diff options
Diffstat (limited to 'arch/x86/mm')
-rw-r--r-- | arch/x86/mm/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/mm/extable.c | 6 | ||||
-rw-r--r-- | arch/x86/mm/fault.c | 467 | ||||
-rw-r--r-- | arch/x86/mm/init_32.c | 135 | ||||
-rw-r--r-- | arch/x86/mm/ioremap.c | 21 | ||||
-rw-r--r-- | arch/x86/mm/mmap.c | 2 | ||||
-rw-r--r-- | arch/x86/mm/numa_64.c | 217 | ||||
-rw-r--r-- | arch/x86/mm/pageattr.c | 15 | ||||
-rw-r--r-- | arch/x86/mm/pat.c | 114 | ||||
-rw-r--r-- | arch/x86/mm/srat_64.c | 1 | ||||
-rw-r--r-- | arch/x86/mm/tlb.c | 296 |
11 files changed, 960 insertions, 316 deletions
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index d8cc96a2738..2b938a38491 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,6 +1,8 @@ obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o gup.o +obj-$(CONFIG_SMP) += tlb.o + obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 7e8db53528a..61b41ca3b5a 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -23,6 +23,12 @@ int fixup_exception(struct pt_regs *regs) fixup = search_exception_tables(regs->ip); if (fixup) { + /* If fixup is less than 16, it means uaccess error */ + if (fixup->fixup < 16) { + current_thread_info()->uaccess_err = -EFAULT; + regs->ip += fixup->fixup; + return 1; + } regs->ip = fixup->fixup; return 1; } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index c76ef1d701c..29644175490 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -26,6 +26,7 @@ #include <linux/kprobes.h> #include <linux/uaccess.h> #include <linux/kdebug.h> +#include <linux/magic.h> #include <asm/system.h> #include <asm/desc.h> @@ -91,8 +92,8 @@ static inline int notify_page_fault(struct pt_regs *regs) * * Opcode checker based on code by Richard Brunner */ -static int is_prefetch(struct pt_regs *regs, unsigned long addr, - unsigned long error_code) +static int is_prefetch(struct pt_regs *regs, unsigned long error_code, + unsigned long addr) { unsigned char *instr; int scan_more = 1; @@ -409,17 +410,16 @@ static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, } #ifdef CONFIG_X86_64 -static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs, - unsigned long error_code) +static noinline void pgtable_bad(struct pt_regs *regs, + unsigned long error_code, unsigned long address) { unsigned long flags = oops_begin(); int sig = SIGKILL; - struct task_struct *tsk; + struct task_struct *tsk = current; printk(KERN_ALERT "%s: Corrupted page table at address %lx\n", - current->comm, address); + tsk->comm, address); dump_pagetable(address); - tsk = current; tsk->thread.cr2 = address; tsk->thread.trap_no = 14; tsk->thread.error_code = error_code; @@ -429,6 +429,196 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs, } #endif +static noinline void no_context(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + struct task_struct *tsk = current; + unsigned long *stackend; + +#ifdef CONFIG_X86_64 + unsigned long flags; + int sig; +#endif + + /* Are we prepared to handle this kernel fault? */ + if (fixup_exception(regs)) + return; + + /* + * X86_32 + * Valid to do another page fault here, because if this fault + * had been triggered by is_prefetch fixup_exception would have + * handled it. + * + * X86_64 + * Hall of shame of CPU/BIOS bugs. + */ + if (is_prefetch(regs, error_code, address)) + return; + + if (is_errata93(regs, address)) + return; + + /* + * Oops. The kernel tried to access some bad page. We'll have to + * terminate things with extreme prejudice. + */ +#ifdef CONFIG_X86_32 + bust_spinlocks(1); +#else + flags = oops_begin(); +#endif + + show_fault_oops(regs, error_code, address); + + stackend = end_of_stack(tsk); + if (*stackend != STACK_END_MAGIC) + printk(KERN_ALERT "Thread overran stack, or stack corrupted\n"); + + tsk->thread.cr2 = address; + tsk->thread.trap_no = 14; + tsk->thread.error_code = error_code; + +#ifdef CONFIG_X86_32 + die("Oops", regs, error_code); + bust_spinlocks(0); + do_exit(SIGKILL); +#else + sig = SIGKILL; + if (__die("Oops", regs, error_code)) + sig = 0; + /* Executive summary in case the body of the oops scrolled away */ + printk(KERN_EMERG "CR2: %016lx\n", address); + oops_end(flags, regs, sig); +#endif +} + +static void __bad_area_nosemaphore(struct pt_regs *regs, + unsigned long error_code, unsigned long address, + int si_code) +{ + struct task_struct *tsk = current; + + /* User mode accesses just cause a SIGSEGV */ + if (error_code & PF_USER) { + /* + * It's possible to have interrupts off here. + */ + local_irq_enable(); + + /* + * Valid to do another page fault here because this one came + * from user space. + */ + if (is_prefetch(regs, error_code, address)) + return; + + if (is_errata100(regs, address)) + return; + + if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && + printk_ratelimit()) { + printk( + "%s%s[%d]: segfault at %lx ip %p sp %p error %lx", + task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, + tsk->comm, task_pid_nr(tsk), address, + (void *) regs->ip, (void *) regs->sp, error_code); + print_vma_addr(" in ", regs->ip); + printk("\n"); + } + + tsk->thread.cr2 = address; + /* Kernel addresses are always protection faults */ + tsk->thread.error_code = error_code | (address >= TASK_SIZE); + tsk->thread.trap_no = 14; + force_sig_info_fault(SIGSEGV, si_code, address, tsk); + return; + } + + if (is_f00f_bug(regs, address)) + return; + + no_context(regs, error_code, address); +} + +static noinline void bad_area_nosemaphore(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + __bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR); +} + +static void __bad_area(struct pt_regs *regs, + unsigned long error_code, unsigned long address, + int si_code) +{ + struct mm_struct *mm = current->mm; + + /* + * Something tried to access memory that isn't in our memory map.. + * Fix it, but check if it's kernel or user first.. + */ + up_read(&mm->mmap_sem); + + __bad_area_nosemaphore(regs, error_code, address, si_code); +} + +static noinline void bad_area(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + __bad_area(regs, error_code, address, SEGV_MAPERR); +} + +static noinline void bad_area_access_error(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + __bad_area(regs, error_code, address, SEGV_ACCERR); +} + +/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */ +static void out_of_memory(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + /* + * We ran out of memory, call the OOM killer, and return the userspace + * (which will retry the fault, or kill us if we got oom-killed). + */ + up_read(¤t->mm->mmap_sem); + pagefault_out_of_memory(); +} + +static void do_sigbus(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + struct task_struct *tsk = current; + struct mm_struct *mm = tsk->mm; + + up_read(&mm->mmap_sem); + + /* Kernel mode? Handle exceptions or die */ + if (!(error_code & PF_USER)) + no_context(regs, error_code, address); +#ifdef CONFIG_X86_32 + /* User space => ok to do another page fault */ + if (is_prefetch(regs, error_code, address)) + return; +#endif + tsk->thread.cr2 = address; + tsk->thread.error_code = error_code; + tsk->thread.trap_no = 14; + force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk); +} + +static noinline void mm_fault_error(struct pt_regs *regs, + unsigned long error_code, unsigned long address, unsigned int fault) +{ + if (fault & VM_FAULT_OOM) + out_of_memory(regs, error_code, address); + else if (fault & VM_FAULT_SIGBUS) + do_sigbus(regs, error_code, address); + else + BUG(); +} + static int spurious_fault_check(unsigned long error_code, pte_t *pte) { if ((error_code & PF_WRITE) && !pte_write(*pte)) @@ -448,8 +638,8 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte) * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. */ -static int spurious_fault(unsigned long address, - unsigned long error_code) +static noinline int spurious_fault(unsigned long error_code, + unsigned long address) { pgd_t *pgd; pud_t *pud; @@ -494,7 +684,7 @@ static int spurious_fault(unsigned long address, * * This assumes no large pages in there. */ -static int vmalloc_fault(unsigned long address) +static noinline int vmalloc_fault(unsigned long address) { #ifdef CONFIG_X86_32 unsigned long pgd_paddr; @@ -573,6 +763,34 @@ static int vmalloc_fault(unsigned long address) int show_unhandled_signals = 1; +static inline int access_error(unsigned long error_code, int write, + struct vm_area_struct *vma) +{ + if (write) { + /* write, present and write, not present */ + if (unlikely(!