diff options
Diffstat (limited to 'arch/i386')
44 files changed, 914 insertions, 572 deletions
diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index bfea1bedcbf..f17bd1d2707 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -37,6 +37,10 @@ config GENERIC_IOMAP bool default y +config GENERIC_HWEIGHT + bool + default y + config ARCH_MAY_HAVE_PC_FDC bool default y @@ -227,6 +231,15 @@ config SCHED_SMT cost of slightly increased overhead in some places. If unsure say N here. +config SCHED_MC + bool "Multi-core scheduler support" + depends on SMP + default y + help + Multi-core scheduler support improves the CPU scheduler's decision + making when dealing with multi-core CPU chips at a cost of slightly + increased overhead in some places. If unsure say N here. + source "kernel/Kconfig.preempt" config X86_UP_APIC @@ -737,7 +750,7 @@ config PHYSICAL_START config HOTPLUG_CPU bool "Support for hot-pluggable CPUs (EXPERIMENTAL)" - depends on SMP && HOTPLUG && EXPERIMENTAL && !X86_VOYAGER + depends on SMP && HOTPLUG && EXPERIMENTAL && !X86_VOYAGER && !X86_PC ---help--- Say Y here to experiment with turning CPUs off and on. CPUs can be controlled through /sys/devices/system/cpu. diff --git a/arch/i386/Kconfig.debug b/arch/i386/Kconfig.debug index 00108ba9a78..6e97df6979e 100644 --- a/arch/i386/Kconfig.debug +++ b/arch/i386/Kconfig.debug @@ -44,8 +44,8 @@ comment "Page alloc debug is incompatible with Software Suspend on i386" depends on DEBUG_KERNEL && SOFTWARE_SUSPEND config DEBUG_PAGEALLOC - bool "Page alloc debugging" - depends on DEBUG_KERNEL && !SOFTWARE_SUSPEND + bool "Debug page memory allocations" + depends on DEBUG_KERNEL && !SOFTWARE_SUSPEND && !HUGETLBFS help Unmap pages from the kernel linear mapping after free_pages(). This results in a large slowdown, but helps to find certain types diff --git a/arch/i386/Makefile b/arch/i386/Makefile index 36bef6543ac..3e4adb1e224 100644 --- a/arch/i386/Makefile +++ b/arch/i386/Makefile @@ -39,6 +39,9 @@ include $(srctree)/arch/i386/Makefile.cpu cflags-$(CONFIG_REGPARM) += -mregparm=3 +# temporary until string.h is fixed +cflags-y += -ffreestanding + # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use # a lot more stack due to the lack of sharing of stacklots: CFLAGS += $(shell if [ $(call cc-version) -lt 0400 ] ; then echo $(call cc-option,-fno-unit-at-a-time); fi ;) @@ -99,8 +102,8 @@ AFLAGS += $(mflags-y) boot := arch/i386/boot -.PHONY: zImage bzImage compressed zlilo bzlilo \ - zdisk bzdisk fdimage fdimage144 fdimage288 install +PHONY += zImage bzImage compressed zlilo bzlilo \ + zdisk bzdisk fdimage fdimage144 fdimage288 isoimage install all: bzImage @@ -119,7 +122,7 @@ zlilo bzlilo: vmlinux zdisk bzdisk: vmlinux $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zdisk -fdimage fdimage144 fdimage288: vmlinux +fdimage fdimage144 fdimage288 isoimage: vmlinux $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) $@ install: @@ -136,6 +139,9 @@ define archhelp echo ' install to $$(INSTALL_PATH) and run lilo' echo ' bzdisk - Create a boot floppy in /dev/fd0' echo ' fdimage - Create a boot floppy image' + echo ' isoimage - Create a boot CD-ROM image' endef -CLEAN_FILES += arch/$(ARCH)/boot/fdimage arch/$(ARCH)/boot/mtools.conf +CLEAN_FILES += arch/$(ARCH)/boot/fdimage \ + arch/$(ARCH)/boot/image.iso \ + arch/$(ARCH)/boot/mtools.conf diff --git a/arch/i386/Makefile.cpu b/arch/i386/Makefile.cpu index dcd936ef45d..a11befba26d 100644 --- a/arch/i386/Makefile.cpu +++ b/arch/i386/Makefile.cpu @@ -39,3 +39,7 @@ cflags-$(CONFIG_X86_ELAN) += -march=i486 # Geode GX1 support cflags-$(CONFIG_MGEODEGX1) += -march=pentium-mmx +# add at the end to overwrite eventual tuning options from earlier +# cpu entries +cflags-$(CONFIG_X86_GENERIC) += $(call tune,generic) + diff --git a/arch/i386/boot/Makefile b/arch/i386/boot/Makefile index f136752563b..33e55476381 100644 --- a/arch/i386/boot/Makefile +++ b/arch/i386/boot/Makefile @@ -62,8 +62,12 @@ $(obj)/setup $(obj)/bootsect: %: %.o FORCE $(obj)/compressed/vmlinux: FORCE $(Q)$(MAKE) $(build)=$(obj)/compressed IMAGE_OFFSET=$(IMAGE_OFFSET) $@ -# Set this if you want to pass append arguments to the zdisk/fdimage kernel +# Set this if you want to pass append arguments to the zdisk/fdimage/isoimage kernel FDARGS = +# Set this if you want an initrd included with the zdisk/fdimage/isoimage kernel +FDINITRD = + +image_cmdline = default linux $(FDARGS) $(if $(FDINITRD),initrd=initrd.img,) $(obj)/mtools.conf: $(src)/mtools.conf.in sed -e 's|@OBJ@|$(obj)|g' < $< > $@ @@ -72,8 +76,11 @@ $(obj)/mtools.conf: $(src)/mtools.conf.in zdisk: $(BOOTIMAGE) $(obj)/mtools.conf MTOOLSRC=$(obj)/mtools.conf mformat a: ; sync syslinux /dev/fd0 ; sync - echo 'default linux $(FDARGS)' | \ + echo '$(image_cmdline)' | \ MTOOLSRC=$(src)/mtools.conf mcopy - a:syslinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' a:initrd.img ; \ + fi MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) a:linux ; sync # These require being root or having syslinux 2.02 or higher installed @@ -81,18 +88,39 @@ fdimage fdimage144: $(BOOTIMAGE) $(obj)/mtools.conf dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=1440 MTOOLSRC=$(obj)/mtools.conf mformat v: ; sync syslinux $(obj)/fdimage ; sync - echo 'default linux $(FDARGS)' | \ + echo '$(image_cmdline)' | \ MTOOLSRC=$(obj)/mtools.conf mcopy - v:syslinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' v:initrd.img ; \ + fi MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) v:linux ; sync fdimage288: $(BOOTIMAGE) $(obj)/mtools.conf dd if=/dev/zero of=$(obj)/fdimage bs=1024 count=2880 MTOOLSRC=$(obj)/mtools.conf mformat w: ; sync syslinux $(obj)/fdimage ; sync - echo 'default linux $(FDARGS)' | \ + echo '$(image_cmdline)' | \ MTOOLSRC=$(obj)/mtools.conf mcopy - w:syslinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + MTOOLSRC=$(obj)/mtools.conf mcopy '$(FDINITRD)' w:initrd.img ; \ + fi MTOOLSRC=$(obj)/mtools.conf mcopy $(BOOTIMAGE) w:linux ; sync +isoimage: $(BOOTIMAGE) + -rm -rf $(obj)/isoimage + mkdir $(obj)/isoimage + cp `echo /usr/lib*/syslinux/isolinux.bin | awk '{ print $1; }'` \ + $(obj)/isoimage + cp $(BOOTIMAGE) $(obj)/isoimage/linux + echo '$(image_cmdline)' > $(obj)/isoimage/isolinux.cfg + if [ -f '$(FDINITRD)' ] ; then \ + cp '$(FDINITRD)' $(obj)/isoimage/initrd.img ; \ + fi + mkisofs -J -r -o $(obj)/image.iso -b isolinux.bin -c boot.cat \ + -no-emul-boot -boot-load-size 4 -boot-info-table \ + $(obj)/isoimage + rm -rf $(obj)/isoimage + zlilo: $(BOOTIMAGE) if [ -f $(INSTALL_PATH)/vmlinuz ]; then mv $(INSTALL_PATH)/vmlinuz $(INSTALL_PATH)/vmlinuz.old; fi if [ -f $(INSTALL_PATH)/System.map ]; then mv $(INSTALL_PATH)/System.map $(INSTALL_PATH)/System.old; fi diff --git a/arch/i386/boot/edd.S b/arch/i386/boot/edd.S index d8d69f2b911..4b84ea216f2 100644 --- a/arch/i386/boot/edd.S +++ b/arch/i386/boot/edd.S @@ -76,6 +76,8 @@ edd_mbr_sig_read: popw %es popw %bx jc edd_mbr_sig_done # on failure, we're done. + cmpb $0, %ah # some BIOSes do not set CF + jne edd_mbr_sig_done # on failure, we're done. movl (EDDBUF+EDD_MBR_SIG_OFFSET), %eax # read sig out of the MBR movl %eax, (%bx) # store success incb (EDD_MBR_SIG_NR_BUF) # note that we stored something diff --git a/arch/i386/boot/video.S b/arch/i386/boot/video.S index 2ac40c8244c..0000a267453 100644 --- a/arch/i386/boot/video.S +++ b/arch/i386/boot/video.S @@ -1924,6 +1924,7 @@ skip10: movb %ah, %al ret store_edid: +#ifdef CONFIG_FB_FIRMWARE_EDID pushw %es # just save all registers pushw %ax pushw %bx @@ -1954,6 +1955,7 @@ store_edid: popw %bx popw %ax popw %es +#endif ret # VIDEO_SELECT-only variables diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c index f1a21945963..033066176b3 100644 --- a/arch/i386/kernel/acpi/boot.c +++ b/arch/i386/kernel/acpi/boot.c @@ -668,10 +668,10 @@ unsigned long __init acpi_find_rsdp(void) unsigned long rsdp_phys = 0; if (efi_enabled) { - if (efi.acpi20) - return __pa(efi.acpi20); - else if (efi.acpi) - return __pa(efi.acpi); + if (efi.acpi20 != EFI_INVALID_TABLE_ADDR) + return efi.acpi20; + else if (efi.acpi != EFI_INVALID_TABLE_ADDR) + return efi.acpi; } /* * Scan memory looking for the RSDP signature. First search EBDA (low diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index 7e3d6b6a4e9..a06a49075f1 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -266,7 +266,7 @@ static void __init early_cpu_detect(void) void __cpuinit generic_identify(struct cpuinfo_x86 * c) { u32 tfms, xlvl; - int junk; + int ebx; if (have_cpuid_p()) { /* Get vendor name */ @@ -282,7 +282,7 @@ void __cpuinit generic_identify(struct cpuinfo_x86 * c) /* Intel-defined flags: level 0x00000001 */ if ( c->cpuid_level >= 0x00000001 ) { u32 capability, excap; - cpuid(0x00000001, &tfms, &junk, &excap, &capability); + cpuid(0x00000001, &tfms, &ebx, &excap, &capability); c->x86_capability[0] = capability; c->x86_capability[4] = excap; c->x86 = (tfms >> 8) & 15; @@ -292,6 +292,11 @@ void __cpuinit generic_identify(struct cpuinfo_x86 * c) if (c->x86 >= 0x6) c->x86_model += ((tfms >> 16) & 0xF) << 4; c->x86_mask = tfms & 15; +#ifdef CONFIG_SMP + c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0); +#else + c->apicid = (ebx >> 24) & 0xFF; +#endif } else { /* Have CPUID level 0 only - unheard of */ c->x86 = 4; @@ -474,7 +479,6 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) cpuid(1, &eax, &ebx, &ecx, &edx); - c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0); if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY)) return; diff --git a/arch/i386/kernel/cpu/cpufreq/Kconfig b/arch/i386/kernel/cpu/cpufreq/Kconfig index 26892d2099b..e44a4c6a4fe 100644 --- a/arch/i386/kernel/cpu/cpufreq/Kconfig +++ b/arch/i386/kernel/cpu/cpufreq/Kconfig @@ -96,7 +96,6 @@ 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. @@ -115,9 +114,9 @@ config X86_SPEEDSTEP_CENTRINO 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. - + For details, take a look at <file:Documentation/cpu-freq/>. - + If in doubt, say N. config X86_SPEEDSTEP_CENTRINO_ACPI @@ -148,7 +147,7 @@ config X86_SPEEDSTEP_ICH help This adds the CPUFreq driver for certain mobile Intel Pentium III (Coppermine), all mobile Intel Pentium III-M (Tualatin) and all - mobile Intel Pentium 4 P4-M on systems which have an Intel ICH2, + mobile Intel Pentium 4 P4-M on systems which have an Intel ICH2, ICH3 or ICH4 southbridge. For details, take a look at <file:Documentation/cpu-freq/>. @@ -161,7 +160,7 @@ config X86_SPEEDSTEP_SMI depends on EXPERIMENTAL help This adds the CPUFreq driver for certain mobile Intel Pentium III - (Coppermine), all mobile Intel Pentium III-M (Tualatin) + (Coppermine), all mobile Intel Pentium III-M (Tualatin) on systems which have an Intel 440BX/ZX/MX southbridge. For details, take a look at <file:Documentation/cpu-freq/>. @@ -203,9 +202,10 @@ config X86_LONGRUN config X86_LONGHAUL tristate "VIA Cyrix III Longhaul" select CPU_FREQ_TABLE + depends on BROKEN help - This adds the CPUFreq driver for VIA Samuel/CyrixIII, - VIA Cyrix Samuel/C3, VIA Cyrix Ezra and VIA Cyrix Ezra-T + This adds the CPUFreq driver for VIA Samuel/CyrixIII, + VIA Cyrix Samuel/C3, VIA Cyrix Ezra and VIA Cyrix Ezra-T processors. For details, take a look at <file:Documentation/cpu-freq/>. @@ -215,11 +215,11 @@ config X86_LONGHAUL comment "shared options" config X86_ACPI_CPUFREQ_PROC_INTF - bool "/proc/acpi/processor/../performance interface (deprecated)" + bool "/proc/acpi/processor/../performance interface (deprecated)" depends on PROC_FS depends on X86_ACPI_CPUFREQ || X86_SPEEDSTEP_CENTRINO_ACPI || X86_POWERNOW_K7_ACPI || X86_POWERNOW_K8_ACPI help - This enables the deprecated /proc/acpi/processor/../performance + This enables the deprecated /proc/acpi/processor/../performance interface. While it is helpful for debugging, the generic, cross-architecture cpufreq interfaces should be used. @@ -233,9 +233,9 @@ config X86_SPEEDSTEP_RELAXED_CAP_CHECK bool "Relaxed speedstep capability checks" depends on (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 - capable, don't always indicate that they are speedstep capable. This + Don't perform all checks for a speedstep capable system which would + normally be done. Some ancient or strange systems, though speedstep + capable, don't always indicate that they are speedstep capable. This option lets the probing code bypass some of those checks if the parameter "relaxed_check=1" is passed to the module. diff --git a/arch/i386/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/i386/kernel/cpu/cpufreq/cpufreq-nforce2.c index 2b62dee35c6..f275e0d4aee 100644 --- a/arch/i386/kernel/cpu/cpufreq/cpufreq-nforce2.c +++ b/arch/i386/kernel/cpu/cpufreq/cpufreq-nforce2.c @@ -39,7 +39,7 @@ static struct pci_dev *nforce2_chipset_dev; static int fid = 0; /* min_fsb, max_fsb: - * minimum and maximum FSB (= FSB at boot time) + * minimum and maximum FSB (= FSB at boot time) */ static int min_fsb = 0; static int max_fsb = 0; @@ -57,10 +57,10 @@ MODULE_PARM_DESC(min_fsb, #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "cpufreq-nforce2", msg) -/* +/** * nforce2_calc_fsb - calculate FSB * @pll: PLL value - * + * * Calculates FSB from PLL value */ static int nforce2_calc_fsb(int pll) @@ -76,10 +76,10 @@ static int nforce2_calc_fsb(int pll) return 0; } -/* +/** * nforce2_calc_pll - calculate PLL value * @fsb: FSB - * + * * Calculate PLL value for given FSB */ static int nforce2_calc_pll(unsigned int fsb) @@ -106,10 +106,10 @@ static int nforce2_calc_pll(unsigned int fsb) return NFORCE2_PLL(mul, div); } -/* +/** * nforce2_write_pll - write PLL value to chipset * @pll: PLL value - * + * * Writes new FSB PLL value to chipset */ static void nforce2_write_pll(int pll) @@ -121,15 +121,13 @@ static void nforce2_write_pll(int pll) pci_write_config_dword(nforce2_chipset_dev, NFORCE2_PLLADR, temp); /* Now write the value in all 64 registers */ - for (temp = 0; temp <= 0x3f; temp++) { - pci_write_config_dword(nforce2_chipset_dev, - NFORCE2_PLLREG, pll); - } + for (temp = 0; temp <= 0x3f; temp++) + pci_write_config_dword(nforce2_chipset_dev, NFORCE2_PLLREG, pll); return; } -/* +/** * nforce2_fsb_read - Read FSB * * Read FSB from chipset @@ -140,39 +138,32 @@ static unsigned int nforce2_fsb_read(int bootfsb) struct pci_dev *nforce2_sub5; u32 fsb, temp = 0; - /* Get chipset boot FSB from subdevice 5 (FSB at boot-time) */ nforce2_sub5 = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, - 0x01EF, - PCI_ANY_ID, - PCI_ANY_ID, - NULL); - + 0x01EF,PCI_ANY_ID,PCI_ANY_ID,NULL); if (!nforce2_sub5) return 0; pci_read_config_dword(nforce2_sub5, NFORCE2_BOOTFSB, &fsb); fsb /= 1000000; - + /* Check if PLL register is already set */ - pci_read_config_byte(nforce2_chipset_dev, - NFORCE2_PLLENABLE, (u8 *)&temp); - + pci_read_config_byte(nforce2_chipset_dev,NFORCE2_PLLENABLE, (u8 *)&temp); + if(bootfsb || !temp) return fsb; /* Use PLL register FSB value */ - pci_read_config_dword(nforce2_chipset_dev, - NFORCE2_PLLREG, &temp); + pci_read_config_dword(nforce2_chipset_dev,NFORCE2_PLLREG, &temp); fsb = nforce2_calc_fsb(temp); return fsb; } -/* +/** * nforce2_set_fsb - set new FSB * @fsb: New FSB - * + * * Sets new FSB */ static int nforce2_set_fsb(unsigned int fsb) @@ -186,7 +177,7 @@ static int nforce2_set_fsb(unsigned int fsb) printk(KERN_ERR "cpufreq: FSB %d is out of range!\n", fsb); return -EINVAL; } - + tfsb = nforce2_fsb_read(0); if (!tfsb) { printk(KERN_ERR "cpufreq: Error while reading the FSB\n"); @@ -194,8 +185,7 @@ static int nforce2_set_fsb(unsigned int fsb) } /* First write? Then set actual value */ - pci_read_config_byte(nforce2_chipset_dev, - NFORCE2_PLLENABLE, (u8 *)&temp); + pci_read_config_byte(nforce2_chipset_dev,NFORCE2_PLLENABLE, (u8 *)&temp); if (!temp) { pll = nforce2_calc_pll(tfsb); @@ -223,7 +213,7 @@ static int nforce2_set_fsb(unsigned int fsb) /* Calculate the PLL reg. value */ if ((pll = nforce2_calc_pll(tfsb)) == -1) return -EINVAL; - + nforce2_write_pll(pll); #ifdef NFORCE2_DELAY mdelay(NFORCE2_DELAY); @@ -239,7 +229,7 @@ static int nforce2_set_fsb(unsigned int fsb) /** * nforce2_get - get the CPU frequency * @cpu: CPU number - * + * * Returns the CPU frequency */ static unsigned int nforce2_get(unsigned int cpu) @@ -354,10 +344,10 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy) printk(KERN_INFO "cpufreq: FSB currently at %i MHz, FID %d.%d\n", fsb, fid / 10, fid % 10); - + /* Set maximum FSB to FSB at boot time */ max_fsb = nforce2_fsb_read(1); - + if(!max_fsb) return -EIO; @@ -398,17 +388,15 @@ static struct cpufreq_driver nforce2_driver = { * nforce2_detect_chipset - detect the Southbridge which contains FSB PLL logic * * Detects nForce2 A2 and C1 stepping - * + * */ static unsigned int nforce2_detect_chipset(void) { u8 revision; nforce2_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, - PCI_DEVICE_ID_NVIDIA_NFORCE2, - PCI_ANY_ID, - PCI_ANY_ID, - NULL); + PCI_DEVICE_ID_NVIDIA_NFORCE2, + PCI_ANY_ID, PCI_ANY_ID, NULL); if (nforce2_chipset_dev == NULL) return -ENODEV; diff --git a/arch/i386/kernel/cpu/cpufreq/elanfreq.c b/arch/i386/kernel/cpu/cpufreq/elanfreq.c index 3f7caa4ae6d..f317276afa7 100644 --- a/arch/i386/kernel/cpu/cpufreq/elanfreq.c +++ b/arch/i386/kernel/cpu/cpufreq/elanfreq.c @@ -1,16 +1,16 @@ /* - * elanfreq: cpufreq driver for the AMD ELAN family + * elanfreq: cpufreq driver for the AMD ELAN family * * (c) Copyright 2002 Robert Schwebel <r.schwebel@pengutronix.de> * - * Parts of this code are (c) Sven Geggus <sven@geggus.net> + * Parts of this code are (c) Sven Geggus <sven@geggus.net> * - * All Rights Reserved. + * All Rights Reserved. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. + * 2 of the License, or (at your option) any later version. * * 2002-02-13: - initial revision for 2.4.18-pre9 by Robert Schwebel * @@ -28,7 +28,7 @@ #include <asm/timex.h> #include <asm/io.h> -#define REG_CSCIR 0x22 /* Chip Setup and Control Index Register */ +#define REG_CSCIR 0x22 /* Chip Setup and Control Index Register */ #define REG_CSCDR 0x23 /* Chip Setup and Control Data Register */ /* Module parameter */ @@ -41,7 +41,7 @@ struct s_elan_multiplier { }; /* - * It is important that the frequencies + * It is important that the frequencies * are listed in ascending order here! */ struct s_elan_multiplier elan_multiplier[] = { @@ -72,78 +72,79 @@ static struct cpufreq_frequency_table elanfreq_table[] = { * elanfreq_get_cpu_frequency: determine current cpu speed * * Finds out at which frequency the CPU of the Elan SOC runs - * at the moment. Frequencies from 1 to 33 MHz are generated + * at the moment. Frequencies from 1 to 33 MHz are generated * the normal way, 66 and 99 MHz are called "Hyperspeed Mode" - * and have the rest of the chip running with 33 MHz. + * and have the rest of the chip running with 33 MHz. */ static unsigned int elanfreq_get_cpu_frequency(unsigned int cpu) { - u8 clockspeed_reg; /* Clock Speed Register */ - + u8 clockspeed_reg; /* Clock Speed Register */ + local_irq_disable(); - outb_p(0x80,REG_CSCIR); - clockspeed_reg = inb_p(REG_CSCDR); + outb_p(0x80,REG_CSCIR); + clockspeed_reg = inb_p(REG_CSCDR); local_irq_enable(); - if ((clockspeed_reg & 0xE0) == 0xE0) { return 0; } + if ((clockspeed_reg & 0xE0) == 0xE0) + return 0; - /* Are we in CPU clock multiplied mode (66/99 MHz)? */ - if ((clockspeed_reg & 0xE0) == 0xC0) { - if ((clockspeed_reg & 0x01) == 0) { + /* Are we in CPU clock multiplied mode (66/99 MHz)? */ + if ((clockspeed_reg & 0xE0) == 0xC0) { + if ((clockspeed_reg & 0x01) == 0) return 66000; - } else { - return 99000; - } - } + else + return 99000; + } /* 33 MHz is not 32 MHz... */ if ((clockspeed_reg & 0xE0)==0xA0) return 33000; - return ((1<<((clockspeed_reg & 0xE0) >> 5)) * 1000); + return ((1<<((clockspeed_reg & 0xE0) >> 5)) * 1000); } /** - * elanfreq_set_cpu_frequency: Change the CPU core frequency - * @cpu: cpu number + * elanfreq_set_cpu_frequency: Change the CPU core frequency + * @cpu: cpu number * @freq: frequency in kHz * - * This function takes a frequency value and changes the CPU frequency + * This function takes a frequency value and changes the CPU frequency * according to this. Note that the frequency has to be checked by * elanfreq_validatespeed() for correctness! - * - * There is no return value. + * + * There is no return value. */ -static void elanfreq_set_cpu_state (unsigned int state) { - +static void elanfreq_set_cpu_state (unsigned int state) +{ struct cpufreq_freqs freqs; freqs.old = elanfreq_get_cpu_frequency(0); freqs.new = elan_multiplier[state].clock; freqs.cpu = 0; /* elanfreq.c is UP only driver */ - + cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - printk(KERN_INFO "elanfreq: attempting to set frequency to %i kHz\n",elan_multiplier[state].clock); + printk(KERN_INFO "elanfreq: attempting to set frequency to %i kHz\n", + elan_multiplier[state].clock); - /* - * Access to the Elan's internal registers is indexed via - * 0x22: Chip Setup & Control Register Index Register (CSCI) - * 0x23: Chip Setup & Control Register Data Register (CSCD) + /* + * Access to the Elan's internal registers is indexed via + * 0x22: Chip Setup & Control Register Index Register (CSCI) + * 0x23: Chip Setup & Control Register Data Register (CSCD) * */ - /* - * 0x40 is the Power Management Unit's Force Mode Register. + /* + * 0x40 is the Power Management Unit's Force Mode Register. * Bit 6 enables Hyperspeed Mode (66/100 MHz core frequency) */ local_irq_disable(); - outb_p(0x40,REG_CSCIR); /* Disable hyperspeed mode */ + outb_p(0x40,REG_CSCIR); /* Disable hyperspeed mode */ outb_p(0x00,REG_CSCDR); local_irq_enable(); /* wait till internal pipelines and */ udelay(1000); /* buffers have cleaned up */ @@ -166,10 +167,10 @@ static void elanfreq_set_cpu_state (unsigned int state) { /** * elanfreq_validatespeed: test if frequency range is valid - * @policy: the policy to validate + * @policy: the policy to validate * - * This function checks if a given frequency range in kHz is valid - * for the hardware supported by the driver. + * This function checks if a given frequency range in kHz is valid + * for the hardware supported by the driver. */ static int elanfreq_verify (struct cpufreq_policy *policy) @@ -177,11 +178,11 @@ static int elanfreq_verify (struct cpufreq_policy *policy) return cpufreq_frequency_table_verify(policy, &elanfreq_table[0]); } -static int elanfreq_target (struct cpufreq_policy *policy, - unsigned int target_freq, +static int elanfreq_target (struct cpufreq_policy *policy, + unsigned int target_freq, unsigned int relation) { - unsigned int newstate = 0; + unsigned int newstate = 0; if (cpufreq_frequency_table_target(policy, &elanfreq_table[0], target_freq, relation, &newstate)) return -EINVAL; @@ -212,7 +213,7 @@ static int elanfreq_cpu_init(struct cpufreq_policy *policy) max_freq = elanfreq_get_cpu_frequency(0); /* table init */ - for (i=0; (elanfreq_table[i].frequency != CPUFREQ_TABLE_END); i++) { + for (i=0; (elanfreq_table[i].frequency != CPUFREQ_TABLE_END); i++) { if (elanfreq_table[i].frequency > max_freq) elanfreq_table[i].frequency = CPUFREQ_ENTRY_INVALID; } @@ -226,8 +227,7 @@ static int elanfreq_cpu_init(struct cpufreq_policy *policy) if (result) return (result); - cpufreq_frequency_table_get_attr(elanfreq_table, policy->cpu); - + cpufreq_frequency_table_get_attr(elanfreq_table, policy->cpu); return 0; } @@ -268,9 +268,9 @@ static struct freq_attr* elanfreq_attr[] = { static struct cpufreq_driver elanfreq_driver = { - .get = elanfreq_get_cpu_frequency, - .verify = elanfreq_verify, - .target = elanfreq_target, + .get = elanfreq_get_cpu_frequency, + .verify = elanfreq_verify, + .target = elanfreq_target, .init = elanfreq_cpu_init, .exit = elanfreq_cpu_exit, .name = "elanfreq", @@ -279,23 +279,21 @@ static struct cpufreq_driver elanfreq_driver = { }; -static int __init elanfreq_init(void) -{ +static int __init elanfreq_init(void) +{ struct cpuinfo_x86 *c = cpu_data; /* Test if we have the right hardware */ if ((c->x86_vendor != X86_VENDOR_AMD) || - (c->x86 != 4) || (c->x86_model!=10)) - { + (c->x86 != 4) || (c->x86_model!=10)) { printk(KERN_INFO "elanfreq: error: no Elan processor found!\n"); return -ENODEV; } - return cpufreq_register_driver(&elanfreq_driver); } -static void __exit elanfreq_exit(void) +static void __exit elanfreq_exit(void) { cpufreq_unregister_driver(&elanfreq_driver); } @@ -309,4 +307,3 @@ MODULE_DESCRIPTION("cpufreq driver for AMD's Elan CPUs"); module_init(elanfreq_init); module_exit(elanfreq_exit); - diff --git a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c index e86ea486c31..92afa3bc84f 100644 --- a/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c +++ b/arch/i386/kernel/cpu/cpufreq/gx-suspmod.c @@ -6,12 +6,12 @@ * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation + * version 2 as published by the Free Software Foundation * * The author(s) of this software shall not be held liable for damages * of any nature resulting due to the use of this software. This * software is provided AS-IS with no warranties. - * + * * Theoritical note: * * (see Geode(tm) CS5530 manual (rev.4.1) page.56) @@ -21,18 +21,18 @@ * * Suspend Modulation works by asserting and de-asserting the SUSP# pin * to CPU(GX1/GXLV) for configurable durations. When asserting SUSP# - * the CPU enters an idle state. GX1 stops its core clock when SUSP# is + * the CPU enters an idle state. GX1 stops its core clock when SUSP# is * asserted then power consumption is reduced. * - * Suspend Modulation's OFF/ON duration are configurable + * Suspend Modulation's OFF/ON duration are configurable * with 'Suspend Modulation OFF Count Register' * and 'Suspend Modulation ON Count Register'. - * These registers are 8bit counters that represent the number of + * These registers are 8bit counters that represent the number of * 32us intervals which the SUSP# pin is asserted(ON)/de-asserted(OFF) * to the processor. * - * These counters define a ratio which is the effective frequency - * of operation of the system. + * These counters define a ratio which is the effective frequency + * of operation of the system. * * OFF Count * F_eff = Fgx * ---------------------- @@ -40,24 +40,24 @@ * * 0 <= On Count, Off Count <= 255 * - * From these limits, we can get register values + * From these limits, we can get register values * * off_duration + on_duration <= MAX_DURATION * on_duration = off_duration * (stock_freq - freq) / freq * - * off_duration = (freq * DURATION) / stock_freq - * on_duration = DURATION - off_duration + * off_duration = (freq * DURATION) / stock_freq + * on_duration = DURATION - off_duration * * *--------------------------------------------------------------------------- * * ChangeLog: - * Dec. 12, 2003 Hiroshi Miura <miura@da-cha.org> - * - fix on/off register mistake - * - fix cpu_khz calc when it stops cpu modulation. + * Dec. 12, 2003 Hiroshi Miura <miura@da-cha.org> + * - fix on/off register mistake + * - fix cpu_khz calc when it stops cpu modulation. * - * Dec. 11, 2002 Hiroshi Miura <miura@da-cha.org> - * - rewrite for Cyrix MediaGX Cx5510/5520 and + * Dec. 11, 2002 Hiroshi Miura <miura@da-cha.org> + * - rewrite for Cyrix MediaGX Cx5510/5520 and * NatSemi Geode Cs5530(A). * * Jul. ??, 2002 Zwane Mwaikambo <zwane@commfireservices.com> @@ -74,40 +74,40 @@ ************************************************************************/ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/module.h> #include <linux/init.h> #include <linux/smp.h> #include <linux/cpufreq.h> #include <linux/pci.h> -#include <asm/processor.h> +#include <asm/processor.h> #include <asm/errno.h> /* PCI config registers, all at F0 */ -#define PCI_PMER1 0x80 /* power management enable register 1 */ -#define PCI_PMER2 0x81 /* power management enable register 2 */ -#define PCI_PMER3 0x82 /* power management enable register 3 */ -#define PCI_IRQTC 0x8c /* irq speedup timer counter register:typical 2 to 4ms */ -#define PCI_VIDTC 0x8d /* video speedup timer counter register: typical 50 to 100ms */ -#define PCI_MODOFF 0x94 /* suspend modulation OFF counter register, 1 = 32us */ -#define PCI_MODON 0x95 /* suspend modulation ON counter register */ -#define PCI_SUSCFG 0x96 /* suspend configuration register */ +#define PCI_PMER1 0x80 /* power management enable register 1 */ +#define PCI_PMER2 0x81 /* power management enable register 2 */ +#define PCI_PMER3 0x82 /* power management enable register 3 */ +#define PCI_IRQTC 0x8c /* irq speedup timer counter register:typical 2 to 4ms */ +#define PCI_VIDTC 0x8d /* video speedup timer counter register: typical 50 to 100ms */ +#define PCI_MODOFF 0x94 /* suspend modulation OFF counter register, 1 = 32us */ +#define PCI_MODON 0x95 /* suspend modulation ON counter register */ +#define PCI_SUSCFG 0x96 /* suspend configuration register */ /* PMER1 bits */ -#define GPM (1<<0) /* global power management */ -#define GIT (1<<1) /* globally enable PM device idle timers */ -#define GTR (1<<2) /* globally enable IO traps */ -#define IRQ_SPDUP (1<<3) /* disable clock throttle during interrupt handling */ -#define VID_SPDUP (1<<4) /* disable clock throttle during vga video handling */ +#define GPM (1<<0) /* global power management */ +#define GIT (1<<1) /* globally enable PM device idle timers */ +#define GTR (1<<2) /* globally enable IO traps */ +#define IRQ_SPDUP (1<<3) /* disable clock throttle during interrupt handling */ +#define VID_SPDUP (1<<4) /* disable clock throttle during vga video handling */ /* SUSCFG bits */ -#define SUSMOD (1<<0) /* enable/disable suspend modulation */ -/* the belows support 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 */ -#define PWRSVE_ISA (1<<3) /* stop ISA clock */ -#define PWRSVE (1<<4) /* active idle */ +#define SUSMOD (1<<0) /* enable/disable suspend modulation */ +/* the belows support 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 */ +#define PWRSVE_ISA (1<<3) /* stop ISA clock */ +#define PWRSVE (1<<4) /* active idle */ struct gxfreq_params { u8 on_duration; @@ -128,7 +128,7 @@ module_param (pci_busclk, int, 0444); /* maximum duration for which the cpu may be suspended * (32us * MAX_DURATION). If no parameter is given, this defaults - * to 255. + * to 255. * Note that this leads to a maximum of 8 ms(!) where the CPU clock * is suspended -- processing power is just 0.39% of what it used to be, * though. 781.25 kHz(!) for a 200 MHz processor -- wow. */ @@ -144,17 +144,17 @@ module_param (max_duration, int, 0444); #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "gx-suspmod", msg) /** - * we can detect a core multipiler from dir0_lsb - * from GX1 datasheet p.56, - * MULT[3:0]: - * 0000 = SYSCLK multiplied by 4 (test only) - * 0001 = SYSCLK multiplied by 10 - * 0010 = SYSCLK multiplied by 4 - * 0011 = SYSCLK multiplied by 6 - * 0100 = SYSCLK multiplied by 9 - * 0101 = SYSCLK multiplied by 5 - * 0110 = SYSCLK multiplied by 7 - * 0111 = SYSCLK multiplied by 8 + * we can detect a core multipiler from dir0_lsb + * from GX1 datasheet p.56, + * MULT[3:0]: + * 0000 = SYSCLK multiplied by 4 (test only) + * 0001 = SYSCLK multiplied by 10 + * 0010 = SYSCLK multiplied by 4 + * 0011 = SYSCLK multiplied by 6 + * 0100 = SYSCLK multiplied by 9 + * 0101 = SYSCLK multiplied by 5 + * 0110 = SYSCLK multiplied by 7 + * 0111 = SYSCLK multiplied by 8 * of 33.3MHz **/ static int gx_freq_mult[16] = { @@ -164,17 +164,17 @@ static int gx_freq_mult[16] = { /**************************************************************** - * Low Level chipset interface * + * Low Level chipset interface * ****************************************************************/ static struct pci_device_id gx_chipset_tbl[] __initdata = { - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, PCI_ANY_ID, PCI_ANY_ID }, - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5520, PCI_ANY_ID, PCI_ANY_ID }, - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5510, PCI_ANY_ID, PCI_ANY_ID }, - { 0, }, + { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, PCI_ANY_ID, PCI_ANY_ID }, + { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5520, PCI_ANY_ID, PCI_ANY_ID }, + { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5510, PCI_ANY_ID, PCI_ANY_ID }, + { 0, }, }; /** - * gx_detect_chipset: + * gx_detect_chipset: * **/ static __init struct pci_dev *gx_detect_chipset(void) @@ -182,17 +182,16 @@ static __init struct pci_dev *gx_detect_chipset(void) struct pci_dev *gx_pci = NULL; /* check if CPU is a MediaGX or a Geode. */ - if ((current_cpu_data.x86_vendor != X86_VENDOR_NSC) && + if ((current_cpu_data.x86_vendor != X86_VENDOR_NSC) && (current_cpu_data.x86_vendor != X86_VENDOR_CYRIX)) { dprintk("error: no MediaGX/Geode processor found!\n"); - return NULL; + return NULL; } /* detect which companion chip is used */ while ((gx_pci = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, gx_pci)) != NULL) { - if ((pci_match_id(gx_chipset_tbl, gx_pci)) != NULL) { + if ((pci_match_id(gx_chipset_tbl, gx_pci)) != NULL) return gx_pci; - } } dprintk("error: no supported chipset found!\n"); @@ -200,24 +199,24 @@ static __init struct pci_dev *gx_detect_chipset(void) } /** - * gx_get_cpuspeed: + * gx_get_cpuspeed: * * Finds out at which efficient frequency the Cyrix MediaGX/NatSemi Geode CPU runs. */ static unsigned int gx_get_cpuspeed(unsigned int cpu) { - if ((gx_params->pci_suscfg & SUSMOD) == 0) + if ((gx_params->pci_suscfg & SUSMOD) == 0) return stock_freq; - return (stock_freq * gx_params->off_duration) + return (stock_freq * gx_params->off_duration) / (gx_params->on_duration + gx_params->off_duration); } /** * gx_validate_speed: * determine current cpu speed - * -**/ + * + **/ static unsigned int gx_validate_speed(unsigned int khz, u8 *on_duration, u8 *off_duration) { @@ -230,7 +229,7 @@ static unsigned int gx_validate_speed(unsigned int khz, u8 *on_duration, u8 *off *on_duration=0; for (i=max_duration; i>0; i--) { - tmp_off = ((khz * i) / stock_freq) & 0xff; + tmp_off = ((khz * i) / stock_freq) & 0xff; tmp_on = i - tmp_off; tmp_freq = (stock_freq * tmp_off) / i; /* if this relation is closer to khz, use this. If it's equal, @@ -247,18 +246,17 @@ static unsigned int gx_validate_speed(unsigned int khz, u8 *on_duration, u8 *off /** - * gx_set_cpuspeed: - * set cpu speed in khz. + * gx_set_cpuspeed: + * set cpu speed in khz. **/ static void gx_set_cpuspeed(unsigned int khz) { - u8 suscfg, pmer1; + u8 suscfg, pmer1; unsigned int new_khz; unsigned long flags; struct cpufreq_freqs freqs; - freqs.cpu = 0; freqs.old = gx_get_cpuspeed(0); @@ -303,18 +301,18 @@ static void gx_set_cpuspeed(unsigned int khz) pci_write_config_byte(gx_params->cs55x0, PCI_MODOFF, gx_params->off_duration); pci_write_config_byte(gx_params->cs55x0, PCI_MODON, gx_params->on_duration); - pci_write_config_byte(gx_params->cs55x0, PCI_SUSCFG, suscfg); - pci_read_config_byte(gx_params->cs55x0, PCI_SUSCFG, &suscfg); + pci_write_config_byte(gx_params->cs55x0, PCI_SUSCFG, suscfg); + pci_read_config_byte(gx_params->cs55x0, PCI_SUSCFG, &suscfg); - local_irq_restore(flags); + local_irq_restore(flags); gx_params->pci_suscfg = suscfg; cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); - dprintk("suspend modulation w/ duration of ON:%d us, OFF:%d us\n", - gx_params->on_duration * 32, gx_params->off_duration * 32); - dprintk("suspend modulation w/ clock speed: %d kHz.\n", freqs.new); + dprintk("suspend modulation w/ duration of ON:%d us, OFF:%d us\n", + gx_params->on_duration * 32, gx_params->off_duration * 32); + dprintk("suspend modulation w/ clock speed: %d kHz.\n", freqs.new); } /**************************************************************** @@ -322,10 +320,10 @@ static void gx_set_cpuspeed(unsigned int khz) ****************************************************************/ /* - * cpufreq_gx_verify: test if frequency range is valid + * cpufreq_gx_verify: test if frequency range is valid * - * This function checks if a given frequency range in kHz is valid - * for the hardware supported by the driver. + * This function checks if a given frequency range in kHz is valid + * for the hardware supported by the driver. */ static int cpufreq_gx_verify(struct cpufreq_policy *policy) @@ -333,8 +331,8 @@ static int cpufreq_gx_verify(struct cpufreq_policy *policy) unsigned int tmp_freq = 0; u8 tmp1, tmp2; - if (!stock_freq || !policy) - return -EINVAL; + if (!stock_freq || !policy) + return -EINVAL; policy->cpu = 0; cpufreq_verify_within_limits(policy, (stock_freq / max_duration), stock_freq); @@ -342,14 +340,14 @@ static int cpufreq_gx_verify(struct cpufreq_policy *policy) /* it needs to be assured that at least one supported frequency is * within policy->min and policy->max. If it is not, policy->max * needs to be increased until one freuqency is supported. - * policy->min may not be decreased, though. This way we guarantee a + * policy->min may not be decreased, though. This way we guarantee a * specific processing capacity. */ tmp_freq = gx_validate_speed(policy->min, &tmp1, &tmp2); - if (tmp_freq < policy->min) + if (tmp_freq < policy->min) tmp_freq += stock_freq / max_duration; policy->min = tmp_freq; - if (policy->min > policy->max) + if (policy->min > policy->max) policy->max = tmp_freq; tmp_freq = gx_validate_speed(policy->max, &tmp1, &tmp2); if (tmp_freq > policy->max) @@ -358,12 +356,12 @@ static int cpufreq_gx_verify(struct cpufreq_policy *policy) if (policy->max < policy->min) policy->max = policy->min; cpufreq_verify_within_limits(policy, (stock_freq / max_duration), stock_freq); - + return 0; } /* - * cpufreq_gx_target: + * cpufreq_gx_target: * */ static int cpufreq_gx_target(struct cpufreq_policy *policy, @@ -373,8 +371,8 @@ static int cpufreq_gx_target(struct cpufreq_policy *policy, u8 tmp1, tmp2; unsigned int tmp_freq; - if (!stock_freq || !policy) - return -EINVAL; + if (!stock_freq || !policy) + return -EINVAL; policy->cpu = 0; @@ -431,7 +429,7 @@ static int cpufreq_gx_cpu_init(struct cpufreq_policy *policy) return 0; } -/* +/* * cpufreq_gx_init: * MediaGX/Geode GX initialize cpufreq driver */ @@ -452,7 +450,7 @@ static int __init cpufreq_gx_init(void) u32 class_rev; /* Test if we have the right hardware */ - if ((gx_pci = gx_detect_chipset()) == NULL) + if ((gx_pci = gx_detect_chipset()) == NULL) return -ENODEV; /* check whether module parameters are sane */ @@ -461,10 +459,9 @@ static int __init cpufreq_gx_init(void) dprintk("geode suspend modulation available.