diff options
Diffstat (limited to 'arch/i386')
33 files changed, 336 insertions, 306 deletions
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index daa75ce4b77..b2751eadbc5 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -142,6 +142,7 @@ config X86_SUMMIT In particular, it is needed for the x440. If you don't have one of these computers, you should say N here. + If you want to build a NUMA kernel, you must select ACPI. config X86_BIGSMP bool "Support for other sub-arch SMP systems with more than 8 CPUs" @@ -169,6 +170,7 @@ config X86_GENERICARCH help This option compiles in the Summit, bigsmp, ES7000, default subarchitectures. It is intended for a generic binary kernel. + If you want a NUMA kernel, select ACPI. We need SRAT for NUMA. config X86_ES7000 bool "Support for Unisys ES7000 IA32 series" @@ -542,7 +544,7 @@ config X86_PAE # Common NUMA Features config NUMA bool "Numa Memory Allocation and Scheduler Support" - depends on SMP && HIGHMEM64G && (X86_NUMAQ || X86_GENERICARCH || (X86_SUMMIT && ACPI)) + depends on SMP && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI) default n if X86_PC default y if (X86_NUMAQ || X86_SUMMIT) @@ -672,7 +674,7 @@ config MTRR See <file:Documentation/mtrr.txt> for more information. config EFI - bool "Boot from EFI support (EXPERIMENTAL)" + bool "Boot from EFI support" depends on ACPI default n ---help--- diff --git a/arch/i386/defconfig b/arch/i386/defconfig index 1629c3ac9be..89ebb7a316a 100644 --- a/arch/i386/defconfig +++ b/arch/i386/defconfig @@ -197,7 +197,7 @@ CONFIG_PM=y # CONFIG_PM_LEGACY is not set # CONFIG_PM_DEBUG is not set CONFIG_SOFTWARE_SUSPEND=y -CONFIG_PM_STD_PARTITION="/dev/hda2" +CONFIG_PM_STD_PARTITION="" # # ACPI (Advanced Configuration and Power Interface) Support diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile index 1b452a1665c..5427a842e84 100644 --- a/arch/i386/kernel/Makefile +++ b/arch/i386/kernel/Makefile @@ -39,7 +39,6 @@ obj-$(CONFIG_VM86) += vm86.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_HPET_TIMER) += hpet.o obj-$(CONFIG_K8_NB) += k8.o -obj-$(CONFIG_AUDIT) += audit.o EXTRA_AFLAGS := -traditional @@ -59,7 +58,8 @@ quiet_cmd_syscall = SYSCALL $@ export CPPFLAGS_vsyscall.lds += -P -C -U$(ARCH) -vsyscall-flags = -shared -s -Wl,-soname=linux-gate.so.1 +vsyscall-flags = -shared -s -Wl,-soname=linux-gate.so.1 \ + $(call ld-option, -Wl$(comma)--hash-style=sysv) SYSCFLAGS_vsyscall-sysenter.so = $(vsyscall-flags) SYSCFLAGS_vsyscall-int80.so = $(vsyscall-flags) diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index 0db6387025c..ee003bc0e8b 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -59,7 +59,7 @@ static inline int gsi_irq_sharing(int gsi) { return gsi; } #define BAD_MADT_ENTRY(entry, end) ( \ (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ - ((acpi_table_entry_header *)entry)->length != sizeof(*entry)) + ((acpi_table_entry_header *)entry)->length < sizeof(*entry)) #define PREFIX "ACPI: " diff --git a/arch/i386/kernel/acpi/wakeup.S b/arch/i386/kernel/acpi/wakeup.S index 9f408eee4e6..b781b38131c 100644 --- a/arch/i386/kernel/acpi/wakeup.S +++ b/arch/i386/kernel/acpi/wakeup.S @@ -292,7 +292,10 @@ ENTRY(do_suspend_lowlevel) pushl $3 call acpi_enter_sleep_state addl $4, %esp - ret + +# In case of S3 failure, we'll emerge here. Jump +# to ret_point to recover + jmp ret_point .p2align 4,,7 ret_point: call restore_registers diff --git a/arch/i386/kernel/audit.c b/arch/i386/kernel/audit.c deleted file mode 100644 index 5a53c6f371f..00000000000 --- a/arch/i386/kernel/audit.c +++ /dev/null @@ -1,23 +0,0 @@ -#include <linux/init.h> -#include <linux/types.h> -#include <linux/audit.h> -#include <asm/unistd.h> - -static unsigned dir_class[] = { -#include <asm-generic/audit_dir_write.h> -~0U -}; - -static unsigned chattr_class[] = { -#include <asm-generic/audit_change_attr.h> -~0U -}; - -static int __init audit_classes_init(void) -{ - audit_register_class(AUDIT_CLASS_DIR_WRITE, dir_class); - audit_register_class(AUDIT_CLASS_CHATTR, chattr_class); - return 0; -} - -__initcall(audit_classes_init); diff --git a/arch/i386/kernel/cpu/cpufreq/Kconfig b/arch/i386/kernel/cpu/cpufreq/Kconfig index e44a4c6a4fe..ccc1edff5c9 100644 --- a/arch/i386/kernel/cpu/cpufreq/Kconfig +++ b/arch/i386/kernel/cpu/cpufreq/Kconfig @@ -96,6 +96,7 @@ config X86_POWERNOW_K8_ACPI config X86_GX_SUSPMOD tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation" + depends on PCI help This add the CPUFreq driver for NatSemi Geode processors which support suspend modulation. @@ -202,7 +203,7 @@ config X86_LONGRUN config X86_LONGHAUL tristate "VIA Cyrix III Longhaul" select CPU_FREQ_TABLE - depends on BROKEN + depends on ACPI_PROCESSOR help This adds the CPUFreq driver for VIA Samuel/CyrixIII, VIA Cyrix Samuel/C3, VIA Cyrix Ezra and VIA Cyrix Ezra-T diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c index 567b39bea07..e6ea00edcb5 100644 --- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -384,8 +384,7 @@ static int acpi_cpufreq_early_init_acpi(void) } /* Do initialization in ACPI core */ - acpi_processor_preregister_performance(acpi_perf_data); - return 0; + return acpi_processor_preregister_performance(acpi_perf_data); } static