diff options
Diffstat (limited to 'arch/x86')
38 files changed, 822 insertions, 312 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 03980cb04291..b6fa2877b173 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -21,12 +21,16 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_IDE select HAVE_OPROFILE + select HAVE_IOREMAP_PROT + select HAVE_GET_USER_PAGES_FAST select HAVE_KPROBES + select ARCH_WANT_OPTIONAL_GPIOLIB select HAVE_KRETPROBES select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64) select HAVE_ARCH_KGDB if !X86_VOYAGER + select HAVE_EFFICIENT_UNALIGNED_ACCESS config ARCH_DEFCONFIG string @@ -329,20 +333,6 @@ config X86_BIGSMP endif -config X86_RDC321X - bool "RDC R-321x SoC" - depends on X86_32 - select M486 - select X86_REBOOTFIXUPS - select GENERIC_GPIO - select LEDS_CLASS - select LEDS_GPIO - select NEW_LEDS - help - This option is needed for RDC R-321x system-on-chip, also known - as R-8610-(G). - If you don't have one of these chips, you should say N here. - config X86_VSMP bool "Support for ScaleMP vSMP" select PARAVIRT @@ -366,6 +356,16 @@ config X86_VISWS A kernel compiled for the Visual Workstation will run on general PCs as well. See <file:Documentation/sgi-visws.txt> for details. +config X86_RDC321X + bool "RDC R-321x SoC" + depends on X86_32 + select M486 + select X86_REBOOTFIXUPS + help + This option is needed for RDC R-321x system-on-chip, also known + as R-8610-(G). + If you don't have one of these chips, you should say N here. + config SCHED_NO_NO_OMIT_FRAME_POINTER def_bool y prompt "Single-depth WCHAN output" @@ -1276,6 +1276,14 @@ config CRASH_DUMP (CONFIG_RELOCATABLE=y). For more details see Documentation/kdump/kdump.txt +config KEXEC_JUMP + bool "kexec jump (EXPERIMENTAL)" + depends on EXPERIMENTAL + depends on KEXEC && HIBERNATION && X86_32 + help + Jump between original kernel and kexeced kernel and invoke + code in physical address mode via KEXEC + config PHYSICAL_START hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP) default "0x1000000" if X86_NUMAQ diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 919ce21ea654..f5631da585b6 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -118,11 +118,6 @@ mflags-$(CONFIG_X86_GENERICARCH):= -Iinclude/asm-x86/mach-generic fcore-$(CONFIG_X86_GENERICARCH) += arch/x86/mach-generic/ mcore-$(CONFIG_X86_GENERICARCH) := arch/x86/mach-default/ -# RDC R-321x subarch support -mflags-$(CONFIG_X86_RDC321X) := -Iinclude/asm-x86/mach-rdc321x -mcore-$(CONFIG_X86_RDC321X) := arch/x86/mach-default/ -core-$(CONFIG_X86_RDC321X) += arch/x86/mach-rdc321x/ - # default subarch .h files mflags-y += -Iinclude/asm-x86/mach-default diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index bc5553b496f7..9fea73706479 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -182,8 +182,6 @@ static unsigned outcnt; static int fill_inbuf(void); static void flush_window(void); static void error(char *m); -static void gzip_mark(void **); -static void gzip_release(void **); /* * This is set up by the setup-routine at boot-time @@ -196,9 +194,6 @@ extern int input_len; static long bytes_out; -static void *malloc(int size); -static void free(void *where); - static void *memset(void *s, int c, unsigned n); static void *memcpy(void *dest, const void *src, unsigned n); @@ -220,40 +215,6 @@ static int lines, cols; #include "../../../../lib/inflate.c" -static void *malloc(int size) -{ - void *p; - - if (size < 0) - error("Malloc error"); - if (free_mem_ptr <= 0) - error("Memory error"); - - free_mem_ptr = (free_mem_ptr + 3) & ~3; /* Align */ - - p = (void *)free_mem_ptr; - free_mem_ptr += size; - - if (free_mem_ptr >= free_mem_end_ptr) - error("Out of memory"); - - return p; -} - -static void free(void *where) -{ /* Don't care */ -} - -static void gzip_mark(void **ptr) -{ - *ptr = (void *) free_mem_ptr; -} - -static void gzip_release(void **ptr) -{ - free_mem_ptr = (memptr) *ptr; -} - static void scroll(void) { int i; diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 58cccb6483b0..a0e1dbe67dc1 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -441,12 +441,6 @@ beyond_if: regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; set_fs(USER_DS); - if (unlikely(current->ptrace & PT_PTRACED)) { - if (current->ptrace & PT_TRACE_EXEC) - ptrace_notify((PTRACE_EVENT_EXEC << 8) | SIGTRAP); - else - send_sig(SIGTRAP, current, 0); - } return 0; } diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 021d71bc69b5..ffc1bb4fed7d 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -201,7 +201,7 @@ sysexit_from_sys_call: movl RDI-ARGOFFSET(%rsp),%r8d /* reload 5th syscall arg */ .endm - .macro auditsys_exit exit + .macro auditsys_exit exit,ebpsave=RBP testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags(%r10) jnz int_ret_from_sys_call TRACE_IRQS_ON @@ -214,7 +214,7 @@ sysexit_from_sys_call: call audit_syscall_exit GET_THREAD_INFO(%r10) movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall return value */ - movl RBP-ARGOFFSET(%rsp),%ebp /* reload user register value */ + movl \ebpsave-ARGOFFSET(%rsp),%ebp /* reload user register value */ movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi cli TRACE_IRQS_OFF @@ -347,7 +347,7 @@ cstar_auditsys: jmp cstar_dispatch sysretl_audit: - auditsys_exit sysretl_from_sys_call + auditsys_exit sysretl_from_sys_call, RCX /* user %ebp in RCX slot */ #endif cstar_tracesys: @@ -826,4 +826,10 @@ ia32_sys_call_table: .quad sys32_fallocate .quad compat_sys_timerfd_settime /* 325 */ .quad compat_sys_timerfd_gettime + .quad compat_sys_signalfd4 + .quad sys_eventfd2 + .quad sys_epoll_create1 + .quad sys_dup3 /* 330 */ + .quad sys_pipe2 + .quad sys_inotify_init1 ia32_syscall_end: diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index f00afdf61e67..d3c64088b981 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -238,7 +238,7 @@ asmlinkage long sys32_pipe(int __user *fd) int retval; int fds[2]; - retval = do_pipe(fds); + retval = do_pipe_flags(fds, 0); if (retval) goto out; if (copy_to_user(fd, fds, sizeof(fds))) diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index a3ddad18aaa3..fa2161d5003b 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -150,6 +150,10 @@ static int __init acpi_sleep_setup(char *str) acpi_realmode_flags |= 2; if (strncmp(str, "s3_beep", 7) == 0) acpi_realmode_flags |= 4; +#ifdef CONFIG_HIBERNATION + if (strncmp(str, "s4_nohwsig", 10) == 0) + acpi_no_s4_hw_signature(); +#endif if (strncmp(str, "old_ordering", 12) == 0) acpi_old_suspend_ordering(); str = strchr(str, ','); diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index c25210e6ac88..74697408576f 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -667,7 +667,7 @@ static int get_device_resources(struct device *dev, _bdf = calc_devid(pcidev->bus->number, pcidev->devfn); /* device not translated by any IOMMU in the system? */ - if (_bdf >= amd_iommu_last_bdf) { + if (_bdf > amd_iommu_last_bdf) { *iommu = NULL; *domain = NULL; *bdf = 0xffff; @@ -1085,7 +1085,7 @@ void prealloc_protection_domains(void) while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { devid = (dev->bus->number << 8) | dev->devfn; - if (devid >= amd_iommu_last_bdf) + if (devid > amd_iommu_last_bdf) continue; devid = amd_iommu_alias_table[devid]; if (domain_for_device(devid)) diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index c9d8ff2eb130..d9a9da597e79 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -732,7 +732,7 @@ static int __init init_exclusion_range(struct ivmd_header *m) set_device_exclusion_range(m->devid, m); break; case ACPI_IVMD_TYPE_ALL: - for (i = 0; i < amd_iommu_last_bdf; ++i) + for (i = 0; i <= amd_iommu_last_bdf; ++i) set_device_exclusion_range(i, m); break; case ACPI_IVMD_TYPE_RANGE: @@ -934,7 +934,7 @@ int __init amd_iommu_init(void) /* * let all alias entries point to itself */ - for (i = 0; i < amd_iommu_last_bdf; ++i) + for (i = 0; i <= amd_iommu_last_bdf; ++i) amd_iommu_alias_table[i] = i; /* diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index bf9b441331e9..9ee24e6bc4b0 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -219,7 +219,6 @@ #include <linux/time.h> #include <linux/sched.h> #include <linux/pm.h> -#include <linux/pm_legacy.h> #include <linux/capability.h> #include <linux/device.h> #include <linux/kernel.h> diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 0ea6a19bfdfe..ad2b15a1334d 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -468,7 +468,7 @@ void hpet_disable(void) #define RTC_NUM_INTS 1 static unsigned long hpet_rtc_flags; -static unsigned long hpet_prev_update_sec; +static int hpet_prev_update_sec; static struct rtc_time hpet_alarm_time; static unsigned long hpet_pie_count; static unsigned long hpet_t1_cmp; @@ -575,6 +575,9 @@ int hpet_set_rtc_irq_bit(unsigned long bit_mask) hpet_rtc_flags |= bit_mask; + if ((bit_mask & RTC_UIE) && !(oldbits & RTC_UIE)) + hpet_prev_update_sec = -1; + if (!oldbits) hpet_rtc_timer_init(); @@ -652,7 +655,7 @@ static void hpet_rtc_timer_reinit(void) if (hpet_rtc_flags & RTC_PIE) hpet_pie_count += lost_ints; if (printk_ratelimit()) - printk(KERN_WARNING "rtc: lost %d interrupts\n", + printk(KERN_WARNING "hpet1: lost %d rtc interrupts\n", lost_ints); } } @@ -670,7 +673,8 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) if (hpet_rtc_flags & RTC_UIE && curr_time.tm_sec != hpet_prev_update_sec) { - rtc_int_flag = RTC_UF; + if (hpet_prev_update_sec >= 0) + rtc_int_flag = RTC_UF; hpet_prev_update_sec = curr_time.tm_sec; } diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c index 0373e88de95a..1f26fd9ec4f4 100644 --- a/arch/x86/kernel/irqinit_64.c +++ b/arch/x86/kernel/irqinit_64.c @@ -43,10 +43,11 @@ #define BUILD_IRQ(nr) \ asmlinkage void IRQ_NAME(nr); \ - asm("\n.p2align\n" \ + asm("\n.text\n.p2align\n" \ "IRQ" #nr "_interrupt:\n\t" \ "push $~(" #nr ") ; " \ - "jmp common_interrupt"); + "jmp common_interrupt\n" \ + ".previous"); #define BI(x,y) \ BUILD_IRQ(x##y) diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 43c019f85f0d..6c27679ec6aa 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -431,7 +431,6 @@ static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs) regs->ip = (unsigned long)p->ainsn.insn; } -/* Called with kretprobe_lock held */ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { @@ -682,8 +681,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; INIT_HLIST_HEAD(&empty_rp); - spin_lock_irqsave(&kretprobe_lock, flags); - head = kretprobe_inst_table_head(current); + kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ #ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; @@ -732,7 +730,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) kretprobe_assert(ri, orig_ret_address, trampoline_address); - spin_unlock_irqrestore(&kretprobe_lock, flags); + kretprobe_hash_unlock(current, &flags); hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 8864230d55af..9fe478d98406 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -22,6 +22,7 @@ #include <asm/cpufeature.h> #include <asm/desc.h> #include <asm/system.h> +#include <asm/cacheflush.h> #define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE))) static u32 kexec_pgd[1024] PAGE_ALIGNED; @@ -85,10 +86,12 @@ static void load_segments(void) * reboot code buffer to allow us to avoid allocations * later. * - * Currently nothing. + * Make control page executable. */ int machine_kexec_prepare(struct kimage *image) { + if (nx_enabled) + set_pages_x(image->control_code_page, 1); return 0; } @@ -98,27 +101,48 @@ int machine_kexec_prepare(struct kimage *image) */ void machine_kexec_cleanup(struct kimage *image) { + if (nx_enabled) + set_pages_nx(image->control_code_page, 1); } /* * Do not allocate memory (or fail in any way) in machine_kexec(). * We are past the point of no return, committed to rebooting now. */ -NORET_TYPE void machine_kexec(struct kimage *image) +void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; void *control_page; + asmlinkage unsigned long + (*relocate_kernel_ptr)(unsigned long indirection_page, + unsigned long control_page, + unsigned long start_address, + unsigned int has_pae, + unsigned int preserve_context); tracer_disable(); /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); + if (image->preserve_context) { +#ifdef CONFIG_X86_IO_APIC + /* We need to put APICs in legacy mode so that we can + * get timer interrupts in second kernel. kexec/kdump + * paths already have calls to disable_IO_APIC() in + * one form or other. kexec jump path also need + * one. + */ + disable_IO_APIC(); +#endif + } + control_page = page_address(image->control_code_page); - memcpy(control_page, relocate_kernel, PAGE_SIZE); + memcpy(control_page, relocate_kernel, PAGE_SIZE/2); + relocate_kernel_ptr = control_page; page_list[PA_CONTROL_PAGE] = __pa(control_page); - page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel; + page_list[VA_CONTROL_PAGE] = (unsigned long)control_page; page_list[PA_PGD] = __pa(kexec_pgd); page_list[VA_PGD] = (unsigned long)kexec_pgd; #ifdef CONFIG_X86_PAE @@ -131,6 +155,7 @@ NORET_TYPE void machine_kexec(struct kimage *image) page_list[VA_PTE_0] = (unsigned long)kexec_pte0; page_list[PA_PTE_1] = __pa(kexec_pte1); page_list[VA_PTE_1] = (unsigned long)kexec_pte1; + page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT); /* The segment registers are funny things, they have both a * visible and an invisible part. Whenever the visible part is @@ -149,8 +174,10 @@ NORET_TYPE void machine_kexec(struct kimage *image) set_idt(phys_to_virt(0),0); /* now call it */ - relocate_kernel((unsigned long)image->head, (unsigned long)page_list, - image->start, cpu_has_pae); + image->start = relocate_kernel_ptr((unsigned long)image->head, + (unsigned long)page_list, + image->start, cpu_has_pae, + image->preserve_context); } void arch_crash_save_vmcoreinfo(void) diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 9dd9262693a3..c43caa3a91f3 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -181,7 +181,7 @@ void machine_kexec_cleanup(struct kimage *image) * Do not allocate memory (or fail in any way) in machine_kexec(). * We are past the point of no return, committed to rebooting now. */ -NORET_TYPE void machine_kexec(struct kimage *image) +void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; void *control_page; diff --git a/arch/x86/kernel/module_64.c b/arch/x86/kernel/module_64.c index 0e867676b5a5..6ba87830d4b1 100644 --- a/arch/x86/kernel/module_64.c +++ b/arch/x86/kernel/module_64.c @@ -22,6 +22,7 @@ #include <linux/fs.h> #include <linux/string.h> #include <linux/kernel.h> +#include <linux/mm.h> #include <linux/slab.h> #include <linux/bug.h> diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 151f2d171f7c..b67a4b1d4eae 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -29,6 +29,7 @@ #include <linux/mm.h> #include <linux/spinlock.h> #include <linux/string.h> +#include <linux/crash_dump.h> #include <linux/dma-mapping.h> #include <linux/bitops.h> #include <linux/pci_ids.h> @@ -36,6 +37,7 @@ #include <linux/delay.h> #include <linux/scatterlist.h> #include <linux/iommu-helper.h> + #include <asm/iommu.h> #include <asm/calgary.h> #include <asm/tce.h> @@ -167,6 +169,8 @@ static void calgary_dump_error_regs(struct iommu_table *tbl); static void calioc2_handle_quirks(struct iommu_table *tbl, struct pci_dev *dev); static void calioc2_tce_cache_blast(struct iommu_table *tbl); static void calioc2_dump_error_regs(struct iommu_table *tbl); +static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl); +static void get_tce_space_from_tar(void); static struct cal_chipset_ops calgary_chip_ops = { .handle_quirks = calgary_handle_quirks, @@ -410,22 +414,6 @@ static void calgary_unmap_sg(struct device *dev, } } -static int calgary_nontranslate_map_sg(struct device* dev, - struct scatterlist *sg, int nelems, int direction) -{ - struct scatterlist *s; - int i; - - for_each_sg(sg, s, nelems, i) { - struct page *p = sg_page(s); - - BUG_ON(!p); - s->dma_address = virt_to_bus(sg_virt(s)); - s->dma_length = s->length; - } - return nelems; -} - static int calgary_map_sg(struct device *dev, struct scatterlist *sg, int nelems, int direction) { @@ -436,9 +424,6 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, unsigned long entry; int i; - if (!translation_enabled(tbl)) - return calgary_nontranslate_map_sg(dev, sg, nelems, direction); - for_each_sg(sg, s, nelems, i) { BUG_ON(!sg_page(s)); @@ -474,7 +459,6 @@ error: static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr, size_t size, int direction) { - dma_addr_t dma_handle = bad_dma_address; void *vaddr = phys_to_virt(paddr); unsigned long uaddr; unsigned int npages; @@ -483,12 +467,7 @@ static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr, uaddr = (unsigned long)vaddr; npages = num_dma_pages(uaddr, size); - if (translation_enabled(tbl)) - dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction); - else - dma_handle = virt_to_bus(vaddr); - - return dma_handle; + return iommu_alloc(dev, tbl, vaddr, npages, direction); } static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle, @@ -497,9 +476,6 @@ static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle, struct iommu_table *tbl = find_iommu_table(dev); unsigned int npages; - if (!translation_enabled(tbl)) - return; - npages = num_dma_pages(dma_handle, size); iommu_free(tbl, dma_handle, npages); } @@ -522,18 +498,12 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size, goto error; memset(ret, 0, size); - if (translation_enabled(tbl)) { - /* set up tces to cover the allocated range */ - mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL); - if (mapping == bad_dma_address) - goto free; - - *dma_handle = mapping; - } else /* non translated slot */ - *dma_handle = virt_to_bus(ret); - + /* set up tces to cover the allocated range */ + mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL); + if (mapping == bad_dma_address) + goto free; + *dma_handle = mapping; return ret; - free: free_pages((unsigned long)ret, get_order(size)); ret = NULL; @@ -541,7 +511,7 @@ error: return ret; } -static const struct dma_mapping_ops calgary_dma_ops = { +static struct dma_mapping_ops calgary_dma_ops = { .alloc_coherent = calgary_alloc_coherent, .map_single = calgary_map_single, .unmap_single = calgary_unmap_single, @@ -830,7 +800,11 @@ static int __init calgary_setup_tar(struct pci_dev *dev, void __iomem *bbar) tbl = pci_iommu(dev->bus); tbl->it_base = (unsigned long)bus_info[dev->bus->number].tce_space; - tce_free(tbl, 0, tbl->it_size); + + if (is_kdump_kernel()) + calgary_init_bitmap_from_tce_table(tbl); + else + tce_free(tbl, 0, tbl->it_size); if (is_calgary(dev->device)) tbl->chip_ops = &calgary_chip_ops; @@ -1209,6 +1183,10 @@ static int __init calgary_init(void) if (ret) return ret; + /* Purely for kdump kernel case */ + if (is_kdump_kernel()) + get_tce_space_from_tar(); + do { dev = pci_get_device(PCI_VENDOR_ID_IBM, PCI_ANY_ID, dev); if (!dev) @@ -1230,6 +1208,16 @@ static int __init calgary_init(void) goto error; } while (1); + dev = NULL; + for_each_pci_dev(dev) { + struct iommu_table *tbl; + + tbl = find_iommu_table(&dev->dev); + + if (translation_enabled(tbl)) + dev->dev.archdata.dma_ops = &calgary_dma_ops; + } + return ret; error: @@ -1251,6 +1239,7 @@ error: calgary_disable_translation(dev); calgary_free_bus(dev); pci_dev_put(dev); /* Undo calgary_init_one()'s pci_dev_get() */ + dev->dev.archdata.dma_ops = NULL; } while (1); return ret; @@ -1339,6 +1328,61 @@ static int __init calgary_bus_has_devices(int bus, unsigned short pci_dev) return (val != 0xffffffff); } +/* + * calgary_init_bitmap_from_tce_table(): + * Funtion for kdump case. In the second/kdump kernel initialize + * the bitmap based on the tce table entries obtained from first kernel + */ +static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl) +{ + u64 *tp; + unsigned int index; + tp = ((u64 *)tbl->it_base); + for (index = 0 ; index < tbl->it_size; index++) { + if (*tp != 0x0) + set_bit(index, tbl->it_map); + tp++; + } +} + +/* + * get_tce_space_from_tar(): + * Function for kdump case. Get the tce tables from first kernel + * by reading the contents of the base adress register of calgary iommu + */ +static void get_tce_space_from_tar() +{ + int bus; + void __iomem *target; + unsigned long tce_space; + + for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) { + struct calgary_bus_info *info = &bus_info[bus]; + unsigned short pci_device; + u32 val; + + val = read_pci_config(bus, 0, 0, 0); + pci_device = (val & 0xFFFF0000) >> 16; + + if (!is_cal_pci_dev(pci_device)) + continue; + if (info->translation_disabled) + continue; + + if (calgary_bus_has_devices(bus, pci_device) || + translate_empty_slots) { + target = calgary_reg(bus_info[bus].bbar, + tar_offset(bus)); + tce_space = be64_to_cpu(readq(target)); + tce_space = tce_space & TAR_SW_BITS; + + tce_space = tce_space & (~specified_table_size); + info->tce_space = (u64 *)__va(tce_space); + } + } + return; +} + void __init detect_calgary(void) { int bus; @@ -1394,7 +1438,8 @@ void __init detect_calgary(void) return; } - specified_table_size = determine_tce_table_size(max_pfn * PAGE_SIZE); + specified_table_size = determine_tce_table_size((is_kdump_kernel() ? + saved_max_pfn : max_pfn) * PAGE_SIZE); for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) { struct calgary_bus_info *info = &bus_info[bus]; @@ -1412,10 +1457,16 @@ void __init detect_calgary(void) if (calgary_bus_has_devices(bus, pci_device) || translate_empty_slots) { - tbl = alloc_tce_table(); - if (!tbl) - goto cleanup; - info->tce_space = tbl; + /* + * If it is kdump kernel, find and use tce tables + * from first kernel, else allocate tce tables here + */ + if (!is_kdump_kernel()) { + tbl = alloc_tce_table(); + if (!tbl) + goto cleanup; + info->tce_space = tbl; + } calgary_found = 1; } } @@ -1430,6 +1481,10 @@ void __init detect_calgary(void) printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d, " "CONFIG_IOMMU_DEBUG is %s.\n", specified_table_size, debugging ? "enabled" : "disabled"); + + /* swiotlb for devices that aren't behind the Calgary. */ + if (max_pfn > MAX_DMA32_PFN) + swiotlb = 1; } return; @@ -1446,7 +1501,7 @@ int __init calgary_iommu_init(void) { int ret; - if (no_iommu || swiotlb) + if (no_iommu || (swiotlb && !calgary_detected)) return -ENODEV; if (!calgary_detected) @@ -1459,15 +1514,14 @@ int __init calgary_iommu_init(void) if (ret) { printk(KERN_ERR "PCI-DMA: Calgary init failed %d, " "falling back to no_iommu\n", ret); - if (max_pfn > MAX_DMA32_PFN) - printk(KERN_ERR "WARNING more than 4GB of memory, " - "32bit PCI may malfunction.\n"); return ret; } force_iommu = 1; bad_dma_address = 0x0; - dma_ops = &calgary_dma_ops; + /* dma_ops is set to swiotlb or nommu */ + if (!dma_ops) + dma_ops = &nommu_dma_ops; return 0; } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index cbecb05551bb..37544123896d 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -11,7 +11,7 @@ static int forbid_dac __read_mostly; -const struct dma_mapping_ops *dma_ops; +struct dma_mapping_ops *dma_ops; EXPORT_SYMBOL(dma_ops); static int iommu_sac_force __read_mostly; @@ -312,6 +312,8 @@ static int dma_release_coherent(struct device *dev, int order, void *vaddr) int dma_supported(struct device *dev, u64 mask) { + struct dma_mapping_ops *ops = get_dma_ops(dev); + #ifdef CONFIG_PCI if (mask > 0xffffffff && forbid_dac > 0) { dev_info(dev, "PCI: Disallowing DAC for device\n"); @@ -319,8 +321,8 @@ int dma_supported(struct device *dev, u64 mask) } #endif - if (dma_ops->dma_supported) - return dma_ops->dma_supported(dev, mask); + if (ops->dma_supported) + return ops->dma_supported(dev, mask); /* Copied from i386. Doesn't make much sense, because it will only work for pci_alloc_coherent. @@ -367,6 +369,7 @@ void * dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { + struct dma_mapping_ops *ops = get_dma_ops(dev); void *memory = NULL; struct page *page; unsigned long dma_mask = 0; @@ -435,8 +438,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, /* Let low level make its own zone decisions */ gfp &= ~(GFP_DMA32|GFP_DMA); - if (dma_ops->alloc_coherent) - return dma_ops->alloc_coherent(dev, size, + if (ops->alloc_coherent) + return ops->alloc_coherent(dev, size, dma_handle, gfp); return NULL; } @@ -448,14 +451,14 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, } } - if (dma_ops->alloc_coherent) { + if (ops->alloc_coherent) { free_pages((unsigned long)memory, get_order(size)); gfp &= ~(GFP_DMA|GFP_DMA32); - return dma_ops->alloc_coherent(dev, size, dma_handle, gfp); + return ops->alloc_coherent(dev, size, dma_handle, gfp); } - if (dma_ops->map_simple) { - *dma_handle = dma_ops->map_simple(dev, virt_to_phys(memory), + if (ops->map_simple) { + *dma_handle = ops->map_simple(dev, virt_to_phys(memory), size, PCI_DMA_BIDIRECTIONAL); if (*dma_handle != bad_dma_address) @@ -477,12 +480,14 @@ EXPORT_SYMBOL(dma_alloc_coherent); void dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t bus) { + struct dma_mapping_ops *ops = get_dma_ops(dev); + int order = get_order(size); WARN_ON(irqs_disabled()); /* for portability */ if (dma_release_coherent(dev, order, vaddr)) return; - if (dma_ops->unmap_single) - dma_ops->unmap_single(dev, bus, size, 0); + if (ops->unmap_single) + ops->unmap_single(dev, bus, size, 0); free_pages((unsigned long)vaddr, order); } EXPORT_SYMBOL(dma_free_coherent); diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index df5f142657d2..744126e64950 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -692,8 +692,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info) extern int agp_amd64_init(void); -static const struct dma_mapping_ops gart_dma_ops = { - .mapping_error = NULL, +static struct dma_mapping_ops gart_dma_ops = { .map_single = gart_map_single, .map_simple = gart_map_simple, .unmap_single = gart_unmap_single, diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 792b9179eff3..3f91f71cdc3e 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -72,21 +72,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, return nents; } -/* Make sure we keep the same behaviour */ -static int nommu_mapping_error(dma_addr_t dma_addr) -{ -#ifdef CONFIG_X86_32 - return 0; -#else - return (dma_addr == bad_dma_address); -#endif -} - - -const struct dma_mapping_ops nommu_dma_ops = { +struct dma_mapping_ops nommu_dma_ops = { .map_single = nommu_map_single, .map_sg = nommu_map_sg, - .mapping_error = nommu_mapping_error, .is_phys = 1, }; diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index 20df839b9c20..c4ce0332759e 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -18,7 +18,7 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size, return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction); } -const struct dma_mapping_ops swiotlb_dma_ops = { +struct dma_mapping_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, .alloc_coherent = swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 