\n"); - params = kmalloc(sizeof(struct gxfreq_params), GFP_KERNEL); + params = kzalloc(sizeof(struct gxfreq_params), GFP_KERNEL); if (params == NULL) return -ENOMEM; - memset(params, 0, sizeof(struct gxfreq_params)); params->cs55x0 = gx_pci; gx_params = params; @@ -478,7 +475,7 @@ static int __init cpufreq_gx_init(void) pci_read_config_dword(params->cs55x0, PCI_CLASS_REVISION, &class_rev); params->pci_rev = class_rev && 0xff; - if ((ret = cpufreq_register_driver(&gx_suspmod_driver))) { + if ((ret = cpufreq_register_driver(&gx_suspmod_driver))) { kfree(params); return ret; /* register error! */ } diff --git a/arch/i386/kernel/cpu/cpufreq/longhaul.h b/arch/i386/kernel/cpu/cpufreq/longhaul.h index 2a495c162ec..d3a95d77ee8 100644 --- a/arch/i386/kernel/cpu/cpufreq/longhaul.h +++ b/arch/i386/kernel/cpu/cpufreq/longhaul.h @@ -234,7 +234,7 @@ static int __initdata ezrat_eblcr[32] = { /* * VIA C3 Nehemiah */ - + static int __initdata nehemiah_a_clock_ratio[32] = { 100, /* 0000 -> 10.0x */ 160, /* 0001 -> 16.0x */ @@ -446,7 +446,7 @@ static int __initdata nehemiah_c_eblcr[32] = { /* end of table */ }; -/* +/* * Voltage scales. Div/Mod by 1000 to get actual voltage. * Which scale to use depends on the VRM type in use. */ diff --git a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c index cc73a7ae34b..ab6504efd80 100644 --- a/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/i386/kernel/cpu/cpufreq/p4-clockmod.c @@ -14,7 +14,7 @@ * The author(s) of this software shall not be held liable for damages * of any nature resulting due to the use of this software. This * software is provided AS-IS with no warranties. - * + * * Date Errata Description * 20020525 N44, O17 12.5% or 25% DC causes lockup * @@ -22,7 +22,7 @@ #include <linux/config.h> #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/module.h> #include <linux/init.h> #include <linux/smp.h> #include <linux/cpufreq.h> @@ -30,7 +30,7 @@ #include <linux/cpumask.h> #include <linux/sched.h> /* current / set_cpus_allowed() */ -#include <asm/processor.h> +#include <asm/processor.h> #include <asm/msr.h> #include <asm/timex.h> @@ -79,7 +79,7 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate) } else { dprintk("CPU#%d setting duty cycle to %d%%\n", cpu, ((125 * newstate) / 10)); - /* bits 63 - 5 : reserved + /* bits 63 - 5 : reserved * bit 4 : enable/disable * bits 3-1 : duty cycle * bit 0 : reserved @@ -132,7 +132,7 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy, } /* run on each logical CPU, see section 13.15.3 of IA32 Intel Architecture Software - * Developer's Manual, Volume 3 + * Developer's Manual, Volume 3 */ cpus_allowed = current->cpus_allowed; @@ -206,7 +206,7 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_P4D); } - + static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) { @@ -234,7 +234,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) dprintk("has errata -- disabling frequencies lower than 2ghz\n"); break; } - + /* get max frequency */ stock_freq = cpufreq_p4_get_frequency(c); if (!stock_freq) @@ -244,13 +244,13 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) for (i=1; (p4clockmod_table[i].frequency != CPUFREQ_TABLE_END); i++) { if ((i<2) && (has_N44_O17_errata[policy->cpu])) p4clockmod_table[i].frequency = CPUFREQ_ENTRY_INVALID; - else if (has_N60_errata[policy->cpu] && p4clockmod_table[i].frequency < 2000000) + else if (has_N60_errata[policy->cpu] && ((stock_freq * i)/8) < 2000000) p4clockmod_table[i].frequency = CPUFREQ_ENTRY_INVALID; else p4clockmod_table[i].frequency = (stock_freq * i)/8; } cpufreq_frequency_table_get_attr(p4clockmod_table, policy->cpu); - + /* cpuinfo and default policy values */ policy->governor = CPUFREQ_DEFAULT_GOVERNOR; policy->cpuinfo.transition_latency = 1000000; /* assumed */ @@ -262,7 +262,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) static int cpufreq_p4_cpu_exit(struct cpufreq_policy *policy) { - cpufreq_frequency_table_put_attr(policy->cpu); + cpufreq_frequency_table_put_attr(policy->cpu); return 0; } @@ -298,7 +298,7 @@ static struct freq_attr* p4clockmod_attr[] = { }; static struct cpufreq_driver p4clockmod_driver = { - .verify = cpufreq_p4_verify, + .verify = cpufreq_p4_verify, .target = cpufreq_p4_target, .init = cpufreq_p4_cpu_init, .exit = cpufreq_p4_cpu_exit, @@ -310,12 +310,12 @@ static struct cpufreq_driver p4clockmod_driver = { static int __init cpufreq_p4_init(void) -{ +{ struct cpuinfo_x86 *c = cpu_data; int ret; /* - * THERM_CONTROL is architectural for IA32 now, so + * THERM_CONTROL is architectural for IA32 now, so * we can rely on the capability checks */ if (c->x86_vendor != X86_VENDOR_INTEL) diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k6.c b/arch/i386/kernel/cpu/cpufreq/powernow-k6.c index 222f8cfe3c5..f89524051e4 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k6.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k6.c @@ -8,7 +8,7 @@ */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/module.h> #include <linux/init.h> #include <linux/cpufreq.h> #include <linux/ioport.h> @@ -50,7 +50,7 @@ static int powernow_k6_get_cpu_multiplier(void) { u64 invalue = 0; u32 msrval; - + msrval = POWERNOW_IOPORT + 0x1; wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */ invalue=inl(POWERNOW_IOPORT + 0x8); @@ -81,7 +81,7 @@ static void powernow_k6_set_state (unsigned int best_i) freqs.old = busfreq * powernow_k6_get_cpu_multiplier(); freqs.new = busfreq * clock_ratio[best_i].index; freqs.cpu = 0; /* powernow-k6.c is UP only driver */ - + cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); /* we now need to transform best_i to the BVC format, see AMD#23446 */ @@ -152,7 +152,7 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy) busfreq = cpu_khz / max_multiplier; /* table init */ - for (i=0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) { + for (i=0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) { if (clock_ratio[i].index > max_multiplier) clock_ratio[i].frequency = CPUFREQ_ENTRY_INVALID; else @@ -182,7 +182,7 @@ static int powernow_k6_cpu_exit(struct cpufreq_policy *policy) powernow_k6_set_state(i); } cpufreq_frequency_table_put_attr(policy->cpu); - return 0; + return 0; } static unsigned int powernow_k6_get(unsigned int cpu) @@ -196,8 +196,8 @@ static struct freq_attr* powernow_k6_attr[] = { }; static struct cpufreq_driver powernow_k6_driver = { - .verify = powernow_k6_verify, - .target = powernow_k6_target, + .verify = powernow_k6_verify, + .target = powernow_k6_target, .init = powernow_k6_cpu_init, .exit = powernow_k6_cpu_exit, .get = powernow_k6_get, @@ -215,7 +215,7 @@ static struct cpufreq_driver powernow_k6_driver = { * on success. */ static int __init powernow_k6_init(void) -{ +{ struct cpuinfo_x86 *c = cpu_data; if ((c->x86_vendor != X86_VENDOR_AMD) || (c->x86 != 5) || diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k7.c b/arch/i386/kernel/cpu/cpufreq/powernow-k7.c index edcd626001d..2bf4237cb94 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k7.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k7.c @@ -199,8 +199,8 @@ static int get_ranges (unsigned char *pst) powernow_table[j].index |= (vid << 8); /* upper 8 bits */ dprintk (" FID: 0x%x (%d.%dx [%dMHz]) " - "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10, - fid_codes[fid] % 10, speed/1000, vid, + "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10, + fid_codes[fid] % 10, speed/1000, vid, mobile_vid_table[vid]/1000, mobile_vid_table[vid]%1000); } @@ -368,8 +368,8 @@ static int powernow_acpi_init(void) } dprintk (" FID: 0x%x (%d.%dx [%dMHz]) " - "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10, - fid_codes[fid] % 10, speed/1000, vid, + "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10, + fid_codes[fid] % 10, speed/1000, vid, mobile_vid_table[vid]/1000, mobile_vid_table[vid]%1000); @@ -460,7 +460,7 @@ static int powernow_decode_bios (int maxfid, int startvid) (maxfid==pst->maxfid) && (startvid==pst->startvid)) { dprintk ("PST:%d (@%p)\n", i, pst); - dprintk (" cpuid: 0x%x fsb: %d maxFID: 0x%x startvid: 0x%x\n", + dprintk (" cpuid: 0x%x fsb: %d maxFID: 0x%x startvid: 0x%x\n", pst->cpuid, pst->fsbspeed, pst->maxfid, pst->startvid); ret = get_ranges ((char *) pst + sizeof (struct pst_s)); diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c index 798da7c2b5d..712a26bd445 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.c @@ -40,21 +40,22 @@ #ifdef CONFIG_X86_POWERNOW_K8_ACPI #include <linux/acpi.h> +#include <linux/mutex.h> #include <acpi/processor.h> #endif #define PFX "powernow-k8: " #define BFX PFX "BIOS error: " -#define VERSION "version 1.60.0" +#define VERSION "version 1.60.1" #include "powernow-k8.h" /* serialize freq changes */ -static DECLARE_MUTEX(fidvid_sem); +static DEFINE_MUTEX(fidvid_mutex); static struct powernow_k8_data *powernow_data[NR_CPUS]; #ifndef CONFIG_SMP -static cpumask_t cpu_core_map[1]; +static cpumask_t cpu_core_map[1] = { CPU_MASK_ALL }; #endif /* Return a frequency in MHz, given an input fid */ @@ -83,11 +84,10 @@ static u32 find_millivolts_from_vid(struct powernow_k8_data *data, u32 vid) */ static u32 convert_fid_to_vco_fid(u32 fid) { - if (fid < HI_FID_TABLE_BOTTOM) { + if (fid < HI_FID_TABLE_BOTTOM) return 8 + (2 * fid); - } else { + else return fid; - } } /* @@ -177,7 +177,7 @@ static int write_new_fid(struct powernow_k8_data *data, u32 fid) if (i++ > 100) { printk(KERN_ERR PFX "internal error - pending bit very stuck - no further pstate changes possible\n"); return 1; - } + } } while (query_current_values_with_pending_wait(data)); count_off_irt(data); @@ -474,8 +474,10 @@ static int check_supported_cpu(unsigned int cpu) goto out; eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE); + if ((eax & CPUID_XFAM) != CPUID_XFAM_K8) + goto out; + if (((eax & CPUID_USE_XFAM_XMOD) != CPUID_USE_XFAM_XMOD) || - ((eax & CPUID_XFAM) != CPUID_XFAM_K8) || ((eax & CPUID_XMOD) > CPUID_XMOD_REV_G)) { printk(KERN_INFO PFX "Processor cpuid %x not supported\n", eax); goto out; @@ -780,9 +782,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) /* verify only 1 entry from the lo frequency table */ if (fid < HI_FID_TABLE_BOTTOM) { if (cntlofreq) { - /* if both entries are the same, ignore this - * one... - */ + /* if both entries are the same, ignore this one ... */ if ((powernow_table[i].frequency != powernow_table[cntlofreq].frequency) || (powernow_table[i].index != powernow_table[cntlofreq].index)) { printk(KERN_ERR PFX "Too many lo freq table entries\n"); @@ -854,7 +854,7 @@ static int transition_frequency(struct powernow_k8_data *data, unsigned int inde dprintk("cpu %d transition to index %u\n", smp_processor_id(), index); /* fid are the lower 8 bits of the index we stored into - * the cpufreq frequency table in find_psb_table, vid are + * the cpufreq frequency table in find_psb_table, vid are * the upper 8 bits. */ @@ -909,7 +909,6 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi u32 checkvid = data->currvid; unsigned int newstate; int ret = -EIO; - int i; /* only run on specific CPU from here on */ oldmask = current->cpus_allowed; @@ -945,23 +944,17 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi if (cpufreq_frequency_table_target(pol, data->powernow_table, targfreq, relation, &newstate)) goto err_out; - down(&fidvid_sem); + mutex_lock(&fidvid_mutex); powernow_k8_acpi_pst_values(data, newstate); if (transition_frequency(data, newstate)) { printk(KERN_ERR PFX "transition frequency failed\n"); ret = 1; - up(&fidvid_sem); + mutex_unlock(&fidvid_mutex); goto err_out; } - - /* Update all the fid/vids of our siblings */ - for_each_cpu_mask(i, cpu_core_map[pol->cpu]) { - powernow_data[i]->currvid = data->currvid; - powernow_data[i]->currfid = data->currfid; - } - up(&fidvid_sem); + mutex_unlock(&fidvid_mutex); pol->cur = find_khz_freq_from_fid(data->currfid); ret = 0; @@ -1048,7 +1041,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) pol->governor = CPUFREQ_DEFAULT_GOVERNOR; pol->cpus = cpu_core_map[pol->cpu]; - /* Take a crude guess here. + /* Take a crude guess here. * That guess was in microseconds, so multiply with 1000 */ pol->cpuinfo.transition_latency = (((data->rvo + 8) * data->vstable * VST_UNITS_20US) + (3 * (1 << data->irt) * 10)) * 1000; @@ -1070,9 +1063,8 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) printk("cpu_init done, current fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); - for_each_cpu_mask(i, cpu_core_map[pol->cpu]) { + for_each_cpu_mask(i, cpu_core_map[pol->cpu]) powernow_data[i] = data; - } return 0; @@ -1103,10 +1095,15 @@ static int __devexit powernowk8_cpu_exit (struct cpufreq_policy *pol) static unsigned int powernowk8_get (unsigned int cpu) { - struct powernow_k8_data *data = powernow_data[cpu]; + struct powernow_k8_data *data; cpumask_t oldmask = current->cpus_allowed; unsigned int khz = 0; + data = powernow_data[first_cpu(cpu_core_map[cpu])]; + + if (!data) + return -EINVAL; + set_cpus_allowed(current, cpumask_of_cpu(cpu)); if (smp_processor_id() != cpu) { printk(KERN_ERR PFX "limiting to CPU %d failed in powernowk8_get\n", cpu); diff --git a/arch/i386/kernel/cpu/cpufreq/powernow-k8.h b/arch/i386/kernel/cpu/cpufreq/powernow-k8.h index d0de37d58e9..79a7c5c87ed 100644 --- a/arch/i386/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/i386/kernel/cpu/cpufreq/powernow-k8.h @@ -63,7 +63,7 @@ struct powernow_k8_data { #define MSR_C_LO_VID_SHIFT 8 /* Field definitions within the FID VID High Control MSR : */ -#define MSR_C_HI_STP_GNT_TO 0x000fffff +#define MSR_C_HI_STP_GNT_TO 0x000fffff /* Field definitions within the FID VID Low Status MSR : */ #define MSR_S_LO_CHANGE_PENDING 0x80000000 /* cleared when completed */ @@ -123,7 +123,7 @@ struct powernow_k8_data { * Most values of interest are enocoded in a single field of the _PSS * entries: the "control" value. */ - + #define IRT_SHIFT 30 #define RVO_SHIFT 28 #define EXT_TYPE_SHIFT 27 @@ -182,10 +182,6 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid); static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index); -#ifndef for_each_cpu_mask -#define for_each_cpu_mask(i,mask) for (i=0;i<1;i++) -#endif - #ifdef CONFIG_SMP static inline void define_siblings(int cpu, cpumask_t cpu_sharedcore_mask[]) { diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c index c173c0fa117..b0ff9075708 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-centrino.c @@ -479,15 +479,13 @@ static int centrino_cpu_init(struct cpufreq_policy *policy) unsigned l, h; int ret; int i; - struct cpuinfo_x86 *c = &cpu_data[policy->cpu]; /* Only Intel makes Enhanced Speedstep-capable CPUs */ if (cpu->x86_vendor != X86_VENDOR_INTEL || !cpu_has(cpu, X86_FEATURE_EST)) return -ENODEV; - if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { + if (cpu_has(cpu, X86_FEATURE_CONSTANT_TSC)) centrino_driver.flags |= CPUFREQ_CONST_LOOPS; - } if (centrino_cpu_init_acpi(policy)) { if (policy->cpu != 0) diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c index 7c47005a180..4f46cac155c 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.c @@ -9,7 +9,7 @@ */ #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/module.h> #include <linux/moduleparam.h> #include <linux/init.h> #include <linux/cpufreq.h> @@ -36,8 +36,8 @@ static unsigned int pentium3_get_frequency (unsigned int processor) /* See table 14 of p3_ds.pdf and table 22 of 29834003.pdf */ struct { unsigned int ratio; /* Frequency Multiplier (x10) */ - u8 bitmap; /* power on configuration bits - [27, 25:22] (in MSR 0x2a) */ + u8 bitmap; /* power on configuration bits + [27, 25:22] (in MSR 0x2a) */ } msr_decode_mult [] = { { 30, 0x01 }, { 35, 0x05 }, @@ -58,9 +58,9 @@ static unsigned int pentium3_get_frequency (unsigned int processor) /* PIII(-M) FSB settings: see table b1-b of 24547206.pdf */ struct { - unsigned int value; /* Front Side Bus speed in MHz */ - u8 bitmap; /* power on configuration bits [18: 19] - (in MSR 0x2a) */ + unsigned int value; /* Front Side Bus speed in MHz */ + u8 bitmap; /* power on configuration bits [18: 19] + (in MSR 0x2a) */ } msr_decode_fsb [] = { { 66, 0x0 }, { 100, 0x2 }, @@ -68,8 +68,8 @@ static unsigned int pentium3_get_frequency (unsigned int processor) { 0, 0xff} }; - u32 msr_lo, msr_tmp; - int i = 0, j = 0; + u32 msr_lo, msr_tmp; + int i = 0, j = 0; /* read MSR 0x2a - we only need the low 32 bits */ rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp); @@ -106,7 +106,7 @@ static unsigned int pentium3_get_frequency (unsigned int processor) static unsigned int pentiumM_get_frequency(void) { - u32 msr_lo, msr_tmp; + u32 msr_lo, msr_tmp; rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp); dprintk("PM - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp); @@ -134,7 +134,7 @@ static unsigned int pentium4_get_frequency(void) dprintk("P4 - MSR_EBC_FREQUENCY_ID: 0x%x 0x%x\n", msr_lo, msr_hi); - /* decode the FSB: see IA-32 Intel (C) Architecture Software + /* decode the FSB: see IA-32 Intel (C) Architecture Software * Developer's Manual, Volume 3: System Prgramming Guide, * revision #12 in Table B-1: MSRs in the Pentium 4 and * Intel Xeon Processors, on page B-4 and B-5. @@ -170,7 +170,7 @@ static unsigned int pentium4_get_frequency(void) return (fsb * mult); } - + unsigned int speedstep_get_processor_frequency(unsigned int processor) { switch (processor) { @@ -198,11 +198,11 @@ EXPORT_SYMBOL_GPL(speedstep_get_processor_frequency); unsigned int speedstep_detect_processor (void) { struct cpuinfo_x86 *c = cpu_data; - u32 ebx, msr_lo, msr_hi; + u32 ebx, msr_lo, msr_hi; dprintk("x86: %x, model: %x\n", c->x86, c->x86_model); - if ((c->x86_vendor != X86_VENDOR_INTEL) || + if ((c->x86_vendor != X86_VENDOR_INTEL) || ((c->x86 != 6) && (c->x86 != 0xF))) return 0; @@ -218,15 +218,15 @@ unsigned int speedstep_detect_processor (void) dprintk("ebx value is %x, x86_mask is %x\n", ebx, c->x86_mask); switch (c->x86_mask) { - case 4: + case 4: /* - * B-stepping [M-P4-M] + * B-stepping [M-P4-M] * sample has ebx = 0x0f, production has 0x0e. */ if ((ebx == 0x0e) || (ebx == 0x0f)) return SPEEDSTEP_PROCESSOR_P4M; break; - case 7: + case 7: /* * C-stepping [M-P4-M] * needs to have ebx=0x0e, else it's a celeron: @@ -253,7 +253,7 @@ unsigned int speedstep_detect_processor (void) * also, M-P4M HTs have ebx=0x8, too * For now, they are distinguished by the model_id string */ - if ((ebx == 0x0e) || (strstr(c->x86_model_id,"Mobile Intel(R) Pentium(R) 4") != NULL)) + if ((ebx == 0x0e) || (strstr(c->x86_model_id,"Mobile Intel(R) Pentium(R) 4") != NULL)) return SPEEDSTEP_PROCESSOR_P4M; break; default: @@ -264,8 +264,7 @@ unsigned int speedstep_detect_processor (void) switch (c->x86_model) { case 0x0B: /* Intel PIII [Tualatin] */ - /* cpuid_ebx(1) is 0x04 for desktop PIII, - 0x06 for mobile PIII-M */ + /* cpuid_ebx(1) is 0x04 for desktop PIII, 0x06 for mobile PIII-M */ ebx = cpuid_ebx(0x00000001); dprintk("ebx is %x\n", ebx); @@ -275,9 +274,8 @@ unsigned int speedstep_detect_processor (void) return 0; /* So far all PIII-M processors support SpeedStep. See - * Intel's 24540640.pdf of June 2003 + * Intel's 24540640.pdf of June 2003 */ - return SPEEDSTEP_PROCESSOR_PIII_T; case 0x08: /* Intel PIII [Coppermine] */ @@ -399,7 +397,7 @@ unsigned int speedstep_get_freqs(unsigned int processor, } } - out: +out: local_irq_restore(flags); return (ret); } diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h index 6a727fd3a77..b735429c50b 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-lib.h @@ -14,7 +14,7 @@ #define SPEEDSTEP_PROCESSOR_PIII_C_EARLY 0x00000001 /* Coppermine core */ #define SPEEDSTEP_PROCESSOR_PIII_C 0x00000002 /* Coppermine core */ -#define SPEEDSTEP_PROCESSOR_PIII_T 0x00000003 /* Tualatin core */ +#define SPEEDSTEP_PROCESSOR_PIII_T 0x00000003 /* Tualatin core */ #define SPEEDSTEP_PROCESSOR_P4M 0x00000004 /* P4-M */ /* the following processors are not speedstep-capable and are not auto-detected @@ -25,8 +25,8 @@ /* speedstep states -- only two of them */ -#define SPEEDSTEP_HIGH 0x00000000 -#define SPEEDSTEP_LOW 0x00000001 +#define SPEEDSTEP_HIGH 0x00000000 +#define SPEEDSTEP_LOW 0x00000001 /* detect a speedstep-capable processor */ @@ -36,13 +36,13 @@ extern unsigned int speedstep_detect_processor (void); extern unsigned int speedstep_get_processor_frequency(unsigned int processor); -/* detect the low and high speeds of the processor. The callback - * set_state"'s first argument is either SPEEDSTEP_HIGH or - * SPEEDSTEP_LOW; the second argument is zero so that no +/* detect the low and high speeds of the processor. The callback + * set_state"'s first argument is either SPEEDSTEP_HIGH or + * SPEEDSTEP_LOW; the second argument is zero so that no * cpufreq_notify_transition calls are initiated. */ extern unsigned int speedstep_get_freqs(unsigned int processor, - unsigned int *low_speed, - unsigned int *high_speed, - unsigned int *transition_latency, - void (*set_state) (unsigned int state)); + unsigned int *low_speed, + unsigned int *high_speed, + unsigned int *transition_latency, + void (*set_state) (unsigned int state)); diff --git a/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c b/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c index 28cc5d524af..c28333d5364 100644 --- a/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/i386/kernel/cpu/cpufreq/speedstep-smi.c @@ -13,8 +13,8 @@ *********************************************************************/ #include <linux/kernel.h> -#include <linux/module.h> -#include <linux/moduleparam.h> +#include <linux/module.h> +#include <linux/moduleparam.h> #include <linux/init.h> #include <linux/cpufreq.h> #include <linux/pci.h> @@ -28,21 +28,21 @@ * * These parameters are got from IST-SMI BIOS call. * If user gives it, these are used. - * + * */ -static int smi_port = 0; -static int smi_cmd = 0; -static unsigned int smi_sig = 0; +static int smi_port = 0; +static int smi_cmd = 0; +static unsigned int smi_sig = 0; /* info about the processor */ -static unsigned int speedstep_processor = 0; +static unsigned int speedstep_processor = 0; -/* - * There are only two frequency states for each processor. Values +/* + * There are only two frequency states for each processor. Values * are in kHz for the time being. */ static struct cpufreq_frequency_table speedstep_freqs[] = { - {SPEEDSTEP_HIGH, 0}, + {SPEEDSTEP_HIGH, 0}, {SPEEDSTEP_LOW, 0}, {0, CPUFREQ_TABLE_END}, }; @@ -75,7 +75,9 @@ static int speedstep_smi_ownership (void) __asm__ __volatile__( "out %%al, (%%dx)\n" : "=D" (result) - : "a" (command), "b" (function), "c" (0), "d" (smi_port), "D" (0), "S" (magic) + : "a" (command), "b" (function), "c" (0), "d" (smi_port), + "D" (0), "S" (magic) + : "memory" ); dprintk("result is %x\n", result); @@ -123,7 +125,7 @@ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) *low = low_mhz * 1000; return result; -} +} /** * speedstep_get_state - set the SpeedStep state @@ -204,7 +206,7 @@ static void speedstep_set_state (unsigned int state) * speedstep_target - set a new CPUFreq policy * @policy: new policy * @target_freq: new freq - * @relation: + * @relation: * * Sets a new CPUFreq policy/freq. */ @@ -283,7 +285,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) state = speedstep_get_state(); speed = speedstep_freqs[state].frequency; - dprintk("currently at %s speed setting - %i MHz\n", + dprintk("currently at %s speed setting - %i MHz\n", (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency) ? "low" : "high", (speed / 1000)); @@ -296,7 +298,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) if (result) return (result); - cpufreq_frequency_table_get_attr(speedstep_freqs, policy->cpu); + cpufreq_frequency_table_get_attr(speedstep_freqs, policy->cpu); return 0; } @@ -332,8 +334,8 @@ static struct freq_attr* speedstep_attr[] = { static struct cpufreq_driver speedstep_driver = { .name = "speedstep-smi", - .verify = speedstep_verify, - .target = speedstep_target, + .verify = speedstep_verify, + .target = speedstep_target, .init = speedstep_cpu_init, .exit = speedstep_cpu_exit, .get = speedstep_get, @@ -370,13 +372,12 @@ static int __init speedstep_init(void) return -ENODEV; } - dprintk("signature:0x%.8lx, command:0x%.8lx, event:0x%.8lx, perf_level:0x%.8lx.\n", + dprintk("signature:0x%.8lx, command:0x%.8lx, event:0x%.8lx, perf_level:0x%.8lx.\n", ist_info.signature, ist_info.command, ist_info.event, ist_info.perf_level); - - /* Error if no IST-SMI BIOS or no PARM + /* Error if no IST-SMI BIOS or no PARM sig= 'ISGE' aka 'Intel Speedstep Gate E' */ - if ((ist_info.signature != 0x47534943) && ( + if ((ist_info.signature != 0x47534943) && ( (smi_port == 0) || (smi_cmd == 0))) return -ENODEV; @@ -386,17 +387,15 @@ static int __init speedstep_init(void) smi_sig = ist_info.signature; /* setup smi_port from MODLULE_PARM or BIOS */ - if ((smi_port > 0xff) || (smi_port < 0)) { + if ((smi_port > 0xff) || (smi_port < 0)) return -EINVAL; - } else if (smi_port == 0) { + else if (smi_port == 0) smi_port = ist_info.command & 0xff; - } - if ((smi_cmd > 0xff) || (smi_cmd < 0)) { + if ((smi_cmd > 0xff) || (smi_cmd < 0)) return -EINVAL; - } else if (smi_cmd == 0) { + else if (smi_cmd == 0) smi_cmd = (ist_info.command >> 16) & 0xff; - } return cpufreq_register_driver(&speedstep_driver); } diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index ce61921369e..9df87b03612 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -173,6 +173,10 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0; /* Cache sizes */ unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ 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_SMP + unsigned int cpu = (c == &boot_cpu_data) ? 