int @@ -568,16 +567,11 @@ static struct cpufreq_driver acpi_cpufreq_driver = { static int __init acpi_cpufreq_init (void) { - int result = 0; - dprintk("acpi_cpufreq_init\n"); - result = acpi_cpufreq_early_init_acpi(); + acpi_cpufreq_early_init_acpi(); - if (!result) - result = cpufreq_register_driver(&acpi_cpufreq_driver); - - return (result); + return cpufreq_register_driver(&acpi_cpufreq_driver); } diff --git a/arch/i386/kernel/cpu/cpufreq/longhaul.c b/arch/i386/kernel/cpu/cpufreq/longhaul.c index 146f607e9c4..4f2c3aeef72 100644 --- a/arch/i386/kernel/cpu/cpufreq/longhaul.c +++ b/arch/i386/kernel/cpu/cpufreq/longhaul.c @@ -29,11 +29,13 @@ #include <linux/cpufreq.h> #include <linux/slab.h> #include <linux/string.h> -#include <linux/pci.h> #include <asm/msr.h> #include <asm/timex.h> #include <asm/io.h> +#include <asm/acpi.h> +#include <linux/acpi.h> +#include <acpi/processor.h> #include "longhaul.h" @@ -56,6 +58,8 @@ static int minvid, maxvid; static unsigned int minmult, maxmult; static int can_scale_voltage; static int vrmrev; +static struct acpi_processor *pr = NULL; +static struct acpi_processor_cx *cx = NULL; /* Module parameters */ static int dont_scale_voltage; @@ -118,84 +122,65 @@ static int longhaul_get_cpu_mult(void) return eblcr_table[invalue]; } +/* For processor with BCR2 MSR */ -static void do_powersaver(union msr_longhaul *longhaul, - unsigned int clock_ratio_index) +static void do_longhaul1(int cx_address, unsigned int clock_ratio_index) { - struct pci_dev *dev; - unsigned long flags; - unsigned int tmp_mask; - int version; - int i; - u16 pci_cmd; - u16 cmd_state[64]; + union msr_bcr2 bcr2; + u32 t; - switch (cpu_model) { - case CPU_EZRA_T: - version = 3; - break; - case CPU_NEHEMIAH: - version = 0xf; - break; - default: - return; - } + rdmsrl(MSR_VIA_BCR2, bcr2.val); + /* Enable software clock multiplier */ + bcr2.bits.ESOFTBF = 1; + bcr2.bits.CLOCKMUL = clock_ratio_index; - rdmsrl(MSR_VIA_LONGHAUL, longhaul->val); - longhaul->bits.SoftBusRatio = clock_ratio_index & 0xf; - longhaul->bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4; - longhaul->bits.EnableSoftBusRatio = 1; - longhaul->bits.RevisionKey = 0; + /* Sync to timer tick */ + safe_halt(); + ACPI_FLUSH_CPU_CACHE(); + /* Change frequency on next halt or sleep */ + wrmsrl(MSR_VIA_BCR2, bcr2.val); + /* Invoke C3 */ + inb(cx_address); + /* Dummy op - must do something useless after P_LVL3 read */ + t = inl(acpi_fadt.xpm_tmr_blk.address); + + /* Disable software clock multiplier */ + local_irq_disable(); + rdmsrl(MSR_VIA_BCR2, bcr2.val); + bcr2.bits.ESOFTBF = 0; + wrmsrl(MSR_VIA_BCR2, bcr2.val); +} - preempt_disable(); - local_irq_save(flags); +/* For processor with Longhaul MSR */ - /* - * get current pci bus master state for all devices - * and clear bus master bit - */ - dev = NULL; - i = 0; - do { - dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev); - if (dev != NULL) { - pci_read_config_word(dev, PCI_COMMAND, &pci_cmd); - cmd_state[i++] = pci_cmd; - pci_cmd &= ~PCI_COMMAND_MASTER; - pci_write_config_word(dev, PCI_COMMAND, pci_cmd); - } - } while (dev != NULL); +static void do_powersaver(int cx_address, unsigned int clock_ratio_index) +{ + union msr_longhaul longhaul; + u32 t; - tmp_mask=inb(0x21); /* works on C3. save mask. */ - outb(0xFE,0x21); /* TMR0 only */ - outb(0xFF,0x80); /* delay */ + rdmsrl(MSR_VIA_LONGHAUL, longhaul.val); + longhaul.bits.RevisionKey = longhaul.bits.RevisionID; + longhaul.bits.SoftBusRatio = clock_ratio_index & 0xf; + longhaul.bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4; + longhaul.bits.EnableSoftBusRatio = 1; + /* Sync to timer tick */ safe_halt(); - wrmsrl(MSR_VIA_LONGHAUL, longhaul->val); - halt(); - + ACPI_FLUSH_CPU_CACHE(); + /* Change frequency on next halt or sleep */ + wrmsrl(MSR_VIA_LONGHAUL, longhaul.val); + /* Invoke C3 */ + inb(cx_address); + /* Dummy op - must do something useless after P_LVL3 read */ + t = inl(acpi_fadt.xpm_tmr_blk.address); + + /* Disable bus ratio bit */ local_irq_disable(); - - outb(tmp_mask,0x21); /* restore mask */ - - /* restore pci bus master state for all devices */ - dev = NULL; - i = 0; - do { - dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev); - if (dev != NULL) { - pci_cmd = cmd_state[i++]; - pci_write_config_byte(dev, PCI_COMMAND, pci_cmd); - } - } while (dev != NULL); - local_irq_restore(flags); - preempt_enable(); - - /* disable bus ratio bit */ - rdmsrl(MSR_VIA_LONGHAUL, longhaul->val); - longhaul->bits.EnableSoftBusRatio = 0; - longhaul->bits.RevisionKey = version; - wrmsrl(MSR_VIA_LONGHAUL, longhaul->val); + longhaul.bits.RevisionKey = longhaul.bits.RevisionID; + longhaul.bits.EnableSoftBusRatio = 0; + longhaul.bits.EnableSoftBSEL = 0; + longhaul.bits.EnableSoftVID = 0; + wrmsrl(MSR_VIA_LONGHAUL, longhaul.val); } /** @@ -209,9 +194,9 @@ static void longhaul_setstate(unsigned int clock_ratio_index) { int speed, mult; struct cpufreq_freqs freqs; - union msr_longhaul longhaul; - union msr_bcr2 bcr2; static unsigned int old_ratio=-1; + unsigned long flags; + unsigned int pic1_mask, pic2_mask; if (old_ratio == clock_ratio_index) return; @@ -234,6 +219,20 @@ static void