(vma->vm_flags & VM_WRITE))) + return 1; + } else if (unlikely(error_code & PF_PROT)) { + /* read, present */ + return 1; + } else { + /* read, not present */ + if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))) + return 1; + } + + return 0; +} + +static int fault_in_kernel_space(unsigned long address) +{ +#ifdef CONFIG_X86_32 + return address >= TASK_SIZE; +#else /* !CONFIG_X86_32 */ + return address >= TASK_SIZE64; +#endif /* CONFIG_X86_32 */ +} + /* * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate @@ -583,16 +801,12 @@ asmlinkage #endif void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) { + unsigned long address; struct task_struct *tsk; struct mm_struct *mm; struct vm_area_struct *vma; - unsigned long address; - int write, si_code; + int write; int fault; -#ifdef CONFIG_X86_64 - unsigned long flags; - int sig; -#endif tsk = current; mm = tsk->mm; @@ -601,8 +815,6 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) /* get the address */ address = read_cr2(); - si_code = SEGV_MAPERR; - if (unlikely(kmmio_fault(regs, address))) return; @@ -619,17 +831,13 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) * (error_code & 4) == 0, and that the fault was not a * protection error (error_code & 9) == 0. */ -#ifdef CONFIG_X86_32 - if (unlikely(address >= TASK_SIZE)) { -#else - if (unlikely(address >= TASK_SIZE64)) { -#endif + if (unlikely(fault_in_kernel_space(address))) { if (!(error_code & (PF_RSVD|PF_USER|PF_PROT)) && vmalloc_fault(address) >= 0) return; /* Can handle a stale RO->RW TLB */ - if (spurious_fault(address, error_code)) + if (spurious_fault(error_code, address)) return; /* kprobes don't want to hook the spurious faults. */ @@ -639,13 +847,13 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) * Don't take the mm semaphore here. If we fixup a prefetch * fault we could otherwise deadlock. */ - goto bad_area_nosemaphore; + bad_area_nosemaphore(regs, error_code, address); + return; } /* kprobes don't want to hook the spurious faults. */ - if (notify_page_fault(regs)) + if (unlikely(notify_page_fault(regs))) return; - /* * It's safe to allow irq's after cr2 has been saved and the * vmalloc fault has been handled. @@ -661,15 +869,17 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) #ifdef CONFIG_X86_64 if (unlikely(error_code & PF_RSVD)) - pgtable_bad(address, regs, error_code); + pgtable_bad(regs, error_code, address); #endif /* * If we're in an interrupt, have no user context or are running in an * atomic region then we must not take the fault. */ - if (unlikely(in_atomic() || !mm)) - goto bad_area_nosemaphore; + if (unlikely(in_atomic() || !mm)) { + bad_area_nosemaphore(regs, error_code, address); + return; + } /* * When running in the kernel we expect faults to occur only to @@ -687,20 +897,32 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) * source. If this is invalid we can skip the address space check, * thus avoiding the deadlock. */ - if (!down_read_trylock(&mm->mmap_sem)) { + if (unlikely(!down_read_trylock(&mm->mmap_sem))) { if ((error_code & PF_USER) == 0 && - !search_exception_tables(regs->ip)) - goto bad_area_nosemaphore; + !search_exception_tables(regs->ip)) { + bad_area_nosemaphore(regs, error_code, address); + return; + } down_read(&mm->mmap_sem); + } else { + /* + * The above down_read_trylock() might have succeeded in which + * case we'll have missed the might_sleep() from down_read(). + */ + might_sleep(); } vma = find_vma(mm, address); - if (!vma) - goto bad_area; - if (vma->vm_start <= address) + if (unlikely(!vma)) { + bad_area(regs, error_code, address); + return; + } + if (likely(vma->vm_start <= address)) goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; + if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { + bad_area(regs, error_code, address); + return; + } if (error_code & PF_USER) { /* * Accessing the stack below %sp is always a bug. @@ -708,31 +930,25 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) * and pusha to work. ("enter $65535,$31" pushes * 32 pointers and then decrements %sp by 65535.) */ - if (address + 65536 + 32 * sizeof(unsigned long) < regs->sp) - goto bad_area; + if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) { + bad_area(regs, error_code, address); + return; + } } - if (expand_stack(vma, address)) - goto bad_area; -/* - * Ok, we have a good vm_area for this memory access, so - * we can handle it.. - */ + if (unlikely(expand_stack(vma, address))) { + bad_area(regs, error_code, address); + return; + } + + /* + * Ok, we have a good vm_area for this memory access, so + * we can handle it.. + */ good_area: - si_code = SEGV_ACCERR; - write = 0; - switch (error_code & (PF_PROT|PF_WRITE)) { - default: /* 3: write, present */ - /* fall through */ - case PF_WRITE: /* write, not present */ - if (!(vma->vm_flags & VM_WRITE)) - goto bad_area; - write++; - break; - case PF_PROT: /* read, present */ - goto bad_area; - case 0: /* read, not present */ - if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) - goto bad_area; + write = error_code & PF_WRITE; + if (unlikely(access_error(error_code, write, vma))) { + bad_area_access_error(regs, error_code, address); + return; } /* @@ -742,11 +958,8 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, 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(); + mm_fault_error(regs, error_code, address, fault); + return; } if (fault & VM_FAULT_MAJOR) tsk->maj_flt++; @@ -764,128 +977,6 @@ good_area: } #endif up_read(&mm->mmap_sem); - 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: - up_read(&mm->mmap_sem); - -bad_area_nosemaphore: - /* User mode accesses just cause a SIGSEGV */ - if (error_code & PF_USER) { - /* - * It's possible to have interrupts off here. - */ - local_irq_enable(); - - /* - * Valid to do another page fault here because this one came - * from user space. - */ - if (is_prefetch(regs, address, error_code)) - return; - - if (is_errata100(regs, address)) - return; - - if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && - printk_ratelimit()) { - printk( - "%s%s[%d]: segfault at %lx ip %p sp %p error %lx", - task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, - tsk->comm, task_pid_nr(tsk), address, - (void *) regs->ip, (void *) regs->sp, error_code); - print_vma_addr(" in ", regs->ip); - printk("\n"); - } - - tsk->thread.cr2 = address; - /* Kernel addresses are always protection faults */ - tsk->thread.error_code = error_code | (address >= TASK_SIZE); - tsk->thread.trap_no = 14; - force_sig_info_fault(SIGSEGV, si_code, address, tsk); - return; - } - - if (is_f00f_bug(regs, address)) - return; - -no_context: - /* Are we prepared to handle this kernel fault? */ - if (fixup_exception(regs)) - return; - - /* - * X86_32 - * Valid to do another page fault here, because if this fault - * had been triggered by is_prefetch fixup_exception would have - * handled it. - * - * X86_64 - * Hall of shame of CPU/BIOS bugs. - */ - if (is_prefetch(regs, address, error_code)) - return; - - if (is_errata93(regs, address)) - return; - -/* - * Oops. The kernel tried to access some bad page. We'll have to - * terminate things with extreme prejudice. - */ -#ifdef CONFIG_X86_32 - bust_spinlocks(1); -#else - flags = oops_begin(); -#endif - - show_fault_oops(regs, error_code, address); - - tsk->thread.cr2 = address; - tsk->thread.trap_no = 14; - tsk->thread.error_code = error_code; - -#ifdef CONFIG_X86_32 - die("Oops", regs, error_code); - bust_spinlocks(0); - do_exit(SIGKILL); -#else - sig = SIGKILL; - if (__die("Oops", regs, error_code)) - sig = 0; - /* Executive summary in case the body of the oops scrolled away */ - printk(KERN_EMERG "CR2: %016lx\n", address); - oops_end(flags, regs, sig); -#endif - -out_of_memory: - /* - * We ran out of memory, call the OOM killer, and return the userspace - * (which will retry the fault, or kill us if we got oom-killed). - */ - up_read(&mm->mmap_sem); - pagefault_out_of_memory(); - return; - -do_sigbus: - up_read(&mm->mmap_sem); - - /* Kernel mode? Handle exceptions or die */ - if (!