0c3927accb00..53bc653ed5ca 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -128,7 +128,7 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(); + tick_nohz_stop_sched_tick(1); while (!need_resched()) { check_pgt_cache(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e8a8e1b99817..3fb62a7d9a16 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -120,7 +120,7 @@ void cpu_idle(void) current_thread_info()->status |= TS_POLLING; /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(); + tick_nohz_stop_sched_tick(1); while (!need_resched()) { rmb(); diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index c30fe25d470d..703310a99023 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -20,11 +20,44 @@ #define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) #define PAE_PGD_ATTR (_PAGE_PRESENT) +/* control_page + PAGE_SIZE/2 ~ control_page + PAGE_SIZE * 3/4 are + * used to save some data for jumping back + */ +#define DATA(offset) (PAGE_SIZE/2+(offset)) + +/* Minimal CPU state */ +#define ESP DATA(0x0) +#define CR0 DATA(0x4) +#define CR3 DATA(0x8) +#define CR4 DATA(0xc) + +/* other data */ +#define CP_VA_CONTROL_PAGE DATA(0x10) +#define CP_PA_PGD DATA(0x14) +#define CP_PA_SWAP_PAGE DATA(0x18) +#define CP_PA_BACKUP_PAGES_MAP DATA(0x1c) + .text .align PAGE_SIZE .globl relocate_kernel relocate_kernel: - movl 8(%esp), %ebp /* list of pages */ + /* Save the CPU context, used for jumping back */ + + pushl %ebx + pushl %esi + pushl %edi + pushl %ebp + pushf + + movl 20+8(%esp), %ebp /* list of pages */ + movl PTR(VA_CONTROL_PAGE)(%ebp), %edi + movl %esp, ESP(%edi) + movl %cr0, %eax + movl %eax, CR0(%edi) + movl %cr3, %eax + movl %eax, CR3(%edi) + movl %cr4, %eax + movl %eax, CR4(%edi) #ifdef CONFIG_X86_PAE /* map the control page at its virtual address */ @@ -138,15 +171,25 @@ relocate_kernel: relocate_new_kernel: /* read the arguments and say goodbye to the stack */ - movl 4(%esp), %ebx /* page_list */ - movl 8(%esp), %ebp /* list of pages */ - movl 12(%esp), %edx /* start address */ - movl 16(%esp), %ecx /* cpu_has_pae */ + movl 20+4(%esp), %ebx /* page_list */ + movl 20+8(%esp), %ebp /* list of pages */ + movl 20+12(%esp), %edx /* start address */ + movl 20+16(%esp), %ecx /* cpu_has_pae */ + movl 20+20(%esp), %esi /* preserve_context */ /* zero out flags, and disable interrupts */ pushl $0 popfl + /* save some information for jumping back */ + movl PTR(VA_CONTROL_PAGE)(%ebp), %edi + movl %edi, CP_VA_CONTROL_PAGE(%edi) + movl PTR(PA_PGD)(%ebp), %eax + movl %eax, CP_PA_PGD(%edi) + movl PTR(PA_SWAP_PAGE)(%ebp), %eax + movl %eax, CP_PA_SWAP_PAGE(%edi) + movl %ebx, CP_PA_BACKUP_PAGES_MAP(%edi) + /* get physical address of control page now */ /* this is impossible after page table switch */ movl PTR(PA_CONTROL_PAGE)(%ebp), %edi @@ -197,8 +240,90 @@ identity_mapped: xorl %eax, %eax movl %eax, %cr3 + movl CP_PA_SWAP_PAGE(%edi), %eax + pushl %eax + pushl %ebx + call swap_pages + addl $8, %esp + + /* To be certain of avoiding problems with self-modifying code + * I need to execute a serializing instruction here. + * So I flush the TLB, it's handy, and not processor dependent. + */ + xorl %eax, %eax + movl %eax, %cr3 + + /* set all of the registers to known values */ + /* leave %esp alone */ + + testl %esi, %esi + jnz 1f + xorl %edi, %edi + xorl %eax, %eax + xorl %ebx, %ebx + xorl %ecx, %ecx + xorl %edx, %edx + xorl %esi, %esi + xorl %ebp, %ebp + ret +1: + popl %edx + movl CP_PA_SWAP_PAGE(%edi), %esp + addl $PAGE_SIZE, %esp +2: + call *%edx + + /* get the re-entry point of the peer system */ + movl 0(%esp), %ebp + call 1f +1: + popl %ebx + subl $(1b - relocate_kernel), %ebx + movl CP_VA_CONTROL_PAGE(%ebx), %edi + lea PAGE_SIZE(%ebx), %esp + movl CP_PA_SWAP_PAGE(%ebx), %eax + movl CP_PA_BACKUP_PAGES_MAP(%ebx), %edx + pushl %eax + pushl %edx + call swap_pages + addl $8, %esp + movl CP_PA_PGD(%ebx), %eax + movl %eax, %cr3 + movl %cr0, %eax + orl $(1<<31), %eax + movl %eax, %cr0 + lea PAGE_SIZE(%edi), %esp + movl %edi, %eax + addl $(virtual_mapped - relocate_kernel), %eax + pushl %eax + ret + +virtual_mapped: + movl CR4(%edi), %eax + movl %eax, %cr4 + movl CR3(%edi), %eax + movl %eax, %cr3 + movl CR0(%edi), %eax + movl %eax, %cr0 + movl ESP(%edi), %esp + movl %ebp, %eax + + popf + popl %ebp + popl %edi + popl %esi + popl %ebx + ret + /* Do the copies */ - movl %ebx, %ecx +swap_pages: + movl 8(%esp), %edx + movl 4(%esp), %ecx + pushl %ebp + pushl %ebx + pushl %edi + pushl %esi + movl %ecx, %ebx jmp 1f 0: /* top, read another word from the indirection page */ @@ -226,27 +351,28 @@ identity_mapped: movl %ecx, %esi /* For every source page do a copy */ andl $0xfffff000, %esi + movl %edi, %eax + movl %esi, %ebp + + movl %edx, %edi movl $1024, %ecx rep ; movsl - jmp 0b -3: - - /* To be certain of avoiding problems with self-modifying code - * I need to execute a serializing instruction here. - * So I flush the TLB, it's handy, and not processor dependent. - */ - xorl %eax, %eax - movl %eax, %cr3 + movl %ebp, %edi + movl %eax, %esi + movl $1024, %ecx + rep ; movsl - /* set all of the registers to known values */ - /* leave %esp alone */ + movl %eax, %edi + movl %edx, %esi + movl $1024, %ecx + rep ; movsl - xorl %eax, %eax - xorl %ebx, %ebx - xorl %ecx, %ecx - xorl %edx, %edx - xorl %esi, %esi - xorl %edi, %edi - xorl %ebp, %ebp + lea PAGE_SIZE(%ebp), %esi + jmp 0b +3: + popl %esi + popl %edi + popl %ebx + popl %ebp ret diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b4aacb9f52e3..b520dae02bf4 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -597,11 +597,11 @@ void __init setup_arch(char **cmdline_p) memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); visws_early_detect(); pre_setup_arch_hook(); - early_cpu_init(); #else printk(KERN_INFO "Command line: %s\n", boot_command_line); #endif + early_cpu_init(); early_ioremap_init(); ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); @@ -665,9 +665,6 @@ void __init setup_arch(char **cmdline_p) bss_resource.start = virt_to_phys(&__bss_start); bss_resource.end = virt_to_phys(&__bss_stop)-1; -#ifdef CONFIG_X86_64 - early_cpu_init(); -#endif strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index 47c3d249e638..b45ef8ddd651 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -53,6 +53,59 @@ sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, return do_sigaltstack(uss, uoss, regs->sp); } +/* + * Signal frame handlers. + */ + +static inline int save_i387(struct _fpstate __user *buf) +{ + struct task_struct *tsk = current; + int err = 0; + + BUILD_BUG_ON(sizeof(struct user_i387_struct) != + sizeof(tsk->thread.xstate->fxsave)); + + if ((unsigned long)buf % 16) + printk("save_i387: bad fpstate %p\n", buf); + + if (!used_math()) + return 0; + clear_used_math(); /* trigger finit */ + if (task_thread_info(tsk)->status & TS_USEDFPU) { + err = save_i387_checking((struct i387_fxsave_struct __user *) + buf); + if (err) + return err; + task_thread_info(tsk)->status &= ~TS_USEDFPU; + stts(); + } else { + if (__copy_to_user(buf, &tsk->thread.xstate->fxsave, + sizeof(struct i387_fxsave_struct))) + return -1; + } + return 1; +} + +/* + * This restores directly out of user space. Exceptions are handled. + */ +static inline int restore_i387(struct _fpstate __user *buf) +{ + struct task_struct *tsk = current; + int err; + + if (!used_math()) { + err = init_fpu(tsk); + if (err) + return err; + } + + if (!