longhaul_setstate(unsigned int clock_ratio_index) dprintk ("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n", fsb, mult/10, mult%10, print_speed(speed/1000)); + preempt_disable(); + local_irq_save(flags); + + pic2_mask = inb(0xA1); + pic1_mask = inb(0x21); /* works on C3. save mask. */ + outb(0xFF,0xA1); /* Overkill */ + outb(0xFE,0x21); /* TMR0 only */ + + /* Disable bus master arbitration */ + if (pr->flags.bm_check) { + acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1, + ACPI_MTX_DO_NOT_LOCK); + } + switch (longhaul_version) { /* @@ -245,20 +244,7 @@ static void longhaul_setstate(unsigned int clock_ratio_index) */ case TYPE_LONGHAUL_V1: case TYPE_LONGHAUL_V2: - rdmsrl (MSR_VIA_BCR2, bcr2.val); - /* Enable software clock multiplier */ - bcr2.bits.ESOFTBF = 1; - bcr2.bits.CLOCKMUL = clock_ratio_index; - local_irq_disable(); - wrmsrl (MSR_VIA_BCR2, bcr2.val); - safe_halt(); - - /* Disable software clock multiplier */ - rdmsrl (MSR_VIA_BCR2, bcr2.val); - bcr2.bits.ESOFTBF = 0; - local_irq_disable(); - wrmsrl (MSR_VIA_BCR2, bcr2.val); - local_irq_enable(); + do_longhaul1(cx->address, clock_ratio_index); break; /* @@ -273,10 +259,22 @@ static void longhaul_setstate(unsigned int clock_ratio_index) * to work in practice. */ case TYPE_POWERSAVER: - do_powersaver(&longhaul, clock_ratio_index); + do_powersaver(cx->address, clock_ratio_index); break; } + /* Enable bus master arbitration */ + if (pr->flags.bm_check) { + acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0, + ACPI_MTX_DO_NOT_LOCK); + } + + outb(pic2_mask,0xA1); /* restore mask */ + outb(pic1_mask,0x21); + + local_irq_restore(flags); + preempt_enable(); + cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); } @@ -324,9 +322,11 @@ static int guess_fsb(void) static int __init longhaul_get_ranges(void) { unsigned long invalue; - unsigned int multipliers[32]= { - 50,30,40,100,55,35,45,95,90,70,80,60,120,75,85,65, - -1,110,120,-1,135,115,125,105,130,150,160,140,-1,155,-1,145 }; + unsigned int ezra_t_multipliers[32]= { + 90, 30, 40, 100, 55, 35, 45, 95, + 50, 70, 80, 60, 120, 75, 85, 65, + -1, 110, 120, -1, 135, 115, 125, 105, + 130, 150, 160, 140, -1, 155, -1, 145 }; unsigned int j, k = 0; union msr_longhaul longhaul; unsigned long lo, hi; @@ -355,13 +355,13 @@ static int __init longhaul_get_ranges(void) invalue = longhaul.bits.MaxMHzBR; if (longhaul.bits.MaxMHzBR4) invalue += 16; - maxmult=multipliers[invalue]; + maxmult=ezra_t_multipliers[invalue]; invalue = longhaul.bits.MinMHzBR; if (longhaul.bits.MinMHzBR4 == 1) minmult = 30; else - minmult = multipliers[invalue]; + minmult = ezra_t_multipliers[invalue]; fsb = eblcr_fsb_table_v2[longhaul.bits.MaxMHzFSB]; break; } @@ -527,6 +527,18 @@ static unsigned int longhaul_get(unsigned int cpu) return calc_speed(longhaul_get_cpu_mult()); } +static acpi_status longhaul_walk_callback(acpi_handle obj_handle, + u32 nesting_level, + void *context, void **return_value) +{ + struct acpi_device *d; + + if ( acpi_bus_get_device(obj_handle, &d) ) { + return 0; + } + *return_value = (void *)acpi_driver_data(d); + return 1; +} static int __init longhaul_cpu_init(struct cpufreq_policy *policy) { @@ -534,6 +546,15 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) char *cpuname=NULL; int ret; + /* Check ACPI support for C3 state */ + acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX, + &longhaul_walk_callback, NULL, (void *)&pr); + if (pr == NULL) goto err_acpi; + + cx = &pr->power.states[ACPI_STATE_C3]; + if (cx->address == 0 || cx->latency > 1000) goto err_acpi; + + /* Now check what we have on this motherboard */ switch (c->x86_model) { case 6: cpu_model = CPU_SAMUEL; @@ -634,6 +655,10 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) cpufreq_frequency_table_get_attr(longhaul_table, policy->cpu); return 0; + +err_acpi: + printk(KERN_ERR PFX "No ACPI support for CPU frequency changes.\n"); + return -ENODEV; } static int __devexit longhaul_cpu_exit(struct cpufreq_policy *policy) @@ -666,6 +691,18 @@ static int __init longhaul_init(void) if (c->x86_vendor != X86_VENDOR_CENTAUR || c->x86 != 6) return -ENODEV; +#ifdef CONFIG_SMP + if (num_online_cpus() > 1) { + return -ENODEV; + printk(KERN_ERR PFX "More than 1 CPU detected, longhaul disabled.\n"); + } +#endif +#ifdef CONFIG_X86_IO_APIC + if (cpu_has_apic) { + printk(KERN_ERR PFX "APIC detected. Longhaul is currently broken in this configuration.\n"); + return -ENODEV; + } +#endif switch (c->x86_model) { case 6 ... 