diff options
Diffstat (limited to 'arch/x86/kernel')
133 files changed, 2380 insertions, 1873 deletions
diff --git a/arch/x86/kernel/.gitignore b/arch/x86/kernel/.gitignore index 40836ad9079..4ea38a39aed 100644 --- a/arch/x86/kernel/.gitignore +++ b/arch/x86/kernel/.gitignore @@ -1 +1,2 @@ vsyscall.lds +vsyscall_32.lds diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 45855c97923..38573340b14 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -3,3 +3,7 @@ include ${srctree}/arch/x86/kernel/Makefile_32 else include ${srctree}/arch/x86/kernel/Makefile_64 endif + +# Workaround to delete .lds files with make clean +# The problem is that we do not enter Makefile_32 with make clean. +clean-files := vsyscall*.lds vsyscall*.so diff --git a/arch/x86/kernel/Makefile_32 b/arch/x86/kernel/Makefile_32 index 7ff02063b85..a7bc93c2766 100644 --- a/arch/x86/kernel/Makefile_32 +++ b/arch/x86/kernel/Makefile_32 @@ -2,7 +2,8 @@ # Makefile for the linux kernel. # -extra-y := head_32.o init_task_32.o vmlinux.lds +extra-y := head_32.o init_task.o vmlinux.lds +CPPFLAGS_vmlinux.lds += -Ui386 obj-y := process_32.o signal_32.o entry_32.o traps_32.o irq_32.o \ ptrace_32.o time_32.o ioport_32.o ldt_32.o setup_32.o i8259_32.o sys_i386_32.o \ @@ -17,6 +18,7 @@ obj-$(CONFIG_MCA) += mca_32.o obj-$(CONFIG_X86_MSR) += msr.o obj-$(CONFIG_X86_CPUID) += cpuid.o obj-$(CONFIG_MICROCODE) += microcode.o +obj-$(CONFIG_PCI) += early-quirks.o obj-$(CONFIG_APM) += apm_32.o obj-$(CONFIG_X86_SMP) += smp_32.o smpboot_32.o tsc_sync.o obj-$(CONFIG_SMP) += smpcommon_32.o @@ -25,7 +27,7 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse_32.o obj-$(CONFIG_X86_LOCAL_APIC) += apic_32.o nmi_32.o obj-$(CONFIG_X86_IO_APIC) += io_apic_32.o obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o -obj-$(CONFIG_KEXEC) += machine_kexec_32.o relocate_kernel_32.o crash_32.o +obj-$(CONFIG_KEXEC) += machine_kexec_32.o relocate_kernel_32.o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_32.o obj-$(CONFIG_X86_NUMAQ) += numaq_32.o obj-$(CONFIG_X86_SUMMIT_NUMA) += summit_32.o @@ -51,7 +53,7 @@ obj-$(CONFIG_SCx200) += scx200_32.o # We must build both images before we can assemble it. # Note: kbuild does not track this dependency due to usage of .incbin $(obj)/vsyscall_32.o: $(obj)/vsyscall-int80_32.so $(obj)/vsyscall-sysenter_32.so -targets += $(foreach F,int80 sysenter,vsyscall-$F.o vsyscall-$F.so) +targets += $(foreach F,int80 sysenter,vsyscall-$F_32.o vsyscall-$F_32.so) targets += vsyscall-note_32.o vsyscall_32.lds # The DSO images are built using a special linker script. @@ -59,7 +61,7 @@ quiet_cmd_syscall = SYSCALL $@ cmd_syscall = $(CC) -m elf_i386 -nostdlib $(SYSCFLAGS_$(@F)) \ -Wl,-T,$(filter-out FORCE,$^) -o $@ -export CPPFLAGS_vsyscall_32.lds += -P -C -U$(ARCH) +export CPPFLAGS_vsyscall_32.lds += -P -C -Ui386 vsyscall-flags = -shared -s -Wl,-soname=linux-gate.so.1 \ $(call ld-option, -Wl$(comma)--hash-style=sysv) diff --git a/arch/x86/kernel/Makefile_64 b/arch/x86/kernel/Makefile_64 index 43da66213a4..5a88890d8ee 100644 --- a/arch/x86/kernel/Makefile_64 +++ b/arch/x86/kernel/Makefile_64 @@ -2,34 +2,32 @@ # Makefile for the linux kernel. # -extra-y := head_64.o head64.o init_task_64.o vmlinux.lds +extra-y := head_64.o head64.o init_task.o vmlinux.lds +CPPFLAGS_vmlinux.lds += -Ux86_64 EXTRA_AFLAGS := -traditional + obj-y := process_64.o signal_64.o entry_64.o traps_64.o irq_64.o \ ptrace_64.o time_64.o ioport_64.o ldt_64.o setup_64.o i8259_64.o sys_x86_64.o \ x8664_ksyms_64.o i387_64.o syscall_64.o vsyscall_64.o \ setup64.o bootflag.o e820_64.o reboot_64.o quirks.o i8237.o \ pci-dma_64.o pci-nommu_64.o alternative.o hpet.o tsc_64.o bugs_64.o \ - perfctr-watchdog.o i8253.o + i8253.o obj-$(CONFIG_STACKTRACE) += stacktrace.o -obj-$(CONFIG_X86_MCE) += mce_64.o therm_throt.o -obj-$(CONFIG_X86_MCE_INTEL) += mce_intel_64.o -obj-$(CONFIG_X86_MCE_AMD) += mce_amd_64.o -obj-$(CONFIG_MTRR) += cpu/mtrr/ -obj-$(CONFIG_ACPI) += acpi/ +obj-y += cpu/ +obj-y += acpi/ obj-$(CONFIG_X86_MSR) += msr.o obj-$(CONFIG_MICROCODE) += microcode.o obj-$(CONFIG_X86_CPUID) += cpuid.o obj-$(CONFIG_SMP) += smp_64.o smpboot_64.o trampoline_64.o tsc_sync.o obj-y += apic_64.o nmi_64.o obj-y += io_apic_64.o mpparse_64.o genapic_64.o genapic_flat_64.o -obj-$(CONFIG_KEXEC) += machine_kexec_64.o relocate_kernel_64.o crash_64.o +obj-$(CONFIG_KEXEC) += machine_kexec_64.o relocate_kernel_64.o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_64.o obj-$(CONFIG_PM) += suspend_64.o obj-$(CONFIG_HIBERNATION) += suspend_asm_64.o -obj-$(CONFIG_CPU_FREQ) += cpu/cpufreq/ obj-$(CONFIG_EARLY_PRINTK) += early_printk.o -obj-$(CONFIG_IOMMU) += pci-gart_64.o aperture_64.o +obj-$(CONFIG_GART_IOMMU) += pci-gart_64.o aperture_64.o obj-$(CONFIG_CALGARY_IOMMU) += pci-calgary_64.o tce_64.o obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o obj-$(CONFIG_KPROBES) += kprobes_64.o @@ -39,16 +37,9 @@ obj-$(CONFIG_K8_NB) += k8.o obj-$(CONFIG_AUDIT) += audit_64.o obj-$(CONFIG_MODULES) += module_64.o -obj-$(CONFIG_PCI) += early-quirks_64.o +obj-$(CONFIG_PCI) += early-quirks.o obj-y += topology.o -obj-y += intel_cacheinfo.o -obj-y += addon_cpuid_features.o obj-y += pcspeaker.o CFLAGS_vsyscall_64.o := $(PROFILING) -g0 - -therm_throt-y += cpu/mcheck/therm_throt.o -intel_cacheinfo-y += cpu/intel_cacheinfo.o -addon_cpuid_features-y += cpu/addon_cpuid_features.o -perfctr-watchdog-y += cpu/perfctr-watchdog.o diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index 3d567193954..1351c3982ee 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -1,5 +1,7 @@ -ifeq ($(CONFIG_X86_32),y) -include ${srctree}/arch/x86/kernel/acpi/Makefile_32 -else -include ${srctree}/arch/x86/kernel/acpi/Makefile_64 +obj-$(CONFIG_ACPI) += boot.o +obj-$(CONFIG_ACPI_SLEEP) += sleep_$(BITS).o wakeup_$(BITS).o + +ifneq ($(CONFIG_ACPI_PROCESSOR),) +obj-y += cstate.o processor.o endif + diff --git a/arch/x86/kernel/acpi/Makefile_32 b/arch/x86/kernel/acpi/Makefile_32 deleted file mode 100644 index a4852a2e919..00000000000 --- a/arch/x86/kernel/acpi/Makefile_32 +++ /dev/null @@ -1,10 +0,0 @@ -obj-$(CONFIG_ACPI) += boot.o -ifneq ($(CONFIG_PCI),) -obj-$(CONFIG_X86_IO_APIC) += earlyquirk_32.o -endif -obj-$(CONFIG_ACPI_SLEEP) += sleep_32.o wakeup_32.o - -ifneq ($(CONFIG_ACPI_PROCESSOR),) -obj-y += cstate.o processor.o -endif - diff --git a/arch/x86/kernel/acpi/Makefile_64 b/arch/x86/kernel/acpi/Makefile_64 deleted file mode 100644 index 629425bc002..00000000000 --- a/arch/x86/kernel/acpi/Makefile_64 +++ /dev/null @@ -1,7 +0,0 @@ -obj-y := boot.o -obj-$(CONFIG_ACPI_SLEEP) += sleep_64.o wakeup_64.o - -ifneq ($(CONFIG_ACPI_PROCESSOR),) -obj-y += processor.o cstate.o -endif - diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index afd2afe9102..289247d974c 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -99,7 +99,7 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; /* * The default interrupt routing model is PIC (8259). This gets - * overriden if IOAPICs are enumerated (below). + * overridden if IOAPICs are enumerated (below). */ enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PIC; @@ -414,8 +414,8 @@ acpi_parse_nmi_src(struct acpi_subtable_header * header, const unsigned long end * * Port 0x4d0-4d1 are ECLR1 and ECLR2, the Edge/Level Control Registers * for the 8259 PIC. bit[n] = 1 means irq[n] is Level, otherwise Edge. - * ECLR1 is IRQ's 0-7 (IRQ 0, 1, 2 must be 0) - * ECLR2 is IRQ's 8-15 (IRQ 8, 13 must be 0) + * ECLR1 is IRQs 0-7 (IRQ 0, 1, 2 must be 0) + * ECLR2 is IRQs 8-15 (IRQ 8, 13 must be 0) */ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) @@ -427,7 +427,7 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) old = inb(0x4d0) | (inb(0x4d1) << 8); /* - * If we use ACPI to set PCI irq's, then we should clear ELCR + * If we use ACPI to set PCI IRQs, then we should clear ELCR * since we will set it correctly as we enable the PCI irq * routing. */ @@ -555,7 +555,7 @@ EXPORT_SYMBOL(acpi_map_lsapic); int acpi_unmap_lsapic(int cpu) { - x86_cpu_to_apicid[cpu] = -1; + per_cpu(x86_cpu_to_apicid, cpu) = -1; cpu_clear(cpu, cpu_present_map); num_processors--; diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 2d39f55d29a..10b67170b13 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -29,7 +29,7 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, unsigned int cpu) { - struct cpuinfo_x86 *c = cpu_data + cpu; + struct cpuinfo_x86 *c = &cpu_data(cpu); flags->bm_check = 0; if (num_online_cpus() == 1) @@ -72,7 +72,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, struct acpi_processor_cx *cx, struct acpi_power_register *reg) { struct cstate_entry *percpu_entry; - struct cpuinfo_x86 *c = cpu_data + cpu; + struct cpuinfo_x86 *c = &cpu_data(cpu); cpumask_t saved_mask; int retval; diff --git a/arch/x86/kernel/acpi/earlyquirk_32.c b/arch/x86/kernel/acpi/earlyquirk_32.c deleted file mode 100644 index 23f78efc577..00000000000 --- a/arch/x86/kernel/acpi/earlyquirk_32.c +++ /dev/null @@ -1,84 +0,0 @@ -/* - * Do early PCI probing for bug detection when the main PCI subsystem is - * not up yet. - */ -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/acpi.h> - -#include <asm/pci-direct.h> -#include <asm/acpi.h> -#include <asm/apic.h> - -#ifdef CONFIG_ACPI - -static int __init nvidia_hpet_check(struct acpi_table_header *header) -{ - return 0; -} -#endif - -static int __init check_bridge(int vendor, int device) -{ -#ifdef CONFIG_ACPI - static int warned; - /* According to Nvidia all timer overrides are bogus unless HPET - is enabled. */ - if (!acpi_use_timer_override && vendor == PCI_VENDOR_ID_NVIDIA) { - if (!warned && acpi_table_parse(ACPI_SIG_HPET, - nvidia_hpet_check)) { - warned = 1; - acpi_skip_timer_override = 1; - printk(KERN_INFO "Nvidia board " - "detected. Ignoring ACPI " - "timer override.\n"); - printk(KERN_INFO "If you got timer trouble " - "try acpi_use_timer_override\n"); - - } - } -#endif - if (vendor == PCI_VENDOR_ID_ATI && timer_over_8254 == 1) { - timer_over_8254 = 0; - printk(KERN_INFO "ATI board detected. Disabling timer routing " - "over 8254.\n"); - } - return 0; -} - -void __init check_acpi_pci(void) -{ - int num, slot, func; - - /* Assume the machine supports type 1. If not it will - always read ffffffff and should not have any side effect. - Actually a few buggy systems can machine check. Allow the user - to disable it by command line option at least -AK */ - if (!early_pci_allowed()) - return; - - /* Poor man's PCI discovery */ - for (num = 0; num < 32; num++) { - for (slot = 0; slot < 32; slot++) { - for (func = 0; func < 8; func++) { - u32 class; - u32 vendor; - class = read_pci_config(num, slot, func, - PCI_CLASS_REVISION); - if (class == 0xffffffff) - break; - - if ((class >> 16) != PCI_CLASS_BRIDGE_PCI) - continue; - - vendor = read_pci_config(num, slot, func, - PCI_VENDOR_ID); - - if (check_bridge(vendor & 0xffff, vendor >> 16)) - return; - } - - } - } -} diff --git a/arch/x86/kernel/acpi/processor.c b/arch/x86/kernel/acpi/processor.c index b54fded4983..f63e5ff0aca 100644 --- a/arch/x86/kernel/acpi/processor.c +++ b/arch/x86/kernel/acpi/processor.c @@ -62,8 +62,7 @@ static void init_intel_pdc(struct acpi_processor *pr, struct cpuinfo_x86 *c) /* Initialize _PDC data based on the CPU vendor */ void arch_acpi_processor_init_pdc(struct acpi_processor *pr) { - unsigned int cpu = pr->id; - struct cpuinfo_x86 *c = cpu_data + cpu; + struct cpuinfo_x86 *c = &cpu_data(pr->id); pr->pdc = NULL; if (c->x86_vendor == X86_VENDOR_INTEL) diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index f22ba8534d2..a97313b1270 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -11,7 +11,7 @@ # # If physical address of wakeup_code is 0x12345, BIOS should call us with # cs = 0x1234, eip = 0x05 -# +# #define BEEP \ inb $97, %al; \ @@ -52,7 +52,6 @@ wakeup_code: BEEP 1: mov $(wakeup_stack - wakeup_code), %sp # Private stack is needed for ASUS board - movw $0x0e00 + 'S', %fs:(0x12) pushl $0 # Kill any dangerous flags popfl @@ -90,9 +89,6 @@ wakeup_code: # make sure %cr4 is set correctly (features, etc) movl real_save_cr4 - wakeup_code, %eax movl %eax, %cr4 - movw $0xb800, %ax - movw %ax,%fs - movw $0x0e00 + 'i', %fs:(0x12) # need a gdt -- use lgdtl to force 32-bit operands, in case # the GDT is located past 16 megabytes. @@ -102,8 +98,6 @@ wakeup_code: movl %eax, %cr0 jmp 1f 1: - movw $0x0e00 + 'n', %fs:(0x14) - movl real_magic - wakeup_code, %eax cmpl $0x12345678, %eax jne bogus_real_magic @@ -122,13 +116,11 @@ real_save_cr4: .long 0 real_magic: .long 0 video_mode: .long 0 realmode_flags: .long 0 -beep_flags: .long 0 real_efer_save_restore: .long 0 real_save_efer_edx: .long 0 real_save_efer_eax: .long 0 bogus_real_magic: - movw $0x0e00 + 'B', %fs:(0x12) jmp bogus_real_magic /* This code uses an extended set of video mode numbers. These include: @@ -194,7 +186,6 @@ wakeup_pmode_return: movw %ax, %es movw %ax, %fs movw %ax, %gs - movw $0x0e00 + 'u', 0xb8016 # reload the gdt, as we need the full 32 bit address lgdt saved_gdt @@ -218,7 +209,6 @@ wakeup_pmode_return: jmp *%eax bogus_magic: - movw $0x0e00 + 'B', 0xb8018 jmp bogus_magic diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 8b4357e1efe..5ed3bc5c61d 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -4,6 +4,7 @@ #include <asm/pgtable.h> #include <asm/page.h> #include <asm/msr.h> +#include <asm/asm-offsets.h> # Copyright 2003 Pavel Machek <pavel@suse.cz>, distribute under GPLv2 # @@ -41,7 +42,6 @@ wakeup_code: # Running in *copy* of this code, somewhere in low 1MB. - movb $0xa1, %al ; outb %al, $0x80 cli cld # setup data segment @@ -65,11 +65,6 @@ wakeup_code: cmpl $0x12345678, %eax jne bogus_real_magic - call verify_cpu # Verify the cpu supports long - # mode - testl %eax, %eax - jnz no_longmode - testl $1, realmode_flags - wakeup_code jz 1f lcall $0xc000,$3 @@ -84,12 +79,6 @@ wakeup_code: call mode_set 1: - movw $0xb800, %ax - movw %ax,%fs - movw $0x0e00 + 'L', %fs:(0x10) - - movb $0xa2, %al ; outb %al, $0x80 - mov %ds, %ax # Find 32bit wakeup_code addr movzx %ax, %esi # (Convert %ds:gdt to a liner ptr) shll $4, %esi @@ -117,14 +106,10 @@ wakeup_32_vector: .code32 wakeup_32: # Running in this code, but at low address; paging is not yet turned on. - movb $0xa5, %al ; outb %al, $0x80 movl $__KERNEL_DS, %eax movl %eax, %ds - movw $0x0e00 + 'i', %ds:(0xb8012) - movb $0xa8, %al ; outb %al, $0x80; - /* * Prepare for entering 64bits mode */ @@ -200,16 +185,11 @@ wakeup_long64: */ lgdt cpu_gdt_descr - movw $0x0e00 + 'n', %ds:(0xb8014) - movb $0xa9, %al ; outb %al, $0x80 - movq saved_magic, %rax movq $0x123456789abcdef0, %rdx cmpq %rdx, %rax jne bogus_64_magic - movw $0x0e00 + 'u', %ds:(0xb8016) - nop nop movw $__KERNEL_DS, %ax @@ -220,13 +200,11 @@ wakeup_long64: movw %ax, %gs movq saved_rsp, %rsp - movw $0x0e00 + 'x', %ds:(0xb8018) movq saved_rbx, %rbx movq saved_rdi, %rdi movq saved_rsi, %rsi movq saved_rbp, %rbp - movw $0x0e00 + '!', %ds:(0xb801a) movq saved_rip, %rax jmp *%rax @@ -256,21 +234,12 @@ realmode_flags: .quad 0 .code16 bogus_real_magic: - movb $0xba,%al ; outb %al,$0x80 jmp bogus_real_magic .code64 bogus_64_magic: - movb $0xb3,%al ; outb %al,$0x80 jmp bogus_64_magic -.code16 -no_longmode: - movb $0xbc,%al ; outb %al,$0x80 - jmp no_longmode - -#include "../verify_cpu_64.S" - /* This code uses an extended set of video mode numbers. These include: * Aliases for standard modes * NORMAL_VGA (-1) @@ -374,31 +343,32 @@ do_suspend_lowlevel: xorl %eax, %eax call save_processor_state - movq %rsp, saved_context_esp(%rip) - movq %rax, saved_context_eax(%rip) - movq %rbx, saved_context_ebx(%rip) - movq %rcx, saved_context_ecx(%rip) - movq %rdx, saved_context_edx(%rip) - movq %rbp, saved_context_ebp(%rip) - movq %rsi, saved_context_esi(%rip) - movq %rdi, saved_context_edi(%rip) - movq %r8, saved_context_r08(%rip) - movq %r9, saved_context_r09(%rip) - movq %r10, saved_context_r10(%rip) - movq %r11, saved_context_r11(%rip) - movq %r12, saved_context_r12(%rip) - movq %r13, saved_context_r13(%rip) - movq %r14, saved_context_r14(%rip) - movq %r15, saved_context_r15(%rip) - pushfq ; popq saved_context_eflags(%rip) + movq $saved_context, %rax + movq %rsp, pt_regs_rsp(%rax) + movq %rbp, pt_regs_rbp(%rax) + movq %rsi, pt_regs_rsi(%rax) + movq %rdi, pt_regs_rdi(%rax) + movq %rbx, pt_regs_rbx(%rax) + movq %rcx, pt_regs_rcx(%rax) + movq %rdx, pt_regs_rdx(%rax) + movq %r8, pt_regs_r8(%rax) + movq %r9, pt_regs_r9(%rax) + movq %r10, pt_regs_r10(%rax) + movq %r11, pt_regs_r11(%rax) + movq %r12, pt_regs_r12(%rax) + movq %r13, pt_regs_r13(%rax) + movq %r14, pt_regs_r14(%rax) + movq %r15, pt_regs_r15(%rax) + pushfq + popq pt_regs_eflags(%rax) movq $.L97, saved_rip(%rip) - movq %rsp,saved_rsp - movq %rbp,saved_rbp - movq %rbx,saved_rbx - movq %rdi,saved_rdi - movq %rsi,saved_rsi + movq %rsp, saved_rsp + movq %rbp, saved_rbp + movq %rbx, saved_rbx + movq %rdi, saved_rdi + movq %rsi, saved_rsi addq $8, %rsp movl $3, %edi @@ -409,32 +379,35 @@ do_suspend_lowlevel: .L99: .align 4 movl $24, %eax - movw %ax, %ds - movq saved_context+58(%rip), %rax - movq %rax, %cr4 - movq saved_context+50(%rip), %rax - movq %rax, %cr3 - movq saved_context+42(%rip), %rax - movq %rax, %cr2 - movq saved_context+34(%rip), %rax - movq %rax, %cr0 - pushq saved_context_eflags(%rip) ; popfq - movq saved_context_esp(%rip), %rsp - movq saved_context_ebp(%rip), %rbp - movq saved_context_eax(%rip), %rax - movq saved_context_ebx(%rip), %rbx - movq saved_context_ecx(%rip), %rcx - movq saved_context_edx(%rip), %rdx - movq saved_context_esi(%rip), %rsi - movq saved_context_edi(%rip), %rdi - movq saved_context_r08(%rip), %r8 - movq saved_context_r09(%rip), %r9 - movq saved_context_r10(%rip), %r10 - movq saved_context_r11(%rip), %r11 - movq saved_context_r12(%rip), %r12 - movq saved_context_r13(%rip), %r13 - movq saved_context_r14(%rip), %r14 - movq saved_context_r15(%rip), %r15 + movw %ax, %ds + + /* We don't restore %rax, it must be 0 anyway */ + movq $saved_context, %rax + movq saved_context_cr4(%rax), %rbx + movq %rbx, %cr4 + movq saved_context_cr3(%rax), %rbx + movq %rbx, %cr3 + movq saved_context_cr2(%rax), %rbx + movq %rbx, %cr2 + movq saved_context_cr0(%rax), %rbx + movq %rbx, %cr0 + pushq pt_regs_eflags(%rax) + popfq + movq pt_regs_rsp(%rax), %rsp + movq pt_regs_rbp(%rax), %rbp + movq pt_regs_rsi(%rax), %rsi + movq pt_regs_rdi(%rax), %rdi + movq pt_regs_rbx(%rax), %rbx + movq pt_regs_rcx(%rax), %rcx + movq pt_regs_rdx(%rax), %rdx + movq pt_regs_r8(%rax), %r8 + movq pt_regs_r9(%rax), %r9 + movq pt_regs_r10(%rax), %r10 + movq pt_regs_r11(%rax), %r11 + movq pt_regs_r12(%rax), %r12 + movq pt_regs_r13(%rax), %r13 + movq pt_regs_r14(%rax), %r14 + movq pt_regs_r15(%rax), %r15 xorl %eax, %eax addq $8, %rsp diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 11b03d3c6fd..d6405e0842b 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -63,11 +63,11 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt); /* Use inline assembly to define this because the nops are defined as inline assembly strings in the include files and we cannot get them easily into strings. */ -asm("\t.data\nintelnops: " +asm("\t.section .rodata, \"a\"\nintelnops: " GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6 GENERIC_NOP7 GENERIC_NOP8); -extern unsigned char intelnops[]; -static unsigned char *intel_nops[ASM_NOP_MAX+1] = { +extern const unsigned char intelnops[]; +static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = { NULL, intelnops, intelnops + 1, @@ -81,11 +81,11 @@ static unsigned char *intel_nops[ASM_NOP_MAX+1] = { #endif #ifdef K8_NOP1 -asm("\t.data\nk8nops: " +asm("\t.section .rodata, \"a\"\nk8nops: " K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6 K8_NOP7 K8_NOP8); -extern unsigned char k8nops[]; -static unsigned char *k8_nops[ASM_NOP_MAX+1] = { +extern const unsigned char k8nops[]; +static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = { NULL, k8nops, k8nops + 1, @@ -99,11 +99,11 @@ static unsigned char *k8_nops[ASM_NOP_MAX+1] = { #endif #ifdef K7_NOP1 -asm("\t.data\nk7nops: " +asm("\t.section .rodata, \"a\"\nk7nops: " K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6 K7_NOP7 K7_NOP8); -extern unsigned char k7nops[]; -static unsigned char *k7_nops[ASM_NOP_MAX+1] = { +extern const unsigned char k7nops[]; +static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = { NULL, k7nops, k7nops + 1, @@ -116,28 +116,49 @@ static unsigned char *k7_nops[ASM_NOP_MAX+1] = { }; #endif +#ifdef P6_NOP1 +asm("\t.section .rodata, \"a\"\np6nops: " + P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6 + P6_NOP7 P6_NOP8); +extern const unsigned char p6nops[]; +static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = { + NULL, + p6nops, + p6nops + 1, + p6nops + 1 + 2, + p6nops + 1 + 2 + 3, + p6nops + 1 + 2 + 3 + 4, + p6nops + 1 + 2 + 3 + 4 + 5, + p6nops + 1 + 2 + 3 + 4 + 5 + 6, + p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, +}; +#endif + #ifdef CONFIG_X86_64 extern char __vsyscall_0; -static inline unsigned char** find_nop_table(void) +static inline const unsigned char*const * find_nop_table(void) { - return k8_nops; + return boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 < 6 ? k8_nops : p6_nops; } #else /* CONFIG_X86_64 */ -static struct nop { +static const struct nop { int cpuid; - unsigned char **noptable; + const unsigned char *const *noptable; } noptypes[] = { { X86_FEATURE_K8, k8_nops }, { X86_FEATURE_K7, k7_nops }, + { X86_FEATURE_P4, p6_nops }, + { X86_FEATURE_P3, p6_nops }, { -1, NULL } }; -static unsigned char** find_nop_table(void) +static const unsigned char*const * find_nop_table(void) { - unsigned char **noptable = intel_nops; + const unsigned char *const *noptable = intel_nops; int i; for (i = 0; noptypes[i].cpuid >= 0; i++) { @@ -154,7 +175,7 @@ static unsigned char** find_nop_table(void) /* Use this to add nops to a buffer, then text_poke the whole buffer. */ static void add_nops(void *insns, unsigned int len) { - unsigned char **noptable = find_nop_table(); + const unsigned char *const *noptable = find_nop_table(); while (len > 0) { unsigned int noplen = len; @@ -336,14 +357,14 @@ void alternatives_smp_switch(int smp) if (smp) { printk(KERN_INFO "SMP alternatives: switching to SMP code\n"); clear_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability); - clear_bit(X86_FEATURE_UP, cpu_data[0].x86_capability); + clear_bit(X86_FEATURE_UP, cpu_data(0).x86_capability); list_for_each_entry(mod, &smp_alt_modules, next) alternatives_smp_lock(mod->locks, mod->locks_end, mod->text, mod->text_end); } else { printk(KERN_INFO "SMP alternatives: switching to UP code\n"); set_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability); - set_bit(X86_FEATURE_UP, cpu_data[0].x86_capability); + set_bit(X86_FEATURE_UP, cpu_data(0).x86_capability); list_for_each_entry(mod, &smp_alt_modules, next) alternatives_smp_unlock(mod->locks, mod->locks_end, mod->text, mod->text_end); @@ -369,8 +390,8 @@ void apply_paravirt(struct paravirt_patch_site *start, BUG_ON(p->len > MAX_PATCH_LEN); /* prep the buffer with the original instructions */ memcpy(insnbuf, p->instr, p->len); - used = paravirt_ops.patch(p->instrtype, p->clobbers, insnbuf, - (unsigned long)p->instr, p->len); + used = pv_init_ops.patch(p->instrtype, p->clobbers, insnbuf, + (unsigned long)p->instr, p->len); BUG_ON(used > p->len); @@ -411,13 +432,10 @@ void __init alternative_instructions(void) if (1 == num_possible_cpus()) { printk(KERN_INFO "SMP alternatives: switching to UP code\n"); set_bit(X86_FEATURE_UP, boot_cpu_data.x86_capability); - set_bit(X86_FEATURE_UP, cpu_data[0].x86_capability); + set_bit(X86_FEATURE_UP, cpu_data(0).x86_capability); alternatives_smp_unlock(__smp_locks, __smp_locks_end, _text, _etext); } - free_init_pages("SMP alternatives", - (unsigned long)__smp_locks, - (unsigned long)__smp_locks_end); } else { alternatives_smp_module_add(NULL, "core kernel", __smp_locks, __smp_locks_end, @@ -428,6 +446,11 @@ void __init alternative_instructions(void) apply_paravirt(__parainstructions, __parainstructions_end); local_irq_restore(flags); + if (smp_alt_once) + free_init_pages("SMP alternatives", + (unsigned long)__smp_locks, + (unsigned long)__smp_locks_end); + restart_nmi(); #ifdef CONFIG_X86_MCE restart_mce(); diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 8f681cae7bf..5b6992799c9 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -20,14 +20,14 @@ #include <linux/ioport.h> #include <asm/e820.h> #include <asm/io.h> -#include <asm/iommu.h> +#include <asm/gart.h> #include <asm/pci-direct.h> #include <asm/dma.h> #include <asm/k8.h> -int iommu_aperture; -int iommu_aperture_disabled __initdata = 0; -int iommu_aperture_allowed __initdata = 0; +int gart_iommu_aperture; +int gart_iommu_aperture_disabled __initdata = 0; +int gart_iommu_aperture_allowed __initdata = 0; int fallback_aper_order __initdata = 1; /* 64MB */ int fallback_aper_force __initdata = 0; @@ -204,14 +204,15 @@ static __u32 __init search_agp_bridge(u32 *order, int *valid_agp) return 0; } -void __init iommu_hole_init(void) +void __init gart_iommu_hole_init(void) { int fix, num; u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0; u64 aper_base, last_aper_base = 0; int valid_agp = 0; - if (iommu_aperture_disabled || !fix_aperture || !early_pci_allowed()) + if (gart_iommu_aperture_disabled || !fix_aperture || + !early_pci_allowed()) return; printk(KERN_INFO "Checking aperture...\n"); @@ -222,7 +223,7 @@ void __init iommu_hole_init(void) continue; iommu_detected = 1; - iommu_aperture = 1; + gart_iommu_aperture = 1; aper_order = (read_pci_config(0, num, 3, 0x90) >> 1) & 7; aper_size = (32 * 1024 * 1024) << aper_order; diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c index 3d67ae18d76..08b07c17696 100644 --- a/arch/x86/kernel/apic_32.c +++ b/arch/x86/kernel/apic_32.c @@ -947,7 +947,7 @@ void __devinit setup_local_APIC(void) * Set up LVT0, LVT1: * * set up through-local-APIC on the BP's LINT0. This is not - * strictly necessery in pure symmetric-IO mode, but sometimes + * strictly necessary in pure symmetric-IO mode, but sometimes * we delegate interrupts to the 8259A. */ /* @@ -998,7 +998,7 @@ void __devinit setup_local_APIC(void) } else { if (esr_disable) /* - * Something untraceble is creating bad interrupts on + * Something untraceable is creating bad interrupts on * secondary quads ... for the moment, just leave the * ESR disabled - we can't do anything useful with the * errors anyway - mbligh @@ -1277,6 +1277,7 @@ void smp_spurious_interrupt(struct pt_regs *regs) /* see sw-dev-man vol 3, chapter 7.4.13.5 */ printk(KERN_INFO "spurious APIC interrupt on CPU#%d, " "should never happen.\n", smp_processor_id()); + __get_cpu_var(irq_stat).irq_spurious_count++; irq_exit(); } diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c index 09b82093bc7..f28ccb588fb 100644 --- a/arch/x86/kernel/apic_64.c +++ b/arch/x86/kernel/apic_64.c @@ -287,6 +287,20 @@ void disable_local_APIC(void) apic_write(APIC_SPIV, value); } +void lapic_shutdown(void) +{ + unsigned long flags; + + if (!cpu_has_apic) + return; + + local_irq_save(flags); + + disable_local_APIC(); + + local_irq_restore(flags); +} + /* * This is to verify that we're looking at a real local APIC. * Check these against your board if the CPUs aren't getting @@ -974,15 +988,12 @@ void __init setup_boot_APIC_clock (void) */ void __cpuinit check_boot_apic_timer_broadcast(void) { - struct clock_event_device *levt = &per_cpu(lapic_events, boot_cpu_id); - if (!disable_apic_timer || (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY)) return; printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n"); lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY; - levt->features |= CLOCK_EVT_FEAT_DUMMY; local_irq_enable(); clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, &boot_cpu_id); @@ -1143,6 +1154,7 @@ asmlinkage void smp_spurious_interrupt(void) if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f))) ack_APIC_irq(); + add_pda(irq_spurious_count, 1); irq_exit(); } diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 32f2365c26e..17089a04102 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -57,7 +57,7 @@ * screen-blanking and gpm (Stephen Rothwell); Linux 1.99.4 * 1.2a:Simple change to stop mysterious bug reports with SMP also added * levels to the printk calls. APM is not defined for SMP machines. - * The new replacment for it is, but Linux doesn't yet support this. + * The new replacement for it is, but Linux doesn't yet support this. * Alan Cox Linux 2.1.55 * 1.3: Set up a valid data descriptor 0x40 for buggy BIOS's * 1.4: Upgraded to support APM 1.2. Integrated ThinkPad suspend patch by diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 8029742c0fc..0e45981b2dd 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -15,6 +15,7 @@ #include <asm/fixmap.h> #include <asm/processor.h> #include <asm/thread_info.h> +#include <asm/bootparam.h> #include <asm/elf.h> #include <xen/interface/xen.h> @@ -116,12 +117,14 @@ void foo(void) #ifdef CONFIG_PARAVIRT BLANK(); - OFFSET(PARAVIRT_enabled, paravirt_ops, paravirt_enabled); - OFFSET(PARAVIRT_irq_disable, paravirt_ops, irq_disable); - OFFSET(PARAVIRT_irq_enable, paravirt_ops, irq_enable); - OFFSET(PARAVIRT_irq_enable_sysexit, paravirt_ops, irq_enable_sysexit); - OFFSET(PARAVIRT_iret, paravirt_ops, iret); - OFFSET(PARAVIRT_read_cr0, paravirt_ops, read_cr0); + OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled); + OFFSET(PARAVIRT_PATCH_pv_cpu_ops, paravirt_patch_template, pv_cpu_ops); + OFFSET(PARAVIRT_PATCH_pv_irq_ops, paravirt_patch_template, pv_irq_ops); + OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); + OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); + OFFSET(PV_CPU_iret, pv_cpu_ops, iret); + OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); + OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); #endif #ifdef CONFIG_XEN @@ -133,6 +136,7 @@ void foo(void) #ifdef CONFIG_LGUEST_GUEST BLANK(); OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); + OFFSET(LGUEST_DATA_pgdir, lguest_data, pgdir); OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc); OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc); OFFSET(LGUEST_PAGES_host_cr3, lguest_pages, state.host_cr3); @@ -144,4 +148,10 @@ void foo(void) OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode); OFFSET(LGUEST_PAGES_regs, lguest_pages, regs); #endif + + BLANK(); + OFFSET(BP_scratch, boot_params, scratch); + OFFSET(BP_loadflags, boot_params, hdr.loadflags); + OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); + OFFSET(BP_version, boot_params, hdr.version); } diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 778953bc636..d1b6ed98774 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -15,12 +15,16 @@ #include <asm/segment.h> #include <asm/thread_info.h> #include <asm/ia32.h> +#include <asm/bootparam.h> #define DEFINE(sym, val) \ asm volatile("\n->" #sym " %0 " #val : : "i" (val)) #define BLANK() asm volatile("\n->" : : ) +#define OFFSET(sym, str, mem) \ + DEFINE(sym, offsetof(struct str, mem)) + #define __NO_STUBS 1 #undef __SYSCALL #undef _ASM_X86_64_UNISTD_H_ @@ -76,10 +80,44 @@ int main(void) DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address)); DEFINE(pbe_next, offsetof(struct pbe, next)); BLANK(); +#define ENTRY(entry) DEFINE(pt_regs_ ## entry, offsetof(struct pt_regs, entry)) + ENTRY(rbx); + ENTRY(rbx); + ENTRY(rcx); + ENTRY(rdx); + ENTRY(rsp); + ENTRY(rbp); + ENTRY(rsi); + ENTRY(rdi); + ENTRY(r8); + ENTRY(r9); + ENTRY(r10); + ENTRY(r11); + ENTRY(r12); + ENTRY(r13); + ENTRY(r14); + ENTRY(r15); + ENTRY(eflags); + BLANK(); +#undef ENTRY +#define ENTRY(entry) DEFINE(saved_context_ ## entry, offsetof(struct saved_context, entry)) + ENTRY(cr0); + ENTRY(cr2); + ENTRY(cr3); + ENTRY(cr4); + ENTRY(cr8); + BLANK(); +#undef ENTRY DEFINE(TSS_ist, offsetof(struct tss_struct, ist)); BLANK(); DEFINE(crypto_tfm_ctx_offset, offsetof(struct crypto_tfm, __crt_ctx)); BLANK(); DEFINE(__NR_syscall_max, sizeof(syscalls) - 1); + + BLANK(); + OFFSET(BP_scratch, boot_params, scratch); + OFFSET(BP_loadflags, boot_params, hdr.loadflags); + OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch); + OFFSET(BP_version, boot_params, hdr.version); return 0; } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 778396c78d6..cfdb2f3bd76 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -2,19 +2,19 @@ # Makefile for x86-compatible CPU details and quirks # -obj-y := common.o proc.o bugs.o +obj-y := intel_cacheinfo.o addon_cpuid_features.o -obj-y += amd.o -obj-y += cyrix.o -obj-y += centaur.o -obj-y += transmeta.o -obj-y += intel.o intel_cacheinfo.o addon_cpuid_features.o -obj-y += nexgen.o -obj-y += umc.o +obj-$(CONFIG_X86_32) += common.o proc.o bugs.o +obj-$(CONFIG_X86_32) += amd.o +obj-$(CONFIG_X86_32) += cyrix.o +obj-$(CONFIG_X86_32) += centaur.o +obj-$(CONFIG_X86_32) += transmeta.o +obj-$(CONFIG_X86_32) += intel.o +obj-$(CONFIG_X86_32) += nexgen.o +obj-$(CONFIG_X86_32) += umc.o -obj-$(CONFIG_X86_MCE) += mcheck/ - -obj-$(CONFIG_MTRR) += mtrr/ -obj-$(CONFIG_CPU_FREQ) += cpufreq/ +obj-$(CONFIG_X86_MCE) += mcheck/ +obj-$(CONFIG_MTRR) += mtrr/ +obj-$(CONFIG_CPU_FREQ) += cpufreq/ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index dcf6bbb1c7c..1ff88c7f45c 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -4,6 +4,7 @@ #include <asm/io.h> #include <asm/processor.h> #include <asm/apic.h> +#include <asm/mach_apic.h> #include "cpu.h" @@ -45,13 +46,17 @@ static __cpuinit int amd_apic_timer_broken(void) case CPUID_XFAM_10H: case CPUID_XFAM_11H: rdmsr(MSR_K8_ENABLE_C1E, lo, hi); - if (lo & ENABLE_C1E_MASK) + if (lo & ENABLE_C1E_MASK) { + if (smp_processor_id() != boot_cpu_physical_apicid) + printk(KERN_INFO "AMD C1E detected late. " + " Force timer broadcast.