(error_code & PF_USER)) - goto no_context; -#ifdef CONFIG_X86_32 - /* User space => ok to do another page fault */ - if (is_prefetch(regs, address, error_code)) - return; -#endif - tsk->thread.cr2 = address; - tsk->thread.error_code = error_code; - tsk->thread.trap_no = 14; - force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk); } DEFINE_SPINLOCK(pgd_lock); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 2cef0507441..06708ee94aa 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -49,7 +49,6 @@ #include <asm/paravirt.h> #include <asm/setup.h> #include <asm/cacheflush.h> -#include <asm/smp.h> unsigned int __VMALLOC_RESERVE = 128 << 20; @@ -675,75 +674,97 @@ static int __init parse_highmem(char *arg) } early_param("highmem", parse_highmem); +#define MSG_HIGHMEM_TOO_BIG \ + "highmem size (%luMB) is bigger than pages available (%luMB)!\n" + +#define MSG_LOWMEM_TOO_SMALL \ + "highmem size (%luMB) results in <64MB lowmem, ignoring it!\n" /* - * Determine low and high memory ranges: + * All of RAM fits into lowmem - but if user wants highmem + * artificially via the highmem=x boot parameter then create + * it: */ -void __init find_low_pfn_range(void) +void __init lowmem_pfn_init(void) { - /* it could update max_pfn */ - /* max_low_pfn is 0, we already have early_res support */ - max_low_pfn = max_pfn; - if (max_low_pfn > MAXMEM_PFN) { - if (highmem_pages == -1) - highmem_pages = max_pfn - MAXMEM_PFN; - if (highmem_pages + MAXMEM_PFN < max_pfn) - max_pfn = MAXMEM_PFN + highmem_pages; - if (highmem_pages + MAXMEM_PFN > max_pfn) { - printk(KERN_WARNING "only %luMB highmem pages " - "available, ignoring highmem size of %uMB.\n", - pages_to_mb(max_pfn - MAXMEM_PFN), + + if (highmem_pages == -1) + highmem_pages = 0; +#ifdef CONFIG_HIGHMEM + if (highmem_pages >= max_pfn) { + printk(KERN_ERR MSG_HIGHMEM_TOO_BIG, + pages_to_mb(highmem_pages), pages_to_mb(max_pfn)); + highmem_pages = 0; + } + if (highmem_pages) { + if (max_low_pfn - highmem_pages < 64*1024*1024/PAGE_SIZE) { + printk(KERN_ERR MSG_LOWMEM_TOO_SMALL, pages_to_mb(highmem_pages)); highmem_pages = 0; } - max_low_pfn = MAXMEM_PFN; + max_low_pfn -= highmem_pages; + } +#else + if (highmem_pages) + printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n"); +#endif +} + +#define MSG_HIGHMEM_TOO_SMALL \ + "only %luMB highmem pages available, ignoring highmem size of %luMB!\n" + +#define MSG_HIGHMEM_TRIMMED \ + "Warning: only 4GB will be used. Use a HIGHMEM64G enabled kernel!\n" +/* + * We have more RAM than fits into lowmem - we try to put it into + * highmem, also taking the highmem=x boot parameter into account: + */ +void __init highmem_pfn_init(void) +{ + max_low_pfn = MAXMEM_PFN; + + if (highmem_pages == -1) + highmem_pages = max_pfn - MAXMEM_PFN; + + if (highmem_pages + MAXMEM_PFN < max_pfn) + max_pfn = MAXMEM_PFN + highmem_pages; + + if (highmem_pages + MAXMEM_PFN > max_pfn) { + printk(KERN_WARNING MSG_HIGHMEM_TOO_SMALL, + pages_to_mb(max_pfn - MAXMEM_PFN), + pages_to_mb(highmem_pages)); + highmem_pages = 0; + } #ifndef CONFIG_HIGHMEM - /* Maximum memory usable is what is directly addressable */ - printk(KERN_WARNING "Warning only %ldMB will be used.\n", - MAXMEM>>20); - if (max_pfn > MAX_NONPAE_PFN) - printk(KERN_WARNING - "Use a HIGHMEM64G enabled kernel.\n"); - else - printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); - max_pfn = MAXMEM_PFN; + /* Maximum memory usable is what is directly addressable */ + printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20); + if (max_pfn > MAX_NONPAE_PFN) + printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n"); + else + printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); + max_pfn = MAXMEM_PFN; #else /* !CONFIG_HIGHMEM */ #ifndef CONFIG_HIGHMEM64G - if (max_pfn > MAX_NONPAE_PFN) { - max_pfn = MAX_NONPAE_PFN; - printk(KERN_WARNING "Warning only 4GB will be used." - "Use a HIGHMEM64G enabled kernel.