9: return cpufreq_register_driver(&longhaul_driver); @@ -699,6 +736,6 @@ MODULE_AUTHOR ("Dave Jones <davej@codemonkey.org.uk>"); MODULE_DESCRIPTION ("Longhaul driver for VIA Cyrix processors."); MODULE_LICENSE ("GPL"); -module_init(longhaul_init); +late_initcall(longhaul_init); module_exit(longhaul_exit); diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index e9f0b928b0a..5c43be47587 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -759,7 +759,7 @@ static int __cpuinit cache_sysfs_init(void) if (num_cache_leaves == 0) return 0; - register_cpu_notifier(&cacheinfo_cpu_notifier); + register_hotcpu_notifier(&cacheinfo_cpu_notifier); for_each_online_cpu(i) { cacheinfo_cpu_callback(&cacheinfo_cpu_notifier, CPU_ONLINE, diff --git a/arch/i386/kernel/cpu/mcheck/mce.h b/arch/i386/kernel/cpu/mcheck/mce.h index dc2416dfef1..84fd4cf7d0f 100644 --- a/arch/i386/kernel/cpu/mcheck/mce.h +++ b/arch/i386/kernel/cpu/mcheck/mce.h @@ -9,6 +9,6 @@ void winchip_mcheck_init(struct cpuinfo_x86 *c); /* Call the installed machine check handler for this CPU setup. */ extern fastcall void (*machine_check_vector)(struct pt_regs *, long error_code); -extern int mce_disabled __initdata; +extern int mce_disabled; extern int nr_mce_banks; diff --git a/arch/i386/kernel/crash.c b/arch/i386/kernel/crash.c index 48f0f62f781..5b96f038367 100644 --- a/arch/i386/kernel/crash.c +++ b/arch/i386/kernel/crash.c @@ -90,7 +90,7 @@ static void crash_save_self(struct pt_regs *regs) crash_save_this_cpu(regs, cpu); } -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static atomic_t waiting_for_crash_ipi; static int crash_nmi_callback(struct pt_regs *regs, int cpu) diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S index d9a260f2efb..87f9f60b803 100644 --- a/arch/i386/kernel/entry.S +++ b/arch/i386/kernel/entry.S @@ -204,11 +204,15 @@ VM_MASK = 0x00020000 ENTRY(ret_from_fork) CFI_STARTPROC pushl %eax - CFI_ADJUST_CFA_OFFSET -4 + CFI_ADJUST_CFA_OFFSET 4 call schedule_tail GET_THREAD_INFO(%ebp) popl %eax CFI_ADJUST_CFA_OFFSET -4 + pushl $0x0202 # Reset kernel eflags + CFI_ADJUST_CFA_OFFSET 4 + popfl + CFI_ADJUST_CFA_OFFSET -4 jmp syscall_exit CFI_ENDPROC diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S index eb79aa2fa8b..a6b8bd89aa2 100644 --- a/arch/i386/kernel/head.S +++ b/arch/i386/kernel/head.S @@ -317,20 +317,14 @@ is386: movl $2,%ecx # set MP movl %eax,%gs lldt %ax cld # gcc2 wants the direction flag cleared at all times + pushl %eax # fake return address #ifdef CONFIG_SMP movb ready, %cl movb $1, ready - cmpb $0,%cl - je 1f # the first CPU calls start_kernel - # all other CPUs call initialize_secondary - call initialize_secondary - jmp L6 -1: + cmpb $0,%cl # the first CPU calls start_kernel + jne initialize_secondary # all other CPUs call initialize_secondary #endif /* CONFIG_SMP */ - call start_kernel -L6: - jmp L6 # main should never return here, but - # just in case, we know what happens. + jmp start_kernel /* * We depend on ET to be correct. This checks for 287/387. diff --git a/arch/i386/kernel/hpet.c b/arch/i386/kernel/hpet.c index c6737c35815..17647a530b2 100644 --- a/arch/i386/kernel/hpet.c +++ b/arch/i386/kernel/hpet.c @@ -35,7 +35,7 @@ static int __init init_hpet_clocksource(void) void __iomem* hpet_base; u64 tmp; - if (!hpet_address) + if (!is_hpet_enabled()) return -ENODEV; /* calculate the hpet address: */ diff --git a/arch/i386/kernel/ioport.c b/arch/i386/kernel/ioport.c index 79026f026b8..498e8bc197d 100644 --- a/arch/i386/kernel/ioport.c +++ b/arch/i386/kernel/ioport.c @@ -79,6 +79,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) memset(bitmap, 0xff, IO_BITMAP_BYTES); t->io_bitmap_ptr = bitmap; + set_thread_flag(TIF_IO_BITMAP); } /* diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c index 6cb529f60dc..5fe547cd8f9 100644 --- a/arch/i386/kernel/irq.c +++ b/arch/i386/kernel/irq.c @@ -82,10 +82,6 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs) } #endif - if (!irq_desc[irq].handle_irq) { - __do_IRQ(irq, regs); - goto out_exit; - } #ifdef CONFIG_4KSTACKS curctx = (union irq_ctx *) current_thread_info(); @@ -125,7 +121,6 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs) #endif __do_IRQ(irq, regs); -out_exit: irq_exit(); return 1; diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c index de2e16e561c..afe6505ca0b 100644 --- a/arch/i386/kernel/kprobes.c +++ b/arch/i386/kernel/kprobes.c @@ -256,11 +256,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) int ret = 0; kprobe_opcode_t *addr; struct kprobe_ctlblk *kcb; -#ifdef CONFIG_PREEMPT - unsigned pre_preempt_count = preempt_count(); -#else - unsigned pre_preempt_count = 1; -#endif addr = (kprobe_opcode_t *)(regs->eip - sizeof(kprobe_opcode_t)); @@ -338,13 +333,15 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) return 1; ss_probe: - if (pre_preempt_count && p->ainsn.boostable == 1 && !p->post_handler){ +#ifndef CONFIG_PREEMPT + if (p->ainsn.boostable == 1 && !p->post_handler){ /* Boost up -- we can execute copied instructions directly */ reset_current_kprobe(); regs->eip = (unsigned long)p->ainsn.insn; preempt_enable_no_resched(); return 1; } +#endif prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; return 1; diff --git a/arch/i386/kernel/machine_kexec.c b/arch/i386/kernel/machine_kexec.c index 511abe52a94..6b1ae6ba76f 100644 --- a/arch/i386/kernel/machine_kexec.c +++ b/arch/i386/kernel/machine_kexec.c @@ -189,14 +189,11 @@ NORET_TYPE void machine_kexec(struct kimage *image) memcpy((void *)reboot_code_buffer, relocate_new_kernel, relocate_new_kernel_size); - /* The segment registers are funny things, they are - * automatically loaded from a table, in memory wherever you - * set them to a specific selector, but this table is never - * accessed again you set the segment to a different selector. - * - * The more common model is are caches where the behide - * the scenes work is done, but is