0 : (c - cpu_data); +#endif if (c->cpuid_level > 3) { static int is_initialized; @@ -205,9 +209,15 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) break; case 2: new_l2 = this_leaf.size/1024; + num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + l2_id = c->apicid >> index_msb; break; case 3: new_l3 = this_leaf.size/1024; + num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + l3_id = c->apicid >> index_msb; break; default: break; @@ -215,11 +225,19 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) } } } - if (c->cpuid_level > 1) { + /* + * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for + * trace cache + */ + if ((num_cache_leaves == 0 || c->x86 == 15) && c->cpuid_level > 1) { /* supports eax=2 call */ int i, j, n; int regs[4]; unsigned char *dp = (unsigned char *)regs; + int only_trace = 0; + + if (num_cache_leaves != 0 && c->x86 == 15) + only_trace = 1; /* Number of times to iterate */ n = cpuid_eax(2) & 0xFF; @@ -241,6 +259,8 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) while (cache_table[k].descriptor != 0) { if (cache_table[k].descriptor == des) { + if (only_trace && cache_table[k].cache_type != LVL_TRACE) + break; switch (cache_table[k].cache_type) { case LVL_1_INST: l1i += cache_table[k].size; @@ -266,34 +286,45 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) } } } + } - if (new_l1d) - l1d = new_l1d; + if (new_l1d) + l1d = new_l1d; - if (new_l1i) - l1i = new_l1i; + if (new_l1i) + l1i = new_l1i; - if (new_l2) - l2 = new_l2; + if (new_l2) { + l2 = new_l2; +#ifdef CONFIG_SMP + cpu_llc_id[cpu] = l2_id; +#endif + } - if (new_l3) - l3 = new_l3; + if (new_l3) { + l3 = new_l3; +#ifdef CONFIG_SMP + cpu_llc_id[cpu] = l3_id; +#endif + } - if ( trace ) - printk (KERN_INFO "CPU: Trace cache: %dK uops", trace); - else if ( l1i ) - printk (KERN_INFO "CPU: L1 I cache: %dK", l1i); - if ( l1d ) - printk(", L1 D cache: %dK\n", l1d); - else - printk("\n"); - if ( l2 ) - printk(KERN_INFO "CPU: L2 cache: %dK\n", l2); - if ( l3 ) - printk(KERN_INFO "CPU: L3 cache: %dK\n", l3); + if (trace) + printk (KERN_INFO "CPU: Trace cache: %dK uops", trace); + else if ( l1i ) + printk (KERN_INFO "CPU: L1 I cache: %dK", l1i); - c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d)); - } + if (l1d) + printk(", L1 D cache: %dK\n", l1d); + else + printk("\n"); + + if (l2) + printk(KERN_INFO "CPU: L2 cache: %dK\n", l2); + + if (l3) + printk(KERN_INFO "CPU: L3 cache: %dK\n", l3); + + c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d)); return l2; } diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c index 3b4618bed70..fff90bda473 100644 --- a/arch/i386/kernel/cpu/mtrr/main.c +++ b/arch/i386/kernel/cpu/mtrr/main.c @@ -36,6 +36,7 @@ #include <linux/pci.h> #include <linux/smp.h> #include <linux/cpu.h> +#include <linux/mutex.h> #include <asm/mtrr.h> @@ -47,7 +48,7 @@ u32 num_var_ranges = 0; unsigned int *usage_table; -static DECLARE_MUTEX(mtrr_sem); +static DEFINE_MUTEX(mtrr_mutex); u32 size_or_mask, size_and_mask; @@ -333,7 +334,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, /* No CPU hotplug when we change MTRR entries */ lock_cpu_hotplug(); /* Search for existing MTRR */ - down(&mtrr_sem); + mutex_lock(&mtrr_mutex); for (i = 0; i < num_var_ranges; ++i) { mtrr_if->get(i, &lbase, &lsize, <ype); if (base >= lbase + lsize) @@ -371,7 +372,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, printk(KERN_INFO "mtrr: no more MTRRs available\n"); error = i; out: - up(&mtrr_sem); + mutex_unlock(&mtrr_mutex); unlock_cpu_hotplug(); return error; } @@ -464,7 +465,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) max = num_var_ranges; /* No CPU hotplug when we change MTRR entries */ lock_cpu_hotplug(); - down(&mtrr_sem); + mutex_lock(&mtrr_mutex); if (reg < 0) { /* Search for existing MTRR */ for (i = 0; i < max; ++i) { @@ -503,7 +504,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) set_mtrr(reg, 0, 0, 0); error = reg; out: - up(&mtrr_sem); + mutex_unlock(&mtrr_mutex); unlock_cpu_hotplug(); return error; } @@ -685,7 +686,7 @@ void mtrr_ap_init(void) if (!mtrr_if || !use_intel()) return; /* - * Ideally we should hold mtrr_sem here to avoid mtrr entries changed, + * Ideally we should hold mtrr_mutex here to avoid mtrr entries changed, * but this routine will be called in cpu boot time, holding the lock * breaks it. This routine is called in two cases: 1.very earily time * of software resume, when there absolutely isn't mtrr entry changes; diff --git a/arch/i386/kernel/cpu/proc.c b/arch/i386/kernel/cpu/proc.c index 5cfbd801169..f94cdb7aca5 100644 --- a/arch/i386/kernel/cpu/proc.c +++ b/arch/i386/kernel/cpu/proc.c @@ -45,7 +45,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, /* Intel-defined (#2) */ - "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", NULL, "est", + "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est", "tm2", NULL, "cid", NULL, NULL, "cx16", "xtpr", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, diff --git a/arch/i386/kernel/dmi_scan.c b/arch/i386/kernel/dmi_scan.c index 6a93d75db43..5efceebc48d 100644 --- a/arch/i386/kernel/dmi_scan.c +++ b/arch/i386/kernel/dmi_scan.c @@ -3,8 +3,10 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/dmi.h> +#include <linux/efi.h> #include <linux/bootmem.h> #include <linux/slab.h> +#include <asm/dmi.h> static char * __init dmi_string(struct dmi_header *dm, u8 s) { @@ -106,7 +108,7 @@ static void __init dmi_save_devices(struct dmi_header *dm) struct dmi_device *dev; for (i = 0; i < count; i++) { - char *d = ((char *) dm) + (i * 2); + char *d = (char *)(dm + 1) + (i * 2); /* Skip disabled device */ if ((*d & 0x80) == 0) @@ -184,47 +186,72 @@ static void __init dmi_decode(struct dmi_header *dm) } } -void __init dmi_scan_machine(void) +static int __init dmi_present(char __iomem *p) { u8 buf[15]; - char __iomem *p, *q; + memcpy_fromio(buf, p, 15); + if ((memcmp(buf, "_DMI_", 5) == 0) && dmi_checksum(buf)) { + u16 num = (buf[13] << 8) | buf[12]; + u16 len = (buf[7] << 8) | buf[6]; + u32 base = (buf[11] << 24) | (buf[10] << 16) | + (buf[9] << 8) | buf[8]; - /* - * no iounmap() for that ioremap(); it would be a no-op, but it's - * so early in setup that sucker gets confused into doing what - * it shouldn't if we actually call it. - */ - p = ioremap(0xF0000, 0x10000); - if (p == NULL) - goto out; - - for (q = p; q < p + 0x10000; q += 16) { - memcpy_fromio(buf, q, 15); - if ((memcmp(buf, "_DMI_", 5) == 0) && dmi_checksum(buf)) { - u16 num = (buf[13] << 8) | buf[12]; - u16 len = (buf[7] << 8) | buf[6]; - u32 base = (buf[11] << 24) | (buf[10] << 16) | - (buf[9] << 8) | buf[8]; - - /* - * DMI version 0.0 means that the real version is taken from - * the SMBIOS version, which we don't know at this point. - */ - if (buf[14] != 0) - printk(KERN_INFO "DMI %d.%d present.\n", - buf[14] >> 4, buf[14] & 0xF); - else - printk(KERN_INFO "DMI present.\n"); + /* + * DMI version 0.0 means that the real version is taken from + * the SMBIOS version, which we don't know at this point. + */ + if (buf[14] != 0) + printk(KERN_INFO "DMI %d.%d present.\n", + buf[14] >> 4, buf[14] & 0xF); + else + printk(KERN_INFO "DMI present.\n"); + if (dmi_table(base,len, num, dmi_decode) == 0) + return 0; + } + return 1; +} + +void __init dmi_scan_machine(void) +{ + char __iomem *p, *q; + int rc; + + if (efi_enabled) { + if (efi.smbios == EFI_INVALID_TABLE_ADDR) + goto out; + + /* This is called as a core_initcall() because it isn't + * needed during early boot. This also means we can + * iounmap the space when we're done with it. + */ + p = dmi_ioremap(efi.smbios, 32); + if (p == NULL) + goto out; + + rc = dmi_present(p + 0x10); /* offset of _DMI_ string */ + dmi_iounmap(p, 32); + if (!rc) + return; + } + else { + /* + * no iounmap() for that ioremap(); it would be a no-op, but + * it's so early in setup that sucker gets confused into doing + * what it shouldn't if we actually call it. + */ + p = dmi_ioremap(0xF0000, 0x10000); + if (p == NULL) + goto out; - if (dmi_table(base,len, num, dmi_decode) == 0) + for (q = p; q < p + 0x10000; q += 16) { + rc = dmi_present(q); + if (!rc) return; } } - -out: printk(KERN_INFO "DMI not present or invalid.\n"); + out: printk(KERN_INFO "DMI not present or invalid.\n"); } - /** * dmi_check_system - check system DMI data * @list: array of dmi_system_id structures to match against @@ -299,3 +326,33 @@ struct dmi_device * dmi_find_device(int type, const char *name, return NULL; } EXPORT_SYMBOL(dmi_find_device); + +/** + * dmi_get_year - Return year of a DMI date + * @field: data index (like dmi_get_system_info) + * + * Returns -1 when the field doesn't exist. 0 when it is broken. + */ +int dmi_get_year(int field) +{ + int year; + char *s = dmi_get_system_info(field); + + if (!s) + return -1; + if (*s == '\0') + return 0; + s = strrchr(s, '/'); + if (!s) + return 0; + + s += 1; + year = simple_strtoul(s, NULL, 0); + if (year && year < 100) { /* 2-digit year */ + year += 1900; + if (year < 1996) /* no dates < spec 1.0 */ + year += 100; + } + + return year; +} diff --git a/arch/i386/kernel/efi.c b/arch/i386/kernel/efi.c index 7ec6cfa01fb..9202b67c4b2 100644 --- a/arch/i386/kernel/efi.c +++ b/arch/i386/kernel/efi.c @@ -361,7 +361,7 @@ void __init efi_init(void) */ c16 = (efi_char16_t *) boot_ioremap(efi.systab->fw_vendor, 2); if (c16) { - for (i = 0; i < sizeof(vendor) && *c16; ++i) + for (i = 0; i < (sizeof(vendor) - 1) && *c16; ++i) vendor[i] = *c16++; vendor[i] = '\0'; } else @@ -381,29 +381,38 @@ void __init efi_init(void) if (config_tables == NULL) printk(KERN_ERR PFX "Could not map EFI Configuration Table!\n"); + efi.mps = EFI_INVALID_TABLE_ADDR; + efi.acpi = EFI_INVALID_TABLE_ADDR; + efi.acpi20 = EFI_INVALID_TABLE_ADDR; + efi.smbios = EFI_INVALID_TABLE_ADDR; + efi.sal_systab = EFI_INVALID_TABLE_ADDR; + efi.boot_info = EFI_INVALID_TABLE_ADDR; + efi.hcdp = EFI_INVALID_TABLE_ADDR; + efi.uga = EFI_INVALID_TABLE_ADDR; + for (i = 0; i < num_config_tables; i++) { if (efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID) == 0) { - efi.mps = (void *)config_tables[i].table; + efi.mps = config_tables[i].table; printk(KERN_INFO " MPS=0x%lx ", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, ACPI_20_TABLE_GUID) == 0) { - efi.acpi20 = __va(config_tables[i].table); + efi.acpi20 = config_tables[i].table; printk(KERN_INFO " ACPI 2.0=0x%lx ", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, ACPI_TABLE_GUID) == 0) { - efi.acpi = __va(config_tables[i].table); + efi.acpi = config_tables[i].table; printk(KERN_INFO " ACPI=0x%lx ", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, SMBIOS_TABLE_GUID) == 0) { - efi.smbios = (void *) config_tables[i].table; + efi.smbios = config_tables[i].table; printk(KERN_INFO " SMBIOS=0x%lx ", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, HCDP_TABLE_GUID) == 0) { - efi.hcdp = (void *)config_tables[i].table; + efi.hcdp = config_tables[i].table; printk(KERN_INFO " HCDP=0x%lx ", config_tables[i].table); } else if (efi_guidcmp(config_tables[i].guid, UGA_IO_PROTOCOL_GUID) == 0) { - efi.uga = (void *)config_tables[i].table; + efi.uga = config_tables[i].table; printk(KERN_INFO " UGA=0x%lx ", config_tables[i].table); } } diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c index 311b4e7266f..3b329af4afc 100644 --- a/arch/i386/kernel/io_apic.c +++ b/arch/i386/kernel/io_apic.c @@ -381,7 +381,7 @@ static void do_irq_balance(void) unsigned long imbalance = 0; cpumask_t allowed_mask, target_cpu_mask, tmp; - for_each_cpu(i) { + for_each_possible_cpu(i) { int package_index; CPU_IRQ(i) = 0; if (!cpu_online(i)) @@ -632,7 +632,7 @@ static int __init balanced_irq_init(void) else printk(KERN_ERR "balanced_irq_init: failed to spawn balanced_irq"); failed: - for_each_cpu(i) { + for_each_possible_cpu(i) { kfree(irq_cpu_data[i].irq_delta); irq_cpu_data[i].irq_delta = NULL; kfree(irq_cpu_data[i].last_irq); diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c index 7a59050242a..f19768789e8 100644 --- a/arch/i386/kernel/kprobes.c +++ b/arch/i386/kernel/kprobes.c @@ -35,12 +35,56 @@ #include <asm/cacheflush.h> #include <asm/kdebug.h> #include <asm/desc.h> +#include <asm/uaccess.h> void jprobe_return_end(void); DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); +/* insert a jmp code */ +static inline void set_jmp_op(void *from, void *to) +{ + struct __arch_jmp_op { + char op; + long raddr; + } __attribute__((packed)) *jop; + jop = (struct __arch_jmp_op *)from; + jop->raddr = (long)(to) - ((long)(from) + 5); + jop->op = RELATIVEJUMP_INSTRUCTION; +} + +/* + * returns non-zero if opcodes can be boosted. + */ +static inline int can_boost(kprobe_opcode_t opcode) +{ + switch (opcode & 0xf0 ) { + case 0x70: + return 0; /* can't boost conditional jump */ + case 0x90: + /* can't boost call and pushf */ + return opcode != 0x9a && opcode != 0x9c; + case 0xc0: + /* can't boost undefined opcodes and soft-interruptions */ + return (0xc1 < opcode && opcode < 0xc6) || + (0xc7 < opcode && opcode < 0xcc) || opcode == 0xcf; + case 0xd0: + /* can boost AA* and XLAT */ + return (opcode == 0xd4 || opcode == 0xd5 || opcode == 0xd7); + case 0xe0: + /* can boost in/out and (may be) jmps */ + return (0xe3 < opcode && opcode != 0xe8); + case 0xf0: + /* clear and set flags can be boost */ + return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe)); + default: + /* currently, can't boost 2 bytes opcodes */ + return opcode != 0x0f; + } +} + + /* * returns non-zero if opcode modifies the interrupt flag. */ @@ -65,6 +109,11 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); p->opcode = *p->addr; + if (can_boost(p->opcode)) { + p->ainsn.boostable = 0; + } else { + p->ainsn.boostable = -1; + } return 0; } @@ -155,9 +204,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) { struct kprobe *p; int ret = 0; - kprobe_opcode_t *addr = NULL; - unsigned long *lp; + kprobe_opcode_t *addr; struct kprobe_ctlblk *kcb; +#ifdef CONFIG_PREEMPT + unsigned pre_preempt_count = preempt_count(); +#endif /* CONFIG_PREEMPT */ + + addr = (kprobe_opcode_t *)(regs->eip - sizeof(kprobe_opcode_t)); /* * We don't want to be preempted for the entire @@ -166,17 +219,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) preempt_disable(); kcb = get_kprobe_ctlblk(); - /* Check if the application is using LDT entry for its code segment and - * calculate the address by reading the base address from the LDT entry. - */ - if ((regs->xcs & 4) && (current->mm)) { - lp = (unsigned long *) ((unsigned long)((regs->xcs >> 3) * 8) - + (char *) current->mm->context.ldt); - addr = (kprobe_opcode_t *) (get_desc_base(lp) + regs->eip - - sizeof(kprobe_opcode_t)); - } else { - addr = (kprobe_opcode_t *)(regs->eip - sizeof(kprobe_opcode_t)); - } /* Check we're not actually recursing */ if (kprobe_running()) { p = get_kprobe(addr); @@ -252,6 +294,21 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) /* handler has already set things up, so skip ss setup */ return 1; + if (p->ainsn.boostable == 1 && +#ifdef CONFIG_PREEMPT + !