\n"); return 1; - break; - default: - /* err on the side of caution */ + } + break; + default: + /* err on the side of caution */ return 1; - } + } return 0; } #endif @@ -261,7 +266,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_HT /* * On a AMD multi core setup the lower bits of the APIC id - * distingush the cores. + * distinguish the cores. */ if (c->x86_max_cores > 1) { int cpu = smp_processor_id(); diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 473eac883c7..9681fa15ddf 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -53,7 +53,7 @@ static u32 __cpuinit ramtop(void) /* 16388 */ continue; /* * Don't MCR over reserved space. Ignore the ISA hole - * we frob around that catastrophy already + * we frob around that catastrophe already */ if (e820.map[i].type == E820_RESERVED) @@ -287,7 +287,7 @@ static void __cpuinit init_c3(struct cpuinfo_x86 *c) c->x86_capability[5] = cpuid_edx(0xC0000001); } - /* Cyrix III family needs CX8 & PGE explicity enabled. */ + /* Cyrix III family needs CX8 & PGE explicitly enabled. */ if (c->x86_model >=6 && c->x86_model <= 9) { rdmsr (MSR_VIA_FCR, lo, hi); lo |= (1<<1 | 1<<7); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d506201d397..e2fcf2051bd 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -207,7 +207,7 @@ static void __cpuinit get_cpu_vendor(struct cpuinfo_x86 *c, int early) static int __init x86_fxsr_setup(char * s) { - /* Tell all the other CPU's to not use it... */ + /* Tell all the other CPUs to not use it... */ disable_x86_fxsr = 1; /* diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig index d8c6f132dc7..151eda0a23f 100644 --- a/arch/x86/kernel/cpu/cpufreq/Kconfig +++ b/arch/x86/kernel/cpu/cpufreq/Kconfig @@ -19,6 +19,9 @@ config X86_ACPI_CPUFREQ Processor Performance States. This driver also supports Intel Enhanced Speedstep. + To compile this driver as a module, choose M here: the + module will be called acpi-cpufreq. + For details, take a look at <file:Documentation/cpu-freq/>. If in doubt, say N. @@ -26,7 +29,7 @@ config X86_ACPI_CPUFREQ config ELAN_CPUFREQ tristate "AMD Elan SC400 and SC410" select CPU_FREQ_TABLE - depends on X86_ELAN + depends on X86_32 && X86_ELAN ---help--- This adds the CPUFreq driver for AMD Elan SC400 and SC410 processors. @@ -42,7 +45,7 @@ config ELAN_CPUFREQ config SC520_CPUFREQ tristate "AMD Elan SC520" select CPU_FREQ_TABLE - depends on X86_ELAN + depends on X86_32 && X86_ELAN ---help--- This adds the CPUFreq driver for AMD Elan SC520 processor. @@ -54,6 +57,7 @@ config SC520_CPUFREQ config X86_POWERNOW_K6 tristate "AMD Mobile K6-2/K6-3 PowerNow!" select CPU_FREQ_TABLE + depends on X86_32 help This adds the CPUFreq driver for mobile AMD K6-2+ and mobile AMD K6-3+ processors. @@ -65,6 +69,7 @@ config X86_POWERNOW_K6 config X86_POWERNOW_K7 tristate "AMD Mobile Athlon/Duron PowerNow!" select CPU_FREQ_TABLE + depends on X86_32 help This adds the CPUFreq driver for mobile AMD K7 mobile processors. @@ -76,23 +81,27 @@ config X86_POWERNOW_K7_ACPI bool depends on X86_POWERNOW_K7 && ACPI_PROCESSOR depends on !(X86_POWERNOW_K7 = y && ACPI_PROCESSOR = m) + depends on X86_32 default y config X86_POWERNOW_K8 tristate "AMD Opteron/Athlon64 PowerNow!" select CPU_FREQ_TABLE - depends on EXPERIMENTAL help This adds the CPUFreq driver for mobile AMD Opteron/Athlon64 processors. + To compile this driver as a module, choose M here: the + module will be called powernow-k8. + For details, take a look at <file:Documentation/cpu-freq/>. If in doubt, say N. config X86_POWERNOW_K8_ACPI - bool "ACPI Support" - select ACPI_PROCESSOR - depends on ACPI && X86_POWERNOW_K8 + bool + prompt "ACPI Support" if X86_32 + depends on ACPI && X86_POWERNOW_K8 && ACPI_PROCESSOR + depends on !(X86_POWERNOW_K8 = y && ACPI_PROCESSOR = m) default y help This provides access to the K8s Processor Performance States via ACPI. @@ -104,7 +113,7 @@ config X86_POWERNOW_K8_ACPI config X86_GX_SUSPMOD tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation" - depends on PCI + depends on X86_32 && PCI help This add the CPUFreq driver for NatSemi Geode processors which support suspend modulation. @@ -114,15 +123,20 @@ config X86_GX_SUSPMOD If in doubt, say N. config X86_SPEEDSTEP_CENTRINO - tristate "Intel Enhanced SpeedStep" + tristate "Intel Enhanced SpeedStep (deprecated)" select CPU_FREQ_TABLE - select X86_SPEEDSTEP_CENTRINO_TABLE + select X86_SPEEDSTEP_CENTRINO_TABLE if X86_32 + depends on X86_32 || (X86_64 && ACPI_PROCESSOR) help + This is deprecated and this functionality is now merged into + acpi_cpufreq (X86_ACPI_CPUFREQ). Use that driver instead of + speedstep_centrino. This adds the CPUFreq driver for Enhanced SpeedStep enabled - mobile CPUs. This means Intel Pentium M (Centrino) CPUs. However, - you also need to say Y to "Use ACPI tables to decode..." below - [which might imply enabling ACPI] if you want to use this driver - on non-Banias CPUs. + mobile CPUs. This means Intel Pentium M (Centrino) CPUs + or 64bit enabled Intel Xeons. + + To compile this driver as a module, choose M here: the + module will be called speedstep-centrino. For details, take a look at <file:Documentation/cpu-freq/>. @@ -130,7 +144,7 @@ config X86_SPEEDSTEP_CENTRINO config X86_SPEEDSTEP_CENTRINO_TABLE bool "Built-in tables for Banias CPUs" - depends on X86_SPEEDSTEP_CENTRINO + depends on X86_32 && X86_SPEEDSTEP_CENTRINO default y help Use built-in tables for Banias CPUs if ACPI encoding @@ -141,6 +155,7 @@ config X86_SPEEDSTEP_CENTRINO_TABLE config X86_SPEEDSTEP_ICH tristate "Intel Speedstep on ICH-M chipsets (ioport interface)" select CPU_FREQ_TABLE + depends on X86_32 help This adds the CPUFreq driver for certain mobile Intel Pentium III (Coppermine), all mobile Intel Pentium III-M (Tualatin) and all @@ -154,7 +169,7 @@ config X86_SPEEDSTEP_ICH config X86_SPEEDSTEP_SMI tristate "Intel SpeedStep on 440BX/ZX/MX chipsets (SMI interface)" select CPU_FREQ_TABLE - depends on EXPERIMENTAL + depends on X86_32 && EXPERIMENTAL help This adds the CPUFreq driver for certain mobile Intel Pentium III (Coppermine), all mobile Intel Pentium III-M (Tualatin) @@ -169,15 +184,24 @@ config X86_P4_CLOCKMOD select CPU_FREQ_TABLE help This adds the CPUFreq driver for Intel Pentium 4 / XEON - processors. + processors. When enabled it will lower CPU temperature by skipping + clocks. + + This driver should be only used in exceptional + circumstances when very low power is needed because it causes severe + slowdowns and noticeable latencies. Normally Speedstep should be used + instead. + + To compile this driver as a module, choose M here: the + module will be called p4-clockmod. For details, take a look at <file:Documentation/cpu-freq/>. - If in doubt, say N. + Unless you are absolutely sure say N. config X86_CPUFREQ_NFORCE2 tristate "nVidia nForce2 FSB changing" - depends on EXPERIMENTAL + depends on X86_32 && EXPERIMENTAL help This adds the CPUFreq driver for FSB changing on nVidia nForce2 platforms. @@ -188,6 +212,7 @@ config X86_CPUFREQ_NFORCE2 config X86_LONGRUN tristate "Transmeta LongRun" + depends on X86_32 help This adds the CPUFreq driver for Transmeta Crusoe and Efficeon processors which support LongRun. @@ -199,7 +224,7 @@ config X86_LONGRUN config X86_LONGHAUL tristate "VIA Cyrix III Longhaul" select CPU_FREQ_TABLE - depends on ACPI_PROCESSOR + depends on X86_32 && ACPI_PROCESSOR help This adds the CPUFreq driver for VIA Samuel/CyrixIII, VIA Cyrix Samuel/C3, VIA Cyrix Ezra and VIA Cyrix Ezra-T @@ -212,7 +237,7 @@ config X86_LONGHAUL config X86_E_POWERSAVER tristate "VIA C7 Enhanced PowerSaver (EXPERIMENTAL)" select CPU_FREQ_TABLE - depends on EXPERIMENTAL + depends on X86_32 && EXPERIMENTAL help This adds the CPUFreq driver for VIA C7 processors. @@ -233,11 +258,11 @@ config X86_ACPI_CPUFREQ_PROC_INTF config X86_SPEEDSTEP_LIB tristate - default X86_SPEEDSTEP_ICH || X86_SPEEDSTEP_SMI || X86_P4_CLOCKMOD + default (X86_SPEEDSTEP_ICH || X86_SPEEDSTEP_SMI || X86_P4_CLOCKMOD) config X86_SPEEDSTEP_RELAXED_CAP_CHECK bool "Relaxed speedstep capability checks" - depends on (X86_SPEEDSTEP_SMI || X86_SPEEDSTEP_ICH) + depends on X86_32 && (X86_SPEEDSTEP_SMI || X86_SPEEDSTEP_ICH) help Don't perform all checks for a speedstep capable system which would normally be done. Some ancient or strange systems, though speedstep diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index ffd01e5dcb5..fea0af0476b 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -77,7 +77,7 @@ static unsigned int acpi_pstate_strict; static int check_est_cpu(unsigned int cpuid) { - struct cpuinfo_x86 *cpu = &cpu_data[cpuid]; + struct cpuinfo_x86 *cpu = &cpu_data(cpuid); if (cpu->x86_vendor != X86_VENDOR_INTEL || !cpu_has(cpu, X86_FEATURE_EST)) @@ -560,7 +560,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) unsigned int cpu = policy->cpu; struct acpi_cpufreq_data *data; unsigned int result = 0; - struct cpuinfo_x86 *c = &cpu_data[policy->cpu]; + struct cpuinfo_x86 *c = &cpu_data(policy->cpu); struct acpi_processor_performance *perf; dprintk("acpi_cpufreq_cpu_init\n"); @@ -595,7 +595,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) dmi_check_system(sw_any_bug_dmi_table); if (bios_with_sw_any_bug && cpus_weight(policy->cpus) == 1) { policy->shared_type = CPUFREQ_SHARED_TYPE_ALL; - policy->cpus = cpu_core_map[cpu]; + policy->cpus = per_cpu(cpu_core_map, cpu); } #endif diff --git a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c index 32f0bda3fc9..f03e9153618 100644 --- a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c +++ b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c @@ -260,7 +260,7 @@ static int nforce2_target(struct cpufreq_policy *policy, freqs.old = nforce2_get(policy->cpu); freqs.new = target_fsb * fid * 100; - freqs.cpu = 0; /* Only one CPU on nForce2 plattforms */ + freqs.cpu = 0; /* Only one CPU on nForce2 platforms */ if (freqs.old == freqs.new) return 0; diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c index c11baaf9f2b..326a4c81f68 100644 --- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c +++ b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c @@ -305,7 +305,7 @@ static struct cpufreq_driver eps_driver = { static int __init eps_init(void) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); /* This driver will work only on Centaur C7 processors with * Enhanced SpeedStep/PowerSaver registers */ diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/arch/x86/kernel/cpu/cpufreq/elanfreq.c index 1e7ae7dafcf..94619c22f56 100644 --- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c +++ b/arch/x86/kernel/cpu/cpufreq/elanfreq.c @@ -199,7 +199,7 @@ static int elanfreq_target (struct cpufreq_policy *policy, static int elanfreq_cpu_init(struct cpufreq_policy *policy) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); unsigned int i; int result; @@ -280,7 +280,7 @@ static struct cpufreq_driver elanfreq_driver = { static int __init elanfreq_init(void) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); /* Test if we have the right hardware */ if ((c->x86_vendor != X86_VENDOR_AMD) || diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c index ed2bda127c4..2ed7db2fd25 100644 --- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c +++ b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c @@ -12,12 +12,12 @@ * of any nature resulting due to the use of this software. This * software is provided AS-IS with no warranties. * - * Theoritical note: + * Theoretical note: * * (see Geode(tm) CS5530 manual (rev.4.1) page.56) * * CPU frequency control on NatSemi Geode GX1/GXLV processor and CS55x0 - * are based on Suspend Moduration. + * are based on Suspend Modulation. * * Suspend Modulation works by asserting and de-asserting the SUSP# pin * to CPU(GX1/GXLV) for configurable durations. When asserting SUSP# @@ -101,11 +101,11 @@ /* SUSCFG bits */ #define SUSMOD (1<<0) /* enable/disable suspend modulation */ -/* the belows support only with cs5530 (after rev.1.2)/cs5530A */ +/* the below is supported only with cs5530 (after rev.1.2)/cs5530A */ #define SMISPDUP (1<<1) /* select how SMI re-enable suspend modulation: */ /* IRQTC timer or read SMI speedup disable reg.(F1BAR[08-09h]) */ #define SUSCFG (1<<2) /* enable powering down a GXLV processor. "Special 3Volt Suspend" mode */ -/* the belows support only with cs5530A */ +/* the below is supported only with cs5530A */ #define PWRSVE_ISA (1<<3) /* stop ISA clock */ #define PWRSVE (1<<4) /* active idle */ diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c index 5045f5d583c..749d00cb2eb 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.c +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c @@ -780,7 +780,7 @@ static int longhaul_setup_southbridge(void) static int __init longhaul_cpu_init(struct cpufreq_policy *policy) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); char *cpuname=NULL; int ret; u32 lo, hi; @@ -959,7 +959,7 @@ static struct cpufreq_driver longhaul_driver = { static int __init longhaul_init(void) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); if (c->x86_vendor != X86_VENDOR_CENTAUR || c->x86 != 6) return -ENODEV; diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c index b2689514295..af4a867a097 100644 --- a/arch/x86/kernel/cpu/cpufreq/longrun.c +++ b/arch/x86/kernel/cpu/cpufreq/longrun.c @@ -172,7 +172,7 @@ static unsigned int __init longrun_determine_freqs(unsigned int *low_freq, u32 save_lo, save_hi; u32 eax, ebx, ecx, edx; u32 try_hi; - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); if (!low_freq || !high_freq) return -EINVAL; @@ -298,7 +298,7 @@ static struct cpufreq_driver longrun_driver = { */ static int __init longrun_init(void) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); if (c->x86_vendor != X86_VENDOR_TRANSMETA || !cpu_has(c, X86_FEATURE_LONGRUN)) diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index 8eb414b906d..14791ec55cf 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -195,12 +195,12 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) { - struct cpuinfo_x86 *c = &cpu_data[policy->cpu]; + struct cpuinfo_x86 *c = &cpu_data(policy->cpu); int cpuid = 0; unsigned int i; #ifdef CONFIG_SMP - policy->cpus = cpu_sibling_map[policy->cpu]; + policy->cpus = per_cpu(cpu_sibling_map, policy->cpu); #endif /* Errata workaround */ @@ -279,7 +279,7 @@ static struct cpufreq_driver p4clockmod_driver = { static int __init cpufreq_p4_init(void) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); int ret; /* diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c index 6d028533931..eb9b62b0830 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c @@ -1,6 +1,6 @@ /* * This file was based upon code in Powertweak Linux (http://powertweak.sf.net) - * (C) 2000-2003 Dave Jones, Arjan van de Ven, Janne Pänkälä, Dominik Brodowski. + * (C) 2000-2003 Dave Jones, Arjan van de Ven, Janne Pänkälä, Dominik Brodowski. * * Licensed under the terms of the GNU GPL License version 2. * @@ -215,7 +215,7 @@ static struct cpufreq_driver powernow_k6_driver = { */ static int __init powernow_k6_init(void) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); if ((c->x86_vendor != X86_VENDOR_AMD) || (c->x86 != 5) || ((c->x86_model != 12) && (c->x86_model != 13))) diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c index 7decd6a50ff..b5a9863d6cd 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c @@ -114,7 +114,7 @@ static int check_fsb(unsigned int fsbspeed) static int check_powernow(void) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); unsigned int maxei, eax, ebx, ecx, edx; if ((c->x86_vendor != X86_VENDOR_AMD) || (c->x86 !=6)) { @@ -565,7 +565,7 @@ static unsigned int powernow_get(unsigned int cpu) } -static int __init acer_cpufreq_pst(struct dmi_system_id *d) +static int __init acer_cpufreq_pst(const struct dmi_system_id *d) { printk(KERN_WARNING "%s laptop with broken PST tables in BIOS detected.\n", d->ident); printk(KERN_WARNING "You need to downgrade to 3A21 (09/09/2002), or try a newer BIOS than 3A71 (01/20/2003)\n"); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index f105ffd0996..99e1ef9939b 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -57,7 +57,7 @@ static struct powernow_k8_data *powernow_data[NR_CPUS]; static int cpu_family = CPU_OPTERON; #ifndef CONFIG_SMP -static cpumask_t cpu_core_map[1]; +DEFINE_PER_CPU(cpumask_t, cpu_core_map); #endif /* Return a frequency in MHz, given an input fid */ @@ -144,7 +144,7 @@ static void count_off_irt(struct powernow_k8_data *data) return; } -/* the voltage stabalization time */ +/* the voltage stabilization time */ static void count_off_vst(struct powernow_k8_data *data) { udelay(data->vstable * VST_UNITS_20US); @@ -643,7 +643,7 @@ static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst, dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid); data->powernow_table = powernow_table; - if (first_cpu(cpu_core_map[data->cpu]) == data->cpu) + if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu) print_basics(data); for (j = 0; j < data->numps; j++) @@ -797,7 +797,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) /* fill in data */ data->numps = data->acpi_data.state_count; - if (first_cpu(cpu_core_map[data->cpu]) == data->cpu) + if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu) print_basics(data); powernow_k8_acpi_pst_values(data, 0); @@ -1171,7 +1171,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) if (cpu_family == CPU_HW_PSTATE) pol->cpus = cpumask_of_cpu(pol->cpu); else - pol->cpus = cpu_core_map[pol->cpu]; + pol->cpus = per_cpu(cpu_core_map, pol->cpu); data->available_cores = &(pol->cpus); /* Take a crude guess here. @@ -1237,7 +1237,7 @@ static unsigned int powernowk8_get (unsigned int cpu) cpumask_t oldmask = current->cpus_allowed; unsigned int khz = 0; - data = powernow_data[first_cpu(cpu_core_map[cpu])]; + data = powernow_data[first_cpu(per_cpu(cpu_core_map, cpu))]; if (!data) return -EINVAL; diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h index 8ae88f18128..afd2b520d35 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h @@ -140,10 +140,10 @@ struct powernow_k8_data { #define PLL_LOCK_CONVERSION (1000/5) /* ms to ns, then divide by clock period */ #define MAXIMUM_VID_STEPS 1 /* Current cpus only allow a single step of 25mV */ -#define VST_UNITS_20US 20 /* Voltage Stabalization Time is in units of 20us */ +#define VST_UNITS_20US 20 /* Voltage Stabilization Time is in units of 20us */ /* - * Most values of interest are enocoded in a single field of the _PSS + * Most values of interest are encoded in a single field of the _PSS * entries: the "control" value. */ diff --git a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c b/arch/x86/kernel/cpu/cpufreq/sc520_freq.c index d9f3e90a7ae..42da9bd677d 100644 --- a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c +++ b/arch/x86/kernel/cpu/cpufreq/sc520_freq.c @@ -102,7 +102,7 @@ static int sc520_freq_target (struct cpufreq_policy *policy, static int sc520_freq_cpu_init(struct cpufreq_policy *policy) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); int result; /* capability check */ @@ -151,7 +151,7 @@ static struct cpufreq_driver sc520_freq_driver = { static int __init sc520_freq_init(void) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); int err; /* Test if we have the right hardware */ diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c index 811d4743854..3031f119619 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c @@ -230,7 +230,7 @@ static struct cpu_model models[] = static int centrino_cpu_init_table(struct cpufreq_policy *policy) { - struct cpuinfo_x86 *cpu = &cpu_data[policy->cpu]; + struct cpuinfo_x86 *cpu = &cpu_data(policy->cpu); struct cpu_model *model; for(model = models; model->cpu_id != NULL; model++) @@ -340,7 +340,7 @@ static unsigned int get_cur_freq(unsigned int cpu) static int centrino_cpu_init(struct cpufreq_policy *policy) { - struct cpuinfo_x86 *cpu = &cpu_data[policy->cpu]; + struct cpuinfo_x86 *cpu = &cpu_data(policy->cpu); unsigned freq; unsigned l, h; int ret; @@ -612,7 +612,7 @@ static struct cpufreq_driver centrino_driver = { */ static int __init centrino_init(void) { - struct cpuinfo_x86 *cpu = cpu_data; + struct cpuinfo_x86 *cpu = &cpu_data(0); if (!cpu_has(cpu, X86_FEATURE_EST)) return -ENODEV; diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c index 36685e8f7be..14d68aa301e 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c @@ -322,7 +322,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) /* only run on CPU to be set, or on its sibling */ #ifdef CONFIG_SMP - policy->cpus = cpu_sibling_map[policy->cpu]; + policy->cpus = per_cpu(cpu_sibling_map, policy->cpu); #endif cpus_allowed = current->cpus_allowed; diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c index b1acc8ce316..76c3ab0da46 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c @@ -228,7 +228,7 @@ EXPORT_SYMBOL_GPL(speedstep_get_processor_frequency); unsigned int speedstep_detect_processor (void) { - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(0); u32 ebx, msr_lo, msr_hi; dprintk("x86: %x, model: %x\n", c->x86, c->x86_model); diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 122d2d75aa9..88d66fb8411 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -93,7 +93,7 @@ static void __cpuinit check_cx686_slop(struct cpuinfo_x86 *c) local_irq_save(flags); ccr3 = getCx86(CX86_CCR3); - setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ + setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ ccr5 = getCx86(CX86_CCR5); if (ccr5 & 2) setCx86(CX86_CCR5, ccr5 & 0xfd); /* reset SLOP */ @@ -115,9 +115,9 @@ static void __cpuinit set_cx86_reorder(void) printk(KERN_INFO "Enable Memory access reorder on Cyrix/NSC processor.\n"); ccr3 = getCx86(CX86_CCR3); - setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ + setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ - /* Load/Store Serialize to mem access disable (=reorder it) */ + /* Load/Store Serialize to mem access disable (=reorder it) */ setCx86(CX86_PCR0, getCx86(CX86_PCR0) & ~0x80); /* set load/store serialize from 1GB to 4GB */ ccr3 |= 0xe0; @@ -146,7 +146,7 @@ static void __cpuinit set_cx86_inc(void) printk(KERN_INFO "Enable Incrementor on Cyrix/NSC processor.\n"); ccr3 = getCx86(CX86_CCR3); - setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ + setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ /* PCR1 -- Performance Control */ /* Incrementor on, whatever that is */ setCx86(CX86_PCR1, getCx86(CX86_PCR1) | 0x02); @@ -256,7 +256,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) u32 vendor, device; /* It isn't really a PCI quirk directly, but the cure is the same. The MediaGX has deep magic SMM stuff that handles the - SB emulation. It thows away the fifo on disable_dma() which + SB emulation. It throws away the fifo on disable_dma() which is wrong and ruins the audio. Bug2: VSA1 has a wrap bug so that using maximum sized DMA diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index dc4e08147b1..cc8c501b9f3 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <asm/processor.h> +#include <asm/pgtable.h> #include <asm/msr.h> #include <asm/uaccess.h> @@ -19,8 +20,6 @@ #include <mach_apic.h> #endif -extern int trap_init_f00f_bug(void); - #ifdef CONFIG_X86_INTEL_USERCOPY /* * Alignment at which movsl is preferred for bulk memory copies. @@ -95,6 +94,20 @@ static int __cpuinit num_cpu_cores(struct cpuinfo_x86 *c) return 1; } +#ifdef CONFIG_X86_F00F_BUG +static void __cpuinit trap_init_f00f_bug(void) +{ + __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO); + + /* + * Update the IDT descriptor and reload the IDT so that + * it uses the read-only mapped virtual address. + */ + idt_descr.address = fix_to_virt(FIX_F00F_IDT); + load_idt(&idt_descr); +} +#endif + static void __cpuinit init_intel(struct cpuinfo_x86 *c) { unsigned int l2 = 0; diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index db6c25aa577..9921b01fe19 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -170,15 +170,15 @@ union l3_cache { unsigned val; }; -static const unsigned short assocs[] = { +static unsigned short assocs[] __cpuinitdata = { [1] = 1, [2] = 2, [4] = 4, [6] = 8, [8] = 16, [0xa] = 32, [0xb] = 48, [0xc] = 64, [0xf] = 0xffff // ?? }; -static const unsigned char levels[] = { 1, 1, 2, 3 }; -static const unsigned char types[] = { 1, 2, 3, 3 }; +static unsigned char levels[] __cpuinitdata = { 1, 1, 2, 3 }; +static unsigned char types[] __cpuinitdata = { 1, 2, 3, 3 }; static void __cpuinit amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, union _cpuid4_leaf_ebx *ebx, @@ -295,7 +295,7 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */ unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; #ifdef CONFIG_X86_HT - unsigned int cpu = (c == &boot_cpu_data) ? 0 : (c - cpu_data); + unsigned int cpu = c->cpu_index; #endif if (c->cpuid_level > 3) { @@ -417,14 +417,14 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) if (new_l2) { l2 = new_l2; #ifdef CONFIG_X86_HT - cpu_llc_id[cpu] = l2_id; + per_cpu(cpu_llc_id, cpu) = l2_id; #endif } if (new_l3) { l3 = new_l3; #ifdef CONFIG_X86_HT - cpu_llc_id[cpu] = l3_id; + per_cpu(cpu_llc_id, cpu) = l3_id; #endif } @@ -459,7 +459,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) struct _cpuid4_info *this_leaf, *sibling_leaf; unsigned long num_threads_sharing; int index_msb, i; - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(cpu); this_leaf = CPUID4_INFO_IDX(cpu, index); num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing; @@ -470,8 +470,8 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) index_msb = get_count_order(num_threads_sharing); for_each_online_cpu(i) { - if (c[i].apicid >> index_msb == - c[cpu].apicid >> index_msb) { + if (cpu_data(i).apicid >> index_msb == + c->apicid >> index_msb) { cpu_set(i, this_leaf->shared_cpu_map); if (i != cpu && cpuid4_info[i]) { sibling_leaf = CPUID4_INFO_IDX(i, index); @@ -493,12 +493,17 @@ static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index) } } #else -static void __init cache_shared_cpu_map_setup(unsigned int cpu, int index) {} -static void __init cache_remove_shared_cpu_map(unsigned int cpu, int index) {} +static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) {} +static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index) {} #endif static void free_cache_attributes(unsigned int cpu) { + int i; + + for (i = 0; i < num_cache_leaves; i++) + cache_remove_shared_cpu_map(cpu, i); + kfree(cpuid4_info[cpu]); cpuid4_info[cpu] = NULL; } @@ -506,8 +511,8 @@ static void free_cache_attributes(unsigned int cpu) static int __cpuinit detect_cache_attributes(unsigned int cpu) { struct _cpuid4_info *this_leaf; - unsigned long j; - int retval; + unsigned long j; + int retval; cpumask_t oldmask; if (num_cache_leaves == 0) @@ -524,19 +529,26 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu) goto out; /* Do cpuid and store the results */ - retval = 0; for (j = 0; j < num_cache_leaves; j++) { this_leaf = CPUID4_INFO_IDX(cpu, j); retval = cpuid4_cache_lookup(j, this_leaf); - if (unlikely(retval < 0)) + if (unlikely(retval < 0)) { + int i; + + for (i = 0; i < j; i++) + cache_remove_shared_cpu_map(cpu, i); break; + } cache_shared_cpu_map_setup(cpu, j); } set_cpus_allowed(current, oldmask); out: - if (retval) - free_cache_attributes(cpu); + if (retval) { + kfree(cpuid4_info[cpu]); + cpuid4_info[cpu] = NULL; + } + return retval; } @@ -669,7 +681,7 @@ static struct kobj_type ktype_percpu_entry = { .sysfs_ops = &sysfs_ops, }; -static void cpuid4_cache_sysfs_exit(unsigned int cpu) +static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu) { kfree(cache_kobject[cpu]); kfree(index_kobject[cpu]); @@ -680,13 +692,14 @@ static void cpuid4_cache_sysfs_exit(unsigned int cpu) static int __cpuinit cpuid4_cache_sysfs_init(unsigned int cpu) { + int err; if (num_cache_leaves == 0) return -ENOENT; - detect_cache_attributes(cpu); - if (cpuid4_info[cpu] == NULL) - return -ENOENT; + err = detect_cache_attributes(cpu); + if (err) + return err; /* Allocate all required memory */ cache_kobject[cpu] = kzalloc(sizeof(struct kobject), GFP_KERNEL); @@ -705,13 +718,15 @@ err_out: return -ENOMEM; } +static cpumask_t cache_dev_map = CPU_MASK_NONE; + /* Add/Remove cache interface for CPU device */ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) { unsigned int cpu = sys_dev->id; unsigned long i, j; struct _index_kobject *this_object; - int retval = 0; + int retval; retval = cpuid4_cache_sysfs_init(cpu); if (unlikely(retval < 0)) @@ -721,6 +736,10 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) kobject_set_name(cache_kobject[cpu], "%s", "cache"); cache_kobject[cpu]->ktype = &ktype_percpu_entry; retval = kobject_register(cache_kobject[cpu]); + if (retval < 0) { + cpuid4_cache_sysfs_exit(cpu); + return retval; + } for (i = 0; i < num_cache_leaves; i++) { this_object = INDEX_KOBJECT_PTR(cpu,i); @@ -740,6 +759,9 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev) break; } } + if (!retval) + cpu_set(cpu, cache_dev_map); + return retval; } @@ -750,13 +772,14 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev) if (cpuid4_info[cpu] == NULL) return; - for (i = 0; i < num_cache_leaves; i++) { - cache_remove_shared_cpu_map(cpu, i); + if (!cpu_isset(cpu, cache_dev_map)) + return; + cpu_clear(cpu, cache_dev_map); + + for (i = 0; i < num_cache_leaves; i++) kobject_unregister(&(INDEX_KOBJECT_PTR(cpu,i)->kobj)); - } kobject_unregister(cache_kobject[cpu]); cpuid4_cache_sysfs_exit(cpu); - return; } static int __cpuinit cacheinfo_cpu_callback(struct notifier_block *nfb, @@ -781,7 +804,7 @@ static int __cpuinit cacheinfo_cpu_callback(struct notifier_block *nfb, static struct notifier_block __cpuinitdata cacheinfo_cpu_notifier = { - .notifier_call = cacheinfo_cpu_callback, + .notifier_call = cacheinfo_cpu_callback, }; static int __cpuinit cache_sysfs_init(void) @@ -791,13 +814,15 @@ static int __cpuinit cache_sysfs_init(void) if (num_cache_leaves == 0) return 0; - register_hotcpu_notifier(&cacheinfo_cpu_notifier); - for_each_online_cpu(i) { - cacheinfo_cpu_callback(&cacheinfo_cpu_notifier, CPU_ONLINE, - (void *)(long)i); - } + int err; + struct sys_device *sys_dev = get_cpu_sysdev(i); + err = cache_add_dev(sys_dev); + if (err) + return err; + } + register_hotcpu_notifier(&cacheinfo_cpu_notifier); return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile index f1ebe1c1c17..d7d2323bbb6 100644 --- a/arch/x86/kernel/cpu/mcheck/Makefile +++ b/arch/x86/kernel/cpu/mcheck/Makefile @@ -1,2 +1,6 @@ -obj-y = mce.o k7.o p4.o p5.o p6.o winchip.o therm_throt.o -obj-$(CONFIG_X86_MCE_NONFATAL) += non-fatal.o +obj-y = mce_$(BITS).o therm_throt.o + +obj-$(CONFIG_X86_32) += k7.o p4.o p5.o p6.o winchip.o +obj-$(CONFIG_X86_MCE_INTEL) += mce_intel_64.o +obj-$(CONFIG_X86_MCE_AMD) += mce_amd_64.o +obj-$(CONFIG_X86_MCE_NONFATAL) += non-fatal.o diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce_32.c index 34c781eddee..34c781eddee 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce_32.c diff --git a/arch/x86/kernel/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index a66d607f5b9..447b351f1f2 100644 --- a/arch/x86/kernel/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -1,8 +1,8 @@ /* * Machine check handler. * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs. - * Rest from unknown author(s). - * 2004 Andi Kleen. Rewrote most of it. + * Rest from unknown author(s). + * 2004 Andi Kleen. Rewrote most of it. */ #include <linux/init.h> @@ -23,7 +23,7 @@ #include <linux/ctype.h> #include <linux/kmod.h> #include <linux/kdebug.h> -#include <asm/processor.h> +#include <asm/processor.h> #include <asm/msr.h> #include <asm/mce.h> #include <asm/uaccess.h> @@ -63,10 +63,10 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_wait); * separate MCEs from kernel messages to avoid bogus bug reports. */ -struct mce_log mcelog = { +struct mce_log mcelog = { MCE_LOG_SIGNATURE, MCE_LOG_LEN, -}; +}; void mce_log(struct mce *mce) { @@ -76,9 +76,6 @@ void mce_log(struct mce *mce) wmb(); for (;;) { entry = rcu_dereference(mcelog.next); - /* The rmb forces the compiler to reload next in each - iteration */ - rmb(); for (;;) { /* When the buffer fills up discard new entries. Assume that the earlier errors are the more interesting. */ @@ -114,42 +111,42 @@ static void print_mce(struct mce *m) "CPU %d: Machine Check Exception: %16Lx Bank %d: %016Lx\n", m->cpu, m->mcgstatus, m->bank, m->status); if (m->rip) { - printk(KERN_EMERG - "RIP%s %02x:<%016Lx> ", + printk(KERN_EMERG "RIP%s %02x:<%016Lx> ", !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "", m->cs, m->rip); if (m->cs == __KERNEL_CS) print_symbol("{%s}", m->rip); printk("\n"); } - printk(KERN_EMERG "TSC %Lx ", m->tsc); + printk(KERN_EMERG "TSC %Lx ", m->tsc); if (m->addr) printk("ADDR %Lx ", m->addr); if (m->misc) - printk("MISC %Lx ", m->misc); + printk("MISC %Lx ", m->misc); printk("\n"); printk(KERN_EMERG "This is not a software problem!\n"); - printk(KERN_EMERG - "Run through mcelog --ascii to decode and contact your hardware vendor\n"); + printk(KERN_EMERG "Run through mcelog --ascii to decode " + "and contact your hardware vendor\n"); } static void mce_panic(char *msg, struct mce *backup, unsigned long start) -{ +{ int i; oops_begin(); for (i = 0; i < MCE_LOG_LEN; i++) { unsigned long tsc = mcelog.entry[i].tsc; + if (time_before(tsc, start)) continue; - print_mce(&mcelog.entry[i]); + print_mce(&mcelog.entry[i]); if (backup && mcelog.entry[i].tsc == backup->tsc) backup = NULL; } if (backup) print_mce(backup); panic(msg); -} +} static int mce_available(struct cpuinfo_x86 *c) { @@ -173,10 +170,9 @@ static inline void mce_get_rip(struct mce *m, struct pt_regs *regs) } } -/* +/* * The actual machine check handler */ - void do_machine_check(struct pt_regs * regs, long error_code) { struct mce m, panicm; @@ -197,7 +193,8 @@ void do_machine_check(struct pt_regs * regs, long error_code) atomic_inc(&mce_entry); if (regs) - notify_die(DIE_NMI, "machine check", regs, error_code, 18, SIGKILL); + notify_die(DIE_NMI, "machine check", regs, error_code, 18, + SIGKILL); if (!banks) goto out2; @@ -207,15 +204,15 @@ void do_machine_check(struct pt_regs * regs, long error_code) /* if the restart IP is not valid, we're done for */ if (!