also dropped at arbitrary - * times. + /* The segment registers are funny things, they have both a + * visible and an invisible part. Whenever the visible part is + * set to a specific selector, the invisible part is loaded + * with from a table in memory. At no other time is the + * descriptor table in memory accessed. * * I take advantage of this here by force loading the * segments, before I zap the gdt with an invalid value. diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c index 2dd928a8464..acb351478e4 100644 --- a/arch/i386/kernel/nmi.c +++ b/arch/i386/kernel/nmi.c @@ -575,6 +575,7 @@ void touch_nmi_watchdog (void) */ touch_softlockup_watchdog(); } +EXPORT_SYMBOL(touch_nmi_watchdog); extern void die_nmi(struct pt_regs *, const char *msg); diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index 94e2c87edea..8657c739656 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -359,16 +359,16 @@ EXPORT_SYMBOL(kernel_thread); */ void exit_thread(void) { - struct task_struct *tsk = current; - struct thread_struct *t = &tsk->thread; - /* The process may have allocated an io port bitmap... nuke it. */ - if (unlikely(NULL != t->io_bitmap_ptr)) { + if (unlikely(test_thread_flag(TIF_IO_BITMAP))) { + struct task_struct *tsk = current; + struct thread_struct *t = &tsk->thread; int cpu = get_cpu(); struct tss_struct *tss = &per_cpu(init_tss, cpu); kfree(t->io_bitmap_ptr); t->io_bitmap_ptr = NULL; + clear_thread_flag(TIF_IO_BITMAP); /* * Careful, clear this in the TSS too: */ @@ -387,6 +387,7 @@ void flush_thread(void) memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); + clear_tsk_thread_flag(tsk, TIF_DEBUG); /* * Forget coprocessor state.. */ @@ -431,7 +432,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long esp, savesegment(gs,p->thread.gs); tsk = current; - if (unlikely(NULL != tsk->thread.io_bitmap_ptr)) { + if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) { p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); if (!p->thread.io_bitmap_ptr) { p->thread.io_bitmap_max = 0; @@ -439,6 +440,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long esp, } memcpy(p->thread.io_bitmap_ptr, tsk->thread.io_bitmap_ptr, IO_BITMAP_BYTES); + set_tsk_thread_flag(p, TIF_IO_BITMAP); } /* @@ -533,10 +535,24 @@ int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs) return 1; } -static inline void -handle_io_bitmap(struct thread_struct *next, struct tss_struct *tss) +static noinline void __switch_to_xtra(struct task_struct *next_p, + struct tss_struct *tss) { - if (!next->io_bitmap_ptr) { + struct thread_struct *next; + + next = &next_p->thread; + + if (test_tsk_thread_flag(next_p, TIF_DEBUG)) { + set_debugreg(next->debugreg[0], 0); + set_debugreg(next->debugreg[1], 1); + set_debugreg(next->debugreg[2], 2); + set_debugreg(next->debugreg[3], 3); + /* no 4 and 5 */ + set_debugreg(next->debugreg[6], 6); + set_debugreg(next->debugreg[7], 7); + } + + if (!test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) { /* * Disable the bitmap via an invalid offset. We still cache * the previous bitmap owner and the IO bitmap contents: @@ -544,6 +560,7 @@ handle_io_bitmap(struct thread_struct *next, struct tss_struct *tss) tss->io_bitmap_base = INVALID_IO_BITMAP_OFFSET; return; } + if (likely(next == tss->io_bitmap_owner)) { /* * Previous owner of the bitmap (hence the bitmap content) @@ -671,20 +688,11 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas set_iopl_mask(next->iopl); /* - * Now maybe reload the debug registers + * Now maybe handle debug registers and/or IO bitmaps */ - if (unlikely(next->debugreg[7])) { - set_debugreg(next->debugreg[0], 0); - set_debugreg(next->debugreg[1], 1); - set_debugreg(next->debugreg[2], 2); - set_debugreg(next->debugreg[3], 3); - /* no 4 and 5 */ - set_debugreg(next->debugreg[6], 6); - set_debugreg(next->debugreg[7], 7); - } - - if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) - handle_io_bitmap(next, tss); + if (unlikely((task_thread_info(next_p)->flags & _TIF_WORK_CTXSW) + || test_tsk_thread_flag(prev_p, TIF_IO_BITMAP))) + __switch_to_xtra(next_p, tss); disable_tsc(prev_p, next_p); diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c index fd7eaf7866e..d3db03f4085 100644 --- a/arch/i386/kernel/ptrace.c +++ b/arch/i386/kernel/ptrace.c @@ -468,8 +468,11 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data) for(i=0; i<4; i++) if ((0x5f54 >> ((data >> (16 + 4*i)) & 0xf)) & 1) goto out_tsk; + if (data) + set_tsk_thread_flag(child, TIF_DEBUG); + else + clear_tsk_thread_flag(child, TIF_DEBUG); } - addr -= (long) &dummy->u_debugreg; addr = addr >> 2; child->thread.debugreg[addr] = data; diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index 08c00d20f16..345ffb7d904 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -26,7 +26,7 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/mmzone.h> -#include <linux/tty.h> +#include <linux/screen_info.h> #include <linux/ioport.h> #include <linux/acpi.h> #include <linux/apm_bios.h> @@ -956,38 +956,6 @@ efi_memory_present_wrapper(unsigned long start, unsigned long end, void *arg) return 0; } - /* - * This function checks if the entire range <start,end> is mapped with type. - * - * Note: this function only works correct if the e820 table is sorted and - * not-overlapping, which is the case - */ -int __init -e820_all_mapped(unsigned long s, unsigned long e, unsigned type) -{ - u64 start = s; - u64 end = e; - int i; - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - if (type && ei->type != type) - continue; - /* is the region (part) in overlap with the current region ?