\n"); - } + if (max_pfn > MAX_NONPAE_PFN) { + max_pfn = MAX_NONPAE_PFN; + printk(KERN_WARNING MSG_HIGHMEM_TRIMMED); + } #endif /* !CONFIG_HIGHMEM64G */ #endif /* !CONFIG_HIGHMEM */ - } else { - if (highmem_pages == -1) - highmem_pages = 0; -#ifdef CONFIG_HIGHMEM - if (highmem_pages >= max_pfn) { - printk(KERN_ERR "highmem size specified (%uMB) is " - "bigger than pages available (%luMB)!.\n", - pages_to_mb(highmem_pages), - pages_to_mb(max_pfn)); - highmem_pages = 0; - } - if (highmem_pages) { - if (max_low_pfn - highmem_pages < - 64*1024*1024/PAGE_SIZE){ - printk(KERN_ERR "highmem size %uMB results in " - "smaller than 64MB lowmem, ignoring it.\n" - , pages_to_mb(highmem_pages)); - highmem_pages = 0; - } - max_low_pfn -= highmem_pages; - } -#else - if (highmem_pages) - printk(KERN_ERR "ignoring highmem size on non-highmem" - " kernel!\n"); -#endif - } +} + +/* + * Determine low and high memory ranges: + */ +void __init find_low_pfn_range(void) +{ + /* it could update max_pfn */ + + if (max_pfn <= MAXMEM_PFN) + lowmem_pfn_init(); + else + highmem_pfn_init(); } #ifndef CONFIG_NEED_MULTIPLE_NODES diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index af750ab973b..433f7bd4648 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -134,25 +134,6 @@ int page_is_ram(unsigned long pagenr) return 0; } -int pagerange_is_ram(unsigned long start, unsigned long end) -{ - int ram_page = 0, not_rampage = 0; - unsigned long page_nr; - - for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT); - ++page_nr) { - if (page_is_ram(page_nr)) - ram_page = 1; - else - not_rampage = 1; - - if (ram_page == not_rampage) - return -1; - } - - return ram_page; -} - /* * Fix up the linear direct mapping of the kernel to avoid cache attribute * conflicts. @@ -367,7 +348,7 @@ EXPORT_SYMBOL(ioremap_nocache); * * Must be freed with iounmap. */ -void __iomem *ioremap_wc(unsigned long phys_addr, unsigned long size) +void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size) { if (pat_enabled) return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC, diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 56fe7124fbe..16582960056 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -4,7 +4,7 @@ * Based on code by Ingo Molnar and Andi Kleen, copyrighted * as follows: * - * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina. + * Copyright 2003-2009 Red Hat Inc. * All Rights Reserved. * Copyright 2005 Andi Kleen, SUSE Labs. * Copyright 2007 Jiri Kosina, SUSE Labs. diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 71a14f89f89..deb1c1ab786 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -20,6 +20,12 @@ #include <asm/acpi.h> #include <asm/k8.h> +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +# define DBG(x...) printk(KERN_DEBUG x) +#else +# define DBG(x...) +#endif + struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -33,6 +39,21 @@ int numa_off __initdata; static unsigned long __initdata nodemap_addr; static unsigned long __initdata nodemap_size; +DEFINE_PER_CPU(int, node_number) = 0; +EXPORT_PER_CPU_SYMBOL(node_number); + +/* + * Map cpu index to node index + */ +DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); + +/* + * Which logical CPUs are on which nodes + */ +cpumask_t *node_to_cpumask_map; +EXPORT_SYMBOL(node_to_cpumask_map); + /* * Given a shift value, try to populate memnodemap[] * Returns : @@ -640,3 +661,199 @@ void __init init_cpu_to_node(void) #endif +/* + * Allocate node_to_cpumask_map based on number of available nodes + * Requires node_possible_map to be valid. + * + * Note: node_to_cpumask() is not valid until after this is done. + * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) + */ +void __init setup_node_to_cpumask_map(void) +{ + unsigned int node, num = 0; + cpumask_t *map; + + /* setup nr_node_ids if not done yet */ + if (nr_node_ids == MAX_NUMNODES) { + for_each_node_mask(node, node_possible_map) + num = node; + nr_node_ids = num + 1; + } + + /* allocate the map */ + map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t)); + DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids); + + pr_debug("Node to cpumask map at %p for %d nodes\n", + map, nr_node_ids); + + /* node_to_cpumask() will now work */ + node_to_cpumask_map = map; +} + +void __cpuinit numa_set_node(int cpu, int node) +{ + int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); + + /* early setting, no percpu area yet */ + if (cpu_to_node_map) { + cpu_to_node_map[cpu] = node; + return; + } + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS + if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) { + printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu); + dump_stack(); + return; + } +#endif + per_cpu(x86_cpu_to_node_map, cpu) = node; + + if (node != NUMA_NO_NODE) + per_cpu(node_number, cpu) = node; +} + +void __cpuinit numa_clear_node(int cpu) +{ + numa_set_node(cpu, NUMA_NO_NODE); +} + +#ifndef CONFIG_DEBUG_PER_CPU_MAPS + +void __cpuinit numa_add_cpu(int cpu) +{ + cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); +} + +void __cpuinit numa_remove_cpu(int cpu) +{ + cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); +} + +#else /* CONFIG_DEBUG_PER_CPU_MAPS */ + +/* + * --------- debug versions of the numa functions --------- + */ +static void __cpuinit numa_set_cpumask(int cpu, int enable) +{ + int node = early_cpu_to_node(cpu); + cpumask_t *mask; + char buf[64]; + + if (node_to_cpumask_map == NULL) { + printk(KERN_ERR "node_to_cpumask_map NULL\n"); + dump_stack(); + return; + } + + mask = &node_to_cpumask_map[node]; + if (enable) + cpu_set(cpu, *mask); + else + cpu_clear(cpu, *mask); + + cpulist_scnprintf(buf, sizeof(buf), mask); + printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n", + enable ? "numa_add_cpu" : "numa_remove_cpu", cpu, node, buf); +} + +void __cpuinit numa_add_cpu(int cpu) +{ + numa_set_cpumask(cpu, 1); +} + +void __cpuinit numa_remove_cpu(int cpu) +{ + numa_set_cpumask(cpu, 0); +} + +int cpu_to_node(int cpu) +{ + if (early_per_cpu_ptr(x86_cpu_to_node_map)) { + printk(KERN_WARNING + "cpu_to_node(%d): usage too early!\n", cpu); + dump_stack(); + return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; + } + return per_cpu(x86_cpu_to_node_map, cpu); +} +EXPORT_SYMBOL(cpu_to_node); + +/* + * Same function as cpu_to_node() but used if called before the + * per_cpu areas are setup. + */ +int early_cpu_to_node(int cpu) +{ + if (early_per_cpu_ptr(x86_cpu_to_node_map)) + return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu]; + + if (!cpu_possible(cpu)) { + printk(KERN_WARNING + "early_cpu_to_node(%d): no per_cpu area!\n", cpu); + dump_stack(); + return NUMA_NO_NODE; + } + return per_cpu(x86_cpu_to_node_map, cpu); +} + + +/* empty cpumask */ +static const cpumask_t cpu_mask_none; + +/* + * Returns a pointer to the bitmask of CPUs on Node 'node'. + */ +const cpumask_t *cpumask_of_node(int node) +{ + if (node_to_cpumask_map == NULL) { + printk(KERN_WARNING + "cpumask_of_node(%d): no node_to_cpumask_map!\n", + node); + dump_stack(); + return (const cpumask_t *)&cpu_online_map; + } + if (node >= nr_node_ids) { + printk(KERN_WARNING + "cpumask_of_node(%d): node > nr_node_ids(%d)\n", + node, nr_node_ids); + dump_stack(); + return &cpu_mask_none; + } + return &node_to_cpumask_map[node]; +} +EXPORT_SYMBOL(cpumask_of_node); + +/* + * Returns a bitmask of CPUs on Node 'node'. + * + * Side note: this function creates the returned cpumask on the stack + * so with a high NR_CPUS count, excessive stack space is used. The + * node_to_cpumask_ptr function should be used whenever possible. + */ +cpumask_t node_to_cpumask(int node) +{ + if (node_to_cpumask_map == NULL) { + printk(KERN_WARNING + "node_to_cpumask(%d): no node_to_cpumask_map!\n", node); + dump_stack(); + return cpu_online_map; + } + if (node >= nr_node_ids) { + printk(KERN_WARNING + "node_to_cpumask(%d): node > nr_node_ids(%d)\n", + node, nr_node_ids); + dump_stack(); + return cpu_mask_none; + } + return node_to_cpumask_map[node]; +} +EXPORT_SYMBOL(node_to_cpumask); + +/* + * --------- end of debug versions of the numa functions --------- + */ + +#endif /* CONFIG_DEBUG_PER_CPU_MAPS */ diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 84ba74820ad..8ca0d8566fc 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -575,7 +575,6 @@ static int __change_page_attr(stru |