(m.mcgstatus & MCG_STATUS_RIPV)) no_way_out = 1; - + rdtscll(mcestart); barrier(); for (i = 0; i < banks; i++) { if (!bank[i]) continue; - - m.misc = 0; + + m.misc = 0; m.addr = 0; m.bank = i; m.tsc = 0; @@ -323,7 +320,7 @@ void do_machine_check(struct pt_regs * regs, long error_code) #ifdef CONFIG_X86_MCE_INTEL /*** * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog - * @cpu: The CPU on which the event occured. + * @cpu: The CPU on which the event occurred. * @status: Event status information * * This function should be called by the thermal interrupt after the @@ -375,7 +372,7 @@ static void mcheck_timer(struct work_struct *work) if (mce_notify_user()) { next_interval = max(next_interval/2, HZ/100); } else { - next_interval = min(next_interval*2, + next_interval = min(next_interval * 2, (int)round_jiffies_relative(check_interval*HZ)); } @@ -426,18 +423,18 @@ static struct notifier_block mce_idle_notifier = { }; static __init int periodic_mcheck_init(void) -{ +{ next_interval = check_interval * HZ; if (next_interval) schedule_delayed_work(&mcheck_work, round_jiffies_relative(next_interval)); idle_notifier_register(&mce_idle_notifier); return 0; -} +} __initcall(periodic_mcheck_init); -/* +/* * Initialize Machine Checks for a CPU. */ static void mce_init(void *dummy) @@ -447,9 +444,9 @@ static void mce_init(void *dummy) rdmsrl(MSR_IA32_MCG_CAP, cap); banks = cap & 0xff; - if (banks > NR_BANKS) { + if (banks > NR_BANKS) { printk(KERN_INFO "MCE: warning: using only %d banks\n", banks); - banks = NR_BANKS; + banks = NR_BANKS; } /* Use accurate RIP reporting if available. */ if ((cap & (1<<9)) && ((cap >> 16) & 0xff) >= 9) @@ -467,15 +464,15 @@ static void mce_init(void *dummy) for (i = 0; i < banks; i++) { wrmsrl(MSR_IA32_MC0_CTL+4*i, bank[i]); wrmsrl(MSR_IA32_MC0_STATUS+4*i, 0); - } + } } /* Add per CPU specific workarounds here */ static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c) -{ +{ /* This should be disabled by the BIOS, but isn't always */ if (c->x86_vendor == X86_VENDOR_AMD && c->x86 == 15) { - /* disable GART TBL walk error reporting, which trips off + /* disable GART TBL walk error reporting, which trips off incorrectly with the IOMMU & 3ware & Cerberus. */ clear_bit(10, &bank[4]); /* Lots of broken BIOS around that don't clear them @@ -483,7 +480,7 @@ static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c) mce_bootlog = 0; } -} +} static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c) { @@ -499,15 +496,15 @@ static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c) } } -/* +/* * Called for each booted CPU to set up machine checks. - * Must be called with preempt off. + * Must be called with preempt off. */ void __cpuinit mcheck_init(struct cpuinfo_x86 *c) { static cpumask_t mce_cpus = CPU_MASK_NONE; - mce_cpu_quirks(c); + mce_cpu_quirks(c); if (mce_dont_init || cpu_test_and_set(smp_processor_id(), mce_cpus) || @@ -556,13 +553,15 @@ static int mce_release(struct inode *inode, struct file *file) return 0; } -static void collect_tscs(void *data) -{ +static void collect_tscs(void *data) +{ unsigned long *cpu_tsc = (unsigned long *)data; + rdtscll(cpu_tsc[smp_processor_id()]); -} +} -static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, loff_t *off) +static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, + loff_t *off) { unsigned long *cpu_tsc; static DECLARE_MUTEX(mce_read_sem); @@ -574,19 +573,20 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, loff if (!cpu_tsc) return -ENOMEM; - down(&mce_read_sem); + down(&mce_read_sem); next = rcu_dereference(mcelog.next); /* Only supports full reads right now */ - if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) { + if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce)) { up(&mce_read_sem); kfree(cpu_tsc); return -EINVAL; } err = 0; - for (i = 0; i < next; i++) { + for (i = 0; i < next; i++) { unsigned long start = jiffies; + while (!mcelog.entry[i].finished) { if (time_after_eq(jiffies, start + 2)) { memset(mcelog.entry + i,0, sizeof(struct mce)); @@ -596,31 +596,34 @@ static ssize_t mce_read(struct file *filp, char __user *ubuf, size_t usize, loff } smp_rmb(); err |= copy_to_user(buf, mcelog.entry + i, sizeof(struct mce)); - buf += sizeof(struct mce); + buf += sizeof(struct mce); timeout: ; - } + } memset(mcelog.entry, 0, next * sizeof(struct mce)); mcelog.next = 0; synchronize_sched(); - /* Collect entries that were still getting written before the synchronize. */ - + /* + * Collect entries that were still getting written before the + * synchronize. + */ on_each_cpu(collect_tscs, cpu_tsc, 1, 1); - for (i = next; i < MCE_LOG_LEN; i++) { - if (mcelog.entry[i].finished && - mcelog.entry[i].tsc < cpu_tsc[mcelog.entry[i].cpu]) { - err |= copy_to_user(buf, mcelog.entry+i, sizeof(struct mce)); + for (i = next; i < MCE_LOG_LEN; i++) { + if (mcelog.entry[i].finished && + mcelog.entry[i].tsc < cpu_tsc[mcelog.entry[i].cpu]) { + err |= copy_to_user(buf, mcelog.entry+i, + sizeof(struct mce)); smp_rmb(); buf += sizeof(struct mce); memset(&mcelog.entry[i], 0, sizeof(struct mce)); } - } + } up(&mce_read_sem); kfree(cpu_tsc); - return err ? -EFAULT : buf - ubuf; + return err ? -EFAULT : buf - ubuf; } static unsigned int mce_poll(struct file *file, poll_table *wait) @@ -631,26 +634,29 @@ static unsigned int mce_poll(struct file *file, poll_table *wait) return 0; } -static int mce_ioctl(struct inode *i, struct file *f,unsigned int cmd, unsigned long arg) +static int mce_ioctl(struct inode *i, struct file *f,unsigned int cmd, + unsigned long arg) { int __user *p = (int __user *)arg; + if (!capable(CAP_SYS_ADMIN)) - return -EPERM; + return -EPERM; switch (cmd) { - case MCE_GET_RECORD_LEN: + case MCE_GET_RECORD_LEN: return put_user(sizeof(struct mce), p); case MCE_GET_LOG_LEN: - return put_user(MCE_LOG_LEN, p); + return put_user(MCE_LOG_LEN, p); case MCE_GETCLEAR_FLAGS: { unsigned flags; - do { + + do { flags = mcelog.flags; - } while (cmpxchg(&mcelog.flags, flags, 0) != flags); - return put_user(flags, p); + } while (cmpxchg(&mcelog.flags, flags, 0) != flags); + return put_user(flags, p); } default: - return -ENOTTY; - } + return -ENOTTY; + } } static const struct file_operations mce_chrdev_ops = { @@ -681,25 +687,22 @@ void __init restart_mce(void) set_in_cr4(X86_CR4_MCE); } -/* - * Old style boot options parsing. Only for compatibility. +/* + * Old style boot options parsing. Only for compatibility. */ - static int __init mcheck_disable(char *str) { mce_dont_init = 1; return 1; } -/* mce=off disables machine check. Note you can reenable it later +/* mce=off disables machine check. Note you can re-enable it later using sysfs. mce=TOLERANCELEVEL (number, see above) mce=bootlog Log MCEs from before booting. Disabled by default on AMD. mce=nobootlog Don't log MCEs from before booting. */ static int __init mcheck_enable(char *str) { - if (*str == '=') - str++; if (!strcmp(str, "off")) mce_dont_init = 1; else if (!strcmp(str, "bootlog") || !strcmp(str,"nobootlog")) @@ -707,16 +710,16 @@ static int __init mcheck_enable(char *str) else if (isdigit(str[0])) get_option(&str, &tolerant); else - printk("mce= argument %s ignored. Please use /sys", str); + printk("mce= argument %s ignored. Please use /sys", str); return 1; } __setup("nomce", mcheck_disable); -__setup("mce", mcheck_enable); +__setup("mce=", mcheck_enable); -/* +/* * Sysfs support - */ + */ /* On resume clear all MCE state. Don't want to see leftovers from the BIOS. Only one CPU is active at this time, the others get readded later using @@ -728,12 +731,12 @@ static int mce_resume(struct sys_device *dev) } /* Reinit MCEs after user configuration changes */ -static void mce_restart(void) -{ +static void mce_restart(void) +{ if (next_interval) cancel_delayed_work(&mcheck_work); /* Timer race is harmless here */ - on_each_cpu(mce_init, NULL, 1, 1); + on_each_cpu(mce_init, NULL, 1, 1); next_interval = check_interval * HZ; if (next_interval) schedule_delayed_work(&mcheck_work, @@ -749,17 +752,17 @@ DEFINE_PER_CPU(struct sys_device, device_mce); /* Why are there no generic functions for this? */ #define ACCESSOR(name, var, start) \ - static ssize_t show_ ## name(struct sys_device *s, char *buf) { \ - return sprintf(buf, "%lx\n", (unsigned long)var); \ - } \ + static ssize_t show_ ## name(struct sys_device *s, char *buf) { \ + return sprintf(buf, "%lx\n", (unsigned long)var); \ + } \ static ssize_t set_ ## name(struct sys_device *s,const char *buf,size_t siz) { \ - char *end; \ - unsigned long new = simple_strtoul(buf, &end, 0); \ - if (end == buf) return -EINVAL; \ - var = new; \ - start; \ - return end-buf; \ - } \ + char *end; \ + unsigned long new = simple_strtoul(buf, &end, 0); \ + if (end == buf) return -EINVAL; \ + var = new; \ + start; \ + return end-buf; \ + } \ static SYSDEV_ATTR(name, 0644, show_ ## name, set_ ## name); /* TBD should generate these dynamically based on number of available banks */ @@ -799,24 +802,41 @@ static struct sysdev_attribute *mce_attributes[] = { NULL }; +static cpumask_t mce_device_initialized = CPU_MASK_NONE; + /* Per cpu sysdev init. All of the cpus still share the same ctl bank */ static __cpuinit int mce_create_device(unsigned int cpu) { int err; int i; - if (!mce_available(&cpu_data[cpu])) + + if (!mce_available(&cpu_data(cpu))) return -EIO; + memset(&per_cpu(device_mce, cpu).kobj, 0, sizeof(struct kobject)); per_cpu(device_mce,cpu).id = cpu; per_cpu(device_mce,cpu).cls = &mce_sysclass; err = sysdev_register(&per_cpu(device_mce,cpu)); + if (err) + return err; + + for (i = 0; mce_attributes[i]; i++) { + err = sysdev_create_file(&per_cpu(device_mce,cpu), + mce_attributes[i]); + if (err) + goto error; + } + cpu_set(cpu, mce_device_initialized); - if (!err) { - for (i = 0; mce_attributes[i]; i++) - sysdev_create_file(&per_cpu(device_mce,cpu), - mce_attributes[i]); + return 0; +error: + while (i--) { + sysdev_remove_file(&per_cpu(device_mce,cpu), + mce_attributes[i]); } + sysdev_unregister(&per_cpu(device_mce,cpu)); + return err; } @@ -824,11 +844,14 @@ static void mce_remove_device(unsigned int cpu) { int i; + if (!cpu_isset(cpu, mce_device_initialized)) + return; + for (i = 0; mce_attributes[i]; i++) sysdev_remove_file(&per_cpu(device_mce,cpu), mce_attributes[i]); sysdev_unregister(&per_cpu(device_mce,cpu)); - memset(&per_cpu(device_mce, cpu).kobj, 0, sizeof(struct kobject)); + cpu_clear(cpu, mce_device_initialized); } /* Get notified when a cpu comes on/off. Be hotplug friendly. */ @@ -862,9 +885,13 @@ static __init int mce_init_device(void) if (!mce_available(&boot_cpu_data)) return -EIO; err = sysdev_class_register(&mce_sysclass); + if (err) + return err; for_each_online_cpu(i) { - mce_create_device(i); + err = mce_create_device(i); + if (err) + return err; } register_hotcpu_notifier(&mce_cpu_notifier); diff --git a/arch/x86/kernel/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c index 2f8a7f18b0f..752fb16a817 100644 --- a/arch/x86/kernel/mce_amd_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c @@ -237,6 +237,7 @@ asmlinkage void mce_threshold_interrupt(void) } } out: + add_pda(irq_threshold_count, 1); irq_exit(); } @@ -471,11 +472,11 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) sprintf(name, "threshold_bank%i", bank); #ifdef CONFIG_SMP - if (cpu_data[cpu].cpu_core_id && shared_bank[bank]) { /* symlink */ - i = first_cpu(cpu_core_map[cpu]); + if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */ + i = first_cpu(per_cpu(cpu_core_map, cpu)); /* first core not up yet */ - if (cpu_data[i].cpu_core_id) + if (cpu_data(i).cpu_core_id) goto out; /* already linked */ @@ -492,7 +493,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (err) goto out; - b->cpus = cpu_core_map[cpu]; + b->cpus = per_cpu(cpu_core_map, cpu); per_cpu(threshold_banks, cpu)[bank] = b; goto out; } @@ -509,7 +510,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) #ifndef CONFIG_SMP b->cpus = CPU_MASK_ALL; #else - b->cpus = cpu_core_map[cpu]; + b->cpus = per_cpu(cpu_core_map, cpu); #endif err = kobject_register(&b->kobj); if (err) diff --git a/arch/x86/kernel/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c index 6551505d8a2..c17eaf5dd6d 100644 --- a/arch/x86/kernel/mce_intel_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c @@ -26,6 +26,7 @@ asmlinkage void smp_thermal_interrupt(void) if (therm_throt_process(msr_val & 1)) mce_log_therm_throt_event(smp_processor_id(), msr_val); + add_pda(irq_thermal_count, 1); irq_exit(); } diff --git a/arch/x86/kernel/cpu/mcheck/p4.c b/arch/x86/kernel/cpu/mcheck/p4.c index 1509edfb231..be4dabfee1f 100644 --- a/arch/x86/kernel/cpu/mcheck/p4.c +++ b/arch/x86/kernel/cpu/mcheck/p4.c @@ -61,6 +61,7 @@ fastcall void smp_thermal_interrupt(struct pt_regs *regs) { irq_enter(); vendor_thermal_interrupt(regs); + __get_cpu_var(irq_stat).irq_thermal_count++; irq_exit(); } diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 1203dc5ab87..24885be5c48 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -131,17 +131,19 @@ static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb, { unsigned int cpu = (unsigned long)hcpu; struct sys_device *sys_dev; - int err; + int err = 0; sys_dev = get_cpu_sysdev(cpu); switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: mutex_lock(&therm_cpu_lock); err = thermal_throttle_add_dev(sys_dev); mutex_unlock(&therm_cpu_lock); WARN_ON(err); break; + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: case CPU_DEAD_FROZEN: mutex_lock(&therm_cpu_lock); @@ -149,10 +151,10 @@ static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb, mutex_unlock(&therm_cpu_lock); break; } - return NOTIFY_OK; + return err ? NOTIFY_BAD : NOTIFY_OK; } -static struct notifier_block thermal_throttle_cpu_notifier = +static struct notifier_block thermal_throttle_cpu_notifier __cpuinitdata = { .notifier_call = thermal_throttle_cpu_callback, }; diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index 2287d4863a8..9964be3de2b 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -147,10 +147,10 @@ static void prepare_set(void) write_cr0(cr0); wbinvd(); - /* Cyrix ARRs - everything else were excluded at the top */ + /* Cyrix ARRs - everything else was excluded at the top */ ccr3 = getCx86(CX86_CCR3); - /* Cyrix ARRs - everything else were excluded at the top */ + /* Cyrix ARRs - everything else was excluded at the top */ setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 56f64e34829..992f08dfbb6 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -182,7 +182,7 @@ static inline void k8_enable_fixed_iorrs(void) /** * Checks and updates an fixed-range MTRR if it differs from the value it - * should have. If K8 extenstions are wanted, update the K8 SYSCFG MSR also. + * should have. If K8 extentions are wanted, update the K8 SYSCFG MSR also. * see AMD publication no. 24593, chapter 7.8.1, page 233 for more information * \param msr MSR address of the MTTR which should be checked and updated * \param changed pointer which indicates whether the MTRR needed to be changed diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index c48b6fea5ab..3b20613325d 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -139,13 +139,12 @@ struct set_mtrr_data { mtrr_type smp_type; }; -#ifdef CONFIG_SMP - static void ipi_handler(void *info) /* [SUMMARY] Synchronisation handler. Executed by "other" CPUs. [RETURNS] Nothing. */ { +#ifdef CONFIG_SMP struct set_mtrr_data *data = info; unsigned long flags; @@ -168,9 +167,8 @@ static void ipi_handler(void *info) atomic_dec(&data->count); local_irq_restore(flags); -} - #endif +} static inline int types_compatible(mtrr_type type1, mtrr_type type2) { return type1 == MTRR_TYPE_UNCACHABLE || @@ -738,13 +736,7 @@ void mtrr_ap_init(void) */ void mtrr_save_state(void) { - int cpu = get_cpu(); - - if (cpu == 0) - mtrr_save_fixed_ranges(NULL); - else - smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1); - put_cpu(); + smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1); } static int __init mtrr_init_finialize(void) @@ -754,7 +746,7 @@ static int __init mtrr_init_finialize(void) if (use_intel()) mtrr_state_warn(); else { - /* The CPUs haven't MTRR and seemes not support SMP. They have + /* The CPUs haven't MTRR and seem to not support SMP. They have * specific drivers, we use a tricky method to support * suspend/resume for them. * TBD: is there any system with such CPU which supports diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 93fecd4b03d..c02541e6e65 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -34,7 +34,7 @@ struct wd_ops { u64 checkbit; }; -static struct wd_ops *wd_ops; +static const struct wd_ops *wd_ops; /* this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's * offset from MSR_P4_BSU_ESCR0. It will be the max for all platforms (for now) @@ -120,7 +120,9 @@ int reserve_perfctr_nmi(unsigned int msr) unsigned int counter; counter = nmi_perfctr_msr_to_bit(msr); - BUG_ON(counter > NMI_MAX_COUNTER_BITS); + /* register not managed by the allocator? */ + if (counter > NMI_MAX_COUNTER_BITS) + return 1; if (!test_and_set_bit(counter, perfctr_nmi_owner)) return 1; @@ -132,7 +134,9 @@ void release_perfctr_nmi(unsigned int msr) unsigned int counter; counter = nmi_perfctr_msr_to_bit(msr); - BUG_ON(counter > NMI_MAX_COUNTER_BITS); + /* register not managed by the allocator? */ + if (counter > NMI_MAX_COUNTER_BITS) + return; clear_bit(counter, perfctr_nmi_owner); } @@ -142,7 +146,9 @@ int reserve_evntsel_nmi(unsigned int msr) unsigned int counter; counter = nmi_evntsel_msr_to_bit(msr); - BUG_ON(counter > NMI_MAX_COUNTER_BITS); + /* register not managed by the allocator? */ + if (counter > NMI_MAX_COUNTER_BITS) + return 1; if (!test_and_set_bit(counter, evntsel_nmi_owner)) return 1; @@ -154,7 +160,9 @@ void release_evntsel_nmi(unsigned int msr) unsigned int counter; counter = nmi_evntsel_msr_to_bit(msr); - BUG_ON(counter > NMI_MAX_COUNTER_BITS); + /* register not managed by the allocator? */ + if (counter > NMI_MAX_COUNTER_BITS) + return; clear_bit(counter, evntsel_nmi_owner); } @@ -317,7 +325,7 @@ static void single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz); } -static struct wd_ops k7_wd_ops = { +static const struct wd_ops k7_wd_ops = { .reserve = single_msr_reserve, .unreserve = single_msr_unreserve, .setup = setup_k7_watchdog, @@ -380,7 +388,7 @@ static void p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) write_watchdog_counter32(wd->perfctr_msr, NULL,nmi_hz); } -static struct wd_ops p6_wd_ops = { +static const struct wd_ops p6_wd_ops = { .reserve = single_msr_reserve, .unreserve = single_msr_unreserve, .setup = setup_p6_watchdog, @@ -532,7 +540,7 @@ static void p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz) write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz); } -static struct wd_ops p4_wd_ops = { +static const struct wd_ops p4_wd_ops = { .reserve = p4_reserve, .unreserve = p4_unreserve, .setup = setup_p4_watchdog, @@ -550,6 +558,8 @@ static struct wd_ops p4_wd_ops = { #define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL #define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK +static struct wd_ops intel_arch_wd_ops; + static int setup_intel_arch_watchdog(unsigned nmi_hz) { unsigned int ebx; @@ -591,11 +601,11 @@ static int setup_intel_arch_watchdog(unsigned nmi_hz) wd->perfctr_msr = perfctr_msr; wd->evntsel_msr = evntsel_msr; wd->cccr_msr = 0; //unused - wd_ops->checkbit = 1ULL << (eax.split.bit_width - 1); + intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1); return 1; } -static struct wd_ops intel_arch_wd_ops = { +static struct wd_ops intel_arch_wd_ops __read_mostly = { .reserve = single_msr_reserve, .unreserve = single_msr_unreserve, .setup = setup_intel_arch_watchdog, diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 1e31b6caffb..066f8c6af4d 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -49,7 +49,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) /* Intel-defined (#2) */ "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est", "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL, - NULL, NULL, "dca", NULL, NULL, NULL, NULL, "popcnt", + NULL, NULL, "dca", "sse4_1", "sse4_2", NULL, NULL, "popcnt", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, /* VIA/Cyrix/Centaur-defined */ @@ -59,10 +59,10 @@ static int show_cpuinfo(struct seq_file *m, void *v) NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, /* AMD-defined (#2) */ - "lahf_lm", "cmp_legacy", "svm", "extapic", "cr8_legacy", - "altmovcr8", "abm", "sse4a", - "misalignsse", "3dnowprefetch", - "osvw", "ibs", NULL, NULL, NULL, NULL, + "lahf_lm", "cmp_legacy", "svm", "extapic", + "cr8_legacy", "abm", "sse4a", "misalignsse", + "3dnowprefetch", "osvw", "ibs", "sse5", + "skinit", "wdt", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, @@ -85,12 +85,13 @@ static int show_cpuinfo(struct seq_file *m, void *v) /* nothing */ }; struct cpuinfo_x86 *c = v; - int i, n = c - cpu_data; + int i, n = 0; int fpu_exception; #ifdef CONFIG_SMP if (!cpu_online(n)) return 0; + n = c->cpu_index; #endif seq_printf(m, "processor\t: %d\n" "vendor_id\t: %s\n" @@ -122,7 +123,8 @@ static int show_cpuinfo(struct seq_file *m, void *v) #ifdef CONFIG_X86_HT if (c->x86_max_cores * smp_num_siblings > 1) { seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", cpus_weight(cpu_core_map[n])); + seq_printf(m, "siblings\t: %d\n", + cpus_weight(per_cpu(cpu_core_map, n))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); } @@ -174,11 +176,15 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { - return *pos < NR_CPUS ? cpu_data + *pos : NULL; + if (*pos == 0) /* just in case, cpu 0 is not the first */ + *pos = first_cpu(cpu_possible_map); + if ((*pos) < NR_CPUS && cpu_possible(*pos)) + return &cpu_data(*pos); + return NULL; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) { - ++*pos; + *pos = next_cpu(*pos, cpu_possible_map); return c_start(m, pos); } static void c_stop(struct seq_file *m, void *v) diff --git a/arch/x86/kernel/cpufreq/Kconfig b/arch/x86/kernel/cpufreq/Kconfig deleted file mode 100644 index a3fd51926cb..00000000000 --- a/arch/x86/kernel/cpufreq/Kconfig +++ /dev/null @@ -1,108 +0,0 @@ -# -# CPU Frequency scaling -# - -menu "CPU Frequency scaling" - -source "drivers/cpufreq/Kconfig" - -if CPU_FREQ - -comment "CPUFreq processor drivers" - -config X86_POWERNOW_K8 - tristate "AMD Opteron/Athlon64 PowerNow!" - select CPU_FREQ_TABLE - help - This adds the CPUFreq driver for mobile AMD Opteron/Athlon64 processors. - - To compile this driver as a module, choose M here: the - module will be called powernow-k8. - - For details, take a look at <file:Documentation/cpu-freq/>. - - If in doubt, say N. - -config X86_POWERNOW_K8_ACPI - bool - depends on X86_POWERNOW_K8 && ACPI_PROCESSOR - depends on !(X86_POWERNOW_K8 = y && ACPI_PROCESSOR = m) - default y - -config X86_SPEEDSTEP_CENTRINO - tristate "Intel Enhanced SpeedStep (deprecated)" - select CPU_FREQ_TABLE - depends on ACPI_PROCESSOR - help - This is deprecated and this functionality is now merged into - acpi_cpufreq (X86_ACPI_CPUFREQ). Use that driver instead of - speedstep_centrino. - This adds the CPUFreq driver for Enhanced SpeedStep enabled - mobile CPUs. This means Intel Pentium M (Centrino) CPUs - or 64bit enabled Intel Xeons. - - To compile this driver as a module, choose M here: the - module will be called speedstep-centrino. - - For details, take a look at <file:Documentation/cpu-freq/>. - - If in doubt, say N. - -config X86_ACPI_CPUFREQ - tristate "ACPI Processor P-States driver" - select CPU_FREQ_TABLE - depends on ACPI_PROCESSOR - help - This driver adds a CPUFreq driver which utilizes the ACPI - Processor Performance States. - This driver also supports Intel Enhanced Speedstep. - - To compile this driver as a module, choose M here: the - module will be called acpi-cpufreq. - - For details, take a look at <file:Documentation/cpu-freq/>. - - If in doubt, say N. - -comment "shared options" - -config X86_ACPI_CPUFREQ_PROC_INTF - bool "/proc/acpi/processor/../performance interface (deprecated)" - depends on PROC_FS - depends on X86_ACPI_CPUFREQ || X86_POWERNOW_K8_ACPI - help - This enables the deprecated /proc/acpi/processor/../performance - interface. While it is helpful for debugging, the generic, - cross-architecture cpufreq interfaces should be used. - - If in doubt, say N. - -config X86_P4_CLOCKMOD - tristate "Intel Pentium 4 clock modulation" - depends on EMBEDDED - select CPU_FREQ_TABLE - help - This adds the clock modulation driver for Intel Pentium 4 / XEON - processors. When enabled it will lower CPU temperature by skipping - clocks. - - This driver should be only used in exceptional - circumstances when very low power is needed because it causes severe - slowdowns and noticeable latencies. Normally Speedstep should be used - instead. - - To compile this driver as a module, choose M here: the - module will be called p4-clockmod. - - For details, take a look at <file:Documentation/cpu-freq/>. - - Unless you are absolutely sure say N. - - -config X86_SPEEDSTEP_LIB - tristate - default X86_P4_CLOCKMOD - -endif - -endmenu diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index f4548c93ccf..05c9936a16c 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -43,8 +43,6 @@ static struct class *cpuid_class; -#ifdef CONFIG_SMP - struct cpuid_command { u32 reg; u32 *data; @@ -62,25 +60,11 @@ static inline void do_cpuid(int cpu, u32 reg, u32 * data) { struct cpuid_command cmd; - preempt_disable(); - if (cpu == smp_processor_id()) { - cpuid(reg, &data[0], &data[1], &data[2], &data[3]); - } else { - cmd.reg = reg; - cmd.data = data; + cmd.reg = reg; + cmd.data = data; - smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1); - } - preempt_enable(); + smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1); } -#else /* ! CONFIG_SMP */ - -static inline void do_cpuid(int cpu, u32 reg, u32 * data) -{ - cpuid(reg, &data[0], &data[1], &data[2], &data[3]); -} - -#endif /* ! CONFIG_SMP */ static loff_t cpuid_seek(struct file *file, loff_t offset, int orig) { @@ -130,7 +114,7 @@ static ssize_t cpuid_read(struct file *file, char __user *buf, static int cpuid_open(struct inode *inode, struct file *file) { unsigned int cpu = iminor(file->f_path.dentry->d_inode); - struct cpuinfo_x86 *c = &(cpu_data)[cpu]; + struct cpuinfo_x86 *c = &cpu_data(cpu); if (cpu >= NR_CPUS || !cpu_online(cpu)) return -ENXIO; /* No such CPU */ @@ -150,32 +134,40 @@ static const struct file_operations cpuid_fops = { .open = cpuid_open, }; -static int cpuid_device_create(int i) +static __cpuinit int cpuid_device_create(int cpu) { - int err = 0; struct device *dev; - dev = device_create(cpuid_class, NULL, MKDEV(CPUID_MAJOR, i), "cpu%d",i); - if (IS_ERR(dev)) - err = PTR_ERR(dev); - return err; + dev = device_create(cpuid_class, NULL, MKDEV(CPUID_MAJOR, cpu), + "cpu%d", cpu); + return IS_ERR(dev) ? PTR_ERR(dev) : 0; +} + +static void cpuid_device_destroy(int cpu) +{ + device_destroy(cpuid_class, MKDEV(CPUID_MAJOR, cpu)); } -static int cpuid_class_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) +static int __cpuinit cpuid_class_cpu_callback(struct notifier_block *nfb, + unsigned long action, + void *hcpu) { unsigned int cpu = (unsigned long)hcpu; + int err = 0; switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - cpuid_device_create(cpu); + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + err = cpuid_device_create(cpu); break; + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: case CPU_DEAD_FROZEN: - device_destroy(cpuid_class, MKDEV(CPUID_MAJOR, cpu)); + cpuid_device_destroy(cpu); break; } - return NOTIFY_OK; + return err ? NOTIFY_BAD : NOTIFY_OK; } static struct notifier_block __cpuinitdata cpuid_class_cpu_notifier = @@ -212,7 +204,7 @@ static int __init cpuid_init(void) out_class: i = 0; for_each_online_cpu(i) { - device_destroy(cpuid_class, MKDEV(CPUID_MAJOR, i)); + cpuid_device_destroy(i); } class_destroy(cpuid_class); out_chrdev: @@ -226,7 +218,7 @@ static void __exit cpuid_exit(void) int cpu = 0; for_each_online_cpu(cpu) - device_destroy(cpuid_class, MKDEV(CPUID_MAJOR, cpu)); + cpuid_device_destroy(cpu); class_destroy(cpuid_class); unregister_chrdev(CPUID_MAJOR, "cpu/cpuid"); unregister_hotcpu_notifier(&cpuid_class_cpu_notifier); diff --git a/arch/x86/kernel/crash_32.c b/arch/x86/kernel/crash.c index 53589d1b1a0..8bb482ff091 100644 --- a/arch/x86/kernel/crash_32.c +++ b/arch/x86/kernel/crash.c @@ -1,5 +1,5 @@ /* - * Architecture specific (i386) functions for kexec based crash dumps. + * Architecture specific (i386/x86_64) functions for kexec based crash dumps. * * Created by: Hariprasad Nellitheertha (hari@in.ibm.com) * @@ -25,8 +25,11 @@ #include <linux/kdebug.h> #include <asm/smp.h> +#ifdef CONFIG_X86_32 #include <mach_ipi.h> - +#else +#include <asm/mach_apic.h> +#endif /* This keeps a track of which one is crashing cpu. */ static int crashing_cpu; @@ -38,7 +41,9 @@ static int crash_nmi_callback(struct notifier_block *self, unsigned long val, void *data) { struct pt_regs *regs; +#ifdef CONFIG_X86_32 struct pt_regs fixed_regs; +#endif int cpu; if (val != DIE_NMI_IPI) @@ -55,10 +60,12 @@ static int crash_nmi_callback(struct notifier_block *self, return NOTIFY_STOP; local_irq_disable(); +#ifdef CONFIG_X86_32 if (!user_mode_vm(regs)) { crash_fixup_ss_esp(&fixed_regs, regs); regs = &fixed_regs; } +#endif crash_save_cpu(regs, cpu); disable_local_APIC(); atomic_dec(&waiting_for_crash_ipi); diff --git a/arch/x86/kernel/crash_64.c b/arch/x86/kernel/crash_64.c deleted file mode 100644 index 13432a1ae90..00000000000 --- a/arch/x86/kernel/crash_64.c +++ /dev/null @@ -1,135 +0,0 @@ -/* - * Architecture specific (x86_64) functions for kexec based crash dumps. - * - * Created by: Hariprasad Nellitheertha (hari@in.ibm.com) - * - * Copyright (C) IBM Corporation, 2004. All rights reserved. - * - */ - -#include <linux/init.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/smp.h> -#include <linux/irq.h> -#include <linux/reboot.h> -#include <linux/kexec.h> -#include <linux/delay.h> -#include <linux/elf.h> -#include <linux/elfcore.h> -#include <linux/kdebug.h> - -#include <asm/processor.h> -#include <asm/hardirq.h> -#include <asm/nmi.h> -#include <asm/hw_irq.h> -#include <asm/mach_apic.h> - -/* This keeps a track of which one is crashing cpu. */ -static int crashing_cpu; - -#ifdef CONFIG_SMP -static atomic_t waiting_for_crash_ipi; - -static int crash_nmi_callback(struct notifier_block *self, - unsigned long val, void *data) -{ - struct pt_regs *regs; - int cpu; - - if (val != DIE_NMI_IPI) - return NOTIFY_OK; - - regs = ((struct die_args *)data)->regs; - cpu = raw_smp_processor_id(); - - /* - * Don't do anything if this handler is invoked on crashing cpu. - * Otherwise, system will completely hang. Crashing cpu can get - * an NMI if system was initially booted with nmi_watchdog parameter. - */ - if (cpu == crashing_cpu) - return NOTIFY_STOP; - local_irq_disable(); - - crash_save_cpu(regs, cpu); - disable_local_APIC(); - atomic_dec(&waiting_for_crash_ipi); - /* Assume hlt works */ - for(;;) - halt(); - - return 1; -} - -static void smp_send_nmi_allbutself(void) -{ - send_IPI_allbutself(NMI_VECTOR); -} - -/* - * This code is a best effort heuristic to get the - * other cpus to stop executing. So races with - * cpu hotplug shouldn't matter. - */ - -static struct notifier_block crash_nmi_nb = { - .notifier_call = crash_nmi_callback, -}; - -static void nmi_shootdown_cpus(void) -{ - unsigned long msecs; - - atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); - if (register_die_notifier(&crash_nmi_nb)) - return; /* return what? */ - - /* - * Ensure the new callback function is set before sending - * out the NMI - */ - wmb(); - - smp_send_nmi_allbutself(); - - msecs = 1000; /* Wait at most a second for the other cpus to stop */ - while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) { - mdelay(1); - msecs--; - } - /* Leave the nmi callback set */ - disable_local_APIC(); -} -#else -static void nmi_shootdown_cpus(void) -{ - /* There are no cpus to shootdown */ -} -#endif - -void machine_crash_shutdown(struct pt_regs *regs) -{ - /* - * This function is only called after the system - * has panicked or is otherwise in a critical state. - * The minimum amount of code to allow a kexec'd kernel - * to run successfully needs to happen here. - * - * In practice this means shooting down the other cpus in - * an SMP system. - */ - /* The kernel is broken so disable interrupts */ - local_irq_disable(); - - /* Make a note of crashing cpu. Will be used in NMI callback.*/ - crashing_cpu = smp_processor_id(); - nmi_shootdown_cpus(); - - if(cpu_has_apic) - disable_local_APIC(); - - disable_IO_APIC(); - - crash_save_cpu(regs, smp_processor_id()); -} diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c index 32e75d0731a..72d0c56c1b4 100644 --- a/arch/x86/kernel/crash_dump_32.c +++ b/arch/x86/kernel/crash_dump_32.c @@ -47,6 +47,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, if (!kdump_buf_page) { printk(KERN_WARNING "Kdump: Kdump buffer page not" " allocated\n"); + kunmap_atomic(vaddr, KM_PTE0); return -EFAULT; } copy_page(kdump_buf_page, vaddr); diff --git a/arch/x86/kernel/e820_32.c b/arch/x86/kernel/e820_32.c index 3c86b979a40..18f500d185a 100644 --- a/arch/x86/kernel/e820_32.c +++ b/arch/x86/kernel/e820_32.c @@ -51,6 +51,13 @@ struct resource code_resource = { .flags = IORESOURCE_BUSY | IORESOURCE_MEM }; +struct resource bss_resource = { + .name = "Kernel bss", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; + static struct resource system_rom_resource = { .name = "System ROM", .start = 0xf0000, @@ -254,7 +261,9 @@ static void __init probe_roms(void) * and also for regions reported as reserved by the e820. */ static void __init -legacy_init_iomem_resources(struct resource *code_resource, struct resource *data_resource) +legacy_init_iomem_resources(struct resource *code_resource, + struct resource *data_resource, + struct resource *bss_resource) { int i; @@ -287,8 +296,10 @@ legacy_init_iomem_resources(struct resource *code_resource, struct resource *dat */ request_resource(res, code_resource); request_resource(res, data_resource); + request_resource(res, bss_resource); #ifdef CONFIG_KEXEC - request_resource(res, &crashk_res); + if (crashk_res.start != crashk_res.end) + request_resource(res, &crashk_res); #endif } } @@ -306,9 +317,11 @@ static int __init request_standard_resources(void) printk("Setting up standard PCI resources\n"); if (efi_enabled) - efi_initialize_iomem_resources(&code_resource, &data_resource); + efi_initialize_iomem_resources(&code_resource, + &data_resource, &bss_resource); else - legacy_init_iomem_resources(&code_resource, &data_resource); + legacy_init_iomem_resources(&code_resource, + &data_resource, &bss_resource); /* EFI systems may still have VGA */ request_resource(&iomem_resource, &video_ram_resource); @@ -705,7 +718,7 @@ void __init e820_register_memory(void) int i; /* - * Search for the bigest gap in the low 32 bits of the e820 + * Search for the biggest gap in the low 32 bits of the e820 * memory space. */ last = 0x100000000ull; diff --git a/arch/x86/kernel/e820_64.c b/arch/x86/kernel/e820_64.c index 0f4d5e209e9..04698e0b056 100644 --- a/arch/x86/kernel/e820_64.c +++ b/arch/x86/kernel/e820_64.c @@ -24,7 +24,7 @@ #include <asm/page.h> #include <asm/e820.h> #include <asm/proto.h> -#include <asm/bootsetup.h> +#include <asm/setup.h> #include <asm/sections.h> struct e820map e820; @@ -47,7 +47,7 @@ unsigned long end_pfn_map; */ static unsigned long __initdata end_user_pfn = MAXMEM>>PAGE_SHIFT; -extern struct resource code_resource, data_resource; +extern struct resource code_resource, data_resource, bss_resource; /* Check for some hardcoded bad areas that early boot is not allowed to touch */ static inline int bad_addr(unsigned long *addrp, unsigned long size) @@ -68,10 +68,15 @@ static inline int bad_addr(unsigned long *addrp, unsigned long size) /* initrd */ #ifdef CONFIG_BLK_DEV_INITRD - if (LOADER_TYPE && INITRD_START && last >= INITRD_START && - addr < INITRD_START+INITRD_SIZE) { - *addrp = PAGE_ALIGN(INITRD_START + INITRD_SIZE); - return 1; + if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) { + unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; + unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; + unsigned long ramdisk_end = ramdisk_image+ramdisk_size; + + if (last >= ramdisk_image && addr < ramdisk_end) { + *addrp = PAGE_ALIGN(ramdisk_end); + return 1; + } } #endif /* kernel code */ @@ -220,8 +225,10 @@ void __init e820_reserve_resources(void) */ request_resource(res, &code_resource); request_resource(res, &data_resource); + request_resource(res, &bss_resource); #ifdef CONFIG_KEXEC - request_resource(res, &crashk_res); + if (crashk_res.start != crashk_res.end) + request_resource(res, &crashk_res); #endif } } @@ -594,8 +601,8 @@ void __init setup_memory_region(void) * Otherwise fake a memory map; one section from 0k->640k, * the next section from 1mb->appropriate_mem_k */ - sanitize_e820_map(E820_MAP, &E820_MAP_NR); - if (copy_e820_map(E820_MAP, E820_MAP_NR) < 0) + sanitize_e820_map(boot_params.e820_map, &boot_params.e820_entries); + if (copy_e820_map(boot_params.e820_map, boot_params.e820_entries) < 0) early_panic("Cannot find a valid memory map"); printk(KERN_INFO "BIOS-provided physical RAM map:\n"); e820_print_map("BIOS-e820"); @@ -723,3 +730,22 @@ __init void e820_setup_gap(void) printk(KERN_INFO "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n", pci_mem_start, gapstart, gapsize); } + +int __init arch_get_ram_range(int slot, u64 *addr, u64 *size) +{ + int i; + + if (slot < 0 || slot >= e820.nr_map) + return -1; + for (i = slot; i < e820.nr_map; i++) { + if (e820.map[i].type != E820_RAM) + continue; + break; + } + if (i == e820.nr_map || e820.map[i].addr > (max_pfn << PAGE_SHIFT)) + return -1; + *addr = e820.map[i].addr; + *size = min_t(u64, e820.map[i].size + e820.map[i].addr, + max_pfn << PAGE_SHIFT) - *addr; + return i + 1; +} diff --git a/arch/x86/kernel/early-quirks_64.c b/arch/x86/kernel/early-quirks.c index 13aa4fd728f..88bb83ec895 100644 --- a/arch/x86/kernel/early-quirks_64.c +++ b/arch/x86/kernel/early-quirks.c @@ -13,33 +13,41 @@ #include <linux/acpi.h> #include <linux/pci_ids.h> #include <asm/pci-direct.h> -#include <asm/proto.h> -#include <asm/iommu.h> #include <asm/dma.h> +#include <asm/io_apic.h> +#include <asm/apic.h> + +#ifdef CONFIG_GART_IOMMU +#include <asm/gart.h> +#endif static void __init via_bugs(void) { -#ifdef CONFIG_IOMMU +#ifdef CONFIG_GART_IOMMU if ((end_pfn > MAX_DMA32_PFN || force_iommu) && - !iommu_aperture_allowed) { + !gart_iommu_aperture_allowed) { printk(KERN_INFO - "Looks like a VIA chipset. Disabling IOMMU. Override with iommu=allowed\n"); - iommu_aperture_disabled = 1; + "Looks like a VIA chipset. Disabling IOMMU." + " Override with iommu=allowed\n"); + gart_iommu_aperture_disabled = 1; } #endif } #ifdef CONFIG_ACPI +#ifdef CONFIG_X86_IO_APIC static int __init nvidia_hpet_check(struct acpi_table_header *header) { return 0; } -#endif +#endif /* CONFIG_X86_IO_APIC */ +#endif /* CONFIG_ACPI */ static void __init nvidia_bugs(void) { #ifdef CONFIG_ACPI +#ifdef CONFIG_X86_IO_APIC /* * All timer overrides on Nvidia are * wrong unless HPET is enabled. @@ -59,17 +67,20 @@ static void __init nvidia_bugs(void) "try acpi_use_timer_override\n"); } #endif +#endif /* RED-PEN skip them on mptables too? */ } static void __init ati_bugs(void) { +#ifdef CONFIG_X86_IO_APIC if (timer_over_8254 == 1) { timer_over_8254 = 0; printk(KERN_INFO - "ATI board detected. Disabling timer routing over 8254.