(task_thread_info(current)->status & TS_USEDFPU)) { + clts(); + task_thread_info(current)->status |= TS_USEDFPU; + } + return restore_fpu_checking((__force struct i387_fxsave_struct *)buf); +} /* * Do a signal return; undo the signal stack. diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index adff5562f5fd..d44395ff34c3 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -326,3 +326,9 @@ ENTRY(sys_call_table) .long sys_fallocate .long sys_timerfd_settime /* 325 */ .long sys_timerfd_gettime + .long sys_signalfd4 + .long sys_eventfd2 + .long sys_epoll_create1 + .long sys_dup3 /* 330 */ + .long sys_pipe2 + .long sys_inotify_init1 diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 1fbb844c3d7a..2977ea37791f 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -1,6 +1,7 @@ obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ pat.o pgtable.o +obj-$(CONFIG_HAVE_GET_USER_PAGES_FAST) += gup.o obj-$(CONFIG_X86_32) += pgtable_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c index 5dfef9fa061a..62fa440678d8 100644 --- a/arch/x86/mm/discontig_32.c +++ b/arch/x86/mm/discontig_32.c @@ -42,7 +42,6 @@ struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); -static bootmem_data_t node0_bdata; /* * numa interface - we expect the numa architecture specific code to have @@ -385,7 +384,7 @@ void __init initmem_init(unsigned long start_pfn, for_each_online_node(nid) memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); - NODE_DATA(0)->bdata = &node0_bdata; + NODE_DATA(0)->bdata = &bootmem_node_data[0]; setup_bootmem_allocator(); } diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c new file mode 100644 index 000000000000..3085f25b4355 --- /dev/null +++ b/arch/x86/mm/gup.c @@ -0,0 +1,295 @@ +/* + * Lockless get_user_pages_fast for x86 + * + * Copyright (C) 2008 Nick Piggin + * Copyright (C) 2008 Novell Inc. + */ +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmstat.h> +#include <linux/highmem.h> + +#include <asm/pgtable.h> + +static inline pte_t gup_get_pte(pte_t *ptep) +{ +#ifndef CONFIG_X86_PAE + return *ptep; +#else + /* + * With get_user_pages_fast, we walk down the pagetables without taking + * any locks. For this we would like to load the pointers atoimcally, + * but that is not possible (without expensive cmpxchg8b) on PAE. What + * we do have is the guarantee that a pte will only either go from not + * present to present, or present to not present or both -- it will not + * switch to a completely different present page without a TLB flush in + * between; something that we are blocking by holding interrupts off. + * + * Setting ptes from not present to present goes: + * ptep->pte_high = h; + * smp_wmb(); + * ptep->pte_low = l; + * + * And present to not present goes: + * ptep->pte_low = 0; + * smp_wmb(); + * ptep->pte_high = 0; + * + * We must ensure here that the load of pte_low sees l iff pte_high + * sees h. We load pte_high *after* loading pte_low, which ensures we + * don't see an older value of pte_high. *Then* we recheck pte_low, + * which ensures that we haven't picked up a changed pte high. We might + * have got rubbish values from pte_low and pte_high, but we are + * guaranteed that pte_low will not have the present bit set *unless* + * it is 'l'. And get_user_pages_fast only operates on present ptes, so + * we're safe. + * + * gup_get_pte should not be used or copied outside gup.c without being + * very careful -- it does not atomically load the pte or anything that + * is likely to be useful for you. + */ + pte_t pte; + +retry: + pte.pte_low = ptep->pte_low; + smp_rmb(); + pte.pte_high = ptep->pte_high; + smp_rmb(); + if (unlikely(pte.pte_low != ptep->pte_low)) + goto retry; + + return pte; +#endif +} + +/* + * The performance critical leaf functions are made noinline otherwise gcc + * inlines everything into a single function which results in too much + * register pressure. + */ +static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask; + pte_t *ptep; + + mask = _PAGE_PRESENT|_PAGE_USER; + if (write) + mask |= _PAGE_RW; + + ptep = pte_offset_map(&pmd, addr); + do { + pte_t pte = gup_get_pte(ptep); + struct page *page; + + if ((pte_val(pte) & (mask | _PAGE_SPECIAL)) != mask) { + pte_unmap(ptep); + return 0; + } + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + page = pte_page(pte); + get_page(page); + pages[*nr] = page; + (*nr)++; + + } while (ptep++, addr += PAGE_SIZE, addr != end); + pte_unmap(ptep - 1); + + return 1; +} + +static inline void get_head_page_multiple(struct page *page, int nr) +{ + VM_BUG_ON(page != compound_head(page)); + VM_BUG_ON(page_count(page) == 0); + atomic_add(nr, &page->_count); +} + +static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask; + pte_t pte = *(pte_t *)&pmd; + struct page *head, *page; + int refs; + + mask = _PAGE_PRESENT|_PAGE_USER; + if (write) + mask |= _PAGE_RW; + if ((pte_val(pte) & mask) != mask) + return 0; + /* hugepages are never "special" */ + VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL); + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + refs = 0; + head = pte_page(pte); + page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + do { + VM_BUG_ON(compound_head(page) != head); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + get_head_page_multiple(head, refs); + + return 1; +} + +static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pmd_t *pmdp; + + pmdp = pmd_offset(&pud, addr); + do { + pmd_t pmd = *pmdp; + + next = pmd_addr_end(addr, end); + if (pmd_none(pmd)) + return 0; + if (unlikely(pmd_large(pmd))) { + if (!gup_huge_pmd(pmd, addr, next, write, pages, nr)) + return 0; + } else { + if (!gup_pte_range(pmd, addr, next, write, pages, nr)) + return 0; + } + } while (pmdp++, addr = next, addr != end); + + return 1; +} + +static noinline int gup_huge_pud(pud_t pud, unsigned long addr, + unsigned long end, int write, struct page **pages, int *nr) +{ + unsigned long mask; + pte_t pte = *(pte_t *)&pud; + struct page *head, *page; + int refs; + + mask = _PAGE_PRESENT|_PAGE_USER; + if (write) + mask |= _PAGE_RW; + if ((pte_val(pte) & mask) != mask) + return 