZ_MASK_HUGE HV_PGSZ_MASK_512K +#elif defined(CONFIG_HUGETLB_PAGE_SIZE_4MB) +#define HV_PGSZ_IDX_HUGE HV_PGSZ_IDX_4MB +#define HV_PGSZ_MASK_HUGE HV_PGSZ_MASK_4MB +#else +#error Broken huge page size setting... +#endif +#endif + +static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsigned long tsb_bytes) +{ + unsigned long tsb_reg, base, tsb_paddr; + unsigned long page_sz, tte; + + mm->context.tsb_block[tsb_idx].tsb_nentries = + tsb_bytes / sizeof(struct tsb); + + base = TSBMAP_BASE; + tte = pgprot_val(PAGE_KERNEL_LOCKED); + tsb_paddr = __pa(mm->context.tsb_block[tsb_idx].tsb); + BUG_ON(tsb_paddr & (tsb_bytes - 1UL)); + + /* Use the smallest page size that can map the whole TSB + * in one TLB entry. + */ + switch (tsb_bytes) { + case 8192 << 0: + tsb_reg = 0x0UL; +#ifdef DCACHE_ALIASING_POSSIBLE + base += (tsb_paddr & 8192); +#endif + page_sz = 8192; + break; + + case 8192 << 1: + tsb_reg = 0x1UL; + page_sz = 64 * 1024; + break; + + case 8192 << 2: + tsb_reg = 0x2UL; + page_sz = 64 * 1024; + break; + + case 8192 << 3: + tsb_reg = 0x3UL; + page_sz = 64 * 1024; + break; + + case 8192 << 4: + tsb_reg = 0x4UL; + page_sz = 512 * 1024; + break; + + case 8192 << 5: + tsb_reg = 0x5UL; + page_sz = 512 * 1024; + break; + + case 8192 << 6: + tsb_reg = 0x6UL; + page_sz = 512 * 1024; + break; + + case 8192 << 7: + tsb_reg = 0x7UL; + page_sz = 4 * 1024 * 1024; + break; + + default: + printk(KERN_ERR "TSB[%s:%d]: Impossible TSB size %lu, killing process.\n", + current->comm, current->pid, tsb_bytes); + do_exit(SIGSEGV); + }; + tte |= pte_sz_bits(page_sz); + + if (tlb_type == cheetah_plus || tlb_type == hypervisor) { + /* Physical mapping, no locked TLB entry for TSB. */ + tsb_reg |= tsb_paddr; + + mm->context.tsb_block[tsb_idx].tsb_reg_val = tsb_reg; + mm->context.tsb_block[tsb_idx].tsb_map_vaddr = 0; + mm->context.tsb_block[tsb_idx].tsb_map_pte = 0; + } else { + tsb_reg |= base; + tsb_reg |= (tsb_paddr & (page_sz - 1UL)); + tte |= (tsb_paddr & ~(page_sz - 1UL)); + + mm->context.tsb_block[tsb_idx].tsb_reg_val = tsb_reg; + mm->context.tsb_block[tsb_idx].tsb_map_vaddr = base; + mm->context.tsb_block[tsb_idx].tsb_map_pte = tte; + } + + /* Setup the Hypervisor TSB descriptor. */ + if (tlb_type == hypervisor) { + struct hv_tsb_descr *hp = &mm->context.tsb_descr[tsb_idx]; + + switch (tsb_idx) { + case MM_TSB_BASE: + hp->pgsz_idx = HV_PGSZ_IDX_BASE; + break; +#ifdef CONFIG_HUGETLB_PAGE + case MM_TSB_HUGE: + hp->pgsz_idx = HV_PGSZ_IDX_HUGE; + break; +#endif + default: + BUG(); + }; + hp->assoc = 1; + hp->num_ttes = tsb_bytes / 16; + hp->ctx_idx = 0; + switch (tsb_idx) { + case MM_TSB_BASE: + hp->pgsz_mask = HV_PGSZ_MASK_BASE; + break; +#ifdef CONFIG_HUGETLB_PAGE + case MM_TSB_HUGE: + hp->pgsz_mask = HV_PGSZ_MASK_HUGE; + break; +#endif + default: + BUG(); + }; + hp->tsb_base = tsb_paddr; + hp->resv = 0; + } +} + +static struct kmem_cache *tsb_caches[8] __read_mostly; + +static const char *tsb_cache_names[8] = { + "tsb_8KB", + "tsb_16KB", + "tsb_32KB", + "tsb_64KB", + "tsb_128KB", + "tsb_256KB", + "tsb_512KB", + "tsb_1MB", +}; + +void __init pgtable_cache_init(void) +{ + unsigned long i; + + for (i = 0; i < 8; i++) { + unsigned long size = 8192 << i; + const char *name = tsb_cache_names[i]; + + tsb_caches[i] = kmem_cache_create(name, + size, size, + 0, NULL); + if (!tsb_caches[i]) { + prom_printf("Could not create %s cache\n", name); + prom_halt(); + } + } +} + +/* When the RSS of an address space exceeds tsb_rss_limit for a TSB, + * do_sparc64_fault() invokes this routine to try and grow it. + * + * When we reach the maximum TSB size supported, we stick ~0UL into + * tsb_rss_limit for that TSB so the grow