\n"); + "ATI board detected. Disabling timer routing over 8254.\n"); } +#endif } struct chipset { @@ -104,7 +115,7 @@ void __init early_quirks(void) if (class == 0xffffffff) break; - if ((class >> 16) != PCI_CLASS_BRIDGE_PCI) + if ((class >> 16) != PCI_CLASS_BRIDGE_PCI) continue; vendor = read_pci_config(num, slot, func, diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index fd9aff3f389..b7d6c23f287 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -6,15 +6,10 @@ #include <asm/io.h> #include <asm/processor.h> #include <asm/fcntl.h> +#include <asm/setup.h> #include <xen/hvc-console.h> /* Simple VGA output */ - -#ifdef __i386__ -#include <asm/setup.h> -#else -#include <asm/bootsetup.h> -#endif #define VGABASE (__ISA_IO_base + 0xb8000) static int max_ypos = 25, max_xpos = 80; @@ -234,10 +229,10 @@ static int __init setup_early_printk(char *buf) early_serial_init(buf); early_console = &early_serial_console; } else if (!strncmp(buf, "vga", 3) - && SCREEN_INFO.orig_video_isVGA == 1) { - max_xpos = SCREEN_INFO.orig_video_cols; - max_ypos = SCREEN_INFO.orig_video_lines; - current_ypos = SCREEN_INFO.orig_y; + && boot_params.screen_info.orig_video_isVGA == 1) { + max_xpos = boot_params.screen_info.orig_video_cols; + max_ypos = boot_params.screen_info.orig_video_lines; + current_ypos = boot_params.screen_info.orig_y; early_console = &early_vga_console; } else if (!strncmp(buf, "simnow", 6)) { simnow_init(buf + 6); diff --git a/arch/x86/kernel/efi_32.c b/arch/x86/kernel/efi_32.c index 2452c6fbe99..e2be78f4939 100644 --- a/arch/x86/kernel/efi_32.c +++ b/arch/x86/kernel/efi_32.c @@ -331,11 +331,13 @@ void __init efi_init(void) memset(&efi, 0, sizeof(efi) ); memset(&efi_phys, 0, sizeof(efi_phys)); - efi_phys.systab = EFI_SYSTAB; - memmap.phys_map = EFI_MEMMAP; - memmap.nr_map = EFI_MEMMAP_SIZE/EFI_MEMDESC_SIZE; - memmap.desc_version = EFI_MEMDESC_VERSION; - memmap.desc_size = EFI_MEMDESC_SIZE; + efi_phys.systab = + (efi_system_table_t *)boot_params.efi_info.efi_systab; + memmap.phys_map = (void *)boot_params.efi_info.efi_memmap; + memmap.nr_map = boot_params.efi_info.efi_memmap_size/ + boot_params.efi_info.efi_memdesc_size; + memmap.desc_version = boot_params.efi_info.efi_memdesc_version; + memmap.desc_size = boot_params.efi_info.efi_memdesc_size; efi.systab = (efi_system_table_t *) boot_ioremap((unsigned long) efi_phys.systab, @@ -446,7 +448,8 @@ void __init efi_init(void) printk(KERN_ERR PFX "Could not map the runtime service table!\n"); /* Map the EFI memory map for use until paging_init() */ - memmap.map = boot_ioremap((unsigned long) EFI_MEMMAP, EFI_MEMMAP_SIZE); + memmap.map = boot_ioremap(boot_params.efi_info.efi_memmap, + boot_params.efi_info.efi_memmap_size); if (memmap.map == NULL) printk(KERN_ERR PFX "Could not map the EFI memory map!\n"); @@ -600,7 +603,8 @@ void __init efi_enter_virtual_mode(void) void __init efi_initialize_iomem_resources(struct resource *code_resource, - struct resource *data_resource) + struct resource *data_resource, + struct resource *bss_resource) { struct resource *res; efi_memory_desc_t *md; @@ -672,6 +676,7 @@ efi_initialize_iomem_resources(struct resource *code_resource, if (md->type == EFI_CONVENTIONAL_MEMORY) { request_resource(res, code_resource); request_resource(res, data_resource); + request_resource(res, bss_resource); #ifdef CONFIG_KEXEC request_resource(res, &crashk_res); #endif diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 8099fea0a72..dc7f938e501 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -437,7 +437,7 @@ ldt_ss: * is still available to implement the setting of the high * 16-bits in the INTERRUPT_RETURN paravirt-op. */ - cmpl $0, paravirt_ops+PARAVIRT_enabled + cmpl $0, pv_info+PARAVIRT_enabled jne restore_nocheck #endif diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index f1cacd4897f..3a058bb1640 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -988,7 +988,7 @@ child_rip: movq %rsi, %rdi call *%rax # exit - xorl %edi, %edi + mov %eax, %edi call do_exit CFI_ENDPROC ENDPROC(child_rip) diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c index 47496a40e84..ce703e21c91 100644 --- a/arch/x86/kernel/genapic_64.c +++ b/arch/x86/kernel/genapic_64.c @@ -24,12 +24,19 @@ #include <acpi/acpi_bus.h> #endif -/* which logical CPU number maps to which CPU (physical APIC ID) */ -u8 x86_cpu_to_apicid[NR_CPUS] __read_mostly +/* + * which logical CPU number maps to which CPU (physical APIC ID) + * + * The following static array is used during kernel startup + * and the x86_cpu_to_apicid_ptr contains the address of the + * array during this time. Is it zeroed when the per_cpu + * data area is removed. + */ +u8 x86_cpu_to_apicid_init[NR_CPUS] __initdata = { [0 ... NR_CPUS-1] = BAD_APICID }; -EXPORT_SYMBOL(x86_cpu_to_apicid); - -u8 x86_cpu_to_log_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; +void *x86_cpu_to_apicid_ptr; +DEFINE_PER_CPU(u8, x86_cpu_to_apicid) = BAD_APICID; +EXPORT_PER_CPU_SYMBOL(x86_cpu_to_apicid); struct genapic __read_mostly *genapic = &apic_flat; diff --git a/arch/x86/kernel/genapic_flat_64.c b/arch/x86/kernel/genapic_flat_64.c index ecb01eefdd2..07352b74bda 100644 --- a/arch/x86/kernel/genapic_flat_64.c +++ b/arch/x86/kernel/genapic_flat_64.c @@ -52,7 +52,6 @@ static void flat_init_apic_ldr(void) num = smp_processor_id(); id = 1UL << num; - x86_cpu_to_log_apicid[num] = id; apic_write(APIC_DFR, APIC_DFR_FLAT); val = apic_read(APIC_LDR) & ~APIC_LDR_MASK; val |= SET_APIC_LOGICAL_ID(id); @@ -173,7 +172,7 @@ static unsigned int physflat_cpu_mask_to_apicid(cpumask_t cpumask) */ cpu = first_cpu(cpumask); if ((unsigned)cpu < NR_CPUS) - return x86_cpu_to_apicid[cpu]; + return per_cpu(x86_cpu_to_apicid, cpu); else return BAD_APICID; } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 8561f626eda..6b3469311e4 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -14,7 +14,6 @@ #include <asm/processor.h> #include <asm/proto.h> #include <asm/smp.h> -#include <asm/bootsetup.h> #include <asm/setup.h> #include <asm/desc.h> #include <asm/pgtable.h> @@ -36,26 +35,15 @@ static void __init clear_bss(void) (unsigned long) __bss_stop - (unsigned long) __bss_start); } -#define NEW_CL_POINTER 0x228 /* Relative to real mode data */ -#define OLD_CL_MAGIC_ADDR 0x20 -#define OLD_CL_MAGIC 0xA33F -#define OLD_CL_OFFSET 0x22 - static void __init copy_bootdata(char *real_mode_data) { - unsigned long new_data; char * command_line; - memcpy(x86_boot_params, real_mode_data, BOOT_PARAM_SIZE); - new_data = *(u32 *) (x86_boot_params + NEW_CL_POINTER); - if (!new_data) { - if (OLD_CL_MAGIC != *(u16 *)(real_mode_data + OLD_CL_MAGIC_ADDR)) { - return; - } - new_data = __pa(real_mode_data) + *(u16 *)(real_mode_data + OLD_CL_OFFSET); + memcpy(&boot_params, real_mode_data, sizeof boot_params); + if (boot_params.hdr.cmd_line_ptr) { + command_line = __va(boot_params.hdr.cmd_line_ptr); + memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); } - command_line = __va(new_data); - memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE); } void __init x86_64_start_kernel(char * real_mode_data) @@ -70,7 +58,7 @@ void __init x86_64_start_kernel(char * real_mode_data) for (i = 0; i < IDT_ENTRIES; i++) set_intr_gate(i, early_idt_handler); - asm volatile("lidt %0" :: "m" (idt_descr)); + load_idt((const struct desc_ptr *)&idt_descr); early_printk("Kernel alive\n"); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 9150ca9b5f8..374b7ece896 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -51,6 +51,15 @@ */ LOW_PAGES = 1<<(32-PAGE_SHIFT_asm) +/* + * To preserve the DMA pool in PAGEALLOC kernels, we'll allocate + * pagetables from above the 16MB DMA limit, so we'll have to set + * up pagetables 16MB more (worst-case): + */ +#ifdef CONFIG_DEBUG_PAGEALLOC +LOW_PAGES = LOW_PAGES + 0x1000000 +#endif + #if PTRS_PER_PMD > 1 PAGE_TABLE_SIZE = (LOW_PAGES / PTRS_PER_PMD) + PTRS_PER_PGD #else @@ -70,22 +79,30 @@ INIT_MAP_BEYOND_END = BOOTBITMAP_SIZE + (PAGE_TABLE_SIZE + ALLOCATOR_SLOP)*PAGE_ */ .section .text.head,"ax",@progbits ENTRY(startup_32) + /* check to see if KEEP_SEGMENTS flag is meaningful */ + cmpw $0x207, BP_version(%esi) + jb 1f + + /* test KEEP_SEGMENTS flag to see if the bootloader is asking + us to not reload segments */ + testb $(1<<6), BP_loadflags(%esi) + jnz 2f /* * Set segments to known values. */ - cld - lgdt boot_gdt_descr - __PAGE_OFFSET +1: lgdt boot_gdt_descr - __PAGE_OFFSET movl $(__BOOT_DS),%eax movl %eax,%ds movl %eax,%es movl %eax,%fs movl %eax,%gs +2: /* * Clear BSS first so that there are no surprises... - * No need to cld as DF is already clear from cld above... */ + cld xorl %eax,%eax movl $__bss_start - __PAGE_OFFSET,%edi movl $__bss_stop - __PAGE_OFFSET,%ecx @@ -107,18 +124,42 @@ ENTRY(startup_32) movsl movl boot_params - __PAGE_OFFSET + NEW_CL_POINTER,%esi andl %esi,%esi - jnz 2f # New command line protocol - cmpw $(OLD_CL_MAGIC),OLD_CL_MAGIC_ADDR - jne 1f - movzwl OLD_CL_OFFSET,%esi - addl $(OLD_CL_BASE_ADDR),%esi -2: + jz 1f # No comand line movl $(boot_command_line - __PAGE_OFFSET),%edi movl $(COMMAND_LINE_SIZE/4),%ecx rep movsl 1: +#ifdef CONFIG_PARAVIRT + cmpw $0x207, (boot_params + BP_version - __PAGE_OFFSET) + jb default_entry + + /* Paravirt-compatible boot parameters. Look to see what architecture + we're booting under. */ + movl (boot_params + BP_hardware_subarch - __PAGE_OFFSET), %eax + cmpl $num_subarch_entries, %eax + jae bad_subarch + + movl subarch_entries - __PAGE_OFFSET(,%eax,4), %eax + subl $__PAGE_OFFSET, %eax + jmp *%eax + +bad_subarch: +WEAK(lguest_entry) +WEAK(xen_entry) + /* Unknown implementation; there's really + nothing we can do at this point. */ + ud2a +.data +subarch_entries: + .long default_entry /* normal x86/PC */ + .long lguest_entry /* lguest hypervisor */ + .long xen_entry /* Xen hypervisor */ +num_subarch_entries = (. - subarch_entries) / 4 +.previous +#endif /* CONFIG_PARAVIRT */ + /* * Initialize page tables. This creates a PDE and a set of page * tables, which are located immediately beyond _end. The variable @@ -131,6 +172,7 @@ ENTRY(startup_32) */ page_pde_offset = (__PAGE_OFFSET >> 20); +default_entry: movl $(pg0 - __PAGE_OFFSET), %edi movl $(swapper_pg_dir - __PAGE_OFFSET), %edx movl $0x007, %eax /* 0x007 = PRESENT+RW+USER */ @@ -443,6 +485,7 @@ early_page_fault: early_fault: cld #ifdef CONFIG_PRINTK + pusha movl $(__KERNEL_DS),%eax movl %eax,%ds movl %eax,%es @@ -534,8 +577,15 @@ int_msg: .asciz "Unknown interrupt or fault at EIP %p %p %p\n" fault_msg: - .ascii "Int %d: CR2 %p err %p EIP %p CS %p flags %p\n" - .asciz "Stack: %p %p %p %p %p %p %p %p\n" + .ascii \ +/* fault info: */ "BUG: Int %d: CR2 %p\n" \ +/* pusha regs: */ " EDI %p ESI %p EBP %p ESP %p\n" \ + " EBX %p EDX %p ECX %p EAX %p\n" \ +/* fault frame: */ " err %p EIP %p CS %p flg %p\n" \ + \ + "Stack: %p %p %p %p %p %p %p %p\n" \ + " %p %p %p %p %p %p %p %p\n" \ + " %p %p %p %p %p %p %p %p\n" #include "../../x86/xen/xen-head.S" diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index f8367074da0..53303f2e547 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -69,12 +69,15 @@ static inline void hpet_clear_mapping(void) * HPET command line enable / disable */ static int boot_hpet_disable; +int hpet_force_user; static int __init hpet_setup(char* str) { if (str) { if (!strncmp("disable", str, 7)) boot_hpet_disable = 1; + if (!strncmp("force", str, 5)) + hpet_force_user = 1; } return 1; } @@ -350,7 +353,7 @@ static int hpet_clocksource_register(void) * * hpet period is in femto seconds per cycle * so we need to convert this to ns/cyc units - * aproximated by mult/2^shift + * approximated by mult/2^shift * * fsec/cyc * 1nsec/1000000fsec = nsec/cyc = mult/2^shift * fsec/cyc * 1ns/1000000fsec * 2^shift = mult diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c index e3d4b73bfdb..edd39ccf139 100644 --- a/arch/x86/kernel/i386_ksyms_32.c +++ b/arch/x86/kernel/i386_ksyms_32.c @@ -1,4 +1,5 @@ #include <linux/module.h> +#include <asm/semaphore.h> #include <asm/checksum.h> #include <asm/desc.h> diff --git a/arch/x86/kernel/i387_64.c b/arch/x86/kernel/i387_64.c index 56c1f114710..bfaff28fb13 100644 --- a/arch/x86/kernel/i387_64.c +++ b/arch/x86/kernel/i387_64.c @@ -92,13 +92,14 @@ int save_i387(struct _fpstate __user *buf) 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.i387.fxsave, + } else { + if (__copy_to_user(buf, &tsk->thread.i387.fxsave, sizeof(struct i387_fxsave_struct))) return -1; - } - return 1; + } + return 1; } /* diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 5cc8841ca2c..a42c8074532 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -86,7 +86,7 @@ static int pit_next_event(unsigned long delta, struct clock_event_device *evt) * On UP the PIT can serve all of the possible timer functions. On SMP systems * it can be solely used for the global tick. * - * The profiling and update capabilites are switched off once the local apic is + * The profiling and update capabilities are switched off once the local apic is * registered. This mechanism replaces the previous #ifdef LOCAL_APIC - * !using_apic_timer decisions in do_timer_interrupt_hook() */ diff --git a/arch/x86/kernel/i8259_32.c b/arch/x86/kernel/i8259_32.c index 679bb33acbf..f634fc715c9 100644 --- a/arch/x86/kernel/i8259_32.c +++ b/arch/x86/kernel/i8259_32.c @@ -349,7 +349,11 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id) * New motherboards sometimes make IRQ 13 be a PCI interrupt, * so allow interrupt sharing. */ -static struct irqaction fpu_irq = { math_error_irq, 0, CPU_MASK_NONE, "fpu", NULL, NULL }; +static struct irqaction fpu_irq = { + .handler = math_error_irq, + .mask = CPU_MASK_NONE, + .name = "fpu", +}; void __init init_ISA_irqs (void) { @@ -399,7 +403,8 @@ void __init native_init_IRQ(void) int vector = FIRST_EXTERNAL_VECTOR + i; if (i >= NR_IRQS) break; - if (vector != SYSCALL_VECTOR) + /* SYSCALL_VECTOR was reserved in trap_init. */ + if (!test_bit(vector, used_vectors)) set_intr_gate(vector, interrupt[i]); } diff --git a/arch/x86/kernel/i8259_64.c b/arch/x86/kernel/i8259_64.c index eb72976cc13..3f27ea0b981 100644 --- a/arch/x86/kernel/i8259_64.c +++ b/arch/x86/kernel/i8259_64.c @@ -395,7 +395,11 @@ device_initcall(i8259A_init_sysfs); * IRQ2 is cascade interrupt to second interrupt controller */ -static struct irqaction irq2 = { no_action, 0, CPU_MASK_NONE, "cascade", NULL, NULL}; +static struct irqaction irq2 = { + .handler = no_action, + .mask = CPU_MASK_NONE, + .name = "cascade", +}; DEFINE_PER_CPU(vector_irq_t, vector_irq) = { [0 ... IRQ0_VECTOR - 1] = -1, [IRQ0_VECTOR] = 0, diff --git a/arch/x86/kernel/init_task_32.c b/arch/x86/kernel/init_task.c index d26fc063a76..468c9c43784 100644 --- a/arch/x86/kernel/init_task_32.c +++ b/arch/x86/kernel/init_task.c @@ -15,7 +15,6 @@ static struct files_struct init_files = INIT_FILES; static struct signal_struct init_signals = INIT_SIGNALS(init_signals); static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); struct mm_struct init_mm = INIT_MM(init_mm); - EXPORT_SYMBOL(init_mm); /* @@ -25,7 +24,7 @@ EXPORT_SYMBOL(init_mm); * way process stacks are handled. This is done by having a special * "init_task" linker map entry.. */ -union thread_union init_thread_union +union thread_union init_thread_union __attribute__((__section__(".data.init_task"))) = { INIT_THREAD_INFO(init_task) }; @@ -35,12 +34,14 @@ union thread_union init_thread_union * All other task structs will be allocated on slabs in fork.c */ struct task_struct init_task = INIT_TASK(init_task); - EXPORT_SYMBOL(init_task); /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, - * no more per-task TSS's. - */ + * no more per-task TSS's. The TSS size is kept cacheline-aligned + * so they are allowed to end up in the .data.cacheline_aligned + * section. Since TSS's are completely CPU-local, we want them + * on exact cacheline boundaries, to eliminate cacheline ping-pong. + */ DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS; diff --git a/arch/x86/kernel/init_task_64.c b/arch/x86/kernel/init_task_64.c deleted file mode 100644 index 4ff33d4f855..00000000000 --- a/arch/x86/kernel/init_task_64.c +++ /dev/null @@ -1,54 +0,0 @@ -#include <linux/mm.h> -#include <linux/module.h> -#include <linux/sched.h> -#include <linux/init.h> -#include <linux/init_task.h> -#include <linux/fs.h> -#include <linux/mqueue.h> - -#include <asm/uaccess.h> -#include <asm/pgtable.h> -#include <asm/desc.h> - -static struct fs_struct init_fs = INIT_FS; -static struct files_struct init_files = INIT_FILES; -static struct signal_struct init_signals = INIT_SIGNALS(init_signals); -static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); -struct mm_struct init_mm = INIT_MM(init_mm); - -EXPORT_SYMBOL(init_mm); - -/* - * Initial task structure. - * - * We need to make sure that this is 8192-byte aligned due to the - * way process stacks are handled. This is done by having a special - * "init_task" linker map entry.. - */ -union thread_union init_thread_union - __attribute__((__section__(".data.init_task"))) = - { INIT_THREAD_INFO(init_task) }; - -/* - * Initial task structure. - * - * All other task structs will be allocated on slabs in fork.c - */ -struct task_struct init_task = INIT_TASK(init_task); - -EXPORT_SYMBOL(init_task); -/* - * per-CPU TSS segments. Threads are completely 'soft' on Linux, - * no more per-task TSS's. The TSS size is kept cacheline-aligned - * so they are allowed to end up in the .data.cacheline_aligned - * section. Since TSS's are completely CPU-local, we want them - * on exact cacheline boundaries, to eliminate cacheline ping-pong. - */ -DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS; - -/* Copies of the original ist values from the tss are only accessed during - * debugging, no special alignment required. - */ -DEFINE_PER_CPU(struct orig_ist, orig_ist); - -#define ALIGN_TO_4K __attribute__((section(".data.init_task"))) diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c index e2f4a1c6854..f35c6eb33da 100644 --- a/arch/x86/kernel/io_apic_32.c +++ b/arch/x86/kernel/io_apic_32.c @@ -378,7 +378,7 @@ static struct irq_cpu_info { #define IRQ_ALLOWED(cpu, allowed_mask) cpu_isset(cpu, allowed_mask) -#define CPU_TO_PACKAGEINDEX(i) (first_cpu(cpu_sibling_map[i])) +#define CPU_TO_PACKAGEINDEX(i) (first_cpu(per_cpu(cpu_sibling_map, i))) static cpumask_t balance_irq_affinity[NR_IRQS] = { [0 ... NR_IRQS-1] = CPU_MASK_ALL @@ -584,7 +584,7 @@ tryanotherirq: imbalance = move_this_load; - /* For physical_balance case, we accumlated both load + /* For physical_balance case, we accumulated both load * values in the one of the siblings cpu_irq[], * to use the same code for physical and logical processors * as much as possible. @@ -598,7 +598,7 @@ tryanotherirq: * (A+B)/2 vs B */ load = CPU_IRQ(min_loaded) >> 1; - for_each_cpu_mask(j, cpu_sibling_map[min_loaded]) { + for_each_cpu_mask(j, per_cpu(cpu_sibling_map, min_loaded)) { if (load > CPU_IRQ(j)) { /* This won't change cpu_sibling_map[min_loaded] */ load = CPU_IRQ(j); @@ -1198,7 +1198,7 @@ static u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 } static int __assign_irq_vector(int irq) { static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0; - int vector, offset, i; + int vector, offset; BUG_ON((unsigned)irq >= NR_IRQ_VECTORS); @@ -1215,11 +1215,8 @@ next: } if (vector == current_vector) return -ENOSPC; - if (vector == SYSCALL_VECTOR) + if (test_and_set_bit(vector, used_vectors)) goto next; - for (i = 0; i < NR_IRQ_VECTORS; i++) - if (irq_vector[i] == vector) - goto next; current_vector = vector; current_offset = offset; @@ -1296,6 +1293,11 @@ static void __init setup_IO_APIC_irqs(void) continue; } + if (!first_notcon) { + apic_printk(APIC_VERBOSE, " not connected.\n"); + first_notcon = 1; + } + entry.trigger = irq_trigger(idx); entry.polarity = irq_polarity(idx); @@ -2290,6 +2292,12 @@ static inline void __init check_timer(void) void __init setup_IO_APIC(void) { + int i; + + /* Reserve all the system vectors. */ + for (i = FIRST_SYSTEM_VECTOR; i < NR_VECTORS; i++) + set_bit(i, used_vectors); + enable_IO_APIC(); if (acpi_ioapic) @@ -2467,7 +2475,7 @@ void destroy_irq(unsigned int irq) } /* - * MSI mesage composition + * MSI message composition */ #ifdef CONFIG_PCI_MSI static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg) diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c index 966fa106249..953328b55a3 100644 --- a/arch/x86/kernel/io_apic_64.c +++ b/arch/x86/kernel/io_apic_64.c @@ -31,6 +31,7 @@ #include <linux/sysdev.h> #include <linux/msi.h> #include <linux/htirq.h> +#include <linux/dmar.h> #ifdef CONFIG_ACPI #include <acpi/acpi_bus.h> #endif @@ -875,6 +876,10 @@ static void __init setup_IO_APIC_irqs(void) apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mpc_apicid, pin); continue; } + if (!first_notcon) { + apic_printk(APIC_VERBOSE, " not connected.\n"); + first_notcon = 1; + } irq = pin_2_irq(idx, apic, pin); add_pin_to_irq(irq, apic, pin); @@ -885,7 +890,7 @@ static void __init setup_IO_APIC_irqs(void) } if (!first_notcon) - apic_printk(APIC_VERBOSE," not connected.\n"); + apic_printk(APIC_VERBOSE, " not connected.\n"); } /* @@ -1766,7 +1771,7 @@ __setup("no_timer_check", notimercheck); /* * - * IRQ's that are handled by the PIC in the MPS IOAPIC case. + * IRQs that are handled by the PIC in the MPS IOAPIC case. * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ. * Linux doesn't really care, as it's not actually used * for any interrupt handling anyway. @@ -1845,7 +1850,7 @@ static struct sysdev_class ioapic_sysdev_class = { static int __init ioapic_init_sysfs(void) { struct sys_device * dev; - int i, size, error = 0; + int i, size, error; error = sysdev_class_register(&ioapic_sysdev_class); if (error) @@ -1854,12 +1859,11 @@ static int __init ioapic_init_sysfs(void) for (i = 0; i < nr_ioapics; i++ ) { size = sizeof(struct sys_device) + nr_ioapic_registers[i] * sizeof(struct IO_APIC_route_entry); - mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL); + mp_ioapic_data[i] = kzalloc(size, GFP_KERNEL); if (!mp_ioapic_data[i]) { printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); continue; } - memset(mp_ioapic_data[i], 0, size); dev = &mp_ioapic_data[i]->dev; dev->id = i; dev->cls = &ioapic_sysdev_class; @@ -1918,7 +1922,7 @@ void destroy_irq(unsigned int irq) } /* - * MSI mesage composition + * MSI message composition */ #ifdef CONFIG_PCI_MSI static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg) @@ -2028,8 +2032,64 @@ void arch_teardown_msi_irq(unsigned int irq) destroy_irq(irq); } -#endif /* CONFIG_PCI_MSI */ +#ifdef CONFIG_DMAR +#ifdef CONFIG_SMP +static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask) +{ + struct irq_cfg *cfg = irq_cfg + irq; + struct msi_msg msg; + unsigned int dest; + cpumask_t tmp; + cpus_and(tmp, mask, cpu_online_map); + if (cpus_empty(tmp)) + return; + + if (assign_irq_vector(irq, mask)) + return; + + cpus_and(tmp, cfg->domain, mask); + dest = cpu_mask_to_apicid(tmp); + + dmar_msi_read(irq, &msg); + + msg.data &= ~MSI_DATA_VECTOR_MASK; + msg.data |= MSI_DATA_VECTOR(cfg->vector); + msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; + msg.address_lo |= MSI_ADDR_DEST_ID(dest); + + dmar_msi_write(irq, &msg); + irq_desc[irq].affinity = mask; +} +#endif /* CONFIG_SMP */ + +struct irq_chip dmar_msi_type = { + .name = "DMAR_MSI", + .unmask = dmar_msi_unmask, + .mask = dmar_msi_mask, + .ack = ack_apic_edge, +#ifdef CONFIG_SMP + .set_affinity = dmar_msi_set_affinity, +#endif + .retrigger = ioapic_retrigger_irq, +}; + +int arch_setup_dmar_msi(unsigned int irq) +{ + int ret; + struct msi_msg msg; + + ret = msi_compose_msg(NULL, irq, &msg); + if (ret < 0) + return ret; + dmar_msi_write(irq, &msg); + set_irq_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq, + "edge"); + return 0; +} +#endif + +#endif /* CONFIG_PCI_MSI */ /* * Hypertransport interrupt support */ diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index e173b763f14..d3fde94f734 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -255,9 +255,17 @@ int show_interrupts(struct seq_file *p, void *v) } if (i < NR_IRQS) { + unsigned any_count = 0; + spin_lock_irqsave(&irq_desc[i].lock, flags); +#ifndef CONFIG_SMP + any_count = kstat_irqs(i); +#else + for_each_online_cpu(j) + any_count |= kstat_cpu(j).irqs[i]; +#endif action = irq_desc[i].action; - if (!action) + if (!action && !any_count) goto skip; seq_printf(p, "%3d: ",i); #ifndef CONFIG_SMP @@ -268,10 +276,12 @@ int show_interrupts(struct seq_file *p, void *v) #endif seq_printf(p, " %8s", irq_desc[i].chip->name); seq_printf(p, "-%-8s", irq_desc[i].name); - seq_printf(p, " %s", action->name); - for (action=action->next; action; action = action->next) - seq_printf(p, ", %s", action->name); + if (action) { + seq_printf(p, " %s", action->name); + while ((action = action->next) != NULL) + seq_printf(p, ", %s", action->name); + } seq_putc(p, '\n'); skip: @@ -280,14 +290,41 @@ skip: seq_printf(p, "NMI: "); for_each_online_cpu(j) seq_printf(p, "%10u ", nmi_count(j)); - seq_putc(p, '\n'); + seq_printf(p, " Non-maskable interrupts\n"); #ifdef CONFIG_X86_LOCAL_APIC seq_printf(p, "LOC: "); for_each_online_cpu(j) seq_printf(p, "%10u ", per_cpu(irq_stat,j).apic_timer_irqs); - seq_putc(p, '\n'); + seq_printf(p, " Local timer interrupts\n"); #endif +#ifdef CONFIG_SMP + seq_printf(p, "RES: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + per_cpu(irq_stat,j).irq_resched_count); + seq_printf(p, " Rescheduling interrupts\n"); + seq_printf(p, "CAL: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + per_cpu(irq_stat,j).irq_call_count); + seq_printf(p, " function call interrupts\n"); + seq_printf(p, "TLB: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + per_cpu(irq_stat,j).irq_tlb_count); + seq_printf(p, " TLB shootdowns\n"); +#endif + seq_printf(p, "TRM: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + per_cpu(irq_stat,j).irq_thermal_count); + seq_printf(p, " Thermal event interrupts\n"); + seq_printf(p, "SPU: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + per_cpu(irq_stat,j).irq_spurious_count); + seq_printf(p, " Spurious interrupts\n"); seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count)); diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 865669efc54..6b5c730d67b 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -62,9 +62,17 @@ int show_interrupts(struct seq_file *p, void *v) } if (i < NR_IRQS) { + unsigned any_count = 0; + spin_lock_irqsave(&irq_desc[i].lock, flags); +#ifndef CONFIG_SMP + any_count = kstat_irqs(i); +#else + for_each_online_cpu(j) + any_count |= kstat_cpu(j).irqs[i]; +#endif action = irq_desc[i].action; - if (!action) + if (!action && !any_count) goto skip; seq_printf(p, "%3d: ",i); #ifndef CONFIG_SMP @@ -76,9 +84,11 @@ int show_interrupts(struct seq_file *p, void *v) seq_printf(p, " %8s", irq_desc[i].chip->name); seq_printf(p, "-%-8s", irq_desc[i].name); - seq_printf(p, " %s", action->name); - for (action=action->next; action; action = action->next) - seq_printf(p, ", %s", action->name); + if (action) { + seq_printf(p, " %s", action->name); + while ((action = action->next) != NULL) + seq_printf(p, ", %s", action->name); + } seq_putc(p, '\n'); skip: spin_unlock_irqrestore(&irq_desc[i].lock, flags); @@ -86,11 +96,37 @@ skip: seq_printf(p, "NMI: "); for_each_online_cpu(j) seq_printf(p, "%10u ", cpu_pda(j)->__nmi_count); - seq_putc(p, '\n'); + seq_printf(p, " Non-maskable interrupts\n"); seq_printf(p, "LOC: "); for_each_online_cpu(j) seq_printf(p, "%10u ", cpu_pda(j)->apic_timer_irqs); - seq_putc(p, '\n'); + seq_printf(p, " Local timer interrupts\n"); +#ifdef CONFIG_SMP + seq_printf(p, "RES: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", cpu_pda(j)->irq_resched_count); + seq_printf(p, " Rescheduling interrupts\n"); + seq_printf(p, "CAL: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", cpu_pda(j)->irq_call_count); + seq_printf(p, " function call interrupts\n"); + seq_printf(p, "TLB: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", cpu_pda(j)->irq_tlb_count); + seq_printf(p, " TLB shootdowns\n"); +#endif + seq_printf(p, "TRM: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", cpu_pda(j)->irq_thermal_count); + seq_printf(p, " Thermal event interrupts\n"); + seq_printf(p, "THR: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", cpu_pda(j)->irq_threshold_count); + seq_printf(p, " Threshold APIC interrupts\n"); + seq_printf(p, "SPU: "); + for_each_online_cpu(j) + seq_printf(p, "%10u ", cpu_pda(j)->irq_spurious_count); + seq_printf(p, " Spurious interrupts\n"); seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); } return 0; diff --git a/arch/x86/kernel/kprobes_32.c b/arch/x86/kernel/kprobes_32.c index e7d0d3c2ef6..d87a523070d 100644 --- a/arch/x86/kernel/kprobes_32.c +++ b/arch/x86/kernel/kprobes_32.c @@ -41,6 +41,13 @@ void jprobe_return_end(void); DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); +struct kretprobe_blackpoint kretprobe_blacklist[] = { + {"__switch_to", }, /* This function switches only current task, but + doesn't switch kernel stack.*/ + {NULL, NULL} /* Terminator */ +}; +const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); + /* insert a jmp code */ static __always_inline void set_jmp_op(void *from, void *to) { @@ -557,12 +564,7 @@ static int __kprobes post_kprobe_handler(struct pt_regs *regs) resume_execution(cur, regs, kcb); regs->eflags |= kcb->kprobe_saved_eflags; -#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT - if (raw_irqs_disabled_flags(regs->eflags)) - trace_hardirqs_off(); - else - trace_hardirqs_on(); -#endif + trace_hardirqs_fixup_flags(regs->eflags); /*Restore back the original saved kprobes variables and continue. */ if (kcb->kprobe_status == KPROBE_REENTER) { @@ -584,7 +586,7 @@ out: return 1; } -static int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) +int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); @@ -666,7 +668,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, ret = NOTIFY_STOP; break; case DIE_GPF: - case DIE_PAGE_FAULT: /* kprobe_running() needs smp_processor_id() */ preempt_disable(); if (kprobe_running() && diff --git a/arch/x86/kernel/kprobes_64.c b/arch/x86/kernel/kprobes_64.c index 62e28e52d78..3db3611933d 100644 --- a/arch/x86/kernel/kprobes_64.c +++ b/arch/x86/kernel/kprobes_64.c @@ -48,6 +48,13 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p); DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); +struct kretprobe_blackpoint kretprobe_blacklist[] = { + {"__switch_to", }, /* This function switches only current task, but + doesn't switch kernel stack.