0; + /* hugepages are never "special" */ + VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL); + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + + refs = 0; + head = pte_page(pte); + page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + do { + VM_BUG_ON(compound_head(page) != head); + pages[*nr] = page; + (*nr)++; + page++; + refs++; + } while (addr += PAGE_SIZE, addr != end); + get_head_page_multiple(head, refs); + + return 1; +} + +static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, + int write, struct page **pages, int *nr) +{ + unsigned long next; + pud_t *pudp; + + pudp = pud_offset(&pgd, addr); + do { + pud_t pud = *pudp; + + next = pud_addr_end(addr, end); + if (pud_none(pud)) + return 0; + if (unlikely(pud_large(pud))) { + if (!gup_huge_pud(pud, addr, next, write, pages, nr)) + return 0; + } else { + if (!gup_pmd_range(pud, addr, next, write, pages, nr)) + return 0; + } + } while (pudp++, addr = next, addr != end); + + return 1; +} + +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages) +{ + struct mm_struct *mm = current->mm; + unsigned long end = start + (nr_pages << PAGE_SHIFT); + unsigned long addr = start; + unsigned long next; + pgd_t *pgdp; + int nr = 0; + + if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, + start, nr_pages*PAGE_SIZE))) + goto slow_irqon; + + /* + * XXX: batch / limit 'nr', to avoid large irq off latency + * needs some instrumenting to determine the common sizes used by + * important workloads (eg. DB2), and whether limiting the batch size + * will decrease performance. + * + * It seems like we're in the clear for the moment. Direct-IO is + * the main guy that batches up lots of get_user_pages, and even + * they are limited to 64-at-a-time which is not so many. + */ + /* + * This doesn't prevent pagetable teardown, but does prevent + * the pagetables and pages from being freed on x86. + * + * So long as we atomically load page table pointers versus teardown + * (which we do on x86, with the above PAE exception), we can follow the + * address down to the the page and take a ref on it. + */ + local_irq_disable(); + pgdp = pgd_offset(mm, addr); + do { + pgd_t pgd = *pgdp; + + next = pgd_addr_end(addr, end); + if (pgd_none(pgd)) + goto slow; + if (!gup_pud_range(pgd, addr, next, write, pages, &nr)) + goto slow; + } while (pgdp++, addr = next, addr != end); + local_irq_enable(); + + VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); + return nr; + + { + int ret; + +slow: + local_irq_enable(); +slow_irqon: + /* Try to get the remaining pages with get_user_pages */ + start += nr << PAGE_SHIFT; + pages += nr; + + down_read(&mm->mmap_sem); + ret = get_user_pages(current, mm, start, + (end - start) >> PAGE_SHIFT, write, 0, pages, NULL); + up_read(&mm->mmap_sem); + + /* Have to be a bit careful with return values */ + if (nr > 0) { + if (ret < 0) + ret = nr; + else + ret += nr; + } + + return ret; + } +} diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 0b3d567e686d..8f307d914c2e 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -124,7 +124,8 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) return 1; } -pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) { pgd_t *pgd; pud_t *pud; @@ -133,9 +134,14 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr) pgd = pgd_offset(mm, addr); pud = pud_alloc(mm, pgd, addr); if (pud) { - if (pud_none(*pud)) - huge_pmd_share(mm, addr, pud); - pte = (pte_t *) pmd_alloc(mm, pud, addr); + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + } else { + BUG_ON(sz != PMD_SIZE); + if (pud_none(*pud)) + huge_pmd_share(mm, addr, pud); + pte = (pte_t *) pmd_alloc(mm, pud, addr); + } } BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); @@ -151,8 +157,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) pgd = pgd_offset(mm, addr); if (pgd_present(*pgd)) { pud = pud_offset(pgd, addr); - if (pud_present(*pud)) + if (pud_present(*pud)) { + if (pud_large(*pud)) + return (pte_t *)pud; pmd = pmd_offset(pud, addr); + } } return (pte_t *) pmd; } @@ -188,6 +197,11 @@ 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) @@ -208,6 +222,11 @@ int pmd_huge(pmd_t pmd) return !!(pmd_val(pmd) & _PAGE_PSE); } +int pud_huge(pud_t pud) +{ + return !!(pud_val(pud) & _PAGE_PSE); +} + struct page * follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write) @@ -216,9 +235,22 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, page = pte_page(*(pte_t *)pmd); if (page) - page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT); + page += ((address & ~PMD_MASK) >> PAGE_SHIFT); + return page; +} + +struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + struct page *page; + + page = pte_page(*(pte_t *)pud); + if (page) + page += ((address & ~PUD_MASK) >> PAGE_SHIFT); return page; } + #endif /* x86_64 also uses this file */ @@ -228,6 +260,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { + struct hstate *h = hstate_file(file); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; unsigned long start_addr; @@ -240,7 +273,7 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, } full_search: - addr = ALIGN(start_addr, HPAGE_SIZE); + addr = ALIGN(start_addr, huge_page_size(h)); for (vma = find_vma(mm, addr); ; vma = vma->vm_next) { /* At this point: (!vma || addr < vma->vm_end). */ @@ -262,7 +295,7 @@ full_search: } if (addr + mm->cached_hole_size < vma->vm_start) mm->cached_hole_size = vma->vm_start - addr; - addr = ALIGN(vma->vm_end, HPAGE_SIZE); + addr = ALIGN(vma->vm_end, huge_page_size(h)); } } @@ -270,6 +303,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr0, unsigned long len, unsigned long pgoff, unsigned long flags) { + struct hstate *h = hstate_file(file); struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev_vma; unsigned long base = mm->mmap_base, addr = addr0; @@ -290,7 +324,7 @@ try_again: goto fail; /* either no address requested or cant fit in requested address hole */ - addr = (mm->free_area_cache - len) & HPAGE_MASK; + addr = (mm->free_area_cache - len) & huge_page_mask(h); do { /* * Lookup failure means no vma is above this address, @@ -321,7 +355,7 @@ try_again: largest_hole = vma->vm_start - addr; /* try just below the current vma->vm_start */ - addr = (vma->vm_start - len) & HPAGE_MASK; + addr = (vma->vm_start - len) & huge_page_mask(h); } while (len <= vma->vm_start); fail: @@ -359,22 +393,23 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { + struct hstate *h = hstate_file(file); struct mm_struct *mm = current->mm; struct vm_area_struct *vma; - if (len & ~HPAGE_MASK) + if (len & ~huge_page_mask(h)) return -EINVAL; if (len > TASK_SIZE) return -ENOMEM; if (flags & MAP_FIXED) { - if (prepare_hugepage_range(addr, len)) + if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } if (addr) { - addr = ALIGN(addr, HPAGE_SIZE); + addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && (!vma || addr + len <= vma->vm_start)) @@ -390,3 +425,20 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, #endif /*HAVE_ARCH_HUGETLB_UNMAPPED_AREA*/ +#ifdef CONFIG_X86_64 +static __init int setup_hugepagesz(char *opt) +{ + unsigned long ps = memparse(opt, &opt); + if (ps == PMD_SIZE) { + hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); + } else if (ps == PUD_SIZE && cpu_has_gbpages) { + hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + } else { + printk(KERN_ERR "hugepagesz: Unsupported page size %lu M\n", + ps >> 20); + return 0; + } + return 1; +} +__setup("hugepagesz=", setup_hugepagesz); +#endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index ec37121f6709..129618ca0ea2 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -86,43 +86,6 @@ early_param("gbpages", parse_direct_gbpages_on); * around without checking the pgd every time. */ -void show_mem(void) -{ - long i, total = 0, reserved = 0; - long shared = 0, cached = 0; - struct page *page; - pg_data_t *pgdat; - - printk(KERN_INFO "Mem-info:\n"); - show_free_areas(); - for_each_online_pgdat(pgdat) { - for (i = 0; i < pgdat->node_spanned_pages; ++i) { - /* - * This loop can take a while with 256 GB and - * 4k pages so defer the NMI watchdog: - */ - if (unlikely(i % MAX_ORDER_NR_PAGES == 0)) - touch_nmi_watchdog(); - - if (!pfn_valid(pgdat->node_start_pfn + i)) - continue; - - page = pfn_to_page(pgdat->node_start_pfn + i); - total++; - if (PageReserved(page)) - reserved++; - else if (PageSwapCache(page)) - cached++; - else if (page_count(page)) - shared += page_count(page) - 1; - } - } - printk(KERN_INFO "%lu pages of RAM\n", total); - printk(KERN_INFO "%lu reserved pages\n", reserved); - printk(KERN_INFO "%lu pages shared\n", shared); - printk(KERN_INFO "%lu pages swap cached\n", cached); -} - int after_bootmem; static __init void *spp_getpage(void) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 24c1d3c30186..016f335bbeea 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -330,6 +330,14 @@ static void __iomem *ioremap_default(resource_size_t phys_addr, return (void __iomem *)ret; } +void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size, + unsigned long prot_val) +{ + return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK), + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_prot); + /** * iounmap - Free a IO remapping * @addr: virtual address from ioremap_* diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 9782f42dd319..a4dd793d6003 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -23,8 +23,6 @@ struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); -static bootmem_data_t plat_node_bdata[MAX_NUMNODES]; - struct memnode memnode; s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = { @@ -198,7 +196,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, nodedata_phys + pgdat_size - 1); memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t)); - NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid]; + NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid]; NODE_DATA(nodeid)->node_start_pfn = start_pfn; NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn; diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index b4becbf8c570..cab0abbd1ebe 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -20,53 +20,6 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> -void show_mem(void) -{ - int total = 0, reserved = 0; - int shared = 0, cached = 0; - int highmem = 0; - struct page *page; - pg_data_t *pgdat; - unsigned long i; - unsigned long flags; - - printk(KERN_INFO "Mem-info:\n"); - show_free_areas(); - for_each_online_pgdat(pgdat) { - pgdat_resize_lock(pgdat, &flags); - for (i = 0; i < pgdat->node_spanned_pages; ++i) { - if (unlikely(i % MAX_ORDER_NR_PAGES == 0)) - touch_nmi_watchdog(); - page = pgdat_page_nr(pgdat, i); - total++; - if (PageHighMem(page)) - highmem++; - if (PageReserved(page)) - reserved++; - else if (PageSwapCache(page)) - cached++; - else if (page_count(page)) - shared += page_count(page) - 1; - } - pgdat_resize_unlock(pgdat, &flags); - } - printk(KERN_INFO "%d pages of RAM\n", total); - printk(KERN_INFO "%d pages of HIGHMEM\n", highmem); - printk(KERN_INFO "%d reserved pages\n", reserved); - printk(KERN_INFO "%d pages shared\n", shared); - printk(KERN_INFO "%d pages swap cached\n", cached); - - printk(KERN_INFO "%lu pages dirty\n", global_page_state(NR_FILE_DIRTY)); - printk(KERN_INFO "%lu pages writeback\n", - global_page_state(NR_WRITEBACK)); - printk(KERN_INFO "%lu pages mapped\n", global_page_state(NR_FILE_MAPPED)); - printk(KERN_INFO "%lu pages slab\n", - global_page_state(NR_SLAB_RECLAIMABLE) + - global_page_state(NR_SLAB_UNRECLAIMABLE)); - printk(KERN_INFO "%lu pages pagetables\n", - global_page_state(NR_PAGETABLE)); -} - /* * Associate a virtual page frame with a given physical page frame * and protection flags for that frame. diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 7f3329b55d2e..3f90289410e6 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -369,20 +369,34 @@ static int __init ppro_init(char **cpu_type) { __u8 cpu_model = boot_cpu_data.x86_model; - if (cpu_model == 14) + switch (cpu_model) { + case 0 ... 2: + *cpu_type = "i386/ppro"; + break; + case 3 ... 5: + *cpu_type = "i386/pii"; + break; + case 6 ... 8: + *cpu_type = "i386/piii"; + break; + case 9: + *cpu_type = "i386/p6_mobile"; + break; + case 10 ... 13: + *cpu_type = "i386/p6"; + break; + case 14: *cpu_type = "i386/core"; - else if (cpu_model == 15 || cpu_model == 23) + break; + case 15: case 23: + *cpu_type = "i386/core_2"; + break; + case 26: *cpu_type = "i386/core_2"; - else if (cpu_model > 0xd) + break; + default: + /* Unknown */ return 0; - else if (cpu_model == 9) { - *cpu_type = "i386/p6_mobile"; - } else if (cpu_model > 5) { - *cpu_type = "i386/piii"; - } else if (cpu_model > 2) { - *cpu_type = "i386/pii"; - } else { - *cpu_type = "i386/ppro"; } model = &op_ppro_spec; diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 2aafb67dc5f1..a09505806b82 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -280,6 +280,7 @@ static void pci_track_mmap_page_range(struct vm_area_struct *vma) static struct vm_operations_struct pci_mmap_ops = { .open = pci_track_mmap_page_range, .close = pci_unmap_page_range, + .access = generic_access_phys, }; int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 4038cbfe3331..7f58304fafb3 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -173,7 +173,7 @@ ENTRY(xen_sysexit) pushq $__USER32_CS pushq %rdx - pushq $VGCF_in_syscall + pushq $0 1: jmp hypercall_iret ENDPATCH(xen_sysexit) RELOC(xen_sysexit, 1b+1) |