(pre_preempt_count) && /* + * This enables booster when the direct + * execution path aren't preempted. + */ +#endif /* CONFIG_PREEMPT */ + !p->post_handler && !p->break_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; + } + ss_probe: prepare_singlestep(p, regs); kcb->kprobe_status = KPROBE_HIT_SS; @@ -267,17 +324,44 @@ no_kprobe: * here. When a retprobed function returns, this probe is hit and * trampoline_probe_handler() runs, calling the kretprobe's handler. */ - void kretprobe_trampoline_holder(void) + void __kprobes kretprobe_trampoline_holder(void) { - asm volatile ( ".global kretprobe_trampoline\n" + asm volatile ( ".global kretprobe_trampoline\n" "kretprobe_trampoline: \n" - "nop\n"); - } + " pushf\n" + /* skip cs, eip, orig_eax, es, ds */ + " subl $20, %esp\n" + " pushl %eax\n" + " pushl %ebp\n" + " pushl %edi\n" + " pushl %esi\n" + " pushl %edx\n" + " pushl %ecx\n" + " pushl %ebx\n" + " movl %esp, %eax\n" + " call trampoline_handler\n" + /* move eflags to cs */ + " movl 48(%esp), %edx\n" + " movl %edx, 44(%esp)\n" + /* save true return address on eflags */ + " movl %eax, 48(%esp)\n" + " popl %ebx\n" + " popl %ecx\n" + " popl %edx\n" + " popl %esi\n" + " popl %edi\n" + " popl %ebp\n" + " popl %eax\n" + /* skip eip, orig_eax, es, ds */ + " addl $16, %esp\n" + " popf\n" + " ret\n"); +} /* - * Called when we hit the probe point at kretprobe_trampoline + * Called from kretprobe_trampoline */ -int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) +fastcall void *__kprobes trampoline_handler(struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head; @@ -306,8 +390,11 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) /* another task is sharing our hash bucket */ continue; - if (ri->rp && ri->rp->handler) + if (ri->rp && ri->rp->handler){ + __get_cpu_var(current_kprobe) = &ri->rp->kp; ri->rp->handler(ri, regs); + __get_cpu_var(current_kprobe) = NULL; + } orig_ret_address = (unsigned long)ri->ret_addr; recycle_rp_inst(ri); @@ -322,18 +409,10 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) } BUG_ON(!orig_ret_address || (orig_ret_address == trampoline_address)); - regs->eip = orig_ret_address; - reset_current_kprobe(); spin_unlock_irqrestore(&kretprobe_lock, flags); - preempt_enable_no_resched(); - /* - * By returning a non-zero value, we are telling - * kprobe_handler() that we don't want the post_handler - * to run (and have re-enabled preemption) - */ - return 1; + return (void*)orig_ret_address; } /* @@ -357,15 +436,17 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * 2) If the single-stepped instruction was a call, the return address * that is atop the stack is the address following the copied instruction. * We need to make it the address following the original instruction. + * + * This function also checks instruction size for preparing direct execution. */ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) { unsigned long *tos = (unsigned long *)®s->esp; - unsigned long next_eip = 0; unsigned long copy_eip = (unsigned long)p->ainsn.insn; unsigned long orig_eip = (unsigned long)p->addr; + regs->eflags &= ~TF_MASK; switch (p->ainsn.insn[0]) { case 0x9c: /* pushfl */ *tos &= ~(TF_MASK | IF_MASK); @@ -375,37 +456,51 @@ static void __kprobes resume_execution(struct kprobe *p, case 0xcb: case 0xc2: case 0xca: - regs->eflags &= ~TF_MASK; - /* eip is already adjusted, no more changes required*/ - return; + case 0xea: /* jmp absolute -- eip is correct */ + /* eip is already adjusted, no more changes required */ + p->ainsn.boostable = 1; + goto no_change; case 0xe8: /* call relative - Fix return addr */ *tos = orig_eip + (*tos - copy_eip); break; case 0xff: if ((p->ainsn.insn[1] & 0x30) == 0x10) { /* call absolute, indirect */ - /* Fix return addr; eip is correct. */ - next_eip = regs->eip; + /* + * Fix return addr; eip is correct. + * But this is not boostable + */ *tos = orig_eip + (*tos - copy_eip); + goto no_change; } else if (((p->ainsn.insn[1] & 0x31) == 0x20) || /* jmp near, absolute indirect */ ((p->ainsn.insn[1] & 0x31) == 0x21)) { /* jmp far, absolute indirect */ - /* eip is correct. */ - next_eip = regs->eip; + /* eip is correct. And this is boostable */ + p->ainsn.boostable = 1; + goto no_change; } - break; - case 0xea: /* jmp absolute -- eip is correct */ - next_eip = regs->eip; - break; default: break; } - regs->eflags &= ~TF_MASK; - if (next_eip) { - regs->eip = next_eip; - } else { - regs->eip = orig_eip + (regs->eip - copy_eip); + if (p->ainsn.boostable == 0) { + if ((regs->eip > copy_eip) && + (regs->eip - copy_eip) + 5 < MAX_INSN_SIZE) { + /* + * These instructions can be executed directly if it + * jumps back to correct address. + */ + set_jmp_op((void *)regs->eip, + (void *)orig_eip + (regs->eip - copy_eip)); + p->ainsn.boostable = 1; + } else { + p->ainsn.boostable = -1; + } } + + regs->eip = orig_eip + (regs->eip - copy_eip); + +no_change: + return; } /* @@ -453,15 +548,57 @@ static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) - return 1; - - if (kcb->kprobe_status & KPROBE_HIT_SS) { - resume_execution(cur, regs, kcb); + switch(kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the eip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->eip = (unsigned long)cur->addr; regs->eflags |= kcb->kprobe_old_eflags; - - reset_current_kprobe(); + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); preempt_enable_no_resched(); + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accouting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr)) + return 1; + + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + if (fixup_exception(regs)) + return 1; + + /* + * fixup_exception() could not handle it, + * Let do_page_fault() fix it. + */ + break; + default: + break; } return 0; } @@ -475,6 +612,9 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, struct die_args *args = (struct die_args *)data; int ret = NOTIFY_DONE; + if (args->regs && user_mode(args->regs)) + return ret; + switch (val) { case DIE_INT3: if (kprobe_handler(args->regs)) @@ -564,12 +704,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } -static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *) &kretprobe_trampoline, - .pre_handler = trampoline_probe_handler -}; - int __init arch_init_kprobes(void) { - return register_kprobe(&trampoline_p); + return 0; } diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c index 5390b521aca..e7c138f66c5 100644 --- a/arch/i386/kernel/microcode.c +++ b/arch/i386/kernel/microcode.c @@ -81,6 +81,7 @@ #include <linux/miscdevice.h> #include <linux/spinlock.h> #include <linux/mm.h> +#include <linux/mutex.h> #include <asm/msr.h> #include <asm/uaccess.h> @@ -114,7 +115,7 @@ MODULE_LICENSE("GPL"); static DEFINE_SPINLOCK(microcode_update_lock); /* no concurrent ->write()s are allowed on /dev/cpu/microcode */ -static DECLARE_MUTEX(microcode_sem); +static DEFINE_MUTEX(microcode_mutex); static void __user *user_buffer; /* user area microcode data buffer */ static unsigned int user_buffer_size; /* it's size */ @@ -202,8 +203,6 @@ static inline void mark_microcode_update (int cpu_num, microcode_header_t *mc_he } else if (mc_header->rev == uci->rev) { /* notify the caller of success on this cpu */ uci->err = MC_SUCCESS; - printk(KERN_ERR "microcode: CPU%d already at revision" - " 0x%x (current=0x%x)\n", cpu_num, mc_header->rev, uci->rev); goto out; } @@ -369,7 +368,6 @@ static void do_update_one (void * unused) struct ucode_cpu_info *uci = ucode_cpu_info + cpu_num; if (uci->mc == NULL) { - printk(KERN_INFO "microcode: No new microcode data for CPU%d\n", cpu_num); return; } @@ -447,7 +445,7 @@ static ssize_t microcode_write (struct file *file, const char __user *buf, size_ return -EINVAL; } - down(µcode_sem); + mutex_lock(µcode_mutex); user_buffer = (void __user *) buf; user_buffer_size = (int) len; @@ -456,31 +454,14 @@ static ssize_t microcode_write (struct file *file, const char __user *buf, size_ if (!ret) ret = (ssize_t)len; - up(µcode_sem); + mutex_unlock(µcode_mutex); return ret; } -static int microcode_ioctl (struct inode *inode, struct file *file, - unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - /* - * XXX: will be removed after microcode_ctl - * is updated to ignore failure of this ioctl() - */ - case MICROCODE_IOCFREE: - return 0; - default: - return -EINVAL; - } - return -EINVAL; -} - static struct file_operations microcode_fops = { .owner = THIS_MODULE, .write = microcode_write, - .ioctl = microcode_ioctl, .open = microcode_open, }; @@ -511,7 +492,6 @@ static int __init microcode_init (void) static void __exit microcode_exit (void) { misc_deregister(µcode_dev); - printk(KERN_INFO "IA-32 Microcode Update Driver v" MICROCODE_VERSION " unregistered\n"); } module_init(microcode_init) diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c index 9074818b947..d43b498ec74 100644 --- a/arch/i386/kernel/nmi.c +++ b/arch/i386/kernel/nmi.c @@ -138,12 +138,12 @@ static int __init check_nmi_watchdog(void) if (nmi_watchdog == NMI_LOCAL_APIC) smp_call_function(nmi_cpu_busy, (void *)&endflag, 0, 0); - for_each_cpu(cpu) + for_each_possible_cpu(cpu) prev_nmi_count[cpu] = per_cpu(irq_stat, cpu).__nmi_count; local_irq_enable(); mdelay((10*1000)/nmi_hz); // wait 10 ticks - for_each_cpu(cpu) { + for_each_possible_cpu(cpu) { #ifdef CONFIG_SMP /* Check cpu_callin_map here because that is set after the timer is started. */ @@ -510,7 +510,7 @@ void touch_nmi_watchdog (void) * Just reset the alert counters, (other CPUs might be * spinning on locks we hold): */ - for_each_cpu(i) + for_each_possible_cpu(i) alert_counter[i] = 0; /* @@ -529,7 +529,8 @@ void nmi_watchdog_tick (struct pt_regs * regs) * always switch the stack NMI-atomically, it's safe to use * smp_processor_id(). */ - int sum, cpu = smp_processor_id(); + unsigned int sum; + int cpu = smp_processor_id(); sum = per_cpu(irq_stat, cpu).apic_timer_irqs; diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c index 299e6167408..24b3e745478 100644 --- a/arch/i386/kernel/process.c +++ b/arch/i386/kernel/process.c @@ -38,7 +38,6 @@ #include <linux/kallsyms.h> #include <linux/ptrace.h> #include <linux/random.h> -#include <linux/kprobes.h> #include <asm/uaccess.h> #include <asm/pgtable.h> @@ -364,13 +363,6 @@ void exit_thread(void) struct task_struct *tsk = current; struct thread_struct *t = &tsk->thread; - /* - * Remove function-return probe instances associated with this task - * and put them back on the free list. Do not insert an exit probe for - * this function, it will be disabled by kprobe_flush_task if you do. - */ - kprobe_flush_task(tsk); - /* The process may have allocated an io port bitmap... nuke it. */ if (unlikely(NULL != t->io_bitmap_ptr)) { int cpu = get_cpu(); diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c index d313a11acaf..8c08660b4e5 100644 --- a/arch/i386/kernel/setup.c +++ b/arch/i386/kernel/setup.c @@ -46,6 +46,7 @@ #include <linux/kexec.h> #include <linux/crash_dump.h> #include <linux/dmi.h> +#include <linux/pfn.h> #include <video/edid.h> @@ -1058,10 +1059,10 @@ static int __init free_available_memory(unsigned long start, unsigned long end, void *arg) { /* check max_low_pfn */ - if (start >= ((max_low_pfn + 1) << PAGE_SHIFT)) + if (start >= (max_low_pfn << PAGE_SHIFT)) return 0; - if (end >= ((max_low_pfn + 1) << PAGE_SHIFT)) - end = (max_low_pfn + 1) << PAGE_SHIFT; + if (end >= (max_low_pfn << PAGE_SHIFT)) + end = max_low_pfn << PAGE_SHIFT; if (start < end) free_bootmem(start, end - start); @@ -1286,8 +1287,6 @@ legacy_init_iomem_resources(struct resource *code_resource, struct resource *dat probe_roms(); for (i = 0; i < e820.nr_map; i++) { struct resource *res; - if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL) - continue; res = kzalloc(sizeof(struct resource), GFP_ATOMIC); switch (e820.map[i].type) { case E820_RAM: res->name = "System RAM"; break; diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index 4c470e99a74..a6969903f2d 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -72,6 +72,9 @@ int phys_proc_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID}; /* Core ID of each logical CPU */ int cpu_core_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID}; +/* Last level cache ID of each logical CPU */ +int cpu_llc_id[NR_CPUS] __cpuinitdata = {[0 ... NR_CPUS-1] = BAD_APICID}; + /* representing HT siblings of each logical CPU */ cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_sibling_map); @@ -440,6 +443,18 @@ static void __devinit smp_callin(void) 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; + /* + * For perf, we return last level cache shared map. + * TBD: when power saving sched policy is added, we will return + * cpu_core_map when power saving policy is enabled + */ + return c->llc_shared_map; +} + /* representing cpus for which sibling maps can be computed */ static cpumask_t cpu_sibling_setup_map; @@ -459,12 +474,16 @@ set_cpu_sibling_map(int 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); } } } else { cpu_set(cpu, cpu_sibling_map[cpu]); } + cpu_set(cpu, c[cpu].llc_shared_map); + if (current_cpu_data.x86_max_cores == 1) { cpu_core_map[cpu] = cpu_sibling_map[cpu]; c[cpu].booted_cores = 1; @@ -472,6 +491,11 @@ set_cpu_sibling_map(int cpu) } 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 (phys_proc_id[cpu] == phys_proc_id[i]) { cpu_set(i, cpu_core_map[cpu]); cpu_set(cpu, cpu_core_map[i]); @@ -1003,7 +1027,6 @@ void cpu_exit_clear(void) cpu_clear(cpu, cpu_callout_map); cpu_clear(cpu, cpu_callin_map); - cpu_clear(cpu, cpu_present_map); cpu_clear(cpu, smp_commenced_mask); unmap_cpu_to_logical_apicid(cpu); @@ -1015,31 +1038,20 @@ struct warm_boot_cpu_info { int cpu; }; -static void __devinit do_warm_boot_cpu(void *p) +static void __cpuinit do_warm_boot_cpu(void *p) { struct warm_boot_cpu_info *info = p; do_boot_cpu(info->apicid, info->cpu); complete(info->complete); } -int __devinit smp_prepare_cpu(int cpu) +static int __cpuinit __smp_prepare_cpu(int cpu) { DECLARE_COMPLETION(done); struct warm_boot_cpu_info info; struct work_struct task; int apicid, ret; - lock_cpu_hotplug(); - - /* - * On x86, CPU0 is never offlined. Trying to bring up an - * already-booted CPU will hang. So check for that case. - */ - if (cpu_online(cpu)) { - ret = -EINVAL; - goto exit; - } - apicid = x86_cpu_to_apicid[cpu]; if (apicid == BAD_APICID) { ret = -ENODEV; @@ -1064,7 +1076,6 @@ int __devinit smp_prepare_cpu(int cpu) zap_low_mappings(); ret = 0; exit: - unlock_cpu_hotplug(); return ret; } #endif @@ -1392,6 +1403,22 @@ void __cpu_die(unsigned int cpu) int __devinit __cpu_up(unsigned int cpu) { +#ifdef CONFIG_HOTPLUG_CPU + int ret=0; + + /* + * We do warm boot only on cpus that had booted earlier + * Otherwise cold boot is all handled from smp_boot_cpus(). + * cpu_callin_map is set during AP kickstart process. Its reset + * when a cpu is taken offline from cpu_exit_clear(). + */ + if (!cpu_isset(cpu, cpu_callin_map)) + ret = __smp_prepare_cpu(cpu); + + if (ret) + return -EIO; +#endif + /* In case one didn't come up */ if (!cpu_isset(cpu, cpu_callin_map)) { printk(KERN_DEBUG "skipping cpu%d, didn't come online\n", cpu); diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S index ac687d00a1c..326595f3fa4 100644 --- a/arch/i386/kernel/syscall_table.S +++ b/arch/i386/kernel/syscall_table.S @@ -310,3 +310,5 @@ ENTRY(sys_call_table) .long sys_pselect6 .long sys_ppoll .long sys_unshare /* 310 */ + .long sys_set_robust_list + .long sys_get_robust_list diff --git a/arch/i386/kernel/timers/timer_pm.c b/arch/i386/kernel/timers/timer_pm.c index 264edaaac31..144e94a0493 100644 --- a/arch/i386/kernel/timers/timer_pm.c +++ b/arch/i386/kernel/timers/timer_pm.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/device.h> #include <linux/init.h> +#include <linux/pci.h> #include <asm/types.h> #include <asm/timer.h> #include <asm/smp.h> @@ -45,24 +46,31 @@ static seqlock_t monotonic_lock = SEQLOCK_UNLOCKED; #define ACPI_PM_MASK 0xFFFFFF /* limit it to 24 bits */ +static int pmtmr_need_workaround __read_mostly = 1; + /*helper function to safely read acpi pm timesource*/ static inline u32 read_pmtmr(void) { - u32 v1=0,v2=0,v3=0; - /* It has been reported that because of various broken - * chipsets (ICH4, PIIX4 and PIIX4E) where the ACPI PM time - * source is not latched, so you must read it multiple - * times to insure a safe value is read. - */ - do { - v1 = inl(pmtmr_ioport); - v2 = inl(pmtmr_ioport); - v3 = inl(pmtmr_ioport); - } while ((v1 > v2 && v1 < v3) || (v2 > v3 && v2 < v1) - || (v3 > v1 && v3 < v2)); - - /* mask the output to 24 bits */ - return v2 & ACPI_PM_MASK; + if (pmtmr_need_workaround) { + u32 v1, v2, v3; + + /* It has been reported that because of various broken + * chipsets (ICH4, PIIX4 and PIIX4E) where the ACPI PM time + * source is not latched, so you must read it multiple + * times to insure a safe value is read. + */ + do { + v1 = inl(pmtmr_ioport); + v2 = inl(pmtmr_ioport); + v3 = inl(pmtmr_ioport); + } while ((v1 > v2 && v1 < v3) || (v2 > v3 && v2 < v1) + || (v3 > v1 && v3 < v2)); + + /* mask the output to 24 bits */ + return v2 & ACPI_PM_MASK; + } + + return inl(pmtmr_ioport) & ACPI_PM_MASK; } @@ -263,6 +271,72 @@ struct init_timer_opts __initdata timer_pmtmr_init = { .opts = &timer_pmtmr, }; +#ifdef CONFIG_PCI +/* + * PIIX4 Errata: + * + * The power management timer may return improper results when read. + * Although the timer value settles properly after incrementing, + * while incrementing there is a 3 ns window every 69.8 ns where the + * timer value is indeterminate (a 4.2% chance that the data will be + * incorrect when read). As a result, the ACPI free running count up + * timer specification is violated due to erroneous reads. + */ +static int __init pmtmr_bug_check(void) +{ + static struct pci_device_id gray_list[] __initdata = { + /* these chipsets may have bug. */ + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_82801DB_0) }, + { }, + }; + struct pci_dev *dev; + int pmtmr_has_bug = 0; + u8 rev; + + if (cur_timer != &timer_pmtmr || !pmtmr_need_workaround) + return 0; + + dev = pci_get_device(PCI_VENDOR_ID_INTEL, + PCI_DEVICE_ID_INTEL_82371AB_3, NULL); + if (dev) { + pci_read_config_byte(dev, PCI_REVISION_ID, &rev); + /* the bug has been fixed in PIIX4M */ + if (rev < 3) { + printk(KERN_WARNING "* Found PM-Timer Bug on this " + "chipset. Due to workarounds for a bug,\n" + "* this time source is slow. Consider trying " + "other time sources (clock=)\n"); + pmtmr_has_bug = 1; + } + pci_dev_put(dev); + } + + if (pci_dev_present(gray_list)) { + printk(KERN_WARNING "* This chipset may have PM-Timer Bug. Due" + " to workarounds for a bug,\n" + "* this time source is slow. If you are sure your timer" + " does not have\n" + "* this bug, please use \"pmtmr_good\" to disable the " + "workaround\n"); + pmtmr_has_bug = 1; + } + + if (!pmtmr_has_bug) + pmtmr_need_workaround = 0; + + return 0; +} +device_initcall(pmtmr_bug_check); +#endif + +static int __init pmtr_good_setup(char *__str) +{ + pmtmr_need_workaround = 0; + return 1; +} +__setup("pmtmr_good", pmtr_good_setup); + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>"); MODULE_DESCRIPTION("Power Management Timer (PMTMR) as primary timing source for x86"); diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c index de5386b01d3..6b63a5aa1e4 100644 --- a/arch/i386/kernel/traps.c +++ b/arch/i386/kernel/traps.c @@ -92,22 +92,21 @@ asmlinkage void spurious_interrupt_bug(void); asmlinkage void machine_check(void); static int kstack_depth_to_print = 24; -struct notifier_block *i386die_chain; -static DEFINE_SPINLOCK(die_notifier_lock); +ATOMIC_NOTIFIER_HEAD(i386die_chain); int register_die_notifier(struct notifier_block *nb) { - int err = 0; - unsigned long flags; - vmalloc_sync_all(); - spin_lock_irqsave(&die_notifier_lock, flags); - err = notifier_chain_register(&i386die_chain, nb); - spin_unlock_irqrestore(&die_notifier_lock, flags); - return err; + return atomic_notifier_chain_register(&i386die_chain, nb); } EXPORT_SYMBOL(register_die_notifier); +int unregister_die_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&i386die_chain, nb); +} +EXPORT_SYMBOL(unregister_die_notifier); + static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) { return p > (void *)tinfo && @@ -386,8 +385,12 @@ void die(const char * str, struct pt_regs * regs, long err) #endif if (nl) printk("\n"); - notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV); - show_registers(regs); + if (notify_die(DIE_OOPS, str, regs, err, + current->thread.trap_no, SIGSEGV) != + NOTIFY_STOP) + show_registers(regs); + else + regs = NULL; } else printk(KERN_EMERG "Recursive die() failure, output suppressed\n"); @@ -395,6 +398,9 @@ void die(const char * str, struct pt_regs * regs, long err) die.lock_owner = -1; spin_unlock_irqrestore(&die.lock, flags); + if (!regs) + return; + if (kexec_should_crash(current)) crash_kexec(regs); @@ -623,7 +629,7 @@ static DEFINE_SPINLOCK(nmi_print_lock); void die_nmi (struct pt_regs *regs, const char *msg) { - if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 0, SIGINT) == + if (notify_die(DIE_NMIWATCHDOG, msg, regs, 0, 2, SIGINT) == NOTIFY_STOP) return; @@ -662,7 +668,7 @@ static void default_do_nmi(struct pt_regs * regs) reason = get_nmi_reason(); if (!(reason & 0xc0)) { - if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT) + if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT) == NOTIFY_STOP) return; #ifdef CONFIG_X86_LOCAL_APIC @@ -678,7 +684,7 @@ static void default_do_nmi(struct pt_regs * regs) unknown_nmi_error(reason, regs); return; } - if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP) + if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT) == NOTIFY_STOP) return; if (reason & 0x80) mem_parity_error(reason, regs); diff --git a/arch/i386/kernel/vm86.c b/arch/i386/kernel/vm86.c index f51c894a7da..aee14fafd13 100644 --- a/arch/i386/kernel/vm86.c +++ b/arch/i386/kernel/vm86.c @@ -43,6 +43,7 @@ #include <linux/smp_lock.h> #include <linux/highmem.h> #include <linux/ptrace.h> +#include <linux/audit.h> #include <asm/uaccess.h> #include <asm/io.h> @@ -252,6 +253,7 @@ out: static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk) { struct tss_struct *tss; + long eax; /* * make sure the vm86() system call doesn't try to do anything silly */ @@ -305,13 +307,19 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk tsk->thread.screen_bitmap = info->screen_bitmap; if (info->flags & VM86_SCREEN_BITMAP) mark_screen_rdonly(tsk->mm); + __asm__ __volatile__("xorl %eax,%eax; movl %eax,%fs; movl %eax,%gs\n\t"); + __asm__ __volatile__("movl %%eax, %0\n" :"=r"(eax)); + + /*call audit_syscall_exit since we do not exit via the normal paths */ + if (unlikely(current->audit_context)) + audit_syscall_exit(current, AUDITSC_RESULT(eax), eax); + __asm__ __volatile__( - "xorl %%eax,%%eax; movl %%eax,%%fs; movl %%eax,%%gs\n\t" "movl %0,%%esp\n\t" "movl %1,%%ebp\n\t" "jmp resume_userspace" : /* no outputs */ - :"r" (&info->regs), "r" (task_thread_info(tsk)) : "ax"); + :"r" (&info->regs), "r" (task_thread_info(tsk))); /* we never return here */ } diff --git a/arch/i386/kernel/vmlinux.lds.S b/arch/i386/kernel/vmlinux.lds.S index 3f21c6f6466..8831303a473 100644 --- a/arch/i386/kernel/vmlinux.lds.S +++ b/arch/i386/kernel/vmlinux.lds.S @@ -7,6 +7,7 @@ #include <asm-generic/vmlinux.lds.h> #include <asm/thread_info.h> #include <asm/page.h> +#include <asm/cache.h> OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386") OUTPUT_ARCH(i386) @@ -135,7 +136,7 @@ SECTIONS __initramfs_start = .; .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { *(.init.ramfs) } __initramfs_end = .; - . = ALIGN(32); + . = ALIGN(L1_CACHE_BYTES); __per_cpu_start = .; .data.percpu : AT(ADDR(.data.percpu) - LOAD_OFFSET) { *(.data.percpu) } __per_cpu_end = .; diff --git a/arch/i386/mach-voyager/voyager_smp.c b/arch/i386/mach-voyager/voyager_smp.c index 8165626a5c3..70e560a1b79 100644 --- a/arch/i386/mach-voyager/voyager_smp.c +++ b/arch/i386/mach-voyager/voyager_smp.c @@ -1700,7 +1700,7 @@ after_handle_vic_irq(unsigned int irq) printk("VOYAGER SMP: CPU%d lost interrupt %d\n", cpu, irq); - for_each_cpu(real_cpu, mask) { + for_each_possible_cpu(real_cpu, mask) { outb(VIC_CPU_MASQUERADE_ENABLE | real_cpu, VIC_PROCESSOR_ID); diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c index c4af9638dbf..fe6eb901326 100644 --- a/arch/i386/mm/discontig.c +++ b/arch/i386/mm/discontig.c @@ -31,6 +31,7 @@ #include <linux/nodemask.h> #include <linux/module.h> #include <linux/kexec.h> +#include <linux/pfn.h> #include <asm/e820.h> #include <asm/setup.h> @@ -352,17 +353,6 @@ void __init zone_sizes_init(void) { int nid; - /* - * Insert nodes into pgdat_list backward so they appear in order. - * Clobber node 0's links and NULL out pgdat_list before starting. - */ - pgdat_list = NULL; - for (nid = MAX_NUMNODES - 1; nid >= 0; nid--) { - if (!node_online(nid)) - continue; - NODE_DATA(nid)->pgdat_next = pgdat_list; - pgdat_list = NODE_DATA(nid); - } for_each_online_node(nid) { unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0}; diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c index 9db3242103b..2889567e21a 100644 --- a/arch/i386/mm/pgtable.c +++ b/arch/i386/mm/pgtable.c @@ -36,7 +36,7 @@ void show_mem(void) printk(KERN_INFO "Mem-info:\n"); show_free_areas(); printk(KERN_INFO "Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); - for_each_pgdat(pgdat) { + for_each_online_pgdat(pgdat) { pgdat_resize_lock(pgdat, &flags); for (i = 0; i < pgdat->node_spanned_pages; ++i) { page = pgdat_page_nr(pgdat, i); diff --git a/arch/i386/oprofile/nmi_int.c b/arch/i386/oprofile/nmi_int.c index 1accce50c2c..1a2076ce6f6 100644 --- a/arch/i386/oprofile/nmi_int.c +++ b/arch/i386/oprofile/nmi_int.c @@ -122,7 +122,7 @@ static void nmi_save_registers(void * dummy) static void free_msrs(void) { int i; - for_each_cpu(i) { + for_each_possible_cpu(i) { kfree(cpu_msrs[i].counters); cpu_msrs[i].counters = NULL; kfree(cpu_msrs[i].controls); |