checks in do_sparc64_fault() + * will not trigger any longer. + * + * The TSB can be anywhere from 8K to 1MB in size, in increasing powers + * of two. The TSB must be aligned to it's size, so f.e. a 512K TSB + * must be 512K aligned. It also must be physically contiguous, so we + * cannot use vmalloc(). + * + * The idea here is to grow the TSB when the RSS of the process approaches + * the number of entries that the current TSB can hold at once. Currently, + * we trigger when the RSS hits 3/4 of the TSB capacity. + */ +void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss) +{ + unsigned long max_tsb_size = 1 * 1024 * 1024; + unsigned long new_size, old_size, flags; + struct tsb *old_tsb, *new_tsb; + unsigned long new_cache_index, old_cache_index; + unsigned long new_rss_limit; + gfp_t gfp_flags; + + if (max_tsb_size > (PAGE_SIZE << MAX_ORDER)) + max_tsb_size = (PAGE_SIZE << MAX_ORDER); + + new_cache_index = 0; + for (new_size = 8192; new_size < max_tsb_size; new_size <<= 1UL) { + unsigned long n_entries = new_size / sizeof(struct tsb); + + n_entries = (n_entries * 3) / 4; + if (n_entries > rss) + break; + + new_cache_index++; + } + + if (new_size == max_tsb_size) + new_rss_limit = ~0UL; + else + new_rss_limit = ((new_size / sizeof(struct tsb)) * 3) / 4; + +retry_tsb_alloc: + gfp_flags = GFP_KERNEL; + if (new_size > (PAGE_SIZE * 2)) + gfp_flags = __GFP_NOWARN | __GFP_NORETRY; + + new_tsb = kmem_cache_alloc_node(tsb_caches[new_cache_index], + gfp_flags, numa_node_id()); + if (unlikely(!new_tsb)) { + /* Not being able to fork due to a high-order TSB + * allocation failure is very bad behavior. Just back + * down to a 0-order allocation and force no TSB + * growing for this address space. + */ + if (mm->context.tsb_block[tsb_index].tsb == NULL && + new_cache_index > 0) { + new_cache_index = 0; + new_size = 8192; + new_rss_limit = ~0UL; + goto retry_tsb_alloc; + } + + /* If we failed on a TSB grow, we are under serious + * memory pressure so don't try to grow any more. + */ + if (mm->context.tsb_block[tsb_index].tsb != NULL) + mm->context.tsb_block[tsb_index].tsb_rss_limit = ~0UL; + return; + } + + /* Mark all tags as invalid. */ + tsb_init(new_tsb, new_size); + + /* Ok, we are about to commit the changes. If we are + * growing an existing TSB the locking is very tricky, + * so WATCH OUT! + * + * We have to hold mm->context.lock while committing to the + * new TSB, this synchronizes us with processors in + * flush_tsb_user() and switch_mm() for this address space. + * + * But even with that lock held, processors run asynchronously + * accessing the old TSB via TLB miss handling. This is OK + * because those actions are just propagating state from the + * Linux page tables into the TSB, page table mappings are not + * being changed. If a real fault occurs, the processor will + * synchronize with us when it hits flush_tsb_user(), this is + * also true for the case where vmscan is modifying the page + * tables. The only thing we need to be careful with is to + * skip any locked TSB entries during copy_tsb(). + * + * When we finish committing to the new TSB, we have to drop + * the lock and ask all other cpus running this address space + * to run tsb_context_switch() to see the new TSB table. + */ + spin_lock_irqsave(&mm->context.lock, flags); + + old_tsb = mm->context.tsb_block[tsb_index].tsb; + old_cache_index = + (mm->context.tsb_block[tsb_index].tsb_reg_val & 0x7UL); + old_size = (mm->context.tsb_block[tsb_index].tsb_nentries * + sizeof(struct tsb)); + + + /* Handle multiple threads trying to grow the TSB at the same time. + * One will get in here first, and bump the size and the