*/ + {NULL, NULL} /* Terminator */ +}; +const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); + /* * returns non-zero if opcode modifies the interrupt flag. */ @@ -544,12 +551,7 @@ int __kprobes post_kprobe_handler(struct pt_regs *regs) resume_execution(cur, regs, kcb); regs->eflags |= kcb->kprobe_saved_rflags; -#ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT - if (raw_irqs_disabled_flags(regs->eflags)) - trace_hardirqs_off(); - else - trace_hardirqs_on(); -#endif + trace_hardirqs_fixup_flags(regs->eflags); /* Restore the original saved kprobes variables and continue. */ if (kcb->kprobe_status == KPROBE_REENTER) { @@ -657,7 +659,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, ret = NOTIFY_STOP; break; case DIE_GPF: - case DIE_PAGE_FAULT: /* kprobe_running() needs smp_processor_id() */ preempt_disable(); if (kprobe_running() && diff --git a/arch/x86/kernel/ldt_32.c b/arch/x86/kernel/ldt_32.c index a8b18421863..9ff90a27c45 100644 --- a/arch/x86/kernel/ldt_32.c +++ b/arch/x86/kernel/ldt_32.c @@ -92,13 +92,13 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) struct mm_struct * old_mm; int retval = 0; - init_MUTEX(&mm->context.sem); + mutex_init(&mm->context.lock); mm->context.size = 0; old_mm = current->mm; if (old_mm && old_mm->context.size > 0) { - down(&old_mm->context.sem); + mutex_lock(&old_mm->context.lock); retval = copy_ldt(&mm->context, &old_mm->context); - up(&old_mm->context.sem); + mutex_unlock(&old_mm->context.lock); } return retval; } @@ -130,7 +130,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount) if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES; - down(&mm->context.sem); + mutex_lock(&mm->context.lock); size = mm->context.size*LDT_ENTRY_SIZE; if (size > bytecount) size = bytecount; @@ -138,7 +138,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount) err = 0; if (copy_to_user(ptr, mm->context.ldt, size)) err = -EFAULT; - up(&mm->context.sem); + mutex_unlock(&mm->context.lock); if (err < 0) goto error_return; if (size != bytecount) { @@ -194,7 +194,7 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode) goto out; } - down(&mm->context.sem); + mutex_lock(&mm->context.lock); if (ldt_info.entry_number >= mm->context.size) { error = alloc_ldt(¤t->mm->context, ldt_info.entry_number+1, 1); if (error < 0) @@ -221,7 +221,7 @@ install: error = 0; out_unlock: - up(&mm->context.sem); + mutex_unlock(&mm->context.lock); out: return error; } diff --git a/arch/x86/kernel/ldt_64.c b/arch/x86/kernel/ldt_64.c index 3796523d616..60e57abb8e9 100644 --- a/arch/x86/kernel/ldt_64.c +++ b/arch/x86/kernel/ldt_64.c @@ -96,13 +96,13 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) struct mm_struct * old_mm; int retval = 0; - init_MUTEX(&mm->context.sem); + mutex_init(&mm->context.lock); mm->context.size = 0; old_mm = current->mm; if (old_mm && old_mm->context.size > 0) { - down(&old_mm->context.sem); + mutex_lock(&old_mm->context.lock); retval = copy_ldt(&mm->context, &old_mm->context); - up(&old_mm->context.sem); + mutex_unlock(&old_mm->context.lock); } return retval; } @@ -133,7 +133,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount) if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES; - down(&mm->context.sem); + mutex_lock(&mm->context.lock); size = mm->context.size*LDT_ENTRY_SIZE; if (size > bytecount) size = bytecount; @@ -141,7 +141,7 @@ static int read_ldt(void __user * ptr, unsigned long bytecount) err = 0; if (copy_to_user(ptr, mm->context.ldt, size)) err = -EFAULT; - up(&mm->context.sem); + mutex_unlock(&mm->context.lock); if (err < 0) goto error_return; if (size != bytecount) { @@ -193,7 +193,7 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode) goto out; } - down(&mm->context.sem); + mutex_lock(&mm->context.lock); if (ldt_info.entry_number >= (unsigned)mm->context.size) { error = alloc_ldt(¤t->mm->context, ldt_info.entry_number+1, 1); if (error < 0) @@ -223,7 +223,7 @@ install: error = 0; out_unlock: - up(&mm->context.sem); + mutex_unlock(&mm->context.lock); out: return error; } diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index deda9a221cf..11b935f4f88 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -10,6 +10,7 @@ #include <linux/kexec.h> #include <linux/delay.h> #include <linux/init.h> +#include <linux/numa.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> @@ -148,24 +149,14 @@ NORET_TYPE void machine_kexec(struct kimage *image) image->start, cpu_has_pae); } -/* crashkernel=size@addr specifies the location to reserve for - * a crash kernel. By reserving this memory we guarantee - * that linux never sets it up as a DMA target. - * Useful for holding code to do something appropriate - * after a kernel panic. - */ -static int __init parse_crashkernel(char *arg) +void arch_crash_save_vmcoreinfo(void) { - unsigned long size, base; - size = memparse(arg, &arg); - if (*arg == '@') { - base = memparse(arg+1, &arg); - /* FIXME: Do I want a sanity check - * to validate the memory range? - */ - crashk_res.start = base; - crashk_res.end = base + size - 1; - } - return 0; +#ifdef CONFIG_ARCH_DISCONTIGMEM_ENABLE + VMCOREINFO_SYMBOL(node_data); + VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); +#endif +#ifdef CONFIG_X86_PAE + VMCOREINFO_CONFIG(X86_PAE); +#endif } -early_param("crashkernel", parse_crashkernel); + diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index cd1899a2f0c..aa3d2c8f773 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -10,6 +10,7 @@ #include <linux/kexec.h> #include <linux/string.h> #include <linux/reboot.h> +#include <linux/numa.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> @@ -230,30 +231,13 @@ NORET_TYPE void machine_kexec(struct kimage *image) image->start); } -/* crashkernel=size@addr specifies the location to reserve for - * a crash kernel. By reserving this memory we guarantee - * that linux never set's it up as a DMA target. - * Useful for holding code to do something appropriate - * after a kernel panic. - */ -static int __init setup_crashkernel(char *arg) +void arch_crash_save_vmcoreinfo(void) { - unsigned long size, base; - char *p; - if (!arg) - return -EINVAL; - size = memparse(arg, &p); - if (arg == p) - return -EINVAL; - if (*p == '@') { - base = memparse(p+1, &p); - /* FIXME: Do I want a sanity check to validate the - * memory range? Yes you do, but it's too early for - * e820 -AK */ - crashk_res.start = base; - crashk_res.end = base + size - 1; - } - return 0; + VMCOREINFO_SYMBOL(init_level4_pgt); + +#ifdef CONFIG_ARCH_DISCONTIGMEM_ENABLE + VMCOREINFO_SYMBOL(node_data); + VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); +#endif } -early_param("crashkernel", setup_crashkernel); diff --git a/arch/x86/kernel/microcode.c b/arch/x86/kernel/microcode.c index 09cf7811035..09c315214a5 100644 --- a/arch/x86/kernel/microcode.c +++ b/arch/x86/kernel/microcode.c @@ -132,7 +132,7 @@ static struct ucode_cpu_info { static void collect_cpu_info(int cpu_num) { - struct cpuinfo_x86 *c = cpu_data + cpu_num; + struct cpuinfo_x86 *c = &cpu_data(cpu_num); struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; unsigned int val[2]; @@ -522,7 +522,7 @@ static struct platform_device *microcode_pdev; static int cpu_request_microcode(int cpu) { char name[30]; - struct cpuinfo_x86 *c = cpu_data + cpu; + struct cpuinfo_x86 *c = &cpu_data(cpu); const struct firmware *firmware; void *buf; unsigned long size; @@ -570,7 +570,7 @@ static int cpu_request_microcode(int cpu) static int apply_microcode_check_cpu(int cpu) { - struct cpuinfo_x86 *c = cpu_data + cpu; + struct cpuinfo_x86 *c = &cpu_data(cpu); struct ucode_cpu_info *uci = ucode_cpu_info + cpu; cpumask_t old; unsigned int val[2]; diff --git a/arch/x86/kernel/mpparse_32.c b/arch/x86/kernel/mpparse_32.c index 13abb4ebfb7..7a05a7f6099 100644 --- a/arch/x86/kernel/mpparse_32.c +++ b/arch/x86/kernel/mpparse_32.c @@ -1001,7 +1001,7 @@ void __init mp_config_acpi_legacy_irqs (void) /* * Use the default configuration for the IRQs 0-15. Unless - * overriden by (MADT) interrupt source override entries. + * overridden by (MADT) interrupt source override entries. */ for (i = 0; i < 16; i++) { int idx; diff --git a/arch/x86/kernel/mpparse_64.c b/arch/x86/kernel/mpparse_64.c index 8bf0ca03ac8..ef4aab12358 100644 --- a/arch/x86/kernel/mpparse_64.c +++ b/arch/x86/kernel/mpparse_64.c @@ -57,6 +57,8 @@ unsigned long mp_lapic_addr = 0; /* Processor that is doing the boot up */ unsigned int boot_cpu_id = -1U; +EXPORT_SYMBOL(boot_cpu_id); + /* Internal processor count */ unsigned int num_processors __cpuinitdata = 0; @@ -86,7 +88,7 @@ static int __init mpf_checksum(unsigned char *mp, int len) return sum & 0xFF; } -static void __cpuinit MP_processor_info (struct mpc_config_processor *m) +static void __cpuinit MP_processor_info(struct mpc_config_processor *m) { int cpu; cpumask_t tmp_map; @@ -123,7 +125,18 @@ static void __cpuinit MP_processor_info (struct mpc_config_processor *m) cpu = 0; } bios_cpu_apicid[cpu] = m->mpc_apicid; - x86_cpu_to_apicid[cpu] = m->mpc_apicid; + /* + * We get called early in the the start_kernel initialization + * process when the per_cpu data area is not yet setup, so we + * use a static array that is removed after the per_cpu data + * area is created. + */ + if (x86_cpu_to_apicid_ptr) { + u8 *x86_cpu_to_apicid = (u8 *)x86_cpu_to_apicid_ptr; + x86_cpu_to_apicid[cpu] = m->mpc_apicid; + } else { + per_cpu(x86_cpu_to_apicid, cpu) = m->mpc_apicid; + } cpu_set(cpu, cpu_possible_map); cpu_set(cpu, cpu_present_map); diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index c044de310b6..ee6eba4ecfe 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -112,7 +112,7 @@ static ssize_t msr_write(struct file *file, const char __user *buf, static int msr_open(struct inode *inode, struct file *file) { unsigned int cpu = iminor(file->f_path.dentry->d_inode); - struct cpuinfo_x86 *c = &(cpu_data)[cpu]; + struct cpuinfo_x86 *c = &cpu_data(cpu); if (cpu >= NR_CPUS || !cpu_online(cpu)) return -ENXIO; /* No such CPU */ @@ -133,37 +133,42 @@ static const struct file_operations msr_fops = { .open = msr_open, }; -static int msr_device_create(int i) +static int __cpuinit msr_device_create(int cpu) { - int err = 0; struct device *dev; - dev = device_create(msr_class, NULL, MKDEV(MSR_MAJOR, i), "msr%d",i); - if (IS_ERR(dev)) - err = PTR_ERR(dev); - return err; + dev = device_create(msr_class, NULL, MKDEV(MSR_MAJOR, cpu), + "msr%d", cpu); + return IS_ERR(dev) ? PTR_ERR(dev) : 0; } -static int msr_class_cpu_callback(struct notifier_block *nfb, +static void msr_device_destroy(int cpu) +{ + device_destroy(msr_class, MKDEV(MSR_MAJOR, cpu)); +} + +static int __cpuinit msr_class_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; + int err = 0; switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - msr_device_create(cpu); + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + err = msr_device_create(cpu); break; + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: case CPU_DEAD_FROZEN: - device_destroy(msr_class, MKDEV(MSR_MAJOR, cpu)); + msr_device_destroy(cpu); break; } - return NOTIFY_OK; + return err ? NOTIFY_BAD : NOTIFY_OK; } -static struct notifier_block __cpuinitdata msr_class_cpu_notifier = -{ +static struct notifier_block __cpuinitdata msr_class_cpu_notifier = { .notifier_call = msr_class_cpu_callback, }; @@ -196,7 +201,7 @@ static int __init msr_init(void) out_class: i = 0; for_each_online_cpu(i) - device_destroy(msr_class, MKDEV(MSR_MAJOR, i)); + msr_device_destroy(i); class_destroy(msr_class); out_chrdev: unregister_chrdev(MSR_MAJOR, "cpu/msr"); @@ -208,7 +213,7 @@ static void __exit msr_exit(void) { int cpu = 0; for_each_online_cpu(cpu) - device_destroy(msr_class, MKDEV(MSR_MAJOR, cpu)); + msr_device_destroy(cpu); class_destroy(msr_class); unregister_chrdev(MSR_MAJOR, "cpu/msr"); unregister_hotcpu_notifier(&msr_class_cpu_notifier); diff --git a/arch/x86/kernel/nmi_32.c b/arch/x86/kernel/nmi_32.c index f803ed0ed1c..600fd404e44 100644 --- a/arch/x86/kernel/nmi_32.c +++ b/arch/x86/kernel/nmi_32.c @@ -51,13 +51,13 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu); static int endflag __initdata = 0; -#ifdef CONFIG_SMP /* The performance counters used by NMI_LOCAL_APIC don't trigger when * the CPU is idle. To make sure the NMI watchdog really ticks on all * CPUs during the test make them busy. */ static __init void nmi_cpu_busy(void *data) { +#ifdef CONFIG_SMP local_irq_enable_in_hardirq(); /* Intentionally don't use cpu_relax here. This is to make sure that the performance counter really ticks, @@ -67,8 +67,8 @@ static __init void nmi_cpu_busy(void *data) care if they get somewhat less cycles. */ while (endflag == 0) mb(); -} #endif +} static int __init check_nmi_watchdog(void) { diff --git a/arch/x86/kernel/paravirt_32.c b/arch/x86/kernel/paravirt_32.c index 739cfb207dd..6a80d67c212 100644 --- a/arch/x86/kernel/paravirt_32.c +++ b/arch/x86/kernel/paravirt_32.c @@ -42,32 +42,33 @@ void _paravirt_nop(void) static void __init default_banner(void) { printk(KERN_INFO "Booting paravirtualized kernel on %s\n", - paravirt_ops.name); + pv_info.name); } char *memory_setup(void) { - return paravirt_ops.memory_setup(); + return pv_init_ops.memory_setup(); } /* Simple instruction patching code. */ -#define DEF_NATIVE(name, code) \ - extern const char start_##name[], end_##name[]; \ - asm("start_" #name ": " code "; end_" #name ":") - -DEF_NATIVE(irq_disable, "cli"); -DEF_NATIVE(irq_enable, "sti"); -DEF_NATIVE(restore_fl, "push %eax; popf"); -DEF_NATIVE(save_fl, "pushf; pop %eax"); -DEF_NATIVE(iret, "iret"); -DEF_NATIVE(irq_enable_sysexit, "sti; sysexit"); -DEF_NATIVE(read_cr2, "mov %cr2, %eax"); -DEF_NATIVE(write_cr3, "mov %eax, %cr3"); -DEF_NATIVE(read_cr3, "mov %cr3, %eax"); -DEF_NATIVE(clts, "clts"); -DEF_NATIVE(read_tsc, "rdtsc"); - -DEF_NATIVE(ud2a, "ud2a"); +#define DEF_NATIVE(ops, name, code) \ + extern const char start_##ops##_##name[], end_##ops##_##name[]; \ + asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":") + +DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); +DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); +DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf"); +DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax"); +DEF_NATIVE(pv_cpu_ops, iret, "iret"); +DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit"); +DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax"); +DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); +DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); +DEF_NATIVE(pv_cpu_ops, clts, "clts"); +DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc"); + +/* Undefined instruction for dealing with missing ops pointers. */ +static const unsigned char ud2a[] = { 0x0f, 0x0b }; static unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) @@ -76,37 +77,29 @@ static unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned ret; switch(type) { -#define SITE(x) case PARAVIRT_PATCH(x): start = start_##x; end = end_##x; goto patch_site - SITE(irq_disable); - SITE(irq_enable); - SITE(restore_fl); - SITE(save_fl); - SITE(iret); - SITE(irq_enable_sysexit); - SITE(read_cr2); - SITE(read_cr3); - SITE(write_cr3); - SITE(clts); - SITE(read_tsc); +#define SITE(ops, x) \ + case PARAVIRT_PATCH(ops.x): \ + start = start_##ops##_##x; \ + end = end_##ops##_##x; \ + goto patch_site + + SITE(pv_irq_ops, irq_disable); + SITE(pv_irq_ops, irq_enable); + SITE(pv_irq_ops, restore_fl); + SITE(pv_irq_ops, save_fl); + SITE(pv_cpu_ops, iret); + SITE(pv_cpu_ops, irq_enable_sysexit); + SITE(pv_mmu_ops, read_cr2); + SITE(pv_mmu_ops, read_cr3); + SITE(pv_mmu_ops, write_cr3); + SITE(pv_cpu_ops, clts); + SITE(pv_cpu_ops, read_tsc); #undef SITE patch_site: ret = paravirt_patch_insns(ibuf, len, start, end); break; - case PARAVIRT_PATCH(make_pgd): - case PARAVIRT_PATCH(make_pte): - case PARAVIRT_PATCH(pgd_val): - case PARAVIRT_PATCH(pte_val): -#ifdef CONFIG_X86_PAE - case PARAVIRT_PATCH(make_pmd): - case PARAVIRT_PATCH(pmd_val): -#endif - /* These functions end up returning exactly what - they're passed, in the same registers. */ - ret = paravirt_patch_nop(); - break; - default: ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; @@ -150,7 +143,7 @@ unsigned paravirt_patch_call(void *insnbuf, return 5; } -unsigned paravirt_patch_jmp(const void *target, void *insnbuf, +unsigned paravirt_patch_jmp(void *insnbuf, const void *target, unsigned long addr, unsigned len) { struct branch *b = insnbuf; @@ -165,22 +158,37 @@ unsigned paravirt_patch_jmp(const void *target, void *insnbuf, return 5; } +/* Neat trick to map patch type back to the call within the + * corresponding structure. */ +static void *get_call_destination(u8 type) +{ + struct paravirt_patch_template tmpl = { + .pv_init_ops = pv_init_ops, + .pv_time_ops = pv_time_ops, + .pv_cpu_ops = pv_cpu_ops, + .pv_irq_ops = pv_irq_ops, + .pv_apic_ops = pv_apic_ops, + .pv_mmu_ops = pv_mmu_ops, + }; + return *((void **)&tmpl + type); +} + unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, unsigned long addr, unsigned len) { - void *opfunc = *((void **)¶virt_ops + type); + void *opfunc = get_call_destination(type); unsigned ret; if (opfunc == NULL) /* If there's no function, patch it with a ud2a (BUG) */ - ret = paravirt_patch_insns(insnbuf, len, start_ud2a, end_ud2a); + ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a)); else if (opfunc == paravirt_nop) /* If the operation is a nop, then nop the callsite */ ret = paravirt_patch_nop(); - else if (type == PARAVIRT_PATCH(iret) || - type == PARAVIRT_PATCH(irq_enable_sysexit)) + else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || + type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit)) /* If operation requires a jmp, then jmp */ - ret = paravirt_patch_jmp(opfunc, insnbuf, addr, len); + ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len); else /* Otherwise call the function; assume target could clobber any caller-save reg */ @@ -205,7 +213,7 @@ unsigned paravirt_patch_insns(void *insnbuf, unsigned len, void init_IRQ(void) { - paravirt_ops.init_IRQ(); + pv_irq_ops.init_IRQ(); } static void native_flush_tlb(void) @@ -233,7 +241,7 @@ extern void native_irq_enable_sysexit(void); static int __init print_banner(void) { - paravirt_ops.banner(); + pv_init_ops.banner(); return 0; } core_initcall(print_banner); @@ -273,47 +281,96 @@ int paravirt_disable_iospace(void) return ret; } -struct paravirt_ops paravirt_ops = { +static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE; + +static inline void enter_lazy(enum paravirt_lazy_mode mode) +{ + BUG_ON(x86_read_percpu(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE); + BUG_ON(preemptible()); + + x86_write_percpu(paravirt_lazy_mode, mode); +} + +void paravirt_leave_lazy(enum paravirt_lazy_mode mode) +{ + BUG_ON(x86_read_percpu(paravirt_lazy_mode) != mode); + BUG_ON(preemptible()); + + x86_write_percpu(paravirt_lazy_mode, PARAVIRT_LAZY_NONE); +} + +void paravirt_enter_lazy_mmu(void) +{ + enter_lazy(PARAVIRT_LAZY_MMU); +} + +void paravirt_leave_lazy_mmu(void) +{ + paravirt_leave_lazy(PARAVIRT_LAZY_MMU); +} + +void paravirt_enter_lazy_cpu(void) +{ + enter_lazy(PARAVIRT_LAZY_CPU); +} + +void paravirt_leave_lazy_cpu(void) +{ + paravirt_leave_lazy(PARAVIRT_LAZY_CPU); +} + +enum paravirt_lazy_mode paravirt_get_lazy_mode(void) +{ + return x86_read_percpu(paravirt_lazy_mode); +} + +struct pv_info pv_info = { .name = "bare hardware", .paravirt_enabled = 0, .kernel_rpl = 0, .shared_kernel_pmd = 1, /* Only used when CONFIG_X86_PAE is set */ +}; - .patch = native_patch, +struct pv_init_ops pv_init_ops = { + .patch = native_patch, .banner = default_banner, .arch_setup = paravirt_nop, .memory_setup = machine_specific_memory_setup, +}; + +struct pv_time_ops pv_time_ops = { + .time_init = hpet_time_init, .get_wallclock = native_get_wallclock, .set_wallclock = native_set_wallclock, - .time_init = hpet_time_init, + .sched_clock = native_sched_clock, + .get_cpu_khz = native_calculate_cpu_khz, +}; + +struct pv_irq_ops pv_irq_ops = { .init_IRQ = native_init_IRQ, + .save_fl = native_save_fl, + .restore_fl = native_restore_fl, + .irq_disable = native_irq_disable, + .irq_enable = native_irq_enable, + .safe_halt = native_safe_halt, + .halt = native_halt, +}; +struct pv_cpu_ops pv_cpu_ops = { .cpuid = native_cpuid, .get_debugreg = native_get_debugreg, .set_debugreg = native_set_debugreg, .clts = native_clts, .read_cr0 = native_read_cr0, .write_cr0 = native_write_cr0, - .read_cr2 = native_read_cr2, - .write_cr2 = native_write_cr2, - .read_cr3 = native_read_cr3, - .write_cr3 = native_write_cr3, .read_cr4 = native_read_cr4, .read_cr4_safe = native_read_cr4_safe, .write_cr4 = native_write_cr4, - .save_fl = native_save_fl, - .restore_fl = native_restore_fl, - .irq_disable = native_irq_disable, - .irq_enable = native_irq_enable, - .safe_halt = native_safe_halt, - .halt = native_halt, .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, .write_msr = native_write_msr_safe, .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, - .sched_clock = native_sched_clock, - .get_cpu_khz = native_calculate_cpu_khz, .load_tr_desc = native_load_tr_desc, .set_ldt = native_set_ldt, .load_gdt = native_load_gdt, @@ -327,9 +384,19 @@ struct paravirt_ops paravirt_ops = { .write_idt_entry = write_dt_entry, .load_esp0 = native_load_esp0, + .irq_enable_sysexit = native_irq_enable_sysexit, + .iret = native_iret, + .set_iopl_mask = native_set_iopl_mask, .io_delay = native_io_delay, + .lazy_mode = { + .enter = paravirt_nop, + .leave = paravirt_nop, + }, +}; + +struct pv_apic_ops pv_apic_ops = { #ifdef CONFIG_X86_LOCAL_APIC .apic_write = native_apic_write, .apic_write_atomic = native_apic_write_atomic, @@ -338,11 +405,17 @@ struct paravirt_ops paravirt_ops = { .setup_secondary_clock = setup_secondary_APIC_clock, .startup_ipi_hook = paravirt_nop, #endif - .set_lazy_mode = paravirt_nop, +}; +struct pv_mmu_ops pv_mmu_ops = { .pagetable_setup_start = native_pagetable_setup_start, .pagetable_setup_done = native_pagetable_setup_done, + .read_cr2 = native_read_cr2, + .write_cr2 = native_write_cr2, + .read_cr3 = native_read_cr3, + .write_cr3 = native_write_cr3, + .flush_tlb_user = native_flush_tlb, .flush_tlb_kernel = native_flush_tlb_global, .flush_tlb_single = native_flush_tlb_single, @@ -381,12 +454,19 @@ struct paravirt_ops paravirt_ops = { .make_pte = native_make_pte, .make_pgd = native_make_pgd, - .irq_enable_sysexit = native_irq_enable_sysexit, - .iret = native_iret, - .dup_mmap = paravirt_nop, .exit_mmap = paravirt_nop, .activate_mm = paravirt_nop, + + .lazy_mode = { + .enter = paravirt_nop, + .leave = paravirt_nop, + }, }; -EXPORT_SYMBOL(paravirt_ops); +EXPORT_SYMBOL_GPL(pv_time_ops); +EXPORT_SYMBOL_GPL(pv_cpu_ops); +EXPORT_SYMBOL_GPL(pv_mmu_ops); +EXPORT_SYMBOL_GPL(pv_apic_ops); +EXPORT_SYMBOL_GPL(pv_info); +EXPORT_SYMBOL (pv_irq_ops); diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 71da01e73f0..6bf1f716909 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -35,7 +35,8 @@ #include <linux/pci_ids.h> #include <linux/pci.h> #include <linux/delay.h> -#include <asm/iommu.h> +#include <linux/scatterlist.h> +#include <asm/gart.h> #include <asm/calgary.h> #include <asm/tce.h> #include <asm/pci-direct.h> @@ -221,10 +222,10 @@ static inline unsigned int num_dma_pages(unsigned long dma, unsigned int dmalen) return npages; } -static inline int translate_phb(struct pci_dev* dev) +static inline int translation_enabled(struct iommu_table *tbl) { - int disabled = bus_info[dev->bus->number].translation_disabled; - return !disabled; + /* only PHBs with translation enabled have an IOMMU table */ + return (tbl != NULL); } static void iommu_range_reserve(struct iommu_table *tbl, @@ -384,33 +385,36 @@ static void calgary_unmap_sg(struct device *dev, struct scatterlist *sglist, int nelems, int direction) { struct iommu_table *tbl = find_iommu_table(dev); + struct scatterlist *s; + int i; - if (!translate_phb(to_pci_dev(dev))) + if (!translation_enabled(tbl)) return; - while (nelems--) { + for_each_sg(sglist, s, nelems, i) { unsigned int npages; - dma_addr_t dma = sglist->dma_address; - unsigned int dmalen = sglist->dma_length; + dma_addr_t dma = s->dma_address; + unsigned int dmalen = s->dma_length; if (dmalen == 0) break; npages = num_dma_pages(dma, dmalen); iommu_free(tbl, dma, npages); - sglist++; } } static int calgary_nontranslate_map_sg(struct device* dev, struct scatterlist *sg, int nelems, int direction) { + struct scatterlist *s; int i; - for (i = 0; i < nelems; i++ ) { - struct scatterlist *s = &sg[i]; - BUG_ON(!s->page); - s->dma_address = virt_to_bus(page_address(s->page) +s->offset); + 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; @@ -420,19 +424,19 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, int nelems, int direction) { struct iommu_table *tbl = find_iommu_table(dev); + struct scatterlist *s; unsigned long vaddr; unsigned int npages; unsigned long entry; int i; - if (!translate_phb(to_pci_dev(dev))) + if (!translation_enabled(tbl)) return calgary_nontranslate_map_sg(dev, sg, nelems, direction); - for (i = 0; i < nelems; i++ ) { - struct scatterlist *s = &sg[i]; - BUG_ON(!s->page); + for_each_sg(sg, s, nelems, i) { + BUG_ON(!sg_page(s)); - vaddr = (unsigned long)page_address(s->page) + s->offset; + vaddr = (unsigned long) sg_virt(s); npages = num_dma_pages(vaddr, s->length); entry = iommu_range_alloc(tbl, npages); @@ -454,9 +458,9 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, return nelems; error: calgary_unmap_sg(dev, sg, nelems, direction); - for (i = 0; i < nelems; i++) { - sg[i].dma_address = bad_dma_address; - sg[i].dma_length = 0; + for_each_sg(sg, s, nelems, i) { + sg->dma_address = bad_dma_address; + sg->dma_length = 0; } return 0; } @@ -472,7 +476,7 @@ static dma_addr_t calgary_map_single(struct device *dev, void *vaddr, uaddr = (unsigned long)vaddr; npages = num_dma_pages(uaddr, size); - if (translate_phb(to_pci_dev(dev))) + if (translation_enabled(tbl)) dma_handle = iommu_alloc(tbl, vaddr, npages, direction); else dma_handle = virt_to_bus(vaddr); @@ -486,7 +490,7 @@ 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 (!translate_phb(to_pci_dev(dev))) + if (!translation_enabled(tbl)) return; npages = num_dma_pages(dma_handle, size); @@ -511,7 +515,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size, goto error; memset(ret, 0, size); - if (translate_phb(to_pci_dev(dev))) { + if (translation_enabled(tbl)) { /* set up tces to cover the allocated range */ mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL); if (mapping == bad_dma_address) @@ -1192,7 +1196,7 @@ static int __init calgary_init(void) { int ret; struct pci_dev *dev = NULL; - void *tce_space; + struct calgary_bus_info *info; ret = calgary_locate_bbars(); if (ret) @@ -1204,12 +1208,14 @@ static int __init calgary_init(void) break; if (!is_cal_pci_dev(dev->device)) continue; - if (!translate_phb(dev)) { + + info = &bus_info[dev->bus->number]; + if (info->translation_disabled) { calgary_init_one_nontraslated(dev); continue; } - tce_space = bus_info[dev->bus->number].tce_space; - if (!tce_space && !translate_empty_slots) + + if (!info->tce_space && !translate_empty_slots) continue; ret = calgary_init_one(dev); @@ -1227,11 +1233,13 @@ error: break; if (!is_cal_pci_dev(dev->device)) continue; - if (!translate_phb(dev)) { + + info = &bus_info[dev->bus->number]; + if (info->translation_disabled) { pci_dev_put(dev); continue; } - if (!bus_info[dev->bus->number].tce_space && !translate_empty_slots) + if (!info->tce_space && !translate_empty_slots) continue; calgary_disable_translation(dev); @@ -1544,7 +1552,7 @@ static void __init calgary_fixup_one_tce_space(struct pci_dev *dev) static int __init calgary_fixup_tce_spaces(void) { struct pci_dev *dev = NULL; - void *tce_space; + struct calgary_bus_info *info; if (no_iommu || swiotlb || !calgary_detected) return -ENODEV; @@ -1557,11 +1565,12 @@ static int __init calgary_fixup_tce_spaces(void) break; if (!is_cal_pci_dev(dev->device)) continue; - if (!translate_phb(dev)) + + info = &bus_info[dev->bus->number]; + if (info->translation_disabled) continue; - tce_space = bus_info[dev->bus->number].tce_space; - if (!tce_space) + if (!info->tce_space) continue; calgary_fixup_one_tce_space(dev); diff --git a/arch/x86/kernel/pci-dma_32.c b/arch/x86/kernel/pci-dma_32.c index 0aae2f3847a..51330321a5d 100644 --- a/arch/x86/kernel/pci-dma_32.c +++ b/arch/x86/kernel/pci-dma_32.c @@ -12,7 +12,6 @@ #include <linux/string.h> #include <linux/pci.h> #include <linux/module.h> -#include <linux/pci.h> #include <asm/io.h> struct dma_coherent_mem { diff --git a/arch/x86/kernel/pci-dma_64.c b/arch/x86/kernel/pci-dma_64.c index 9576a2eb375..aa805b11b24 100644 --- a/arch/x86/kernel/pci-dma_64.c +++ b/arch/x86/kernel/pci-dma_64.c @@ -7,11 +7,12 @@ #include <linux/string.h> #include <linux/pci.h> #include <linux/module.h> +#include <linux/dmar.h> #include <asm/io.h> -#include <asm/iommu.h> +#include <asm/gart.h> #include <asm/calgary.h> -int iommu_merge __read_mostly = 0; +int iommu_merge __read_mostly = 1; EXPORT_SYMBOL(iommu_merge); dma_addr_t bad_dma_address __read_mostly; @@ -51,11 +52,9 @@ dma_alloc_pages(struct device *dev, gfp_t gfp, unsigned order) { struct page *page; int node; -#ifdef CONFIG_PCI - if (dev->bus == &pci_bus_type) - node = pcibus_to_node(to_pci_dev(dev)->bus); - else -#endif + + node = dev_to_node(dev); + if (node == -1) node = numa_node_id(); if (node < first_node(node_online_map)) @@ -276,7 +275,7 @@ __init int iommu_setup(char *p) swiotlb = 1; #endif -#ifdef CONFIG_IOMMU +#ifdef CONFIG_GART_IOMMU gart_parse_options(p); #endif @@ -299,14 +298,16 @@ void __init pci_iommu_alloc(void) * The order of these functions is important for * fall-back/fail-over reasons */ -#ifdef CONFIG_IOMMU - iommu_hole_init(); +#ifdef CONFIG_GART_IOMMU + gart_iommu_hole_init(); #endif #ifdef CONFIG_CALGARY_IOMMU detect_calgary(); #endif + detect_intel_iommu(); + #ifdef CONFIG_SWIOTLB pci_swiotlb_init(); #endif @@ -318,7 +319,9 @@ static int __init pci_iommu_init(void) calgary_iommu_init(); #endif -#ifdef CONFIG_IOMMU + intel_iommu_init(); + +#ifdef CONFIG_GART_IOMMU gart_iommu_init(); #endif diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index 4918c575d58..06bcba53604 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -8,6 +8,7 @@ * See Documentation/DMA-mapping.txt for the interface specification. * * Copyright 2002 Andi Kleen, SuSE Labs. + * Subject to the GNU General Public License v2 only. */ #include <linux/types.h> @@ -23,22 +24,23 @@ #include <linux/interrupt.h> #include <linux/bitops.h> #include <linux/kdebug.h> +#include <linux/scatterlist.h> #include <asm/atomic.h> #include <asm/io.h> #include <asm/mtrr.h> #include <asm/pgtable.h> #include <asm/proto.h> -#include <asm/iommu.h> +#include <asm/gart.h> #include <asm/cacheflush.h> #include <asm/swiotlb.h> #include <asm/dma.h> #include <asm/k8.h> -unsigned long iommu_bus_base; /* GART remapping area (physical) */ +static unsigned long iommu_bus_base; /* GART remapping area (physical) */ static unsigned long iommu_size; /* size of remapping area bytes */ static unsigned long iommu_pages; /* .. and in pages */ -u32 *iommu_gatt_base; /* Remapping table */ +static u32 *iommu_gatt_base; /* Remapping table */ /* If this is disabled the IOMMU will use an optimized flushing strategy of only flushing when an mapping is reused. With it true the GART is flushed @@ -133,8 +135,8 @@ static void flush_gart(void) /* Debugging aid for drivers that don't free their IOMMU tables */ static void **iommu_leak_tab; static int leak_trace; -int iommu_leak_pages = 20; -void dump_leak(void) +static int iommu_leak_pages = 20; +static void dump_leak(void) { int i; static int dump; @@ -278,10 +280,10 @@ static void gart_unmap_single(struct device *dev, dma_addr_t dma_addr, */ static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) { + struct scatterlist *s; int i; - for (i = 0; i < nents; i++) { - struct scatterlist *s = &sg[i]; + for_each_sg(sg, s, nents, i) { if (!s->dma_length || !s->length) break; gart_unmap_single(dev, s->dma_address, s->dma_length, dir); @@ -292,15 +294,15 @@ static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg, int nents, int dir) { + struct scatterlist *s; int i; #ifdef CONFIG_IOMMU_DEBUG printk(KERN_DEBUG "dma_map_sg overflow\n"); #endif - for (i = 0; i < nents; i++ ) { - struct scatterlist *s = &sg[i]; - unsigned long addr = page_to_phys(s->page) + s->offset; + for_each_sg(sg, s, nents, i) { + unsigned long addr = sg_phys(s); if (nonforced_iommu(dev, addr, s->length)) { addr = dma_map_area(dev, addr, s->length, dir); if (addr == bad_dma_address) { @@ -319,24 +321,23 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg, } /* Map multiple scatterlist entries continuous into the first. */ -static int __dma_map_cont(struct scatterlist *sg, int start, int stopat, +static int __dma_map_cont(struct scatterlist *start, int nelems, struct scatterlist *sout, unsigned long pages) { unsigned long iommu_start = alloc_iommu(pages); unsigned long iommu_page = iommu_start; + struct scatterlist *s; int i; if (iommu_start == -1) return -1; - - for (i = start; i < stopat; i++) { - struct scatterlist *s = &sg[i]; + + for_each_sg(start, s, nelems, i) { unsigned long pages, addr; unsigned long phys_addr = s->dma_address; - BUG_ON(i > start && s->offset); - if (i == start) { - *sout = *s; + BUG_ON(s != start && s->offset); + if (s == start) { sout->dma_address = iommu_bus_base; sout->dma_address += iommu_page*PAGE_SIZE + s->offset; sout->dma_length = s->length; @@ -357,30 +358,32 @@ static int __dma_map_cont(struct scatterlist *sg, int start, int stopat, return 0; } -static inline int dma_map_cont(struct scatterlist *sg, int start, int stopat, +static inline int dma_map_cont(struct scatterlist *start, int nelems, struct scatterlist *sout, unsigned long pages, int need) { - if (!need) { - BUG_ON(stopat - start != 1); - *sout = sg[start]; - sout->dma_length = sg[start].length; + if (!need) { + BUG_ON(nelems != 1); + sout->dma_address = start->dma_address; + sout->dma_length = start->length; return 0; - } - return __dma_map_cont(sg, start, stopat, sout, pages); + } + return __dma_map_cont(start, nelems, sout, pages); } /* * DMA map all entries in a scatterlist. * Merge chunks that have page aligned sizes into a continuous mapping. */ -int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) +static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, + int dir) { int i; int out; int start; unsigned long pages = 0; int need = 0, nextneed; + struct scatterlist *s, *ps, *start_sg, *sgmap; if (nents == 0) return 0; @@ -390,9 +393,10 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) out = 0; start = 0; - for (i = 0; i < nents; i++) { - struct scatterlist *s = &sg[i]; - dma_addr_t addr = page_to_phys(s->page) + s->offset; + start_sg = sgmap = sg; + ps = NULL; /* shut up gcc */ + for_each_sg(sg, s, nents, i) { + dma_addr_t addr = sg_phys(s); s->dma_address = addr; BUG_ON(s->length == 0); @@ -400,34 +404,38 @@ int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) /* Handle the previous not yet processed entries */ if (i > start) { - struct scatterlist *ps = &sg[i-1]; /* Can only merge when the last chunk ends on a page boundary and the new one doesn't have an offset. */ if (!iommu_merge || !nextneed || !need || s->offset || - (ps->offset + ps->length) % PAGE_SIZE) { - if (dma_map_cont(sg, start, i, sg+out, pages, - need) < 0) + (ps->offset + ps->length) % PAGE_SIZE) { + if (dma_map_cont(start_sg, i - start, sgmap, + pages, need) < 0) goto error; out++; + sgmap = sg_next(sgmap); pages = 0; - start = i; + start = i; + start_sg = s; } } need = nextneed; pages += to_pages(s->offset, s->length); + ps = s; } - if (dma_map_cont(sg, start, i, sg+out, pages, need) < 0) + if (dma_map_cont(start_sg, i - start, sgmap, pages, need) < 0) goto error; out++; flush_gart(); - if (out < nents) - sg[out].dma_length = 0; + if (out < nents) { + sgmap = sg_next(sgmap); + sgmap->dma_length = 0; + } return out; error: flush_gart(); - gart_unmap_sg(dev, sg, nents, dir); + gart_unmap_sg(dev, sg, out, dir); /* When it was forced or merged try again in a dumb way */ if (force_iommu || iommu_merge) { out = dma_map_sg_nonforce(dev, sg, nents, dir); @@ -437,8 +445,8 @@ error: if (panic_on_overflow) panic("dma_map_sg: overflow on %lu pages\n", pages); iommu_full(dev, pages << PAGE_SHIFT, dir); - for (i = 0; i < nents; i++) - sg[i].dma_address = bad_dma_address; + for_each_sg(sg, s, nents, i) + s->dma_address = bad_dma_address; return 0; } @@ -619,12 +627,12 @@ void __init gart_iommu_init(void) return; /* Did we detect a different HW IOMMU? */ - if (iommu_detected && !iommu_aperture) + if (iommu_detected && !gart_iommu_aperture) return; if (no_iommu || (!force_iommu && end_pfn <= MAX_DMA32_PFN) || - !iommu_aperture || + !gart_iommu_aperture || (no_agp && init_k8_gatt(&info) < 0)) { if (end_pfn > MAX_DMA32_PFN) { printk(KERN_ERR "WARNING more than 4GB of memory " @@ -725,9 +733,9 @@ void __init gart_parse_options(char *p) fix_aperture = 0; /* duplicated from pci-dma.c */ if (!strncmp(p,"force",5)) - iommu_aperture_allowed = 1; + gart_iommu_aperture_allowed = 1; if (!strncmp(p,"allowed",7)) - iommu_aperture_allowed = 1; + gart_iommu_aperture_allowed = 1; if (!strncmp(p, "memaper", 7)) { fallback_aper_force = 1; p += 7; diff --git a/arch/x86/kernel/pci-nommu_64.c b/arch/x86/kernel/pci-nommu_64.c index 2a34c6c025a..ab08e183222 100644 --- a/arch/x86/kernel/pci-nommu_64.c +++ b/arch/x86/kernel/pci-nommu_64.c @@ -5,8 +5,9 @@ #include <linux/pci.h> #include <linux/string.h> #include <linux/dma-mapping.h> +#include <linux/scatterlist.h> -#include <asm/iommu.h> +#include <asm/gart.h> #include <asm/processor.h> #include <asm/dma.h> @@ -57,12 +58,12 @@ static void nommu_unmap_single(struct device *dev, dma_addr_t addr,size_t size, static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, int direction) { + struct scatterlist *s; int i; - for (i = 0; i < nents; i++ ) { - struct scatterlist *s = &sg[i]; - BUG_ON(!s->page); - s->dma_address = virt_to_bus(page_address(s->page) +s->offset); + for_each_sg(sg, s, nents, i) { + BUG_ON(!sg_page(s)); + s->dma_address = virt_to_bus(sg_virt(s)); if (!check_addr("map_sg", hwdev, s->dma_address, s->length)) return 0; s->dma_length = s->length; diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c index b2f405ea7c8..102866d729a 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb_64.c @@ -5,7 +5,7 @@ #include <linux/module.h> #include <linux/dma-mapping.h> -#include <asm/iommu.h> +#include <asm/gart.h> #include <asm/swiotlb.h> #include <asm/dma.h> diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 097aeafce5f..7b899584d29 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -295,34 +295,52 @@ static int __init idle_setup(char *str) } early_param("idle", idle_setup); -void show_regs(struct pt_regs * regs) +void __show_registers(struct pt_regs *regs, int all) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; unsigned long d0, d1, d2, d3, d6, d7; + unsigned long esp; + unsigned short ss, gs; + + if (user_mode_vm(regs)) { + esp = regs->esp; + ss = regs->xss & 0xffff; + savesegment(gs, gs); + } else { + esp = (unsigned long) (®s->esp); + savesegment(ss, ss); + savesegment(gs, gs); + } printk("\n"); - printk("Pid: %d, comm: %20s\n", current->pid, current->comm); - printk("EIP: %04x:[<%08lx>] CPU: %d\n",0xffff & regs->xcs,regs->eip, smp_processor_id()); + printk("Pid: %d, comm: %s %s (%s %.