*/ - if (ei->addr >= end || ei->addr + ei->size <= start) - continue; - /* if the region is at the beginning of <start,end> we move - * start to the end of the region since it's ok until there - */ - if (ei->addr <= start) - start = ei->addr + ei->size; - /* if start is now at or beyond end, we're done, full - * coverage */ - if (start >= end) - return 1; /* we're done */ - } - return 0; -} - /* * Find the highest page frame number we have available */ @@ -1327,7 +1295,10 @@ legacy_init_iomem_resources(struct resource *code_resource, struct resource *dat res->start = e820.map[i].addr; res->end = res->start + e820.map[i].size - 1; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; - request_resource(&iomem_resource, res); + if (request_resource(&iomem_resource, res)) { + kfree(res); + continue; + } if (e820.map[i].type == E820_RAM) { /* * We don't know which RAM region contains kernel data, diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index 6f5fea05f1d..f948419c888 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -212,14 +212,20 @@ valid_k7: * then we print a warning if not, and always resync. */ -static atomic_t tsc_start_flag = ATOMIC_INIT(0); -static atomic_t tsc_count_start = ATOMIC_INIT(0); -static atomic_t tsc_count_stop = ATOMIC_INIT(0); -static unsigned long long tsc_values[NR_CPUS]; +static struct { + atomic_t start_flag; + atomic_t count_start; + atomic_t count_stop; + unsigned long long values[NR_CPUS]; +} tsc __initdata = { + .start_flag = ATOMIC_INIT(0), + .count_start = ATOMIC_INIT(0), + .count_stop = ATOMIC_INIT(0), +}; #define NR_LOOPS 5 -static void __init synchronize_tsc_bp (void) +static void __init synchronize_tsc_bp(void) { int i; unsigned long long t0; @@ -233,7 +239,7 @@ static void __init synchronize_tsc_bp (void) /* convert from kcyc/sec to cyc/usec */ one_usec = cpu_khz / 1000; - atomic_set(&tsc_start_flag, 1); + atomic_set(&tsc.start_flag, 1); wmb(); /* @@ -250,16 +256,16 @@ static void __init synchronize_tsc_bp (void) /* * all APs synchronize but they loop on '== num_cpus' */ - while (atomic_read(&tsc_count_start) != num_booting_cpus()-1) + while (atomic_read(&tsc.count_start) != num_booting_cpus()-1) cpu_relax(); - atomic_set(&tsc_count_stop, 0); + atomic_set(&tsc.count_stop, 0); wmb(); /* * this lets the APs save their current TSC: */ - atomic_inc(&tsc_count_start); + atomic_inc(&tsc.count_start); - rdtscll(tsc_values[smp_processor_id()]); + rdtscll(tsc.values[smp_processor_id()]); /* * We clear the TSC in the last loop: */ @@ -269,56 +275,54 @@ static void __init synchronize_tsc_bp (void) /* * Wait for all APs to leave the synchronization point: */ - while (atomic_read(&tsc_count_stop) != num_booting_cpus()-1) + while (atomic_read(&tsc.count_stop) != num_booting_cpus()-1) cpu_relax(); - atomic_set(&tsc_count_start, 0); + atomic_set(&tsc.count_start, 0); wmb(); - atomic_inc(&tsc_count_stop); + atomic_inc(&tsc.count_stop); } sum = 0; for (i = 0; i < NR_CPUS; i++) { if (cpu_isset(i, cpu_callout_map)) { - t0 = tsc_values[i]; + t0 = tsc.values[i]; sum += t0; } } avg = sum; do_div(avg, num_booting_cpus()); - sum = 0; for (i = 0; i < NR_CPUS; i++) { if (!cpu_isset(i, cpu_callout_map)) continue; - delta = tsc_values[i] - avg; + delta = tsc.values[i] - avg; if (delta < 0) delta = -delta; /* * We report bigger than 2 microseconds clock differences. */ if (delta > 2*one_usec) { - long realdelta; + long long realdelta; + if (!buggy) { buggy = 1; printk("\n"); } realdelta = delta; do_div(realdelta, one_usec); - if (tsc_values[i] < avg) + if (tsc.values[i] < avg) realdelta = -realdelta; - if (realdelta > 0) - printk(KERN_INFO "CPU#%d had %ld usecs TSC " + if (realdelta) + printk(KERN_INFO "CPU#%d had %Ld usecs TSC " "skew, fixed it up.\n", i, realdelta); } - - sum += delta; } if (!buggy) printk("passed.\n"); } -static void __init synchronize_tsc_ap (void) +static void __init synchronize_tsc_ap(void) { int i; @@ -327,20 +331,20 @@ static void __init synchronize_tsc_ap (void) * this gets called, so we first wait for the BP to * finish SMP initialization: */ - while (!atomic_read(&tsc_start_flag)) + while (!atomic_read(&tsc.start_flag)) cpu_relax(); for (i = 0; i < NR_LOOPS; i++) { - atomic_inc(&tsc_count_start); - while (atomic_read(&tsc_count_start) != num_booting_cpus()) + atomic_inc(&tsc.count_start); + while (atomic_read(&tsc.count_start) != num_booting_cpus()) cpu_relax(); - rdtscll(tsc_values[smp_processor_id()]); + rdtscll(tsc.values[smp_processor_id()]); if (i == NR_LOOPS-1) write_tsc(0, 0); - atomic_inc(&tsc_count_stop); - while (atomic_read(&tsc_count_stop) != num_booting_cpus()) + atomic_inc(&tsc.count_stop); + while (atomic_read(&tsc.count_stop) != num_booting_cpus()) cpu_relax(); } } diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c