RSS limit. + * The others will get in here next and hit this check. + */ + if (unlikely(old_tsb && + (rss < mm->context.tsb_block[tsb_index].tsb_rss_limit))) { + spin_unlock_irqrestore(&mm->context.lock, flags); + + kmem_cache_free(tsb_caches[new_cache_index], new_tsb); + return; + } + + mm->context.tsb_block[tsb_index].tsb_rss_limit = new_rss_limit; + + if (old_tsb) { + extern void copy_tsb(unsigned long old_tsb_base, + unsigned long old_tsb_size, + unsigned long new_tsb_base, + unsigned long new_tsb_size); + unsigned long old_tsb_base = (unsigned long) old_tsb; + unsigned long new_tsb_base = (unsigned long) new_tsb; + + if (tlb_type == cheetah_plus || tlb_type == hypervisor) { + old_tsb_base = __pa(old_tsb_base); + new_tsb_base = __pa(new_tsb_base); + } + copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size); + } + + mm->context.tsb_block[tsb_index].tsb = new_tsb; + setup_tsb_params(mm, tsb_index, new_size); + + spin_unlock_irqrestore(&mm->context.lock, flags); + + /* If old_tsb is NULL, we're being invoked for the first time + * from init_new_context(). + */ + if (old_tsb) { + /* Reload it on the local cpu. */ + tsb_context_switch(mm); + + /* Now force other processors to do the same. */ + preempt_disable(); + smp_tsb_sync(mm); + preempt_enable(); + + /* Now it is safe to free the old tsb. */ + kmem_cache_free(tsb_caches[old_cache_index], old_tsb); + } +} + +int init_new_context(struct task_struct *tsk, struct mm_struct *mm) +{ +#ifdef CONFIG_HUGETLB_PAGE + unsigned long huge_pte_count; +#endif + unsigned int i; + + spin_lock_init(&mm->context.lock); + + mm->context.sparc64_ctx_val = 0UL; + +#ifdef CONFIG_HUGETLB_PAGE + /* We reset it to zero because the fork() page copying + * will re-increment the counters as the parent PTEs are + * copied into the child address space. + */ + huge_pte_count = mm->context.huge_pte_count; + mm->context.huge_pte_count = 0; +#endif + + /* copy_mm() copies over the parent's mm_struct before calling + * us, so we need to zero out the TSB pointer or else tsb_grow() + * will be confused and think there is an older TSB to free up. + */ + for (i = 0; i < MM_NUM_TSBS; i++) + mm->context.tsb_block[i].tsb = NULL; + + /* If this is fork, inherit the parent's TSB size. We would + * grow it to that size on the first page fault anyways. + */ + tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm)); + +#ifdef CONFIG_HUGETLB_PAGE + if (unlikely(huge_pte_count)) + tsb_grow(mm, MM_TSB_HUGE, huge_pte_count); +#endif + + if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb)) + return -ENOMEM; + + return 0; +} + +static void tsb_destroy_one(struct tsb_config *tp) +{ + unsigned long cache_index; + + if (!tp->tsb) + return; + cache_index = tp->tsb_reg_val & 0x7UL; + kmem_cache_free(tsb_caches[cache_index], tp->tsb); + tp->tsb = NULL; + tp->tsb_reg_val = 0UL; +} + +void destroy_context(struct mm_struct *mm) +{ + unsigned long flags, i; + + for (i = 0; i < MM_NUM_TSBS; i++) + tsb_destroy_one(&mm->context.tsb_block[i]); + + spin_lock_irqsave(&ctx_alloc_lock, flags); + + if (CTX_VALID(mm->context)) { + unsigned long nr = CTX_NRBITS(mm->context); + mmu_context_bmap[nr>>6] &= ~(1UL << (nr & 63)); + } + + spin_unlock_irqrestore(&ctx_alloc_lock, flags); +} diff --git a/arch/sparc/mm/ultra.S b/arch/sparc/mm/ultra.S new file mode 100644 index 000000000000..e4c146f7c7e9 --- /dev/null +++ b/arch/sparc/mm/ultra.S @@ -0,0 +1,767 @@ +/* + * ultra.S: Don't expand these all over the place... + * + * Copyright (C) 1997, 2000, 2008 David S. Miller (davem@davemloft.net) + */ + +#include <asm/asi.h> +#include <asm/pgtable.h> +#include <asm/page.h> +#include <asm/spitfire.h> +#include <asm/mmu_context.h> +#include <asm/mmu.h> +#include <asm/pil.h> +#include <asm/head.h> +#include <asm/thread_info.h> +#include <asm/cacheflush.h> +#include <asm/hypervisor.h> +#include <asm/cpudata.h> + + /* Basically, most of the Spitfire vs. Cheetah madness + * has to do with the fact that Cheetah does not support + * IMMU flushes out of the secondary context. Someone needs + * to throw a south lake birthday party for the folks + * in Microelectronics who refused to fix this shit. + */ + + /* This file is meant to be read efficiently by the CPU, not humans. + * Staraj sie tego nikomu nie pierdolnac... + */ + .text + .align 32 + .globl __flush_tlb_mm +__flush_tlb_mm: /* 18 insns */ + /* %o0=(ctx & TAG_CONTEXT_BITS), %o1=SECONDARY_CONTEXT */ + ldxa [%o1] ASI_DMMU, %g2 + cmp %g2, %o0 + bne,pn %icc, __spitfire_flush_tlb_mm_slow + mov 0x50, %g3 + stxa %g0, [%g3] ASI_DMMU_DEMAP + stxa %g0, [%g3] ASI_IMMU_DEMAP + sethi %hi(KERNBASE), %g3 + flush %g3 + retl + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + + .align 32 + .globl __flush_tlb_pending +__flush_tlb_pending: /* 26 insns */ + /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ + rdpr %pstate, %g7 + sllx %o1, 3, %o1 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, %pstate + mov SECONDARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + stxa %o0, [%o4] ASI_DMMU +1: sub %o1, (1 << 3), %o1 + ldx [%o2 + %o1], %o3 + andcc %o3, 1, %g0 + andn %o3, 1, %o3 + be,pn %icc, 2f + or %o3, 0x10, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +2: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + brnz,pt %o1, 1b + nop + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + retl + wrpr %g7, 0x0, %pstate + nop + nop + nop + nop + + .align 32 + .globl __flush_tlb_kernel_range +__flush_tlb_kernel_range: /* 16 insns */ + /* %o0=start, %o1=end */ + cmp %o0, %o1 + be,pn %xcc, 2f + sethi %hi(PAGE_SIZE), %o4 + sub %o1, %o0, %o3 + sub %o3, %o4, %o3 + or %o0, 0x20, %o0 ! Nucleus +1: stxa %g0, [%o0 + %o3] ASI_DMMU_DEMAP + stxa %g0, [%o0 + %o3] ASI_IMMU_DEMAP + membar #Sync + brnz,pt %o3, 1b + sub %o3, %o4, %o3 +2: sethi %hi(KERNBASE), %o3 + flush %o3 + retl + nop + nop + +__spitfire_flush_tlb_mm_slow: + rdpr %pstate, %g1 + wrpr %g1, PSTATE_IE, %pstate + stxa %o0, [%o1] ASI_DMMU + stxa %g0, [%g3] ASI_DMMU_DEMAP + stxa %g0, [%g3] ASI_IMMU_DEMAP + flush %g6 + stxa %g2, [%o1] ASI_DMMU + sethi %hi(KERNBASE), %o1 + flush %o1 + retl + wrpr %g1, 0, %pstate + +/* + * The following code flushes one page_size worth. + */ + .section .kprobes.text, "ax" + .align 32 + .globl __flush_icache_page +__flush_icache_page: /* %o0 = phys_page */ + srlx %o0, PAGE_SHIFT, %o0 + sethi %uhi(PAGE_OFFSET), %g1 + sllx %o0, PAGE_SHIFT, %o0 + sethi %hi(PAGE_SIZE), %g2 + sllx %g1, 32, %g1 + add %o0, %g1, %o0 +1: subcc %g2, 32, %g2 + bne,pt %icc, 1b + flush %o0 + %g2 + retl + nop + +#ifdef DCACHE_ALIASING_POSSIBLE + +#if (PAGE_SHIFT != 13) +#error only page shift of 13 is supported by dcache flush +#endif + +#define DTAG_MASK 0x3 + + /* This routine is Spitfire specific so the hardcoded + * D-cache size and line-size are OK. + */ + .align 64 + .globl __flush_dcache_page +__flush_dcache_page: /* %o0=kaddr, %o1=flush_icache */ + sethi %uhi(PAGE_OFFSET), %g1 + sllx %g1, 32, %g1 + sub %o0, %g1, %o0 ! physical address + srlx %o0, 11, %o0 ! make D-cache TAG + sethi %hi(1 << 14), %o2 ! D-cache size + sub %o2, (1 << 5), %o2 ! D-cache line size +1: ldxa [%o2] ASI_DCACHE_TAG, %o3 ! load D-cache TAG + andcc %o3, DTAG_MASK, %g0 ! Valid? + be,pn %xcc, 2f ! Nope, branch + andn %o3, DTAG_MASK, %o3 ! Clear valid bits + cmp %o3, %o0 ! TAG match? + bne,pt %xcc, 2f ! Nope, branch + nop + stxa %g0, [%o2] ASI_DCACHE_TAG ! Invalidate TAG + membar #Sync +2: brnz,pt %o2, 1b + sub %o2, (1 << 5), %o2 ! D-cache line size + + /* The I-cache does not snoop local stores so we + * better flush that too when necessary. + */ + brnz,pt %o1, __flush_icache_page + sllx %o0, 11, %o0 + retl + nop + +#endif /* DCACHE_ALIASING_POSSIBLE */ + + .previous + + /* Cheetah specific versions, patched at boot time. */ +__cheetah_flush_tlb_mm: /* 19 insns */ + rdpr %pstate, %g7 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, 0x0, %pstate + wrpr %g0, 1, %tl + mov PRIMARY_CONTEXT, %o2 + mov 0x40, %g3 + ldxa [%o2] ASI_DMMU, %g2 + srlx %g2, CTX_PGSZ1_NUC_SHIFT, %o1 + sllx %o1, CTX_PGSZ1_NUC_SHIFT, %o1 + or %o0, %o1, %o0 /* Preserve nucleus page size fields */ + stxa %o0, [%o2] ASI_DMMU + stxa %g0, [%g3] ASI_DMMU_DEMAP + stxa %g0, [%g3] ASI_IMMU_DEMAP + stxa %g2, [%o2] ASI_DMMU + sethi %hi(KERNBASE), %o2 + flush %o2 + wrpr %g0, 0, %tl + retl + wrpr %g7, 0x0, %pstate + +__cheetah_flush_tlb_pending: /* 27 insns */ + /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ + rdpr %pstate, %g7 + sllx %o1, 3, %o1 + andn %g7, PSTATE_IE, %g2 + wrpr %g2, 0x0, %pstate + wrpr %g0, 1, %tl + mov PRIMARY_CONTEXT, %o4 + ldxa [%o4] ASI_DMMU, %g2 + srlx %g2, CTX_PGSZ1_NUC_SHIFT, %o3 + sllx %o3, CTX_PGSZ1_NUC_SHIFT, %o3 + or %o0, %o3, %o0 /* Preserve nucleus page size fields */ + stxa %o0, [%o4] ASI_DMMU +1: sub %o1, (1 << 3), %o1 + ldx [%o2 + %o1], %o3 + andcc %o3, 1, %g0 + be,pn %icc, 2f + andn %o3, 1, %o3 + stxa %g0, [%o3] ASI_IMMU_DEMAP +2: stxa %g0, [%o3] ASI_DMMU_DEMAP + membar #Sync + brnz,pt %o1, 1b + nop + stxa %g2, [%o4] ASI_DMMU + sethi %hi(KERNBASE), %o4 + flush %o4 + wrpr %g0, 0, %tl + retl + wrpr %g7, 0x0, %pstate + +#ifdef DCACHE_ALIASING_POSSIBLE +__cheetah_flush_dcache_page: /* 11 insns */ + sethi %uhi(PAGE_OFFSET), %g1 + sllx %g1, 32, %g1 + sub %o0, %g1, %o0 + sethi %hi(PAGE_SIZE), %o4 +1: subcc %o4, (1 << 5), %o4 + stxa %g0, [%o0 + %o4] ASI_DCACHE_INVALIDATE + membar #Sync + bne,pt %icc, 1b + nop + retl /* I-cache flush never needed on Cheetah, see callers. */ + nop +#endif /* DCACHE_ALIASING_POSSIBLE */ + + /* Hypervisor specific versions, patched at boot time. */ +__hypervisor_tlb_tl0_error: + save %sp, -192, %sp + mov %i0, %o0 + call hypervisor_tlbop_error + mov %i1, %o1 + ret + restore + +__hypervisor_flush_tlb_mm: /* 10 insns */ + mov %o0, %o2 /* ARG2: mmu context */ + mov 0, %o0 /* ARG0: CPU lists unimplemented */ + mov 0, %o1 /* ARG1: CPU lists unimplemented */ + mov HV_MMU_ALL, %o3 /* ARG3: flags */ + mov HV_FAST_MMU_DEMAP_CTX, %o5 + ta HV_FAST_TRAP + brnz,pn %o0, __hypervisor_tlb_tl0_error + mov HV_FAST_MMU_DEMAP_CTX, %o1 + retl + nop + +__hypervisor_flush_tlb_pending: /* 16 insns */ + /* %o0 = context, %o1 = nr, %o2 = vaddrs[] */ + sllx %o1, 3, %g1 + mov %o2, %g2 + mov %o0, %g3 +1: sub %g1, (1 << 3), %g1 + ldx [%g2 + %g1], %o0 /* ARG0: vaddr + IMMU-bit */ + mov %g3, %o1 /* ARG1: mmu context */ + mov HV_MMU_ALL, %o2 /* ARG2: flags */ + srlx %o0, PAGE_SHIFT, %o0 + sllx %o0, PAGE_SHIFT, %o0 + ta HV_MMU_UNMAP_ADDR_TRAP + brnz,pn %o0, __hypervisor_tlb_tl0_error + mov HV_MMU_UNMAP_ADDR_TRAP, %o1 + brnz,pt %g1, 1b + nop + retl + nop + +__hypervisor_flush_tlb_kernel_range: /* 16 insns */ + /* %o0=start, %o1=end */ + cmp %o0, %o1 + be,pn %xcc, 2f + sethi %hi(PAGE_SIZE), %g3 + mov %o0, %g1 + sub %o1, %g1, %g2 + sub %g2, %g3, %g2 +1: add %g1, %g2, %o0 /* ARG0: virtual address */ + mov 0, %o1 /* ARG1: mmu context */ + mov HV_MMU_ALL, %o2 /* ARG2: flags */ + ta HV_MMU_UNMAP_ADDR_TRAP + brnz,pn %o0, __hypervisor_tlb_tl0_error + mov HV_MMU_UNMAP_ADDR_TRAP, %o1 + brnz,pt %g2, 1b + sub %g2, %g3, %g2 +2: retl + nop + +#ifdef DCACHE_ALIASING_POSSIBLE + /* XXX Niagara and friends have an 8K cache, so no aliasing is + * XXX possible, but nothing explicit in the Hypervisor API + * XXX guarantees this. + */ +__hypervisor_flush_dcache_page: /* 2 insns */ + retl + nop +#endif + +tlb_patch_one: +1: lduw [%o1], %g1 + stw %g1, [%o0] + flush %o0 + subcc %o2, 1, %o2 + add %o1, 4, %o1 + bne,pt %icc, 1b + add %o0, 4, %o0 + retl + nop + + .globl cheetah_patch_cachetlbops +cheetah_patch_cachetlbops: + save %sp, -128, %sp + + sethi %hi(__flush_tlb_mm), %o0 + or %o0, %lo(__flush_tlb_mm), %o0 + sethi %hi(__cheetah_flush_tlb_mm), %o1 + or %o1, %lo(__cheetah_flush_tlb_mm), %o1 + call tlb_patch_one + mov 19, %o2 + + sethi %hi(__flush_tlb_pending), %o0 + or %o0, %lo(__flush_tlb_pending), %o0 + sethi %hi(__cheetah_flush_tlb_pending), %o1 + or %o1, %lo(__cheetah_flush_tlb_pending), %o1 + call tlb_patch_one + mov 27, %o2 + +#ifdef DCACHE_ALIASING_POSSIBLE + sethi %hi(__flush_dcache_page), %o0 + or %o0, %lo(__flush_dcache_page), %o0 + sethi %hi(__cheetah_flush_dcache_page), %o1 + or %o1, %lo(__cheetah_flush_dcache_page), %o1 + call tlb_patch_one + mov 11, %o2 +#endif /* DCACHE_ALIASING_POSSIBLE */ + + ret + restore + +#ifdef CONFIG_SMP + /* These are all called by the slaves of a cross call, at + * trap level 1, with interrupts fully disabled. + * + * Register usage: + * %g5 mm->context (all tlb flushes) + * %g1 address arg 1 (tlb page and range flushes) + * %g7 address arg 2 (tlb range flush only) + * + * %g6 scratch 1 + * %g2 scratch 2 + * %g3 scratch 3 + * %g4 scratch 4 + */ + .align 32 + .globl xcall_flush_tlb_mm +xcall_flush_tlb_mm: /* 21 insns */ + mov PRIMARY_CONTEXT, %g2 + ldxa [%g2] ASI_DMMU, %g3 + srlx %g3, CTX_PGSZ1_NUC_SHIFT, %g4 + sllx %g4, CTX_PGSZ1_NUC_SHIFT, %g4 + or %g5, %g4, %g5 /* Preserve nucleus page size fields */ + stxa %g5, [%g2] ASI_DMMU + mov 0x40, %g4 + stxa %g0, [%g4] ASI_DMMU_DEMAP + stxa %g0, [%g4] ASI_IMMU_DEMAP + stxa %g3, [%g2] ASI_DMMU + retry + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + + .globl xcall_flush_tlb_pending +xcall_flush_tlb_pending: /* 21 insns */ + /* %g5=context, %g1=nr, %g7=vaddrs[] */ + sllx %g1, 3, %g1 + mov PRIMARY_CONTEXT, %g4 + ldxa [%g4] ASI_DMMU, %g2 + srlx %g2, CTX_PGSZ1_NUC_SHIFT, %g4 + sllx %g4, CTX_PGSZ1_NUC_SHIFT, %g4 + or %g5, %g4, %g5 + mov PRIMARY_CONTEXT, %g4 + stxa %g5, [%g4] ASI_DMMU +1: sub %g1, (1 << 3), %g1 + ldx [%g7 + %g1], %g5 + andcc %g5, 0x1, %g0 + be,pn %icc, 2f + + andn %g5, 0x1, %g5 + stxa %g0, [%g5] ASI_IMMU_DEMAP +2: stxa %g0, [%g5] ASI_DMMU_DEMAP + membar #Sync + brnz,pt %g1, 1b + nop + stxa %g2, [%g4] ASI_DMMU + retry + nop + + .globl xcall_flush_tlb_kernel_range +xcall_flush_tlb_kernel_range: /* 25 insns */ + sethi %hi(PAGE_SIZE - 1), %g2 + or %g2, %lo(PAGE_SIZE - 1), %g2 + andn %g1, %g2, %g1 + andn %g7, %g2, %g7 + sub %g7, %g1, %g3 + add %g2, 1, %g2 + sub %g3, %g2, %g3 + or %g1, 0x20, %g1 ! Nucleus +1: stxa %g0, [%g1 + %g3] ASI_DMMU_DEMAP + stxa %g0, [%g1 + %g3] ASI_IMMU_DEMAP + membar #Sync + brnz,pt %g3, 1b + sub %g3, %g2, %g3 + retry + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + nop + + /* This runs in a very controlled environment, so we do + * not need to worry about BH races etc. + */ + .globl xcall_sync_tick +xcall_sync_tick: + +661: rdpr %pstate, %g2 + wrpr %g2, PSTATE_IG | PSTATE_AG, %pstate + .section .sun4v_2insn_patch, "ax" + .word 661b + nop + nop + .previous + + rdpr %pil, %g2 + wrpr %g0, 15, %pil + sethi %hi(109f), %g7 + b,pt %xcc, etrap_irq +109: or %g7, %lo(109b), %g7 +#ifdef CONFIG_TRACE_IRQFLAGS + call trace_hardirqs_off + nop +#endif + call smp_synchronize_tick_client + nop + b rtrap_xcall + ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %l1 + + .globl xcall_fetch_glob_regs +xcall_fetch_glob_regs: + sethi %hi(global_reg_snapshot), %g1 + or %g1, %lo(global_reg_snapshot), %g1 + __GET_CPUID(%g2) + sllx %g2, 6, %g3 + add %g1, %g3, %g1 + rdpr %tstate, %g7 + stx %g7, [%g1 + GR_SNAP_TSTATE] + rdpr %tpc, %g7 + stx %g7, [%g1 + GR_SNAP_TPC] + rdpr %tnpc, %g7 + stx %g7, [%g1 + GR_SNAP_TNPC] + stx %o7, [%g1 + GR_SNAP_O7] + stx %i7, [%g1 + GR_SNAP_I7] + /* Don't try this at home kids... */ + rdpr %cwp, %g2 + sub %g2, 1, %g7 + wrpr %g7, %cwp + mov %i7, %g7 + wrpr %g2, %cwp + stx %g7, [%g1 + GR_SNAP_RPC] + sethi %hi(trap_block), %g7 + or %g7, %lo(trap_block), %g7 + sllx %g2, TRAP_BLOCK_SZ_SHIFT, %g2 + add %g7, %g2, %g7 + ldx [%g7 + TRAP_PER_CPU_THREAD], %g3 + stx %g3, [%g1 + GR_SNAP_THREAD] + retry + +#ifdef DCACHE_ALIASING_POSSIBLE + .align 32 + .globl xcall_flush_dcache_page_cheetah +xcall_flush_dcache_page_cheetah: /* %g1 == physical page address */ + sethi %hi(PAGE_SIZE), %g3 +1: subcc %g3, (1 << 5), %g3 + stxa %g0, [%g1 + %g3] ASI_DCACHE_INVALIDATE + membar #Sync + bne,pt %icc, 1b + nop + retry + nop +#endif /* DCACHE_ALIASING_POSSIBLE */ + + .globl xcall_flush_dcache_page_spitfire +xcall_flush_dcache_page_spitfire: /* %g1 == physical page address + %g7 == kernel page virtual address + %g5 == (page->mapping != NULL) */ +#ifdef DCACHE_ALIASING_POSSIBLE + srlx %g1, (13 - 2), %g1 ! Form tag comparitor + sethi %hi(L1DCACHE_SIZE), %g3 ! D$ size == 16K + sub %g3, (1 << 5), %g3 ! D$ linesize == 32 +1: ldxa [%g3] ASI_DCACHE_TAG, %g2 + andcc %g2, 0x3, %g0 + be,pn %xcc, 2f + andn %g2, 0x3, %g2 + cmp %g2, %g1 + + bne,pt %xcc, 2f + nop + stxa %g0, [%g3] ASI_DCACHE_TAG + membar #Sync +2: cmp %g3, 0 + bne,pt %xcc, 1b + sub %g3, (1 << 5), %g3 + + brz,pn %g5, 2f +#endif /* DCACHE_ALIASING_POSSIBLE */ + sethi %hi(PAGE_SIZE), %g3 + +1: flush %g7 + subcc %g3, (1 << 5), %g3 + bne,pt %icc, 1b + add %g7, (1 << 5), %g7 + +2: retry + nop + nop + + /* %g5: error + * %g6: tlb op + */ +__hypervisor_tlb_xcall_error: + mov %g5, %g4 + mov %g6, %g5 + ba,pt %xcc, etrap + rd %pc, %g7 + mov %l4, %o0 + call hypervisor_tlbop_error_xcall + mov %l5, %o1 + ba,a,pt %xcc, rtrap + + .globl __hypervisor_xcall_flush_tlb_mm +__hypervisor_xcall_flush_tlb_mm: /* 21 insns */ + /* %g5=ctx, g1,g2,g3,g4,g7=scratch, %g6=unusable */ + mov %o0, %g2 + mov %o1, %g3 + mov %o2, %g4 + mov %o3, %g1 + mov %o5, %g7 + clr %o0 /* ARG0: CPU lists unimplemented */ + clr %o1 /* ARG1: CPU lists unimplemented */ + mov %g5, %o2 /* ARG2: mmu context */ + mov HV_MMU_ALL, %o3 /* ARG3: flags */ + mov HV_FAST_MMU_DEMAP_CTX, %o5 + ta HV_FAST_TRAP + mov HV_FAST_MMU_DEMAP_CTX, %g6 + brnz,pn %o0, __hypervisor_tlb_xcall_error + mov %o0, %g5 + mov %g2, %o0 + mov %g3, %o1 + mov %g4, %o2 + mov %g1, %o3 + mov %g7, %o5 + membar #Sync + retry + + .globl __hypervisor_xcall_flush_tlb_pending +__hypervisor_xcall_flush_tlb_pending: /* 21 insns */ + /* %g5=ctx, %g1=nr, %g7=vaddrs[], %g2,%g3,%g4,g6=scratch */ + sllx %g1, 3, %g1 + mov %o0, %g2 + mov %o1, %g3 + mov %o2, %g4 +1: sub %g1, (1 << 3), %g1 + ldx [%g7 + %g1], %o0 /* ARG0: virtual address */ + mov %g5, %o1 /* ARG1: mmu context */ + mov HV_MMU_ALL, %o2 /* ARG2: flags */ + srlx %o0, PAGE_SHIFT, %o0 + sllx %o0, PAGE_SHIFT, %o0 + ta HV_MMU_UNMAP_ADDR_TRAP + mov HV_MMU_UNMAP_ADDR_TRAP, %g6 + brnz,a,pn %o0, __hypervisor_tlb_xcall_error + mov %o0, %g5 + brnz,pt %g1, 1b + nop + mov %g2, %o0 + mov %g3, %o1 + mov %g4, %o2 + membar #Sync + retry + + .globl __hypervisor_xcall_flush_tlb_kernel_range +__hypervisor_xcall_flush_tlb_kernel_range: /* 25 insns */ + /* %g1=start, %g7=end, g2,g3,g4,g5,g6=scratch */ + sethi %hi(PAGE_SIZE - 1), %g2 + or %g2, %lo(PAGE_SIZE - 1), %g2 + andn %g1, %g2, %g1 + andn %g7, %g2, %g7 + sub %g7, %g1, %g3 + add %g2, 1, %g2 + sub %g3, %g2, %g3 + mov %o0, %g2 + mov %o1, %g4 + mov %o2, %g7 +1: add %g1, %g3, %o0 /* ARG0: virtual address */ + mov 0, %o1 /* ARG1: mmu context */ + mov HV_MMU_ALL, %o2 /* ARG2: flags */ + ta HV_MMU_UNMAP_ADDR_TRAP + mov HV_MMU_UNMAP_ADDR_TRAP, %g6 + brnz,pn %o0, __hypervisor_tlb_xcall_error + mov %o0, %g5 + sethi %hi(PAGE_SIZE), %o2 + brnz,pt %g3, 1b + sub %g3, %o2, %g3 + mov %g2, %o0 + mov %g4, %o1 + mov %g7, %o2 + membar #Sync + retry + + /* These just get rescheduled to PIL vectors. */ + .globl xcall_call_function +xcall_call_function: + wr %g0, (1 << PIL_SMP_CALL_FUNC), %set_softint + retry + + .globl xcall_call_function_single +xcall_call_function_single: + wr %g0, (1 << PIL_SMP_CALL_FUNC_SNGL), %set_softint + retry + + .globl xcall_receive_signal +xcall_receive_signal: + wr %g0, (1 << PIL_SMP_RECEIVE_SIGNAL), %set_softint + retry + + .globl xcall_capture +xcall_capture: + wr %g0, (1 << PIL_SMP_CAPTURE), %set_softint + retry + + .globl xcall_new_mmu_context_version +xcall_new_mmu_context_version: + wr %g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint + retry + +#ifdef CONFIG_KGDB + .globl xcall_kgdb_capture +xcall_kgdb_capture: +661: rdpr %pstate, %g2 + wrpr %g2, PSTATE_IG | PSTATE_AG, %pstate + .section .sun4v_2insn_patch, "ax" + .word 661b + nop + nop + .previous + + rdpr %pil, %g2 + wrpr %g0, 15, %pil + sethi %hi(109f), %g7 + ba,pt %xcc, etrap_irq +109: or %g7, %lo(109b), %g7 +#ifdef CONFIG_TRACE_IRQFLAGS + call trace_hardirqs_off + nop +#endif + call smp_kgdb_capture_client + add %sp, PTREGS_OFF, %o0 + /* Has to be a non-v9 branch due to the large distance. */ + ba rtrap_xcall + ldx [%sp + PTREGS_OFF + PT_V9_TSTATE], %l1 +#endif + +#endif /* CONFIG_SMP */ + + + .globl hypervisor_patch_cachetlbops +hypervisor_patch_cachetlbops: + save %sp, -128, %sp + + sethi %hi(__flush_tlb_mm), %o0 + or %o0, %lo(__flush_tlb_mm), %o0 + sethi %hi(__hypervisor_flush_tlb_mm), %o1 + or %o1, %lo(__hypervisor_flush_tlb_mm), %o1 + call tlb_patch_one + mov 10, %o2 + + sethi %hi(__flush_tlb_pending), %o0 + or %o0, %lo(__flush_tlb_pending), %o0 + sethi %hi(__hypervisor_flush_tlb_pending), %o1 + or %o1, %lo(__hypervisor_flush_tlb_pending), %o1 + call tlb_patch_one + mov 16, %o2 + + sethi %hi(__flush_tlb_kernel_range), %o0 + or %o0, %lo(__flush_tlb_kernel_range), %o0 + sethi %hi(__hypervisor_flush_tlb_kernel_range), %o1 + or %o1, %lo(__hypervisor_flush_tlb_kernel_range), %o1 + call tlb_patch_one + mov 16, %o2 + +#ifdef DCACHE_ALIASING_POSSIBLE + sethi %hi(__flush_dcache_page), %o0 + or %o0, %lo(__flush_dcache_page), %o0 + sethi %hi(__hypervisor_flush_dcache_page), %o1 + or %o1, %lo(__hypervisor_flush_dcache_page), %o1 + call tlb_patch_one + mov 2, %o2 +#endif /* DCACHE_ALIASING_POSSIBLE */ + +#ifdef CONFIG_SMP + sethi %hi(xcall_flush_tlb_mm), %o0 + or %o0, %lo(xcall_flush_tlb_mm), %o0 + sethi %hi(__hypervisor_xcall_flush_tlb_mm), %o1 + or %o1, %lo(__hypervisor_xcall_flush_tlb_mm), %o1 + call tlb_patch_one + mov 21, %o2 + + sethi %hi(xcall_flush_tlb_pending), %o0 + or %o0, %lo(xcall_flush_tlb_pending), %o0 + sethi %hi(__hypervisor_xcall_flush_tlb_pending), %o1 + or %o1, %lo(__hypervisor_xcall_flush_tlb_pending), %o1 + call tlb_patch_one + mov 21, %o2 + + sethi %hi(xcall_flush_tlb_kernel_range), %o0 + or %o0, %lo(xcall_flush_tlb_kernel_range), %o0 + sethi %hi(__hypervisor_xcall_flush_tlb_kernel_range), %o1 + or %o1, %lo(__hypervisor_xcall_flush_tlb_kernel_range), %o1 + call tlb_patch_one + mov 25, %o2 +#endif /* CONFIG_SMP */ + + ret + restore |