*s)\n", + task_pid_nr(current), current->comm, + print_tainted(), init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + + printk("EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n", + 0xffff & regs->xcs, regs->eip, regs->eflags, + smp_processor_id()); print_symbol("EIP is at %s\n", regs->eip); - if (user_mode_vm(regs)) - printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp); - printk(" EFLAGS: %08lx %s (%s %.*s)\n", - regs->eflags, print_tainted(), init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", - regs->eax,regs->ebx,regs->ecx,regs->edx); - printk("ESI: %08lx EDI: %08lx EBP: %08lx", - regs->esi, regs->edi, regs->ebp); - printk(" DS: %04x ES: %04x FS: %04x\n", - 0xffff & regs->xds,0xffff & regs->xes, 0xffff & regs->xfs); + regs->eax, regs->ebx, regs->ecx, regs->edx); + printk("ESI: %08lx EDI: %08lx EBP: %08lx ESP: %08lx\n", + regs->esi, regs->edi, regs->ebp, esp); + printk(" DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x\n", + regs->xds & 0xffff, regs->xes & 0xffff, + regs->xfs & 0xffff, gs, ss); + + if (!all) + return; cr0 = read_cr0(); cr2 = read_cr2(); cr3 = read_cr3(); cr4 = read_cr4_safe(); - printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4); + printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", + cr0, cr2, cr3, cr4); get_debugreg(d0, 0); get_debugreg(d1, 1); @@ -330,10 +348,16 @@ void show_regs(struct pt_regs * regs) get_debugreg(d3, 3); printk("DR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n", d0, d1, d2, d3); + get_debugreg(d6, 6); get_debugreg(d7, 7); - printk("DR6: %08lx DR7: %08lx\n", d6, d7); + printk("DR6: %08lx DR7: %08lx\n", + d6, d7); +} +void show_regs(struct pt_regs *regs) +{ + __show_registers(regs, 1); show_trace(NULL, regs, ®s->esp); } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 7352d4b377e..6309b275cb9 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -581,7 +581,7 @@ static inline void __switch_to_xtra(struct task_struct *prev_p, * * Kprobes not supported here. Set the probe on schedule instead. */ -__kprobes struct task_struct * +struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread, diff --git a/arch/x86/kernel/ptrace_32.c b/arch/x86/kernel/ptrace_32.c index 0cecd7513c9..ff5431cc03e 100644 --- a/arch/x86/kernel/ptrace_32.c +++ b/arch/x86/kernel/ptrace_32.c @@ -165,7 +165,7 @@ static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_ seg &= ~7UL; - down(&child->mm->context.sem); + mutex_lock(&child->mm->context.lock); if (unlikely((seg >> 3) >= child->mm->context.size)) addr = -1L; /* bogus selector, access would fault */ else { @@ -179,7 +179,7 @@ static unsigned long convert_eip_to_linear(struct task_struct *child, struct pt_ addr &= 0xffff; addr += base; } - up(&child->mm->context.sem); + mutex_unlock(&child->mm->context.lock); } return addr; } @@ -524,11 +524,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = 0; break; - case PTRACE_DETACH: - /* detach a process that was attached. */ - ret = ptrace_detach(child, data); - break; - case PTRACE_GETREGS: { /* Get all gp regs from the child. */ if (!access_ok(VERIFY_WRITE, datap, FRAME_SIZE*sizeof(long))) { ret = -EIO; @@ -637,7 +632,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code) /* User-mode eip? */ info.si_addr = user_mode_vm(regs) ? (void __user *) regs->eip : NULL; - /* Send us the fakey SIGTRAP */ + /* Send us the fake SIGTRAP */ force_sig_info(SIGTRAP, &info, tsk); } diff --git a/arch/x86/kernel/ptrace_64.c b/arch/x86/kernel/ptrace_64.c index c0cac42df3b..607085f3f08 100644 --- a/arch/x86/kernel/ptrace_64.c +++ b/arch/x86/kernel/ptrace_64.c @@ -103,7 +103,7 @@ unsigned long convert_rip_to_linear(struct task_struct *child, struct pt_regs *r seg &= ~7UL; - down(&child->mm->context.sem); + mutex_lock(&child->mm->context.lock); if (unlikely((seg >> 3) >= child->mm->context.size)) addr = -1L; /* bogus selector, access would fault */ else { @@ -117,7 +117,7 @@ unsigned long convert_rip_to_linear(struct task_struct *child, struct pt_regs *r addr &= 0xffff; addr += base; } - up(&child->mm->context.sem); + mutex_unlock(&child->mm->context.lock); } return addr; @@ -500,11 +500,6 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) ret = 0; break; - case PTRACE_DETACH: - /* detach a process that was attached. */ - ret = ptrace_detach(child, data); - break; - case PTRACE_GETREGS: { /* Get all gp regs from the child. */ if (!access_ok(VERIFY_WRITE, (unsigned __user *)data, sizeof(struct user_regs_struct))) { diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index d769e204f94..fab30e13483 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -45,9 +45,12 @@ static void __devinit quirk_intel_irqbalance(struct pci_dev *dev) if (!(config & 0x2)) pci_write_config_byte(dev, 0xf4, config); } -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7320_MCH, quirk_intel_irqbalance); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7525_MCH, quirk_intel_irqbalance); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7520_MCH, quirk_intel_irqbalance); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7320_MCH, + quirk_intel_irqbalance); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7525_MCH, + quirk_intel_irqbalance); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7520_MCH, + quirk_intel_irqbalance); #endif #if defined(CONFIG_HPET_TIMER) @@ -56,7 +59,9 @@ unsigned long force_hpet_address; static enum { NONE_FORCE_HPET_RESUME, OLD_ICH_FORCE_HPET_RESUME, - ICH_FORCE_HPET_RESUME + ICH_FORCE_HPET_RESUME, + VT8237_FORCE_HPET_RESUME, + NVIDIA_FORCE_HPET_RESUME, } force_hpet_resume_type; static void __iomem *rcba_base; @@ -146,17 +151,17 @@ static void ich_force_enable_hpet(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ESB2_0, - ich_force_enable_hpet); + ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH6_1, - ich_force_enable_hpet); + ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_0, - ich_force_enable_hpet); + ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_1, - ich_force_enable_hpet); + ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH7_31, - ich_force_enable_hpet); + ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH8_1, - ich_force_enable_hpet); + ich_force_enable_hpet); static struct pci_dev *cached_dev; @@ -232,10 +237,140 @@ static void old_ich_force_enable_hpet(struct pci_dev *dev) printk(KERN_DEBUG "Failed to force enable HPET\n"); } +/* + * Undocumented chipset features. Make sure that the user enforced + * this. + */ +static void old_ich_force_enable_hpet_user(struct pci_dev *dev) +{ + if (hpet_force_user) + old_ich_force_enable_hpet(dev); +} + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_0, + old_ich_force_enable_hpet_user); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_12, + old_ich_force_enable_hpet_user); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801DB_0, + old_ich_force_enable_hpet_user); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801DB_12, + old_ich_force_enable_hpet_user); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801EB_0, - old_ich_force_enable_hpet); + old_ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801EB_12, - old_ich_force_enable_hpet); + old_ich_force_enable_hpet); + + +static void vt8237_force_hpet_resume(void) +{ + u32 val; + + if (!force_hpet_address || !cached_dev) + return; + + val = 0xfed00000 | 0x80; + pci_write_config_dword(cached_dev, 0x68, val); + + pci_read_config_dword(cached_dev, 0x68, &val); + if (val & 0x80) + printk(KERN_DEBUG "Force enabled HPET at resume\n"); + else + BUG(); +} + +static void vt8237_force_enable_hpet(struct pci_dev *dev) +{ + u32 uninitialized_var(val); + + if (!hpet_force_user || hpet_address || force_hpet_address) + return; + + pci_read_config_dword(dev, 0x68, &val); + /* + * Bit 7 is HPET enable bit. + * Bit 31:10 is HPET base address (contrary to what datasheet claims) + */ + if (val & 0x80) { + force_hpet_address = (val & ~0x3ff); + printk(KERN_DEBUG "HPET at base address 0x%lx\n", + force_hpet_address); + return; + } + + /* + * HPET is disabled. Trying enabling at FED00000 and check + * whether it sticks + */ + val = 0xfed00000 | 0x80; + pci_write_config_dword(dev, 0x68, val); + + pci_read_config_dword(dev, 0x68, &val); + if (val & 0x80) { + force_hpet_address = (val & ~0x3ff); + printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n", + force_hpet_address); + cached_dev = dev; + force_hpet_resume_type = VT8237_FORCE_HPET_RESUME; + return; + } + + printk(KERN_DEBUG "Failed to force enable HPET\n"); +} + +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, + vt8237_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237, + vt8237_force_enable_hpet); + +/* + * Undocumented chipset feature taken from LinuxBIOS. + */ +static void nvidia_force_hpet_resume(void) +{ + pci_write_config_dword(cached_dev, 0x44, 0xfed00001); + printk(KERN_DEBUG "Force enabled HPET at resume\n"); +} + +static void nvidia_force_enable_hpet(struct pci_dev *dev) +{ + u32 uninitialized_var(val); + + if (!hpet_force_user || hpet_address || force_hpet_address) + return; + + pci_write_config_dword(dev, 0x44, 0xfed00001); + pci_read_config_dword(dev, 0x44, &val); + force_hpet_address = val & 0xfffffffe; + force_hpet_resume_type = NVIDIA_FORCE_HPET_RESUME; + printk(KERN_DEBUG "Force enabled HPET at base address 0x%lx\n", + force_hpet_address); + cached_dev = dev; + return; +} + +/* ISA Bridges */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0050, + nvidia_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0051, + nvidia_force_enable_hpet); + +/* LPC bridges */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0360, + nvidia_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0361, + nvidia_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0362, + nvidia_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0363, + nvidia_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0364, + nvidia_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0365, + nvidia_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0366, + nvidia_force_enable_hpet); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x0367, + nvidia_force_enable_hpet); void force_hpet_resume(void) { @@ -246,6 +381,12 @@ void force_hpet_resume(void) case OLD_ICH_FORCE_HPET_RESUME: return old_ich_force_hpet_resume(); + case VT8237_FORCE_HPET_RESUME: + return vt8237_force_hpet_resume(); + + case NVIDIA_FORCE_HPET_RESUME: + return nvidia_force_hpet_resume(); + default: break; } diff --git a/arch/x86/kernel/reboot_64.c b/arch/x86/kernel/reboot_64.c index 368db2b9c5a..71b13c5f581 100644 --- a/arch/x86/kernel/reboot_64.c +++ b/arch/x86/kernel/reboot_64.c @@ -11,12 +11,13 @@ #include <linux/sched.h> #include <asm/io.h> #include <asm/delay.h> +#include <asm/desc.h> #include <asm/hw_irq.h> #include <asm/system.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/apic.h> -#include <asm/iommu.h> +#include <asm/gart.h> /* * Power off function, if any @@ -136,7 +137,7 @@ void machine_emergency_restart(void) } case BOOT_TRIPLE: - __asm__ __volatile__("lidt (%0)": :"r" (&no_idt)); + load_idt((const struct desc_ptr *)&no_idt); __asm__ __volatile__("int3"); reboot_type = BOOT_KBD; diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c index 8b30b26ad06..1a07bbea7be 100644 --- a/arch/x86/kernel/reboot_fixups_32.c +++ b/arch/x86/kernel/reboot_fixups_32.c @@ -12,6 +12,7 @@ #include <linux/interrupt.h> #include <asm/reboot_fixups.h> #include <asm/msr.h> +#include <asm/geode.h> static void cs5530a_warm_reset(struct pci_dev *dev) { @@ -24,11 +25,8 @@ static void cs5530a_warm_reset(struct pci_dev *dev) static void cs5536_warm_reset(struct pci_dev *dev) { - /* - * 6.6.2.12 Soft Reset (DIVIL_SOFT_RESET) - * writing 1 to the LSB of this MSR causes a hard reset. - */ - wrmsrl(0x51400017, 1ULL); + /* writing 1 to the LSB of this MSR causes a hard reset */ + wrmsrl(MSR_DIVIL_SOFT_RESET, 1ULL); udelay(50); /* shouldn't get here but be safe and spin a while */ } diff --git a/arch/x86/kernel/setup64.c b/arch/x86/kernel/setup64.c index 1200aaac403..3558ac78c92 100644 --- a/arch/x86/kernel/setup64.c +++ b/arch/x86/kernel/setup64.c @@ -11,7 +11,6 @@ #include <linux/bootmem.h> #include <linux/bitops.h> #include <linux/module.h> -#include <asm/bootsetup.h> #include <asm/pda.h> #include <asm/pgtable.h> #include <asm/processor.h> @@ -23,8 +22,9 @@ #include <asm/percpu.h> #include <asm/proto.h> #include <asm/sections.h> +#include <asm/setup.h> -char x86_boot_params[BOOT_PARAM_SIZE] __initdata; +struct boot_params __initdata boot_params; cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE; @@ -185,6 +185,12 @@ void __cpuinit check_efer(void) unsigned long kernel_eflags; /* + * Copies of the original ist values from the tss are only accessed during + * debugging, no special alignment required. + */ +DEFINE_PER_CPU(struct orig_ist, orig_ist); + +/* * cpu_init() initializes state that is per-CPU. Some data is already * initialized (naturally) in the bootstrap process, such as the GDT * and IDT. We reload them nevertheless, this function acts as a @@ -224,8 +230,8 @@ void __cpuinit cpu_init (void) memcpy(cpu_gdt(cpu), cpu_gdt_table, GDT_SIZE); cpu_gdt_descr[cpu].size = GDT_SIZE; - asm volatile("lgdt %0" :: "m" (cpu_gdt_descr[cpu])); - asm volatile("lidt %0" :: "m" (idt_descr)); + load_gdt((const struct desc_ptr *)&cpu_gdt_descr[cpu]); + load_idt((const struct desc_ptr *)&idt_descr); memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8); syscall_init(); diff --git a/arch/x86/kernel/setup_32.c b/arch/x86/kernel/setup_32.c index c8e1bc38d42..e1e18c34c82 100644 --- a/arch/x86/kernel/setup_32.c +++ b/arch/x86/kernel/setup_32.c @@ -60,6 +60,7 @@ #include <asm/vmi.h> #include <setup_arch.h> #include <bios_ebda.h> +#include <asm/cacheflush.h> /* This value is set up by the early boot code to point to the value immediately after the boot time page tables. It contains a *physical* @@ -73,6 +74,7 @@ int disable_pse __devinitdata = 0; */ extern struct resource code_resource; extern struct resource data_resource; +extern struct resource bss_resource; /* cpu data as detected by the assembly code in head.S */ struct cpuinfo_x86 new_cpu_data __cpuinitdata = { 0, 0, 0, 0, -1, 1, 0, 0, -1 }; @@ -84,9 +86,6 @@ unsigned long mmu_cr4_features; /* for MCA, but anyone else can use it if they want */ unsigned int machine_id; -#ifdef CONFIG_MCA -EXPORT_SYMBOL(machine_id); -#endif unsigned int machine_submodel_id; unsigned int BIOS_revision; unsigned int mca_pentium_flag; @@ -137,10 +136,11 @@ EXPORT_SYMBOL(edd); */ static inline void copy_edd(void) { - memcpy(edd.mbr_signature, EDD_MBR_SIGNATURE, sizeof(edd.mbr_signature)); - memcpy(edd.edd_info, EDD_BUF, sizeof(edd.edd_info)); - edd.mbr_signature_nr = EDD_MBR_SIG_NR; - edd.edd_info_nr = EDD_NR; + memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer, + sizeof(edd.mbr_signature)); + memcpy(edd.edd_info, boot_params.eddbuf, sizeof(edd.edd_info)); + edd.mbr_signature_nr = boot_params.edd_mbr_sig_buf_entries; + edd.edd_info_nr = boot_params.eddbuf_entries; } #else static inline void copy_edd(void) @@ -377,6 +377,49 @@ extern unsigned long __init setup_memory(void); extern void zone_sizes_init(void); #endif /* !CONFIG_NEED_MULTIPLE_NODES */ +static inline unsigned long long get_total_mem(void) +{ + unsigned long long total; + + total = max_low_pfn - min_low_pfn; +#ifdef CONFIG_HIGHMEM + total += highend_pfn - highstart_pfn; +#endif + + return total << PAGE_SHIFT; +} + +#ifdef CONFIG_KEXEC +static void __init reserve_crashkernel(void) +{ + unsigned long long total_mem; + unsigned long long crash_size, crash_base; + int ret; + + total_mem = get_total_mem(); + + ret = parse_crashkernel(boot_command_line, total_mem, + &crash_size, &crash_base); + if (ret == 0 && crash_size > 0) { + if (crash_base > 0) { + printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " + "for crashkernel (System RAM: %ldMB)\n", + (unsigned long)(crash_size >> 20), + (unsigned long)(crash_base >> 20), + (unsigned long)(total_mem >> 20)); + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; + reserve_bootmem(crash_base, crash_size); + } else + printk(KERN_INFO "crashkernel reservation failed - " + "you have to specify a base address\n"); + } +} +#else +static inline void __init reserve_crashkernel(void) +{} +#endif + void __init setup_bootmem_allocator(void) { unsigned long bootmap_size; @@ -434,26 +477,25 @@ void __init setup_bootmem_allocator(void) #endif numa_kva_reserve(); #ifdef CONFIG_BLK_DEV_INITRD - if (LOADER_TYPE && INITRD_START) { - if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) { - reserve_bootmem(INITRD_START, INITRD_SIZE); - initrd_start = INITRD_START + PAGE_OFFSET; - initrd_end = initrd_start+INITRD_SIZE; - } - else { + if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) { + unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; + unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; + unsigned long ramdisk_end = ramdisk_image + ramdisk_size; + unsigned long end_of_lowmem = max_low_pfn << PAGE_SHIFT; + + if (ramdisk_end <= end_of_lowmem) { + reserve_bootmem(ramdisk_image, ramdisk_size); + initrd_start = ramdisk_image + PAGE_OFFSET; + initrd_end = initrd_start+ramdisk_size; + } else { printk(KERN_ERR "initrd extends beyond end of memory " - "(0x%08lx > 0x%08lx)\ndisabling initrd\n", - INITRD_START + INITRD_SIZE, - max_low_pfn << PAGE_SHIFT); + "(0x%08lx > 0x%08lx)\ndisabling initrd\n", + ramdisk_end, end_of_lowmem); initrd_start = 0; } } #endif -#ifdef CONFIG_KEXEC - if (crashk_res.start != crashk_res.end) - reserve_bootmem(crashk_res.start, - crashk_res.end - crashk_res.start + 1); -#endif + reserve_crashkernel(); } /* @@ -512,28 +554,29 @@ void __init setup_arch(char **cmdline_p) * the system table is valid. If not, then initialize normally. */ #ifdef CONFIG_EFI - if ((LOADER_TYPE == 0x50) && EFI_SYSTAB) + if ((boot_params.hdr.type_of_loader == 0x50) && + boot_params.efi_info.efi_systab) efi_enabled = 1; #endif - ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV); - screen_info = SCREEN_INFO; - edid_info = EDID_INFO; - apm_info.bios = APM_BIOS_INFO; - ist_info = IST_INFO; - saved_videomode = VIDEO_MODE; - if( SYS_DESC_TABLE.length != 0 ) { - set_mca_bus(SYS_DESC_TABLE.table[3] & 0x2); - machine_id = SYS_DESC_TABLE.table[0]; - machine_submodel_id = SYS_DESC_TABLE.table[1]; - BIOS_revision = SYS_DESC_TABLE.table[2]; + ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); + screen_info = boot_params.screen_info; + edid_info = boot_params.edid_info; + apm_info.bios = boot_params.apm_bios_info; + ist_info = boot_params.ist_info; + saved_videomode = boot_params.hdr.vid_mode; + if( boot_params.sys_desc_table.length != 0 ) { + set_mca_bus(boot_params.sys_desc_table.table[3] & 0x2); + machine_id = boot_params.sys_desc_table.table[0]; + machine_submodel_id = boot_params.sys_desc_table.table[1]; + BIOS_revision = boot_params.sys_desc_table.table[2]; } - bootloader_type = LOADER_TYPE; + bootloader_type = boot_params.hdr.type_of_loader; #ifdef CONFIG_BLK_DEV_RAM - rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK; - rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0); - rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0); + rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK; + rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0); + rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0); #endif ARCH_SETUP if (efi_enabled) @@ -545,7 +588,7 @@ void __init setup_arch(char **cmdline_p) copy_edd(); - if (!MOUNT_ROOT_RDONLY) + if (!boot_params.hdr.root_flags) root_mountflags &= ~MS_RDONLY; init_mm.start_code = (unsigned long) _text; init_mm.end_code = (unsigned long) _etext; @@ -556,6 +599,8 @@ void __init setup_arch(char **cmdline_p) code_resource.end = virt_to_phys(_etext)-1; data_resource.start = virt_to_phys(_etext); data_resource.end = virt_to_phys(_edata)-1; + bss_resource.start = virt_to_phys(&__bss_start); + bss_resource.end = virt_to_phys(&__bss_stop)-1; parse_early_param(); @@ -580,7 +625,7 @@ void __init setup_arch(char **cmdline_p) /* * NOTE: before this point _nobody_ is allowed to allocate * any memory using the bootmem allocator. Although the - * alloctor is now initialised only the first 8Mb of the kernel + * allocator is now initialised only the first 8Mb of the kernel * virtual address space has been mapped. All allocations before * paging_init() has completed must use the alloc_bootmem_low_pages() * variant (which allocates DMA'able memory) and care must be taken @@ -617,9 +662,7 @@ void __init setup_arch(char **cmdline_p) #endif #ifdef CONFIG_PCI -#ifdef CONFIG_X86_IO_APIC - check_acpi_pci(); /* Checks more than just ACPI actually */ -#endif + early_quirks(); #endif #ifdef CONFIG_ACPI diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c index b7da90e79c7..238633d3d09 100644 --- a/arch/x86/kernel/setup_64.c +++ b/arch/x86/kernel/setup_64.c @@ -52,13 +52,13 @@ #include <asm/dma.h> #include <asm/mpspec.h> #include <asm/mmu_context.h> -#include <asm/bootsetup.h> #include <asm/proto.h> #include <asm/setup.h> #include <asm/mach_apic.h> #include <asm/numa.h> #include <asm/sections.h> #include <asm/dmi.h> +#include <asm/cacheflush.h> /* * Machine setup.. @@ -134,6 +134,12 @@ struct resource code_resource = { .end = 0, .flags = IORESOURCE_RAM, }; +struct resource bss_resource = { + .name = "Kernel bss", + .start = 0, + .end = 0, + .flags = IORESOURCE_RAM, +}; #ifdef CONFIG_PROC_VMCORE /* elfcorehdr= specifies the location of elf core header @@ -180,10 +186,11 @@ EXPORT_SYMBOL(edd); */ static inline void copy_edd(void) { - memcpy(edd.mbr_signature, EDD_MBR_SIGNATURE, sizeof(edd.mbr_signature)); - memcpy(edd.edd_info, EDD_BUF, sizeof(edd.edd_info)); - edd.mbr_signature_nr = EDD_MBR_SIG_NR; - edd.edd_info_nr = EDD_NR; + memcpy(edd.mbr_signature, boot_params.edd_mbr_sig_buffer, + sizeof(edd.mbr_signature)); + memcpy(edd.edd_info, boot_params.eddbuf, sizeof(edd.edd_info)); + edd.mbr_signature_nr = boot_params.edd_mbr_sig_buf_entries; + edd.edd_info_nr = boot_params.eddbuf_entries; } #else static inline void copy_edd(void) @@ -191,6 +198,37 @@ static inline void copy_edd(void) } #endif +#ifdef CONFIG_KEXEC +static void __init reserve_crashkernel(void) +{ + unsigned long long free_mem; + unsigned long long crash_size, crash_base; + int ret; + + free_mem = ((unsigned long long)max_low_pfn - min_low_pfn) << PAGE_SHIFT; + + ret = parse_crashkernel(boot_command_line, free_mem, + &crash_size, &crash_base); + if (ret == 0 && crash_size) { + if (crash_base > 0) { + printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " + "for crashkernel (System RAM: %ldMB)\n", + (unsigned long)(crash_size >> 20), + (unsigned long)(crash_base >> 20), + (unsigned long)(free_mem >> 20)); + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; + reserve_bootmem(crash_base, crash_size); + } else + printk(KERN_INFO "crashkernel reservation failed - " + "you have to specify a base address\n"); + } +} +#else +static inline void __init reserve_crashkernel(void) +{} +#endif + #define EBDA_ADDR_POINTER 0x40E unsigned __initdata ebda_addr; @@ -220,21 +258,21 @@ void __init setup_arch(char **cmdline_p) { printk(KERN_INFO "Command line: %s\n", boot_command_line); - ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV); - screen_info = SCREEN_INFO; - edid_info = EDID_INFO; - saved_video_mode = SAVED_VIDEO_MODE; - bootloader_type = LOADER_TYPE; + ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); + screen_info = boot_params.screen_info; + edid_info = boot_params.edid_info; + saved_video_mode = boot_params.hdr.vid_mode; + bootloader_type = boot_params.hdr.type_of_loader; #ifdef CONFIG_BLK_DEV_RAM - rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK; - rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0); - rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0); + rd_image_start = boot_params.hdr.ram_size & RAMDISK_IMAGE_START_MASK; + rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0); + rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0); #endif setup_memory_region(); copy_edd(); - if (!MOUNT_ROOT_RDONLY) + if (!boot_params.hdr.root_flags) root_mountflags &= ~MS_RDONLY; init_mm.start_code = (unsigned long) &_text; init_mm.end_code = (unsigned long) &_etext; @@ -245,6 +283,8 @@ void __init setup_arch(char **cmdline_p) code_resource.end = virt_to_phys(&_etext)-1; data_resource.start = virt_to_phys(&_etext); data_resource.end = virt_to_phys(&_edata)-1; + bss_resource.start = virt_to_phys(&__bss_start); + bss_resource.end = virt_to_phys(&__bss_stop)-1; early_identify_cpu(&boot_cpu_data); @@ -271,6 +311,11 @@ void __init setup_arch(char **cmdline_p) dmi_scan_machine(); +#ifdef CONFIG_SMP + /* setup to use the static apicid table during kernel startup */ + x86_cpu_to_apicid_ptr = (void *)&x86_cpu_to_apicid_init; +#endif + #ifdef CONFIG_ACPI /* * Initialize the ACPI boot-time table parser (gets the RSDP and SDT). @@ -339,28 +384,25 @@ void __init setup_arch(char **cmdline_p) */ find_smp_config(); #ifdef CONFIG_BLK_DEV_INITRD - if (LOADER_TYPE && INITRD_START) { - if (INITRD_START + INITRD_SIZE <= (end_pfn << PAGE_SHIFT)) { - reserve_bootmem_generic(INITRD_START, INITRD_SIZE); - initrd_start = INITRD_START + PAGE_OFFSET; - initrd_end = initrd_start+INITRD_SIZE; - } - else { + if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) { + unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; + unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; + unsigned long ramdisk_end = ramdisk_image + ramdisk_size; + unsigned long end_of_mem = end_pfn << PAGE_SHIFT; + + if (ramdisk_end <= end_of_mem) { + reserve_bootmem_generic(ramdisk_image, ramdisk_size); + initrd_start = ramdisk_image + PAGE_OFFSET; + initrd_end = initrd_start+ramdisk_size; + } else { printk(KERN_ERR "initrd extends beyond end of memory " - "(0x%08lx > 0x%08lx)\ndisabling initrd\n", - (unsigned long)(INITRD_START + INITRD_SIZE), - (unsigned long)(end_pfn << PAGE_SHIFT)); + "(0x%08lx > 0x%08lx)\ndisabling initrd\n", + ramdisk_end, end_of_mem); initrd_start = 0; } } #endif -#ifdef CONFIG_KEXEC - if (crashk_res.start != crashk_res.end) { - reserve_bootmem_generic(crashk_res.start, - crashk_res.end - crashk_res.start + 1); - } -#endif - + reserve_crashkernel(); paging_init(); #ifdef CONFIG_PCI @@ -526,7 +568,7 @@ static void __init amd_detect_cmp(struct cpuinfo_x86 *c) but in the same order as the HT nodeids. If that doesn't result in a usable node fall back to the path for the previous case. */ - int ht_nodeid = apicid - (cpu_data[0].phys_proc_id << bits); + int ht_nodeid = apicid - (cpu_data(0).phys_proc_id << bits); if (ht_nodeid >= 0 && apicid_to_node[ht_nodeid] != NUMA_NO_NODE) node = apicid_to_node[ht_nodeid]; @@ -601,7 +643,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) level = cpuid_eax(1); if (c->x86 == 15 && ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58)) set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability); - if (c->x86 == 0x10) + if (c->x86 == 0x10 || c->x86 == 0x11) set_bit(X86_FEATURE_REP_GOOD, &c->x86_capability); /* Enable workaround for FXSAVE leak */ @@ -850,6 +892,7 @@ void __cpuinit early_identify_cpu(struct cpuinfo_x86 *c) #ifdef CONFIG_SMP c->phys_proc_id = (cpuid_ebx(1) >> 24) & 0xff; + c->cpu_index = 0; #endif } @@ -956,6 +999,7 @@ void __cpuinit print_cpu_info(struct cpuinfo_x86 *c) static int show_cpuinfo(struct seq_file *m, void *v) { struct cpuinfo_x86 *c = v; + int cpu = 0; /* * These flag bits must match the definitions in <asm/cpufeature.h>. @@ -965,7 +1009,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) * applications want to get the raw CPUID data, they should access * /dev/cpu/<cpu_nr>/cpuid instead. */ - static char *x86_cap_flags[] = { + static const char *const x86_cap_flags[] = { /* Intel-defined */ "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce", "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov", @@ -996,7 +1040,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) /* Intel-defined (#2) */ "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est", "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL, - NULL, NULL, "dca", NULL, NULL, NULL, NULL, "popcnt", + NULL, NULL, "dca", "sse4_1", "sse4_2", NULL, NULL, "popcnt", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, /* VIA/Cyrix/Centaur-defined */ @@ -1006,10 +1050,10 @@ static int show_cpuinfo(struct seq_file *m, void *v) NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, /* AMD-defined (#2) */ - "lahf_lm", "cmp_legacy", "svm", "extapic", "cr8_legacy", - "altmovcr8", "abm", "sse4a", - "misalignsse", "3dnowprefetch", - "osvw", "ibs", NULL, NULL, NULL, NULL, + "lahf_lm", "cmp_legacy", "svm", "extapic", + "cr8_legacy", "abm", "sse4a", "misalignsse", + "3dnowprefetch", "osvw", "ibs", "sse5", + "skinit", "wdt", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, @@ -1019,7 +1063,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, }; - static char *x86_power_flags[] = { + static const char *const x86_power_flags[] = { "ts", /* temperature sensor */ "fid", /* frequency id control */ "vid", /* voltage id control */ @@ -1034,8 +1078,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) #ifdef CONFIG_SMP - if (!cpu_online(c-cpu_data)) + if (!cpu_online(c->cpu_index)) return 0; + cpu = c->cpu_index; #endif seq_printf(m,"processor\t: %u\n" @@ -1043,7 +1088,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) "cpu family\t: %d\n" "model\t\t: %d\n" "model name\t: %s\n", - (unsigned)(c-cpu_data), + (unsigned)cpu, c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown", c->x86, (int)c->x86_model, @@ -1055,7 +1100,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "stepping\t: unknown\n"); if (cpu_has(c,X86_FEATURE_TSC)) { - unsigned int freq = cpufreq_quick_get((unsigned)(c-cpu_data)); + unsigned int freq = cpufreq_quick_get((unsigned)cpu); if (!freq) freq = cpu_khz; seq_printf(m, "cpu MHz\t\t: %u.