index 316421a7f56..edd00f6cee3 100644 --- a/arch/i386/kernel/time.c +++ b/arch/i386/kernel/time.c @@ -135,7 +135,7 @@ unsigned long profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); - if (in_lock_functions(pc)) + if (!user_mode_vm(regs) && in_lock_functions(pc)) return *(unsigned long *)(regs->ebp + 4); return pc; @@ -206,15 +206,16 @@ irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) unsigned long get_cmos_time(void) { unsigned long retval; + unsigned long flags; - spin_lock(&rtc_lock); + spin_lock_irqsave(&rtc_lock, flags); if (efi_enabled) retval = efi_get_time(); else retval = mach_get_cmos_time(); - spin_unlock(&rtc_lock); + spin_unlock_irqrestore(&rtc_lock, flags); return retval; } diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index 2bf8b55b91f..7e9edafffd8 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -92,7 +92,11 @@ asmlinkage void spurious_interrupt_bug(void); asmlinkage void machine_check(void); static int kstack_depth_to_print = 24; +#ifdef CONFIG_STACK_UNWIND static int call_trace = 1; +#else +#define call_trace (-1) +#endif ATOMIC_NOTIFIER_HEAD(i386die_chain); int register_die_notifier(struct notifier_block *nb) @@ -100,13 +104,13 @@ int register_die_notifier(struct notifier_block *nb) vmalloc_sync_all(); return atomic_notifier_chain_register(&i386die_chain, nb); } -EXPORT_SYMBOL(register_die_notifier); +EXPORT_SYMBOL(register_die_notifier); /* used modular by kdb */ int unregister_die_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&i386die_chain, nb); } -EXPORT_SYMBOL(unregister_die_notifier); +EXPORT_SYMBOL(unregister_die_notifier); /* used modular by kdb */ static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) { @@ -188,10 +192,20 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unw_ret = show_trace_unwind(&info, log_lvl); } if (unw_ret > 0) { - if (call_trace > 0) + if (call_trace == 1 && !arch_unw_user_mode(&info)) { + print_symbol("DWARF2 unwinder stuck at %s\n", + UNW_PC(&info)); + if (UNW_SP(&info) >= PAGE_OFFSET) { + printk("Leftover inexact backtrace:\n"); + stack = (void *)UNW_SP(&info); + } else + printk("Full inexact backtrace again:\n"); + } else if (call_trace >= 1) return; - printk("%sLegacy call trace:\n", log_lvl); - } + else + printk("Full inexact backtrace again:\n"); + } else + printk("Inexact backtrace:\n"); } if (task == current) { @@ -324,35 +338,35 @@ void show_registers(struct pt_regs *regs) static void handle_BUG(struct pt_regs *regs) { + unsigned long eip = regs->eip; unsigned short ud2; - unsigned short line; - char *file; - char c; - unsigned long eip; - - eip = regs->eip; if (eip < PAGE_OFFSET) - goto no_bug; + return; if (__get_user(ud2, (unsigned short __user *)eip)) - goto no_bug; + return; if (ud2 != 0x0b0f) - goto no_bug; - if (__get_user(line, (unsigned short __user *)(eip + 2))) - goto bug; - if (__get_user(file, (char * __user *)(eip + 4)) || - (unsigned long)file < PAGE_OFFSET || __get_user(c, file)) - file = "<bad filename>"; + return; printk(KERN_EMERG "------------[ cut here ]------------\n"); - printk(KERN_EMERG "kernel BUG at %s:%d!\n", file, line); -no_bug: - return; +#ifdef CONFIG_DEBUG_BUGVERBOSE + do { + unsigned short line; + char *file; + char c; + + if (__get_user(line, (unsigned short __user *)(eip + 2))) + break; + if (__get_user(file, (char * __user *)(eip + 4)) || + (unsigned long)file < PAGE_OFFSET || __get_user(c, file)) + file = "<bad filename>"; - /* Here we know it was a BUG but file-n-line is unavailable */ -bug: - printk(KERN_EMERG "Kernel BUG\n"); + printk(KERN_EMERG "kernel BUG at %s:%d!\n", file, line); + return; + } while (0); +#endif + printk(KERN_EMERG "Kernel BUG at [verbose debug info unavailable]\n"); } /* This is gone through when something in the kernel @@ -442,11 +456,9 @@ void die(const char * str, struct pt_regs * regs, long err) if (in_interrupt()) panic("Fatal exception in interrupt"); - if (panic_on_oops) { - printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n"); - ssleep(5); + if (panic_on_oops) panic("Fatal exception"); - } + oops_exit(); do_exit(SIGSEGV); } @@ -1232,14 +1244,18 @@ static int __init kstack_setup(char *s) } __setup("kstack=", kstack_setup); +#ifdef CONFIG_STACK_UNWIND static int __init call_trace_setup(char *s) { if (strcmp(s, "old") == 0) call_trace = -1; else if (strcmp(s, "both") == 0) call_trace = 0; - else if (strcmp(s, "new") == 0) + else if (strcmp(s, "newfallback") == 0) call_trace = 1; + else if (strcmp(s, "new") == 2) + call_trace = 2; return 1; } __setup("call_trace=", call_trace_setup); +#endif diff --git a/arch/i386/kernel/vsyscall.lds.S b/arch/i386/kernel/vsyscall.lds.S index e26975fc68b..f66cd11adb7 100644 --- a/arch/i386/kernel/vsyscall.lds.S +++ b/arch/i386/kernel/vsyscall.lds.S @@ -10,6 +10,7 @@ SECTIONS . = VDSO_PRELINK + SIZEOF_HEADERS; .hash : { *(.hash) } :text + .gnu.hash : { *(.gnu.hash) } .dynsym : { *(.dynsym) } .dynstr : { *(.dynstr) } .gnu.version : { *(.gnu.version) } diff --git a/arch/i386/lib/usercopy.c b/arch/i386/lib/usercopy.c index 4b75212ab6d..efc7e7d5f4d 100644 --- a/arch/i386/lib/usercopy.c +++ b/arch/i386/lib/usercopy.c @@ -843,7 +843,6 @@ unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *fr