%03u\n", @@ -1068,9 +1113,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) #ifdef CONFIG_SMP if (smp_num_siblings * c->x86_max_cores > 1) { - int cpu = c - cpu_data; seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", cpus_weight(cpu_core_map[cpu])); + seq_printf(m, "siblings\t: %d\n", + cpus_weight(per_cpu(cpu_core_map, cpu))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); } @@ -1125,12 +1170,16 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { - return *pos < NR_CPUS ? cpu_data + *pos : NULL; + if (*pos == 0) /* just in case, cpu 0 is not the first */ + *pos = first_cpu(cpu_possible_map); + if ((*pos) < NR_CPUS && cpu_possible(*pos)) + return &cpu_data(*pos); + return NULL; } static void *c_next(struct seq_file *m, void *v, loff_t *pos) { - ++*pos; + *pos = next_cpu(*pos, cpu_possible_map); return c_start(m, pos); } diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c index d01d51fcce2..9bdd83022f5 100644 --- a/arch/x86/kernel/signal_32.c +++ b/arch/x86/kernel/signal_32.c @@ -200,8 +200,8 @@ badframe: if (show_unhandled_signals && printk_ratelimit()) printk("%s%s[%d] bad frame in sigreturn frame:%p eip:%lx" " esp:%lx oeax:%lx\n", - current->pid > 1 ? KERN_INFO : KERN_EMERG, - current->comm, current->pid, frame, regs->eip, + task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG, + current->comm, task_pid_nr(current), frame, regs->eip, regs->esp, regs->orig_eax); force_sig(SIGSEGV, current); @@ -385,7 +385,6 @@ static int setup_frame(int sig, struct k_sigaction *ka, regs->edx = (unsigned long) 0; regs->ecx = (unsigned long) 0; - set_fs(USER_DS); regs->xds = __USER_DS; regs->xes = __USER_DS; regs->xss = __USER_DS; @@ -479,7 +478,6 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, regs->edx = (unsigned long) &frame->info; regs->ecx = (unsigned long) &frame->uc; - set_fs(USER_DS); regs->xds = __USER_DS; regs->xes = __USER_DS; regs->xss = __USER_DS; @@ -596,7 +594,7 @@ static void fastcall do_signal(struct pt_regs *regs) signr = get_signal_to_deliver(&info, &ka, regs, NULL); if (signr > 0) { - /* Reenable any watchpoints before delivering the + /* Re-enable any watchpoints before delivering the * signal to user space. The processor register will * have been cleared if the watchpoint triggered * inside the kernel. diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index 683802bec41..ab086b0357f 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -410,7 +410,7 @@ static void do_signal(struct pt_regs *regs) signr = get_signal_to_deliver(&info, &ka, regs, NULL); if (signr > 0) { - /* Reenable any watchpoints before delivering the + /* Re-enable any watchpoints before delivering the * signal to user space. The processor register will * have been cleared if the watchpoint triggered * inside the kernel. diff --git a/arch/x86/kernel/smp_32.c b/arch/x86/kernel/smp_32.c index 2d35d850202..fcaa026eb80 100644 --- a/arch/x86/kernel/smp_32.c +++ b/arch/x86/kernel/smp_32.c @@ -69,7 +69,7 @@ * * B stepping CPUs may hang. There are hardware work arounds * for this. We warn about it in case your board doesn't have the work - * arounds. Basically thats so I can tell anyone with a B stepping + * arounds. Basically that's so I can tell anyone with a B stepping * CPU and SMP problems "tough". * * Specific items [From Pentium Processor Specification Update] @@ -273,7 +273,7 @@ void leave_mm(unsigned long cpu) * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask); * Stop ipi delivery for the old mm. This is not synchronized with * the other cpus, but smp_invalidate_interrupt ignore flush ipis - * for the wrong mm, and in the worst case we perform a superflous + * for the wrong mm, and in the worst case we perform a superfluous * tlb flush. * 1a2) set cpu_tlbstate to TLBSTATE_OK * Now the smp_invalidate_interrupt won't call leave_mm if cpu0 @@ -342,6 +342,7 @@ fastcall void smp_invalidate_interrupt(struct pt_regs *regs) smp_mb__after_clear_bit(); out: put_cpu_no_resched(); + __get_cpu_var(irq_stat).irq_tlb_count++; } void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm, @@ -609,7 +610,7 @@ static void stop_this_cpu (void * dummy) */ cpu_clear(smp_processor_id(), cpu_online_map); disable_local_APIC(); - if (cpu_data[smp_processor_id()].hlt_works_ok) + if (cpu_data(smp_processor_id()).hlt_works_ok) for(;;) halt(); for (;;); } @@ -640,6 +641,7 @@ static void native_smp_send_stop(void) fastcall void smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); + __get_cpu_var(irq_stat).irq_resched_count++; } fastcall void smp_call_function_interrupt(struct pt_regs *regs) @@ -660,6 +662,7 @@ fastcall void smp_call_function_interrupt(struct pt_regs *regs) */ irq_enter(); (*func)(info); + __get_cpu_var(irq_stat).irq_call_count++; irq_exit(); if (wait) { @@ -673,7 +676,7 @@ static int convert_apicid_to_cpu(int apic_id) int i; for (i = 0; i < NR_CPUS; i++) { - if (x86_cpu_to_apicid[i] == apic_id) + if (per_cpu(x86_cpu_to_apicid, i) == apic_id) return i; } return -1; @@ -705,3 +708,4 @@ struct smp_ops smp_ops = { .smp_send_reschedule = native_smp_send_reschedule, .smp_call_function_mask = native_smp_call_function_mask, }; +EXPORT_SYMBOL_GPL(smp_ops); diff --git a/arch/x86/kernel/smp_64.c b/arch/x86/kernel/smp_64.c index df4a82812ad..03fa6ed559c 100644 --- a/arch/x86/kernel/smp_64.c +++ b/arch/x86/kernel/smp_64.c @@ -163,6 +163,7 @@ asmlinkage void smp_invalidate_interrupt(struct pt_regs *regs) out: ack_APIC_irq(); cpu_clear(cpu, f->flush_cpumask); + add_pda(irq_tlb_count, 1); } static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, @@ -321,17 +322,27 @@ void unlock_ipi_call_lock(void) } /* - * this function sends a 'generic call function' IPI to one other CPU - * in the system. - * - * cpu is a standard Linux logical CPU number. + * this function sends a 'generic call function' IPI to all other CPU + * of the system defined in the mask. */ -static void -__smp_call_function_single(int cpu, void (*func) (void *info), void *info, - int nonatomic, int wait) + +static int +__smp_call_function_mask(cpumask_t mask, + void (*func)(void *), void *info, + int wait) { struct call_data_struct data; - int cpus = 1; + cpumask_t allbutself; + int cpus; + + allbutself = cpu_online_map; + cpu_clear(smp_processor_id(), allbutself); + + cpus_and(mask, mask, allbutself); + cpus = cpus_weight(mask); + + if (!cpus) + return 0; data.func = func; data.info = info; @@ -342,19 +353,55 @@ __smp_call_function_single(int cpu, void (*func) (void *info), void *info, call_data = &data; wmb(); - /* Send a message to all other CPUs and wait for them to respond */ - send_IPI_mask(cpumask_of_cpu(cpu), CALL_FUNCTION_VECTOR); + + /* Send a message to other CPUs */ + if (cpus_equal(mask, allbutself)) + send_IPI_allbutself(CALL_FUNCTION_VECTOR); + else + send_IPI_mask(mask, CALL_FUNCTION_VECTOR); /* Wait for response */ while (atomic_read(&data.started) != cpus) cpu_relax(); if (!wait) - return; + return 0; while (atomic_read(&data.finished) != cpus) cpu_relax(); + + return 0; +} +/** + * smp_call_function_mask(): Run a function on a set of other CPUs. + * @mask: The set of cpus to run on. Must not include the current cpu. + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait (atomically) until function has completed on other CPUs. + * + * Returns 0 on success, else a negative status code. + * + * If @wait is true, then returns once @func has returned; otherwise + * it returns just before the target cpu calls @func. + * + * You must not call this function with disabled interrupts or from a + * hardware interrupt handler or from a bottom half handler. + */ +int smp_call_function_mask(cpumask_t mask, + void (*func)(void *), void *info, + int wait) +{ + int ret; + + /* Can deadlock when called with interrupts disabled */ + WARN_ON(irqs_disabled()); + + spin_lock(&call_lock); + ret = __smp_call_function_mask(mask, func, info, wait); + spin_unlock(&call_lock); + return ret; } +EXPORT_SYMBOL(smp_call_function_mask); /* * smp_call_function_single - Run a function on a specific CPU @@ -373,6 +420,7 @@ int smp_call_function_single (int cpu, void (*func) (void *info), void *info, int nonatomic, int wait) { /* prevent preemption and reschedule on another processor */ + int ret; int me = get_cpu(); /* Can deadlock when called with interrupts disabled */ @@ -386,51 +434,14 @@ int smp_call_function_single (int cpu, void (*func) (void *info), void *info, return 0; } - spin_lock(&call_lock); - __smp_call_function_single(cpu, func, info, nonatomic, wait); - spin_unlock(&call_lock); + ret = smp_call_function_mask(cpumask_of_cpu(cpu), func, info, wait); + put_cpu(); - return 0; + return ret; } EXPORT_SYMBOL(smp_call_function_single); /* - * this function sends a 'generic call function' IPI to all other CPUs - * in the system. - */ -static void __smp_call_function (void (*func) (void *info), void *info, - int nonatomic, int wait) -{ - struct call_data_struct data; - int cpus = num_online_cpus()-1; - - if (!cpus) - return; - - data.func = func; - data.info = info; - atomic_set(&data.started, 0); - data.wait = wait; - if (wait) - atomic_set(&data.finished, 0); - - call_data = &data; - wmb(); - /* Send a message to all other CPUs and wait for them to respond */ - send_IPI_allbutself(CALL_FUNCTION_VECTOR); - - /* Wait for response */ - while (atomic_read(&data.started) != cpus) - cpu_relax(); - - if (!wait) - return; - - while (atomic_read(&data.finished) != cpus) - cpu_relax(); -} - -/* * smp_call_function - run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. @@ -448,10 +459,7 @@ static void __smp_call_function (void (*func) (void *info), void *info, int smp_call_function (void (*func) (void *info), void *info, int nonatomic, int wait) { - spin_lock(&call_lock); - __smp_call_function(func,info,nonatomic,wait); - spin_unlock(&call_lock); - return 0; + return smp_call_function_mask(cpu_online_map, func, info, wait); } EXPORT_SYMBOL(smp_call_function); @@ -478,7 +486,7 @@ void smp_send_stop(void) /* Don't deadlock on the call lock in panic */ nolock = !spin_trylock(&call_lock); local_irq_save(flags); - __smp_call_function(stop_this_cpu, NULL, 0, 0); + __smp_call_function_mask(cpu_online_map, stop_this_cpu, NULL, 0); if (!nolock) spin_unlock(&call_lock); disable_local_APIC(); @@ -493,6 +501,7 @@ void smp_send_stop(void) asmlinkage void smp_reschedule_interrupt(void) { ack_APIC_irq(); + add_pda(irq_resched_count, 1); } asmlinkage void smp_call_function_interrupt(void) @@ -514,6 +523,7 @@ asmlinkage void smp_call_function_interrupt(void) exit_idle(); irq_enter(); (*func)(info); + add_pda(irq_call_count, 1); irq_exit(); if (wait) { mb(); diff --git a/arch/x86/kernel/smpboot_32.c b/arch/x86/kernel/smpboot_32.c index e4f61d1c624..ef0f34ede1a 100644 --- a/arch/x86/kernel/smpboot_32.c +++ b/arch/x86/kernel/smpboot_32.c @@ -67,15 +67,15 @@ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); /* Last level cache ID of each logical CPU */ -int cpu_llc_id[NR_CPUS] __cpuinitdata = {[0 ... NR_CPUS-1] = BAD_APICID}; +DEFINE_PER_CPU(u8, cpu_llc_id) = BAD_APICID; /* representing HT siblings of each logical CPU */ -cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly; -EXPORT_SYMBOL(cpu_sibling_map); +DEFINE_PER_CPU(cpumask_t, cpu_sibling_map); +EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); /* representing HT and core siblings of each logical CPU */ -cpumask_t cpu_core_map[NR_CPUS] __read_mostly; -EXPORT_SYMBOL(cpu_core_map); +DEFINE_PER_CPU(cpumask_t, cpu_core_map); +EXPORT_PER_CPU_SYMBOL(cpu_core_map); /* bitmap of online cpus */ cpumask_t cpu_online_map __read_mostly; @@ -89,12 +89,20 @@ EXPORT_SYMBOL(cpu_possible_map); static cpumask_t smp_commenced_mask; /* Per CPU bogomips and other parameters */ -struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned; -EXPORT_SYMBOL(cpu_data); +DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); +EXPORT_PER_CPU_SYMBOL(cpu_info); -u8 x86_cpu_to_apicid[NR_CPUS] __read_mostly = - { [0 ... NR_CPUS-1] = 0xff }; -EXPORT_SYMBOL(x86_cpu_to_apicid); +/* + * The following static array is used during kernel startup + * and the x86_cpu_to_apicid_ptr contains the address of the + * array during this time. Is it zeroed when the per_cpu + * data area is removed. + */ +u8 x86_cpu_to_apicid_init[NR_CPUS] __initdata = + { [0 ... NR_CPUS-1] = BAD_APICID }; +void *x86_cpu_to_apicid_ptr; +DEFINE_PER_CPU(u8, x86_cpu_to_apicid) = BAD_APICID; +EXPORT_PER_CPU_SYMBOL(x86_cpu_to_apicid); u8 apicid_2_node[MAX_APICID]; @@ -102,8 +110,8 @@ u8 apicid_2_node[MAX_APICID]; * Trampoline 80x86 program as an array. */ -extern unsigned char trampoline_data []; -extern unsigned char trampoline_end []; +extern const unsigned char trampoline_data []; +extern const unsigned char trampoline_end []; static unsigned char *trampoline_base; static int trampoline_exec; @@ -118,7 +126,7 @@ DEFINE_PER_CPU(int, cpu_state) = { 0 }; * has made sure it's suitably aligned. */ -static unsigned long __devinit setup_trampoline(void) +static unsigned long __cpuinit setup_trampoline(void) { memcpy(trampoline_base, trampoline_data, trampoline_end - trampoline_data); return virt_to_phys(trampoline_base); @@ -150,9 +158,10 @@ void __init smp_alloc_memory(void) void __cpuinit smp_store_cpu_info(int id) { - struct cpuinfo_x86 *c = cpu_data + id; + struct cpuinfo_x86 *c = &cpu_data(id); *c = boot_cpu_data; + c->cpu_index = id; if (id!=0) identify_secondary_cpu(c); /* @@ -294,13 +303,13 @@ static int cpucount; /* maps the cpu to the sched domain representing multi-core */ cpumask_t cpu_coregroup_map(int cpu) { - struct cpuinfo_x86 *c = cpu_data + cpu; + struct cpuinfo_x86 *c = &cpu_data(cpu); /* * For perf, we return last level cache shared map. * And for power savings, we return cpu_core_map */ if (sched_mc_power_savings || sched_smt_power_savings) - return cpu_core_map[cpu]; + return per_cpu(cpu_core_map, cpu); else return c->llc_shared_map; } @@ -311,61 +320,61 @@ static cpumask_t cpu_sibling_setup_map; void __cpuinit set_cpu_sibling_map(int cpu) { int i; - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(cpu); cpu_set(cpu, cpu_sibling_setup_map); if (smp_num_siblings > 1) { for_each_cpu_mask(i, cpu_sibling_setup_map) { - if (c[cpu].phys_proc_id == c[i].phys_proc_id && - c[cpu].cpu_core_id == c[i].cpu_core_id) { - cpu_set(i, cpu_sibling_map[cpu]); - cpu_set(cpu, cpu_sibling_map[i]); - cpu_set(i, cpu_core_map[cpu]); - cpu_set(cpu, cpu_core_map[i]); - cpu_set(i, c[cpu].llc_shared_map); - cpu_set(cpu, c[i].llc_shared_map); + if (c->phys_proc_id == cpu_data(i).phys_proc_id && + c->cpu_core_id == cpu_data(i).cpu_core_id) { + cpu_set(i, per_cpu(cpu_sibling_map, cpu)); + cpu_set(cpu, per_cpu(cpu_sibling_map, i)); + cpu_set(i, per_cpu(cpu_core_map, cpu)); + cpu_set(cpu, per_cpu(cpu_core_map, i)); + cpu_set(i, c->llc_shared_map); + cpu_set(cpu, cpu_data(i).llc_shared_map); } } } else { - cpu_set(cpu, cpu_sibling_map[cpu]); + cpu_set(cpu, per_cpu(cpu_sibling_map, cpu)); } - cpu_set(cpu, c[cpu].llc_shared_map); + cpu_set(cpu, c->llc_shared_map); if (current_cpu_data.x86_max_cores == 1) { - cpu_core_map[cpu] = cpu_sibling_map[cpu]; - c[cpu].booted_cores = 1; + per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu); + c->booted_cores = 1; return; } for_each_cpu_mask(i, cpu_sibling_setup_map) { - if (cpu_llc_id[cpu] != BAD_APICID && - cpu_llc_id[cpu] == cpu_llc_id[i]) { - cpu_set(i, c[cpu].llc_shared_map); - cpu_set(cpu, c[i].llc_shared_map); + if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && + per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { + cpu_set(i, c->llc_shared_map); + cpu_set(cpu, cpu_data(i).llc_shared_map); } - if (c[cpu].phys_proc_id == c[i].phys_proc_id) { - cpu_set(i, cpu_core_map[cpu]); - cpu_set(cpu, cpu_core_map[i]); + if (c->phys_proc_id == cpu_data(i).phys_proc_id) { + cpu_set(i, per_cpu(cpu_core_map, cpu)); + cpu_set(cpu, per_cpu(cpu_core_map, i)); /* * Does this new cpu bringup a new core? */ - if (cpus_weight(cpu_sibling_map[cpu]) == 1) { + if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) { /* * for each core in package, increment * the booted_cores for this new cpu */ - if (first_cpu(cpu_sibling_map[i]) == i) - c[cpu].booted_cores++; + if (first_cpu(per_cpu(cpu_sibling_map, i)) == i) + c->booted_cores++; /* * increment the core count for all * the other cpus in this package */ if (i != cpu) - c[i].booted_cores++; - } else if (i != cpu && !c[cpu].booted_cores) - c[cpu].booted_cores = c[i].booted_cores; + cpu_data(i).booted_cores++; + } else if (i != cpu && !c->booted_cores) + c->booted_cores = cpu_data(i).booted_cores; } } } @@ -412,7 +421,7 @@ static void __cpuinit start_secondary(void *unused) /* * We need to hold call_lock, so there is no inconsistency * between the time smp_call_function() determines number of - * IPI receipients, and the time when the determination is made + * IPI recipients, and the time when the determination is made * for which cpus receive the IPI. Holding this * lock helps us to not include this cpu in a currently in progress * smp_call_function(). @@ -804,7 +813,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) irq_ctx_init(cpu); - x86_cpu_to_apicid[cpu] = apicid; + per_cpu(x86_cpu_to_apicid, cpu) = apicid; /* * This grunge runs the startup process for * the targeted processor. @@ -844,7 +853,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) /* number CPUs logically, starting from 1 (BSP is 0) */ Dprintk("OK.\n"); printk("CPU%d: ", cpu); - print_cpu_info(&cpu_data[cpu]); + print_cpu_info(&cpu_data(cpu)); Dprintk("CPU has booted.\n"); } else { boot_error= 1; @@ -866,7 +875,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu) cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */ cpucount--; } else { - x86_cpu_to_apicid[cpu] = apicid; + per_cpu(x86_cpu_to_apicid, cpu) = apicid; cpu_set(cpu, cpu_present_map); } @@ -915,7 +924,7 @@ static int __cpuinit __smp_prepare_cpu(int cpu) struct warm_boot_cpu_info info; int apicid, ret; - apicid = x86_cpu_to_apicid[cpu]; + apicid = per_cpu(x86_cpu_to_apicid, cpu); if (apicid == BAD_APICID) { ret = -ENODEV; goto exit; @@ -961,11 +970,11 @@ static void __init smp_boot_cpus(unsigned int max_cpus) */ smp_store_cpu_info(0); /* Final full version of the data */ printk("CPU%d: ", 0); - print_cpu_info(&cpu_data[0]); + print_cpu_info(&cpu_data(0)); boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID)); boot_cpu_logical_apicid = logical_smp_processor_id(); - x86_cpu_to_apicid[0] = boot_cpu_physical_apicid; + per_cpu(x86_cpu_to_apicid, 0) = boot_cpu_physical_apicid; current_thread_info()->cpu = 0; @@ -983,8 +992,8 @@ static void __init smp_boot_cpus(unsigned int max_cpus) printk(KERN_NOTICE "Local APIC not detected." " Using dummy APIC emulation.\n"); map_cpu_to_logical_apicid(); - cpu_set(0, cpu_sibling_map[0]); - cpu_set(0, cpu_core_map[0]); + cpu_set(0, per_cpu(cpu_sibling_map, 0)); + cpu_set(0, per_cpu(cpu_core_map, 0)); return; } @@ -1008,8 +1017,9 @@ static void __init smp_boot_cpus(unsigned int max_cpus) printk(KERN_ERR "... forcing use of dummy APIC emulation. (tell your hw vendor)\n"); smpboot_clear_io_apic_irqs(); phys_cpu_present_map = physid_mask_of_physid(0); - cpu_set(0, cpu_sibling_map[0]); - cpu_set(0, cpu_core_map[0]); + map_cpu_to_logical_apicid(); + cpu_set(0, per_cpu(cpu_sibling_map, 0)); + cpu_set(0, per_cpu(cpu_core_map, 0)); return; } @@ -1021,10 +1031,17 @@ static void __init smp_boot_cpus(unsigned int max_cpus) if (!max_cpus) { smp_found_config = 0; printk(KERN_INFO "SMP mode deactivated, forcing use of dummy APIC emulation.\n"); + + if (nmi_watchdog == NMI_LOCAL_APIC) { + printk(KERN_INFO "activating minimal APIC for NMI watchdog use.\n"); + connect_bsp_APIC(); + setup_local_APIC(); + } smpboot_clear_io_apic_irqs(); phys_cpu_present_map = physid_mask_of_physid(0); - cpu_set(0, cpu_sibling_map[0]); - cpu_set(0, cpu_core_map[0]); + map_cpu_to_logical_apicid(); + cpu_set(0, per_cpu(cpu_sibling_map, 0)); + cpu_set(0, per_cpu(cpu_core_map, 0)); return; } @@ -1076,7 +1093,7 @@ static void __init smp_boot_cpus(unsigned int max_cpus) Dprintk("Before bogomips.\n"); for (cpu = 0; cpu < NR_CPUS; cpu++) if (cpu_isset(cpu, cpu_callout_map)) - bogosum += cpu_data[cpu].loops_per_jiffy; + bogosum += cpu_data(cpu).loops_per_jiffy; printk(KERN_INFO "Total of %d processors activated (%lu.%02lu BogoMIPS).\n", cpucount+1, @@ -1102,16 +1119,16 @@ static void __init smp_boot_cpus(unsigned int max_cpus) Dprintk("Boot done.\n"); /* - * construct cpu_sibling_map[], so that we can tell sibling CPUs + * construct cpu_sibling_map, so that we can tell sibling CPUs * efficiently. */ for (cpu = 0; cpu < NR_CPUS; cpu++) { - cpus_clear(cpu_sibling_map[cpu]); - cpus_clear(cpu_core_map[cpu]); + cpus_clear(per_cpu(cpu_sibling_map, cpu)); + cpus_clear(per_cpu(cpu_core_map, cpu)); } - cpu_set(0, cpu_sibling_map[0]); - cpu_set(0, cpu_core_map[0]); + cpu_set(0, per_cpu(cpu_sibling_map, 0)); + cpu_set(0, per_cpu(cpu_core_map, 0)); smpboot_setup_io_apic(); @@ -1146,23 +1163,23 @@ void __init native_smp_prepare_boot_cpu(void) void remove_siblinginfo(int cpu) { int sibling; - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(cpu); - for_each_cpu_mask(sibling, cpu_core_map[cpu]) { - cpu_clear(cpu, cpu_core_map[sibling]); - /* + for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) { + cpu_clear(cpu, per_cpu(cpu_core_map, sibling)); + /*/ * last thread sibling in this cpu core going down */ - if (cpus_weight(cpu_sibling_map[cpu]) == 1) - c[sibling].booted_cores--; + if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) + cpu_data(sibling).booted_cores--; } - for_each_cpu_mask(sibling, cpu_sibling_map[cpu]) - cpu_clear(cpu, cpu_sibling_map[sibling]); - cpus_clear(cpu_sibling_map[cpu]); - cpus_clear(cpu_core_map[cpu]); - c[cpu].phys_proc_id = 0; - c[cpu].cpu_core_id = 0; + for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu)) + cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling)); + cpus_clear(per_cpu(cpu_sibling_map, cpu)); + cpus_clear(per_cpu(cpu_core_map, cpu)); + c->phys_proc_id = 0; + c->cpu_core_id = 0; cpu_clear(cpu, cpu_sibling_setup_map); } diff --git a/arch/x86/kernel/smpboot_64.c b/arch/x86/kernel/smpboot_64.c index 720a7d1f886..500670c93d8 100644 --- a/arch/x86/kernel/smpboot_64.c +++ b/arch/x86/kernel/smpboot_64.c @@ -65,7 +65,7 @@ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); /* Last level cache ID of each logical CPU */ -u8 cpu_llc_id[NR_CPUS] __cpuinitdata = {[0 ... NR_CPUS-1] = BAD_APICID}; +DEFINE_PER_CPU(u8, cpu_llc_id) = BAD_APICID; /* Bitmask of currently online CPUs */ cpumask_t cpu_online_map __read_mostly; @@ -84,26 +84,26 @@ cpumask_t cpu_possible_map; EXPORT_SYMBOL(cpu_possible_map); /* Per CPU bogomips and other parameters */ -struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned; -EXPORT_SYMBOL(cpu_data); +DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); +EXPORT_PER_CPU_SYMBOL(cpu_info); /* Set when the idlers are all forked */ int smp_threads_ready; /* representing HT siblings of each logical CPU */ -cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly; -EXPORT_SYMBOL(cpu_sibling_map); +DEFINE_PER_CPU(cpumask_t, cpu_sibling_map); +EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); /* representing HT and core siblings of each logical CPU */ -cpumask_t cpu_core_map[NR_CPUS] __read_mostly; -EXPORT_SYMBOL(cpu_core_map); +DEFINE_PER_CPU(cpumask_t, cpu_core_map); +EXPORT_PER_CPU_SYMBOL(cpu_core_map); /* * Trampoline 80x86 program as an array. */ -extern unsigned char trampoline_data[]; -extern unsigned char trampoline_end[]; +extern const unsigned char trampoline_data[]; +extern const unsigned char trampoline_end[]; /* State of each CPU */ DEFINE_PER_CPU(int, cpu_state) = { 0 }; @@ -138,9 +138,10 @@ static unsigned long __cpuinit setup_trampoline(void) static void __cpuinit smp_store_cpu_info(int id) { - struct cpuinfo_x86 *c = cpu_data + id; + struct cpuinfo_x86 *c = &cpu_data(id); *c = boot_cpu_data; + c->cpu_index = id; identify_cpu(c); print_cpu_info(c); } @@ -237,13 +238,13 @@ void __cpuinit smp_callin(void) /* maps the cpu to the sched domain representing multi-core */ cpumask_t cpu_coregroup_map(int cpu) { - struct cpuinfo_x86 *c = cpu_data + cpu; + struct cpuinfo_x86 *c = &cpu_data(cpu); /* * For perf, we return last level cache shared map. * And for power savings, we return cpu_core_map */ if (sched_mc_power_savings || sched_smt_power_savings) - return cpu_core_map[cpu]; + return per_cpu(cpu_core_map, cpu); else return c->llc_shared_map; } @@ -254,61 +255,61 @@ static cpumask_t cpu_sibling_setup_map; static inline void set_cpu_sibling_map(int cpu) { int i; - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(cpu); cpu_set(cpu, cpu_sibling_setup_map); if (smp_num_siblings > 1) { for_each_cpu_mask(i, cpu_sibling_setup_map) { - if (c[cpu].phys_proc_id == c[i].phys_proc_id && - c[cpu].cpu_core_id == c[i].cpu_core_id) { - cpu_set(i, cpu_sibling_map[cpu]); - cpu_set(cpu, cpu_sibling_map[i]); - cpu_set(i, cpu_core_map[cpu]); - cpu_set(cpu, cpu_core_map[i]); - cpu_set(i, c[cpu].llc_shared_map); - cpu_set(cpu, c[i].llc_shared_map); + if (c->phys_proc_id == cpu_data(i).phys_proc_id && + c->cpu_core_id == cpu_data(i).cpu_core_id) { + cpu_set(i, per_cpu(cpu_sibling_map, cpu)); + cpu_set(cpu, per_cpu(cpu_sibling_map, i)); + cpu_set(i, per_cpu(cpu_core_map, cpu)); + cpu_set(cpu, per_cpu(cpu_core_map, i)); + cpu_set(i, c->llc_shared_map); + cpu_set(cpu, cpu_data(i).llc_shared_map); } } } else { - cpu_set(cpu, cpu_sibling_map[cpu]); + cpu_set(cpu, per_cpu(cpu_sibling_map, cpu)); } - cpu_set(cpu, c[cpu].llc_shared_map); + cpu_set(cpu, c->llc_shared_map); if (current_cpu_data.x86_max_cores == 1) { - cpu_core_map[cpu] = cpu_sibling_map[cpu]; - c[cpu].booted_cores = 1; + per_cpu(cpu_core_map, cpu) = per_cpu(cpu_sibling_map, cpu); + c->booted_cores = 1; return; } for_each_cpu_mask(i, cpu_sibling_setup_map) { - if (cpu_llc_id[cpu] != BAD_APICID && - cpu_llc_id[cpu] == cpu_llc_id[i]) { - cpu_set(i, c[cpu].llc_shared_map); - cpu_set(cpu, c[i].llc_shared_map); + if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && + per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { + cpu_set(i, c->llc_shared_map); + cpu_set(cpu, cpu_data(i).llc_shared_map); } - if (c[cpu].phys_proc_id == c[i].phys_proc_id) { - cpu_set(i, cpu_core_map[cpu]); - cpu_set(cpu, cpu_core_map[i]); + if (c->phys_proc_id == cpu_data(i).phys_proc_id) { + cpu_set(i, per_cpu(cpu_core_map, cpu)); + cpu_set(cpu, per_cpu(cpu_core_map, i)); /* * Does this new cpu bringup a new core? */ - if (cpus_weight(cpu_sibling_map[cpu]) == 1) { + if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) { /* * for each core in package, increment * the booted_cores for this new cpu */ - if (first_cpu(cpu_sibling_map[i]) == i) - c[cpu].booted_cores++; + if (first_cpu(per_cpu(cpu_sibling_map, i)) == i) + c->booted_cores++; /* * increment the core count for all * the other cpus in this package */ if (i != cpu) - c[i].booted_cores++; - } else if (i != cpu && !c[cpu].booted_cores) - c[cpu].booted_cores = c[i].booted_cores; + cpu_data(i).booted_cores++; + } else if (i != cpu && !c->booted_cores) + c->booted_cores = cpu_data(i).booted_cores; } } } @@ -350,7 +351,7 @@ void __cpuinit start_secondary(void) /* * We need to hold call_lock, so there is no inconsistency * between the time smp_call_function() determines number of - * IPI receipients, and the time when the determination is made + * IPI recipients, and the time when the determination is made * for which cpus receive the IPI in genapic_flat.c. Holding this * lock helps us to not include this cpu in a currently in progress * smp_call_function(). @@ -387,7 +388,7 @@ static void inquire_remote_apic(int apicid) printk(KERN_INFO "Inquiring remote APIC #%d...\n", apicid); - for (i = 0; i < sizeof(regs) / sizeof(*regs); i++) { + for (i = 0; i < ARRAY_SIZE(regs); i++) { printk("... APIC #%d %s: ", apicid, names[i]); /* @@ -694,8 +695,7 @@ do_rest: clear_node_cpumask(cpu); /* was set by numa_add_cpu */ cpu_clear(cpu, cpu_present_map); cpu_clear(cpu, cpu_possible_map); - x86_cpu_to_apicid[cpu] = BAD_APICID; - x86_cpu_to_log_apicid[cpu] = BAD_APICID; + per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; return -EIO; } @@ -735,8 +735,8 @@ static __init void disable_smp(void) phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id); else phys_cpu_present_map = physid_mask_of_physid(0); - cpu_set(0, cpu_sibling_map[0]); - cpu_set(0, cpu_core_map[0]); + cpu_set(0, per_cpu(cpu_sibling_map, 0)); + cpu_set(0, per_cpu(cpu_core_map, 0)); } #ifdef CONFIG_HOTPLUG_CPU @@ -842,6 +842,26 @@ static int __init smp_sanity_check(unsigned max_cpus) } /* + * Copy apicid's found by MP_processor_info from initial array to the per cpu + * data area. The x86_cpu_to_apicid_init array is then expendable and the + * x86_cpu_to_apicid_ptr is zeroed indicating that the static array is no + * longer available. + */ +void __init smp_set_apicids(void) +{ + int cpu; + + for_each_cpu_mask(cpu, cpu_possible_map) { + if (per_cpu_offset(cpu)) + per_cpu(x86_cpu_to_apicid, cpu) = + x86_cpu_to_apicid_init[cpu]; + } + + /* indicate the static array will be going away soon */ + x86_cpu_to_apicid_ptr = NULL; +} + +/* * Prepare for SMP bootup. The MP table or ACPI has been read * earlier. Just do some sanity checking here and enable APIC mode. */ @@ -850,6 +870,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) nmi_watchdog_default(); current_cpu_data = boot_cpu_data; current_thread_info()->cpu = 0; /* needed? */ + smp_set_apicids(); set_cpu_sibling_map(0); if (smp_sanity_check(max_cpus) < 0) { @@ -969,23 +990,23 @@ void __init smp_cpus_done(unsigned int max_cpus) static void remove_siblinginfo(int cpu) { int sibling; - struct cpuinfo_x86 *c = cpu_data; + struct cpuinfo_x86 *c = &cpu_data(cpu); - for_each_cpu_mask(sibling, cpu_core_map[cpu]) { - cpu_clear(cpu, cpu_core_map[sibling]); + for_each_cpu_mask(sibling, per_cpu(cpu_core_map, cpu)) { + cpu_clear(cpu, per_cpu(cpu_core_map, sibling)); /* * last thread sibling in this cpu core going down */ - if (cpus_weight(cpu_sibling_map[cpu]) == 1) - c[sibling].booted_cores--; + if (cpus_weight(per_cpu(cpu_sibling_map, cpu)) == 1) + cpu_data(sibling).booted_cores--; } - for_each_cpu_mask(sibling, cpu_sibling_map[cpu]) - cpu_clear(cpu, cpu_sibling_map[sibling]); - cpus_clear(cpu_sibling_map[cpu]); - cpus_clear(cpu_core_map[cpu]); - c[cpu].phys_proc_id = 0; - c[cpu].cpu_core_id = 0; + for_each_cpu_mask(sibling, per_cpu(cpu_sibling_map, cpu)) + cpu_clear(cpu, per_cpu(cpu_sibling_map, sibling)); + cpus_clear(per_cpu(cpu_sibling_map, cpu)); + cpus_clear(per_cpu(cpu_core_map, cpu)); + c->phys_proc_id = 0; + c->cpu_core_id = 0; cpu_clear(cpu, cpu_sibling_setup_map); } diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 413e527cdeb..6fa6cf036c7 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -33,7 +33,7 @@ static void save_stack_address(void *data, unsigned long addr) trace->entries[trace->nr_entries++] = addr; } -static struct stacktrace_ops save_stack_ops = { +static const struct stacktrace_ops save_stack_ops = { .warning = save_stack_warning, .warning_symbol = save_stack_warning_symbol, .stack = save_stack_stack, diff --git a/arch/x86/kernel/summit_32.c b/arch/x86/kernel/summit_32.c index 91c7acc8d99..72f46340159 100644 --- a/arch/x86/kernel/summit_32.c +++ b/arch/x86/kernel/summit_32.c @@ -64,7 +64,7 @@ static int __init setup_pci_node_map_for_wpeg(int wpeg_num, int last_bus) switch (rio_devs[wpeg_num]->type){ case CompatWPEG: - /* The Compatability Winnipeg controls the 2 legacy buses, + /* The Compatibility Winnipeg controls the 2 legacy buses, * the 66MHz PCI bus [2 slots] and the 2 "extra" buses in case * a PCI-PCI bridge card is used in either slot: total 5 buses. */ diff --git a/arch/x86/kernel/suspend_64.c b/arch/x86/kernel/suspend_64.c index 573c0a6e0ac..db284ef44d5 100644 --- a/arch/x86/kernel/suspend_64.c +++ b/arch/x86/kernel/suspend_64.c @@ -19,12 +19,6 @@ extern const void __nosave_begin, __nosave_end; struct saved_context saved_context; -unsigned long saved_context_eax, saved_context_ebx, saved_context_ecx, saved_context_edx; -unsigned long saved_context_esp, saved_context_ebp, saved_context_esi, saved_context_edi; -unsigned long saved_context_r08, saved_context_r09, saved_context_r10, saved_context_r11; -unsigned long saved_context_r12, saved_context_r13, saved_context_r14, saved_context_r15; -unsigned long saved_context_eflags; - void __save_processor_state(struct saved_context *ctxt) { kernel_fpu_begin(); @@ -32,9 +26,9 @@ void __save_processor_state(struct saved_context *ctxt) /* * descriptor tables */ - asm volatile ("sgdt %0" : "=m" (ctxt->gdt_limit)); - asm volatile ("sidt %0" : "=m" (ctxt->idt_limit)); - asm volatile ("str %0" : "=m" (ctxt->tr)); + store_gdt((struct desc_ptr *)&ctxt->gdt_limit); + store_idt((struct desc_ptr *)&ctxt->idt_limit); + store_tr(ctxt->tr); /* XMM0..XMM15 should be handled by kernel_fpu_begin(). */ /* @@ -91,8 +85,9 @@ void __restore_processor_state(struct saved_context *ctxt) * now restore the descriptor tables to their proper values * ltr is done i fix_processor_context(). */ - asm volatile ("lgdt %0" :: "m" (ctxt->gdt_limit)); - asm volatile ("lidt %0" :: "m" (ctxt->idt_limit)); + load_gdt((const struct desc_ptr *)&ctxt->gdt_limit); + load_idt((const struct desc_ptr *)&ctxt->idt_limit); + /* * segment registers @@ -123,7 +118,7 @@ void fix_processor_context(void) int cpu = smp_processor_id(); struct tss_struct *t = &per_cpu(init_tss, cpu); - set_tss_desc(cpu,t); /* This just modifies memory; should not be neccessary. But... This is neccessary, because 386 hardware has concept of busy TSS or some similar stupidity. */ + set_tss_desc(cpu,t); /* This just modifies memory; should not be necessary. But... This is necessary, because 386 hardware has concept of busy TSS or some similar stupidity. */ cpu_gdt(cpu)[GDT_ENTRY_TSS].type = 9; @@ -150,8 +145,22 @@ void fix_processor_context(void) /* Defined in arch/x86_64/kernel/suspend_asm.S */ extern int restore_image(void); +/* + * Address to jump to in the last phase of restore in order to get to the image + * kernel's text (this value is passed in the image header). + */ +unsigned long restore_jump_address; + +/* + * Value of the cr3 register from before the hibernation (this value is passed + * in the image header). + */ +unsigned long restore_cr3; + pgd_t *temp_level4_pgt; +void *relocated_restore_code; + static int res_phys_pud_init(pud_t *pud, unsigned long address, unsigned long end) { long i, j; @@ -175,7 +184,7 @@ static int res_phys_pud_init(pud_t *pud, unsigned long address, unsigned long en if (paddr >= end) break; - pe = _PAGE_NX | _PAGE_PSE | _KERNPG_TABLE | paddr; + pe = __PAGE_KERNEL_LARGE_EXEC | paddr; pe &= __supported_pte_mask; set_pmd(pmd, __pmd(pe)); } @@ -183,25 +192,42 @@ static int res_phys_pud_init(pud_t *pud, unsigned long address, unsigned long en return 0; } +static int res_kernel_text_pud_init(pud_t *pud, unsigned long start) +{ + pmd_t *pmd; + unsigned long paddr; + + pmd = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!pmd) + return -ENOMEM; + set_pud(pud + pud_index(start), __pud(__pa(pmd) | _KERNPG_TABLE)); + for (paddr = 0; paddr < KERNEL_TEXT_SIZE; pmd++, paddr += PMD_SIZE) { + unsigned long pe; + + pe = __PAGE_KERNEL_LARGE_EXEC | _PAGE_GLOBAL | paddr; + pe &= __supported_pte_mask; + set_pmd(pmd, __pmd(pe)); + } + + return 0; +} + static int set_up_temporary_mappings(void) { unsigned long start, end, next; + pud_t *pud; int error; temp_level4_pgt = (pgd_t *)get_safe_page(GFP_ATOMIC); if (!temp_level4_pgt) return -ENOMEM; - /* It is safe to reuse the original kernel mapping */ - set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map), - init_level4_pgt[pgd_index(__START_KERNEL_map)]); - /* Set up the direct mapping from scratch */ start = (unsigned long)pfn_to_kaddr(0); end = (unsigned long)pfn_to_kaddr(end_pfn); for (; start < end; start = next) { - pud_t *pud = (pud_t *)get_safe_page(GFP_ATOMIC); + pud = (pud_t *)get_safe_page(GFP_ATOMIC); if (!pud) return -ENOMEM; next = start + PGDIR_SIZE; @@ -212,7 +238,17 @@ static int set_up_temporary_mappings(void) set_pgd(temp_level4_pgt + pgd_index(start), mk_kernel_pgd(__pa(pud))); } - return 0; + + /* Set up the kernel text mapping from scratch */ + pud = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!pud) + return -ENOMEM; + error = res_kernel_text_pud_init(pud, __START_KERNEL_map); + if (!error) + set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map), + __pgd(__pa(pud) | _PAGE_TABLE)); + + return error; } int swsusp_arch_resume(void) @@ -222,6 +258,13 @@ int swsusp_arch_resume(void) /* We have got enough memory and from now on we cannot recover */ if ((error = set_up_temporary_mappings())) return error; + + relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC); + if (!relocated_restore_code) + return -ENOMEM; + memcpy(relocated_restore_code, &core_restore_code, + &restore_registers - &core_restore_code); + restore_image(); return 0; } @@ -236,4 +279,43 @@ int pfn_is_nosave(unsigned long pfn) unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT; return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn); } + +struct restore_data_record { + unsigned long jump_address; + unsigned long cr3; + unsigned long magic; +}; + +#define RESTORE_MAGIC 0x0123456789ABCDEFUL + +/** + * arch_hibernation_header_save - populate the architecture specific part + * of a hibernation image header + * @addr: address to save the data at + */ +int arch_hibernation_header_save(void *addr, unsigned int max_size) +{ + struct restore_data_record *rdr = addr; + + if (max_size < sizeof(struct restore_data_record)) + return -EOVERFLOW; + rdr->jump_address = restore_jump_address; + rdr->cr3 = restore_cr3; + rdr->magic = RESTORE_MAGIC; + return 0; +} + +/** + * arch_hibernation_header_restore - read the architecture specific data + * from the hibernation image header + * @addr: address to read the data from + */ +int arch_hibernation_header_restore(void *addr) +{ + struct restore_data_record *rdr = addr; + + restore_jump_address = rdr->jump_address; + restore_cr3 = rdr->cr3; + return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL; +} #endif /* CONFIG_HIBERNATION */ diff --git a/arch/x86/kernel/suspend_asm_64.S b/arch/x86/kernel/suspend_asm_64.S index 16d183f67bc..72f952103e5 100644 --- a/arch/x86/kernel/suspend_asm_64.S +++ b/arch/x86/kernel/suspend_asm_64.S @@ -2,8 +2,8 @@ * * Distribute under GPLv2. * - * swsusp_arch_resume may not use any stack, nor any variable that is - * not "NoSave" during copying pages: + * swsusp_arch_resume must not use any stack or any nonlocal variables while + * copying pages: * * Its rewriting one kernel image with another. What is stack in "old" * image could very well be data page in "new" image, and overwriting @@ -17,24 +17,31 @@ #include <asm/asm-offsets.h> ENTRY(swsusp_arch_suspend) + movq $saved_context, %rax + movq %rsp, pt_regs_rsp(%rax) + movq %rbp, pt_regs_rbp(%rax) + movq %rsi, pt_regs_rsi(%rax) + movq %rdi, pt_regs_rdi(%rax) + movq %rbx, pt_regs_rbx(%rax) + movq %rcx, pt_regs_rcx(%rax) + movq %rdx, pt_regs_rdx(%rax) + movq %r8, pt_regs_r8(%rax) + movq %r9, pt_regs_r9(%rax) + movq %r10, pt_regs_r10(%rax) + movq %r11, pt_regs_r11(%rax) + movq %r12, pt_regs_r12(%rax) + movq %r13, pt_regs_r13(%rax) + movq %r14, pt_regs_r14(%rax) + movq %r15, pt_regs_r15(%rax) + pushfq + popq pt_regs_eflags(%rax) - movq %rsp, saved_context_esp(%rip) - movq %rax, saved_context_eax(%rip) - movq %rbx, saved_context_ebx(%rip) - movq %rcx, saved_context_ecx(%rip) - movq %rdx, saved_context_edx(%rip) - movq %rbp, saved_context_ebp(%rip) - movq %rsi, saved_context_esi(%rip) - movq %rdi, saved_context_edi(%rip) - movq %r8, saved_context_r08(%rip) - movq %r9, saved_context_r09(%rip) - movq %r10, saved_context_r10(%rip) - movq %r11, saved_context_r11(%rip) - movq %r12, saved_context_r12(%rip) - movq %r13, saved_context_r13(%rip) - movq %r14, saved_context_r14(%rip) - movq %r15, saved_context_r15(%rip) - pushfq ; popq saved_context_eflags(%rip) + /* save the address of restore_registers */ + movq $restore_registers, %rax + movq %rax, restore_jump_address(%rip) + /* save cr3 */ + movq %cr3, %rax + movq %rax, restore_cr3(%rip) call swsusp_save ret @@ -54,7 +61,17 @@ ENTRY(restore_image) movq %rcx, %cr3; movq %rax, %cr4; # turn PGE back on + /* prepare to jump to the image kernel */ + movq restore_jump_address(%rip), %rax + movq restore_cr3(%rip), %rbx + + /* prepare to copy image data to their original locations */ movq restore_pblist(%rip), %rdx + movq relocated_restore_code(%rip), %rcx + jmpq *%rcx + + /* code below has been relocated to a safe page */ +ENTRY(core_restore_code) loop: testq %rdx, %rdx jz done @@ -62,7 +79,7 @@ loop: /* get addresses from the pbe and copy the page */ movq pbe_address(%rdx), %rsi movq pbe_orig_address(%rdx), %rdi - movq $512, %rcx + movq $(PAGE_SIZE >> 3), %rcx rep movsq @@ -70,10 +87,22 @@ loop: movq pbe_next(%rdx), %rdx jmp loop done: + /* jump to the restore_registers address from the image header */ + jmpq *%rax + /* + * NOTE: This assumes that the boot kernel's text mapping covers the + * image kernel's page containing restore_registers and the address of + * this page is the same as in the image kernel's text mapping (it + * should always be true, because the text mapping is linear, starting + * from 0, and is supposed to cover the entire kernel text for every + * kernel). + * + * code below belongs to the image kernel + */ + +ENTRY(restore_registers) /* go back to the original page tables */ - movq $(init_level4_pgt - __START_KERNEL_map), %rax - addq phys_base(%rip), %rax - movq %rax, %cr3 + movq %rbx, %cr3 /* Flush TLB, including "global" things (vmalloc) */ movq mmu_cr4_features(%rip), %rax @@ -84,27 +113,29 @@ done: movq %rcx, %cr3 movq %rax, %cr4; # turn PGE back on - movl $24, %eax - movl %eax, %ds - - movq saved_context_esp(%rip), %rsp - movq saved_context_ebp(%rip), %rbp - /* Don't restore %rax, it must be 0 anyway */ - movq saved_context_ebx(%rip), %rbx - movq saved_context_ecx(%rip), %rcx - movq saved_context_edx(%rip), %rdx - movq saved_context_esi(%rip), %rsi - movq saved_context_edi(%rip), %rdi - movq saved_context_r08(%rip), %r8 - movq saved_context_r09(%rip), %r9 - movq saved_context_r10(%rip), %r10 - movq saved_context_r11(%rip), %r11 - movq saved_context_r12(%rip), %r12 - movq saved_context_r13(%rip), %r13 - movq saved_context_r14(%rip), %r14 - movq saved_context_r15(%rip), %r15 - pushq saved_context_eflags(%rip) ; popfq + /* We don't restore %rax, it must be 0 anyway */ + movq $saved_context, %rax + movq pt_regs_rsp(%rax), %rsp + movq pt_regs_rbp(%rax), %rbp + movq pt_regs_rsi(%rax), %rsi + movq pt_regs_rdi(%rax), %rdi + movq pt_regs_rbx(%rax), %rbx + movq pt_regs_rcx(%rax), %rcx + movq pt_regs_rdx(%rax), %rdx + movq pt_regs_r8(%rax), %r8 + movq pt_regs_r9(%rax), %r9 + movq pt_regs_r10(%rax), %r10 + movq pt_regs_r11(%rax), %r11 + movq pt_regs_r12(%rax), %r12 + movq pt_regs_r13(%rax), %r13 + movq pt_regs_r14(%rax), %r14 + movq pt_regs_r15(%rax), %r15 + pushq pt_regs_eflags(%rax) + popfq xorq %rax, %rax + /* tell the hibernation core that we've just restored the memory */ + movq %rax, in_suspend(%rip) + ret diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c index f8bae9ba032..a86d26f036e 100644 --- a/arch/x86/kernel/sys_i386_32.c +++ b/arch/x86/kernel/sys_i386_32.c @@ -17,10 +17,10 @@ #include <linux/mman.h> #include <linux/file.h> #include <linux/utsname.h> +#include <linux/ipc.h> #include <asm/uaccess.h> #include <asm/unistd.h> -#include <asm/ipc.h> /* * sys_pipe() is the normal C calling standard for creating diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c index e3f2569b2c4..9e540fee700 100644 --- a/arch/x86/kernel/tce_64.c +++ b/arch/x86/kernel/tce_64.c @@ -40,9 +40,9 @@ static inline void flush_tce(void* tceaddr) { /* a single tce can't cross a cache line */ if (cpu_has_clflush) - asm volatile("clflush (%0)" :: "r" (tceaddr)); + clflush(tceaddr); else - asm volatile("wbinvd":::"memory"); + wbinvd(); } void tce_build(struct iommu_table *tbl, unsigned long index, diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index c25f23eb397..8caa0b77746 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -44,15 +44,15 @@ int arch_register_cpu(int num) * Also certain PCI quirks require not to enable hotplug control * for all CPU's. */ - if (num && enable_cpu_hotplug) +#ifdef CONFIG_HOTPLUG_CPU + if (num) cpu_devices[num].cpu.hotpluggable = 1; +#endif return register_cpu(&cpu_devices[num].cpu, num); } #ifdef CONFIG_HOTPLUG_CPU -int enable_cpu_hotplug = 1; - void arch_unregister_cpu(int num) { return unregister_cpu(&cpu_devices[num].cpu); } diff --git a/arch/x86/kernel/trampoline_32.S b/arch/x86/kernel/trampoline_32.S index f62815f8d06..9bcc1c6aca3 100644 --- a/arch/x86/kernel/trampoline_32.S +++ b/arch/x86/kernel/trampoline_32.S @@ -36,11 +36,11 @@ #include <asm/segment.h> #include <asm/page.h> -.data - /* We can free up trampoline after bootup if cpu hotplug is not supported. */ #ifndef CONFIG_HOTPLUG_CPU .section ".init.data","aw",@progbits +#else +.section .rodata,"a",@progbits #endif .code16 diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S index 607983b0d27..e30b67c6a9f 100644 --- a/arch/x86/kernel/trampoline_64.S +++ b/arch/x86/kernel/trampoline_64.S @@ -33,7 +33,12 @@ #include <asm/msr.h> #include <asm/segment.h> -.data +/* We can free up trampoline after bootup if cpu hotplug is not supported. */ +#ifndef CONFIG_HOTPLUG_CPU +.section .init.data, "aw", @progbits +#else +.section .rodata, "a", @progbits +#endif .code16 diff --git a/arch/x86/kernel/traps_32.c b/arch/x86/kernel/traps_32.c index 05c27ecaf2a..298d13ed3ab 100644 --- a/arch/x86/kernel/traps_32.c +++ b/arch/x86/kernel/traps_32.c @@ -63,6 +63,9 @@ int panic_on_unrecovered_nmi; +DECLARE_BITMAP(used_vectors, NR_VECTORS); +EXPORT_SYMBOL_GPL(used_vectors); + asmlinkage int system_call(void); /* Do we ignore FPU interrupts ? */ @@ -112,7 +115,7 @@ struct stack_frame { static inline unsigned long print_context_stack(struct thread_info *tinfo, unsigned long *stack, unsigned long ebp, - struct stacktrace_ops *ops, void *data) + const struct stacktrace_ops *ops, void *data) { #ifdef CONFIG_FRAME_POINTER struct stack_frame *frame = (struct stack_frame *)ebp; @@ -149,7 +152,7 @@ static inline unsigned long print_context_stack(struct thread_info *tinfo, void dump_trace(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, - struct stacktrace_ops *ops, void *data) + const struct stacktrace_ops *ops, void *data) { unsigned long ebp = 0; @@ -221,7 +224,7 @@ static void print_trace_address(void *data, unsigned long addr) touch_nmi_watchdog(); } -static struct stacktrace_ops print_trace_ops = { +static const struct stacktrace_ops print_trace_ops = { .warning = print_trace_warning, .warning_symbol = print_trace_warning_symbol, .stack = print_trace_stack, @@ -288,48 +291,24 @@ EXPORT_SYMBOL(dump_stack); void show_registers(struct pt_regs *regs) { int i; - int in_kernel = 1; - unsigned long esp; - unsigned short ss, gs; - - esp = (unsigned long) (®s->esp); - savesegment(ss, ss); - savesegment(gs, gs); - if (user_mode_vm(regs)) { - in_kernel = 0; - esp = regs->esp; - ss = regs->xss & 0xffff; - } + print_modules(); - printk(KERN_EMERG "CPU: %d\n" - KERN_EMERG "EIP: %04x:[<%08lx>] %s VLI\n" - KERN_EMERG "EFLAGS: %08lx (%s %.*s)\n", - smp_processor_id(), 0xffff & regs->xcs, regs->eip, - print_tainted(), regs->eflags, init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - print_symbol(KERN_EMERG "EIP is at %s\n", regs->eip); - printk(KERN_EMERG "eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n", - regs->eax, regs->ebx, regs->ecx, regs->edx); - printk(KERN_EMERG "esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n", - regs->esi, regs->edi, regs->ebp, esp); - printk(KERN_EMERG "ds: %04x es: %04x fs: %04x gs: %04x ss: %04x\n", - regs->xds & 0xffff, regs->xes & 0xffff, regs->xfs & 0xffff, gs, ss); + __show_registers(regs, 0); printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)", - TASK_COMM_LEN, current->comm, current->pid, + TASK_COMM_LEN, current->comm, task_pid_nr(current), current_thread_info(), current, task_thread_info(current)); /* * When in-kernel, we also print out the stack and code at the * time of the fault.. */ - if (in_kernel) { + if (!user_mode_vm(regs)) { u8 *eip; unsigned int code_prologue = code_bytes * 43 / 64; unsigned int code_len = code_bytes; unsigned char c; printk("\n" KERN_EMERG "Stack: "); - show_stack_log_lvl(NULL, regs, (unsigned long *)esp, KERN_EMERG); + show_stack_log_lvl(NULL, regs, ®s->esp, KERN_EMERG); printk(KERN_EMERG "Code: "); @@ -374,11 +353,11 @@ int is_valid_bugaddr(unsigned long eip) void die(const char * str, struct pt_regs * regs, long err) { static struct { - spinlock_t lock; + raw_spinlock_t lock; u32 lock_owner; int lock_owner_depth; } die = { - .lock = __SPIN_LOCK_UNLOCKED(die.lock), + .lock = __RAW_SPIN_LOCK_UNLOCKED, .lock_owner = -1, .lock_owner_depth = 0 }; @@ -389,40 +368,34 @@ void die(const char * str, struct pt_regs * regs, long err) if (die.lock_owner != raw_smp_processor_id()) { console_verbose(); - spin_lock_irqsave(&die.lock, flags); + __raw_spin_lock(&die.lock); + raw_local_save_flags(flags); die.lock_owner = smp_processor_id(); die.lock_owner_depth = 0; bust_spinlocks(1); } else - local_save_flags(flags); + raw_local_save_flags(flags); if (++die.lock_owner_depth < 3) { - int nl = 0; unsigned long esp; unsigned short ss; report_bug(regs->eip, regs); - printk(KERN_EMERG "%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter); + printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, + ++die_counter); #ifdef CONFIG_PREEMPT - printk(KERN_EMERG "PREEMPT "); - nl = 1; + printk("PREEMPT "); #endif #ifdef CONFIG_SMP - if (!nl) - printk(KERN_EMERG); printk("SMP "); - nl = 1; #endif #ifdef CONFIG_DEBUG_PAGEALLOC - if (!nl) - printk(KERN_EMERG); printk("DEBUG_PAGEALLOC"); - nl = 1; #endif - if (nl) - printk("\n"); + printk("\n"); + if (notify_die(DIE_OOPS, str, regs, err, current->thread.trap_no, SIGSEGV) != NOTIFY_STOP) { @@ -446,7 +419,8 @@ void die(const char * str, struct pt_regs * regs, long err) bust_spinlocks(0); die.lock_owner = -1; add_taint(TAINT_DIE); - spin_unlock_irqrestore(&die.lock, flags); + __raw_spin_unlock(&die.lock); + raw_local_irq_restore(flags); if (!regs) return; @@ -629,7 +603,7 @@ fastcall void __kprobes do_general_protection(struct pt_regs * regs, printk_ratelimit()) printk(KERN_INFO "%s[%d] general protection eip:%lx esp:%lx error:%lx\n", - current->comm, current->pid, + current->comm, task_pid_nr(current), regs->eip, regs->esp, error_code); force_sig(SIGSEGV, current); @@ -815,6 +789,8 @@ void restart_nmi(void) #ifdef CONFIG_KPROBES fastcall void __kprobes do_int3(struct pt_regs *regs, long error_code) { + trace_hardirqs_fixup(); + if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) return; @@ -1112,20 +1088,6 @@ asmlinkage void math_emulate(long arg) #endif /* CONFIG_MATH_EMULATION */ -#ifdef CONFIG_X86_F00F_BUG -void __init trap_init_f00f_bug(void) -{ - __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO); - - /* - * Update the IDT descriptor and reload the IDT so that - * it uses the read-only mapped virtual address. - */ - idt_descr.address = fix_to_virt(FIX_F00F_IDT); - load_idt(&idt_descr); -} -#endif - /* * This needs to use 'idt_table' rather than 'idt', and * thus use the _nonmapped_ version of the IDT, as the @@ -1163,6 +1125,8 @@ static void __init set_task_gate(unsigned int n, unsigned int gdt_entry) void __init trap_init(void) { + int i; + #ifdef CONFIG_EISA void __iomem *p = ioremap(0x0FFFD9, 4); if (readl(p) == 'E'+('I'<<8)+('S'<<16)+('A'<<24)) { @@ -1222,6 +1186,11 @@ void __init trap_init(void) set_system_gate(SYSCALL_VECTOR,&system_call); + /* Reserve all the builtin and the syscall vector. */ + for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++) + set_bit(i, used_vectors); + set_bit(SYSCALL_VECTOR, used_vectors); + /* * Should be a barrier for any external CPU state. */ diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c index bc7116acf8f..4a6bd4965f5 100644 --- a/arch/x86/kernel/traps_64.c +++ b/arch/x86/kernel/traps_64.c @@ -201,7 +201,7 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, #define MSG(txt) ops->warning(data, txt) /* - * x86-64 can have upto three kernel stacks: + * x86-64 can have up to three kernel stacks: * process stack * interrupt stack * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack @@ -215,7 +215,7 @@ static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack, - struct stacktrace_ops *ops, void *data) + const struct stacktrace_ops *ops, void *data) { const unsigned cpu = get_cpu(); unsigned long *irqstack_end = (unsigned long*)cpu_pda(cpu)->irqstackptr; @@ -336,7 +336,7 @@ static void print_trace_address(void *data, unsigned long addr) printk_address(addr); } -static struct stacktrace_ops print_trace_ops = { +static const struct stacktrace_ops print_trace_ops = { .warning = print_trace_warning, .warning_symbol = print_trace_warning_symbol, .stack = print_trace_stack, @@ -462,7 +462,7 @@ void out_of_line_bug(void) EXPORT_SYMBOL(out_of_line_bug); #endif -static DEFINE_SPINLOCK(die_lock); +static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED; static int die_owner = -1; static unsigned int die_nest_count; @@ -474,13 +474,13 @@ unsigned __kprobes long oops_begin(void) oops_enter(); /* racy, but better than risking deadlock. */ - local_irq_save(flags); + raw_local_irq_save(flags); cpu = smp_processor_id(); - if (!spin_trylock(&die_lock)) { + if (!__raw_spin_trylock(&die_lock)) { if (cpu == die_owner) /* nested oops. should stop eventually */; else - spin_lock(&die_lock); + __raw_spin_lock(&die_lock); } die_nest_count++; die_owner = cpu; @@ -494,12 +494,10 @@ void __kprobes oops_end(unsigned long flags) die_owner = -1; bust_spinlocks(0); die_nest_count--; - if (die_nest_count) - /* We still own the lock */ - local_irq_restore(flags); - else + if (!die_nest_count) /* Nest count reaches zero, release the lock. */ - spin_unlock_irqrestore(&die_lock, flags); + __raw_spin_unlock(&die_lock); + raw_local_irq_restore(flags); if (panic_on_oops) panic("Fatal exception"); oops_exit(); @@ -809,6 +807,8 @@ asmlinkage __kprobes void default_do_nmi(struct pt_regs *regs) /* runs on IST stack. */ asmlinkage void __kprobes do_int3(struct pt_regs * regs, long error_code) { + trace_hardirqs_fixup(); + if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) { return; } diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c index b85ad754f70..9ebc0dab66b 100644 --- a/arch/x86/kernel/tsc_32.c +++ b/arch/x86/kernel/tsc_32.c @@ -59,7 +59,7 @@ int check_tsc_unstable(void) } EXPORT_SYMBOL_GPL(check_tsc_unstable); -/* Accellerators for sched_clock() +/* Accelerators for sched_clock() * convert from cycles(64bits) => nanoseconds (64bits) * basic equation: * ns = cycles / (freq / ns_per_sec) @@ -74,7 +74,7 @@ EXPORT_SYMBOL_GPL(check_tsc_unstable); * And since SC is a constant power of two, we can convert the div * into a shift. * - * We can use khz divisor instead of mhz to keep a better percision, since + * We can use khz divisor instead of mhz to keep a better precision, since * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. * (mathieu.desnoyers@polymtl.ca) * @@ -131,38 +131,43 @@ unsigned long native_calculate_cpu_khz(void) { unsigned long long start, end; unsigned long count; - u64 delta64; + u64 delta64 = (u64)ULLONG_MAX; int i; unsigned long flags; local_irq_save(flags); - /* run 3 times to ensure the cache is warm */ + /* run 3 times to ensure the cache is warm and to get an accurate reading */ for (i = 0; i < 3; i++) { mach_prepare_counter(); rdtscll(start); mach_countup(&count); rdtscll(end); - } - /* - * Error: ECTCNEVERSET - * The CTC wasn't reliable: we got a hit on the very first read, - * or the CPU was so fast/slow that the quotient wouldn't fit in - * 32 bits.. - */ - if (count <= 1) - goto err; - delta64 = end - start; + /* + * Error: ECTCNEVERSET + * The CTC wasn't reliable: we got a hit on the very first read, + * or the CPU was so fast/slow that the quotient wouldn't fit in + * 32 bits.. + */ + if (count <= 1) + continue; + + /* cpu freq too slow: */ + if ((end - start) <= CALIBRATE_TIME_MSEC) + continue; + + /* + * We want the minimum time of all runs in case one of them + * is inaccurate due to SMI or other delay + */ + delta64 = min(delta64, (end - start)); + } - /* cpu freq too fast: */ + /* cpu freq too fast (or every run was bad): */ if (delta64 > (1ULL<<32)) goto err; - /* cpu freq too slow: */ - if (delta64 <= CALIBRATE_TIME_MSEC) - goto err; - delta64 += CALIBRATE_TIME_MSEC/2; /* round for do_div */ do_div(delta64,CALIBRATE_TIME_MSEC); @@ -181,8 +186,8 @@ int recalibrate_cpu_khz(void) if (cpu_has_tsc) { cpu_khz = calculate_cpu_khz(); tsc_khz = cpu_khz; - cpu_data[0].loops_per_jiffy = - cpufreq_scale(cpu_data[0].loops_per_jiffy, + cpu_data(0).loops_per_jiffy = + cpufreq_scale(cpu_data(0).loops_per_jiffy, cpu_khz_old, cpu_khz); return 0; } else @@ -215,7 +220,7 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) return 0; } ref_freq = freq->old; - loops_per_jiffy_ref = cpu_data[freq->cpu].loops_per_jiffy; + loops_per_jiffy_ref = cpu_data(freq->cpu).loops_per_jiffy; cpu_khz_ref = cpu_khz; } @@ -223,7 +228,7 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) || (val == CPUFREQ_RESUMECHANGE)) { if (!(freq->flags & CPUFREQ_CONST_LOOPS)) - cpu_data[freq->cpu].loops_per_jiffy = + cpu_data(freq->cpu).loops_per_jiffy = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new); @@ -349,10 +354,10 @@ __cpuinit int unsynchronized_tsc(void) static void __init check_geode_tsc_reliable(void) { - unsigned long val; + unsigned long res_low, res_high; - rdmsrl(MSR_GEODE_BUSCONT_CONF0, val); - if ((val & RTSC_SUSP)) + rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); + if (res_low & RTSC_SUSP) clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; } #else diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c index 9f22e542c37..9c70af45b42 100644 --- a/arch/x86/kernel/tsc_64.c +++ b/arch/x86/kernel/tsc_64.c @@ -73,13 +73,13 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, struct cpufreq_freqs *freq = data; unsigned long *lpj, dummy; - if (cpu_has(&cpu_data[freq->cpu], X86_FEATURE_CONSTANT_TSC)) + if (cpu_has(&cpu_data(freq->cpu), X86_FEATURE_CONSTANT_TSC)) return 0; lpj = &dummy; if (!(freq->flags & CPUFREQ_CONST_LOOPS)) #ifdef CONFIG_SMP - lpj = &cpu_data[freq->cpu].loops_per_jiffy; + lpj = &cpu_data(freq->cpu).loops_per_jiffy; #else lpj = &boot_cpu_data.loops_per_jiffy; #endif diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c index 18673e0f193..f02bad68aba 100644 --- a/arch/x86/kernel/vmi_32.c +++ b/arch/x86/kernel/vmi_32.c @@ -134,21 +134,21 @@ static unsigned vmi_patch(u8 type, u16 clobbers, void *insns, unsigned long eip, unsigned len) { switch (type) { - case PARAVIRT_PATCH(irq_disable): + case PARAVIRT_PATCH(pv_irq_ops.irq_disable): return patch_internal(VMI_CALL_DisableInterrupts, len, insns, eip); - case PARAVIRT_PATCH(irq_enable): + case PARAVIRT_PATCH(pv_irq_ops.irq_enable): return patch_internal(VMI_CALL_EnableInterrupts, len, insns, eip); - case PARAVIRT_PATCH(restore_fl): + case PARAVIRT_PATCH(pv_irq_ops.restore_fl): return patch_internal(VMI_CALL_SetInterruptMask, len, insns, eip); - case PARAVIRT_PATCH(save_fl): + case PARAVIRT_PATCH(pv_irq_ops.save_fl): return patch_internal(VMI_CALL_GetInterruptMask, len, insns, eip); - case PARAVIRT_PATCH(iret): + case PARAVIRT_PATCH(pv_cpu_ops.iret): return patch_internal(VMI_CALL_IRET, len, insns, eip); - case PARAVIRT_PATCH(irq_enable_sysexit): + case PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit): return patch_internal(VMI_CALL_SYSEXIT, len, insns, eip); default: break; @@ -552,24 +552,22 @@ vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip, } #endif -static void vmi_set_lazy_mode(enum paravirt_lazy_mode mode) +static void vmi_enter_lazy_cpu(void) { - static DEFINE_PER_CPU(enum paravirt_lazy_mode, lazy_mode); - - if (!vmi_ops.set_lazy_mode) - return; + paravirt_enter_lazy_cpu(); + vmi_ops.set_lazy_mode(2); +} - /* Modes should never nest or overlap */ - BUG_ON(__get_cpu_var(lazy_mode) && !(mode == PARAVIRT_LAZY_NONE || - mode == PARAVIRT_LAZY_FLUSH)); +static void vmi_enter_lazy_mmu(void) +{ + paravirt_enter_lazy_mmu(); + vmi_ops.set_lazy_mode(1); +} - if (mode == PARAVIRT_LAZY_FLUSH) { - vmi_ops.set_lazy_mode(0); - vmi_ops.set_lazy_mode(__get_cpu_var(lazy_mode)); - } else { - vmi_ops.set_lazy_mode(mode); - __get_cpu_var(lazy_mode) = mode; - } +static void vmi_leave_lazy(void) +{ + paravirt_leave_lazy(paravirt_get_lazy_mode()); + vmi_ops.set_lazy_mode(0); } static inline int __init check_vmi_rom(struct vrom_header *rom) @@ -690,9 +688,9 @@ do { \ reloc = call_vrom_long_func(vmi_rom, get_reloc, \ VMI_CALL_##vmicall); \ if (rel->type == VMI_RELOCATION_CALL_REL) \ - paravirt_ops.opname = (void *)rel->eip; \ + opname = (void *)rel->eip; \ else if (rel->type == VMI_RELOCATION_NOP) \ - paravirt_ops.opname = (void *)vmi_nop; \ + opname = (void *)vmi_nop; \ else if (rel->type != VMI_RELOCATION_NONE) \ printk(KERN_WARNING "VMI: Unknown relocation " \ "type %d for " #vmicall"\n",\ @@ -712,7 +710,7 @@ do { \ VMI_CALL_##vmicall); \ BUG_ON(rel->type == VMI_RELOCATION_JUMP_REL); \ if (rel->type == VMI_RELOCATION_CALL_REL) { \ - paravirt_ops.opname = wrapper; \ + opname = wrapper; \ vmi_ops.cache = (void *)rel->eip; \ } \ } while (0) @@ -732,11 +730,11 @@ static inline int __init activate_vmi(void) } savesegment(cs, kernel_cs); - paravirt_ops.paravirt_enabled = 1; - paravirt_ops.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK; + pv_info.paravirt_enabled = 1; + pv_info.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK; + pv_info.name = "vmi"; - paravirt_ops.patch = vmi_patch; - paravirt_ops.name = "vmi"; + pv_init_ops.patch = vmi_patch; /* * Many of these operations are ABI compatible with VMI. @@ -754,26 +752,26 @@ static inline int __init activate_vmi(void) */ /* CPUID is special, so very special it gets wrapped like a present */ - para_wrap(cpuid, vmi_cpuid, cpuid, CPUID); - - para_fill(clts, CLTS); - para_fill(get_debugreg, GetDR); - para_fill(set_debugreg, SetDR); - para_fill(read_cr0, GetCR0); - para_fill(read_cr2, GetCR2); - para_fill(read_cr3, GetCR3); - para_fill(read_cr4, GetCR4); - para_fill(write_cr0, SetCR0); - para_fill(write_cr2, SetCR2); - para_fill(write_cr3, SetCR3); - para_fill(write_cr4, SetCR4); - para_fill(save_fl, GetInterruptMask); - para_fill(restore_fl, SetInterruptMask); - para_fill(irq_disable, DisableInterrupts); - para_fill(irq_enable, EnableInterrupts); - - para_fill(wbinvd, WBINVD); - para_fill(read_tsc, RDTSC); + para_wrap(pv_cpu_ops.cpuid, vmi_cpuid, cpuid, CPUID); + + para_fill(pv_cpu_ops.clts, CLTS); + para_fill(pv_cpu_ops.get_debugreg, GetDR); + para_fill(pv_cpu_ops.set_debugreg, SetDR); + para_fill(pv_cpu_ops.read_cr0, GetCR0); + para_fill(pv_mmu_ops.read_cr2, GetCR2); + para_fill(pv_mmu_ops.read_cr3, GetCR3); + para_fill(pv_cpu_ops.read_cr4, GetCR4); + para_fill(pv_cpu_ops.write_cr0, SetCR0); + para_fill(pv_mmu_ops.write_cr2, SetCR2); + para_fill(pv_mmu_ops.write_cr3, SetCR3); + para_fill(pv_cpu_ops.write_cr4, SetCR4); + para_fill(pv_irq_ops.save_fl, GetInterruptMask); + para_fill(pv_irq_ops.restore_fl, SetInterruptMask); + para_fill(pv_irq_ops.irq_disable, DisableInterrupts); + para_fill(pv_irq_ops.irq_enable, EnableInterrupts); + + para_fill(pv_cpu_ops.wbinvd, WBINVD); + para_fill(pv_cpu_ops.read_tsc, RDTSC); /* The following we emulate with trap and emulate for now */ /* paravirt_ops.read_msr = vmi_rdmsr */ @@ -781,29 +779,38 @@ static inline int __init activate_vmi(void) /* paravirt_ops.rdpmc = vmi_rdpmc */ /* TR interface doesn't pass TR value, wrap */ - para_wrap(load_tr_desc, vmi_set_tr, set_tr, SetTR); + para_wrap(pv_cpu_ops.load_tr_desc, vmi_set_tr, set_tr, SetTR); /* LDT is special, too */ - para_wrap(set_ldt, vmi_set_ldt, _set_ldt, SetLDT); - - para_fill(load_gdt, SetGDT); - para_fill(load_idt, SetIDT); - para_fill(store_gdt, GetGDT); - para_fill(store_idt, GetIDT); - para_fill(store_tr, GetTR); - paravirt_ops.load_tls = vmi_load_tls; - para_fill(write_ldt_entry, WriteLDTEntry); - para_fill(write_gdt_entry, WriteGDTEntry); - para_fill(write_idt_entry, WriteIDTEntry); - para_wrap(load_esp0, vmi_load_esp0, set_kernel_stack, UpdateKernelStack); - para_fill(set_iopl_mask, SetIOPLMask); - para_fill(io_delay, IODelay); - para_wrap(set_lazy_mode, vmi_set_lazy_mode, set_lazy_mode, SetLazyMode); + para_wrap(pv_cpu_ops.set_ldt, vmi_set_ldt, _set_ldt, SetLDT); + + para_fill(pv_cpu_ops.load_gdt, SetGDT); + para_fill(pv_cpu_ops.load_idt, SetIDT); + para_fill(pv_cpu_ops.store_gdt, GetGDT); + para_fill(pv_cpu_ops.store_idt, GetIDT); + para_fill(pv_cpu_ops.store_tr, GetTR); + pv_cpu_ops.load_tls = vmi_load_tls; + para_fill(pv_cpu_ops.write_ldt_entry, WriteLDTEntry); + para_fill(pv_cpu_ops.write_gdt_entry, WriteGDTEntry); + para_fill(pv_cpu_ops.write_idt_entry, WriteIDTEntry); + para_wrap(pv_cpu_ops.load_esp0, vmi_load_esp0, set_kernel_stack, UpdateKernelStack); + para_fill(pv_cpu_ops.set_iopl_mask, SetIOPLMask); + para_fill(pv_cpu_ops.io_delay, IODelay); + + para_wrap(pv_cpu_ops.lazy_mode.enter, vmi_enter_lazy_cpu, + set_lazy_mode, SetLazyMode); + para_wrap(pv_cpu_ops.lazy_mode.leave, vmi_leave_lazy, + set_lazy_mode, SetLazyMode); + + para_wrap(pv_mmu_ops.lazy_mode.enter, vmi_enter_lazy_mmu, + set_lazy_mode, SetLazyMode); + para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy, + set_lazy_mode, SetLazyMode); /* user and kernel flush are just handled with different flags to FlushTLB */ - para_wrap(flush_tlb_user, vmi_flush_tlb_user, _flush_tlb, FlushTLB); - para_wrap(flush_tlb_kernel, vmi_flush_tlb_kernel, _flush_tlb, FlushTLB); - para_fill(flush_tlb_single, InvalPage); + para_wrap(pv_mmu_ops.flush_tlb_user, vmi_flush_tlb_user, _flush_tlb, FlushTLB); + para_wrap(pv_mmu_ops.flush_tlb_kernel, vmi_flush_tlb_kernel, _flush_tlb, FlushTLB); + para_fill(pv_mmu_ops.flush_tlb_single, InvalPage); /* * Until a standard flag format can be agreed on, we need to @@ -819,41 +826,41 @@ static inline int __init activate_vmi(void) #endif if (vmi_ops.set_pte) { - paravirt_ops.set_pte = vmi_set_pte; - paravirt_ops.set_pte_at = vmi_set_pte_at; - paravirt_ops.set_pmd = vmi_set_pmd; + pv_mmu_ops.set_pte = vmi_set_pte; + pv_mmu_ops.set_pte_at = vmi_set_pte_at; + pv_mmu_ops.set_pmd = vmi_set_pmd; #ifdef CONFIG_X86_PAE - paravirt_ops.set_pte_atomic = vmi_set_pte_atomic; - paravirt_ops.set_pte_present = vmi_set_pte_present; - paravirt_ops.set_pud = vmi_set_pud; - paravirt_ops.pte_clear = vmi_pte_clear; - paravirt_ops.pmd_clear = vmi_pmd_clear; + pv_mmu_ops.set_pte_atomic = vmi_set_pte_atomic; + pv_mmu_ops.set_pte_present = vmi_set_pte_present; + pv_mmu_ops.set_pud = vmi_set_pud; + pv_mmu_ops.pte_clear = vmi_pte_clear; + pv_mmu_ops.pmd_clear = vmi_pmd_clear; #endif } if (vmi_ops.update_pte) { - paravirt_ops.pte_update = vmi_update_pte; - paravirt_ops.pte_update_defer = vmi_update_pte_defer; + pv_mmu_ops.pte_update = vmi_update_pte; + pv_mmu_ops.pte_update_defer = vmi_update_pte_defer; } vmi_ops.allocate_page = vmi_get_function(VMI_CALL_AllocatePage); if (vmi_ops.allocate_page) { - paravirt_ops.alloc_pt = vmi_allocate_pt; - paravirt_ops.alloc_pd = vmi_allocate_pd; - paravirt_ops.alloc_pd_clone = vmi_allocate_pd_clone; + pv_mmu_ops.alloc_pt = vmi_allocate_pt; + pv_mmu_ops.alloc_pd = vmi_allocate_pd; + pv_mmu_ops.alloc_pd_clone = vmi_allocate_pd_clone; } vmi_ops.release_page = vmi_get_function(VMI_CALL_ReleasePage); if (vmi_ops.release_page) { - paravirt_ops.release_pt = vmi_release_pt; - paravirt_ops.release_pd = vmi_release_pd; + pv_mmu_ops.release_pt = vmi_release_pt; + pv_mmu_ops.release_pd = vmi_release_pd; } /* Set linear is needed in all cases */ vmi_ops.set_linear_mapping = vmi_get_function(VMI_CALL_SetLinearMapping); #ifdef CONFIG_HIGHPTE if (vmi_ops.set_linear_mapping) - paravirt_ops.kmap_atomic_pte = vmi_kmap_atomic_pte; + pv_mmu_ops.kmap_atomic_pte = vmi_kmap_atomic_pte; #endif /* @@ -863,17 +870,17 @@ static inline int __init activate_vmi(void) * the backend. They are performance critical anyway, so requiring * a patch is not a big problem. */ - paravirt_ops.irq_enable_sysexit = (void *)0xfeedbab0; - paravirt_ops.iret = (void *)0xbadbab0; + pv_cpu_ops.irq_enable_sysexit = (void *)0xfeedbab0; + pv_cpu_ops.iret = (void *)0xbadbab0; #ifdef CONFIG_SMP - para_wrap(startup_ipi_hook, vmi_startup_ipi_hook, set_initial_ap_state, SetInitialAPState); + para_wrap(pv_apic_ops.startup_ipi_hook, vmi_startup_ipi_hook, set_initial_ap_state, SetInitialAPState); #endif #ifdef CONFIG_X86_LOCAL_APIC - para_fill(apic_read, APICRead); - para_fill(apic_write, APICWrite); - para_fill(apic_write_atomic, APICWrite); + para_fill(pv_apic_ops.apic_read, APICRead); + para_fill(pv_apic_ops.apic_write, APICWrite); + para_fill(pv_apic_ops.apic_write_atomic, APICWrite); #endif /* @@ -891,15 +898,15 @@ static inline int __init activate_vmi(void) vmi_timer_ops.set_alarm = vmi_get_function(VMI_CALL_SetAlarm); vmi_timer_ops.cancel_alarm = vmi_get_function(VMI_CALL_CancelAlarm); - paravirt_ops.time_init = vmi_time_init; - paravirt_ops.get_wallclock = vmi_get_wallclock; - paravirt_ops.set_wallclock = vmi_set_wallclock; + pv_time_ops.time_init = vmi_time_init; + pv_time_ops.get_wallclock = vmi_get_wallclock; + pv_time_ops.set_wallclock = vmi_set_wallclock; #ifdef CONFIG_X86_LOCAL_APIC - paravirt_ops.setup_boot_clock = vmi_time_bsp_init; - paravirt_ops.setup_secondary_clock = vmi_time_ap_init; + pv_apic_ops.setup_boot_clock = vmi_time_bsp_init; + pv_apic_ops.setup_secondary_clock = vmi_time_ap_init; #endif - paravirt_ops.sched_clock = vmi_sched_clock; - paravirt_ops.get_cpu_khz = vmi_cpu_khz; + pv_time_ops.sched_clock = vmi_sched_clock; + pv_time_ops.get_cpu_khz = vmi_cpu_khz; /* We have true wallclock functions; disable CMOS clock sync */ no_sync_cmos_clock = 1; @@ -908,7 +915,7 @@ static inline int __init activate_vmi(void) disable_vmi_timer = 1; } - para_fill(safe_halt, Halt); + para_fill(pv_irq_ops.safe_halt, Halt); /* * Alternative instruction rewriting doesn't happen soon enough diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 93847d84815..ad4005c6d4a 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -48,12 +48,12 @@ ({unsigned long v; \ extern char __vsyscall_0; \ asm("" : "=r" (v) : "0" (x)); \ - ((v - VSYSCALL_FIRST_PAGE) + __pa_symbol(&__vsyscall_0)); }) + ((v - VSYSCALL_START) + __pa_symbol(&__vsyscall_0)); }) /* * vsyscall_gtod_data contains data that is : * - readonly from vsyscalls - * - writen by timer interrupt or systcl (/proc/sys/kernel/vsyscall64) + * - written by timer interrupt or systcl (/proc/sys/kernel/vsyscall64) * Try to keep this structure as small as possible to avoid cache line ping pongs */ int __vgetcpu_mode __section_vgetcpu_mode; @@ -64,6 +64,16 @@ struct vsyscall_gtod_data __vsyscall_gtod_data __section_vsyscall_gtod_data = .sysctl_enabled = 1, }; +void update_vsyscall_tz(void) +{ + unsigned long flags; + + write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags); + /* sys_tz has changed */ + vsyscall_gtod_data.sys_tz = sys_tz; + write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); +} + void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) { unsigned long flags; @@ -77,8 +87,6 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) vsyscall_gtod_data.clock.shift = clock->shift; vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec; vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec; - vsyscall_gtod_data.sys_tz = sys_tz; - vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec; vsyscall_gtod_data.wall_to_monotonic = wall_to_monotonic; write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); } @@ -164,7 +172,7 @@ time_t __vsyscall(1) vtime(time_t *t) if (unlikely(!__vsyscall_gtod_data.sysctl_enabled)) return time_syscall(t); - vgettimeofday(&tv, 0); + vgettimeofday(&tv, NULL); result = tv.tv_sec; if (t) *t = result; @@ -258,18 +266,10 @@ out: return ret; } -static int vsyscall_sysctl_nostrat(ctl_table *t, int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen) -{ - return -ENOSYS; -} - static ctl_table kernel_table2[] = { - { .ctl_name = 99, .procname = "vsyscall64", + { .procname = "vsyscall64", .data = &vsyscall_gtod_data.sysctl_enabled, .maxlen = sizeof(int), .mode = 0644, - .strategy = vsyscall_sysctl_nostrat, .proc_handler = vsyscall_sysctl_change }, {} }; @@ -289,9 +289,9 @@ static void __cpuinit vsyscall_set_cpu(int cpu) unsigned long *d; unsigned long node = 0; #ifdef CONFIG_NUMA - node = cpu_to_node[cpu]; + node = cpu_to_node(cpu); #endif - if (cpu_has(&cpu_data[cpu], X86_FEATURE_RDTSCP)) + if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP)) write_rdtscp_aux((node << 12) | cpu); /* Store cpu number in limit so that it can be loaded quickly |