unsigned long copy_to_user(void __user *to, const void *from, unsigned long n) { - might_sleep(); BUG_ON((long) n < 0); if (access_ok(VERIFY_WRITE, to, n)) n = __copy_to_user(to, from, n); @@ -870,7 +869,6 @@ EXPORT_SYMBOL(copy_to_user); unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) { - might_sleep(); BUG_ON((long) n < 0); if (access_ok(VERIFY_READ, from, n)) n = __copy_from_user(to, from, n); diff --git a/arch/i386/oprofile/nmi_int.c b/arch/i386/oprofile/nmi_int.c index fa8a37bcb39..5f8dc8a21bd 100644 --- a/arch/i386/oprofile/nmi_int.c +++ b/arch/i386/oprofile/nmi_int.c @@ -13,6 +13,7 @@ #include <linux/oprofile.h> #include <linux/sysdev.h> #include <linux/slab.h> +#include <linux/moduleparam.h> #include <asm/nmi.h> #include <asm/msr.h> #include <asm/apic.h> @@ -296,12 +297,14 @@ static int nmi_create_files(struct super_block * sb, struct dentry * root) return 0; } +static int p4force; +module_param(p4force, int, 0); static int __init p4_init(char ** cpu_type) { __u8 cpu_model = boot_cpu_data.x86_model; - if (cpu_model > 4) + if (!p4force && (cpu_model > 6 || cpu_model == 5)) return 0; #ifndef CONFIG_SMP @@ -334,6 +337,8 @@ static int __init ppro_init(char ** cpu_type) if (cpu_model == 14) *cpu_type = "i386/core"; + else if (cpu_model == 15) + *cpu_type = "i386/core_2"; else if (cpu_model > 0xd) return 0; else if (cpu_model == 9) { diff --git a/arch/i386/pci/common.c b/arch/i386/pci/common.c index c624b61e110..1220dd828ce 100644 --- a/arch/i386/pci/common.c +++ b/arch/i386/pci/common.c @@ -17,10 +17,6 @@ #include "pci.h" -#ifdef CONFIG_PCI_BIOS -extern void pcibios_sort(void); -#endif - unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | PCI_PROBE_MMCONF; @@ -241,6 +237,11 @@ char * __devinit pcibios_setup(char *str) pci_probe &= ~PCI_PROBE_MMCONF; return NULL; } + /* override DMI blacklist */ + else if (!strcmp(str, "mmconf")) { + pci_probe |= PCI_PROBE_MMCONF_FORCE; + return NULL; + } #endif else if (!strcmp(str, "noacpi")) { acpi_noirq_set(); diff --git a/arch/i386/pci/init.c b/arch/i386/pci/init.c index c7650a7e0b0..51087a9d917 100644 --- a/arch/i386/pci/init.c +++ b/arch/i386/pci/init.c @@ -14,8 +14,12 @@ static __init int pci_access_init(void) #ifdef CONFIG_PCI_BIOS pci_pcbios_init(); #endif - if (raw_pci_ops) - return 0; + /* + * don't check for raw_pci_ops here because we want pcbios as last + * fallback, yet it's needed to run first to set pcibios_last_bus + * in case legacy PCI probing is used. otherwise detecting peer busses + * fails. + */ #ifdef CONFIG_PCI_DIRECT pci_direct_init(); #endif diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c index e545b0992c4..ef5a2faa7d8 100644 --- a/arch/i386/pci/mmconfig.c +++ b/arch/i386/pci/mmconfig.c @@ -12,6 +12,7 @@ #include <linux/pci.h> #include <linux/init.h> #include <linux/acpi.h> +#include <linux/dmi.h> #include <asm/e820.h> #include "pci.h" @@ -178,7 +179,7 @@ static __init void unreachable_devices(void) pci_exp_set_dev_base(addr, k, PCI_DEVFN(i, 0)); if (addr == 0 || readl((u32 __iomem *)mmcfg_virt_addr) != val1) { - set_bit(i, fallback_slots); + set_bit(i + 32*k, fallback_slots); printk(KERN_NOTICE "PCI: No mmconfig possible on %x:%x\n", k, i); } @@ -187,9 +188,31 @@ static __init void unreachable_devices(void) } } +static int disable_mcfg(struct dmi_system_id *d) +{ + printk("PCI: %s detected. Disabling MCFG.\n", d->ident); + pci_probe &= ~PCI_PROBE_MMCONF; + return 0; +} + +static struct dmi_system_id __initdata dmi_bad_mcfg[] = { + /* Has broken MCFG table that makes the system hang when used */ + { + .callback = disable_mcfg, + .ident = "Intel D3C5105 SDV", + .matches = { + DMI_MATCH(DMI_BIOS_VENDOR, "Intel"), + DMI_MATCH(DMI_BOARD_NAME, "D26928"), + }, + }, + {} +}; + void __init pci_mmcfg_init(void) { - if ((pci_probe & PCI_PROBE_MMCONF) == 0) + dmi_check_system(dmi_bad_mcfg); + + if ((pci_probe & (PCI_PROBE_MMCONF_FORCE|PCI_PROBE_MMCONF)) == 0) return; acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg); @@ -198,15 +221,6 @@ void __init pci_mmcfg_init(void) (pci_mmcfg_config[0].base_address == 0)) return; - if (!e820_all_mapped(pci_mmcfg_config[0].base_address, - pci_mmcfg_config[0].base_address + MMCONFIG_APER_MIN, - E820_RESERVED)) { - printk(KERN_ERR "PCI: BIOS Bug: MCFG area at %x is not E820-reserved\n", - pci_mmcfg_config[0].base_address); - printk(KERN_ERR "PCI: Not using MMCONFIG.\n"); - return; - } - printk(KERN_INFO "PCI: Using MMCONFIG\n"); raw_pci_ops = &pci_mmcfg; pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF; diff --git a/arch/i386/pci/pci.h b/arch/i386/pci/pci.h index 12bf3d8dda2..49a849b3a24 100644 --- a/arch/i386/pci/pci.h +++ b/arch/i386/pci/pci.h @@ -16,7 +16,8 @@ #define PCI_PROBE_CONF1 0x0002 #define PCI_PROBE_CONF2 0x0004 #define PCI_PROBE_MMCONF 0x0008 -#define PCI_PROBE_MASK 0x000f +#define PCI_PROBE_MMCONF_FORCE 0x0010 +#define PCI_PROBE_MASK 0x00ff #define PCI_NO_SORT 0x0100 #define PCI_BIOS_SORT 0x0200 @@ -84,4 +85,4 @@ extern int pci_conf1_read(unsigned int seg, unsigned int bus, extern void pci_direct_init(void); extern void pci_pcbios_init(void); extern void pci_mmcfg_init(void); - +extern void pcibios_sort(void); |